x86/oprofile: add CONFIG_OPROFILE_IBS option

Signed-off-by: Robert Richter <robert.richter@amd.com>
Cc: oprofile-list <oprofile-list@lists.sourceforge.net>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Barry Kasindorf <barry.kasindorf@amd.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/arch/Kconfig b/arch/Kconfig
index b0fabfa864ffa12be40160f9b2c6d3b1010ab149..2651af48b2e508cf39492ca1dcd4462ff7004d0d 100644 (file)
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -13,6 +13,20 @@ config OPROFILE
 
          If unsure, say N.
 
+config OPROFILE_IBS
+       bool "OProfile AMD IBS support (EXPERIMENTAL)"
+       default n
+       depends on OPROFILE && SMP && X86
+       help
+          Instruction-Based Sampling (IBS) is a new profiling
+          technique that provides rich, precise program performance
+          information. IBS is introduced by AMD Family10h processors
+          (AMD Opteron Quad-Core processor “Barcelona”) to overcome
+          the limitations of conventional performance counter
+          sampling.
+
+         If unsure, say N.
+
 config HAVE_OPROFILE
        def_bool n
 

diff --git a/arch/x86/oprofile/op_model_athlon.c b/arch/x86/oprofile/op_model_athlon.c
index 9c8c8c58313246ad9a859c42fdad29e92b0ef931..fb6015c1132b6d8ce93fa7d391e706101bf655fe 100644 (file)
--- a/arch/x86/oprofile/op_model_athlon.c
+++ b/arch/x86/oprofile/op_model_athlon.c
@@ -47,6 +47,10 @@
 #define CTRL_SET_HOST_ONLY(val, h) (val |= ((h & 1) << 9))
 #define CTRL_SET_GUEST_ONLY(val, h) (val |= ((h & 1) << 8))
 
+static unsigned long reset_value[NUM_COUNTERS];
+
+#ifdef CONFIG_OPROFILE_IBS
+
 /* IbsFetchCtl bits/masks */
 #define IBS_FETCH_HIGH_VALID_BIT       (1UL << 17)     /* bit 49 */
 #define IBS_FETCH_HIGH_ENABLE          (1UL << 16)     /* bit 48 */
@@ -104,7 +108,6 @@ struct ibs_op_sample {
 */
 static void clear_ibs_nmi(void);
 
-static unsigned long reset_value[NUM_COUNTERS];
 static int ibs_allowed;        /* AMD Family10h and later */
 
 struct op_ibs_config {
@@ -118,6 +121,8 @@ struct op_ibs_config {
 
 static struct op_ibs_config ibs_config;
 
+#endif
+
 /* functions for op_amd_spec */
 
 static void op_amd_fill_in_addresses(struct op_msrs * const msrs)
@@ -188,6 +193,8 @@ static void op_amd_setup_ctrs(struct op_msrs const * const msrs)
        }
 }
 
+#ifdef CONFIG_OPROFILE_IBS
+
 static inline int
 op_amd_handle_ibs(struct pt_regs * const regs,
                  struct op_msrs const * const msrs)
@@ -261,6 +268,8 @@ op_amd_handle_ibs(struct pt_regs * const regs,
        return 1;
 }
 
+#endif
+
 static int op_amd_check_ctrs(struct pt_regs * const regs,
                             struct op_msrs const * const msrs)
 {
@@ -277,7 +286,9 @@ static int op_amd_check_ctrs(struct pt_regs * const regs,
                }
        }
 
+#ifdef CONFIG_OPROFILE_IBS
        op_amd_handle_ibs(regs, msrs);
+#endif
 
        /* See op_model_ppro.c */
        return 1;
@@ -294,6 +305,8 @@ static void op_amd_start(struct op_msrs const * const msrs)
                        CTRL_WRITE(low, high, msrs, i);
                }
        }
+
+#ifdef CONFIG_OPROFILE_IBS
        if (ibs_allowed && ibs_config.fetch_enabled) {
                low = (ibs_config.max_cnt_fetch >> 4) & 0xFFFF;
                high = IBS_FETCH_HIGH_ENABLE;
@@ -305,6 +318,7 @@ static void op_amd_start(struct op_msrs const * const msrs)
                high = 0;
                wrmsr(MSR_AMD64_IBSOPCTL, low, high);
        }
+#endif
 }
 
