perf/arch: Remove perf_sample_data::regs_user_copy

struct perf_sample_data lives on-stack, we should be careful about it's
size. Furthermore, the pt_regs copy in there is only because x86_64 is a
trainwreck, solve it differently.

Reported-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Steven Rostedt <rostedt@goodmis.org>
Link: https://lkml.kernel.org/r/20201030151955.258178461@infradead.org

diff --git a/arch/arm/kernel/perf_regs.c b/arch/arm/kernel/perf_regs.c
index 05fe92a..0529f90 100644 (file)
--- a/arch/arm/kernel/perf_regs.c
+++ b/arch/arm/kernel/perf_regs.c
@@ -32,8 +32,7 @@ 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)
+                       struct pt_regs *regs)
 {
        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 94e8718..f6f58e6 100644 (file)
--- a/arch/arm64/kernel/perf_regs.c
+++ b/arch/arm64/kernel/perf_regs.c
@@ -73,8 +73,7 @@ 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)
+                       struct pt_regs *regs)
 {
        regs_user->regs = task_pt_regs(current);
        regs_user->abi = perf_reg_abi(current);

diff --git a/arch/csky/kernel/perf_regs.c b/arch/csky/kernel/perf_regs.c
index eb32838..09b7f88 100644 (file)
--- a/arch/csky/kernel/perf_regs.c
+++ b/arch/csky/kernel/perf_regs.c
@@ -32,8 +32,7 @@ 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)
+                       struct pt_regs *regs)
 {
        regs_user->regs = task_pt_regs(current);
        regs_user->abi = perf_reg_abi(current);

diff --git a/arch/powerpc/perf/perf_regs.c b/arch/powerpc/perf/perf_regs.c
index 8e53f2f..6f681b1 100644 (file)
--- a/arch/powerpc/perf/perf_regs.c
+++ b/arch/powerpc/perf/perf_regs.c
@@ -144,8 +144,7 @@ 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)
+                       struct pt_regs *regs)
 {
        regs_user->regs = task_pt_regs(current);
        regs_user->abi = (regs_user->regs) ? perf_reg_abi(current) :

diff --git a/arch/riscv/kernel/perf_regs.c b/arch/riscv/kernel/perf_regs.c
index 04a38fb..fd304a2 100644 (file)
--- a/arch/riscv/kernel/perf_regs.c
+++ b/arch/riscv/kernel/perf_regs.c
@@ -36,8 +36,7 @@ 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)
+                       struct pt_regs *regs)
 {
        regs_user->regs = task_pt_regs(current);
        regs_user->abi = perf_reg_abi(current);

diff --git a/arch/s390/kernel/perf_regs.c b/arch/s390/kernel/perf_regs.c
index 4352a50..6e9e5d5 100644 (file)
--- a/arch/s390/kernel/perf_regs.c
+++ b/arch/s390/kernel/perf_regs.c
@@ -53,8 +53,7 @@ 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)
+                       struct pt_regs *regs)
 {
        /*
         * Use the regs from the first interruption and let

diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index bb7e113..f9e5352 100644 (file)
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -101,8 +101,7 @@ 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)
+                       struct pt_regs *regs)
 {
        regs_user->regs = task_pt_regs(current);
        regs_user->abi = perf_reg_abi(current);
@@ -129,12 +128,20 @@ u64 perf_reg_abi(struct task_struct *task)
                return PERF_SAMPLE_REGS_ABI_64;
 }
 
+static DEFINE_PER_CPU(struct pt_regs, nmi_user_regs);
+
 void perf_get_regs_user(struct perf_regs *regs_user,
-                       struct pt_regs *regs,
-                       struct pt_regs *regs_user_copy)
+                       struct pt_regs *regs)
 {
+       struct pt_regs *regs_user_copy = this_cpu_ptr(&nmi_user_regs);
        struct pt_regs *user_regs = task_pt_regs(current);
 
+       if (!in_nmi()) {
+               regs_user->regs = user_regs;
+               regs_user->abi = perf_reg_abi(current);
+               return;
+       }
+
        /*
         * If we're in an NMI that interrupted task_pt_regs setup, then
         * we can't sample user regs at all.  This check isn't really

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index b775ae0..96450f6 100644 (file)
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1022,13 +1022,7 @@ struct perf_sample_data {
        struct perf_callchain_entry     *callchain;
        u64                             aux_size;
 
-       /*
-        * 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;
 

diff --git a/include/linux/perf_regs.h b/include/linux/perf_regs.h
index 2d12e97..f632c57 100644 (file)
--- a/include/linux/perf_regs.h
+++ b/include/linux/perf_regs.h
@@ -20,8 +20,7 @@ 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);
+                       struct pt_regs *regs);
 #else
 
 #define PERF_REG_EXTENDED_MASK 0
@@ -42,8 +41,7 @@ static inline u64 perf_reg_abi(struct task_struct *task)
 }
 
 static inline void perf_get_regs_user(struct perf_regs *regs_user,
-                                     struct pt_regs *regs,
-                                     struct pt_regs *regs_user_copy)
+                                     struct pt_regs *regs)
 {
        regs_user->regs = task_pt_regs(current);
        regs_user->abi = perf_reg_abi(current);

diff --git a/kernel/events/core.c b/kernel/events/core.c
index fc681c7..d67c9cb 100644 (file)
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6374,14 +6374,13 @@ 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_user_copy)
+                                 struct pt_regs *regs)
 {
        if (user_mode(regs)) {
                regs_user->abi = perf_reg_abi(current);
                regs_user->regs = regs;
        } else if (!(current->flags & PF_KTHREAD)) {
-               perf_get_regs_user(regs_user, regs, regs_user_copy);
+               perf_get_regs_user(regs_user, regs);
        } else {
                regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE;
                regs_user->regs = NULL;
@@ -7083,8 +7082,7 @@ 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,
-                                     &data->regs_user_copy);
+               perf_sample_regs_user(&data->regs_user, regs);
 
        if (sample_type & PERF_SAMPLE_REGS_USER) {
                /* regs dump ABI info */