From 84e478c6f1eb9c4bfa1fff2f8108e9a061b46428 Mon Sep 17 00:00:00 2001 From: Don Zickus Date: Fri, 5 Feb 2010 21:47:05 -0500 Subject: nmi_watchdog: Config option to enable new nmi_watchdog These are the bits that enable the new nmi_watchdog and safely isolate the old nmi_watchdog. Only one or the other can run, not both at the same time. Signed-off-by: Don Zickus Cc: Linus Torvalds Cc: Andrew Morton Cc: gorcunov@gmail.com Cc: aris@redhat.com Cc: peterz@infradead.org LKML-Reference: <1265424425-31562-4-git-send-email-dzickus@redhat.com> Signed-off-by: Ingo Molnar --- include/linux/nmi.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nmi.h b/include/linux/nmi.h index b752e807adde..a42ff0bef708 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -47,4 +47,8 @@ static inline bool trigger_all_cpu_backtrace(void) } #endif +#ifdef CONFIG_NMI_WATCHDOG +int hw_nmi_is_cpu_stuck(struct pt_regs *); +#endif + #endif -- cgit v1.2.3 From 504d7cf10ee42bb76b9556859f23d4121dee0a77 Mon Sep 17 00:00:00 2001 From: Don Zickus Date: Fri, 12 Feb 2010 17:19:19 -0500 Subject: nmi_watchdog: Compile and portability fixes The original patch was x86_64 centric. Changed the code to make it less so. ested by building and running on a powerpc. Signed-off-by: Don Zickus Cc: peterz@infradead.org Cc: gorcunov@gmail.com Cc: aris@redhat.com LKML-Reference: <1266013161-31197-2-git-send-email-dzickus@redhat.com> Signed-off-by: Ingo Molnar --- include/linux/nmi.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nmi.h b/include/linux/nmi.h index a42ff0bef708..794e7354c5bf 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -20,10 +20,14 @@ extern void touch_nmi_watchdog(void); extern void acpi_nmi_disable(void); extern void acpi_nmi_enable(void); #else +#ifndef CONFIG_NMI_WATCHDOG static inline void touch_nmi_watchdog(void) { touch_softlockup_watchdog(); } +#else +extern void touch_nmi_watchdog(void); +#endif static inline void acpi_nmi_disable(void) { } static inline void acpi_nmi_enable(void) { } #endif @@ -49,6 +53,11 @@ static inline bool trigger_all_cpu_backtrace(void) #ifdef CONFIG_NMI_WATCHDOG int hw_nmi_is_cpu_stuck(struct pt_regs *); +u64 hw_nmi_get_sample_period(void); +extern int nmi_watchdog_enabled; +struct ctl_table; +extern int proc_nmi_enabled(struct ctl_table *, int , + void __user *, size_t *, loff_t *); #endif #endif -- cgit v1.2.3 From 47195d57636604ff6048b0d7aa3e4ed9643f6073 Mon Sep 17 00:00:00 2001 From: Don Zickus Date: Mon, 22 Feb 2010 18:09:03 -0500 Subject: nmi_watchdog: Clean up various small details Mostly copy/paste whitespace damage with a couple of nitpicks by the checkpatch script. Fix the struct definition as requested by Ingo too. Signed-off-by: Don Zickus Cc: peterz@infradead.org Cc: gorcunov@gmail.com Cc: aris@redhat.com LKML-Reference: <1266880143-24943-1-git-send-email-dzickus@redhat.com> Signed-off-by: Ingo Molnar -- arch/x86/kernel/apic/hw_nmi.c | 14 +++++------ arch/x86/kernel/traps.c | 6 ++-- include/linux/nmi.h | 2 - kernel/nmi_watchdog.c | 51 ++++++++++++++++++++---------------------- 4 files changed, 36 insertions(+), 37 deletions(-) --- include/linux/nmi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 794e7354c5bf..22cc7960b649 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -57,7 +57,7 @@ u64 hw_nmi_get_sample_period(void); extern int nmi_watchdog_enabled; struct ctl_table; extern int proc_nmi_enabled(struct ctl_table *, int , - void __user *, size_t *, loff_t *); + void __user *, size_t *, loff_t *); #endif #endif -- cgit v1.2.3 From 927a7c9c1793def3a55d60c926d3945528e6bf1b Mon Sep 17 00:00:00 2001 From: Magnus Damm Date: Fri, 19 Mar 2010 04:47:19 +0000 Subject: dmaengine: shdma: Enable on SH-Mobile ARM Enable the shdma dmaengine driver on SH-Mobile ARM. Signed-off-by: Magnus Damm Signed-off-by: Paul Mundt --- include/linux/serial_sci.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/serial_sci.h b/include/linux/serial_sci.h index f5364a1de68b..837efa4e63c2 100644 --- a/include/linux/serial_sci.h +++ b/include/linux/serial_sci.h @@ -3,7 +3,7 @@ #include #ifdef CONFIG_SERIAL_SH_SCI_DMA -#include +#include #endif /* -- cgit v1.2.3 From 58687acba59266735adb8ccd9b5b9aa2c7cd205b Mon Sep 17 00:00:00 2001 From: Don Zickus Date: Fri, 7 May 2010 17:11:44 -0400 Subject: lockup_detector: Combine nmi_watchdog and softlockup detector The new nmi_watchdog (which uses the perf event subsystem) is very similar in structure to the softlockup detector. Using Ingo's suggestion, I combined the two functionalities into one file: kernel/watchdog.c. Now both the nmi_watchdog (or hardlockup detector) and softlockup detector sit on top of the perf event subsystem, which is run every 60 seconds or so to see if there are any lockups. To detect hardlockups, cpus not responding to interrupts, I implemented an hrtimer that runs 5 times for every perf event overflow event. If that stops counting on a cpu, then the cpu is most likely in trouble. To detect softlockups, tasks not yielding to the scheduler, I used the previous kthread idea that now gets kicked every time the hrtimer fires. If the kthread isn't being scheduled neither is anyone else and the warning is printed to the console. I tested this on x86_64 and both the softlockup and hardlockup paths work. V2: - cleaned up the Kconfig and softlockup combination - surrounded hardlockup cases with #ifdef CONFIG_PERF_EVENTS_NMI - seperated out the softlockup case from perf event subsystem - re-arranged the enabling/disabling nmi watchdog from proc space - added cpumasks for hardlockup failure cases - removed fallback to soft events if no PMU exists for hard events V3: - comment cleanups - drop support for older softlockup code - per_cpu cleanups - completely remove software clock base hardlockup detector - use per_cpu masking on hard/soft lockup detection - #ifdef cleanups - rename config option NMI_WATCHDOG to LOCKUP_DETECTOR - documentation additions V4: - documentation fixes - convert per_cpu to __get_cpu_var - powerpc compile fixes V5: - split apart warn flags for hard and soft lockups TODO: - figure out how to make an arch-agnostic clock2cycles call (if possible) to feed into perf events as a sample period [fweisbec: merged conflict patch] Signed-off-by: Don Zickus Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Cyrill Gorcunov Cc: Eric Paris Cc: Randy Dunlap LKML-Reference: <1273266711-18706-2-git-send-email-dzickus@redhat.com> Signed-off-by: Frederic Weisbecker --- include/linux/nmi.h | 8 ++++---- include/linux/sched.h | 6 ++++++ 2 files changed, 10 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 22cc7960b649..abd48aacaf79 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -20,7 +20,7 @@ extern void touch_nmi_watchdog(void); extern void acpi_nmi_disable(void); extern void acpi_nmi_enable(void); #else -#ifndef CONFIG_NMI_WATCHDOG +#ifndef CONFIG_LOCKUP_DETECTOR static inline void touch_nmi_watchdog(void) { touch_softlockup_watchdog(); @@ -51,12 +51,12 @@ static inline bool trigger_all_cpu_backtrace(void) } #endif -#ifdef CONFIG_NMI_WATCHDOG +#ifdef CONFIG_LOCKUP_DETECTOR int hw_nmi_is_cpu_stuck(struct pt_regs *); u64 hw_nmi_get_sample_period(void); -extern int nmi_watchdog_enabled; +extern int watchdog_enabled; struct ctl_table; -extern int proc_nmi_enabled(struct ctl_table *, int , +extern int proc_dowatchdog_enabled(struct ctl_table *, int , void __user *, size_t *, loff_t *); #endif diff --git a/include/linux/sched.h b/include/linux/sched.h index dad7f668ebf7..37efe8fa5306 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -346,6 +346,12 @@ extern int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, size_t *lenp, loff_t *ppos); #endif +#ifdef CONFIG_LOCKUP_DETECTOR +extern int proc_dowatchdog_thresh(struct ctl_table *table, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos); +#endif + /* Attach to any functions which should be ignored in wchan output. */ #define __sched __attribute__((__section__(".sched.text"))) -- cgit v1.2.3 From 332fbdbca3f7716c5620970755ae054d213bcc4e Mon Sep 17 00:00:00 2001 From: Don Zickus Date: Fri, 7 May 2010 17:11:45 -0400 Subject: lockup_detector: Touch_softlockup cleanups and softlockup_tick removal Just some code cleanup to make touch_softlockup clearer and remove the softlockup_tick function as it is no longer needed. Also remove the /proc softlockup_thres call as it has been changed to watchdog_thres. Signed-off-by: Don Zickus Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Cyrill Gorcunov Cc: Eric Paris Cc: Randy Dunlap LKML-Reference: <1273266711-18706-3-git-send-email-dzickus@redhat.com> Signed-off-by: Frederic Weisbecker --- include/linux/sched.h | 16 +++------------- 1 file changed, 3 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 37efe8fa5306..33f9b2ad0bbb 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -312,19 +312,15 @@ extern void scheduler_tick(void); extern void sched_show_task(struct task_struct *p); #ifdef CONFIG_DETECT_SOFTLOCKUP -extern void softlockup_tick(void); extern void touch_softlockup_watchdog(void); extern void touch_softlockup_watchdog_sync(void); extern void touch_all_softlockup_watchdogs(void); -extern int proc_dosoftlockup_thresh(struct ctl_table *table, int write, - void __user *buffer, - size_t *lenp, loff_t *ppos); +extern int proc_dowatchdog_thresh(struct ctl_table *table, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos); extern unsigned int softlockup_panic; extern int softlockup_thresh; #else -static inline void softlockup_tick(void) -{ -} static inline void touch_softlockup_watchdog(void) { } @@ -346,12 +342,6 @@ extern int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, size_t *lenp, loff_t *ppos); #endif -#ifdef CONFIG_LOCKUP_DETECTOR -extern int proc_dowatchdog_thresh(struct ctl_table *table, int write, - void __user *buffer, - size_t *lenp, loff_t *ppos); -#endif - /* Attach to any functions which should be ignored in wchan output. */ #define __sched __attribute__((__section__(".sched.text"))) -- cgit v1.2.3 From 19cc36c0f0457e5c6629ec24036fbbe8255c88ec Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 13 May 2010 02:30:49 +0200 Subject: lockup_detector: Fix forgotten config conversion Fix forgotten CONFIG_DETECT_SOFTLOCKUP -> CONFIG_LOCKUP_DETECTOR in sched.h Fixes: arch/x86/built-in.o: In function `touch_nmi_watchdog': (.text+0x1bd59): undefined reference to `touch_softlockup_watchdog' kernel/built-in.o: In function `show_state_filter': (.text+0x10d01): undefined reference to `touch_all_softlockup_watchdogs' kernel/built-in.o: In function `sched_clock_idle_wakeup_event': (.text+0x362f9): undefined reference to `touch_softlockup_watchdog' kernel/built-in.o: In function `timekeeping_resume': timekeeping.c:(.text+0x38757): undefined reference to `touch_softlockup_watchdog' kernel/built-in.o: In function `tick_nohz_handler': tick-sched.c:(.text+0x3e5b9): undefined reference to `touch_softlockup_watchdog' kernel/built-in.o: In function `tick_sched_timer': tick-sched.c:(.text+0x3e671): undefined reference to `touch_softlockup_watchdog' kernel/built-in.o: In function `tick_check_idle': (.text+0x3e90b): undefined reference to `touch_softlockup_watchdog' Signed-off-by: Frederic Weisbecker Cc: Don Zickus Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Cyrill Gorcunov Cc: Eric Paris Cc: Randy Dunlap --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 33f9b2ad0bbb..3958e0cd24f7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -311,7 +311,7 @@ extern void scheduler_tick(void); extern void sched_show_task(struct task_struct *p); -#ifdef CONFIG_DETECT_SOFTLOCKUP +#ifdef CONFIG_LOCKUP_DETECTOR extern void touch_softlockup_watchdog(void); extern void touch_softlockup_watchdog_sync(void); extern void touch_all_softlockup_watchdogs(void); -- cgit v1.2.3 From cafcd80d216bc2136b8edbb794327e495792c666 Mon Sep 17 00:00:00 2001 From: Don Zickus Date: Fri, 14 May 2010 11:11:21 -0400 Subject: lockup_detector: Cross arch compile fixes Combining the softlockup and hardlockup code causes watchdog.c to build even without the hardlockup detection support. So if an arch, that has the previous and the new nmi watchdog implementations cohabiting, wants to know if the generic one is in use, CONFIG_LOCKUP_DETECTOR is not a reliable check. We need to use CONFIG_HARDLOCKUP_DETECTOR instead. Fixes: kernel/built-in.o: In function `touch_nmi_watchdog': (.text+0x449bc): multiple definition of `touch_nmi_watchdog' arch/sparc/kernel/built-in.o:(.text+0x11b28): first defined here Signed-off-by: Don Zickus Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Don Zickus Cc: Cyrill Gorcunov LKML-Reference: <20100514151121.GR15159@redhat.com> [ use CONFIG_HARDLOCKUP_DETECTOR instead of CONFIG_PERF_EVENTS_NMI] Signed-off-by: Frederic Weisbecker --- include/linux/nmi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nmi.h b/include/linux/nmi.h index abd48aacaf79..06aab5eee134 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -20,7 +20,7 @@ extern void touch_nmi_watchdog(void); extern void acpi_nmi_disable(void); extern void acpi_nmi_enable(void); #else -#ifndef CONFIG_LOCKUP_DETECTOR +#ifndef CONFIG_HARDLOCKUP_DETECTOR static inline void touch_nmi_watchdog(void) { touch_softlockup_watchdog(); -- cgit v1.2.3 From 75b93489b449db4a34f0424c72f51821d985f52f Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Sun, 23 May 2010 16:39:02 +0000 Subject: serial: add a new port type, found on some sh-mobile SoCs Such ports are found, e.g., on SH7372. Signed-off-by: Guennadi Liakhovetski Signed-off-by: Paul Mundt --- include/linux/serial_core.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index f10db6e5f3b5..522832023a69 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -186,6 +186,9 @@ #define PORT_ALTERA_JTAGUART 91 #define PORT_ALTERA_UART 92 +/* SH-SCI */ +#define PORT_SCIFB 93 + #ifdef __KERNEL__ #include -- cgit v1.2.3 From 5360bd776f73d0a7da571d72a09a03f237e99900 Mon Sep 17 00:00:00 2001 From: Chris Metcalf Date: Fri, 28 May 2010 23:01:00 -0400 Subject: Fix up the "generic" unistd.h ABI to be more useful. Reserve 16 "architecture-specific" syscall numbers starting at 244. Allow use of the sys_sync_file_range2() API with the generic unistd.h by specifying __ARCH_WANT_SYNC_FILE_RANGE2 before including it. Allow using the generic unistd.h to create the "compat" syscall table by specifying __SYSCALL_COMPAT before including it. Use sys_fadvise64_64 for __NR3264_fadvise64 in both 32- and 64-bit mode. Request the appropriate __ARCH_WANT_COMPAT_SYS_xxx values when some deprecated syscall modes are selected. As part of this change to fix up the syscalls, also provide a couple of missing signal-related syscall prototypes in . Signed-off-by: Chris Metcalf Acked-by: Arnd Bergmann --- include/linux/syscalls.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index a1a86a53bc73..4a19d9bb8368 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -364,9 +364,13 @@ asmlinkage long sys_init_module(void __user *umod, unsigned long len, asmlinkage long sys_delete_module(const char __user *name_user, unsigned int flags); +asmlinkage long sys_rt_sigaction(int sig, const struct sigaction __user *act, + struct sigaction __user *oact, + size_t sigsetsize); asmlinkage long sys_rt_sigprocmask(int how, sigset_t __user *set, sigset_t __user *oset, size_t sigsetsize); asmlinkage long sys_rt_sigpending(sigset_t __user *set, size_t sigsetsize); +asmlinkage long sys_rt_sigsuspend(sigset_t __user *unewset, size_t sigsetsize); asmlinkage long sys_rt_sigtimedwait(const sigset_t __user *uthese, siginfo_t __user *uinfo, const struct timespec __user *uts, -- cgit v1.2.3 From 139ef32b0e6b88b00b5e3e74d052d938f178dc9b Mon Sep 17 00:00:00 2001 From: Chris Metcalf Date: Mon, 7 Jun 2010 08:48:13 -0400 Subject: Revert adding some arch-specific signal syscalls to . It turns out there is some variance on the calling conventions for these syscalls, and is already the mechanism used to handle this. Switch arch/tile over to using that mechanism and tweak the calling conventions for a couple of tile syscalls to match . Acked-by: Arnd Bergmann Signed-off-by: Chris Metcalf --- include/linux/syscalls.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 1e3cd5fec7ed..7f614ce274a9 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -364,13 +364,9 @@ asmlinkage long sys_init_module(void __user *umod, unsigned long len, asmlinkage long sys_delete_module(const char __user *name_user, unsigned int flags); -asmlinkage long sys_rt_sigaction(int sig, const struct sigaction __user *act, - struct sigaction __user *oact, - size_t sigsetsize); asmlinkage long sys_rt_sigprocmask(int how, sigset_t __user *set, sigset_t __user *oset, size_t sigsetsize); asmlinkage long sys_rt_sigpending(sigset_t __user *set, size_t sigsetsize); -asmlinkage long sys_rt_sigsuspend(sigset_t __user *unewset, size_t sigsetsize); asmlinkage long sys_rt_sigtimedwait(const sigset_t __user *uthese, siginfo_t __user *uinfo, const struct timespec __user *uts, -- cgit v1.2.3 From 50a323b73069b169385a8ac65633dee837a7d13f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 8 Jun 2010 21:40:36 +0200 Subject: sched: define and use CPU_PRI_* enums for cpu notifier priorities Instead of hardcoding priority 10 and 20 in sched and perf, collect them into CPU_PRI_* enums. Signed-off-by: Tejun Heo Acked-by: Peter Zijlstra Cc: Rusty Russell Cc: Paul Mackerras Cc: Ingo Molnar Cc: Arnaldo Carvalho de Melo --- include/linux/cpu.h | 9 +++++++++ include/linux/perf_event.h | 2 +- 2 files changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index e287863ac053..2d9073883ea9 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -48,6 +48,15 @@ extern ssize_t arch_cpu_release(const char *, size_t); #endif struct notifier_block; +/* + * CPU notifier priorities. + */ +enum { + /* migration should happen before other stuff but after perf */ + CPU_PRI_PERF = 20, + CPU_PRI_MIGRATION = 10, +}; + #ifdef CONFIG_SMP /* Need to know about CPUs going up/down? */ #if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE) diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 5d0266d94985..469e03e96fe7 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1068,7 +1068,7 @@ static inline void perf_event_disable(struct perf_event *event) { } #define perf_cpu_notifier(fn) \ do { \ static struct notifier_block fn##_nb __cpuinitdata = \ - { .notifier_call = fn, .priority = 20 }; \ + { .notifier_call = fn, .priority = CPU_PRI_PERF }; \ fn(&fn##_nb, (unsigned long)CPU_UP_PREPARE, \ (void *)(unsigned long)smp_processor_id()); \ fn(&fn##_nb, (unsigned long)CPU_STARTING, \ -- cgit v1.2.3 From 3a101d0548e925ab16ca6aaa8cf4f767d322ddb0 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 8 Jun 2010 21:40:36 +0200 Subject: sched: adjust when cpu_active and cpuset configurations are updated during cpu on/offlining Currently, when a cpu goes down, cpu_active is cleared before CPU_DOWN_PREPARE starts and cpuset configuration is updated from a default priority cpu notifier. When a cpu is coming up, it's set before CPU_ONLINE but cpuset configuration again is updated from the same cpu notifier. For cpu notifiers, this presents an inconsistent state. Threads which a CPU_DOWN_PREPARE notifier expects to be bound to the CPU can be migrated to other cpus because the cpu is no more inactive. Fix it by updating cpu_active in the highest priority cpu notifier and cpuset configuration in the second highest when a cpu is coming up. Down path is updated similarly. This guarantees that all other cpu notifiers see consistent cpu_active and cpuset configuration. cpuset_track_online_cpus() notifier is converted to cpuset_update_active_cpus() which just updates the configuration and now called from cpuset_cpu_[in]active() notifiers registered from sched_init_smp(). If cpuset is disabled, cpuset_update_active_cpus() degenerates into partition_sched_domains() making separate notifier for !CONFIG_CPUSETS unnecessary. This problem is triggered by cmwq. During CPU_DOWN_PREPARE, hotplug callback creates a kthread and kthread_bind()s it to the target cpu, and the thread is expected to run on that cpu. * Ingo's test discovered __cpuinit/exit markups were incorrect. Fixed. Signed-off-by: Tejun Heo Acked-by: Peter Zijlstra Cc: Rusty Russell Cc: Ingo Molnar Cc: Paul Menage --- include/linux/cpu.h | 16 ++++++++++++++++ include/linux/cpuset.h | 6 ++++++ 2 files changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 2d9073883ea9..de6b1722cdca 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -52,6 +52,22 @@ struct notifier_block; * CPU notifier priorities. */ enum { + /* + * SCHED_ACTIVE marks a cpu which is coming up active during + * CPU_ONLINE and CPU_DOWN_FAILED and must be the first + * notifier. CPUSET_ACTIVE adjusts cpuset according to + * cpu_active mask right after SCHED_ACTIVE. During + * CPU_DOWN_PREPARE, SCHED_INACTIVE and CPUSET_INACTIVE are + * ordered in the similar way. + * + * This ordering guarantees consistent cpu_active mask and + * migration behavior to all cpu notifiers. + */ + CPU_PRI_SCHED_ACTIVE = INT_MAX, + CPU_PRI_CPUSET_ACTIVE = INT_MAX - 1, + CPU_PRI_SCHED_INACTIVE = INT_MIN + 1, + CPU_PRI_CPUSET_INACTIVE = INT_MIN, + /* migration should happen before other stuff but after perf */ CPU_PRI_PERF = 20, CPU_PRI_MIGRATION = 10, diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 457ed765a116..f20eb8f16025 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -20,6 +20,7 @@ extern int number_of_cpusets; /* How many cpusets are defined in system? */ extern int cpuset_init(void); extern void cpuset_init_smp(void); +extern void cpuset_update_active_cpus(void); extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask); extern int cpuset_cpus_allowed_fallback(struct task_struct *p); extern nodemask_t cpuset_mems_allowed(struct task_struct *p); @@ -132,6 +133,11 @@ static inline void set_mems_allowed(nodemask_t nodemask) static inline int cpuset_init(void) { return 0; } static inline void cpuset_init_smp(void) {} +static inline void cpuset_update_active_cpus(void) +{ + partition_sched_domains(1, NULL, NULL); +} + static inline void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask) { -- cgit v1.2.3 From 21aa9af03d06cb1d19a3738e5cf12acff984e69b Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 8 Jun 2010 21:40:37 +0200 Subject: sched: add hooks for workqueue Concurrency managed workqueue needs to know when workers are going to sleep and waking up. Using these two hooks, cmwq keeps track of the current concurrency level and throttles execution of new works if it's too high and wakes up another worker from the sleep hook if it becomes too low. This patch introduces PF_WQ_WORKER to identify workqueue workers and adds the following two hooks. * wq_worker_waking_up(): called when a worker is woken up. * wq_worker_sleeping(): called when a worker is going to sleep and may return a pointer to a local task which should be woken up. The returned task is woken up using try_to_wake_up_local() which is simplified ttwu which is called under rq lock and can only wake up local tasks. Both hooks are currently defined as noop in kernel/workqueue_sched.h. Later cmwq implementation will replace them with proper implementation. These hooks are hard coded as they'll always be enabled. Signed-off-by: Tejun Heo Acked-by: Peter Zijlstra Cc: Mike Galbraith Cc: Ingo Molnar --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index f118809c953f..edc3dd168d87 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1696,6 +1696,7 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t * #define PF_EXITING 0x00000004 /* getting shut down */ #define PF_EXITPIDONE 0x00000008 /* pi exit done on shut down */ #define PF_VCPU 0x00000010 /* I'm a virtual CPU */ +#define PF_WQ_WORKER 0x00000020 /* I'm a workqueue worker */ #define PF_FORKNOEXEC 0x00000040 /* forked but didn't exec */ #define PF_MCE_PROCESS 0x00000080 /* process policy on mce errors */ #define PF_SUPERPRIV 0x00000100 /* used super-user privileges */ -- cgit v1.2.3 From b0f82b81fe6bbcf78d478071f33e44554726bc81 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 20 May 2010 07:47:21 +0200 Subject: perf: Drop the skip argument from perf_arch_fetch_regs_caller Drop this argument now that we always want to rewind only to the state of the first caller. It means frame pointers are not necessary anymore to reliably get the source of an event. But this also means we need this helper to be a macro now, as an inline function is not an option since we need to know when to provide a default implentation. Signed-off-by: Frederic Weisbecker Signed-off-by: Paul Mackerras Cc: David Miller Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo --- include/linux/perf_event.h | 32 +++++++------------------------- 1 file changed, 7 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index fb6c91eac7e3..bea785cef493 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -905,8 +905,10 @@ extern atomic_t perf_swevent_enabled[PERF_COUNT_SW_MAX]; extern void __perf_sw_event(u32, u64, int, struct pt_regs *, u64); -extern void -perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip); +#ifndef perf_arch_fetch_caller_regs +static inline void +perf_arch_fetch_caller_regs(struct regs *regs, unsigned long ip) { } +#endif /* * Take a snapshot of the regs. Skip ip and frame pointer to @@ -916,31 +918,11 @@ perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip); * - bp for callchains * - eflags, for future purposes, just in case */ -static inline void perf_fetch_caller_regs(struct pt_regs *regs, int skip) +static inline void perf_fetch_caller_regs(struct pt_regs *regs) { - unsigned long ip; - memset(regs, 0, sizeof(*regs)); - switch (skip) { - case 1 : - ip = CALLER_ADDR0; - break; - case 2 : - ip = CALLER_ADDR1; - break; - case 3 : - ip = CALLER_ADDR2; - break; - case 4: - ip = CALLER_ADDR3; - break; - /* No need to support further for now */ - default: - ip = 0; - } - - return perf_arch_fetch_caller_regs(regs, ip, skip); + perf_arch_fetch_caller_regs(regs, CALLER_ADDR0); } static inline void @@ -950,7 +932,7 @@ perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr) struct pt_regs hot_regs; if (!regs) { - perf_fetch_caller_regs(&hot_regs, 1); + perf_fetch_caller_regs(&hot_regs); regs = &hot_regs; } __perf_sw_event(event_id, nr, nmi, regs, addr); -- cgit v1.2.3 From c676329abb2b8359d9a5d734dec0c81779823fd6 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 25 May 2010 10:48:51 +0200 Subject: sched_clock: Add local_clock() API and improve documentation For people who otherwise get to write: cpu_clock(smp_processor_id()), there is now: local_clock(). Also, as per suggestion from Andrew, provide some documentation on the various clock interfaces, and minimize the unsigned long long vs u64 mess. Signed-off-by: Peter Zijlstra Cc: Andrew Morton Cc: Linus Torvalds Cc: Jens Axboe LKML-Reference: <1275052414.1645.52.camel@laptop> Signed-off-by: Ingo Molnar --- include/linux/sched.h | 37 +++++++++++++++++++++---------------- 1 file changed, 21 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index edc3dd168d87..c2d4316a04bb 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1791,20 +1791,23 @@ static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask) #endif /* - * Architectures can set this to 1 if they have specified - * CONFIG_HAVE_UNSTABLE_SCHED_CLOCK in their arch Kconfig, - * but then during bootup it turns out that sched_clock() - * is reliable after all: + * Do not use outside of architecture code which knows its limitations. + * + * sched_clock() has no promise of monotonicity or bounded drift between + * CPUs, use (which you should not) requires disabling IRQs. + * + * Please use one of the three interfaces below. */ -#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK -extern int sched_clock_stable; -#endif - -/* ftrace calls sched_clock() directly */ extern unsigned long long notrace sched_clock(void); +/* + * See the comment in kernel/sched_clock.c + */ +extern u64 cpu_clock(int cpu); +extern u64 local_clock(void); +extern u64 sched_clock_cpu(int cpu); + extern void sched_clock_init(void); -extern u64 sched_clock_cpu(int cpu); #ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK static inline void sched_clock_tick(void) @@ -1819,17 +1822,19 @@ static inline void sched_clock_idle_wakeup_event(u64 delta_ns) { } #else +/* + * Architectures can set this to 1 if they have specified + * CONFIG_HAVE_UNSTABLE_SCHED_CLOCK in their arch Kconfig, + * but then during bootup it turns out that sched_clock() + * is reliable after all: + */ +extern int sched_clock_stable; + extern void sched_clock_tick(void); extern void sched_clock_idle_sleep_event(void); extern void sched_clock_idle_wakeup_event(u64 delta_ns); #endif -/* - * For kernel-internal use: high-speed (but slightly incorrect) per-cpu - * clock constructed from sched_clock(): - */ -extern unsigned long long cpu_clock(int cpu); - extern unsigned long long task_sched_runtime(struct task_struct *task); extern unsigned long long thread_group_sched_runtime(struct task_struct *task); -- cgit v1.2.3 From 83cd4fe27ad8446619b2e030b171b858501de87d Mon Sep 17 00:00:00 2001 From: Venkatesh Pallipadi Date: Fri, 21 May 2010 17:09:41 -0700 Subject: sched: Change nohz idle load balancing logic to push model In the new push model, all idle CPUs indeed go into nohz mode. There is still the concept of idle load balancer (performing the load balancing on behalf of all the idle cpu's in the system). Busy CPU kicks the nohz balancer when any of the nohz CPUs need idle load balancing. The kickee CPU does the idle load balancing on behalf of all idle CPUs instead of the normal idle balance. This addresses the below two problems with the current nohz ilb logic: * the idle load balancer continued to have periodic ticks during idle and wokeup frequently, even though it did not have any rebalancing to do on behalf of any of the idle CPUs. * On x86 and CPUs that have APIC timer stoppage on idle CPUs, this periodic wakeup can result in a periodic additional interrupt on a CPU doing the timer broadcast. Also currently we are migrating the unpinned timers from an idle to the cpu doing idle load balancing (when all the cpus in the system are idle, there is no idle load balancing cpu and timers get added to the same idle cpu where the request was made. So the existing optimization works only on semi idle system). And In semi idle system, we no longer have periodic ticks on the idle load balancer CPU. Using that cpu will add more delays to the timers than intended (as that cpu's timer base may not be uptodate wrt jiffies etc). This was causing mysterious slowdowns during boot etc. For now, in the semi idle case, use the nearest busy cpu for migrating timers from an idle cpu. This is good for power-savings anyway. Signed-off-by: Venkatesh Pallipadi Signed-off-by: Suresh Siddha Signed-off-by: Peter Zijlstra Cc: Thomas Gleixner LKML-Reference: <1274486981.2840.46.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar --- include/linux/sched.h | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index c2d4316a04bb..a3e5b1cd0438 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -271,14 +271,11 @@ extern int runqueue_is_locked(int cpu); extern cpumask_var_t nohz_cpu_mask; #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ) -extern int select_nohz_load_balancer(int cpu); -extern int get_nohz_load_balancer(void); +extern void select_nohz_load_balancer(int stop_tick); +extern int get_nohz_timer_target(void); extern int nohz_ratelimit(int cpu); #else -static inline int select_nohz_load_balancer(int cpu) -{ - return 0; -} +static inline void select_nohz_load_balancer(int stop_tick) { } static inline int nohz_ratelimit(int cpu) { -- cgit v1.2.3 From 9d5efe05eb0c904545a28b19c18b949f23334de0 Mon Sep 17 00:00:00 2001 From: Srivatsa Vaddagiri Date: Tue, 8 Jun 2010 14:57:02 +1000 Subject: sched: Fix capacity calculations for SMT4 Handle cpu capacity being reported as 0 on cores with more number of hardware threads. For example on a Power7 core with 4 hardware threads, core power is 1177 and thus power of each hardware thread is 1177/4 = 294. This low power can lead to capacity for each hardware thread being calculated as 0, which leads to tasks bouncing within the core madly! Fix this by reporting capacity for hardware threads as 1, provided their power is not scaled down significantly because of frequency scaling or real-time tasks usage of cpu. Signed-off-by: Srivatsa Vaddagiri Signed-off-by: Michael Neuling Signed-off-by: Peter Zijlstra Cc: Arjan van de Ven LKML-Reference: <20100608045702.21D03CC895@localhost.localdomain> Signed-off-by: Ingo Molnar --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index a3e5b1cd0438..c731296e5e93 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -857,7 +857,7 @@ struct sched_group { * CPU power of this group, SCHED_LOAD_SCALE being max power for a * single CPU. */ - unsigned int cpu_power; + unsigned int cpu_power, cpu_power_orig; /* * The CPUs this group covers. -- cgit v1.2.3 From 532cb4c401e225b084c14d6bd6a2f8ee561de2f1 Mon Sep 17 00:00:00 2001 From: Michael Neuling Date: Tue, 8 Jun 2010 14:57:02 +1000 Subject: sched: Add asymmetric group packing option for sibling domain Check to see if the group is packed in a sched doman. This is primarily intended to used at the sibling level. Some cores like POWER7 prefer to use lower numbered SMT threads. In the case of POWER7, it can move to lower SMT modes only when higher threads are idle. When in lower SMT modes, the threads will perform better since they share less core resources. Hence when we have idle threads, we want them to be the higher ones. This adds a hook into f_b_g() called check_asym_packing() to check the packing. This packing function is run on idle threads. It checks to see if the busiest CPU in this domain (core in the P7 case) has a higher CPU number than what where the packing function is being run on. If it is, calculate the imbalance and return the higher busier thread as the busiest group to f_b_g(). Here we are assuming a lower CPU number will be equivalent to a lower SMT thread number. It also creates a new SD_ASYM_PACKING flag to enable this feature at any scheduler domain level. It also creates an arch hook to enable this feature at the sibling level. The default function doesn't enable this feature. Based heavily on patch from Peter Zijlstra. Fixes from Srivatsa Vaddagiri. Signed-off-by: Michael Neuling Signed-off-by: Srivatsa Vaddagiri Signed-off-by: Peter Zijlstra Cc: Arjan van de Ven Cc: "H. Peter Anvin" Cc: Thomas Gleixner LKML-Reference: <20100608045702.2936CCC897@localhost.localdomain> Signed-off-by: Ingo Molnar --- include/linux/sched.h | 4 +++- include/linux/topology.h | 1 + 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index c731296e5e93..ff154e10752b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -801,7 +801,7 @@ enum cpu_idle_type { #define SD_POWERSAVINGS_BALANCE 0x0100 /* Balance for power savings */ #define SD_SHARE_PKG_RESOURCES 0x0200 /* Domain members share cpu pkg resources */ #define SD_SERIALIZE 0x0400 /* Only a single load balancing instance */ - +#define SD_ASYM_PACKING 0x0800 /* Place busy groups earlier in the domain */ #define SD_PREFER_SIBLING 0x1000 /* Prefer to place tasks in a sibling domain */ enum powersavings_balance_level { @@ -836,6 +836,8 @@ static inline int sd_balance_for_package_power(void) return SD_PREFER_SIBLING; } +extern int __weak arch_sd_sibiling_asym_packing(void); + /* * Optimise SD flags for power savings: * SD_BALANCE_NEWIDLE helps agressive task consolidation and power savings. diff --git a/include/linux/topology.h b/include/linux/topology.h index c44df50a05ab..cf57f30d0dcb 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -103,6 +103,7 @@ int arch_update_cpu_topology(void); | 1*SD_SHARE_PKG_RESOURCES \ | 0*SD_SERIALIZE \ | 0*SD_PREFER_SIBLING \ + | arch_sd_sibiling_asym_packing() \ , \ .last_balance = jiffies, \ .balance_interval = 1, \ -- cgit v1.2.3 From ecc55f84b2e9741f29daa787ded93986df6cbe17 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 21 May 2010 15:11:34 +0200 Subject: perf, trace: Inline perf_swevent_put_recursion_context() Inline perf_swevent_put_recursion_context into perf_tp_event(), this shrinks the per trace template code footprint and saves a function call. Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- include/linux/ftrace_event.h | 3 +-- include/linux/perf_event.h | 2 +- 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 3167f2df4126..0af31cd335d6 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -257,8 +257,7 @@ static inline void perf_trace_buf_submit(void *raw_data, int size, int rctx, u64 addr, u64 count, struct pt_regs *regs, void *head) { - perf_tp_event(addr, count, raw_data, size, regs, head); - perf_swevent_put_recursion_context(rctx); + perf_tp_event(addr, count, raw_data, size, regs, head, rctx); } #endif diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 5d0266d94985..c691a0b27bcd 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1001,7 +1001,7 @@ static inline bool perf_paranoid_kernel(void) extern void perf_event_init(void); extern void perf_tp_event(u64 addr, u64 count, void *record, int entry_size, struct pt_regs *regs, - struct hlist_head *head); + struct hlist_head *head, int rctx); extern void perf_bp_event(struct perf_event *event, void *data); #ifndef perf_misc_flags -- cgit v1.2.3 From 3af9e859281bda7eb7c20b51879cf43aa788ac2e Mon Sep 17 00:00:00 2001 From: Eric B Munson Date: Tue, 18 May 2010 15:30:49 +0100 Subject: perf: Add non-exec mmap() tracking Add the capacility to track data mmap()s. This can be used together with PERF_SAMPLE_ADDR for data profiling. Signed-off-by: Anton Blanchard [Updated code for stable perf ABI] Signed-off-by: Eric B Munson Signed-off-by: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: Paul Mackerras Cc: Mike Galbraith Cc: Steven Rostedt LKML-Reference: <1274193049-25997-1-git-send-email-ebmunson@us.ibm.com> Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index c691a0b27bcd..36efad90cd43 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -214,8 +214,9 @@ struct perf_event_attr { * See also PERF_RECORD_MISC_EXACT_IP */ precise_ip : 2, /* skid constraint */ + mmap_data : 1, /* non-exec mmap data */ - __reserved_1 : 47; + __reserved_1 : 46; union { __u32 wakeup_events; /* wakeup every n events */ @@ -962,14 +963,7 @@ perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr) } } -extern void __perf_event_mmap(struct vm_area_struct *vma); - -static inline void perf_event_mmap(struct vm_area_struct *vma) -{ - if (vma->vm_flags & VM_EXEC) - __perf_event_mmap(vma); -} - +extern void perf_event_mmap(struct vm_area_struct *vma); extern struct perf_guest_info_callbacks *perf_guest_cbs; extern int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks); extern int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks); -- cgit v1.2.3 From 8d2cacbbb8deadfae78aa16e4e1ee619bdd7019e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 25 May 2010 17:49:05 +0200 Subject: perf: Cleanup {start,commit,cancel}_txn details Clarify some of the transactional group scheduling API details and change it so that a successfull ->commit_txn also closes the transaction. Signed-off-by: Peter Zijlstra Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: Paul Mackerras Cc: Mike Galbraith Cc: Steven Rostedt LKML-Reference: <1274803086.5882.1752.camel@twins> Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 27 ++++++++++++++++++++++----- 1 file changed, 22 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 36efad90cd43..f1b6ba0770e0 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -549,7 +549,10 @@ struct hw_perf_event { struct perf_event; -#define PERF_EVENT_TXN_STARTED 1 +/* + * Common implementation detail of pmu::{start,commit,cancel}_txn + */ +#define PERF_EVENT_TXN 0x1 /** * struct pmu - generic performance monitoring unit @@ -563,14 +566,28 @@ struct pmu { void (*unthrottle) (struct perf_event *event); /* - * group events scheduling is treated as a transaction, - * add group events as a whole and perform one schedulability test. - * If test fails, roll back the whole group + * Group events scheduling is treated as a transaction, add group + * events as a whole and perform one schedulability test. If the test + * fails, roll back the whole group */ + /* + * Start the transaction, after this ->enable() doesn't need + * to do schedulability tests. + */ void (*start_txn) (const struct pmu *pmu); - void (*cancel_txn) (const struct pmu *pmu); + /* + * If ->start_txn() disabled the ->enable() schedulability test + * then ->commit_txn() is required to perform one. On success + * the transaction is closed. On error the transaction is kept + * open until ->cancel_txn() is called. + */ int (*commit_txn) (const struct pmu *pmu); + /* + * Will cancel the transaction, assumes ->disable() is called for + * each successfull ->enable() during the transaction. + */ + void (*cancel_txn) (const struct pmu *pmu); }; /** -- cgit v1.2.3 From ca5135e6b4a3cbc7e187737520fbc4b508f6f7a2 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 28 May 2010 19:33:23 +0200 Subject: perf: Rename perf_mmap_data to perf_buffer Rename to clarify code. s/perf_mmap_data/perf_buffer/g and selective s/data/buffer/g Signed-off-by: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: Paul Mackerras Cc: Mike Galbraith Cc: Steven Rostedt LKML-Reference: Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index f1b6ba0770e0..2a0da021c23f 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -602,7 +602,7 @@ enum perf_event_active_state { struct file; -struct perf_mmap_data { +struct perf_buffer { atomic_t refcount; struct rcu_head rcu_head; #ifdef CONFIG_PERF_USE_VMALLOC @@ -727,7 +727,7 @@ struct perf_event { atomic_t mmap_count; int mmap_locked; struct user_struct *mmap_user; - struct perf_mmap_data *data; + struct perf_buffer *buffer; /* poll related */ wait_queue_head_t waitq; @@ -825,7 +825,7 @@ struct perf_cpu_context { struct perf_output_handle { struct perf_event *event; - struct perf_mmap_data *data; + struct perf_buffer *buffer; unsigned long wakeup; unsigned long size; void *addr; -- cgit v1.2.3 From d57e34fdd60be7ffd0b1d86bfa1a553df86b7172 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 28 May 2010 19:41:35 +0200 Subject: perf: Simplify the ring-buffer logic: make perf_buffer_alloc() do everything needed Currently there are perf_buffer_alloc() + perf_buffer_init() + some separate bits, fold it all into a single perf_buffer_alloc() and only leave the attachment to the event separate. Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 2a0da021c23f..441992a9775c 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -602,6 +602,8 @@ enum perf_event_active_state { struct file; +#define PERF_BUFFER_WRITABLE 0x01 + struct perf_buffer { atomic_t refcount; struct rcu_head rcu_head; -- cgit v1.2.3 From a6e6dea68c18f705957573ee5596097c7e82d0e5 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 21 May 2010 14:27:58 +0200 Subject: perf: Add perf_event::child_count Only child counters adding back their values into the parent counter are responsible for cross-cpu updates to event->count. So if we pull that out into a new child_count variable, we get an event->count that is only modified locally. Signed-off-by: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: Paul Mackerras Cc: Mike Galbraith Cc: Steven Rostedt LKML-Reference: Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 441992a9775c..f34dab9b275e 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -671,6 +671,7 @@ struct perf_event { enum perf_event_active_state state; unsigned int attach_state; atomic64_t count; + atomic64_t child_count; /* * These are the total time in nanoseconds that the event -- cgit v1.2.3 From e78505958cf123048fb48cb56b79cebb8edd15fb Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 21 May 2010 14:43:08 +0200 Subject: perf: Convert perf_event to local_t Since now all modification to event->count (and ->prev_count and ->period_left) are local to a cpu, change then to local64_t so we avoid the LOCK'ed ops. Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index f34dab9b275e..7342979f95f2 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -487,6 +487,7 @@ struct perf_guest_info_callbacks { #include #include #include +#include #define PERF_MAX_STACK_DEPTH 255 @@ -536,10 +537,10 @@ struct hw_perf_event { struct arch_hw_breakpoint info; #endif }; - atomic64_t prev_count; + local64_t prev_count; u64 sample_period; u64 last_period; - atomic64_t period_left; + local64_t period_left; u64 interrupts; u64 freq_time_stamp; @@ -670,7 +671,7 @@ struct perf_event { enum perf_event_active_state state; unsigned int attach_state; - atomic64_t count; + local64_t count; atomic64_t child_count; /* -- cgit v1.2.3 From 7be7923633a142402266d642ccebf74f556a649b Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 9 Jun 2010 11:57:23 +0200 Subject: perf: Fix build breakage for architecutes without atomic64_t The local64.h include dependency was not dependent on PERF_EVENT=y, which meant that arch's without atomic64_t support ended up including it and failed to build. Signed-off-by: Peter Zijlstra LKML-Reference: --- include/linux/perf_event.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 7342979f95f2..1218d05728b9 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -462,6 +462,7 @@ enum perf_callchain_context { #ifdef CONFIG_PERF_EVENTS # include +# include #endif struct perf_guest_info_callbacks { @@ -487,7 +488,6 @@ struct perf_guest_info_callbacks { #include #include #include -#include #define PERF_MAX_STACK_DEPTH 255 -- cgit v1.2.3 From 039ca4e74a1cf60bd7487324a564ecf5c981f254 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 26 May 2010 17:22:17 +0800 Subject: tracing: Remove kmemtrace ftrace plugin We have been resisting new ftrace plugins and removing existing ones, and kmemtrace has been superseded by kmem trace events and perf-kmem, so we remove it. Signed-off-by: Li Zefan Acked-by: Pekka Enberg Acked-by: Eduard - Gabriel Munteanu Cc: Ingo Molnar Cc: Steven Rostedt [ remove kmemtrace from the makefile, handle slob too ] Signed-off-by: Frederic Weisbecker --- include/linux/kmemtrace.h | 25 ------------------------- include/linux/slab_def.h | 3 ++- include/linux/slub_def.h | 3 ++- 3 files changed, 4 insertions(+), 27 deletions(-) delete mode 100644 include/linux/kmemtrace.h (limited to 'include/linux') diff --git a/include/linux/kmemtrace.h b/include/linux/kmemtrace.h deleted file mode 100644 index b616d3930c3b..000000000000 --- a/include/linux/kmemtrace.h +++ /dev/null @@ -1,25 +0,0 @@ -/* - * Copyright (C) 2008 Eduard - Gabriel Munteanu - * - * This file is released under GPL version 2. - */ - -#ifndef _LINUX_KMEMTRACE_H -#define _LINUX_KMEMTRACE_H - -#ifdef __KERNEL__ - -#include - -#ifdef CONFIG_KMEMTRACE -extern void kmemtrace_init(void); -#else -static inline void kmemtrace_init(void) -{ -} -#endif - -#endif /* __KERNEL__ */ - -#endif /* _LINUX_KMEMTRACE_H */ - diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index 1812dac8c496..1acfa73ce2ac 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -14,7 +14,8 @@ #include /* kmalloc_sizes.h needs PAGE_SIZE */ #include /* kmalloc_sizes.h needs L1_CACHE_BYTES */ #include -#include + +#include #ifndef ARCH_KMALLOC_MINALIGN /* diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 55695c8d2f8a..2345d3a033e6 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -10,9 +10,10 @@ #include #include #include -#include #include +#include + enum stat_item { ALLOC_FASTPATH, /* Allocation from cpu slab */ ALLOC_SLOWPATH, /* Allocation by getting a new cpu slab */ -- cgit v1.2.3 From 8e4b50f94e8c1435a3e0ece42b7f97bc857d0145 Mon Sep 17 00:00:00 2001 From: Clemens Ladisch Date: Thu, 10 Jun 2010 08:26:28 +0200 Subject: firewire: core: add CSR SPLIT_TIMEOUT support Implement the SPLIT_TIMEOUT registers. Besides being required by the spec, this is desirable for some IIDC devices and necessary for many audio devices to be able to increase the timeout from userspace. Signed-off-by: Clemens Ladisch --- include/linux/firewire.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/firewire.h b/include/linux/firewire.h index 72e2b8ac2a5a..cdf8213c68ca 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -89,6 +89,11 @@ struct fw_card { struct list_head transaction_list; unsigned long reset_jiffies; + u32 split_timeout_hi; + u32 split_timeout_lo; + unsigned int split_timeout_cycles; + unsigned int split_timeout_jiffies; + unsigned long long guid; unsigned max_receive; int link_speed; -- cgit v1.2.3 From a1a1132bd83d0aea51d4f19be4b4a58a064a0131 Mon Sep 17 00:00:00 2001 From: Clemens Ladisch Date: Thu, 10 Jun 2010 08:35:06 +0200 Subject: firewire: add CSR PRIORITY_BUDGET support If supported by the OHCI controller, implement the PRIORITY_BUDGET register, which is required for nodes that can use asynchronous priority arbitration. To allow the core to determine what features the lowlevel device supports, add a new card driver callback. Signed-off-by: Clemens Ladisch --- include/linux/firewire.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/firewire.h b/include/linux/firewire.h index cdf8213c68ca..a50377d91254 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -32,6 +32,7 @@ #define CSR_CYCLE_TIME 0x200 #define CSR_BUS_TIME 0x204 #define CSR_BUSY_TIMEOUT 0x210 +#define CSR_PRIORITY_BUDGET 0x218 #define CSR_BUS_MANAGER_ID 0x21c #define CSR_BANDWIDTH_AVAILABLE 0x220 #define CSR_CHANNELS_AVAILABLE 0x224 -- cgit v1.2.3 From 3d1f46eb60b155c705e389ecdf313f11b4b91976 Mon Sep 17 00:00:00 2001 From: Clemens Ladisch Date: Thu, 10 Jun 2010 08:35:37 +0200 Subject: firewire: core: add CSR MAINT_UTILITY support Implement the MAIN_UTILITY register, which is utterly optional but useful as a safe target for diagnostic read/write/broadcast transactions. Signed-off-by: Clemens Ladisch --- include/linux/firewire.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/firewire.h b/include/linux/firewire.h index a50377d91254..f1160e831dad 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -38,6 +38,7 @@ #define CSR_CHANNELS_AVAILABLE 0x224 #define CSR_CHANNELS_AVAILABLE_HI 0x224 #define CSR_CHANNELS_AVAILABLE_LO 0x228 +#define CSR_MAINT_UTILITY 0x230 #define CSR_BROADCAST_CHANNEL 0x234 #define CSR_CONFIG_ROM 0x400 #define CSR_CONFIG_ROM_END 0x800 @@ -122,6 +123,8 @@ struct fw_card { bool broadcast_channel_allocated; u32 broadcast_channel; __be32 topology_map[(CSR_TOPOLOGY_MAP_END - CSR_TOPOLOGY_MAP) / 4]; + + __be32 maint_utility_register; }; struct fw_attribute_group { -- cgit v1.2.3 From 7e0e314f198d5048b74c8f0ef9f4c1c02e5ecfc9 Mon Sep 17 00:00:00 2001 From: Clemens Ladisch Date: Thu, 10 Jun 2010 08:37:15 +0200 Subject: firewire: core: add CSR abdicate support Implement the abdicate bit, which is required for bus manager capable nodes and tested by the Base 1394 Test Suite. Finally, something to do at a command reset! :-) Signed-off-by: Clemens Ladisch --- include/linux/firewire.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/firewire.h b/include/linux/firewire.h index f1160e831dad..4d22643215ef 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -119,6 +119,8 @@ struct fw_card { int bm_retries; int bm_generation; __be32 bm_transaction_data[2]; + bool bm_abdicate; /* value of csr_abdicate before last bus reset */ + bool csr_abdicate; /* visible in CSR STATE_CLEAR/SET registers */ bool broadcast_channel_allocated; u32 broadcast_channel; -- cgit v1.2.3 From c6de9f08912311ddc1b3502b90e10fd449acd401 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Mon, 31 May 2010 16:48:09 +0800 Subject: x86, mce: Add HW_ERR printk prefix for hardware error logging This makes hardware error related log in printk log more explicit. So that the users can report it to hardware vendor instead of LKML or software vendor. Signed-off-by: Huang Ying Reviewed-by: Hidetoshi Seto LKML-Reference: <1275295689.3444.462.camel@yhuang-dev.sh.intel.com> Signed-off-by: H. Peter Anvin --- include/linux/kernel.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 8317ec4b9f3b..3bf740bb069e 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -247,6 +247,13 @@ extern struct pid *session_of_pgrp(struct pid *pgrp); #define FW_WARN "[Firmware Warn]: " #define FW_INFO "[Firmware Info]: " +/* + * HW_ERR + * Add this to a message for hardware errors, so that user can report + * it to hardware vendor instead of LKML or software vendor. + */ +#define HW_ERR "[Hardware Error]: " + #ifdef CONFIG_PRINTK asmlinkage int vprintk(const char *fmt, va_list args) __attribute__ ((format (printf, 1, 0))); -- cgit v1.2.3 From 551d55a944b143ef26fbd482d1c463199d6f65cf Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Sat, 17 Apr 2010 08:48:42 -0400 Subject: tree/tiny rcu: Add debug RCU head objects Helps finding racy users of call_rcu(), which results in hangs because list entries are overwritten and/or skipped. Changelog since v4: - Bissectability is now OK - Now generate a WARN_ON_ONCE() for non-initialized rcu_head passed to call_rcu(). Statically initialized objects are detected with object_is_static(). - Rename rcu_head_init_on_stack to init_rcu_head_on_stack. - Remove init_rcu_head() completely. Changelog since v3: - Include comments from Lai Jiangshan This new patch version is based on the debugobjects with the newly introduced "active state" tracker. Non-initialized entries are all considered as "statically initialized". An activation fixup (triggered by call_rcu()) takes care of performing the debug object initialization without issuing any warning. Since we cannot increase the size of struct rcu_head, I don't see much room to put an identifier for statically initialized rcu_head structures. So for now, we have to live without "activation without explicit init" detection. But the main purpose of this debug option is to detect double-activations (double call_rcu() use of a rcu_head before the callback is executed), which is correctly addressed here. This also detects potential internal RCU callback corruption, which would cause the callbacks to be executed twice. Signed-off-by: Mathieu Desnoyers CC: David S. Miller CC: "Paul E. McKenney" CC: akpm@linux-foundation.org CC: mingo@elte.hu CC: laijs@cn.fujitsu.com CC: dipankar@in.ibm.com CC: josh@joshtriplett.org CC: dvhltc@us.ibm.com CC: niv@us.ibm.com CC: tglx@linutronix.de CC: peterz@infradead.org CC: rostedt@goodmis.org CC: Valdis.Kletnieks@vt.edu CC: dhowells@redhat.com CC: eric.dumazet@gmail.com CC: Alexey Dobriyan Signed-off-by: Paul E. McKenney Reviewed-by: Lai Jiangshan --- include/linux/rcupdate.h | 49 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 49 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index b653b4aaa8a6..2b7fc506e479 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -40,6 +40,7 @@ #include #include #include +#include #ifdef CONFIG_RCU_TORTURE_TEST extern int rcutorture_runnable; /* for sysctl */ @@ -79,6 +80,16 @@ extern void rcu_init(void); (ptr)->next = NULL; (ptr)->func = NULL; \ } while (0) +/* + * init_rcu_head_on_stack()/destroy_rcu_head_on_stack() are needed for dynamic + * initialization and destruction of rcu_head on the stack. rcu_head structures + * allocated dynamically in the heap or defined statically don't need any + * initialization. + */ +#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD +extern void init_rcu_head_on_stack(struct rcu_head *head); +extern void destroy_rcu_head_on_stack(struct rcu_head *head); +#else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ static inline void init_rcu_head_on_stack(struct rcu_head *head) { } @@ -86,6 +97,7 @@ static inline void init_rcu_head_on_stack(struct rcu_head *head) static inline void destroy_rcu_head_on_stack(struct rcu_head *head) { } +#endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ #ifdef CONFIG_DEBUG_LOCK_ALLOC @@ -517,4 +529,41 @@ extern void call_rcu(struct rcu_head *head, extern void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *head)); +/* + * debug_rcu_head_queue()/debug_rcu_head_unqueue() are used internally + * by call_rcu() and rcu callback execution, and are therefore not part of the + * RCU API. Leaving in rcupdate.h because they are used by all RCU flavors. + */ + +#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD +# define STATE_RCU_HEAD_READY 0 +# define STATE_RCU_HEAD_QUEUED 1 + +extern struct debug_obj_descr rcuhead_debug_descr; + +static inline void debug_rcu_head_queue(struct rcu_head *head) +{ + debug_object_activate(head, &rcuhead_debug_descr); + debug_object_active_state(head, &rcuhead_debug_descr, + STATE_RCU_HEAD_READY, + STATE_RCU_HEAD_QUEUED); +} + +static inline void debug_rcu_head_unqueue(struct rcu_head *head) +{ + debug_object_active_state(head, &rcuhead_debug_descr, + STATE_RCU_HEAD_QUEUED, + STATE_RCU_HEAD_READY); + debug_object_deactivate(head, &rcuhead_debug_descr); +} +#else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ +static inline void debug_rcu_head_queue(struct rcu_head *head) +{ +} + +static inline void debug_rcu_head_unqueue(struct rcu_head *head) +{ +} +#endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ + #endif /* __LINUX_RCUPDATE_H */ -- cgit v1.2.3 From f5155b33277c9678041a27869165619bb34f722f Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 30 Apr 2010 06:42:01 -0700 Subject: rcu: add an rcu_dereference_index_check() The sparse RCU-pointer checking relies on type magic that dereferences the pointer in question. This does not work if the pointer is in fact an array index. This commit therefore supplies a new RCU API that omits the sparse checking to continue to support rcu_dereference() on integers. Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 2b7fc506e479..9fbc54a2585d 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -566,4 +566,37 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head) } #endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ +#ifndef CONFIG_PROVE_RCU +#define __do_rcu_dereference_check(c) do { } while (0) +#endif /* #ifdef CONFIG_PROVE_RCU */ + +#define __rcu_dereference_index_check(p, c) \ + ({ \ + typeof(p) _________p1 = ACCESS_ONCE(p); \ + __do_rcu_dereference_check(c); \ + smp_read_barrier_depends(); \ + (_________p1); \ + }) + +/** + * rcu_dereference_index_check() - rcu_dereference for indices with debug checking + * @p: The pointer to read, prior to dereferencing + * @c: The conditions under which the dereference will take place + * + * Similar to rcu_dereference_check(), but omits the sparse checking. + * This allows rcu_dereference_index_check() to be used on integers, + * which can then be used as array indices. Attempting to use + * rcu_dereference_check() on an integer will give compiler warnings + * because the sparse address-space mechanism relies on dereferencing + * the RCU-protected pointer. Dereferencing integers is not something + * that even gcc will put up with. + * + * Note that this function does not implicitly check for RCU read-side + * critical sections. If this function gains lots of uses, it might + * make sense to provide versions for each flavor of RCU, but it does + * not make sense as of early 2010. + */ +#define rcu_dereference_index_check(p, c) \ + __rcu_dereference_index_check((p), (c)) + #endif /* __LINUX_RCUPDATE_H */ -- cgit v1.2.3 From 71d1d5c722db9ae3b3f9c08ef7ddcd7759fbb1e0 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 11 May 2010 16:13:14 -0700 Subject: rcu: add __rcu API for later sparse checking This commit defines an __rcu API, but provides only vacuous definitions for it. This breaks dependencies among most of the subsequent patches, allowing them to reach mainline asynchronously via whatever trees are appropriate. Signed-off-by: Arnd Bergmann Signed-off-by: Paul E. McKenney Cc: Christopher Li Cc: Josh Triplett --- include/linux/compiler.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index a5a472b10746..c1a62c56a660 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -16,6 +16,7 @@ # define __release(x) __context__(x,-1) # define __cond_lock(x,c) ((c) ? ({ __acquire(x); 1; }) : 0) # define __percpu __attribute__((noderef, address_space(3))) +# define __rcu extern void __chk_user_ptr(const volatile void __user *); extern void __chk_io_ptr(const volatile void __iomem *); #else @@ -34,6 +35,7 @@ extern void __chk_io_ptr(const volatile void __iomem *); # define __release(x) (void)0 # define __cond_lock(x,c) (c) # define __percpu +# define __rcu #endif #ifdef __KERNEL__ -- cgit v1.2.3 From a25909a4d4a29e272f953e12595bf2f04a292dbd Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 13 May 2010 12:32:28 -0700 Subject: lockdep: Add an in_workqueue_context() lockdep-based test function Some recent uses of RCU make use of workqueues. In these uses, execution within the context of a specific workqueue takes the place of the usual RCU read-side primitives such as rcu_read_lock(), and flushing of workqueues takes the place of the usual RCU grace-period primitives. Checking for correct use of rcu_dereference() in such cases requires a test of whether the code is executing in the context of a particular workqueue. This commit adds an in_workqueue_context() function that provides this test. This new function is only defined when lockdep is enabled, which allows it to be used as the second argument of rcu_dereference_check(). Signed-off-by: Paul E. McKenney --- include/linux/workqueue.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 9466e860d8c2..d0f7c8178498 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -297,4 +297,8 @@ static inline long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg) #else long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg); #endif /* CONFIG_SMP */ + +#ifdef CONFIG_LOCKDEP +int in_workqueue_context(struct workqueue_struct *wq); +#endif #endif -- cgit v1.2.3 From 2c666df80764389886110c942a7916ba9622583d Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 29 Apr 2010 20:48:47 -0700 Subject: vfs: add fs.h to define struct file The sparse RCU-pointer annotations require definition of the underlying type of any pointer passed to rcu_dereference() and friends. So fcheck_files() needs "struct file" to be defined, so include fs.h. Signed-off-by: Arnd Bergmann Signed-off-by: Paul E. McKenney Cc: Al Viro --- include/linux/fdtable.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h index 013dc529e95f..551671e87927 100644 --- a/include/linux/fdtable.h +++ b/include/linux/fdtable.h @@ -11,6 +11,7 @@ #include #include #include +#include #include -- cgit v1.2.3 From 81bdf5bd7349bd4523538cbd7878f334bc2bfe14 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sun, 2 May 2010 18:10:06 -0700 Subject: net: Make accesses to ->br_port safe for sparse RCU The new versions of the rcu_dereference() APIs requires that any pointers passed to one of these APIs be fully defined. The ->br_port field in struct net_device points to a struct net_bridge_port, which is an incomplete type. This commit therefore changes ->br_port to be a void*, and introduces a br_port() helper function to convert the type to struct net_bridge_port, and applies this new helper function where required. Signed-off-by: Arnd Bergmann Signed-off-by: Paul E. McKenney Cc: David Miller Cc: Stephen Hemminger Cc: Eric Dumazet --- include/linux/if_bridge.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 938b7e81df95..d001d782922d 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -101,6 +101,9 @@ struct __fdb_entry { #include +/* br_handle_frame_hook() needs the following forward declaration. */ +struct net_bridge_port; + extern void brioctl_set(int (*ioctl_hook)(struct net *, unsigned int, void __user *)); extern struct sk_buff *(*br_handle_frame_hook)(struct net_bridge_port *p, struct sk_buff *skb); -- cgit v1.2.3 From db3c9cc105ee844f6cd7a1beb9926fb8e9a093ae Mon Sep 17 00:00:00 2001 From: Stefan Richter Date: Sat, 12 Jun 2010 20:30:21 +0200 Subject: firewire: replace get_features card driver hook by feature variables in the fw_card struct. The hook appeared to be an unnecessary abstraction in the card driver interface. Cleaner would be to pass those feature flags as arguments to fw_card_initialize() or fw_card_add(), but the FairnessControl register is in the SCLK domain and may therefore not be accessible while Link Power Status is off, i.e. before the card->driver->enable call from fw_card_add(). Signed-off-by: Stefan Richter --- include/linux/firewire.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/firewire.h b/include/linux/firewire.h index 4d22643215ef..5acb5fc19180 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -122,6 +122,9 @@ struct fw_card { bool bm_abdicate; /* value of csr_abdicate before last bus reset */ bool csr_abdicate; /* visible in CSR STATE_CLEAR/SET registers */ + bool priority_budget_implemented; /* controller feature */ + bool broadcast_channel_auto_allocated; /* controller feature */ + bool broadcast_channel_allocated; u32 broadcast_channel; __be32 topology_map[(CSR_TOPOLOGY_MAP_END - CSR_TOPOLOGY_MAP) / 4]; -- cgit v1.2.3 From c8a94ded57e9cc2498d401b2f5c856213a3e19fb Mon Sep 17 00:00:00 2001 From: Stefan Richter Date: Sat, 12 Jun 2010 20:34:50 +0200 Subject: firewire: normalize STATE_CLEAR/SET CSR access interface Push the maintenance of STATE_CLEAR/SET.abdicate down into the card driver. This way, the read/write_csr_reg driver method works uniformly across all CSR offsets. Signed-off-by: Stefan Richter --- include/linux/firewire.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firewire.h b/include/linux/firewire.h index 5acb5fc19180..5553018d45d6 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -119,8 +119,7 @@ struct fw_card { int bm_retries; int bm_generation; __be32 bm_transaction_data[2]; - bool bm_abdicate; /* value of csr_abdicate before last bus reset */ - bool csr_abdicate; /* visible in CSR STATE_CLEAR/SET registers */ + bool bm_abdicate; bool priority_budget_implemented; /* controller feature */ bool broadcast_channel_auto_allocated; /* controller feature */ -- cgit v1.2.3 From 33e553fe2b4a983ef34a57ab1440d8d33397bb12 Mon Sep 17 00:00:00 2001 From: Stefan Richter Date: Sun, 20 Jun 2010 22:50:35 +0200 Subject: firewire: remove an unused function argument void (*fw_address_callback_t)(..., int speed, ...) is the speed that a remote node chose to transmit a request to us. In case of split transactions, firewire-core will transmit the response at that speed. Upper layer drivers on the other hand (firewire-net, -sbp2, firedtv, and userspace drivers) cannot do anything useful with that speed datum, except log it for debug purposes. But data that is merely potentially (not even actually) used for debug purposes does not belong into the API. Signed-off-by: Stefan Richter --- include/linux/firewire.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firewire.h b/include/linux/firewire.h index 5553018d45d6..e44b502c8341 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -265,7 +265,7 @@ typedef void (*fw_transaction_callback_t)(struct fw_card *card, int rcode, typedef void (*fw_address_callback_t)(struct fw_card *card, struct fw_request *request, int tcode, int destination, int source, - int generation, int speed, + int generation, unsigned long long offset, void *data, size_t length, void *callback_data); -- cgit v1.2.3 From 604f45167824e18ad5766e51ecf1d4d65f15118d Mon Sep 17 00:00:00 2001 From: Stefan Richter Date: Sun, 20 Jun 2010 22:52:55 +0200 Subject: firewire: cdev: freeze FW_CDEV_VERSION due to libraw1394 bug libraw1394 v2.0.0...v2.0.5 takes FW_CDEV_VERSION from an externally installed header file and uses it to declare its own implementation level in FW_CDEV_IOC_GET_INFO. This is wrong; it should set the real version for which it was actually written. If we add features to the kernel ABI that require the kernel to check a client's implementation level, we can not trust the client version if it was set from FW_CDEV_VERSION. Hence freeze FW_CDEV_VERSION at the current value (no damage has been done yet), clearly document FW_CDEV_VERSION as a dummy version and what clients are expected to do with fw_cdev_get_info.version, and use a new defined constant (which is not placed into the exported header file) as kernel implementation level. Note, in order to check in client program source code which features are present in an externally installed linux/firewire-cdev.h, use preprocessor directives like #ifdef FW_CDEV_IOC_ALLOCATE_ISO_RESOURCE or #ifdef FW_CDEV_EVENT_ISO_RESOURCE_ALLOCATED instead of a check of FW_CDEV_VERSION. Signed-off-by: Stefan Richter --- include/linux/firewire-cdev.h | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firewire-cdev.h b/include/linux/firewire-cdev.h index 6ffb24a1f2f2..0d0cc07358af 100644 --- a/include/linux/firewire-cdev.h +++ b/include/linux/firewire-cdev.h @@ -219,7 +219,7 @@ union fw_cdev_event { struct fw_cdev_event_response response; struct fw_cdev_event_request request; struct fw_cdev_event_iso_interrupt iso_interrupt; - struct fw_cdev_event_iso_resource iso_resource; + struct fw_cdev_event_iso_resource iso_resource; /* added in 2.6.30 */ }; /* available since kernel version 2.6.22 */ @@ -252,22 +252,32 @@ union fw_cdev_event { #define FW_CDEV_IOC_GET_CYCLE_TIMER2 _IOWR('#', 0x14, struct fw_cdev_get_cycle_timer2) /* - * FW_CDEV_VERSION History + * ABI version history * 1 (2.6.22) - initial version + * (2.6.24) - added %FW_CDEV_IOC_GET_CYCLE_TIMER * 2 (2.6.30) - changed &fw_cdev_event_iso_interrupt.header if * &fw_cdev_create_iso_context.header_size is 8 or more + * - added %FW_CDEV_IOC_*_ISO_RESOURCE*, + * %FW_CDEV_IOC_GET_SPEED, %FW_CDEV_IOC_SEND_BROADCAST_REQUEST, + * %FW_CDEV_IOC_SEND_STREAM_PACKET * (2.6.32) - added time stamp to xmit &fw_cdev_event_iso_interrupt * (2.6.33) - IR has always packet-per-buffer semantics now, not one of * dual-buffer or packet-per-buffer depending on hardware * 3 (2.6.34) - made &fw_cdev_get_cycle_timer reliable + * - added %FW_CDEV_IOC_GET_CYCLE_TIMER2 */ -#define FW_CDEV_VERSION 3 +#define FW_CDEV_VERSION 3 /* Meaningless; don't use this macro. */ /** * struct fw_cdev_get_info - General purpose information ioctl - * @version: The version field is just a running serial number. - * We never break backwards compatibility, but may add more - * structs and ioctls in later revisions. + * @version: The version field is just a running serial number. Both an + * input parameter (ABI version implemented by the client) and + * output parameter (ABI version implemented by the kernel). + * A client must not fill in an %FW_CDEV_VERSION defined from an + * included kernel header file but the actual version for which + * the client was implemented. This is necessary for forward + * compatibility. We never break backwards compatibility, but + * may add more structs, events, and ioctls in later revisions. * @rom_length: If @rom is non-zero, at most rom_length bytes of configuration * ROM will be copied into that user space address. In either * case, @rom_length is updated with the actual length of the -- cgit v1.2.3 From e205597d188a9ea69ce43f740a14f07b3f5b996a Mon Sep 17 00:00:00 2001 From: Stefan Richter Date: Sun, 20 Jun 2010 22:53:55 +0200 Subject: firewire: cdev: fix ABI for FCP and address range mapping, add fw_cdev_event_request2 The problem: A target-like userspace driver, e.g. AV/C target or SBP-2/3 target, needs to be able to act as responder and requester. In the latter role, it needs to send requests to nods from which it received requests. This is currently impossible because fw_cdev_event_request lacks information about sender node ID. Reported-by: Jay Fenlason Libffado + libraw1394 + firewire-core is currently unable to drive two or more audio devices on the same bus. Reported-by: Arnold Krille This is because libffado requires destination node ID of FCP requests and sender node ID of FCP responses to match. It even prohibits libffado from working with a bus on which libraw1394 opens a /dev/fw* as default ioctl device that does not correspond with the audio device. This is because libraw1394 does not receive the sender node ID from the kernel. Moreover, fw_cdev_event_request makes it impossible to tell unicast and broadcast write requests apart. The fix: Add a replacement of struct fw_cdev_event_request request, boringly called struct fw_cdev_event_request2. The new event will be sent to a userspace client instead of the old one if the client claims compatibility with ABI version 4 or later. libraw1394 needs to be extended to make use of the new event, in order to properly support libffado and other FCP or address range mapping users who require correct sender node IDs. Further notes: While we are at it, change back the range of possible values of fw_cdev_event_request.tcode to 0x0...0xb like in ABI version <= 3. The preceding change "firewire: expose extended tcode of incoming lock requests to (userspace) drivers" expanded it to 0x0...0x17 which could catch sloppily coded clients by surprise. The extended range of codes is only used in the new fw_cdev_event_request2.tcode. Jay and I also suggested an alternative approach to fix the ABI for incoming requests: Add an FW_CDEV_IOC_GET_REQUEST_INFO ioctl which can be called after reception of an fw_cdev_event_request, before issuing of the closing FW_CDEV_IOC_SEND_RESPONSE ioctl. The new ioctl would reveal the vital information about a request that fw_cdev_event_request lacks. Jay showed an implementation of this approach. The former event approach adds 27 LOC of rather trivial code to core-cdev.c, the ioctl approach 34 LOC, some of which is nontrivial. The ioctl approach would certainly also add more LOC to userspace programs which require the expanded information on inbound requests. This approach is probably only on the lighter-weight side in case of clients that want to be compatible with kernels that lack the new capability, like libraw1394. However, the code to be added to such libraw1394-like clients in case of the event approach is a straight- forward additional switch () case in its event handler. Signed-off-by: Stefan Richter --- include/linux/firewire-cdev.h | 76 +++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 74 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firewire-cdev.h b/include/linux/firewire-cdev.h index 0d0cc07358af..52c7ffe934ad 100644 --- a/include/linux/firewire-cdev.h +++ b/include/linux/firewire-cdev.h @@ -32,6 +32,9 @@ #define FW_CDEV_EVENT_ISO_RESOURCE_ALLOCATED 0x04 #define FW_CDEV_EVENT_ISO_RESOURCE_DEALLOCATED 0x05 +/* available since kernel version 2.6.36 */ +#define FW_CDEV_EVENT_REQUEST2 0x06 + /** * struct fw_cdev_event_common - Common part of all fw_cdev_event_ types * @closure: For arbitrary use by userspace @@ -98,11 +101,46 @@ struct fw_cdev_event_response { }; /** - * struct fw_cdev_event_request - Sent on incoming request to an address region + * struct fw_cdev_event_request - Old version of &fw_cdev_event_request2 * @closure: See &fw_cdev_event_common; set by %FW_CDEV_IOC_ALLOCATE ioctl * @type: See &fw_cdev_event_common; always %FW_CDEV_EVENT_REQUEST + * @tcode: See &fw_cdev_event_request2 + * @offset: See &fw_cdev_event_request2 + * @handle: See &fw_cdev_event_request2 + * @length: See &fw_cdev_event_request2 + * @data: See &fw_cdev_event_request2 + * + * This event is sent instead of &fw_cdev_event_request2 if the kernel or + * the client implements ABI version <= 3. + * + * Unlike &fw_cdev_event_request2, the sender identity cannot be established, + * broadcast write requests cannot be distinguished from unicast writes, and + * @tcode of lock requests is %TCODE_LOCK_REQUEST. + * + * Requests to the FCP_REQUEST or FCP_RESPONSE register are responded to as + * with &fw_cdev_event_request2, except in kernel 2.6.32 and older which send + * the response packet of the client's %FW_CDEV_IOC_SEND_RESPONSE ioctl. + */ +struct fw_cdev_event_request { + __u64 closure; + __u32 type; + __u32 tcode; + __u64 offset; + __u32 handle; + __u32 length; + __u32 data[0]; +}; + +/** + * struct fw_cdev_event_request2 - Sent on incoming request to an address region + * @closure: See &fw_cdev_event_common; set by %FW_CDEV_IOC_ALLOCATE ioctl + * @type: See &fw_cdev_event_common; always %FW_CDEV_EVENT_REQUEST2 * @tcode: Transaction code of the incoming request * @offset: The offset into the 48-bit per-node address space + * @source_node_id: Sender node ID + * @destination_node_id: Destination node ID + * @card: The index of the card from which the request came + * @generation: Bus generation in which the request is valid * @handle: Reference to the kernel-side pending request * @length: Data length, i.e. the request's payload size in bytes * @data: Incoming data, if any @@ -115,12 +153,42 @@ struct fw_cdev_event_response { * * The payload data for requests carrying data (write and lock requests) * follows immediately and can be accessed through the @data field. + * + * Unlike &fw_cdev_event_request, @tcode of lock requests is one of the + * firewire-core specific %TCODE_LOCK_MASK_SWAP...%TCODE_LOCK_VENDOR_DEPENDENT, + * i.e. encodes the extended transaction code. + * + * @card may differ from &fw_cdev_get_info.card because requests are received + * from all cards of the Linux host. @source_node_id, @destination_node_id, and + * @generation pertain to that card. Destination node ID and bus generation may + * therefore differ from the corresponding fields of the last + * &fw_cdev_event_bus_reset. + * + * @destination_node_id may also differ from the current node ID because of a + * non-local bus ID part or in case of a broadcast write request. Note, a + * client must call an %FW_CDEV_IOC_SEND_RESPONSE ioctl even in case of a + * broadcast write request; the kernel will then release the kernel-side pending + * request but will not actually send a response packet. + * + * In case of a write request to FCP_REQUEST or FCP_RESPONSE, the kernel already + * sent a write response immediately after the request was received; in this + * case the client must still call an %FW_CDEV_IOC_SEND_RESPONSE ioctl to + * release the kernel-side pending request, though another response won't be + * sent. + * + * If the client subsequently needs to initiate requests to the sender node of + * an &fw_cdev_event_request2, it needs to use a device file with matching + * card index, node ID, and generation for outbound requests. */ -struct fw_cdev_event_request { +struct fw_cdev_event_request2 { __u64 closure; __u32 type; __u32 tcode; __u64 offset; + __u32 source_node_id; + __u32 destination_node_id; + __u32 card; + __u32 generation; __u32 handle; __u32 length; __u32 data[0]; @@ -200,6 +268,7 @@ struct fw_cdev_event_iso_resource { * @bus_reset: Valid if @common.type == %FW_CDEV_EVENT_BUS_RESET * @response: Valid if @common.type == %FW_CDEV_EVENT_RESPONSE * @request: Valid if @common.type == %FW_CDEV_EVENT_REQUEST + * @request2: Valid if @common.type == %FW_CDEV_EVENT_REQUEST2 * @iso_interrupt: Valid if @common.type == %FW_CDEV_EVENT_ISO_INTERRUPT * @iso_resource: Valid if @common.type == * %FW_CDEV_EVENT_ISO_RESOURCE_ALLOCATED or @@ -218,6 +287,7 @@ union fw_cdev_event { struct fw_cdev_event_bus_reset bus_reset; struct fw_cdev_event_response response; struct fw_cdev_event_request request; + struct fw_cdev_event_request2 request2; /* added in 2.6.36 */ struct fw_cdev_event_iso_interrupt iso_interrupt; struct fw_cdev_event_iso_resource iso_resource; /* added in 2.6.30 */ }; @@ -263,8 +333,10 @@ union fw_cdev_event { * (2.6.32) - added time stamp to xmit &fw_cdev_event_iso_interrupt * (2.6.33) - IR has always packet-per-buffer semantics now, not one of * dual-buffer or packet-per-buffer depending on hardware + * - shared use and auto-response for FCP registers * 3 (2.6.34) - made &fw_cdev_get_cycle_timer reliable * - added %FW_CDEV_IOC_GET_CYCLE_TIMER2 + * 4 (2.6.36) - added %FW_CDEV_EVENT_REQUEST2 */ #define FW_CDEV_VERSION 3 /* Meaningless; don't use this macro. */ -- cgit v1.2.3 From 3b2b65d68fc87b02ac393a031a4ebb3de84a8218 Mon Sep 17 00:00:00 2001 From: Stefan Richter Date: Sun, 20 Jun 2010 22:54:22 +0200 Subject: firewire: cdev: extend fw_cdev_event_iso_interrupt documentation Add information regarding the 2.6.32 update to the xmit variant of fw_cdev_event_iso_interrupt. Signed-off-by: Stefan Richter --- include/linux/firewire-cdev.h | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firewire-cdev.h b/include/linux/firewire-cdev.h index 52c7ffe934ad..8b9b27373219 100644 --- a/include/linux/firewire-cdev.h +++ b/include/linux/firewire-cdev.h @@ -204,10 +204,21 @@ struct fw_cdev_event_request2 { * @header: Stripped headers, if any * * This event is sent when the controller has completed an &fw_cdev_iso_packet - * with the %FW_CDEV_ISO_INTERRUPT bit set. In the receive case, the headers - * stripped of all packets up until and including the interrupt packet are - * returned in the @header field. The amount of header data per packet is as - * specified at iso context creation by &fw_cdev_create_iso_context.header_size. + * with the %FW_CDEV_ISO_INTERRUPT bit set. + * + * Isochronous transmit events: + * + * In version 1 of the ABI, &header_length is 0. In version 3 and some + * implementations of version 2 of the ABI, &header_length is a multiple of 4 + * and &header contains timestamps of all packets up until the interrupt packet. + * The format of the timestamps is as described below for isochronous reception. + * + * Isochronous receive events: + * + * The headers stripped of all packets up until and including the interrupt + * packet are returned in the @header field. The amount of header data per + * packet is as specified at iso context creation by + * &fw_cdev_create_iso_context.header_size. * * In version 1 of this ABI, header data consisted of the 1394 isochronous * packet header, followed by quadlets from the packet payload if -- cgit v1.2.3 From 97dc135947181a6670949a480da56c3ebf8d3715 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 16 Jun 2010 09:52:26 -0400 Subject: NFSv41: Clean up the NFSv4.1 minor version specific operations Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index d6e10a4c06e5..c82ee7cd6288 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -15,6 +15,7 @@ struct nlm_host; struct nfs4_sequence_args; struct nfs4_sequence_res; struct nfs_server; +struct nfs4_minor_version_ops; /* * The nfs_client identifies our client state to the server. @@ -70,11 +71,7 @@ struct nfs_client { */ char cl_ipaddr[48]; unsigned char cl_id_uniquifier; - int (* cl_call_sync)(struct nfs_server *server, - struct rpc_message *msg, - struct nfs4_sequence_args *args, - struct nfs4_sequence_res *res, - int cache_reply); + const struct nfs4_minor_version_ops *cl_mvops; #endif /* CONFIG_NFS_V4 */ #ifdef CONFIG_NFS_V4_1 -- cgit v1.2.3 From d77d76ffb638bd013782138cca6d8f4918c5afd6 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 16 Jun 2010 09:52:27 -0400 Subject: NFSv41: Clean up exclusive create Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 51914d7d6cc4..a319cb926abf 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -196,8 +196,10 @@ struct nfs_openargs { __u64 clientid; __u64 id; union { - struct iattr * attrs; /* UNCHECKED, GUARDED */ - nfs4_verifier verifier; /* EXCLUSIVE */ + struct { + struct iattr * attrs; /* UNCHECKED, GUARDED */ + nfs4_verifier verifier; /* EXCLUSIVE */ + }; nfs4_stateid delegation; /* CLAIM_DELEGATE_CUR */ fmode_t delegation_type; /* CLAIM_PREVIOUS */ } u; -- cgit v1.2.3 From 69da9bcb98ccbfb5d5f751bc13418f1307332925 Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Wed, 16 Jun 2010 17:57:28 +0200 Subject: ALSA: usb-audio: unify UAC macros and struct names Get rid of the last occurances of _v1 suffixes, and move the version number right after the "uac" string. Now things are consitent again. Sorry for the forth and back, but it just looks much nicer this way. Signed-off-by: Daniel Mack Signed-off-by: Takashi Iwai --- include/linux/usb/audio-v2.h | 2 +- include/linux/usb/audio.h | 12 ++++++------ 2 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/audio-v2.h b/include/linux/usb/audio-v2.h index 383b94ba8c20..716aebe339e8 100644 --- a/include/linux/usb/audio-v2.h +++ b/include/linux/usb/audio-v2.h @@ -121,7 +121,7 @@ struct uac2_feature_unit_descriptor { /* 4.9.2 Class-Specific AS Interface Descriptor */ -struct uac_as_header_descriptor_v2 { +struct uac2_as_header_descriptor { __u8 bLength; __u8 bDescriptorType; __u8 bDescriptorSubtype; diff --git a/include/linux/usb/audio.h b/include/linux/usb/audio.h index c51200c715e5..a54b8255d75f 100644 --- a/include/linux/usb/audio.h +++ b/include/linux/usb/audio.h @@ -39,8 +39,8 @@ #define UAC_MIXER_UNIT 0x04 #define UAC_SELECTOR_UNIT 0x05 #define UAC_FEATURE_UNIT 0x06 -#define UAC_PROCESSING_UNIT_V1 0x07 -#define UAC_EXTENSION_UNIT_V1 0x08 +#define UAC1_PROCESSING_UNIT 0x07 +#define UAC1_EXTENSION_UNIT 0x08 /* A.6 Audio Class-Specific AS Interface Descriptor Subtypes */ #define UAC_AS_GENERAL 0x01 @@ -151,7 +151,7 @@ /* Terminal Control Selectors */ /* 4.3.2 Class-Specific AC Interface Descriptor */ -struct uac_ac_header_descriptor_v1 { +struct uac1_ac_header_descriptor { __u8 bLength; /* 8 + n */ __u8 bDescriptorType; /* USB_DT_CS_INTERFACE */ __u8 bDescriptorSubtype; /* UAC_MS_HEADER */ @@ -165,7 +165,7 @@ struct uac_ac_header_descriptor_v1 { /* As above, but more useful for defining your own descriptors: */ #define DECLARE_UAC_AC_HEADER_DESCRIPTOR(n) \ -struct uac_ac_header_descriptor_v1_##n { \ +struct uac1_ac_header_descriptor_##n { \ __u8 bLength; \ __u8 bDescriptorType; \ __u8 bDescriptorSubtype; \ @@ -205,7 +205,7 @@ struct uac_input_terminal_descriptor { #define UAC_TERMINAL_CS_COPY_PROTECT_CONTROL 0x01 /* 4.3.2.2 Output Terminal Descriptor */ -struct uac_output_terminal_descriptor_v1 { +struct uac1_output_terminal_descriptor { __u8 bLength; /* in bytes: 9 */ __u8 bDescriptorType; /* CS_INTERFACE descriptor type */ __u8 bDescriptorSubtype; /* OUTPUT_TERMINAL descriptor subtype */ @@ -395,7 +395,7 @@ static inline __u8 *uac_processing_unit_specific(struct uac_processing_unit_desc } /* 4.5.2 Class-Specific AS Interface Descriptor */ -struct uac_as_header_descriptor_v1 { +struct uac1_as_header_descriptor { __u8 bLength; /* in bytes: 7 */ __u8 bDescriptorType; /* USB_DT_CS_INTERFACE */ __u8 bDescriptorSubtype; /* AS_GENERAL */ -- cgit v1.2.3 From 157a57b6fae7d3c6d24b7623dcc6679c6d244621 Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Wed, 16 Jun 2010 17:57:30 +0200 Subject: ALSA: usb-audio: move and add some comments Also add a list of open topics. Signed-off-by: Daniel Mack Signed-off-by: Takashi Iwai --- include/linux/usb/audio-v2.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/audio-v2.h b/include/linux/usb/audio-v2.h index 716aebe339e8..964cb603f7c7 100644 --- a/include/linux/usb/audio-v2.h +++ b/include/linux/usb/audio-v2.h @@ -18,6 +18,21 @@ /* v1.0 and v2.0 of this standard have many things in common. For the rest * of the definitions, please refer to audio.h */ +/* + * bmControl field decoders + * + * From the USB Audio spec v2.0: + * + * bmaControls() is a (ch+1)-element array of 4-byte bitmaps, + * each containing a set of bit pairs. If a Control is present, + * it must be Host readable. If a certain Control is not + * present then the bit pair must be set to 0b00. + * If a Control is present but read-only, the bit pair must be + * set to 0b01. If a Control is also Host programmable, the bit + * pair must be set to 0b11. The value 0b10 is not allowed. + * + */ + static inline bool uac2_control_is_readable(u32 bmControls, u8 control) { return (bmControls >> (control * 2)) & 0x1; -- cgit v1.2.3 From 45a73372efe4a63f44aa2e1125d4a777c2fdc8d8 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 23 Jun 2010 23:00:37 +0200 Subject: hw_breakpoints: Fix per task breakpoint tracking Freeing a perf event can happen in several ways. A task calls perf_event_exit_task() right before exiting. This helper will detach all the events from the task context and queue their removal through free_event() if they are child tasks. The task also loses its context reference there. Releasing the breakpoint slot from the constraint table is made from free_event() that calls release_bp_slot(). We count the number of breakpoints this task is running by looking at the task's perf_event_ctxp and iterating through its attached events. But at this time, the reference to this context has been cleaned up already. So looking at the event->ctx instead of task->perf_event_ctxp to count the remaining breakpoints should solve the problem. At least it would for child breakpoints, but not for parent ones. If the parent exits before the child, it will remove all its events from the context but free_event() will be called later, on fd release time. And checking the number of breakpoints the task has attached to its context at this time is unreliable as all events have been removed from the context. To solve this, we keep track of the list of per task breakpoints. On top of it, we maintain our array of numbers of breakpoints used by the tasks. We use the context address as a task id. So, instead of looking at the number of events attached to a context, we walk through our list of per task breakpoints and count the number of breakpoints that use the same ctx than the one to be reserved or released from the constraint table, and update the count on top of this result. In the meantime it solves a bad refcounting, it also solves a warning, reported by Paul. Badness at /home/paulus/kernel/perf/kernel/hw_breakpoint.c:114 NIP: c0000000000cb470 LR: c0000000000cb46c CTR: c00000000032d9b8 REGS: c000000118e7b570 TRAP: 0700 Not tainted (2.6.35-rc3-perf-00008-g76b0f13 ) MSR: 9000000000029032 CR: 44004424 XER: 000fffff TASK = c0000001187dcad0[3143] 'perf' THREAD: c000000118e78000 CPU: 1 GPR00: c0000000000cb46c c000000118e7b7f0 c0000000009866a0 0000000000000020 GPR04: 0000000000000000 000000000000001d 0000000000000000 0000000000000001 GPR08: c0000000009bed68 c00000000086dff8 c000000000a5bf10 0000000000000001 GPR12: 0000000024004422 c00000000ffff200 0000000000000000 0000000000000000 GPR16: 0000000000000000 0000000000000000 0000000000000018 00000000101150f4 GPR20: 0000000010206b40 0000000000000000 0000000000000000 00000000101150f4 GPR24: c0000001199090c0 0000000000000001 0000000000000000 0000000000000001 GPR28: 0000000000000000 0000000000000000 c0000000008ec290 0000000000000000 NIP [c0000000000cb470] .task_bp_pinned+0x5c/0x12c LR [c0000000000cb46c] .task_bp_pinned+0x58/0x12c Call Trace: [c000000118e7b7f0] [c0000000000cb46c] .task_bp_pinned+0x58/0x12c (unreliable) [c000000118e7b8a0] [c0000000000cb584] .toggle_bp_task_slot+0x44/0xe4 [c000000118e7b940] [c0000000000cb6c8] .toggle_bp_slot+0xa4/0x164 [c000000118e7b9f0] [c0000000000cbafc] .release_bp_slot+0x44/0x6c [c000000118e7ba80] [c0000000000c4178] .bp_perf_event_destroy+0x10/0x24 [c000000118e7bb00] [c0000000000c4aec] .free_event+0x180/0x1bc [c000000118e7bbc0] [c0000000000c54c4] .perf_event_release_kernel+0x14c/0x170 Reported-by: Paul Mackerras Signed-off-by: Frederic Weisbecker Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Prasad Cc: Mahesh Salgaonkar Cc: Will Deacon Cc: Jason Wessel --- include/linux/perf_event.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 63b5aa5dce69..0dd5f8ad77ac 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -533,8 +533,10 @@ struct hw_perf_event { struct hrtimer hrtimer; }; #ifdef CONFIG_HAVE_HW_BREAKPOINT - /* breakpoint */ - struct arch_hw_breakpoint info; + struct { /* breakpoint */ + struct arch_hw_breakpoint info; + struct list_head bp_list; + }; #endif }; local64_t prev_count; -- cgit v1.2.3 From 5cfaf214856eb934759ae500a0b812dd06a00bd9 Mon Sep 17 00:00:00 2001 From: Nobuhiro Iwamatsu Date: Wed, 23 Jun 2010 09:17:53 +0900 Subject: perf: Fix argument of perf_arch_fetch_caller_regs "struct regs" was set to argument of perf_arch_fetch_caller_regs off-case. It should be "struct pt_regs". This fixes various build errors in archs that have CONFIG_PERF_EVENTS=y but no overriden implementation of perf_arch_fetch_caller_regs. cc1: warnings being treated as errors In file included from include/linux/ftrace_event.h:8, from include/trace/syscall.h:6, from include/linux/syscalls.h:75, from arch/sh/kernel/sys_sh32.c:9: include/linux/perf_event.h:937: error: 'struct regs' declared inside parameter list include/linux/perf_event.h:937: error: its scope is only this definition or declaration, which is probably not what you want include/linux/perf_event.h: In function 'perf_fetch_caller_regs': include/linux/perf_event.h:952: error: passing argument 1 of 'perf_arch_fetch_caller_regs' from incompatible pointer type Signed-off-by: Nobuhiro Iwamatsu Reported-by: Stephen Rothwell Cc: Paul Mackerras Cc: David Miller Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo LKML-Reference: Signed-off-by: Frederic Weisbecker --- include/linux/perf_event.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 0dd5f8ad77ac..937495c25073 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -936,7 +936,7 @@ extern void __perf_sw_event(u32, u64, int, struct pt_regs *, u64); #ifndef perf_arch_fetch_caller_regs static inline void -perf_arch_fetch_caller_regs(struct regs *regs, unsigned long ip) { } +perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip) { } #endif /* -- cgit v1.2.3 From b505ff5e7291cca6379549297e3852ce3622d550 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Fri, 18 Jun 2010 11:09:59 -0600 Subject: of: kill struct of_device Now that the device tree node pointer has been moved out of struct of_device and into the common struct device, there isn't anything unique about of_device anymore. In fact, there isn't much need for a separate of_bus when all busses have access to OF style probing. arch/powerpc and arch/microblaze are moving away from using the of_bus and using the regular platform bus instead for mmio devices. This patch makes of_device the same as platform_device as a stepping stone in migrating of_platform_drivers over to the platform bus. Signed-off-by: Grant Likely Acked-by: David S. Miller Cc: Michal Simek Cc: Benjamin Herrenschmidt Cc: Stephen Rothwell --- include/linux/of_device.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_device.h b/include/linux/of_device.h index 11651facc5f1..a3ae5900fc58 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -3,9 +3,26 @@ #ifdef CONFIG_OF_DEVICE #include +#include #include #include + +/* + * The of_device *was* a kind of "base class" that was a superset of + * struct device for use by devices attached to an OF node and probed + * using OF properties. However, the important bit of OF-style + * probing, namely the device node pointer, has been moved into the + * common struct device when CONFIG_OF is set to make OF-style probing + * available to all bus types. So now, just make of_device and + * platform_device equivalent so that current of_platform bus users + * can be transparently migrated over to using the platform bus. + * + * This line will go away once all references to of_device are removed + * from the kernel. + */ +#define of_device platform_device + #include #define to_of_device(d) container_of(d, struct of_device, dev) -- cgit v1.2.3 From e3873444990dd6f8a095d1f72b5ad45192f8c506 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Fri, 18 Jun 2010 11:09:59 -0600 Subject: of/irq: Move irq_of_parse_and_map() to common code Merge common code between PowerPC and Microblaze. SPARC implements irq_of_parse_and_map(), but the implementation is different, so it does not use this code. Signed-off-by: Grant Likely Acked-by: Benjamin Herrenschmidt Cc: Michal Simek Cc: "David S. Miller" Cc: Stephen Rothwell Cc: Jeremy Kerr --- include/linux/of_irq.h | 41 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) create mode 100644 include/linux/of_irq.h (limited to 'include/linux') diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h new file mode 100644 index 000000000000..0e37c05b7dd8 --- /dev/null +++ b/include/linux/of_irq.h @@ -0,0 +1,41 @@ +#ifndef __OF_IRQ_H +#define __OF_IRQ_H + +#if defined(CONFIG_OF) +struct of_irq; +#include +#include + +/* + * irq_of_parse_and_map() is used ba all OF enabled platforms; but SPARC + * implements it differently. However, the prototype is the same for all, + * so declare it here regardless of the CONFIG_OF_IRQ setting. + */ +extern unsigned int irq_of_parse_and_map(struct device_node *node, int index); + +#if defined(CONFIG_OF_IRQ) +/** + * of_irq - container for device_node/irq_specifier pair for an irq controller + * @controller: pointer to interrupt controller device tree node + * @size: size of interrupt specifier + * @specifier: array of cells @size long specifing the specific interrupt + * + * This structure is returned when an interrupt is mapped. The controller + * field needs to be put() after use + */ +#define OF_MAX_IRQ_SPEC 4 /* We handle specifiers of at most 4 cells */ +struct of_irq { + struct device_node *controller; /* Interrupt controller node */ + u32 size; /* Specifier size */ + u32 specifier[OF_MAX_IRQ_SPEC]; /* Specifier copy */ +}; + +extern int of_irq_map_one(struct device_node *device, int index, + struct of_irq *out_irq); +extern unsigned int irq_create_of_mapping(struct device_node *controller, + const u32 *intspec, + unsigned int intsize); + +#endif /* CONFIG_OF_IRQ */ +#endif /* CONFIG_OF */ +#endif /* __OF_IRQ_H */ -- cgit v1.2.3 From c9642c49aae1272d7c24008a40ae614470b957a6 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Mon, 24 May 2010 16:22:30 +0800 Subject: tracing: Use a global field list for all syscall exit events All syscall exit events have the same fields. The kernel size drops 2.5K: text data bss dec hex filename 7018612 2034376 7251132 16304120 f8c7f8 vmlinux.o.orig 7018612 2031888 7251132 16301632 f8be40 vmlinux.o Signed-off-by: Li Zefan LKML-Reference: <4BFA3746.8070100@cn.fujitsu.com> Signed-off-by: Steven Rostedt --- include/linux/syscalls.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 7f614ce274a9..7994bd44eb56 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -165,7 +165,6 @@ extern struct trace_event_functions exit_syscall_print_funcs; .enter_event = &event_enter_##sname, \ .exit_event = &event_exit_##sname, \ .enter_fields = LIST_HEAD_INIT(__syscall_meta_##sname.enter_fields), \ - .exit_fields = LIST_HEAD_INIT(__syscall_meta_##sname.exit_fields), \ }; #define SYSCALL_DEFINE0(sname) \ @@ -180,7 +179,6 @@ extern struct trace_event_functions exit_syscall_print_funcs; .enter_event = &event_enter__##sname, \ .exit_event = &event_exit__##sname, \ .enter_fields = LIST_HEAD_INIT(__syscall_meta__##sname.enter_fields), \ - .exit_fields = LIST_HEAD_INIT(__syscall_meta__##sname.exit_fields), \ }; \ asmlinkage long sys_##sname(void) #else -- cgit v1.2.3 From cf32b71e981ca63e8f349d8585ca2a3583b556e0 Mon Sep 17 00:00:00 2001 From: Ernst Schwab Date: Mon, 28 Jun 2010 17:49:29 -0700 Subject: spi/mmc_spi: SPI bus locking API, using mutex SPI bus locking API to allow exclusive access to the SPI bus, especially, but not limited to, for the mmc_spi driver. Coded according to an outline from Grant Likely; here is his specification (accidentally swapped function names corrected): It requires 3 things to be added to struct spi_master. - 1 Mutex - 1 spin lock - 1 flag. The mutex protects spi_sync, and provides sleeping "for free" The spinlock protects the atomic spi_async call. The flag is set when the lock is obtained, and checked while holding the spinlock in spi_async(). If the flag is checked, then spi_async() must fail immediately. The current runtime API looks like this: spi_async(struct spi_device*, struct spi_message*); spi_sync(struct spi_device*, struct spi_message*); The API needs to be extended to this: spi_async(struct spi_device*, struct spi_message*) spi_sync(struct spi_device*, struct spi_message*) spi_bus_lock(struct spi_master*) /* although struct spi_device* might be easier */ spi_bus_unlock(struct spi_master*) spi_async_locked(struct spi_device*, struct spi_message*) spi_sync_locked(struct spi_device*, struct spi_message*) Drivers can only call the last two if they already hold the spi_master_lock(). spi_bus_lock() obtains the mutex, obtains the spin lock, sets the flag, and releases the spin lock before returning. It doesn't even need to sleep while waiting for "in-flight" spi_transactions to complete because its purpose is to guarantee no additional transactions are added. It does not guarantee that the bus is idle. spi_bus_unlock() clears the flag and releases the mutex, which will wake up any waiters. The difference between spi_async() and spi_async_locked() is that the locked version bypasses the check of the lock flag. Both versions need to obtain the spinlock. The difference between spi_sync() and spi_sync_locked() is that spi_sync() must hold the mutex while enqueuing a new transfer. spi_sync_locked() doesn't because the mutex is already held. Note however that spi_sync must *not* continue to hold the mutex while waiting for the transfer to complete, otherwise only one transfer could be queued up at a time! Almost no code needs to be written. The current spi_async() and spi_sync() can probably be renamed to __spi_async() and __spi_sync() so that spi_async(), spi_sync(), spi_async_locked() and spi_sync_locked() can just become wrappers around the common code. spi_sync() is protected by a mutex because it can sleep spi_async() needs to be protected with a flag and a spinlock because it can be called atomically and must not sleep Signed-off-by: Ernst Schwab [grant.likely@secretlab.ca: use spin_lock_irqsave()] Signed-off-by: Grant Likely Tested-by: Matt Fleming Tested-by: Antonio Ospite --- include/linux/spi/spi.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index af56071b06f9..ae0a5286f558 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -262,6 +262,13 @@ struct spi_master { #define SPI_MASTER_NO_RX BIT(1) /* can't do buffer read */ #define SPI_MASTER_NO_TX BIT(2) /* can't do buffer write */ + /* lock and mutex for SPI bus locking */ + spinlock_t bus_lock_spinlock; + struct mutex bus_lock_mutex; + + /* flag indicating that the SPI bus is locked for exclusive use */ + bool bus_lock_flag; + /* Setup mode and clock, etc (spi driver may call many times). * * IMPORTANT: this may be called when transfers to another @@ -542,6 +549,8 @@ static inline void spi_message_free(struct spi_message *m) extern int spi_setup(struct spi_device *spi); extern int spi_async(struct spi_device *spi, struct spi_message *message); +extern int spi_async_locked(struct spi_device *spi, + struct spi_message *message); /*---------------------------------------------------------------------------*/ @@ -551,6 +560,9 @@ extern int spi_async(struct spi_device *spi, struct spi_message *message); */ extern int spi_sync(struct spi_device *spi, struct spi_message *message); +extern int spi_sync_locked(struct spi_device *spi, struct spi_message *message); +extern int spi_bus_lock(struct spi_master *master); +extern int spi_bus_unlock(struct spi_master *master); /** * spi_write - SPI synchronous write -- cgit v1.2.3 From a1d0ce8213e9ddf4046ef5ba95c55762d075f541 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 8 Jun 2010 11:22:06 -0400 Subject: tracing: Use class->reg() for all registering of events Because kprobes and syscalls need special processing to register events, the class->reg() method was created to handle the differences. But instead of creating a default ->reg for perf and ftrace events, the code was scattered with: if (class->reg) class->reg(); else default_reg(); This is messy and can also lead to bugs. This patch cleans up this code and creates a default reg() entry for the events allowing for the code to directly call the class->reg() without the condition. Reported-by: Peter Zijlstra Acked-by: Peter Zijlstra Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 0af31cd335d6..01df7ca4ead7 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -146,6 +146,9 @@ struct ftrace_event_class { int (*raw_init)(struct ftrace_event_call *); }; +extern int ftrace_event_reg(struct ftrace_event_call *event, + enum trace_reg type); + enum { TRACE_EVENT_FL_ENABLED_BIT, TRACE_EVENT_FL_FILTERED_BIT, -- cgit v1.2.3 From b56c0d8937e665a27d90517ee7a746d0aa05af46 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:09 +0200 Subject: kthread: implement kthread_worker Implement simple work processor for kthread. This is to ease using kthread. Single thread workqueue used to be used for things like this but workqueue won't guarantee fixed kthread association anymore to enable worker sharing. This can be used in cases where specific kthread association is necessary, for example, when it should have RT priority or be assigned to certain cgroup. Signed-off-by: Tejun Heo Cc: Andrew Morton --- include/linux/kthread.h | 64 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 64 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kthread.h b/include/linux/kthread.h index aabc8a13ba71..f93cb6979edc 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -34,4 +34,68 @@ int kthread_should_stop(void); int kthreadd(void *unused); extern struct task_struct *kthreadd_task; +/* + * Simple work processor based on kthread. + * + * This provides easier way to make use of kthreads. A kthread_work + * can be queued and flushed using queue/flush_kthread_work() + * respectively. Queued kthread_works are processed by a kthread + * running kthread_worker_fn(). + * + * A kthread_work can't be freed while it is executing. + */ +struct kthread_work; +typedef void (*kthread_work_func_t)(struct kthread_work *work); + +struct kthread_worker { + spinlock_t lock; + struct list_head work_list; + struct task_struct *task; +}; + +struct kthread_work { + struct list_head node; + kthread_work_func_t func; + wait_queue_head_t done; + atomic_t flushing; + int queue_seq; + int done_seq; +}; + +#define KTHREAD_WORKER_INIT(worker) { \ + .lock = SPIN_LOCK_UNLOCKED, \ + .work_list = LIST_HEAD_INIT((worker).work_list), \ + } + +#define KTHREAD_WORK_INIT(work, fn) { \ + .node = LIST_HEAD_INIT((work).node), \ + .func = (fn), \ + .done = __WAIT_QUEUE_HEAD_INITIALIZER((work).done), \ + .flushing = ATOMIC_INIT(0), \ + } + +#define DEFINE_KTHREAD_WORKER(worker) \ + struct kthread_worker worker = KTHREAD_WORKER_INIT(worker) + +#define DEFINE_KTHREAD_WORK(work, fn) \ + struct kthread_work work = KTHREAD_WORK_INIT(work, fn) + +static inline void init_kthread_worker(struct kthread_worker *worker) +{ + *worker = (struct kthread_worker)KTHREAD_WORKER_INIT(*worker); +} + +static inline void init_kthread_work(struct kthread_work *work, + kthread_work_func_t fn) +{ + *work = (struct kthread_work)KTHREAD_WORK_INIT(*work, fn); +} + +int kthread_worker_fn(void *worker_ptr); + +bool queue_kthread_work(struct kthread_worker *worker, + struct kthread_work *work); +void flush_kthread_work(struct kthread_work *work); +void flush_kthread_worker(struct kthread_worker *worker); + #endif /* _LINUX_KTHREAD_H */ -- cgit v1.2.3 From 82805ab77d25643f579d90397dcd34f05d1b750a Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:09 +0200 Subject: kthread: implement kthread_data() Implement kthread_data() which takes @task pointing to a kthread and returns @data specified when creating the kthread. The caller is responsible for ensuring the validity of @task when calling this function. Signed-off-by: Tejun Heo --- include/linux/kthread.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kthread.h b/include/linux/kthread.h index f93cb6979edc..685ea65eb803 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -30,6 +30,7 @@ struct task_struct *kthread_create(int (*threadfn)(void *data), void kthread_bind(struct task_struct *k, unsigned int cpu); int kthread_stop(struct task_struct *k); int kthread_should_stop(void); +void *kthread_data(struct task_struct *k); int kthreadd(void *unused); extern struct task_struct *kthreadd_task; -- cgit v1.2.3 From c790bce0481857412c964c5e9d46d56e41c4b051 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:09 +0200 Subject: workqueue: kill RT workqueue With stop_machine() converted to use cpu_stop, RT workqueue doesn't have any user left. Kill RT workqueue support. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 20 +++++++++----------- 1 file changed, 9 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 9466e860d8c2..0697946c66a1 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -181,12 +181,11 @@ static inline void destroy_work_on_stack(struct work_struct *work) { } extern struct workqueue_struct * -__create_workqueue_key(const char *name, int singlethread, - int freezeable, int rt, struct lock_class_key *key, - const char *lock_name); +__create_workqueue_key(const char *name, int singlethread, int freezeable, + struct lock_class_key *key, const char *lock_name); #ifdef CONFIG_LOCKDEP -#define __create_workqueue(name, singlethread, freezeable, rt) \ +#define __create_workqueue(name, singlethread, freezeable) \ ({ \ static struct lock_class_key __key; \ const char *__lock_name; \ @@ -197,19 +196,18 @@ __create_workqueue_key(const char *name, int singlethread, __lock_name = #name; \ \ __create_workqueue_key((name), (singlethread), \ - (freezeable), (rt), &__key, \ + (freezeable), &__key, \ __lock_name); \ }) #else -#define __create_workqueue(name, singlethread, freezeable, rt) \ - __create_workqueue_key((name), (singlethread), (freezeable), (rt), \ +#define __create_workqueue(name, singlethread, freezeable) \ + __create_workqueue_key((name), (singlethread), (freezeable), \ NULL, NULL) #endif -#define create_workqueue(name) __create_workqueue((name), 0, 0, 0) -#define create_rt_workqueue(name) __create_workqueue((name), 0, 0, 1) -#define create_freezeable_workqueue(name) __create_workqueue((name), 1, 1, 0) -#define create_singlethread_workqueue(name) __create_workqueue((name), 1, 0, 0) +#define create_workqueue(name) __create_workqueue((name), 0, 0) +#define create_freezeable_workqueue(name) __create_workqueue((name), 1, 1) +#define create_singlethread_workqueue(name) __create_workqueue((name), 1, 0) extern void destroy_workqueue(struct workqueue_struct *wq); -- cgit v1.2.3 From 4690c4ab56c71919893ca25252f2dd65b58188c7 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:10 +0200 Subject: workqueue: misc/cosmetic updates Make the following updates in preparation of concurrency managed workqueue. None of these changes causes any visible behavior difference. * Add comments and adjust indentations to data structures and several functions. * Rename wq_per_cpu() to get_cwq() and swap the position of two parameters for consistency. Convert a direct per_cpu_ptr() access to wq->cpu_wq to get_cwq(). * Add work_static() and Update set_wq_data() such that it sets the flags part to WORK_STRUCT_PENDING | WORK_STRUCT_STATIC if static | @extra_flags. * Move santiy check on work->entry emptiness from queue_work_on() to __queue_work() which all queueing paths share. * Make __queue_work() take @cpu and @wq instead of @cwq. * Restructure flush_work() and __create_workqueue_key() to make them easier to modify. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 0697946c66a1..e724dafc9e6d 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -96,9 +96,14 @@ struct execute_work { #ifdef CONFIG_DEBUG_OBJECTS_WORK extern void __init_work(struct work_struct *work, int onstack); extern void destroy_work_on_stack(struct work_struct *work); +static inline unsigned int work_static(struct work_struct *work) +{ + return *work_data_bits(work) & (1 << WORK_STRUCT_STATIC); +} #else static inline void __init_work(struct work_struct *work, int onstack) { } static inline void destroy_work_on_stack(struct work_struct *work) { } +static inline unsigned int work_static(struct work_struct *work) { return 0; } #endif /* -- cgit v1.2.3 From 97e37d7b9e65a6ac939f796f91081135b7a08acc Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:10 +0200 Subject: workqueue: merge feature parameters into flags Currently, __create_workqueue_key() takes @singlethread and @freezeable paramters and store them separately in workqueue_struct. Merge them into a single flags parameter and field and use WQ_FREEZEABLE and WQ_SINGLE_THREAD. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 25 +++++++++++++++---------- 1 file changed, 15 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index e724dafc9e6d..d89cfc143b1a 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -184,13 +184,17 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } #define work_clear_pending(work) \ clear_bit(WORK_STRUCT_PENDING, work_data_bits(work)) +enum { + WQ_FREEZEABLE = 1 << 0, /* freeze during suspend */ + WQ_SINGLE_THREAD = 1 << 1, /* no per-cpu worker */ +}; extern struct workqueue_struct * -__create_workqueue_key(const char *name, int singlethread, int freezeable, +__create_workqueue_key(const char *name, unsigned int flags, struct lock_class_key *key, const char *lock_name); #ifdef CONFIG_LOCKDEP -#define __create_workqueue(name, singlethread, freezeable) \ +#define __create_workqueue(name, flags) \ ({ \ static struct lock_class_key __key; \ const char *__lock_name; \ @@ -200,19 +204,20 @@ __create_workqueue_key(const char *name, int singlethread, int freezeable, else \ __lock_name = #name; \ \ - __create_workqueue_key((name), (singlethread), \ - (freezeable), &__key, \ + __create_workqueue_key((name), (flags), &__key, \ __lock_name); \ }) #else -#define __create_workqueue(name, singlethread, freezeable) \ - __create_workqueue_key((name), (singlethread), (freezeable), \ - NULL, NULL) +#define __create_workqueue(name, flags) \ + __create_workqueue_key((name), (flags), NULL, NULL) #endif -#define create_workqueue(name) __create_workqueue((name), 0, 0) -#define create_freezeable_workqueue(name) __create_workqueue((name), 1, 1) -#define create_singlethread_workqueue(name) __create_workqueue((name), 1, 0) +#define create_workqueue(name) \ + __create_workqueue((name), 0) +#define create_freezeable_workqueue(name) \ + __create_workqueue((name), WQ_FREEZEABLE | WQ_SINGLE_THREAD) +#define create_singlethread_workqueue(name) \ + __create_workqueue((name), WQ_SINGLE_THREAD) extern void destroy_workqueue(struct workqueue_struct *wq); -- cgit v1.2.3 From 22df02bb3fab24af97bff4c69cc6fd8529fc66fe Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:10 +0200 Subject: workqueue: define masks for work flags and conditionalize STATIC flags Work flags are about to see more traditional mask handling. Define WORK_STRUCT_*_BIT as the bit position constant and redefine WORK_STRUCT_* as bit masks. Also, make WORK_STRUCT_STATIC_* flags conditional While at it, re-define these constants as enums and use WORK_STRUCT_STATIC instead of hard-coding 2 in WORK_DATA_STATIC_INIT(). Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 29 +++++++++++++++++++++-------- 1 file changed, 21 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index d89cfc143b1a..d60c5701ab45 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -22,12 +22,25 @@ typedef void (*work_func_t)(struct work_struct *work); */ #define work_data_bits(work) ((unsigned long *)(&(work)->data)) +enum { + WORK_STRUCT_PENDING_BIT = 0, /* work item is pending execution */ +#ifdef CONFIG_DEBUG_OBJECTS_WORK + WORK_STRUCT_STATIC_BIT = 1, /* static initializer (debugobjects) */ +#endif + + WORK_STRUCT_PENDING = 1 << WORK_STRUCT_PENDING_BIT, +#ifdef CONFIG_DEBUG_OBJECTS_WORK + WORK_STRUCT_STATIC = 1 << WORK_STRUCT_STATIC_BIT, +#else + WORK_STRUCT_STATIC = 0, +#endif + + WORK_STRUCT_FLAG_MASK = 3UL, + WORK_STRUCT_WQ_DATA_MASK = ~WORK_STRUCT_FLAG_MASK, +}; + struct work_struct { atomic_long_t data; -#define WORK_STRUCT_PENDING 0 /* T if work item pending execution */ -#define WORK_STRUCT_STATIC 1 /* static initializer (debugobjects) */ -#define WORK_STRUCT_FLAG_MASK (3UL) -#define WORK_STRUCT_WQ_DATA_MASK (~WORK_STRUCT_FLAG_MASK) struct list_head entry; work_func_t func; #ifdef CONFIG_LOCKDEP @@ -36,7 +49,7 @@ struct work_struct { }; #define WORK_DATA_INIT() ATOMIC_LONG_INIT(0) -#define WORK_DATA_STATIC_INIT() ATOMIC_LONG_INIT(2) +#define WORK_DATA_STATIC_INIT() ATOMIC_LONG_INIT(WORK_STRUCT_STATIC) struct delayed_work { struct work_struct work; @@ -98,7 +111,7 @@ extern void __init_work(struct work_struct *work, int onstack); extern void destroy_work_on_stack(struct work_struct *work); static inline unsigned int work_static(struct work_struct *work) { - return *work_data_bits(work) & (1 << WORK_STRUCT_STATIC); + return *work_data_bits(work) & WORK_STRUCT_STATIC; } #else static inline void __init_work(struct work_struct *work, int onstack) { } @@ -167,7 +180,7 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } * @work: The work item in question */ #define work_pending(work) \ - test_bit(WORK_STRUCT_PENDING, work_data_bits(work)) + test_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) /** * delayed_work_pending - Find out whether a delayable work item is currently @@ -182,7 +195,7 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } * @work: The work item in question */ #define work_clear_pending(work) \ - clear_bit(WORK_STRUCT_PENDING, work_data_bits(work)) + clear_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) enum { WQ_FREEZEABLE = 1 << 0, /* freeze during suspend */ -- cgit v1.2.3 From 0f900049cbe2767d47c2a62b54f0e822e1d66840 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:11 +0200 Subject: workqueue: update cwq alignement work->data field is used for two purposes. It points to cwq it's queued on and the lower bits are used for flags. Currently, two bits are reserved which is always safe as 4 byte alignment is guaranteed on every architecture. However, future changes will need more flag bits. On SMP, the percpu allocator is capable of honoring larger alignment (there are other users which depend on it) and larger alignment works just fine. On UP, percpu allocator is a thin wrapper around kzalloc/kfree() and don't honor alignment request. This patch introduces WORK_STRUCT_FLAG_BITS and implements alloc/free_cwqs() which guarantees max(1 << WORK_STRUCT_FLAG_BITS, __alignof__(unsigned long long) alignment both on SMP and UP. On SMP, simply wrapping percpu allocator is enough. On UP, extra space is allocated so that cwq can be aligned and the original pointer can be stored after it which is used in the free path. * Alignment problem on UP is reported by Michal Simek. Signed-off-by: Tejun Heo Cc: Christoph Lameter Cc: Ingo Molnar Cc: Frederic Weisbecker Reported-by: Michal Simek --- include/linux/workqueue.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index d60c5701ab45..b90958a037dc 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -26,6 +26,9 @@ enum { WORK_STRUCT_PENDING_BIT = 0, /* work item is pending execution */ #ifdef CONFIG_DEBUG_OBJECTS_WORK WORK_STRUCT_STATIC_BIT = 1, /* static initializer (debugobjects) */ + WORK_STRUCT_FLAG_BITS = 2, +#else + WORK_STRUCT_FLAG_BITS = 1, #endif WORK_STRUCT_PENDING = 1 << WORK_STRUCT_PENDING_BIT, @@ -35,7 +38,7 @@ enum { WORK_STRUCT_STATIC = 0, #endif - WORK_STRUCT_FLAG_MASK = 3UL, + WORK_STRUCT_FLAG_MASK = (1UL << WORK_STRUCT_FLAG_BITS) - 1, WORK_STRUCT_WQ_DATA_MASK = ~WORK_STRUCT_FLAG_MASK, }; -- cgit v1.2.3 From 73f53c4aa732eced5fcb1844d3d452c30905f20f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:11 +0200 Subject: workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 21 +++++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index b90958a037dc..8762f62103d8 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -26,11 +26,13 @@ enum { WORK_STRUCT_PENDING_BIT = 0, /* work item is pending execution */ #ifdef CONFIG_DEBUG_OBJECTS_WORK WORK_STRUCT_STATIC_BIT = 1, /* static initializer (debugobjects) */ - WORK_STRUCT_FLAG_BITS = 2, + WORK_STRUCT_COLOR_SHIFT = 3, /* color for workqueue flushing */ #else - WORK_STRUCT_FLAG_BITS = 1, + WORK_STRUCT_COLOR_SHIFT = 2, /* color for workqueue flushing */ #endif + WORK_STRUCT_COLOR_BITS = 4, + WORK_STRUCT_PENDING = 1 << WORK_STRUCT_PENDING_BIT, #ifdef CONFIG_DEBUG_OBJECTS_WORK WORK_STRUCT_STATIC = 1 << WORK_STRUCT_STATIC_BIT, @@ -38,6 +40,21 @@ enum { WORK_STRUCT_STATIC = 0, #endif + /* + * The last color is no color used for works which don't + * participate in workqueue flushing. + */ + WORK_NR_COLORS = (1 << WORK_STRUCT_COLOR_BITS) - 1, + WORK_NO_COLOR = WORK_NR_COLORS, + + /* + * Reserve 6 bits off of cwq pointer w/ debugobjects turned + * off. This makes cwqs aligned to 64 bytes which isn't too + * excessive while allowing 15 workqueue flush colors. + */ + WORK_STRUCT_FLAG_BITS = WORK_STRUCT_COLOR_SHIFT + + WORK_STRUCT_COLOR_BITS, + WORK_STRUCT_FLAG_MASK = (1UL << WORK_STRUCT_FLAG_BITS) - 1, WORK_STRUCT_WQ_DATA_MASK = ~WORK_STRUCT_FLAG_MASK, }; -- cgit v1.2.3 From affee4b294a0fc97d67c8a77dc080c4dd262a79e Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:12 +0200 Subject: workqueue: reimplement work flushing using linked works A work is linked to the next one by having WORK_STRUCT_LINKED bit set and these links can be chained. When a linked work is dispatched to a worker, all linked works are dispatched to the worker's newly added ->scheduled queue and processed back-to-back. Currently, as there's only single worker per cwq, having linked works doesn't make any visible behavior difference. This change is to prepare for multiple shared workers per cpu. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 8762f62103d8..4f4fdba722c3 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -24,8 +24,9 @@ typedef void (*work_func_t)(struct work_struct *work); enum { WORK_STRUCT_PENDING_BIT = 0, /* work item is pending execution */ + WORK_STRUCT_LINKED_BIT = 1, /* next work is linked to this one */ #ifdef CONFIG_DEBUG_OBJECTS_WORK - WORK_STRUCT_STATIC_BIT = 1, /* static initializer (debugobjects) */ + WORK_STRUCT_STATIC_BIT = 2, /* static initializer (debugobjects) */ WORK_STRUCT_COLOR_SHIFT = 3, /* color for workqueue flushing */ #else WORK_STRUCT_COLOR_SHIFT = 2, /* color for workqueue flushing */ @@ -34,6 +35,7 @@ enum { WORK_STRUCT_COLOR_BITS = 4, WORK_STRUCT_PENDING = 1 << WORK_STRUCT_PENDING_BIT, + WORK_STRUCT_LINKED = 1 << WORK_STRUCT_LINKED_BIT, #ifdef CONFIG_DEBUG_OBJECTS_WORK WORK_STRUCT_STATIC = 1 << WORK_STRUCT_STATIC_BIT, #else -- cgit v1.2.3 From 1e19ffc63dbbaea7a7d1c63d99c38d3e5a4c7edf Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:12 +0200 Subject: workqueue: implement per-cwq active work limit Add cwq->nr_active, cwq->max_active and cwq->delayed_work. nr_active counts the number of active works per cwq. A work is active if it's flushable (colored) and is on cwq's worklist. If nr_active reaches max_active, new works are queued on cwq->delayed_work and activated later as works on the cwq complete and decrement nr_active. cwq->max_active can be specified via the new @max_active parameter to __create_workqueue() and is set to 1 for all workqueues for now. As each cwq has only single worker now, this double queueing doesn't cause any behavior difference visible to its users. This will be used to reimplement freeze/thaw and implement shared worker pool. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 4f4fdba722c3..eb753b7790e5 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -225,11 +225,11 @@ enum { }; extern struct workqueue_struct * -__create_workqueue_key(const char *name, unsigned int flags, +__create_workqueue_key(const char *name, unsigned int flags, int max_active, struct lock_class_key *key, const char *lock_name); #ifdef CONFIG_LOCKDEP -#define __create_workqueue(name, flags) \ +#define __create_workqueue(name, flags, max_active) \ ({ \ static struct lock_class_key __key; \ const char *__lock_name; \ @@ -239,20 +239,20 @@ __create_workqueue_key(const char *name, unsigned int flags, else \ __lock_name = #name; \ \ - __create_workqueue_key((name), (flags), &__key, \ - __lock_name); \ + __create_workqueue_key((name), (flags), (max_active), \ + &__key, __lock_name); \ }) #else -#define __create_workqueue(name, flags) \ - __create_workqueue_key((name), (flags), NULL, NULL) +#define __create_workqueue(name, flags, max_active) \ + __create_workqueue_key((name), (flags), (max_active), NULL, NULL) #endif #define create_workqueue(name) \ - __create_workqueue((name), 0) + __create_workqueue((name), 0, 1) #define create_freezeable_workqueue(name) \ - __create_workqueue((name), WQ_FREEZEABLE | WQ_SINGLE_THREAD) + __create_workqueue((name), WQ_FREEZEABLE | WQ_SINGLE_THREAD, 1) #define create_singlethread_workqueue(name) \ - __create_workqueue((name), WQ_SINGLE_THREAD) + __create_workqueue((name), WQ_SINGLE_THREAD, 1) extern void destroy_workqueue(struct workqueue_struct *wq); -- cgit v1.2.3 From a0a1a5fd4fb15ec61117c759fe9f5c16c53d9e9c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:12 +0200 Subject: workqueue: reimplement workqueue freeze using max_active Currently, workqueue freezing is implemented by marking the worker freezeable and calling try_to_freeze() from dispatch loop. Reimplement it using cwq->limit so that the workqueue is frozen instead of the worker. * workqueue_struct->saved_max_active is added which stores the specified max_active on initialization. * On freeze, all cwq->max_active's are quenched to zero. Freezing is complete when nr_active on all cwqs reach zero. * On thaw, all cwq->max_active's are restored to wq->saved_max_active and the worklist is repopulated. This new implementation allows having single shared pool of workers per cpu. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index eb753b7790e5..ab0b7fb99bc2 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -340,4 +340,11 @@ static inline long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg) #else long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg); #endif /* CONFIG_SMP */ + +#ifdef CONFIG_FREEZER +extern void freeze_workqueues_begin(void); +extern bool freeze_workqueues_busy(void); +extern void thaw_workqueues(void); +#endif /* CONFIG_FREEZER */ + #endif -- cgit v1.2.3 From db7bccf45cb87522096b8f43144e31ca605a9f24 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:12 +0200 Subject: workqueue: reimplement CPU hotplugging support using trustee Reimplement CPU hotplugging support using trustee thread. On CPU down, a trustee thread is created and each step of CPU down is executed by the trustee and workqueue_cpu_callback() simply drives and waits for trustee state transitions. CPU down operation no longer waits for works to be drained but trustee sticks around till all pending works have been completed. If CPU is brought back up while works are still draining, workqueue_cpu_callback() tells trustee to step down and tell workers to rebind to the cpu. As it's difficult to tell whether cwqs are empty if it's freezing or frozen, trustee doesn't consider draining to be complete while a gcwq is freezing or frozen (tracked by new GCWQ_FREEZING flag). Also, workers which get unbound from their cpu are marked with WORKER_ROGUE. Trustee based implementation doesn't bring any new feature at this point but it will be used to manage worker pool when dynamic shared worker pool is implemented. Signed-off-by: Tejun Heo --- include/linux/cpu.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index de6b1722cdca..4823af64e9db 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -71,6 +71,8 @@ enum { /* migration should happen before other stuff but after perf */ CPU_PRI_PERF = 20, CPU_PRI_MIGRATION = 10, + /* prepare workqueues for other notifiers */ + CPU_PRI_WORKQUEUE = 5, }; #ifdef CONFIG_SMP -- cgit v1.2.3 From 502ca9d819792e7d79b6e002afe9094c641fe410 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:13 +0200 Subject: workqueue: make single thread workqueue shared worker pool friendly Reimplement st (single thread) workqueue so that it's friendly to shared worker pool. It was originally implemented by confining st workqueues to use cwq of a fixed cpu and always having a worker for the cpu. This implementation isn't very friendly to shared worker pool and suboptimal in that it ends up crossing cpu boundaries often. Reimplement st workqueue using dynamic single cpu binding and cwq->limit. WQ_SINGLE_THREAD is replaced with WQ_SINGLE_CPU. In a single cpu workqueue, at most single cwq is bound to the wq at any given time. Arbitration is done using atomic accesses to wq->single_cpu when queueing a work. Once bound, the binding stays till the workqueue is drained. Note that the binding is never broken while a workqueue is frozen. This is because idle cwqs may have works waiting in delayed_works queue while frozen. On thaw, the cwq is restarted if there are any delayed works or unbound otherwise. When combined with max_active limit of 1, single cpu workqueue has exactly the same execution properties as the original single thread workqueue while allowing sharing of per-cpu workers. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index ab0b7fb99bc2..10611f7fc809 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -221,7 +221,7 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } enum { WQ_FREEZEABLE = 1 << 0, /* freeze during suspend */ - WQ_SINGLE_THREAD = 1 << 1, /* no per-cpu worker */ + WQ_SINGLE_CPU = 1 << 1, /* only single cpu at a time */ }; extern struct workqueue_struct * @@ -250,9 +250,9 @@ __create_workqueue_key(const char *name, unsigned int flags, int max_active, #define create_workqueue(name) \ __create_workqueue((name), 0, 1) #define create_freezeable_workqueue(name) \ - __create_workqueue((name), WQ_FREEZEABLE | WQ_SINGLE_THREAD, 1) + __create_workqueue((name), WQ_FREEZEABLE | WQ_SINGLE_CPU, 1) #define create_singlethread_workqueue(name) \ - __create_workqueue((name), WQ_SINGLE_THREAD, 1) + __create_workqueue((name), WQ_SINGLE_CPU, 1) extern void destroy_workqueue(struct workqueue_struct *wq); -- cgit v1.2.3 From 7a22ad757ec75186ad43a5b4670fa7423ee8f480 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:13 +0200 Subject: workqueue: carry cpu number in work data once execution starts To implement non-reentrant workqueue, the last gcwq a work was executed on must be reliably obtainable as long as the work structure is valid even if the previous workqueue has been destroyed. To achieve this, work->data will be overloaded to carry the last cpu number once execution starts so that the previous gcwq can be located reliably. This means that cwq can't be obtained from work after execution starts but only gcwq. Implement set_work_{cwq|cpu}(), get_work_[g]cwq() and clear_work_data() to set work data to the cpu number when starting execution, access the overloaded work data and clear it after cancellation. queue_delayed_work_on() is updated to preserve the last cpu while in-flight in timer and other callers which depended on getting cwq from work after execution starts are converted to depend on gcwq instead. * Anton Blanchard fixed compile error on powerpc due to missing linux/threads.h include. Signed-off-by: Tejun Heo Cc: Anton Blanchard --- include/linux/workqueue.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 10611f7fc809..0a7814131e66 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -9,6 +9,7 @@ #include #include #include +#include #include struct workqueue_struct; @@ -59,6 +60,7 @@ enum { WORK_STRUCT_FLAG_MASK = (1UL << WORK_STRUCT_FLAG_BITS) - 1, WORK_STRUCT_WQ_DATA_MASK = ~WORK_STRUCT_FLAG_MASK, + WORK_STRUCT_NO_CPU = NR_CPUS << WORK_STRUCT_FLAG_BITS, }; struct work_struct { @@ -70,8 +72,9 @@ struct work_struct { #endif }; -#define WORK_DATA_INIT() ATOMIC_LONG_INIT(0) -#define WORK_DATA_STATIC_INIT() ATOMIC_LONG_INIT(WORK_STRUCT_STATIC) +#define WORK_DATA_INIT() ATOMIC_LONG_INIT(WORK_STRUCT_NO_CPU) +#define WORK_DATA_STATIC_INIT() \ + ATOMIC_LONG_INIT(WORK_STRUCT_NO_CPU | WORK_STRUCT_STATIC) struct delayed_work { struct work_struct work; -- cgit v1.2.3 From 18aa9effad4adb2c1efe123af4eb24fec9f59b30 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:13 +0200 Subject: workqueue: implement WQ_NON_REENTRANT With gcwq managing all the workers and work->data pointing to the last gcwq it was on, non-reentrance can be easily implemented by checking whether the work is still running on the previous gcwq on queueing. Implement it. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 0a7814131e66..07cf5e5f91cb 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -225,6 +225,7 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } enum { WQ_FREEZEABLE = 1 << 0, /* freeze during suspend */ WQ_SINGLE_CPU = 1 << 1, /* only single cpu at a time */ + WQ_NON_REENTRANT = 1 << 2, /* guarantee non-reentrance */ }; extern struct workqueue_struct * -- cgit v1.2.3 From e22bee782b3b00bd4534ae9b1c5fb2e8e6573c5c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:14 +0200 Subject: workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 07cf5e5f91cb..b8f4ec45c40a 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -226,6 +226,7 @@ enum { WQ_FREEZEABLE = 1 << 0, /* freeze during suspend */ WQ_SINGLE_CPU = 1 << 1, /* only single cpu at a time */ WQ_NON_REENTRANT = 1 << 2, /* guarantee non-reentrance */ + WQ_RESCUER = 1 << 3, /* has an rescue worker */ }; extern struct workqueue_struct * @@ -252,11 +253,12 @@ __create_workqueue_key(const char *name, unsigned int flags, int max_active, #endif #define create_workqueue(name) \ - __create_workqueue((name), 0, 1) + __create_workqueue((name), WQ_RESCUER, 1) #define create_freezeable_workqueue(name) \ - __create_workqueue((name), WQ_FREEZEABLE | WQ_SINGLE_CPU, 1) + __create_workqueue((name), \ + WQ_FREEZEABLE | WQ_SINGLE_CPU | WQ_RESCUER, 1) #define create_singlethread_workqueue(name) \ - __create_workqueue((name), WQ_SINGLE_CPU, 1) + __create_workqueue((name), WQ_SINGLE_CPU | WQ_RESCUER, 1) extern void destroy_workqueue(struct workqueue_struct *wq); -- cgit v1.2.3 From b71ab8c2025caef8db719aa41af0ed735dc543cd Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:14 +0200 Subject: workqueue: increase max_active of keventd and kill current_is_keventd() Define WQ_MAX_ACTIVE and create keventd with max_active set to half of it which means that keventd now can process upto WQ_MAX_ACTIVE / 2 - 1 works concurrently. Unless some combination can result in dependency loop longer than max_active, deadlock won't happen and thus it's unnecessary to check whether current_is_keventd() before trying to schedule a work. Kill current_is_keventd(). (Lockdep annotations are broken. We need lock_map_acquire_read_norecurse()) Signed-off-by: Tejun Heo Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Christoph Lameter Cc: Tony Luck Cc: Andi Kleen Cc: Oleg Nesterov --- include/linux/workqueue.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index b8f4ec45c40a..33e24e734d50 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -227,6 +227,9 @@ enum { WQ_SINGLE_CPU = 1 << 1, /* only single cpu at a time */ WQ_NON_REENTRANT = 1 << 2, /* guarantee non-reentrance */ WQ_RESCUER = 1 << 3, /* has an rescue worker */ + + WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */ + WQ_DFL_ACTIVE = WQ_MAX_ACTIVE / 2, }; extern struct workqueue_struct * @@ -280,7 +283,6 @@ extern int schedule_delayed_work(struct delayed_work *work, unsigned long delay) extern int schedule_delayed_work_on(int cpu, struct delayed_work *work, unsigned long delay); extern int schedule_on_each_cpu(work_func_t func); -extern int current_is_keventd(void); extern int keventd_up(void); extern void init_workqueues(void); -- cgit v1.2.3 From d320c03830b17af64e4547075003b1eeb274bc6c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:14 +0200 Subject: workqueue: s/__create_workqueue()/alloc_workqueue()/, and add system workqueues This patch makes changes to make new workqueue features available to its users. * Now that workqueue is more featureful, there should be a public workqueue creation function which takes paramters to control them. Rename __create_workqueue() to alloc_workqueue() and make 0 max_active mean WQ_DFL_ACTIVE. In the long run, all create_workqueue_*() will be converted over to alloc_workqueue(). * To further unify access interface, rename keventd_wq to system_wq and export it. * Add system_long_wq and system_nrt_wq. The former is to host long running works separately (so that flush_scheduled_work() dosen't take so long) and the latter guarantees any queued work item is never executed in parallel by multiple CPUs. These will be used by future patches to update workqueue users. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 40 +++++++++++++++++++++++++++++----------- 1 file changed, 29 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 33e24e734d50..48b7422f25ae 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -232,12 +232,31 @@ enum { WQ_DFL_ACTIVE = WQ_MAX_ACTIVE / 2, }; +/* + * System-wide workqueues which are always present. + * + * system_wq is the one used by schedule[_delayed]_work[_on](). + * Multi-CPU multi-threaded. There are users which expect relatively + * short queue flush time. Don't queue works which can run for too + * long. + * + * system_long_wq is similar to system_wq but may host long running + * works. Queue flushing might take relatively long. + * + * system_nrt_wq is non-reentrant and guarantees that any given work + * item is never executed in parallel by multiple CPUs. Queue + * flushing might take relatively long. + */ +extern struct workqueue_struct *system_wq; +extern struct workqueue_struct *system_long_wq; +extern struct workqueue_struct *system_nrt_wq; + extern struct workqueue_struct * -__create_workqueue_key(const char *name, unsigned int flags, int max_active, - struct lock_class_key *key, const char *lock_name); +__alloc_workqueue_key(const char *name, unsigned int flags, int max_active, + struct lock_class_key *key, const char *lock_name); #ifdef CONFIG_LOCKDEP -#define __create_workqueue(name, flags, max_active) \ +#define alloc_workqueue(name, flags, max_active) \ ({ \ static struct lock_class_key __key; \ const char *__lock_name; \ @@ -247,21 +266,20 @@ __create_workqueue_key(const char *name, unsigned int flags, int max_active, else \ __lock_name = #name; \ \ - __create_workqueue_key((name), (flags), (max_active), \ - &__key, __lock_name); \ + __alloc_workqueue_key((name), (flags), (max_active), \ + &__key, __lock_name); \ }) #else -#define __create_workqueue(name, flags, max_active) \ - __create_workqueue_key((name), (flags), (max_active), NULL, NULL) +#define alloc_workqueue(name, flags, max_active) \ + __alloc_workqueue_key((name), (flags), (max_active), NULL, NULL) #endif #define create_workqueue(name) \ - __create_workqueue((name), WQ_RESCUER, 1) + alloc_workqueue((name), WQ_RESCUER, 1) #define create_freezeable_workqueue(name) \ - __create_workqueue((name), \ - WQ_FREEZEABLE | WQ_SINGLE_CPU | WQ_RESCUER, 1) + alloc_workqueue((name), WQ_FREEZEABLE | WQ_SINGLE_CPU | WQ_RESCUER, 1) #define create_singlethread_workqueue(name) \ - __create_workqueue((name), WQ_SINGLE_CPU | WQ_RESCUER, 1) + alloc_workqueue((name), WQ_SINGLE_CPU | WQ_RESCUER, 1) extern void destroy_workqueue(struct workqueue_struct *wq); -- cgit v1.2.3 From dcd989cb73ab0f7b722d64ab6516f101d9f43f88 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:14 +0200 Subject: workqueue: implement several utility APIs Implement the following utility APIs. workqueue_set_max_active() : adjust max_active of a wq workqueue_congested() : test whether a wq is contested work_cpu() : determine the last / current cpu of a work work_busy() : query whether a work is busy * Anton Blanchard fixed missing ret initialization in work_busy(). Signed-off-by: Tejun Heo Cc: Anton Blanchard --- include/linux/workqueue.