diff options
Diffstat (limited to 'tools')
633 files changed, 44070 insertions, 11278 deletions
diff --git a/tools/Makefile b/tools/Makefile index c8a90d01dd8e..9dfede37c8ff 100644 --- a/tools/Makefile +++ b/tools/Makefile @@ -18,7 +18,7 @@ help: @echo ' iio - IIO tools' @echo ' kvm_stat - top-like utility for displaying kvm statistics' @echo ' leds - LEDs tools' - @echo ' lguest - a minimal 32-bit x86 hypervisor' + @echo ' liblockdep - user-space wrapper for kernel locking-validator' @echo ' net - misc networking tools' @echo ' perf - Linux performance measurement and analysis tool' @echo ' selftests - various kernel selftests' @@ -89,10 +89,10 @@ freefall: FORCE kvm_stat: FORCE $(call descend,kvm/$@) -all: acpi cgroup cpupower gpio hv firewire lguest \ - perf selftests turbostat usb \ +all: acpi cgroup cpupower gpio hv firewire liblockdep \ + perf selftests spi turbostat usb \ virtio vm net x86_energy_perf_policy \ - tmon freefall objtool kvm_stat + tmon freefall iio objtool kvm_stat acpi_install: $(call descend,power/$(@:_install=),install) @@ -100,9 +100,12 @@ acpi_install: cpupower_install: $(call descend,power/$(@:_install=),install) -cgroup_install firewire_install gpio_install hv_install lguest_install perf_install usb_install virtio_install vm_install net_install objtool_install: +cgroup_install firewire_install gpio_install hv_install iio_install perf_install spi_install usb_install virtio_install vm_install net_install objtool_install: $(call descend,$(@:_install=),install) +liblockdep_install: + $(call descend,lib/lockdep,install) + selftests_install: $(call descend,testing/$(@:_install=),install) @@ -119,7 +122,7 @@ kvm_stat_install: $(call descend,kvm/$(@:_install=),install) install: acpi_install cgroup_install cpupower_install gpio_install \ - hv_install firewire_install lguest_install \ + hv_install firewire_install iio_install liblockdep_install \ perf_install selftests_install turbostat_install usb_install \ virtio_install vm_install net_install x86_energy_perf_policy_install \ tmon_install freefall_install objtool_install kvm_stat_install @@ -130,7 +133,7 @@ acpi_clean: cpupower_clean: $(call descend,power/cpupower,clean) -cgroup_clean hv_clean firewire_clean lguest_clean spi_clean usb_clean virtio_clean vm_clean net_clean iio_clean gpio_clean objtool_clean leds_clean: +cgroup_clean hv_clean firewire_clean spi_clean usb_clean virtio_clean vm_clean net_clean iio_clean gpio_clean objtool_clean leds_clean: $(call descend,$(@:_clean=),clean) liblockdep_clean: @@ -164,7 +167,7 @@ freefall_clean: build_clean: $(call descend,build,clean) -clean: acpi_clean cgroup_clean cpupower_clean hv_clean firewire_clean lguest_clean \ +clean: acpi_clean cgroup_clean cpupower_clean hv_clean firewire_clean \ perf_clean selftests_clean turbostat_clean spi_clean usb_clean virtio_clean \ vm_clean net_clean iio_clean x86_energy_perf_policy_clean tmon_clean \ freefall_clean build_clean libbpf_clean libsubcmd_clean liblockdep_clean \ diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h index 5e3c673fa3f4..5db2d4c6a55f 100644 --- a/tools/arch/arm/include/uapi/asm/kvm.h +++ b/tools/arch/arm/include/uapi/asm/kvm.h @@ -203,6 +203,14 @@ struct kvm_arch_memory_slot { #define KVM_DEV_ARM_VGIC_LINE_LEVEL_INTID_MASK 0x3ff #define VGIC_LEVEL_INFO_LINE_LEVEL 0 +/* Device Control API on vcpu fd */ +#define KVM_ARM_VCPU_PMU_V3_CTRL 0 +#define KVM_ARM_VCPU_PMU_V3_IRQ 0 +#define KVM_ARM_VCPU_PMU_V3_INIT 1 +#define KVM_ARM_VCPU_TIMER_CTRL 1 +#define KVM_ARM_VCPU_TIMER_IRQ_VTIMER 0 +#define KVM_ARM_VCPU_TIMER_IRQ_PTIMER 1 + #define KVM_DEV_ARM_VGIC_CTRL_INIT 0 #define KVM_DEV_ARM_ITS_SAVE_TABLES 1 #define KVM_DEV_ARM_ITS_RESTORE_TABLES 2 diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index 70eea2ecc663..9f3ca24bbcc6 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -232,6 +232,9 @@ struct kvm_arch_memory_slot { #define KVM_ARM_VCPU_PMU_V3_CTRL 0 #define KVM_ARM_VCPU_PMU_V3_IRQ 0 #define KVM_ARM_VCPU_PMU_V3_INIT 1 +#define KVM_ARM_VCPU_TIMER_CTRL 1 +#define KVM_ARM_VCPU_TIMER_IRQ_VTIMER 0 +#define KVM_ARM_VCPU_TIMER_IRQ_PTIMER 1 /* KVM_IRQ_LINE irq field index values */ #define KVM_ARM_IRQ_TYPE_SHIFT 24 diff --git a/tools/arch/parisc/include/uapi/asm/mman.h b/tools/arch/parisc/include/uapi/asm/mman.h index 03d8d5b7ae7f..286c0bd74573 100644 --- a/tools/arch/parisc/include/uapi/asm/mman.h +++ b/tools/arch/parisc/include/uapi/asm/mman.h @@ -36,9 +36,7 @@ #define PROT_READ 0x1 #define PROT_SEM 0x8 #define PROT_WRITE 0x2 -/* MADV_HWPOISON is undefined on parisc, fix it for perf */ #define MADV_HWPOISON 100 -/* MADV_SOFT_OFFLINE is undefined on parisc, fix it for perf */ #define MADV_SOFT_OFFLINE 101 /* MAP_32BIT is undefined on parisc, fix it for perf */ #define MAP_32BIT 0 diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h index 07fbeb927834..8cf8f0c96906 100644 --- a/tools/arch/powerpc/include/uapi/asm/kvm.h +++ b/tools/arch/powerpc/include/uapi/asm/kvm.h @@ -60,6 +60,12 @@ struct kvm_regs { #define KVM_SREGS_E_FSL_PIDn (1 << 0) /* PID1/PID2 */ +/* flags for kvm_run.flags */ +#define KVM_RUN_PPC_NMI_DISP_MASK (3 << 0) +#define KVM_RUN_PPC_NMI_DISP_FULLY_RECOV (1 << 0) +#define KVM_RUN_PPC_NMI_DISP_LIMITED_RECOV (2 << 0) +#define KVM_RUN_PPC_NMI_DISP_NOT_RECOV (3 << 0) + /* * Feature bits indicate which sections of the sregs struct are valid, * both in KVM_GET_SREGS and KVM_SET_SREGS. On KVM_SET_SREGS, registers diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h index 3dd2a1d308dd..69d09c39bbcd 100644 --- a/tools/arch/s390/include/uapi/asm/kvm.h +++ b/tools/arch/s390/include/uapi/asm/kvm.h @@ -28,6 +28,7 @@ #define KVM_DEV_FLIC_CLEAR_IO_IRQ 8 #define KVM_DEV_FLIC_AISM 9 #define KVM_DEV_FLIC_AIRQ_INJECT 10 +#define KVM_DEV_FLIC_AISM_ALL 11 /* * We can have up to 4*64k pending subchannels + 8 adapter interrupts, * as well as up to ASYNC_PF_PER_VCPU*KVM_MAX_VCPUS pfault done interrupts. @@ -53,6 +54,11 @@ struct kvm_s390_ais_req { __u16 mode; }; +struct kvm_s390_ais_all { + __u8 simm; + __u8 nimm; +}; + #define KVM_S390_IO_ADAPTER_MASK 1 #define KVM_S390_IO_ADAPTER_MAP 2 #define KVM_S390_IO_ADAPTER_UNMAP 3 @@ -70,6 +76,7 @@ struct kvm_s390_io_adapter_req { #define KVM_S390_VM_TOD 1 #define KVM_S390_VM_CRYPTO 2 #define KVM_S390_VM_CPU_MODEL 3 +#define KVM_S390_VM_MIGRATION 4 /* kvm attributes for mem_ctrl */ #define KVM_S390_VM_MEM_ENABLE_CMMA 0 @@ -151,6 +158,11 @@ struct kvm_s390_vm_cpu_subfunc { #define KVM_S390_VM_CRYPTO_DISABLE_AES_KW 2 #define KVM_S390_VM_CRYPTO_DISABLE_DEA_KW 3 +/* kvm attributes for migration mode */ +#define KVM_S390_VM_MIGRATION_STOP 0 +#define KVM_S390_VM_MIGRATION_START 1 +#define KVM_S390_VM_MIGRATION_STATUS 2 + /* for KVM_GET_REGS and KVM_SET_REGS */ struct kvm_regs { /* general purpose regs for s390 */ diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 2701e5f8145b..8ea315a11fe0 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -177,7 +177,7 @@ #define X86_FEATURE_PERFCTR_NB ( 6*32+24) /* NB performance counter extensions */ #define X86_FEATURE_BPEXT (6*32+26) /* data breakpoint extension */ #define X86_FEATURE_PTSC ( 6*32+27) /* performance time-stamp counter */ -#define X86_FEATURE_PERFCTR_L2 ( 6*32+28) /* L2 performance counter extensions */ +#define X86_FEATURE_PERFCTR_LLC ( 6*32+28) /* Last Level Cache performance counter extensions */ #define X86_FEATURE_MWAITX ( 6*32+29) /* MWAIT extension (MONITORX/MWAITX) */ /* @@ -286,6 +286,7 @@ #define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */ #define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */ #define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */ +#define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */ #define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/ diff --git a/tools/arch/x86/include/asm/unistd_32.h b/tools/arch/x86/include/asm/unistd_32.h index 88b3f8c8920c..0e4312ffc945 100644 --- a/tools/arch/x86/include/asm/unistd_32.h +++ b/tools/arch/x86/include/asm/unistd_32.h @@ -10,3 +10,6 @@ #ifndef __NR_getcpu # define __NR_getcpu 318 #endif +#ifndef __NR_setns +# define __NR_setns 346 +#endif diff --git a/tools/arch/x86/include/asm/unistd_64.h b/tools/arch/x86/include/asm/unistd_64.h index fbdb70ee8837..dd56bb36132a 100644 --- a/tools/arch/x86/include/asm/unistd_64.h +++ b/tools/arch/x86/include/asm/unistd_64.h @@ -10,3 +10,6 @@ #ifndef __NR_getcpu # define __NR_getcpu 309 #endif +#ifndef __NR_setns +#define __NR_setns 308 +#endif diff --git a/tools/arch/x86/include/uapi/asm/unistd.h b/tools/arch/x86/include/uapi/asm/unistd.h new file mode 100644 index 000000000000..a26df0d75cd0 --- /dev/null +++ b/tools/arch/x86/include/uapi/asm/unistd.h @@ -0,0 +1,17 @@ +#ifndef _UAPI_ASM_X86_UNISTD_H +#define _UAPI_ASM_X86_UNISTD_H + +/* x32 syscall flag bit */ +#define __X32_SYSCALL_BIT 0x40000000 + +#ifndef __KERNEL__ +# ifdef __i386__ +# include <asm/unistd_32.h> +# elif defined(__ILP32__) +# include <asm/unistd_x32.h> +# else +# include <asm/unistd_64.h> +# endif +#endif + +#endif /* _UAPI_ASM_X86_UNISTD_H */ diff --git a/tools/build/Makefile.build b/tools/build/Makefile.build index e279a71c650d..c46b20e4ad87 100644 --- a/tools/build/Makefile.build +++ b/tools/build/Makefile.build @@ -19,15 +19,9 @@ else Q=@ endif -ifneq ($(filter 4.%,$(MAKE_VERSION)),) # make-4 -ifneq ($(filter %s ,$(firstword x$(MAKEFLAGS))),) +ifneq ($(findstring s,$(filter-out --%,$(MAKEFLAGS))),) quiet=silent_ endif -else # make-3.8x -ifneq ($(filter s% -s%,$(MAKEFLAGS)),) - quiet=silent_ -endif -endif build-dir := $(srctree)/tools/build diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index 523911f316ce..c71a05b9c984 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -64,7 +64,8 @@ FEATURE_TESTS_BASIC := \ get_cpuid \ bpf \ sched_getcpu \ - sdt + sdt \ + setns # FEATURE_TESTS_BASIC + FEATURE_TESTS_EXTRA is the complete list # of all feature tests diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index e35e4e5ad192..ee2546ddf028 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -49,7 +49,8 @@ FILES= \ test-sdt.bin \ test-cxx.bin \ test-jvmti.bin \ - test-sched_getcpu.bin + test-sched_getcpu.bin \ + test-setns.bin FILES := $(addprefix $(OUTPUT),$(FILES)) @@ -95,6 +96,9 @@ $(OUTPUT)test-glibc.bin: $(OUTPUT)test-sched_getcpu.bin: $(BUILD) +$(OUTPUT)test-setns.bin: + $(BUILD) + DWARFLIBS := -ldw ifeq ($(findstring -static,${LDFLAGS}),-static) DWARFLIBS += -lelf -lebl -lz -llzma -lbz2 diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c index cc6c7c01f4ca..b5cfc6445771 100644 --- a/tools/build/feature/test-all.c +++ b/tools/build/feature/test-all.c @@ -153,6 +153,10 @@ # include "test-sdt.c" #undef main +#define main main_test_setns +# include "test-setns.c" +#undef main + int main(int argc, char *argv[]) { main_test_libpython(); @@ -188,6 +192,7 @@ int main(int argc, char *argv[]) main_test_libcrypto(); main_test_sched_getcpu(); main_test_sdt(); + main_test_setns(); return 0; } diff --git a/tools/build/feature/test-bpf.c b/tools/build/feature/test-bpf.c index 7598361ef1f1..da2172ff9662 100644 --- a/tools/build/feature/test-bpf.c +++ b/tools/build/feature/test-bpf.c @@ -11,6 +11,8 @@ # define __NR_bpf 280 # elif defined(__sparc__) # define __NR_bpf 349 +# elif defined(__s390__) +# define __NR_bpf 351 # else # error __NR_bpf not defined. libbpf does not support your arch. # endif diff --git a/tools/build/feature/test-setns.c b/tools/build/feature/test-setns.c new file mode 100644 index 000000000000..1f714d2a658b --- /dev/null +++ b/tools/build/feature/test-setns.c @@ -0,0 +1,7 @@ +#define _GNU_SOURCE +#include <sched.h> + +int main(void) +{ + return setns(0, 0); +} diff --git a/tools/build/tests/ex/Makefile b/tools/build/tests/ex/Makefile index c50d5782ad5a..027d6c8a58a7 100644 --- a/tools/build/tests/ex/Makefile +++ b/tools/build/tests/ex/Makefile @@ -8,7 +8,7 @@ ex: include $(srctree)/tools/build/Makefile.include ex: ex-in.o libex-in.o - gcc -o $@ $^ + $(CC) -o $@ $^ ex.%: fixdep FORCE make -f $(srctree)/tools/build/Makefile.build dir=. $@ diff --git a/tools/hv/bondvf.sh b/tools/hv/bondvf.sh deleted file mode 100755 index d85968cb1bf2..000000000000 --- a/tools/hv/bondvf.sh +++ /dev/null @@ -1,211 +0,0 @@ -#!/bin/bash - -# This example script creates bonding network devices based on synthetic NIC -# (the virtual network adapter usually provided by Hyper-V) and the matching -# VF NIC (SRIOV virtual function). So the synthetic NIC and VF NIC can -# function as one network device, and fail over to the synthetic NIC if VF is -# down. -# -# Usage: -# - After configured vSwitch and vNIC with SRIOV, start Linux virtual -# machine (VM) -# - Run this scripts on the VM. It will create configuration files in -# distro specific directory. -# - Reboot the VM, so that the bonding config are enabled. -# -# The config files are DHCP by default. You may edit them if you need to change -# to Static IP or change other settings. -# - -sysdir=/sys/class/net -netvsc_cls={f8615163-df3e-46c5-913f-f2d2f965ed0e} -bondcnt=0 - -# Detect Distro -if [ -f /etc/redhat-release ]; -then - cfgdir=/etc/sysconfig/network-scripts - distro=redhat -elif grep -q 'Ubuntu' /etc/issue -then - cfgdir=/etc/network - distro=ubuntu -elif grep -q 'SUSE' /etc/issue -then - cfgdir=/etc/sysconfig/network - distro=suse -else - echo "Unsupported Distro" - exit 1 -fi - -echo Detected Distro: $distro, or compatible - -# Get a list of ethernet names -list_eth=(`cd $sysdir && ls -d */ | cut -d/ -f1 | grep -v bond`) -eth_cnt=${#list_eth[@]} - -echo List of net devices: - -# Get the MAC addresses -for (( i=0; i < $eth_cnt; i++ )) -do - list_mac[$i]=`cat $sysdir/${list_eth[$i]}/address` - echo ${list_eth[$i]}, ${list_mac[$i]} -done - -# Find NIC with matching MAC -for (( i=0; i < $eth_cnt-1; i++ )) -do - for (( j=i+1; j < $eth_cnt; j++ )) - do - if [ "${list_mac[$i]}" = "${list_mac[$j]}" ] - then - list_match[$i]=${list_eth[$j]} - break - fi - done -done - -function create_eth_cfg_redhat { - local fn=$cfgdir/ifcfg-$1 - - rm -f $fn - echo DEVICE=$1 >>$fn - echo TYPE=Ethernet >>$fn - echo BOOTPROTO=none >>$fn - echo UUID=`uuidgen` >>$fn - echo ONBOOT=yes >>$fn - echo PEERDNS=yes >>$fn - echo IPV6INIT=yes >>$fn - echo MASTER=$2 >>$fn - echo SLAVE=yes >>$fn -} - -function create_eth_cfg_pri_redhat { - create_eth_cfg_redhat $1 $2 -} - -function create_bond_cfg_redhat { - local fn=$cfgdir/ifcfg-$1 - - rm -f $fn - echo DEVICE=$1 >>$fn - echo TYPE=Bond >>$fn - echo BOOTPROTO=dhcp >>$fn - echo UUID=`uuidgen` >>$fn - echo ONBOOT=yes >>$fn - echo PEERDNS=yes >>$fn - echo IPV6INIT=yes >>$fn - echo BONDING_MASTER=yes >>$fn - echo BONDING_OPTS=\"mode=active-backup miimon=100 primary=$2\" >>$fn -} - -function del_eth_cfg_ubuntu { - local fn=$cfgdir/interfaces - local tmpfl=$(mktemp) - - local nic_start='^[ \t]*(auto|iface|mapping|allow-.*)[ \t]+'$1 - local nic_end='^[ \t]*(auto|iface|mapping|allow-.*|source)' - - awk "/$nic_end/{x=0} x{next} /$nic_start/{x=1;next} 1" $fn >$tmpfl - - cp $tmpfl $fn - - rm $tmpfl -} - -function create_eth_cfg_ubuntu { - local fn=$cfgdir/interfaces - - del_eth_cfg_ubuntu $1 - - echo $'\n'auto $1 >>$fn - echo iface $1 inet manual >>$fn - echo bond-master $2 >>$fn -} - -function create_eth_cfg_pri_ubuntu { - local fn=$cfgdir/interfaces - - create_eth_cfg_ubuntu $1 $2 - echo bond-primary $1 >>$fn -} - -function create_bond_cfg_ubuntu { - local fn=$cfgdir/interfaces - - del_eth_cfg_ubuntu $1 - - echo $'\n'auto $1 >>$fn - echo iface $1 inet dhcp >>$fn - echo bond-mode active-backup >>$fn - echo bond-miimon 100 >>$fn - echo bond-slaves none >>$fn -} - -function create_eth_cfg_suse { - local fn=$cfgdir/ifcfg-$1 - - rm -f $fn - echo BOOTPROTO=none >>$fn - echo STARTMODE=auto >>$fn -} - -function create_eth_cfg_pri_suse { - create_eth_cfg_suse $1 -} - -function create_bond_cfg_suse { - local fn=$cfgdir/ifcfg-$1 - - rm -f $fn - echo BOOTPROTO=dhcp >>$fn - echo STARTMODE=auto >>$fn - echo BONDING_MASTER=yes >>$fn - echo BONDING_SLAVE_0=$2 >>$fn - echo BONDING_SLAVE_1=$3 >>$fn - echo BONDING_MODULE_OPTS=\'mode=active-backup miimon=100 primary=$2\' >>$fn -} - -function create_bond { - local bondname=bond$bondcnt - local primary - local secondary - - local class_id1=`cat $sysdir/$1/device/class_id 2>/dev/null` - local class_id2=`cat $sysdir/$2/device/class_id 2>/dev/null` - - if [ "$class_id1" = "$netvsc_cls" ] - then - primary=$2 - secondary=$1 - elif [ "$class_id2" = "$netvsc_cls" ] - then - primary=$1 - secondary=$2 - else - return 0 - fi - - echo $'\nBond name:' $bondname - - echo configuring $primary - create_eth_cfg_pri_$distro $primary $bondname - - echo configuring $secondary - create_eth_cfg_$distro $secondary $bondname - - echo creating: $bondname with primary slave: $primary - create_bond_cfg_$distro $bondname $primary $secondary - - let bondcnt=bondcnt+1 -} - -for (( i=0; i < $eth_cnt-1; i++ )) -do - if [ -n "${list_match[$i]}" ] - then - create_bond ${list_eth[$i]} ${list_match[$i]} - fi -done diff --git a/tools/hv/hv_fcopy_daemon.c b/tools/hv/hv_fcopy_daemon.c index 26ae609a9448..457a1521f32f 100644 --- a/tools/hv/hv_fcopy_daemon.c +++ b/tools/hv/hv_fcopy_daemon.c @@ -138,14 +138,17 @@ void print_usage(char *argv[]) int main(int argc, char *argv[]) { - int fcopy_fd, len; + int fcopy_fd; int error; int daemonize = 1, long_index = 0, opt; int version = FCOPY_CURRENT_VERSION; - char *buffer[4096 * 2]; - struct hv_fcopy_hdr *in_msg; + union { + struct hv_fcopy_hdr hdr; + struct hv_start_fcopy start; + struct hv_do_fcopy copy; + __u32 kernel_modver; + } buffer = { }; int in_handshake = 1; - __u32 kernel_modver; static struct option long_options[] = { {"help", no_argument, 0, 'h' }, @@ -195,32 +198,31 @@ int main(int argc, char *argv[]) * In this loop we process fcopy messages after the * handshake is complete. */ - len = pread(fcopy_fd, buffer, (4096 * 2), 0); + ssize_t len; + + len = pread(fcopy_fd, &buffer, sizeof(buffer), 0); if (len < 0) { syslog(LOG_ERR, "pread failed: %s", strerror(errno)); exit(EXIT_FAILURE); } if (in_handshake) { - if (len != sizeof(kernel_modver)) { + if (len != sizeof(buffer.kernel_modver)) { syslog(LOG_ERR, "invalid version negotiation"); exit(EXIT_FAILURE); } - kernel_modver = *(__u32 *)buffer; in_handshake = 0; - syslog(LOG_INFO, "kernel module version: %d", - kernel_modver); + syslog(LOG_INFO, "kernel module version: %u", + buffer.kernel_modver); continue; } - in_msg = (struct hv_fcopy_hdr *)buffer; - - switch (in_msg->operation) { + switch (buffer.hdr.operation) { case START_FILE_COPY: - error = hv_start_fcopy((struct hv_start_fcopy *)in_msg); + error = hv_start_fcopy(&buffer.start); break; case WRITE_TO_FILE: - error = hv_copy_data((struct hv_do_fcopy *)in_msg); + error = hv_copy_data(&buffer.copy); break; case COMPLETE_FCOPY: error = hv_copy_finished(); @@ -231,7 +233,7 @@ int main(int argc, char *argv[]) default: syslog(LOG_ERR, "Unknown operation: %d", - in_msg->operation); + buffer.hdr.operation); } diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c index f1758fcbc37d..eaa3bec273c8 100644 --- a/tools/hv/hv_kvp_daemon.c +++ b/tools/hv/hv_kvp_daemon.c @@ -39,6 +39,7 @@ #include <fcntl.h> #include <dirent.h> #include <net/if.h> +#include <limits.h> #include <getopt.h> /* @@ -97,6 +98,8 @@ static struct utsname uts_buf; #define KVP_SCRIPTS_PATH "/usr/libexec/hypervkvpd/" #endif +#define KVP_NET_DIR "/sys/class/net/" + #define MAX_FILE_NAME 100 #define ENTRIES_PER_BLOCK 50 @@ -596,26 +599,21 @@ static char *kvp_get_if_name(char *guid) DIR *dir; struct dirent *entry; FILE *file; - char *p, *q, *x; + char *p, *x; char *if_name = NULL; char buf[256]; - char *kvp_net_dir = "/sys/class/net/"; - char dev_id[256]; + char dev_id[PATH_MAX]; - dir = opendir(kvp_net_dir); + dir = opendir(KVP_NET_DIR); if (dir == NULL) return NULL; - snprintf(dev_id, sizeof(dev_id), "%s", kvp_net_dir); - q = dev_id + strlen(kvp_net_dir); - while ((entry = readdir(dir)) != NULL) { /* * Set the state for the next pass. */ - *q = '\0'; - strcat(dev_id, entry->d_name); - strcat(dev_id, "/device/device_id"); + snprintf(dev_id, sizeof(dev_id), "%s%s/device/device_id", + KVP_NET_DIR, entry->d_name); file = fopen(dev_id, "r"); if (file == NULL) @@ -653,12 +651,12 @@ static char *kvp_if_name_to_mac(char *if_name) FILE *file; char *p, *x; char buf[256]; - char addr_file[256]; + char addr_file[PATH_MAX]; unsigned int i; char *mac_addr = NULL; - snprintf(addr_file, sizeof(addr_file), "%s%s%s", "/sys/class/net/", - if_name, "/address"); + snprintf(addr_file, sizeof(addr_file), "%s%s%s", KVP_NET_DIR, + if_name, "/address"); file = fopen(addr_file, "r"); if (file == NULL) @@ -688,28 +686,22 @@ static char *kvp_mac_to_if_name(char *mac) DIR *dir; struct dirent *entry; FILE *file; - char *p, *q, *x; + char *p, *x; char *if_name = NULL; char buf[256]; - char *kvp_net_dir = "/sys/class/net/"; - char dev_id[256]; + char dev_id[PATH_MAX]; unsigned int i; - dir = opendir(kvp_net_dir); + dir = opendir(KVP_NET_DIR); if (dir == NULL) return NULL; - snprintf(dev_id, sizeof(dev_id), "%s", kvp_net_dir); - q = dev_id + strlen(kvp_net_dir); - while ((entry = readdir(dir)) != NULL) { /* * Set the state for the next pass. */ - *q = '\0'; - - strcat(dev_id, entry->d_name); - strcat(dev_id, "/address"); + snprintf(dev_id, sizeof(dev_id), "%s%s/address", KVP_NET_DIR, + entry->d_name); file = fopen(dev_id, "r"); if (file == NULL) @@ -1144,7 +1136,7 @@ static int process_ip_string(FILE *f, char *ip_string, int type) int i = 0; int j = 0; char str[256]; - char sub_str[10]; + char sub_str[13]; int offset = 0; memset(addr, 0, sizeof(addr)); @@ -1218,9 +1210,9 @@ static int process_ip_string(FILE *f, char *ip_string, int type) static int kvp_set_ip_info(char *if_name, struct hv_kvp_ipaddr_value *new_val) { int error = 0; - char if_file[128]; + char if_file[PATH_MAX]; FILE *file; - char cmd[512]; + char cmd[PATH_MAX]; char *mac_addr; /* diff --git a/tools/hv/hv_vss_daemon.c b/tools/hv/hv_vss_daemon.c index e0829809c897..b2b4ebffab8c 100644 --- a/tools/hv/hv_vss_daemon.c +++ b/tools/hv/hv_vss_daemon.c @@ -21,6 +21,7 @@ #include <sys/types.h> #include <sys/poll.h> #include <sys/ioctl.h> +#include <sys/stat.h> #include <fcntl.h> #include <stdio.h> #include <mntent.h> @@ -30,6 +31,7 @@ #include <ctype.h> #include <errno.h> #include <linux/fs.h> +#include <linux/major.h> #include <linux/hyperv.h> #include <syslog.h> #include <getopt.h> @@ -70,6 +72,7 @@ static int vss_operate(int operation) char match[] = "/dev/"; FILE *mounts; struct mntent *ent; + struct stat sb; char errdir[1024] = {0}; unsigned int cmd; int error = 0, root_seen = 0, save_errno = 0; @@ -92,6 +95,10 @@ static int vss_operate(int operation) while ((ent = getmntent(mounts))) { if (strncmp(ent->mnt_fsname, match, strlen(match))) continue; + if (stat(ent->mnt_fsname, &sb) == -1) + continue; + if (S_ISBLK(sb.st_mode) && major(sb.st_rdev) == LOOP_MAJOR) + continue; if (hasmntopt(ent, MNTOPT_RO) != NULL) continue; if (strcmp(ent->mnt_type, "vfat") == 0) @@ -261,7 +268,9 @@ int main(int argc, char *argv[]) if (len != sizeof(struct hv_vss_msg)) { syslog(LOG_ERR, "write failed; error: %d %s", errno, strerror(errno)); - exit(EXIT_FAILURE); + + if (op == VSS_OP_FREEZE) + vss_operate(VSS_OP_THAW); } } diff --git a/tools/iio/Build b/tools/iio/Build new file mode 100644 index 000000000000..f74cbda64710 --- /dev/null +++ b/tools/iio/Build @@ -0,0 +1,3 @@ +lsiio-y += lsiio.o iio_utils.o +iio_event_monitor-y += iio_event_monitor.o iio_utils.o +iio_generic_buffer-y += iio_generic_buffer.o iio_utils.o diff --git a/tools/iio/Makefile b/tools/iio/Makefile index 5446d625e17d..d4d956020adf 100644 --- a/tools/iio/Makefile +++ b/tools/iio/Makefile @@ -1,31 +1,67 @@ +include ../scripts/Makefile.include + +bindir ?= /usr/bin + +ifeq ($(srctree),) +srctree := $(patsubst %/,%,$(dir $(CURDIR))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +endif + +# Do not use make's built-in rules +# (this improves performance and avoids hard-to-debug behaviour); +MAKEFLAGS += -r + CC = $(CROSS_COMPILE)gcc -CFLAGS += -Wall -g -D_GNU_SOURCE +LD = $(CROSS_COMPILE)ld +CFLAGS += -O2 -Wall -g -D_GNU_SOURCE -I$(OUTPUT)include -BINDIR=usr/bin -INSTALL_PROGRAM=install -m 755 -p -DEL_FILE=rm -f +ALL_TARGETS := iio_event_monitor lsiio iio_generic_buffer +ALL_PROGRAMS := $(patsubst %,$(OUTPUT)%,$(ALL_TARGETS)) -all: iio_event_monitor lsiio iio_generic_buffer +all: $(ALL_PROGRAMS) -iio_event_monitor: iio_event_monitor.o iio_utils.o +export srctree OUTPUT CC LD CFLAGS +include $(srctree)/tools/build/Makefile.include -lsiio: lsiio.o iio_utils.o +# +# We need the following to be outside of kernel tree +# +$(OUTPUT)include/linux/iio: ../../include/uapi/linux/iio + mkdir -p $(OUTPUT)include/linux/iio 2>&1 || true + ln -sf $(CURDIR)/../../include/uapi/linux/iio/events.h $@ + ln -sf $(CURDIR)/../../include/uapi/linux/iio/types.h $@ -iio_generic_buffer: iio_generic_buffer.o iio_utils.o +prepare: $(OUTPUT)include/linux/iio -%.o: %.c iio_utils.h +LSIIO_IN := $(OUTPUT)lsiio-in.o +$(LSIIO_IN): prepare FORCE + $(Q)$(MAKE) $(build)=lsiio +$(OUTPUT)lsiio: $(LSIIO_IN) + $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@ -install: - - mkdir -p $(INSTALL_ROOT)/$(BINDIR) - - $(INSTALL_PROGRAM) "iio_event_monitor" "$(INSTALL_ROOT)/$(BINDIR)/iio_event_monitor" - - $(INSTALL_PROGRAM) "lsiio" "$(INSTALL_ROOT)/$(BINDIR)/lsiio" - - $(INSTALL_PROGRAM) "iio_generic_buffer" "$(INSTALL_ROOT)/$(BINDIR)/iio_generic_buffer" +IIO_EVENT_MONITOR_IN := $(OUTPUT)iio_event_monitor-in.o +$(IIO_EVENT_MONITOR_IN): prepare FORCE + $(Q)$(MAKE) $(build)=iio_event_monitor +$(OUTPUT)iio_event_monitor: $(IIO_EVENT_MONITOR_IN) + $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@ -uninstall: - $(DEL_FILE) "$(INSTALL_ROOT)/$(BINDIR)/iio_event_monitor" - $(DEL_FILE) "$(INSTALL_ROOT)/$(BINDIR)/lsiio" - $(DEL_FILE) "$(INSTALL_ROOT)/$(BINDIR)/iio_generic_buffer" +IIO_GENERIC_BUFFER_IN := $(OUTPUT)iio_generic_buffer-in.o +$(IIO_GENERIC_BUFFER_IN): prepare FORCE + $(Q)$(MAKE) $(build)=iio_generic_buffer +$(OUTPUT)iio_generic_buffer: $(IIO_GENERIC_BUFFER_IN) + $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@ -.PHONY: clean clean: - rm -f *.o iio_event_monitor lsiio iio_generic_buffer + rm -f $(ALL_PROGRAMS) + rm -rf $(OUTPUT)include/linux/iio + find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete + +install: $(ALL_PROGRAMS) + install -d -m 755 $(DESTDIR)$(bindir); \ + for program in $(ALL_PROGRAMS); do \ + install $$program $(DESTDIR)$(bindir); \ + done + +FORCE: + +.PHONY: all install clean FORCE prepare diff --git a/tools/iio/iio_utils.h b/tools/iio/iio_utils.h index 780f2014f8fa..8b379da26e35 100644 --- a/tools/iio/iio_utils.h +++ b/tools/iio/iio_utils.h @@ -13,7 +13,7 @@ #include <stdint.h> /* Made up value to limit allocation sizes */ -#define IIO_MAX_NAME_LENGTH 30 +#define IIO_MAX_NAME_LENGTH 64 #define FORMAT_SCAN_ELEMENTS_DIR "%s/scan_elements" #define FORMAT_TYPE_FILE "%s_type" diff --git a/tools/include/asm/sections.h b/tools/include/asm/sections.h new file mode 100644 index 000000000000..a80643d7a7f1 --- /dev/null +++ b/tools/include/asm/sections.h @@ -0,0 +1,4 @@ +#ifndef __TOOLS_INCLUDE_LINUX_ASM_SECTIONS_H +#define __TOOLS_INCLUDE_LINUX_ASM_SECTIONS_H + +#endif /* __TOOLS_INCLUDE_LINUX_ASM_SECTIONS_H */ diff --git a/tools/include/linux/bitops.h b/tools/include/linux/bitops.h index 1aecad369af5..969db1981868 100644 --- a/tools/include/linux/bitops.h +++ b/tools/include/linux/bitops.h @@ -61,4 +61,14 @@ static inline unsigned fls_long(unsigned long l) return fls64(l); } +/** + * rol32 - rotate a 32-bit value left + * @word: value to rotate + * @shift: bits to roll + */ +static inline __u32 rol32(__u32 word, unsigned int shift) +{ + return (word << shift) | (word >> ((-shift) & 31)); +} + #endif diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h index 825d44f89a29..3723b9f8f964 100644 --- a/tools/include/linux/compiler-gcc.h +++ b/tools/include/linux/compiler-gcc.h @@ -19,3 +19,16 @@ /* &a[0] degrades to a pointer: a different type from an array */ #define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) + +#define noinline __attribute__((noinline)) +#ifndef __packed +#define __packed __attribute__((packed)) +#endif +#ifndef __noreturn +#define __noreturn __attribute__((noreturn)) +#endif +#ifndef __aligned +#define __aligned(x) __attribute__((aligned(x))) +#endif +#define __printf(a, b) __attribute__((format(printf, a, b))) +#define __scanf(a, b) __attribute__((format(scanf, a, b))) diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h index 23299d7e7160..d7a5604c38d7 100644 --- a/tools/include/linux/compiler.h +++ b/tools/include/linux/compiler.h @@ -17,6 +17,10 @@ # define __always_inline inline __attribute__((always_inline)) #endif +#ifndef noinline +#define noinline +#endif + /* Are two types/vars the same type (ignoring qualifiers)? */ #ifndef __same_type # define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b)) @@ -45,6 +49,10 @@ # define __maybe_unused __attribute__((unused)) #endif +#ifndef __used +# define __used __attribute__((__unused__)) +#endif + #ifndef __packed # define __packed __attribute__((__packed__)) #endif @@ -65,6 +73,14 @@ # define unlikely(x) __builtin_expect(!!(x), 0) #endif +#ifndef __init +# define __init +#endif + +#ifndef noinline +# define noinline +#endif + #define uninitialized_var(x) x = *(&(x)) #define ACCESS_ONCE(x) (*(volatile typeof(x) *)&(x)) diff --git a/tools/include/linux/coresight-pmu.h b/tools/include/linux/coresight-pmu.h index 7d410260661b..edfeaba95429 100644 --- a/tools/include/linux/coresight-pmu.h +++ b/tools/include/linux/coresight-pmu.h @@ -24,6 +24,12 @@ /* ETMv3.5/PTM's ETMCR config bit */ #define ETM_OPT_CYCACC 12 #define ETM_OPT_TS 28 +#define ETM_OPT_RETSTK 29 + +/* ETMv4 CONFIGR programming bits for the ETM OPTs */ +#define ETM4_CFG_BIT_CYCACC 4 +#define ETM4_CFG_BIT_TS 11 +#define ETM4_CFG_BIT_RETSTK 12 static inline int coresight_get_trace_id(int cpu) { diff --git a/tools/lib/lockdep/uinclude/linux/debug_locks.h b/tools/include/linux/debug_locks.h index f38eb64df794..61cc7f501168 100644 --- a/tools/lib/lockdep/uinclude/linux/debug_locks.h +++ b/tools/include/linux/debug_locks.h @@ -3,8 +3,9 @@ #include <stddef.h> #include <linux/compiler.h> +#include <asm/bug.h> -#define DEBUG_LOCKS_WARN_ON(x) (x) +#define DEBUG_LOCKS_WARN_ON(x) WARN_ON(x) extern bool debug_locks; extern bool debug_locks_silent; diff --git a/tools/include/linux/delay.h b/tools/include/linux/delay.h new file mode 100644 index 000000000000..55aa4173af1f --- /dev/null +++ b/tools/include/linux/delay.h @@ -0,0 +1,4 @@ +#ifndef _TOOLS_INCLUDE_LINUX_DELAY_H +#define _TOOLS_INCLUDE_LINUX_DELAY_H + +#endif /* _TOOLS_INCLUDE_LINUX_DELAY_H */ diff --git a/tools/include/linux/err.h b/tools/include/linux/err.h index bdc3dd8131d4..abf0478a8fb2 100644 --- a/tools/include/linux/err.h +++ b/tools/include/linux/err.h @@ -46,4 +46,9 @@ static inline bool __must_check IS_ERR(__force const void *ptr) return IS_ERR_VALUE((unsigned long)ptr); } +static inline bool __must_check IS_ERR_OR_NULL(__force const void *ptr) +{ + return unlikely(!ptr) || IS_ERR_VALUE((unsigned long)ptr); +} + #endif /* _LINUX_ERR_H */ diff --git a/tools/include/linux/ftrace.h b/tools/include/linux/ftrace.h new file mode 100644 index 000000000000..949f541ce11e --- /dev/null +++ b/tools/include/linux/ftrace.h @@ -0,0 +1,4 @@ +#ifndef _TOOLS_INCLUDE_LINUX_FTRACE_H +#define _TOOLS_INCLUDE_LINUX_FTRACE_H + +#endif /* _TOOLS_INCLUDE_LINUX_FTRACE_H */ diff --git a/tools/include/linux/gfp.h b/tools/include/linux/gfp.h new file mode 100644 index 000000000000..22030756fbc0 --- /dev/null +++ b/tools/include/linux/gfp.h @@ -0,0 +1,4 @@ +#ifndef _TOOLS_INCLUDE_LINUX_GFP_H +#define _TOOLS_INCLUDE_LINUX_GFP_H + +#endif /* _TOOLS_INCLUDE_LINUX_GFP_H */ diff --git a/tools/lib/lockdep/uinclude/linux/hardirq.h b/tools/include/linux/hardirq.h index c8f3f8f58729..c8f3f8f58729 100644 --- a/tools/lib/lockdep/uinclude/linux/hardirq.h +++ b/tools/include/linux/hardirq.h diff --git a/tools/include/linux/interrupt.h b/tools/include/linux/interrupt.h new file mode 100644 index 000000000000..6be25bbdca9e --- /dev/null +++ b/tools/include/linux/interrupt.h @@ -0,0 +1,4 @@ +#ifndef _TOOLS_INCLUDE_LINUX_INTERRUPT_H +#define _TOOLS_INCLUDE_LINUX_INTERRUPT_H + +#endif /* _TOOLS_INCLUDE_LINUX_INTERRUPT_H */ diff --git a/tools/lib/lockdep/uinclude/linux/irqflags.h b/tools/include/linux/irqflags.h index 6cc296f0fad0..df77669cfe1c 100644 --- a/tools/lib/lockdep/uinclude/linux/irqflags.h +++ b/tools/include/linux/irqflags.h @@ -17,19 +17,19 @@ #define raw_local_irq_disable() do { } while (0) #define raw_local_irq_enable() do { } while (0) #define raw_local_irq_save(flags) ((flags) = 0) -#define raw_local_irq_restore(flags) do { } while (0) +#define raw_local_irq_restore(flags) ((void)(flags)) #define raw_local_save_flags(flags) ((flags) = 0) -#define raw_irqs_disabled_flags(flags) do { } while (0) +#define raw_irqs_disabled_flags(flags) ((void)(flags)) #define raw_irqs_disabled() 0 #define raw_safe_halt() #define local_irq_enable() do { } while (0) #define local_irq_disable() do { } while (0) #define local_irq_save(flags) ((flags) = 0) -#define local_irq_restore(flags) do { } while (0) +#define local_irq_restore(flags) ((void)(flags)) #define local_save_flags(flags) ((flags) = 0) #define irqs_disabled() (1) -#define irqs_disabled_flags(flags) (0) +#define irqs_disabled_flags(flags) ((void)(flags), 0) #define safe_halt() do { } while (0) #define trace_lock_release(x, y) diff --git a/tools/include/linux/jhash.h b/tools/include/linux/jhash.h new file mode 100644 index 000000000000..348c6f47e4cc --- /dev/null +++ b/tools/include/linux/jhash.h @@ -0,0 +1,175 @@ +#ifndef _LINUX_JHASH_H +#define _LINUX_JHASH_H + +/* jhash.h: Jenkins hash support. + * + * Copyright (C) 2006. Bob Jenkins (bob_jenkins@burtleburtle.net) + * + * http://burtleburtle.net/bob/hash/ + * + * These are the credits from Bob's sources: + * + * lookup3.c, by Bob Jenkins, May 2006, Public Domain. + * + * These are functions for producing 32-bit hashes for hash table lookup. + * hashword(), hashlittle(), hashlittle2(), hashbig(), mix(), and final() + * are externally useful functions. Routines to test the hash are included + * if SELF_TEST is defined. You can use this free for any purpose. It's in + * the public domain. It has no warranty. + * + * Copyright (C) 2009-2010 Jozsef Kadlecsik (kadlec@blackhole.kfki.hu) + * + * I've modified Bob's hash to be useful in the Linux kernel, and + * any bugs present are my fault. + * Jozsef + */ +#include <linux/bitops.h> +#include <linux/unaligned/packed_struct.h> + +/* Best hash sizes are of power of two */ +#define jhash_size(n) ((u32)1<<(n)) +/* Mask the hash value, i.e (value & jhash_mask(n)) instead of (value % n) */ +#define jhash_mask(n) (jhash_size(n)-1) + +/* __jhash_mix -- mix 3 32-bit values reversibly. */ +#define __jhash_mix(a, b, c) \ +{ \ + a -= c; a ^= rol32(c, 4); c += b; \ + b -= a; b ^= rol32(a, 6); a += c; \ + c -= b; c ^= rol32(b, 8); b += a; \ + a -= c; a ^= rol32(c, 16); c += b; \ + b -= a; b ^= rol32(a, 19); a += c; \ + c -= b; c ^= rol32(b, 4); b += a; \ +} + +/* __jhash_final - final mixing of 3 32-bit values (a,b,c) into c */ +#define __jhash_final(a, b, c) \ +{ \ + c ^= b; c -= rol32(b, 14); \ + a ^= c; a -= rol32(c, 11); \ + b ^= a; b -= rol32(a, 25); \ + c ^= b; c -= rol32(b, 16); \ + a ^= c; a -= rol32(c, 4); \ + b ^= a; b -= rol32(a, 14); \ + c ^= b; c -= rol32(b, 24); \ +} + +/* An arbitrary initial parameter */ +#define JHASH_INITVAL 0xdeadbeef + +/* jhash - hash an arbitrary key + * @k: sequence of bytes as key + * @length: the length of the key + * @initval: the previous hash, or an arbitray value + * + * The generic version, hashes an arbitrary sequence of bytes. + * No alignment or length assumptions are made about the input key. + * + * Returns the hash value of the key. The result depends on endianness. + */ +static inline u32 jhash(const void *key, u32 length, u32 initval) +{ + u32 a, b, c; + const u8 *k = key; + + /* Set up the internal state */ + a = b = c = JHASH_INITVAL + length + initval; + + /* All but the last block: affect some 32 bits of (a,b,c) */ + while (length > 12) { + a += __get_unaligned_cpu32(k); + b += __get_unaligned_cpu32(k + 4); + c += __get_unaligned_cpu32(k + 8); + __jhash_mix(a, b, c); + length -= 12; + k += 12; + } + /* Last block: affect all 32 bits of (c) */ + /* All the case statements fall through */ + switch (length) { + case 12: c += (u32)k[11]<<24; + case 11: c += (u32)k[10]<<16; + case 10: c += (u32)k[9]<<8; + case 9: c += k[8]; + case 8: b += (u32)k[7]<<24; + case 7: b += (u32)k[6]<<16; + case 6: b += (u32)k[5]<<8; + case 5: b += k[4]; + case 4: a += (u32)k[3]<<24; + case 3: a += (u32)k[2]<<16; + case 2: a += (u32)k[1]<<8; + case 1: a += k[0]; + __jhash_final(a, b, c); + case 0: /* Nothing left to add */ + break; + } + + return c; +} + +/* jhash2 - hash an array of u32's + * @k: the key which must be an array of u32's + * @length: the number of u32's in the key + * @initval: the previous hash, or an arbitray value + * + * Returns the hash value of the key. + */ +static inline u32 jhash2(const u32 *k, u32 length, u32 initval) +{ + u32 a, b, c; + + /* Set up the internal state */ + a = b = c = JHASH_INITVAL + (length<<2) + initval; + + /* Handle most of the key */ + while (length > 3) { + a += k[0]; + b += k[1]; + c += k[2]; + __jhash_mix(a, b, c); + length -= 3; + k += 3; + } + + /* Handle the last 3 u32's: all the case statements fall through */ + switch (length) { + case 3: c += k[2]; + case 2: b += k[1]; + case 1: a += k[0]; + __jhash_final(a, b, c); + case 0: /* Nothing left to add */ + break; + } + + return c; +} + + +/* __jhash_nwords - hash exactly 3, 2 or 1 word(s) */ +static inline u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval) +{ + a += initval; + b += initval; + c += initval; + + __jhash_final(a, b, c); + + return c; +} + +static inline u32 jhash_3words(u32 a, u32 b, u32 c, u32 initval) +{ + return __jhash_nwords(a, b, c, initval + JHASH_INITVAL + (3 << 2)); +} + +static inline u32 jhash_2words(u32 a, u32 b, u32 initval) +{ + return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2)); +} + +static inline u32 jhash_1word(u32 a, u32 initval) +{ + return __jhash_nwords(a, 0, 0, initval + JHASH_INITVAL + (1 << 2)); +} + +#endif /* _LINUX_JHASH_H */ diff --git a/tools/lib/lockdep/uinclude/linux/kallsyms.h b/tools/include/linux/kallsyms.h index b0f2dbdf1a15..582cc1e5f3a4 100644 --- a/tools/lib/lockdep/uinclude/linux/kallsyms.h +++ b/tools/include/linux/kallsyms.h @@ -3,6 +3,7 @@ #include <linux/kernel.h> #include <stdio.h> +#include <unistd.h> #define KSYM_NAME_LEN 128 @@ -24,7 +25,7 @@ static inline void print_ip_sym(unsigned long ip) name = backtrace_symbols((void **)&ip, 1); - printf("%s\n", *name); + dprintf(STDOUT_FILENO, "%s\n", *name); free(name); } diff --git a/tools/lib/lockdep/uinclude/linux/kern_levels.h b/tools/include/linux/kern_levels.h index 3b9bade28698..3b9bade28698 100644 --- a/tools/lib/lockdep/uinclude/linux/kern_levels.h +++ b/tools/include/linux/kern_levels.h diff --git a/tools/include/linux/kernel.h b/tools/include/linux/kernel.h index 73ccc48126bb..77d2e94ca5df 100644 --- a/tools/include/linux/kernel.h +++ b/tools/include/linux/kernel.h @@ -5,6 +5,8 @@ #include <stddef.h> #include <assert.h> #include <linux/compiler.h> +#include <endian.h> +#include <byteswap.h> #ifndef UINT_MAX #define UINT_MAX (~0U) @@ -32,6 +34,7 @@ (type *)((char *)__mptr - offsetof(type, member)); }) #endif +#define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)])) #define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:-!!(e); })) #ifndef max @@ -67,12 +70,33 @@ #endif #endif -/* - * Both need more care to handle endianness - * (Don't use bitmap_copy_le() for now) - */ -#define cpu_to_le64(x) (x) -#define cpu_to_le32(x) (x) +#if __BYTE_ORDER == __BIG_ENDIAN +#define cpu_to_le16 bswap_16 +#define cpu_to_le32 bswap_32 +#define cpu_to_le64 bswap_64 +#define le16_to_cpu bswap_16 +#define le32_to_cpu bswap_32 +#define le64_to_cpu bswap_64 +#define cpu_to_be16 +#define cpu_to_be32 +#define cpu_to_be64 +#define be16_to_cpu +#define be32_to_cpu +#define be64_to_cpu +#else +#define cpu_to_le16 +#define cpu_to_le32 +#define cpu_to_le64 +#define le16_to_cpu +#define le32_to_cpu +#define le64_to_cpu +#define cpu_to_be16 bswap_16 +#define cpu_to_be32 bswap_32 +#define cpu_to_be64 bswap_64 +#define be16_to_cpu bswap_16 +#define be32_to_cpu bswap_32 +#define be64_to_cpu bswap_64 +#endif int vscnprintf(char *buf, size_t size, const char *fmt, va_list args); int scnprintf(char * buf, size_t size, const char * fmt, ...); @@ -89,4 +113,7 @@ int scnprintf(char * buf, size_t size, const char * fmt, ...); #define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1) #define round_down(x, y) ((x) & ~__round_mask(x, y)) +#define current_gfp_context(k) 0 +#define synchronize_sched() + #endif diff --git a/tools/lib/lockdep/uinclude/linux/kmemcheck.h b/tools/include/linux/kmemcheck.h index 94d598bc6abe..94d598bc6abe 100644 --- a/tools/lib/lockdep/uinclude/linux/kmemcheck.h +++ b/tools/include/linux/kmemcheck.h diff --git a/tools/include/linux/linkage.h b/tools/include/linux/linkage.h new file mode 100644 index 000000000000..bc763d500262 --- /dev/null +++ b/tools/include/linux/linkage.h @@ -0,0 +1,4 @@ +#ifndef _TOOLS_INCLUDE_LINUX_LINKAGE_H +#define _TOOLS_INCLUDE_LINUX_LINKAGE_H + +#endif /* _TOOLS_INCLUDE_LINUX_LINKAGE_H */ diff --git a/tools/lib/lockdep/uinclude/linux/lockdep.h b/tools/include/linux/lockdep.h index c808c7d02d21..8da3e8effafa 100644 --- a/tools/lib/lockdep/uinclude/linux/lockdep.h +++ b/tools/include/linux/lockdep.h @@ -7,8 +7,15 @@ #include <limits.h> #include <linux/utsname.h> #include <linux/compiler.h> +#include <linux/export.h> +#include <linux/kern_levels.h> +#include <linux/err.h> +#include <linux/rcu.h> +#include <linux/list.h> +#include <linux/hardirq.h> +#include <unistd.h> -#define MAX_LOCK_DEPTH 2000UL +#define MAX_LOCK_DEPTH 63UL #define asmlinkage #define __visible @@ -29,31 +36,32 @@ extern struct task_struct *__curr(void); #define current (__curr()) -#define debug_locks_off() 1 +static inline int debug_locks_off(void) +{ + return 1; +} + #define task_pid_nr(tsk) ((tsk)->pid) #define KSYM_NAME_LEN 128 -#define printk printf +#define printk(...) dprintf(STDOUT_FILENO, __VA_ARGS__) +#define pr_err(format, ...) fprintf (stderr, format, ## __VA_ARGS__) +#define pr_warn pr_err #define list_del_rcu list_del #define atomic_t unsigned long #define atomic_inc(x) ((*(x))++) -static struct new_utsname *init_utsname(void) -{ - static struct new_utsname n = (struct new_utsname) { - .release = "liblockdep", - .version = LIBLOCKDEP_VERSION, - }; - - return &n; -} - #define print_tainted() "" #define static_obj(x) 1 #define debug_show_all_locks() extern void debug_check_no_locks_held(void); +static __used bool __is_kernel_percpu_address(unsigned long addr, void *can_addr) +{ + return false; +} + #endif diff --git a/tools/lib/lockdep/uinclude/linux/module.h b/tools/include/linux/module.h index 09c7a7be8ccc..07055db296f3 100644 --- a/tools/lib/lockdep/uinclude/linux/module.h +++ b/tools/include/linux/module.h @@ -3,4 +3,9 @@ #define module_param(name, type, perm) +static inline bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr) +{ + return false; +} + #endif diff --git a/tools/include/linux/mutex.h b/tools/include/linux/mutex.h new file mode 100644 index 000000000000..a8180d25f2fc --- /dev/null +++ b/tools/include/linux/mutex.h @@ -0,0 +1,4 @@ +#ifndef _TOOLS_INCLUDE_LINUX_MUTEX_H +#define _TOOLS_INCLUDE_LINUX_MUTEX_H + +#endif /* _TOOLS_INCLUDE_LINUX_MUTEX_H */ diff --git a/tools/include/linux/proc_fs.h b/tools/include/linux/proc_fs.h new file mode 100644 index 000000000000..8b3b03b64fda --- /dev/null +++ b/tools/include/linux/proc_fs.h @@ -0,0 +1,4 @@ +#ifndef _TOOLS_INCLUDE_LINUX_PROC_FS_H +#define _TOOLS_INCLUDE_LINUX_PROC_FS_H + +#endif /* _TOOLS_INCLUDE_LINUX_PROC_FS_H */ diff --git a/tools/lib/lockdep/uinclude/linux/rcu.h b/tools/include/linux/rcu.h index 042ee8e463c9..5080649dad04 100644 --- a/tools/lib/lockdep/uinclude/linux/rcu.h +++ b/tools/include/linux/rcu.h @@ -18,4 +18,7 @@ static inline bool rcu_is_watching(void) return false; } +#define rcu_assign_pointer(p, v) ((p) = (v)) +#define RCU_INIT_POINTER(p, v) p=(v) + #endif diff --git a/tools/include/linux/sched/clock.h b/tools/include/linux/sched/clock.h new file mode 100644 index 000000000000..5837d17c4182 --- /dev/null +++ b/tools/include/linux/sched/clock.h @@ -0,0 +1,4 @@ +#ifndef _TOOLS_PERF_LINUX_SCHED_CLOCK_H +#define _TOOLS_PERF_LINUX_SCHED_CLOCK_H + +#endif /* _TOOLS_PERF_LINUX_SCHED_CLOCK_H */ diff --git a/tools/include/linux/sched/mm.h b/tools/include/linux/sched/mm.h new file mode 100644 index 000000000000..c8d9f19c1f35 --- /dev/null +++ b/tools/include/linux/sched/mm.h @@ -0,0 +1,4 @@ +#ifndef _TOOLS_PERF_LINUX_SCHED_MM_H +#define _TOOLS_PERF_LINUX_SCHED_MM_H + +#endif /* _TOOLS_PERF_LINUX_SCHED_MM_H */ diff --git a/tools/include/linux/sched/task.h b/tools/include/linux/sched/task.h new file mode 100644 index 000000000000..a97890eca110 --- /dev/null +++ b/tools/include/linux/sched/task.h @@ -0,0 +1,4 @@ +#ifndef _TOOLS_PERF_LINUX_SCHED_TASK_H +#define _TOOLS_PERF_LINUX_SCHED_TASK_H + +#endif /* _TOOLS_PERF_LINUX_SCHED_TASK_H */ diff --git a/tools/include/linux/seq_file.h b/tools/include/linux/seq_file.h new file mode 100644 index 000000000000..102fd9217f1f --- /dev/null +++ b/tools/include/linux/seq_file.h @@ -0,0 +1,4 @@ +#ifndef _TOOLS_INCLUDE_LINUX_SEQ_FILE_H +#define _TOOLS_INCLUDE_LINUX_SEQ_FILE_H + +#endif /* _TOOLS_INCLUDE_LINUX_SEQ_FILE_H */ diff --git a/tools/include/linux/spinlock.h b/tools/include/linux/spinlock.h index 58397dcb19d6..417cda4f793f 100644 --- a/tools/include/linux/spinlock.h +++ b/tools/include/linux/spinlock.h @@ -1,5 +1,31 @@ +#ifndef __LINUX_SPINLOCK_H_ +#define __LINUX_SPINLOCK_H_ + +#include <pthread.h> +#include <stdbool.h> + #define spinlock_t pthread_mutex_t #define DEFINE_SPINLOCK(x) pthread_mutex_t x = PTHREAD_MUTEX_INITIALIZER; #define spin_lock_irqsave(x, f) (void)f, pthread_mutex_lock(x) #define spin_unlock_irqrestore(x, f) (void)f, pthread_mutex_unlock(x) + +#define arch_spinlock_t pthread_mutex_t +#define __ARCH_SPIN_LOCK_UNLOCKED PTHREAD_MUTEX_INITIALIZER + +static inline void arch_spin_lock(arch_spinlock_t *mutex) +{ + pthread_mutex_lock(mutex); +} + +static inline void arch_spin_unlock(arch_spinlock_t *mutex) +{ + pthread_mutex_unlock(mutex); +} + +static inline bool arch_spin_is_locked(arch_spinlock_t *mutex) +{ + return true; +} + +#endif diff --git a/tools/lib/lockdep/uinclude/linux/stacktrace.h b/tools/include/linux/stacktrace.h index 39aecc6b19d1..39aecc6b19d1 100644 --- a/tools/lib/lockdep/uinclude/linux/stacktrace.h +++ b/tools/include/linux/stacktrace.h diff --git a/tools/include/linux/string.h b/tools/include/linux/string.h index d62b56cf8c12..a30fad536f52 100644 --- a/tools/include/linux/string.h +++ b/tools/include/linux/string.h @@ -1,8 +1,8 @@ #ifndef _TOOLS_LINUX_STRING_H_ #define _TOOLS_LINUX_STRING_H_ - #include <linux/types.h> /* for size_t */ +#include <string.h> void *memdup(const void *src, size_t len); @@ -18,6 +18,14 @@ extern size_t strlcpy(char *dest, const char *src, size_t size); char *str_error_r(int errnum, char *buf, size_t buflen); -int prefixcmp(const char *str, const char *prefix); +/** + * strstarts - does @str start with @prefix? + * @str: string to examine + * @prefix: prefix to look for. + */ +static inline bool strstarts(const char *str, const char *prefix) +{ + return strncmp(str, prefix, strlen(prefix)) == 0; +} #endif /* _LINUX_STRING_H_ */ diff --git a/tools/include/linux/unaligned/packed_struct.h b/tools/include/linux/unaligned/packed_struct.h new file mode 100644 index 000000000000..c0d817de4df2 --- /dev/null +++ b/tools/include/linux/unaligned/packed_struct.h @@ -0,0 +1,46 @@ +#ifndef _LINUX_UNALIGNED_PACKED_STRUCT_H +#define _LINUX_UNALIGNED_PACKED_STRUCT_H + +#include <linux/kernel.h> + +struct __una_u16 { u16 x; } __packed; +struct __una_u32 { u32 x; } __packed; +struct __una_u64 { u64 x; } __packed; + +static inline u16 __get_unaligned_cpu16(const void *p) +{ + const struct __una_u16 *ptr = (const struct __una_u16 *)p; + return ptr->x; +} + +static inline u32 __get_unaligned_cpu32(const void *p) +{ + const struct __una_u32 *ptr = (const struct __una_u32 *)p; + return ptr->x; +} + +static inline u64 __get_unaligned_cpu64(const void *p) +{ + const struct __una_u64 *ptr = (const struct __una_u64 *)p; + return ptr->x; +} + +static inline void __put_unaligned_cpu16(u16 val, void *p) +{ + struct __una_u16 *ptr = (struct __una_u16 *)p; + ptr->x = val; +} + +static inline void __put_unaligned_cpu32(u32 val, void *p) +{ + struct __una_u32 *ptr = (struct __una_u32 *)p; + ptr->x = val; +} + +static inline void __put_unaligned_cpu64(u64 val, void *p) +{ + struct __una_u64 *ptr = (struct __una_u64 *)p; + ptr->x = val; +} + +#endif /* _LINUX_UNALIGNED_PACKED_STRUCT_H */ diff --git a/tools/include/trace/events/lock.h b/tools/include/trace/events/lock.h new file mode 100644 index 000000000000..5b15fd5ee1af --- /dev/null +++ b/tools/include/trace/events/lock.h @@ -0,0 +1,4 @@ +#ifndef _TOOLS_INCLUDE_TRACE_EVENTS_LOCK_H +#define _TOOLS_INCLUDE_TRACE_EVENTS_LOCK_H + +#endif /* _TOOLS_INCLUDE_TRACE_EVENTS_LOCK_H */ diff --git a/tools/include/uapi/asm-generic/fcntl.h b/tools/include/uapi/asm-generic/fcntl.h new file mode 100644 index 000000000000..ac190958c981 --- /dev/null +++ b/tools/include/uapi/asm-generic/fcntl.h @@ -0,0 +1,220 @@ +#ifndef _ASM_GENERIC_FCNTL_H +#define _ASM_GENERIC_FCNTL_H + +#include <linux/types.h> + +/* + * FMODE_EXEC is 0x20 + * FMODE_NONOTIFY is 0x4000000 + * These cannot be used by userspace O_* until internal and external open + * flags are split. + * -Eric Paris + */ + +/* + * When introducing new O_* bits, please check its uniqueness in fcntl_init(). + */ + +#define O_ACCMODE 00000003 +#define O_RDONLY 00000000 +#define O_WRONLY 00000001 +#define O_RDWR 00000002 +#ifndef O_CREAT +#define O_CREAT 00000100 /* not fcntl */ +#endif +#ifndef O_EXCL +#define O_EXCL 00000200 /* not fcntl */ +#endif +#ifndef O_NOCTTY +#define O_NOCTTY 00000400 /* not fcntl */ +#endif +#ifndef O_TRUNC +#define O_TRUNC 00001000 /* not fcntl */ +#endif +#ifndef O_APPEND +#define O_APPEND 00002000 +#endif +#ifndef O_NONBLOCK +#define O_NONBLOCK 00004000 +#endif +#ifndef O_DSYNC +#define O_DSYNC 00010000 /* used to be O_SYNC, see below */ +#endif +#ifndef FASYNC +#define FASYNC 00020000 /* fcntl, for BSD compatibility */ +#endif +#ifndef O_DIRECT +#define O_DIRECT 00040000 /* direct disk access hint */ +#endif +#ifndef O_LARGEFILE +#define O_LARGEFILE 00100000 +#endif +#ifndef O_DIRECTORY +#define O_DIRECTORY 00200000 /* must be a directory */ +#endif +#ifndef O_NOFOLLOW +#define O_NOFOLLOW 00400000 /* don't follow links */ +#endif +#ifndef O_NOATIME +#define O_NOATIME 01000000 +#endif +#ifndef O_CLOEXEC +#define O_CLOEXEC 02000000 /* set close_on_exec */ +#endif + +/* + * Before Linux 2.6.33 only O_DSYNC semantics were implemented, but using + * the O_SYNC flag. We continue to use the existing numerical value + * for O_DSYNC semantics now, but using the correct symbolic name for it. + * This new value is used to request true Posix O_SYNC semantics. It is + * defined in this strange way to make sure applications compiled against + * new headers get at least O_DSYNC semantics on older kernels. + * + * This has the nice side-effect that we can simply test for O_DSYNC + * wherever we do not care if O_DSYNC or O_SYNC is used. + * + * Note: __O_SYNC must never be used directly. + */ +#ifndef O_SYNC +#define __O_SYNC 04000000 +#define O_SYNC (__O_SYNC|O_DSYNC) +#endif + +#ifndef O_PATH +#define O_PATH 010000000 +#endif + +#ifndef __O_TMPFILE +#define __O_TMPFILE 020000000 +#endif + +/* a horrid kludge trying to make sure that this will fail on old kernels */ +#define O_TMPFILE (__O_TMPFILE | O_DIRECTORY) +#define O_TMPFILE_MASK (__O_TMPFILE | O_DIRECTORY | O_CREAT) + +#ifndef O_NDELAY +#define O_NDELAY O_NONBLOCK +#endif + +#define F_DUPFD 0 /* dup */ +#define F_GETFD 1 /* get close_on_exec */ +#define F_SETFD 2 /* set/clear close_on_exec */ +#define F_GETFL 3 /* get file->f_flags */ +#define F_SETFL 4 /* set file->f_flags */ +#ifndef F_GETLK +#define F_GETLK 5 +#define F_SETLK 6 +#define F_SETLKW 7 +#endif +#ifndef F_SETOWN +#define F_SETOWN 8 /* for sockets. */ +#define F_GETOWN 9 /* for sockets. */ +#endif +#ifndef F_SETSIG +#define F_SETSIG 10 /* for sockets. */ +#define F_GETSIG 11 /* for sockets. */ +#endif + +#ifndef CONFIG_64BIT +#ifndef F_GETLK64 +#define F_GETLK64 12 /* using 'struct flock64' */ +#define F_SETLK64 13 +#define F_SETLKW64 14 +#endif +#endif + +#ifndef F_SETOWN_EX +#define F_SETOWN_EX 15 +#define F_GETOWN_EX 16 +#endif + +#ifndef F_GETOWNER_UIDS +#define F_GETOWNER_UIDS 17 +#endif + +/* + * Open File Description Locks + * + * Usually record locks held by a process are released on *any* close and are + * not inherited across a fork(). + * + * These cmd values will set locks that conflict with process-associated + * record locks, but are "owned" by the open file description, not the + * process. This means that they are inherited across fork() like BSD (flock) + * locks, and they are only released automatically when the last reference to + * the the open file against which they were acquired is put. + */ +#define F_OFD_GETLK 36 +#define F_OFD_SETLK 37 +#define F_OFD_SETLKW 38 + +#define F_OWNER_TID 0 +#define F_OWNER_PID 1 +#define F_OWNER_PGRP 2 + +struct f_owner_ex { + int type; + __kernel_pid_t pid; +}; + +/* for F_[GET|SET]FL */ +#define FD_CLOEXEC 1 /* actually anything with low bit set goes */ + +/* for posix fcntl() and lockf() */ +#ifndef F_RDLCK +#define F_RDLCK 0 +#define F_WRLCK 1 +#define F_UNLCK 2 +#endif + +/* for old implementation of bsd flock () */ +#ifndef F_EXLCK +#define F_EXLCK 4 /* or 3 */ +#define F_SHLCK 8 /* or 4 */ +#endif + +/* operations for bsd flock(), also used by the kernel implementation */ +#define LOCK_SH 1 /* shared lock */ +#define LOCK_EX 2 /* exclusive lock */ +#define LOCK_NB 4 /* or'd with one of the above to prevent + blocking */ +#define LOCK_UN 8 /* remove lock */ + +#define LOCK_MAND 32 /* This is a mandatory flock ... */ +#define LOCK_READ 64 /* which allows concurrent read operations */ +#define LOCK_WRITE 128 /* which allows concurrent write operations */ +#define LOCK_RW 192 /* which allows concurrent read & write ops */ + +#define F_LINUX_SPECIFIC_BASE 1024 + +#ifndef HAVE_ARCH_STRUCT_FLOCK +#ifndef __ARCH_FLOCK_PAD +#define __ARCH_FLOCK_PAD +#endif + +struct flock { + short l_type; + short l_whence; + __kernel_off_t l_start; + __kernel_off_t l_len; + __kernel_pid_t l_pid; + __ARCH_FLOCK_PAD +}; +#endif + +#ifndef HAVE_ARCH_STRUCT_FLOCK64 +#ifndef __ARCH_FLOCK64_PAD +#define __ARCH_FLOCK64_PAD +#endif + +struct flock64 { + short l_type; + short l_whence; + __kernel_loff_t l_start; + __kernel_loff_t l_len; + __kernel_pid_t l_pid; + __ARCH_FLOCK64_PAD +}; +#endif + +#endif /* _ASM_GENERIC_FCNTL_H */ diff --git a/tools/include/uapi/asm-generic/ioctls.h b/tools/include/uapi/asm-generic/ioctls.h new file mode 100644 index 000000000000..14baf9f23a14 --- /dev/null +++ b/tools/include/uapi/asm-generic/ioctls.h @@ -0,0 +1,118 @@ +#ifndef __ASM_GENERIC_IOCTLS_H +#define __ASM_GENERIC_IOCTLS_H + +#include <linux/ioctl.h> + +/* + * These are the most common definitions for tty ioctl numbers. + * Most of them do not use the recommended _IOC(), but there is + * probably some source code out there hardcoding the number, + * so we might as well use them for all new platforms. + * + * The architectures that use different values here typically + * try to be compatible with some Unix variants for the same + * architecture. + */ + +/* 0x54 is just a magic number to make these relatively unique ('T') */ + +#define TCGETS 0x5401 +#define TCSETS 0x5402 +#define TCSETSW 0x5403 +#define TCSETSF 0x5404 +#define TCGETA 0x5405 +#define TCSETA 0x5406 +#define TCSETAW 0x5407 +#define TCSETAF 0x5408 +#define TCSBRK 0x5409 +#define TCXONC 0x540A +#define TCFLSH 0x540B +#define TIOCEXCL 0x540C +#define TIOCNXCL 0x540D +#define TIOCSCTTY 0x540E +#define TIOCGPGRP 0x540F +#define TIOCSPGRP 0x5410 +#define TIOCOUTQ 0x5411 +#define TIOCSTI 0x5412 +#define TIOCGWINSZ 0x5413 +#define TIOCSWINSZ 0x5414 +#define TIOCMGET 0x5415 +#define TIOCMBIS 0x5416 +#define TIOCMBIC 0x5417 +#define TIOCMSET 0x5418 +#define TIOCGSOFTCAR 0x5419 +#define TIOCSSOFTCAR 0x541A +#define FIONREAD 0x541B +#define TIOCINQ FIONREAD +#define TIOCLINUX 0x541C +#define TIOCCONS 0x541D +#define TIOCGSERIAL 0x541E +#define TIOCSSERIAL 0x541F +#define TIOCPKT 0x5420 +#define FIONBIO 0x5421 +#define TIOCNOTTY 0x5422 +#define TIOCSETD 0x5423 +#define TIOCGETD 0x5424 +#define TCSBRKP 0x5425 /* Needed for POSIX tcsendbreak() */ +#define TIOCSBRK 0x5427 /* BSD compatibility */ +#define TIOCCBRK 0x5428 /* BSD compatibility */ +#define TIOCGSID 0x5429 /* Return the session ID of FD */ +#define TCGETS2 _IOR('T', 0x2A, struct termios2) +#define TCSETS2 _IOW('T', 0x2B, struct termios2) +#define TCSETSW2 _IOW('T', 0x2C, struct termios2) +#define TCSETSF2 _IOW('T', 0x2D, struct termios2) +#define TIOCGRS485 0x542E +#ifndef TIOCSRS485 +#define TIOCSRS485 0x542F +#endif +#define TIOCGPTN _IOR('T', 0x30, unsigned int) /* Get Pty Number (of pty-mux device) */ +#define TIOCSPTLCK _IOW('T', 0x31, int) /* Lock/unlock Pty */ +#define TIOCGDEV _IOR('T', 0x32, unsigned int) /* Get primary device node of /dev/console */ +#define TCGETX 0x5432 /* SYS5 TCGETX compatibility */ +#define TCSETX 0x5433 +#define TCSETXF 0x5434 +#define TCSETXW 0x5435 +#define TIOCSIG _IOW('T', 0x36, int) /* pty: generate signal */ +#define TIOCVHANGUP 0x5437 +#define TIOCGPKT _IOR('T', 0x38, int) /* Get packet mode state */ +#define TIOCGPTLCK _IOR('T', 0x39, int) /* Get Pty lock state */ +#define TIOCGEXCL _IOR('T', 0x40, int) /* Get exclusive mode state */ +#define TIOCGPTPEER _IO('T', 0x41) /* Safely open the slave */ + +#define FIONCLEX 0x5450 +#define FIOCLEX 0x5451 +#define FIOASYNC 0x5452 +#define TIOCSERCONFIG 0x5453 +#define TIOCSERGWILD 0x5454 +#define TIOCSERSWILD 0x5455 +#define TIOCGLCKTRMIOS 0x5456 +#define TIOCSLCKTRMIOS 0x5457 +#define TIOCSERGSTRUCT 0x5458 /* For debugging only */ +#define TIOCSERGETLSR 0x5459 /* Get line status register */ +#define TIOCSERGETMULTI 0x545A /* Get multiport config */ +#define TIOCSERSETMULTI 0x545B /* Set multiport config */ + +#define TIOCMIWAIT 0x545C /* wait for a change on serial input line(s) */ +#define TIOCGICOUNT 0x545D /* read serial port inline interrupt counts */ + +/* + * Some arches already define FIOQSIZE due to a historical + * conflict with a Hayes modem-specific ioctl value. + */ +#ifndef FIOQSIZE +# define FIOQSIZE 0x5460 +#endif + +/* Used for packet mode */ +#define TIOCPKT_DATA 0 +#define TIOCPKT_FLUSHREAD 1 +#define TIOCPKT_FLUSHWRITE 2 +#define TIOCPKT_STOP 4 +#define TIOCPKT_START 8 +#define TIOCPKT_NOSTOP 16 +#define TIOCPKT_DOSTOP 32 +#define TIOCPKT_IOCTL 64 + +#define TIOCSER_TEMT 0x01 /* Transmitter physically empty */ + +#endif /* __ASM_GENERIC_IOCTLS_H */ diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h new file mode 100644 index 000000000000..101593ab10ac --- /dev/null +++ b/tools/include/uapi/drm/drm.h @@ -0,0 +1,933 @@ +/** + * \file drm.h + * Header for the Direct Rendering Manager + * + * \author Rickard E. (Rik) Faith <faith@valinux.com> + * + * \par Acknowledgments: + * Dec 1999, Richard Henderson <rth@twiddle.net>, move to generic \c cmpxchg. + */ + +/* + * Copyright 1999 Precision Insight, Inc., Cedar Park, Texas. + * Copyright 2000 VA Linux Systems, Inc., Sunnyvale, California. + * All rights reserved. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice (including the next + * paragraph) shall be included in all copies or substantial portions of the + * Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ + +#ifndef _DRM_H_ +#define _DRM_H_ + +#if defined(__KERNEL__) + +#include <linux/types.h> +#include <asm/ioctl.h> +typedef unsigned int drm_handle_t; + +#elif defined(__linux__) + +#include <linux/types.h> +#include <asm/ioctl.h> +typedef unsigned int drm_handle_t; + +#else /* One of the BSDs */ + +#include <sys/ioccom.h> +#include <sys/types.h> +typedef int8_t __s8; +typedef uint8_t __u8; +typedef int16_t __s16; +typedef uint16_t __u16; +typedef int32_t __s32; +typedef uint32_t __u32; +typedef int64_t __s64; +typedef uint64_t __u64; +typedef size_t __kernel_size_t; +typedef unsigned long drm_handle_t; + +#endif + +#if defined(__cplusplus) +extern "C" { +#endif + +#define DRM_NAME "drm" /**< Name in kernel, /dev, and /proc */ +#define DRM_MIN_ORDER 5 /**< At least 2^5 bytes = 32 bytes */ +#define DRM_MAX_ORDER 22 /**< Up to 2^22 bytes = 4MB */ +#define DRM_RAM_PERCENT 10 /**< How much system ram can we lock? */ + +#define _DRM_LOCK_HELD 0x80000000U /**< Hardware lock is held */ +#define _DRM_LOCK_CONT 0x40000000U /**< Hardware lock is contended */ +#define _DRM_LOCK_IS_HELD(lock) ((lock) & _DRM_LOCK_HELD) +#define _DRM_LOCK_IS_CONT(lock) ((lock) & _DRM_LOCK_CONT) +#define _DRM_LOCKING_CONTEXT(lock) ((lock) & ~(_DRM_LOCK_HELD|_DRM_LOCK_CONT)) + +typedef unsigned int drm_context_t; +typedef unsigned int drm_drawable_t; +typedef unsigned int drm_magic_t; + +/** + * Cliprect. + * + * \warning: If you change this structure, make sure you change + * XF86DRIClipRectRec in the server as well + * + * \note KW: Actually it's illegal to change either for + * backwards-compatibility reasons. + */ +struct drm_clip_rect { + unsigned short x1; + unsigned short y1; + unsigned short x2; + unsigned short y2; +}; + +/** + * Drawable information. + */ +struct drm_drawable_info { + unsigned int num_rects; + struct drm_clip_rect *rects; +}; + +/** + * Texture region, + */ +struct drm_tex_region { + unsigned char next; + unsigned char prev; + unsigned char in_use; + unsigned char padding; + unsigned int age; +}; + +/** + * Hardware lock. + * + * The lock structure is a simple cache-line aligned integer. To avoid + * processor bus contention on a multiprocessor system, there should not be any + * other data stored in the same cache line. + */ +struct drm_hw_lock { + __volatile__ unsigned int lock; /**< lock variable */ + char padding[60]; /**< Pad to cache line */ +}; + +/** + * DRM_IOCTL_VERSION ioctl argument type. + * + * \sa drmGetVersion(). + */ +struct drm_version { + int version_major; /**< Major version */ + int version_minor; /**< Minor version */ + int version_patchlevel; /**< Patch level */ + __kernel_size_t name_len; /**< Length of name buffer */ + char __user *name; /**< Name of driver */ + __kernel_size_t date_len; /**< Length of date buffer */ + char __user *date; /**< User-space buffer to hold date */ + __kernel_size_t desc_len; /**< Length of desc buffer */ + char __user *desc; /**< User-space buffer to hold desc */ +}; + +/** + * DRM_IOCTL_GET_UNIQUE ioctl argument type. + * + * \sa drmGetBusid() and drmSetBusId(). + */ +struct drm_unique { + __kernel_size_t unique_len; /**< Length of unique */ + char __user *unique; /**< Unique name for driver instantiation */ +}; + +struct drm_list { + int count; /**< Length of user-space structures */ + struct drm_version __user *version; +}; + +struct drm_block { + int unused; +}; + +/** + * DRM_IOCTL_CONTROL ioctl argument type. + * + * \sa drmCtlInstHandler() and drmCtlUninstHandler(). + */ +struct drm_control { + enum { + DRM_ADD_COMMAND, + DRM_RM_COMMAND, + DRM_INST_HANDLER, + DRM_UNINST_HANDLER + } func; + int irq; +}; + +/** + * Type of memory to map. + */ +enum drm_map_type { + _DRM_FRAME_BUFFER = 0, /**< WC (no caching), no core dump */ + _DRM_REGISTERS = 1, /**< no caching, no core dump */ + _DRM_SHM = 2, /**< shared, cached */ + _DRM_AGP = 3, /**< AGP/GART */ + _DRM_SCATTER_GATHER = 4, /**< Scatter/gather memory for PCI DMA */ + _DRM_CONSISTENT = 5 /**< Consistent memory for PCI DMA */ +}; + +/** + * Memory mapping flags. + */ +enum drm_map_flags { + _DRM_RESTRICTED = 0x01, /**< Cannot be mapped to user-virtual */ + _DRM_READ_ONLY = 0x02, + _DRM_LOCKED = 0x04, /**< shared, cached, locked */ + _DRM_KERNEL = 0x08, /**< kernel requires access */ + _DRM_WRITE_COMBINING = 0x10, /**< use write-combining if available */ + _DRM_CONTAINS_LOCK = 0x20, /**< SHM page that contains lock */ + _DRM_REMOVABLE = 0x40, /**< Removable mapping */ + _DRM_DRIVER = 0x80 /**< Managed by driver */ +}; + +struct drm_ctx_priv_map { + unsigned int ctx_id; /**< Context requesting private mapping */ + void *handle; /**< Handle of map */ +}; + +/** + * DRM_IOCTL_GET_MAP, DRM_IOCTL_ADD_MAP and DRM_IOCTL_RM_MAP ioctls + * argument type. + * + * \sa drmAddMap(). + */ +struct drm_map { + unsigned long offset; /**< Requested physical address (0 for SAREA)*/ + unsigned long size; /**< Requested physical size (bytes) */ + enum drm_map_type type; /**< Type of memory to map */ + enum drm_map_flags flags; /**< Flags */ + void *handle; /**< User-space: "Handle" to pass to mmap() */ + /**< Kernel-space: kernel-virtual address */ + int mtrr; /**< MTRR slot used */ + /* Private data */ +}; + +/** + * DRM_IOCTL_GET_CLIENT ioctl argument type. + */ +struct drm_client { + int idx; /**< Which client desired? */ + int auth; /**< Is client authenticated? */ + unsigned long pid; /**< Process ID */ + unsigned long uid; /**< User ID */ + unsigned long magic; /**< Magic */ + unsigned long iocs; /**< Ioctl count */ +}; + +enum drm_stat_type { + _DRM_STAT_LOCK, + _DRM_STAT_OPENS, + _DRM_STAT_CLOSES, + _DRM_STAT_IOCTLS, + _DRM_STAT_LOCKS, + _DRM_STAT_UNLOCKS, + _DRM_STAT_VALUE, /**< Generic value */ + _DRM_STAT_BYTE, /**< Generic byte counter (1024bytes/K) */ + _DRM_STAT_COUNT, /**< Generic non-byte counter (1000/k) */ + + _DRM_STAT_IRQ, /**< IRQ */ + _DRM_STAT_PRIMARY, /**< Primary DMA bytes */ + _DRM_STAT_SECONDARY, /**< Secondary DMA bytes */ + _DRM_STAT_DMA, /**< DMA */ + _DRM_STAT_SPECIAL, /**< Special DMA (e.g., priority or polled) */ + _DRM_STAT_MISSED /**< Missed DMA opportunity */ + /* Add to the *END* of the list */ +}; + +/** + * DRM_IOCTL_GET_STATS ioctl argument type. + */ +struct drm_stats { + unsigned long count; + struct { + unsigned long value; + enum drm_stat_type type; + } data[15]; +}; + +/** + * Hardware locking flags. + */ +enum drm_lock_flags { + _DRM_LOCK_READY = 0x01, /**< Wait until hardware is ready for DMA */ + _DRM_LOCK_QUIESCENT = 0x02, /**< Wait until hardware quiescent */ + _DRM_LOCK_FLUSH = 0x04, /**< Flush this context's DMA queue first */ + _DRM_LOCK_FLUSH_ALL = 0x08, /**< Flush all DMA queues first */ + /* These *HALT* flags aren't supported yet + -- they will be used to support the + full-screen DGA-like mode. */ + _DRM_HALT_ALL_QUEUES = 0x10, /**< Halt all current and future queues */ + _DRM_HALT_CUR_QUEUES = 0x20 /**< Halt all current queues */ +}; + +/** + * DRM_IOCTL_LOCK, DRM_IOCTL_UNLOCK and DRM_IOCTL_FINISH ioctl argument type. + * + * \sa drmGetLock() and drmUnlock(). + */ +struct drm_lock { + int context; + enum drm_lock_flags flags; +}; + +/** + * DMA flags + * + * \warning + * These values \e must match xf86drm.h. + * + * \sa drm_dma. + */ +enum drm_dma_flags { + /* Flags for DMA buffer dispatch */ + _DRM_DMA_BLOCK = 0x01, /**< + * Block until buffer dispatched. + * + * \note The buffer may not yet have + * been processed by the hardware -- + * getting a hardware lock with the + * hardware quiescent will ensure + * that the buffer has been + * processed. + */ + _DRM_DMA_WHILE_LOCKED = 0x02, /**< Dispatch while lock held */ + _DRM_DMA_PRIORITY = 0x04, /**< High priority dispatch */ + + /* Flags for DMA buffer request */ + _DRM_DMA_WAIT = 0x10, /**< Wait for free buffers */ + _DRM_DMA_SMALLER_OK = 0x20, /**< Smaller-than-requested buffers OK */ + _DRM_DMA_LARGER_OK = 0x40 /**< Larger-than-requested buffers OK */ +}; + +/** + * DRM_IOCTL_ADD_BUFS and DRM_IOCTL_MARK_BUFS ioctl argument type. + * + * \sa drmAddBufs(). + */ +struct drm_buf_desc { + int count; /**< Number of buffers of this size */ + int size; /**< Size in bytes */ + int low_mark; /**< Low water mark */ + int high_mark; /**< High water mark */ + enum { + _DRM_PAGE_ALIGN = 0x01, /**< Align on page boundaries for DMA */ + _DRM_AGP_BUFFER = 0x02, /**< Buffer is in AGP space */ + _DRM_SG_BUFFER = 0x04, /**< Scatter/gather memory buffer */ + _DRM_FB_BUFFER = 0x08, /**< Buffer is in frame buffer */ + _DRM_PCI_BUFFER_RO = 0x10 /**< Map PCI DMA buffer read-only */ + } flags; + unsigned long agp_start; /**< + * Start address of where the AGP buffers are + * in the AGP aperture + */ +}; + +/** + * DRM_IOCTL_INFO_BUFS ioctl argument type. + */ +struct drm_buf_info { + int count; /**< Entries in list */ + struct drm_buf_desc __user *list; +}; + +/** + * DRM_IOCTL_FREE_BUFS ioctl argument type. + */ +struct drm_buf_free { + int count; + int __user *list; +}; + +/** + * Buffer information + * + * \sa drm_buf_map. + */ +struct drm_buf_pub { + int idx; /**< Index into the master buffer list */ + int total; /**< Buffer size */ + int used; /**< Amount of buffer in use (for DMA) */ + void __user *address; /**< Address of buffer */ +}; + +/** + * DRM_IOCTL_MAP_BUFS ioctl argument type. + */ +struct drm_buf_map { + int count; /**< Length of the buffer list */ +#ifdef __cplusplus + void __user *virt; +#else + void __user *virtual; /**< Mmap'd area in user-virtual */ +#endif + struct drm_buf_pub __user *list; /**< Buffer information */ +}; + +/** + * DRM_IOCTL_DMA ioctl argument type. + * + * Indices here refer to the offset into the buffer list in drm_buf_get. + * + * \sa drmDMA(). + */ +struct drm_dma { + int context; /**< Context handle */ + int send_count; /**< Number of buffers to send */ + int __user *send_indices; /**< List of handles to buffers */ + int __user *send_sizes; /**< Lengths of data to send */ + enum drm_dma_flags flags; /**< Flags */ + int request_count; /**< Number of buffers requested */ + int request_size; /**< Desired size for buffers */ + int __user *request_indices; /**< Buffer information */ + int __user *request_sizes; + int granted_count; /**< Number of buffers granted */ +}; + +enum drm_ctx_flags { + _DRM_CONTEXT_PRESERVED = 0x01, + _DRM_CONTEXT_2DONLY = 0x02 +}; + +/** + * DRM_IOCTL_ADD_CTX ioctl argument type. + * + * \sa drmCreateContext() and drmDestroyContext(). + */ +struct drm_ctx { + drm_context_t handle; + enum drm_ctx_flags flags; +}; + +/** + * DRM_IOCTL_RES_CTX ioctl argument type. + */ +struct drm_ctx_res { + int count; + struct drm_ctx __user *contexts; +}; + +/** + * DRM_IOCTL_ADD_DRAW and DRM_IOCTL_RM_DRAW ioctl argument type. + */ +struct drm_draw { + drm_drawable_t handle; +}; + +/** + * DRM_IOCTL_UPDATE_DRAW ioctl argument type. + */ +typedef enum { + DRM_DRAWABLE_CLIPRECTS +} drm_drawable_info_type_t; + +struct drm_update_draw { + drm_drawable_t handle; + unsigned int type; + unsigned int num; + unsigned long long data; +}; + +/** + * DRM_IOCTL_GET_MAGIC and DRM_IOCTL_AUTH_MAGIC ioctl argument type. + */ +struct drm_auth { + drm_magic_t magic; +}; + +/** + * DRM_IOCTL_IRQ_BUSID ioctl argument type. + * + * \sa drmGetInterruptFromBusID(). + */ +struct drm_irq_busid { + int irq; /**< IRQ number */ + int busnum; /**< bus number */ + int devnum; /**< device number */ + int funcnum; /**< function number */ +}; + +enum drm_vblank_seq_type { + _DRM_VBLANK_ABSOLUTE = 0x0, /**< Wait for specific vblank sequence number */ + _DRM_VBLANK_RELATIVE = 0x1, /**< Wait for given number of vblanks */ + /* bits 1-6 are reserved for high crtcs */ + _DRM_VBLANK_HIGH_CRTC_MASK = 0x0000003e, + _DRM_VBLANK_EVENT = 0x4000000, /**< Send event instead of blocking */ + _DRM_VBLANK_FLIP = 0x8000000, /**< Scheduled buffer swap should flip */ + _DRM_VBLANK_NEXTONMISS = 0x10000000, /**< If missed, wait for next vblank */ + _DRM_VBLANK_SECONDARY = 0x20000000, /**< Secondary display controller */ + _DRM_VBLANK_SIGNAL = 0x40000000 /**< Send signal instead of blocking, unsupported */ +}; +#define _DRM_VBLANK_HIGH_CRTC_SHIFT 1 + +#define _DRM_VBLANK_TYPES_MASK (_DRM_VBLANK_ABSOLUTE | _DRM_VBLANK_RELATIVE) +#define _DRM_VBLANK_FLAGS_MASK (_DRM_VBLANK_EVENT | _DRM_VBLANK_SIGNAL | \ + _DRM_VBLANK_SECONDARY | _DRM_VBLANK_NEXTONMISS) + +struct drm_wait_vblank_request { + enum drm_vblank_seq_type type; + unsigned int sequence; + unsigned long signal; +}; + +struct drm_wait_vblank_reply { + enum drm_vblank_seq_type type; + unsigned int sequence; + long tval_sec; + long tval_usec; +}; + +/** + * DRM_IOCTL_WAIT_VBLANK ioctl argument type. + * + * \sa drmWaitVBlank(). + */ +union drm_wait_vblank { + struct drm_wait_vblank_request request; + struct drm_wait_vblank_reply reply; +}; + +#define _DRM_PRE_MODESET 1 +#define _DRM_POST_MODESET 2 + +/** + * DRM_IOCTL_MODESET_CTL ioctl argument type + * + * \sa drmModesetCtl(). + */ +struct drm_modeset_ctl { + __u32 crtc; + __u32 cmd; +}; + +/** + * DRM_IOCTL_AGP_ENABLE ioctl argument type. + * + * \sa drmAgpEnable(). + */ +struct drm_agp_mode { + unsigned long mode; /**< AGP mode */ +}; + +/** + * DRM_IOCTL_AGP_ALLOC and DRM_IOCTL_AGP_FREE ioctls argument type. + * + * \sa drmAgpAlloc() and drmAgpFree(). + */ +struct drm_agp_buffer { + unsigned long size; /**< In bytes -- will round to page boundary */ + unsigned long handle; /**< Used for binding / unbinding */ + unsigned long type; /**< Type of memory to allocate */ + unsigned long physical; /**< Physical used by i810 */ +}; + +/** + * DRM_IOCTL_AGP_BIND and DRM_IOCTL_AGP_UNBIND ioctls argument type. + * + * \sa drmAgpBind() and drmAgpUnbind(). + */ +struct drm_agp_binding { + unsigned long handle; /**< From drm_agp_buffer */ + unsigned long offset; /**< In bytes -- will round to page boundary */ +}; + +/** + * DRM_IOCTL_AGP_INFO ioctl argument type. + * + * \sa drmAgpVersionMajor(), drmAgpVersionMinor(), drmAgpGetMode(), + * drmAgpBase(), drmAgpSize(), drmAgpMemoryUsed(), drmAgpMemoryAvail(), + * drmAgpVendorId() and drmAgpDeviceId(). + */ +struct drm_agp_info { + int agp_version_major; + int agp_version_minor; + unsigned long mode; + unsigned long aperture_base; /* physical address */ + unsigned long aperture_size; /* bytes */ + unsigned long memory_allowed; /* bytes */ + unsigned long memory_used; + + /* PCI information */ + unsigned short id_vendor; + unsigned short id_device; +}; + +/** + * DRM_IOCTL_SG_ALLOC ioctl argument type. + */ +struct drm_scatter_gather { + unsigned long size; /**< In bytes -- will round to page boundary */ + unsigned long handle; /**< Used for mapping / unmapping */ +}; + +/** + * DRM_IOCTL_SET_VERSION ioctl argument type. + */ +struct drm_set_version { + int drm_di_major; + int drm_di_minor; + int drm_dd_major; + int drm_dd_minor; +}; + +/** DRM_IOCTL_GEM_CLOSE ioctl argument type */ +struct drm_gem_close { + /** Handle of the object to be closed. */ + __u32 handle; + __u32 pad; +}; + +/** DRM_IOCTL_GEM_FLINK ioctl argument type */ +struct drm_gem_flink { + /** Handle for the object being named */ + __u32 handle; + + /** Returned global name */ + __u32 name; +}; + +/** DRM_IOCTL_GEM_OPEN ioctl argument type */ +struct drm_gem_open { + /** Name of object being opened */ + __u32 name; + + /** Returned handle for the object */ + __u32 handle; + + /** Returned size of the object */ + __u64 size; +}; + +#define DRM_CAP_DUMB_BUFFER 0x1 +#define DRM_CAP_VBLANK_HIGH_CRTC 0x2 +#define DRM_CAP_DUMB_PREFERRED_DEPTH 0x3 +#define DRM_CAP_DUMB_PREFER_SHADOW 0x4 +#define DRM_CAP_PRIME 0x5 +#define DRM_PRIME_CAP_IMPORT 0x1 +#define DRM_PRIME_CAP_EXPORT 0x2 +#define DRM_CAP_TIMESTAMP_MONOTONIC 0x6 +#define DRM_CAP_ASYNC_PAGE_FLIP 0x7 +/* + * The CURSOR_WIDTH and CURSOR_HEIGHT capabilities return a valid widthxheight + * combination for the hardware cursor. The intention is that a hardware + * agnostic userspace can query a cursor plane size to use. + * + * Note that the cross-driver contract is to merely return a valid size; + * drivers are free to attach another meaning on top, eg. i915 returns the + * maximum plane size. + */ +#define DRM_CAP_CURSOR_WIDTH 0x8 +#define DRM_CAP_CURSOR_HEIGHT 0x9 +#define DRM_CAP_ADDFB2_MODIFIERS 0x10 +#define DRM_CAP_PAGE_FLIP_TARGET 0x11 +#define DRM_CAP_CRTC_IN_VBLANK_EVENT 0x12 +#define DRM_CAP_SYNCOBJ 0x13 + +/** DRM_IOCTL_GET_CAP ioctl argument type */ +struct drm_get_cap { + __u64 capability; + __u64 value; +}; + +/** + * DRM_CLIENT_CAP_STEREO_3D + * + * if set to 1, the DRM core will expose the stereo 3D capabilities of the + * monitor by advertising the supported 3D layouts in the flags of struct + * drm_mode_modeinfo. + */ +#define DRM_CLIENT_CAP_STEREO_3D 1 + +/** + * DRM_CLIENT_CAP_UNIVERSAL_PLANES + * + * If set to 1, the DRM core will expose all planes (overlay, primary, and + * cursor) to userspace. + */ +#define DRM_CLIENT_CAP_UNIVERSAL_PLANES 2 + +/** + * DRM_CLIENT_CAP_ATOMIC + * + * If set to 1, the DRM core will expose atomic properties to userspace + */ +#define DRM_CLIENT_CAP_ATOMIC 3 + +/** DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */ +struct drm_set_client_cap { + __u64 capability; + __u64 value; +}; + +#define DRM_RDWR O_RDWR +#define DRM_CLOEXEC O_CLOEXEC +struct drm_prime_handle { + __u32 handle; + + /** Flags.. only applicable for handle->fd */ + __u32 flags; + + /** Returned dmabuf file descriptor */ + __s32 fd; +}; + +struct drm_syncobj_create { + __u32 handle; + __u32 flags; +}; + +struct drm_syncobj_destroy { + __u32 handle; + __u32 pad; +}; + +#define DRM_SYNCOBJ_FD_TO_HANDLE_FLAGS_IMPORT_SYNC_FILE (1 << 0) +#define DRM_SYNCOBJ_HANDLE_TO_FD_FLAGS_EXPORT_SYNC_FILE (1 << 0) +struct drm_syncobj_handle { + __u32 handle; + __u32 flags; + + __s32 fd; + __u32 pad; +}; + +#if defined(__cplusplus) +} +#endif + +#include "drm_mode.h" + +#if defined(__cplusplus) +extern "C" { +#endif + +#define DRM_IOCTL_BASE 'd' +#define DRM_IO(nr) _IO(DRM_IOCTL_BASE,nr) +#define DRM_IOR(nr,type) _IOR(DRM_IOCTL_BASE,nr,type) +#define DRM_IOW(nr,type) _IOW(DRM_IOCTL_BASE,nr,type) +#define DRM_IOWR(nr,type) _IOWR(DRM_IOCTL_BASE,nr,type) + +#define DRM_IOCTL_VERSION DRM_IOWR(0x00, struct drm_version) +#define DRM_IOCTL_GET_UNIQUE DRM_IOWR(0x01, struct drm_unique) +#define DRM_IOCTL_GET_MAGIC DRM_IOR( 0x02, struct drm_auth) +#define DRM_IOCTL_IRQ_BUSID DRM_IOWR(0x03, struct drm_irq_busid) +#define DRM_IOCTL_GET_MAP DRM_IOWR(0x04, struct drm_map) +#define DRM_IOCTL_GET_CLIENT DRM_IOWR(0x05, struct drm_client) +#define DRM_IOCTL_GET_STATS DRM_IOR( 0x06, struct drm_stats) +#define DRM_IOCTL_SET_VERSION DRM_IOWR(0x07, struct drm_set_version) +#define DRM_IOCTL_MODESET_CTL DRM_IOW(0x08, struct drm_modeset_ctl) +#define DRM_IOCTL_GEM_CLOSE DRM_IOW (0x09, struct drm_gem_close) +#define DRM_IOCTL_GEM_FLINK DRM_IOWR(0x0a, struct drm_gem_flink) +#define DRM_IOCTL_GEM_OPEN DRM_IOWR(0x0b, struct drm_gem_open) +#define DRM_IOCTL_GET_CAP DRM_IOWR(0x0c, struct drm_get_cap) +#define DRM_IOCTL_SET_CLIENT_CAP DRM_IOW( 0x0d, struct drm_set_client_cap) + +#define DRM_IOCTL_SET_UNIQUE DRM_IOW( 0x10, struct drm_unique) +#define DRM_IOCTL_AUTH_MAGIC DRM_IOW( 0x11, struct drm_auth) +#define DRM_IOCTL_BLOCK DRM_IOWR(0x12, struct drm_block) +#define DRM_IOCTL_UNBLOCK DRM_IOWR(0x13, struct drm_block) +#define DRM_IOCTL_CONTROL DRM_IOW( 0x14, struct drm_control) +#define DRM_IOCTL_ADD_MAP DRM_IOWR(0x15, struct drm_map) +#define DRM_IOCTL_ADD_BUFS DRM_IOWR(0x16, struct drm_buf_desc) +#define DRM_IOCTL_MARK_BUFS DRM_IOW( 0x17, struct drm_buf_desc) +#define DRM_IOCTL_INFO_BUFS DRM_IOWR(0x18, struct drm_buf_info) +#define DRM_IOCTL_MAP_BUFS DRM_IOWR(0x19, struct drm_buf_map) +#define DRM_IOCTL_FREE_BUFS DRM_IOW( 0x1a, struct drm_buf_free) + +#define DRM_IOCTL_RM_MAP DRM_IOW( 0x1b, struct drm_map) + +#define DRM_IOCTL_SET_SAREA_CTX DRM_IOW( 0x1c, struct drm_ctx_priv_map) +#define DRM_IOCTL_GET_SAREA_CTX DRM_IOWR(0x1d, struct drm_ctx_priv_map) + +#define DRM_IOCTL_SET_MASTER DRM_IO(0x1e) +#define DRM_IOCTL_DROP_MASTER DRM_IO(0x1f) + +#define DRM_IOCTL_ADD_CTX DRM_IOWR(0x20, struct drm_ctx) +#define DRM_IOCTL_RM_CTX DRM_IOWR(0x21, struct drm_ctx) +#define DRM_IOCTL_MOD_CTX DRM_IOW( 0x22, struct drm_ctx) +#define DRM_IOCTL_GET_CTX DRM_IOWR(0x23, struct drm_ctx) +#define DRM_IOCTL_SWITCH_CTX DRM_IOW( 0x24, struct drm_ctx) +#define DRM_IOCTL_NEW_CTX DRM_IOW( 0x25, struct drm_ctx) +#define DRM_IOCTL_RES_CTX DRM_IOWR(0x26, struct drm_ctx_res) +#define DRM_IOCTL_ADD_DRAW DRM_IOWR(0x27, struct drm_draw) +#define DRM_IOCTL_RM_DRAW DRM_IOWR(0x28, struct drm_draw) +#define DRM_IOCTL_DMA DRM_IOWR(0x29, struct drm_dma) +#define DRM_IOCTL_LOCK DRM_IOW( 0x2a, struct drm_lock) +#define DRM_IOCTL_UNLOCK DRM_IOW( 0x2b, struct drm_lock) +#define DRM_IOCTL_FINISH DRM_IOW( 0x2c, struct drm_lock) + +#define DRM_IOCTL_PRIME_HANDLE_TO_FD DRM_IOWR(0x2d, struct drm_prime_handle) +#define DRM_IOCTL_PRIME_FD_TO_HANDLE DRM_IOWR(0x2e, struct drm_prime_handle) + +#define DRM_IOCTL_AGP_ACQUIRE DRM_IO( 0x30) +#define DRM_IOCTL_AGP_RELEASE DRM_IO( 0x31) +#define DRM_IOCTL_AGP_ENABLE DRM_IOW( 0x32, struct drm_agp_mode) +#define DRM_IOCTL_AGP_INFO DRM_IOR( 0x33, struct drm_agp_info) +#define DRM_IOCTL_AGP_ALLOC DRM_IOWR(0x34, struct drm_agp_buffer) +#define DRM_IOCTL_AGP_FREE DRM_IOW( 0x35, struct drm_agp_buffer) +#define DRM_IOCTL_AGP_BIND DRM_IOW( 0x36, struct drm_agp_binding) +#define DRM_IOCTL_AGP_UNBIND DRM_IOW( 0x37, struct drm_agp_binding) + +#define DRM_IOCTL_SG_ALLOC DRM_IOWR(0x38, struct drm_scatter_gather) +#define DRM_IOCTL_SG_FREE DRM_IOW( 0x39, struct drm_scatter_gather) + +#define DRM_IOCTL_WAIT_VBLANK DRM_IOWR(0x3a, union drm_wait_vblank) + +#define DRM_IOCTL_UPDATE_DRAW DRM_IOW(0x3f, struct drm_update_draw) + +#define DRM_IOCTL_MODE_GETRESOURCES DRM_IOWR(0xA0, struct drm_mode_card_res) +#define DRM_IOCTL_MODE_GETCRTC DRM_IOWR(0xA1, struct drm_mode_crtc) +#define DRM_IOCTL_MODE_SETCRTC DRM_IOWR(0xA2, struct drm_mode_crtc) +#define DRM_IOCTL_MODE_CURSOR DRM_IOWR(0xA3, struct drm_mode_cursor) +#define DRM_IOCTL_MODE_GETGAMMA DRM_IOWR(0xA4, struct drm_mode_crtc_lut) +#define DRM_IOCTL_MODE_SETGAMMA DRM_IOWR(0xA5, struct drm_mode_crtc_lut) +#define DRM_IOCTL_MODE_GETENCODER DRM_IOWR(0xA6, struct drm_mode_get_encoder) +#define DRM_IOCTL_MODE_GETCONNECTOR DRM_IOWR(0xA7, struct drm_mode_get_connector) +#define DRM_IOCTL_MODE_ATTACHMODE DRM_IOWR(0xA8, struct drm_mode_mode_cmd) /* deprecated (never worked) */ +#define DRM_IOCTL_MODE_DETACHMODE DRM_IOWR(0xA9, struct drm_mode_mode_cmd) /* deprecated (never worked) */ + +#define DRM_IOCTL_MODE_GETPROPERTY DRM_IOWR(0xAA, struct drm_mode_get_property) +#define DRM_IOCTL_MODE_SETPROPERTY DRM_IOWR(0xAB, struct drm_mode_connector_set_property) +#define DRM_IOCTL_MODE_GETPROPBLOB DRM_IOWR(0xAC, struct drm_mode_get_blob) +#define DRM_IOCTL_MODE_GETFB DRM_IOWR(0xAD, struct drm_mode_fb_cmd) +#define DRM_IOCTL_MODE_ADDFB DRM_IOWR(0xAE, struct drm_mode_fb_cmd) +#define DRM_IOCTL_MODE_RMFB DRM_IOWR(0xAF, unsigned int) +#define DRM_IOCTL_MODE_PAGE_FLIP DRM_IOWR(0xB0, struct drm_mode_crtc_page_flip) +#define DRM_IOCTL_MODE_DIRTYFB DRM_IOWR(0xB1, struct drm_mode_fb_dirty_cmd) + +#define DRM_IOCTL_MODE_CREATE_DUMB DRM_IOWR(0xB2, struct drm_mode_create_dumb) +#define DRM_IOCTL_MODE_MAP_DUMB DRM_IOWR(0xB3, struct drm_mode_map_dumb) +#define DRM_IOCTL_MODE_DESTROY_DUMB DRM_IOWR(0xB4, struct drm_mode_destroy_dumb) +#define DRM_IOCTL_MODE_GETPLANERESOURCES DRM_IOWR(0xB5, struct drm_mode_get_plane_res) +#define DRM_IOCTL_MODE_GETPLANE DRM_IOWR(0xB6, struct drm_mode_get_plane) +#define DRM_IOCTL_MODE_SETPLANE DRM_IOWR(0xB7, struct drm_mode_set_plane) +#define DRM_IOCTL_MODE_ADDFB2 DRM_IOWR(0xB8, struct drm_mode_fb_cmd2) +#define DRM_IOCTL_MODE_OBJ_GETPROPERTIES DRM_IOWR(0xB9, struct drm_mode_obj_get_properties) +#define DRM_IOCTL_MODE_OBJ_SETPROPERTY DRM_IOWR(0xBA, struct drm_mode_obj_set_property) +#define DRM_IOCTL_MODE_CURSOR2 DRM_IOWR(0xBB, struct drm_mode_cursor2) +#define DRM_IOCTL_MODE_ATOMIC DRM_IOWR(0xBC, struct drm_mode_atomic) +#define DRM_IOCTL_MODE_CREATEPROPBLOB DRM_IOWR(0xBD, struct drm_mode_create_blob) +#define DRM_IOCTL_MODE_DESTROYPROPBLOB DRM_IOWR(0xBE, struct drm_mode_destroy_blob) + +#define DRM_IOCTL_SYNCOBJ_CREATE DRM_IOWR(0xBF, struct drm_syncobj_create) +#define DRM_IOCTL_SYNCOBJ_DESTROY DRM_IOWR(0xC0, struct drm_syncobj_destroy) +#define DRM_IOCTL_SYNCOBJ_HANDLE_TO_FD DRM_IOWR(0xC1, struct drm_syncobj_handle) +#define DRM_IOCTL_SYNCOBJ_FD_TO_HANDLE DRM_IOWR(0xC2, struct drm_syncobj_handle) + +/** + * Device specific ioctls should only be in their respective headers + * The device specific ioctl range is from 0x40 to 0x9f. + * Generic IOCTLS restart at 0xA0. + * + * \sa drmCommandNone(), drmCommandRead(), drmCommandWrite(), and + * drmCommandReadWrite(). + */ +#define DRM_COMMAND_BASE 0x40 +#define DRM_COMMAND_END 0xA0 + +/** + * Header for events written back to userspace on the drm fd. The + * type defines the type of event, the length specifies the total + * length of the event (including the header), and user_data is + * typically a 64 bit value passed with the ioctl that triggered the + * event. A read on the drm fd will always only return complete + * events, that is, if for example the read buffer is 100 bytes, and + * there are two 64 byte events pending, only one will be returned. + * + * Event types 0 - 0x7fffffff are generic drm events, 0x80000000 and + * up are chipset specific. + */ +struct drm_event { + __u32 type; + __u32 length; +}; + +#define DRM_EVENT_VBLANK 0x01 +#define DRM_EVENT_FLIP_COMPLETE 0x02 + +struct drm_event_vblank { + struct drm_event base; + __u64 user_data; + __u32 tv_sec; + __u32 tv_usec; + __u32 sequence; + __u32 crtc_id; /* 0 on older kernels that do not support this */ +}; + +/* typedef area */ +#ifndef __KERNEL__ +typedef struct drm_clip_rect drm_clip_rect_t; +typedef struct drm_drawable_info drm_drawable_info_t; +typedef struct drm_tex_region drm_tex_region_t; +typedef struct drm_hw_lock drm_hw_lock_t; +typedef struct drm_version drm_version_t; +typedef struct drm_unique drm_unique_t; +typedef struct drm_list drm_list_t; +typedef struct drm_block drm_block_t; +typedef struct drm_control drm_control_t; +typedef enum drm_map_type drm_map_type_t; +typedef enum drm_map_flags drm_map_flags_t; +typedef struct drm_ctx_priv_map drm_ctx_priv_map_t; +typedef struct drm_map drm_map_t; +typedef struct drm_client drm_client_t; +typedef enum drm_stat_type drm_stat_type_t; +typedef struct drm_stats drm_stats_t; +typedef enum drm_lock_flags drm_lock_flags_t; +typedef struct drm_lock drm_lock_t; +typedef enum drm_dma_flags drm_dma_flags_t; +typedef struct drm_buf_desc drm_buf_desc_t; +typedef struct drm_buf_info drm_buf_info_t; +typedef struct drm_buf_free drm_buf_free_t; +typedef struct drm_buf_pub drm_buf_pub_t; +typedef struct drm_buf_map drm_buf_map_t; +typedef struct drm_dma drm_dma_t; +typedef union drm_wait_vblank drm_wait_vblank_t; +typedef struct drm_agp_mode drm_agp_mode_t; +typedef enum drm_ctx_flags drm_ctx_flags_t; +typedef struct drm_ctx drm_ctx_t; +typedef struct drm_ctx_res drm_ctx_res_t; +typedef struct drm_draw drm_draw_t; +typedef struct drm_update_draw drm_update_draw_t; +typedef struct drm_auth drm_auth_t; +typedef struct drm_irq_busid drm_irq_busid_t; +typedef enum drm_vblank_seq_type drm_vblank_seq_type_t; + +typedef struct drm_agp_buffer drm_agp_buffer_t; +typedef struct drm_agp_binding drm_agp_binding_t; +typedef struct drm_agp_info drm_agp_info_t; +typedef struct drm_scatter_gather drm_scatter_gather_t; +typedef struct drm_set_version drm_set_version_t; +#endif + +#if defined(__cplusplus) +} +#endif + +#endif diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h new file mode 100644 index 000000000000..7ccbd6a2bbe0 --- /dev/null +++ b/tools/include/uapi/drm/i915_drm.h @@ -0,0 +1,1474 @@ +/* + * Copyright 2003 Tungsten Graphics, Inc., Cedar Park, Texas. + * All Rights Reserved. