From 3243b4ed817fad04e56e7b7dc78ec28dc8322ff2 Mon Sep 17 00:00:00 2001 From: Krzysztof Oledzki Date: Wed, 4 Jun 2008 03:40:17 +0200 Subject: x86: add another PCI ID for ICH6 force-hpet Tested on Asus P5GDC-V $ lspci -n -n |grep ISA 00:1f.0 ISA bridge [0601]: Intel Corporation 82801FB/FR (ICH6/ICH6R) LPC Interface Bridge [8086:2640] (rev 03) Force enabled HPET at base address 0xfed00000 hpet clockevent registered hpet0: at MMIO 0xfed00000, IRQs 2, 8, 0 hpet0: 3 64-bit timers, 14318180 Hz Signed-off-by: Krzysztof Piotr Oledzki Signed-off-by: Ingo Molnar --- arch/x86/kernel/quirks.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch') diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index d89a648..06e1fd6 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -158,6 +158,8 @@ static void ich_force_enable_hpet(struct pci_dev *dev) DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ESB2_0, ich_force_enable_hpet); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH6_0, + ich_force_enable_hpet); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH6_1, ich_force_enable_hpet); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH7_0, -- cgit v1.1 From f3561810b163aca5388ad550abbbc82ae5323189 Mon Sep 17 00:00:00 2001 From: Joe Buehler Date: Mon, 9 Jun 2008 08:55:20 -0400 Subject: x86: add PCI ID for 6300ESB force hpet 00:1f.0 ISA bridge: Intel Corporation 6300ESB LPC Interface Controller (rev 02) 00:1f.0 Class 0601: 8086:25a1 (rev 02) kernel: pci 0000:00:1f.0: Force enabled HPET at 0xfed00000 kernel: hpet clockevent registered kernel: hpet0: at MMIO 0xfed00000, IRQs 2, 8, 0 kernel: hpet0: 3 64-bit timers, 14318180 Hz Signed-off-by: Ingo Molnar --- arch/x86/kernel/quirks.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch') diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index 06e1fd6..f327aba 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -257,6 +257,8 @@ static void old_ich_force_enable_hpet_user(struct pci_dev *dev) old_ich_force_enable_hpet(dev); } +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ESB_1, + old_ich_force_enable_hpet_user); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82801CA_0, old_ich_force_enable_hpet_user); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82801CA_12, -- cgit v1.1 From 286f571837ba9d67625afd015366d79345abb414 Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Tue, 22 Jul 2008 21:08:46 +0200 Subject: x86: apic_*.c: add description to AMD's extended LVT functions Signed-off-by: Robert Richter Cc: oprofile-list Cc: Barry Kasindorf Signed-off-by: Ingo Molnar --- arch/x86/kernel/apic_32.c | 3 +++ arch/x86/kernel/apic_64.c | 3 +++ 2 files changed, 6 insertions(+) (limited to 'arch') diff --git a/arch/x86/kernel/apic_32.c b/arch/x86/kernel/apic_32.c index d6c8983..fad94b0 100644 --- a/arch/x86/kernel/apic_32.c +++ b/arch/x86/kernel/apic_32.c @@ -646,6 +646,9 @@ int setup_profiling_timer(unsigned int multiplier) * * Vector mappings are hard coded. On K8 only offset 0 (APIC500) and * MCE interrupts are supported. Thus MCE offset must be set to 0. + * + * If mask=1, the LVT entry does not generate interrupts while mask=0 + * enables the vector. See also the BKDGs. */ #define APIC_EILVT_LVTOFF_MCE 0 diff --git a/arch/x86/kernel/apic_64.c b/arch/x86/kernel/apic_64.c index 7f1f030..42bf69f 100644 --- a/arch/x86/kernel/apic_64.c +++ b/arch/x86/kernel/apic_64.c @@ -205,6 +205,9 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen) * * Vector mappings are hard coded. On K8 only offset 0 (APIC500) and * MCE interrupts are supported. Thus MCE offset must be set to 0. + * + * If mask=1, the LVT entry does not generate interrupts while mask=0 + * enables the vector. See also the BKDGs. */ #define APIC_EILVT_LVTOFF_MCE 0 -- cgit v1.1 From 12f2b2610e812627acf338aaf043fef20bb726ca Mon Sep 17 00:00:00 2001 From: Barry Kasindorf Date: Tue, 22 Jul 2008 21:08:47 +0200 Subject: oprofile: Add support for AMD Family 11h This patch add support for AMD Family 11h CPUs. Signed-off-by: Barry Kasindorf Signed-off-by: Robert Richter Cc: oprofile-list Signed-off-by: Ingo Molnar --- arch/x86/oprofile/nmi_int.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'arch') diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index 3f90289..33db99a 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -436,6 +436,10 @@ int __init op_nmi_init(struct oprofile_operations *ops) model = &op_athlon_spec; cpu_type = "x86-64/family10"; break; + case 0x11: + model = &op_athlon_spec; + cpu_type = "x86-64/family11h"; + break; } break; -- cgit v1.1 From adf5ec0bca553b763a6b9baed2677a4c7470025b Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Tue, 22 Jul 2008 21:08:48 +0200 Subject: x86/oprofile: introduce model specific init/exit functions This patch implements model specific OProfile init/exit functions for x86 CPUs. Though there is more rework needed at the initialization code, this new introduced functions allow it to keep model specific code in the corresponding op_model_*.c files. The function interface is the same as for oprofile_arch_init/exit(). Signed-off-by: Robert Richter Cc: oprofile-list Signed-off-by: Ingo Molnar --- arch/x86/oprofile/nmi_int.c | 11 ++++++++++- arch/x86/oprofile/op_model_athlon.c | 18 +++++++++++++++--- arch/x86/oprofile/op_x86_model.h | 2 ++ 3 files changed, 27 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index 33db99a..75e8891 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -1,10 +1,11 @@ /** * @file nmi_int.c * - * @remark Copyright 2002 OProfile authors + * @remark Copyright 2002-2008 OProfile authors * @remark Read the file COPYING * * @author John Levon + * @author Robert Richter */ #include @@ -411,6 +412,7 @@ int __init op_nmi_init(struct oprofile_operations *ops) __u8 vendor = boot_cpu_data.x86_vendor; __u8 family = boot_cpu_data.x86; char *cpu_type; + int ret = 0; if (!cpu_has_apic) return -ENODEV; @@ -466,6 +468,11 @@ int __init op_nmi_init(struct oprofile_operations *ops) return -ENODEV; } + if (model->init) + ret = model->init(ops); + if (ret) + return ret; + init_sysfs(); using_nmi = 1; ops->create_files = nmi_create_files; @@ -482,4 +489,6 @@ void op_nmi_exit(void) { if (using_nmi) exit_sysfs(); + if (model->exit) + model->exit(); } diff --git a/arch/x86/oprofile/op_model_athlon.c b/arch/x86/oprofile/op_model_athlon.c index 3d53487..dd8b1dc 100644 --- a/arch/x86/oprofile/op_model_athlon.c +++ b/arch/x86/oprofile/op_model_athlon.c @@ -1,14 +1,15 @@ /* - * @file op_model_athlon.h + * @file op_model_athlon.c * athlon / K7 / K8 / Family 10h model-specific MSR operations * - * @remark Copyright 2002 OProfile authors + * @remark Copyright 2002-2008 OProfile authors * @remark Read the file COPYING * * @author John Levon * @author Philippe Elie * @author Graydon Hoare - */ + * @author Robert Richter +*/ #include #include @@ -178,7 +179,18 @@ static void athlon_shutdown(struct op_msrs const * const msrs) } } +static int op_amd_init(struct oprofile_operations *ops) +{ + return 0; +} + +static void op_amd_exit(void) +{ +} + struct op_x86_model_spec const op_athlon_spec = { + .init = op_amd_init, + .exit = op_amd_exit, .num_counters = NUM_COUNTERS, .num_controls = NUM_CONTROLS, .fill_in_addresses = &athlon_fill_in_addresses, diff --git a/arch/x86/oprofile/op_x86_model.h b/arch/x86/oprofile/op_x86_model.h index 45b605f..ee9ca96 100644 --- a/arch/x86/oprofile/op_x86_model.h +++ b/arch/x86/oprofile/op_x86_model.h @@ -32,6 +32,8 @@ struct pt_regs; * various x86 CPU models' perfctr support. */ struct op_x86_model_spec { + int (*init)(struct oprofile_operations *ops); + void (*exit)(void); unsigned int const num_counters; unsigned int const num_controls; void (*fill_in_addresses)(struct op_msrs * const msrs); -- cgit v1.1 From dfa154289701ed315909b4e371a0381c52c8bdc9 Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Tue, 22 Jul 2008 21:08:49 +0200 Subject: x86/oprofile: Minor changes in op_model_athlon.c Signed-off-by: Robert Richter Cc: oprofile-list Cc: Barry Kasindorf Signed-off-by: Ingo Molnar --- arch/x86/oprofile/op_model_athlon.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch') diff --git a/arch/x86/oprofile/op_model_athlon.c b/arch/x86/oprofile/op_model_athlon.c index dd8b1dc..d25d7f1 100644 --- a/arch/x86/oprofile/op_model_athlon.c +++ b/arch/x86/oprofile/op_model_athlon.c @@ -45,6 +45,8 @@ static unsigned long reset_value[NUM_COUNTERS]; +/* functions for op_athlon_spec */ + static void athlon_fill_in_addresses(struct op_msrs * const msrs) { int i; -- cgit v1.1 From 6657fe4f5650ff7174d418d4bfa50c4640e81a2b Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Tue, 22 Jul 2008 21:08:50 +0200 Subject: x86/oprofile: renaming athlon_*() into op_amd_*() These functions contain code for all AMD CPUs. The new names fit better. Signed-off-by: Robert Richter Cc: oprofile-list Cc: Barry Kasindorf Signed-off-by: Ingo Molnar --- arch/x86/oprofile/nmi_int.c | 8 ++++---- arch/x86/oprofile/op_model_athlon.c | 28 ++++++++++++++-------------- arch/x86/oprofile/op_x86_model.h | 2 +- 3 files changed, 19 insertions(+), 19 deletions(-) (limited to 'arch') diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index 75e8891..b298193 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -425,21 +425,21 @@ int __init op_nmi_init(struct oprofile_operations *ops) default: return -ENODEV; case 6: - model = &op_athlon_spec; + model = &op_amd_spec; cpu_type = "i386/athlon"; break; case 0xf: - model = &op_athlon_spec; + model = &op_amd_spec; /* Actually it could be i386/hammer too, but give user space an consistent name. */ cpu_type = "x86-64/hammer"; break; case 0x10: - model = &op_athlon_spec; + model = &op_amd_spec; cpu_type = "x86-64/family10"; break; case 