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 48b7422f25ae..0a7f79729380 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -61,6 +61,10 @@ enum { WORK_STRUCT_FLAG_MASK = (1UL << WORK_STRUCT_FLAG_BITS) - 1, WORK_STRUCT_WQ_DATA_MASK = ~WORK_STRUCT_FLAG_MASK, WORK_STRUCT_NO_CPU = NR_CPUS << WORK_STRUCT_FLAG_BITS, + + /* bit mask for work_busy() return values */ + WORK_BUSY_PENDING = 1 << 0, + WORK_BUSY_RUNNING = 1 << 1, }; struct work_struct { @@ -307,9 +311,14 @@ extern void init_workqueues(void); int execute_in_process_context(work_func_t fn, struct execute_work *); extern int flush_work(struct work_struct *work); - extern int cancel_work_sync(struct work_struct *work); +extern void workqueue_set_max_active(struct workqueue_struct *wq, + int max_active); +extern bool workqueue_congested(unsigned int cpu, struct workqueue_struct *wq); +extern unsigned int work_cpu(struct work_struct *work); +extern unsigned int work_busy(struct work_struct *work); + /* * Kill off a pending schedule_delayed_work(). Note that the work callback * function may still be running on return from cancel_delayed_work(), unless -- cgit v1.2.3 From 649027d73a6309ac34dc2886362e662bd73456dc Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:14 +0200 Subject: workqueue: implement high priority workqueue This patch implements high priority workqueue which can be specified with WQ_HIGHPRI flag on creation. A high priority workqueue has the following properties. * A work queued to it is queued at the head of the worklist of the respective gcwq after other highpri works, while normal works are always appended at the end. * As long as there are highpri works on gcwq->worklist, [__]need_more_worker() remains %true and process_one_work() wakes up another worker before it start executing a work. The above two properties guarantee that works queued to high priority workqueues are dispatched to workers and start execution as soon as possible regardless of the state of other works. Signed-off-by: Tejun Heo Cc: Andi Kleen Cc: Andrew Morton --- include/linux/workqueue.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 0a7f79729380..006dcf7e808a 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -231,6 +231,7 @@ enum { WQ_SINGLE_CPU = 1 << 1, /* only single cpu at a time */ WQ_NON_REENTRANT = 1 << 2, /* guarantee non-reentrance */ WQ_RESCUER = 1 << 3, /* has an rescue worker */ + WQ_HIGHPRI = 1 << 4, /* high priority */ WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */ WQ_DFL_ACTIVE = WQ_MAX_ACTIVE / 2, -- cgit v1.2.3 From fb0e7beb5c1b6fb4da786ba709d7138373d5fb22 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:15 +0200 Subject: workqueue: implement cpu intensive workqueue This patch implements cpu intensive workqueue which can be specified with WQ_CPU_INTENSIVE flag on creation. Works queued to a cpu intensive workqueue don't participate in concurrency management. IOW, it doesn't contribute to gcwq->nr_running and thus doesn't delay excution of other works. Note that although cpu intensive works won't delay other works, they can be delayed by other works. Combine with WQ_HIGHPRI to avoid being delayed by other works too. As the name suggests this is useful when using workqueue for cpu intensive works. Workers executing cpu intensive works are not considered for workqueue concurrency management and left for the scheduler to manage. Signed-off-by: Tejun Heo Cc: Andrew Morton --- include/linux/workqueue.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 006dcf7e808a..3f36d37ac5ba 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -232,6 +232,7 @@ enum { WQ_NON_REENTRANT = 1 << 2, /* guarantee non-reentrance */ WQ_RESCUER = 1 << 3, /* has an rescue worker */ WQ_HIGHPRI = 1 << 4, /* high priority */ + WQ_CPU_INTENSIVE = 1 << 5, /* cpu instensive workqueue */ WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */ WQ_DFL_ACTIVE = WQ_MAX_ACTIVE / 2, -- cgit v1.2.3 From 2ec57d448b2e8fcfba539a46701b43f14f037f17 Mon Sep 17 00:00:00 2001 From: Michael Neuling Date: Tue, 29 Jun 2010 12:02:01 +1000 Subject: sched: Fix spelling of sibling No logic changes, only spelling. Signed-off-by: Michael Neuling Cc: linuxppc-dev@ozlabs.org Cc: David Howells Cc: Peter Zijlstra LKML-Reference: <15249.1277776921@neuling.org> Signed-off-by: Ingo Molnar --- include/linux/topology.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/topology.h b/include/linux/topology.h index cf57f30d0dcb..b572e432d2f3 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -103,7 +103,7 @@ int arch_update_cpu_topology(void); | 1*SD_SHARE_PKG_RESOURCES \ | 0*SD_SERIALIZE \ | 0*SD_PREFER_SIBLING \ - | arch_sd_sibiling_asym_packing() \ + | arch_sd_sibling_asym_packing() \ , \ .last_balance = jiffies, \ .balance_interval = 1, \ -- cgit v1.2.3 From a53f4b61a76a7e95139b8e8abba02e9bfe87a58a Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 1 Jul 2010 12:45:34 -0700 Subject: Revert "net: Make accesses to ->br_port safe for sparse RCU" This reverts commit 81bdf5bd7349bd4523538cbd7878f334bc2bfe14, which is obsoleted by commit f350a0a87374 from the net tree. --- include/linux/if_bridge.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index d001d782922d..938b7e81df95 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -101,9 +101,6 @@ struct __fdb_entry { #include -/* br_handle_frame_hook() needs the following forward declaration. */ -struct net_bridge_port; - extern void brioctl_set(int (*ioctl_hook)(struct net *, unsigned int, void __user *)); extern struct sk_buff *(*br_handle_frame_hook)(struct net_bridge_port *p, struct sk_buff *skb); -- cgit v1.2.3 From ad72cf9885c536e3adae03f8337557ac9dd1e4bb Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 2 Jul 2010 10:03:52 +0200 Subject: libata: take advantage of cmwq and remove concurrency limitations libata has two concurrency related limitations. a. ata_wq which is used for polling PIO has single thread per CPU. If there are multiple devices doing polling PIO on the same CPU, they can't be executed simultaneously. b. ata_aux_wq which is used for SCSI probing has single thread. In cases where SCSI probing is stalled for extended period of time which is possible for ATAPI devices, this will stall all probing. #a is solved by increasing maximum concurrency of ata_wq. Please note that polling PIO might be used under allocation path and thus needs to be served by a separate wq with a rescuer. #b is solved by using the default wq instead and achieving exclusion via per-port mutex. Signed-off-by: Tejun Heo Acked-by: Jeff Garzik --- include/linux/libata.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index b85f3ff34d7d..f010f18a0f86 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -751,6 +751,7 @@ struct ata_port { struct ata_host *host; struct device *dev; + struct mutex scsi_scan_mutex; struct delayed_work hotplug_task; struct work_struct scsi_rescan_task; -- cgit v1.2.3 From bdbc5dd7de5d07d6c9d3536e598956165a031d4c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 2 Jul 2010 10:03:51 +0200 Subject: workqueue: prepare for WQ_UNBOUND implementation In preparation of WQ_UNBOUND addition, make the following changes. * Add WORK_CPU_* constants for pseudo cpu id numbers used (currently only WORK_CPU_NONE) and use them instead of NR_CPUS. This is to allow another pseudo cpu id for unbound cpu. * Reorder WQ_* flags. * Make workqueue_struct->cpu_wq a union which contains a percpu pointer, regular pointer and an unsigned long value and use kzalloc/kfree() in UP allocation path. This will be used to implement unbound workqueues which will use only one cwq on SMPs. * Move alloc_cwqs() allocation after initialization of wq fields, so that alloc_cwqs() has access to wq->flags. * Trivial relocation of wq local variables in freeze functions. These changes don't cause any functional change. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 3f36d37ac5ba..139069a6286c 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -50,6 +50,10 @@ enum { WORK_NR_COLORS = (1 << WORK_STRUCT_COLOR_BITS) - 1, WORK_NO_COLOR = WORK_NR_COLORS, + /* special cpu IDs */ + WORK_CPU_NONE = NR_CPUS, + WORK_CPU_LAST = WORK_CPU_NONE, + /* * Reserve 6 bits off of cwq pointer w/ debugobjects turned * off. This makes cwqs aligned to 64 bytes which isn't too @@ -60,7 +64,7 @@ enum { WORK_STRUCT_FLAG_MASK = (1UL << WORK_STRUCT_FLAG_BITS) - 1, WORK_STRUCT_WQ_DATA_MASK = ~WORK_STRUCT_FLAG_MASK, - WORK_STRUCT_NO_CPU = NR_CPUS << WORK_STRUCT_FLAG_BITS, + WORK_STRUCT_NO_CPU = WORK_CPU_NONE << WORK_STRUCT_FLAG_BITS, /* bit mask for work_busy() return values */ WORK_BUSY_PENDING = 1 << 0, @@ -227,9 +231,9 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } clear_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) enum { - WQ_FREEZEABLE = 1 << 0, /* freeze during suspend */ + WQ_NON_REENTRANT = 1 << 0, /* guarantee non-reentrance */ WQ_SINGLE_CPU = 1 << 1, /* only single cpu at a time */ - WQ_NON_REENTRANT = 1 << 2, /* guarantee non-reentrance */ + WQ_FREEZEABLE = 1 << 2, /* freeze during suspend */ WQ_RESCUER = 1 << 3, /* has an rescue worker */ WQ_HIGHPRI = 1 << 4, /* high priority */ WQ_CPU_INTENSIVE = 1 << 5, /* cpu instensive workqueue */ -- cgit v1.2.3 From f34217977d717385a3e9fd7018ac39fade3964c0 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 2 Jul 2010 10:03:51 +0200 Subject: workqueue: implement unbound workqueue This patch implements unbound workqueue which can be specified with WQ_UNBOUND flag on creation. An unbound workqueue has the following properties. * It uses a dedicated gcwq with a pseudo CPU number WORK_CPU_UNBOUND. This gcwq is always online and disassociated. * Workers are not bound to any CPU and not concurrency managed. Works are dispatched to workers as soon as possible and the only applied limitation is @max_active. IOW, all unbound workqeueues are implicitly high priority. Unbound workqueues can be used as simple execution context provider. Contexts unbound to any cpu are served as soon as possible. Signed-off-by: Tejun Heo Cc: Arjan van de Ven Cc: David Howells --- include/linux/workqueue.h | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 139069a6286c..67ce734747f6 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -51,7 +51,8 @@ enum { WORK_NO_COLOR = WORK_NR_COLORS, /* special cpu IDs */ - WORK_CPU_NONE = NR_CPUS, + WORK_CPU_UNBOUND = NR_CPUS, + WORK_CPU_NONE = NR_CPUS + 1, WORK_CPU_LAST = WORK_CPU_NONE, /* @@ -237,11 +238,17 @@ enum { WQ_RESCUER = 1 << 3, /* has an rescue worker */ WQ_HIGHPRI = 1 << 4, /* high priority */ WQ_CPU_INTENSIVE = 1 << 5, /* cpu instensive workqueue */ + WQ_UNBOUND = 1 << 6, /* not bound to any cpu */ WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */ + WQ_MAX_UNBOUND_PER_CPU = 4, /* 4 * #cpus for unbound wq */ WQ_DFL_ACTIVE = WQ_MAX_ACTIVE / 2, }; +/* unbound wq's aren't per-cpu, scale max_active according to #cpus */ +#define WQ_UNBOUND_MAX_ACTIVE \ + max_t(int, WQ_MAX_ACTIVE, num_possible_cpus() * WQ_MAX_UNBOUND_PER_CPU) + /* * System-wide workqueues which are always present. * @@ -256,10 +263,16 @@ enum { * system_nrt_wq is non-reentrant and guarantees that any given work * item is never executed in parallel by multiple CPUs. Queue * flushing might take relatively long. + * + * system_unbound_wq is unbound workqueue. Workers are not bound to + * any specific CPU, not concurrency managed, and all queued works are + * executed immediately as long as max_active limit is not reached and + * resources are available. */ extern struct workqueue_struct *system_wq; extern struct workqueue_struct *system_long_wq; extern struct workqueue_struct *system_nrt_wq; +extern struct workqueue_struct *system_unbound_wq; extern struct workqueue_struct * __alloc_workqueue_key(const char *name, unsigned int flags, int max_active, -- cgit v1.2.3 From c7fc77f78f16d138ca997ce096a62f46e2e9420a Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 2 Jul 2010 10:03:51 +0200 Subject: workqueue: remove WQ_SINGLE_CPU and use WQ_UNBOUND instead WQ_SINGLE_CPU combined with @max_active of 1 is used to achieve full ordering among works queued to a workqueue. The same can be achieved using WQ_UNBOUND as unbound workqueues always use the gcwq for WORK_CPU_UNBOUND. As @max_active is always one and benefits from cpu locality isn't accessible anyway, serving them with unbound workqueues should be fine. Drop WQ_SINGLE_CPU support and use WQ_UNBOUND instead. Note that most single thread workqueue users will be converted to use multithread or non-reentrant instead and only the ones which require strict ordering will keep using WQ_UNBOUND + @max_active of 1. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 67ce734747f6..d74a529ed13e 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -233,12 +233,11 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } enum { WQ_NON_REENTRANT = 1 << 0, /* guarantee non-reentrance */ - WQ_SINGLE_CPU = 1 << 1, /* only single cpu at a time */ + WQ_UNBOUND = 1 << 1, /* not bound to any cpu */ WQ_FREEZEABLE = 1 << 2, /* freeze during suspend */ WQ_RESCUER = 1 << 3, /* has an rescue worker */ WQ_HIGHPRI = 1 << 4, /* high priority */ WQ_CPU_INTENSIVE = 1 << 5, /* cpu instensive workqueue */ - WQ_UNBOUND = 1 << 6, /* not bound to any cpu */ WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */ WQ_MAX_UNBOUND_PER_CPU = 4, /* 4 * #cpus for unbound wq */ @@ -300,9 +299,9 @@ __alloc_workqueue_key(const char *name, unsigned int flags, int max_active, #define create_workqueue(name) \ alloc_workqueue((name), WQ_RESCUER, 1) #define create_freezeable_workqueue(name) \ - alloc_workqueue((name), WQ_FREEZEABLE | WQ_SINGLE_CPU | WQ_RESCUER, 1) + alloc_workqueue((name), WQ_FREEZEABLE | WQ_UNBOUND | WQ_RESCUER, 1) #define create_singlethread_workqueue(name) \ - alloc_workqueue((name), WQ_SINGLE_CPU | WQ_RESCUER, 1) + alloc_workqueue((name), WQ_UNBOUND | WQ_RESCUER, 1) extern void destroy_workqueue(struct workqueue_struct *wq); -- cgit v1.2.3 From 3c8e1a84fd6b984a7bce8816db2e3defc57bbfe4 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Wed, 30 Jun 2010 14:27:37 -0600 Subject: spi/spi-gpio: add support for controllers without MISO or MOSI pin There are some boards that do not strictly follow SPI standard and use only 3 wires (SCLK, MOSI or MISO, SS) for connecting some simple auxiliary chips and controls them with GPIO based 'spi controller'. In this configuration the MISO or MOSI line is missing (it is not required if the chip does not transfer any data back to host or host only reads data from chip). This patch adds support for such non-standard configuration in GPIO-based SPI controller. It has been tested in configuration without MISO pin. Reviewed-by: Kyungmin Park Signed-off-by: Marek Szyprowski Acked-by: David Brownell Signed-off-by: Grant Likely --- include/linux/spi/spi_gpio.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi_gpio.h b/include/linux/spi/spi_gpio.h index ca6782ee4b9f..369b3d7d5b95 100644 --- a/include/linux/spi/spi_gpio.h +++ b/include/linux/spi/spi_gpio.h @@ -29,11 +29,16 @@ * SPI_GPIO_NO_CHIPSELECT to the controller_data: * .controller_data = (void *) SPI_GPIO_NO_CHIPSELECT; * + * If the MISO or MOSI pin is not available then it should be set to + * SPI_GPIO_NO_MISO or SPI_GPIO_NO_MOSI. + * * If the bitbanged bus is later switched to a "native" controller, * that platform_device and controller_data should be removed. */ #define SPI_GPIO_NO_CHIPSELECT ((unsigned long)-1l) +#define SPI_GPIO_NO_MISO ((unsigned long)-1l) +#define SPI_GPIO_NO_MOSI ((unsigned long)-1l) /** * struct spi_gpio_platform_data - parameter for bitbanged SPI master -- cgit v1.2.3 From 7adde04a2f5a798f04a556dfb3b69bff388e5dc4 Mon Sep 17 00:00:00 2001 From: Xiaotian Feng Date: Wed, 30 Jun 2010 17:57:22 +0800 Subject: slab: fix caller tracking on !CONFIG_DEBUG_SLAB && CONFIG_TRACING In slab, all __xxx_track_caller is defined on CONFIG_DEBUG_SLAB || CONFIG_TRACING, thus caller tracking function should be worked for CONFIG_TRACING. But if CONFIG_DEBUG_SLAB is not set, include/linux/slab.h will define xxx_track_caller to __xxx() without consideration of CONFIG_TRACING. This will break the caller tracking behaviour then. Cc: Christoph Lameter Cc: Matt Mackall Cc: Vegard Nossum Cc: Dmitry Monakhov Cc: Catalin Marinas Acked-by: David Rientjes Signed-off-by: Xiaotian Feng Signed-off-by: Pekka Enberg --- include/linux/slab.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 49d1247cd6d9..59260e21bdf5 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -268,7 +268,8 @@ static inline void *kmem_cache_alloc_node(struct kmem_cache *cachep, * allocator where we care about the real place the memory allocation * request comes from. */ -#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_SLUB) +#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_SLUB) || \ + (defined(CONFIG_SLAB) && defined(CONFIG_TRACING)) extern void *__kmalloc_track_caller(size_t, gfp_t, unsigned long); #define kmalloc_track_caller(size, flags) \ __kmalloc_track_caller(size, flags, _RET_IP_) @@ -286,7 +287,8 @@ extern void *__kmalloc_track_caller(size_t, gfp_t, unsigned long); * standard allocator where we care about the real place the memory * allocation request comes from. */ -#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_SLUB) +#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_SLUB) || \ + (defined(CONFIG_SLAB) && defined(CONFIG_TRACING)) extern void *__kmalloc_node_track_caller(size_t, gfp_t, int, unsigned long); #define kmalloc_node_track_caller(size, flags, node) \ __kmalloc_node_track_caller(size, flags, node, \ -- cgit v1.2.3 From 7dc2e1134a22dc242175d5321c0c9e97d16eb87b Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Tue, 8 Jun 2010 07:48:06 -0600 Subject: of/irq: merge irq mapping code Merge common irq mapping code between PowerPC and Microblaze. This patch merges of_irq_find_parent(), of_irq_map_raw() and of_irq_map_one(). The functions are dependent on one another, so all three are merged in a single patch. Other than cosmetic difference (ie. DBG() vs. pr_debug()), the implementations are identical. of_irq_to_resource() is also merged, but in this case the implementations are different. This patch drops the microblaze version and uses the powerpc implementation unchanged. The microblaze version essentially open-coded irq_of_parse_and_map() which it does not need to do. Therefore the powerpc version is safe to adopt. Signed-off-by: Grant Likely CC: Michal Simek CC: Benjamin Herrenschmidt CC: Stephen Rothwell --- include/linux/of_irq.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h index 0e37c05b7dd8..5929781c104d 100644 --- a/include/linux/of_irq.h +++ b/include/linux/of_irq.h @@ -4,6 +4,8 @@ #if defined(CONFIG_OF) struct of_irq; #include +#include +#include #include /* @@ -30,11 +32,38 @@ struct of_irq { u32 specifier[OF_MAX_IRQ_SPEC]; /* Specifier copy */ }; +/* + * Workarounds only applied to 32bit powermac machines + */ +#define OF_IMAP_OLDWORLD_MAC 0x00000001 +#define OF_IMAP_NO_PHANDLE 0x00000002 + +#if defined(CONFIG_PPC32) && defined(CONFIG_PPC_PMAC) +extern unsigned int of_irq_workarounds; +extern struct device_node *of_irq_dflt_pic; +extern int of_irq_map_oldworld(struct device_node *device, int index, + struct of_irq *out_irq); +#else /* CONFIG_PPC32 && CONFIG_PPC_PMAC */ +#define of_irq_workarounds (0) +#define of_irq_dflt_pic (NULL) +static inline int of_irq_map_oldworld(struct device_node *device, int index, + struct of_irq *out_irq) +{ + return -EINVAL; +} +#endif /* CONFIG_PPC32 && CONFIG_PPC_PMAC */ + + +extern int of_irq_map_raw(struct device_node *parent, const u32 *intspec, + u32 ointsize, const u32 *addr, + struct of_irq *out_irq); extern int of_irq_map_one(struct device_node *device, int index, struct of_irq *out_irq); extern unsigned int irq_create_of_mapping(struct device_node *controller, const u32 *intspec, unsigned int intsize); +extern int of_irq_to_resource(struct device_node *dev, int index, + struct resource *r); #endif /* CONFIG_OF_IRQ */ #endif /* CONFIG_OF */ -- cgit v1.2.3 From 6b884a8d50a6eea2fb3dad7befe748f67193073b Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Tue, 8 Jun 2010 07:48:09 -0600 Subject: of/address: merge of_iomap() Merge common code between Microblaze and PowerPC. This patch creates new of_address.h and address.c files to containing address translation and mapping routines. First routine to be moved it of_iomap() Signed-off-by: Grant Likely Acked-by: Benjamin Herrenschmidt CC: Michal Simek CC: Stephen Rothwell --- include/linux/of_address.h | 9 +++++++++ 1 file changed, 9 insertions(+) create mode 100644 include/linux/of_address.h (limited to 'include/linux') diff --git a/include/linux/of_address.h b/include/linux/of_address.h new file mode 100644 index 000000000000..570831d7e795 --- /dev/null +++ b/include/linux/of_address.h @@ -0,0 +1,9 @@ +#ifndef __OF_ADDRESS_H +#define __OF_ADDRESS_H +#include +#include + +extern void __iomem *of_iomap(struct device_node *device, int index); + +#endif /* __OF_ADDRESS_H */ + -- cgit v1.2.3 From 1f5bef30cf6c66f097ea5dfc580a41924df888d1 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Tue, 8 Jun 2010 07:48:09 -0600 Subject: of/address: merge of_address_to_resource() Merge common code between PowerPC and Microblaze. This patch also moves the prototype of pci_address_to_pio() out of pci-bridge.h and into prom.h because the only user of pci_address_to_pio() is of_address_to_resource(). Signed-off-by: Grant Likely Acked-by: Benjamin Herrenschmidt CC: Michal Simek CC: Stephen Rothwell --- include/linux/of_address.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_address.h b/include/linux/of_address.h index 570831d7e795..474b794ed9d2 100644 --- a/include/linux/of_address.h +++ b/include/linux/of_address.h @@ -3,6 +3,11 @@ #include #include +extern int __of_address_to_resource(struct device_node *dev, const u32 *addrp, + u64 size, unsigned int flags, + struct resource *r); +extern int of_address_to_resource(struct device_node *dev, int index, + struct resource *r); extern void __iomem *of_iomap(struct device_node *device, int index); #endif /* __OF_ADDRESS_H */ -- cgit v1.2.3 From dbbdee94734bf6f1db7af42008a53655e77cab8f Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Tue, 8 Jun 2010 07:48:10 -0600 Subject: of/address: Merge all of the bus translation code Microblaze and PowerPC share a large chunk of code for translating OF device tree data into usable addresses. Differences between the two consist of cosmetic differences, and the addition of dma-ranges support code to powerpc but not microblaze. This patch moves the powerpc version into common code and applies many of the cosmetic (non-functional) changes from the microblaze version. Signed-off-by: Grant Likely Acked-by: Benjamin Herrenschmidt CC: Michal Simek CC: Wolfram Sang CC: Stephen Rothwell --- include/linux/of_address.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_address.h b/include/linux/of_address.h index 474b794ed9d2..cc567df9a00d 100644 --- a/include/linux/of_address.h +++ b/include/linux/of_address.h @@ -3,9 +3,7 @@ #include #include -extern int __of_address_to_resource(struct device_node *dev, const u32 *addrp, - u64 size, unsigned int flags, - struct resource *r); +extern u64 of_translate_address(struct device_node *np, const u32 *addr); extern int of_address_to_resource(struct device_node *dev, int index, struct resource *r); extern void __iomem *of_iomap(struct device_node *device, int index); -- cgit v1.2.3 From dd27dcda37f0b1a3b674760fb411abc5c8fe309c Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Tue, 8 Jun 2010 07:48:12 -0600 Subject: of/device: merge of_device_uevent Merge common code between powerpc and microblaze Signed-off-by: Grant Likely CC: Michal Simek CC: Wolfram Sang CC: Stephen Rothwell CC: Benjamin Herrenschmidt CC: microblaze-uclinux@itee.uq.edu.au CC: linuxppc-dev@ozlabs.org --- include/linux/of_device.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_device.h b/include/linux/of_device.h index a3ae5900fc58..da83e734c026 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -44,6 +44,10 @@ static inline void of_device_free(struct of_device *dev) extern ssize_t of_device_get_modalias(struct of_device *ofdev, char *str, ssize_t len); + +extern int of_device_uevent(struct device *dev, struct kobj_uevent_env *env); + + #endif /* CONFIG_OF_DEVICE */ #endif /* _LINUX_OF_DEVICE_H */ -- cgit v1.2.3 From 34a1c1e8c700f7cd849deb21193718a172722f8d Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Tue, 8 Jun 2010 07:48:13 -0600 Subject: of: Modify of_device_get_modalias to be passed struct device Now that the of_node pointer is part of struct device, of_device_get_modalias could be used on any struct device that has the device node pointer set. This patch changes of_device_get_modalias to accept a struct device instead of a struct of_device. Signed-off-by: Grant Likely CC: Michal Simek CC: Benjamin Herrenschmidt CC: Wolfram Sang CC: Stephen Rothwell CC: microblaze-uclinux@itee.uq.edu.au CC: linuxppc-dev@ozlabs.org --- include/linux/of_device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/of_device.h b/include/linux/of_device.h index da83e734c026..238e92e007e6 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -42,7 +42,7 @@ static inline void of_device_free(struct of_device *dev) of_release_dev(&dev->dev); } -extern ssize_t of_device_get_modalias(struct of_device *ofdev, +extern ssize_t of_device_get_modalias(struct device *dev, char *str, ssize_t len); extern int of_device_uevent(struct device *dev, struct kobj_uevent_env *env); -- cgit v1.2.3 From 5fd200f3b351183b5489cef69961c60af9cead2f Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Tue, 8 Jun 2010 07:48:13 -0600 Subject: of/device: Merge of_platform_bus_probe() Merge common code between PowerPC and microblaze. This patch merges the code that scans the tree and registers devices. The functions merged are of_platform_bus_probe(), of_platform_bus_create(), and of_platform_device_create(). This patch also move the of_default_bus_ids[] table out of a Microblaze header file and makes it non-static. The device ids table isn't merged because powerpc and microblaze use different default data. Signed-off-by: Grant Likely CC: Michal Simek CC: Grant Likely CC: Benjamin Herrenschmidt CC: Stephen Rothwell CC: microblaze-uclinux@itee.uq.edu.au CC: linuxppc-dev@ozlabs.org --- include/linux/of_platform.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index 1643d3761eb4..4bbba41396ef 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -25,6 +25,8 @@ */ extern struct bus_type of_platform_bus_type; +extern const struct of_device_id of_default_bus_ids[]; + /* * An of_platform_driver driver is attached to a basic of_device on * the "platform bus" (of_platform_bus_type). @@ -63,6 +65,21 @@ static inline void of_unregister_platform_driver(struct of_platform_driver *drv) extern struct of_device *of_find_device_by_node(struct device_node *np); extern int of_bus_type_init(struct bus_type *bus, const char *name); + +#if !defined(CONFIG_SPARC) /* SPARC has its own device registration method */ +/* Platform devices and busses creation */ +extern struct of_device *of_platform_device_create(struct device_node *np, + const char *bus_id, + struct device *parent); + +/* pseudo "matches" value to not do deep probe */ +#define OF_NO_DEEP_PROBE ((struct of_device_id *)-1) + +extern int of_platform_bus_probe(struct device_node *root, + const struct of_device_id *matches, + struct device *parent); +#endif /* !CONFIG_SPARC */ + #endif /* CONFIG_OF_DEVICE */ #endif /* _LINUX_OF_PLATFORM_H */ -- cgit v1.2.3 From 94c0931983ee9d1cd96c32d52ac64c17464f0bbd Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Tue, 8 Jun 2010 07:48:14 -0600 Subject: of: Merge of_device_alloc() and of_device_make_bus_id() This patch merges the common routines of_device_alloc() and of_device_make_bus_id() from powerpc and microblaze. Signed-off-by: Grant Likely CC: Michal Simek CC: Grant Likely CC: Benjamin Herrenschmidt CC: Stephen Rothwell CC: microblaze-uclinux@itee.uq.edu.au CC: linuxppc-dev@ozlabs.org CC: devicetree-discuss@lists.ozlabs.org --- include/linux/of_platform.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index 4bbba41396ef..a51fd30176aa 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -60,6 +60,9 @@ static inline void of_unregister_platform_driver(struct of_platform_driver *drv) of_unregister_driver(drv); } +extern struct of_device *of_device_alloc(struct device_node *np, + const char *bus_id, + struct device *parent); #include extern struct of_device *of_find_device_by_node(struct device_node *np); -- cgit v1.2.3 From a19e3da5bc5fc6c10ab73f310bea80f3845b4531 Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Tue, 8 Jun 2010 07:48:16 -0600 Subject: of/gpio: Kill of_gpio_chip and add members directly to gpio_chip The OF gpio infrastructure is great for describing GPIO connections within the device tree. However, using a GPIO binding still requires changes to the gpio controller just to add an of_gpio structure. In most cases, the gpio controller doesn't actually need any special support and the simple OF gpio mapping function is more than sufficient. Additional, the current scheme of using of_gpio_chip requires a convoluted scheme to maintain 1:1 mappings between of_gpio_chip and gpio_chip instances. If the struct of_gpio_chip data members were moved into struct gpio_chip, then it would simplify the processing of OF gpio bindings, and it would make it trivial to use device tree OF connections on existing gpiolib controller drivers. This patch eliminates the of_gpio_chip structure and moves the relevant fields into struct gpio_chip (conditional on CONFIG_OF_GPIO). This move simplifies the existing code and prepares for adding automatic device tree support to existing drivers. Signed-off-by: Grant Likely Cc: Andrew Morton Cc: Anton Vorontsov Cc: Grant Likely Cc: David Brownell Cc: Bill Gatliff Cc: Dmitry Eremin-Solenikov Cc: Benjamin Herrenschmidt Cc: Jean Delvare --- include/linux/of_gpio.h | 29 +++++------------------------ 1 file changed, 5 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_gpio.h b/include/linux/of_gpio.h index fc2472c3c254..460d6810c5eb 100644 --- a/include/linux/of_gpio.h +++ b/include/linux/of_gpio.h @@ -32,35 +32,18 @@ enum of_gpio_flags { #ifdef CONFIG_OF_GPIO -/* - * Generic OF GPIO chip - */ -struct of_gpio_chip { - struct gpio_chip gc; - int gpio_cells; - int (*xlate)(struct of_gpio_chip *of_gc, struct device_node *np, - const void *gpio_spec, enum of_gpio_flags *flags); -}; - -static inline struct of_gpio_chip *to_of_gpio_chip(struct gpio_chip *gc) -{ - return container_of(gc, struct of_gpio_chip, gc); -} - /* * OF GPIO chip for memory mapped banks */ struct of_mm_gpio_chip { - struct of_gpio_chip of_gc; + struct gpio_chip gc; void (*save_regs)(struct of_mm_gpio_chip *mm_gc); void __iomem *regs; }; static inline struct of_mm_gpio_chip *to_of_mm_gpio_chip(struct gpio_chip *gc) { - struct of_gpio_chip *of_gc = to_of_gpio_chip(gc); - - return container_of(of_gc, struct of_mm_gpio_chip, of_gc); + return container_of(gc, struct of_mm_gpio_chip, gc); } extern int of_get_gpio_flags(struct device_node *np, int index, @@ -69,11 +52,9 @@ extern unsigned int of_gpio_count(struct device_node *np); extern int of_mm_gpiochip_add(struct device_node *np, struct of_mm_gpio_chip *mm_gc); -extern int of_gpio_simple_xlate(struct of_gpio_chip *of_gc, - struct device_node *np, - const void *gpio_spec, - enum of_gpio_flags *flags); -#else +extern int of_gpio_simple_xlate(struct gpio_chip *gc, struct device_node *np, + const void *gpio_spec, u32 *flags); +#else /* CONFIG_OF_GPIO */ /* Drivers may not strictly depend on the GPIO support, so let them link. */ static inline int of_get_gpio_flags(struct device_node *np, int index, -- cgit v1.2.3 From 594fa265e084073443390c5b93d5410fd28e9bcd Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Tue, 8 Jun 2010 07:48:16 -0600 Subject: of/gpio: stop using device_node data pointer to find gpio_chip Currently the kernel uses the struct device_node.data pointer to resolve a struct gpio_chip pointer from a device tree node. However, the .data member doesn't provide any type checking and there aren't any rules enforced on what it should be used for. There's no guarantee that the data stored in it actually points to an gpio_chip pointer. Instead of relying on the .data pointer, this patch modifies the code to add a lookup function which scans through the registered gpio_chips and returns the gpio_chip that has a pointer to the specified device_node. Signed-off-by: Grant Likely CC: Andrew Morton CC: Anton Vorontsov CC: Grant Likely CC: David Brownell CC: Bill Gatliff CC: Dmitry Eremin-Solenikov CC: Benjamin Herrenschmidt CC: Jean Delvare CC: linux-kernel@vger.kernel.org CC: devicetree-discuss@lists.ozlabs.org --- include/linux/of_gpio.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_gpio.h b/include/linux/of_gpio.h index 460d6810c5eb..1020587efed1 100644 --- a/include/linux/of_gpio.h +++ b/include/linux/of_gpio.h @@ -54,6 +54,9 @@ extern int of_mm_gpiochip_add(struct device_node *np, struct of_mm_gpio_chip *mm_gc); extern int of_gpio_simple_xlate(struct gpio_chip *gc, struct device_node *np, const void *gpio_spec, u32 *flags); + +extern struct gpio_chip *of_node_to_gpiochip(struct device_node *np); + #else /* CONFIG_OF_GPIO */ /* Drivers may not strictly depend on the GPIO support, so let them link. */ -- cgit v1.2.3 From 391c970c0dd1100e3b9e1681f7d0f20aac35455a Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Tue, 8 Jun 2010 07:48:17 -0600 Subject: of/gpio: add default of_xlate function if device has a node pointer Implement generic OF gpio hooks and thus make device-enabled GPIO chips (i.e. the ones that have gpio_chip->dev specified) automatically attach to the OpenFirmware subsystem. Which means that now we can handle I2C and SPI GPIO chips almost* transparently. * "Almost" because some chips still require platform data, and for these chips OF-glue is still needed, though with this change the glue will be much smaller. Signed-off-by: Anton Vorontsov Signed-off-by: Grant Likely Cc: David Brownell Cc: Bill Gatliff Cc: Dmitry Eremin-Solenikov Cc: Benjamin Herrenschmidt Cc: Jean Delvare Cc: Andrew Morton CC: linux-kernel@vger.kernel.org CC: devicetree-discuss@lists.ozlabs.org --- include/linux/of_gpio.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_gpio.h b/include/linux/of_gpio.h index 1020587efed1..6598c04dab01 100644 --- a/include/linux/of_gpio.h +++ b/include/linux/of_gpio.h @@ -52,9 +52,9 @@ extern unsigned int of_gpio_count(struct device_node *np); extern int of_mm_gpiochip_add(struct device_node *np, struct of_mm_gpio_chip *mm_gc); -extern int of_gpio_simple_xlate(struct gpio_chip *gc, struct device_node *np, - const void *gpio_spec, u32 *flags); +extern void of_gpiochip_add(struct gpio_chip *gc); +extern void of_gpiochip_remove(struct gpio_chip *gc); extern struct gpio_chip *of_node_to_gpiochip(struct device_node *np); #else /* CONFIG_OF_GPIO */ @@ -71,6 +71,9 @@ static inline unsigned int of_gpio_count(struct device_node *np) return 0; } +static inline void of_gpiochip_add(struct gpio_chip *gc) { } +static inline void of_gpiochip_remove(struct gpio_chip *gc) { } + #endif /* CONFIG_OF_GPIO */ /** -- cgit v1.2.3 From 8cec0e7b4c7c0b76f2b5285f250211ad81c3eafd Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Tue, 8 Jun 2010 07:48:17 -0600 Subject: of/device: Add OF style matching helper function Add of_driver_match_device() helper function. This function can be used by bus types to determine if a driver works with a device when using OF style matching. If CONFIG_OF is unselected, then it is a nop. Signed-off-by: Grant Likely CC: Greg Kroah-Hartman CC: Michal Simek CC: Grant Likely CC: Benjamin Herrenschmidt CC: Stephen Rothwell CC: linux-kernel@vger.kernel.org CC: microblaze-uclinux@itee.uq.edu.au CC: linuxppc-dev@ozlabs.org CC: devicetree-discuss@lists.ozlabs.org --- include/linux/of_device.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_device.h b/include/linux/of_device.h index 238e92e007e6..91d75fb0c726 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -30,6 +30,17 @@ extern const struct of_device_id *of_match_device( const struct of_device_id *matches, const struct device *dev); +/** + * of_driver_match_device - Tell if a driver's of_match_table matches a device. + * @drv: the device_driver structure to test + * @dev: the device structure to match against + */ +static inline int of_driver_match_device(const struct device *dev, + const struct device_driver *drv) +{ + return of_match_device(drv->of_match_table, dev) != NULL; +} + extern struct of_device *of_dev_get(struct of_device *dev); extern void of_dev_put(struct of_device *dev); @@ -48,6 +59,14 @@ extern ssize_t of_device_get_modalias(struct device *dev, extern int of_device_uevent(struct device *dev, struct kobj_uevent_env *env); +#else /* CONFIG_OF_DEVICE */ + +static inline int of_driver_match_device(struct device *dev, + struct device_driver *drv) +{ + return 0; +} + #endif /* CONFIG_OF_DEVICE */ #endif /* _LINUX_OF_DEVICE_H */ -- cgit v1.2.3 From f9f5a4669f1334a558f102c311debfd008e7c2bc Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Wed, 9 Jun 2010 22:22:17 -0600 Subject: of/device: Move struct of_device define outside of CONFIG_OF_DEVICE test Some code uses of_device even when CONFIG_OF_DEVICE is not set. This patch makes of_device valid all the time by moving it outside of the ifdef CONFIG_OF_DEVICE test. Reported-by: Randy Dunlap Signed-off-by: Grant Likely Acked-by: Randy Dunlap --- include/linux/of_device.h | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_device.h b/include/linux/of_device.h index 91d75fb0c726..7d27f5a878f6 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -1,13 +1,6 @@ #ifndef _LINUX_OF_DEVICE_H #define _LINUX_OF_DEVICE_H -#ifdef CONFIG_OF_DEVICE -#include -#include -#include -#include - - /* * The of_device *was* a kind of "base class" that was a superset of * struct device for use by devices attached to an OF node and probed @@ -22,7 +15,12 @@ * from the kernel. */ #define of_device platform_device +#include +#ifdef CONFIG_OF_DEVICE +#include +#include +#include #include #define to_of_device(d) container_of(d, struct of_device, dev) -- cgit v1.2.3 From 9fd049927ccba1c1d0343239b82f28c4e07fb95d Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Tue, 8 Jun 2010 07:48:18 -0600 Subject: of/i2c: Generalize OF support This patch cleans up the i2c OF support code to make it selectable by all architectures and allow for automatic registration of i2c devices. Signed-off-by: Grant Likely --- include/linux/of_i2c.h | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_i2c.h b/include/linux/of_i2c.h index 34974b5a76f7..0efe8d465f55 100644 --- a/include/linux/of_i2c.h +++ b/include/linux/of_i2c.h @@ -12,12 +12,19 @@ #ifndef __LINUX_OF_I2C_H #define __LINUX_OF_I2C_H +#if defined(CONFIG_OF_I2C) || defined(CONFIG_OF_I2C_MODULE) #include -void of_register_i2c_devices(struct i2c_adapter *adap, - struct device_node *adap_node); +extern void of_i2c_register_devices(struct i2c_adapter *adap); /* must call put_device() when done with returned i2c_client device */ -struct i2c_client *of_find_i2c_device_by_node(struct device_node *node); +extern struct i2c_client *of_find_i2c_device_by_node(struct device_node *node); + +#else +static inline void of_i2c_register_devices(struct i2c_adapter *adap) +{ + return; +} +#endif /* CONFIG_OF_I2C */ #endif /* __LINUX_OF_I2C_H */ -- cgit v1.2.3 From 8eab945c5616fc984e97b922d6a2559be93f39a1 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Thu, 1 Jul 2010 18:05:56 +0300 Subject: sunrpc: make the cache cleaner workqueue deferrable This patch makes the cache_cleaner workqueue deferrable, to prevent unnecessary system wake-ups, which is very important for embedded battery-powered devices. do_cache_clean() is called every 30 seconds at the moment, and often makes the system wake up from its power-save sleep state. With this change, when the workqueue uses a deferrable timer, the do_cache_clean() invocation will be delayed and combined with the closest "real" wake-up. This improves the power consumption situation. Note, I tried to create a DECLARE_DELAYED_WORK_DEFERRABLE() helper macro, similar to DECLARE_DELAYED_WORK(), but failed because of the way the timer wheel core stores the deferrable flag (it is the LSBit in the time->base pointer). My attempt to define a static variable with this bit set ended up with the "initializer element is not constant" error. Thus, I have to use run-time initialization, so I created a new cache_initialize() function which is called once when sunrpc is being initialized. Signed-off-by: Artem Bityutskiy Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/cache.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index 6f52b4d7c447..7bf3e84b92f4 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -192,6 +192,7 @@ extern int cache_check(struct cache_detail *detail, extern void cache_flush(void); extern void cache_purge(struct cache_detail *detail); #define NEVER (0x7FFFFFFF) +extern void __init cache_initialize(void); extern int cache_register(struct cache_detail *cd); extern void cache_unregister(struct cache_detail *cd); -- cgit v1.2.3 From de5d9bf6541736dc7ad264d2b5cc99bc1b2ad958 Mon Sep 17 00:00:00 2001 From: Chris Metcalf Date: Fri, 2 Jul 2010 13:41:14 -0400 Subject: Move list types from to . This allows a list_head (or hlist_head, etc.) to be used from places that used to be impractical, in particular , which used to cause include file recursion: includes , which always includes for the prefetch macros, as well as , which often includes directly or indirectly. This avoids a lot of painful workaround hackery on the tile architecture, where we use a list_head in the thread_struct to chain together tasks that are activated on a particular hardwall. Signed-off-by: Chris Metcalf Reviewed-by: Matthew Wilcox --- include/linux/list.h | 13 +------------ include/linux/types.h | 12 ++++++++++++ 2 files changed, 13 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/list.h b/include/linux/list.h index 8392884a2977..bc43e8a0d7f6 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -1,6 +1,7 @@ #ifndef _LINUX_LIST_H #define _LINUX_LIST_H +#include #include #include #include @@ -16,10 +17,6 @@ * using the generic single-entry routines. */ -struct list_head { - struct list_head *next, *prev; -}; - #define LIST_HEAD_INIT(name) { &(name), &(name) } #define LIST_HEAD(name) \ @@ -551,14 +548,6 @@ static inline void list_splice_tail_init(struct list_head *list, * You lose the ability to access the tail in O(1). */ -struct hlist_head { - struct hlist_node *first; -}; - -struct hlist_node { - struct hlist_node *next, **pprev; -}; - #define HLIST_HEAD_INIT { .first = NULL } #define HLIST_HEAD(name) struct hlist_head name = { .first = NULL } #define INIT_HLIST_HEAD(ptr) ((ptr)->first = NULL) diff --git a/include/linux/types.h b/include/linux/types.h index 23d237a075e2..336cc39c46f1 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -197,6 +197,18 @@ typedef struct { } atomic64_t; #endif +struct list_head { + struct list_head *next, *prev; +}; + +struct hlist_head { + struct hlist_node *first; +}; + +struct hlist_node { + struct hlist_node *next, **pprev; +}; + struct ustat { __kernel_daddr_t f_tfree; __kernel_ino_t f_tinode; -- cgit v1.2.3 From 250b2b6dd421c9f8844a867d2ac06e0661e0ad93 Mon Sep 17 00:00:00 2001 From: Stefan Richter Date: Mon, 21 Jun 2010 23:24:35 +0200 Subject: firewire: cdev: fix fw_cdev_event_bus_reset.bm_node_id Fix an obscure ABI feature that is a bit of a hassle to implement. However, somebody put it into the ABI, so let's fill in a sensible value there. Signed-off-by: Stefan Richter --- include/linux/firewire-cdev.h | 5 +++++ include/linux/firewire.h | 1 + 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/firewire-cdev.h b/include/linux/firewire-cdev.h index 8b9b27373219..d31022b05bd9 100644 --- a/include/linux/firewire-cdev.h +++ b/include/linux/firewire-cdev.h @@ -66,6 +66,10 @@ struct fw_cdev_event_common { * This event is sent when the bus the device belongs to goes through a bus * reset. It provides information about the new bus configuration, such as * new node ID for this device, new root ID, and others. + * + * If @bm_node_id is 0xffff right after bus reset it can be reread by an + * %FW_CDEV_IOC_GET_INFO ioctl after bus manager selection was finished. + * Kernels with ABI version < 4 do not set @bm_node_id. */ struct fw_cdev_event_bus_reset { __u64 closure; @@ -348,6 +352,7 @@ union fw_cdev_event { * 3 (2.6.34) - made &fw_cdev_get_cycle_timer reliable * - added %FW_CDEV_IOC_GET_CYCLE_TIMER2 * 4 (2.6.36) - added %FW_CDEV_EVENT_REQUEST2 + * - implemented &fw_cdev_event_bus_reset.bm_node_id */ #define FW_CDEV_VERSION 3 /* Meaningless; don't use this macro. */ diff --git a/include/linux/firewire.h b/include/linux/firewire.h index e44b502c8341..db30a752a87a 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -119,6 +119,7 @@ struct fw_card { int bm_retries; int bm_generation; __be32 bm_transaction_data[2]; + int bm_node_id; bool bm_abdicate; bool priority_budget_implemented; /* controller feature */ -- cgit v1.2.3 From ffa71f33a820d1ab3f2fc5723819ac60fb76080b Mon Sep 17 00:00:00 2001 From: Kenji Kaneshige Date: Fri, 18 Jun 2010 12:22:40 +0900 Subject: x86, ioremap: Fix incorrect physical address handling in PAE mode Current x86 ioremap() doesn't handle physical address higher than 32-bit properly in X86_32 PAE mode. When physical address higher than 32-bit is passed to ioremap(), higher 32-bits in physical address is cleared wrongly. Due to this bug, ioremap() can map wrong address to linear address space. In my case, 64-bit MMIO region was assigned to a PCI device (ioat device) on my system. Because of the ioremap()'s bug, wrong physical address (instead of MMIO region) was mapped to linear address space. Because of this, loading ioatdma driver caused unexpected behavior (kernel panic, kernel hangup, ...). Signed-off-by: Kenji Kaneshige LKML-Reference: <4C1AE680.7090408@jp.fujitsu.com> Signed-off-by: H. Peter Anvin --- include/linux/io.h | 4 ++-- include/linux/vmalloc.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/io.h b/include/linux/io.h index 6c7f0ba0d5fa..7fd2d2138bf3 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -29,10 +29,10 @@ void __iowrite64_copy(void __iomem *to, const void *from, size_t count); #ifdef CONFIG_MMU int ioremap_page_range(unsigned long addr, unsigned long end, - unsigned long phys_addr, pgprot_t prot); + phys_addr_t phys_addr, pgprot_t prot); #else static inline int ioremap_page_range(unsigned long addr, unsigned long end, - unsigned long phys_addr, pgprot_t prot) + phys_addr_t phys_addr, pgprot_t prot) { return 0; } diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 227c2a585e4f..de05e96e0a70 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -30,7 +30,7 @@ struct vm_struct { unsigned long flags; struct page **pages; unsigned int nr_pages; - unsigned long phys_addr; + phys_addr_t phys_addr; void *caller; }; -- cgit v1.2.3 From a1d75f258230b75d46aecdf28b2e732413028863 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Mon, 12 Jul 2010 14:41:40 +0200 Subject: fuse: add store request Userspace filesystem can request data to be stored in the inode's mapping. This request is synchronous and has no reply. If the write to the fuse device returns an error then the store request was not fully completed (but may have updated some pages). If the stored data overflows the current file size, then the size is extended, similarly to a write(2) on the filesystem. Pages which have been completely stored are marked uptodate. Signed-off-by: Miklos Szeredi --- include/linux/fuse.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fuse.h b/include/linux/fuse.h index 88e0eb596919..a90bd49834aa 100644 --- a/include/linux/fuse.h +++ b/include/linux/fuse.h @@ -37,6 +37,9 @@ * * 7.14 * - add splice support to fuse device + * + * 7.15 + * - add store notify */ #ifndef _LINUX_FUSE_H @@ -68,7 +71,7 @@ #define FUSE_KERNEL_VERSION 7 /** Minor version number of this interface */ -#define FUSE_KERNEL_MINOR_VERSION 14 +#define FUSE_KERNEL_MINOR_VERSION 15 /** The node ID of the root inode */ #define FUSE_ROOT_ID 1 @@ -260,6 +263,7 @@ enum fuse_notify_code { FUSE_NOTIFY_POLL = 1, FUSE_NOTIFY_INVAL_INODE = 2, FUSE_NOTIFY_INVAL_ENTRY = 3, + FUSE_NOTIFY_STORE = 4, FUSE_NOTIFY_CODE_MAX, }; @@ -568,4 +572,11 @@ struct fuse_notify_inval_entry_out { __u32 padding; }; +struct fuse_notify_store_out { + __u64 nodeid; + __u64 offset; + __u32 size; + __u32 padding; +}; + #endif /* _LINUX_FUSE_H */ -- cgit v1.2.3 From 2d45ba381a74a743eeaa2b06c7c5c0d2bf73ba1a Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Mon, 12 Jul 2010 14:41:40 +0200 Subject: fuse: add retrieve request Userspace filesystem can request data to be retrieved from the inode's mapping. This request is synchronous and the retrieved data is queued as a new request. If the write to the fuse device returns an error then the retrieve request was not completed and a reply will not be sent. Only present pages are returned in the retrieve reply. Retrieving stops when it finds a non-present page and only data prior to that is returned. This request doesn't change the dirty state of pages. Signed-off-by: Miklos Szeredi --- include/linux/fuse.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fuse.h b/include/linux/fuse.h index a90bd49834aa..c3c578e09833 100644 --- a/include/linux/fuse.h +++ b/include/linux/fuse.h @@ -40,6 +40,7 @@ * * 7.15 * - add store notify + * - add retrieve notify */ #ifndef _LINUX_FUSE_H @@ -254,6 +255,7 @@ enum fuse_opcode { FUSE_DESTROY = 38, FUSE_IOCTL = 39, FUSE_POLL = 40, + FUSE_NOTIFY_REPLY = 41, /* CUSE specific operations */ CUSE_INIT = 4096, @@ -264,6 +266,7 @@ enum fuse_notify_code { FUSE_NOTIFY_INVAL_INODE = 2, FUSE_NOTIFY_INVAL_ENTRY = 3, FUSE_NOTIFY_STORE = 4, + FUSE_NOTIFY_RETRIEVE = 5, FUSE_NOTIFY_CODE_MAX, }; @@ -579,4 +582,22 @@ struct fuse_notify_store_out { __u32 padding; }; +struct fuse_notify_retrieve_out { + __u64 notify_unique; + __u64 nodeid; + __u64 offset; + __u32 size; + __u32 padding; +}; + +/* Matches the size of fuse_write_in */ +struct fuse_notify_retrieve_in { + __u64 dummy1; + __u64 offset; + __u32 size; + __u32 dummy2; + __u64 dummy3; + __u64 dummy4; +}; + #endif /* _LINUX_FUSE_H */ -- cgit v1.2.3 From 02d37bed188c500ee7afb0a2dc6b65a80704c58e Mon Sep 17 00:00:00 2001 From: Stefan Richter Date: Thu, 8 Jul 2010 16:09:06 +0200 Subject: firewire: core: integrate software-forced bus resets with bus management Bus resets which are triggered - by the kernel drivers after updates of the local nodes' config ROM, - by userspace software via ioctl shall be deferred until after >=2 seconds after the last bus reset. If multiple modifications of the local nodes' config ROM happen in a row, only a single bus reset should happen after them. When the local node's link goes from inactive to active or vice versa, and at the two occasions of bus resets mentioned above --- and if the current gap count differs from 63 --- the bus reset should be preceded by a PHY configuration packet that reaffirms the gap count. Otherwise a bus manager would have to reset the bus again right after that. This is necessary to promote bus stability, e.g. leave grace periods for allocations and reallocations of isochronous channels and bandwidth, SBP-2 reconnections etc.; see IEEE 1394 clause 8.2.1. This change implements all of the above by moving bus reset initiation into a delayed work (except for bus resets which are triggered by the bus manager workqueue job and are performed there immediately). It comes with a necessary addition to the card driver methods that allows to get the current gap count from PHY registers. Signed-off-by: Stefan Richter --- include/linux/firewire.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firewire.h b/include/linux/firewire.h index db30a752a87a..adc5b55e6e5f 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -114,8 +114,10 @@ struct fw_card { struct list_head link; - /* Work struct for BM duties. */ - struct delayed_work work; + struct delayed_work br_work; /* bus reset job */ + bool br_short; + + struct delayed_work bm_work; /* bus manager job */ int bm_retries; int bm_generation; __be32 bm_transaction_data[2]; -- cgit v1.2.3 From 035ebefc737cce56d3938e9b7eaa5ac0e9c28715 Mon Sep 17 00:00:00 2001 From: Andres Salomon Date: Tue, 13 Jul 2010 09:42:26 +0000 Subject: of/sparc: move is_root_node() to of.h Rename is_root_node() to of_node_is_root() and make it available for all archs to use, as it's not PROM-specific. Signed-off-by: Andres Salomon Acked-by: David S. Miller Signed-off-by: Grant Likely --- include/linux/of.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index a367e19bb3af..b0756f33249e 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -70,6 +70,11 @@ extern struct device_node *allnodes; extern struct device_node *of_chosen; extern rwlock_t devtree_lock; +static inline bool of_node_is_root(const struct device_node *node) +{ + return node && (node->parent == NULL); +} + static inline int of_node_check_flag(struct device_node *n, unsigned long flag) { return test_bit(flag, &n->_flags); -- cgit v1.2.3 From 8fd00b4d7014b00448eb33cf0590815304769798 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Wed, 26 Aug 2009 18:41:16 +0200 Subject: rlimits: security, add task_struct to setrlimit Add task_struct to task_setrlimit of security_operations to be able to set rlimit of task other than current. Signed-off-by: Jiri Slaby Acked-by: Eric Paris Acked-by: James Morris --- include/linux/security.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index 0c8819170463..1a3eb5ff4357 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1501,7 +1501,8 @@ struct security_operations { int (*task_setnice) (struct task_struct *p, int nice); int (*task_setioprio) (struct task_struct *p, int ioprio); int (*task_getioprio) (struct task_struct *p); - int (*task_setrlimit) (unsigned int resource, struct rlimit *new_rlim); + int (*task_setrlimit) (struct task_struct *p, unsigned int resource, + struct rlimit *new_rlim); int (*task_setscheduler) (struct task_struct *p, int policy, struct sched_param *lp); int (*task_getscheduler) (struct task_struct *p); @@ -1751,7 +1752,8 @@ void security_task_getsecid(struct task_struct *p, u32 *secid); int security_task_setnice(struct task_struct *p, int nice); int security_task_setioprio(struct task_struct *p, int ioprio); int security_task_getioprio(struct task_struct *p); -int security_task_setrlimit(unsigned int resource, struct rlimit *new_rlim); +int security_task_setrlimit(struct task_struct *p, unsigned int resource, + struct rlimit *new_rlim); int security_task_setscheduler(struct task_struct *p, int policy, struct sched_param *lp); int security_task_getscheduler(struct task_struct *p); @@ -2313,7 +2315,8 @@ static inline int security_task_getioprio(struct task_struct *p) return 0; } -static inline int security_task_setrlimit(unsigned int resource, +static inline int security_task_setrlimit(struct task_struct *p, + unsigned int resource, struct rlimit *new_rlim) { return 0; -- cgit v1.2.3 From 5ab46b345e418747b3a52f0892680c0745c4223c Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 28 Aug 2009 14:05:12 +0200 Subject: rlimits: add task_struct to update_rlimit_cpu Add task_struct as a parameter to update_rlimit_cpu to be able to set rlimit_cpu of different task than current. Signed-off-by: Jiri Slaby Acked-by: James Morris --- include/linux/posix-timers.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 4f71bf4e628c..3e23844a6990 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -117,6 +117,6 @@ void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx, long clock_nanosleep_restart(struct restart_block *restart_block); -void update_rlimit_cpu(unsigned long rlim_new); +void update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new); #endif -- cgit v1.2.3 From 7855c35da7ba16b389d17710401c4a55a3ea2102 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Wed, 26 Aug 2009 23:45:34 +0200 Subject: rlimits: split sys_setrlimit Create do_setrlimit from sys_setrlimit and declare do_setrlimit in the resource header. This is the first phase to have generic do_prlimit which allows to be called from read, write and compat rlimits code. The new do_setrlimit also accepts a task pointer to change the limits of. Currently, it cannot be other than current, but this will change with locking later. Also pass tsk->group_leader to security_task_setrlimit to check whether current is allowed to change rlimits of the process and not its arbitrary thread because it makes more sense given that rlimit are per process and not per-thread. Signed-off-by: Jiri Slaby --- include/linux/resource.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/resource.h b/include/linux/resource.h index f1e914eefeab..cf8dc96653ee 100644 --- a/include/linux/resource.h +++ b/include/linux/resource.h @@ -73,6 +73,8 @@ struct rlimit { struct task_struct; int getrusage(struct task_struct *p, int who, struct rusage __user *ru); +int do_setrlimit(struct task_struct *tsk, unsigned int resource, + struct rlimit *new_rlim); #endif /* __KERNEL__ */ -- cgit v1.2.3 From 6a1d5e2c85d06da35cdfd93f1a27675bfdc3ad8c Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Wed, 24 Mar 2010 17:06:58 +0100 Subject: rlimits: add rlimit64 structure Add a platform independent structure for resource limits to use with a new prlimit64 syscall. This structure is the same which uses glibc for 64-bit limits. Also add corresponding infinity which is a 64-bit full of bit-ones. Signed-off-by: Jiri Slaby --- include/linux/resource.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/resource.h b/include/linux/resource.h index cf8dc96653ee..037aa7e6335d 100644 --- a/include/linux/resource.h +++ b/include/linux/resource.h @@ -43,6 +43,13 @@ struct rlimit { unsigned long rlim_max; }; +#define RLIM64_INFINITY (~0ULL) + +struct rlimit64 { + __u64 rlim_cur; + __u64 rlim_max; +}; + #define PRIO_MIN (-20) #define PRIO_MAX 20 -- cgit v1.2.3 From 5b41535aac0c07135ff6a4c5c2ae115d1c20c0bc Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Wed, 24 Mar 2010 16:11:29 +0100 Subject: rlimits: redo do_setrlimit to more generic do_prlimit It now allows also reading of limits. I.e. all read and writes will later use this function. It takes two parameters, new and old limits which can be both NULL. If new is non-NULL, the value in it is set to rlimits. If old is non-NULL, current rlimits are stored there. If both are non-NULL, old are stored prior to setting the new ones, atomically. (Similar to sigaction.) Signed-off-by: Jiri Slaby --- include/linux/resource.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/resource.h b/include/linux/resource.h index 037aa7e6335d..88d36f9145ba 100644 --- a/include/linux/resource.h +++ b/include/linux/resource.h @@ -80,8 +80,8 @@ struct rlimit64 { struct task_struct; int getrusage(struct task_struct *p, int who, struct rusage __user *ru); -int do_setrlimit(struct task_struct *tsk, unsigned int resource, - struct rlimit *new_rlim); +int do_prlimit(struct task_struct *tsk, unsigned int resource, + struct rlimit *new_rlim, struct rlimit *old_rlim); #endif /* __KERNEL__ */ -- cgit v1.2.3 From c022a0acad534fd5f5d5f17280f6d4d135e74e81 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Tue, 4 May 2010 18:03:50 +0200 Subject: rlimits: implement prlimit64 syscall This patch adds the code to support the sys_prlimit64 syscall which modifies-and-returns the rlim values of a selected process atomically. The first parameter, pid, being 0 means current process. Unlike the current implementation, it is a generic interface, architecture indepentent so that we needn't handle compat stuff anymore. In the future, after glibc start to use this we can deprecate sys_setrlimit and sys_getrlimit in favor to clean up the code finally. It also adds a possibility of changing limits of other processes. We check the user's permissions to do that and if it succeeds, the new limits are propagated online. This is good for large scale applications such as SAP or databases where administrators need to change limits time by time (e.g. on crashes increase core size). And it is unacceptable to restart the service. For safety, all rlim users now either use accessors or doesn't need them due to - locking - the fact a process was just forked and nobody else knows about it yet (and nobody can't thus read/write limits) hence it is safe to modify limits now. The limitation is that we currently stay at ulong internal representation. So the rlim64_is_infinity check is used where value is compared against ULONG_MAX on 32-bit which is the maximum value there. And since internally the limits are held in struct rlimit, converters which are used before and after do_prlimit call in sys_prlimit64 are introduced. Signed-off-by: Jiri Slaby --- include/linux/syscalls.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 7f614ce274a9..a60943be4270 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -35,6 +35,7 @@ struct oldold_utsname; struct old_utsname; struct pollfd; struct rlimit; +struct rlimit64; struct rusage; struct sched_param; struct sel_arg_struct; @@ -644,6 +645,9 @@ asmlinkage long sys_old_getrlimit(unsigned int resource, struct rlimit __user *r #endif asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim); +asmlinkage long sys_prlimit64(pid_t pid, unsigned int resource, + const struct rlimit64 __user *new_rlim, + struct rlimit64 __user *old_rlim); asmlinkage long sys_getrusage(int who, struct rusage __user *ru); asmlinkage long sys_umask(int mask); -- cgit v1.2.3 From af537b0a6c650ab6ff7104d8163e96866b31c835 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Fri, 9 Jul 2010 14:07:14 -0500 Subject: slub: Use kmem_cache flags to detect if slab is in debugging mode. The cacheline with the flags is reachable from the hot paths after the percpu allocator changes went in. So there is no need anymore to put a flag into each slab page. Get rid of the SlubDebug flag and use the flags in kmem_cache instead. Acked-by: David Rientjes Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/page-flags.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 5b59f35dcb8f..6fa317801e1c 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -128,7 +128,6 @@ enum pageflags { /* SLUB */ PG_slub_frozen = PG_active, - PG_slub_debug = PG_error, }; #ifndef __GENERATING_BOUNDS_H @@ -215,7 +214,6 @@ PAGEFLAG(SwapBacked, swapbacked) __CLEARPAGEFLAG(SwapBacked, swapbacked) __PAGEFLAG(SlobFree, slob_free) __PAGEFLAG(SlubFrozen, slub_frozen) -__PAGEFLAG(SlubDebug, slub_debug) /* * Private page markings that may be used by the filesystem that owns the page -- cgit v1.2.3 From 396e894d289d69bacf5acd983c97cd6e21a14c08 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 9 Jul 2010 15:12:27 +0200 Subject: sched: Revert nohz_ratelimit() for now Norbert reported that nohz_ratelimit() causes his laptop to burn about 4W (40%) extra. For now back out the change and see if we can adjust the power management code to make better decisions. Reported-by: Norbert Preining Signed-off-by: Peter Zijlstra Acked-by: Mike Galbraith Cc: Arjan van de Ven LKML-Reference: Signed-off-by: Ingo Molnar --- include/linux/sched.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 747fcaedddb7..6e0bb86de990 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -273,17 +273,11 @@ extern cpumask_var_t nohz_cpu_mask; #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ) extern int select_nohz_load_balancer(int cpu); extern int get_nohz_load_balancer(void); -extern int nohz_ratelimit(int cpu); #else static inline int select_nohz_load_balancer(int cpu) { return 0; } - -static inline int nohz_ratelimit(int cpu) -{ - return 0; -} #endif /* -- cgit v1.2.3 From 323f99cbc35c52a65dea9d072b3ecf1e662240d2 Mon Sep 17 00:00:00 2001 From: Tom Lyon Date: Fri, 2 Jul 2010 16:56:14 -0400 Subject: iommu-api: Extension to check for interrupt remapping This patch allows IOMMU users to determine whether the hardware and software support safe, isolated interrupt remapping. Not all Intel IOMMUs have the hardware, and the software for AMD is not there yet. Signed-off-by: Tom Lyon Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index be22ad83689c..0a2ba4098996 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -30,6 +30,7 @@ struct iommu_domain { }; #define IOMMU_CAP_CACHE_COHERENCY 0x1 +#define IOMMU_CAP_INTR_REMAP 0x2 /* isolates device intrs */ struct iommu_ops { int (*domain_init)(struct iommu_domain *domain); -- cgit v1.2.3 From eb7beb5c09af75494234ea6acd09d0a647cf7338 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 16 Jul 2010 00:50:03 +0200 Subject: tracing: Remove special traces Special traces type was only used by sysprof. Lets remove it now that sysprof ftrace plugin has been dropped. Signed-off-by: Frederic Weisbecker Acked-by: Soeren Sandmann Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Steven Rostedt Cc: Li Zefan --- include/linux/kernel.h | 5 ----- include/linux/sched.h | 12 ------------ 2 files changed, 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 8317ec4b9f3b..adee958b5989 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -508,9 +508,6 @@ extern void tracing_start(void); extern void tracing_stop(void); extern void ftrace_off_permanent(void); -extern void -ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3); - static inline void __attribute__ ((format (printf, 1, 2))) ____trace_printk_check_format(const char *fmt, ...) { @@ -586,8 +583,6 @@ __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap); extern void ftrace_dump(enum ftrace_dump_mode oops_dump_mode); #else -static inline void -ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) { } static inline int trace_printk(const char *fmt, ...) __attribute__ ((format (printf, 1, 2))); diff --git a/include/linux/sched.h b/include/linux/sched.h index 747fcaedddb7..f751ea9dcb7b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2434,18 +2434,6 @@ static inline void set_task_cpu(struct task_struct *p, unsigned int cpu) #endif /* CONFIG_SMP */ -#ifdef CONFIG_TRACING -extern void -__trace_special(void *__tr, void *__data, - unsigned long arg1, unsigned long arg2, unsigned long arg3); -#else -static inline void -__trace_special(void *__tr, void *__data, - unsigned long arg1, unsigned long arg2, unsigned long arg3) -{ -} -#endif - extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask); extern long sched_getaffinity(pid_t pid, struct cpumask *mask); -- cgit v1.2.3 From e870e9a1240bcef1157ffaaf71dac63362e71904 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Fri, 2 Jul 2010 11:07:32 +0800 Subject: tracing: Allow to disable cmdline recording We found that even enabling a single trace event that will rarely be triggered can add big overhead to context switch. (lmbench context switch test) ------------------------------------------------- 2p/0K 2p/16K 2p/64K 8p/16K 8p/64K 16p/16K 16p/64K ctxsw ctxsw ctxsw ctxsw ctxsw ctxsw ctxsw ------ ------ ------ ------ ------ ------- ------- 2.19 2.3 2.21 2.56 2.13 2.54 2.07 2.39 2.51 2.35 2.75 2.27 2.81 2.24 The overhead is 6% ~ 11%. It's because when a trace event is enabled 3 tracepoints (sched_switch, sched_wakeup, sched_wakeup_new) will be activated to map pid to cmdname. We'd like to avoid this overhead, so add a trace option '(no)record-cmd' to allow to disable cmdline recording. Signed-off-by: Li Zefan LKML-Reference: <4C2D57F4.2050204@cn.fujitsu.com> Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 01df7ca4ead7..2b7b1395b4d5 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -152,11 +152,13 @@ extern int ftrace_event_reg(struct ftrace_event_call *event, enum { TRACE_EVENT_FL_ENABLED_BIT, TRACE_EVENT_FL_FILTERED_BIT, + TRACE_EVENT_FL_RECORDED_CMD_BIT, }; enum { - TRACE_EVENT_FL_ENABLED = (1 << TRACE_EVENT_FL_ENABLED_BIT), - TRACE_EVENT_FL_FILTERED = (1 << TRACE_EVENT_FL_FILTERED_BIT), + TRACE_EVENT_FL_ENABLED = (1 << TRACE_EVENT_FL_ENABLED_BIT), + TRACE_EVENT_FL_FILTERED = (1 << TRACE_EVENT_FL_FILTERED_BIT), + TRACE_EVENT_FL_RECORDED_CMD = (1 << TRACE_EVENT_FL_RECORDED_CMD_BIT), }; struct ftrace_event_call { @@ -174,6 +176,7 @@ struct ftrace_event_call { * 32 bit flags: * bit 1: enabled * bit 2: filter_active + * bit 3: enabled cmd record * * Changes to flags must hold the event_mutex. * -- cgit v1.2.3 From bc289ae98b75d93228d24f521ef02a076e506e94 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Thu, 3 Jun 2010 18:26:24 +0800 Subject: tracing: Reduce latency and remove percpu trace_seq __print_flags() and __print_symbolic() use percpu trace_seq: 1) Its memory is allocated at compile time, it wastes memory if we don't use tracing. 2) It is percpu data and it wastes more memory for multi-cpus system. 3) It disables preemption when it executes its core routine "trace_seq_printf(s, "%s: ", #call);" and introduces latency. So we move this trace_seq to struct trace_iterator. Signed-off-by: Lai Jiangshan LKML-Reference: <4C078350.7090106@cn.fujitsu.com> Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 2b7b1395b4d5..02b8b24f8f51 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -11,8 +11,6 @@ struct trace_array; struct tracer; struct dentry; -DECLARE_PER_CPU(struct trace_seq, ftrace_event_seq); - struct trace_print_flags { unsigned long mask; const char *name; @@ -58,6 +56,9 @@ struct trace_iterator { struct ring_buffer_iter *buffer_iter[NR_CPUS]; unsigned long iter_flags; + /* trace_seq for __print_flags() and __print_symbolic() etc. */ + struct trace_seq tmp_seq; + /* The below is zeroed out in pipe_read */ struct trace_seq seq; struct trace_entry *ent; -- cgit v1.2.3 From ade7ce31c22e961dfbe1a6d57fd362c90c187cbd Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 4 Jun 2010 10:56:01 +0200 Subject: quota: Clean up the namespace in dqblk_xfs.h Almost all identifiers use the FS_* namespace, so rename the missing few XFS_* ones to FS_* as well. Without this some people might get upset about having too many XFS names in generic code. Acked-by: Steven Whitehouse Signed-off-by: Christoph Hellwig Signed-off-by: Jan Kara --- include/linux/dqblk_xfs.h | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dqblk_xfs.h b/include/linux/dqblk_xfs.h index 4389ae72024e..86552807aed9 100644 --- a/include/linux/dqblk_xfs.h +++ b/include/linux/dqblk_xfs.h @@ -49,7 +49,7 @@ #define FS_DQUOT_VERSION 1 /* fs_disk_quota.d_version */ typedef struct fs_disk_quota { __s8 d_version; /* version of this structure */ - __s8 d_flags; /* XFS_{USER,PROJ,GROUP}_QUOTA */ + __s8 d_flags; /* FS_{USER,PROJ,GROUP}_QUOTA */ __u16 d_fieldmask; /* field specifier */ __u32 d_id; /* user, project, or group ID */ __u64 d_blk_hardlimit;/* absolute limit on disk blks */ @@ -119,18 +119,18 @@ typedef struct fs_disk_quota { #define FS_DQ_ACCT_MASK (FS_DQ_BCOUNT | FS_DQ_ICOUNT | FS_DQ_RTBCOUNT) /* - * Various flags related to quotactl(2). Only relevant to XFS filesystems. + * Various flags related to quotactl(2). */ -#define XFS_QUOTA_UDQ_ACCT (1<<0) /* user quota accounting */ -#define XFS_QUOTA_UDQ_ENFD (1<<1) /* user quota limits enforcement */ -#define XFS_QUOTA_GDQ_ACCT (1<<2) /* group quota accounting */ -#define XFS_QUOTA_GDQ_ENFD (1<<3) /* group quota limits enforcement */ -#define XFS_QUOTA_PDQ_ACCT (1<<4) /* project quota accounting */ -#define XFS_QUOTA_PDQ_ENFD (1<<5) /* project quota limits enforcement */ +#define FS_QUOTA_UDQ_ACCT (1<<0) /* user quota accounting */ +#define FS_QUOTA_UDQ_ENFD (1<<1) /* user quota limits enforcement */ +#define FS_QUOTA_GDQ_ACCT (1<<2) /* group quota accounting */ +#define FS_QUOTA_GDQ_ENFD (1<<3) /* group quota limits enforcement */ +#define FS_QUOTA_PDQ_ACCT (1<<4) /* project quota accounting */ +#define FS_QUOTA_PDQ_ENFD (1<<5) /* project quota limits enforcement */ -#define XFS_USER_QUOTA (1<<0) /* user quota type */ -#define XFS_PROJ_QUOTA (1<<1) /* project quota type */ -#define XFS_GROUP_QUOTA (1<<2) /* group quota type */ +#define FS_USER_QUOTA (1<<0) /* user quota type */ +#define FS_PROJ_QUOTA (1<<1) /* project quota type */ +#define FS_GROUP_QUOTA (1<<2) /* group quota type */ /* * fs_quota_stat is the struct returned in Q_XGETQSTAT for a given file system. @@ -151,7 +151,7 @@ typedef struct fs_qfilestat { typedef struct fs_quota_stat { __s8 qs_version; /* version number for future changes */ - __u16 qs_flags; /* XFS_QUOTA_{U,P,G}DQ_{ACCT,ENFD} */ + __u16 qs_flags; /* FS_QUOTA_{U,P,G}DQ_{ACCT,ENFD} */ __s8 qs_pad; /* unused */ fs_qfilestat_t qs_uquota; /* user quota storage information */ fs_qfilestat_t qs_gquota; /* group quota storage information */ -- cgit v1.2.3 From 189eef59e70e3e56edf726864629f310d114eefb Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 4 Jun 2010 10:56:29 +0200 Subject: quota: clean up quota active checks The various quota operations check for any quota beeing active on a superblock, and the inode not having the noquota flag. Merge these two checks into a dquot_active check and move that into dquot.c as that's the only place where it's needed. Signed-off-by: Christoph Hellwig Signed-off-by: Jan Kara --- include/linux/quotaops.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index aa36793b48bd..126193c1a5ce 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -145,11 +145,6 @@ static inline bool sb_has_quota_active(struct super_block *sb, int type) !sb_has_quota_suspended(sb, type); } -static inline unsigned sb_any_quota_active(struct super_block *sb) -{ - return sb_any_quota_loaded(sb) & ~sb_any_quota_suspended(sb); -} - /* * Operations supported for diskquotas. */ @@ -194,11 +189,6 @@ static inline int sb_has_quota_active(struct super_block *sb, int type) return 0; } -static inline int sb_any_quota_active(struct super_block *sb) -{ - return 0; -} - static inline void dquot_initialize(struct inode *inode) { } -- cgit v1.2.3 From 4c4d3901225518ed1a4c938ba15ba09842a00770 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 7 Jun 2010 10:20:39 +0200 Subject: ext3: remove vestiges of nobh support The nobh option was only supported for writeback mode, but given that all write paths (except mmapped writed) actually create buffer heads, it effectively was a no-op already. Signed-off-by: Christoph Hellwig Signed-off-by: Jan Kara --- include/linux/ext3_fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h index 7fc62d4550b2..3d3a9915dde2 100644 --- a/include/linux/ext3_fs.h +++ b/include/linux/ext3_fs.h @@ -400,7 +400,6 @@ struct ext3_inode { #define EXT3_MOUNT_POSIX_ACL 0x08000 /* POSIX Access Control Lists */ #define EXT3_MOUNT_RESERVATION 0x10000 /* Preallocation */ #define EXT3_MOUNT_BARRIER 0x20000 /* Use block barriers */ -#define EXT3_MOUNT_NOBH 0x40000 /* No bufferheads */ #define EXT3_MOUNT_QUOTA 0x80000 /* Some quota option set */ #define EXT3_MOUNT_USRQUOTA 0x100000 /* "old" user quota */ #define EXT3_MOUNT_GRPQUOTA 0x200000 /* "old" group quota */ -- cgit v1.2.3 From fb5ffb0e160c93c3fe08ab83845eb9a2768af812 Mon Sep 17 00:00:00 2001 From: Jiaying Zhang Date: Tue, 20 Jul 2010 16:54:43 +0200 Subject: quota: Change quota error message to print out disk and function name The current quota error message doesn't always print the disk name, so it is hard to identify the "bad" disk when quota error happens. This patch changes the standardized quota error message to print out disk name and function name. It also uses a combination of cpp macro and inline function to provide better type checking and to lower the text size of the message. [Jan Kara: Export __quota_error] Signed-off-by: Jiaying Zhang Signed-off-by: Jan Kara --- include/linux/quotaops.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 126193c1a5ce..4881b49b1a9a 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -28,6 +28,12 @@ static inline bool is_quota_modification(struct inode *inode, struct iattr *ia) #if defined(CONFIG_QUOTA) +#define quota_error(sb, fmt, args...) \ + __quota_error((sb), __func__, fmt , ## args) + +extern void __quota_error(struct super_block *sb, const char *func, + const char *fmt, ...); + /* * declaration of quota_function calls in kernel. */ -- cgit v1.2.3 From 9849ed4d72251d273524efb8b70be0be9aecb1df Mon Sep 17 00:00:00 2001 From: Mike Frysinger Date: Tue, 20 Jul 2010 03:13:35 -0400 Subject: tracing/documentation: Document dynamic ftracer internals Add more details to the dynamic function tracing design implementation. Signed-off-by: Mike Frysinger LKML-Reference: <1279610015-10250-1-git-send-email-vapier@gentoo.org> Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 41e46330d9be..dcd6a7c3a435 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -1,3 +1,8 @@ +/* + * Ftrace header. For implementation details beyond the random comments + * scattered below, see: Documentation/trace/ftrace-design.txt + */ + #ifndef _LINUX_FTRACE_H #define _LINUX_FTRACE_H -- cgit v1.2.3 From e120153ddf8620fd0a194d301e9c5a8b28483bb5 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 22 Jul 2010 14:14:25 +0200 Subject: workqueue: fix how cpu number is stored in work->data Once a work starts execution, its data contains the cpu number it was on instead of pointing to cwq. This is added by commit 7a22ad75 (workqueue: carry cpu number in work data once execution starts) to reliably determine the work was last on even if the workqueue itself was destroyed inbetween. Whether data points to a cwq or contains a cpu number was distinguished by comparing the value against PAGE_OFFSET. The assumption was that a cpu number should be below PAGE_OFFSET while a pointer to cwq should be above it. However, on architectures which use separate address spaces for user and kernel spaces, this doesn't hold as PAGE_OFFSET is zero. Fix it by using an explicit flag, WORK_STRUCT_CWQ, to mark what the data field contains. If the flag is set, it's pointing to a cwq; otherwise, it contains a cpu number. Reported on s390 and microblaze during linux-next testing. Signed-off-by: Tejun Heo Reported-by: Sachin Sant Reported-by: Michal Simek Reported-by: Martin Schwidefsky Tested-by: Martin Schwidefsky Tested-by: Michal Simek --- include/linux/workqueue.h | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index d74a529ed13e..5f76001c4e6d 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -25,17 +25,19 @@ typedef void (*work_func_t)(struct work_struct *work); enum { WORK_STRUCT_PENDING_BIT = 0, /* work item is pending execution */ - WORK_STRUCT_LINKED_BIT = 1, /* next work is linked to this one */ + WORK_STRUCT_CWQ_BIT = 1, /* data points to cwq */ + WORK_STRUCT_LINKED_BIT = 2, /* next work is linked to this one */ #ifdef CONFIG_DEBUG_OBJECTS_WORK - WORK_STRUCT_STATIC_BIT = 2, /* static initializer (debugobjects) */ - WORK_STRUCT_COLOR_SHIFT = 3, /* color for workqueue flushing */ + WORK_STRUCT_STATIC_BIT = 3, /* static initializer (debugobjects) */ + WORK_STRUCT_COLOR_SHIFT = 4, /* color for workqueue flushing */ #else - WORK_STRUCT_COLOR_SHIFT = 2, /* color for workqueue flushing */ + WORK_STRUCT_COLOR_SHIFT = 3, /* color for workqueue flushing */ #endif WORK_STRUCT_COLOR_BITS = 4, WORK_STRUCT_PENDING = 1 << WORK_STRUCT_PENDING_BIT, + WORK_STRUCT_CWQ = 1 << WORK_STRUCT_CWQ_BIT, WORK_STRUCT_LINKED = 1 << WORK_STRUCT_LINKED_BIT, #ifdef CONFIG_DEBUG_OBJECTS_WORK WORK_STRUCT_STATIC = 1 << WORK_STRUCT_STATIC_BIT, @@ -56,8 +58,8 @@ enum { WORK_CPU_LAST = WORK_CPU_NONE, /* - * Reserve 6 bits off of cwq pointer w/ debugobjects turned - * off. This makes cwqs aligned to 64 bytes which isn't too + * Reserve 7 bits off of cwq pointer w/ debugobjects turned + * off. This makes cwqs aligned to 128 bytes which isn't too * excessive while allowing 15 workqueue flush colors. */ WORK_STRUCT_FLAG_BITS = WORK_STRUCT_COLOR_SHIFT + -- cgit v1.2.3 From 8b8edefa2fffbff97f9eec8b70e78ae23abad1a0 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 20 Jul 2010 22:09:01 +0200 Subject: fscache: convert object to use workqueue instead of slow-work Make fscache object state transition callbacks use workqueue instead of slow-work. New dedicated unbound CPU workqueue fscache_object_wq is created. get/put callbacks are renamed and modified to take @object and called directly from the enqueue wrapper and the work function. While at it, make all open coded instances of get/put to use fscache_get/put_object(). * Unbound workqueue is used. * work_busy() output is printed instead of slow-work flags in object debugging outputs. They mean basically the same thing bit-for-bit. * sysctl fscache.object_max_active added to control concurrency. The default value is nr_cpus clamped between 4 and WQ_UNBOUND_MAX_ACTIVE. * slow_work_sleep_till_thread_needed() is replaced with fscache private implementation fscache_object_sleep_till_congested() which waits on fscache_object_wq congestion. * debugfs support is dropped for now. Tracing API based debug facility is planned to be added. Signed-off-by: Tejun Heo Acked-by: David Howells --- include/linux/fscache-cache.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index c57db27ac861..27c8df503152 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -21,6 +21,7 @@ #include #include #include +#include #define NR_MAXCACHES BITS_PER_LONG @@ -389,7 +390,7 @@ struct fscache_object { struct fscache_cache *cache; /* cache that supplied this object */ struct fscache_cookie *cookie; /* netfs's file/index object */ struct fscache_object *parent; /* parent object */ - struct slow_work work; /* attention scheduling record */ + struct work_struct work; /* attention scheduling record */ struct list_head dependents; /* FIFO of dependent objects */ struct list_head dep_link; /* link in parent's dependents list */ struct list_head pending_ops; /* unstarted operations on this object */ @@ -411,7 +412,7 @@ extern const char *fscache_object_states[]; (test_bit(FSCACHE_IOERROR, &(obj)->cache->flags) && \ (obj)->state >= FSCACHE_OBJECT_DYING) -extern const struct slow_work_ops fscache_object_slow_work_ops; +extern void fscache_object_work_func(struct work_struct *work); /** * fscache_object_init - Initialise a cache object description @@ -433,7 +434,7 @@ void fscache_object_init(struct fscache_object *object, spin_lock_init(&object->lock); INIT_LIST_HEAD(&object->cache_link); INIT_HLIST_NODE(&object->cookie_link); - vslow_work_init(&object->work, &fscache_object_slow_work_ops); + INIT_WORK(&object->work, fscache_object_work_func); INIT_LIST_HEAD(&object->dependents); INIT_LIST_HEAD(&object->dep_link); INIT_LIST_HEAD(&object->pending_ops); @@ -534,6 +535,8 @@ extern void fscache_io_error(struct fscache_cache *cache); extern void fscache_mark_pages_cached(struct fscache_retrieval *op, struct pagevec *pagevec); +extern bool fscache_object_sleep_till_congested(signed long *timeoutp); + extern enum fscache_checkaux fscache_check_aux(struct fscache_object *object, const void *data, uint16_t datalen); -- cgit v1.2.3 From 8af7c12436803291c90295259db23d371a7ad9cc Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 20 Jul 2010 22:09:01 +0200 Subject: fscache: convert operation to use workqueue instead of slow-work Make fscache operation to use only workqueue instead of combination of workqueue and slow-work. FSCACHE_OP_SLOW is dropped and FSCACHE_OP_FAST is renamed to FSCACHE_OP_ASYNC and uses newly added fscache_op_wq workqueue to execute op->processor(). fscache_operation_init_slow() is dropped and fscache_operation_init() now takes @processor argument directly. * Unbound workqueue is used. * fscache_retrieval_work() is no longer necessary as OP_ASYNC now does the equivalent thing. * sysctl fscache.operation_max_active added to control concurrency. The default value is nr_cpus clamped between 2 and WQ_UNBOUND_MAX_ACTIVE. * debugfs support is dropped for now. Tracing API based debug facility is planned to be added. Signed-off-by: Tejun Heo Acked-by: David Howells --- include/linux/fscache-cache.h | 37 +++++++++++-------------------------- 1 file changed, 11 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 27c8df503152..17ed9c1dbfbe 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -77,18 +77,14 @@ typedef void (*fscache_operation_release_t)(struct fscache_operation *op); typedef void (*fscache_operation_processor_t)(struct fscache_operation *op); struct fscache_operation { - union { - struct work_struct fast_work; /* record for fast ops */ - struct slow_work slow_work; /* record for (very) slow ops */ - }; + struct work_struct work; /* record for async ops */ struct list_head pend_link; /* link in object->pending_ops */ struct fscache_object *object; /* object to be operated upon */ unsigned long flags; #define FSCACHE_OP_TYPE 0x000f /* operation type */ -#define FSCACHE_OP_FAST 0x0001 /* - fast op, processor may not sleep for disk */ -#define FSCACHE_OP_SLOW 0x0002 /* - (very) slow op, processor may sleep for disk */ -#define FSCACHE_OP_MYTHREAD 0x0003 /* - processing is done be issuing thread, not pool */ +#define FSCACHE_OP_ASYNC 0x0001 /* - async op, processor may sleep for disk */ +#define FSCACHE_OP_MYTHREAD 0x0002 /* - processing is done be issuing thread, not pool */ #define FSCACHE_OP_WAITING 4 /* cleared when op is woken */ #define FSCACHE_OP_EXCLUSIVE 5 /* exclusive op, other ops must wait */ #define FSCACHE_OP_DEAD 6 /* op is now dead */ @@ -106,7 +102,8 @@ struct fscache_operation { /* operation releaser */ fscache_operation_release_t release; -#ifdef CONFIG_SLOW_WORK_DEBUG +#ifdef CONFIG_WORKQUEUE_DEBUGFS + struct work_struct put_work; /* work to delay operation put */ const char *name; /* operation name */ const char *state; /* operation state */ #define fscache_set_op_name(OP, N) do { (OP)->name = (N); } while(0) @@ -118,7 +115,7 @@ struct fscache_operation { }; extern atomic_t fscache_op_debug_id; -extern const struct slow_work_ops fscache_op_slow_work_ops; +extern void fscache_op_work_func(struct work_struct *work); extern void fscache_enqueue_operation(struct fscache_operation *); extern void fscache_put_operation(struct fscache_operation *); @@ -129,33 +126,21 @@ extern void fscache_put_operation(struct fscache_operation *); * @release: The release function to assign * * Do basic initialisation of an operation. The caller must still set flags, - * object, either fast_work or slow_work if necessary, and processor if needed. + * object and processor if needed. */ static inline void fscache_operation_init(struct fscache_operation *op, - fscache_operation_release_t release) + fscache_operation_processor_t processor, + fscache_operation_release_t release) { + INIT_WORK(&op->work, fscache_op_work_func); atomic_set(&op->usage, 1); op->debug_id = atomic_inc_return(&fscache_op_debug_id); + op->processor = processor; op->release = release; INIT_LIST_HEAD(&op->pend_link); fscache_set_op_state(op, "Init"); } -/** - * fscache_operation_init_slow - Do additional initialisation of a slow op - * @op: The operation to initialise - * @processor: The processor function to assign - * - * Do additional initialisation of an operation as required for slow work. - */ -static inline -void fscache_operation_init_slow(struct fscache_operation *op, - fscache_operation_processor_t processor) -{ - op->processor = processor; - slow_work_init(&op->slow_work, &fscache_op_slow_work_ops); -} - /* * data read operation */ -- cgit v1.2.3 From d098adfb7d281258173a43151483e52e21761021 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 20 Jul 2010 22:09:01 +0200 Subject: fscache: drop references to slow-work fscache no longer uses slow-work. Drop references to it. Signed-off-by: Tejun Heo Acked-by: David Howells --- include/linux/fscache-cache.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 17ed9c1dbfbe..b8581c09d19f 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -20,7 +20,6 @@ #include #include -#include #include #define NR_MAXCACHES BITS_PER_LONG -- cgit v1.2.3 From 183d03cc4ff39e0f0d952c09aa96d0abfd6e0c3c Mon Sep 17 00:00:00 2001 From: Stefano Stabellini Date: Mon, 17 May 2010 17:08:21 +0100 Subject: xen: Xen PCI platform device driver. Add the xen pci platform device driver that is responsible for initializing the grant table and xenbus in PV on HVM mode. Few changes to xenbus and grant table are necessary to allow the delayed initialization in HVM mode. Grant table needs few additional modifications to work in HVM mode. The Xen PCI platform device raises an irq every time an event has been delivered to us. However these interrupts are only delivered to vcpu 0. The Xen PCI platform interrupt handler calls xen_hvm_evtchn_do_upcall that is a little wrapper around __xen_evtchn_do_upcall, the traditional Xen upcall handler, the very same used with traditional PV guests. When running on HVM the event channel upcall is never called while in progress because it is a normal Linux irq handler (and we cannot switch the irq chip wholesale to the Xen PV ones as we are running QEMU and might have passed in PCI devices), therefore we cannot be sure that evtchn_upcall_pending is 0 when returning. For this reason if evtchn_upcall_pending is set by Xen we need to loop again on the event channels set pending otherwise we might loose some event channel deliveries. Signed-off-by: Stefano Stabellini Signed-off-by: Sheng Yang Signed-off-by: Jeremy Fitzhardinge --- include/linux/pci_ids.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 3bedcc149c84..cca2526f28d7 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2772,3 +2772,6 @@ #define PCI_DEVICE_ID_RME_DIGI32 0x9896 #define PCI_DEVICE_ID_RME_DIGI32_PRO 0x9897 #define PCI_DEVICE_ID_RME_DIGI32_8 0x9898 + +#define PCI_VENDOR_ID_XEN 0x5853 +#define PCI_DEVICE_ID_XEN_PLATFORM 0x0001 -- cgit v1.2.3 From 2f1b7cd29fa4917f19d2624afc773d941684c5df Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Thu, 22 Jul 2010 03:22:18 +0900 Subject: nilfs2: clarify byte offset in super block format This inserts comments indicating hexadecimal offset in declaration of nilfs_super_block structure so that people can know offset of its fields without counting from the head. Signed-off-by: Ryusuke Konishi --- include/linux/nilfs2_fs.h | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nilfs2_fs.h b/include/linux/nilfs2_fs.h index 8c2c6116e788..cc3465e5be38 100644 --- a/include/linux/nilfs2_fs.h +++ b/include/linux/nilfs2_fs.h @@ -160,7 +160,7 @@ struct nilfs_super_root { * struct nilfs_super_block - structure of super block on disk */ struct nilfs_super_block { - __le32 s_rev_level; /* Revision level */ +/*00*/ __le32 s_rev_level; /* Revision level */ __le16 s_minor_rev_level; /* minor revision level */ __le16 s_magic; /* Magic signature */ @@ -169,47 +169,47 @@ struct nilfs_super_block { is excluded. */ __le16 s_flags; /* flags */ __le32 s_crc_seed; /* Seed value of CRC calculation */ - __le32 s_sum; /* Check sum of super block */ +/*10*/ __le32 s_sum; /* Check sum of super block */ __le32 s_log_block_size; /* Block size represented as follows blocksize = 1 << (s_log_block_size + 10) */ __le64 s_nsegments; /* Number of segments in filesystem */ - __le64 s_dev_size; /* block device size in bytes */ +/*20*/ __le64 s_dev_size; /* block device size in bytes */ __le64 s_first_data_block; /* 1st seg disk block number */ - __le32 s_blocks_per_segment; /* number of blocks per full segment */ +/*30*/ __le32 s_blocks_per_segment; /* number of blocks per full segment */ __le32 s_r_segments_percentage; /* Reserved segments percentage */ __le64 s_last_cno; /* Last checkpoint number */ - __le64 s_last_pseg; /* disk block addr pseg written last */ +/*40*/ __le64 s_last_pseg; /* disk block addr pseg written last */ __le64 s_last_seq; /* seq. number of seg written last */ - __le64 s_free_blocks_count; /* Free blocks count */ +/*50*/ __le64 s_free_blocks_count; /* Free blocks count */ __le64 s_ctime; /* Creation time (execution time of newfs) */ - __le64 s_mtime; /* Mount time */ +/*60*/ __le64 s_mtime; /* Mount time */ __le64 s_wtime; /* Write time */ - __le16 s_mnt_count; /* Mount count */ +/*70*/ __le16 s_mnt_count; /* Mount count */ __le16 s_max_mnt_count; /* Maximal mount count */ __le16 s_state; /* File system state */ __le16 s_errors; /* Behaviour when detecting errors */ __le64 s_lastcheck; /* time of last check */ - __le32 s_checkinterval; /* max. time between checks */ +/*80*/ __le32 s_checkinterval; /* max. time between checks */ __le32 s_creator_os; /* OS */ __le16 s_def_resuid; /* Default uid for reserved blocks */ __le16 s_def_resgid; /* Default gid for reserved blocks */ __le32 s_first_ino; /* First non-reserved inode */ - __le16 s_inode_size; /* Size of an inode */ +/*90*/ __le16 s_inode_size; /* Size of an inode */ __le16 s_dat_entry_size; /* Size of a dat entry */ __le16 s_checkpoint_size; /* Size of a checkpoint */ __le16 s_segment_usage_size; /* Size of a segment usage */ - __u8 s_uuid[16]; /* 128-bit uuid for volume */ - char s_volume_name[80]; /* volume name */ +/*98*/ __u8 s_uuid[16]; /* 128-bit uuid for volume */ +/*A8*/ char s_volume_name[80]; /* volume name */ - __le32 s_c_interval; /* Commit interval of segment */ +/*F8*/ __le32 s_c_interval; /* Commit interval of segment */ __le32 s_c_block_max; /* Threshold of data amount for the segment construction */ __u32 s_reserved[192]; /* padding to the end of the block */ -- cgit v1.2.3 From 1a80a1763fb760b3a84a28df87515f7cdc07a4f4 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Thu, 22 Jul 2010 03:22:19 +0900 Subject: nilfs2: add feature set fields to super block This adds three new fields to nilfs_super_block structure, compatible feature set, readonly-compatible feature set, and incompatible feature set in order to prepare for future disk format modifications. The role of these fields conforms to those of ext3 or other filesystems. Most important flags are the incompatible feature set; it is used to refuse to mount the filesystem which sets an incompatible feature the kernel doesn't know about. Signed-off-by: Ryusuke Konishi --- include/linux/nilfs2_fs.h | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nilfs2_fs.h b/include/linux/nilfs2_fs.h index cc3465e5be38..7dd4cd494490 100644 --- a/include/linux/nilfs2_fs.h +++ b/include/linux/nilfs2_fs.h @@ -212,7 +212,10 @@ struct nilfs_super_block { /*F8*/ __le32 s_c_interval; /* Commit interval of segment */ __le32 s_c_block_max; /* Threshold of data amount for the segment construction */ - __u32 s_reserved[192]; /* padding to the end of the block */ +/*100*/ __le64 s_feature_compat; /* Compatible feature set */ + __le64 s_feature_compat_ro; /* Read-only compatible feature set */ + __le64 s_feature_incompat; /* Incompatible feature set */ + __u32 s_reserved[186]; /* padding to the end of the block */ }; /* @@ -227,6 +230,16 @@ struct nilfs_super_block { #define NILFS_CURRENT_REV 2 /* current major revision */ #define NILFS_MINOR_REV 0 /* minor revision */ +/* + * Feature set definitions + * + * If there is a bit set in the incompatible feature set that the kernel + * doesn't know about, it should refuse to mount the filesystem. + */ +#define NILFS_FEATURE_COMPAT_SUPP 0ULL +#define NILFS_FEATURE_COMPAT_RO_SUPP 0ULL +#define NILFS_FEATURE_INCOMPAT_SUPP 0ULL + /* * Bytes count of super_block for CRC-calculation */ -- cgit v1.2.3 From 43d2932d88e4ab776dd388c20b003ebd5e1d1f1f Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 21 Jul 2010 14:22:21 +0200 Subject: quota: Use mark_inode_dirty_sync instead of mark_inode_dirty Quota code never touches file data. It just modifies i_blocks + i_bytes of inodes and inode flags of quota files. So use mark_inode_dirty_sync instead of mark_inode_dirty. Signed-off-by: Jan Kara --- include/linux/quotaops.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 4881b49b1a9a..d50ba858cfe0 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -266,7 +266,7 @@ static inline int dquot_alloc_space_nodirty(struct inode *inode, qsize_t nr) static inline void dquot_alloc_space_nofail(struct inode *inode, qsize_t nr) { __dquot_alloc_space(inode, nr, DQUOT_SPACE_WARN|DQUOT_SPACE_NOFAIL); - mark_inode_dirty(inode); + mark_inode_dirty_sync(inode); } static inline int dquot_alloc_space(struct inode *inode, qsize_t nr) @@ -275,7 +275,7 @@ static inline int dquot_alloc_space(struct inode *inode, qsize_t nr) ret = dquot_alloc_space_nodirty(inode, nr); if (!ret) - mark_inode_dirty(inode); + mark_inode_dirty_sync(inode); return ret; } @@ -305,7 +305,7 @@ static inline int dquot_prealloc_block(struct inode *inode, qsize_t nr) ret = dquot_prealloc_block_nodirty(inode, nr); if (!ret) - mark_inode_dirty(inode); + mark_inode_dirty_sync(inode); return ret; } @@ -321,7 +321,7 @@ static inline int dquot_claim_block(struct inode *inode, qsize_t nr) ret = dquot_claim_space_nodirty(inode, nr << inode->i_blkbits); if (!ret) - mark_inode_dirty(inode); + mark_inode_dirty_sync(inode); return ret; } @@ -333,7 +333,7 @@ static inline void dquot_free_space_nodirty(struct inode *inode, qsize_t nr) static inline void dquot_free_space(struct inode *inode, qsize_t nr) { dquot_free_space_nodirty(inode, nr); - mark_inode_dirty(inode); + mark_inode_dirty_sync(inode); } static inline void dquot_free_block_nodirty(struct inode *inode, qsize_t nr) -- cgit v1.2.3 From 181a51f6e040d0ac006d6adaf4a031ffa440f41c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 20 Jul 2010 22:09:02 +0200 Subject: slow-work: kill it slow-work doesn't have any user left. Kill it. Signed-off-by: Tejun Heo Acked-by: David Howells --- include/linux/slow-work.h | 163 ---------------------------------------------- 1 file changed, 163 deletions(-) delete mode 100644 include/linux/slow-work.h (limited to 'include/linux') diff --git a/include/linux/slow-work.h b/include/linux/slow-work.h deleted file mode 100644 index 13337bf6c3f5..000000000000 --- a/include/linux/slow-work.h +++ /dev/null @@ -1,163 +0,0 @@ -/* Worker thread pool for slow items, such as filesystem lookups or mkdirs - * - * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. - * - * See Documentation/slow-work.txt - */ - -#ifndef _LINUX_SLOW_WORK_H -#define _LINUX_SLOW_WORK_H - -#ifdef CONFIG_SLOW_WORK - -#include -#include - -struct slow_work; -#ifdef CONFIG_SLOW_WORK_DEBUG -struct seq_file; -#endif - -/* - * The operations used to support slow work items - */ -struct slow_work_ops { - /* owner */ - struct module *owner; - - /* get a ref on a work item - * - return 0 if successful, -ve if not - */ - int (*get_ref)(struct slow_work *work); - - /* discard a ref to a work item */ - void (*put_ref)(struct slow_work *work); - - /* execute a work item */ - void (*execute)(struct slow_work *work); - -#ifdef CONFIG_SLOW_WORK_DEBUG - /* describe a work item for debugfs */ - void (*desc)(struct slow_work *work, struct seq_file *m); -#endif -}; - -/* - * A slow work item - * - A reference is held on the parent object by the thread pool when it is - * queued - */ -struct slow_work { - struct module *owner; /* the owning module */ - unsigned long flags; -#define SLOW_WORK_PENDING 0 /* item pending (further) execution */ -#define SLOW_WORK_EXECUTING 1 /* item currently executing */ -#define SLOW_WORK_ENQ_DEFERRED 2 /* item enqueue deferred */ -#define SLOW_WORK_VERY_SLOW 3 /* item is very slow */ -#define SLOW_WORK_CANCELLING 4 /* item is being cancelled, don't enqueue */ -#define SLOW_WORK_DELAYED 5 /* item is struct delayed_slow_work with active timer */ - const struct slow_work_ops *ops; /* operations table for this item */ - struct list_head link; /* link in queue */ -#ifdef CONFIG_SLOW_WORK_DEBUG - struct timespec mark; /* jiffies at which queued or exec begun */ -#endif -}; - -struct delayed_slow_work { - struct slow_work work; - struct timer_list timer; -}; - -/** - * slow_work_init - Initialise a slow work item - * @work: The work item to initialise - * @ops: The operations to use to handle the slow work item - * - * Initialise a slow work item. - */ -static inline void slow_work_init(struct slow_work *work, - const struct slow_work_ops *ops) -{ - work->flags = 0; - work->ops = ops; - INIT_LIST_HEAD(&work->link); -} - -/** - * slow_work_init - Initialise a delayed slow work item - * @work: The work item to initialise - * @ops: The operations to use to handle the slow work item - * - * Initialise a delayed slow work item. - */ -static inline void delayed_slow_work_init(struct delayed_slow_work *dwork, - const struct slow_work_ops *ops) -{ - init_timer(&dwork->timer); - slow_work_init(&dwork->work, ops); -} - -/** - * vslow_work_init - Initialise a very slow work item - * @work: The work item to initialise - * @ops: The operations to use to handle the slow work item - * - * Initialise a very slow work item. This item will be restricted such that - * only a certain number of the pool threads will be able to execute items of - * this type. - */ -static inline void vslow_work_init(struct slow_work *work, - const struct slow_work_ops *ops) -{ - work->flags = 1 << SLOW_WORK_VERY_SLOW; - work->ops = ops; - INIT_LIST_HEAD(&work->link); -} - -/** - * slow_work_is_queued - Determine if a slow work item is on the work queue - * work: The work item to test - * - * Determine if the specified slow-work item is on the work queue. This - * returns true if it is actually on the queue. - * - * If the item is executing and has been marked for requeue when execution - * finishes, then false will be returned. - * - * Anyone wishing to wait for completion of execution can wait on the - * SLOW_WORK_EXECUTING bit. - */ -static inline bool slow_work_is_queued(struct slow_work *work) -{ - unsigned long flags = work->flags; - return flags & SLOW_WORK_PENDING && !(flags & SLOW_WORK_EXECUTING); -} - -extern int slow_work_enqueue(struct slow_work *work); -extern void slow_work_cancel(struct slow_work *work); -extern int slow_work_register_user(struct module *owner); -extern void slow_work_unregister_user(struct module *owner); - -extern int delayed_slow_work_enqueue(struct delayed_slow_work *dwork, - unsigned long delay); - -static inline void delayed_slow_work_cancel(struct delayed_slow_work *dwork) -{ - slow_work_cancel(&dwork->work); -} - -extern bool slow_work_sleep_till_thread_needed(struct slow_work *work, - signed long *_timeout); - -#ifdef CONFIG_SYSCTL -extern ctl_table slow_work_sysctls[]; -#endif - -#endif /* CONFIG_SLOW_WORK */ -#endif /* _LINUX_SLOW_WORK_H */ -- cgit v1.2.3 From 18d0cdfd1a4cc9028c0ef80f94538b31541f8fe5 Mon Sep 17 00:00:00 2001 From: Stefan Richter Date: Sun, 18 Jul 2010 12:44:01 +0200 Subject: firewire: normalize status values in packet callbacks core-transaction.c transmit_complete_callback() and close_transaction() expect packet callback status to be an ACK or RCODE, and ACKs get translated to RCODEs for transaction callbacks. An old comment on the packet callback API (been there from the initial submission of the stack) and the dummy_driver implementation of send_request/send_response deviated from this as they also included -ERRNO in the range of status values. Let's narrow status values down to ACK and RCODE to prevent surprises. RCODE_CANCELLED is chosen as the dummy_driver's RCODE as its meaning of "transaction timed out" comes closest to what happens when a transaction coincides with card removal. Signed-off-by: Stefan Richter --- include/linux/firewire.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firewire.h b/include/linux/firewire.h index adc5b55e6e5f..0c38b8e97722 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -285,10 +285,10 @@ struct fw_packet { u32 timestamp; /* - * This callback is called when the packet transmission has - * completed; for successful transmission, the status code is - * the ack received from the destination, otherwise it's a - * negative errno: ENOMEM, ESTALE, ETIMEDOUT, ENODEV, EIO. + * This callback is called when the packet transmission has completed. + * For successful transmission, the status code is the ack received + * from the destination. Otherwise it is one of the juju-specific + * rcodes: RCODE_SEND_ERROR, _CANCELLED, _BUSY, _GENERATION, _NO_ACK. * The callback can be called from tasklet context and thus * must never block. */ -- cgit v1.2.3 From d505e6e87127d4dbdaa5d91561eed810c180ca23 Mon Sep 17 00:00:00 2001 From: Stefan Richter Date: Sat, 17 Jul 2010 21:36:02 +0200 Subject: firewire: cdev: some clarifications to the API documentation Response events: - are generated on more occasions than their documentation claimed. CSR allocation: - An already occupied CSR can be determined from errno==EBUSY. Bus resets: - Note that FW_CDEV_IOC_INITIATE_BUS_RESET is nonblocking and that the client is not required to observe a grace period since kernels 2.6.36+ will enforce it now (commit 02d37bed). - The possible values of fw_cdev_initiate_bus_reset.type are listed in the kerneldoc comment already. - Clarify that an application that uses FW_CDEV_IOC_ADD_DESCRIPTOR and FW_CDEV_IOC_REMOVE_DESCRIPTOR does not have to issue a bus reset. Isochronous I/O contexts: - At most one can be created per open file descriptor. Signed-off-by: Stefan Richter --- include/linux/firewire-cdev.h | 33 +++++++++++++++++++++++++-------- 1 file changed, 25 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firewire-cdev.h b/include/linux/firewire-cdev.h index d31022b05bd9..fde9568151d5 100644 --- a/include/linux/firewire-cdev.h +++ b/include/linux/firewire-cdev.h @@ -84,8 +84,9 @@ struct fw_cdev_event_bus_reset { /** * struct fw_cdev_event_response - Sent when a response packet was received - * @closure: See &fw_cdev_event_common; - * set by %FW_CDEV_IOC_SEND_REQUEST ioctl + * @closure: See &fw_cdev_event_common; set by %FW_CDEV_IOC_SEND_REQUEST + * or %FW_CDEV_IOC_SEND_BROADCAST_REQUEST + * or %FW_CDEV_IOC_SEND_STREAM_PACKET ioctl * @type: See &fw_cdev_event_common; always %FW_CDEV_EVENT_RESPONSE * @rcode: Response code returned by the remote node * @length: Data length, i.e. the response's payload size in bytes @@ -95,6 +96,11 @@ struct fw_cdev_event_bus_reset { * sent by %FW_CDEV_IOC_SEND_REQUEST ioctl. The payload data for responses * carrying data (read and lock responses) follows immediately and can be * accessed through the @data field. + * + * The event is also generated after conclusions of transactions that do not + * involve response packets. This includes unified write transactions, + * broadcast write transactions, and transmission of asynchronous stream + * packets. @rcode indicates success or failure of such transmissions. */ struct fw_cdev_event_response { __u64 closure; @@ -447,7 +453,9 @@ struct fw_cdev_send_response { * range to be used for later deallocation of the range. * * The address range is allocated on all local nodes. The address allocation - * is exclusive except for the FCP command and response registers. + * is exclusive except for the FCP command and response registers. If an + * exclusive address region is already in use, the ioctl fails with errno set + * to %EBUSY. */ struct fw_cdev_allocate { __u64 offset; @@ -475,9 +483,14 @@ struct fw_cdev_deallocate { * Initiate a bus reset for the bus this device is on. The bus reset can be * either the original (long) bus reset or the arbitrated (short) bus reset * introduced in 1394a-2000. + * + * The ioctl returns immediately. A subsequent &fw_cdev_event_bus_reset + * indicates when the reset actually happened. Since ABI v4, this may be + * considerably later than the ioctl because the kernel ensures a grace period + * between subsequent bus resets as per IEEE 1394 bus management specification. */ struct fw_cdev_initiate_bus_reset { - __u32 type; /* FW_CDEV_SHORT_RESET or FW_CDEV_LONG_RESET */ + __u32 type; }; /** @@ -501,9 +514,10 @@ struct fw_cdev_initiate_bus_reset { * * @immediate, @key, and @data array elements are CPU-endian quadlets. * - * If successful, the kernel adds the descriptor and writes back a handle to the - * kernel-side object to be used for later removal of the descriptor block and - * immediate key. + * If successful, the kernel adds the descriptor and writes back a @handle to + * the kernel-side object to be used for later removal of the descriptor block + * and immediate key. The kernel will also generate a bus reset to signal the + * change of the configuration ROM to other nodes. * * This ioctl affects the configuration ROMs of all local nodes. * The ioctl only succeeds on device files which represent a local node. @@ -522,7 +536,8 @@ struct fw_cdev_add_descriptor { * descriptor was added * * Remove a descriptor block and accompanying immediate key from the local - * nodes' configuration ROMs. + * nodes' configuration ROMs. The kernel will also generate a bus reset to + * signal the change of the configuration ROM to other nodes. */ struct fw_cdev_remove_descriptor { __u32 handle; @@ -554,6 +569,8 @@ struct fw_cdev_remove_descriptor { * * Note that the effect of a @header_size > 4 depends on * &fw_cdev_get_info.version, as documented at &fw_cdev_event_iso_interrupt. + * + * No more than one iso context can be created per fd. */ struct fw_cdev_create_iso_context { __u32 type; -- cgit v1.2.3 From 850bb6f23b93c04ce1e4509a87fa607dc17d97c1 Mon Sep 17 00:00:00 2001 From: Stefan Richter Date: Fri, 16 Jul 2010 22:25:14 +0200 Subject: firewire: cdev: add PHY packet transmission Add an FW_CDEV_IOC_SEND_PHY_PACKET ioctl() for /dev/fw* which can be used to implement bus management related functionality in userspace. This is also half of the functionality (the transmit part) that is needed to support a userspace implementation of a VersaPHY transaction layer. Safety considerations: - PHY packets are generally broadcasts and may have interesting effects on PHYs and the bus, e.g. make asynchronous arbitration impossible due to too low gap count. Hence some kind of elevated privileges should be required of a process to be able to send PHY packets. This implementation assumes that a process that is allowed to open the /dev/fw* of a local node does have this privilege. There was an inconclusive discussion about introducing POSIX capabilities as a means to check for user privileges for these kinds of operations. - The kernel does not check integrity of the supplied packet data. That would be far too much code, considering the many kinds of PHY packets. A process which got the privilege to send these packets is trusted to do it correctly. Just like with the other "send packet" ioctls, a non-blocking API is chosen; i.e. the ioctl may return even before AT DMA started. After transmission, an event for poll()/read() is enqueued. Most users are going to need a blocking API, but a blocking userspace wrapper is easy to implement, and the second of the two existing libraw1394 calls raw1394_phy_packet_write() and raw1394_start_phy_packet_write() can be better supported that way. Signed-off-by: Stefan Richter --- include/linux/firewire-cdev.h | 44 ++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 43 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firewire-cdev.h b/include/linux/firewire-cdev.h index fde9568151d5..5bc051b9a013 100644 --- a/include/linux/firewire-cdev.h +++ b/include/linux/firewire-cdev.h @@ -34,6 +34,7 @@ /* available since kernel version 2.6.36 */ #define FW_CDEV_EVENT_REQUEST2 0x06 +#define FW_CDEV_EVENT_PHY_PACKET_SENT 0x07 /** * struct fw_cdev_event_common - Common part of all fw_cdev_event_ types @@ -283,6 +284,19 @@ struct fw_cdev_event_iso_resource { __s32 bandwidth; }; +/** + * struct fw_cdev_event_phy_packet - A PHY packet was transmitted + * @closure: See &fw_cdev_event_common; + * set by %FW_CDEV_IOC_SEND_PHY_PACKET ioctl + * @type: %FW_CDEV_EVENT_PHY_PACKET_SENT + * @rcode: %RCODE_..., indicates success or failure of transmission + */ +struct fw_cdev_event_phy_packet { + __u64 closure; + __u32 type; + __u32 rcode; +}; + /** * union fw_cdev_event - Convenience union of fw_cdev_event_ types * @common: Valid for all types @@ -294,6 +308,7 @@ struct fw_cdev_event_iso_resource { * @iso_resource: Valid if @common.type == * %FW_CDEV_EVENT_ISO_RESOURCE_ALLOCATED or * %FW_CDEV_EVENT_ISO_RESOURCE_DEALLOCATED + * @phy_packet: Valid if @common.type == %FW_CDEV_EVENT_PHY_PACKET_SENT * * Convenience union for userspace use. Events could be read(2) into an * appropriately aligned char buffer and then cast to this union for further @@ -311,6 +326,7 @@ union fw_cdev_event { struct fw_cdev_event_request2 request2; /* added in 2.6.36 */ struct fw_cdev_event_iso_interrupt iso_interrupt; struct fw_cdev_event_iso_resource iso_resource; /* added in 2.6.30 */ + struct fw_cdev_event_phy_packet phy_packet; /* added in 2.6.36 */ }; /* available since kernel version 2.6.22 */ @@ -342,6 +358,9 @@ union fw_cdev_event { /* available since kernel version 2.6.34 */ #define FW_CDEV_IOC_GET_CYCLE_TIMER2 _IOWR('#', 0x14, struct fw_cdev_get_cycle_timer2) +/* available since kernel version 2.6.36 */ +#define FW_CDEV_IOC_SEND_PHY_PACKET _IOWR('#', 0x15, struct fw_cdev_send_phy_packet) + /* * ABI version history * 1 (2.6.22) - initial version @@ -357,8 +376,9 @@ union fw_cdev_event { * - shared use and auto-response for FCP registers * 3 (2.6.34) - made &fw_cdev_get_cycle_timer reliable * - added %FW_CDEV_IOC_GET_CYCLE_TIMER2 - * 4 (2.6.36) - added %FW_CDEV_EVENT_REQUEST2 + * 4 (2.6.36) - added %FW_CDEV_EVENT_REQUEST2, %FW_CDEV_EVENT_PHY_PACKET_SENT * - implemented &fw_cdev_event_bus_reset.bm_node_id + * - added %FW_CDEV_IOC_SEND_PHY_PACKET */ #define FW_CDEV_VERSION 3 /* Meaningless; don't use this macro. */ @@ -808,4 +828,26 @@ struct fw_cdev_send_stream_packet { __u32 speed; }; +/** + * struct fw_cdev_send_phy_packet - send a PHY packet + * @closure: Passed back to userspace in the PHY-packet-sent event + * @data: First and second quadlet of the PHY packet + * @generation: The bus generation where packet is valid + * + * The %FW_CDEV_IOC_SEND_PHY_PACKET ioctl sends a PHY packet to all nodes + * on the same card as this device. After transmission, an + * %FW_CDEV_EVENT_PHY_PACKET_SENT event is generated. + * + * The payload @data[] shall be specified in host byte order. Usually, + * @data[1] needs to be the bitwise inverse of @data[0]. VersaPHY packets + * are an exception to this rule. + * + * The ioctl is only permitted on device files which represent a local node. + */ +struct fw_cdev_send_phy_packet { + __u64 closure; + __u32 data[2]; + __u32 generation; +}; + #endif /* _LINUX_FIREWIRE_CDEV_H */ -- cgit v1.2.3 From bf54e1462b9192fdef7ea9e2bc44fdc16a4b87bc Mon Sep 17 00:00:00 2001 From: Stefan Richter Date: Fri, 16 Jul 2010 22:25:51 +0200 Subject: firewire: cdev: add PHY packet reception Add an FW_CDEV_IOC_RECEIVE_PHY_PACKETS ioctl() and FW_CDEV_EVENT_PHY_PACKET_RECEIVED poll()/read() event for /dev/fw*. This can be used to get information from remote PHYs by remote access PHY packets. This is also the 2nd half of the functionality (the receive part) to support a userspace implementation of a VersaPHY transaction layer. Safety considerations: - PHY packets are generally broadcasts, hence some kind of elevated privileges should be required of a process to be able to listen in on PHY packets. This implementation assumes that a process that is allowed to open the /dev/fw* of a local node does have this privilege. There was an inconclusive discussion about introducing POSIX capabilities as a means to check for user privileges for these kinds of operations. Other limitations: - PHY packet reception may be switched on by ioctl() but cannot be switched off again. It would be trivial to provide an off switch, but this is not worth the code. The client should simply close() the fd then, or just ignore further events. - For sake of simplicity of API and kernel-side implementation, no filter per packet content is provided. Signed-off-by: Stefan Richter --- include/linux/firewire-cdev.h | 39 ++++++++++++++++++++++++++++++++------- include/linux/firewire.h | 3 ++- 2 files changed, 34 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firewire-cdev.h b/include/linux/firewire-cdev.h index 5bc051b9a013..b87409160794 100644 --- a/include/linux/firewire-cdev.h +++ b/include/linux/firewire-cdev.h @@ -35,6 +35,7 @@ /* available since kernel version 2.6.36 */ #define FW_CDEV_EVENT_REQUEST2 0x06 #define FW_CDEV_EVENT_PHY_PACKET_SENT 0x07 +#define FW_CDEV_EVENT_PHY_PACKET_RECEIVED 0x08 /** * struct fw_cdev_event_common - Common part of all fw_cdev_event_ types @@ -285,16 +286,24 @@ struct fw_cdev_event_iso_resource { }; /** - * struct fw_cdev_event_phy_packet - A PHY packet was transmitted - * @closure: See &fw_cdev_event_common; - * set by %FW_CDEV_IOC_SEND_PHY_PACKET ioctl - * @type: %FW_CDEV_EVENT_PHY_PACKET_SENT + * struct fw_cdev_event_phy_packet - A PHY packet was transmitted or received + * @closure: See &fw_cdev_event_common; set by %FW_CDEV_IOC_SEND_PHY_PACKET + * or %FW_CDEV_IOC_RECEIVE_PHY_PACKETS ioctl + * @type: %FW_CDEV_EVENT_PHY_PACKET_SENT or %..._RECEIVED * @rcode: %RCODE_..., indicates success or failure of transmission + * @length: Data length in bytes + * @data: Incoming data + * + * If @type is %FW_CDEV_EVENT_PHY_PACKET_SENT, @length is 0 and @data empty. + * If @type is %FW_CDEV_EVENT_PHY_PACKET_RECEIVED, @length is 8 and @data + * consists of the two PHY packet quadlets, in host byte order. */ struct fw_cdev_event_phy_packet { __u64 closure; __u32 type; __u32 rcode; + __u32 length; + __u32 data[0]; }; /** @@ -308,7 +317,9 @@ struct fw_cdev_event_phy_packet { * @iso_resource: Valid if @common.type == * %FW_CDEV_EVENT_ISO_RESOURCE_ALLOCATED or * %FW_CDEV_EVENT_ISO_RESOURCE_DEALLOCATED - * @phy_packet: Valid if @common.type == %FW_CDEV_EVENT_PHY_PACKET_SENT + * @phy_packet: Valid if @common.type == + * %FW_CDEV_EVENT_PHY_PACKET_SENT or + * %FW_CDEV_EVENT_PHY_PACKET_RECEIVED * * Convenience union for userspace use. Events could be read(2) into an * appropriately aligned char buffer and then cast to this union for further @@ -360,6 +371,7 @@ union fw_cdev_event { /* available since kernel version 2.6.36 */ #define FW_CDEV_IOC_SEND_PHY_PACKET _IOWR('#', 0x15, struct fw_cdev_send_phy_packet) +#define FW_CDEV_IOC_RECEIVE_PHY_PACKETS _IOW('#', 0x16, struct fw_cdev_receive_phy_packets) /* * ABI version history @@ -376,9 +388,9 @@ union fw_cdev_event { * - shared use and auto-response for FCP registers * 3 (2.6.34) - made &fw_cdev_get_cycle_timer reliable * - added %FW_CDEV_IOC_GET_CYCLE_TIMER2 - * 4 (2.6.36) - added %FW_CDEV_EVENT_REQUEST2, %FW_CDEV_EVENT_PHY_PACKET_SENT + * 4 (2.6.36) - added %FW_CDEV_EVENT_REQUEST2, %FW_CDEV_EVENT_PHY_PACKET_* * - implemented &fw_cdev_event_bus_reset.bm_node_id - * - added %FW_CDEV_IOC_SEND_PHY_PACKET + * - added %FW_CDEV_IOC_SEND_PHY_PACKET, _RECEIVE_PHY_PACKETS */ #define FW_CDEV_VERSION 3 /* Meaningless; don't use this macro. */ @@ -850,4 +862,17 @@ struct fw_cdev_send_phy_packet { __u32 generation; }; +/** + * struct fw_cdev_receive_phy_packets - start reception of PHY packets + * @closure: Passed back to userspace in phy packet events + * + * This ioctl activates issuing of %FW_CDEV_EVENT_PHY_PACKET_RECEIVED due to + * incoming PHY packets from any node on the same bus as the device. + * + * The ioctl is only permitted on device files which represent a local node. + */ +struct fw_cdev_receive_phy_packets { + __u64 closure; +}; + #endif /* _LINUX_FIREWIRE_CDEV_H */ diff --git a/include/linux/firewire.h b/include/linux/firewire.h index 0c38b8e97722..d974aa4a24c9 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -111,9 +111,10 @@ struct fw_card { bool beta_repeaters_present; int index; - struct list_head link; + struct list_head phy_receiver_list; + struct delayed_work br_work; /* bus reset job */ bool br_short; -- cgit v1.2.3 From cc550216ae9a2993ef3973464714dc1a39ab1f86 Mon Sep 17 00:00:00 2001 From: Stefan Richter Date: Sun, 18 Jul 2010 13:00:50 +0200 Subject: firewire: cdev: add PHY pinging This extends the FW_CDEV_IOC_SEND_PHY_PACKET ioctl() for /dev/fw* to be useful for ping time measurements. One application for it would be gap count optimization in userspace that is based on ping times rather than hop count. (The latter is implemented in firewire-core itself but is not applicable to beta PHYs that act as repeater.) Signed-off-by: Stefan Richter --- include/linux/firewire-cdev.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firewire-cdev.h b/include/linux/firewire-cdev.h index b87409160794..da0fec7e8dc0 100644 --- a/include/linux/firewire-cdev.h +++ b/include/linux/firewire-cdev.h @@ -294,7 +294,10 @@ struct fw_cdev_event_iso_resource { * @length: Data length in bytes * @data: Incoming data * - * If @type is %FW_CDEV_EVENT_PHY_PACKET_SENT, @length is 0 and @data empty. + * If @type is %FW_CDEV_EVENT_PHY_PACKET_SENT, @length is 0 and @data empty, + * except in case of a ping packet: Then, @length is 4, and @data[0] is the + * ping time in 49.152MHz clocks if @rcode is %RCODE_COMPLETE. + * * If @type is %FW_CDEV_EVENT_PHY_PACKET_RECEIVED, @length is 8 and @data * consists of the two PHY packet quadlets, in host byte order. */ -- cgit v1.2.3 From 8e2b2b46ea4ca5ef790dddf78b360ed736a62d7c Mon Sep 17 00:00:00 2001 From: Stefan Richter Date: Fri, 23 Jul 2010 13:05:39 +0200 Subject: firewire: cdev: improve FW_CDEV_IOC_ALLOCATE In both the ieee1394 stack and the firewire stack, the core treats kernelspace drivers better than userspace drivers when it comes to CSR address range allocation: The former may request a register to be placed automatically at a free spot anywhere inside a specified address range. The latter may only request a register at a fixed offset. Hence, userspace drivers which do not require a fixed offset potentially need to implement a retry loop with incremented offset in each retry until the kernel does not fail allocation with EBUSY. This awkward procedure is not fundamentally necessary as the core already provides a superior allocation API to kernelspace drivers. Therefore change the ioctl() ABI by addition of a region_end member in the existing struct fw_cdev_allocate. Userspace and kernelspace APIs work the same way now. There is a small cost to pay by clients though: If client source code is required to compile with older kernel headers too, then any use of the new member fw_cdev_allocate.region_end needs to be enclosed by #ifdef/#endif directives. However, any client program that seriously wants to use address range allocations will require a kernel of cdev ABI version >= 4 at runtime and a linux/firewire-cdev.h header of >= 4 anyway. This is because v4 brings FW_CDEV_EVENT_REQUEST2. The only client program in which build-time compatibility with struct fw_cdev_allocate as found in older kernel headers makes sense is libraw1394. (libraw1394 uses the older broken FW_CDEV_EVENT_REQUEST to implement a makeshift, incorrect transaction responder that does at least work somewhat in many simple scenarios, relying on guesswork by libraw1394 and by libraw1394 based applications. Plus, address range allocation and transaction responder is only one of many features that libraw1394 needs to provide, and these other features need to work with kernel and kernel-headers as old as possible. Any new linux/firewire-cdev.h based client that implements a transaction responder should never attempt to do it like libraw1394; instead it should make a header and kernel of v4 or later a hard requirement.) While we are at it, update the struct fw_cdev_allocate documentation to better reflect the recent fw_cdev_event_request2 ABI addition. Signed-off-by: Stefan Richter --- include/linux/firewire-cdev.h | 29 ++++++++++++++++++++++++----- 1 file changed, 24 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firewire-cdev.h b/include/linux/firewire-cdev.h index da0fec7e8dc0..14831119ff71 100644 --- a/include/linux/firewire-cdev.h +++ b/include/linux/firewire-cdev.h @@ -394,6 +394,7 @@ union fw_cdev_event { * 4 (2.6.36) - added %FW_CDEV_EVENT_REQUEST2, %FW_CDEV_EVENT_PHY_PACKET_* * - implemented &fw_cdev_event_bus_reset.bm_node_id * - added %FW_CDEV_IOC_SEND_PHY_PACKET, _RECEIVE_PHY_PACKETS + * - added &fw_cdev_allocate.region_end */ #define FW_CDEV_VERSION 3 /* Meaningless; don't use this macro. */ @@ -473,17 +474,21 @@ struct fw_cdev_send_response { }; /** - * struct fw_cdev_allocate - Allocate a CSR address range + * struct fw_cdev_allocate - Allocate a CSR in an address range * @offset: Start offset of the address range * @closure: To be passed back to userspace in request events - * @length: Length of the address range, in bytes + * @length: Length of the CSR, in bytes * @handle: Handle to the allocation, written by the kernel + * @region_end: First address above the address range (added in ABI v4, 2.6.36) * * Allocate an address range in the 48-bit address space on the local node * (the controller). This allows userspace to listen for requests with an - * offset within that address range. When the kernel receives a request - * within the range, an &fw_cdev_event_request event will be written back. - * The @closure field is passed back to userspace in the response event. + * offset within that address range. Every time when the kernel receives a + * request within the range, an &fw_cdev_event_request2 event will be emitted. + * (If the kernel or the client implements ABI version <= 3, an + * &fw_cdev_event_request will be generated instead.) + * + * The @closure field is passed back to userspace in these request events. * The @handle field is an out parameter, returning a handle to the allocated * range to be used for later deallocation of the range. * @@ -491,12 +496,26 @@ struct fw_cdev_send_response { * is exclusive except for the FCP command and response registers. If an * exclusive address region is already in use, the ioctl fails with errno set * to %EBUSY. + * + * If kernel and client implement ABI version >= 4, the kernel looks up a free + * spot of size @length inside [@offset..@region_end) and, if found, writes + * the start address of the new CSR back in @offset. I.e. @offset is an + * in and out parameter. If this automatic placement of a CSR in a bigger + * address range is not desired, the client simply needs to set @region_end + * = @offset + @length. + * + * If the kernel or the client implements ABI version <= 3, @region_end is + * ignored and effectively assumed to be @offset + @length. + * + * @region_end is only present in a kernel header >= 2.6.36. If necessary, + * this can for example be tested by #ifdef FW_CDEV_EVENT_REQUEST2. */ struct fw_cdev_allocate { __u64 offset; __u64 closure; __u32 length; __u32 handle; + __u64 region_end; /* available since kernel version 2.6.36 */ }; /** -- cgit v1.2.3 From 22b8f15c2f7130bb0386f548428df2ffd4e81903 Mon Sep 17 00:00:00 2001 From: Patrick Pannuto Date: Mon, 19 Jul 2010 15:09:26 -0700 Subject: timer: Added usleep[_range] timer usleep[_range] are finer precision implementations of msleep and are designed to be drop-in replacements for udelay where a precise sleep / busy-wait is unnecessary. They also allow an easy interface to specify slack when a precise (ish) wakeup is unnecessary to help minimize wakeups Signed-off-by: Patrick Pannuto Cc: akinobu.mita@gmail.com Cc: sboyd@codeaurora.org Acked-by: Arjan van de Ven LKML-Reference: <4C44CDD2.1070708@codeaurora.org> Signed-off-by: Thomas Gleixner --- include/linux/delay.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/delay.h b/include/linux/delay.h index fd832c6d419e..0e303d1aacd8 100644 --- a/include/linux/delay.h +++ b/include/linux/delay.h @@ -45,6 +45,12 @@ extern unsigned long lpj_fine; void calibrate_delay(void); void msleep(unsigned int msecs); unsigned long msleep_interruptible(unsigned int msecs); +void usleep_range(unsigned long min, unsigned long max); + +static inline void usleep(unsigned long usecs) +{ + usleep_range(usecs, usecs); +} static inline void ssleep(unsigned int seconds) { -- cgit v1.2.3 From 808be4b22f47886d2279852ada3d186fc20909bc Mon Sep 17 00:00:00 2001 From: Vasily Khoruzhick Date: Sat, 17 Jul 2010 13:57:03 +0300 Subject: Add s3c-adc-battery driver s3c-adc-battery is driver for monitoring and charging battery on iPAQ H1930/H1940/RX1950. It depends on s3c-adc driver to get battery voltage and current. Signed-off-by: Vasily Khoruzhick Signed-off-by: Anton Vorontsov --- include/linux/s3c_adc_battery.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) create mode 100644 include/linux/s3c_adc_battery.h (limited to 'include/linux') diff --git a/include/linux/s3c_adc_battery.h b/include/linux/s3c_adc_battery.h new file mode 100644 index 000000000000..dbce22faa660 --- /dev/null +++ b/include/linux/s3c_adc_battery.h @@ -0,0 +1,36 @@ +#ifndef _S3C_ADC_BATTERY_H +#define _S3C_ADC_BATTERY_H + +struct s3c_adc_bat_thresh { + int volt; /* mV */ + int cur; /* mA */ + int level; /* percent */ +}; + +struct s3c_adc_bat_pdata { + int (*init)(void); + void (*exit)(void); + void (*enable_charger)(void); + void (*disable_charger)(void); + + int gpio_charge_finished; + + const struct s3c_adc_bat_thresh *lut_noac; + unsigned int lut_noac_cnt; + const struct s3c_adc_bat_thresh *lut_acin; + unsigned int lut_acin_cnt; + + const unsigned int volt_channel; + const unsigned int current_channel; + const unsigned int backup_volt_channel; + + const unsigned int volt_mult; + const unsigned int current_mult; + const unsigned int backup_volt_mult; + const unsigned int internal_impedance; + + const unsigned int backup_volt_max; + const unsigned int backup_volt_min; +}; + +#endif -- cgit v1.2.3 From eca3930163ba8884060ce9d9ff5ef0d9b7c7b00f Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Tue, 8 Jun 2010 07:48:21 -0600 Subject: of: Merge of_platform_bus_type with platform_bus_type of_platform_bus was being used in the same manner as the platform_bus. The only difference being that of_platform_bus devices are generated from data in the device tree, and platform_bus devices are usually statically allocated in platform code. Having them separate causes the problem of device drivers having to be registered twice if it was possible for the same device to appear on either bus. This patch removes of_platform_bus_type and registers all of_platform bus devices and drivers on the platform bus instead. A previous patch made the of_device structure an alias for the platform_device structure, and a shim is used to adapt of_platform_drivers to the platform bus. After all of of_platform_bus drivers are converted to be normal platform drivers, the shim code can be removed. Signed-off-by: Grant Likely Acked-by: David S. Miller --- include/linux/of_device.h | 6 ++++++ include/linux/of_platform.h | 21 ++++++++------------- 2 files changed, 14 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_device.h b/include/linux/of_device.h index 7d27f5a878f6..8cd1fe7864e3 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -65,6 +65,12 @@ static inline int of_driver_match_device(struct device *dev, return 0; } +static inline int of_device_uevent(struct device *dev, + struct kobj_uevent_env *env) +{ + return -ENODEV; +} + #endif /* CONFIG_OF_DEVICE */ #endif /* _LINUX_OF_DEVICE_H */ diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index a51fd30176aa..133ecf31a60f 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -17,19 +17,19 @@ #include #include #include +#include /* - * The of_platform_bus_type is a bus type used by drivers that do not - * attach to a macio or similar bus but still use OF probing - * mechanism + * of_platform_bus_type isn't it's own bus anymore. It's now just an alias + * for the platform bus. */ -extern struct bus_type of_platform_bus_type; +#define of_platform_bus_type platform_bus_type extern const struct of_device_id of_default_bus_ids[]; /* * An of_platform_driver driver is attached to a basic of_device on - * the "platform bus" (of_platform_bus_type). + * the "platform bus" (platform_bus_type). */ struct of_platform_driver { @@ -42,6 +42,7 @@ struct of_platform_driver int (*shutdown)(struct of_device* dev); struct device_driver driver; + struct platform_driver platform_driver; }; #define to_of_platform_driver(drv) \ container_of(drv,struct of_platform_driver, driver) @@ -51,14 +52,8 @@ extern int of_register_driver(struct of_platform_driver *drv, extern void of_unregister_driver(struct of_platform_driver *drv); /* Platform drivers register/unregister */ -static inline int of_register_platform_driver(struct of_platform_driver *drv) -{ - return of_register_driver(drv, &of_platform_bus_type); -} -static inline void of_unregister_platform_driver(struct of_platform_driver *drv) -{ - of_unregister_driver(drv); -} +extern int of_register_platform_driver(struct of_platform_driver *drv); +extern void of_unregister_platform_driver(struct of_platform_driver *drv); extern struct of_device *of_device_alloc(struct device_node *np, const char *bus_id, -- cgit v1.2.3 From 1ab1d63a85cee2545272f63a7644e9f855cb65d0 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Thu, 24 Jun 2010 15:14:37 -0600 Subject: of/platform: remove all of_bus_type and of_platform_bus_type references Both of_bus_type and of_platform_bus_type are just #define aliases for the platform bus. This patch removes all references to them and switches to the of_register_platform_driver()/of_unregister_platform_driver() API for registering. Subsequent patches will convert each user of of_register_platform_driver() into plain platform_drivers without the of_platform_driver shim. At which point the of_register_platform_driver()/of_unregister_platform_driver() functions can be removed. Signed-off-by: Grant Likely Acked-by: David S. Miller --- include/linux/of_platform.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index 133ecf31a60f..429513ae8f6e 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -19,12 +19,6 @@ #include #include -/* - * of_platform_bus_type isn't it's own bus anymore. It's now just an alias - * for the platform bus. - */ -#define of_platform_bus_type platform_bus_type - extern const struct of_device_id of_default_bus_ids[]; /* -- cgit v1.2.3 From 129ac799ad627b1e08382739f9e8cd75d7477fa3 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Tue, 29 Jun 2010 09:26:53 -0700 Subject: of: remove asm/of_platform.h Only thing left in it is of_instantiate_rtc() which can be moved to asm/prom.h on PowerPC and is unused in microblaze. Signed-off-by: Grant Likely Acked-by: David S. Miller --- include/linux/of_platform.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index 429513ae8f6e..a79f59bf61a0 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -52,8 +52,6 @@ extern void of_unregister_platform_driver(struct of_platform_driver *drv); extern struct of_device *of_device_alloc(struct device_node *np, const char *bus_id, struct device *parent); -#include - extern struct of_device *of_find_device_by_node(struct device_node *np); extern int of_bus_type_init(struct bus_type *bus, const char *name); -- cgit v1.2.3 From 295960429675e17ec658320ebb24385727032bed Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Tue, 29 Jun 2010 11:15:54 -0600 Subject: of: remove asm/of_device.h It is mostly unused now. Sparc has a few defines left in it, but they can be moved to other headers. Removing this header means that new architectures adding CONFIG_OF support don't need to also add this header file. Signed-off-by: Grant Likely Acked-by: David S. Miller --- include/linux/of_device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/of_device.h b/include/linux/of_device.h index 8cd1fe7864e3..0f1911994559 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -16,12 +16,12 @@ */ #define of_device platform_device #include +#include /* temporary until merge */ #ifdef CONFIG_OF_DEVICE #include #include #include -#include #define to_of_device(d) container_of(d, struct of_device, dev) -- cgit v1.2.3 From 94a0cb1fc61ab7a0d47d268a7764374efeb2160b Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Thu, 22 Jul 2010 13:59:23 -0600 Subject: of/device: Replace of_device with platform_device in includes and core code of_device is currently just an #define alias to platform_device until it gets removed entirely. This patch removes references to it from the include directories and the core drivers/of code. Signed-off-by: Grant Likely Acked-by: David S. Miller --- include/linux/of_device.h | 10 +++++----- include/linux/of_platform.h | 16 ++++++++-------- 2 files changed, 13 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_device.h b/include/linux/of_device.h index 0f1911994559..e11a0be7893a 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -39,14 +39,14 @@ static inline int of_driver_match_device(const struct device *dev, return of_match_device(drv->of_match_table, dev) != NULL; } -extern struct of_device *of_dev_get(struct of_device *dev); -extern void of_dev_put(struct of_device *dev); +extern struct platform_device *of_dev_get(struct platform_device *dev); +extern void of_dev_put(struct platform_device *dev); -extern int of_device_register(struct of_device *ofdev); -extern void of_device_unregister(struct of_device *ofdev); +extern int of_device_register(struct platform_device *ofdev); +extern void of_device_unregister(struct platform_device *ofdev); extern void of_release_dev(struct device *dev); -static inline void of_device_free(struct of_device *dev) +static inline void of_device_free(struct platform_device *dev) { of_release_dev(&dev->dev); } diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index a79f59bf61a0..b24c5a5b0426 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -27,13 +27,13 @@ extern const struct of_device_id of_default_bus_ids[]; */ struct of_platform_driver { - int (*probe)(struct of_device* dev, + int (*probe)(struct platform_device* dev, const struct of_device_id *match); - int (*remove)(struct of_device* dev); + int (*remove)(struct platform_device* dev); - int (*suspend)(struct of_device* dev, pm_message_t state); - int (*resume)(struct of_device* dev); - int (*shutdown)(struct of_device* dev); + int (*suspend)(struct platform_device* dev, pm_message_t state); + int (*resume)(struct platform_device* dev); + int (*shutdown)(struct platform_device* dev); struct device_driver driver; struct platform_driver platform_driver; @@ -49,16 +49,16 @@ extern void of_unregister_driver(struct of_platform_driver *drv); extern int of_register_platform_driver(struct of_platform_driver *drv); extern void of_unregister_platform_driver(struct of_platform_driver *drv); -extern struct of_device *of_device_alloc(struct device_node *np, +extern struct platform_device *of_device_alloc(struct device_node *np, const char *bus_id, struct device *parent); -extern struct of_device *of_find_device_by_node(struct device_node *np); +extern struct platform_device *of_find_device_by_node(struct device_node *np); extern int of_bus_type_init(struct bus_type *bus, const char *name); #if !defined(CONFIG_SPARC) /* SPARC has its own device registration method */ /* Platform devices and busses creation */ -extern struct of_device *of_platform_device_create(struct device_node *np, +extern struct platform_device *of_platform_device_create(struct device_node *np, const char *bus_id, struct device *parent); -- cgit v1.2.3 From c0dd394ca5e78649b7013c3ce2d6338af9f228f0 Mon Sep 17 00:00:00 2001 From: Jonas Bonn Date: Fri, 23 Jul 2010 20:19:24 +0200 Subject: of: remove of_default_bus_ids This list used was by only two platforms with all other platforms defining an own list of valid bus id's to pass to of_platform_bus_probe. This patch: i) copies the default list to the two platforms that depended on it (powerpc) ii) remove the usage of of_default_bus_ids in of_platform_bus_probe iii) removes the definition of the list from all architectures that defined it Passing a NULL 'matches' parameter to of_platform_bus_probe is still valid; the function returns no error in that case as the NULL value is equivalent to an empty list. Signed-off-by: Jonas Bonn [grant.likely@secretlab.ca: added __initdata annotations, warn on and return error on missing match table, and fix whitespace errors] Signed-off-by: Grant Likely --- include/linux/of_platform.