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the + * "Software"), to deal in the Software without restriction, including + * without limitation the rights to use, copy, modify, merge, publish, + * distribute, sub license, and/or sell copies of the Software, and to + * permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice (including the + * next paragraph) shall be included in all copies or substantial portions + * of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS + * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. + * IN NO EVENT SHALL TUNGSTEN GRAPHICS AND/OR ITS SUPPLIERS BE LIABLE FOR + * ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, + * TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE + * SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. + * + */ + +#ifndef _UAPI_I915_DRM_H_ +#define _UAPI_I915_DRM_H_ + +#include "drm.h" + +#if defined(__cplusplus) +extern "C" { +#endif + +/* Please note that modifications to all structs defined here are + * subject to backwards-compatibility constraints. + */ + +/** + * DOC: uevents generated by i915 on it's device node + * + * I915_L3_PARITY_UEVENT - Generated when the driver receives a parity mismatch + * event from the gpu l3 cache. Additional information supplied is ROW, + * BANK, SUBBANK, SLICE of the affected cacheline. Userspace should keep + * track of these events and if a specific cache-line seems to have a + * persistent error remap it with the l3 remapping tool supplied in + * intel-gpu-tools. The value supplied with the event is always 1. + * + * I915_ERROR_UEVENT - Generated upon error detection, currently only via + * hangcheck. The error detection event is a good indicator of when things + * began to go badly. The value supplied with the event is a 1 upon error + * detection, and a 0 upon reset completion, signifying no more error + * exists. NOTE: Disabling hangcheck or reset via module parameter will + * cause the related events to not be seen. + * + * I915_RESET_UEVENT - Event is generated just before an attempt to reset the + * the GPU. The value supplied with the event is always 1. NOTE: Disable + * reset via module parameter will cause this event to not be seen. + */ +#define I915_L3_PARITY_UEVENT "L3_PARITY_ERROR" +#define I915_ERROR_UEVENT "ERROR" +#define I915_RESET_UEVENT "RESET" + +/* + * MOCS indexes used for GPU surfaces, defining the cacheability of the + * surface data and the coherency for this data wrt. CPU vs. GPU accesses. + */ +enum i915_mocs_table_index { + /* + * Not cached anywhere, coherency between CPU and GPU accesses is + * guaranteed. + */ + I915_MOCS_UNCACHED, + /* + * Cacheability and coherency controlled by the kernel automatically + * based on the DRM_I915_GEM_SET_CACHING IOCTL setting and the current + * usage of the surface (used for display scanout or not). + */ + I915_MOCS_PTE, + /* + * Cached in all GPU caches available on the platform. + * Coherency between CPU and GPU accesses to the surface is not + * guaranteed without extra synchronization. + */ + I915_MOCS_CACHED, +}; + +/* Each region is a minimum of 16k, and there are at most 255 of them. + */ +#define I915_NR_TEX_REGIONS 255 /* table size 2k - maximum due to use + * of chars for next/prev indices */ +#define I915_LOG_MIN_TEX_REGION_SIZE 14 + +typedef struct _drm_i915_init { + enum { + I915_INIT_DMA = 0x01, + I915_CLEANUP_DMA = 0x02, + I915_RESUME_DMA = 0x03 + } func; + unsigned int mmio_offset; + int sarea_priv_offset; + unsigned int ring_start; + unsigned int ring_end; + unsigned int ring_size; + unsigned int front_offset; + unsigned int back_offset; + unsigned int depth_offset; + unsigned int w; + unsigned int h; + unsigned int pitch; + unsigned int pitch_bits; + unsigned int back_pitch; + unsigned int depth_pitch; + unsigned int cpp; + unsigned int chipset; +} drm_i915_init_t; + +typedef struct _drm_i915_sarea { + struct drm_tex_region texList[I915_NR_TEX_REGIONS + 1]; + int last_upload; /* last time texture was uploaded */ + int last_enqueue; /* last time a buffer was enqueued */ + int last_dispatch; /* age of the most recently dispatched buffer */ + int ctxOwner; /* last context to upload state */ + int texAge; + int pf_enabled; /* is pageflipping allowed? */ + int pf_active; + int pf_current_page; /* which buffer is being displayed? */ + int perf_boxes; /* performance boxes to be displayed */ + int width, height; /* screen size in pixels */ + + drm_handle_t front_handle; + int front_offset; + int front_size; + + drm_handle_t back_handle; + int back_offset; + int back_size; + + drm_handle_t depth_handle; + int depth_offset; + int depth_size; + + drm_handle_t tex_handle; + int tex_offset; + int tex_size; + int log_tex_granularity; + int pitch; + int rotation; /* 0, 90, 180 or 270 */ + int rotated_offset; + int rotated_size; + int rotated_pitch; + int virtualX, virtualY; + + unsigned int front_tiled; + unsigned int back_tiled; + unsigned int depth_tiled; + unsigned int rotated_tiled; + unsigned int rotated2_tiled; + + int pipeA_x; + int pipeA_y; + int pipeA_w; + int pipeA_h; + int pipeB_x; + int pipeB_y; + int pipeB_w; + int pipeB_h; + + /* fill out some space for old userspace triple buffer */ + drm_handle_t unused_handle; + __u32 unused1, unused2, unused3; + + /* buffer object handles for static buffers. May change + * over the lifetime of the client. + */ + __u32 front_bo_handle; + __u32 back_bo_handle; + __u32 unused_bo_handle; + __u32 depth_bo_handle; + +} drm_i915_sarea_t; + +/* due to userspace building against these headers we need some compat here */ +#define planeA_x pipeA_x +#define planeA_y pipeA_y +#define planeA_w pipeA_w +#define planeA_h pipeA_h +#define planeB_x pipeB_x +#define planeB_y pipeB_y +#define planeB_w pipeB_w +#define planeB_h pipeB_h + +/* Flags for perf_boxes + */ +#define I915_BOX_RING_EMPTY 0x1 +#define I915_BOX_FLIP 0x2 +#define I915_BOX_WAIT 0x4 +#define I915_BOX_TEXTURE_LOAD 0x8 +#define I915_BOX_LOST_CONTEXT 0x10 + +/* + * i915 specific ioctls. + * + * The device specific ioctl range is [DRM_COMMAND_BASE, DRM_COMMAND_END) ie + * [0x40, 0xa0) (a0 is excluded). The numbers below are defined as offset + * against DRM_COMMAND_BASE and should be between [0x0, 0x60). + */ +#define DRM_I915_INIT 0x00 +#define DRM_I915_FLUSH 0x01 +#define DRM_I915_FLIP 0x02 +#define DRM_I915_BATCHBUFFER 0x03 +#define DRM_I915_IRQ_EMIT 0x04 +#define DRM_I915_IRQ_WAIT 0x05 +#define DRM_I915_GETPARAM 0x06 +#define DRM_I915_SETPARAM 0x07 +#define DRM_I915_ALLOC 0x08 +#define DRM_I915_FREE 0x09 +#define DRM_I915_INIT_HEAP 0x0a +#define DRM_I915_CMDBUFFER 0x0b +#define DRM_I915_DESTROY_HEAP 0x0c +#define DRM_I915_SET_VBLANK_PIPE 0x0d +#define DRM_I915_GET_VBLANK_PIPE 0x0e +#define DRM_I915_VBLANK_SWAP 0x0f +#define DRM_I915_HWS_ADDR 0x11 +#define DRM_I915_GEM_INIT 0x13 +#define DRM_I915_GEM_EXECBUFFER 0x14 +#define DRM_I915_GEM_PIN 0x15 +#define DRM_I915_GEM_UNPIN 0x16 +#define DRM_I915_GEM_BUSY 0x17 +#define DRM_I915_GEM_THROTTLE 0x18 +#define DRM_I915_GEM_ENTERVT 0x19 +#define DRM_I915_GEM_LEAVEVT 0x1a +#define DRM_I915_GEM_CREATE 0x1b +#define DRM_I915_GEM_PREAD 0x1c +#define DRM_I915_GEM_PWRITE 0x1d +#define DRM_I915_GEM_MMAP 0x1e +#define DRM_I915_GEM_SET_DOMAIN 0x1f +#define DRM_I915_GEM_SW_FINISH 0x20 +#define DRM_I915_GEM_SET_TILING 0x21 +#define DRM_I915_GEM_GET_TILING 0x22 +#define DRM_I915_GEM_GET_APERTURE 0x23 +#define DRM_I915_GEM_MMAP_GTT 0x24 +#define DRM_I915_GET_PIPE_FROM_CRTC_ID 0x25 +#define DRM_I915_GEM_MADVISE 0x26 +#define DRM_I915_OVERLAY_PUT_IMAGE 0x27 +#define DRM_I915_OVERLAY_ATTRS 0x28 +#define DRM_I915_GEM_EXECBUFFER2 0x29 +#define DRM_I915_GEM_EXECBUFFER2_WR DRM_I915_GEM_EXECBUFFER2 +#define DRM_I915_GET_SPRITE_COLORKEY 0x2a +#define DRM_I915_SET_SPRITE_COLORKEY 0x2b +#define DRM_I915_GEM_WAIT 0x2c +#define DRM_I915_GEM_CONTEXT_CREATE 0x2d +#define DRM_I915_GEM_CONTEXT_DESTROY 0x2e +#define DRM_I915_GEM_SET_CACHING 0x2f +#define DRM_I915_GEM_GET_CACHING 0x30 +#define DRM_I915_REG_READ 0x31 +#define DRM_I915_GET_RESET_STATS 0x32 +#define DRM_I915_GEM_USERPTR 0x33 +#define DRM_I915_GEM_CONTEXT_GETPARAM 0x34 +#define DRM_I915_GEM_CONTEXT_SETPARAM 0x35 +#define DRM_I915_PERF_OPEN 0x36 + +#define DRM_IOCTL_I915_INIT DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t) +#define DRM_IOCTL_I915_FLUSH DRM_IO ( DRM_COMMAND_BASE + DRM_I915_FLUSH) +#define DRM_IOCTL_I915_FLIP DRM_IO ( DRM_COMMAND_BASE + DRM_I915_FLIP) +#define DRM_IOCTL_I915_BATCHBUFFER DRM_IOW( DRM_COMMAND_BASE + DRM_I915_BATCHBUFFER, drm_i915_batchbuffer_t) +#define DRM_IOCTL_I915_IRQ_EMIT DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_IRQ_EMIT, drm_i915_irq_emit_t) +#define DRM_IOCTL_I915_IRQ_WAIT DRM_IOW( DRM_COMMAND_BASE + DRM_I915_IRQ_WAIT, drm_i915_irq_wait_t) +#define DRM_IOCTL_I915_GETPARAM DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GETPARAM, drm_i915_getparam_t) +#define DRM_IOCTL_I915_SETPARAM DRM_IOW( DRM_COMMAND_BASE + DRM_I915_SETPARAM, drm_i915_setparam_t) +#define DRM_IOCTL_I915_ALLOC DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_ALLOC, drm_i915_mem_alloc_t) +#define DRM_IOCTL_I915_FREE DRM_IOW( DRM_COMMAND_BASE + DRM_I915_FREE, drm_i915_mem_free_t) +#define DRM_IOCTL_I915_INIT_HEAP DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT_HEAP, drm_i915_mem_init_heap_t) +#define DRM_IOCTL_I915_CMDBUFFER DRM_IOW( DRM_COMMAND_BASE + DRM_I915_CMDBUFFER, drm_i915_cmdbuffer_t) +#define DRM_IOCTL_I915_DESTROY_HEAP DRM_IOW( DRM_COMMAND_BASE + DRM_I915_DESTROY_HEAP, drm_i915_mem_destroy_heap_t) +#define DRM_IOCTL_I915_SET_VBLANK_PIPE DRM_IOW( DRM_COMMAND_BASE + DRM_I915_SET_VBLANK_PIPE, drm_i915_vblank_pipe_t) +#define DRM_IOCTL_I915_GET_VBLANK_PIPE DRM_IOR( DRM_COMMAND_BASE + DRM_I915_GET_VBLANK_PIPE, drm_i915_vblank_pipe_t) +#define DRM_IOCTL_I915_VBLANK_SWAP DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_VBLANK_SWAP, drm_i915_vblank_swap_t) +#define DRM_IOCTL_I915_HWS_ADDR DRM_IOW(DRM_COMMAND_BASE + DRM_I915_HWS_ADDR, struct drm_i915_gem_init) +#define DRM_IOCTL_I915_GEM_INIT DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_INIT, struct drm_i915_gem_init) +#define DRM_IOCTL_I915_GEM_EXECBUFFER DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_EXECBUFFER, struct drm_i915_gem_execbuffer) +#define DRM_IOCTL_I915_GEM_EXECBUFFER2 DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_EXECBUFFER2, struct drm_i915_gem_execbuffer2) +#define DRM_IOCTL_I915_GEM_EXECBUFFER2_WR DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_EXECBUFFER2_WR, struct drm_i915_gem_execbuffer2) +#define DRM_IOCTL_I915_GEM_PIN DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_PIN, struct drm_i915_gem_pin) +#define DRM_IOCTL_I915_GEM_UNPIN DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_UNPIN, struct drm_i915_gem_unpin) +#define DRM_IOCTL_I915_GEM_BUSY DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_BUSY, struct drm_i915_gem_busy) +#define DRM_IOCTL_I915_GEM_SET_CACHING DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_SET_CACHING, struct drm_i915_gem_caching) +#define DRM_IOCTL_I915_GEM_GET_CACHING DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_GET_CACHING, struct drm_i915_gem_caching) +#define DRM_IOCTL_I915_GEM_THROTTLE DRM_IO ( DRM_COMMAND_BASE + DRM_I915_GEM_THROTTLE) +#define DRM_IOCTL_I915_GEM_ENTERVT DRM_IO(DRM_COMMAND_BASE + DRM_I915_GEM_ENTERVT) +#define DRM_IOCTL_I915_GEM_LEAVEVT DRM_IO(DRM_COMMAND_BASE + DRM_I915_GEM_LEAVEVT) +#define DRM_IOCTL_I915_GEM_CREATE DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_CREATE, struct drm_i915_gem_create) +#define DRM_IOCTL_I915_GEM_PREAD DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_PREAD, struct drm_i915_gem_pread) +#define DRM_IOCTL_I915_GEM_PWRITE DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_PWRITE, struct drm_i915_gem_pwrite) +#define DRM_IOCTL_I915_GEM_MMAP DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP, struct drm_i915_gem_mmap) +#define DRM_IOCTL_I915_GEM_MMAP_GTT DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP_GTT, struct drm_i915_gem_mmap_gtt) +#define DRM_IOCTL_I915_GEM_SET_DOMAIN DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_SET_DOMAIN, struct drm_i915_gem_set_domain) +#define DRM_IOCTL_I915_GEM_SW_FINISH DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_SW_FINISH, struct drm_i915_gem_sw_finish) +#define DRM_IOCTL_I915_GEM_SET_TILING DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_SET_TILING, struct drm_i915_gem_set_tiling) +#define DRM_IOCTL_I915_GEM_GET_TILING DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_GET_TILING, struct drm_i915_gem_get_tiling) +#define DRM_IOCTL_I915_GEM_GET_APERTURE DRM_IOR (DRM_COMMAND_BASE + DRM_I915_GEM_GET_APERTURE, struct drm_i915_gem_get_aperture) +#define DRM_IOCTL_I915_GET_PIPE_FROM_CRTC_ID DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GET_PIPE_FROM_CRTC_ID, struct drm_i915_get_pipe_from_crtc_id) +#define DRM_IOCTL_I915_GEM_MADVISE DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MADVISE, struct drm_i915_gem_madvise) +#define DRM_IOCTL_I915_OVERLAY_PUT_IMAGE DRM_IOW(DRM_COMMAND_BASE + DRM_I915_OVERLAY_PUT_IMAGE, struct drm_intel_overlay_put_image) +#define DRM_IOCTL_I915_OVERLAY_ATTRS DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_OVERLAY_ATTRS, struct drm_intel_overlay_attrs) +#define DRM_IOCTL_I915_SET_SPRITE_COLORKEY DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_SET_SPRITE_COLORKEY, struct drm_intel_sprite_colorkey) +#define DRM_IOCTL_I915_GET_SPRITE_COLORKEY DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GET_SPRITE_COLORKEY, struct drm_intel_sprite_colorkey) +#define DRM_IOCTL_I915_GEM_WAIT DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_WAIT, struct drm_i915_gem_wait) +#define DRM_IOCTL_I915_GEM_CONTEXT_CREATE DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_CREATE, struct drm_i915_gem_context_create) +#define DRM_IOCTL_I915_GEM_CONTEXT_DESTROY DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_DESTROY, struct drm_i915_gem_context_destroy) +#define DRM_IOCTL_I915_REG_READ DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_REG_READ, struct drm_i915_reg_read) +#define DRM_IOCTL_I915_GET_RESET_STATS DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GET_RESET_STATS, struct drm_i915_reset_stats) +#define DRM_IOCTL_I915_GEM_USERPTR DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_USERPTR, struct drm_i915_gem_userptr) +#define DRM_IOCTL_I915_GEM_CONTEXT_GETPARAM DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_GETPARAM, struct drm_i915_gem_context_param) +#define DRM_IOCTL_I915_GEM_CONTEXT_SETPARAM DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_SETPARAM, struct drm_i915_gem_context_param) +#define DRM_IOCTL_I915_PERF_OPEN DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_OPEN, struct drm_i915_perf_open_param) + +/* Allow drivers to submit batchbuffers directly to hardware, relying + * on the security mechanisms provided by hardware. + */ +typedef struct drm_i915_batchbuffer { + int start; /* agp offset */ + int used; /* nr bytes in use */ + int DR1; /* hw flags for GFX_OP_DRAWRECT_INFO */ + int DR4; /* window origin for GFX_OP_DRAWRECT_INFO */ + int num_cliprects; /* mulitpass with multiple cliprects? */ + struct drm_clip_rect __user *cliprects; /* pointer to userspace cliprects */ +} drm_i915_batchbuffer_t; + +/* As above, but pass a pointer to userspace buffer which can be + * validated by the kernel prior to sending to hardware. + */ +typedef struct _drm_i915_cmdbuffer { + char __user *buf; /* pointer to userspace command buffer */ + int sz; /* nr bytes in buf */ + int DR1; /* hw flags for GFX_OP_DRAWRECT_INFO */ + int DR4; /* window origin for GFX_OP_DRAWRECT_INFO */ + int num_cliprects; /* mulitpass with multiple cliprects? */ + struct drm_clip_rect __user *cliprects; /* pointer to userspace cliprects */ +} drm_i915_cmdbuffer_t; + +/* Userspace can request & wait on irq's: + */ +typedef struct drm_i915_irq_emit { + int __user *irq_seq; +} drm_i915_irq_emit_t; + +typedef struct drm_i915_irq_wait { + int irq_seq; +} drm_i915_irq_wait_t; + +/* Ioctl to query kernel params: + */ +#define I915_PARAM_IRQ_ACTIVE 1 +#define I915_PARAM_ALLOW_BATCHBUFFER 2 +#define I915_PARAM_LAST_DISPATCH 3 +#define I915_PARAM_CHIPSET_ID 4 +#define I915_PARAM_HAS_GEM 5 +#define I915_PARAM_NUM_FENCES_AVAIL 6 +#define I915_PARAM_HAS_OVERLAY 7 +#define I915_PARAM_HAS_PAGEFLIPPING 8 +#define I915_PARAM_HAS_EXECBUF2 9 +#define I915_PARAM_HAS_BSD 10 +#define I915_PARAM_HAS_BLT 11 +#define I915_PARAM_HAS_RELAXED_FENCING 12 +#define I915_PARAM_HAS_COHERENT_RINGS 13 +#define I915_PARAM_HAS_EXEC_CONSTANTS 14 +#define I915_PARAM_HAS_RELAXED_DELTA 15 +#define I915_PARAM_HAS_GEN7_SOL_RESET 16 +#define I915_PARAM_HAS_LLC 17 +#define I915_PARAM_HAS_ALIASING_PPGTT 18 +#define I915_PARAM_HAS_WAIT_TIMEOUT 19 +#define I915_PARAM_HAS_SEMAPHORES 20 +#define I915_PARAM_HAS_PRIME_VMAP_FLUSH 21 +#define I915_PARAM_HAS_VEBOX 22 +#define I915_PARAM_HAS_SECURE_BATCHES 23 +#define I915_PARAM_HAS_PINNED_BATCHES 24 +#define I915_PARAM_HAS_EXEC_NO_RELOC 25 +#define I915_PARAM_HAS_EXEC_HANDLE_LUT 26 +#define I915_PARAM_HAS_WT 27 +#define I915_PARAM_CMD_PARSER_VERSION 28 +#define I915_PARAM_HAS_COHERENT_PHYS_GTT 29 +#define I915_PARAM_MMAP_VERSION 30 +#define I915_PARAM_HAS_BSD2 31 +#define I915_PARAM_REVISION 32 +#define I915_PARAM_SUBSLICE_TOTAL 33 +#define I915_PARAM_EU_TOTAL 34 +#define I915_PARAM_HAS_GPU_RESET 35 +#define I915_PARAM_HAS_RESOURCE_STREAMER 36 +#define I915_PARAM_HAS_EXEC_SOFTPIN 37 +#define I915_PARAM_HAS_POOLED_EU 38 +#define I915_PARAM_MIN_EU_IN_POOL 39 +#define I915_PARAM_MMAP_GTT_VERSION 40 + +/* Query whether DRM_I915_GEM_EXECBUFFER2 supports user defined execution + * priorities and the driver will attempt to execute batches in priority order. + */ +#define I915_PARAM_HAS_SCHEDULER 41 +#define I915_PARAM_HUC_STATUS 42 + +/* Query whether DRM_I915_GEM_EXECBUFFER2 supports the ability to opt-out of + * synchronisation with implicit fencing on individual objects. + * See EXEC_OBJECT_ASYNC. + */ +#define I915_PARAM_HAS_EXEC_ASYNC 43 + +/* Query whether DRM_I915_GEM_EXECBUFFER2 supports explicit fence support - + * both being able to pass in a sync_file fd to wait upon before executing, + * and being able to return a new sync_file fd that is signaled when the + * current request is complete. See I915_EXEC_FENCE_IN and I915_EXEC_FENCE_OUT. + */ +#define I915_PARAM_HAS_EXEC_FENCE 44 + +/* Query whether DRM_I915_GEM_EXECBUFFER2 supports the ability to capture + * user specified bufffers for post-mortem debugging of GPU hangs. See + * EXEC_OBJECT_CAPTURE. + */ +#define I915_PARAM_HAS_EXEC_CAPTURE 45 + +#define I915_PARAM_SLICE_MASK 46 + +/* Assuming it's uniform for each slice, this queries the mask of subslices + * per-slice for this system. + */ +#define I915_PARAM_SUBSLICE_MASK 47 + +/* + * Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying the batch buffer + * as the first execobject as opposed to the last. See I915_EXEC_BATCH_FIRST. + */ +#define I915_PARAM_HAS_EXEC_BATCH_FIRST 48 + +typedef struct drm_i915_getparam { + __s32 param; + /* + * WARNING: Using pointers instead of fixed-size u64 means we need to write + * compat32 code. Don't repeat this mistake. + */ + int __user *value; +} drm_i915_getparam_t; + +/* Ioctl to set kernel params: + */ +#define I915_SETPARAM_USE_MI_BATCHBUFFER_START 1 +#define I915_SETPARAM_TEX_LRU_LOG_GRANULARITY 2 +#define I915_SETPARAM_ALLOW_BATCHBUFFER 3 +#define I915_SETPARAM_NUM_USED_FENCES 4 + +typedef struct drm_i915_setparam { + int param; + int value; +} drm_i915_setparam_t; + +/* A memory manager for regions of shared memory: + */ +#define I915_MEM_REGION_AGP 1 + +typedef struct drm_i915_mem_alloc { + int region; + int alignment; + int size; + int __user *region_offset; /* offset from start of fb or agp */ +} drm_i915_mem_alloc_t; + +typedef struct drm_i915_mem_free { + int region; + int region_offset; +} drm_i915_mem_free_t; + +typedef struct drm_i915_mem_init_heap { + int region; + int size; + int start; +} drm_i915_mem_init_heap_t; + +/* Allow memory manager to be torn down and re-initialized (eg on + * rotate): + */ +typedef struct drm_i915_mem_destroy_heap { + int region; +} drm_i915_mem_destroy_heap_t; + +/* Allow X server to configure which pipes to monitor for vblank signals + */ +#define DRM_I915_VBLANK_PIPE_A 1 +#define DRM_I915_VBLANK_PIPE_B 2 + +typedef struct drm_i915_vblank_pipe { + int pipe; +} drm_i915_vblank_pipe_t; + +/* Schedule buffer swap at given vertical blank: + */ +typedef struct drm_i915_vblank_swap { + drm_drawable_t drawable; + enum drm_vblank_seq_type seqtype; + unsigned int sequence; +} drm_i915_vblank_swap_t; + +typedef struct drm_i915_hws_addr { + __u64 addr; +} drm_i915_hws_addr_t; + +struct drm_i915_gem_init { + /** + * Beginning offset in the GTT to be managed by the DRM memory + * manager. + */ + __u64 gtt_start; + /** + * Ending offset in the GTT to be managed by the DRM memory + * manager. + */ + __u64 gtt_end; +}; + +struct drm_i915_gem_create { + /** + * Requested size for the object. + * + * The (page-aligned) allocated size for the object will be returned. + */ + __u64 size; + /** + * Returned handle for the object. + * + * Object handles are nonzero. + */ + __u32 handle; + __u32 pad; +}; + +struct drm_i915_gem_pread { + /** Handle for the object being read. */ + __u32 handle; + __u32 pad; + /** Offset into the object to read from */ + __u64 offset; + /** Length of data to read */ + __u64 size; + /** + * Pointer to write the data into. + * + * This is a fixed-size type for 32/64 compatibility. + */ + __u64 data_ptr; +}; + +struct drm_i915_gem_pwrite { + /** Handle for the object being written to. */ + __u32 handle; + __u32 pad; + /** Offset into the object to write to */ + __u64 offset; + /** Length of data to write */ + __u64 size; + /** + * Pointer to read the data from. + * + * This is a fixed-size type for 32/64 compatibility. + */ + __u64 data_ptr; +}; + +struct drm_i915_gem_mmap { + /** Handle for the object being mapped. */ + __u32 handle; + __u32 pad; + /** Offset in the object to map. */ + __u64 offset; + /** + * Length of data to map. + * + * The value will be page-aligned. + */ + __u64 size; + /** + * Returned pointer the data was mapped at. + * + * This is a fixed-size type for 32/64 compatibility. + */ + __u64 addr_ptr; + + /** + * Flags for extended behaviour. + * + * Added in version 2. + */ + __u64 flags; +#define I915_MMAP_WC 0x1 +}; + +struct drm_i915_gem_mmap_gtt { + /** Handle for the object being mapped. */ + __u32 handle; + __u32 pad; + /** + * Fake offset to use for subsequent mmap call + * + * This is a fixed-size type for 32/64 compatibility. + */ + __u64 offset; +}; + +struct drm_i915_gem_set_domain { + /** Handle for the object */ + __u32 handle; + + /** New read domains */ + __u32 read_domains; + + /** New write domain */ + __u32 write_domain; +}; + +struct drm_i915_gem_sw_finish { + /** Handle for the object */ + __u32 handle; +}; + +struct drm_i915_gem_relocation_entry { + /** + * Handle of the buffer being pointed to by this relocation entry. + * + * It's appealing to make this be an index into the mm_validate_entry + * list to refer to the buffer, but this allows the driver to create + * a relocation list for state buffers and not re-write it per + * exec using the buffer. + */ + __u32 target_handle; + + /** + * Value to be added to the offset of the target buffer to make up + * the relocation entry. + */ + __u32 delta; + + /** Offset in the buffer the relocation entry will be written into */ + __u64 offset; + + /** + * Offset value of the target buffer that the relocation entry was last + * written as. + * + * If the buffer has the same offset as last time, we can skip syncing + * and writing the relocation. This value is written back out by + * the execbuffer ioctl when the relocation is written. + */ + __u64 presumed_offset; + + /** + * Target memory domains read by this operation. + */ + __u32 read_domains; + + /** + * Target memory domains written by this operation. + * + * Note that only one domain may be written by the whole + * execbuffer operation, so that where there are conflicts, + * the application will get -EINVAL back. + */ + __u32 write_domain; +}; + +/** @{ + * Intel memory domains + * + * Most of these just align with the various caches in + * the system and are used to flush and invalidate as + * objects end up cached in different domains. + */ +/** CPU cache */ +#define I915_GEM_DOMAIN_CPU 0x00000001 +/** Render cache, used by 2D and 3D drawing */ +#define I915_GEM_DOMAIN_RENDER 0x00000002 +/** Sampler cache, used by texture engine */ +#define I915_GEM_DOMAIN_SAMPLER 0x00000004 +/** Command queue, used to load batch buffers */ +#define I915_GEM_DOMAIN_COMMAND 0x00000008 +/** Instruction cache, used by shader programs */ +#define I915_GEM_DOMAIN_INSTRUCTION 0x00000010 +/** Vertex address cache */ +#define I915_GEM_DOMAIN_VERTEX 0x00000020 +/** GTT domain - aperture and scanout */ +#define I915_GEM_DOMAIN_GTT 0x00000040 +/** WC domain - uncached access */ +#define I915_GEM_DOMAIN_WC 0x00000080 +/** @} */ + +struct drm_i915_gem_exec_object { + /** + * User's handle for a buffer to be bound into the GTT for this + * operation. + */ + __u32 handle; + + /** Number of relocations to be performed on this buffer */ + __u32 relocation_count; + /** + * Pointer to array of struct drm_i915_gem_relocation_entry containing + * the relocations to be performed in this buffer. + */ + __u64 relocs_ptr; + + /** Required alignment in graphics aperture */ + __u64 alignment; + + /** + * Returned value of the updated offset of the object, for future + * presumed_offset writes. + */ + __u64 offset; +}; + +struct drm_i915_gem_execbuffer { + /** + * List of buffers to be validated with their relocations to be + * performend on them. + * + * This is a pointer to an array of struct drm_i915_gem_validate_entry. + * + * These buffers must be listed in an order such that all relocations + * a buffer is performing refer to buffers that have already appeared + * in the validate list. + */ + __u64 buffers_ptr; + __u32 buffer_count; + + /** Offset in the batchbuffer to start execution from. */ + __u32 batch_start_offset; + /** Bytes used in batchbuffer from batch_start_offset */ + __u32 batch_len; + __u32 DR1; + __u32 DR4; + __u32 num_cliprects; + /** This is a struct drm_clip_rect *cliprects */ + __u64 cliprects_ptr; +}; + +struct drm_i915_gem_exec_object2 { + /** + * User's handle for a buffer to be bound into the GTT for this + * operation. + */ + __u32 handle; + + /** Number of relocations to be performed on this buffer */ + __u32 relocation_count; + /** + * Pointer to array of struct drm_i915_gem_relocation_entry containing + * the relocations to be performed in this buffer. + */ + __u64 relocs_ptr; + + /** Required alignment in graphics aperture */ + __u64 alignment; + + /** + * When the EXEC_OBJECT_PINNED flag is specified this is populated by + * the user with the GTT offset at which this object will be pinned. + * When the I915_EXEC_NO_RELOC flag is specified this must contain the + * presumed_offset of the object. + * During execbuffer2 the kernel populates it with the value of the + * current GTT offset of the object, for future presumed_offset writes. + */ + __u64 offset; + +#define EXEC_OBJECT_NEEDS_FENCE (1<<0) +#define EXEC_OBJECT_NEEDS_GTT (1<<1) +#define EXEC_OBJECT_WRITE (1<<2) +#define EXEC_OBJECT_SUPPORTS_48B_ADDRESS (1<<3) +#define EXEC_OBJECT_PINNED (1<<4) +#define EXEC_OBJECT_PAD_TO_SIZE (1<<5) +/* The kernel implicitly tracks GPU activity on all GEM objects, and + * synchronises operations with outstanding rendering. This includes + * rendering on other devices if exported via dma-buf. However, sometimes + * this tracking is too coarse and the user knows better. For example, + * if the object is split into non-overlapping ranges shared between different + * clients or engines (i.e. suballocating objects), the implicit tracking + * by kernel assumes that each operation affects the whole object rather + * than an individual range, causing needless synchronisation between clients. + * The kernel will also forgo any CPU cache flushes prior to rendering from + * the object as the client is expected to be also handling such domain + * tracking. + * + * The kernel maintains the implicit tracking in order to manage resources + * used by the GPU - this flag only disables the synchronisation prior to + * rendering with this object in this execbuf. + * + * Opting out of implicit synhronisation requires the user to do its own + * explicit tracking to avoid rendering corruption. See, for example, + * I915_PARAM_HAS_EXEC_FENCE to order execbufs and execute them asynchronously. + */ +#define EXEC_OBJECT_ASYNC (1<<6) +/* Request that the contents of this execobject be copied into the error + * state upon a GPU hang involving this batch for post-mortem debugging. + * These buffers are recorded in no particular order as "user" in + * /sys/class/drm/cardN/error. Query I915_PARAM_HAS_EXEC_CAPTURE to see + * if the kernel supports this flag. + */ +#define EXEC_OBJECT_CAPTURE (1<<7) +/* All remaining bits are MBZ and RESERVED FOR FUTURE USE */ +#define __EXEC_OBJECT_UNKNOWN_FLAGS -(EXEC_OBJECT_CAPTURE<<1) + __u64 flags; + + union { + __u64 rsvd1; + __u64 pad_to_size; + }; + __u64 rsvd2; +}; + +struct drm_i915_gem_execbuffer2 { + /** + * List of gem_exec_object2 structs + */ + __u64 buffers_ptr; + __u32 buffer_count; + + /** Offset in the batchbuffer to start execution from. */ + __u32 batch_start_offset; + /** Bytes used in batchbuffer from batch_start_offset */ + __u32 batch_len; + __u32 DR1; + __u32 DR4; + __u32 num_cliprects; + /** This is a struct drm_clip_rect *cliprects */ + __u64 cliprects_ptr; +#define I915_EXEC_RING_MASK (7<<0) +#define I915_EXEC_DEFAULT (0<<0) +#define I915_EXEC_RENDER (1<<0) +#define I915_EXEC_BSD (2<<0) +#define I915_EXEC_BLT (3<<0) +#define I915_EXEC_VEBOX (4<<0) + +/* Used for switching the constants addressing mode on gen4+ RENDER ring. + * Gen6+ only supports relative addressing to dynamic state (default) and + * absolute addressing. + * + * These flags are ignored for the BSD and BLT rings. + */ +#define I915_EXEC_CONSTANTS_MASK (3<<6) +#define I915_EXEC_CONSTANTS_REL_GENERAL (0<<6) /* default */ +#define I915_EXEC_CONSTANTS_ABSOLUTE (1<<6) +#define I915_EXEC_CONSTANTS_REL_SURFACE (2<<6) /* gen4/5 only */ + __u64 flags; + __u64 rsvd1; /* now used for context info */ + __u64 rsvd2; +}; + +/** Resets the SO write offset registers for transform feedback on gen7. */ +#define I915_EXEC_GEN7_SOL_RESET (1<<8) + +/** Request a privileged ("secure") batch buffer. Note only available for + * DRM_ROOT_ONLY | DRM_MASTER processes. + */ +#define I915_EXEC_SECURE (1<<9) + +/** Inform the kernel that the batch is and will always be pinned. This + * negates the requirement for a workaround to be performed to avoid + * an incoherent CS (such as can be found on 830/845). If this flag is + * not passed, the kernel will endeavour to make sure the batch is + * coherent with the CS before execution. If this flag is passed, + * userspace assumes the responsibility for ensuring the same. + */ +#define I915_EXEC_IS_PINNED (1<<10) + +/** Provide a hint to the kernel that the command stream and auxiliary + * state buffers already holds the correct presumed addresses and so the + * relocation process may be skipped if no buffers need to be moved in + * preparation for the execbuffer. + */ +#define I915_EXEC_NO_RELOC (1<<11) + +/** Use the reloc.handle as an index into the exec object array rather + * than as the per-file handle. + */ +#define I915_EXEC_HANDLE_LUT (1<<12) + +/** Used for switching BSD rings on the platforms with two BSD rings */ +#define I915_EXEC_BSD_SHIFT (13) +#define I915_EXEC_BSD_MASK (3 << I915_EXEC_BSD_SHIFT) +/* default ping-pong mode */ +#define I915_EXEC_BSD_DEFAULT (0 << I915_EXEC_BSD_SHIFT) +#define I915_EXEC_BSD_RING1 (1 << I915_EXEC_BSD_SHIFT) +#define I915_EXEC_BSD_RING2 (2 << I915_EXEC_BSD_SHIFT) + +/** Tell the kernel that the batchbuffer is processed by + * the resource streamer. + */ +#define I915_EXEC_RESOURCE_STREAMER (1<<15) + +/* Setting I915_EXEC_FENCE_IN implies that lower_32_bits(rsvd2) represent + * a sync_file fd to wait upon (in a nonblocking manner) prior to executing + * the batch. + * + * Returns -EINVAL if the sync_file fd cannot be found. + */ +#define I915_EXEC_FENCE_IN (1<<16) + +/* Setting I915_EXEC_FENCE_OUT causes the ioctl to return a sync_file fd + * in the upper_32_bits(rsvd2) upon success. Ownership of the fd is given + * to the caller, and it should be close() after use. (The fd is a regular + * file descriptor and will be cleaned up on process termination. It holds + * a reference to the request, but nothing else.) + * + * The sync_file fd can be combined with other sync_file and passed either + * to execbuf using I915_EXEC_FENCE_IN, to atomic KMS ioctls (so that a flip + * will only occur after this request completes), or to other devices. + * + * Using I915_EXEC_FENCE_OUT requires use of + * DRM_IOCTL_I915_GEM_EXECBUFFER2_WR ioctl so that the result is written + * back to userspace. Failure to do so will cause the out-fence to always + * be reported as zero, and the real fence fd to be leaked. + */ +#define I915_EXEC_FENCE_OUT (1<<17) + +/* + * Traditionally the execbuf ioctl has only considered the final element in + * the execobject[] to be the executable batch. Often though, the client + * will known the batch object prior to construction and being able to place + * it into the execobject[] array first can simplify the relocation tracking. + * Setting I915_EXEC_BATCH_FIRST tells execbuf to use element 0 of the + * execobject[] as the * batch instead (the default is to use the last + * element). + */ +#define I915_EXEC_BATCH_FIRST (1<<18) +#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_BATCH_FIRST<<1)) + +#define I915_EXEC_CONTEXT_ID_MASK (0xffffffff) +#define i915_execbuffer2_set_context_id(eb2, context) \ + (eb2).rsvd1 = context & I915_EXEC_CONTEXT_ID_MASK +#define i915_execbuffer2_get_context_id(eb2) \ + ((eb2).rsvd1 & I915_EXEC_CONTEXT_ID_MASK) + +struct drm_i915_gem_pin { + /** Handle of the buffer to be pinned. */ + __u32 handle; + __u32 pad; + + /** alignment required within the aperture */ + __u64 alignment; + + /** Returned GTT offset of the buffer. */ + __u64 offset; +}; + +struct drm_i915_gem_unpin { + /** Handle of the buffer to be unpinned. */ + __u32 handle; + __u32 pad; +}; + +struct drm_i915_gem_busy { + /** Handle of the buffer to check for busy */ + __u32 handle; + + /** Return busy status + * + * A return of 0 implies that the object is idle (after + * having flushed any pending activity), and a non-zero return that + * the object is still in-flight on the GPU. (The GPU has not yet + * signaled completion for all pending requests that reference the + * object.) An object is guaranteed to become idle eventually (so + * long as no new GPU commands are executed upon it). Due to the + * asynchronous nature of the hardware, an object reported + * as busy may become idle before the ioctl is completed. + * + * Furthermore, if the object is busy, which engine is busy is only + * provided as a guide. There are race conditions which prevent the + * report of which engines are busy from being always accurate. + * However, the converse is not true. If the object is idle, the + * result of the ioctl, that all engines are idle, is accurate. + * + * The returned dword is split into two fields to indicate both + * the engines on which the object is being read, and the + * engine on which it is currently being written (if any). + * + * The low word (bits 0:15) indicate if the object is being written + * to by any engine (there can only be one, as the GEM implicit + * synchronisation rules force writes to be serialised). Only the + * engine for the last write is reported. + * + * The high word (bits 16:31) are a bitmask of which engines are + * currently reading from the object. Multiple engines may be + * reading from the object simultaneously. + * + * The value of each engine is the same as specified in the + * EXECBUFFER2 ioctl, i.e. I915_EXEC_RENDER, I915_EXEC_BSD etc. + * Note I915_EXEC_DEFAULT is a symbolic value and is mapped to + * the I915_EXEC_RENDER engine for execution, and so it is never + * reported as active itself. Some hardware may have parallel + * execution engines, e.g. multiple media engines, which are + * mapped to the same identifier in the EXECBUFFER2 ioctl and + * so are not separately reported for busyness. + * + * Caveat emptor: + * Only the boolean result of this query is reliable; that is whether + * the object is idle or busy. The report of which engines are busy + * should be only used as a heuristic. + */ + __u32 busy; +}; + +/** + * I915_CACHING_NONE + * + * GPU access is not coherent with cpu caches. Default for machines without an + * LLC. + */ +#define I915_CACHING_NONE 0 +/** + * I915_CACHING_CACHED + * + * GPU access is coherent with cpu caches and furthermore the data is cached in + * last-level caches shared between cpu cores and the gpu GT. Default on + * machines with HAS_LLC. + */ +#define I915_CACHING_CACHED 1 +/** + * I915_CACHING_DISPLAY + * + * Special GPU caching mode which is coherent with the scanout engines. + * Transparently falls back to I915_CACHING_NONE on platforms where no special + * cache mode (like write-through or gfdt flushing) is available. The kernel + * automatically sets this mode when using a buffer as a scanout target. + * Userspace can manually set this mode to avoid a costly stall and clflush in + * the hotpath of drawing the first frame. + */ +#define I915_CACHING_DISPLAY 2 + +struct drm_i915_gem_caching { + /** + * Handle of the buffer to set/get the caching level of. */ + __u32 handle; + + /** + * Cacheing level to apply or return value + * + * bits0-15 are for generic caching control (i.e. the above defined + * values). bits16-31 are reserved for platform-specific variations + * (e.g. l3$ caching on gen7). */ + __u32 caching; +}; + +#define I915_TILING_NONE 0 +#define I915_TILING_X 1 +#define I915_TILING_Y 2 +#define I915_TILING_LAST I915_TILING_Y + +#define I915_BIT_6_SWIZZLE_NONE 0 +#define I915_BIT_6_SWIZZLE_9 1 +#define I915_BIT_6_SWIZZLE_9_10 2 +#define I915_BIT_6_SWIZZLE_9_11 3 +#define I915_BIT_6_SWIZZLE_9_10_11 4 +/* Not seen by userland */ +#define I915_BIT_6_SWIZZLE_UNKNOWN 5 +/* Seen by userland. */ +#define I915_BIT_6_SWIZZLE_9_17 6 +#define I915_BIT_6_SWIZZLE_9_10_17 7 + +struct drm_i915_gem_set_tiling { + /** Handle of the buffer to have its tiling state updated */ + __u32 handle; + + /** + * Tiling mode for the object (I915_TILING_NONE, I915_TILING_X, + * I915_TILING_Y). + * + * This value is to be set on request, and will be updated by the + * kernel on successful return with the actual chosen tiling layout. + * + * The tiling mode may be demoted to I915_TILING_NONE when the system + * has bit 6 swizzling that can't be managed correctly by GEM. + * + * Buffer contents become undefined when changing tiling_mode. + */ + __u32 tiling_mode; + + /** + * Stride in bytes for the object when in I915_TILING_X or + * I915_TILING_Y. + */ + __u32 stride; + + /** + * Returned address bit 6 swizzling required for CPU access through + * mmap mapping. + */ + __u32 swizzle_mode; +}; + +struct drm_i915_gem_get_tiling { + /** Handle of the buffer to get tiling state for. */ + __u32 handle; + + /** + * Current tiling mode for the object (I915_TILING_NONE, I915_TILING_X, + * I915_TILING_Y). + */ + __u32 tiling_mode; + + /** + * Returned address bit 6 swizzling required for CPU access through + * mmap mapping. + */ + __u32 swizzle_mode; + + /** + * Returned address bit 6 swizzling required for CPU access through + * mmap mapping whilst bound. + */ + __u32 phys_swizzle_mode; +}; + +struct drm_i915_gem_get_aperture { + /** Total size of the aperture used by i915_gem_execbuffer, in bytes */ + __u64 aper_size; + + /** + * Available space in the aperture used by i915_gem_execbuffer, in + * bytes + */ + __u64 aper_available_size; +}; + +struct drm_i915_get_pipe_from_crtc_id { + /** ID of CRTC being requested **/ + __u32 crtc_id; + + /** pipe of requested CRTC **/ + __u32 pipe; +}; + +#define I915_MADV_WILLNEED 0 +#define I915_MADV_DONTNEED 1 +#define __I915_MADV_PURGED 2 /* internal state */ + +struct drm_i915_gem_madvise { + /** Handle of the buffer to change the backing store advice */ + __u32 handle; + + /* Advice: either the buffer will be needed again in the near future, + * or wont be and could be discarded under memory pressure. + */ + __u32 madv; + + /** Whether the backing store still exists. */ + __u32 retained; +}; + +/* flags */ +#define I915_OVERLAY_TYPE_MASK 0xff +#define I915_OVERLAY_YUV_PLANAR 0x01 +#define I915_OVERLAY_YUV_PACKED 0x02 +#define I915_OVERLAY_RGB 0x03 + +#define I915_OVERLAY_DEPTH_MASK 0xff00 +#define I915_OVERLAY_RGB24 0x1000 +#define I915_OVERLAY_RGB16 0x2000 +#define I915_OVERLAY_RGB15 0x3000 +#define I915_OVERLAY_YUV422 0x0100 +#define I915_OVERLAY_YUV411 0x0200 +#define I915_OVERLAY_YUV420 0x0300 +#define I915_OVERLAY_YUV410 0x0400 + +#define I915_OVERLAY_SWAP_MASK 0xff0000 +#define I915_OVERLAY_NO_SWAP 0x000000 +#define I915_OVERLAY_UV_SWAP 0x010000 +#define I915_OVERLAY_Y_SWAP 0x020000 +#define I915_OVERLAY_Y_AND_UV_SWAP 0x030000 + +#define I915_OVERLAY_FLAGS_MASK 0xff000000 +#define I915_OVERLAY_ENABLE 0x01000000 + +struct drm_intel_overlay_put_image { + /* various flags and src format description */ + __u32 flags; + /* source picture description */ + __u32 bo_handle; + /* stride values and offsets are in bytes, buffer relative */ + __u16 stride_Y; /* stride for packed formats */ + __u16 stride_UV; + __u32 offset_Y; /* offset for packet formats */ + __u32 offset_U; + __u32 offset_V; + /* in pixels */ + __u16 src_width; + __u16 src_height; + /* to compensate the scaling factors for partially covered surfaces */ + __u16 src_scan_width; + __u16 src_scan_height; + /* output crtc description */ + __u32 crtc_id; + __u16 dst_x; + __u16 dst_y; + __u16 dst_width; + __u16 dst_height; +}; + +/* flags */ +#define I915_OVERLAY_UPDATE_ATTRS (1<<0) +#define I915_OVERLAY_UPDATE_GAMMA (1<<1) +#define I915_OVERLAY_DISABLE_DEST_COLORKEY (1<<2) +struct drm_intel_overlay_attrs { + __u32 flags; + __u32 color_key; + __s32 brightness; + __u32 contrast; + __u32 saturation; + __u32 gamma0; + __u32 gamma1; + __u32 gamma2; + __u32 gamma3; + __u32 gamma4; + __u32 gamma5; +}; + +/* + * Intel sprite handling + * + * Color keying works with a min/mask/max tuple. Both source and destination + * color keying is allowed. + * + * Source keying: + * Sprite pixels within the min & max values, masked against the color channels + * specified in the mask field, will be transparent. All other pixels will + * be displayed on top of the primary plane. For RGB surfaces, only the min + * and mask fields will be used; ranged compares are not allowed. + * + * Destination keying: + * Primary plane pixels that match the min value, masked against the color + * channels specified in the mask field, will be replaced by corresponding + * pixels from the sprite plane. + * + * Note that source & destination keying are exclusive; only one can be + * active on a given plane. + */ + +#define I915_SET_COLORKEY_NONE (1<<0) /* disable color key matching */ +#define I915_SET_COLORKEY_DESTINATION (1<<1) +#define I915_SET_COLORKEY_SOURCE (1<<2) +struct drm_intel_sprite_colorkey { + __u32 plane_id; + __u32 min_value; + __u32 channel_mask; + __u32 max_value; + __u32 flags; +}; + +struct drm_i915_gem_wait { + /** Handle of BO we shall wait on */ + __u32 bo_handle; + __u32 flags; + /** Number of nanoseconds to wait, Returns time remaining. */ + __s64 timeout_ns; +}; + +struct drm_i915_gem_context_create { + /* output: id of new context*/ + __u32 ctx_id; + __u32 pad; +}; + +struct drm_i915_gem_context_destroy { + __u32 ctx_id; + __u32 pad; +}; + +struct drm_i915_reg_read { + /* + * Register offset. + * For 64bit wide registers where the upper 32bits don't immediately + * follow the lower 32bits, the offset of the lower 32bits must + * be specified + */ + __u64 offset; + __u64 val; /* Return value */ +}; +/* Known registers: + * + * Render engine timestamp - 0x2358 + 64bit - gen7+ + * - Note this register returns an invalid value if using the default + * single instruction 8byte read, in order to workaround that use + * offset (0x2538 | 1) instead. + * + */ + +struct drm_i915_reset_stats { + __u32 ctx_id; + __u32 flags; + + /* All resets since boot/module reload, for all contexts */ + __u32 reset_count; + + /* Number of batches lost when active in GPU, for this context */ + __u32 batch_active; + + /* Number of batches lost pending for execution, for this context */ + __u32 batch_pending; + + __u32 pad; +}; + +struct drm_i915_gem_userptr { + __u64 user_ptr; + __u64 user_size; + __u32 flags; +#define I915_USERPTR_READ_ONLY 0x1 +#define I915_USERPTR_UNSYNCHRONIZED 0x80000000 + /** + * Returned handle for the object. + * + * Object handles are nonzero. + */ + __u32 handle; +}; + +struct drm_i915_gem_context_param { + __u32 ctx_id; + __u32 size; + __u64 param; +#define I915_CONTEXT_PARAM_BAN_PERIOD 0x1 +#define I915_CONTEXT_PARAM_NO_ZEROMAP 0x2 +#define I915_CONTEXT_PARAM_GTT_SIZE 0x3 +#define I915_CONTEXT_PARAM_NO_ERROR_CAPTURE 0x4 +#define I915_CONTEXT_PARAM_BANNABLE 0x5 + __u64 value; +}; + +enum drm_i915_oa_format { + I915_OA_FORMAT_A13 = 1, /* HSW only */ + I915_OA_FORMAT_A29, /* HSW only */ + I915_OA_FORMAT_A13_B8_C8, /* HSW only */ + I915_OA_FORMAT_B4_C8, /* HSW only */ + I915_OA_FORMAT_A45_B8_C8, /* HSW only */ + I915_OA_FORMAT_B4_C8_A16, /* HSW only */ + I915_OA_FORMAT_C4_B8, /* HSW+ */ + + /* Gen8+ */ + I915_OA_FORMAT_A12, + I915_OA_FORMAT_A12_B8_C8, + I915_OA_FORMAT_A32u40_A4u32_B8_C8, + + I915_OA_FORMAT_MAX /* non-ABI */ +}; + +enum drm_i915_perf_property_id { + /** + * Open the stream for a specific context handle (as used with + * execbuffer2). A stream opened for a specific context this way + * won't typically require root privileges. + */ + DRM_I915_PERF_PROP_CTX_HANDLE = 1, + + /** + * A value of 1 requests the inclusion of raw OA unit reports as + * part of stream samples. + */ + DRM_I915_PERF_PROP_SAMPLE_OA, + + /** + * The value specifies which set of OA unit metrics should be + * be configured, defining the contents of any OA unit reports. + */ + DRM_I915_PERF_PROP_OA_METRICS_SET, + + /** + * The value specifies the size and layout of OA unit reports. + */ + DRM_I915_PERF_PROP_OA_FORMAT, + + /** + * Specifying this property implicitly requests periodic OA unit + * sampling and (at least on Haswell) the sampling frequency is derived + * from this exponent as follows: + * + * 80ns * 2^(period_exponent + 1) + */ + DRM_I915_PERF_PROP_OA_EXPONENT, + + DRM_I915_PERF_PROP_MAX /* non-ABI */ +}; + +struct drm_i915_perf_open_param { + __u32 flags; +#define I915_PERF_FLAG_FD_CLOEXEC (1<<0) +#define I915_PERF_FLAG_FD_NONBLOCK (1<<1) +#define I915_PERF_FLAG_DISABLED (1<<2) + + /** The number of u64 (id, value) pairs */ + __u32 num_properties; + + /** + * Pointer to array of u64 (id, value) pairs configuring the stream + * to open. + */ + __u64 properties_ptr; +}; + +/** + * Enable data capture for a stream that was either opened in a disabled state + * via I915_PERF_FLAG_DISABLED or was later disabled via + * I915_PERF_IOCTL_DISABLE. + * + * It is intended to be cheaper to disable and enable a stream than it may be + * to close and re-open a stream with the same configuration. + * + * It's undefined whether any pending data for the stream will be lost. + */ +#define I915_PERF_IOCTL_ENABLE _IO('i', 0x0) + +/** + * Disable data capture for a stream. + * + * It is an error to try and read a stream that is disabled. + */ +#define I915_PERF_IOCTL_DISABLE _IO('i', 0x1) + +/** + * Common to all i915 perf records + */ +struct drm_i915_perf_record_header { + __u32 type; + __u16 pad; + __u16 size; +}; + +enum drm_i915_perf_record_type { + + /** + * Samples are the work horse record type whose contents are extensible + * and defined when opening an i915 perf stream based on the given + * properties. + * + * Boolean properties following the naming convention + * DRM_I915_PERF_SAMPLE_xyz_PROP request the inclusion of 'xyz' data in + * every sample. + * + * The order of these sample properties given by userspace has no + * affect on the ordering of data within a sample. The order is + * documented here. + * + * struct { + * struct drm_i915_perf_record_header header; + * + * { u32 oa_report[]; } && DRM_I915_PERF_PROP_SAMPLE_OA + * }; + */ + DRM_I915_PERF_RECORD_SAMPLE = 1, + + /* + * Indicates that one or more OA reports were not written by the + * hardware. This can happen for example if an MI_REPORT_PERF_COUNT + * command collides with periodic sampling - which would be more likely + * at higher sampling frequencies. + */ + DRM_I915_PERF_RECORD_OA_REPORT_LOST = 2, + + /** + * An error occurred that resulted in all pending OA reports being lost. + */ + DRM_I915_PERF_RECORD_OA_BUFFER_LOST = 3, + + DRM_I915_PERF_RECORD_MAX /* non-ABI */ +}; + +#if defined(__cplusplus) +} +#endif + +#endif /* _UAPI_I915_DRM_H_ */ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 94dfa9def355..461811e57140 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -30,9 +30,14 @@ #define BPF_FROM_LE BPF_TO_LE #define BPF_FROM_BE BPF_TO_BE +/* jmp encodings */ #define BPF_JNE 0x50 /* jump != */ +#define BPF_JLT 0xa0 /* LT is unsigned, '<' */ +#define BPF_JLE 0xb0 /* LE is unsigned, '<=' */ #define BPF_JSGT 0x60 /* SGT is signed '>', GT in x86 */ #define BPF_JSGE 0x70 /* SGE is signed '>=', GE in x86 */ +#define BPF_JSLT 0xc0 /* SLT is signed, '<' */ +#define BPF_JSLE 0xd0 /* SLE is signed, '<=' */ #define BPF_CALL 0x80 /* function call */ #define BPF_EXIT 0x90 /* function return */ @@ -82,6 +87,11 @@ enum bpf_cmd { BPF_PROG_ATTACH, BPF_PROG_DETACH, BPF_PROG_TEST_RUN, + BPF_PROG_GET_NEXT_ID, + BPF_MAP_GET_NEXT_ID, + BPF_PROG_GET_FD_BY_ID, + BPF_MAP_GET_FD_BY_ID, + BPF_OBJ_GET_INFO_BY_FD, }; enum bpf_map_type { @@ -99,6 +109,8 @@ enum bpf_map_type { BPF_MAP_TYPE_LPM_TRIE, BPF_MAP_TYPE_ARRAY_OF_MAPS, BPF_MAP_TYPE_HASH_OF_MAPS, + BPF_MAP_TYPE_DEVMAP, + BPF_MAP_TYPE_SOCKMAP, }; enum bpf_prog_type { @@ -115,17 +127,28 @@ enum bpf_prog_type { BPF_PROG_TYPE_LWT_IN, BPF_PROG_TYPE_LWT_OUT, BPF_PROG_TYPE_LWT_XMIT, + BPF_PROG_TYPE_SOCK_OPS, + BPF_PROG_TYPE_SK_SKB, }; enum bpf_attach_type { BPF_CGROUP_INET_INGRESS, BPF_CGROUP_INET_EGRESS, BPF_CGROUP_INET_SOCK_CREATE, + BPF_CGROUP_SOCK_OPS, + BPF_SK_SKB_STREAM_PARSER, + BPF_SK_SKB_STREAM_VERDICT, __MAX_BPF_ATTACH_TYPE }; #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE +enum bpf_sockmap_flags { + BPF_SOCKMAP_UNSPEC, + BPF_SOCKMAP_STRPARSER, + __MAX_BPF_SOCKMAP_FLAG +}; + /* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command * to the given target_fd cgroup the descendent cgroup will be able to * override effective bpf program that was inherited from this cgroup @@ -146,6 +169,7 @@ enum bpf_attach_type { #define BPF_NOEXIST 1 /* create new element if it didn't exist */ #define BPF_EXIST 2 /* update existing element */ +/* flags for BPF_MAP_CREATE command */ #define BPF_F_NO_PREALLOC (1U << 0) /* Instead of having one common LRU list in the * BPF_MAP_TYPE_LRU_[PERCPU_]HASH map, use a percpu LRU list @@ -154,6 +178,8 @@ enum bpf_attach_type { * across different LRU lists. */ #define BPF_F_NO_COMMON_LRU (1U << 1) +/* Specify numa node during map creation */ +#define BPF_F_NUMA_NODE (1U << 2) union bpf_attr { struct { /* anonymous struct used by BPF_MAP_CREATE command */ @@ -161,8 +187,13 @@ union bpf_attr { __u32 key_size; /* size of key in bytes */ __u32 value_size; /* size of value in bytes */ __u32 max_entries; /* max number of entries in a map */ - __u32 map_flags; /* prealloc or not */ + __u32 map_flags; /* BPF_MAP_CREATE related + * flags defined above. + */ __u32 inner_map_fd; /* fd pointing to the inner map */ + __u32 numa_node; /* numa node (effective only if + * BPF_F_NUMA_NODE is set). + */ }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -209,6 +240,21 @@ union bpf_attr { __u32 repeat; __u32 duration; } test; + + struct { /* anonymous struct used by BPF_*_GET_*_ID */ + union { + __u32 start_id; + __u32 prog_id; + __u32 map_id; + }; + __u32 next_id; + }; + + struct { /* anonymous struct used by BPF_OBJ_GET_INFO_BY_FD */ + __u32 bpf_fd; + __u32 info_len; + __aligned_u64 info; + } info; } __attribute__((aligned(8))); /* BPF helper function descriptions: @@ -313,8 +359,11 @@ union bpf_attr { * @flags: room for future extensions * Return: 0 on success or negative error * - * u64 bpf_perf_event_read(&map, index) - * Return: Number events read or error code + * u64 bpf_perf_event_read(map, flags) + * read perf event counter value + * @map: pointer to perf_event_array map + * @flags: index of event in the map or bitmask flags + * Return: value of perf event counter read or error code * * int bpf_redirect(ifindex, flags) * redirect to another netdev @@ -328,11 +377,11 @@ union bpf_attr { * @skb: pointer to skb * Return: realm if != 0 * - * int bpf_perf_event_output(ctx, map, index, data, size) + * int bpf_perf_event_output(ctx, map, flags, data, size) * output perf raw sample * @ctx: struct pt_regs* * @map: pointer to perf_event_array map - * @index: index of event in the map + * @flags: index of event in the map or bitmask flags * @data: data on stack to be output as raw data * @size: size of data * Return: 0 on success or negative error @@ -490,6 +539,44 @@ union bpf_attr { * Get the owner uid of the socket stored inside sk_buff. * @skb: pointer to skb * Return: uid of the socket owner on success or overflowuid if failed. + * + * u32 bpf_set_hash(skb, hash) + * Set full skb->hash. + * @skb: pointer to skb + * @hash: hash to set + * + * int bpf_setsockopt(bpf_socket, level, optname, optval, optlen) + * Calls setsockopt. Not all opts are available, only those with + * integer optvals plus TCP_CONGESTION. + * Supported levels: SOL_SOCKET and IPROTO_TCP + * @bpf_socket: pointer to bpf_socket + * @level: SOL_SOCKET or IPROTO_TCP + * @optname: option name + * @optval: pointer to option value + * @optlen: length of optval in byes + * Return: 0 or negative error + * + * int bpf_skb_adjust_room(skb, len_diff, mode, flags) + * Grow or shrink room in sk_buff. + * @skb: pointer to skb + * @len_diff: (signed) amount of room to grow/shrink + * @mode: operation mode (enum bpf_adj_room_mode) + * @flags: reserved for future use + * Return: 0 on success or negative error code + * + * int bpf_sk_redirect_map(map, key, flags) + * Redirect skb to a sock in map using key as a lookup key for the + * sock in map. + * @map: pointer to sockmap + * @key: key to lookup sock in map + * @flags: reserved for future use + * Return: SK_REDIRECT + * + * int bpf_sock_map_update(skops, map, key, flags) + * @skops: pointer to bpf_sock_ops + * @map: pointer to sockmap to update + * @key: key to insert/update sock in map + * @flags: same flags as map update elem */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -539,7 +626,13 @@ union bpf_attr { FN(xdp_adjust_head), \ FN(probe_read_str), \ FN(get_socket_cookie), \ - FN(get_socket_uid), + FN(get_socket_uid), \ + FN(set_hash), \ + FN(setsockopt), \ + FN(skb_adjust_room), \ + FN(redirect_map), \ + FN(sk_redirect_map), \ + FN(sock_map_update), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -589,6 +682,11 @@ enum bpf_func_id { /* BPF_FUNC_perf_event_output for sk_buff input context. */ #define BPF_F_CTXLEN_MASK (0xfffffULL << 32) +/* Mode for BPF_FUNC_skb_adjust_room helper. */ +enum bpf_adj_room_mode { + BPF_ADJ_ROOM_NET, +}; + /* user accessible mirror of in-kernel sk_buff. * new fields can only be added to the end of this structure */ @@ -611,6 +709,15 @@ struct __sk_buff { __u32 data; __u32 data_end; __u32 napi_id; + + /* accessed by BPF_PROG_TYPE_sk_skb types */ + __u32 family; + __u32 remote_ip4; /* Stored in network byte order */ + __u32 local_ip4; /* Stored in network byte order */ + __u32 remote_ip6[4]; /* Stored in network byte order */ + __u32 local_ip6[4]; /* Stored in network byte order */ + __u32 remote_port; /* Stored in network byte order */ + __u32 local_port; /* stored in host byte order */ }; struct bpf_tunnel_key { @@ -670,4 +777,83 @@ struct xdp_md { __u32 data_end; }; +enum sk_action { + SK_ABORTED = 0, + SK_DROP, + SK_REDIRECT, +}; + +#define BPF_TAG_SIZE 8 + +struct bpf_prog_info { + __u32 type; + __u32 id; + __u8 tag[BPF_TAG_SIZE]; + __u32 jited_prog_len; + __u32 xlated_prog_len; + __aligned_u64 jited_prog_insns; + __aligned_u64 xlated_prog_insns; +} __attribute__((aligned(8))); + +struct bpf_map_info { + __u32 type; + __u32 id; + __u32 key_size; + __u32 value_size; + __u32 max_entries; + __u32 map_flags; +} __attribute__((aligned(8))); + +/* User bpf_sock_ops struct to access socket values and specify request ops + * and their replies. + * Some of this fields are in network (bigendian) byte order and may need + * to be converted before use (bpf_ntohl() defined in samples/bpf/bpf_endian.h). + * New fields can only be added at the end of this structure + */ +struct bpf_sock_ops { + __u32 op; + union { + __u32 reply; + __u32 replylong[4]; + }; + __u32 family; + __u32 remote_ip4; /* Stored in network byte order */ + __u32 local_ip4; /* Stored in network byte order */ + __u32 remote_ip6[4]; /* Stored in network byte order */ + __u32 local_ip6[4]; /* Stored in network byte order */ + __u32 remote_port; /* Stored in network byte order */ + __u32 local_port; /* stored in host byte order */ +}; + +/* List of known BPF sock_ops operators. + * New entries can only be added at the end + */ +enum { + BPF_SOCK_OPS_VOID, + BPF_SOCK_OPS_TIMEOUT_INIT, /* Should return SYN-RTO value to use or + * -1 if default value should be used + */ + BPF_SOCK_OPS_RWND_INIT, /* Should return initial advertized + * window (in packets) or -1 if default + * value should be used + */ + BPF_SOCK_OPS_TCP_CONNECT_CB, /* Calls BPF program right before an + * active connection is initialized + */ + BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB, /* Calls BPF program when an + * active connection is + * established + */ + BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB, /* Calls BPF program when a + * passive connection is + * established + */ + BPF_SOCK_OPS_NEEDS_ECN, /* If connection's congestion control + * needs ECN + */ +}; + +#define TCP_BPF_IW 1001 /* Set TCP initial congestion window */ +#define TCP_BPF_SNDCWND_CLAMP 1002 /* Set sndcwnd_clamp */ + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/tools/include/uapi/linux/fcntl.h b/tools/include/uapi/linux/fcntl.h index 813afd6eee71..ec69d55bcec7 100644 --- a/tools/include/uapi/linux/fcntl.h +++ b/tools/include/uapi/linux/fcntl.h @@ -43,6 +43,27 @@ /* (1U << 31) is reserved for signed error codes */ /* + * Set/Get write life time hints. {GET,SET}_RW_HINT operate on the + * underlying inode, while {GET,SET}_FILE_RW_HINT operate only on + * the specific file. + */ +#define F_GET_RW_HINT (F_LINUX_SPECIFIC_BASE + 11) +#define F_SET_RW_HINT (F_LINUX_SPECIFIC_BASE + 12) +#define F_GET_FILE_RW_HINT (F_LINUX_SPECIFIC_BASE + 13) +#define F_SET_FILE_RW_HINT (F_LINUX_SPECIFIC_BASE + 14) + +/* + * Valid hint values for F_{GET,SET}_RW_HINT. 0 is "not set", or can be + * used to clear any hints previously set. + */ +#define RWF_WRITE_LIFE_NOT_SET 0 +#define RWH_WRITE_LIFE_NONE 1 +#define RWH_WRITE_LIFE_SHORT 2 +#define RWH_WRITE_LIFE_MEDIUM 3 +#define RWH_WRITE_LIFE_LONG 4 +#define RWH_WRITE_LIFE_EXTREME 5 + +/* * Types of directory notifications that may be requested. */ #define DN_ACCESS 0x00000001 /* File accessed */ diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h new file mode 100644 index 000000000000..6cd63c18708a --- /dev/null +++ b/tools/include/uapi/linux/kvm.h @@ -0,0 +1,1419 @@ +#ifndef __LINUX_KVM_H +#define __LINUX_KVM_H + +/* + * Userspace interface for /dev/kvm - kernel based virtual machine + * + * Note: you must update KVM_API_VERSION if you change this interface. + */ + +#include <linux/types.h> +#include <linux/compiler.h> +#include <linux/ioctl.h> +#include <asm/kvm.h> + +#define KVM_API_VERSION 12 + +/* *** Deprecated interfaces *** */ + +#define KVM_TRC_SHIFT 16 + +#define KVM_TRC_ENTRYEXIT (1 << KVM_TRC_SHIFT) +#define KVM_TRC_HANDLER (1 << (KVM_TRC_SHIFT + 1)) + +#define KVM_TRC_VMENTRY (KVM_TRC_ENTRYEXIT + 0x01) +#define KVM_TRC_VMEXIT (KVM_TRC_ENTRYEXIT + 0x02) +#define KVM_TRC_PAGE_FAULT (KVM_TRC_HANDLER + 0x01) + +#define KVM_TRC_HEAD_SIZE 12 +#define KVM_TRC_CYCLE_SIZE 8 +#define KVM_TRC_EXTRA_MAX 7 + +#define KVM_TRC_INJ_VIRQ (KVM_TRC_HANDLER + 0x02) +#define KVM_TRC_REDELIVER_EVT (KVM_TRC_HANDLER + 0x03) +#define KVM_TRC_PEND_INTR (KVM_TRC_HANDLER + 0x04) +#define KVM_TRC_IO_READ (KVM_TRC_HANDLER + 0x05) +#define KVM_TRC_IO_WRITE (KVM_TRC_HANDLER + 0x06) +#define KVM_TRC_CR_READ (KVM_TRC_HANDLER + 0x07) +#define KVM_TRC_CR_WRITE (KVM_TRC_HANDLER + 0x08) +#define KVM_TRC_DR_READ (KVM_TRC_HANDLER + 0x09) +#define KVM_TRC_DR_WRITE (KVM_TRC_HANDLER + 0x0A) +#define KVM_TRC_MSR_READ (KVM_TRC_HANDLER + 0x0B) +#define KVM_TRC_MSR_WRITE (KVM_TRC_HANDLER + 0x0C) +#define KVM_TRC_CPUID (KVM_TRC_HANDLER + 0x0D) +#define KVM_TRC_INTR (KVM_TRC_HANDLER + 0x0E) +#define KVM_TRC_NMI (KVM_TRC_HANDLER + 0x0F) +#define KVM_TRC_VMMCALL (KVM_TRC_HANDLER + 0x10) +#define KVM_TRC_HLT (KVM_TRC_HANDLER + 0x11) +#define KVM_TRC_CLTS (KVM_TRC_HANDLER + 0x12) +#define KVM_TRC_LMSW (KVM_TRC_HANDLER + 0x13) +#define KVM_TRC_APIC_ACCESS (KVM_TRC_HANDLER + 0x14) +#define KVM_TRC_TDP_FAULT (KVM_TRC_HANDLER + 0x15) +#define KVM_TRC_GTLB_WRITE (KVM_TRC_HANDLER + 0x16) +#define KVM_TRC_STLB_WRITE (KVM_TRC_HANDLER + 0x17) +#define KVM_TRC_STLB_INVAL (KVM_TRC_HANDLER + 0x18) +#define KVM_TRC_PPC_INSTR (KVM_TRC_HANDLER + 0x19) + +struct kvm_user_trace_setup { + __u32 buf_size; + __u32 buf_nr; +}; + +#define __KVM_DEPRECATED_MAIN_W_0x06 \ + _IOW(KVMIO, 0x06, struct kvm_user_trace_setup) +#define __KVM_DEPRECATED_MAIN_0x07 _IO(KVMIO, 0x07) +#define __KVM_DEPRECATED_MAIN_0x08 _IO(KVMIO, 0x08) + +#define __KVM_DEPRECATED_VM_R_0x70 _IOR(KVMIO, 0x70, struct kvm_assigned_irq) + +struct kvm_breakpoint { + __u32 enabled; + __u32 padding; + __u64 address; +}; + +struct kvm_debug_guest { + __u32 enabled; + __u32 pad; + struct kvm_breakpoint breakpoints[4]; + __u32 singlestep; +}; + +#define __KVM_DEPRECATED_VCPU_W_0x87 _IOW(KVMIO, 0x87, struct kvm_debug_guest) + +/* *** End of deprecated interfaces *** */ + + +/* for KVM_CREATE_MEMORY_REGION */ +struct kvm_memory_region { + __u32 slot; + __u32 flags; + __u64 guest_phys_addr; + __u64 memory_size; /* bytes */ +}; + +/* for KVM_SET_USER_MEMORY_REGION */ +struct kvm_userspace_memory_region { + __u32 slot; + __u32 flags; + __u64 guest_phys_addr; + __u64 memory_size; /* bytes */ + __u64 userspace_addr; /* start of the userspace allocated memory */ +}; + +/* + * The bit 0 ~ bit 15 of kvm_memory_region::flags are visible for userspace, + * other bits are reserved for kvm internal use which are defined in + * include/linux/kvm_host.h. + */ +#define KVM_MEM_LOG_DIRTY_PAGES (1UL << 0) +#define KVM_MEM_READONLY (1UL << 1) + +/* for KVM_IRQ_LINE */ +struct kvm_irq_level { + /* + * ACPI gsi notion of irq. + * For IA-64 (APIC model) IOAPIC0: irq 0-23; IOAPIC1: irq 24-47.. + * For X86 (standard AT mode) PIC0/1: irq 0-15. IOAPIC0: 0-23.. + * For ARM: See Documentation/virtual/kvm/api.txt + */ + union { + __u32 irq; + __s32 status; + }; + __u32 level; +}; + + +struct kvm_irqchip { + __u32 chip_id; + __u32 pad; + union { + char dummy[512]; /* reserving space */ +#ifdef __KVM_HAVE_PIT + struct kvm_pic_state pic; +#endif +#ifdef __KVM_HAVE_IOAPIC + struct kvm_ioapic_state ioapic; +#endif + } chip; +}; + +/* for KVM_CREATE_PIT2 */ +struct kvm_pit_config { + __u32 flags; + __u32 pad[15]; +}; + +#define KVM_PIT_SPEAKER_DUMMY 1 + +struct kvm_s390_skeys { + __u64 start_gfn; + __u64 count; + __u64 skeydata_addr; + __u32 flags; + __u32 reserved[9]; +}; + +#define KVM_S390_CMMA_PEEK (1 << 0) + +/** + * kvm_s390_cmma_log - Used for CMMA migration. + * + * Used both for input and output. + * + * @start_gfn: Guest page number to start from. + * @count: Size of the result buffer. + * @flags: Control operation mode via KVM_S390_CMMA_* flags + * @remaining: Used with KVM_S390_GET_CMMA_BITS. Indicates how many dirty + * pages are still remaining. + * @mask: Used with KVM_S390_SET_CMMA_BITS. Bitmap of bits to actually set + * in the PGSTE. + * @values: Pointer to the values buffer. + * + * Used in KVM_S390_{G,S}ET_CMMA_BITS ioctls. + */ +struct kvm_s390_cmma_log { + __u64 start_gfn; + __u32 count; + __u32 flags; + union { + __u64 remaining; + __u64 mask; + }; + __u64 values; +}; + +struct kvm_hyperv_exit { +#define KVM_EXIT_HYPERV_SYNIC 1 +#define KVM_EXIT_HYPERV_HCALL 2 + __u32 type; + union { + struct { + __u32 msr; + __u64 control; + __u64 evt_page; + __u64 msg_page; + } synic; + struct { + __u64 input; + __u64 result; + __u64 params[2]; + } hcall; + } u; +}; + +#define KVM_S390_GET_SKEYS_NONE 1 +#define KVM_S390_SKEYS_MAX 1048576 + +#define KVM_EXIT_UNKNOWN 0 +#define KVM_EXIT_EXCEPTION 1 +#define KVM_EXIT_IO 2 +#define KVM_EXIT_HYPERCALL 3 +#define KVM_EXIT_DEBUG 4 +#define KVM_EXIT_HLT 5 +#define KVM_EXIT_MMIO 6 +#define KVM_EXIT_IRQ_WINDOW_OPEN 7 +#define KVM_EXIT_SHUTDOWN 8 +#define KVM_EXIT_FAIL_ENTRY 9 +#define KVM_EXIT_INTR 10 +#define KVM_EXIT_SET_TPR 11 +#define KVM_EXIT_TPR_ACCESS 12 +#define KVM_EXIT_S390_SIEIC 13 +#define KVM_EXIT_S390_RESET 14 +#define KVM_EXIT_DCR 15 /* deprecated */ +#define KVM_EXIT_NMI 16 +#define KVM_EXIT_INTERNAL_ERROR 17 +#define KVM_EXIT_OSI 18 +#define KVM_EXIT_PAPR_HCALL 19 +#define KVM_EXIT_S390_UCONTROL 20 +#define KVM_EXIT_WATCHDOG 21 +#define KVM_EXIT_S390_TSCH 22 +#define KVM_EXIT_EPR 23 +#define KVM_EXIT_SYSTEM_EVENT 24 +#define KVM_EXIT_S390_STSI 25 +#define KVM_EXIT_IOAPIC_EOI 26 +#define KVM_EXIT_HYPERV 27 + +/* For KVM_EXIT_INTERNAL_ERROR */ +/* Emulate instruction failed. */ +#define KVM_INTERNAL_ERROR_EMULATION 1 +/* Encounter unexpected simultaneous exceptions. */ +#define KVM_INTERNAL_ERROR_SIMUL_EX 2 +/* Encounter unexpected vm-exit due to delivery event. */ +#define KVM_INTERNAL_ERROR_DELIVERY_EV 3 + +/* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */ +struct kvm_run { + /* in */ + __u8 request_interrupt_window; + __u8 immediate_exit; + __u8 padding1[6]; + + /* out */ + __u32 exit_reason; + __u8 ready_for_interrupt_injection; + __u8 if_flag; + __u16 flags; + + /* in (pre_kvm_run), out (post_kvm_run) */ + __u64 cr8; + __u64 apic_base; + +#ifdef __KVM_S390 + /* the processor status word for s390 */ + __u64 psw_mask; /* psw upper half */ + __u64 psw_addr; /* psw lower half */ +#endif + union { + /* KVM_EXIT_UNKNOWN */ + struct { + __u64 hardware_exit_reason; + } hw; + /* KVM_EXIT_FAIL_ENTRY */ + struct { + __u64 hardware_entry_failure_reason; + } fail_entry; + /* KVM_EXIT_EXCEPTION */ + struct { + __u32 exception; + __u32 error_code; + } ex; + /* KVM_EXIT_IO */ + struct { +#define KVM_EXIT_IO_IN 0 +#define KVM_EXIT_IO_OUT 1 + __u8 direction; + __u8 size; /* bytes */ + __u16 port; + __u32 count; + __u64 data_offset; /* relative to kvm_run start */ + } io; + /* KVM_EXIT_DEBUG */ + struct { + struct kvm_debug_exit_arch arch; + } debug; + /* KVM_EXIT_MMIO */ + struct { + __u64 phys_addr; + __u8 data[8]; + __u32 len; + __u8 is_write; + } mmio; + /* KVM_EXIT_HYPERCALL */ + struct { + __u64 nr; + __u64 args[6]; + __u64 ret; + __u32 longmode; + __u32 pad; + } hypercall; + /* KVM_EXIT_TPR_ACCESS */ + struct { + __u64 rip; + __u32 is_write; + __u32 pad; + } tpr_access; + /* KVM_EXIT_S390_SIEIC */ + struct { + __u8 icptcode; + __u16 ipa; + __u32 ipb; + } s390_sieic; + /* KVM_EXIT_S390_RESET */ +#define KVM_S390_RESET_POR 1 +#define KVM_S390_RESET_CLEAR 2 +#define KVM_S390_RESET_SUBSYSTEM 4 +#define KVM_S390_RESET_CPU_INIT 8 +#define KVM_S390_RESET_IPL 16 + __u64 s390_reset_flags; + /* KVM_EXIT_S390_UCONTROL */ + struct { + __u64 trans_exc_code; + __u32 pgm_code; + } s390_ucontrol; + /* KVM_EXIT_DCR (deprecated) */ + struct { + __u32 dcrn; + __u32 data; + __u8 is_write; + } dcr; + /* KVM_EXIT_INTERNAL_ERROR */ + struct { + __u32 suberror; + /* Available with KVM_CAP_INTERNAL_ERROR_DATA: */ + __u32 ndata; + __u64 data[16]; + } internal; + /* KVM_EXIT_OSI */ + struct { + __u64 gprs[32]; + } osi; + /* KVM_EXIT_PAPR_HCALL */ + struct { + __u64 nr; + __u64 ret; + __u64 args[9]; + } papr_hcall; + /* KVM_EXIT_S390_TSCH */ + struct { + __u16 subchannel_id; + __u16 subchannel_nr; + __u32 io_int_parm; + __u32 io_int_word; + __u32 ipb; + __u8 dequeued; + } s390_tsch; + /* KVM_EXIT_EPR */ + struct { + __u32 epr; + } epr; + /* KVM_EXIT_SYSTEM_EVENT */ + struct { +#define KVM_SYSTEM_EVENT_SHUTDOWN 1 +#define KVM_SYSTEM_EVENT_RESET 2 +#define KVM_SYSTEM_EVENT_CRASH 3 + __u32 type; + __u64 flags; + } system_event; + /* KVM_EXIT_S390_STSI */ + struct { + __u64 addr; + __u8 ar; + __u8 reserved; + __u8 fc; + __u8 sel1; + __u16 sel2; + } s390_stsi; + /* KVM_EXIT_IOAPIC_EOI */ + struct { + __u8 vector; + } eoi; + /* KVM_EXIT_HYPERV */ + struct kvm_hyperv_exit hyperv; + /* Fix the size of the union. */ + char padding[256]; + }; + + /* + * shared registers between kvm and userspace. + * kvm_valid_regs specifies the register classes set by the host + * kvm_dirty_regs specified the register classes dirtied by userspace + * struct kvm_sync_regs is architecture specific, as well as the + * bits for kvm_valid_regs and kvm_dirty_regs + */ + __u64 kvm_valid_regs; + __u64 kvm_dirty_regs; + union { + struct kvm_sync_regs regs; + char padding[2048]; + } s; +}; + +/* for KVM_REGISTER_COALESCED_MMIO / KVM_UNREGISTER_COALESCED_MMIO */ + +struct kvm_coalesced_mmio_zone { + __u64 addr; + __u32 size; + __u32 pad; +}; + +struct kvm_coalesced_mmio { + __u64 phys_addr; + __u32 len; + __u32 pad; + __u8 data[8]; +}; + +struct kvm_coalesced_mmio_ring { + __u32 first, last; + struct kvm_coalesced_mmio coalesced_mmio[0]; +}; + +#define KVM_COALESCED_MMIO_MAX \ + ((PAGE_SIZE - sizeof(struct kvm_coalesced_mmio_ring)) / \ + sizeof(struct kvm_coalesced_mmio)) + +/* for KVM_TRANSLATE */ +struct kvm_translation { + /* in */ + __u64 linear_address; + + /* out */ + __u64 physical_address; + __u8 valid; + __u8 writeable; + __u8 usermode; + __u8 pad[5]; +}; + +/* for KVM_S390_MEM_OP */ +struct kvm_s390_mem_op { + /* in */ + __u64 gaddr; /* the guest address */ + __u64 flags; /* flags */ + __u32 size; /* amount of bytes */ + __u32 op; /* type of operation */ + __u64 buf; /* buffer in userspace */ + __u8 ar; /* the access register number */ + __u8 reserved[31]; /* should be set to 0 */ +}; +/* types for kvm_s390_mem_op->op */ +#define KVM_S390_MEMOP_LOGICAL_READ 0 +#define KVM_S390_MEMOP_LOGICAL_WRITE 1 +/* flags for kvm_s390_mem_op->flags */ +#define KVM_S390_MEMOP_F_CHECK_ONLY (1ULL << 0) +#define KVM_S390_MEMOP_F_INJECT_EXCEPTION (1ULL << 1) + +/* for KVM_INTERRUPT */ +struct kvm_interrupt { + /* in */ + __u32 irq; +}; + +/* for KVM_GET_DIRTY_LOG */ +struct kvm_dirty_log { + __u32 slot; + __u32 padding1; + union { + void __user *dirty_bitmap; /* one bit per page */ + __u64 padding2; + }; +}; + +/* for KVM_SET_SIGNAL_MASK */ +struct kvm_signal_mask { + __u32 len; + __u8 sigset[0]; +}; + +/* for KVM_TPR_ACCESS_REPORTING */ +struct kvm_tpr_access_ctl { + __u32 enabled; + __u32 flags; + __u32 reserved[8]; +}; + +/* for KVM_SET_VAPIC_ADDR */ +struct kvm_vapic_addr { + __u64 vapic_addr; +}; + +/* for KVM_SET_MP_STATE */ + +/* not all states are valid on all architectures */ +#define KVM_MP_STATE_RUNNABLE 0 +#define KVM_MP_STATE_UNINITIALIZED 1 +#define KVM_MP_STATE_INIT_RECEIVED 2 +#define KVM_MP_STATE_HALTED 3 +#define KVM_MP_STATE_SIPI_RECEIVED 4 +#define KVM_MP_STATE_STOPPED 5 +#define KVM_MP_STATE_CHECK_STOP 6 +#define KVM_MP_STATE_OPERATING 7 +#define KVM_MP_STATE_LOAD 8 + +struct kvm_mp_state { + __u32 mp_state; +}; + +struct kvm_s390_psw { + __u64 mask; + __u64 addr; +}; + +/* valid values for type in kvm_s390_interrupt */ +#define KVM_S390_SIGP_STOP 0xfffe0000u +#define KVM_S390_PROGRAM_INT 0xfffe0001u +#define KVM_S390_SIGP_SET_PREFIX 0xfffe0002u +#define KVM_S390_RESTART 0xfffe0003u +#define KVM_S390_INT_PFAULT_INIT 0xfffe0004u +#define KVM_S390_INT_PFAULT_DONE 0xfffe0005u +#define KVM_S390_MCHK 0xfffe1000u +#define KVM_S390_INT_CLOCK_COMP 0xffff1004u +#define KVM_S390_INT_CPU_TIMER 0xffff1005u +#define KVM_S390_INT_VIRTIO 0xffff2603u +#define KVM_S390_INT_SERVICE 0xffff2401u +#define KVM_S390_INT_EMERGENCY 0xffff1201u +#define KVM_S390_INT_EXTERNAL_CALL 0xffff1202u +/* Anything below 0xfffe0000u is taken by INT_IO */ +#define KVM_S390_INT_IO(ai,cssid,ssid,schid) \ + (((schid)) | \ + ((ssid) << 16) | \ + ((cssid) << 18) | \ + ((ai) << 26)) +#define KVM_S390_INT_IO_MIN 0x00000000u +#define KVM_S390_INT_IO_MAX 0xfffdffffu +#define KVM_S390_INT_IO_AI_MASK 0x04000000u + + +struct kvm_s390_interrupt { + __u32 type; + __u32 parm; + __u64 parm64; +}; + +struct kvm_s390_io_info { + __u16 subchannel_id; + __u16 subchannel_nr; + __u32 io_int_parm; + __u32 io_int_word; +}; + +struct kvm_s390_ext_info { + __u32 ext_params; + __u32 pad; + __u64 ext_params2; +}; + +struct kvm_s390_pgm_info { + __u64 trans_exc_code; + __u64 mon_code; + __u64 per_address; + __u32 data_exc_code; + __u16 code; + __u16 mon_class_nr; + __u8 per_code; + __u8 per_atmid; + __u8 exc_access_id; + __u8 per_access_id; + __u8 op_access_id; +#define KVM_S390_PGM_FLAGS_ILC_VALID 0x01 +#define KVM_S390_PGM_FLAGS_ILC_0 0x02 +#define KVM_S390_PGM_FLAGS_ILC_1 0x04 +#define KVM_S390_PGM_FLAGS_ILC_MASK 0x06 +#define KVM_S390_PGM_FLAGS_NO_REWIND 0x08 + __u8 flags; + __u8 pad[2]; +}; + +struct kvm_s390_prefix_info { + __u32 address; +}; + +struct kvm_s390_extcall_info { + __u16 code; +}; + +struct kvm_s390_emerg_info { + __u16 code; +}; + +#define KVM_S390_STOP_FLAG_STORE_STATUS 0x01 +struct kvm_s390_stop_info { + __u32 flags; +}; + +struct kvm_s390_mchk_info { + __u64 cr14; + __u64 mcic; + __u64 failing_storage_address; + __u32 ext_damage_code; + __u32 pad; + __u8 fixed_logout[16]; +}; + +struct kvm_s390_irq { + __u64 type; + union { + struct kvm_s390_io_info io; + struct kvm_s390_ext_info ext; + struct kvm_s390_pgm_info pgm; + struct kvm_s390_emerg_info emerg; + struct kvm_s390_extcall_info extcall; + struct kvm_s390_prefix_info prefix; + struct kvm_s390_stop_info stop; + struct kvm_s390_mchk_info mchk; + char reserved[64]; + } u; +}; + +struct kvm_s390_irq_state { + __u64 buf; + __u32 flags; + __u32 len; + __u32 reserved[4]; +}; + +/* for KVM_SET_GUEST_DEBUG */ + +#define KVM_GUESTDBG_ENABLE 0x00000001 +#define KVM_GUESTDBG_SINGLESTEP 0x00000002 + +struct kvm_guest_debug { + __u32 control; + __u32 pad; + struct kvm_guest_debug_arch arch; +}; + +enum { + kvm_ioeventfd_flag_nr_datamatch, + kvm_ioeventfd_flag_nr_pio, + kvm_ioeventfd_flag_nr_deassign, + kvm_ioeventfd_flag_nr_virtio_ccw_notify, + kvm_ioeventfd_flag_nr_fast_mmio, + kvm_ioeventfd_flag_nr_max, +}; + +#define KVM_IOEVENTFD_FLAG_DATAMATCH (1 << kvm_ioeventfd_flag_nr_datamatch) +#define KVM_IOEVENTFD_FLAG_PIO (1 << kvm_ioeventfd_flag_nr_pio) +#define KVM_IOEVENTFD_FLAG_DEASSIGN (1 << kvm_ioeventfd_flag_nr_deassign) +#define KVM_IOEVENTFD_FLAG_VIRTIO_CCW_NOTIFY \ + (1 << kvm_ioeventfd_flag_nr_virtio_ccw_notify) + +#define KVM_IOEVENTFD_VALID_FLAG_MASK ((1 << kvm_ioeventfd_flag_nr_max) - 1) + +struct kvm_ioeventfd { + __u64 datamatch; + __u64 addr; /* legal pio/mmio address */ + __u32 len; /* 1, 2, 4, or 8 bytes; or 0 to ignore length */ + __s32 fd; + __u32 flags; + __u8 pad[36]; +}; + +/* for KVM_ENABLE_CAP */ +struct kvm_enable_cap { + /* in */ + __u32 cap; + __u32 flags; + __u64 args[4]; + __u8 pad[64]; +}; + +/* for KVM_PPC_GET_PVINFO */ + +#define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0) + +struct kvm_ppc_pvinfo { + /* out */ + __u32 flags; + __u32 hcall[4]; + __u8 pad[108]; +}; + +/* for KVM_PPC_GET_SMMU_INFO */ +#define KVM_PPC_PAGE_SIZES_MAX_SZ 8 + +struct kvm_ppc_one_page_size { + __u32 page_shift; /* Page shift (or 0) */ + __u32 pte_enc; /* Encoding in the HPTE (>>12) */ +}; + +struct kvm_ppc_one_seg_page_size { + __u32 page_shift; /* Base page shift of segment (or 0) */ + __u32 slb_enc; /* SLB encoding for BookS */ + struct kvm_ppc_one_page_size enc[KVM_PPC_PAGE_SIZES_MAX_SZ]; +}; + +#define KVM_PPC_PAGE_SIZES_REAL 0x00000001 +#define KVM_PPC_1T_SEGMENTS 0x00000002 + +struct kvm_ppc_smmu_info { + __u64 flags; + __u32 slb_size; + __u32 pad; + struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ]; +}; + +/* for KVM_PPC_RESIZE_HPT_{PREPARE,COMMIT} */ +struct kvm_ppc_resize_hpt { + __u64 flags; + __u32 shift; + __u32 pad; +}; + +#define KVMIO 0xAE + +/* machine type bits, to be used as argument to KVM_CREATE_VM */ +#define KVM_VM_S390_UCONTROL 1 + +/* on ppc, 0 indicate default, 1 should force HV and 2 PR */ +#define KVM_VM_PPC_HV 1 +#define KVM_VM_PPC_PR 2 + +/* on MIPS, 0 forces trap & emulate, 1 forces VZ ASE */ +#define KVM_VM_MIPS_TE 0 +#define KVM_VM_MIPS_VZ 1 + +#define KVM_S390_SIE_PAGE_OFFSET 1 + +/* + * ioctls for /dev/kvm fds: + */ +#define KVM_GET_API_VERSION _IO(KVMIO, 0x00) +#define KVM_CREATE_VM _IO(KVMIO, 0x01) /* returns a VM fd */ +#define KVM_GET_MSR_INDEX_LIST _IOWR(KVMIO, 0x02, struct kvm_msr_list) + +#define KVM_S390_ENABLE_SIE _IO(KVMIO, 0x06) +/* + * Check if a kvm extension is available. Argument is extension number, + * return is 1 (yes) or 0 (no, sorry). + */ +#define KVM_CHECK_EXTENSION _IO(KVMIO, 0x03) +/* + * Get size for mmap(vcpu_fd) + */ +#define KVM_GET_VCPU_MMAP_SIZE _IO(KVMIO, 0x04) /* in bytes */ +#define KVM_GET_SUPPORTED_CPUID _IOWR(KVMIO, 0x05, struct kvm_cpuid2) +#define KVM_TRACE_ENABLE __KVM_DEPRECATED_MAIN_W_0x06 +#define KVM_TRACE_PAUSE __KVM_DEPRECATED_MAIN_0x07 +#define KVM_TRACE_DISABLE __KVM_DEPRECATED_MAIN_0x08 +#define KVM_GET_EMULATED_CPUID _IOWR(KVMIO, 0x09, struct kvm_cpuid2) + +/* + * Extension capability list. + */ +#define KVM_CAP_IRQCHIP 0 +#define KVM_CAP_HLT 1 +#define KVM_CAP_MMU_SHADOW_CACHE_CONTROL 2 +#define KVM_CAP_USER_MEMORY 3 +#define KVM_CAP_SET_TSS_ADDR 4 +#define KVM_CAP_VAPIC 6 +#define KVM_CAP_EXT_CPUID 7 +#define KVM_CAP_CLOCKSOURCE 8 +#define KVM_CAP_NR_VCPUS 9 /* returns recommended max vcpus per vm */ +#define KVM_CAP_NR_MEMSLOTS 10 /* returns max memory slots per vm */ +#define KVM_CAP_PIT 11 +#define KVM_CAP_NOP_IO_DELAY 12 +#define KVM_CAP_PV_MMU 13 +#define KVM_CAP_MP_STATE 14 +#define KVM_CAP_COALESCED_MMIO 15 +#define KVM_CAP_SYNC_MMU 16 /* Changes to host mmap are reflected in guest */ +#define KVM_CAP_IOMMU 18 +/* Bug in KVM_SET_USER_MEMORY_REGION fixed: */ +#define KVM_CAP_DESTROY_MEMORY_REGION_WORKS 21 +#define KVM_CAP_USER_NMI 22 +#ifdef __KVM_HAVE_GUEST_DEBUG +#define KVM_CAP_SET_GUEST_DEBUG 23 +#endif +#ifdef __KVM_HAVE_PIT +#define KVM_CAP_REINJECT_CONTROL 24 +#endif +#define KVM_CAP_IRQ_ROUTING 25 +#define KVM_CAP_IRQ_INJECT_STATUS 26 +#define KVM_CAP_ASSIGN_DEV_IRQ 29 +/* Another bug in KVM_SET_USER_MEMORY_REGION fixed: */ +#define KVM_CAP_JOIN_MEMORY_REGIONS_WORKS 30 +#ifdef __KVM_HAVE_MCE +#define KVM_CAP_MCE 31 +#endif +#define KVM_CAP_IRQFD 32 +#ifdef __KVM_HAVE_PIT +#define KVM_CAP_PIT2 33 +#endif +#define KVM_CAP_SET_BOOT_CPU_ID 34 +#ifdef __KVM_HAVE_PIT_STATE2 +#define KVM_CAP_PIT_STATE2 35 +#endif +#define KVM_CAP_IOEVENTFD 36 +#define KVM_CAP_SET_IDENTITY_MAP_ADDR 37 +#ifdef __KVM_HAVE_XEN_HVM +#define KVM_CAP_XEN_HVM 38 +#endif +#define KVM_CAP_ADJUST_CLOCK 39 +#define KVM_CAP_INTERNAL_ERROR_DATA 40 +#ifdef __KVM_HAVE_VCPU_EVENTS +#define KVM_CAP_VCPU_EVENTS 41 +#endif +#define KVM_CAP_S390_PSW 42 +#define KVM_CAP_PPC_SEGSTATE 43 +#define KVM_CAP_HYPERV 44 +#define KVM_CAP_HYPERV_VAPIC 45 +#define KVM_CAP_HYPERV_SPIN 46 +#define KVM_CAP_PCI_SEGMENT 47 +#define KVM_CAP_PPC_PAIRED_SINGLES 48 +#define KVM_CAP_INTR_SHADOW 49 +#ifdef __KVM_HAVE_DEBUGREGS +#define KVM_CAP_DEBUGREGS 50 +#endif +#define KVM_CAP_X86_ROBUST_SINGLESTEP 51 +#define KVM_CAP_PPC_OSI 52 +#define KVM_CAP_PPC_UNSET_IRQ 53 +#define KVM_CAP_ENABLE_CAP 54 +#ifdef __KVM_HAVE_XSAVE +#define KVM_CAP_XSAVE 55 +#endif +#ifdef __KVM_HAVE_XCRS +#define KVM_CAP_XCRS 56 +#endif +#define KVM_CAP_PPC_GET_PVINFO 57 +#define KVM_CAP_PPC_IRQ_LEVEL 58 +#define KVM_CAP_ASYNC_PF 59 +#define KVM_CAP_TSC_CONTROL 60 +#define KVM_CAP_GET_TSC_KHZ 61 +#define KVM_CAP_PPC_BOOKE_SREGS 62 +#define KVM_CAP_SPAPR_TCE 63 +#define KVM_CAP_PPC_SMT 64 +#define KVM_CAP_PPC_RMA 65 +#define KVM_CAP_MAX_VCPUS 66 /* returns max vcpus per vm */ +#define KVM_CAP_PPC_HIOR 67 +#define KVM_CAP_PPC_PAPR 68 +#define KVM_CAP_SW_TLB 69 +#define KVM_CAP_ONE_REG 70 +#define KVM_CAP_S390_GMAP 71 +#define KVM_CAP_TSC_DEADLINE_TIMER 72 +#define KVM_CAP_S390_UCONTROL 73 +#define KVM_CAP_SYNC_REGS 74 +#define KVM_CAP_PCI_2_3 75 +#define KVM_CAP_KVMCLOCK_CTRL 76 +#define KVM_CAP_SIGNAL_MSI 77 +#define KVM_CAP_PPC_GET_SMMU_INFO 78 +#define KVM_CAP_S390_COW 79 +#define KVM_CAP_PPC_ALLOC_HTAB 80 +#define KVM_CAP_READONLY_MEM 81 +#define KVM_CAP_IRQFD_RESAMPLE 82 +#define KVM_CAP_PPC_BOOKE_WATCHDOG 83 +#define KVM_CAP_PPC_HTAB_FD 84 +#define KVM_CAP_S390_CSS_SUPPORT 85 +#define KVM_CAP_PPC_EPR 86 +#define KVM_CAP_ARM_PSCI 87 +#define KVM_CAP_ARM_SET_DEVICE_ADDR 88 +#define KVM_CAP_DEVICE_CTRL 89 +#define KVM_CAP_IRQ_MPIC 90 +#define KVM_CAP_PPC_RTAS 91 +#define KVM_CAP_IRQ_XICS 92 +#define KVM_CAP_ARM_EL1_32BIT 93 +#define KVM_CAP_SPAPR_MULTITCE 94 +#define KVM_CAP_EXT_EMUL_CPUID 95 +#define KVM_CAP_HYPERV_TIME 96 +#define KVM_CAP_IOAPIC_POLARITY_IGNORED 97 +#define KVM_CAP_ENABLE_CAP_VM 98 +#define KVM_CAP_S390_IRQCHIP 99 +#define KVM_CAP_IOEVENTFD_NO_LENGTH 100 +#define KVM_CAP_VM_ATTRIBUTES 101 +#define KVM_CAP_ARM_PSCI_0_2 102 +#define KVM_CAP_PPC_FIXUP_HCALL 103 +#define KVM_CAP_PPC_ENABLE_HCALL 104 +#define KVM_CAP_CHECK_EXTENSION_VM 105 +#define KVM_CAP_S390_USER_SIGP 106 +#define KVM_CAP_S390_VECTOR_REGISTERS 107 +#define KVM_CAP_S390_MEM_OP 108 +#define KVM_CAP_S390_USER_STSI 109 +#define KVM_CAP_S390_SKEYS 110 +#define KVM_CAP_MIPS_FPU 111 +#define KVM_CAP_MIPS_MSA 112 +#define KVM_CAP_S390_INJECT_IRQ 113 +#define KVM_CAP_S390_IRQ_STATE 114 +#define KVM_CAP_PPC_HWRNG 115 +#define KVM_CAP_DISABLE_QUIRKS 116 +#define KVM_CAP_X86_SMM 117 +#define KVM_CAP_MULTI_ADDRESS_SPACE 118 +#define KVM_CAP_GUEST_DEBUG_HW_BPS 119 +#define KVM_CAP_GUEST_DEBUG_HW_WPS 120 +#define KVM_CAP_SPLIT_IRQCHIP 121 +#define KVM_CAP_IOEVENTFD_ANY_LENGTH 122 +#define KVM_CAP_HYPERV_SYNIC 123 +#define KVM_CAP_S390_RI 124 +#define KVM_CAP_SPAPR_TCE_64 125 +#define KVM_CAP_ARM_PMU_V3 126 +#define KVM_CAP_VCPU_ATTRIBUTES 127 +#define KVM_CAP_MAX_VCPU_ID 128 +#define KVM_CAP_X2APIC_API 129 +#define KVM_CAP_S390_USER_INSTR0 130 +#define KVM_CAP_MSI_DEVID 131 +#define KVM_CAP_PPC_HTM 132 +#define KVM_CAP_SPAPR_RESIZE_HPT 133 +#define KVM_CAP_PPC_MMU_RADIX 134 +#define KVM_CAP_PPC_MMU_HASH_V3 135 +#define KVM_CAP_IMMEDIATE_EXIT 136 +#define KVM_CAP_MIPS_VZ 137 +#define KVM_CAP_MIPS_TE 138 +#define KVM_CAP_MIPS_64BIT 139 +#define KVM_CAP_S390_GS 140 +#define KVM_CAP_S390_AIS 141 +#define KVM_CAP_SPAPR_TCE_VFIO 142 +#define KVM_CAP_X86_GUEST_MWAIT 143 +#define KVM_CAP_ARM_USER_IRQ 144 +#define KVM_CAP_S390_CMMA_MIGRATION 145 +#define KVM_CAP_PPC_FWNMI 146 +#define KVM_CAP_PPC_SMT_POSSIBLE 147 +#define KVM_CAP_HYPERV_SYNIC2 148 +#define KVM_CAP_HYPERV_VP_INDEX 149 + +#ifdef KVM_CAP_IRQ_ROUTING + +struct kvm_irq_routing_irqchip { + __u32 irqchip; + __u32 pin; +}; + +struct kvm_irq_routing_msi { + __u32 address_lo; + __u32 address_hi; + __u32 data; + union { + __u32 pad; + __u32 devid; + }; +}; + +struct kvm_irq_routing_s390_adapter { + __u64 ind_addr; + __u64 summary_addr; + __u64 ind_offset; + __u32 summary_offset; + __u32 adapter_id; +}; + +struct kvm_irq_routing_hv_sint { + __u32 vcpu; + __u32 sint; +}; + +/* gsi routing entry types */ +#define KVM_IRQ_ROUTING_IRQCHIP 1 +#define KVM_IRQ_ROUTING_MSI 2 +#define KVM_IRQ_ROUTING_S390_ADAPTER 3 +#define KVM_IRQ_ROUTING_HV_SINT 4 + +struct kvm_irq_routing_entry { + __u32 gsi; + __u32 type; + __u32 flags; + __u32 pad; + union { + struct kvm_irq_routing_irqchip irqchip; + struct kvm_irq_routing_msi msi; + struct kvm_irq_routing_s390_adapter adapter; + struct kvm_irq_routing_hv_sint hv_sint; + __u32 pad[8]; + } u; +}; + +struct kvm_irq_routing { + __u32 nr; + __u32 flags; + struct kvm_irq_routing_entry entries[0]; +}; + +#endif + +#ifdef KVM_CAP_MCE +/* x86 MCE */ +struct kvm_x86_mce { + __u64 status; + __u64 addr; + __u64 misc; + __u64 mcg_status; + __u8 bank; + __u8 pad1[7]; + __u64 pad2[3]; +}; +#endif + +#ifdef KVM_CAP_XEN_HVM +struct kvm_xen_hvm_config { + __u32 flags; + __u32 msr; + __u64 blob_addr_32; + __u64 blob_addr_64; + __u8 blob_size_32; + __u8 blob_size_64; + __u8 pad2[30]; +}; +#endif + +#define KVM_IRQFD_FLAG_DEASSIGN (1 << 0) +/* + * Available with KVM_CAP_IRQFD_RESAMPLE + * + * KVM_IRQFD_FLAG_RESAMPLE indicates resamplefd is valid and specifies + * the irqfd to operate in resampling mode for level triggered interrupt + * emulation. See Documentation/virtual/kvm/api.txt. + */ +#define KVM_IRQFD_FLAG_RESAMPLE (1 << 1) + +struct kvm_irqfd { + __u32 fd; + __u32 gsi; + __u32 flags; + __u32 resamplefd; + __u8 pad[16]; +}; + +/* For KVM_CAP_ADJUST_CLOCK */ + +/* Do not use 1, KVM_CHECK_EXTENSION returned it before we had flags. */ +#define KVM_CLOCK_TSC_STABLE 2 + +struct kvm_clock_data { + __u64 clock; + __u32 flags; + __u32 pad[9]; +}; + +/* For KVM_CAP_SW_TLB */ + +#define KVM_MMU_FSL_BOOKE_NOHV 0 +#define KVM_MMU_FSL_BOOKE_HV 1 + +struct kvm_config_tlb { + __u64 params; + __u64 array; + __u32 mmu_type; + __u32 array_len; +}; + +struct kvm_dirty_tlb { + __u64 bitmap; + __u32 num_dirty; +}; + +/* Available with KVM_CAP_ONE_REG */ + +#define KVM_REG_ARCH_MASK 0xff00000000000000ULL +#define KVM_REG_GENERIC 0x0000000000000000ULL + +/* + * Architecture specific registers are to be defined in arch headers and + * ORed with the arch identifier. + */ +#define KVM_REG_PPC 0x1000000000000000ULL +#define KVM_REG_X86 0x2000000000000000ULL +#define KVM_REG_IA64 0x3000000000000000ULL +#define KVM_REG_ARM 0x4000000000000000ULL +#define KVM_REG_S390 0x5000000000000000ULL +#define KVM_REG_ARM64 0x6000000000000000ULL +#define KVM_REG_MIPS 0x7000000000000000ULL + +#define KVM_REG_SIZE_SHIFT 52 +#define KVM_REG_SIZE_MASK 0x00f0000000000000ULL +#define KVM_REG_SIZE_U8 0x0000000000000000ULL +#define KVM_REG_SIZE_U16 0x0010000000000000ULL +#define KVM_REG_SIZE_U32 0x0020000000000000ULL +#define KVM_REG_SIZE_U64 0x0030000000000000ULL +#define KVM_REG_SIZE_U128 0x0040000000000000ULL +#define KVM_REG_SIZE_U256 0x0050000000000000ULL +#define KVM_REG_SIZE_U512 0x0060000000000000ULL +#define KVM_REG_SIZE_U1024 0x0070000000000000ULL + +struct kvm_reg_list { + __u64 n; /* number of regs */ + __u64 reg[0]; +}; + +struct kvm_one_reg { + __u64 id; + __u64 addr; +}; + +#define KVM_MSI_VALID_DEVID (1U << 0) +struct kvm_msi { + __u32 address_lo; + __u32 address_hi; + __u32 data; + __u32 flags; + __u32 devid; + __u8 pad[12]; +}; + +struct kvm_arm_device_addr { + __u64 id; + __u64 addr; +}; + +/* + * Device control API, available with KVM_CAP_DEVICE_CTRL + */ +#define KVM_CREATE_DEVICE_TEST 1 + +struct kvm_create_device { + __u32 type; /* in: KVM_DEV_TYPE_xxx */ + __u32 fd; /* out: device handle */ + __u32 flags; /* in: KVM_CREATE_DEVICE_xxx */ +}; + +struct kvm_device_attr { + __u32 flags; /* no flags currently defined */ + __u32 group; /* device-defined */ + __u64 attr; /* group-defined */ + __u64 addr; /* userspace address of attr data */ +}; + +#define KVM_DEV_VFIO_GROUP 1 +#define KVM_DEV_VFIO_GROUP_ADD 1 +#define KVM_DEV_VFIO_GROUP_DEL 2 +#define KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE 3 + +enum kvm_device_type { + KVM_DEV_TYPE_FSL_MPIC_20 = 1, +#define KVM_DEV_TYPE_FSL_MPIC_20 KVM_DEV_TYPE_FSL_MPIC_20 + KVM_DEV_TYPE_FSL_MPIC_42, +#define KVM_DEV_TYPE_FSL_MPIC_42 KVM_DEV_TYPE_FSL_MPIC_42 + KVM_DEV_TYPE_XICS, +#define KVM_DEV_TYPE_XICS KVM_DEV_TYPE_XICS + KVM_DEV_TYPE_VFIO, +#define KVM_DEV_TYPE_VFIO KVM_DEV_TYPE_VFIO + KVM_DEV_TYPE_ARM_VGIC_V2, +#define KVM_DEV_TYPE_ARM_VGIC_V2 KVM_DEV_TYPE_ARM_VGIC_V2 + KVM_DEV_TYPE_FLIC, +#define KVM_DEV_TYPE_FLIC KVM_DEV_TYPE_FLIC + KVM_DEV_TYPE_ARM_VGIC_V3, +#define KVM_DEV_TYPE_ARM_VGIC_V3 KVM_DEV_TYPE_ARM_VGIC_V3 + KVM_DEV_TYPE_ARM_VGIC_ITS, +#define KVM_DEV_TYPE_ARM_VGIC_ITS KVM_DEV_TYPE_ARM_VGIC_ITS + KVM_DEV_TYPE_MAX, +}; + +struct kvm_vfio_spapr_tce { + __s32 groupfd; + __s32 tablefd; +}; + +/* + * ioctls for VM fds + */ +#define KVM_SET_MEMORY_REGION _IOW(KVMIO, 0x40, struct kvm_memory_region) +/* + * KVM_CREATE_VCPU receives as a parameter the vcpu slot, and returns + * a vcpu fd. + */ +#define KVM_CREATE_VCPU _IO(KVMIO, 0x41) +#define KVM_GET_DIRTY_LOG _IOW(KVMIO, 0x42, struct kvm_dirty_log) +/* KVM_SET_MEMORY_ALIAS is obsolete: */ +#define KVM_SET_MEMORY_ALIAS _IOW(KVMIO, 0x43, struct kvm_memory_alias) +#define KVM_SET_NR_MMU_PAGES _IO(KVMIO, 0x44) +#define KVM_GET_NR_MMU_PAGES _IO(KVMIO, 0x45) +#define KVM_SET_USER_MEMORY_REGION _IOW(KVMIO, 0x46, \ + struct kvm_userspace_memory_region) +#define KVM_SET_TSS_ADDR _IO(KVMIO, 0x47) +#define KVM_SET_IDENTITY_MAP_ADDR _IOW(KVMIO, 0x48, __u64) + +/* enable ucontrol for s390 */ +struct kvm_s390_ucas_mapping { + __u64 user_addr; + __u64 vcpu_addr; + __u64 length; +}; +#define KVM_S390_UCAS_MAP _IOW(KVMIO, 0x50, struct kvm_s390_ucas_mapping) +#define KVM_S390_UCAS_UNMAP _IOW(KVMIO, 0x51, struct kvm_s390_ucas_mapping) +#define KVM_S390_VCPU_FAULT _IOW(KVMIO, 0x52, unsigned long) + +/* Device model IOC */ +#define KVM_CREATE_IRQCHIP _IO(KVMIO, 0x60) +#define KVM_IRQ_LINE _IOW(KVMIO, 0x61, struct kvm_irq_level) +#define KVM_GET_IRQCHIP _IOWR(KVMIO, 0x62, struct kvm_irqchip) +#define KVM_SET_IRQCHIP _IOR(KVMIO, 0x63, struct kvm_irqchip) +#define KVM_CREATE_PIT _IO(KVMIO, 0x64) +#define KVM_GET_PIT _IOWR(KVMIO, 0x65, struct kvm_pit_state) +#define KVM_SET_PIT _IOR(KVMIO, 0x66, struct kvm_pit_state) +#define KVM_IRQ_LINE_STATUS _IOWR(KVMIO, 0x67, struct kvm_irq_level) +#define KVM_REGISTER_COALESCED_MMIO \ + _IOW(KVMIO, 0x67, struct kvm_coalesced_mmio_zone) +#define KVM_UNREGISTER_COALESCED_MMIO \ + _IOW(KVMIO, 0x68, struct kvm_coalesced_mmio_zone) +#define KVM_ASSIGN_PCI_DEVICE _IOR(KVMIO, 0x69, \ + struct kvm_assigned_pci_dev) +#define KVM_SET_GSI_ROUTING _IOW(KVMIO, 0x6a, struct kvm_irq_routing) +/* deprecated, replaced by KVM_ASSIGN_DEV_IRQ */ +#define KVM_ASSIGN_IRQ __KVM_DEPRECATED_VM_R_0x70 +#define KVM_ASSIGN_DEV_IRQ _IOW(KVMIO, 0x70, struct kvm_assigned_irq) +#define KVM_REINJECT_CONTROL _IO(KVMIO, 0x71) +#define KVM_DEASSIGN_PCI_DEVICE _IOW(KVMIO, 0x72, \ + struct kvm_assigned_pci_dev) +#define KVM_ASSIGN_SET_MSIX_NR _IOW(KVMIO, 0x73, \ + struct kvm_assigned_msix_nr) +#define