0x11: - model = &op_athlon_spec; + model = &op_amd_spec; cpu_type = "x86-64/family11h"; break; } diff --git a/arch/x86/oprofile/op_model_athlon.c b/arch/x86/oprofile/op_model_athlon.c index d25d7f1..40ecb02 100644 --- a/arch/x86/oprofile/op_model_athlon.c +++ b/arch/x86/oprofile/op_model_athlon.c @@ -45,9 +45,9 @@ static unsigned long reset_value[NUM_COUNTERS]; -/* functions for op_athlon_spec */ +/* functions for op_amd_spec */ -static void athlon_fill_in_addresses(struct op_msrs * const msrs) +static void op_amd_fill_in_addresses(struct op_msrs * const msrs) { int i; @@ -67,7 +67,7 @@ static void athlon_fill_in_addresses(struct op_msrs * const msrs) } -static void athlon_setup_ctrs(struct op_msrs const * const msrs) +static void op_amd_setup_ctrs(struct op_msrs const * const msrs) { unsigned int low, high; int i; @@ -116,7 +116,7 @@ static void athlon_setup_ctrs(struct op_msrs const * const msrs) } -static int athlon_check_ctrs(struct pt_regs * const regs, +static int op_amd_check_ctrs(struct pt_regs * const regs, struct op_msrs const * const msrs) { unsigned int low, high; @@ -137,7 +137,7 @@ static int athlon_check_ctrs(struct pt_regs * const regs, } -static void athlon_start(struct op_msrs const * const msrs) +static void op_amd_start(struct op_msrs const * const msrs) { unsigned int low, high; int i; @@ -151,7 +151,7 @@ static void athlon_start(struct op_msrs const * const msrs) } -static void athlon_stop(struct op_msrs const * const msrs) +static void op_amd_stop(struct op_msrs const * const msrs) { unsigned int low, high; int i; @@ -167,7 +167,7 @@ static void athlon_stop(struct op_msrs const * const msrs) } } -static void athlon_shutdown(struct op_msrs const * const msrs) +static void op_amd_shutdown(struct op_msrs const * const msrs) { int i; @@ -190,15 +190,15 @@ static void op_amd_exit(void) { } -struct op_x86_model_spec const op_athlon_spec = { +struct op_x86_model_spec const op_amd_spec = { .init = op_amd_init, .exit = op_amd_exit, .num_counters = NUM_COUNTERS, .num_controls = NUM_CONTROLS, - .fill_in_addresses = &athlon_fill_in_addresses, - .setup_ctrs = &athlon_setup_ctrs, - .check_ctrs = &athlon_check_ctrs, - .start = &athlon_start, - .stop = &athlon_stop, - .shutdown = &athlon_shutdown + .fill_in_addresses = &op_amd_fill_in_addresses, + .setup_ctrs = &op_amd_setup_ctrs, + .check_ctrs = &op_amd_check_ctrs, + .start = &op_amd_start, + .stop = &op_amd_stop, + .shutdown = &op_amd_shutdown }; diff --git a/arch/x86/oprofile/op_x86_model.h b/arch/x86/oprofile/op_x86_model.h index ee9ca96..05a0261 100644 --- a/arch/x86/oprofile/op_x86_model.h +++ b/arch/x86/oprofile/op_x86_model.h @@ -48,6 +48,6 @@ struct op_x86_model_spec { extern struct op_x86_model_spec const op_ppro_spec; extern struct op_x86_model_spec const op_p4_spec; extern struct op_x86_model_spec const op_p4_ht2_spec; -extern struct op_x86_model_spec const op_athlon_spec; +extern struct op_x86_model_spec const op_amd_spec; #endif /* OP_X86_MODEL_H */ -- cgit v1.1 From 56784f11df473b4c1d9d0e37777fd7c0b77b6bca Mon Sep 17 00:00:00 2001 From: Barry Kasindorf Date: Tue, 22 Jul 2008 21:08:55 +0200 Subject: x86/oprofile: add IBS support for AMD CPUs, model specific code 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 --- arch/x86/oprofile/op_model_athlon.c | 257 ++++++++++++++++++++++++++++++++++++ 1 file changed, 257 insertions(+) (limited to 'arch') diff --git a/arch/x86/oprofile/op_model_athlon.c b/arch/x86/oprofile/op_model_athlon.c index 40ecb02..229e0b4 100644 --- a/arch/x86/oprofile/op_model_athlon.c +++ b/arch/x86/oprofile/op_model_athlon.c @@ -9,9 +9,13 @@ * @author Philippe Elie * @author Graydon Hoare * @author Robert Richter + * @author Barry Kasindorf */ #include +#include +#include + #include #include #include @@ -43,7 +47,83 @@ #define CTRL_SET_HOST_ONLY(val, h) (val |= ((h & 1) << 9)) #define CTRL_SET_GUEST_ONLY(val, h) (val |= ((h & 1) << 8)) +#define IBS_FETCH_CTL_HIGH_MASK 0xFFFFFFFF +/* high dword bit IbsFetchCtl[bit 49] */ +#define IBS_FETCH_VALID_BIT (1UL << 17) +/* high dword bit IbsFetchCtl[bit 52] */ +#define IBS_FETCH_PHY_ADDR_VALID_BIT (1UL << 20) +/* high dword bit IbsFetchCtl[bit 48] */ +#define IBS_FETCH_ENABLE (1UL << 16) + +#define IBS_FETCH_CTL_CNT_MASK 0x00000000FFFF0000UL +#define IBS_FETCH_CTL_MAX_CNT_MASK 0x000000000000FFFFUL + +/*IbsOpCtl masks/bits */ +#define IBS_OP_VALID_BIT (1ULL<<18) /* IbsOpCtl[bit18] */ +#define IBS_OP_ENABLE (1ULL<<17) /* IBS_OP_ENABLE[bit17]*/ + +/* Codes used in cpu_buffer.c */ +#define IBS_FETCH_BEGIN 3 +#define IBS_OP_BEGIN 4 + +/*IbsOpData3 masks */ +#define IBS_CTL_LVT_OFFSET_VALID_BIT (1ULL<<8) + +/*PCI Extended Configuration Constants */ +/* MSR to set the IBS control register APIC LVT offset */ +#define IBS_LVT_OFFSET_PCI 0x1CC + +struct ibs_fetch_sample { + /* MSRC001_1031 IBS Fetch Linear Address Register */ + unsigned int ibs_fetch_lin_addr_low; + unsigned int ibs_fetch_lin_addr_high; + /* MSRC001_1030 IBS Fetch Control Register */ + unsigned int ibs_fetch_ctl_low; + unsigned int ibs_fetch_ctl_high; + /* MSRC001_1032 IBS Fetch Physical Address Register */ + unsigned int ibs_fetch_phys_addr_low; + unsigned int ibs_fetch_phys_addr_high; +}; + +struct ibs_op_sample { + /* MSRC001_1034 IBS Op Logical Address Register (IbsRIP) */ + unsigned int ibs_op_rip_low; + unsigned int ibs_op_rip_high; + /* MSRC001_1035 IBS Op Data Register */ + unsigned int ibs_op_data1_low; + unsigned int ibs_op_data1_high; + /* MSRC001_1036 IBS Op Data 2 Register */ + unsigned int ibs_op_data2_low; + unsigned int ibs_op_data2_high; + /* MSRC001_1037 IBS Op Data 3 Register */ + unsigned int ibs_op_data3_low; + unsigned int ibs_op_data3_high; + /* MSRC001_1038 IBS DC Linear Address Register (IbsDcLinAd) */ + unsigned int ibs_dc_linear_low; + unsigned int ibs_dc_linear_high; + /* MSRC001_1039 IBS DC Physical Address Register (IbsDcPhysAd) */ + unsigned int ibs_dc_phys_low; + unsigned int ibs_dc_phys_high; +}; + +/* + * unitialize the APIC for the IBS interrupts if needed on AMD Family10h+ +*/ +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 { + unsigned long op_enabled; + unsigned long fetch_enabled; + unsigned long max_cnt_fetch; + unsigned long max_cnt_op; + unsigned long rand_en; + unsigned long dispatched_ops; +}; + +static struct op_ibs_config ibs_config; /* functions for op_amd_spec */ @@ -121,6 +201,8 @@ static int op_amd_check_ctrs(struct pt_regs * const regs, { unsigned int low, high; int i; + struct ibs_fetch_sample ibs_fetch; + struct ibs_op_sample ibs_op; for (i = 0 ; i < NUM_COUNTERS; ++i) { if (!reset_value[i]) @@ -132,6 +214,65 @@ static int op_amd_check_ctrs(struct pt_regs * const regs, } } + /*If AMD and IBS is available */ + if (ibs_allowed && ibs_config.fetch_enabled) { + rdmsr(MSR_AMD64_IBSFETCHCTL, low, high); + if (high & IBS_FETCH_VALID_BIT) { + ibs_fetch.ibs_fetch_ctl_high = high; + ibs_fetch.ibs_fetch_ctl_low = low; + rdmsr(MSR_AMD64_IBSFETCHLINAD, low, high); + ibs_fetch.ibs_fetch_lin_addr_high = high; + ibs_fetch.ibs_fetch_lin_addr_low = low; + rdmsr(MSR_AMD64_IBSFETCHPHYSAD, low, high); + ibs_fetch.ibs_fetch_phys_addr_high = high; + ibs_fetch.ibs_fetch_phys_addr_low = low; + + oprofile_add_ibs_sample(regs, + (unsigned int *)&ibs_fetch, + IBS_FETCH_BEGIN); + + /*reenable the IRQ */ + rdmsr(MSR_AMD64_IBSFETCHCTL, low, high); + high &= ~(IBS_FETCH_VALID_BIT); + high |= IBS_FETCH_ENABLE; + low &= IBS_FETCH_CTL_MAX_CNT_MASK; + wrmsr(MSR_AMD64_IBSFETCHCTL, low, high); + } + } + + if (ibs_allowed && ibs_config.op_enabled) { + rdmsr(MSR_AMD64_IBSOPCTL, low, high); + if (low & IBS_OP_VALID_BIT) { + rdmsr(MSR_AMD64_IBSOPRIP, low, high); + ibs_op.ibs_op_rip_low = low; + ibs_op.ibs_op_rip_high = high; + rdmsr(MSR_AMD64_IBSOPDATA, low, high); + ibs_op.ibs_op_data1_low = low; + ibs_op.ibs_op_data1_high = high; + rdmsr(MSR_AMD64_IBSOPDATA2, low, high); + ibs_op.ibs_op_data2_low = low; + ibs_op.ibs_op_data2_high = high; + rdmsr(MSR_AMD64_IBSOPDATA3, low, high); + ibs_op.ibs_op_data3_low = low; + ibs_op.ibs_op_data3_high = high; + rdmsr(MSR_AMD64_IBSDCLINAD, low, high); + ibs_op.ibs_dc_linear_low = low; + ibs_op.ibs_dc_linear_high = high; + rdmsr(MSR_AMD64_IBSDCPHYSAD, low, high); + ibs_op.ibs_dc_phys_low = low; + ibs_op.ibs_dc_phys_high = high; + + /* reenable the IRQ */ + oprofile_add_ibs_sample(regs, + (unsigned int *)&ibs_op, + IBS_OP_BEGIN); + rdmsr(MSR_AMD64_IBSOPCTL, low, high); + low &= ~(IBS_OP_VALID_BIT); + low |= IBS_OP_ENABLE; + wrmsr(MSR_AMD64_IBSOPCTL, low, high); + } + } + /* See op_model_ppro.c */ return 1; } @@ -148,6 +289,17 @@ static void op_amd_start(struct op_msrs const * const msrs) CTRL_WRITE(low, high, msrs, i); } } + if (ibs_allowed && ibs_config.fetch_enabled) { + low = (ibs_config.max_cnt_fetch >> 4) & 0xFFFF; + high = IBS_FETCH_ENABLE; + wrmsr(MSR_AMD64_IBSFETCHCTL, low, high); + } + + if (ibs_allowed && ibs_config.op_enabled) { + low = ((ibs_config.max_cnt_op >> 4) & 0xFFFF) + IBS_OP_ENABLE; + high = 0; + wrmsr(MSR_AMD64_IBSOPCTL, low, high); + } } @@ -165,6 +317,18 @@ static void op_amd_stop(struct op_msrs const * const msrs) CTRL_SET_INACTIVE(low); CTRL_WRITE(low, high, msrs, i); } + + if (ibs_allowed && ibs_config.fetch_enabled) { + low = 0; /* clear max count and enable */ + high = 0; + wrmsr(MSR_AMD64_IBSFETCHCTL, low, high); + } + + if (ibs_allowed && ibs_config.op_enabled) { + low = 0; /* clear max count and enable */ + high = 0; + wrmsr(MSR_AMD64_IBSOPCTL, low, high); + } } static void op_amd_shutdown(struct op_msrs const * const msrs) @@ -181,6 +345,99 @@ static void op_amd_shutdown(struct op_msrs const * const msrs) } } +static inline void apic_init_ibs_nmi_per_cpu(void *arg) +{ + setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_NMI, 