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index b24c5a5b0426..4e6d989c06df 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -19,8 +19,6 @@ #include #include -extern const struct of_device_id of_default_bus_ids[]; - /* * An of_platform_driver driver is attached to a basic of_device on * the "platform bus" (platform_bus_type). -- cgit v1.2.3 From 6cda9fa2575ec0869fe77b0bdf295c0e51868cab Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Sun, 25 Jul 2010 20:39:03 +0900 Subject: nilfs2: avoid rec_len overflow with 64KB block size With 64KB blocksize, a directory entry can have size 64KB which does not fit into 16 bits we have for entry length. So this patch stores 0xffff instead and converts value when read from / written to disk. Nilfs derives its directory implementation from ext2 filesystem, and this draws upon the corresponding change on ext2. Signed-off-by: Ryusuke Konishi --- include/linux/nilfs2_fs.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nilfs2_fs.h b/include/linux/nilfs2_fs.h index 7dd4cd494490..970828a5ffc5 100644 --- a/include/linux/nilfs2_fs.h +++ b/include/linux/nilfs2_fs.h @@ -326,7 +326,25 @@ enum { #define NILFS_DIR_ROUND (NILFS_DIR_PAD - 1) #define NILFS_DIR_REC_LEN(name_len) (((name_len) + 12 + NILFS_DIR_ROUND) & \ ~NILFS_DIR_ROUND) +#define NILFS_MAX_REC_LEN ((1<<16)-1) +static inline unsigned nilfs_rec_len_from_disk(__le16 dlen) +{ + unsigned len = le16_to_cpu(dlen); + + if (len == NILFS_MAX_REC_LEN) + return 1 << 16; + return len; +} + +static inline __le16 nilfs_rec_len_to_disk(unsigned len) +{ + if (len == (1 << 16)) + return cpu_to_le16(NILFS_MAX_REC_LEN); + else if (len > (1 << 16)) + BUG(); + return cpu_to_le16(len); +} /** * struct nilfs_finfo - file information -- cgit v1.2.3 From 89c0fd014d34d409a7b196667c2b9a4813b6c968 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Sun, 25 Jul 2010 22:44:53 +0900 Subject: nilfs2: reject filesystem with unsupported block size This inserts sanity check that refuses to mount a filesystem with unsupported block size. Previously, kernel code of nilfs was looking only limitation of devices though mkfs.nilfs2 limits the range of block sizes; there was no check that prevents rec_len overflow with larger block sizes. With this change, block sizes larger than 64KB or smaller than 1KB will get rejected explicitly by kernel. Signed-off-by: Ryusuke Konishi --- include/linux/nilfs2_fs.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nilfs2_fs.h b/include/linux/nilfs2_fs.h index 970828a5ffc5..f5487b6f91ed 100644 --- a/include/linux/nilfs2_fs.h +++ b/include/linux/nilfs2_fs.h @@ -286,6 +286,12 @@ struct nilfs_super_block { #define NILFS_NAME_LEN 255 +/* + * Block size limitations + */ +#define NILFS_MIN_BLOCK_SIZE 1024 +#define NILFS_MAX_BLOCK_SIZE 65536 + /* * The new version of the directory entry. Since V0 structures are * stored in intel byte order, and the name_len field could never be -- cgit v1.2.3 From ce3bf7ab22527183634a76512d9854a38615e4d5 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Tue, 13 Jul 2010 17:56:19 -0700 Subject: time: Implement timespec_add After accidentally misusing timespec_add_safe, I wanted to make sure we don't accidently trip over that issue again, so I created a simple timespec_add() function which we can use to replace the instances of timespec_add_safe() that don't want the overflow detection. Signed-off-by: John Stultz LKML-Reference: <1279068988-21864-3-git-send-email-johnstul@us.ibm.com> Signed-off-by: Thomas Gleixner --- include/linux/time.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/time.h b/include/linux/time.h index ea3559f0b3f2..9072df83de1f 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -76,9 +76,25 @@ extern unsigned long mktime(const unsigned int year, const unsigned int mon, const unsigned int min, const unsigned int sec); extern void set_normalized_timespec(struct timespec *ts, time_t sec, s64 nsec); + +/* + * timespec_add_safe assumes both values are positive and checks + * for overflow. It will return TIME_T_MAX if the reutrn would be + * smaller then either of the arguments. + */ extern struct timespec timespec_add_safe(const struct timespec lhs, const struct timespec rhs); + +static inline struct timespec timespec_add(struct timespec lhs, + struct timespec rhs) +{ + struct timespec ts_delta; + set_normalized_timespec(&ts_delta, lhs.tv_sec + rhs.tv_sec, + lhs.tv_nsec + rhs.tv_nsec); + return ts_delta; +} + /* * sub = lhs - rhs, in normalized form */ -- cgit v1.2.3 From 7615856ebfee52b080c22d263ca4debbd0df0ac1 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Tue, 13 Jul 2010 17:56:23 -0700 Subject: timkeeping: Fix update_vsyscall to provide wall_to_monotonic offset update_vsyscall() did not provide the wall_to_monotoinc offset, so arch specific implementations tend to reference wall_to_monotonic directly. This limits future cleanups in the timekeeping core, so this patch fixes the update_vsyscall interface to provide wall_to_monotonic, allowing wall_to_monotonic to be made static as planned in Documentation/feature-removal-schedule.txt Signed-off-by: John Stultz Cc: Martin Schwidefsky Cc: Anton Blanchard Cc: Paul Mackerras Cc: Tony Luck LKML-Reference: <1279068988-21864-7-git-send-email-johnstul@us.ibm.com> Signed-off-by: Thomas Gleixner --- include/linux/clocksource.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 5ea3c60c160c..21677d99a161 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -313,11 +313,13 @@ clocksource_calc_mult_shift(struct clocksource *cs, u32 freq, u32 minsec) #ifdef CONFIG_GENERIC_TIME_VSYSCALL extern void -update_vsyscall(struct timespec *ts, struct clocksource *c, u32 mult); +update_vsyscall(struct timespec *ts, struct timespec *wtm, + struct clocksource *c, u32 mult); extern void update_vsyscall_tz(void); #else static inline void -update_vsyscall(struct timespec *ts, struct clocksource *c, u32 mult) +update_vsyscall(struct timespec *ts, struct timespec *wtm, + struct clocksource *c, u32 mult) { } -- cgit v1.2.3 From 8ab4351a4c888016620f43bde605b3d0964af339 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Tue, 13 Jul 2010 17:56:25 -0700 Subject: hrtimer: Cleanup direct access to wall_to_monotonic Provides an accessor function to replace hrtimer.c's direct access of wall_to_monotonic. This will allow wall_to_monotonic to be made static as planned in Documentation/feature-removal-schedule.txt Signed-off-by: John Stultz LKML-Reference: <1279068988-21864-9-git-send-email-johnstul@us.ibm.com> Signed-off-by: Thomas Gleixner --- include/linux/time.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/time.h b/include/linux/time.h index 9072df83de1f..a57e0f67b3d0 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -126,7 +126,8 @@ extern int timekeeping_suspended; unsigned long get_seconds(void); struct timespec current_kernel_time(void); -struct timespec __current_kernel_time(void); /* does not hold xtime_lock */ +struct timespec __current_kernel_time(void); /* does not take xtime_lock */ +struct timespec __get_wall_to_monotonic(void); /* does not take xtime_lock */ struct timespec get_monotonic_coarse(void); #define CURRENT_TIME (current_kernel_time()) -- cgit v1.2.3 From 0fb86b06298b6cd3205cac2e68a499f269282dac Mon Sep 17 00:00:00 2001 From: John Stultz Date: Tue, 13 Jul 2010 17:56:26 -0700 Subject: timekeeping: Make xtime and wall_to_monotonic static This patch makes xtime and wall_to_monotonic static, as planned in Documentation/feature-removal-schedule.txt. This will allow for further cleanups to the timekeeping core. Signed-off-by: John Stultz LKML-Reference: <1279068988-21864-10-git-send-email-johnstul@us.ibm.com> Signed-off-by: Thomas Gleixner --- include/linux/time.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/time.h b/include/linux/time.h index a57e0f67b3d0..cb34e35fabac 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -113,8 +113,6 @@ static inline struct timespec timespec_sub(struct timespec lhs, #define timespec_valid(ts) \ (((ts)->tv_sec >= 0) && (((unsigned long) (ts)->tv_nsec) < NSEC_PER_SEC)) -extern struct timespec xtime; -extern struct timespec wall_to_monotonic; extern seqlock_t xtime_lock; extern void read_persistent_clock(struct timespec *ts); -- cgit v1.2.3 From 852db46d55e85b475a72e665ca08d3317769ceef Mon Sep 17 00:00:00 2001 From: John Stultz Date: Tue, 13 Jul 2010 17:56:28 -0700 Subject: clocksource: Add __clocksource_updatefreq_hz/khz methods To properly handle clocksources that change frequencies at the clocksource->enable() point, this patch adds a method that will update the clocksource's mult/shift and max_idle_ns values. Signed-off-by: John Stultz LKML-Reference: <1279068988-21864-12-git-send-email-johnstul@us.ibm.com> Signed-off-by: Thomas Gleixner --- include/linux/clocksource.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 21677d99a161..c37b21ad5a3b 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -292,6 +292,8 @@ clocks_calc_mult_shift(u32 *mult, u32 *shift, u32 from, u32 to, u32 minsec); */ extern int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq); +extern void +__clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq); static inline int clocksource_register_hz(struct clocksource *cs, u32 hz) { @@ -303,6 +305,15 @@ static inline int clocksource_register_khz(struct clocksource *cs, u32 khz) return __clocksource_register_scale(cs, 1000, khz); } +static inline void __clocksource_updatefreq_hz(struct clocksource *cs, u32 hz) +{ + __clocksource_updatefreq_scale(cs, 1, hz); +} + +static inline void __clocksource_updatefreq_khz(struct clocksource *cs, u32 khz) +{ + __clocksource_updatefreq_scale(cs, 1000, khz); +} static inline void clocksource_calc_mult_shift(struct clocksource *cs, u32 freq, u32 minsec) -- cgit v1.2.3 From a0d40c80256e31b23849f2ba781b74bf0218a1fa Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Fri, 26 Mar 2010 15:28:51 -0700 Subject: vmap: add flag to allow lazy unmap to be disabled at runtime Add a flag to force lazy_max_pages() to zero to prevent any outstanding mapped pages. We'll need this for Xen. Signed-off-by: Jeremy Fitzhardinge Signed-off-by: Konrad Rzeszutek Wilk Acked-by: Nick Piggin --- include/linux/vmalloc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 227c2a585e4f..b840fdaf438c 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -7,6 +7,8 @@ struct vm_area_struct; /* vma defining user mapping in mm_types.h */ +extern bool vmap_lazy_unmap; + /* bits in flags of vmalloc's vm_struct below */ #define VM_IOREMAP 0x00000001 /* ioremap() and friends */ #define VM_ALLOC 0x00000002 /* vmalloc() */ -- cgit v1.2.3 From 47def82672b3ba4e7c5e9a4fe48a556f8684d0d6 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Tue, 27 Jul 2010 11:56:05 -0400 Subject: jbd2: Remove __GFP_NOFAIL from jbd2 layer __GFP_NOFAIL is going away, so add our own retry loop. Also add jbd2__journal_start() and jbd2__journal_restart() which take a gfp mask, so that file systems can optionally (re)start transaction handles using GFP_KERNEL. If they do this, then they need to be prepared to handle receiving an PTR_ERR(-ENOMEM) error, and be ready to reflect that error up to userspace. Signed-off-by: "Theodore Ts'o" --- include/linux/jbd2.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index a4d2e9f7088a..5a72bc75b273 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1081,7 +1081,9 @@ static inline handle_t *journal_current_handle(void) */ extern handle_t *jbd2_journal_start(journal_t *, int nblocks); -extern int jbd2_journal_restart (handle_t *, int nblocks); +extern handle_t *jbd2__journal_start(journal_t *, int nblocks, int gfp_mask); +extern int jbd2_journal_restart(handle_t *, int nblocks); +extern int jbd2__journal_restart(handle_t *, int nblocks, int gfp_mask); extern int jbd2_journal_extend (handle_t *, int nblocks); extern int jbd2_journal_get_write_access(handle_t *, struct buffer_head *); extern int jbd2_journal_get_create_access (handle_t *, struct buffer_head *); -- cgit v1.2.3 From 552ef8024f909d9b3a7442d0ab0d48a22de24e9e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 27 Jul 2010 11:56:06 -0400 Subject: direct-io: move aio_complete into ->end_io Filesystems with unwritten extent support must not complete an AIO request until the transaction to convert the extent has been commited. That means the aio_complete calls needs to be moved into the ->end_io callback so that the filesystem can control when to call it exactly. This makes a bit of a mess out of dio_complete and the ->end_io callback prototype even more complicated. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Signed-off-by: "Theodore Ts'o" --- include/linux/fs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 471e1ff5079a..a0912f6075e5 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -415,7 +415,8 @@ struct buffer_head; typedef int (get_block_t)(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset, - ssize_t bytes, void *private); + ssize_t bytes, void *private, int ret, + bool is_async); /* * Attribute flags. These should be or-ed together to figure out what -- cgit v1.2.3 From b3c567e474b5ba4447b6e16063a3b0cffc22d205 Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Wed, 21 Jul 2010 13:28:10 +0530 Subject: intel_mid: Add Mrst & Mfld DMA Drivers This patch add DMA drivers for DMA controllers in Langwell chipset of Intel(R) Moorestown platform and DMA controllers in Penwell of Intel(R) Medfield platfrom This patch adds support for Moorestown DMAC1 and DMAC2 controllers. It also add support for Medfiled GP DMA and DMAC1 controllers. These controllers supports memory to peripheral and peripheral to memory transfers. It support only single block transfers. This driver is based on Kernel DMA engine Anyone who wishes to use this controller should use DMA engine APIs This controller exposes DMA_SLAVE capabilities and notifies the client drivers of DMA transaction completion Config option required to be enabled CONFIG_INTEL_MID_DMAC=y Signed-off-by: Vinod Koul Signed-off-by: Alan Cox Signed-off-by: Dan Williams --- include/linux/intel_mid_dma.h | 86 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 86 insertions(+) create mode 100644 include/linux/intel_mid_dma.h (limited to 'include/linux') diff --git a/include/linux/intel_mid_dma.h b/include/linux/intel_mid_dma.h new file mode 100644 index 000000000000..d9d08b6269b6 --- /dev/null +++ b/include/linux/intel_mid_dma.h @@ -0,0 +1,86 @@ +/* + * intel_mid_dma.h - Intel MID DMA Drivers + * + * Copyright (C) 2008-10 Intel Corp + * Author: Vinod Koul + * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; version 2 of the License. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA. + * + * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + * + * + */ +#ifndef __INTEL_MID_DMA_H__ +#define __INTEL_MID_DMA_H__ + +#include + +/*DMA transaction width, src and dstn width would be same +The DMA length must be width aligned, +for 32 bit width the length must be 32 bit (4bytes) aligned only*/ +enum intel_mid_dma_width { + LNW_DMA_WIDTH_8BIT = 0x0, + LNW_DMA_WIDTH_16BIT = 0x1, + LNW_DMA_WIDTH_32BIT = 0x2, +}; + +/*DMA mode configurations*/ +enum intel_mid_dma_mode { + LNW_DMA_PER_TO_MEM = 0, /*periphral to memory configuration*/ + LNW_DMA_MEM_TO_PER, /*memory to periphral configuration*/ + LNW_DMA_MEM_TO_MEM, /*mem to mem confg (testing only)*/ +}; + +/*DMA handshaking*/ +enum intel_mid_dma_hs_mode { + LNW_DMA_HW_HS = 0, /*HW Handshaking only*/ + LNW_DMA_SW_HS = 1, /*SW Handshaking not recommended*/ +}; + +/*Burst size configuration*/ +enum intel_mid_dma_msize { + LNW_DMA_MSIZE_1 = 0x0, + LNW_DMA_MSIZE_4 = 0x1, + LNW_DMA_MSIZE_8 = 0x2, + LNW_DMA_MSIZE_16 = 0x3, + LNW_DMA_MSIZE_32 = 0x4, + LNW_DMA_MSIZE_64 = 0x5, +}; + +/** + * struct intel_mid_dma_slave - DMA slave structure + * + * @dirn: DMA trf direction + * @src_width: tx register width + * @dst_width: rx register width + * @hs_mode: HW/SW handshaking mode + * @cfg_mode: DMA data transfer mode (per-per/mem-per/mem-mem) + * @src_msize: Source DMA burst size + * @dst_msize: Dst DMA burst size + * @device_instance: DMA peripheral device instance, we can have multiple + * peripheral device connected to single DMAC + */ +struct intel_mid_dma_slave { + enum dma_data_direction dirn; + enum intel_mid_dma_width src_width; /*width of DMA src txn*/ + enum intel_mid_dma_width dst_width; /*width of DMA dst txn*/ + enum intel_mid_dma_hs_mode hs_mode; /*handshaking*/ + enum intel_mid_dma_mode cfg_mode; /*mode configuration*/ + enum intel_mid_dma_msize src_msize; /*size if src burst*/ + enum intel_mid_dma_msize dst_msize; /*size of dst burst*/ + unsigned int device_instance; /*0, 1 for periphral instance*/ +}; + +#endif /*__INTEL_MID_DMA_H__*/ -- cgit v1.2.3 From e9fd702a58c49dbb14481dca88dad44758da393a Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 20:12:04 -0500 Subject: audit: convert audit watches to use fsnotify instead of inotify Audit currently uses inotify to pin inodes in core and to detect when watched inodes are deleted or unmounted. This patch uses fsnotify instead of inotify. Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 4d6f47b51189..8f8341e9f021 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -58,9 +58,12 @@ FS_MOVED_FROM | FS_MOVED_TO | FS_CREATE |\ FS_DELETE) +#define FS_MOVE (FS_MOVED_FROM | FS_MOVED_TO) + /* listeners that hard code group numbers near the top */ #define DNOTIFY_GROUP_NUM UINT_MAX -#define INOTIFY_GROUP_NUM (DNOTIFY_GROUP_NUM-1) +#define AUDIT_WATCH_GROUP_NUM (DNOTIFY_GROUP_NUM-1) +#define INOTIFY_GROUP_NUM (AUDIT_WATCH_GROUP_NUM-1) struct fsnotify_group; struct fsnotify_event; -- cgit v1.2.3 From 9e1c74321d87a8b079f04d89e750b39a43365e1f Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 20:12:05 -0500 Subject: fsnotify: duplicate fsnotify_mark_entry data between 2 marks Simple copy fsnotify information from one mark to another in preparation for the second mark to replace the first. Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 8f8341e9f021..390516732956 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -342,6 +342,8 @@ extern void fsnotify_recalc_inode_mask(struct inode *inode); extern void fsnotify_init_mark(struct fsnotify_mark_entry *entry, void (*free_mark)(struct fsnotify_mark_entry *entry)); /* find (and take a reference) to a mark associated with group and inode */ extern struct fsnotify_mark_entry *fsnotify_find_mark_entry(struct fsnotify_group *group, struct inode *inode); +/* copy the values from old into new */ +extern void fsnotify_duplicate_mark(struct fsnotify_mark_entry *new, struct fsnotify_mark_entry *old); /* attach the mark to both the group and the inode */ extern int fsnotify_add_mark(struct fsnotify_mark_entry *entry, struct fsnotify_group *group, struct inode *inode); /* given a mark, flag it to be freed when all references are dropped */ -- cgit v1.2.3 From 40554c3dae83bd892b7fbfaa2ea9de739cbcf065 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 20:12:05 -0500 Subject: fsnotify: allow addition of duplicate fsnotify marks This patch allows a task to add a second fsnotify mark to an inode for the same group. This mark will be added to the end of the inode's list and this will never be found by the stand fsnotify_find_mark() function. This is useful if a user wants to add a new mark before removing the old one. Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 390516732956..1679f250d59e 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -345,7 +345,7 @@ extern struct fsnotify_mark_entry *fsnotify_find_mark_entry(struct fsnotify_grou /* copy the values from old into new */ extern void fsnotify_duplicate_mark(struct fsnotify_mark_entry *new, struct fsnotify_mark_entry *old); /* attach the mark to both the group and the inode */ -extern int fsnotify_add_mark(struct fsnotify_mark_entry *entry, struct fsnotify_group *group, struct inode *inode); +extern int fsnotify_add_mark(struct fsnotify_mark_entry *entry, struct fsnotify_group *group, struct inode *inode, int allow_dups); /* given a mark, flag it to be freed when all references are dropped */ extern void fsnotify_destroy_mark_by_entry(struct fsnotify_mark_entry *entry); /* run all the marks in a group, and flag them to be freed */ -- cgit v1.2.3 From 28a3a7eb3b1f3e7d834e19f06e794e429058a4dd Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 20:12:05 -0500 Subject: audit: reimplement audit_trees using fsnotify rather than inotify Simply switch audit_trees from using inotify to using fsnotify for it's inode pinning and disappearing act information. Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 1679f250d59e..e25284371020 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -62,8 +62,9 @@ /* listeners that hard code group numbers near the top */ #define DNOTIFY_GROUP_NUM UINT_MAX -#define AUDIT_WATCH_GROUP_NUM (DNOTIFY_GROUP_NUM-1) -#define INOTIFY_GROUP_NUM (AUDIT_WATCH_GROUP_NUM-1) +#define AUDIT_WATCH_GROUP_NUM (DNOTIFY_GROUP_NUM-1) +#define AUDIT_TREE_GROUP_NUM (AUDIT_WATCH_GROUP_NUM-1) +#define INOTIFY_GROUP_NUM (AUDIT_TREE_GROUP_NUM-1) struct fsnotify_group; struct fsnotify_event; -- cgit v1.2.3 From 2dfc1cae4c42b93b831b2417540df2b895ab7108 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 20:30:52 -0500 Subject: inotify: remove inotify in kernel interface nothing uses inotify in the kernel, drop it! Signed-off-by: Eric Paris --- include/linux/fs.h | 5 -- include/linux/fsnotify.h | 50 +------------- include/linux/inotify.h | 174 ----------------------------------------------- 3 files changed, 3 insertions(+), 226 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 68ca1b0491af..e5598d2f99b9 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -771,11 +771,6 @@ struct inode { struct hlist_head i_fsnotify_mark_entries; /* fsnotify mark entries */ #endif -#ifdef CONFIG_INOTIFY - struct list_head inotify_watches; /* watches on this inode */ - struct mutex inotify_mutex; /* protects the watches list */ -#endif - unsigned long i_state; unsigned long dirtied_when; /* jiffies of first dirtying */ diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 01755909ce81..f958e93feb97 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -11,8 +11,6 @@ * (C) Copyright 2005 Robert Love */ -#include -#include #include #include #include @@ -25,16 +23,12 @@ static inline void fsnotify_d_instantiate(struct dentry *entry, struct inode *inode) { __fsnotify_d_instantiate(entry, inode); - - inotify_d_instantiate(entry, inode); } /* Notify this dentry's parent about a child's events. */ static inline void fsnotify_parent(struct dentry *dentry, __u32 mask) { __fsnotify_parent(dentry, mask); - - inotify_dentry_parent_queue_event(dentry, mask, 0, dentry->d_name.name); } /* @@ -48,8 +42,6 @@ static inline void fsnotify_d_move(struct dentry *entry) * cares about events from this entry. */ __fsnotify_update_dcache_flags(entry); - - inotify_d_move(entry); } /* @@ -57,8 +49,6 @@ static inline void fsnotify_d_move(struct dentry *entry) */ static inline void fsnotify_link_count(struct inode *inode) { - inotify_inode_queue_event(inode, IN_ATTRIB, 0, NULL, NULL); - fsnotify(inode, FS_ATTRIB, inode, FSNOTIFY_EVENT_INODE, NULL, 0); } @@ -70,7 +60,6 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir, int isdir, struct inode *target, struct dentry *moved) { struct inode *source = moved->d_inode; - u32 in_cookie = inotify_get_cookie(); u32 fs_cookie = fsnotify_get_cookie(); __u32 old_dir_mask = (FS_EVENT_ON_CHILD | FS_MOVED_FROM); __u32 new_dir_mask = (FS_EVENT_ON_CHILD | FS_MOVED_TO); @@ -80,31 +69,18 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir, old_dir_mask |= FS_DN_RENAME; if (isdir) { - isdir = IN_ISDIR; old_dir_mask |= FS_IN_ISDIR; new_dir_mask |= FS_IN_ISDIR; } - inotify_inode_queue_event(old_dir, IN_MOVED_FROM|isdir, in_cookie, old_name, - source); - inotify_inode_queue_event(new_dir, IN_MOVED_TO|isdir, in_cookie, new_name, - source); - fsnotify(old_dir, old_dir_mask, old_dir, FSNOTIFY_EVENT_INODE, old_name, fs_cookie); fsnotify(new_dir, new_dir_mask, new_dir, FSNOTIFY_EVENT_INODE, new_name, fs_cookie); - if (target) { - inotify_inode_queue_event(target, IN_DELETE_SELF, 0, NULL, NULL); - inotify_inode_is_dead(target); - - /* this is really a link_count change not a removal */ + if (target) fsnotify_link_count(target); - } - if (source) { - inotify_inode_queue_event(source, IN_MOVE_SELF, 0, NULL, NULL); + if (source) fsnotify(source, FS_MOVE_SELF, moved->d_inode, FSNOTIFY_EVENT_INODE, NULL, 0); - } audit_inode_child(moved, new_dir); } @@ -134,9 +110,6 @@ static inline void fsnotify_nameremove(struct dentry *dentry, int isdir) */ static inline void fsnotify_inoderemove(struct inode *inode) { - inotify_inode_queue_event(inode, IN_DELETE_SELF, 0, NULL, NULL); - inotify_inode_is_dead(inode); - fsnotify(inode, FS_DELETE_SELF, inode, FSNOTIFY_EVENT_INODE, NULL, 0); __fsnotify_inode_delete(inode); } @@ -146,8 +119,6 @@ static inline void fsnotify_inoderemove(struct inode *inode) */ static inline void fsnotify_create(struct inode *inode, struct dentry *dentry) { - inotify_inode_queue_event(inode, IN_CREATE, 0, dentry->d_name.name, - dentry->d_inode); audit_inode_child(dentry, inode); fsnotify(inode, FS_CREATE, dentry->d_inode, FSNOTIFY_EVENT_INODE, dentry->d_name.name, 0); @@ -160,8 +131,6 @@ static inline void fsnotify_create(struct inode *inode, struct dentry *dentry) */ static inline void fsnotify_link(struct inode *dir, struct inode *inode, struct dentry *new_dentry) { - inotify_inode_queue_event(dir, IN_CREATE, 0, new_dentry->d_name.name, - inode); fsnotify_link_count(inode); audit_inode_child(new_dentry, dir); @@ -176,7 +145,6 @@ static inline void fsnotify_mkdir(struct inode *inode, struct dentry *dentry) __u32 mask = (FS_CREATE | FS_IN_ISDIR); struct inode *d_inode = dentry->d_inode; - inotify_inode_queue_event(inode, mask, 0, dentry->d_name.name, d_inode); audit_inode_child(dentry, inode); fsnotify(inode, mask, d_inode, FSNOTIFY_EVENT_INODE, dentry->d_name.name, 0); @@ -193,8 +161,6 @@ static inline void fsnotify_access(struct dentry *dentry) if (S_ISDIR(inode->i_mode)) mask |= FS_IN_ISDIR; - inotify_inode_queue_event(inode, mask, 0, NULL, NULL); - fsnotify_parent(dentry, mask); fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0); } @@ -210,8 +176,6 @@ static inline void fsnotify_modify(struct dentry *dentry) if (S_ISDIR(inode->i_mode)) mask |= FS_IN_ISDIR; - inotify_inode_queue_event(inode, mask, 0, NULL, NULL); - fsnotify_parent(dentry, mask); fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0); } @@ -227,8 +191,6 @@ static inline void fsnotify_open(struct dentry *dentry) if (S_ISDIR(inode->i_mode)) mask |= FS_IN_ISDIR; - inotify_inode_queue_event(inode, mask, 0, NULL, NULL); - fsnotify_parent(dentry, mask); fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0); } @@ -246,8 +208,6 @@ static inline void fsnotify_close(struct file *file) if (S_ISDIR(inode->i_mode)) mask |= FS_IN_ISDIR; - inotify_inode_queue_event(inode, mask, 0, NULL, NULL); - fsnotify_parent(dentry, mask); fsnotify(inode, mask, file, FSNOTIFY_EVENT_FILE, NULL, 0); } @@ -263,8 +223,6 @@ static inline void fsnotify_xattr(struct dentry *dentry) if (S_ISDIR(inode->i_mode)) mask |= FS_IN_ISDIR; - inotify_inode_queue_event(inode, mask, 0, NULL, NULL); - fsnotify_parent(dentry, mask); fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0); } @@ -299,14 +257,12 @@ static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid) if (mask) { if (S_ISDIR(inode->i_mode)) mask |= FS_IN_ISDIR; - inotify_inode_queue_event(inode, mask, 0, NULL, NULL); - fsnotify_parent(dentry, mask); fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0); } } -#if defined(CONFIG_INOTIFY) || defined(CONFIG_FSNOTIFY) /* notify helpers */ +#if defined(CONFIG_FSNOTIFY) /* notify helpers */ /* * fsnotify_oldname_init - save off the old filename before we change it diff --git a/include/linux/inotify.h b/include/linux/inotify.h index 37ea2894b3c0..959a38b8f75d 100644 --- a/include/linux/inotify.h +++ b/include/linux/inotify.h @@ -69,178 +69,4 @@ struct inotify_event { #define IN_CLOEXEC O_CLOEXEC #define IN_NONBLOCK O_NONBLOCK -#ifdef __KERNEL__ - -#include -#include - -/* - * struct inotify_watch - represents a watch request on a specific inode - * - * h_list is protected by ih->mutex of the associated inotify_handle. - * i_list, mask are protected by inode->inotify_mutex of the associated inode. - * ih, inode, and wd are never written to once the watch is created. - * - * Callers must use the established inotify interfaces to access inotify_watch - * contents. The content of this structure is private to the inotify - * implementation. - */ -struct inotify_watch { - struct list_head h_list; /* entry in inotify_handle's list */ - struct list_head i_list; /* entry in inode's list */ - atomic_t count; /* reference count */ - struct inotify_handle *ih; /* associated inotify handle */ - struct inode *inode; /* associated inode */ - __s32 wd; /* watch descriptor */ - __u32 mask; /* event mask for this watch */ -}; - -struct inotify_operations { - void (*handle_event)(struct inotify_watch *, u32, u32, u32, - const char *, struct inode *); - void (*destroy_watch)(struct inotify_watch *); -}; - -#ifdef CONFIG_INOTIFY - -/* Kernel API for producing events */ - -extern void inotify_d_instantiate(struct dentry *, struct inode *); -extern void inotify_d_move(struct dentry *); -extern void inotify_inode_queue_event(struct inode *, __u32, __u32, - const char *, struct inode *); -extern void inotify_dentry_parent_queue_event(struct dentry *, __u32, __u32, - const char *); -extern void inotify_unmount_inodes(struct list_head *); -extern void inotify_inode_is_dead(struct inode *); -extern u32 inotify_get_cookie(void); - -/* Kernel Consumer API */ - -extern struct inotify_handle *inotify_init(const struct inotify_operations *); -extern void inotify_init_watch(struct inotify_watch *); -extern void inotify_destroy(struct inotify_handle *); -extern __s32 inotify_find_watch(struct inotify_handle *, struct inode *, - struct inotify_watch **); -extern __s32 inotify_find_update_watch(struct inotify_handle *, struct inode *, - u32); -extern __s32 inotify_add_watch(struct inotify_handle *, struct inotify_watch *, - struct inode *, __u32); -extern __s32 inotify_clone_watch(struct inotify_watch *, struct inotify_watch *); -extern void inotify_evict_watch(struct inotify_watch *); -extern int inotify_rm_watch(struct inotify_handle *, struct inotify_watch *); -extern int inotify_rm_wd(struct inotify_handle *, __u32); -extern void inotify_remove_watch_locked(struct inotify_handle *, - struct inotify_watch *); -extern void get_inotify_watch(struct inotify_watch *); -extern void put_inotify_watch(struct inotify_watch *); -extern int pin_inotify_watch(struct inotify_watch *); -extern void unpin_inotify_watch(struct inotify_watch *); - -#else - -static inline void inotify_d_instantiate(struct dentry *dentry, - struct inode *inode) -{ -} - -static inline void inotify_d_move(struct dentry *dentry) -{ -} - -static inline void inotify_inode_queue_event(struct inode *inode, - __u32 mask, __u32 cookie, - const char *filename, - struct inode *n_inode) -{ -} - -static inline void inotify_dentry_parent_queue_event(struct dentry *dentry, - __u32 mask, __u32 cookie, - const char *filename) -{ -} - -static inline void inotify_unmount_inodes(struct list_head *list) -{ -} - -static inline void inotify_inode_is_dead(struct inode *inode) -{ -} - -static inline u32 inotify_get_cookie(void) -{ - return 0; -} - -static inline struct inotify_handle *inotify_init(const struct inotify_operations *ops) -{ - return ERR_PTR(-EOPNOTSUPP); -} - -static inline void inotify_init_watch(struct inotify_watch *watch) -{ -} - -static inline void inotify_destroy(struct inotify_handle *ih) -{ -} - -static inline __s32 inotify_find_watch(struct inotify_handle *ih, struct inode *inode, - struct inotify_watch **watchp) -{ - return -EOPNOTSUPP; -} - -static inline __s32 inotify_find_update_watch(struct inotify_handle *ih, - struct inode *inode, u32 mask) -{ - return -EOPNOTSUPP; -} - -static inline __s32 inotify_add_watch(struct inotify_handle *ih, - struct inotify_watch *watch, - struct inode *inode, __u32 mask) -{ - return -EOPNOTSUPP; -} - -static inline int inotify_rm_watch(struct inotify_handle *ih, - struct inotify_watch *watch) -{ - return -EOPNOTSUPP; -} - -static inline int inotify_rm_wd(struct inotify_handle *ih, __u32 wd) -{ - return -EOPNOTSUPP; -} - -static inline void inotify_remove_watch_locked(struct inotify_handle *ih, - struct inotify_watch *watch) -{ -} - -static inline void get_inotify_watch(struct inotify_watch *watch) -{ -} - -static inline void put_inotify_watch(struct inotify_watch *watch) -{ -} - -extern inline int pin_inotify_watch(struct inotify_watch *watch) -{ - return 0; -} - -extern inline void unpin_inotify_watch(struct inotify_watch *watch) -{ -} - -#endif /* CONFIG_INOTIFY */ - -#endif /* __KERNEL __ */ - #endif /* _LINUX_INOTIFY_H */ -- cgit v1.2.3 From 7b0a04fbfb35650941af87728d4891515b4fc179 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:21 -0500 Subject: fsnotify: provide the data type to should_send_event fanotify is only interested in event types which contain enough information to open the original file in the context of the fanotify listener. Since fanotify may not want to send events if that data isn't present we pass the data type to the should_send_event function call so fanotify can express its lack of interest. Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index e25284371020..61aed0c54fe9 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -84,7 +84,8 @@ struct fsnotify_event_private_data; * valid group and inode to use to clean up. */ struct fsnotify_ops { - bool (*should_send_event)(struct fsnotify_group *group, struct inode *inode, __u32 mask); + bool (*should_send_event)(struct fsnotify_group *group, struct inode *inode, + __u32 mask, int data_type); int (*handle_event)(struct fsnotify_group *group, struct fsnotify_event *event); void (*free_group_priv)(struct fsnotify_group *group); void (*freeing_mark)(struct fsnotify_mark_entry *entry, struct fsnotify_group *group); -- cgit v1.2.3 From 8112e2d6a7356e8c3ff1f7f3c86f375ed0305705 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:21 -0500 Subject: fsnotify: include data in should_send calls fanotify is going to need to look at file->private_data to know if an event should be sent or not. This passes the data (which might be a file, dentry, inode, or none) to the should_send function calls so fanotify can get that information when available Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 61aed0c54fe9..2766df67f1ec 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -85,7 +85,7 @@ struct fsnotify_event_private_data; */ struct fsnotify_ops { bool (*should_send_event)(struct fsnotify_group *group, struct inode *inode, - __u32 mask, int data_type); + __u32 mask, void *data, int data_type); int (*handle_event)(struct fsnotify_group *group, struct fsnotify_event *event); void (*free_group_priv)(struct fsnotify_group *group); void (*freeing_mark)(struct fsnotify_mark_entry *entry, struct fsnotify_group *group); -- cgit v1.2.3 From 2a12a9d7814631e918dec93abad856e692d5286d Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:21 -0500 Subject: fsnotify: pass a file instead of an inode to open, read, and write fanotify, the upcoming notification system actually needs a struct path so it can do opens in the context of listeners, and it needs a file so it can get f_flags from the original process. Close was the only operation that already was passing a struct file to the notification hook. This patch passes a file for access, modify, and open as well as they are easily available to these hooks. Signed-off-by: Eric Paris --- include/linux/fsnotify.h | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index f958e93feb97..845e57abfb86 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -153,8 +153,9 @@ static inline void fsnotify_mkdir(struct inode *inode, struct dentry *dentry) /* * fsnotify_access - file was read */ -static inline void fsnotify_access(struct dentry *dentry) +static inline void fsnotify_access(struct file *file) { + struct dentry *dentry = file->f_path.dentry; struct inode *inode = dentry->d_inode; __u32 mask = FS_ACCESS; @@ -162,14 +163,15 @@ static inline void fsnotify_access(struct dentry *dentry) mask |= FS_IN_ISDIR; fsnotify_parent(dentry, mask); - fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0); + fsnotify(inode, mask, file, FSNOTIFY_EVENT_FILE, NULL, 0); } /* * fsnotify_modify - file was modified */ -static inline void fsnotify_modify(struct dentry *dentry) +static inline void fsnotify_modify(struct file *file) { + struct dentry *dentry = file->f_path.dentry; struct inode *inode = dentry->d_inode; __u32 mask = FS_MODIFY; @@ -177,14 +179,15 @@ static inline void fsnotify_modify(struct dentry *dentry) mask |= FS_IN_ISDIR; fsnotify_parent(dentry, mask); - fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0); + fsnotify(inode, mask, file, FSNOTIFY_EVENT_FILE, NULL, 0); } /* * fsnotify_open - file was opened */ -static inline void fsnotify_open(struct dentry *dentry) +static inline void fsnotify_open(struct file *file) { + struct dentry *dentry = file->f_path.dentry; struct inode *inode = dentry->d_inode; __u32 mask = FS_OPEN; @@ -192,7 +195,7 @@ static inline void fsnotify_open(struct dentry *dentry) mask |= FS_IN_ISDIR; fsnotify_parent(dentry, mask); - fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0); + fsnotify(inode, mask, file, FSNOTIFY_EVENT_FILE, NULL, 0); } /* -- cgit v1.2.3 From 28c60e37f874dcbb93c4afc839ba5e4911c4f4bc Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:21 -0500 Subject: fsnotify: send struct file when sending events to parents when possible fanotify needs a path in order to open an fd to the object which changed. Currently notifications to inode's parents are done using only the inode. For some parental notification we have the entire file, send that so fanotify can use it. Signed-off-by: Eric Paris --- include/linux/fsnotify.h | 40 +++++++++++++++++++++------------------- include/linux/fsnotify_backend.h | 4 ++-- 2 files changed, 23 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 845e57abfb86..04ea03ea8090 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -26,9 +26,14 @@ static inline void fsnotify_d_instantiate(struct dentry *entry, } /* Notify this dentry's parent about a child's events. */ -static inline void fsnotify_parent(struct dentry *dentry, __u32 mask) +static inline void fsnotify_parent(struct file *file, struct dentry *dentry, __u32 mask) { - __fsnotify_parent(dentry, mask); + BUG_ON(file && dentry); + + if (file) + dentry = file->f_path.dentry; + + __fsnotify_parent(file, dentry, mask); } /* @@ -102,7 +107,7 @@ static inline void fsnotify_nameremove(struct dentry *dentry, int isdir) if (isdir) mask |= FS_IN_ISDIR; - fsnotify_parent(dentry, mask); + fsnotify_parent(NULL, dentry, mask); } /* @@ -155,14 +160,13 @@ static inline void fsnotify_mkdir(struct inode *inode, struct dentry *dentry) */ static inline void fsnotify_access(struct file *file) { - struct dentry *dentry = file->f_path.dentry; - struct inode *inode = dentry->d_inode; + struct inode *inode = file->f_path.dentry->d_inode; __u32 mask = FS_ACCESS; if (S_ISDIR(inode->i_mode)) mask |= FS_IN_ISDIR; - fsnotify_parent(dentry, mask); + fsnotify_parent(file, NULL, mask); fsnotify(inode, mask, file, FSNOTIFY_EVENT_FILE, NULL, 0); } @@ -171,14 +175,13 @@ static inline void fsnotify_access(struct file *file) */ static inline void fsnotify_modify(struct file *file) { - struct dentry *dentry = file->f_path.dentry; - struct inode *inode = dentry->d_inode; + struct inode *inode = file->f_path.dentry->d_inode; __u32 mask = FS_MODIFY; if (S_ISDIR(inode->i_mode)) mask |= FS_IN_ISDIR; - fsnotify_parent(dentry, mask); + fsnotify_parent(file, NULL, mask); fsnotify(inode, mask, file, FSNOTIFY_EVENT_FILE, NULL, 0); } @@ -187,14 +190,13 @@ static inline void fsnotify_modify(struct file *file) */ static inline void fsnotify_open(struct file *file) { - struct dentry *dentry = file->f_path.dentry; - struct inode *inode = dentry->d_inode; + struct inode *inode = file->f_path.dentry->d_inode; __u32 mask = FS_OPEN; if (S_ISDIR(inode->i_mode)) mask |= FS_IN_ISDIR; - fsnotify_parent(dentry, mask); + fsnotify_parent(file, NULL, mask); fsnotify(inode, mask, file, FSNOTIFY_EVENT_FILE, NULL, 0); } @@ -203,15 +205,14 @@ static inline void fsnotify_open(struct file *file) */ static inline void fsnotify_close(struct file *file) { - struct dentry *dentry = file->f_path.dentry; - struct inode *inode = dentry->d_inode; + struct inode *inode = file->f_path.dentry->d_inode; fmode_t mode = file->f_mode; __u32 mask = (mode & FMODE_WRITE) ? FS_CLOSE_WRITE : FS_CLOSE_NOWRITE; if (S_ISDIR(inode->i_mode)) mask |= FS_IN_ISDIR; - fsnotify_parent(dentry, mask); + fsnotify_parent(file, NULL, mask); fsnotify(inode, mask, file, FSNOTIFY_EVENT_FILE, NULL, 0); } @@ -226,7 +227,7 @@ static inline void fsnotify_xattr(struct dentry *dentry) if (S_ISDIR(inode->i_mode)) mask |= FS_IN_ISDIR; - fsnotify_parent(dentry, mask); + fsnotify_parent(NULL, dentry, mask); fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0); } @@ -260,7 +261,8 @@ static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid) if (mask) { if (S_ISDIR(inode->i_mode)) mask |= FS_IN_ISDIR; - fsnotify_parent(dentry, mask); + + fsnotify_parent(NULL, dentry, mask); fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0); } } @@ -283,7 +285,7 @@ static inline void fsnotify_oldname_free(const char *old_name) kfree(old_name); } -#else /* CONFIG_INOTIFY || CONFIG_FSNOTIFY */ +#else /* CONFIG_FSNOTIFY */ static inline const char *fsnotify_oldname_init(const char *name) { @@ -294,6 +296,6 @@ static inline void fsnotify_oldname_free(const char *old_name) { } -#endif /* ! CONFIG_INOTIFY */ +#endif /* CONFIG_FSNOTIFY */ #endif /* _LINUX_FS_NOTIFY_H */ diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 2766df67f1ec..0e0c2b76b067 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -259,7 +259,7 @@ struct fsnotify_mark_entry { /* main fsnotify call to send events */ extern void fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is, const char *name, u32 cookie); -extern void __fsnotify_parent(struct dentry *dentry, __u32 mask); +extern void __fsnotify_parent(struct file *file, struct dentry *dentry, __u32 mask); extern void __fsnotify_inode_delete(struct inode *inode); extern u32 fsnotify_get_cookie(void); @@ -367,7 +367,7 @@ static inline void fsnotify(struct inode *to_tell, __u32 mask, void *data, int d const char *name, u32 cookie) {} -static inline void __fsnotify_parent(struct dentry *dentry, __u32 mask) +static inline void __fsnotify_parent(struct file *file, struct dentry *dentry, __u32 mask) {} static inline void __fsnotify_inode_delete(struct inode *inode) -- cgit v1.2.3 From 74766bbfa99adf8cb8119df6121851edba21c9d9 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:21 -0500 Subject: fsnotify: per group notification queue merge types inotify only wishes to merge a new event with the last event on the notification fifo. fanotify is willing to merge any events including by means of bitwise OR masks of multiple events together. This patch moves the inotify event merging logic out of the generic fsnotify notification.c and into the inotify code. This allows each use of fsnotify to provide their own merge functionality. Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 0e0c2b76b067..25789d45fad8 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -328,8 +328,10 @@ extern struct fsnotify_event_private_data *fsnotify_remove_priv_from_event(struc struct fsnotify_event *event); /* attach the event to the group notification queue */ -extern int fsnotify_add_notify_event(struct fsnotify_group *group, struct fsnotify_event *event, - struct fsnotify_event_private_data *priv); +extern int fsnotify_add_notify_event(struct fsnotify_group *group, + struct fsnotify_event *event, + struct fsnotify_event_private_data *priv, + int (*merge)(struct list_head *, struct fsnotify_event *)); /* true if the group notification queue is empty */ extern bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group); /* return, but do not dequeue the first event on the notification queue */ -- cgit v1.2.3 From b4e4e1407312ae5a267ed7d716e6d4e7120a8430 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:21 -0500 Subject: fsnotify: clone existing events fsnotify_clone_event will take an event, clone it, and return the cloned event to the caller. Since events may be in use by multiple fsnotify groups simultaneously certain event entries (such as the mask) cannot be changed after the event was created. Since fanotify would like to merge events happening on the same file it needs a new clean event to work with so it can change any fields it wishes. Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 25789d45fad8..3a7fff235539 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -363,6 +363,9 @@ extern struct fsnotify_event *fsnotify_create_event(struct inode *to_tell, __u32 void *data, int data_is, const char *name, u32 cookie, gfp_t gfp); +/* fanotify likes to change events after they are on lists... */ +extern struct fsnotify_event *fsnotify_clone_event(struct fsnotify_event *old_event); + #else static inline void fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is, -- cgit v1.2.3 From 1201a5361b9bd6512ae01e6f2b7aa79d458cafb1 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:22 -0500 Subject: fsnotify: replace an event on a list fanotify would like to clone events already on its notification list, make changes to the new event, and then replace the old event on the list with the new event. This patch implements the replace functionality of that process. Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 3a7fff235539..427f6ffab127 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -365,6 +365,8 @@ extern struct fsnotify_event *fsnotify_create_event(struct inode *to_tell, __u32 /* fanotify likes to change events after they are on lists... */ extern struct fsnotify_event *fsnotify_clone_event(struct fsnotify_event *old_event); +extern int fsnotify_replace_event(struct fsnotify_event_holder *old_holder, + struct fsnotify_event *new_event); #else -- cgit v1.2.3 From 74be0cc82835aecad332a29896b0f212ba893403 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:22 -0500 Subject: fsnotify: remove group_num altogether The original fsnotify interface has a group-num which was intended to be able to find a group after it was added. I no longer think this is a necessary thing to do and so we remove the group_num. Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 427f6ffab127..57e503d017c8 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -60,12 +60,6 @@ #define FS_MOVE (FS_MOVED_FROM | FS_MOVED_TO) -/* listeners that hard code group numbers near the top */ -#define DNOTIFY_GROUP_NUM UINT_MAX -#define AUDIT_WATCH_GROUP_NUM (DNOTIFY_GROUP_NUM-1) -#define AUDIT_TREE_GROUP_NUM (AUDIT_WATCH_GROUP_NUM-1) -#define INOTIFY_GROUP_NUM (AUDIT_TREE_GROUP_NUM-1) - struct fsnotify_group; struct fsnotify_event; struct fsnotify_mark_entry; @@ -124,7 +118,6 @@ struct fsnotify_group { * closed. */ atomic_t refcnt; /* things with interest in this group */ - unsigned int group_num; /* simply prevents accidental group collision */ const struct fsnotify_ops *ops; /* how this group handles things */ @@ -312,8 +305,7 @@ static inline void __fsnotify_d_instantiate(struct dentry *dentry, struct inode /* must call when a group changes its ->mask */ extern void fsnotify_recalc_global_mask(void); /* get a reference to an existing or create a new group */ -extern struct fsnotify_group *fsnotify_obtain_group(unsigned int group_num, - __u32 mask, +extern struct fsnotify_group *fsnotify_obtain_group(__u32 mask, const struct fsnotify_ops *ops); /* run all marks associated with this group and update group->mask */ extern void fsnotify_recalc_group_mask(struct fsnotify_group *group); -- cgit v1.2.3 From ffab83402f01555a5fa32efb48a4dd0ce8d12ef5 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:22 -0500 Subject: fsnotify: fsnotify_obtain_group should be fsnotify_alloc_group fsnotify_obtain_group was intended to be able to find an already existing group. Nothing uses that functionality. This just renames it to fsnotify_alloc_group so it is clear what it is doing. Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 57e503d017c8..7d3c03e46862 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -305,11 +305,11 @@ static inline void __fsnotify_d_instantiate(struct dentry *dentry, struct inode /* must call when a group changes its ->mask */ extern void fsnotify_recalc_global_mask(void); /* get a reference to an existing or create a new group */ -extern struct fsnotify_group *fsnotify_obtain_group(__u32 mask, +extern struct fsnotify_group *fsnotify_alloc_group(__u32 mask, const struct fsnotify_ops *ops); /* run all marks associated with this group and update group->mask */ extern void fsnotify_recalc_group_mask(struct fsnotify_group *group); -/* drop reference on a group from fsnotify_obtain_group */ +/* drop reference on a group from fsnotify_alloc_group */ extern void fsnotify_put_group(struct fsnotify_group *group); /* take a reference to an event */ -- cgit v1.2.3 From 0d2e2a1d00d7d23e5bd9bb0935cde7c3d5835c56 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:22 -0500 Subject: fsnotify: drop mask argument from fsnotify_alloc_group Nothing uses the mask argument to fsnotify_alloc_group. This patch drops that argument. Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 7d3c03e46862..58326049ab29 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -305,8 +305,7 @@ static inline void __fsnotify_d_instantiate(struct dentry *dentry, struct inode /* must call when a group changes its ->mask */ extern void fsnotify_recalc_global_mask(void); /* get a reference to an existing or create a new group */ -extern struct fsnotify_group *fsnotify_alloc_group(__u32 mask, - const struct fsnotify_ops *ops); +extern struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops); /* run all marks associated with this group and update group->mask */ extern void fsnotify_recalc_group_mask(struct fsnotify_group *group); /* drop reference on a group from fsnotify_alloc_group */ -- cgit v1.2.3 From 19c2a0e1a2f60112c158342ba5f568f72b741c2c Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:23 -0500 Subject: fsnotify: rename fsnotify_groups to fsnotify_inode_groups Simple renaming patch. fsnotify is about to support mount point listeners so I am renaming fsnotify_groups and fsnotify_mask to indicate these are lists used only for groups which have watches on inodes. Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 58326049ab29..21079ade5620 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -95,10 +95,10 @@ struct fsnotify_ops { struct fsnotify_group { /* * global list of all groups receiving events from fsnotify. - * anchored by fsnotify_groups and protected by either fsnotify_grp_mutex + * anchored by fsnotify_inode_groups and protected by either fsnotify_grp_mutex * or fsnotify_grp_srcu depending on write vs read. */ - struct list_head group_list; + struct list_head inode_group_list; /* * Defines all of the event types in which this group is interested. @@ -136,7 +136,7 @@ struct fsnotify_group { struct list_head mark_entries; /* all inode mark entries for this group */ /* prevents double list_del of group_list. protected by global fsnotify_grp_mutex */ - bool on_group_list; + bool on_inode_group_list; /* groups can define private fields here or use the void *private */ union { -- cgit v1.2.3 From 7131485a93679ff9a543b74df280cfd119eb03ca Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:23 -0500 Subject: fsnotify: mount point listeners list and global mask currently all of the notification systems implemented select which inodes they care about and receive messages only about those inodes (or the children of those inodes.) This patch begins to flesh out fsnotify support for the concept of listeners that want to hear notification for an inode accessed below a given monut point. This patch implements a second list of fsnotify groups to hold these types of groups and a second global mask to hold the events of interest for this type of group. The reason we want a second group list and mask is because the inode based notification should_send_event support which makes each group look for a mark on the given inode. With one nfsmount listener that means that every group would have to take the inode->i_lock, look for their mark, not find one, and return for every operation. By seperating vfsmount from inode listeners only when there is a inode listener will the inode groups have to look for their mark and take the inode lock. vfsmount listeners will have to grab the lock and look for a mark but there should be fewer of them, and one vfsmount listener won't cause the i_lock to be grabbed and released for every fsnotify group on every io operation. Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 21079ade5620..dea48bee057d 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -99,6 +99,10 @@ struct fsnotify_group { * or fsnotify_grp_srcu depending on write vs read. */ struct list_head inode_group_list; + /* + * same as above except anchored by fsnotify_vfsmount_groups + */ + struct list_head vfsmount_group_list; /* * Defines all of the event types in which this group is interested. @@ -137,6 +141,7 @@ struct fsnotify_group { /* prevents double list_del of group_list. protected by global fsnotify_grp_mutex */ bool on_inode_group_list; + bool on_vfsmount_group_list; /* groups can define private fields here or use the void *private */ union { -- cgit v1.2.3 From 3a9fb89f4cd04c23e16397befba92efb5d989b74 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:23 -0500 Subject: fsnotify: include vfsmount in should_send_event when appropriate To ensure that a group will not duplicate events when it receives it based on the vfsmount and the inode should_send_event test we should distinguish those two cases. We pass a vfsmount to this function so groups can make their own determinations. Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index dea48bee057d..c2a04b7e4fca 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -79,7 +79,8 @@ struct fsnotify_event_private_data; */ struct fsnotify_ops { bool (*should_send_event)(struct fsnotify_group *group, struct inode *inode, - __u32 mask, void *data, int data_type); + struct vfsmount *mnt, __u32 mask, void *data, + int data_type); int (*handle_event)(struct fsnotify_group *group, struct fsnotify_event *event); void (*free_group_priv)(struct fsnotify_group *group); void (*freeing_mark)(struct fsnotify_mark_entry *entry, struct fsnotify_group *group); -- cgit v1.2.3 From 2823e04de4f1a49087b58ff2bb8f61361ffd9321 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:23 -0500 Subject: fsnotify: put inode specific fields in an fsnotify_mark in a union The addition of marks on vfs mounts will be simplified if the inode specific parts of a mark and the vfsmnt specific parts of a mark are actually in a union so naming can be easy. This patch just implements the inode struct and the union. Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index c2a04b7e4fca..dca7f2cbde90 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -226,6 +226,15 @@ struct fsnotify_event { struct list_head private_data_list; /* groups can store private data here */ }; +/* + * Inode specific fields in an fsnotify_mark_entry + */ +struct fsnotify_inode_mark { + struct inode *inode; /* inode this entry is associated with */ + struct hlist_node i_list; /* list of mark_entries by inode->i_fsnotify_mark_entries */ + struct list_head free_i_list; /* tmp list used when freeing this mark */ +}; + /* * a mark is simply an entry attached to an in core inode which allows an * fsnotify listener to indicate they are either no longer interested in events @@ -241,12 +250,12 @@ struct fsnotify_mark_entry { /* we hold ref for each i_list and g_list. also one ref for each 'thing' * in kernel that found and may be using this mark. */ atomic_t refcnt; /* active things looking at this mark */ - struct inode *inode; /* inode this entry is associated with */ struct fsnotify_group *group; /* group this mark entry is for */ - struct hlist_node i_list; /* list of mark_entries by inode->i_fsnotify_mark_entries */ struct list_head g_list; /* list of mark_entries by group->i_fsnotify_mark_entries */ - spinlock_t lock; /* protect group, inode, and killme */ - struct list_head free_i_list; /* tmp list used when freeing this mark */ + spinlock_t lock; /* protect group and inode */ + union { + struct fsnotify_inode_mark i; + }; struct list_head free_g_list; /* tmp list used when freeing this mark */ void (*free_mark)(struct fsnotify_mark_entry *entry); /* called on final put+free */ }; -- cgit v1.2.3 From 4136510dd61a1ca151fc5b9d8c1ebd5a8ce2e8f4 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:23 -0500 Subject: fsnotify: add vfsmount specific fields to the fsnotify_mark_entry union vfsmount marks need mostly the same data as inode specific fields, but for consistency and understandability we put that data in a vfsmount specific struct inside a union with inode specific data. Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index dca7f2cbde90..0c0fd4ee2840 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -235,6 +235,15 @@ struct fsnotify_inode_mark { struct list_head free_i_list; /* tmp list used when freeing this mark */ }; +/* + * Mount point specific fields in an fsnotify_mark_entry + */ +struct fsnotify_vfsmount_mark { + struct vfsmount *mnt; /* inode this entry is associated with */ + struct hlist_node m_list; /* list of mark_entries by inode->i_fsnotify_mark_entries */ + struct list_head free_m_list; /* tmp list used when freeing this mark */ +}; + /* * a mark is simply an entry attached to an in core inode which allows an * fsnotify listener to indicate they are either no longer interested in events @@ -255,6 +264,7 @@ struct fsnotify_mark_entry { spinlock_t lock; /* protect group and inode */ union { struct fsnotify_inode_mark i; + struct fsnotify_vfsmount_mark m; }; struct list_head free_g_list; /* tmp list used when freeing this mark */ void (*free_mark)(struct fsnotify_mark_entry *entry); /* called on final put+free */ -- cgit v1.2.3 From 098cf2fc77ee190c92bf9d08d69a13305f2487ec Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:24 -0500 Subject: fsnotify: add flags to fsnotify_mark_entries To differentiate between inode and vfsmount (or other future) types of marks we add a flags field and set the inode bit on inode marks (the only currently supported type of mark) Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 0c0fd4ee2840..cf165857199b 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -267,6 +267,9 @@ struct fsnotify_mark_entry { struct fsnotify_vfsmount_mark m; }; struct list_head free_g_list; /* tmp list used when freeing this mark */ +#define FSNOTIFY_MARK_FLAG_INODE 0x01 +#define FSNOTIFY_MARK_FLAG_VFSMOUNT 0x02 + unsigned int flags; /* vfsmount or inode mark? */ void (*free_mark)(struct fsnotify_mark_entry *entry); /* called on final put+free */ }; -- cgit v1.2.3 From 72acc854427948efed7a83da27f7dc3239ac9afc Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Thu, 17 Dec 2009 21:24:24 -0500 Subject: fsnotify: kill FSNOTIFY_EVENT_FILE Some fsnotify operations send a struct file. This is more information than we technically need. We instead send a struct path in all cases instead of sometimes a path and sometimes a file. Signed-off-by: Andreas Gruenbacher Signed-off-by: Eric Paris --- include/linux/fsnotify.h | 36 +++++++++++++++++++----------------- include/linux/fsnotify_backend.h | 5 ++--- 2 files changed, 21 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 04ea03ea8090..06d296d85ebf 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -26,14 +26,12 @@ static inline void fsnotify_d_instantiate(struct dentry *entry, } /* Notify this dentry's parent about a child's events. */ -static inline void fsnotify_parent(struct file *file, struct dentry *dentry, __u32 mask) +static inline void fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask) { - BUG_ON(file && dentry); + if (!dentry) + dentry = path->dentry; - if (file) - dentry = file->f_path.dentry; - - __fsnotify_parent(file, dentry, mask); + __fsnotify_parent(path, dentry, mask); } /* @@ -160,14 +158,15 @@ static inline void fsnotify_mkdir(struct inode *inode, struct dentry *dentry) */ static inline void fsnotify_access(struct file *file) { - struct inode *inode = file->f_path.dentry->d_inode; + struct path *path = &file->f_path; + struct inode *inode = path->dentry->d_inode; __u32 mask = FS_ACCESS; if (S_ISDIR(inode->i_mode)) mask |= FS_IN_ISDIR; - fsnotify_parent(file, NULL, mask); - fsnotify(inode, mask, file, FSNOTIFY_EVENT_FILE, NULL, 0); + fsnotify_parent(path, NULL, mask); + fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0); } /* @@ -175,14 +174,15 @@ static inline void fsnotify_access(struct file *file) */ static inline void fsnotify_modify(struct file *file) { - struct inode *inode = file->f_path.dentry->d_inode; + struct path *path = &file->f_path; + struct inode *inode = path->dentry->d_inode; __u32 mask = FS_MODIFY; if (S_ISDIR(inode->i_mode)) mask |= FS_IN_ISDIR; - fsnotify_parent(file, NULL, mask); - fsnotify(inode, mask, file, FSNOTIFY_EVENT_FILE, NULL, 0); + fsnotify_parent(path, NULL, mask); + fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0); } /* @@ -190,14 +190,15 @@ static inline void fsnotify_modify(struct file *file) */ static inline void fsnotify_open(struct file *file) { - struct inode *inode = file->f_path.dentry->d_inode; + struct path *path = &file->f_path; + struct inode *inode = path->dentry->d_inode; __u32 mask = FS_OPEN; if (S_ISDIR(inode->i_mode)) mask |= FS_IN_ISDIR; - fsnotify_parent(file, NULL, mask); - fsnotify(inode, mask, file, FSNOTIFY_EVENT_FILE, NULL, 0); + fsnotify_parent(path, NULL, mask); + fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0); } /* @@ -205,6 +206,7 @@ static inline void fsnotify_open(struct file *file) */ static inline void fsnotify_close(struct file *file) { + struct path *path = &file->f_path; struct inode *inode = file->f_path.dentry->d_inode; fmode_t mode = file->f_mode; __u32 mask = (mode & FMODE_WRITE) ? FS_CLOSE_WRITE : FS_CLOSE_NOWRITE; @@ -212,8 +214,8 @@ static inline void fsnotify_close(struct file *file) if (S_ISDIR(inode->i_mode)) mask |= FS_IN_ISDIR; - fsnotify_parent(file, NULL, mask); - fsnotify(inode, mask, file, FSNOTIFY_EVENT_FILE, NULL, 0); + fsnotify_parent(path, NULL, mask); + fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0); } /* diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index cf165857199b..7a6ba755acc3 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -214,7 +214,6 @@ struct fsnotify_event { #define FSNOTIFY_EVENT_NONE 0 #define FSNOTIFY_EVENT_PATH 1 #define FSNOTIFY_EVENT_INODE 2 -#define FSNOTIFY_EVENT_FILE 3 int data_type; /* which of the above union we have */ atomic_t refcnt; /* how many groups still are using/need to send this event */ __u32 mask; /* the type of access, bitwise OR for FS_* event types */ @@ -280,7 +279,7 @@ struct fsnotify_mark_entry { /* main fsnotify call to send events */ extern void fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is, const char *name, u32 cookie); -extern void __fsnotify_parent(struct file *file, struct dentry *dentry, __u32 mask); +extern void __fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask); extern void __fsnotify_inode_delete(struct inode *inode); extern u32 fsnotify_get_cookie(void); @@ -393,7 +392,7 @@ static inline void fsnotify(struct inode *to_tell, __u32 mask, void *data, int d const char *name, u32 cookie) {} -static inline void __fsnotify_parent(struct file *file, struct dentry *dentry, __u32 mask) +static inline void __fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask) {} static inline void __fsnotify_inode_delete(struct inode *inode) -- cgit v1.2.3 From e61ce86737b4d60521e4e71f9892fe4bdcfb688b Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:24 -0500 Subject: fsnotify: rename fsnotify_mark_entry to just fsnotify_mark The name is long and it serves no real purpose. So rename fsnotify_mark_entry to just fsnotify_mark. Signed-off-by: Eric Paris --- include/linux/fs.h | 2 +- include/linux/fsnotify.h | 18 +++++++++--------- include/linux/fsnotify_backend.h | 38 +++++++++++++++++++------------------- 3 files changed, 29 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index e5598d2f99b9..85fe89c43487 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -768,7 +768,7 @@ struct inode { #ifdef CONFIG_FSNOTIFY __u32 i_fsnotify_mask; /* all events this inode cares about */ - struct hlist_head i_fsnotify_mark_entries; /* fsnotify mark entries */ + struct hlist_head i_fsnotify_marks; #endif unsigned long i_state; diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 06d296d85ebf..62e93a9dd115 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -19,10 +19,10 @@ * fsnotify_d_instantiate - instantiate a dentry for inode * Called with dcache_lock held. */ -static inline void fsnotify_d_instantiate(struct dentry *entry, - struct inode *inode) +static inline void fsnotify_d_instantiate(struct dentry *dentry, + struct inode *inode) { - __fsnotify_d_instantiate(entry, inode); + __fsnotify_d_instantiate(dentry, inode); } /* Notify this dentry's parent about a child's events. */ @@ -35,16 +35,16 @@ static inline void fsnotify_parent(struct path *path, struct dentry *dentry, __u } /* - * fsnotify_d_move - entry has been moved - * Called with dcache_lock and entry->d_lock held. + * fsnotify_d_move - dentry has been moved + * Called with dcache_lock and dentry->d_lock held. */ -static inline void fsnotify_d_move(struct dentry *entry) +static inline void fsnotify_d_move(struct dentry *dentry) { /* - * On move we need to update entry->d_flags to indicate if the new parent - * cares about events from this entry. + * On move we need to update dentry->d_flags to indicate if the new parent + * cares about events from this dentry. */ - __fsnotify_update_dcache_flags(entry); + __fsnotify_update_dcache_flags(dentry); } /* diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 7a6ba755acc3..59c072e8fddd 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -62,7 +62,7 @@ struct fsnotify_group; struct fsnotify_event; -struct fsnotify_mark_entry; +struct fsnotify_mark; struct fsnotify_event_private_data; /* @@ -83,7 +83,7 @@ struct fsnotify_ops { int data_type); int (*handle_event)(struct fsnotify_group *group, struct fsnotify_event *event); void (*free_group_priv)(struct fsnotify_group *group); - void (*freeing_mark)(struct fsnotify_mark_entry *entry, struct fsnotify_group *group); + void (*freeing_mark)(struct fsnotify_mark *entry, struct fsnotify_group *group); void (*free_event_priv)(struct fsnotify_event_private_data *priv); }; @@ -133,12 +133,12 @@ struct fsnotify_group { unsigned int q_len; /* events on the queue */ unsigned int max_events; /* maximum events allowed on the list */ - /* stores all fastapth entries assoc with this group so they can be cleaned on unregister */ - spinlock_t mark_lock; /* protect mark_entries list */ + /* stores all fastpath marks assoc with this group so they can be cleaned on unregister */ + spinlock_t mark_lock; /* protect marks_list */ atomic_t num_marks; /* 1 for each mark entry and 1 for not being * past the point of no return when freeing * a group */ - struct list_head mark_entries; /* all inode mark entries for this group */ + struct list_head marks_list; /* all inode marks for this group */ /* prevents double list_del of group_list. protected by global fsnotify_grp_mutex */ bool on_inode_group_list; @@ -226,20 +226,20 @@ struct fsnotify_event { }; /* - * Inode specific fields in an fsnotify_mark_entry + * Inode specific fields in an fsnotify_mark */ struct fsnotify_inode_mark { struct inode *inode; /* inode this entry is associated with */ - struct hlist_node i_list; /* list of mark_entries by inode->i_fsnotify_mark_entries */ + struct hlist_node i_list; /* list of marks by inode->i_fsnotify_marks */ struct list_head free_i_list; /* tmp list used when freeing this mark */ }; /* - * Mount point specific fields in an fsnotify_mark_entry + * Mount point specific fields in an fsnotify_mark */ struct fsnotify_vfsmount_mark { struct vfsmount *mnt; /* inode this entry is associated with */ - struct hlist_node m_list; /* list of mark_entries by inode->i_fsnotify_mark_entries */ + struct hlist_node m_list; /* list of marks by inode->i_fsnotify_marks */ struct list_head free_m_list; /* tmp list used when freeing this mark */ }; @@ -253,13 +253,13 @@ struct fsnotify_vfsmount_mark { * (such as dnotify) will flush these when the open fd is closed and not at * inode eviction or modification. */ -struct fsnotify_mark_entry { +struct fsnotify_mark { __u32 mask; /* mask this mark entry is for */ /* we hold ref for each i_list and g_list. also one ref for each 'thing' * in kernel that found and may be using this mark. */ atomic_t refcnt; /* active things looking at this mark */ struct fsnotify_group *group; /* group this mark entry is for */ - struct list_head g_list; /* list of mark_entries by group->i_fsnotify_mark_entries */ + struct list_head g_list; /* list of marks by group->i_fsnotify_marks */ spinlock_t lock; /* protect group and inode */ union { struct fsnotify_inode_mark i; @@ -269,7 +269,7 @@ struct fsnotify_mark_entry { #define FSNOTIFY_MARK_FLAG_INODE 0x01 #define FSNOTIFY_MARK_FLAG_VFSMOUNT 0x02 unsigned int flags; /* vfsmount or inode mark? */ - void (*free_mark)(struct fsnotify_mark_entry *entry); /* called on final put+free */ + void (*free_mark)(struct fsnotify_mark *entry); /* called on final put+free */ }; #ifdef CONFIG_FSNOTIFY @@ -361,19 +361,19 @@ extern struct fsnotify_event *fsnotify_remove_notify_event(struct fsnotify_group /* run all marks associated with an inode and update inode->i_fsnotify_mask */ extern void fsnotify_recalc_inode_mask(struct inode *inode); -extern void fsnotify_init_mark(struct fsnotify_mark_entry *entry, void (*free_mark)(struct fsnotify_mark_entry *entry)); +extern void fsnotify_init_mark(struct fsnotify_mark *entry, void (*free_mark)(struct fsnotify_mark *entry)); /* find (and take a reference) to a mark associated with group and inode */ -extern struct fsnotify_mark_entry *fsnotify_find_mark_entry(struct fsnotify_group *group, struct inode *inode); +extern struct fsnotify_mark *fsnotify_find_mark_entry(struct fsnotify_group *group, struct inode *inode); /* copy the values from old into new */ -extern void fsnotify_duplicate_mark(struct fsnotify_mark_entry *new, struct fsnotify_mark_entry *old); +extern void fsnotify_duplicate_mark(struct fsnotify_mark *new, struct fsnotify_mark *old); /* attach the mark to both the group and the inode */ -extern int fsnotify_add_mark(struct fsnotify_mark_entry *entry, struct fsnotify_group *group, struct inode *inode, int allow_dups); +extern int fsnotify_add_mark(struct fsnotify_mark *entry, struct fsnotify_group *group, struct inode *inode, int allow_dups); /* given a mark, flag it to be freed when all references are dropped */ -extern void fsnotify_destroy_mark_by_entry(struct fsnotify_mark_entry *entry); +extern void fsnotify_destroy_mark_by_entry(struct fsnotify_mark *entry); /* run all the marks in a group, and flag them to be freed */ extern void fsnotify_clear_marks_by_group(struct fsnotify_group *group); -extern void fsnotify_get_mark(struct fsnotify_mark_entry *entry); -extern void fsnotify_put_mark(struct fsnotify_mark_entry *entry); +extern void fsnotify_get_mark(struct fsnotify_mark *entry); +extern void fsnotify_put_mark(struct fsnotify_mark *entry); extern void fsnotify_unmount_inodes(struct list_head *list); /* put here because inotify does some weird stuff when destroying watches */ -- cgit v1.2.3 From d07754412f9cdc2f4a99318d5ee81ace6715ea99 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:24 -0500 Subject: fsnotify: rename fsnotify_find_mark_entry to fsnotify_find_mark the _entry portion of fsnotify functions is useless. Drop it. Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 59c072e8fddd..83b6bfeb2d66 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -363,13 +363,13 @@ extern struct fsnotify_event *fsnotify_remove_notify_event(struct fsnotify_group extern void fsnotify_recalc_inode_mask(struct inode *inode); extern void fsnotify_init_mark(struct fsnotify_mark *entry, void (*free_mark)(struct fsnotify_mark *entry)); /* find (and take a reference) to a mark associated with group and inode */ -extern struct fsnotify_mark *fsnotify_find_mark_entry(struct fsnotify_group *group, struct inode *inode); +extern struct fsnotify_mark *fsnotify_find_mark(struct fsnotify_group *group, struct inode *inode); /* copy the values from old into new */ extern void fsnotify_duplicate_mark(struct fsnotify_mark *new, struct fsnotify_mark *old); /* attach the mark to both the group and the inode */ extern int fsnotify_add_mark(struct fsnotify_mark *entry, struct fsnotify_group *group, struct inode *inode, int allow_dups); /* given a mark, flag it to be freed when all references are dropped */ -extern void fsnotify_destroy_mark_by_entry(struct fsnotify_mark *entry); +extern void fsnotify_destroy_mark(struct fsnotify_mark *entry); /* run all the marks in a group, and flag them to be freed */ extern void fsnotify_clear_marks_by_group(struct fsnotify_group *group); extern void fsnotify_get_mark(struct fsnotify_mark *entry); -- cgit v1.2.3 From 841bdc10f573aa010dd5818d35a5690b7d9f73ce Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:24 -0500 Subject: fsnotify: rename mark_entry to just mark previously I used mark_entry when talking about marks on inodes. The _entry is pretty useless. Just use "mark" instead. Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 83b6bfeb2d66..ff654c1932f2 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -83,7 +83,7 @@ struct fsnotify_ops { int data_type); int (*handle_event)(struct fsnotify_group *group, struct fsnotify_event *event); void (*free_group_priv)(struct fsnotify_group *group); - void (*freeing_mark)(struct fsnotify_mark *entry, struct fsnotify_group *group); + void (*freeing_mark)(struct fsnotify_mark *mark, struct fsnotify_group *group); void (*free_event_priv)(struct fsnotify_event_private_data *priv); }; @@ -135,7 +135,7 @@ struct fsnotify_group { /* stores all fastpath marks assoc with this group so they can be cleaned on unregister */ spinlock_t mark_lock; /* protect marks_list */ - atomic_t num_marks; /* 1 for each mark entry and 1 for not being + atomic_t num_marks; /* 1 for each mark and 1 for not being * past the point of no return when freeing * a group */ struct list_head marks_list; /* all inode marks for this group */ @@ -229,7 +229,7 @@ struct fsnotify_event { * Inode specific fields in an fsnotify_mark */ struct fsnotify_inode_mark { - struct inode *inode; /* inode this entry is associated with */ + struct inode *inode; /* inode this mark is associated with */ struct hlist_node i_list; /* list of marks by inode->i_fsnotify_marks */ struct list_head free_i_list; /* tmp list used when freeing this mark */ }; @@ -238,13 +238,13 @@ struct fsnotify_inode_mark { * Mount point specific fields in an fsnotify_mark */ struct fsnotify_vfsmount_mark { - struct vfsmount *mnt; /* inode this entry is associated with */ + struct vfsmount *mnt; /* vfsmount this mark is associated with */ struct hlist_node m_list; /* list of marks by inode->i_fsnotify_marks */ struct list_head free_m_list; /* tmp list used when freeing this mark */ }; /* - * a mark is simply an entry attached to an in core inode which allows an + * a mark is simply an object attached to an in core inode which allows an * fsnotify listener to indicate they are either no longer interested in events * of a type matching mask or only interested in those events. * @@ -254,11 +254,11 @@ struct fsnotify_vfsmount_mark { * inode eviction or modification. */ struct fsnotify_mark { - __u32 mask; /* mask this mark entry is for */ + __u32 mask; /* mask this mark is for */ /* we hold ref for each i_list and g_list. also one ref for each 'thing' * in kernel that found and may be using this mark. */ atomic_t refcnt; /* active things looking at this mark */ - struct fsnotify_group *group; /* group this mark entry is for */ + struct fsnotify_group *group; /* group this mark is for */ struct list_head g_list; /* list of marks by group->i_fsnotify_marks */ spinlock_t lock; /* protect group and inode */ union { @@ -269,7 +269,7 @@ struct fsnotify_mark { #define FSNOTIFY_MARK_FLAG_INODE 0x01 #define FSNOTIFY_MARK_FLAG_VFSMOUNT 0x02 unsigned int flags; /* vfsmount or inode mark? */ - void (*free_mark)(struct fsnotify_mark *entry); /* called on final put+free */ + void (*free_mark)(struct fsnotify_mark *mark); /* called on final put+free */ }; #ifdef CONFIG_FSNOTIFY @@ -361,19 +361,19 @@ extern struct fsnotify_event *fsnotify_remove_notify_event(struct fsnotify_group /* run all marks associated with an inode and update inode->i_fsnotify_mask */ extern void fsnotify_recalc_inode_mask(struct inode *inode); -extern void fsnotify_init_mark(struct fsnotify_mark *entry, void (*free_mark)(struct fsnotify_mark *entry)); +extern void fsnotify_init_mark(struct fsnotify_mark *mark, void (*free_mark)(struct fsnotify_mark *mark)); /* find (and take a reference) to a mark associated with group and inode */ extern struct fsnotify_mark *fsnotify_find_mark(struct fsnotify_group *group, struct inode *inode); /* copy the values from old into new */ extern void fsnotify_duplicate_mark(struct fsnotify_mark *new, struct fsnotify_mark *old); /* attach the mark to both the group and the inode */ -extern int fsnotify_add_mark(struct fsnotify_mark *entry, struct fsnotify_group *group, struct inode *inode, int allow_dups); +extern int fsnotify_add_mark(struct fsnotify_mark *mark, struct fsnotify_group *group, struct inode *inode, int allow_dups); /* given a mark, flag it to be freed when all references are dropped */ -extern void fsnotify_destroy_mark(struct fsnotify_mark *entry); +extern void fsnotify_destroy_mark(struct fsnotify_mark *mark); /* run all the marks in a group, and flag them to be freed */ extern void fsnotify_clear_marks_by_group(struct fsnotify_group *group); -extern void fsnotify_get_mark(struct fsnotify_mark *entry); -extern void fsnotify_put_mark(struct fsnotify_mark *entry); +extern void fsnotify_get_mark(struct fsnotify_mark *mark); +extern void fsnotify_put_mark(struct fsnotify_mark *mark); extern void fsnotify_unmount_inodes(struct list_head *list); /* put here because inotify does some weird stuff when destroying watches */ -- cgit v1.2.3 From ecf081d1a73b077916f514f2ec744ded32b88ca1 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:25 -0500 Subject: vfs: introduce FMODE_NONOTIFY This is a new f_mode which can only be set by the kernel. It indicates that the fd was opened by fanotify and should not cause future fanotify events. This is needed to prevent fanotify livelock. An example of obvious livelock is from fanotify close events. Process A closes file1 This creates a close event for file1. fanotify opens file1 for Listener X Listener X deals with the event and closes its fd for file1. This creates a close event for file1. fanotify opens file1 for Listener X Listener X deals with the event and closes its fd for file1. This creates a close event for file1. fanotify opens file1 for Listener X Listener X deals with the event and closes its fd for file1. notice a pattern? The fix is to add the FMODE_NONOTIFY bit to the open filp done by the kernel for fanotify. Thus when that file is used it will not generate future events. This patch simply defines the bit. Signed-off-by: Eric Paris --- include/linux/fs.h | 6 +++++- include/linux/fsnotify.h | 24 ++++++++++++++++-------- 2 files changed, 21 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 85fe89c43487..50ef4d4c95bf 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -90,6 +90,9 @@ struct inodes_stat_t { /* Expect random access pattern */ #define FMODE_RANDOM ((__force fmode_t)0x1000) +/* File was opened by fanotify and shouldn't generate fanotify events */ +#define FMODE_NONOTIFY ((__force fmode_t)8388608) + /* * The below are the various read and write types that we support. Some of * them include behavioral modifiers that send information down to the @@ -2508,7 +2511,8 @@ int proc_nr_files(struct ctl_table *table, int write, int __init get_filesystem_list(char *buf); #define ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE]) -#define OPEN_FMODE(flag) ((__force fmode_t)((flag + 1) & O_ACCMODE)) +#define OPEN_FMODE(flag) ((__force fmode_t)(((flag + 1) & O_ACCMODE) | \ + (flag & FMODE_NONOTIFY))) #endif /* __KERNEL__ */ #endif /* _LINUX_FS_H */ diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 62e93a9dd115..5184a2b786c1 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -165,8 +165,10 @@ static inline void fsnotify_access(struct file *file) if (S_ISDIR(inode->i_mode)) mask |= FS_IN_ISDIR; - fsnotify_parent(path, NULL, mask); - fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0); + if (!(file->f_mode & FMODE_NONOTIFY)) { + fsnotify_parent(path, NULL, mask); + fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0); + } } /* @@ -181,8 +183,10 @@ static inline void fsnotify_modify(struct file *file) if (S_ISDIR(inode->i_mode)) mask |= FS_IN_ISDIR; - fsnotify_parent(path, NULL, mask); - fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0); + if (!(file->f_mode & FMODE_NONOTIFY)) { + fsnotify_parent(path, NULL, mask); + fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0); + } } /* @@ -197,8 +201,10 @@ static inline void fsnotify_open(struct file *file) if (S_ISDIR(inode->i_mode)) mask |= FS_IN_ISDIR; - fsnotify_parent(path, NULL, mask); - fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0); + if (!(file->f_mode & FMODE_NONOTIFY)) { + fsnotify_parent(path, NULL, mask); + fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0); + } } /* @@ -214,8 +220,10 @@ static inline void fsnotify_close(struct file *file) if (S_ISDIR(inode->i_mode)) mask |= FS_IN_ISDIR; - fsnotify_parent(path, NULL, mask); - fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0); + if (!(file->f_mode & FMODE_NONOTIFY)) { + fsnotify_parent(path, NULL, mask); + fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0); + } } /* -- cgit v1.2.3 From 12ed2e36c98aec6c41559222e311f4aa15d254b6 Mon Sep 17 00:00:00 2001 From: "Signed-off-by: Wu Fengguang" Date: Mon, 8 Feb 2010 12:31:29 -0500 Subject: fanotify: FMODE_NONOTIFY and __O_SYNC in sparc conflict sparc used the same value as FMODE_NONOTIFY so change FMODE_NONOTIFY to be something unique. Signed-off-by: Wu Fengguang Signed-off-by: Eric Paris --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 50ef4d4c95bf..f9a003278758 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -91,7 +91,7 @@ struct inodes_stat_t { #define FMODE_RANDOM ((__force fmode_t)0x1000) /* File was opened by fanotify and shouldn't generate fanotify events */ -#define FMODE_NONOTIFY ((__force fmode_t)8388608) +#define FMODE_NONOTIFY ((__force fmode_t)16777216) /* 0x1000000 */ /* * The below are the various read and write types that we support. Some of -- cgit v1.2.3 From ff0b16a9850e8a240ad59e10b0a1291a8fcf7cbc Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:25 -0500 Subject: fanotify: fscking all notification system fanotify is a novel file notification system which bases notification on giving userspace both an event type (open, close, read, write) and an open file descriptor to the object in question. This should address a number of races and problems with other notification systems like inotify and dnotify and should allow the future implementation of blocking or access controlled notification. These are useful for on access scanners or hierachical storage management schemes. This patch just implements the basics of the fsnotify functions. Signed-off-by: Eric Paris --- include/linux/Kbuild | 1 + include/linux/fanotify.h | 40 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 41 insertions(+) create mode 100644 include/linux/fanotify.h (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index 2fc8e14cc24a..d5cca9a05f14 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -210,6 +210,7 @@ unifdef-y += ethtool.h unifdef-y += eventpoll.h unifdef-y += signalfd.h unifdef-y += ext2_fs.h +unifdef-y += fanotify.h unifdef-y += fb.h unifdef-y += fcntl.h unifdef-y += filter.h diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h new file mode 100644 index 000000000000..b560f86d1401 --- /dev/null +++ b/include/linux/fanotify.h @@ -0,0 +1,40 @@ +#ifndef _LINUX_FANOTIFY_H +#define _LINUX_FANOTIFY_H + +#include + +/* the following events that user-space can register for */ +#define FAN_ACCESS 0x00000001 /* File was accessed */ +#define FAN_MODIFY 0x00000002 /* File was modified */ +#define FAN_CLOSE_WRITE 0x00000008 /* Unwrittable file closed */ +#define FAN_CLOSE_NOWRITE 0x00000010 /* Writtable file closed */ +#define FAN_OPEN 0x00000020 /* File was opened */ + +#define FAN_EVENT_ON_CHILD 0x08000000 /* interested in child events */ + +/* FIXME currently Q's have no limit.... */ +#define FAN_Q_OVERFLOW 0x00004000 /* Event queued overflowed */ + +/* helper events */ +#define FAN_CLOSE (FAN_CLOSE_WRITE | FAN_CLOSE_NOWRITE) /* close */ + +/* + * All of the events - we build the list by hand so that we can add flags in + * the future and not break backward compatibility. Apps will get only the + * events that they originally wanted. Be sure to add new events here! + */ +#define FAN_ALL_EVENTS (FAN_ACCESS |\ + FAN_MODIFY |\ + FAN_CLOSE |\ + FAN_OPEN) + +/* + * All legal FAN bits userspace can request (although possibly not all + * at the same time. + */ +#define FAN_ALL_INCOMING_EVENTS (FAN_ALL_EVENTS |\ + FAN_EVENT_ON_CHILD) +#ifdef __KERNEL__ + +#endif /* __KERNEL__ */ +#endif /* _LINUX_FANOTIFY_H */ -- cgit v1.2.3 From 11637e4b7dc098e9a863f0a619d55ebc60f5949e Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:25 -0500 Subject: fanotify: fanotify_init syscall declaration This patch defines a new syscall fanotify_init() of the form: int sys_fanotify_init(unsigned int flags, unsigned int event_f_flags, unsigned int priority) This syscall is used to create and fanotify group. This is very similar to the inotify_init() syscall. Signed-off-by: Eric Paris --- include/linux/syscalls.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 13ebb5413a79..198dcc9bd025 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -813,6 +813,8 @@ asmlinkage long sys_pselect6(int, fd_set __user *, fd_set __user *, asmlinkage long sys_ppoll(struct pollfd __user *, unsigned int, struct timespec __user *, const sigset_t __user *, size_t); +asmlinkage long sys_fanotify_init(unsigned int flags, unsigned int event_f_flags, + unsigned int priority); int kernel_execve(const char *filename, char *const argv[], char *const envp[]); -- cgit v1.2.3 From 52c923dd079df49f58016a9e56df184b132611d6 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:26 -0500 Subject: fanotify: fanotify_init syscall implementation NAME fanotify_init - initialize an fanotify group SYNOPSIS int fanotify_init(unsigned int flags, unsigned int event_f_flags, int priority); DESCRIPTION fanotify_init() initializes a new fanotify instance and returns a file descriptor associated with the new fanotify event queue. The following values can be OR'd into the flags field: FAN_NONBLOCK Set the O_NONBLOCK file status flag on the new open file description. Using this flag saves extra calls to fcntl(2) to achieve the same result. FAN_CLOEXEC Set the close-on-exec (FD_CLOEXEC) flag on the new file descriptor. See the description of the O_CLOEXEC flag in open(2) for reasons why this may be useful. The event_f_flags argument is unused and must be set to 0 The priority argument is unused and must be set to 0 RETURN VALUE On success, this system call return a new file descriptor. On error, -1 is returned, and errno is set to indicate the error. ERRORS EINVAL An invalid value was specified in flags. EINVAL A non-zero valid was passed in event_f_flags or in priority ENFILE The system limit on the total number of file descriptors has been reached. ENOMEM Insufficient kernel memory is available. CONFORMING TO These system calls are Linux-specific. Signed-off-by: Eric Paris --- include/linux/fanotify.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index b560f86d1401..00bc6d4fbb58 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -18,6 +18,10 @@ /* helper events */ #define FAN_CLOSE (FAN_CLOSE_WRITE | FAN_CLOSE_NOWRITE) /* close */ +#define FAN_CLOEXEC 0x00000001 +#define FAN_NONBLOCK 0x00000002 + +#define FAN_ALL_INIT_FLAGS (FAN_CLOEXEC | FAN_NONBLOCK) /* * All of the events - we build the list by hand so that we can add flags in * the future and not break backward compatibility. Apps will get only the -- cgit v1.2.3 From bbaa4168b2d2d8cc674e6d35806e8426aef464b8 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:26 -0500 Subject: fanotify: sys_fanotify_mark declartion This patch simply declares the new sys_fanotify_mark syscall int fanotify_mark(int fanotify_fd, unsigned int flags, u64_mask, int dfd const char *pathname) Signed-off-by: Eric Paris --- include/linux/syscalls.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 198dcc9bd025..5b05c37059e9 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -815,6 +815,9 @@ asmlinkage long sys_ppoll(struct pollfd __user *, unsigned int, size_t); asmlinkage long sys_fanotify_init(unsigned int flags, unsigned int event_f_flags, unsigned int priority); +asmlinkage long sys_fanotify_mark(int fanotify_fd, unsigned int flags, + u64 mask, int fd, + const char __user *pathname); int kernel_execve(const char *filename, char *const argv[], char *const envp[]); -- cgit v1.2.3 From 2a3edf86040a7e15684525a2aadc29f532c51325 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:26 -0500 Subject: fanotify: fanotify_mark syscall implementation NAME fanotify_mark - add, remove, or modify an fanotify mark on a filesystem object SYNOPSIS int fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int dfd, const char *pathname) DESCRIPTION fanotify_mark() is used to add remove or modify a mark on a filesystem object. Marks are used to indicate that the fanotify group is interested in events which occur on that object. At this point in time marks may only be added to files and directories. fanotify_fd must be a file descriptor returned by fanotify_init() The flags field must contain exactly one of the following: FAN_MARK_ADD - or the bits in mask and ignored mask into the mark FAN_MARK_REMOVE - bitwise remove the bits in mask and ignored mark from the mark The following values can be OR'd into the flags field: FAN_MARK_DONT_FOLLOW - same meaning as O_NOFOLLOW as described in open(2) FAN_MARK_ONLYDIR - same meaning as O_DIRECTORY as described in open(2) dfd may be any of the following: AT_FDCWD: the object will be lookup up based on pathname similar to open(2) file descriptor of a directory: if pathname is not NULL the object to modify will be lookup up similar to openat(2) file descriptor of the final object: if pathname is NULL the object to modify will be the object referenced by dfd The mask is the bitwise OR of the set of events of interest such as: FAN_ACCESS - object was accessed (read) FAN_MODIFY - object was modified (write) FAN_CLOSE_WRITE - object was writable and was closed FAN_CLOSE_NOWRITE - object was read only and was closed FAN_OPEN - object was opened FAN_EVENT_ON_CHILD - interested in objected that happen to children. Only relavent when the object is a directory FAN_Q_OVERFLOW - event queue overflowed (not implemented) RETURN VALUE On success, this system call returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EINVAL An invalid value was specified in flags. EINVAL An invalid value was specified in mask. EINVAL An invalid value was specified in ignored_mask. EINVAL fanotify_fd is not a file descriptor as returned by fanotify_init() EBADF fanotify_fd is not a valid file descriptor EBADF dfd is not a valid file descriptor and path is NULL. ENOTDIR dfd is not a directory and path is not NULL EACCESS no search permissions on some part of the path ENENT file not found ENOMEM Insufficient kernel memory is available. CONFORMING TO These system calls are Linux-specific. Signed-off-by: Eric Paris --- include/linux/fanotify.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 00bc6d4fbb58..95aeea2a3ca6 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -18,10 +18,23 @@ /* helper events */ #define FAN_CLOSE (FAN_CLOSE_WRITE | FAN_CLOSE_NOWRITE) /* close */ +/* flags used for fanotify_init() */ #define FAN_CLOEXEC 0x00000001 #define FAN_NONBLOCK 0x00000002 #define FAN_ALL_INIT_FLAGS (FAN_CLOEXEC | FAN_NONBLOCK) + +/* flags used for fanotify_modify_mark() */ +#define FAN_MARK_ADD 0x00000001 +#define FAN_MARK_REMOVE 0x00000002 +#define FAN_MARK_DONT_FOLLOW 0x00000004 +#define FAN_MARK_ONLYDIR 0x00000008 + +#define FAN_ALL_MARK_FLAGS (FAN_MARK_ADD |\ + FAN_MARK_REMOVE |\ + FAN_MARK_DONT_FOLLOW |\ + FAN_MARK_ONLYDIR) + /* * All of the events - we build the list by hand so that we can add flags in * the future and not break backward compatibility. Apps will get only the -- cgit v1.2.3 From a1014f102322398e67524b68b3300acf384e6c1f Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:26 -0500 Subject: fanotify: send events using read Send events to userspace by reading the file descriptor from fanotify_init(). One will get blocks of data which look like: struct fanotify_event_metadata { __u32 event_len; __u32 vers; __s32 fd; __u64 mask; __s64 pid; __u64 cookie; } __attribute__ ((packed)); Simple code to retrieve and deal with events is below while ((len = read(fan_fd, buf, sizeof(buf))) > 0) { struct fanotify_event_metadata *metadata; metadata = (void *)buf; while(FAN_EVENT_OK(metadata, len)) { [PROCESS HERE!!] if (metadata->fd >= 0 && close(metadata->fd) != 0) goto fail; metadata = FAN_EVENT_NEXT(metadata, len); } } Signed-off-by: Eric Paris --- include/linux/fanotify.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 95aeea2a3ca6..c1c66162a46c 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -51,6 +51,30 @@ */ #define FAN_ALL_INCOMING_EVENTS (FAN_ALL_EVENTS |\ FAN_EVENT_ON_CHILD) + +#define FAN_ALL_OUTGOING_EVENTS (FAN_ALL_EVENTS |\ + FAN_Q_OVERFLOW) + +#define FANOTIFY_METADATA_VERSION 1 + +struct fanotify_event_metadata { + __u32 event_len; + __u32 vers; + __s32 fd; + __u64 mask; +} __attribute__ ((packed)); + +/* Helper functions to deal with fanotify_event_metadata buffers */ +#define FAN_EVENT_METADATA_LEN (sizeof(struct fanotify_event_metadata)) + +#define FAN_EVENT_NEXT(meta, len) ((len) -= (meta)->event_len, \ + (struct fanotify_event_metadata*)(((char *)(meta)) + \ + (meta)->event_len)) + +#define FAN_EVENT_OK(meta, len) ((long)(len) >= (long)FAN_EVENT_METADATA_LEN && \ + (long)(meta)->event_len >= (long)FAN_EVENT_METADATA_LEN && \ + (long)(meta)->event_len <= (long)(len)) + #ifdef __KERNEL__ #endif /* __KERNEL__ */ -- cgit v1.2.3 From 32c3263221bd63316815286dccacdc7abfd7f3c4 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Thu, 17 Dec 2009 21:24:27 -0500 Subject: fanotify: Add pids to events Pass the process identifiers of the triggering processes to fanotify listeners: this information is useful for event filtering and logging. Signed-off-by: Andreas Gruenbacher Signed-off-by: Eric Paris --- include/linux/fanotify.h | 1 + include/linux/fsnotify_backend.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index c1c66162a46c..5f633af4d1b0 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -62,6 +62,7 @@ struct fanotify_event_metadata { __u32 vers; __s32 fd; __u64 mask; + __s64 pid; } __attribute__ ((packed)); /* Helper functions to deal with fanotify_event_metadata buffers */ diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index ff654c1932f2..7d93572ec568 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -221,6 +221,7 @@ struct fsnotify_event { u32 sync_cookie; /* used to corrolate events, namely inotify mv events */ char *file_name; size_t name_len; + struct pid *tgid; struct list_head private_data_list; /* groups can store private data here */ }; -- cgit v1.2.3 From 5444e2981c31d0ed7465475e451b8437084337e5 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:27 -0500 Subject: fsnotify: split generic and inode specific mark code currently all marking is done by functions in inode-mark.c. Some of this is pretty generic and should be instead done in a generic function and we should only put the inode specific code in inode-mark.c Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 7d93572ec568..27cccbecbf23 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -364,11 +364,12 @@ extern struct fsnotify_event *fsnotify_remove_notify_event(struct fsnotify_group extern void fsnotify_recalc_inode_mask(struct inode *inode); extern void fsnotify_init_mark(struct fsnotify_mark *mark, void (*free_mark)(struct fsnotify_mark *mark)); /* find (and take a reference) to a mark associated with group and inode */ -extern struct fsnotify_mark *fsnotify_find_mark(struct fsnotify_group *group, struct inode *inode); +extern struct fsnotify_mark *fsnotify_find_inode_mark(struct fsnotify_group *group, struct inode *inode); /* copy the values from old into new */ extern void fsnotify_duplicate_mark(struct fsnotify_mark *new, struct fsnotify_mark *old); /* attach the mark to both the group and the inode */ -extern int fsnotify_add_mark(struct fsnotify_mark *mark, struct fsnotify_group *group, struct inode *inode, int allow_dups); +extern int fsnotify_add_mark(struct fsnotify_mark *mark, struct fsnotify_group *group, + struct inode *inode, struct vfsmount *mnt, int allow_dups); /* given a mark, flag it to be freed when all references are dropped */ extern void fsnotify_destroy_mark(struct fsnotify_mark *mark); /* run all the marks in a group, and flag them to be freed */ -- cgit v1.2.3 From 2504c5d63b811b71bbaa8d5d5af163e698f4df1f Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Thu, 17 Dec 2009 21:24:27 -0500 Subject: fsnotify/vfsmount: add fsnotify fields to struct vfsmount This patch adds the list and mask fields needed to support vfsmount marks. These are the same fields fsnotify needs on an inode. They are not used, just declared and we note where the cleanup hook should be (the function is not yet defined) Signed-off-by: Andreas Gruenbacher Signed-off-by: Eric Paris --- include/linux/mount.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mount.h b/include/linux/mount.h index 4bd05474d11d..907210bd9f9c 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -56,7 +56,11 @@ struct vfsmount { struct list_head mnt_mounts; /* list of children, anchored here */ struct list_head mnt_child; /* and going through their mnt_child */ int mnt_flags; - /* 4 bytes hole on 64bits arches */ + /* 4 bytes hole on 64bits arches without fsnotify */ +#ifdef CONFIG_FSNOTIFY + __u32 mnt_fsnotify_mask; + struct hlist_head mnt_fsnotify_marks; +#endif const char *mnt_devname; /* Name of device e.g. /dev/dsk/hda1 */ struct list_head mnt_list; struct list_head mnt_expire; /* link in fs-specific expiry list */ -- cgit v1.2.3 From 0d48b7f01f442bc88a69aa98f3b6b015f2817608 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:27 -0500 Subject: fsnotify: vfsmount marks generic functions Much like inode-mark.c has all of the code dealing with marks on inodes this patch adds a vfsmount-mark.c which has similar code but is intended for marks on vfsmounts. Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 27cccbecbf23..f21ff1bd4b5a 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -360,6 +360,8 @@ extern struct fsnotify_event *fsnotify_remove_notify_event(struct fsnotify_group /* functions used to manipulate the marks attached to inodes */ +/* run all marks associated with a vfsmount and update mnt->mnt_fsnotify_mask */ +extern void fsnotify_recalc_vfsmount_mask(struct vfsmount *mnt); /* run all marks associated with an inode and update inode->i_fsnotify_mask */ extern void fsnotify_recalc_inode_mask(struct inode *inode); extern void fsnotify_init_mark(struct fsnotify_mark *mark, void (*free_mark)(struct fsnotify_mark *mark)); -- cgit v1.2.3 From ca9c726eea013394d1e846331b117effb21ead83 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Thu, 17 Dec 2009 21:24:27 -0500 Subject: fsnotify: Infrastructure for per-mount watches Per-mount watches allow groups to listen to fsnotify events on an entire mount. This patch simply adds and initializes the fields needed in the vfsmount struct to make this happen. Signed-off-by: Andreas Gruenbacher Signed-off-by: Eric Paris --- include/linux/fsnotify.h | 8 ++++++++ include/linux/fsnotify_backend.h | 4 ++++ 2 files changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 5184a2b786c1..06c0e50c7968 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -95,6 +95,14 @@ static inline void fsnotify_inode_delete(struct inode *inode) __fsnotify_inode_delete(inode); } +/* + * fsnotify_vfsmount_delete - a vfsmount is being destroyed, clean up is needed + */ +static inline void fsnotify_vfsmount_delete(struct vfsmount *mnt) +{ + __fsnotify_vfsmount_delete(mnt); +} + /* * fsnotify_nameremove - a filename was removed from a directory */ diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index f21ff1bd4b5a..1af42cbfc429 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -282,6 +282,7 @@ extern void fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is, const char *name, u32 cookie); extern void __fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask); extern void __fsnotify_inode_delete(struct inode *inode); +extern void __fsnotify_vfsmount_delete(struct vfsmount *mnt); extern u32 fsnotify_get_cookie(void); static inline int fsnotify_inode_watches_children(struct inode *inode) @@ -402,6 +403,9 @@ static inline void __fsnotify_parent(struct path *path, struct dentry *dentry, _ static inline void __fsnotify_inode_delete(struct inode *inode) {} +static inline void __fsnotify_vfsmount_delete(struct vfsmount *mnt) +{} + static inline void __fsnotify_update_dcache_flags(struct dentry *dentry) {} -- cgit v1.2.3 From 1c529063a3e4c15eaae28db31326a7aaab7091b5 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:28 -0500 Subject: fanotify: should_send_event needs to handle vfsmounts currently should_send_event in fanotify only cares about marks on inodes. This patch extends that interface to indicate that it cares about events that happened on vfsmounts. Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 1af42cbfc429..2d2f015fb700 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -368,6 +368,8 @@ extern void fsnotify_recalc_inode_mask(struct inode *inode); extern void fsnotify_init_mark(struct fsnotify_mark *mark, void (*free_mark)(struct fsnotify_mark *mark)); /* find (and take a reference) to a mark associated with group and inode */ extern struct fsnotify_mark *fsnotify_find_inode_mark(struct fsnotify_group *group, struct inode *inode); +/* find (and take a reference) to a mark associated with group and vfsmount */ +extern struct fsnotify_mark *fsnotify_find_vfsmount_mark(struct fsnotify_group *group, struct vfsmount *mnt); /* copy the values from old into new */ extern void fsnotify_duplicate_mark(struct fsnotify_mark *new, struct fsnotify_mark *old); /* attach the mark to both the group and the inode */ -- cgit v1.2.3 From 0ff21db9fcc39042b814dad8a4b7508710a75235 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:29 -0500 Subject: fanotify: hooks the fanotify_mark syscall to the vfsmount code Create a new fanotify_mark flag which indicates we should attach the mark to the vfsmount holding the object referenced by dfd and pathname rather than the inode itself. Signed-off-by: Eric Paris --- include/linux/fanotify.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 5f633af4d1b0..e25d348188ca 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -29,11 +29,13 @@ #define FAN_MARK_REMOVE 0x00000002 #define FAN_MARK_DONT_FOLLOW 0x00000004 #define FAN_MARK_ONLYDIR 0x00000008 +#define FAN_MARK_ON_VFSMOUNT 0x00000010 #define FAN_ALL_MARK_FLAGS (FAN_MARK_ADD |\ FAN_MARK_REMOVE |\ FAN_MARK_DONT_FOLLOW |\ - FAN_MARK_ONLYDIR) + FAN_MARK_ONLYDIR |\ + FAN_MARK_ON_VFSMOUNT) /* * All of the events - we build the list by hand so that we can add flags in -- cgit v1.2.3 From eac8e9e80ccbd30801b7b76a2ee4c6c5a681e53c Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Thu, 17 Dec 2009 21:24:29 -0500 Subject: fanotify: rename FAN_MARK_ON_VFSMOUNT to FAN_MARK_MOUNT the term 'vfsmount' isn't sensicle to userspace. instead call is 'mount. Signed-off-by: Andreas Gruenbacher Signed-off-by: Eric Paris --- include/linux/fanotify.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index e25d348188ca..5ee22fb274e5 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -29,13 +29,13 @@ #define FAN_MARK_REMOVE 0x00000002 #define FAN_MARK_DONT_FOLLOW 0x00000004 #define FAN_MARK_ONLYDIR 0x00000008 -#define FAN_MARK_ON_VFSMOUNT 0x00000010 +#define FAN_MARK_MOUNT 0x00000010 #define FAN_ALL_MARK_FLAGS (FAN_MARK_ADD |\ FAN_MARK_REMOVE |\ FAN_MARK_DONT_FOLLOW |\ FAN_MARK_ONLYDIR |\ - FAN_MARK_ON_VFSMOUNT) + FAN_MARK_MOUNT) /* * All of the events - we build the list by hand so that we can add flags in -- cgit v1.2.3 From 88380fe66e0ac22529f5426ab27d67da00ed2628 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Thu, 17 Dec 2009 21:24:29 -0500 Subject: fanotify: remove fanotify.h declarations fanotify_mark_validate functions are all needlessly declared in headers as static inlines. Instead just do the checks where they are needed for code readability. Signed-off-by: Andreas Gruenbacher Signed-off-by: Eric Paris --- include/linux/fanotify.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 5ee22fb274e5..90e59b24fd04 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -47,13 +47,6 @@ FAN_CLOSE |\ FAN_OPEN) -/* - * All legal FAN bits userspace can request (although possibly not all - * at the same time. - */ -#define FAN_ALL_INCOMING_EVENTS (FAN_ALL_EVENTS |\ - FAN_EVENT_ON_CHILD) - #define FAN_ALL_OUTGOING_EVENTS (FAN_ALL_EVENTS |\ FAN_Q_OVERFLOW) -- cgit v1.2.3 From 90b1e7a57880fb66437ab7db39e1e65ca0372822 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:33 -0500 Subject: fsnotify: allow marks to not pin inodes in core inotify marks must pin inodes in core. dnotify doesn't technically need to since they are closed when the directory is closed. fanotify also need to pin inodes in core as it works today. But the next step is to introduce the concept of 'ignored masks' which is actually a mask of events for an inode of no interest. I claim that these should be liberally sent to the kernel and should not pin the inode in core. If the inode is brought back in the listener will get an event it may have thought excluded, but this is not a serious situation and one any listener should deal with. This patch lays the ground work for non-pinning inode marks by using lazy inode pinning. We do not pin a mark until it has a non-zero mask entry. If a listener new sets a mask we never pin the inode. Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 2d2f015fb700..489c881ed4ec 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -267,8 +267,9 @@ struct fsnotify_mark { struct fsnotify_vfsmount_mark m; }; struct list_head free_g_list; /* tmp list used when freeing this mark */ -#define FSNOTIFY_MARK_FLAG_INODE 0x01 -#define FSNOTIFY_MARK_FLAG_VFSMOUNT 0x02 +#define FSNOTIFY_MARK_FLAG_INODE 0x01 +#define FSNOTIFY_MARK_FLAG_VFSMOUNT 0x02 +#define FSNOTIFY_MARK_FLAG_OBJECT_PINNED 0x04 unsigned int flags; /* vfsmount or inode mark? */ void (*free_mark)(struct fsnotify_mark *mark); /* called on final put+free */ }; @@ -372,6 +373,8 @@ extern struct fsnotify_mark *fsnotify_find_inode_mark(struct fsnotify_group *gro extern struct fsnotify_mark *fsnotify_find_vfsmount_mark(struct fsnotify_group *group, struct vfsmount *mnt); /* copy the values from old into new */ extern void fsnotify_duplicate_mark(struct fsnotify_mark *new, struct fsnotify_mark *old); +/* set the mask of a mark (might pin the object into memory */ +extern void fsnotify_set_mark_mask_locked(struct fsnotify_mark *mark, __u32 mask); /* attach the mark to both the group and the inode */ extern int fsnotify_add_mark(struct fsnotify_mark *mark, struct fsnotify_group *group, struct inode *inode, struct vfsmount *mnt, int allow_dups); -- cgit v1.2.3 From 33af5e32e0bb73c704b5e156f4411cdb53e6cc59 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:33 -0500 Subject: fsnotify: ignored_mask - excluding notification The ignored_mask is a new mask which is part of fsnotify marks. A group's should_send_event() function can use the ignored mask to determine that certain events are not of interest. In particular if a group registers a mask including FS_OPEN on a vfsmount they could add FS_OPEN to the ignored_mask for individual inodes and not send open events for those inodes. Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 489c881ed4ec..018416ec5ce4 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -266,6 +266,7 @@ struct fsnotify_mark { struct fsnotify_inode_mark i; struct fsnotify_vfsmount_mark m; }; + __u32 ignored_mask; /* events types to ignore */ struct list_head free_g_list; /* tmp list used when freeing this mark */ #define FSNOTIFY_MARK_FLAG_INODE 0x01 #define FSNOTIFY_MARK_FLAG_VFSMOUNT 0x02 @@ -373,6 +374,8 @@ extern struct fsnotify_mark *fsnotify_find_inode_mark(struct fsnotify_group *gro extern struct fsnotify_mark *fsnotify_find_vfsmount_mark(struct fsnotify_group *group, struct vfsmount *mnt); /* copy the values from old into new */ extern void fsnotify_duplicate_mark(struct fsnotify_mark *new, struct fsnotify_mark *old); +/* set the ignored_mask of a mark */ +extern void fsnotify_set_mark_ignored_mask_locked(struct fsnotify_mark *mark, __u32 mask); /* set the mask of a mark (might pin the object into memory */ extern void fsnotify_set_mark_mask_locked(struct fsnotify_mark *mark, __u32 mask); /* attach the mark to both the group and the inode */ -- cgit v1.2.3 From b9e4e3bd0495fea9e8f8e712889c9cd8ffa43c94 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:33 -0500 Subject: fanotify: allow users to set an ignored_mask Change the sys_fanotify_mark() system call so users can set ignored_masks on inodes. Remember, if a user new sets a real mask, and only sets ignored masks, the ignore will never be pinned in memory. Thus ignored_masks can be lost under memory pressure and the user may again get events they previously thought were ignored. Signed-off-by: Eric Paris --- include/linux/fanotify.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 90e59b24fd04..b8daa9f9b560 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -30,12 +30,14 @@ #define FAN_MARK_DONT_FOLLOW 0x00000004 #define FAN_MARK_ONLYDIR 0x00000008 #define FAN_MARK_MOUNT 0x00000010 +#define FAN_MARK_IGNORED_MASK 0x00000020 #define FAN_ALL_MARK_FLAGS (FAN_MARK_ADD |\ FAN_MARK_REMOVE |\ FAN_MARK_DONT_FOLLOW |\ FAN_MARK_ONLYDIR |\ - FAN_MARK_MOUNT) + FAN_MARK_MOUNT |\ + FAN_MARK_IGNORED_MASK) /* * All of the events - we build the list by hand so that we can add flags in -- cgit v1.2.3 From c908370fc1ac27fd7e1fc0f34c693047b26564ce Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:33 -0500 Subject: fsnotify: allow ignored_mask to survive modification Some inodes a group may want to never hear about a set of events even if the inode is modified. We add a new mark flag which indicates that these marks should not have their ignored_mask cleared on modification. Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 018416ec5ce4..8ca19df8a171 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -271,6 +271,7 @@ struct fsnotify_mark { #define FSNOTIFY_MARK_FLAG_INODE 0x01 #define FSNOTIFY_MARK_FLAG_VFSMOUNT 0x02 #define FSNOTIFY_MARK_FLAG_OBJECT_PINNED 0x04 +#define FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY 0x08 unsigned int flags; /* vfsmount or inode mark? */ void (*free_mark)(struct fsnotify_mark *mark); /* called on final put+free */ }; -- cgit v1.2.3 From c9778a98e7440fb73e0d27b8155a688663a0d493 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:33 -0500 Subject: fanotify: allow ignored_masks to survive modify Some users may want to truely ignore an inode even if it has been modified. Say you are wanting a mount which contains a log file and you really don't want any notification about that file. This patch allows the listener to do that. Signed-off-by: Eric Paris --- include/linux/fanotify.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index b8daa9f9b560..e43934d0b74c 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -31,13 +31,15 @@ #define FAN_MARK_ONLYDIR 0x00000008 #define FAN_MARK_MOUNT 0x00000010 #define FAN_MARK_IGNORED_MASK 0x00000020 +#define FAN_MARK_IGNORED_SURV_MODIFY 0x00000040 #define FAN_ALL_MARK_FLAGS (FAN_MARK_ADD |\ FAN_MARK_REMOVE |\ FAN_MARK_DONT_FOLLOW |\ FAN_MARK_ONLYDIR |\ FAN_MARK_MOUNT |\ - FAN_MARK_IGNORED_MASK) + FAN_MARK_IGNORED_MASK |\ + FAN_MARK_IGNORED_SURV_MODIFY) /* * All of the events - we build the list by hand so that we can add flags in -- cgit v1.2.3 From 4d92604cc90aa18bbbe0f6e23b7a9fdb612836d3 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:34 -0500 Subject: fanotify: clear all fanotify marks fanotify listeners may want to clear all marks. They may want to do this to destroy all of their inode marks which have nothing but ignores. Realistically this is useful for av vendors who update policy and want to clear all of their cached allows. Signed-off-by: Eric Paris --- include/linux/fanotify.h | 1 + include/linux/fsnotify_backend.h | 6 ++++++ 2 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index e43934d0b74c..385896c9f828 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -32,6 +32,7 @@ #define FAN_MARK_MOUNT 0x00000010 #define FAN_MARK_IGNORED_MASK 0x00000020 #define FAN_MARK_IGNORED_SURV_MODIFY 0x00000040 +#define FAN_MARK_FLUSH 0x00000080 #define FAN_ALL_MARK_FLAGS (FAN_MARK_ADD |\ FAN_MARK_REMOVE |\ diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 8ca19df8a171..be4a36ed2008 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -384,6 +384,12 @@ extern int fsnotify_add_mark(struct fsnotify_mark *mark, struct fsnotify_group * struct inode *inode, struct vfsmount *mnt, int allow_dups); /* given a mark, flag it to be freed when all references are dropped */ extern void fsnotify_destroy_mark(struct fsnotify_mark *mark); +/* run all the marks in a group, and clear all of the vfsmount marks */ +extern void fsnotify_clear_vfsmount_marks_by_group(struct fsnotify_group *group); +/* run all the marks in a group, and clear all of the inode marks */ +extern void fsnotify_clear_inode_marks_by_group(struct fsnotify_group *group); +/* run all the marks in a group, and clear all of the marks where mark->flags & flags is true*/ +extern void fsnotify_clear_marks_by_group_flags(struct fsnotify_group *group, unsigned int flags); /* run all the marks in a group, and flag them to be freed */ extern void fsnotify_clear_marks_by_group(struct fsnotify_group *group); extern void fsnotify_get_mark(struct fsnotify_mark *mark); -- cgit v1.2.3 From cb2d429faf2cae62d3c51e28099a181d5fe8c244 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:34 -0500 Subject: fsnotify: add group priorities This introduces an ordering to fsnotify groups. With purely asynchronous notification based "things" implementing fsnotify (inotify, dnotify) ordering isn't particularly important. But if people want to use fsnotify for the basis of sycronous notification or blocking notification ordering becomes important. eg. A Hierarchical Storage Management listener would need to get its event before an AV scanner could get its event (since the HSM would need to bring the data in for the AV scanner to scan.) Typically asynchronous notification would want to run after the AV scanner made any relevant access decisions so as to not send notification about an event that was denied. Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index be4a36ed2008..8b2e095e5907 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -140,6 +140,7 @@ struct fsnotify_group { * a group */ struct list_head marks_list; /* all inode marks for this group */ + unsigned int priority; /* order of this group compared to others */ /* prevents double list_del of group_list. protected by global fsnotify_grp_mutex */ bool on_inode_group_list; bool on_vfsmount_group_list; -- cgit v1.2.3 From 6e5f77b32e9097a8a68a8d453799676cacf70cad Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:34 -0500 Subject: fsnotify: intoduce a notification merge argument Each group can define their own notification (and secondary_q) merge function. Inotify does tail drop, fanotify does matching and drop which can actually allocate a completely new event. But for fanotify to properly deal with permissions events it needs to know the new event which was ultimately added to the notification queue. This patch just implements a void ** argument which is passed to the merge function. fanotify can use this field to pass the new event back to higher layers. Signed-off-by: Eric Paris for fanotify to properly deal with permissions events --- include/linux/fsnotify_backend.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 8b2e095e5907..afc690192972 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -355,7 +355,10 @@ extern struct fsnotify_event_private_data *fsnotify_remove_priv_from_event(struc extern int fsnotify_add_notify_event(struct fsnotify_group *group, struct fsnotify_event *event, struct fsnotify_event_private_data *priv, - int (*merge)(struct list_head *, struct fsnotify_event *)); + int (*merge)(struct list_head *, + struct fsnotify_event *, + void **), + void **arg); /* true if the group notification queue is empty */ extern bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group); /* return, but do not dequeue the first event on the notification queue */ -- cgit v1.2.3 From 59b0df211bd9699d7e0d01fcf9345a149f75b033 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Mon, 8 Feb 2010 12:53:52 -0500 Subject: fsnotify: use unsigned char * for dentry->d_name.name fsnotify was using char * when it passed around the d_name.name string internally but it is actually an unsigned char *. This patch switches fsnotify to use unsigned and should silence some pointer signess warnings which have popped out of xfs. I do not add -Wpointer-sign to the fsnotify code as there are still issues with kstrdup and strlen which would pop out needless warnings. Signed-off-by: Eric Paris --- include/linux/fsnotify.h | 12 ++++++------ include/linux/fsnotify_backend.h | 9 +++++---- 2 files changed, 11 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 06c0e50c7968..b8cf161f5a6d 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -59,14 +59,14 @@ static inline void fsnotify_link_count(struct inode *inode) * fsnotify_move - file old_name at old_dir was moved to new_name at new_dir */ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir, - const char *old_name, + const unsigned char *old_name, int isdir, struct inode *target, struct dentry *moved) { struct inode *source = moved->d_inode; u32 fs_cookie = fsnotify_get_cookie(); __u32 old_dir_mask = (FS_EVENT_ON_CHILD | FS_MOVED_FROM); __u32 new_dir_mask = (FS_EVENT_ON_CHILD | FS_MOVED_TO); - const char *new_name = moved->d_name.name; + const unsigned char *new_name = moved->d_name.name; if (old_dir == new_dir) old_dir_mask |= FS_DN_RENAME; @@ -290,7 +290,7 @@ static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid) /* * fsnotify_oldname_init - save off the old filename before we change it */ -static inline const char *fsnotify_oldname_init(const char *name) +static inline const unsigned char *fsnotify_oldname_init(const unsigned char *name) { return kstrdup(name, GFP_KERNEL); } @@ -298,19 +298,19 @@ static inline const char *fsnotify_oldname_init(const char *name) /* * fsnotify_oldname_free - free the name we got from fsnotify_oldname_init */ -static inline void fsnotify_oldname_free(const char *old_name) +static inline void fsnotify_oldname_free(const unsigned char *old_name) { kfree(old_name); } #else /* CONFIG_FSNOTIFY */ -static inline const char *fsnotify_oldname_init(const char *name) +static inline const char *fsnotify_oldname_init(const unsigned char *name) { return NULL; } -static inline void fsnotify_oldname_free(const char *old_name) +static inline void fsnotify_oldname_free(const unsigned char *old_name) { } diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index afc690192972..efe9ba321cf2 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -220,7 +220,7 @@ struct fsnotify_event { __u32 mask; /* the type of access, bitwise OR for FS_* event types */ u32 sync_cookie; /* used to corrolate events, namely inotify mv events */ - char *file_name; + const unsigned char *file_name; size_t name_len; struct pid *tgid; @@ -283,7 +283,7 @@ struct fsnotify_mark { /* main fsnotify call to send events */ extern void fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is, - const char *name, u32 cookie); + const unsigned char *name, u32 cookie); extern void __fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask); extern void __fsnotify_inode_delete(struct inode *inode); extern void __fsnotify_vfsmount_delete(struct vfsmount *mnt); @@ -402,7 +402,8 @@ extern void fsnotify_unmount_inodes(struct list_head *list); /* put here because inotify does some weird stuff when destroying watches */ extern struct fsnotify_event *fsnotify_create_event(struct inode *to_tell, __u32 mask, - void *data, int data_is, const char *name, + void *data, int data_is, + const unsigned char *name, u32 cookie, gfp_t gfp); /* fanotify likes to change events after they are on lists... */ @@ -413,7 +414,7 @@ extern int fsnotify_replace_event(struct fsnotify_event_holder *old_holder, #else static inline void fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is, - const char *name, u32 cookie) + const unsigned char *name, u32 cookie) {} static inline void __fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask) -- cgit v1.2.3 From 6e006701ccc1590500186ef21e074bd900c5dd67 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Wed, 20 Jan 2010 22:27:56 +0200 Subject: dnotify: move dir_notify_enable declaration Move dir_notify_enable declaration to where it belongs -- dnotify.h . Signed-off-by: Alexey Dobriyan Signed-off-by: Eric Paris --- include/linux/dnotify.h | 1 + include/linux/fs.h | 3 --- 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dnotify.h b/include/linux/dnotify.h index ecc06286226d..3290555a52ee 100644 --- a/include/linux/dnotify.h +++ b/include/linux/dnotify.h @@ -28,6 +28,7 @@ struct dnotify_struct { FS_CREATE | FS_DN_RENAME |\ FS_MOVED_FROM | FS_MOVED_TO) +extern int dir_notify_enable; extern void dnotify_flush(struct file *, fl_owner_t); extern int fcntl_dirnotify(int, struct file *, unsigned long); diff --git a/include/linux/fs.h b/include/linux/fs.h index f9a003278758..d92c212476f9 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -410,9 +410,6 @@ extern int get_max_files(void); extern int sysctl_nr_open; extern struct inodes_stat_t inodes_stat; extern int leases_enable, lease_break_time; -#ifdef CONFIG_DNOTIFY -extern int dir_notify_enable; -#endif struct buffer_head; typedef int (get_block_t)(struct inode *inode, sector_t iblock, -- cgit v1.2.3 From d14f1729483fad3a8817fbbcbd017678b7d1ad26 Mon Sep 17 00:00:00 2001 From: Dave Young Date: Thu, 25 Feb 2010 20:28:57 -0500 Subject: sysctl extern cleanup: inotify Extern declarations in sysctl.c should be move to their own head file, and then include them in relavant .c files. Move inotify_table extern declaration to linux/inotify.h Signed-off-by: Dave Young Signed-off-by: Andrew Morton Signed-off-by: Eric Paris --- include/linux/inotify.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/inotify.h b/include/linux/inotify.h index 959a38b8f75d..94d209a1b689 100644 --- a/include/linux/inotify.h +++ b/include/linux/inotify.h @@ -69,4 +69,9 @@ struct inotify_event { #define IN_CLOEXEC O_CLOEXEC #define IN_NONBLOCK O_NONBLOCK +#ifdef __KERNEL__ +#include +extern struct ctl_table inotify_table[]; /* for sysctl */ +#endif + #endif /* _LINUX_INOTIFY_H */ -- cgit v1.2.3 From c4ec54b40d33f8016fea970a383cc584dd0e6019 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:34 -0500 Subject: fsnotify: new fsnotify hooks and events types for access decisions introduce a new fsnotify hook, fsnotify_perm(), which is called from the security code. This hook is used to allow fsnotify groups to make access control decisions about events on the system. We also must change the generic fsnotify function to return an error code if we intend these hooks to be in any way useful. Signed-off-by: Eric Paris --- include/linux/fsnotify.h | 19 +++++++++++++++++++ include/linux/fsnotify_backend.h | 15 ++++++++++----- include/linux/security.h | 1 + 3 files changed, 30 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index b8cf161f5a6d..64efda9aae62 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -34,6 +34,25 @@ static inline void fsnotify_parent(struct path *path, struct dentry *dentry, __u __fsnotify_parent(path, dentry, mask); } +/* simple call site for access decisions */ +static inline int fsnotify_perm(struct file *file, int mask) +{ + struct path *path = &file->f_path; + struct inode *inode = path->dentry->d_inode; + __u32 fsnotify_mask; + + if (file->f_mode & FMODE_NONOTIFY) + return 0; + if (!(mask & (MAY_READ | MAY_OPEN))) + return 0; + if (mask & MAY_READ) + fsnotify_mask = FS_ACCESS_PERM; + if (mask & MAY_OPEN) + fsnotify_mask = FS_OPEN_PERM; + + return fsnotify(inode, fsnotify_mask, path, FSNOTIFY_EVENT_PATH, NULL, 0); +} + /* * fsnotify_d_move - dentry has been moved * Called with dcache_lock and dentry->d_lock held. diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index efe9ba321cf2..c34728e7d8cb 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -41,6 +41,9 @@ #define FS_Q_OVERFLOW 0x00004000 /* Event queued overflowed */ #define FS_IN_IGNORED 0x00008000 /* last inotify event here */ +#define FS_OPEN_PERM 0x00010000 /* open event in an permission hook */ +#define FS_ACCESS_PERM 0x00020000 /* access event in a permissions hook */ + #define FS_IN_ISDIR 0x40000000 /* event occurred against dir */ #define FS_IN_ONESHOT 0x80000000 /* only send event once */ @@ -282,8 +285,8 @@ struct fsnotify_mark { /* called from the vfs helpers */ /* main fsnotify call to send events */ -extern void fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is, - const unsigned char *name, u32 cookie); +extern int fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is, + const unsigned char *name, u32 cookie); extern void __fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask); extern void __fsnotify_inode_delete(struct inode *inode); extern void __fsnotify_vfsmount_delete(struct vfsmount *mnt); @@ -413,9 +416,11 @@ extern int fsnotify_replace_event(struct fsnotify_event_holder *old_holder, #else -static inline void fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is, - const unsigned char *name, u32 cookie) -{} +static inline int fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is, + const unsigned char *name, u32 cookie) +{ + return 0; +} static inline void __fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask) {} diff --git a/include/linux/security.h b/include/linux/security.h index 0c8819170463..24fc29540aa3 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -23,6 +23,7 @@ #define __LINUX_SECURITY_H #include +#include #include #include #include -- cgit v1.2.3 From 9e66e4233db9c7e31e9ee706be2c9ddd54cf99b3 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:34 -0500 Subject: fanotify: permissions and blocking This is the backend work needed for fanotify to support the new FS_OPEN_PERM and FS_ACCESS_PERM fsnotify events. This is done using the new fsnotify secondary queue. No userspace interface is provided actually respond to or request these events. Signed-off-by: Eric Paris --- include/linux/fanotify.h | 18 ++++++++++++++++++ include/linux/fsnotify_backend.h | 12 ++++++++++++ 2 files changed, 30 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 385896c9f828..02f80676c238 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -15,6 +15,9 @@ /* FIXME currently Q's have no limit.... */ #define FAN_Q_OVERFLOW 0x00004000 /* Event queued overflowed */ +#define FAN_OPEN_PERM 0x00010000 /* File open in perm check */ +#define FAN_ACCESS_PERM 0x00020000 /* File accessed in perm check */ + /* helper events */ #define FAN_CLOSE (FAN_CLOSE_WRITE | FAN_CLOSE_NOWRITE) /* close */ @@ -52,7 +55,14 @@ FAN_CLOSE |\ FAN_OPEN) +/* + * All events which require a permission response from userspace + */ +#define FAN_ALL_PERM_EVENTS (FAN_OPEN_PERM |\ + FAN_ACCESS_PERM) + #define FAN_ALL_OUTGOING_EVENTS (FAN_ALL_EVENTS |\ + FAN_ALL_PERM_EVENTS |\ FAN_Q_OVERFLOW) #define FANOTIFY_METADATA_VERSION 1 @@ -65,6 +75,10 @@ struct fanotify_event_metadata { __s64 pid; } __attribute__ ((packed)); +/* Legit userspace responses to a _PERM event */ +#define FAN_ALLOW 0x01 +#define FAN_DENY 0x02 + /* Helper functions to deal with fanotify_event_metadata buffers */ #define FAN_EVENT_METADATA_LEN (sizeof(struct fanotify_event_metadata)) @@ -78,5 +92,9 @@ struct fanotify_event_metadata { #ifdef __KERNEL__ +struct fanotify_wait { + struct fsnotify_event *event; + __s32 fd; +}; #endif /* __KERNEL__ */ #endif /* _LINUX_FANOTIFY_H */ diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index c34728e7d8cb..b0d00fd6bfad 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -159,6 +159,14 @@ struct fsnotify_group { struct fasync_struct *fa; /* async notification */ struct user_struct *user; } inotify_data; +#endif +#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS + struct fanotify_group_private_data { + /* allows a group to block waiting for a userspace response */ + struct mutex access_mutex; + struct list_head access_list; + wait_queue_head_t access_waitq; + } fanotify_data; #endif }; }; @@ -227,6 +235,10 @@ struct fsnotify_event { size_t name_len; struct pid *tgid; +#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS + __u32 response; /* userspace answer to question */ +#endif /* CONFIG_FANOTIFY_ACCESS_PERMISSIONS */ + struct list_head private_data_list; /* groups can store private data here */ }; -- cgit v1.2.3 From b2d879096ac799722e6017ee82c0586f0d101c9c Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 21:24:34 -0500 Subject: fanotify: userspace interface for permission responses fanotify groups need to respond to events which include permissions types. To do so groups will send a response using write() on the fanotify_fd they have open. Signed-off-by: Eric Paris --- include/linux/fanotify.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 02f80676c238..f0949a57ca9d 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -75,6 +75,11 @@ struct fanotify_event_metadata { __s64 pid; } __attribute__ ((packed)); +struct fanotify_response { + __s32 fd; + __u32 response; +} __attribute__ ((packed)); + /* Legit userspace responses to a _PERM event */ #define FAN_ALLOW 0x01 #define FAN_DENY 0x02 -- cgit v1.2.3 From fb1cfb88c8597d847553f39efc2bbd41c72c5f50 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Wed, 12 May 2010 11:42:29 -0400 Subject: fsnotify: initialize mask in fsnotify_perm akpm got a warning the fsnotify_mask could be used uninitialized in fsnotify_perm(). It's not actually possible but his compiler complained about it. This patch just initializes it to 0 to shut up the compiler. Reported-by: Andrew Morton Signed-off-by: Eric Paris --- include/linux/fsnotify.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 64efda9aae62..59d0df43ff9d 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -39,16 +39,18 @@ static inline int fsnotify_perm(struct file *file, int mask) { struct path *path = &file->f_path; struct inode *inode = path->dentry->d_inode; - __u32 fsnotify_mask; + __u32 fsnotify_mask = 0; if (file->f_mode & FMODE_NONOTIFY) return 0; if (!(mask & (MAY_READ | MAY_OPEN))) return 0; - if (mask & MAY_READ) - fsnotify_mask = FS_ACCESS_PERM; if (mask & MAY_OPEN) fsnotify_mask = FS_OPEN_PERM; + else if (mask & MAY_READ) + fsnotify_mask = FS_ACCESS_PERM; + else + BUG(); return fsnotify(inode, fsnotify_mask, path, FSNOTIFY_EVENT_PATH, NULL, 0); } -- cgit v1.2.3 From 08ae89380a8210a9965d04083e1de78cb8bca4b1 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 27 May 2010 09:41:40 -0400 Subject: fanotify: drop the useless priority argument The priority argument in fanotify is useless. Kill it. Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 1 - include/linux/syscalls.h | 3 +-- 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index b0d00fd6bfad..b9b3f24ad4fc 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -143,7 +143,6 @@ struct fsnotify_group { * a group */ struct list_head marks_list; /* all inode marks for this group */ - unsigned int priority; /* order of this group compared to others */ /* prevents double list_del of group_list. protected by global fsnotify_grp_mutex */ bool on_inode_group_list; bool on_vfsmount_group_list; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 5b05c37059e9..0ec26a74f20a 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -813,8 +813,7 @@ asmlinkage long sys_pselect6(int, fd_set __user *, fd_set __user *, asmlinkage long sys_ppoll(struct pollfd __user *, unsigned int, struct timespec __user *, const sigset_t __user *, size_t); -asmlinkage long sys_fanotify_init(unsigned int flags, unsigned int event_f_flags, - unsigned int priority); +asmlinkage long sys_fanotify_init(unsigned int flags, unsigned int event_f_flags); asmlinkage long sys_fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int fd, const char __user *pathname); -- cgit v1.2.3 From 8c1934c8d70b22ca8333b216aec6c7d09fdbd6a6 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Wed, 28 Jul 2010 10:18:37 -0400 Subject: inotify: allow users to request not to recieve events on unlinked children An inotify watch on a directory will send events for children even if those children have been unlinked. This patch add a new inotify flag IN_EXCL_UNLINK which allows a watch to specificy they don't care about unlinked children. This should fix performance problems seen by tasks which add a watch to /tmp and then are overrun with events when other processes are reading and writing to unlinked files they created in /tmp. https://bugzilla.kernel.org/show_bug.cgi?id=16296 Requested-by: Matthias Clasen Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 1 + include/linux/inotify.