From 606576ce816603d9fe1fb453a88bc6eea16ca709 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 6 Oct 2008 19:06:12 -0400 Subject: ftrace: rename FTRACE to FUNCTION_TRACER Due to confusion between the ftrace infrastructure and the gcc profiling tracer "ftrace", this patch renames the config options from FTRACE to FUNCTION_TRACER. The other two names that are offspring from FTRACE DYNAMIC_FTRACE and FTRACE_MCOUNT_RECORD will stay the same. This patch was generated mostly by script, and partially by hand. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- include/linux/ftrace.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index a3d46151be19..0e9529589151 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -8,7 +8,7 @@ #include #include -#ifdef CONFIG_FTRACE +#ifdef CONFIG_FUNCTION_TRACER extern int ftrace_enabled; extern int @@ -36,12 +36,12 @@ void clear_ftrace_function(void); extern void ftrace_stub(unsigned long a0, unsigned long a1); -#else /* !CONFIG_FTRACE */ +#else /* !CONFIG_FUNCTION_TRACER */ # define register_ftrace_function(ops) do { } while (0) # define unregister_ftrace_function(ops) do { } while (0) # define clear_ftrace_function(ops) do { } while (0) static inline void ftrace_kill_atomic(void) { } -#endif /* CONFIG_FTRACE */ +#endif /* CONFIG_FUNCTION_TRACER */ #ifdef CONFIG_DYNAMIC_FTRACE # define FTRACE_HASHBITS 10 @@ -101,7 +101,7 @@ void ftrace_kill_atomic(void); static inline void tracer_disable(void) { -#ifdef CONFIG_FTRACE +#ifdef CONFIG_FUNCTION_TRACER ftrace_enabled = 0; #endif } @@ -113,7 +113,7 @@ static inline void tracer_disable(void) */ static inline int __ftrace_enabled_save(void) { -#ifdef CONFIG_FTRACE +#ifdef CONFIG_FUNCTION_TRACER int saved_ftrace_enabled = ftrace_enabled; ftrace_enabled = 0; return saved_ftrace_enabled; @@ -124,7 +124,7 @@ static inline int __ftrace_enabled_save(void) static inline void __ftrace_enabled_restore(int enabled) { -#ifdef CONFIG_FTRACE +#ifdef CONFIG_FUNCTION_TRACER ftrace_enabled = enabled; #endif } -- cgit v1.2.3 From 4ce72a2c063a7fa8e42a9435440ae3364115a58d Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 22 Oct 2008 15:25:26 +0800 Subject: sched: add CONFIG_SMP consistency a patch from Henrik Austad did this: >> Do not declare select_task_rq as part of sched_class when CONFIG_SMP is >> not set. Peter observed: > While a proper cleanup, could you do it by re-arranging the methods so > as to not create an additional ifdef? Do not declare select_task_rq and some other methods as part of sched_class when CONFIG_SMP is not set. Also gather those methods to avoid CONFIG_SMP mess. Idea-by: Henrik Austad Signed-off-by: Li Zefan Acked-by: Peter Zijlstra Acked-by: Henrik Austad Signed-off-by: Ingo Molnar --- include/linux/sched.h | 12 +++++++----- kernel/sched_fair.c | 5 ++--- kernel/sched_idletask.c | 5 ++--- kernel/sched_rt.c | 5 ++--- 4 files changed, 13 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 4f59c8e8597d..c05b45faef18 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -897,7 +897,6 @@ struct sched_class { void (*enqueue_task) (struct rq *rq, struct task_struct *p, int wakeup); void (*dequeue_task) (struct rq *rq, struct task_struct *p, int sleep); void (*yield_task) (struct rq *rq); - int (*select_task_rq)(struct task_struct *p, int sync); void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int sync); @@ -905,6 +904,8 @@ struct sched_class { void (*put_prev_task) (struct rq *rq, struct task_struct *p); #ifdef CONFIG_SMP + int (*select_task_rq)(struct task_struct *p, int sync); + unsigned long (*load_balance) (struct rq *this_rq, int this_cpu, struct rq *busiest, unsigned long max_load_move, struct sched_domain *sd, enum cpu_idle_type idle, @@ -916,16 +917,17 @@ struct sched_class { void (*pre_schedule) (struct rq *this_rq, struct task_struct *task); void (*post_schedule) (struct rq *this_rq); void (*task_wake_up) (struct rq *this_rq, struct task_struct *task); -#endif - void (*set_curr_task) (struct rq *rq); - void (*task_tick) (struct rq *rq, struct task_struct *p, int queued); - void (*task_new) (struct rq *rq, struct task_struct *p); void (*set_cpus_allowed)(struct task_struct *p, const cpumask_t *newmask); void (*rq_online)(struct rq *rq); void (*rq_offline)(struct rq *rq); +#endif + + void (*set_curr_task) (struct rq *rq); + void (*task_tick) (struct rq *rq, struct task_struct *p, int queued); + void (*task_new) (struct rq *rq, struct task_struct *p); void (*switched_from) (struct rq *this_rq, struct task_struct *task, int running); diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index a0aa38b10fdd..8de48a5da354 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -1593,9 +1593,6 @@ static const struct sched_class fair_sched_class = { .enqueue_task = enqueue_task_fair, .dequeue_task = dequeue_task_fair, .yield_task = yield_task_fair, -#ifdef CONFIG_SMP - .select_task_rq = select_task_rq_fair, -#endif /* CONFIG_SMP */ .check_preempt_curr = check_preempt_wakeup, @@ -1603,6 +1600,8 @@ static const struct sched_class fair_sched_class = { .put_prev_task = put_prev_task_fair, #ifdef CONFIG_SMP + .select_task_rq = select_task_rq_fair, + .load_balance = load_balance_fair, .move_one_task = move_one_task_fair, #endif diff --git a/kernel/sched_idletask.c b/kernel/sched_idletask.c index dec4ccabe2f5..8a21a2e28c13 100644 --- a/kernel/sched_idletask.c +++ b/kernel/sched_idletask.c @@ -105,9 +105,6 @@ static const struct sched_class idle_sched_class = { /* dequeue is not valid, we print a debug message there: */ .dequeue_task = dequeue_task_idle, -#ifdef CONFIG_SMP - .select_task_rq = select_task_rq_idle, -#endif /* CONFIG_SMP */ .check_preempt_curr = check_preempt_curr_idle, @@ -115,6 +112,8 @@ static const struct sched_class idle_sched_class = { .put_prev_task = put_prev_task_idle, #ifdef CONFIG_SMP + .select_task_rq = select_task_rq_idle, + .load_balance = load_balance_idle, .move_one_task = move_one_task_idle, #endif diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index cdf5740ab03e..c9aa5bede226 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -1502,9 +1502,6 @@ static const struct sched_class rt_sched_class = { .enqueue_task = enqueue_task_rt, .dequeue_task = dequeue_task_rt, .yield_task = yield_task_rt, -#ifdef CONFIG_SMP - .select_task_rq = select_task_rq_rt, -#endif /* CONFIG_SMP */ .check_preempt_curr = check_preempt_curr_rt, @@ -1512,6 +1509,8 @@ static const struct sched_class rt_sched_class = { .put_prev_task = put_prev_task_rt, #ifdef CONFIG_SMP + .select_task_rq = select_task_rq_rt, + .load_balance = load_balance_rt, .move_one_task = move_one_task_rt, .set_cpus_allowed = set_cpus_allowed_rt, -- cgit v1.2.3 From 593eb8a2d63e95772a5f22d746f18a997c5ee463 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 23 Oct 2008 09:32:59 -0400 Subject: ftrace: return error on failed modified text. Have the ftrace_modify_code return error values: -EFAULT on error of reading the address -EINVAL if what is read does not match what it expected -EPERM if the write fails to update after a successful match. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- arch/x86/kernel/ftrace.c | 14 +++++++------- include/linux/ftrace.h | 24 ++++++++++++++++++++++-- kernel/trace/ftrace.c | 21 +++++++++++++++------ 3 files changed, 44 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 8821ceabf51d..428291581cb2 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -62,7 +62,6 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code, unsigned char *new_code) { unsigned char replaced[MCOUNT_INSN_SIZE]; - int ret; /* * Note: Due to modules and __init, code can @@ -72,15 +71,16 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code, * No real locking needed, this code is run through * kstop_machine, or before SMP starts. */ - if (__copy_from_user_inatomic(replaced, (char __user *)ip, MCOUNT_INSN_SIZE)) - return 1; + if (__copy_from_user_inatomic(replaced, (char __user *)ip, + MCOUNT_INSN_SIZE)) + return -EFAULT; if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0) - return 2; + return -EINVAL; - ret = __copy_to_user_inatomic((char __user *)ip, new_code, - MCOUNT_INSN_SIZE); - WARN_ON_ONCE(ret); + if (__copy_to_user_inatomic((char __user *)ip, new_code, + MCOUNT_INSN_SIZE)) + return -EPERM; sync_core(); diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 0e9529589151..79fa10cbdcfb 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -72,13 +72,33 @@ extern unsigned char *ftrace_nop_replace(void); extern unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr); extern int ftrace_dyn_arch_init(void *data); extern int ftrace_mcount_set(unsigned long *data); -extern int ftrace_modify_code(unsigned long ip, unsigned char *old_code, - unsigned char *new_code); extern int ftrace_update_ftrace_func(ftrace_func_t func); extern void ftrace_caller(void); extern void ftrace_call(void); extern void mcount_call(void); +/** + * ftrace_modify_code - modify code segment + * @ip: the address of the code segment + * @old_code: the contents of what is expected to be there + * @new_code: the code to patch in + * + * This is a very sensitive operation and great care needs + * to be taken by the arch. The operation should carefully + * read the location, check to see if what is read is indeed + * what we expect it to be, and then on success of the compare, + * it should write to the location. + * + * Return must be: + * 0 on success + * -EFAULT on error reading the location + * -EINVAL on a failed compare of the contents + * -EPERM on error writing to the location + * Any other value will be considered a failure. + */ +extern int ftrace_modify_code(unsigned long ip, unsigned char *old_code, + unsigned char *new_code); + extern int skip_trace(unsigned long ip); extern void ftrace_release(void *start, unsigned long size); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 1f54a94189fe..b2de8de77356 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -596,22 +596,22 @@ ftrace_code_disable(struct dyn_ftrace *rec) { unsigned long ip; unsigned char *nop, *call; - int failed; + int ret; ip = rec->ip; nop = ftrace_nop_replace(); call = ftrace_call_replace(ip, mcount_addr); - failed = ftrace_modify_code(ip, call, nop); - if (failed) { - switch (failed) { - case 1: + ret = ftrace_modify_code(ip, call, nop); + if (ret) { + switch (ret) { + case -EFAULT: WARN_ON_ONCE(1); pr_info("ftrace faulted on modifying "); print_ip_sym(ip); break; - case 2: + case -EINVAL: WARN_ON_ONCE(1); pr_info("ftrace failed to modify "); print_ip_sym(ip); @@ -620,6 +620,15 @@ ftrace_code_disable(struct dyn_ftrace *rec) print_ip_ins(" replace: ", nop); printk(KERN_CONT "\n"); break; + case -EPERM: + WARN_ON_ONCE(1); + pr_info("ftrace faulted on writing "); + print_ip_sym(ip); + break; + default: + WARN_ON_ONCE(1); + pr_info("ftrace faulted on unknown error "); + print_ip_sym(ip); } rec->flags |= FTRACE_FL_FAILED; -- cgit v1.2.3 From 81adbdc029ecc416d56563e7f159100181dd711d Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 23 Oct 2008 09:33:02 -0400 Subject: ftrace: only have ftrace_kill atomic When an anomaly is detected, we need a way to completely disable ftrace. Right now we have two functions: ftrace_kill and ftrace_kill_atomic. The ftrace_kill tries to do it in a "nice" way by converting everything back to a nop. The "nice" way is dangerous itself, so this patch removes it and only has the "atomic" version, which is all that is needed. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- include/linux/ftrace.h | 3 +-- kernel/trace/ftrace.c | 42 ++---------------------------------------- kernel/trace/trace.c | 2 +- 3 files changed, 4 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 79fa10cbdcfb..ac58e94668b7 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -40,7 +40,7 @@ extern void ftrace_stub(unsigned long a0, unsigned long a1); # define register_ftrace_function(ops) do { } while (0) # define unregister_ftrace_function(ops) do { } while (0) # define clear_ftrace_function(ops) do { } while (0) -static inline void ftrace_kill_atomic(void) { } +static inline void ftrace_kill(void) { } #endif /* CONFIG_FUNCTION_TRACER */ #ifdef CONFIG_DYNAMIC_FTRACE @@ -117,7 +117,6 @@ static inline void ftrace_release(void *start, unsigned long size) { } /* totally disable ftrace - can not re-enable after this */ void ftrace_kill(void); -void ftrace_kill_atomic(void); static inline void tracer_disable(void) { diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index b2de8de77356..93245ae046e1 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1549,22 +1549,6 @@ int ftrace_force_update(void) return ret; } -static void ftrace_force_shutdown(void) -{ - struct task_struct *task; - int command = FTRACE_DISABLE_CALLS | FTRACE_UPDATE_TRACE_FUNC; - - mutex_lock(&ftraced_lock); - task = ftraced_task; - ftraced_task = NULL; - ftraced_suspend = -1; - ftrace_run_update_code(command); - mutex_unlock(&ftraced_lock); - - if (task) - kthread_stop(task); -} - static __init int ftrace_init_debugfs(void) { struct dentry *d_tracer; @@ -1795,17 +1779,16 @@ core_initcall(ftrace_dynamic_init); # define ftrace_shutdown() do { } while (0) # define ftrace_startup_sysctl() do { } while (0) # define ftrace_shutdown_sysctl() do { } while (0) -# define ftrace_force_shutdown() do { } while (0) #endif /* CONFIG_DYNAMIC_FTRACE */ /** - * ftrace_kill_atomic - kill ftrace from critical sections + * ftrace_kill - kill ftrace * * This function should be used by panic code. It stops ftrace * but in a not so nice way. If you need to simply kill ftrace * from a non-atomic section, use ftrace_kill. */ -void ftrace_kill_atomic(void) +void ftrace_kill(void) { ftrace_disabled = 1; ftrace_enabled = 0; @@ -1815,27 +1798,6 @@ void ftrace_kill_atomic(void) clear_ftrace_function(); } -/** - * ftrace_kill - totally shutdown ftrace - * - * This is a safety measure. If something was detected that seems - * wrong, calling this function will keep ftrace from doing - * any more modifications, and updates. - * used when something went wrong. - */ -void ftrace_kill(void) -{ - mutex_lock(&ftrace_sysctl_lock); - ftrace_disabled = 1; - ftrace_enabled = 0; - - clear_ftrace_function(); - mutex_unlock(&ftrace_sysctl_lock); - - /* Try to totally disable ftrace */ - ftrace_force_shutdown(); -} - /** * register_ftrace_function - register a function for profiling * @ops - ops structure that holds the function for profiling. diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index aeb2f2505bc5..333a5162149b 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3097,7 +3097,7 @@ void ftrace_dump(void) dump_ran = 1; /* No turning back! */ - ftrace_kill_atomic(); + ftrace_kill(); for_each_tracing_cpu(cpu) { atomic_inc(&global_trace.data[cpu]->disabled); -- cgit v1.2.3 From 4d296c24326783bff1282ac72f310d8bac8df413 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 23 Oct 2008 09:33:06 -0400 Subject: ftrace: remove mcount set The arch dependent function ftrace_mcount_set was only used by the daemon start up code. This patch removes it. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- arch/arm/kernel/ftrace.c | 13 ------------- arch/powerpc/kernel/ftrace.c | 17 ----------------- arch/sparc64/kernel/ftrace.c | 18 ------------------ arch/x86/kernel/ftrace.c | 7 ------- include/linux/ftrace.h | 1 - kernel/trace/ftrace.c | 9 --------- 6 files changed, 65 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c index 76d50e6091bc..6c90479e8974 100644 --- a/arch/arm/kernel/ftrace.c +++ b/arch/arm/kernel/ftrace.c @@ -95,19 +95,6 @@ int ftrace_update_ftrace_func(ftrace_func_t func) return ret; } -int ftrace_mcount_set(unsigned long *data) -{ - unsigned long pc, old; - unsigned long *addr = data; - unsigned char *new; - - pc = (unsigned long)&mcount_call; - memcpy(&old, &mcount_call, MCOUNT_INSN_SIZE); - new = ftrace_call_replace(pc, *addr); - *addr = ftrace_modify_code(pc, (unsigned char *)&old, new); - return 0; -} - /* run from kstop_machine */ int __init ftrace_dyn_arch_init(void *data) { diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index 3855ceb937b0..6b75522e8b34 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -126,23 +126,6 @@ notrace int ftrace_update_ftrace_func(ftrace_func_t func) return ret; } -notrace int ftrace_mcount_set(unsigned long *data) -{ - unsigned long ip = (long)(&mcount_call); - unsigned long *addr = data; - unsigned char old[MCOUNT_INSN_SIZE], *new; - - /* - * Replace the mcount stub with a pointer to the - * ip recorder function. - */ - memcpy(old, &mcount_call, MCOUNT_INSN_SIZE); - new = ftrace_call_replace(ip, *addr); - *addr = ftrace_modify_code(ip, old, new); - - return 0; -} - int __init ftrace_dyn_arch_init(void *data) { /* This is running in kstop_machine */ diff --git a/arch/sparc64/kernel/ftrace.c b/arch/sparc64/kernel/ftrace.c index 4298d0aee713..447942041a7c 100644 --- a/arch/sparc64/kernel/ftrace.c +++ b/arch/sparc64/kernel/ftrace.c @@ -69,24 +69,6 @@ notrace int ftrace_update_ftrace_func(ftrace_func_t func) return ftrace_modify_code(ip, old, new); } -notrace int ftrace_mcount_set(unsigned long *data) -{ - unsigned long ip = (long)(&mcount_call); - unsigned long *addr = data; - unsigned char old[MCOUNT_INSN_SIZE], *new; - - /* - * Replace the mcount stub with a pointer to the - * ip recorder function. - */ - memcpy(old, &mcount_call, MCOUNT_INSN_SIZE); - new = ftrace_call_replace(ip, *addr); - *addr = ftrace_modify_code(ip, old, new); - - return 0; -} - - int __init ftrace_dyn_arch_init(void *data) { ftrace_mcount_set(data); diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index da4fb0deecf7..b399eed23538 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -103,13 +103,6 @@ notrace int ftrace_update_ftrace_func(ftrace_func_t func) return ret; } -notrace int ftrace_mcount_set(unsigned long *data) -{ - /* mcount is initialized as a nop */ - *data = 0; - return 0; -} - int __init ftrace_dyn_arch_init(void *data) { extern const unsigned char ftrace_test_p6nop[]; diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index ac58e94668b7..1c4835f86911 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -71,7 +71,6 @@ extern int ftrace_ip_converted(unsigned long ip); extern unsigned char *ftrace_nop_replace(void); extern unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr); extern int ftrace_dyn_arch_init(void *data); -extern int ftrace_mcount_set(unsigned long *data); extern int ftrace_update_ftrace_func(ftrace_func_t func); extern void ftrace_caller(void); extern void ftrace_call(void); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index e758cab0836f..226fd9132d53 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -620,7 +620,6 @@ static int ftrace_update_code(void *ignore); static int __ftrace_modify_code(void *data) { - unsigned long addr; int *command = data; if (*command & FTRACE_ENABLE_CALLS) { @@ -639,14 +638,6 @@ static int __ftrace_modify_code(void *data) if (*command & FTRACE_UPDATE_TRACE_FUNC) ftrace_update_ftrace_func(ftrace_trace_function); - if (*command & FTRACE_ENABLE_MCOUNT) { - addr = (unsigned long)ftrace_record_ip; - ftrace_mcount_set(&addr); - } else if (*command & FTRACE_DISABLE_MCOUNT) { - addr = (unsigned long)ftrace_stub; - ftrace_mcount_set(&addr); - } - return 0; } -- cgit v1.2.3 From 08f5ac906d2c0faf96d608c54a0b03177376da8d Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 23 Oct 2008 09:33:07 -0400 Subject: ftrace: remove ftrace hash The ftrace hash was used by the ftrace_daemon code. The record ip function would place the calling address (ip) into the hash. The daemon would later read the hash and modify that code. The hash complicates the code. This patch removes it. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- include/linux/ftrace.h | 8 +- kernel/trace/ftrace.c | 243 +++++++------------------------------------------ kernel/trace/trace.c | 3 - 3 files changed, 38 insertions(+), 216 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 1c4835f86911..703eb53cfa2b 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -44,8 +44,6 @@ static inline void ftrace_kill(void) { } #endif /* CONFIG_FUNCTION_TRACER */ #ifdef CONFIG_DYNAMIC_FTRACE -# define FTRACE_HASHBITS 10 -# define FTRACE_HASHSIZE (1< #include #include -#include #include #include @@ -189,9 +188,7 @@ static int ftrace_filtered; static int tracing_on; static int frozen_record_count; -static struct hlist_head ftrace_hash[FTRACE_HASHSIZE]; - -static DEFINE_PER_CPU(int, ftrace_shutdown_disable_cpu); +static LIST_HEAD(ftrace_new_addrs); static DEFINE_MUTEX(ftrace_regex_lock); @@ -210,8 +207,6 @@ struct ftrace_page { static struct ftrace_page *ftrace_pages_start; static struct ftrace_page *ftrace_pages; -static int ftrace_record_suspend; - static struct dyn_ftrace *ftrace_free_records; @@ -242,72 +237,6 @@ static inline int record_frozen(struct dyn_ftrace *rec) # define record_frozen(rec) ({ 0; }) #endif /* CONFIG_KPROBES */ -int skip_trace(unsigned long ip) -{ - unsigned long fl; - struct dyn_ftrace *rec; - struct hlist_node *t; - struct hlist_head *head; - - if (frozen_record_count == 0) - return 0; - - head = &ftrace_hash[hash_long(ip, FTRACE_HASHBITS)]; - hlist_for_each_entry_rcu(rec, t, head, node) { - if (rec->ip == ip) { - if (record_frozen(rec)) { - if (rec->flags & FTRACE_FL_FAILED) - return 1; - - if (!