Merge branch 'wip-2.6.34' into old-private-masterarchived-private-master

1 files changed, 200 insertions, 197 deletions

diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 527e17eae575..4d6d711717f2 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -1,5 +1,6 @@
 #include <trace/syscall.h>
 #include <trace/events/syscalls.h>
+#include <linux/slab.h>
 #include <linux/kernel.h>
 #include <linux/ftrace.h>
 #include <linux/perf_event.h>
@@ -14,6 +15,43 @@ static int sys_refcount_exit;
 static DECLARE_BITMAP(enabled_enter_syscalls, NR_syscalls);
 static DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls);
 
+extern unsigned long __start_syscalls_metadata[];
+extern unsigned long __stop_syscalls_metadata[];
+
+static struct syscall_metadata **syscalls_metadata;
+
+static struct syscall_metadata *find_syscall_meta(unsigned long syscall)
+{
+        struct syscall_metadata *start;
+        struct syscall_metadata *stop;
+        char str[KSYM_SYMBOL_LEN];
+
+
+        start = (struct syscall_metadata *)__start_syscalls_metadata;
+        stop = (struct syscall_metadata *)__stop_syscalls_metadata;
+        kallsyms_lookup(syscall, NULL, NULL, NULL, str);
+
+        for ( ; start < stop; start++) {
+                /*
+                 * Only compare after the "sys" prefix. Archs that use
+                 * syscall wrappers may have syscalls symbols aliases prefixed
+                 * with "SyS" instead of "sys", leading to an unwanted
+                 * mismatch.
+                 */
+                if (start->name && !strcmp(start->name + 3, str + 3))
+                        return start;
+        }
+        return NULL;
+}
+
+static struct syscall_metadata *syscall_nr_to_meta(int nr)
+{
+        if (!syscalls_metadata || nr >= NR_syscalls || nr < 0)
+                return NULL;
+
+        return syscalls_metadata[nr];
+}
+
 enum print_line_t
 print_syscall_enter(struct trace_iterator *iter, int flags)
 {
@@ -30,7 +68,7 @@ print_syscall_enter(struct trace_iterator *iter, int flags)
         if (!entry)
                 goto end;
 
-        if (entry->enter_id != ent->type) {
+        if (entry->enter_event->id != ent->type) {
                 WARN_ON_ONCE(1);
                 goto end;
         }
@@ -85,7 +123,7 @@ print_syscall_exit(struct trace_iterator *iter, int flags)
                 return TRACE_TYPE_HANDLED;
         }
 
-        if (entry->exit_id != ent->type) {
+        if (entry->exit_event->id != ent->type) {
                 WARN_ON_ONCE(1);
                 return TRACE_TYPE_UNHANDLED;
         }
@@ -103,92 +141,79 @@ extern char *__bad_type_size(void);
 #define SYSCALL_FIELD(type, name)                                       \
         sizeof(type) != sizeof(trace.name) ?                            \
                 __bad_type_size() :                                     \
-                #type, #name, offsetof(typeof(trace), name), sizeof(trace.name)
+                #type, #name, offsetof(typeof(trace), name),            \
+                sizeof(trace.name), is_signed_type(type)
 
-int syscall_enter_format(struct ftrace_event_call *call, struct trace_seq *s)
+static
+int  __set_enter_print_fmt(struct syscall_metadata *entry, char *buf, int len)
 {
         int i;
-        int nr;
-        int ret;
-        struct syscall_metadata *entry;
-        struct syscall_trace_enter trace;
-        int offset = offsetof(struct syscall_trace_enter, args);
+        int pos = 0;
 
-        nr = syscall_name_to_nr(call->data);
-        entry = syscall_nr_to_meta(nr);
-
-        if (!entry)
-                return 0;
-
-        ret = trace_seq_printf(s, "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n",
-                               SYSCALL_FIELD(int, nr));
-        if (!ret)
-                return 0;
+        /* When len=0, we just calculate the needed length */
+#define LEN_OR_ZERO (len ? len - pos : 0)
 