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index b9b3f24ad4fc..4b809fcd4996 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -44,6 +44,7 @@ #define FS_OPEN_PERM 0x00010000 /* open event in an permission hook */ #define FS_ACCESS_PERM 0x00020000 /* access event in a permissions hook */ +#define FS_EXCL_UNLINK 0x04000000 /* do not send events if object is unlinked */ #define FS_IN_ISDIR 0x40000000 /* event occurred against dir */ #define FS_IN_ONESHOT 0x80000000 /* only send event once */ diff --git a/include/linux/inotify.h b/include/linux/inotify.h index 94d209a1b689..b74f2ef2c368 100644 --- a/include/linux/inotify.h +++ b/include/linux/inotify.h @@ -51,6 +51,7 @@ struct inotify_event { /* special flags */ #define IN_ONLYDIR 0x01000000 /* only watch the path if it is a directory */ #define IN_DONT_FOLLOW 0x02000000 /* don't follow a sym link */ +#define IN_EXCL_UNLINK 0x04000000 /* exclude events on unlinked objects */ #define IN_MASK_ADD 0x20000000 /* add to the mask of an already existing watch */ #define IN_ISDIR 0x40000000 /* event occurred against dir */ #define IN_ONESHOT 0x80000000 /* only send event once */ -- cgit v1.2.3 From f874e1ac21d7708464dc656a10312542c54719f1 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Wed, 28 Jul 2010 10:18:37 -0400 Subject: inotify: force inotify and fsnotify use same bits inotify uses bits called IN_* and fsnotify uses bits called FS_*. These need to line up. This patch adds build time checks to make sure noone can change these bits so they are not the same. Signed-off-by: Eric Paris --- include/linux/inotify.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/inotify.h b/include/linux/inotify.h index b74f2ef2c368..d33041e2a42a 100644 --- a/include/linux/inotify.h +++ b/include/linux/inotify.h @@ -73,6 +73,15 @@ struct inotify_event { #ifdef __KERNEL__ #include extern struct ctl_table inotify_table[]; /* for sysctl */ + +#define ALL_INOTIFY_BITS (IN_ACCESS | IN_MODIFY | IN_ATTRIB | IN_CLOSE_WRITE | \ + IN_CLOSE_NOWRITE | IN_OPEN | IN_MOVED_FROM | \ + IN_MOVED_TO | IN_CREATE | IN_DELETE | \ + IN_DELETE_SELF | IN_MOVE_SELF | IN_UNMOUNT | \ + IN_Q_OVERFLOW | IN_IGNORED | IN_ONLYDIR | \ + IN_DONT_FOLLOW | IN_EXCL_UNLINK | IN_MASK_ADD | \ + IN_ISDIR | IN_ONESHOT) + #endif #endif /* _LINUX_INOTIFY_H */ -- cgit v1.2.3 From 20dee624ca40db227aa70cb3f44d2d6cb4fdbab4 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Wed, 28 Jul 2010 10:18:37 -0400 Subject: fsnotify: check to make sure all fsnotify bits are unique This patch adds a check to make sure that all fsnotify bits are unique and we cannot accidentally use the same bit for 2 different fsnotify event types. Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 4b809fcd4996..a46355db1e47 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -64,6 +64,15 @@ #define FS_MOVE (FS_MOVED_FROM | FS_MOVED_TO) +#define ALL_FSNOTIFY_EVENTS (FS_ACCESS | FS_MODIFY | FS_ATTRIB | \ + FS_CLOSE_WRITE | FS_CLOSE_NOWRITE | FS_OPEN | \ + FS_MOVED_FROM | FS_MOVED_TO | FS_CREATE | \ + FS_DELETE | FS_DELETE_SELF | FS_MOVE_SELF | \ + FS_UNMOUNT | FS_Q_OVERFLOW | FS_IN_IGNORED | \ + FS_OPEN_PERM | FS_ACCESS_PERM | FS_EXCL_UNLINK | \ + FS_IN_ISDIR | FS_IN_ONESHOT | FS_DN_RENAME | \ + FS_DN_MULTISHOT | FS_EVENT_ON_CHILD) + struct fsnotify_group; struct fsnotify_event; struct fsnotify_mark; -- cgit v1.2.3 From 80af2588676483ac4e998b5092e9d008dab3ab62 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Wed, 28 Jul 2010 10:18:37 -0400 Subject: fanotify: groups can specify their f_flags for new fd Currently fanotify fds opened for thier listeners are done with f_flags equal to O_RDONLY | O_LARGEFILE. This patch instead takes f_flags from the fanotify_init syscall and uses those when opening files in the context of the listener. Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index a46355db1e47..a83859d7d36e 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -169,14 +169,17 @@ struct fsnotify_group { struct user_struct *user; } inotify_data; #endif -#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS +#ifdef CONFIG_FANOTIFY struct fanotify_group_private_data { +#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS /* allows a group to block waiting for a userspace response */ struct mutex access_mutex; struct list_head access_list; wait_queue_head_t access_waitq; +#endif /* CONFIG_FANOTIFY_ACCESS_PERMISSIONS */ + int f_flags; } fanotify_data; -#endif +#endif /* CONFIG_FANOTIFY */ }; }; -- cgit v1.2.3 From f70ab54cc6c3907b0727ba332b3976f80f3846d0 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Wed, 28 Jul 2010 10:18:37 -0400 Subject: fsnotify: fsnotify_add_notify_event should return an event Rather than the horrific void ** argument and such just to pass the fanotify_merge event back to the caller of fsnotify_add_notify_event() have those things return an event if it was different than the event suggusted to be added. Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index a83859d7d36e..564b5ea4a831 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -379,13 +379,11 @@ extern struct fsnotify_event_private_data *fsnotify_remove_priv_from_event(struc struct fsnotify_event *event); /* attach the event to the group notification queue */ -extern int fsnotify_add_notify_event(struct fsnotify_group *group, - struct fsnotify_event *event, - struct fsnotify_event_private_data *priv, - int (*merge)(struct list_head *, - struct fsnotify_event *, - void **), - void **arg); +extern struct fsnotify_event *fsnotify_add_notify_event(struct fsnotify_group *group, + struct fsnotify_event *event, + struct fsnotify_event_private_data *priv, + struct fsnotify_event *(*merge)(struct list_head *, + struct fsnotify_event *)); /* true if the group notification queue is empty */ extern bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group); /* return, but do not dequeue the first event on the notification queue */ -- cgit v1.2.3 From 3bcf3860a4ff9bbc522820b4b765e65e4deceb3e Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Wed, 28 Jul 2010 10:18:37 -0400 Subject: fsnotify: store struct file not struct path Al explains that calling dentry_open() with a mnt/dentry pair is only garunteed to be safe if they are already used in an open struct file. To make sure this is the case don't store and use a struct path in fsnotify, always use a struct file. Signed-off-by: Eric Paris --- include/linux/fsnotify.h | 37 ++++++++++++++++--------------------- include/linux/fsnotify_backend.h | 16 ++++++++-------- 2 files changed, 24 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 59d0df43ff9d..e4e2204187ee 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -26,19 +26,18 @@ static inline void fsnotify_d_instantiate(struct dentry *dentry, } /* Notify this dentry's parent about a child's events. */ -static inline void fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask) +static inline void fsnotify_parent(struct file *file, struct dentry *dentry, __u32 mask) { if (!dentry) - dentry = path->dentry; + dentry = file->f_path.dentry; - __fsnotify_parent(path, dentry, mask); + __fsnotify_parent(file, dentry, mask); } /* simple call site for access decisions */ static inline int fsnotify_perm(struct file *file, int mask) { - struct path *path = &file->f_path; - struct inode *inode = path->dentry->d_inode; + struct inode *inode = file->f_path.dentry->d_inode; __u32 fsnotify_mask = 0; if (file->f_mode & FMODE_NONOTIFY) @@ -52,7 +51,7 @@ static inline int fsnotify_perm(struct file *file, int mask) else BUG(); - return fsnotify(inode, fsnotify_mask, path, FSNOTIFY_EVENT_PATH, NULL, 0); + return fsnotify(inode, fsnotify_mask, file, FSNOTIFY_EVENT_FILE, NULL, 0); } /* @@ -187,16 +186,15 @@ static inline void fsnotify_mkdir(struct inode *inode, struct dentry *dentry) */ static inline void fsnotify_access(struct file *file) { - struct path *path = &file->f_path; - struct inode *inode = path->dentry->d_inode; + struct inode *inode = file->f_path.dentry->d_inode; __u32 mask = FS_ACCESS; if (S_ISDIR(inode->i_mode)) mask |= FS_IN_ISDIR; if (!(file->f_mode & FMODE_NONOTIFY)) { - fsnotify_parent(path, NULL, mask); - fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0); + fsnotify_parent(file, NULL, mask); + fsnotify(inode, mask, file, FSNOTIFY_EVENT_FILE, NULL, 0); } } @@ -205,16 +203,15 @@ static inline void fsnotify_access(struct file *file) */ static inline void fsnotify_modify(struct file *file) { - struct path *path = &file->f_path; - struct inode *inode = path->dentry->d_inode; + struct inode *inode = file->f_path.dentry->d_inode; __u32 mask = FS_MODIFY; if (S_ISDIR(inode->i_mode)) mask |= FS_IN_ISDIR; if (!(file->f_mode & FMODE_NONOTIFY)) { - fsnotify_parent(path, NULL, mask); - fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0); + fsnotify_parent(file, NULL, mask); + fsnotify(inode, mask, file, FSNOTIFY_EVENT_FILE, NULL, 0); } } @@ -223,16 +220,15 @@ static inline void fsnotify_modify(struct file *file) */ static inline void fsnotify_open(struct file *file) { - struct path *path = &file->f_path; - struct inode *inode = path->dentry->d_inode; + struct inode *inode = file->f_path.dentry->d_inode; __u32 mask = FS_OPEN; if (S_ISDIR(inode->i_mode)) mask |= FS_IN_ISDIR; if (!(file->f_mode & FMODE_NONOTIFY)) { - fsnotify_parent(path, NULL, mask); - fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0); + fsnotify_parent(file, NULL, mask); + fsnotify(inode, mask, file, FSNOTIFY_EVENT_FILE, NULL, 0); } } @@ -241,7 +237,6 @@ static inline void fsnotify_open(struct file *file) */ static inline void fsnotify_close(struct file *file) { - struct path *path = &file->f_path; struct inode *inode = file->f_path.dentry->d_inode; fmode_t mode = file->f_mode; __u32 mask = (mode & FMODE_WRITE) ? FS_CLOSE_WRITE : FS_CLOSE_NOWRITE; @@ -250,8 +245,8 @@ static inline void fsnotify_close(struct file *file) mask |= FS_IN_ISDIR; if (!(file->f_mode & FMODE_NONOTIFY)) { - fsnotify_parent(path, NULL, mask); - fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0); + fsnotify_parent(file, NULL, mask); + fsnotify(inode, mask, file, FSNOTIFY_EVENT_FILE, NULL, 0); } } diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 564b5ea4a831..3410d388163e 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -223,20 +223,20 @@ struct fsnotify_event { /* to_tell may ONLY be dereferenced during handle_event(). */ struct inode *to_tell; /* either the inode the event happened to or its parent */ /* - * depending on the event type we should have either a path or inode - * We hold a reference on path, but NOT on inode. Since we have the ref on - * the path, it may be dereferenced at any point during this object's + * depending on the event type we should have either a file or inode + * We hold a reference on file, but NOT on inode. Since we have the ref on + * the file, it may be dereferenced at any point during this object's * lifetime. That reference is dropped when this object's refcnt hits - * 0. If this event contains an inode instead of a path, the inode may + * 0. If this event contains an inode instead of a file, the inode may * ONLY be used during handle_event(). */ union { - struct path path; + struct file *file; struct inode *inode; }; /* when calling fsnotify tell it if the data is a path or inode */ #define FSNOTIFY_EVENT_NONE 0 -#define FSNOTIFY_EVENT_PATH 1 +#define FSNOTIFY_EVENT_FILE 1 #define FSNOTIFY_EVENT_INODE 2 int data_type; /* which of the above union we have */ atomic_t refcnt; /* how many groups still are using/need to send this event */ @@ -311,7 +311,7 @@ struct fsnotify_mark { /* main fsnotify call to send events */ extern int fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is, const unsigned char *name, u32 cookie); -extern void __fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask); +extern void __fsnotify_parent(struct file *file, struct dentry *dentry, __u32 mask); extern void __fsnotify_inode_delete(struct inode *inode); extern void __fsnotify_vfsmount_delete(struct vfsmount *mnt); extern u32 fsnotify_get_cookie(void); @@ -444,7 +444,7 @@ static inline int fsnotify(struct inode *to_tell, __u32 mask, void *data, int da return 0; } -static inline void __fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask) +static inline void __fsnotify_parent(struct file *file, struct dentry *dentry, __u32 mask) {} static inline void __fsnotify_inode_delete(struct inode *inode) -- cgit v1.2.3 From 700307a29ad61090dcf1d45f8f4a135f5e9211ae Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Wed, 28 Jul 2010 10:18:38 -0400 Subject: fsnotify: use an explicit flag to indicate fsnotify_destroy_mark has been called Currently fsnotify check is mark->group is NULL to decide if fsnotify_destroy_mark() has already been called or not. With the upcoming rcu work it is a heck of a lot easier to use an explicit flag than worry about group being set to NULL. Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 3410d388163e..8e24cdf72928 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -300,6 +300,7 @@ struct fsnotify_mark { #define FSNOTIFY_MARK_FLAG_VFSMOUNT 0x02 #define FSNOTIFY_MARK_FLAG_OBJECT_PINNED 0x04 #define FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY 0x08 +#define FSNOTIFY_MARK_FLAG_ALIVE 0x10 unsigned int flags; /* vfsmount or inode mark? */ void (*free_mark)(struct fsnotify_mark *mark); /* called on final put+free */ }; -- cgit v1.2.3 From 75c1be487a690db43da2c1234fcacd84c982803c Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Wed, 28 Jul 2010 10:18:38 -0400 Subject: fsnotify: srcu to protect read side of inode and vfsmount locks Currently reading the inode->i_fsnotify_marks or vfsmount->mnt_fsnotify_marks lists are protected by a spinlock on both the read and the write side. This patch protects the read side of those lists with a new single srcu. Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 8e24cdf72928..84159390969f 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -302,6 +302,7 @@ struct fsnotify_mark { #define FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY 0x08 #define FSNOTIFY_MARK_FLAG_ALIVE 0x10 unsigned int flags; /* vfsmount or inode mark? */ + struct list_head destroy_list; void (*free_mark)(struct fsnotify_mark *mark); /* called on final put+free */ }; -- cgit v1.2.3 From 3a9b16b407f10b2a771bcae13fb5791e527d6bcf Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Wed, 28 Jul 2010 10:18:38 -0400 Subject: fsnotify: send fsnotify_mark to groups in event handling functions With the change of fsnotify to use srcu walking the marks list instead of walking the global groups list we now know the mark in question. The code can send the mark to the group's handling functions and the groups won't have to find those marks themselves. Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 84159390969f..225dc0c3a48c 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -92,9 +92,10 @@ struct fsnotify_event_private_data; */ struct fsnotify_ops { bool (*should_send_event)(struct fsnotify_group *group, struct inode *inode, - struct vfsmount *mnt, __u32 mask, void *data, - int data_type); - int (*handle_event)(struct fsnotify_group *group, struct fsnotify_event *event); + struct vfsmount *mnt, struct fsnotify_mark *mark, + __u32 mask, void *data, int data_type); + int (*handle_event)(struct fsnotify_group *group, struct fsnotify_mark *mark, + struct fsnotify_event *event); void (*free_group_priv)(struct fsnotify_group *group); void (*freeing_mark)(struct fsnotify_mark *mark, struct fsnotify_group *group); void (*free_event_priv)(struct fsnotify_event_private_data *priv); -- cgit v1.2.3 From 03930979afa63e079e9aefd4d3dd429240711027 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Wed, 28 Jul 2010 10:18:39 -0400 Subject: fsnotify: remove the global masks Because we walk the object->fsnotify_marks list instead of the global fsnotify groups list we don't need the fsnotify_inode_mask and fsnotify_vfsmount_mask as these were simply shortcuts in fsnotify() for performance. They are now extra checks, rip them out. Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 225dc0c3a48c..07d3c8954721 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -365,8 +365,6 @@ static inline void __fsnotify_d_instantiate(struct dentry *dentry, struct inode /* called from fsnotify listeners, such as fanotify or dnotify */ -/* must call when a group changes its ->mask */ -extern void fsnotify_recalc_global_mask(void); /* get a reference to an existing or create a new group */ extern struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops); /* run all marks associated with this group and update group->mask */ -- cgit v1.2.3 From 43709a288ed03aa0e2979ab63dd089b3889645c4 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Wed, 28 Jul 2010 10:18:39 -0400 Subject: fsnotify: remove group->mask group->mask is now useless. It was originally a shortcut for fsnotify to save on performance. These checks are now redundant, so we remove them. Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 07d3c8954721..c4e7aab87461 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -119,15 +119,6 @@ struct fsnotify_group { */ struct list_head vfsmount_group_list; - /* - * Defines all of the event types in which this group is interested. - * This mask is a bitwise OR of the FS_* events from above. Each time - * this mask changes for a group (if it changes) the correct functions - * must be called to update the global structures which indicate global - * interest in event types. - */ - __u32 mask; - /* * How the refcnt is used is up to each group. When the refcnt hits 0 * fsnotify will clean up all of the resources associated with this group. @@ -367,8 +358,6 @@ static inline void __fsnotify_d_instantiate(struct dentry *dentry, struct inode /* get a reference to an existing or create a new group */ extern struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops); -/* run all marks associated with this group and update group->mask */ -extern void fsnotify_recalc_group_mask(struct fsnotify_group *group); /* drop reference on a group from fsnotify_alloc_group */ extern void fsnotify_put_group(struct fsnotify_group *group); -- cgit v1.2.3 From 02436668d98385f5b5d9ffb695a37dadf98ed8a8 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Wed, 28 Jul 2010 10:18:39 -0400 Subject: fsnotify: remove global fsnotify groups lists The global fsnotify groups lists were invented as a way to increase the performance of fsnotify by shortcutting events which were not interesting. With the changes to walk the object lists rather than global groups lists these shortcuts are not useful. Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 15 --------------- 1 file changed, 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index c4e7aab87461..2e7cc8c2a151 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -108,17 +108,6 @@ struct fsnotify_ops { * everything will be cleaned up. */ struct fsnotify_group { - /* - * global list of all groups receiving events from fsnotify. - * anchored by fsnotify_inode_groups and protected by either fsnotify_grp_mutex - * or fsnotify_grp_srcu depending on write vs read. - */ - struct list_head inode_group_list; - /* - * same as above except anchored by fsnotify_vfsmount_groups - */ - struct list_head vfsmount_group_list; - /* * How the refcnt is used is up to each group. When the refcnt hits 0 * fsnotify will clean up all of the resources associated with this group. @@ -145,10 +134,6 @@ struct fsnotify_group { * a group */ struct list_head marks_list; /* all inode marks for this group */ - /* prevents double list_del of group_list. protected by global fsnotify_grp_mutex */ - bool on_inode_group_list; - bool on_vfsmount_group_list; - /* groups can define private fields here or use the void *private */ union { void *private; -- cgit v1.2.3 From ce8f76fb7320297ccbe7c950fd9a2d727dd6a5a0 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Wed, 28 Jul 2010 10:18:39 -0400 Subject: fsnotify: pass both the vfsmount mark and inode mark should_send_event() and handle_event() will both need to look up the inode event if they get a vfsmount event. Lets just pass both at the same time since we have them both after walking the lists in lockstep. Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 2e7cc8c2a151..d38f922977f9 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -92,9 +92,12 @@ struct fsnotify_event_private_data; */ struct fsnotify_ops { bool (*should_send_event)(struct fsnotify_group *group, struct inode *inode, - struct vfsmount *mnt, struct fsnotify_mark *mark, + struct vfsmount *mnt, struct fsnotify_mark *inode_mark, + struct fsnotify_mark *vfsmount_mark, __u32 mask, void *data, int data_type); - int (*handle_event)(struct fsnotify_group *group, struct fsnotify_mark *mark, + int (*handle_event)(struct fsnotify_group *group, + struct fsnotify_mark *inode_mark, + struct fsnotify_mark *vfsmount_mark, struct fsnotify_event *event); void (*free_group_priv)(struct fsnotify_group *group); void (*freeing_mark)(struct fsnotify_mark *mark, struct fsnotify_group *group); -- cgit v1.2.3 From 1968f5eed54ce47bde488fd9a450912e4a2d7138 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Wed, 28 Jul 2010 10:18:39 -0400 Subject: fanotify: use both marks when possible fanotify currently, when given a vfsmount_mark will look up (if it exists) the corresponding inode mark. This patch drops that lookup and uses the mark provided. Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index d38f922977f9..9bbfd7204b04 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -92,7 +92,7 @@ struct fsnotify_event_private_data; */ struct fsnotify_ops { bool (*should_send_event)(struct fsnotify_group *group, struct inode *inode, - struct vfsmount *mnt, struct fsnotify_mark *inode_mark, + struct fsnotify_mark *inode_mark, struct fsnotify_mark *vfsmount_mark, __u32 mask, void *data, int data_type); int (*handle_event)(struct fsnotify_group *group, -- cgit v1.2.3 From 685fd0b4ea3f0f1d5385610b0d5b57775a8d5842 Mon Sep 17 00:00:00 2001 From: Ian Campbell Date: Thu, 29 Jul 2010 11:16:32 +0100 Subject: irq: Add new IRQ flag IRQF_NO_SUSPEND A small number of users of IRQF_TIMER are using it for the implied no suspend behaviour on interrupts which are not timer interrupts. Therefore add a new IRQF_NO_SUSPEND flag, rename IRQF_TIMER to __IRQF_TIMER and redefine IRQF_TIMER in terms of these new flags. Signed-off-by: Ian Campbell Cc: Jeremy Fitzhardinge Cc: Dmitry Torokhov Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Grant Likely Cc: xen-devel@lists.xensource.com Cc: linux-input@vger.kernel.org Cc: linuxppc-dev@ozlabs.org Cc: devicetree-discuss@lists.ozlabs.org LKML-Reference: <1280398595-29708-1-git-send-email-ian.campbell@citrix.com> Signed-off-by: Thomas Gleixner --- include/linux/interrupt.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index c2331138ca1b..a0384a4d1e6f 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -53,16 +53,21 @@ * IRQF_ONESHOT - Interrupt is not reenabled after the hardirq handler finished. * Used by threaded interrupts which need to keep the * irq line disabled until the threaded handler has been run. + * IRQF_NO_SUSPEND - Do not disable this IRQ during suspend + * */ #define IRQF_DISABLED 0x00000020 #define IRQF_SAMPLE_RANDOM 0x00000040 #define IRQF_SHARED 0x00000080 #define IRQF_PROBE_SHARED 0x00000100 -#define IRQF_TIMER 0x00000200 +#define __IRQF_TIMER 0x00000200 #define IRQF_PERCPU 0x00000400 #define IRQF_NOBALANCING 0x00000800 #define IRQF_IRQPOLL 0x00001000 #define IRQF_ONESHOT 0x00002000 +#define IRQF_NO_SUSPEND 0x00004000 + +#define IRQF_TIMER (__IRQF_TIMER | IRQF_NO_SUSPEND) /* * Bits used by threaded handlers: -- cgit v1.2.3 From 872e330e38806d835bd6c311c93ab998e2fb9058 Mon Sep 17 00:00:00 2001 From: Stefan Richter Date: Thu, 29 Jul 2010 18:19:22 +0200 Subject: firewire: add isochronous multichannel reception This adds the DMA context programming and userspace ABI for multichannel reception, i.e. for listening on multiple channel numbers by means of a single DMA context. The use case is reception of more streams than there are IR DMA units offered by the link layer. This is already implemented by the older ohci1394 + ieee1394 + raw1394 stack. And as discussed recently on linux1394-devel, this feature is occasionally used in practice. The big drawbacks of this mode are that buffer layout and interrupt generation necessarily differ from single-channel reception: Headers and trailers are not stripped from packets, packets are not aligned with buffer chunks, interrupts are per buffer chunk, not per packet. These drawbacks also cause a rather hefty code footprint to support this rarely used OHCI-1394 feature. (367 lines added, among them 94 lines of added userspace ABI documentation.) This implementation enforces that a multichannel reception context may only listen to channels to which no single-channel context on the same link layer is presently listening to. OHCI-1394 would allow to overlay single-channel contexts by the multi-channel context, but this would be a departure from the present first-come-first-served policy of IR context creation. The implementation is heavily based on an earlier one by Jay Fenlason. Thanks Jay. Signed-off-by: Stefan Richter --- include/linux/firewire-cdev.h | 281 +++++++++++++++++++++++++++++------------- include/linux/firewire.h | 29 +++-- 2 files changed, 214 insertions(+), 96 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firewire-cdev.h b/include/linux/firewire-cdev.h index 14831119ff71..bc5c26fc1c64 100644 --- a/include/linux/firewire-cdev.h +++ b/include/linux/firewire-cdev.h @@ -25,17 +25,18 @@ #include #include -#define FW_CDEV_EVENT_BUS_RESET 0x00 -#define FW_CDEV_EVENT_RESPONSE 0x01 -#define FW_CDEV_EVENT_REQUEST 0x02 -#define FW_CDEV_EVENT_ISO_INTERRUPT 0x03 -#define FW_CDEV_EVENT_ISO_RESOURCE_ALLOCATED 0x04 -#define FW_CDEV_EVENT_ISO_RESOURCE_DEALLOCATED 0x05 +#define FW_CDEV_EVENT_BUS_RESET 0x00 +#define FW_CDEV_EVENT_RESPONSE 0x01 +#define FW_CDEV_EVENT_REQUEST 0x02 +#define FW_CDEV_EVENT_ISO_INTERRUPT 0x03 +#define FW_CDEV_EVENT_ISO_RESOURCE_ALLOCATED 0x04 +#define FW_CDEV_EVENT_ISO_RESOURCE_DEALLOCATED 0x05 /* available since kernel version 2.6.36 */ -#define FW_CDEV_EVENT_REQUEST2 0x06 -#define FW_CDEV_EVENT_PHY_PACKET_SENT 0x07 -#define FW_CDEV_EVENT_PHY_PACKET_RECEIVED 0x08 +#define FW_CDEV_EVENT_REQUEST2 0x06 +#define FW_CDEV_EVENT_PHY_PACKET_SENT 0x07 +#define FW_CDEV_EVENT_PHY_PACKET_RECEIVED 0x08 +#define FW_CDEV_EVENT_ISO_INTERRUPT_MULTICHANNEL 0x09 /** * struct fw_cdev_event_common - Common part of all fw_cdev_event_ types @@ -218,35 +219,41 @@ struct fw_cdev_event_request2 { * This event is sent when the controller has completed an &fw_cdev_iso_packet * with the %FW_CDEV_ISO_INTERRUPT bit set. * - * Isochronous transmit events: + * Isochronous transmit events (context type %FW_CDEV_ISO_CONTEXT_TRANSMIT): * - * In version 1 of the ABI, &header_length is 0. In version 3 and some - * implementations of version 2 of the ABI, &header_length is a multiple of 4 - * and &header contains timestamps of all packets up until the interrupt packet. - * The format of the timestamps is as described below for isochronous reception. + * In version 3 and some implementations of version 2 of the ABI, &header_length + * is a multiple of 4 and &header contains timestamps of all packets up until + * the interrupt packet. The format of the timestamps is as described below for + * isochronous reception. In version 1 of the ABI, &header_length was 0. * - * Isochronous receive events: + * Isochronous receive events (context type %FW_CDEV_ISO_CONTEXT_RECEIVE): * * The headers stripped of all packets up until and including the interrupt * packet are returned in the @header field. The amount of header data per * packet is as specified at iso context creation by * &fw_cdev_create_iso_context.header_size. * - * In version 1 of this ABI, header data consisted of the 1394 isochronous - * packet header, followed by quadlets from the packet payload if - * &fw_cdev_create_iso_context.header_size > 4. + * Hence, _interrupt.header_length / _context.header_size is the number of + * packets received in this interrupt event. The client can now iterate + * through the mmap()'ed DMA buffer according to this number of packets and + * to the buffer sizes as the client specified in &fw_cdev_queue_iso. * - * In version 2 of this ABI, header data consist of the 1394 isochronous - * packet header, followed by a timestamp quadlet if - * &fw_cdev_create_iso_context.header_size > 4, followed by quadlets from the - * packet payload if &fw_cdev_create_iso_context.header_size > 8. + * Since version 2 of this ABI, the portion for each packet in _interrupt.header + * consists of the 1394 isochronous packet header, followed by a timestamp + * quadlet if &fw_cdev_create_iso_context.header_size > 4, followed by quadlets + * from the packet payload if &fw_cdev_create_iso_context.header_size > 8. * - * Behaviour of ver. 1 of this ABI is no longer available since ABI ver. 2. + * Format of 1394 iso packet header: 16 bits data_length, 2 bits tag, 6 bits + * channel, 4 bits tcode, 4 bits sy, in big endian byte order. + * data_length is the actual received size of the packet without the four + * 1394 iso packet header bytes. + * + * Format of timestamp: 16 bits invalid, 3 bits cycleSeconds, 13 bits + * cycleCount, in big endian byte order. * - * Format of 1394 iso packet header: 16 bits len, 2 bits tag, 6 bits channel, - * 4 bits tcode, 4 bits sy, in big endian byte order. Format of timestamp: - * 16 bits invalid, 3 bits cycleSeconds, 13 bits cycleCount, in big endian byte - * order. + * In version 1 of the ABI, no timestamp quadlet was inserted; instead, payload + * data followed directly after the 1394 is header if header_size > 4. + * Behaviour of ver. 1 of this ABI is no longer available since ABI ver. 2. */ struct fw_cdev_event_iso_interrupt { __u64 closure; @@ -256,6 +263,43 @@ struct fw_cdev_event_iso_interrupt { __u32 header[0]; }; +/** + * struct fw_cdev_event_iso_interrupt_mc - An iso buffer chunk was completed + * @closure: See &fw_cdev_event_common; + * set by %FW_CDEV_CREATE_ISO_CONTEXT ioctl + * @type: %FW_CDEV_EVENT_ISO_INTERRUPT_MULTICHANNEL + * @completed: Offset into the receive buffer; data before this offest is valid + * + * This event is sent in multichannel contexts (context type + * %FW_CDEV_ISO_CONTEXT_RECEIVE_MULTICHANNEL) for &fw_cdev_iso_packet buffer + * chunks that have the %FW_CDEV_ISO_INTERRUPT bit set. Whether this happens + * when a packet is completed and/or when a buffer chunk is completed depends + * on the hardware implementation. + * + * The buffer is continuously filled with the following data, per packet: + * - the 1394 iso packet header as described at &fw_cdev_event_iso_interrupt, + * but in little endian byte order, + * - packet payload (as many bytes as specified in the data_length field of + * the 1394 iso packet header) in big endian byte order, + * - 0...3 padding bytes as needed to align the following trailer quadlet, + * - trailer quadlet, containing the reception timestamp as described at + * &fw_cdev_event_iso_interrupt, but in little endian byte order. + * + * Hence the per-packet size is data_length (rounded up to a multiple of 4) + 8. + * When processing the data, stop before a packet that would cross the + * @completed offset. + * + * A packet near the end of a buffer chunk will typically spill over into the + * next queued buffer chunk. It is the responsibility of the client to check + * for this condition, assemble a broken-up packet from its parts, and not to + * re-queue any buffer chunks in which as yet unread packet parts reside. + */ +struct fw_cdev_event_iso_interrupt_mc { + __u64 closure; + __u32 type; + __u32 completed; +}; + /** * struct fw_cdev_event_iso_resource - Iso resources were allocated or freed * @closure: See &fw_cdev_event_common; @@ -311,16 +355,18 @@ struct fw_cdev_event_phy_packet { /** * union fw_cdev_event - Convenience union of fw_cdev_event_ types - * @common: Valid for all types - * @bus_reset: Valid if @common.type == %FW_CDEV_EVENT_BUS_RESET - * @response: Valid if @common.type == %FW_CDEV_EVENT_RESPONSE - * @request: Valid if @common.type == %FW_CDEV_EVENT_REQUEST - * @request2: Valid if @common.type == %FW_CDEV_EVENT_REQUEST2 - * @iso_interrupt: Valid if @common.type == %FW_CDEV_EVENT_ISO_INTERRUPT - * @iso_resource: Valid if @common.type == + * @common: Valid for all types + * @bus_reset: Valid if @common.type == %FW_CDEV_EVENT_BUS_RESET + * @response: Valid if @common.type == %FW_CDEV_EVENT_RESPONSE + * @request: Valid if @common.type == %FW_CDEV_EVENT_REQUEST + * @request2: Valid if @common.type == %FW_CDEV_EVENT_REQUEST2 + * @iso_interrupt: Valid if @common.type == %FW_CDEV_EVENT_ISO_INTERRUPT + * @iso_interrupt_mc: Valid if @common.type == + * %FW_CDEV_EVENT_ISO_INTERRUPT_MULTICHANNEL + * @iso_resource: Valid if @common.type == * %FW_CDEV_EVENT_ISO_RESOURCE_ALLOCATED or * %FW_CDEV_EVENT_ISO_RESOURCE_DEALLOCATED - * @phy_packet: Valid if @common.type == + * @phy_packet: Valid if @common.type == * %FW_CDEV_EVENT_PHY_PACKET_SENT or * %FW_CDEV_EVENT_PHY_PACKET_RECEIVED * @@ -337,10 +383,11 @@ union fw_cdev_event { struct fw_cdev_event_bus_reset bus_reset; struct fw_cdev_event_response response; struct fw_cdev_event_request request; - struct fw_cdev_event_request2 request2; /* added in 2.6.36 */ + struct fw_cdev_event_request2 request2; /* added in 2.6.36 */ struct fw_cdev_event_iso_interrupt iso_interrupt; - struct fw_cdev_event_iso_resource iso_resource; /* added in 2.6.30 */ - struct fw_cdev_event_phy_packet phy_packet; /* added in 2.6.36 */ + struct fw_cdev_event_iso_interrupt_mc iso_interrupt_mc; /* added in 2.6.36 */ + struct fw_cdev_event_iso_resource iso_resource; /* added in 2.6.30 */ + struct fw_cdev_event_phy_packet phy_packet; /* added in 2.6.36 */ }; /* available since kernel version 2.6.22 */ @@ -375,6 +422,7 @@ union fw_cdev_event { /* available since kernel version 2.6.36 */ #define FW_CDEV_IOC_SEND_PHY_PACKET _IOWR('#', 0x15, struct fw_cdev_send_phy_packet) #define FW_CDEV_IOC_RECEIVE_PHY_PACKETS _IOW('#', 0x16, struct fw_cdev_receive_phy_packets) +#define FW_CDEV_IOC_SET_ISO_CHANNELS _IOW('#', 0x17, struct fw_cdev_set_iso_channels) /* * ABI version history @@ -391,10 +439,13 @@ union fw_cdev_event { * - shared use and auto-response for FCP registers * 3 (2.6.34) - made &fw_cdev_get_cycle_timer reliable * - added %FW_CDEV_IOC_GET_CYCLE_TIMER2 - * 4 (2.6.36) - added %FW_CDEV_EVENT_REQUEST2, %FW_CDEV_EVENT_PHY_PACKET_* + * 4 (2.6.36) - added %FW_CDEV_EVENT_REQUEST2, %FW_CDEV_EVENT_PHY_PACKET_*, + * and &fw_cdev_allocate.region_end * - implemented &fw_cdev_event_bus_reset.bm_node_id * - added %FW_CDEV_IOC_SEND_PHY_PACKET, _RECEIVE_PHY_PACKETS - * - added &fw_cdev_allocate.region_end + * - added %FW_CDEV_EVENT_ISO_INTERRUPT_MULTICHANNEL, + * %FW_CDEV_ISO_CONTEXT_RECEIVE_MULTICHANNEL, and + * %FW_CDEV_IOC_SET_ISO_CHANNELS */ #define FW_CDEV_VERSION 3 /* Meaningless; don't use this macro. */ @@ -597,34 +648,43 @@ struct fw_cdev_remove_descriptor { __u32 handle; }; -#define FW_CDEV_ISO_CONTEXT_TRANSMIT 0 -#define FW_CDEV_ISO_CONTEXT_RECEIVE 1 +#define FW_CDEV_ISO_CONTEXT_TRANSMIT 0 +#define FW_CDEV_ISO_CONTEXT_RECEIVE 1 +#define FW_CDEV_ISO_CONTEXT_RECEIVE_MULTICHANNEL 2 /* added in 2.6.36 */ /** - * struct fw_cdev_create_iso_context - Create a context for isochronous IO - * @type: %FW_CDEV_ISO_CONTEXT_TRANSMIT or %FW_CDEV_ISO_CONTEXT_RECEIVE - * @header_size: Header size to strip for receive contexts - * @channel: Channel to bind to - * @speed: Speed for transmit contexts - * @closure: To be returned in &fw_cdev_event_iso_interrupt + * struct fw_cdev_create_iso_context - Create a context for isochronous I/O + * @type: %FW_CDEV_ISO_CONTEXT_TRANSMIT or %FW_CDEV_ISO_CONTEXT_RECEIVE or + * %FW_CDEV_ISO_CONTEXT_RECEIVE_MULTICHANNEL + * @header_size: Header size to strip in single-channel reception + * @channel: Channel to bind to in single-channel reception or transmission + * @speed: Transmission speed + * @closure: To be returned in &fw_cdev_event_iso_interrupt or + * &fw_cdev_event_iso_interrupt_multichannel * @handle: Handle to context, written back by kernel * * Prior to sending or receiving isochronous I/O, a context must be created. * The context records information about the transmit or receive configuration * and typically maps to an underlying hardware resource. A context is set up * for either sending or receiving. It is bound to a specific isochronous - * channel. + * @channel. * - * If a context was successfully created, the kernel writes back a handle to the - * context, which must be passed in for subsequent operations on that context. + * In case of multichannel reception, @header_size and @channel are ignored + * and the channels are selected by %FW_CDEV_IOC_SET_ISO_CHANNELS. + * + * For %FW_CDEV_ISO_CONTEXT_RECEIVE contexts, @header_size must be at least 4 + * and must be a multiple of 4. It is ignored in other context types. * - * For receive contexts, @header_size must be at least 4 and must be a multiple - * of 4. + * @speed is ignored in receive context types. * - * Note that the effect of a @header_size > 4 depends on - * &fw_cdev_get_info.version, as documented at &fw_cdev_event_iso_interrupt. + * If a context was successfully created, the kernel writes back a handle to the + * context, which must be passed in for subsequent operations on that context. * + * Limitations: * No more than one iso context can be created per fd. + * The total number of contexts that all userspace and kernelspace drivers can + * create on a card at a time is a hardware limit, typically 4 or 8 contexts per + * direction, and of them at most one multichannel receive context. */ struct fw_cdev_create_iso_context { __u32 type; @@ -635,6 +695,22 @@ struct fw_cdev_create_iso_context { __u32 handle; }; +/** + * struct fw_cdev_set_iso_channels - Select channels in multichannel reception + * @channels: Bitmask of channels to listen to + * @handle: Handle of the mutichannel receive context + * + * @channels is the bitwise or of 1ULL << n for each channel n to listen to. + * + * The ioctl fails with errno %EBUSY if there is already another receive context + * on a channel in @channels. In that case, the bitmask of all unoccupied + * channels is returned in @channels. + */ +struct fw_cdev_set_iso_channels { + __u64 channels; + __u32 handle; +}; + #define FW_CDEV_ISO_PAYLOAD_LENGTH(v) (v) #define FW_CDEV_ISO_INTERRUPT (1 << 16) #define FW_CDEV_ISO_SKIP (1 << 17) @@ -645,42 +721,72 @@ struct fw_cdev_create_iso_context { /** * struct fw_cdev_iso_packet - Isochronous packet - * @control: Contains the header length (8 uppermost bits), the sy field - * (4 bits), the tag field (2 bits), a sync flag (1 bit), - * a skip flag (1 bit), an interrupt flag (1 bit), and the + * @control: Contains the header length (8 uppermost bits), + * the sy field (4 bits), the tag field (2 bits), a sync flag + * or a skip flag (1 bit), an interrupt flag (1 bit), and the * payload length (16 lowermost bits) - * @header: Header and payload + * @header: Header and payload in case of a transmit context. * * &struct fw_cdev_iso_packet is used to describe isochronous packet queues. - * * Use the FW_CDEV_ISO_ macros to fill in @control. + * The @header array is empty in case of receive contexts. + * + * Context type %FW_CDEV_ISO_CONTEXT_TRANSMIT: + * + * @control.HEADER_LENGTH must be a multiple of 4. It specifies the numbers of + * bytes in @header that will be prepended to the packet's payload. These bytes + * are copied into the kernel and will not be accessed after the ioctl has + * returned. + * + * The @control.SY and TAG fields are copied to the iso packet header. These + * fields are specified by IEEE 1394a and IEC 61883-1. + * + * The @control.SKIP flag specifies that no packet is to be sent in a frame. + * When using this, all other fields except @control.INTERRUPT must be zero. + * + * When a packet with the @control.INTERRUPT flag set has been completed, an + * &fw_cdev_event_iso_interrupt event will be sent. + * + * Context type %FW_CDEV_ISO_CONTEXT_RECEIVE: * - * For transmit packets, the header length must be a multiple of 4 and specifies - * the numbers of bytes in @header that will be prepended to the packet's - * payload; these bytes are copied into the kernel and will not be accessed - * after the ioctl has returned. The sy and tag fields are copied to the iso - * packet header (these fields are specified by IEEE 1394a and IEC 61883-1). - * The skip flag specifies that no packet is to be sent in a frame; when using - * this, all other fields except the interrupt flag must be zero. - * - * For receive packets, the header length must be a multiple of the context's - * header size; if the header length is larger than the context's header size, - * multiple packets are queued for this entry. The sy and tag fields are - * ignored. If the sync flag is set, the context drops all packets until - * a packet with a matching sy field is received (the sync value to wait for is - * specified in the &fw_cdev_start_iso structure). The payload length defines - * how many payload bytes can be received for one packet (in addition to payload - * quadlets that have been defined as headers and are stripped and returned in - * the &fw_cdev_event_iso_interrupt structure). If more bytes are received, the - * additional bytes are dropped. If less bytes are received, the remaining - * bytes in this part of the payload buffer will not be written to, not even by - * the next packet, i.e., packets received in consecutive frames will not - * necessarily be consecutive in memory. If an entry has queued multiple - * packets, the payload length is divided equally among them. - * - * When a packet with the interrupt flag set has been completed, the + * @control.HEADER_LENGTH must be a multiple of the context's header_size. + * If the HEADER_LENGTH is larger than the context's header_size, multiple + * packets are queued for this entry. + * + * The @control.SY and TAG fields are ignored. + * + * If the @control.SYNC flag is set, the context drops all packets until a + * packet with a sy field is received which matches &fw_cdev_start_iso.sync. + * + * @control.PAYLOAD_LENGTH defines how many payload bytes can be received for + * one packet (in addition to payload quadlets that have been defined as headers + * and are stripped and returned in the &fw_cdev_event_iso_interrupt structure). + * If more bytes are received, the additional bytes are dropped. If less bytes + * are received, the remaining bytes in this part of the payload buffer will not + * be written to, not even by the next packet. I.e., packets received in + * consecutive frames will not necessarily be consecutive in memory. If an + * entry has queued multiple packets, the PAYLOAD_LENGTH is divided equally + * among them. + * + * When a packet with the @control.INTERRUPT flag set has been completed, an * &fw_cdev_event_iso_interrupt event will be sent. An entry that has queued * multiple receive packets is completed when its last packet is completed. + * + * Context type %FW_CDEV_ISO_CONTEXT_RECEIVE_MULTICHANNEL: + * + * Here, &fw_cdev_iso_packet would be more aptly named _iso_buffer_chunk since + * it specifies a chunk of the mmap()'ed buffer, while the number and alignment + * of packets to be placed into the buffer chunk is not known beforehand. + * + * @control.PAYLOAD_LENGTH is the size of the buffer chunk and specifies room + * for header, payload, padding, and trailer bytes of one or more packets. + * It must be a multiple of 4. + * + * @control.HEADER_LENGTH, TAG and SY are ignored. SYNC is treated as described + * for single-channel reception. + * + * When a buffer chunk with the @control.INTERRUPT flag set has been filled + * entirely, an &fw_cdev_event_iso_interrupt_mc event will be sent. */ struct fw_cdev_iso_packet { __u32 control; @@ -689,9 +795,9 @@ struct fw_cdev_iso_packet { /** * struct fw_cdev_queue_iso - Queue isochronous packets for I/O - * @packets: Userspace pointer to packet data + * @packets: Userspace pointer to an array of &fw_cdev_iso_packet * @data: Pointer into mmap()'ed payload buffer - * @size: Size of packet data in bytes + * @size: Size of the @packets array, in bytes * @handle: Isochronous context handle * * Queue a number of isochronous packets for reception or transmission. @@ -704,6 +810,9 @@ struct fw_cdev_iso_packet { * The kernel may or may not queue all packets, but will write back updated * values of the @packets, @data and @size fields, so the ioctl can be * resubmitted easily. + * + * In case of a multichannel receive context, @data must be quadlet-aligned + * relative to the buffer start. */ struct fw_cdev_queue_iso { __u64 packets; diff --git a/include/linux/firewire.h b/include/linux/firewire.h index d974aa4a24c9..1cd637ef62d2 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -372,17 +372,19 @@ void fw_core_remove_descriptor(struct fw_descriptor *desc); * scatter-gather streaming (e.g. assembling video frame automatically). */ struct fw_iso_packet { - u16 payload_length; /* Length of indirect payload. */ - u32 interrupt:1; /* Generate interrupt on this packet */ - u32 skip:1; /* Set to not send packet at all. */ - u32 tag:2; - u32 sy:4; - u32 header_length:8; /* Length of immediate header. */ - u32 header[0]; + u16 payload_length; /* Length of indirect payload */ + u32 interrupt:1; /* Generate interrupt on this packet */ + u32 skip:1; /* tx: Set to not send packet at all */ + /* rx: Sync bit, wait for matching sy */ + u32 tag:2; /* tx: Tag in packet header */ + u32 sy:4; /* tx: Sy in packet header */ + u32 header_length:8; /* Length of immediate header */ + u32 header[0]; /* tx: Top of 1394 isoch. data_block */ }; -#define FW_ISO_CONTEXT_TRANSMIT 0 -#define FW_ISO_CONTEXT_RECEIVE 1 +#define FW_ISO_CONTEXT_TRANSMIT 0 +#define FW_ISO_CONTEXT_RECEIVE 1 +#define FW_ISO_CONTEXT_RECEIVE_MULTICHANNEL 2 #define FW_ISO_CONTEXT_MATCH_TAG0 1 #define FW_ISO_CONTEXT_MATCH_TAG1 2 @@ -406,24 +408,31 @@ struct fw_iso_buffer { int fw_iso_buffer_init(struct fw_iso_buffer *buffer, struct fw_card *card, int page_count, enum dma_data_direction direction); void fw_iso_buffer_destroy(struct fw_iso_buffer *buffer, struct fw_card *card); +size_t fw_iso_buffer_lookup(struct fw_iso_buffer *buffer, dma_addr_t completed); struct fw_iso_context; typedef void (*fw_iso_callback_t)(struct fw_iso_context *context, u32 cycle, size_t header_length, void *header, void *data); +typedef void (*fw_iso_mc_callback_t)(struct fw_iso_context *context, + dma_addr_t completed, void *data); struct fw_iso_context { struct fw_card *card; int type; int channel; int speed; size_t header_size; - fw_iso_callback_t callback; + union { + fw_iso_callback_t sc; + fw_iso_mc_callback_t mc; + } callback; void *callback_data; }; struct fw_iso_context *fw_iso_context_create(struct fw_card *card, int type, int channel, int speed, size_t header_size, fw_iso_callback_t callback, void *callback_data); +int fw_iso_context_set_channels(struct fw_iso_context *ctx, u64 *channels); int fw_iso_context_queue(struct fw_iso_context *ctx, struct fw_iso_packet *packet, struct fw_iso_buffer *buffer, -- cgit v1.2.3 From c6601225380088018ae93df2ba7f0bb65334d63b Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Fri, 23 Jul 2010 15:04:01 -0600 Subject: of/device: Make of_device_make_bus_id() usable by other code. The AMBA bus should also use of_device_make_bus_id() when populating device out of device tree data. This patch makes the function non-static, and adds a suitable prototype in of_device.h Signed-off-by: Grant Likely --- include/linux/of_device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/of_device.h b/include/linux/of_device.h index e11a0be7893a..35aa44ad9f2c 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -27,6 +27,7 @@ extern const struct of_device_id *of_match_device( const struct of_device_id *matches, const struct device *dev); +extern void of_device_make_bus_id(struct device *dev); /** * of_driver_match_device - Tell if a driver's of_match_table matches a device. -- cgit v1.2.3 From 559e2b7ee7a1c7753d534abcb2742a4775339293 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Fri, 23 Jul 2010 20:11:18 -0600 Subject: of: Provide default of_node_to_nid() implementation. of_node_to_nid() is only relevant in a few architectures. Don't force everyone to implement it anyway. Signed-off-by: Grant Likely --- include/linux/of.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index b0756f33249e..cad7cf0ab278 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -146,6 +146,11 @@ static inline unsigned long of_read_ulong(const __be32 *cell, int size) #define OF_BAD_ADDR ((u64)-1) +#ifndef of_node_to_nid +static inline int of_node_to_nid(struct device_node *np) { return -1; } +#define of_node_to_nid of_node_to_nid +#endif + extern struct device_node *of_find_node_by_name(struct device_node *from, const char *name); #define for_each_node_by_name(dn, name) \ -- cgit v1.2.3 From 12b15e83289bc7cf2ec9a342412e0c955beeb395 Mon Sep 17 00:00:00 2001 From: Anatolij Gustschin Date: Tue, 27 Jul 2010 22:35:58 +0200 Subject: of/spi: call of_register_spi_devices() from spi core code Move of_register_spi_devices() call from drivers to spi_register_master(). Also change the function to use the struct device_node pointer from master spi device instead of passing it as function argument. Signed-off-by: Anatolij Gustschin Signed-off-by: Grant Likely --- include/linux/of_spi.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_spi.h b/include/linux/of_spi.h index 5f71ee8c0868..9e3e70f78ae6 100644 --- a/include/linux/of_spi.h +++ b/include/linux/of_spi.h @@ -9,10 +9,15 @@ #ifndef __LINUX_OF_SPI_H #define __LINUX_OF_SPI_H -#include #include -extern void of_register_spi_devices(struct spi_master *master, - struct device_node *np); +#if defined(CONFIG_OF_SPI) || defined(CONFIG_OF_SPI_MODULE) +extern void of_register_spi_devices(struct spi_master *master); +#else +static inline void of_register_spi_devices(struct spi_master *master) +{ + return; +} +#endif /* CONFIG_OF_SPI */ #endif /* __LINUX_OF_SPI */ -- cgit v1.2.3 From 253d2e549818f5a4a52e2db0aba3dacee21e5b38 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Fri, 16 Jul 2010 10:19:22 -0700 Subject: PCI: disable mmio during bar sizing It is a known issue that mmio decoding shall be disabled while doing PCI bar sizing. Host bridge and other devices (PCI PIC) shall be excluded for certain platforms. This patch mainly comes from Mathew Willcox's patch in http://kerneltrap.org/mailarchive/linux-kernel/2007/9/13/258969. A new flag bit "mmio_alway_on" is added to pci_dev with the intention that devices with their mmio decoding cannot be disabled during BAR sizing shall have this bit set, preferrablly in their quirks. Without this patch, Intel Moorestown platform graphics unit will be corrupted during bar sizing activities. Signed-off-by: Jacob Pan Signed-off-by: Jesse Barnes --- include/linux/pci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index f26fda76b87f..b1d17956a153 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -270,6 +270,8 @@ struct pci_dev { unsigned int d1_support:1; /* Low power state D1 is supported */ unsigned int d2_support:1; /* Low power state D2 is supported */ unsigned int no_d1d2:1; /* Only allow D0 and D3 */ + unsigned int mmio_always_on:1; /* disallow turning off io/mem + decoding during bar sizing */ unsigned int wakeup_prepared:1; unsigned int d3_delay; /* D3->D0 transition time in ms */ -- cgit v1.2.3 From 911e1c9b05a8e3559a7aa89083930700a0b9e7ee Mon Sep 17 00:00:00 2001 From: Narendra K Date: Mon, 26 Jul 2010 05:56:50 -0500 Subject: PCI: export SMBIOS provided firmware instance and label to sysfs This patch exports SMBIOS provided firmware instance and label of onboard PCI devices to sysfs. New files are: /sys/bus/pci/devices/.../label which contains the firmware name for the device in question, and /sys/bus/pci/devices/.../index which contains the firmware device type instance for the given device. Signed-off-by: Jordan Hargrave Signed-off-by: Narendra K Signed-off-by: Jesse Barnes --- include/linux/dmi.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmi.h b/include/linux/dmi.h index a8a3e1ac281d..90e087f8d951 100644 --- a/include/linux/dmi.h +++ b/include/linux/dmi.h @@ -20,6 +20,7 @@ enum dmi_device_type { DMI_DEV_TYPE_SAS, DMI_DEV_TYPE_IPMI = -1, DMI_DEV_TYPE_OEM_STRING = -2, + DMI_DEV_TYPE_DEV_ONBOARD = -3, }; struct dmi_header { @@ -37,6 +38,14 @@ struct dmi_device { #ifdef CONFIG_DMI +struct dmi_dev_onboard { + struct dmi_device dev; + int instance; + int segment; + int bus; + int devfn; +}; + extern int dmi_check_system(const struct dmi_system_id *list); const struct dmi_system_id *dmi_first_match(const struct dmi_system_id *list); extern const char * dmi_get_system_info(int field); -- cgit v1.2.3 From 30da55242818a8ca08583188ebcbaccd283ad4d9 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Fri, 23 Jul 2010 14:56:28 +0100 Subject: PCI: MSI: Restore read_msi_msg_desc(); add get_cached_msi_msg_desc() commit 2ca1af9aa3285c6a5f103ed31ad09f7399fc65d7 "PCI: MSI: Remove unsafe and unnecessary hardware access" changed read_msi_msg_desc() to return the last MSI message written instead of reading it from the device, since it may be called while the device is in a reduced power state. However, the pSeries platform code really does need to read messages from the device, since they are initially written by firmware. Therefore: - Restore the previous behaviour of read_msi_msg_desc() - Add new functions get_cached_msi_msg{,_desc}() which return the last MSI message written - Use the new functions where appropriate Acked-by: Michael Ellerman Signed-off-by: Ben Hutchings Signed-off-by: Jesse Barnes --- include/linux/msi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index 6991ab5b24d1..91b05c171854 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -14,8 +14,10 @@ struct irq_desc; extern void mask_msi_irq(unsigned int irq); extern void unmask_msi_irq(unsigned int irq); extern void read_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg); +extern void get_cached_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg); extern void write_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg); extern void read_msi_msg(unsigned int irq, struct msi_msg *msg); +extern void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg); extern void write_msi_msg(unsigned int irq, struct msi_msg *msg); struct msi_desc { -- cgit v1.2.3 From f11ac8db5d07b6e99d41ff4aa39d878ee5cef1c5 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 25 Jun 2010 16:35:53 -0400 Subject: NFSv4: Ensure that we track the NFSv4 lock state in read/write requests. This patch fixes bugzilla entry 14501: https://bugzilla.kernel.org/show_bug.cgi?id=14501 Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 13 +++++++++++-- include/linux/nfs_page.h | 1 + include/linux/nfs_xdr.h | 2 ++ 3 files changed, 14 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 77c2ae53431c..a9d802615082 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -72,13 +72,20 @@ struct nfs_access_entry { int mask; }; +struct nfs_lock_context { + atomic_t count; + struct list_head list; + struct nfs_open_context *open_context; + fl_owner_t lockowner; + pid_t pid; +}; + struct nfs4_state; struct nfs_open_context { - atomic_t count; + struct nfs_lock_context lock_context; struct path path; struct rpc_cred *cred; struct nfs4_state *state; - fl_owner_t lockowner; fmode_t mode; unsigned long flags; @@ -353,6 +360,8 @@ extern void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr); extern struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx); extern void put_nfs_open_context(struct nfs_open_context *ctx); extern struct nfs_open_context *nfs_find_open_context(struct inode *inode, struct rpc_cred *cred, fmode_t mode); +extern struct nfs_lock_context *nfs_get_lock_context(struct nfs_open_context *ctx); +extern void nfs_put_lock_context(struct nfs_lock_context *l_ctx); extern u64 nfs_compat_user_ino64(u64 fileid); extern void nfs_fattr_init(struct nfs_fattr *fattr); diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 3c60685d972b..f8b60e7f4c44 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -39,6 +39,7 @@ struct nfs_page { struct list_head wb_list; /* Defines state of page: */ struct page *wb_page; /* page to read in/write out */ struct nfs_open_context *wb_context; /* File state context info */ + struct nfs_lock_context *wb_lock_context; /* lock context info */ atomic_t wb_complete; /* i/os we're waiting for */ pgoff_t wb_index; /* Offset >> PAGE_CACHE_SHIFT */ unsigned int wb_offset, /* Offset & ~PAGE_CACHE_MASK */ diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index a319cb926abf..87202c7026e3 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -334,6 +334,7 @@ struct nfs4_delegreturnres { struct nfs_readargs { struct nfs_fh * fh; struct nfs_open_context *context; + struct nfs_lock_context *lock_context; __u64 offset; __u32 count; unsigned int pgbase; @@ -354,6 +355,7 @@ struct nfs_readres { struct nfs_writeargs { struct nfs_fh * fh; struct nfs_open_context *context; + struct nfs_lock_context *lock_context; __u64 offset; __u32 count; enum nfs3_stable_how stable; -- cgit v1.2.3 From d3c7b7ccc199ee564177ee914c04771d6bc00295 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 1 Jul 2010 12:49:01 -0400 Subject: NFSv4: Add support for the RELEASE_LOCKOWNER operation This is needed by NFSv4.0 servers in order to keep the number of locking stateids at a manageable level. Signed-off-by: Trond Myklebust --- include/linux/nfs4.h | 1 + include/linux/nfs_xdr.h | 4 ++++ 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 9b8299af3741..07e40c625972 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -523,6 +523,7 @@ enum { NFSPROC4_CLNT_GETACL, NFSPROC4_CLNT_SETACL, NFSPROC4_CLNT_FS_LOCATIONS, + NFSPROC4_CLNT_RELEASE_LOCKOWNER, /* nfs41 */ NFSPROC4_CLNT_EXCHANGE_ID, diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 87202c7026e3..fc461926c412 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -315,6 +315,10 @@ struct nfs_lockt_res { struct nfs4_sequence_res seq_res; }; +struct nfs_release_lockowner_args { + struct nfs_lowner lock_owner; +}; + struct nfs4_delegreturnargs { const struct nfs_fh *fhandle; const nfs4_stateid *stateid; -- cgit v1.2.3 From 22ae782f86b726f9cea752c0f269ff6dcdf2f6e1 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Thu, 29 Jul 2010 11:49:01 -0600 Subject: of/address: Clean up function declarations This patch moves the declaration of of_get_address(), of_get_pci_address(), and of_pci_address_to_resource() out of arch code and into the common linux/of_address header file. This patch also fixes some of the asm/prom.h ordering issues. It still includes some header files that it ideally shouldn't be, but at least the ordering is consistent now so that of_* overrides work. Signed-off-by: Grant Likely --- include/linux/of_address.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_address.h b/include/linux/of_address.h index cc567df9a00d..8aea06f0564c 100644 --- a/include/linux/of_address.h +++ b/include/linux/of_address.h @@ -8,5 +8,37 @@ extern int of_address_to_resource(struct device_node *dev, int index, struct resource *r); extern void __iomem *of_iomap(struct device_node *device, int index); +/* Extract an address from a device, returns the region size and + * the address space flags too. The PCI version uses a BAR number + * instead of an absolute index + */ +extern const u32 *of_get_address(struct device_node *dev, int index, + u64 *size, unsigned int *flags); + +#ifndef pci_address_to_pio +static inline unsigned long pci_address_to_pio(phys_addr_t addr) { return -1; } +#define pci_address_to_pio pci_address_to_pio +#endif + +#ifdef CONFIG_PCI +extern const u32 *of_get_pci_address(struct device_node *dev, int bar_no, + u64 *size, unsigned int *flags); +extern int of_pci_address_to_resource(struct device_node *dev, int bar, + struct resource *r); +#else /* CONFIG_PCI */ +static inline int of_pci_address_to_resource(struct device_node *dev, int bar, + struct resource *r) +{ + return -ENOSYS; +} + +static inline const u32 *of_get_pci_address(struct device_node *dev, + int bar_no, u64 *size, unsigned int *flags) +{ + return NULL; +} +#endif /* CONFIG_PCI */ + + #endif /* __OF_ADDRESS_H */ -- cgit v1.2.3 From 6ee0578b4daaea01c96b172c6aacca43fd9807a6 Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Fri, 30 Jul 2010 14:57:37 -0700 Subject: workqueue: mark init_workqueues() as early_initcall() Mark init_workqueues() as early_initcall() and thus it will be initialized before smp bringup. init_workqueues() registers for the hotcpu notifier and thus it should cope with the processors that are brought online after the workqueues are initialized. x86 smp bringup code uses workqueues and uses a workaround for the cold boot process (as the workqueues are initialized post smp_init()). Marking init_workqueues() as early_initcall() will pave the way for cleaning up this code. Signed-off-by: Suresh Siddha Signed-off-by: Tejun Heo Cc: Oleg Nesterov Cc: Andrew Morton --- include/linux/workqueue.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 5f76001c4e6d..51dc9a727e5e 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -327,7 +327,6 @@ extern int schedule_delayed_work_on(int cpu, struct delayed_work *work, extern int schedule_on_each_cpu(work_func_t func); extern int keventd_up(void); -extern void init_workqueues(void); int execute_in_process_context(work_func_t fn, struct execute_work *); extern int flush_work(struct work_struct *work); -- cgit v1.2.3 From 0814a979a64a5ae61c7567496d090e204ecabd2b Mon Sep 17 00:00:00 2001 From: Anatolij Gustschin Date: Fri, 23 Jul 2010 04:00:36 +0000 Subject: powerpc/5121: move fsl-diu-fb.h to include/linux Some DIU structures will be used in platform code in subsequent MPC5121 DIU patch, so we move this header to be able to include it elsewhere. Signed-off-by: Anatolij Gustschin Acked-by: Timur Tabi Signed-off-by: Grant Likely --- include/linux/fsl-diu-fb.h | 223 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 223 insertions(+) create mode 100644 include/linux/fsl-diu-fb.h (limited to 'include/linux') diff --git a/include/linux/fsl-diu-fb.h b/include/linux/fsl-diu-fb.h new file mode 100644 index 000000000000..fc295d7ea463 --- /dev/null +++ b/include/linux/fsl-diu-fb.h @@ -0,0 +1,223 @@ +/* + * Copyright 2008 Freescale Semiconductor, Inc. All Rights Reserved. + * + * Freescale DIU Frame Buffer device driver + * + * Authors: Hongjun Chen + * Paul Widmer + * Srikanth Srinivasan + * York Sun + * + * Based on imxfb.c Copyright (C) 2004 S.Hauer, Pengutronix + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + */ + +#ifndef __FSL_DIU_FB_H__ +#define __FSL_DIU_FB_H__ + +/* Arbitrary threshold to determine the allocation method + * See mpc8610fb_set_par(), map_video_memory(), and unmap_video_memory() + */ +#define MEM_ALLOC_THRESHOLD (1024*768*4+32) +/* Minimum value that the pixel clock can be set to in pico seconds + * This is determined by platform clock/3 where the minimum platform + * clock is 533MHz. This gives 5629 pico seconds. + */ +#define MIN_PIX_CLK 5629 +#define MAX_PIX_CLK 96096 + +#include + +struct mfb_alpha { + int enable; + int alpha; +}; + +struct mfb_chroma_key { + int enable; + __u8 red_max; + __u8 green_max; + __u8 blue_max; + __u8 red_min; + __u8 green_min; + __u8 blue_min; +}; + +struct aoi_display_offset { + int x_aoi_d; + int y_aoi_d; +}; + +#define MFB_SET_CHROMA_KEY _IOW('M', 1, struct mfb_chroma_key) +#define MFB_WAIT_FOR_VSYNC _IOW('F', 0x20, u_int32_t) +#define MFB_SET_BRIGHTNESS _IOW('M', 3, __u8) + +#define MFB_SET_ALPHA 0x80014d00 +#define MFB_GET_ALPHA 0x40014d00 +#define MFB_SET_AOID 0x80084d04 +#define MFB_GET_AOID 0x40084d04 +#define MFB_SET_PIXFMT 0x80014d08 +#define MFB_GET_PIXFMT 0x40014d08 + +#define FBIOGET_GWINFO 0x46E0 +#define FBIOPUT_GWINFO 0x46E1 + +#ifdef __KERNEL__ +#include + +/* + * These are the fields of area descriptor(in DDR memory) for every plane + */ +struct diu_ad { + /* Word 0(32-bit) in DDR memory */ +/* __u16 comp; */ +/* __u16 pixel_s:2; */ +/* __u16 pallete:1; */ +/* __u16 red_c:2; */ +/* __u16 green_c:2; */ +/* __u16 blue_c:2; */ +/* __u16 alpha_c:3; */ +/* __u16 byte_f:1; */ +/* __u16 res0:3; */ + + __be32 pix_fmt; /* hard coding pixel format */ + + /* Word 1(32-bit) in DDR memory */ + __le32 addr; + + /* Word 2(32-bit) in DDR memory */ +/* __u32 delta_xs:11; */ +/* __u32 res1:1; */ +/* __u32 delta_ys:11; */ +/* __u32 res2:1; */ +/* __u32 g_alpha:8; */ + __le32 src_size_g_alpha; + + /* Word 3(32-bit) in DDR memory */ +/* __u32 delta_xi:11; */ +/* __u32 res3:5; */ +/* __u32 delta_yi:11; */ +/* __u32 res4:3; */ +/* __u32 flip:2; */ + __le32 aoi_size; + + /* Word 4(32-bit) in DDR memory */ + /*__u32 offset_xi:11; + __u32 res5:5; + __u32 offset_yi:11; + __u32 res6:5; + */ + __le32 offset_xyi; + + /* Word 5(32-bit) in DDR memory */ + /*__u32 offset_xd:11; + __u32 res7:5; + __u32 offset_yd:11; + __u32 res8:5; */ + __le32 offset_xyd; + + + /* Word 6(32-bit) in DDR memory */ + __u8 ckmax_r; + __u8 ckmax_g; + __u8 ckmax_b; + __u8 res9; + + /* Word 7(32-bit) in DDR memory */ + __u8 ckmin_r; + __u8 ckmin_g; + __u8 ckmin_b; + __u8 res10; +/* __u32 res10:8; */ + + /* Word 8(32-bit) in DDR memory */ + __le32 next_ad; + + /* Word 9(32-bit) in DDR memory, just for 64-bit aligned */ + __u32 paddr; +} __attribute__ ((packed)); + +/* DIU register map */ +struct diu { + __be32 desc[3]; + __be32 gamma; + __be32 pallete; + __be32 cursor; + __be32 curs_pos; + __be32 diu_mode; + __be32 bgnd; + __be32 bgnd_wb; + __be32 disp_size; + __be32 wb_size; + __be32 wb_mem_addr; + __be32 hsyn_para; + __be32 vsyn_para; + __be32 syn_pol; + __be32 thresholds; + __be32 int_status; + __be32 int_mask; + __be32 colorbar[8]; + __be32 filling; + __be32 plut; +} __attribute__ ((packed)); + +struct diu_hw { + struct diu *diu_reg; + spinlock_t reg_lock; + + __u32 mode; /* DIU operation mode */ +}; + +struct diu_addr { + __u8 __iomem *vaddr; /* Virtual address */ + dma_addr_t paddr; /* Physical address */ + __u32 offset; +}; + +struct diu_pool { + struct diu_addr ad; + struct diu_addr gamma; + struct diu_addr pallete; + struct diu_addr cursor; +}; + +#define FSL_DIU_BASE_OFFSET 0x2C000 /* Offset of DIU */ +#define INT_LCDC 64 /* DIU interrupt number */ + +#define FSL_AOI_NUM 6 /* 5 AOIs and one dummy AOI */ + /* 1 for plane 0, 2 for plane 1&2 each */ + +/* Minimum X and Y resolutions */ +#define MIN_XRES 64 +#define MIN_YRES 64 + +/* HW cursor parameters */ +#define MAX_CURS 32 + +/* Modes of operation of DIU */ +#define MFB_MODE0 0 /* DIU off */ +#define MFB_MODE1 1 /* All three planes output to display */ +#define MFB_MODE2 2 /* Plane 1 to display, planes 2+3 written back*/ +#define MFB_MODE3 3 /* All three planes written back to memory */ +#define MFB_MODE4 4 /* Color bar generation */ + +/* INT_STATUS/INT_MASK field descriptions */ +#define INT_VSYNC 0x01 /* Vsync interrupt */ +#define INT_VSYNC_WB 0x02 /* Vsync interrupt for write back operation */ +#define INT_UNDRUN 0x04 /* Under run exception interrupt */ +#define INT_PARERR 0x08 /* Display parameters error interrupt */ +#define INT_LS_BF_VS 0x10 /* Lines before vsync. interrupt */ + +/* Panels'operation modes */ +#define MFB_TYPE_OUTPUT 0 /* Panel output to display */ +#define MFB_TYPE_OFF 1 /* Panel off */ +#define MFB_TYPE_WB 2 /* Panel written back to memory */ +#define MFB_TYPE_TEST 3 /* Panel generate color bar */ + +#endif /* __KERNEL__ */ +#endif /* __FSL_DIU_FB_H__ */ -- cgit v1.2.3 From 08354809d6c73eb73973e132502a0a4e53250971 Mon Sep 17 00:00:00 2001 From: Jassi Brar Date: Fri, 25 Jun 2010 18:21:19 +0900 Subject: ahci_platform: Provide for vendor specific init Some AHCI implementations may use Vendor Specific HBA[A0h, FFh] and/or Port[70h, 7Fh] registers to 'prepare' for initialization. For that, the platform needs memory mapped address of AHCI registers. This patch adds the 'mmio' argument and reorders the call to platform init function. Signed-off-by: Jassi Brar Signed-off-by: Jeff Garzik --- include/linux/ahci_platform.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ahci_platform.h b/include/linux/ahci_platform.h index f7dd576dd5a4..be3d9a77d6ed 100644 --- a/include/linux/ahci_platform.h +++ b/include/linux/ahci_platform.h @@ -15,11 +15,13 @@ #ifndef _AHCI_PLATFORM_H #define _AHCI_PLATFORM_H +#include + struct device; struct ata_port_info; struct ahci_platform_data { - int (*init)(struct device *dev); + int (*init)(struct device *dev, void __iomem *addr); void (*exit)(struct device *dev); const struct ata_port_info *ata_port_info; unsigned int force_port_map; -- cgit v1.2.3 From 5b6ae5ba0c45c4d04721537308728688414c9e6b Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 30 Jul 2010 11:42:42 +0200 Subject: libata: more PCI IDs for jmicron controllers Add support for JMB364 and 369. Patch-originally-from: Aries Lee Signed-off-by: Tejun Heo Signed-off-by: Jeff Garzik --- include/linux/pci_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 3bedcc149c84..eb200e6beb65 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2324,9 +2324,11 @@ #define PCI_DEVICE_ID_JMICRON_JMB361 0x2361 #define PCI_DEVICE_ID_JMICRON_JMB362 0x2362 #define PCI_DEVICE_ID_JMICRON_JMB363 0x2363 +#define PCI_DEVICE_ID_JMICRON_JMB364 0x2364 #define PCI_DEVICE_ID_JMICRON_JMB365 0x2365 #define PCI_DEVICE_ID_JMICRON_JMB366 0x2366 #define PCI_DEVICE_ID_JMICRON_JMB368 0x2368 +#define PCI_DEVICE_ID_JMICRON_JMB369 0x2369 #define PCI_DEVICE_ID_JMICRON_JMB38X_SD 0x2381 #define PCI_DEVICE_ID_JMICRON_JMB38X_MMC 0x2382 #define PCI_DEVICE_ID_JMICRON_JMB38X_MS 0x2383 -- cgit v1.2.3 From 9938424f0c4d208883cbf32083ec2bfcc220f85b Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Mon, 14 Jun 2010 18:10:33 +0200 Subject: mtd: add an ioctl to query the lock status of a flash sector This patchs adds a way for user space programs to find out whether a flash sector is locked. An optional driver method in the mtd_info struct provides the information. Signed-off-by: Richard Cochran Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/mtd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index 5326435a7571..43b7d72c6116 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -216,6 +216,7 @@ struct mtd_info { /* Chip-supported device locking */ int (*lock) (struct mtd_info *mtd, loff_t ofs, uint64_t len); int (*unlock) (struct mtd_info *mtd, loff_t ofs, uint64_t len); + int (*is_locked) (struct mtd_info *mtd, loff_t ofs, uint64_t len); /* Power Management functions */ int (*suspend) (struct mtd_info *mtd); -- cgit v1.2.3 From 30fe8115b55223cb84530ce04c4a20ba9d6dcf0b Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Wed, 23 Jun 2010 13:36:02 -0700 Subject: mtd: nand: edit macro flag for BBT scan of last page in block NAND_BB_LAST_PAGE used to be in nand.h, but it pertained to bad block management and so belongs next to NAND_BBT_SCAN2NDPAGE in bbm.h. Also, its previous flag value (0x00000400) conflicted with NAND_BBT_SCANALLPAGES so I changed its value to 0x00008000. All uses of the name were modified to provide consistency with other "NAND_BBT_*" flags. Signed-off-by: Brian Norris Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/bbm.h | 2 ++ include/linux/mtd/nand.h | 2 -- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/bbm.h b/include/linux/mtd/bbm.h index 9c3757c5759d..8ad0b8629c3f 100644 --- a/include/linux/mtd/bbm.h +++ b/include/linux/mtd/bbm.h @@ -82,6 +82,8 @@ struct nand_bbt_descr { #define NAND_BBT_SAVECONTENT 0x00002000 /* Search good / bad pattern on the first and the second page */ #define NAND_BBT_SCAN2NDPAGE 0x00004000 +/* Search good / bad pattern on the last page of the eraseblock */ +#define NAND_BBT_SCANLASTPAGE 0x00008000 /* The maximum number of blocks to scan for a bbt */ #define NAND_BBT_SCAN_MAXBLOCKS 4 diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index a81b185e23a7..50f3aa00a452 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -181,8 +181,6 @@ typedef enum { #define NAND_NO_READRDY 0x00000100 /* Chip does not allow subpage writes */ #define NAND_NO_SUBPAGE_WRITE 0x00000200 -/* Chip stores bad block marker on the last page of the eraseblock */ -#define NAND_BB_LAST_PAGE 0x00000400 /* Device is one of 'new' xD cards that expose fake nand command set */ #define NAND_BROKEN_XD 0x00000400 -- cgit v1.2.3 From 58373ff0afff4cc8ac40608872995f4d87eb72ec Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Thu, 15 Jul 2010 12:15:44 -0700 Subject: mtd: nand: more BB Detection refactoring and dynamic scan options This is a revision to PATCH 2/2 that I sent. Link: http://lists.infradead.org/pipermail/linux-mtd/2010-July/030911.html Added new flag for scanning of both bytes 1 and 6 of the OOB for a BB marker (instead of simply one or the other). The "check_pattern" and "check_short_pattern" functions were updated to include support for scanning the two different locations in the OOB. In order to handle increases in variety of necessary scanning patterns, I implemented dynamic memory allocation of nand_bbt_descr structs in new function 'nand_create_default_bbt_descr()'. This replaces some increasingly-unwieldy, statically-declared descriptors. It can replace several more (e.g. "flashbased" structs). However, I do not test the flashbased options personally. How this was tested: I referenced 30+ data sheets (covering 100+ parts), and I tested a selection of 10 different chips to varying degrees. Particularly, I tested the creation of bad-block descriptors and basic BB scanning on three parts: ST NAND04GW3B2D, 2K page ST NAND128W3A, 512B page Samsung K9F1G08U0A, 2K page To test these, I wrote some fake bad block markers to the flash (in OOB bytes 1, 6, and elsewhere) to see if the scanning routine would detect them properly. However, this method was somewhat limited because the driver I am using has some bugs in its OOB write functionality. Signed-off-by: Brian Norris Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/bbm.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/bbm.h b/include/linux/mtd/bbm.h index 8ad0b8629c3f..a04b962492a8 100644 --- a/include/linux/mtd/bbm.h +++ b/include/linux/mtd/bbm.h @@ -84,6 +84,10 @@ struct nand_bbt_descr { #define NAND_BBT_SCAN2NDPAGE 0x00004000 /* Search good / bad pattern on the last page of the eraseblock */ #define NAND_BBT_SCANLASTPAGE 0x00008000 +/* Chip stores bad block marker on BOTH 1st and 6th bytes of OOB */ +#define NAND_BBT_SCANBYTE1AND6 0x00100000 +/* The nand_bbt_descr was created dynamicaly and must be freed */ +#define NAND_BBT_DYNAMICSTRUCT 0x00200000 /* The maximum number of blocks to scan for a bbt */ #define NAND_BBT_SCAN_MAXBLOCKS 4 -- cgit v1.2.3 From a51dca9cd3bb4ec5a05bfb6feabf024a5c808a37 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Mon, 2 Aug 2010 08:43:25 -0400 Subject: jbd2: Use atomic variables to avoid taking t_handle_lock in jbd2_journal_stop By using an atomic_t for t_updates and t_outstanding credits, this should allow us to not need to take transaction t_handle_lock in jbd2_journal_stop(). Signed-off-by: "Theodore Ts'o" --- include/linux/jbd2.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 5a72bc75b273..a72ce21de0e1 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -601,13 +601,13 @@ struct transaction_s * Number of outstanding updates running on this transaction * [t_handle_lock] */ - int t_updates; + atomic_t t_updates; /* * Number of buffers reserved for use by all handles in this transaction * handle but not yet modified. [t_handle_lock] */ - int t_outstanding_credits; + atomic_t t_outstanding_credits; /* * Forward and backward links for the circular list of all transactions @@ -1258,8 +1258,8 @@ static inline int jbd_space_needed(journal_t *journal) { int nblocks = journal->j_max_transaction_buffers; if (journal->j_committing_transaction) - nblocks += journal->j_committing_transaction-> - t_outstanding_credits; + nblocks += atomic_read(&journal->j_committing_transaction-> + t_outstanding_credits); return nblocks; } -- cgit v1.2.3 From 7957e9c4d175cc065f4277211fcb7d784fcee860 Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Mon, 2 Aug 2010 19:33:51 -0700 Subject: Input: add static inline accessors for ABS properties In preparation for dynamically allocated ABS axis, introduce a number of static inline access helpers. This should make the transition less painful. Signed-off-by: Daniel Mack Signed-off-by: Dmitry Torokhov --- include/linux/input.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include/linux') diff --git a/include/linux/input.h b/include/linux/input.h index 339d043ccb53..4a5531161de1 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -1469,6 +1469,36 @@ static inline void input_set_abs_params(struct input_dev *dev, int axis, int min dev->absbit[BIT_WORD(axis)] |= BIT_MASK(axis); } +#define INPUT_GENERATE_ABS_ACCESSORS(_suffix, _item) \ +static inline int input_abs_get_##_suffix(struct input_dev *dev, \ + unsigned int axis) \ +{ \ + return dev->abs##_item[axis]; \ +} \ + \ +static inline void input_abs_set_##_suffix(struct input_dev *dev, \ + unsigned int axis, int val) \ +{ \ + dev->abs##_item[axis] = val; \ +} + +INPUT_GENERATE_ABS_ACCESSORS(min, min) +INPUT_GENERATE_ABS_ACCESSORS(max, max) +INPUT_GENERATE_ABS_ACCESSORS(fuzz, fuzz) +INPUT_GENERATE_ABS_ACCESSORS(flat, flat) +INPUT_GENERATE_ABS_ACCESSORS(res, res) + +static inline int input_abs_get_val(struct input_dev *dev, unsigned int axis) +{ + return dev->abs[axis]; +} + +static inline void input_abs_set_val(struct input_dev *dev, + unsigned int axis, int val) +{ + dev->abs[axis] = val; +} + int input_get_keycode(struct input_dev *dev, unsigned int scancode, unsigned int *keycode); int input_set_keycode(struct input_dev *dev, -- cgit v1.2.3 From d31b2865a4e8a9dd02f39e56c8fadb824c5e187b Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Mon, 2 Aug 2010 20:18:21 -0700 Subject: Input: dynamically allocate ABS information As all callers are now changed to only use the input_abs_*() access helpers, switching over to dynamically allocated ABS information is easy. This reduces size of struct input_dev from 3152 to 1640 on 64 bit architectures. Signed-off-by: Daniel Mack Signed-off-by: Dmitry Torokhov --- include/linux/input.h | 57 ++++++++++++++++----------------------------------- 1 file changed, 18 insertions(+), 39 deletions(-) (limited to 'include/linux') diff --git a/include/linux/input.h b/include/linux/input.h index 4a5531161de1..896a92227bc4 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -776,6 +776,7 @@ struct input_absinfo { #define REP_DELAY 0x00 #define REP_PERIOD 0x01 #define REP_MAX 0x01 +#define REP_CNT (REP_MAX+1) /* * Sounds @@ -1099,21 +1100,18 @@ struct input_mt_slot { * @repeat_key: stores key code of the last key pressed; used to implement * software autorepeat * @timer: timer for software autorepeat - * @abs: current values for reports from absolute axes * @rep: current values for autorepeat parameters (delay, rate) * @mt: pointer to array of struct input_mt_slot holding current values * of tracked contacts * @mtsize: number of MT slots the device uses * @slot: MT slot currently being transmitted + * @absinfo: array of &struct absinfo elements holding information + * about absolute axes (current value, min, max, flat, fuzz, + * resolution) * @key: reflects current state of device's keys/buttons * @led: reflects current state of device's LEDs * @snd: reflects current state of sound effects * @sw: reflects current state of device's switches - * @absmax: maximum values for events coming from absolute axes - * @absmin: minimum values for events coming from absolute axes - * @absfuzz: describes noisiness for axes - * @absflat: size of the center flat position (used by joydev) - * @absres: resolution used for events coming form absolute axes * @open: this method is called when the very first user calls * input_open_device(). The driver must prepare the device * to start generating events (start polling thread, @@ -1180,24 +1178,19 @@ struct input_dev { unsigned int repeat_key; struct timer_list timer; - int abs[ABS_CNT]; - int rep[REP_MAX + 1]; + int rep[REP_CNT]; struct input_mt_slot *mt; int mtsize; int slot; + struct input_absinfo *absinfo; + unsigned long key[BITS_TO_LONGS(KEY_CNT)]; unsigned long led[BITS_TO_LONGS(LED_CNT)]; unsigned long snd[BITS_TO_LONGS(SND_CNT)]; unsigned long sw[BITS_TO_LONGS(SW_CNT)]; - int absmax[ABS_CNT]; - int absmin[ABS_CNT]; - int absfuzz[ABS_CNT]; - int absflat[ABS_CNT]; - int absres[ABS_CNT]; - int (*open)(struct input_dev *dev); void (*close)(struct input_dev *dev); int (*flush)(struct input_dev *dev, struct file *file); @@ -1459,45 +1452,31 @@ static inline void input_set_events_per_packet(struct input_dev *dev, int n_even dev->hint_events_per_packet = n_events; } -static inline void input_set_abs_params(struct input_dev *dev, int axis, int min, int max, int fuzz, int flat) -{ - dev->absmin[axis] = min; - dev->absmax[axis] = max; - dev->absfuzz[axis] = fuzz; - dev->absflat[axis] = flat; - - dev->absbit[BIT_WORD(axis)] |= BIT_MASK(axis); -} +void input_alloc_absinfo(struct input_dev *dev); +void input_set_abs_params(struct input_dev *dev, unsigned int axis, + int min, int max, int fuzz, int flat); #define INPUT_GENERATE_ABS_ACCESSORS(_suffix, _item) \ static inline int input_abs_get_##_suffix(struct input_dev *dev, \ unsigned int axis) \ { \ - return dev->abs##_item[axis]; \ + return dev->absinfo ? dev->absinfo[axis]._item : 0; \ } \ \ static inline void input_abs_set_##_suffix(struct input_dev *dev, \ unsigned int axis, int val) \ { \ - dev->abs##_item[axis] = val; \ + input_alloc_absinfo(dev); \ + if (dev->absinfo) \ + dev->absinfo[axis]._item = val; \ } -INPUT_GENERATE_ABS_ACCESSORS(min, min) -INPUT_GENERATE_ABS_ACCESSORS(max, max) +INPUT_GENERATE_ABS_ACCESSORS(val, value) +INPUT_GENERATE_ABS_ACCESSORS(min, minimum) +INPUT_GENERATE_ABS_ACCESSORS(max, maximum) INPUT_GENERATE_ABS_ACCESSORS(fuzz, fuzz) INPUT_GENERATE_ABS_ACCESSORS(flat, flat) -INPUT_GENERATE_ABS_ACCESSORS(res, res) - -static inline int input_abs_get_val(struct input_dev *dev, unsigned int axis) -{ - return dev->abs[axis]; -} - -static inline void input_abs_set_val(struct input_dev *dev, - unsigned int axis, int val) -{ - dev->abs[axis] = val; -} +INPUT_GENERATE_ABS_ACCESSORS(res, resolution) int input_get_keycode(struct input_dev *dev, unsigned int scancode, unsigned int *keycode); -- cgit v1.2.3 From 078ff546a806b2c2ab74c25c8edd4c6d4680656a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Wed, 17 Mar 2010 20:36:51 +0200 Subject: OMAP: DSS2: OMAPFB: Add support for switching memory regions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Separate the memory region from the framebuffer device a little bit. It's now possible to select the memory region used by the framebuffer device using the new mem_idx parameter of omapfb_plane_info. If the mem_idx is specified it will be interpreted as an index into the memory regions array, if it's not specified the framebuffer's index is used instead. So by default each framebuffer keeps using it's own memory region which preserves backwards compatibility. This allows cloning the same memory region to several overlays and yet each overlay can be controlled independently since they can be associated with separate framebuffer devices. Signed-off-by: Ville Syrjälä Signed-off-by: Tomi Valkeinen --- include/linux/omapfb.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/omapfb.h b/include/linux/omapfb.h index 9bdd91486b49..0ecf7311c1ae 100644 --- a/include/linux/omapfb.h +++ b/include/linux/omapfb.h @@ -85,6 +85,9 @@ #define OMAPFB_MEMTYPE_SRAM 1 #define OMAPFB_MEMTYPE_MAX 1 +#define OMAPFB_MEM_IDX_ENABLED 0x80 +#define OMAPFB_MEM_IDX_MASK 0x7f + enum omapfb_color_format { OMAPFB_COLOR_RGB565 = 0, OMAPFB_COLOR_YUV422, @@ -136,7 +139,7 @@ struct omapfb_plane_info { __u8 enabled; __u8 channel_out; __u8 mirror; - __u8 reserved1; + __u8 mem_idx; __u32 out_width; __u32 out_height; __u32 reserved2[12]; -- cgit v1.2.3 From a931da6ac9331a6c80dd91c199105806f2336188 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Tue, 3 Aug 2010 21:35:12 -0400 Subject: jbd2: Change j_state_lock to be a rwlock_t Lockstat reports have shown that j_state_lock is a major source of lock contention, especially on systems with more than 4 CPU cores. So change it to be a read/write spinlock. Signed-off-by: "Theodore Ts'o" --- include/linux/jbd2.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index a72ce21de0e1..15d5743ccfbb 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -764,7 +764,7 @@ struct journal_s /* * Protect the various scalars in the journal */ - spinlock_t j_state_lock; + rwlock_t j_state_lock; /* * Number of processes waiting to create a barrier lock [j_state_lock] -- cgit v1.2.3 From 8dd420466c7bfc459fa04680bd5690bfc41a4553 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Tue, 3 Aug 2010 21:38:29 -0400 Subject: jbd2: Remove t_handle_lock from start_this_handle() This should remove the last exclusive lock from start_this_handle(), so that we should now be able to start multiple transactions at the same time on large SMP systems. Signed-off-by: "Theodore Ts'o" --- include/linux/jbd2.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 15d5743ccfbb..01743b5446ff 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -629,7 +629,7 @@ struct transaction_s /* * How many handles used this transaction? [t_handle_lock] */ - int t_handle_count; + atomic_t t_handle_count; /* * This transaction is being forced and some process is -- cgit v1.2.3 From f1f88fc7e818c6678c6799a2edb8f1aeccc124aa Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 31 Jul 2010 14:29:07 -0400 Subject: SUNRPC: The function rpc_restart_call() should return success/failure Both rpc_restart_call_prepare() and rpc_restart_call() test for the RPC_TASK_KILLED flag, and fail to restart the RPC call if that flag is set. This patch allows callers to know whether or not the restart was successful, so that they can perform cleanups etc in case of failure. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/clnt.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 8ed9642a5a76..debe75532199 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -148,8 +148,8 @@ int rpc_call_sync(struct rpc_clnt *clnt, const struct rpc_message *msg, int flags); struct rpc_task *rpc_call_null(struct rpc_clnt *clnt, struct rpc_cred *cred, int flags); -void rpc_restart_call_prepare(struct rpc_task *); -void rpc_restart_call(struct rpc_task *); +int rpc_restart_call_prepare(struct rpc_task *); +int rpc_restart_call(struct rpc_task *); void rpc_setbufsize(struct rpc_clnt *, unsigned int, unsigned int); size_t rpc_max_payload(struct rpc_clnt *); void rpc_force_rebind(struct rpc_clnt *); -- cgit v1.2.3 From 173bdd746b128241d3d6d202142820692e7dd530 Mon Sep 17 00:00:00 2001 From: Shubhrajyoti D Date: Tue, 3 Aug 2010 19:44:40 -0700 Subject: Input: gpio_keys - add hooks to enable/disable device Allow platform code to specify callbcks that will be invoked when input device is opened or closed, allowing, for example, to enable the device. Signed-off-by: Shubhrajyoti D Signed-off-by: Dmitry Torokhov --- include/linux/gpio_keys.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio_keys.h b/include/linux/gpio_keys.h index cd0b3f30f48e..ce73a30113b4 100644 --- a/include/linux/gpio_keys.h +++ b/include/linux/gpio_keys.h @@ -17,6 +17,8 @@ struct gpio_keys_platform_data { struct gpio_keys_button *buttons; int nbuttons; unsigned int rep:1; /* enable input subsystem auto repeat */ + int (*enable)(struct device *dev); + void (*disable)(struct device *dev); }; #endif -- cgit v1.2.3 From b5272b509a8570bb559156001e74ee162c5cb96a Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Wed, 21 Jul 2010 10:13:06 +0000 Subject: sh: add a list of parent configurations to struct clk Many system clocks can select a parent by writing a value to a specific field in the configuration register. Add a list of parents and location and width of the source selection field in the clock configuration register to struct clk to assist in clk_set_parent() implementation. Signed-off-by: Guennadi Liakhovetski Acked-by: Magnus Damm Signed-off-by: Paul Mundt --- include/linux/sh_clk.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sh_clk.h b/include/linux/sh_clk.h index 1636d1e2a5f1..08a07b9a894f 100644 --- a/include/linux/sh_clk.h +++ b/include/linux/sh_clk.h @@ -25,6 +25,10 @@ struct clk { int id; struct clk *parent; + struct clk **parent_table; /* list of parents to */ + unsigned short parent_num; /* choose between */ + unsigned char src_shift; /* source clock field in the */ + unsigned char src_width; /* configuration register */ struct clk_ops *ops; struct list_head children; -- cgit v1.2.3 From b3dd51a8a6ce2e618e8a1be8fa0e7d3d4733c300 Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Wed, 21 Jul 2010 10:13:10 +0000 Subject: sh: add a reparent function to DIV6 clocks Add support for reparenting of div6 clocks on SuperH and SH-Mobile SoCs. Signed-off-by: Guennadi Liakhovetski Acked-by: Magnus Damm Signed-off-by: Paul Mundt --- include/linux/sh_clk.h | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sh_clk.h b/include/linux/sh_clk.h index 08a07b9a894f..875ce50719a9 100644 --- a/include/linux/sh_clk.h +++ b/include/linux/sh_clk.h @@ -142,13 +142,22 @@ int sh_clk_div4_enable_register(struct clk *clks, int nr, int sh_clk_div4_reparent_register(struct clk *clks, int nr, struct clk_div4_table *table); -#define SH_CLK_DIV6(_parent, _reg, _flags) \ -{ \ - .parent = _parent, \ - .enable_reg = (void __iomem *)_reg, \ - .flags = _flags, \ +#define SH_CLK_DIV6_EXT(_parent, _reg, _flags, _parents, \ + _num_parents, _src_shift, _src_width) \ +{ \ + .parent = _parent, \ + .enable_reg = (void __iomem *)_reg, \ + .flags = _flags, \ + .parent_table = _parents, \ + .parent_num = _num_parents, \ + .src_shift = _src_shift, \ + .src_width = _src_width, \ } +#define SH_CLK_DIV6(_parent, _reg, _flags) \ + SH_CLK_DIV6_EXT(_parent, _reg, _flags, NULL, 0, 0, 0) + int sh_clk_div6_register(struct clk *clks, int nr); +int sh_clk_div6_reparent_register(struct clk *clks, int nr); #endif /* __SH_CLOCK_H */ -- cgit v1.2.3 From e1b004c3ef9c59db5f013528628b51c8653155ec Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 4 Aug 2010 10:53:00 +0200 Subject: Revert "timer: Added usleep[_range] timer" This reverts commit 22b8f15c2f7130bb0386f548428df2ffd4e81903 to merge an advanced version. Signed-off-by: Thomas Gleixner --- include/linux/delay.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/delay.h b/include/linux/delay.h index 0e303d1aacd8..fd832c6d419e 100644 --- a/include/linux/delay.h +++ b/include/linux/delay.h @@ -45,12 +45,6 @@ extern unsigned long lpj_fine; void calibrate_delay(void); void msleep(unsigned int msecs); unsigned long msleep_interruptible(unsigned int msecs); -void usleep_range(unsigned long min, unsigned long max); - -static inline void usleep(unsigned long usecs) -{ - usleep_range(usecs, usecs); -} static inline void ssleep(unsigned int seconds) { -- cgit v1.2.3 From 5e7f5a178bba45c5aca3448fddecabd4e28f1f6b Mon Sep 17 00:00:00 2001 From: Patrick Pannuto Date: Mon, 2 Aug 2010 15:01:04 -0700 Subject: timer: Added usleep_range timer usleep_range is a finer precision implementations of msleep and is designed to be a drop-in replacement for udelay where a precise sleep / busy-wait is unnecessary. Since an easy interface to hrtimers could lead to an undesired proliferation of interrupts, we provide only a "range" API, forcing the caller to think about an acceptable tolerance on both ends and hopefully avoiding introducing another interrupt. INTRO As discussed here ( http://lkml.org/lkml/2007/8/3/250 ), msleep(1) is not precise enough for many drivers (yes, sleep precision is an unfair notion, but consistently sleeping for ~an order of magnitude greater than requested is worth fixing). This patch adds a usleep API so that udelay does not have to be used. Obviously not every udelay can be replaced (those in atomic contexts or being used for simple bitbanging come to mind), but there are many, many examples of mydriver_write(...) /* Wait for hardware to latch */ udelay(100) in various drivers where a busy-wait loop is neither beneficial nor necessary, but msleep simply does not provide enough precision and people are using a busy-wait loop instead. CONCERNS FROM THE RFC Why is udelay a problem / necessary? Most callers of udelay are in device/ driver initialization code, which is serial... As I see it, there is only benefit to sleeping over a delay; the notion of "refactoring" areas that use udelay was presented, but I see usleep as the refactoring. Consider i2c, if the bus is busy, you need to wait a bit (say 100us) before trying again, your current options are: * udelay(100) * msleep(1) <-- As noted above, actually as high as ~20ms on some platforms, so not really an option * Manually set up an hrtimer to try again in 100us (which is what usleep does anyway...) People choose the udelay route because it is EASY; we need to provide a better easy route. Device / driver / boot code is *currently* serial, but every few months someone makes noise about parallelizing boot, and IMHO, a little forward-thinking now is one less thing to worry about if/when that ever happens udelay's could be preempted Sure, but if udelay plans on looping 1000 times, and it gets preempted on loop 200, whenever it's scheduled again, it is going to do the next 800 loops. Is the interruptible case needed? Probably not, but I see usleep as a very logical parallel to msleep, so it made sense to include the "full" API. Processors are getting faster (albeit not as quickly as they are becoming more parallel), so if someone wanted to be interruptible for a few usecs, why not let them? If this is a contentious point, I'm happy to remove it. OTHER THOUGHTS I believe there is also value in exposing the usleep_range option; it gives the scheduler a lot more flexibility and allows the programmer to express his intent much more clearly; it's something I would hope future driver writers will take advantage of. To get the results in the NUMBERS section below, I literally s/udelay/usleep the kernel tree; I had to go in and undo the changes to the USB drivers, but everything else booted successfully; I find that extremely telling in and of itself -- many people are using a delay API where a sleep will suit them just fine. SOME ATTEMPTS AT NUMBERS It turns out that calculating quantifiable benefit on this is challenging, so instead I will simply present the current state of things, and I hope this to be sufficient: How many udelay calls are there in 2.6.35-rc5? udealy(ARG) >= | COUNT 1000 | 319 500 | 414 100 | 1146 20 | 1832 I am working on Android, so that is my focus for this. The following table is a modified usleep that simply printk's the amount of time requested to sleep; these tests were run on a kernel with udelay >= 20 --> usleep "boot" is power-on to lock screen "power collapse" is when the power button is pushed and the device suspends "resume" is when the power button is pushed and the lock screen is displayed (no touchscreen events or anything, just turning on the display) "use device" is from the unlock swipe to clicking around a bit; there is no sd card in this phone, so fail loading music, video, camera ACTION | TOTAL NUMBER OF USLEEP CALLS | NET TIME (us) boot | 22 | 1250 power-collapse | 9 | 1200 resume | 5 | 500 use device | 59 | 7700 The most interesting category to me is the "use device" field; 7700us of busy-wait time that could be put towards better responsiveness, or at the least less power usage. Signed-off-by: Patrick Pannuto Cc: apw@canonical.com Cc: corbet@lwn.net Cc: arjan@linux.intel.com Cc: Randy Dunlap Cc: Andrew Morton Signed-off-by: Thomas Gleixner --- include/linux/delay.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/delay.h b/include/linux/delay.h index fd832c6d419e..a6ecb34cf547 100644 --- a/include/linux/delay.h +++ b/include/linux/delay.h @@ -45,6 +45,7 @@ extern unsigned long lpj_fine; void calibrate_delay(void); void msleep(unsigned int msecs); unsigned long msleep_interruptible(unsigned int msecs); +void usleep_range(unsigned long min, unsigned long max); static inline void ssleep(unsigned int seconds) { -- cgit v1.2.3 From ad0d363b8fb7559a410483635349e22de6727988 Mon Sep 17 00:00:00 2001 From: Kyungmin Park Date: Fri, 28 May 2010 11:03:11 +0900 Subject: mtd: OneNAND: Introduce chip_probe function Samsung SoCs use the own OneNAND controler and detect OneNAND chip at power on. To use this feature, introduce the chip_probe function. Also remove workaround for Samsung SoCs. Signed-off-by: Kyungmin Park Signed-off-by: David Woodhouse --- include/linux/mtd/onenand.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/onenand.h b/include/linux/mtd/onenand.h index c26ff86ad08a..0c8815bfae1c 100644 --- a/include/linux/mtd/onenand.h +++ b/include/linux/mtd/onenand.h @@ -68,6 +68,7 @@ struct onenand_bufferram { * @write_word: [REPLACEABLE] hardware specific function for write * register of OneNAND * @mmcontrol: sync burst read function + * @chip_probe: [REPLACEABLE] hardware specific function for chip probe * @block_markbad: function to mark a block as bad * @scan_bbt: [REPLACEALBE] hardware specific function for scanning * Bad block Table @@ -114,6 +115,7 @@ struct onenand_chip { unsigned short (*read_word)(void __iomem *addr); void (*write_word)(unsigned short value, void __iomem *addr); void (*mmcontrol)(struct mtd_info *mtd, int sync_read); + int (*chip_probe)(struct mtd_info *mtd); int (*block_markbad)(struct mtd_info *mtd, loff_t ofs); int (*scan_bbt)(struct mtd_info *mtd); -- cgit v1.2.3 From 5d8d9a4d9ff74c55901642b4e2ac5124830ddafe Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 31 Jul 2010 14:29:07 -0400 Subject: NFS: Ensure the AUTH_UNIX credcache is allocated dynamically Signed-off-by: Trond Myklebust --- include/linux/sunrpc/auth.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index 87d7ec0bf779..784e78c73ec5 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -125,11 +125,12 @@ struct rpc_credops { extern const struct rpc_authops authunix_ops; extern const struct rpc_authops authnull_ops; -void __init rpc_init_authunix(void); -void __init rpc_init_generic_auth(void); -void __init rpcauth_init_module(void); +int __init rpc_init_authunix(void); +int __init rpc_init_generic_auth(void); +int __init rpcauth_init_module(void); void __exit rpcauth_remove_module(void); void __exit rpc_destroy_generic_auth(void); +void rpc_destroy_authunix(void); struct rpc_cred * rpc_lookup_cred(void); struct rpc_cred * rpc_lookup_machine_cred(void); -- cgit v1.2.3 From 988664a0f6bbfc356e6ce55f7a87b8594050012f Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 31 Jul 2010 14:29:07 -0400 Subject: SUNRPC: Store the hashtable size in struct rpc_cred_cache Cleanup in preparation for allowing the user to determine the maximum hash table size. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/auth.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index 784e78c73ec5..84d64b6926a9 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -65,6 +65,7 @@ struct rpc_cred { #define RPC_CREDCACHE_NR (1 << RPC_CREDCACHE_HASHBITS) struct rpc_cred_cache { struct hlist_head hashtable[RPC_CREDCACHE_NR]; + unsigned int hashbits; spinlock_t lock; }; -- cgit v1.2.3 From 241269bd0b580faae71575443d9ab38df7469126 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 31 Jul 2010 14:29:08 -0400 Subject: SUNRPC: Make the credential cache hashtable size configurable This patch allows the user to configure the credential cache hashtable size using a new module parameter: auth_hashtable_size When set, this parameter will be rounded up to the nearest power of two, with a maximum allowed value of 1024 elements. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/auth.h | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index 84d64b6926a9..d2737625a247 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -61,14 +61,7 @@ struct rpc_cred { /* * Client authentication handle */ -#define RPC_CREDCACHE_HASHBITS 4 -#define RPC_CREDCACHE_NR (1 << RPC_CREDCACHE_HASHBITS) -struct rpc_cred_cache { - struct hlist_head hashtable[RPC_CREDCACHE_NR]; - unsigned int hashbits; - spinlock_t lock; -}; - +struct rpc_cred_cache; struct rpc_authops; struct rpc_auth { unsigned int au_cslack; /* call cred size estimate */ -- cgit v1.2.3 From d9b6cd94601e1d17273f93a326a135fbf487a918 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 31 Jul 2010 14:29:08 -0400 Subject: SUNRPC: Ensure that rpc_exit() always wakes up a sleeping task Make rpc_exit() non-inline, and ensure that it always wakes up a task that has been queued. Kill off the now unused rpc_wake_up_task(). Signed-off-by: Trond Myklebust --- include/linux/sunrpc/sched.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 7be4f3a6d246..88513fd8e208 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -213,6 +213,7 @@ struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req, const struct rpc_call_ops *ops); void rpc_put_task(struct rpc_task *); void rpc_exit_task(struct rpc_task *); +void rpc_exit(struct rpc_task *, int); void rpc_release_calldata(const struct rpc_call_ops *, void *); void rpc_killall_tasks(struct rpc_clnt *); void rpc_execute(struct rpc_task *); @@ -241,12 +242,6 @@ void rpc_destroy_mempool(void); extern struct workqueue_struct *rpciod_workqueue; void rpc_prepare_task(struct rpc_task *task); -static inline void rpc_exit(struct rpc_task *task, int status) -{ - task->tk_status = status; - task->tk_action = rpc_exit_task; -} - static inline int rpc_wait_for_completion_task(struct rpc_task *task) { return __rpc_wait_for_completion_task(task, NULL); -- cgit v1.2.3 From 58f9612c6ea858f532021a0ce42ec53cb0a493b3 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 31 Jul 2010 14:29:08 -0400 Subject: SUNRPC: Move remaining RPC client related task initialisation into clnt.c Now that rpc_run_task() is the sole entry point for RPC calls, we can move the remaining rpc_client-related initialisation of struct rpc_task from sched.c into clnt.c. Also move rpc_killall_tasks() into the same file, since that too is relative to the rpc_clnt. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/clnt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index debe75532199..569dc722a600 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -131,6 +131,7 @@ struct rpc_clnt *rpc_bind_new_program(struct rpc_clnt *, struct rpc_clnt *rpc_clone_client(struct rpc_clnt *); void rpc_shutdown_client(struct rpc_clnt *); void rpc_release_client(struct rpc_clnt *); +void rpc_task_release_client(struct rpc_task *); int rpcb_register(u32, u32, int, unsigned short); int rpcb_v4_register(const u32 program, const u32 version, -- cgit v1.2.3 From 8572b8e2e3c5f3d990122348c4d2c64dad338611 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 31 Jul 2010 14:29:08 -0400 Subject: SUNRPC: Clean up of rpc_bindcred() Signed-off-by: Trond Myklebust --- include/linux/sunrpc/auth.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index d2737625a247..90e4c3827ac0 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -106,7 +106,7 @@ struct rpc_credops { void (*crdestroy)(struct rpc_cred *); int (*crmatch)(struct auth_cred *, struct rpc_cred *, int); - void (*crbind)(struct rpc_task *, struct rpc_cred *, int); + struct rpc_cred * (*crbind)(struct rpc_task *, struct rpc_cred *, int); __be32 * (*crmarshal)(struct rpc_task *, __be32 *); int (*crrefresh)(struct rpc_task *); __be32 * (*crvalidate)(struct rpc_task *, __be32 *); @@ -135,8 +135,8 @@ void rpcauth_release(struct rpc_auth *); struct rpc_cred * rpcauth_lookup_credcache(struct rpc_auth *, struct auth_cred *, int); void rpcauth_init_cred(struct rpc_cred *, const struct auth_cred *, struct rpc_auth *, const struct rpc_credops *); struct rpc_cred * rpcauth_lookupcred(struct rpc_auth *, int); -void rpcauth_bindcred(struct rpc_task *, struct rpc_cred *, int); -void rpcauth_generic_bind_cred(struct rpc_task *, struct rpc_cred *, int); +int rpcauth_bindcred(struct rpc_task *, struct rpc_cred *, int); +struct rpc_cred * rpcauth_generic_bind_cred(struct rpc_task *, struct rpc_cred *, int); void put_rpccred(struct rpc_cred *); void rpcauth_unbindcred(struct rpc_task *); __be32 * rpcauth_marshcred(struct rpc_task *, __be32 *); -- cgit v1.2.3 From a17c2153d2e271b0cbacae9bed83b0eaa41db7e1 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 31 Jul 2010 14:29:08 -0400 Subject: SUNRPC: Move the bound cred to struct rpc_rqst This will allow us to save the original generic cred in rpc_message, so that if we migrate from one server to another, we can generate a new bound cred without having to punt back to the NFS layer. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/auth.h | 2 -- include/linux/sunrpc/xprt.h | 1 + 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index 90e4c3827ac0..5bbc447175dc 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -135,10 +135,8 @@ void rpcauth_release(struct rpc_auth *); struct rpc_cred * rpcauth_lookup_credcache(struct rpc_auth *, struct auth_cred *, int); void rpcauth_init_cred(struct rpc_cred *, const struct auth_cred *, struct rpc_auth *, const struct rpc_credops *); struct rpc_cred * rpcauth_lookupcred(struct rpc_auth *, int); -int rpcauth_bindcred(struct rpc_task *, struct rpc_cred *, int); struct rpc_cred * rpcauth_generic_bind_cred(struct rpc_task *, struct rpc_cred *, int); void put_rpccred(struct rpc_cred *); -void rpcauth_unbindcred(struct rpc_task *); __be32 * rpcauth_marshcred(struct rpc_task *, __be32 *); __be32 * rpcauth_checkverf(struct rpc_task *, __be32 *); int rpcauth_wrap_req(struct rpc_task *task, kxdrproc_t encode, void *rqstp, __be32 *data, void *obj); diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index b51470302399..ff5a77b28c50 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -64,6 +64,7 @@ struct rpc_rqst { * This is the private part */ struct rpc_task * rq_task; /* RPC task data */ + struct rpc_cred * rq_cred; /* Bound cred */ __be32 rq_xid; /* request XID */ int rq_cong; /* has incremented xprt->cong */ u32 rq_seqno; /* gss seq no. used on req. */ -- cgit v1.2.3 From e3b5e0d552b34d65e15b20610273b200555eea53 Mon Sep 17 00:00:00 2001 From: Ilya Yanok Date: Thu, 8 Jul 2010 10:10:38 +0000 Subject: powerpc/fsl_pci: add quirk for mpc8308 pcie bridge This patch adds the quirk for PCIE controller found on Freescale MPC8308. The quirk is the same as for other MPC83xx processors. Signed-off-by: Ilya Yanok Signed-off-by: Kumar Gala --- include/linux/pci_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 3bedcc149c84..79bb11f35c4b 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2264,6 +2264,7 @@ #define PCI_DEVICE_ID_TDI_EHCI 0x0101 #define PCI_VENDOR_ID_FREESCALE 0x1957 +#define PCI_DEVICE_ID_MPC8308 0xc006 #define PCI_DEVICE_ID_MPC8315E 0x00b4 #define PCI_DEVICE_ID_MPC8315 0x00b5 #define PCI_DEVICE_ID_MPC8314E 0x00b6 -- cgit v1.2.3 From 0c42bd0e425e9c8ddb7019fc446f7d915e36c5f6 Mon Sep 17 00:00:00 2001 From: Yong Wang Date: Fri, 30 Jul 2010 16:23:03 +0800 Subject: dmaengine: Driver for Topcliff PCH DMA controller Topcliff PCH is the platform controller hub that is going to be used in Intel's upcoming general embedded platforms. This adds the driver for Topcliff PCH DMA controller. The DMA channels are strictly for device to host or host to device transfers and cannot be used for generic memcpy. Signed-off-by: Yong Wang [kill GFP_ATOMIC, kill __raw_{read|write}l, locking fixlet] Signed-off-by: Dan Williams --- include/linux/pch_dma.h | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) create mode 100644 include/linux/pch_dma.h (limited to 'include/linux') diff --git a/include/linux/pch_dma.h b/include/linux/pch_dma.h new file mode 100644 index 000000000000..fdafe529ef8a --- /dev/null +++ b/include/linux/pch_dma.h @@ -0,0 +1,37 @@ +/* + * Copyright (c) 2010 Intel Corporation + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + */ + +#ifndef PCH_DMA_H +#define PCH_DMA_H + +#include + +enum pch_dma_width { + PCH_DMA_WIDTH_1_BYTE, + PCH_DMA_WIDTH_2_BYTES, + PCH_DMA_WIDTH_4_BYTES, +}; + +struct pch_dma_slave { + struct device *dma_dev; + unsigned int chan_id; + dma_addr_t tx_reg; + dma_addr_t rx_reg; + enum pch_dma_width width; +}; + +#endif -- cgit v1.2.3 From c156d0a5b0c667999e06d0bb52e3d1376faec8bf Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 4 Aug 2010 13:37:33 +0200 Subject: DMAENGINE: generic slave channel control v3 This adds an interface to the DMAengine to make it possible to reconfigure a slave channel at runtime. We add a few foreseen config parameters to the passed struct, with a void * pointer for custom per-device or per-platform runtime slave data. Signed-off-by: Linus Walleij Signed-off-by: Dan Williams --- include/linux/dmaengine.h | 71 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 71 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 5204f018931b..c61d4ca27bcc 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -114,11 +114,17 @@ enum dma_ctrl_flags { * @DMA_TERMINATE_ALL: terminate all ongoing transfers * @DMA_PAUSE: pause ongoing transfers * @DMA_RESUME: resume paused transfer + * @DMA_SLAVE_CONFIG: this command is only implemented by DMA controllers + * that need to runtime reconfigure the slave channels (as opposed to passing + * configuration data in statically from the platform). An additional + * argument of struct dma_slave_config must be passed in with this + * command. */ enum dma_ctrl_cmd { DMA_TERMINATE_ALL, DMA_PAUSE, DMA_RESUME, + DMA_SLAVE_CONFIG, }; /** @@ -199,6 +205,71 @@ struct dma_chan_dev { atomic_t *idr_ref; }; +/** + * enum dma_slave_buswidth - defines bus with of the DMA slave + * device, source or target buses + */ +enum dma_slave_buswidth { + DMA_SLAVE_BUSWIDTH_UNDEFINED = 0, + DMA_SLAVE_BUSWIDTH_1_BYTE = 1, + DMA_SLAVE_BUSWIDTH_2_BYTES = 2, + DMA_SLAVE_BUSWIDTH_4_BYTES = 4, + DMA_SLAVE_BUSWIDTH_8_BYTES = 8, +}; + +/** + * struct dma_slave_config - dma slave channel runtime config + * @direction: whether the data shall go in or out on this slave + * channel, right now. DMA_TO_DEVICE and DMA_FROM_DEVICE are + * legal values, DMA_BIDIRECTIONAL is not acceptable since we + * need to differentiate source and target addresses. + * @src_addr: this is the physical address where DMA slave data + * should be read (RX), if the source is memory this argument is + * ignored. + * @dst_addr: this is the physical address where DMA slave data + * should be written (TX), if the source is memory this argument + * is ignored. + * @src_addr_width: this is the width in bytes of the source (RX) + * register where DMA data shall be read. If the source + * is memory this may be ignored depending on architecture. + * Legal values: 1, 2, 4, 8. + * @dst_addr_width: same as src_addr_width but for destination + * target (TX) mutatis mutandis. + * @src_maxburst: the maximum number of words (note: words, as in + * units of the src_addr_width member, not bytes) that can be sent + * in one burst to the device. Typically something like half the + * FIFO depth on I/O peripherals so you don't overflow it. This + * may or may not be applicable on memory sources. + * @dst_maxburst: same as src_maxburst but for destination target + * mutatis mutandis. + * + * This struct is passed in as configuration data to a DMA engine + * in order to set up a certain channel for DMA transport at runtime. + * The DMA device/engine has to provide support for an additional + * command in the channel config interface, DMA_SLAVE_CONFIG + * and this struct will then be passed in as an argument to the + * DMA engine device_control() function. + * + * The rationale for adding configuration information to this struct + * is as follows: if it is likely that most DMA slave controllers in + * the world will support the configuration option, then make it + * generic. If not: if it is fixed so that it be sent in static from + * the platform data, then prefer to do that. Else, if it is neither + * fixed at runtime, nor generic enough (such as bus mastership on + * some CPU family and whatnot) then create a custom slave config + * struct and pass that, then make this config a member of that + * struct, if applicable. + */ +struct dma_slave_config { + enum dma_data_direction direction; + dma_addr_t src_addr; + dma_addr_t dst_addr; + enum dma_slave_buswidth src_addr_width; + enum dma_slave_buswidth dst_addr_width; + u32 src_maxburst; + u32 dst_maxburst; +}; + static inline const char *dma_chan_name(struct dma_chan *chan) { return dev_name(&chan->dev->device); -- cgit v1.2.3 From fca3ec01e0b40cab82cac7745e154b01969e6219 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Wed, 4 Aug 2010 14:34:24 +0100 Subject: drm,io-mapping: Specify slot to use for atomic mappings This is required should we ever attempt to use an io-mapping where KM_USER0 is verboten, such as inside an IRQ context. Signed-off-by: Chris Wilson Cc: Eric Anholt Signed-off-by: Dave Airlie --- include/linux/io-mapping.h | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h index 25085ddd955f..e0ea40f6c515 100644 --- a/include/linux/io-mapping.h +++ b/include/linux/io-mapping.h @@ -79,7 +79,9 @@ io_mapping_free(struct io_mapping *mapping) /* Atomic map/unmap */ static inline void * -io_mapping_map_atomic_wc(struct io_mapping *mapping, unsigned long offset) +io_mapping_map_atomic_wc(struct io_mapping *mapping, + unsigned long offset, + int slot) { resource_size_t phys_addr; unsigned long pfn; @@ -87,13 +89,13 @@ io_mapping_map_atomic_wc(struct io_mapping *mapping, unsigned long offset) BUG_ON(offset >= mapping->size); phys_addr = mapping->base + offset; pfn = (unsigned long) (phys_addr >> PAGE_SHIFT); - return iomap_atomic_prot_pfn(pfn, KM_USER0, mapping->prot); + return iomap_atomic_prot_pfn(pfn, slot, mapping->prot); } static inline void -io_mapping_unmap_atomic(void *vaddr) +io_mapping_unmap_atomic(void *vaddr, int slot) { - iounmap_atomic(vaddr, KM_USER0); + iounmap_atomic(vaddr, slot); } static inline void * @@ -133,13 +135,15 @@ io_mapping_free(struct io_mapping *mapping) /* Atomic map/unmap */ static inline void * -io_mapping_map_atomic_wc(struct io_mapping *mapping, unsigned long offset) +io_mapping_map_atomic_wc(struct io_mapping *mapping, + unsigned long offset, + int slot) { return ((char *) mapping) + offset; } static inline void -io_mapping_unmap_atomic(void *vaddr) +io_mapping_unmap_atomic(void *vaddr, int slot) { } -- cgit v1.2.3 From 5aa9a2cbc037b2ec34b76619d233852d2d17b502 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Fri, 4 Jun 2010 03:07:34 +0200 Subject: [ARM] wm97xx_batt: remove now useless header file Signed-off-by: Marek Vasut Acked-by: Mark Brown Signed-off-by: Eric Miao --- include/linux/wm97xx_batt.h | 16 ---------------- 1 file changed, 16 deletions(-) delete mode 100644 include/linux/wm97xx_batt.h (limited to 'include/linux') diff --git a/include/linux/wm97xx_batt.h b/include/linux/wm97xx_batt.h deleted file mode 100644 index a1d6419c2ff8..000000000000 --- a/include/linux/wm97xx_batt.h +++ /dev/null @@ -1,16 +0,0 @@ -#ifndef _LINUX_WM97XX_BAT_H -#define _LINUX_WM97XX_BAT_H - -#include - -#warning This file will be removed soon, use wm97xx.h instead! - -#define wm97xx_batt_info wm97xx_batt_pdata - -#ifdef CONFIG_BATTERY_WM97XX -void wm97xx_bat_set_pdata(struct wm97xx_batt_info *data); -#else -static inline void wm97xx_bat_set_pdata(struct wm97xx_batt_info *data) {} -#endif - -#endif -- cgit v1.2.3 From f6a21388bd255773cc80d4423afb4c69d4daa173 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Sat, 19 Jun 2010 04:08:29 +0000 Subject: POWER: Add JZ4740 battery driver. Add support for the battery voltage measurement part of the JZ4740 ADC unit. Signed-off-by: Lars-Peter Clausen Acked-by: Anton Vorontsov Cc: linux-mips@linux-mips.org Cc: linux-kernel@vger.kernel.org Patchwork: https://patchwork.linux-mips.org/patch/1416/ Signed-off-by: Ralf Baechle --- include/linux/power/jz4740-battery.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) create mode 100644 include/linux/power/jz4740-battery.h (limited to 'include/linux') diff --git a/include/linux/power/jz4740-battery.h b/include/linux/power/jz4740-battery.h new file mode 100644 index 000000000000..19c9610c720a --- /dev/null +++ b/include/linux/power/jz4740-battery.h @@ -0,0 +1,24 @@ +/* + * Copyright (C) 2009, Jiejing Zhang + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 675 Mass Ave, Cambridge, MA 02139, USA. + * + */ + +#ifndef __JZ4740_BATTERY_H +#define __JZ4740_BATTERY_H + +struct jz_battery_platform_data { + struct power_supply_info info; + int gpio_charge; /* GPIO port of Charger state */ + int gpio_charge_active_low; +}; + +#endif -- cgit v1.2.3 From 534af1082329392bc29f6badf815e69ae2ae0f4c Mon Sep 17 00:00:00 2001 From: Jason Wessel Date: Thu, 5 Aug 2010 09:22:20 -0500 Subject: kgdb,kdb: individual register set and and get API The kdb shell specification includes the ability to get and set architecture specific registers by name. For the time being individual register get and set will be implemented on a per architecture basis. If an architecture defines DBG_MAX_REG_NUM > 0 then kdb and the gdbstub will use the capability for individually getting and setting architecture specific registers. Signed-off-by: Jason Wessel --- include/linux/kgdb.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index 9340f34d1bb5..d5eb882e01f3 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -90,6 +90,19 @@ struct kgdb_bkpt { enum kgdb_bpstate state; }; +struct dbg_reg_def_t { + char *name; + int size; + int offset; +}; + +#ifndef DBG_MAX_REG_NUM +#define DBG_MAX_REG_NUM 0 +#else +extern struct dbg_reg_def_t dbg_reg_def[]; +extern char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs); +extern int dbg_set_reg(int regno, void *mem, struct pt_regs *regs); +#endif #ifndef KGDB_MAX_BREAKPOINTS # define KGDB_MAX_BREAKPOINTS 1000 #endif -- cgit v1.2.3 From 55751145dc1e08e16df418cdd101661f5c6ac991 Mon Sep 17 00:00:00 2001 From: Jason Wessel Date: Thu, 5 Aug 2010 09:22:21 -0500 Subject: gdbstub: Implement gdbserial 'p' and 'P' packets The gdbserial 'p' and 'P' packets allow gdb to individually get and set registers instead of querying for all the available registers. Signed-off-by: Jason Wessel --- include/linux/kgdb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index d5eb882e01f3..cc96f0f23e04 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -294,7 +294,7 @@ extern void kgdb_unregister_io_module(struct kgdb_io *local_kgdb_io_ops); extern struct kgdb_io *dbg_io_ops; extern int kgdb_hex2long(char **ptr, unsigned long *long_val); -extern int kgdb_mem2hex(char *mem, char *buf, int count); +extern char *kgdb_mem2hex(char *mem, char *buf, int count); extern int kgdb_hex2mem(char *buf, char *mem, int count); extern int kgdb_isremovedbreak(unsigned long addr); -- cgit v1.2.3 From b45cfba4e9005d64d419718e7ff7f7cab44c1994 Mon Sep 17 00:00:00 2001 From: Jesse Barnes Date: Thu, 5 Aug 2010 09:22:30 -0500 Subject: vt,console,kdb: implement atomic console enter/leave functions These functions allow the kernel debugger to save and restore the state of the system console. Signed-off-by: Jesse Barnes Signed-off-by: Jason Wessel CC: David Airlie CC: Andrew Morton --- include/linux/console.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/console.h b/include/linux/console.h index dcca5339ceb3..f76fc297322d 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -55,6 +55,16 @@ struct consw { void (*con_invert_region)(struct vc_data *, u16 *, int); u16 *(*con_screen_pos)(struct vc_data *, int); unsigned long (*con_getxy)(struct vc_data *, unsigned long, int *, int *); + /* + * Prepare the console for the debugger. This includes, but is not + * limited to, unblanking the console, loading an appropriate + * palette, and allowing debugger generated output. + */ + int (*con_debug_enter)(struct vc_data *); + /* + * Restore the console to its pre-debug state as closely as possible. + */ + int (*con_debug_leave)(struct vc_data *); }; extern const struct consw *conswitchp; @@ -69,6 +79,9 @@ int register_con_driver(const struct consw *csw, int first, int last); int unregister_con_driver(const struct consw *csw); int take_over_console(const struct consw *sw, int first, int last, int deflt); void give_up_console(const struct consw *sw); +int con_debug_enter(struct vc_data *vc); +int con_debug_leave(void); + /* scroll */ #define SM_UP (1) #define SM_DOWN (2) -- cgit v1.2.3 From 81d4450732c68aa728f2c86c0c2993c6cfc3d032 Mon Sep 17 00:00:00 2001 From: Jason Wessel Date: Thu, 5 Aug 2010 09:22:30 -0500 Subject: vt,console,kdb: automatically set kdb LINES variable The kernel console interface stores the number of lines it is configured to use. The kdb debugger can greatly benefit by knowing how many lines there are on the console for the pager functionality without having the end user compile in the setting or have to repeatedly change it at run time. Signed-off-by: Jason Wessel Signed-off-by: Jesse Barnes CC: David Airlie CC: Andrew Morton --- include/linux/kdb.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kdb.h b/include/linux/kdb.h index ccb2b3ec0fe8..ea6e5244ed3f 100644 --- a/include/linux/kdb.h +++ b/include/linux/kdb.h @@ -114,4 +114,8 @@ enum { KDB_INIT_EARLY, KDB_INIT_FULL, }; + +extern int kdbgetintenv(const char *, int *); +extern int kdb_set(int, const char **); + #endif /* !_KDB_H */ -- cgit v1.2.3 From d219adc1228a3887486b58a430e736b0831f192c Mon Sep 17 00:00:00 2001 From: Jesse Barnes Date: Mon, 2 Aug 2010 12:05:41 -0700 Subject: fb: add hooks to handle KDB enter/exit Add fb ops to handle enter/exit of the kernel debugger. If present, the fb core will register them with KGDB and they'll be called when the debugger is entered and exited. The new functions are responsible for switching to an appropriate debug framebuffer and restoring the interrupted state at exit time. Signed-off-by: Jesse Barnes Signed-off-by: Jason Wessel --- include/linux/fb.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index e7445df44d6c..0c5659c41b01 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -3,6 +3,9 @@ #include #include +#ifdef __KERNEL__ +#include +#endif /* __KERNEL__ */ /* Definitions of frame buffers */ @@ -607,6 +610,12 @@ struct fb_deferred_io { * LOCKING NOTE: those functions must _ALL_ be called with the console * semaphore held, this is the only suitable locking mechanism we have * in 2.6. Some may be called at interrupt time at this point though. + * + * The exception to this is the debug related hooks. Putting the fb + * into a debug state (e.g. flipping to the kernel console) and restoring + * it must be done in a lock-free manner, so low level drivers should + * keep track of the initial console (if applicable) and may need to + * perform direct, unlocked hardware writes in these hooks. */ struct fb_ops { @@ -676,6 +685,10 @@ struct fb_ops { /* teardown any resources to do with this framebuffer */ void (*fb_destroy)(struct fb_info *info); + + /* called at KDB enter and leave time to prepare the console */ + int (*fb_debug_enter)(struct fb_info *info); + int (*fb_debug_leave)(struct fb_info *info); }; #ifdef CONFIG_FB_TILEBLITTING -- cgit v1.2.3 From 1a4240f4764ac78adbf4b0ebb49b3bd8c72ffa11 Mon Sep 17 00:00:00 2001 From: Wang Lei Date: Wed, 4 Aug 2010 15:16:33 +0100 Subject: DNS: Separate out CIFS DNS Resolver code Separate out the DNS resolver key type from the CIFS filesystem into its own module so that it can be made available for general use, including the AFS filesystem module. This facility makes it possible for the kernel to upcall to userspace to have it issue DNS requests, package up the replies and present them to the kernel in a useful form. The kernel is then able to cache the DNS replies as keys can be retained in keyrings. Resolver keys are of type "dns_resolver" and have a case-insensitive description that is of the form "[:]". The optional indicates the particular DNS lookup and packaging that's required. The is the query to be made. If isn't given, a basic hostname to IP address lookup is made, and the result is stored in the key in the form of a printable string consisting of a comma-separated list of IPv4 and IPv6 addresses. This key type is supported by userspace helpers driven from /sbin/request-key and configured through /etc/request-key.conf. The cifs.upcall utility is invoked for UNC path server name to IP address resolution. The CIFS functionality is encapsulated by the dns_resolve_unc_to_ip() function, which is used to resolve a UNC path to an IP address for CIFS filesystem. This part remains in the CIFS module for now. See the added Documentation/networking/dns_resolver.txt for more information. Signed-off-by: Wang Lei Signed-off-by: David Howells Acked-by: Jeff Layton Signed-off-by: Steve French --- include/linux/dns_resolver.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) create mode 100644 include/linux/dns_resolver.h (limited to 'include/linux') diff --git a/include/linux/dns_resolver.h b/include/linux/dns_resolver.h new file mode 100644 index 000000000000..cc92268af89a --- /dev/null +++ b/include/linux/dns_resolver.h @@ -0,0 +1,34 @@ +/* + * DNS Resolver upcall management for CIFS DFS and AFS + * Handles host name to IP address resolution and DNS query for AFSDB RR. + * + * Copyright (c) International Business Machines Corp., 2008 + * Author(s): Steve French (sfrench@us.ibm.com) + * Wang Lei (wang840925@gmail.com) + * + * This library is free software; you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License as published + * by the Free Software Foundation; either version 2.1 of the License, or + * (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See + * the GNU Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public License + * along with this library; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#ifndef _LINUX_DNS_RESOLVER_H +#define _LINUX_DNS_RESOLVER_H + +#ifdef __KERNEL__ + +extern int dns_query(const char *type, const char *name, size_t namelen, + const char *options, char **_result, time_t *_expiry); + +#endif /* KERNEL */ + +#endif /* _LINUX_DNS_RESOLVER_H */ -- cgit v1.2.3 From cc7447a5fa92759b0856d6a83ba2539c6a94e67e Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Wed, 16 Jun 2010 11:44:18 +0200 Subject: Driver core: Drop __must_check from bus_for_each_drv() There is little rationale for marking bus_for_each_drv() __must_check. It is more of an iteration helper than a real function. You don't know in advance which callback it will be used on, so you have no clue how important it can be to check the returned value. In practice, this helper function can be used for best-effort tasks. As a matter of fact, bus_for_each_dev() is not marked __must_check. So remove it from bus_for_each_drv() as well. This is the same that was done back in October 2006 by Russell King for device_for_each_child(), for exactly the same reasons. Signed-off-by: Jean Delvare Cc: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 6a8276f683b6..ddffdf7da393 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -84,9 +84,8 @@ struct device *bus_find_device_by_name(struct bus_type *bus, struct device *start, const char *name); -int __must_check bus_for_each_drv(struct bus_type *bus, - struct device_driver *start, void *data, - int (*fn)(struct device_driver *, void *)); +int bus_for_each_drv(struct bus_type *bus, struct device_driver *start, + void *data, int (*fn)(struct device_driver *, void *)); void bus_sort_breadthfirst(struct bus_type *bus, int (*compare)(const struct device *a, -- cgit v1.2.3 From 44f28bdea09415d40b4d73a7668db5961362ec53 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 21 Jun 2010 16:11:44 +0200 Subject: Driver core: reduce duplicated code for platform_device creation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This makes the two similar functions platform_device_register_simple and platform_device_register_data one line inline functions using a new generic function platform_device_register_resndata. Signed-off-by: Uwe Kleine-König Signed-off-by: Greg Kroah-Hartman --- include/linux/platform_device.h | 62 ++++++++++++++++++++++++++++++++++++++--- 1 file changed, 58 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index 5417944d3687..d7ecad0093bb 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -43,10 +43,64 @@ extern struct resource *platform_get_resource_byname(struct platform_device *, u extern int platform_get_irq_byname(struct platform_device *, const char *); extern int platform_add_devices(struct platform_device **, int); -extern struct platform_device *platform_device_register_simple(const char *, int id, - const struct resource *, unsigned int); -extern struct platform_device *platform_device_register_data(struct device *, - const char *, int, const void *, size_t); +extern struct platform_device *platform_device_register_resndata( + struct device *parent, const char *name, int id, + const struct resource *res, unsigned int num, + const void *data, size_t size); + +/** + * platform_device_register_simple - add a platform-level device and its resources + * @name: base name of the device we're adding + * @id: instance id + * @res: set of resources that needs to be allocated for the device + * @num: number of resources + * + * This function creates a simple platform device that requires minimal + * resource and memory management. Canned release function freeing memory + * allocated for the device allows drivers using such devices to be + * unloaded without waiting for the last reference to the device to be + * dropped. + * + * This interface is primarily intended for use with legacy drivers which + * probe hardware directly. Because such drivers create sysfs device nodes + * themselves, rather than letting system infrastructure handle such device + * enumeration tasks, they don't fully conform to the Linux driver model. + * In particular, when such drivers are built as modules, they can't be + * "hotplugged". + * + * Returns &struct platform_device pointer on success, or ERR_PTR() on error. + */ +static inline struct platform_device *platform_device_register_simple( + const char *name, int id, + const struct resource *res, unsigned int num) +{ + return platform_device_register_resndata(NULL, name, id, + res, num, NULL, 0); +} + +/** + * platform_device_register_data - add a platform-level device with platform-specific data + * @parent: parent device for the device we're adding + * @name: base name of the device we're adding + * @id: instance id + * @data: platform specific data for this platform device + * @size: size of platform specific data + * + * This function creates a simple platform device that requires minimal + * resource and memory management. Canned release function freeing memory + * allocated for the device allows drivers using such devices to be + * unloaded without waiting for the last reference to the device to be + * dropped. + * + * Returns &struct platform_device pointer on success, or ERR_PTR() on error. + */ +static inline struct platform_device *platform_device_register_data( + struct device *parent, const char *name, int id, + const void *data, size_t size) +{ + return platform_device_register_resndata(parent, name, id, + NULL, 0, data, size); +} extern struct platform_device *platform_device_alloc(const char *name, int id); extern int platform_device_add_resources(struct platform_device *pdev, -- cgit v1.2.3 From 49c19400f60bbe362202d7e7b3e68cc66040d0fa Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Fri, 2 Jul 2010 16:54:05 +0200 Subject: sysfs: sysfs_chmod_file's attr can be const sysfs_chmod_file doesn't change the attribute it operates on, so this attribute can be marked const. Signed-off-by: Jean Delvare Signed-off-by: Greg Kroah-Hartman --- include/linux/sysfs.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index f2694eb4dd3d..8bf06b64487c 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -136,8 +136,8 @@ int __must_check sysfs_create_file(struct kobject *kobj, const struct attribute *attr); int __must_check sysfs_create_files(struct kobject *kobj, const struct attribute **attr); -int __must_check sysfs_chmod_file(struct kobject *kobj, struct attribute *attr, - mode_t mode); +int __must_check sysfs_chmod_file(struct kobject *kobj, + const struct attribute *attr, mode_t mode); void sysfs_remove_file(struct kobject *kobj, const struct attribute *attr); void sysfs_remove_files(struct kobject *kobj, const struct attribute **attr); @@ -225,7 +225,7 @@ static inline int sysfs_create_files(struct kobject *kobj, } static inline int sysfs_chmod_file(struct kobject *kobj, - struct attribute *attr, mode_t mode) + const struct attribute *attr, mode_t mode) { return 0; } -- cgit v1.2.3 From 45daef0fdcc44f6af86fdebc4fc7eb7c79375398 Mon Sep 17 00:00:00 2001 From: Magnus Damm Date: Fri, 23 Jul 2010 19:56:18 +0900 Subject: Driver core: Add BUS_NOTIFY_BIND_DRIVER Add BUS_NOTIFY_BIND_DRIVER as a bus notifier event. For driver binding/unbinding we with this in place have the following bus notifier events: - BUS_NOTIFY_BIND_DRIVER - before ->probe() - BUS_NOTIFY_BOUND_DRIVER - after ->probe() - BUS_NOTIFY_UNBIND_DRIVER - before ->remove() - BUS_NOTIFY_UNBOUND_DRIVER - after ->remove() The event BUS_NOTIFY_BIND_DRIVER allows bus code to be notified that ->probe() is about to be called. Useful for bus code that needs to setup hardware before the driver gets to run. With this in place platform drivers can be loaded and unloaded as modules and the new BIND event allows bus code to control for instance device clocks that must be enabled before the driver can be executed. Without this patch there is no way for the bus code to get notified that a modular driver is about to be probed. Signed-off-by: Magnus Damm Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index ddffdf7da393..0ca24e93304f 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -109,10 +109,12 @@ extern int bus_unregister_notifier(struct bus_type *bus, */ #define BUS_NOTIFY_ADD_DEVICE 0x00000001 /* device added */ #define BUS_NOTIFY_DEL_DEVICE 0x00000002 /* device removed */ -#define BUS_NOTIFY_BOUND_DRIVER 0x00000003 /* driver bound to device */ -#define BUS_NOTIFY_UNBIND_DRIVER 0x00000004 /* driver about to be +#define BUS_NOTIFY_BIND_DRIVER 0x00000003 /* driver about to be + bound */ +#define BUS_NOTIFY_BOUND_DRIVER 0x00000004 /* driver bound to device */ +#define BUS_NOTIFY_UNBIND_DRIVER 0x00000005 /* driver about to be unbound */ -#define BUS_NOTIFY_UNBOUND_DRIVER 0x00000005 /* driver is unbound +#define BUS_NOTIFY_UNBOUND_DRIVER 0x00000006 /* driver is unbound from the device */ extern struct kset *bus_get_kset(struct bus_type *bus); -- cgit v1.2.3 From 6fd69dc578fa0b1bbc3aad70ae3af9a137211707 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Wed, 28 Jul 2010 22:09:26 -0700 Subject: sysfs: Remove owner field from sysfs struct attribute Signed-off-by: Guenter Roeck Acked-by: Tejun Heo Signed-off-by: Greg Kroah-Hartman --- include/linux/sysfs.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 8bf06b64487c..3c92121ba9af 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -22,14 +22,8 @@ struct kobject; struct module; enum kobj_ns_type; -/* FIXME - * The *owner field is no longer used. - * x86 tree has been cleaned up. The owner - * attribute is still left for other arches. - */ struct attribute { const char *name; - struct module *owner; mode_t mode; #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lock_class_key *key; -- cgit v1.2.3 From 6937e8f8c0135f2325194c372ada6dc655499992 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 5 Aug 2010 17:38:18 +0200 Subject: driver core: device_rename's new_name can be const The new_name argument to device_rename() can be const as kobject_rename's new_name argument is. Signed-off-by: Johannes Berg Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 0ca24e93304f..516fecacf27b 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -552,7 +552,7 @@ extern int device_for_each_child(struct device *dev, void *data, int (*fn)(struct device *dev, void *data)); extern struct device *device_find_child(struct device *dev, void *data, int (*match)(struct device *dev, void *data)); -extern int device_rename(struct device *dev, char *new_name); +extern int device_rename(struct device *dev, const char *new_name); extern int device_move(struct device *dev, struct device *new_parent, enum dpm_order dpm_order); extern const char *device_get_devnode(struct device *dev, -- cgit v1.2.3 From 8ae664184c45def51ff0b61d4bd6c6671db6cb4f Mon Sep 17 00:00:00 2001 From: Stefani Seibold Date: Thu, 5 Aug 2010 09:19:26 +0200 Subject: mtd: change struct flchip_shared spinlock locking into mutex This patch prevent to schedule while atomic by changing the flchip_shared spinlock into a mutex. This should be save since no atomic path will use this lock. It was suggested by Arnd Bergmann and Vasiliy Kulikov. Signed-off-by: Stefani Seibold Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/flashchip.