KVM_ASSIGN_SET_MSIX_ENTRY _IOW(KVMIO, 0x74, \ + struct kvm_assigned_msix_entry) +#define KVM_DEASSIGN_DEV_IRQ _IOW(KVMIO, 0x75, struct kvm_assigned_irq) +#define KVM_IRQFD _IOW(KVMIO, 0x76, struct kvm_irqfd) +#define KVM_CREATE_PIT2 _IOW(KVMIO, 0x77, struct kvm_pit_config) +#define KVM_SET_BOOT_CPU_ID _IO(KVMIO, 0x78) +#define KVM_IOEVENTFD _IOW(KVMIO, 0x79, struct kvm_ioeventfd) +#define KVM_XEN_HVM_CONFIG _IOW(KVMIO, 0x7a, struct kvm_xen_hvm_config) +#define KVM_SET_CLOCK _IOW(KVMIO, 0x7b, struct kvm_clock_data) +#define KVM_GET_CLOCK _IOR(KVMIO, 0x7c, struct kvm_clock_data) +/* Available with KVM_CAP_PIT_STATE2 */ +#define KVM_GET_PIT2 _IOR(KVMIO, 0x9f, struct kvm_pit_state2) +#define KVM_SET_PIT2 _IOW(KVMIO, 0xa0, struct kvm_pit_state2) +/* Available with KVM_CAP_PPC_GET_PVINFO */ +#define KVM_PPC_GET_PVINFO _IOW(KVMIO, 0xa1, struct kvm_ppc_pvinfo) +/* Available with KVM_CAP_TSC_CONTROL */ +#define KVM_SET_TSC_KHZ _IO(KVMIO, 0xa2) +#define KVM_GET_TSC_KHZ _IO(KVMIO, 0xa3) +/* Available with KVM_CAP_PCI_2_3 */ +#define KVM_ASSIGN_SET_INTX_MASK _IOW(KVMIO, 0xa4, \ + struct kvm_assigned_pci_dev) +/* Available with KVM_CAP_SIGNAL_MSI */ +#define KVM_SIGNAL_MSI _IOW(KVMIO, 0xa5, struct kvm_msi) +/* Available with KVM_CAP_PPC_GET_SMMU_INFO */ +#define KVM_PPC_GET_SMMU_INFO _IOR(KVMIO, 0xa6, struct kvm_ppc_smmu_info) +/* Available with KVM_CAP_PPC_ALLOC_HTAB */ +#define KVM_PPC_ALLOCATE_HTAB _IOWR(KVMIO, 0xa7, __u32) +#define KVM_CREATE_SPAPR_TCE _IOW(KVMIO, 0xa8, struct kvm_create_spapr_tce) +#define KVM_CREATE_SPAPR_TCE_64 _IOW(KVMIO, 0xa8, \ + struct kvm_create_spapr_tce_64) +/* Available with KVM_CAP_RMA */ +#define KVM_ALLOCATE_RMA _IOR(KVMIO, 0xa9, struct kvm_allocate_rma) +/* Available with KVM_CAP_PPC_HTAB_FD */ +#define KVM_PPC_GET_HTAB_FD _IOW(KVMIO, 0xaa, struct kvm_get_htab_fd) +/* Available with KVM_CAP_ARM_SET_DEVICE_ADDR */ +#define KVM_ARM_SET_DEVICE_ADDR _IOW(KVMIO, 0xab, struct kvm_arm_device_addr) +/* Available with KVM_CAP_PPC_RTAS */ +#define KVM_PPC_RTAS_DEFINE_TOKEN _IOW(KVMIO, 0xac, struct kvm_rtas_token_args) +/* Available with KVM_CAP_SPAPR_RESIZE_HPT */ +#define KVM_PPC_RESIZE_HPT_PREPARE _IOR(KVMIO, 0xad, struct kvm_ppc_resize_hpt) +#define KVM_PPC_RESIZE_HPT_COMMIT _IOR(KVMIO, 0xae, struct kvm_ppc_resize_hpt) +/* Available with KVM_CAP_PPC_RADIX_MMU or KVM_CAP_PPC_HASH_MMU_V3 */ +#define KVM_PPC_CONFIGURE_V3_MMU _IOW(KVMIO, 0xaf, struct kvm_ppc_mmuv3_cfg) +/* Available with KVM_CAP_PPC_RADIX_MMU */ +#define KVM_PPC_GET_RMMU_INFO _IOW(KVMIO, 0xb0, struct kvm_ppc_rmmu_info) + +/* ioctl for vm fd */ +#define KVM_CREATE_DEVICE _IOWR(KVMIO, 0xe0, struct kvm_create_device) + +/* ioctls for fds returned by KVM_CREATE_DEVICE */ +#define KVM_SET_DEVICE_ATTR _IOW(KVMIO, 0xe1, struct kvm_device_attr) +#define KVM_GET_DEVICE_ATTR _IOW(KVMIO, 0xe2, struct kvm_device_attr) +#define KVM_HAS_DEVICE_ATTR _IOW(KVMIO, 0xe3, struct kvm_device_attr) + +/* + * ioctls for vcpu fds + */ +#define KVM_RUN _IO(KVMIO, 0x80) +#define KVM_GET_REGS _IOR(KVMIO, 0x81, struct kvm_regs) +#define KVM_SET_REGS _IOW(KVMIO, 0x82, struct kvm_regs) +#define KVM_GET_SREGS _IOR(KVMIO, 0x83, struct kvm_sregs) +#define KVM_SET_SREGS _IOW(KVMIO, 0x84, struct kvm_sregs) +#define KVM_TRANSLATE _IOWR(KVMIO, 0x85, struct kvm_translation) +#define KVM_INTERRUPT _IOW(KVMIO, 0x86, struct kvm_interrupt) +/* KVM_DEBUG_GUEST is no longer supported, use KVM_SET_GUEST_DEBUG instead */ +#define KVM_DEBUG_GUEST __KVM_DEPRECATED_VCPU_W_0x87 +#define KVM_GET_MSRS _IOWR(KVMIO, 0x88, struct kvm_msrs) +#define KVM_SET_MSRS _IOW(KVMIO, 0x89, struct kvm_msrs) +#define KVM_SET_CPUID _IOW(KVMIO, 0x8a, struct kvm_cpuid) +#define KVM_SET_SIGNAL_MASK _IOW(KVMIO, 0x8b, struct kvm_signal_mask) +#define KVM_GET_FPU _IOR(KVMIO, 0x8c, struct kvm_fpu) +#define KVM_SET_FPU _IOW(KVMIO, 0x8d, struct kvm_fpu) +#define KVM_GET_LAPIC _IOR(KVMIO, 0x8e, struct kvm_lapic_state) +#define KVM_SET_LAPIC _IOW(KVMIO, 0x8f, struct kvm_lapic_state) +#define KVM_SET_CPUID2 _IOW(KVMIO, 0x90, struct kvm_cpuid2) +#define KVM_GET_CPUID2 _IOWR(KVMIO, 0x91, struct kvm_cpuid2) +/* Available with KVM_CAP_VAPIC */ +#define KVM_TPR_ACCESS_REPORTING _IOWR(KVMIO, 0x92, struct kvm_tpr_access_ctl) +/* Available with KVM_CAP_VAPIC */ +#define KVM_SET_VAPIC_ADDR _IOW(KVMIO, 0x93, struct kvm_vapic_addr) +/* valid for virtual machine (for floating interrupt)_and_ vcpu */ +#define KVM_S390_INTERRUPT _IOW(KVMIO, 0x94, struct kvm_s390_interrupt) +/* store status for s390 */ +#define KVM_S390_STORE_STATUS_NOADDR (-1ul) +#define KVM_S390_STORE_STATUS_PREFIXED (-2ul) +#define KVM_S390_STORE_STATUS _IOW(KVMIO, 0x95, unsigned long) +/* initial ipl psw for s390 */ +#define KVM_S390_SET_INITIAL_PSW _IOW(KVMIO, 0x96, struct kvm_s390_psw) +/* initial reset for s390 */ +#define KVM_S390_INITIAL_RESET _IO(KVMIO, 0x97) +#define KVM_GET_MP_STATE _IOR(KVMIO, 0x98, struct kvm_mp_state) +#define KVM_SET_MP_STATE _IOW(KVMIO, 0x99, struct kvm_mp_state) +/* Available with KVM_CAP_USER_NMI */ +#define KVM_NMI _IO(KVMIO, 0x9a) +/* Available with KVM_CAP_SET_GUEST_DEBUG */ +#define KVM_SET_GUEST_DEBUG _IOW(KVMIO, 0x9b, struct kvm_guest_debug) +/* MCE for x86 */ +#define KVM_X86_SETUP_MCE _IOW(KVMIO, 0x9c, __u64) +#define KVM_X86_GET_MCE_CAP_SUPPORTED _IOR(KVMIO, 0x9d, __u64) +#define KVM_X86_SET_MCE _IOW(KVMIO, 0x9e, struct kvm_x86_mce) +/* Available with KVM_CAP_VCPU_EVENTS */ +#define KVM_GET_VCPU_EVENTS _IOR(KVMIO, 0x9f, struct kvm_vcpu_events) +#define KVM_SET_VCPU_EVENTS _IOW(KVMIO, 0xa0, struct kvm_vcpu_events) +/* Available with KVM_CAP_DEBUGREGS */ +#define KVM_GET_DEBUGREGS _IOR(KVMIO, 0xa1, struct kvm_debugregs) +#define KVM_SET_DEBUGREGS _IOW(KVMIO, 0xa2, struct kvm_debugregs) +/* + * vcpu version available with KVM_ENABLE_CAP + * vm version available with KVM_CAP_ENABLE_CAP_VM + */ +#define KVM_ENABLE_CAP _IOW(KVMIO, 0xa3, struct kvm_enable_cap) +/* Available with KVM_CAP_XSAVE */ +#define KVM_GET_XSAVE _IOR(KVMIO, 0xa4, struct kvm_xsave) +#define KVM_SET_XSAVE _IOW(KVMIO, 0xa5, struct kvm_xsave) +/* Available with KVM_CAP_XCRS */ +#define KVM_GET_XCRS _IOR(KVMIO, 0xa6, struct kvm_xcrs) +#define KVM_SET_XCRS _IOW(KVMIO, 0xa7, struct kvm_xcrs) +/* Available with KVM_CAP_SW_TLB */ +#define KVM_DIRTY_TLB _IOW(KVMIO, 0xaa, struct kvm_dirty_tlb) +/* Available with KVM_CAP_ONE_REG */ +#define KVM_GET_ONE_REG _IOW(KVMIO, 0xab, struct kvm_one_reg) +#define KVM_SET_ONE_REG _IOW(KVMIO, 0xac, struct kvm_one_reg) +/* VM is being stopped by host */ +#define KVM_KVMCLOCK_CTRL _IO(KVMIO, 0xad) +#define KVM_ARM_VCPU_INIT _IOW(KVMIO, 0xae, struct kvm_vcpu_init) +#define KVM_ARM_PREFERRED_TARGET _IOR(KVMIO, 0xaf, struct kvm_vcpu_init) +#define KVM_GET_REG_LIST _IOWR(KVMIO, 0xb0, struct kvm_reg_list) +/* Available with KVM_CAP_S390_MEM_OP */ +#define KVM_S390_MEM_OP _IOW(KVMIO, 0xb1, struct kvm_s390_mem_op) +/* Available with KVM_CAP_S390_SKEYS */ +#define KVM_S390_GET_SKEYS _IOW(KVMIO, 0xb2, struct kvm_s390_skeys) +#define KVM_S390_SET_SKEYS _IOW(KVMIO, 0xb3, struct kvm_s390_skeys) +/* Available with KVM_CAP_S390_INJECT_IRQ */ +#define KVM_S390_IRQ _IOW(KVMIO, 0xb4, struct kvm_s390_irq) +/* Available with KVM_CAP_S390_IRQ_STATE */ +#define KVM_S390_SET_IRQ_STATE _IOW(KVMIO, 0xb5, struct kvm_s390_irq_state) +#define KVM_S390_GET_IRQ_STATE _IOW(KVMIO, 0xb6, struct kvm_s390_irq_state) +/* Available with KVM_CAP_X86_SMM */ +#define KVM_SMI _IO(KVMIO, 0xb7) +/* Available with KVM_CAP_S390_CMMA_MIGRATION */ +#define KVM_S390_GET_CMMA_BITS _IOWR(KVMIO, 0xb8, struct kvm_s390_cmma_log) +#define KVM_S390_SET_CMMA_BITS _IOW(KVMIO, 0xb9, struct kvm_s390_cmma_log) + +#define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) +#define KVM_DEV_ASSIGN_PCI_2_3 (1 << 1) +#define KVM_DEV_ASSIGN_MASK_INTX (1 << 2) + +struct kvm_assigned_pci_dev { + __u32 assigned_dev_id; + __u32 busnr; + __u32 devfn; + __u32 flags; + __u32 segnr; + union { + __u32 reserved[11]; + }; +}; + +#define KVM_DEV_IRQ_HOST_INTX (1 << 0) +#define KVM_DEV_IRQ_HOST_MSI (1 << 1) +#define KVM_DEV_IRQ_HOST_MSIX (1 << 2) + +#define KVM_DEV_IRQ_GUEST_INTX (1 << 8) +#define KVM_DEV_IRQ_GUEST_MSI (1 << 9) +#define KVM_DEV_IRQ_GUEST_MSIX (1 << 10) + +#define KVM_DEV_IRQ_HOST_MASK 0x00ff +#define KVM_DEV_IRQ_GUEST_MASK 0xff00 + +struct kvm_assigned_irq { + __u32 assigned_dev_id; + __u32 host_irq; /* ignored (legacy field) */ + __u32 guest_irq; + __u32 flags; + union { + __u32 reserved[12]; + }; +}; + +struct kvm_assigned_msix_nr { + __u32 assigned_dev_id; + __u16 entry_nr; + __u16 padding; +}; + +#define KVM_MAX_MSIX_PER_DEV 256 +struct kvm_assigned_msix_entry { + __u32 assigned_dev_id; + __u32 gsi; + __u16 entry; /* The index of entry in the MSI-X table */ + __u16 padding[3]; +}; + +#define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0) +#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1) + +/* Available with KVM_CAP_ARM_USER_IRQ */ + +/* Bits for run->s.regs.device_irq_level */ +#define KVM_ARM_DEV_EL1_VTIMER (1 << 0) +#define KVM_ARM_DEV_EL1_PTIMER (1 << 1) +#define KVM_ARM_DEV_PMU (1 << 2) + +#endif /* __LINUX_KVM_H */ diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index b1c0b187acfe..140ae638cfd6 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -139,8 +139,9 @@ enum perf_event_sample_format { PERF_SAMPLE_IDENTIFIER = 1U << 16, PERF_SAMPLE_TRANSACTION = 1U << 17, PERF_SAMPLE_REGS_INTR = 1U << 18, + PERF_SAMPLE_PHYS_ADDR = 1U << 19, - PERF_SAMPLE_MAX = 1U << 19, /* non-ABI */ + PERF_SAMPLE_MAX = 1U << 20, /* non-ABI */ }; /* @@ -174,6 +175,8 @@ enum perf_branch_sample_type_shift { PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT = 14, /* no flags */ PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT = 15, /* no cycles */ + PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT = 16, /* save branch type */ + PERF_SAMPLE_BRANCH_MAX_SHIFT /* non-ABI */ }; @@ -198,9 +201,30 @@ enum perf_branch_sample_type { PERF_SAMPLE_BRANCH_NO_FLAGS = 1U << PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT, PERF_SAMPLE_BRANCH_NO_CYCLES = 1U << PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT, + PERF_SAMPLE_BRANCH_TYPE_SAVE = + 1U << PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT, + PERF_SAMPLE_BRANCH_MAX = 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT, }; +/* + * Common flow change classification + */ +enum { + PERF_BR_UNKNOWN = 0, /* unknown */ + PERF_BR_COND = 1, /* conditional */ + PERF_BR_UNCOND = 2, /* unconditional */ + PERF_BR_IND = 3, /* indirect */ + PERF_BR_CALL = 4, /* function call */ + PERF_BR_IND_CALL = 5, /* indirect function call */ + PERF_BR_RET = 6, /* function return */ + PERF_BR_SYSCALL = 7, /* syscall */ + PERF_BR_SYSRET = 8, /* syscall return */ + PERF_BR_COND_CALL = 9, /* conditional function call */ + PERF_BR_COND_RET = 10, /* conditional function return */ + PERF_BR_MAX, +}; + #define PERF_SAMPLE_BRANCH_PLM_ALL \ (PERF_SAMPLE_BRANCH_USER|\ PERF_SAMPLE_BRANCH_KERNEL|\ @@ -791,6 +815,7 @@ enum perf_event_type { * { u64 transaction; } && PERF_SAMPLE_TRANSACTION * { u64 abi; # enum perf_sample_regs_abi * u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_INTR + * { u64 phys_addr;} && PERF_SAMPLE_PHYS_ADDR * }; */ PERF_RECORD_SAMPLE = 9, @@ -931,14 +956,20 @@ union perf_mem_data_src { mem_snoop:5, /* snoop mode */ mem_lock:2, /* lock instr */ mem_dtlb:7, /* tlb access */ - mem_rsvd:31; + mem_lvl_num:4, /* memory hierarchy level number */ + mem_remote:1, /* remote */ + mem_snoopx:2, /* snoop mode, ext */ + mem_rsvd:24; }; }; #elif defined(__BIG_ENDIAN_BITFIELD) union perf_mem_data_src { __u64 val; struct { - __u64 mem_rsvd:31, + __u64 mem_rsvd:24, + mem_snoopx:2, /* snoop mode, ext */ + mem_remote:1, /* remote */ + mem_lvl_num:4, /* memory hierarchy level number */ mem_dtlb:7, /* tlb access */ mem_lock:2, /* lock instr */ mem_snoop:5, /* snoop mode */ @@ -975,6 +1006,22 @@ union perf_mem_data_src { #define PERF_MEM_LVL_UNC 0x2000 /* Uncached memory */ #define PERF_MEM_LVL_SHIFT 5 +#define PERF_MEM_REMOTE_REMOTE 0x01 /* Remote */ +#define PERF_MEM_REMOTE_SHIFT 37 + +#define PERF_MEM_LVLNUM_L1 0x01 /* L1 */ +#define PERF_MEM_LVLNUM_L2 0x02 /* L2 */ +#define PERF_MEM_LVLNUM_L3 0x03 /* L3 */ +#define PERF_MEM_LVLNUM_L4 0x04 /* L4 */ +/* 5-0xa available */ +#define PERF_MEM_LVLNUM_ANY_CACHE 0x0b /* Any cache */ +#define PERF_MEM_LVLNUM_LFB 0x0c /* LFB */ +#define PERF_MEM_LVLNUM_RAM 0x0d /* RAM */ +#define PERF_MEM_LVLNUM_PMEM 0x0e /* PMEM */ +#define PERF_MEM_LVLNUM_NA 0x0f /* N/A */ + +#define PERF_MEM_LVLNUM_SHIFT 33 + /* snoop mode */ #define PERF_MEM_SNOOP_NA 0x01 /* not available */ #define PERF_MEM_SNOOP_NONE 0x02 /* no snoop */ @@ -983,6 +1030,10 @@ union perf_mem_data_src { #define PERF_MEM_SNOOP_HITM 0x10 /* snoop hit modified */ #define PERF_MEM_SNOOP_SHIFT 19 +#define PERF_MEM_SNOOPX_FWD 0x01 /* forward */ +/* 1 free */ +#define PERF_MEM_SNOOPX_SHIFT 37 + /* locked instruction */ #define PERF_MEM_LOCK_NA 0x01 /* not available */ #define PERF_MEM_LOCK_LOCKED 0x02 /* locked transaction */ @@ -1015,6 +1066,7 @@ union perf_mem_data_src { * in_tx: running in a hardware transaction * abort: aborting a hardware transaction * cycles: cycles from last branch (or 0 if not supported) + * type: branch type */ struct perf_branch_entry { __u64 from; @@ -1024,7 +1076,8 @@ struct perf_branch_entry { in_tx:1, /* in transaction */ abort:1, /* transaction abort */ cycles:16, /* cycle count to last branch */ - reserved:44; + type:4, /* branch type */ + reserved:40; }; #endif /* _UAPI_LINUX_PERF_EVENT_H */ diff --git a/tools/include/uapi/linux/sched.h b/tools/include/uapi/linux/sched.h new file mode 100644 index 000000000000..e2a6c7b3510b --- /dev/null +++ b/tools/include/uapi/linux/sched.h @@ -0,0 +1,52 @@ +#ifndef _UAPI_LINUX_SCHED_H +#define _UAPI_LINUX_SCHED_H + +/* + * cloning flags: + */ +#define CSIGNAL 0x000000ff /* signal mask to be sent at exit */ +#define CLONE_VM 0x00000100 /* set if VM shared between processes */ +#define CLONE_FS 0x00000200 /* set if fs info shared between processes */ +#define CLONE_FILES 0x00000400 /* set if open files shared between processes */ +#define CLONE_SIGHAND 0x00000800 /* set if signal handlers and blocked signals shared */ +#define CLONE_PTRACE 0x00002000 /* set if we want to let tracing continue on the child too */ +#define CLONE_VFORK 0x00004000 /* set if the parent wants the child to wake it up on mm_release */ +#define CLONE_PARENT 0x00008000 /* set if we want to have the same parent as the cloner */ +#define CLONE_THREAD 0x00010000 /* Same thread group? */ +#define CLONE_NEWNS 0x00020000 /* New mount namespace group */ +#define CLONE_SYSVSEM 0x00040000 /* share system V SEM_UNDO semantics */ +#define CLONE_SETTLS 0x00080000 /* create a new TLS for the child */ +#define CLONE_PARENT_SETTID 0x00100000 /* set the TID in the parent */ +#define CLONE_CHILD_CLEARTID 0x00200000 /* clear the TID in the child */ +#define CLONE_DETACHED 0x00400000 /* Unused, ignored */ +#define CLONE_UNTRACED 0x00800000 /* set if the tracing process can't force CLONE_PTRACE on this clone */ +#define CLONE_CHILD_SETTID 0x01000000 /* set the TID in the child */ +#define CLONE_NEWCGROUP 0x02000000 /* New cgroup namespace */ +#define CLONE_NEWUTS 0x04000000 /* New utsname namespace */ +#define CLONE_NEWIPC 0x08000000 /* New ipc namespace */ +#define CLONE_NEWUSER 0x10000000 /* New user namespace */ +#define CLONE_NEWPID 0x20000000 /* New pid namespace */ +#define CLONE_NEWNET 0x40000000 /* New network namespace */ +#define CLONE_IO 0x80000000 /* Clone io context */ + +/* + * Scheduling policies + */ +#define SCHED_NORMAL 0 +#define SCHED_FIFO 1 +#define SCHED_RR 2 +#define SCHED_BATCH 3 +/* SCHED_ISO: reserved but not implemented yet */ +#define SCHED_IDLE 5 +#define SCHED_DEADLINE 6 + +/* Can be ORed in to make sure the process is reverted back to SCHED_NORMAL on fork */ +#define SCHED_RESET_ON_FORK 0x40000000 + +/* + * For the sched_{set,get}attr() calls + */ +#define SCHED_FLAG_RESET_ON_FORK 0x01 +#define SCHED_FLAG_RECLAIM 0x02 + +#endif /* _UAPI_LINUX_SCHED_H */ diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h new file mode 100644 index 000000000000..60180c0b5dc6 --- /dev/null +++ b/tools/include/uapi/linux/vhost.h @@ -0,0 +1,209 @@ +#ifndef _LINUX_VHOST_H +#define _LINUX_VHOST_H +/* Userspace interface for in-kernel virtio accelerators. */ + +/* vhost is used to reduce the number of system calls involved in virtio. + * + * Existing virtio net code is used in the guest without modification. + * + * This header includes interface used by userspace hypervisor for + * device configuration. + */ + +#include <linux/types.h> +#include <linux/compiler.h> +#include <linux/ioctl.h> +#include <linux/virtio_config.h> +#include <linux/virtio_ring.h> + +struct vhost_vring_state { + unsigned int index; + unsigned int num; +}; + +struct vhost_vring_file { + unsigned int index; + int fd; /* Pass -1 to unbind from file. */ + +}; + +struct vhost_vring_addr { + unsigned int index; + /* Option flags. */ + unsigned int flags; + /* Flag values: */ + /* Whether log address is valid. If set enables logging. */ +#define VHOST_VRING_F_LOG 0 + + /* Start of array of descriptors (virtually contiguous) */ + __u64 desc_user_addr; + /* Used structure address. Must be 32 bit aligned */ + __u64 used_user_addr; + /* Available structure address. Must be 16 bit aligned */ + __u64 avail_user_addr; + /* Logging support. */ + /* Log writes to used structure, at offset calculated from specified + * address. Address must be 32 bit aligned. */ + __u64 log_guest_addr; +}; + +/* no alignment requirement */ +struct vhost_iotlb_msg { + __u64 iova; + __u64 size; + __u64 uaddr; +#define VHOST_ACCESS_RO 0x1 +#define VHOST_ACCESS_WO 0x2 +#define VHOST_ACCESS_RW 0x3 + __u8 perm; +#define VHOST_IOTLB_MISS 1 +#define VHOST_IOTLB_UPDATE 2 +#define VHOST_IOTLB_INVALIDATE 3 +#define VHOST_IOTLB_ACCESS_FAIL 4 + __u8 type; +}; + +#define VHOST_IOTLB_MSG 0x1 + +struct vhost_msg { + int type; + union { + struct vhost_iotlb_msg iotlb; + __u8 padding[64]; + }; +}; + +struct vhost_memory_region { + __u64 guest_phys_addr; + __u64 memory_size; /* bytes */ + __u64 userspace_addr; + __u64 flags_padding; /* No flags are currently specified. */ +}; + +/* All region addresses and sizes must be 4K aligned. */ +#define VHOST_PAGE_SIZE 0x1000 + +struct vhost_memory { + __u32 nregions; + __u32 padding; + struct vhost_memory_region regions[0]; +}; + +/* ioctls */ + +#define VHOST_VIRTIO 0xAF + +/* Features bitmask for forward compatibility. Transport bits are used for + * vhost specific features. */ +#define VHOST_GET_FEATURES _IOR(VHOST_VIRTIO, 0x00, __u64) +#define VHOST_SET_FEATURES _IOW(VHOST_VIRTIO, 0x00, __u64) + +/* Set current process as the (exclusive) owner of this file descriptor. This + * must be called before any other vhost command. Further calls to + * VHOST_OWNER_SET fail until VHOST_OWNER_RESET is called. */ +#define VHOST_SET_OWNER _IO(VHOST_VIRTIO, 0x01) +/* Give up ownership, and reset the device to default values. + * Allows subsequent call to VHOST_OWNER_SET to succeed. */ +#define VHOST_RESET_OWNER _IO(VHOST_VIRTIO, 0x02) + +/* Set up/modify memory layout */ +#define VHOST_SET_MEM_TABLE _IOW(VHOST_VIRTIO, 0x03, struct vhost_memory) + +/* Write logging setup. */ +/* Memory writes can optionally be logged by setting bit at an offset + * (calculated from the physical address) from specified log base. + * The bit is set using an atomic 32 bit operation. */ +/* Set base address for logging. */ +#define VHOST_SET_LOG_BASE _IOW(VHOST_VIRTIO, 0x04, __u64) +/* Specify an eventfd file descriptor to signal on log write. */ +#define VHOST_SET_LOG_FD _IOW(VHOST_VIRTIO, 0x07, int) + +/* Ring setup. */ +/* Set number of descriptors in ring. This parameter can not + * be modified while ring is running (bound to a device). */ +#define VHOST_SET_VRING_NUM _IOW(VHOST_VIRTIO, 0x10, struct vhost_vring_state) +/* Set addresses for the ring. */ +#define VHOST_SET_VRING_ADDR _IOW(VHOST_VIRTIO, 0x11, struct vhost_vring_addr) +/* Base value where queue looks for available descriptors */ +#define VHOST_SET_VRING_BASE _IOW(VHOST_VIRTIO, 0x12, struct vhost_vring_state) +/* Get accessor: reads index, writes value in num */ +#define VHOST_GET_VRING_BASE _IOWR(VHOST_VIRTIO, 0x12, struct vhost_vring_state) + +/* Set the vring byte order in num. Valid values are VHOST_VRING_LITTLE_ENDIAN + * or VHOST_VRING_BIG_ENDIAN (other values return -EINVAL). + * The byte order cannot be changed while the device is active: trying to do so + * returns -EBUSY. + * This is a legacy only API that is simply ignored when VIRTIO_F_VERSION_1 is + * set. + * Not all kernel configurations support this ioctl, but all configurations that + * support SET also support GET. + */ +#define VHOST_VRING_LITTLE_ENDIAN 0 +#define VHOST_VRING_BIG_ENDIAN 1 +#define VHOST_SET_VRING_ENDIAN _IOW(VHOST_VIRTIO, 0x13, struct vhost_vring_state) +#define VHOST_GET_VRING_ENDIAN _IOW(VHOST_VIRTIO, 0x14, struct vhost_vring_state) + +/* The following ioctls use eventfd file descriptors to signal and poll + * for events. */ + +/* Set eventfd to poll for added buffers */ +#define VHOST_SET_VRING_KICK _IOW(VHOST_VIRTIO, 0x20, struct vhost_vring_file) +/* Set eventfd to signal when buffers have beed used */ +#define VHOST_SET_VRING_CALL _IOW(VHOST_VIRTIO, 0x21, struct vhost_vring_file) +/* Set eventfd to signal an error */ +#define VHOST_SET_VRING_ERR _IOW(VHOST_VIRTIO, 0x22, struct vhost_vring_file) +/* Set busy loop timeout (in us) */ +#define VHOST_SET_VRING_BUSYLOOP_TIMEOUT _IOW(VHOST_VIRTIO, 0x23, \ + struct vhost_vring_state) +/* Get busy loop timeout (in us) */ +#define VHOST_GET_VRING_BUSYLOOP_TIMEOUT _IOW(VHOST_VIRTIO, 0x24, \ + struct vhost_vring_state) + +/* VHOST_NET specific defines */ + +/* Attach virtio net ring to a raw socket, or tap device. + * The socket must be already bound to an ethernet device, this device will be + * used for transmit. Pass fd -1 to unbind from the socket and the transmit + * device. This can be used to stop the ring (e.g. for migration). */ +#define VHOST_NET_SET_BACKEND _IOW(VHOST_VIRTIO, 0x30, struct vhost_vring_file) + +/* Feature bits */ +/* Log all write descriptors. Can be changed while device is active. */ +#define VHOST_F_LOG_ALL 26 +/* vhost-net should add virtio_net_hdr for RX, and strip for TX packets. */ +#define VHOST_NET_F_VIRTIO_NET_HDR 27 + +/* VHOST_SCSI specific definitions */ + +/* + * Used by QEMU userspace to ensure a consistent vhost-scsi ABI. + * + * ABI Rev 0: July 2012 version starting point for v3.6-rc merge candidate + + * RFC-v2 vhost-scsi userspace. Add GET_ABI_VERSION ioctl usage + * ABI Rev 1: January 2013. Ignore vhost_tpgt filed in struct vhost_scsi_target. + * All the targets under vhost_wwpn can be seen and used by guset. + */ + +#define VHOST_SCSI_ABI_VERSION 1 + +struct vhost_scsi_target { + int abi_version; + char vhost_wwpn[224]; /* TRANSPORT_IQN_LEN */ + unsigned short vhost_tpgt; + unsigned short reserved; +}; + +#define VHOST_SCSI_SET_ENDPOINT _IOW(VHOST_VIRTIO, 0x40, struct vhost_scsi_target) +#define VHOST_SCSI_CLEAR_ENDPOINT _IOW(VHOST_VIRTIO, 0x41, struct vhost_scsi_target) +/* Changing this breaks userspace. */ +#define VHOST_SCSI_GET_ABI_VERSION _IOW(VHOST_VIRTIO, 0x42, int) +/* Set and get the events missed flag */ +#define VHOST_SCSI_SET_EVENTS_MISSED _IOW(VHOST_VIRTIO, 0x43, __u32) +#define VHOST_SCSI_GET_EVENTS_MISSED _IOW(VHOST_VIRTIO, 0x44, __u32) + +/* VHOST_VSOCK specific defines */ + +#define VHOST_VSOCK_SET_GUEST_CID _IOW(VHOST_VIRTIO, 0x60, __u64) +#define VHOST_VSOCK_SET_RUNNING _IOW(VHOST_VIRTIO, 0x61, int) + +#endif diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h new file mode 100644 index 000000000000..87bf30b182df --- /dev/null +++ b/tools/include/uapi/sound/asound.h @@ -0,0 +1,1026 @@ +/* + * Advanced Linux Sound Architecture - ALSA - Driver + * Copyright (c) 1994-2003 by Jaroslav Kysela <perex@perex.cz>, + * Abramo Bagnara <abramo@alsa-project.org> + * + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + */ + +#ifndef _UAPI__SOUND_ASOUND_H +#define _UAPI__SOUND_ASOUND_H + +#if defined(__KERNEL__) || defined(__linux__) +#include <linux/types.h> +#else +#include <sys/ioctl.h> +#endif + +#ifndef __KERNEL__ +#include <stdlib.h> +#endif + +/* + * protocol version + */ + +#define SNDRV_PROTOCOL_VERSION(major, minor, subminor) (((major)<<16)|((minor)<<8)|(subminor)) +#define SNDRV_PROTOCOL_MAJOR(version) (((version)>>16)&0xffff) +#define SNDRV_PROTOCOL_MINOR(version) (((version)>>8)&0xff) +#define SNDRV_PROTOCOL_MICRO(version) ((version)&0xff) +#define SNDRV_PROTOCOL_INCOMPATIBLE(kversion, uversion) \ + (SNDRV_PROTOCOL_MAJOR(kversion) != SNDRV_PROTOCOL_MAJOR(uversion) || \ + (SNDRV_PROTOCOL_MAJOR(kversion) == SNDRV_PROTOCOL_MAJOR(uversion) && \ + SNDRV_PROTOCOL_MINOR(kversion) != SNDRV_PROTOCOL_MINOR(uversion))) + +/**************************************************************************** + * * + * Digital audio interface * + * * + ****************************************************************************/ + +struct snd_aes_iec958 { + unsigned char status[24]; /* AES/IEC958 channel status bits */ + unsigned char subcode[147]; /* AES/IEC958 subcode bits */ + unsigned char pad; /* nothing */ + unsigned char dig_subframe[4]; /* AES/IEC958 subframe bits */ +}; + +/**************************************************************************** + * * + * CEA-861 Audio InfoFrame. Used in HDMI and DisplayPort * + * * + ****************************************************************************/ + +struct snd_cea_861_aud_if { + unsigned char db1_ct_cc; /* coding type and channel count */ + unsigned char db2_sf_ss; /* sample frequency and size */ + unsigned char db3; /* not used, all zeros */ + unsigned char db4_ca; /* channel allocation code */ + unsigned char db5_dminh_lsv; /* downmix inhibit & level-shit values */ +}; + +/**************************************************************************** + * * + * Section for driver hardware dependent interface - /dev/snd/hw? * + * * + ****************************************************************************/ + +#define SNDRV_HWDEP_VERSION SNDRV_PROTOCOL_VERSION(1, 0, 1) + +enum { + SNDRV_HWDEP_IFACE_OPL2 = 0, + SNDRV_HWDEP_IFACE_OPL3, + SNDRV_HWDEP_IFACE_OPL4, + SNDRV_HWDEP_IFACE_SB16CSP, /* Creative Signal Processor */ + SNDRV_HWDEP_IFACE_EMU10K1, /* FX8010 processor in EMU10K1 chip */ + SNDRV_HWDEP_IFACE_YSS225, /* Yamaha FX processor */ + SNDRV_HWDEP_IFACE_ICS2115, /* Wavetable synth */ + SNDRV_HWDEP_IFACE_SSCAPE, /* Ensoniq SoundScape ISA card (MC68EC000) */ + SNDRV_HWDEP_IFACE_VX, /* Digigram VX cards */ + SNDRV_HWDEP_IFACE_MIXART, /* Digigram miXart cards */ + SNDRV_HWDEP_IFACE_USX2Y, /* Tascam US122, US224 & US428 usb */ + SNDRV_HWDEP_IFACE_EMUX_WAVETABLE, /* EmuX wavetable */ + SNDRV_HWDEP_IFACE_BLUETOOTH, /* Bluetooth audio */ + SNDRV_HWDEP_IFACE_USX2Y_PCM, /* Tascam US122, US224 & US428 rawusb pcm */ + SNDRV_HWDEP_IFACE_PCXHR, /* Digigram PCXHR */ + SNDRV_HWDEP_IFACE_SB_RC, /* SB Extigy/Audigy2NX remote control */ + SNDRV_HWDEP_IFACE_HDA, /* HD-audio */ + SNDRV_HWDEP_IFACE_USB_STREAM, /* direct access to usb stream */ + SNDRV_HWDEP_IFACE_FW_DICE, /* TC DICE FireWire device */ + SNDRV_HWDEP_IFACE_FW_FIREWORKS, /* Echo Audio Fireworks based device */ + SNDRV_HWDEP_IFACE_FW_BEBOB, /* BridgeCo BeBoB based device */ + SNDRV_HWDEP_IFACE_FW_OXFW, /* Oxford OXFW970/971 based device */ + SNDRV_HWDEP_IFACE_FW_DIGI00X, /* Digidesign Digi 002/003 family */ + SNDRV_HWDEP_IFACE_FW_TASCAM, /* TASCAM FireWire series */ + SNDRV_HWDEP_IFACE_LINE6, /* Line6 USB processors */ + SNDRV_HWDEP_IFACE_FW_MOTU, /* MOTU FireWire series */ + SNDRV_HWDEP_IFACE_FW_FIREFACE, /* RME Fireface series */ + + /* Don't forget to change the following: */ + SNDRV_HWDEP_IFACE_LAST = SNDRV_HWDEP_IFACE_FW_FIREFACE +}; + +struct snd_hwdep_info { + unsigned int device; /* WR: device number */ + int card; /* R: card number */ + unsigned char id[64]; /* ID (user selectable) */ + unsigned char name[80]; /* hwdep name */ + int iface; /* hwdep interface */ + unsigned char reserved[64]; /* reserved for future */ +}; + +/* generic DSP loader */ +struct snd_hwdep_dsp_status { + unsigned int version; /* R: driver-specific version */ + unsigned char id[32]; /* R: driver-specific ID string */ + unsigned int num_dsps; /* R: number of DSP images to transfer */ + unsigned int dsp_loaded; /* R: bit flags indicating the loaded DSPs */ + unsigned int chip_ready; /* R: 1 = initialization finished */ + unsigned char reserved[16]; /* reserved for future use */ +}; + +struct snd_hwdep_dsp_image { + unsigned int index; /* W: DSP index */ + unsigned char name[64]; /* W: ID (e.g. file name) */ + unsigned char __user *image; /* W: binary image */ + size_t length; /* W: size of image in bytes */ + unsigned long driver_data; /* W: driver-specific data */ +}; + +#define SNDRV_HWDEP_IOCTL_PVERSION _IOR ('H', 0x00, int) +#define SNDRV_HWDEP_IOCTL_INFO _IOR ('H', 0x01, struct snd_hwdep_info) +#define SNDRV_HWDEP_IOCTL_DSP_STATUS _IOR('H', 0x02, struct snd_hwdep_dsp_status) +#define SNDRV_HWDEP_IOCTL_DSP_LOAD _IOW('H', 0x03, struct snd_hwdep_dsp_image) + +/***************************************************************************** + * * + * Digital Audio (PCM) interface - /dev/snd/pcm?? * + * * + *****************************************************************************/ + +#define SNDRV_PCM_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 14) + +typedef unsigned long snd_pcm_uframes_t; +typedef signed long snd_pcm_sframes_t; + +enum { + SNDRV_PCM_CLASS_GENERIC = 0, /* standard mono or stereo device */ + SNDRV_PCM_CLASS_MULTI, /* multichannel device */ + SNDRV_PCM_CLASS_MODEM, /* software modem class */ + SNDRV_PCM_CLASS_DIGITIZER, /* digitizer class */ + /* Don't forget to change the following: */ + SNDRV_PCM_CLASS_LAST = SNDRV_PCM_CLASS_DIGITIZER, +}; + +enum { + SNDRV_PCM_SUBCLASS_GENERIC_MIX = 0, /* mono or stereo subdevices are mixed together */ + SNDRV_PCM_SUBCLASS_MULTI_MIX, /* multichannel subdevices are mixed together */ + /* Don't forget to change the following: */ + SNDRV_PCM_SUBCLASS_LAST = SNDRV_PCM_SUBCLASS_MULTI_MIX, +}; + +enum { + SNDRV_PCM_STREAM_PLAYBACK = 0, + SNDRV_PCM_STREAM_CAPTURE, + SNDRV_PCM_STREAM_LAST = SNDRV_PCM_STREAM_CAPTURE, +}; + +typedef int __bitwise snd_pcm_access_t; +#define SNDRV_PCM_ACCESS_MMAP_INTERLEAVED ((__force snd_pcm_access_t) 0) /* interleaved mmap */ +#define SNDRV_PCM_ACCESS_MMAP_NONINTERLEAVED ((__force snd_pcm_access_t) 1) /* noninterleaved mmap */ +#define SNDRV_PCM_ACCESS_MMAP_COMPLEX ((__force snd_pcm_access_t) 2) /* complex mmap */ +#define SNDRV_PCM_ACCESS_RW_INTERLEAVED ((__force snd_pcm_access_t) 3) /* readi/writei */ +#define SNDRV_PCM_ACCESS_RW_NONINTERLEAVED ((__force snd_pcm_access_t) 4) /* readn/writen */ +#define SNDRV_PCM_ACCESS_LAST SNDRV_PCM_ACCESS_RW_NONINTERLEAVED + +typedef int __bitwise snd_pcm_format_t; +#define SNDRV_PCM_FORMAT_S8 ((__force snd_pcm_format_t) 0) +#define SNDRV_PCM_FORMAT_U8 ((__force snd_pcm_format_t) 1) +#define SNDRV_PCM_FORMAT_S16_LE ((__force snd_pcm_format_t) 2) +#define SNDRV_PCM_FORMAT_S16_BE ((__force snd_pcm_format_t) 3) +#define SNDRV_PCM_FORMAT_U16_LE ((__force snd_pcm_format_t) 4) +#define SNDRV_PCM_FORMAT_U16_BE ((__force snd_pcm_format_t) 5) +#define SNDRV_PCM_FORMAT_S24_LE ((__force snd_pcm_format_t) 6) /* low three bytes */ +#define SNDRV_PCM_FORMAT_S24_BE ((__force snd_pcm_format_t) 7) /* low three bytes */ +#define SNDRV_PCM_FORMAT_U24_LE ((__force snd_pcm_format_t) 8) /* low three bytes */ +#define SNDRV_PCM_FORMAT_U24_BE ((__force snd_pcm_format_t) 9) /* low three bytes */ +#define SNDRV_PCM_FORMAT_S32_LE ((__force snd_pcm_format_t) 10) +#define SNDRV_PCM_FORMAT_S32_BE ((__force snd_pcm_format_t) 11) +#define SNDRV_PCM_FORMAT_U32_LE ((__force snd_pcm_format_t) 12) +#define SNDRV_PCM_FORMAT_U32_BE ((__force snd_pcm_format_t) 13) +#define SNDRV_PCM_FORMAT_FLOAT_LE ((__force snd_pcm_format_t) 14) /* 4-byte float, IEEE-754 32-bit, range -1.0 to 1.0 */ +#define SNDRV_PCM_FORMAT_FLOAT_BE ((__force snd_pcm_format_t) 15) /* 4-byte float, IEEE-754 32-bit, range -1.0 to 1.0 */ +#define SNDRV_PCM_FORMAT_FLOAT64_LE ((__force snd_pcm_format_t) 16) /* 8-byte float, IEEE-754 64-bit, range -1.0 to 1.0 */ +#define SNDRV_PCM_FORMAT_FLOAT64_BE ((__force snd_pcm_format_t) 17) /* 8-byte float, IEEE-754 64-bit, range -1.0 to 1.0 */ +#define SNDRV_PCM_FORMAT_IEC958_SUBFRAME_LE ((__force snd_pcm_format_t) 18) /* IEC-958 subframe, Little Endian */ +#define SNDRV_PCM_FORMAT_IEC958_SUBFRAME_BE ((__force snd_pcm_format_t) 19) /* IEC-958 subframe, Big Endian */ +#define SNDRV_PCM_FORMAT_MU_LAW ((__force snd_pcm_format_t) 20) +#define SNDRV_PCM_FORMAT_A_LAW ((__force snd_pcm_format_t) 21) +#define SNDRV_PCM_FORMAT_IMA_ADPCM ((__force snd_pcm_format_t) 22) +#define SNDRV_PCM_FORMAT_MPEG ((__force snd_pcm_format_t) 23) +#define SNDRV_PCM_FORMAT_GSM ((__force snd_pcm_format_t) 24) +#define SNDRV_PCM_FORMAT_SPECIAL ((__force snd_pcm_format_t) 31) +#define SNDRV_PCM_FORMAT_S24_3LE ((__force snd_pcm_format_t) 32) /* in three bytes */ +#define SNDRV_PCM_FORMAT_S24_3BE ((__force snd_pcm_format_t) 33) /* in three bytes */ +#define SNDRV_PCM_FORMAT_U24_3LE ((__force snd_pcm_format_t) 34) /* in three bytes */ +#define SNDRV_PCM_FORMAT_U24_3BE ((__force snd_pcm_format_t) 35) /* in three bytes */ +#define SNDRV_PCM_FORMAT_S20_3LE ((__force snd_pcm_format_t) 36) /* in three bytes */ +#define SNDRV_PCM_FORMAT_S20_3BE ((__force snd_pcm_format_t) 37) /* in three bytes */ +#define SNDRV_PCM_FORMAT_U20_3LE ((__force snd_pcm_format_t) 38) /* in three bytes */ +#define SNDRV_PCM_FORMAT_U20_3BE ((__force snd_pcm_format_t) 39) /* in three bytes */ +#define SNDRV_PCM_FORMAT_S18_3LE ((__force snd_pcm_format_t) 40) /* in three bytes */ +#define SNDRV_PCM_FORMAT_S18_3BE ((__force snd_pcm_format_t) 41) /* in three bytes */ +#define SNDRV_PCM_FORMAT_U18_3LE ((__force snd_pcm_format_t) 42) /* in three bytes */ +#define SNDRV_PCM_FORMAT_U18_3BE ((__force snd_pcm_format_t) 43) /* in three bytes */ +#define SNDRV_PCM_FORMAT_G723_24 ((__force snd_pcm_format_t) 44) /* 8 samples in 3 bytes */ +#define SNDRV_PCM_FORMAT_G723_24_1B ((__force snd_pcm_format_t) 45) /* 1 sample in 1 byte */ +#define SNDRV_PCM_FORMAT_G723_40 ((__force snd_pcm_format_t) 46) /* 8 Samples in 5 bytes */ +#define SNDRV_PCM_FORMAT_G723_40_1B ((__force snd_pcm_format_t) 47) /* 1 sample in 1 byte */ +#define SNDRV_PCM_FORMAT_DSD_U8 ((__force snd_pcm_format_t) 48) /* DSD, 1-byte samples DSD (x8) */ +#define SNDRV_PCM_FORMAT_DSD_U16_LE ((__force snd_pcm_format_t) 49) /* DSD, 2-byte samples DSD (x16), little endian */ +#define SNDRV_PCM_FORMAT_DSD_U32_LE ((__force snd_pcm_format_t) 50) /* DSD, 4-byte samples DSD (x32), little endian */ +#define SNDRV_PCM_FORMAT_DSD_U16_BE ((__force snd_pcm_format_t) 51) /* DSD, 2-byte samples DSD (x16), big endian */ +#define SNDRV_PCM_FORMAT_DSD_U32_BE ((__force snd_pcm_format_t) 52) /* DSD, 4-byte samples DSD (x32), big endian */ +#define SNDRV_PCM_FORMAT_LAST SNDRV_PCM_FORMAT_DSD_U32_BE + +#ifdef SNDRV_LITTLE_ENDIAN +#define SNDRV_PCM_FORMAT_S16 SNDRV_PCM_FORMAT_S16_LE +#define SNDRV_PCM_FORMAT_U16 SNDRV_PCM_FORMAT_U16_LE +#define SNDRV_PCM_FORMAT_S24 SNDRV_PCM_FORMAT_S24_LE +#define SNDRV_PCM_FORMAT_U24 SNDRV_PCM_FORMAT_U24_LE +#define SNDRV_PCM_FORMAT_S32 SNDRV_PCM_FORMAT_S32_LE +#define SNDRV_PCM_FORMAT_U32 SNDRV_PCM_FORMAT_U32_LE +#define SNDRV_PCM_FORMAT_FLOAT SNDRV_PCM_FORMAT_FLOAT_LE +#define SNDRV_PCM_FORMAT_FLOAT64 SNDRV_PCM_FORMAT_FLOAT64_LE +#define SNDRV_PCM_FORMAT_IEC958_SUBFRAME SNDRV_PCM_FORMAT_IEC958_SUBFRAME_LE +#endif +#ifdef SNDRV_BIG_ENDIAN +#define SNDRV_PCM_FORMAT_S16 SNDRV_PCM_FORMAT_S16_BE +#define SNDRV_PCM_FORMAT_U16 SNDRV_PCM_FORMAT_U16_BE +#define SNDRV_PCM_FORMAT_S24 SNDRV_PCM_FORMAT_S24_BE +#define SNDRV_PCM_FORMAT_U24 SNDRV_PCM_FORMAT_U24_BE +#define SNDRV_PCM_FORMAT_S32 SNDRV_PCM_FORMAT_S32_BE +#define SNDRV_PCM_FORMAT_U32 SNDRV_PCM_FORMAT_U32_BE +#define SNDRV_PCM_FORMAT_FLOAT SNDRV_PCM_FORMAT_FLOAT_BE +#define SNDRV_PCM_FORMAT_FLOAT64 SNDRV_PCM_FORMAT_FLOAT64_BE +#define SNDRV_PCM_FORMAT_IEC958_SUBFRAME SNDRV_PCM_FORMAT_IEC958_SUBFRAME_BE +#endif + +typedef int __bitwise snd_pcm_subformat_t; +#define SNDRV_PCM_SUBFORMAT_STD ((__force snd_pcm_subformat_t) 0) +#define SNDRV_PCM_SUBFORMAT_LAST SNDRV_PCM_SUBFORMAT_STD + +#define SNDRV_PCM_INFO_MMAP 0x00000001 /* hardware supports mmap */ +#define SNDRV_PCM_INFO_MMAP_VALID 0x00000002 /* period data are valid during transfer */ +#define SNDRV_PCM_INFO_DOUBLE 0x00000004 /* Double buffering needed for PCM start/stop */ +#define SNDRV_PCM_INFO_BATCH 0x00000010 /* double buffering */ +#define SNDRV_PCM_INFO_SYNC_APPLPTR 0x00000020 /* need the explicit sync of appl_ptr update */ +#define SNDRV_PCM_INFO_INTERLEAVED 0x00000100 /* channels are interleaved */ +#define SNDRV_PCM_INFO_NONINTERLEAVED 0x00000200 /* channels are not interleaved */ +#define SNDRV_PCM_INFO_COMPLEX 0x00000400 /* complex frame organization (mmap only) */ +#define SNDRV_PCM_INFO_BLOCK_TRANSFER 0x00010000 /* hardware transfer block of samples */ +#define SNDRV_PCM_INFO_OVERRANGE 0x00020000 /* hardware supports ADC (capture) overrange detection */ +#define SNDRV_PCM_INFO_RESUME 0x00040000 /* hardware supports stream resume after suspend */ +#define SNDRV_PCM_INFO_PAUSE 0x00080000 /* pause ioctl is supported */ +#define SNDRV_PCM_INFO_HALF_DUPLEX 0x00100000 /* only half duplex */ +#define SNDRV_PCM_INFO_JOINT_DUPLEX 0x00200000 /* playback and capture stream are somewhat correlated */ +#define SNDRV_PCM_INFO_SYNC_START 0x00400000 /* pcm support some kind of sync go */ +#define SNDRV_PCM_INFO_NO_PERIOD_WAKEUP 0x00800000 /* period wakeup can be disabled */ +#define SNDRV_PCM_INFO_HAS_WALL_CLOCK 0x01000000 /* (Deprecated)has audio wall clock for audio/system time sync */ +#define SNDRV_PCM_INFO_HAS_LINK_ATIME 0x01000000 /* report hardware link audio time, reset on startup */ +#define SNDRV_PCM_INFO_HAS_LINK_ABSOLUTE_ATIME 0x02000000 /* report absolute hardware link audio time, not reset on startup */ +#define SNDRV_PCM_INFO_HAS_LINK_ESTIMATED_ATIME 0x04000000 /* report estimated link audio time */ +#define SNDRV_PCM_INFO_HAS_LINK_SYNCHRONIZED_ATIME 0x08000000 /* report synchronized audio/system time */ + +#define SNDRV_PCM_INFO_DRAIN_TRIGGER 0x40000000 /* internal kernel flag - trigger in drain */ +#define SNDRV_PCM_INFO_FIFO_IN_FRAMES 0x80000000 /* internal kernel flag - FIFO size is in frames */ + + + +typedef int __bitwise snd_pcm_state_t; +#define SNDRV_PCM_STATE_OPEN ((__force snd_pcm_state_t) 0) /* stream is open */ +#define SNDRV_PCM_STATE_SETUP ((__force snd_pcm_state_t) 1) /* stream has a setup */ +#define SNDRV_PCM_STATE_PREPARED ((__force snd_pcm_state_t) 2) /* stream is ready to start */ +#define SNDRV_PCM_STATE_RUNNING ((__force snd_pcm_state_t) 3) /* stream is running */ +#define SNDRV_PCM_STATE_XRUN ((__force snd_pcm_state_t) 4) /* stream reached an xrun */ +#define SNDRV_PCM_STATE_DRAINING ((__force snd_pcm_state_t) 5) /* stream is draining */ +#define SNDRV_PCM_STATE_PAUSED ((__force snd_pcm_state_t) 6) /* stream is paused */ +#define SNDRV_PCM_STATE_SUSPENDED ((__force snd_pcm_state_t) 7) /* hardware is suspended */ +#define SNDRV_PCM_STATE_DISCONNECTED ((__force snd_pcm_state_t) 8) /* hardware is disconnected */ +#define SNDRV_PCM_STATE_LAST SNDRV_PCM_STATE_DISCONNECTED + +enum { + SNDRV_PCM_MMAP_OFFSET_DATA = 0x00000000, + SNDRV_PCM_MMAP_OFFSET_STATUS = 0x80000000, + SNDRV_PCM_MMAP_OFFSET_CONTROL = 0x81000000, +}; + +union snd_pcm_sync_id { + unsigned char id[16]; + unsigned short id16[8]; + unsigned int id32[4]; +}; + +struct snd_pcm_info { + unsigned int device; /* RO/WR (control): device number */ + unsigned int subdevice; /* RO/WR (control): subdevice number */ + int stream; /* RO/WR (control): stream direction */ + int card; /* R: card number */ + unsigned char id[64]; /* ID (user selectable) */ + unsigned char name[80]; /* name of this device */ + unsigned char subname[32]; /* subdevice name */ + int dev_class; /* SNDRV_PCM_CLASS_* */ + int dev_subclass; /* SNDRV_PCM_SUBCLASS_* */ + unsigned int subdevices_count; + unsigned int subdevices_avail; + union snd_pcm_sync_id sync; /* hardware synchronization ID */ + unsigned char reserved[64]; /* reserved for future... */ +}; + +typedef int snd_pcm_hw_param_t; +#define SNDRV_PCM_HW_PARAM_ACCESS 0 /* Access type */ +#define SNDRV_PCM_HW_PARAM_FORMAT 1 /* Format */ +#define SNDRV_PCM_HW_PARAM_SUBFORMAT 2 /* Subformat */ +#define SNDRV_PCM_HW_PARAM_FIRST_MASK SNDRV_PCM_HW_PARAM_ACCESS +#define SNDRV_PCM_HW_PARAM_LAST_MASK SNDRV_PCM_HW_PARAM_SUBFORMAT + +#define SNDRV_PCM_HW_PARAM_SAMPLE_BITS 8 /* Bits per sample */ +#define SNDRV_PCM_HW_PARAM_FRAME_BITS 9 /* Bits per frame */ +#define SNDRV_PCM_HW_PARAM_CHANNELS 10 /* Channels */ +#define SNDRV_PCM_HW_PARAM_RATE 11 /* Approx rate */ +#define SNDRV_PCM_HW_PARAM_PERIOD_TIME 12 /* Approx distance between + * interrupts in us + */ +#define SNDRV_PCM_HW_PARAM_PERIOD_SIZE 13 /* Approx frames between + * interrupts + */ +#define SNDRV_PCM_HW_PARAM_PERIOD_BYTES 14 /* Approx bytes between + * interrupts + */ +#define SNDRV_PCM_HW_PARAM_PERIODS 15 /* Approx interrupts per + * buffer + */ +#define SNDRV_PCM_HW_PARAM_BUFFER_TIME 16 /* Approx duration of buffer + * in us + */ +#define SNDRV_PCM_HW_PARAM_BUFFER_SIZE 17 /* Size of buffer in frames */ +#define SNDRV_PCM_HW_PARAM_BUFFER_BYTES 18 /* Size of buffer in bytes */ +#define SNDRV_PCM_HW_PARAM_TICK_TIME 19 /* Approx tick duration in us */ +#define SNDRV_PCM_HW_PARAM_FIRST_INTERVAL SNDRV_PCM_HW_PARAM_SAMPLE_BITS +#define SNDRV_PCM_HW_PARAM_LAST_INTERVAL SNDRV_PCM_HW_PARAM_TICK_TIME + +#define SNDRV_PCM_HW_PARAMS_NORESAMPLE (1<<0) /* avoid rate resampling */ +#define SNDRV_PCM_HW_PARAMS_EXPORT_BUFFER (1<<1) /* export buffer */ +#define SNDRV_PCM_HW_PARAMS_NO_PERIOD_WAKEUP (1<<2) /* disable period wakeups */ + +struct snd_interval { + unsigned int min, max; + unsigned int openmin:1, + openmax:1, + integer:1, + empty:1; +}; + +#define SNDRV_MASK_MAX 256 + +struct snd_mask { + __u32 bits[(SNDRV_MASK_MAX+31)/32]; +}; + +struct snd_pcm_hw_params { + unsigned int flags; + struct snd_mask masks[SNDRV_PCM_HW_PARAM_LAST_MASK - + SNDRV_PCM_HW_PARAM_FIRST_MASK + 1]; + struct snd_mask mres[5]; /* reserved masks */ + struct snd_interval intervals[SNDRV_PCM_HW_PARAM_LAST_INTERVAL - + SNDRV_PCM_HW_PARAM_FIRST_INTERVAL + 1]; + struct snd_interval ires[9]; /* reserved intervals */ + unsigned int rmask; /* W: requested masks */ + unsigned int cmask; /* R: changed masks */ + unsigned int info; /* R: Info flags for returned setup */ + unsigned int msbits; /* R: used most significant bits */ + unsigned int rate_num; /* R: rate numerator */ + unsigned int rate_den; /* R: rate denominator */ + snd_pcm_uframes_t fifo_size; /* R: chip FIFO size in frames */ + unsigned char reserved[64]; /* reserved for future */ +}; + +enum { + SNDRV_PCM_TSTAMP_NONE = 0, + SNDRV_PCM_TSTAMP_ENABLE, + SNDRV_PCM_TSTAMP_LAST = SNDRV_PCM_TSTAMP_ENABLE, +}; + +struct snd_pcm_sw_params { + int tstamp_mode; /* timestamp mode */ + unsigned int period_step; + unsigned int sleep_min; /* min ticks to sleep */ + snd_pcm_uframes_t avail_min; /* min avail frames for wakeup */ + snd_pcm_uframes_t xfer_align; /* obsolete: xfer size need to be a multiple */ + snd_pcm_uframes_t start_threshold; /* min hw_avail frames for automatic start */ + snd_pcm_uframes_t stop_threshold; /* min avail frames for automatic stop */ + snd_pcm_uframes_t silence_threshold; /* min distance from noise for silence filling */ + snd_pcm_uframes_t silence_size; /* silence block size */ + snd_pcm_uframes_t boundary; /* pointers wrap point */ + unsigned int proto; /* protocol version */ + unsigned int tstamp_type; /* timestamp type (req. proto >= 2.0.12) */ + unsigned char reserved[56]; /* reserved for future */ +}; + +struct snd_pcm_channel_info { + unsigned int channel; + __kernel_off_t offset; /* mmap offset */ + unsigned int first; /* offset to first sample in bits */ + unsigned int step; /* samples distance in bits */ +}; + +enum { + /* + * first definition for backwards compatibility only, + * maps to wallclock/link time for HDAudio playback and DEFAULT/DMA time for everything else + */ + SNDRV_PCM_AUDIO_TSTAMP_TYPE_COMPAT = 0, + + /* timestamp definitions */ + SNDRV_PCM_AUDIO_TSTAMP_TYPE_DEFAULT = 1, /* DMA time, reported as per hw_ptr */ + SNDRV_PCM_AUDIO_TSTAMP_TYPE_LINK = 2, /* link time reported by sample or wallclock counter, reset on startup */ + SNDRV_PCM_AUDIO_TSTAMP_TYPE_LINK_ABSOLUTE = 3, /* link time reported by sample or wallclock counter, not reset on startup */ + SNDRV_PCM_AUDIO_TSTAMP_TYPE_LINK_ESTIMATED = 4, /* link time estimated indirectly */ + SNDRV_PCM_AUDIO_TSTAMP_TYPE_LINK_SYNCHRONIZED = 5, /* link time synchronized with system time */ + SNDRV_PCM_AUDIO_TSTAMP_TYPE_LAST = SNDRV_PCM_AUDIO_TSTAMP_TYPE_LINK_SYNCHRONIZED +}; + +struct snd_pcm_status { + snd_pcm_state_t state; /* stream state */ + struct timespec trigger_tstamp; /* time when stream was started/stopped/paused */ + struct timespec tstamp; /* reference timestamp */ + snd_pcm_uframes_t appl_ptr; /* appl ptr */ + snd_pcm_uframes_t hw_ptr; /* hw ptr */ + snd_pcm_sframes_t delay; /* current delay in frames */ + snd_pcm_uframes_t avail; /* number of frames available */ + snd_pcm_uframes_t avail_max; /* max frames available on hw since last status */ + snd_pcm_uframes_t overrange; /* count of ADC (capture) overrange detections from last status */ + snd_pcm_state_t suspended_state; /* suspended stream state */ + __u32 audio_tstamp_data; /* needed for 64-bit alignment, used for configs/report to/from userspace */ + struct timespec audio_tstamp; /* sample counter, wall clock, PHC or on-demand sync'ed */ + struct timespec driver_tstamp; /* useful in case reference system tstamp is reported with delay */ + __u32 audio_tstamp_accuracy; /* in ns units, only valid if indicated in audio_tstamp_data */ + unsigned char reserved[52-2*sizeof(struct timespec)]; /* must be filled with zero */ +}; + +struct snd_pcm_mmap_status { + snd_pcm_state_t state; /* RO: state - SNDRV_PCM_STATE_XXXX */ + int pad1; /* Needed for 64 bit alignment */ + snd_pcm_uframes_t hw_ptr; /* RO: hw ptr (0...boundary-1) */ + struct timespec tstamp; /* Timestamp */ + snd_pcm_state_t suspended_state; /* RO: suspended stream state */ + struct timespec audio_tstamp; /* from sample counter or wall clock */ +}; + +struct snd_pcm_mmap_control { + snd_pcm_uframes_t appl_ptr; /* RW: appl ptr (0...boundary-1) */ + snd_pcm_uframes_t avail_min; /* RW: min available frames for wakeup */ +}; + +#define SNDRV_PCM_SYNC_PTR_HWSYNC (1<<0) /* execute hwsync */ +#define SNDRV_PCM_SYNC_PTR_APPL (1<<1) /* get appl_ptr from driver (r/w op) */ +#define SNDRV_PCM_SYNC_PTR_AVAIL_MIN (1<<2) /* get avail_min from driver */ + +struct snd_pcm_sync_ptr { + unsigned int flags; + union { + struct snd_pcm_mmap_status status; + unsigned char reserved[64]; + } s; + union { + struct snd_pcm_mmap_control control; + unsigned char reserved[64]; + } c; +}; + +struct snd_xferi { + snd_pcm_sframes_t result; + void __user *buf; + snd_pcm_uframes_t frames; +}; + +struct snd_xfern { + snd_pcm_sframes_t result; + void __user * __user *bufs; + snd_pcm_uframes_t frames; +}; + +enum { + SNDRV_PCM_TSTAMP_TYPE_GETTIMEOFDAY = 0, /* gettimeofday equivalent */ + SNDRV_PCM_TSTAMP_TYPE_MONOTONIC, /* posix_clock_monotonic equivalent */ + SNDRV_PCM_TSTAMP_TYPE_MONOTONIC_RAW, /* monotonic_raw (no NTP) */ + SNDRV_PCM_TSTAMP_TYPE_LAST = SNDRV_PCM_TSTAMP_TYPE_MONOTONIC_RAW, +}; + +/* channel positions */ +enum { + SNDRV_CHMAP_UNKNOWN = 0, + SNDRV_CHMAP_NA, /* N/A, silent */ + SNDRV_CHMAP_MONO, /* mono stream */ + /* this follows the alsa-lib mixer channel value + 3 */ + SNDRV_CHMAP_FL, /* front left */ + SNDRV_CHMAP_FR, /* front right */ + SNDRV_CHMAP_RL, /* rear left */ + SNDRV_CHMAP_RR, /* rear right */ + SNDRV_CHMAP_FC, /* front center */ + SNDRV_CHMAP_LFE, /* LFE */ + SNDRV_CHMAP_SL, /* side left */ + SNDRV_CHMAP_SR, /* side right */ + SNDRV_CHMAP_RC, /* rear center */ + /* new definitions */ + SNDRV_CHMAP_FLC, /* front left center */ + SNDRV_CHMAP_FRC, /* front right center */ + SNDRV_CHMAP_RLC, /* rear left center */ + SNDRV_CHMAP_RRC, /* rear right center */ + SNDRV_CHMAP_FLW, /* front left wide */ + SNDRV_CHMAP_FRW, /* front right wide */ + SNDRV_CHMAP_FLH, /* front left high */ + SNDRV_CHMAP_FCH, /* front center high */ + SNDRV_CHMAP_FRH, /* front right high */ + SNDRV_CHMAP_TC, /* top center */ + SNDRV_CHMAP_TFL, /* top front left */ + SNDRV_CHMAP_TFR, /* top front right */ + SNDRV_CHMAP_TFC, /* top front center */ + SNDRV_CHMAP_TRL, /* top rear left */ + SNDRV_CHMAP_TRR, /* top rear right */ + SNDRV_CHMAP_TRC, /* top rear center */ + /* new definitions for UAC2 */ + SNDRV_CHMAP_TFLC, /* top front left center */ + SNDRV_CHMAP_TFRC, /* top front right center */ + SNDRV_CHMAP_TSL, /* top side left */ + SNDRV_CHMAP_TSR, /* top side right */ + SNDRV_CHMAP_LLFE, /* left LFE */ + SNDRV_CHMAP_RLFE, /* right LFE */ + SNDRV_CHMAP_BC, /* bottom center */ + SNDRV_CHMAP_BLC, /* bottom left center */ + SNDRV_CHMAP_BRC, /* bottom right center */ + SNDRV_CHMAP_LAST = SNDRV_CHMAP_BRC, +}; + +#define SNDRV_CHMAP_POSITION_MASK 0xffff +#define SNDRV_CHMAP_PHASE_INVERSE (0x01 << 16) +#define SNDRV_CHMAP_DRIVER_SPEC (0x02 << 16) + +#define SNDRV_PCM_IOCTL_PVERSION _IOR('A', 0x00, int) +#define SNDRV_PCM_IOCTL_INFO _IOR('A', 0x01, struct snd_pcm_info) +#define SNDRV_PCM_IOCTL_TSTAMP _IOW('A', 0x02, int) +#define SNDRV_PCM_IOCTL_TTSTAMP _IOW('A', 0x03, int) +#define SNDRV_PCM_IOCTL_USER_PVERSION _IOW('A', 0x04, int) +#define SNDRV_PCM_IOCTL_HW_REFINE _IOWR('A', 0x10, struct snd_pcm_hw_params) +#define SNDRV_PCM_IOCTL_HW_PARAMS _IOWR('A', 0x11, struct snd_pcm_hw_params) +#define SNDRV_PCM_IOCTL_HW_FREE _IO('A', 0x12) +#define SNDRV_PCM_IOCTL_SW_PARAMS _IOWR('A', 0x13, struct snd_pcm_sw_params) +#define SNDRV_PCM_IOCTL_STATUS _IOR('A', 0x20, struct snd_pcm_status) +#define SNDRV_PCM_IOCTL_DELAY _IOR('A', 0x21, snd_pcm_sframes_t) +#define SNDRV_PCM_IOCTL_HWSYNC _IO('A', 0x22) +#define SNDRV_PCM_IOCTL_SYNC_PTR _IOWR('A', 0x23, struct snd_pcm_sync_ptr) +#define SNDRV_PCM_IOCTL_STATUS_EXT _IOWR('A', 0x24, struct snd_pcm_status) +#define SNDRV_PCM_IOCTL_CHANNEL_INFO _IOR('A', 0x32, struct snd_pcm_channel_info) +#define SNDRV_PCM_IOCTL_PREPARE _IO('A', 0x40) +#define SNDRV_PCM_IOCTL_RESET _IO('A', 0x41) +#define SNDRV_PCM_IOCTL_START _IO('A', 0x42) +#define SNDRV_PCM_IOCTL_DROP _IO('A', 0x43) +#define SNDRV_PCM_IOCTL_DRAIN _IO('A', 0x44) +#define SNDRV_PCM_IOCTL_PAUSE _IOW('A', 0x45, int) +#define SNDRV_PCM_IOCTL_REWIND _IOW('A', 0x46, snd_pcm_uframes_t) +#define SNDRV_PCM_IOCTL_RESUME _IO('A', 0x47) +#define SNDRV_PCM_IOCTL_XRUN _IO('A', 0x48) +#define SNDRV_PCM_IOCTL_FORWARD _IOW('A', 0x49, snd_pcm_uframes_t) +#define SNDRV_PCM_IOCTL_WRITEI_FRAMES _IOW('A', 0x50, struct snd_xferi) +#define SNDRV_PCM_IOCTL_READI_FRAMES _IOR('A', 0x51, struct snd_xferi) +#define SNDRV_PCM_IOCTL_WRITEN_FRAMES _IOW('A', 0x52, struct snd_xfern) +#define SNDRV_PCM_IOCTL_READN_FRAMES _IOR('A', 0x53, struct snd_xfern) +#define SNDRV_PCM_IOCTL_LINK _IOW('A', 0x60, int) +#define SNDRV_PCM_IOCTL_UNLINK _IO('A', 0x61) + +/***************************************************************************** + * * + * MIDI v1.0 interface * + * * + *****************************************************************************/ + +/* + * Raw MIDI section - /dev/snd/midi?? + */ + +#define SNDRV_RAWMIDI_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 0) + +enum { + SNDRV_RAWMIDI_STREAM_OUTPUT = 0, + SNDRV_RAWMIDI_STREAM_INPUT, + SNDRV_RAWMIDI_STREAM_LAST = SNDRV_RAWMIDI_STREAM_INPUT, +}; + +#define SNDRV_RAWMIDI_INFO_OUTPUT 0x00000001 +#define SNDRV_RAWMIDI_INFO_INPUT 0x00000002 +#define SNDRV_RAWMIDI_INFO_DUPLEX 0x00000004 + +struct snd_rawmidi_info { + unsigned int device; /* RO/WR (control): device number */ + unsigned int subdevice; /* RO/WR (control): subdevice number */ + int stream; /* WR: stream */ + int card; /* R: card number */ + unsigned int flags; /* SNDRV_RAWMIDI_INFO_XXXX */ + unsigned char id[64]; /* ID (user selectable) */ + unsigned char name[80]; /* name of device */ + unsigned char subname[32]; /* name of active or selected subdevice */ + unsigned int subdevices_count; + unsigned int subdevices_avail; + unsigned char reserved[64]; /* reserved for future use */ +}; + +struct snd_rawmidi_params { + int stream; + size_t buffer_size; /* queue size in bytes */ + size_t avail_min; /* minimum avail bytes for wakeup */ + unsigned int no_active_sensing: 1; /* do not send active sensing byte in close() */ + unsigned char reserved[16]; /* reserved for future use */ +}; + +struct snd_rawmidi_status { + int stream; + struct timespec tstamp; /* Timestamp */ + size_t avail; /* available bytes */ + size_t xruns; /* count of overruns since last status (in bytes) */ + unsigned char reserved[16]; /* reserved for future use */ +}; + +#define SNDRV_RAWMIDI_IOCTL_PVERSION _IOR('W', 0x00, int) +#define SNDRV_RAWMIDI_IOCTL_INFO _IOR('W', 0x01, struct snd_rawmidi_info) +#define SNDRV_RAWMIDI_IOCTL_PARAMS _IOWR('W', 0x10, struct snd_rawmidi_params) +#define SNDRV_RAWMIDI_IOCTL_STATUS _IOWR('W', 0x20, struct snd_rawmidi_status) +#define SNDRV_RAWMIDI_IOCTL_DROP _IOW('W', 0x30, int) +#define SNDRV_RAWMIDI_IOCTL_DRAIN _IOW('W', 0x31, int) + +/* + * Timer section - /dev/snd/timer + */ + +#define SNDRV_TIMER_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 6) + +enum { + SNDRV_TIMER_CLASS_NONE = -1, + SNDRV_TIMER_CLASS_SLAVE = 0, + SNDRV_TIMER_CLASS_GLOBAL, + SNDRV_TIMER_CLASS_CARD, + SNDRV_TIMER_CLASS_PCM, + SNDRV_TIMER_CLASS_LAST = SNDRV_TIMER_CLASS_PCM, +}; + +/* slave timer classes */ +enum { + SNDRV_TIMER_SCLASS_NONE = 0, + SNDRV_TIMER_SCLASS_APPLICATION, + SNDRV_TIMER_SCLASS_SEQUENCER, /* alias */ + SNDRV_TIMER_SCLASS_OSS_SEQUENCER, /* alias */ + SNDRV_TIMER_SCLASS_LAST = SNDRV_TIMER_SCLASS_OSS_SEQUENCER, +}; + +/* global timers (device member) */ +#define SNDRV_TIMER_GLOBAL_SYSTEM 0 +#define SNDRV_TIMER_GLOBAL_RTC 1 /* unused */ +#define SNDRV_TIMER_GLOBAL_HPET 2 +#define SNDRV_TIMER_GLOBAL_HRTIMER 3 + +/* info flags */ +#define SNDRV_TIMER_FLG_SLAVE (1<<0) /* cannot be controlled */ + +struct snd_timer_id { + int dev_class; + int dev_sclass; + int card; + int device; + int subdevice; +}; + +struct snd_timer_ginfo { + struct snd_timer_id tid; /* requested timer ID */ + unsigned int flags; /* timer flags - SNDRV_TIMER_FLG_* */ + int card; /* card number */ + unsigned char id[64]; /* timer identification */ + unsigned char name[80]; /* timer name */ + unsigned long reserved0; /* reserved for future use */ + unsigned long resolution; /* average period resolution in ns */ + unsigned long resolution_min; /* minimal period resolution in ns */ + unsigned long resolution_max; /* maximal period resolution in ns */ + unsigned int clients; /* active timer clients */ + unsigned char reserved[32]; +}; + +struct snd_timer_gparams { + struct snd_timer_id tid; /* requested timer ID */ + unsigned long period_num; /* requested precise period duration (in seconds) - numerator */ + unsigned long period_den; /* requested precise period duration (in seconds) - denominator */ + unsigned char reserved[32]; +}; + +struct snd_timer_gstatus { + struct snd_timer_id tid; /* requested timer ID */ + unsigned long resolution; /* current period resolution in ns */ + unsigned long resolution_num; /* precise current period resolution (in seconds) - numerator */ + unsigned long resolution_den; /* precise current period resolution (in seconds) - denominator */ + unsigned char reserved[32]; +}; + +struct snd_timer_select { + struct snd_timer_id id; /* bind to timer ID */ + unsigned char reserved[32]; /* reserved */ +}; + +struct snd_timer_info { + unsigned int flags; /* timer flags - SNDRV_TIMER_FLG_* */ + int card; /* card number */ + unsigned char id[64]; /* timer identificator */ + unsigned char name[80]; /* timer name */ + unsigned long reserved0; /* reserved for future use */ + unsigned long resolution; /* average period resolution in ns */ + unsigned char reserved[64]; /* reserved */ +}; + +#define SNDRV_TIMER_PSFLG_AUTO (1<<0) /* auto start, otherwise one-shot */ +#define SNDRV_TIMER_PSFLG_EXCLUSIVE (1<<1) /* exclusive use, precise start/stop/pause/continue */ +#define SNDRV_TIMER_PSFLG_EARLY_EVENT (1<<2) /* write early event to the poll queue */ + +struct snd_timer_params { + unsigned int flags; /* flags - SNDRV_MIXER_PSFLG_* */ + unsigned int ticks; /* requested resolution in ticks */ + unsigned int queue_size; /* total size of queue (32-1024) */ + unsigned int reserved0; /* reserved, was: failure locations */ + unsigned int filter; /* event filter (bitmask of SNDRV_TIMER_EVENT_*) */ + unsigned char reserved[60]; /* reserved */ +}; + +struct snd_timer_status { + struct timespec tstamp; /* Timestamp - last update */ + unsigned int resolution; /* current period resolution in ns */ + unsigned int lost; /* counter of master tick lost */ + unsigned int overrun; /* count of read queue overruns */ + unsigned int queue; /* used queue size */ + unsigned char reserved[64]; /* reserved */ +}; + +#define SNDRV_TIMER_IOCTL_PVERSION _IOR('T', 0x00, int) +#define SNDRV_TIMER_IOCTL_NEXT_DEVICE _IOWR('T', 0x01, struct snd_timer_id) +#define SNDRV_TIMER_IOCTL_TREAD _IOW('T', 0x02, int) +#define SNDRV_TIMER_IOCTL_GINFO _IOWR('T', 0x03, struct snd_timer_ginfo) +#define SNDRV_TIMER_IOCTL_GPARAMS _IOW('T', 0x04, struct snd_timer_gparams) +#define SNDRV_TIMER_IOCTL_GSTATUS _IOWR('T', 0x05, struct snd_timer_gstatus) +#define SNDRV_TIMER_IOCTL_SELECT _IOW('T', 0x10, struct snd_timer_select) +#define SNDRV_TIMER_IOCTL_INFO _IOR('T', 0x11, struct snd_timer_info) +#define SNDRV_TIMER_IOCTL_PARAMS _IOW('T', 0x12, struct snd_timer_params) +#define SNDRV_TIMER_IOCTL_STATUS _IOR('T', 0x14, struct snd_timer_status) +/* The following four ioctls are changed since 1.0.9 due to confliction */ +#define SNDRV_TIMER_IOCTL_START _IO('T', 0xa0) +#define SNDRV_TIMER_IOCTL_STOP _IO('T', 0xa1) +#define SNDRV_TIMER_IOCTL_CONTINUE _IO('T', 0xa2) +#define SNDRV_TIMER_IOCTL_PAUSE _IO('T', 0xa3) + +struct snd_timer_read { + unsigned int resolution; + unsigned int ticks; +}; + +enum { + SNDRV_TIMER_EVENT_RESOLUTION = 0, /* val = resolution in ns */ + SNDRV_TIMER_EVENT_TICK, /* val = ticks */ + SNDRV_TIMER_EVENT_START, /* val = resolution in ns */ + SNDRV_TIMER_EVENT_STOP, /* val = 0 */ + SNDRV_TIMER_EVENT_CONTINUE, /* val = resolution in ns */ + SNDRV_TIMER_EVENT_PAUSE, /* val = 0 */ + SNDRV_TIMER_EVENT_EARLY, /* val = 0, early event */ + SNDRV_TIMER_EVENT_SUSPEND, /* val = 0 */ + SNDRV_TIMER_EVENT_RESUME, /* val = resolution in ns */ + /* master timer events for slave timer instances */ + SNDRV_TIMER_EVENT_MSTART = SNDRV_TIMER_EVENT_START + 10, + SNDRV_TIMER_EVENT_MSTOP = SNDRV_TIMER_EVENT_STOP + 10, + SNDRV_TIMER_EVENT_MCONTINUE = SNDRV_TIMER_EVENT_CONTINUE + 10, + SNDRV_TIMER_EVENT_MPAUSE = SNDRV_TIMER_EVENT_PAUSE + 10, + SNDRV_TIMER_EVENT_MSUSPEND = SNDRV_TIMER_EVENT_SUSPEND + 10, + SNDRV_TIMER_EVENT_MRESUME = SNDRV_TIMER_EVENT_RESUME + 10, +}; + +struct snd_timer_tread { + int event; + struct timespec tstamp; + unsigned int val; +}; + +/**************************************************************************** + * * + * Section for driver control interface - /dev/snd/control? * + * * + ****************************************************************************/ + +#define SNDRV_CTL_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 7) + +struct snd_ctl_card_info { + int card; /* card number */ + int pad; /* reserved for future (was type) */ + unsigned char id[16]; /* ID of card (user selectable) */ + unsigned char driver[16]; /* Driver name */ + unsigned char name[32]; /* Short name of soundcard */ + unsigned char longname[80]; /* name + info text about soundcard */ + unsigned char reserved_[16]; /* reserved for future (was ID of mixer) */ + unsigned char mixername[80]; /* visual mixer identification */ + unsigned char components[128]; /* card components / fine identification, delimited with one space (AC97 etc..) */ +}; + +typedef int __bitwise snd_ctl_elem_type_t; +#define SNDRV_CTL_ELEM_TYPE_NONE ((__force snd_ctl_elem_type_t) 0) /* invalid */ +#define SNDRV_CTL_ELEM_TYPE_BOOLEAN ((__force snd_ctl_elem_type_t) 1) /* boolean type */ +#define SNDRV_CTL_ELEM_TYPE_INTEGER ((__force snd_ctl_elem_type_t) 2) /* integer type */ +#define SNDRV_CTL_ELEM_TYPE_ENUMERATED ((__force snd_ctl_elem_type_t) 3) /* enumerated type */ +#define SNDRV_CTL_ELEM_TYPE_BYTES ((__force snd_ctl_elem_type_t) 4) /* byte array */ +#define SNDRV_CTL_ELEM_TYPE_IEC958 ((__force snd_ctl_elem_type_t) 5) /* IEC958 (S/PDIF) setup */ +#define SNDRV_CTL_ELEM_TYPE_INTEGER64 ((__force snd_ctl_elem_type_t) 6) /* 64-bit integer type */ +#define SNDRV_CTL_ELEM_TYPE_LAST SNDRV_CTL_ELEM_TYPE_INTEGER64 + +typedef int __bitwise snd_ctl_elem_iface_t; +#define SNDRV_CTL_ELEM_IFACE_CARD ((__force snd_ctl_elem_iface_t) 0) /* global control */ +#define SNDRV_CTL_ELEM_IFACE_HWDEP ((__force snd_ctl_elem_iface_t) 1) /* hardware dependent device */ +#define SNDRV_CTL_ELEM_IFACE_MIXER ((__force snd_ctl_elem_iface_t) 2) /* virtual mixer device */ +#define SNDRV_CTL_ELEM_IFACE_PCM ((__force snd_ctl_elem_iface_t) 3) /* PCM device */ +#define SNDRV_CTL_ELEM_IFACE_RAWMIDI ((__force snd_ctl_elem_iface_t) 4) /* RawMidi device */ +#define SNDRV_CTL_ELEM_IFACE_TIMER ((__force snd_ctl_elem_iface_t) 5) /* timer device */ +#define SNDRV_CTL_ELEM_IFACE_SEQUENCER ((__force snd_ctl_elem_iface_t) 6) /* sequencer client */ +#define SNDRV_CTL_ELEM_IFACE_LAST SNDRV_CTL_ELEM_IFACE_SEQUENCER + +#define SNDRV_CTL_ELEM_ACCESS_READ (1<<0) +#define SNDRV_CTL_ELEM_ACCESS_WRITE (1<<1) +#define SNDRV_CTL_ELEM_ACCESS_READWRITE (SNDRV_CTL_ELEM_ACCESS_READ|SNDRV_CTL_ELEM_ACCESS_WRITE) +#define SNDRV_CTL_ELEM_ACCESS_VOLATILE (1<<2) /* control value may be changed without a notification */ +#define SNDRV_CTL_ELEM_ACCESS_TIMESTAMP (1<<3) /* when was control changed */ +#define SNDRV_CTL_ELEM_ACCESS_TLV_READ (1<<4) /* TLV read is possible */ +#define SNDRV_CTL_ELEM_ACCESS_TLV_WRITE (1<<5) /* TLV write is possible */ +#define SNDRV_CTL_ELEM_ACCESS_TLV_READWRITE (SNDRV_CTL_ELEM_ACCESS_TLV_READ|SNDRV_CTL_ELEM_ACCESS_TLV_WRITE) +#define SNDRV_CTL_ELEM_ACCESS_TLV_COMMAND (1<<6) /* TLV command is possible */ +#define SNDRV_CTL_ELEM_ACCESS_INACTIVE (1<<8) /* control does actually nothing, but may be updated */ +#define SNDRV_CTL_ELEM_ACCESS_LOCK (1<<9) /* write lock */ +#define SNDRV_CTL_ELEM_ACCESS_OWNER (1<<10) /* write lock owner */ +#define SNDRV_CTL_ELEM_ACCESS_TLV_CALLBACK (1<<28) /* kernel use a TLV callback */ +#define SNDRV_CTL_ELEM_ACCESS_USER (1<<29) /* user space element */ +/* bits 30 and 31 are obsoleted (for indirect access) */ + +/* for further details see the ACPI and PCI power management specification */ +#define SNDRV_CTL_POWER_D0 0x0000 /* full On */ +#define SNDRV_CTL_POWER_D1 0x0100 /* partial On */ +#define SNDRV_CTL_POWER_D2 0x0200 /* partial On */ +#define SNDRV_CTL_POWER_D3 0x0300 /* Off */ +#define SNDRV_CTL_POWER_D3hot (SNDRV_CTL_POWER_D3|0x0000) /* Off, with power */ +#define SNDRV_CTL_POWER_D3cold (SNDRV_CTL_POWER_D3|0x0001) /* Off, without power */ + +#define SNDRV_CTL_ELEM_ID_NAME_MAXLEN 44 + +struct snd_ctl_elem_id { + unsigned int numid; /* numeric identifier, zero = invalid */ + snd_ctl_elem_iface_t iface; /* interface identifier */ + unsigned int device; /* device/client number */ + unsigned int subdevice; /* subdevice (substream) number */ + unsigned char name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN]; /* ASCII name of item */ + unsigned int index; /* index of item */ +}; + +struct snd_ctl_elem_list { + unsigned int offset; /* W: first element ID to get */ + unsigned int space; /* W: count of element IDs to get */ + unsigned int used; /* R: count of element IDs set */ + unsigned int count; /* R: count of all elements */ + struct snd_ctl_elem_id __user *pids; /* R: IDs */ + unsigned char reserved[50]; +}; + +struct snd_ctl_elem_info { + struct snd_ctl_elem_id id; /* W: element ID */ + snd_ctl_elem_type_t type; /* R: value type - SNDRV_CTL_ELEM_TYPE_* */ + unsigned int access; /* R: value access (bitmask) - SNDRV_CTL_ELEM_ACCESS_* */ + unsigned int count; /* count of values */ + __kernel_pid_t owner; /* owner's PID of this control */ + union { + struct { + long min; /* R: minimum value */ + long max; /* R: maximum value */ + long step; /* R: step (0 variable) */ + } integer; + struct { + long long min; /* R: minimum value */ + long long max; /* R: maximum value */ + long long step; /* R: step (0 variable) */ + } integer64; + struct { + unsigned int items; /* R: number of items */ + unsigned int item; /* W: item number */ + char name[64]; /* R: value name */ + __u64 names_ptr; /* W: names list (ELEM_ADD only) */ + unsigned int names_length; + } enumerated; + unsigned char reserved[128]; + } value; + union { + unsigned short d[4]; /* dimensions */ + unsigned short *d_ptr; /* indirect - obsoleted */ + } dimen; + unsigned char reserved[64-4*sizeof(unsigned short)]; +}; + +struct snd_ctl_elem_value { + struct snd_ctl_elem_id id; /* W: element ID */ + unsigned int indirect: 1; /* W: indirect access - obsoleted */ + union { + union { + long value[128]; + long *value_ptr; /* obsoleted */ + } integer; + union { + long long value[64]; + long long *value_ptr; /* obsoleted */ + } integer64; + union { + unsigned int item[128]; + unsigned int *item_ptr; /* obsoleted */ + } enumerated; + union { + unsigned char data[512]; + unsigned char *data_ptr; /* obsoleted */ + } bytes; + struct snd_aes_iec958 iec958; + } value; /* RO */ + struct timespec tstamp; + unsigned char reserved[128-sizeof(struct timespec)]; +}; + +struct snd_ctl_tlv { + unsigned int numid; /* control element numeric identification */ + unsigned int length; /* in bytes aligned to 4 */ + unsigned int tlv[0]; /* first TLV */ +}; + +#define SNDRV_CTL_IOCTL_PVERSION _IOR('U', 0x00, int) +#define SNDRV_CTL_IOCTL_CARD_INFO _IOR('U', 0x01, struct snd_ctl_card_info) +#define SNDRV_CTL_IOCTL_ELEM_LIST _IOWR('U', 0x10, struct snd_ctl_elem_list) +#define SNDRV_CTL_IOCTL_ELEM_INFO _IOWR('U', 0x11, struct snd_ctl_elem_info) +#define SNDRV_CTL_IOCTL_ELEM_READ _IOWR('U', 0x12, struct snd_ctl_elem_value) +#define SNDRV_CTL_IOCTL_ELEM_WRITE _IOWR('U', 0x13, struct snd_ctl_elem_value) +#define SNDRV_CTL_IOCTL_ELEM_LOCK _IOW('U', 0x14, struct snd_ctl_elem_id) +#define SNDRV_CTL_IOCTL_ELEM_UNLOCK _IOW('U', 0x15, struct snd_ctl_elem_id) +#define SNDRV_CTL_IOCTL_SUBSCRIBE_EVENTS _IOWR('U', 0x16, int) +#define SNDRV_CTL_IOCTL_ELEM_ADD _IOWR('U', 0x17, struct snd_ctl_elem_info) +#define SNDRV_CTL_IOCTL_ELEM_REPLACE _IOWR('U', 0x18, struct snd_ctl_elem_info) +#define SNDRV_CTL_IOCTL_ELEM_REMOVE _IOWR('U', 0x19, struct snd_ctl_elem_id) +#define SNDRV_CTL_IOCTL_TLV_READ _IOWR('U', 0x1a, struct snd_ctl_tlv) +#define SNDRV_CTL_IOCTL_TLV_WRITE _IOWR('U', 0x1b, struct snd_ctl_tlv) +#define SNDRV_CTL_IOCTL_TLV_COMMAND _IOWR('U', 0x1c, struct snd_ctl_tlv) +#define SNDRV_CTL_IOCTL_HWDEP_NEXT_DEVICE _IOWR('U', 0x20, int) +#define SNDRV_CTL_IOCTL_HWDEP_INFO _IOR('U', 0x21, struct snd_hwdep_info) +#define SNDRV_CTL_IOCTL_PCM_NEXT_DEVICE _IOR('U', 0x30, int) +#define SNDRV_CTL_IOCTL_PCM_INFO _IOWR('U', 0x31, struct snd_pcm_info) +#define SNDRV_CTL_IOCTL_PCM_PREFER_SUBDEVICE _IOW('U', 0x32, int) +#define SNDRV_CTL_IOCTL_RAWMIDI_NEXT_DEVICE _IOWR('U', 0x40, int) +#define SNDRV_CTL_IOCTL_RAWMIDI_INFO _IOWR('U', 0x41, struct snd_rawmidi_info) +#define SNDRV_CTL_IOCTL_RAWMIDI_PREFER_SUBDEVICE _IOW('U', 0x42, int) +#define SNDRV_CTL_IOCTL_POWER _IOWR('U', 0xd0, int) +#define SNDRV_CTL_IOCTL_POWER_STATE _IOR('U', 0xd1, int) + +/* + * Read interface. + */ + +enum sndrv_ctl_event_type { + SNDRV_CTL_EVENT_ELEM = 0, + SNDRV_CTL_EVENT_LAST = SNDRV_CTL_EVENT_ELEM, +}; + +#define SNDRV_CTL_EVENT_MASK_VALUE (1<<0) /* element value was changed */ +#define SNDRV_CTL_EVENT_MASK_INFO (1<<1) /* element info was changed */ +#define SNDRV_CTL_EVENT_MASK_ADD (1<<2) /* element was added */ +#define SNDRV_CTL_EVENT_MASK_TLV (1<<3) /* element TLV tree was changed */ +#define SNDRV_CTL_EVENT_MASK_REMOVE (~0U) /* element was removed */ + +struct snd_ctl_event { + int type; /* event type - SNDRV_CTL_EVENT_* */ + union { + struct { + unsigned int mask; + struct snd_ctl_elem_id id; + } elem; + unsigned char data8[60]; + } data; +}; + +/* + * Control names + */ + +#define SNDRV_CTL_NAME_NONE "" +#define SNDRV_CTL_NAME_PLAYBACK "Playback " +#define SNDRV_CTL_NAME_CAPTURE "Capture " + +#define SNDRV_CTL_NAME_IEC958_NONE "" +#define SNDRV_CTL_NAME_IEC958_SWITCH "Switch" +#define SNDRV_CTL_NAME_IEC958_VOLUME "Volume" +#define SNDRV_CTL_NAME_IEC958_DEFAULT "Default" +#define SNDRV_CTL_NAME_IEC958_MASK "Mask" +#define SNDRV_CTL_NAME_IEC958_CON_MASK "Con Mask" +#define SNDRV_CTL_NAME_IEC958_PRO_MASK "Pro Mask" +#define SNDRV_CTL_NAME_IEC958_PCM_STREAM "PCM Stream" +#define SNDRV_CTL_NAME_IEC958(expl,direction,what) "IEC958 " expl SNDRV_CTL_NAME_##direction SNDRV_CTL_NAME_IEC958_##what + +#endif /* _UAPI__SOUND_ASOUND_H */ diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat index 8f74ed8e7237..32283d88701a 100755 --- a/tools/kvm/kvm_stat/kvm_stat +++ b/tools/kvm/kvm_stat/kvm_stat @@ -295,114 +295,6 @@ class ArchS390(Arch): ARCH = Arch.get_arch() -def walkdir(path): - """Returns os.walk() data for specified directory. - - As it is only a wrapper it returns the same 3-tuple of (dirpath, - dirnames, filenames). - """ - return next(os.walk(path)) - - -def parse_int_list(list_string): - """Returns an int list from a string of comma separated integers and - integer ranges.""" - integers = [] - members = list_string.split(',') - - for member in members: - if '-' not in member: - integers.append(int(member)) - else: - int_range = member.split('-') - integers.extend(range(int(int_range[0]), - int(int_range[1]) + 1)) - - return integers - - -def get_pid_from_gname(gname): - """Fuzzy function to convert guest name to QEMU process pid. - - Returns a list of potential pids, can be empty if no match found. - Throws an exception on processing errors. - - """ - pids = [] - try: - child = subprocess.Popen(['ps', '-A', '--format', 'pid,args'], - stdout=subprocess.PIPE) - except: - raise Exception - for line in child.stdout: - line = line.lstrip().split(' ', 1) - # perform a sanity check before calling the more expensive - # function to possibly extract the guest name - if ' -name ' in line[1] and gname == get_gname_from_pid(line[0]): - pids.append(int(line[0])) - child.stdout.close() - - return pids - - -def get_gname_from_pid(pid): - """Returns the guest name for a QEMU process pid. - - Extracts the guest name from the QEMU comma line by processing the '-name' - option. Will also handle names specified out of sequence. - - """ - name = '' - try: - line = open('/proc/{}/cmdline'.format(pid), 'rb').read().split('\0') - parms = line[line.index('-name') + 1].split(',') - while '' in parms: - # commas are escaped (i.e. ',,'), hence e.g. 'foo,bar' results in - # ['foo', '', 'bar'], which we revert here - idx = parms.index('') - parms[idx - 1] += ',' + parms[idx + 1] - del parms[idx:idx+2] - # the '-name' switch allows for two ways to specify the guest name, - # where the plain name overrides the name specified via 'guest=' - for arg in parms: - if '=' not in arg: - name = arg - break - if arg[:6] == 'guest=': - name = arg[6:] - except (ValueError, IOError, IndexError): - pass - - return name - - -def get_online_cpus(): - """Returns a list of cpu id integers.""" - with open('/sys/devices/system/cpu/online') as cpu_list: - cpu_string = cpu_list.readline() - return parse_int_list(cpu_string) - - -def get_filters(): - """Returns a dict of trace events, their filter ids and - the values that can be filtered. - - Trace events can be filtered for special values by setting a - filter string via an ioctl. The string normally has the format - identifier==value. For each filter a new event will be created, to - be able to distinguish the events. - - """ - filters = {} - filters['kvm_userspace_exit'] = ('reason', USERSPACE_EXIT_REASONS) - if ARCH.exit_reasons: - filters['kvm_exit'] = ('exit_reason', ARCH.exit_reasons) - return filters - -libc = ctypes.CDLL('libc.so.6', use_errno=True) -syscall = libc.syscall - - class perf_event_attr(ctypes.Structure): """Struct that holds the necessary data to set up a trace event. @@ -432,25 +324,6 @@ class perf_event_attr(ctypes.Structure): self.read_format = PERF_FORMAT_GROUP -def perf_event_open(attr, pid, cpu, group_fd, flags): - """Wrapper for the sys_perf_evt_open() syscall. - - Used to set up performance events, returns a file descriptor or -1 - on error. - - Attributes are: - - syscall number - - struct perf_event_attr * - - pid or -1 to monitor all pids - - cpu number or -1 to monitor all cpus - - The file descriptor of the group leader or -1 to create a group. - - flags - - """ - return syscall(ARCH.sc_perf_evt_open, ctypes.pointer(attr), - ctypes.c_int(pid), ctypes.c_int(cpu), - ctypes.c_int(group_fd), ctypes.c_long(flags)) - PERF_TYPE_TRACEPOINT = 2 PERF_FORMAT_GROUP = 1 << 3 @@ -495,6 +368,8 @@ class Event(object): """Represents a performance event and manages its life cycle.""" def __init__(self, name, group, trace_cpu, trace_pid, trace_point, trace_filter, trace_set='kvm'): + self.libc = ctypes.CDLL('libc.so.6', use_errno=True) + self.syscall = self.libc.syscall self.name = name self.fd = None self.setup_event(group, trace_cpu, trace_pid, trace_point, @@ -511,6 +386,25 @@ class Event(object): if self.fd: os.close(self.fd) + def perf_event_open(self, attr, pid, cpu, group_fd, flags): + """Wrapper for the sys_perf_evt_open() syscall. + + Used to set up performance events, returns a file descriptor or -1 + on error. + + Attributes are: + - syscall number + - struct perf_event_attr * + - pid or -1 to monitor all pids + - cpu number or -1 to monitor all cpus + - The file descriptor of the group leader or -1 to create a group. + - flags + + """ + return self.syscall(ARCH.sc_perf_evt_open, ctypes.pointer(attr), + ctypes.c_int(pid), ctypes.c_int(cpu), + ctypes.c_int(group_fd), ctypes.c_long(flags)) + def setup_event_attribute(self, trace_set, trace_point): """Returns an initialized ctype perf_event_attr struct.""" @@ -539,8 +433,8 @@ class Event(object): if group.events: group_leader = group.events[0].fd - fd = perf_event_open(event_attr, trace_pid, - trace_cpu, group_leader, 0) + fd = self.perf_event_open(event_attr, trace_pid, + trace_cpu, group_leader, 0) if fd == -1: err = ctypes.get_errno() raise OSError(err, os.strerror(err), @@ -575,17 +469,53 @@ class Event(object): fcntl.ioctl(self.fd, ARCH.ioctl_numbers['RESET'], 0) -class TracepointProvider(object): +class Provider(object): + """Encapsulates functionalities used by all providers.""" + @staticmethod + def is_field_wanted(fields_filter, field): + """Indicate whether field is valid according to fields_filter.""" + if not fields_filter or fields_filter == "help": + return True + return re.match(fields_filter, field) is not None + + @staticmethod + def walkdir(path): + """Returns os.walk() data for specified directory. + + As it is only a wrapper it returns the same 3-tuple of (dirpath, + dirnames, filenames). + """ + return next(os.walk(path)) + + +class TracepointProvider(Provider): """Data provider for the stats class. Manages the events/groups from which it acquires its data. """ - def __init__(self): + def __init__(self, pid, fields_filter): self.group_leaders = [] - self.filters = get_filters() - self._fields = self.get_available_fields() - self._pid = 0 + self.filters = self.get_filters() + self.update_fields(fields_filter) + self.pid = pid + + @staticmethod + def get_filters(): + """Returns a dict of trace events, their filter ids and + the values that can be filtered. + + Trace events can be filtered for special values by setting a + filter string via an ioctl. The string normally has the format + identifier==value. For each filter a new event will be created, to + be able to distinguish the events. + + """ + filters = {} + filters['kvm_userspace_exit'] = ('reason', USERSPACE_EXIT_REASONS) + if ARCH.exit_reasons: + filters['kvm_exit'] = ('exit_reason', ARCH.exit_reasons) + return filters def get_available_fields(self): """Returns a list of available event's of format 'event name(filter @@ -603,7 +533,7 @@ class TracepointProvider(object): """ path = os.path.join(PATH_DEBUGFS_TRACING, 'events', 'kvm') - fields = walkdir(path)[1] + fields = self.walkdir(path)[1] extra = [] for field in fields: if field in self.filters: @@ -613,6 +543,34 @@ class TracepointProvider(object): fields += extra return fields + def update_fields(self, fields_filter): + """Refresh fields, applying fields_filter""" + self._fields = [field for field in self.get_available_fields() + if self.is_field_wanted(fields_filter, field)] + + @staticmethod + def get_online_cpus(): + """Returns a list of cpu id integers.""" + def parse_int_list(list_string): + """Returns an int list from a string of comma separated integers and + integer ranges.""" + integers = [] + members = list_string.split(',') + + for member in members: + if '-' not in member: + integers.append(int(member)) + else: + int_range = member.split('-') + integers.extend(range(int(int_range[0]), + int(int_range[1]) + 1)) + + return integers + + with open('/sys/devices/system/cpu/online') as cpu_list: + cpu_string = cpu_list.readline() + return parse_int_list(cpu_string) + def setup_traces(self): """Creates all event and group objects needed to be able to retrieve data.""" @@ -621,9 +579,9 @@ class TracepointProvider(object): # Fetch list of all threads of the monitored pid, as qemu # starts a thread for each vcpu. path = os.path.join('/proc', str(self._pid), 'task') - groupids = walkdir(path)[1] + groupids = self.walkdir(path)[1] else: - groupids = get_online_cpus() + groupids = self.get_online_cpus() # The constant is needed as a buffer for python libs, std # streams and other files that the script opens. @@ -671,9 +629,6 @@ class TracepointProvider(object): self.group_leaders.append(group) - def available_fields(self): - return self.get_available_fields() - @property def fields(self): return self._fields @@ -707,7 +662,7 @@ class TracepointProvider(object): self.setup_traces() self.fields = self._fields - def read(self): + def read(self, by_guest=0): """Returns 'event name: current value' for all enabled events.""" ret = defaultdict(int) for group in self.group_leaders: @@ -723,16 +678,17 @@ class TracepointProvider(object): event.reset() -class DebugfsProvider(object): +class DebugfsProvider(Provider): """Provides data from the files that KVM creates in the kvm debugfs folder.""" - def __init__(self): - self._fields = self.get_available_fields() + def __init__(self, pid, fields_filter, include_past): + self.update_fields(fields_filter) self._baseline = {} - self._pid = 0 self.do_read = True self.paths = [] - self.reset() + self.pid = pid + if include_past: + self.restore() def get_available_fields(self): """"Returns a list of available fields. @@ -740,7 +696,12 @@ class DebugfsProvider(object): The fields are all available KVM debugfs files """ - return walkdir(PATH_DEBUGFS_KVM)[2] + return self.walkdir(PATH_DEBUGFS_KVM)[2] + + def update_fields(self, fields_filter): + """Refresh fields, applying fields_filter""" + self._fields = [field for field in self.get_available_fields() + if self.is_field_wanted(fields_filter, field)] @property def fields(self): @@ -757,10 +718,9 @@ class DebugfsProvider(object): @pid.setter def pid(self, pid): + self._pid = pid if pid != 0: - self._pid = pid - - vms = walkdir(PATH_DEBUGFS_KVM)[1] + vms = self.walkdir(PATH_DEBUGFS_KVM)[1] if len(vms) == 0: self.do_read = False @@ -771,8 +731,15 @@ class DebugfsProvider(object): self.do_read = True self.reset() - def read(self, reset=0): - """Returns a dict with format:'file name / field -> current value'.""" + def read(self, reset=0, by_guest=0): + """Returns a dict with format:'file name / field -> current value'. + + Parameter 'reset': + 0 plain read + 1 reset field counts to 0 + 2 restore the original field counts + + """ results = {} # If no debugfs filtering support is available, then don't read. @@ -789,12 +756,22 @@ class DebugfsProvider(object): for field in self._fields: value = self.read_field(field, path) key = path + field - if reset: + if reset == 1: self._baseline[key] = value + if reset == 2: + self._baseline[key] = 0 if self._baseline.get(key, -1) == -1: self._baseline[key] = value - results[field] = (results.get(field, 0) + value - - self._baseline.get(key, 0)) + increment = (results.get(field, 0) + value - + self._baseline.get(key, 0)) + if by_guest: + pid = key.split('-')[0] + if pid in results: + results[pid] += increment + else: + results[pid] = increment + else: + results[field] = increment return results @@ -813,6 +790,11 @@ class DebugfsProvider(object): self._baseline = {} self.read(1) + def restore(self): + """Reset field counters""" + self._baseline = {} + self.read(2) + class Stats(object): """Manages the data providers and the data they provide. @@ -821,33 +803,32 @@ class Stats(object): provider data. """ - def __init__(self, providers, pid, fields=None): - self.providers = providers - self._pid_filter = pid - self._fields_filter = fields + def __init__(self, options): + self.providers = self.get_providers(options) + self._pid_filter = options.pid + self._fields_filter = options.fields self.values = {} - self.update_provider_pid() - self.update_provider_filters() + + @staticmethod + def get_providers(options): + """Returns a list of data providers depending on the passed options.""" + providers = [] + + if options.debugfs: + providers.append(DebugfsProvider(options.pid, options.fields, + options.dbgfs_include_past)) + if options.tracepoints or not providers: + providers.append(TracepointProvider(options.pid, options.fields)) + + return providers def update_provider_filters(self): """Propagates fields filters to providers.""" - def wanted(key): - if not self._fields_filter: - return True - return re.match(self._fields_filter, key) is not None - # As we reset the counters when updating the fields we can # also clear the cache of old values. self.values = {} for provider in self.providers: - provider_fields = [key for key in provider.get_available_fields() - if wanted(key)] - provider.fields = provider_fields - - def update_provider_pid(self): - """Propagates pid filters to providers.""" - for provider in self.providers: - provider.pid = self._pid_filter + provider.update_fields(self._fields_filter) def reset(self): self.values = {} @@ -873,27 +854,52 @@ class Stats(object): if pid != self._pid_filter: self._pid_filter = pid self.values = {} - self.update_provider_pid() + for provider in self.providers: + provider.pid = self._pid_filter - def get(self): + def get(self, by_guest=0): """Returns a dict with field -> (value, delta to last value) of all provider data.""" for provider in self.providers: - new = provider.read() - for key in provider.fields: + new = provider.read(by_guest=by_guest) + for key in new if by_guest else provider.fields: oldval = self.values.get(key, (0, 0))[0] newval = new.get(key, 0) newdelta = newval - oldval self.values[key] = (newval, newdelta) return self.values -LABEL_WIDTH = 40 -NUMBER_WIDTH = 10 -DELAY_INITIAL = 0.25 -DELAY_REGULAR = 3.0 + def toggle_display_guests(self, to_pid): + """Toggle between collection of stats by individual event and by + guest pid + + Events reported by DebugfsProvider change when switching to/from + reading by guest values. Hence we have to remove the excess event + names from self.values. + + """ + if any(isinstance(ins, TracepointProvider) for ins in self.providers): + return 1 + if to_pid: + for provider in self.providers: + if isinstance(provider, DebugfsProvider): + for key in provider.fields: + if key in self.values.keys(): + del self.values[key] + else: + oldvals = self.values.copy() + for key in oldvals: + if key.isdigit(): + del self.values[key] + # Update oldval (see get()) + self.get(to_pid) + return 0 + +DELAY_DEFAULT = 3.0 MAX_GUEST_NAME_LEN = 48 MAX_REGEX_LEN = 44 DEFAULT_REGEX = r'^[^\(]*$' +SORT_DEFAULT = 0 class Tui(object): @@ -901,7 +907,10 @@ class Tui(object): def __init__(self, stats): self.stats = stats self.screen = None - self.update_drilldown() + self._delay_initial = 0.25 + self._delay_regular = DELAY_DEFAULT + self._sorting = SORT_DEFAULT + self._display_guests = 0 def __enter__(self): """Initialises curses for later use. Based on curses.wrapper @@ -929,7 +938,7 @@ class Tui(object): return self def __exit__(self, *exception): - """Resets the terminal to its normal state. Based on curses.wrappre + """Resets the terminal to its normal state. Based on curses.wrapper implementation from the Python standard library.""" if self.screen: self.screen.keypad(0) @@ -937,6 +946,86 @@ class Tui(object): curses.nocbreak() curses.endwin() + def get_all_gnames(self): + """Returns a list of (pid, gname) tuples of all running guests""" + res = [] + try: + child = subprocess.Popen(['ps', '-A', '--format', 'pid,args'], + stdout=subprocess.PIPE) + except: + raise Exception + for line in child.stdout: + line = line.lstrip().split(' ', 1) + # perform a sanity check before calling the more expensive + # function to possibly extract the guest name + if ' -name ' in line[1]: + res.append((line[0], self.get_gname_from_pid(line[0]))) + child.stdout.close() + + return res + + def print_all_gnames(self, row): + """Print a list of all running guests along with their pids.""" + self.screen.addstr(row, 2, '%8s %-60s' % + ('Pid', 'Guest Name (fuzzy list, might be ' + 'inaccurate!)'), + curses.A_UNDERLINE) + row += 1 + try: + for line in self.get_all_gnames(): + self.screen.addstr(row, 2, '%8s %-60s' % (line[0], line[1])) + row += 1 + if row >= self.screen.getmaxyx()[0]: + break + except Exception: + self.screen.addstr(row + 1, 2, 'Not available') + + def get_pid_from_gname(self, gname): + """Fuzzy function to convert guest name to QEMU process pid. + + Returns a list of potential pids, can be empty if no match found. + Throws an exception on processing errors. + + """ + pids = [] + for line in self.get_all_gnames(): + if gname == line[1]: + pids.append(int(line[0])) + + return pids + + @staticmethod + def get_gname_from_pid(pid): + """Returns the guest name for a QEMU process pid. + + Extracts the guest name from the QEMU comma line by processing the + '-name' option. Will also handle names specified out of sequence. + + """ + name = '' + try: + line = open('/proc/{}/cmdline' + .format(pid), 'rb').read().split('\0') + parms = line[line.index('-name') + 1].split(',') + while '' in parms: + # commas are escaped (i.e. ',,'), hence e.g. 