0); +} + +static inline void apic_clear_ibs_nmi_per_cpu(void *arg) +{ + setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_FIX, 1); +} + +/* + * initialize the APIC for the IBS interrupts + * if needed on AMD Family10h rev B0 and later + */ +static void setup_ibs(void) +{ + struct pci_dev *gh_device = NULL; + u32 low, high; + u8 vector; + + ibs_allowed = boot_cpu_has(X86_FEATURE_IBS); + + if (!ibs_allowed) + return; + + /* This gets the APIC_EILVT_LVTOFF_IBS value */ + vector = setup_APIC_eilvt_ibs(0, 0, 1); + + /*see if the IBS control register is already set correctly*/ + /*remove this when we know for sure it is done + in the kernel init*/ + rdmsr(MSR_AMD64_IBSCTL, low, high); + if ((low & (IBS_CTL_LVT_OFFSET_VALID_BIT | vector)) != + (IBS_CTL_LVT_OFFSET_VALID_BIT | vector)) { + + /**** Be sure to run loop until NULL is returned to + decrement reference count on any pci_dev structures + returned ****/ + while ((gh_device = pci_get_device(PCI_VENDOR_ID_AMD, + PCI_DEVICE_ID_AMD_10H_NB_MISC, gh_device)) + != NULL) { + /* This code may change if we can find a proper + * way to get at the PCI extended config space */ + pci_write_config_dword( + gh_device, IBS_LVT_OFFSET_PCI, + (vector | IBS_CTL_LVT_OFFSET_VALID_BIT)); + } + } + on_each_cpu(apic_init_ibs_nmi_per_cpu, NULL, 1, 1); +} + + +/* + * unitialize the APIC for the IBS interrupts if needed on AMD Family10h + * rev B0 and later */ +static void clear_ibs_nmi(void) +{ + if (ibs_allowed) + on_each_cpu(apic_clear_ibs_nmi_per_cpu, NULL, 1, 1); +} + +static void setup_ibs_files(struct super_block *sb, struct dentry *root) +{ + char buf[12]; + struct dentry *dir; + + if (!ibs_allowed) + return; + + /* setup some reasonable defaults */ + ibs_config.max_cnt_fetch = 250000; + ibs_config.fetch_enabled = 0; + ibs_config.max_cnt_op = 250000; + ibs_config.op_enabled = 0; + ibs_config.dispatched_ops = 1; + snprintf(buf, sizeof(buf), "ibs_fetch"); + dir = oprofilefs_mkdir(sb, root, buf); + oprofilefs_create_ulong(sb, dir, "rand_enable", + &ibs_config.rand_en); + oprofilefs_create_ulong(sb, dir, "enable", + &ibs_config.fetch_enabled); + oprofilefs_create_ulong(sb, dir, "max_count", + &ibs_config.max_cnt_fetch); + snprintf(buf, sizeof(buf), "ibs_uops"); + dir = oprofilefs_mkdir(sb, root, buf); + oprofilefs_create_ulong(sb, dir, "enable", + &ibs_config.op_enabled); + oprofilefs_create_ulong(sb, dir, "max_count", + &ibs_config.max_cnt_op); + oprofilefs_create_ulong(sb, dir, "dispatched_ops", + &ibs_config.dispatched_ops); +} + static int op_amd_init(struct oprofile_operations *ops) { return 0; -- cgit v1.1 From 7939d2bf7e30353d40d14f967b7fe2b2a7be5bd9 Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Tue, 22 Jul 2008 21:08:56 +0200 Subject: x86/oprofile: separating the IBS handler Signed-off-by: Robert Richter Cc: oprofile-list Cc: Barry Kasindorf Signed-off-by: Ingo Molnar --- arch/x86/oprofile/op_model_athlon.c | 45 +++++++++++++++++++++++-------------- 1 file changed, 28 insertions(+), 17 deletions(-) (limited to 'arch') diff --git a/arch/x86/oprofile/op_model_athlon.c b/arch/x86/oprofile/op_model_athlon.c index 229e0b4..a2c8e2e 100644 --- a/arch/x86/oprofile/op_model_athlon.c +++ b/arch/x86/oprofile/op_model_athlon.c @@ -195,27 +195,18 @@ static void op_amd_setup_ctrs(struct op_msrs const * const msrs) } } - -static int op_amd_check_ctrs(struct pt_regs * const regs, - struct op_msrs const * const msrs) +static inline int +op_amd_handle_ibs(struct pt_regs * const regs, + struct op_msrs const * const msrs) { unsigned int low, high; - int i; struct ibs_fetch_sample ibs_fetch; struct ibs_op_sample ibs_op; - for (i = 0 ; i < NUM_COUNTERS; ++i) { - if (!reset_value[i]) - continue; - CTR_READ(low, high, msrs, i); - if (CTR_OVERFLOWED(low)) { - oprofile_add_sample(regs, i); - CTR_WRITE(reset_value[i], msrs, i); - } - } + if (!ibs_allowed) + return 1; - /*If AMD and IBS is available */ - if (ibs_allowed && ibs_config.fetch_enabled) { + if (ibs_config.fetch_enabled) { rdmsr(MSR_AMD64_IBSFETCHCTL, low, high); if (high & IBS_FETCH_VALID_BIT) { ibs_fetch.ibs_fetch_ctl_high = high; @@ -240,7 +231,7 @@ static int op_amd_check_ctrs(struct pt_regs * const regs, } } - if (ibs_allowed && ibs_config.op_enabled) { + if (ibs_config.op_enabled) { rdmsr(MSR_AMD64_IBSOPCTL, low, high); if (low & IBS_OP_VALID_BIT) { rdmsr(MSR_AMD64_IBSOPRIP, low, high); @@ -273,10 +264,30 @@ static int op_amd_check_ctrs(struct pt_regs * const regs, } } - /* See op_model_ppro.c */ return 1; } +static int op_amd_check_ctrs(struct pt_regs * const regs, + struct op_msrs const * const msrs) +{ + unsigned int low, high; + int i; + + for (i = 0 ; i < NUM_COUNTERS; ++i) { + if (!reset_value[i]) + continue; + CTR_READ(low, high, msrs, i); + if (CTR_OVERFLOWED(low)) { + oprofile_add_sample(regs, i); + CTR_WRITE(reset_value[i], msrs, i); + } + } + + op_amd_handle_ibs(regs, msrs); + + /* See op_model_ppro.c */ + return 1; +} static void op_amd_start(struct op_msrs const * const msrs) { -- cgit v1.1 From 7d77f2dcae37cf232950cd0181fb0a2cddb18130 Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Tue, 22 Jul 2008 21:08:57 +0200 Subject: OProfile: change IBS interrupt initialization Signed-off-by: Robert Richter Cc: oprofile-list Cc: Barry Kasindorf Signed-off-by: Ingo Molnar --- arch/x86/oprofile/op_model_athlon.c | 84 ++++++++++++++++++++++++------------- 1 file changed, 54 insertions(+), 30 deletions(-) (limited to 'arch') diff --git a/arch/x86/oprofile/op_model_athlon.c b/arch/x86/oprofile/op_model_athlon.c index a2c8e2e..90193b1 100644 --- a/arch/x86/oprofile/op_model_athlon.c +++ b/arch/x86/oprofile/op_model_athlon.c @@ -356,9 +356,11 @@ static void op_amd_shutdown(struct op_msrs const * const msrs) } } +static u8 ibs_eilvt_off; + static inline void apic_init_ibs_nmi_per_cpu(void *arg) { - setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_NMI, 0); + ibs_eilvt_off = setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_NMI, 0); } static inline void apic_clear_ibs_nmi_per_cpu(void *arg) @@ -366,45 +368,67 @@ static inline void apic_clear_ibs_nmi_per_cpu(void *arg) setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_FIX, 1); } +static int pfm_amd64_setup_eilvt(void) +{ +#define IBSCTL_LVTOFFSETVAL (1 << 8) +#define IBSCTL 0x1cc + struct pci_dev *cpu_cfg; + int nodes; + u32 value = 0; + + /* per CPU setup */ + on_each_cpu(apic_init_ibs_nmi_per_cpu, NULL, 0, 1); + + nodes = 0; + cpu_cfg = NULL; + do { + cpu_cfg = pci_get_device(PCI_VENDOR_ID_AMD, + PCI_DEVICE_ID_AMD_10H_NB_MISC, + cpu_cfg); + if (!cpu_cfg) + break; + ++nodes; + pci_write_config_dword(cpu_cfg, IBSCTL, ibs_eilvt_off + | IBSCTL_LVTOFFSETVAL); + pci_read_config_dword(cpu_cfg, IBSCTL, &value); + if (value != (ibs_eilvt_off | IBSCTL_LVTOFFSETVAL)) { + printk(KERN_DEBUG "Failed to setup IBS LVT offset, " + "IBSCTL = 0x%08x", value); + return 1; + } + } while (1); + + if (!nodes) { + printk(KERN_DEBUG "No CPU node configured for IBS"); + return 1; + } + +#ifdef CONFIG_NUMA + /* Sanity check */ + /* Works only for 64bit with proper numa implementation. */ + if (nodes != num_possible_nodes()) { + printk(KERN_DEBUG "Failed to setup CPU node(s) for IBS, " + "found: %d, expected %d", + nodes, num_possible_nodes()); + return 1; + } +#endif + return 0; +} + /* * initialize the APIC for the IBS interrupts - * if needed on AMD Family10h rev B0 and later + * if available (AMD Family10h rev B0 and later) */ static void setup_ibs(void) { - struct pci_dev *gh_device = NULL; - u32 low, high; - u8 vector; - ibs_allowed = boot_cpu_has(X86_FEATURE_IBS); if (!ibs_allowed) return; - /* This gets the APIC_EILVT_LVTOFF_IBS value */ - vector = setup_APIC_eilvt_ibs(0, 0, 1); - - /*see if the IBS control register is already set correctly*/ - /*remove this when we know for sure it is done - in the kernel init*/ - rdmsr(MSR_AMD64_IBSCTL, low, high); - if ((low & (IBS_CTL_LVT_OFFSET_VALID_BIT | vector)) != - (IBS_CTL_LVT_OFFSET_VALID_BIT | vector)) { - - /**** Be sure to run loop until NULL is returned to - decrement reference count on any pci_dev structures - returned ****/ - while ((gh_device = pci_get_device(PCI_VENDOR_ID_AMD, - PCI_DEVICE_ID_AMD_10H_NB_MISC, gh_device)) - != NULL) { - /* This code may change if we can find a proper - * way to get at the PCI extended config space */ - pci_write_config_dword( - gh_device, IBS_LVT_OFFSET_PCI, - (vector | IBS_CTL_LVT_OFFSET_VALID_BIT)); - } - } - on_each_cpu(apic_init_ibs_nmi_per_cpu, NULL, 1, 1); + if (pfm_amd64_setup_eilvt()) + ibs_allowed = 0; } -- cgit v1.1 From 90645700ef8393cd9cdc02d83da36726fc88f49e Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Tue, 22 Jul 2008 21:08:58 +0200 Subject: OProfile: Fix build error in op_model_athlon.c Signed-off-by: Robert Richter Cc: oprofile-list Cc: Barry Kasindorf Signed-off-by: Ingo Molnar --- arch/x86/oprofile/op_model_athlon.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'arch') diff --git a/arch/x86/oprofile/op_model_athlon.c b/arch/x86/oprofile/op_model_athlon.c index 90193b1..284c456 100644 --- a/arch/x86/oprofile/op_model_athlon.c +++ b/arch/x86/oprofile/op_model_athlon.c @@ -73,6 +73,11 @@ /* MSR to set the IBS control register APIC LVT offset */ #define IBS_LVT_OFFSET_PCI 0x1CC +/* The function interface needs to be fixed, something like add + data. Should then be added to linux/oprofile.h. */ +extern void oprofile_add_ibs_sample(struct pt_regs *const regs, + unsigned int * const ibs_sample, u8 code); + struct ibs_fetch_sample { /* MSRC001_1031 IBS Fetch Linear Address Register */ unsigned int ibs_fetch_lin_addr_low; -- cgit v1.1 From ebb535de267386f659e0348185b1e361dbba3b59 Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Tue, 22 Jul 2008 21:08:59 +0200 Subject: OProfile: on_each_cpu(): kill unused retry parameter Signed-off-by: Robert Richter Cc: oprofile-list Cc: Barry Kasindorf Signed-off-by: Ingo Molnar --- arch/x86/oprofile/op_model_athlon.