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/flashchip.h b/include/linux/mtd/flashchip.h index f43e9b49b751..23cc10f8e343 100644 --- a/include/linux/mtd/flashchip.h +++ b/include/linux/mtd/flashchip.h @@ -92,7 +92,7 @@ struct flchip { /* This is used to handle contention on write/erase operations between partitions of the same physical chip. */ struct flchip_shared { - spinlock_t lock; + struct mutex lock; struct flchip *writing; struct flchip *erasing; }; -- cgit v1.2.3 From 2dc11581376829303b98eadb2de253bee065a56a Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Fri, 6 Aug 2010 09:25:50 -0600 Subject: of/device: Replace struct of_device with struct platform_device of_device is just an alias for platform_device, so remove it entirely. Also replace to_of_device() with to_platform_device() and update comment blocks. This patch was initially generated from the following semantic patch, and then edited by hand to pick up the bits that coccinelle didn't catch. @@ @@ -struct of_device +struct platform_device Signed-off-by: Grant Likely Reviewed-by: David S. Miller --- include/linux/of_device.h | 16 ---------------- include/linux/of_platform.h | 14 +++++++++++--- 2 files changed, 11 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_device.h b/include/linux/of_device.h index 35aa44ad9f2c..835f85ecd2de 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -1,20 +1,6 @@ #ifndef _LINUX_OF_DEVICE_H #define _LINUX_OF_DEVICE_H -/* - * The of_device *was* a kind of "base class" that was a superset of - * struct device for use by devices attached to an OF node and probed - * using OF properties. However, the important bit of OF-style - * probing, namely the device node pointer, has been moved into the - * common struct device when CONFIG_OF is set to make OF-style probing - * available to all bus types. So now, just make of_device and - * platform_device equivalent so that current of_platform bus users - * can be transparently migrated over to using the platform bus. - * - * This line will go away once all references to of_device are removed - * from the kernel. - */ -#define of_device platform_device #include #include /* temporary until merge */ @@ -23,8 +9,6 @@ #include #include -#define to_of_device(d) container_of(d, struct of_device, dev) - extern const struct of_device_id *of_match_device( const struct of_device_id *matches, const struct device *dev); extern void of_device_make_bus_id(struct device *dev); diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index 4e6d989c06df..a68716ad38ce 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -19,9 +19,17 @@ #include #include -/* - * An of_platform_driver driver is attached to a basic of_device on - * the "platform bus" (platform_bus_type). +/** + * of_platform_driver - Legacy of-aware driver for platform devices. + * + * An of_platform_driver driver is attached to a basic platform_device on + * ether the "platform bus" (platform_bus_type), or the ibm ebus + * (ibmebus_bus_type). + * + * of_platform_driver is being phased out when used with the platform_bus_type, + * and regular platform_drivers should be used instead. When the transition + * is complete, only ibmebus will be using this structure, and the + * platform_driver member of this structure will be removed. */ struct of_platform_driver { -- cgit v1.2.3 From 31d1d48e199e99077fb30f6fb9a793be7bec756f Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 6 Aug 2010 16:34:43 +0100 Subject: Fix init ordering of /dev/console vs callers of modprobe Make /dev/console get initialised before any initialisation routine that invokes modprobe because if modprobe fails, it's going to want to open /dev/console, presumably to write an error message to. The problem with that is that if the /dev/console driver is not yet initialised, the chardev handler will call request_module() to invoke modprobe, which will fail, because we never compile /dev/console as a module. This will lead to a modprobe loop, showing the following in the kernel log: request_module: runaway loop modprobe char-major-5-1 request_module: runaway loop modprobe char-major-5-1 request_module: runaway loop modprobe char-major-5-1 request_module: runaway loop modprobe char-major-5-1 request_module: runaway loop modprobe char-major-5-1 This can happen, for example, when the built in md5 module can't find the built in cryptomgr module (because the latter fails to initialise). The md5 module comes before the call to tty_init(), presumably because 'crypto' comes before 'drivers' alphabetically. Fix this by calling tty_init() from chrdev_init(). Signed-off-by: David Howells Signed-off-by: Linus Torvalds --- include/linux/tty.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 931078b73226..7802a243ee13 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -552,6 +552,9 @@ static inline void tty_audit_push_task(struct task_struct *tsk, } #endif +/* tty_io.c */ +extern int __init tty_init(void); + /* tty_ioctl.c */ extern int n_tty_ioctl_helper(struct tty_struct *tty, struct file *file, unsigned int cmd, unsigned long arg); -- cgit v1.2.3 From d5eff1a3412f6d75bf28f423c5015ece8055407a Mon Sep 17 00:00:00 2001 From: Bryan Schumaker Date: Tue, 3 Aug 2010 13:04:00 -0400 Subject: NFS: Fix /proc/mount for legacy binary interface Add a flag so we know if we mounted the NFS server using the legacy binary interface. If we used the legacy interface, then we should not show the mountd options. Signed-off-by: Bryan Schumaker Signed-off-by: Trond Myklebust --- include/linux/nfs_mount.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_mount.h b/include/linux/nfs_mount.h index 4499016e6d0d..5d59ae861aa6 100644 --- a/include/linux/nfs_mount.h +++ b/include/linux/nfs_mount.h @@ -69,5 +69,6 @@ struct nfs_mount_data { #define NFS_MOUNT_LOOKUP_CACHE_NONEG 0x10000 #define NFS_MOUNT_LOOKUP_CACHE_NONE 0x20000 #define NFS_MOUNT_NORESVPORT 0x40000 +#define NFS_MOUNT_LEGACY_INTERFACE 0x80000 #endif -- cgit v1.2.3 From 9261ec1a8d7b17e2540bef7cad3470870d13b61e Mon Sep 17 00:00:00 2001 From: Jason Wessel Date: Fri, 6 Aug 2010 15:36:47 -0500 Subject: console: Fix compilation regression A regression of building without CONFIG_HW_CONSOLE was introduced with commit b45cfba4e9005d64d419718e7ff7f7cab44c1994 (vt,console,kdb: implement atomic console enter/leave functions). ERROR: "con_debug_enter" [drivers/serial/kgdboc.ko] undefined! ERROR: "vc_cons" [drivers/serial/kgdboc.ko] undefined! ERROR: "fg_console" [drivers/serial/kgdboc.ko] undefined! ERROR: "con_debug_leave" [drivers/serial/kgdboc.ko] undefined! When there is no HW console the con_debug_enter and con_debug_leave functions should have no code. Signed-off-by: Jason Wessel CC: Jesse Barnes Reported-by: Randy Dunlap --- include/linux/console.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/console.h b/include/linux/console.h index f76fc297322d..95cf6f08a59d 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -79,8 +79,13 @@ int register_con_driver(const struct consw *csw, int first, int last); int unregister_con_driver(const struct consw *csw); int take_over_console(const struct consw *sw, int first, int last, int deflt); void give_up_console(const struct consw *sw); +#ifdef CONFIG_HW_CONSOLE int con_debug_enter(struct vc_data *vc); int con_debug_leave(void); +#else +#define con_debug_enter(vc) (0) +#define con_debug_leave() (0) +#endif /* scroll */ #define SM_UP (1) -- cgit v1.2.3 From 18cb2aef91b37dbce2bec2f39bb1dddd0e9dd838 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Sat, 7 Aug 2010 03:26:23 +0900 Subject: percpu: handle __percpu notations in UP accessors UP accessors didn't take care of __percpu notations leading to a lot of spurious sparse warnings on UP configurations. Fix it. Signed-off-by: Namhyung Kim Signed-off-by: Tejun Heo --- include/linux/percpu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index b8b9084527b1..49466b13c5c6 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -149,7 +149,7 @@ extern void __init percpu_init_late(void); #else /* CONFIG_SMP */ -#define per_cpu_ptr(ptr, cpu) ({ (void)(cpu); (ptr); }) +#define per_cpu_ptr(ptr, cpu) ({ (void)(cpu); VERIFY_PERCPU_PTR((ptr)); }) /* can't distinguish from other static vars, always false */ static inline bool is_kernel_percpu_address(unsigned long addr) -- cgit v1.2.3 From e2e1a148bc45855816ae6b4692ce29d0020fa22e Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 9 Jun 2010 10:42:09 +0200 Subject: block: add sysfs knob for turning off disk entropy contributions There are two reasons for doing this: - On SSD disks, the completion times aren't as random as they are for rotational drives. So it's questionable whether they should contribute to the random pool in the first place. - Calling add_disk_randomness() has a lot of overhead. This adds /sys/block//queue/add_random that will allow you to switch off on a per-device basis. The default setting is on, so there should be no functional changes from this patch. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 09a840264d6f..b8224ea4a5de 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -467,11 +467,13 @@ struct request_queue #define QUEUE_FLAG_IO_STAT 15 /* do IO stats */ #define QUEUE_FLAG_DISCARD 16 /* supports DISCARD */ #define QUEUE_FLAG_NOXMERGES 17 /* No extended merges */ +#define QUEUE_FLAG_ADD_RANDOM 18 /* Contributes to random pool */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_CLUSTER) | \ (1 << QUEUE_FLAG_STACKABLE) | \ - (1 << QUEUE_FLAG_SAME_COMP)) + (1 << QUEUE_FLAG_SAME_COMP) | \ + (1 << QUEUE_FLAG_ADD_RANDOM)) static inline int queue_is_locked(struct request_queue *q) { @@ -596,6 +598,7 @@ enum { test_bit(QUEUE_FLAG_NOXMERGES, &(q)->queue_flags) #define blk_queue_nonrot(q) test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags) #define blk_queue_io_stat(q) test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags) +#define blk_queue_add_random(q) test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags) #define blk_queue_flushing(q) ((q)->ordseq) #define blk_queue_stackable(q) \ test_bit(QUEUE_FLAG_STACKABLE, &(q)->queue_flags) -- cgit v1.2.3 From 41f2df62894bfcd3bf868af916b32b90aa7168dc Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 17 Jun 2010 08:54:16 +0200 Subject: block: BARRIER request should imply SYNC A barrier request should by defintion have priority in get_request and let the queue be unplugged immediately as it's blocking all forward progress due to the queue draining. Most filesystems already get this implicitly by the way how submit_bh treats the buffer_ordered flag, and gfs2 sets it explicitly. But btrfs and XFS are still forgetting to set the flag, as is blkdev_issue_flush and some places in DM/MD. For XFS on metadata heavy workloads this gives a consistent speedup in the 2-3% range. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 68ca1b0491af..598878831497 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -136,7 +136,7 @@ struct inodes_stat_t { * SWRITE_SYNC * SWRITE_SYNC_PLUG Like WRITE_SYNC/WRITE_SYNC_PLUG, but locks the buffer. * See SWRITE. - * WRITE_BARRIER Like WRITE, but tells the block layer that all + * WRITE_BARRIER Like WRITE_SYNC, but tells the block layer that all * previously submitted writes must be safely on storage * before this one is started. Also guarantees that when * this write is complete, it itself is also safely on @@ -159,7 +159,7 @@ struct inodes_stat_t { #define SWRITE_SYNC_PLUG \ (SWRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_NOIDLE)) #define SWRITE_SYNC (SWRITE_SYNC_PLUG | (1 << BIO_RW_UNPLUG)) -#define WRITE_BARRIER (WRITE | (1 << BIO_RW_BARRIER)) +#define WRITE_BARRIER (WRITE_SYNC | (1 << BIO_RW_BARRIER)) /* * These aren't really reads or writes, they pass down information about -- cgit v1.2.3 From bfe172310e58225f0d07f9354b683abacbd6a0d8 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Mon, 31 May 2010 15:59:03 +0900 Subject: block: kill ISA_DMA_THRESHOLD usage block uses ISA_DMA_THRESHOLD for BLK_BOUNCE_ISA. Only SCSI uses ISA_DMA_THRESHOLD for ancient drivers with non-zero unchecked_isa_dma. Nowadays drivers (and subsystems) use dma_mask properly instead of ISA_DMA_THRESHOLD. Documentation/scsi/scsi_mid_low_api.txt says: unchecked_isa_dma - 1=>only use bottom 16 MB of ram (ISA DMA addressing restriction), 0=>can use full 32 bit (or better) DMA address space So block simply uses DMA_BIT_MASK(24) for BLK_BOUNCE_ISA for SCSI. Signed-off-by: FUJITA Tomonori Acked-by: James Bottomley Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index b8224ea4a5de..d7ae241a9e55 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -712,7 +712,7 @@ extern unsigned long blk_max_low_pfn, blk_max_pfn; #define BLK_BOUNCE_HIGH -1ULL #endif #define BLK_BOUNCE_ANY (-1ULL) -#define BLK_BOUNCE_ISA (ISA_DMA_THRESHOLD) +#define BLK_BOUNCE_ISA (DMA_BIT_MASK(24)) /* * default timeout for SG_IO if none specified -- cgit v1.2.3 From 33659ebbae262228eef4e0fe990f393d1f0ed941 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 7 Aug 2010 18:17:56 +0200 Subject: block: remove wrappers for request type/flags Remove all the trivial wrappers for the cmd_type and cmd_flags fields in struct requests. This allows much easier grepping for different request types instead of unwinding through macros. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 41 +++++++++++++---------------------------- include/linux/blktrace_api.h | 2 +- 2 files changed, 14 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d7ae241a9e55..3ecd28ef9ba4 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -604,33 +604,20 @@ enum { test_bit(QUEUE_FLAG_STACKABLE, &(q)->queue_flags) #define blk_queue_discard(q) test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags) -#define blk_fs_request(rq) ((rq)->cmd_type == REQ_TYPE_FS) -#define blk_pc_request(rq) ((rq)->cmd_type == REQ_TYPE_BLOCK_PC) -#define blk_special_request(rq) ((rq)->cmd_type == REQ_TYPE_SPECIAL) -#define blk_sense_request(rq) ((rq)->cmd_type == REQ_TYPE_SENSE) - -#define blk_failfast_dev(rq) ((rq)->cmd_flags & REQ_FAILFAST_DEV) -#define blk_failfast_transport(rq) ((rq)->cmd_flags & REQ_FAILFAST_TRANSPORT) -#define blk_failfast_driver(rq) ((rq)->cmd_flags & REQ_FAILFAST_DRIVER) -#define blk_noretry_request(rq) (blk_failfast_dev(rq) || \ - blk_failfast_transport(rq) || \ - blk_failfast_driver(rq)) -#define blk_rq_started(rq) ((rq)->cmd_flags & REQ_STARTED) -#define blk_rq_io_stat(rq) ((rq)->cmd_flags & REQ_IO_STAT) -#define blk_rq_quiet(rq) ((rq)->cmd_flags & REQ_QUIET) - -#define blk_account_rq(rq) (blk_rq_started(rq) && (blk_fs_request(rq) || blk_discard_rq(rq))) - -#define blk_pm_suspend_request(rq) ((rq)->cmd_type == REQ_TYPE_PM_SUSPEND) -#define blk_pm_resume_request(rq) ((rq)->cmd_type == REQ_TYPE_PM_RESUME) +#define blk_noretry_request(rq) \ + ((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \ + REQ_FAILFAST_DRIVER)) + +#define blk_account_rq(rq) \ + (((rq)->cmd_flags & REQ_STARTED) && \ + ((rq)->cmd_type == REQ_TYPE_FS || \ + ((rq)->cmd_flags & REQ_DISCARD))) + #define blk_pm_request(rq) \ - (blk_pm_suspend_request(rq) || blk_pm_resume_request(rq)) + ((rq)->cmd_type == REQ_TYPE_PM_SUSPEND || \ + (rq)->cmd_type == REQ_TYPE_PM_RESUME) #define blk_rq_cpu_valid(rq) ((rq)->cpu != -1) -#define blk_sorted_rq(rq) ((rq)->cmd_flags & REQ_SORTED) -#define blk_barrier_rq(rq) ((rq)->cmd_flags & REQ_HARDBARRIER) -#define blk_fua_rq(rq) ((rq)->cmd_flags & REQ_FUA) -#define blk_discard_rq(rq) ((rq)->cmd_flags & REQ_DISCARD) #define blk_bidi_rq(rq) ((rq)->next_rq != NULL) /* rq->queuelist of dequeued request must be list_empty() */ #define blk_queued_rq(rq) (!list_empty(&(rq)->queuelist)) @@ -652,9 +639,6 @@ static inline bool rq_is_sync(struct request *rq) return rw_is_sync(rq->cmd_flags); } -#define rq_is_meta(rq) ((rq)->cmd_flags & REQ_RW_META) -#define rq_noidle(rq) ((rq)->cmd_flags & REQ_NOIDLE) - static inline int blk_queue_full(struct request_queue *q, int sync) { if (sync) @@ -687,7 +671,8 @@ static inline void blk_clear_queue_full(struct request_queue *q, int sync) (REQ_NOMERGE | REQ_STARTED | REQ_HARDBARRIER | REQ_SOFTBARRIER) #define rq_mergeable(rq) \ (!((rq)->cmd_flags & RQ_NOMERGE_FLAGS) && \ - (blk_discard_rq(rq) || blk_fs_request((rq)))) + (((rq)->cmd_flags & REQ_DISCARD) || \ + (rq)->cmd_type == REQ_TYPE_FS)) /* * q->prep_rq_fn return values diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 416bf62d6d46..23faa67e8022 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -224,7 +224,7 @@ static inline int blk_trace_init_sysfs(struct device *dev) static inline int blk_cmd_buf_len(struct request *rq) { - return blk_pc_request(rq) ? rq->cmd_len * 3 : 1; + return (rq->cmd_type == REQ_TYPE_BLOCK_PC) ? rq->cmd_len * 3 : 1; } extern void blk_dump_cmd(char *buf, struct request *rq); -- cgit v1.2.3 From 7b6d91daee5cac6402186ff224c3af39d79f4a0e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 7 Aug 2010 18:20:39 +0200 Subject: block: unify flags for struct bio and struct request Remove the current bio flags and reuse the request flags for the bio, too. This allows to more easily trace the type of I/O from the filesystem down to the block driver. There were two flags in the bio that were missing in the requests: BIO_RW_UNPLUG and BIO_RW_AHEAD. Also I've renamed two request flags that had a superflous RW in them. Note that the flags are in bio.h despite having the REQ_ name - as blkdev.h includes bio.h that is the only way to go for now. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/bio.h | 125 ++++++++++++++++++++++++++++++------------------- include/linux/blkdev.h | 66 +------------------------- include/linux/fs.h | 38 ++++++++------- 3 files changed, 99 insertions(+), 130 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 7fc5606e6ea5..4d379c8250ae 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -138,55 +138,83 @@ struct bio { #define BIO_POOL_IDX(bio) ((bio)->bi_flags >> BIO_POOL_OFFSET) /* - * bio bi_rw flags - * - * bit 0 -- data direction - * If not set, bio is a read from device. If set, it's a write to device. - * bit 1 -- fail fast device errors - * bit 2 -- fail fast transport errors - * bit 3 -- fail fast driver errors - * bit 4 -- rw-ahead when set - * bit 5 -- barrier - * Insert a serialization point in the IO queue, forcing previously - * submitted IO to be completed before this one is issued. - * bit 6 -- synchronous I/O hint. - * bit 7 -- Unplug the device immediately after submitting this bio. - * bit 8 -- metadata request - * Used for tracing to differentiate metadata and data IO. May also - * get some preferential treatment in the IO scheduler - * bit 9 -- discard sectors - * Informs the lower level device that this range of sectors is no longer - * used by the file system and may thus be freed by the device. Used - * for flash based storage. - * Don't want driver retries for any fast fail whatever the reason. - * bit 10 -- Tell the IO scheduler not to wait for more requests after this - one has been submitted, even if it is a SYNC request. + * Request flags. For use in the cmd_flags field of struct request, and in + * bi_rw of struct bio. Note that some flags are only valid in either one. */ -enum bio_rw_flags { - BIO_RW, - BIO_RW_FAILFAST_DEV, - BIO_RW_FAILFAST_TRANSPORT, - BIO_RW_FAILFAST_DRIVER, - /* above flags must match REQ_* */ - BIO_RW_AHEAD, - BIO_RW_BARRIER, - BIO_RW_SYNCIO, - BIO_RW_UNPLUG, - BIO_RW_META, - BIO_RW_DISCARD, - BIO_RW_NOIDLE, +enum rq_flag_bits { + /* common flags */ + __REQ_WRITE, /* not set, read. set, write */ + __REQ_FAILFAST_DEV, /* no driver retries of device errors */ + __REQ_FAILFAST_TRANSPORT, /* no driver retries of transport errors */ + __REQ_FAILFAST_DRIVER, /* no driver retries of driver errors */ + + __REQ_HARDBARRIER, /* may not be passed by drive either */ + __REQ_SYNC, /* request is sync (sync write or read) */ + __REQ_META, /* metadata io request */ + __REQ_DISCARD, /* request to discard sectors */ + __REQ_NOIDLE, /* don't anticipate more IO after this one */ + + /* bio only flags */ + __REQ_UNPLUG, /* unplug the immediately after submission */ + __REQ_RAHEAD, /* read ahead, can fail anytime */ + + /* request only flags */ + __REQ_SORTED, /* elevator knows about this request */ + __REQ_SOFTBARRIER, /* may not be passed by ioscheduler */ + __REQ_FUA, /* forced unit access */ + __REQ_NOMERGE, /* don't touch this for merging */ + __REQ_STARTED, /* drive already may have started this one */ + __REQ_DONTPREP, /* don't call prep for this one */ + __REQ_QUEUED, /* uses queueing */ + __REQ_ELVPRIV, /* elevator private data attached */ + __REQ_FAILED, /* set if the request failed */ + __REQ_QUIET, /* don't worry about errors */ + __REQ_PREEMPT, /* set for "ide_preempt" requests */ + __REQ_ORDERED_COLOR, /* is before or after barrier */ + __REQ_ALLOCED, /* request came from our alloc pool */ + __REQ_COPY_USER, /* contains copies of user pages */ + __REQ_INTEGRITY, /* integrity metadata has been remapped */ + __REQ_IO_STAT, /* account I/O stat */ + __REQ_MIXED_MERGE, /* merge of different types, fail separately */ + __REQ_NR_BITS, /* stops here */ }; -/* - * First four bits must match between bio->bi_rw and rq->cmd_flags, make - * that explicit here. - */ -#define BIO_RW_RQ_MASK 0xf - -static inline bool bio_rw_flagged(struct bio *bio, enum bio_rw_flags flag) -{ - return (bio->bi_rw & (1 << flag)) != 0; -} +#define REQ_WRITE (1 << __REQ_WRITE) +#define REQ_FAILFAST_DEV (1 << __REQ_FAILFAST_DEV) +#define REQ_FAILFAST_TRANSPORT (1 << __REQ_FAILFAST_TRANSPORT) +#define REQ_FAILFAST_DRIVER (1 << __REQ_FAILFAST_DRIVER) +#define REQ_HARDBARRIER (1 << __REQ_HARDBARRIER) +#define REQ_SYNC (1 << __REQ_SYNC) +#define REQ_META (1 << __REQ_META) +#define REQ_DISCARD (1 << __REQ_DISCARD) +#define REQ_NOIDLE (1 << __REQ_NOIDLE) + +#define REQ_FAILFAST_MASK \ + (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) +#define REQ_COMMON_MASK \ + (REQ_WRITE | REQ_FAILFAST_MASK | REQ_HARDBARRIER | REQ_SYNC | \ + REQ_META| REQ_DISCARD | REQ_NOIDLE) + +#define REQ_UNPLUG (1 << __REQ_UNPLUG) +#define REQ_RAHEAD (1 << __REQ_RAHEAD) + +#define REQ_SORTED (1 << __REQ_SORTED) +#define REQ_SOFTBARRIER (1 << __REQ_SOFTBARRIER) +#define REQ_FUA (1 << __REQ_FUA) +#define REQ_NOMERGE (1 << __REQ_NOMERGE) +#define REQ_STARTED (1 << __REQ_STARTED) +#define REQ_DONTPREP (1 << __REQ_DONTPREP) +#define REQ_QUEUED (1 << __REQ_QUEUED) +#define REQ_ELVPRIV (1 << __REQ_ELVPRIV) +#define REQ_FAILED (1 << __REQ_FAILED) +#define REQ_QUIET (1 << __REQ_QUIET) +#define REQ_PREEMPT (1 << __REQ_PREEMPT) +#define REQ_ORDERED_COLOR (1 << __REQ_ORDERED_COLOR) +#define REQ_ALLOCED (1 << __REQ_ALLOCED) +#define REQ_COPY_USER (1 << __REQ_COPY_USER) +#define REQ_INTEGRITY (1 << __REQ_INTEGRITY) +#define REQ_IO_STAT (1 << __REQ_IO_STAT) +#define REQ_MIXED_MERGE (1 << __REQ_MIXED_MERGE) /* * upper 16 bits of bi_rw define the io priority of this bio @@ -211,7 +239,10 @@ static inline bool bio_rw_flagged(struct bio *bio, enum bio_rw_flags flag) #define bio_offset(bio) bio_iovec((bio))->bv_offset #define bio_segments(bio) ((bio)->bi_vcnt - (bio)->bi_idx) #define bio_sectors(bio) ((bio)->bi_size >> 9) -#define bio_empty_barrier(bio) (bio_rw_flagged(bio, BIO_RW_BARRIER) && !bio_has_data(bio) && !bio_rw_flagged(bio, BIO_RW_DISCARD)) +#define bio_empty_barrier(bio) \ + ((bio->bi_rw & REQ_HARDBARRIER) && \ + !bio_has_data(bio) && \ + !(bio->bi_rw & REQ_DISCARD)) static inline unsigned int bio_cur_bytes(struct bio *bio) { diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 3ecd28ef9ba4..3fc0f5908619 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -84,70 +84,6 @@ enum { REQ_LB_OP_FLUSH = 0x41, /* flush request */ }; -/* - * request type modified bits. first four bits match BIO_RW* bits, important - */ -enum rq_flag_bits { - __REQ_RW, /* not set, read. set, write */ - __REQ_FAILFAST_DEV, /* no driver retries of device errors */ - __REQ_FAILFAST_TRANSPORT, /* no driver retries of transport errors */ - __REQ_FAILFAST_DRIVER, /* no driver retries of driver errors */ - /* above flags must match BIO_RW_* */ - __REQ_DISCARD, /* request to discard sectors */ - __REQ_SORTED, /* elevator knows about this request */ - __REQ_SOFTBARRIER, /* may not be passed by ioscheduler */ - __REQ_HARDBARRIER, /* may not be passed by drive either */ - __REQ_FUA, /* forced unit access */ - __REQ_NOMERGE, /* don't touch this for merging */ - __REQ_STARTED, /* drive already may have started this one */ - __REQ_DONTPREP, /* don't call prep for this one */ - __REQ_QUEUED, /* uses queueing */ - __REQ_ELVPRIV, /* elevator private data attached */ - __REQ_FAILED, /* set if the request failed */ - __REQ_QUIET, /* don't worry about errors */ - __REQ_PREEMPT, /* set for "ide_preempt" requests */ - __REQ_ORDERED_COLOR, /* is before or after barrier */ - __REQ_RW_SYNC, /* request is sync (sync write or read) */ - __REQ_ALLOCED, /* request came from our alloc pool */ - __REQ_RW_META, /* metadata io request */ - __REQ_COPY_USER, /* contains copies of user pages */ - __REQ_INTEGRITY, /* integrity metadata has been remapped */ - __REQ_NOIDLE, /* Don't anticipate more IO after this one */ - __REQ_IO_STAT, /* account I/O stat */ - __REQ_MIXED_MERGE, /* merge of different types, fail separately */ - __REQ_NR_BITS, /* stops here */ -}; - -#define REQ_RW (1 << __REQ_RW) -#define REQ_FAILFAST_DEV (1 << __REQ_FAILFAST_DEV) -#define REQ_FAILFAST_TRANSPORT (1 << __REQ_FAILFAST_TRANSPORT) -#define REQ_FAILFAST_DRIVER (1 << __REQ_FAILFAST_DRIVER) -#define REQ_DISCARD (1 << __REQ_DISCARD) -#define REQ_SORTED (1 << __REQ_SORTED) -#define REQ_SOFTBARRIER (1 << __REQ_SOFTBARRIER) -#define REQ_HARDBARRIER (1 << __REQ_HARDBARRIER) -#define REQ_FUA (1 << __REQ_FUA) -#define REQ_NOMERGE (1 << __REQ_NOMERGE) -#define REQ_STARTED (1 << __REQ_STARTED) -#define REQ_DONTPREP (1 << __REQ_DONTPREP) -#define REQ_QUEUED (1 << __REQ_QUEUED) -#define REQ_ELVPRIV (1 << __REQ_ELVPRIV) -#define REQ_FAILED (1 << __REQ_FAILED) -#define REQ_QUIET (1 << __REQ_QUIET) -#define REQ_PREEMPT (1 << __REQ_PREEMPT) -#define REQ_ORDERED_COLOR (1 << __REQ_ORDERED_COLOR) -#define REQ_RW_SYNC (1 << __REQ_RW_SYNC) -#define REQ_ALLOCED (1 << __REQ_ALLOCED) -#define REQ_RW_META (1 << __REQ_RW_META) -#define REQ_COPY_USER (1 << __REQ_COPY_USER) -#define REQ_INTEGRITY (1 << __REQ_INTEGRITY) -#define REQ_NOIDLE (1 << __REQ_NOIDLE) -#define REQ_IO_STAT (1 << __REQ_IO_STAT) -#define REQ_MIXED_MERGE (1 << __REQ_MIXED_MERGE) - -#define REQ_FAILFAST_MASK (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | \ - REQ_FAILFAST_DRIVER) - #define BLK_MAX_CDB 16 /* @@ -631,7 +567,7 @@ enum { */ static inline bool rw_is_sync(unsigned int rw_flags) { - return !(rw_flags & REQ_RW) || (rw_flags & REQ_RW_SYNC); + return !(rw_flags & REQ_WRITE) || (rw_flags & REQ_SYNC); } static inline bool rq_is_sync(struct request *rq) diff --git a/include/linux/fs.h b/include/linux/fs.h index 598878831497..c5c92943c767 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -144,29 +144,31 @@ struct inodes_stat_t { * of this IO. * */ -#define RW_MASK 1 -#define RWA_MASK 2 -#define READ 0 -#define WRITE 1 -#define READA 2 /* read-ahead - don't block if no resources */ -#define SWRITE 3 /* for ll_rw_block() - wait for buffer lock */ -#define READ_SYNC (READ | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG)) -#define READ_META (READ | (1 << BIO_RW_META)) -#define WRITE_SYNC_PLUG (WRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_NOIDLE)) -#define WRITE_SYNC (WRITE_SYNC_PLUG | (1 << BIO_RW_UNPLUG)) -#define WRITE_ODIRECT_PLUG (WRITE | (1 << BIO_RW_SYNCIO)) -#define WRITE_META (WRITE | (1 << BIO_RW_META)) -#define SWRITE_SYNC_PLUG \ - (SWRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_NOIDLE)) -#define SWRITE_SYNC (SWRITE_SYNC_PLUG | (1 << BIO_RW_UNPLUG)) -#define WRITE_BARRIER (WRITE_SYNC | (1 << BIO_RW_BARRIER)) +#define RW_MASK 1 +#define RWA_MASK 2 + +#define READ 0 +#define WRITE 1 +#define READA 2 /* readahead - don't block if no resources */ +#define SWRITE 3 /* for ll_rw_block() - wait for buffer lock */ + +#define READ_SYNC (READ | REQ_SYNC | REQ_UNPLUG) +#define READ_META (READ | REQ_META) +#define WRITE_SYNC_PLUG (WRITE | REQ_SYNC | REQ_NOIDLE) +#define WRITE_SYNC (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG) +#define WRITE_ODIRECT_PLUG (WRITE | REQ_SYNC) +#define WRITE_META (WRITE | REQ_META) +#define WRITE_BARRIER (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \ + REQ_HARDBARRIER) +#define SWRITE_SYNC_PLUG (SWRITE | REQ_SYNC | REQ_NOIDLE) +#define SWRITE_SYNC (SWRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG) /* * These aren't really reads or writes, they pass down information about * parts of device that are now unused by the file system. */ -#define DISCARD_NOBARRIER (WRITE | (1 << BIO_RW_DISCARD)) -#define DISCARD_BARRIER (DISCARD_NOBARRIER | (1 << BIO_RW_BARRIER)) +#define DISCARD_NOBARRIER (WRITE | REQ_DISCARD) +#define DISCARD_BARRIER (WRITE | REQ_DISCARD | REQ_HARDBARRIER) #define SEL_IN 1 #define SEL_OUT 2 -- cgit v1.2.3 From c1955ce32fdb0877b7a1b22feb2669358f65be76 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 19 Jun 2010 23:08:06 +0200 Subject: writeback: remove wb_list The wb_list member of struct backing_device_info always has exactly one element. Just use the direct bdi->wb pointer instead and simplify some code. Also remove bdi_task_init which is now trivial to prepare for the next patch. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/backing-dev.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index e9aec0d099df..50f146146169 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -45,8 +45,6 @@ enum bdi_stat_item { #define BDI_STAT_BATCH (8*(1+ilog2(nr_cpu_ids))) struct bdi_writeback { - struct list_head list; /* hangs off the bdi */ - struct backing_dev_info *bdi; /* our parent bdi */ unsigned int nr; @@ -80,8 +78,7 @@ struct backing_dev_info { unsigned int max_ratio, max_prop_frac; struct bdi_writeback wb; /* default writeback info for this bdi */ - spinlock_t wb_lock; /* protects update side of wb_list */ - struct list_head wb_list; /* the flusher threads hanging off this bdi */ + spinlock_t wb_lock; /* protects work_list */ struct list_head work_list; -- cgit v1.2.3 From 082439004b31adc146e96e5f1c574dd2b57dcd93 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 19 Jun 2010 23:08:22 +0200 Subject: writeback: merge bdi_writeback_task and bdi_start_fn Move all code for the writeback thread into fs/fs-writeback.c instead of splitting it over two functions in two files. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/backing-dev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 50f146146169..e536f3a74e60 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -102,7 +102,7 @@ void bdi_unregister(struct backing_dev_info *bdi); int bdi_setup_and_register(struct backing_dev_info *, char *, unsigned int); void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages); void bdi_start_background_writeback(struct backing_dev_info *bdi); -int bdi_writeback_task(struct bdi_writeback *wb); +int bdi_writeback_thread(void *data); int bdi_has_dirty_io(struct backing_dev_info *bdi); void bdi_arm_supers_timer(void); -- cgit v1.2.3 From 66ac0280197981f88774e74b60c8e5f9f07c1dba Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 18 Jun 2010 16:59:42 +0200 Subject: block: don't allocate a payload for discard request Allocating a fixed payload for discard requests always was a horrible hack, and it's not coming to byte us when adding support for discard in DM/MD. So change the code to leave the allocation of a payload to the lowlevel driver. Unfortunately that means we'll need another hack, which allows us to update the various block layer length fields indicating that we have a payload. Instead of hiding this in sd.c, which we already partially do for UNMAP support add a documented helper in the core block layer for it. Signed-off-by: Christoph Hellwig Acked-by: Mike Snitzer Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 3fc0f5908619..204fbe22354d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -705,6 +705,8 @@ extern struct request *blk_make_request(struct request_queue *, struct bio *, gfp_t); extern void blk_insert_request(struct request_queue *, struct request *, int, void *); extern void blk_requeue_request(struct request_queue *, struct request *); +extern void blk_add_request_payload(struct request *rq, struct page *page, + unsigned int len); extern int blk_rq_check_limits(struct request_queue *q, struct request *rq); extern int blk_lld_busy(struct request_queue *q); extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src, -- cgit v1.2.3 From 1676effca4cd2a6b32e6e8e0ecaa91522dfda6fa Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Mon, 21 Jun 2010 11:02:48 +0200 Subject: gcc-4.6: fs: fix unused but set warnings No real bugs I believe, just some dead code, and some shut up code. Signed-off-by: Andi Kleen Cc: Eric Paris Signed-off-by: Andrew Morton Signed-off-by: Jens Axboe --- include/linux/audit.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index f391d45c8aea..e24afabc548f 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -544,7 +544,7 @@ extern int audit_signals; #define audit_putname(n) do { ; } while (0) #define __audit_inode(n,d) do { ; } while (0) #define __audit_inode_child(i,p) do { ; } while (0) -#define audit_inode(n,d) do { ; } while (0) +#define audit_inode(n,d) do { (void)(d); } while (0) #define audit_inode_child(i,p) do { ; } while (0) #define audit_core_dumps(i) do { ; } while (0) #define auditsc_get_stamp(c,t,s) (0) -- cgit v1.2.3 From 28018c242a4ec7017bbbf81d2d3952f820a27118 Mon Sep 17 00:00:00 2001 From: James Bottomley Date: Thu, 1 Jul 2010 19:49:17 +0900 Subject: block: implement an unprep function corresponding directly to prep Reviewed-by: FUJITA Tomonori Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 204fbe22354d..6bba04c7ec48 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -200,6 +200,7 @@ struct request_pm_state typedef void (request_fn_proc) (struct request_queue *q); typedef int (make_request_fn) (struct request_queue *q, struct bio *bio); typedef int (prep_rq_fn) (struct request_queue *, struct request *); +typedef void (unprep_rq_fn) (struct request_queue *, struct request *); typedef void (unplug_fn) (struct request_queue *); struct bio_vec; @@ -282,6 +283,7 @@ struct request_queue request_fn_proc *request_fn; make_request_fn *make_request_fn; prep_rq_fn *prep_rq_fn; + unprep_rq_fn *unprep_rq_fn; unplug_fn *unplug_fn; merge_bvec_fn *merge_bvec_fn; prepare_flush_fn *prepare_flush_fn; @@ -841,6 +843,7 @@ extern void blk_complete_request(struct request *); extern void __blk_complete_request(struct request *); extern void blk_abort_request(struct request *); extern void blk_abort_queue(struct request_queue *); +extern void blk_unprep_request(struct request *); /* * Access functions for manipulating queue properties @@ -885,6 +888,7 @@ extern int blk_queue_dma_drain(struct request_queue *q, extern void blk_queue_lld_busy(struct request_queue *q, lld_busy_fn *fn); extern void blk_queue_segment_boundary(struct request_queue *, unsigned long); extern void blk_queue_prep_rq(struct request_queue *, prep_rq_fn *pfn); +extern void blk_queue_unprep_rq(struct request_queue *, unprep_rq_fn *ufn); extern void blk_queue_merge_bvec(struct request_queue *, merge_bvec_fn *); extern void blk_queue_dma_alignment(struct request_queue *, int); extern void blk_queue_update_dma_alignment(struct request_queue *, int); -- cgit v1.2.3 From 8749534fe6826596b71bc409c872b047a8e2755b Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Sat, 3 Jul 2010 17:45:32 +0900 Subject: block: introduce REQ_FLUSH flag SCSI-ml needs a way to mark a request as flush request in q->prepare_flush_fn because it needs to identify them later (e.g. in q->request_fn or prep_rq_fn). queue_flush sets REQ_HARDBARRIER in rq->cmd_flags however the block layer also sends normal REQ_TYPE_FS requests with REQ_HARDBARRIER. So SCSI-ml can't use REQ_HARDBARRIER to identify flush requests. We could change the block layer to clear REQ_HARDBARRIER bit before sending non flush requests to the lower layers. However, intorudcing the new flag looks cleaner (surely easier). Signed-off-by: FUJITA Tomonori Cc: James Bottomley Cc: David S. Miller Cc: Rusty Russell Cc: Alasdair G Kergon Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/bio.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 4d379c8250ae..f655b54c9ef3 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -174,6 +174,7 @@ enum rq_flag_bits { __REQ_ALLOCED, /* request came from our alloc pool */ __REQ_COPY_USER, /* contains copies of user pages */ __REQ_INTEGRITY, /* integrity metadata has been remapped */ + __REQ_FLUSH, /* request for cache flush */ __REQ_IO_STAT, /* account I/O stat */ __REQ_MIXED_MERGE, /* merge of different types, fail separately */ __REQ_NR_BITS, /* stops here */ @@ -213,6 +214,7 @@ enum rq_flag_bits { #define REQ_ALLOCED (1 << __REQ_ALLOCED) #define REQ_COPY_USER (1 << __REQ_COPY_USER) #define REQ_INTEGRITY (1 << __REQ_INTEGRITY) +#define REQ_FLUSH (1 << __REQ_FLUSH) #define REQ_IO_STAT (1 << __REQ_IO_STAT) #define REQ_MIXED_MERGE (1 << __REQ_MIXED_MERGE) -- cgit v1.2.3 From 00fff26539bfe3fad21c164fc4002d9ede056fb0 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Sat, 3 Jul 2010 17:45:40 +0900 Subject: block: remove q->prepare_flush_fn completely This removes q->prepare_flush_fn completely (changes the blk_queue_ordered API). Signed-off-by: FUJITA Tomonori Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6bba04c7ec48..3a2c5d9a9288 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -212,7 +212,6 @@ struct bvec_merge_data { }; typedef int (merge_bvec_fn) (struct request_queue *, struct bvec_merge_data *, struct bio_vec *); -typedef void (prepare_flush_fn) (struct request_queue *, struct request *); typedef void (softirq_done_fn)(struct request *); typedef int (dma_drain_needed_fn)(struct request *); typedef int (lld_busy_fn) (struct request_queue *q); @@ -286,7 +285,6 @@ struct request_queue unprep_rq_fn *unprep_rq_fn; unplug_fn *unplug_fn; merge_bvec_fn *merge_bvec_fn; - prepare_flush_fn *prepare_flush_fn; softirq_done_fn *softirq_done_fn; rq_timed_out_fn *rq_timed_out_fn; dma_drain_needed_fn *dma_drain_needed; @@ -896,7 +894,7 @@ extern void blk_queue_softirq_done(struct request_queue *, softirq_done_fn *); extern void blk_queue_rq_timed_out(struct request_queue *, rq_timed_out_fn *); extern void blk_queue_rq_timeout(struct request_queue *, unsigned int); extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev); -extern int blk_queue_ordered(struct request_queue *, unsigned, prepare_flush_fn *); +extern int blk_queue_ordered(struct request_queue *, unsigned); extern bool blk_do_ordered(struct request_queue *, struct request **); extern unsigned blk_ordered_cur_seq(struct request_queue *); extern unsigned blk_ordered_req_seq(struct request *); -- cgit v1.2.3 From a89f5c899db3c6be4bb426e4efb72ecee29a93b5 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Tue, 6 Jul 2010 09:03:18 +0200 Subject: block: remove unused REQ_TYPE_LINUX_BLOCK Nobody uses REQ_TYPE_LINUX_BLOCK (and its REQ_LB_OP_*). Signed-off-by: FUJITA Tomonori Acked-by: Jeff Garzik Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 15 --------------- 1 file changed, 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 3a2c5d9a9288..baf5258f5985 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -60,7 +60,6 @@ enum rq_cmd_type_bits { REQ_TYPE_PM_RESUME, /* resume request */ REQ_TYPE_PM_SHUTDOWN, /* shutdown request */ REQ_TYPE_SPECIAL, /* driver defined type */ - REQ_TYPE_LINUX_BLOCK, /* generic block layer message */ /* * for ATA/ATAPI devices. this really doesn't belong here, ide should * use REQ_TYPE_SPECIAL and use rq->cmd[0] with the range of driver @@ -70,20 +69,6 @@ enum rq_cmd_type_bits { REQ_TYPE_ATA_PC, }; -/* - * For request of type REQ_TYPE_LINUX_BLOCK, rq->cmd[0] is the opcode being - * sent down (similar to how REQ_TYPE_BLOCK_PC means that ->cmd[] holds a - * SCSI cdb. - * - * 0x00 -> 0x3f are driver private, to be used for whatever purpose they need, - * typically to differentiate REQ_TYPE_SPECIAL requests. - * - */ -enum { - REQ_LB_OP_EJECT = 0x40, /* eject request */ - REQ_LB_OP_FLUSH = 0x41, /* flush request */ -}; - #define BLK_MAX_CDB 16 /* -- cgit v1.2.3 From 8a6cfeb6deca3a8fefd639d898b0d163c0b5d368 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 8 Jul 2010 10:18:46 +0200 Subject: block: push down BKL into .locked_ioctl As a preparation for the removal of the big kernel lock in the block layer, this removes the BKL from the common ioctl handling code, moving it into every single driver still using it. Signed-off-by: Arnd Bergmann Acked-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index baf5258f5985..a8b05fc80c6d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1246,7 +1246,6 @@ static inline int blk_integrity_rq(struct request *rq) struct block_device_operations { int (*open) (struct block_device *, fmode_t); int (*release) (struct gendisk *, fmode_t); - int (*locked_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*direct_access) (struct block_device *, sector_t, -- cgit v1.2.3 From 62c2a7d969f30163f733c81158254b3095b23e72 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 7 Jul 2010 16:51:26 +0200 Subject: block: push BKL into blktrace ioctls The blktrace driver currently needs the BKL, but we should not need to take that in the block layer, so just push it down into the driver itself. It is quite likely that the BKL is not actually required in blktrace code and could be removed in a follow-on patch. Signed-off-by: Arnd Bergmann Acked-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blktrace_api.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 23faa67e8022..07c698621ad0 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -5,6 +5,7 @@ #ifdef __KERNEL__ #include #include +#include #endif /* @@ -203,6 +204,17 @@ extern int blk_trace_init_sysfs(struct device *dev); extern struct attribute_group blk_trace_attr_group; +struct compat_blk_user_trace_setup { + char name[32]; + u16 act_mask; + u32 buf_size; + u32 buf_nr; + compat_u64 start_lba; + compat_u64 end_lba; + u32 pid; +}; +#define BLKTRACESETUP32 _IOWR(0x12, 115, struct compat_blk_user_trace_setup) + #else /* !CONFIG_BLK_DEV_IO_TRACE */ # define blk_trace_ioctl(bdev, cmd, arg) (-ENOTTY) # define blk_trace_shutdown(q) do { } while (0) -- cgit v1.2.3 From 2669b19fa4debcdd6a660ace1a124c0900f113e6 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Fri, 9 Jul 2010 14:24:38 +1000 Subject: block: fix for block tracing build error block/compat_ioctl.c: In function 'compat_blkdev_ioctl': block/compat_ioctl.c:754: error: 'BLKTRACESETUP32' undeclared (first use in this function) Signed-off-by: Stephen Rothwell Acked-by: Arnd Bergmann Signed-off-by: Jens Axboe --- include/linux/blktrace_api.h | 26 +++++++++++++++----------- 1 file changed, 15 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 07c698621ad0..3395cf7130f5 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -204,17 +204,6 @@ extern int blk_trace_init_sysfs(struct device *dev); extern struct attribute_group blk_trace_attr_group; -struct compat_blk_user_trace_setup { - char name[32]; - u16 act_mask; - u32 buf_size; - u32 buf_nr; - compat_u64 start_lba; - compat_u64 end_lba; - u32 pid; -}; -#define BLKTRACESETUP32 _IOWR(0x12, 115, struct compat_blk_user_trace_setup) - #else /* !CONFIG_BLK_DEV_IO_TRACE */ # define blk_trace_ioctl(bdev, cmd, arg) (-ENOTTY) # define blk_trace_shutdown(q) do { } while (0) @@ -232,6 +221,21 @@ static inline int blk_trace_init_sysfs(struct device *dev) #endif /* CONFIG_BLK_DEV_IO_TRACE */ +#ifdef CONFIG_COMPAT + +struct compat_blk_user_trace_setup { + char name[32]; + u16 act_mask; + u32 buf_size; + u32 buf_nr; + compat_u64 start_lba; + compat_u64 end_lba; + u32 pid; +}; +#define BLKTRACESETUP32 _IOWR(0x12, 115, struct compat_blk_user_trace_setup) + +#endif + #if defined(CONFIG_EVENT_TRACING) && defined(CONFIG_BLOCK) static inline int blk_cmd_buf_len(struct request *rq) -- cgit v1.2.3 From edca4a380584a65a16839bdee33ec82244f0f88e Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Tue, 3 Aug 2010 12:54:51 +0200 Subject: block: disallow FS recursion from sb_issue_discard allocation Filesystems can call sb_issue_discard on a memory reclaim path (e.g. ext4 calls sb_issue_discard during journal commit). Use GFP_NOFS in sb_issue_discard to avoid recursing back into the FS. Reported-by: Mikulas Patocka Signed-off-by: Mike Snitzer Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index a8b05fc80c6d..89c855c5655c 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -933,7 +933,7 @@ static inline int sb_issue_discard(struct super_block *sb, { block <<= (sb->s_blocksize_bits - 9); nr_blocks <<= (sb->s_blocksize_bits - 9); - return blkdev_issue_discard(sb->s_bdev, block, nr_blocks, GFP_KERNEL, + return blkdev_issue_discard(sb->s_bdev, block, nr_blocks, GFP_NOFS, BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER); } -- cgit v1.2.3 From aca27ba9618276dd2f777bcd5a1419589ccf1ca8 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 3 Aug 2010 13:14:33 +0200 Subject: bio, fs: update RWA_MASK, READA and SWRITE to match the corresponding BIO_RW_* bits Commit a82afdf (block: use the same failfast bits for bio and request) moved BIO_RW_* bits around such that they match up with REQ_* bits. Unfortunately, fs.h hard coded RW_MASK, RWA_MASK, READ, WRITE, READA and SWRITE as 0, 1, 2 and 3, and expected them to match with BIO_RW_* bits. READ/WRITE didn't change but BIO_RW_AHEAD was moved to bit 4 instead of bit 1, breaking RWA_MASK, READA and SWRITE. This patch updates RWA_MASK, READA and SWRITE such that they match the BIO_RW_* bits again. A follow up patch will update the definitions to directly use BIO_RW_* bits so that this kind of breakage won't happen again. Neil also spotted missing RWA_MASK conversion. Stable: The offending commit a82afdf was released with v2.6.32, so this patch should be applied to all kernels since then but it must _NOT_ be applied to kernels earlier than that. Signed-off-by: Tejun Heo Reported-and-bisected-by: Vladislav Bolkhovitin Root-caused-by: Neil Brown Cc: stable@kernel.org Signed-off-by: Jens Axboe --- include/linux/fs.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index c5c92943c767..55dad7bca25b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -145,12 +145,12 @@ struct inodes_stat_t { * */ #define RW_MASK 1 -#define RWA_MASK 2 +#define RWA_MASK 16 #define READ 0 #define WRITE 1 -#define READA 2 /* readahead - don't block if no resources */ -#define SWRITE 3 /* for ll_rw_block() - wait for buffer lock */ +#define READA 16 /* readahead - don't block if no resources */ +#define SWRITE 17 /* for ll_rw_block(), wait for buffer lock */ #define READ_SYNC (READ | REQ_SYNC | REQ_UNPLUG) #define READ_META (READ | REQ_META) -- cgit v1.2.3 From 7cc015811ef8992dfcce314d0ed9642bc18143d1 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 3 Aug 2010 13:14:58 +0200 Subject: bio, fs: separate out bio_types.h and define READ/WRITE constants in terms of BIO_RW_* flags linux/fs.h hard coded READ/WRITE constants which should match BIO_RW_* flags. This is fragile and caused breakage during BIO_RW_* flag rearrangement. The hardcoding is to avoid include dependency hell. Create linux/bio_types.h which contatins definitions for bio data structures and flags and include it from bio.h and fs.h, and make fs.h define all READ/WRITE related constants in terms of BIO_RW_* flags. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/bio.h | 183 +------------------------------------------ include/linux/blk_types.h | 193 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/fs.h | 15 ++-- 3 files changed, 204 insertions(+), 187 deletions(-) create mode 100644 include/linux/blk_types.h (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index f655b54c9ef3..5274103434ad 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -9,7 +9,7 @@ * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of - + * * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * @@ -28,6 +28,9 @@ #include +/* struct bio, bio_vec and BIO_* flags are defined in blk_types.h */ +#include + #define BIO_DEBUG #ifdef BIO_DEBUG @@ -40,184 +43,6 @@ #define BIO_MAX_SIZE (BIO_MAX_PAGES << PAGE_CACHE_SHIFT) #define BIO_MAX_SECTORS (BIO_MAX_SIZE >> 9) -/* - * was unsigned short, but we might as well be ready for > 64kB I/O pages - */ -struct bio_vec { - struct page *bv_page; - unsigned int bv_len; - unsigned int bv_offset; -}; - -struct bio_set; -struct bio; -struct bio_integrity_payload; -typedef void (bio_end_io_t) (struct bio *, int); -typedef void (bio_destructor_t) (struct bio *); - -/* - * main unit of I/O for the block layer and lower layers (ie drivers and - * stacking drivers) - */ -struct bio { - sector_t bi_sector; /* device address in 512 byte - sectors */ - struct bio *bi_next; /* request queue link */ - struct block_device *bi_bdev; - unsigned long bi_flags; /* status, command, etc */ - unsigned long bi_rw; /* bottom bits READ/WRITE, - * top bits priority - */ - - unsigned short bi_vcnt; /* how many bio_vec's */ - unsigned short bi_idx; /* current index into bvl_vec */ - - /* Number of segments in this BIO after - * physical address coalescing is performed. - */ - unsigned int bi_phys_segments; - - unsigned int bi_size; /* residual I/O count */ - - /* - * To keep track of the max segment size, we account for the - * sizes of the first and last mergeable segments in this bio. - */ - unsigned int bi_seg_front_size; - unsigned int bi_seg_back_size; - - unsigned int bi_max_vecs; /* max bvl_vecs we can hold */ - - unsigned int bi_comp_cpu; /* completion CPU */ - - atomic_t bi_cnt; /* pin count */ - - struct bio_vec *bi_io_vec; /* the actual vec list */ - - bio_end_io_t *bi_end_io; - - void *bi_private; -#if defined(CONFIG_BLK_DEV_INTEGRITY) - struct bio_integrity_payload *bi_integrity; /* data integrity */ -#endif - - bio_destructor_t *bi_destructor; /* destructor */ - - /* - * We can inline a number of vecs at the end of the bio, to avoid - * double allocations for a small number of bio_vecs. This member - * MUST obviously be kept at the very end of the bio. - */ - struct bio_vec bi_inline_vecs[0]; -}; - -/* - * bio flags - */ -#define BIO_UPTODATE 0 /* ok after I/O completion */ -#define BIO_RW_BLOCK 1 /* RW_AHEAD set, and read/write would block */ -#define BIO_EOF 2 /* out-out-bounds error */ -#define BIO_SEG_VALID 3 /* bi_phys_segments valid */ -#define BIO_CLONED 4 /* doesn't own data */ -#define BIO_BOUNCED 5 /* bio is a bounce bio */ -#define BIO_USER_MAPPED 6 /* contains user pages */ -#define BIO_EOPNOTSUPP 7 /* not supported */ -#define BIO_CPU_AFFINE 8 /* complete bio on same CPU as submitted */ -#define BIO_NULL_MAPPED 9 /* contains invalid user pages */ -#define BIO_FS_INTEGRITY 10 /* fs owns integrity data, not block layer */ -#define BIO_QUIET 11 /* Make BIO Quiet */ -#define bio_flagged(bio, flag) ((bio)->bi_flags & (1 << (flag))) - -/* - * top 4 bits of bio flags indicate the pool this bio came from - */ -#define BIO_POOL_BITS (4) -#define BIO_POOL_NONE ((1UL << BIO_POOL_BITS) - 1) -#define BIO_POOL_OFFSET (BITS_PER_LONG - BIO_POOL_BITS) -#define BIO_POOL_MASK (1UL << BIO_POOL_OFFSET) -#define BIO_POOL_IDX(bio) ((bio)->bi_flags >> BIO_POOL_OFFSET) - -/* - * Request flags. For use in the cmd_flags field of struct request, and in - * bi_rw of struct bio. Note that some flags are only valid in either one. - */ -enum rq_flag_bits { - /* common flags */ - __REQ_WRITE, /* not set, read. set, write */ - __REQ_FAILFAST_DEV, /* no driver retries of device errors */ - __REQ_FAILFAST_TRANSPORT, /* no driver retries of transport errors */ - __REQ_FAILFAST_DRIVER, /* no driver retries of driver errors */ - - __REQ_HARDBARRIER, /* may not be passed by drive either */ - __REQ_SYNC, /* request is sync (sync write or read) */ - __REQ_META, /* metadata io request */ - __REQ_DISCARD, /* request to discard sectors */ - __REQ_NOIDLE, /* don't anticipate more IO after this one */ - - /* bio only flags */ - __REQ_UNPLUG, /* unplug the immediately after submission */ - __REQ_RAHEAD, /* read ahead, can fail anytime */ - - /* request only flags */ - __REQ_SORTED, /* elevator knows about this request */ - __REQ_SOFTBARRIER, /* may not be passed by ioscheduler */ - __REQ_FUA, /* forced unit access */ - __REQ_NOMERGE, /* don't touch this for merging */ - __REQ_STARTED, /* drive already may have started this one */ - __REQ_DONTPREP, /* don't call prep for this one */ - __REQ_QUEUED, /* uses queueing */ - __REQ_ELVPRIV, /* elevator private data attached */ - __REQ_FAILED, /* set if the request failed */ - __REQ_QUIET, /* don't worry about errors */ - __REQ_PREEMPT, /* set for "ide_preempt" requests */ - __REQ_ORDERED_COLOR, /* is before or after barrier */ - __REQ_ALLOCED, /* request came from our alloc pool */ - __REQ_COPY_USER, /* contains copies of user pages */ - __REQ_INTEGRITY, /* integrity metadata has been remapped */ - __REQ_FLUSH, /* request for cache flush */ - __REQ_IO_STAT, /* account I/O stat */ - __REQ_MIXED_MERGE, /* merge of different types, fail separately */ - __REQ_NR_BITS, /* stops here */ -}; - -#define REQ_WRITE (1 << __REQ_WRITE) -#define REQ_FAILFAST_DEV (1 << __REQ_FAILFAST_DEV) -#define REQ_FAILFAST_TRANSPORT (1 << __REQ_FAILFAST_TRANSPORT) -#define REQ_FAILFAST_DRIVER (1 << __REQ_FAILFAST_DRIVER) -#define REQ_HARDBARRIER (1 << __REQ_HARDBARRIER) -#define REQ_SYNC (1 << __REQ_SYNC) -#define REQ_META (1 << __REQ_META) -#define REQ_DISCARD (1 << __REQ_DISCARD) -#define REQ_NOIDLE (1 << __REQ_NOIDLE) - -#define REQ_FAILFAST_MASK \ - (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) -#define REQ_COMMON_MASK \ - (REQ_WRITE | REQ_FAILFAST_MASK | REQ_HARDBARRIER | REQ_SYNC | \ - REQ_META| REQ_DISCARD | REQ_NOIDLE) - -#define REQ_UNPLUG (1 << __REQ_UNPLUG) -#define REQ_RAHEAD (1 << __REQ_RAHEAD) - -#define REQ_SORTED (1 << __REQ_SORTED) -#define REQ_SOFTBARRIER (1 << __REQ_SOFTBARRIER) -#define REQ_FUA (1 << __REQ_FUA) -#define REQ_NOMERGE (1 << __REQ_NOMERGE) -#define REQ_STARTED (1 << __REQ_STARTED) -#define REQ_DONTPREP (1 << __REQ_DONTPREP) -#define REQ_QUEUED (1 << __REQ_QUEUED) -#define REQ_ELVPRIV (1 << __REQ_ELVPRIV) -#define REQ_FAILED (1 << __REQ_FAILED) -#define REQ_QUIET (1 << __REQ_QUIET) -#define REQ_PREEMPT (1 << __REQ_PREEMPT) -#define REQ_ORDERED_COLOR (1 << __REQ_ORDERED_COLOR) -#define REQ_ALLOCED (1 << __REQ_ALLOCED) -#define REQ_COPY_USER (1 << __REQ_COPY_USER) -#define REQ_INTEGRITY (1 << __REQ_INTEGRITY) -#define REQ_FLUSH (1 << __REQ_FLUSH) -#define REQ_IO_STAT (1 << __REQ_IO_STAT) -#define REQ_MIXED_MERGE (1 << __REQ_MIXED_MERGE) - /* * upper 16 bits of bi_rw define the io priority of this bio */ diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h new file mode 100644 index 000000000000..118523734af0 --- /dev/null +++ b/include/linux/blk_types.h @@ -0,0 +1,193 @@ +/* + * Block data types and constants. Directly include this file only to + * break include dependency loop. + */ +#ifndef __LINUX_BLK_TYPES_H +#define __LINUX_BLK_TYPES_H + +#ifdef CONFIG_BLOCK + +#include + +struct bio_set; +struct bio; +struct bio_integrity_payload; +struct page; +struct block_device; +typedef void (bio_end_io_t) (struct bio *, int); +typedef void (bio_destructor_t) (struct bio *); + +/* + * was unsigned short, but we might as well be ready for > 64kB I/O pages + */ +struct bio_vec { + struct page *bv_page; + unsigned int bv_len; + unsigned int bv_offset; +}; + +/* + * main unit of I/O for the block layer and lower layers (ie drivers and + * stacking drivers) + */ +struct bio { + sector_t bi_sector; /* device address in 512 byte + sectors */ + struct bio *bi_next; /* request queue link */ + struct block_device *bi_bdev; + unsigned long bi_flags; /* status, command, etc */ + unsigned long bi_rw; /* bottom bits READ/WRITE, + * top bits priority + */ + + unsigned short bi_vcnt; /* how many bio_vec's */ + unsigned short bi_idx; /* current index into bvl_vec */ + + /* Number of segments in this BIO after + * physical address coalescing is performed. + */ + unsigned int bi_phys_segments; + + unsigned int bi_size; /* residual I/O count */ + + /* + * To keep track of the max segment size, we account for the + * sizes of the first and last mergeable segments in this bio. + */ + unsigned int bi_seg_front_size; + unsigned int bi_seg_back_size; + + unsigned int bi_max_vecs; /* max bvl_vecs we can hold */ + + unsigned int bi_comp_cpu; /* completion CPU */ + + atomic_t bi_cnt; /* pin count */ + + struct bio_vec *bi_io_vec; /* the actual vec list */ + + bio_end_io_t *bi_end_io; + + void *bi_private; +#if defined(CONFIG_BLK_DEV_INTEGRITY) + struct bio_integrity_payload *bi_integrity; /* data integrity */ +#endif + + bio_destructor_t *bi_destructor; /* destructor */ + + /* + * We can inline a number of vecs at the end of the bio, to avoid + * double allocations for a small number of bio_vecs. This member + * MUST obviously be kept at the very end of the bio. + */ + struct bio_vec bi_inline_vecs[0]; +}; + +/* + * bio flags + */ +#define BIO_UPTODATE 0 /* ok after I/O completion */ +#define BIO_RW_BLOCK 1 /* RW_AHEAD set, and read/write would block */ +#define BIO_EOF 2 /* out-out-bounds error */ +#define BIO_SEG_VALID 3 /* bi_phys_segments valid */ +#define BIO_CLONED 4 /* doesn't own data */ +#define BIO_BOUNCED 5 /* bio is a bounce bio */ +#define BIO_USER_MAPPED 6 /* contains user pages */ +#define BIO_EOPNOTSUPP 7 /* not supported */ +#define BIO_CPU_AFFINE 8 /* complete bio on same CPU as submitted */ +#define BIO_NULL_MAPPED 9 /* contains invalid user pages */ +#define BIO_FS_INTEGRITY 10 /* fs owns integrity data, not block layer */ +#define BIO_QUIET 11 /* Make BIO Quiet */ +#define bio_flagged(bio, flag) ((bio)->bi_flags & (1 << (flag))) + +/* + * top 4 bits of bio flags indicate the pool this bio came from + */ +#define BIO_POOL_BITS (4) +#define BIO_POOL_NONE ((1UL << BIO_POOL_BITS) - 1) +#define BIO_POOL_OFFSET (BITS_PER_LONG - BIO_POOL_BITS) +#define BIO_POOL_MASK (1UL << BIO_POOL_OFFSET) +#define BIO_POOL_IDX(bio) ((bio)->bi_flags >> BIO_POOL_OFFSET) + +/* + * Request flags. For use in the cmd_flags field of struct request, and in + * bi_rw of struct bio. Note that some flags are only valid in either one. + */ +enum rq_flag_bits { + /* common flags */ + __REQ_WRITE, /* not set, read. set, write */ + __REQ_FAILFAST_DEV, /* no driver retries of device errors */ + __REQ_FAILFAST_TRANSPORT, /* no driver retries of transport errors */ + __REQ_FAILFAST_DRIVER, /* no driver retries of driver errors */ + + __REQ_HARDBARRIER, /* may not be passed by drive either */ + __REQ_SYNC, /* request is sync (sync write or read) */ + __REQ_META, /* metadata io request */ + __REQ_DISCARD, /* request to discard sectors */ + __REQ_NOIDLE, /* don't anticipate more IO after this one */ + + /* bio only flags */ + __REQ_UNPLUG, /* unplug the immediately after submission */ + __REQ_RAHEAD, /* read ahead, can fail anytime */ + + /* request only flags */ + __REQ_SORTED, /* elevator knows about this request */ + __REQ_SOFTBARRIER, /* may not be passed by ioscheduler */ + __REQ_FUA, /* forced unit access */ + __REQ_NOMERGE, /* don't touch this for merging */ + __REQ_STARTED, /* drive already may have started this one */ + __REQ_DONTPREP, /* don't call prep for this one */ + __REQ_QUEUED, /* uses queueing */ + __REQ_ELVPRIV, /* elevator private data attached */ + __REQ_FAILED, /* set if the request failed */ + __REQ_QUIET, /* don't worry about errors */ + __REQ_PREEMPT, /* set for "ide_preempt" requests */ + __REQ_ORDERED_COLOR, /* is before or after barrier */ + __REQ_ALLOCED, /* request came from our alloc pool */ + __REQ_COPY_USER, /* contains copies of user pages */ + __REQ_INTEGRITY, /* integrity metadata has been remapped */ + __REQ_FLUSH, /* request for cache flush */ + __REQ_IO_STAT, /* account I/O stat */ + __REQ_MIXED_MERGE, /* merge of different types, fail separately */ + __REQ_NR_BITS, /* stops here */ +}; + +#define REQ_WRITE (1 << __REQ_WRITE) +#define REQ_FAILFAST_DEV (1 << __REQ_FAILFAST_DEV) +#define REQ_FAILFAST_TRANSPORT (1 << __REQ_FAILFAST_TRANSPORT) +#define REQ_FAILFAST_DRIVER (1 << __REQ_FAILFAST_DRIVER) +#define REQ_HARDBARRIER (1 << __REQ_HARDBARRIER) +#define REQ_SYNC (1 << __REQ_SYNC) +#define REQ_META (1 << __REQ_META) +#define REQ_DISCARD (1 << __REQ_DISCARD) +#define REQ_NOIDLE (1 << __REQ_NOIDLE) + +#define REQ_FAILFAST_MASK \ + (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) +#define REQ_COMMON_MASK \ + (REQ_WRITE | REQ_FAILFAST_MASK | REQ_HARDBARRIER | REQ_SYNC | \ + REQ_META| REQ_DISCARD | REQ_NOIDLE) + +#define REQ_UNPLUG (1 << __REQ_UNPLUG) +#define REQ_RAHEAD (1 << __REQ_RAHEAD) + +#define REQ_SORTED (1 << __REQ_SORTED) +#define REQ_SOFTBARRIER (1 << __REQ_SOFTBARRIER) +#define REQ_FUA (1 << __REQ_FUA) +#define REQ_NOMERGE (1 << __REQ_NOMERGE) +#define REQ_STARTED (1 << __REQ_STARTED) +#define REQ_DONTPREP (1 << __REQ_DONTPREP) +#define REQ_QUEUED (1 << __REQ_QUEUED) +#define REQ_ELVPRIV (1 << __REQ_ELVPRIV) +#define REQ_FAILED (1 << __REQ_FAILED) +#define REQ_QUIET (1 << __REQ_QUIET) +#define REQ_PREEMPT (1 << __REQ_PREEMPT) +#define REQ_ORDERED_COLOR (1 << __REQ_ORDERED_COLOR) +#define REQ_ALLOCED (1 << __REQ_ALLOCED) +#define REQ_COPY_USER (1 << __REQ_COPY_USER) +#define REQ_INTEGRITY (1 << __REQ_INTEGRITY) +#define REQ_FLUSH (1 << __REQ_FLUSH) +#define REQ_IO_STAT (1 << __REQ_IO_STAT) +#define REQ_MIXED_MERGE (1 << __REQ_MIXED_MERGE) + +#endif /* CONFIG_BLOCK */ +#endif /* __LINUX_BLK_TYPES_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 55dad7bca25b..c53911277210 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -8,6 +8,7 @@ #include #include +#include /* * It's silly to have NR_OPEN bigger than NR_FILE, but you can change @@ -117,7 +118,7 @@ struct inodes_stat_t { * immediately wait on this read without caring about * unplugging. * READA Used for read-ahead operations. Lower priority, and the - * block layer could (in theory) choose to ignore this + * block layer could (in theory) choose to ignore this * request if it runs into resource problems. * WRITE A normal async write. Device will be plugged. * SWRITE Like WRITE, but a special case for ll_rw_block() that @@ -144,13 +145,13 @@ struct inodes_stat_t { * of this IO. * */ -#define RW_MASK 1 -#define RWA_MASK 16 +#define RW_MASK REQ_WRITE +#define RWA_MASK REQ_RAHEAD #define READ 0 -#define WRITE 1 -#define READA 16 /* readahead - don't block if no resources */ -#define SWRITE 17 /* for ll_rw_block(), wait for buffer lock */ +#define WRITE RW_MASK +#define READA RWA_MASK +#define SWRITE (WRITE | READA) #define READ_SYNC (READ | REQ_SYNC | REQ_UNPLUG) #define READ_META (READ | REQ_META) @@ -2200,7 +2201,6 @@ static inline void insert_inode_hash(struct inode *inode) { extern void file_move(struct file *f, struct list_head *list); extern void file_kill(struct file *f); #ifdef CONFIG_BLOCK -struct bio; extern void submit_bio(int, struct bio *); extern int bdev_read_only(struct block_device *); #endif @@ -2267,7 +2267,6 @@ static inline int xip_truncate_page(struct address_space *mapping, loff_t from) #endif #ifdef CONFIG_BLOCK -struct bio; typedef void (dio_submit_t)(int rw, struct bio *bio, struct inode *inode, loff_t file_offset); void dio_end_io(struct bio *bio, int error); -- cgit v1.2.3 From 4aeefdc69f7b6f3f287e6fd8d4b213953b9e92d8 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 3 Aug 2010 13:22:51 +0200 Subject: coda: fixup clash with block layer REQ_* defines CODA should not be using defines in the global name space of that nature, prefix them with CODA_. Signed-off-by: Jens Axboe --- include/linux/coda_psdev.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/coda_psdev.h b/include/linux/coda_psdev.h index 8859e2ede9fe..284b520934a0 100644 --- a/include/linux/coda_psdev.h +++ b/include/linux/coda_psdev.h @@ -86,9 +86,9 @@ struct upc_req { wait_queue_head_t uc_sleep; /* process' wait queue */ }; -#define REQ_ASYNC 0x1 -#define REQ_READ 0x2 -#define REQ_WRITE 0x4 -#define REQ_ABORT 0x8 +#define CODA_REQ_ASYNC 0x1 +#define CODA_REQ_READ 0x2 +#define CODA_REQ_WRITE 0x4 +#define CODA_REQ_ABORT 0x8 #endif -- cgit v1.2.3 From 6f904ff0e39ea88f81eb77e8dfb4e1238492f0a8 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Sun, 25 Jul 2010 14:29:11 +0300 Subject: writeback: harmonize writeback threads naming The write-back code mixes words "thread" and "task" for the same things. This is not a big deal, but still an inconsistency. hch: a convention I tend to use and I've seen in various places is to always use _task for the storage of the task_struct pointer, and thread everywhere else. This especially helps with having foo_thread for the actual thread and foo_task for a global variable keeping the task_struct pointer This patch renames: * 'bdi_add_default_flusher_task()' -> 'bdi_add_default_flusher_thread()' * 'bdi_forker_task()' -> 'bdi_forker_thread()' because bdi threads are 'bdi_writeback_thread()', so these names are more consistent. This patch also amends commentaries and makes them refer the forker and bdi threads as "thread", not "task". Also, while on it, make 'bdi_add_default_flusher_thread()' declaration use 'static void' instead of 'void static' and make checkpatch.pl happy. Signed-off-by: Artem Bityutskiy Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/backing-dev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index e536f3a74e60..f0936f5f85dd 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -50,7 +50,7 @@ struct bdi_writeback { unsigned long last_old_flush; /* last old data flush */ - struct task_struct *task; /* writeback task */ + struct task_struct *task; /* writeback thread */ struct list_head b_dirty; /* dirty inodes */ struct list_head b_io; /* parked for writeback */ struct list_head b_more_io; /* parked for more writeback */ -- cgit v1.2.3 From 080dcec41709be72613133f695be75b98dd43e88 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Sun, 25 Jul 2010 14:29:16 +0300 Subject: writeback: simplify bdi code a little This patch simplifies bdi code a little by removing the 'pending_list' which is redundant. Indeed, currently the forker thread ('bdi_forker_thread()') is working like this: 1. In a loop, fetch all bdi's which have works but have no writeback thread and move them to the 'pending_list'. 2. If the list is empty, sleep for 5 sec. 3. Otherwise, take one bdi from the list, fork the writeback thread for this bdi, and repeat the loop. IOW, it first moves everything to the 'pending_list', then process only one element, and so on. This patch simplifies the algorithm, which is now as follows. 1. Find the first bdi which has a work and remove it from the global list of bdi's (bdi_list). 2. If there was not such bdi, sleep 5 sec. 3. Fork the writeback thread for this bdi and repeat the loop. IOW, now we find the first bdi to process, process it, and so on. This is simpler and involves less lists. The bonus now is that we can get rid of a couple of functions, as well as remove complications which involve 'rcu_call()' and 'bdi->rcu_head'. This patch also makes sure we use 'list_add_tail_rcu()', instead of plain 'list_add_tail()', but this piece of code is going to be removed in the next patch anyway. Signed-off-by: Artem Bityutskiy Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/backing-dev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index f0936f5f85dd..95ecb2bebca8 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -58,7 +58,6 @@ struct bdi_writeback { struct backing_dev_info { struct list_head bdi_list; - struct rcu_head rcu_head; unsigned long ra_pages; /* max readahead in PAGE_CACHE_SIZE units */ unsigned long state; /* Always use atomic bitops on this */ unsigned int capabilities; /* Device capabilities */ -- cgit v1.2.3 From ecd584030da67ede1bf17955746a6ce834d9fc6b Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Sun, 25 Jul 2010 14:29:18 +0300 Subject: writeback: move last_active to bdi Currently bdi threads use local variable 'last_active' which stores last time when the bdi thread did some useful work. Move this local variable to 'struct bdi_writeback'. This is just a preparation for the further patches which will make the forker thread decide when bdi threads should be killed. Signed-off-by: Artem Bityutskiy Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/backing-dev.h | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 95ecb2bebca8..71b6223e0a77 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -45,15 +45,16 @@ enum bdi_stat_item { #define BDI_STAT_BATCH (8*(1+ilog2(nr_cpu_ids))) struct bdi_writeback { - struct backing_dev_info *bdi; /* our parent bdi */ + struct backing_dev_info *bdi; /* our parent bdi */ unsigned int nr; - unsigned long last_old_flush; /* last old data flush */ + unsigned long last_old_flush; /* last old data flush */ + unsigned long last_active; /* last time bdi thread was active */ - struct task_struct *task; /* writeback thread */ - struct list_head b_dirty; /* dirty inodes */ - struct list_head b_io; /* parked for writeback */ - struct list_head b_more_io; /* parked for more writeback */ + struct task_struct *task; /* writeback thread */ + struct list_head b_dirty; /* dirty inodes */ + struct list_head b_io; /* parked for writeback */ + struct list_head b_more_io; /* parked for more writeback */ }; struct backing_dev_info { -- cgit v1.2.3 From 6467716a37673e8d47b4984eb19839bdad0a8353 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Sun, 25 Jul 2010 14:29:22 +0300 Subject: writeback: optimize periodic bdi thread wakeups Whe the first inode for a bdi is marked dirty, we wake up the bdi thread which should take care of the periodic background write-out. However, the write-out will actually start only 'dirty_writeback_interval' centisecs later, so we can delay the wake-up. This change was requested by Nick Piggin who pointed out that if we delay the wake-up, we weed out 2 unnecessary contex switches, which matters because '__mark_inode_dirty()' is a hot-path function. This patch introduces a new function - 'bdi_wakeup_thread_delayed()', which sets up a timer to wake-up the bdi thread and returns. So the wake-up is delayed. We also delete the timer in bdi threads just before writing-back. And synchronously delete it when unregistering bdi. At the unregister point the bdi does not have any users, so no one can arm it again. Since now we take 'bdi->wb_lock' in the timer, which can execute in softirq context, we have to use 'spin_lock_bh()' for 'bdi->wb_lock'. This patch makes this change as well. This patch also moves the 'bdi_wb_init()' function down in the file to avoid forward-declaration of 'bdi_wakeup_thread_delayed()'. Signed-off-by: Artem Bityutskiy Signed-off-by: Jens Axboe --- include/linux/backing-dev.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 71b6223e0a77..7628219e5386 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -52,6 +52,7 @@ struct bdi_writeback { unsigned long last_active; /* last time bdi thread was active */ struct task_struct *task; /* writeback thread */ + struct timer_list wakeup_timer; /* used for delayed bdi thread wakeup */ struct list_head b_dirty; /* dirty inodes */ struct list_head b_io; /* parked for writeback */ struct list_head b_more_io; /* parked for more writeback */ @@ -105,6 +106,7 @@ void bdi_start_background_writeback(struct backing_dev_info *bdi); int bdi_writeback_thread(void *data); int bdi_has_dirty_io(struct backing_dev_info *bdi); void bdi_arm_supers_timer(void); +void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi); extern spinlock_t bdi_lock; extern struct list_head bdi_list; -- cgit v1.2.3 From e7f52dfb4f378ea1bbfd4476f4e8ba42f5fb332c Mon Sep 17 00:00:00 2001 From: Lars Ellenberg Date: Tue, 3 Aug 2010 20:20:20 +0200 Subject: drbd: revert "delay probes", feature is being re-implemented differently It was a now abandoned attempt to throttle resync bandwidth based on the delay it causes on the bulk data socket. It has no userbase yet, and has been disabled by 9173465ccb51c09cc3102a10af93e9f469a0af6f already. This removes the now unused code. The basic feature, namely using up "idle" bandwith of network and disk IO subsystem, with minimal impact to application IO, is being reimplemented differently. Signed-off-by: Philipp Reisner Signed-off-by: Lars Ellenberg Signed-off-by: Jens Axboe --- include/linux/drbd.h | 2 +- include/linux/drbd_nl.h | 9 +++++---- 2 files changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/drbd.h b/include/linux/drbd.h index b8d2516668aa..479ee3a1d901 100644 --- a/include/linux/drbd.h +++ b/include/linux/drbd.h @@ -53,7 +53,7 @@ extern const char *drbd_buildtag(void); -#define REL_VERSION "8.3.8" +#define REL_VERSION "8.3.8.1" #define API_VERSION 88 #define PRO_VERSION_MIN 86 #define PRO_VERSION_MAX 94 diff --git a/include/linux/drbd_nl.h b/include/linux/drbd_nl.h index ce77a746fc9d..5f042810a56c 100644 --- a/include/linux/drbd_nl.h +++ b/include/linux/drbd_nl.h @@ -78,10 +78,11 @@ NL_PACKET(syncer_conf, 8, NL_INTEGER( 30, T_MAY_IGNORE, rate) NL_INTEGER( 31, T_MAY_IGNORE, after) NL_INTEGER( 32, T_MAY_IGNORE, al_extents) - NL_INTEGER( 71, T_MAY_IGNORE, dp_volume) - NL_INTEGER( 72, T_MAY_IGNORE, dp_interval) - NL_INTEGER( 73, T_MAY_IGNORE, throttle_th) - NL_INTEGER( 74, T_MAY_IGNORE, hold_off_th) +/* NL_INTEGER( 71, T_MAY_IGNORE, dp_volume) + * NL_INTEGER( 72, T_MAY_IGNORE, dp_interval) + * NL_INTEGER( 73, T_MAY_IGNORE, throttle_th) + * NL_INTEGER( 74, T_MAY_IGNORE, hold_off_th) + * feature will be reimplemented differently with 8.3.9 */ NL_STRING( 52, T_MAY_IGNORE, verify_alg, SHARED_SECRET_MAX) NL_STRING( 51, T_MAY_IGNORE, cpu_mask, 32) NL_STRING( 64, T_MAY_IGNORE, csums_alg, SHARED_SECRET_MAX) -- cgit v1.2.3 From 387ac089361fbe5ef287e6950c5c40f6b18e5c55 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 5 Aug 2010 08:34:13 +0200 Subject: block: fix missing export of blk_types.h Stephen reports: After merging the block tree, today's linux-next build (x86_64 allmodconfig) failed like this: usr/include/linux/fs.h:11: included file 'linux/blk_types.h' is not exported Caused by commit 9d3dbbcd9a84518ff5e32ffe671d06a48cf84fd9 ("bio, fs: separate out bio_types.h and define READ/WRITE constants in terms of BIO_RW_* flags"). Reported-by: Stephen Rothwell Signed-off-by: Jens Axboe --- include/linux/Kbuild | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index 2fc8e14cc24a..671715b869fc 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -39,6 +39,7 @@ header-y += ax25.h header-y += b1lli.h header-y += baycom.h header-y += bfs_fs.h +header-y += blk_types.h header-y += blkpg.h header-y += bpqether.h header-y += bsg.h -- cgit v1.2.3 From 78ef7fab0eb0a5b159842bac89aed74bb0aa7bfe Mon Sep 17 00:00:00 2001 From: Barry Song <21cnbao@gmail.com> Date: Fri, 15 Jan 2010 15:50:14 +0800 Subject: mtd-physmap: add support users can assign the probe type in board files There are three reasons to add this support: 1. users probably know the interface type of their flashs, then probe can be faster if they give the right type in platform data since wrong types will not be detected. 2. sometimes, detecting can cause destory to system. For example, for kernel XIP, detecting can cause NOR enter a mode instructions can not be fetched right, which will make kernel crash. 3. For a new probe which is not listed in the rom_probe_types, if users assign it in board files, physmap can still probe it. Signed-off-by: Barry Song <21cnbao@gmail.com> Signed-off-by: Mike Frysinger Signed-off-by: David Woodhouse --- include/linux/mtd/physmap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mtd/physmap.h b/include/linux/mtd/physmap.h index 76f7cabf07d3..bcfd9f777454 100644 --- a/include/linux/mtd/physmap.h +++ b/include/linux/mtd/physmap.h @@ -25,6 +25,7 @@ struct physmap_flash_data { void (*set_vpp)(struct map_info *, int); unsigned int nr_parts; unsigned int pfow_base; + char *probe_type; struct mtd_partition *parts; }; -- cgit v1.2.3 From 6088c0587706b2cf21ce50c11576718bff5fae0c Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Sun, 8 Aug 2010 14:15:22 +0100 Subject: jffs2: Update copyright notices Signed-off-by: David Woodhouse --- include/linux/jffs2.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/jffs2.h b/include/linux/jffs2.h index 0874ab59ffef..b9898894ec8d 100644 --- a/include/linux/jffs2.h +++ b/include/linux/jffs2.h @@ -1,7 +1,8 @@ /* * JFFS2 -- Journalling Flash File System, Version 2. * - * Copyright (C) 2001-2003 Red Hat, Inc. + * Copyright © 2001-2007 Red Hat, Inc. + * Copyright © 2004-2010 David Woodhouse * * Created by David Woodhouse * -- cgit v1.2.3 From 9f2cc6f759ca0b072107c171a3b5cd79c7ea5de3 Mon Sep 17 00:00:00 2001 From: H Hartley Sweeten Date: Fri, 21 May 2010 18:38:52 -0500 Subject: watchdog: wdt_pci.c: move ids to pci_ids.h Move the VENDOR/DEVICE ids to pci_ids.h. Signed-off-by: H Hartley Sweeten Cc: Jesse Barnes Signed-off-by: Wim Van Sebroeck --- include/linux/pci_ids.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index c81eec4d3c35..f6a3b2d36cad 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2372,6 +2372,9 @@ #define PCI_VENDOR_ID_AKS 0x416c #define PCI_DEVICE_ID_AKS_ALADDINCARD 0x0100 +#define PCI_VENDOR_ID_ACCESSIO 0x494f +#define PCI_DEVICE_ID_ACCESSIO_WDG_CSM 0x22c0 + #define PCI_VENDOR_ID_S3 0x5333 #define PCI_DEVICE_ID_S3_TRIO 0x8811 #define PCI_DEVICE_ID_S3_868 0x8880 -- cgit v1.2.3 From ad4ecef2f13c790f95b55320f2925c205d8f971f Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Mon, 2 Aug 2010 15:48:23 +0800 Subject: ACPI, APEI, Rename CPER and GHES severity constants The abbreviation of severity should be SEV instead of SER, so the CPER severity constants are renamed accordingly. GHES severity constants are renamed in the same way too. Signed-off-by: Huang Ying Signed-off-by: Andi Kleen Signed-off-by: Len Brown --- include/linux/cper.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cper.h b/include/linux/cper.h index 4b38f905b705..bf972f81e2a7 100644 --- a/include/linux/cper.h +++ b/include/linux/cper.h @@ -39,10 +39,10 @@ * Severity difinition for error_severity in struct cper_record_header * and section_severity in struct cper_section_descriptor */ -#define CPER_SER_RECOVERABLE 0x0 -#define CPER_SER_FATAL 0x1 -#define CPER_SER_CORRECTED 0x2 -#define CPER_SER_INFORMATIONAL 0x3 +#define CPER_SEV_RECOVERABLE 0x0 +#define CPER_SEV_FATAL 0x1 +#define CPER_SEV_CORRECTED 0x2 +#define CPER_SEV_INFORMATIONAL 0x3 /* * Validation bits difinition for validation_bits in struct -- cgit v1.2.3 From a1452a3771c4eb85bd779790b040efdc36f4274e Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Sun, 8 Aug 2010 20:58:20 +0100 Subject: mtd: Update copyright notices Signed-off-by: David Woodhouse --- include/linux/mtd/bbm.h | 18 ++++++++++++++++-- include/linux/mtd/blktrans.h | 16 ++++++++++++++-- include/linux/mtd/cfi.h | 20 +++++++++++++++++--- include/linux/mtd/cfi_endian.h | 19 +++++++++++++++++++ include/linux/mtd/concat.h | 17 +++++++++++++++-- include/linux/mtd/doc2000.h | 23 ++++++++++++++++++----- include/linux/mtd/flashchip.h | 19 +++++++++++++++---- include/linux/mtd/gen_probe.h | 19 +++++++++++++++++-- include/linux/mtd/map.h | 18 ++++++++++++++++++ include/linux/mtd/mtd.h | 17 +++++++++++++++-- include/linux/mtd/nand.h | 6 +++--- include/linux/mtd/nand_ecc.h | 4 +++- include/linux/mtd/nftl.h | 17 ++++++++++++++++- 13 files changed, 186 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/bbm.h b/include/linux/mtd/bbm.h index a04b962492a8..7fa20beb2ab9 100644 --- a/include/linux/mtd/bbm.h +++ b/include/linux/mtd/bbm.h @@ -4,12 +4,26 @@ * NAND family Bad Block Management (BBM) header file * - Bad Block Table (BBT) implementation * - * Copyright (c) 2005 Samsung Electronics + * Copyright © 2005 Samsung Electronics * Kyungmin Park * - * Copyright (c) 2000-2005 + * Copyright © 2000-2005 * Thomas Gleixner * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + * */ #ifndef __LINUX_MTD_BBM_H #define __LINUX_MTD_BBM_H diff --git a/include/linux/mtd/blktrans.h b/include/linux/mtd/blktrans.h index b481ccd7ff3c..26529ebd59cc 100644 --- a/include/linux/mtd/blktrans.h +++ b/include/linux/mtd/blktrans.h @@ -1,7 +1,19 @@ /* - * (C) 2003 David Woodhouse + * Copyright © 2003-2010 David Woodhouse * - * Interface to Linux block layer for MTD 'translation layers'. + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA * */ diff --git a/include/linux/mtd/cfi.h b/include/linux/mtd/cfi.h index 574d9ee066f1..d2118b0eac9a 100644 --- a/include/linux/mtd/cfi.h +++ b/include/linux/mtd/cfi.h @@ -1,6 +1,20 @@ - -/* Common Flash Interface structures - * See http://support.intel.com/design/flash/technote/index.htm +/* + * Copyright © 2000-2010 David Woodhouse et al. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + * */ #ifndef __MTD_CFI_H__ diff --git a/include/linux/mtd/cfi_endian.h b/include/linux/mtd/cfi_endian.h index d802f7736be3..51cc3f5917a8 100644 --- a/include/linux/mtd/cfi_endian.h +++ b/include/linux/mtd/cfi_endian.h @@ -1,3 +1,22 @@ +/* + * Copyright © 2001-2010 David Woodhouse + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + * + */ + #include #ifndef CONFIG_MTD_CFI_ADV_OPTIONS diff --git a/include/linux/mtd/concat.h b/include/linux/mtd/concat.h index e80c674daeb3..ccdbe93a909c 100644 --- a/include/linux/mtd/concat.h +++ b/include/linux/mtd/concat.h @@ -1,9 +1,22 @@ /* * MTD device concatenation layer definitions * - * (C) 2002 Robert Kaiser + * Copyright © 2002 Robert Kaiser + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA * - * This code is GPL */ #ifndef MTD_CONCAT_H diff --git a/include/linux/mtd/doc2000.h b/include/linux/mtd/doc2000.h index 0a6d516ab71d..0f6fea73a1f6 100644 --- a/include/linux/mtd/doc2000.h +++ b/include/linux/mtd/doc2000.h @@ -1,12 +1,25 @@ /* * Linux driver for Disk-On-Chip devices * - * Copyright (C) 1999 Machine Vision Holdings, Inc. - * Copyright (C) 2001-2003 David Woodhouse - * Copyright (C) 2002-2003 Greg Ungerer - * Copyright (C) 2002-2003 SnapGear Inc + * Copyright © 1999 Machine Vision Holdings, Inc. + * Copyright © 1999-2010 David Woodhouse + * Copyright © 2002-2003 Greg Ungerer + * Copyright © 2002-2003 SnapGear Inc + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA * - * Released under GPL */ #ifndef __MTD_DOC2000_H__ diff --git a/include/linux/mtd/flashchip.h b/include/linux/mtd/flashchip.h index 23cc10f8e343..b63fa457febd 100644 --- a/include/linux/mtd/flashchip.h +++ b/include/linux/mtd/flashchip.h @@ -1,10 +1,21 @@ - /* - * struct flchip definition + * Copyright © 2000 Red Hat UK Limited + * Copyright © 2000-2010 David Woodhouse + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. * - * Contains information about the location and state of a given flash device + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA * - * (C) 2000 Red Hat. GPLd. */ #ifndef __MTD_FLASHCHIP_H__ diff --git a/include/linux/mtd/gen_probe.h b/include/linux/mtd/gen_probe.h index df362ddf2949..2c456054fded 100644 --- a/include/linux/mtd/gen_probe.h +++ b/include/linux/mtd/gen_probe.h @@ -1,6 +1,21 @@ /* - * (C) 2001, 2001 Red Hat, Inc. - * GPL'd + * Copyright © 2001 Red Hat UK Limited + * Copyright © 2001-2010 David Woodhouse + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + * */ #ifndef __LINUX_MTD_GEN_PROBE_H__ diff --git a/include/linux/mtd/map.h b/include/linux/mtd/map.h index de89eca864ce..eea3a4fb7405 100644 --- a/include/linux/mtd/map.h +++ b/include/linux/mtd/map.h @@ -1,3 +1,21 @@ +/* + * Copyright © 2000-2010 David Woodhouse et al. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + * + */ /* Overhauled routines for dealing with different mmap regions of flash */ diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index 43b7d72c6116..eae914e97f33 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -1,7 +1,20 @@ /* - * Copyright (C) 1999-2003 David Woodhouse et al. + * Copyright © 1999-2010 David Woodhouse et al. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA * - * Released under GPL */ #ifndef __MTD_MTD_H__ diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 50f3aa00a452..102e12c58cb3 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -1,9 +1,9 @@ /* * linux/include/linux/mtd/nand.h * - * Copyright (c) 2000 David Woodhouse - * Steven J. Hill - * Thomas Gleixner + * Copyright © 2000-2010 David Woodhouse + * Steven J. Hill + * Thomas Gleixner * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as diff --git a/include/linux/mtd/nand_ecc.h b/include/linux/mtd/nand_ecc.h index 41bc013571d0..4d8406c81652 100644 --- a/include/linux/mtd/nand_ecc.h +++ b/include/linux/mtd/nand_ecc.h @@ -1,7 +1,9 @@ /* * drivers/mtd/nand_ecc.h * - * Copyright (C) 2000 Steven J. Hill (sjhill@realitydiluted.com) + * Copyright (C) 2000-2010 Steven J. Hill + * David Woodhouse + * Thomas Gleixner * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as diff --git a/include/linux/mtd/nftl.h b/include/linux/mtd/nftl.h index dcaf611ed748..b059629e22bc 100644 --- a/include/linux/mtd/nftl.h +++ b/include/linux/mtd/nftl.h @@ -1,5 +1,20 @@ /* - * (C) 1999-2003 David Woodhouse + * Copyright © 1999-2010 David Woodhouse + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + * */ #ifndef __MTD_NFTL_H__ -- cgit v1.2.3 From 6ae0185fe201eae0548dace2a84acb5050fc8606 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Sun, 8 Aug 2010 21:19:42 +0100 Subject: mtd: Remove obsolete include Signed-off-by: David Woodhouse --- include/linux/mtd/compatmac.h | 10 ---------- include/linux/mtd/map.h | 1 - include/linux/mtd/mtd.h | 1 - 3 files changed, 12 deletions(-) delete mode 100644 include/linux/mtd/compatmac.h (limited to 'include/linux') diff --git a/include/linux/mtd/compatmac.h b/include/linux/mtd/compatmac.h deleted file mode 100644 index 7d1300d9bd51..000000000000 --- a/include/linux/mtd/compatmac.h +++ /dev/null @@ -1,10 +0,0 @@ - -#ifndef __LINUX_MTD_COMPATMAC_H__ -#define __LINUX_MTD_COMPATMAC_H__ - -/* Nothing to see here. We write 2.5-compatible code and this - file makes it all OK in older kernels, but it's empty in _current_ - kernels. Include guard just to make GCC ignore it in future inclusions - anyway... */ - -#endif /* __LINUX_MTD_COMPATMAC_H__ */ diff --git a/include/linux/mtd/map.h b/include/linux/mtd/map.h index eea3a4fb7405..a9e6ba46865e 100644 --- a/include/linux/mtd/map.h +++ b/include/linux/mtd/map.h @@ -27,7 +27,6 @@ #include #include -#include #include #include diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index eae914e97f33..8485e42a9b09 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -26,7 +26,6 @@ #include #include -#include #include #include -- cgit v1.2.3 From c9243f5bdd6637b2bb7dc254b54d9edf957ef17e Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sun, 4 Jul 2010 00:15:07 +0200 Subject: autofs/autofs4: Move compat_ioctl handling into fs Handling of autofs ioctl numbers does not need to be generic and can easily be done directly in autofs itself. This also pushes the BKL into autofs and autofs4 ioctl methods. Signed-off-by: Arnd Bergmann Acked-by: H. Peter Anvin Cc: Al Viro Cc: Ian Kent Cc: Autofs Cc: John Kacur Signed-off-by: Frederic Weisbecker --- include/linux/auto_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/auto_fs.h b/include/linux/auto_fs.h index 7b09c8348fd3..da64e15004b6 100644 --- a/include/linux/auto_fs.h +++ b/include/linux/auto_fs.h @@ -79,6 +79,7 @@ struct autofs_packet_expire { #define AUTOFS_IOC_FAIL _IO(0x93,0x61) #define AUTOFS_IOC_CATATONIC _IO(0x93,0x62) #define AUTOFS_IOC_PROTOVER _IOR(0x93,0x63,int) +#define AUTOFS_IOC_SETTIMEOUT32 _IOWR(0x93,0x64,compat_ulong_t) #define AUTOFS_IOC_SETTIMEOUT _IOWR(0x93,0x64,unsigned long) #define AUTOFS_IOC_EXPIRE _IOR(0x93,0x65,struct autofs_packet_expire) -- cgit v1.2.3 From 5fd8f7388c9a8601c2dbe0da458df602fe427e83 Mon Sep 17 00:00:00 2001 From: Sylwester Nawrocki Date: Tue, 3 Aug 2010 09:50:29 -0300 Subject: V4L/DVB: v4l: Add driver for Samsung S5P SoC video postprocessor This driver exports a video device node per each camera interface/ video postprocessor (FIMC) device contained in Samsung S5P SoC series. The driver is based on v4l2-mem2mem framework. Signed-off-by: Sylwester Nawrocki Signed-off-by: Kyungmin Park Signed-off-by: Pawel Osciak Signed-off-by: Mauro Carvalho Chehab --- include/linux/videodev2.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index 047f7e6edb86..61490c6dcdbd 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -277,6 +277,7 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_RGB565 v4l2_fourcc('R', 'G', 'B', 'P') /* 16 RGB-5-6-5 */ #define V4L2_PIX_FMT_RGB555X v4l2_fourcc('R', 'G', 'B', 'Q') /* 16 RGB-5-5-5 BE */ #define V4L2_PIX_FMT_RGB565X v4l2_fourcc('R', 'G', 'B', 'R') /* 16 RGB-5-6-5 BE */ +#define V4L2_PIX_FMT_BGR666 v4l2_fourcc('B', 'G', 'R', 'H') /* 18 BGR-6-6-6 */ #define V4L2_PIX_FMT_BGR24 v4l2_fourcc('B', 'G', 'R', '3') /* 24 BGR-8-8-8 */ #define V4L2_PIX_FMT_RGB24 v4l2_fourcc('R', 'G', 'B', '3') /* 24 RGB-8-8-8 */ #define V4L2_PIX_FMT_BGR32 v4l2_fourcc('B', 'G', 'R', '4') /* 32 BGR-8-8-8-8 */ -- cgit v1.2.3 From 1b5ad24878b7e5a543b98c5d2f8c0d8c0dd3088f Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Sat, 7 Aug 2010 14:29:22 +0200 Subject: slub: add missing __percpu markup in mm/slub_def.h kmem_cache->cpu_slab is a percpu pointer but was missing __percpu markup. Add it. Signed-off-by: Namhyung Kim Acked-by: Tejun Heo Signed-off-by: Pekka Enberg --- include/linux/slub_def.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 6447a723ecb1..5ec4bc0e45aa 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -68,7 +68,7 @@ struct kmem_cache_order_objects { * Slab cache management. */ struct kmem_cache { - struct kmem_cache_cpu *cpu_slab; + struct kmem_cache_cpu __percpu *cpu_slab; /* Used for retriving partial slabs etc */ unsigned long flags; int size; /* The size of an object including meta data */ -- cgit v1.2.3 From 0e4f6a791b1e8cfde75a74e2f885642ecb3fe9d8 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 4 Jul 2010 12:18:57 +0400 Subject: Fix reiserfs_file_release() a) count file openers correctly; i_count use was completely wrong b) use new mutex for exclusion between final close/open/truncate, to protect tailpacking logics. i_mutex use was wrong and resulted in deadlocks. Signed-off-by: Al Viro --- include/linux/reiserfs_fs_i.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/reiserfs_fs_i.h b/include/linux/reiserfs_fs_i.h index 89f4d3abbf5a..97959bdfe214 100644 --- a/include/linux/reiserfs_fs_i.h +++ b/include/linux/reiserfs_fs_i.h @@ -25,7 +25,6 @@ typedef enum { i_link_saved_truncate_mask = 0x0020, i_has_xattr_dir = 0x0040, i_data_log = 0x0080, - i_ever_mapped = 0x0100 } reiserfs_inode_flags; struct reiserfs_inode_info { @@ -53,7 +52,8 @@ struct reiserfs_inode_info { ** flushed */ unsigned int i_trans_id; struct reiserfs_journal_list *i_jl; - struct mutex i_mmap; + atomic_t openers; + struct mutex tailpack; #ifdef CONFIG_REISERFS_FS_XATTR struct rw_semaphore i_xattr_sem; #endif -- cgit v1.2.3 From eafdc7d190a944c755a9fe68573c193e6e0217e7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 4 Jun 2010 11:29:53 +0200 Subject: sort out blockdev_direct_IO variants Move the call to vmtruncate to get rid of accessive blocks to the callers in prepearation of the new truncate calling sequence. This was only done for DIO_LOCKING filesystems, so the __blockdev_direct_IO_newtrunc variant was not needed anyway. Get rid of blockdev_direct_IO_no_locking and its _newtrunc variant while at it as just opencoding the two additional paramters is shorted than the name suffix. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/fs.h | 42 ++++++------------------------------------ 1 file changed, 6 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index f91affb7d530..b347b2d5666f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2269,16 +2269,6 @@ static inline int xip_truncate_page(struct address_space *mapping, loff_t from) struct bio; typedef void (dio_submit_t)(int rw, struct bio *bio, struct inode *inode, loff_t file_offset); -void dio_end_io(struct bio *bio, int error); - -ssize_t __blockdev_direct_IO_newtrunc(int rw, struct kiocb *iocb, struct inode *inode, - struct block_device *bdev, const struct iovec *iov, loff_t offset, - unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io, - dio_submit_t submit_io, int lock_type); -ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, - struct block_device *bdev, const struct iovec *iov, loff_t offset, - unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io, - dio_submit_t submit_io, int lock_type); enum { /* need locking between buffered and direct access */ @@ -2288,24 +2278,13 @@ enum { DIO_SKIP_HOLES = 0x02, }; -static inline ssize_t blockdev_direct_IO_newtrunc(int rw, struct kiocb *iocb, - struct inode *inode, struct block_device *bdev, const struct iovec *iov, - loff_t offset, unsigned long nr_segs, get_block_t get_block, - dio_iodone_t end_io) -{ - return __blockdev_direct_IO_newtrunc(rw, iocb, inode, bdev, iov, offset, - nr_segs, get_block, end_io, NULL, - DIO_LOCKING | DIO_SKIP_HOLES); -} +void dio_end_io(struct bio *bio, int error); + +ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, + struct block_device *bdev, const struct iovec *iov, loff_t offset, + unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io, + dio_submit_t submit_io, int flags); -static inline ssize_t blockdev_direct_IO_no_locking_newtrunc(int rw, struct kiocb *iocb, - struct inode *inode, struct block_device *bdev, const struct iovec *iov, - loff_t offset, unsigned long nr_segs, get_block_t get_block, - dio_iodone_t end_io) -{ - return __blockdev_direct_IO_newtrunc(rw, iocb, inode, bdev, iov, offset, - nr_segs, get_block, end_io, NULL, 0); -} static inline ssize_t blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, struct block_device *bdev, const struct iovec *iov, loff_t offset, unsigned long nr_segs, get_block_t get_block, @@ -2315,15 +2294,6 @@ static inline ssize_t blockdev_direct_IO(int rw, struct kiocb *iocb, nr_segs, get_block, end_io, NULL, DIO_LOCKING | DIO_SKIP_HOLES); } - -static inline ssize_t blockdev_direct_IO_no_locking(int rw, struct kiocb *iocb, - struct inode *inode, struct block_device *bdev, const struct iovec *iov, - loff_t offset, unsigned long nr_segs, get_block_t get_block, - dio_iodone_t end_io) -{ - return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset, - nr_segs, get_block, end_io, NULL, 0); -} #endif extern const struct file_operations generic_ro_fops; -- cgit v1.2.3 From ea0f04e59543bafb3d2cbe37a0d375acb0bb2c34 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 4 Jun 2010 11:29:54 +0200 Subject: get rid of nobh_write_begin_newtrunc Move the call to vmtruncate to get rid of accessive blocks to the only remaining caller and rename the non-truncating version to nobh_write_begin. Get rid of the superflous file argument to it while we're at it. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/buffer_head.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 1b9ba193b789..cfda5f0b2a4b 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -231,11 +231,7 @@ void block_sync_page(struct page *); sector_t generic_block_bmap(struct address_space *, sector_t, get_block_t *); int block_truncate_page(struct address_space *, loff_t, get_block_t *); int file_fsync(struct file *, int); -int nobh_write_begin_newtrunc(struct file *, struct address_space *, - loff_t, unsigned, unsigned, - struct page **, void **, get_block_t*); -int nobh_write_begin(struct file *, struct address_space *, - loff_t, unsigned, unsigned, +int nobh_write_begin(struct address_space *, loff_t, unsigned, unsigned, struct page **, void **, get_block_t*); int nobh_write_end(struct file *, struct address_space *, loff_t, unsigned, unsigned, -- cgit v1.2.3 From 282dc178849882289d30e58b54be6b2799b351aa Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 4 Jun 2010 11:29:55 +0200 Subject: get rid of cont_write_begin_newtrunc Move the call to vmtruncate to get rid of accessive blocks to the callers in preparation of the new truncate sequence and rename the non-truncating version to cont_write_begin. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/buffer_head.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index cfda5f0b2a4b..7638647f0424 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -217,9 +217,6 @@ int generic_write_end(struct file *, struct address_space *, struct page *, void *); void page_zero_new_buffers(struct page *page, unsigned from, unsigned to); int block_prepare_write(struct page*, unsigned, unsigned, get_block_t*); -int cont_write_begin_newtrunc(struct file *, struct address_space *, loff_t, - unsigned, unsigned, struct page **, void **, - get_block_t *, loff_t *); int cont_write_begin(struct file *, struct address_space *, loff_t, unsigned, unsigned, struct page **, void **, get_block_t *, loff_t *); -- cgit v1.2.3 From 6e1db88d536adcbbfe562b2d4b7d6425784fff12 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 4 Jun 2010 11:29:57 +0200 Subject: introduce __block_write_begin Split up the block_write_begin implementation - __block_write_begin is a new trivial wrapper for block_prepare_write that always takes an already allocated page and can be either called from block_write_begin or filesystem code that already has a page allocated. Remove the handling of already allocated pages from block_write_begin after switching all callers that do it to __block_write_begin. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/buffer_head.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 7638647f0424..accc9f81bb63 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -209,6 +209,8 @@ int block_write_begin_newtrunc(struct file *, struct address_space *, int block_write_begin(struct file *, struct address_space *, loff_t, unsigned, unsigned, struct page **, void **, get_block_t*); +int __block_write_begin(struct page *page, loff_t pos, unsigned len, + get_block_t *get_block); int block_write_end(struct file *, struct address_space *, loff_t, unsigned, unsigned, struct page *, void *); -- cgit v1.2.3 From 155130a4f7848b1aac439cab6bda1a175507c71c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 4 Jun 2010 11:29:58 +0200 Subject: get rid of block_write_begin_newtrunc Move the call to vmtruncate to get rid of accessive blocks to the callers in preparation of the new truncate sequence and rename the non-truncating version to block_write_begin. While we're at it also remove several unused arguments to block_write_begin. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/buffer_head.h | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index accc9f81bb63..3f69054f86d9 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -203,12 +203,8 @@ int block_write_full_page_endio(struct page *page, get_block_t *get_block, int block_read_full_page(struct page*, get_block_t*); int block_is_partially_uptodate(struct page *page, read_descriptor_t *desc, unsigned long from); -int block_write_begin_newtrunc(struct file *, struct address_space *, - loff_t, unsigned, unsigned, - struct page **, void **, get_block_t*); -int block_write_begin(struct file *, struct address_space *, - loff_t, unsigned, unsigned, - struct page **, void **, get_block_t*); +int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len, + unsigned flags, struct page **pagep, get_block_t *get_block); int __block_write_begin(struct page *page, loff_t pos, unsigned len, get_block_t *get_block); int block_write_end(struct file *, struct address_space *, -- cgit v1.2.3 From 6a1a90ad1b0edb556a7550a6ef8a8756f0304dd5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 4 Jun 2010 11:30:00 +0200 Subject: rename generic_setattr Despite its name it's now a generic implementation of ->setattr, but rather a helper to copy attributes from a struct iattr to the inode. Rename it to setattr_copy to reflect this fact. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index b347b2d5666f..8ebb5f01a418 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2393,7 +2393,7 @@ extern int buffer_migrate_page(struct address_space *, extern int inode_change_ok(const struct inode *, struct iattr *); extern int inode_newsize_ok(const struct inode *, loff_t offset); extern int __must_check inode_setattr(struct inode *, const struct iattr *); -extern void generic_setattr(struct inode *inode, const struct iattr *attr); +extern void setattr_copy(struct inode *inode, const struct iattr *attr); extern void file_update_time(struct file *file); -- cgit v1.2.3 From 1025774ce411f2bd4b059ad7b53f0003569b74fa Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 4 Jun 2010 11:30:02 +0200 Subject: remove inode_setattr Replace inode_setattr with opencoded variants of it in all callers. This moves the remaining call to vmtruncate into the filesystem methods where it can be replaced with the proper truncate sequence. In a few cases it was obvious that we would never end up calling vmtruncate so it was left out in the opencoded variant: spufs: explicitly checks for ATTR_SIZE earlier btrfs,hugetlbfs,logfs,dlmfs: explicitly clears ATTR_SIZE earlier ufs: contains an opencoded simple_seattr + truncate that sets the filesize just above In addition to that ncpfs called inode_setattr with handcrafted iattrs, which allowed to trim down the opencoded variant. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 8ebb5f01a418..6ecb83c00a6d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2392,7 +2392,6 @@ extern int buffer_migrate_page(struct address_space *, extern int inode_change_ok(const struct inode *, struct iattr *); extern int inode_newsize_ok(const struct inode *, loff_t offset); -extern int __must_check inode_setattr(struct inode *, const struct iattr *); extern void setattr_copy(struct inode *inode, const struct iattr *attr); extern void file_update_time(struct file *file); -- cgit v1.2.3 From 2c27c65ed0696f0b5df2dad2cf6462d72164d547 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 4 Jun 2010 11:30:04 +0200 Subject: check ATTR_SIZE contraints in inode_change_ok Make sure we check the truncate constraints early on in ->setattr by adding those checks to inode_change_ok. Also clean up and document inode_change_ok to make this obvious. As a fallout we don't have to call inode_newsize_ok from simple_setsize and simplify it down to a truncate_setsize which doesn't return an error. This simplifies a lot of setattr implementations and means we use truncate_setsize almost everywhere. Get rid of fat_setsize now that it's trivial and mark ext2_setsize static to make the calling convention obvious. Keep the inode_newsize_ok in vmtruncate for now as all callers need an audit for its removal anyway. Note: setattr code in ecryptfs doesn't call inode_change_ok at all and needs a deeper audit, but that is left for later. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/fs.h | 1 - include/linux/mm.h | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 6ecb83c00a6d..5547b1b027db 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2355,7 +2355,6 @@ extern int simple_link(struct dentry *, struct inode *, struct dentry *); extern int simple_unlink(struct inode *, struct dentry *); extern int simple_rmdir(struct inode *, struct dentry *); extern int simple_rename(struct inode *, struct dentry *, struct inode *, struct dentry *); -extern int simple_setsize(struct inode *, loff_t); extern int noop_fsync(struct file *, int); extern int simple_empty(struct dentry *); extern int simple_readpage(struct file *file, struct page *page); diff --git a/include/linux/mm.h b/include/linux/mm.h index a2b48041b910..980164ea10ee 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -815,6 +815,7 @@ static inline void unmap_shared_mapping_range(struct address_space *mapping, } extern void truncate_pagecache(struct inode *inode, loff_t old, loff_t new); +extern void truncate_setsize(struct inode *inode, loff_t newsize); extern int vmtruncate(struct inode *inode, loff_t offset); extern int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end); -- cgit v1.2.3 From b5fc510c48f631882ccec3c0f02a25d5b67de09f Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 4 Jul 2010 12:24:09 +0400 Subject: get rid of file_fsync() Copy and simplify in the only two users remaining. Signed-off-by: Al Viro --- include/linux/buffer_head.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 3f69054f86d9..620f1d1088cb 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -225,7 +225,6 @@ int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, void block_sync_page(struct page *); sector_t generic_block_bmap(struct address_space *, sector_t, get_block_t *); int block_truncate_page(struct address_space *, loff_t, get_block_t *); -int file_fsync(struct file *, int); int nobh_write_begin(struct address_space *, loff_t, unsigned, unsigned, struct page **, void **, get_block_t*); int nobh_write_end(struct file *, struct address_space *, -- cgit v1.2.3 From a4ffdde6e56fdf8c34ddadc2674d6eb978083369 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 2 Jun 2010 17:38:30 -0400 Subject: simplify checks for I_CLEAR/I_FREEING add I_CLEAR instead of replacing I_FREEING with it. I_CLEAR is equivalent to I_FREEING for almost all code looking at either; it's there to keep track of having called clear_inode() exactly once per inode lifetime, at some point after having set I_FREEING. I_CLEAR and I_FREEING never get set at the same time with the current code, so we can switch to setting i_flags to I_FREEING | I_CLEAR instead of I_CLEAR without loss of information. As the result of such change, checks become simpler and the amount of code that needs to know about I_CLEAR shrinks a lot. Signed-off-by: Al Viro --- include/linux/fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 5547b1b027db..218693d8d446 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1616,8 +1616,8 @@ struct super_operations { * I_FREEING Set when inode is about to be freed but still has dirty * pages or buffers attached or the inode itself is still * dirty. - * I_CLEAR Set by clear_inode(). In this state the inode is clean - * and can be destroyed. + * I_CLEAR Added by clear_inode(). In this state the inode is clean + * and can be destroyed. Inode keeps I_FREEING. * * Inodes that are I_WILL_FREE, I_FREEING or I_CLEAR are * prohibited for many purposes. iget() must wait for -- cgit v1.2.3 From be7ce4161f9e6bf2497f90337d1214aa6ee06e15 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 4 Jun 2010 19:40:39 -0400 Subject: New method - evict_inode() Hybrid of ->clear_inode() and ->delete_inode(); if present, does all fs work to be done when in-core inode is about to be gone, for whatever reason. Signed-off-by: Al Viro --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 218693d8d446..ce50be4b0b41 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1563,6 +1563,7 @@ struct super_operations { void (*dirty_inode) (struct inode *); int (*write_inode) (struct inode *, struct writeback_control *wbc); void (*drop_inode) (struct inode *); + void (*evict_inode) (struct inode *); void (*delete_inode) (struct inode *); void (*put_super) (struct super_block *); void (*write_super) (struct super_block *); -- cgit v1.2.3 From c6287315cb958e740466555ca5e9d007f25b39bd Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 4 Jun 2010 19:56:17 -0400 Subject: generic_detach_inode() can be static now Signed-off-by: Al Viro --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index ce50be4b0b41..e0ecb8e75ebf 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2167,7 +2167,6 @@ extern ino_t iunique(struct super_block *, ino_t); extern int inode_needs_sync(struct inode *inode); extern void generic_delete_inode(struct inode *inode); extern void generic_drop_inode(struct inode *inode); -extern int generic_detach_inode(struct inode *inode); extern struct inode *ilookup5_nowait(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), -- cgit v1.2.3 From b0683aa638b3326c6fc22e5290dfa75e08bd83f5 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 4 Jun 2010 20:55:25 -0400 Subject: new helper: end_writeback() Essentially, the minimal variant of ->evict_inode(). It's a trimmed-down clear_inode(), sans any fs callbacks. Once it returns we know that no async writeback will be happening; every ->evict_inode() instance should do that once and do that before doing anything ->write_inode() could interfere with (e.g. freeing the on-disk inode). Signed-off-by: Al Viro --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index e0ecb8e75ebf..3c23c1dcb1bd 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2184,6 +2184,7 @@ extern void unlock_new_inode(struct inode *); extern void __iget(struct inode * inode); extern void iget_failed(struct inode *); extern void clear_inode(struct inode *); +extern void end_writeback(struct inode *); extern void destroy_inode(struct inode *); extern void __destroy_inode(struct inode *); extern struct inode *new_inode(struct super_block *); -- cgit v1.2.3 From ac14a95b5239d37b6082c3791b88d7ab4e8e444c Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 6 Jun 2010 07:08:19 -0400 Subject: convert ext3 to ->evict_inode() Signed-off-by: Al Viro --- include/linux/ext3_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h index 7fc62d4550b2..e7cb21766992 100644 --- a/include/linux/ext3_fs.h +++ b/include/linux/ext3_fs.h @@ -896,7 +896,7 @@ int ext3_get_blocks_handle(handle_t *handle, struct inode *inode, extern struct inode *ext3_iget(struct super_block *, unsigned long); extern int ext3_write_inode (struct inode *, struct writeback_control *); extern int ext3_setattr (struct dentry *, struct iattr *); -extern void ext3_delete_inode (struct inode *); +extern void ext3_evict_inode (struct inode *); extern int ext3_sync_inode (handle_t *, struct inode *); extern void ext3_discard_reservation (struct inode *); extern void ext3_dirty_inode(struct inode *); -- cgit v1.2.3 From c103135c14e03fc9a9e5f0adc01df9ad272cf2a1 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 6 Jun 2010 22:31:14 -0400 Subject: new helper: __dentry_path() builds path relative to fs root, called under dcache_lock, doesn't append any nonsense to unlinked ones. Signed-off-by: Al Viro --- include/linux/dcache.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index eebb617c17d8..d23be0386e2d 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -315,6 +315,7 @@ extern char *dynamic_dname(struct dentry *, char *, int, const char *, ...); extern char *__d_path(const struct path *path, struct path *root, char *, int); extern char *d_path(const struct path *, char *, int); +extern char *__dentry_path(struct dentry *, char *, int); extern char *dentry_path(struct dentry *, char *, int); /* Allocation counts.. */ -- cgit v1.2.3 From 845a2cc0507055278e0fa722ed0f8c791b7401dd Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 7 Jun 2010 11:37:37 -0400 Subject: convert reiserfs to ->evict_inode() Signed-off-by: Al Viro --- include/linux/reiserfs_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index 3b603f474186..2a464ae147ce 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -2033,7 +2033,7 @@ void reiserfs_read_locked_inode(struct inode *inode, struct reiserfs_iget_args *args); int reiserfs_find_actor(struct inode *inode, void *p); int reiserfs_init_locked_inode(struct inode *inode, void *p); -void reiserfs_delete_inode(struct inode *inode); +void reiserfs_evict_inode(struct inode *inode); int reiserfs_write_inode(struct inode *inode, struct writeback_control *wbc); int reiserfs_get_block(struct inode *inode, sector_t block, struct buffer_head *bh_result, int create); -- cgit v1.2.3 From 07958f9f5b9e8422c15368a1733a52ea99009896 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 7 Jun 2010 13:20:09 -0400 Subject: ->delete_inode() is gone Signed-off-by: Al Viro --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 3c23c1dcb1bd..2b1254771e46 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1564,7 +1564,6 @@ struct super_operations { int (*write_inode) (struct inode *, struct writeback_control *wbc); void (*drop_inode) (struct inode *); void (*evict_inode) (struct inode *); - void (*delete_inode) (struct inode *); void (*put_super) (struct super_block *); void (*write_super) (struct super_block *); int (*sync_fs)(struct super_block *sb, int wait); -- cgit v1.2.3 From 30140837f256558c943636245ab90897a9455a70 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 7 Jun 2010 13:23:20 -0400 Subject: fs/inode.c:clear_inode() is gone Signed-off-by: Al Viro --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 2b1254771e46..4eaa6b2e35db 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2182,7 +2182,6 @@ extern void unlock_new_inode(struct inode *); extern void __iget(struct inode * inode); extern void iget_failed(struct inode *); -extern void clear_inode(struct inode *); extern void end_writeback(struct inode *); extern void destroy_inode(struct inode *); extern void __destroy_inode(struct inode *); -- cgit v1.2.3 From 45321ac54316eaeeebde0b5f728a1791e500974c Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 7 Jun 2010 13:43:19 -0400 Subject: Make ->drop_inode() just return whether inode needs to be dropped ... and let iput_final() do the actual eviction or retention Signed-off-by: Al Viro --- include/linux/fs.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 4eaa6b2e35db..8553adbda57b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1562,7 +1562,7 @@ struct super_operations { void (*dirty_inode) (struct inode *); int (*write_inode) (struct inode *, struct writeback_control *wbc); - void (*drop_inode) (struct inode *); + int (*drop_inode) (struct inode *); void (*evict_inode) (struct inode *); void (*put_super) (struct super_block *); void (*write_super) (struct super_block *); @@ -2164,8 +2164,8 @@ extern void iput(struct inode *); extern struct inode * igrab(struct inode *); extern ino_t iunique(struct super_block *, ino_t); extern int inode_needs_sync(struct inode *inode); -extern void generic_delete_inode(struct inode *inode); -extern void generic_drop_inode(struct inode *inode); +extern int generic_delete_inode(struct inode *inode); +extern int generic_drop_inode(struct inode *inode); extern struct inode *ilookup5_nowait(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), -- cgit v1.2.3 From b57922d97fd6f79b6dbe6db0c4fd30d219fa08c1 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 7 Jun 2010 14:34:48 -0400 Subject: convert remaining ->clear_inode() to ->evict_inode() Signed-off-by: Al Viro --- include/linux/fs.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 8553adbda57b..dec9ac598859 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1571,7 +1571,6 @@ struct super_operations { int (*unfreeze_fs) (struct super_block *); int (*statfs) (struct dentry *, struct kstatfs *); int (*remount_fs) (struct super_block *, int *, char *); - void (*clear_inode) (struct inode *); void (*umount_begin) (struct super_block *); int (*show_options)(struct seq_file *, struct vfsmount *); @@ -1616,7 +1615,7 @@ struct super_operations { * I_FREEING Set when inode is about to be freed but still has dirty * pages or buffers attached or the inode itself is still * dirty. - * I_CLEAR Added by clear_inode(). In this state the inode is clean + * I_CLEAR Added by end_writeback(). In this state the inode is clean * and can be destroyed. Inode keeps I_FREEING. * * Inodes that are I_WILL_FREE, I_FREEING or I_CLEAR are -- cgit v1.2.3 From ebabe9a9001af0af56c0c2780ca1576246e7a74b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 7 Jul 2010 18:53:11 +0200 Subject: pass a struct path to vfs_statfs We'll need the path to implement the flags field for statvfs support. We do have it available in all callers except: - ecryptfs_statfs. This one doesn't actually need vfs_statfs but just needs to do a caller to the lower filesystem statfs method. - sys_ustat. Add a non-exported statfs_by_dentry helper for it which doesn't won't be able to fill out the flags field later on. In addition rename the helpers for statfs vs fstatfs to do_*statfs instead of the misleading vfs prefix. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/fs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index dec9ac598859..9bedf4219f83 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1813,7 +1813,8 @@ extern struct vfsmount *collect_mounts(struct path *); extern void drop_collected_mounts(struct vfsmount *); extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *, struct vfsmount *); -extern int vfs_statfs(struct dentry *, struct kstatfs *); +extern int vfs_statfs(struct path *, struct kstatfs *); +extern int statfs_by_dentry(struct dentry *, struct kstatfs *); extern int freeze_super(struct super_block *super); extern int thaw_super(struct super_block *super); -- cgit v1.2.3 From 365b18189789bfa1acd9939e6312b8a4b4577b28 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 7 Jul 2010 18:53:25 +0200 Subject: add f_flags to struct statfs(64) Add a flags field to help glibc implementing statvfs(3) efficiently. We copy the flag values from glibc, and add a new ST_VALID flag to denote that f_flags is implemented. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/statfs.h | 25 +++++++++++++++++++++++-- 1 file changed, 23 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/statfs.h b/include/linux/statfs.h index b34cc829f98d..0166d320a75d 100644 --- a/include/linux/statfs.h +++ b/include/linux/statfs.h @@ -2,7 +2,6 @@ #define _LINUX_STATFS_H #include - #include struct kstatfs { @@ -16,7 +15,29 @@ struct kstatfs { __kernel_fsid_t f_fsid; long f_namelen; long f_frsize; - long f_spare[5]; + long f_flags; + long f_spare[4]; }; +/* + * Definitions for the flag in f_flag. + * + * Generally these flags are equivalent to the MS_ flags used in the mount + * ABI. The exception is ST_VALID which has the same value as MS_REMOUNT + * which doesn't make any sense for statfs. + */ +#define ST_RDONLY 0x0001 /* mount read-only */ +#define ST_NOSUID 0x0002 /* ignore suid and sgid bits */ +#define ST_NODEV 0x0004 /* disallow access to device special files */ +#define ST_NOEXEC 0x0008 /* disallow program execution */ +#define ST_SYNCHRONOUS 0x0010 /* writes are synced at once */ +#define ST_VALID 0x0020 /* f_flags support is implemented */ +#define ST_MANDLOCK 0x0040 /* allow mandatory locks on an FS */ +/* 0x0080 used for ST_WRITE in glibc */ +/* 0x0100 used for ST_APPEND in glibc */ +/* 0x0200 used for ST_IMMUTABLE in glibc */ +#define ST_NOATIME 0x0400 /* do not update access times */ +#define ST_NODIRATIME 0x0800 /* do not update directory access times */ +#define ST_RELATIME 0x1000 /* update atime relative to mtime/ctime */ + #endif -- cgit v1.2.3 From 2aec7c523291621ebb68ba8e0bd9b52a26bb76ee Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Mon, 19 Jul 2010 18:19:41 +0200 Subject: mbcache: Remove unused features The mbcache code was written to support a variable number of indexes, but all the existing users use exactly one index. Simplify to code to support only that case. There are also no users of the cache entry free operation, and none of the users keep extra data in cache entries. Remove those features as well. Signed-off-by: Andreas Gruenbacher Signed-off-by: Al Viro --- include/linux/mbcache.h | 20 +++++--------------- 1 file changed, 5 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mbcache.h b/include/linux/mbcache.h index a09b84e4fdb4..54cbbac1e71d 100644 --- a/include/linux/mbcache.h +++ b/include/linux/mbcache.h @@ -4,9 +4,6 @@ (C) 2001 by Andreas Gruenbacher, */ -/* Hardwire the number of additional indexes */ -#define MB_CACHE_INDEXES_COUNT 1 - struct mb_cache_entry { struct list_head e_lru_list; struct mb_cache *e_cache; @@ -18,17 +15,12 @@ struct mb_cache_entry { struct { struct list_head o_list; unsigned int o_key; - } e_indexes[0]; -}; - -struct mb_cache_op { - int (*free)(struct mb_cache_entry *, gfp_t); + } e_index; }; /* Functions on caches */ -struct mb_cache * mb_cache_create(const char *, struct mb_cache_op *, size_t, - int, int); +struct mb_cache *mb_cache_create(const char *, int); void mb_cache_shrink(struct block_device *); void mb_cache_destroy(struct mb_cache *); @@ -36,17 +28,15 @@ void mb_cache_destroy(struct mb_cache *); struct mb_cache_entry *mb_cache_entry_alloc(struct mb_cache *, gfp_t); int mb_cache_entry_insert(struct mb_cache_entry *, struct block_device *, - sector_t, unsigned int[]); + sector_t, unsigned int); void mb_cache_entry_release(struct mb_cache_entry *); void mb_cache_entry_free(struct mb_cache_entry *); struct mb_cache_entry *mb_cache_entry_get(struct mb_cache *, struct block_device *, sector_t); -#if !defined(MB_CACHE_INDEXES_COUNT) || (MB_CACHE_INDEXES_COUNT > 0) -struct mb_cache_entry *mb_cache_entry_find_first(struct mb_cache *cache, int, +struct mb_cache_entry *mb_cache_entry_find_first(struct mb_cache *cache, struct block_device *, unsigned int); -struct mb_cache_entry *mb_cache_entry_find_next(struct mb_cache_entry *, int, +struct mb_cache_entry *mb_cache_entry_find_next(struct mb_cache_entry *, struct block_device *, unsigned int); -#endif -- cgit v1.2.3 From 7a4dec53897ecd3367efb1e12fe8a4edc47dc0e9 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 9 Aug 2010 12:05:43 -0400 Subject: Fix sget() race with failing mount If sget() finds a matching superblock being set up, it'll grab an active reference to it and grab s_umount. That's fine - we'll wait for completion of foofs_get_sb() that way. However, if said foofs_get_sb() fails we'll end up holding the halfway-created superblock. deactivate_locked_super() called by foofs_get_sb() will just unlock the sucker since we are holding another active reference to it. What we need is a way to tell if superblock has been successfully set up. Unfortunately, neither ->s_root nor the check for MS_ACTIVE quite fit. Cheap and easy way, suitable for backport: new flag set by the (only) caller of ->get_sb(). If that flag isn't present by the time sget() grabbed s_umount on preexisting superblock it has found, it's seeing a stillborn and should just bury it with deactivate_locked_super() (and repeat the search). Longer term we want to set that flag in ->get_sb() instances (and check for it to distinguish between "sget() found us a live sb" and "sget() has allocated an sb, we need to set it up" in there, instead of checking ->s_root as we do now). Signed-off-by: Al Viro Cc: stable@kernel.org --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 9bedf4219f83..58e4b035e282 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -209,6 +209,7 @@ struct inodes_stat_t { #define MS_KERNMOUNT (1<<22) /* this is a kern_mount call */ #define MS_I_VERSION (1<<23) /* Update inode I_version field */ #define MS_STRICTATIME (1<<24) /* Always perform atime updates */ +#define MS_BORN (1<<29) #define MS_ACTIVE (1<<30) #define MS_NOUSER (1<<31) -- cgit v1.2.3 From 597781f3e51f48ef8e67be772196d9e9673752c4 Mon Sep 17 00:00:00 2001 From: Cesar Eduardo Barros Date: Mon, 9 Aug 2010 17:18:32 -0700 Subject: kmap_atomic: make kunmap_atomic() harder to misuse kunmap_atomic() is currently at level -4 on Rusty's "Hard To Misuse" list[1] ("Follow common convention and you'll get it wrong"), except in some architectures when CONFIG_DEBUG_HIGHMEM is set[2][3]. kunmap() takes a pointer to a struct page; kunmap_atomic(), however, takes takes a pointer to within the page itself. This seems to once in a while trip people up (the convention they are following is the one from kunmap()). Make it much harder to misuse, by moving it to level 9 on Rusty's list[4] ("The compiler/linker won't let you get it wrong"). This is done by refusing to build if the type of its first argument is a pointer to a struct page. The real kunmap_atomic() is renamed to kunmap_atomic_notypecheck() (which is what you would call in case for some strange reason calling it with a pointer to a struct page is not incorrect in your code). The previous version of this patch was compile tested on x86-64. [1] http://ozlabs.org/~rusty/index.cgi/tech/2008-04-01.html [2] In these cases, it is at level 5, "Do it right or it will always break at runtime." [3] At least mips and powerpc look very similar, and sparc also seems to share a common ancestor with both; there seems to be quite some degree of copy-and-paste coding here. The include/asm/highmem.h file for these three archs mention x86 CPUs at its top. [4] http://ozlabs.org/~rusty/index.cgi/tech/2008-03-30.html [5] As an aside, could someone tell me why mn10300 uses unsigned long as the first parameter of kunmap_atomic() instead of void *? Signed-off-by: Cesar Eduardo Barros Cc: Russell King (arch/arm) Cc: Ralf Baechle (arch/mips) Cc: David Howells (arch/frv, arch/mn10300) Cc: Koichi Yasutake (arch/mn10300) Cc: Kyle McMartin (arch/parisc) Cc: Helge Deller (arch/parisc) Cc: "James E.J. Bottomley" (arch/parisc) Cc: Benjamin Herrenschmidt (arch/powerpc) Cc: Paul Mackerras (arch/powerpc) Cc: "David S. Miller" (arch/sparc) Cc: Thomas Gleixner (arch/x86) Cc: Ingo Molnar (arch/x86) Cc: "H. Peter Anvin" (arch/x86) Cc: Arnd Bergmann (include/asm-generic) Cc: Rusty Russell ("Hard To Misuse" list) Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/highmem.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index caafd0561aa1..67460f010224 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -2,6 +2,7 @@ #define _LINUX_HIGHMEM_H #include +#include #include #include @@ -72,7 +73,7 @@ static inline void *kmap_atomic(struct page *page, enum km_type idx) } #define kmap_atomic_prot(page, idx, prot) kmap_atomic(page, idx) -#define kunmap_atomic(addr, idx) do { pagefault_enable(); } while (0) +#define kunmap_atomic_notypecheck(addr, idx) do { pagefault_enable(); } while (0) #define kmap_atomic_pfn(pfn, idx) kmap_atomic(pfn_to_page(pfn), (idx)) #define kmap_atomic_to_page(ptr) virt_to_page(ptr) @@ -81,6 +82,13 @@ static inline void *kmap_atomic(struct page *page, enum km_type idx) #endif /* CONFIG_HIGHMEM */ +/* Prevent people trying to call kunmap_atomic() as if it were kunmap() */ +/* kunmap_atomic() should get the return value of kmap_atomic, not the page. */ +#define kunmap_atomic(addr, idx) do { \ + BUILD_BUG_ON(__same_type((addr), struct page *)); \ + kunmap_atomic_notypecheck((addr), (idx)); \ + } while (0) + /* when CONFIG_HIGHMEM is not set these will be plain clear/copy_page */ #ifndef clear_user_highpage static inline void clear_user_highpage(struct page *page, unsigned long vaddr) -- cgit v1.2.3 From bb4a340e075b7897ece109686bfa177f8518d2db Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Mon, 9 Aug 2010 17:18:37 -0700 Subject: mm: rename anon_vma_lock to vma_lock_anon_vma Rename anon_vma_lock to vma_lock_anon_vma. This matches the naming style used in page_lock_anon_vma and will come in really handy further down in this patch series. Signed-off-by: Rik van Riel Acked-by: Mel Gorman Acked-by: KAMEZAWA Hiroyuki Tested-by: Larry Woodman Acked-by: Larry Woodman Reviewed-by: Minchan Kim Acked-by: Linus Torvalds Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rmap.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 77216742c178..80cd162a8aa6 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -99,14 +99,14 @@ static inline struct anon_vma *page_anon_vma(struct page *page) return page_rmapping(page); } -static inline void anon_vma_lock(struct vm_area_struct *vma) +static inline void vma_lock_anon_vma(struct vm_area_struct *vma) { struct anon_vma *anon_vma = vma->anon_vma; if (anon_vma) spin_lock(&anon_vma->lock); } -static inline void anon_vma_unlock(struct vm_area_struct *vma) +static inline void vma_unlock_anon_vma(struct vm_area_struct *vma) { struct anon_vma *anon_vma = vma->anon_vma; if (anon_vma) -- cgit v1.2.3 From cba48b98f2348c814316c4b4f411a07a0e4a2bf9 Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Mon, 9 Aug 2010 17:18:38 -0700 Subject: mm: change direct call of spin_lock(anon_vma->lock) to inline function Subsitute a direct call of spin_lock(anon_vma->lock) with an inline function doing exactly the same. This makes it easier to do the substitution to the root anon_vma lock in a following patch. We will deal with the handful of special locks (nested, dec_and_lock, etc) separately. Signed-off-by: Rik van Riel Acked-by: Mel Gorman Acked-by: KAMEZAWA Hiroyuki Tested-by: Larry Woodman Acked-by: Larry Woodman Reviewed-by: Minchan Kim Acked-by: Linus Torvalds Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rmap.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 80cd162a8aa6..5f981be61416 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -113,6 +113,16 @@ static inline void vma_unlock_anon_vma(struct vm_area_struct *vma) spin_unlock(&anon_vma->lock); } +static inline void anon_vma_lock(struct anon_vma *anon_vma) +{ + spin_lock(&anon_vma->lock); +} + +static inline void anon_vma_unlock(struct anon_vma *anon_vma) +{ + spin_unlock(&anon_vma->lock); +} + /* * anon_vma helper functions. */ -- cgit v1.2.3 From 5c341ee1dfc8fe69d66b1c8b19e463c6d7201ae1 Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Mon, 9 Aug 2010 17:18:39 -0700 Subject: mm: track the root (oldest) anon_vma Track the root (oldest) anon_vma in each anon_vma tree. Because we only take the lock on the root anon_vma, we cannot use the lock on higher-up anon_vmas to lock anything. This makes it impossible to do an indirect lookup of the root anon_vma, since the data structures could go away from under us. However, a direct pointer is safe because the root anon_vma is always the last one that gets freed on munmap or exit, by virtue of the same_vma list order and unlink_anon_vmas walking the list forward. [akpm@linux-foundation.org: fix typo] Signed-off-by: Rik van Riel Acked-by: Mel Gorman Acked-by: KAMEZAWA Hiroyuki Tested-by: Larry Woodman Acked-by: Larry Woodman Reviewed-by: Minchan Kim Acked-by: Linus Torvalds Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rmap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 5f981be61416..41fa6ddc6214 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -26,6 +26,7 @@ */ struct anon_vma { spinlock_t lock; /* Serialize access to vma list */ + struct anon_vma *root; /* Root of this anon_vma tree */ #if defined(CONFIG_KSM) || defined(CONFIG_MIGRATION) /* -- cgit v1.2.3 From 012f18004da33ba672e3c60838cc4898126174d3 Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Mon, 9 Aug 2010 17:18:40 -0700 Subject: mm: always lock the root (oldest) anon_vma Always (and only) lock the root (oldest) anon_vma whenever we do something in an anon_vma. The recently introduced anon_vma scalability is due to the rmap code scanning only the VMAs that need to be scanned. Many common operations still took the anon_vma lock on the root anon_vma, so always taking that lock is not expected to introduce any scalability issues. However, always taking the same lock does mean we only need to take one lock, which means rmap_walk on pages from any anon_vma in the vma is excluded from occurring during an munmap, expand_stack or other operation that needs to exclude rmap_walk and similar functions. Also add the proper locking to vma_adjust. Signed-off-by: Rik van Riel Tested-by: Larry Woodman Acked-by: Larry Woodman Reviewed-by: Minchan Kim Reviewed-by: KAMEZAWA Hiroyuki Acked-by: Mel Gorman Acked-by: Linus Torvalds Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rmap.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 41fa6ddc6214..af43cb9a0506 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -104,24 +104,24 @@ static inline void vma_lock_anon_vma(struct vm_area_struct *vma) { struct anon_vma *anon_vma = vma->anon_vma; if (anon_vma) - spin_lock(&anon_vma->lock); + spin_lock(&anon_vma->root->lock); } static inline void vma_unlock_anon_vma(struct vm_area_struct *vma) { struct anon_vma *anon_vma = vma->anon_vma; if (anon_vma) - spin_unlock(&anon_vma->lock); + spin_unlock(&anon_vma->root->lock); } static inline void anon_vma_lock(struct anon_vma *anon_vma) { - spin_lock(&anon_vma->lock); + spin_lock(&anon_vma->root->lock); } static inline void anon_vma_unlock(struct anon_vma *anon_vma) { - spin_unlock(&anon_vma->lock); + spin_unlock(&anon_vma->root->lock); } /* -- cgit v1.2.3 From 76545066c8521f3e32c849744744842b4df25b79 Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Mon, 9 Aug 2010 17:18:41 -0700 Subject: mm: extend KSM refcounts to the anon_vma root KSM reference counts can cause an anon_vma to exist after the processe it belongs to have already exited. Because the anon_vma lock now lives in the root anon_vma, we need to ensure that the root anon_vma stays around until after all the "child" anon_vmas have been freed. The obvious way to do this is to have a "child" anon_vma take a reference to the root in anon_vma_fork. When the anon_vma is freed at munmap or process exit, we drop the refcount in anon_vma_unlink and possibly free the root anon_vma. The KSM anon_vma reference count function also needs to be modified to deal with the possibility of freeing 2 levels of anon_vma. The easiest way to do this is to break out the KSM magic and make it generic. When compiling without CONFIG_KSM, this code is compiled out. Signed-off-by: Rik van Riel Tested-by: Larry Woodman Acked-by: Larry Woodman Reviewed-by: Minchan Kim Cc: KAMEZAWA Hiroyuki Acked-by: Mel Gorman Acked-by: Linus Torvalds Tested-by: Dave Young Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rmap.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index af43cb9a0506..dc9b3c0bf5d4 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -81,6 +81,13 @@ static inline int anonvma_external_refcount(struct anon_vma *anon_vma) { return atomic_read(&anon_vma->external_refcount); } + +static inline void get_anon_vma(struct anon_vma *anon_vma) +{ + atomic_inc(&anon_vma->external_refcount); +} + +void drop_anon_vma(struct anon_vma *); #else static inline void anonvma_external_refcount_init(struct anon_vma *anon_vma) { @@ -90,6 +97,14 @@ static inline int anonvma_external_refcount(struct anon_vma *anon_vma) { return 0; } + +static inline void get_anon_vma(struct anon_vma *anon_vma) +{ +} + +static inline void drop_anon_vma(struct anon_vma *anon_vma) +{ +} #endif /* CONFIG_KSM */ static inline struct anon_vma *page_anon_vma(struct page *page) -- cgit v1.2.3 From a9877cc2937889e5669114f28612b494384152a4 Mon Sep 17 00:00:00 2001 From: Richard Kennedy Date: Mon, 9 Aug 2010 17:18:42 -0700 Subject: buffer_head: remove redundant test from wait_on_buffer The comment suggests that when b_count equals zero it is calling __wait_no_buffer to trigger some debug, but as there is no debug in __wait_on_buffer the whole thing is redundant. AFAICT from the git log this has been the case for at least 5 years, so it seems safe just to remove this. Signed-off-by: Richard Kennedy Cc: Nick Piggin Cc: Jens Axboe Cc: Jeff Mahoney Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/buffer_head.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 1b9ba193b789..2ce51fac7d3d 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -314,15 +314,10 @@ map_bh(struct buffer_head *bh, struct super_block *sb, sector_t block) bh->b_size = sb->s_blocksize; } -/* - * Calling wait_on_buffer() for a zero-ref buffer is illegal, so we call into - * __wait_on_buffer() just to trip a debug check. Because debug code in inline - * functions is bloaty. - */ static inline void wait_on_buffer(struct buffer_head *bh) { might_sleep(); - if (buffer_locked(bh) || atomic_read(&bh->b_count) == 0) + if (buffer_locked(bh)) __wait_on_buffer(bh); } -- cgit v1.2.3 From 6f48d0ebd907ae419387f27b602ee98870cfa7bb Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Mon, 9 Aug 2010 17:18:52 -0700 Subject: oom: select task from tasklist for mempolicy ooms The oom killer presently kills current whenever there is no more memory free or reclaimable on its mempolicy's nodes. There is no guarantee that current is a memory-hogging task or that killing it will free any substantial amount of memory, however. In such situations, it is better to scan the tasklist for nodes that are allowed to allocate on current's set of nodes and kill the task with the highest badness() score. This ensures that the most memory-hogging task, or the one configured by the user with /proc/pid/oom_adj, is always selected in such scenarios. Signed-off-by: David Rientjes Reviewed-by: KOSAKI Motohiro Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mempolicy.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 7b9ef6bf45aa..31ac26ca4acf 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -210,6 +210,8 @@ extern struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask); extern bool init_nodemask_of_mempolicy(nodemask_t *mask); +extern bool mempolicy_nodemask_intersects(struct task_struct *tsk, + const nodemask_t *mask); extern unsigned slab_node(struct mempolicy *policy); extern enum zone_type policy_zone; @@ -338,7 +340,16 @@ static inline struct zonelist *huge_zonelist(struct vm_area_struct *vma, return node_zonelist(0, gfp_flags); } -static inline bool init_nodemask_of_mempolicy(nodemask_t *m) { return false; } +static inline bool init_nodemask_of_mempolicy(nodemask_t *m) +{ + return false; +} + +static inline bool mempolicy_nodemask_intersects(struct task_struct *tsk, + const nodemask_t *mask) +{ + return false; +} static inline int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from_nodes, -- cgit v1.2.3 From 309ed882508cc471320ff79265e7340774d6746c Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Mon, 9 Aug 2010 17:18:54 -0700 Subject: oom: extract panic helper function There are various points in the oom killer where the kernel must determine whether to panic or not. It's better to extract this to a helper function to remove all the confusion as to its semantics. Also fix a call to dump_header() where tasklist_lock is not read- locked, as required. There's no functional change with this patch. Acked-by: KOSAKI Motohiro Signed-off-by: David Rientjes Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/oom.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/oom.h b/include/linux/oom.h index 537662315627..3ae6d94d0540 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -22,6 +22,7 @@ enum oom_constraint { CONSTRAINT_NONE, CONSTRAINT_CPUSET, CONSTRAINT_MEMORY_POLICY, + CONSTRAINT_MEMCG, }; extern int try_set_zone_oom(struct zonelist *zonelist, gfp_t gfp_flags); -- cgit v1.2.3 From 8e4228e1edb922afa83366803a1e5b3fa8e987c2 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Mon, 9 Aug 2010 17:18:56 -0700 Subject: oom: move sysctl declarations to oom.h The three oom killer sysctl variables (sysctl_oom_dump_tasks, sysctl_oom_kill_allocating_task, and sysctl_panic_on_oom) are better declared in include/linux/oom.h rather than kernel/sysctl.c. Signed-off-by: David Rientjes Acked-by: KOSAKI Motohiro Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/oom.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/oom.h b/include/linux/oom.h index 3ae6d94d0540..1a8e407a1a53 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -44,5 +44,10 @@ static inline void oom_killer_enable(void) { oom_killer_disabled = false; } + +/* sysctls */ +extern int sysctl_oom_dump_tasks; +extern int sysctl_oom_kill_allocating_task; +extern int sysctl_panic_on_oom; #endif /* __KERNEL__*/ #endif /* _INCLUDE_LINUX_OOM_H */ -- cgit v1.2.3 From ff321feac22313cf53ffceb69224b09ac19ff22b Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Mon, 9 Aug 2010 17:18:57 -0700 Subject: mm: rename try_set_zone_oom() to try_set_zonelist_oom() We have been used naming try_set_zone_oom and clear_zonelist_oom. The role of functions is to lock of zonelist for preventing parallel OOM. So clear_zonelist_oom makes sense but try_set_zone_oome is rather awkward and unmatched with clear_zonelist_oom. Let's change it with try_set_zonelist_oom. Signed-off-by: Minchan Kim Acked-by: David Rientjes Reviewed-by: KOSAKI Motohiro Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/oom.