+        pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
         for (i = 0; i < entry->nb_args; i++) {
-                ret = trace_seq_printf(s, "\tfield:%s %s;", entry->types[i],
-                                        entry->args[i]);
-                if (!ret)
-                        return 0;
-                ret = trace_seq_printf(s, "\toffset:%d;\tsize:%zu;\n", offset,
-                                       sizeof(unsigned long));
-                if (!ret)
-                        return 0;
-                offset += sizeof(unsigned long);
+                pos += snprintf(buf + pos, LEN_OR_ZERO, "%s: 0x%%0%zulx%s",
+                                entry->args[i], sizeof(unsigned long),
+                                i == entry->nb_args - 1 ? "" : ", ");
         }
+        pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
 
-        trace_seq_puts(s, "\nprint fmt: \"");
         for (i = 0; i < entry->nb_args; i++) {
-                ret = trace_seq_printf(s, "%s: 0x%%0%zulx%s", entry->args[i],
-                                        sizeof(unsigned long),
-                                        i == entry->nb_args - 1 ? "" : ", ");
-                if (!ret)
-                        return 0;
+                pos += snprintf(buf + pos, LEN_OR_ZERO,
+                                ", ((unsigned long)(REC->%s))", entry->args[i]);
         }
-        trace_seq_putc(s, '"');
 
-        for (i = 0; i < entry->nb_args; i++) {
-                ret = trace_seq_printf(s, ", ((unsigned long)(REC->%s))",
-                                       entry->args[i]);
-                if (!ret)
-                        return 0;
-        }
+#undef LEN_OR_ZERO
 
-        return trace_seq_putc(s, '\n');
+        /* return the length of print_fmt */
+        return pos;
 }
 
-int syscall_exit_format(struct ftrace_event_call *call, struct trace_seq *s)
+static int set_syscall_print_fmt(struct ftrace_event_call *call)
 {
-        int ret;
-        struct syscall_trace_exit trace;
+        char *print_fmt;
+        int len;
+        struct syscall_metadata *entry = call->data;
 
-        ret = trace_seq_printf(s,
-                               "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
-                               "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n",
-                               SYSCALL_FIELD(int, nr),
-                               SYSCALL_FIELD(long, ret));
-        if (!ret)
+        if (entry->enter_event != call) {
+                call->print_fmt = "\"0x%lx\", REC->ret";
                 return 0;
+        }
+
+        /* First: called with 0 length to calculate the needed length */
+        len = __set_enter_print_fmt(entry, NULL, 0);
+
+        print_fmt = kmalloc(len + 1, GFP_KERNEL);
+        if (!print_fmt)
+                return -ENOMEM;
+
+        /* Second: actually write the @print_fmt */
+        __set_enter_print_fmt(entry, print_fmt, len + 1);
+        call->print_fmt = print_fmt;
+
+        return 0;
+}
+
+static void free_syscall_print_fmt(struct ftrace_event_call *call)
+{
+        struct syscall_metadata *entry = call->data;
 
-        return trace_seq_printf(s, "\nprint fmt: \"0x%%lx\", REC->ret\n");
+        if (entry->enter_event == call)
+                kfree(call->print_fmt);
 }
 
 int syscall_enter_define_fields(struct ftrace_event_call *call)
 {
         struct syscall_trace_enter trace;
-        struct syscall_metadata *meta;
+        struct syscall_metadata *meta = call->data;
         int ret;
-        int nr;
         int i;
         int offset = offsetof(typeof(trace), args);
 
-        nr = syscall_name_to_nr(call->data);
-        meta = syscall_nr_to_meta(nr);
-
-        if (!meta)
-                return 0;
-
-        ret = trace_define_common_fields(call);
+        ret = trace_define_field(call, SYSCALL_FIELD(int, nr), FILTER_OTHER);
         if (ret)
                 return ret;
 