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/x86/oprofile/op_model_athlon.c b/arch/x86/oprofile/op_model_athlon.c index 284c456..ce73236 100644 --- a/arch/x86/oprofile/op_model_athlon.c +++ b/arch/x86/oprofile/op_model_athlon.c @@ -382,7 +382,7 @@ static int pfm_amd64_setup_eilvt(void) u32 value = 0; /* per CPU setup */ - on_each_cpu(apic_init_ibs_nmi_per_cpu, NULL, 0, 1); + on_each_cpu(apic_init_ibs_nmi_per_cpu, NULL, 1); nodes = 0; cpu_cfg = NULL; @@ -443,7 +443,7 @@ static void setup_ibs(void) static void clear_ibs_nmi(void) { if (ibs_allowed) - on_each_cpu(apic_clear_ibs_nmi_per_cpu, NULL, 1, 1); + on_each_cpu(apic_clear_ibs_nmi_per_cpu, NULL, 1); } static void setup_ibs_files(struct super_block *sb, struct dentry *root) -- cgit v1.1 From fc2bd7345b4e006a34c2ea3711d8c6b83cba50f7 Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Tue, 22 Jul 2008 21:09:00 +0200 Subject: OProfile: fix setup_ibs_files() function interface Signed-off-by: Robert Richter Cc: oprofile-list Cc: Barry Kasindorf Signed-off-by: Ingo Molnar --- arch/x86/oprofile/op_model_athlon.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/x86/oprofile/op_model_athlon.c b/arch/x86/oprofile/op_model_athlon.c index ce73236..2650b12 100644 --- a/arch/x86/oprofile/op_model_athlon.c +++ b/arch/x86/oprofile/op_model_athlon.c @@ -446,13 +446,13 @@ static void clear_ibs_nmi(void) on_each_cpu(apic_clear_ibs_nmi_per_cpu, NULL, 1); } -static void setup_ibs_files(struct super_block *sb, struct dentry *root) +static int setup_ibs_files(struct super_block * sb, struct dentry * root) { char buf[12]; struct dentry *dir; if (!ibs_allowed) - return; + return 0; /* setup some reasonable defaults */ ibs_config.max_cnt_fetch = 250000; @@ -476,6 +476,8 @@ static void setup_ibs_files(struct super_block *sb, struct dentry *root) &ibs_config.max_cnt_op); oprofilefs_create_ulong(sb, dir, "dispatched_ops", &ibs_config.dispatched_ops); + + return 0; } static int op_amd_init(struct oprofile_operations *ops) -- cgit v1.1 From 270d3e1a10e6ef85d5a085377e01d91dbcbe3726 Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Tue, 22 Jul 2008 21:09:01 +0200 Subject: OProfile: enable IBS for AMD CPUs Signed-off-by: Robert Richter Cc: oprofile-list Cc: Barry Kasindorf Signed-off-by: Ingo Molnar --- arch/x86/oprofile/nmi_int.c | 14 ++++++++------ arch/x86/oprofile/op_model_athlon.c | 18 +++++++++++++++++- 2 files changed, 25 insertions(+), 7 deletions(-) (limited to 'arch') diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index b298193..287513a 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -468,6 +468,14 @@ int __init op_nmi_init(struct oprofile_operations *ops) return -ENODEV; } + /* default values, can be overwritten by model */ + ops->create_files = nmi_create_files; + ops->setup = nmi_setup; + ops->shutdown = nmi_shutdown; + ops->start = nmi_start; + ops->stop = nmi_stop; + ops->cpu_type = cpu_type; + if (model->init) ret = model->init(ops); if (ret) @@ -475,12 +483,6 @@ int __init op_nmi_init(struct oprofile_operations *ops) init_sysfs(); using_nmi = 1; - ops->create_files = nmi_create_files; - ops->setup = nmi_setup; - ops->shutdown = nmi_shutdown; - ops->start = nmi_start; - ops->stop = nmi_stop; - ops->cpu_type = cpu_type; printk(KERN_INFO "oprofile: using NMI interrupt.\n"); return 0; } diff --git a/arch/x86/oprofile/op_model_athlon.c b/arch/x86/oprofile/op_model_athlon.c index 2650b12..0d83903 100644 --- a/arch/x86/oprofile/op_model_athlon.c +++ b/arch/x86/oprofile/op_model_athlon.c @@ -446,13 +446,25 @@ static void clear_ibs_nmi(void) on_each_cpu(apic_clear_ibs_nmi_per_cpu, NULL, 1); } +static int (*create_arch_files)(struct super_block * sb, struct dentry * root); + static int setup_ibs_files(struct super_block * sb, struct dentry * root) { char buf[12]; struct dentry *dir; + int ret = 0; + + /* architecture specific files */ + if (create_arch_files) + ret = create_arch_files(sb, root); + + if (ret) + return ret; if (!ibs_allowed) - return 0; + return ret; + + /* model specific files */ /* setup some reasonable defaults */ ibs_config.max_cnt_fetch = 250000; @@ -482,11 +494,15 @@ static int setup_ibs_files(struct super_block * sb, struct dentry * root) static int op_amd_init(struct oprofile_operations *ops) { + setup_ibs(); + create_arch_files = ops->create_files; + ops->create_files = setup_ibs_files; return 0; } static void op_amd_exit(void) { + clear_ibs_nmi(); } struct op_x86_model_spec const op_amd_spec = { -- cgit v1.1 From a4c408a41167949f820e2740e56a8f2f7bb6177c Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Tue, 22 Jul 2008 21:09:02 +0200 Subject: OProfile: fix IBS build error for UP Signed-off-by: Robert Richter Cc: oprofile-list Cc: Barry Kasindorf Signed-off-by: Ingo Molnar --- arch/x86/oprofile/op_model_athlon.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'arch') diff --git a/arch/x86/oprofile/op_model_athlon.c b/arch/x86/oprofile/op_model_athlon.c index 0d83903..1acb067 100644 --- a/arch/x86/oprofile/op_model_athlon.c +++ b/arch/x86/oprofile/op_model_athlon.c @@ -361,6 +361,26 @@ static void op_amd_shutdown(struct op_msrs const * const msrs) } } +#ifndef CONFIG_SMP + +/* 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; +} + +static void op_amd_exit(void) {} + +#else + static u8 ibs_eilvt_off; static inline void apic_init_ibs_nmi_per_cpu(void *arg) @@ -505,6 +525,8 @@ static void op_amd_exit(void) clear_ibs_nmi(); } +#endif + struct op_x86_model_spec const op_amd_spec = { .init = op_amd_init, .exit = op_amd_exit, -- cgit v1.1 From 87f0baccc2e4f194c931186d3c8499314494a484 Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Tue, 22 Jul 2008 21:09:03 +0200 Subject: x86/oprofile: macro definition cleanup in op_model_athlon.c Signed-off-by: Robert Richter Cc: oprofile-list Cc: Barry Kasindorf Signed-off-by: Ingo Molnar --- arch/x86/oprofile/op_model_athlon.c | 46 ++++++++++++++----------------------- 1 file changed, 17 insertions(+), 29 deletions(-) (limited to 'arch') diff --git a/arch/x86/oprofile/op_model_athlon.c b/arch/x86/oprofile/op_model_athlon.c index 1acb067..a3a2058 100644 --- a/arch/x86/oprofile/op_model_athlon.c +++ b/arch/x86/oprofile/op_model_athlon.c @@ -47,32 +47,20 @@ #define CTRL_SET_HOST_ONLY(val, h) (val |= ((h & 1) << 9)) #define CTRL_SET_GUEST_ONLY(val, h) (val |= ((h & 1) << 8)) -#define IBS_FETCH_CTL_HIGH_MASK 0xFFFFFFFF -/* high dword bit IbsFetchCtl[bit 49] */ -#define IBS_FETCH_VALID_BIT (1UL << 17) -/* high dword bit IbsFetchCtl[bit 52] */ -#define IBS_FETCH_PHY_ADDR_VALID_BIT (1UL << 20) -/* high dword bit IbsFetchCtl[bit 48] */ -#define IBS_FETCH_ENABLE (1UL << 16) +/* IbsFetchCtl bits/masks */ +#define IBS_FETCH_HIGH_VALID_BIT (1UL << 17) /* bit 49 */ +#define IBS_FETCH_HIGH_ENABLE (1UL << 16) /* bit 48 */ +#define IBS_FETCH_LOW_MAX_CNT_MASK 0x0000FFFFUL /* MaxCnt mask */ -#define IBS_FETCH_CTL_CNT_MASK 0x00000000FFFF0000UL -#define IBS_FETCH_CTL_MAX_CNT_MASK 0x000000000000FFFFUL - -/*IbsOpCtl masks/bits */ -#define IBS_OP_VALID_BIT (1ULL<<18) /* IbsOpCtl[bit18] */ -#define IBS_OP_ENABLE (1ULL<<17) /* IBS_OP_ENABLE[bit17]*/ +/*IbsOpCtl bits */ +#define IBS_OP_LOW_VALID_BIT (1ULL<<18) /* bit 18 */ +#define IBS_OP_LOW_ENABLE (1ULL<<17) /* bit 17 */ /* Codes used in cpu_buffer.c */ +/* This produces duplicate code, need to be fixed */ #define IBS_FETCH_BEGIN 3 #define IBS_OP_BEGIN 4 -/*IbsOpData3 masks */ -#define IBS_CTL_LVT_OFFSET_VALID_BIT (1ULL<<8) - -/*PCI Extended Configuration Constants */ -/* MSR to set the IBS control register APIC LVT offset */ -#define IBS_LVT_OFFSET_PCI 0x1CC - /* The function interface needs to be fixed, something like add data. Should then be added to linux/oprofile.h. */ extern void oprofile_add_ibs_sample(struct pt_regs *const regs, @@ -213,7 +201,7 @@ op_amd_handle_ibs(struct pt_regs * const regs, if (ibs_config.fetch_enabled) { rdmsr(MSR_AMD64_IBSFETCHCTL, low, high); - if (high & IBS_FETCH_VALID_BIT) { + if (high & IBS_FETCH_HIGH_VALID_BIT) { ibs_fetch.ibs_fetch_ctl_high = high; ibs_fetch.ibs_fetch_ctl_low = low; rdmsr(MSR_AMD64_IBSFETCHLINAD, low, high); @@ -229,16 +217,16 @@ op_amd_handle_ibs(struct pt_regs * const regs, /*reenable the IRQ */ rdmsr(MSR_AMD64_IBSFETCHCTL, low, high); - high &= ~(IBS_FETCH_VALID_BIT); - high |= IBS_FETCH_ENABLE; - low &= IBS_FETCH_CTL_MAX_CNT_MASK; + high &= ~IBS_FETCH_HIGH_VALID_BIT; + high |= IBS_FETCH_HIGH_ENABLE; + low &= IBS_FETCH_LOW_MAX_CNT_MASK; wrmsr(MSR_AMD64_IBSFETCHCTL, low, high); } } if (ibs_config.op_enabled) { rdmsr(MSR_AMD64_IBSOPCTL, low, high); - if (low & IBS_OP_VALID_BIT) { + if (low & IBS_OP_LOW_VALID_BIT) { rdmsr(MSR_AMD64_IBSOPRIP, low, high); ibs_op.ibs_op_rip_low = low; ibs_op.ibs_op_rip_high = high; @@ -263,8 +251,8 @@ op_amd_handle_ibs(struct pt_regs * const regs, (unsigned int *)&ibs_op, IBS_OP_BEGIN); rdmsr(MSR_AMD64_IBSOPCTL, low, high); - low &= ~(IBS_OP_VALID_BIT); - low |= IBS_OP_ENABLE; + low &= ~IBS_OP_LOW_VALID_BIT; + low |= IBS_OP_LOW_ENABLE; wrmsr(MSR_AMD64_IBSOPCTL, low, high); } } @@ -307,12 +295,12 @@ static void op_amd_start(struct op_msrs const * const msrs) } if (ibs_allowed && ibs_config.fetch_enabled) { low = (ibs_config.max_cnt_fetch >> 4) & 0xFFFF; - high = IBS_FETCH_ENABLE; + high = IBS_FETCH_HIGH_ENABLE; wrmsr(MSR_AMD64_IBSFETCHCTL, low, high); } if (ibs_allowed && ibs_config.op_enabled) { - low = ((ibs_config.max_cnt_op >> 4) & 0xFFFF) + IBS_OP_ENABLE; + low = ((ibs_config.max_cnt_op >> 4) & 0xFFFF) + IBS_OP_LOW_ENABLE; high = 0; wrmsr(MSR_AMD64_IBSOPCTL, low, high); } -- cgit v1.1 From 543a157bbdfae8eb997506031c3b2d4d17957098 Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Tue, 22 Jul 2008 21:09:04 +0200 Subject: x86/oprofile: op_model_athlon.c: fix counter reset when reenabling IBS OP Signed-off-by: Robert Richter Cc: oprofile-list Cc: Barry Kasindorf Signed-off-by: Ingo Molnar --- arch/x86/oprofile/op_model_athlon.