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/oom.h b/include/linux/oom.h index 1a8e407a1a53..9d7c34a741e7 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -25,7 +25,7 @@ enum oom_constraint { CONSTRAINT_MEMCG, }; -extern int try_set_zone_oom(struct zonelist *zonelist, gfp_t gfp_flags); +extern int try_set_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags); extern void clear_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags); extern void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, -- cgit v1.2.3 From b645bd1286f2fbcd2eb4ab3bed5884f63c42e363 Mon Sep 17 00:00:00 2001 From: Alexander Nevenchannyy Date: Mon, 9 Aug 2010 17:19:00 -0700 Subject: mmzone.h: remove dead prototype get_zone_counts() was dropped from kernel tree, see: http://www.mail-archive.com/mm-commits@vger.kernel.org/msg07313.html but its prototype remains. Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index b4d109e389b8..9ed9c459b14c 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -651,8 +651,6 @@ typedef struct pglist_data { #include extern struct mutex zonelists_mutex; -void get_zone_counts(unsigned long *active, unsigned long *inactive, - unsigned long *free); void build_all_zonelists(void *data); void wakeup_kswapd(struct zone *zone, int order); int zone_watermark_ok(struct zone *z, int order, unsigned long mark, -- cgit v1.2.3 From 251060006003b79b788f8ce5a827ee5354a42910 Mon Sep 17 00:00:00 2001 From: Lee Schermerhorn Date: Mon, 9 Aug 2010 17:19:00 -0700 Subject: topology: alternate fix for ia64 tiger_defconfig build breakage Define stubs for the numa_*_id() generic percpu related functions for non-NUMA configurations in where the other non-numa stubs live. Fixes ia64 !NUMA build breakage -- e.g., tiger_defconfig Back out now unneeded '#ifndef CONFIG_NUMA' guards from ia64 smpboot.c Signed-off-by: Lee Schermerhorn Tested-by: Tony Luck Acked-by: Tony Luck Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/topology.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/topology.h b/include/linux/topology.h index b572e432d2f3..64e084ff5e5c 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -292,10 +292,6 @@ static inline void set_cpu_numa_mem(int cpu, int node) #else /* !CONFIG_HAVE_MEMORYLESS_NODES */ -static inline void set_numa_mem(int node) {} - -static inline void set_cpu_numa_mem(int cpu, int node) {} - #ifndef numa_mem_id /* Returns the number of the nearest Node with memory */ static inline int numa_mem_id(void) -- cgit v1.2.3 From 627295e492638936e76f3d8fcb1e0a3367b88341 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Mon, 9 Aug 2010 17:19:02 -0700 Subject: gcc-4.6: pagemap: avoid unused-but-set variable Avoid quite a lot of warnings in header files in a gcc 4.6 -Wall builds Signed-off-by: Andi Kleen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 3c62ed408492..78a702ce4fcb 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -423,8 +423,10 @@ static inline int fault_in_pages_readable(const char __user *uaddr, int size) const char __user *end = uaddr + size - 1; if (((unsigned long)uaddr & PAGE_MASK) != - ((unsigned long)end & PAGE_MASK)) + ((unsigned long)end & PAGE_MASK)) { ret = __get_user(c, end); + (void)c; + } } return ret; } -- cgit v1.2.3 From 4e60c86bd9e5a7110ed28874d0b6592186550ae8 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Mon, 9 Aug 2010 17:19:03 -0700 Subject: gcc-4.6: mm: fix unused but set warnings No real bugs, just some dead code and some fixups. Signed-off-by: Andi Kleen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/highmem.h | 6 +++++- include/linux/mmdebug.h | 2 +- 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 67460f010224..e3060ef85b6d 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -73,7 +73,11 @@ static inline void *kmap_atomic(struct page *page, enum km_type idx) } #define kmap_atomic_prot(page, idx, prot) kmap_atomic(page, idx) -#define kunmap_atomic_notypecheck(addr, idx) do { pagefault_enable(); } while (0) +static inline void kunmap_atomic_notypecheck(void *addr, enum km_type idx) +{ + pagefault_enable(); +} + #define kmap_atomic_pfn(pfn, idx) kmap_atomic(pfn_to_page(pfn), (idx)) #define kmap_atomic_to_page(ptr) virt_to_page(ptr) diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h index ee24ef8ab616..c04ecfe03f7f 100644 --- a/include/linux/mmdebug.h +++ b/include/linux/mmdebug.h @@ -4,7 +4,7 @@ #ifdef CONFIG_DEBUG_VM #define VM_BUG_ON(cond) BUG_ON(cond) #else -#define VM_BUG_ON(cond) do { } while (0) +#define VM_BUG_ON(cond) do { (void)(cond); } while (0) #endif #ifdef CONFIG_DEBUG_VIRTUAL -- cgit v1.2.3 From 27f5e0f694fd0600274a76854636c0749e3bb1f6 Mon Sep 17 00:00:00 2001 From: Tim Chen Date: Mon, 9 Aug 2010 17:19:04 -0700 Subject: tmpfs: add accurate compare function to percpu_counter library Add percpu_counter_compare that allows for a quick but accurate comparison of percpu_counter with a given value. A rough count is provided by the count field in percpu_counter structure, without accounting for the other values stored in individual cpu counters. The actual count is a sum of count and the cpu counters. However, count field is never different from the actual value by a factor of batch*num_online_cpu. We do not need to get actual count for comparison if count is different from the given value by this factor and allows for quick comparison without summing up all the per cpu counters. Signed-off-by: Tim Chen Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/percpu_counter.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h index c88d67b59394..8a7d510ffa9c 100644 --- a/include/linux/percpu_counter.h +++ b/include/linux/percpu_counter.h @@ -40,6 +40,7 @@ void percpu_counter_destroy(struct percpu_counter *fbc); void percpu_counter_set(struct percpu_counter *fbc, s64 amount); void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch); s64 __percpu_counter_sum(struct percpu_counter *fbc); +int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs); static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) { @@ -98,6 +99,16 @@ static inline void percpu_counter_set(struct percpu_counter *fbc, s64 amount) fbc->count = amount; } +static inline int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs) +{ + if (fbc->count > rhs) + return 1; + else if (fbc->count < rhs) + return -1; + else + return 0; +} + static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) { -- cgit v1.2.3 From 7e496299d4d2ad8083effed6c5a18313a919edc6 Mon Sep 17 00:00:00 2001 From: Tim Chen Date: Mon, 9 Aug 2010 17:19:05 -0700 Subject: tmpfs: make tmpfs scalable with percpu_counter for used blocks The current implementation of tmpfs is not scalable. We found that stat_lock is contended by multiple threads when we need to get a new page, leading to useless spinning inside this spin lock. This patch makes use of the percpu_counter library to maintain local count of used blocks to speed up getting and returning of pages. So the acquisition of stat_lock is unnecessary for getting and returning blocks, improving the performance of tmpfs on system with large number of cpus. On a 4 socket 32 core NHM-EX system, we saw improvement of 270%. The implementation below has a slight chance of race between threads causing a slight overshoot of the maximum configured blocks. However, any overshoot is small, and is bounded by the number of cpus. This happens when the number of used blocks is slightly below the maximum configured blocks when a thread checks the used block count, and another thread allocates the last block before the current thread does. This should not be a problem for tmpfs, as the overshoot is most likely to be a few blocks and bounded. If a strict limit is really desired, then configured the max blocks to be the limit less the number of cpus in system. Signed-off-by: Tim Chen Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/shmem_fs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index e164291fb3e7..399be5ad2f99 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -3,6 +3,7 @@ #include #include +#include /* inode in-kernel data */ @@ -23,7 +24,7 @@ struct shmem_inode_info { struct shmem_sb_info { unsigned long max_blocks; /* How many blocks are allowed */ - unsigned long free_blocks; /* How many are left for allocation */ + struct percpu_counter used_blocks; /* How many are allocated */ unsigned long max_inodes; /* How many inodes are allowed */ unsigned long free_inodes; /* How many are left for allocation */ spinlock_t stat_lock; /* Serialize shmem_sb_info changes */ -- cgit v1.2.3 From ba6f0ff3981e6263ab81ac512f04cca55b85ec81 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Mon, 9 Aug 2010 17:19:08 -0700 Subject: ksm: fix ksm swapin time optimization The new anon-vma code, was suboptimal and it lead to erratic invocation of ksm_does_need_to_copy. That leads to host hangs or guest vnc lockup, or weird behavior. It's unclear why ksm_does_need_to_copy is unstable but the point is that when KSM is not in use, ksm_does_need_to_copy must never run or we bounce pages for no good reason. I suspect the same hangs will happen with KVM swaps. But this at least fixes the regression in the new-anon-vma code and it only let KSM bugs triggers when KSM is in use. The code in do_swap_page likely doesn't cope well with a not-swapcache, especially the memcg code. Signed-off-by: Andrea Arcangeli Signed-off-by: Rik van Riel Cc: Izik Eidus Cc: Avi Kivity Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ksm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 43bdab769fc3..74d691ee9121 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -78,7 +78,7 @@ static inline struct page *ksm_might_need_to_copy(struct page *page, struct anon_vma *anon_vma = page_anon_vma(page); if (!anon_vma || - (anon_vma == vma->anon_vma && + (anon_vma->root == vma->anon_vma->root && page->index == linear_page_index(vma, address))) return page; -- cgit v1.2.3 From ebf8aa44beed48cd17893a83d92a4403e5f9d9e2 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 9 Aug 2010 17:19:11 -0700 Subject: radix-tree: omplement function radix_tree_range_tag_if_tagged Implement function for setting one tag if another tag is set for each item in given range. Signed-off-by: Jan Kara Cc: Dave Chinner Cc: Nick Piggin Cc: Chris Mason Cc: Theodore Ts'o Cc: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/radix-tree.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 55ca73cf25e5..a4b00e9cca90 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -192,6 +192,10 @@ unsigned int radix_tree_gang_lookup_tag_slot(struct radix_tree_root *root, void ***results, unsigned long first_index, unsigned int max_items, unsigned int tag); +unsigned long radix_tree_range_tag_if_tagged(struct radix_tree_root *root, + unsigned long *first_indexp, unsigned long last_index, + unsigned long nr_to_tag, + unsigned int fromtag, unsigned int totag); int radix_tree_tagged(struct radix_tree_root *root, unsigned int tag); static inline void radix_tree_preload_end(void) -- cgit v1.2.3 From f446daaea9d4a420d16c606f755f3689dcb2d0ce Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 9 Aug 2010 17:19:12 -0700 Subject: mm: implement writeback livelock avoidance using page tagging We try to avoid livelocks of writeback when some steadily creates dirty pages in a mapping we are writing out. For memory-cleaning writeback, using nr_to_write works reasonably well but we cannot really use it for data integrity writeback. This patch tries to solve the problem. The idea is simple: Tag all pages that should be written back with a special tag (TOWRITE) in the radix tree. This can be done rather quickly and thus livelocks should not happen in practice. Then we start doing the hard work of locking pages and sending them to disk only for those pages that have TOWRITE tag set. Note: Adding new radix tree tag grows radix tree node from 288 to 296 bytes for 32-bit archs and from 552 to 560 bytes for 64-bit archs. However, the number of slab/slub items per page remains the same (13 and 7 respectively). Signed-off-by: Jan Kara Cc: Dave Chinner Cc: Nick Piggin Cc: Chris Mason Cc: Theodore Ts'o Cc: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 1 + include/linux/radix-tree.h | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index e5106e49bd2c..488efec09d14 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -687,6 +687,7 @@ struct block_device { */ #define PAGECACHE_TAG_DIRTY 0 #define PAGECACHE_TAG_WRITEBACK 1 +#define PAGECACHE_TAG_TOWRITE 2 int mapping_tagged(struct address_space *mapping, int tag); diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index a4b00e9cca90..634b8e674ac5 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -55,7 +55,7 @@ static inline int radix_tree_is_indirect_ptr(void *ptr) /*** radix-tree API starts here ***/ -#define RADIX_TREE_MAX_TAGS 2 +#define RADIX_TREE_MAX_TAGS 3 /* root tags are stored in gfp_mask, shifted by __GFP_BITS_SHIFT */ struct radix_tree_root { -- cgit v1.2.3 From 25edde0332916ae706ccf83de688be57bcc844b7 Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Mon, 9 Aug 2010 17:19:27 -0700 Subject: vmscan: kill prev_priority completely Since 2.6.28 zone->prev_priority is unused. Then it can be removed safely. It reduce stack usage slightly. Now I have to say that I'm sorry. 2 years ago, I thought prev_priority can be integrate again, it's useful. but four (or more) times trying haven't got good performance number. Thus I give up such approach. The rest of this changelog is notes on prev_priority and why it existed in the first place and why it might be not necessary any more. This information is based heavily on discussions between Andrew Morton, Rik van Riel and Kosaki Motohiro who is heavily quotes from. Historically prev_priority was important because it determined when the VM would start unmapping PTE pages. i.e. there are no balances of note within the VM, Anon vs File and Mapped vs Unmapped. Without prev_priority, there is a potential risk of unnecessarily increasing minor faults as a large amount of read activity of use-once pages could push mapped pages to the end of the LRU and get unmapped. There is no proof this is still a problem but currently it is not considered to be. Active files are not deactivated if the active file list is smaller than the inactive list reducing the liklihood that file-mapped pages are being pushed off the LRU and referenced executable pages are kept on the active list to avoid them getting pushed out by read activity. Even if it is a problem, prev_priority prev_priority wouldn't works nowadays. First of all, current vmscan still a lot of UP centric code. it expose some weakness on some dozens CPUs machine. I think we need more and more improvement. The problem is, current vmscan mix up per-system-pressure, per-zone-pressure and per-task-pressure a bit. example, prev_priority try to boost priority to other concurrent priority. but if the another task have mempolicy restriction, it is unnecessary, but also makes wrong big latency and exceeding reclaim. per-task based priority + prev_priority adjustment make the emulation of per-system pressure. but it have two issue 1) too rough and brutal emulation 2) we need per-zone pressure, not per-system. Another example, currently DEF_PRIORITY is 12. it mean the lru rotate about 2 cycle (1/4096 + 1/2048 + 1/1024 + .. + 1) before invoking OOM-Killer. but if 10,0000 thrreads enter DEF_PRIORITY reclaim at the same time, the system have higher memory pressure than priority==0 (1/4096*10,000 > 2). prev_priority can't solve such multithreads workload issue. In other word, prev_priority concept assume the sysmtem don't have lots threads." Signed-off-by: KOSAKI Motohiro Signed-off-by: Mel Gorman Reviewed-by: Johannes Weiner Reviewed-by: Rik van Riel Cc: Dave Chinner Cc: Chris Mason Cc: Nick Piggin Cc: Rik van Riel Cc: Johannes Weiner Cc: Christoph Hellwig Cc: KAMEZAWA Hiroyuki Cc: KOSAKI Motohiro Cc: Andrea Arcangeli Cc: Michael Rubin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 5 ----- include/linux/mmzone.h | 15 --------------- 2 files changed, 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 9411d32840b0..9f1afd361583 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -98,11 +98,6 @@ extern void mem_cgroup_end_migration(struct mem_cgroup *mem, /* * For memory reclaim. */ -extern int mem_cgroup_get_reclaim_priority(struct mem_cgroup *mem); -extern void mem_cgroup_note_reclaim_priority(struct mem_cgroup *mem, - int priority); -extern void mem_cgroup_record_reclaim_priority(struct mem_cgroup *mem, - int priority); int mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg); int mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg); unsigned long mem_cgroup_zone_nr_pages(struct mem_cgroup *memcg, diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 9ed9c459b14c..6e6e62648a4d 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -347,21 +347,6 @@ struct zone { /* Zone statistics */ atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS]; - /* - * prev_priority holds the scanning priority for this zone. It is - * defined as the scanning priority at which we achieved our reclaim - * target at the previous try_to_free_pages() or balance_pgdat() - * invocation. - * - * We use prev_priority as a measure of how much stress page reclaim is - * under - it drives the swappiness decision: whether to unmap mapped - * pages. - * - * Access to both this field is quite racy even on uniprocessor. But - * it is expected to average out OK. - */ - int prev_priority; - /* * The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on * this zone's LRU. Maintained by the pageout code. -- cgit v1.2.3 From 74bcbf40546bb7500f2a7ba4ff3cc056a6bd004a Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Mon, 9 Aug 2010 17:19:43 -0700 Subject: oom: move badness() declaration into oom.h Cc: Minchan Kim Cc: David Rientjes Cc: KAMEZAWA Hiroyuki Cc: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/oom.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/oom.h b/include/linux/oom.h index 9d7c34a741e7..40e5e3a6bc20 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -14,6 +14,8 @@ struct zonelist; struct notifier_block; +struct mem_cgroup; +struct task_struct; /* * Types of limitations to the nodes from which allocations may occur @@ -45,6 +47,10 @@ static inline void oom_killer_enable(void) oom_killer_disabled = false; } +/* The badness from the OOM killer */ +extern unsigned long badness(struct task_struct *p, struct mem_cgroup *mem, + const nodemask_t *nodemask, unsigned long uptime); + /* sysctls */ extern int sysctl_oom_dump_tasks; extern int sysctl_oom_kill_allocating_task; -- cgit v1.2.3 From a63d83f427fbce97a6cea0db2e64b0eb8435cd10 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Mon, 9 Aug 2010 17:19:46 -0700 Subject: oom: badness heuristic rewrite This a complete rewrite of the oom killer's badness() heuristic which is used to determine which task to kill in oom conditions. The goal is to make it as simple and predictable as possible so the results are better understood and we end up killing the task which will lead to the most memory freeing while still respecting the fine-tuning from userspace. Instead of basing the heuristic on mm->total_vm for each task, the task's rss and swap space is used instead. This is a better indication of the amount of memory that will be freeable if the oom killed task is chosen and subsequently exits. This helps specifically in cases where KDE or GNOME is chosen for oom kill on desktop systems instead of a memory hogging task. The baseline for the heuristic is a proportion of memory that each task is currently using in memory plus swap compared to the amount of "allowable" memory. "Allowable," in this sense, means the system-wide resources for unconstrained oom conditions, the set of mempolicy nodes, the mems attached to current's cpuset, or a memory controller's limit. The proportion is given on a scale of 0 (never kill) to 1000 (always kill), roughly meaning that if a task has a badness() score of 500 that the task consumes approximately 50% of allowable memory resident in RAM or in swap space. The proportion is always relative to the amount of "allowable" memory and not the total amount of RAM systemwide so that mempolicies and cpusets may operate in isolation; they shall not need to know the true size of the machine on which they are running if they are bound to a specific set of nodes or mems, respectively. Root tasks are given 3% extra memory just like __vm_enough_memory() provides in LSMs. In the event of two tasks consuming similar amounts of memory, it is generally better to save root's task. Because of the change in the badness() heuristic's baseline, it is also necessary to introduce a new user interface to tune it. It's not possible to redefine the meaning of /proc/pid/oom_adj with a new scale since the ABI cannot be changed for backward compatability. Instead, a new tunable, /proc/pid/oom_score_adj, is added that ranges from -1000 to +1000. It may be used to polarize the heuristic such that certain tasks are never considered for oom kill while others may always be considered. The value is added directly into the badness() score so a value of -500, for example, means to discount 50% of its memory consumption in comparison to other tasks either on the system, bound to the mempolicy, in the cpuset, or sharing the same memory controller. /proc/pid/oom_adj is changed so that its meaning is rescaled into the units used by /proc/pid/oom_score_adj, and vice versa. Changing one of these per-task tunables will rescale the value of the other to an equivalent meaning. Although /proc/pid/oom_adj was originally defined as a bitshift on the badness score, it now shares the same linear growth as /proc/pid/oom_score_adj but with different granularity. This is required so the ABI is not broken with userspace applications and allows oom_adj to be deprecated for future removal. Signed-off-by: David Rientjes Cc: Nick Piggin Cc: KAMEZAWA Hiroyuki Cc: KOSAKI Motohiro Cc: Oleg Nesterov Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 8 ++++++++ include/linux/oom.h | 14 +++++++++++++- include/linux/sched.h | 3 ++- 3 files changed, 23 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 9f1afd361583..73564cac38c7 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -125,6 +125,8 @@ void mem_cgroup_update_file_mapped(struct page *page, int val); unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, gfp_t gfp_mask, int nid, int zid); +u64 mem_cgroup_get_limit(struct mem_cgroup *mem); + #else /* CONFIG_CGROUP_MEM_RES_CTLR */ struct mem_cgroup; @@ -304,6 +306,12 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, return 0; } +static inline +u64 mem_cgroup_get_limit(struct mem_cgroup *mem) +{ + return 0; +} + #endif /* CONFIG_CGROUP_MEM_CONT */ #endif /* _LINUX_MEMCONTROL_H */ diff --git a/include/linux/oom.h b/include/linux/oom.h index 40e5e3a6bc20..73b8d7b6dd19 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -1,14 +1,24 @@ #ifndef __INCLUDE_LINUX_OOM_H #define __INCLUDE_LINUX_OOM_H -/* /proc//oom_adj set to -17 protects from the oom-killer */ +/* + * /proc//oom_adj set to -17 protects from the oom-killer + */ #define OOM_DISABLE (-17) /* inclusive */ #define OOM_ADJUST_MIN (-16) #define OOM_ADJUST_MAX 15 +/* + * /proc//oom_score_adj set to OOM_SCORE_ADJ_MIN disables oom killing for + * pid. + */ +#define OOM_SCORE_ADJ_MIN (-1000) +#define OOM_SCORE_ADJ_MAX 1000 + #ifdef __KERNEL__ +#include #include #include @@ -27,6 +37,8 @@ enum oom_constraint { CONSTRAINT_MEMCG, }; +extern unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem, + const nodemask_t *nodemask, unsigned long totalpages); extern int try_set_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags); extern void clear_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags); diff --git a/include/linux/sched.h b/include/linux/sched.h index 9591907c4f79..ce160d68f5e7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -621,7 +621,8 @@ struct signal_struct { struct tty_audit_buf *tty_audit_buf; #endif - int oom_adj; /* OOM kill score adjustment (bit shift) */ + int oom_adj; /* OOM kill score adjustment (bit shift) */ + int oom_score_adj; /* OOM kill score adjustment */ }; /* Context switch must be unlocked if interrupts are to be enabled */ -- cgit v1.2.3 From 51b1bd2ace1595b72956224deda349efa880b693 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Mon, 9 Aug 2010 17:19:47 -0700 Subject: oom: deprecate oom_adj tunable /proc/pid/oom_adj is now deprecated so that that it may eventually be removed. The target date for removal is August 2012. A warning will be printed to the kernel log if a task attempts to use this interface. Future warning will be suppressed until the kernel is rebooted to prevent spamming the kernel log. Signed-off-by: David Rientjes Cc: Nick Piggin Cc: KAMEZAWA Hiroyuki Cc: KOSAKI Motohiro Cc: Oleg Nesterov Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/oom.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/oom.h b/include/linux/oom.h index 73b8d7b6dd19..f209b683e118 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -2,6 +2,9 @@ #define __INCLUDE_LINUX_OOM_H /* + * /proc//oom_adj is deprecated, see + * Documentation/feature-removal-schedule.txt. + * * /proc//oom_adj set to -17 protects from the oom-killer */ #define OOM_DISABLE (-17) -- cgit v1.2.3 From ad8c2ee801ad7a52d919b478d9b2c7b39a72d295 Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Mon, 9 Aug 2010 17:19:48 -0700 Subject: rmap: add exclusive page to private anon_vma on swapin On swapin it is fairly common for a page to be owned exclusively by one process. In that case we want to add the page to the anon_vma of that process's VMA, instead of to the root anon_vma. This will reduce the amount of rmap searching that the swapout code needs to do. Signed-off-by: Rik van Riel Cc: Andrea Arcangeli Cc: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rmap.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index dc9b3c0bf5d4..d6661de56f30 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -162,6 +162,8 @@ static inline void anon_vma_merge(struct vm_area_struct *vma, */ void page_move_anon_rmap(struct page *, struct vm_area_struct *, unsigned long); void page_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long); +void do_page_add_anon_rmap(struct page *, struct vm_area_struct *, + unsigned long, int); void page_add_new_anon_rmap(struct page *, struct vm_area_struct *, unsigned long); void page_add_file_rmap(struct page *); void page_remove_rmap(struct page *); -- cgit v1.2.3 From d2997b1042ec150616c1963b5e5e919ffd0b0ebf Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Mon, 9 Aug 2010 17:20:11 -0700 Subject: hibernation: freeze swap at hibernation When taking a memory snapshot in hibernate_snapshot(), all (directly called) memory allocations use GFP_ATOMIC. Hence swap misusage during hibernation never occurs. But from a pessimistic point of view, there is no guarantee that no page allcation has __GFP_WAIT. It is better to have a global indication "we enter hibernation, don't use swap!". This patch tries to freeze new-swap-allocation during hibernation. (All user processes are frozenm so swapin is not a concern). This way, no updates will happen to swap_map[] between hibernate_snapshot() and save_image(). Swap is thawed when swsusp_free() is called. We can be assured that swap corruption will not occur. Signed-off-by: KAMEZAWA Hiroyuki Cc: "Rafael J. Wysocki" Cc: Hugh Dickins Cc: KOSAKI Motohiro Cc: Ondrej Zary Cc: Balbir Singh Cc: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index ff4acea9bbdb..91c9d3fc8513 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -316,7 +316,6 @@ extern long nr_swap_pages; extern long total_swap_pages; extern void si_swapinfo(struct sysinfo *); extern swp_entry_t get_swap_page(void); -extern swp_entry_t get_swap_page_of_type(int); extern int valid_swaphandles(swp_entry_t, unsigned long *); extern int add_swap_count_continuation(swp_entry_t, gfp_t); extern void swap_shmem_alloc(swp_entry_t); @@ -333,6 +332,13 @@ extern int reuse_swap_page(struct page *); extern int try_to_free_swap(struct page *); struct backing_dev_info; +#ifdef CONFIG_HIBERNATION +void hibernation_freeze_swap(void); +void hibernation_thaw_swap(void); +swp_entry_t get_swap_for_hibernation(int type); +void swap_free_for_hibernation(swp_entry_t val); +#endif + /* linux/mm/thrash.c */ extern struct mm_struct *swap_token_mm; extern void grab_swap_token(struct mm_struct *); -- cgit v1.2.3 From 71abbbf856a0e70ca478782505c800891260ba84 Mon Sep 17 00:00:00 2001 From: Ai Li Date: Mon, 9 Aug 2010 17:20:13 -0700 Subject: cpuidle: extend cpuidle and menu governor to handle dynamic states On some SoC chips, HW resources may be in use during any particular idle period. As a consequence, the cpuidle states that the SoC is safe to enter can change from idle period to idle period. In addition, the latency and threshold of each cpuidle state can vary, depending on the operating condition when the CPU becomes idle, e.g. the current cpu frequency, the current state of the HW blocks, etc. cpuidle core and the menu governor, in the current form, are geared towards cpuidle states that are static, i.e. the availabiltiy of the states, their latencies, their thresholds are non-changing during run time. cpuidle does not provide any hook that cpuidle drivers can use to adjust those values on the fly for the current idle period before the menu governor selects the target cpuidle state. This patch extends cpuidle core and the menu governor to handle states that are dynamic. There are three additions in the patch and the patch maintains backwards-compatibility with existing cpuidle drivers. 1) add prepare() to struct cpuidle_device. A cpuidle driver can hook into the callback and cpuidle will call prepare() before calling the governor's select function. The callback gives the cpuidle driver a chance to update the dynamic information of the cpuidle states for the current idle period, e.g. state availability, latencies, thresholds, power values, etc. 2) add CPUIDLE_FLAG_IGNORE as one of the state flags. In the prepare() function, a cpuidle driver can set/clear the flag to indicate to the menu governor whether a cpuidle state should be ignored, i.e. not available, during the current idle period. 3) add power_specified bit to struct cpuidle_device. The menu governor currently assumes that the cpuidle states are arranged in the order of increasing latency, threshold, and power savings. This is true or can be made true for static states. Once the state parameters are dynamic, the latencies, thresholds, and power savings for the cpuidle states can increase or decrease by different amounts from idle period to idle period. So the assumption of increasing latency, threshold, and power savings from Cn to C(n+1) can no longer be guaranteed. It can be straightforward to calculate the power consumption of each available state and to specify it in power_usage for the idle period. Using the power_usage fields, the menu governor then selects the state that has the lowest power consumption and that still satisfies all other critieria. The power_specified bit defaults to 0. For existing cpuidle drivers, cpuidle detects that power_specified is 0 and fills in a dummy set of power_usage values. Signed-off-by: Ai Li Cc: Len Brown Acked-by: Arjan van de Ven Cc: Ingo Molnar Cc: Venkatesh Pallipadi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpuidle.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 55215cce5005..36ca9721a0c2 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -52,6 +52,7 @@ struct cpuidle_state { #define CPUIDLE_FLAG_SHALLOW (0x20) /* low latency, minimal savings */ #define CPUIDLE_FLAG_BALANCED (0x40) /* medium latency, moderate savings */ #define CPUIDLE_FLAG_DEEP (0x80) /* high latency, large savings */ +#define CPUIDLE_FLAG_IGNORE (0x100) /* ignore during this idle period */ #define CPUIDLE_DRIVER_FLAGS_MASK (0xFFFF0000) @@ -84,6 +85,7 @@ struct cpuidle_state_kobj { struct cpuidle_device { unsigned int registered:1; unsigned int enabled:1; + unsigned int power_specified:1; unsigned int cpu; int last_residency; @@ -97,6 +99,8 @@ struct cpuidle_device { struct completion kobj_unregister; void *governor_data; struct cpuidle_state *safe_state; + + int (*prepare) (struct cpuidle_device *dev); }; DECLARE_PER_CPU(struct cpuidle_device *, cpuidle_devices); -- cgit v1.2.3 From ea6b101d8a3ea4e1dec29df31188c2f9852296fe Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Mon, 9 Aug 2010 17:20:18 -0700 Subject: include/linux/compiler-gcc.h: use __same_type() in __must_be_array() We should use the __same_type() helper in __must_be_array(). Signed-off-by: Rusty Russell Reported-by: Andrew Morton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compiler-gcc.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 0da5b187f124..16508bcddacc 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -35,8 +35,7 @@ (typeof(ptr)) (__ptr + (off)); }) /* &a[0] degrades to a pointer: a different type from an array */ -#define __must_be_array(a) \ - BUILD_BUG_ON_ZERO(__builtin_types_compatible_p(typeof(a), typeof(&a[0]))) +#define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) /* * Force always-inline if the user requests it so via the .config, -- cgit v1.2.3 From cf4ca4874fc45166198424384275f443a672d0b7 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Mon, 9 Aug 2010 17:20:20 -0700 Subject: kernel.h: remove unused NIPQUAD and NIPQUAD_FMT There are no more uses of NIPQUAD or NIPQUAD_FMT. Remove the definitions. Signed-off-by: Joe Perches Cc: "David S. Miller" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 7d5b10ff63e0..5b57236dfbd0 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -615,17 +615,6 @@ ftrace_vprintk(const char *fmt, va_list ap) static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } #endif /* CONFIG_TRACING */ -/* - * Display an IP address in readable format. - */ - -#define NIPQUAD(addr) \ - ((unsigned char *)&addr)[0], \ - ((unsigned char *)&addr)[1], \ - ((unsigned char *)&addr)[2], \ - ((unsigned char *)&addr)[3] -#define NIPQUAD_FMT "%u.%u.%u.%u" - /* * min()/max()/clamp() macros that also do * strict type-checking.. See the -- cgit v1.2.3 From e269b085175acf03fc687a7416b9fd84aa9c6c23 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Mon, 9 Aug 2010 17:20:23 -0700 Subject: iommu: inline iommu_num_pages A profile of a network benchmark showed iommu_num_pages rather high up: 0.52% iommu_num_pages Looking at the profile, an integer divide is taking almost all of the time: % : c000000000376ea4 <.iommu_num_pages>: 1.93 : c000000000376ea4: fb e1 ff f8 std r31,-8(r1) 0.00 : c000000000376ea8: f8 21 ff c1 stdu r1,-64(r1) 0.00 : c000000000376eac: 7c 3f 0b 78 mr r31,r1 3.86 : c000000000376eb0: 38 84 ff ff addi r4,r4,-1 0.00 : c000000000376eb4: 38 05 ff ff addi r0,r5,-1 0.00 : c000000000376eb8: 7c 84 2a 14 add r4,r4,r5 46.95 : c000000000376ebc: 7c 00 18 38 and r0,r0,r3 45.66 : c000000000376ec0: 7c 84 02 14 add r4,r4,r0 0.00 : c000000000376ec4: 7c 64 2b 92 divdu r3,r4,r5 0.00 : c000000000376ec8: 38 3f 00 40 addi r1,r31,64 0.00 : c000000000376ecc: eb e1 ff f8 ld r31,-8(r1) 1.61 : c000000000376ed0: 4e 80 00 20 blr Since every caller of iommu_num_pages passes in a constant power of two we can inline this such that the divide is replaced by a shift. The entire function is only a few instructions once optimised, so it is a good candidate for inlining overall. Signed-off-by: Anton Blanchard Cc: Akinobu Mita Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/iommu-helper.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iommu-helper.h b/include/linux/iommu-helper.h index 64d1b638745d..86bdeffe43ad 100644 --- a/include/linux/iommu-helper.h +++ b/include/linux/iommu-helper.h @@ -1,6 +1,8 @@ #ifndef _LINUX_IOMMU_HELPER_H #define _LINUX_IOMMU_HELPER_H +#include + static inline unsigned long iommu_device_max_index(unsigned long size, unsigned long offset, u64 dma_mask) @@ -20,7 +22,13 @@ extern unsigned long iommu_area_alloc(unsigned long *map, unsigned long size, unsigned long boundary_size, unsigned long align_mask); -extern unsigned long iommu_num_pages(unsigned long addr, unsigned long len, - unsigned long io_page_size); +static inline unsigned long iommu_num_pages(unsigned long addr, + unsigned long len, + unsigned long io_page_size) +{ + unsigned long size = (addr & (io_page_size - 1)) + len; + + return DIV_ROUND_UP(size, io_page_size); +} #endif -- cgit v1.2.3 From ea98eed9bcb62d1319db8b1210712c6a110a886c Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Mon, 9 Aug 2010 17:20:56 -0700 Subject: flex_array: add helpers to get and put to make pointers easy to use Getting and putting arrays of pointers with flex arrays is a PITA. You have to remember to pass &ptr to the _put and you have to do weird and wacky casting to get the ptr back from the _get. Add two functions flex_array_get_ptr() and flex_array_put_ptr() to handle all of the magic. [akpm@linux-foundation.org: simplification suggested by Joe] Signed-off-by: Eric Paris Cc: David Rientjes Cc: Dave Hansen Cc: Joe Perches Cc: James Morris Cc: Joe Perches Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/flex_array.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/flex_array.h b/include/linux/flex_array.h index 1d747f72298b..631b77f2ac70 100644 --- a/include/linux/flex_array.h +++ b/include/linux/flex_array.h @@ -70,4 +70,9 @@ int flex_array_clear(struct flex_array *fa, unsigned int element_nr); void *flex_array_get(struct flex_array *fa, unsigned int element_nr); int flex_array_shrink(struct flex_array *fa); +#define flex_array_put_ptr(fa, nr, src, gfp) \ + flex_array_put(fa, nr, &(void *)(src), gfp) + +void *flex_array_get_ptr(struct flex_array *fa, unsigned int element_nr); + #endif /* _FLEX_ARRAY_H */ -- cgit v1.2.3 From de75d60d5ea235e6e09f4962ab22541ce0fe176a Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 10 Aug 2010 12:14:27 -0400 Subject: block: make sure that REQ_* types are seen even with CONFIG_BLOCK=n These form the basis of the basic WRITE etc primitives, so we need them to be always visible. Otherwise we see errors like: mm/filemap.c:2164: error: 'REQ_WRITE' undeclared fs/read_write.c:362: error: 'REQ_WRITE' undeclared fs/splice.c:1108: error: 'REQ_WRITE' undeclared fs/aio.c:1496: error: 'REQ_WRITE' undeclared Reported-by: Randy Dunlap Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 118523734af0..53691774d34e 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -108,6 +108,8 @@ struct bio { #define BIO_POOL_MASK (1UL << BIO_POOL_OFFSET) #define BIO_POOL_IDX(bio) ((bio)->bi_flags >> BIO_POOL_OFFSET) +#endif /* CONFIG_BLOCK */ + /* * Request flags. For use in the cmd_flags field of struct request, and in * bi_rw of struct bio. Note that some flags are only valid in either one. @@ -189,5 +191,4 @@ enum rq_flag_bits { #define REQ_IO_STAT (1 << __REQ_IO_STAT) #define REQ_MIXED_MERGE (1 << __REQ_MIXED_MERGE) -#endif /* CONFIG_BLOCK */ #endif /* __LINUX_BLK_TYPES_H */ -- cgit v1.2.3 From 26df6d13406d1a53b0bda08bd712f1924affd7cd Mon Sep 17 00:00:00 2001 From: "hyc@symas.com" Date: Tue, 22 Jun 2010 10:14:49 -0700 Subject: tty: Add EXTPROC support for LINEMODE This patch is against the 2.6.34 source. Paraphrased from the 1989 BSD patch by David Borman @ cray.com: These are the changes needed for the kernel to support LINEMODE in the server. There is a new bit in the termios local flag word, EXTPROC. When this bit is set, several aspects of the terminal driver are disabled. Input line editing, character echo, and mapping of signals are all disabled. This allows the telnetd to turn off these functions when in linemode, but still keep track of what state the user wants the terminal to be in. New ioctl: TIOCSIG Generate a signal to processes in the current process group of the pty. There is a new mode for packet driver, the TIOCPKT_IOCTL bit. When packet mode is turned on in the pty, and the EXTPROC bit is set, then whenever the state of the pty is changed, the next read on the master side of the pty will have the TIOCPKT_IOCTL bit set. This allows the process on the server side of the pty to know when the state of the terminal has changed; it can then issue the appropriate ioctl to retrieve the new state. Since the original BSD patches accompanied the source code for telnet I've left that reference here, but obviously the feature is useful for any remote terminal protocol, including ssh. The corresponding feature has existed in the BSD tty driver since 1989. For historical reference, a good copy of the relevant files can be found here: http://anonsvn.mit.edu/viewvc/krb5/trunk/src/appl/telnet/?pathrev=17741 Signed-off-by: Howard Chu Cc: Alan Cox Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 7802a243ee13..2df60e4ff40e 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -179,6 +179,7 @@ struct tty_bufhead { #define L_FLUSHO(tty) _L_FLAG((tty), FLUSHO) #define L_PENDIN(tty) _L_FLAG((tty), PENDIN) #define L_IEXTEN(tty) _L_FLAG((tty), IEXTEN) +#define L_EXTPROC(tty) _L_FLAG((tty), EXTPROC) struct device; struct signal_struct; -- cgit v1.2.3 From 8fd4bd22350784d5b2fe9274f6790ba353976415 Mon Sep 17 00:00:00 2001 From: Jesse Barnes Date: Wed, 23 Jun 2010 12:56:12 -0700 Subject: vt/console: try harder to print output when panicing Jesse's initial patch commit said: "At panic time (i.e. when oops_in_progress is set) we should try a bit harder to update the screen and make sure output gets to the VT, since some drivers are capable of flipping back to it. So make sure we try to unblank and update the display if called from a panic context." I've enhanced this to add a flag to the vc that console layer can set to indicate they want this behaviour to occur. This also adds support to fbcon for that flag and adds an fb flag for drivers to indicate they want to use the support. It enables this for KMS drivers. Signed-off-by: Dave Airlie Signed-off-by: Jesse Barnes Acked-by: James Simmons Cc: Alan Cox Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- include/linux/console_struct.h | 1 + include/linux/fb.h | 4 ++++ include/linux/vt_kern.h | 7 +++++++ 3 files changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h index 38fe59dc89ae..d7d9acdccffb 100644 --- a/include/linux/console_struct.h +++ b/include/linux/console_struct.h @@ -105,6 +105,7 @@ struct vc_data { struct vc_data **vc_display_fg; /* [!] Ptr to var holding fg console for this display */ unsigned long vc_uni_pagedir; unsigned long *vc_uni_pagedir_loc; /* [!] Location of uni_pagedir variable for this console */ + bool vc_panic_force_write; /* when oops/panic this VC can accept forced output/blanking */ /* additional information is in vt_kern.h */ }; diff --git a/include/linux/fb.h b/include/linux/fb.h index 0c5659c41b01..f0268deca658 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -825,6 +825,10 @@ struct fb_tile_ops { */ #define FBINFO_BE_MATH 0x100000 +/* report to the VT layer that this fb driver can accept forced console + output like oopses */ +#define FBINFO_CAN_FORCE_OUTPUT 0x200000 + struct fb_info { int node; int flags; diff --git a/include/linux/vt_kern.h b/include/linux/vt_kern.h index 7f56db4a79f0..56cce345aa8d 100644 --- a/include/linux/vt_kern.h +++ b/include/linux/vt_kern.h @@ -100,6 +100,13 @@ extern int unbind_con_driver(const struct consw *csw, int first, int last, int deflt); int vty_init(const struct file_operations *console_fops); +static inline bool vt_force_oops_output(struct vc_data *vc) +{ + if (oops_in_progress && vc->vc_panic_force_write) + return true; + return false; +} + /* * vc_screen.c shares this temporary buffer with the console write code so that * we can easily avoid touching user space while holding the console spinlock. -- cgit v1.2.3 From 8a1e803d0148e320b9200a442dfb88f8cbde88e7 Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Tue, 1 Jun 2010 22:52:42 +0200 Subject: istallion: use bit ops for the board flags This lets us avoid problems with races on the flag changes Signed-off-by: Alan Cox Cc: Arnd Bergmann Signed-off-by: Greg Kroah-Hartman --- include/linux/istallion.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/istallion.h b/include/linux/istallion.h index 7faca98c7d14..ad700a60c158 100644 --- a/include/linux/istallion.h +++ b/include/linux/istallion.h @@ -86,7 +86,7 @@ struct stlibrd { unsigned long magic; unsigned int brdnr; unsigned int brdtype; - unsigned int state; + unsigned long state; unsigned int nrpanels; unsigned int nrports; unsigned int nrdevs; -- cgit v1.2.3 From d87d9b7d19f04b16c4406d3c0feeca10090e0ada Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Tue, 1 Jun 2010 22:52:53 +0200 Subject: tty: serial - fix tty referencing in set_ldisc Pass down the ldisc number so that the drivers don't have to peek into the tty object themselves. This lets us get rid of another case of back referencing port to tty which we don't want (because of races versus hangup/close). Signed-off-by: Alan Cox Cc: Arnd Bergmann Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index f10db6e5f3b5..32928161fab6 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -220,7 +220,7 @@ struct uart_ops { void (*flush_buffer)(struct uart_port *); void (*set_termios)(struct uart_port *, struct ktermios *new, struct ktermios *old); - void (*set_ldisc)(struct uart_port *); + void (*set_ldisc)(struct uart_port *, int new); void (*pm)(struct uart_port *, unsigned int state, unsigned int oldstate); int (*set_wake)(struct uart_port *, unsigned int state); -- cgit v1.2.3 From ff917ba4f1a6189f90ed2c975984d6a1a1dc553d Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Tue, 1 Jun 2010 22:52:55 +0200 Subject: tty: Make vt's have a tty_port The vt layer isn't safely handling reference counts to tty object on the input side. Add a tty port structure to the vt layer in order to implement this using the standard helpers. Signed-off-by: Alan Cox Cc: Arnd Bergmann Signed-off-by: Greg Kroah-Hartman --- include/linux/console_struct.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h index d7d9acdccffb..25bf67f541fc 100644 --- a/include/linux/console_struct.h +++ b/include/linux/console_struct.h @@ -21,6 +21,8 @@ struct vt_struct; #define NPAR 16 struct vc_data { + struct tty_port port; /* Upper level data */ + unsigned short vc_num; /* Console number */ unsigned int vc_cols; /* [#] Console size */ unsigned int vc_rows; -- cgit v1.2.3 From 8ce73264b75be4d5ed480440ac32dfc1f25ff678 Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Tue, 1 Jun 2010 22:52:56 +0200 Subject: tty: Move the vt_tty field from the vc_data into the standard tty_port This takes all the tty references through the expected interface points so we can refcount them. Signed-off-by: Alan Cox Cc: Arnd Bergmann Signed-off-by: Greg Kroah-Hartman --- include/linux/console_struct.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h index 25bf67f541fc..7f0c32908568 100644 --- a/include/linux/console_struct.h +++ b/include/linux/console_struct.h @@ -58,7 +58,6 @@ struct vc_data { /* VT terminal data */ unsigned int vc_state; /* Escape sequence parser state */ unsigned int vc_npar,vc_par[NPAR]; /* Parameters of current escape sequence */ - struct tty_struct *vc_tty; /* TTY we are attached to */ /* data for manual vt switching */ struct vt_mode vt_mode; struct pid *vt_pid; -- cgit v1.2.3 From ec79d6056de58511d8e46d9ae59d3878f958dc3e Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 1 Jun 2010 22:53:01 +0200 Subject: tty: replace BKL with a new tty_lock As a preparation for replacing the big kernel lock in the TTY layer, wrap all the callers in new macros tty_lock, tty_lock_nested and tty_unlock. Signed-off-by: Arnd Bergmann Cc: Alan Cox Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 2df60e4ff40e..6ead6b60c743 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -13,6 +13,7 @@ #include #include #include +#include #include @@ -576,5 +577,35 @@ extern int vt_ioctl(struct tty_struct *tty, struct file *file, extern long vt_compat_ioctl(struct tty_struct *tty, struct file * file, unsigned int cmd, unsigned long arg); +/* functions for preparation of BKL removal */ + +/* + * tty_lock_nested get the tty_lock while potentially holding it + * + * The Big TTY Mutex is a recursive lock, meaning you can take it + * from a thread that is already holding it. + * This is bad for a number of reasons, so tty_lock_nested should + * really be used as rarely as possible. If a code location can + * be shown to never get called with this held already, it should + * use tty_lock() instead. + */ +static inline void __lockfunc tty_lock_nested(void) __acquires(kernel_lock) +{ + lock_kernel(); +} +static inline void tty_lock(void) __acquires(kernel_lock) +{ +#ifdef CONFIG_LOCK_KERNEL + /* kernel_locked is 1 for !CONFIG_LOCK_KERNEL */ + WARN_ON(kernel_locked()); +#endif + lock_kernel(); +} +static inline void tty_unlock(void) __releases(kernel_lock) +{ + unlock_kernel(); +} +#define tty_locked() (kernel_locked()) + #endif /* __KERNEL__ */ #endif -- cgit v1.2.3 From be1bc2889a4db4961ef69f47fb471ecae9f23ade Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 1 Jun 2010 22:53:05 +0200 Subject: tty: introduce wait_event_interruptible_tty Calling wait_event_interruptible implicitly releases the BKL when it sleeps, but we need to do this explcitly when we have converted it to a mutex. Signed-off-by: Arnd Bergmann Cc: Alan Cox Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 42 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 42 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 6ead6b60c743..955d72ea71c0 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -607,5 +607,47 @@ static inline void tty_unlock(void) __releases(kernel_lock) } #define tty_locked() (kernel_locked()) +/* + * wait_event_interruptible_tty -- wait for a condition with the tty lock held + * + * The condition we are waiting for might take a long time to + * become true, or might depend on another thread taking the + * BTM. In either case, we need to drop the BTM to guarantee + * forward progress. This is a leftover from the conversion + * from the BKL and should eventually get removed as the BTM + * falls out of use. + * + * Do not use in new code. + */ +#define wait_event_interruptible_tty(wq, condition) \ +({ \ + int __ret = 0; \ + if (!(condition)) { \ + __wait_event_interruptible_tty(wq, condition, __ret); \ + } \ + __ret; \ +}) + +#define __wait_event_interruptible_tty(wq, condition, ret) \ +do { \ + DEFINE_WAIT(__wait); \ + \ + for (;;) { \ + prepare_to_wait(&wq, &__wait, TASK_INTERRUPTIBLE); \ + if (condition) \ + break; \ + if (!signal_pending(current)) { \ + tty_unlock(); \ + schedule(); \ + tty_lock(); \ + continue; \ + } \ + ret = -ERESTARTSYS; \ + break; \ + } \ + finish_wait(&wq, &__wait); \ +} while (0) + + #endif /* __KERNEL__ */ #endif -- cgit v1.2.3 From ddcd9fb66ae7f448b517242c10a31d4e17bcad45 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 1 Jun 2010 22:53:08 +0200 Subject: tty: remove tty_lock_nested This changes all remaining users of tty_lock_nested to be non-recursive, which lets us kill this function. As a consequence, we won't need to keep the lock count any more, which allows more simplifications later. Signed-off-by: Arnd Bergmann Cc: Alan Cox Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 16 +--------------- 1 file changed, 1 insertion(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 955d72ea71c0..0fbafb0b69bf 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -417,6 +417,7 @@ extern int is_ignored(int sig); extern int tty_signal(int sig, struct tty_struct *tty); extern void tty_hangup(struct tty_struct *tty); extern void tty_vhangup(struct tty_struct *tty); +extern void tty_vhangup_locked(struct tty_struct *tty); extern void tty_vhangup_self(void); extern void tty_unhangup(struct file *filp); extern int tty_hung_up_p(struct file *filp); @@ -578,21 +579,6 @@ extern long vt_compat_ioctl(struct tty_struct *tty, struct file * file, unsigned int cmd, unsigned long arg); /* functions for preparation of BKL removal */ - -/* - * tty_lock_nested get the tty_lock while potentially holding it - * - * The Big TTY Mutex is a recursive lock, meaning you can take it - * from a thread that is already holding it. - * This is bad for a number of reasons, so tty_lock_nested should - * really be used as rarely as possible. If a code location can - * be shown to never get called with this held already, it should - * use tty_lock() instead. - */ -static inline void __lockfunc tty_lock_nested(void) __acquires(kernel_lock) -{ - lock_kernel(); -} static inline void tty_lock(void) __acquires(kernel_lock) { #ifdef CONFIG_LOCK_KERNEL -- cgit v1.2.3 From b07471fa51358ce64cc25e1501544502362e4404 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 6 Aug 2010 21:40:30 +0200 Subject: tty: implement BTM as mutex instead of BKL The tty locking now follows the rules for mutexes, so we can replace the BKL usage with a new subsystem wide mutex. Using a regular mutex here will change the behaviour when blocked on the BTM from spinning to sleeping, but that should not be visible to the user. Using the mutex also means that all the BTM is now covered by lockdep. Signed-off-by: Arnd Bergmann Cc: Alan Cox Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 18 +++++------------- 1 file changed, 5 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 0fbafb0b69bf..1437da3ddc62 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -578,20 +578,12 @@ extern int vt_ioctl(struct tty_struct *tty, struct file *file, extern long vt_compat_ioctl(struct tty_struct *tty, struct file * file, unsigned int cmd, unsigned long arg); +/* tty_mutex.c */ /* functions for preparation of BKL removal */ -static inline void tty_lock(void) __acquires(kernel_lock) -{ -#ifdef CONFIG_LOCK_KERNEL - /* kernel_locked is 1 for !CONFIG_LOCK_KERNEL */ - WARN_ON(kernel_locked()); -#endif - lock_kernel(); -} -static inline void tty_unlock(void) __releases(kernel_lock) -{ - unlock_kernel(); -} -#define tty_locked() (kernel_locked()) +extern void __lockfunc tty_lock(void) __acquires(tty_lock); +extern void __lockfunc tty_unlock(void) __releases(tty_lock); +extern struct task_struct *__big_tty_mutex_owner; +#define tty_locked() (current == __big_tty_mutex_owner) /* * wait_event_interruptible_tty -- wait for a condition with the tty lock held -- cgit v1.2.3 From 61fd15262bb9c88a05fd89af22add9317dc1b1f4 Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Wed, 30 Jun 2010 17:58:38 +0100 Subject: serial: max3107: Abstract out the platform specific bits At the moment there is only one platform type supported and there is is hard wired, but with these changes the infrastructure is now there for anyone else to provide methods for their hardware. Signed-off-by: Alan Cox Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 32928161fab6..9ddc866ccc09 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -186,6 +186,10 @@ #define PORT_ALTERA_JTAGUART 91 #define PORT_ALTERA_UART 92 +/* MAX3107 */ +#define PORT_MAX3107 94 + + #ifdef __KERNEL__ #include -- cgit v1.2.3 From 75e0b946cf2fef14236ff999b6d7eacbae2034b0 Mon Sep 17 00:00:00 2001 From: Kevin Winchester Date: Sat, 10 Jul 2010 18:57:56 -0300 Subject: vt: Fix warning: statement with no effect due to vt_kern.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Using: gcc (GCC) 4.5.0 20100610 (prerelease) with CONFIG_CONSOLE_TRANSLATIONS=n, the following warnings are seen: drivers/char/vt_ioctl.c: In function ‘vt_ioctl’: drivers/char/vt_ioctl.c:1309:4: warning: statement with no effect drivers/char/vt.c: In function ‘vc_allocate’: drivers/char/vt.c:774:3: warning: statement with no effect drivers/video/console/vgacon.c: In function ‘vgacon_init’: drivers/video/console/vgacon.c:587:3: warning: statement with no effect drivers/video/console/vgacon.c: In function ‘vgacon_deinit’: drivers/video/console/vgacon.c:606:2: warning: statement with no effect drivers/video/console/fbcon.c: In function ‘fbcon_init’: drivers/video/console/fbcon.c:1087:3: warning: statement with no effect drivers/video/console/fbcon.c:1089:3: warning: statement with no effect drivers/video/console/fbcon.c: In function ‘fbcon_set_disp’: drivers/video/console/fbcon.c:1369:3: warning: statement with no effect drivers/video/console/fbcon.c:1371:3: warning: statement with no effect This is because several functions in include/linux/vt_kern.h are defined to (0). Convert them to static inline functions to silence the warnings and gain a bit of type safety. Signed-off-by: Kevin Winchester Signed-off-by: Greg Kroah-Hartman --- include/linux/vt_kern.h | 57 +++++++++++++++++++++++++++++++++++++++---------- 1 file changed, 46 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vt_kern.h b/include/linux/vt_kern.h index 56cce345aa8d..6625cc1ab758 100644 --- a/include/linux/vt_kern.h +++ b/include/linux/vt_kern.h @@ -76,17 +76,52 @@ int con_copy_unimap(struct vc_data *dst_vc, struct vc_data *src_vc); #define vc_translate(vc, c) ((vc)->vc_translate[(c) | \ ((vc)->vc_toggle_meta ? 0x80 : 0)]) #else -#define con_set_trans_old(arg) (0) -#define con_get_trans_old(arg) (-EINVAL) -#define con_set_trans_new(arg) (0) -#define con_get_trans_new(arg) (-EINVAL) -#define con_clear_unimap(vc, ui) (0) -#define con_set_unimap(vc, ct, list) (0) -#define con_set_default_unimap(vc) (0) -#define con_copy_unimap(d, s) (0) -#define con_get_unimap(vc, ct, uct, list) (-EINVAL) -#define con_free_unimap(vc) do { ; } while (0) -#define con_protect_unimap(vc, rdonly) do { ; } while (0) +static inline int con_set_trans_old(unsigned char __user *table) +{ + return 0; +} +static inline int con_get_trans_old(unsigned char __user *table) +{ + return -EINVAL; +} +static inline int con_set_trans_new(unsigned short __user *table) +{ + return 0; +} +static inline int con_get_trans_new(unsigned short __user *table) +{ + return -EINVAL; +} +static inline int con_clear_unimap(struct vc_data *vc, struct unimapinit *ui) +{ + return 0; +} +static inline +int con_set_unimap(struct vc_data *vc, ushort ct, struct unipair __user *list) +{ + return 0; +} +static inline +int con_get_unimap(struct vc_data *vc, ushort ct, ushort __user *uct, + struct unipair __user *list) +{ + return -EINVAL; +} +static inline int con_set_default_unimap(struct vc_data *vc) +{ + return 0; +} +static inline void con_free_unimap(struct vc_data *vc) +{ +} +static inline void con_protect_unimap(struct vc_data *vc, int rdonly) +{ +} +static inline +int con_copy_unimap(struct vc_data *dst_vc, struct vc_data *src_vc) +{ + return 0; +} #define vc_translate(vc, c) (c) #endif -- cgit v1.2.3 From 93e3d58284626ff6466f9c3dac8800cd6f8079c6 Mon Sep 17 00:00:00 2001 From: John Villalovos Date: Tue, 20 Jul 2010 15:26:46 -0700 Subject: serial: fix missing bit coverage of ASYNC_FLAGS It seems that currently ASYNC_FLAGS is one bit short of covering all the bits of the ASYNC user flags. In particular it does not cover the ASYNC_AUTOPROBE bit. ASYNCB_LAST_USER and ASYNCB_AUTOPROBE are both equal to 15. Therefore: ASYNC_AUTOPROBE = 1000 0000 0000 0000 ASYNC_FLAGS = 0111 1111 1111 1111 So ASYNC_FLAGS is not covering the ASYNC_AUTOPROBE bit. This patch fixes the issue and with the patch the values will be: ASYNC_AUTOPROBE = 1000 0000 0000 0000 ASYNC_FLAGS = 1111 1111 1111 1111 As a side note, doing a "git grep" I didn't find any use of ASYNC_AUTOPROBE or ASYNCB_AUTOPROBE in the kernel, besides this include file. Signed-off-by: John Villalovos Cc: Alan Cox Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- include/linux/serial.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/serial.h b/include/linux/serial.h index c8613c3ff9d3..c3b45add494d 100644 --- a/include/linux/serial.h +++ b/include/linux/serial.h @@ -151,7 +151,7 @@ struct serial_uart_config { #define ASYNC_BUGGY_UART (1U << ASYNCB_BUGGY_UART) #define ASYNC_AUTOPROBE (1U << ASYNCB_AUTOPROBE) -#define ASYNC_FLAGS ((1U << ASYNCB_LAST_USER) - 1) +#define ASYNC_FLAGS ((1U << (ASYNCB_LAST_USER + 1)) - 1) #define ASYNC_USR_MASK (ASYNC_SPD_HI|ASYNC_SPD_VHI| \ ASYNC_CALLOUT_NOHUP|ASYNC_SPD_SHI|ASYNC_LOW_LATENCY) #define ASYNC_SPD_CUST (ASYNC_SPD_HI|ASYNC_SPD_VHI) -- cgit v1.2.3 From 1b6331848b69d1ed165a6bdc75c4046d68767563 Mon Sep 17 00:00:00 2001 From: Claudio Scordino Date: Tue, 20 Jul 2010 15:26:47 -0700 Subject: serial: general fixes in the serial_rs485 structure Fix several issues related to the RS485 interface: - It adds the flag SER_RS485_RTS_BEFORE_SEND that was missing from the serial_rs485 structure (even if "delay_rts_before_send" was existing) - It adds a further "delay_rts_after_send" field for those drivers that can have a delay after send (e.g., atmel_serial) - It fixes the usage of the structure in the atmel_serial driver (where "delay_rts_before_send" should be used instead of "delay_rts_after_send"). Signed-off-by: Claudio Scordino Signed-off-by: Bernhard Roth Cc: Philippe De Muyter Cc: Alan Cox Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- include/linux/serial.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/serial.h b/include/linux/serial.h index c3b45add494d..ef914061511e 100644 --- a/include/linux/serial.h +++ b/include/linux/serial.h @@ -210,8 +210,10 @@ struct serial_rs485 { #define SER_RS485_ENABLED (1 << 0) #define SER_RS485_RTS_ON_SEND (1 << 1) #define SER_RS485_RTS_AFTER_SEND (1 << 2) +#define SER_RS485_RTS_BEFORE_SEND (1 << 3) __u32 delay_rts_before_send; /* Milliseconds */ - __u32 padding[6]; /* Memory is cheap, new structs + __u32 delay_rts_after_send; /* Milliseconds */ + __u32 padding[5]; /* Memory is cheap, new structs are a royal PITA .. */ }; -- cgit v1.2.3 From d843fc6e9dc9bee7061b6833594860ea93ad98e1 Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Tue, 27 Jul 2010 08:20:22 +0100 Subject: hsu: driver for Medfield High Speed UART device This is a PCI & UART driver, which suppors both PIO and DMA mode UART operation. It has 3 identical UART ports and one internal DMA controller. Current FW will export 4 pci devices for hsu: 3 uart ports and 1 dma controller, each has one IRQ line. And we need to discuss the device model, one PCI device covering whole HSU should be a better model, but there is a problem of how to export the 4 IRQs info Current driver set the highest baud rate to 2746800bps, which is easy to scale down to 115200/230400.... To suport higher baud rate, we need add special process, change DLAB/DLH/PS/DIV/MUL registers all together. 921600 is the highest baud rate that has been tested with Bluetooth modem connected to HSU port 0. Will test more when there is right BT firmware. Current version contains several work around for A0's Silicon bugs Signed-off-by: Feng Tang Signed-off-by: Alan Cox Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 2 ++ include/linux/serial_mfd.h | 47 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/serial_reg.h | 16 +++++++++++++++ 3 files changed, 65 insertions(+) create mode 100644 include/linux/serial_mfd.h (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 9ddc866ccc09..f8fce351463d 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -189,6 +189,8 @@ /* MAX3107 */ #define PORT_MAX3107 94 +/* High Speed UART for Medfield */ +#define PORT_MFD 95 #ifdef __KERNEL__ diff --git a/include/linux/serial_mfd.h b/include/linux/serial_mfd.h new file mode 100644 index 000000000000..2b071e0b034d --- /dev/null +++ b/include/linux/serial_mfd.h @@ -0,0 +1,47 @@ +#ifndef _SERIAL_MFD_H_ +#define _SERIAL_MFD_H_ + +/* HW register offset definition */ +#define UART_FOR 0x08 +#define UART_PS 0x0C +#define UART_MUL 0x0D +#define UART_DIV 0x0E + +#define HSU_GBL_IEN 0x0 +#define HSU_GBL_IST 0x4 + +#define HSU_GBL_INT_BIT_PORT0 0x0 +#define HSU_GBL_INT_BIT_PORT1 0x1 +#define HSU_GBL_INT_BIT_PORT2 0x2 +#define HSU_GBL_INT_BIT_IRI 0x3 +#define HSU_GBL_INT_BIT_HDLC 0x4 +#define HSU_GBL_INT_BIT_DMA 0x5 + +#define HSU_GBL_ISR 0x8 +#define HSU_GBL_DMASR 0x400 +#define HSU_GBL_DMAISR 0x404 + +#define HSU_PORT_REG_OFFSET 0x80 +#define HSU_PORT0_REG_OFFSET 0x80 +#define HSU_PORT1_REG_OFFSET 0x100 +#define HSU_PORT2_REG_OFFSET 0x180 +#define HSU_PORT_REG_LENGTH 0x80 + +#define HSU_DMA_CHANS_REG_OFFSET 0x500 +#define HSU_DMA_CHANS_REG_LENGTH 0x40 + +#define HSU_CH_SR 0x0 /* channel status reg */ +#define HSU_CH_CR 0x4 /* control reg */ +#define HSU_CH_DCR 0x8 /* descriptor control reg */ +#define HSU_CH_BSR 0x10 /* max fifo buffer size reg */ +#define HSU_CH_MOTSR 0x14 /* minimum ocp transfer size */ +#define HSU_CH_D0SAR 0x20 /* desc 0 start addr */ +#define HSU_CH_D0TSR 0x24 /* desc 0 transfer size */ +#define HSU_CH_D1SAR 0x28 +#define HSU_CH_D1TSR 0x2C +#define HSU_CH_D2SAR 0x30 +#define HSU_CH_D2TSR 0x34 +#define HSU_CH_D3SAR 0x38 +#define HSU_CH_D3TSR 0x3C + +#endif diff --git a/include/linux/serial_reg.h b/include/linux/serial_reg.h index cf9327c051ad..c7a0ce11cd47 100644 --- a/include/linux/serial_reg.h +++ b/include/linux/serial_reg.h @@ -221,8 +221,24 @@ #define UART_FCR_PXAR16 0x80 /* receive FIFO threshold = 16 */ #define UART_FCR_PXAR32 0xc0 /* receive FIFO threshold = 32 */ +/* + * Intel MID on-chip HSU (High Speed UART) defined bits + */ +#define UART_FCR_HSU_64_1B 0x00 /* receive FIFO treshold = 1 */ +#define UART_FCR_HSU_64_16B 0x40 /* receive FIFO treshold = 16 */ +#define UART_FCR_HSU_64_32B 0x80 /* receive FIFO treshold = 32 */ +#define UART_FCR_HSU_64_56B 0xc0 /* receive FIFO treshold = 56 */ + +#define UART_FCR_HSU_16_1B 0x00 /* receive FIFO treshold = 1 */ +#define UART_FCR_HSU_16_4B 0x40 /* receive FIFO treshold = 4 */ +#define UART_FCR_HSU_16_8B 0x80 /* receive FIFO treshold = 8 */ +#define UART_FCR_HSU_16_14B 0xc0 /* receive FIFO treshold = 14 */ +#define UART_FCR_HSU_64B_FIFO 0x20 /* chose 64 bytes FIFO */ +#define UART_FCR_HSU_16B_FIFO 0x00 /* chose 16 bytes FIFO */ +#define UART_FCR_HALF_EMPT_TXI 0x00 /* trigger TX_EMPT IRQ for half empty */ +#define UART_FCR_FULL_EMPT_TXI 0x08 /* trigger TX_EMPT IRQ for full empty */ /* * These register definitions are for the 16C950 -- cgit v1.2.3 From 235dae5d094c415fcf0fc79fa637f1901bc8afe2 Mon Sep 17 00:00:00 2001 From: Philippe Langlais Date: Thu, 29 Jul 2010 17:13:57 +0200 Subject: U6715 16550A serial driver support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit UART Features extract from STEricsson U6715 data-sheet (arm926 SoC for mobile phone): * Fully compatible with industry standard 16C550 and 16C450 from various manufacturers * RX and TX 64 byte FIFO reduces CPU interrupts * Full double buffering * Modem control signals include CTS, RTS, (and DSR, DTR on UART1 only) * Automatic baud rate selection * Manual or automatic RTS/CTS smart hardware flow control * Programmable serial characteristics: – Baud rate generation (50 to 3.25M baud) – 5, 6, 7 or 8-bit characters – Even, odd or no-parity bit generation and detection – 1, 1.5 or 2 stop bit generation * Independent control of transmit, receive, line status, data set interrupts and FIFOs * Full status-reporting capabilities * Separate DMA signaling for RX and TX * Timed interrupt to spread receive interrupt on known duration * DMA time-out interrupt to allow detection of end of reception * Carkit pulse coding and decoding compliant with USB carkit control interface [40] In 16550A auto-configuration, if the fifo size is 64 then it's an U6 16550A port Add set_termios hook & export serial8250_do_set_termios to change uart clock following baudrate Signed-off-by: Philippe Langlais Acked-by: Alan Cox Signed-off-by: Greg Kroah-Hartman --- include/linux/serial.h | 3 ++- include/linux/serial_8250.h | 5 +++++ include/linux/serial_core.h | 3 +++ 3 files changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/serial.h b/include/linux/serial.h index ef914061511e..1ebc694a6d52 100644 --- a/include/linux/serial.h +++ b/include/linux/serial.h @@ -77,7 +77,8 @@ struct serial_struct { #define PORT_16654 11 #define PORT_16850 12 #define PORT_RSA 13 /* RSA-DV II/S card */ -#define PORT_MAX 13 +#define PORT_U6_16550A 14 +#define PORT_MAX 14 #define SERIAL_IO_PORT 0 #define SERIAL_IO_HUB6 1 diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index fb46aba11fb5..7638deaaba65 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -32,6 +32,9 @@ struct plat_serial8250_port { unsigned int type; /* If UPF_FIXED_TYPE */ unsigned int (*serial_in)(struct uart_port *, int); void (*serial_out)(struct uart_port *, int, int); + void (*set_termios)(struct uart_port *, + struct ktermios *new, + struct ktermios *old); }; /* @@ -71,5 +74,7 @@ extern int early_serial_setup(struct uart_port *port); extern int serial8250_find_port(struct uart_port *p); extern int serial8250_find_port_for_earlycon(void); extern int setup_early_serial8250_console(char *cmdline); +extern void serial8250_do_set_termios(struct uart_port *port, + struct ktermios *termios, struct ktermios *old); #endif diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index f8fce351463d..8129ca2d57e3 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -282,6 +282,9 @@ struct uart_port { unsigned char __iomem *membase; /* read/write[bwl] */ unsigned int (*serial_in)(struct uart_port *, int); void (*serial_out)(struct uart_port *, int, int); + void (*set_termios)(struct uart_port *, + struct ktermios *new, + struct ktermios *old); unsigned int irq; /* irq number */ unsigned long irqflags; /* irq flags */ unsigned int uartclk; /* base uart clock */ -- cgit v1.2.3 From 6d88e6792574497bfac9a81403cc47712040636f Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Wed, 9 Jun 2010 17:34:17 -0400 Subject: USB: don't stop root-hub status polls too soon This patch (as1390) fixes a problem that crops up when a UHCI host controller is unbound from uhci-hcd while there are still some active URBs. The URBs have to be unlinked when the root hub is unregistered, and uhci-hcd relies upon root-hub status polls as part of its unlinking procedure. But usb_hcd_poll_rh_status() won't make those status calls if hcd->rh_registered is clear, and the flag is cleared _before_ the unregistration takes place. Since hcd->rh_registered is used for other things and needs to be cleared early, the solution is to add a new flag (rh_pollable) and use it instead. It gets cleared _after_ the root hub is unregistered. Now that the status polls don't end too soon, we have to make sure they also don't occur too late -- after the root hub's usb_device structure or the HCD's private structures are deallocated. Therefore the patch adds usb_get_device() and usb_put_device() calls to protect the root hub structure, and it adds an extra del_timer_sync() to prevent the root-hub timer from causing an unexpected status poll. This additional complexity would not be needed if the HCD framework had provided separate stop() and release() callbacks instead of just stop(). This lack could be fixed at some future time (although it would require changes to every host controller driver); when that happens this patch won't be needed any more. Signed-off-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/hcd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 2e3a4ea1a3da..11b638195901 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -95,6 +95,7 @@ struct usb_hcd { #define HCD_FLAG_SAW_IRQ 0x00000002 unsigned rh_registered:1;/* is root hub registered? */ + unsigned rh_pollable:1; /* may we poll the root hub? */ /* The next flag is a stopgap, to be removed when all the HCDs * support the new root-hub polling mechanism. */ -- cgit v1.2.3 From 6e1c3b467ffd9d6eb725dda544f6fd10e471ea71 Mon Sep 17 00:00:00 2001 From: Igor Grinberg Date: Thu, 27 May 2010 09:32:13 +0300 Subject: USB: otg.h: Fix the mixup in parameters order. otg_io_write() function does not follow the declaration of struct otg_io_access_ops. Signed-off-by: Igor Grinberg Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/otg.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/otg.h b/include/linux/usb/otg.h index f8302d036a76..54b2c5e48b9d 100644 --- a/include/linux/usb/otg.h +++ b/include/linux/usb/otg.h @@ -146,10 +146,10 @@ static inline int otg_io_read(struct otg_transceiver *otg, u32 reg) return -EINVAL; } -static inline int otg_io_write(struct otg_transceiver *otg, u32 reg, u32 val) +static inline int otg_io_write(struct otg_transceiver *otg, u32 val, u32 reg) { if (otg->io_ops && otg->io_ops->write) - return otg->io_ops->write(otg, reg, val); + return otg->io_ops->write(otg, val, reg); return -EINVAL; } -- cgit v1.2.3 From aa4d8342988d0c1a79ff19b2ede1e81dfbb16ea5 Mon Sep 17 00:00:00 2001 From: Alek Du Date: Fri, 4 Jun 2010 15:47:54 +0800 Subject: USB: EHCI: EHCI 1.1 addendum: preparation EHCI 1.1 addendum introduced several energy efficiency extensions for EHCI USB host controllers: 1. LPM (link power management) 2. Per-port change 3. Shorter periodic frame list 4. Hardware prefetching This patch is intended to define the HW bits and debug interface for EHCI 1.1 addendum. The LPM and Per-port change patches will be sent out after this patch. Signed-off-by: Jacob Pan Signed-off-by: Alek Du Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/ehci_def.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/ehci_def.h b/include/linux/usb/ehci_def.h index 80287af2a738..2e262cb15425 100644 --- a/include/linux/usb/ehci_def.h +++ b/include/linux/usb/ehci_def.h @@ -39,6 +39,12 @@ struct ehci_caps { #define HCS_N_PORTS(p) (((p)>>0)&0xf) /* bits 3:0, ports on HC */ u32 hcc_params; /* HCCPARAMS - offset 0x8 */ +/* EHCI 1.1 addendum */ +#define HCC_32FRAME_PERIODIC_LIST(p) ((p)&(1 << 19)) +#define HCC_PER_PORT_CHANGE_EVENT(p) ((p)&(1 << 18)) +#define HCC_LPM(p) ((p)&(1 << 17)) +#define HCC_HW_PREFETCH(p) ((p)&(1 << 16)) + #define HCC_EXT_CAPS(p) (((p)>>8)&0xff) /* for pci extended caps */ #define HCC_ISOC_CACHE(p) ((p)&(1 << 7)) /* true: can cache isoc frame */ #define HCC_ISOC_THRES(p) (((p)>>4)&0x7) /* bits 6:4, uframes cached */ @@ -54,6 +60,13 @@ struct ehci_regs { /* USBCMD: offset 0x00 */ u32 command; + +/* EHCI 1.1 addendum */ +#define CMD_HIRD (0xf<<24) /* host initiated resume duration */ +#define CMD_PPCEE (1<<15) /* per port change event enable */ +#define CMD_FSP (1<<14) /* fully synchronized prefetch */ +#define CMD_ASPE (1<<13) /* async schedule prefetch enable */ +#define CMD_PSPE (1<<12) /* periodic schedule prefetch enable */ /* 23:16 is r/w intr rate, in microframes; default "8" == 1/msec */ #define CMD_PARK (1<<11) /* enable "park" on async qh */ #define CMD_PARK_CNT(c) (((c)>>8)&3) /* how many transfers to park for */ @@ -67,6 +80,7 @@ struct ehci_regs { /* USBSTS: offset 0x04 */ u32 status; +#define STS_PPCE_MASK (0xff<<16) /* Per-Port change event 1-16 */ #define STS_ASS (1<<15) /* Async Schedule Status */ #define STS_PSS (1<<14) /* Periodic Schedule Status */ #define STS_RECL (1<<13) /* Reclamation */ @@ -100,6 +114,14 @@ struct ehci_regs { /* PORTSC: offset 0x44 */ u32 port_status[0]; /* up to N_PORTS */ +/* EHCI 1.1 addendum */ +#define PORTSC_SUSPEND_STS_ACK 0 +#define PORTSC_SUSPEND_STS_NYET 1 +#define PORTSC_SUSPEND_STS_STALL 2 +#define PORTSC_SUSPEND_STS_ERR 3 + +#define PORT_DEV_ADDR (0x7f<<25) /* device address */ +#define PORT_SSTS (0x3<<23) /* suspend status */ /* 31:23 reserved */ #define PORT_WKOC_E (1<<22) /* wake on overcurrent (enable) */ #define PORT_WKDISC_E (1<<21) /* wake on disconnect (enable) */ @@ -115,6 +137,7 @@ struct ehci_regs { #define PORT_USB11(x) (((x)&(3<<10)) == (1<<10)) /* USB 1.1 device */ /* 11:10 for detecting lowspeed devices (reset vs release ownership) */ /* 9 reserved */ +#define PORT_LPM (1<<9) /* LPM transaction */ #define PORT_RESET (1<<8) /* reset port */ #define PORT_SUSPEND (1<<7) /* suspend port */ #define PORT_RESUME (1<<6) /* resume it */ -- cgit v1.2.3 From 48f24970144479c29b8cee6d2e1dbedf6dcf9cfb Mon Sep 17 00:00:00 2001 From: Alek Du Date: Fri, 4 Jun 2010 15:47:55 +0800 Subject: USB: EHCI: EHCI 1.1 addendum: Basic LPM feature support With this patch, the LPM capable EHCI host controller can put device into L1 sleep state which is a mode that can enter/exit quickly, and reduce power consumption. Signed-off-by: Jacob Pan Signed-off-by: Alek Du Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/hcd.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 11b638195901..9b867e64a0f4 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -300,6 +300,10 @@ struct hc_driver { int (*update_hub_device)(struct usb_hcd *, struct usb_device *hdev, struct usb_tt *tt, gfp_t mem_flags); int (*reset_device)(struct usb_hcd *, struct usb_device *); + /* Notifies the HCD after a device is connected and its + * address is set + */ + int (*update_device)(struct usb_hcd *, struct usb_device *); }; extern int usb_hcd_link_urb_to_ep(struct usb_hcd *hcd, struct urb *urb); -- cgit v1.2.3 From c532b29a6f6d31e84a7c88f995eebdc75ebd4248 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Tue, 1 Jun 2010 23:04:41 +0200 Subject: USB-BKL: Convert usb_driver ioctl to unlocked_ioctl And audit all the users. None needed the BKL. That was easy because there was only very few around. Tested with allmodconfig build on x86-64 Signed-off-by: Andi Kleen Cc: Arnd Bergmann From: Andi Kleen --- include/linux/usb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index d5922a877994..e6cbc34901f4 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -843,7 +843,7 @@ struct usb_driver { void (*disconnect) (struct usb_interface *intf); - int (*ioctl) (struct usb_interface *intf, unsigned int code, + int (*unlocked_ioctl) (struct usb_interface *intf, unsigned int code, void *buf); int (*suspend) (struct usb_interface *intf, pm_message_t message); -- cgit v1.2.3 From 7898aee1dacbb246fee958f0a6102320b61768d9 Mon Sep 17 00:00:00 2001 From: Michal Nazarewicz Date: Wed, 16 Jun 2010 12:07:58 +0200 Subject: USB: gadget: f_fs: functionfs_add() renamed to functionfs_bind_config() FunctionFS had a bit unique name for function used to add it to USB configuration. Renamed as to match naming convention of other functions. Signed-off-by: Michal Nazarewicz Signed-off-by: Kyungmin Park Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/functionfs.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/functionfs.h b/include/linux/usb/functionfs.h index a34a2a043b21..6f649c13193b 100644 --- a/include/linux/usb/functionfs.h +++ b/include/linux/usb/functionfs.h @@ -180,9 +180,9 @@ static int functionfs_bind(struct ffs_data *ffs, struct usb_composite_dev *cdev) static void functionfs_unbind(struct ffs_data *ffs) __attribute__((nonnull)); -static int functionfs_add(struct usb_composite_dev *cdev, - struct usb_configuration *c, - struct ffs_data *ffs) +static int functionfs_bind_config(struct usb_composite_dev *cdev, + struct usb_configuration *c, + struct ffs_data *ffs) __attribute__((warn_unused_result, nonnull)); -- cgit v1.2.3 From f2adc4f8aaf272de9ac71dcb18d95ebe05fc3f94 Mon Sep 17 00:00:00 2001 From: Michal Nazarewicz Date: Wed, 16 Jun 2010 12:07:59 +0200 Subject: USB: gadget: composite: usb_string_ids_*() functions added usb_string_ids_tab() and usb_string_ids_n() functions added to the composite framework. The first accepts an array of usb_string object and for each registeres a string id and the second registeres a given number of ids and returns the first. This may simplify string ids registration since gadgets and composite functions won't have to call usb_string_id() several times and each time check for errer status -- all this will be done with a single call. Signed-off-by: Michal Nazarewicz Signed-off-by: Kyungmin Park Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/composite.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index 139353efad34..f378075c839a 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -342,6 +342,10 @@ struct usb_composite_dev { }; extern int usb_string_id(struct usb_composite_dev *c); +extern int usb_string_ids_tab(struct usb_composite_dev *c, + struct usb_string *str); +extern int usb_string_ids_n(struct usb_composite_dev *c, unsigned n); + /* messaging utils */ #define DBG(d, fmt, args...) \ -- cgit v1.2.3 From 3f3e12d050052032a51f75e72e540322e2a7da2b Mon Sep 17 00:00:00 2001 From: Michal Nazarewicz Date: Mon, 21 Jun 2010 13:57:08 +0200 Subject: USB: gadget: composite: added disconnect callback Added a disconnect() callback to composite devices which is called by composite glue when its disconnect callback is called by gadget. Signed-off-by: Michal Nazarewicz Signed-off-by: Kyungmin Park Acked-by: David Brownell Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/composite.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index f378075c839a..890bc1472190 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -276,6 +276,8 @@ struct usb_composite_driver { int (*bind)(struct usb_composite_dev *); int (*unbind)(struct usb_composite_dev *); + void (*disconnect)(struct usb_composite_dev *); + /* global suspend hooks */ void (*suspend)(struct usb_composite_dev *); void (*resume)(struct usb_composite_dev *); -- cgit v1.2.3 From 541c7d432f76771079e7c295d596ea47cc6a3030 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Tue, 22 Jun 2010 16:39:10 -0400 Subject: USB: convert usb_hcd bitfields into atomic flags This patch (as1393) converts several of the single-bit fields in struct usb_hcd to atomic flags. This is for safety's sake; not all CPUs can update bitfield values atomically, and these flags are used in multiple contexts. The flag fields that are set only during registration or removal can remain as they are, since non-atomic accesses at those times will not cause any problems. (Strictly speaking, the authorized_default flag should become atomic as well. I didn't bother with it because it gets changed only via sysfs. It can be done later, if anyone wants.) Signed-off-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/hcd.h | 22 +++++++++++++++++----- 1 file changed, 17 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 9b867e64a0f4..f8f8fa7a56e8 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -89,19 +89,31 @@ struct usb_hcd { */ const struct hc_driver *driver; /* hw-specific hooks */ - /* Flags that need to be manipulated atomically */ + /* Flags that need to be manipulated atomically because they can + * change while the host controller is running. Always use + * set_bit() or clear_bit() to change their values. + */ unsigned long flags; -#define HCD_FLAG_HW_ACCESSIBLE 0x00000001 -#define HCD_FLAG_SAW_IRQ 0x00000002 +#define HCD_FLAG_HW_ACCESSIBLE 0 /* at full power */ +#define HCD_FLAG_SAW_IRQ 1 +#define HCD_FLAG_POLL_RH 2 /* poll for rh status? */ +#define HCD_FLAG_POLL_PENDING 3 /* status has changed? */ + + /* The flags can be tested using these macros; they are likely to + * be slightly faster than test_bit(). + */ +#define HCD_HW_ACCESSIBLE(hcd) ((hcd)->flags & (1U << HCD_FLAG_HW_ACCESSIBLE)) +#define HCD_SAW_IRQ(hcd) ((hcd)->flags & (1U << HCD_FLAG_SAW_IRQ)) +#define HCD_POLL_RH(hcd) ((hcd)->flags & (1U << HCD_FLAG_POLL_RH)) +#define HCD_POLL_PENDING(hcd) ((hcd)->flags & (1U << HCD_FLAG_POLL_PENDING)) + /* Flags that get set only during HCD registration or removal. */ unsigned rh_registered:1;/* is root hub registered? */ unsigned rh_pollable:1; /* may we poll the root hub? */ /* The next flag is a stopgap, to be removed when all the HCDs * support the new root-hub polling mechanism. */ unsigned uses_new_polling:1; - unsigned poll_rh:1; /* poll for rh status? */ - unsigned poll_pending:1; /* status has changed? */ unsigned wireless:1; /* Wireless USB HCD */ unsigned authorized_default:1; unsigned has_tt:1; /* Integrated TT in root hub */ -- cgit v1.2.3 From 4147200d25c423e627ab4487530b3d9f2ef829c8 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Fri, 25 Jun 2010 14:02:14 -0400 Subject: USB: add do_wakeup parameter for PCI HCD suspend This patch (as1385) adds a "do_wakeup" parameter to the pci_suspend method used by PCI-based host controller drivers. ehci-hcd in particular needs to know whether or not to enable wakeup when suspending a controller. Although that information is currently available through device_may_wakeup(), when support is added for runtime suspend this will no longer be true. Signed-off-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/hcd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index f8f8fa7a56e8..ae10020b4023 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -211,7 +211,7 @@ struct hc_driver { * a whole, not just the root hub; they're for PCI bus glue. */ /* called after suspending the hub, before entering D3 etc */ - int (*pci_suspend)(struct usb_hcd *hcd); + int (*pci_suspend)(struct usb_hcd *hcd, bool do_wakeup); /* called after entering D0 (etc), before resuming the hub */ int (*pci_resume)(struct usb_hcd *hcd, bool hibernated); -- cgit v1.2.3 From ff2f07874362d34684296f2bd5547a099f33c6d4 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Fri, 25 Jun 2010 14:02:35 -0400 Subject: USB: fix race between root-hub wakeup & controller suspend This patch (as1395) adds code to hcd_pci_suspend() for handling wakeup races. This is another general race pattern, similar to the "open vs. unregister" race we're all familiar with. Here, the race is between suspending a device and receiving a wakeup request from one of the device's suspended children. In particular, if a root-hub wakeup is requested at about the same time as the corresponding USB controller is suspended, and if the controller is enabled for wakeup, then the controller should either fail to suspend or else wake right back up again. During system sleep this won't happen very much, especially since host controllers generally aren't enabled for wakeup during sleep. However it is definitely an issue for runtime PM. Something like this will be needed to prevent the controller from autosuspending while waiting for a root-hub resume to take place. (That is, in fact, the common case, for which there is an extra test.) Signed-off-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/hcd.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index ae10020b4023..3b571f1ffbb3 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -98,6 +98,7 @@ struct usb_hcd { #define HCD_FLAG_SAW_IRQ 1 #define HCD_FLAG_POLL_RH 2 /* poll for rh status? */ #define HCD_FLAG_POLL_PENDING 3 /* status has changed? */ +#define HCD_FLAG_WAKEUP_PENDING 4 /* root hub is resuming? */ /* The flags can be tested using these macros; they are likely to * be slightly faster than test_bit(). @@ -106,6 +107,7 @@ struct usb_hcd { #define HCD_SAW_IRQ(hcd) ((hcd)->flags & (1U << HCD_FLAG_SAW_IRQ)) #define HCD_POLL_RH(hcd) ((hcd)->flags & (1U << HCD_FLAG_POLL_RH)) #define HCD_POLL_PENDING(hcd) ((hcd)->flags & (1U << HCD_FLAG_POLL_PENDING)) +#define HCD_WAKEUP_PENDING(hcd) ((hcd)->flags & (1U << HCD_FLAG_WAKEUP_PENDING)) /* Flags that get set only during HCD registration or removal. */ unsigned rh_registered:1;/* is root hub registered? */ -- cgit v1.2.3 From 5128993b6f5f38bc567f3c246248ca29fd599132 Mon Sep 17 00:00:00 2001 From: Ajay Kumar Gupta Date: Thu, 8 Jul 2010 14:03:01 +0530 Subject: USB: ulpi: fix compilation warning Fixes below compilation warning from ulpi.h include/linux/usb/ulpi.h:145: warning: 'struct otg_io_access_ops' declared inside parameter list include/linux/usb/ulpi.h:145: warning: its scope is only this definition or declaration, which is probably not what you want Signed-off-by: Ajay Kumar Gupta Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/ulpi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/ulpi.h b/include/linux/usb/ulpi.h index 2369d07c3c87..900d97b7096a 100644 --- a/include/linux/usb/ulpi.h +++ b/include/linux/usb/ulpi.h @@ -11,6 +11,7 @@ #ifndef __LINUX_USB_ULPI_H #define __LINUX_USB_ULPI_H +#include /*-------------------------------------------------------------------------*/ /* -- cgit v1.2.3 From 13dd0c9767349b280cf131c34461f85e5effc42a Mon Sep 17 00:00:00 2001 From: Igor Grinberg Date: Thu, 15 Jul 2010 16:00:16 +0300 Subject: USB: otg/ulpi: extend the generic ulpi driver. 1) Introduce ulpi specific flags for control of the ulpi phy 2) Extend the generic ulpi driver with support for Function and Interface control of upli phy 3) Update the platforms using the generic ulpi driver with new ulpi flags 4) Remove the otg control flags not in use Signed-off-by: Igor Grinberg Signed-off-by: Mike Rapoport Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/otg.h | 7 ------- include/linux/usb/ulpi.h | 39 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 39 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/otg.h b/include/linux/usb/otg.h index 54b2c5e48b9d..545cba73ccaf 100644 --- a/include/linux/usb/otg.h +++ b/include/linux/usb/otg.h @@ -43,13 +43,6 @@ enum usb_xceiv_events { USB_EVENT_ENUMERATED, /* gadget driver enumerated */ }; -#define USB_OTG_PULLUP_ID (1 << 0) -#define USB_OTG_PULLDOWN_DP (1 << 1) -#define USB_OTG_PULLDOWN_DM (1 << 2) -#define USB_OTG_EXT_VBUS_INDICATOR (1 << 3) -#define USB_OTG_DRV_VBUS (1 << 4) -#define USB_OTG_DRV_VBUS_EXT (1 << 5) - struct otg_transceiver; /* for transceivers connected thru an ULPI interface, the user must diff --git a/include/linux/usb/ulpi.h b/include/linux/usb/ulpi.h index 900d97b7096a..82b1507f4735 100644 --- a/include/linux/usb/ulpi.h +++ b/include/linux/usb/ulpi.h @@ -14,6 +14,41 @@ #include /*-------------------------------------------------------------------------*/ +/* + * ULPI Flags + */ +#define ULPI_OTG_ID_PULLUP (1 << 0) +#define ULPI_OTG_DP_PULLDOWN_DIS (1 << 1) +#define ULPI_OTG_DM_PULLDOWN_DIS (1 << 2) +#define ULPI_OTG_DISCHRGVBUS (1 << 3) +#define ULPI_OTG_CHRGVBUS (1 << 4) +#define ULPI_OTG_DRVVBUS (1 << 5) +#define ULPI_OTG_DRVVBUS_EXT (1 << 6) +#define ULPI_OTG_EXTVBUSIND (1 << 7) + +#define ULPI_IC_6PIN_SERIAL (1 << 8) +#define ULPI_IC_3PIN_SERIAL (1 << 9) +#define ULPI_IC_CARKIT (1 << 10) +#define ULPI_IC_CLKSUSPM (1 << 11) +#define ULPI_IC_AUTORESUME (1 << 12) +#define ULPI_IC_EXTVBUS_INDINV (1 << 13) +#define ULPI_IC_IND_PASSTHRU (1 << 14) +#define ULPI_IC_PROTECT_DIS (1 << 15) + +#define ULPI_FC_HS (1 << 16) +#define ULPI_FC_FS (1 << 17) +#define ULPI_FC_LS (1 << 18) +#define ULPI_FC_FS4LS (1 << 19) +#define ULPI_FC_TERMSEL (1 << 20) +#define ULPI_FC_OP_NORM (1 << 21) +#define ULPI_FC_OP_NODRV (1 << 22) +#define ULPI_FC_OP_DIS_NRZI (1 << 23) +#define ULPI_FC_OP_NSYNC_NEOP (1 << 24) +#define ULPI_FC_RST (1 << 25) +#define ULPI_FC_SUSPM (1 << 26) + +/*-------------------------------------------------------------------------*/ + /* * Macros for Set and Clear * See ULPI 1.1 specification to find the registers with Set and Clear offsets @@ -59,6 +94,10 @@ /*-------------------------------------------------------------------------*/ +/* + * Register Bits + */ + /* Function Control */ #define ULPI_FUNC_CTRL_XCVRSEL (1 << 0) #define ULPI_FUNC_CTRL_XCVRSEL_MASK (3 << 0) -- cgit v1.2.3 From 93362a875fc69881ae69299efaf19a55a1f57db0 Mon Sep 17 00:00:00 2001 From: Phil Dibowitz Date: Thu, 22 Jul 2010 00:05:01 +0200 Subject: USB delay init quirk for logitech Harmony 700-series devices The Logitech Harmony 700 series needs an extra delay during initialization. This patch adds a USB quirk which enables such a delay and adds the device to the quirks list. Signed-off-by: Phil Dibowitz Cc: stable Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/quirks.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h index 16b7f3347545..3e93de7ecbc3 100644 --- a/include/linux/usb/quirks.h +++ b/include/linux/usb/quirks.h @@ -26,4 +26,8 @@ and can't handle talking to these interfaces */ #define USB_QUIRK_HONOR_BNUMINTERFACES 0x00000020 +/* device needs a pause during initialization, after we read the device + descriptor */ +#define USB_QUIRK_DELAY_INIT 0x00000040 + #endif /* __LINUX_USB_QUIRKS_H */ -- cgit v1.2.3 From c6ba1c2af2da31ffb57949edbd1dba34f97d1d4b Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 29 Jul 2010 15:54:38 -0700 Subject: USB:: fix linux/usb.h kernel-doc warnings Fix kernel-doc warnings in linux/usb.h: Warning(include/linux/usb.h:185): No description found for parameter 'resetting_device' Warning(include/linux/usb.h:1212): No description found for parameter 'stream_id' Signed-off-by: Randy Dunlap Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index e6cbc34901f4..35fe6ab222bb 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -127,6 +127,8 @@ enum usb_interface_condition { * queued reset so that usb_cancel_queued_reset() doesn't try to * remove from the workqueue when running inside the worker * thread. See __usb_queue_reset_device(). + * @resetting_device: USB core reset the device, so use alt setting 0 as + * current; needs bandwidth alloc after reset. * * USB device drivers attach to interfaces on a physical device. Each * interface encapsulates a single high level function, such as feeding @@ -1015,6 +1017,7 @@ typedef void (*usb_complete_t)(struct urb *); * is a different endpoint (and pipe) from "out" endpoint two. * The current configuration controls the existence, type, and * maximum packet size of any given endpoint. + * @stream_id: the endpoint's stream ID for bulk streams * @dev: Identifies the USB device to perform the request. * @status: This is read in non-iso completion functions to get the * status of the particular request. ISO requests only use it -- cgit v1.2.3 From 72d2e9f9f90ccafdce1f0a4a9eaabfb031f86def Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 9 Aug 2010 16:37:16 -0700 Subject: i2c.h: fix kernel-doc warnings Fix kernel-doc warnings in linux/i2c.h: Warning(include/linux/i2c.h:176): No description found for parameter 'alert' Warning(include/linux/i2c.h:259): No description found for parameter 'of_node' Signed-off-by: Randy Dunlap Signed-off-by: Linus Torvalds --- include/linux/i2c.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 21067b418536..38dd4025aa4e 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -108,6 +108,7 @@ extern s32 i2c_smbus_write_i2c_block_data(struct i2c_client *client, * @shutdown: Callback for device shutdown * @suspend: Callback for device suspend * @resume: Callback for device resume + * @alert: Alert callback, for example for the SMBus alert protocol * @command: Callback for bus-wide signaling (optional) * @driver: Device driver model driver * @id_table: List of I2C devices supported by this driver @@ -233,6 +234,7 @@ static inline void i2c_set_clientdata(struct i2c_client *dev, void *data) * @addr: stored in i2c_client.addr * @platform_data: stored in i2c_client.dev.platform_data * @archdata: copied into i2c_client.dev.archdata + * @of_node: pointer to OpenFirmware device node * @irq: stored in i2c_client.irq * * I2C doesn't actually support hardware probing, although controllers and -- cgit v1.2.3 From 496ee9b8f349a8ae2065114c414a47e89bdeb930 Mon Sep 17 00:00:00 2001 From: Lubomir Rintel Date: Thu, 22 Jul 2010 03:11:48 +0200 Subject: V7: Adjust sanity checks for some volumes Newly mkfs-ed filesystems from Seventh Edition have last modification time set to zero, but are otherwise perfectly valid. Also, tighten up other sanity checks to filter out most filesystems with different bytesex than we're using. Cc: Christoph Hellwig Signed-off-by: Lubomir Rintel Signed-off-by: Al Viro --- include/linux/sysv_fs.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sysv_fs.h b/include/linux/sysv_fs.h index 96411306eec6..e47d6d90023d 100644 --- a/include/linux/sysv_fs.h +++ b/include/linux/sysv_fs.h @@ -148,6 +148,17 @@ struct v7_super_block { char s_fname[6]; /* file system name */ char s_fpack[6]; /* file system pack name */ }; +/* Constants to aid sanity checking */ +/* This is not a hard limit, nor enforced by v7 kernel. It's actually just + * the limit used by Seventh Edition's ls, though is high enough to assume + * that no reasonable file system would have that much entries in root + * directory. Thus, if we see anything higher, we just probably got the + * endiannes wrong. */ +#define V7_NFILES 1024 +/* The disk addresses are three-byte (despite direct block addresses being + * aligned word-wise in inode). If the most significant byte is non-zero, + * something is most likely wrong (not a filesystem, bad bytesex). */ +#define V7_MAXSIZE 0x00ffffff /* Coherent super-block data on disk */ #define COH_NICINOD 100 /* number of inode cache entries */ -- cgit v1.2.3 From f7ad3c6be90809b53b7f0ae9d4eaa45ce2564a79 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Tue, 10 Aug 2010 11:41:36 +0200 Subject: vfs: add helpers to get root and pwd Add three helpers that retrieve a refcounted copy of the root and cwd from the supplied fs_struct. get_fs_root() get_fs_pwd() get_fs_root_and_pwd() Signed-off-by: Miklos Szeredi Signed-off-by: Al Viro --- include/linux/fs_struct.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h index 78a05bfcd8eb..eca3d5202138 100644 --- a/include/linux/fs_struct.h +++ b/include/linux/fs_struct.h @@ -21,4 +21,31 @@ extern void free_fs_struct(struct fs_struct *); extern void daemonize_fs_struct(void); extern int unshare_fs_struct(void); +static inline void get_fs_root(struct fs_struct *fs, struct path *root) +{ + read_lock(&fs->lock); + *root = fs->root; + path_get(root); + read_unlock(&fs->lock); +} + +static inline void get_fs_pwd(struct fs_struct *fs, struct path *pwd) +{ + read_lock(&fs->lock); + *pwd = fs->pwd; + path_get(pwd); + read_unlock(&fs->lock); +} + +static inline void get_fs_root_and_pwd(struct fs_struct *fs, struct path *root, + struct path *pwd) +{ + read_lock(&fs->lock); + *root = fs->root; + path_get(root); + *pwd = fs->pwd; + path_get(pwd); + read_unlock(&fs->lock); +} + #endif /* _LINUX_FS_STRUCT_H */ -- cgit v1.2.3 From 8df9d1a4142311c084ffeeacb67cd34d190eff74 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Tue, 10 Aug 2010 11:41:41 +0200 Subject: vfs: show unreachable paths in getcwd and proc Prepend "(unreachable)" to path strings if the path is not reachable from the current root. Two places updated are - the return string from getcwd() - and symlinks under /proc/$PID. Other uses of d_path() are left unchanged (we know that some old software crashes if /proc/mounts is changed). Signed-off-by: Miklos Szeredi Signed-off-by: Al Viro --- include/linux/dcache.h | 1 + include/linux/path.h | 5 +++++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index d23be0386e2d..6a4aea30aa09 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -315,6 +315,7 @@ extern char *dynamic_dname(struct dentry *, char *, int, const char *, ...); extern char *__d_path(const struct path *path, struct path *root, char *, int); extern char *d_path(const struct path *, char *, int); +extern char *d_path_with_unreachable(const struct path *, char *, int); extern char *__dentry_path(struct dentry *, char *, int); extern char *dentry_path(struct dentry *, char *, int); diff --git a/include/linux/path.h b/include/linux/path.h index 915e0c382a51..edc98dec6266 100644 --- a/include/linux/path.h +++ b/include/linux/path.h @@ -12,4 +12,9 @@ struct path { extern void path_get(struct path *); extern void path_put(struct path *); +static inline int path_equal(const struct path *path1, const struct path *path2) +{ + return path1->mnt == path2->mnt && path1->dentry == path2->dentry; +} + #endif /* _LINUX_PATH_H */ -- cgit v1.2.3 From 532490f0a5350fd92d838b7430a4c846bc8eac3f Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Mon, 2 Aug 2010 13:46:56 +0200 Subject: vfs: remove unused MNT_STRICTATIME Commit d0adde574b8487ef30f69e2d08bba769e4be513f added MNT_STRICTATIME but it isn't actually used (MS_STRICTATIME clears MNT_RELATIME and MNT_NOATIME rather than setting any mount flag). Signed-off-by: Miklos Szeredi Signed-off-by: Al Viro --- include/linux/mount.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mount.h b/include/linux/mount.h index 907210bd9f9c..5e7a59408dd4 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -27,7 +27,6 @@ struct mnt_namespace; #define MNT_NODIRATIME 0x10 #define MNT_RELATIME 0x20 #define MNT_READONLY 0x40 /* does the user want this to be r/o? */ -#define MNT_STRICTATIME 0x80 #define MNT_SHRINKABLE 0x100 #define MNT_WRITE_HOLD 0x200 -- cgit v1.2.3 From 8edf344c66a3f214d709dad1421c29d678915b3f Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Fri, 28 May 2010 09:29:15 +0900 Subject: hugetlb: move definition of is_vm_hugetlb_page() to hugepage_inline.h is_vm_hugetlb_page() is a widely used inline function to insert hooks into hugetlb code. But we can't use it in pagemap.h because of circular dependency of the header files. This patch removes this limitation. Acked-by: Mel Gorman Acked-by: Fengguang Wu Signed-off-by: Naoya Horiguchi Signed-off-by: Andi Kleen --- include/linux/hugetlb.h | 11 +---------- include/linux/hugetlb_inline.h | 22 ++++++++++++++++++++++ include/linux/pagemap.h | 1 + 3 files changed, 24 insertions(+), 10 deletions(-) create mode 100644 include/linux/hugetlb_inline.h (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 78b4bc64c006..d47a7c41745d 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -2,6 +2,7 @@ #define _LINUX_HUGETLB_H #include +#include struct ctl_table; struct user_struct; @@ -14,11 +15,6 @@ struct user_struct; int PageHuge(struct page *page); -static inline int is_vm_hugetlb_page(struct vm_area_struct *vma) -{ - return vma->vm_flags & VM_HUGETLB; -} - void reset_vma_resv_huge_pages(struct vm_area_struct *vma); int hugetlb_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); int hugetlb_overcommit_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); @@ -77,11 +73,6 @@ static inline int PageHuge(struct page *page) return 0; } -static inline int is_vm_hugetlb_page(struct vm_area_struct *vma) -{ - return 0; -} - static inline void reset_vma_resv_huge_pages(struct vm_area_struct *vma) { } diff --git a/include/linux/hugetlb_inline.h b/include/linux/hugetlb_inline.h new file mode 100644 index 000000000000..cf00b6df53dc --- /dev/null +++ b/include/linux/hugetlb_inline.h @@ -0,0 +1,22 @@ +#ifndef _LINUX_HUGETLB_INLINE_H +#define _LINUX_HUGETLB_INLINE_H 1 + +#ifdef CONFIG_HUGETLBFS + +#include + +static inline int is_vm_hugetlb_page(struct vm_area_struct *vma) +{ + return vma->vm_flags & VM_HUGETLB; +} + +#else + +static inline int is_vm_hugetlb_page(struct vm_area_struct *vma) +{ + return 0; +} + +#endif + +#endif diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 3c62ed408492..b2bd2bae9775 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -13,6 +13,7 @@ #include #include #include /* for in_interrupt() */ +#include /* * Bits in mapping->flags. The lower __GFP_BITS_SHIFT bits are the page -- cgit v1.2.3 From 0fe6e20b9c4c53b3e97096ee73a0857f60aad43f Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Fri, 28 May 2010 09:29:16 +0900 Subject: hugetlb, rmap: add reverse mapping for hugepage This patch adds reverse mapping feature for hugepage by introducing mapcount for shared/private-mapped hugepage and anon_vma for private-mapped hugepage. While hugepage is not currently swappable, reverse mapping can be useful for memory error handler. Without this patch, memory error handler cannot identify processes using the bad hugepage nor unmap it from them. That is: - for shared hugepage: we can collect processes using a hugepage through pagecache, but can not unmap the hugepage because of the lack of mapcount. - for privately mapped hugepage: we can neither collect processes nor unmap the hugepage. This patch solves these problems. This patch include the bug fix given by commit 23be7468e8, so reverts it. Dependency: "hugetlb: move definition of is_vm_hugetlb_page() to hugepage_inline.h" ChangeLog since May 24. - create hugetlb_inline.h and move is_vm_hugetlb_index() in it. - move functions setting up anon_vma for hugepage into mm/rmap.c. ChangeLog since May 13. - rebased to 2.6.34 - fix logic error (in case that private mapping and shared mapping coexist) - move is_vm_hugetlb_page() into include/linux/mm.h to use this function from linear_page_index() - define and use linear_hugepage_index() instead of compound_order() - use page_move_anon_rmap() in hugetlb_cow() - copy exclusive switch of __set_page_anon_rmap() into hugepage counterpart. - revert commit 24be7468 completely Signed-off-by: Naoya Horiguchi Cc: Andi Kleen Cc: Andrew Morton Cc: Mel Gorman Cc: Andrea Arcangeli Cc: Larry Woodman Cc: Lee Schermerhorn Acked-by: Fengguang Wu Acked-by: Mel Gorman Signed-off-by: Andi Kleen --- include/linux/hugetlb.h | 1 + include/linux/pagemap.h | 8 +++++++- include/linux/poison.h | 9 --------- include/linux/rmap.h | 5 +++++ 4 files changed, 13 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index d47a7c41745d..e688fd89354d 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -99,6 +99,7 @@ static inline void hugetlb_report_meminfo(struct seq_file *m) #define is_hugepage_only_range(mm, addr, len) 0 #define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) ({BUG(); 0; }) #define hugetlb_fault(mm, vma, addr, flags) ({ BUG(); 0; }) +#define huge_pte_offset(mm, address) 0 #define hugetlb_change_protection(vma, address, end, newprot) diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index b2bd2bae9775..a547d9689170 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -282,10 +282,16 @@ static inline loff_t page_offset(struct page *page) return ((loff_t)page->index) << PAGE_CACHE_SHIFT; } +extern pgoff_t linear_hugepage_index(struct vm_area_struct *vma, + unsigned long address); + static inline pgoff_t linear_page_index(struct vm_area_struct *vma, unsigned long address) { - pgoff_t pgoff = (address - vma->vm_start) >> PAGE_SHIFT; + pgoff_t pgoff; + if (unlikely(is_vm_hugetlb_page(vma))) + return linear_hugepage_index(vma, address); + pgoff = (address - vma->vm_start) >> PAGE_SHIFT; pgoff += vma->vm_pgoff; return pgoff >> (PAGE_CACHE_SHIFT - PAGE_SHIFT); } diff --git a/include/linux/poison.h b/include/linux/poison.h index 34066ffd893d..2110a81c5e2a 100644 --- a/include/linux/poison.h +++ b/include/linux/poison.h @@ -48,15 +48,6 @@ #define POISON_FREE 0x6b /* for use-after-free poisoning */ #define POISON_END 0xa5 /* end-byte of poisoning */ -/********** mm/hugetlb.c **********/ -/* - * Private mappings of hugetlb pages use this poisoned value for - * page->mapping. The core VM should not be doing anything with this mapping - * but futex requires the existence of some page->mapping value even though it - * is unused if PAGE_MAPPING_ANON is set. - */ -#define HUGETLB_POISON ((void *)(0x00300300 + POISON_POINTER_DELTA + PAGE_MAPPING_ANON)) - /********** arch/$ARCH/mm/init.c **********/ #define POISON_FREE_INITMEM 0xcc diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 77216742c178..9d50e7ef5f5a 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -140,6 +140,11 @@ void page_add_new_anon_rmap(struct page *, struct vm_area_struct *, unsigned lon void page_add_file_rmap(struct page *); void page_remove_rmap(struct page *); +void hugepage_add_anon_rmap(struct page *, struct vm_area_struct *, + unsigned long); +void hugepage_add_new_anon_rmap(struct page *, struct vm_area_struct *, + unsigned long); + static inline void page_dup_rmap(struct page *page) { atomic_inc(&page->_mapcount); -- cgit v1.2.3 From 93f70f900da36fbc19c13c2aa04b2e468c8d00fb Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Fri, 28 May 2010 09:29:20 +0900 Subject: HWPOISON, hugetlb: isolate corrupted hugepage If error hugepage is not in-use, we can fully recovery from error by dequeuing it from freelist, so return RECOVERY. Otherwise whether or not we can recovery depends on user processes, so return DELAYED. Dependency: "HWPOISON, hugetlb: enable error handling path for hugepage" Signed-off-by: Naoya Horiguchi Cc: Andrew Morton Acked-by: Fengguang Wu Signed-off-by: Andi Kleen --- include/linux/hugetlb.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index e688fd89354d..f479700df61b 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -43,6 +43,7 @@ int hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, int acctflags); void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed); +void __isolate_hwpoisoned_huge_page(struct page *page); extern unsigned long hugepages_treat_as_movable; extern const unsigned long hugetlb_zero, hugetlb_infinity; @@ -100,6 +101,7 @@ static inline void hugetlb_report_meminfo(struct seq_file *m) #define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) ({BUG(); 0; }) #define hugetlb_fault(mm, vma, addr, flags) ({ BUG(); 0; }) #define huge_pte_offset(mm, address) 0 +#define __isolate_hwpoisoned_huge_page(page) 0 #define hugetlb_change_protection(vma, address, end, newprot) -- cgit v1.2.3 From e3390f67a7267daa227380b6f1bbf13c7ddd4aff Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Tue, 15 Jun 2010 13:18:13 +0900 Subject: hwpoison: rename CONFIG CONFIG_HUGETLBFS controls hugetlbfs interface code. OTOH, CONFIG_HUGETLB_PAGE controls hugepage management code. So we should use CONFIG_HUGETLB_PAGE here. Signed-off-by: Naoya Horiguchi Signed-off-by: Andi Kleen --- include/linux/hugetlb_inline.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb_inline.h b/include/linux/hugetlb_inline.h index cf00b6df53dc..6931489a5c14 100644 --- a/include/linux/hugetlb_inline.h +++ b/include/linux/hugetlb_inline.h @@ -1,7 +1,7 @@ #ifndef _LINUX_HUGETLB_INLINE_H -#define _LINUX_HUGETLB_INLINE_H 1 +#define _LINUX_HUGETLB_INLINE_H -#ifdef CONFIG_HUGETLBFS +#ifdef CONFIG_HUGETLB_PAGE #include -- cgit v1.2.3 From 156f252857dfd81f03d77d09e33b5f7d2b113e2b Mon Sep 17 00:00:00 2001 From: Kyungmin Park Date: Wed, 16 Jun 2010 09:04:16 +0200 Subject: drivers: regulator: add Maxim 8998 driver Acked-by: Mark Brown This patch adds voltage regulator driver for Maxim 8998 chip. This chip is used on Samsung Aquila and GONI boards and provides following functionalities: - 4 BUCK voltage converters, 17 LDO power regulators and 5 other power controllers - battery charger This patch adds basic driver for voltage regulators and MAX 8998 MFD core. Signed-off-by: Kyungmin Park Signed-off-by: Marek Szyprowski Acked-by: Samuel Ortiz Acked-by: Mark Brown Signed-off-by: Liam Girdwood --- include/linux/mfd/max8998-private.h | 112 ++++++++++++++++++++++++++++++++++++ include/linux/mfd/max8998.h | 78 +++++++++++++++++++++++++ 2 files changed, 190 insertions(+) create mode 100644 include/linux/mfd/max8998-private.h create mode 100644 include/linux/mfd/max8998.h (limited to 'include/linux') diff --git a/include/linux/mfd/max8998-private.h b/include/linux/mfd/max8998-private.h new file mode 100644 index 000000000000..6dc75b3e2d33 --- /dev/null +++ b/include/linux/mfd/max8998-private.h @@ -0,0 +1,112 @@ +/* + * max8698.h - Voltage regulator driver for the Maxim 8998 + * + * Copyright (C) 2009-2010 Samsung Electrnoics + * Kyungmin Park + * Marek Szyprowski + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#ifndef __LINUX_MFD_MAX8998_PRIV_H +#define __LINUX_MFD_MAX8998_PRIV_H + +/* MAX 8998 registers */ +enum { + MAX8998_REG_IRQ1, + MAX8998_REG_IRQ2, + MAX8998_REG_IRQ3, + MAX8998_REG_IRQ4, + MAX8998_REG_IRQM1, + MAX8998_REG_IRQM2, + MAX8998_REG_IRQM3, + MAX8998_REG_IRQM4, + MAX8998_REG_STATUS1, + MAX8998_REG_STATUS2, + MAX8998_REG_STATUSM1, + MAX8998_REG_STATUSM2, + MAX8998_REG_CHGR1, + MAX8998_REG_CHGR2, + MAX8998_REG_LDO_ACTIVE_DISCHARGE1, + MAX8998_REG_LDO_ACTIVE_DISCHARGE2, + MAX8998_REG_BUCK_ACTIVE_DISCHARGE3, + MAX8998_REG_ONOFF1, + MAX8998_REG_ONOFF2, + MAX8998_REG_ONOFF3, + MAX8998_REG_ONOFF4, + MAX8998_REG_BUCK1_DVSARM1, + MAX8998_REG_BUCK1_DVSARM2, + MAX8998_REG_BUCK1_DVSARM3, + MAX8998_REG_BUCK1_DVSARM4, + MAX8998_REG_BUCK2_DVSINT1, + MAX8998_REG_BUCK2_DVSINT2, + MAX8998_REG_BUCK3, + MAX8998_REG_BUCK4, + MAX8998_REG_LDO2_LDO3, + MAX8998_REG_LDO4, + MAX8998_REG_LDO5, + MAX8998_REG_LDO6, + MAX8998_REG_LDO7, + MAX8998_REG_LDO8_LDO9, + MAX8998_REG_LDO10_LDO11, + MAX8998_REG_LDO12, + MAX8998_REG_LDO13, + MAX8998_REG_LDO14, + MAX8998_REG_LDO15, + MAX8998_REG_LDO16, + MAX8998_REG_LDO17, + MAX8998_REG_BKCHR, + MAX8998_REG_LBCNFG1, + MAX8998_REG_LBCNFG2, +}; + +/** + * struct max8998_dev - max8998 master device for sub-drivers + * @dev: master device of the chip (can be used to access platform data) + * @i2c_client: i2c client private data + * @dev_read(): chip register read function + * @dev_write(): chip register write function + * @dev_update(): chip register update function + * @iolock: mutex for serializing io access + */ + +struct max8998_dev { + struct device *dev; + struct i2c_client *i2c_client; + int (*dev_read)(struct max8998_dev *max8998, u8 reg, u8 *dest); + int (*dev_write)(struct max8998_dev *max8998, u8 reg, u8 val); + int (*dev_update)(struct max8998_dev *max8998, u8 reg, u8 val, u8 mask); + struct mutex iolock; +}; + +static inline int max8998_read_reg(struct max8998_dev *max8998, u8 reg, + u8 *value) +{ + return max8998->dev_read(max8998, reg, value); +} + +static inline int max8998_write_reg(struct max8998_dev *max8998, u8 reg, + u8 value) +{ + return max8998->dev_write(max8998, reg, value); +} + +static inline int max8998_update_reg(struct max8998_dev *max8998, u8 reg, + u8 value, u8 mask) +{ + return max8998->dev_update(max8998, reg, value, mask); +} + +#endif /* __LINUX_MFD_MAX8998_PRIV_H */ diff --git a/include/linux/mfd/max8998.h b/include/linux/mfd/max8998.h new file mode 100644 index 000000000000..1d3601a2d853 --- /dev/null +++ b/include/linux/mfd/max8998.h @@ -0,0 +1,78 @@ +/* + * max8698.h - Voltage regulator driver for the Maxim 8998 + * + * Copyright (C) 2009-2010 Samsung Electrnoics + * Kyungmin Park + * Marek Szyprowski + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#ifndef __LINUX_MFD_MAX8998_H +#define __LINUX_MFD_MAX8998_H + +#include + +/* MAX 8998 regulator ids */ +enum { + MAX8998_LDO2 = 2, + MAX8998_LDO3, + MAX8998_LDO4, + MAX8998_LDO5, + MAX8998_LDO6, + MAX8998_LDO7, + MAX8998_LDO8, + MAX8998_LDO9, + MAX8998_LDO10, + MAX8998_LDO11, + MAX8998_LDO12, + MAX8998_LDO13, + MAX8998_LDO14, + MAX8998_LDO15, + MAX8998_LDO16, + MAX8998_LDO17, + MAX8998_BUCK1, + MAX8998_BUCK2, + MAX8998_BUCK3, + MAX8998_BUCK4, + MAX8998_EN32KHZ_AP, + MAX8998_EN32KHZ_CP, + MAX8998_ENVICHG, + MAX8998_ESAFEOUT1, + MAX8998_ESAFEOUT2, +}; + +/** + * max8998_regulator_data - regulator data + * @id: regulator id + * @initdata: regulator init data (contraints, supplies, ...) + */ +struct max8998_regulator_data { + int id; + struct regulator_init_data *initdata; +}; + +/** + * struct max8998_board - packages regulator init data + * @num_regulators: number of regultors used + * @regulators: array of defined regulators + */ + +struct max8998_platform_data { + int num_regulators; + struct max8998_regulator_data *regulators; +}; + +#endif /* __LINUX_MFD_MAX8998_H */ -- cgit v1.2.3 From 549931f99e030d63a437c23943fd8dc9b7c0e41c Mon Sep 17 00:00:00 2001 From: Sundar R Iyer Date: Tue, 13 Jul 2010 11:51:28 +0530 Subject: ab8500-mfd: add regulator support to ab8500 mfd device Acked-by: Linus Walleij Acked-By: Mattias Wallin Acked-By: Bengt JONSSON Signed-off-by: Sundar R Iyer Acked-by: Mark Brown Acked-by: Samuel Ortiz Signed-off-by: Liam Girdwood --- include/linux/mfd/ab8500.h | 6 ++++++ include/linux/regulator/ab8500.h | 25 +++++++++++++++++++++++++ 2 files changed, 31 insertions(+) create mode 100644 include/linux/regulator/ab8500.h (limited to 'include/linux') diff --git a/include/linux/mfd/ab8500.h b/include/linux/mfd/ab8500.h index b63ff3ba3351..f5cec4500f38 100644 --- a/include/linux/mfd/ab8500.h +++ b/include/linux/mfd/ab8500.h @@ -76,6 +76,8 @@ #define AB8500_NR_IRQS 104 #define AB8500_NUM_IRQ_REGS 13 +#define AB8500_NUM_REGULATORS 15 + /** * struct ab8500 - ab8500 internal structure * @dev: parent device @@ -108,14 +110,18 @@ struct ab8500 { u8 oldmask[AB8500_NUM_IRQ_REGS]; }; +struct regulator_init_data; + /** * struct ab8500_platform_data - AB8500 platform data * @irq_base: start of AB8500 IRQs, AB8500_NR_IRQS will be used * @init: board-specific initialization after detection of ab8500 + * @regulator: machine-specific constraints for regulators */ struct ab8500_platform_data { int irq_base; void (*init) (struct ab8500 *); + struct regulator_init_data *regulator[AB8500_NUM_REGULATORS]; }; extern int ab8500_write(struct ab8500 *a8500, u16 addr, u8 data); diff --git a/include/linux/regulator/ab8500.h b/include/linux/regulator/ab8500.h new file mode 100644 index 000000000000..f509877c2ed4 --- /dev/null +++ b/include/linux/regulator/ab8500.h @@ -0,0 +1,25 @@ +/* + * Copyright (C) ST-Ericsson SA 2010 + * + * License Terms: GNU General Public License v2 + * + * Author: Sundar Iyer for ST-Ericsson + * + */ + +#ifndef __LINUX_MFD_AB8500_REGULATOR_H +#define __LINUX_MFD_AB8500_REGULATOR_H + +/* AB8500 regulators */ +#define AB8500_LDO_AUX1 0 +#define AB8500_LDO_AUX2 1 +#define AB8500_LDO_AUX3 2 +#define AB8500_LDO_INTCORE 3 +#define AB8500_LDO_TVOUT 4 +#define AB8500_LDO_AUDIO 5 +#define AB8500_LDO_ANAMIC1 6 +#define AB8500_LDO_ANAMIC2 7 +#define AB8500_LDO_DMIC 8 +#define AB8500_LDO_ANA 9 + +#endif -- cgit v1.2.3 From 9bbb9e5a33109b2832e2e63dcc7a132924ab374b Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Wed, 11 Aug 2010 23:04:12 -0600 Subject: param: use ops in struct kernel_param, rather than get and set fns directly This is more kernel-ish, saves some space, and also allows us to expand the ops without breaking all the callers who are happy for the new members to be NULL. The few places which defined their own param types are changed to the new scheme (more which crept in recently fixed in following patches). Since we're touching them anyway, we change get() and set() to take a const struct kernel_param (which they really are). This causes some harmless warnings until we fix them (in following patches). To reduce churn, module_param_call creates the ops struct so the callers don't have to change (and casts the functions to reduce warnings). The modern version which takes an ops struct is called module_param_cb. Signed-off-by: Rusty Russell Reviewed-by: Takashi Iwai Tested-by: Phil Carmody Cc: "David S. Miller" Cc: Ville Syrjala Cc: Dmitry Torokhov Cc: Alessandro Rubini Cc: Michal Januszewski Cc: Trond Myklebust Cc: "J. Bruce Fields" Cc: Neil Brown Cc: linux-kernel@vger.kernel.org Cc: linux-input@vger.kernel.org Cc: linux-fbdev-devel@lists.sourceforge.net Cc: linux-nfs@vger.kernel.org Cc: netdev@vger.kernel.org --- include/linux/moduleparam.h | 123 +++++++++++++++++++++++++++----------------- 1 file changed, 75 insertions(+), 48 deletions(-) (limited to 'include/linux') diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h index 82a9124f7d75..02e5090ce32f 100644 --- a/include/linux/moduleparam.h +++ b/include/linux/moduleparam.h @@ -31,20 +31,21 @@ static const char __module_cat(name,__LINE__)[] \ struct kernel_param; -/* Returns 0, or -errno. arg is in kp->arg. */ -typedef int (*param_set_fn)(const char *val, struct kernel_param *kp); -/* Returns length written or -errno. Buffer is 4k (ie. be short!) */ -typedef int (*param_get_fn)(char *buffer, struct kernel_param *kp); +struct kernel_param_ops { + /* Returns 0, or -errno. arg is in kp->arg. */ + int (*set)(const char *val, const struct kernel_param *kp); + /* Returns length written or -errno. Buffer is 4k (ie. be short!) */ + int (*get)(char *buffer, const struct kernel_param *kp); +}; /* Flag bits for kernel_param.flags */ #define KPARAM_ISBOOL 2 struct kernel_param { const char *name; + const struct kernel_param_ops *ops; u16 perm; u16 flags; - param_set_fn set; - param_get_fn get; union { void *arg; const struct kparam_string *str; @@ -63,8 +64,7 @@ struct kparam_array { unsigned int max; unsigned int *num; - param_set_fn set; - param_get_fn get; + const struct kernel_param_ops *ops; unsigned int elemsize; void *elem; }; @@ -83,7 +83,7 @@ struct kparam_array parameters. perm sets the visibility in sysfs: 000 means it's not there, read bits mean it's readable, write bits mean it's writable. */ -#define __module_param_call(prefix, name, set, get, arg, isbool, perm) \ +#define __module_param_call(prefix, name, ops, arg, isbool, perm) \ /* Default value instead of permissions? */ \ static int __param_perm_check_##name __attribute__((unused)) = \ BUILD_BUG_ON_ZERO((perm) < 0 || (perm) > 0777 || ((perm) & 2)) \ @@ -92,20 +92,37 @@ struct kparam_array static struct kernel_param __moduleparam_const __param_##name \ __used \ __attribute__ ((unused,__section__ ("__param"),aligned(sizeof(void *)))) \ - = { __param_str_##name, perm, isbool ? KPARAM_ISBOOL : 0, \ - set, get, { arg } } + = { __param_str_##name, ops, perm, isbool ? KPARAM_ISBOOL : 0, \ + { arg } } + +/* Obsolete - use module_param_cb() */ +#define module_param_call(name, set, get, arg, perm) \ + static struct kernel_param_ops __param_ops_##name = \ + { (void *)set, (void *)get }; \ + __module_param_call(MODULE_PARAM_PREFIX, \ + name, &__param_ops_##name, arg, \ + __same_type(*(arg), bool), \ + (perm) + sizeof(__check_old_set_param(set))*0) + +/* We don't get oldget: it's often a new-style param_get_uint, etc. */ +static inline int +__check_old_set_param(int (*oldset)(const char *, struct kernel_param *)) +{ + return 0; +} -#define module_param_call(name, set, get, arg, perm) \ +#define module_param_cb(name, ops, arg, perm) \ __module_param_call(MODULE_PARAM_PREFIX, \ - name, set, get, arg, \ - __same_type(*(arg), bool), perm) + name, ops, arg, __same_type(*(arg), bool), perm) -/* Helper functions: type is byte, short, ushort, int, uint, long, - ulong, charp, bool or invbool, or XXX if you define param_get_XXX, - param_set_XXX and param_check_XXX. */ +/* + * Helper functions: type is byte, short, ushort, int, uint, long, + * ulong, charp, bool or invbool, or XXX if you define param_ops_XXX + * and param_check_XXX. + */ #define module_param_named(name, value, type, perm) \ param_check_##type(name, &(value)); \ - module_param_call(name, param_set_##type, param_get_##type, &value, perm); \ + module_param_cb(name, ¶m_ops_##type, &value, perm); \ __MODULE_PARM_TYPE(name, #type) #define module_param(name, type, perm) \ @@ -126,7 +143,7 @@ struct kparam_array */ #define core_param(name, var, type, perm) \ param_check_##type(name, &(var)); \ - __module_param_call("", name, param_set_##type, param_get_##type, \ + __module_param_call("", name, ¶m_ops_##type, \ &var, __same_type(var, bool), perm) #endif /* !MODULE */ @@ -135,7 +152,7 @@ struct kparam_array static const struct kparam_string __param_string_##name \ = { len, string }; \ __module_param_call(MODULE_PARAM_PREFIX, name, \ - param_set_copystring, param_get_string, \ + ¶m_ops_string, \ .str = &__param_string_##name, 0, perm); \ __MODULE_PARM_TYPE(name, "string") @@ -162,41 +179,50 @@ static inline void destroy_params(const struct kernel_param *params, #define __param_check(name, p, type) \ static inline type *__check_##name(void) { return(p); } -extern int param_set_byte(const char *val, struct kernel_param *kp); -extern int param_get_byte(char *buffer, struct kernel_param *kp); +extern struct kernel_param_ops param_ops_byte; +extern int param_set_byte(const char *val, const struct kernel_param *kp); +extern int param_get_byte(char *buffer, const struct kernel_param *kp); #define param_check_byte(name, p) __param_check(name, p, unsigned char) -extern int param_set_short(const char *val, struct kernel_param *kp); -extern int param_get_short(char *buffer, struct kernel_param *kp); +extern struct kernel_param_ops param_ops_short; +extern int param_set_short(const char *val, const struct kernel_param *kp); +extern int param_get_short(char *buffer, const struct kernel_param *kp); #define param_check_short(name, p) __param_check(name, p, short) -extern int param_set_ushort(const char *val, struct kernel_param *kp); -extern int param_get_ushort(char *buffer, struct kernel_param *kp); +extern struct kernel_param_ops param_ops_ushort; +extern int param_set_ushort(const char *val, const struct kernel_param *kp); +extern int param_get_ushort(char *buffer, const struct kernel_param *kp); #define param_check_ushort(name, p) __param_check(name, p, unsigned short) -extern int param_set_int(const char *val, struct kernel_param *kp); -extern int param_get_int(char *buffer, struct kernel_param *kp); +extern struct kernel_param_ops param_ops_int; +extern int param_set_int(const char *val, const struct kernel_param *kp); +extern int param_get_int(char *buffer, const struct kernel_param *kp); #define param_check_int(name, p) __param_check(name, p, int) -extern int param_set_uint(const char *val, struct kernel_param *kp); -extern int param_get_uint(char *buffer, struct kernel_param *kp); +extern struct kernel_param_ops param_ops_uint; +extern int param_set_uint(const char *val, const struct kernel_param *kp); +extern int param_get_uint(char *buffer, const struct kernel_param *kp); #define param_check_uint(name, p) __param_check(name, p, unsigned int) -extern int param_set_long(const char *val, struct kernel_param *kp); -extern int param_get_long(char *buffer, struct kernel_param *kp); +extern struct kernel_param_ops param_ops_long; +extern int param_set_long(const char *val, const struct kernel_param *kp); +extern int param_get_long(char *buffer, const struct kernel_param *kp); #define param_check_long(name, p) __param_check(name, p, long) -extern int param_set_ulong(const char *val, struct kernel_param *kp); -extern int param_get_ulong(char *buffer, struct kernel_param *kp); +extern struct kernel_param_ops param_ops_ulong; +extern int param_set_ulong(const char *val, const struct kernel_param *kp); +extern int param_get_ulong(char *buffer, const struct kernel_param *kp); #define param_check_ulong(name, p) __param_check(name, p, unsigned long) -extern int param_set_charp(const char *val, struct kernel_param *kp); -extern int param_get_charp(char *buffer, struct kernel_param *kp); +extern struct kernel_param_ops param_ops_charp; +extern int param_set_charp(const char *val, const struct kernel_param *kp); +extern int param_get_charp(char *buffer, const struct kernel_param *kp); #define param_check_charp(name, p) __param_check(name, p, char *) /* For historical reasons "bool" parameters can be (unsigned) "int". */ -extern int param_set_bool(const char *val, struct kernel_param *kp); -extern int param_get_bool(char *buffer, struct kernel_param *kp); +extern struct kernel_param_ops param_ops_bool; +extern int param_set_bool(const char *val, const struct kernel_param *kp); +extern int param_get_bool(char *buffer, const struct kernel_param *kp); #define param_check_bool(name, p) \ static inline void __check_##name(void) \ { \ @@ -205,17 +231,18 @@ extern int param_get_bool(char *buffer, struct kernel_param *kp); !__same_type(*(p), int)); \ } -extern int param_set_invbool(const char *val, struct kernel_param *kp); -extern int param_get_invbool(char *buffer, struct kernel_param *kp); +extern struct kernel_param_ops param_ops_invbool; +extern int param_set_invbool(const char *val, const struct kernel_param *kp); +extern int param_get_invbool(char *buffer, const struct kernel_param *kp); #define param_check_invbool(name, p) __param_check(name, p, bool) /* Comma-separated array: *nump is set to number they actually specified. */ #define module_param_array_named(name, array, type, nump, perm) \ static const struct kparam_array __param_arr_##name \ - = { ARRAY_SIZE(array), nump, param_set_##type, param_get_##type,\ + = { ARRAY_SIZE(array), nump, ¶m_ops_##type, \ sizeof(array[0]), array }; \ __module_param_call(MODULE_PARAM_PREFIX, name, \ - param_array_set, param_array_get, \ + ¶m_array_ops, \ .arr = &__param_arr_##name, \ __same_type(array[0], bool), perm); \ __MODULE_PARM_TYPE(name, "array of " #type) @@ -223,11 +250,11 @@ extern int param_get_invbool(char *buffer, struct kernel_param *kp); #define module_param_array(name, type, nump, perm) \ module_param_array_named(name, name, type, nump, perm) -extern int param_array_set(const char *val, struct kernel_param *kp); -extern int param_array_get(char *buffer, struct kernel_param *kp); +extern struct kernel_param_ops param_array_ops; -extern int param_set_copystring(const char *val, struct kernel_param *kp); -extern int param_get_string(char *buffer, struct kernel_param *kp); +extern struct kernel_param_ops param_ops_string; +extern int param_set_copystring(const char *val, const struct kernel_param *); +extern int param_get_string(char *buffer, const struct kernel_param *kp); /* for exporting parameters in /sys/parameters */ @@ -235,13 +262,13 @@ struct module; #if defined(CONFIG_SYSFS) && defined(CONFIG_MODULES) extern int module_param_sysfs_setup(struct module *mod, - struct kernel_param *kparam, + const struct kernel_param *kparam, unsigned int num_params); extern void module_param_sysfs_remove(struct module *mod); #else static inline int module_param_sysfs_setup(struct module *mod, - struct kernel_param *kparam, + const struct kernel_param *kparam, unsigned int num_params) { return 0; -- cgit v1.2.3 From e6df34a4429b77fdffb6e05adf263468a3dcda33 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Wed, 11 Aug 2010 23:04:17 -0600 Subject: param: add a free hook to kernel_param_ops. This allows us to generalize the KPARAM_KMALLOCED flag, by calling a function on every parameter when a module is unloaded. Signed-off-by: Rusty Russell Reviewed-by: Takashi Iwai Tested-by: Phil Carmody --- include/linux/moduleparam.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h index 02e5090ce32f..9f51568f51c8 100644 --- a/include/linux/moduleparam.h +++ b/include/linux/moduleparam.h @@ -36,6 +36,8 @@ struct kernel_param_ops { int (*set)(const char *val, const struct kernel_param *kp); /* Returns length written or -errno. Buffer is 4k (ie. be short!) */ int (*get)(char *buffer, const struct kernel_param *kp); + /* Optional function to free kp->arg when module unloaded. */ + void (*free)(void *arg); }; /* Flag bits for kernel_param.flags */ -- cgit v1.2.3 From 914dcaa84c53f2c3efa6016efcae13fd92a8a17c Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Wed, 11 Aug 2010 23:04:18 -0600 Subject: param: make param sections const. Since this section can be read-only (they're in .rodata), they should always have been const. Minor flow-through various functions. Signed-off-by: Rusty Russell Tested-by: Phil Carmody --- include/linux/moduleparam.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h index 9f51568f51c8..6d48831fe7d2 100644 --- a/include/linux/moduleparam.h +++ b/include/linux/moduleparam.h @@ -161,7 +161,7 @@ __check_old_set_param(int (*oldset)(const char *, struct kernel_param *)) /* Called on module insert or kernel boot */ extern int parse_args(const char *name, char *args, - struct kernel_param *params, + const struct kernel_param *params, unsigned num, int (*unknown)(char *param, char *val)); -- cgit v1.2.3 From 907b29eb41aa604477a655bff7345731da94514d Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Wed, 11 Aug 2010 23:04:19 -0600 Subject: param: locking for kernel parameters There may be cases (most obviously, sysfs-writable charp parameters) where a module needs to prevent sysfs access to parameters. Rather than express this in terms of a big lock, the functions are expressed in terms of what they protect against. This is clearer, esp. if the implementation changes to a module-level or even param-level lock. Signed-off-by: Rusty Russell Reviewed-by: Takashi Iwai Tested-by: Phil Carmody --- include/linux/moduleparam.h | 56 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 56 insertions(+) (limited to 'include/linux') diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h index 6d48831fe7d2..ca74a3402d63 100644 --- a/include/linux/moduleparam.h +++ b/include/linux/moduleparam.h @@ -130,6 +130,62 @@ __check_old_set_param(int (*oldset)(const char *, struct kernel_param *)) #define module_param(name, type, perm) \ module_param_named(name, name, type, perm) +/** + * kparam_block_sysfs_write - make sure a parameter isn't written via sysfs. + * @name: the name of the parameter + * + * There's no point blocking write on a paramter that isn't writable via sysfs! + */ +#define kparam_block_sysfs_write(name) \ + do { \ + BUG_ON(!(__param_##name.perm & 0222)); \ + __kernel_param_lock(); \ + } while (0) + +/** + * kparam_unblock_sysfs_write - allows sysfs to write to a parameter again. + * @name: the name of the parameter + */ +#define kparam_unblock_sysfs_write(name) \ + do { \ + BUG_ON(!(__param_##name.perm & 0222)); \ + __kernel_param_unlock(); \ + } while (0) + +/** + * kparam_block_sysfs_read - make sure a parameter isn't read via sysfs. + * @name: the name of the parameter + * + * This also blocks sysfs writes. + */ +#define kparam_block_sysfs_read(name) \ + do { \ + BUG_ON(!(__param_##name.perm & 0444)); \ + __kernel_param_lock(); \ + } while (0) + +/** + * kparam_unblock_sysfs_read - allows sysfs to read a parameter again. + * @name: the name of the parameter + */ +#define kparam_unblock_sysfs_read(name) \ + do { \ + BUG_ON(!(__param_##name.perm & 0444)); \ + __kernel_param_unlock(); \ + } while (0) + +#ifdef CONFIG_SYSFS +extern void __kernel_param_lock(void); +extern void __kernel_param_unlock(void); +#else +static inline void __kernel_param_lock(void) +{ +} +static inline void __kernel_param_unlock(void) +{ +} +#endif + #ifndef MODULE /** * core_param - define a historical core kernel parameter. -- cgit v1.2.3 From 546970bc6afc7fb37447fbac09b82c7884662c21 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Wed, 11 Aug 2010 23:04:20 -0600 Subject: param: add kerneldoc to moduleparam.h Also reorders the macros with the most common ones at the top. Signed-off-by: Rusty Russell Reviewed-by: Takashi Iwai Tested-by: Phil Carmody --- include/linux/moduleparam.h | 121 ++++++++++++++++++++++++++++++++++---------- 1 file changed, 95 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h index ca74a3402d63..893549c04265 100644 --- a/include/linux/moduleparam.h +++ b/include/linux/moduleparam.h @@ -71,6 +71,62 @@ struct kparam_array void *elem; }; +/** + * module_param - typesafe helper for a module/cmdline parameter + * @value: the variable to alter, and exposed parameter name. + * @type: the type of the parameter + * @perm: visibility in sysfs. + * + * @value becomes the module parameter, or (prefixed by KBUILD_MODNAME and a + * ".") the kernel commandline parameter. Note that - is changed to _, so + * the user can use "foo-bar=1" even for variable "foo_bar". + * + * @perm is 0 if the the variable is not to appear in sysfs, or 0444 + * for world-readable, 0644 for root-writable, etc. Note that if it + * is writable, you may need to use kparam_block_sysfs_write() around + * accesses (esp. charp, which can be kfreed when it changes). + * + * The @type is simply pasted to refer to a param_ops_##type and a + * param_check_##type: for convenience many standard types are provided but + * you can create your own by defining those variables. + * + * Standard types are: + * byte, short, ushort, int, uint, long, ulong + * charp: a character pointer + * bool: a bool, values 0/1, y/n, Y/N. + * invbool: the above, only sense-reversed (N = true). + */ +#define module_param(name, type, perm) \ + module_param_named(name, name, type, perm) + +/** + * module_param_named - typesafe helper for a renamed module/cmdline parameter + * @name: a valid C identifier which is the parameter name. + * @value: the actual lvalue to alter. + * @type: the type of the parameter + * @perm: visibility in sysfs. + * + * Usually it's a good idea to have variable names and user-exposed names the + * same, but that's harder if the variable must be non-static or is inside a + * structure. This allows exposure under a different name. + */ +#define module_param_named(name, value, type, perm) \ + param_check_##type(name, &(value)); \ + module_param_cb(name, ¶m_ops_##type, &value, perm); \ + __MODULE_PARM_TYPE(name, #type) + +/** + * module_param_cb - general callback for a module/cmdline parameter + * @name: a valid C identifier which is the parameter name. + * @ops: the set & get operations for this parameter. + * @perm: visibility in sysfs. + * + * The ops can have NULL set or get functions. + */ +#define module_param_cb(name, ops, arg, perm) \ + __module_param_call(MODULE_PARAM_PREFIX, \ + name, ops, arg, __same_type(*(arg), bool), perm) + /* On alpha, ia64 and ppc64 relocations to global data cannot go into read-only sections (which is part of respective UNIX ABI on these platforms). So 'const' makes no sense and even causes compile failures @@ -82,9 +138,7 @@ struct kparam_array #endif /* This is the fundamental function for registering boot/module - parameters. perm sets the visibility in sysfs: 000 means it's - not there, read bits mean it's readable, write bits mean it's - writable. */ + parameters. */ #define __module_param_call(prefix, name, ops, arg, isbool, perm) \ /* Default value instead of permissions? */ \ static int __param_perm_check_##name __attribute__((unused)) = \ @@ -113,23 +167,6 @@ __check_old_set_param(int (*oldset)(const char *, struct kernel_param *)) return 0; } -#define module_param_cb(name, ops, arg, perm) \ - __module_param_call(MODULE_PARAM_PREFIX, \ - name, ops, arg, __same_type(*(arg), bool), perm) - -/* - * Helper functions: type is byte, short, ushort, int, uint, long, - * ulong, charp, bool or invbool, or XXX if you define param_ops_XXX - * and param_check_XXX. - */ -#define module_param_named(name, value, type, perm) \ - param_check_##type(name, &(value)); \ - module_param_cb(name, ¶m_ops_##type, &value, perm); \ - __MODULE_PARM_TYPE(name, #type) - -#define module_param(name, type, perm) \ - module_param_named(name, name, type, perm) - /** * kparam_block_sysfs_write - make sure a parameter isn't written via sysfs. * @name: the name of the parameter @@ -191,7 +228,7 @@ static inline void __kernel_param_unlock(void) * core_param - define a historical core kernel parameter. * @name: the name of the cmdline and sysfs parameter (often the same as var) * @var: the variable - * @type: the type (for param_set_##type and param_get_##type) + * @type: the type of the parameter * @perm: visibility in sysfs * * core_param is just like module_param(), but cannot be modular and @@ -205,7 +242,16 @@ static inline void __kernel_param_unlock(void) &var, __same_type(var, bool), perm) #endif /* !MODULE */ -/* Actually copy string: maxlen param is usually sizeof(string). */ +/** + * module_param_string - a char array parameter + * @name: the name of the parameter + * @string: the string variable + * @len: the maximum length of the string, incl. terminator + * @perm: visibility in sysfs. + * + * This actually copies the string when it's set (unlike type charp). + * @len is usually just sizeof(string). + */ #define module_param_string(name, string, len, perm) \ static const struct kparam_string __param_string_##name \ = { len, string }; \ @@ -294,7 +340,33 @@ extern int param_set_invbool(const char *val, const struct kernel_param *kp); extern int param_get_invbool(char *buffer, const struct kernel_param *kp); #define param_check_invbool(name, p) __param_check(name, p, bool) -/* Comma-separated array: *nump is set to number they actually specified. */ +/** + * module_param_array - a parameter which is an array of some type + * @name: the name of the array variable + * @type: the type, as per module_param() + * @nump: optional pointer filled in with the number written + * @perm: visibility in sysfs + * + * Input and output are as comma-separated values. Commas inside values + * don't work properly (eg. an array of charp). + * + * ARRAY_SIZE(@name) is used to determine the number of elements in the + * array, so the definition must be visible. + */ +#define module_param_array(name, type, nump, perm) \ + module_param_array_named(name, name, type, nump, perm) + +/** + * module_param_array_named - renamed parameter which is an array of some type + * @name: a valid C identifier which is the parameter name + * @array: the name of the array variable + * @type: the type, as per module_param() + * @nump: optional pointer filled in with the number written + * @perm: visibility in sysfs + * + * This exposes a different name than the actual variable name. See + * module_param_named() for why this might be necessary. + */ #define module_param_array_named(name, array, type, nump, perm) \ static const struct kparam_array __param_arr_##name \ = { ARRAY_SIZE(array), nump, ¶m_ops_##type, \ @@ -305,9 +377,6 @@ extern int param_get_invbool(char *buffer, const struct kernel_param *kp); __same_type(array[0], bool), perm); \ __MODULE_PARM_TYPE(name, "array of " #type) -#define module_param_array(name, type, nump, perm) \ - module_param_array_named(name, name, type, nump, perm) - extern struct kernel_param_ops param_array_ops; extern struct kernel_param_ops param_ops_string; -- cgit v1.2.3 From a6de51b2787012ba3ab62c7d50df1b749b83d5f0 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Wed, 11 Aug 2010 23:04:40 -0600 Subject: param: don't deref arg in __same_type() checks gcc allows this when arg is a function, but sparse complains: drivers/char/ipmi/ipmi_watchdog.c:303:1: error: cannot dereference this type drivers/char/ipmi/ipmi_watchdog.c:307:1: error: cannot dereference this type drivers/char/ipmi/ipmi_watchdog.c:311:1: error: cannot dereference this type Reported-by: Randy Dunlap Tested-by: Randy Dunlap Signed-off-by: Rusty Russell --- include/linux/moduleparam.