'foo,bar' results + # in # ['foo', '', 'bar'], which we revert here + idx = parms.index('') + parms[idx - 1] += ',' + parms[idx + 1] + del parms[idx:idx+2] + # the '-name' switch allows for two ways to specify the guest name, + # where the plain name overrides the name specified via 'guest=' + for arg in parms: + if '=' not in arg: + name = arg + break + if arg[:6] == 'guest=': + name = arg[6:] + except (ValueError, IOError, IndexError): + pass + + return name + def update_drilldown(self): """Sets or removes a filter that only allows fields without braces.""" if not self.stats.fields_filter: @@ -954,7 +1043,7 @@ class Tui(object): if pid is None: pid = self.stats.pid_filter self.screen.erase() - gname = get_gname_from_pid(pid) + gname = self.get_gname_from_pid(pid) if gname: gname = ('({})'.format(gname[:MAX_GUEST_NAME_LEN] + '...' if len(gname) > MAX_GUEST_NAME_LEN @@ -970,13 +1059,13 @@ class Tui(object): if len(regex) > MAX_REGEX_LEN: regex = regex[:MAX_REGEX_LEN] + '...' self.screen.addstr(1, 17, 'regex filter: {0}'.format(regex)) - self.screen.addstr(2, 1, 'Event') - self.screen.addstr(2, 1 + LABEL_WIDTH + NUMBER_WIDTH - - len('Total'), 'Total') - self.screen.addstr(2, 1 + LABEL_WIDTH + NUMBER_WIDTH + 7 - - len('%Total'), '%Total') - self.screen.addstr(2, 1 + LABEL_WIDTH + NUMBER_WIDTH + 7 + 8 - - len('Current'), 'Current') + if self._display_guests: + col_name = 'Guest Name' + else: + col_name = 'Event' + self.screen.addstr(2, 1, '%-40s %10s%7s %8s' % + (col_name, 'Total', '%Total', 'CurAvg/s'), + curses.A_STANDOUT) self.screen.addstr(4, 1, 'Collecting data...') self.screen.refresh() @@ -984,16 +1073,25 @@ class Tui(object): row = 3 self.screen.move(row, 0) self.screen.clrtobot() - stats = self.stats.get() + stats = self.stats.get(self._display_guests) - def sortkey(x): + def sortCurAvg(x): + # sort by current events if available if stats[x][1]: return (-stats[x][1], -stats[x][0]) else: return (0, -stats[x][0]) + + def sortTotal(x): + # sort by totals + return (0, -stats[x][0]) total = 0. for val in stats.values(): total += val[0] + if self._sorting == SORT_DEFAULT: + sortkey = sortCurAvg + else: + sortkey = sortTotal for key in sorted(stats.keys(), key=sortkey): if row >= self.screen.getmaxyx()[0]: @@ -1001,18 +1099,61 @@ class Tui(object): values = stats[key] if not values[0] and not values[1]: break - col = 1 - self.screen.addstr(row, col, key) - col += LABEL_WIDTH - self.screen.addstr(row, col, '%10d' % (values[0],)) - col += NUMBER_WIDTH - self.screen.addstr(row, col, '%7.1f' % (values[0] * 100 / total,)) - col += 7 - if values[1] is not None: - self.screen.addstr(row, col, '%8d' % (values[1] / sleeptime,)) + if values[0] is not None: + cur = int(round(values[1] / sleeptime)) if values[1] else '' + if self._display_guests: + key = self.get_gname_from_pid(key) + self.screen.addstr(row, 1, '%-40s %10d%7.1f %8s' % + (key, values[0], values[0] * 100 / total, + cur)) row += 1 + if row == 3: + self.screen.addstr(4, 1, 'No matching events reported yet') self.screen.refresh() + def show_msg(self, text): + """Display message centered text and exit on key press""" + hint = 'Press any key to continue' + curses.cbreak() + self.screen.erase() + (x, term_width) = self.screen.getmaxyx() + row = 2 + for line in text: + start = (term_width - len(line)) / 2 + self.screen.addstr(row, start, line) + row += 1 + self.screen.addstr(row + 1, (term_width - len(hint)) / 2, hint, + curses.A_STANDOUT) + self.screen.getkey() + + def show_help_interactive(self): + """Display help with list of interactive commands""" + msg = (' b toggle events by guests (debugfs only, honors' + ' filters)', + ' c clear filter', + ' f filter by regular expression', + ' g filter by guest name', + ' h display interactive commands reference', + ' o toggle sorting order (Total vs CurAvg/s)', + ' p filter by PID', + ' q quit', + ' r reset stats', + ' s set update interval', + ' x toggle reporting of stats for individual child trace' + ' events', + 'Any other key refreshes statistics immediately') + curses.cbreak() + self.screen.erase() + self.screen.addstr(0, 0, "Interactive commands reference", + curses.A_BOLD) + self.screen.addstr(2, 0, "Press any key to exit", curses.A_STANDOUT) + row = 4 + for line in msg: + self.screen.addstr(row, 0, line) + row += 1 + self.screen.getkey() + self.refresh_header() + def show_filter_selection(self): """Draws filter selection mask. @@ -1059,6 +1200,7 @@ class Tui(object): 'This might limit the shown data to the trace ' 'statistics.') self.screen.addstr(5, 0, msg) + self.print_all_gnames(7) curses.echo() self.screen.addstr(3, 0, "Pid [0 or pid]: ") @@ -1077,10 +1219,40 @@ class Tui(object): self.refresh_header(pid) self.update_pid(pid) break - except ValueError: msg = '"' + str(pid) + '": Not a valid pid' - continue + + def show_set_update_interval(self): + """Draws update interval selection mask.""" + msg = '' + while True: + self.screen.erase() + self.screen.addstr(0, 0, 'Set update interval (defaults to %fs).' % + DELAY_DEFAULT, curses.A_BOLD) + self.screen.addstr(4, 0, msg) + self.screen.addstr(2, 0, 'Change delay from %.1fs to ' % + self._delay_regular) + curses.echo() + val = self.screen.getstr() + curses.noecho() + + try: + if len(val) > 0: + delay = float(val) + if delay < 0.1: + msg = '"' + str(val) + '": Value must be >=0.1' + continue + if delay > 25.5: + msg = '"' + str(val) + '": Value must be <=25.5' + continue + else: + delay = DELAY_DEFAULT + self._delay_regular = delay + break + + except ValueError: + msg = '"' + str(val) + '": Invalid value' + self.refresh_header() def show_vm_selection_by_guest_name(self): """Draws guest selection mask. @@ -1098,6 +1270,7 @@ class Tui(object): 'This might limit the shown data to the trace ' 'statistics.') self.screen.addstr(5, 0, msg) + self.print_all_gnames(7) curses.echo() self.screen.addstr(3, 0, "Guest [ENTER or guest]: ") gname = self.screen.getstr() @@ -1110,7 +1283,7 @@ class Tui(object): else: pids = [] try: - pids = get_pid_from_gname(gname) + pids = self.get_pid_from_gname(gname) except: msg = '"' + gname + '": Internal error while searching, ' \ 'use pid filter instead' @@ -1128,38 +1301,60 @@ class Tui(object): def show_stats(self): """Refreshes the screen and processes user input.""" - sleeptime = DELAY_INITIAL + sleeptime = self._delay_initial self.refresh_header() + start = 0.0 # result based on init value never appears on screen while True: - self.refresh_body(sleeptime) + self.refresh_body(time.time() - start) curses.halfdelay(int(sleeptime * 10)) - sleeptime = DELAY_REGULAR + start = time.time() + sleeptime = self._delay_regular try: char = self.screen.getkey() - if char == 'x': + if char == 'b': + self._display_guests = not self._display_guests + if self.stats.toggle_display_guests(self._display_guests): + self.show_msg(['Command not available with tracepoints' + ' enabled', 'Restart with debugfs only ' + '(see option \'-d\') and try again!']) + self._display_guests = not self._display_guests self.refresh_header() - self.update_drilldown() - sleeptime = DELAY_INITIAL - if char == 'q': - break if char == 'c': self.stats.fields_filter = DEFAULT_REGEX self.refresh_header(0) self.update_pid(0) - sleeptime = DELAY_INITIAL if char == 'f': + curses.curs_set(1) self.show_filter_selection() - sleeptime = DELAY_INITIAL + curses.curs_set(0) + sleeptime = self._delay_initial if char == 'g': + curses.curs_set(1) self.show_vm_selection_by_guest_name() - sleeptime = DELAY_INITIAL + curses.curs_set(0) + sleeptime = self._delay_initial + if char == 'h': + self.show_help_interactive() + if char == 'o': + self._sorting = not self._sorting if char == 'p': + curses.curs_set(1) self.show_vm_selection_by_pid() - sleeptime = DELAY_INITIAL + curses.curs_set(0) + sleeptime = self._delay_initial + if char == 'q': + break if char == 'r': - self.refresh_header() self.stats.reset() - sleeptime = DELAY_INITIAL + if char == 's': + curses.curs_set(1) + self.show_set_update_interval() + curses.curs_set(0) + sleeptime = self._delay_initial + if char == 'x': + self.update_drilldown() + # prevents display of current values on next refresh + self.stats.get() except KeyboardInterrupt: break except curses.error: @@ -1218,8 +1413,8 @@ performance. Requirements: - Access to: - /sys/kernel/debug/kvm - /sys/kernel/debug/trace/events/* + %s + %s/events/* /proc/pid/task - /proc/sys/kernel/perf_event_paranoid < 1 if user has no CAP_SYS_ADMIN and perf events are used. @@ -1227,15 +1422,19 @@ Requirements: the large number of files that are possibly opened. Interactive Commands: + b toggle events by guests (debugfs only, honors filters) c clear filter f filter by regular expression g filter by guest name + h display interactive commands reference + o toggle sorting order (Total vs CurAvg/s) p filter by PID q quit - x toggle reporting of stats for individual child trace events r reset stats + s set update interval + x toggle reporting of stats for individual child trace events Press any other key to refresh statistics immediately. -""" +""" % (PATH_DEBUGFS_KVM, PATH_DEBUGFS_TRACING) class PlainHelpFormatter(optparse.IndentedHelpFormatter): def format_description(self, description): @@ -1246,7 +1445,7 @@ Press any other key to refresh statistics immediately. def cb_guest_to_pid(option, opt, val, parser): try: - pids = get_pid_from_gname(val) + pids = Tui.get_pid_from_gname(val) except: raise optparse.OptionValueError('Error while searching for guest ' '"{}", use "-p" to specify a pid ' @@ -1268,6 +1467,13 @@ Press any other key to refresh statistics immediately. dest='once', help='run in batch mode for one second', ) + optparser.add_option('-i', '--debugfs-include-past', + action='store_true', + default=False, + dest='dbgfs_include_past', + help='include all available data on past events for ' + 'debugfs', + ) optparser.add_option('-l', '--log', action='store_true', default=False, @@ -1288,9 +1494,10 @@ Press any other key to refresh statistics immediately. ) optparser.add_option('-f', '--fields', action='store', - default=None, + default=DEFAULT_REGEX, dest='fields', - help='fields to display (regex)', + help='''fields to display (regex) + "-f help" for a list of available events''', ) optparser.add_option('-p', '--pid', action='store', @@ -1311,20 +1518,6 @@ Press any other key to refresh statistics immediately. return options -def get_providers(options): - """Returns a list of data providers depending on the passed options.""" - providers = [] - - if options.tracepoints: - providers.append(TracepointProvider()) - if options.debugfs: - providers.append(DebugfsProvider()) - if len(providers) == 0: - providers.append(TracepointProvider()) - - return providers - - def check_access(options): """Exits if the current user can't access all needed directories.""" if not os.path.exists('/sys/kernel/debug'): @@ -1365,8 +1558,18 @@ def main(): sys.stderr.write('Did you use a (unsupported) tid instead of a pid?\n') sys.exit('Specified pid does not exist.') - providers = get_providers(options) - stats = Stats(providers, options.pid, fields=options.fields) + stats = Stats(options) + + if options.fields == "help": + event_list = "\n" + s = stats.get() + for key in s.keys(): + if key.find('(') != -1: + key = key[0:key.find('(')] + if event_list.find('\n' + key + '\n') == -1: + event_list += key + '\n' + sys.stdout.write(event_list) + return "" if options.log: log(stats) diff --git a/tools/kvm/kvm_stat/kvm_stat.txt b/tools/kvm/kvm_stat/kvm_stat.txt index 109431bdc63c..e5cf836be8a1 100644 --- a/tools/kvm/kvm_stat/kvm_stat.txt +++ b/tools/kvm/kvm_stat/kvm_stat.txt @@ -29,18 +29,26 @@ meaning of events. INTERACTIVE COMMANDS -------------------- [horizontal] +*b*:: toggle events by guests (debugfs only, honors filters) + *c*:: clear filter *f*:: filter by regular expression *g*:: filter by guest name +*h*:: display interactive commands reference + +*o*:: toggle sorting order (Total vs CurAvg/s) + *p*:: filter by PID *q*:: quit *r*:: reset stats +*s*:: set update interval + *x*:: toggle reporting of stats for child trace events Press any other key to refresh statistics immediately. @@ -64,6 +72,10 @@ OPTIONS --debugfs:: retrieve statistics from debugfs +-i:: +--debugfs-include-past:: + include all available data on past events for debugfs + -p<pid>:: --pid=<pid>:: limit statistics to one virtual machine (pid) diff --git a/tools/lguest/.gitignore b/tools/lguest/.gitignore deleted file mode 100644 index 8d9a8383a52e..000000000000 --- a/tools/lguest/.gitignore +++ /dev/null @@ -1,2 +0,0 @@ -lguest -include diff --git a/tools/lguest/Makefile b/tools/lguest/Makefile deleted file mode 100644 index d04599a79802..000000000000 --- a/tools/lguest/Makefile +++ /dev/null @@ -1,14 +0,0 @@ -# This creates the demonstration utility "lguest" which runs a Linux guest. -CFLAGS:=-m32 -Wall -Wmissing-declarations -Wmissing-prototypes -O3 -U_FORTIFY_SOURCE -Iinclude - -all: lguest - -include/linux/virtio_types.h: ../../include/uapi/linux/virtio_types.h - mkdir -p include/linux 2>&1 || true - ln -sf ../../../../include/uapi/linux/virtio_types.h $@ - -lguest: include/linux/virtio_types.h - -clean: - rm -f lguest - rm -rf include diff --git a/tools/lguest/extract b/tools/lguest/extract deleted file mode 100644 index 7730bb6e4b94..000000000000 --- a/tools/lguest/extract +++ /dev/null @@ -1,58 +0,0 @@ -#! /bin/sh - -set -e - -PREFIX=$1 -shift - -trap 'rm -r $TMPDIR' 0 -TMPDIR=`mktemp -d` - -exec 3>/dev/null -for f; do - while IFS=" -" read -r LINE; do - case "$LINE" in - *$PREFIX:[0-9]*:\**) - NUM=`echo "$LINE" | sed "s/.*$PREFIX:\([0-9]*\).*/\1/"` - if [ -f $TMPDIR/$NUM ]; then - echo "$TMPDIR/$NUM already exits prior to $f" - exit 1 - fi - exec 3>>$TMPDIR/$NUM - echo $f | sed 's,\.\./,,g' > $TMPDIR/.$NUM - /bin/echo "$LINE" | sed -e "s/$PREFIX:[0-9]*//" -e "s/:\*/*/" >&3 - ;; - *$PREFIX:[0-9]*) - NUM=`echo "$LINE" | sed "s/.*$PREFIX:\([0-9]*\).*/\1/"` - if [ -f $TMPDIR/$NUM ]; then - echo "$TMPDIR/$NUM already exits prior to $f" - exit 1 - fi - exec 3>>$TMPDIR/$NUM - echo $f | sed 's,\.\./,,g' > $TMPDIR/.$NUM - /bin/echo "$LINE" | sed "s/$PREFIX:[0-9]*//" >&3 - ;; - *:\**) - /bin/echo "$LINE" | sed -e "s/:\*/*/" -e "s,/\*\*/,," >&3 - echo >&3 - exec 3>/dev/null - ;; - *) - /bin/echo "$LINE" >&3 - ;; - esac - done < $f - echo >&3 - exec 3>/dev/null -done - -LASTFILE="" -for f in $TMPDIR/*; do - if [ "$LASTFILE" != $(cat $TMPDIR/.$(basename $f) ) ]; then - LASTFILE=$(cat $TMPDIR/.$(basename $f) ) - echo "[ $LASTFILE ]" - fi - cat $f -done - diff --git a/tools/lguest/lguest.c b/tools/lguest/lguest.c deleted file mode 100644 index 897cd6f3f687..000000000000 --- a/tools/lguest/lguest.c +++ /dev/null @@ -1,3420 +0,0 @@ -/*P:100 - * This is the Launcher code, a simple program which lays out the "physical" - * memory for the new Guest by mapping the kernel image and the virtual - * devices, then opens /dev/lguest to tell the kernel about the Guest and - * control it. -:*/ -#define _LARGEFILE64_SOURCE -#define _GNU_SOURCE -#include <stdio.h> -#include <string.h> -#include <unistd.h> -#include <err.h> -#include <stdint.h> -#include <stdlib.h> -#include <elf.h> -#include <sys/mman.h> -#include <sys/param.h> -#include <sys/types.h> -#include <sys/stat.h> -#include <sys/wait.h> -#include <sys/eventfd.h> -#include <fcntl.h> -#include <stdbool.h> -#include <errno.h> -#include <ctype.h> -#include <sys/socket.h> -#include <sys/ioctl.h> -#include <sys/time.h> -#include <time.h> -#include <netinet/in.h> -#include <net/if.h> -#include <linux/sockios.h> -#include <linux/if_tun.h> -#include <sys/uio.h> -#include <termios.h> -#include <getopt.h> -#include <assert.h> -#include <sched.h> -#include <limits.h> -#include <stddef.h> -#include <signal.h> -#include <pwd.h> -#include <grp.h> -#include <sys/user.h> -#include <linux/pci_regs.h> - -#ifndef VIRTIO_F_ANY_LAYOUT -#define VIRTIO_F_ANY_LAYOUT 27 -#endif - -/*L:110 - * We can ignore the 43 include files we need for this program, but I do want - * to draw attention to the use of kernel-style types. - * - * As Linus said, "C is a Spartan language, and so should your naming be." I - * like these abbreviations, so we define them here. Note that u64 is always - * unsigned long long, which works on all Linux systems: this means that we can - * use %llu in printf for any u64. - */ -typedef unsigned long long u64; -typedef uint32_t u32; -typedef uint16_t u16; -typedef uint8_t u8; -/*:*/ - -#define VIRTIO_CONFIG_NO_LEGACY -#define VIRTIO_PCI_NO_LEGACY -#define VIRTIO_BLK_NO_LEGACY -#define VIRTIO_NET_NO_LEGACY - -/* Use in-kernel ones, which defines VIRTIO_F_VERSION_1 */ -#include "../../include/uapi/linux/virtio_config.h" -#include "../../include/uapi/linux/virtio_net.h" -#include "../../include/uapi/linux/virtio_blk.h" -#include "../../include/uapi/linux/virtio_console.h" -#include "../../include/uapi/linux/virtio_rng.h" -#include <linux/virtio_ring.h> -#include "../../include/uapi/linux/virtio_pci.h" -#include <asm/bootparam.h> -#include "../../include/linux/lguest_launcher.h" - -#define BRIDGE_PFX "bridge:" -#ifndef SIOCBRADDIF -#define SIOCBRADDIF 0x89a2 /* add interface to bridge */ -#endif -/* We can have up to 256 pages for devices. */ -#define DEVICE_PAGES 256 -/* This will occupy 3 pages: it must be a power of 2. */ -#define VIRTQUEUE_NUM 256 - -/*L:120 - * verbose is both a global flag and a macro. The C preprocessor allows - * this, and although I wouldn't recommend it, it works quite nicely here. - */ -static bool verbose; -#define verbose(args...) \ - do { if (verbose) printf(args); } while(0) -/*:*/ - -/* The pointer to the start of guest memory. */ -static void *guest_base; -/* The maximum guest physical address allowed, and maximum possible. */ -static unsigned long guest_limit, guest_max, guest_mmio; -/* The /dev/lguest file descriptor. */ -static int lguest_fd; - -/* a per-cpu variable indicating whose vcpu is currently running */ -static unsigned int __thread cpu_id; - -/* 5 bit device number in the PCI_CONFIG_ADDR => 32 only */ -#define MAX_PCI_DEVICES 32 - -/* This is our list of devices. */ -struct device_list { - /* Counter to assign interrupt numbers. */ - unsigned int next_irq; - - /* Counter to print out convenient device numbers. */ - unsigned int device_num; - - /* PCI devices. */ - struct device *pci[MAX_PCI_DEVICES]; -}; - -/* The list of Guest devices, based on command line arguments. */ -static struct device_list devices; - -/* - * Just like struct virtio_pci_cfg_cap in uapi/linux/virtio_pci.h, - * but uses a u32 explicitly for the data. - */ -struct virtio_pci_cfg_cap_u32 { - struct virtio_pci_cap cap; - u32 pci_cfg_data; /* Data for BAR access. */ -}; - -struct virtio_pci_mmio { - struct virtio_pci_common_cfg cfg; - u16 notify; - u8 isr; - u8 padding; - /* Device-specific configuration follows this. */ -}; - -/* This is the layout (little-endian) of the PCI config space. */ -struct pci_config { - u16 vendor_id, device_id; - u16 command, status; - u8 revid, prog_if, subclass, class; - u8 cacheline_size, lat_timer, header_type, bist; - u32 bar[6]; - u32 cardbus_cis_ptr; - u16 subsystem_vendor_id, subsystem_device_id; - u32 expansion_rom_addr; - u8 capabilities, reserved1[3]; - u32 reserved2; - u8 irq_line, irq_pin, min_grant, max_latency; - - /* Now, this is the linked capability list. */ - struct virtio_pci_cap common; - struct virtio_pci_notify_cap notify; - struct virtio_pci_cap isr; - struct virtio_pci_cap device; - struct virtio_pci_cfg_cap_u32 cfg_access; -}; - -/* The device structure describes a single device. */ -struct device { - /* The name of this device, for --verbose. */ - const char *name; - - /* Any queues attached to this device */ - struct virtqueue *vq; - - /* Is it operational */ - bool running; - - /* Has it written FEATURES_OK but not re-checked it? */ - bool wrote_features_ok; - - /* PCI configuration */ - union { - struct pci_config config; - u32 config_words[sizeof(struct pci_config) / sizeof(u32)]; - }; - - /* Features we offer, and those accepted. */ - u64 features, features_accepted; - - /* Device-specific config hangs off the end of this. */ - struct virtio_pci_mmio *mmio; - - /* PCI MMIO resources (all in BAR0) */ - size_t mmio_size; - u32 mmio_addr; - - /* Device-specific data. */ - void *priv; -}; - -/* The virtqueue structure describes a queue attached to a device. */ -struct virtqueue { - struct virtqueue *next; - - /* Which device owns me. */ - struct device *dev; - - /* Name for printing errors. */ - const char *name; - - /* The actual ring of buffers. */ - struct vring vring; - - /* The information about this virtqueue (we only use queue_size on) */ - struct virtio_pci_common_cfg pci_config; - - /* Last available index we saw. */ - u16 last_avail_idx; - - /* How many are used since we sent last irq? */ - unsigned int pending_used; - - /* Eventfd where Guest notifications arrive. */ - int eventfd; - - /* Function for the thread which is servicing this virtqueue. */ - void (*service)(struct virtqueue *vq); - pid_t thread; -}; - -/* Remember the arguments to the program so we can "reboot" */ -static char **main_args; - -/* The original tty settings to restore on exit. */ -static struct termios orig_term; - -/* - * We have to be careful with barriers: our devices are all run in separate - * threads and so we need to make sure that changes visible to the Guest happen - * in precise order. - */ -#define wmb() __asm__ __volatile__("" : : : "memory") -#define rmb() __asm__ __volatile__("lock; addl $0,0(%%esp)" : : : "memory") -#define mb() __asm__ __volatile__("lock; addl $0,0(%%esp)" : : : "memory") - -/* Wrapper for the last available index. Makes it easier to change. */ -#define lg_last_avail(vq) ((vq)->last_avail_idx) - -/* - * The virtio configuration space is defined to be little-endian. x86 is - * little-endian too, but it's nice to be explicit so we have these helpers. - */ -#define cpu_to_le16(v16) (v16) -#define cpu_to_le32(v32) (v32) -#define cpu_to_le64(v64) (v64) -#define le16_to_cpu(v16) (v16) -#define le32_to_cpu(v32) (v32) -#define le64_to_cpu(v64) (v64) - -/* - * A real device would ignore weird/non-compliant driver behaviour. We - * stop and flag it, to help debugging Linux problems. - */ -#define bad_driver(d, fmt, ...) \ - errx(1, "%s: bad driver: " fmt, (d)->name, ## __VA_ARGS__) -#define bad_driver_vq(vq, fmt, ...) \ - errx(1, "%s vq %s: bad driver: " fmt, (vq)->dev->name, \ - vq->name, ## __VA_ARGS__) - -/* Is this iovec empty? */ -static bool iov_empty(const struct iovec iov[], unsigned int num_iov) -{ - unsigned int i; - - for (i = 0; i < num_iov; i++) - if (iov[i].iov_len) - return false; - return true; -} - -/* Take len bytes from the front of this iovec. */ -static void iov_consume(struct device *d, - struct iovec iov[], unsigned num_iov, - void *dest, unsigned len) -{ - unsigned int i; - - for (i = 0; i < num_iov; i++) { - unsigned int used; - - used = iov[i].iov_len < len ? iov[i].iov_len : len; - if (dest) { - memcpy(dest, iov[i].iov_base, used); - dest += used; - } - iov[i].iov_base += used; - iov[i].iov_len -= used; - len -= used; - } - if (len != 0) - bad_driver(d, "iovec too short!"); -} - -/*L:100 - * The Launcher code itself takes us out into userspace, that scary place where - * pointers run wild and free! Unfortunately, like most userspace programs, - * it's quite boring (which is why everyone likes to hack on the kernel!). - * Perhaps if you make up an Lguest Drinking Game at this point, it will get - * you through this section. Or, maybe not. - * - * The Launcher sets up a big chunk of memory to be the Guest's "physical" - * memory and stores it in "guest_base". In other words, Guest physical == - * Launcher virtual with an offset. - * - * This can be tough to get your head around, but usually it just means that we - * use these trivial conversion functions when the Guest gives us its - * "physical" addresses: - */ -static void *from_guest_phys(unsigned long addr) -{ - return guest_base + addr; -} - -static unsigned long to_guest_phys(const void *addr) -{ - return (addr - guest_base); -} - -/*L:130 - * Loading the Kernel. - * - * We start with couple of simple helper routines. open_or_die() avoids - * error-checking code cluttering the callers: - */ -static int open_or_die(const char *name, int flags) -{ - int fd = open(name, flags); - if (fd < 0) - err(1, "Failed to open %s", name); - return fd; -} - -/* map_zeroed_pages() takes a number of pages. */ -static void *map_zeroed_pages(unsigned int num) -{ - int fd = open_or_die("/dev/zero", O_RDONLY); - void *addr; - - /* - * We use a private mapping (ie. if we write to the page, it will be - * copied). We allocate an extra two pages PROT_NONE to act as guard - * pages against read/write attempts that exceed allocated space. - */ - addr = mmap(NULL, getpagesize() * (num+2), - PROT_NONE, MAP_PRIVATE, fd, 0); - - if (addr == MAP_FAILED) - err(1, "Mmapping %u pages of /dev/zero", num); - - if (mprotect(addr + getpagesize(), getpagesize() * num, - PROT_READ|PROT_WRITE) == -1) - err(1, "mprotect rw %u pages failed", num); - - /* - * One neat mmap feature is that you can close the fd, and it - * stays mapped. - */ - close(fd); - - /* Return address after PROT_NONE page */ - return addr + getpagesize(); -} - -/* Get some bytes which won't be mapped into the guest. */ -static unsigned long get_mmio_region(size_t size) -{ - unsigned long addr = guest_mmio; - size_t i; - - if (!size) - return addr; - - /* Size has to be a power of 2 (and multiple of 16) */ - for (i = 1; i < size; i <<= 1); - - guest_mmio += i; - - return addr; -} - -/* - * This routine is used to load the kernel or initrd. It tries mmap, but if - * that fails (Plan 9's kernel file isn't nicely aligned on page boundaries), - * it falls back to reading the memory in. - */ -static void map_at(int fd, void *addr, unsigned long offset, unsigned long len) -{ - ssize_t r; - - /* - * We map writable even though for some segments are marked read-only. - * The kernel really wants to be writable: it patches its own - * instructions. - * - * MAP_PRIVATE means that the page won't be copied until a write is - * done to it. This allows us to share untouched memory between - * Guests. - */ - if (mmap(addr, len, PROT_READ|PROT_WRITE, - MAP_FIXED|MAP_PRIVATE, fd, offset) != MAP_FAILED) - return; - - /* pread does a seek and a read in one shot: saves a few lines. */ - r = pread(fd, addr, len, offset); - if (r != len) - err(1, "Reading offset %lu len %lu gave %zi", offset, len, r); -} - -/* - * This routine takes an open vmlinux image, which is in ELF, and maps it into - * the Guest memory. ELF = Embedded Linking Format, which is the format used - * by all modern binaries on Linux including the kernel. - * - * The ELF headers give *two* addresses: a physical address, and a virtual - * address. We use the physical address; the Guest will map itself to the - * virtual address. - * - * We return the starting address. - */ -static unsigned long map_elf(int elf_fd, const Elf32_Ehdr *ehdr) -{ - Elf32_Phdr phdr[ehdr->e_phnum]; - unsigned int i; - - /* - * Sanity checks on the main ELF header: an x86 executable with a - * reasonable number of correctly-sized program headers. - */ - if (ehdr->e_type != ET_EXEC - || ehdr->e_machine != EM_386 - || ehdr->e_phentsize != sizeof(Elf32_Phdr) - || ehdr->e_phnum < 1 || ehdr->e_phnum > 65536U/sizeof(Elf32_Phdr)) - errx(1, "Malformed elf header"); - - /* - * An ELF executable contains an ELF header and a number of "program" - * headers which indicate which parts ("segments") of the program to - * load where. - */ - - /* We read in all the program headers at once: */ - if (lseek(elf_fd, ehdr->e_phoff, SEEK_SET) < 0) - err(1, "Seeking to program headers"); - if (read(elf_fd, phdr, sizeof(phdr)) != sizeof(phdr)) - err(1, "Reading program headers"); - - /* - * Try all the headers: there are usually only three. A read-only one, - * a read-write one, and a "note" section which we don't load. - */ - for (i = 0; i < ehdr->e_phnum; i++) { - /* If this isn't a loadable segment, we ignore it */ - if (phdr[i].p_type != PT_LOAD) - continue; - - verbose("Section %i: size %i addr %p\n", - i, phdr[i].p_memsz, (void *)phdr[i].p_paddr); - - /* We map this section of the file at its physical address. */ - map_at(elf_fd, from_guest_phys(phdr[i].p_paddr), - phdr[i].p_offset, phdr[i].p_filesz); - } - - /* The entry point is given in the ELF header. */ - return ehdr->e_entry; -} - -/*L:150 - * A bzImage, unlike an ELF file, is not meant to be loaded. You're supposed - * to jump into it and it will unpack itself. We used to have to perform some - * hairy magic because the unpacking code scared me. - * - * Fortunately, Jeremy Fitzhardinge convinced me it wasn't that hard and wrote - * a small patch to jump over the tricky bits in the Guest, so now we just read - * the funky header so we know where in the file to load, and away we go! - */ -static unsigned long load_bzimage(int fd) -{ - struct boot_params boot; - int r; - /* Modern bzImages get loaded at 1M. */ - void *p = from_guest_phys(0x100000); - - /* - * Go back to the start of the file and read the header. It should be - * a Linux boot header (see Documentation/x86/boot.txt) - */ - lseek(fd, 0, SEEK_SET); - read(fd, &boot, sizeof(boot)); - - /* Inside the setup_hdr, we expect the magic "HdrS" */ - if (memcmp(&boot.hdr.header, "HdrS", 4) != 0) - errx(1, "This doesn't look like a bzImage to me"); - - /* Skip over the extra sectors of the header. */ - lseek(fd, (boot.hdr.setup_sects+1) * 512, SEEK_SET); - - /* Now read everything into memory. in nice big chunks. */ - while ((r = read(fd, p, 65536)) > 0) - p += r; - - /* Finally, code32_start tells us where to enter the kernel. */ - return boot.hdr.code32_start; -} - -/*L:140 - * Loading the kernel is easy when it's a "vmlinux", but most kernels - * come wrapped up in the self-decompressing "bzImage" format. With a little - * work, we can load those, too. - */ -static unsigned long load_kernel(int fd) -{ - Elf32_Ehdr hdr; - - /* Read in the first few bytes. */ - if (read(fd, &hdr, sizeof(hdr)) != sizeof(hdr)) - err(1, "Reading kernel"); - - /* If it's an ELF file, it starts with "\177ELF" */ - if (memcmp(hdr.e_ident, ELFMAG, SELFMAG) == 0) - return map_elf(fd, &hdr); - - /* Otherwise we assume it's a bzImage, and try to load it. */ - return load_bzimage(fd); -} - -/* - * This is a trivial little helper to align pages. Andi Kleen hated it because - * it calls getpagesize() twice: "it's dumb code." - * - * Kernel guys get really het up about optimization, even when it's not - * necessary. I leave this code as a reaction against that. - */ -static inline unsigned long page_align(unsigned long addr) -{ - /* Add upwards and truncate downwards. */ - return ((addr + getpagesize()-1) & ~(getpagesize()-1)); -} - -/*L:180 - * An "initial ram disk" is a disk image loaded into memory along with the - * kernel which the kernel can use to boot from without needing any drivers. - * Most distributions now use this as standard: the initrd contains the code to - * load the appropriate driver modules for the current machine. - * - * Importantly, James Morris works for RedHat, and Fedora uses initrds for its - * kernels. He sent me this (and tells me when I break it). - */ -static unsigned long load_initrd(const char *name, unsigned long mem) -{ - int ifd; - struct stat st; - unsigned long len; - - ifd = open_or_die(name, O_RDONLY); - /* fstat() is needed to get the file size. */ - if (fstat(ifd, &st) < 0) - err(1, "fstat() on initrd '%s'", name); - - /* - * We map the initrd at the top of memory, but mmap wants it to be - * page-aligned, so we round the size up for that. - */ - len = page_align(st.st_size); - map_at(ifd, from_guest_phys(mem - len), 0, st.st_size); - /* - * Once a file is mapped, you can close the file descriptor. It's a - * little odd, but quite useful. - */ - close(ifd); - verbose("mapped initrd %s size=%lu @ %p\n", name, len, (void*)mem-len); - - /* We return the initrd size. */ - return len; -} -/*:*/ - -/* - * Simple routine to roll all the commandline arguments together with spaces - * between them. - */ -static void concat(char *dst, char *args[]) -{ - unsigned int i, len = 0; - - for (i = 0; args[i]; i++) { - if (i) { - strcat(dst+len, " "); - len++; - } - strcpy(dst+len, args[i]); - len += strlen(args[i]); - } - /* In case it's empty. */ - dst[len] = '\0'; -} - -/*L:185 - * This is where we actually tell the kernel to initialize the Guest. We - * saw the arguments it expects when we looked at initialize() in lguest_user.c: - * the base of Guest "physical" memory, the top physical page to allow and the - * entry point for the Guest. - */ -static void tell_kernel(unsigned long start) -{ - unsigned long args[] = { LHREQ_INITIALIZE, - (unsigned long)guest_base, - guest_limit / getpagesize(), start, - (guest_mmio+getpagesize()-1) / getpagesize() }; - verbose("Guest: %p - %p (%#lx, MMIO %#lx)\n", - guest_base, guest_base + guest_limit, - guest_limit, guest_mmio); - lguest_fd = open_or_die("/dev/lguest", O_RDWR); - if (write(lguest_fd, args, sizeof(args)) < 0) - err(1, "Writing to /dev/lguest"); -} -/*:*/ - -/*L:200 - * Device Handling. - * - * When the Guest gives us a buffer, it sends an array of addresses and sizes. - * We need to make sure it's not trying to reach into the Launcher itself, so - * we have a convenient routine which checks it and exits with an error message - * if something funny is going on: - */ -static void *_check_pointer(struct device *d, - unsigned long addr, unsigned int size, - unsigned int line) -{ - /* - * Check if the requested address and size exceeds the allocated memory, - * or addr + size wraps around. - */ - if ((addr + size) > guest_limit || (addr + size) < addr) - bad_driver(d, "%s:%i: Invalid address %#lx", - __FILE__, line, addr); - /* - * We return a pointer for the caller's convenience, now we know it's - * safe to use. - */ - return from_guest_phys(addr); -} -/* A macro which transparently hands the line number to the real function. */ -#define check_pointer(d,addr,size) _check_pointer(d, addr, size, __LINE__) - -/* - * Each buffer in the virtqueues is actually a chain of descriptors. This - * function returns the next descriptor in the chain, or vq->vring.num if we're - * at the end. - */ -static unsigned next_desc(struct device *d, struct vring_desc *desc, - unsigned int i, unsigned int max) -{ - unsigned int next; - - /* If this descriptor says it doesn't chain, we're done. */ - if (!(desc[i].flags & VRING_DESC_F_NEXT)) - return max; - - /* Check they're not leading us off end of descriptors. */ - next = desc[i].next; - /* Make sure compiler knows to grab that: we don't want it changing! */ - wmb(); - - if (next >= max) - bad_driver(d, "Desc next is %u", next); - - return next; -} - -/* - * This actually sends the interrupt for this virtqueue, if we've used a - * buffer. - */ -static void trigger_irq(struct virtqueue *vq) -{ - unsigned long buf[] = { LHREQ_IRQ, vq->dev->config.irq_line }; - - /* Don't inform them if nothing used. */ - if (!vq->pending_used) - return; - vq->pending_used = 0; - - /* - * 2.4.7.1: - * - * If the VIRTIO_F_EVENT_IDX feature bit is not negotiated: - * The driver MUST set flags to 0 or 1. - */ - if (vq->vring.avail->flags > 1) - bad_driver_vq(vq, "avail->flags = %u\n", vq->vring.avail->flags); - - /* - * 2.4.7.2: - * - * If the VIRTIO_F_EVENT_IDX feature bit is not negotiated: - * - * - The device MUST ignore the used_event value. - * - After the device writes a descriptor index into the used ring: - * - If flags is 1, the device SHOULD NOT send an interrupt. - * - If flags is 0, the device MUST send an interrupt. - */ - if (vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT) { - return; - } - - /* - * 4.1.4.5.1: - * - * If MSI-X capability is disabled, the device MUST set the Queue - * Interrupt bit in ISR status before sending a virtqueue notification - * to the driver. - */ - vq->dev->mmio->isr = 0x1; - - /* Send the Guest an interrupt tell them we used something up. */ - if (write(lguest_fd, buf, sizeof(buf)) != 0) - err(1, "Triggering irq %i", vq->dev->config.irq_line); -} - -/* - * This looks in the virtqueue for the first available buffer, and converts - * it to an iovec for convenient access. Since descriptors consist of some - * number of output then some number of input descriptors, it's actually two - * iovecs, but we pack them into one and note how many of each there were. - * - * This function waits if necessary, and returns the descriptor number found. - */ -static unsigned wait_for_vq_desc(struct virtqueue *vq, - struct iovec iov[], - unsigned int *out_num, unsigned int *in_num) -{ - unsigned int i, head, max; - struct vring_desc *desc; - u16 last_avail = lg_last_avail(vq); - - /* - * 2.4.7.1: - * - * The driver MUST handle spurious interrupts from the device. - * - * That's why this is a while loop. - */ - - /* There's nothing available? */ - while (last_avail == vq->vring.avail->idx) { - u64 event; - - /* - * Since we're about to sleep, now is a good time to tell the - * Guest about what we've used up to now. - */ - trigger_irq(vq); - - /* OK, now we need to know about added descriptors. */ - vq->vring.used->flags &= ~VRING_USED_F_NO_NOTIFY; - - /* - * They could have slipped one in as we were doing that: make - * sure it's written, then check again. - */ - mb(); - if (last_avail != vq->vring.avail->idx) { - vq->vring.used->flags |= VRING_USED_F_NO_NOTIFY; - break; - } - - /* Nothing new? Wait for eventfd to tell us they refilled. */ - if (read(vq->eventfd, &event, sizeof(event)) != sizeof(event)) - errx(1, "Event read failed?"); - - /* We don't need to be notified again. */ - vq->vring.used->flags |= VRING_USED_F_NO_NOTIFY; - } - - /* Check it isn't doing very strange things with descriptor numbers. */ - if ((u16)(vq->vring.avail->idx - last_avail) > vq->vring.num) - bad_driver_vq(vq, "Guest moved used index from %u to %u", - last_avail, vq->vring.avail->idx); - - /* - * Make sure we read the descriptor number *after* we read the ring - * update; don't let the cpu or compiler change the order. - */ - rmb(); - - /* - * Grab the next descriptor number they're advertising, and increment - * the index we've seen. - */ - head = vq->vring.avail->ring[last_avail % vq->vring.num]; - lg_last_avail(vq)++; - - /* If their number is silly, that's a fatal mistake. */ - if (head >= vq->vring.num) - bad_driver_vq(vq, "Guest says index %u is available", head); - - /* When we start there are none of either input nor output. */ - *out_num = *in_num = 0; - - max = vq->vring.num; - desc = vq->vring.desc; - i = head; - - /* - * We have to read the descriptor after we read the descriptor number, - * but there's a data dependency there so the CPU shouldn't reorder - * that: no rmb() required. - */ - - do { - /* - * If this is an indirect entry, then this buffer contains a - * descriptor table which we handle as if it's any normal - * descriptor chain. - */ - if (desc[i].flags & VRING_DESC_F_INDIRECT) { - /* 2.4.5.3.1: - * - * The driver MUST NOT set the VIRTQ_DESC_F_INDIRECT - * flag unless the VIRTIO_F_INDIRECT_DESC feature was - * negotiated. - */ - if (!(vq->dev->features_accepted & - (1<<VIRTIO_RING_F_INDIRECT_DESC))) - bad_driver_vq(vq, "vq indirect not negotiated"); - - /* - * 2.4.5.3.1: - * - * The driver MUST NOT set the VIRTQ_DESC_F_INDIRECT - * flag within an indirect descriptor (ie. only one - * table per descriptor). - */ - if (desc != vq->vring.desc) - bad_driver_vq(vq, "Indirect within indirect"); - - /* - * Proposed update VIRTIO-134 spells this out: - * - * A driver MUST NOT set both VIRTQ_DESC_F_INDIRECT - * and VIRTQ_DESC_F_NEXT in flags. - */ - if (desc[i].flags & VRING_DESC_F_NEXT) - bad_driver_vq(vq, "indirect and next together"); - - if (desc[i].len % sizeof(struct vring_desc)) - bad_driver_vq(vq, - "Invalid size for indirect table"); - /* - * 2.4.5.3.2: - * - * The device MUST ignore the write-only flag - * (flags&VIRTQ_DESC_F_WRITE) in the descriptor that - * refers to an indirect table. - * - * We ignore it here: :) - */ - - max = desc[i].len / sizeof(struct vring_desc); - desc = check_pointer(vq->dev, desc[i].addr, desc[i].len); - i = 0; - - /* 2.4.5.3.1: - * - * A driver MUST NOT create a descriptor chain longer - * than the Queue Size of the device. - */ - if (max > vq->pci_config.queue_size) - bad_driver_vq(vq, - "indirect has too many entries"); - } - - /* Grab the first descriptor, and check it's OK. */ - iov[*out_num + *in_num].iov_len = desc[i].len; - iov[*out_num + *in_num].iov_base - = check_pointer(vq->dev, desc[i].addr, desc[i].len); - /* If this is an input descriptor, increment that count. */ - if (desc[i].flags & VRING_DESC_F_WRITE) - (*in_num)++; - else { - /* - * If it's an output descriptor, they're all supposed - * to come before any input descriptors. - */ - if (*in_num) - bad_driver_vq(vq, - "Descriptor has out after in"); - (*out_num)++; - } - - /* If we've got too many, that implies a descriptor loop. */ - if (*out_num + *in_num > max) - bad_driver_vq(vq, "Looped descriptor"); - } while ((i = next_desc(vq->dev, desc, i, max)) != max); - - return head; -} - -/* - * After we've used one of their buffers, we tell the Guest about it. Sometime - * later we'll want to send them an interrupt using trigger_irq(); note that - * wait_for_vq_desc() does that for us if it has to wait. - */ -static void add_used(struct virtqueue *vq, unsigned int head, int len) -{ - struct vring_used_elem *used; - - /* - * The virtqueue contains a ring of used buffers. Get a pointer to the - * next entry in that used ring. - */ - used = &vq->vring.used->ring[vq->vring.used->idx % vq->vring.num]; - used->id = head; - used->len = len; - /* Make sure buffer is written before we update index. */ - wmb(); - vq->vring.used->idx++; - vq->pending_used++; -} - -/* And here's the combo meal deal. Supersize me! */ -static void add_used_and_trigger(struct virtqueue *vq, unsigned head, int len) -{ - add_used(vq, head, len); - trigger_irq(vq); -} - -/* - * The Console - * - * We associate some data with the console for our exit hack. - */ -struct console_abort { - /* How many times have they hit ^C? */ - int count; - /* When did they start? */ - struct timeval start; -}; - -/* This is the routine which handles console input (ie. stdin). */ -static void console_input(struct virtqueue *vq) -{ - int len; - unsigned int head, in_num, out_num; - struct console_abort *abort = vq->dev->priv; - struct iovec iov[vq->vring.num]; - - /* Make sure there's a descriptor available. */ - head = wait_for_vq_desc(vq, iov, &out_num, &in_num); - if (out_num) - bad_driver_vq(vq, "Output buffers in console in queue?"); - - /* Read into it. This is where we usually wait. */ - len = readv(STDIN_FILENO, iov, in_num); - if (len <= 0) { - /* Ran out of input? */ - warnx("Failed to get console input, ignoring console."); - /* - * For simplicity, dying threads kill the whole Launcher. So - * just nap here. - */ - for (;;) - pause(); - } - - /* Tell the Guest we used a buffer. */ - add_used_and_trigger(vq, head, len); - - /* - * Three ^C within one second? Exit. - * - * This is such a hack, but works surprisingly well. Each ^C has to - * be in a buffer by itself, so they can't be too fast. But we check - * that we get three within about a second, so they can't be too - * slow. - */ - if (len != 1 || ((char *)iov[0].iov_base)[0] != 3) { - abort->count = 0; - return; - } - - abort->count++; - if (abort->count == 1) - gettimeofday(&abort->start, NULL); - else if (abort->count == 3) { - struct timeval now; - gettimeofday(&now, NULL); - /* Kill all Launcher processes with SIGINT, like normal ^C */ - if (now.tv_sec <= abort->start.tv_sec+1) - kill(0, SIGINT); - abort->count = 0; - } -} - -/* This is the routine which handles console output (ie. stdout). */ -static void console_output(struct virtqueue *vq) -{ - unsigned int head, out, in; - struct iovec iov[vq->vring.num]; - - /* We usually wait in here, for the Guest to give us something. */ - head = wait_for_vq_desc(vq, iov, &out, &in); - if (in) - bad_driver_vq(vq, "Input buffers in console output queue?"); - - /* writev can return a partial write, so we loop here. */ - while (!iov_empty(iov, out)) { - int len = writev(STDOUT_FILENO, iov, out); - if (len <= 0) { - warn("Write to stdout gave %i (%d)", len, errno); - break; - } - iov_consume(vq->dev, iov, out, NULL, len); - } - - /* - * We're finished with that buffer: if we're going to sleep, - * wait_for_vq_desc() will prod the Guest with an interrupt. - */ - add_used(vq, head, 0); -} - -/* - * The Network - * - * Handling output for network is also simple: we get all the output buffers - * and write them to /dev/net/tun. - */ -struct net_info { - int tunfd; -}; - -static void net_output(struct virtqueue *vq) -{ - struct net_info *net_info = vq->dev->priv; - unsigned int head, out, in; - struct iovec iov[vq->vring.num]; - - /* We usually wait in here for the Guest to give us a packet. */ - head = wait_for_vq_desc(vq, iov, &out, &in); - if (in) - bad_driver_vq(vq, "Input buffers in net output queue?"); - /* - * Send the whole thing through to /dev/net/tun. It expects the exact - * same format: what a coincidence! - */ - if (writev(net_info->tunfd, iov, out) < 0) - warnx("Write to tun failed (%d)?", errno); - - /* - * Done with that one; wait_for_vq_desc() will send the interrupt if - * all packets are processed. - */ - add_used(vq, head, 0); -} - -/* - * Handling network input is a bit trickier, because I've tried to optimize it. - * - * First we have a helper routine which tells is if from this file descriptor - * (ie. the /dev/net/tun device) will block: - */ -static bool will_block(int fd) -{ - fd_set fdset; - struct timeval zero = { 0, 0 }; - FD_ZERO(&fdset); - FD_SET(fd, &fdset); - return select(fd+1, &fdset, NULL, NULL, &zero) != 1; -} - -/* - * This handles packets coming in from the tun device to our Guest. Like all - * service routines, it gets called again as soon as it returns, so you don't - * see a while(1) loop here. - */ -static void net_input(struct virtqueue *vq) -{ - int len; - unsigned int head, out, in; - struct iovec iov[vq->vring.num]; - struct net_info *net_info = vq->dev->priv; - - /* - * Get a descriptor to write an incoming packet into. This will also - * send an interrupt if they're out of descriptors. - */ - head = wait_for_vq_desc(vq, iov, &out, &in); - if (out) - bad_driver_vq(vq, "Output buffers in net input queue?"); - - /* - * If it looks like we'll block reading from the tun device, send them - * an interrupt. - */ - if (vq->pending_used && will_block(net_info->tunfd)) - trigger_irq(vq); - - /* - * Read in the packet. This is where we normally wait (when there's no - * incoming network traffic). - */ - len = readv(net_info->tunfd, iov, in); - if (len <= 0) - warn("Failed to read from tun (%d).", errno); - - /* - * Mark that packet buffer as used, but don't interrupt here. We want - * to wait until we've done as much work as we can. - */ - add_used(vq, head, len); -} -/*:*/ - -/* This is the helper to create threads: run the service routine in a loop. */ -static int do_thread(void *_vq) -{ - struct virtqueue *vq = _vq; - - for (;;) - vq->service(vq); - return 0; -} - -/* - * When a child dies, we kill our entire process group with SIGTERM. This - * also has the side effect that the shell restores the console for us! - */ -static void kill_launcher(int signal) -{ - kill(0, SIGTERM); -} - -static void reset_vq_pci_config(struct virtqueue *vq) -{ - vq->pci_config.queue_size = VIRTQUEUE_NUM; - vq->pci_config.queue_enable = 0; -} - -static void reset_device(struct device *dev) -{ - struct virtqueue *vq; - - verbose("Resetting device %s\n", dev->name); - - /* Clear any features they've acked. */ - dev->features_accepted = 0; - - /* We're going to be explicitly killing threads, so ignore them. */ - signal(SIGCHLD, SIG_IGN); - - /* - * 4.1.4.3.1: - * - * The device MUST present a 0 in queue_enable on reset. - * - * This means we set it here, and reset the saved ones in every vq. - */ - dev->mmio->cfg.queue_enable = 0; - - /* Get rid of the virtqueue threads */ - for (vq = dev->vq; vq; vq = vq->next) { - vq->last_avail_idx = 0; - reset_vq_pci_config(vq); - if (vq->thread != (pid_t)-1) { - kill(vq->thread, SIGTERM); - waitpid(vq->thread, NULL, 0); - vq->thread = (pid_t)-1; - } - } - dev->running = false; - dev->wrote_features_ok = false; - - /* Now we care if threads die. */ - signal(SIGCHLD, (void *)kill_launcher); -} - -static void cleanup_devices(void) -{ - unsigned int i; - - for (i = 1; i < MAX_PCI_DEVICES; i++) { - struct device *d = devices.pci[i]; - if (!d) - continue; - reset_device(d); - } - - /* If we saved off the original terminal settings, restore them now. */ - if (orig_term.c_lflag & (ISIG|ICANON|ECHO)) - tcsetattr(STDIN_FILENO, TCSANOW, &orig_term); -} - -/*L:217 - * We do PCI. This is mainly done to let us test the kernel virtio PCI - * code. - */ - -/* Linux expects a PCI host bridge: ours is a dummy, and first on the bus. */ -static struct device pci_host_bridge; - -static void init_pci_host_bridge(void) -{ - pci_host_bridge.name = "PCI Host Bridge"; - pci_host_bridge.config.class = 0x06; /* bridge */ - pci_host_bridge.config.subclass = 0; /* host bridge */ - devices.pci[0] = &pci_host_bridge; -} - -/* The IO ports used to read the PCI config space. */ -#define PCI_CONFIG_ADDR 0xCF8 -#define PCI_CONFIG_DATA 0xCFC - -/* - * Not really portable, but does help readability: this is what the Guest - * writes to the PCI_CONFIG_ADDR IO port. - */ -union pci_config_addr { - struct { - unsigned mbz: 2; - unsigned offset: 6; - unsigned funcnum: 3; - unsigned devnum: 5; - unsigned busnum: 8; - unsigned reserved: 7; - unsigned enabled : 1; - } bits; - u32 val; -}; - -/* - * We cache what they wrote to the address port, so we know what they're - * talking about when they access the data port. - */ -static union pci_config_addr pci_config_addr; - -static struct device *find_pci_device(unsigned int index) -{ - return devices.pci[index]; -} - -/* PCI can do 1, 2 and 4 byte reads; we handle that here. */ -static void ioread(u16 off, u32 v, u32 mask, u32 *val) -{ - assert(off < 4); - assert(mask == 0xFF || mask == 0xFFFF || mask == 0xFFFFFFFF); - *val = (v >> (off * 8)) & mask; -} - -/* PCI can do 1, 2 and 4 byte writes; we handle that here. */ -static void iowrite(u16 off, u32 v, u32 mask, u32 *dst) -{ - assert(off < 4); - assert(mask == 0xFF || mask == 0xFFFF || mask == 0xFFFFFFFF); - *dst &= ~(mask << (off * 8)); - *dst |= (v & mask) << (off * 8); -} - -/* - * Where PCI_CONFIG_DATA accesses depends on the previous write to - * PCI_CONFIG_ADDR. - */ -static struct device *dev_and_reg(u32 *reg) -{ - if (!pci_config_addr.bits.enabled) - return NULL; - - if (pci_config_addr.bits.funcnum != 0) - return NULL; - - if (pci_config_addr.bits.busnum != 0) - return NULL; - - if (pci_config_addr.bits.offset * 4 >= sizeof(struct pci_config)) - return NULL; - - *reg = pci_config_addr.bits.offset; - return find_pci_device(pci_config_addr.bits.devnum); -} - -/* - * We can get invalid combinations of values while they're writing, so we - * only fault if they try to write with some invalid bar/offset/length. - */ -static bool valid_bar_access(struct device *d, - struct virtio_pci_cfg_cap_u32 *cfg_access) -{ - /* We only have 1 bar (BAR0) */ - if (cfg_access->cap.bar != 0) - return false; - - /* Check it's within BAR0. */ - if (cfg_access->cap.offset >= d->mmio_size - || cfg_access->cap.offset + cfg_access->cap.length > d->mmio_size) - return false; - - /* Check length is 1, 2 or 4. */ - if (cfg_access->cap.length != 1 - && cfg_access->cap.length != 2 - && cfg_access->cap.length != 4) - return false; - - /* - * 4.1.4.7.2: - * - * The driver MUST NOT write a cap.offset which is not a multiple of - * cap.length (ie. all accesses MUST be aligned). - */ - if (cfg_access->cap.offset % cfg_access->cap.length != 0) - return false; - - /* Return pointer into word in BAR0. */ - return true; -} - -/* Is this accessing the PCI config address port?. */ -static bool is_pci_addr_port(u16 port) -{ - return port >= PCI_CONFIG_ADDR && port < PCI_CONFIG_ADDR + 4; -} - -static bool pci_addr_iowrite(u16 port, u32 mask, u32 val) -{ - iowrite(port - PCI_CONFIG_ADDR, val, mask, - &pci_config_addr.val); - verbose("PCI%s: %#x/%x: bus %u dev %u func %u reg %u\n", - pci_config_addr.bits.enabled ? "" : " DISABLED", - val, mask, - pci_config_addr.bits.busnum, - pci_config_addr.bits.devnum, - pci_config_addr.bits.funcnum, - pci_config_addr.bits.offset); - return true; -} - -static void pci_addr_ioread(u16 port, u32 mask, u32 *val) -{ - ioread(port - PCI_CONFIG_ADDR, pci_config_addr.val, mask, val); -} - -/* Is this accessing the PCI config data port?. */ -static bool is_pci_data_port(u16 port) -{ - return port >= PCI_CONFIG_DATA && port < PCI_CONFIG_DATA + 4; -} - -static void emulate_mmio_write(struct device *d, u32 off, u32 val, u32 mask); - -static bool pci_data_iowrite(u16 port, u32 mask, u32 val) -{ - u32 reg, portoff; - struct device *d = dev_and_reg(®); - - /* Complain if they don't belong to a device. */ - if (!d) - return false; - - /* They can do 1 byte writes, etc. */ - portoff = port - PCI_CONFIG_DATA; - - /* - * PCI uses a weird way to determine the BAR size: the OS - * writes all 1's, and sees which ones stick. - */ - if (&d->config_words[reg] == &d->config.bar[0]) { - int i; - - iowrite(portoff, val, mask, &d->config.bar[0]); - for (i = 0; (1 << i) < d->mmio_size; i++) - d->config.bar[0] &= ~(1 << i); - return true; - } else if ((&d->config_words[reg] > &d->config.bar[0] - && &d->config_words[reg] <= &d->config.bar[6]) - || &d->config_words[reg] == &d->config.expansion_rom_addr) { - /* Allow writing to any other BAR, or expansion ROM */ - iowrite(portoff, val, mask, &d->config_words[reg]); - return true; - /* We let them override latency timer and cacheline size */ - } else if (&d->config_words[reg] == (void *)&d->config.cacheline_size) { - /* Only let them change the first two fields. */ - if (mask == 0xFFFFFFFF) - mask = 0xFFFF; - iowrite(portoff, val, mask, &d->config_words[reg]); - return true; - } else if (&d->config_words[reg] == (void *)&d->config.command - && mask == 0xFFFF) { - /* Ignore command writes. */ - return true; - } else if (&d->config_words[reg] - == (void *)&d->config.cfg_access.cap.bar - || &d->config_words[reg] - == &d->config.cfg_access.cap.length - || &d->config_words[reg] - == &d->config.cfg_access.cap.offset) { - - /* - * The VIRTIO_PCI_CAP_PCI_CFG capability - * provides a backdoor to access the MMIO - * regions without mapping them. Weird, but - * useful. - */ - iowrite(portoff, val, mask, &d->config_words[reg]); - return true; - } else if (&d->config_words[reg] == &d->config.cfg_access.pci_cfg_data) { - u32 write_mask; - - /* - * 4.1.4.7.1: - * - * Upon detecting driver write access to pci_cfg_data, the - * device MUST execute a write access at offset cap.offset at - * BAR selected by cap.bar using the first cap.length bytes - * from pci_cfg_data. - */ - - /* Must be bar 0 */ - if (!valid_bar_access(d, &d->config.cfg_access)) - return false; - - iowrite(portoff, val, mask, &d->config.cfg_access.pci_cfg_data); - - /* - * Now emulate a write. The mask we use is set by - * len, *not* this write! - */ - write_mask = (1ULL<<(8*d->config.cfg_access.cap.length)) - 1; - verbose("Window writing %#x/%#x to bar %u, offset %u len %u\n", - d->config.cfg_access.pci_cfg_data, write_mask, - d->config.cfg_access.cap.bar, - d->config.cfg_access.cap.offset, - d->config.cfg_access.cap.length); - - emulate_mmio_write(d, d->config.cfg_access.cap.offset, - d->config.cfg_access.pci_cfg_data, - write_mask); - return true; - } - - /* - * 4.1.4.1: - * - * The driver MUST NOT write into any field of the capability - * structure, with the exception of those with cap_type - * VIRTIO_PCI_CAP_PCI_CFG... - */ - return false; -} - -static u32 emulate_mmio_read(struct device *d, u32 off, u32 mask); - -static void pci_data_ioread(u16 port, u32 mask, u32 *val) -{ - u32 reg; - struct device *d = dev_and_reg(®); - - if (!d) - return; - - /* Read through the PCI MMIO access window is special */ - if (&d->config_words[reg] == &d->config.cfg_access.pci_cfg_data) { - u32 read_mask; - - /* - * 4.1.4.7.1: - * - * Upon detecting driver read access to pci_cfg_data, the - * device MUST execute a read access of length cap.length at - * offset cap.offset at BAR selected by cap.bar and store the - * first cap.length bytes in pci_cfg_data. - */ - /* Must be bar 0 */ - if (!valid_bar_access(d, &d->config.cfg_access)) - bad_driver(d, - "Invalid cfg_access to bar%u, offset %u len %u", - d->config.cfg_access.cap.bar, - d->config.cfg_access.cap.offset, - d->config.cfg_access.cap.length); - - /* - * Read into the window. The mask we use is set by - * len, *not* this read! - */ - read_mask = (1ULL<<(8*d->config.cfg_access.cap.length))-1; - d->config.cfg_access.pci_cfg_data - = emulate_mmio_read(d, - d->config.cfg_access.cap.offset, - read_mask); - verbose("Window read %#x/%#x from bar %u, offset %u len %u\n", - d->config.cfg_access.pci_cfg_data, read_mask, - d->config.cfg_access.cap.bar, - d->config.cfg_access.cap.offset, - d->config.cfg_access.cap.length); - } - ioread(port - PCI_CONFIG_DATA, d->config_words[reg], mask, val); -} - -/*L:216 - * This is where we emulate a handful of Guest instructions. It's ugly - * and we used to do it in the kernel but it grew over time. - */ - -/* - * We use the ptrace syscall's pt_regs struct to talk about registers - * to lguest: these macros convert the names to the offsets. - */ -#define getreg(name) getreg_off(offsetof(struct user_regs_struct, name)) -#define setreg(name, val) \ - setreg_off(offsetof(struct user_regs_struct, name), (val)) - -static u32 getreg_off(size_t offset) -{ - u32 r; - unsigned long args[] = { LHREQ_GETREG, offset }; - - if (pwrite(lguest_fd, args, sizeof(args), cpu_id) < 0) - err(1, "Getting register %u", offset); - if (pread(lguest_fd, &r, sizeof(r), cpu_id) != sizeof(r)) - err(1, "Reading register %u", offset); - - return r; -} - -static void setreg_off(size_t offset, u32 val) -{ - unsigned long args[] = { LHREQ_SETREG, offset, val }; - - if (pwrite(lguest_fd, args, sizeof(args), cpu_id) < 0) - err(1, "Setting register %u", offset); -} - -/* Get register by instruction encoding */ -static u32 getreg_num(unsigned regnum, u32 mask) -{ - /* 8 bit ops use regnums 4-7 for high parts of word */ - if (mask == 0xFF && (regnum & 0x4)) - return getreg_num(regnum & 0x3, 0xFFFF) >> 8; - - switch (regnum) { - case 0: return getreg(eax) & mask; - case 1: return getreg(ecx) & mask; - case 2: return getreg(edx) & mask; - case 3: return getreg(ebx) & mask; - case 4: return getreg(esp) & mask; - case 5: return getreg(ebp) & mask; - case 6: return getreg(esi) & mask; - case 7: return getreg(edi) & mask; - } - abort(); -} - -/* Set register by instruction encoding */ -static void setreg_num(unsigned regnum, u32 val, u32 mask) -{ - /* Don't try to set bits out of range */ - assert(~(val & ~mask)); - - /* 8 bit ops use regnums 4-7 for high parts of word */ - if (mask == 0xFF && (regnum & 0x4)) { - /* Construct the 16 bits we want. */ - val = (val << 8) | getreg_num(regnum & 0x3, 0xFF); - setreg_num(regnum & 0x3, val, 0xFFFF); - return; - } - - switch (regnum) { - case 0: setreg(eax, val | (getreg(eax) & ~mask)); return; - case 1: setreg(ecx, val | (getreg(ecx) & ~mask)); return; - case 2: setreg(edx, val | (getreg(edx) & ~mask)); return; - case 3: setreg(ebx, val | (getreg(ebx) & ~mask)); return; - case 4: setreg(esp, val | (getreg(esp) & ~mask)); return; - case 5: setreg(ebp, val | (getreg(ebp) & ~mask)); return; - case 6: setreg(esi, val | (getreg(esi) & ~mask)); return; - case 7: setreg(edi, val | (getreg(edi) & ~mask)); return; - } - abort(); -} - -/* Get bytes of displacement appended to instruction, from r/m encoding */ -static u32 insn_displacement_len(u8 mod_reg_rm) -{ - /* Switch on the mod bits */ - switch (mod_reg_rm >> 6) { - case 0: - /* If mod == 0, and r/m == 101, 16-bit displacement follows */ - if ((mod_reg_rm & 0x7) == 0x5) - return 2; - /* Normally, mod == 0 means no literal displacement */ - return 0; - case 1: - /* One byte displacement */ - return 1; - case 2: - /* Four byte displacement */ - return 4; - case 3: - /* Register mode */ - return 0; - } - abort(); -} - -static void emulate_insn(const u8 insn[]) -{ - unsigned long args[] = { LHREQ_TRAP, 13 }; - unsigned int insnlen = 0, in = 0, small_operand = 0, byte_access; - unsigned int eax, port, mask; - /* - * Default is to return all-ones on IO port reads, which traditionally - * means "there's nothing there". - */ - u32 val = 0xFFFFFFFF; - - /* - * This must be the Guest kernel trying to do something, not userspace! - * The bottom two bits of the CS segment register are the privilege - * level. - */ - if ((getreg(xcs) & 3) != 0x1) - goto no_emulate; - - /* Decoding x86 instructions is icky. */ - - /* - * Around 2.6.33, the kernel started using an emulation for the - * cmpxchg8b instruction in early boot on many configurations. This - * code isn't paravirtualized, and it tries to disable interrupts. - * Ignore it, which will Mostly Work. - */ - if (insn[insnlen] == 0xfa) { - /* "cli", or Clear Interrupt Enable instruction. Skip it. */ - insnlen = 1; - goto skip_insn; - } - - /* - * 0x66 is an "operand prefix". It means a 16, not 32 bit in/out. - */ - if (insn[insnlen] == 0x66) { - small_operand = 1; - /* The instruction is 1 byte so far, read the next byte. */ - insnlen = 1; - } - - /* If the lower bit isn't set, it's a single byte access */ - byte_access = !(insn[insnlen] & 1); - - /* - * Now we can ignore the lower bit and decode the 4 opcodes - * we need to emulate. - */ - switch (insn[insnlen] & 0xFE) { - case 0xE4: /* in <next byte>,%al */ - port = insn[insnlen+1]; - insnlen += 2; - in = 1; - break; - case 0xEC: /* in (%dx),%al */ - port = getreg(edx) & 0xFFFF; - insnlen += 1; - in = 1; - break; - case 0xE6: /* out %al,<next byte> */ - port = insn[insnlen+1]; - insnlen += 2; - break; - case 0xEE: /* out %al,(%dx) */ - port = getreg(edx) & 0xFFFF; - insnlen += 1; - break; - default: - /* OK, we don't know what this is, can't emulate. */ - goto no_emulate; - } - - /* Set a mask of the 1, 2 or 4 bytes, depending on size of IO */ - if (byte_access) - mask = 0xFF; - else if (small_operand) - mask = 0xFFFF; - else - mask = 0xFFFFFFFF; - - /* - * If it was an "IN" instruction, they expect the result to be read - * into %eax, so we change %eax. - */ - eax = getreg(eax); - - if (in) { - /* This is the PS/2 keyboard status; 1 means ready for output */ - if (port == 0x64) - val = 1; - else if (is_pci_addr_port(port)) - pci_addr_ioread(port, mask, &val); - else if (is_pci_data_port(port)) - pci_data_ioread(port, mask, &val); - - /* Clear the bits we're about to read */ - eax &= ~mask; - /* Copy bits in from val. */ - eax |= val & mask; - /* Now update the register. */ - setreg(eax, eax); - } else { - if (is_pci_addr_port(port)) { - if (!pci_addr_iowrite(port, mask, eax)) - goto bad_io; - } else if (is_pci_data_port(port)) { - if (!pci_data_iowrite(port, mask, eax)) - goto bad_io; - } - /* There are many other ports, eg. CMOS clock, serial - * and parallel ports, so we ignore them all. */ - } - - verbose("IO %s of %x to %u: %#08x\n", - in ? "IN" : "OUT", mask, port, eax); -skip_insn: - /* Finally, we've "done" the instruction, so move past it. */ - setreg(eip, getreg(eip) + insnlen); - return; - -bad_io: - warnx("Attempt to %s port %u (%#x mask)", - in ? "read from" : "write to", port, mask); - -no_emulate: - /* Inject trap into Guest. */ - if (write(lguest_fd, args, sizeof(args)) < 0) - err(1, "Reinjecting trap 13 for fault at %#x", getreg(eip)); -} - -static struct device *find_mmio_region(unsigned long paddr, u32 *off) -{ - unsigned int i; - - for (i = 1; i < MAX_PCI_DEVICES; i++) { - struct device *d = devices.pci[i]; - - if (!d) - continue; - if (paddr < d->mmio_addr) - continue; - if (paddr >= d->mmio_addr + d->mmio_size) - continue; - *off = paddr - d->mmio_addr; - return d; - } - return NULL; -} - -/* FIXME: Use vq array. */ -static struct virtqueue *vq_by_num(struct device *d, u32 num) -{ - struct virtqueue *vq = d->vq; - - while (num-- && vq) - vq = vq->next; - - return vq; -} - -static void save_vq_config(const struct virtio_pci_common_cfg *cfg, - struct virtqueue *vq) -{ - vq->pci_config = *cfg; -} - -static void restore_vq_config(struct virtio_pci_common_cfg *cfg, - struct virtqueue *vq) -{ - /* Only restore the per-vq part */ - size_t off = offsetof(struct virtio_pci_common_cfg, queue_size); - - memcpy((void *)cfg + off, (void *)&vq->pci_config + off, - sizeof(*cfg) - off); -} - -/* - * 4.1.4.3.2: - * - * The driver MUST configure the other virtqueue fields before - * enabling the virtqueue with queue_enable. - * - * When they enable the virtqueue, we check that their setup is valid. - */ -static void check_virtqueue(struct device *d, struct virtqueue *vq) -{ - /* Because lguest is 32 bit, all the descriptor high bits must be 0 */ - if (vq->pci_config.queue_desc_hi - || vq->pci_config.queue_avail_hi - || vq->pci_config.queue_used_hi) - bad_driver_vq(vq, "invalid 64-bit queue address"); - - /* - * 2.4.1: - * - * The driver MUST ensure that the physical address of the first byte - * of each virtqueue part is a multiple of the specified alignment - * value in the above table. - */ - if (vq->pci_config.queue_desc_lo % 16 - || vq->pci_config.queue_avail_lo % 2 - || vq->pci_config.queue_used_lo % 4) - bad_driver_vq(vq, "invalid alignment in queue addresses"); - - /* Initialize the virtqueue and check they're all in range. */ - vq->vring.num = vq->pci_config.queue_size; - vq->vring.desc = check_pointer(vq->dev, - vq->pci_config.queue_desc_lo, - sizeof(*vq->vring.desc) * vq->vring.num); - vq->vring.avail = check_pointer(vq->dev, - vq->pci_config.queue_avail_lo, - sizeof(*vq->vring.avail) - + (sizeof(vq->vring.avail->ring[0]) - * vq->vring.num)); - vq->vring.used = check_pointer(vq->dev, - vq->pci_config.queue_used_lo, - sizeof(*vq->vring.used) - + (sizeof(vq->vring.used->ring[0]) - * vq->vring.num)); - - /* - * 2.4.9.1: - * - * The driver MUST initialize flags in the used ring to 0 - * when allocating the used ring. - */ - if (vq->vring.used->flags != 0) - bad_driver_vq(vq, "invalid initial used.flags %#x", - vq->vring.used->flags); -} - -static void start_virtqueue(struct virtqueue *vq) -{ - /* - * Create stack for thread. Since the stack grows upwards, we point - * the stack pointer to the end of this region. - */ - char *stack = malloc(32768); - - /* Create a zero-initialized eventfd. */ - vq->eventfd = eventfd(0, 0); - if (vq->eventfd < 0) - err(1, "Creating eventfd"); - - /* - * CLONE_VM: because it has to access the Guest memory, and SIGCHLD so - * we get a signal if it dies. - */ - vq->thread = clone(do_thread, stack + 32768, CLONE_VM | SIGCHLD, vq); - if (vq->thread == (pid_t)-1) - err(1, "Creating clone"); -} - -static void start_virtqueues(struct device *d) -{ - struct virtqueue *vq; - - for (vq = d->vq; vq; vq = vq->next) { - if (vq->pci_config.queue_enable) - start_virtqueue(vq); - } -} - -static void emulate_mmio_write(struct device *d, u32 off, u32 val, u32 mask) -{ - struct virtqueue *vq; - - switch (off) { - case offsetof(struct virtio_pci_mmio, cfg.device_feature_select): - /* - * 4.1.4.3.1: - * - * The device MUST present the feature bits it is offering in - * device_feature, starting at bit device_feature_select ∗ 32 - * for any device_feature_select written by the driver - */ - if (val == 0) - d->mmio->cfg.device_feature = d->features; - else if (val == 1) - d->mmio->cfg.device_feature = (d->features >> 32); - else - d->mmio->cfg.device_feature = 0; - goto feature_write_through32; - case offsetof(struct virtio_pci_mmio, cfg.guest_feature_select): - if (val > 1) - bad_driver(d, "Unexpected driver select %u", val); - goto feature_write_through32; - case offsetof(struct virtio_pci_mmio, cfg.guest_feature): - if (d->mmio->cfg.guest_feature_select == 0) { - d->features_accepted &= ~((u64)0xFFFFFFFF); - d->features_accepted |= val; - } else { - assert(d->mmio->cfg.guest_feature_select == 1); - d->features_accepted &= 0xFFFFFFFF; - d->features_accepted |= ((u64)val) << 32; - } - /* - * 2.2.1: - * - * The driver MUST NOT accept a feature which the device did - * not offer - */ - if (d->features_accepted & ~d->features) - bad_driver(d, "over-accepted features %#llx of %#llx", - d->features_accepted, d->features); - goto feature_write_through32; - case offsetof(struct virtio_pci_mmio, cfg.device_status): { - u8 prev; - - verbose("%s: device status -> %#x\n", d->name, val); - /* - * 4.1.4.3.1: - * - * The device MUST reset when 0 is written to device_status, - * and present a 0 in device_status once that is done. - */ - if (val == 0) { - reset_device(d); - goto write_through8; - } - - /* 2.1.1: The driver MUST NOT clear a device status bit. */ - if (d->mmio->cfg.device_status & ~val) - bad_driver(d, "unset of device status bit %#x -> %#x", - d->mmio->cfg.device_status, val); - - /* - * 2.1.2: - * - * The device MUST NOT consume buffers or notify the driver - * before DRIVER_OK. - */ - if (val & VIRTIO_CONFIG_S_DRIVER_OK - && !(d->mmio->cfg.device_status & VIRTIO_CONFIG_S_DRIVER_OK)) - start_virtqueues(d); - - /* - * 3.1.1: - * - * The driver MUST follow this sequence to initialize a device: - * - Reset the device. - * - Set the ACKNOWLEDGE status bit: the guest OS has - * notice the device. - * - Set the DRIVER status bit: the guest OS knows how - * to drive the device. - * - Read device feature bits, and write the subset - * of feature bits understood by the OS and driver - * to the device. During this step the driver MAY - * read (but MUST NOT write) the device-specific - * configuration fields to check that it can - * support the device before accepting it. - * - Set the FEATURES_OK status bit. The driver - * MUST not accept new feature bits after this - * step. - * - Re-read device status to ensure the FEATURES_OK - * bit is still set: otherwise, the device does - * not support our subset of features and the - * device is unusable. - * - Perform device-specific setup, including - * discovery of virtqueues for the device, - * optional per-bus setup, reading and possibly - * writing the device’s virtio configuration - * space, and population of virtqueues. - * - Set the DRIVER_OK status bit. At this point the - * device is “live”. - */ - prev = 0; - switch (val & ~d->mmio->cfg.device_status) { - case VIRTIO_CONFIG_S_DRIVER_OK: - prev |= VIRTIO_CONFIG_S_FEATURES_OK; /* fall thru */ - case VIRTIO_CONFIG_S_FEATURES_OK: - prev |= VIRTIO_CONFIG_S_DRIVER; /* fall thru */ - case VIRTIO_CONFIG_S_DRIVER: - prev |= VIRTIO_CONFIG_S_ACKNOWLEDGE; /* fall thru */ - case VIRTIO_CONFIG_S_ACKNOWLEDGE: - break; - default: - bad_driver(d, "unknown device status bit %#x -> %#x", - d->mmio->cfg.device_status, val); - } - if (d->mmio->cfg.device_status != prev) - bad_driver(d, "unexpected status transition %#x -> %#x", - d->mmio->cfg.device_status, val); - - /* If they just wrote FEATURES_OK, we make sure they read */ - switch (val & ~d->mmio->cfg.device_status) { - case VIRTIO_CONFIG_S_FEATURES_OK: - d->wrote_features_ok = true; - break; - case VIRTIO_CONFIG_S_DRIVER_OK: - if (d->wrote_features_ok) - bad_driver(d, "did not re-read FEATURES_OK"); - break; - } - goto write_through8; - } - case offsetof(struct virtio_pci_mmio, cfg.queue_select): - vq = vq_by_num(d, val); - /* - * 4.1.4.3.1: - * - * The device MUST present a 0 in queue_size if the virtqueue - * corresponding to the current queue_select is unavailable. - */ - if (!vq) { - d->mmio->cfg.queue_size = 0; - goto write_through16; - } - /* Save registers for old vq, if it was a valid vq */ - if (d->mmio->cfg.queue_size) - save_vq_config(&d->mmio->cfg, - vq_by_num(d, d->mmio->cfg.queue_select)); - /* Restore the registers for the queue they asked for */ - restore_vq_config(&d->mmio->cfg, vq); - goto write_through16; - case offsetof(struct virtio_pci_mmio, cfg.queue_size): - /* - * 4.1.4.3.2: - * - * The driver MUST NOT write a value which is not a power of 2 - * to queue_size. - */ - if (val & (val-1)) - bad_driver(d, "invalid queue size %u", val); - if (d->mmio->cfg.queue_enable) - bad_driver(d, "changing queue size on live device"); - goto write_through16; - case offsetof(struct virtio_pci_mmio, cfg.queue_msix_vector): - bad_driver(d, "attempt to set MSIX vector to %u", val); - case offsetof(struct virtio_pci_mmio, cfg.queue_enable): { - struct virtqueue *vq = vq_by_num(d, d->mmio->cfg.queue_select); - - /* - * 4.1.4.3.2: - * - * The driver MUST NOT write a 0 to queue_enable. - */ - if (val != 1) - bad_driver(d, "setting queue_enable to %u", val); - - /* - * 3.1.1: - * - * 7. Perform device-specific setup, including discovery of - * virtqueues for the device, optional per-bus setup, - * reading and possibly writing the device’s virtio - * configuration space, and population of virtqueues. - * 8. Set the DRIVER_OK status bit. - * - * All our devices require all virtqueues to be enabled, so - * they should have done that before setting DRIVER_OK. - */ - if (d->mmio->cfg.device_status & VIRTIO_CONFIG_S_DRIVER_OK) - bad_driver(d, "enabling vq after DRIVER_OK"); - - d->mmio->cfg.queue_enable = val; - save_vq_config(&d->mmio->cfg, vq); - check_virtqueue(d, vq); - goto write_through16; - } - case offsetof(struct virtio_pci_mmio, cfg.queue_notify_off): - bad_driver(d, "attempt to write to queue_notify_off"); - case offsetof(struct virtio_pci_mmio, cfg.queue_desc_lo): - case offsetof(struct virtio_pci_mmio, cfg.queue_desc_hi): - case offsetof(struct virtio_pci_mmio, cfg.queue_avail_lo): - case offsetof(struct virtio_pci_mmio, cfg.queue_avail_hi): - case offsetof(struct virtio_pci_mmio, cfg.queue_used_lo): - case offsetof(struct virtio_pci_mmio, cfg.queue_used_hi): - /* - * 4.1.4.3.2: - * - * The driver MUST configure the other virtqueue fields before - * enabling the virtqueue with queue_enable. - */ - if (d->mmio->cfg.queue_enable) - bad_driver(d, "changing queue on live device"); - - /* - * 3.1.1: - * - * The driver MUST follow this sequence to initialize a device: - *... - * 5. Set the FEATURES_OK status bit. The driver MUST not - * accept new feature bits after this step. - */ - if (!(d->mmio->cfg.device_status & VIRTIO_CONFIG_S_FEATURES_OK)) - bad_driver(d, "setting up vq before FEATURES_OK"); - - /* - * 6. Re-read device status to ensure the FEATURES_OK bit is - * still set... - */ - if (d->wrote_features_ok) - bad_driver(d, "didn't re-read FEATURES_OK before setup"); - - goto write_through32; - case offsetof(struct virtio_pci_mmio, notify): - vq = vq_by_num(d, val); - if (!vq) - bad_driver(d, "Invalid vq notification on %u", val); - /* Notify the process handling this vq by adding 1 to eventfd */ - write(vq->eventfd, "\1\0\0\0\0\0\0\0", 8); - goto write_through16; - case offsetof(struct virtio_pci_mmio, isr): - bad_driver(d, "Unexpected write to isr"); - /* Weird corner case: write to emerg_wr of console */ - case sizeof(struct virtio_pci_mmio) - + offsetof(struct virtio_console_config, emerg_wr): - if (strcmp(d->name, "console") == 0) { - char c = val; - write(STDOUT_FILENO, &c, 1); - goto write_through32; - } - /* Fall through... */ - default: - /* - * 4.1.4.3.2: - * - * The driver MUST NOT write to device_feature, num_queues, - * config_generation or queue_notify_off. - */ - bad_driver(d, "Unexpected write to offset %u", off); - } - -feature_write_through32: - /* - * 3.1.1: - * - * The driver MUST follow this sequence to initialize a device: - *... - * - Set the DRIVER status bit: the guest OS knows how - * to drive the device. - * - Read device feature bits, and write the subset - * of feature bits understood by the OS and driver - * to the device. - *... - * - Set the FEATURES_OK status bit. The driver MUST not - * accept new feature bits after this step. - */ - if (!(d->mmio->cfg.device_status & VIRTIO_CONFIG_S_DRIVER)) - bad_driver(d, "feature write before VIRTIO_CONFIG_S_DRIVER"); - if (d->mmio->cfg.device_status & VIRTIO_CONFIG_S_FEATURES_OK) - bad_driver(d, "feature write after VIRTIO_CONFIG_S_FEATURES_OK"); - - /* - * 4.1.3.1: - * - * The driver MUST access each field using the “natural” access - * method, i.e. 32-bit accesses for 32-bit fields, 16-bit accesses for - * 16-bit fields and 8-bit accesses for 8-bit fields. - */ -write_through32: - if (mask != 0xFFFFFFFF) { - bad_driver(d, "non-32-bit write to offset %u (%#x)", - off, getreg(eip)); - return; - } - memcpy((char *)d->mmio + off, &val, 4); - return; - -write_through16: - if (mask != 0xFFFF) - bad_driver(d, "non-16-bit write to offset %u (%#x)", - off, getreg(eip)); - memcpy((char *)d->mmio + off, &val, 2); - return; - -write_through8: - if (mask != 0xFF) - bad_driver(d, "non-8-bit write to offset %u (%#x)", - off, getreg(eip)); - memcpy((char *)d->mmio + off, &val, 1); - return; -} - -static u32 emulate_mmio_read(struct device *d, u32 off, u32 mask) -{ - u8 isr; - u32 val = 0; - - switch (off) { - case offsetof(struct virtio_pci_mmio, cfg.device_feature_select): - case offsetof(struct virtio_pci_mmio, cfg.device_feature): - case offsetof(struct virtio_pci_mmio, cfg.guest_feature_select): - case offsetof(struct virtio_pci_mmio, cfg.guest_feature): - /* - * 3.1.1: - * - * The driver MUST follow this sequence to initialize a device: - *... - * - Set the DRIVER status bit: the guest OS knows how - * to drive the device. - * - Read device feature bits, and write the subset - * of feature bits understood by the OS and driver - * to the device. - */ - if (!(d->mmio->cfg.device_status & VIRTIO_CONFIG_S_DRIVER)) - bad_driver(d, - "feature read before VIRTIO_CONFIG_S_DRIVER"); - goto read_through32; - case offsetof(struct virtio_pci_mmio, cfg.msix_config): - bad_driver(d, "read of msix_config"); - case offsetof(struct virtio_pci_mmio, cfg.num_queues): - goto read_through16; - case offsetof(struct virtio_pci_mmio, cfg.device_status): - /* As they did read, any write of FEATURES_OK is now fine. */ - d->wrote_features_ok = false; - goto read_through8; - case offsetof(struct virtio_pci_mmio, cfg.config_generation): - /* - * 4.1.4.3.1: - * - * The device MUST present a changed config_generation after - * the driver has read a device-specific configuration value - * which has changed since any part of the device-specific - * configuration was last read. - * - * This is simple: none of our devices change config, so this - * is always 0. - */ - goto read_through8; - case offsetof(struct virtio_pci_mmio, notify): - /* - * 3.1.1: - * - * The driver MUST NOT notify the device before setting - * DRIVER_OK. - */ - if (!(d->mmio->cfg.device_status & VIRTIO_CONFIG_S_DRIVER_OK)) - bad_driver(d, "notify before VIRTIO_CONFIG_S_DRIVER_OK"); - goto read_through16; - case offsetof(struct virtio_pci_mmio, isr): - if (mask != 0xFF) - bad_driver(d, "non-8-bit read from offset %u (%#x)", - off, getreg(eip)); - isr = d->mmio->isr; - /* - * 4.1.4.5.1: - * - * The device MUST reset ISR status to 0 on driver read. - */ - d->mmio->isr = 0; - return isr; - case offsetof(struct virtio_pci_mmio, padding): - bad_driver(d, "read from padding (%#x)", getreg(eip)); - default: - /* Read from device config space, beware unaligned overflow */ - if (off > d->mmio_size - 4) - bad_driver(d, "read past end (%#x)", getreg(eip)); - - /* - * 3.1.1: - * The driver MUST follow this sequence to initialize a device: - *... - * 3. Set the DRIVER status bit: the guest OS knows how to - * drive the device. - * 4. Read device feature bits, and write the subset of - * feature bits understood by the OS and driver to the - * device. During this step the driver MAY read (but MUST NOT - * write) the device-specific configuration fields to check - * that it can support the device before accepting it. - */ - if (!(d->mmio->cfg.device_status & VIRTIO_CONFIG_S_DRIVER)) - bad_driver(d, - "config read before VIRTIO_CONFIG_S_DRIVER"); - - if (mask == 0xFFFFFFFF) - goto read_through32; - else if (mask == 0xFFFF) - goto read_through16; - else - goto read_through8; - } - - /* - * 4.1.3.1: - * - * The driver MUST access each field using the “natural” access - * method, i.e. 32-bit accesses for 32-bit fields, 16-bit accesses for - * 16-bit fields and 8-bit accesses for 8-bit fields. - */ -read_through32: - if (mask != 0xFFFFFFFF) - bad_driver(d, "non-32-bit read to offset %u (%#x)", - off, getreg(eip)); - memcpy(&val, (char *)d->mmio + off, 4); - return val; - -read_through16: - if (mask != 0xFFFF) - bad_driver(d, "non-16-bit read to offset %u (%#x)", - off, getreg(eip)); - memcpy(&val, (char *)d->mmio + off, 2); - return val; - -read_through8: - if (mask != 0xFF) - bad_driver(d, "non-8-bit read to offset %u (%#x)", - off, getreg(eip)); - memcpy(&val, (char *)d->mmio + off, 1); - return val; -} - -static void emulate_mmio(unsigned long paddr, const u8 *insn) -{ - u32 val, off, mask = 0xFFFFFFFF, insnlen = 0; - struct device *d = find_mmio_region(paddr, &off); - unsigned long args[] = { LHREQ_TRAP, 14 }; - - if (!d) { - warnx("MMIO touching %#08lx (not a device)", paddr); - goto reinject; - } - - /* Prefix makes it a 16 bit op */ - if (insn[0] == 0x66) { - mask = 0xFFFF; - insnlen++; - } - - /* iowrite */ - if (insn[insnlen] == 0x89) { - /* Next byte is r/m byte: bits 3-5 are register. */ - val = getreg_num((insn[insnlen+1] >> 3) & 0x7, mask); - emulate_mmio_write(d, off, val, mask); - insnlen += 2 + insn_displacement_len(insn[insnlen+1]); - } else if (insn[insnlen] == 0x8b) { /* ioread */ - /* Next byte is r/m byte: bits 3-5 are register. */ - val = emulate_mmio_read(d, off, mask); - setreg_num((insn[insnlen+1] >> 3) & 0x7, val, mask); - insnlen += 2 + insn_displacement_len(insn[insnlen+1]); - } else if (insn[0] == 0x88) { /* 8-bit iowrite */ - mask = 0xff; - /* Next byte is r/m byte: bits 3-5 are register. */ - val = getreg_num((insn[1] >> 3) & 0x7, mask); - emulate_mmio_write(d, off, val, mask); - insnlen = 2 + insn_displacement_len(insn[1]); - } else if (insn[0] == 0x8a) { /* 8-bit ioread */ - mask = 0xff; - val = emulate_mmio_read(d, off, mask); - setreg_num((insn[1] >> 3) & 0x7, val, mask); - insnlen = 2 + insn_displacement_len(insn[1]); - } else { - warnx("Unknown MMIO instruction touching %#08lx:" - " %02x %02x %02x %02x at %u", - paddr, insn[0], insn[1], insn[2], insn[3], getreg(eip)); - reinject: - /* Inject trap into Guest. */ - if (write(lguest_fd, args, sizeof(args)) < 0) - err(1, "Reinjecting trap 14 for fault at %#x", - getreg(eip)); - return; - } - - /* Finally, we've "done" the instruction, so move past it. */ - setreg(eip, getreg(eip) + insnlen); -} - -/*L:190 - * Device Setup - * - * All devices need a descriptor so the Guest knows it exists, and a "struct - * device" so the Launcher can keep track of it. We have common helper - * routines to allocate and manage them. - */ -static void add_pci_virtqueue(struct device *dev, - void (*service)(struct virtqueue *), - const char *name) -{ - struct virtqueue **i, *vq = malloc(sizeof(*vq)); - - /* Initialize the virtqueue */ - vq->next = NULL; - vq->last_avail_idx = 0; - vq->dev = dev; - vq->name = name; - - /* - * This is the routine the service thread will run, and its Process ID - * once it's running. - */ - vq->service = service; - vq->thread = (pid_t)-1; - - /* Initialize the configuration. */ - reset_vq_pci_config(vq); - vq->pci_config.queue_notify_off = 0; - - /* Add one to the number of queues */ - vq->dev->mmio->cfg.num_queues++; - - /* - * Add to tail of list, so dev->vq is first vq, dev->vq->next is - * second. - */ - for (i = &dev->vq; *i; i = &(*i)->next); - *i = vq; -} - -/* The Guest accesses the feature bits via the PCI common config MMIO region */ -static void add_pci_feature(struct device *dev, unsigned bit) -{ - dev->features |= (1ULL << bit); -} - -/* For devices with no config. */ -static void no_device_config(struct device *dev) -{ - dev->mmio_addr = get_mmio_region(dev->mmio_size); - - dev->config.bar[0] = dev->mmio_addr; - /* Bottom 4 bits must be zero */ - assert(~(dev->config.bar[0] & 0xF)); -} - -/* This puts the device config into BAR0 */ -static void set_device_config(struct device *dev, const void *conf, size_t len) -{ - /* Set up BAR 0 */ - dev->mmio_size += len; - dev->mmio = realloc(dev->mmio, dev->mmio_size); - memcpy(dev->mmio + 1, conf, len); - - /* - * 4.1.4.6: - * - * The device MUST present at least one VIRTIO_PCI_CAP_DEVICE_CFG - * capability for any device type which has a device-specific - * configuration. - */ - /* Hook up device cfg */ - dev->config.cfg_access.cap.cap_next - = offsetof(struct pci_config, device); - - /* - * 4.1.4.6.1: - * - * The offset for the device-specific configuration MUST be 4-byte - * aligned. - */ - assert(dev->config.cfg_access.cap.cap_next % 4 == 0); - - /* Fix up device cfg field length. */ - dev->config.device.length = len; - - /* The rest is the same as the no-config case */ - no_device_config(dev); -} - -static void init_cap(struct virtio_pci_cap *cap, size_t caplen, int type, - size_t bar_offset, size_t bar_bytes, u8 next) -{ - cap->cap_vndr = PCI_CAP_ID_VNDR; - cap->cap_next = next; - cap->cap_len = caplen; - cap->cfg_type = type; - cap->bar = 0; - memset(cap->padding, 0, sizeof(cap->padding)); - cap->offset = bar_offset; - cap->length = bar_bytes; -} - -/* - * This sets up the pci_config structure, as defined in the virtio 1.0 - * standard (and PCI standard). - */ -static void init_pci_config(struct pci_config *pci, u16 type, - u8 class, u8 subclass) -{ - size_t bar_offset, bar_len; - - /* - * 4.1.4.4.1: - * - * The device MUST either present notify_off_multiplier as an even - * power of 2, or present notify_off_multiplier as 0. - * - * 2.1.2: - * - * The device MUST initialize device status to 0 upon reset. - */ - memset(pci, 0, sizeof(*pci)); - - /* 4.1.2.1: Devices MUST have the PCI Vendor ID 0x1AF4 */ - pci->vendor_id = 0x1AF4; - /* 4.1.2.1: ... PCI Device ID calculated by adding 0x1040 ... */ - pci->device_id = 0x1040 + type; - - /* - * PCI have specific codes for different types of devices. - * Linux doesn't care, but it's a good clue for people looking - * at the device. - */ - pci->class = class; - pci->subclass = subclass; - - /* - * 4.1.2.1: - * - * Non-transitional devices SHOULD have a PCI Revision ID of 1 or - * higher - */ - pci->revid = 1; - - /* - * 4.1.2.1: - * - * Non-transitional devices SHOULD have a PCI Subsystem Device ID of - * 0x40 or higher. - */ - pci->subsystem_device_id = 0x40; - - /* We use our dummy interrupt controller, and irq_line is the irq */ - pci->irq_line = devices.next_irq++; - pci->irq_pin = 0; - - /* Support for extended capabilities. */ - pci->status = (1 << 4); - - /* Link them in. */ - /* - * 4.1.4.3.1: - * - * The device MUST present at least one common configuration - * capability. - */ - pci->capabilities = offsetof(struct pci_config, common); - - /* 4.1.4.3.1 ... offset MUST be 4-byte aligned. */ - assert(pci->capabilities % 4 == 0); - - bar_offset = offsetof(struct virtio_pci_mmio, cfg); - bar_len = sizeof(((struct virtio_pci_mmio *)0)->cfg); - init_cap(&pci->common, sizeof(pci->common), VIRTIO_PCI_CAP_COMMON_CFG, - bar_offset, bar_len, - offsetof(struct pci_config, notify)); - - /* - * 4.1.4.4.1: - * - * The device MUST present at least one notification capability. - */ - bar_offset += bar_len; - bar_len = sizeof(((struct virtio_pci_mmio *)0)->notify); - - /* - * 4.1.4.4.1: - * - * The cap.offset MUST be 2-byte aligned. - */ - assert(pci->common.cap_next % 2 == 0); - - /* FIXME: Use a non-zero notify_off, for per-queue notification? */ - /* - * 4.1.4.4.1: - * - * The value cap.length presented by the device MUST be at least 2 and - * MUST be large enough to support queue notification offsets for all - * supported queues in all possible configurations. - */ - assert(bar_len >= 2); - - init_cap(&pci->notify.cap, sizeof(pci->notify), - VIRTIO_PCI_CAP_NOTIFY_CFG, - bar_offset, bar_len, - offsetof(struct pci_config, isr)); - - bar_offset += bar_len; - bar_len = sizeof(((struct virtio_pci_mmio *)0)->isr); - /* - * 4.1.4.5.1: - * - * The device MUST present at least one VIRTIO_PCI_CAP_ISR_CFG - * capability. - */ - init_cap(&pci->isr, sizeof(pci->isr), - VIRTIO_PCI_CAP_ISR_CFG, - bar_offset, bar_len, - offsetof(struct pci_config, cfg_access)); - - /* - * 4.1.4.7.1: - * - * The device MUST present at least one VIRTIO_PCI_CAP_PCI_CFG - * capability. - */ - /* This doesn't have any presence in the BAR */ - init_cap(&pci->cfg_access.cap, sizeof(pci->cfg_access), - VIRTIO_PCI_CAP_PCI_CFG, - 0, 0, 0); - - bar_offset += bar_len + sizeof(((struct virtio_pci_mmio *)0)->padding); - assert(bar_offset == sizeof(struct virtio_pci_mmio)); - - /* - * This gets sewn in and length set in set_device_config(). - * Some devices don't have a device configuration interface, so - * we never expose this if we don't call set_device_config(). - */ - init_cap(&pci->device, sizeof(pci->device), VIRTIO_PCI_CAP_DEVICE_CFG, - bar_offset, 0, 0); -} - -/* - * This routine does all the creation and setup of a new device, but we don't - * actually place the MMIO region until we know the size (if any) of the - * device-specific config. And we don't actually start the service threads - * until later. - * - * See what I mean about userspace being boring? - */ -static struct device *new_pci_device(const char *name, u16 type, - u8 class, u8 subclass) -{ - struct device *dev = malloc(sizeof(*dev)); - - /* Now we populate the fields one at a time. */ - dev->name = name; - dev->vq = NULL; - dev->running = false; - dev->wrote_features_ok = false; - dev->mmio_size = sizeof(struct virtio_pci_mmio); - dev->mmio = calloc(1, dev->mmio_size); - dev->features = (u64)1 << VIRTIO_F_VERSION_1; - dev->features_accepted = 0; - - if (devices.device_num + 1 >= MAX_PCI_DEVICES) - errx(1, "Can only handle 31 PCI devices"); - - init_pci_config(&dev->config, type, class, subclass); - assert(!devices.pci[devices.device_num+1]); - devices.pci[++devices.device_num] = dev; - - return dev; -} - -/* - * Our first setup routine is the console. It's a fairly simple device, but - * UNIX tty handling makes it uglier than it could be. - */ -static void setup_console(void) -{ - struct device *dev; - struct virtio_console_config conf; - - /* If we can save the initial standard input settings... */ - if (tcgetattr(STDIN_FILENO, &orig_term) == 0) { - struct termios term = orig_term; - /* - * Then we turn off echo, line buffering and ^C etc: We want a - * raw input stream to the Guest. - */ - term.c_lflag &= ~(ISIG|ICANON|ECHO); - tcsetattr(STDIN_FILENO, TCSANOW, &term); - } - - dev = new_pci_device("console", VIRTIO_ID_CONSOLE, 0x07, 0x00); - - /* We store the console state in dev->priv, and initialize it. */ - dev->priv = malloc(sizeof(struct console_abort)); - ((struct console_abort *)dev->priv)->count = 0; - - /* - * The console needs two virtqueues: the input then the output. When - * they put something the input queue, we make sure we're listening to - * stdin. When they put something in the output queue, we write it to - * stdout. - */ - add_pci_virtqueue(dev, console_input, "input"); - add_pci_virtqueue(dev, console_output, "output"); - - /* We need a configuration area for the emerg_wr early writes. */ - add_pci_feature(dev, VIRTIO_CONSOLE_F_EMERG_WRITE); - set_device_config(dev, &conf, sizeof(conf)); - - verbose("device %u: console\n", devices.device_num); -} -/*:*/ - -/*M:010 - * Inter-guest networking is an interesting area. Simplest is to have a - * --sharenet=<name> option which opens or creates a named pipe. This can be - * used to send packets to another guest in a 1:1 manner. - * - * More sophisticated is to use one of the tools developed for project like UML - * to do networking. - * - * Faster is to do virtio bonding in kernel. Doing this 1:1 would be - * completely generic ("here's my vring, attach to your vring") and would work - * for any traffic. Of course, namespace and permissions issues need to be - * dealt with. A more sophisticated "multi-channel" virtio_net.c could hide - * multiple inter-guest channels behind one interface, although it would - * require some manner of hotplugging new virtio channels. - * - * Finally, we could use a virtio network switch in the kernel, ie. vhost. -:*/ - -static u32 str2ip(const char *ipaddr) -{ - unsigned int b[4]; - - if (sscanf(ipaddr, "%u.