perf: Move task_pt_regs sampling into arch code

On x86_64, at least, task_pt_regs may be only partially initialized
in many contexts, so x86_64 should not use it without extra care
from interrupt context, let alone NMI context.

This will allow x86_64 to override the logic and will supply some
scratch space to use to make a cleaner copy of user regs.

Tested-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: chenggang.qcg@taobao.com
Cc: Wu Fengguang <fengguang.wu@intel.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Jean Pihet <jean.pihet@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mark Salter <msalter@redhat.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Will Deacon <will.deacon@arm.com>
Cc: linux-arm-kernel@lists.infradead.org
Link: http://lkml.kernel.org/r/e431cd4c18c2e1c44c774f10758527fb2d1025c4.1420396372.git.luto@amacapital.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/arm/kernel/perf_regs.c b/arch/arm/kernel/perf_regs.c
index 6e4379c..592dda3 100644 (file)
--- a/arch/arm/kernel/perf_regs.c
+++ b/arch/arm/kernel/perf_regs.c
@@ -28,3 +28,11 @@ u64 perf_reg_abi(struct task_struct *task)
 {
        return PERF_SAMPLE_REGS_ABI_32;
 }
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+                       struct pt_regs *regs,
+                       struct pt_regs *regs_user_copy)
+{
+       regs_user->regs = task_pt_regs(current);
+       regs_user->abi = perf_reg_abi(current);
+}

diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c
index 6762ad7..3f62b35 100644 (file)
--- a/arch/arm64/kernel/perf_regs.c
+++ b/arch/arm64/kernel/perf_regs.c
@@ -50,3 +50,11 @@ u64 perf_reg_abi(struct task_struct *task)
        else
                return PERF_SAMPLE_REGS_ABI_64;
 }
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+                       struct pt_regs *regs,
+                       struct pt_regs *regs_user_copy)
+{
+       regs_user->regs = task_pt_regs(current);
+       regs_user->abi = perf_reg_abi(current);
+}

diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index e309cc5..3bbbb1a 100644 (file)
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -78,6 +78,14 @@ u64 perf_reg_abi(struct task_struct *task)
 {
        return PERF_SAMPLE_REGS_ABI_32;
 }
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+                       struct pt_regs *regs,
+                       struct pt_regs *regs_user_copy)
+{
+       regs_user->regs = task_pt_regs(current);
+       regs_user->abi = perf_reg_abi(current);
+}
 #else /* CONFIG_X86_64 */
 #define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \
                       (1ULL << PERF_REG_X86_ES) | \
@@ -102,4 +110,12 @@ u64 perf_reg_abi(struct task_struct *task)
        else
                return PERF_SAMPLE_REGS_ABI_64;
 }
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+                       struct pt_regs *regs,
+                       struct pt_regs *regs_user_copy)
+{
+       regs_user->regs = task_pt_regs(current);
+       regs_user->abi = perf_reg_abi(current);
+}
 #endif /* CONFIG_X86_32 */

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 486e84c..4f7a61c 100644 (file)
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -79,11 +79,6 @@ struct perf_branch_stack {
        struct perf_branch_entry        entries[0];
 };
 
-struct perf_regs {
-       __u64           abi;
-       struct pt_regs  *regs;
-};
-
 struct task_struct;
 
 /*
@@ -610,7 +605,14 @@ struct perf_sample_data {
                u32     reserved;
        }                               cpu_entry;
        struct perf_callchain_entry     *callchain;
+
+       /*
+        * regs_user may point to task_pt_regs or to regs_user_copy, depending
+        * on arch details.
+        */
        struct perf_regs                regs_user;
+       struct pt_regs                  regs_user_copy;
+
        struct perf_regs                regs_intr;
        u64                             stack_user_size;
 } ____cacheline_aligned;

diff --git a/include/linux/perf_regs.h b/include/linux/perf_regs.h
index 3c73d5f..a5f98d5 100644 (file)
--- a/include/linux/perf_regs.h
+++ b/include/linux/perf_regs.h
@@ -1,11 +1,19 @@
 #ifndef _LINUX_PERF_REGS_H
 #define _LINUX_PERF_REGS_H
 
+struct perf_regs {
+       __u64           abi;
+       struct pt_regs  *regs;
+};
+
 #ifdef CONFIG_HAVE_PERF_REGS
 #include <asm/perf_regs.h>
 u64 perf_reg_value(struct pt_regs *regs, int idx);
 int perf_reg_validate(u64 mask);
 u64 perf_reg_abi(struct task_struct *task);
+void perf_get_regs_user(struct perf_regs *regs_user,
+                       struct pt_regs *regs,
+                       struct pt_regs *regs_user_copy);
 #else
 static inline u64 perf_reg_value(struct pt_regs *regs, int idx)
 {
@@ -21,5 +29,13 @@ static inline u64 perf_reg_abi(struct task_struct *task)
 {
        return PERF_SAMPLE_REGS_ABI_NONE;
 }
+
+static inline void perf_get_regs_user(struct perf_regs *regs_user,
+                                     struct pt_regs *regs,
+                                     struct pt_regs *regs_user_copy)
+{
+       regs_user->regs = task_pt_regs(current);
+       regs_user->abi = perf_reg_abi(current);
+}
 #endif /* CONFIG_HAVE_PERF_REGS */
 #endif /* _LINUX_PERF_REGS_H */

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4c1ee7f..882f835 100644 (file)
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4461,18 +4461,14 @@ perf_output_sample_regs(struct perf_output_handle *handle,
 }
 
 static void perf_sample_regs_user(struct perf_regs *regs_user,
-                                 struct pt_regs *regs)
+                                 struct pt_regs *regs,
+                                 struct pt_regs *regs_user_copy)
 {
-       if (!user_mode(regs)) {
-               if (current->mm)
-                       regs = task_pt_regs(current);
-               else
-                       regs = NULL;
-       }
-
-       if (regs) {
-               regs_user->abi  = perf_reg_abi(current);
+       if (user_mode(regs)) {
+               regs_user->abi = perf_reg_abi(current);
                regs_user->regs = regs;
+       } else if (current->mm) {
+               perf_get_regs_user(regs_user, regs, regs_user_copy);
        } else {
                regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE;
                regs_user->regs = NULL;
@@ -4951,7 +4947,8 @@ void perf_prepare_sample(struct perf_event_header *header,
        }
 
        if (sample_type & (PERF_SAMPLE_REGS_USER | PERF_SAMPLE_STACK_USER))
-               perf_sample_regs_user(&data->regs_user, regs);
+               perf_sample_regs_user(&data->regs_user, regs,
+                                     &data->regs_user_copy);
 
        if (sample_type & PERF_SAMPLE_REGS_USER) {
                /* regs dump ABI info */