perf: Generalize some arch callchain code

- Most archs use one callchain buffer per cpu, except x86 that needs
  to deal with NMIs. Provide a default perf_callchain_buffer()
  implementation that x86 overrides.

- Centralize all the kernel/user regs handling and invoke new arch
  handlers from there: perf_callchain_user() / perf_callchain_kernel()
  That avoid all the user_mode(), current->mm checks and so...

- Invert some parameters in perf_callchain_*() helpers: entry to the
  left, regs to the right, following the traditional (dst, src).

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Acked-by: Paul Mackerras <paulus@samba.org>
Tested-by: Will Deacon <will.deacon@arm.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: David Miller <davem@davemloft.net>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Borislav Petkov <bp@amd64.org>

5 files changed, 43 insertions, 177 deletions

diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index a07c3b1955f0..0e3bbdb15927 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -3044,17 +3044,13 @@ user_backtrace(struct frame_tail *tail,
         return buftail.fp - 1;
 }
 
-static void
-perf_callchain_user(struct pt_regs *regs,
-                    struct perf_callchain_entry *entry)
+void
+perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
         struct frame_tail *tail;
 
         perf_callchain_store(entry, PERF_CONTEXT_USER);
 
-        if (!user_mode(regs))
-                regs = task_pt_regs(current);
-
         tail = (struct frame_tail *)regs->ARM_fp - 1;
 
         while (tail && !((unsigned long)tail & 0x3))
@@ -3075,9 +3071,8 @@ callchain_trace(struct stackframe *fr,
         return 0;
 }
 
-static void
-perf_callchain_kernel(struct pt_regs *regs,
-                      struct perf_callchain_entry *entry)
+void
+perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
         struct stackframe fr;
 
@@ -3088,33 +3083,3 @@ perf_callchain_kernel(struct pt_regs *regs,
         fr.pc = regs->ARM_pc;
         walk_stackframe(&fr, callchain_trace, entry);
 }
-
-static void
-perf_do_callchain(struct pt_regs *regs,
-                  struct perf_callchain_entry *entry)
-{
-        int is_user;
-
-        if (!regs)
-                return;
-
-        is_user = user_mode(regs);
-
-        if (!is_user)
-                perf_callchain_kernel(regs, entry);
-
-        if (current->mm)
-                perf_callchain_user(regs, entry);
-}
-
-static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_irq_entry);
-
-struct perf_callchain_entry *
-perf_callchain(struct pt_regs *regs)
-{
-        struct perf_callchain_entry *entry = &__get_cpu_var(pmc_irq_entry);
-
-        entry->nr = 0;
-        perf_do_callchain(regs, entry);
-        return entry;
-}
diff --git a/arch/powerpc/kernel/perf_callchain.c b/arch/powerpc/kernel/perf_callchain.c
index a286c2e5a3ea..f7a85ede8407 100644
--- a/arch/powerpc/kernel/perf_callchain.c
+++ b/arch/powerpc/kernel/perf_callchain.c
@@ -46,8 +46,8 @@ static int valid_next_sp(unsigned long sp, unsigned long prev_sp)
         return 0;
 }
 
-static void perf_callchain_kernel(struct pt_regs *regs,
-                                  struct perf_callchain_entry *entry)
+void
+perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
         unsigned long sp, next_sp;
         unsigned long next_ip;
@@ -221,8 +221,8 @@ static int sane_signal_64_frame(unsigned long sp)
                 puc == (unsigned long) &sf->uc;
 }
 
-static void perf_callchain_user_64(struct pt_regs *regs,
-                                   struct perf_callchain_entry *entry)
+static void perf_callchain_user_64(struct perf_callchain_entry *entry,
+                                   struct pt_regs *regs)
 {
         unsigned long sp, next_sp;
         unsigned long next_ip;
@@ -303,8 +303,8 @@ static int read_user_stack_32(unsigned int __user *ptr, unsigned int *ret)
         return __get_user_inatomic(*ret, ptr);
 }
 