%u.%u.%u", &b[0], &b[1], &b[2], &b[3]) != 4) - errx(1, "Failed to parse IP address '%s'", ipaddr); - return (b[0] << 24) | (b[1] << 16) | (b[2] << 8) | b[3]; -} - -static void str2mac(const char *macaddr, unsigned char mac[6]) -{ - unsigned int m[6]; - if (sscanf(macaddr, "%02x:%02x:%02x:%02x:%02x:%02x", - &m[0], &m[1], &m[2], &m[3], &m[4], &m[5]) != 6) - errx(1, "Failed to parse mac address '%s'", macaddr); - mac[0] = m[0]; - mac[1] = m[1]; - mac[2] = m[2]; - mac[3] = m[3]; - mac[4] = m[4]; - mac[5] = m[5]; -} - -/* - * This code is "adapted" from libbridge: it attaches the Host end of the - * network device to the bridge device specified by the command line. - * - * This is yet another James Morris contribution (I'm an IP-level guy, so I - * dislike bridging), and I just try not to break it. - */ -static void add_to_bridge(int fd, const char *if_name, const char *br_name) -{ - int ifidx; - struct ifreq ifr; - - if (!*br_name) - errx(1, "must specify bridge name"); - - ifidx = if_nametoindex(if_name); - if (!ifidx) - errx(1, "interface %s does not exist!", if_name); - - strncpy(ifr.ifr_name, br_name, IFNAMSIZ); - ifr.ifr_name[IFNAMSIZ-1] = '\0'; - ifr.ifr_ifindex = ifidx; - if (ioctl(fd, SIOCBRADDIF, &ifr) < 0) - err(1, "can't add %s to bridge %s", if_name, br_name); -} - -/* - * This sets up the Host end of the network device with an IP address, brings - * it up so packets will flow, the copies the MAC address into the hwaddr - * pointer. - */ -static void configure_device(int fd, const char *tapif, u32 ipaddr) -{ - struct ifreq ifr; - struct sockaddr_in sin; - - memset(&ifr, 0, sizeof(ifr)); - strcpy(ifr.ifr_name, tapif); - - /* Don't read these incantations. Just cut & paste them like I did! */ - sin.sin_family = AF_INET; - sin.sin_addr.s_addr = htonl(ipaddr); - memcpy(&ifr.ifr_addr, &sin, sizeof(sin)); - if (ioctl(fd, SIOCSIFADDR, &ifr) != 0) - err(1, "Setting %s interface address", tapif); - ifr.ifr_flags = IFF_UP; - if (ioctl(fd, SIOCSIFFLAGS, &ifr) != 0) - err(1, "Bringing interface %s up", tapif); -} - -static int get_tun_device(char tapif[IFNAMSIZ]) -{ - struct ifreq ifr; - int vnet_hdr_sz; - int netfd; - - /* Start with this zeroed. Messy but sure. */ - memset(&ifr, 0, sizeof(ifr)); - - /* - * We open the /dev/net/tun device and tell it we want a tap device. A - * tap device is like a tun device, only somehow different. To tell - * the truth, I completely blundered my way through this code, but it - * works now! - */ - netfd = open_or_die("/dev/net/tun", O_RDWR); - ifr.ifr_flags = IFF_TAP | IFF_NO_PI | IFF_VNET_HDR; - strcpy(ifr.ifr_name, "tap%d"); - if (ioctl(netfd, TUNSETIFF, &ifr) != 0) - err(1, "configuring /dev/net/tun"); - - if (ioctl(netfd, TUNSETOFFLOAD, - TUN_F_CSUM|TUN_F_TSO4|TUN_F_TSO6|TUN_F_TSO_ECN) != 0) - err(1, "Could not set features for tun device"); - - /* - * We don't need checksums calculated for packets coming in this - * device: trust us! - */ - ioctl(netfd, TUNSETNOCSUM, 1); - - /* - * In virtio before 1.0 (aka legacy virtio), we added a 16-bit - * field at the end of the network header iff - * VIRTIO_NET_F_MRG_RXBUF was negotiated. For virtio 1.0, - * that became the norm, but we need to tell the tun device - * about our expanded header (which is called - * virtio_net_hdr_mrg_rxbuf in the legacy system). - */ - vnet_hdr_sz = sizeof(struct virtio_net_hdr_v1); - if (ioctl(netfd, TUNSETVNETHDRSZ, &vnet_hdr_sz) != 0) - err(1, "Setting tun header size to %u", vnet_hdr_sz); - - memcpy(tapif, ifr.ifr_name, IFNAMSIZ); - return netfd; -} - -/*L:195 - * Our network is a Host<->Guest network. This can either use bridging or - * routing, but the principle is the same: it uses the "tun" device to inject - * packets into the Host as if they came in from a normal network card. We - * just shunt packets between the Guest and the tun device. - */ -static void setup_tun_net(char *arg) -{ - struct device *dev; - struct net_info *net_info = malloc(sizeof(*net_info)); - int ipfd; - u32 ip = INADDR_ANY; - bool bridging = false; - char tapif[IFNAMSIZ], *p; - struct virtio_net_config conf; - - net_info->tunfd = get_tun_device(tapif); - - /* First we create a new network device. */ - dev = new_pci_device("net", VIRTIO_ID_NET, 0x02, 0x00); - dev->priv = net_info; - - /* Network devices need a recv and a send queue, just like console. */ - add_pci_virtqueue(dev, net_input, "rx"); - add_pci_virtqueue(dev, net_output, "tx"); - - /* - * We need a socket to perform the magic network ioctls to bring up the - * tap interface, connect to the bridge etc. Any socket will do! - */ - ipfd = socket(PF_INET, SOCK_DGRAM, IPPROTO_IP); - if (ipfd < 0) - err(1, "opening IP socket"); - - /* If the command line was --tunnet=bridge:<name> do bridging. */ - if (!strncmp(BRIDGE_PFX, arg, strlen(BRIDGE_PFX))) { - arg += strlen(BRIDGE_PFX); - bridging = true; - } - - /* A mac address may follow the bridge name or IP address */ - p = strchr(arg, ':'); - if (p) { - str2mac(p+1, conf.mac); - add_pci_feature(dev, VIRTIO_NET_F_MAC); - *p = '\0'; - } - - /* arg is now either an IP address or a bridge name */ - if (bridging) - add_to_bridge(ipfd, tapif, arg); - else - ip = str2ip(arg); - - /* Set up the tun device. */ - configure_device(ipfd, tapif, ip); - - /* Expect Guest to handle everything except UFO */ - add_pci_feature(dev, VIRTIO_NET_F_CSUM); - add_pci_feature(dev, VIRTIO_NET_F_GUEST_CSUM); - add_pci_feature(dev, VIRTIO_NET_F_GUEST_TSO4); - add_pci_feature(dev, VIRTIO_NET_F_GUEST_TSO6); - add_pci_feature(dev, VIRTIO_NET_F_GUEST_ECN); - add_pci_feature(dev, VIRTIO_NET_F_HOST_TSO4); - add_pci_feature(dev, VIRTIO_NET_F_HOST_TSO6); - add_pci_feature(dev, VIRTIO_NET_F_HOST_ECN); - /* We handle indirect ring entries */ - add_pci_feature(dev, VIRTIO_RING_F_INDIRECT_DESC); - set_device_config(dev, &conf, sizeof(conf)); - - /* We don't need the socket any more; setup is done. */ - close(ipfd); - - if (bridging) - verbose("device %u: tun %s attached to bridge: %s\n", - devices.device_num, tapif, arg); - else - verbose("device %u: tun %s: %s\n", - devices.device_num, tapif, arg); -} -/*:*/ - -/* This hangs off device->priv. */ -struct vblk_info { - /* The size of the file. */ - off64_t len; - - /* The file descriptor for the file. */ - int fd; - -}; - -/*L:210 - * The Disk - * - * The disk only has one virtqueue, so it only has one thread. It is really - * simple: the Guest asks for a block number and we read or write that position - * in the file. - * - * Before we serviced each virtqueue in a separate thread, that was unacceptably - * slow: the Guest waits until the read is finished before running anything - * else, even if it could have been doing useful work. - * - * We could have used async I/O, except it's reputed to suck so hard that - * characters actually go missing from your code when you try to use it. - */ -static void blk_request(struct virtqueue *vq) -{ - struct vblk_info *vblk = vq->dev->priv; - unsigned int head, out_num, in_num, wlen; - int ret, i; - u8 *in; - struct virtio_blk_outhdr out; - struct iovec iov[vq->vring.num]; - off64_t off; - - /* - * Get the next request, where we normally wait. It triggers the - * interrupt to acknowledge previously serviced requests (if any). - */ - head = wait_for_vq_desc(vq, iov, &out_num, &in_num); - - /* Copy the output header from the front of the iov (adjusts iov) */ - iov_consume(vq->dev, iov, out_num, &out, sizeof(out)); - - /* Find and trim end of iov input array, for our status byte. */ - in = NULL; - for (i = out_num + in_num - 1; i >= out_num; i--) { - if (iov[i].iov_len > 0) { - in = iov[i].iov_base + iov[i].iov_len - 1; - iov[i].iov_len--; - break; - } - } - if (!in) - bad_driver_vq(vq, "Bad virtblk cmd with no room for status"); - - /* - * For historical reasons, block operations are expressed in 512 byte - * "sectors". - */ - off = out.sector * 512; - - if (out.type & VIRTIO_BLK_T_OUT) { - /* - * Write - * - * Move to the right location in the block file. This can fail - * if they try to write past end. - */ - if (lseek64(vblk->fd, off, SEEK_SET) != off) - err(1, "Bad seek to sector %llu", out.sector); - - ret = writev(vblk->fd, iov, out_num); - verbose("WRITE to sector %llu: %i\n", out.sector, ret); - - /* - * Grr... Now we know how long the descriptor they sent was, we - * make sure they didn't try to write over the end of the block - * file (possibly extending it). - */ - if (ret > 0 && off + ret > vblk->len) { - /* Trim it back to the correct length */ - ftruncate64(vblk->fd, vblk->len); - /* Die, bad Guest, die. */ - bad_driver_vq(vq, "Write past end %llu+%u", off, ret); - } - - wlen = sizeof(*in); - *in = (ret >= 0 ? VIRTIO_BLK_S_OK : VIRTIO_BLK_S_IOERR); - } else if (out.type & VIRTIO_BLK_T_FLUSH) { - /* Flush */ - ret = fdatasync(vblk->fd); - verbose("FLUSH fdatasync: %i\n", ret); - wlen = sizeof(*in); - *in = (ret >= 0 ? VIRTIO_BLK_S_OK : VIRTIO_BLK_S_IOERR); - } else { - /* - * Read - * - * Move to the right location in the block file. This can fail - * if they try to read past end. - */ - if (lseek64(vblk->fd, off, SEEK_SET) != off) - err(1, "Bad seek to sector %llu", out.sector); - - ret = readv(vblk->fd, iov + out_num, in_num); - if (ret >= 0) { - wlen = sizeof(*in) + ret; - *in = VIRTIO_BLK_S_OK; - } else { - wlen = sizeof(*in); - *in = VIRTIO_BLK_S_IOERR; - } - } - - /* Finished that request. */ - add_used(vq, head, wlen); -} - -/*L:198 This actually sets up a virtual block device. */ -static void setup_block_file(const char *filename) -{ - struct device *dev; - struct vblk_info *vblk; - struct virtio_blk_config conf; - - /* Create the device. */ - dev = new_pci_device("block", VIRTIO_ID_BLOCK, 0x01, 0x80); - - /* The device has one virtqueue, where the Guest places requests. */ - add_pci_virtqueue(dev, blk_request, "request"); - - /* Allocate the room for our own bookkeeping */ - vblk = dev->priv = malloc(sizeof(*vblk)); - - /* First we open the file and store the length. */ - vblk->fd = open_or_die(filename, O_RDWR|O_LARGEFILE); - vblk->len = lseek64(vblk->fd, 0, SEEK_END); - - /* Tell Guest how many sectors this device has. */ - conf.capacity = cpu_to_le64(vblk->len / 512); - - /* - * Tell Guest not to put in too many descriptors at once: two are used - * for the in and out elements. - */ - add_pci_feature(dev, VIRTIO_BLK_F_SEG_MAX); - conf.seg_max = cpu_to_le32(VIRTQUEUE_NUM - 2); - - set_device_config(dev, &conf, sizeof(struct virtio_blk_config)); - - verbose("device %u: virtblock %llu sectors\n", - devices.device_num, le64_to_cpu(conf.capacity)); -} - -/*L:211 - * Our random number generator device reads from /dev/urandom into the Guest's - * input buffers. The usual case is that the Guest doesn't want random numbers - * and so has no buffers although /dev/urandom is still readable, whereas - * console is the reverse. - * - * The same logic applies, however. - */ -struct rng_info { - int rfd; -}; - -static void rng_input(struct virtqueue *vq) -{ - int len; - unsigned int head, in_num, out_num, totlen = 0; - struct rng_info *rng_info = vq->dev->priv; - struct iovec iov[vq->vring.num]; - - /* First we need a buffer from the Guests's virtqueue. */ - head = wait_for_vq_desc(vq, iov, &out_num, &in_num); - if (out_num) - bad_driver_vq(vq, "Output buffers in rng?"); - - /* - * Just like the console write, we loop to cover the whole iovec. - * In this case, short reads actually happen quite a bit. - */ - while (!iov_empty(iov, in_num)) { - len = readv(rng_info->rfd, iov, in_num); - if (len <= 0) - err(1, "Read from /dev/urandom gave %i", len); - iov_consume(vq->dev, iov, in_num, NULL, len); - totlen += len; - } - - /* Tell the Guest about the new input. */ - add_used(vq, head, totlen); -} - -/*L:199 - * This creates a "hardware" random number device for the Guest. - */ -static void setup_rng(void) -{ - struct device *dev; - struct rng_info *rng_info = malloc(sizeof(*rng_info)); - - /* Our device's private info simply contains the /dev/urandom fd. */ - rng_info->rfd = open_or_die("/dev/urandom", O_RDONLY); - - /* Create the new device. */ - dev = new_pci_device("rng", VIRTIO_ID_RNG, 0xff, 0); - dev->priv = rng_info; - - /* The device has one virtqueue, where the Guest places inbufs. */ - add_pci_virtqueue(dev, rng_input, "input"); - - /* We don't have any configuration space */ - no_device_config(dev); - - verbose("device %u: rng\n", devices.device_num); -} -/* That's the end of device setup. */ - -/*L:230 Reboot is pretty easy: clean up and exec() the Launcher afresh. */ -static void __attribute__((noreturn)) restart_guest(void) -{ - unsigned int i; - - /* - * Since we don't track all open fds, we simply close everything beyond - * stderr. - */ - for (i = 3; i < FD_SETSIZE; i++) - close(i); - - /* Reset all the devices (kills all threads). */ - cleanup_devices(); - - execv(main_args[0], main_args); - err(1, "Could not exec %s", main_args[0]); -} - -/*L:220 - * Finally we reach the core of the Launcher which runs the Guest, serves - * its input and output, and finally, lays it to rest. - */ -static void __attribute__((noreturn)) run_guest(void) -{ - for (;;) { - struct lguest_pending notify; - int readval; - - /* We read from the /dev/lguest device to run the Guest. */ - readval = pread(lguest_fd, ¬ify, sizeof(notify), cpu_id); - if (readval == sizeof(notify)) { - if (notify.trap == 13) { - verbose("Emulating instruction at %#x\n", - getreg(eip)); - emulate_insn(notify.insn); - } else if (notify.trap == 14) { - verbose("Emulating MMIO at %#x\n", - getreg(eip)); - emulate_mmio(notify.addr, notify.insn); - } else - errx(1, "Unknown trap %i addr %#08x\n", - notify.trap, notify.addr); - /* ENOENT means the Guest died. Reading tells us why. */ - } else if (errno == ENOENT) { - char reason[1024] = { 0 }; - pread(lguest_fd, reason, sizeof(reason)-1, cpu_id); - errx(1, "%s", reason); - /* ERESTART means that we need to reboot the guest */ - } else if (errno == ERESTART) { - restart_guest(); - /* Anything else means a bug or incompatible change. */ - } else - err(1, "Running guest failed"); - } -} -/*L:240 - * This is the end of the Launcher. The good news: we are over halfway - * through! The bad news: the most fiendish part of the code still lies ahead - * of us. - * - * Are you ready? Take a deep breath and join me in the core of the Host, in - * "make Host". -:*/ - -static struct option opts[] = { - { "verbose", 0, NULL, 'v' }, - { "tunnet", 1, NULL, 't' }, - { "block", 1, NULL, 'b' }, - { "rng", 0, NULL, 'r' }, - { "initrd", 1, NULL, 'i' }, - { "username", 1, NULL, 'u' }, - { "chroot", 1, NULL, 'c' }, - { NULL }, -}; -static void usage(void) -{ - errx(1, "Usage: lguest [--verbose] " - "[--tunnet=(<ipaddr>:<macaddr>|bridge:<bridgename>:<macaddr>)\n" - "|--block=<filename>|--initrd=<filename>]...\n" - "<mem-in-mb> vmlinux [args...]"); -} - -/*L:105 The main routine is where the real work begins: */ -int main(int argc, char *argv[]) -{ - /* Memory, code startpoint and size of the (optional) initrd. */ - unsigned long mem = 0, start, initrd_size = 0; - /* Two temporaries. */ - int i, c; - /* The boot information for the Guest. */ - struct boot_params *boot; - /* If they specify an initrd file to load. */ - const char *initrd_name = NULL; - - /* Password structure for initgroups/setres[gu]id */ - struct passwd *user_details = NULL; - - /* Directory to chroot to */ - char *chroot_path = NULL; - - /* Save the args: we "reboot" by execing ourselves again. */ - main_args = argv; - - /* - * First we initialize the device list. We remember next interrupt - * number to use for devices (1: remember that 0 is used by the timer). - */ - devices.next_irq = 1; - - /* We're CPU 0. In fact, that's the only CPU possible right now. */ - cpu_id = 0; - - /* - * We need to know how much memory so we can set up the device - * descriptor and memory pages for the devices as we parse the command - * line. So we quickly look through the arguments to find the amount - * of memory now. - */ - for (i = 1; i < argc; i++) { - if (argv[i][0] != '-') { - mem = atoi(argv[i]) * 1024 * 1024; - /* - * We start by mapping anonymous pages over all of - * guest-physical memory range. This fills it with 0, - * and ensures that the Guest won't be killed when it - * tries to access it. - */ - guest_base = map_zeroed_pages(mem / getpagesize() - + DEVICE_PAGES); - guest_limit = mem; - guest_max = guest_mmio = mem + DEVICE_PAGES*getpagesize(); - break; - } - } - - /* If we exit via err(), this kills all the threads, restores tty. */ - atexit(cleanup_devices); - - /* We always have a console device, and it's always device 1. */ - setup_console(); - - /* The options are fairly straight-forward */ - while ((c = getopt_long(argc, argv, "v", opts, NULL)) != EOF) { - switch (c) { - case 'v': - verbose = true; - break; - case 't': - setup_tun_net(optarg); - break; - case 'b': - setup_block_file(optarg); - break; - case 'r': - setup_rng(); - break; - case 'i': - initrd_name = optarg; - break; - case 'u': - user_details = getpwnam(optarg); - if (!user_details) - err(1, "getpwnam failed, incorrect username?"); - break; - case 'c': - chroot_path = optarg; - break; - default: - warnx("Unknown argument %s", argv[optind]); - usage(); - } - } - /* - * After the other arguments we expect memory and kernel image name, - * followed by command line arguments for the kernel. - */ - if (optind + 2 > argc) - usage(); - - verbose("Guest base is at %p\n", guest_base); - - /* Initialize the (fake) PCI host bridge device. */ - init_pci_host_bridge(); - - /* Now we load the kernel */ - start = load_kernel(open_or_die(argv[optind+1], O_RDONLY)); - - /* Boot information is stashed at physical address 0 */ - boot = from_guest_phys(0); - - /* Map the initrd image if requested (at top of physical memory) */ - if (initrd_name) { - initrd_size = load_initrd(initrd_name, mem); - /* - * These are the location in the Linux boot header where the - * start and size of the initrd are expected to be found. - */ - boot->hdr.ramdisk_image = mem - initrd_size; - boot->hdr.ramdisk_size = initrd_size; - /* The bootloader type 0xFF means "unknown"; that's OK. */ - boot->hdr.type_of_loader = 0xFF; - } - - /* - * The Linux boot header contains an "E820" memory map: ours is a - * simple, single region. - */ - boot->e820_entries = 1; - boot->e820_table[0] = ((struct e820_entry) { 0, mem, E820_TYPE_RAM }); - /* - * The boot header contains a command line pointer: we put the command - * line after the boot header. - */ - boot->hdr.cmd_line_ptr = to_guest_phys(boot + 1); - /* We use a simple helper to copy the arguments separated by spaces. */ - concat((char *)(boot + 1), argv+optind+2); - - /* Set kernel alignment to 16M (CONFIG_PHYSICAL_ALIGN) */ - boot->hdr.kernel_alignment = 0x1000000; - - /* Boot protocol version: 2.07 supports the fields for lguest. */ - boot->hdr.version = 0x207; - - /* X86_SUBARCH_LGUEST tells the Guest it's an lguest. */ - boot->hdr.hardware_subarch = X86_SUBARCH_LGUEST; - - /* Tell the entry path not to try to reload segment registers. */ - boot->hdr.loadflags |= KEEP_SEGMENTS; - - /* We don't support tboot: */ - boot->tboot_addr = 0; - - /* Ensure this is 0 to prevent APM from loading: */ - boot->apm_bios_info.version = 0; - - /* We tell the kernel to initialize the Guest. */ - tell_kernel(start); - - /* Ensure that we terminate if a device-servicing child dies. */ - signal(SIGCHLD, kill_launcher); - - /* If requested, chroot to a directory */ - if (chroot_path) { - if (chroot(chroot_path) != 0) - err(1, "chroot(\"%s\") failed", chroot_path); - - if (chdir("/") != 0) - err(1, "chdir(\"/\") failed"); - - verbose("chroot done\n"); - } - - /* If requested, drop privileges */ - if (user_details) { - uid_t u; - gid_t g; - - u = user_details->pw_uid; - g = user_details->pw_gid; - - if (initgroups(user_details->pw_name, g) != 0) - err(1, "initgroups failed"); - - if (setresgid(g, g, g) != 0) - err(1, "setresgid failed"); - - if (setresuid(u, u, u) != 0) - err(1, "setresuid failed"); - - verbose("Dropping privileges completed\n"); - } - - /* Finally, run the Guest. This doesn't return. */ - run_guest(); -} -/*:*/ - -/*M:999 - * Mastery is done: you now know everything I do. - * - * But surely you have seen code, features and bugs in your wanderings which - * you now yearn to attack? That is the real game, and I look forward to you - * patching and forking lguest into the Your-Name-Here-visor. - * - * Farewell, and good coding! - * Rusty Russell. - */ diff --git a/tools/lguest/lguest.txt b/tools/lguest/lguest.txt deleted file mode 100644 index 06e1f4649511..000000000000 --- a/tools/lguest/lguest.txt +++ /dev/null @@ -1,125 +0,0 @@ - __ - (___()'`; Rusty's Remarkably Unreliable Guide to Lguest - /, /` - or, A Young Coder's Illustrated Hypervisor - \\"--\\ http://lguest.ozlabs.org - -Lguest is designed to be a minimal 32-bit x86 hypervisor for the Linux kernel, -for Linux developers and users to experiment with virtualization with the -minimum of complexity. Nonetheless, it should have sufficient features to -make it useful for specific tasks, and, of course, you are encouraged to fork -and enhance it (see drivers/lguest/README). - -Features: - -- Kernel module which runs in a normal kernel. -- Simple I/O model for communication. -- Simple program to create new guests. -- Logo contains cute puppies: http://lguest.ozlabs.org - -Developer features: - -- Fun to hack on. -- No ABI: being tied to a specific kernel anyway, you can change anything. -- Many opportunities for improvement or feature implementation. - -Running Lguest: - -- The easiest way to run lguest is to use same kernel as guest and host. - You can configure them differently, but usually it's easiest not to. - - You will need to configure your kernel with the following options: - - "Processor type and features": - "Paravirtualized guest support" = Y - "Lguest guest support" = Y - "High Memory Support" = off/4GB - "Alignment value to which kernel should be aligned" = 0x100000 - (CONFIG_PARAVIRT=y, CONFIG_LGUEST_GUEST=y, CONFIG_HIGHMEM64G=n and - CONFIG_PHYSICAL_ALIGN=0x100000) - - "Device Drivers": - "Block devices" - "Virtio block driver" = M/Y - "Network device support" - "Universal TUN/TAP device driver support" = M/Y - "Virtio network driver" = M/Y - (CONFIG_VIRTIO_BLK=m, CONFIG_VIRTIO_NET=m and CONFIG_TUN=m) - - "Virtualization" - "Linux hypervisor example code" = M/Y - (CONFIG_LGUEST=m) - -- A tool called "lguest" is available in this directory: type "make" - to build it. If you didn't build your kernel in-tree, use "make - O=<builddir>". - -- Create or find a root disk image. There are several useful ones - around, such as the xm-test tiny root image at - http://xm-test.xensource.com/ramdisks/initrd-1.1-i386.img - - For more serious work, I usually use a distribution ISO image and - install it under qemu, then make multiple copies: - - dd if=/dev/zero of=rootfile bs=1M count=2048 - qemu -cdrom image.iso -hda rootfile -net user -net nic -boot d - - Make sure that you install a getty on /dev/hvc0 if you want to log in on the - console! - -- "modprobe lg" if you built it as a module. - -- Run an lguest as root: - - tools/lguest/lguest 64 vmlinux --tunnet=192.168.19.1 \ - --block=rootfile root=/dev/vda - - Explanation: - 64: the amount of memory to use, in MB. - - vmlinux: the kernel image found in the top of your build directory. You - can also use a standard bzImage. - - --tunnet=192.168.19.1: configures a "tap" device for networking with this - IP address. - - --block=rootfile: a file or block device which becomes /dev/vda - inside the guest. - - root=/dev/vda: this (and anything else on the command line) are - kernel boot parameters. - -- Configuring networking. I usually have the host masquerade, using - "iptables -t nat -A POSTROUTING -o eth0 -j MASQUERADE" and "echo 1 > - /proc/sys/net/ipv4/ip_forward". In this example, I would configure - eth0 inside the guest at 192.168.19.2. - - Another method is to bridge the tap device to an external interface - using --tunnet=bridge:<bridgename>, and perhaps run dhcp on the guest - to obtain an IP address. The bridge needs to be configured first: - this option simply adds the tap interface to it. - - A simple example on my system: - - ifconfig eth0 0.0.0.0 - brctl addbr lg0 - ifconfig lg0 up - brctl addif lg0 eth0 - dhclient lg0 - - Then use --tunnet=bridge:lg0 when launching the guest. - - See: - - http://www.linuxfoundation.org/collaborate/workgroups/networking/bridge - - for general information on how to get bridging to work. - -- Random number generation. Using the --rng option will provide a - /dev/hwrng in the guest that will read from the host's /dev/random. - Use this option in conjunction with rng-tools (see ../hw_random.txt) - to provide entropy to the guest kernel's /dev/random. - -There is a helpful mailing list at http://ozlabs.org/mailman/listinfo/lguest - -Good luck! -Rusty Russell rusty@rustcorp.com.au. diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile index eb6e0b36bfc1..1e83e3c07448 100644 --- a/tools/lib/api/Makefile +++ b/tools/lib/api/Makefile @@ -8,22 +8,28 @@ srctree := $(patsubst %/,%,$(dir $(srctree))) #$(info Determined 'srctree' to be $(srctree)) endif -CC = $(CROSS_COMPILE)gcc -AR = $(CROSS_COMPILE)ar -LD = $(CROSS_COMPILE)ld +CC ?= $(CROSS_COMPILE)gcc +AR ?= $(CROSS_COMPILE)ar +LD ?= $(CROSS_COMPILE)ld MAKEFLAGS += --no-print-directory LIBFILE = $(OUTPUT)libapi.a CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) -CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC +CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -U_FORTIFY_SOURCE -fPIC -ifeq ($(CC), clang) +ifeq ($(DEBUG),0) +ifeq ($(CC_NO_CLANG), 0) CFLAGS += -O3 else CFLAGS += -O6 endif +endif + +ifeq ($(DEBUG),0) + CFLAGS += -D_FORTIFY_SOURCE +endif # Treat warnings as errors unless directed not to ifneq ($(WERROR),0) diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c index 809c7721cd24..a7ecf8f469f4 100644 --- a/tools/lib/api/fs/fs.c +++ b/tools/lib/api/fs/fs.c @@ -387,6 +387,22 @@ int filename__read_str(const char *filename, char **buf, size_t *sizep) return err; } +int filename__write_int(const char *filename, int value) +{ + int fd = open(filename, O_WRONLY), err = -1; + char buf[64]; + + if (fd < 0) + return err; + + sprintf(buf, "%d", value); + if (write(fd, buf, sizeof(buf)) == sizeof(buf)) + err = 0; + + close(fd); + return err; +} + int procfs__read_str(const char *entry, char **buf, size_t *sizep) { char path[PATH_MAX]; @@ -480,3 +496,17 @@ int sysctl__read_int(const char *sysctl, int *value) return filename__read_int(path, value); } + +int sysfs__write_int(const char *entry, int value) +{ + char path[PATH_MAX]; + const char *sysfs = sysfs__mountpoint(); + + if (!sysfs) + return -1; + + if (snprintf(path, sizeof(path), "%s/%s", sysfs, entry) >= PATH_MAX) + return -1; + + return filename__write_int(path, value); +} diff --git a/tools/lib/api/fs/fs.h b/tools/lib/api/fs/fs.h index 956c21127d1e..45605348461e 100644 --- a/tools/lib/api/fs/fs.h +++ b/tools/lib/api/fs/fs.h @@ -31,6 +31,8 @@ int filename__read_int(const char *filename, int *value); int filename__read_ull(const char *filename, unsigned long long *value); int filename__read_str(const char *filename, char **buf, size_t *sizep); +int filename__write_int(const char *filename, int value); + int procfs__read_str(const char *entry, char **buf, size_t *sizep); int sysctl__read_int(const char *sysctl, int *value); @@ -38,4 +40,6 @@ int sysfs__read_int(const char *entry, int *value); int sysfs__read_ull(const char *entry, unsigned long long *value); int sysfs__read_str(const char *entry, char **buf, size_t *sizep); int sysfs__read_bool(const char *entry, bool *value); + +int sysfs__write_int(const char *entry, int value); #endif /* __API_FS__ */ diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index 1f5300e56b44..d2441db34740 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -154,12 +154,12 @@ all: fixdep $(VERSION_FILES) all_cmd all_cmd: $(CMD_TARGETS) $(BPF_IN): force elfdep bpfdep - @(test -f ../../../include/uapi/linux/bpf.h -a -f ../../../include/uapi/linux/bpf.h && ( \ + @(test -f ../../include/uapi/linux/bpf.h -a -f ../../../include/uapi/linux/bpf.h && ( \ (diff -B ../../include/uapi/linux/bpf.h ../../../include/uapi/linux/bpf.h >/dev/null) || \ - echo "Warning: tools/include/uapi/linux/bpf.h differs from kernel" >&2 )) || true - @(test -f ../../../include/uapi/linux/bpf_common.h -a -f ../../../include/uapi/linux/bpf_common.h && ( \ + echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf.h' differs from latest version at 'include/uapi/linux/bpf.h'" >&2 )) || true + @(test -f ../../include/uapi/linux/bpf_common.h -a -f ../../../include/uapi/linux/bpf_common.h && ( \ (diff -B ../../include/uapi/linux/bpf_common.h ../../../include/uapi/linux/bpf_common.h >/dev/null) || \ - echo "Warning: tools/include/uapi/linux/bpf_common.h differs from kernel" >&2 )) || true + echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf_common.h' differs from latest version at 'include/uapi/linux/bpf_common.h'" >&2 )) || true $(Q)$(MAKE) $(build)=libbpf $(OUTPUT)libbpf.so: $(BPF_IN) @@ -189,6 +189,10 @@ install_lib: all_cmd $(call QUIET_INSTALL, $(LIB_FILE)) \ $(call do_install,$(LIB_FILE),$(libdir_SQ)) +install_headers: + $(call QUIET_INSTALL, headers) \ + $(call do_install,bpf.h,$(prefix)/include/bpf,644) + install: install_lib ### Cleaning rules diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 6e178987af8e..1d6907d379c9 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -39,6 +39,8 @@ # define __NR_bpf 280 # elif defined(__sparc__) # define __NR_bpf 349 +# elif defined(__s390__) +# define __NR_bpf 351 # else # error __NR_bpf not defined. libbpf does not support your arch. # endif @@ -55,8 +57,9 @@ static inline int sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr, return syscall(__NR_bpf, cmd, attr, size); } -int bpf_create_map(enum bpf_map_type map_type, int key_size, - int value_size, int max_entries, __u32 map_flags) +int bpf_create_map_node(enum bpf_map_type map_type, int key_size, + int value_size, int max_entries, __u32 map_flags, + int node) { union bpf_attr attr; @@ -67,12 +70,24 @@ int bpf_create_map(enum bpf_map_type map_type, int key_size, attr.value_size = value_size; attr.max_entries = max_entries; attr.map_flags = map_flags; + if (node >= 0) { + attr.map_flags |= BPF_F_NUMA_NODE; + attr.numa_node = node; + } return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr)); } -int bpf_create_map_in_map(enum bpf_map_type map_type, int key_size, - int inner_map_fd, int max_entries, __u32 map_flags) +int bpf_create_map(enum bpf_map_type map_type, int key_size, + int value_size, int max_entries, __u32 map_flags) +{ + return bpf_create_map_node(map_type, key_size, value_size, + max_entries, map_flags, -1); +} + +int bpf_create_map_in_map_node(enum bpf_map_type map_type, int key_size, + int inner_map_fd, int max_entries, + __u32 map_flags, int node) { union bpf_attr attr; @@ -84,10 +99,21 @@ int bpf_create_map_in_map(enum bpf_map_type map_type, int key_size, attr.inner_map_fd = inner_map_fd; attr.max_entries = max_entries; attr.map_flags = map_flags; + if (node >= 0) { + attr.map_flags |= BPF_F_NUMA_NODE; + attr.numa_node = node; + } return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr)); } +int bpf_create_map_in_map(enum bpf_map_type map_type, int key_size, + int inner_map_fd, int max_entries, __u32 map_flags) +{ + return bpf_create_map_in_map_node(map_type, key_size, inner_map_fd, + max_entries, map_flags, -1); +} + int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, size_t insns_cnt, const char *license, __u32 kern_version, char *log_buf, size_t log_buf_sz) @@ -120,7 +146,7 @@ int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns, size_t insns_cnt, int strict_alignment, const char *license, __u32 kern_version, - char *log_buf, size_t log_buf_sz) + char *log_buf, size_t log_buf_sz, int log_level) { union bpf_attr attr; @@ -131,7 +157,7 @@ int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns, attr.license = ptr_to_u64(license); attr.log_buf = ptr_to_u64(log_buf); attr.log_size = log_buf_sz; - attr.log_level = 2; + attr.log_level = log_level; log_buf[0] = 0; attr.kern_version = kern_version; attr.prog_flags = strict_alignment ? BPF_F_STRICT_ALIGNMENT : 0; @@ -257,3 +283,70 @@ int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size, *duration = attr.test.duration; return ret; } + +int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id) +{ + union bpf_attr attr; + int err; + + bzero(&attr, sizeof(attr)); + attr.start_id = start_id; + + err = sys_bpf(BPF_PROG_GET_NEXT_ID, &attr, sizeof(attr)); + if (!err) + *next_id = attr.next_id; + + return err; +} + +int bpf_map_get_next_id(__u32 start_id, __u32 *next_id) +{ + union bpf_attr attr; + int err; + + bzero(&attr, sizeof(attr)); + attr.start_id = start_id; + + err = sys_bpf(BPF_MAP_GET_NEXT_ID, &attr, sizeof(attr)); + if (!err) + *next_id = attr.next_id; + + return err; +} + +int bpf_prog_get_fd_by_id(__u32 id) +{ + union bpf_attr attr; + + bzero(&attr, sizeof(attr)); + attr.prog_id = id; + + return sys_bpf(BPF_PROG_GET_FD_BY_ID, &attr, sizeof(attr)); +} + +int bpf_map_get_fd_by_id(__u32 id) +{ + union bpf_attr attr; + + bzero(&attr, sizeof(attr)); + attr.map_id = id; + + return sys_bpf(BPF_MAP_GET_FD_BY_ID, &attr, sizeof(attr)); +} + +int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len) +{ + union bpf_attr attr; + int err; + + bzero(&attr, sizeof(attr)); + attr.info.bpf_fd = prog_fd; + attr.info.info_len = *info_len; + attr.info.info = ptr_to_u64(info); + + err = sys_bpf(BPF_OBJ_GET_INFO_BY_FD, &attr, sizeof(attr)); + if (!err) + *info_len = attr.info.info_len; + + return err; +} diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 972bd8333eb7..b8ea5843c39e 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -24,8 +24,14 @@ #include <linux/bpf.h> #include <stddef.h> +int bpf_create_map_node(enum bpf_map_type map_type, int key_size, + int value_size, int max_entries, __u32 map_flags, + int node); int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size, int max_entries, __u32 map_flags); +int bpf_create_map_in_map_node(enum bpf_map_type map_type, int key_size, + int inner_map_fd, int max_entries, + __u32 map_flags, int node); int bpf_create_map_in_map(enum bpf_map_type map_type, int key_size, int inner_map_fd, int max_entries, __u32 map_flags); @@ -38,7 +44,7 @@ int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns, size_t insns_cnt, int strict_alignment, const char *license, __u32 kern_version, - char *log_buf, size_t log_buf_sz); + char *log_buf, size_t log_buf_sz, int log_level); int bpf_map_update_elem(int fd, const void *key, const void *value, __u64 flags); @@ -54,5 +60,10 @@ int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type); int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size, void *data_out, __u32 *size_out, __u32 *retval, __u32 *duration); +int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id); +int bpf_map_get_next_id(__u32 start_id, __u32 *next_id); +int bpf_prog_get_fd_by_id(__u32 id); +int bpf_map_get_fd_by_id(__u32 id); +int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len); #endif diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 1a2c07eb7795..35f6dfcdc565 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -879,7 +879,8 @@ bpf_object__create_maps(struct bpf_object *obj) size_t j; int err = *pfd; - pr_warning("failed to create map: %s\n", + pr_warning("failed to create map (name: '%s'): %s\n", + obj->maps[i].name, strerror(errno)); for (j = 0; j < i; j++) zclose(obj->maps[j].fd); @@ -1744,3 +1745,32 @@ long libbpf_get_error(const void *ptr) return PTR_ERR(ptr); return 0; } + +int bpf_prog_load(const char *file, enum bpf_prog_type type, + struct bpf_object **pobj, int *prog_fd) +{ + struct bpf_program *prog; + struct bpf_object *obj; + int err; + + obj = bpf_object__open(file); + if (IS_ERR(obj)) + return -ENOENT; + + prog = bpf_program__next(NULL, obj); + if (!prog) { + bpf_object__close(obj); + return -ENOENT; + } + + bpf_program__set_type(prog, type); + err = bpf_object__load(obj); + if (err) { + bpf_object__close(obj); + return -EINVAL; + } + + *pobj = obj; + *prog_fd = bpf_program__fd(prog); + return 0; +} diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 32c7252f734e..7959086eb9c9 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -243,4 +243,6 @@ int bpf_map__pin(struct bpf_map *map, const char *path); long libbpf_get_error(const void *ptr); +int bpf_prog_load(const char *file, enum bpf_prog_type type, + struct bpf_object **pobj, int *prog_fd); #endif diff --git a/tools/lib/lockdep/Makefile b/tools/lib/lockdep/Makefile index 3bc0ef9f8923..ed9ace59d112 100644 --- a/tools/lib/lockdep/Makefile +++ b/tools/lib/lockdep/Makefile @@ -79,6 +79,7 @@ INCLUDES = -I. -I./uinclude -I./include -I../../include $(CONFIG_INCLUDES) # Set compile option CFLAGS if not set elsewhere CFLAGS ?= -g -DCONFIG_LOCKDEP -DCONFIG_STACKTRACE -DCONFIG_PROVE_LOCKING -DBITS_PER_LONG=__WORDSIZE -DLIBLOCKDEP_VERSION='"$(LIBLOCKDEP_VERSION)"' -rdynamic -O0 -g CFLAGS += -fPIC +CFLAGS += -Wall override CFLAGS += $(CONFIG_FLAGS) $(INCLUDES) $(PLUGIN_DIR_SQ) @@ -100,7 +101,7 @@ include $(srctree)/tools/build/Makefile.include do_compile_shared_library = \ ($(print_shared_lib_compile) \ - $(CC) --shared $^ -o $@ -lpthread -ldl -Wl,-soname='"$@"';$(shell ln -sf $@ liblockdep.so)) + $(CC) $(LDFLAGS) --shared $^ -o $@ -lpthread -ldl -Wl,-soname='$(@F)';$(shell ln -sf $(@F) $(@D)/liblockdep.so)) do_build_static_lib = \ ($(print_static_lib_build) \ @@ -118,10 +119,10 @@ all_cmd: $(CMD_TARGETS) $(LIB_IN): force $(Q)$(MAKE) $(build)=liblockdep -liblockdep.so.$(LIBLOCKDEP_VERSION): $(LIB_IN) +$(OUTPUT)liblockdep.so.$(LIBLOCKDEP_VERSION): $(LIB_IN) $(Q)$(do_compile_shared_library) -liblockdep.a: $(LIB_IN) +$(OUTPUT)liblockdep.a: $(LIB_IN) $(Q)$(do_build_static_lib) tags: force @@ -149,7 +150,7 @@ install_lib: all_cmd install: install_lib clean: - $(RM) *.o *~ $(TARGETS) *.a *liblockdep*.so* $(VERSION_FILES) .*.d .*.cmd + $(RM) $(OUTPUT)*.o *~ $(TARGETS) $(OUTPUT)*.a $(OUTPUT)*liblockdep*.so* $(VERSION_FILES) $(OUTPUT).*.d $(OUTPUT).*.cmd $(RM) tags TAGS PHONY += force diff --git a/tools/lib/lockdep/lockdep.c b/tools/lib/lockdep/lockdep.c index a0a2e3a266af..ced6d7443cea 100644 --- a/tools/lib/lockdep/lockdep.c +++ b/tools/lib/lockdep/lockdep.c @@ -1,8 +1,27 @@ #include <linux/lockdep.h> +#include <stdlib.h> /* Trivial API wrappers, we don't (yet) have RCU in user-space: */ #define hlist_for_each_entry_rcu hlist_for_each_entry #define hlist_add_head_rcu hlist_add_head #define hlist_del_rcu hlist_del +#define list_for_each_entry_rcu list_for_each_entry +#define list_add_tail_rcu list_add_tail + +u32 prandom_u32(void) +{ + /* Used only by lock_pin_lock() which is dead code */ + abort(); +} + +static struct new_utsname *init_utsname(void) +{ + static struct new_utsname n = (struct new_utsname) { + .release = "liblockdep", + .version = LIBLOCKDEP_VERSION, + }; + + return &n; +} #include "../../../kernel/locking/lockdep.c" diff --git a/tools/lib/lockdep/preload.c b/tools/lib/lockdep/preload.c index 52844847569c..6a2d3c5d4e92 100644 --- a/tools/lib/lockdep/preload.c +++ b/tools/lib/lockdep/preload.c @@ -4,6 +4,7 @@ #include <dlfcn.h> #include <stdlib.h> #include <sysexits.h> +#include <unistd.h> #include "include/liblockdep/mutex.h" #include "../../include/linux/rbtree.h" @@ -122,8 +123,6 @@ static struct rb_node **__get_lock_node(void *lock, struct rb_node **parent) #define LIBLOCKDEP_STATIC_ENTRIES 1024 #endif -#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) - static struct lock_lookup __locks[LIBLOCKDEP_STATIC_ENTRIES]; static int __locks_nr; @@ -149,7 +148,7 @@ static struct lock_lookup *alloc_lock(void) int idx = __locks_nr++; if (idx >= ARRAY_SIZE(__locks)) { - fprintf(stderr, + dprintf(STDERR_FILENO, "LOCKDEP error: insufficient LIBLOCKDEP_STATIC_ENTRIES\n"); exit(EX_UNAVAILABLE); } diff --git a/tools/lib/lockdep/rbtree.c b/tools/lib/lockdep/rbtree.c index f7f43033c8b7..297c304571f8 100644 --- a/tools/lib/lockdep/rbtree.c +++ b/tools/lib/lockdep/rbtree.c @@ -1 +1 @@ -#include "../../../lib/rbtree.c" +#include "../../lib/rbtree.c" diff --git a/tools/lib/lockdep/run_tests.sh b/tools/lib/lockdep/run_tests.sh index 1069d96248c1..f9b94098fc98 100755 --- a/tools/lib/lockdep/run_tests.sh +++ b/tools/lib/lockdep/run_tests.sh @@ -4,9 +4,9 @@ make &> /dev/null for i in `ls tests/*.c`; do testname=$(basename "$i" .c) - gcc -o tests/$testname -pthread -lpthread $i liblockdep.a -Iinclude -D__USE_LIBLOCKDEP &> /dev/null + gcc -o tests/$testname -pthread $i liblockdep.a -Iinclude -D__USE_LIBLOCKDEP &> /dev/null echo -ne "$testname... " - if [ $(timeout 1 ./tests/$testname | wc -l) -gt 0 ]; then + if [ $(timeout 1 ./tests/$testname 2>&1 | wc -l) -gt 0 ]; then echo "PASSED!" else echo "FAILED!" @@ -18,9 +18,9 @@ done for i in `ls tests/*.c`; do testname=$(basename "$i" .c) - gcc -o tests/$testname -pthread -lpthread -Iinclude $i &> /dev/null + gcc -o tests/$testname -pthread -Iinclude $i &> /dev/null echo -ne "(PRELOAD) $testname... " - if [ $(timeout 1 ./lockdep ./tests/$testname | wc -l) -gt 0 ]; then + if [ $(timeout 1 ./lockdep ./tests/$testname 2>&1 | wc -l) -gt 0 ]; then echo "PASSED!" else echo "FAILED!" diff --git a/tools/lib/lockdep/uinclude/asm/hash.h b/tools/lib/lockdep/uinclude/asm/hash.h deleted file mode 100644 index d82b170bb216..000000000000 --- a/tools/lib/lockdep/uinclude/asm/hash.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __ASM_GENERIC_HASH_H -#define __ASM_GENERIC_HASH_H - -/* Stub */ - -#endif /* __ASM_GENERIC_HASH_H */ diff --git a/tools/lib/lockdep/uinclude/asm/hweight.h b/tools/lib/lockdep/uinclude/asm/hweight.h deleted file mode 100644 index fab00ff936d1..000000000000 --- a/tools/lib/lockdep/uinclude/asm/hweight.h +++ /dev/null @@ -1,3 +0,0 @@ - -/* empty file */ - diff --git a/tools/lib/lockdep/uinclude/asm/sections.h b/tools/lib/lockdep/uinclude/asm/sections.h deleted file mode 100644 index fab00ff936d1..000000000000 --- a/tools/lib/lockdep/uinclude/asm/sections.h +++ /dev/null @@ -1,3 +0,0 @@ - -/* empty file */ - diff --git a/tools/lib/lockdep/uinclude/linux/bitops.h b/tools/lib/lockdep/uinclude/linux/bitops.h deleted file mode 100644 index fab00ff936d1..000000000000 --- a/tools/lib/lockdep/uinclude/linux/bitops.h +++ /dev/null @@ -1,3 +0,0 @@ - -/* empty file */ - diff --git a/tools/lib/lockdep/uinclude/linux/compiler.h b/tools/lib/lockdep/uinclude/linux/compiler.h deleted file mode 100644 index fd3e56a83fc2..000000000000 --- a/tools/lib/lockdep/uinclude/linux/compiler.h +++ /dev/null @@ -1,10 +0,0 @@ -#ifndef _LIBLOCKDEP_LINUX_COMPILER_H_ -#define _LIBLOCKDEP_LINUX_COMPILER_H_ - -#define __used __attribute__((__unused__)) -#define unlikely -#define READ_ONCE(x) (x) -#define WRITE_ONCE(x, val) x=(val) -#define RCU_INIT_POINTER(p, v) p=(v) - -#endif diff --git a/tools/lib/lockdep/uinclude/linux/delay.h b/tools/lib/lockdep/uinclude/linux/delay.h deleted file mode 100644 index fab00ff936d1..000000000000 --- a/tools/lib/lockdep/uinclude/linux/delay.h +++ /dev/null @@ -1,3 +0,0 @@ - -/* empty file */ - diff --git a/tools/lib/lockdep/uinclude/linux/ftrace.h b/tools/lib/lockdep/uinclude/linux/ftrace.h deleted file mode 100644 index fab00ff936d1..000000000000 --- a/tools/lib/lockdep/uinclude/linux/ftrace.h +++ /dev/null @@ -1,3 +0,0 @@ - -/* empty file */ - diff --git a/tools/lib/lockdep/uinclude/linux/gfp.h b/tools/lib/lockdep/uinclude/linux/gfp.h deleted file mode 100644 index fab00ff936d1..000000000000 --- a/tools/lib/lockdep/uinclude/linux/gfp.h +++ /dev/null @@ -1,3 +0,0 @@ - -/* empty file */ - diff --git a/tools/lib/lockdep/uinclude/linux/hash.h b/tools/lib/lockdep/uinclude/linux/hash.h deleted file mode 100644 index 0f8479858dc0..000000000000 --- a/tools/lib/lockdep/uinclude/linux/hash.h +++ /dev/null @@ -1 +0,0 @@ -#include "../../../include/linux/hash.h" diff --git a/tools/lib/lockdep/uinclude/linux/interrupt.h b/tools/lib/lockdep/uinclude/linux/interrupt.h deleted file mode 100644 index fab00ff936d1..000000000000 --- a/tools/lib/lockdep/uinclude/linux/interrupt.h +++ /dev/null @@ -1,3 +0,0 @@ - -/* empty file */ - diff --git a/tools/lib/lockdep/uinclude/linux/kernel.h b/tools/lib/lockdep/uinclude/linux/kernel.h deleted file mode 100644 index 276c7a8b2ed1..000000000000 --- a/tools/lib/lockdep/uinclude/linux/kernel.h +++ /dev/null @@ -1,47 +0,0 @@ -#ifndef _LIBLOCKDEP_LINUX_KERNEL_H_ -#define _LIBLOCKDEP_LINUX_KERNEL_H_ - -#include <linux/export.h> -#include <linux/types.h> -#include <linux/rcu.h> -#include <linux/hardirq.h> -#include <linux/kern_levels.h> - -#ifndef container_of -#define container_of(ptr, type, member) ({ \ - const typeof(((type *)0)->member) * __mptr = (ptr); \ - (type *)((char *)__mptr - offsetof(type, member)); }) -#endif - -#define max(x, y) ({ \ - typeof(x) _max1 = (x); \ - typeof(y) _max2 = (y); \ - (void) (&_max1 == &_max2); \ - _max1 > _max2 ? _max1 : _max2; }) - -#define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)])) -#define WARN_ON(x) (x) -#define WARN_ON_ONCE(x) (x) -#define likely(x) (x) -#define WARN(x, y...) (x) -#define uninitialized_var(x) x -#define __init -#define noinline -#define list_add_tail_rcu list_add_tail -#define list_for_each_entry_rcu list_for_each_entry -#define barrier() -#define synchronize_sched() - -#ifndef CALLER_ADDR0 -#define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0)) -#endif - -#ifndef _RET_IP_ -#define _RET_IP_ CALLER_ADDR0 -#endif - -#ifndef _THIS_IP_ -#define _THIS_IP_ ({ __label__ __here; __here: (unsigned long)&&__here; }) -#endif - -#endif diff --git a/tools/lib/lockdep/uinclude/linux/linkage.h b/tools/lib/lockdep/uinclude/linux/linkage.h deleted file mode 100644 index fab00ff936d1..000000000000 --- a/tools/lib/lockdep/uinclude/linux/linkage.h +++ /dev/null @@ -1,3 +0,0 @@ - -/* empty file */ - diff --git a/tools/lib/lockdep/uinclude/linux/list.h b/tools/lib/lockdep/uinclude/linux/list.h deleted file mode 100644 index 6e9ef31ed82e..000000000000 --- a/tools/lib/lockdep/uinclude/linux/list.h +++ /dev/null @@ -1 +0,0 @@ -#include "../../../include/linux/list.h" diff --git a/tools/lib/lockdep/uinclude/linux/mutex.h b/tools/lib/lockdep/uinclude/linux/mutex.h deleted file mode 100644 index fab00ff936d1..000000000000 --- a/tools/lib/lockdep/uinclude/linux/mutex.h +++ /dev/null @@ -1,3 +0,0 @@ - -/* empty file */ - diff --git a/tools/lib/lockdep/uinclude/linux/poison.h b/tools/lib/lockdep/uinclude/linux/poison.h deleted file mode 100644 index 0c27bdf14233..000000000000 --- a/tools/lib/lockdep/uinclude/linux/poison.h +++ /dev/null @@ -1 +0,0 @@ -#include "../../../include/linux/poison.h" diff --git a/tools/lib/lockdep/uinclude/linux/prefetch.h b/tools/lib/lockdep/uinclude/linux/prefetch.h deleted file mode 100644 index d73fe6f850ac..000000000000 --- a/tools/lib/lockdep/uinclude/linux/prefetch.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef _LIBLOCKDEP_LINUX_PREFETCH_H_ -#define _LIBLOCKDEP_LINUX_PREFETCH_H - -static inline void prefetch(void *a __attribute__((unused))) { } - -#endif diff --git a/tools/lib/lockdep/uinclude/linux/proc_fs.h b/tools/lib/lockdep/uinclude/linux/proc_fs.h deleted file mode 100644 index fab00ff936d1..000000000000 --- a/tools/lib/lockdep/uinclude/linux/proc_fs.h +++ /dev/null @@ -1,3 +0,0 @@ - -/* empty file */ - diff --git a/tools/lib/lockdep/uinclude/linux/rbtree_augmented.h b/tools/lib/lockdep/uinclude/linux/rbtree_augmented.h deleted file mode 100644 index c3759477379c..000000000000 --- a/tools/lib/lockdep/uinclude/linux/rbtree_augmented.h +++ /dev/null @@ -1,2 +0,0 @@ -#define __always_inline -#include "../../../include/linux/rbtree_augmented.h" diff --git a/tools/lib/lockdep/uinclude/linux/seq_file.h b/tools/lib/lockdep/uinclude/linux/seq_file.h deleted file mode 100644 index fab00ff936d1..000000000000 --- a/tools/lib/lockdep/uinclude/linux/seq_file.h +++ /dev/null @@ -1,3 +0,0 @@ - -/* empty file */ - diff --git a/tools/lib/lockdep/uinclude/linux/spinlock.h b/tools/lib/lockdep/uinclude/linux/spinlock.h deleted file mode 100644 index 68c1aa2bcba5..000000000000 --- a/tools/lib/lockdep/uinclude/linux/spinlock.h +++ /dev/null @@ -1,25 +0,0 @@ -#ifndef _LIBLOCKDEP_SPINLOCK_H_ -#define _LIBLOCKDEP_SPINLOCK_H_ - -#include <pthread.h> -#include <stdbool.h> - -#define arch_spinlock_t pthread_mutex_t -#define __ARCH_SPIN_LOCK_UNLOCKED PTHREAD_MUTEX_INITIALIZER - -static inline void arch_spin_lock(arch_spinlock_t *mutex) -{ - pthread_mutex_lock(mutex); -} - -static inline void arch_spin_unlock(arch_spinlock_t *mutex) -{ - pthread_mutex_unlock(mutex); -} - -static inline bool arch_spin_is_locked(arch_spinlock_t *mutex) -{ - return true; -} - -#endif diff --git a/tools/lib/lockdep/uinclude/linux/stringify.h b/tools/lib/lockdep/uinclude/linux/stringify.h deleted file mode 100644 index 05dfcd1ac118..000000000000 --- a/tools/lib/lockdep/uinclude/linux/stringify.h +++ /dev/null @@ -1,7 +0,0 @@ -#ifndef _LIBLOCKDEP_LINUX_STRINGIFY_H_ -#define _LIBLOCKDEP_LINUX_STRINGIFY_H_ - -#define __stringify_1(x...) #x -#define __stringify(x...) __stringify_1(x) - -#endif diff --git a/tools/lib/lockdep/uinclude/trace/events/lock.h b/tools/lib/lockdep/uinclude/trace/events/lock.h deleted file mode 100644 index fab00ff936d1..000000000000 --- a/tools/lib/lockdep/uinclude/trace/events/lock.h +++ /dev/null @@ -1,3 +0,0 @@ - -/* empty file */ - diff --git a/tools/lib/string.c b/tools/lib/string.c index 8e678af1c6ee..a4246f14ded1 100644 --- a/tools/lib/string.c +++ b/tools/lib/string.c @@ -39,27 +39,45 @@ void *memdup(const void *src, size_t len) * @s: input string * @res: result * - * This routine returns 0 iff the first character is one of 'Yy1Nn0'. - * Otherwise it will return -EINVAL. Value pointed to by res is - * updated upon finding a match. + * This routine returns 0 iff the first character is one of 'Yy1Nn0', or + * [oO][NnFf] for "on" and "off". Otherwise it will return -EINVAL. Value + * pointed to by res is updated upon finding a match. */ int strtobool(const char *s, bool *res) { + if (!s) + return -EINVAL; + switch (s[0]) { case 'y': case 'Y': case '1': *res = true; - break; + return 0; case 'n': case 'N': case '0': *res = false; - break; + return 0; + case 'o': + case 'O': + switch (s[1]) { + case 'n': + case 'N': + *res = true; + return 0; + case 'f': + case 'F': + *res = false; + return 0; + default: + break; + } default: - return -EINVAL; + break; } - return 0; + + return -EINVAL; } /** @@ -87,12 +105,3 @@ size_t __weak strlcpy(char *dest, const char *src, size_t size) } return ret; } - -int prefixcmp(const char *str, const char *prefix) -{ - for (; ; str++, prefix++) - if (!*prefix) - return 0; - else if (*str != *prefix) - return (unsigned char)*prefix - (unsigned char)*str; -} diff --git a/tools/lib/subcmd/Makefile b/tools/lib/subcmd/Makefile index 3d1c3b5b5150..7e9f03c97e4c 100644 --- a/tools/lib/subcmd/Makefile +++ b/tools/lib/subcmd/Makefile @@ -21,7 +21,7 @@ LIBFILE = $(OUTPUT)libsubcmd.a CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC -ifeq ($(CC), clang) +ifeq ($(CC_NO_CLANG), 0) CFLAGS += -O3 else CFLAGS += -O6 diff --git a/tools/lib/subcmd/help.c b/tools/lib/subcmd/help.c index ba970a73d053..0310520f918e 100644 --- a/tools/lib/subcmd/help.c +++ b/tools/lib/subcmd/help.c @@ -171,7 +171,7 @@ static void list_commands_in_dir(struct cmdnames *cmds, while ((de = readdir(dir)) != NULL) { int entlen; - if (prefixcmp(de->d_name, prefix)) + if (!strstarts(de->d_name, prefix)) continue; astrcat(&buf, de->d_name); diff --git a/tools/lib/subcmd/parse-options.c b/tools/lib/subcmd/parse-options.c index 359bfa77f39c..2bd6fd0c1d40 100644 --- a/tools/lib/subcmd/parse-options.c +++ b/tools/lib/subcmd/parse-options.c @@ -368,7 +368,7 @@ retry: return 0; } if (!rest) { - if (!prefixcmp(options->long_name, "no-")) { + if (strstarts(options->long_name, "no-")) { /* * The long name itself starts with "no-", so * accept the option without "no-" so that users @@ -381,7 +381,7 @@ retry: goto match; } /* Abbreviated case */ - if (!prefixcmp(options->long_name + 3, arg)) { + if (strstarts(options->long_name + 3, arg)) { flags |= OPT_UNSET; goto is_abbreviated; } @@ -406,7 +406,7 @@ is_abbreviated: continue; } /* negated and abbreviated very much? */ - if (!prefixcmp("no-", arg)) { + if (strstarts("no-", arg)) { flags |= OPT_UNSET; goto is_abbreviated; } @@ -416,7 +416,7 @@ is_abbreviated: flags |= OPT_UNSET; rest = skip_prefix(arg + 3, options->long_name); /* abbreviated and negated? */ - if (!rest && !prefixcmp(options->long_name, arg + 3)) + if (!rest && strstarts(options->long_name, arg + 3)) goto is_abbreviated; if (!rest) continue; @@ -456,7 +456,7 @@ static void check_typos(const char *arg, const struct option *options) if (strlen(arg) < 3) return; - if (!prefixcmp(arg, "no-")) { + if (strstarts(arg, "no-")) { fprintf(stderr, " Error: did you mean `--%s` (with two dashes ?)", arg); exit(129); } @@ -464,7 +464,7 @@ static void check_typos(const char *arg, const struct option *options) for (; options->type != OPTION_END; options++) { if (!options->long_name) continue; - if (!prefixcmp(options->long_name, arg)) { + if (strstarts(options->long_name, arg)) { fprintf(stderr, " Error: did you mean `--%s` (with two dashes ?)", arg); exit(129); } @@ -933,10 +933,10 @@ opt: if (opts->long_name == NULL) continue; - if (!prefixcmp(opts->long_name, optstr)) + if (strstarts(opts->long_name, optstr)) print_option_help(opts, 0); - if (!prefixcmp("no-", optstr) && - !prefixcmp(opts->long_name, optstr + 3)) + if (strstarts("no-", optstr) && + strstarts(opts->long_name, optstr + 3)) print_option_help(opts, 0); } diff --git a/tools/net/bpf_jit_disasm.c b/tools/net/bpf_jit_disasm.c index ad572e6cdbd0..422d9abd666a 100644 --- a/tools/net/bpf_jit_disasm.c +++ b/tools/net/bpf_jit_disasm.c @@ -159,8 +159,8 @@ static void put_log_buff(char *buff) free(buff); } -static unsigned int get_last_jit_image(char *haystack, size_t hlen, - uint8_t *image, size_t ilen) +static uint8_t *get_last_jit_image(char *haystack, size_t hlen, + unsigned int *ilen) { char *ptr, *pptr, *tmp; off_t off = 0; @@ -168,9 +168,10 @@ static unsigned int get_last_jit_image(char *haystack, size_t hlen, regmatch_t pmatch[1]; unsigned long base; regex_t regex; + uint8_t *image; if (hlen == 0) - return 0; + return NULL; ret = regcomp(®ex, "flen=[[:alnum:]]+ proglen=[[:digit:]]+ " "pass=[[:digit:]]+ image=[[:xdigit:]]+", REG_EXTENDED); @@ -194,11 +195,22 @@ static unsigned int get_last_jit_image(char *haystack, size_t hlen, &flen, &proglen, &pass, &base); if (ret != 4) { regfree(®ex); - return 0; + return NULL; + } + if (proglen > 1000000) { + printf("proglen of %d too big, stopping\n", proglen); + return NULL; } + image = malloc(proglen); + if (!image) { + printf("Out of memory\n"); + return NULL; + } + memset(image, 0, proglen); + tmp = ptr = haystack + off; - while ((ptr = strtok(tmp, "\n")) != NULL && ulen < ilen) { + while ((ptr = strtok(tmp, "\n")) != NULL && ulen < proglen) { tmp = NULL; if (!strstr(ptr, "JIT code")) continue; @@ -208,10 +220,12 @@ static unsigned int get_last_jit_image(char *haystack, size_t hlen, ptr = pptr; do { image[ulen++] = (uint8_t) strtoul(pptr, &pptr, 16); - if (ptr == pptr || ulen >= ilen) { + if (ptr == pptr) { ulen--; break; } + if (ulen >= proglen) + break; ptr = pptr; } while (1); } @@ -222,7 +236,8 @@ static unsigned int get_last_jit_image(char *haystack, size_t hlen, printf("%lx + <x>:\n", base); regfree(®ex); - return ulen; + *ilen = ulen; + return image; } static void usage(void) @@ -237,12 +252,12 @@ static void usage(void) int main(int argc, char **argv) { unsigned int len, klen, opt, opcodes = 0; - static uint8_t image[32768]; char *kbuff, *file = NULL; char *ofile = NULL; int ofd; ssize_t nr; uint8_t *pos; + uint8_t *image = NULL; while ((opt = getopt(argc, argv, "of:O:")) != -1) { switch (opt) { @@ -262,7 +277,6 @@ int main(int argc, char **argv) } bfd_init(); - memset(image, 0, sizeof(image)); kbuff = get_log_buff(file, &klen); if (!kbuff) { @@ -270,8 +284,8 @@ int main(int argc, char **argv) return -1; } - len = get_last_jit_image(kbuff, klen, image, sizeof(image)); - if (len <= 0) { + image = get_last_jit_image(kbuff, klen, &len); + if (!image) { fprintf(stderr, "No JIT image found!\n"); goto done; } @@ -301,5 +315,6 @@ int main(int argc, char **argv) done: put_log_buff(kbuff); + free(image); return 0; } diff --git a/tools/objtool/Build b/tools/objtool/Build index d6cdece5e58b..749becdf5b90 100644 --- a/tools/objtool/Build +++ b/tools/objtool/Build @@ -1,5 +1,9 @@ objtool-y += arch/$(SRCARCH)/ objtool-y += builtin-check.o +objtool-y += builtin-orc.o +objtool-y += check.o +objtool-y += orc_gen.o +objtool-y += orc_dump.o objtool-y += elf.o objtool-y += special.o objtool-y += objtool.o diff --git a/tools/objtool/Documentation/stack-validation.txt b/tools/objtool/Documentation/stack-validation.txt index 55a60d331f47..6a1af43862df 100644 --- a/tools/objtool/Documentation/stack-validation.txt +++ b/tools/objtool/Documentation/stack-validation.txt @@ -11,9 +11,6 @@ analyzes every .o file and ensures the validity of its stack metadata. It enforces a set of rules on asm code and C inline assembly code so that stack traces can be reliable. -Currently it only checks frame pointer usage, but there are plans to add -CFI validation for C files and CFI generation for asm files. - For each function, it recursively follows all possible code paths and validates the correct frame pointer state at each instruction. @@ -23,6 +20,10 @@ alternative execution paths to a given instruction (or set of instructions). Similarly, it knows how to follow switch statements, for which gcc sometimes uses jump tables. +(Objtool also has an 'orc generate' subcommand which generates debuginfo +for the ORC unwinder. See Documentation/x86/orc-unwinder.txt in the +kernel tree for more details.) + Why do we need stack metadata validation? ----------------------------------------- @@ -93,62 +94,24 @@ a) More reliable stack traces for frame pointer enabled kernels or at the very end of the function after the stack frame has been destroyed. This is an inherent limitation of frame pointers. -b) 100% reliable stack traces for DWARF enabled kernels - - (NOTE: This is not yet implemented) - - As an alternative to frame pointers, DWARF Call Frame Information - (CFI) metadata can be used to walk the stack. Unlike frame pointers, - CFI metadata is out of band. So it doesn't affect runtime - performance and it can be reliable even when interrupts or exceptions - are involved. +b) ORC (Oops Rewind Capability) unwind table generation - For C code, gcc automatically generates DWARF CFI metadata. But for - asm code, generating CFI is a tedious manual approach which requires - manually placed .cfi assembler macros to be scattered throughout the - code. It's clumsy and very easy to get wrong, and it makes the real - code harder to read. + An alternative to frame pointers and DWARF, ORC unwind data can be + used to walk the stack. Unlike frame pointers, ORC data is out of + band. So it doesn't affect runtime performance and it can be + reliable even when interrupts or exceptions are involved. - Stacktool will improve this situation in several ways. For code - which already has CFI annotations, it will validate them. For code - which doesn't have CFI annotations, it will generate them. So an - architecture can opt to strip out all the manual .cfi annotations - from their asm code and have objtool generate them instead. - - We might also add a runtime stack validation debug option where we - periodically walk the stack from schedule() and/or an NMI to ensure - that the stack metadata is sane and that we reach the bottom of the - stack. - - So the benefit of objtool here will be that external tooling should - always show perfect stack traces. And the same will be true for - kernel warning/oops traces if the architecture has a runtime DWARF - unwinder. + For more details, see Documentation/x86/orc-unwinder.txt. c) Higher live patching compatibility rate - (NOTE: This is not yet implemented) - - Currently with CONFIG_LIVEPATCH there's a basic live patching - framework which is safe for roughly 85-90% of "security" fixes. But - patches can't have complex features like function dependency or - prototype changes, or data structure changes. - - There's a strong need to support patches which have the more complex - features so that the patch compatibility rate for security fixes can - eventually approach something resembling 100%. To achieve that, a - "consistency model" is needed, which allows tasks to be safely - transitioned from an unpatched state to a patched state. - - One of the key requirements of the currently proposed livepatch - consistency model [*] is that it needs to walk the stack of each - sleeping task to determine if it can be transitioned to the patched - state. If objtool can ensure that stack traces are reliable, this - consistency model can be used and the live patching compatibility - rate can be improved significantly. - - [*] https://lkml.kernel.org/r/cover.1423499826.git.jpoimboe@redhat.com + Livepatch has an optional "consistency model", which is needed for + more complex patches. In order for the consistency model to work, + stack traces need to be reliable (or an unreliable condition needs to + be detectable). Objtool makes that possible. + For more details, see the livepatch documentation in the Linux kernel + source tree at Documentation/livepatch/livepatch.txt. Rules ----- @@ -201,80 +164,84 @@ To achieve the validation, objtool enforces the following rules: return normally. -Errors in .S files ------------------- +Objtool warnings +---------------- -If you're getting an error in a compiled .S file which you don't -understand, first make sure that the affected code follows the above -rules. +For asm files, if you're getting an error which doesn't make sense, +first make sure that the affected code follows the above rules. + +For C files, the common culprits are inline asm statements and calls to +"noreturn" functions. See below for more details. + +Another possible cause for errors in C code is if the Makefile removes +-fno-omit-frame-pointer or adds -fomit-frame-pointer to the gcc options. Here are some examples of common warnings reported by objtool, what they mean, and suggestions for how to fix them. -1. asm_file.o: warning: objtool: func()+0x128: call without frame pointer save/setup +1. file.o: warning: objtool: func()+0x128: call without frame pointer save/setup The func() function made a function call without first saving and/or - updating the frame pointer. - - If func() is indeed a callable function, add proper frame pointer - logic using the FRAME_BEGIN and FRAME_END macros. Otherwise, remove - its ELF function annotation by changing ENDPROC to END. + updating the frame pointer, and CONFIG_FRAME_POINTER is enabled. - If you're getting this error in a .c file, see the "Errors in .c - files" section. + If the error is for an asm file, and func() is indeed a callable + function, add proper frame pointer logic using the FRAME_BEGIN and + FRAME_END macros. Otherwise, if it's not a callable function, remove + its ELF function annotation by changing ENDPROC to END, and instead + use the manual unwind hint macros in asm/unwind_hints.h. + If it's a GCC-compiled .c file, the error may be because the function + uses an inline asm() statement which has a "call" instruction. An + asm() statement with a call instruction must declare the use of the + stack pointer in its output operand. For example, on x86_64: -2. asm_file.o: warning: objtool: .text+0x53: return instruction outside of a callable function - - A return instruction was detected, but objtool couldn't find a way - for a callable function to reach the instruction. + register void *__sp asm("rsp"); + asm volatile("call func" : "+r" (__sp)); - If the return instruction is inside (or reachable from) a callable - function, the function needs to be annotated with the ENTRY/ENDPROC - macros. + Otherwise the stack frame may not get created before the call. - If you _really_ need a return instruction outside of a function, and - are 100% sure that it won't affect stack traces, you can tell - objtool to ignore it. See the "Adding exceptions" section below. +2. file.o: warning: objtool: .text+0x53: unreachable instruction -3. asm_file.o: warning: objtool: func()+0x9: function has unreachable instruction + Objtool couldn't find a code path to reach the instruction. - The instruction lives inside of a callable function, but there's no - possible control flow path from the beginning of the function to the - instruction. + If the error is for an asm file, and the instruction is inside (or + reachable from) a callable function, the function should be annotated + with the ENTRY/ENDPROC macros (ENDPROC is the important one). + Otherwise, the code should probably be annotated with the unwind hint + macros in asm/unwind_hints.h so objtool and the unwinder can know the + stack state associated with the code. - If the instruction is actually needed, and it's actually in a - callable function, ensure that its function is properly annotated - with ENTRY/ENDPROC. + If you're 100% sure the code won't affect stack traces, or if you're + a just a bad person, you can tell objtool to ignore it. See the + "Adding exceptions" section below. If it's not actually in a callable function (e.g. kernel entry code), change ENDPROC to END. -4. asm_file.o: warning: objtool: func(): can't find starting instruction +4. file.o: warning: objtool: func(): can't find starting instruction or - asm_file.o: warning: objtool: func()+0x11dd: can't decode instruction + file.o: warning: objtool: func()+0x11dd: can't decode instruction - Did you put data in a text section? If so, that can confuse + Does the file have data in a text section? If so, that can confuse objtool's instruction decoder. Move the data to a more appropriate section like .data or .rodata. -5. asm_file.o: warning: objtool: func()+0x6: kernel entry/exit from callable instruction - - This is a kernel entry/exit instruction like sysenter or sysret. - Such instructions aren't allowed in a callable function, and are most - likely part of the kernel entry code. +5. file.o: warning: objtool: func()+0x6: unsupported instruction in callable function - If the instruction isn't actually in a callable function, change - ENDPROC to END. + This is a kernel entry/exit instruction like sysenter or iret. Such + instructions aren't allowed in a callable function, and are most + likely part of the kernel entry code. They should usually not have + the callable function annotation (ENDPROC) and should always be + annotated with the unwind hint macros in asm/unwind_hints.h. -6. asm_file.o: warning: objtool: func()+0x26: sibling call from callable instruction with changed frame pointer +6. file.o: warning: objtool: func()+0x26: sibling call from callable instruction with modified stack frame - This is a dynamic jump or a jump to an undefined symbol. Stacktool + This is a dynamic jump or a jump to an undefined symbol. Objtool assumed it's a sibling call and detected that the frame pointer wasn't first restored to its original state. @@ -282,24 +249,28 @@ they mean, and suggestions for how to fix them. destination code to the local file. If the instruction is not actually in a callable function (e.g. - kernel entry code), change ENDPROC to END. + kernel entry code), change ENDPROC to END and annotate manually with + the unwind hint macros in asm/unwind_hints.h. -7. asm_file: warning: objtool: func()+0x5c: frame pointer state mismatch +7. file: warning: objtool: func()+0x5c: stack state mismatch The instruction's frame pointer state is inconsistent, depending on which execution path was taken to reach the instruction. - Make sure the function pushes and sets up the frame pointer (for - x86_64, this means rbp) at the beginning of the function and pops it - at the end of the function. Also make sure that no other code in the - function touches the frame pointer. + Make sure that, when CONFIG_FRAME_POINTER is enabled, the function + pushes and sets up the frame pointer (for x86_64, this means rbp) at + the beginning of the function and pops it at the end of the function. + Also make sure that no other code in the function touches the frame + pointer. + Another possibility is that the code has some asm or inline asm which + does some unusual things to the stack or the frame pointer. In such + cases it's probably appropriate to use the unwind hint macros in + asm/unwind_hints.h. -Errors in .c files ------------------- -1. c_file.o: warning: objtool: funcA() falls through to next function funcB() +8. file.o: warning: objtool: funcA() falls through to next function funcB() This means that funcA() doesn't end with a return instruction or an unconditional jump, and that objtool has determined that the function @@ -318,22 +289,6 @@ Errors in .c files might be corrupt due to a gcc bug. For more details, see: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=70646 -2. If you're getting any other objtool error in a compiled .c file, it - may be because the file uses an asm() statement which has a "call" - instruction. An asm() statement with a call instruction must declare - the use of the stack pointer in its output operand. For example, on - x86_64: - - register void *__sp asm("rsp"); - asm volatile("call func" : "+r" (__sp)); - - Otherwise the stack frame may not get created before the call. - -3. Another possible cause for errors in C code is if the Makefile removes - -fno-omit-frame-pointer or adds -fomit-frame-pointer to the gcc options. - -Also see the above section for .S file errors for more information what -the individual error messages mean. If the error doesn't seem to make sense, it could be a bug in objtool. Feel free to ask the objtool maintainer for help. diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile index 27e019c09bd2..6976c73e60c4 100644 --- a/tools/objtool/Makefile +++ b/tools/objtool/Makefile @@ -25,7 +25,8 @@ OBJTOOL_IN := $(OBJTOOL)-in.o all: $(OBJTOOL) INCLUDES := -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(HOSTARCH)/include/uapi -CFLAGS += -Wall -Werror $(EXTRA_WARNINGS) -fomit-frame-pointer -O2 -g $(INCLUDES) +WARNINGS := $(EXTRA_WARNINGS) -Wno-switch-default -Wno-switch-enum -Wno-packed +CFLAGS += -Wall -Werror $(WARNINGS) -fomit-frame-pointer -O2 -g $(INCLUDES) LDFLAGS += -lelf $(LIBSUBCMD) # Allow old libelf to be used: @@ -52,6 +53,9 @@ $(OBJTOOL): $(LIBSUBCMD) $(OBJTOOL_IN) diff -I'^#include' arch/x86/insn/inat.h ../../arch/x86/include/asm/inat.h >/dev/null && \ diff -I'^#include' arch/x86/insn/inat_types.h ../../arch/x86/include/asm/inat_types.h >/dev/null) \ || echo "warning: objtool: x86 instruction decoder differs from kernel" >&2 )) || true + @(test -d ../../kernel -a -d ../../tools -a -d ../objtool && (( \ + diff ../../arch/x86/include/asm/orc_types.h orc_types.h >/dev/null) \ + || echo "warning: objtool: orc_types.h differs from kernel" >&2 )) || true $(QUIET_LINK)$(CC) $(OBJTOOL_IN) $(LDFLAGS) -o $@ diff --git a/tools/objtool/arch.h b/tools/objtool/arch.h index a59e061c0b4a..b0d7dc3d71b5 100644 --- a/tools/objtool/arch.h +++ b/tools/objtool/arch.h @@ -19,25 +19,64 @@ #define _ARCH_H #include <stdbool.h> +#include <linux/list.h> #include "elf.h" +#include "cfi.h" -#define INSN_FP_SAVE 1 -#define INSN_FP_SETUP 2 -#define INSN_FP_RESTORE 3 -#define INSN_JUMP_CONDITIONAL 4 -#define INSN_JUMP_UNCONDITIONAL 5 -#define INSN_JUMP_DYNAMIC 6 -#define INSN_CALL 7 -#define INSN_CALL_DYNAMIC 8 -#define INSN_RETURN 9 -#define INSN_CONTEXT_SWITCH 10 -#define INSN_NOP 11 -#define INSN_OTHER 12 +#define INSN_JUMP_CONDITIONAL 1 +#define INSN_JUMP_UNCONDITIONAL 2 +#define INSN_JUMP_DYNAMIC 3 +#define INSN_CALL 4 +#define INSN_CALL_DYNAMIC 5 +#define INSN_RETURN 6 +#define INSN_CONTEXT_SWITCH 7 +#define INSN_STACK 8 +#define INSN_BUG 9 +#define INSN_NOP 10 +#define INSN_OTHER 11 #define INSN_LAST INSN_OTHER +enum op_dest_type { + OP_DEST_REG, + OP_DEST_REG_INDIRECT, + OP_DEST_MEM, + OP_DEST_PUSH, + OP_DEST_LEAVE, +}; + +struct op_dest { + enum op_dest_type type; + unsigned char reg; + int offset; +}; + +enum op_src_type { + OP_SRC_REG, + OP_SRC_REG_INDIRECT, + OP_SRC_CONST, + OP_SRC_POP, + OP_SRC_ADD, + OP_SRC_AND, +}; + +struct op_src { + enum op_src_type type; + unsigned char reg; + int offset; +}; + +struct stack_op { + struct op_dest dest; + struct op_src src; +}; + +void arch_initial_func_cfi_state(struct cfi_state *state); + int arch_decode_instruction(struct elf *elf, struct section *sec, unsigned long offset, unsigned int maxlen, unsigned int *len, unsigned char *type, - unsigned long *displacement); + unsigned long *immediate, struct stack_op *op); + +bool arch_callee_saved_reg(unsigned char reg); #endif /* _ARCH_H */ diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 6ac99e3266eb..0e8c8ec4fd4e 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -27,6 +27,17 @@ #include "../../arch.h" #include "../../warn.h" +static unsigned char op_to_cfi_reg[][2] = { + {CFI_AX, CFI_R8}, + {CFI_CX, CFI_R9}, + {CFI_DX, CFI_R10}, + {CFI_BX, CFI_R11}, + {CFI_SP, CFI_R12}, + {CFI_BP, CFI_R13}, + {CFI_SI, CFI_R14}, + {CFI_DI, CFI_R15}, +}; + static int is_x86_64(struct elf *elf) { switch (elf->ehdr.e_machine) { @@ -40,24 +51,50 @@ static int is_x86_64(struct elf *elf) } } +bool arch_callee_saved_reg(unsigned char reg) +{ + switch (reg) { + case CFI_BP: + case CFI_BX: + case CFI_R12: + case CFI_R13: + case CFI_R14: + case CFI_R15: + return true; + + case CFI_AX: + case CFI_CX: + case CFI_DX: + case CFI_SI: + case CFI_DI: + case CFI_SP: + case CFI_R8: + case CFI_R9: + case CFI_R10: + case CFI_R11: + case CFI_RA: + default: + return false; + } +} + int arch_decode_instruction(struct elf *elf, struct section *sec, unsigned long offset, unsigned int maxlen, unsigned int *len, unsigned char *type, - unsigned long *immediate) + unsigned long *immediate, struct stack_op *op) { struct insn insn; - int x86_64; - unsigned char op1, op2, ext; + int x86_64, sign; + unsigned char op1, op2, rex = 0, rex_b = 0, rex_r = 0, rex_w = 0, + rex_x = 0, modrm = 0, modrm_mod = 0, modrm_rm = 0, + modrm_reg = 0, sib = 0; x86_64 = is_x86_64(elf); if (x86_64 == -1) return -1; - insn_init(&insn, (void *)(sec->data + offset), maxlen, x86_64); + insn_init(&insn, sec->data->d_buf + offset, maxlen, x86_64); insn_get_length(&insn); - insn_get_opcode(&insn); - insn_get_modrm(&insn); - insn_get_immediate(&insn); if (!insn_complete(&insn)) { WARN_FUNC("can't decode instruction", sec, offset); @@ -73,67 +110,312 @@ int arch_decode_instruction(struct elf *elf, struct section *sec, op1 = insn.opcode.bytes[0]; op2 = insn.opcode.bytes[1]; + if (insn.rex_prefix.nbytes) { + rex = insn.rex_prefix.bytes[0]; + rex_w = X86_REX_W(rex) >> 3; + rex_r = X86_REX_R(rex) >> 2; + rex_x = X86_REX_X(rex) >> 1; + rex_b = X86_REX_B(rex); + } + + if (insn.modrm.nbytes) { + modrm = insn.modrm.bytes[0]; + modrm_mod = X86_MODRM_MOD(modrm); + modrm_reg = X86_MODRM_REG(modrm); + modrm_rm = X86_MODRM_RM(modrm); + } + + if (insn.sib.nbytes) + sib = insn.sib.bytes[0]; + switch (op1) { - case 0x55: - if (!insn.rex_prefix.nbytes) - /* push rbp */ - *type = INSN_FP_SAVE; + + case 0x1: + case 0x29: + if (rex_w && !rex_b && modrm_mod == 3 && modrm_rm == 4) { + + /* add/sub reg, %rsp */ + *type = INSN_STACK; + op->src.type = OP_SRC_ADD; + op->src.reg = op_to_cfi_reg[modrm_reg][rex_r]; + op->dest.type = OP_SRC_REG; + op->dest.reg = CFI_SP; + } + break; + + case 0x50 ... 0x57: + + /* push reg */ + *type = INSN_STACK; + op->src.type = OP_SRC_REG; + op->src.reg = op_to_cfi_reg[op1 & 0x7][rex_b]; + op->dest.type = OP_DEST_PUSH; + + break; + + case 0x58 ... 0x5f: + + /* pop reg */ + *type = INSN_STACK; + op->src.type = OP_SRC_POP; + op->dest.type = OP_DEST_REG; + op->dest.reg = op_to_cfi_reg[op1 & 0x7][rex_b]; + break; - case 0x5d: - if (!insn.rex_prefix.nbytes) - /* pop rbp */ - *type = INSN_FP_RESTORE; + case 0x68: + case 0x6a: + /* push immediate */ + *type = INSN_STACK; + op->src.type = OP_SRC_CONST; + op->dest.type = OP_DEST_PUSH; break; case 0x70 ... 0x7f: *type = INSN_JUMP_CONDITIONAL; break; + case 0x81: + case 0x83: + if (rex != 0x48) + break; + + if (modrm == 0xe4) { + /* and imm, %rsp */ + *type = INSN_STACK; + op->src.type = OP_SRC_AND; + op->src.reg = CFI_SP; + op->src.offset = insn.immediate.value; + op->dest.type = OP_DEST_REG; + op->dest.reg = CFI_SP; + break; + } + + if (modrm == 0xc4) + sign = 1; + else if (modrm == 0xec) + sign = -1; + else + break; + + /* add/sub imm, %rsp */ + *type = INSN_STACK; + op->src.type = OP_SRC_ADD; + op->src.reg = CFI_SP; + op->src.offset = insn.immediate.value * sign; + op->dest.type = OP_DEST_REG; + op->dest.reg = CFI_SP; + break; + case 0x89: - if (insn.rex_prefix.nbytes == 1 && - insn.rex_prefix.bytes[0] == 0x48 && - insn.modrm.nbytes && insn.modrm.bytes[0] == 0xe5) - /* mov rsp, rbp */ - *type = INSN_FP_SETUP; + if (rex == 0x48 && modrm == 0xe5) { + + /* mov %rsp, %rbp */ + *type = INSN_STACK; + op->src.type = OP_SRC_REG; + op->src.reg = CFI_SP; + op->dest.type = OP_DEST_REG; + op->dest.reg = CFI_BP; + break; + } + + if (rex_w && !rex_b && modrm_mod == 3 && modrm_rm == 4) { + + /* mov reg, %rsp */ + *type = INSN_STACK; + op->src.type = OP_SRC_REG; + op->src.reg = op_to_cfi_reg[modrm_reg][rex_r]; + op->dest.type = OP_DEST_REG; + op->dest.reg = CFI_SP; + break; + } + + /* fallthrough */ + case 0x88: + if (!rex_b && + (modrm_mod == 1 || modrm_mod == 2) && modrm_rm == 5) { + + /* mov reg, disp(%rbp) */ + *type = INSN_STACK; + op->src.type = OP_SRC_REG; + op->src.reg = op_to_cfi_reg[modrm_reg][rex_r]; + op->dest.type = OP_DEST_REG_INDIRECT; + op->dest.reg = CFI_BP; + op->dest.offset = insn.displacement.value; + + } else if (rex_w && !rex_b && modrm_rm == 4 && sib == 0x24) { + + /* mov reg, disp(%rsp) */ + *type = INSN_STACK; + op->src.type = OP_SRC_REG; + op->src.reg = op_to_cfi_reg[modrm_reg][rex_r]; + op->dest.type = OP_DEST_REG_INDIRECT; + op->dest.reg = CFI_SP; + op->dest.offset = insn.displacement.value; + } + + break; + + case 0x8b: + if (rex_w && !rex_b && modrm_mod == 1 && modrm_rm == 5) { + + /* mov disp(%rbp), reg */ + *type = INSN_STACK; + op->src.type = OP_SRC_REG_INDIRECT; + op->src.reg = CFI_BP; + op->src.offset = insn.displacement.value; + op->dest.type = OP_DEST_REG; + op->dest.reg = op_to_cfi_reg[modrm_reg][rex_r]; + + } else if (rex_w && !rex_b && sib == 0x24 && + modrm_mod != 3 && modrm_rm == 4) { + + /* mov disp(%rsp), reg */ + *type = INSN_STACK; + op->src.type = OP_SRC_REG_INDIRECT; + op->src.reg = CFI_SP; + op->src.offset = insn.displacement.value; + op->dest.type = OP_DEST_REG; + op->dest.reg = op_to_cfi_reg[modrm_reg][rex_r]; + } + break; case 0x8d: - if (insn.rex_prefix.nbytes && - insn.rex_prefix.bytes[0] == 0x48 && - insn.modrm.nbytes && insn.modrm.bytes[0] == 0x2c && - insn.sib.nbytes && insn.sib.bytes[0] == 0x24) - /* lea %(rsp), %rbp */ - *type = INSN_FP_SETUP; + if (sib == 0x24 && rex_w && !rex_b && !rex_x) { + + /* lea disp(%rsp), reg */ + *type = INSN_STACK; + op->src.type = OP_SRC_ADD; + op->src.reg = CFI_SP; + op->src.offset = insn.displacement.value; + op->dest.type = OP_DEST_REG; + op->dest.reg = op_to_cfi_reg[modrm_reg][rex_r]; + + } else if (rex == 0x48 && modrm == 0x65) { + + /* lea disp(%rbp), %rsp */ + *type = INSN_STACK; + op->src.type = OP_SRC_ADD; + op->src.reg = CFI_BP; + op->src.offset = insn.displacement.value; + op->dest.type = OP_DEST_REG; + op->dest.reg = CFI_SP; + + } else if (rex == 0x49 && modrm == 0x62 && + insn.displacement.value == -8) { + + /* + * lea -0x8(%r10), %rsp + * + * Restoring rsp back to its original value after a + * stack realignment. + */ + *type = INSN_STACK; + op->src.type = OP_SRC_ADD; + op->src.reg = CFI_R10; + op->src.offset = -8; + op->dest.type = OP_DEST_REG; + op->dest.reg = CFI_SP; + + } else if (rex == 0x49 && modrm == 0x65 && + insn.displacement.value == -16) { + + /* + * lea -0x10(%r13), %rsp + * + * Restoring rsp back to its original value after a + * stack realignment. + */ + *type = INSN_STACK; + op->src.type = OP_SRC_ADD; + op->src.reg = CFI_R13; + op->src.offset = -16; + op->dest.type = OP_DEST_REG; + op->dest.reg = CFI_SP; + } + + break; + + case 0x8f: + /* pop to mem */ + *type = INSN_STACK; + op->src.type = OP_SRC_POP; + op->dest.type = OP_DEST_MEM; break; case 0x90: *type = INSN_NOP; break; + case 0x9c: + /* pushf */ + *type = INSN_STACK; + op->src.type = OP_SRC_CONST; + op->dest.type = OP_DEST_PUSH; + break; + + case 0x9d: + /* popf */ + *type = INSN_STACK; + op->src.type = OP_SRC_POP; + op->dest.type = OP_DEST_MEM; + break; + case 0x0f: - if (op2 >= 0x80 && op2 <= 0x8f) + + if (op2 >= 0x80 && op2 <= 0x8f) { + *type = INSN_JUMP_CONDITIONAL; - else if (op2 == 0x05 || op2 == 0x07 || op2 == 0x34 || - op2 == 0x35) + + } else if (op2 == 0x05 || op2 == 0x07 || op2 == 0x34 || + op2 == 0x35) { + /* sysenter, sysret */ *type = INSN_CONTEXT_SWITCH; - else if (op2 == 0x0d || op2 == 0x1f) + + } else if (op2 == 0x0b || op2 == 0xb9) { + + /* ud2 */ + *type = INSN_BUG; + + } else if (op2 == 0x0d || op2 == 0x1f) { + /* nopl/nopw */ *type = INSN_NOP; - else if (op2 == 0x01 && insn.modrm.nbytes && - (insn.modrm.bytes[0] == 0xc2 || - insn.modrm.bytes[0] == 0xd8)) - /* vmlaunch, vmrun */ - *type = INSN_CONTEXT_SWITCH; + + } else if (op2 == 0xa0 || op2 == 0xa8) { + + /* push fs/gs */ + *type = INSN_STACK; + op->src.type = OP_SRC_CONST; + op->dest.type = OP_DEST_PUSH; + + } else if (op2 == 0xa1 || op2 == 0xa9) { + + /* pop fs/gs */ + *type = INSN_STACK; + op->src.type = OP_SRC_POP; + op->dest.type = OP_DEST_MEM; + } break; - case 0xc9: /* leave */ - *type = INSN_FP_RESTORE; + case 0xc9: + /* + * leave + * + * equivalent to: + * mov bp, sp + * pop bp + */ + *type = INSN_STACK; + op->dest.type = OP_DEST_LEAVE; + break; - case 0xe3: /* jecxz/jrcxz */ + case 0xe3: + /* jecxz/jrcxz */ *type = INSN_JUMP_CONDITIONAL; break; @@ -158,14 +440,27 @@ int arch_decode_instruction(struct elf *elf, struct section *sec, break; case 0xff: - ext = X86_MODRM_REG(insn.modrm.bytes[0]); - if (ext == 2 || ext == 3) + if (modrm_reg == 2 || modrm_reg == 3) + *type = INSN_CALL_DYNAMIC; - else if (ext == 4) + + else if (modrm_reg == 4) + *type = INSN_JUMP_DYNAMIC; - else if (ext == 5) /*jmpf */ + + else if (modrm_reg == 5) + + /* jmpf */ *type = INSN_CONTEXT_SWITCH; + else if (modrm_reg == 6) { + + /* push from mem */ + *type = INSN_STACK; + op->src.type = OP_SRC_CONST; + op->dest.type = OP_DEST_PUSH; + } + break; default: @@ -176,3 +471,21 @@ int arch_decode_instruction(struct elf *elf, struct section *sec, return 0; } + +void arch_initial_func_cfi_state(struct cfi_state *state) +{ + int i; + + for (i = 0; i < CFI_NUM_REGS; i++) { + state->regs[i].base = CFI_UNDEFINED; + state->regs[i].offset = 0; + } + + /* initial CFA (call frame address) */ + state->cfa.base = CFI_SP; + state->cfa.offset = 8; + + /* initial RA (return address) */ + state->regs[16].base = CFI_CFA; + state->regs[16].offset = -8; +} diff --git a/tools/objtool/arch/x86/insn/x86-opcode-map.txt b/tools/objtool/arch/x86/insn/x86-opcode-map.txt index 767be7c76034..12e377184ee4 100644 --- a/tools/objtool/arch/x86/insn/x86-opcode-map.txt +++ b/tools/objtool/arch/x86/insn/x86-opcode-map.txt @@ -1009,7 +1009,7 @@ GrpTable: Grp15 1: fxstor | RDGSBASE Ry (F3),(11B) 2: vldmxcsr Md (v1) | WRFSBASE Ry (F3),(11B) 3: vstmxcsr Md (v1) | WRGSBASE Ry (F3),(11B) -4: XSAVE +4: XSAVE | ptwrite Ey (F3),(11B) 5: XRSTOR | lfence (11B) 6: XSAVEOPT | clwb (66) | mfence (11B) 7: clflush | clflushopt (66) | sfence (11B) diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c index 5f66697fe1e0..57254f5b2779 100644 --- a/tools/objtool/builtin-check.c +++ b/tools/objtool/builtin-check.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2015 Josh Poimboeuf <jpoimboe@redhat.com> + * Copyright (C) 2015-2017 Josh Poimboeuf <jpoimboe@redhat.com> * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -25,1287 +25,33 @@ * For more information, see tools/objtool/Documentation/stack-validation.txt. */ -#include <string.h> -#include <stdlib.h> #include <subcmd/parse-options.h> - #include "builtin.h" -#include "elf.h" -#include "special.h" -#include "arch.h" -#include "warn.h" - -#include <linux/hashtable.h> -#include <linux/kernel.h> - -#define STATE_FP_SAVED 0x1 -#define STATE_FP_SETUP 0x2 -#define STATE_FENTRY 0x4 - -struct instruction { - struct list_head list; - struct hlist_node hash; - struct section *sec; - unsigned long offset; - unsigned int len, state; - unsigned char type; - unsigned long immediate; - bool alt_group, visited, dead_end; - struct symbol *call_dest; - struct instruction *jump_dest; - struct list_head alts; - struct symbol *func; -}; - -struct alternative { - struct list_head list; - struct instruction *insn; -}; - -struct objtool_file { - struct elf *elf; - struct list_head insn_list; - DECLARE_HASHTABLE(insn_hash, 16); - struct section *rodata, *whitelist; - bool ignore_unreachables, c_file; -}; - -const char *objname; -static bool nofp; - -static struct instruction *find_insn(struct objtool_file *file, - struct section *sec, unsigned long offset) -{ - struct instruction *insn; - - hash_for_each_possible(file->insn_hash, insn, hash, offset) - if (insn->sec == sec && insn->offset == offset) - return insn; - - return NULL; -} - -static struct instruction *next_insn_same_sec(struct objtool_file *file, - struct instruction *insn) -{ - struct instruction *next = list_next_entry(insn, list); - - if (&next->list == &file->insn_list || next->sec != insn->sec) - return NULL; - - return next; -} - -static bool gcov_enabled(struct objtool_file *file) -{ - struct section *sec; - struct symbol *sym; - - list_for_each_entry(sec, &file->elf->sections, list) - list_for_each_entry(sym, &sec->symbol_list, list) - if (!strncmp(sym->name, "__gcov_.", 8)) - return true; - - return false; -} - -#define for_each_insn(file, insn) \ - list_for_each_entry(insn, &file->insn_list, list) - -#define func_for_each_insn(file, func, insn) \ - for (insn = find_insn(file, func->sec, func->offset); \ - insn && &insn->list != &file->insn_list && \ - insn->sec == func->sec && \ - insn->offset < func->offset + func->len; \ - insn = list_next_entry(insn, list)) - -#define func_for_each_insn_continue_reverse(file, func, insn) \ - for (insn = list_prev_entry(insn, list); \ - &insn->list != &file->insn_list && \ - insn->sec == func->sec && insn->offset >= func->offset; \ - insn = list_prev_entry(insn, list)) - -#define sec_for_each_insn_from(file, insn) \ - for (; insn; insn = next_insn_same_sec(file, insn)) - - -/* - * Check if the function has been manually whitelisted with the - * STACK_FRAME_NON_STANDARD macro, or if it should be automatically whitelisted - * due to its use of a context switching instruction. - */ -static bool ignore_func(struct objtool_file *file, struct symbol *func) -{ - struct rela *rela; - struct instruction *insn; - - /* check for STACK_FRAME_NON_STANDARD */ - if (file->whitelist && file->whitelist->rela) - list_for_each_entry(rela, &file->whitelist->rela->rela_list, list) { - if (rela->sym->type == STT_SECTION && - rela->sym->sec == func->sec && - rela->addend == func->offset) - return true; - if (rela->sym->type == STT_FUNC && rela->sym == func) - return true; - } - - /* check if it has a context switching instruction */ - func_for_each_insn(file, func, insn) - if (insn->type == INSN_CONTEXT_SWITCH) - return true; - - return false; -} - -/* - * This checks to see if the given function is a "noreturn" function. - * - * For global functions which are outside the scope of this object file, we - * have to keep a manual list of them. - * - * For local functions, we have to detect them manually by simply looking for - * the lack of a return instruction. - * - * Returns: - * -1: error - * 0: no dead end - * 1: dead end - */ -static int __dead_end_function(struct objtool_file *file, struct symbol *func, - int recursion) -{ - int i; - struct instruction *insn; - bool empty = true; - - /* - * Unfortunately these have to be hard coded because the noreturn - * attribute isn't provided in ELF data. - */ - static const char * const global_noreturns[] = { - "__stack_chk_fail", - "panic", - "do_exit", - "do_task_dead", - "__module_put_and_exit", - "complete_and_exit", - "kvm_spurious_fault", - "__reiserfs_panic", - "lbug_with_loc", - "fortify_panic", - }; - - if (func->bind == STB_WEAK) - return 0; - - if (func->bind == STB_GLOBAL) - for (i = 0; i < ARRAY_SIZE(global_noreturns); i++) - if (!strcmp(func->name, global_noreturns[i])) - return 1; - - if (!func->sec) - return 0; - - func_for_each_insn(file, func, insn) { - empty = false; - - if (insn->type == INSN_RETURN) - return 0; - } - - if (empty) - return 0; - - /* - * A function can have a sibling call instead of a return. In that - * case, the function's dead-end status depends on whether the target - * of the sibling call returns. - */ - func_for_each_insn(file, func, insn) { - if (insn->sec != func->sec || - insn->offset >= func->offset + func->len) - break; - - if (insn->type == INSN_JUMP_UNCONDITIONAL) { - struct instruction *dest = insn->jump_dest; - struct symbol *dest_func; - - if (!dest) - /* sibling call to another file */ - return 0; - - if (dest->sec != func->sec || - dest->offset < func->offset || - dest->offset >= func->offset + func->len) { - /* local sibling call */ - dest_func = find_symbol_by_offset(dest->sec, - dest->offset); - if (!dest_func) - continue; - - if (recursion == 5) { - WARN_FUNC("infinite recursion (objtool bug!)", - dest->sec, dest->offset); - return -1; - } - - return __dead_end_function(file, dest_func, - recursion + 1); - } - } - - if (insn->type == INSN_JUMP_DYNAMIC && list_empty(&insn->alts)) - /* sibling call */ - return 0; - } - - return 1; -} - -static int dead_end_function(struct objtool_file *file, struct symbol *func) -{ - return __dead_end_function(file, func, 0); -} - -/* - * Call the arch-specific instruction decoder for all the instructions and add - * them to the global instruction list. - */ -static int decode_instructions(struct objtool_file *file) -{ - struct section *sec; - struct symbol *func; - unsigned long offset; - struct instruction *insn; - int ret; - - list_for_each_entry(sec, &file->elf->sections, list) { - - if (!