Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754957Ab2HGNYw (ORCPT ); Tue, 7 Aug 2012 09:24:52 -0400 Received: from mx1.redhat.com ([209.132.183.28]:51185 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754542Ab2HGNVX (ORCPT ); Tue, 7 Aug 2012 09:21:23 -0400 From: Jiri Olsa To: linux-kernel@vger.kernel.org Cc: Arnaldo Carvalho de Melo , Arun Sharma , Benjamin Redelings , Corey Ashford , Cyrill Gorcunov , "Frank Ch. Eigler" , Frederic Weisbecker , Ingo Molnar , Masami Hiramatsu , Paul Mackerras , Peter Zijlstra , Robert Richter , Stephane Eranian , Tom Zanussi , Ulrich Drepper , Jiri Olsa Subject: [PATCH 01/12] perf: Unified API to record selective sets of arch registers Date: Tue, 7 Aug 2012 15:20:36 +0200 Message-Id: <1344345647-11536-2-git-send-email-jolsa@redhat.com> In-Reply-To: <1344345647-11536-1-git-send-email-jolsa@redhat.com> References: <1344345647-11536-1-git-send-email-jolsa@redhat.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 7472 Lines: 254 This brings a new API to help the selective dump of registers on event sampling, and its implementation for x86 arch. Added HAVE_PERF_REGS config option to determine if the architecture provides perf registers ABI. The information about desired registers will be passed in u64 mask. It's up to the architecture to map the registers into the mask bits. For the x86 arch implementation, both 32 and 64 bit registers bits are defined within single enum to ensure 64 bit system can provide register dump for compat task if needed in the future. Original-patch-by: Frederic Weisbecker Cc: Arnaldo Carvalho de Melo Cc: Arun Sharma Cc: Benjamin Redelings Cc: Corey Ashford Cc: Cyrill Gorcunov Cc: Frank Ch. Eigler Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Masami Hiramatsu Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Robert Richter Cc: Stephane Eranian Cc: Tom Zanussi Cc: Ulrich Drepper [ Added missing linux/errno.h include ] Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Jiri Olsa --- arch/Kconfig | 6 +++ arch/x86/Kconfig | 1 + arch/x86/include/asm/perf_regs.h | 33 +++++++++++++++ arch/x86/kernel/Makefile | 2 + arch/x86/kernel/perf_regs.c | 90 ++++++++++++++++++++++++++++++++++++++++ include/linux/perf_regs.h | 19 +++++++++ 6 files changed, 151 insertions(+) create mode 100644 arch/x86/include/asm/perf_regs.h create mode 100644 arch/x86/kernel/perf_regs.c create mode 100644 include/linux/perf_regs.h diff --git a/arch/Kconfig b/arch/Kconfig index 72f2fa1..68d827b 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -222,6 +222,12 @@ config HAVE_PERF_EVENTS_NMI subsystem. Also has support for calculating CPU cycle events to determine how many clock cycles in a given period. +config HAVE_PERF_REGS + bool + help + Support selective register dumps for perf events. This includes + bit-mapping of each registers and a unique architecture id. + config HAVE_ARCH_JUMP_LABEL bool diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 50c660d..b657353 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -60,6 +60,7 @@ config X86 select HAVE_MIXED_BREAKPOINTS_REGS select PERF_EVENTS select HAVE_PERF_EVENTS_NMI + select HAVE_PERF_REGS select ANON_INODES select HAVE_ALIGNED_STRUCT_PAGE if SLUB && !M386 select HAVE_CMPXCHG_LOCAL if !M386 diff --git a/arch/x86/include/asm/perf_regs.h b/arch/x86/include/asm/perf_regs.h new file mode 100644 index 0000000..3f2207b --- /dev/null +++ b/arch/x86/include/asm/perf_regs.h @@ -0,0 +1,33 @@ +#ifndef _ASM_X86_PERF_REGS_H +#define _ASM_X86_PERF_REGS_H + +enum perf_event_x86_regs { + PERF_REG_X86_AX, + PERF_REG_X86_BX, + PERF_REG_X86_CX, + PERF_REG_X86_DX, + PERF_REG_X86_SI, + PERF_REG_X86_DI, + PERF_REG_X86_BP, + PERF_REG_X86_SP, + PERF_REG_X86_IP, + PERF_REG_X86_FLAGS, + PERF_REG_X86_CS, + PERF_REG_X86_SS, + PERF_REG_X86_DS, + PERF_REG_X86_ES, + PERF_REG_X86_FS, + PERF_REG_X86_GS, + PERF_REG_X86_R8, + PERF_REG_X86_R9, + PERF_REG_X86_R10, + PERF_REG_X86_R11, + PERF_REG_X86_R12, + PERF_REG_X86_R13, + PERF_REG_X86_R14, + PERF_REG_X86_R15, + + PERF_REG_X86_32_MAX = PERF_REG_X86_GS + 1, + PERF_REG_X86_64_MAX = PERF_REG_X86_R15 + 1, +}; +#endif /* _ASM_X86_PERF_REGS_H */ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 8215e56..8d7a619 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -100,6 +100,8 @@ obj-$(CONFIG_SWIOTLB) += pci-swiotlb.o obj-$(CONFIG_OF) += devicetree.o obj-$(CONFIG_UPROBES) += uprobes.o +obj-$(CONFIG_PERF_EVENTS) += perf_regs.o + ### # 64 bit specific files ifeq ($(CONFIG_X86_64),y) diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c new file mode 100644 index 0000000..3d692352 --- /dev/null +++ b/arch/x86/kernel/perf_regs.c @@ -0,0 +1,90 @@ +#include +#include +#include +#include +#include +#include + +#ifdef CONFIG_X86_32 +#define PERF_REG_X86_MAX PERF_REG_X86_32_MAX +#else +#define PERF_REG_X86_MAX PERF_REG_X86_64_MAX +#endif + +#define PT_REGS_OFFSET(id, r) [id] = offsetof(struct pt_regs, r) + +static unsigned int pt_regs_offset[PERF_REG_X86_MAX] = { + PT_REGS_OFFSET(PERF_REG_X86_AX, ax), + PT_REGS_OFFSET(PERF_REG_X86_BX, bx), + PT_REGS_OFFSET(PERF_REG_X86_CX, cx), + PT_REGS_OFFSET(PERF_REG_X86_DX, dx), + PT_REGS_OFFSET(PERF_REG_X86_SI, si), + PT_REGS_OFFSET(PERF_REG_X86_DI, di), + PT_REGS_OFFSET(PERF_REG_X86_BP, bp), + PT_REGS_OFFSET(PERF_REG_X86_SP, sp), + PT_REGS_OFFSET(PERF_REG_X86_IP, ip), + PT_REGS_OFFSET(PERF_REG_X86_FLAGS, flags), + PT_REGS_OFFSET(PERF_REG_X86_CS, cs), + PT_REGS_OFFSET(PERF_REG_X86_SS, ss), +#ifdef CONFIG_X86_32 + PT_REGS_OFFSET(PERF_REG_X86_DS, ds), + PT_REGS_OFFSET(PERF_REG_X86_ES, es), + PT_REGS_OFFSET(PERF_REG_X86_FS, fs), + PT_REGS_OFFSET(PERF_REG_X86_GS, gs), +#else + /* + * The pt_regs struct does not store + * ds, es, fs, gs in 64 bit mode. + */ + (unsigned int) -1, + (unsigned int) -1, + (unsigned int) -1, + (unsigned int) -1, +#endif +#ifdef CONFIG_X86_64 + PT_REGS_OFFSET(PERF_REG_X86_R8, r8), + PT_REGS_OFFSET(PERF_REG_X86_R9, r9), + PT_REGS_OFFSET(PERF_REG_X86_R10, r10), + PT_REGS_OFFSET(PERF_REG_X86_R11, r11), + PT_REGS_OFFSET(PERF_REG_X86_R12, r12), + PT_REGS_OFFSET(PERF_REG_X86_R13, r13), + PT_REGS_OFFSET(PERF_REG_X86_R14, r14), + PT_REGS_OFFSET(PERF_REG_X86_R15, r15), +#endif +}; + +u64 perf_reg_value(struct pt_regs *regs, int idx) +{ + if (WARN_ON_ONCE(idx > ARRAY_SIZE(pt_regs_offset))) + return 0; + + return regs_get_register(regs, pt_regs_offset[idx]); +} + +#define REG_RESERVED (~((1ULL << PERF_REG_X86_MAX) - 1ULL)) + +#ifdef CONFIG_X86_32 +int perf_reg_validate(u64 mask) +{ + if (!mask || mask & REG_RESERVED) + return -EINVAL; + + return 0; +} +#else /* CONFIG_X86_64 */ +#define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \ + (1ULL << PERF_REG_X86_ES) | \ + (1ULL << PERF_REG_X86_FS) | \ + (1ULL << PERF_REG_X86_GS)) + +int perf_reg_validate(u64 mask) +{ + if (!mask || mask & REG_RESERVED) + return -EINVAL; + + if (mask & REG_NOSUPPORT) + return -EINVAL; + + return 0; +} +#endif /* CONFIG_X86_32 */ diff --git a/include/linux/perf_regs.h b/include/linux/perf_regs.h new file mode 100644 index 0000000..a2f1a98 --- /dev/null +++ b/include/linux/perf_regs.h @@ -0,0 +1,19 @@ +#ifndef _LINUX_PERF_REGS_H +#define _LINUX_PERF_REGS_H + +#ifdef CONFIG_HAVE_PERF_REGS +#include +u64 perf_reg_value(struct pt_regs *regs, int idx); +int perf_reg_validate(u64 mask); +#else +static inline u64 perf_reg_value(struct pt_regs *regs, int idx) +{ + return 0; +} + +static inline int perf_reg_validate(u64 mask) +{ + return mask ? -ENOSYS : 0; +} +#endif /* CONFIG_HAVE_PERF_REGS */ +#endif /* _LINUX_PERF_REGS_H */ -- 1.7.11.2 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/