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h index 893549c04265..9d2f1837b3d8 100644 --- a/include/linux/moduleparam.h +++ b/include/linux/moduleparam.h @@ -125,7 +125,7 @@ struct kparam_array */ #define module_param_cb(name, ops, arg, perm) \ __module_param_call(MODULE_PARAM_PREFIX, \ - name, ops, arg, __same_type(*(arg), bool), perm) + name, ops, arg, __same_type((arg), bool *), perm) /* On alpha, ia64 and ppc64 relocations to global data cannot go into read-only sections (which is part of respective UNIX ABI on these @@ -157,7 +157,7 @@ struct kparam_array { (void *)set, (void *)get }; \ __module_param_call(MODULE_PARAM_PREFIX, \ name, &__param_ops_##name, arg, \ - __same_type(*(arg), bool), \ + __same_type(arg, bool *), \ (perm) + sizeof(__check_old_set_param(set))*0) /* We don't get oldget: it's often a new-style param_get_uint, etc. */ @@ -330,9 +330,9 @@ extern int param_get_bool(char *buffer, const struct kernel_param *kp); #define param_check_bool(name, p) \ static inline void __check_##name(void) \ { \ - BUILD_BUG_ON(!__same_type(*(p), bool) && \ - !__same_type(*(p), unsigned int) && \ - !__same_type(*(p), int)); \ + BUILD_BUG_ON(!__same_type((p), bool *) && \ + !__same_type((p), unsigned int *) && \ + !__same_type((p), int *)); \ } extern struct kernel_param_ops param_ops_invbool; -- cgit v1.2.3 From 13bcbc008790b05413c9a16763b423c206528c0a Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Tue, 10 Aug 2010 18:01:09 -0700 Subject: include/linux/fs.h: complete hexification of FMODE_* constants One straggler which was missed due to merge ordering issues. Cc: Wu Fengguang Cc: Eric Paris Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 1542e0e52b2e..267d02630517 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -93,7 +93,7 @@ struct inodes_stat_t { #define FMODE_RANDOM ((__force fmode_t)0x1000) /* File was opened by fanotify and shouldn't generate fanotify events */ -#define FMODE_NONOTIFY ((__force fmode_t)16777216) /* 0x1000000 */ +#define FMODE_NONOTIFY ((__force fmode_t)0x1000000) /* * The below are the various read and write types that we support. Some of -- cgit v1.2.3 From 5a19ae4bb003a428b9c8367daf05eed5029dc4cd Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 10 Aug 2010 18:01:28 -0700 Subject: virtio_9p.h: include linux/types.h Add to so that types are explicitly defined: linux/virtio_9p.h:15: found __[us]{8,16,32,64} type without #include Signed-off-by: Randy Dunlap Cc: Eric Van Hensbergen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/virtio_9p.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/virtio_9p.h b/include/linux/virtio_9p.h index 395c38a47adb..1faa80d92f05 100644 --- a/include/linux/virtio_9p.h +++ b/include/linux/virtio_9p.h @@ -2,6 +2,7 @@ #define _LINUX_VIRTIO_9P_H /* This header is BSD licensed so anyone can use the definitions to implement * compatible drivers/servers. */ +#include #include #include #include -- cgit v1.2.3 From 6da24b786ed1963a7f872c1899627968c76d17d7 Mon Sep 17 00:00:00 2001 From: Kyungmin Park Date: Tue, 10 Aug 2010 18:01:36 -0700 Subject: mmc: recognize CSD structure The eMMC spec 4.4 and 4.3 + additional feature chips has CSD structure version 3 and version 3 have to check the CSD_STRUCTURE byte in the EXT_CSD register. Also fix EXT_CSD revision message. [akpm@linux-foundation.org: fix comment, per Chris Ball] Signed-off-by: Kyungmin Park Cc: Adrian Hunter Cc: Chris Ball Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmc/card.h | 1 + include/linux/mmc/mmc.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index d02d2c6e0cfe..c83c7a7303fd 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -24,6 +24,7 @@ struct mmc_cid { }; struct mmc_csd { + unsigned char structure; unsigned char mmca_vsn; unsigned short cmdclass; unsigned short tacc_clks; diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h index 8a49cbf0376d..52ce98866287 100644 --- a/include/linux/mmc/mmc.h +++ b/include/linux/mmc/mmc.h @@ -254,6 +254,7 @@ struct _mmc_csd { #define EXT_CSD_BUS_WIDTH 183 /* R/W */ #define EXT_CSD_HS_TIMING 185 /* R/W */ #define EXT_CSD_CARD_TYPE 196 /* RO */ +#define EXT_CSD_STRUCTURE 194 /* RO */ #define EXT_CSD_REV 192 /* RO */ #define EXT_CSD_SEC_CNT 212 /* RO, 4 bytes */ #define EXT_CSD_S_A_TIMEOUT 217 -- cgit v1.2.3 From 7310ece86ad7da027f85a37a0638164118a5d12f Mon Sep 17 00:00:00 2001 From: Michal Miroslaw Date: Tue, 10 Aug 2010 18:01:40 -0700 Subject: mmc: implement SD-combo (IO+mem) support Signed-off-by: Michal Miroslaw Cc: Adrian Hunter Cc: Chris Ball Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmc/card.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index c83c7a7303fd..340d391aecbb 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -93,6 +93,7 @@ struct mmc_card { #define MMC_TYPE_MMC 0 /* MMC card */ #define MMC_TYPE_SD 1 /* SD card */ #define MMC_TYPE_SDIO 2 /* SDIO card */ +#define MMC_TYPE_SD_COMBO 3 /* SD combo (IO+mem) card */ unsigned int state; /* (our) card state */ #define MMC_STATE_PRESENT (1<<0) /* present in sysfs */ #define MMC_STATE_READONLY (1<<1) /* card is read-only */ -- cgit v1.2.3 From 4c2ef25fe0b847d2ae818f74758ddb0be1c27d8e Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Tue, 10 Aug 2010 18:01:41 -0700 Subject: mmc: fix all hangs related to mmc/sd card insert/removal during suspend/resume If you don't use CONFIG_MMC_UNSAFE_RESUME, as soon as you attempt to suspend, the card will be removed, therefore this patch doesn't change the behavior of this option. However the removal will be done by pm notifier, which runs while userspace is still not frozen and thus can freely use del_gendisk, without the risk of deadlock which would happen otherwise. Card detect workqueue is now disabled while userspace is frozen, Therefore if you do use CONFIG_MMC_UNSAFE_RESUME, and remove the card during suspend, the removal will be detected as soon as userspace is unfrozen, again at the moment it is safe to call del_gendisk. Tested with and without CONFIG_MMC_UNSAFE_RESUME with suspend and hibernate. [akpm@linux-foundation.org: clean up function prototype] [akpm@linux-foundation.org: fix CONFIG_PM-n linkage, small cleanups] [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Maxim Levitsky Cc: David Brownell Cc: Alan Stern Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmc/host.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index f65913c9f5a4..513ff0376b09 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -124,6 +124,7 @@ struct mmc_host { unsigned int f_min; unsigned int f_max; u32 ocr_avail; + struct notifier_block pm_notify; #define MMC_VDD_165_195 0x00000080 /* VDD voltage 1.65 - 1.95 */ #define MMC_VDD_20_21 0x00000100 /* VDD voltage 2.0 ~ 2.1 */ @@ -183,6 +184,7 @@ struct mmc_host { /* Only used with MMC_CAP_DISABLE */ int enabled; /* host is enabled */ + int rescan_disable; /* disable card detection */ int nesting_cnt; /* "enable" nesting count */ int en_dis_recurs; /* detect recursion */ unsigned int disable_delay; /* disable delay in msecs */ @@ -257,6 +259,7 @@ int mmc_card_can_sleep(struct mmc_host *host); int mmc_host_enable(struct mmc_host *host); int mmc_host_disable(struct mmc_host *host); int mmc_host_lazy_disable(struct mmc_host *host); +int mmc_pm_notify(struct notifier_block *notify_block, unsigned long, void *); static inline void mmc_set_disable_delay(struct mmc_host *host, unsigned int disable_delay) -- cgit v1.2.3 From 6f51be3d37dff73cf8db771df4169f4c2f1cbf66 Mon Sep 17 00:00:00 2001 From: Grazvydas Ignotas Date: Tue, 10 Aug 2010 18:01:50 -0700 Subject: sdio: allow non-standard SDIO cards There are some chips (like TI WL12xx series) that can be interfaced over SDIO but don't support the SDIO specification, meaning that they are missing CIA (Common I/O Area) with all it's registers. Current Linux SDIO implementation relies on those registers to identify and configure the card, so non-standard cards can not function and cause lots of warnings from the core when it reads invalid data from non-existent registers. After this patch, init_card() host callback can now set new quirk MMC_QUIRK_NONSTD_SDIO, which means that SDIO core should not try to access any standard SDIO registers and rely on init_card() to fill all SDIO structures instead. As those cards are usually embedded chips, all the required information can be obtained from machine board files by the host driver when it's called through init_card() callback. Signed-off-by: Grazvydas Ignotas Cc: Adrian Hunter Cc: Tony Lindgren Cc: Bob Copeland Cc: Kalle Valo Cc: Madhusudhan Chikkature Cc: Kishore Kadiyala Cc: Russell King Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmc/card.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 340d391aecbb..4d893eaf8174 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -103,6 +103,8 @@ struct mmc_card { #define MMC_QUIRK_LENIENT_FN0 (1<<0) /* allow SDIO FN0 writes outside of the VS CCCR range */ #define MMC_QUIRK_BLKSZ_FOR_BYTE_MODE (1<<1) /* use func->cur_blksize */ /* for byte mode */ +#define MMC_QUIRK_NONSTD_SDIO (1<<2) /* non-standard SDIO card attached */ + /* (missing CIA registers) */ u32 raw_cid[4]; /* raw card CID */ u32 raw_csd[4]; /* raw card CSD */ -- cgit v1.2.3 From 4a22b8a4ad5561436b16f5278d2f9e406ffb8705 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Tue, 10 Aug 2010 18:02:23 -0700 Subject: gpio: max730x: make pullups configurable via platformdata The gpios on the max730x chips have support for internal pullups while in input mode. This patch adds support for configuring these pullups via platform data. A new member ("input_pullup_active") to the platform data struct is introduced. A set bit in this variable activates the pullups while the respective port is in input mode. This is a compatible enhancement since unset bits lead to disables pullups which was the default in the original driver. _Note_: the 4 lowest bits in "input_pullup_active" are unused because the first 4 ports of the controller are not used, too. Signed-off-by: Marc Kleine-Budde Reviewed-by: Wolfram Sang Cc: David Brownell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/spi/max7301.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/max7301.h b/include/linux/spi/max7301.h index 34af0a3477bf..bcaa2f762cc1 100644 --- a/include/linux/spi/max7301.h +++ b/include/linux/spi/max7301.h @@ -11,6 +11,7 @@ struct max7301 { struct mutex lock; u8 port_config[8]; /* field 0 is unused */ u32 out_level; /* cached output levels */ + u32 input_pullup_active; struct gpio_chip chip; struct device *dev; int (*write)(struct device *dev, unsigned int reg, unsigned int val); @@ -20,6 +21,13 @@ struct max7301 { struct max7301_platform_data { /* number assigned to the first GPIO */ unsigned base; + /* + * bitmask controlling the pullup configuration, + * + * _note_ the 4 lowest bits are unused, because the first 4 + * ports of the controller are not used, too. + */ + u32 input_pullup_active; }; extern int __max730x_remove(struct device *dev); -- cgit v1.2.3 From c34f16b70a52e348a62944fe0d5c7c1eb9ad5b72 Mon Sep 17 00:00:00 2001 From: Gregory Bean Date: Tue, 10 Aug 2010 18:02:27 -0700 Subject: gpio: sx150x: add Semtech I2C sx150x gpio expander driver Add support for Semtech SX150-series I2C GPIO expanders. Compatible models include: 8 bits: sx1508q 16 bits: sx1509q Signed-off-by: Gregory Bean Cc: David Brownell Cc: Jean Delvare Cc: Trilok Soni Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/i2c/sx150x.h | 78 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 78 insertions(+) create mode 100644 include/linux/i2c/sx150x.h (limited to 'include/linux') diff --git a/include/linux/i2c/sx150x.h b/include/linux/i2c/sx150x.h new file mode 100644 index 000000000000..ee3049cb9ba5 --- /dev/null +++ b/include/linux/i2c/sx150x.h @@ -0,0 +1,78 @@ +/* + * Driver for the Semtech SX150x I2C GPIO Expanders + * + * Copyright (c) 2010, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ +#ifndef __LINUX_I2C_SX150X_H +#define __LINUX_I2C_SX150X_H + +/** + * struct sx150x_platform_data - config data for SX150x driver + * @gpio_base: The index number of the first GPIO assigned to this + * GPIO expander. The expander will create a block of + * consecutively numbered gpios beginning at the given base, + * with the size of the block depending on the model of the + * expander chip. + * @oscio_is_gpo: If set to true, the driver will configure OSCIO as a GPO + * instead of as an oscillator, increasing the size of the + * GP(I)O pool created by this expander by one. The + * output-only GPO pin will be added at the end of the block. + * @io_pullup_ena: A bit-mask which enables or disables the pull-up resistor + * for each IO line in the expander. Setting the bit at + * position n will enable the pull-up for the IO at + * the corresponding offset. For chips with fewer than + * 16 IO pins, high-end bits are ignored. + * @io_pulldn_ena: A bit-mask which enables-or disables the pull-down + * resistor for each IO line in the expander. Setting the + * bit at position n will enable the pull-down for the IO at + * the corresponding offset. For chips with fewer than + * 16 IO pins, high-end bits are ignored. + * @io_open_drain_ena: A bit-mask which enables-or disables open-drain + * operation for each IO line in the expander. Setting the + * bit at position n enables open-drain operation for + * the IO at the corresponding offset. Clearing the bit + * enables regular push-pull operation for that IO. + * For chips with fewer than 16 IO pins, high-end bits + * are ignored. + * @io_polarity: A bit-mask which enables polarity inversion for each IO line + * in the expander. Setting the bit at position n inverts + * the polarity of that IO line, while clearing it results + * in normal polarity. For chips with fewer than 16 IO pins, + * high-end bits are ignored. + * @irq_summary: The 'summary IRQ' line to which the GPIO expander's INT line + * is connected, via which it reports interrupt events + * across all GPIO lines. This must be a real, + * pre-existing IRQ line. + * Setting this value < 0 disables the irq_chip functionality + * of the driver. + * @irq_base: The first 'virtual IRQ' line at which our block of GPIO-based + * IRQ lines will appear. Similarly to gpio_base, the expander + * will create a block of irqs beginning at this number. + * This value is ignored if irq_summary is < 0. + */ +struct sx150x_platform_data { + unsigned gpio_base; + bool oscio_is_gpo; + u16 io_pullup_ena; + u16 io_pulldn_ena; + u16 io_open_drain_ena; + u16 io_polarity; + int irq_summary; + unsigned irq_base; +}; + +#endif /* __LINUX_I2C_SX150X_H */ -- cgit v1.2.3 From 158e0a2d1b3cffed8b46cbc56393a1394672ef79 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Tue, 10 Aug 2010 18:03:00 -0700 Subject: memcg: use find_lock_task_mm() in memory cgroups oom When the OOM killer scans task, it check a task is under memcg or not when it's called via memcg's context. But, as Oleg pointed out, a thread group leader may have NULL ->mm and task_in_mem_cgroup() may do wrong decision. We have to use find_lock_task_mm() in memcg as generic OOM-Killer does. Signed-off-by: KAMEZAWA Hiroyuki Cc: Oleg Nesterov Cc: Daisuke Nishimura Cc: Balbir Singh Reviewed-by: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/oom.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/oom.h b/include/linux/oom.h index f209b683e118..5e3aa8311c5e 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -66,6 +66,8 @@ static inline void oom_killer_enable(void) extern unsigned long badness(struct task_struct *p, struct mem_cgroup *mem, const nodemask_t *nodemask, unsigned long uptime); +extern struct task_struct *find_lock_task_mm(struct task_struct *p); + /* sysctls */ extern int sysctl_oom_dump_tasks; extern int sysctl_oom_kill_allocating_task; -- cgit v1.2.3 From 14fec79680f7cc4617d6ba69324e63d4a732986c Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Tue, 10 Aug 2010 18:03:05 -0700 Subject: memcg: mem_cgroup_shrink_node_zone() doesn't need sc.nodemask Currently mem_cgroup_shrink_node_zone() call shrink_zone() directly. thus it doesn't need to initialize sc.nodemask because shrink_zone() doesn't use it at all. Signed-off-by: KOSAKI Motohiro Acked-by: KAMEZAWA Hiroyuki Acked-by: Mel Gorman Cc: Balbir Singh Cc: Nishimura Daisuke Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 91c9d3fc8513..2fee51a11b73 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -244,8 +244,7 @@ extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem, extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem, gfp_t gfp_mask, bool noswap, unsigned int swappiness, - struct zone *zone, - int nid); + struct zone *zone); extern int __isolate_lru_page(struct page *page, int mode, int file); extern unsigned long shrink_all_memory(unsigned long nr_pages); extern int vm_swappiness; -- cgit v1.2.3 From 00918b6ab89df8984ca06397cb77994dabd73f9b Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Tue, 10 Aug 2010 18:03:05 -0700 Subject: memcg: remove nid and zid argument from mem_cgroup_soft_limit_reclaim() mem_cgroup_soft_limit_reclaim() has zone, nid and zid argument. but nid and zid can be calculated from zone. So remove it. Signed-off-by: KOSAKI Motohiro Acked-by: KAMEZAWA Hiroyuki Acked-by: Mel Gorman Cc: Balbir Singh Cc: Nishimura Daisuke Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 73564cac38c7..159a0762aeaf 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -123,8 +123,7 @@ static inline bool mem_cgroup_disabled(void) void mem_cgroup_update_file_mapped(struct page *page, int val); unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, - gfp_t gfp_mask, int nid, - int zid); + gfp_t gfp_mask); u64 mem_cgroup_get_limit(struct mem_cgroup *mem); #else /* CONFIG_CGROUP_MEM_RES_CTLR */ @@ -301,7 +300,7 @@ static inline void mem_cgroup_update_file_mapped(struct page *page, static inline unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, - gfp_t gfp_mask, int nid, int zid) + gfp_t gfp_mask) { return 0; } -- cgit v1.2.3 From a6eb9fe105d5de0053b261148cee56c94b4720ca Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Tue, 10 Aug 2010 18:03:22 -0700 Subject: dma-mapping: rename ARCH_KMALLOC_MINALIGN to ARCH_DMA_MINALIGN Now each architecture has the own dma_get_cache_alignment implementation. dma_get_cache_alignment returns the minimum DMA alignment. Architectures define it as ARCH_KMALLOC_MINALIGN (it's used to make sure that malloc'ed buffer is DMA-safe; the buffer doesn't share a cache with the others). So we can unify dma_get_cache_alignment implementations. This patch: dma_get_cache_alignment() needs to know if an architecture defines ARCH_KMALLOC_MINALIGN or not (needs to know if architecture has DMA alignment restriction). However, slab.h define ARCH_KMALLOC_MINALIGN if architectures doesn't define it. Let's rename ARCH_KMALLOC_MINALIGN to ARCH_DMA_MINALIGN. ARCH_KMALLOC_MINALIGN is used only in the internals of slab/slob/slub (except for crypto). Signed-off-by: FUJITA Tomonori Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab_def.h | 4 +++- include/linux/slob_def.h | 4 +++- include/linux/slub_def.h | 8 +++++--- 3 files changed, 11 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index 1acfa73ce2ac..791a502f6906 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -17,7 +17,6 @@ #include -#ifndef ARCH_KMALLOC_MINALIGN /* * Enforce a minimum alignment for the kmalloc caches. * Usually, the kmalloc caches are cache_line_size() aligned, except when @@ -27,6 +26,9 @@ * ARCH_KMALLOC_MINALIGN allows that. * Note that increasing this value may disable some debug features. */ +#ifdef ARCH_DMA_MINALIGN +#define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN +#else #define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long) #endif diff --git a/include/linux/slob_def.h b/include/linux/slob_def.h index 62667f72c2ef..4382db09df4f 100644 --- a/include/linux/slob_def.h +++ b/include/linux/slob_def.h @@ -1,7 +1,9 @@ #ifndef __LINUX_SLOB_DEF_H #define __LINUX_SLOB_DEF_H -#ifndef ARCH_KMALLOC_MINALIGN +#ifdef ARCH_DMA_MINALIGN +#define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN +#else #define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long) #endif diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 6447a723ecb1..6d14409c4d9a 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -106,15 +106,17 @@ struct kmem_cache { /* * Kmalloc subsystem. */ -#if defined(ARCH_KMALLOC_MINALIGN) && ARCH_KMALLOC_MINALIGN > 8 -#define KMALLOC_MIN_SIZE ARCH_KMALLOC_MINALIGN +#if defined(ARCH_DMA_MINALIGN) && ARCH_DMA_MINALIGN > 8 +#define KMALLOC_MIN_SIZE ARCH_DMA_MINALIGN #else #define KMALLOC_MIN_SIZE 8 #endif #define KMALLOC_SHIFT_LOW ilog2(KMALLOC_MIN_SIZE) -#ifndef ARCH_KMALLOC_MINALIGN +#ifdef ARCH_DMA_MINALIGN +#define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN +#else #define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long) #endif -- cgit v1.2.3 From 4565f0170dfc849b3629c27d769db800467baa62 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Tue, 10 Aug 2010 18:03:22 -0700 Subject: dma-mapping: unify dma_get_cache_alignment implementations dma_get_cache_alignment returns the minimum DMA alignment. Architectures defines it as ARCH_DMA_MINALIGN (formally ARCH_KMALLOC_MINALIGN). So we can unify dma_get_cache_alignment implementations. Note that some architectures implement dma_get_cache_alignment wrongly. dma_get_cache_alignment() should return the minimum DMA alignment. So fully-coherent architectures should return 1. This patch also fixes this issue. Signed-off-by: FUJITA Tomonori Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/dma-mapping.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 89b7e1a605b8..e0670a512056 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -142,6 +142,14 @@ static inline int dma_set_seg_boundary(struct device *dev, unsigned long mask) return -EIO; } +static inline int dma_get_cache_alignment(void) +{ +#ifdef ARCH_DMA_MINALIGN + return ARCH_DMA_MINALIGN; +#endif + return 1; +} + /* flags for the coherent memory api */ #define DMA_MEMORY_MAP 0x01 #define DMA_MEMORY_IO 0x02 -- cgit v1.2.3 From c7ff0d9c92435e836e13aaa8d0e56d4000424bcc Mon Sep 17 00:00:00 2001 From: TAMUKI Shoichi Date: Tue, 10 Aug 2010 18:03:28 -0700 Subject: panic: keep blinking in spite of long spin timer mode To keep panic_timeout accuracy when running under a hypervisor, the current implementation only spins on long time (1 second) calls to mdelay. That brings a good effect, but the problem is the keyboard LEDs don't blink at all on that situation. This patch changes to call to panic_blink_enter() between every mdelay and keeps blinking in spite of long spin timer mode. The time to call to mdelay is now 100ms. Even this change will keep panic_timeout accuracy enough when running under a hypervisor. Signed-off-by: TAMUKI Shoichi Cc: Ben Dooks Cc: Russell King Acked-by: Dmitry Torokhov Cc: Anton Blanchard Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 5b57236dfbd0..452833d67b21 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -177,7 +177,7 @@ struct va_format { }; extern struct atomic_notifier_head panic_notifier_list; -extern long (*panic_blink)(long time); +extern long (*panic_blink)(int state); NORET_TYPE void panic(const char * fmt, ...) __attribute__ ((NORET_AND format (printf, 1, 2))) __cold; extern void oops_enter(void); -- cgit v1.2.3 From 863a6049202412a6d655d052eb1c45ca7dd74a83 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 10 Aug 2010 18:03:30 -0700 Subject: lib/bug.c: add oops end marker to WARN implementation We are missing the oops end marker for the exception based WARN implementation in lib/bug.c. This is useful for logfile analysis tools. Signed-off-by: Anton Blanchard Cc: Ingo Molnar Cc: Arjan van de Ven Cc: "Kirill A. Shutemov" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 452833d67b21..d848cb854655 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -182,6 +182,7 @@ NORET_TYPE void panic(const char * fmt, ...) __attribute__ ((NORET_AND format (printf, 1, 2))) __cold; extern void oops_enter(void); extern void oops_exit(void); +void print_oops_end_marker(void); extern int oops_may_print(void); NORET_TYPE void do_exit(long error_code) ATTRIB_NORET; -- cgit v1.2.3 From 0bcaa65a56ab74003666cf741b0bfa1e9263a11c Mon Sep 17 00:00:00 2001 From: Lubomir Rintel Date: Tue, 10 Aug 2010 18:03:33 -0700 Subject: fs/sysv: v7: adjust sanity checks for some volumes Newly mkfs-ed filesystems from Seventh Edition have last modification time set to zero, but are otherwise perfectly valid. Also, tighten up other sanity checks to filter out most filesystems with [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Lubomir Rintel Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sysv_fs.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sysv_fs.h b/include/linux/sysv_fs.h index 96411306eec6..e47d6d90023d 100644 --- a/include/linux/sysv_fs.h +++ b/include/linux/sysv_fs.h @@ -148,6 +148,17 @@ struct v7_super_block { char s_fname[6]; /* file system name */ char s_fpack[6]; /* file system pack name */ }; +/* Constants to aid sanity checking */ +/* This is not a hard limit, nor enforced by v7 kernel. It's actually just + * the limit used by Seventh Edition's ls, though is high enough to assume + * that no reasonable file system would have that much entries in root + * directory. Thus, if we see anything higher, we just probably got the + * endiannes wrong. */ +#define V7_NFILES 1024 +/* The disk addresses are three-byte (despite direct block addresses being + * aligned word-wise in inode). If the most significant byte is non-zero, + * something is most likely wrong (not a filesystem, bad bytesex). */ +#define V7_MAXSIZE 0x00ffffff /* Coherent super-block data on disk */ #define COH_NICINOD 100 /* number of inode cache entries */ -- cgit v1.2.3 From ad9c7ed0685406fe3cd7f0749b82bf433a39dd9c Mon Sep 17 00:00:00 2001 From: "Robert P. J. Day" Date: Tue, 10 Aug 2010 18:03:34 -0700 Subject: kfifo: kfifo_is_{full,empty} should return bools, not ints For consistency with other kfifo routines, return bool, not int. Signed-off-by: Robert P. J. Day Cc: Stefani Seibold Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kfifo.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kfifo.h b/include/linux/kfifo.h index 9fad0527344f..57c4eedf4dd6 100644 --- a/include/linux/kfifo.h +++ b/include/linux/kfifo.h @@ -171,7 +171,7 @@ static inline unsigned int kfifo_len(struct kfifo *fifo) * kfifo_is_empty - returns true if the fifo is empty * @fifo: the fifo to be used. */ -static inline __must_check int kfifo_is_empty(struct kfifo *fifo) +static inline __must_check bool kfifo_is_empty(struct kfifo *fifo) { return fifo->in == fifo->out; } @@ -180,7 +180,7 @@ static inline __must_check int kfifo_is_empty(struct kfifo *fifo) * kfifo_is_full - returns true if the fifo is full * @fifo: the fifo to be used. */ -static inline __must_check int kfifo_is_full(struct kfifo *fifo) +static inline __must_check bool kfifo_is_full(struct kfifo *fifo) { return kfifo_len(fifo) == kfifo_size(fifo); } -- cgit v1.2.3 From 4201d9a8e86b51dd40aa8a0dabd093376c859985 Mon Sep 17 00:00:00 2001 From: Stefani Seibold Date: Tue, 10 Aug 2010 18:03:38 -0700 Subject: kfifo: add the new generic kfifo API Add the new version of the kfifo API files kfifo.c and kfifo.h. Signed-off-by: Stefani Seibold Cc: Greg KH Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kfifo-new.h | 844 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 844 insertions(+) create mode 100644 include/linux/kfifo-new.h (limited to 'include/linux') diff --git a/include/linux/kfifo-new.h b/include/linux/kfifo-new.h new file mode 100644 index 000000000000..311f8753d713 --- /dev/null +++ b/include/linux/kfifo-new.h @@ -0,0 +1,844 @@ +/* + * A generic kernel FIFO implementation + * + * Copyright (C) 2009/2010 Stefani Seibold + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + * + */ + +#ifndef _LINUX_KFIFO_H +#define _LINUX_KFIFO_H + +/* + * How to porting drivers to the new generic FIFO API: + * + * - Modify the declaration of the "struct kfifo *" object into a + * in-place "struct kfifo" object + * - Init the in-place object with kfifo_alloc() or kfifo_init() + * Note: The address of the in-place "struct kfifo" object must be + * passed as the first argument to this functions + * - Replace the use of __kfifo_put into kfifo_in and __kfifo_get + * into kfifo_out + * - Replace the use of kfifo_put into kfifo_in_spinlocked and kfifo_get + * into kfifo_out_spinlocked + * Note: the spinlock pointer formerly passed to kfifo_init/kfifo_alloc + * must be passed now to the kfifo_in_spinlocked and kfifo_out_spinlocked + * as the last parameter + * - The formerly __kfifo_* functions are renamed into kfifo_* + */ + +/* + * Note about locking : There is no locking required until only * one reader + * and one writer is using the fifo and no kfifo_reset() will be * called + * kfifo_reset_out() can be safely used, until it will be only called + * in the reader thread. + * For multiple writer and one reader there is only a need to lock the writer. + * And vice versa for only one writer and multiple reader there is only a need + * to lock the reader. + */ + +#include +#include +#include +#include + +struct __kfifo { + unsigned int in; + unsigned int out; + unsigned int mask; + unsigned int esize; + void *data; +}; + +#define __STRUCT_KFIFO_COMMON(datatype, recsize, ptrtype) \ + union { \ + struct __kfifo kfifo; \ + datatype *type; \ + char (*rectype)[recsize]; \ + ptrtype *ptr; \ + const ptrtype *ptr_const; \ + } + +#define __STRUCT_KFIFO(type, size, recsize, ptrtype) \ +{ \ + __STRUCT_KFIFO_COMMON(type, recsize, ptrtype); \ + type buf[((size < 2) || (size & (size - 1))) ? -1 : size]; \ +} + +#define STRUCT_KFIFO(type, size) \ + struct __STRUCT_KFIFO(type, size, 0, type) + +#define __STRUCT_KFIFO_PTR(type, recsize, ptrtype) \ +{ \ + __STRUCT_KFIFO_COMMON(type, recsize, ptrtype); \ + type buf[0]; \ +} + +#define STRUCT_KFIFO_PTR(type) \ + struct __STRUCT_KFIFO_PTR(type, 0, type) + +/* + * define compatibility "struct kfifo" for dynamic allocated fifos + */ +struct kfifo __STRUCT_KFIFO_PTR(unsigned char, 0, void); + +#define STRUCT_KFIFO_REC_1(size) \ + struct __STRUCT_KFIFO(unsigned char, size, 1, void) + +#define STRUCT_KFIFO_REC_2(size) \ + struct __STRUCT_KFIFO(unsigned char, size, 2, void) + +/* + * define kfifo_rec types + */ +struct kfifo_rec_ptr_1 __STRUCT_KFIFO_PTR(unsigned char, 1, void); +struct kfifo_rec_ptr_2 __STRUCT_KFIFO_PTR(unsigned char, 2, void); + +/* + * helper macro to distinguish between real in place fifo where the fifo + * array is a part of the structure and the fifo type where the array is + * outside of the fifo structure. + */ +#define __is_kfifo_ptr(fifo) (sizeof(*fifo) == sizeof(struct __kfifo)) + +/** + * DECLARE_KFIFO_PTR - macro to declare a fifo pointer object + * @fifo: name of the declared fifo + * @type: type of the fifo elements + */ +#define DECLARE_KFIFO_PTR(fifo, type) STRUCT_KFIFO_PTR(type) fifo + +/** + * DECLARE_KFIFO - macro to declare a fifo object + * @fifo: name of the declared fifo + * @type: type of the fifo elements + * @size: the number of elements in the fifo, this must be a power of 2 + */ +#define DECLARE_KFIFO(fifo, type, size) STRUCT_KFIFO(type, size) fifo + +/** + * INIT_KFIFO - Initialize a fifo declared by DECLARE_KFIFO + * @fifo: name of the declared fifo datatype + */ +#define INIT_KFIFO(fifo) \ +(void)({ \ + typeof(&(fifo)) __tmp = &(fifo); \ + struct __kfifo *__kfifo = &__tmp->kfifo; \ + __kfifo->in = 0; \ + __kfifo->out = 0; \ + __kfifo->mask = __is_kfifo_ptr(__tmp) ? 0 : ARRAY_SIZE(__tmp->buf) - 1;\ + __kfifo->esize = sizeof(*__tmp->buf); \ + __kfifo->data = __is_kfifo_ptr(__tmp) ? NULL : __tmp->buf; \ +}) + +/** + * DEFINE_KFIFO - macro to define and initialize a fifo + * @fifo: name of the declared fifo datatype + * @type: type of the fifo elements + * @size: the number of elements in the fifo, this must be a power of 2 + * + * Note: the macro can be used for global and local fifo data type variables. + */ +#define DEFINE_KFIFO(fifo, type, size) \ + DECLARE_KFIFO(fifo, type, size) = \ + (typeof(fifo)) { \ + { \ + { \ + .in = 0, \ + .out = 0, \ + .mask = __is_kfifo_ptr(&(fifo)) ? \ + 0 : \ + ARRAY_SIZE((fifo).buf) - 1, \ + .esize = sizeof(*(fifo).buf), \ + .data = __is_kfifo_ptr(&(fifo)) ? \ + NULL : \ + (fifo).buf, \ + } \ + } \ + } + + +static inline unsigned int __must_check +__kfifo_must_check_helper(unsigned int val) +{ + return val; +} + +/** + * kfifo_initialized - Check if the fifo is initialized + * @fifo: address of the fifo to check + * + * Return %true if fifo is initialized, otherwise %false. + * Assumes the fifo was 0 before. + */ +#define kfifo_initialized(fifo) ((fifo)->kfifo.mask) + +/** + * kfifo_esize - returns the size of the element managed by the fifo + * @fifo: address of the fifo to be used + */ +#define kfifo_esize(fifo) ((fifo)->kfifo.esize) + +/** + * kfifo_recsize - returns the size of the record length field + * @fifo: address of the fifo to be used + */ +#define kfifo_recsize(fifo) (sizeof(*(fifo)->rectype)) + +/** + * kfifo_size - returns the size of the fifo in elements + * @fifo: address of the fifo to be used + */ +#define kfifo_size(fifo) ((fifo)->kfifo.mask + 1) + +/** + * kfifo_reset - removes the entire fifo content + * @fifo: address of the fifo to be used + * + * Note: usage of kfifo_reset() is dangerous. It should be only called when the + * fifo is exclusived locked or when it is secured that no other thread is + * accessing the fifo. + */ +#define kfifo_reset(fifo) \ +(void)({ \ + typeof(fifo + 1) __tmp = (fifo); \ + __tmp->kfifo.in = __tmp->kfifo.out = 0; \ +}) + +/** + * kfifo_reset_out - skip fifo content + * @fifo: address of the fifo to be used + * + * Note: The usage of kfifo_reset_out() is safe until it will be only called + * from the reader thread and there is only one concurrent reader. Otherwise + * it is dangerous and must be handled in the same way as kfifo_reset(). + */ +#define kfifo_reset_out(fifo) \ +(void)({ \ + typeof(fifo + 1) __tmp = (fifo); \ + __tmp->kfifo.out = __tmp->kfifo.in; \ +}) + +/** + * kfifo_len - returns the number of used elements in the fifo + * @fifo: address of the fifo to be used + */ +#define kfifo_len(fifo) \ +({ \ + typeof(fifo + 1) __tmpl = (fifo); \ + __tmpl->kfifo.in - __tmpl->kfifo.out; \ +}) + +/** + * kfifo_is_empty - returns true if the fifo is empty + * @fifo: address of the fifo to be used + */ +#define kfifo_is_empty(fifo) \ +({ \ + typeof(fifo + 1) __tmpq = (fifo); \ + __tmpq->kfifo.in == __tmpq->kfifo.out; \ +}) + +/** + * kfifo_is_full - returns true if the fifo is full + * @fifo: address of the fifo to be used + */ +#define kfifo_is_full(fifo) \ +({ \ + typeof(fifo + 1) __tmpq = (fifo); \ + kfifo_len(__tmpq) > __tmpq->kfifo.mask; \ +}) + +/** + * kfifo_avail - returns the number of unused elements in the fifo + * @fifo: address of the fifo to be used + */ +#define kfifo_avail(fifo) \ +__kfifo_must_check_helper( \ +({ \ + typeof(fifo + 1) __tmpq = (fifo); \ + const size_t __recsize = sizeof(*__tmpq->rectype); \ + unsigned int __avail = kfifo_size(__tmpq) - kfifo_len(__tmpq); \ + (__recsize) ? ((__avail <= __recsize) ? 0 : \ + __kfifo_max_r(__avail - __recsize, __recsize)) : \ + __avail; \ +}) \ +) + +/** + * kfifo_skip - skip output data + * @fifo: address of the fifo to be used + */ +#define kfifo_skip(fifo) \ +(void)({ \ + typeof(fifo + 1) __tmp = (fifo); \ + const size_t __recsize = sizeof(*__tmp->rectype); \ + struct __kfifo *__kfifo = &__tmp->kfifo; \ + if (__recsize) \ + __kfifo_skip_r(__kfifo, __recsize); \ + else \ + __kfifo->out++; \ +}) + +/** + * kfifo_peek_len - gets the size of the next fifo record + * @fifo: address of the fifo to be used + * + * This function returns the size of the next fifo record in number of bytes. + */ +#define kfifo_peek_len(fifo) \ +__kfifo_must_check_helper( \ +({ \ + typeof(fifo + 1) __tmp = (fifo); \ + const size_t __recsize = sizeof(*__tmp->rectype); \ + struct __kfifo *__kfifo = &__tmp->kfifo; \ + (!__recsize) ? kfifo_len(__tmp) * sizeof(*__tmp->type) : \ + __kfifo_len_r(__kfifo, __recsize); \ +}) \ +) + +/** + * kfifo_alloc - dynamically allocates a new fifo buffer + * @fifo: pointer to the fifo + * @size: the number of elements in the fifo, this must be a power of 2 + * @gfp_mask: get_free_pages mask, passed to kmalloc() + * + * This macro dynamically allocates a new fifo buffer. + * + * The numer of elements will be rounded-up to a power of 2. + * The fifo will be release with kfifo_free(). + * Return 0 if no error, otherwise an error code. + */ +#define kfifo_alloc(fifo, size, gfp_mask) \ +__kfifo_must_check_helper( \ +({ \ + typeof(fifo + 1) __tmp = (fifo); \ + struct __kfifo *__kfifo = &__tmp->kfifo; \ + __is_kfifo_ptr(__tmp) ? \ + __kfifo_alloc(__kfifo, size, sizeof(*__tmp->type), gfp_mask) : \ + -EINVAL; \ +}) \ +) + +/** + * kfifo_free - frees the fifo + * @fifo: the fifo to be freed + */ +#define kfifo_free(fifo) \ +({ \ + typeof(fifo + 1) __tmp = (fifo); \ + struct __kfifo *__kfifo = &__tmp->kfifo; \ + if (__is_kfifo_ptr(__tmp)) \ + __kfifo_free(__kfifo); \ +}) + +/** + * kfifo_init - initialize a fifo using a preallocated buffer + * @fifo: the fifo to assign the buffer + * @buffer: the preallocated buffer to be used + * @size: the size of the internal buffer, this have to be a power of 2 + * + * This macro initialize a fifo using a preallocated buffer. + * + * The numer of elements will be rounded-up to a power of 2. + * Return 0 if no error, otherwise an error code. + */ +#define kfifo_init(fifo, buffer, size) \ +({ \ + typeof(fifo + 1) __tmp = (fifo); \ + struct __kfifo *__kfifo = &__tmp->kfifo; \ + __is_kfifo_ptr(__tmp) ? \ + __kfifo_init(__kfifo, buffer, size, sizeof(*__tmp->type)) : \ + -EINVAL; \ +}) + +/** + * kfifo_put - put data into the fifo + * @fifo: address of the fifo to be used + * @val: the data to be added + * + * This macro copies the given value into the fifo. + * It returns 0 if the fifo was full. Otherwise it returns the number + * processed elements. + * + * Note that with only one concurrent reader and one concurrent + * writer, you don't need extra locking to use these macro. + */ +#define kfifo_put(fifo, val) \ +({ \ + typeof(fifo + 1) __tmp = (fifo); \ + typeof(val + 1) __val = (val); \ + unsigned int __ret; \ + const size_t __recsize = sizeof(*__tmp->rectype); \ + struct __kfifo *__kfifo = &__tmp->kfifo; \ + if (0) { \ + typeof(__tmp->ptr_const) __dummy __attribute__ ((unused)); \ + __dummy = (typeof(__val))NULL; \ + } \ + if (__recsize) \ + __ret = __kfifo_in_r(__kfifo, __val, sizeof(*__val), \ + __recsize); \ + else { \ + __ret = !kfifo_is_full(__tmp); \ + if (__ret) { \ + (__is_kfifo_ptr(__tmp) ? \ + ((typeof(__tmp->type))__kfifo->data) : \ + (__tmp->buf) \ + )[__kfifo->in & __tmp->kfifo.mask] = \ + *(typeof(__tmp->type))__val; \ + smp_wmb(); \ + __kfifo->in++; \ + } \ + } \ + __ret; \ +}) + +/** + * kfifo_get - get data from the fifo + * @fifo: address of the fifo to be used + * @val: the var where to store the data to be added + * + * This macro reads the data from the fifo. + * It returns 0 if the fifo was empty. Otherwise it returns the number + * processed elements. + * + * Note that with only one concurrent reader and one concurrent + * writer, you don't need extra locking to use these macro. + */ +#define kfifo_get(fifo, val) \ +__kfifo_must_check_helper( \ +({ \ + typeof(fifo + 1) __tmp = (fifo); \ + typeof(val + 1) __val = (val); \ + unsigned int __ret; \ + const size_t __recsize = sizeof(*__tmp->rectype); \ + struct __kfifo *__kfifo = &__tmp->kfifo; \ + if (0) \ + __val = (typeof(__tmp->ptr))0; \ + if (__recsize) \ + __ret = __kfifo_out_r(__kfifo, __val, sizeof(*__val), \ + __recsize); \ + else { \ + __ret = !kfifo_is_empty(__tmp); \ + if (__ret) { \ + *(typeof(__tmp->type))__val = \ + (__is_kfifo_ptr(__tmp) ? \ + ((typeof(__tmp->type))__kfifo->data) : \ + (__tmp->buf) \ + )[__kfifo->out & __tmp->kfifo.mask]; \ + smp_wmb(); \ + __kfifo->out++; \ + } \ + } \ + __ret; \ +}) \ +) + +/** + * kfifo_peek - get data from the fifo without removing + * @fifo: address of the fifo to be used + * @val: the var where to store the data to be added + * + * This reads the data from the fifo without removing it from the fifo. + * It returns 0 if the fifo was empty. Otherwise it returns the number + * processed elements. + * + * Note that with only one concurrent reader and one concurrent + * writer, you don't need extra locking to use these macro. + */ +#define kfifo_peek(fifo, val) \ +__kfifo_must_check_helper( \ +({ \ + typeof(fifo + 1) __tmp = (fifo); \ + typeof(val + 1) __val = (val); \ + unsigned int __ret; \ + const size_t __recsize = sizeof(*__tmp->rectype); \ + struct __kfifo *__kfifo = &__tmp->kfifo; \ + if (0) \ + __val = (typeof(__tmp->ptr))NULL; \ + if (__recsize) \ + __ret = __kfifo_out_peek_r(__kfifo, __val, sizeof(*__val), \ + __recsize); \ + else { \ + __ret = !kfifo_is_empty(__tmp); \ + if (__ret) { \ + *(typeof(__tmp->type))__val = \ + (__is_kfifo_ptr(__tmp) ? \ + ((typeof(__tmp->type))__kfifo->data) : \ + (__tmp->buf) \ + )[__kfifo->out & __tmp->kfifo.mask]; \ + smp_wmb(); \ + } \ + } \ + __ret; \ +}) \ +) + +/** + * kfifo_in - put data into the fifo + * @fifo: address of the fifo to be used + * @buf: the data to be added + * @n: number of elements to be added + * + * This macro copies the given buffer into the fifo and returns the + * number of copied elements. + * + * Note that with only one concurrent reader and one concurrent + * writer, you don't need extra locking to use these macro. + */ +#define kfifo_in(fifo, buf, n) \ +({ \ + typeof(fifo + 1) __tmp = (fifo); \ + typeof(buf + 1) __buf = (buf); \ + unsigned long __n = (n); \ + const size_t __recsize = sizeof(*__tmp->rectype); \ + struct __kfifo *__kfifo = &__tmp->kfifo; \ + if (0) { \ + typeof(__tmp->ptr_const) __dummy __attribute__ ((unused)); \ + __dummy = (typeof(__buf))NULL; \ + } \ + (__recsize) ?\ + __kfifo_in_r(__kfifo, __buf, __n, __recsize) : \ + __kfifo_in(__kfifo, __buf, __n); \ +}) + +/** + * kfifo_in_spinlocked - put data into the fifo using a spinlock for locking + * @fifo: address of the fifo to be used + * @buf: the data to be added + * @n: number of elements to be added + * @lock: pointer to the spinlock to use for locking + * + * This macro copies the given values buffer into the fifo and returns the + * number of copied elements. + */ +#define kfifo_in_spinlocked(fifo, buf, n, lock) \ +({ \ + unsigned long __flags; \ + unsigned int __ret; \ + spin_lock_irqsave(lock, __flags); \ + __ret = kfifo_in(fifo, buf, n); \ + spin_unlock_irqrestore(lock, __flags); \ + __ret; \ +}) + +/* alias for kfifo_in_spinlocked, will be removed in a future release */ +#define kfifo_in_locked(fifo, buf, n, lock) \ + kfifo_in_spinlocked(fifo, buf, n, lock) + +/** + * kfifo_out - get data from the fifo + * @fifo: address of the fifo to be used + * @buf: pointer to the storage buffer + * @n: max. number of elements to get + * + * This macro get some data from the fifo and return the numbers of elements + * copied. + * + * Note that with only one concurrent reader and one concurrent + * writer, you don't need extra locking to use these macro. + */ +#define kfifo_out(fifo, buf, n) \ +__kfifo_must_check_helper( \ +({ \ + typeof(fifo + 1) __tmp = (fifo); \ + typeof(buf + 1) __buf = (buf); \ + unsigned long __n = (n); \ + const size_t __recsize = sizeof(*__tmp->rectype); \ + struct __kfifo *__kfifo = &__tmp->kfifo; \ + if (0) { \ + typeof(__tmp->ptr) __dummy = NULL; \ + __buf = __dummy; \ + } \ + (__recsize) ?\ + __kfifo_out_r(__kfifo, __buf, __n, __recsize) : \ + __kfifo_out(__kfifo, __buf, __n); \ +}) \ +) + +/** + * kfifo_out_spinlocked - get data from the fifo using a spinlock for locking + * @fifo: address of the fifo to be used + * @buf: pointer to the storage buffer + * @n: max. number of elements to get + * @lock: pointer to the spinlock to use for locking + * + * This macro get the data from the fifo and return the numbers of elements + * copied. + */ +#define kfifo_out_spinlocked(fifo, buf, n, lock) \ +__kfifo_must_check_helper( \ +({ \ + unsigned long __flags; \ + unsigned int __ret; \ + spin_lock_irqsave(lock, __flags); \ + __ret = kfifo_out(fifo, buf, n); \ + spin_unlock_irqrestore(lock, __flags); \ + __ret; \ +}) \ +) + +/* alias for kfifo_out_spinlocked, will be removed in a future release */ +#define kfifo_out_locked(fifo, buf, n, lock) \ + kfifo_out_spinlocked(fifo, buf, n, lock) + +/** + * kfifo_from_user - puts some data from user space into the fifo + * @fifo: address of the fifo to be used + * @from: pointer to the data to be added + * @len: the length of the data to be added + * @copied: pointer to output variable to store the number of copied bytes + * + * This macro copies at most @len bytes from the @from into the + * fifo, depending of the available space and returns -EFAULT/0. + * + * Note that with only one concurrent reader and one concurrent + * writer, you don't need extra locking to use these macro. + */ +#define kfifo_from_user(fifo, from, len, copied) \ +__kfifo_must_check_helper( \ +({ \ + typeof(fifo + 1) __tmp = (fifo); \ + const void __user *__from = (from); \ + unsigned int __len = (len); \ + unsigned int *__copied = (copied); \ + const size_t __recsize = sizeof(*__tmp->rectype); \ + struct __kfifo *__kfifo = &__tmp->kfifo; \ + (__recsize) ? \ + __kfifo_from_user_r(__kfifo, __from, __len, __copied, __recsize) : \ + __kfifo_from_user(__kfifo, __from, __len, __copied); \ +}) \ +) + +/** + * kfifo_to_user - copies data from the fifo into user space + * @fifo: address of the fifo to be used + * @to: where the data must be copied + * @len: the size of the destination buffer + * @copied: pointer to output variable to store the number of copied bytes + * + * This macro copies at most @len bytes from the fifo into the + * @to buffer and returns -EFAULT/0. + * + * Note that with only one concurrent reader and one concurrent + * writer, you don't need extra locking to use these macro. + */ +#define kfifo_to_user(fifo, to, len, copied) \ +__kfifo_must_check_helper( \ +({ \ + typeof(fifo + 1) __tmp = (fifo); \ + void __user *__to = (to); \ + unsigned int __len = (len); \ + unsigned int *__copied = (copied); \ + const size_t __recsize = sizeof(*__tmp->rectype); \ + struct __kfifo *__kfifo = &__tmp->kfifo; \ + (__recsize) ? \ + __kfifo_to_user_r(__kfifo, __to, __len, __copied, __recsize) : \ + __kfifo_to_user(__kfifo, __to, __len, __copied); \ +}) \ +) + +/** + * kfifo_dma_in_prepare - setup a scatterlist for DMA input + * @fifo: address of the fifo to be used + * @sgl: pointer to the scatterlist array + * @nents: number of entries in the scatterlist array + * @len: number of elements to transfer + * + * This macro fills a scatterlist for DMA input. + * It returns the number entries in the scatterlist array. + * + * Note that with only one concurrent reader and one concurrent + * writer, you don't need extra locking to use these macros. + */ +#define kfifo_dma_in_prepare(fifo, sgl, nents, len) \ +({ \ + typeof(fifo + 1) __tmp = (fifo); \ + struct scatterlist *__sgl = (sgl); \ + int __nents = (nents); \ + unsigned int __len = (len); \ + const size_t __recsize = sizeof(*__tmp->rectype); \ + struct __kfifo *__kfifo = &__tmp->kfifo; \ + (__recsize) ? \ + __kfifo_dma_in_prepare_r(__kfifo, __sgl, __nents, __len, __recsize) : \ + __kfifo_dma_in_prepare(__kfifo, __sgl, __nents, __len); \ +}) + +/** + * kfifo_dma_in_finish - finish a DMA IN operation + * @fifo: address of the fifo to be used + * @len: number of bytes to received + * + * This macro finish a DMA IN operation. The in counter will be updated by + * the len parameter. No error checking will be done. + * + * Note that with only one concurrent reader and one concurrent + * writer, you don't need extra locking to use these macros. + */ +#define kfifo_dma_in_finish(fifo, len) \ +(void)({ \ + typeof(fifo + 1) __tmp = (fifo); \ + unsigned int __len = (len); \ + const size_t __recsize = sizeof(*__tmp->rectype); \ + struct __kfifo *__kfifo = &__tmp->kfifo; \ + if (__recsize) \ + __kfifo_dma_in_finish_r(__kfifo, __len, __recsize); \ + else \ + __kfifo->in += __len / sizeof(*__tmp->type); \ +}) + +/** + * kfifo_dma_out_prepare - setup a scatterlist for DMA output + * @fifo: address of the fifo to be used + * @sgl: pointer to the scatterlist array + * @nents: number of entries in the scatterlist array + * @len: number of elements to transfer + * + * This macro fills a scatterlist for DMA output which at most @len bytes + * to transfer. + * It returns the number entries in the scatterlist array. + * A zero means there is no space available and the scatterlist is not filled. + * + * Note that with only one concurrent reader and one concurrent + * writer, you don't need extra locking to use these macros. + */ +#define kfifo_dma_out_prepare(fifo, sgl, nents, len) \ +({ \ + typeof(fifo + 1) __tmp = (fifo); \ + struct scatterlist *__sgl = (sgl); \ + int __nents = (nents); \ + unsigned int __len = (len); \ + const size_t __recsize = sizeof(*__tmp->rectype); \ + struct __kfifo *__kfifo = &__tmp->kfifo; \ + (__recsize) ? \ + __kfifo_dma_out_prepare_r(__kfifo, __sgl, __nents, __len, __recsize) : \ + __kfifo_dma_out_prepare(__kfifo, __sgl, __nents, __len); \ +}) + +/** + * kfifo_dma_out_finish - finish a DMA OUT operation + * @fifo: address of the fifo to be used + * @len: number of bytes transferd + * + * This macro finish a DMA OUT operation. The out counter will be updated by + * the len parameter. No error checking will be done. + * + * Note that with only one concurrent reader and one concurrent + * writer, you don't need extra locking to use these macros. + */ +#define kfifo_dma_out_finish(fifo, len) \ +(void)({ \ + typeof(fifo + 1) __tmp = (fifo); \ + unsigned int __len = (len); \ + const size_t __recsize = sizeof(*__tmp->rectype); \ + struct __kfifo *__kfifo = &__tmp->kfifo; \ + if (__recsize) \ + __kfifo_dma_out_finish_r(__kfifo, __recsize); \ + else \ + __kfifo->out += __len / sizeof(*__tmp->type); \ +}) + +/** + * kfifo_out_peek - gets some data from the fifo + * @fifo: address of the fifo to be used + * @buf: pointer to the storage buffer + * @n: max. number of elements to get + * + * This macro get the data from the fifo and return the numbers of elements + * copied. The data is not removed from the fifo. + * + * Note that with only one concurrent reader and one concurrent + * writer, you don't need extra locking to use these macro. + */ +#define kfifo_out_peek(fifo, buf, n) \ +__kfifo_must_check_helper( \ +({ \ + typeof(fifo + 1) __tmp = (fifo); \ + typeof(buf + 1) __buf = (buf); \ + unsigned long __n = (n); \ + const size_t __recsize = sizeof(*__tmp->rectype); \ + struct __kfifo *__kfifo = &__tmp->kfifo; \ + if (0) { \ + typeof(__tmp->ptr) __dummy __attribute__ ((unused)) = NULL; \ + __buf = __dummy; \ + } \ + (__recsize) ? \ + __kfifo_out_peek_r(__kfifo, __buf, __n, __recsize) : \ + __kfifo_out_peek(__kfifo, __buf, __n); \ +}) \ +) + +extern int __kfifo_alloc(struct __kfifo *fifo, unsigned int size, + size_t esize, gfp_t gfp_mask); + +extern void __kfifo_free(struct __kfifo *fifo); + +extern int __kfifo_init(struct __kfifo *fifo, void *buffer, + unsigned int size, size_t esize); + +extern unsigned int __kfifo_in(struct __kfifo *fifo, + const void *buf, unsigned int len); + +extern unsigned int __kfifo_out(struct __kfifo *fifo, + void *buf, unsigned int len); + +extern int __kfifo_from_user(struct __kfifo *fifo, + const void __user *from, unsigned long len, unsigned int *copied); + +extern int __kfifo_to_user(struct __kfifo *fifo, + void __user *to, unsigned long len, unsigned int *copied); + +extern unsigned int __kfifo_dma_in_prepare(struct __kfifo *fifo, + struct scatterlist *sgl, int nents, unsigned int len); + +extern unsigned int __kfifo_dma_out_prepare(struct __kfifo *fifo, + struct scatterlist *sgl, int nents, unsigned int len); + +extern unsigned int __kfifo_out_peek(struct __kfifo *fifo, + void *buf, unsigned int len); + +extern unsigned int __kfifo_in_r(struct __kfifo *fifo, + const void *buf, unsigned int len, size_t recsize); + +extern unsigned int __kfifo_out_r(struct __kfifo *fifo, + void *buf, unsigned int len, size_t recsize); + +extern int __kfifo_from_user_r(struct __kfifo *fifo, + const void __user *from, unsigned long len, unsigned int *copied, + size_t recsize); + +extern int __kfifo_to_user_r(struct __kfifo *fifo, void __user *to, + unsigned long len, unsigned int *copied, size_t recsize); + +extern unsigned int __kfifo_dma_in_prepare_r(struct __kfifo *fifo, + struct scatterlist *sgl, int nents, unsigned int len, size_t recsize); + +extern void __kfifo_dma_in_finish_r(struct __kfifo *fifo, + unsigned int len, size_t recsize); + +extern unsigned int __kfifo_dma_out_prepare_r(struct __kfifo *fifo, + struct scatterlist *sgl, int nents, unsigned int len, size_t recsize); + +extern void __kfifo_dma_out_finish_r(struct __kfifo *fifo, size_t recsize); + +extern unsigned int __kfifo_len_r(struct __kfifo *fifo, size_t recsize); + +extern unsigned int __kfifo_out_peek_r(struct __kfifo *fifo, + void *buf, unsigned int len, size_t recsize); + +extern unsigned int __kfifo_max_r(unsigned int len, size_t recsize); + +#endif -- cgit v1.2.3 From 2e956fb320568cc70861761483e2f0e2db75fd66 Mon Sep 17 00:00:00 2001 From: Stefani Seibold Date: Tue, 10 Aug 2010 18:03:38 -0700 Subject: kfifo: replace the old non generic API Simply replace the whole kfifo.c and kfifo.h files with the new generic version and fix the kerneldoc API template file. Signed-off-by: Stefani Seibold Cc: Greg KH Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kfifo-new.h | 844 -------------------------------- include/linux/kfifo.h | 1193 +++++++++++++++++++++++++++------------------ 2 files changed, 711 insertions(+), 1326 deletions(-) delete mode 100644 include/linux/kfifo-new.h (limited to 'include/linux') diff --git a/include/linux/kfifo-new.h b/include/linux/kfifo-new.h deleted file mode 100644 index 311f8753d713..000000000000 --- a/include/linux/kfifo-new.h +++ /dev/null @@ -1,844 +0,0 @@ -/* - * A generic kernel FIFO implementation - * - * Copyright (C) 2009/2010 Stefani Seibold - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. - * - */ - -#ifndef _LINUX_KFIFO_H -#define _LINUX_KFIFO_H - -/* - * How to porting drivers to the new generic FIFO API: - * - * - Modify the declaration of the "struct kfifo *" object into a - * in-place "struct kfifo" object - * - Init the in-place object with kfifo_alloc() or kfifo_init() - * Note: The address of the in-place "struct kfifo" object must be - * passed as the first argument to this functions - * - Replace the use of __kfifo_put into kfifo_in and __kfifo_get - * into kfifo_out - * - Replace the use of kfifo_put into kfifo_in_spinlocked and kfifo_get - * into kfifo_out_spinlocked - * Note: the spinlock pointer formerly passed to kfifo_init/kfifo_alloc - * must be passed now to the kfifo_in_spinlocked and kfifo_out_spinlocked - * as the last parameter - * - The formerly __kfifo_* functions are renamed into kfifo_* - */ - -/* - * Note about locking : There is no locking required until only * one reader - * and one writer is using the fifo and no kfifo_reset() will be * called - * kfifo_reset_out() can be safely used, until it will be only called - * in the reader thread. - * For multiple writer and one reader there is only a need to lock the writer. - * And vice versa for only one writer and multiple reader there is only a need - * to lock the reader. - */ - -#include -#include -#include -#include - -struct __kfifo { - unsigned int in; - unsigned int out; - unsigned int mask; - unsigned int esize; - void *data; -}; - -#define __STRUCT_KFIFO_COMMON(datatype, recsize, ptrtype) \ - union { \ - struct __kfifo kfifo; \ - datatype *type; \ - char (*rectype)[recsize]; \ - ptrtype *ptr; \ - const ptrtype *ptr_const; \ - } - -#define __STRUCT_KFIFO(type, size, recsize, ptrtype) \ -{ \ - __STRUCT_KFIFO_COMMON(type, recsize, ptrtype); \ - type buf[((size < 2) || (size & (size - 1))) ? -1 : size]; \ -} - -#define STRUCT_KFIFO(type, size) \ - struct __STRUCT_KFIFO(type, size, 0, type) - -#define __STRUCT_KFIFO_PTR(type, recsize, ptrtype) \ -{ \ - __STRUCT_KFIFO_COMMON(type, recsize, ptrtype); \ - type buf[0]; \ -} - -#define STRUCT_KFIFO_PTR(type) \ - struct __STRUCT_KFIFO_PTR(type, 0, type) - -/* - * define compatibility "struct kfifo" for dynamic allocated fifos - */ -struct kfifo __STRUCT_KFIFO_PTR(unsigned char, 0, void); - -#define STRUCT_KFIFO_REC_1(size) \ - struct __STRUCT_KFIFO(unsigned char, size, 1, void) - -#define STRUCT_KFIFO_REC_2(size) \ - struct __STRUCT_KFIFO(unsigned char, size, 2, void) - -/* - * define kfifo_rec types - */ -struct kfifo_rec_ptr_1 __STRUCT_KFIFO_PTR(unsigned char, 1, void); -struct kfifo_rec_ptr_2 __STRUCT_KFIFO_PTR(unsigned char, 2, void); - -/* - * helper macro to distinguish between real in place fifo where the fifo - * array is a part of the structure and the fifo type where the array is - * outside of the fifo structure. - */ -#define __is_kfifo_ptr(fifo) (sizeof(*fifo) == sizeof(struct __kfifo)) - -/** - * DECLARE_KFIFO_PTR - macro to declare a fifo pointer object - * @fifo: name of the declared fifo - * @type: type of the fifo elements - */ -#define DECLARE_KFIFO_PTR(fifo, type) STRUCT_KFIFO_PTR(type) fifo - -/** - * DECLARE_KFIFO - macro to declare a fifo object - * @fifo: name of the declared fifo - * @type: type of the fifo elements - * @size: the number of elements in the fifo, this must be a power of 2 - */ -#define DECLARE_KFIFO(fifo, type, size) STRUCT_KFIFO(type, size) fifo - -/** - * INIT_KFIFO - Initialize a fifo declared by DECLARE_KFIFO - * @fifo: name of the declared fifo datatype - */ -#define INIT_KFIFO(fifo) \ -(void)({ \ - typeof(&(fifo)) __tmp = &(fifo); \ - struct __kfifo *__kfifo = &__tmp->kfifo; \ - __kfifo->in = 0; \ - __kfifo->out = 0; \ - __kfifo->mask = __is_kfifo_ptr(__tmp) ? 0 : ARRAY_SIZE(__tmp->buf) - 1;\ - __kfifo->esize = sizeof(*__tmp->buf); \ - __kfifo->data = __is_kfifo_ptr(__tmp) ? NULL : __tmp->buf; \ -}) - -/** - * DEFINE_KFIFO - macro to define and initialize a fifo - * @fifo: name of the declared fifo datatype - * @type: type of the fifo elements - * @size: the number of elements in the fifo, this must be a power of 2 - * - * Note: the macro can be used for global and local fifo data type variables. - */ -#define DEFINE_KFIFO(fifo, type, size) \ - DECLARE_KFIFO(fifo, type, size) = \ - (typeof(fifo)) { \ - { \ - { \ - .in = 0, \ - .out = 0, \ - .mask = __is_kfifo_ptr(&(fifo)) ? \ - 0 : \ - ARRAY_SIZE((fifo).buf) - 1, \ - .esize = sizeof(*(fifo).buf), \ - .data = __is_kfifo_ptr(&(fifo)) ? \ - NULL : \ - (fifo).buf, \ - } \ - } \ - } - - -static inline unsigned int __must_check -__kfifo_must_check_helper(unsigned int val) -{ - return val; -} - -/** - * kfifo_initialized - Check if the fifo is initialized - * @fifo: address of the fifo to check - * - * Return %true if fifo is initialized, otherwise %false. - * Assumes the fifo was 0 before. - */ -#define kfifo_initialized(fifo) ((fifo)->kfifo.mask) - -/** - * kfifo_esize - returns the size of the element managed by the fifo - * @fifo: address of the fifo to be used - */ -#define kfifo_esize(fifo) ((fifo)->kfifo.esize) - -/** - * kfifo_recsize - returns the size of the record length field - * @fifo: address of the fifo to be used - */ -#define kfifo_recsize(fifo) (sizeof(*(fifo)->rectype)) - -/** - * kfifo_size - returns the size of the fifo in elements - * @fifo: address of the fifo to be used - */ -#define kfifo_size(fifo) ((fifo)->kfifo.mask + 1) - -/** - * kfifo_reset - removes the entire fifo content - * @fifo: address of the fifo to be used - * - * Note: usage of kfifo_reset() is dangerous. It should be only called when the - * fifo is exclusived locked or when it is secured that no other thread is - * accessing the fifo. - */ -#define kfifo_reset(fifo) \ -(void)({ \ - typeof(fifo + 1) __tmp = (fifo); \ - __tmp->kfifo.in = __tmp->kfifo.out = 0; \ -}) - -/** - * kfifo_reset_out - skip fifo content - * @fifo: address of the fifo to be used - * - * Note: The usage of kfifo_reset_out() is safe until it will be only called - * from the reader thread and there is only one concurrent reader. Otherwise - * it is dangerous and must be handled in the same way as kfifo_reset(). - */ -#define kfifo_reset_out(fifo) \ -(void)({ \ - typeof(fifo + 1) __tmp = (fifo); \ - __tmp->kfifo.out = __tmp->kfifo.in; \ -}) - -/** - * kfifo_len - returns the number of used elements in the fifo - * @fifo: address of the fifo to be used - */ -#define kfifo_len(fifo) \ -({ \ - typeof(fifo + 1) __tmpl = (fifo); \ - __tmpl->kfifo.in - __tmpl->kfifo.out; \ -}) - -/** - * kfifo_is_empty - returns true if the fifo is empty - * @fifo: address of the fifo to be used - */ -#define kfifo_is_empty(fifo) \ -({ \ - typeof(fifo + 1) __tmpq = (fifo); \ - __tmpq->kfifo.in == __tmpq->kfifo.out; \ -}) - -/** - * kfifo_is_full - returns true if the fifo is full - * @fifo: address of the fifo to be used - */ -#define kfifo_is_full(fifo) \ -({ \ - typeof(fifo + 1) __tmpq = (fifo); \ - kfifo_len(__tmpq) > __tmpq->kfifo.mask; \ -}) - -/** - * kfifo_avail - returns the number of unused elements in the fifo - * @fifo: address of the fifo to be used - */ -#define kfifo_avail(fifo) \ -__kfifo_must_check_helper( \ -({ \ - typeof(fifo + 1) __tmpq = (fifo); \ - const size_t __recsize = sizeof(*__tmpq->rectype); \ - unsigned int __avail = kfifo_size(__tmpq) - kfifo_len(__tmpq); \ - (__recsize) ? ((__avail <= __recsize) ? 0 : \ - __kfifo_max_r(__avail - __recsize, __recsize)) : \ - __avail; \ -}) \ -) - -/** - * kfifo_skip - skip output data - * @fifo: address of the fifo to be used - */ -#define kfifo_skip(fifo) \ -(void)({ \ - typeof(fifo + 1) __tmp = (fifo); \ - const size_t __recsize = sizeof(*__tmp->rectype); \ - struct __kfifo *__kfifo = &__tmp->kfifo; \ - if (__recsize) \ - __kfifo_skip_r(__kfifo, __recsize); \ - else \ - __kfifo->out++; \ -}) - -/** - * kfifo_peek_len - gets the size of the next fifo record - * @fifo: address of the fifo to be used - * - * This function returns the size of the next fifo record in number of bytes. - */ -#define kfifo_peek_len(fifo) \ -__kfifo_must_check_helper( \ -({ \ - typeof(fifo + 1) __tmp = (fifo); \ - const size_t __recsize = sizeof(*__tmp->rectype); \ - struct __kfifo *__kfifo = &__tmp->kfifo; \ - (!__recsize) ? kfifo_len(__tmp) * sizeof(*__tmp->type) : \ - __kfifo_len_r(__kfifo, __recsize); \ -}) \ -) - -/** - * kfifo_alloc - dynamically allocates a new fifo buffer - * @fifo: pointer to the fifo - * @size: the number of elements in the fifo, this must be a power of 2 - * @gfp_mask: get_free_pages mask, passed to kmalloc() - * - * This macro dynamically allocates a new fifo buffer. - * - * The numer of elements will be rounded-up to a power of 2. - * The fifo will be release with kfifo_free(). - * Return 0 if no error, otherwise an error code. - */ -#define kfifo_alloc(fifo, size, gfp_mask) \ -__kfifo_must_check_helper( \ -({ \ - typeof(fifo + 1) __tmp = (fifo); \ - struct __kfifo *__kfifo = &__tmp->kfifo; \ - __is_kfifo_ptr(__tmp) ? \ - __kfifo_alloc(__kfifo, size, sizeof(*__tmp->type), gfp_mask) : \ - -EINVAL; \ -}) \ -) - -/** - * kfifo_free - frees the fifo - * @fifo: the fifo to be freed - */ -#define kfifo_free(fifo) \ -({ \ - typeof(fifo + 1) __tmp = (fifo); \ - struct __kfifo *__kfifo = &__tmp->kfifo; \ - if (__is_kfifo_ptr(__tmp)) \ - __kfifo_free(__kfifo); \ -}) - -/** - * kfifo_init - initialize a fifo using a preallocated buffer - * @fifo: the fifo to assign the buffer - * @buffer: the preallocated buffer to be used - * @size: the size of the internal buffer, this have to be a power of 2 - * - * This macro initialize a fifo using a preallocated buffer. - * - * The numer of elements will be rounded-up to a power of 2. - * Return 0 if no error, otherwise an error code. - */ -#define kfifo_init(fifo, buffer, size) \ -({ \ - typeof(fifo + 1) __tmp = (fifo); \ - struct __kfifo *__kfifo = &__tmp->kfifo; \ - __is_kfifo_ptr(__tmp) ? \ - __kfifo_init(__kfifo, buffer, size, sizeof(*__tmp->type)) : \ - -EINVAL; \ -}) - -/** - * kfifo_put - put data into the fifo - * @fifo: address of the fifo to be used - * @val: the data to be added - * - * This macro copies the given value into the fifo. - * It returns 0 if the fifo was full. Otherwise it returns the number - * processed elements. - * - * Note that with only one concurrent reader and one concurrent - * writer, you don't need extra locking to use these macro. - */ -#define kfifo_put(fifo, val) \ -({ \ - typeof(fifo + 1) __tmp = (fifo); \ - typeof(val + 1) __val = (val); \ - unsigned int __ret; \ - const size_t __recsize = sizeof(*__tmp->rectype); \ - struct __kfifo *__kfifo = &__tmp->kfifo; \ - if (0) { \ - typeof(__tmp->ptr_const) __dummy __attribute__ ((unused)); \ - __dummy = (typeof(__val))NULL; \ - } \ - if (__recsize) \ - __ret = __kfifo_in_r(__kfifo, __val, sizeof(*__val), \ - __recsize); \ - else { \ - __ret = !kfifo_is_full(__tmp); \ - if (__ret) { \ - (__is_kfifo_ptr(__tmp) ? \ - ((typeof(__tmp->type))__kfifo->data) : \ - (__tmp->buf) \ - )[__kfifo->in & __tmp->kfifo.mask] = \ - *(typeof(__tmp->type))__val; \ - smp_wmb(); \ - __kfifo->in++; \ - } \ - } \ - __ret; \ -}) - -/** - * kfifo_get - get data from the fifo - * @fifo: address of the fifo to be used - * @val: the var where to store the data to be added - * - * This macro reads the data from the fifo. - * It returns 0 if the fifo was empty. Otherwise it returns the number - * processed elements. - * - * Note that with only one concurrent reader and one concurrent - * writer, you don't need extra locking to use these macro. - */ -#define kfifo_get(fifo, val) \ -__kfifo_must_check_helper( \ -({ \ - typeof(fifo + 1) __tmp = (fifo); \ - typeof(val + 1) __val = (val); \ - unsigned int __ret; \ - const size_t __recsize = sizeof(*__tmp->rectype); \ - struct __kfifo *__kfifo = &__tmp->kfifo; \ - if (0) \ - __val = (typeof(__tmp->ptr))0; \ - if (__recsize) \ - __ret = __kfifo_out_r(__kfifo, __val, sizeof(*__val), \ - __recsize); \ - else { \ - __ret = !kfifo_is_empty(__tmp); \ - if (__ret) { \ - *(typeof(__tmp->type))__val = \ - (__is_kfifo_ptr(__tmp) ? \ - ((typeof(__tmp->type))__kfifo->data) : \ - (__tmp->buf) \ - )[__kfifo->out & __tmp->kfifo.mask]; \ - smp_wmb(); \ - __kfifo->out++; \ - } \ - } \ - __ret; \ -}) \ -) - -/** - * kfifo_peek - get data from the fifo without removing - * @fifo: address of the fifo to be used - * @val: the var where to store the data to be added - * - * This reads the data from the fifo without removing it from the fifo. - * It returns 0 if the fifo was empty. Otherwise it returns the number - * processed elements. - * - * Note that with only one concurrent reader and one concurrent - * writer, you don't need extra locking to use these macro. - */ -#define kfifo_peek(fifo, val) \ -__kfifo_must_check_helper( \ -({ \ - typeof(fifo + 1) __tmp = (fifo); \ - typeof(val + 1) __val = (val); \ - unsigned int __ret; \ - const size_t __recsize = sizeof(*__tmp->rectype); \ - struct __kfifo *__kfifo = &__tmp->kfifo; \ - if (0) \ - __val = (typeof(__tmp->ptr))NULL; \ - if (__recsize) \ - __ret = __kfifo_out_peek_r(__kfifo, __val, sizeof(*__val), \ - __recsize); \ - else { \ - __ret = !kfifo_is_empty(__tmp); \ - if (__ret) { \ - *(typeof(__tmp->type))__val = \ - (__is_kfifo_ptr(__tmp) ? \ - ((typeof(__tmp->type))__kfifo->data) : \ - (__tmp->buf) \ - )[__kfifo->out & __tmp->kfifo.mask]; \ - smp_wmb(); \ - } \ - } \ - __ret; \ -}) \ -) - -/** - * kfifo_in - put data into the fifo - * @fifo: address of the fifo to be used - * @buf: the data to be added - * @n: number of elements to be added - * - * This macro copies the given buffer into the fifo and returns the - * number of copied elements. - * - * Note that with only one concurrent reader and one concurrent - * writer, you don't need extra locking to use these macro. - */ -#define kfifo_in(fifo, buf, n) \ -({ \ - typeof(fifo + 1) __tmp = (fifo); \ - typeof(buf + 1) __buf = (buf); \ - unsigned long __n = (n); \ - const size_t __recsize = sizeof(*__tmp->rectype); \ - struct __kfifo *__kfifo = &__tmp->kfifo; \ - if (0) { \ - typeof(__tmp->ptr_const) __dummy __attribute__ ((unused)); \ - __dummy = (typeof(__buf))NULL; \ - } \ - (__recsize) ?\ - __kfifo_in_r(__kfifo, __buf, __n, __recsize) : \ - __kfifo_in(__kfifo, __buf, __n); \ -}) - -/** - * kfifo_in_spinlocked - put data into the fifo using a spinlock for locking - * @fifo: address of the fifo to be used - * @buf: the data to be added - * @n: number of elements to be added - * @lock: pointer to the spinlock to use for locking - * - * This macro copies the given values buffer into the fifo and returns the - * number of copied elements. - */ -#define kfifo_in_spinlocked(fifo, buf, n, lock) \ -({ \ - unsigned long __flags; \ - unsigned int __ret; \ - spin_lock_irqsave(lock, __flags); \ - __ret = kfifo_in(fifo, buf, n); \ - spin_unlock_irqrestore(lock, __flags); \ - __ret; \ -}) - -/* alias for kfifo_in_spinlocked, will be removed in a future release */ -#define kfifo_in_locked(fifo, buf, n, lock) \ - kfifo_in_spinlocked(fifo, buf, n, lock) - -/** - * kfifo_out - get data from the fifo - * @fifo: address of the fifo to be used - * @buf: pointer to the storage buffer - * @n: max. number of elements to get - * - * This macro get some data from the fifo and return the numbers of elements - * copied. - * - * Note that with only one concurrent reader and one concurrent - * writer, you don't need extra locking to use these macro. - */ -#define kfifo_out(fifo, buf, n) \ -__kfifo_must_check_helper( \ -({ \ - typeof(fifo + 1) __tmp = (fifo); \ - typeof(buf + 1) __buf = (buf); \ - unsigned long __n = (n); \ - const size_t __recsize = sizeof(*__tmp->rectype); \ - struct __kfifo *__kfifo = &__tmp->kfifo; \ - if (0) { \ - typeof(__tmp->ptr) __dummy = NULL; \ - __buf = __dummy; \ - } \ - (__recsize) ?\ - __kfifo_out_r(__kfifo, __buf, __n, __recsize) : \ - __kfifo_out(__kfifo, __buf, __n); \ -}) \ -) - -/** - * kfifo_out_spinlocked - get data from the fifo using a spinlock for locking - * @fifo: address of the fifo to be used - * @buf: pointer to the storage buffer - * @n: max. number of elements to get - * @lock: pointer to the spinlock to use for locking - * - * This macro get the data from the fifo and return the numbers of elements - * copied. - */ -#define kfifo_out_spinlocked(fifo, buf, n, lock) \ -__kfifo_must_check_helper( \ -({ \ - unsigned long __flags; \ - unsigned int __ret; \ - spin_lock_irqsave(lock, __flags); \ - __ret = kfifo_out(fifo, buf, n); \ - spin_unlock_irqrestore(lock, __flags); \ - __ret; \ -}) \ -) - -/* alias for kfifo_out_spinlocked, will be removed in a future release */ -#define kfifo_out_locked(fifo, buf, n, lock) \ - kfifo_out_spinlocked(fifo, buf, n, lock) - -/** - * kfifo_from_user - puts some data from user space into the fifo - * @fifo: address of the fifo to be used - * @from: pointer to the data to be added - * @len: the length of the data to be added - * @copied: pointer to output variable to store the number of copied bytes - * - * This macro copies at most @len bytes from the @from into the - * fifo, depending of the available space and returns -EFAULT/0. - * - * Note that with only one concurrent reader and one concurrent - * writer, you don't need extra locking to use these macro. - */ -#define kfifo_from_user(fifo, from, len, copied) \ -__kfifo_must_check_helper( \ -({ \ - typeof(fifo + 1) __tmp = (fifo); \ - const void __user *__from = (from); \ - unsigned int __len = (len); \ - unsigned int *__copied = (copied); \ - const size_t __recsize = sizeof(*__tmp->rectype); \ - struct __kfifo *__kfifo = &__tmp->kfifo; \ - (__recsize) ? \ - __kfifo_from_user_r(__kfifo, __from, __len, __copied, __recsize) : \ - __kfifo_from_user(__kfifo, __from, __len, __copied); \ -}) \ -) - -/** - * kfifo_to_user - copies data from the fifo into user space - * @fifo: address of the fifo to be used - * @to: where the data must be copied - * @len: the size of the destination buffer - * @copied: pointer to output variable to store the number of copied bytes - * - * This macro copies at most @len bytes from the fifo into the - * @to buffer and returns -EFAULT/0. - * - * Note that with only one concurrent reader and one concurrent - * writer, you don't need extra locking to use these macro. - */ -#define kfifo_to_user(fifo, to, len, copied) \ -__kfifo_must_check_helper( \ -({ \ - typeof(fifo + 1) __tmp = (fifo); \ - void __user *__to = (to); \ - unsigned int __len = (len); \ - unsigned int *__copied = (copied); \ - const size_t __recsize = sizeof(*__tmp->rectype); \ - struct __kfifo *__kfifo = &__tmp->kfifo; \ - (__recsize) ? \ - __kfifo_to_user_r(__kfifo, __to, __len, __copied, __recsize) : \ - __kfifo_to_user(__kfifo, __to, __len, __copied); \ -}) \ -) - -/** - * kfifo_dma_in_prepare - setup a scatterlist for DMA input - * @fifo: address of the fifo to be used - * @sgl: pointer to the scatterlist array - * @nents: number of entries in the scatterlist array - * @len: number of elements to transfer - * - * This macro fills a scatterlist for DMA input. - * It returns the number entries in the scatterlist array. - * - * Note that with only one concurrent reader and one concurrent - * writer, you don't need extra locking to use these macros. - */ -#define kfifo_dma_in_prepare(fifo, sgl, nents, len) \ -({ \ - typeof(fifo + 1) __tmp = (fifo); \ - struct scatterlist *__sgl = (sgl); \ - int __nents = (nents); \ - unsigned int __len = (len); \ - const size_t __recsize = sizeof(*__tmp->rectype); \ - struct __kfifo *__kfifo = &__tmp->kfifo; \ - (__recsize) ? \ - __kfifo_dma_in_prepare_r(__kfifo, __sgl, __nents, __len, __recsize) : \ - __kfifo_dma_in_prepare(__kfifo, __sgl, __nents, __len); \ -}) - -/** - * kfifo_dma_in_finish - finish a DMA IN operation - * @fifo: address of the fifo to be used - * @len: number of bytes to received - * - * This macro finish a DMA IN operation. The in counter will be updated by - * the len parameter. No error checking will be done. - * - * Note that with only one concurrent reader and one concurrent - * writer, you don't need extra locking to use these macros. - */ -#define kfifo_dma_in_finish(fifo, len) \ -(void)({ \ - typeof(fifo + 1) __tmp = (fifo); \ - unsigned int __len = (len); \ - const size_t __recsize = sizeof(*__tmp->rectype); \ - struct __kfifo *__kfifo = &__tmp->kfifo; \ - if (__recsize) \ - __kfifo_dma_in_finish_r(__kfifo, __len, __recsize); \ - else \ - __kfifo->in += __len / sizeof(*__tmp->type); \ -}) - -/** - * kfifo_dma_out_prepare - setup a scatterlist for DMA output - * @fifo: address of the fifo to be used - * @sgl: pointer to the scatterlist array - * @nents: number of entries in the scatterlist array - * @len: number of elements to transfer - * - * This macro fills a scatterlist for DMA output which at most @len bytes - * to transfer. - * It returns the number entries in the scatterlist array. - * A zero means there is no space available and the scatterlist is not filled. - * - * Note that with only one concurrent reader and one concurrent - * writer, you don't need extra locking to use these macros. - */ -#define kfifo_dma_out_prepare(fifo, sgl, nents, len) \ -({ \ - typeof(fifo + 1) __tmp = (fifo); \ - struct scatterlist *__sgl = (sgl); \ - int __nents = (nents); \ - unsigned int __len = (len); \ - const size_t __recsize = sizeof(*__tmp->rectype); \ - struct __kfifo *__kfifo = &__tmp->kfifo; \ - (__recsize) ? \ - __kfifo_dma_out_prepare_r(__kfifo, __sgl, __nents, __len, __recsize) : \ - __kfifo_dma_out_prepare(__kfifo, __sgl, __nents, __len); \ -}) - -/** - * kfifo_dma_out_finish - finish a DMA OUT operation - * @fifo: address of the fifo to be used - * @len: number of bytes transferd - * - * This macro finish a DMA OUT operation. The out counter will be updated by - * the len parameter. No error checking will be done. - * - * Note that with only one concurrent reader and one concurrent - * writer, you don't need extra locking to use these macros. - */ -#define kfifo_dma_out_finish(fifo, len) \ -(void)({ \ - typeof(fifo + 1) __tmp = (fifo); \ - unsigned int __len = (len); \ - const size_t __recsize = sizeof(*__tmp->rectype); \ - struct __kfifo *__kfifo = &__tmp->kfifo; \ - if (__recsize) \ - __kfifo_dma_out_finish_r(__kfifo, __recsize); \ - else \ - __kfifo->out += __len / sizeof(*__tmp->type); \ -}) - -/** - * kfifo_out_peek - gets some data from the fifo - * @fifo: address of the fifo to be used - * @buf: pointer to the storage buffer - * @n: max. number of elements to get - * - * This macro get the data from the fifo and return the numbers of elements - * copied. The data is not removed from the fifo. - * - * Note that with only one concurrent reader and one concurrent - * writer, you don't need extra locking to use these macro. - */ -#define kfifo_out_peek(fifo, buf, n) \ -__kfifo_must_check_helper( \ -({ \ - typeof(fifo + 1) __tmp = (fifo); \ - typeof(buf + 1) __buf = (buf); \ - unsigned long __n = (n); \ - const size_t __recsize = sizeof(*__tmp->rectype); \ - struct __kfifo *__kfifo = &__tmp->kfifo; \ - if (0) { \ - typeof(__tmp->ptr) __dummy __attribute__ ((unused)) = NULL; \ - __buf = __dummy; \ - } \ - (__recsize) ? \ - __kfifo_out_peek_r(__kfifo, __buf, __n, __recsize) : \ - __kfifo_out_peek(__kfifo, __buf, __n); \ -}) \ -) - -extern int __kfifo_alloc(struct __kfifo *fifo, unsigned int size, - size_t esize, gfp_t gfp_mask); - -extern void __kfifo_free(struct __kfifo *fifo); - -extern int __kfifo_init(struct __kfifo *fifo, void *buffer, - unsigned int size, size_t esize); - -extern unsigned int __kfifo_in(struct __kfifo *fifo, - const void *buf, unsigned int len); - -extern unsigned int __kfifo_out(struct __kfifo *fifo, - void *buf, unsigned int len); - -extern int __kfifo_from_user(struct __kfifo *fifo, - const void __user *from, unsigned long len, unsigned int *copied); - -extern int __kfifo_to_user(struct __kfifo *fifo, - void __user *to, unsigned long len, unsigned int *copied); - -extern unsigned int __kfifo_dma_in_prepare(struct __kfifo *fifo, - struct scatterlist *sgl, int nents, unsigned int len); - -extern unsigned int __kfifo_dma_out_prepare(struct __kfifo *fifo, - struct scatterlist *sgl, int nents, unsigned int len); - -extern unsigned int __kfifo_out_peek(struct __kfifo *fifo, - void *buf, unsigned int len); - -extern unsigned int __kfifo_in_r(struct __kfifo *fifo, - const void *buf, unsigned int len, size_t recsize); - -extern unsigned int __kfifo_out_r(struct __kfifo *fifo, - void *buf, unsigned int len, size_t recsize); - -extern int __kfifo_from_user_r(struct __kfifo *fifo, - const void __user *from, unsigned long len, unsigned int *copied, - size_t recsize); - -extern int __kfifo_to_user_r(struct __kfifo *fifo, void __user *to, - unsigned long len, unsigned int *copied, size_t recsize); - -extern unsigned int __kfifo_dma_in_prepare_r(struct __kfifo *fifo, - struct scatterlist *sgl, int nents, unsigned int len, size_t recsize); - -extern void __kfifo_dma_in_finish_r(struct __kfifo *fifo, - unsigned int len, size_t recsize); - -extern unsigned int __kfifo_dma_out_prepare_r(struct __kfifo *fifo, - struct scatterlist *sgl, int nents, unsigned int len, size_t recsize); - -extern void __kfifo_dma_out_finish_r(struct __kfifo *fifo, size_t recsize); - -extern unsigned int __kfifo_len_r(struct __kfifo *fifo, size_t recsize); - -extern unsigned int __kfifo_out_peek_r(struct __kfifo *fifo, - void *buf, unsigned int len, size_t recsize); - -extern unsigned int __kfifo_max_r(unsigned int len, size_t recsize); - -#endif diff --git a/include/linux/kfifo.h b/include/linux/kfifo.h index 57c4eedf4dd6..311f8753d713 100644 --- a/include/linux/kfifo.h +++ b/include/linux/kfifo.h @@ -1,8 +1,7 @@ /* - * A generic kernel FIFO implementation. + * A generic kernel FIFO implementation * - * Copyright (C) 2009 Stefani Seibold - * Copyright (C) 2004 Stelian Pop + * Copyright (C) 2009/2010 Stefani Seibold * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -20,8 +19,11 @@ * */ +#ifndef _LINUX_KFIFO_H +#define _LINUX_KFIFO_H + /* - * Howto porting drivers to the new generic fifo API: + * How to porting drivers to the new generic FIFO API: * * - Modify the declaration of the "struct kfifo *" object into a * in-place "struct kfifo" object @@ -30,586 +32,813 @@ * passed as the first argument to this functions * - Replace the use of __kfifo_put into kfifo_in and __kfifo_get * into kfifo_out - * - Replace the use of kfifo_put into kfifo_in_locked and kfifo_get - * into kfifo_out_locked + * - Replace the use of kfifo_put into kfifo_in_spinlocked and kfifo_get + * into kfifo_out_spinlocked * Note: the spinlock pointer formerly passed to kfifo_init/kfifo_alloc - * must be passed now to the kfifo_in_locked and kfifo_out_locked - * as the last parameter. - * - All formerly name __kfifo_* functions has been renamed into kfifo_* + * must be passed now to the kfifo_in_spinlocked and kfifo_out_spinlocked + * as the last parameter + * - The formerly __kfifo_* functions are renamed into kfifo_* */ -#ifndef _LINUX_KFIFO_H -#define _LINUX_KFIFO_H +/* + * Note about locking : There is no locking required until only * one reader + * and one writer is using the fifo and no kfifo_reset() will be * called + * kfifo_reset_out() can be safely used, until it will be only called + * in the reader thread. + * For multiple writer and one reader there is only a need to lock the writer. + * And vice versa for only one writer and multiple reader there is only a need + * to lock the reader. + */ #include #include - -struct kfifo { - unsigned char *buffer; /* the buffer holding the data */ - unsigned int size; /* the size of the allocated buffer */ - unsigned int in; /* data is added at offset (in % size) */ - unsigned int out; /* data is extracted from off. (out % size) */ +#include +#include + +struct __kfifo { + unsigned int in; + unsigned int out; + unsigned int mask; + unsigned int esize; + void *data; }; -/* - * Macros for declaration and initialization of the kfifo datatype - */ - -/* helper macro */ -#define __kfifo_initializer(s, b) \ - (struct kfifo) { \ - .size = s, \ - .in = 0, \ - .out = 0, \ - .buffer = b \ +#define __STRUCT_KFIFO_COMMON(datatype, recsize, ptrtype) \ + union { \ + struct __kfifo kfifo; \ + datatype *type; \ + char (*rectype)[recsize]; \ + ptrtype *ptr; \ + const ptrtype *ptr_const; \ } -/** - * DECLARE_KFIFO - macro to declare a kfifo and the associated buffer - * @name: name of the declared kfifo datatype - * @size: size of the fifo buffer. Must be a power of two. - * - * Note1: the macro can be used inside struct or union declaration - * Note2: the macro creates two objects: - * A kfifo object with the given name and a buffer for the kfifo - * object named name##kfifo_buffer - */ -#define DECLARE_KFIFO(name, size) \ -union { \ - struct kfifo name; \ - unsigned char name##kfifo_buffer[size + sizeof(struct kfifo)]; \ +#define __STRUCT_KFIFO(type, size, recsize, ptrtype) \ +{ \ + __STRUCT_KFIFO_COMMON(type, recsize, ptrtype); \ + type buf[((size < 2) || (size & (size - 1))) ? -1 : size]; \ } -/** - * INIT_KFIFO - Initialize a kfifo declared by DECLARE_KFIFO - * @name: name of the declared kfifo datatype +#define STRUCT_KFIFO(type, size) \ + struct __STRUCT_KFIFO(type, size, 0, type) + +#define __STRUCT_KFIFO_PTR(type, recsize, ptrtype) \ +{ \ + __STRUCT_KFIFO_COMMON(type, recsize, ptrtype); \ + type buf[0]; \ +} + +#define STRUCT_KFIFO_PTR(type) \ + struct __STRUCT_KFIFO_PTR(type, 0, type) + +/* + * define compatibility "struct kfifo" for dynamic allocated fifos */ -#define INIT_KFIFO(name) \ - name = __kfifo_initializer(sizeof(name##kfifo_buffer) - \ - sizeof(struct kfifo), \ - name##kfifo_buffer + sizeof(struct kfifo)) +struct kfifo __STRUCT_KFIFO_PTR(unsigned char, 0, void); -/** - * DEFINE_KFIFO - macro to define and initialize a kfifo - * @name: name of the declared kfifo datatype - * @size: size of the fifo buffer. Must be a power of two. - * - * Note1: the macro can be used for global and local kfifo data type variables - * Note2: the macro creates two objects: - * A kfifo object with the given name and a buffer for the kfifo - * object named name##kfifo_buffer +#define STRUCT_KFIFO_REC_1(size) \ + struct __STRUCT_KFIFO(unsigned char, size, 1, void) + +#define STRUCT_KFIFO_REC_2(size) \ + struct __STRUCT_KFIFO(unsigned char, size, 2, void) + +/* + * define kfifo_rec types */ -#define DEFINE_KFIFO(name, size) \ - unsigned char name##kfifo_buffer[size]; \ - struct kfifo name = __kfifo_initializer(size, name##kfifo_buffer) +struct kfifo_rec_ptr_1 __STRUCT_KFIFO_PTR(unsigned char, 1, void); +struct kfifo_rec_ptr_2 __STRUCT_KFIFO_PTR(unsigned char, 2, void); -extern void kfifo_init(struct kfifo *fifo, void *buffer, - unsigned int size); -extern __must_check int kfifo_alloc(struct kfifo *fifo, unsigned int size, - gfp_t gfp_mask); -extern void kfifo_free(struct kfifo *fifo); -extern unsigned int kfifo_in(struct kfifo *fifo, - const void *from, unsigned int len); -extern __must_check unsigned int kfifo_out(struct kfifo *fifo, - void *to, unsigned int len); -extern __must_check unsigned int kfifo_out_peek(struct kfifo *fifo, - void *to, unsigned int len, unsigned offset); +/* + * helper macro to distinguish between real in place fifo where the fifo + * array is a part of the structure and the fifo type where the array is + * outside of the fifo structure. + */ +#define __is_kfifo_ptr(fifo) (sizeof(*fifo) == sizeof(struct __kfifo)) /** - * kfifo_initialized - Check if kfifo is initialized. - * @fifo: fifo to check - * Return %true if FIFO is initialized, otherwise %false. - * Assumes the fifo was 0 before. + * DECLARE_KFIFO_PTR - macro to declare a fifo pointer object + * @fifo: name of the declared fifo + * @type: type of the fifo elements */ -static inline bool kfifo_initialized(struct kfifo *fifo) -{ - return fifo->buffer != NULL; -} +#define DECLARE_KFIFO_PTR(fifo, type) STRUCT_KFIFO_PTR(type) fifo /** - * kfifo_reset - removes the entire FIFO contents - * @fifo: the fifo to be emptied. + * DECLARE_KFIFO - macro to declare a fifo object + * @fifo: name of the declared fifo + * @type: type of the fifo elements + * @size: the number of elements in the fifo, this must be a power of 2 */ -static inline void kfifo_reset(struct kfifo *fifo) -{ - fifo->in = fifo->out = 0; -} +#define DECLARE_KFIFO(fifo, type, size) STRUCT_KFIFO(type, size) fifo /** - * kfifo_reset_out - skip FIFO contents - * @fifo: the fifo to be emptied. - */ -static inline void kfifo_reset_out(struct kfifo *fifo) -{ - smp_mb(); - fifo->out = fifo->in; -} + * INIT_KFIFO - Initialize a fifo declared by DECLARE_KFIFO + * @fifo: name of the declared fifo datatype + */ +#define INIT_KFIFO(fifo) \ +(void)({ \ + typeof(&(fifo)) __tmp = &(fifo); \ + struct __kfifo *__kfifo = &__tmp->kfifo; \ + __kfifo->in = 0; \ + __kfifo->out = 0; \ + __kfifo->mask = __is_kfifo_ptr(__tmp) ? 0 : ARRAY_SIZE(__tmp->buf) - 1;\ + __kfifo->esize = sizeof(*__tmp->buf); \ + __kfifo->data = __is_kfifo_ptr(__tmp) ? NULL : __tmp->buf; \ +}) /** - * kfifo_size - returns the size of the fifo in bytes - * @fifo: the fifo to be used. - */ -static inline __must_check unsigned int kfifo_size(struct kfifo *fifo) + * DEFINE_KFIFO - macro to define and initialize a fifo + * @fifo: name of the declared fifo datatype + * @type: type of the fifo elements + * @size: the number of elements in the fifo, this must be a power of 2 + * + * Note: the macro can be used for global and local fifo data type variables. + */ +#define DEFINE_KFIFO(fifo, type, size) \ + DECLARE_KFIFO(fifo, type, size) = \ + (typeof(fifo)) { \ + { \ + { \ + .in = 0, \ + .out = 0, \ + .mask = __is_kfifo_ptr(&(fifo)) ? \ + 0 : \ + ARRAY_SIZE((fifo).buf) - 1, \ + .esize = sizeof(*(fifo).buf), \ + .data = __is_kfifo_ptr(&(fifo)) ? \ + NULL : \ + (fifo).buf, \ + } \ + } \ + } + + +static inline unsigned int __must_check +__kfifo_must_check_helper(unsigned int val) { - return fifo->size; + return val; } /** - * kfifo_len - returns the number of used bytes in the FIFO - * @fifo: the fifo to be used. + * kfifo_initialized - Check if the fifo is initialized + * @fifo: address of the fifo to check + * + * Return %true if fifo is initialized, otherwise %false. + * Assumes the fifo was 0 before. */ -static inline unsigned int kfifo_len(struct kfifo *fifo) -{ - register unsigned int out; - - out = fifo->out; - smp_rmb(); - return fifo->in - out; -} +#define kfifo_initialized(fifo) ((fifo)->kfifo.mask) /** - * kfifo_is_empty - returns true if the fifo is empty - * @fifo: the fifo to be used. + * kfifo_esize - returns the size of the element managed by the fifo + * @fifo: address of the fifo to be used */ -static inline __must_check bool kfifo_is_empty(struct kfifo *fifo) -{ - return fifo->in == fifo->out; -} +#define kfifo_esize(fifo) ((fifo)->kfifo.esize) /** - * kfifo_is_full - returns true if the fifo is full - * @fifo: the fifo to be used. + * kfifo_recsize - returns the size of the record length field + * @fifo: address of the fifo to be used */ -static inline __must_check bool kfifo_is_full(struct kfifo *fifo) -{ - return kfifo_len(fifo) == kfifo_size(fifo); -} +#define kfifo_recsize(fifo) (sizeof(*(fifo)->rectype)) /** - * kfifo_avail - returns the number of bytes available in the FIFO - * @fifo: the fifo to be used. + * kfifo_size - returns the size of the fifo in elements + * @fifo: address of the fifo to be used */ -static inline __must_check unsigned int kfifo_avail(struct kfifo *fifo) -{ - return kfifo_size(fifo) - kfifo_len(fifo); -} +#define kfifo_size(fifo) ((fifo)->kfifo.mask + 1) /** - * kfifo_in_locked - puts some data into the FIFO using a spinlock for locking - * @fifo: the fifo to be used. - * @from: the data to be added. - * @n: the length of the data to be added. - * @lock: pointer to the spinlock to use for locking. + * kfifo_reset - removes the entire fifo content + * @fifo: address of the fifo to be used * - * This function copies at most @n bytes from the @from buffer into - * the FIFO depending on the free space, and returns the number of - * bytes copied. + * Note: usage of kfifo_reset() is dangerous. It should be only called when the + * fifo is exclusived locked or when it is secured that no other thread is + * accessing the fifo. */ -static inline unsigned int kfifo_in_locked(struct kfifo *fifo, - const void *from, unsigned int n, spinlock_t *lock) -{ - unsigned long flags; - unsigned int ret; - - spin_lock_irqsave(lock, flags); - - ret = kfifo_in(fifo, from, n); - - spin_unlock_irqrestore(lock, flags); - - return ret; -} +#define kfifo_reset(fifo) \ +(void)({ \ + typeof(fifo + 1) __tmp = (fifo); \ + __tmp->kfifo.in = __tmp->kfifo.out = 0; \ +}) /** - * kfifo_out_locked - gets some data from the FIFO using a spinlock for locking - * @fifo: the fifo to be used. - * @to: where the data must be copied. - * @n: the size of the destination buffer. - * @lock: pointer to the spinlock to use for locking. + * kfifo_reset_out - skip fifo content + * @fifo: address of the fifo to be used * - * This function copies at most @n bytes from the FIFO into the - * @to buffer and returns the number of copied bytes. - */ -static inline __must_check unsigned int kfifo_out_locked(struct kfifo *fifo, - void *to, unsigned int n, spinlock_t *lock) -{ - unsigned long flags; - unsigned int ret; - - spin_lock_irqsave(lock, flags); - - ret = kfifo_out(fifo, to, n); - - spin_unlock_irqrestore(lock, flags); - - return ret; -} - -extern void kfifo_skip(struct kfifo *fifo, unsigned int len); - -extern __must_check int kfifo_from_user(struct kfifo *fifo, - const void __user *from, unsigned int n, unsigned *lenout); - -extern __must_check int kfifo_to_user(struct kfifo *fifo, - void __user *to, unsigned int n, unsigned *lenout); - -/* - * __kfifo_add_out internal helper function for updating the out offset + * Note: The usage of kfifo_reset_out() is safe until it will be only called + * from the reader thread and there is only one concurrent reader. Otherwise + * it is dangerous and must be handled in the same way as kfifo_reset(). */ -static inline void __kfifo_add_out(struct kfifo *fifo, - unsigned int off) -{ - smp_mb(); - fifo->out += off; -} +#define kfifo_reset_out(fifo) \ +(void)({ \ + typeof(fifo + 1) __tmp = (fifo); \ + __tmp->kfifo.out = __tmp->kfifo.in; \ +}) -/* - * __kfifo_add_in internal helper function for updating the in offset +/** + * kfifo_len - returns the number of used elements in the fifo + * @fifo: address of the fifo to be used */ -static inline void __kfifo_add_in(struct kfifo *fifo, - unsigned int off) -{ - smp_wmb(); - fifo->in += off; -} +#define kfifo_len(fifo) \ +({ \ + typeof(fifo + 1) __tmpl = (fifo); \ + __tmpl->kfifo.in - __tmpl->kfifo.out; \ +}) -/* - * __kfifo_off internal helper function for calculating the index of a - * given offeset +/** + * kfifo_is_empty - returns true if the fifo is empty + * @fifo: address of the fifo to be used */ -static inline unsigned int __kfifo_off(struct kfifo *fifo, unsigned int off) -{ - return off & (fifo->size - 1); -} +#define kfifo_is_empty(fifo) \ +({ \ + typeof(fifo + 1) __tmpq = (fifo); \ + __tmpq->kfifo.in == __tmpq->kfifo.out; \ +}) -/* - * __kfifo_peek_n internal helper function for determinate the length of - * the next record in the fifo +/** + * kfifo_is_full - returns true if the fifo is full + * @fifo: address of the fifo to be used */ -static inline unsigned int __kfifo_peek_n(struct kfifo *fifo, - unsigned int recsize) -{ -#define __KFIFO_GET(fifo, off, shift) \ - ((fifo)->buffer[__kfifo_off((fifo), (fifo)->out+(off))] << (shift)) +#define kfifo_is_full(fifo) \ +({ \ + typeof(fifo + 1) __tmpq = (fifo); \ + kfifo_len(__tmpq) > __tmpq->kfifo.mask; \ +}) - unsigned int l; +/** + * kfifo_avail - returns the number of unused elements in the fifo + * @fifo: address of the fifo to be used + */ +#define kfifo_avail(fifo) \ +__kfifo_must_check_helper( \ +({ \ + typeof(fifo + 1) __tmpq = (fifo); \ + const size_t __recsize = sizeof(*__tmpq->rectype); \ + unsigned int __avail = kfifo_size(__tmpq) - kfifo_len(__tmpq); \ + (__recsize) ? ((__avail <= __recsize) ? 0 : \ + __kfifo_max_r(__avail - __recsize, __recsize)) : \ + __avail; \ +}) \ +) - l = __KFIFO_GET(fifo, 0, 0); +/** + * kfifo_skip - skip output data + * @fifo: address of the fifo to be used + */ +#define kfifo_skip(fifo) \ +(void)({ \ + typeof(fifo + 1) __tmp = (fifo); \ + const size_t __recsize = sizeof(*__tmp->rectype); \ + struct __kfifo *__kfifo = &__tmp->kfifo; \ + if (__recsize) \ + __kfifo_skip_r(__kfifo, __recsize); \ + else \ + __kfifo->out++; \ +}) - if (--recsize) - l |= __KFIFO_GET(fifo, 1, 8); +/** + * kfifo_peek_len - gets the size of the next fifo record + * @fifo: address of the fifo to be used + * + * This function returns the size of the next fifo record in number of bytes. + */ +#define kfifo_peek_len(fifo) \ +__kfifo_must_check_helper( \ +({ \ + typeof(fifo + 1) __tmp = (fifo); \ + const size_t __recsize = sizeof(*__tmp->rectype); \ + struct __kfifo *__kfifo = &__tmp->kfifo; \ + (!__recsize) ? kfifo_len(__tmp) * sizeof(*__tmp->type) : \ + __kfifo_len_r(__kfifo, __recsize); \ +}) \ +) - return l; -#undef __KFIFO_GET -} +/** + * kfifo_alloc - dynamically allocates a new fifo buffer + * @fifo: pointer to the fifo + * @size: the number of elements in the fifo, this must be a power of 2 + * @gfp_mask: get_free_pages mask, passed to kmalloc() + * + * This macro dynamically allocates a new fifo buffer. + * + * The numer of elements will be rounded-up to a power of 2. + * The fifo will be release with kfifo_free(). + * Return 0 if no error, otherwise an error code. + */ +#define kfifo_alloc(fifo, size, gfp_mask) \ +__kfifo_must_check_helper( \ +({ \ + typeof(fifo + 1) __tmp = (fifo); \ + struct __kfifo *__kfifo = &__tmp->kfifo; \ + __is_kfifo_ptr(__tmp) ? \ + __kfifo_alloc(__kfifo, size, sizeof(*__tmp->type), gfp_mask) : \ + -EINVAL; \ +}) \ +) -/* - * __kfifo_poke_n internal helper function for storing the length of - * the next record into the fifo +/** + * kfifo_free - frees the fifo + * @fifo: the fifo to be freed */ -static inline void __kfifo_poke_n(struct kfifo *fifo, - unsigned int recsize, unsigned int n) -{ -#define __KFIFO_PUT(fifo, off, val, shift) \ - ( \ - (fifo)->buffer[__kfifo_off((fifo), (fifo)->in+(off))] = \ - (unsigned char)((val) >> (shift)) \ - ) +#define kfifo_free(fifo) \ +({ \ + typeof(fifo + 1) __tmp = (fifo); \ + struct __kfifo *__kfifo = &__tmp->kfifo; \ + if (__is_kfifo_ptr(__tmp)) \ + __kfifo_free(__kfifo); \ +}) - __KFIFO_PUT(fifo, 0, n, 0); +/** + * kfifo_init - initialize a fifo using a preallocated buffer + * @fifo: the fifo to assign the buffer + * @buffer: the preallocated buffer to be used + * @size: the size of the internal buffer, this have to be a power of 2 + * + * This macro initialize a fifo using a preallocated buffer. + * + * The numer of elements will be rounded-up to a power of 2. + * Return 0 if no error, otherwise an error code. + */ +#define kfifo_init(fifo, buffer, size) \ +({ \ + typeof(fifo + 1) __tmp = (fifo); \ + struct __kfifo *__kfifo = &__tmp->kfifo; \ + __is_kfifo_ptr(__tmp) ? \ + __kfifo_init(__kfifo, buffer, size, sizeof(*__tmp->type)) : \ + -EINVAL; \ +}) - if (--recsize) - __KFIFO_PUT(fifo, 1, n, 8); -#undef __KFIFO_PUT -} +/** + * kfifo_put - put data into the fifo + * @fifo: address of the fifo to be used + * @val: the data to be added + * + * This macro copies the given value into the fifo. + * It returns 0 if the fifo was full. Otherwise it returns the number + * processed elements. + * + * Note that with only one concurrent reader and one concurrent + * writer, you don't need extra locking to use these macro. + */ +#define kfifo_put(fifo, val) \ +({ \ + typeof(fifo + 1) __tmp = (fifo); \ + typeof(val + 1) __val = (val); \ + unsigned int __ret; \ + const size_t __recsize = sizeof(*__tmp->rectype); \ + struct __kfifo *__kfifo = &__tmp->kfifo; \ + if (0) { \ + typeof(__tmp->ptr_const) __dummy __attribute__ ((unused)); \ + __dummy = (typeof(__val))NULL; \ + } \ + if (__recsize) \ + __ret = __kfifo_in_r(__kfifo, __val, sizeof(*__val), \ + __recsize); \ + else { \ + __ret = !kfifo_is_full(__tmp); \ + if (__ret) { \ + (__is_kfifo_ptr(__tmp) ? \ + ((typeof(__tmp->type))__kfifo->data) : \ + (__tmp->buf) \ + )[__kfifo->in & __tmp->kfifo.mask] = \ + *(typeof(__tmp->type))__val; \ + smp_wmb(); \ + __kfifo->in++; \ + } \ + } \ + __ret; \ +}) -/* - * __kfifo_in_... internal functions for put date into the fifo - * do not call it directly, use kfifo_in_rec() instead - */ -extern unsigned int __kfifo_in_n(struct kfifo *fifo, - const void *from, unsigned int n, unsigned int recsize); +/** + * kfifo_get - get data from the fifo + * @fifo: address of the fifo to be used + * @val: the var where to store the data to be added + * + * This macro reads the data from the fifo. + * It returns 0 if the fifo was empty. Otherwise it returns the number + * processed elements. + * + * Note that with only one concurrent reader and one concurrent + * writer, you don't need extra locking to use these macro. + */ +#define kfifo_get(fifo, val) \ +__kfifo_must_check_helper( \ +({ \ + typeof(fifo + 1) __tmp = (fifo); \ + typeof(val + 1) __val = (val); \ + unsigned int __ret; \ + const size_t __recsize = sizeof(*__tmp->rectype); \ + struct __kfifo *__kfifo = &__tmp->kfifo; \ + if (0) \ + __val = (typeof(__tmp->ptr))0; \ + if (__recsize) \ + __ret = __kfifo_out_r(__kfifo, __val, sizeof(*__val), \ + __recsize); \ + else { \ + __ret = !kfifo_is_empty(__tmp); \ + if (__ret) { \ + *(typeof(__tmp->type))__val = \ + (__is_kfifo_ptr(__tmp) ? \ + ((typeof(__tmp->type))__kfifo->data) : \ + (__tmp->buf) \ + )[__kfifo->out & __tmp->kfifo.mask]; \ + smp_wmb(); \ + __kfifo->out++; \ + } \ + } \ + __ret; \ +}) \ +) -extern unsigned int __kfifo_in_generic(struct kfifo *fifo, - const void *from, unsigned int n, unsigned int recsize); +/** + * kfifo_peek - get data from the fifo without removing + * @fifo: address of the fifo to be used + * @val: the var where to store the data to be added + * + * This reads the data from the fifo without removing it from the fifo. + * It returns 0 if the fifo was empty. Otherwise it returns the number + * processed elements. + * + * Note that with only one concurrent reader and one concurrent + * writer, you don't need extra locking to use these macro. + */ +#define kfifo_peek(fifo, val) \ +__kfifo_must_check_helper( \ +({ \ + typeof(fifo + 1) __tmp = (fifo); \ + typeof(val + 1) __val = (val); \ + unsigned int __ret; \ + const size_t __recsize = sizeof(*__tmp->rectype); \ + struct __kfifo *__kfifo = &__tmp->kfifo; \ + if (0) \ + __val = (typeof(__tmp->ptr))NULL; \ + if (__recsize) \ + __ret = __kfifo_out_peek_r(__kfifo, __val, sizeof(*__val), \ + __recsize); \ + else { \ + __ret = !kfifo_is_empty(__tmp); \ + if (__ret) { \ + *(typeof(__tmp->type))__val = \ + (__is_kfifo_ptr(__tmp) ? \ + ((typeof(__tmp->type))__kfifo->data) : \ + (__tmp->buf) \ + )[__kfifo->out & __tmp->kfifo.mask]; \ + smp_wmb(); \ + } \ + } \ + __ret; \ +}) \ +) -static inline unsigned int __kfifo_in_rec(struct kfifo *fifo, - const void *from, unsigned int n, unsigned int recsize) -{ - unsigned int ret; +/** + * kfifo_in - put data into the fifo + * @fifo: address of the fifo to be used + * @buf: the data to be added + * @n: number of elements to be added + * + * This macro copies the given buffer into the fifo and returns the + * number of copied elements. + * + * Note that with only one concurrent reader and one concurrent + * writer, you don't need extra locking to use these macro. + */ +#define kfifo_in(fifo, buf, n) \ +({ \ + typeof(fifo + 1) __tmp = (fifo); \ + typeof(buf + 1) __buf = (buf); \ + unsigned long __n = (n); \ + const size_t __recsize = sizeof(*__tmp->rectype); \ + struct __kfifo *__kfifo = &__tmp->kfifo; \ + if (0) { \ + typeof(__tmp->ptr_const) __dummy __attribute__ ((unused)); \ + __dummy = (typeof(__buf))NULL; \ + } \ + (__recsize) ?\ + __kfifo_in_r(__kfifo, __buf, __n, __recsize) : \ + __kfifo_in(__kfifo, __buf, __n); \ +}) - ret = __kfifo_in_n(fifo, from, n, recsize); +/** + * kfifo_in_spinlocked - put data into the fifo using a spinlock for locking + * @fifo: address of the fifo to be used + * @buf: the data to be added + * @n: number of elements to be added + * @lock: pointer to the spinlock to use for locking + * + * This macro copies the given values buffer into the fifo and returns the + * number of copied elements. + */ +#define kfifo_in_spinlocked(fifo, buf, n, lock) \ +({ \ + unsigned long __flags; \ + unsigned int __ret; \ + spin_lock_irqsave(lock, __flags); \ + __ret = kfifo_in(fifo, buf, n); \ + spin_unlock_irqrestore(lock, __flags); \ + __ret; \ +}) + +/* alias for kfifo_in_spinlocked, will be removed in a future release */ +#define kfifo_in_locked(fifo, buf, n, lock) \ + kfifo_in_spinlocked(fifo, buf, n, lock) - if (likely(ret == 0)) { - if (recsize) - __kfifo_poke_n(fifo, recsize, n); - __kfifo_add_in(fifo, n + recsize); - } - return ret; -} +/** + * kfifo_out - get data from the fifo + * @fifo: address of the fifo to be used + * @buf: pointer to the storage buffer + * @n: max. number of elements to get + * + * This macro get some data from the fifo and return the numbers of elements + * copied. + * + * Note that with only one concurrent reader and one concurrent + * writer, you don't need extra locking to use these macro. + */ +#define kfifo_out(fifo, buf, n) \ +__kfifo_must_check_helper( \ +({ \ + typeof(fifo + 1) __tmp = (fifo); \ + typeof(buf + 1) __buf = (buf); \ + unsigned long __n = (n); \ + const size_t __recsize = sizeof(*__tmp->rectype); \ + struct __kfifo *__kfifo = &__tmp->kfifo; \ + if (0) { \ + typeof(__tmp->ptr) __dummy = NULL; \ + __buf = __dummy; \ + } \ + (__recsize) ?\ + __kfifo_out_r(__kfifo, __buf, __n, __recsize) : \ + __kfifo_out(__kfifo, __buf, __n); \ +}) \ +) + +/** + * kfifo_out_spinlocked - get data from the fifo using a spinlock for locking + * @fifo: address of the fifo to be used + * @buf: pointer to the storage buffer + * @n: max. number of elements to get + * @lock: pointer to the spinlock to use for locking + * + * This macro get the data from the fifo and return the numbers of elements + * copied. + */ +#define kfifo_out_spinlocked(fifo, buf, n, lock) \ +__kfifo_must_check_helper( \ +({ \ + unsigned long __flags; \ + unsigned int __ret; \ + spin_lock_irqsave(lock, __flags); \ + __ret = kfifo_out(fifo, buf, n); \ + spin_unlock_irqrestore(lock, __flags); \ + __ret; \ +}) \ +) + +/* alias for kfifo_out_spinlocked, will be removed in a future release */ +#define kfifo_out_locked(fifo, buf, n, lock) \ + kfifo_out_spinlocked(fifo, buf, n, lock) /** - * kfifo_in_rec - puts some record data into the FIFO - * @fifo: the fifo to be used. - * @from: the data to be added. - * @n: the length of the data to be added. - * @recsize: size of record field + * kfifo_from_user - puts some data from user space into the fifo + * @fifo: address of the fifo to be used + * @from: pointer to the data to be added + * @len: the length of the data to be added + * @copied: pointer to output variable to store the number of copied bytes * - * This function copies @n bytes from the @from into the FIFO and returns - * the number of bytes which cannot be copied. - * A returned value greater than the @n value means that the record doesn't - * fit into the buffer. + * This macro copies at most @len bytes from the @from into the + * fifo, depending of the available space and returns -EFAULT/0. * * Note that with only one concurrent reader and one concurrent - * writer, you don't need extra locking to use these functions. - */ -static inline __must_check unsigned int kfifo_in_rec(struct kfifo *fifo, - void *from, unsigned int n, unsigned int recsize) -{ - if (!__builtin_constant_p(recsize)) - return __kfifo_in_generic(fifo, from, n, recsize); - return __kfifo_in_rec(fifo, from, n, recsize); -} + * writer, you don't need extra locking to use these macro. + */ +#define kfifo_from_user(fifo, from, len, copied) \ +__kfifo_must_check_helper( \ +({ \ + typeof(fifo + 1) __tmp = (fifo); \ + const void __user *__from = (from); \ + unsigned int __len = (len); \ + unsigned int *__copied = (copied); \ + const size_t __recsize = sizeof(*__tmp->rectype); \ + struct __kfifo *__kfifo = &__tmp->kfifo; \ + (__recsize) ? \ + __kfifo_from_user_r(__kfifo, __from, __len, __copied, __recsize) : \ + __kfifo_from_user(__kfifo, __from, __len, __copied); \ +}) \ +) -/* - * __kfifo_out_... internal functions for get date from the fifo - * do not call it directly, use kfifo_out_rec() instead - */ -extern unsigned int __kfifo_out_n(struct kfifo *fifo, - void *to, unsigned int reclen, unsigned int recsize); +/** + * kfifo_to_user - copies data from the fifo into user space + * @fifo: address of the fifo to be used + * @to: where the data must be copied + * @len: the size of the destination buffer + * @copied: pointer to output variable to store the number of copied bytes + * + * This macro copies at most @len bytes from the fifo into the + * @to buffer and returns -EFAULT/0. + * + * Note that with only one concurrent reader and one concurrent + * writer, you don't need extra locking to use these macro. + */ +#define kfifo_to_user(fifo, to, len, copied) \ +__kfifo_must_check_helper( \ +({ \ + typeof(fifo + 1) __tmp = (fifo); \ + void __user *__to = (to); \ + unsigned int __len = (len); \ + unsigned int *__copied = (copied); \ + const size_t __recsize = sizeof(*__tmp->rectype); \ + struct __kfifo *__kfifo = &__tmp->kfifo; \ + (__recsize) ? \ + __kfifo_to_user_r(__kfifo, __to, __len, __copied, __recsize) : \ + __kfifo_to_user(__kfifo, __to, __len, __copied); \ +}) \ +) + +/** + * kfifo_dma_in_prepare - setup a scatterlist for DMA input + * @fifo: address of the fifo to be used + * @sgl: pointer to the scatterlist array + * @nents: number of entries in the scatterlist array + * @len: number of elements to transfer + * + * This macro fills a scatterlist for DMA input. + * It returns the number entries in the scatterlist array. + * + * Note that with only one concurrent reader and one concurrent + * writer, you don't need extra locking to use these macros. + */ +#define kfifo_dma_in_prepare(fifo, sgl, nents, len) \ +({ \ + typeof(fifo + 1) __tmp = (fifo); \ + struct scatterlist *__sgl = (sgl); \ + int __nents = (nents); \ + unsigned int __len = (len); \ + const size_t __recsize = sizeof(*__tmp->rectype); \ + struct __kfifo *__kfifo = &__tmp->kfifo; \ + (__recsize) ? \ + __kfifo_dma_in_prepare_r(__kfifo, __sgl, __nents, __len, __recsize) : \ + __kfifo_dma_in_prepare(__kfifo, __sgl, __nents, __len); \ +}) -extern unsigned int __kfifo_out_generic(struct kfifo *fifo, - void *to, unsigned int n, - unsigned int recsize, unsigned int *total); +/** + * kfifo_dma_in_finish - finish a DMA IN operation + * @fifo: address of the fifo to be used + * @len: number of bytes to received + * + * This macro finish a DMA IN operation. The in counter will be updated by + * the len parameter. No error checking will be done. + * + * Note that with only one concurrent reader and one concurrent + * writer, you don't need extra locking to use these macros. + */ +#define kfifo_dma_in_finish(fifo, len) \ +(void)({ \ + typeof(fifo + 1) __tmp = (fifo); \ + unsigned int __len = (len); \ + const size_t __recsize = sizeof(*__tmp->rectype); \ + struct __kfifo *__kfifo = &__tmp->kfifo; \ + if (__recsize) \ + __kfifo_dma_in_finish_r(__kfifo, __len, __recsize); \ + else \ + __kfifo->in += __len / sizeof(*__tmp->type); \ +}) -static inline unsigned int __kfifo_out_rec(struct kfifo *fifo, - void *to, unsigned int n, unsigned int recsize, - unsigned int *total) -{ - unsigned int l; - - if (!recsize) { - l = n; - if (total) - *total = l; - } else { - l = __kfifo_peek_n(fifo, recsize); - if (total) - *total = l; - if (n < l) - return l; - } +/** + * kfifo_dma_out_prepare - setup a scatterlist for DMA output + * @fifo: address of the fifo to be used + * @sgl: pointer to the scatterlist array + * @nents: number of entries in the scatterlist array + * @len: number of elements to transfer + * + * This macro fills a scatterlist for DMA output which at most @len bytes + * to transfer. + * It returns the number entries in the scatterlist array. + * A zero means there is no space available and the scatterlist is not filled. + * + * Note that with only one concurrent reader and one concurrent + * writer, you don't need extra locking to use these macros. + */ +#define kfifo_dma_out_prepare(fifo, sgl, nents, len) \ +({ \ + typeof(fifo + 1) __tmp = (fifo); \ + struct scatterlist *__sgl = (sgl); \ + int __nents = (nents); \ + unsigned int __len = (len); \ + const size_t __recsize = sizeof(*__tmp->rectype); \ + struct __kfifo *__kfifo = &__tmp->kfifo; \ + (__recsize) ? \ + __kfifo_dma_out_prepare_r(__kfifo, __sgl, __nents, __len, __recsize) : \ + __kfifo_dma_out_prepare(__kfifo, __sgl, __nents, __len); \ +}) - return __kfifo_out_n(fifo, to, l, recsize); -} +/** + * kfifo_dma_out_finish - finish a DMA OUT operation + * @fifo: address of the fifo to be used + * @len: number of bytes transferd + * + * This macro finish a DMA OUT operation. The out counter will be updated by + * the len parameter. No error checking will be done. + * + * Note that with only one concurrent reader and one concurrent + * writer, you don't need extra locking to use these macros. + */ +#define kfifo_dma_out_finish(fifo, len) \ +(void)({ \ + typeof(fifo + 1) __tmp = (fifo); \ + unsigned int __len = (len); \ + const size_t __recsize = sizeof(*__tmp->rectype); \ + struct __kfifo *__kfifo = &__tmp->kfifo; \ + if (__recsize) \ + __kfifo_dma_out_finish_r(__kfifo, __recsize); \ + else \ + __kfifo->out += __len / sizeof(*__tmp->type); \ +}) /** - * kfifo_out_rec - gets some record data from the FIFO - * @fifo: the fifo to be used. - * @to: where the data must be copied. - * @n: the size of the destination buffer. - * @recsize: size of record field - * @total: pointer where the total number of to copied bytes should stored + * kfifo_out_peek - gets some data from the fifo + * @fifo: address of the fifo to be used + * @buf: pointer to the storage buffer + * @n: max. number of elements to get * - * This function copies at most @n bytes from the FIFO to @to and returns the - * number of bytes which cannot be copied. - * A returned value greater than the @n value means that the record doesn't - * fit into the @to buffer. + * This macro get the data from the fifo and return the numbers of elements + * copied. The data is not removed from the fifo. * * Note that with only one concurrent reader and one concurrent - * writer, you don't need extra locking to use these functions. + * writer, you don't need extra locking to use these macro. */ -static inline __must_check unsigned int kfifo_out_rec(struct kfifo *fifo, - void *to, unsigned int n, unsigned int recsize, - unsigned int *total) +#define kfifo_out_peek(fifo, buf, n) \ +__kfifo_must_check_helper( \ +({ \ + typeof(fifo + 1) __tmp = (fifo); \ + typeof(buf + 1) __buf = (buf); \ + unsigned long __n = (n); \ + const size_t __recsize = sizeof(*__tmp->rectype); \ + struct __kfifo *__kfifo = &__tmp->kfifo; \ + if (0) { \ + typeof(__tmp->ptr) __dummy __attribute__ ((unused)) = NULL; \ + __buf = __dummy; \ + } \ + (__recsize) ? \ + __kfifo_out_peek_r(__kfifo, __buf, __n, __recsize) : \ + __kfifo_out_peek(__kfifo, __buf, __n); \ +}) \ +) -{ - if (!__builtin_constant_p(recsize)) - return __kfifo_out_generic(fifo, to, n, recsize, total); - return __kfifo_out_rec(fifo, to, n, recsize, total); -} +extern int __kfifo_alloc(struct __kfifo *fifo, unsigned int size, + size_t esize, gfp_t gfp_mask); -/* - * __kfifo_from_user_... internal functions for transfer from user space into - * the fifo. do not call it directly, use kfifo_from_user_rec() instead - */ -extern unsigned int __kfifo_from_user_n(struct kfifo *fifo, - const void __user *from, unsigned int n, unsigned int recsize); +extern void __kfifo_free(struct __kfifo *fifo); -extern unsigned int __kfifo_from_user_generic(struct kfifo *fifo, - const void __user *from, unsigned int n, unsigned int recsize); +extern int __kfifo_init(struct __kfifo *fifo, void *buffer, + unsigned int size, size_t esize); -static inline unsigned int __kfifo_from_user_rec(struct kfifo *fifo, - const void __user *from, unsigned int n, unsigned int recsize) -{ - unsigned int ret; +extern unsigned int __kfifo_in(struct __kfifo *fifo, + const void *buf, unsigned int len); - ret = __kfifo_from_user_n(fifo, from, n, recsize); +extern unsigned int __kfifo_out(struct __kfifo *fifo, + void *buf, unsigned int len); - if (likely(ret == 0)) { - if (recsize) - __kfifo_poke_n(fifo, recsize, n); - __kfifo_add_in(fifo, n + recsize); - } - return ret; -} +extern int __kfifo_from_user(struct __kfifo *fifo, + const void __user *from, unsigned long len, unsigned int *copied); -/** - * kfifo_from_user_rec - puts some data from user space into the FIFO - * @fifo: the fifo to be used. - * @from: pointer to the data to be added. - * @n: the length of the data to be added. - * @recsize: size of record field - * - * This function copies @n bytes from the @from into the - * FIFO and returns the number of bytes which cannot be copied. - * - * If the returned value is equal or less the @n value, the copy_from_user() - * functions has failed. Otherwise the record doesn't fit into the buffer. - * - * Note that with only one concurrent reader and one concurrent - * writer, you don't need extra locking to use these functions. - */ -static inline __must_check unsigned int kfifo_from_user_rec(struct kfifo *fifo, - const void __user *from, unsigned int n, unsigned int recsize) -{ - if (!__builtin_constant_p(recsize)) - return __kfifo_from_user_generic(fifo, from, n, recsize); - return __kfifo_from_user_rec(fifo, from, n, recsize); -} +extern int __kfifo_to_user(struct __kfifo *fifo, + void __user *to, unsigned long len, unsigned int *copied); -/* - * __kfifo_to_user_... internal functions for transfer fifo data into user space - * do not call it directly, use kfifo_to_user_rec() instead - */ -extern unsigned int __kfifo_to_user_n(struct kfifo *fifo, - void __user *to, unsigned int n, unsigned int reclen, - unsigned int recsize); +extern unsigned int __kfifo_dma_in_prepare(struct __kfifo *fifo, + struct scatterlist *sgl, int nents, unsigned int len); -extern unsigned int __kfifo_to_user_generic(struct kfifo *fifo, - void __user *to, unsigned int n, unsigned int recsize, - unsigned int *total); +extern unsigned int __kfifo_dma_out_prepare(struct __kfifo *fifo, + struct scatterlist *sgl, int nents, unsigned int len); -static inline unsigned int __kfifo_to_user_rec(struct kfifo *fifo, - void __user *to, unsigned int n, - unsigned int recsize, unsigned int *total) -{ - unsigned int l; - - if (!recsize) { - l = n; - if (total) - *total = l; - } else { - l = __kfifo_peek_n(fifo, recsize); - if (total) - *total = l; - if (n < l) - return l; - } +extern unsigned int __kfifo_out_peek(struct __kfifo *fifo, + void *buf, unsigned int len); - return __kfifo_to_user_n(fifo, to, n, l, recsize); -} +extern unsigned int __kfifo_in_r(struct __kfifo *fifo, + const void *buf, unsigned int len, size_t recsize); -/** - * kfifo_to_user_rec - gets data from the FIFO and write it to user space - * @fifo: the fifo to be used. - * @to: where the data must be copied. - * @n: the size of the destination buffer. - * @recsize: size of record field - * @total: pointer where the total number of to copied bytes should stored - * - * This function copies at most @n bytes from the FIFO to the @to. - * In case of an error, the function returns the number of bytes which cannot - * be copied. - * If the returned value is equal or less the @n value, the copy_to_user() - * functions has failed. Otherwise the record doesn't fit into the @to buffer. - * - * Note that with only one concurrent reader and one concurrent - * writer, you don't need extra locking to use these functions. - */ -static inline __must_check unsigned int kfifo_to_user_rec(struct kfifo *fifo, - void __user *to, unsigned int n, unsigned int recsize, - unsigned int *total) -{ - if (!__builtin_constant_p(recsize)) - return __kfifo_to_user_generic(fifo, to, n, recsize, total); - return __kfifo_to_user_rec(fifo, to, n, recsize, total); -} +extern unsigned int __kfifo_out_r(struct __kfifo *fifo, + void *buf, unsigned int len, size_t recsize); -/* - * __kfifo_peek_... internal functions for peek into the next fifo record - * do not call it directly, use kfifo_peek_rec() instead - */ -extern unsigned int __kfifo_peek_generic(struct kfifo *fifo, - unsigned int recsize); +extern int __kfifo_from_user_r(struct __kfifo *fifo, + const void __user *from, unsigned long len, unsigned int *copied, + size_t recsize); -/** - * kfifo_peek_rec - gets the size of the next FIFO record data - * @fifo: the fifo to be used. - * @recsize: size of record field - * - * This function returns the size of the next FIFO record in number of bytes - */ -static inline __must_check unsigned int kfifo_peek_rec(struct kfifo *fifo, - unsigned int recsize) -{ - if (!__builtin_constant_p(recsize)) - return __kfifo_peek_generic(fifo, recsize); - if (!recsize) - return kfifo_len(fifo); - return __kfifo_peek_n(fifo, recsize); -} +extern int __kfifo_to_user_r(struct __kfifo *fifo, void __user *to, + unsigned long len, unsigned int *copied, size_t recsize); -/* - * __kfifo_skip_... internal functions for skip the next fifo record - * do not call it directly, use kfifo_skip_rec() instead - */ -extern void __kfifo_skip_generic(struct kfifo *fifo, unsigned int recsize); +extern unsigned int __kfifo_dma_in_prepare_r(struct __kfifo *fifo, + struct scatterlist *sgl, int nents, unsigned int len, size_t recsize); -static inline void __kfifo_skip_rec(struct kfifo *fifo, - unsigned int recsize) -{ - unsigned int l; +extern void __kfifo_dma_in_finish_r(struct __kfifo *fifo, + unsigned int len, size_t recsize); - if (recsize) { - l = __kfifo_peek_n(fifo, recsize); +extern unsigned int __kfifo_dma_out_prepare_r(struct __kfifo *fifo, + struct scatterlist *sgl, int nents, unsigned int len, size_t recsize); - if (l + recsize <= kfifo_len(fifo)) { - __kfifo_add_out(fifo, l + recsize); - return; - } - } - kfifo_reset_out(fifo); -} +extern void __kfifo_dma_out_finish_r(struct __kfifo *fifo, size_t recsize); -/** - * kfifo_skip_rec - skip the next fifo out record - * @fifo: the fifo to be used. - * @recsize: size of record field - * - * This function skips the next FIFO record - */ -static inline void kfifo_skip_rec(struct kfifo *fifo, - unsigned int recsize) -{ - if (!__builtin_constant_p(recsize)) - __kfifo_skip_generic(fifo, recsize); - else - __kfifo_skip_rec(fifo, recsize); -} +extern unsigned int __kfifo_len_r(struct __kfifo *fifo, size_t recsize); -/** - * kfifo_avail_rec - returns the number of bytes available in a record FIFO - * @fifo: the fifo to be used. - * @recsize: size of record field - */ -static inline __must_check unsigned int kfifo_avail_rec(struct kfifo *fifo, - unsigned int recsize) -{ - unsigned int l = kfifo_size(fifo) - kfifo_len(fifo); +extern unsigned int __kfifo_out_peek_r(struct __kfifo *fifo, + void *buf, unsigned int len, size_t recsize); - return (l > recsize) ? l - recsize : 0; -} +extern unsigned int __kfifo_max_r(unsigned int len, size_t recsize); #endif -- cgit v1.2.3 From 9a94241afcc9a481691a9c29b7460217925b59b8 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Wed, 11 Aug 2010 18:20:56 +0200 Subject: i2c: Add support for custom probe function The probe method used by i2c_new_probed_device() may not be suitable for all cases. Let the caller provide its own, optional probe function. Signed-off-by: Jean Delvare Acked-by: Mauro Carvalho Chehab --- include/linux/i2c.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 38dd4025aa4e..59a9f3cdc0b5 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -284,12 +284,15 @@ i2c_new_device(struct i2c_adapter *adap, struct i2c_board_info const *info); /* If you don't know the exact address of an I2C device, use this variant * instead, which can probe for device presence in a list of possible - * addresses. + * addresses. The "probe" callback function is optional. If it is provided, + * it must return 1 on successful probe, 0 otherwise. If it is not provided, + * a default probing method is used. */ extern struct i2c_client * i2c_new_probed_device(struct i2c_adapter *adap, struct i2c_board_info *info, - unsigned short const *addr_list); + unsigned short const *addr_list, + int (*probe)(struct i2c_adapter *, unsigned short addr)); /* For devices that use several addresses, use i2c_new_dummy() to make * client handles for the extra addresses. -- cgit v1.2.3 From d44f19d586b6113fb5db10e1a36457f0db3b01aa Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Wed, 11 Aug 2010 18:20:57 +0200 Subject: V4L/DVB: Use custom I2C probing function mechanism Now that i2c-core offers the possibility to provide custom probing function for I2C devices, let's make use of it. Signed-off-by: Jean Delvare Acked-by: Mauro Carvalho Chehab --- include/linux/i2c.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 59a9f3cdc0b5..c8627e453e97 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -294,6 +294,9 @@ i2c_new_probed_device(struct i2c_adapter *adap, unsigned short const *addr_list, int (*probe)(struct i2c_adapter *, unsigned short addr)); +/* Common custom probe functions */ +extern int i2c_probe_func_quick_read(struct i2c_adapter *, unsigned short addr); + /* For devices that use several addresses, use i2c_new_dummy() to make * client handles for the extra addresses. */ -- cgit v1.2.3 From fe61e07e9ebc890c70d97a1f72ddaad4bee2d848 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Wed, 11 Aug 2010 18:20:58 +0200 Subject: i2c: Move adapter locking helpers to i2c-core Uninline i2c adapter locking helper functions, move them to i2c-core, and use them in i2c-core itself. The functions are still exported for external users. This makes future updates to the locking model (which will be needed for multiplexing support) possible and transparent. Signed-off-by: Jean Delvare Cc: Michael Lawnick --- include/linux/i2c.h | 20 +++----------------- 1 file changed, 3 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index c8627e453e97..5bf0f4beea31 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -382,23 +382,9 @@ static inline void i2c_set_adapdata(struct i2c_adapter *dev, void *data) dev_set_drvdata(&dev->dev, data); } -/** - * i2c_lock_adapter - Prevent access to an I2C bus segment - * @adapter: Target I2C bus segment - */ -static inline void i2c_lock_adapter(struct i2c_adapter *adapter) -{ - rt_mutex_lock(&adapter->bus_lock); -} - -/** - * i2c_unlock_adapter - Reauthorize access to an I2C bus segment - * @adapter: Target I2C bus segment - */ -static inline void i2c_unlock_adapter(struct i2c_adapter *adapter) -{ - rt_mutex_unlock(&adapter->bus_lock); -} +/* Adapter locking functions, exported for shared pin cases */ +void i2c_lock_adapter(struct i2c_adapter *); +void i2c_unlock_adapter(struct i2c_adapter *); /*flags for the client struct: */ #define I2C_CLIENT_PEC 0x04 /* Use Packet Error Checking */ -- cgit v1.2.3 From dafc50d141c27959dbd3a1cfe9857a86d23402a7 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Wed, 11 Aug 2010 18:21:01 +0200 Subject: i2c: Use a separate mutex for userspace client lists Moving userspace-instantiated clients to separate lists wasn't nearly enough to avoid deadlocks in multiplexed bus cases. We also want to have a dedicated mutex to protect each list. Signed-off-by: Jean Delvare Cc: Michael Lawnick --- include/linux/i2c.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 5bf0f4beea31..798bad8741e4 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -368,6 +368,7 @@ struct i2c_adapter { char name[48]; struct completion dev_released; + struct mutex userspace_clients_lock; struct list_head userspace_clients; }; #define to_i2c_adapter(d) container_of(d, struct i2c_adapter, dev) -- cgit v1.2.3 From 0826374bff57411d239f2fcb15da3c35af0a93cd Mon Sep 17 00:00:00 2001 From: Michael Lawnick Date: Wed, 11 Aug 2010 18:21:02 +0200 Subject: i2c: Multiplexed I2C bus core support Add multiplexed bus core support. I2C multiplexer and switches like pca954x get instantiated as new adapters per port. Signed-off-by: Michael Lawnick Acked-by: Rodolfo Giometti Signed-off-by: Jean Delvare --- include/linux/i2c-mux.h | 46 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/i2c.h | 8 ++++++++ 2 files changed, 54 insertions(+) create mode 100644 include/linux/i2c-mux.h (limited to 'include/linux') diff --git a/include/linux/i2c-mux.h b/include/linux/i2c-mux.h new file mode 100644 index 000000000000..34536effd652 --- /dev/null +++ b/include/linux/i2c-mux.h @@ -0,0 +1,46 @@ +/* + * + * i2c-mux.h - functions for the i2c-bus mux support + * + * Copyright (c) 2008-2009 Rodolfo Giometti + * Copyright (c) 2008-2009 Eurotech S.p.A. + * Michael Lawnick + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + */ + +#ifndef _LINUX_I2C_MUX_H +#define _LINUX_I2C_MUX_H + +#ifdef __KERNEL__ + +/* + * Called to create a i2c bus on a multiplexed bus segment. + * The mux_dev and chan_id parameters are passed to the select + * and deselect callback functions to perform hardware-specific + * mux control. + */ +struct i2c_adapter *i2c_add_mux_adapter(struct i2c_adapter *parent, + void *mux_dev, u32 force_nr, u32 chan_id, + int (*select) (struct i2c_adapter *, + void *mux_dev, u32 chan_id), + int (*deselect) (struct i2c_adapter *, + void *mux_dev, u32 chan_id)); + +int i2c_del_mux_adapter(struct i2c_adapter *adap); + +#endif /* __KERNEL__ */ + +#endif /* _LINUX_I2C_MUX_H */ diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 798bad8741e4..4bae0b72ed3c 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -37,6 +37,7 @@ #include /* for struct device_node */ extern struct bus_type i2c_bus_type; +extern struct device_type i2c_adapter_type; /* --- General options ------------------------------------------------ */ @@ -383,6 +384,13 @@ static inline void i2c_set_adapdata(struct i2c_adapter *dev, void *data) dev_set_drvdata(&dev->dev, data); } +static inline int i2c_parent_is_i2c_adapter(const struct i2c_adapter *adapter) +{ + return adapter->dev.parent != NULL + && adapter->dev.parent->bus == &i2c_bus_type + && adapter->dev.parent->type == &i2c_adapter_type; +} + /* Adapter locking functions, exported for shared pin cases */ void i2c_lock_adapter(struct i2c_adapter *); void i2c_unlock_adapter(struct i2c_adapter *); -- cgit v1.2.3 From 7f528135da9704d67db1f727162024b078e1cd8f Mon Sep 17 00:00:00 2001 From: Michael Lawnick Date: Wed, 11 Aug 2010 18:21:03 +0200 Subject: i2c: I2C bus multiplexer driver pca954x I2C driver for PCA954x I2C multiplexer series. Signed-off-by: Michael Lawnick Acked-by: Rodolfo Giometti Signed-off-by: Jean Delvare --- include/linux/i2c/pca954x.h | 47 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) create mode 100644 include/linux/i2c/pca954x.h (limited to 'include/linux') diff --git a/include/linux/i2c/pca954x.h b/include/linux/i2c/pca954x.h new file mode 100644 index 000000000000..28f1f8d5ab1f --- /dev/null +++ b/include/linux/i2c/pca954x.h @@ -0,0 +1,47 @@ +/* + * + * pca954x.h - I2C multiplexer/switch support + * + * Copyright (c) 2008-2009 Rodolfo Giometti + * Copyright (c) 2008-2009 Eurotech S.p.A. + * Michael Lawnick + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + */ + + +#ifndef _LINUX_I2C_PCA954X_H +#define _LINUX_I2C_PCA954X_H + +/* Platform data for the PCA954x I2C multiplexers */ + +/* Per channel initialisation data: + * @adap_id: bus number for the adapter. 0 = don't care + * @deselect_on_exit: set this entry to 1, if your H/W needs deselection + * of this channel after transaction. + * + */ +struct pca954x_platform_mode { + int adap_id; + unsigned int deselect_on_exit:1; +}; + +/* Per mux/switch data, used with i2c_register_board_info */ +struct pca954x_platform_data { + struct pca954x_platform_mode *modes; + int num_modes; +}; + +#endif /* _LINUX_I2C_PCA954X_H */ -- cgit v1.2.3 From d5302fe41ffb28d0a48be6a71becba36d3453ae0 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Thu, 12 Aug 2010 06:38:24 +1000 Subject: Make lib/raid6/test build correctly. Some bit-rot needs to be cleaned out. Signed-off-by: NeilBrown --- include/linux/raid/pq.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/raid/pq.h b/include/linux/raid/pq.h index 1cbbd2c11aa9..2b59cc824395 100644 --- a/include/linux/raid/pq.h +++ b/include/linux/raid/pq.h @@ -62,7 +62,9 @@ extern const char raid6_empty_zero_page[PAGE_SIZE]; #define disable_kernel_altivec() #define EXPORT_SYMBOL(sym) +#define EXPORT_SYMBOL_GPL(sym) #define MODULE_LICENSE(licence) +#define MODULE_DESCRIPTION(desc) #define subsys_initcall(x) #define module_exit(x) #endif /* __KERNEL__ */ -- cgit v1.2.3 From 71beefe8c0b9e12ed4ac9fe13b98a035ddeaf8eb Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Thu, 12 Aug 2010 11:44:50 +1000 Subject: vgaarb: drop vga.h include We don't actually need this include on any platform. built on powerpc + x86, reported on m68k. Reported-by: Geert Uytterhoeven Signed-off-by: Dave Airlie --- include/linux/vgaarb.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vgaarb.h b/include/linux/vgaarb.h index 814f294d4cd0..6228b5b77d35 100644 --- a/include/linux/vgaarb.h +++ b/include/linux/vgaarb.h @@ -31,7 +31,6 @@ #ifndef LINUX_VGA_H #define LINUX_VGA_H -#include /* Legacy VGA regions */ #define VGA_RSRC_NONE 0x00 -- cgit v1.2.3 From 31ce4bfdfd10bf5db9bf85c92bbe0cf2edbdcad8 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Thu, 12 Aug 2010 11:47:50 +1000 Subject: io-mapping: move asm include inside the config option nouveau starting using these APIs, the first on non-x86 hw, and this include isn't required on anything with real amounts of vmalloc space. this fixes a build problem on powerpc. Signed-off-by: Dave Airlie --- include/linux/io-mapping.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h index e0ea40f6c515..0a6b3d5c490c 100644 --- a/include/linux/io-mapping.h +++ b/include/linux/io-mapping.h @@ -22,7 +22,6 @@ #include #include #include -#include /* * The io_mapping mechanism provides an abstraction for mapping @@ -33,6 +32,8 @@ #ifdef CONFIG_HAVE_ATOMIC_IOMAP +#include + struct io_mapping { resource_size_t base; unsigned long size; -- cgit v1.2.3 From a5664dad7e1a278d2915c2bf79cf42250e12d7db Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Thu, 12 Aug 2010 04:14:01 +0100 Subject: dm ioctl: make bio or request based device type immutable Determine whether a mapped device is bio-based or request-based when loading its first (inactive) table and don't allow that to be changed later. This patch performs different device initialisation in each of the two cases. (We don't think it's necessary to add code to support changing between the two types.) Allowed md->type transitions: DM_TYPE_NONE to DM_TYPE_BIO_BASED DM_TYPE_NONE to DM_TYPE_REQUEST_BASED We now prevent table_load from replacing the inactive table with a conflicting type of table even after an explicit table_clear. Introduce 'type_lock' into the struct mapped_device to protect md->type and to prepare for the next patch that will change the queue initialization and allocate memory while md->type_lock is held. Signed-off-by: Mike Snitzer Acked-by: Kiyoshi Ueda Signed-off-by: Alasdair G Kergon drivers/md/dm-ioctl.c | 15 +++++++++++++++ drivers/md/dm.c | 37 ++++++++++++++++++++++++++++++------- drivers/md/dm.h | 5 +++++ include/linux/dm-ioctl.h | 4 ++-- 4 files changed, 52 insertions(+), 9 deletions(-) --- include/linux/dm-ioctl.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dm-ioctl.h b/include/linux/dm-ioctl.h index 2c445e113790..43b2de17449b 100644 --- a/include/linux/dm-ioctl.h +++ b/include/linux/dm-ioctl.h @@ -266,9 +266,9 @@ enum { #define DM_DEV_SET_GEOMETRY _IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl) #define DM_VERSION_MAJOR 4 -#define DM_VERSION_MINOR 17 +#define DM_VERSION_MINOR 18 #define DM_VERSION_PATCHLEVEL 0 -#define DM_VERSION_EXTRA "-ioctl (2010-03-05)" +#define DM_VERSION_EXTRA "-ioctl (2010-06-29)" /* Status bits */ #define DM_READONLY_FLAG (1 << 0) /* In/Out */ -- cgit v1.2.3 From 57cba5d3658d9fdc019c6af14a2d80aefa651e56 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Thu, 12 Aug 2010 04:14:04 +0100 Subject: dm: rename map_info flush_request to target_request_nr 'target_request_nr' is a more generic name that reflects the fact that it will be used for both flush and discard support. Signed-off-by: Mike Snitzer Signed-off-by: Alasdair G Kergon --- include/linux/device-mapper.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 1381cd97b4ed..531a6f2635ae 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -22,7 +22,7 @@ typedef enum { STATUSTYPE_INFO, STATUSTYPE_TABLE } status_type_t; union map_info { void *ptr; unsigned long long ll; - unsigned flush_request; + unsigned target_request_nr; }; /* @@ -174,7 +174,7 @@ struct dm_target { * A number of zero-length barrier requests that will be submitted * to the target for the purpose of flushing cache. * - * The request number will be placed in union map_info->flush_request. + * The request number will be placed in union map_info->target_request_nr. * It is a responsibility of the target driver to remap these requests * to the real underlying devices. */ -- cgit v1.2.3 From 7e507eb6432afdd798d4c6dccf949b8c43ef151c Mon Sep 17 00:00:00 2001 From: Peter Rajnoha Date: Thu, 12 Aug 2010 04:14:05 +0100 Subject: dm: allow autoloading of dm mod Add devname:mapper/control and MAPPER_CTRL_MINOR module alias to support dm-mod module autoloading. Signed-off-by: Kay Sievers Signed-off-by: Peter Rajnoha Signed-off-by: Alasdair G Kergon --- include/linux/dm-ioctl.h | 1 + include/linux/miscdevice.