(rec->flags & FTRACE_FL_CONVERTED)) - return 1; - - if (!tracing_on || !ftrace_enabled) - return 1; - - if (ftrace_filtered) { - fl = rec->flags & (FTRACE_FL_FILTER | - FTRACE_FL_NOTRACE); - if (!fl || (fl & FTRACE_FL_NOTRACE)) - return 1; - } - } - break; - } - } - - return 0; -} - -static inline int -ftrace_ip_in_hash(unsigned long ip, unsigned long key) -{ - struct dyn_ftrace *p; - struct hlist_node *t; - int found = 0; - - hlist_for_each_entry_rcu(p, t, &ftrace_hash[key], node) { - if (p->ip == ip) { - found = 1; - break; - } - } - - return found; -} - -static inline void -ftrace_add_hash(struct dyn_ftrace *node, unsigned long key) -{ - hlist_add_head_rcu(&node->node, &ftrace_hash[key]); -} - -/* called from kstop_machine */ -static inline void ftrace_del_hash(struct dyn_ftrace *node) -{ - hlist_del(&node->node); -} - static void ftrace_free_rec(struct dyn_ftrace *rec) { rec->ip = (unsigned long)ftrace_free_records; @@ -362,69 +291,36 @@ static struct dyn_ftrace *ftrace_alloc_dyn_node(unsigned long ip) } if (ftrace_pages->index == ENTRIES_PER_PAGE) { - if (!ftrace_pages->next) - return NULL; + if (!ftrace_pages->next) { + /* allocate another page */ + ftrace_pages->next = + (void *)get_zeroed_page(GFP_KERNEL); + if (!ftrace_pages->next) + return NULL; + } ftrace_pages = ftrace_pages->next; } return &ftrace_pages->records[ftrace_pages->index++]; } -static void +static struct dyn_ftrace * ftrace_record_ip(unsigned long ip) { - struct dyn_ftrace *node; - unsigned long key; - int resched; - int cpu; + struct dyn_ftrace *rec; if (!ftrace_enabled || ftrace_disabled) - return; - - resched = need_resched(); - preempt_disable_notrace(); - - /* - * We simply need to protect against recursion. - * Use the the raw version of smp_processor_id and not - * __get_cpu_var which can call debug hooks that can - * cause a recursive crash here. - */ - cpu = raw_smp_processor_id(); - per_cpu(ftrace_shutdown_disable_cpu, cpu)++; - if (per_cpu(ftrace_shutdown_disable_cpu, cpu) != 1) - goto out; - - if (unlikely(ftrace_record_suspend)) - goto out; - - key = hash_long(ip, FTRACE_HASHBITS); - - FTRACE_WARN_ON_ONCE(key >= FTRACE_HASHSIZE); - - if (ftrace_ip_in_hash(ip, key)) - goto out; - - /* This ip may have hit the hash before the lock */ - if (ftrace_ip_in_hash(ip, key)) - goto out; - - node = ftrace_alloc_dyn_node(ip); - if (!node) - goto out; + return NULL; - node->ip = ip; + rec = ftrace_alloc_dyn_node(ip); + if (!rec) + return NULL; - ftrace_add_hash(node, key); + rec->ip = ip; - out: - per_cpu(ftrace_shutdown_disable_cpu, cpu)--; + list_add(&rec->list, &ftrace_new_addrs); - /* prevent recursion with scheduler */ - if (resched) - preempt_enable_no_resched_notrace(); - else - preempt_enable_notrace(); + return rec; } #define FTRACE_ADDR ((long)(ftrace_caller)) @@ -543,7 +439,6 @@ static void ftrace_replace_code(int enable) rec->flags |= FTRACE_FL_FAILED; if ((system_state == SYSTEM_BOOTING) || !core_kernel_text(rec->ip)) { - ftrace_del_hash(rec); ftrace_free_rec(rec); } } @@ -551,15 +446,6 @@ static void ftrace_replace_code(int enable) } } -static void ftrace_shutdown_replenish(void) -{ - if (ftrace_pages->next) - return; - - /* allocate another page */ - ftrace_pages->next = (void *)get_zeroed_page(GFP_KERNEL); -} - static void print_ip_ins(const char *fmt, unsigned char *p) { int i; @@ -616,18 +502,11 @@ ftrace_code_disable(struct dyn_ftrace *rec) return 1; } -static int ftrace_update_code(void *ignore); - static int __ftrace_modify_code(void *data) { int *command = data; if (*command & FTRACE_ENABLE_CALLS) { - /* - * Update any recorded ips now that we have the - * machine stopped - */ - ftrace_update_code(NULL); ftrace_replace_code(1); tracing_on = 1; } else if (*command & FTRACE_DISABLE_CALLS) { @@ -738,84 +617,34 @@ static cycle_t ftrace_update_time; static unsigned long ftrace_update_cnt; unsigned long ftrace_update_tot_cnt; -static int ftrace_update_code(void *ignore) +static int ftrace_update_code(void) { - int i, save_ftrace_enabled; + struct dyn_ftrace *p, *t; cycle_t start, stop; - struct dyn_ftrace *p; - struct hlist_node *t, *n; - struct hlist_head *head, temp_list; - - /* Don't be recording funcs now */ - ftrace_record_suspend++; - save_ftrace_enabled = ftrace_enabled; - ftrace_enabled = 0; start = ftrace_now(raw_smp_processor_id()); ftrace_update_cnt = 0; - /* No locks needed, the machine is stopped! */ - for (i = 0; i < FTRACE_HASHSIZE; i++) { - INIT_HLIST_HEAD(&temp_list); - head = &ftrace_hash[i]; + list_for_each_entry_safe(p, t, &ftrace_new_addrs, list) { - /* all CPUS are stopped, we are safe to modify code */ - hlist_for_each_entry_safe(p, t, n, head, node) { - /* Skip over failed records which have not been - * freed. */ - if (p->flags & FTRACE_FL_FAILED) - continue; + /* If something went wrong, bail without enabling anything */ + if (unlikely(ftrace_disabled)) + return -1; - /* Unconverted records are always at the head of the - * hash bucket. Once we encounter a converted record, - * simply skip over to the next bucket. Saves ftraced - * some processor cycles (ftrace does its bid for - * global warming :-p ). */ - if (p->flags & (FTRACE_FL_CONVERTED)) - break; + list_del_init(&p->list); - /* Ignore updates to this record's mcount site. - * Reintroduce this record at the head of this - * bucket to attempt to "convert" it again if - * the kprobe on it is unregistered before the - * next run. */ - if (get_kprobe((void *)p->ip)) { - ftrace_del_hash(p); - INIT_HLIST_NODE(&p->node); - hlist_add_head(&p->node, &temp_list); - freeze_record(p); - continue; - } else { - unfreeze_record(p); - } - - /* convert record (i.e, patch mcount-call with NOP) */ - if (ftrace_code_disable(p)) { - p->flags |= FTRACE_FL_CONVERTED; - ftrace_update_cnt++; - } else { - if ((system_state == SYSTEM_BOOTING) || - !core_kernel_text(p->ip)) { - ftrace_del_hash(p); - ftrace_free_rec(p); - } - } - } - - hlist_for_each_entry_safe(p, t, n, &temp_list, node) { - hlist_del(&p->node); - INIT_HLIST_NODE(&p->node); - hlist_add_head(&p->node, head); - } + /* convert record (i.e, patch mcount-call with NOP) */ + if (ftrace_code_disable(p)) { + p->flags |= FTRACE_FL_CONVERTED; + ftrace_update_cnt++; + } else + ftrace_free_rec(p); } stop = ftrace_now(raw_smp_processor_id()); ftrace_update_time = stop - start; ftrace_update_tot_cnt += ftrace_update_cnt; - ftrace_enabled = save_ftrace_enabled; - ftrace_record_suspend--; - return 0; } @@ -847,7 +676,7 @@ static int __init ftrace_dyn_table_alloc(unsigned long num_to_init) pg = ftrace_pages = ftrace_pages_start; cnt = num_to_init / ENTRIES_PER_PAGE; - pr_info("ftrace: allocating %ld hash entries in %d pages\n", + pr_info("ftrace: allocating %ld entries in %d pages\n", num_to_init, cnt); for (i = 0; i < cnt; i++) { @@ -1451,20 +1280,18 @@ static int ftrace_convert_nops(unsigned long *start, unsigned long addr; unsigned long flags; + mutex_lock(&ftrace_start_lock); p = start; while (p < end) { addr = ftrace_call_adjust(*p++); - /* should not be called from interrupt context */ - spin_lock(&ftrace_lock); ftrace_record_ip(addr); - spin_unlock(&ftrace_lock); - ftrace_shutdown_replenish(); } - /* p is ignored */ + /* disable interrupts to prevent kstop machine */ local_irq_save(flags); - ftrace_update_code(p); + ftrace_update_code(); local_irq_restore(flags); + mutex_unlock(&ftrace_start_lock); return 0; } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 333a5162149b..06951e229443 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -865,9 +865,6 @@ function_trace_call(unsigned long ip, unsigned long parent_ip) if (unlikely(!ftrace_function_enabled)) return; - if (skip_trace(ip)) - return; - pc = preempt_count(); resched = need_resched(); preempt_disable_notrace(); -- cgit v1.2.3 From c3a90c788b743303c4d824780a3a7271693fb64a Mon Sep 17 00:00:00 2001 From: Remi Denis-Courmont Date: Sun, 26 Oct 2008 23:07:25 -0700 Subject: Phonet: do not reply to indication reset packets This fixes a potential error packet loop. Signed-off-by: Remi Denis-Courmont Signed-off-by: David S. Miller --- include/linux/phonet.h | 1 + net/phonet/af_phonet.c | 5 ++++- 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/phonet.h b/include/linux/phonet.h index c9609f9aedac..4157faa857b6 100644 --- a/include/linux/phonet.h +++ b/include/linux/phonet.h @@ -72,6 +72,7 @@ struct phonetmsg { } pn_msg_u; }; #define PN_COMMON_MESSAGE 0xF0 +#define PN_COMMGR 0x10 #define PN_PREFIX 0xE0 /* resource for extended messages */ #define pn_submsg_id pn_msg_u.base.pn_submsg_id #define pn_e_submsg_id pn_msg_u.ext.pn_e_submsg_id diff --git a/net/phonet/af_phonet.c b/net/phonet/af_phonet.c index b9d97effebe3..defeb7a0d502 100644 --- a/net/phonet/af_phonet.c +++ b/net/phonet/af_phonet.c @@ -261,6 +261,8 @@ static inline int can_respond(struct sk_buff *skb) return 0; /* we are not the destination */ if (ph->pn_res == PN_PREFIX && !pskb_may_pull(skb, 5)) return 0; + if (ph->pn_res == PN_COMMGR) /* indications */ + return 0; ph = pn_hdr(skb); /* re-acquires the pointer */ pm = pn_msg(skb); @@ -309,7 +311,8 @@ static int send_reset_indications(struct sk_buff *rskb) return pn_raw_send(data, sizeof(data), rskb->dev, pn_object(oph->pn_sdev, 0x00), - pn_object(oph->pn_rdev, oph->pn_robj), 0x10); + pn_object(oph->pn_rdev, oph->pn_robj), + PN_COMMGR); } -- cgit v1.2.3 From 5550af4df179e52753d3a43a788a113ad8cd95cd Mon Sep 17 00:00:00 2001 From: Sheng Yang Date: Wed, 15 Oct 2008 20:15:06 +0800 Subject: KVM: Fix guest shared interrupt with in-kernel irqchip Every call of kvm_set_irq() should offer an irq_source_id, which is allocated by kvm_request_irq_source_id(). Based on irq_source_id, we identify the irq source and