 
@@ -323,6 +337,7 @@ static void op_amd_stop(struct op_msrs const * const msrs)
                CTRL_WRITE(low, high, msrs, i);
        }
 
+#ifdef CONFIG_OPROFILE_IBS
        if (ibs_allowed && ibs_config.fetch_enabled) {
                low = 0;                /* clear max count and enable */
                high = 0;
@@ -334,6 +349,7 @@ static void op_amd_stop(struct op_msrs const * const msrs)
                high = 0;
                wrmsr(MSR_AMD64_IBSOPCTL, low, high);
        }
+#endif
 }
 
 static void op_amd_shutdown(struct op_msrs const * const msrs)
@@ -350,17 +366,10 @@ static void op_amd_shutdown(struct op_msrs const * const msrs)
        }
 }
 
-#ifndef CONFIG_SMP
+#ifndef CONFIG_OPROFILE_IBS
 
 /* no IBS support */
 
-static void setup_ibs(void)
-{
-       ibs_allowed = 0;
-}
-
-static void clear_ibs_nmi(void) {}
-
 static int op_amd_init(struct oprofile_operations *ops)
 {
        return 0;
@@ -441,8 +450,12 @@ static void setup_ibs(void)
        if (!ibs_allowed)
                return;
 
-       if (pfm_amd64_setup_eilvt())
+       if (pfm_amd64_setup_eilvt()) {
                ibs_allowed = 0;
+               return;
+       }
+
+       printk(KERN_INFO "oprofile: AMD IBS detected\n");
 }
 
 

diff --git a/drivers/oprofile/buffer_sync.c b/drivers/oprofile/buffer_sync.c
index e1782d2df09f444555abbee971682cafbb4b246e..ed982273fb8b1d9311aba68a3b2a42de5d174e78 100644 (file)
--- a/drivers/oprofile/buffer_sync.c
+++ b/drivers/oprofile/buffer_sync.c
@@ -328,6 +328,8 @@ static void add_trace_begin(void)
        add_event_entry(TRACE_BEGIN_CODE);
 }
 
+#ifdef CONFIG_OPROFILE_IBS
+
 #define IBS_FETCH_CODE_SIZE    2
 #define IBS_OP_CODE_SIZE       5
 #define IBS_EIP(offset)                                \
@@ -390,6 +392,8 @@ static void add_ibs_begin(struct oprofile_cpu_buffer *cpu_buf, int code,
        }
 }
 
+#endif
+
 static void add_sample_entry(unsigned long offset, unsigned long event)
 {
        add_event_entry(offset);
@@ -586,6 +590,7 @@ void sync_buffer(int cpu)
                        } else if (s->event == CPU_TRACE_BEGIN) {
                                state = sb_bt_start;
                                add_trace_begin();
+#ifdef CONFIG_OPROFILE_IBS
                        } else if (s->event == IBS_FETCH_BEGIN) {
                                state = sb_bt_start;
                                add_ibs_begin(cpu_buf,
@@ -594,6 +599,7 @@ void sync_buffer(int cpu)
                                state = sb_bt_start;
                                add_ibs_begin(cpu_buf,
                                        IBS_OP_CODE, in_kernel, mm);
+#endif
                        } else {
                                struct mm_struct *oldmm = mm;
 

diff --git a/drivers/oprofile/cpu_buffer.c b/drivers/oprofile/cpu_buffer.c
index c9ac4e1569186f1857b827df78924ad09ac34183..aba905b3afb8eac02dd64693a04b4f58ae514f7a 100644 (file)
--- a/drivers/oprofile/cpu_buffer.c
+++ b/drivers/oprofile/cpu_buffer.c
@@ -253,6 +253,8 @@ void oprofile_add_sample(struct pt_regs * const regs, unsigned long event)
        oprofile_add_ext_sample(pc, regs, event, is_kernel);
 }
 
+#ifdef CONFIG_OPROFILE_IBS
+
 #define MAX_IBS_SAMPLE_SIZE    14
 static int log_ibs_sample(struct oprofile_cpu_buffer *cpu_buf,
        unsigned long pc, int is_kernel, unsigned  int *ibs, int ibs_code)
@@ -318,6 +320,8 @@ void oprofile_add_ibs_sample(struct pt_regs *const regs,
                oprofile_ops.backtrace(regs, backtrace_depth);
 }
 
+#endif
+
 void oprofile_add_pc(unsigned long pc, int is_kernel, unsigned long event)
 {
        struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(cpu_buffer);