@@ -208,11 +233,11 @@ int syscall_exit_define_fields(struct ftrace_event_call *call)
         struct syscall_trace_exit trace;
         int ret;
 
-        ret = trace_define_common_fields(call);
+        ret = trace_define_field(call, SYSCALL_FIELD(int, nr), FILTER_OTHER);
         if (ret)
                 return ret;
 
-        ret = trace_define_field(call, SYSCALL_FIELD(long, ret), 0,
+        ret = trace_define_field(call, SYSCALL_FIELD(long, ret),
                                  FILTER_OTHER);
 
         return ret;
@@ -239,8 +264,8 @@ void ftrace_syscall_enter(struct pt_regs *regs, long id)
 
         size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args;
 
-        event = trace_current_buffer_lock_reserve(&buffer, sys_data->enter_id,
-                                                  size, 0, 0);
+        event = trace_current_buffer_lock_reserve(&buffer,
+                        sys_data->enter_event->id, size, 0, 0);
         if (!event)
                 return;
 
@@ -271,8 +296,8 @@ void ftrace_syscall_exit(struct pt_regs *regs, long ret)
         if (!sys_data)
                 return;
 
-        event = trace_current_buffer_lock_reserve(&buffer, sys_data->exit_id,
-                                sizeof(*entry), 0, 0);
+        event = trace_current_buffer_lock_reserve(&buffer,
+                        sys_data->exit_event->id, sizeof(*entry), 0, 0);
         if (!event)
                 return;
 
@@ -285,23 +310,18 @@ void ftrace_syscall_exit(struct pt_regs *regs, long ret)
                 trace_current_buffer_unlock_commit(buffer, event, 0, 0);
 }
 
-int reg_event_syscall_enter(void *ptr)
+int reg_event_syscall_enter(struct ftrace_event_call *call)
 {
         int ret = 0;
         int num;
-        char *name;
 
-        name = (char *)ptr;
-        num = syscall_name_to_nr(name);
+        num = ((struct syscall_metadata *)call->data)->syscall_nr;
         if (num < 0 || num >= NR_syscalls)
                 return -ENOSYS;
         mutex_lock(&syscall_trace_lock);
         if (!sys_refcount_enter)
                 ret = register_trace_sys_enter(ftrace_syscall_enter);
-        if (ret) {
-                pr_info("event trace: Could not activate"
-                                "syscall entry trace point");
-        } else {
+        if (!ret) {
                 set_bit(num, enabled_enter_syscalls);
                 sys_refcount_enter++;
         }
@@ -309,13 +329,11 @@ int reg_event_syscall_enter(void *ptr)
         return ret;
 }
 
-void unreg_event_syscall_enter(void *ptr)
+void unreg_event_syscall_enter(struct ftrace_event_call *call)
 {
         int num;
-        char *name;
 
-        name = (char *)ptr;
-        num = syscall_name_to_nr(name);
+        num = ((struct syscall_metadata *)call->data)->syscall_nr;
         if (num < 0 || num >= NR_syscalls)
                 return;
         mutex_lock(&syscall_trace_lock);
@@ -326,23 +344,18 @@ void unreg_event_syscall_enter(void *ptr)
         mutex_unlock(&syscall_trace_lock);
 }
 
-int reg_event_syscall_exit(void *ptr)
+int reg_event_syscall_exit(struct ftrace_event_call *call)
 {
         int ret = 0;
         int num;
-        char *name;
 
-        name = (char *)ptr;
-        num = syscall_name_to_nr(name);
+        num = ((struct syscall_metadata *)call->data)->syscall_nr;
         if (num < 0 || num >= NR_syscalls)
                 return -ENOSYS;
         mutex_lock(&syscall_trace_lock);
         if (!sys_refcount_exit)
                 ret = register_trace_sys_exit(ftrace_syscall_exit);
-        if (ret) {
-                pr_info("event trace: Could not activate"
-                                "syscall exit trace point");
-        } else {
+        if (!ret) {
                 set_bit(num, enabled_exit_syscalls);
                 sys_refcount_exit++;
         }
@@ -350,13 +363,11 @@ int reg_event_syscall_exit(void *ptr)
         return ret;
 }
 