(sec->sh.sh_flags & SHF_EXECINSTR)) - continue; - - for (offset = 0; offset < sec->len; offset += insn->len) { - insn = malloc(sizeof(*insn)); - memset(insn, 0, sizeof(*insn)); - - INIT_LIST_HEAD(&insn->alts); - insn->sec = sec; - insn->offset = offset; - - ret = arch_decode_instruction(file->elf, sec, offset, - sec->len - offset, - &insn->len, &insn->type, - &insn->immediate); - if (ret) - return ret; - - if (!insn->type || insn->type > INSN_LAST) { - WARN_FUNC("invalid instruction type %d", - insn->sec, insn->offset, insn->type); - return -1; - } - - hash_add(file->insn_hash, &insn->hash, insn->offset); - list_add_tail(&insn->list, &file->insn_list); - } - - list_for_each_entry(func, &sec->symbol_list, list) { - if (func->type != STT_FUNC) - continue; - - if (!find_insn(file, sec, func->offset)) { - WARN("%s(): can't find starting instruction", - func->name); - return -1; - } - - func_for_each_insn(file, func, insn) - if (!insn->func) - insn->func = func; - } - } - - return 0; -} - -/* - * Find all uses of the unreachable() macro, which are code path dead ends. - */ -static int add_dead_ends(struct objtool_file *file) -{ - struct section *sec; - struct rela *rela; - struct instruction *insn; - bool found; - - sec = find_section_by_name(file->elf, ".rela.discard.unreachable"); - if (!sec) - return 0; - - list_for_each_entry(rela, &sec->rela_list, list) { - if (rela->sym->type != STT_SECTION) { - WARN("unexpected relocation symbol type in %s", sec->name); - return -1; - } - insn = find_insn(file, rela->sym->sec, rela->addend); - if (insn) - insn = list_prev_entry(insn, list); - else if (rela->addend == rela->sym->sec->len) { - found = false; - list_for_each_entry_reverse(insn, &file->insn_list, list) { - if (insn->sec == rela->sym->sec) { - found = true; - break; - } - } - - if (!found) { - WARN("can't find unreachable insn at %s+0x%x", - rela->sym->sec->name, rela->addend); - return -1; - } - } else { - WARN("can't find unreachable insn at %s+0x%x", - rela->sym->sec->name, rela->addend); - return -1; - } - - insn->dead_end = true; - } - - return 0; -} - -/* - * Warnings shouldn't be reported for ignored functions. - */ -static void add_ignores(struct objtool_file *file) -{ - struct instruction *insn; - struct section *sec; - struct symbol *func; - - list_for_each_entry(sec, &file->elf->sections, list) { - list_for_each_entry(func, &sec->symbol_list, list) { - if (func->type != STT_FUNC) - continue; - - if (!ignore_func(file, func)) - continue; - - func_for_each_insn(file, func, insn) - insn->visited = true; - } - } -} - -/* - * Find the destination instructions for all jumps. - */ -static int add_jump_destinations(struct objtool_file *file) -{ - struct instruction *insn; - struct rela *rela; - struct section *dest_sec; - unsigned long dest_off; - - for_each_insn(file, insn) { - if (insn->type != INSN_JUMP_CONDITIONAL && - insn->type != INSN_JUMP_UNCONDITIONAL) - continue; - - /* skip ignores */ - if (insn->visited) - continue; - - rela = find_rela_by_dest_range(insn->sec, insn->offset, - insn->len); - if (!rela) { - dest_sec = insn->sec; - dest_off = insn->offset + insn->len + insn->immediate; - } else if (rela->sym->type == STT_SECTION) { - dest_sec = rela->sym->sec; - dest_off = rela->addend + 4; - } else if (rela->sym->sec->idx) { - dest_sec = rela->sym->sec; - dest_off = rela->sym->sym.st_value + rela->addend + 4; - } else { - /* sibling call */ - insn->jump_dest = 0; - continue; - } - - insn->jump_dest = find_insn(file, dest_sec, dest_off); - if (!insn->jump_dest) { - - /* - * This is a special case where an alt instruction - * jumps past the end of the section. These are - * handled later in handle_group_alt(). - */ - if (!strcmp(insn->sec->name, ".altinstr_replacement")) - continue; - - WARN_FUNC("can't find jump dest instruction at %s+0x%lx", - insn->sec, insn->offset, dest_sec->name, - dest_off); - return -1; - } - } - - return 0; -} - -/* - * Find the destination instructions for all calls. - */ -static int add_call_destinations(struct objtool_file *file) -{ - struct instruction *insn; - unsigned long dest_off; - struct rela *rela; - - for_each_insn(file, insn) { - if (insn->type != INSN_CALL) - continue; - - rela = find_rela_by_dest_range(insn->sec, insn->offset, - insn->len); - if (!rela) { - dest_off = insn->offset + insn->len + insn->immediate; - insn->call_dest = find_symbol_by_offset(insn->sec, - dest_off); - if (!insn->call_dest) { - WARN_FUNC("can't find call dest symbol at offset 0x%lx", - insn->sec, insn->offset, dest_off); - return -1; - } - } else if (rela->sym->type == STT_SECTION) { - insn->call_dest = find_symbol_by_offset(rela->sym->sec, - rela->addend+4); - if (!insn->call_dest || - insn->call_dest->type != STT_FUNC) { - WARN_FUNC("can't find call dest symbol at %s+0x%x", - insn->sec, insn->offset, - rela->sym->sec->name, - rela->addend + 4); - return -1; - } - } else - insn->call_dest = rela->sym; - } - - return 0; -} - -/* - * The .alternatives section requires some extra special care, over and above - * what other special sections require: - * - * 1. Because alternatives are patched in-place, we need to insert a fake jump - * instruction at the end so that validate_branch() skips all the original - * replaced instructions when validating the new instruction path. - * - * 2. An added wrinkle is that the new instruction length might be zero. In - * that case the old instructions are replaced with noops. We simulate that - * by creating a fake jump as the only new instruction. - * - * 3. In some cases, the alternative section includes an instruction which - * conditionally jumps to the _end_ of the entry. We have to modify these - * jumps' destinations to point back to .text rather than the end of the - * entry in .altinstr_replacement. - * - * 4. It has been requested that we don't validate the !POPCNT feature path - * which is a "very very small percentage of machines". - */ -static int handle_group_alt(struct objtool_file *file, - struct special_alt *special_alt, - struct instruction *orig_insn, - struct instruction **new_insn) -{ - struct instruction *last_orig_insn, *last_new_insn, *insn, *fake_jump; - unsigned long dest_off; - - last_orig_insn = NULL; - insn = orig_insn; - sec_for_each_insn_from(file, insn) { - if (insn->offset >= special_alt->orig_off + special_alt->orig_len) - break; - - if (special_alt->skip_orig) - insn->type = INSN_NOP; - - insn->alt_group = true; - last_orig_insn = insn; - } - - if (!next_insn_same_sec(file, last_orig_insn)) { - WARN("%s: don't know how to handle alternatives at end of section", - special_alt->orig_sec->name); - return -1; - } - - fake_jump = malloc(sizeof(*fake_jump)); - if (!fake_jump) { - WARN("malloc failed"); - return -1; - } - memset(fake_jump, 0, sizeof(*fake_jump)); - INIT_LIST_HEAD(&fake_jump->alts); - fake_jump->sec = special_alt->new_sec; - fake_jump->offset = -1; - fake_jump->type = INSN_JUMP_UNCONDITIONAL; - fake_jump->jump_dest = list_next_entry(last_orig_insn, list); - - if (!special_alt->new_len) { - *new_insn = fake_jump; - return 0; - } - - last_new_insn = NULL; - insn = *new_insn; - sec_for_each_insn_from(file, insn) { - if (insn->offset >= special_alt->new_off + special_alt->new_len) - break; - - last_new_insn = insn; - - if (insn->type != INSN_JUMP_CONDITIONAL && - insn->type != INSN_JUMP_UNCONDITIONAL) - continue; - - if (!insn->immediate) - continue; - - dest_off = insn->offset + insn->len + insn->immediate; - if (dest_off == special_alt->new_off + special_alt->new_len) - insn->jump_dest = fake_jump; - - if (!insn->jump_dest) { - WARN_FUNC("can't find alternative jump destination", - insn->sec, insn->offset); - return -1; - } - } - - if (!last_new_insn) { - WARN_FUNC("can't find last new alternative instruction", - special_alt->new_sec, special_alt->new_off); - return -1; - } - - list_add(&fake_jump->list, &last_new_insn->list); - - return 0; -} - -/* - * A jump table entry can either convert a nop to a jump or a jump to a nop. - * If the original instruction is a jump, make the alt entry an effective nop - * by just skipping the original instruction. - */ -static int handle_jump_alt(struct objtool_file *file, - struct special_alt *special_alt, - struct instruction *orig_insn, - struct instruction **new_insn) -{ - if (orig_insn->type == INSN_NOP) - return 0; - - if (orig_insn->type != INSN_JUMP_UNCONDITIONAL) { - WARN_FUNC("unsupported instruction at jump label", - orig_insn->sec, orig_insn->offset); - return -1; - } - - *new_insn = list_next_entry(orig_insn, list); - return 0; -} - -/* - * Read all the special sections which have alternate instructions which can be - * patched in or redirected to at runtime. Each instruction having alternate - * instruction(s) has them added to its insn->alts list, which will be - * traversed in validate_branch(). - */ -static int add_special_section_alts(struct objtool_file *file) -{ - struct list_head special_alts; - struct instruction *orig_insn, *new_insn; - struct special_alt *special_alt, *tmp; - struct alternative *alt; - int ret; - - ret = special_get_alts(file->elf, &special_alts); - if (ret) - return ret; - - list_for_each_entry_safe(special_alt, tmp, &special_alts, list) { - alt = malloc(sizeof(*alt)); - if (!alt) { - WARN("malloc failed"); - ret = -1; - goto out; - } - - orig_insn = find_insn(file, special_alt->orig_sec, - special_alt->orig_off); - if (!orig_insn) { - WARN_FUNC("special: can't find orig instruction", - special_alt->orig_sec, special_alt->orig_off); - ret = -1; - goto out; - } +#include "check.h" - new_insn = NULL; - if (!special_alt->group || special_alt->new_len) { - new_insn = find_insn(file, special_alt->new_sec, - special_alt->new_off); - if (!new_insn) { - WARN_FUNC("special: can't find new instruction", - special_alt->new_sec, - special_alt->new_off); - ret = -1; - goto out; - } - } +bool no_fp, no_unreachable; - if (special_alt->group) { - ret = handle_group_alt(file, special_alt, orig_insn, - &new_insn); - if (ret) - goto out; - } else if (special_alt->jump_or_nop) { - ret = handle_jump_alt(file, special_alt, orig_insn, - &new_insn); - if (ret) - goto out; - } - - alt->insn = new_insn; - list_add_tail(&alt->list, &orig_insn->alts); - - list_del(&special_alt->list); - free(special_alt); - } - -out: - return ret; -} - -static int add_switch_table(struct objtool_file *file, struct symbol *func, - struct instruction *insn, struct rela *table, - struct rela *next_table) -{ - struct rela *rela = table; - struct instruction *alt_insn; - struct alternative *alt; - - list_for_each_entry_from(rela, &file->rodata->rela->rela_list, list) { - if (rela == next_table) - break; - - if (rela->sym->sec != insn->sec || - rela->addend <= func->offset || - rela->addend >= func->offset + func->len) - break; - - alt_insn = find_insn(file, insn->sec, rela->addend); - if (!alt_insn) { - WARN("%s: can't find instruction at %s+0x%x", - file->rodata->rela->name, insn->sec->name, - rela->addend); - return -1; - } - - alt = malloc(sizeof(*alt)); - if (!alt) { - WARN("malloc failed"); - return -1; - } - - alt->insn = alt_insn; - list_add_tail(&alt->list, &insn->alts); - } - - return 0; -} - -/* - * find_switch_table() - Given a dynamic jump, find the switch jump table in - * .rodata associated with it. - * - * There are 3 basic patterns: - * - * 1. jmpq *[rodata addr](,%reg,8) - * - * This is the most common case by far. It jumps to an address in a simple - * jump table which is stored in .rodata. - * - * 2. jmpq *[rodata addr](%rip) - * - * This is caused by a rare GCC quirk, currently only seen in three driver - * functions in the kernel, only with certain obscure non-distro configs. - * - * As part of an optimization, GCC makes a copy of an existing switch jump - * table, modifies it, and then hard-codes the jump (albeit with an indirect - * jump) to use a single entry in the table. The rest of the jump table and - * some of its jump targets remain as dead code. - * - * In such a case we can just crudely ignore all unreachable instruction - * warnings for the entire object file. Ideally we would just ignore them - * for the function, but that would require redesigning the code quite a - * bit. And honestly that's just not worth doing: unreachable instruction - * warnings are of questionable value anyway, and this is such a rare issue. - * - * 3. mov [rodata addr],%reg1 - * ... some instructions ... - * jmpq *(%reg1,%reg2,8) - * - * This is a fairly uncommon pattern which is new for GCC 6. As of this - * writing, there are 11 occurrences of it in the allmodconfig kernel. - * - * TODO: Once we have DWARF CFI and smarter instruction decoding logic, - * ensure the same register is used in the mov and jump instructions. - */ -static struct rela *find_switch_table(struct objtool_file *file, - struct symbol *func, - struct instruction *insn) -{ - struct rela *text_rela, *rodata_rela; - struct instruction *orig_insn = insn; - - text_rela = find_rela_by_dest_range(insn->sec, insn->offset, insn->len); - if (text_rela && text_rela->sym == file->rodata->sym) { - /* case 1 */ - rodata_rela = find_rela_by_dest(file->rodata, - text_rela->addend); - if (rodata_rela) - return rodata_rela; - - /* case 2 */ - rodata_rela = find_rela_by_dest(file->rodata, - text_rela->addend + 4); - if (!rodata_rela) - return NULL; - file->ignore_unreachables = true; - return rodata_rela; - } - - /* case 3 */ - func_for_each_insn_continue_reverse(file, func, insn) { - if (insn->type == INSN_JUMP_DYNAMIC) - break; - - /* allow small jumps within the range */ - if (insn->type == INSN_JUMP_UNCONDITIONAL && - insn->jump_dest && - (insn->jump_dest->offset <= insn->offset || - insn->jump_dest->offset > orig_insn->offset)) - break; - - /* look for a relocation which references .rodata */ - text_rela = find_rela_by_dest_range(insn->sec, insn->offset, - insn->len); - if (!text_rela || text_rela->sym != file->rodata->sym) - continue; - - /* - * Make sure the .rodata address isn't associated with a - * symbol. gcc jump tables are anonymous data. - */ - if (find_symbol_containing(file->rodata, text_rela->addend)) - continue; - - return find_rela_by_dest(file->rodata, text_rela->addend); - } - - return NULL; -} - -static int add_func_switch_tables(struct objtool_file *file, - struct symbol *func) -{ - struct instruction *insn, *prev_jump = NULL; - struct rela *rela, *prev_rela = NULL; - int ret; - - func_for_each_insn(file, func, insn) { - if (insn->type != INSN_JUMP_DYNAMIC) - continue; - - rela = find_switch_table(file, func, insn); - if (!rela) - continue; - - /* - * We found a switch table, but we don't know yet how big it - * is. Don't add it until we reach the end of the function or - * the beginning of another switch table in the same function. - */ - if (prev_jump) { - ret = add_switch_table(file, func, prev_jump, prev_rela, - rela); - if (ret) - return ret; - } - - prev_jump = insn; - prev_rela = rela; - } - - if (prev_jump) { - ret = add_switch_table(file, func, prev_jump, prev_rela, NULL); - if (ret) - return ret; - } - - return 0; -} - -/* - * For some switch statements, gcc generates a jump table in the .rodata - * section which contains a list of addresses within the function to jump to. - * This finds these jump tables and adds them to the insn->alts lists. - */ -static int add_switch_table_alts(struct objtool_file *file) -{ - struct section *sec; - struct symbol *func; - int ret; - - if (!file->rodata || !file->rodata->rela) - return 0; - - list_for_each_entry(sec, &file->elf->sections, list) { - list_for_each_entry(func, &sec->symbol_list, list) { - if (func->type != STT_FUNC) - continue; - - ret = add_func_switch_tables(file, func); - if (ret) - return ret; - } - } - - return 0; -} - -static int decode_sections(struct objtool_file *file) -{ - int ret; - - ret = decode_instructions(file); - if (ret) - return ret; - - ret = add_dead_ends(file); - if (ret) - return ret; - - add_ignores(file); - - ret = add_jump_destinations(file); - if (ret) - return ret; - - ret = add_call_destinations(file); - if (ret) - return ret; - - ret = add_special_section_alts(file); - if (ret) - return ret; - - ret = add_switch_table_alts(file); - if (ret) - return ret; - - return 0; -} - -static bool is_fentry_call(struct instruction *insn) -{ - if (insn->type == INSN_CALL && - insn->call_dest->type == STT_NOTYPE && - !strcmp(insn->call_dest->name, "__fentry__")) - return true; - - return false; -} - -static bool has_modified_stack_frame(struct instruction *insn) -{ - return (insn->state & STATE_FP_SAVED) || - (insn->state & STATE_FP_SETUP); -} - -static bool has_valid_stack_frame(struct instruction *insn) -{ - return (insn->state & STATE_FP_SAVED) && - (insn->state & STATE_FP_SETUP); -} - -static unsigned int frame_state(unsigned long state) -{ - return (state & (STATE_FP_SAVED | STATE_FP_SETUP)); -} - -/* - * Follow the branch starting at the given instruction, and recursively follow - * any other branches (jumps). Meanwhile, track the frame pointer state at - * each instruction and validate all the rules described in - * tools/objtool/Documentation/stack-validation.txt. - */ -static int validate_branch(struct objtool_file *file, - struct instruction *first, unsigned char first_state) -{ - struct alternative *alt; - struct instruction *insn; - struct section *sec; - struct symbol *func = NULL; - unsigned char state; - int ret; - - insn = first; - sec = insn->sec; - state = first_state; - - if (insn->alt_group && list_empty(&insn->alts)) { - WARN_FUNC("don't know how to handle branch to middle of alternative instruction group", - sec, insn->offset); - return 1; - } - - while (1) { - if (file->c_file && insn->func) { - if (func && func != insn->func) { - WARN("%s() falls through to next function %s()", - func->name, insn->func->name); - return 1; - } - - func = insn->func; - } - - if (insn->visited) { - if (frame_state(insn->state) != frame_state(state)) { - WARN_FUNC("frame pointer state mismatch", - sec, insn->offset); - return 1; - } - - return 0; - } - - insn->visited = true; - insn->state = state; - - list_for_each_entry(alt, &insn->alts, list) { - ret = validate_branch(file, alt->insn, state); - if (ret) - return 1; - } - - switch (insn->type) { - - case INSN_FP_SAVE: - if (!nofp) { - if (state & STATE_FP_SAVED) { - WARN_FUNC("duplicate frame pointer save", - sec, insn->offset); - return 1; - } - state |= STATE_FP_SAVED; - } - break; - - case INSN_FP_SETUP: - if (!nofp) { - if (state & STATE_FP_SETUP) { - WARN_FUNC("duplicate frame pointer setup", - sec, insn->offset); - return 1; - } - state |= STATE_FP_SETUP; - } - break; - - case INSN_FP_RESTORE: - if (!nofp) { - if (has_valid_stack_frame(insn)) - state &= ~STATE_FP_SETUP; - - state &= ~STATE_FP_SAVED; - } - break; - - case INSN_RETURN: - if (!nofp && has_modified_stack_frame(insn)) { - WARN_FUNC("return without frame pointer restore", - sec, insn->offset); - return 1; - } - return 0; - - case INSN_CALL: - if (is_fentry_call(insn)) { - state |= STATE_FENTRY; - break; - } - - ret = dead_end_function(file, insn->call_dest); - if (ret == 1) - return 0; - if (ret == -1) - return 1; - - /* fallthrough */ - case INSN_CALL_DYNAMIC: - if (!nofp && !has_valid_stack_frame(insn)) { - WARN_FUNC("call without frame pointer save/setup", - sec, insn->offset); - return 1; - } - break; - - case INSN_JUMP_CONDITIONAL: - case INSN_JUMP_UNCONDITIONAL: - if (insn->jump_dest) { - ret = validate_branch(file, insn->jump_dest, - state); - if (ret) - return 1; - } else if (has_modified_stack_frame(insn)) { - WARN_FUNC("sibling call from callable instruction with changed frame pointer", - sec, insn->offset); - return 1; - } /* else it's a sibling call */ - - if (insn->type == INSN_JUMP_UNCONDITIONAL) - return 0; - - break; - - case INSN_JUMP_DYNAMIC: - if (list_empty(&insn->alts) && - has_modified_stack_frame(insn)) { - WARN_FUNC("sibling call from callable instruction with changed frame pointer", - sec, insn->offset); - return 1; - } - - return 0; - - default: - break; - } - - if (insn->dead_end) - return 0; - - insn = next_insn_same_sec(file, insn); - if (!insn) { - WARN("%s: unexpected end of section", sec->name); - return 1; - } - } - - return 0; -} - -static bool is_kasan_insn(struct instruction *insn) -{ - return (insn->type == INSN_CALL && - !strcmp(insn->call_dest->name, "__asan_handle_no_return")); -} - -static bool is_ubsan_insn(struct instruction *insn) -{ - return (insn->type == INSN_CALL && - !strcmp(insn->call_dest->name, - "__ubsan_handle_builtin_unreachable")); -} - -static bool ignore_unreachable_insn(struct symbol *func, - struct instruction *insn) -{ - int i; - - if (insn->type == INSN_NOP) - return true; - - /* - * Check if this (or a subsequent) instruction is related to - * CONFIG_UBSAN or CONFIG_KASAN. - * - * End the search at 5 instructions to avoid going into the weeds. - */ - for (i = 0; i < 5; i++) { - - if (is_kasan_insn(insn) || is_ubsan_insn(insn)) - return true; - - if (insn->type == INSN_JUMP_UNCONDITIONAL && insn->jump_dest) { - insn = insn->jump_dest; - continue; - } - - if (insn->offset + insn->len >= func->offset + func->len) - break; - insn = list_next_entry(insn, list); - } - - return false; -} - -static int validate_functions(struct objtool_file *file) -{ - struct section *sec; - struct symbol *func; - struct instruction *insn; - int ret, warnings = 0; - - list_for_each_entry(sec, &file->elf->sections, list) { - list_for_each_entry(func, &sec->symbol_list, list) { - if (func->type != STT_FUNC) - continue; - - insn = find_insn(file, sec, func->offset); - if (!insn) - continue; - - ret = validate_branch(file, insn, 0); - warnings += ret; - } - } - - list_for_each_entry(sec, &file->elf->sections, list) { - list_for_each_entry(func, &sec->symbol_list, list) { - if (func->type != STT_FUNC) - continue; - - func_for_each_insn(file, func, insn) { - if (insn->visited) - continue; - - insn->visited = true; - - if (file->ignore_unreachables || warnings || - ignore_unreachable_insn(func, insn)) - continue; - - /* - * gcov produces a lot of unreachable - * instructions. If we get an unreachable - * warning and the file has gcov enabled, just - * ignore it, and all other such warnings for - * the file. - */ - if (!file->ignore_unreachables && - gcov_enabled(file)) { - file->ignore_unreachables = true; - continue; - } - - WARN_FUNC("function has unreachable instruction", insn->sec, insn->offset); - warnings++; - } - } - } - - return warnings; -} - -static int validate_uncallable_instructions(struct objtool_file *file) -{ - struct instruction *insn; - int warnings = 0; - - for_each_insn(file, insn) { - if (!insn->visited && insn->type == INSN_RETURN) { - WARN_FUNC("return instruction outside of a callable function", - insn->sec, insn->offset); - warnings++; - } - } - - return warnings; -} - -static void cleanup(struct objtool_file *file) -{ - struct instruction *insn, *tmpinsn; - struct alternative *alt, *tmpalt; - - list_for_each_entry_safe(insn, tmpinsn, &file->insn_list, list) { - list_for_each_entry_safe(alt, tmpalt, &insn->alts, list) { - list_del(&alt->list); - free(alt); - } - list_del(&insn->list); - hash_del(&insn->hash); - free(insn); - } - elf_close(file->elf); -} - -const char * const check_usage[] = { +static const char * const check_usage[] = { "objtool check [<options>] file.o", NULL, }; +const struct option check_options[] = { + OPT_BOOLEAN('f', "no-fp", &no_fp, "Skip frame pointer validation"), + OPT_BOOLEAN('u', "no-unreachable", &no_unreachable, "Skip 'unreachable instruction' warnings"), + OPT_END(), +}; + int cmd_check(int argc, const char **argv) { - struct objtool_file file; - int ret, warnings = 0; - - const struct option options[] = { - OPT_BOOLEAN('f', "no-fp", &nofp, "Skip frame pointer validation"), - OPT_END(), - }; + const char *objname; - argc = parse_options(argc, argv, options, check_usage, 0); + argc = parse_options(argc, argv, check_options, check_usage, 0); if (argc != 1) - usage_with_options(check_usage, options); + usage_with_options(check_usage, check_options); objname = argv[0]; - file.elf = elf_open(objname); - if (!file.elf) { - fprintf(stderr, "error reading elf file %s\n", objname); - return 1; - } - - INIT_LIST_HEAD(&file.insn_list); - hash_init(file.insn_hash); - file.whitelist = find_section_by_name(file.elf, ".discard.func_stack_frame_non_standard"); - file.rodata = find_section_by_name(file.elf, ".rodata"); - file.ignore_unreachables = false; - file.c_file = find_section_by_name(file.elf, ".comment"); - - ret = decode_sections(&file); - if (ret < 0) - goto out; - warnings += ret; - - ret = validate_functions(&file); - if (ret < 0) - goto out; - warnings += ret; - - ret = validate_uncallable_instructions(&file); - if (ret < 0) - goto out; - warnings += ret; - -out: - cleanup(&file); - - /* ignore warnings for now until we get all the code cleaned up */ - if (ret || warnings) - return 0; - return 0; + return check(objname, no_fp, no_unreachable, false); } diff --git a/tools/objtool/builtin-orc.c b/tools/objtool/builtin-orc.c new file mode 100644 index 000000000000..4c6b5c9ef073 --- /dev/null +++ b/tools/objtool/builtin-orc.c @@ -0,0 +1,70 @@ +/* + * Copyright (C) 2017 Josh Poimboeuf <jpoimboe@redhat.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +/* + * objtool orc: + * + * This command analyzes a .o file and adds .orc_unwind and .orc_unwind_ip + * sections to it, which is used by the in-kernel ORC unwinder. + * + * This command is a superset of "objtool check". + */ + +#include <string.h> +#include <subcmd/parse-options.h> +#include "builtin.h" +#include "check.h" + + +static const char *orc_usage[] = { + "objtool orc generate [<options>] file.o", + "objtool orc dump file.o", + NULL, +}; + +extern const struct option check_options[]; +extern bool no_fp, no_unreachable; + +int cmd_orc(int argc, const char **argv) +{ + const char *objname; + + argc--; argv++; + if (!strncmp(argv[0], "gen", 3)) { + argc = parse_options(argc, argv, check_options, orc_usage, 0); + if (argc != 1) + usage_with_options(orc_usage, check_options); + + objname = argv[0]; + + return check(objname, no_fp, no_unreachable, true); + + } + + if (!strcmp(argv[0], "dump")) { + if (argc != 2) + usage_with_options(orc_usage, check_options); + + objname = argv[1]; + + return orc_dump(objname); + } + + usage_with_options(orc_usage, check_options); + + return 0; +} diff --git a/tools/objtool/builtin.h b/tools/objtool/builtin.h index 34d2ba78a616..dd526067fed5 100644 --- a/tools/objtool/builtin.h +++ b/tools/objtool/builtin.h @@ -18,5 +18,6 @@ #define _BUILTIN_H extern int cmd_check(int argc, const char **argv); +extern int cmd_orc(int argc, const char **argv); #endif /* _BUILTIN_H */ diff --git a/tools/objtool/cfi.h b/tools/objtool/cfi.h new file mode 100644 index 000000000000..2fe883c665c7 --- /dev/null +++ b/tools/objtool/cfi.h @@ -0,0 +1,55 @@ +/* + * Copyright (C) 2015-2017 Josh Poimboeuf <jpoimboe@redhat.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef _OBJTOOL_CFI_H +#define _OBJTOOL_CFI_H + +#define CFI_UNDEFINED -1 +#define CFI_CFA -2 +#define CFI_SP_INDIRECT -3 +#define CFI_BP_INDIRECT -4 + +#define CFI_AX 0 +#define CFI_DX 1 +#define CFI_CX 2 +#define CFI_BX 3 +#define CFI_SI 4 +#define CFI_DI 5 +#define CFI_BP 6 +#define CFI_SP 7 +#define CFI_R8 8 +#define CFI_R9 9 +#define CFI_R10 10 +#define CFI_R11 11 +#define CFI_R12 12 +#define CFI_R13 13 +#define CFI_R14 14 +#define CFI_R15 15 +#define CFI_RA 16 +#define CFI_NUM_REGS 17 + +struct cfi_reg { + int base; + int offset; +}; + +struct cfi_state { + struct cfi_reg cfa; + struct cfi_reg regs[CFI_NUM_REGS]; +}; + +#endif /* _OBJTOOL_CFI_H */ diff --git a/tools/objtool/check.c b/tools/objtool/check.c new file mode 100644 index 000000000000..f744617c9946 --- /dev/null +++ b/tools/objtool/check.c @@ -0,0 +1,1964 @@ +/* + * Copyright (C) 2015-2017 Josh Poimboeuf <jpoimboe@redhat.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#include <string.h> +#include <stdlib.h> + +#include "check.h" +#include "elf.h" +#include "special.h" +#include "arch.h" +#include "warn.h" + +#include <linux/hashtable.h> +#include <linux/kernel.h> + +struct alternative { + struct list_head list; + struct instruction *insn; +}; + +const char *objname; +static bool no_fp; +struct cfi_state initial_func_cfi; + +struct instruction *find_insn(struct objtool_file *file, + struct section *sec, unsigned long offset) +{ + struct instruction *insn; + + hash_for_each_possible(file->insn_hash, insn, hash, offset) + if (insn->sec == sec && insn->offset == offset) + return insn; + + return NULL; +} + +static struct instruction *next_insn_same_sec(struct objtool_file *file, + struct instruction *insn) +{ + struct instruction *next = list_next_entry(insn, list); + + if (!next || &next->list == &file->insn_list || next->sec != insn->sec) + return NULL; + + return next; +} + +#define func_for_each_insn(file, func, insn) \ + for (insn = find_insn(file, func->sec, func->offset); \ + insn && &insn->list != &file->insn_list && \ + insn->sec == func->sec && \ + insn->offset < func->offset + func->len; \ + insn = list_next_entry(insn, list)) + +#define func_for_each_insn_continue_reverse(file, func, insn) \ + for (insn = list_prev_entry(insn, list); \ + &insn->list != &file->insn_list && \ + insn->sec == func->sec && insn->offset >= func->offset; \ + insn = list_prev_entry(insn, list)) + +#define sec_for_each_insn_from(file, insn) \ + for (; insn; insn = next_insn_same_sec(file, insn)) + +#define sec_for_each_insn_continue(file, insn) \ + for (insn = next_insn_same_sec(file, insn); insn; \ + insn = next_insn_same_sec(file, insn)) + +/* + * Check if the function has been manually whitelisted with the + * STACK_FRAME_NON_STANDARD macro, or if it should be automatically whitelisted + * due to its use of a context switching instruction. + */ +static bool ignore_func(struct objtool_file *file, struct symbol *func) +{ + struct rela *rela; + + /* check for STACK_FRAME_NON_STANDARD */ + if (file->whitelist && file->whitelist->rela) + list_for_each_entry(rela, &file->whitelist->rela->rela_list, list) { + if (rela->sym->type == STT_SECTION && + rela->sym->sec == func->sec && + rela->addend == func->offset) + return true; + if (rela->sym->type == STT_FUNC && rela->sym == func) + return true; + } + + return false; +} + +/* + * This checks to see if the given function is a "noreturn" function. + * + * For global functions which are outside the scope of this object file, we + * have to keep a manual list of them. + * + * For local functions, we have to detect them manually by simply looking for + * the lack of a return instruction. + * + * Returns: + * -1: error + * 0: no dead end + * 1: dead end + */ +static int __dead_end_function(struct objtool_file *file, struct symbol *func, + int recursion) +{ + int i; + struct instruction *insn; + bool empty = true; + + /* + * Unfortunately these have to be hard coded because the noreturn + * attribute isn't provided in ELF data. + */ + static const char * const global_noreturns[] = { + "__stack_chk_fail", + "panic", + "do_exit", + "do_task_dead", + "__module_put_and_exit", + "complete_and_exit", + "kvm_spurious_fault", + "__reiserfs_panic", + "lbug_with_loc", + "fortify_panic", + }; + + if (func->bind == STB_WEAK) + return 0; + + if (func->bind == STB_GLOBAL) + for (i = 0; i < ARRAY_SIZE(global_noreturns); i++) + if (!strcmp(func->name, global_noreturns[i])) + return 1; + + if (!func->sec) + return 0; + + func_for_each_insn(file, func, insn) { + empty = false; + + if (insn->type == INSN_RETURN) + return 0; + } + + if (empty) + return 0; + + /* + * A function can have a sibling call instead of a return. In that + * case, the function's dead-end status depends on whether the target + * of the sibling call returns. + */ + func_for_each_insn(file, func, insn) { + if (insn->sec != func->sec || + insn->offset >= func->offset + func->len) + break; + + if (insn->type == INSN_JUMP_UNCONDITIONAL) { + struct instruction *dest = insn->jump_dest; + struct symbol *dest_func; + + if (!dest) + /* sibling call to another file */ + return 0; + + if (dest->sec != func->sec || + dest->offset < func->offset || + dest->offset >= func->offset + func->len) { + /* local sibling call */ + dest_func = find_symbol_by_offset(dest->sec, + dest->offset); + if (!dest_func) + continue; + + if (recursion == 5) { + WARN_FUNC("infinite recursion (objtool bug!)", + dest->sec, dest->offset); + return -1; + } + + return __dead_end_function(file, dest_func, + recursion + 1); + } + } + + if (insn->type == INSN_JUMP_DYNAMIC && list_empty(&insn->alts)) + /* sibling call */ + return 0; + } + + return 1; +} + +static int dead_end_function(struct objtool_file *file, struct symbol *func) +{ + return __dead_end_function(file, func, 0); +} + +static void clear_insn_state(struct insn_state *state) +{ + int i; + + memset(state, 0, sizeof(*state)); + state->cfa.base = CFI_UNDEFINED; + for (i = 0; i < CFI_NUM_REGS; i++) { + state->regs[i].base = CFI_UNDEFINED; + state->vals[i].base = CFI_UNDEFINED; + } + state->drap_reg = CFI_UNDEFINED; + state->drap_offset = -1; +} + +/* + * Call the arch-specific instruction decoder for all the instructions and add + * them to the global instruction list. + */ +static int decode_instructions(struct objtool_file *file) +{ + struct section *sec; + struct symbol *func; + unsigned long offset; + struct instruction *insn; + int ret; + + for_each_sec(file, sec) { + + if (!(sec->sh.sh_flags & SHF_EXECINSTR)) + continue; + + if (strcmp(sec->name, ".altinstr_replacement") && + strcmp(sec->name, ".altinstr_aux") && + strncmp(sec->name, ".discard.", 9)) + sec->text = true; + + for (offset = 0; offset < sec->len; offset += insn->len) { + insn = malloc(sizeof(*insn)); + if (!insn) { + WARN("malloc failed"); + return -1; + } + memset(insn, 0, sizeof(*insn)); + INIT_LIST_HEAD(&insn->alts); + clear_insn_state(&insn->state); + + insn->sec = sec; + insn->offset = offset; + + ret = arch_decode_instruction(file->elf, sec, offset, + sec->len - offset, + &insn->len, &insn->type, + &insn->immediate, + &insn->stack_op); + if (ret) + return ret; + + if (!insn->type || insn->type > INSN_LAST) { + WARN_FUNC("invalid instruction type %d", + insn->sec, insn->offset, insn->type); + return -1; + } + + hash_add(file->insn_hash, &insn->hash, insn->offset); + list_add_tail(&insn->list, &file->insn_list); + } + + list_for_each_entry(func, &sec->symbol_list, list) { + if (func->type != STT_FUNC) + continue; + + if (!find_insn(file, sec, func->offset)) { + WARN("%s(): can't find starting instruction", + func->name); + return -1; + } + + func_for_each_insn(file, func, insn) + if (!insn->func) + insn->func = func; + } + } + + return 0; +} + +/* + * Mark "ud2" instructions and manually annotated dead ends. + */ +static int add_dead_ends(struct objtool_file *file) +{ + struct section *sec; + struct rela *rela; + struct instruction *insn; + bool found; + + /* + * By default, "ud2" is a dead end unless otherwise annotated, because + * GCC 7 inserts it for certain divide-by-zero cases. + */ + for_each_insn(file, insn) + if (insn->type == INSN_BUG) + insn->dead_end = true; + + /* + * Check for manually annotated dead ends. + */ + sec = find_section_by_name(file->elf, ".rela.discard.unreachable"); + if (!sec) + goto reachable; + + list_for_each_entry(rela, &sec->rela_list, list) { + if (rela->sym->type != STT_SECTION) { + WARN("unexpected relocation symbol type in %s", sec->name); + return -1; + } + insn = find_insn(file, rela->sym->sec, rela->addend); + if (insn) + insn = list_prev_entry(insn, list); + else if (rela->addend == rela->sym->sec->len) { + found = false; + list_for_each_entry_reverse(insn, &file->insn_list, list) { + if (insn->sec == rela->sym->sec) { + found = true; + break; + } + } + + if (!found) { + WARN("can't find unreachable insn at %s+0x%x", + rela->sym->sec->name, rela->addend); + return -1; + } + } else { + WARN("can't find unreachable insn at %s+0x%x", + rela->sym->sec->name, rela->addend); + return -1; + } + + insn->dead_end = true; + } + +reachable: + /* + * These manually annotated reachable checks are needed for GCC 4.4, + * where the Linux unreachable() macro isn't supported. In that case + * GCC doesn't know the "ud2" is fatal, so it generates code as if it's + * not a dead end. + */ + sec = find_section_by_name(file->elf, ".rela.discard.reachable"); + if (!sec) + return 0; + + list_for_each_entry(rela, &sec->rela_list, list) { + if (rela->sym->type != STT_SECTION) { + WARN("unexpected relocation symbol type in %s", sec->name); + return -1; + } + insn = find_insn(file, rela->sym->sec, rela->addend); + if (insn) + insn = list_prev_entry(insn, list); + else if (rela->addend == rela->sym->sec->len) { + found = false; + list_for_each_entry_reverse(insn, &file->insn_list, list) { + if (insn->sec == rela->sym->sec) { + found = true; + break; + } + } + + if (!found) { + WARN("can't find reachable insn at %s+0x%x", + rela->sym->sec->name, rela->addend); + return -1; + } + } else { + WARN("can't find reachable insn at %s+0x%x", + rela->sym->sec->name, rela->addend); + return -1; + } + + insn->dead_end = false; + } + + return 0; +} + +/* + * Warnings shouldn't be reported for ignored functions. + */ +static void add_ignores(struct objtool_file *file) +{ + struct instruction *insn; + struct section *sec; + struct symbol *func; + + for_each_sec(file, sec) { + list_for_each_entry(func, &sec->symbol_list, list) { + if (func->type != STT_FUNC) + continue; + + if (!ignore_func(file, func)) + continue; + + func_for_each_insn(file, func, insn) + insn->ignore = true; + } + } +} + +/* + * Find the destination instructions for all jumps. + */ +static int add_jump_destinations(struct objtool_file *file) +{ + struct instruction *insn; + struct rela *rela; + struct section *dest_sec; + unsigned long dest_off; + + for_each_insn(file, insn) { + if (insn->type != INSN_JUMP_CONDITIONAL && + insn->type != INSN_JUMP_UNCONDITIONAL) + continue; + + if (insn->ignore) + continue; + + rela = find_rela_by_dest_range(insn->sec, insn->offset, + insn->len); + if (!rela) { + dest_sec = insn->sec; + dest_off = insn->offset + insn->len + insn->immediate; + } else if (rela->sym->type == STT_SECTION) { + dest_sec = rela->sym->sec; + dest_off = rela->addend + 4; + } else if (rela->sym->sec->idx) { + dest_sec = rela->sym->sec; + dest_off = rela->sym->sym.st_value + rela->addend + 4; + } else { + /* sibling call */ + insn->jump_dest = 0; + continue; + } + + insn->jump_dest = find_insn(file, dest_sec, dest_off); + if (!insn->jump_dest) { + + /* + * This is a special case where an alt instruction + * jumps past the end of the section. These are + * handled later in handle_group_alt(). + */ + if (!strcmp(insn->sec->name, ".altinstr_replacement")) + continue; + + WARN_FUNC("can't find jump dest instruction at %s+0x%lx", + insn->sec, insn->offset, dest_sec->name, + dest_off); + return -1; + } + } + + return 0; +} + +/* + * Find the destination instructions for all calls. + */ +static int add_call_destinations(struct objtool_file *file) +{ + struct instruction *insn; + unsigned long dest_off; + struct rela *rela; + + for_each_insn(file, insn) { + if (insn->type != INSN_CALL) + continue; + + rela = find_rela_by_dest_range(insn->sec, insn->offset, + insn->len); + if (!rela) { + dest_off = insn->offset + insn->len + insn->immediate; + insn->call_dest = find_symbol_by_offset(insn->sec, + dest_off); + if (!insn->call_dest) { + WARN_FUNC("can't find call dest symbol at offset 0x%lx", + insn->sec, insn->offset, dest_off); + return -1; + } + } else if (rela->sym->type == STT_SECTION) { + insn->call_dest = find_symbol_by_offset(rela->sym->sec, + rela->addend+4); + if (!insn->call_dest || + insn->call_dest->type != STT_FUNC) { + WARN_FUNC("can't find call dest symbol at %s+0x%x", + insn->sec, insn->offset, + rela->sym->sec->name, + rela->addend + 4); + return -1; + } + } else + insn->call_dest = rela->sym; + } + + return 0; +} + +/* + * The .alternatives section requires some extra special care, over and above + * what other special sections require: + * + * 1. Because alternatives are patched in-place, we need to insert a fake jump + * instruction at the end so that validate_branch() skips all the original + * replaced instructions when validating the new instruction path. + * + * 2. An added wrinkle is that the new instruction length might be zero. In + * that case the old instructions are replaced with noops. We simulate that + * by creating a fake jump as the only new instruction. + * + * 3. In some cases, the alternative section includes an instruction which + * conditionally jumps to the _end_ of the entry. We have to modify these + * jumps' destinations to point back to .text rather than the end of the + * entry in .altinstr_replacement. + * + * 4. It has been requested that we don't validate the !POPCNT feature path + * which is a "very very small percentage of machines". + */ +static int handle_group_alt(struct objtool_file *file, + struct special_alt *special_alt, + struct instruction *orig_insn, + struct instruction **new_insn) +{ + struct instruction *last_orig_insn, *last_new_insn, *insn, *fake_jump; + unsigned long dest_off; + + last_orig_insn = NULL; + insn = orig_insn; + sec_for_each_insn_from(file, insn) { + if (insn->offset >= special_alt->orig_off + special_alt->orig_len) + break; + + if (special_alt->skip_orig) + insn->type = INSN_NOP; + + insn->alt_group = true; + last_orig_insn = insn; + } + + if (!next_insn_same_sec(file, last_orig_insn)) { + WARN("%s: don't know how to handle alternatives at end of section", + special_alt->orig_sec->name); + return -1; + } + + fake_jump = malloc(sizeof(*fake_jump)); + if (!fake_jump) { + WARN("malloc failed"); + return -1; + } + memset(fake_jump, 0, sizeof(*fake_jump)); + INIT_LIST_HEAD(&fake_jump->alts); + clear_insn_state(&fake_jump->state); + + fake_jump->sec = special_alt->new_sec; + fake_jump->offset = -1; + fake_jump->type = INSN_JUMP_UNCONDITIONAL; + fake_jump->jump_dest = list_next_entry(last_orig_insn, list); + fake_jump->ignore = true; + + if (!special_alt->new_len) { + *new_insn = fake_jump; + return 0; + } + + last_new_insn = NULL; + insn = *new_insn; + sec_for_each_insn_from(file, insn) { + if (insn->offset >= special_alt->new_off + special_alt->new_len) + break; + + last_new_insn = insn; + + if (insn->type != INSN_JUMP_CONDITIONAL && + insn->type != INSN_JUMP_UNCONDITIONAL) + continue; + + if (!insn->immediate) + continue; + + dest_off = insn->offset + insn->len + insn->immediate; + if (dest_off == special_alt->new_off + special_alt->new_len) + insn->jump_dest = fake_jump; + + if (!insn->jump_dest) { + WARN_FUNC("can't find alternative jump destination", + insn->sec, insn->offset); + return -1; + } + } + + if (!last_new_insn) { + WARN_FUNC("can't find last new alternative instruction", + special_alt->new_sec, special_alt->new_off); + return -1; + } + + list_add(&fake_jump->list, &last_new_insn->list); + + return 0; +} + +/* + * A jump table entry can either convert a nop to a jump or a jump to a nop. + * If the original instruction is a jump, make the alt entry an effective nop + * by just skipping the original instruction. + */ +static int handle_jump_alt(struct objtool_file *file, + struct special_alt *special_alt, + struct instruction *orig_insn, + struct instruction **new_insn) +{ + if (orig_insn->type == INSN_NOP) + return 0; + + if (orig_insn->type != INSN_JUMP_UNCONDITIONAL) { + WARN_FUNC("unsupported instruction at jump label", + orig_insn->sec, orig_insn->offset); + return -1; + } + + *new_insn = list_next_entry(orig_insn, list); + return 0; +} + +/* + * Read all the special sections which have alternate instructions which can be + * patched in or redirected to at runtime. Each instruction having alternate + * instruction(s) has them added to its insn->alts list, which will be + * traversed in validate_branch(). + */ +static int add_special_section_alts(struct objtool_file *file) +{ + struct list_head special_alts; + struct instruction *orig_insn, *new_insn; + struct special_alt *special_alt, *tmp; + struct alternative *alt; + int ret; + + ret = special_get_alts(file->elf, &special_alts); + if (ret) + return ret; + + list_for_each_entry_safe(special_alt, tmp, &special_alts, list) { + alt = malloc(sizeof(*alt)); + if (!alt) { + WARN("malloc failed"); + ret = -1; + goto out; + } + + orig_insn = find_insn(file, special_alt->orig_sec, + special_alt->orig_off); + if (!orig_insn) { + WARN_FUNC("special: can't find orig instruction", + special_alt->orig_sec, special_alt->orig_off); + ret = -1; + goto out; + } + + new_insn = NULL; + if (!special_alt->group || special_alt->new_len) { + new_insn = find_insn(file, special_alt->new_sec, + special_alt->new_off); + if (!new_insn) { + WARN_FUNC("special: can't find new instruction", + special_alt->new_sec, + special_alt->new_off); + ret = -1; + goto out; + } + } + + if (special_alt->group) { + ret = handle_group_alt(file, special_alt, orig_insn, + &new_insn); + if (ret) + goto out; + } else if (special_alt->jump_or_nop) { + ret = handle_jump_alt(file, special_alt, orig_insn, + &new_insn); + if (ret) + goto out; + } + + alt->insn = new_insn; + list_add_tail(&alt->list, &orig_insn->alts); + + list_del(&special_alt->list); + free(special_alt); + } + +out: + return ret; +} + +static int add_switch_table(struct objtool_file *file, struct symbol *func, + struct instruction *insn, struct rela *table, + struct rela *next_table) +{ + struct rela *rela = table; + struct instruction *alt_insn; + struct alternative *alt; + + list_for_each_entry_from(rela, &file->rodata->rela->rela_list, list) { + if (rela == next_table) + break; + + if (rela->sym->sec != insn->sec || + rela->addend <= func->offset || + rela->addend >= func->offset + func->len) + break; + + alt_insn = find_insn(file, insn->sec, rela->addend); + if (!alt_insn) { + WARN("%s: can't find instruction at %s+0x%x", + file->rodata->rela->name, insn->sec->name, + rela->addend); + return -1; + } + + alt = malloc(sizeof(*alt)); + if (!alt) { + WARN("malloc failed"); + return -1; + } + + alt->insn = alt_insn; + list_add_tail(&alt->list, &insn->alts); + } + + return 0; +} + +/* + * find_switch_table() - Given a dynamic jump, find the switch jump table in + * .rodata associated with it. + * + * There are 3 basic patterns: + * + * 1. jmpq *[rodata addr](,%reg,8) + * + * This is the most common case by far. It jumps to an address in a simple + * jump table which is stored in .rodata. + * + * 2. jmpq *[rodata addr](%rip) + * + * This is caused by a rare GCC quirk, currently only seen in three driver + * functions in the kernel, only with certain obscure non-distro configs. + * + * As part of an optimization, GCC makes a copy of an existing switch jump + * table, modifies it, and then hard-codes the jump (albeit with an indirect + * jump) to use a single entry in the table. The rest of the jump table and + * some of its jump targets remain as dead code. + * + * In such a case we can just crudely ignore all unreachable instruction + * warnings for the entire object file. Ideally we would just ignore them + * for the function, but that would require redesigning the code quite a + * bit. And honestly that's just not worth doing: unreachable instruction + * warnings are of questionable value anyway, and this is such a rare issue. + * + * 3. mov [rodata addr],%reg1 + * ... some instructions ... + * jmpq *(%reg1,%reg2,8) + * + * This is a fairly uncommon pattern which is new for GCC 6. As of this + * writing, there are 11 occurrences of it in the allmodconfig kernel. + * + * TODO: Once we have DWARF CFI and smarter instruction decoding logic, + * ensure the same register is used in the mov and jump instructions. + */ +static struct rela *find_switch_table(struct objtool_file *file, + struct symbol *func, + struct instruction *insn) +{ + struct rela *text_rela, *rodata_rela; + struct instruction *orig_insn = insn; + + text_rela = find_rela_by_dest_range(insn->sec, insn->offset, insn->len); + if (text_rela && text_rela->sym == file->rodata->sym) { + /* case 1 */ + rodata_rela = find_rela_by_dest(file->rodata, + text_rela->addend); + if (rodata_rela) + return rodata_rela; + + /* case 2 */ + rodata_rela = find_rela_by_dest(file->rodata, + text_rela->addend + 4); + if (!rodata_rela) + return NULL; + file->ignore_unreachables = true; + return rodata_rela; + } + + /* case 3 */ + func_for_each_insn_continue_reverse(file, func, insn) { + if (insn->type == INSN_JUMP_DYNAMIC) + break; + + /* allow small jumps within the range */ + if (insn->type == INSN_JUMP_UNCONDITIONAL && + insn->jump_dest && + (insn->jump_dest->offset <= insn->offset || + insn->jump_dest->offset > orig_insn->offset)) + break; + + /* look for a relocation which references .rodata */ + text_rela = find_rela_by_dest_range(insn->sec, insn->offset, + insn->len); + if (!text_rela || text_rela->sym != file->rodata->sym) + continue; + + /* + * Make sure the .rodata address isn't associated with a + * symbol. gcc jump tables are anonymous data. + */ + if (find_symbol_containing(file->rodata, text_rela->addend)) + continue; + + return find_rela_by_dest(file->rodata, text_rela->addend); + } + + return NULL; +} + +static int add_func_switch_tables(struct objtool_file *file, + struct symbol *func) +{ + struct instruction *insn, *prev_jump = NULL; + struct rela *rela, *prev_rela = NULL; + int ret; + + func_for_each_insn(file, func, insn) { + if (insn->type != INSN_JUMP_DYNAMIC) + continue; + + rela = find_switch_table(file, func, insn); + if (!rela) + continue; + + /* + * We found a switch table, but we don't know yet how big it + * is. Don't add it until we reach the end of the function or + * the beginning of another switch table in the same function. + */ + if (prev_jump) { + ret = add_switch_table(file, func, prev_jump, prev_rela, + rela); + if (ret) + return ret; + } + + prev_jump = insn; + prev_rela = rela; + } + + if (prev_jump) { + ret = add_switch_table(file, func, prev_jump, prev_rela, NULL); + if (ret) + return ret; + } + + return 0; +} + +/* + * For some switch statements, gcc generates a jump table in the .rodata + * section which contains a list of addresses within the function to jump to. + * This finds these jump tables and adds them to the insn->alts lists. + */ +static int add_switch_table_alts(struct objtool_file *file) +{ + struct section *sec; + struct symbol *func; + int ret; + + if (!file->rodata || !file->rodata->rela) + return 0; + + for_each_sec(file, sec) { + list_for_each_entry(func, &sec->symbol_list, list) { + if (func->type != STT_FUNC) + continue; + + ret = add_func_switch_tables(file, func); + if (ret) + return ret; + } + } + + return 0; +} + +static int read_unwind_hints(struct objtool_file *file) +{ + struct section *sec, *relasec; + struct rela *rela; + struct unwind_hint *hint; + struct instruction *insn; + struct cfi_reg *cfa; + int i; + + sec = find_section_by_name(file->elf, ".discard.unwind_hints"); + if (!sec) + return 0; + + relasec = sec->rela; + if (!relasec) { + WARN("missing .rela.discard.unwind_hints section"); + return -1; + } + + if (sec->len % sizeof(struct unwind_hint)) { + WARN("struct unwind_hint size mismatch"); + return -1; + } + + file->hints = true; + + for (i = 0; i < sec->len / sizeof(struct unwind_hint); i++) { + hint = (struct unwind_hint *)sec->data->d_buf + i; + + rela = find_rela_by_dest(sec, i * sizeof(*hint)); + if (!rela) { + WARN("can't find rela for unwind_hints[%d]", i); + return -1; + } + + insn = find_insn(file, rela->sym->sec, rela->addend); + if (!insn) { + WARN("can't find insn for unwind_hints[%d]", i); + return -1; + } + + cfa = &insn->state.cfa; + + if (hint->type == UNWIND_HINT_TYPE_SAVE) { + insn->save = true; + continue; + + } else if (hint->type == UNWIND_HINT_TYPE_RESTORE) { + insn->restore = true; + insn->hint = true; + continue; + } + + insn->hint = true; + + switch (hint->sp_reg) { + case ORC_REG_UNDEFINED: + cfa->base = CFI_UNDEFINED; + break; + case ORC_REG_SP: + cfa->base = CFI_SP; + break; + case ORC_REG_BP: + cfa->base = CFI_BP; + break; + case ORC_REG_SP_INDIRECT: + cfa->base = CFI_SP_INDIRECT; + break; + case ORC_REG_R10: + cfa->base = CFI_R10; + break; + case ORC_REG_R13: + cfa->base = CFI_R13; + break; + case ORC_REG_DI: + cfa->base = CFI_DI; + break; + case ORC_REG_DX: + cfa->base = CFI_DX; + break; + default: + WARN_FUNC("unsupported unwind_hint sp base reg %d", + insn->sec, insn->offset, hint->sp_reg); + return -1; + } + + cfa->offset = hint->sp_offset; + insn->state.type = hint->type; + } + + return 0; +} + +static int decode_sections(struct objtool_file *file) +{ + int ret; + + ret = decode_instructions(file); + if (ret) + return ret; + + ret = add_dead_ends(file); + if (ret) + return ret; + + add_ignores(file); + + ret = add_jump_destinations(file); + if (ret) + return ret; + + ret = add_call_destinations(file); + if (ret) + return ret; + + ret = add_special_section_alts(file); + if (ret) + return ret; + + ret = add_switch_table_alts(file); + if (ret) + return ret; + + ret = read_unwind_hints(file); + if (ret) + return ret; + + return 0; +} + +static bool is_fentry_call(struct instruction *insn) +{ + if (insn->type == INSN_CALL && + insn->call_dest->type == STT_NOTYPE && + !strcmp(insn->call_dest->name, "__fentry__")) + return true; + + return false; +} + +static bool has_modified_stack_frame(struct insn_state *state) +{ + int i; + + if (state->cfa.base != initial_func_cfi.cfa.base || + state->cfa.offset != initial_func_cfi.cfa.offset || + state->stack_size != initial_func_cfi.cfa.offset || + state->drap) + return true; + + for (i = 0; i < CFI_NUM_REGS; i++) + if (state->regs[i].base != initial_func_cfi.regs[i].base || + state->regs[i].offset != initial_func_cfi.regs[i].offset) + return true; + + return false; +} + +static bool has_valid_stack_frame(struct insn_state *state) +{ + if (state->cfa.base == CFI_BP && state->regs[CFI_BP].base == CFI_CFA && + state->regs[CFI_BP].offset == -16) + return true; + + if (state->drap && state->regs[CFI_BP].base == CFI_BP) + return true; + + return false; +} + +static int update_insn_state_regs(struct instruction *insn, struct insn_state *state) +{ + struct cfi_reg *cfa = &state->cfa; + struct stack_op *op = &insn->stack_op; + + if (cfa->base != CFI_SP) + return 0; + + /* push */ + if (op->dest.type == OP_DEST_PUSH) + cfa->offset += 8; + + /* pop */ + if (op->src.type == OP_SRC_POP) + cfa->offset -= 8; + + /* add immediate to sp */ + if (op->dest.type == OP_DEST_REG && op->src.type == OP_SRC_ADD && + op->dest.reg == CFI_SP && op->src.reg == CFI_SP) + cfa->offset -= op->src.offset; + + return 0; +} + +static void save_reg(struct insn_state *state, unsigned char reg, int base, + int offset) +{ + if (arch_callee_saved_reg(reg) && + state->regs[reg].base == CFI_UNDEFINED) { + state->regs[reg].base = base; + state->regs[reg].offset = offset; + } +} + +static void restore_reg(struct insn_state *state, unsigned char reg) +{ + state->regs[reg].base = CFI_UNDEFINED; + state->regs[reg].offset = 0; +} + +/* + * A note about DRAP stack alignment: + * + * GCC has the concept of a DRAP register, which is used to help keep track of + * the stack pointer when aligning the stack. r10 or r13 is used as the DRAP + * register. The typical DRAP pattern is: + * + * 4c 8d 54 24 08 lea 0x8(%rsp),%r10 + * 48 83 e4 c0 and $0xffffffffffffffc0,%rsp + * 41 ff 72 f8 pushq -0x8(%r10) + * 55 push %rbp + * 48 89 e5 mov %rsp,%rbp + * (more pushes) + * 41 52 push %r10 + * ... + * 41 5a pop %r10 + * (more pops) + * 5d pop %rbp + * 49 8d 62 f8 lea -0x8(%r10),%rsp + * c3 retq + * + * There are some variations in the epilogues, like: + * + * 5b pop %rbx + * 41 5a pop %r10 + * 41 5c pop %r12 + * 41 5d pop %r13 + * 41 5e pop %r14 + * c9 leaveq + * 49 8d 62 f8 lea -0x8(%r10),%rsp + * c3 retq + * + * and: + * + * 4c 8b 55 e8 mov -0x18(%rbp),%r10 + * 48 8b 5d e0 mov -0x20(%rbp),%rbx + * 4c 8b 65 f0 mov -0x10(%rbp),%r12 + * 4c 8b 6d f8 mov -0x8(%rbp),%r13 + * c9 leaveq + * 49 8d 62 f8 lea -0x8(%r10),%rsp + * c3 retq + * + * Sometimes r13 is used as the DRAP register, in which case it's saved and + * restored beforehand: + * + * 41 55 push %r13 + * 4c 8d 6c 24 10 lea 0x10(%rsp),%r13 + * 48 83 e4 f0 and $0xfffffffffffffff0,%rsp + * ... + * 49 8d 65 f0 lea -0x10(%r13),%rsp + * 41 5d pop %r13 + * c3 retq + */ +static int update_insn_state(struct instruction *insn, struct insn_state *state) +{ + struct stack_op *op = &insn->stack_op; + struct cfi_reg *cfa = &state->cfa; + struct cfi_reg *regs = state->regs; + + /* stack operations don't make sense with an undefined CFA */ + if (cfa->base == CFI_UNDEFINED) { + if (insn->func) { + WARN_FUNC("undefined stack state", insn->sec, insn->offset); + return -1; + } + return 0; + } + + if (state->type == ORC_TYPE_REGS || state->type == ORC_TYPE_REGS_IRET) + return update_insn_state_regs(insn, state); + + switch (op->dest.type) { + + case OP_DEST_REG: + switch (op->src.type) { + + case OP_SRC_REG: + if (op->src.reg == CFI_SP && op->dest.reg == CFI_BP) { + + if (cfa->base == CFI_SP && + regs[CFI_BP].base == CFI_CFA && + regs[CFI_BP].offset == -cfa->offset) { + + /* mov %rsp, %rbp */ + cfa->base = op->dest.reg; + state->bp_scratch = false; + } + + else if (state->drap) { + + /* drap: mov %rsp, %rbp */ + regs[CFI_BP].base = CFI_BP; + regs[CFI_BP].offset = -state->stack_size; + state->bp_scratch = false; + } + } + + else if (op->dest.reg == cfa->base) { + + /* mov %reg, %rsp */ + if (cfa->base == CFI_SP && + state->vals[op->src.reg].base == CFI_CFA) { + + /* + * This is needed for the rare case + * where GCC does something dumb like: + * + * lea 0x8(%rsp), %rcx + * ... + * mov %rcx, %rsp + */ + cfa->offset = -state->vals[op->src.reg].offset; + state->stack_size = cfa->offset; + + } else { + cfa->base = CFI_UNDEFINED; + cfa->offset = 0; + } + } + + break; + + case OP_SRC_ADD: + if (op->dest.reg == CFI_SP && op->src.reg == CFI_SP) { + + /* add imm, %rsp */ + state->stack_size -= op->src.offset; + if (cfa->base == CFI_SP) + cfa->offset -= op->src.offset; + break; + } + + if (op->dest.reg == CFI_SP && op->src.reg == CFI_BP) { + + /* lea disp(%rbp), %rsp */ + state->stack_size = -(op->src.offset + regs[CFI_BP].offset); + break; + } + + if (op->src.reg == CFI_SP && cfa->base == CFI_SP) { + + /* drap: lea disp(%rsp), %drap */ + state->drap_reg = op->dest.reg; + + /* + * lea disp(%rsp), %reg + * + * This is needed for the rare case where GCC + * does something dumb like: + * + * lea 0x8(%rsp), %rcx + * ... + * mov %rcx, %rsp + */ + state->vals[op->dest.reg].base = CFI_CFA; + state->vals[op->dest.reg].offset = \ + -state->stack_size + op->src.offset; + + break; + } + + if (state->drap && op->dest.reg == CFI_SP && + op->src.reg == state->drap_reg) { + + /* drap: lea disp(%drap), %rsp */ + cfa->base = CFI_SP; + cfa->offset = state->stack_size = -op->src.offset; + state->drap_reg = CFI_UNDEFINED; + state->drap = false; + break; + } + + if (op->dest.reg == state->cfa.base) { + WARN_FUNC("unsupported stack register modification", + insn->sec, insn->offset); + return -1; + } + + break; + + case OP_SRC_AND: + if (op->dest.reg != CFI_SP || + (state->drap_reg != CFI_UNDEFINED && cfa->base != CFI_SP) || + (state->drap_reg == CFI_UNDEFINED && cfa->base != CFI_BP)) { + WARN_FUNC("unsupported stack pointer realignment", + insn->sec, insn->offset); + return -1; + } + + if (state->drap_reg != CFI_UNDEFINED) { + /* drap: and imm, %rsp */ + cfa->base = state->drap_reg; + cfa->offset = state->stack_size = 0; + state->drap = true; + } + + /* + * Older versions of GCC (4.8ish) realign the stack + * without DRAP, with a frame pointer. + */ + + break; + + case OP_SRC_POP: + if (!state->drap && op->dest.type == OP_DEST_REG && + op->dest.reg == cfa->base) { + + /* pop %rbp */ + cfa->base = CFI_SP; + } + + if (state->drap && cfa->base == CFI_BP_INDIRECT && + op->dest.type == OP_DEST_REG && + op->dest.reg == state->drap_reg && + state->drap_offset == -state->stack_size) { + + /* drap: pop %drap */ + cfa->base = state->drap_reg; + cfa->offset = 0; + state->drap_offset = -1; + + } else if (regs[op->dest.reg].offset == -state->stack_size) { + + /* pop %reg */ + restore_reg(state, op->dest.reg); + } + + state->stack_size -= 8; + if (cfa->base == CFI_SP) + cfa->offset -= 8; + + break; + + case OP_SRC_REG_INDIRECT: + if (state->drap && op->src.reg == CFI_BP && + op->src.offset == state->drap_offset) { + + /* drap: mov disp(%rbp), %drap */ + cfa->base = state->drap_reg; + cfa->offset = 0; + state->drap_offset = -1; + } + + if (state->drap && op->src.reg == CFI_BP && + op->src.offset == regs[op->dest.reg].offset) { + + /* drap: mov disp(%rbp), %reg */ + restore_reg(state, op->dest.reg); + + } else if (op->src.reg == cfa->base && + op->src.offset == regs[op->dest.reg].offset + cfa->offset) { + + /* mov disp(%rbp), %reg */ + /* mov disp(%rsp), %reg */ + restore_reg(state, op->dest.reg); + } + + break; + + default: + WARN_FUNC("unknown stack-related instruction", + insn->sec, insn->offset); + return -1; + } + + break; + + case OP_DEST_PUSH: + state->stack_size += 8; + if (cfa->base == CFI_SP) + cfa->offset += 8; + + if (op->src.type != OP_SRC_REG) + break; + + if (state->drap) { + if (op->src.reg == cfa->base && op->src.reg == state->drap_reg) { + + /* drap: push %drap */ + cfa->base = CFI_BP_INDIRECT; + cfa->offset = -state->stack_size; + + /* save drap so we know when to restore it */ + state->drap_offset = -state->stack_size; + + } else if (op->src.reg == CFI_BP && cfa->base == state->drap_reg) { + + /* drap: push %rbp */ + state->stack_size = 0; + + } else if (regs[op->src.reg].base == CFI_UNDEFINED) { + + /* drap: push %reg */ + save_reg(state, op->src.reg, CFI_BP, -state->stack_size); + } + + } else { + + /* push %reg */ + save_reg(state, op->src.reg, CFI_CFA, -state->stack_size); + } + + /* detect when asm code uses rbp as a scratch register */ + if (!no_fp && insn->func && op->src.reg == CFI_BP && + cfa->base != CFI_BP) + state->bp_scratch = true; + break; + + case OP_DEST_REG_INDIRECT: + + if (state->drap) { + if (op->src.reg == cfa->base && op->src.reg == state->drap_reg) { + + /* drap: mov %drap, disp(%rbp) */ + cfa->base = CFI_BP_INDIRECT; + cfa->offset = op->dest.offset; + + /* save drap offset so we know when to restore it */ + state->drap_offset = op->dest.offset; + } + + else if (regs[op->src.reg].base == CFI_UNDEFINED) { + + /* drap: mov reg, disp(%rbp) */ + save_reg(state, op->src.reg, CFI_BP, op->dest.offset); + } + + } else if (op->dest.reg == cfa->base) { + + /* mov reg, disp(%rbp) */ + /* mov reg, disp(%rsp) */ + save_reg(state, op->src.reg, CFI_CFA, + op->dest.offset - state->cfa.offset); + } + + break; + + case OP_DEST_LEAVE: + if ((!state->drap && cfa->base != CFI_BP) || + (state->drap && cfa->base != state->drap_reg)) { + WARN_FUNC("leave instruction with modified stack frame", + insn->sec, insn->offset); + return -1; + } + + /* leave (mov %rbp, %rsp; pop %rbp) */ + + state->stack_size = -state->regs[CFI_BP].offset - 8; + restore_reg(state, CFI_BP); + + if (!state->drap) { + cfa->base = CFI_SP; + cfa->offset -= 8; + } + + break; + + case OP_DEST_MEM: + if (op->src.type != OP_SRC_POP) { + WARN_FUNC("unknown stack-related memory operation", + insn->sec, insn->offset); + return -1; + } + + /* pop mem */ + state->stack_size -= 8; + if (cfa->base == CFI_SP) + cfa->offset -= 8; + + break; + + default: + WARN_FUNC("unknown stack-related instruction", + insn->sec, insn->offset); + return -1; + } + + return 0; +} + +static bool insn_state_match(struct instruction *insn, struct insn_state *state) +{ + struct insn_state *state1 = &insn->state, *state2 = state; + int i; + + if (memcmp(&state1->cfa, &state2->cfa, sizeof(state1->cfa))) { + WARN_FUNC("stack state mismatch: cfa1=%d%+d cfa2=%d%+d", + insn->sec, insn->offset, + state1->cfa.base, state1->cfa.offset, + state2->cfa.base, state2->cfa.offset); + + } else if (memcmp(&state1->regs, &state2->regs, sizeof(state1->regs))) { + for (i = 0; i < CFI_NUM_REGS; i++) { + if (!memcmp(&state1->regs[i], &state2->regs[i], + sizeof(struct cfi_reg))) + continue; + + WARN_FUNC("stack state mismatch: reg1[%d]=%d%+d reg2[%d]=%d%+d", + insn->sec, insn->offset, + i, state1->regs[i].base, state1->regs[i].offset, + i, state2->regs[i].base, state2->regs[i].offset); + break; + } + + } else if (state1->type != state2->type) { + WARN_FUNC("stack state mismatch: type1=%d type2=%d", + insn->sec, insn->offset, state1->type, state2->type); + + } else if (state1->drap != state2->drap || + (state1->drap && state1->drap_reg != state2->drap_reg) || + (state1->drap && state1->drap_offset != state2->drap_offset)) { + WARN_FUNC("stack state mismatch: drap1=%d(%d,%d) drap2=%d(%d,%d)", + insn->sec, insn->offset, + state1->drap, state1->drap_reg, state1->drap_offset, + state2->drap, state2->drap_reg, state2->drap_offset); + + } else + return true; + + return false; +} + +/* + * Follow the branch starting at the given instruction, and recursively follow + * any other branches (jumps). Meanwhile, track the frame pointer state at + * each instruction and validate all the rules described in + * tools/objtool/Documentation/stack-validation.txt. + */ +static int validate_branch(struct objtool_file *file, struct instruction *first, + struct insn_state state) +{ + struct alternative *alt; + struct instruction *insn, *next_insn; + struct section *sec; + struct symbol *func = NULL; + int ret; + + insn = first; + sec = insn->sec; + + if (insn->alt_group && list_empty(&insn->alts)) { + WARN_FUNC("don't know how to handle branch to middle of alternative instruction group", + sec, insn->offset); + return 1; + } + + while (1) { + next_insn = next_insn_same_sec(file, insn); + + + if (file->c_file && func && insn->func && func != insn->func) { + WARN("%s() falls through to next function %s()", + func->name, insn->func->name); + return 1; + } + + if (insn->func) + func = insn->func; + + if (func && insn->ignore) { + WARN_FUNC("BUG: why am I validating an ignored function?", + sec, insn->offset); + return 1; + } + + if (insn->visited) { + if (!insn->hint && !insn_state_match(insn, &state)) + return 1; + + return 0; + } + + if (insn->hint) { + if (insn->restore) { + struct instruction *save_insn, *i; + + i = insn; + save_insn = NULL; + func_for_each_insn_continue_reverse(file, func, i) { + if (i->save) { + save_insn = i; + break; + } + } + + if (!save_insn) { + WARN_FUNC("no corresponding CFI save for CFI restore", + sec, insn->offset); + return 1; + } + + if (!save_insn->visited) { + /* + * Oops, no state to copy yet. + * Hopefully we can reach this + * instruction from another branch + * after the save insn has been + * visited. + */ + if (insn == first) + return 0; + + WARN_FUNC("objtool isn't smart enough to handle this CFI save/restore combo", + sec, insn->offset); + return 1; + } + + insn->state = save_insn->state; + } + + state = insn->state; + + } else + insn->state = state; + + insn->visited = true; + + list_for_each_entry(alt, &insn->alts, list) { + ret = validate_branch(file, alt->insn, state); + if (ret) + return 1; + } + + switch (insn->type) { + + case INSN_RETURN: + if (func && has_modified_stack_frame(&state)) { + WARN_FUNC("return with modified stack frame", + sec, insn->offset); + return 1; + } + + if (state.bp_scratch) { + WARN("%s uses BP as a scratch register", + insn->func->name); + return 1; + } + + return 0; + + case INSN_CALL: + if (is_fentry_call(insn)) + break; + + ret = dead_end_function(file, insn->call_dest); + if (ret == 1) + return 0; + if (ret == -1) + return 1; + + /* fallthrough */ + case INSN_CALL_DYNAMIC: + if (!no_fp && func && !has_valid_stack_frame(&state)) { + WARN_FUNC("call without frame pointer save/setup", + sec, insn->offset); + return 1; + } + break; + + case INSN_JUMP_CONDITIONAL: + case INSN_JUMP_UNCONDITIONAL: + if (insn->jump_dest && + (!func || !insn->jump_dest->func || + func == insn->jump_dest->func)) { + ret = validate_branch(file, insn->jump_dest, + state); + if (ret) + return 1; + + } else if (func && has_modified_stack_frame(&state)) { + WARN_FUNC("sibling call from callable instruction with modified stack frame", + sec, insn->offset); + return 1; + } + + if (insn->type == INSN_JUMP_UNCONDITIONAL) + return 0; + + break; + + case INSN_JUMP_DYNAMIC: + if (func && list_empty(&insn->alts) && + has_modified_stack_frame(&state)) { + WARN_FUNC("sibling call from callable instruction with modified stack frame", + sec, insn->offset); + return 1; + } + + return 0; + + case INSN_CONTEXT_SWITCH: + if (func && (!next_insn || !next_insn->hint)) { + WARN_FUNC("unsupported instruction in callable function", + sec, insn->offset); + return 1; + } + return 0; + + case INSN_STACK: + if (update_insn_state(insn, &state)) + return 1; + + break; + + default: + break; + } + + if (insn->dead_end) + return 0; + + insn = next_insn; + if (!insn) { + WARN("%s: unexpected end of section", sec->name); + return 1; + } + } + + return 0; +} + +static int validate_unwind_hints(struct objtool_file *file) +{ + struct instruction *insn; + int ret, warnings = 0; + struct insn_state state; + + if (!file->hints) + return 0; + + clear_insn_state(&state); + + for_each_insn(file, insn) { + if (insn->hint && !insn->visited) { + ret = validate_branch(file, insn, state); + warnings += ret; + } + } + + return warnings; +} + +static bool is_kasan_insn(struct instruction *insn) +{ + return (insn->type == INSN_CALL && + !strcmp(insn->call_dest->name, "__asan_handle_no_return")); +} + +static bool is_ubsan_insn(struct instruction *insn) +{ + return (insn->type == INSN_CALL && + !strcmp(insn->call_dest->name, + "__ubsan_handle_builtin_unreachable")); +} + +static bool ignore_unreachable_insn(struct instruction *insn) +{ + int i; + + if (insn->ignore || insn->type == INSN_NOP) + return true; + + /* + * Ignore any unused exceptions. This can happen when a whitelisted + * function has an exception table entry. + * + * Also ignore alternative replacement instructions. This can happen + * when a whitelisted function uses one of the ALTERNATIVE macros. + */ + if (!strcmp(insn->sec->name, ".fixup") || + !strcmp(insn->sec->name, ".altinstr_replacement") || + !strcmp(insn->sec->name, ".altinstr_aux")) + return true; + + /* + * Check if this (or a subsequent) instruction is related to + * CONFIG_UBSAN or CONFIG_KASAN. + * + * End the search at 5 instructions to avoid going into the weeds. + */ + if (!insn->func) + return false; + for (i = 0; i < 5; i++) { + + if (is_kasan_insn(insn) || is_ubsan_insn(insn)) + return true; + + if (insn->type == INSN_JUMP_UNCONDITIONAL && insn->jump_dest) { + insn = insn->jump_dest; + continue; + } + + if (insn->offset + insn->len >= insn->func->offset + insn->func->len) + break; + insn = list_next_entry(insn, list); + } + + return false; +} + +static int validate_functions(struct objtool_file *file) +{ + struct section *sec; + struct symbol *func; + struct instruction *insn; + struct insn_state state; + int ret, warnings = 0; + + clear_insn_state(&state); + + state.cfa = initial_func_cfi.cfa; + memcpy(&state.regs, &initial_func_cfi.regs, + CFI_NUM_REGS * sizeof(struct cfi_reg)); + state.stack_size = initial_func_cfi.cfa.offset; + + for_each_sec(file, sec) { + list_for_each_entry(func, &sec->symbol_list, list) { + if (func->type != STT_FUNC) + continue; + + insn = find_insn(file, sec, func->offset); + if (!insn || insn->ignore) + continue; + + ret = validate_branch(file, insn, state); + warnings += ret; + } + } + + return warnings; +} + +static int validate_reachable_instructions(struct objtool_file *file) +{ + struct instruction *insn; + + if (file->ignore_unreachables) + return 0; + + for_each_insn(file, insn) { + if (insn->visited || ignore_unreachable_insn(insn)) + continue; + + WARN_FUNC("unreachable instruction", insn->sec, insn->offset); + return 1; + } + + return 0; +} + +static void cleanup(struct objtool_file *file) +{ + struct instruction *insn, *tmpinsn; + struct alternative *alt, *tmpalt; + + list_for_each_entry_safe(insn, tmpinsn, &file->insn_list, list) { + list_for_each_entry_safe(alt, tmpalt, &insn->alts, list) { + list_del(&alt->list); + free(alt); + } + list_del(&insn->list); + hash_del(&insn->hash); + free(insn); + } + elf_close(file->elf); +} + +int check(const char *_objname, bool _no_fp, bool no_unreachable, bool orc) +{ + struct objtool_file file; + int ret, warnings = 0; + + objname = _objname; + no_fp = _no_fp; + + file.elf = elf_open(objname, orc ? O_RDWR : O_RDONLY); + if (!file.elf) + return 1; + + INIT_LIST_HEAD(&file.insn_list); + hash_init(file.insn_hash); + file.whitelist = find_section_by_name(file.elf, ".discard.func_stack_frame_non_standard"); + file.rodata = find_section_by_name(file.elf, ".rodata"); + file.c_file = find_section_by_name(file.elf, ".comment"); + file.ignore_unreachables = no_unreachable; + file.hints = false; + + arch_initial_func_cfi_state(&initial_func_cfi); + + ret = decode_sections(&file); + if (ret < 0) + goto out; + warnings += ret; + + if (list_empty(&file.insn_list)) + goto out; + + ret = validate_functions(&file); + if (ret < 0) + goto out; + warnings += ret; + + ret = validate_unwind_hints(&file); + if (ret < 0) + goto out; + warnings += ret; + + if (!warnings) { + ret = validate_reachable_instructions(&file); + if (ret < 0) + goto out; + warnings += ret; + } + + if (orc) { + ret = create_orc(&file); + if (ret < 0) + goto out; + + ret = create_orc_sections(&file); + if (ret < 0) + goto out; + + ret = elf_write(file.elf); + if (ret < 0) + goto out; + } + +out: + cleanup(&file); + + /* ignore warnings for now until we get all the code cleaned up */ + if (ret || warnings) + return 0; + return 0; +} diff --git a/tools/objtool/check.h b/tools/objtool/check.h new file mode 100644 index 000000000000..47d9ea70a83d --- /dev/null +++ b/tools/objtool/check.h @@ -0,0 +1,80 @@ +/* + * Copyright (C) 2017 Josh Poimboeuf <jpoimboe@redhat.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef _CHECK_H +#define _CHECK_H + +#include <stdbool.h> +#include "elf.h" +#include "cfi.h" +#include "arch.h" +#include "orc.h" +#include <linux/hashtable.h> + +struct insn_state { + struct cfi_reg cfa; + struct cfi_reg regs[CFI_NUM_REGS]; + int stack_size; + unsigned char type; + bool bp_scratch; + bool drap; + int drap_reg, drap_offset; + struct cfi_reg vals[CFI_NUM_REGS]; +}; + +struct instruction { + struct list_head list; + struct hlist_node hash; + struct section *sec; + unsigned long offset; + unsigned int len; + unsigned char type; + unsigned long immediate; + bool alt_group, visited, dead_end, ignore, hint, save, restore; + struct symbol *call_dest; + struct instruction *jump_dest; + struct list_head alts; + struct symbol *func; + struct stack_op stack_op; + struct insn_state state; + struct orc_entry orc; +}; + +struct objtool_file { + struct elf *elf; + struct list_head insn_list; + DECLARE_HASHTABLE(insn_hash, 16); + struct section *rodata, *whitelist; + bool ignore_unreachables, c_file, hints; +}; + +int check(const char *objname, bool no_fp, bool no_unreachable, bool orc); + +struct instruction *find_insn(struct objtool_file *file, + struct section *sec, unsigned long offset); + +#define for_each_insn(file, insn) \ + list_for_each_entry(insn, &file->insn_list, list) + +#define sec_for_each_insn(file, sec, insn) \ + for (insn = find_insn(file, sec, 0); \ + insn && &insn->list != &file->insn_list && \ + insn->sec == sec; \ + insn = list_next_entry(insn, list)) + + +#endif /* _CHECK_H */ diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index d897702ce742..6e9f980a7d26 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -30,13 +30,6 @@ #include "elf.h" #include "warn.h" -/* - * Fallback for systems without this "read, mmaping if possible" cmd. - */ -#ifndef ELF_C_READ_MMAP -#define ELF_C_READ_MMAP ELF_C_READ -#endif - struct section *find_section_by_name(struct elf *elf, const char *name) { struct section *sec; @@ -139,12 +132,12 @@ static int read_sections(struct elf *elf) int i; if (elf_getshdrnum(elf->elf, §ions_nr)) { - perror("elf_getshdrnum"); + WARN_ELF("elf_getshdrnum"); return -1; } if (elf_getshdrstrndx(elf->elf, &shstrndx)) { - perror("elf_getshdrstrndx"); + WARN_ELF("elf_getshdrstrndx"); return -1; } @@ -165,37 +158,36 @@ static int read_sections(struct elf *elf) s = elf_getscn(elf->elf, i); if (!s) { - perror("elf_getscn"); + WARN_ELF("elf_getscn"); return -1; } sec->idx = elf_ndxscn(s); if (!gelf_getshdr(s, &sec->sh)) { - perror("gelf_getshdr"); + WARN_ELF("gelf_getshdr"); return -1; } sec->name = elf_strptr(elf->elf, shstrndx, sec->sh.sh_name); if (!sec->name) { - perror("elf_strptr"); + WARN_ELF("elf_strptr"); return -1; } - sec->elf_data = elf_getdata(s, NULL); - if (!sec->elf_data) { - perror("elf_getdata"); + sec->data = elf_getdata(s, NULL); + if (!sec->data) { + WARN_ELF("elf_getdata"); return -1; } - if (sec->elf_data->d_off != 0 || - sec->elf_data->d_size != sec->sh.sh_size) { + if (sec->data->d_off != 0 || + sec->data->d_size != sec->sh.sh_size) { WARN("unexpected data attributes for %s", sec->name); return -1; } - sec->data = (unsigned long)sec->elf_data->d_buf; - sec->len = sec->elf_data->d_size; + sec->len = sec->data->d_size; } /* sanity check, one more call to elf_nextscn() should return NULL */ @@ -232,15 +224,15 @@ static int read_symbols(struct elf *elf) sym->idx = i; - if (!gelf_getsym(symtab->elf_data, i, &sym->sym)) { - perror("gelf_getsym"); + if (!gelf_getsym(symtab->data, i, &sym->sym)) { + WARN_ELF("gelf_getsym"); goto err; } sym->name = elf_strptr(elf->elf, symtab->sh.sh_link, sym->sym.st_name); if (!sym->name) { - perror("elf_strptr"); + WARN_ELF("elf_strptr"); goto err; } @@ -322,8 +314,8 @@ static int read_relas(struct elf *elf) } memset(rela, 0, sizeof(*rela)); - if (!gelf_getrela(sec->elf_data, i, &rela->rela)) { - perror("gelf_getrela"); + if (!gelf_getrela(sec->data, i, &rela->rela)) { + WARN_ELF("gelf_getrela"); return -1; } @@ -347,9 +339,10 @@ static int read_relas(struct elf *elf) return 0; } -struct elf *elf_open(const char *name) +struct elf *elf_open(const char *name, int flags) { struct elf *elf; + Elf_Cmd cmd; elf_version(EV_CURRENT); @@ -362,26 +355,27 @@ struct elf *elf_open(const char *name) INIT_LIST_HEAD(&elf->sections); - elf->name = strdup(name); - if (!elf->name) { - perror("strdup"); - goto err; - } - - elf->fd = open(name, O_RDONLY); + elf->fd = open(name, flags); if (elf->fd == -1) { perror("open"); goto err; } - elf->elf = elf_begin(elf->fd, ELF_C_READ_MMAP, NULL); + if ((flags & O_ACCMODE) == O_RDONLY) + cmd = ELF_C_READ_MMAP; + else if ((flags & O_ACCMODE) == O_RDWR) + cmd = ELF_C_RDWR; + else /* O_WRONLY */ + cmd = ELF_C_WRITE; + + elf->elf = elf_begin(elf->fd, cmd, NULL); if (!elf->elf) { - perror("elf_begin"); + WARN_ELF("elf_begin"); goto err; } if (!gelf_getehdr(elf->elf, &elf->ehdr)) { - perror("gelf_getehdr"); + WARN_ELF("gelf_getehdr"); goto err; } @@ -401,12 +395,206 @@ err: return NULL; } +struct section *elf_create_section(struct elf *elf, const char *name, + size_t entsize, int nr) +{ + struct section *sec, *shstrtab; + size_t size = entsize * nr; + struct Elf_Scn *s; + Elf_Data *data; + + sec = malloc(sizeof(*sec)); + if (!sec) { + perror("malloc"); + return NULL; + } + memset(sec, 0, sizeof(*sec)); + + INIT_LIST_HEAD(&sec->symbol_list); + INIT_LIST_HEAD(&sec->rela_list); + hash_init(sec->rela_hash); + hash_init(sec->symbol_hash); + + list_add_tail(&sec->list, &elf->sections); + + s = elf_newscn(elf->elf); + if (!s) { + WARN_ELF("elf_newscn"); + return NULL; + } + + sec->name = strdup(name); + if (!sec->name) { + perror("strdup"); + return NULL; + } + + sec->idx = elf_ndxscn(s); + sec->len = size; + sec->changed = true; + + sec->data = elf_newdata(s); + if (!sec->data) { + WARN_ELF("elf_newdata"); + return NULL; + } + + sec->data->d_size = size; + sec->data->d_align = 1; + + if (size) { + sec->data->d_buf = malloc(size); + if (!sec->data->d_buf) { + perror("malloc"); + return NULL; + } + memset(sec->data->d_buf, 0, size); + } + + if (!gelf_getshdr(s, &sec->sh)) { + WARN_ELF("gelf_getshdr"); + return NULL; + } + + sec->sh.sh_size = size; + sec->sh.sh_entsize = entsize; + sec->sh.sh_type = SHT_PROGBITS; + sec->sh.sh_addralign = 1; + sec->sh.sh_flags = SHF_ALLOC; + + + /* Add section name to .shstrtab */ + shstrtab = find_section_by_name(elf, ".shstrtab"); + if (!shstrtab) { + WARN("can't find .shstrtab section"); + return NULL; + } + + s = elf_getscn(elf->elf, shstrtab->idx); + if (!s) { + WARN_ELF("elf_getscn"); + return NULL; + } + + data = elf_newdata(s); + if (!data) { + WARN_ELF("elf_newdata"); + return NULL; + } + + data->d_buf = sec->name; + data->d_size = strlen(name) + 1; + data->d_align = 1; + + sec->sh.sh_name = shstrtab->len; + + shstrtab->len += strlen(name) + 1; + shstrtab->changed = true; + + return sec; +} + +struct section *elf_create_rela_section(struct elf *elf, struct section *base) +{ + char *relaname; + struct section *sec; + + relaname = malloc(strlen(base->name) + strlen(".rela") + 1); + if (!relaname) { + perror("malloc"); + return NULL; + } + strcpy(relaname, ".rela"); + strcat(relaname, base->name); + + sec = elf_create_section(elf, relaname, sizeof(GElf_Rela), 0); + if (!sec) + return NULL; + + base->rela = sec; + sec->base = base; + + sec->sh.sh_type = SHT_RELA; + sec->sh.sh_addralign = 8; + sec->sh.sh_link = find_section_by_name(elf, ".symtab")->idx; + sec->sh.sh_info = base->idx; + sec->sh.sh_flags = SHF_INFO_LINK; + + return sec; +} + +int elf_rebuild_rela_section(struct section *sec) +{ + struct rela *rela; + int nr, idx = 0, size; + GElf_Rela *relas; + + nr = 0; + list_for_each_entry(rela, &sec->rela_list, list) + nr++; + + size = nr * sizeof(*relas); + relas = malloc(size); + if (!relas) { + perror("malloc"); + return -1; + } + + sec->data->d_buf = relas; + sec->data->d_size = size; + + sec->sh.sh_size = size; + + idx = 0; + list_for_each_entry(rela, &sec->rela_list, list) { + relas[idx].r_offset = rela->offset; + relas[idx].r_addend = rela->addend; + relas[idx].r_info = GELF_R_INFO(rela->sym->idx, rela->type); + idx++; + } + + return 0; +} + +int elf_write(struct elf *elf) +{ + struct section *sec; + Elf_Scn *s; + + list_for_each_entry(sec, &elf->sections, list) { + if (sec->changed) { + s = elf_getscn(elf->elf, sec->idx); + if (!s) { + WARN_ELF("elf_getscn"); + return -1; + } + if (!gelf_update_shdr (s, &sec->sh)) { + WARN_ELF("gelf_update_shdr"); + return -1; + } + } + } + + if (elf_update(elf->elf, ELF_C_WRITE) < 0) { + WARN_ELF("elf_update"); + return -1; + } + + return 0; +} + void elf_close(struct elf *elf) { struct section *sec, *tmpsec; struct symbol *sym, *tmpsym; struct rela *rela, *tmprela; + if (elf->elf) + elf_end(elf->elf); + + if (elf->fd > 0) + close(elf->fd); + list_for_each_entry_safe(sec, tmpsec, &elf->sections, list) { list_for_each_entry_safe(sym, tmpsym, &sec->symbol_list, list) { list_del(&sym->list); @@ -421,11 +609,6 @@ void elf_close(struct elf *elf) list_del(&sec->list); free(sec); } - if (elf->name) - free(elf->name); - if (elf->fd > 0) - close(elf->fd); - if (elf->elf) - elf_end(elf->elf); + free(elf); } diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h index 731973e1a3f5..d86e2ff14466 100644 --- a/tools/objtool/elf.h +++ b/tools/objtool/elf.h @@ -28,6 +28,13 @@ # define elf_getshdrstrndx elf_getshstrndx #endif +/* + * Fallback for systems without this "read, mmaping if possible" cmd. + */ +#ifndef ELF_C_READ_MMAP +#define ELF_C_READ_MMAP ELF_C_READ +#endif + struct section { struct list_head list; GElf_Shdr sh; @@ -37,11 +44,11 @@ struct section { DECLARE_HASHTABLE(rela_hash, 16); struct section *base, *rela; struct symbol *sym; - Elf_Data *elf_data; + Elf_Data *data; char *name; int idx; - unsigned long data; unsigned int len; + bool changed, text; }; struct symbol { @@ -76,7 +83,7 @@ struct elf { }; -struct elf *elf_open(const char *name); +struct elf *elf_open(const char *name, int flags); struct section *find_section_by_name(struct elf *elf, const char *name); struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset); struct symbol *find_symbol_containing(struct section *sec, unsigned long offset); @@ -84,8 +91,14 @@ struct rela *find_rela_by_dest(struct section *sec, unsigned long offset); struct rela *find_rela_by_dest_range(struct section *sec, unsigned long offset, unsigned int len); struct symbol *find_containing_func(struct section *sec, unsigned long offset); +struct section *elf_create_section(struct elf *elf, const char *name, size_t + entsize, int nr); +struct section *elf_create_rela_section(struct elf *elf, struct section *base); +int elf_rebuild_rela_section(struct section *sec); +int elf_write(struct elf *elf); void elf_close(struct elf *elf); - +#define for_each_sec(file, sec) \ + list_for_each_entry(sec, &file->elf->sections, list) #endif /* _OBJTOOL_ELF_H */ diff --git a/tools/objtool/objtool.c b/tools/objtool/objtool.c index ecc5b1b5d15d..31e0f9143840 100644 --- a/tools/objtool/objtool.c +++ b/tools/objtool/objtool.c @@ -42,10 +42,11 @@ struct cmd_struct { }; static const char objtool_usage_string[] = - "objtool [OPTIONS] COMMAND [ARGS]"; + "objtool COMMAND [ARGS]"; static struct cmd_struct objtool_cmds[] = { {"check", cmd_check, "Perform stack metadata validation on an object file" }, + {"orc", cmd_orc, "Generate in-place ORC unwind tables for an object file" }, }; bool help; diff --git a/tools/objtool/orc.h b/tools/objtool/orc.h new file mode 100644 index 000000000000..a4139e386ef3 --- /dev/null +++ b/tools/objtool/orc.h @@ -0,0 +1,30 @@ +/* + * Copyright (C) 2017 Josh Poimboeuf <jpoimboe@redhat.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef _ORC_H +#define _ORC_H + +#include "orc_types.h" + +struct objtool_file; + +int create_orc(struct objtool_file *file); +int create_orc_sections(struct objtool_file *file); + +int orc_dump(const char *objname); + +#endif /* _ORC_H */ diff --git a/tools/objtool/orc_dump.c b/tools/objtool/orc_dump.c new file mode 100644 index 000000000000..36c5bf6a2675 --- /dev/null +++ b/tools/objtool/orc_dump.c @@ -0,0 +1,212 @@ +/* + * Copyright (C) 2017 Josh Poimboeuf <jpoimboe@redhat.