From 345c25730d085c45622ac779da4dbd97dc3a10fe Mon Sep 17 00:00:00 2001 From: Barry Kasindorf Date: Tue, 22 Jul 2008 21:08:54 +0200 Subject: x86/oprofile: add IBS support for AMD CPUs, IBS buffer handling routines This patchset supports the new profiling hardware available in the latest AMD CPUs in the oProfile driver. Signed-off-by: Barry Kasindorf Signed-off-by: Robert Richter Cc: oprofile-list Signed-off-by: Ingo Molnar --- drivers/oprofile/cpu_buffer.c | 68 ++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 67 insertions(+), 1 deletion(-) (limited to 'drivers/oprofile/cpu_buffer.c') diff --git a/drivers/oprofile/cpu_buffer.c b/drivers/oprofile/cpu_buffer.c index 2450b3a393ff..c9ac4e156918 100644 --- a/drivers/oprofile/cpu_buffer.c +++ b/drivers/oprofile/cpu_buffer.c @@ -5,6 +5,7 @@ * @remark Read the file COPYING * * @author John Levon + * @author Barry Kasindorf * * Each CPU has a local buffer that stores PC value/event * pairs. We also log context switches when we notice them. @@ -207,7 +208,7 @@ static int log_sample(struct oprofile_cpu_buffer * cpu_buf, unsigned long pc, return 1; } -static int oprofile_begin_trace(struct oprofile_cpu_buffer * cpu_buf) +static int oprofile_begin_trace(struct oprofile_cpu_buffer *cpu_buf) { if (nr_available_slots(cpu_buf) < 4) { cpu_buf->sample_lost_overflow++; @@ -252,6 +253,71 @@ void oprofile_add_sample(struct pt_regs * const regs, unsigned long event) oprofile_add_ext_sample(pc, regs, event, is_kernel); } +#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) +{ + struct task_struct *task; + + cpu_buf->sample_received++; + + if (nr_available_slots(cpu_buf) < MAX_IBS_SAMPLE_SIZE) { + cpu_buf->sample_lost_overflow++; + return 0; + } + + is_kernel = !!is_kernel; + + /* notice a switch from user->kernel or vice versa */ + if (cpu_buf->last_is_kernel != is_kernel) { + cpu_buf->last_is_kernel = is_kernel; + add_code(cpu_buf, is_kernel); + } + + /* notice a task switch */ + if (!is_kernel) { + task = current; + + if (cpu_buf->last_task != task) { + cpu_buf->last_task = task; + add_code(cpu_buf, (unsigned long)task); + } + } + + add_code(cpu_buf, ibs_code); + add_sample(cpu_buf, ibs[0], ibs[1]); + add_sample(cpu_buf, ibs[2], ibs[3]); + add_sample(cpu_buf, ibs[4], ibs[5]); + + if (ibs_code == IBS_OP_BEGIN) { + add_sample(cpu_buf, ibs[6], ibs[7]); + add_sample(cpu_buf, ibs[8], ibs[9]); + add_sample(cpu_buf, ibs[10], ibs[11]); + } + + return 1; +} + +void oprofile_add_ibs_sample(struct pt_regs *const regs, + unsigned int * const ibs_sample, u8 code) +{ + int is_kernel = !user_mode(regs); + unsigned long pc = profile_pc(regs); + + struct oprofile_cpu_buffer *cpu_buf = + &per_cpu(cpu_buffer, smp_processor_id()); + + if (!backtrace_depth) { + log_ibs_sample(cpu_buf, pc, is_kernel, ibs_sample, code); + return; + } + + /* if log_sample() fails we can't backtrace since we lost the source + * of this event */ + if (log_ibs_sample(cpu_buf, pc, is_kernel, ibs_sample, code)) + oprofile_ops.backtrace(regs, backtrace_depth); +} + void oprofile_add_pc(unsigned long pc, int is_kernel, unsigned long event) { struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(cpu_buffer); -- cgit v1.2.3 From 852402cc27bfa1200164e9e8dc7f6e5f0a4fbd46 Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Tue, 22 Jul 2008 21:09:06 +0200 Subject: x86/oprofile: add CONFIG_OPROFILE_IBS option Signed-off-by: Robert Richter Cc: oprofile-list Cc: Robert Richter Cc: Barry Kasindorf Signed-off-by: Ingo Molnar --- arch/Kconfig | 14 ++++++++++++++ arch/x86/oprofile/op_model_athlon.c | 33 +++++++++++++++++++++++---------- drivers/oprofile/buffer_sync.c | 6 ++++++ drivers/oprofile/cpu_buffer.c | 4 ++++ 4 files changed, 47 insertions(+), 10 deletions(-) (limited to 'drivers/oprofile/cpu_buffer.c') diff --git a/arch/Kconfig b/arch/Kconfig index b0fabfa864ff..2651af48b2e5 100644 --- 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 9c8c8c583132..fb6015c1132b 100644 --- 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 e1782d2df09f..ed982273fb8b 100644 --- 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 c9ac4e156918..aba905b3afb8 100644 --- 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); -- cgit v1.2.3 From bd17b625c09d1ed14c4d98604186b0bbb314f6b2 Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Tue, 22 Jul 2008 21:09:07 +0200 Subject: oprofile: fix printk in cpu_buffer.c Signed-off-by: Robert Richter Cc: oprofile-list Cc: Robert Richter Cc: Barry Kasindorf Signed-off-by: Ingo Molnar --- drivers/oprofile/cpu_buffer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/oprofile/cpu_buffer.c') diff --git a/drivers/oprofile/cpu_buffer.c b/drivers/oprofile/cpu_buffer.c index aba905b3afb8..4decab624e76 100644 --- a/drivers/oprofile/cpu_buffer.c +++ b/drivers/oprofile/cpu_buffer.c @@ -364,7 +364,7 @@ static void wq_sync_buffer(struct work_struct *work) struct oprofile_cpu_buffer * b = container_of(work, struct oprofile_cpu_buffer, work.work); if (b->cpu != smp_processor_id()) { - printk("WQ on CPU%d, prefer CPU%d\n", + printk(KERN_DEBUG "WQ on CPU%d, prefer CPU%d\n", smp_processor_id(), b->cpu); } sync_buffer(b->cpu); -- cgit v1.2.3