-void unreg_event_syscall_exit(void *ptr)
+void unreg_event_syscall_exit(struct ftrace_event_call *call)
 {
         int num;
-        char *name;
 
-        name = (char *)ptr;
-        num = syscall_name_to_nr(name);
+        num = ((struct syscall_metadata *)call->data)->syscall_nr;
         if (num < 0 || num >= NR_syscalls)
                 return;
         mutex_lock(&syscall_trace_lock);
@@ -367,33 +378,73 @@ void unreg_event_syscall_exit(void *ptr)
         mutex_unlock(&syscall_trace_lock);
 }
 
-struct trace_event event_syscall_enter = {
-        .trace                  = print_syscall_enter,
-};
+int init_syscall_trace(struct ftrace_event_call *call)
+{
+        int id;
+
+        if (set_syscall_print_fmt(call) < 0)
+                return -ENOMEM;
 
-struct trace_event event_syscall_exit = {
-        .trace                  = print_syscall_exit,
-};
+        id = trace_event_raw_init(call);
 
-#ifdef CONFIG_EVENT_PROFILE
+        if (id < 0) {
+                free_syscall_print_fmt(call);
+                return id;
+        }
 
-static DECLARE_BITMAP(enabled_prof_enter_syscalls, NR_syscalls);
-static DECLARE_BITMAP(enabled_prof_exit_syscalls, NR_syscalls);
-static int sys_prof_refcount_enter;
-static int sys_prof_refcount_exit;
+        return id;
+}
+
+unsigned long __init arch_syscall_addr(int nr)
+{
+        return (unsigned long)sys_call_table[nr];
+}
 
-static void prof_syscall_enter(struct pt_regs *regs, long id)
+int __init init_ftrace_syscalls(void)
+{
+        struct syscall_metadata *meta;
+        unsigned long addr;
+        int i;
+
+        syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) *
+                                        NR_syscalls, GFP_KERNEL);
+        if (!syscalls_metadata) {
+                WARN_ON(1);
+                return -ENOMEM;
+        }
+
+        for (i = 0; i < NR_syscalls; i++) {
+                addr = arch_syscall_addr(i);
+                meta = find_syscall_meta(addr);
+                if (!meta)
+                        continue;
+
+                meta->syscall_nr = i;
+                syscalls_metadata[i] = meta;
+        }
+
+        return 0;
+}
+core_initcall(init_ftrace_syscalls);
+
+#ifdef CONFIG_PERF_EVENTS
+
+static DECLARE_BITMAP(enabled_perf_enter_syscalls, NR_syscalls);
+static DECLARE_BITMAP(enabled_perf_exit_syscalls, NR_syscalls);
+static int sys_perf_refcount_enter;
+static int sys_perf_refcount_exit;
+
+static void perf_syscall_enter(struct pt_regs *regs, long id)
 {
         struct syscall_metadata *sys_data;
         struct syscall_trace_enter *rec;
         unsigned long flags;
-        char *raw_data;
         int syscall_nr;
+        int rctx;
         int size;
-        int cpu;
 
         syscall_nr = syscall_get_nr(current, regs);
-        if (!test_bit(syscall_nr, enabled_prof_enter_syscalls))
+        if (!test_bit(syscall_nr, enabled_perf_enter_syscalls))
                 return;
 
         sys_data = syscall_nr_to_meta(syscall_nr);
@@ -405,91 +456,67 @@ static void prof_syscall_enter(struct pt_regs *regs, long id)
         size = ALIGN(size + sizeof(u32), sizeof(u64));
         size -= sizeof(u32);
 