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/x86/oprofile/op_model_athlon.c b/arch/x86/oprofile/op_model_athlon.c index a3a2058..9c8c8c5 100644 --- a/arch/x86/oprofile/op_model_athlon.c +++ b/arch/x86/oprofile/op_model_athlon.c @@ -251,6 +251,7 @@ op_amd_handle_ibs(struct pt_regs * const regs, (unsigned int *)&ibs_op, IBS_OP_BEGIN); rdmsr(MSR_AMD64_IBSOPCTL, low, high); + high = 0; low &= ~IBS_OP_LOW_VALID_BIT; low |= IBS_OP_LOW_ENABLE; wrmsr(MSR_AMD64_IBSOPCTL, low, high); -- cgit v1.1 From 09691616850b3614dfb44790e1e1419b6a7f5d13 Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Tue, 22 Jul 2008 21:09:05 +0200 Subject: x86: apic: export symbols for extended interrupt LVT functions This patch adds EXPORT_SYMBOLs to allow OProfile to be built as module. Cc: Arjan van de Ven Signed-off-by: Robert Richter Cc: oprofile-list Cc: Arjan van de Ven Cc: Barry Kasindorf Signed-off-by: Ingo Molnar --- arch/x86/kernel/apic_32.c | 1 + arch/x86/kernel/apic_64.c | 1 + 2 files changed, 2 insertions(+) (limited to 'arch') diff --git a/arch/x86/kernel/apic_32.c b/arch/x86/kernel/apic_32.c index fad94b0..ed3a6d7 100644 --- a/arch/x86/kernel/apic_32.c +++ b/arch/x86/kernel/apic_32.c @@ -672,6 +672,7 @@ u8 setup_APIC_eilvt_ibs(u8 vector, u8 msg_type, u8 mask) setup_APIC_eilvt(APIC_EILVT_LVTOFF_IBS, vector, msg_type, mask); return APIC_EILVT_LVTOFF_IBS; } +EXPORT_SYMBOL(setup_APIC_eilvt_ibs); /* * Local APIC start and shutdown diff --git a/arch/x86/kernel/apic_64.c b/arch/x86/kernel/apic_64.c index 42bf69f..45ec90e 100644 --- a/arch/x86/kernel/apic_64.c +++ b/arch/x86/kernel/apic_64.c @@ -232,6 +232,7 @@ u8 setup_APIC_eilvt_ibs(u8 vector, u8 msg_type, u8 mask) setup_APIC_eilvt(APIC_EILVT_LVTOFF_IBS, vector, msg_type, mask); return APIC_EILVT_LVTOFF_IBS; } +EXPORT_SYMBOL(setup_APIC_eilvt_ibs); /* * Program the next event, relative to now -- cgit v1.1 From 6aa360e6c16c145edf1837690e0f7aaea6b86ef3 Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Wed, 23 Jul 2008 15:28:14 +0200 Subject: x86: apic: changing export symbols to *_GPL This fits better here. Signed-off-by: Robert Richter Cc: Arjan van de Ven Cc: Barry Kasindorf Cc: oprofile-list Signed-off-by: Ingo Molnar --- arch/x86/kernel/apic_32.c | 2 +- arch/x86/kernel/apic_64.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/apic_32.c b/arch/x86/kernel/apic_32.c index ed3a6d7..0059e7a 100644 --- a/arch/x86/kernel/apic_32.c +++ b/arch/x86/kernel/apic_32.c @@ -672,7 +672,7 @@ u8 setup_APIC_eilvt_ibs(u8 vector, u8 msg_type, u8 mask) setup_APIC_eilvt(APIC_EILVT_LVTOFF_IBS, vector, msg_type, mask); return APIC_EILVT_LVTOFF_IBS; } -EXPORT_SYMBOL(setup_APIC_eilvt_ibs); +EXPORT_SYMBOL_GPL(setup_APIC_eilvt_ibs); /* * Local APIC start and shutdown diff --git a/arch/x86/kernel/apic_64.c b/arch/x86/kernel/apic_64.c index 45ec90e..e571351 100644 --- a/arch/x86/kernel/apic_64.c +++ b/arch/x86/kernel/apic_64.c @@ -232,7 +232,7 @@ u8 setup_APIC_eilvt_ibs(u8 vector, u8 msg_type, u8 mask) setup_APIC_eilvt(APIC_EILVT_LVTOFF_IBS, vector, msg_type, mask); return APIC_EILVT_LVTOFF_IBS; } -EXPORT_SYMBOL(setup_APIC_eilvt_ibs); +EXPORT_SYMBOL_GPL(setup_APIC_eilvt_ibs); /* * Program the next event, relative to now -- cgit v1.1 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 +++++++++++++++++++++++---------- 2 files changed, 37 insertions(+), 10 deletions(-) (limited to 'arch') diff --git a/arch/Kconfig b/arch/Kconfig index b0fabfa..2651af4 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 9c8c8c5..fb6015c 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"); } -- cgit v1.1 From 6852fd9b86d05063c6ef49d2e12e061cc7f6a105 Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Tue, 22 Jul 2008 21:09:08 +0200 Subject: x86/oprofile: reanaming op_model_athlon.c to op_model_amd.c Signed-off-by: Robert Richter Cc: oprofile-list Cc: Barry Kasindorf Signed-off-by: Ingo Molnar --- arch/x86/oprofile/Makefile | 2 +- arch/x86/oprofile/op_model_amd.c | 543 ++++++++++++++++++++++++++++++++++++ arch/x86/oprofile/op_model_athlon.c | 543 ------------------------------------ 3 files changed, 544 insertions(+), 544 deletions(-) create mode 100644 arch/x86/oprofile/op_model_amd.c delete mode 100644 arch/x86/oprofile/op_model_athlon.c (limited to 'arch') diff --git a/arch/x86/oprofile/Makefile b/arch/x86/oprofile/Makefile index 30f3eb3..446902b 100644 --- a/arch/x86/oprofile/Makefile +++ b/arch/x86/oprofile/Makefile @@ -7,6 +7,6 @@ DRIVER_OBJS = $(addprefix ../../../drivers/oprofile/, \ timer_int.o ) oprofile-y := $(DRIVER_OBJS) init.o backtrace.o -oprofile-$(CONFIG_X86_LOCAL_APIC) += nmi_int.o op_model_athlon.o \ +oprofile-$(CONFIG_X86_LOCAL_APIC) += nmi_int.o op_model_amd.o \ op_model_ppro.o op_model_p4.o oprofile-$(CONFIG_X86_IO_APIC) += nmi_timer_int.o diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c new file mode 100644 index 0000000..d9faf60 --- /dev/null +++ b/arch/x86/oprofile/op_model_amd.c @@ -0,0 +1,543 @@ +/* + * @file op_model_amd.c + * athlon / K7 / K8 / Family 10h model-specific MSR operations + * + * @remark Copyright 2002-2008 OProfile authors + * @remark Read the file COPYING + * + * @author John Levon + * @author Philippe Elie + * @author Graydon Hoare + * @author Robert Richter + * @author Barry Kasindorf +*/ + +#include +#include +#include + +#include +#include +#include + +#include "op_x86_model.h" +#include "op_counter.h" + +#define NUM_COUNTERS 4 +#define NUM_CONTROLS 4 + +#define CTR_IS_RESERVED(msrs, c) (msrs->counters[(c)].addr ? 1 : 0) +#define CTR_READ(l, h, msrs, c) do {rdmsr(msrs->counters[(c)].addr, (l), (h)); } while (0) +#define CTR_WRITE(l, msrs, c) do {wrmsr(msrs->counters[(c)].addr, -(unsigned int)(l), -1); } while (0) +#define CTR_OVERFLOWED(n) (!((n) & (1U<<31))) + +#define CTRL_IS_RESERVED(msrs, c) (msrs->controls[(c)].addr ? 1 : 0) +#define CTRL_READ(l, h, msrs, c) do {rdmsr(msrs->controls[(c)].addr, (l), (h)); } while (0) +#define CTRL_WRITE(l, h, msrs, c) do {wrmsr(msrs->controls[(c)].addr, (l), (h)); } while (0) +#define CTRL_SET_ACTIVE(n) (n |= (1<<22)) +#define CTRL_SET_INACTIVE(n) (n &= ~(1<<22)) +#define CTRL_CLEAR_LO(x) (x &= (1<<21)) +#define CTRL_CLEAR_HI(x) (x &= 0xfffffcf0) +#define CTRL_SET_ENABLE(val) (val |= 1<<20) +#define CTRL_SET_USR(val, u) (val |= ((u & 1) << 16)) +#define CTRL_SET_KERN(val, k) (val |= ((k & 1) << 17)) +#define CTRL_SET_UM(val, m) (val |= (m << 8)) +#define CTRL_SET_EVENT_LOW(val, e) (val |= (e & 0xff)) +#define CTRL_SET_EVENT_HIGH(val, e) (val |= ((e >> 8) & 0xf)) +#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 */ +#define IBS_FETCH_LOW_MAX_CNT_MASK 0x0000FFFFUL /* MaxCnt mask */ + +/*IbsOpCtl bits */ +#define IBS_OP_LOW_VALID_BIT (1ULL<<18) /* bit 18 */ +#define IBS_OP_LOW_ENABLE (1ULL<<17) /* bit 17 */ + +/* Codes used in cpu_buffer.c */ +/* This produces duplicate code, need to be fixed */ +#define IBS_FETCH_BEGIN 3 +#define IBS_OP_BEGIN 4 + +/* The function interface needs to be fixed, something like add + data. Should then be added to linux/oprofile.h. */ +extern void oprofile_add_ibs_sample(struct pt_regs *const regs, + unsigned int * const ibs_sample, u8 code); + +struct ibs_fetch_sample { + /* MSRC001_1031 IBS Fetch Linear Address Register */ + unsigned int ibs_fetch_lin_addr_low; + unsigned int ibs_fetch_lin_addr_high; + /* MSRC001_1030 IBS Fetch Control Register */ + unsigned int ibs_fetch_ctl_low; + unsigned int ibs_fetch_ctl_high; + /* MSRC001_1032 IBS Fetch Physical Address Register */ + unsigned int ibs_fetch_phys_addr_low; + unsigned int ibs_fetch_phys_addr_high; +}; + +struct ibs_op_sample { + /* MSRC001_1034 IBS Op Logical Address Register (IbsRIP) */ + unsigned int ibs_op_rip_low; + unsigned int ibs_op_rip_high; + /* MSRC001_1035 IBS Op Data Register */ + unsigned int ibs_op_data1_low; + unsigned int ibs_op_data1_high; + /* MSRC001_1036 IBS Op Data 2 Register */ + unsigned int ibs_op_data2_low; + unsigned int ibs_op_data2_high; + /* MSRC001_1037 IBS Op Data 3 Register */ + unsigned int ibs_op_data3_low; + unsigned int ibs_op_data3_high; + /* MSRC001_1038 IBS DC Linear Address Register (IbsDcLinAd) */ + unsigned int ibs_dc_linear_low; + unsigned int ibs_dc_linear_high; + /* MSRC001_1039 IBS DC Physical Address Register (IbsDcPhysAd) */ + unsigned int ibs_dc_phys_low; + unsigned int ibs_dc_phys_high; +}; + +/* + * unitialize the APIC for the IBS interrupts if needed on AMD Family10h+ +*/ +static void clear_ibs_nmi(void); + +static int ibs_allowed; /* AMD Family10h and later */ + +struct op_ibs_config { + unsigned long op_enabled; + unsigned long fetch_enabled; + unsigned long max_cnt_fetch; + unsigned long max_cnt_op; + unsigned long rand_en; + unsigned long dispatched_ops; +}; + +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) +{ + int i; + + for (i = 0; i < NUM_COUNTERS; i++) { + if (reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i)) + msrs->counters[i].addr = MSR_K7_PERFCTR0 + i; + else + msrs->counters[i].addr = 0; + } + + for (i = 0; i < NUM_CONTROLS; i++) { + if (reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i)) + msrs->controls[i].addr = MSR_K7_EVNTSEL0 + i; + else + msrs->controls[i].addr = 0; + } +} + + +static void op_amd_setup_ctrs(struct op_msrs const * const msrs) +{ + unsigned int low, high; + int i; + + /* clear all counters */ + for (i = 0 ; i < NUM_CONTROLS; ++i) { + if (unlikely(!CTRL_IS_RESERVED(msrs, i))) + continue; + CTRL_READ(low, high, msrs, i); + CTRL_CLEAR_LO(low); + CTRL_CLEAR_HI(high); + CTRL_WRITE(low, high, msrs, i); + } + + /* avoid a false detection of ctr overflows in NMI handler */ + for (i = 0; i < NUM_COUNTERS; ++i) { + if (unlikely(!CTR_IS_RESERVED(msrs, i))) + continue; + CTR_WRITE(1, msrs, i); + } + + /* enable active counters */ + for (i = 0; i < NUM_COUNTERS; ++i) { + if ((counter_config[i].enabled) && (CTR_IS_RESERVED(msrs, i))) { + reset_value[i] = counter_config[i].count; + + CTR_WRITE(counter_config[i].count, msrs, i); + + CTRL_READ(low, high, msrs, i); + CTRL_CLEAR_LO(low); + CTRL_CLEAR_HI(high); + CTRL_SET_ENABLE(low); + CTRL_SET_USR(low, counter_config[i].user); + CTRL_SET_KERN(low, counter_config[i].kernel); + CTRL_SET_UM(low, counter_config[i].unit_mask); + CTRL_SET_EVENT_LOW(low, counter_config[i].event); + CTRL_SET_EVENT_HIGH(high, counter_config[i].event); + CTRL_SET_HOST_ONLY(high, 0); + CTRL_SET_GUEST_ONLY(high, 0); + + CTRL_WRITE(low, high, msrs, i); + } else { + reset_value[i] = 0; + } + } +} + +#ifdef CONFIG_OPROFILE_IBS + +static inline int +op_amd_handle_ibs(struct pt_regs * const regs, + struct op_msrs const * const msrs) +{ + unsigned int low, high; + struct ibs_fetch_sample ibs_fetch; + struct ibs_op_sample ibs_op; + + if (!ibs_allowed) + return 1; + + if (ibs_config.fetch_enabled) { + rdmsr(MSR_AMD64_IBSFETCHCTL, low, high); + if (high & IBS_FETCH_HIGH_VALID_BIT) { + ibs_fetch.ibs_fetch_ctl_high = high; + ibs_fetch.ibs_fetch_ctl_low = low; + rdmsr(MSR_AMD64_IBSFETCHLINAD, low, high); + ibs_fetch.ibs_fetch_lin_addr_high = high; + ibs_fetch.ibs_fetch_lin_addr_low = low; + rdmsr(MSR_AMD64_IBSFETCHPHYSAD, low, high); + ibs_fetch.ibs_fetch_phys_addr_high = high; + ibs_fetch.ibs_fetch_phys_addr_low = low; + + oprofile_add_ibs_sample(regs, + (unsigned int *)&ibs_fetch, + IBS_FETCH_BEGIN); + + /*reenable the IRQ */ + rdmsr(MSR_AMD64_IBSFETCHCTL, low, high); + high &= ~IBS_FETCH_HIGH_VALID_BIT; + high |= IBS_FETCH_HIGH_ENABLE; + low &= IBS_FETCH_LOW_MAX_CNT_MASK; + wrmsr(MSR_AMD64_IBSFETCHCTL, low, high); + } + } + + if (ibs_config.op_enabled) { + rdmsr(MSR_AMD64_IBSOPCTL, low, high); + if (low & IBS_OP_LOW_VALID_BIT) { + rdmsr(MSR_AMD64_IBSOPRIP, low, high); + ibs_op.ibs_op_rip_low = low; + ibs_op.ibs_op_rip_high = high; + rdmsr(MSR_AMD64_IBSOPDATA, low, high); + ibs_op.ibs_op_data1_low = low; + ibs_op.ibs_op_data1_high = high; + rdmsr(MSR_AMD64_IBSOPDATA2, low, high); + ibs_op.ibs_op_data2_low = low; + ibs_op.ibs_op_data2_high = high; + rdmsr(MSR_AMD64_IBSOPDATA3, low, high); + ibs_op.ibs_op_data3_low = low; + ibs_op.ibs_op_data3_high = high; + rdmsr(MSR_AMD64_IBSDCLINAD, low, high); + ibs_op.ibs_dc_linear_low = low; + ibs_op.ibs_dc_linear_high = high; + rdmsr(MSR_AMD64_IBSDCPHYSAD, low, high); + ibs_op.ibs_dc_phys_low = low; + ibs_op.ibs_dc_phys_high = high; + + /* reenable the IRQ */ + oprofile_add_ibs_sample(regs, + (unsigned int *)&ibs_op, + IBS_OP_BEGIN); + rdmsr(MSR_AMD64_IBSOPCTL, low, high); + high = 0; + low &= ~IBS_OP_LOW_VALID_BIT; + low |= IBS_OP_LOW_ENABLE; + wrmsr(MSR_AMD64_IBSOPCTL, low, high); + } + } + + return 1; +} + +#endif + +static int op_amd_check_ctrs(struct pt_regs * const regs, + struct op_msrs const * const msrs) +{ + unsigned int low, high; + int i; + + for (i = 0 ; i < NUM_COUNTERS; ++i) { + if (!reset_value[i]) + continue; + CTR_READ(low, high, msrs, i); + if (CTR_OVERFLOWED(low)) { + oprofile_add_sample(regs, i); + CTR_WRITE(reset_value[i], msrs, i); + } + } + +#ifdef CONFIG_OPROFILE_IBS + op_amd_handle_ibs(regs, msrs); +#endif + + /* See op_model_ppro.c */ + return 1; +} + +static void op_amd_start(struct op_msrs const * const msrs) +{ + unsigned int low, high; + int i; + for (i = 0 ; i < NUM_COUNTERS ; ++i) { + if (reset_value[i]) { + CTRL_READ(low, high, msrs, i); + CTRL_SET_ACTIVE(low); + 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; + wrmsr(MSR_AMD64_IBSFETCHCTL, low, high); + } + + if (ibs_allowed && ibs_config.op_enabled) { + low = ((ibs_config.max_cnt_op >> 4) & 0xFFFF) + IBS_OP_LOW_ENABLE; + high = 0; + wrmsr(MSR_AMD64_IBSOPCTL, low, high); + } +#endif +} + + +static void op_amd_stop(struct op_msrs const * const msrs) +{ + unsigned int low, high; + int i; + + /* Subtle: stop on all counters to avoid race with + * setting our pm callback */ + for (i = 0 ; i < NUM_COUNTERS ; ++i) { + if (!reset_value[i]) + continue; + CTRL_READ(low, high, msrs, i); + CTRL_SET_INACTIVE(low); + 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; + wrmsr(MSR_AMD64_IBSFETCHCTL, low, high); + } + + if (ibs_allowed && ibs_config.op_enabled) { + low = 0; /* clear max count and enable */ + high = 0; + wrmsr(MSR_AMD64_IBSOPCTL, low, high); + } +#endif +} + +static void op_amd_shutdown(struct op_msrs const * const msrs) +{ + int i; + + for (i = 0 ; i < NUM_COUNTERS ; ++i) { + if (CTR_IS_RESERVED(msrs, i)) + release_perfctr_nmi(MSR_K7_PERFCTR0 + i); + } + for (i = 0 ; i < NUM_CONTROLS ; ++i) { + if (CTRL_IS_RESERVED(msrs, i)) + release_evntsel_nmi(MSR_K7_EVNTSEL0 + i); + } +} + +#ifndef CONFIG_OPROFILE_IBS + +/* no IBS support */ + +static int op_amd_init(struct oprofile_operations *ops) +{ + return 0; +} + +static void op_amd_exit(void) {} + +#else + +static u8 ibs_eilvt_off; + +static inline void apic_init_ibs_nmi_per_cpu(void *arg) +{ + ibs_eilvt_off = setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_NMI, 0); +} + +static inline void apic_clear_ibs_nmi_per_cpu(void *arg) +{ + setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_FIX, 1); +} + +static int pfm_amd64_setup_eilvt(void) +{ +#define IBSCTL_LVTOFFSETVAL (1 << 8) +#define IBSCTL 0x1cc + struct pci_dev *cpu_cfg; + int nodes; + u32 value = 0; + + /* per CPU setup */ + on_each_cpu(apic_init_ibs_nmi_per_cpu, NULL, 1); + + nodes = 0; + cpu_cfg = NULL; + do { + cpu_cfg = pci_get_device(PCI_VENDOR_ID_AMD, + PCI_DEVICE_ID_AMD_10H_NB_MISC, + cpu_cfg); + if (!cpu_cfg) + break; + ++nodes; + pci_write_config_dword(cpu_cfg, IBSCTL, ibs_eilvt_off + | IBSCTL_LVTOFFSETVAL); + pci_read_config_dword(cpu_cfg, IBSCTL, &value); + if (value != (ibs_eilvt_off | IBSCTL_LVTOFFSETVAL)) { + printk(KERN_DEBUG "Failed to setup IBS LVT offset, " + "IBSCTL = 0x%08x", value); + return 1; + } + } while (1); + + if (!nodes) { + printk(KERN_DEBUG "No CPU node configured for IBS"); + return 1; + } + +#ifdef CONFIG_NUMA + /* Sanity check */ + /* Works only for 64bit with proper numa implementation. */ + if (nodes != num_possible_nodes()) { + printk(KERN_DEBUG "Failed to setup CPU node(s) for IBS, " + "found: %d, expected %d", + nodes, num_possible_nodes()); + return 1; + } +#endif + return 0; +} + +/* + * initialize the APIC for the IBS interrupts + * if available (AMD Family10h rev B0 and later) + */ +static void setup_ibs(void) +{ + ibs_allowed = boot_cpu_has(X86_FEATURE_IBS); + + if (!ibs_allowed) + return; + + if (pfm_amd64_setup_eilvt()) { + ibs_allowed = 0; + return; + } + + printk(KERN_INFO "oprofile: AMD IBS detected\n"); +} + + +/* + * unitialize the APIC for the IBS interrupts if needed on AMD Family10h + * rev B0 and later */ +static void clear_ibs_nmi(void) +{ + if (ibs_allowed) + on_each_cpu(apic_clear_ibs_nmi_per_cpu, NULL, 1); +} + +static int (*create_arch_files)(struct super_block * sb, struct dentry * root); + +static int setup_ibs_files(struct super_block * sb, struct dentry * root) +{ + char buf[12]; + struct dentry *dir; + int ret = 0; + + /* architecture specific files */ + if (create_arch_files) + ret = create_arch_files(sb, root); + + if (ret) + return ret; + + if (!ibs_allowed) + return ret; + + /* model specific files */ + + /* setup some reasonable defaults */ + ibs_config.max_cnt_fetch = 250000; + ibs_config.fetch_enabled = 0; + ibs_config.max_cnt_op = 250000; + ibs_config.op_enabled = 0; + ibs_config.dispatched_ops = 1; + snprintf(buf, sizeof(buf), "ibs_fetch"); + dir = oprofilefs_mkdir(sb, root, buf); + oprofilefs_create_ulong(sb, dir, "rand_enable", + &ibs_config.rand_en); + oprofilefs_create_ulong(sb, dir, "enable", + &ibs_config.fetch_enabled); + oprofilefs_create_ulong(sb, dir, "max_count", + &ibs_config.max_cnt_fetch); + snprintf(buf, sizeof(buf), "ibs_uops"); + dir = oprofilefs_mkdir(sb, root, buf); + oprofilefs_create_ulong(sb, dir, "enable", + &ibs_config.op_enabled); + oprofilefs_create_ulong(sb, dir, "max_count", + &ibs_config.max_cnt_op); + oprofilefs_create_ulong(sb, dir, "dispatched_ops", + &ibs_config.dispatched_ops); + + return 0; +} + +static int op_amd_init(struct oprofile_operations *ops) +{ + setup_ibs(); + create_arch_files = ops->create_files; + ops->create_files = setup_ibs_files; + return 0; +} + +static void op_amd_exit(void) +{ + clear_ibs_nmi(); +} + +#endif + +struct op_x86_model_spec const op_amd_spec = { + .init = op_amd_init, + .exit = op_amd_exit, + .num_counters = NUM_COUNTERS, + .num_controls = NUM_CONTROLS, + .fill_in_addresses = &op_amd_fill_in_addresses, + .setup_ctrs = &op_amd_setup_ctrs, + .check_ctrs = &op_amd_check_ctrs, + .start = &op_amd_start, + .stop = &op_amd_stop, + .shutdown = &op_amd_shutdown +}; diff --git a/arch/x86/oprofile/op_model_athlon.c b/arch/x86/oprofile/op_model_athlon.c deleted file mode 100644 index fb6015c..0000000 --- a/arch/x86/oprofile/op_model_athlon.c +++ /dev/null @@ -1,543 +0,0 @@ -/* - * @file op_model_athlon.c - * athlon / K7 / K8 / Family 10h model-specific MSR operations - * - * @remark Copyright 2002-2008 OProfile authors - * @remark Read the file COPYING - * - * @author John Levon - * @author Philippe Elie - * @author Graydon Hoare - * @author Robert Richter - * @author Barry Kasindorf -*/ - -#include -#include -#include - -#include -#include -#include - -#include "op_x86_model.h" -#include "op_counter.h" - -#define NUM_COUNTERS 4 -#define NUM_CONTROLS 4 - -#define CTR_IS_RESERVED(msrs, c) (msrs->counters[(c)].addr ? 