-static inline void perf_callchain_user_64(struct pt_regs *regs,
-                                          struct perf_callchain_entry *entry)
+static inline void perf_callchain_user_64(struct perf_callchain_entry *entry,
+                                          struct pt_regs *regs)
 {
 }
 
@@ -423,8 +423,8 @@ static unsigned int __user *signal_frame_32_regs(unsigned int sp,
         return mctx->mc_gregs;
 }
 
-static void perf_callchain_user_32(struct pt_regs *regs,
-                                   struct perf_callchain_entry *entry)
+static void perf_callchain_user_32(struct perf_callchain_entry *entry,
+                                   struct pt_regs *regs)
 {
         unsigned int sp, next_sp;
         unsigned int next_ip;
@@ -471,32 +471,11 @@ static void perf_callchain_user_32(struct pt_regs *regs,
         }
 }
 
-/*
- * Since we can't get PMU interrupts inside a PMU interrupt handler,
- * we don't need separate irq and nmi entries here.
- */
-static DEFINE_PER_CPU(struct perf_callchain_entry, cpu_perf_callchain);
-
-struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
+void
+perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
-        struct perf_callchain_entry *entry = &__get_cpu_var(cpu_perf_callchain);
-
-        entry->nr = 0;
-
-        if (!user_mode(regs)) {
-                perf_callchain_kernel(regs, entry);
-                if (current->mm)
-                        regs = task_pt_regs(current);
-                else
-                        regs = NULL;
-        }
-
-        if (regs) {
-                if (current_is_64bit())
-                        perf_callchain_user_64(regs, entry);
-                else
-                        perf_callchain_user_32(regs, entry);
-        }
-
-        return entry;
+        if (current_is_64bit())
+                perf_callchain_user_64(entry, regs);
+        else
+                perf_callchain_user_32(entry, regs);
 }
diff --git a/arch/sh/kernel/perf_callchain.c b/arch/sh/kernel/perf_callchain.c
index 00143f3dd196..ef076a91292a 100644
--- a/arch/sh/kernel/perf_callchain.c
+++ b/arch/sh/kernel/perf_callchain.c
@@ -44,44 +44,11 @@ static const struct stacktrace_ops callchain_ops = {
         .address        = callchain_address,
 };
 
-static void
-perf_callchain_kernel(struct pt_regs *regs, struct perf_callchain_entry *entry)
+void
+perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
         perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
         perf_callchain_store(entry, regs->pc);
 
         unwind_stack(NULL, regs, NULL, &callchain_ops, entry);
 }
-
-static void
-perf_do_callchain(struct pt_regs *regs, struct perf_callchain_entry *entry)
-{
-        int is_user;
-
-        if (!regs)
-                return;
-
-        is_user = user_mode(regs);
-
-        /*
-         * Only the kernel side is implemented for now.
-         */
-        if (!is_user)
-                perf_callchain_kernel(regs, entry);
-}
-
-/*
- * No need for separate IRQ and NMI entries.
- */
-static DEFINE_PER_CPU(struct perf_callchain_entry, callchain);
-
-struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
-{
-        struct perf_callchain_entry *entry = &__get_cpu_var(callchain);
-
-        entry->nr = 0;
-
-        perf_do_callchain(regs, entry);
-
-        return entry;
-}
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index 2a95a9079862..460162d74aba 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -1283,14 +1283,16 @@ void __init init_hw_perf_events(void)
         register_die_notifier(&perf_event_nmi_notifier);
 }
 
-static void perf_callchain_kernel(struct pt_regs *regs,
-                                  struct perf_callchain_entry *entry)
+void perf_callchain_kernel(struct perf_callchain_entry *entry,
+                           struct pt_regs *regs)
 {
         unsigned long ksp, fp;
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
         int graph = 0;
 #endif
 
+        stack_trace_flush();
+
         perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
         perf_callchain_store(entry, regs->tpc);
 
@@ -1330,8 +1332,8 @@ static void perf_callchain_kernel(struct pt_regs *regs,
         } while (entry->nr < PERF_MAX_STACK_DEPTH);
 }
 