-        if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE,
-                      "profile buffer not large enough"))
+        if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
+                      "perf buffer not large enough"))
                 return;
 
-        /* Protect the per cpu buffer, begin the rcu read side */
-        local_irq_save(flags);
-
-        cpu = smp_processor_id();
-
-        if (in_nmi())
-                raw_data = rcu_dereference(trace_profile_buf_nmi);
-        else
-                raw_data = rcu_dereference(trace_profile_buf);
-
-        if (!raw_data)
-                goto end;
-
-        raw_data = per_cpu_ptr(raw_data, cpu);
-
-        /* zero the dead bytes from align to not leak stack to user */
-        *(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
+        rec = (struct syscall_trace_enter *)perf_trace_buf_prepare(size,
+                                sys_data->enter_event->id, &rctx, &flags);
+        if (!rec)
+                return;
 
-        rec = (struct syscall_trace_enter *) raw_data;
-        tracing_generic_entry_update(&rec->ent, 0, 0);
-        rec->ent.type = sys_data->enter_id;
         rec->nr = syscall_nr;
         syscall_get_arguments(current, regs, 0, sys_data->nb_args,
                                (unsigned long *)&rec->args);
-        perf_tp_event(sys_data->enter_id, 0, 1, rec, size);
-
-end:
-        local_irq_restore(flags);
+        perf_trace_buf_submit(rec, size, rctx, 0, 1, flags, regs);
 }
 
-int reg_prof_syscall_enter(char *name)
+int perf_sysenter_enable(struct ftrace_event_call *call)
 {
         int ret = 0;
         int num;
 
-        num = syscall_name_to_nr(name);
-        if (num < 0 || num >= NR_syscalls)
-                return -ENOSYS;
+        num = ((struct syscall_metadata *)call->data)->syscall_nr;
 
         mutex_lock(&syscall_trace_lock);
-        if (!sys_prof_refcount_enter)
-                ret = register_trace_sys_enter(prof_syscall_enter);
+        if (!sys_perf_refcount_enter)
+                ret = register_trace_sys_enter(perf_syscall_enter);
         if (ret) {
                 pr_info("event trace: Could not activate"
                                 "syscall entry trace point");
         } else {
-                set_bit(num, enabled_prof_enter_syscalls);
-                sys_prof_refcount_enter++;
+                set_bit(num, enabled_perf_enter_syscalls);
+                sys_perf_refcount_enter++;
         }
         mutex_unlock(&syscall_trace_lock);
         return ret;
 }
 
-void unreg_prof_syscall_enter(char *name)
+void perf_sysenter_disable(struct ftrace_event_call *call)
 {
         int num;
 
-        num = syscall_name_to_nr(name);
-        if (num < 0 || num >= NR_syscalls)
-                return;
+        num = ((struct syscall_metadata *)call->data)->syscall_nr;
 
         mutex_lock(&syscall_trace_lock);
-        sys_prof_refcount_enter--;
-        clear_bit(num, enabled_prof_enter_syscalls);
-        if (!sys_prof_refcount_enter)
-                unregister_trace_sys_enter(prof_syscall_enter);
+        sys_perf_refcount_enter--;
+        clear_bit(num, enabled_perf_enter_syscalls);
+        if (!sys_perf_refcount_enter)
+                unregister_trace_sys_enter(perf_syscall_enter);
         mutex_unlock(&syscall_trace_lock);
 }
 