implement logical OR for shared level interrupts. The allocated irq_source_id can be freed by kvm_free_irq_source_id(). Currently, we support at most sizeof(unsigned long) different irq sources. [Amit: - rebase to kvm.git HEAD - move definition of KVM_USERSPACE_IRQ_SOURCE_ID to common file - move kvm_request_irq_source_id to the update_irq ioctl] [Xiantao: - Add kvm/ia64 stuff and make it work for kvm/ia64 guests] Signed-off-by: Sheng Yang Signed-off-by: Amit Shah Signed-off-by: Xiantao Zhang Signed-off-by: Avi Kivity --- arch/ia64/include/asm/kvm_host.h | 3 +++ arch/ia64/kvm/kvm-ia64.c | 8 +++++--- arch/x86/include/asm/kvm_host.h | 3 +++ arch/x86/kvm/i8254.c | 11 +++++++++-- arch/x86/kvm/i8254.h | 1 + arch/x86/kvm/x86.c | 6 +++++- include/linux/kvm_host.h | 7 ++++++- virt/kvm/irq_comm.c | 42 +++++++++++++++++++++++++++++++++++++--- virt/kvm/kvm_main.c | 12 ++++++++---- 9 files changed, 79 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/arch/ia64/include/asm/kvm_host.h b/arch/ia64/include/asm/kvm_host.h index 85db124d37f6..04c0b88f7b3a 100644 --- a/arch/ia64/include/asm/kvm_host.h +++ b/arch/ia64/include/asm/kvm_host.h @@ -417,6 +417,9 @@ struct kvm_arch { struct list_head assigned_dev_head; struct dmar_domain *intel_iommu_domain; struct hlist_head irq_ack_notifier_list; + + unsigned long irq_sources_bitmap; + unsigned long irq_states[KVM_IOAPIC_NUM_PINS]; }; union cpuid3_t { diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index a312c9e9b9ef..8a2b13ff0aff 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -778,6 +778,9 @@ static void kvm_init_vm(struct kvm *kvm) kvm_build_io_pmt(kvm); INIT_LIST_HEAD(&kvm->arch.assigned_dev_head); + + /* Reserve bit 0 of irq_sources_bitmap for userspace irq source */ + set_bit(KVM_USERSPACE_IRQ_SOURCE_ID, &kvm->arch.irq_sources_bitmap); } struct kvm *kvm_arch_create_vm(void) @@ -941,9 +944,8 @@ long kvm_arch_vm_ioctl(struct file *filp, goto out; if (irqchip_in_kernel(kvm)) { mutex_lock(&kvm->lock); - kvm_ioapic_set_irq(kvm->arch.vioapic, - irq_event.irq, - irq_event.level); + kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, + irq_event.irq, irq_event.level); mutex_unlock(&kvm->lock); r = 0; } diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 65679d006337..8346be87cfa1 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -364,6 +364,9 @@ struct kvm_arch{ struct page *ept_identity_pagetable; bool ept_identity_pagetable_done; + + unsigned long irq_sources_bitmap; + unsigned long irq_states[KVM_IOAPIC_NUM_PINS]; }; struct kvm_vm_stat { diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 11c6725fb798..8772dc946823 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -545,6 +545,12 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm) if (!pit) return NULL; + mutex_lock(&kvm->lock); + pit->irq_source_id = kvm_request_irq_source_id(kvm); + mutex_unlock(&kvm->lock); + if (pit->irq_source_id < 0) + return NULL; + mutex_init(&pit->pit_state.lock); mutex_lock(&pit->pit_state.lock); spin_lock_init(&pit->pit_state.inject_lock); @@ -587,6 +593,7 @@ void kvm_free_pit(struct kvm *kvm) mutex_lock(&kvm->arch.vpit->pit_state.lock); timer = &kvm->arch.vpit->pit_state.pit_timer.timer; hrtimer_cancel(timer); + kvm_free_irq_source_id(kvm, kvm->arch.vpit->irq_source_id); mutex_unlock(&kvm->arch.vpit->pit_state.lock); kfree(kvm->arch.vpit); } @@ -595,8 +602,8 @@ void kvm_free_pit(struct kvm *kvm) static void __inject_pit_timer_intr(struct kvm *kvm) { mutex_lock(&kvm->lock); - kvm_set_irq(kvm, 0, 1); - kvm_set_irq(kvm, 0, 0); + kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 1); + kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 0); mutex_unlock(&kvm->lock); } diff --git a/arch/x86/kvm/i8254.h b/arch/x86/kvm/i8254.h index e436d4983aa1..4178022b97aa 100644 --- a/arch/x86/kvm/i8254.h +++ b/arch/x86/kvm/i8254.h @@ -44,6 +44,7 @@ struct kvm_pit { struct kvm_io_device speaker_dev; struct kvm *kvm; struct kvm_kpit_state pit_state; + int irq_source_id; }; #define KVM_PIT_BASE_ADDRESS 0x40 diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 4f0677d1eae8..f1f8ff2f1fa2 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1742,7 +1742,8 @@ long kvm_arch_vm_ioctl(struct file *filp, goto out; if (irqchip_in_kernel(kvm)) { mutex_lock(&kvm->lock); - kvm_set_irq(kvm, irq_event.irq, irq_event.level); + kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, + irq_event.irq, irq_event.level); mutex_unlock(&kvm->lock); r = 0; } @@ -4013,6 +4014,9 @@ struct kvm *kvm_arch_create_vm(void) INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); INIT_LIST_HEAD(&kvm->arch.assigned_dev_head); + /* Reserve bit 0 of irq_sources_bitmap for userspace irq source */ + set_bit(KVM_USERSPACE_IRQ_SOURCE_ID, &kvm->arch.irq_sources_bitmap); + return kvm; } diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 3833c48fae3a..bb92be2153bc 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -37,6 +37,8 @@ #define KVM_REQ_UNHALT 6 #define KVM_REQ_MMU_SYNC 7 +#define KVM_USERSPACE_IRQ_SOURCE_ID 0 + struct kvm_vcpu; extern struct kmem_cache *kvm_vcpu_cache; @@ -306,15 +308,18 @@ struct kvm_assigned_dev_kernel { int host_irq; int guest_irq; int