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#include <unistd.h> +#include "orc.h" +#include "warn.h" + +static const char *reg_name(unsigned int reg) +{ + switch (reg) { + case ORC_REG_PREV_SP: + return "prevsp"; + case ORC_REG_DX: + return "dx"; + case ORC_REG_DI: + return "di"; + case ORC_REG_BP: + return "bp"; + case ORC_REG_SP: + return "sp"; + case ORC_REG_R10: + return "r10"; + case ORC_REG_R13: + return "r13"; + case ORC_REG_BP_INDIRECT: + return "bp(ind)"; + case ORC_REG_SP_INDIRECT: + return "sp(ind)"; + default: + return "?"; + } +} + +static const char *orc_type_name(unsigned int type) +{ + switch (type) { + case ORC_TYPE_CALL: + return "call"; + case ORC_TYPE_REGS: + return "regs"; + case ORC_TYPE_REGS_IRET: + return "iret"; + default: + return "?"; + } +} + +static void print_reg(unsigned int reg, int offset) +{ + if (reg == ORC_REG_BP_INDIRECT) + printf("(bp%+d)", offset); + else if (reg == ORC_REG_SP_INDIRECT) + printf("(sp%+d)", offset); + else if (reg == ORC_REG_UNDEFINED) + printf("(und)"); + else + printf("%s%+d", reg_name(reg), offset); +} + +int orc_dump(const char *_objname) +{ + int fd, nr_entries, i, *orc_ip = NULL, orc_size = 0; + struct orc_entry *orc = NULL; + char *name; + unsigned long nr_sections, orc_ip_addr = 0; + size_t shstrtab_idx; + Elf *elf; + Elf_Scn *scn; + GElf_Shdr sh; + GElf_Rela rela; + GElf_Sym sym; + Elf_Data *data, *symtab = NULL, *rela_orc_ip = NULL; + + + objname = _objname; + + elf_version(EV_CURRENT); + + fd = open(objname, O_RDONLY); + if (fd == -1) { + perror("open"); + return -1; + } + + elf = elf_begin(fd, ELF_C_READ_MMAP, NULL); + if (!elf) { + WARN_ELF("elf_begin"); + return -1; + } + + if (elf_getshdrnum(elf, &nr_sections)) { + WARN_ELF("elf_getshdrnum"); + return -1; + } + + if (elf_getshdrstrndx(elf, &shstrtab_idx)) { + WARN_ELF("elf_getshdrstrndx"); + return -1; + } + + for (i = 0; i < nr_sections; i++) { + scn = elf_getscn(elf, i); + if (!scn) { + WARN_ELF("elf_getscn"); + return -1; + } + + if (!gelf_getshdr(scn, &sh)) { + WARN_ELF("gelf_getshdr"); + return -1; + } + + name = elf_strptr(elf, shstrtab_idx, sh.sh_name); + if (!name) { + WARN_ELF("elf_strptr"); + return -1; + } + + data = elf_getdata(scn, NULL); + if (!data) { + WARN_ELF("elf_getdata"); + return -1; + } + + if (!strcmp(name, ".symtab")) { + symtab = data; + } else if (!strcmp(name, ".orc_unwind")) { + orc = data->d_buf; + orc_size = sh.sh_size; + } else if (!strcmp(name, ".orc_unwind_ip")) { + orc_ip = data->d_buf; + orc_ip_addr = sh.sh_addr; + } else if (!strcmp(name, ".rela.orc_unwind_ip")) { + rela_orc_ip = data; + } + } + + if (!symtab || !orc || !orc_ip) + return 0; + + if (orc_size % sizeof(*orc) != 0) { + WARN("bad .orc_unwind section size"); + return -1; + } + + nr_entries = orc_size / sizeof(*orc); + for (i = 0; i < nr_entries; i++) { + if (rela_orc_ip) { + if (!gelf_getrela(rela_orc_ip, i, &rela)) { + WARN_ELF("gelf_getrela"); + return -1; + } + + if (!gelf_getsym(symtab, GELF_R_SYM(rela.r_info), &sym)) { + WARN_ELF("gelf_getsym"); + return -1; + } + + scn = elf_getscn(elf, sym.st_shndx); + if (!scn) { + WARN_ELF("elf_getscn"); + return -1; + } + + if (!gelf_getshdr(scn, &sh)) { + WARN_ELF("gelf_getshdr"); + return -1; + } + + name = elf_strptr(elf, shstrtab_idx, sh.sh_name); + if (!name || !*name) { + WARN_ELF("elf_strptr"); + return -1; + } + + printf("%s+%lx:", name, rela.r_addend); + + } else { + printf("%lx:", orc_ip_addr + (i * sizeof(int)) + orc_ip[i]); + } + + + printf(" sp:"); + + print_reg(orc[i].sp_reg, orc[i].sp_offset); + + printf(" bp:"); + + print_reg(orc[i].bp_reg, orc[i].bp_offset); + + printf(" type:%s\n", orc_type_name(orc[i].type)); + } + + elf_end(elf); + close(fd); + + return 0; +} diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c new file mode 100644 index 000000000000..e5ca31429c9b --- /dev/null +++ b/tools/objtool/orc_gen.c @@ -0,0 +1,214 @@ +/* + * Copyright (C) 2017 Josh Poimboeuf <jpoimboe@redhat.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#include <stdlib.h> +#include <string.h> + +#include "orc.h" +#include "check.h" +#include "warn.h" + +int create_orc(struct objtool_file *file) +{ + struct instruction *insn; + + for_each_insn(file, insn) { + struct orc_entry *orc = &insn->orc; + struct cfi_reg *cfa = &insn->state.cfa; + struct cfi_reg *bp = &insn->state.regs[CFI_BP]; + + if (cfa->base == CFI_UNDEFINED) { + orc->sp_reg = ORC_REG_UNDEFINED; + continue; + } + + switch (cfa->base) { + case CFI_SP: + orc->sp_reg = ORC_REG_SP; + break; + case CFI_SP_INDIRECT: + orc->sp_reg = ORC_REG_SP_INDIRECT; + break; + case CFI_BP: + orc->sp_reg = ORC_REG_BP; + break; + case CFI_BP_INDIRECT: + orc->sp_reg = ORC_REG_BP_INDIRECT; + break; + case CFI_R10: + orc->sp_reg = ORC_REG_R10; + break; + case CFI_R13: + orc->sp_reg = ORC_REG_R13; + break; + case CFI_DI: + orc->sp_reg = ORC_REG_DI; + break; + case CFI_DX: + orc->sp_reg = ORC_REG_DX; + break; + default: + WARN_FUNC("unknown CFA base reg %d", + insn->sec, insn->offset, cfa->base); + return -1; + } + + switch(bp->base) { + case CFI_UNDEFINED: + orc->bp_reg = ORC_REG_UNDEFINED; + break; + case CFI_CFA: + orc->bp_reg = ORC_REG_PREV_SP; + break; + case CFI_BP: + orc->bp_reg = ORC_REG_BP; + break; + default: + WARN_FUNC("unknown BP base reg %d", + insn->sec, insn->offset, bp->base); + return -1; + } + + orc->sp_offset = cfa->offset; + orc->bp_offset = bp->offset; + orc->type = insn->state.type; + } + + return 0; +} + +static int create_orc_entry(struct section *u_sec, struct section *ip_relasec, + unsigned int idx, struct section *insn_sec, + unsigned long insn_off, struct orc_entry *o) +{ + struct orc_entry *orc; + struct rela *rela; + + /* populate ORC data */ + orc = (struct orc_entry *)u_sec->data->d_buf + idx; + memcpy(orc, o, sizeof(*orc)); + + /* populate rela for ip */ + rela = malloc(sizeof(*rela)); + if (!rela) { + perror("malloc"); + return -1; + } + memset(rela, 0, sizeof(*rela)); + + rela->sym = insn_sec->sym; + rela->addend = insn_off; + rela->type = R_X86_64_PC32; + rela->offset = idx * sizeof(int); + + list_add_tail(&rela->list, &ip_relasec->rela_list); + hash_add(ip_relasec->rela_hash, &rela->hash, rela->offset); + + return 0; +} + +int create_orc_sections(struct objtool_file *file) +{ + struct instruction *insn, *prev_insn; + struct section *sec, *u_sec, *ip_relasec; + unsigned int idx; + + struct orc_entry empty = { + .sp_reg = ORC_REG_UNDEFINED, + .bp_reg = ORC_REG_UNDEFINED, + .type = ORC_TYPE_CALL, + }; + + sec = find_section_by_name(file->elf, ".orc_unwind"); + if (sec) { + WARN("file already has .orc_unwind section, skipping"); + return -1; + } + + /* count the number of needed orcs */ + idx = 0; + for_each_sec(file, sec) { + if (!sec->text) + continue; + + prev_insn = NULL; + sec_for_each_insn(file, sec, insn) { + if (!prev_insn || + memcmp(&insn->orc, &prev_insn->orc, + sizeof(struct orc_entry))) { + idx++; + } + prev_insn = insn; + } + + /* section terminator */ + if (prev_insn) + idx++; + } + if (!idx) + return -1; + + + /* create .orc_unwind_ip and .rela.orc_unwind_ip sections */ + sec = elf_create_section(file->elf, ".orc_unwind_ip", sizeof(int), idx); + + ip_relasec = elf_create_rela_section(file->elf, sec); + if (!ip_relasec) + return -1; + + /* create .orc_unwind section */ + u_sec = elf_create_section(file->elf, ".orc_unwind", + sizeof(struct orc_entry), idx); + + /* populate sections */ + idx = 0; + for_each_sec(file, sec) { + if (!sec->text) + continue; + + prev_insn = NULL; + sec_for_each_insn(file, sec, insn) { + if (!prev_insn || memcmp(&insn->orc, &prev_insn->orc, + sizeof(struct orc_entry))) { + + if (create_orc_entry(u_sec, ip_relasec, idx, + insn->sec, insn->offset, + &insn->orc)) + return -1; + + idx++; + } + prev_insn = insn; + } + + /* section terminator */ + if (prev_insn) { + if (create_orc_entry(u_sec, ip_relasec, idx, + prev_insn->sec, + prev_insn->offset + prev_insn->len, + &empty)) + return -1; + + idx++; + } + } + + if (elf_rebuild_rela_section(ip_relasec)) + return -1; + + return 0; +} diff --git a/tools/objtool/orc_types.h b/tools/objtool/orc_types.h new file mode 100644 index 000000000000..9c9dc579bd7d --- /dev/null +++ b/tools/objtool/orc_types.h @@ -0,0 +1,107 @@ +/* + * Copyright (C) 2017 Josh Poimboeuf <jpoimboe@redhat.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef _ORC_TYPES_H +#define _ORC_TYPES_H + +#include <linux/types.h> +#include <linux/compiler.h> + +/* + * The ORC_REG_* registers are base registers which are used to find other + * registers on the stack. + * + * ORC_REG_PREV_SP, also known as DWARF Call Frame Address (CFA), is the + * address of the previous frame: the caller's SP before it called the current + * function. + * + * ORC_REG_UNDEFINED means the corresponding register's value didn't change in + * the current frame. + * + * The most commonly used base registers are SP and BP -- which the previous SP + * is usually based on -- and PREV_SP and UNDEFINED -- which the previous BP is + * usually based on. + * + * The rest of the base registers are needed for special cases like entry code + * and GCC realigned stacks. + */ +#define ORC_REG_UNDEFINED 0 +#define ORC_REG_PREV_SP 1 +#define ORC_REG_DX 2 +#define ORC_REG_DI 3 +#define ORC_REG_BP 4 +#define ORC_REG_SP 5 +#define ORC_REG_R10 6 +#define ORC_REG_R13 7 +#define ORC_REG_BP_INDIRECT 8 +#define ORC_REG_SP_INDIRECT 9 +#define ORC_REG_MAX 15 + +/* + * ORC_TYPE_CALL: Indicates that sp_reg+sp_offset resolves to PREV_SP (the + * caller's SP right before it made the call). Used for all callable + * functions, i.e. all C code and all callable asm functions. + * + * ORC_TYPE_REGS: Used in entry code to indicate that sp_reg+sp_offset points + * to a fully populated pt_regs from a syscall, interrupt, or exception. + * + * ORC_TYPE_REGS_IRET: Used in entry code to indicate that sp_reg+sp_offset + * points to the iret return frame. + * + * The UNWIND_HINT macros are used only for the unwind_hint struct. They + * aren't used in struct orc_entry due to size and complexity constraints. + * Objtool converts them to real types when it converts the hints to orc + * entries. + */ +#define ORC_TYPE_CALL 0 +#define ORC_TYPE_REGS 1 +#define ORC_TYPE_REGS_IRET 2 +#define UNWIND_HINT_TYPE_SAVE 3 +#define UNWIND_HINT_TYPE_RESTORE 4 + +#ifndef __ASSEMBLY__ +/* + * This struct is more or less a vastly simplified version of the DWARF Call + * Frame Information standard. It contains only the necessary parts of DWARF + * CFI, simplified for ease of access by the in-kernel unwinder. It tells the + * unwinder how to find the previous SP and BP (and sometimes entry regs) on + * the stack for a given code address. Each instance of the struct corresponds + * to one or more code locations. + */ +struct orc_entry { + s16 sp_offset; + s16 bp_offset; + unsigned sp_reg:4; + unsigned bp_reg:4; + unsigned type:2; +} __packed; + +/* + * This struct is used by asm and inline asm code to manually annotate the + * location of registers on the stack for the ORC unwinder. + * + * Type can be either ORC_TYPE_* or UNWIND_HINT_TYPE_*. + */ +struct unwind_hint { + u32 ip; + s16 sp_offset; + u8 sp_reg; + u8 type; +}; +#endif /* __ASSEMBLY__ */ + +#endif /* _ORC_TYPES_H */ diff --git a/tools/objtool/special.c b/tools/objtool/special.c index bff8abb3a4aa..84f001d52322 100644 --- a/tools/objtool/special.c +++ b/tools/objtool/special.c @@ -91,16 +91,16 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry, alt->jump_or_nop = entry->jump_or_nop; if (alt->group) { - alt->orig_len = *(unsigned char *)(sec->data + offset + + alt->orig_len = *(unsigned char *)(sec->data->d_buf + offset + entry->orig_len); - alt->new_len = *(unsigned char *)(sec->data + offset + + alt->new_len = *(unsigned char *)(sec->data->d_buf + offset + entry->new_len); } if (entry->feature) { unsigned short feature; - feature = *(unsigned short *)(sec->data + offset + + feature = *(unsigned short *)(sec->data->d_buf + offset + entry->feature); /* diff --git a/tools/objtool/warn.h b/tools/objtool/warn.h index ac7e07523e84..afd9f7a05f6d 100644 --- a/tools/objtool/warn.h +++ b/tools/objtool/warn.h @@ -18,6 +18,13 @@ #ifndef _WARN_H #define _WARN_H +#include <stdlib.h> +#include <string.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include "elf.h" + extern const char *objname; static inline char *offstr(struct section *sec, unsigned long offset) @@ -57,4 +64,7 @@ static inline char *offstr(struct section *sec, unsigned long offset) free(_str); \ }) +#define WARN_ELF(format, ...) \ + WARN(format ": %s", ##__VA_ARGS__, elf_errmsg(-1)) + #endif /* _WARN_H */ diff --git a/tools/pci/pcitest.c b/tools/pci/pcitest.c index ad54a58d7dda..9074b477bff0 100644 --- a/tools/pci/pcitest.c +++ b/tools/pci/pcitest.c @@ -173,6 +173,7 @@ usage: "\t-D <dev> PCI endpoint test device {default: /dev/pci-endpoint-test.0}\n" "\t-b <bar num> BAR test (bar number between 0..5)\n" "\t-m <msi num> MSI test (msi number between 1..32)\n" + "\t-l Legacy IRQ test\n" "\t-r Read buffer test\n" "\t-w Write buffer test\n" "\t-c Copy buffer test\n" diff --git a/tools/perf/Build b/tools/perf/Build index bd8eeb60533c..b48ca40fccf9 100644 --- a/tools/perf/Build +++ b/tools/perf/Build @@ -50,6 +50,6 @@ libperf-y += util/ libperf-y += arch/ libperf-y += ui/ libperf-y += scripts/ -libperf-y += trace/beauty/ +libperf-$(CONFIG_AUDIT) += trace/beauty/ gtk-y += ui/gtk/ diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile index 098cfb9ca8f0..db11478e30b4 100644 --- a/tools/perf/Documentation/Makefile +++ b/tools/perf/Documentation/Makefile @@ -192,7 +192,7 @@ do-install-man: man # $(INSTALL) -m 644 $(DOC_MAN5) $(DESTDIR)$(man5dir); \ # $(INSTALL) -m 644 $(DOC_MAN7) $(DESTDIR)$(man7dir) -install-man: check-man-tools man +install-man: check-man-tools man do-install-man ifdef missing_tools DO_INSTALL_MAN = $(warning Please install $(missing_tools) to have the man pages installed) diff --git a/tools/perf/Documentation/intel-pt.txt b/tools/perf/Documentation/intel-pt.txt index b0b3007d3c9c..76971d2e4164 100644 --- a/tools/perf/Documentation/intel-pt.txt +++ b/tools/perf/Documentation/intel-pt.txt @@ -104,9 +104,12 @@ system, asynchronous, interrupt, transaction abort, trace begin, trace end, and in transaction, respectively. While it is possible to create scripts to analyze the data, an alternative -approach is available to export the data to a postgresql database. Refer to -script export-to-postgresql.py for more details, and to script -call-graph-from-postgresql.py for an example of using the database. +approach is available to export the data to a sqlite or postgresql database. +Refer to script export-to-sqlite.py or export-to-postgresql.py for more details, +and to script call-graph-from-sql.py for an example of using the database. + +There is also script intel-pt-events.py which provides an example of how to +unpack the raw data for power events and PTWRITE. As mentioned above, it is easy to capture too much data. One way to limit the data captured is to use 'snapshot' mode which is explained further below. @@ -364,6 +367,42 @@ cyc_thresh Specifies how frequently CYC packets are produced - see cyc CYC packets are not requested by default. +pt Specifies pass-through which enables the 'branch' config term. + + The default config selects 'pt' if it is available, so a user will + never need to specify this term. + +branch Enable branch tracing. Branch tracing is enabled by default so to + disable branch tracing use 'branch=0'. + + The default config selects 'branch' if it is available. + +ptw Enable PTWRITE packets which are produced when a ptwrite instruction + is executed. + + Support for this feature is indicated by: + + /sys/bus/event_source/devices/intel_pt/caps/ptwrite + + which contains "1" if the feature is supported and + "0" otherwise. + +fup_on_ptw Enable a FUP packet to follow the PTWRITE packet. The FUP packet + provides the address of the ptwrite instruction. In the absence of + fup_on_ptw, the decoder will use the address of the previous branch + if branch tracing is enabled, otherwise the address will be zero. + Note that fup_on_ptw will work even when branch tracing is disabled. + +pwr_evt Enable power events. The power events provide information about + changes to the CPU C-state. + + Support for this feature is indicated by: + + /sys/bus/event_source/devices/intel_pt/caps/power_event_trace + + which contains "1" if the feature is supported and + "0" otherwise. + new snapshot option ------------------- @@ -674,13 +713,15 @@ Having no option is the same as which, in turn, is the same as - --itrace=ibxe + --itrace=ibxwpe The letters are: i synthesize "instructions" events b synthesize "branches" events x synthesize "transactions" events + w synthesize "ptwrite" events + p synthesize "power" events c synthesize branches events (calls only) r synthesize branches events (returns only) e synthesize tracing error events @@ -699,7 +740,40 @@ and "r" can be combined to get calls and returns. 'flags' field can be used in perf script to determine whether the event is a tranasaction start, commit or abort. -Error events are new. They show where the decoder lost the trace. Error events +Note that "instructions", "branches" and "transactions" events depend on code +flow packets which can be disabled by using the config term "branch=0". Refer +to the config terms section above. + +"ptwrite" events record the payload of the ptwrite instruction and whether +"fup_on_ptw" was used. "ptwrite" events depend on PTWRITE packets which are +recorded only if the "ptw" config term was used. Refer to the config terms +section above. perf script "synth" field displays "ptwrite" information like +this: "ip: 0 payload: 0x123456789abcdef0" where "ip" is 1 if "fup_on_ptw" was +used. + +"Power" events correspond to power event packets and CBR (core-to-bus ratio) +packets. While CBR packets are always recorded when tracing is enabled, power +event packets are recorded only if the "pwr_evt" config term was used. Refer to +the config terms section above. The power events record information about +C-state changes, whereas CBR is indicative of CPU frequency. perf script +"event,synth" fields display information like this: + cbr: cbr: 22 freq: 2189 MHz (200%) + mwait: hints: 0x60 extensions: 0x1 + pwre: hw: 0 cstate: 2 sub-cstate: 0 + exstop: ip: 1 + pwrx: deepest cstate: 2 last cstate: 2 wake reason: 0x4 +Where: + "cbr" includes the frequency and the percentage of maximum non-turbo + "mwait" shows mwait hints and extensions + "pwre" shows C-state transitions (to a C-state deeper than C0) and + whether initiated by hardware + "exstop" indicates execution stopped and whether the IP was recorded + exactly, + "pwrx" indicates return to C0 +For more details refer to the Intel 64 and IA-32 Architectures Software +Developer Manuals. + +Error events show where the decoder lost the trace. Error events are quite important. Users must know if what they are seeing is a complete picture or not. @@ -799,7 +873,7 @@ amended to take the number of elements as a parameter. $ cat ~/.perfconfig [intel-pt] - mispred-all + mispred-all = on $ perf record -e intel_pt//u ./sort 3000 Bubble sorting array of 3000 elements diff --git a/tools/perf/Documentation/itrace.txt b/tools/perf/Documentation/itrace.txt index e2a4c5e0dbe5..a3abe04c779d 100644 --- a/tools/perf/Documentation/itrace.txt +++ b/tools/perf/Documentation/itrace.txt @@ -3,13 +3,15 @@ c synthesize branches events (calls only) r synthesize branches events (returns only) x synthesize transactions events + w synthesize ptwrite events + p synthesize power events e synthesize error events d create a debug log g synthesize a call chain (use with i or x) l synthesize last branch entries (use with i or x) s skip initial number of events - The default is all events i.e. the same as --itrace=ibxe + The default is all events i.e. the same as --itrace=ibxwpe In addition, the period (default 100000) for instructions events can be specified in units of: @@ -26,8 +28,8 @@ Also the number of last branch entries (default 64, max. 1024) for instructions or transactions events can be specified. - It is also possible to skip events generated (instructions, branches, transactions) - at the beginning. This is useful to ignore initialization code. + It is also possible to skip events generated (instructions, branches, transactions, + ptwrite, power) at the beginning. This is useful to ignore initialization code. --itrace=i0nss1000000 diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt index a89273d8e744..c635eab6af54 100644 --- a/tools/perf/Documentation/perf-annotate.txt +++ b/tools/perf/Documentation/perf-annotate.txt @@ -43,6 +43,10 @@ OPTIONS --quiet:: Do not show any message. (Suppress -v) +-n:: +--show-nr-samples:: + Show the number of samples for each symbol + -D:: --dump-raw-trace:: Dump raw trace in ASCII. @@ -88,6 +92,8 @@ OPTIONS --asm-raw:: Show raw instruction encoding of assembly instructions. +--show-total-period:: Show a column with the sum of periods. + --source:: Interleave source code with assembly code. Enabled by default, disable with --no-source. diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt index 058064db39d2..84681007f80f 100644 --- a/tools/perf/Documentation/perf-buildid-cache.txt +++ b/tools/perf/Documentation/perf-buildid-cache.txt @@ -61,6 +61,11 @@ OPTIONS --verbose:: Be more verbose. +--target-ns=PID: + Obtain mount namespace information from the target pid. This is + used when creating a uprobe for a process that resides in a + different mount namespace from the perf(1) utility. + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-buildid-list[1] diff --git a/tools/perf/Documentation/perf-ftrace.txt b/tools/perf/Documentation/perf-ftrace.txt index 6e6a8b22c859..721a447f046e 100644 --- a/tools/perf/Documentation/perf-ftrace.txt +++ b/tools/perf/Documentation/perf-ftrace.txt @@ -48,6 +48,39 @@ OPTIONS Ranges of CPUs are specified with -: 0-2. Default is to trace on all online CPUs. +-T:: +--trace-funcs=:: + Only trace functions given by the argument. Multiple functions + can be given by using this option more than once. The function + argument also can be a glob pattern. It will be passed to + 'set_ftrace_filter' in tracefs. + +-N:: +--notrace-funcs=:: + Do not trace functions given by the argument. Like -T option, + this can be used more than once to specify multiple functions + (or glob patterns). It will be passed to 'set_ftrace_notrace' + in tracefs. + +-G:: +--graph-funcs=:: + Set graph filter on the given function (or a glob pattern). + This is useful for the function_graph tracer only and enables + tracing for functions executed from the given function. + This can be used more than once to specify multiple functions. + It will be passed to 'set_graph_function' in tracefs. + +-g:: +--nograph-funcs=:: + Set graph notrace filter on the given function (or a glob pattern). + Like -G option, this is useful for the function_graph tracer only + and disables tracing for function executed from the given function. + This can be used more than once to specify multiple functions. + It will be passed to 'set_graph_notrace' in tracefs. + +-D:: +--graph-depth=:: + Set max depth for function graph tracer to follow SEE ALSO -------- diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt index 73496320fca3..4be08a1e3f8d 100644 --- a/tools/perf/Documentation/perf-mem.txt +++ b/tools/perf/Documentation/perf-mem.txt @@ -59,6 +59,10 @@ OPTIONS --ldload:: Specify desired latency for loads event. +-p:: +--phys-data:: + Record/Report sample physical addresses + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-report[1] diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt index 165c2b1d4317..d7e4869905f1 100644 --- a/tools/perf/Documentation/perf-probe.txt +++ b/tools/perf/Documentation/perf-probe.txt @@ -130,6 +130,11 @@ OPTIONS --max-probes=NUM:: Set the maximum number of probe points for an event. Default is 128. +--target-ns=PID: + Obtain mount namespace information from the target pid. This is + used when creating a uprobe for a process that resides in a + different mount namespace from the perf(1) utility. + -x:: --exec=PATH:: Specify path to the executable or shared library file for user @@ -264,6 +269,15 @@ Add probes at malloc() function on libc ./perf probe -x /lib/libc.so.6 malloc or ./perf probe /lib/libc.so.6 malloc +Add a uprobe to a target process running in a different mount namespace + + ./perf probe --target-ns <target pid> -x /lib64/libc.so.6 malloc + +Add a USDT probe to a target process running in a different mount namespace + + ./perf probe --target-ns <target pid> -x /usr/lib/jvm/java-1.8.0-openjdk-1.8.0.121-0.b13.el7_3.x86_64/jre/lib/amd64/server/libjvm.so %sdt_hotspot:thread__sleep__end + + SEE ALSO -------- linkperf:perf-trace[1], linkperf:perf-record[1], linkperf:perf-buildid-cache[1] diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index b0e9e921d534..e397453e5a46 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -249,7 +249,10 @@ OPTIONS -d:: --data:: - Record the sample addresses. + Record the sample virtual addresses. + +--phys-data:: + Record the sample physical addresses. -T:: --timestamp:: @@ -332,6 +335,7 @@ following filters are defined: - no_tx: only when the target is not in a hardware transaction - abort_tx: only when the target is a hardware transaction abort - cond: conditional branches + - save_type: save branch type during sampling in case binary is not available later + The option requires at least one branch type among any, any_call, any_ret, ind_call, cond. diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 9fa84617181e..383a98d992ed 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -137,6 +137,7 @@ OPTIONS - mem: type of memory access for the data at the time of the sample - snoop: type of snoop (if any) for the data at the time of the sample - dcacheline: the cacheline the data address is on at the time of the sample + - phys_daddr: physical address of data being executed on at the time of sample And the default sort keys are changed to local_weight, mem, sym, dso, symbol_daddr, dso_daddr, snoop, tlb, locked, see '--mem-mode'. diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index 3517e204a2b3..18dfcfa38454 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -116,8 +116,9 @@ OPTIONS --fields:: Comma separated list of fields to print. Options are: comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff, - srcline, period, iregs, brstack, brstacksym, flags, bpf-output, brstackinsn, - callindent, insn, insnlen. Field list can be prepended with the type, trace, sw or hw, + srcline, period, iregs, brstack, brstacksym, flags, bpf-output, brstackinsn, brstackoff, + callindent, insn, insnlen, synth, phys_addr. + Field list can be prepended with the type, trace, sw or hw, to indicate to which event type the field list applies. e.g., -F sw:comm,tid,time,ip,sym and -F trace:time,cpu,trace @@ -130,6 +131,14 @@ OPTIONS i.e., the specified fields apply to all event types if the type string is not given. + In addition to overriding fields, it is also possible to add or remove + fields from the defaults. For example + + -F -cpu,+insn + + removes the cpu field and adds the insn field. Adding/removing fields + cannot be mixed with normal overriding. + The arguments are processed in the order received. A later usage can reset a prior request. e.g.: @@ -185,6 +194,9 @@ OPTIONS instruction bytes and the instruction length of the current instruction. + The synth field is used by synthesized events which may be created when + Instruction Trace decoding. + Finally, a user may not set fields to none for all event types. i.e., -F "" is not allowed. @@ -203,6 +215,8 @@ OPTIONS is printed. This is the full execution path leading to the sample. This is only supported when the sample was recorded with perf record -b or -j any. + The brstackoff field will print an offset into a specific dso/binary. + -k:: --vmlinux=<file>:: vmlinux pathname diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index bd0e4417f2be..c37d61682dfb 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -41,13 +41,13 @@ report:: - a symbolically formed event like 'pmu/param1=0x3,param2/' where param1 and param2 are defined as formats for the PMU in - /sys/bus/event_sources/devices/<pmu>/format/* + /sys/bus/event_source/devices/<pmu>/format/* - a symbolically formed event like 'pmu/config=M,config1=N,config2=K/' where M, N, K are numbers (in decimal, hex, octal format). Acceptable values for each of 'config', 'config1' and 'config2' parameters are defined by corresponding entries in - /sys/bus/event_sources/devices/<pmu>/format/* + /sys/bus/event_source/devices/<pmu>/format/* -i:: --no-inherit:: @@ -239,6 +239,20 @@ taskset. --no-merge:: Do not merge results from same PMUs. +--smi-cost:: +Measure SMI cost if msr/aperf/ and msr/smi/ events are supported. + +During the measurement, the /sys/device/cpu/freeze_on_smi will be set to +freeze core counters on SMI. +The aperf counter will not be effected by the setting. +The cost of SMI can be measured by (aperf - unhalted core cycles). + +In practice, the percentages of SMI cycles is very useful for performance +oriented analysis. --metric_only will be applied by default. +The output is SMI cycles%, equals to (aperf - unhalted core cycles) / aperf + +Users who wants to get the actual value can apply --no-metric-only. + EXAMPLES -------- diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt index e71d63843f45..d864ea6fd367 100644 --- a/tools/perf/Documentation/perf-top.txt +++ b/tools/perf/Documentation/perf-top.txt @@ -237,6 +237,10 @@ Default is to monitor all CPUS. --hierarchy:: Enable hierarchy output. +--force:: + Don't do ownership validation. + + INTERACTIVE PROMPTING KEYS -------------------------- diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt index c1e3288a2dfb..d53bea6bd571 100644 --- a/tools/perf/Documentation/perf-trace.txt +++ b/tools/perf/Documentation/perf-trace.txt @@ -37,7 +37,7 @@ OPTIONS --expr:: --event:: List of syscalls and other perf events (tracepoints, HW cache events, - etc) to show. + etc) to show. Globbing is supported, e.g.: "epoll_*", "*msg*", etc. See 'perf list' for a complete list of events. Prefixing with ! shows all syscalls but the ones specified. You may need to escape it. diff --git a/tools/perf/Documentation/perf.data-file-format.txt b/tools/perf/Documentation/perf.data-file-format.txt index de8b39dda7b8..e90c59c6d815 100644 --- a/tools/perf/Documentation/perf.data-file-format.txt +++ b/tools/perf/Documentation/perf.data-file-format.txt @@ -398,6 +398,11 @@ struct auxtrace_error_event { char msg[MAX_AUXTRACE_ERROR_MSG]; }; + PERF_RECORD_HEADER_FEATURE = 80, + +Describes a header feature. These are records used in pipe-mode that +contain information that otherwise would be in perf.data file's header. + Event types Define the event attributes with their IDs. @@ -422,8 +427,9 @@ struct perf_pipe_file_header { }; The information about attrs, data, and event_types is instead in the -synthesized events PERF_RECORD_ATTR, PERF_RECORD_HEADER_TRACING_DATA and -PERF_RECORD_HEADER_EVENT_TYPE that are generated by perf record in pipe-mode. +synthesized events PERF_RECORD_ATTR, PERF_RECORD_HEADER_TRACING_DATA, +PERF_RECORD_HEADER_EVENT_TYPE, and PERF_RECORD_HEADER_FEATURE +that are generated by perf record in pipe-mode. References: diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index a29da46d180f..62072822dc85 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -70,15 +70,23 @@ tools/include/linux/hash.h tools/include/linux/kernel.h tools/include/linux/list.h tools/include/linux/log2.h +tools/include/uapi/asm-generic/fcntl.h +tools/include/uapi/asm-generic/ioctls.h tools/include/uapi/asm-generic/mman-common.h tools/include/uapi/asm-generic/mman.h +tools/include/uapi/drm/drm.h +tools/include/uapi/drm/i915_drm.h tools/include/uapi/linux/bpf.h tools/include/uapi/linux/bpf_common.h tools/include/uapi/linux/fcntl.h tools/include/uapi/linux/hw_breakpoint.h +tools/include/uapi/linux/kvm.h tools/include/uapi/linux/mman.h tools/include/uapi/linux/perf_event.h +tools/include/uapi/linux/sched.h tools/include/uapi/linux/stat.h +tools/include/uapi/linux/vhost.h +tools/include/uapi/sound/asound.h tools/include/linux/poison.h tools/include/linux/rbtree.h tools/include/linux/rbtree_augmented.h diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 1f4fbc9a3292..63f534a0902f 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -35,7 +35,7 @@ ifeq ($(SRCARCH),x86) ifeq (${IS_64_BIT}, 1) CFLAGS += -DHAVE_ARCH_X86_64_SUPPORT -DHAVE_SYSCALL_TABLE -I$(OUTPUT)arch/x86/include/generated ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S - LIBUNWIND_LIBS = -lunwind -lunwind-x86_64 + LIBUNWIND_LIBS = -lunwind-x86_64 -lunwind -llzma $(call detected,CONFIG_X86_64) else LIBUNWIND_LIBS = -lunwind-x86 -llzma -lunwind @@ -61,7 +61,7 @@ endif # Disable it on all other architectures in case libdw unwind # support is detected in system. Add supported architectures # to the check. -ifneq ($(SRCARCH),$(filter $(SRCARCH),x86 arm)) +ifneq ($(SRCARCH),$(filter $(SRCARCH),x86 arm powerpc)) NO_LIBDW_DWARF_UNWIND := 1 endif @@ -103,8 +103,12 @@ ifdef LIBDW_DIR LIBDW_CFLAGS := -I$(LIBDW_DIR)/include LIBDW_LDFLAGS := -L$(LIBDW_DIR)/lib endif +DWARFLIBS := -ldw +ifeq ($(findstring -static,${LDFLAGS}),-static) + DWARFLIBS += -lelf -lebl -ldl -lz -llzma -lbz2 +endif FEATURE_CHECK_CFLAGS-libdw-dwarf-unwind := $(LIBDW_CFLAGS) -FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind := $(LIBDW_LDFLAGS) -ldw +FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind := $(LIBDW_LDFLAGS) $(DWARFLIBS) # for linking with debug library, run like: # make DEBUG=1 LIBBABELTRACE_DIR=/opt/libbabeltrace/ @@ -144,7 +148,7 @@ ifndef DEBUG endif ifeq ($(DEBUG),0) -ifeq ($(CC), clang) +ifeq ($(CC_NO_CLANG), 0) CFLAGS += -O3 else CFLAGS += -O6 @@ -180,7 +184,7 @@ ifdef PYTHON_CONFIG PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS)) PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null) - ifeq ($(CC), clang) + ifeq ($(CC_NO_CLANG), 1) PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS)) endif FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS) @@ -330,6 +334,11 @@ ifeq ($(feature-sched_getcpu), 1) CFLAGS += -DHAVE_SCHED_GETCPU_SUPPORT endif +ifeq ($(feature-setns), 1) + CFLAGS += -DHAVE_SETNS_SUPPORT + $(call detected,CONFIG_SETNS) +endif + ifndef NO_LIBELF CFLAGS += -DHAVE_LIBELF_SUPPORT EXTLIBS += -lelf @@ -360,10 +369,6 @@ ifndef NO_LIBELF else CFLAGS += -DHAVE_DWARF_SUPPORT $(LIBDW_CFLAGS) LDFLAGS += $(LIBDW_LDFLAGS) - DWARFLIBS := -ldw - ifeq ($(findstring -static,${LDFLAGS}),-static) - DWARFLIBS += -lelf -lebl -lz -llzma -lbz2 - endif EXTLIBS += ${DWARFLIBS} $(call detected,CONFIG_DWARF) endif # PERF_HAVE_DWARF_REGS @@ -500,6 +505,10 @@ ifndef NO_LOCAL_LIBUNWIND EXTLIBS += $(LIBUNWIND_LIBS) LDFLAGS += $(LIBUNWIND_LIBS) endif +ifeq ($(findstring -static,${LDFLAGS}),-static) + # gcc -static links libgcc_eh which contans piece of libunwind + LIBUNWIND_LDFLAGS += -Wl,--allow-multiple-definition +endif ifndef NO_LIBUNWIND CFLAGS += -DHAVE_LIBUNWIND_SUPPORT diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 5008f51a08a2..91ef44bfaf3e 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -33,6 +33,11 @@ include ../scripts/utilities.mak # # Define EXTRA_CFLAGS=-m64 or EXTRA_CFLAGS=-m32 as appropriate for cross-builds. # +# Define EXCLUDE_EXTLIBS=-lmylib to exclude libmylib from the auto-generated +# EXTLIBS. +# +# Define EXTRA_PERFLIBS to pass extra libraries to PERFLIBS. +# # Define NO_DWARF if you do not want debug-info analysis feature at all. # # Define WERROR=0 to disable treating any warnings as errors. @@ -159,8 +164,8 @@ LN = ln -f MKDIR = mkdir FIND = find INSTALL = install -FLEX = flex -BISON = bison +FLEX ?= flex +BISON ?= bison STRIP = strip AWK = awk @@ -235,7 +240,7 @@ endif ifeq ($(FEATURES_DUMP),) FEATURE_DUMP_EXPORT := $(realpath $(OUTPUT)FEATURE-DUMP) else -FEATURE_DUMP_EXPORT := $(FEATURES_DUMP) +FEATURE_DUMP_EXPORT := $(realpath $(FEATURES_DUMP)) endif export prefix bindir sharedir sysconfdir DESTDIR @@ -274,7 +279,13 @@ LIBTRACEEVENT = $(TE_PATH)libtraceevent.a export LIBTRACEEVENT LIBTRACEEVENT_DYNAMIC_LIST = $(TE_PATH)libtraceevent-dynamic-list -LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS = -Xlinker --dynamic-list=$(LIBTRACEEVENT_DYNAMIC_LIST) + +# +# The static build has no dynsym table, so this does not work for +# static build. Looks like linker starts to scream about that now +# (in Fedora 26) so we need to switch it off for static build. +DYNAMIC_LIST_LDFLAGS = -Xlinker --dynamic-list=$(LIBTRACEEVENT_DYNAMIC_LIST) +LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS = $(if $(findstring -static,$(LDFLAGS)),,$(DYNAMIC_LIST_LDFLAGS)) LIBAPI = $(API_PATH)libapi.a export LIBAPI @@ -352,7 +363,8 @@ ifdef ASCIIDOC8 export ASCIIDOC8 endif -LIBS = -Wl,--whole-archive $(PERFLIBS) -Wl,--no-whole-archive -Wl,--start-group $(EXTLIBS) -Wl,--end-group +EXTLIBS := $(call filter-out,$(EXCLUDE_EXTLIBS),$(EXTLIBS)) +LIBS = -Wl,--whole-archive $(PERFLIBS) $(EXTRA_PERFLIBS) -Wl,--no-whole-archive -Wl,--start-group $(EXTLIBS) -Wl,--end-group ifeq ($(USE_CLANG), 1) CLANGLIBS_LIST = AST Basic CodeGen Driver Frontend Lex Tooling Edit Sema Analysis Parse Serialization @@ -375,6 +387,60 @@ export INSTALL SHELL_PATH SHELL = $(SHELL_PATH) +beauty_outdir := $(OUTPUT)trace/beauty/generated +beauty_ioctl_outdir := $(beauty_outdir)/ioctl +drm_ioctl_array := $(beauty_ioctl_outdir)/drm_ioctl_array.c +drm_hdr_dir := $(srctree)/tools/include/uapi/drm +drm_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/drm_ioctl.sh + +# Create output directory if not already present +_dummy := $(shell [ -d '$(beauty_ioctl_outdir)' ] || mkdir -p '$(beauty_ioctl_outdir)') + +$(drm_ioctl_array): $(drm_hdr_dir)/drm.h $(drm_hdr_dir)/i915_drm.h $(drm_ioctl_tbl) + $(Q)$(SHELL) '$(drm_ioctl_tbl)' $(drm_hdr_dir) > $@ + +pkey_alloc_access_rights_array := $(beauty_outdir)/pkey_alloc_access_rights_array.c +asm_generic_hdr_dir := $(srctree)/tools/include/uapi/asm-generic/ +pkey_alloc_access_rights_tbl := $(srctree)/tools/perf/trace/beauty/pkey_alloc_access_rights.sh + +$(pkey_alloc_access_rights_array): $(asm_generic_hdr_dir)/mman-common.h $(pkey_alloc_access_rights_tbl) + $(Q)$(SHELL) '$(pkey_alloc_access_rights_tbl)' $(asm_generic_hdr_dir) > $@ + +sndrv_ctl_ioctl_array := $(beauty_ioctl_outdir)/sndrv_ctl_ioctl_array.c +sndrv_ctl_hdr_dir := $(srctree)/tools/include/uapi/sound +sndrv_ctl_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh + +$(sndrv_ctl_ioctl_array): $(sndrv_ctl_hdr_dir)/asound.h $(sndrv_ctl_ioctl_tbl) + $(Q)$(SHELL) '$(sndrv_ctl_ioctl_tbl)' $(sndrv_ctl_hdr_dir) > $@ + +sndrv_pcm_ioctl_array := $(beauty_ioctl_outdir)/sndrv_pcm_ioctl_array.c +sndrv_pcm_hdr_dir := $(srctree)/tools/include/uapi/sound +sndrv_pcm_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh + +$(sndrv_pcm_ioctl_array): $(sndrv_pcm_hdr_dir)/asound.h $(sndrv_pcm_ioctl_tbl) + $(Q)$(SHELL) '$(sndrv_pcm_ioctl_tbl)' $(sndrv_pcm_hdr_dir) > $@ + +kvm_ioctl_array := $(beauty_ioctl_outdir)/kvm_ioctl_array.c +kvm_hdr_dir := $(srctree)/tools/include/uapi/linux +kvm_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/kvm_ioctl.sh + +$(kvm_ioctl_array): $(kvm_hdr_dir)/kvm.h $(kvm_ioctl_tbl) + $(Q)$(SHELL) '$(kvm_ioctl_tbl)' $(kvm_hdr_dir) > $@ + +vhost_virtio_ioctl_array := $(beauty_ioctl_outdir)/vhost_virtio_ioctl_array.c +vhost_virtio_hdr_dir := $(srctree)/tools/include/uapi/linux +vhost_virtio_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/vhost_virtio_ioctl.sh + +$(vhost_virtio_ioctl_array): $(vhost_virtio_hdr_dir)/vhost.h $(vhost_virtio_ioctl_tbl) + $(Q)$(SHELL) '$(vhost_virtio_ioctl_tbl)' $(vhost_virtio_hdr_dir) > $@ + +perf_ioctl_array := $(beauty_ioctl_outdir)/perf_ioctl_array.c +perf_hdr_dir := $(srctree)/tools/include/uapi/linux +perf_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/perf_ioctl.sh + +$(perf_ioctl_array): $(perf_hdr_dir)/perf_event.h $(perf_ioctl_tbl) + $(Q)$(SHELL) '$(perf_ioctl_tbl)' $(perf_hdr_dir) > $@ + all: shell_compatibility_test $(ALL_PROGRAMS) $(LANG_BINDINGS) $(OTHER_PROGRAMS) $(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS) $(LIBTRACEEVENT_DYNAMIC_LIST) @@ -469,7 +535,13 @@ endif __build-dir = $(subst $(OUTPUT),,$(dir $@)) build-dir = $(if $(__build-dir),$(__build-dir),.) -prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders +prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioctl_array) \ + $(pkey_alloc_access_rights_array) \ + $(sndrv_pcm_ioctl_array) \ + $(sndrv_ctl_ioctl_array) \ + $(kvm_ioctl_array) \ + $(vhost_virtio_ioctl_array) \ + $(perf_ioctl_array) $(OUTPUT)%.o: %.c prepare FORCE $(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=$(build-dir) $@ @@ -512,7 +584,7 @@ $(LIBJVMTI_IN): FORCE $(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=jvmti obj=jvmti $(OUTPUT)$(LIBJVMTI): $(LIBJVMTI_IN) - $(QUIET_LINK)$(CC) -shared -Wl,-soname -Wl,$(LIBJVMTI) -o $@ $< -lelf -lrt + $(QUIET_LINK)$(CC) -shared -Wl,-soname -Wl,$(LIBJVMTI) -o $@ $< endif $(patsubst perf-%,%.o,$(PROGRAMS)): $(wildcard */*.h) @@ -703,7 +775,11 @@ install-tests: all install-gtk $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \ $(INSTALL) tests/attr.py '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \ - $(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr' + $(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell'; \ + $(INSTALL) tests/shell/*.sh '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell'; \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/lib'; \ + $(INSTALL) tests/shell/lib/*.sh '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/lib' install-bin: install-tools install-tests install-traceevent-plugins @@ -734,7 +810,14 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea $(call QUIET_CLEAN, core-gen) $(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)FEATURE-DUMP $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex* \ $(OUTPUT)util/intel-pt-decoder/inat-tables.c \ $(OUTPUT)tests/llvm-src-{base,kbuild,prologue,relocation}.c \ - $(OUTPUT)pmu-events/pmu-events.c + $(OUTPUT)pmu-events/pmu-events.c \ + $(OUTPUT)$(drm_ioctl_array) \ + $(OUTPUT)$(pkey_alloc_access_rights_array) \ + $(OUTPUT)$(sndrv_ctl_ioctl_array) \ + $(OUTPUT)$(sndrv_pcm_ioctl_array) \ + $(OUTPUT)$(kvm_ioctl_array) \ + $(OUTPUT)$(vhost_virtio_ioctl_array) \ + $(OUTPUT)$(perf_ioctl_array) $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean $(python-clean) diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index 29361d9b635a..fbfc055d3f4d 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -17,6 +17,7 @@ #include <api/fs/fs.h> #include <linux/bitops.h> +#include <linux/compiler.h> #include <linux/coresight-pmu.h> #include <linux/kernel.h> #include <linux/log2.h> @@ -202,19 +203,18 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, pr_debug2("%s snapshot size: %zu\n", CORESIGHT_ETM_PMU_NAME, opts->auxtrace_snapshot_size); - if (cs_etm_evsel) { - /* - * To obtain the auxtrace buffer file descriptor, the auxtrace - * event must come first. - */ - perf_evlist__to_front(evlist, cs_etm_evsel); - /* - * In the case of per-cpu mmaps, we need the CPU on the - * AUX event. - */ - if (!cpu_map__empty(cpus)) - perf_evsel__set_sample_bit(cs_etm_evsel, CPU); - } + /* + * To obtain the auxtrace buffer file descriptor, the auxtrace + * event must come first. + */ + perf_evlist__to_front(evlist, cs_etm_evsel); + + /* + * In the case of per-cpu mmaps, we need the CPU on the + * AUX event. + */ + if (!cpu_map__empty(cpus)) + perf_evsel__set_sample_bit(cs_etm_evsel, CPU); /* Add dummy event to keep tracking */ if (opts->full_auxtrace) { @@ -266,6 +266,32 @@ static u64 cs_etm_get_config(struct auxtrace_record *itr) return config; } +#ifndef BIT +#define BIT(N) (1UL << (N)) +#endif + +static u64 cs_etmv4_get_config(struct auxtrace_record *itr) +{ + u64 config = 0; + u64 config_opts = 0; + + /* + * The perf event variable config bits represent both + * the command line options and register programming + * bits in ETMv3/PTM. For ETMv4 we must remap options + * to real bits + */ + config_opts = cs_etm_get_config(itr); + if (config_opts & BIT(ETM_OPT_CYCACC)) + config |= BIT(ETM4_CFG_BIT_CYCACC); + if (config_opts & BIT(ETM_OPT_TS)) + config |= BIT(ETM4_CFG_BIT_TS); + if (config_opts & BIT(ETM_OPT_RETSTK)) + config |= BIT(ETM4_CFG_BIT_RETSTK); + + return config; +} + static size_t cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused, struct perf_evlist *evlist __maybe_unused) @@ -363,7 +389,7 @@ static void cs_etm_get_metadata(int cpu, u32 *offset, magic = __perf_cs_etmv4_magic; /* Get trace configuration register */ info->priv[*offset + CS_ETMV4_TRCCONFIGR] = - cs_etm_get_config(itr); + cs_etmv4_get_config(itr); /* Get traceID from the framework */ info->priv[*offset + CS_ETMV4_TRCTRACEIDR] = coresight_get_trace_id(cpu); @@ -583,8 +609,7 @@ static FILE *cs_device__open_file(const char *name) } -static __attribute__((format(printf, 2, 3))) -int cs_device__print_file(const char *name, const char *fmt, ...) +static int __printf(2, 3) cs_device__print_file(const char *name, const char *fmt, ...) { va_list args; FILE *file; diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build index 90ad64b231cd..2e6595310420 100644 --- a/tools/perf/arch/powerpc/util/Build +++ b/tools/perf/arch/powerpc/util/Build @@ -5,4 +5,6 @@ libperf-y += perf_regs.o libperf-$(CONFIG_DWARF) += dwarf-regs.o libperf-$(CONFIG_DWARF) += skip-callchain-idx.o + libperf-$(CONFIG_LIBUNWIND) += unwind-libunwind.o +libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c index bf9a2594572c..9c4e23d8c8ce 100644 --- a/tools/perf/arch/powerpc/util/sym-handling.c +++ b/tools/perf/arch/powerpc/util/sym-handling.c @@ -126,7 +126,7 @@ void arch__post_process_probe_trace_events(struct perf_probe_event *pev, struct rb_node *tmp; int i = 0; - map = get_target_map(pev->target, pev->uprobes); + map = get_target_map(pev->target, pev->nsi, pev->uprobes); if (!map || map__load(map) < 0) return; diff --git a/tools/perf/arch/powerpc/util/unwind-libdw.c b/tools/perf/arch/powerpc/util/unwind-libdw.c new file mode 100644 index 000000000000..3a24b3c43273 --- /dev/null +++ b/tools/perf/arch/powerpc/util/unwind-libdw.c @@ -0,0 +1,73 @@ +#include <elfutils/libdwfl.h> +#include "../../util/unwind-libdw.h" +#include "../../util/perf_regs.h" +#include "../../util/event.h" + +/* See backends/ppc_initreg.c and backends/ppc_regs.c in elfutils. */ +static const int special_regs[3][2] = { + { 65, PERF_REG_POWERPC_LINK }, + { 101, PERF_REG_POWERPC_XER }, + { 109, PERF_REG_POWERPC_CTR }, +}; + +bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg) +{ + struct unwind_info *ui = arg; + struct regs_dump *user_regs = &ui->sample->user_regs; + Dwarf_Word dwarf_regs[32], dwarf_nip; + size_t i; + +#define REG(r) ({ \ + Dwarf_Word val = 0; \ + perf_reg_value(&val, user_regs, PERF_REG_POWERPC_##r); \ + val; \ +}) + + dwarf_regs[0] = REG(R0); + dwarf_regs[1] = REG(R1); + dwarf_regs[2] = REG(R2); + dwarf_regs[3] = REG(R3); + dwarf_regs[4] = REG(R4); + dwarf_regs[5] = REG(R5); + dwarf_regs[6] = REG(R6); + dwarf_regs[7] = REG(R7); + dwarf_regs[8] = REG(R8); + dwarf_regs[9] = REG(R9); + dwarf_regs[10] = REG(R10); + dwarf_regs[11] = REG(R11); + dwarf_regs[12] = REG(R12); + dwarf_regs[13] = REG(R13); + dwarf_regs[14] = REG(R14); + dwarf_regs[15] = REG(R15); + dwarf_regs[16] = REG(R16); + dwarf_regs[17] = REG(R17); + dwarf_regs[18] = REG(R18); + dwarf_regs[19] = REG(R19); + dwarf_regs[20] = REG(R20); + dwarf_regs[21] = REG(R21); + dwarf_regs[22] = REG(R22); + dwarf_regs[23] = REG(R23); + dwarf_regs[24] = REG(R24); + dwarf_regs[25] = REG(R25); + dwarf_regs[26] = REG(R26); + dwarf_regs[27] = REG(R27); + dwarf_regs[28] = REG(R28); + dwarf_regs[29] = REG(R29); + dwarf_regs[30] = REG(R30); + dwarf_regs[31] = REG(R31); + if (!dwfl_thread_state_registers(thread, 0, 32, dwarf_regs)) + return false; + + dwarf_nip = REG(NIP); + dwfl_thread_state_register_pc(thread, dwarf_nip); + for (i = 0; i < ARRAY_SIZE(special_regs); i++) { + Dwarf_Word val = 0; + perf_reg_value(&val, user_regs, special_regs[i][1]); + if (!dwfl_thread_state_registers(thread, + special_regs[i][0], 1, + &val)) + return false; + } + + return true; +} diff --git a/tools/perf/arch/s390/util/Build b/tools/perf/arch/s390/util/Build index 5bd7b9260cc0..bd518b623d7a 100644 --- a/tools/perf/arch/s390/util/Build +++ b/tools/perf/arch/s390/util/Build @@ -1,4 +1,5 @@ libperf-y += header.o +libperf-y += sym-handling.o libperf-y += kvm-stat.o libperf-$(CONFIG_DWARF) += dwarf-regs.o diff --git a/tools/perf/arch/s390/util/sym-handling.c b/tools/perf/arch/s390/util/sym-handling.c new file mode 100644 index 000000000000..e103f6e46afe --- /dev/null +++ b/tools/perf/arch/s390/util/sym-handling.c @@ -0,0 +1,29 @@ +/* + * Architecture specific ELF symbol handling and relocation mapping. + * + * Copyright 2017 IBM Corp. + * Author(s): Thomas Richter <tmricht@linux.vnet.ibm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + */ + +#include "symbol.h" + +#ifdef HAVE_LIBELF_SUPPORT +bool elf__needs_adjust_symbols(GElf_Ehdr ehdr) +{ + if (ehdr.e_type == ET_EXEC) + return false; + return ehdr.e_type == ET_REL || ehdr.e_type == ET_DYN; +} + +void arch__adjust_sym_map_offset(GElf_Sym *sym, + GElf_Shdr *shdr __maybe_unused, + struct map *map) +{ + if (map->type == MAP__FUNCTION) + sym->st_value += map->start; +} +#endif diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile index 6c9211b18ec0..9a628a24c5c9 100644 --- a/tools/perf/arch/x86/Makefile +++ b/tools/perf/arch/x86/Makefile @@ -20,7 +20,7 @@ _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') $(header): $(sys)/syscall_64.tbl $(systbl) @(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \ (diff -B arch/x86/entry/syscalls/syscall_64.tbl ../../arch/x86/entry/syscalls/syscall_64.tbl >/dev/null) \ - || echo "Warning: x86_64's syscall_64.tbl differs from kernel" >&2 )) || true + || echo "Warning: Kernel ABI header at 'tools/arch/x86/entry/syscalls/syscall_64.tbl' differs from latest version at 'arch/x86/entry/syscalls/syscall_64.tbl'" >&2 )) || true $(Q)$(SHELL) '$(systbl)' $(sys)/syscall_64.tbl 'x86_64' > $@ clean:: diff --git a/tools/perf/arch/x86/annotate/instructions.c b/tools/perf/arch/x86/annotate/instructions.c index c1625f256df3..d84b72063a30 100644 --- a/tools/perf/arch/x86/annotate/instructions.c +++ b/tools/perf/arch/x86/annotate/instructions.c @@ -76,3 +76,49 @@ static struct ins x86__instructions[] = { { .name = "xbeginq", .ops = &jump_ops, }, { .name = "retq", .ops = &ret_ops, }, }; + +static bool x86__ins_is_fused(struct arch *arch, const char *ins1, + const char *ins2) +{ + if (arch->family != 6 || arch->model < 0x1e || strstr(ins2, "jmp")) + return false; + + if (arch->model == 0x1e) { + /* Nehalem */ + if ((strstr(ins1, "cmp") && !strstr(ins1, "xchg")) || + strstr(ins1, "test")) { + return true; + } + } else { + /* Newer platform */ + if ((strstr(ins1, "cmp") && !strstr(ins1, "xchg")) || + strstr(ins1, "test") || + strstr(ins1, "add") || + strstr(ins1, "sub") || + strstr(ins1, "and") || + strstr(ins1, "inc") || + strstr(ins1, "dec")) { + return true; + } + } + + return false; +} + +static int x86__cpuid_parse(struct arch *arch, char *cpuid) +{ + unsigned int family, model, stepping; + int ret; + + /* + * cpuid = "GenuineIntel,family,model,stepping" + */ + ret = sscanf(cpuid, "%*[^,],%u,%u,%u", &family, &model, &stepping); + if (ret == 3) { + arch->family = family; + arch->model = model; + return 0; + } + + return -1; +} diff --git a/tools/perf/arch/x86/include/arch-tests.h b/tools/perf/arch/x86/include/arch-tests.h index b48de2f5813c..4e0b806a7a0f 100644 --- a/tools/perf/arch/x86/include/arch-tests.h +++ b/tools/perf/arch/x86/include/arch-tests.h @@ -1,11 +1,14 @@ #ifndef ARCH_TESTS_H #define ARCH_TESTS_H +#include <linux/compiler.h> +struct test; + /* Tests */ -int test__rdpmc(int subtest); -int test__perf_time_to_tsc(int subtest); -int test__insn_x86(int subtest); -int test__intel_cqm_count_nmi_context(int subtest); +int test__rdpmc(struct test *test __maybe_unused, int subtest); +int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest); +int test__insn_x86(struct test *test __maybe_unused, int subtest); +int test__intel_cqm_count_nmi_context(struct test *test __maybe_unused, int subtest); #ifdef HAVE_DWARF_UNWIND_SUPPORT struct thread; diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-32.c b/tools/perf/arch/x86/tests/insn-x86-dat-32.c index 0f196eec9f48..3cbf6fad169f 100644 --- a/tools/perf/arch/x86/tests/insn-x86-dat-32.c +++ b/tools/perf/arch/x86/tests/insn-x86-dat-32.c @@ -1664,3 +1664,15 @@ "0f c7 1d 78 56 34 12 \txrstors 0x12345678",}, {{0x0f, 0xc7, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "", "0f c7 9c c8 78 56 34 12 \txrstors 0x12345678(%eax,%ecx,8)",}, +{{0xf3, 0x0f, 0xae, 0x20, }, 4, 0, "", "", +"f3 0f ae 20 \tptwritel (%eax)",}, +{{0xf3, 0x0f, 0xae, 0x25, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "", +"f3 0f ae 25 78 56 34 12 \tptwritel 0x12345678",}, +{{0xf3, 0x0f, 0xae, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "", +"f3 0f ae a4 c8 78 56 34 12 \tptwritel 0x12345678(%eax,%ecx,8)",}, +{{0xf3, 0x0f, 0xae, 0x20, }, 4, 0, "", "", +"f3 0f ae 20 \tptwritel (%eax)",}, +{{0xf3, 0x0f, 0xae, 0x25, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "", +"f3 0f ae 25 78 56 34 12 \tptwritel 0x12345678",}, +{{0xf3, 0x0f, 0xae, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "", +"f3 0f ae a4 c8 78 56 34 12 \tptwritel 0x12345678(%eax,%ecx,8)",}, diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-64.c b/tools/perf/arch/x86/tests/insn-x86-dat-64.c index af25bc8240d0..aa512fa944dd 100644 --- a/tools/perf/arch/x86/tests/insn-x86-dat-64.c +++ b/tools/perf/arch/x86/tests/insn-x86-dat-64.c @@ -1696,3 +1696,33 @@ "0f c7 9c c8 78 56 34 12 \txrstors 0x12345678(%rax,%rcx,8)",}, {{0x41, 0x0f, 0xc7, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "", "41 0f c7 9c c8 78 56 34 12 \txrstors 0x12345678(%r8,%rcx,8)",}, +{{0xf3, 0x0f, 0xae, 0x20, }, 4, 0, "", "", +"f3 0f ae 20 \tptwritel (%rax)",}, +{{0xf3, 0x41, 0x0f, 0xae, 0x20, }, 5, 0, "", "", +"f3 41 0f ae 20 \tptwritel (%r8)",}, +{{0xf3, 0x0f, 0xae, 0x24, 0x25, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "", +"f3 0f ae 24 25 78 56 34 12 \tptwritel 0x12345678",}, +{{0xf3, 0x0f, 0xae, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "", +"f3 0f ae a4 c8 78 56 34 12 \tptwritel 0x12345678(%rax,%rcx,8)",}, +{{0xf3, 0x41, 0x0f, 0xae, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"f3 41 0f ae a4 c8 78 56 34 12 \tptwritel 0x12345678(%r8,%rcx,8)",}, +{{0xf3, 0x0f, 0xae, 0x20, }, 4, 0, "", "", +"f3 0f ae 20 \tptwritel (%rax)",}, +{{0xf3, 0x41, 0x0f, 0xae, 0x20, }, 5, 0, "", "", +"f3 41 0f ae 20 \tptwritel (%r8)",}, +{{0xf3, 0x0f, 0xae, 0x24, 0x25, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "", +"f3 0f ae 24 25 78 56 34 12 \tptwritel 0x12345678",}, +{{0xf3, 0x0f, 0xae, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "", +"f3 0f ae a4 c8 78 56 34 12 \tptwritel 0x12345678(%rax,%rcx,8)",}, +{{0xf3, 0x41, 0x0f, 0xae, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"f3 41 0f ae a4 c8 78 56 34 12 \tptwritel 0x12345678(%r8,%rcx,8)",}, +{{0xf3, 0x48, 0x0f, 0xae, 0x20, }, 5, 0, "", "", +"f3 48 0f ae 20 \tptwriteq (%rax)",}, +{{0xf3, 0x49, 0x0f, 0xae, 0x20, }, 5, 0, "", "", +"f3 49 0f ae 20 \tptwriteq (%r8)",}, +{{0xf3, 0x48, 0x0f, 0xae, 0x24, 0x25, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"f3 48 0f ae 24 25 78 56 34 12 \tptwriteq 0x12345678",}, +{{0xf3, 0x48, 0x0f, 0xae, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"f3 48 0f ae a4 c8 78 56 34 12 \tptwriteq 0x12345678(%rax,%rcx,8)",}, +{{0xf3, 0x49, 0x0f, 0xae, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"f3 49 0f ae a4 c8 78 56 34 12 \tptwriteq 0x12345678(%r8,%rcx,8)",}, diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-src.c b/tools/perf/arch/x86/tests/insn-x86-dat-src.c index 979487dae8d4..6cdb65d25b79 100644 --- a/tools/perf/arch/x86/tests/insn-x86-dat-src.c +++ b/tools/perf/arch/x86/tests/insn-x86-dat-src.c @@ -1343,6 +1343,26 @@ int main(void) asm volatile("xrstors 0x12345678(%rax,%rcx,8)"); asm volatile("xrstors 0x12345678(%r8,%rcx,8)"); + /* ptwrite */ + + asm volatile("ptwrite (%rax)"); + asm volatile("ptwrite (%r8)"); + asm volatile("ptwrite (0x12345678)"); + asm volatile("ptwrite 0x12345678(%rax,%rcx,8)"); + asm volatile("ptwrite 0x12345678(%r8,%rcx,8)"); + + asm volatile("ptwritel (%rax)"); + asm volatile("ptwritel (%r8)"); + asm volatile("ptwritel (0x12345678)"); + asm volatile("ptwritel 0x12345678(%rax,%rcx,8)"); + asm volatile("ptwritel 0x12345678(%r8,%rcx,8)"); + + asm volatile("ptwriteq (%rax)"); + asm volatile("ptwriteq (%r8)"); + asm volatile("ptwriteq (0x12345678)"); + asm volatile("ptwriteq 0x12345678(%rax,%rcx,8)"); + asm volatile("ptwriteq 0x12345678(%r8,%rcx,8)"); + #else /* #ifdef __x86_64__ */ /* bound r32, mem (same op code as EVEX prefix) */ @@ -2653,6 +2673,16 @@ int main(void) asm volatile("xrstors (0x12345678)"); asm volatile("xrstors 0x12345678(%eax,%ecx,8)"); + /* ptwrite */ + + asm volatile("ptwrite (%eax)"); + asm volatile("ptwrite (0x12345678)"); + asm volatile("ptwrite 0x12345678(%eax,%ecx,8)"); + + asm volatile("ptwritel (%eax)"); + asm volatile("ptwritel (0x12345678)"); + asm volatile("ptwritel 0x12345678(%eax,%ecx,8)"); + #endif /* #ifndef __x86_64__ */ /* Following line is a marker for the awk script - do not change */ diff --git a/tools/perf/arch/x86/tests/insn-x86.c b/tools/perf/arch/x86/tests/insn-x86.c index 08d9b2bc185c..b3860586a0c2 100644 --- a/tools/perf/arch/x86/tests/insn-x86.c +++ b/tools/perf/arch/x86/tests/insn-x86.c @@ -171,7 +171,7 @@ static int test_data_set(struct test_data *dat_set, int x86_64) * verbose (-v) option to see all the instructions and whether or not they * decoded successfuly. */ -int test__insn_x86(int subtest __maybe_unused) +int test__insn_x86(struct test *test __maybe_unused, int subtest __maybe_unused) { int ret = 0; diff --git a/tools/perf/arch/x86/tests/intel-cqm.c b/tools/perf/arch/x86/tests/intel-cqm.c index f9713a71d77e..57f86b6e7d6f 100644 --- a/tools/perf/arch/x86/tests/intel-cqm.c +++ b/tools/perf/arch/x86/tests/intel-cqm.c @@ -36,7 +36,7 @@ static pid_t spawn(void) * the last read counter value to avoid triggering a WARN_ON_ONCE() in * smp_call_function_many() caused by sending IPIs from NMI context. */ -int test__intel_cqm_count_nmi_context(int subtest __maybe_unused) +int test__intel_cqm_count_nmi_context(struct test *test __maybe_unused, int subtest __maybe_unused) { struct perf_evlist *evlist = NULL; struct perf_evsel *evsel = NULL; diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c b/tools/perf/arch/x86/tests/perf-time-to-tsc.c index e3ae9cff2b67..5dd7efb192ce 100644 --- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c +++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c @@ -37,7 +37,7 @@ * %0 is returned, otherwise %-1 is returned. If TSC conversion is not * supported then then the test passes but " (not supported)" is printed. */ -int test__perf_time_to_tsc(int subtest __maybe_unused) +int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe_unused) { struct record_opts opts = { .mmap_pages = UINT_MAX, diff --git a/tools/perf/arch/x86/tests/rdpmc.c b/tools/perf/arch/x86/tests/rdpmc.c index 500cf96db979..17fec30a0b31 100644 --- a/tools/perf/arch/x86/tests/rdpmc.c +++ b/tools/perf/arch/x86/tests/rdpmc.c @@ -154,7 +154,7 @@ out_close: return 0; } -int test__rdpmc(int subtest __maybe_unused) +int test__rdpmc(struct test *test __maybe_unused, int subtest __maybe_unused) { int status = 0; int wret = 0; diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c index af2bce7a2cd6..781df40b2966 100644 --- a/tools/perf/arch/x86/util/intel-bts.c +++ b/tools/perf/arch/x86/util/intel-bts.c @@ -35,10 +35,6 @@ #define KiB_MASK(x) (KiB(x) - 1) #define MiB_MASK(x) (MiB(x) - 1) -#define INTEL_BTS_DFLT_SAMPLE_SIZE KiB(4) - -#define INTEL_BTS_MAX_SAMPLE_SIZE KiB(60) - struct intel_bts_snapshot_ref { void *ref_buf; size_t ref_offset; diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index f630de0206a1..db0ba8caf5a2 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -40,10 +40,6 @@ #define KiB_MASK(x) (KiB(x) - 1) #define MiB_MASK(x) (MiB(x) - 1) -#define INTEL_PT_DEFAULT_SAMPLE_SIZE KiB(4) - -#define INTEL_PT_MAX_SAMPLE_SIZE KiB(60) - #define INTEL_PT_PSB_PERIOD_NEAR 256 struct intel_pt_snapshot_ref { @@ -196,6 +192,7 @@ static u64 intel_pt_default_config(struct perf_pmu *intel_pt_pmu) int psb_cyc, psb_periods, psb_period; int pos = 0; u64 config; + char c; pos += scnprintf(buf + pos, sizeof(buf) - pos, "tsc"); @@ -229,6 +226,10 @@ static u64 intel_pt_default_config(struct perf_pmu *intel_pt_pmu) } } + if (perf_pmu__scan_file(intel_pt_pmu, "format/pt", "%c", &c) == 1 && + perf_pmu__scan_file(intel_pt_pmu, "format/branch", "%c", &c) == 1) + pos += scnprintf(buf + pos, sizeof(buf) - pos, ",pt,branch"); + pr_debug2("%s default config: %s\n", intel_pt_pmu->name, buf); intel_pt_parse_terms(&intel_pt_pmu->format, buf, &config); @@ -700,6 +701,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, perf_evsel__set_sample_bit(switch_evsel, TID); perf_evsel__set_sample_bit(switch_evsel, TIME); perf_evsel__set_sample_bit(switch_evsel, CPU); + perf_evsel__reset_sample_bit(switch_evsel, BRANCH_STACK); opts->record_switch_events = false; ptr->have_sched_switch = 3; @@ -751,6 +753,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, tracking_evsel->attr.freq = 0; tracking_evsel->attr.sample_period = 1; + tracking_evsel->no_aux_samples = true; if (need_immediate) tracking_evsel->immediate = true; @@ -760,6 +763,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, /* And the CPU for switch events */ perf_evsel__set_sample_bit(tracking_evsel, CPU); } + perf_evsel__reset_sample_bit(tracking_evsel, BRANCH_STACK); } /* diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c index 27de0c8c5c19..469d65b21122 100644 --- a/tools/perf/bench/numa.c +++ b/tools/perf/bench/numa.c @@ -700,7 +700,7 @@ static inline uint32_t lfsr_32(uint32_t lfsr) * kernel (KSM, zero page, etc.) cannot optimize away RAM * accesses: */ -static inline u64 access_data(u64 *data __attribute__((unused)), u64 val) +static inline u64 access_data(u64 *data, u64 val) { if (g->p.data_reads) val += *data; diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 7a5dc7e5c577..c38373195c4a 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -177,14 +177,11 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel, */ process_branch_stack(sample->branch_stack, al, sample); - sample->period = 1; - sample->weight = 1; - he = hists__add_entry(hists, al, NULL, NULL, NULL, sample, true); if (he == NULL) return -ENOMEM; - ret = hist_entry__inc_addr_samples(he, evsel->idx, al->addr); + ret = hist_entry__inc_addr_samples(he, sample, evsel->idx, al->addr); hists__inc_nr_samples(hists, true); return ret; } @@ -397,6 +394,8 @@ int cmd_annotate(int argc, const char **argv) .namespaces = perf_event__process_namespaces, .attr = perf_event__process_attr, .build_id = perf_event__process_build_id, + .tracing_data = perf_event__process_tracing_data, + .feature = perf_event__process_feature, .ordered_events = true, .ordering_requires_timestamps = true, }, @@ -404,7 +403,7 @@ int cmd_annotate(int argc, const char **argv) struct perf_data_file file = { .mode = PERF_DATA_MODE_READ, }; - const struct option options[] = { + struct option options[] = { OPT_STRING('i', "input", &input_name, "file", "input file name"), OPT_STRING('d', "dsos", &symbol_conf.dso_list_str, "dso[,dso...]", @@ -446,13 +445,20 @@ int cmd_annotate(int argc, const char **argv) "Show event group information together"), OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period, "Show a column with the sum of periods"), + OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples, + "Show a column with the number of samples"), OPT_CALLBACK_DEFAULT(0, "stdio-color", NULL, "mode", "'always' (default), 'never' or 'auto' only applicable to --stdio mode", stdio__config_color, "always"), OPT_END() }; - int ret = hists__init(); + int ret; + + set_option_flag(options, 0, "show-total-period", PARSE_OPT_EXCLUSIVE); + set_option_flag(options, 0, "show-nr-samples", PARSE_OPT_EXCLUSIVE); + + ret = hists__init(); if (ret < 0) return ret; @@ -468,6 +474,11 @@ int cmd_annotate(int argc, const char **argv) annotate.sym_hist_filter = argv[0]; } + if (symbol_conf.show_nr_samples && annotate.use_gtk) { + pr_err("--show-nr-samples is not available in --gtk mode at this time\n"); + return ret; + } + if (quiet) perf_quiet_option(); diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c index 9eba7f1add1f..e3eb6240ced0 100644 --- a/tools/perf/builtin-buildid-cache.c +++ b/tools/perf/builtin-buildid-cache.c @@ -14,6 +14,7 @@ #include <unistd.h> #include "builtin.h" #include "perf.h" +#include "namespaces.h" #include "util/cache.h" #include "util/debug.h" #include "util/header.h" @@ -165,33 +166,41 @@ static int build_id_cache__add_kcore(const char *filename, bool force) return 0; } -static int build_id_cache__add_file(const char *filename) +static int build_id_cache__add_file(const char *filename, struct nsinfo *nsi) { char sbuild_id[SBUILD_ID_SIZE]; u8 build_id[BUILD_ID_SIZE]; int err; + struct nscookie nsc; - if (filename__read_build_id(filename, &build_id, sizeof(build_id)) < 0) { + nsinfo__mountns_enter(nsi, &nsc); + err = filename__read_build_id(filename, &build_id, sizeof(build_id)); + nsinfo__mountns_exit(&nsc); + if (err < 0) { pr_debug("Couldn't read a build-id in %s\n", filename); return -1; } build_id__sprintf(build_id, sizeof(build_id), sbuild_id); - err = build_id_cache__add_s(sbuild_id, filename, + err = build_id_cache__add_s(sbuild_id, filename, nsi, false, false); pr_debug("Adding %s %s: %s\n", sbuild_id, filename, err ? "FAIL" : "Ok"); return err; } -static int build_id_cache__remove_file(const char *filename) +static int build_id_cache__remove_file(const char *filename, struct nsinfo *nsi) { u8 build_id[BUILD_ID_SIZE]; char sbuild_id[SBUILD_ID_SIZE]; + struct nscookie nsc; int err; - if (filename__read_build_id(filename, &build_id, sizeof(build_id)) < 0) { + nsinfo__mountns_enter(nsi, &nsc); + err = filename__read_build_id(filename, &build_id, sizeof(build_id)); + nsinfo__mountns_exit(&nsc); + if (err < 0) { pr_debug("Couldn't read a build-id in %s\n", filename); return -1; } @@ -204,13 +213,13 @@ static int build_id_cache__remove_file(const char *filename) return err; } -static int build_id_cache__purge_path(const char *pathname) +static int build_id_cache__purge_path(const char *pathname, struct nsinfo *nsi) { struct strlist *list; struct str_node *pos; int err; - err = build_id_cache__list_build_ids(pathname, &list); + err = build_id_cache__list_build_ids(pathname, nsi, &list); if (err) goto out; @@ -234,7 +243,7 @@ static bool dso__missing_buildid_cache(struct dso *dso, int parm __maybe_unused) char filename[PATH_MAX]; u8 build_id[BUILD_ID_SIZE]; - if (dso__build_id_filename(dso, filename, sizeof(filename)) && + if (dso__build_id_filename(dso, filename, sizeof(filename), false) && filename__read_build_id(filename, build_id, sizeof(build_id)) != sizeof(build_id)) { if (errno == ENOENT) @@ -256,24 +265,30 @@ static int build_id_cache__fprintf_missing(struct perf_session *session, FILE *f return 0; } -static int build_id_cache__update_file(const char *filename) +static int build_id_cache__update_file(const char *filename, struct nsinfo *nsi) { u8 build_id[BUILD_ID_SIZE]; char sbuild_id[SBUILD_ID_SIZE]; + struct nscookie nsc; - int err = 0; + int err; - if (filename__read_build_id(filename, &build_id, sizeof(build_id)) < 0) { + nsinfo__mountns_enter(nsi, &nsc); + err = filename__read_build_id(filename, &build_id, sizeof(build_id)); + nsinfo__mountns_exit(&nsc); + if (err < 0) { pr_debug("Couldn't read a build-id in %s\n", filename); return -1; } + err = 0; build_id__sprintf(build_id, sizeof(build_id), sbuild_id); if (build_id_cache__cached(sbuild_id)) err = build_id_cache__remove_s(sbuild_id); if (!err) - err = build_id_cache__add_s(sbuild_id, filename, false, false); + err = build_id_cache__add_s(sbuild_id, filename, nsi, false, + false); pr_debug("Updating %s %s: %s\n", sbuild_id, filename, err ? "FAIL" : "Ok"); @@ -286,6 +301,7 @@ int cmd_buildid_cache(int argc, const char **argv) struct strlist *list; struct str_node *pos; int ret = 0; + int ns_id = -1; bool force = false; char const *add_name_list_str = NULL, *remove_name_list_str = NULL, @@ -299,6 +315,7 @@ int cmd_buildid_cache(int argc, const char **argv) .mode = PERF_DATA_MODE_READ, }; struct perf_session *session = NULL; + struct nsinfo *nsi = NULL; const struct option buildid_cache_options[] = { OPT_STRING('a', "add", &add_name_list_str, @@ -315,6 +332,7 @@ int cmd_buildid_cache(int argc, const char **argv) OPT_STRING('u', "update", &update_name_list_str, "file list", "file(s) to update"), OPT_INCR('v', "verbose", &verbose, "be more verbose"), + OPT_INTEGER(0, "target-ns", &ns_id, "target pid for namespace context"), OPT_END() }; const char * const buildid_cache_usage[] = { @@ -330,6 +348,9 @@ int cmd_buildid_cache(int argc, const char **argv) !missing_filename && !update_name_list_str)) usage_with_options(buildid_cache_usage, buildid_cache_options); + if (ns_id > 0) + nsi = nsinfo__new(ns_id); + if (missing_filename) { file.path = missing_filename; file.force = force; @@ -348,7 +369,7 @@ int cmd_buildid_cache(int argc, const char **argv) list = strlist__new(add_name_list_str, NULL); if (list) { strlist__for_each_entry(pos, list) - if (build_id_cache__add_file(pos->s)) { + if (build_id_cache__add_file(pos->s, nsi)) { if (errno == EEXIST) { pr_debug("%s already in the cache\n", pos->s); @@ -366,7 +387,7 @@ int cmd_buildid_cache(int argc, const char **argv) list = strlist__new(remove_name_list_str, NULL); if (list) { strlist__for_each_entry(pos, list) - if (build_id_cache__remove_file(pos->s)) { + if (build_id_cache__remove_file(pos->s, nsi)) { if (errno == ENOENT) { pr_debug("%s wasn't in the cache\n", pos->s); @@ -384,7 +405,7 @@ int cmd_buildid_cache(int argc, const char **argv) list = strlist__new(purge_name_list_str, NULL); if (list) { strlist__for_each_entry(pos, list) - if (build_id_cache__purge_path(pos->s)) { + if (build_id_cache__purge_path(pos->s, nsi)) { if (errno == ENOENT) { pr_debug("%s wasn't in the cache\n", pos->s); @@ -405,7 +426,7 @@ int cmd_buildid_cache(int argc, const char **argv) list = strlist__new(update_name_list_str, NULL); if (list) { strlist__for_each_entry(pos, list) - if (build_id_cache__update_file(pos->s)) { + if (build_id_cache__update_file(pos->s, nsi)) { if (errno == ENOENT) { pr_debug("%s wasn't in the cache\n", pos->s); @@ -424,6 +445,7 @@ int cmd_buildid_cache(int argc, const char **argv) out: perf_session__delete(session); + nsinfo__zput(nsi); return ret; } diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index 620a467ee304..475999e48f66 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -1725,10 +1725,10 @@ static int c2c_hists__init_sort(struct perf_hpp_list *hpp_list, char *name) tok; tok = strtok_r(NULL, ", ", &tmp)) { \ ret = _fn(hpp_list, tok); \ if (ret == -EINVAL) { \ - error("Invalid --fields key: `%s'", tok); \ + pr_err("Invalid --fields key: `%s'", tok); \ break; \ } else if (ret == -ESRCH) { \ - error("Unknown --fields key: `%s'", tok); \ + pr_err("Unknown --fields key: `%s'", tok); \ break; \ } \ } \ diff --git a/tools/perf/builtin-config.c b/tools/perf/builtin-config.c index 80668fa7556e..a1d82e33282c 100644 --- a/tools/perf/builtin-config.c +++ b/tools/perf/builtin-config.c @@ -13,6 +13,7 @@ #include "util/util.h" #include "util/debug.h" #include "util/config.h" +#include <linux/string.h> static bool use_system_config, use_user_config; @@ -58,7 +59,7 @@ static int set_config(struct perf_config_set *set, const char *file_name, fprintf(fp, "[%s]\n", section->name); perf_config_items__for_each_entry(§ion->items, item) { - if (!use_system_config && section->from_system_config) + if (!use_system_config && item->from_system_config) continue; if (item->value) fprintf(fp, "\t%s = %s\n", @@ -79,7 +80,7 @@ static int show_spec_config(struct perf_config_set *set, const char *var) return -1; perf_config_items__for_each_entry(&set->sections, section) { - if (prefixcmp(var, section->name) != 0) + if (!strstarts(var, section->name)) continue; perf_config_items__for_each_entry(§ion->items, item) { @@ -156,7 +157,7 @@ static int parse_config_arg(char *arg, char **var, char **value) int cmd_config(int argc, const char **argv) { - int i, ret = 0; + int i, ret = -1; struct perf_config_set *set; char *user_config = mkpath("%s/.perfconfig", getenv("HOME")); const char *config_filename; @@ -186,10 +187,8 @@ int cmd_config(int argc, const char **argv) * because of reinitializing with options config file location. */ set = perf_config_set__new(); - if (!set) { - ret = -1; + if (!set) goto out_err; - } switch (actions) { case ACTION_LIST: @@ -197,41 +196,54 @@ int cmd_config(int argc, const char **argv) pr_err("Error: takes no arguments\n"); parse_options_usage(config_usage, config_options, "l", 1); } else { - ret = show_config(set); - if (ret < 0) + if (show_config(set) < 0) { pr_err("Nothing configured, " "please check your %s \n", config_filename); + goto out_err; + } } break; default: - if (argc) { - for (i = 0; argv[i]; i++) { - char *var, *value; - char *arg = strdup(argv[i]); - - if (!arg) { - pr_err("%s: strdup failed\n", __func__); - ret = -1; - break; - } + if (!argc) { + usage_with_options(config_usage, config_options); + break; + } - if (parse_config_arg(arg, &var, &value) < 0) { - free(arg); - ret = -1; - break; - } + for (i = 0; argv[i]; i++) { + char *var, *value; + char *arg = strdup(argv[i]); + + if (!arg) { + pr_err("%s: strdup failed\n", __func__); + goto out_err; + } - if (value == NULL) - ret = show_spec_config(set, var); - else - ret = set_config(set, config_filename, var, value); + if (parse_config_arg(arg, &var, &value) < 0) { free(arg); + goto out_err; } - } else - usage_with_options(config_usage, config_options); + + if (value == NULL) { + if (show_spec_config(set, var) < 0) { + pr_err("%s is not configured: %s\n", + var, config_filename); + free(arg); + goto out_err; + } + } else { + if (set_config(set, config_filename, var, value) < 0) { + pr_err("Failed to set '%s=%s' on %s\n", + var, value, config_filename); + free(arg); + goto out_err; + } + } + free(arg); + } } - perf_config_set__delete(set); + ret = 0; out_err: + perf_config_set__delete(set); return ret; } diff --git a/tools/perf/builtin-data.c b/tools/perf/builtin-data.c index 0adb5f82335a..46cd8490baf4 100644 --- a/tools/perf/builtin-data.c +++ b/tools/perf/builtin-data.c @@ -69,7 +69,7 @@ static int cmd_data_convert(int argc, const char **argv) }; #ifndef HAVE_LIBBABELTRACE_SUPPORT - pr_err("No conversion support compiled in.\n"); + pr_err("No conversion support compiled in. perf should be compiled with environment variables LIBBABELTRACE=1 and LIBBABELTRACE_DIR=/path/to/libbabeltrace/\n"); return -1; #endif diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index eec5df80f5a3..0cd4cf6a344b 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -1302,7 +1302,10 @@ static int diff__config(const char *var, const char *value, void *cb __maybe_unused) { if (!strcmp(var, "diff.order")) { - sort_compute = perf_config_int(var, value); + int ret; + if (perf_config_int(&ret, var, value) < 0) + return -1; + sort_compute = ret; return 0; } if (!strcmp(var, "diff.compute")) { diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c index 9e0b35cd0eea..25a42acabee1 100644 --- a/tools/perf/builtin-ftrace.c +++ b/tools/perf/builtin-ftrace.c @@ -28,9 +28,19 @@ #define DEFAULT_TRACER "function_graph" struct perf_ftrace { - struct perf_evlist *evlist; - struct target target; - const char *tracer; + struct perf_evlist *evlist; + struct target target; + const char *tracer; + struct list_head filters; + struct list_head notrace; + struct list_head graph_funcs; + struct list_head nograph_funcs; + int graph_depth; +}; + +struct filter_entry { + struct list_head list; + char name[]; }; static bool done; @@ -61,6 +71,7 @@ static int __write_tracing_file(const char *name, const char *val, bool append) int fd, ret = -1; ssize_t size = strlen(val); int flags = O_WRONLY; + char errbuf[512]; file = get_tracing_file(name); if (!file) { @@ -75,14 +86,16 @@ static int __write_tracing_file(const char *name, const char *val, bool append) fd = open(file, flags); if (fd < 0) { - pr_debug("cannot open tracing file: %s\n", name); + pr_debug("cannot open tracing file: %s: %s\n", + name, str_error_r(errno, errbuf, sizeof(errbuf))); goto out; } if (write(fd, val, size) == size) ret = 0; else - pr_debug("write '%s' to tracing/%s failed\n", val, name); + pr_debug("write '%s' to tracing/%s failed: %s\n", + val, name, str_error_r(errno, errbuf, sizeof(errbuf))); close(fd); out: @@ -101,6 +114,7 @@ static int append_tracing_file(const char *name, const char *val) } static int reset_tracing_cpu(void); +static void reset_tracing_filters(void); static int reset_tracing_files(struct perf_ftrace *ftrace __maybe_unused) { @@ -116,6 +130,10 @@ static int reset_tracing_files(struct perf_ftrace *ftrace __maybe_unused) if (reset_tracing_cpu() < 0) return -1; + if (write_tracing_file("max_graph_depth", "0") < 0) + return -1; + + reset_tracing_filters(); return 0; } @@ -181,6 +199,68 @@ static int reset_tracing_cpu(void) return ret; } +static int __set_tracing_filter(const char *filter_file, struct list_head *funcs) +{ + struct filter_entry *pos; + + list_for_each_entry(pos, funcs, list) { + if (append_tracing_file(filter_file, pos->name) < 0) + return -1; + } + + return 0; +} + +static int set_tracing_filters(struct perf_ftrace *ftrace) +{ + int ret; + + ret = __set_tracing_filter("set_ftrace_filter", &ftrace->filters); + if (ret < 0) + return ret; + + ret = __set_tracing_filter("set_ftrace_notrace", &ftrace->notrace); + if (ret < 0) + return ret; + + ret = __set_tracing_filter("set_graph_function", &ftrace->graph_funcs); + if (ret < 0) + return ret; + + /* old kernels do not have this filter */ + __set_tracing_filter("set_graph_notrace", &ftrace->nograph_funcs); + + return ret; +} + +static void reset_tracing_filters(void) +{ + write_tracing_file("set_ftrace_filter", " "); + write_tracing_file("set_ftrace_notrace", " "); + write_tracing_file("set_graph_function", " "); + write_tracing_file("set_graph_notrace", " "); +} + +static int set_tracing_depth(struct perf_ftrace *ftrace) +{ + char buf[16]; + + if (ftrace->graph_depth == 0) + return 0; + + if (ftrace->graph_depth < 0) { + pr_err("invalid graph depth: %d\n", ftrace->graph_depth); + return -1; + } + + snprintf(buf, sizeof(buf), "%d", ftrace->graph_depth); + + if (write_tracing_file("max_graph_depth", buf) < 0) + return -1; + + return 0; +} + static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv) { char *trace_file; @@ -223,11 +303,23 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv) goto out_reset; } + if (set_tracing_filters(ftrace) < 0) { + pr_err("failed to set tracing filters\n"); + goto out_reset; + } + + if (set_tracing_depth(ftrace) < 0) { + pr_err("failed to set graph depth\n"); + goto out_reset; + } + if (write_tracing_file("current_tracer", ftrace->tracer) < 0) { pr_err("failed to set current_tracer to %s\n", ftrace->tracer); goto out_reset; } + setup_pager(); + trace_file = get_tracing_file("trace_pipe"); if (!trace_file) { pr_err("failed to open trace_pipe\n"); @@ -251,8 +343,6 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv) goto out_close_fd; } - setup_pager(); - perf_evlist__start_workload(ftrace->evlist); while (!done) { @@ -291,7 +381,7 @@ static int perf_ftrace_config(const char *var, const char *value, void *cb) { struct perf_ftrace *ftrace = cb; - if (prefixcmp(var, "ftrace.")) + if (!strstarts(var, "ftrace.")) return 0; if (strcmp(var, "ftrace.tracer")) @@ -307,6 +397,32 @@ static int perf_ftrace_config(const char *var, const char *value, void *cb) return -1; } +static int parse_filter_func(const struct option *opt, const char *str, + int unset __maybe_unused) +{ + struct list_head *head = opt->value; + struct filter_entry *entry; + + entry = malloc(sizeof(*entry) + strlen(str) + 1); + if (entry == NULL) + return -ENOMEM; + + strcpy(entry->name, str); + list_add_tail(&entry->list, head); + + return 0; +} + +static void delete_filter_func(struct list_head *head) +{ + struct filter_entry *pos, *tmp; + + list_for_each_entry_safe(pos, tmp, head, list) { + list_del(&pos->list); + free(pos); + } +} + int cmd_ftrace(int argc, const char **argv) { int ret; @@ -330,9 +446,24 @@ int cmd_ftrace(int argc, const char **argv) "system-wide collection from all CPUs"), OPT_STRING('C', "cpu", &ftrace.target.cpu_list, "cpu", "list of cpus to monitor"), + OPT_CALLBACK('T', "trace-funcs", &ftrace.filters, "func", + "trace given functions only", parse_filter_func), + OPT_CALLBACK('N', "notrace-funcs", &ftrace.notrace, "func", + "do not trace given functions", parse_filter_func), + OPT_CALLBACK('G', "graph-funcs", &ftrace.graph_funcs, "func", + "Set graph filter on given functions", parse_filter_func), + OPT_CALLBACK('g', "nograph-funcs", &ftrace.nograph_funcs, "func", + "Set nograph filter on given functions", parse_filter_func), + OPT_INTEGER('D', "graph-depth", &ftrace.graph_depth, + "Max depth for function graph tracer"), OPT_END() }; + INIT_LIST_HEAD(&ftrace.filters); + INIT_LIST_HEAD(&ftrace.notrace); + INIT_LIST_HEAD(&ftrace.graph_funcs); + INIT_LIST_HEAD(&ftrace.nograph_funcs); + ret = perf_config(perf_ftrace_config, &ftrace); if (ret < 0) return -1; @@ -348,12 +479,14 @@ int cmd_ftrace(int argc, const char **argv) target__strerror(&ftrace.target, ret, errbuf, 512); pr_err("%s\n", errbuf); - return -EINVAL; + goto out_delete_filters; } ftrace.evlist = perf_evlist__new(); - if (ftrace.evlist == NULL) - return -ENOMEM; + if (ftrace.evlist == NULL) { + ret = -ENOMEM; + goto out_delete_filters; + } ret = perf_evlist__create_maps(ftrace.evlist, &ftrace.target); if (ret < 0) @@ -364,5 +497,11 @@ int cmd_ftrace(int argc, const char **argv) out_delete_evlist: perf_evlist__delete(ftrace.evlist); +out_delete_filters: + delete_filter_func(&ftrace.filters); + delete_filter_func(&ftrace.notrace); + delete_filter_func(&ftrace.graph_funcs); + delete_filter_func(&ftrace.nograph_funcs); + return ret; } diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c index 492f8e14ab09..dbe4e4153bcf 100644 --- a/tools/perf/builtin-help.c +++ b/tools/perf/builtin-help.c @@ -90,7 +90,7 @@ static int check_emacsclient_version(void) */ finish_command(&ec_process); - if (prefixcmp(buffer.buf, "emacsclient")) { + if (!strstarts(buffer.buf, "emacsclient")) { fprintf(stderr, "Failed to parse emacsclient version.\n"); goto out; } @@ -108,10 +108,14 @@ out: return ret; } -static void exec_woman_emacs(const char *path, const char *page) +static void exec_failed(const char *cmd) { char sbuf[STRERR_BUFSIZE]; + pr_warning("failed to exec '%s': %s", cmd, str_error_r(errno, sbuf, sizeof(sbuf))); +} +static void exec_woman_emacs(const char *path, const char *page) +{ if (!check_emacsclient_version()) { /* This works only with emacsclient version >= 22. */ char *man_page; @@ -122,8 +126,7 @@ static void exec_woman_emacs(const char *path, const char *page) execlp(path, "emacsclient", "-e", man_page, NULL); free(man_page); } - warning("failed to exec '%s': %s", path, - str_error_r(errno, sbuf, sizeof(sbuf))); + exec_failed(path); } } @@ -134,7 +137,6 @@ static void exec_man_konqueror(const char *path, const char *page) if (display && *display) { char *man_page; const char *filename = "kfmclient"; - char sbuf[STRERR_BUFSIZE]; /* It's simpler to launch konqueror using kfmclient. */ if (path) { @@ -155,33 +157,27 @@ static void exec_man_konqueror(const char *path, const char *page) execlp(path, filename, "newTab", man_page, NULL); free(man_page); } - warning("failed to exec '%s': %s", path, - str_error_r(errno, sbuf, sizeof(sbuf))); + exec_failed(path); } } static void exec_man_man(const char *path, const char *page) { - char sbuf[STRERR_BUFSIZE]; - if (!path) path = "man"; execlp(path, "man", page, NULL); - warning("failed to exec '%s': %s", path, - str_error_r(errno, sbuf, sizeof(sbuf))); + exec_failed(path); } static void exec_man_cmd(const char *cmd, const char *page) { - char sbuf[STRERR_BUFSIZE]; char *shell_cmd; if (asprintf(&shell_cmd, "%s %s", cmd, page) > 0) { execl("/bin/sh", "sh", "-c", shell_cmd, NULL); free(shell_cmd); } - warning("failed to exec '%s': %s", cmd, - str_error_r(errno, sbuf, sizeof(sbuf))); + exec_failed(cmd); } static void add_man_viewer(const char *name) @@ -214,6 +210,12 @@ static void do_add_man_viewer_info(const char *name, man_viewer_info_list = new; } +static void unsupported_man_viewer(const char *name, const char *var) +{ + pr_warning("'%s': path for unsupported man viewer.\n" + "Please consider using 'man.<tool>.%s' instead.", name, var); +} + static int add_man_viewer_path(const char *name, size_t len, const char *value) @@ -221,9 +223,7 @@ static int add_man_viewer_path(const char *name, if (supported_man_viewer(name, len)) do_add_man_viewer_info(name, len, value); else - warning("'%s': path for unsupported man viewer.\n" - "Please consider using 'man.<tool>.cmd' instead.", - name); + unsupported_man_viewer(name, "cmd"); return 0; } @@ -233,9 +233,7 @@ static int add_man_viewer_cmd(const char *name, const char *value) { if (supported_man_viewer(name, len)) - warning("'%s': cmd for supported man viewer.\n" - "Please consider using 'man.<tool>.path' instead.", - name); + unsupported_man_viewer(name, "path"); else do_add_man_viewer_info(name, len, value); @@ -247,8 +245,10 @@ static int add_man_viewer_info(const char *var, const char *value) const char *name = var + 4; const char *subkey = strrchr(name, '.'); - if (!subkey) - return error("Config with no key for man viewer: %s", name); + if (!subkey) { + pr_err("Config with no key for man viewer: %s", name); + return -1; + } if (!strcmp(subkey, ".path")) { if (!value) @@ -261,7 +261,7 @@ static int add_man_viewer_info(const char *var, const char *value) return add_man_viewer_cmd(name, subkey - name, value); } - warning("'%s': unsupported man viewer sub key.", subkey); + pr_warning("'%s': unsupported man viewer sub key.", subkey); return 0; } @@ -283,7 +283,7 @@ static int perf_help_config(const char *var, const char *value, void *cb) add_man_viewer(value); return 0; } - if (!prefixcmp(var, "man.")) + if (!strstarts(var, "man.")) return add_man_viewer_info(var, value); return 0; @@ -313,7 +313,7 @@ static const char *cmd_to_page(const char *perf_cmd) if (!perf_cmd) return "perf"; - else if (!prefixcmp(perf_cmd, "perf")) + else if (!strstarts(perf_cmd, "perf")) return perf_cmd; return asprintf(&s, "perf-%s", perf_cmd) < 0 ? NULL : s; @@ -332,7 +332,7 @@ static void setup_man_path(void) setenv("MANPATH", new_path, 1); free(new_path); } else { - error("Unable to setup man path"); + pr_err("Unable to setup man path"); } } @@ -349,7 +349,7 @@ static void exec_viewer(const char *name, const char *page) else if (info) exec_man_cmd(info, page); else - warning("'%s': unknown man viewer.", name); + pr_warning("'%s': unknown man viewer.", name); } static int show_man_page(const char *perf_cmd) diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index ea8db38eedd1..2b8032908fb2 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -770,6 +770,7 @@ int cmd_inject(int argc, const char **argv) .finished_round = perf_event__repipe_oe_synth, .build_id = perf_event__repipe_op2_synth, .id_index = perf_event__repipe_op2_synth, + .feature = perf_event__repipe_op2_synth, }, .input_name = "-", .samples = LIST_HEAD_INIT(inject.samples), diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index 9409c9464667..24ee68ecdd42 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -627,7 +627,6 @@ static const struct { { "GFP_HIGHUSER_MOVABLE", "HUM" }, { "GFP_HIGHUSER", "HU" }, { "GFP_USER", "U" }, - { "GFP_TEMPORARY", "TMP" }, { "GFP_KERNEL_ACCOUNT", "KAC" }, { "GFP_KERNEL", "K" }, { "GFP_NOFS", "NF" }, @@ -643,7 +642,7 @@ static const struct { { "__GFP_FS", "F" }, { "__GFP_COLD", "CO" }, { "__GFP_NOWARN", "NWR" }, - { "__GFP_REPEAT", "R" }, + { "__GFP_RETRY_MAYFAIL", "R" }, { "__GFP_NOFAIL", "NF" }, { "__GFP_NORETRY", "NR" }, { "__GFP_COMP", "C" }, @@ -1715,7 +1714,7 @@ static int setup_slab_sorting(struct list_head *sort_list, const char *arg) if (!tok) break; if (slab_sort_dimension__add(tok, sort_list) < 0) { - error("Unknown slab --sort key: '%s'", tok); + pr_err("Unknown slab --sort key: '%s'", tok); free(str); return -1; } @@ -1741,7 +1740,7 @@ static int setup_page_sorting(struct list_head *sort_list, const char *arg) if (!tok) break; if (page_sort_dimension__add(tok, sort_list) < 0) { - error("Unknown page --sort key: '%s'", tok); + pr_err("Unknown page --sort key: '%s'", tok); free(str); return -1; } diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index e001c0290793..0f15634ef82c 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -23,6 +23,7 @@ struct perf_mem { bool hide_unresolved; bool dump_raw; bool force; + bool phys_addr; int operation; const char *cpu_list; DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); @@ -101,6 +102,9 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem) rec_argv[i++] = "-d"; + if (mem->phys_addr) + rec_argv[i++] = "--phys-data"; + for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) { if (!perf_mem_events[j].record) continue; @@ -161,30 +165,60 @@ dump_raw_samples(struct perf_tool *tool, if (al.map != NULL) al.map->dso->hit = 1; - if (symbol_conf.field_sep) { - fmt = "%d%s%d%s0x%"PRIx64"%s0x%"PRIx64"%s%"PRIu64 - "%s0x%"PRIx64"%s%s:%s\n"; + if (mem->phys_addr) { + if (symbol_conf.field_sep) { + fmt = "%d%s%d%s0x%"PRIx64"%s0x%"PRIx64"%s0x%016"PRIx64 + "%s%"PRIu64"%s0x%"PRIx64"%s%s:%s\n"; + } else { + fmt = "%5d%s%5d%s0x%016"PRIx64"%s0x016%"PRIx64 + "%s0x%016"PRIx64"%s%5"PRIu64"%s0x%06"PRIx64 + "%s%s:%s\n"; + symbol_conf.field_sep = " "; + } + + printf(fmt, + sample->pid, + symbol_conf.field_sep, + sample->tid, + symbol_conf.field_sep, + sample->ip, + symbol_conf.field_sep, + sample->addr, + symbol_conf.field_sep, + sample->phys_addr, + symbol_conf.field_sep, + sample->weight, + symbol_conf.field_sep, + sample->data_src, + symbol_conf.field_sep, + al.map ? (al.map->dso ? al.map->dso->long_name : "???") : "???", + al.sym ? al.sym->name : "???"); } else { - fmt = "%5d%s%5d%s0x%016"PRIx64"%s0x016%"PRIx64 - "%s%5"PRIu64"%s0x%06"PRIx64"%s%s:%s\n"; - symbol_conf.field_sep = " "; - } + if (symbol_conf.field_sep) { + fmt = "%d%s%d%s0x%"PRIx64"%s0x%"PRIx64"%s%"PRIu64 + "%s0x%"PRIx64"%s%s:%s\n"; + } else { + fmt = "%5d%s%5d%s0x%016"PRIx64"%s0x016%"PRIx64 + "%s%5"PRIu64"%s0x%06"PRIx64"%s%s:%s\n"; + symbol_conf.field_sep = " "; + } - printf(fmt, - sample->pid, - symbol_conf.field_sep, - sample->tid, - symbol_conf.field_sep, - sample->ip, - symbol_conf.field_sep, - sample->addr, - symbol_conf.field_sep, - sample->weight, - symbol_conf.field_sep, - sample->data_src, - symbol_conf.field_sep, - al.map ? (al.map->dso ? al.map->dso->long_name : "???") : "???", - al.sym ? al.sym->name : "???"); + printf(fmt, + sample->pid, + symbol_conf.field_sep, + sample->tid, + symbol_conf.field_sep, + sample->ip, + symbol_conf.field_sep, + sample->addr, + symbol_conf.field_sep, + sample->weight, + symbol_conf.field_sep, + sample->data_src, + symbol_conf.field_sep, + al.map ? (al.map->dso ? al.map->dso->long_name : "???") : "???", + al.sym ? al.sym->name : "???"); + } out_put: addr_location__put(&al); return 0; @@ -224,7 +258,10 @@ static int report_raw_events(struct perf_mem *mem) if (ret < 0) goto out_delete; - printf("# PID, TID, IP, ADDR, LOCAL WEIGHT, DSRC, SYMBOL\n"); + if (mem->phys_addr) + printf("# PID, TID, IP, ADDR, PHYS ADDR, LOCAL WEIGHT, DSRC, SYMBOL\n"); + else + printf("# PID, TID, IP, ADDR, LOCAL WEIGHT, DSRC, SYMBOL\n"); ret = perf_session__process_events(session); @@ -254,9 +291,16 @@ static int report_events(int argc, const char **argv, struct perf_mem *mem) * there is no weight (cost) associated with stores, so don't print * the column */ - if (!