-static void prof_syscall_exit(struct pt_regs *regs, long ret)
+static void perf_syscall_exit(struct pt_regs *regs, long ret)
 {
         struct syscall_metadata *sys_data;
         struct syscall_trace_exit *rec;
         unsigned long flags;
         int syscall_nr;
-        char *raw_data;
+        int rctx;
         int size;
-        int cpu;
 
         syscall_nr = syscall_get_nr(current, regs);
-        if (!test_bit(syscall_nr, enabled_prof_exit_syscalls))
+        if (!test_bit(syscall_nr, enabled_perf_exit_syscalls))
                 return;
 
         sys_data = syscall_nr_to_meta(syscall_nr);
@@ -504,79 +531,55 @@ static void prof_syscall_exit(struct pt_regs *regs, long ret)
          * Impossible, but be paranoid with the future
          * How to put this check outside runtime?
          */
-        if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE,
-                "exit event has grown above profile buffer size"))
+        if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
+                "exit event has grown above perf buffer size"))
                 return;
 
-        /* Protect the per cpu buffer, begin the rcu read side */
-        local_irq_save(flags);
-        cpu = smp_processor_id();
-
-        if (in_nmi())
-                raw_data = rcu_dereference(trace_profile_buf_nmi);
-        else
-                raw_data = rcu_dereference(trace_profile_buf);
-
-        if (!raw_data)
-                goto end;
-
-        raw_data = per_cpu_ptr(raw_data, cpu);
-
-        /* zero the dead bytes from align to not leak stack to user */
-        *(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
-
-        rec = (struct syscall_trace_exit *)raw_data;
+        rec = (struct syscall_trace_exit *)perf_trace_buf_prepare(size,
+                                sys_data->exit_event->id, &rctx, &flags);
+        if (!rec)
+                return;
 
-        tracing_generic_entry_update(&rec->ent, 0, 0);
-        rec->ent.type = sys_data->exit_id;
         rec->nr = syscall_nr;
         rec->ret = syscall_get_return_value(current, regs);
 
-        perf_tp_event(sys_data->exit_id, 0, 1, rec, size);
-
-end:
-        local_irq_restore(flags);
+        perf_trace_buf_submit(rec, size, rctx, 0, 1, flags, regs);
 }
 
-int reg_prof_syscall_exit(char *name)
+int perf_sysexit_enable(struct ftrace_event_call *call)
 {
         int ret = 0;
         int num;
 
-        num = syscall_name_to_nr(name);
-        if (num < 0 || num >= NR_syscalls)
-                return -ENOSYS;
+        num = ((struct syscall_metadata *)call->data)->syscall_nr;
 
         mutex_lock(&syscall_trace_lock);
-        if (!sys_prof_refcount_exit)
-                ret = register_trace_sys_exit(prof_syscall_exit);
+        if (!sys_perf_refcount_exit)
+                ret = register_trace_sys_exit(perf_syscall_exit);
         if (ret) {
                 pr_info("event trace: Could not activate"
-                                "syscall entry trace point");
+                                "syscall exit trace point");
         } else {
-                set_bit(num, enabled_prof_exit_syscalls);
-                sys_prof_refcount_exit++;
+                set_bit(num, enabled_perf_exit_syscalls);
+                sys_perf_refcount_exit++;
         }
         mutex_unlock(&syscall_trace_lock);
         return ret;
 }
 
-void unreg_prof_syscall_exit(char *name)
+void perf_sysexit_disable(struct ftrace_event_call *call)
 {
         int num;
 
-        num = syscall_name_to_nr(name);
-        if (num < 0 || num >= NR_syscalls)
-                return;
+        num = ((struct syscall_metadata *)call->data)->syscall_nr;
 
         mutex_lock(&syscall_trace_lock);
-        sys_prof_refcount_exit--;
-        clear_bit(num, enabled_prof_exit_syscalls);
-        if (!sys_prof_refcount_exit)
-                unregister_trace_sys_exit(prof_syscall_exit);
+        sys_perf_refcount_exit--;
+        clear_bit(num, enabled_perf_exit_syscalls);
+        if (!sys_perf_refcount_exit)
+                unregister_trace_sys_exit(perf_syscall_exit);
         mutex_unlock(&syscall_trace_lock);
 }
 
-#endif
-
+#endif /* CONFIG_PERF_EVENTS */