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dm-ioctl.h b/include/linux/dm-ioctl.h index 43b2de17449b..49eab360d5d4 100644 --- a/include/linux/dm-ioctl.h +++ b/include/linux/dm-ioctl.h @@ -11,6 +11,7 @@ #include #define DM_DIR "mapper" /* Slashes not supported */ +#define DM_CONTROL_NODE "control" #define DM_MAX_TYPE_NAME 16 #define DM_NAME_LEN 128 #define DM_UUID_LEN 129 diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h index f6c9b7dcb9fd..bafffc737903 100644 --- a/include/linux/miscdevice.h +++ b/include/linux/miscdevice.h @@ -38,6 +38,7 @@ #define KVM_MINOR 232 #define BTRFS_MINOR 234 #define AUTOFS_MINOR 235 +#define MAPPER_CTRL_MINOR 236 #define MISC_DYNAMIC_MINOR 255 struct device; -- cgit v1.2.3 From 5ae89a8720c28caf35c4e53711d77df2856c404e Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Thu, 12 Aug 2010 04:14:08 +0100 Subject: dm: linear support discard Allow discards to be passed through to linear mappings if at least one underlying device supports it. Discards will be forwarded only to devices that support them. A target that supports discards should set num_discard_requests to indicate how many times each discard request must be submitted to it. Verify table's underlying devices support discards prior to setting the associated DM device as capable of discards (via QUEUE_FLAG_DISCARD). Signed-off-by: Mike Snitzer Signed-off-by: Mikulas Patocka Reviewed-by: Joe Thornber Signed-off-by: Alasdair G Kergon --- include/linux/device-mapper.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 531a6f2635ae..751ce21dea7b 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -180,6 +180,12 @@ struct dm_target { */ unsigned num_flush_requests; + /* + * The number of discard requests that will be submitted to the + * target. map_info->request_nr is used just like num_flush_requests. + */ + unsigned num_discard_requests; + /* target specific data */ void *private; -- cgit v1.2.3 From 56a67df766039666f61fb15b079f713e44a735ae Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Thu, 12 Aug 2010 04:14:10 +0100 Subject: dm: factor out max_io_len_target_boundary Split max_io_len_target_boundary out of max_io_len so that the discard support can make use of it without duplicating max_io_len code. Avoiding max_io_len's split_io logic enables DM's discard support to submit the entire discard request to a target. But discards must still be split on target boundaries. Signed-off-by: Mike Snitzer Signed-off-by: Alasdair G Kergon --- include/linux/device-mapper.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 751ce21dea7b..2970022faa63 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -398,6 +398,12 @@ void *dm_vcalloc(unsigned long nmemb, unsigned long elem_size); #define dm_array_too_big(fixed, obj, num) \ ((num) > (UINT_MAX - (fixed)) / (obj)) +/* + * Sector offset taken relative to the start of the target instead of + * relative to the start of the device. + */ +#define dm_target_offset(ti, sector) ((sector) - (ti)->begin) + static inline sector_t to_sector(unsigned long n) { return (n >> SECTOR_SHIFT); -- cgit v1.2.3 From 27e34995e1a863c1e9beba30e51dfe2a083f918d Mon Sep 17 00:00:00 2001 From: Rabin Vincent Date: Fri, 2 Jul 2010 16:52:08 +0530 Subject: mfd: Add STMPE I/O Expander support Add support for the STMPE family of I/O Expanders from STMicroelectronics. These devices include upto 24 gpios and a varying selection of blocks, including PWM, keypad, and touchscreen controllers. This patch adds the MFD core. [l.fu@pengutronix.de: fix stmpe811 enable hook] [l.fu@pengutronix.de: add touchscreen platform data] Acked-by: Luotao Fu Acked-by: Linus Walleij Signed-off-by: Rabin Vincent Signed-off-by: Samuel Ortiz --- include/linux/mfd/stmpe.h | 197 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 197 insertions(+) create mode 100644 include/linux/mfd/stmpe.h (limited to 'include/linux') diff --git a/include/linux/mfd/stmpe.h b/include/linux/mfd/stmpe.h new file mode 100644 index 000000000000..90faa98b577f --- /dev/null +++ b/include/linux/mfd/stmpe.h @@ -0,0 +1,197 @@ +/* + * Copyright (C) ST-Ericsson SA 2010 + * + * License Terms: GNU General Public License, version 2 + * Author: Rabin Vincent for ST-Ericsson + */ + +#ifndef __LINUX_MFD_STMPE_H +#define __LINUX_MFD_STMPE_H + +#include + +enum stmpe_block { + STMPE_BLOCK_GPIO = 1 << 0, + STMPE_BLOCK_KEYPAD = 1 << 1, + STMPE_BLOCK_TOUCHSCREEN = 1 << 2, + STMPE_BLOCK_ADC = 1 << 3, + STMPE_BLOCK_PWM = 1 << 4, + STMPE_BLOCK_ROTATOR = 1 << 5, +}; + +enum stmpe_partnum { + STMPE811, + STMPE1601, + STMPE2401, + STMPE2403, +}; + +/* + * For registers whose locations differ on variants, the correct address is + * obtained by indexing stmpe->regs with one of the following. + */ +enum { + STMPE_IDX_CHIP_ID, + STMPE_IDX_ICR_LSB, + STMPE_IDX_IER_LSB, + STMPE_IDX_ISR_MSB, + STMPE_IDX_GPMR_LSB, + STMPE_IDX_GPSR_LSB, + STMPE_IDX_GPCR_LSB, + STMPE_IDX_GPDR_LSB, + STMPE_IDX_GPEDR_MSB, + STMPE_IDX_GPRER_LSB, + STMPE_IDX_GPFER_LSB, + STMPE_IDX_GPAFR_U_MSB, + STMPE_IDX_IEGPIOR_LSB, + STMPE_IDX_ISGPIOR_MSB, + STMPE_IDX_MAX, +}; + + +struct stmpe_variant_info; + +/** + * struct stmpe - STMPE MFD structure + * @lock: lock protecting I/O operations + * @irq_lock: IRQ bus lock + * @dev: device, mostly for dev_dbg() + * @i2c: i2c client + * @variant: the detected STMPE model number + * @regs: list of addresses of registers which are at different addresses on + * different variants. Indexed by one of STMPE_IDX_*. + * @irq_base: starting IRQ number for internal IRQs + * @num_gpios: number of gpios, differs for variants + * @ier: cache of IER registers for bus_lock + * @oldier: cache of IER registers for bus_lock + * @pdata: platform data + */ +struct stmpe { + struct mutex lock; + struct mutex irq_lock; + struct device *dev; + struct i2c_client *i2c; + enum stmpe_partnum partnum; + struct stmpe_variant_info *variant; + const u8 *regs; + + int irq_base; + int num_gpios; + u8 ier[2]; + u8 oldier[2]; + struct stmpe_platform_data *pdata; +}; + +extern int stmpe_reg_write(struct stmpe *stmpe, u8 reg, u8 data); +extern int stmpe_reg_read(struct stmpe *stmpe, u8 reg); +extern int stmpe_block_read(struct stmpe *stmpe, u8 reg, u8 length, + u8 *values); +extern int stmpe_block_write(struct stmpe *stmpe, u8 reg, u8 length, + const u8 *values); +extern int stmpe_set_bits(struct stmpe *stmpe, u8 reg, u8 mask, u8 val); +extern int stmpe_set_altfunc(struct stmpe *stmpe, u32 pins, + enum stmpe_block block); +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 { + struct matrix_keymap_data *keymap_data; + unsigned int debounce_ms; + unsigned int scan_count; + bool no_autorepeat; +}; + +/** + * struct stmpe_gpio_platform_data - STMPE GPIO platform data + * @gpio_base: first gpio number assigned. A maximum of + * %STMPE_NR_GPIOS GPIOs will be allocated. + */ +struct stmpe_gpio_platform_data { + int gpio_base; + void (*setup)(struct stmpe *stmpe, unsigned gpio_base); + void (*remove)(struct stmpe *stmpe, unsigned gpio_base); +}; + +/** + * struct stmpe_ts_platform_data - stmpe811 touch screen controller platform + * data + * @sample_time: ADC converstion time in number of clock. + * (0 -> 36 clocks, 1 -> 44 clocks, 2 -> 56 clocks, 3 -> 64 clocks, + * 4 -> 80 clocks, 5 -> 96 clocks, 6 -> 144 clocks), + * recommended is 4. + * @mod_12b: ADC Bit mode (0 -> 10bit ADC, 1 -> 12bit ADC) + * @ref_sel: ADC reference source + * (0 -> internal reference, 1 -> external reference) + * @adc_freq: ADC Clock speed + * (0 -> 1.625 MHz, 1 -> 3.25 MHz, 2 || 3 -> 6.5 MHz) + * @ave_ctrl: Sample average control + * (0 -> 1 sample, 1 -> 2 samples, 2 -> 4 samples, 3 -> 8 samples) + * @touch_det_delay: Touch detect interrupt delay + * (0 -> 10 us, 1 -> 50 us, 2 -> 100 us, 3 -> 500 us, + * 4-> 1 ms, 5 -> 5 ms, 6 -> 10 ms, 7 -> 50 ms) + * recommended is 3 + * @settling: Panel driver settling time + * (0 -> 10 us, 1 -> 100 us, 2 -> 500 us, 3 -> 1 ms, + * 4 -> 5 ms, 5 -> 10 ms, 6 for 50 ms, 7 -> 100 ms) + * recommended is 2 + * @fraction_z: Length of the fractional part in z + * (fraction_z ([0..7]) = Count of the fractional part) + * recommended is 7 + * @i_drive: current limit value of the touchscreen drivers + * (0 -> 20 mA typical 35 mA max, 1 -> 50 mA typical 80 mA max) + * + * */ +struct stmpe_ts_platform_data { + u8 sample_time; + u8 mod_12b; + u8 ref_sel; + u8 adc_freq; + u8 ave_ctrl; + u8 touch_det_delay; + u8 settling; + u8 fraction_z; + u8 i_drive; +}; + +/** + * struct stmpe_platform_data - STMPE platform data + * @id: device id to distinguish between multiple STMPEs on the same board + * @blocks: bitmask of blocks to enable (use STMPE_BLOCK_*) + * @irq_trigger: IRQ trigger to use for the interrupt to the host + * @irq_invert_polarity: IRQ line is connected with reversed polarity + * @irq_base: base IRQ number. %STMPE_NR_IRQS irqs will be used, or + * %STMPE_NR_INTERNAL_IRQS if the GPIO driver is not used. + * @gpio: GPIO-specific platform data + * @keypad: keypad-specific platform data + * @ts: touchscreen-specific platform data + */ +struct stmpe_platform_data { + int id; + unsigned int blocks; + int irq_base; + unsigned int irq_trigger; + bool irq_invert_polarity; + + struct stmpe_gpio_platform_data *gpio; + struct stmpe_keypad_platform_data *keypad; + struct stmpe_ts_platform_data *ts; +}; + +#define STMPE_NR_INTERNAL_IRQS 9 +#define STMPE_INT_GPIO(x) (STMPE_NR_INTERNAL_IRQS + (x)) + +#define STMPE_NR_GPIOS 24 +#define STMPE_NR_IRQS STMPE_INT_GPIO(STMPE_NR_GPIOS) + +#endif -- cgit v1.2.3 From 91f4debf5e2df904e7fade530bd1a6d182efd72c Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Mon, 12 Jul 2010 03:48:08 +0200 Subject: mfd: Add JZ4740 ADC driver This patch adds a MFD driver for the JZ4740 ADC unit. The driver is used to demultiplex IRQs and synchronize access to shared registers between the battery, hwmon and (future) touchscreen driver. Signed-off-by: Lars-Peter Clausen Signed-off-by: Samuel Ortiz --- include/linux/jz4740-adc.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) create mode 100644 include/linux/jz4740-adc.h (limited to 'include/linux') diff --git a/include/linux/jz4740-adc.h b/include/linux/jz4740-adc.h new file mode 100644 index 000000000000..9053f95e9687 --- /dev/null +++ b/include/linux/jz4740-adc.h @@ -0,0 +1,32 @@ + +#ifndef __LINUX_JZ4740_ADC +#define __LINUX_JZ4740_ADC + +#include + +/* + * jz4740_adc_set_config - Configure a JZ4740 adc device + * @dev: Pointer to a jz4740-adc device + * @mask: Mask for the config value to be set + * @val: Value to be set + * + * This function can be used by the JZ4740 ADC mfd cells to configure their + * options in the shared config register. +*/ +int jz4740_adc_set_config(struct device *dev, uint32_t mask, uint32_t val); + +#define JZ_ADC_CONFIG_SPZZ BIT(31) +#define JZ_ADC_CONFIG_EX_IN BIT(30) +#define JZ_ADC_CONFIG_DNUM_MASK (0x7 << 16) +#define JZ_ADC_CONFIG_DMA_ENABLE BIT(15) +#define JZ_ADC_CONFIG_XYZ_MASK (0x2 << 13) +#define JZ_ADC_CONFIG_SAMPLE_NUM_MASK (0x7 << 10) +#define JZ_ADC_CONFIG_CLKDIV_MASK (0xf << 5) +#define JZ_ADC_CONFIG_BAT_MB BIT(4) + +#define JZ_ADC_CONFIG_DNUM(dnum) ((dnum) << 16) +#define JZ_ADC_CONFIG_XYZ_OFFSET(dnum) ((xyz) << 13) +#define JZ_ADC_CONFIG_SAMPLE_NUM(x) ((x) << 10) +#define JZ_ADC_CONFIG_CLKDIV(div) ((div) << 5) + +#endif -- cgit v1.2.3 From 9accdc1bf239ef20c0fe12ceff2a7532374fd7cd Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 8 Jul 2010 21:09:51 +0900 Subject: mfd: Add additional WM8994 GPIO functions Later revisions of the WM8994 add some more GPIO functions, define them in the header file. Signed-off-by: Mark Brown Signed-off-by: Samuel Ortiz --- include/linux/mfd/wm8994/gpio.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/wm8994/gpio.h b/include/linux/mfd/wm8994/gpio.h index b4d4c22991e8..0c79b5ff4b5a 100644 --- a/include/linux/mfd/wm8994/gpio.h +++ b/include/linux/mfd/wm8994/gpio.h @@ -36,6 +36,10 @@ #define WM8994_GP_FN_WSEQ_STATUS 16 #define WM8994_GP_FN_FIFO_ERROR 17 #define WM8994_GP_FN_OPCLK 18 +#define WM8994_GP_FN_THW 19 +#define WM8994_GP_FN_DCS_DONE 20 +#define WM8994_GP_FN_FLL1_OUT 21 +#define WM8994_GP_FN_FLL2_OUT 22 #define WM8994_GPN_DIR 0x8000 /* GPN_DIR */ #define WM8994_GPN_DIR_MASK 0x8000 /* GPN_DIR */ -- cgit v1.2.3 From 5981f4e65cb455a820b3d07b8e4bac506233f3ea Mon Sep 17 00:00:00 2001 From: Sundar R Iyer Date: Wed, 21 Jul 2010 11:41:07 +0530 Subject: mfd: Add stmpe auto sleep feature Some STMPE devices support entering sleep mode automatically on a specified timeout of inactivity on the I2C bus with the host system. Acked-by: Linus Walleij Acked-by: Rabin Vincent Signed-off-by: Sundar R Iyer Signed-off-by: Samuel Ortiz --- include/linux/mfd/stmpe.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/stmpe.h b/include/linux/mfd/stmpe.h index 90faa98b577f..39ca7588659b 100644 --- a/include/linux/mfd/stmpe.h +++ b/include/linux/mfd/stmpe.h @@ -170,6 +170,8 @@ struct stmpe_ts_platform_data { * @blocks: bitmask of blocks to enable (use STMPE_BLOCK_*) * @irq_trigger: IRQ trigger to use for the interrupt to the host * @irq_invert_polarity: IRQ line is connected with reversed polarity + * @autosleep: bool to enable/disable stmpe autosleep + * @autosleep_timeout: inactivity timeout in milliseconds for autosleep * @irq_base: base IRQ number. %STMPE_NR_IRQS irqs will be used, or * %STMPE_NR_INTERNAL_IRQS if the GPIO driver is not used. * @gpio: GPIO-specific platform data @@ -182,6 +184,8 @@ struct stmpe_platform_data { int irq_base; unsigned int irq_trigger; bool irq_invert_polarity; + bool autosleep; + int autosleep_timeout; struct stmpe_gpio_platform_data *gpio; struct stmpe_keypad_platform_data *keypad; -- cgit v1.2.3 From 3b16bb539c558cd523ea380653d4bf24a8c9e833 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 2 Aug 2010 11:14:17 +0200 Subject: mfd: New mc13783 function exposing flags MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This is needed for the mc13783-adc driver to decide if a touch screen is connected. If so some channels are not available as generic hwmon inputs. Signed-off-by: Uwe Kleine-König Signed-off-by: Samuel Ortiz --- include/linux/mfd/mc13783.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/mc13783.h b/include/linux/mfd/mc13783.h index 4a894f688549..0fa44fb8dd26 100644 --- a/include/linux/mfd/mc13783.h +++ b/include/linux/mfd/mc13783.h @@ -21,6 +21,8 @@ int mc13783_reg_write(struct mc13783 *mc13783, unsigned int offset, u32 val); int mc13783_reg_rmw(struct mc13783 *mc13783, unsigned int offset, u32 mask, u32 val); +int mc13783_get_flags(struct mc13783 *mc13783); + int mc13783_irq_request(struct mc13783 *mc13783, int irq, irq_handler_t handler, const char *name, void *dev); int mc13783_irq_request_nounmask(struct mc13783 *mc13783, int irq, -- cgit v1.2.3 From b6e6d54cab7633dd2216ede77ccd00cdaebd77ad Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 2 Aug 2010 15:48:04 +0200 Subject: mfd: Get rid of now unused mc13783 private header MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This adds all remaining definitions that are used by the core driver to the .c file. Signed-off-by: Uwe Kleine-König Signed-off-by: Samuel Ortiz --- include/linux/mfd/mc13783-private.h | 220 ------------------------------------ 1 file changed, 220 deletions(-) delete mode 100644 include/linux/mfd/mc13783-private.h (limited to 'include/linux') diff --git a/include/linux/mfd/mc13783-private.h b/include/linux/mfd/mc13783-private.h deleted file mode 100644 index 95cf9360553f..000000000000 --- a/include/linux/mfd/mc13783-private.h +++ /dev/null @@ -1,220 +0,0 @@ -/* - * Copyright 2009 Pengutronix, Sascha Hauer - * - * Initial development of this code was funded by - * Phytec Messtechnik GmbH, http://www.phytec.de - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. - */ - -#ifndef __LINUX_MFD_MC13783_PRIV_H -#define __LINUX_MFD_MC13783_PRIV_H - -#include -#include -#include -#include - -struct mc13783 { - struct spi_device *spidev; - struct mutex lock; - int irq; - int flags; - - irq_handler_t irqhandler[MC13783_NUM_IRQ]; - void *irqdata[MC13783_NUM_IRQ]; - - /* XXX these should go as platformdata to the regulator subdevice */ - struct mc13783_regulator_init_data *regulators; - int num_regulators; -}; - -#define MC13783_REG_INTERRUPT_STATUS_0 0 -#define MC13783_REG_INTERRUPT_MASK_0 1 -#define MC13783_REG_INTERRUPT_SENSE_0 2 -#define MC13783_REG_INTERRUPT_STATUS_1 3 -#define MC13783_REG_INTERRUPT_MASK_1 4 -#define MC13783_REG_INTERRUPT_SENSE_1 5 -#define MC13783_REG_POWER_UP_MODE_SENSE 6 -#define MC13783_REG_REVISION 7 -#define MC13783_REG_SEMAPHORE 8 -#define MC13783_REG_ARBITRATION_PERIPHERAL_AUDIO 9 -#define MC13783_REG_ARBITRATION_SWITCHERS 10 -#define MC13783_REG_ARBITRATION_REGULATORS_0 11 -#define MC13783_REG_ARBITRATION_REGULATORS_1 12 -#define MC13783_REG_POWER_CONTROL_0 13 -#define MC13783_REG_POWER_CONTROL_1 14 -#define MC13783_REG_POWER_CONTROL_2 15 -#define MC13783_REG_REGEN_ASSIGNMENT 16 -#define MC13783_REG_CONTROL_SPARE 17 -#define MC13783_REG_MEMORY_A 18 -#define MC13783_REG_MEMORY_B 19 -#define MC13783_REG_RTC_TIME 20 -#define MC13783_REG_RTC_ALARM 21 -#define MC13783_REG_RTC_DAY 22 -#define MC13783_REG_RTC_DAY_ALARM 23 -#define MC13783_REG_SWITCHERS_0 24 -#define MC13783_REG_SWITCHERS_1 25 -#define MC13783_REG_SWITCHERS_2 26 -#define MC13783_REG_SWITCHERS_3 27 -#define MC13783_REG_SWITCHERS_4 28 -#define MC13783_REG_SWITCHERS_5 29 -#define MC13783_REG_REGULATOR_SETTING_0 30 -#define MC13783_REG_REGULATOR_SETTING_1 31 -#define MC13783_REG_REGULATOR_MODE_0 32 -#define MC13783_REG_REGULATOR_MODE_1 33 -#define MC13783_REG_POWER_MISCELLANEOUS 34 -#define MC13783_REG_POWER_SPARE 35 -#define MC13783_REG_AUDIO_RX_0 36 -#define MC13783_REG_AUDIO_RX_1 37 -#define MC13783_REG_AUDIO_TX 38 -#define MC13783_REG_AUDIO_SSI_NETWORK 39 -#define MC13783_REG_AUDIO_CODEC 40 -#define MC13783_REG_AUDIO_STEREO_DAC 41 -#define MC13783_REG_AUDIO_SPARE 42 -#define MC13783_REG_ADC_0 43 -#define MC13783_REG_ADC_1 44 -#define MC13783_REG_ADC_2 45 -#define MC13783_REG_ADC_3 46 -#define MC13783_REG_ADC_4 47 -#define MC13783_REG_CHARGER 48 -#define MC13783_REG_USB 49 -#define MC13783_REG_CHARGE_USB_SPARE 50 -#define MC13783_REG_LED_CONTROL_0 51 -#define MC13783_REG_LED_CONTROL_1 52 -#define MC13783_REG_LED_CONTROL_2 53 -#define MC13783_REG_LED_CONTROL_3 54 -#define MC13783_REG_LED_CONTROL_4 55 -#define MC13783_REG_LED_CONTROL_5 56 -#define MC13783_REG_SPARE 57 -#define MC13783_REG_TRIM_0 58 -#define MC13783_REG_TRIM_1 59 -#define MC13783_REG_TEST_0 60 -#define MC13783_REG_TEST_1 61 -#define MC13783_REG_TEST_2 62 -#define MC13783_REG_TEST_3 63 -#define MC13783_REG_NB 64 - -/* - * Reg Regulator Mode 0 - */ -#define MC13783_REGCTRL_VAUDIO_EN (1 << 0) -#define MC13783_REGCTRL_VAUDIO_STBY (1 << 1) -#define MC13783_REGCTRL_VAUDIO_MODE (1 << 2) -#define MC13783_REGCTRL_VIOHI_EN (1 << 3) -#define MC13783_REGCTRL_VIOHI_STBY (1 << 4) -#define MC13783_REGCTRL_VIOHI_MODE (1 << 5) -#define MC13783_REGCTRL_VIOLO_EN (1 << 6) -#define MC13783_REGCTRL_VIOLO_STBY (1 << 7) -#define MC13783_REGCTRL_VIOLO_MODE (1 << 8) -#define MC13783_REGCTRL_VDIG_EN (1 << 9) -#define MC13783_REGCTRL_VDIG_STBY (1 << 10) -#define MC13783_REGCTRL_VDIG_MODE (1 << 11) -#define MC13783_REGCTRL_VGEN_EN (1 << 12) -#define MC13783_REGCTRL_VGEN_STBY (1 << 13) -#define MC13783_REGCTRL_VGEN_MODE (1 << 14) -#define MC13783_REGCTRL_VRFDIG_EN (1 << 15) -#define MC13783_REGCTRL_VRFDIG_STBY (1 << 16) -#define MC13783_REGCTRL_VRFDIG_MODE (1 << 17) -#define MC13783_REGCTRL_VRFREF_EN (1 << 18) -#define MC13783_REGCTRL_VRFREF_STBY (1 << 19) -#define MC13783_REGCTRL_VRFREF_MODE (1 << 20) -#define MC13783_REGCTRL_VRFCP_EN (1 << 21) -#define MC13783_REGCTRL_VRFCP_STBY (1 << 22) -#define MC13783_REGCTRL_VRFCP_MODE (1 << 23) - -/* - * Reg Regulator Mode 1 - */ -#define MC13783_REGCTRL_VSIM_EN (1 << 0) -#define MC13783_REGCTRL_VSIM_STBY (1 << 1) -#define MC13783_REGCTRL_VSIM_MODE (1 << 2) -#define MC13783_REGCTRL_VESIM_EN (1 << 3) -#define MC13783_REGCTRL_VESIM_STBY (1 << 4) -#define MC13783_REGCTRL_VESIM_MODE (1 << 5) -#define MC13783_REGCTRL_VCAM_EN (1 << 6) -#define MC13783_REGCTRL_VCAM_STBY (1 << 7) -#define MC13783_REGCTRL_VCAM_MODE (1 << 8) -#define MC13783_REGCTRL_VRFBG_EN (1 << 9) -#define MC13783_REGCTRL_VRFBG_STBY (1 << 10) -#define MC13783_REGCTRL_VVIB_EN (1 << 11) -#define MC13783_REGCTRL_VRF1_EN (1 << 12) -#define MC13783_REGCTRL_VRF1_STBY (1 << 13) -#define MC13783_REGCTRL_VRF1_MODE (1 << 14) -#define MC13783_REGCTRL_VRF2_EN (1 << 15) -#define MC13783_REGCTRL_VRF2_STBY (1 << 16) -#define MC13783_REGCTRL_VRF2_MODE (1 << 17) -#define MC13783_REGCTRL_VMMC1_EN (1 << 18) -#define MC13783_REGCTRL_VMMC1_STBY (1 << 19) -#define MC13783_REGCTRL_VMMC1_MODE (1 << 20) -#define MC13783_REGCTRL_VMMC2_EN (1 << 21) -#define MC13783_REGCTRL_VMMC2_STBY (1 << 22) -#define MC13783_REGCTRL_VMMC2_MODE (1 << 23) - -/* - * Reg Regulator Misc. - */ -#define MC13783_REGCTRL_GPO1_EN (1 << 6) -#define MC13783_REGCTRL_GPO2_EN (1 << 8) -#define MC13783_REGCTRL_GPO3_EN (1 << 10) -#define MC13783_REGCTRL_GPO4_EN (1 << 12) -#define MC13783_REGCTRL_VIBPINCTRL (1 << 14) - -/* - * Reg Switcher 4 - */ -#define MC13783_SWCTRL_SW1A_MODE (1 << 0) -#define MC13783_SWCTRL_SW1A_STBY_MODE (1 << 2) -#define MC13783_SWCTRL_SW1A_DVS_SPEED (1 << 6) -#define MC13783_SWCTRL_SW1A_PANIC_MODE (1 << 8) -#define MC13783_SWCTRL_SW1A_SOFTSTART (1 << 9) -#define MC13783_SWCTRL_SW1B_MODE (1 << 10) -#define MC13783_SWCTRL_SW1B_STBY_MODE (1 << 12) -#define MC13783_SWCTRL_SW1B_DVS_SPEED (1 << 14) -#define MC13783_SWCTRL_SW1B_PANIC_MODE (1 << 16) -#define MC13783_SWCTRL_SW1B_SOFTSTART (1 << 17) -#define MC13783_SWCTRL_PLL_EN (1 << 18) -#define MC13783_SWCTRL_PLL_FACTOR (1 << 19) - -/* - * Reg Switcher 5 - */ -#define MC13783_SWCTRL_SW2A_MODE (1 << 0) -#define MC13783_SWCTRL_SW2A_STBY_MODE (1 << 2) -#define MC13783_SWCTRL_SW2A_DVS_SPEED (1 << 6) -#define MC13783_SWCTRL_SW2A_PANIC_MODE (1 << 8) -#define MC13783_SWCTRL_SW2A_SOFTSTART (1 << 9) -#define MC13783_SWCTRL_SW2B_MODE (1 << 10) -#define MC13783_SWCTRL_SW2B_STBY_MODE (1 << 12) -#define MC13783_SWCTRL_SW2B_DVS_SPEED (1 << 14) -#define MC13783_SWCTRL_SW2B_PANIC_MODE (1 << 16) -#define MC13783_SWCTRL_SW2B_SOFTSTART (1 << 17) -#define MC13783_SWSET_SW3 (1 << 18) -#define MC13783_SWCTRL_SW3_EN (1 << 20) -#define MC13783_SWCTRL_SW3_STBY (1 << 21) -#define MC13783_SWCTRL_SW3_MODE (1 << 22) - -static inline int mc13783_set_bits(struct mc13783 *mc13783, unsigned int offset, - u32 mask, u32 val) -{ - int ret; - mc13783_lock(mc13783); - ret = mc13783_reg_rmw(mc13783, offset, mask, val); - mc13783_unlock(mc13783); - - return ret; -} - -#endif /* __LINUX_MFD_MC13783_PRIV_H */ -- cgit v1.2.3 From c6c193326384aecfd668c8f271799a44dbc74c1a Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Wed, 11 Aug 2010 01:11:04 +0200 Subject: mfd: Add TPS6586x driver Add mfd core driver for TPS6586x PMICs family. The driver provides I/O access for the sub-device drivers and performs regstration of the sub-devices based on the platform requirements. In addition it implements GPIOlib interface for the chip GPIOs. TODO: - add interrupt support - add platform data for PWM, backlight leds and charger Signed-off-by: Mike Rapoport Signed-off-by: Mike Rapoport Signed-off-by: Samuel Ortiz --- include/linux/mfd/tps6586x.h | 47 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) create mode 100644 include/linux/mfd/tps6586x.h (limited to 'include/linux') diff --git a/include/linux/mfd/tps6586x.h b/include/linux/mfd/tps6586x.h new file mode 100644 index 000000000000..772b3ae640af --- /dev/null +++ b/include/linux/mfd/tps6586x.h @@ -0,0 +1,47 @@ +#ifndef __LINUX_MFD_TPS6586X_H +#define __LINUX_MFD_TPS6586X_H + +enum { + TPS6586X_ID_SM_0, + TPS6586X_ID_SM_1, + TPS6586X_ID_SM_2, + TPS6586X_ID_LDO_0, + TPS6586X_ID_LDO_1, + TPS6586X_ID_LDO_2, + TPS6586X_ID_LDO_3, + TPS6586X_ID_LDO_4, + TPS6586X_ID_LDO_5, + TPS6586X_ID_LDO_6, + TPS6586X_ID_LDO_7, + TPS6586X_ID_LDO_8, + TPS6586X_ID_LDO_9, + TPS6586X_ID_LDO_RTC, +}; + +struct tps6586x_subdev_info { + int id; + const char *name; + void *platform_data; +}; + +struct tps6586x_platform_data { + int num_subdevs; + struct tps6586x_subdev_info *subdevs; + + int gpio_base; +}; + +/* + * NOTE: the functions below are not intended for use outside + * of the TPS6586X sub-device drivers + */ +extern int tps6586x_write(struct device *dev, int reg, uint8_t val); +extern int tps6586x_writes(struct device *dev, int reg, int len, uint8_t *val); +extern int tps6586x_read(struct device *dev, int reg, uint8_t *val); +extern int tps6586x_reads(struct device *dev, int reg, int len, uint8_t *val); +extern int tps6586x_set_bits(struct device *dev, int reg, uint8_t bit_mask); +extern int tps6586x_clr_bits(struct device *dev, int reg, uint8_t bit_mask); +extern int tps6586x_update(struct device *dev, int reg, uint8_t val, + uint8_t mask); + +#endif /*__LINUX_MFD_TPS6586X_H */ -- cgit v1.2.3 From 16c4042f08919f447d6b2a55679546c9b97c7264 Mon Sep 17 00:00:00 2001 From: Wu Fengguang Date: Wed, 11 Aug 2010 14:17:39 -0700 Subject: writeback: avoid unnecessary calculation of bdi dirty thresholds Split get_dirty_limits() into global_dirty_limits()+bdi_dirty_limit(), so that the latter can be avoided when under global dirty background threshold (which is the normal state for most systems). Signed-off-by: Wu Fengguang Cc: Peter Zijlstra Cc: Christoph Hellwig Cc: Dave Chinner Cc: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/writeback.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index c24eca71e80c..72a5d647a5f2 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -124,8 +124,9 @@ struct ctl_table; int dirty_writeback_centisecs_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); -void get_dirty_limits(unsigned long *pbackground, unsigned long *pdirty, - unsigned long *pbdi_dirty, struct backing_dev_info *bdi); +void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty); +unsigned long bdi_dirty_limit(struct backing_dev_info *bdi, + unsigned long dirty); void page_writeback_init(void); void balance_dirty_pages_ratelimited_nr(struct address_space *mapping, -- cgit v1.2.3 From 81d73a32d775ae9674ea6edf0b5b721fc3bc57d9 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 11 Aug 2010 14:17:44 -0700 Subject: mm: fix writeback_in_progress() Commit 83ba7b071f3 ("writeback: simplify the write back thread queue") broke writeback_in_progress() as in that commit we started to remove work items from the list at the moment we start working on them and not at the moment they are finished. Thus if the flusher thread was doing some work but there was no other work queued, writeback_in_progress() returned false. This could in particular cause unnecessary queueing of background writeback from balance_dirty_pages() or writeout work from writeback_sb_if_idle(). This patch fixes the problem by introducing a bit in the bdi state which indicates that the flusher thread is processing some work and uses this bit for writeback_in_progress() test. NOTE: Both callsites of writeback_in_progress() (namely, writeback_inodes_sb_if_idle() and balance_dirty_pages()) would actually need a different information than what writeback_in_progress() provides. They would need to know whether *the kind of writeback they are going to submit* is already queued. But this information isn't that simple to provide so let's fix writeback_in_progress() for the time being. Signed-off-by: Jan Kara Cc: Christoph Hellwig Cc: Wu Fengguang Acked-by: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/backing-dev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 7628219e5386..35b00746c712 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -31,6 +31,7 @@ enum bdi_state { BDI_async_congested, /* The async (write) queue is getting full */ BDI_sync_congested, /* The sync queue is getting full */ BDI_registered, /* bdi_register() was done */ + BDI_writeback_running, /* Writeback is in progress */ BDI_unused, /* Available bits start here */ }; -- cgit v1.2.3 From dfe86cba7676d58db8de7e623f5e72f1b0d3ca35 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Wed, 11 Aug 2010 14:17:46 -0700 Subject: mmc: add erase, secure erase, trim and secure trim operations SD/MMC cards tend to support an erase operation. In addition, eMMC v4.4 cards can support secure erase, trim and secure trim operations that are all variants of the basic erase command. SD/MMC device attributes "erase_size" and "preferred_erase_size" have been added. "erase_size" is the minimum size, in bytes, of an erase operation. For MMC, "erase_size" is the erase group size reported by the card. Note that "erase_size" does not apply to trim or secure trim operations where the minimum size is always one 512 byte sector. For SD, "erase_size" is 512 if the card is block-addressed, 0 otherwise. SD/MMC cards can erase an arbitrarily large area up to and including the whole card. When erasing a large area it may be desirable to do it in smaller chunks for three reasons: 1. A single erase command will make all other I/O on the card wait. This is not a problem if the whole card is being erased, but erasing one partition will make I/O for another partition on the same card wait for the duration of the erase - which could be a several minutes. 2. To be able to inform the user of erase progress. 3. The erase timeout becomes too large to be very useful. Because the erase timeout contains a margin which is multiplied by the size of the erase area, the value can end up being several minutes for large areas. "erase_size" is not the most efficient unit to erase (especially for SD where it is just one sector), hence "preferred_erase_size" provides a good chunk size for erasing large areas. For MMC, "preferred_erase_size" is the high-capacity erase size if a card specifies one, otherwise it is based on the capacity of the card. For SD, "preferred_erase_size" is the allocation unit size specified by the card. "preferred_erase_size" is in bytes. Signed-off-by: Adrian Hunter Acked-by: Jens Axboe Cc: Kyungmin Park Cc: Madhusudhan Chikkature Cc: Christoph Hellwig Cc: Ben Gardiner Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmc/card.h | 20 ++++++++++++++++++++ include/linux/mmc/core.h | 19 +++++++++++++++++++ include/linux/mmc/host.h | 1 + include/linux/mmc/mmc.h | 26 +++++++++++++++++++------- include/linux/mmc/sd.h | 5 +++++ 5 files changed, 64 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 4d893eaf8174..6b7525099e56 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -31,6 +31,7 @@ struct mmc_csd { unsigned int tacc_ns; unsigned int r2w_factor; unsigned int max_dtr; + unsigned int erase_size; /* In sectors */ unsigned int read_blkbits; unsigned int write_blkbits; unsigned int capacity; @@ -42,9 +43,16 @@ struct mmc_csd { struct mmc_ext_csd { u8 rev; + u8 erase_group_def; + u8 sec_feature_support; unsigned int sa_timeout; /* Units: 100ns */ unsigned int hs_max_dtr; unsigned int sectors; + unsigned int hc_erase_size; /* In sectors */ + unsigned int hc_erase_timeout; /* In milliseconds */ + unsigned int sec_trim_mult; /* Secure trim multiplier */ + unsigned int sec_erase_mult; /* Secure erase multiplier */ + unsigned int trim_timeout; /* In milliseconds */ }; struct sd_scr { @@ -54,6 +62,12 @@ struct sd_scr { #define SD_SCR_BUS_WIDTH_4 (1<<2) }; +struct sd_ssr { + unsigned int au; /* In sectors */ + unsigned int erase_timeout; /* In milliseconds */ + unsigned int erase_offset; /* In milliseconds */ +}; + struct sd_switch_caps { unsigned int hs_max_dtr; }; @@ -106,6 +120,11 @@ struct mmc_card { #define MMC_QUIRK_NONSTD_SDIO (1<<2) /* non-standard SDIO card attached */ /* (missing CIA registers) */ + unsigned int erase_size; /* erase size in sectors */ + unsigned int erase_shift; /* if erase unit is power 2 */ + unsigned int pref_erase; /* in sectors */ + u8 erased_byte; /* value of erased bytes */ + u32 raw_cid[4]; /* raw card CID */ u32 raw_csd[4]; /* raw card CSD */ u32 raw_scr[2]; /* raw card SCR */ @@ -113,6 +132,7 @@ struct mmc_card { struct mmc_csd csd; /* card specific */ struct mmc_ext_csd ext_csd; /* mmc v4 extended card specific */ struct sd_scr scr; /* extra SD information */ + struct sd_ssr ssr; /* yet more SD information */ struct sd_switch_caps sw_caps; /* switch (CMD6) caps */ unsigned int sdio_funcs; /* number of SDIO functions */ diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index e4898e9eeb59..7429033acb66 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -92,6 +92,8 @@ struct mmc_command { * actively failing requests */ + unsigned int erase_timeout; /* in milliseconds */ + struct mmc_data *data; /* data segment associated with cmd */ struct mmc_request *mrq; /* associated request */ }; @@ -134,6 +136,23 @@ extern int mmc_wait_for_cmd(struct mmc_host *, struct mmc_command *, int); extern int mmc_wait_for_app_cmd(struct mmc_host *, struct mmc_card *, struct mmc_command *, int); +#define MMC_ERASE_ARG 0x00000000 +#define MMC_SECURE_ERASE_ARG 0x80000000 +#define MMC_TRIM_ARG 0x00000001 +#define MMC_SECURE_TRIM1_ARG 0x80000001 +#define MMC_SECURE_TRIM2_ARG 0x80008000 + +#define MMC_SECURE_ARGS 0x80000000 +#define MMC_TRIM_ARGS 0x00008001 + +extern int mmc_erase(struct mmc_card *card, unsigned int from, unsigned int nr, + unsigned int arg); +extern int mmc_can_erase(struct mmc_card *card); +extern int mmc_can_trim(struct mmc_card *card); +extern int mmc_can_secure_erase_trim(struct mmc_card *card); +extern int mmc_erase_group_aligned(struct mmc_card *card, unsigned int from, + unsigned int nr); + extern void mmc_set_data_timeout(struct mmc_data *, const struct mmc_card *); extern unsigned int mmc_align_data_size(struct mmc_card *, unsigned int); diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 513ff0376b09..1575b52c3bfa 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -156,6 +156,7 @@ struct mmc_host { #define MMC_CAP_DISABLE (1 << 7) /* Can the host be disabled */ #define MMC_CAP_NONREMOVABLE (1 << 8) /* Nonremovable e.g. eMMC */ #define MMC_CAP_WAIT_WHILE_BUSY (1 << 9) /* Waits while card is busy */ +#define MMC_CAP_ERASE (1 << 10) /* Allow erase/trim commands */ mmc_pm_flag_t pm_caps; /* supported pm features */ diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h index 52ce98866287..dd11ae51fb68 100644 --- a/include/linux/mmc/mmc.h +++ b/include/linux/mmc/mmc.h @@ -251,13 +251,21 @@ struct _mmc_csd { * EXT_CSD fields */ -#define EXT_CSD_BUS_WIDTH 183 /* R/W */ -#define EXT_CSD_HS_TIMING 185 /* R/W */ -#define EXT_CSD_CARD_TYPE 196 /* RO */ -#define EXT_CSD_STRUCTURE 194 /* RO */ -#define EXT_CSD_REV 192 /* RO */ -#define EXT_CSD_SEC_CNT 212 /* RO, 4 bytes */ -#define EXT_CSD_S_A_TIMEOUT 217 +#define EXT_CSD_ERASE_GROUP_DEF 175 /* R/W */ +#define EXT_CSD_ERASED_MEM_CONT 181 /* RO */ +#define EXT_CSD_BUS_WIDTH 183 /* R/W */ +#define EXT_CSD_HS_TIMING 185 /* R/W */ +#define EXT_CSD_REV 192 /* RO */ +#define EXT_CSD_STRUCTURE 194 /* RO */ +#define EXT_CSD_CARD_TYPE 196 /* RO */ +#define EXT_CSD_SEC_CNT 212 /* RO, 4 bytes */ +#define EXT_CSD_S_A_TIMEOUT 217 /* RO */ +#define EXT_CSD_ERASE_TIMEOUT_MULT 223 /* RO */ +#define EXT_CSD_HC_ERASE_GRP_SIZE 224 /* RO */ +#define EXT_CSD_SEC_TRIM_MULT 229 /* RO */ +#define EXT_CSD_SEC_ERASE_MULT 230 /* RO */ +#define EXT_CSD_SEC_FEATURE_SUPPORT 231 /* RO */ +#define EXT_CSD_TRIM_MULT 232 /* RO */ /* * EXT_CSD field definitions @@ -275,6 +283,10 @@ struct _mmc_csd { #define EXT_CSD_BUS_WIDTH_4 1 /* Card is in 4 bit mode */ #define EXT_CSD_BUS_WIDTH_8 2 /* Card is in 8 bit mode */ +#define EXT_CSD_SEC_ER_EN BIT(0) +#define EXT_CSD_SEC_BD_BLK_EN BIT(2) +#define EXT_CSD_SEC_GB_CL_EN BIT(4) + /* * MMC_SWITCH access modes */ diff --git a/include/linux/mmc/sd.h b/include/linux/mmc/sd.h index f310062cffb4..3fd85e088cc3 100644 --- a/include/linux/mmc/sd.h +++ b/include/linux/mmc/sd.h @@ -21,8 +21,13 @@ /* class 10 */ #define SD_SWITCH 6 /* adtc [31:0] See below R1 */ + /* class 5 */ +#define SD_ERASE_WR_BLK_START 32 /* ac [31:0] data addr R1 */ +#define SD_ERASE_WR_BLK_END 33 /* ac [31:0] data addr R1 */ + /* Application commands */ #define SD_APP_SET_BUS_WIDTH 6 /* ac [1:0] bus width R1 */ +#define SD_APP_SD_STATUS 13 /* adtc R1 */ #define SD_APP_SEND_NUM_WR_BLKS 22 /* adtc R1 */ #define SD_APP_OP_COND 41 /* bcr [31:0] OCR R3 */ #define SD_APP_SEND_SCR 51 /* adtc R1 */ -- cgit v1.2.3 From 8d57a98ccd0b4489003473979da8f5a1363ba7a3 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Wed, 11 Aug 2010 14:17:49 -0700 Subject: block: add secure discard Secure discard is the same as discard except that all copies of the discarded sectors (perhaps created by garbage collection) must also be erased. Signed-off-by: Adrian Hunter Acked-by: Jens Axboe Cc: Kyungmin Park Cc: Madhusudhan Chikkature Cc: Christoph Hellwig Cc: Ben Gardiner Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/blk_types.h | 2 ++ include/linux/blkdev.h | 7 ++++++- include/linux/fs.h | 2 ++ 3 files changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 53691774d34e..ca83a97c9715 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -150,6 +150,7 @@ enum rq_flag_bits { __REQ_FLUSH, /* request for cache flush */ __REQ_IO_STAT, /* account I/O stat */ __REQ_MIXED_MERGE, /* merge of different types, fail separately */ + __REQ_SECURE, /* secure discard (used with __REQ_DISCARD) */ __REQ_NR_BITS, /* stops here */ }; @@ -190,5 +191,6 @@ enum rq_flag_bits { #define REQ_FLUSH (1 << __REQ_FLUSH) #define REQ_IO_STAT (1 << __REQ_IO_STAT) #define REQ_MIXED_MERGE (1 << __REQ_MIXED_MERGE) +#define REQ_SECURE (1 << __REQ_SECURE) #endif /* __LINUX_BLK_TYPES_H */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 89c855c5655c..2c54906f678f 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -389,6 +389,7 @@ struct request_queue #define QUEUE_FLAG_DISCARD 16 /* supports DISCARD */ #define QUEUE_FLAG_NOXMERGES 17 /* No extended merges */ #define QUEUE_FLAG_ADD_RANDOM 18 /* Contributes to random pool */ +#define QUEUE_FLAG_SECDISCARD 19 /* supports SECDISCARD */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_CLUSTER) | \ @@ -524,6 +525,8 @@ enum { #define blk_queue_stackable(q) \ test_bit(QUEUE_FLAG_STACKABLE, &(q)->queue_flags) #define blk_queue_discard(q) test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags) +#define blk_queue_secdiscard(q) (blk_queue_discard(q) && \ + test_bit(QUEUE_FLAG_SECDISCARD, &(q)->queue_flags)) #define blk_noretry_request(rq) \ ((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \ @@ -918,10 +921,12 @@ static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt, } enum{ BLKDEV_WAIT, /* wait for completion */ - BLKDEV_BARRIER, /*issue request with barrier */ + BLKDEV_BARRIER, /* issue request with barrier */ + BLKDEV_SECURE, /* secure discard */ }; #define BLKDEV_IFL_WAIT (1 << BLKDEV_WAIT) #define BLKDEV_IFL_BARRIER (1 << BLKDEV_BARRIER) +#define BLKDEV_IFL_SECURE (1 << BLKDEV_SECURE) extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *, unsigned long); extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector, diff --git a/include/linux/fs.h b/include/linux/fs.h index 267d02630517..7a0625e26a39 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -174,6 +174,7 @@ struct inodes_stat_t { */ #define DISCARD_NOBARRIER (WRITE | REQ_DISCARD) #define DISCARD_BARRIER (WRITE | REQ_DISCARD | REQ_HARDBARRIER) +#define DISCARD_SECURE (DISCARD_NOBARRIER | REQ_SECURE) #define SEL_IN 1 #define SEL_OUT 2 @@ -317,6 +318,7 @@ struct inodes_stat_t { #define BLKALIGNOFF _IO(0x12,122) #define BLKPBSZGET _IO(0x12,123) #define BLKDISCARDZEROES _IO(0x12,124) +#define BLKSECDISCARD _IO(0x12,125) #define BMAP_IOCTL 1 /* obsolete - kept for compatibility */ #define FIBMAP _IO(0x00,1) /* bmap access */ -- cgit v1.2.3 From 12fdff3fc2483f906ae6404a6e8dcf2550310b6f Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 12 Aug 2010 16:54:57 +0100 Subject: Add a dummy printk function for the maintenance of unused printks Add a dummy printk function for the maintenance of unused printks through gcc format checking, and also so that side-effect checking is maintained too. Signed-off-by: David Howells Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index d848cb854655..2b0a35e6bc69 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -306,6 +306,13 @@ static inline void log_buf_kexec_setup(void) } #endif +/* + * Dummy printk for disabled debugging statements to use whilst maintaining + * gcc's format and side-effect checking. + */ +static inline __attribute__ ((format (printf, 1, 2))) +int no_printk(const char *s, ...) { return 0; } + extern int printk_needs_cpu(int cpu); extern void printk_tick(void); -- cgit v1.2.3 From 4936a3b90d79dd8775c6ac23c2cf2dcebe29abde Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Mon, 9 Aug 2010 14:20:10 -0700 Subject: x86/hpet: Use the FSEC_PER_SEC constant for femto-second periods The current computation, introduced with f12a15be63, of FSEC_PER_SEC using the multiplication of (FSEC_PER_NSEC * NSEC_PER_SEC) is performed only with 32bit integers on small machines, resulting in an overflow and a *very* short intervals being programmed. An interrupt storm follows. Note that we also have to specify FSEC_PER_SEC as being long long to overcome the same limitations. Signed-off-by: Chris Wilson Signed-off-by: John Stultz Cc: Thomas Gleixner Acked-by: Ingo Molnar Acked-by: H. Peter Anvin Signed-off-by: Linus Torvalds --- include/linux/time.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/time.h b/include/linux/time.h index cb34e35fabac..12612701b1ae 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -38,7 +38,7 @@ extern struct timezone sys_tz; #define NSEC_PER_MSEC 1000000L #define USEC_PER_SEC 1000000L #define NSEC_PER_SEC 1000000000L -#define FSEC_PER_SEC 1000000000000000L +#define FSEC_PER_SEC 1000000000000000LL #define TIME_T_MAX (time_t)((1UL << ((sizeof(time_t) << 3) - 1)) - 1) -- cgit v1.2.3 From 2069601b3f0ea38170d4b509b89f3ca0a373bdc1 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 12 Aug 2010 14:23:04 -0700 Subject: Revert "fsnotify: store struct file not struct path" This reverts commit 3bcf3860a4ff9bbc522820b4b765e65e4deceb3e (and the accompanying commit c1e5c954020e "vfs/fsnotify: fsnotify_close can delay the final work in fput" that was a horribly ugly hack to make it work at all). The 'struct file' approach not only causes that disgusting hack, it somehow breaks pulseaudio, probably due to some other subtlety with f_count handling. Fix up various conflicts due to later fsnotify work. Signed-off-by: Linus Torvalds --- include/linux/fsnotify.h | 37 +++++++++++++++++++++---------------- include/linux/fsnotify_backend.h | 16 ++++++++-------- 2 files changed, 29 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index e4e2204187ee..59d0df43ff9d 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -26,18 +26,19 @@ static inline void fsnotify_d_instantiate(struct dentry *dentry, } /* Notify this dentry's parent about a child's events. */ -static inline void fsnotify_parent(struct file *file, struct dentry *dentry, __u32 mask) +static inline void fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask) { if (!dentry) - dentry = file->f_path.dentry; + dentry = path->dentry; - __fsnotify_parent(file, dentry, mask); + __fsnotify_parent(path, dentry, mask); } /* simple call site for access decisions */ static inline int fsnotify_perm(struct file *file, int mask) { - struct inode *inode = file->f_path.dentry->d_inode; + struct path *path = &file->f_path; + struct inode *inode = path->dentry->d_inode; __u32 fsnotify_mask = 0; if (file->f_mode & FMODE_NONOTIFY) @@ -51,7 +52,7 @@ static inline int fsnotify_perm(struct file *file, int mask) else BUG(); - return fsnotify(inode, fsnotify_mask, file, FSNOTIFY_EVENT_FILE, NULL, 0); + return fsnotify(inode, fsnotify_mask, path, FSNOTIFY_EVENT_PATH, NULL, 0); } /* @@ -186,15 +187,16 @@ static inline void fsnotify_mkdir(struct inode *inode, struct dentry *dentry) */ static inline void fsnotify_access(struct file *file) { - struct inode *inode = file->f_path.dentry->d_inode; + struct path *path = &file->f_path; + struct inode *inode = path->dentry->d_inode; __u32 mask = FS_ACCESS; if (S_ISDIR(inode->i_mode)) mask |= FS_IN_ISDIR; if (!(file->f_mode & FMODE_NONOTIFY)) { - fsnotify_parent(file, NULL, mask); - fsnotify(inode, mask, file, FSNOTIFY_EVENT_FILE, NULL, 0); + fsnotify_parent(path, NULL, mask); + fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0); } } @@ -203,15 +205,16 @@ static inline void fsnotify_access(struct file *file) */ static inline void fsnotify_modify(struct file *file) { - struct inode *inode = file->f_path.dentry->d_inode; + struct path *path = &file->f_path; + struct inode *inode = path->dentry->d_inode; __u32 mask = FS_MODIFY; if (S_ISDIR(inode->i_mode)) mask |= FS_IN_ISDIR; if (!(file->f_mode & FMODE_NONOTIFY)) { - fsnotify_parent(file, NULL, mask); - fsnotify(inode, mask, file, FSNOTIFY_EVENT_FILE, NULL, 0); + fsnotify_parent(path, NULL, mask); + fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0); } } @@ -220,15 +223,16 @@ static inline void fsnotify_modify(struct file *file) */ static inline void fsnotify_open(struct file *file) { - struct inode *inode = file->f_path.dentry->d_inode; + struct path *path = &file->f_path; + struct inode *inode = path->dentry->d_inode; __u32 mask = FS_OPEN; if (S_ISDIR(inode->i_mode)) mask |= FS_IN_ISDIR; if (!(file->f_mode & FMODE_NONOTIFY)) { - fsnotify_parent(file, NULL, mask); - fsnotify(inode, mask, file, FSNOTIFY_EVENT_FILE, NULL, 0); + fsnotify_parent(path, NULL, mask); + fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0); } } @@ -237,6 +241,7 @@ static inline void fsnotify_open(struct file *file) */ static inline void fsnotify_close(struct file *file) { + struct path *path = &file->f_path; struct inode *inode = file->f_path.dentry->d_inode; fmode_t mode = file->f_mode; __u32 mask = (mode & FMODE_WRITE) ? FS_CLOSE_WRITE : FS_CLOSE_NOWRITE; @@ -245,8 +250,8 @@ static inline void fsnotify_close(struct file *file) mask |= FS_IN_ISDIR; if (!(file->f_mode & FMODE_NONOTIFY)) { - fsnotify_parent(file, NULL, mask); - fsnotify(inode, mask, file, FSNOTIFY_EVENT_FILE, NULL, 0); + fsnotify_parent(path, NULL, mask); + fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0); } } diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 9bbfd7204b04..ed36fb57c426 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -203,20 +203,20 @@ struct fsnotify_event { /* to_tell may ONLY be dereferenced during handle_event(). */ struct inode *to_tell; /* either the inode the event happened to or its parent */ /* - * depending on the event type we should have either a file or inode - * We hold a reference on file, but NOT on inode. Since we have the ref on - * the file, it may be dereferenced at any point during this object's + * depending on the event type we should have either a path or inode + * We hold a reference on path, but NOT on inode. Since we have the ref on + * the path, it may be dereferenced at any point during this object's * lifetime. That reference is dropped when this object's refcnt hits - * 0. If this event contains an inode instead of a file, the inode may + * 0. If this event contains an inode instead of a path, the inode may * ONLY be used during handle_event(). */ union { - struct file *file; + struct path path; struct inode *inode; }; /* when calling fsnotify tell it if the data is a path or inode */ #define FSNOTIFY_EVENT_NONE 0 -#define FSNOTIFY_EVENT_FILE 1 +#define FSNOTIFY_EVENT_PATH 1 #define FSNOTIFY_EVENT_INODE 2 int data_type; /* which of the above union we have */ atomic_t refcnt; /* how many groups still are using/need to send this event */ @@ -293,7 +293,7 @@ struct fsnotify_mark { /* main fsnotify call to send events */ extern int fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is, const unsigned char *name, u32 cookie); -extern void __fsnotify_parent(struct file *file, struct dentry *dentry, __u32 mask); +extern void __fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask); extern void __fsnotify_inode_delete(struct inode *inode); extern void __fsnotify_vfsmount_delete(struct vfsmount *mnt); extern u32 fsnotify_get_cookie(void); @@ -422,7 +422,7 @@ static inline int fsnotify(struct inode *to_tell, __u32 mask, void *data, int da return 0; } -static inline void __fsnotify_parent(struct file *file, struct dentry *dentry, __u32 mask) +static inline void __fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask) {} static inline void __fsnotify_inode_delete(struct inode *inode) -- cgit v1.2.3 From e259f191f2244df04a7746fac1df8aa68ebd0106 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Fri, 13 Aug 2010 09:39:18 +0200 Subject: dma-mapping: fix build errors on !HAS_DMA architectures commit 4565f0170dfc849b3629c27d769db800467baa62 "dma-mapping: unify dma_get_cache_alignment implementations" causes build errors on !HAS_DMA architectures/platforms like s390 and sun3: include/linux/dma-mapping.h:145: error: static declaration of 'dma_get_cache_alignment' follows non-static declaration include/asm-generic/dma-mapping-broken.h:73: error: previous declaration of 'dma_get_cache_alignment' was here Fix this by adding an explicit ifdef. Cc: Geert Uytterhoeven Acked-by: FUJITA Tomonori Signed-off-by: Heiko Carstens Signed-off-by: Linus Torvalds --- include/linux/dma-mapping.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index e0670a512056..ce29b8151198 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -142,6 +142,7 @@ static inline int dma_set_seg_boundary(struct device *dev, unsigned long mask) return -EIO; } +#ifdef CONFIG_HAS_DMA static inline int dma_get_cache_alignment(void) { #ifdef ARCH_DMA_MINALIGN @@ -149,6 +150,7 @@ static inline int dma_get_cache_alignment(void) #endif return 1; } +#endif /* flags for the coherent memory api */ #define DMA_MEMORY_MAP 0x01 -- cgit v1.2.3 From b19dd42faf413b4705d4adb38521e82d73fa4249 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sun, 4 Jul 2010 00:15:10 +0200 Subject: bkl: Remove locked .ioctl file operation The last user is gone, so we can safely remove this Signed-off-by: Arnd Bergmann Cc: John Kacur Cc: Al Viro Cc: Thomas Gleixner Signed-off-by: Frederic Weisbecker --- include/linux/fs.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 7a0625e26a39..3c786fdaeab6 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1483,8 +1483,8 @@ struct block_device_operations; /* * NOTE: - * read, write, poll, fsync, readv, writev, unlocked_ioctl and compat_ioctl - * can be called without the big kernel lock held in all filesystems. + * all file operations except setlease can be called without + * the big kernel lock held in all filesystems. */ struct file_operations { struct module *owner; @@ -1495,7 +1495,6 @@ struct file_operations { ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t); int (*readdir) (struct file *, void *, filldir_t); unsigned int (*poll) (struct file *, struct poll_table_struct *); - int (*ioctl) (struct inode *, struct file *, unsigned int, unsigned long); long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long); long (*compat_ioctl) (struct file *, unsigned int, unsigned long); int (*mmap) (struct file *, struct vm_area_struct *); -- cgit v1.2.3 From 92298e668372f2f6c8a79fb272f13d65161a4876 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Fri, 13 Aug 2010 10:22:17 +1000 Subject: PCI: provide stub pci_domain_nr function for !CONFIG_PCI configs Allows the new PCI domain aware DRM code to compile on m68k. Reported-by: Geert Uytterhoeven Signed-off-by: Dave Airlie Signed-off-by: Jesse Barnes --- include/linux/pci.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index b1d17956a153..c8d95e369ff4 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1214,6 +1214,9 @@ static inline struct pci_dev *pci_get_bus_and_slot(unsigned int bus, unsigned int devfn) { return NULL; } +static inline int pci_domain_nr(struct pci_bus *bus) +{ return 0; } + #define dev_is_pci(d) (false) #define dev_is_pf(d) (false) #define dev_num_vf(d) (0) -- cgit v1.2.3 From c7887325230aec47d47a32562a6e26014a0fafca Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 11 Aug 2010 11:26:22 +0100 Subject: Mark arguments to certain syscalls as being const Mark arguments to certain system calls as being const where they should be but aren't. The list includes: (*) The filename arguments of various stat syscalls, execve(), various utimes syscalls and some mount syscalls. (*) The filename arguments of some syscall helpers relating to the above. (*) The buffer argument of various write syscalls. Signed-off-by: David Howells Acked-by: David S. Miller Signed-off-by: Linus Torvalds --- include/linux/compat.h | 6 +++--- include/linux/fs.h | 6 +++--- include/linux/syscalls.h | 20 ++++++++++---------- include/linux/time.h | 2 +- 4 files changed, 17 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 168f7daa7bde..9ddc8780e8db 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -331,7 +331,7 @@ asmlinkage long compat_sys_epoll_pwait(int epfd, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize); -asmlinkage long compat_sys_utimensat(unsigned int dfd, char __user *filename, +asmlinkage long compat_sys_utimensat(unsigned int dfd, const char __user *filename, struct compat_timespec __user *t, int flags); asmlinkage long compat_sys_signalfd(int ufd, @@ -348,9 +348,9 @@ asmlinkage long compat_sys_move_pages(pid_t pid, unsigned long nr_page, const int __user *nodes, int __user *status, int flags); -asmlinkage long compat_sys_futimesat(unsigned int dfd, char __user *filename, +asmlinkage long compat_sys_futimesat(unsigned int dfd, const char __user *filename, struct compat_timeval __user *t); -asmlinkage long compat_sys_newfstatat(unsigned int dfd, char __user * filename, +asmlinkage long compat_sys_newfstatat(unsigned int dfd, const char __user * filename, struct compat_stat __user *statbuf, int flag); asmlinkage long compat_sys_openat(unsigned int dfd, const char __user *filename, diff --git a/include/linux/fs.h b/include/linux/fs.h index 7a0625e26a39..5f0ca2fbb2a0 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2320,10 +2320,10 @@ void inode_set_bytes(struct inode *inode, loff_t bytes); extern int vfs_readdir(struct file *, filldir_t, void *); -extern int vfs_stat(char __user *, struct kstat *); -extern int vfs_lstat(char __user *, struct kstat *); +extern int vfs_stat(const char __user *, struct kstat *); +extern int vfs_lstat(const char __user *, struct kstat *); extern int vfs_fstat(unsigned int, struct kstat *); -extern int vfs_fstatat(int , char __user *, struct kstat *, int); +extern int vfs_fstatat(int , const char __user *, struct kstat *, int); extern int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd, unsigned long arg); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 1b67bd333b5e..6e5d19788634 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -394,7 +394,7 @@ asmlinkage long sys_umount(char __user *name, int flags); asmlinkage long sys_oldumount(char __user *name); asmlinkage long sys_truncate(const char __user *path, long length); asmlinkage long sys_ftruncate(unsigned int fd, unsigned long length); -asmlinkage long sys_stat(char __user *filename, +asmlinkage long sys_stat(const char __user *filename, struct __old_kernel_stat __user *statbuf); asmlinkage long sys_statfs(const char __user * path, struct statfs __user *buf); @@ -403,21 +403,21 @@ asmlinkage long sys_statfs64(const char __user *path, size_t sz, asmlinkage long sys_fstatfs(unsigned int fd, struct statfs __user *buf); asmlinkage long sys_fstatfs64(unsigned int fd, size_t sz, struct statfs64 __user *buf); -asmlinkage long sys_lstat(char __user *filename, +asmlinkage long sys_lstat(const char __user *filename, struct __old_kernel_stat __user *statbuf); asmlinkage long sys_fstat(unsigned int fd, struct __old_kernel_stat __user *statbuf); -asmlinkage long sys_newstat(char __user *filename, +asmlinkage long sys_newstat(const char __user *filename, struct stat __user *statbuf); -asmlinkage long sys_newlstat(char __user *filename, +asmlinkage long sys_newlstat(const char __user *filename, struct stat __user *statbuf); asmlinkage long sys_newfstat(unsigned int fd, struct stat __user *statbuf); asmlinkage long sys_ustat(unsigned dev, struct ustat __user *ubuf); #if BITS_PER_LONG == 32 -asmlinkage long sys_stat64(char __user *filename, +asmlinkage long sys_stat64(const char __user *filename, struct stat64 __user *statbuf); asmlinkage long sys_fstat64(unsigned long fd, struct stat64 __user *statbuf); -asmlinkage long sys_lstat64(char __user *filename, +asmlinkage long sys_lstat64(const char __user *filename, struct stat64 __user *statbuf); asmlinkage long sys_truncate64(const char __user *path, loff_t length); asmlinkage long sys_ftruncate64(unsigned int fd, loff_t length); @@ -760,7 +760,7 @@ asmlinkage long sys_linkat(int olddfd, const char __user *oldname, int newdfd, const char __user *newname, int flags); asmlinkage long sys_renameat(int olddfd, const char __user * oldname, int newdfd, const char __user * newname); -asmlinkage long sys_futimesat(int dfd, char __user *filename, +asmlinkage long sys_futimesat(int dfd, const char __user *filename, struct timeval __user *utimes); asmlinkage long sys_faccessat(int dfd, const char __user *filename, int mode); asmlinkage long sys_fchmodat(int dfd, const char __user * filename, @@ -769,13 +769,13 @@ asmlinkage long sys_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group, int flag); asmlinkage long sys_openat(int dfd, const char __user *filename, int flags, int mode); -asmlinkage long sys_newfstatat(int dfd, char __user *filename, +asmlinkage long sys_newfstatat(int dfd, const char __user *filename, struct stat __user *statbuf, int flag); -asmlinkage long sys_fstatat64(int dfd, char __user *filename, +asmlinkage long sys_fstatat64(int dfd, const char __user *filename, struct stat64 __user *statbuf, int flag); asmlinkage long sys_readlinkat(int dfd, const char __user *path, char __user *buf, int bufsiz); -asmlinkage long sys_utimensat(int dfd, char __user *filename, +asmlinkage long sys_utimensat(int dfd, const char __user *filename, struct timespec __user *utimes, int flags); asmlinkage long sys_unshare(unsigned long unshare_flags); diff --git a/include/linux/time.h b/include/linux/time.h index 12612701b1ae..9f15ac7ab92a 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -150,7 +150,7 @@ extern void do_gettimeofday(struct timeval *tv); extern int do_settimeofday(struct timespec *tv); extern int do_sys_settimeofday(struct timespec *tv, struct timezone *tz); #define do_posix_clock_monotonic_gettime(ts) ktime_get_ts(ts) -extern long do_utimes(int dfd, char __user *filename, struct timespec *times, int flags); +extern long do_utimes(int dfd, const char __user *filename, struct timespec *times, int flags); struct itimerval; extern int do_setitimer(int which, struct itimerval *value, struct itimerval *ovalue); -- cgit v1.2.3 From 5950ec8d3e47a08ec0b678a0e0ba5d1b9b62dd8e Mon Sep 17 00:00:00 2001 From: "Ira W. Snyder" Date: Sat, 14 Aug 2010 21:08:49 +0200 Subject: hwmon: (ltc4245) Expose all GPIO pins as analog voltages Add support for exposing all GPIO pins as analog voltages. Though this is not an ideal use of the chip, some hardware engineers may decide that the LTC4245 meets their design requirements when studying the datasheet. The GPIO pins are sampled in round-robin fashion, meaning that a slow reader will see stale data. A userspace application can detect this, because it will get -EAGAIN when reading from a sysfs file which contains stale data. Users can choose to use this feature on a per-chip basis by using either platform data or the OF device tree (where applicable). Signed-off-by: Ira W. Snyder Signed-off-by: Jean Delvare --- include/linux/i2c/ltc4245.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) create mode 100644 include/linux/i2c/ltc4245.h (limited to 'include/linux') diff --git a/include/linux/i2c/ltc4245.h b/include/linux/i2c/ltc4245.h new file mode 100644 index 000000000000..56bda4be0016 --- /dev/null +++ b/include/linux/i2c/ltc4245.h @@ -0,0 +1,21 @@ +/* + * Platform Data for LTC4245 hardware monitor chip + * + * Copyright (c) 2010 Ira W. Snyder + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#ifndef LINUX_LTC4245_H +#define LINUX_LTC4245_H + +#include + +struct ltc4245_platform_data { + bool use_extra_gpios; +}; + +#endif /* LINUX_LTC4245_H */ -- cgit v1.2.3 From 60641aa1f379820e99ac7f45a38b43795670c741 Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Sat, 14 Aug 2010 10:15:12 +0200 Subject: include: replace unifdef-y with header-y unifdef-y and header-y has same semantic. So there is no need to have both. Drop the unifdef-y variant and sort all lines again Signed-off-by: Sam Ravnborg --- include/linux/Kbuild | 468 +++++++++++++++++----------------- include/linux/byteorder/Kbuild | 4 +- include/linux/dvb/Kbuild | 7 +- include/linux/netfilter/Kbuild | 19 +- include/linux/netfilter_arp/Kbuild | 3 +- include/linux/netfilter_bridge/Kbuild | 5 +- include/linux/netfilter_ipv4/Kbuild | 5 +- include/linux/netfilter_ipv6/Kbuild | 5 +- include/linux/nfsd/Kbuild | 12 +- include/linux/sunrpc/Kbuild | 2 +- 10 files changed, 262 insertions(+), 268 deletions(-) (limited to 'include/linux') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index 9d65d4d0bd9c..626b629429ff 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -15,380 +15,380 @@ header-y += netfilter_bridge/ header-y += netfilter_ipv4/ header-y += netfilter_ipv6/ header-y += usb/ +header-y += wimax/ + +objhdr-y += version.h + +ifneq ($(wildcard $(srctree)/arch/$(SRCARCH)/include/asm/a.out.h \ + $(srctree)/include/asm-$(SRCARCH)/a.out.h),) +header-y += a.out.h +endif +ifneq ($(wildcard $(srctree)/arch/$(SRCARCH)/include/asm/kvm.h \ + $(srctree)/include/asm-$(SRCARCH)/kvm.h),) +header-y += kvm.h +endif +ifneq ($(wildcard $(srctree)/arch/$(SRCARCH)/include/asm/kvm_para.h \ + $(srctree)/include/asm-$(SRCARCH)/kvm_para.h),) +header-y += kvm_para.h +endif +header-y += acct.h +header-y += adb.h +header-y += adfs_fs.h header-y += affs_hardblocks.h +header-y += agpgart.h header-y += aio_abi.h +header-y += apm_bios.h header-y += arcfb.h +header-y += atalk.h +header-y += atm.h +header-y += atm_eni.h +header-y += atm_he.h +header-y += atm_idt77105.h +header-y += atm_nicstar.h +header-y += atm_tcp.h +header-y += atm_zatm.h header-y += atmapi.h header-y += atmarp.h header-y += atmbr2684.h header-y += atmclip.h -header-y += atm_eni.h -header-y += atm_he.h -header-y += atm_idt77105.h +header-y += atmdev.h header-y += atmioc.h header-y += atmlec.h header-y += atmmpc.h -header-y += atm_nicstar.h header-y += atmppp.h header-y += atmsap.h header-y += atmsvc.h -header-y += atm_zatm.h +header-y += audit.h +header-y += auto_fs.h header-y += auto_fs4.h +header-y += auxvec.h header-y += ax25.h header-y += b1lli.h header-y += baycom.h header-y += bfs_fs.h +header-y += binfmts.h header-y += blk_types.h header-y += blkpg.h +header-y += blktrace_api.h header-y += bpqether.h header-y += bsg.h header-y += can.h +header-y += capability.h +header-y += capi.h header-y += cciss_defs.h +header-y += cciss_ioctl.h header-y += cdk.h +header-y += cdrom.h +header-y += cgroupstats.h header-y += chio.h +header-y += cm4000_cs.h +header-y += cn_proc.h +header-y += coda.h header-y += coda_psdev.h header-y += coff.h header-y += comstats.h +header-y += connector.h header-y += const.h -header-y += cgroupstats.h header-y += cramfs_fs.h +header-y += cuda.h +header-y += cyclades.h header-y += cycx_cfm.h header-y += dcbnl.h -header-y += dlmconstants.h +header-y += dccp.h +header-y += dlm.h header-y += dlm_device.h header-y += dlm_netlink.h +header-y += dlm_plock.h +header-y += dlmconstants.h header-y += dm-ioctl.h header-y += dm-log-userspace.h header-y += dn.h header-y += dqblk_xfs.h +header-y += edd.h header-y += efs_fs_sb.h -header-y += elf-fdpic.h header-y += elf-em.h +header-y += elf-fdpic.h +header-y += elf.h +header-y += elfcore.h +header-y += errno.h +header-y += errqueue.h +header-y += ethtool.h +header-y += eventpoll.h +header-y += ext2_fs.h header-y += fadvise.h header-y += falloc.h +header-y += fanotify.h +header-y += fb.h +header-y += fcntl.h header-y += fd.h header-y += fdreg.h header-y += fib_rules.h header-y += fiemap.h +header-y += filter.h header-y += firewire-cdev.h header-y += firewire-constants.h +header-y += flat.h +header-y += fs.h header-y += fuse.h -header-y += genetlink.h +header-y += futex.h +header-y += gameport.h header-y += gen_stats.h +header-y += generic_serial.h +header-y += genetlink.h header-y += gfs2_ondisk.h header-y += gigaset_dev.h +header-y += hdlc.h +header-y += hdlcdrv.h +header-y += hdreg.h +header-y += hid.h +header-y += hiddev.h +header-y += hidraw.h +header-y += hpet.h header-y += hysdn_if.h +header-y += i2c-dev.h +header-y += i2c.h header-y += i2o-dev.h header-y += i8k.h +header-y += icmp.h +header-y += icmpv6.h +header-y += if.h +header-y += if_addr.h header-y += if_addrlabel.h header-y += if_arcnet.h +header-y += if_arp.h header-y += if_bonding.h +header-y += if_bridge.h header-y += if_cablemodem.h +header-y += if_ec.h +header-y += if_eql.h +header-y += if_ether.h header-y += if_fc.h -header-y += if.h +header-y += if_fddi.h +header-y += if_frad.h header-y += if_hippi.h header-y += if_infiniband.h +header-y += if_link.h +header-y += if_ltalk.h header-y += if_packet.h +header-y += if_phonet.h header-y += if_plip.h header-y += if_ppp.h +header-y += if_pppol2tp.h +header-y += if_pppox.h header-y += if_slip.h header-y += if_strip.h +header-y += if_tr.h header-y += if_tun.h +header-y += if_tunnel.h +header-y += if_vlan.h header-y += if_x25.h +header-y += igmp.h +header-y += in.h +header-y += in6.h header-y += in_route.h +header-y += inet_diag.h +header-y += inotify.h +header-y += input.h header-y += ioctl.h +header-y += ip.h header-y += ip6_tunnel.h +header-y += ip_vs.h +header-y += ipc.h +header-y += ipmi.h header-y += ipmi_msgdefs.h header-y += ipsec.h -header-y += ip_vs.h +header-y += ipv6.h +header-y += ipv6_route.h header-y += ipx.h header-y += irda.h +header-y += irqnr.h +header-y += isdn.h +header-y += isdn_divertif.h +header-y += isdn_ppp.h +header-y += isdnif.h header-y += iso_fs.h +header-y += ivtv.h +header-y += ivtvfb.h header-y += ixjuser.h header-y += jffs2.h +header-y += joystick.h +header-y += kd.h +header-y += kdev_t.h +header-y += kernel.h +header-y += kernelcapi.h +header-y += keyboard.h header-y += keyctl.h +header-y += l2tp.h header-y += limits.h +header-y += llc.h +header-y += loop.h +header-y += lp.h header-y += magic.h header-y += major.h header-y += map_to_7segment.h header-y += matroxfb.h +header-y += mempolicy.h header-y += meye.h +header-y += mii.h header-y += minix_fs.h +header-y += mman.h header-y += mmtimer.h header-y += mqueue.h +header-y += mroute.h +header-y += mroute6.h +header-y += msdos_fs.h +header-y += msg.h header-y += mtio.h +header-y += n_r3964.h +header-y += nbd.h +header-y += ncp.h +header-y += ncp_fs.h +header-y += ncp_mount.h header-y += ncp_no.h header-y += neighbour.h +header-y += net.h header-y += net_dropmon.h header-y += net_tstamp.h +header-y += netdevice.h +header-y += netfilter.h header-y += netfilter_arp.h +header-y += netfilter_bridge.h +header-y += netfilter_decnet.h +header-y += netfilter_ipv4.h +header-y += netfilter_ipv6.h +header-y += netlink.h header-y += netrom.h +header-y += nfs.h header-y += nfs2.h +header-y += nfs3.h +header-y += nfs4.h header-y += nfs4_mount.h +header-y += nfs_fs.h +header-y += nfs_idmap.h header-y += nfs_mount.h +header-y += nfsacl.h header-y += nl80211.h +header-y += nubus.h +header-y += nvram.h header-y += omapfb.h +header-y += oom.h header-y += param.h +header-y += parport.h +header-y += patchkey.h +header-y += pci.h header-y += pci_regs.h header-y += perf_event.h +header-y += personality.h header-y += pfkeyv2.h header-y += pg.h header-y += phantom.h header-y += phonet.h header-y += pkt_cls.h header-y += pkt_sched.h +header-y += pktcdvd.h +header-y += pmu.h +header-y += poll.h header-y += posix_types.h header-y += ppdev.h +header-y += ppp-comp.h +header-y += ppp_defs.h +header-y += pps.h header-y += prctl.h -header-y += qnxtypes.h +header-y += ptrace.h header-y += qnx4_fs.h +header-y += qnxtypes.h +header-y += quota.h header-y += radeonfb.h +header-y += random.h header-y += raw.h +header-y += reboot.h +header-y += reiserfs_fs.h +header-y += reiserfs_xattr.h header-y += resource.h +header-y += rfkill.h header-y += romfs_fs.h header-y += rose.h +header-y += route.h +header-y += rtc.h +header-y += rtnetlink.h +header-y += scc.h +header-y += sched.h +header-y += screen_info.h +header-y += sdla.h +header-y += securebits.h +header-y += selinux_netlink.h +header-y += sem.h +header-y += serial.h +header-y += serial_core.h header-y += serial_reg.h +header-y += serio.h +header-y += shm.h +header-y += signal.h +header-y += signalfd.h +header-y += smb.h +header-y += smb_fs.h +header-y += smb_mount.h header-y += smbno.h header-y += snmp.h +header-y += socket.h header-y += sockios.h header-y += som.h +header-y += sonet.h +header-y += sonypi.h header-y += sound.h +header-y += soundcard.h +header-y += stat.h +header-y += stddef.h +header-y += string.h header-y += suspend_ioctls.h +header-y += swab.h +header-y += synclink.h +header-y += sysctl.h header-y += taskstats.h +header-y += tcp.h header-y += telephony.h header-y += termios.h +header-y += time.h header-y += times.h +header-y += timex.h header-y += tiocl.h header-y += tipc.h header-y += tipc_config.h header-y += toshiba.h +header-y += tty.h +header-y += types.h header-y += udf_fs_i.h +header-y += udp.h +header-y += uinput.h +header-y += uio.h header-y += ultrasound.h header-y += un.h +header-y += unistd.h +header-y += usbdevice_fs.h header-y += utime.h +header-y += utsname.h header-y += veth.h +header-y += vhost.h +header-y += videodev.h +header-y += videodev2.h header-y += videotext.h -header-y += x25.h - -unifdef-y += acct.h -unifdef-y += adb.h -unifdef-y += adfs_fs.h -unifdef-y += agpgart.h -ifneq ($(wildcard $(srctree)/arch/$(SRCARCH)/include/asm/a.out.h \ - $(srctree)/include/asm-$(SRCARCH)/a.out.h),) -unifdef-y += a.out.h -endif -unifdef-y += apm_bios.h -unifdef-y += atalk.h -unifdef-y += atmdev.h -unifdef-y += atm.h -unifdef-y += atm_tcp.h -unifdef-y += audit.h -unifdef-y += auto_fs.h -unifdef-y += auxvec.h -unifdef-y += binfmts.h -unifdef-y += blktrace_api.h -unifdef-y += capability.h -unifdef-y += capi.h -unifdef-y += cciss_ioctl.h -unifdef-y += cdrom.h -unifdef-y += cm4000_cs.h -unifdef-y += cn_proc.h -unifdef-y += coda.h -unifdef-y += connector.h -unifdef-y += cuda.h -unifdef-y += cyclades.h -unifdef-y += dccp.h -unifdef-y += dlm.h -unifdef-y += dlm_plock.h -unifdef-y += edd.h -unifdef-y += elf.h -unifdef-y += elfcore.h -unifdef-y += errno.h -unifdef-y += errqueue.h -unifdef-y += ethtool.h -unifdef-y += eventpoll.h -unifdef-y += signalfd.h -unifdef-y += ext2_fs.h -unifdef-y += fanotify.h -unifdef-y += fb.h -unifdef-y += fcntl.h -unifdef-y += filter.h -unifdef-y += flat.h -unifdef-y += futex.h -unifdef-y += fs.h -unifdef-y += gameport.h -unifdef-y += generic_serial.h -unifdef-y += hdlcdrv.h -unifdef-y += hdlc.h -unifdef-y += hdreg.h -unifdef-y += hid.h -unifdef-y += hiddev.h -unifdef-y += hidraw.h -unifdef-y += hpet.h -unifdef-y += i2c.h -unifdef-y += i2c-dev.h -unifdef-y += icmp.h -unifdef-y += icmpv6.h -unifdef-y += if_addr.h -unifdef-y += if_arp.h -unifdef-y += if_bridge.h -unifdef-y += if_ec.h -unifdef-y += if_eql.h -unifdef-y += if_ether.h -unifdef-y += if_fddi.h -unifdef-y += if_frad.h -unifdef-y += if_ltalk.h -unifdef-y += if_link.h -unifdef-y += if_phonet.h -unifdef-y += if_pppol2tp.h -unifdef-y += if_pppox.h -unifdef-y += if_tr.h -unifdef-y += if_tunnel.h -unifdef-y += if_vlan.h -unifdef-y += igmp.h -unifdef-y += inet_diag.h -unifdef-y += in.h -unifdef-y += in6.h -unifdef-y += inotify.h -unifdef-y += input.h -unifdef-y += ip.h -unifdef-y += ipc.h -unifdef-y += ipmi.h -unifdef-y += ipv6.h -unifdef-y += ipv6_route.h -unifdef-y += isdn.h -unifdef-y += isdnif.h -unifdef-y += isdn_divertif.h -unifdef-y += isdn_ppp.h -unifdef-y += ivtv.h -unifdef-y += ivtvfb.h -unifdef-y += joystick.h -unifdef-y += kdev_t.h -unifdef-y += kd.h -unifdef-y += kernelcapi.h -unifdef-y += kernel.h -unifdef-y += keyboard.h -ifneq ($(wildcard $(srctree)/arch/$(SRCARCH)/include/asm/kvm.h \ - $(srctree)/include/asm-$(SRCARCH)/kvm.h),) -unifdef-y += kvm.h -endif -ifneq ($(wildcard $(srctree)/arch/$(SRCARCH)/include/asm/kvm_para.h \ - $(srctree)/include/asm-$(SRCARCH)/kvm_para.h),) -unifdef-y += kvm_para.h -endif -unifdef-y += l2tp.h -unifdef-y += llc.h -unifdef-y += loop.h -unifdef-y += lp.h -unifdef-y += mempolicy.h -unifdef-y += mii.h -unifdef-y += mman.h -unifdef-y += mroute.h -unifdef-y += mroute6.h -unifdef-y += msdos_fs.h -unifdef-y += msg.h -unifdef-y += nbd.h -unifdef-y += ncp_fs.h -unifdef-y += ncp.h -unifdef-y += ncp_mount.h -unifdef-y += netdevice.h -unifdef-y += netfilter_bridge.h -unifdef-y += netfilter_decnet.h -unifdef-y += netfilter.h -unifdef-y += netfilter_ipv4.h -unifdef-y += netfilter_ipv6.h -unifdef-y += net.h -unifdef-y += netlink.h -unifdef-y += nfs3.h -unifdef-y += nfs4.h -unifdef-y += nfsacl.h -unifdef-y += nfs_fs.h -unifdef-y += nfs.h -unifdef-y += nfs_idmap.h -unifdef-y += n_r3964.h -unifdef-y += nubus.h -unifdef-y += nvram.h -unifdef-y += oom.h -unifdef-y += parport.h -unifdef-y += patchkey.h -unifdef-y += pci.h -unifdef-y += personality.h -unifdef-y += pktcdvd.h -unifdef-y += pmu.h -unifdef-y += poll.h -unifdef-y += ppp_defs.h -unifdef-y += ppp-comp.h -unifdef-y += pps.h -unifdef-y += ptrace.h -unifdef-y += quota.h -unifdef-y += random.h -unifdef-y += rfkill.h -unifdef-y += irqnr.h -unifdef-y += reboot.h -unifdef-y += reiserfs_fs.h -unifdef-y += reiserfs_xattr.h -unifdef-y += route.h -unifdef-y += rtc.h -unifdef-y += rtnetlink.h -unifdef-y += scc.h -unifdef-y += sched.h -unifdef-y += screen_info.h -unifdef-y += sdla.h -unifdef-y += securebits.h -unifdef-y += selinux_netlink.h -unifdef-y += sem.h -unifdef-y += serial_core.h -unifdef-y += serial.h -unifdef-y += serio.h -unifdef-y += shm.h -unifdef-y += signal.h -unifdef-y += smb_fs.h -unifdef-y += smb.h -unifdef-y += smb_mount.h -unifdef-y += socket.h -unifdef-y += sonet.h -unifdef-y += sonypi.h -unifdef-y += soundcard.h -unifdef-y += stat.h -unifdef-y += stddef.h -unifdef-y += string.h -unifdef-y += swab.h -unifdef-y += synclink.h -unifdef-y += sysctl.h -unifdef-y += tcp.h -unifdef-y += time.h -unifdef-y += timex.h -unifdef-y += tty.h -unifdef-y += types.h -unifdef-y += udp.h -unifdef-y += uinput.h -unifdef-y += uio.h -unifdef-y += unistd.h -unifdef-y += usbdevice_fs.h -unifdef-y += utsname.h -unifdef-y += vhost.h -unifdef-y += videodev2.h -unifdef-y += videodev.h -unifdef-y += virtio_config.h -unifdef-y += virtio_ids.h -unifdef-y += virtio_blk.h -unifdef-y += virtio_net.h -unifdef-y += virtio_9p.h -unifdef-y += virtio_balloon.h -unifdef-y += virtio_console.h -unifdef-y += virtio_pci.h -unifdef-y += virtio_ring.h -unifdef-y += virtio_rng.h -unifdef-y += vt.h -unifdef-y += wait.h -unifdef-y += wanrouter.h -unifdef-y += watchdog.h -unifdef-y += wireless.h -unifdef-y += xattr.h -unifdef-y += xfrm.h - -objhdr-y += version.h +header-y += virtio_9p.h +header-y += virtio_balloon.h +header-y += virtio_blk.h +header-y += virtio_config.h +header-y += virtio_console.h +header-y += virtio_ids.h +header-y += virtio_net.h +header-y += virtio_pci.h +header-y += virtio_ring.h +header-y += virtio_rng.h +header-y += vt.h +header-y += wait.h +header-y += wanrouter.h +header-y += watchdog.h header-y += wimax.h -header-y += wimax/ +header-y += wireless.h +header-y += x25.h +header-y += xattr.h +header-y += xfrm.h diff --git a/include/linux/byteorder/Kbuild b/include/linux/byteorder/Kbuild index 38437225b092..5896e344ba6c 100644 --- a/include/linux/byteorder/Kbuild +++ b/include/linux/byteorder/Kbuild @@ -1,2 +1,2 @@ -unifdef-y += big_endian.h -unifdef-y += little_endian.h +header-y += big_endian.h +header-y += little_endian.h diff --git a/include/linux/dvb/Kbuild b/include/linux/dvb/Kbuild index d97b3a51e227..f4dba8637f98 100644 --- a/include/linux/dvb/Kbuild +++ b/include/linux/dvb/Kbuild @@ -1,9 +1,8 @@ +header-y += audio.h header-y += ca.h +header-y += dmx.h header-y += frontend.h header-y += net.h header-y += osd.h header-y += version.h - -unifdef-y += audio.h -unifdef-y += dmx.h -unifdef-y += video.h +header-y += video.h diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild index edeeabdc1500..9d40effe7ca7 100644 --- a/include/linux/netfilter/Kbuild +++ b/include/linux/netfilter/Kbuild @@ -1,8 +1,14 @@ +header-y += nf_conntrack_common.h +header-y += nf_conntrack_ftp.h header-y += nf_conntrack_sctp.h +header-y += nf_conntrack_tcp.h header-y += nf_conntrack_tuple_common.h +header-y += nfnetlink.h +header-y += nfnetlink_compat.h header-y += nfnetlink_conntrack.h header-y += nfnetlink_log.h header-y += nfnetlink_queue.h +header-y += x_tables.h header-y += xt_CHECKSUM.h header-y += xt_CLASSIFY.h header-y += xt_CONNMARK.h @@ -31,9 +37,9 @@ header-y += xt_dccp.h header-y += xt_dscp.h header-y += xt_esp.h header-y += xt_hashlimit.h +header-y += xt_helper.h header-y += xt_iprange.h header-y += xt_ipvs.h -header-y += xt_helper.h header-y += xt_length.h header-y += xt_limit.h header-y += xt_mac.h @@ -41,7 +47,9 @@ header-y += xt_mark.h header-y += xt_multiport.h header-y += xt_osf.h header-y += xt_owner.h +header-y += xt_physdev.h header-y += xt_pkttype.h +header-y += xt_policy.h header-y += xt_quota.h header-y += xt_rateest.h header-y += xt_realm.h @@ -54,12 +62,3 @@ header-y += xt_tcpmss.h header-y += xt_tcpudp.h header-y += xt_time.h header-y += xt_u32.h - -unifdef-y += nf_conntrack_common.h -unifdef-y += nf_conntrack_ftp.h -unifdef-y += nf_conntrack_tcp.h -unifdef-y += nfnetlink.h -unifdef-y += nfnetlink_compat.h -unifdef-y += x_tables.h -unifdef-y += xt_physdev.h -unifdef-y += xt_policy.h diff --git a/include/linux/netfilter_arp/Kbuild b/include/linux/netfilter_arp/Kbuild index 4f13dfcb92ea..b27439c71037 100644 --- a/include/linux/netfilter_arp/Kbuild +++ b/include/linux/netfilter_arp/Kbuild @@ -1,3 +1,2 @@ +header-y += arp_tables.h header-y += arpt_mangle.h - -unifdef-y += arp_tables.h diff --git a/include/linux/netfilter_bridge/Kbuild b/include/linux/netfilter_bridge/Kbuild index 76ff4c47d8c4..d4d78672873e 100644 --- a/include/linux/netfilter_bridge/Kbuild +++ b/include/linux/netfilter_bridge/Kbuild @@ -1,3 +1,4 @@ +header-y += ebt_802_3.h header-y += ebt_among.h header-y += ebt_arp.h header-y += ebt_arpreply.h @@ -12,6 +13,4 @@ header-y += ebt_redirect.h header-y += ebt_stp.h header-y += ebt_ulog.h header-y += ebt_vlan.h - -unifdef-y += ebtables.h -unifdef-y += ebt_802_3.h +header-y += ebtables.h diff --git a/include/linux/netfilter_ipv4/Kbuild b/include/linux/netfilter_ipv4/Kbuild index 431b40761920..f9930c87fff3 100644 --- a/include/linux/netfilter_ipv4/Kbuild +++ b/include/linux/netfilter_ipv4/Kbuild @@ -1,3 +1,5 @@ +header-y += ip_queue.h +header-y += ip_tables.h header-y += ipt_CLUSTERIP.h header-y += ipt_ECN.h header-y += ipt_LOG.h @@ -10,6 +12,3 @@ header-y += ipt_ah.h header-y += ipt_ecn.h header-y += ipt_realm.h header-y += ipt_ttl.h - -unifdef-y += ip_queue.h -unifdef-y += ip_tables.h diff --git a/include/linux/netfilter_ipv6/Kbuild b/include/linux/netfilter_ipv6/Kbuild index e864eaee9e5e..bd095bc075e9 100644 --- a/include/linux/netfilter_ipv6/Kbuild +++ b/include/linux/netfilter_ipv6/Kbuild @@ -1,12 +1,11 @@ +header-y += ip6_tables.h header-y += ip6t_HL.h header-y += ip6t_LOG.h header-y += ip6t_REJECT.h header-y += ip6t_ah.h header-y += ip6t_frag.h -header-y += ip6t_ipv6header.h header-y += ip6t_hl.h +header-y += ip6t_ipv6header.h header-y += ip6t_mh.h header-y += ip6t_opts.h header-y += ip6t_rt.h - -unifdef-y += ip6_tables.h diff --git a/include/linux/nfsd/Kbuild b/include/linux/nfsd/Kbuild index fc972048e572..55d1467de3c1 100644 --- a/include/linux/nfsd/Kbuild +++ b/include/linux/nfsd/Kbuild @@ -1,6 +1,6 @@ -unifdef-y += const.h -unifdef-y += debug.h -unifdef-y += export.h -unifdef-y += nfsfh.h -unifdef-y += stats.h -unifdef-y += syscall.h +header-y += const.h +header-y += debug.h +header-y += export.h +header-y += nfsfh.h +header-y += stats.h +header-y += syscall.h diff --git a/include/linux/sunrpc/Kbuild b/include/linux/sunrpc/Kbuild index fb438f158eee..98df21164a86 100644 --- a/include/linux/sunrpc/Kbuild +++ b/include/linux/sunrpc/Kbuild @@ -1 +1 @@ -unifdef-y += debug.h +header-y += debug.h -- cgit v1.2.3 From 99c796df94afca5256860dd4760017f1dbb3480c Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 17 Aug 2010 22:13:22 +0100 Subject: VIDEO: amba clcd: don't disable an already disabled clock Fix the clock enable/disable tracking in the AMBA CLCD driver so that the driver doesn't try to disable an already disabled clock, thereby causing the clock (if shared) to become unbalanced. This resolves a problem with CLCD on LPC32xx ARM platforms. Reported-by: Kevin Wells Signed-off-by: Russell King --- include/linux/amba/clcd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/amba/clcd.h b/include/linux/amba/clcd.h index ca16c3801a1e..be33b3affc8a 100644 --- a/include/linux/amba/clcd.h +++ b/include/linux/amba/clcd.h @@ -150,6 +150,7 @@ struct clcd_fb { u16 off_cntl; u32 clcd_cntl; u32 cmap[16]; + bool clk_enabled; }; static inline void clcdfb_decode(struct clcd_fb *fb, struct clcd_regs *regs) -- cgit v1.2.3 From d7627467b7a8dd6944885290a03a07ceb28c10eb Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 17 Aug 2010 23:52:56 +0100 Subject: Make do_execve() take a const filename pointer Make do_execve() take a const filename pointer so that kernel_execve() compiles correctly on ARM: arch/arm/kernel/sys_arm.c:88: warning: passing argument 1 of 'do_execve' discards qualifiers from pointer target type This also requires the argv and envp arguments to be consted twice, once for the pointer array and once for the strings the array points to. This is because do_execve() passes a pointer to the filename (now const) to copy_strings_kernel(). A simpler alternative would be to cast the filename pointer in do_execve() when it's passed to copy_strings_kernel(). do_execve() may not change any of the strings it is passed as part of the argv or envp lists as they are some of them in .rodata, so marking these strings as const should be fine. Further kernel_execve() and sys_execve() need to be changed to match. This has been test built on x86_64, frv, arm and mips. Signed-off-by: David Howells Tested-by: Ralf Baechle Acked-by: Russell King Signed-off-by: Linus Torvalds --- include/linux/binfmts.h | 7 ++++--- include/linux/sched.h | 4 +++- include/linux/syscalls.h | 2 +- 3 files changed, 8 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index c809e286d213..a065612fc928 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -50,8 +50,8 @@ struct linux_binprm{ int unsafe; /* how unsafe this exec is (mask of LSM_UNSAFE_*) */ unsigned int per_clear; /* bits to clear in current->personality */ int argc, envc; - char * filename; /* Name of binary as seen by procps */ - char * interp; /* Name of the binary really executed. Most + const char * filename; /* Name of binary as seen by procps */ + const char * interp; /* Name of the binary really executed. Most of the time same as filename, but could be different for binfmt_{misc,script} */ unsigned interp_flags; @@ -126,7 +126,8 @@ extern int setup_arg_pages(struct linux_binprm * bprm, unsigned long stack_top, int executable_stack); extern int bprm_mm_init(struct linux_binprm *bprm); -extern int copy_strings_kernel(int argc,char ** argv,struct linux_binprm *bprm); +extern int copy_strings_kernel(int argc, const char *const *argv, + struct linux_binprm *bprm); extern int prepare_bprm_creds(struct linux_binprm *bprm); extern void install_exec_creds(struct linux_binprm *bprm); extern void do_coredump(long signr, int exit_code, struct pt_regs *regs); diff --git a/include/linux/sched.h b/include/linux/sched.h index ce160d68f5e7..1e2a6db2d7dd 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2109,7 +2109,9 @@ extern void daemonize(const char *, ...); extern int allow_signal(int); extern int disallow_signal(int); -extern int do_execve(char *, char __user * __user *, char __user * __user *, struct pt_regs *); +extern int do_execve(const char *, + const char __user * const __user *, + const char __user * const __user *, struct pt_regs *); extern long do_fork(unsigned long, unsigned long, struct pt_regs *, unsigned long, int __user *, int __user *); struct task_struct *fork_idle(int); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 6e5d19788634..e6319d18a55d 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -820,7 +820,7 @@ asmlinkage long sys_fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int fd, const char __user *pathname); -int kernel_execve(const char *filename, char *const argv[], char *const envp[]); +int kernel_execve(const char *filename, const char *const argv[], const char *const envp[]); asmlinkage long sys_perf_event_open( -- cgit v1.2.3 From 5c79a5ae23e72fa12f1c7c528f62bf3ea35da0dc Mon Sep 17 00:00:00 2001 From: Ernst Schwab Date: Mon, 16 Aug 2010 15:10:11 +0200 Subject: spi.h: missing kernel-doc notation, please fix Added comments in kernel-doc notation for previously added struct fields. Signed-off-by: Ernst Schwab Acked-by: Randy Dunlap Signed-off-by: Grant Likely --- include/linux/spi/spi.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index ae0a5286f558..92e52a1e6af3 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -213,6 +213,9 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * @dma_alignment: SPI controller constraint on DMA buffers alignment. * @mode_bits: flags understood by this controller driver * @flags: other constraints relevant to this driver + * @bus_lock_spinlock: spinlock for SPI bus locking + * @bus_lock_mutex: mutex for SPI bus locking + * @bus_lock_flag: indicates that the SPI bus is locked for exclusive use * @setup: updates the device mode and clocking records used by a * device's SPI controller; protocol code may call this. This * must fail if an unrecognized or unsupported mode is requested. -- cgit v1.2.3 From 87e99511ea54510ffb60b98001d108794d5037f8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 11 Aug 2010 17:05:45 +0200 Subject: kill BH_Ordered flag Instead of abusing a buffer_head flag just add a variant of sync_dirty_buffer which allows passing the exact type of write flag required. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/buffer_head.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 43e649a72529..72c1cf83eb85 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -32,7 +32,6 @@ enum bh_state_bits { BH_Delay, /* Buffer is not yet allocated on disk */ BH_Boundary, /* Block is followed by a discontiguity */ BH_Write_EIO, /* I/O error on write */ - BH_Ordered, /* ordered write */ BH_Eopnotsupp, /* operation not supported (barrier) */ BH_Unwritten, /* Buffer is allocated on disk but not written */ BH_Quiet, /* Buffer Error Prinks to be quiet */ @@ -125,7 +124,6 @@ BUFFER_FNS(Async_Write, async_write) BUFFER_FNS(Delay, delay) BUFFER_FNS(Boundary, boundary) BUFFER_FNS(Write_EIO, write_io_error) -BUFFER_FNS(Ordered, ordered) BUFFER_FNS(Eopnotsupp, eopnotsupp) BUFFER_FNS(Unwritten, unwritten) @@ -183,6 +181,7 @@ void unlock_buffer(struct buffer_head *bh); void __lock_buffer(struct buffer_head *bh); void ll_rw_block(int, int, struct buffer_head * bh[]); int sync_dirty_buffer(struct buffer_head *bh); +int __sync_dirty_buffer(struct buffer_head *bh, int rw); int submit_bh(int, struct buffer_head *); void write_boundary_block(struct block_device *bdev, sector_t bblock, unsigned blocksize); -- cgit v1.2.3 From 9cb569d601e0b93e01c20a22872270ec663b75f6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 11 Aug 2010 17:06:24 +0200 Subject: remove SWRITE* I/O types These flags aren't real I/O types, but tell ll_rw_block to always lock the buffer instead of giving up on a failed trylock. Instead add a new write_dirty_buffer helper that implements this semantic and use it from the existing SWRITE* callers. Note that the ll_rw_block code had a bug where it didn't promote WRITE_SYNC_PLUG properly, which this patch fixes. In the ufs code clean up the helper that used to call ll_rw_block to mirror sync_dirty_buffer, which is the function it implements for compound buffers. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/buffer_head.h | 1 + include/linux/fs.h | 9 --------- 2 files changed, 1 insertion(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 72c1cf83eb85..ec94c12f21da 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -182,6 +182,7 @@ void __lock_buffer(struct buffer_head *bh); void ll_rw_block(int, int, struct buffer_head * bh[]); int sync_dirty_buffer(struct buffer_head *bh); int __sync_dirty_buffer(struct buffer_head *bh, int rw); +void write_dirty_buffer(struct buffer_head *bh, int rw); int submit_bh(int, struct buffer_head *); void write_boundary_block(struct block_device *bdev, sector_t bblock, unsigned blocksize); diff --git a/include/linux/fs.h b/include/linux/fs.h index 9a96b4d83fc1..29f7c975304c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -125,9 +125,6 @@ struct inodes_stat_t { * block layer could (in theory) choose to ignore this * request if it runs into resource problems. * WRITE A normal async write. Device will be plugged. - * SWRITE Like WRITE, but a special case for ll_rw_block() that - * tells it to lock the buffer first. Normally a buffer - * must be locked before doing IO. * WRITE_SYNC_PLUG Synchronous write. Identical to WRITE, but passes down * the hint that someone will be waiting on this IO * shortly. The device must still be unplugged explicitly, @@ -138,9 +135,6 @@ struct inodes_stat_t { * immediately after submission. The write equivalent * of READ_SYNC. * WRITE_ODIRECT_PLUG Special case write for O_DIRECT only. - * SWRITE_SYNC - * SWRITE_SYNC_PLUG Like WRITE_SYNC/WRITE_SYNC_PLUG, but locks the buffer. - * See SWRITE. * WRITE_BARRIER Like WRITE_SYNC, but tells the block layer that all * previously submitted writes must be safely on storage * before this one is started. Also guarantees that when @@ -155,7 +149,6 @@ struct inodes_stat_t { #define READ 0 #define WRITE RW_MASK #define READA RWA_MASK -#define SWRITE (WRITE | READA) #define READ_SYNC (READ | REQ_SYNC | REQ_UNPLUG) #define READ_META (READ | REQ_META) @@ -165,8 +158,6 @@ struct inodes_stat_t { #define WRITE_META (WRITE | REQ_META) #define WRITE_BARRIER (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \ REQ_HARDBARRIER) -#define SWRITE_SYNC_PLUG (SWRITE | REQ_SYNC | REQ_NOIDLE) -#define SWRITE_SYNC (SWRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG) /* * These aren't really reads or writes, they pass down information about -- cgit v1.2.3 From 2a4419b5b2a77f3f4537c14f7ad7df95770655dd Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 18 Aug 2010 04:37:33 +1000 Subject: fs: fs_struct rwlock to spinlock fs: fs_struct rwlock to spinlock struct fs_struct.lock is an rwlock with the read-side used to protect root and pwd members while taking references to them. Taking a reference to a path typically requires just 2 atomic ops, so the critical section is very small. Parallel read-side operations would have cacheline contention on the lock, the dentry, and the vfsmount cachelines, so the rwlock is unlikely to ever give a real parallelism increase. Replace it with a spinlock to avoid one or two atomic operations in typical path lookup fastpath. Signed-off-by: Nick Piggin Signed-off-by: Al Viro --- include/linux/fs_struct.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h index eca3d5202138..a42b5bf02f8b 100644 --- a/include/linux/fs_struct.h +++ b/include/linux/fs_struct.h @@ -5,7 +5,7 @@ struct fs_struct { int users; - rwlock_t lock; + spinlock_t lock; int umask; int in_exec; struct path root, pwd; @@ -23,29 +23,29 @@ extern int unshare_fs_struct(void); static inline void get_fs_root(struct fs_struct *fs, struct path *root) { - read_lock(&fs->lock); + spin_lock(&fs->lock); *root = fs->root; path_get(root); - read_unlock(&fs->lock); + spin_unlock(&fs->lock); } static inline void get_fs_pwd(struct fs_struct *fs, struct path *pwd) { - read_lock(&fs->lock); + spin_lock(&fs->lock); *pwd = fs->pwd; path_get(pwd); - read_unlock(&fs->lock); + spin_unlock(&fs->lock); } static inline void get_fs_root_and_pwd(struct fs_struct *fs, struct path *root, struct path *pwd) { - read_lock(&fs->lock); + spin_lock(&fs->lock); *root = fs->root; path_get(root); *pwd = fs->pwd; path_get(pwd); - read_unlock(&fs->lock); + spin_unlock(&fs->lock); } #endif /* _LINUX_FS_STRUCT_H */ -- cgit v1.2.3 From ee2ffa0dfdd2db19705f2ba1c6a4c0bfe8122dd8 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 18 Aug 2010 04:37:35 +1000 Subject: fs: cleanup files_lock locking fs: cleanup files_lock locking Lock tty_files with a new spinlock, tty_files_lock; provide helpers to manipulate the per-sb files list; unexport the files_lock spinlock. Cc: linux-kernel@vger.kernel.org Cc: Christoph Hellwig Cc: Alan Cox Acked-by: Andi Kleen Acked-by: Greg Kroah-Hartman Signed-off-by: Nick Piggin Signed-off-by: Al Viro --- include/linux/fs.h | 7 ++----- include/linux/tty.h | 1 + 2 files changed, 3 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 29f7c975304c..5a9a9e5a3705 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -944,9 +944,6 @@ struct file { unsigned long f_mnt_write_state; #endif }; -extern spinlock_t files_lock; -#define file_list_lock() spin_lock(&files_lock); -#define file_list_unlock() spin_unlock(&files_lock); #define get_file(x) atomic_long_inc(&(x)->f_count) #define fput_atomic(x) atomic_long_add_unless(&(x)->f_count, -1, 1) @@ -2188,8 +2185,8 @@ static inline void insert_inode_hash(struct inode *inode) { __insert_inode_hash(inode, inode->i_ino); } -extern void file_move(struct file *f, struct list_head *list); -extern void file_kill(struct file *f); +extern void file_sb_list_add(struct file *f, struct super_block *sb); +extern void file_sb_list_del(struct file *f); #ifdef CONFIG_BLOCK extern void submit_bio(int, struct bio *); extern int bdev_read_only(struct block_device *); diff --git a/include/linux/tty.h b/include/linux/tty.h index 1437da3ddc62..f6b371a2514e 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -470,6 +470,7 @@ extern struct tty_struct *tty_pair_get_tty(struct tty_struct *tty); extern struct tty_struct *tty_pair_get_pty(struct tty_struct *tty); extern struct mutex tty_mutex; +extern spinlock_t tty_files_lock; extern void tty_write_unlock(struct tty_struct *tty); extern int tty_write_lock(struct tty_struct *tty, int ndelay); -- cgit v1.2.3 From d996b62a8df1d935b01319bf8defb95b5709f7b8 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 18 Aug 2010 04:37:36 +1000 Subject: tty: fix fu_list abuse tty: fix fu_list abuse tty code abuses fu_list, which causes a bug in remount,ro handling. If a tty device node is opened on a filesystem, then the last link to the inode removed, the filesystem will be allowed to be remounted readonly. This is because fs_may_remount_ro does not find the 0 link tty inode on the file sb list (because the tty code incorrectly removed it to use for its own purpose). This can result in a filesystem with errors after it is marked "clean". Taking idea from Christoph's initial patch, allocate a tty private struct at file->private_data and put our required list fields in there, linking file and tty. This makes tty nodes behave the same way as other device nodes and avoid meddling with the vfs, and avoids this bug. The error handling is not trivial in the tty code, so for this bugfix, I take the simple approach of using __GFP_NOFAIL and don't worry about memory errors. This is not a problem because our allocator doesn't fail small allocs as a rule anyway. So proper error handling is left as an exercise for tty hackers. [ Arguably filesystem's device inode would ideally be divorced from the driver's pseudo inode when it is opened, but in practice it's not clear whether that will ever be worth implementing. ] Cc: linux-kernel@vger.kernel.org Cc: Christoph Hellwig Cc: Alan Cox Cc: Greg Kroah-Hartman Signed-off-by: Nick Piggin Signed-off-by: Al Viro --- include/linux/fs.h | 2 -- include/linux/tty.h | 8 ++++++++ 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 5a9a9e5a3705..5e65add0f163 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2185,8 +2185,6 @@ static inline void insert_inode_hash(struct inode *inode) { __insert_inode_hash(inode, inode->i_ino); } -extern void file_sb_list_add(struct file *f, struct super_block *sb); -extern void file_sb_list_del(struct file *f); #ifdef CONFIG_BLOCK extern void submit_bio(int, struct bio *); extern int bdev_read_only(struct block_device *); diff --git a/include/linux/tty.h b/include/linux/tty.h index f6b371a2514e..67d64e6efe7a 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -329,6 +329,13 @@ struct tty_struct { struct tty_port *port; }; +/* Each of a tty's open files has private_data pointing to tty_file_private */ +struct tty_file_private { + struct tty_struct *tty; + struct file *file; + struct list_head list; +}; + /* tty magic number */ #define TTY_MAGIC 0x5401 @@ -458,6 +465,7 @@ extern void proc_clear_tty(struct task_struct *p); extern struct tty_struct *get_current_tty(void); extern void tty_default_fops(struct file_operations *fops); extern struct tty_struct *alloc_tty_struct(void); +extern void tty_add_file(struct tty_struct *tty, struct file *file); extern void free_tty_struct(struct tty_struct *tty); extern void initialize_tty_struct(struct tty_struct *tty, struct tty_driver *driver, int idx); -- cgit v1.2.3 From 2dc91abe03d8ce6dd7f9251faffafca5f6b9e85d Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 18 Aug 2010 04:37:37 +1000 Subject: lglock: introduce special lglock and brlock spin locks lglock: introduce special lglock and brlock spin locks This patch introduces "local-global" locks (lglocks). These can be used to: - Provide fast exclusive access to per-CPU data, with exclusive access to another CPU's data allowed but possibly subject to contention, and to provide very slow exclusive access to all per-CPU data. - Or to provide very fast and scalable read serialisation, and to provide very slow exclusive serialisation of data (not necessarily per-CPU data). Brlocks are also implemented as a short-hand notation for the latter use case. Thanks to Paul for local/global naming convention. Cc: linux-kernel@vger.kernel.org Cc: Al Viro Cc: "Paul E. McKenney" Signed-off-by: Nick Piggin Signed-off-by: Al Viro --- include/linux/lglock.h | 172 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 172 insertions(+) create mode 100644 include/linux/lglock.h (limited to 'include/linux') diff --git a/include/linux/lglock.h b/include/linux/lglock.h new file mode 100644 index 000000000000..b288cb713b90 --- /dev/null +++ b/include/linux/lglock.h @@ -0,0 +1,172 @@ +/* + * Specialised local-global spinlock. Can only be declared as global variables + * to avoid overhead and keep things simple (and we don't want to start using + * these inside dynamically allocated structures). + * + * "local/global locks" (lglocks) can be used to: + * + * - Provide fast exclusive access to per-CPU data, with exclusive access to + * another CPU's data allowed but possibly subject to contention, and to + * provide very slow exclusive access to all per-CPU data. + * - Or to provide very fast and scalable read serialisation, and to provide + * very slow exclusive serialisation of data (not necessarily per-CPU data). + * + * Brlocks are also implemented as a short-hand notation for the latter use + * case. + * + * Copyright 2009, 2010, Nick Piggin, Novell Inc. + */ +#ifndef __LINUX_LGLOCK_H +#define __LINUX_LGLOCK_H + +#include +#include +#include + +/* can make br locks by using local lock for read side, global lock for write */ +#define br_lock_init(name) name##_lock_init() +#define br_read_lock(name) name##_local_lock() +#define br_read_unlock(name) name##_local_unlock() +#define br_write_lock(name) name##_global_lock_online() +#define br_write_unlock(name) name##_global_unlock_online() + +#define DECLARE_BRLOCK(name) DECLARE_LGLOCK(name) +#define DEFINE_BRLOCK(name) DEFINE_LGLOCK(name) + + +#define lg_lock_init(name) name##_lock_init() +#define lg_local_lock(name) name##_local_lock() +#define lg_local_unlock(name) name##_local_unlock() +#define lg_local_lock_cpu(name, cpu) name##_local_lock_cpu(cpu) +#define lg_local_unlock_cpu(name, cpu) name##_local_unlock_cpu(cpu) +#define lg_global_lock(name) name##_global_lock() +#define lg_global_unlock(name) name##_global_unlock() +#define lg_global_lock_online(name) name##_global_lock_online() +#define lg_global_unlock_online(name) name##_global_unlock_online() + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +#define LOCKDEP_INIT_MAP lockdep_init_map + +#define DEFINE_LGLOCK_LOCKDEP(name) \ + struct lock_class_key name##_lock_key; \ + struct lockdep_map name##_lock_dep_map; \ + EXPORT_SYMBOL(name##_lock_dep_map) + +#else +#define LOCKDEP_INIT_MAP(a, b, c, d) + +#define DEFINE_LGLOCK_LOCKDEP(name) +#endif + + +#define DECLARE_LGLOCK(name) \ + extern void name##_lock_init(void); \ + extern void name##_local_lock(void); \ + extern void name##_local_unlock(void); \ + extern void name##_local_lock_cpu(int cpu); \ + extern void name##_local_unlock_cpu(int cpu); \ + extern void name##_global_lock(void); \ + extern void name##_global_unlock(void); \ + extern void name##_global_lock_online(void); \ + extern void name##_global_unlock_online(void); \ + +#define DEFINE_LGLOCK(name) \ + \ + DEFINE_PER_CPU(arch_spinlock_t, name##_lock); \ + DEFINE_LGLOCK_LOCKDEP(name); \ + \ + void name##_lock_init(void) { \ + int i; \ + LOCKDEP_INIT_MAP(&name##_lock_dep_map, #name, &name##_lock_key, 0); \ + for_each_possible_cpu(i) { \ + arch_spinlock_t *lock; \ + lock = &per_cpu(name##_lock, i); \ + *lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; \ + } \ + } \ + EXPORT_SYMBOL(name##_lock_init); \ + \ + void name##_local_lock(void) { \ + arch_spinlock_t *lock; \ + preempt_disable(); \ + rwlock_acquire_read(&name##_lock_dep_map, 0, 0, _THIS_IP_); \ + lock = &__get_cpu_var(name##_lock); \ + arch_spin_lock(lock); \ + } \ + EXPORT_SYMBOL(name##_local_lock); \ + \ + void name##_local_unlock(void) { \ + arch_spinlock_t *lock; \ + rwlock_release(&name##_lock_dep_map, 1, _THIS_IP_); \ + lock = &__get_cpu_var(name##_lock); \ + arch_spin_unlock(lock); \ + preempt_enable(); \ + } \ + EXPORT_SYMBOL(name##_local_unlock); \ + \ + void name##_local_lock_cpu(int cpu) { \ + arch_spinlock_t *lock; \ + preempt_disable(); \ + rwlock_acquire_read(&name##_lock_dep_map, 0, 0, _THIS_IP_); \ + lock = &per_cpu(name##_lock, cpu); \ + arch_spin_lock(lock); \ + } \ + EXPORT_SYMBOL(name##_local_lock_cpu); \ + \ + void name##_local_unlock_cpu(int cpu) { \ + arch_spinlock_t *lock; \ + rwlock_release(&name##_lock_dep_map, 1, _THIS_IP_); \ + lock = &per_cpu(name##_lock, cpu); \ + arch_spin_unlock(lock); \ + preempt_enable(); \ + } \ + EXPORT_SYMBOL(name##_local_unlock_cpu); \ + \ + void name##_global_lock_online(void) { \ + int i; \ + preempt_disable(); \ + rwlock_acquire(&name##_lock_dep_map, 0, 0, _RET_IP_); \ + for_each_online_cpu(i) { \ + arch_spinlock_t *lock; \ + lock = &per_cpu(name##_lock, i); \ + arch_spin_lock(lock); \ + } \ + } \ + EXPORT_SYMBOL(name##_global_lock_online); \ + \ + void name##_global_unlock_online(void) { \ + int i; \ + rwlock_release(&name##_lock_dep_map, 1, _RET_IP_); \ + for_each_online_cpu(i) { \ + arch_spinlock_t *lock; \ + lock = &per_cpu(name##_lock, i); \ + arch_spin_unlock(lock); \ + } \ + preempt_enable(); \ + } \ + EXPORT_SYMBOL(name##_global_unlock_online); \ + \ + void name##_global_lock(void) { \ + int i; \ + preempt_disable(); \ + rwlock_acquire(&name##_lock_dep_map, 0, 0, _RET_IP_); \ + for_each_online_cpu(i) { \ + arch_spinlock_t *lock; \ + lock = &per_cpu(name##_lock, i); \ + arch_spin_lock(lock); \ + } \ + } \ + EXPORT_SYMBOL(name##_global_lock); \ + \ + void name##_global_unlock(void) { \ + int i; \ + rwlock_release(&name##_lock_dep_map, 1, _RET_IP_); \ + for_each_online_cpu(i) { \ + arch_spinlock_t *lock; \ + lock = &per_cpu(name##_lock, i); \ + arch_spin_unlock(lock); \ + } \ + preempt_enable(); \ + } \ + EXPORT_SYMBOL(name##_global_unlock); +#endif -- cgit v1.2.3 From 6416ccb7899960868f5016751fb81bf25213d24f Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 18 Aug 2010 04:37:38 +1000 Subject: fs: scale files_lock fs: scale files_lock Improve scalability of files_lock by adding per-cpu, per-sb files lists, protected with an lglock. The lglock provides fast access to the per-cpu lists to add and remove files. It also provides a snapshot of all the per-cpu lists (although this is very slow). One difficulty with this approach is that a file can be removed from the list by another CPU. We must track which per-cpu list the file is on with a new variale in the file struct (packed into a hole on 64-bit archs). Scalability could suffer if files are frequently removed from different cpu's list. However loads with frequent removal of files imply short interval between adding and removing the files, and the scheduler attempts to avoid moving processes too far away. Also, even in the case of cross-CPU removal, the hardware has much more opportunity to parallelise cacheline transfers with N cachelines than with 1. A worst-case test of 1 CPU allocating files subsequently being freed by N CPUs degenerates to contending on a single lock, which is no worse than before. When more than one CPU are allocating files, even if they are always freed by different CPUs, there will be more parallelism than the single-lock case. Testing results: On a 2 socket, 8 core opteron, I measure the number of times the lock is taken to remove the file, the number of times it is removed by the same CPU that added it, and the number of times it is removed by the same node that added it. Booting: locks= 25049 cpu-hits= 23174 (92.5%) node-hits= 23945 (95.6%) kbuild -j16 locks=2281913 cpu-hits=2208126 (96.8%) node-hits=2252674 (98.7%) dbench 64 locks=4306582 cpu-hits=4287247 (99.6%) node-hits=4299527 (99.8%) So a file is removed from the same CPU it was added by over 90% of the time. It remains within the same node 95% of the time. Tim Chen ran some numbers for a 64 thread Nehalem system performing a compile. throughput 2.6.34-rc2 24.5 +patch 24.9 us sys idle IO wait (in %) 2.6.34-rc2 51.25 28.25 17.25 3.25 +patch 53.75 18.5 19 8.75 So significantly less CPU time spent in kernel code, higher idle time and slightly higher throughput. Single threaded performance difference was within the noise of microbenchmarks. That is not to say penalty does not exist, the code is larger and more memory accesses required so it will be slightly slower. Cc: linux-kernel@vger.kernel.org Cc: Tim Chen Cc: Andi Kleen Signed-off-by: Nick Piggin Signed-off-by: Al Viro --- include/linux/fs.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 5e65add0f163..76041b614758 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -920,6 +920,9 @@ struct file { #define f_vfsmnt f_path.mnt const struct file_operations *f_op; spinlock_t f_lock; /* f_ep_links, f_flags, no IRQ */ +#ifdef CONFIG_SMP + int f_sb_list_cpu; +#endif atomic_long_t f_count; unsigned int f_flags; fmode_t f_mode; @@ -1334,7 +1337,11 @@ struct super_block { struct list_head s_inodes; /* all inodes */ struct hlist_head s_anon; /* anonymous dentries for (nfs) exporting */ +#ifdef CONFIG_SMP + struct list_head __percpu *s_files; +#else struct list_head s_files; +#endif /* s_dentry_lru and s_nr_dentry_unused are protected by dcache_lock */ struct list_head s_dentry_lru; /* unused dentry lru */ int s_nr_dentry_unused; /* # of dentry on lru */ -- cgit v1.2.3 From 1495cc9df4e81f5a8fa9b0b8f1034b14d24b7d8c Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Tue, 17 Aug 2010 21:15:46 -0700 Subject: Input: sysrq - drop tty argument from sysrq ops handlers Noone is using tty argument so let's get rid of it. Acked-by: Alan Cox Acked-by: Jason Wessel Acked-by: Greg Kroah-Hartman Signed-off-by: Dmitry Torokhov --- include/linux/sysrq.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sysrq.h b/include/linux/sysrq.h index 609e8ca5f534..4ee650315119 100644 --- a/include/linux/sysrq.h +++ b/include/linux/sysrq.h @@ -31,7 +31,7 @@ struct tty_struct; #define SYSRQ_ENABLE_RTNICE 0x0100 struct sysrq_key_op { - void (*handler)(int, struct tty_struct *); + void (*handler)(int); char *help_msg; char *action_msg; int enable_mask; @@ -58,6 +58,10 @@ static inline void handle_sysrq(int key, struct tty_struct *tty) { } +static inline void __handle_sysrq(int key, struct tty_struct *tty, int check_mask); +{ +} + static inline int register_sysrq_key(int key, struct sysrq_key_op *op) { return -EINVAL; -- cgit v1.2.3 From b35de43b31040828f83046f40fd34ba33146409d Mon Sep 17 00:00:00 2001 From: Andrea Righi Date: Thu, 19 Aug 2010 14:13:27 -0700 Subject: kfifo: implement missing __kfifo_skip_r() kfifo_skip() is currently broken, due to the missing of the internal helper function. Add it. Signed-off-by: Andrea Righi Cc: Greg KH Acked-by: Stefani Seibold Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kfifo.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kfifo.h b/include/linux/kfifo.h index 311f8753d713..4aa95f203f3e 100644 --- a/include/linux/kfifo.h +++ b/include/linux/kfifo.h @@ -836,6 +836,8 @@ extern void __kfifo_dma_out_finish_r(struct __kfifo *fifo, size_t recsize); extern unsigned int __kfifo_len_r(struct __kfifo *fifo, size_t recsize); +extern void __kfifo_skip_r(struct __kfifo *fifo, size_t recsize); + extern unsigned int __kfifo_out_peek_r(struct __kfifo *fifo, void *buf, unsigned int len, size_t recsize); -- cgit v1.2.3 From f335397d177c906256ee1bba28e8c49e8ec63817 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Tue, 17 Aug 2010 21:15:47 -0700 Subject: Input: sysrq - drop tty argument form handle_sysrq() Sysrq operations do not accept tty argument anymore so no need to pass it to us. [Stephen Rothwell : fix build breakage in drm code caused by sysrq using bool but not including linux/types.h] [Sachin Sant : fix build breakage in s390 keyboadr driver] Acked-by: Alan Cox Acked-by: Jason Wessel Acked-by: Greg Kroah-Hartman Signed-off-by: Dmitry Torokhov --- include/linux/serial_core.h | 2 +- include/linux/sysrq.h | 12 +++++------- 2 files changed, 6 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 3c2ad99fed34..64458a9a8938 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -465,7 +465,7 @@ uart_handle_sysrq_char(struct uart_port *port, unsigned int ch) #ifdef SUPPORT_SYSRQ if (port->sysrq) { if (ch && time_before(jiffies, port->sysrq)) { - handle_sysrq(ch, port->state->port.tty); + handle_sysrq(ch); port->sysrq = 0; return 1; } diff --git a/include/linux/sysrq.h b/include/linux/sysrq.h index 4ee650315119..387fa7d05c98 100644 --- a/include/linux/sysrq.h +++ b/include/linux/sysrq.h @@ -15,9 +15,7 @@ #define _LINUX_SYSRQ_H #include - -struct pt_regs; -struct tty_struct; +#include /* Possible values of bitmask for enabling sysrq functions */ /* 0x0001 is reserved for enable everything */ @@ -44,8 +42,8 @@ struct sysrq_key_op { * are available -- else NULL's). */ -void handle_sysrq(int key, struct tty_struct *tty); -void __handle_sysrq(int key, struct tty_struct *tty, int check_mask); +void handle_sysrq(int key); +void __handle_sysrq(int key, bool check_mask); int register_sysrq_key(int key, struct sysrq_key_op *op); int unregister_sysrq_key(int key, struct sysrq_key_op *op); struct sysrq_key_op *__sysrq_get_key_op(int key); @@ -54,11 +52,11 @@ int sysrq_toggle_support(int enable_mask); #else -static inline void handle_sysrq(int key, struct tty_struct *tty) +static inline void handle_sysrq(int key) { } -static inline void __handle_sysrq(int key, struct tty_struct *tty, int check_mask); +static inline void __handle_sysrq(int key, bool check_mask) { } -- cgit v1.2.3 From 6ee9f4b4affe751d313d2538999aeec134d413a6 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Tue, 17 Aug 2010 21:15:47 -0700 Subject: USB: drop tty argument from usb_serial_handle_sysrq_char() Since handle_sysrq() does not take tty as argument anymore we can drop it from usb_serial_handle_sysrq_char() as well. Acked-by: Alan Cox Acked-by: Jason Wessel Acked-by: Greg Kroah-Hartman Signed-off-by: Dmitry Torokhov --- include/linux/usb/serial.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index 84a4c44c208b..55675b1efb28 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -342,8 +342,7 @@ extern int usb_serial_generic_submit_read_urb(struct usb_serial_port *port, extern void usb_serial_generic_process_read_urb(struct urb *urb); extern int usb_serial_generic_prepare_write_buffer(struct usb_serial_port *port, void *dest, size_t size); -extern int usb_serial_handle_sysrq_char(struct tty_struct *tty, - struct usb_serial_port *port, +extern int usb_serial_handle_sysrq_char(struct usb_serial_port *port, unsigned int ch); extern int usb_serial_handle_break(struct usb_serial_port *port); -- cgit v1.2.3 From 8905aaafb4b5d9764c5b4b54c7d03eb41bb0a7e9 Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Thu, 19 Aug 2010 09:52:28 -0700 Subject: Input: uinput - add devname alias to allow module on-demand load Recent modprobe and udev versions allow to create device nodes for modules which are not loaded. Only the first access will cause the in-kernel module loader to pull-in the module. Systems which never access the device node will not needlessly load the module, and no longer need init scripts or other facilities to unconditionally load it. Signed-off-by: Kay Sievers Signed-off-by: Dmitry Torokhov --- include/linux/miscdevice.h | 1 + include/linux/uinput.h | 1 - 2 files changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h index bafffc737903..18fd13028ba1 100644 --- a/include/linux/miscdevice.h +++ b/include/linux/miscdevice.h @@ -33,6 +33,7 @@ #define MWAVE_MINOR 219 /* ACP/Mwave Modem */ #define MPT_MINOR 220 #define MPT2SAS_MINOR 221 +#define UINPUT_MINOR 223 #define HPET_MINOR 228 #define FUSE_MINOR 229 #define KVM_MINOR 232 diff --git a/include/linux/uinput.h b/include/linux/uinput.h index 60c81da77f0f..05f7fed2b173 100644 --- a/include/linux/uinput.h +++ b/include/linux/uinput.h @@ -37,7 +37,6 @@ #define UINPUT_VERSION 3 #ifdef __KERNEL__ -#define UINPUT_MINOR 223 #define UINPUT_NAME "uinput" #define UINPUT_BUFFER_SIZE 16 #define UINPUT_NUM_REQUESTS 16 -- cgit v1.2.3 From 297c5eee372478fc32fec5fe8eed711eedb13f3d Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 20 Aug 2010 16:24:55 -0700 Subject: mm: make the vma list be doubly linked It's a really simple list, and several of the users want to go backwards in it to find the previous vma. So rather than have to look up the previous entry with 'find_vma_prev()' or something similar, just make it doubly linked instead. Tested-by: Ian Campbell Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index b8bb9a6a1f37..ee7e258627f9 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -134,7 +134,7 @@ struct vm_area_struct { within vm_mm. */ /* linked list of VM areas per task, sorted by address */ - struct vm_area_struct *vm_next; + struct vm_area_struct *vm_next, *vm_prev; pgprot_t vm_page_prot; /* Access permissions of this VMA. */ unsigned long vm_flags; /* Flags, see mm.h. */ -- cgit v1.2.3 From 2eebf582c9b3106abb9c33f4fc0a347fb9391037 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Wed, 18 Aug 2010 12:25:50 -0400 Subject: fanotify: flush outstanding perm requests on group destroy When an fanotify listener is closing it may cause a deadlock between the listener and the original task doing an fs operation. If the original task is waiting for a permissions response it will be holding the srcu lock. The listener cannot clean up and exit until after that srcu lock is syncronized. Thus deadlock. The fix introduced here is to stop accepting new permissions events when a listener is shutting down and to grant permission for all outstanding events. Thus the original task will eventually release the srcu lock and the listener can complete shutdown. Reported-by: Andreas Gruenbacher Cc: Andreas Gruenbacher Signed-off-by: Eric Paris --- include/linux/fanotify.h | 7 ------- include/linux/fsnotify_backend.h | 1 + 2 files changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index f0949a57ca9d..985435622ecd 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -95,11 +95,4 @@ struct fanotify_response { (long)(meta)->event_len >= (long)FAN_EVENT_METADATA_LEN && \ (long)(meta)->event_len <= (long)(len)) -#ifdef __KERNEL__ - -struct fanotify_wait { - struct fsnotify_event *event; - __s32 fd; -}; -#endif /* __KERNEL__ */ #endif /* _LINUX_FANOTIFY_H */ diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index ed36fb57c426..e40190d16878 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -156,6 +156,7 @@ struct fsnotify_group { struct mutex access_mutex; struct list_head access_list; wait_queue_head_t access_waitq; + bool bypass_perm; /* protected by access_mutex */ #endif /* CONFIG_FANOTIFY_ACCESS_PERMISSIONS */ int f_flags; } fanotify_data; -- cgit v1.2.3 From 8488a38f4d2f43bd55a3e0db4cd57a5bef3af6d6 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 11 Aug 2010 15:01:02 +0100 Subject: kobject: Break the kobject namespace defs into their own header Break the kobject namespace defs into their own header to avoid a header file inclusion ordering problem between linux/sysfs.h and linux/kobject.h. This fixes the build breakage on older versions of gcc. Signed-off-by: David Howells Cc: Eric Biederman Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 35 +---------------------------- include/linux/kobject_ns.h | 56 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/sysfs.h | 1 + 3 files changed, 58 insertions(+), 34 deletions(-) create mode 100644 include/linux/kobject_ns.h (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index cf343a852534..7950a37a7146 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include @@ -136,42 +137,8 @@ struct kobj_attribute { extern const struct sysfs_ops kobj_sysfs_ops; -/* - * Namespace types which are used to tag kobjects and sysfs entries. - * Network namespace will likely be the first. - */ -enum kobj_ns_type { - KOBJ_NS_TYPE_NONE = 0, - KOBJ_NS_TYPE_NET, - KOBJ_NS_TYPES -}; - struct sock; -/* - * Callbacks so sysfs can determine namespaces - * @current_ns: return calling task's namespace - * @netlink_ns: return namespace to which a sock belongs (right?) - * @initial_ns: return the initial namespace (i.e. init_net_ns) - */ -struct kobj_ns_type_operations { - enum kobj_ns_type type; - const void *(*current_ns)(void); - const void *(*netlink_ns)(struct sock *sk); - const void *(*initial_ns)(void); -}; - -int kobj_ns_type_register(const struct kobj_ns_type_operations *ops); -int kobj_ns_type_registered(enum kobj_ns_type type); -const struct kobj_ns_type_operations *kobj_child_ns_ops(struct kobject *parent); -const struct kobj_ns_type_operations *kobj_ns_ops(struct kobject *kobj); - -const void *kobj_ns_current(enum kobj_ns_type type); -const void *kobj_ns_netlink(enum kobj_ns_type type, struct sock *sk); -const void *kobj_ns_initial(enum kobj_ns_type type); -void kobj_ns_exit(enum kobj_ns_type type, const void *ns); - - /** * struct kset - a set of kobjects of a specific type, belonging to a specific subsystem. * diff --git a/include/linux/kobject_ns.h b/include/linux/kobject_ns.h new file mode 100644 index 000000000000..82cb5bf461fb --- /dev/null +++ b/include/linux/kobject_ns.h @@ -0,0 +1,56 @@ +/* Kernel object name space definitions + * + * Copyright (c) 2002-2003 Patrick Mochel + * Copyright (c) 2002-2003 Open Source Development Labs + * Copyright (c) 2006-2008 Greg Kroah-Hartman + * Copyright (c) 2006-2008 Novell Inc. + * + * Split from kobject.h by David Howells (dhowells@redhat.com) + * + * This file is released under the GPLv2. + * + * Please read Documentation/kobject.txt before using the kobject + * interface, ESPECIALLY the parts about reference counts and object + * destructors. + */ + +#ifndef _LINUX_KOBJECT_NS_H +#define _LINUX_KOBJECT_NS_H + +struct sock; +struct kobject; + +/* + * Namespace types which are used to tag kobjects and sysfs entries. + * Network namespace will likely be the first. + */ +enum kobj_ns_type { + KOBJ_NS_TYPE_NONE = 0, + KOBJ_NS_TYPE_NET, + KOBJ_NS_TYPES +}; + +/* + * Callbacks so sysfs can determine namespaces + * @current_ns: return calling task's namespace + * @netlink_ns: return namespace to which a sock belongs (right?) + * @initial_ns: return the initial namespace (i.e. init_net_ns) + */ +struct kobj_ns_type_operations { + enum kobj_ns_type type; + const void *(*current_ns)(void); + const void *(*netlink_ns)(struct sock *sk); + const void *(*initial_ns)(void); +}; + +int kobj_ns_type_register(const struct kobj_ns_type_operations *ops); +int kobj_ns_type_registered(enum kobj_ns_type type); +const struct kobj_ns_type_operations *kobj_child_ns_ops(struct kobject *parent); +const struct kobj_ns_type_operations *kobj_ns_ops(struct kobject *kobj); + +const void *kobj_ns_current(enum kobj_ns_type type); +const void *kobj_ns_netlink(enum kobj_ns_type type, struct sock *sk); +const void *kobj_ns_initial(enum kobj_ns_type type); +void kobj_ns_exit(enum kobj_ns_type type, const void *ns); + +#endif /* _LINUX_KOBJECT_NS_H */ diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 3c92121ba9af..96eb576d82fd 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -16,6 +16,7 @@ #include #include #include +#include #include struct kobject; -- cgit v1.2.3 From d187abb9a83e6c6b6e9f2ca17962bdeafb4bc903 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 11 Aug 2010 12:07:13 -0700 Subject: USB: gadget: fix composite kernel-doc warnings Warning(include/linux/usb/composite.h:284): No description found for parameter 'disconnect' Warning(drivers/usb/gadget/composite.c:744): No description found for parameter 'c' Warning(drivers/usb/gadget/composite.c:744): Excess function parameter 'cdev' description in 'usb_string_ids_n' Signed-off-by: Randy Dunlap Cc: David Brownell Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/composite.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index 890bc1472190..617068134ae8 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -247,6 +247,7 @@ int usb_add_config(struct usb_composite_dev *, * value; it should return zero on successful initialization. * @unbind: Reverses @bind(); called as a side effect of unregistering * this driver. + * @disconnect: optional driver disconnect method * @suspend: Notifies when the host stops sending USB traffic, * after function notifications * @resume: Notifies configuration when the host restarts USB traffic, -- cgit v1.2.3 From e41e704bc4f49057fc68b643108366e6e6781aa3 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 24 Aug 2010 14:22:47 +0200 Subject: workqueue: improve destroy_workqueue() debuggability Now that the worklist is global, having works pending after wq destruction can easily lead to oops and destroy_workqueue() have several BUG_ON()s to catch these cases. Unfortunately, BUG_ON() doesn't tell much about how the work became pending after the final flush_workqueue(). This patch adds WQ_DYING which is set before the final flush begins. If a work is requested to be queued on a dying workqueue, WARN_ON_ONCE() is triggered and the request is ignored. This clearly indicates which caller is trying to queue a work on a dying workqueue and keeps the system working in most cases. Locking rule comment is updated such that the 'I' rule includes modifying the field from destruction path. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 4f9d277bcd9a..c959666eafca 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -241,6 +241,8 @@ enum { WQ_HIGHPRI = 1 << 4, /* high priority */ WQ_CPU_INTENSIVE = 1 << 5, /* cpu instensive workqueue */ + WQ_DYING = 1 << 6, /* internal: workqueue is dying */ + WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */ WQ_MAX_UNBOUND_PER_CPU = 4, /* 4 * #cpus for unbound wq */ WQ_DFL_ACTIVE = WQ_MAX_ACTIVE / 2, -- cgit v1.2.3 From 8ca3eb08097f6839b2206e2242db4179aee3cfb3 Mon Sep 17 00:00:00 2001 From: "Luck, Tony" Date: Tue, 24 Aug 2010 11:44:18 -0700 Subject: guard page for stacks that grow upwards pa-risc and ia64 have stacks that grow upwards. Check that they do not run into other mappings. By making VM_GROWSUP 0x0 on architectures that do not ever use it, we can avoid some unpleasant #ifdefs in check_stack_guard_page(). Signed-off-by: Tony Luck Signed-off-by: Linus Torvalds --- include/linux/mm.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 709f6728fc90..831c693416b2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -78,7 +78,11 @@ extern unsigned int kobjsize(const void *objp); #define VM_MAYSHARE 0x00000080 #define VM_GROWSDOWN 0x00000100 /* general info on the segment */ +#if defined(CONFIG_STACK_GROWSUP) || defined(CONFIG_IA64) #define VM_GROWSUP 0x00000200 +#else +#define VM_GROWSUP 0x00000000 +#endif #define VM_PFNMAP 0x00000400 /* Page-ranges managed without "struct page", just pure PFN */ #define VM_DENYWRITE 0x00000800 /* ETXTBSY on write attempts.. */ @@ -1330,8 +1334,10 @@ unsigned long ra_submit(struct file_ra_state *ra, /* Do stack extension */ extern int expand_stack(struct vm_area_struct *vma, unsigned long address); -#ifdef CONFIG_IA64 +#if VM_GROWSUP extern int expand_upwards(struct vm_area_struct *vma, unsigned long address); +#else + #define expand_upwards(vma, address) do { } while (0) #endif extern int expand_stack_downwards(struct vm_area_struct *vma, unsigned long address); -- cgit v1.2.3 From 75fb60f26befb59dbfa05cb122972642b7bdd219 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 23 Aug 2010 23:53:11 +0200 Subject: ACPI/PCI: Negotiate _OSC control bits before requesting them It is possible that the BIOS will not grant control of all _OSC features requested via acpi_pci_osc_control_set(), so it is recommended to negotiate the final set of _OSC features with the query flag set before calling _OSC to request control of these features. To implement it, rework acpi_pci_osc_control_set() so that the caller can specify the mask of _OSC control bits to negotiate and the mask of _OSC control bits that are absolutely necessary to it. Then, acpi_pci_osc_control_set() will run _OSC queries in a loop until the mask of _OSC control bits returned by the BIOS is equal to the mask passed to it. Also, before running the _OSC request acpi_pci_osc_control_set() will check if the caller's required control bits are present in the final mask. Using this mechanism we will be able to avoid situations in which the BIOS doesn't grant control of certain _OSC features, because they depend on some other _OSC features that have not been requested. Signed-off-by: Rafael J. Wysocki Signed-off-by: Jesse Barnes --- include/linux/acpi.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index ccf94dc5acdf..c227757feb06 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -304,8 +304,8 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context); OSC_PCI_EXPRESS_PME_CONTROL | \ OSC_PCI_EXPRESS_AER_CONTROL | \ OSC_PCI_EXPRESS_CAP_STRUCTURE_CONTROL) - -extern acpi_status acpi_pci_osc_control_set(acpi_handle handle, u32 flags); +extern acpi_status acpi_pci_osc_control_set(acpi_handle handle, + u32 *mask, u32 req); extern void acpi_early_init(void); #else /* !CONFIG_ACPI */ -- cgit v1.2.3 From 8a2e8e5dec7e29c56a46ba176c664ab6a3d04118 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 25 Aug 2010 10:33:56 +0200 Subject: workqueue: fix cwq->nr_active underflow cwq->nr_active is used to keep track of how many work items are active for the cpu workqueue, where 'active' is defined as either pending on global worklist or executing. This is used to implement the max_active limit and workqueue freezing. If a work item is queued after nr_active has already reached max_active, the work item doesn't increment nr_active and is put on the delayed queue and gets activated later as previous active work items retire. try_to_grab_pending() which is used in the cancellation path unconditionally decremented nr_active whether the work item being cancelled is currently active or delayed, so cancelling a delayed work item makes nr_active underflow. This breaks max_active enforcement and triggers BUG_ON() in destroy_workqueue() later on. This patch fixes this bug by adding a flag WORK_STRUCT_DELAYED, which is set while a work item in on the delayed list and making try_to_grab_pending() decrement nr_active iff the work item is currently active. The addition of the flag enlarges cwq alignment to 256 bytes which is getting a bit too large. It's scheduled to be reduced back to 128 bytes by merging WORK_STRUCT_PENDING and WORK_STRUCT_CWQ in the next devel cycle. Signed-off-by: Tejun Heo Reported-by: Johannes Berg --- include/linux/workqueue.h | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index c959666eafca..f11100f96482 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -25,18 +25,20 @@ typedef void (*work_func_t)(struct work_struct *work); enum { WORK_STRUCT_PENDING_BIT = 0, /* work item is pending execution */ - WORK_STRUCT_CWQ_BIT = 1, /* data points to cwq */ - WORK_STRUCT_LINKED_BIT = 2, /* next work is linked to this one */ + WORK_STRUCT_DELAYED_BIT = 1, /* work item is delayed */ + WORK_STRUCT_CWQ_BIT = 2, /* data points to cwq */ + WORK_STRUCT_LINKED_BIT = 3, /* next work is linked to this one */ #ifdef CONFIG_DEBUG_OBJECTS_WORK - WORK_STRUCT_STATIC_BIT = 3, /* static initializer (debugobjects) */ - WORK_STRUCT_COLOR_SHIFT = 4, /* color for workqueue flushing */ + WORK_STRUCT_STATIC_BIT = 4, /* static initializer (debugobjects) */ + WORK_STRUCT_COLOR_SHIFT = 5, /* color for workqueue flushing */ #else - WORK_STRUCT_COLOR_SHIFT = 3, /* color for workqueue flushing */ + WORK_STRUCT_COLOR_SHIFT = 4, /* color for workqueue flushing */ #endif WORK_STRUCT_COLOR_BITS = 4, WORK_STRUCT_PENDING = 1 << WORK_STRUCT_PENDING_BIT, + WORK_STRUCT_DELAYED = 1 << WORK_STRUCT_DELAYED_BIT, WORK_STRUCT_CWQ = 1 << WORK_STRUCT_CWQ_BIT, WORK_STRUCT_LINKED = 1 << WORK_STRUCT_LINKED_BIT, #ifdef CONFIG_DEBUG_OBJECTS_WORK @@ -59,8 +61,8 @@ enum { /* * Reserve 7 bits off of cwq pointer w/ debugobjects turned - * off. This makes cwqs aligned to 128 bytes which isn't too - * excessive while allowing 15 workqueue flush colors. + * off. This makes cwqs aligned to 256 bytes and allows 15 + * workqueue flush colors. */ WORK_STRUCT_FLAG_BITS = WORK_STRUCT_COLOR_SHIFT + WORK_STRUCT_COLOR_BITS, -- cgit v1.2.3 From 04cbe1de6fbda9649a6f25666194e6955d3e717e Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Thu, 19 Aug 2010 21:29:43 +0100 Subject: vgaarb: Wrap vga_(get|put) in CONFIG_VGA_ARB Fix link failure without the vga arbitrator. Signed-off-by: Chris Wilson Cc: Dave Airlie Cc: Jesse Barnes Signed-off-by: Dave Airlie --- include/linux/vgaarb.h | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vgaarb.h b/include/linux/vgaarb.h index 6228b5b77d35..e9e1524b582c 100644 --- a/include/linux/vgaarb.h +++ b/include/linux/vgaarb.h @@ -93,8 +93,11 @@ extern void vga_set_legacy_decoding(struct pci_dev *pdev, * Nested calls are supported (a per-resource counter is maintained) */ -extern int vga_get(struct pci_dev *pdev, unsigned int rsrc, - int interruptible); +#if defined(CONFIG_VGA_ARB) +extern int vga_get(struct pci_dev *pdev, unsigned int rsrc, int interruptible); +#else +static inline int vga_get(struct pci_dev *pdev, unsigned int rsrc, int interruptible) { return 0; } +#endif /** * vga_get_interruptible @@ -131,7 +134,11 @@ static inline int vga_get_uninterruptible(struct pci_dev *pdev, * are already locked by another card. It can be called in any context */ +#if defined(CONFIG_VGA_ARB) extern int vga_tryget(struct pci_dev *pdev, unsigned int rsrc); +#else +static inline int vga_tryget(struct pci_dev *pdev, unsigned int rsrc) { return 0; } +#endif /** * vga_put - release lock on legacy VGA resources @@ -146,7 +153,11 @@ extern int vga_tryget(struct pci_dev *pdev, unsigned int rsrc); * released if the counter reaches 0. */ +#if defined(CONFIG_VGA_ARB) extern void vga_put(struct pci_dev *pdev, unsigned int rsrc); +#else +#define vga_put(pdev, rsrc) +#endif /** -- cgit v1.2.3 From 0fb85621df4f9f7c663c6c77c302e821a832c95e Mon Sep 17 00:00:00 2001 From: Tvrtko Ursulin Date: Fri, 20 Aug 2010 10:02:15 +0100 Subject: fanotify: resize pid and reorder structure resize pid and reorder the fanotify_event_metadata so it is naturally aligned and we can work towards dropping the packed attributed Signed-off-by: Tvrtko Ursulin Cc: Andreas Dilger Signed-off-by: Eric Paris --- include/linux/fanotify.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 985435622ecd..63531a6b4d2a 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -65,14 +65,14 @@ FAN_ALL_PERM_EVENTS |\ FAN_Q_OVERFLOW) -#define FANOTIFY_METADATA_VERSION 1 +#define FANOTIFY_METADATA_VERSION 2 struct fanotify_event_metadata { __u32 event_len; __u32 vers; - __s32 fd; __u64 mask; - __s64 pid; + __s32 fd; + __s32 pid; } __attribute__ ((packed)); struct fanotify_response { -- cgit v1.2.3 From bad849b3dc0fae1297c8d47f846f8d202a6145ed Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 26 Aug 2010 16:00:34 +0100 Subject: NOMMU: Stub out vm_get_page_prot() if there's no MMU Stub out vm_get_page_prot() if there's no MMU. This was added by commit 804af2cf6e7a ("[AGPGART] remove private page protection map") and is used in commit c07fbfd17e61 ("fbmem: VM_IO set, but not propagated") in the fbmem video driver, but the function doesn't exist on NOMMU, resulting in an undefined symbol at link time. Signed-off-by: David Howells Reviewed-by: Konrad Rzeszutek Wilk Signed-off-by: Linus Torvalds --- include/linux/mm.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 831c693416b2..e6b1210772ce 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1363,7 +1363,15 @@ static inline unsigned long vma_pages(struct vm_area_struct *vma) return (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; } +#ifdef CONFIG_MMU pgprot_t vm_get_page_prot(unsigned long vm_flags); +#else +static inline pgprot_t vm_get_page_prot(unsigned long vm_flags) +{ + return __pgprot(0); +} +#endif + struct vm_area_struct *find_extend_vma(struct mm_struct *, unsigned long addr); int remap_pfn_range(struct vm_area_struct *, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t); -- cgit v1.2.3 From a28dec2f26013aad89446b1f708f948617bc28a2 Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Sun, 8 Aug 2010 18:03:33 +0400 Subject: powerpc/85xx: Add P1021 PCI IDs and quirks This is needed for proper PCI-E support on P1021 SoCs. Signed-off-by: Anton Vorontsov Signed-off-by: Kumar Gala --- include/linux/pci_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index f6a3b2d36cad..10d33309e9a6 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2300,6 +2300,8 @@ #define PCI_DEVICE_ID_P2010 0x0079 #define PCI_DEVICE_ID_P1020E 0x0100 #define PCI_DEVICE_ID_P1020 0x0101 +#define PCI_DEVICE_ID_P1021E 0x0102 +#define PCI_DEVICE_ID_P1021 0x0103 #define PCI_DEVICE_ID_P1011E 0x0108 #define PCI_DEVICE_ID_P1011 0x0109 #define PCI_DEVICE_ID_P1022E 0x0110 -- cgit v1.2.3 From 71cad0554956de87c3fc413b1eac9313887eb14f Mon Sep 17 00:00:00 2001 From: Philippe Langlais Date: Tue, 31 Aug 2010 14:19:09 +0200 Subject: serial: fix port type conflict between NS16550A & U6_16550A Bug seen by Dr. David Alan Gilbert with sparse Signed-off-by: Philippe Langlais Cc: stable Signed-off-by: Greg Kroah-Hartman --- include/linux/serial.h | 3 +-- include/linux/serial_core.h | 3 ++- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/serial.h b/include/linux/serial.h index 1ebc694a6d52..ef914061511e 100644 --- a/include/linux/serial.h +++ b/include/linux/serial.h @@ -77,8 +77,7 @@ struct serial_struct { #define PORT_16654 11 #define PORT_16850 12 #define PORT_RSA 13 /* RSA-DV II/S card */ -#define PORT_U6_16550A 14 -#define PORT_MAX 14 +#define PORT_MAX 13 #define SERIAL_IO_PORT 0 #define SERIAL_IO_HUB6 1 diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 64458a9a8938..563e23400913 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -44,7 +44,8 @@ #define PORT_RM9000 16 /* PMC-Sierra RM9xxx internal UART */ #define PORT_OCTEON 17 /* Cavium OCTEON internal UART */ #define PORT_AR7 18 /* Texas Instruments AR7 internal UART */ -#define PORT_MAX_8250 18 /* max port ID */ +#define PORT_U6_16550A 19 /* ST-Ericsson U6xxx internal UART */ +#define PORT_MAX_8250 19 /* max port ID */ /* * ARM specific type numbers. These are not currently guaranteed -- cgit v1.2.3 From f8f235e5bbf4e61f3e0886a44afb1dc4cfe8f337 Mon Sep 17 00:00:00 2001 From: Zhenyu Wang Date: Fri, 27 Aug 2010 11:08:57 +0800 Subject: agp/intel: Fix cache control for Sandybridge Sandybridge GTT has new cache control bits in PTE, which controls graphics page cache in LLC or LLC/MLC, so we need to extend the mask function to respect the new bits. And set cache control to always LLC only by default on Gen6. Signed-off-by: Zhenyu Wang Cc: stable@kernel.org Signed-off-by: Chris Wilson --- include/linux/intel-gtt.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) create mode 100644 include/linux/intel-gtt.h (limited to 'include/linux') diff --git a/include/linux/intel-gtt.h b/include/linux/intel-gtt.h new file mode 100644 index 000000000000..1d19ab2afa39 --- /dev/null +++ b/include/linux/intel-gtt.h @@ -0,0 +1,20 @@ +/* + * Common Intel AGPGART and GTT definitions. + */ +#ifndef _INTEL_GTT_H +#define _INTEL_GTT_H + +#include + +/* This is for Intel only GTT controls. + * + * Sandybridge: AGP_USER_CACHED_MEMORY default to LLC only + */ + +#define AGP_USER_CACHED_MEMORY_LLC_MLC (AGP_USER_TYPES + 2) +#define AGP_USER_UNCACHED_MEMORY (AGP_USER_TYPES + 4) + +/* flag for GFDT type */ +#define AGP_USER_CACHED_MEMORY_GFDT (1 << 3) + +#endif -- cgit v1.2.3