1 : 0) -#define CTR_READ(l, h, msrs, c) do {rdmsr(msrs->counters[(c)].addr, (l), (h)); } while (0) -#define CTR_WRITE(l, msrs, c) do {wrmsr(msrs->counters[(c)].addr, -(unsigned int)(l), -1); } while (0) -#define CTR_OVERFLOWED(n) (!((n) & (1U<<31))) - -#define CTRL_IS_RESERVED(msrs, c) (msrs->controls[(c)].addr ? 1 : 0) -#define CTRL_READ(l, h, msrs, c) do {rdmsr(msrs->controls[(c)].addr, (l), (h)); } while (0) -#define CTRL_WRITE(l, h, msrs, c) do {wrmsr(msrs->controls[(c)].addr, (l), (h)); } while (0) -#define CTRL_SET_ACTIVE(n) (n |= (1<<22)) -#define CTRL_SET_INACTIVE(n) (n &= ~(1<<22)) -#define CTRL_CLEAR_LO(x) (x &= (1<<21)) -#define CTRL_CLEAR_HI(x) (x &= 0xfffffcf0) -#define CTRL_SET_ENABLE(val) (val |= 1<<20) -#define CTRL_SET_USR(val, u) (val |= ((u & 1) << 16)) -#define CTRL_SET_KERN(val, k) (val |= ((k & 1) << 17)) -#define CTRL_SET_UM(val, m) (val |= (m << 8)) -#define CTRL_SET_EVENT_LOW(val, e) (val |= (e & 0xff)) -#define CTRL_SET_EVENT_HIGH(val, e) (val |= ((e >> 8) & 0xf)) -#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 */ -#define IBS_FETCH_LOW_MAX_CNT_MASK 0x0000FFFFUL /* MaxCnt mask */ - -/*IbsOpCtl bits */ -#define IBS_OP_LOW_VALID_BIT (1ULL<<18) /* bit 18 */ -#define IBS_OP_LOW_ENABLE (1ULL<<17) /* bit 17 */ - -/* Codes used in cpu_buffer.c */ -/* This produces duplicate code, need to be fixed */ -#define IBS_FETCH_BEGIN 3 -#define IBS_OP_BEGIN 4 - -/* The function interface needs to be fixed, something like add - data. Should then be added to linux/oprofile.h. */ -extern void oprofile_add_ibs_sample(struct pt_regs *const regs, - unsigned int * const ibs_sample, u8 code); - -struct ibs_fetch_sample { - /* MSRC001_1031 IBS Fetch Linear Address Register */ - unsigned int ibs_fetch_lin_addr_low; - unsigned int ibs_fetch_lin_addr_high; - /* MSRC001_1030 IBS Fetch Control Register */ - unsigned int ibs_fetch_ctl_low; - unsigned int ibs_fetch_ctl_high; - /* MSRC001_1032 IBS Fetch Physical Address Register */ - unsigned int ibs_fetch_phys_addr_low; - unsigned int ibs_fetch_phys_addr_high; -}; - -struct ibs_op_sample { - /* MSRC001_1034 IBS Op Logical Address Register (IbsRIP) */ - unsigned int ibs_op_rip_low; - unsigned int ibs_op_rip_high; - /* MSRC001_1035 IBS Op Data Register */ - unsigned int ibs_op_data1_low; - unsigned int ibs_op_data1_high; - /* MSRC001_1036 IBS Op Data 2 Register */ - unsigned int ibs_op_data2_low; - unsigned int ibs_op_data2_high; - /* MSRC001_1037 IBS Op Data 3 Register */ - unsigned int ibs_op_data3_low; - unsigned int ibs_op_data3_high; - /* MSRC001_1038 IBS DC Linear Address Register (IbsDcLinAd) */ - unsigned int ibs_dc_linear_low; - unsigned int ibs_dc_linear_high; - /* MSRC001_1039 IBS DC Physical Address Register (IbsDcPhysAd) */ - unsigned int ibs_dc_phys_low; - unsigned int ibs_dc_phys_high; -}; - -/* - * unitialize the APIC for the IBS interrupts if needed on AMD Family10h+ -*/ -static void clear_ibs_nmi(void); - -static int ibs_allowed; /* AMD Family10h and later */ - -struct op_ibs_config { - unsigned long op_enabled; - unsigned long fetch_enabled; - unsigned long max_cnt_fetch; - unsigned long max_cnt_op; - unsigned long rand_en; - unsigned long dispatched_ops; -}; - -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) -{ - int i; - - for (i = 0; i < NUM_COUNTERS; i++) { - if (reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i)) - msrs->counters[i].addr = MSR_K7_PERFCTR0 + i; - else - msrs->counters[i].addr = 0; - } - - for (i = 0; i < NUM_CONTROLS; i++) { - if (reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i)) - msrs->controls[i].addr = MSR_K7_EVNTSEL0 + i; - else - msrs->controls[i].addr = 0; - } -} - - -static void op_amd_setup_ctrs(struct op_msrs const * const msrs) -{ - unsigned int low, high; - int i; - - /* clear all counters */ - for (i = 0 ; i < NUM_CONTROLS; ++i) { - if (unlikely(!CTRL_IS_RESERVED(msrs, i))) - continue; - CTRL_READ(low, high, msrs, i); - CTRL_CLEAR_LO(low); - CTRL_CLEAR_HI(high); - CTRL_WRITE(low, high, msrs, i); - } - - /* avoid a false detection of ctr overflows in NMI handler */ - for (i = 0; i < NUM_COUNTERS; ++i) { - if (unlikely(!CTR_IS_RESERVED(msrs, i))) - continue; - CTR_WRITE(1, msrs, i); - } - - /* enable active counters */ - for (i = 0; i < NUM_COUNTERS; ++i) { - if ((counter_config[i].enabled) && (CTR_IS_RESERVED(msrs, i))) { - reset_value[i] = counter_config[i].count; - - CTR_WRITE(counter_config[i].count, msrs, i); - - CTRL_READ(low, high, msrs, i); - CTRL_CLEAR_LO(low); - CTRL_CLEAR_HI(high); - CTRL_SET_ENABLE(low); - CTRL_SET_USR(low, counter_config[i].user); - CTRL_SET_KERN(low, counter_config[i].kernel); - CTRL_SET_UM(low, counter_config[i].unit_mask); - CTRL_SET_EVENT_LOW(low, counter_config[i].event); - CTRL_SET_EVENT_HIGH(high, counter_config[i].event); - CTRL_SET_HOST_ONLY(high, 0); - CTRL_SET_GUEST_ONLY(high, 0); - - CTRL_WRITE(low, high, msrs, i); - } else { - reset_value[i] = 0; - } - } -} - -#ifdef CONFIG_OPROFILE_IBS - -static inline int -op_amd_handle_ibs(struct pt_regs * const regs, - struct op_msrs const * const msrs) -{ - unsigned int low, high; - struct ibs_fetch_sample ibs_fetch; - struct ibs_op_sample ibs_op; - - if (!ibs_allowed) - return 1; - - if (ibs_config.fetch_enabled) { - rdmsr(MSR_AMD64_IBSFETCHCTL, low, high); - if (high & IBS_FETCH_HIGH_VALID_BIT) { - ibs_fetch.ibs_fetch_ctl_high = high; - ibs_fetch.ibs_fetch_ctl_low = low; - rdmsr(MSR_AMD64_IBSFETCHLINAD, low, high); - ibs_fetch.ibs_fetch_lin_addr_high = high; - ibs_fetch.ibs_fetch_lin_addr_low = low; - rdmsr(MSR_AMD64_IBSFETCHPHYSAD, low, high); - ibs_fetch.ibs_fetch_phys_addr_high = high; - ibs_fetch.ibs_fetch_phys_addr_low = low; - - oprofile_add_ibs_sample(regs, - (unsigned int *)&ibs_fetch, - IBS_FETCH_BEGIN); - - /*reenable the IRQ */ - rdmsr(MSR_AMD64_IBSFETCHCTL, low, high); - high &= ~IBS_FETCH_HIGH_VALID_BIT; - high |= IBS_FETCH_HIGH_ENABLE; - low &= IBS_FETCH_LOW_MAX_CNT_MASK; - wrmsr(MSR_AMD64_IBSFETCHCTL, low, high); - } - } - - if (ibs_config.op_enabled) { - rdmsr(MSR_AMD64_IBSOPCTL, low, high); - if (low & IBS_OP_LOW_VALID_BIT) { - rdmsr(MSR_AMD64_IBSOPRIP, low, high); - ibs_op.ibs_op_rip_low = low; - ibs_op.ibs_op_rip_high = high; - rdmsr(MSR_AMD64_IBSOPDATA, low, high); - ibs_op.ibs_op_data1_low = low; - ibs_op.ibs_op_data1_high = high; - rdmsr(MSR_AMD64_IBSOPDATA2, low, high); - ibs_op.ibs_op_data2_low = low; - ibs_op.ibs_op_data2_high = high; - rdmsr(MSR_AMD64_IBSOPDATA3, low, high); - ibs_op.ibs_op_data3_low = low; - ibs_op.ibs_op_data3_high = high; - rdmsr(MSR_AMD64_IBSDCLINAD, low, high); - ibs_op.ibs_dc_linear_low = low; - ibs_op.ibs_dc_linear_high = high; - rdmsr(MSR_AMD64_IBSDCPHYSAD, low, high); - ibs_op.ibs_dc_phys_low = low; - ibs_op.ibs_dc_phys_high = high; - - /* reenable the IRQ */ - oprofile_add_ibs_sample(regs, - (unsigned int *)&ibs_op, - IBS_OP_BEGIN); - rdmsr(MSR_AMD64_IBSOPCTL, low, high); - high = 0; - low &= ~IBS_OP_LOW_VALID_BIT; - low |= IBS_OP_LOW_ENABLE; - wrmsr(MSR_AMD64_IBSOPCTL, low, high); - } - } - - return 1; -} - -#endif - -static int op_amd_check_ctrs(struct pt_regs * const regs, - struct op_msrs const * const msrs) -{ - unsigned int low, high; - int i; - - for (i = 0 ; i < NUM_COUNTERS; ++i) { - if (!reset_value[i]) - continue; - CTR_READ(low, high, msrs, i); - if (CTR_OVERFLOWED(low)) { - oprofile_add_sample(regs, i); - CTR_WRITE(reset_value[i], msrs, i); - } - } - -#ifdef CONFIG_OPROFILE_IBS - op_amd_handle_ibs(regs, msrs); -#endif - - /* See op_model_ppro.c */ - return 1; -} - -static void op_amd_start(struct op_msrs const * const msrs) -{ - unsigned int low, high; - int i; - for (i = 0 ; i < NUM_COUNTERS ; ++i) { - if (reset_value[i]) { - CTRL_READ(low, high, msrs, i); - CTRL_SET_ACTIVE(low); - 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; - wrmsr(MSR_AMD64_IBSFETCHCTL, low, high); - } - - if (ibs_allowed && ibs_config.op_enabled) { - low = ((ibs_config.max_cnt_op >> 4) & 0xFFFF) + IBS_OP_LOW_ENABLE; - high = 0; - wrmsr(MSR_AMD64_IBSOPCTL, low, high); - } -#endif -} - - -static void op_amd_stop(struct op_msrs const * const msrs) -{ - unsigned int low, high; - int i; - - /* Subtle: stop on all counters to avoid race with - * setting our pm callback */ - for (i = 0 ; i < NUM_COUNTERS ; ++i) { - if (!reset_value[i]) - continue; - CTRL_READ(low, high, msrs, i); - CTRL_SET_INACTIVE(low); - 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; - wrmsr(MSR_AMD64_IBSFETCHCTL, low, high); - } - - if (ibs_allowed && ibs_config.op_enabled) { - low = 0; /* clear max count and enable */ - high = 0; - wrmsr(MSR_AMD64_IBSOPCTL, low, high); - } -#endif -} - -static void op_amd_shutdown(struct op_msrs const * const msrs) -{ - int i; - - for (i = 0 ; i < NUM_COUNTERS ; ++i) { - if (CTR_IS_RESERVED(msrs, i)) - release_perfctr_nmi(MSR_K7_PERFCTR0 + i); - } - for (i = 0 ; i < NUM_CONTROLS ; ++i) { - if (CTRL_IS_RESERVED(msrs, i)) - release_evntsel_nmi(MSR_K7_EVNTSEL0 + i); - } -} - -#ifndef CONFIG_OPROFILE_IBS - -/* no IBS support */ - -static int op_amd_init(struct oprofile_operations *ops) -{ - return 0; -} - -static void op_amd_exit(void) {} - -#else - -static u8 ibs_eilvt_off; - -static inline void apic_init_ibs_nmi_per_cpu(void *arg) -{ - ibs_eilvt_off = setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_NMI, 0); -} - -static inline void apic_clear_ibs_nmi_per_cpu(void *arg) -{ - setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_FIX, 1); -} - -static int pfm_amd64_setup_eilvt(void) -{ -#define IBSCTL_LVTOFFSETVAL (1 << 8) -#define IBSCTL 0x1cc - struct pci_dev *cpu_cfg; - int nodes; - u32 value = 0; - - /* per CPU setup */ - on_each_cpu(apic_init_ibs_nmi_per_cpu, NULL, 