irq_requested; + int irq_source_id; struct pci_dev *dev; struct kvm *kvm; }; -void kvm_set_irq(struct kvm *kvm, int irq, int level); +void kvm_set_irq(struct kvm *kvm, int irq_source_id, int irq, int level); void kvm_notify_acked_irq(struct kvm *kvm, unsigned gsi); void kvm_register_irq_ack_notifier(struct kvm *kvm, struct kvm_irq_ack_notifier *kian); void kvm_unregister_irq_ack_notifier(struct kvm *kvm, struct kvm_irq_ack_notifier *kian); +int kvm_request_irq_source_id(struct kvm *kvm); +void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id); #ifdef CONFIG_DMAR int kvm_iommu_map_pages(struct kvm *kvm, gfn_t base_gfn, diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index d0169f5e6047..55ad76ee2d09 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -25,15 +25,23 @@ #include "ioapic.h" /* This should be called with the kvm->lock mutex held */ -void kvm_set_irq(struct kvm *kvm, int irq, int level) +void kvm_set_irq(struct kvm *kvm, int irq_source_id, int irq, int level) { + unsigned long *irq_state = (unsigned long *)&kvm->arch.irq_states[irq]; + + /* Logical OR for level trig interrupt */ + if (level) + set_bit(irq_source_id, irq_state); + else + clear_bit(irq_source_id, irq_state); + /* Not possible to detect if the guest uses the PIC or the * IOAPIC. So set the bit in both. The guest will ignore * writes to the unused one. */ - kvm_ioapic_set_irq(kvm->arch.vioapic, irq, level); + kvm_ioapic_set_irq(kvm->arch.vioapic, irq, !!(*irq_state)); #ifdef CONFIG_X86 - kvm_pic_set_irq(pic_irqchip(kvm), irq, level); + kvm_pic_set_irq(pic_irqchip(kvm), irq, !!(*irq_state)); #endif } @@ -58,3 +66,31 @@ void kvm_unregister_irq_ack_notifier(struct kvm *kvm, { hlist_del(&kian->link); } + +/* The caller must hold kvm->lock mutex */ +int kvm_request_irq_source_id(struct kvm *kvm) +{ + unsigned long *bitmap = &kvm->arch.irq_sources_bitmap; + int irq_source_id = find_first_zero_bit(bitmap, + sizeof(kvm->arch.irq_sources_bitmap)); + if (irq_source_id >= sizeof(kvm->arch.irq_sources_bitmap)) { + printk(KERN_WARNING "kvm: exhaust allocatable IRQ sources!\n"); + irq_source_id = -EFAULT; + } else + set_bit(irq_source_id, bitmap); + return irq_source_id; +} + +void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id) +{ + int i; + + if (irq_source_id <= 0 || + irq_source_id >= sizeof(kvm->arch.irq_sources_bitmap)) { + printk(KERN_ERR "kvm: IRQ source ID out of range!\n"); + return; + } + for (i = 0; i < KVM_IOAPIC_NUM_PINS; i++) + clear_bit(irq_source_id, &kvm->arch.irq_states[i]); + clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap); +} diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index cf0ab8ed3845..a87f45edfae8 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -105,14 +105,12 @@ static void kvm_assigned_dev_interrupt_work_handler(struct work_struct *work) */ mutex_lock(&assigned_dev->kvm->lock); kvm_set_irq(assigned_dev->kvm, + assigned_dev->irq_source_id, assigned_dev->guest_irq, 1); mutex_unlock(&assigned_dev->kvm->lock); kvm_put_kvm(assigned_dev->kvm); } -/* FIXME: Implement the OR logic needed to make shared interrupts on - * this line behave properly - */ static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id) { struct kvm_assigned_dev_kernel *assigned_dev = @@ -134,7 +132,7 @@ static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian) dev = container_of(kian, struct kvm_assigned_dev_kernel, ack_notifier); - kvm_set_irq(dev->kvm, dev->guest_irq, 0); + kvm_set_irq(dev->kvm, dev->irq_source_id, dev->guest_irq, 0); enable_irq(dev->host_irq); } @@ -146,6 +144,7 @@ static void kvm_free_assigned_device(struct kvm *kvm, free_irq(assigned_dev->host_irq, (void *)assigned_dev); kvm_unregister_irq_ack_notifier(kvm, &assigned_dev->ack_notifier); + kvm_free_irq_source_id(kvm, assigned_dev->irq_source_id); if (cancel_work_sync(&assigned_dev->interrupt_work)) /* We had pending work. That means we will have to take @@ -215,6 +214,11 @@ static int kvm_vm_ioctl_assign_irq(struct kvm *kvm, match->ack_notifier.gsi = assigned_irq->guest_irq; match->ack_notifier.irq_acked = kvm_assigned_dev_ack_irq; kvm_register_irq_ack_notifier(kvm, &match->ack_notifier); + r = kvm_request_irq_source_id(kvm); + if (r < 0) + goto out_release; + else + match->irq_source_id = r; /* Even though this is PCI, we don't want to use shared * interrupts. Sharing host devices with guest-assigned devices -- cgit v1.2.3 From bb45e202e695dea8657bb03a01d1522c37558672 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Sun, 19 Oct 2008 16:39:45 +0200 Subject: KVM: Future-proof device assignment ABI Reserve some space so we can add more data. Signed-off-by: Avi Kivity --- include/linux/kvm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 797fcd781242..f18b86fa8655 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -489,6 +489,9 @@ struct kvm_assigned_pci_dev { __u32 busnr; __u32 devfn; __u32 flags; + union { + __u32 reserved[12]; + }; }; struct kvm_assigned_irq { @@ -496,6 +499,9 @@ struct kvm_assigned_irq { __u32 host_irq; __u32 guest_irq; __u32 flags; + union { + __u32 reserved[12]; + }; }; #define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) -- cgit v1.2.3