-static void perf_callchain_user_64(struct pt_regs *regs,
-                                   struct perf_callchain_entry *entry)
+static void perf_callchain_user_64(struct perf_callchain_entry *entry,
+                                   struct pt_regs *regs)
 {
         unsigned long ufp;
 
@@ -1353,8 +1355,8 @@ static void perf_callchain_user_64(struct pt_regs *regs,
         } while (entry->nr < PERF_MAX_STACK_DEPTH);
 }
 
-static void perf_callchain_user_32(struct pt_regs *regs,
-                                   struct perf_callchain_entry *entry)
+static void perf_callchain_user_32(struct perf_callchain_entry *entry,
+                                   struct pt_regs *regs)
 {
         unsigned long ufp;
 
@@ -1376,30 +1378,12 @@ static void perf_callchain_user_32(struct pt_regs *regs,
         } while (entry->nr < PERF_MAX_STACK_DEPTH);
 }
 
-/* Like powerpc we can't get PMU interrupts within the PMU handler,
- * so no need for separate NMI and IRQ chains as on x86.
- */
-static DEFINE_PER_CPU(struct perf_callchain_entry, callchain);
-
-struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
+void
+perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
-        struct perf_callchain_entry *entry = &__get_cpu_var(callchain);
-
-        entry->nr = 0;
-        if (!user_mode(regs)) {
-                stack_trace_flush();
-                perf_callchain_kernel(regs, entry);
-                if (current->mm)
-                        regs = task_pt_regs(current);
-                else
-                        regs = NULL;
-        }
-        if (regs) {
-                flushw_user();
-                if (test_thread_flag(TIF_32BIT))
-                        perf_callchain_user_32(regs, entry);
-                else
-                        perf_callchain_user_64(regs, entry);
-        }
-        return entry;
+        flushw_user();
+        if (test_thread_flag(TIF_32BIT))
+                perf_callchain_user_32(entry, regs);
+        else
+                perf_callchain_user_64(entry, regs);
 }
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 8af28caeafc1..39f8421b86e6 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1571,9 +1571,7 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
  * callchain support
  */
 
-
-static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_irq_entry);
-static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_nmi_entry);
+static DEFINE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry_nmi);
 
 
 static void
@@ -1607,8 +1605,8 @@ static const struct stacktrace_ops backtrace_ops = {
         .walk_stack             = print_context_stack_bp,
 };
 
-static void
-perf_callchain_kernel(struct pt_regs *regs, struct perf_callchain_entry *entry)
+void
+perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
         perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
         perf_callchain_store(entry, regs->ip);
@@ -1653,14 +1651,12 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
 }
 #endif
 
-static void
-perf_callchain_user(struct pt_regs *regs, struct perf_callchain_entry *entry)
+void
+perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
         struct stack_frame frame;
         const void __user *fp;
 
-        if (!user_mode(regs))
-                regs = task_pt_regs(current);
 
         fp = (void __user *)regs->bp;
 
@@ -1687,42 +1683,17 @@ perf_callchain_user(struct pt_regs *regs, struct perf_callchain_entry *entry)
         }
 }
 
-static void
-perf_do_callchain(struct pt_regs *regs, struct perf_callchain_entry *entry)
-{
-        int is_user;
-
-        if (!regs)
-                return;
-
-        is_user = user_mode(regs);
-
-        if (!is_user)
-                perf_callchain_kernel(regs, entry);
-
-        if (current->mm)
-                perf_callchain_user(regs, entry);
-}
-
-struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
+struct perf_callchain_entry *perf_callchain_buffer(void)
 {
-        struct perf_callchain_entry *entry;
-
         if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
                 /* TODO: We don't support guest os callchain now */
                 return NULL;
         }
 
         if (in_nmi())
-                entry = &__get_cpu_var(pmc_nmi_entry);
-        else
-                entry = &__get_cpu_var(pmc_irq_entry);
-
-        entry->nr = 0;
-
-        perf_do_callchain(regs, entry);
+                return &__get_cpu_var(perf_callchain_entry_nmi);
 
-        return entry;
+        return &__get_cpu_var(perf_callchain_entry);
 }
 
 unsigned long perf_instruction_pointer(struct pt_regs *regs)