1); - - nodes = 0; - cpu_cfg = NULL; - do { - cpu_cfg = pci_get_device(PCI_VENDOR_ID_AMD, - PCI_DEVICE_ID_AMD_10H_NB_MISC, - cpu_cfg); - if (!cpu_cfg) - break; - ++nodes; - pci_write_config_dword(cpu_cfg, IBSCTL, ibs_eilvt_off - | IBSCTL_LVTOFFSETVAL); - pci_read_config_dword(cpu_cfg, IBSCTL, &value); - if (value != (ibs_eilvt_off | IBSCTL_LVTOFFSETVAL)) { - printk(KERN_DEBUG "Failed to setup IBS LVT offset, " - "IBSCTL = 0x%08x", value); - return 1; - } - } while (1); - - if (!nodes) { - printk(KERN_DEBUG "No CPU node configured for IBS"); - return 1; - } - -#ifdef CONFIG_NUMA - /* Sanity check */ - /* Works only for 64bit with proper numa implementation. */ - if (nodes != num_possible_nodes()) { - printk(KERN_DEBUG "Failed to setup CPU node(s) for IBS, " - "found: %d, expected %d", - nodes, num_possible_nodes()); - return 1; - } -#endif - return 0; -} - -/* - * initialize the APIC for the IBS interrupts - * if available (AMD Family10h rev B0 and later) - */ -static void setup_ibs(void) -{ - ibs_allowed = boot_cpu_has(X86_FEATURE_IBS); - - if (!ibs_allowed) - return; - - if (pfm_amd64_setup_eilvt()) { - ibs_allowed = 0; - return; - } - - printk(KERN_INFO "oprofile: AMD IBS detected\n"); -} - - -/* - * unitialize the APIC for the IBS interrupts if needed on AMD Family10h - * rev B0 and later */ -static void clear_ibs_nmi(void) -{ - if (ibs_allowed) - on_each_cpu(apic_clear_ibs_nmi_per_cpu, NULL, 1); -} - -static int (*create_arch_files)(struct super_block * sb, struct dentry * root); - -static int setup_ibs_files(struct super_block * sb, struct dentry * root) -{ - char buf[12]; - struct dentry *dir; - int ret = 0; - - /* architecture specific files */ - if (create_arch_files) - ret = create_arch_files(sb, root); - - if (ret) - return ret; - - if (!ibs_allowed) - return ret; - - /* model specific files */ - - /* setup some reasonable defaults */ - ibs_config.max_cnt_fetch = 250000; - ibs_config.fetch_enabled = 0; - ibs_config.max_cnt_op = 250000; - ibs_config.op_enabled = 0; - ibs_config.dispatched_ops = 1; - snprintf(buf, sizeof(buf), "ibs_fetch"); - dir = oprofilefs_mkdir(sb, root, buf); - oprofilefs_create_ulong(sb, dir, "rand_enable", - &ibs_config.rand_en); - oprofilefs_create_ulong(sb, dir, "enable", - &ibs_config.fetch_enabled); - oprofilefs_create_ulong(sb, dir, "max_count", - &ibs_config.max_cnt_fetch); - snprintf(buf, sizeof(buf), "ibs_uops"); - dir = oprofilefs_mkdir(sb, root, buf); - oprofilefs_create_ulong(sb, dir, "enable", - &ibs_config.op_enabled); - oprofilefs_create_ulong(sb, dir, "max_count", - &ibs_config.max_cnt_op); - oprofilefs_create_ulong(sb, dir, "dispatched_ops", - &ibs_config.dispatched_ops); - - return 0; -} - -static int op_amd_init(struct oprofile_operations *ops) -{ - setup_ibs(); - create_arch_files = ops->create_files; - ops->create_files = setup_ibs_files; - return 0; -} - -static void op_amd_exit(void) -{ - clear_ibs_nmi(); -} - -#endif - -struct op_x86_model_spec const op_amd_spec = { - .init = op_amd_init, - .exit = op_amd_exit, - .num_counters = NUM_COUNTERS, - .num_controls = NUM_CONTROLS, - .fill_in_addresses = &op_amd_fill_in_addresses, - .setup_ctrs = &op_amd_setup_ctrs, - .check_ctrs = &op_amd_check_ctrs, - .start = &op_amd_start, - .stop = &op_amd_stop, - .shutdown = &op_amd_shutdown -}; -- cgit v1.1 From 64a76f667d987a559ad0726b4692c987800b22bc Mon Sep 17 00:00:00 2001 From: David Brownell Date: Tue, 29 Jul 2008 12:47:38 -0700 Subject: hpet: /dev/hpet - fixes and cleanup Minor /dev/hpet updates and bugfixes: * Remove dead code, mostly remnants of an incomplete/unusable kernel interface ... noted when addressing "sparse" warnings: + hpet_unregister() and a routine it calls + hpet_task and all references, including hpet_task_lock + hpet_data.hd_flags (and HPET_DATA_PLATFORM) * Correct and improve boot message: + displays *counter* (shared between comparators) bit width, not *timer* bit widths (which are often mixed) + relabel "timers" as "comparators"; this is less confusing, they are not independent like normal timers are (sigh) + display MHz not Hz; it's never less than 10 MHz. * Tighten and correct the userspace interface code + don't accidentally program comparators in 64-bit mode using 32-bit values ... always force comparators into 32-bit mode + provide the correct bit definition flagging comparators with periodic capability ... the ABI is unchanged * Update Documentation/hpet.txt + be more correct and current + expand description a bit + don't mention that now-gone kernel interface Plus, add a FIXME comment for something that could cause big trouble on systems with more capable HPETs than at least Intel seems to ship. It seems that few folk use this userspace interface; it's not very usable given the general lack of HPET IRQ routing. I'm told that the only real point of it any more is to mmap for fast timestamps; IMO that's handled better through the gettimeofday() vsyscall. Signed-off-by: David Brownell Acked-by: Clemens Ladisch Signed-off-by: Ingo Molnar --- arch/x86/kernel/hpet.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index ad2b15a..82d4591 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -115,13 +115,17 @@ static void hpet_reserve_platform_timers(unsigned long id) hd.hd_phys_address = hpet_address; hd.hd_address = hpet; hd.hd_nirqs = nrtimers; - hd.hd_flags = HPET_DATA_PLATFORM; hpet_reserve_timer(&hd, 0); #ifdef CONFIG_HPET_EMULATE_RTC hpet_reserve_timer(&hd, 1); #endif + /* + * NOTE that hd_irq[] reflects IOAPIC input pins (LEGACY_8254 + * is wrong for i8259!) not the output IRQ. Many BIOS writers + * don't bother configuring *any* comparator interrupts. + */ hd.hd_irq[0] = HPET_LEGACY_8254; hd.hd_irq[1] = HPET_LEGACY_RTC; -- cgit v1.1 From e7250b8ae3870f37f660c2f65cafcaba85e3bfd3 Mon Sep 17 00:00:00 2001 From: Andreas Herrmann Date: Fri, 5 Sep 2008 18:33:26 +0200 Subject: x86: hpet: modify IXP400 quirk to enable interrupts The current quirk is incomplete. Some more chipset fiddling has to be done to enable HPET interrupts. This patch aims to do this. From my tests it seems to work faultlessly. But the official statement is that HPET is not supported on SB4X0. Users will still have to use hpet=force to enable it. Use it at your own risk. Signed-off-by: Andreas Herrmann Signed-off-by: Ingo Molnar --- arch/x86/kernel/quirks.c | 41 +++++++++++++++++++++++++++++++++++++++-- 1 file changed, 39 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index d138588..f6a11b9 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -354,9 +354,27 @@ static void ati_force_hpet_resume(void) printk(KERN_DEBUG "Force enabled HPET at resume\n"); } +static u32 ati_ixp4x0_rev(struct pci_dev *dev) +{ + u32 d; + u8 b; + + pci_read_config_byte(dev, 0xac, &b); + b &= ~(1<<5); + pci_write_config_byte(dev, 0xac, b); + pci_read_config_dword(dev, 0x70, &d); + d |= 1<<8; + pci_write_config_dword(dev, 0x70, d); + pci_read_config_dword(dev, 0x8, &d); + d &= 0xff; + dev_printk(KERN_DEBUG, &dev->dev, "SB4X0 revision 0x%x\n", d); + return d; +} + static void ati_force_enable_hpet(struct pci_dev *dev) { - u32 uninitialized_var(val); + u32 d, val; + u8 b; if (hpet_address || force_hpet_address) return; @@ -366,14 +384,33 @@ static void ati_force_enable_hpet(struct pci_dev *dev) return; } + d = ati_ixp4x0_rev(dev); + if (d < 0x82) + return; + + /* base address */ pci_write_config_dword(dev, 0x14, 0xfed00000); pci_read_config_dword(dev, 0x14, &val); + + /* enable interrupt */ + outb(0x72, 0xcd6); b = inb(0xcd7); + b |= 0x1; + outb(0x72, 0xcd6); outb(b, 0xcd7); + outb(0x72, 0xcd6); b = inb(0xcd7); + if (!(b & 0x1)) + return; + pci_read_config_dword(dev, 0x64, &d); + d |= (1<<10); + pci_write_config_dword(dev, 0x64, d); + pci_read_config_dword(dev, 0x64, &d); + if (!(d & (1<<10))) + return; + force_hpet_address = val; force_hpet_resume_type = ATI_FORCE_HPET_RESUME; dev_printk(KERN_DEBUG, &dev->dev, "Force enabled HPET at 0x%lx\n", force_hpet_address); cached_dev = dev; - return; } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_IXP400_SMBUS, ati_force_enable_hpet); -- cgit v1.1 From d7451fca18e2ec62641ae4bbfe946069f13765a3 Mon Sep 17 00:00:00 2001 From: Jordan Crouse Date: Fri, 12 Sep 2008 11:45:22 -0600 Subject: x86, hpet: SB600 - remove HPET resources from PCI device Prevent the HPET resources from appearing in PCI device 14.0 which confuses the PCI resource engine. Signed-off-by: Jordan Crouse Signed-off-by: Ingo Molnar --- arch/x86/pci/fixup.c | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'arch') diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index 4bdaa59..3c27a80 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -511,3 +511,31 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1201, fam10h_pci_cfg_space_size); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1202, fam10h_pci_cfg_space_size); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1203, fam10h_pci_cfg_space_size); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1204, fam10h_pci_cfg_space_size); + +/* + * SB600: Disable BAR1 on device 14.0 to avoid HPET resources from + * confusing the PCI engine: + */ +static void sb600_disable_hpet_bar(struct pci_dev *dev) +{ + u8 val; + + /* + * The SB600 and SB700 both share the same device + * ID, but the PM register 0x55 does something different + * for the SB700, so make sure we are dealing with the + * SB600 before touching the bit: + */ + + pci_read_config_byte(dev, 0x08, &val); + + if (val < 0x2F) { + outb(0x55, 0xCD6); + val = inb(0xCD7); + + /* Set bit 7 in PM register 0x55 */ + outb(0x55, 0xCD6); + outb(val | 0x80, 0xCD7); + } +} +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_ATI, 0x4385, sb600_disable_hpet_bar); -- cgit v1.1