(mem->operation & MEM_OPERATION_LOAD)) - rep_argv[i++] = "--sort=mem,sym,dso,symbol_daddr," - "dso_daddr,tlb,locked"; + if (!(mem->operation & MEM_OPERATION_LOAD)) { + if (mem->phys_addr) + rep_argv[i++] = "--sort=mem,sym,dso,symbol_daddr," + "dso_daddr,tlb,locked,phys_daddr"; + else + rep_argv[i++] = "--sort=mem,sym,dso,symbol_daddr," + "dso_daddr,tlb,locked"; + } else if (mem->phys_addr) + rep_argv[i++] = "--sort=local_weight,mem,sym,dso,symbol_daddr," + "dso_daddr,snoop,tlb,locked,phys_daddr"; for (j = 1; j < argc; j++, i++) rep_argv[i] = argv[j]; @@ -373,6 +417,7 @@ int cmd_mem(int argc, const char **argv) "separator for columns, no spaces will be added" " between columns '.' is reserved."), OPT_BOOLEAN('f', "force", &mem.force, "don't complain, do it"), + OPT_BOOLEAN('p', "phys-data", &mem.phys_addr, "Record/Report sample physical addresses"), OPT_END() }; const char *const mem_subcommands[] = { "record", "report", NULL }; diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c index cf9f9e9c2fc0..c0065923a525 100644 --- a/tools/perf/builtin-probe.c +++ b/tools/perf/builtin-probe.c @@ -58,6 +58,7 @@ static struct { struct line_range line_range; char *target; struct strfilter *filter; + struct nsinfo *nsi; } params; /* Parse an event definition. Note that any error must die. */ @@ -80,6 +81,9 @@ static int parse_probe_event(const char *str) params.target_used = true; } + if (params.nsi) + pev->nsi = nsinfo__get(params.nsi); + /* Parse a perf-probe command into event */ ret = parse_perf_probe_command(str, pev); pr_debug("%d arguments\n", pev->nargs); @@ -189,7 +193,7 @@ static int opt_set_target(const struct option *opt, const char *str, /* Expand given path to absolute path, except for modulename */ if (params.uprobes || strchr(str, '/')) { - tmp = realpath(str, NULL); + tmp = nsinfo__realpath(str, params.nsi); if (!tmp) { pr_warning("Failed to get the absolute path of %s: %m\n", str); return ret; @@ -208,6 +212,34 @@ static int opt_set_target(const struct option *opt, const char *str, return ret; } +static int opt_set_target_ns(const struct option *opt __maybe_unused, + const char *str, int unset __maybe_unused) +{ + int ret = -ENOENT; + pid_t ns_pid; + struct nsinfo *nsip; + + if (str) { + errno = 0; + ns_pid = (pid_t)strtol(str, NULL, 10); + if (errno != 0) { + ret = -errno; + pr_warning("Failed to parse %s as a pid: %s\n", str, + strerror(errno)); + return ret; + } + nsip = nsinfo__new(ns_pid); + if (nsip && nsip->need_setns) + params.nsi = nsinfo__get(nsip); + nsinfo__put(nsip); + + ret = 0; + } + + return ret; +} + + /* Command option callbacks */ #ifdef HAVE_DWARF_SUPPORT @@ -299,6 +331,7 @@ static void cleanup_params(void) line_range__clear(¶ms.line_range); free(params.target); strfilter__delete(params.filter); + nsinfo__put(params.nsi); memset(¶ms, 0, sizeof(params)); } @@ -383,7 +416,7 @@ static int del_perf_probe_caches(struct strfilter *filter) } strlist__for_each_entry(nd, bidlist) { - cache = probe_cache__new(nd->s); + cache = probe_cache__new(nd->s, NULL); if (!cache) continue; if (probe_cache__filter_purge(cache, filter) < 0 || @@ -554,6 +587,8 @@ __cmd_probe(int argc, const char **argv) OPT_BOOLEAN(0, "cache", &probe_conf.cache, "Manipulate probe cache"), OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory", "Look for files with symbols relative to this directory"), + OPT_CALLBACK(0, "target-ns", NULL, "pid", + "target pid for namespace contexts", opt_set_target_ns), OPT_END() }; int ret; @@ -634,15 +669,15 @@ __cmd_probe(int argc, const char **argv) pr_err_with_code(" Error: Failed to show event list.", ret); return ret; case 'F': - ret = show_available_funcs(params.target, params.filter, - params.uprobes); + ret = show_available_funcs(params.target, params.nsi, + params.filter, params.uprobes); if (ret < 0) pr_err_with_code(" Error: Failed to show functions.", ret); return ret; #ifdef HAVE_DWARF_SUPPORT case 'L': ret = show_line_range(¶ms.line_range, params.target, - params.uprobes); + params.nsi, params.uprobes); if (ret < 0) pr_err_with_code(" Error: Failed to show lines.", ret); return ret; diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index ee7d0a82ccd0..56f8142ff97f 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -453,7 +453,7 @@ try_again: } if (perf_evlist__apply_filters(evlist, &pos)) { - error("failed to set filter \"%s\" on event %s with %d (%s)\n", + pr_err("failed to set filter \"%s\" on event %s with %d (%s)\n", pos->filter, perf_evsel__name(pos), errno, str_error_r(errno, msg, sizeof(msg))); rc = -1; @@ -461,7 +461,7 @@ try_again: } if (perf_evlist__apply_drv_configs(evlist, &pos, &err_term)) { - error("failed to set config \"%s\" on event %s with %d (%s)\n", + pr_err("failed to set config \"%s\" on event %s with %d (%s)\n", err_term->val.drv_cfg, perf_evsel__name(pos), errno, str_error_r(errno, msg, sizeof(msg))); rc = -1; @@ -799,6 +799,13 @@ static int record__synthesize(struct record *rec, bool tail) return 0; if (file->is_pipe) { + err = perf_event__synthesize_features( + tool, session, rec->evlist, process_synthesized_event); + if (err < 0) { + pr_err("Couldn't synthesize features.\n"); + return err; + } + err = perf_event__synthesize_attrs(tool, session, process_synthesized_event); if (err < 0) { @@ -1597,6 +1604,8 @@ static struct option __record_options[] = { OPT_BOOLEAN('s', "stat", &record.opts.inherit_stat, "per thread counts"), OPT_BOOLEAN('d', "data", &record.opts.sample_address, "Record the sample addresses"), + OPT_BOOLEAN(0, "phys-data", &record.opts.sample_phys_addr, + "Record the sample physical addresses"), OPT_BOOLEAN(0, "sample-cpu", &record.opts.sample_cpu, "Record the sample cpu"), OPT_BOOLEAN_SET('T', "timestamp", &record.opts.sample_time, &record.opts.sample_time_set, @@ -1821,7 +1830,7 @@ int cmd_record(int argc, const char **argv) record.opts.tail_synthesize = true; if (rec->evlist->nr_entries == 0 && - perf_evlist__add_default(rec->evlist) < 0) { + __perf_evlist__add_default(rec->evlist, !record.opts.no_samples) < 0) { pr_err("Not enough memory for event selector list\n"); goto out; } diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 22478ff2b706..f9dff652dcbd 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -38,6 +38,7 @@ #include "util/time-utils.h" #include "util/auxtrace.h" #include "util/units.h" +#include "util/branch.h" #include <dlfcn.h> #include <errno.h> @@ -73,6 +74,7 @@ struct report { u64 queue_size; int socket_filter; DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); + struct branch_type_stat brtype_stat; }; static int report__config(const char *var, const char *value, void *cb) @@ -94,10 +96,9 @@ static int report__config(const char *var, const char *value, void *cb) symbol_conf.cumulate_callchain = perf_config_bool(var, value); return 0; } - if (!strcmp(var, "report.queue-size")) { - rep->queue_size = perf_config_u64(var, value); - return 0; - } + if (!strcmp(var, "report.queue-size")) + return perf_config_u64(&rep->queue_size, var, value); + if (!strcmp(var, "report.sort_order")) { default_sort_order = strdup(value); return 0; @@ -114,43 +115,60 @@ static int hist_iter__report_callback(struct hist_entry_iter *iter, struct report *rep = arg; struct hist_entry *he = iter->he; struct perf_evsel *evsel = iter->evsel; + struct perf_sample *sample = iter->sample; struct mem_info *mi; struct branch_info *bi; if (!ui__has_annotation()) return 0; - hist__account_cycles(iter->sample->branch_stack, al, iter->sample, + hist__account_cycles(sample->branch_stack, al, sample, rep->nonany_branch_mode); if (sort__mode == SORT_MODE__BRANCH) { bi = he->branch_info; - err = addr_map_symbol__inc_samples(&bi->from, evsel->idx); + err = addr_map_symbol__inc_samples(&bi->from, sample, evsel->idx); if (err) goto out; - err = addr_map_symbol__inc_samples(&bi->to, evsel->idx); + err = addr_map_symbol__inc_samples(&bi->to, sample, evsel->idx); } else if (rep->mem_mode) { mi = he->mem_info; - err = addr_map_symbol__inc_samples(&mi->daddr, evsel->idx); + err = addr_map_symbol__inc_samples(&mi->daddr, sample, evsel->idx); if (err) goto out; - err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr); + err = hist_entry__inc_addr_samples(he, sample, evsel->idx, al->addr); } else if (symbol_conf.cumulate_callchain) { if (single) - err = hist_entry__inc_addr_samples(he, evsel->idx, + err = hist_entry__inc_addr_samples(he, sample, evsel->idx, al->addr); } else { - err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr); + err = hist_entry__inc_addr_samples(he, sample, evsel->idx, al->addr); } out: return err; } +static int hist_iter__branch_callback(struct hist_entry_iter *iter, + struct addr_location *al __maybe_unused, + bool single __maybe_unused, + void *arg) +{ + struct hist_entry *he = iter->he; + struct report *rep = arg; + struct branch_info *bi; + + bi = he->branch_info; + branch_type_count(&rep->brtype_stat, &bi->flags, + bi->from.addr, bi->to.addr); + + return 0; +} + static int process_sample_event(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -189,6 +207,8 @@ static int process_sample_event(struct perf_tool *tool, */ if (!sample->branch_stack) goto out_put; + + iter.add_entry_cb = hist_iter__branch_callback; iter.ops = &hist_iter_branch; } else if (rep->mem_mode) { iter.ops = &hist_iter_mem; @@ -221,7 +241,7 @@ static int process_read_event(struct perf_tool *tool, const char *name = evsel ? perf_evsel__name(evsel) : "unknown"; int err = perf_read_values_add_value(&rep->show_threads_values, event->read.pid, event->read.tid, - event->read.id, + evsel->idx, name, event->read.value); @@ -229,10 +249,6 @@ static int process_read_event(struct perf_tool *tool, return err; } - dump_printf(": %d %d %s %" PRIu64 "\n", event->read.pid, event->read.tid, - evsel ? perf_evsel__name(evsel) : "FAIL", - event->read.value); - return 0; } @@ -259,10 +275,11 @@ static int report__setup_sample_type(struct report *rep) "'perf record' without -g?\n"); return -EINVAL; } - if (symbol_conf.use_callchain) { - ui__error("Selected -g or --branch-history but no " - "callchain data. Did\n" - "you call 'perf record' without -g?\n"); + if (symbol_conf.use_callchain && + !symbol_conf.show_branchflag_count) { + ui__error("Selected -g or --branch-history.\n" + "But no callchain or branch data.\n" + "Did you call 'perf record' without -g or -b?\n"); return -1; } } else if (!callchain_param.enabled && @@ -397,7 +414,8 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist, hists__fprintf_nr_sample_events(hists, rep, evname, stdout); hists__fprintf(hists, !quiet, 0, 0, rep->min_percent, stdout, - symbol_conf.use_callchain); + symbol_conf.use_callchain || + symbol_conf.show_branchflag_count); fprintf(stdout, "\n\n"); } @@ -411,6 +429,9 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist, perf_read_values_destroy(&rep->show_threads_values); } + if (sort__mode == SORT_MODE__BRANCH) + branch_type_stat_display(stdout, &rep->brtype_stat); + return 0; } @@ -558,6 +579,7 @@ static int __cmd_report(struct report *rep) ui__error("failed to set cpu bitmap\n"); return ret; } + session->itrace_synth_opts->cpu_bitmap = rep->cpu_bitmap; } if (rep->show_threads) { @@ -718,6 +740,7 @@ int cmd_report(int argc, const char **argv) .id_index = perf_event__process_id_index, .auxtrace_info = perf_event__process_auxtrace_info, .auxtrace = perf_event__process_auxtrace, + .feature = perf_event__process_feature, .ordered_events = true, .ordering_requires_timestamps = true, }, @@ -943,6 +966,8 @@ repeat: if (has_br_stack && branch_call_mode) symbol_conf.show_branchflag_count = true; + memset(&report.brtype_stat, 0, sizeof(struct branch_type_stat)); + /* * Branch mode is a tristate: * -1 means default, so decide based on the file having branch data. @@ -988,6 +1013,10 @@ repeat: /* Force tty output for header output and per-thread stat. */ if (report.header || report.header_only || report.show_threads) use_browser = 0; + if (report.header || report.header_only) + report.tool.show_feat_hdr = SHOW_FEAT_HEADER; + if (report.show_full_info) + report.tool.show_feat_hdr = SHOW_FEAT_HEADER_FULL_INFO; if (strcmp(input_name, "-") != 0) setup_browser(true); diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 39996c53995a..322b4def8411 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -2066,7 +2066,7 @@ static void save_task_callchain(struct perf_sched *sched, if (thread__resolve_callchain(thread, cursor, evsel, sample, NULL, NULL, sched->max_stack + 2) != 0) { if (verbose > 0) - error("Failed to resolve callchain. Skipping\n"); + pr_err("Failed to resolve callchain. Skipping\n"); return; } diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 4761b0d7fcb5..3d4c3b5e1868 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -85,6 +85,9 @@ enum perf_output_field { PERF_OUTPUT_INSN = 1U << 21, PERF_OUTPUT_INSNLEN = 1U << 22, PERF_OUTPUT_BRSTACKINSN = 1U << 23, + PERF_OUTPUT_BRSTACKOFF = 1U << 24, + PERF_OUTPUT_SYNTH = 1U << 25, + PERF_OUTPUT_PHYS_ADDR = 1U << 26, }; struct output_option { @@ -115,6 +118,14 @@ struct output_option { {.str = "insn", .field = PERF_OUTPUT_INSN}, {.str = "insnlen", .field = PERF_OUTPUT_INSNLEN}, {.str = "brstackinsn", .field = PERF_OUTPUT_BRSTACKINSN}, + {.str = "brstackoff", .field = PERF_OUTPUT_BRSTACKOFF}, + {.str = "synth", .field = PERF_OUTPUT_SYNTH}, + {.str = "phys_addr", .field = PERF_OUTPUT_PHYS_ADDR}, +}; + +enum { + OUTPUT_TYPE_SYNTH = PERF_TYPE_MAX, + OUTPUT_TYPE_MAX }; /* default set to maintain compatibility with current format */ @@ -124,7 +135,7 @@ static struct { unsigned int print_ip_opts; u64 fields; u64 invalid_fields; -} output[PERF_TYPE_MAX] = { +} output[OUTPUT_TYPE_MAX] = { [PERF_TYPE_HARDWARE] = { .user_set = false, @@ -166,7 +177,8 @@ static struct { PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP | PERF_OUTPUT_SYM | PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD | PERF_OUTPUT_ADDR | - PERF_OUTPUT_DATA_SRC | PERF_OUTPUT_WEIGHT, + PERF_OUTPUT_DATA_SRC | PERF_OUTPUT_WEIGHT | + PERF_OUTPUT_PHYS_ADDR, .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, }, @@ -182,12 +194,44 @@ static struct { .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, }, + + [OUTPUT_TYPE_SYNTH] = { + .user_set = false, + + .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | + PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | + PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP | + PERF_OUTPUT_SYM | PERF_OUTPUT_DSO | + PERF_OUTPUT_SYNTH, + + .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, + }, }; +static inline int output_type(unsigned int type) +{ + switch (type) { + case PERF_TYPE_SYNTH: + return OUTPUT_TYPE_SYNTH; + default: + return type; + } +} + +static inline unsigned int attr_type(unsigned int type) +{ + switch (type) { + case OUTPUT_TYPE_SYNTH: + return PERF_TYPE_SYNTH; + default: + return type; + } +} + static bool output_set_by_user(void) { int j; - for (j = 0; j < PERF_TYPE_MAX; ++j) { + for (j = 0; j < OUTPUT_TYPE_MAX; ++j) { if (output[j].user_set) return true; } @@ -208,7 +252,7 @@ static const char *output_field2str(enum perf_output_field field) return str; } -#define PRINT_FIELD(x) (output[attr->type].fields & PERF_OUTPUT_##x) +#define PRINT_FIELD(x) (output[output_type(attr->type)].fields & PERF_OUTPUT_##x) static int perf_evsel__do_check_stype(struct perf_evsel *evsel, u64 sample_type, const char *sample_msg, @@ -216,7 +260,7 @@ static int perf_evsel__do_check_stype(struct perf_evsel *evsel, bool allow_user_set) { struct perf_event_attr *attr = &evsel->attr; - int type = attr->type; + int type = output_type(attr->type); const char *evname; if (attr->sample_type & sample_type) @@ -298,10 +342,10 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel, "selected.\n"); return -EINVAL; } - if (PRINT_FIELD(DSO) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR)) { - pr_err("Display of DSO requested but neither sample IP nor " - "sample address\nis selected. Hence, no addresses to convert " - "to DSO.\n"); + if (PRINT_FIELD(DSO) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR) && + !PRINT_FIELD(BRSTACK) && !PRINT_FIELD(BRSTACKSYM) && !PRINT_FIELD(BRSTACKOFF)) { + pr_err("Display of DSO requested but no address to convert. Select\n" + "sample IP, sample address, brstack, brstacksym, or brstackoff.\n"); return -EINVAL; } if (PRINT_FIELD(SRCLINE) && !PRINT_FIELD(IP)) { @@ -341,12 +385,17 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel, PERF_OUTPUT_IREGS)) return -EINVAL; + if (PRINT_FIELD(PHYS_ADDR) && + perf_evsel__check_stype(evsel, PERF_SAMPLE_PHYS_ADDR, "PHYS_ADDR", + PERF_OUTPUT_PHYS_ADDR)) + return -EINVAL; + return 0; } static void set_print_ip_opts(struct perf_event_attr *attr) { - unsigned int type = attr->type; + unsigned int type = output_type(attr->type); output[type].print_ip_opts = 0; if (PRINT_FIELD(IP)) @@ -374,16 +423,17 @@ static int perf_session__check_output_opt(struct perf_session *session) unsigned int j; struct perf_evsel *evsel; - for (j = 0; j < PERF_TYPE_MAX; ++j) { - evsel = perf_session__find_first_evtype(session, j); + for (j = 0; j < OUTPUT_TYPE_MAX; ++j) { + evsel = perf_session__find_first_evtype(session, attr_type(j)); /* * even if fields is set to 0 (ie., show nothing) event must * exist if user explicitly includes it on the command line */ - if (!evsel && output[j].user_set && !output[j].wildcard_set) { + if (!evsel && output[j].user_set && !output[j].wildcard_set && + j != OUTPUT_TYPE_SYNTH) { pr_err("%s events do not exist. " - "Remove corresponding -f option to proceed.\n", + "Remove corresponding -F option to proceed.\n", event_type(j)); return -1; } @@ -514,18 +564,43 @@ mispred_str(struct branch_entry *br) return br->flags.predicted ? 'P' : 'M'; } -static void print_sample_brstack(struct perf_sample *sample) +static void print_sample_brstack(struct perf_sample *sample, + struct thread *thread, + struct perf_event_attr *attr) { struct branch_stack *br = sample->branch_stack; - u64 i; + struct addr_location alf, alt; + u64 i, from, to; if (!(br && br->nr)) return; for (i = 0; i < br->nr; i++) { - printf(" 0x%"PRIx64"/0x%"PRIx64"/%c/%c/%c/%d ", - br->entries[i].from, - br->entries[i].to, + from = br->entries[i].from; + to = br->entries[i].to; + + if (PRINT_FIELD(DSO)) { + memset(&alf, 0, sizeof(alf)); + memset(&alt, 0, sizeof(alt)); + thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, from, &alf); + thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt); + } + + printf("0x%"PRIx64, from); + if (PRINT_FIELD(DSO)) { + printf("("); + map__fprintf_dsoname(alf.map, stdout); + printf(")"); + } + + printf("/0x%"PRIx64, to); + if (PRINT_FIELD(DSO)) { + printf("("); + map__fprintf_dsoname(alt.map, stdout); + printf(")"); + } + + printf("/%c/%c/%c/%d ", mispred_str( br->entries + i), br->entries[i].flags.in_tx? 'X' : '-', br->entries[i].flags.abort? 'A' : '-', @@ -534,7 +609,8 @@ static void print_sample_brstack(struct perf_sample *sample) } static void print_sample_brstacksym(struct perf_sample *sample, - struct thread *thread) + struct thread *thread, + struct perf_event_attr *attr) { struct branch_stack *br = sample->branch_stack; struct addr_location alf, alt; @@ -559,8 +635,18 @@ static void print_sample_brstacksym(struct perf_sample *sample, alt.sym = map__find_symbol(alt.map, alt.addr); symbol__fprintf_symname_offs(alf.sym, &alf, stdout); + if (PRINT_FIELD(DSO)) { + printf("("); + map__fprintf_dsoname(alf.map, stdout); + printf(")"); + } putchar('/'); symbol__fprintf_symname_offs(alt.sym, &alt, stdout); + if (PRINT_FIELD(DSO)) { + printf("("); + map__fprintf_dsoname(alt.map, stdout); + printf(")"); + } printf("/%c/%c/%c/%d ", mispred_str( br->entries + i), br->entries[i].flags.in_tx? 'X' : '-', @@ -569,6 +655,51 @@ static void print_sample_brstacksym(struct perf_sample *sample, } } +static void print_sample_brstackoff(struct perf_sample *sample, + struct thread *thread, + struct perf_event_attr *attr) +{ + struct branch_stack *br = sample->branch_stack; + struct addr_location alf, alt; + u64 i, from, to; + + if (!(br && br->nr)) + return; + + for (i = 0; i < br->nr; i++) { + + memset(&alf, 0, sizeof(alf)); + memset(&alt, 0, sizeof(alt)); + from = br->entries[i].from; + to = br->entries[i].to; + + thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, from, &alf); + if (alf.map && !alf.map->dso->adjust_symbols) + from = map__map_ip(alf.map, from); + + thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt); + if (alt.map && !alt.map->dso->adjust_symbols) + to = map__map_ip(alt.map, to); + + printf("0x%"PRIx64, from); + if (PRINT_FIELD(DSO)) { + printf("("); + map__fprintf_dsoname(alf.map, stdout); + printf(")"); + } + printf("/0x%"PRIx64, to); + if (PRINT_FIELD(DSO)) { + printf("("); + map__fprintf_dsoname(alt.map, stdout); + printf(")"); + } + printf("/%c/%c/%c/%d ", + mispred_str(br->entries + i), + br->entries[i].flags.in_tx ? 'X' : '-', + br->entries[i].flags.abort ? 'A' : '-', + br->entries[i].flags.cycles); + } +} #define MAXBB 16384UL static int grab_bb(u8 *buffer, u64 start, u64 end, @@ -906,6 +1037,7 @@ static void print_sample_bts(struct perf_sample *sample, struct machine *machine) { struct perf_event_attr *attr = &evsel->attr; + unsigned int type = output_type(attr->type); bool print_srcline_last = false; if (PRINT_FIELD(CALLINDENT)) @@ -913,7 +1045,7 @@ static void print_sample_bts(struct perf_sample *sample, /* print branch_from information */ if (PRINT_FIELD(IP)) { - unsigned int print_opts = output[attr->type].print_ip_opts; + unsigned int print_opts = output[type].print_ip_opts; struct callchain_cursor *cursor = NULL; if (symbol_conf.use_callchain && sample->callchain && @@ -936,7 +1068,7 @@ static void print_sample_bts(struct perf_sample *sample, /* print branch_to information */ if (PRINT_FIELD(ADDR) || ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) && - !output[attr->type].user_set)) { + !output[type].user_set)) { printf(" => "); print_sample_addr(sample, thread, attr); } @@ -1079,6 +1211,127 @@ static void print_sample_bpf_output(struct perf_sample *sample) (char *)(sample->raw_data)); } +static void print_sample_spacing(int len, int spacing) +{ + if (len > 0 && len < spacing) + printf("%*s", spacing - len, ""); +} + +static void print_sample_pt_spacing(int len) +{ + print_sample_spacing(len, 34); +} + +static void print_sample_synth_ptwrite(struct perf_sample *sample) +{ + struct perf_synth_intel_ptwrite *data = perf_sample__synth_ptr(sample); + int len; + + if (perf_sample__bad_synth_size(sample, *data)) + return; + + len = printf(" IP: %u payload: %#" PRIx64 " ", + data->ip, le64_to_cpu(data->payload)); + print_sample_pt_spacing(len); +} + +static void print_sample_synth_mwait(struct perf_sample *sample) +{ + struct perf_synth_intel_mwait *data = perf_sample__synth_ptr(sample); + int len; + + if (perf_sample__bad_synth_size(sample, *data)) + return; + + len = printf(" hints: %#x extensions: %#x ", + data->hints, data->extensions); + print_sample_pt_spacing(len); +} + +static void print_sample_synth_pwre(struct perf_sample *sample) +{ + struct perf_synth_intel_pwre *data = perf_sample__synth_ptr(sample); + int len; + + if (perf_sample__bad_synth_size(sample, *data)) + return; + + len = printf(" hw: %u cstate: %u sub-cstate: %u ", + data->hw, data->cstate, data->subcstate); + print_sample_pt_spacing(len); +} + +static void print_sample_synth_exstop(struct perf_sample *sample) +{ + struct perf_synth_intel_exstop *data = perf_sample__synth_ptr(sample); + int len; + + if (perf_sample__bad_synth_size(sample, *data)) + return; + + len = printf(" IP: %u ", data->ip); + print_sample_pt_spacing(len); +} + +static void print_sample_synth_pwrx(struct perf_sample *sample) +{ + struct perf_synth_intel_pwrx *data = perf_sample__synth_ptr(sample); + int len; + + if (perf_sample__bad_synth_size(sample, *data)) + return; + + len = printf(" deepest cstate: %u last cstate: %u wake reason: %#x ", + data->deepest_cstate, data->last_cstate, + data->wake_reason); + print_sample_pt_spacing(len); +} + +static void print_sample_synth_cbr(struct perf_sample *sample) +{ + struct perf_synth_intel_cbr *data = perf_sample__synth_ptr(sample); + unsigned int percent, freq; + int len; + + if (perf_sample__bad_synth_size(sample, *data)) + return; + + freq = (le32_to_cpu(data->freq) + 500) / 1000; + len = printf(" cbr: %2u freq: %4u MHz ", data->cbr, freq); + if (data->max_nonturbo) { + percent = (5 + (1000 * data->cbr) / data->max_nonturbo) / 10; + len += printf("(%3u%%) ", percent); + } + print_sample_pt_spacing(len); +} + +static void print_sample_synth(struct perf_sample *sample, + struct perf_evsel *evsel) +{ + switch (evsel->attr.config) { + case PERF_SYNTH_INTEL_PTWRITE: + print_sample_synth_ptwrite(sample); + break; + case PERF_SYNTH_INTEL_MWAIT: + print_sample_synth_mwait(sample); + break; + case PERF_SYNTH_INTEL_PWRE: + print_sample_synth_pwre(sample); + break; + case PERF_SYNTH_INTEL_EXSTOP: + print_sample_synth_exstop(sample); + break; + case PERF_SYNTH_INTEL_PWRX: + print_sample_synth_pwrx(sample); + break; + case PERF_SYNTH_INTEL_CBR: + print_sample_synth_cbr(sample); + break; + default: + break; + } +} + struct perf_script { struct perf_tool tool; struct perf_session *session; @@ -1132,8 +1385,9 @@ static void process_event(struct perf_script *script, { struct thread *thread = al->thread; struct perf_event_attr *attr = &evsel->attr; + unsigned int type = output_type(attr->type); - if (output[attr->type].fields == 0) + if (output[type].fields == 0) return; print_sample_start(sample, thread, evsel); @@ -1162,6 +1416,10 @@ static void process_event(struct perf_script *script, if (PRINT_FIELD(TRACE)) event_format__print(evsel->tp_format, sample->cpu, sample->raw_data, sample->raw_size); + + if (attr->type == PERF_TYPE_SYNTH && PRINT_FIELD(SYNTH)) + print_sample_synth(sample, evsel); + if (PRINT_FIELD(ADDR)) print_sample_addr(sample, thread, attr); @@ -1180,20 +1438,25 @@ static void process_event(struct perf_script *script, cursor = &callchain_cursor; putchar(cursor ? '\n' : ' '); - sample__fprintf_sym(sample, al, 0, output[attr->type].print_ip_opts, cursor, stdout); + sample__fprintf_sym(sample, al, 0, output[type].print_ip_opts, cursor, stdout); } if (PRINT_FIELD(IREGS)) print_sample_iregs(sample, attr); if (PRINT_FIELD(BRSTACK)) - print_sample_brstack(sample); + print_sample_brstack(sample, thread, attr); else if (PRINT_FIELD(BRSTACKSYM)) - print_sample_brstacksym(sample, thread); + print_sample_brstacksym(sample, thread, attr); + else if (PRINT_FIELD(BRSTACKOFF)) + print_sample_brstackoff(sample, thread, attr); if (perf_evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT)) print_sample_bpf_output(sample); print_insn(sample, attr, thread, machine); + + if (PRINT_FIELD(PHYS_ADDR)) + printf("%16" PRIx64, sample->phys_addr); printf("\n"); } @@ -1325,7 +1588,8 @@ static int process_attr(struct perf_tool *tool, union perf_event *event, evlist = *pevlist; evsel = perf_evlist__last(*pevlist); - if (evsel->attr.type >= PERF_TYPE_MAX) + if (evsel->attr.type >= PERF_TYPE_MAX && + evsel->attr.type != PERF_TYPE_SYNTH) return 0; evlist__for_each_entry(evlist, pos) { @@ -1727,6 +1991,7 @@ static int parse_output_fields(const struct option *opt __maybe_unused, int rc = 0; char *str = strdup(arg); int type = -1; + enum { DEFAULT, SET, ADD, REMOVE } change = DEFAULT; if (!str) return -ENOMEM; @@ -1749,6 +2014,8 @@ static int parse_output_fields(const struct option *opt __maybe_unused, type = PERF_TYPE_RAW; else if (!strcmp(str, "break")) type = PERF_TYPE_BREAKPOINT; + else if (!strcmp(str, "synth")) + type = OUTPUT_TYPE_SYNTH; else { fprintf(stderr, "Invalid event type in field string.\n"); rc = -EINVAL; @@ -1772,23 +2039,44 @@ static int parse_output_fields(const struct option *opt __maybe_unused, goto out; } + /* Don't override defaults for +- */ + if (strchr(str, '+') || strchr(str, '-')) + goto parse; + if (output_set_by_user()) pr_warning("Overriding previous field request for all events.\n"); - for (j = 0; j < PERF_TYPE_MAX; ++j) { + for (j = 0; j < OUTPUT_TYPE_MAX; ++j) { output[j].fields = 0; output[j].user_set = true; output[j].wildcard_set = true; } } +parse: for (tok = strtok_r(tok, ",", &strtok_saveptr); tok; tok = strtok_r(NULL, ",", &strtok_saveptr)) { + if (*tok == '+') { + if (change == SET) + goto out_badmix; + change = ADD; + tok++; + } else if (*tok == '-') { + if (change == SET) + goto out_badmix; + change = REMOVE; + tok++; + } else { + if (change != SET && change != DEFAULT) + goto out_badmix; + change = SET; + } + for (i = 0; i < imax; ++i) { if (strcmp(tok, all_output_options[i].str) == 0) break; } if (i == imax && strcmp(tok, "flags") == 0) { - print_flags = true; + print_flags = change == REMOVE ? false : true; continue; } if (i == imax) { @@ -1801,12 +2089,16 @@ static int parse_output_fields(const struct option *opt __maybe_unused, /* add user option to all events types for * which it is valid */ - for (j = 0; j < PERF_TYPE_MAX; ++j) { + for (j = 0; j < OUTPUT_TYPE_MAX; ++j) { if (output[j].invalid_fields & all_output_options[i].field) { pr_warning("\'%s\' not valid for %s events. Ignoring.\n", all_output_options[i].str, event_type(j)); - } else - output[j].fields |= all_output_options[i].field; + } else { + if (change == REMOVE) + output[j].fields &= ~all_output_options[i].field; + else + output[j].fields |= all_output_options[i].field; + } } } else { if (output[type].invalid_fields & all_output_options[i].field) { @@ -1826,7 +2118,11 @@ static int parse_output_fields(const struct option *opt __maybe_unused, "Events will not be displayed.\n", event_type(type)); } } + goto out; +out_badmix: + fprintf(stderr, "Cannot mix +-field with overridden fields\n"); + rc = -EINVAL; out: free(str); return rc; @@ -1914,16 +2210,11 @@ static struct script_desc *script_desc__findnew(const char *name) s = script_desc__new(name); if (!s) - goto out_delete_desc; + return NULL; script_desc__add(s); return s; - -out_delete_desc: - script_desc__delete(s); - - return NULL; } static const char *ends_with(const char *str, const char *suffix) @@ -2397,6 +2688,7 @@ int cmd_script(int argc, const char **argv) .attr = process_attr, .event_update = perf_event__process_event_update, .tracing_data = perf_event__process_tracing_data, + .feature = perf_event__process_feature, .build_id = perf_event__process_build_id, .id_index = perf_event__process_id_index, .auxtrace_info = perf_event__process_auxtrace_info, @@ -2444,10 +2736,11 @@ int cmd_script(int argc, const char **argv) symbol__config_symfs), OPT_CALLBACK('F', "fields", NULL, "str", "comma separated output fields prepend with 'type:'. " - "Valid types: hw,sw,trace,raw. " + "+field to add and -field to remove." + "Valid types: hw,sw,trace,raw,synth. " "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso," "addr,symoff,period,iregs,brstack,brstacksym,flags," - "bpf-output,callindent,insn,insnlen,brstackinsn", + "bpf-output,callindent,insn,insnlen,brstackinsn,synth,phys_addr", parse_output_fields), OPT_BOOLEAN('a', "all-cpus", &system_wide, "system-wide collection from all CPUs"), @@ -2686,10 +2979,13 @@ int cmd_script(int argc, const char **argv) return -1; if (header || header_only) { + script.tool.show_feat_hdr = SHOW_FEAT_HEADER; perf_session__fprintf_info(session, stdout, show_full_info); if (header_only) goto out_delete; } + if (show_full_info) + script.tool.show_feat_hdr = SHOW_FEAT_HEADER_FULL_INFO; if (symbol__init(&session->header.env) < 0) goto out_delete; @@ -2706,6 +3002,7 @@ int cmd_script(int argc, const char **argv) err = perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap); if (err < 0) goto out_delete; + itrace_synth_opts.cpu_bitmap = cpu_bitmap; } if (!no_callchain) diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index ad9324d1daf9..69523ed55894 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -86,6 +86,7 @@ #define DEFAULT_SEPARATOR " " #define CNTR_NOT_SUPPORTED "<not supported>" #define CNTR_NOT_COUNTED "<not counted>" +#define FREEZE_ON_SMI_PATH "devices/cpu/freeze_on_smi" static void print_counters(struct timespec *ts, int argc, const char **argv); @@ -122,6 +123,14 @@ static const char * topdown_attrs[] = { NULL, }; +static const char *smi_cost_attrs = { + "{" + "msr/aperf/," + "msr/smi/," + "cycles" + "}" +}; + static struct perf_evlist *evsel_list; static struct target target = { @@ -137,6 +146,8 @@ static bool null_run = false; static int detailed_run = 0; static bool transaction_run; static bool topdown_run = false; +static bool smi_cost = false; +static bool smi_reset = false; static bool big_num = true; static int big_num_opt = -1; static const char *csv_sep = NULL; @@ -202,10 +213,20 @@ static void perf_stat__reset_stats(void) static int create_perf_stat_counter(struct perf_evsel *evsel) { struct perf_event_attr *attr = &evsel->attr; + struct perf_evsel *leader = evsel->leader; - if (stat_config.scale) + if (stat_config.scale) { attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED | PERF_FORMAT_TOTAL_TIME_RUNNING; + } + + /* + * The event is part of non trivial group, let's enable + * the group read (for leader) and ID retrieval for all + * members. + */ + if (leader->nr_members > 1) + attr->read_format |= PERF_FORMAT_ID|PERF_FORMAT_GROUP; attr->inherit = !no_inherit; @@ -322,13 +343,21 @@ static int read_counter(struct perf_evsel *counter) struct perf_counts_values *count; count = perf_counts(counter->counts, cpu, thread); - if (perf_evsel__read(counter, cpu, thread, count)) { + + /* + * The leader's group read loads data into its group members + * (via perf_evsel__read_counter) and sets threir count->loaded. + */ + if (!count->loaded && + perf_evsel__read_counter(counter, cpu, thread)) { counter->counts->scaled = -1; perf_counts(counter->counts, cpu, thread)->ena = 0; perf_counts(counter->counts, cpu, thread)->run = 0; return -1; } + count->loaded = false; + if (STAT_RECORD) { if (perf_evsel__write_stat_event(counter, cpu, thread, count)) { pr_err("failed to write stat event\n"); @@ -548,6 +577,11 @@ static int store_counter_ids(struct perf_evsel *counter) return __store_counter_ids(counter, cpus, threads); } +static bool perf_evsel__should_store_id(struct perf_evsel *counter) +{ + return STAT_RECORD || counter->attr.read_format & PERF_FORMAT_ID; +} + static int __run_perf_stat(int argc, const char **argv) { int interval = stat_config.interval; @@ -620,19 +654,20 @@ try_again: if (l > unit_width) unit_width = l; - if (STAT_RECORD && store_counter_ids(counter)) + if (perf_evsel__should_store_id(counter) && + store_counter_ids(counter)) return -1; } if (perf_evlist__apply_filters(evsel_list, &counter)) { - error("failed to set filter \"%s\" on event %s with %d (%s)\n", + pr_err("failed to set filter \"%s\" on event %s with %d (%s)\n", counter->filter, perf_evsel__name(counter), errno, str_error_r(errno, msg, sizeof(msg))); return -1; } if (perf_evlist__apply_drv_configs(evsel_list, &counter, &err_term)) { - error("failed to set config \"%s\" on event %s with %d (%s)\n", + pr_err("failed to set config \"%s\" on event %s with %d (%s)\n", err_term->val.drv_cfg, perf_evsel__name(counter), errno, str_error_r(errno, msg, sizeof(msg))); return -1; @@ -672,7 +707,7 @@ try_again: process_interval(); } } - wait(&status); + waitpid(child_pid, &status, 0); if (workload_exec_errno) { const char *emsg = str_error_r(workload_exec_errno, msg, sizeof(msg)); @@ -1222,7 +1257,7 @@ static bool collect_data(struct perf_evsel *counter, if (counter->merged_stat) return false; cb(counter, data, true); - if (!no_merge) + if (!no_merge && counter->auto_merge_stats) collect_all_aliases(counter, cb, data); return true; } @@ -1782,6 +1817,8 @@ static const struct option stat_options[] = { "Only print computed metrics. No raw values", enable_metric_only), OPT_BOOLEAN(0, "topdown", &topdown_run, "measure topdown level 1 statistics"), + OPT_BOOLEAN(0, "smi-cost", &smi_cost, + "measure SMI cost"), OPT_END() }; @@ -2160,6 +2197,39 @@ static int add_default_attributes(void) return 0; } + if (smi_cost) { + int smi; + + if (sysfs__read_int(FREEZE_ON_SMI_PATH, &smi) < 0) { + fprintf(stderr, "freeze_on_smi is not supported.\n"); + return -1; + } + + if (!smi) { + if (sysfs__write_int(FREEZE_ON_SMI_PATH, 1) < 0) { + fprintf(stderr, "Failed to set freeze_on_smi.\n"); + return -1; + } + smi_reset = true; + } + + if (pmu_have_event("msr", "aperf") && + pmu_have_event("msr", "smi")) { + if (!force_metric_only) + metric_only = true; + err = parse_events(evsel_list, smi_cost_attrs, NULL); + } else { + fprintf(stderr, "To measure SMI cost, it needs " + "msr/aperf/, msr/smi/ and cpu/cycles/ support\n"); + return -1; + } + if (err) { + fprintf(stderr, "Cannot set up SMI cost events\n"); + return -1; + } + return 0; + } + if (topdown_run) { char *str = NULL; bool warn = false; @@ -2742,6 +2812,9 @@ int cmd_stat(int argc, const char **argv) perf_stat__exit_aggr_mode(); perf_evlist__free_stats(evsel_list); out: + if (smi_cost && smi_reset) + sysfs__write_int(FREEZE_ON_SMI_PATH, 0); + perf_evlist__delete(evsel_list); return status; } diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 10b6362ca0bf..ee954bde7e3e 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -134,7 +134,7 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he) return err; } - err = symbol__disassemble(sym, map, NULL, 0); + err = symbol__disassemble(sym, map, NULL, 0, NULL, NULL); if (err == 0) { out_assign: top->sym_filter_entry = he; @@ -183,6 +183,7 @@ static void ui__warn_map_erange(struct map *map, struct symbol *sym, u64 ip) static void perf_top__record_precise_ip(struct perf_top *top, struct hist_entry *he, + struct perf_sample *sample, int counter, u64 ip) { struct annotation *notes; @@ -199,7 +200,7 @@ static void perf_top__record_precise_ip(struct perf_top *top, if (pthread_mutex_trylock(¬es->lock)) return; - err = hist_entry__inc_addr_samples(he, counter, ip); + err = hist_entry__inc_addr_samples(he, sample, counter, ip); pthread_mutex_unlock(¬es->lock); @@ -586,6 +587,13 @@ static void *display_thread_tui(void *arg) .refresh = top->delay_secs, }; + /* In order to read symbols from other namespaces perf to needs to call + * setns(2). This isn't permitted if the struct_fs has multiple users. + * unshare(2) the fs so that we may continue to setns into namespaces + * that we're observing. + */ + unshare(CLONE_FS); + perf_top__sort_new_samples(top); /* @@ -627,6 +635,13 @@ static void *display_thread(void *arg) struct perf_top *top = arg; int delay_msecs, c; + /* In order to read symbols from other namespaces perf to needs to call + * setns(2). This isn't permitted if the struct_fs has multiple users. + * unshare(2) the fs so that we may continue to setns into namespaces + * that we're observing. + */ + unshare(CLONE_FS); + display_setup_sig(); pthread__unblock_sigwinch(); repeat: @@ -671,7 +686,7 @@ static int hist_iter__top_callback(struct hist_entry_iter *iter, struct perf_evsel *evsel = iter->evsel; if (perf_hpp_list.sym && single) - perf_top__record_precise_ip(top, he, evsel->idx, al->addr); + perf_top__record_precise_ip(top, he, iter->sample, evsel->idx, al->addr); hist__account_cycles(iter->sample->branch_stack, al, iter->sample, !(top->record_opts.branch_stack & PERF_SAMPLE_BRANCH_ANY)); @@ -958,7 +973,7 @@ static int __cmd_top(struct perf_top *top) ret = perf_evlist__apply_drv_configs(evlist, &pos, &err_term); if (ret) { - error("failed to set config \"%s\" on event %s with %d (%s)\n", + pr_err("failed to set config \"%s\" on event %s with %d (%s)\n", err_term->val.drv_cfg, perf_evsel__name(pos), errno, str_error_r(errno, msg, sizeof(msg))); goto out_delete; @@ -1205,6 +1220,7 @@ int cmd_top(int argc, const char **argv) "Show raw trace event output (do not use print fmt or plugins)"), OPT_BOOLEAN(0, "hierarchy", &symbol_conf.report_hierarchy, "Show entries in a hierarchy"), + OPT_BOOLEAN(0, "force", &symbol_conf.force, "don't complain, do it"), OPT_END() }; const char * const top_usage[] = { diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 4b2a5d298197..771ddab94bb0 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -64,6 +64,10 @@ # define O_CLOEXEC 02000000 #endif +#ifndef F_LINUX_SPECIFIC_BASE +# define F_LINUX_SPECIFIC_BASE 1024 +#endif + struct trace { struct perf_tool tool; struct syscalltbl *sctbl; @@ -279,34 +283,21 @@ out_delete: ({ struct syscall_tp *fields = evsel->priv; \ fields->name.pointer(&fields->name, sample); }) -struct strarray { - int offset; - int nr_entries; - const char **entries; -}; +size_t strarray__scnprintf(struct strarray *sa, char *bf, size_t size, const char *intfmt, int val) +{ + int idx = val - sa->offset; -#define DEFINE_STRARRAY(array) struct strarray strarray__##array = { \ - .nr_entries = ARRAY_SIZE(array), \ - .entries = array, \ -} + if (idx < 0 || idx >= sa->nr_entries) + return scnprintf(bf, size, intfmt, val); -#define DEFINE_STRARRAY_OFFSET(array, off) struct strarray strarray__##array = { \ - .offset = off, \ - .nr_entries = ARRAY_SIZE(array), \ - .entries = array, \ + return scnprintf(bf, size, "%s", sa->entries[idx]); } static size_t __syscall_arg__scnprintf_strarray(char *bf, size_t size, const char *intfmt, struct syscall_arg *arg) { - struct strarray *sa = arg->parm; - int idx = arg->val - sa->offset; - - if (idx < 0 || idx >= sa->nr_entries) - return scnprintf(bf, size, intfmt, arg->val); - - return scnprintf(bf, size, "%s", sa->entries[idx]); + return strarray__scnprintf(arg->parm, bf, size, intfmt, arg->val); } static size_t syscall_arg__scnprintf_strarray(char *bf, size_t size, @@ -317,24 +308,35 @@ static size_t syscall_arg__scnprintf_strarray(char *bf, size_t size, #define SCA_STRARRAY syscall_arg__scnprintf_strarray -#if defined(__i386__) || defined(__x86_64__) -/* - * FIXME: Make this available to all arches as soon as the ioctl beautifier - * gets rewritten to support all arches. - */ -static size_t syscall_arg__scnprintf_strhexarray(char *bf, size_t size, - struct syscall_arg *arg) -{ - return __syscall_arg__scnprintf_strarray(bf, size, "%#x", arg); +struct strarrays { + int nr_entries; + struct strarray **entries; +}; + +#define DEFINE_STRARRAYS(array) struct strarrays strarrays__##array = { \ + .nr_entries = ARRAY_SIZE(array), \ + .entries = array, \ } -#define SCA_STRHEXARRAY syscall_arg__scnprintf_strhexarray -#endif /* defined(__i386__) || defined(__x86_64__) */ +size_t syscall_arg__scnprintf_strarrays(char *bf, size_t size, + struct syscall_arg *arg) +{ + struct strarrays *sas = arg->parm; + int i; -static size_t syscall_arg__scnprintf_fd(char *bf, size_t size, - struct syscall_arg *arg); + for (i = 0; i < sas->nr_entries; ++i) { + struct strarray *sa = sas->entries[i]; + int idx = arg->val - sa->offset; -#define SCA_FD syscall_arg__scnprintf_fd + if (idx >= 0 && idx < sa->nr_entries) { + if (sa->entries[idx] == NULL) + break; + return scnprintf(bf, size, "%s", sa->entries[idx]); + } + } + + return scnprintf(bf, size, "%d", arg->val); +} #ifndef AT_FDCWD #define AT_FDCWD -100 @@ -358,21 +360,20 @@ static size_t syscall_arg__scnprintf_close_fd(char *bf, size_t size, #define SCA_CLOSE_FD syscall_arg__scnprintf_close_fd -static size_t syscall_arg__scnprintf_hex(char *bf, size_t size, - struct syscall_arg *arg) +size_t syscall_arg__scnprintf_hex(char *bf, size_t size, struct syscall_arg *arg) { return scnprintf(bf, size, "%#lx", arg->val); } -#define SCA_HEX syscall_arg__scnprintf_hex - -static size_t syscall_arg__scnprintf_int(char *bf, size_t size, - struct syscall_arg *arg) +size_t syscall_arg__scnprintf_int(char *bf, size_t size, struct syscall_arg *arg) { return scnprintf(bf, size, "%d", arg->val); } -#define SCA_INT syscall_arg__scnprintf_int +size_t syscall_arg__scnprintf_long(char *bf, size_t size, struct syscall_arg *arg) +{ + return scnprintf(bf, size, "%ld", arg->val); +} static const char *bpf_cmd[] = { "MAP_CREATE", "MAP_LOOKUP_ELEM", "MAP_UPDATE_ELEM", "MAP_DELETE_ELEM", @@ -407,12 +408,27 @@ static DEFINE_STRARRAY(whences); static const char *fcntl_cmds[] = { "DUPFD", "GETFD", "SETFD", "GETFL", "SETFL", "GETLK", "SETLK", - "SETLKW", "SETOWN", "GETOWN", "SETSIG", "GETSIG", "F_GETLK64", - "F_SETLK64", "F_SETLKW64", "F_SETOWN_EX", "F_GETOWN_EX", - "F_GETOWNER_UIDS", + "SETLKW", "SETOWN", "GETOWN", "SETSIG", "GETSIG", "GETLK64", + "SETLK64", "SETLKW64", "SETOWN_EX", "GETOWN_EX", + "GETOWNER_UIDS", }; static DEFINE_STRARRAY(fcntl_cmds); +static const char *fcntl_linux_specific_cmds[] = { + "SETLEASE", "GETLEASE", "NOTIFY", [5] = "CANCELLK", "DUPFD_CLOEXEC", + "SETPIPE_SZ", "GETPIPE_SZ", "ADD_SEALS", "GET_SEALS", + "GET_RW_HINT", "SET_RW_HINT", "GET_FILE_RW_HINT", "SET_FILE_RW_HINT", +}; + +static DEFINE_STRARRAY_OFFSET(fcntl_linux_specific_cmds, F_LINUX_SPECIFIC_BASE); + +static struct strarray *fcntl_cmds_arrays[] = { + &strarray__fcntl_cmds, + &strarray__fcntl_linux_specific_cmds, +}; + +static DEFINE_STRARRAYS(fcntl_cmds_arrays); + static const char *rlimit_resources[] = { "CPU", "FSIZE", "DATA", "STACK", "CORE", "RSS", "NPROC", "NOFILE", "MEMLOCK", "AS", "LOCKS", "SIGPENDING", "MSGQUEUE", "NICE", "RTPRIO", @@ -495,33 +511,6 @@ static size_t syscall_arg__scnprintf_pipe_flags(char *bf, size_t size, #define SCA_PIPE_FLAGS syscall_arg__scnprintf_pipe_flags -#if defined(__i386__) || defined(__x86_64__) -/* - * FIXME: Make this available to all arches. - */ -#define TCGETS 0x5401 - -static const char *tioctls[] = { - "TCGETS", "TCSETS", "TCSETSW", "TCSETSF", "TCGETA", "TCSETA", "TCSETAW", - "TCSETAF", "TCSBRK", "TCXONC", "TCFLSH", "TIOCEXCL", "TIOCNXCL", - "TIOCSCTTY", "TIOCGPGRP", "TIOCSPGRP", "TIOCOUTQ", "TIOCSTI", - "TIOCGWINSZ", "TIOCSWINSZ", "TIOCMGET", "TIOCMBIS", "TIOCMBIC", - "TIOCMSET", "TIOCGSOFTCAR", "TIOCSSOFTCAR", "FIONREAD", "TIOCLINUX", - "TIOCCONS", "TIOCGSERIAL", "TIOCSSERIAL", "TIOCPKT", "FIONBIO", - "TIOCNOTTY", "TIOCSETD", "TIOCGETD", "TCSBRKP", [0x27] = "TIOCSBRK", - "TIOCCBRK", "TIOCGSID", "TCGETS2", "TCSETS2", "TCSETSW2", "TCSETSF2", - "TIOCGRS485", "TIOCSRS485", "TIOCGPTN", "TIOCSPTLCK", - "TIOCGDEV||TCGETX", "TCSETX", "TCSETXF", "TCSETXW", "TIOCSIG", - "TIOCVHANGUP", "TIOCGPKT", "TIOCGPTLCK", "TIOCGEXCL", - [0x50] = "FIONCLEX", "FIOCLEX", "FIOASYNC", "TIOCSERCONFIG", - "TIOCSERGWILD", "TIOCSERSWILD", "TIOCGLCKTRMIOS", "TIOCSLCKTRMIOS", - "TIOCSERGSTRUCT", "TIOCSERGETLSR", "TIOCSERGETMULTI", "TIOCSERSETMULTI", - "TIOCMIWAIT", "TIOCGICOUNT", [0x60] = "FIOQSIZE", -}; - -static DEFINE_STRARRAY_OFFSET(tioctls, 0x5401); -#endif /* defined(__i386__) || defined(__x86_64__) */ - #ifndef GRND_NONBLOCK #define GRND_NONBLOCK 0x0001 #endif @@ -552,9 +541,9 @@ static size_t syscall_arg__scnprintf_getrandom_flags(char *bf, size_t size, #define SCA_GETRANDOM_FLAGS syscall_arg__scnprintf_getrandom_flags -#define STRARRAY(arg, name, array) \ - .arg_scnprintf = { [arg] = SCA_STRARRAY, }, \ - .arg_parm = { [arg] = &strarray__##array, } +#define STRARRAY(name, array) \ + { .scnprintf = SCA_STRARRAY, \ + .parm = &strarray__##array, } #include "trace/beauty/eventfd.c" #include "trace/beauty/flock.c" @@ -571,242 +560,219 @@ static size_t syscall_arg__scnprintf_getrandom_flags(char *bf, size_t size, #include "trace/beauty/socket_type.c" #include "trace/beauty/waitid_options.c" +struct syscall_arg_fmt { + size_t (*scnprintf)(char *bf, size_t size, struct syscall_arg *arg); + void *parm; + const char *name; + bool show_zero; +}; + static struct syscall_fmt { const char *name; const char *alias; - size_t (*arg_scnprintf[6])(char *bf, size_t size, struct syscall_arg *arg); - void *arg_parm[6]; - bool errmsg; + struct syscall_arg_fmt arg[6]; + u8 nr_args; bool errpid; bool timeout; bool hexret; } syscall_fmts[] = { - { .name = "access", .errmsg = true, - .arg_scnprintf = { [1] = SCA_ACCMODE, /* mode */ }, }, - { .name = "arch_prctl", .errmsg = true, .alias = "prctl", }, - { .name = "bpf", .errmsg = true, STRARRAY(0, cmd, bpf_cmd), }, + { .name = "access", + .arg = { [1] = { .scnprintf = SCA_ACCMODE, /* mode */ }, }, }, + { .name = "arch_prctl", .alias = "prctl", }, + { .name = "bpf", + .arg = { [0] = STRARRAY(cmd, bpf_cmd), }, }, { .name = "brk", .hexret = true, - .arg_scnprintf = { [0] = SCA_HEX, /* brk */ }, }, - { .name = "chdir", .errmsg = true, }, - { .name = "chmod", .errmsg = true, }, - { .name = "chroot", .errmsg = true, }, - { .name = "clock_gettime", .errmsg = true, STRARRAY(0, clk_id, clockid), }, - { .name = "clone", .errpid = true, }, - { .name = "close", .errmsg = true, - .arg_scnprintf = { [0] = SCA_CLOSE_FD, /* fd */ }, }, - { .name = "connect", .errmsg = true, }, - { .name = "creat", .errmsg = true, }, - { .name = "dup", .errmsg = true, }, - { .name = "dup2", .errmsg = true, }, - { .name = "dup3", .errmsg = true, }, - { .name = "epoll_ctl", .errmsg = true, STRARRAY(1, op, epoll_ctl_ops), }, - { .name = "eventfd2", .errmsg = true, - .arg_scnprintf = { [1] = SCA_EFD_FLAGS, /* flags */ }, }, - { .name = "faccessat", .errmsg = true, }, - { .name = "fadvise64", .errmsg = true, }, - { .name = "fallocate", .errmsg = true, }, - { .name = "fchdir", .errmsg = true, }, - { .name = "fchmod", .errmsg = true, }, - { .name = "fchmodat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, - { .name = "fchown", .errmsg = true, }, - { .name = "fchownat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, - { .name = "fcntl", .errmsg = true, - .arg_scnprintf = { [1] = SCA_STRARRAY, /* cmd */ }, - .arg_parm = { [1] = &strarray__fcntl_cmds, /* cmd */ }, }, - { .name = "fdatasync", .errmsg = true, }, - { .name = "flock", .errmsg = true, - .arg_scnprintf = { [1] = SCA_FLOCK, /* cmd */ }, }, - { .name = "fsetxattr", .errmsg = true, }, - { .name = "fstat", .errmsg = true, .alias = "newfstat", }, - { .name = "fstatat", .errmsg = true, .alias = "newfstatat", }, - { .name = "fstatfs", .errmsg = true, }, - { .name = "fsync", .errmsg = true, }, - { .name = "ftruncate", .errmsg = true, }, - { .name = "futex", .errmsg = true, - .arg_scnprintf = { [1] = SCA_FUTEX_OP, /* op */ }, }, - { .name = "futimesat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, - { .name = "getdents", .errmsg = true, }, - { .name = "getdents64", .errmsg = true, }, - { .name = "getitimer", .errmsg = true, STRARRAY(0, which, itimers), }, + .arg = { [0] = { .scnprintf = SCA_HEX, /* brk */ }, }, }, + { .name = "clock_gettime", + .arg = { [0] = STRARRAY(clk_id, clockid), }, }, + { .name = "clone", .errpid = true, .nr_args = 5, + .arg = { [0] = { .name = "flags", .scnprintf = SCA_CLONE_FLAGS, }, + [1] = { .name = "child_stack", .scnprintf = SCA_HEX, }, + [2] = { .name = "parent_tidptr", .scnprintf = SCA_HEX, }, + [3] = { .name = "child_tidptr", .scnprintf = SCA_HEX, }, + [4] = { .name = "tls", .scnprintf = SCA_HEX, }, }, }, + { .name = "close", + .arg = { [0] = { .scnprintf = SCA_CLOSE_FD, /* fd */ }, }, }, + { .name = "epoll_ctl", + .arg = { [1] = STRARRAY(op, epoll_ctl_ops), }, }, + { .name = "eventfd2", + .arg = { [1] = { .scnprintf = SCA_EFD_FLAGS, /* flags */ }, }, }, + { .name = "fchmodat", + .arg = { [0] = { .scnprintf = SCA_FDAT, /* fd */ }, }, }, + { .name = "fchownat", + .arg = { [0] = { .scnprintf = SCA_FDAT, /* fd */ }, }, }, + { .name = "fcntl", + .arg = { [1] = { .scnprintf = SCA_FCNTL_CMD, /* cmd */ + .parm = &strarrays__fcntl_cmds_arrays, + .show_zero = true, }, + [2] = { .scnprintf = SCA_FCNTL_ARG, /* arg */ }, }, }, + { .name = "flock", + .arg = { [1] = { .scnprintf = SCA_FLOCK, /* cmd */ }, }, }, + { .name = "fstat", .alias = "newfstat", }, + { .name = "fstatat", .alias = "newfstatat", }, + { .name = "futex", + .arg = { [1] = { .scnprintf = SCA_FUTEX_OP, /* op */ }, }, }, + { .name = "futimesat", + .arg = { [0] = { .scnprintf = SCA_FDAT, /* fd */ }, }, }, + { .name = "getitimer", + .arg = { [0] = STRARRAY(which, itimers), }, }, { .name = "getpid", .errpid = true, }, { .name = "getpgid", .errpid = true, }, { .name = "getppid", .errpid = true, }, - { .name = "getrandom", .errmsg = true, - .arg_scnprintf = { [2] = SCA_GETRANDOM_FLAGS, /* flags */ }, }, - { .name = "getrlimit", .errmsg = true, STRARRAY(0, resource, rlimit_resources), }, - { .name = "getxattr", .errmsg = true, }, - { .name = "inotify_add_watch", .errmsg = true, }, - { .name = "ioctl", .errmsg = true, - .arg_scnprintf = { + { .name = "getrandom", + .arg = { [2] = { .scnprintf = SCA_GETRANDOM_FLAGS, /* flags */ }, }, }, + { .name = "getrlimit", + .arg = { [0] = STRARRAY(resource, rlimit_resources), }, }, + { .name = "ioctl", + .arg = { #if defined(__i386__) || defined(__x86_64__) /* * FIXME: Make this available to all arches. */ - [1] = SCA_STRHEXARRAY, /* cmd */ - [2] = SCA_HEX, /* arg */ }, - .arg_parm = { [1] = &strarray__tioctls, /* cmd */ }, }, + [1] = { .scnprintf = SCA_IOCTL_CMD, /* cmd */ }, + [2] = { .scnprintf = SCA_HEX, /* arg */ }, }, }, #else - [2] = SCA_HEX, /* arg */ }, }, + [2] = { .scnprintf = SCA_HEX, /* arg */ }, }, }, #endif - { .name = "keyctl", .errmsg = true, STRARRAY(0, option, keyctl_options), }, - { .name = "kill", .errmsg = true, - .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, }, - { .name = "lchown", .errmsg = true, }, - { .name = "lgetxattr", .errmsg = true, }, - { .name = "linkat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, - { .name = "listxattr", .errmsg = true, }, - { .name = "llistxattr", .errmsg = true, }, - { .name = "lremovexattr", .errmsg = true, }, - { .name = "lseek", .errmsg = true, - .arg_scnprintf = { [2] = SCA_STRARRAY, /* whence */ }, - .arg_parm = { [2] = &strarray__whences, /* whence */ }, }, - { .name = "lsetxattr", .errmsg = true, }, - { .name = "lstat", .errmsg = true, .alias = "newlstat", }, - { .name = "lsxattr", .errmsg = true, }, - { .name = "madvise", .errmsg = true, - .arg_scnprintf = { [0] = SCA_HEX, /* start */ - [2] = SCA_MADV_BHV, /* behavior */ }, }, - { .name = "mkdir", .errmsg = true, }, - { .name = "mkdirat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, - { .name = "mknod", .errmsg = true, }, - { .name = "mknodat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, - { .name = "mlock", .errmsg = true, - .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, }, - { .name = "mlockall", .errmsg = true, - .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, }, + { .name = "keyctl", + .arg = { [0] = STRARRAY(option, keyctl_options), }, }, + { .name = "kill", + .arg = { [1] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, }, + { .name = "linkat", + .arg = { [0] = { .scnprintf = SCA_FDAT, /* fd */ }, }, }, + { .name = "lseek", + .arg = { [2] = STRARRAY(whence, whences), }, }, + { .name = "lstat", .alias = "newlstat", }, + { .name = "madvise", + .arg = { [0] = { .scnprintf = SCA_HEX, /* start */ }, + [2] = { .scnprintf = SCA_MADV_BHV, /* behavior */ }, }, }, + { .name = "mkdirat", + .arg = { [0] = { .scnprintf = SCA_FDAT, /* fd */ }, }, }, + { .name = "mknodat", + .arg = { [0] = { .scnprintf = SCA_FDAT, /* fd */ }, }, }, + { .name = "mlock", + .arg = { [0] = { .scnprintf = SCA_HEX, /* addr */ }, }, }, + { .name = "mlockall", + .arg = { [0] = { .scnprintf = SCA_HEX, /* addr */ }, }, }, { .name = "mmap", .hexret = true, /* The standard mmap maps to old_mmap on s390x */ #if defined(__s390x__) .alias = "old_mmap", #endif - .arg_scnprintf = { [0] = SCA_HEX, /* addr */ - [2] = SCA_MMAP_PROT, /* prot */ - [3] = SCA_MMAP_FLAGS, /* flags */ }, }, - { .name = "mprotect", .errmsg = true, - .arg_scnprintf = { [0] = SCA_HEX, /* start */ - [2] = SCA_MMAP_PROT, /* prot */ }, }, - { .name = "mq_unlink", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FILENAME, /* u_name */ }, }, + .arg = { [0] = { .scnprintf = SCA_HEX, /* addr */ }, + [2] = { .scnprintf = SCA_MMAP_PROT, /* prot */ }, + [3] = { .scnprintf = SCA_MMAP_FLAGS, /* flags */ }, }, }, + { .name = "mprotect", + .arg = { [0] = { .scnprintf = SCA_HEX, /* start */ }, + [2] = { .scnprintf = SCA_MMAP_PROT, /* prot */ }, }, }, + { .name = "mq_unlink", + .arg = { [0] = { .scnprintf = SCA_FILENAME, /* u_name */ }, }, }, { .name = "mremap", .hexret = true, - .arg_scnprintf = { [0] = SCA_HEX, /* addr */ - [3] = SCA_MREMAP_FLAGS, /* flags */ - [4] = SCA_HEX, /* new_addr */ }, }, - { .name = "munlock", .errmsg = true, - .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, }, - { .name = "munmap", .errmsg = true, - .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, }, - { .name = "name_to_handle_at", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, - { .name = "newfstatat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, - { .name = "open", .errmsg = true, - .arg_scnprintf = { [1] = SCA_OPEN_FLAGS, /* flags */ }, }, - { .name = "open_by_handle_at", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ - [2] = SCA_OPEN_FLAGS, /* flags */ }, }, - { .name = "openat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ - [2] = SCA_OPEN_FLAGS, /* flags */ }, }, - { .name = "perf_event_open", .errmsg = true, - .arg_scnprintf = { [2] = SCA_INT, /* cpu */ - [3] = SCA_FD, /* group_fd */ - [4] = SCA_PERF_FLAGS, /* flags */ }, }, - { .name = "pipe2", .errmsg = true, - .arg_scnprintf = { [1] = SCA_PIPE_FLAGS, /* flags */ }, }, - { .name = "poll", .errmsg = true, .timeout = true, }, - { .name = "ppoll", .errmsg = true, .timeout = true, }, - { .name = "pread", .errmsg = true, .alias = "pread64", }, - { .name = "preadv", .errmsg = true, .alias = "pread", }, - { .name = "prlimit64", .errmsg = true, STRARRAY(1, resource, rlimit_resources), }, - { .name = "pwrite", .errmsg = true, .alias = "pwrite64", }, - { .name = "pwritev", .errmsg = true, }, - { .name = "read", .errmsg = true, }, - { .name = "readlink", .errmsg = true, }, - { .name = "readlinkat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, - { .name = "readv", .errmsg = true, }, - { .name = "recvfrom", .errmsg = true, - .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, }, - { .name = "recvmmsg", .errmsg = true, - .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, }, - { .name = "recvmsg", .errmsg = true, - .arg_scnprintf = { [2] = SCA_MSG_FLAGS, /* flags */ }, }, - { .name = "removexattr", .errmsg = true, }, - { .name = "renameat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, - { .name = "rmdir", .errmsg = true, }, - { .name = "rt_sigaction", .errmsg = true, - .arg_scnprintf = { [0] = SCA_SIGNUM, /* sig */ }, }, - { .name = "rt_sigprocmask", .errmsg = true, STRARRAY(0, how, sighow), }, - { .name = "rt_sigqueueinfo", .errmsg = true, - .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, }, - { .name = "rt_tgsigqueueinfo", .errmsg = true, - .arg_scnprintf = { [2] = SCA_SIGNUM, /* sig */ }, }, - { .name = "sched_getattr", .errmsg = true, }, - { .name = "sched_setattr", .errmsg = true, }, - { .name = "sched_setscheduler", .errmsg = true, - .arg_scnprintf = { [1] = SCA_SCHED_POLICY, /* policy */ }, }, - { .name = "seccomp", .errmsg = true, - .arg_scnprintf = { [0] = SCA_SECCOMP_OP, /* op */ - [1] = SCA_SECCOMP_FLAGS, /* flags */ }, }, - { .name = "select", .errmsg = true, .timeout = true, }, - { .name = "sendmmsg", .errmsg = true, - .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, }, - { .name = "sendmsg", .errmsg = true, - .arg_scnprintf = { [2] = SCA_MSG_FLAGS, /* flags */ }, }, - { .name = "sendto", .errmsg = true, - .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, }, + .arg = { [0] = { .scnprintf = SCA_HEX, /* addr */ }, + [3] = { .scnprintf = SCA_MREMAP_FLAGS, /* flags */ }, + [4] = { .scnprintf = SCA_HEX, /* new_addr */ }, }, }, + { .name = "munlock", + .arg = { [0] = { .scnprintf = SCA_HEX, /* addr */ }, }, }, + { .name = "munmap", + .arg = { [0] = { .scnprintf = SCA_HEX, /* addr */ }, }, }, + { .name = "name_to_handle_at", + .arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, }, + { .name = "newfstatat", + .arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, }, + { .name = "open", + .arg = { [1] = { .scnprintf = SCA_OPEN_FLAGS, /* flags */ }, }, }, + { .name = "open_by_handle_at", + .arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, + [2] = { .scnprintf = SCA_OPEN_FLAGS, /* flags */ }, }, }, + { .name = "openat", + .arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, + [2] = { .scnprintf = SCA_OPEN_FLAGS, /* flags */ }, }, }, + { .name = "perf_event_open", + .arg = { [2] = { .scnprintf = SCA_INT, /* cpu */ }, + [3] = { .scnprintf = SCA_FD, /* group_fd */ }, + [4] = { .scnprintf = SCA_PERF_FLAGS, /* flags */ }, }, }, + { .name = "pipe2", + .arg = { [1] = { .scnprintf = SCA_PIPE_FLAGS, /* flags */ }, }, }, + { .name = "pkey_alloc", + .arg = { [1] = { .scnprintf = SCA_PKEY_ALLOC_ACCESS_RIGHTS, /* access_rights */ }, }, }, + { .name = "pkey_free", + .arg = { [0] = { .scnprintf = SCA_INT, /* key */ }, }, }, + { .name = "pkey_mprotect", + .arg = { [0] = { .scnprintf = SCA_HEX, /* start */ }, + [2] = { .scnprintf = SCA_MMAP_PROT, /* prot */ }, + [3] = { .scnprintf = SCA_INT, /* pkey */ }, }, }, + { .name = "poll", .timeout = true, }, + { .name = "ppoll", .timeout = true, }, + { .name = "pread", .alias = "pread64", }, + { .name = "preadv", .alias = "pread", }, + { .name = "prlimit64", + .arg = { [1] = STRARRAY(resource, rlimit_resources), }, }, + { .name = "pwrite", .alias = "pwrite64", }, + { .name = "readlinkat", + .arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, }, + { .name = "recvfrom", + .arg = { [3] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, }, + { .name = "recvmmsg", + .arg = { [3] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, }, + { .name = "recvmsg", + .arg = { [2] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, }, + { .name = "renameat", + .arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, }, + { .name = "rt_sigaction", + .arg = { [0] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, }, + { .name = "rt_sigprocmask", + .arg = { [0] = STRARRAY(how, sighow), }, }, + { .name = "rt_sigqueueinfo", + .arg = { [1] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, }, + { .name = "rt_tgsigqueueinfo", + .arg = { [2] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, }, + { .name = "sched_setscheduler", + .arg = { [1] = { .scnprintf = SCA_SCHED_POLICY, /* policy */ }, }, }, + { .name = "seccomp", + .arg = { [0] = { .scnprintf = SCA_SECCOMP_OP, /* op */ }, + [1] = { .scnprintf = SCA_SECCOMP_FLAGS, /* flags */ }, }, }, + { .name = "select", .timeout = true, }, + { .name = "sendmmsg", + .arg = { [3] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, }, + { .name = "sendmsg", + .arg = { [2] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, }, + { .name = "sendto", + .arg = { [3] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, }, { .name = "set_tid_address", .errpid = true, }, - { .name = "setitimer", .errmsg = true, STRARRAY(0, which, itimers), }, - { .name = "setpgid", .errmsg = true, }, - { .name = "setrlimit", .errmsg = true, STRARRAY(0, resource, rlimit_resources), }, - { .name = "setxattr", .errmsg = true, }, - { .name = "shutdown", .errmsg = true, }, - { .name = "socket", .errmsg = true, - .arg_scnprintf = { [0] = SCA_STRARRAY, /* family */ - [1] = SCA_SK_TYPE, /* type */ }, - .arg_parm = { [0] = &strarray__socket_families, /* family */ }, }, - { .name = "socketpair", .errmsg = true, - .arg_scnprintf = { [0] = SCA_STRARRAY, /* family */ - [1] = SCA_SK_TYPE, /* type */ }, - .arg_parm = { [0] = &strarray__socket_families, /* family */ }, }, - { .name = "stat", .errmsg = true, .alias = "newstat", }, - { .name = "statfs", .errmsg = true, }, - { .name = "statx", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* flags */ - [2] = SCA_STATX_FLAGS, /* flags */ - [3] = SCA_STATX_MASK, /* mask */ }, }, - { .name = "swapoff", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FILENAME, /* specialfile */ }, }, - { .name = "swapon", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FILENAME, /* specialfile */ }, }, - { .name = "symlinkat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, - { .name = "tgkill", .errmsg = true, - .arg_scnprintf = { [2] = SCA_SIGNUM, /* sig */ }, }, - { .name = "tkill", .errmsg = true, - .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, }, - { .name = "truncate", .errmsg = true, }, - { .name = "uname", .errmsg = true, .alias = "newuname", }, - { .name = "unlinkat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, - { .name = "utime", .errmsg = true, }, - { .name = "utimensat", .errmsg = true, - .arg_scnprintf = { [0] = SCA_FDAT, /* dirfd */ }, }, - { .name = "utimes", .errmsg = true, }, - { .name = "vmsplice", .errmsg = true, }, + { .name = "setitimer", + .arg = { [0] = STRARRAY(which, itimers), }, }, + { .name = "setrlimit", + .arg = { [0] = STRARRAY(resource, rlimit_resources), }, }, + { .name = "socket", + .arg = { [0] = STRARRAY(family, socket_families), + [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, }, }, + { .name = "socketpair", + .arg = { [0] = STRARRAY(family, socket_families), + [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, }, }, + { .name = "stat", .alias = "newstat", }, + { .name = "statx", + .arg = { [0] = { .scnprintf = SCA_FDAT, /* fdat */ }, + [2] = { .scnprintf = SCA_STATX_FLAGS, /* flags */ } , + [3] = { .scnprintf = SCA_STATX_MASK, /* mask */ }, }, }, + { .name = "swapoff", + .arg = { [0] = { .scnprintf = SCA_FILENAME, /* specialfile */ }, }, }, + { .name = "swapon", + .arg = { [0] = { .scnprintf = SCA_FILENAME, /* specialfile */ }, }, }, + { .name = "symlinkat", + .arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, }, + { .name = "tgkill", + .arg = { [2] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, }, + { .name = "tkill", + .arg = { [1] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, }, + { .name = "uname", .alias = "newuname", }, + { .name = "unlinkat", + .arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, }, + { .name = "utimensat", + .arg = { [0] = { .scnprintf = SCA_FDAT, /* dirfd */ }, }, }, { .name = "wait4", .errpid = true, - .arg_scnprintf = { [2] = SCA_WAITID_OPTIONS, /* options */ }, }, + .arg = { [2] = { .scnprintf = SCA_WAITID_OPTIONS, /* options */ }, }, }, { .name = "waitid", .errpid = true, - .arg_scnprintf = { [3] = SCA_WAITID_OPTIONS, /* options */ }, }, - { .name = "write", .errmsg = true, }, - { .name = "writev", .errmsg = true, }, + .arg = { [3] = { .scnprintf = SCA_WAITID_OPTIONS, /* options */ }, }, }, }; static int syscall_fmt__cmp(const void *name, const void *fmtp) @@ -828,8 +794,7 @@ struct syscall { const char *name; bool is_exit; struct syscall_fmt *fmt; - size_t (**arg_scnprintf)(char *bf, size_t size, struct syscall_arg *arg); - void **arg_parm; + struct syscall_arg_fmt *arg_fmt; }; /* @@ -859,6 +824,8 @@ static size_t fprintf_duration(unsigned long t, bool calculated, FILE *fp) * filename.ptr: The filename char pointer that will be vfs_getname'd * filename.entry_str_pos: Where to insert the string translated from * filename.ptr by the vfs_getname tracepoint/kprobe. + * ret_scnprintf: syscall args may set this to a different syscall return + * formatter, for instance, fcntl may return fds, file flags, etc. */ struct thread_trace { u64 entry_time; @@ -867,6 +834,7 @@ struct thread_trace { unsigned long pfmaj, pfmin; char *entry_str; double runtime_ms; + size_t (*ret_scnprintf)(char *bf, size_t size, struct syscall_arg *arg); struct { unsigned long ptr; short int entry_str_pos; @@ -917,6 +885,15 @@ fail: return NULL; } + +void syscall_arg__set_ret_scnprintf(struct syscall_arg *arg, + size_t (*ret_scnprintf)(char *bf, size_t size, struct syscall_arg *arg)) +{ + struct thread_trace *ttrace = thread__priv(arg->thread); + + ttrace->ret_scnprintf = ret_scnprintf; +} + #define TRACE_PFMAJ (1 << 0) #define TRACE_PFMIN (1 << 1) @@ -996,8 +973,7 @@ static const char *thread__fd_path(struct thread *thread, int fd, return ttrace->paths.table[fd]; } -static size_t syscall_arg__scnprintf_fd(char *bf, size_t size, - struct syscall_arg *arg) +size_t syscall_arg__scnprintf_fd(char *bf, size_t size, struct syscall_arg *arg) { int fd = arg->val; size_t printed = scnprintf(bf, size, "%d", fd); @@ -1162,32 +1138,46 @@ static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist) return err; } +static int syscall__alloc_arg_fmts(struct syscall *sc, int nr_args) +{ + int idx; + + if (nr_args == 6 && sc->fmt && sc->fmt->nr_args != 0) + nr_args = sc->fmt->nr_args; + + sc->arg_fmt = calloc(nr_args, sizeof(*sc->arg_fmt)); + if (sc->arg_fmt == NULL) + return -1; + + for (idx = 0; idx < nr_args; ++idx) { + if (sc->fmt) + sc->arg_fmt[idx] = sc->fmt->arg[idx]; + } + + sc->nr_args = nr_args; + return 0; +} + static int syscall__set_arg_fmts(struct syscall *sc) { struct format_field *field; int idx = 0, len; - sc->arg_scnprintf = calloc(sc->nr_args, sizeof(void *)); - if (sc->arg_scnprintf == NULL) - return -1; - - if (sc->fmt) - sc->arg_parm = sc->fmt->arg_parm; + for (field = sc->args; field; field = field->next, ++idx) { + if (sc->fmt && sc->fmt->arg[idx].scnprintf) + continue; - for (field = sc->args; field; field = field->next) { - if (sc->fmt && sc->fmt->arg_scnprintf[idx]) - sc->arg_scnprintf[idx] = sc->fmt->arg_scnprintf[idx]; - else if (strcmp(field->type, "const char *") == 0 && + if (strcmp(field->type, "const char *") == 0 && (strcmp(field->name, "filename") == 0 || strcmp(field->name, "path") == 0 || strcmp(field->name, "pathname") == 0)) - sc->arg_scnprintf[idx] = SCA_FILENAME; + sc->arg_fmt[idx].scnprintf = SCA_FILENAME; else if (field->flags & FIELD_IS_POINTER) - sc->arg_scnprintf[idx] = syscall_arg__scnprintf_hex; + sc->arg_fmt[idx].scnprintf = syscall_arg__scnprintf_hex; else if (strcmp(field->type, "pid_t") == 0) - sc->arg_scnprintf[idx] = SCA_PID; + sc->arg_fmt[idx].scnprintf = SCA_PID; else if (strcmp(field->type, "umode_t") == 0) - sc->arg_scnprintf[idx] = SCA_MODE_T; + sc->arg_fmt[idx].scnprintf = SCA_MODE_T; else if ((strcmp(field->type, "int") == 0 || strcmp(field->type, "unsigned int") == 0 || strcmp(field->type, "long") == 0) && @@ -1200,9 +1190,8 @@ static int syscall__set_arg_fmts(struct syscall *sc) * 23 unsigned int * 7 unsigned long */ - sc->arg_scnprintf[idx] = SCA_FD; + sc->arg_fmt[idx].scnprintf = SCA_FD; } - ++idx; } return 0; @@ -1247,11 +1236,13 @@ static int trace__read_syscall_info(struct trace *trace, int id) sc->tp_format = trace_event__tp_format("syscalls", tp_name); } + if (syscall__alloc_arg_fmts(sc, IS_ERR(sc->tp_format) ? 6 : sc->tp_format->format.nr_fields)) + return -1; + if (IS_ERR(sc->tp_format)) return -1; sc->args = sc->tp_format->format.fields; - sc->nr_args = sc->tp_format->format.nr_fields; /* * We need to check and discard the first variable '__syscall_nr' * or 'nr' that mean the syscall number. It is needless here. @@ -1270,6 +1261,7 @@ static int trace__read_syscall_info(struct trace *trace, int id) static int trace__validate_ev_qualifier(struct trace *trace) { int err = 0, i; + size_t nr_allocated; struct str_node *pos; trace->ev_qualifier_ids.nr = strlist__nr_entries(trace->ev_qualifier); @@ -1283,13 +1275,18 @@ static int trace__validate_ev_qualifier(struct trace *trace) goto out; } + nr_allocated = trace->ev_qualifier_ids.nr; i = 0; strlist__for_each_entry(pos, trace->ev_qualifier) { const char *sc = pos->s; - int id = syscalltbl__id(trace->sctbl, sc); + int id = syscalltbl__id(trace->sctbl, sc), match_next = -1; if (id < 0) { + id = syscalltbl__strglobmatch_first(trace->sctbl, sc, &match_next); + if (id >= 0) + goto matches; + if (err == 0) { fputs("Error:\tInvalid syscall ", trace->output); err = -EINVAL; @@ -1299,13 +1296,37 @@ static int trace__validate_ev_qualifier(struct trace *trace) fputs(sc, trace->output); } - +matches: trace->ev_qualifier_ids.entries[i++] = id; + if (match_next == -1) + continue; + + while (1) { + id = syscalltbl__strglobmatch_next(trace->sctbl, sc, &match_next); + if (id < 0) + break; + if (nr_allocated == trace->ev_qualifier_ids.nr) { + void *entries; + + nr_allocated += 8; + entries = realloc(trace->ev_qualifier_ids.entries, + nr_allocated * sizeof(trace->ev_qualifier_ids.entries[0])); + if (entries == NULL) { + err = -ENOMEM; + fputs("\nError:\t Not enough memory for parsing\n", trace->output); + goto out_free; + } + trace->ev_qualifier_ids.entries = entries; + } + trace->ev_qualifier_ids.nr++; + trace->ev_qualifier_ids.entries[i++] = id; + } } if (err < 0) { fputs("\nHint:\ttry 'perf list syscalls:sys_enter_*'" "\nHint:\tand: 'man syscalls'\n", trace->output); +out_free: zfree(&trace->ev_qualifier_ids.entries); trace->ev_qualifier_ids.nr = 0; } @@ -1321,33 +1342,68 @@ out: * variable to read it. Most notably this avoids extended load instructions * on unaligned addresses */ +unsigned long syscall_arg__val(struct syscall_arg *arg, u8 idx) +{ + unsigned long val; + unsigned char *p = arg->args + sizeof(unsigned long) * idx; + + memcpy(&val, p, sizeof(val)); + return val; +} + +static size_t syscall__scnprintf_name(struct syscall *sc, char *bf, size_t size, + struct syscall_arg *arg) +{ + if (sc->arg_fmt && sc->arg_fmt[arg->idx].name) + return scnprintf(bf, size, "%s: ", sc->arg_fmt[arg->idx].name); + + return scnprintf(bf, size, "arg%d: ", arg->idx); +} + +static size_t syscall__scnprintf_val(struct syscall *sc, char *bf, size_t size, + struct syscall_arg *arg, unsigned long val) +{ + if (sc->arg_fmt && sc->arg_fmt[arg->idx].scnprintf) { + arg->val = val; + if (sc->arg_fmt[arg->idx].parm) + arg->parm = sc->arg_fmt[arg->idx].parm; + return sc->arg_fmt[arg->idx].scnprintf(bf, size, arg); + } + return scnprintf(bf, size, "%ld", val); +} static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size, unsigned char *args, struct trace *trace, struct thread *thread) { size_t printed = 0; - unsigned char *p; unsigned long val; + u8 bit = 1; + struct syscall_arg arg = { + .args = args, + .idx = 0, + .mask = 0, + .trace = trace, + .thread = thread, + }; + struct thread_trace *ttrace = thread__priv(thread); + + /* + * Things like fcntl will set this in its 'cmd' formatter to pick the + * right formatter for the return value (an fd? file flags?), which is + * not needed for syscalls that always return a given type, say an fd. + */ + ttrace->ret_scnprintf = NULL; if (sc->args != NULL) { struct format_field *field; - u8 bit = 1; - struct syscall_arg arg = { - .idx = 0, - .mask = 0, - .trace = trace, - .thread = thread, - }; for (field = sc->args; field; field = field->next, ++arg.idx, bit <<= 1) { if (arg.mask & bit) continue; - /* special care for unaligned accesses */ - p = args + sizeof(unsigned long) * arg.idx; - memcpy(&val, p, sizeof(val)); + val = syscall_arg__val(&arg, arg.idx); /* * Suppress this argument if its value is zero and @@ -1355,23 +1411,16 @@ static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size, * strarray for it. */ if (val == 0 && - !(sc->arg_scnprintf && - sc->arg_scnprintf[arg.idx] == SCA_STRARRAY && - sc->arg_parm[arg.idx])) + !(sc->arg_fmt && + (sc->arg_fmt[arg.idx].show_zero || + sc->arg_fmt[arg.idx].scnprintf == SCA_STRARRAY || + sc->arg_fmt[arg.idx].scnprintf == SCA_STRARRAYS) && + sc->arg_fmt[arg.idx].parm)) continue; printed += scnprintf(bf + printed, size - printed, "%s%s: ", printed ? ", " : "", field->name); - if (sc->arg_scnprintf && sc->arg_scnprintf[arg.idx]) { - arg.val = val; - if (sc->arg_parm) - arg.parm = sc->arg_parm[arg.idx]; - printed += sc->arg_scnprintf[arg.idx](bf + printed, - size - printed, &arg); - } else { - printed += scnprintf(bf + printed, size - printed, - "%ld", val); - } + printed += syscall__scnprintf_val(sc, bf + printed, size - printed, &arg, val); } } else if (IS_ERR(sc->tp_format)) { /* @@ -1379,16 +1428,17 @@ static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size, * may end up not having any args, like with gettid(), so only * print the raw args when we didn't manage to read it. */ - int i = 0; - - while (i < 6) { - /* special care for unaligned accesses */ - p = args + sizeof(unsigned long) * i; - memcpy(&val, p, sizeof(val)); - printed += scnprintf(bf + printed, size - printed, - "%sarg%d: %ld", - printed ? ", " : "", i, val); - ++i; + while (arg.idx < sc->nr_args) { + if (arg.mask & bit) + goto next_arg; + val = syscall_arg__val(&arg, arg.idx); + if (printed) + printed += scnprintf(bf + printed, size - printed, ", "); + printed += syscall__scnprintf_name(sc, bf + printed, size - printed, &arg); + printed += syscall__scnprintf_val(sc, bf + printed, size - printed, &arg, val); +next_arg: + ++arg.idx; + bit <<= 1; } } @@ -1635,17 +1685,31 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel, } if (sc->fmt == NULL) { + if (ret < 0) + goto errno_print; signed_print: fprintf(trace->output, ") = %ld", ret); - } else if (ret < 0 && (sc->fmt->errmsg || sc->fmt->errpid)) { + } else if (ret < 0) { +errno_print: { char bf[STRERR_BUFSIZE]; const char *emsg = str_error_r(-ret, bf, sizeof(bf)), *e = audit_errno_to_name(-ret); fprintf(trace->output, ") = -1 %s %s", e, emsg); + } } else if (ret == 0 && sc->fmt->timeout) fprintf(trace->output, ") = 0 Timeout"); - else if (sc->fmt->hexret) + else if (ttrace->ret_scnprintf) { + char bf[1024]; + struct syscall_arg arg = { + .val = ret, + .thread = thread, + .trace = trace, + }; + ttrace->ret_scnprintf(bf, sizeof(bf), &arg); + ttrace->ret_scnprintf = NULL; + fprintf(trace->output, ") = %s", bf); + } else if (sc->fmt->hexret) fprintf(trace->output, ") = %#lx", ret); else if (sc->fmt->errpid) { struct thread *child = machine__find_thread(trace->host, ret, ret); @@ -2171,6 +2235,30 @@ out_enomem: goto out; } +static int trace__set_filter_loop_pids(struct trace *trace) +{ + unsigned int nr = 1; + pid_t pids[32] = { + getpid(), + }; + struct thread *thread = machine__find_thread(trace->host, pids[0], pids[0]); + + while (thread && nr < ARRAY_SIZE(pids)) { + struct thread *parent = machine__find_thread(trace->host, thread->ppid, thread->ppid); + + if (parent == NULL) + break; + + if (!strcmp(thread__comm_str(parent), "sshd")) { + pids[nr++] = parent->tid; + break; + } + thread = parent; + } + + return perf_evlist__set_filter_pids(trace->evlist, nr, pids); +} + static int trace__run(struct trace *trace, int argc, const char **argv) { struct perf_evlist *evlist = trace->evlist; @@ -2294,7 +2382,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv) if (trace->filter_pids.nr > 0) err = perf_evlist__set_filter_pids(evlist, trace->filter_pids.nr, trace->filter_pids.entries); else if (thread_map__pid(evlist->threads, 0) == -1) - err = perf_evlist__set_filter_pid(evlist, getpid()); + err = trace__set_filter_loop_pids(trace); if (err < 0) goto out_error_mem; @@ -2756,7 +2844,7 @@ static int trace__parse_events_option(const struct option *opt, const char *str, struct trace *trace = (struct trace *)opt->value; const char *s = str; char *sep = NULL, *lists[2] = { NULL, NULL, }; - int len = strlen(str), err = -1, list; + int len = strlen(str) + 1, err = -1, list, idx; char *strace_groups_dir = system_path(STRACE_GROUPS_DIR); char group_name[PATH_MAX]; @@ -2773,7 +2861,8 @@ static int trace__parse_events_option(const struct option *opt, const char *str, *sep = '\0'; list = 0; - if (syscalltbl__id(trace->sctbl, s) >= 0) { + if (syscalltbl__id(trace->sctbl, s) >= 0 || + syscalltbl__strglobmatch_first(trace->sctbl, s, &idx) >= 0) { list = 1; } else { path__join(group_name, sizeof(group_name), strace_groups_dir, s); diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index 83fe2202382e..932fda54b8a6 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -1,9 +1,15 @@ #!/bin/sh HEADERS=' +include/uapi/drm/drm.h +include/uapi/drm/i915_drm.h include/uapi/linux/fcntl.h +include/uapi/linux/kvm.h include/uapi/linux/perf_event.h +include/uapi/linux/sched.h include/uapi/linux/stat.h +include/uapi/linux/vhost.h +include/uapi/sound/asound.h include/linux/hash.h include/uapi/linux/hw_breakpoint.h arch/x86/include/asm/disabled-features.h @@ -16,6 +22,7 @@ arch/x86/include/uapi/asm/perf_regs.h arch/x86/include/uapi/asm/kvm.h arch/x86/include/uapi/asm/kvm_perf.h arch/x86/include/uapi/asm/svm.h +arch/x86/include/uapi/asm/unistd.h arch/x86/include/uapi/asm/vmx.h arch/powerpc/include/uapi/asm/kvm.h arch/s390/include/uapi/asm/kvm.h @@ -29,12 +36,13 @@ include/asm-generic/bitops/__fls.h include/asm-generic/bitops/fls.h include/asm-generic/bitops/fls64.h include/linux/coresight-pmu.h +include/uapi/asm-generic/ioctls.h include/uapi/asm-generic/mman-common.h ' check () { file=$1 - opts= + opts="--ignore-blank-lines --ignore-space-change" shift while [ -n "$*" ]; do @@ -45,7 +53,7 @@ check () { cmd="diff $opts ../$file ../../$file > /dev/null" test -f ../../$file && - eval $cmd || echo "Warning: $file differs from kernel" >&2 + eval $cmd || echo "Warning: Kernel ABI header at 'tools/$file' differs from latest version at '$file'" >&2 } @@ -55,7 +63,7 @@ for i in $HEADERS; do done # diff with extra ignore lines -check arch/x86/lib/memcpy_64.S -B -I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -check arch/x86/lib/memset_64.S -B -I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -check include/uapi/asm-generic/mman.h -B -I "^#include <\(uapi/\)*asm-generic/mman-common.h>" -check include/uapi/linux/mman.h -B -I "^#include <\(uapi/\)*asm/mman.h>" +check arch/x86/lib/memcpy_64.S -I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" +check arch/x86/lib/memset_64.S -I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" +check include/uapi/asm-generic/mman.h -I "^#include <\(uapi/\)*asm-generic/mman-common.h>" +check include/uapi/linux/mman.h -I "^#include <\(uapi/\)*asm/mman.h>" diff --git a/tools/perf/jvmti/jvmti_agent.c b/tools/perf/jvmti/jvmti_agent.c index e9651a9d670e..cf36de7ea255 100644 --- a/tools/perf/jvmti/jvmti_agent.c +++ b/tools/perf/jvmti/jvmti_agent.c @@ -304,7 +304,7 @@ jvmti_close(void *agent) FILE *fp = agent; if (!fp) { - warnx("jvmti: incalid fd in close_agent"); + warnx("jvmti: invalid fd in close_agent"); return -1; } diff --git a/tools/perf/jvmti/jvmti_agent.h b/tools/perf/jvmti/jvmti_agent.h index bedf5d0ba9ff..c53a41f48b63 100644 --- a/tools/perf/jvmti/jvmti_agent.h +++ b/tools/perf/jvmti/jvmti_agent.h @@ -5,8 +5,6 @@ #include <stdint.h> #include <jvmti.h> -#define __unused __attribute__((unused)) - #if defined(__cplusplus) extern "C" { #endif diff --git a/tools/perf/jvmti/libjvmti.c b/tools/perf/jvmti/libjvmti.c index 5612641c69b4..6d710904c837 100644 --- a/tools/perf/jvmti/libjvmti.c +++ b/tools/perf/jvmti/libjvmti.c @@ -1,3 +1,4 @@ +#include <linux/compiler.h> #include <sys/types.h> #include <stdio.h> #include <string.h> @@ -238,7 +239,7 @@ code_generated_cb(jvmtiEnv *jvmti, } JNIEXPORT jint JNICALL -Agent_OnLoad(JavaVM *jvm, char *options, void *reserved __unused) +Agent_OnLoad(JavaVM *jvm, char *options, void *reserved __maybe_unused) { jvmtiEventCallbacks cb; jvmtiCapabilities caps1; @@ -313,7 +314,7 @@ Agent_OnLoad(JavaVM *jvm, char *options, void *reserved __unused) } JNIEXPORT void JNICALL -Agent_OnUnload(JavaVM *jvm __unused) +Agent_OnUnload(JavaVM *jvm __maybe_unused) { int ret; diff --git a/tools/perf/perf-sys.h b/tools/perf/perf-sys.h index e4b717e9eb6c..c11f0c76e90c 100644 --- a/tools/perf/perf-sys.h +++ b/tools/perf/perf-sys.h @@ -9,16 +9,6 @@ #include <linux/perf_event.h> #include <asm/barrier.h> -#if defined(__i386__) -#define cpu_relax() asm volatile("rep; nop" ::: "memory"); -#define CPUINFO_PROC {"model name"} -#endif - -#if defined(__x86_64__) -#define cpu_relax() asm volatile("rep; nop" ::: "memory"); -#define CPUINFO_PROC {"model name"} -#endif - #ifdef __powerpc__ #define CPUINFO_PROC {"cpu"} #endif @@ -43,19 +33,10 @@ #define CPUINFO_PROC {"cpu model"} #endif -#ifdef __ia64__ -#define cpu_relax() asm volatile ("hint @pause" ::: "memory") -#define CPUINFO_PROC {"model name"} -#endif - #ifdef __arm__ #define CPUINFO_PROC {"model name", "Processor"} #endif -#ifdef __aarch64__ -#define cpu_relax() asm volatile("yield" ::: "memory") -#endif - #ifdef __mips__ #define CPUINFO_PROC {"cpu model"} #endif @@ -72,13 +53,8 @@ #define CPUINFO_PROC {"core ID"} #endif -#ifdef __tile__ -#define cpu_relax() asm volatile ("mfspr zero, PASS" ::: "memory") -#define CPUINFO_PROC {"model name"} -#endif - -#ifndef cpu_relax -#define cpu_relax() barrier() +#ifndef CPUINFO_PROC +#define CPUINFO_PROC { "model name", } #endif static inline int diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 628a5e412cb1..2f19e03c5c40 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -89,7 +89,7 @@ struct pager_config { static int pager_command_config(const char *var, const char *value, void *data) { struct pager_config *c = data; - if (!prefixcmp(var, "pager.") && !strcmp(var + 6, c->cmd)) + if (strstarts(var, "pager.") && !strcmp(var + 6, c->cmd)) c->val = perf_config_bool(var, value); return 0; } @@ -108,9 +108,9 @@ static int check_pager_config(const char *cmd) static int browser_command_config(const char *var, const char *value, void *data) { struct pager_config *c = data; - if (!prefixcmp(var, "tui.") && !strcmp(var + 4, c->cmd)) + if (strstarts(var, "tui.") && !strcmp(var + 4, c->cmd)) c->val = perf_config_bool(var, value); - if (!prefixcmp(var, "gtk.") && !strcmp(var + 4, c->cmd)) + if (strstarts(var, "gtk.") && !strcmp(var + 4, c->cmd)) c->val = perf_config_bool(var, value) ? 2 : 0; return 0; } @@ -192,7 +192,7 @@ static int handle_options(const char ***argv, int *argc, int *envchanged) /* * Check remaining flags. */ - if (!prefixcmp(cmd, CMD_EXEC_PATH)) { + if (strstarts(cmd, CMD_EXEC_PATH)) { cmd += strlen(CMD_EXEC_PATH); if (*cmd == '=') set_argv_exec_path(cmd + 1); @@ -229,7 +229,7 @@ static int handle_options(const char ***argv, int *argc, int *envchanged) *envchanged = 1; (*argv)++; (*argc)--; - } else if (!prefixcmp(cmd, CMD_DEBUGFS_DIR)) { + } else if (strstarts(cmd, CMD_DEBUGFS_DIR)) { tracing_path_set(cmd + strlen(CMD_DEBUGFS_DIR)); fprintf(stderr, "dir: %s\n", tracing_path); if (envchanged) @@ -467,17 +467,23 @@ int main(int argc, const char **argv) * - cannot execute it externally (since it would just do * the same thing over again) * - * So we just directly call the internal command handler, and - * die if that one cannot handle it. + * So we just directly call the internal command handler. If that one + * fails to handle this, then maybe we just run a renamed perf binary + * that contains a dash in its name. To handle this scenario, we just + * fall through and ignore the "xxxx" part of the command string. */ - if (!prefixcmp(cmd, "perf-")) { + if (strstarts(cmd, "perf-")) { cmd += 5; argv[0] = cmd; handle_internal_command(argc, argv); - fprintf(stderr, "cannot handle %s internally", cmd); - goto out; + /* + * If the command is handled, the above function does not + * return undo changes and fall through in such a case. + */ + cmd -= 5; + argv[0] = cmd; } - if (!prefixcmp(cmd, "trace")) { + if (strstarts(cmd, "trace")) { #ifdef HAVE_LIBAUDIT_SUPPORT setup_path(); argv[0] = "trace"; @@ -495,7 +501,7 @@ int main(int argc, const char **argv) commit_pager_choice(); if (argc > 0) { - if (!prefixcmp(argv[0], "--")) + if (strstarts(argv[0], "--")) argv[0] += 2; } else { /* The user didn't specify a command; give them help */ diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 806c216a1078..dc442ba21bf6 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -7,6 +7,7 @@ #include <linux/perf_event.h> extern bool test_attr__enabled; +void test_attr__ready(void); void test_attr__init(void); void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu, int fd, int group_fd, unsigned long flags); @@ -42,6 +43,7 @@ struct record_opts { bool no_samples; bool raw_samples; bool sample_address; + bool sample_phys_addr; bool sample_weight; bool sample_time; bool sample_time_set; diff --git a/tools/perf/pmu-events/README b/tools/perf/pmu-events/README index 1408ade0d773..c2ee3e4417fe 100644 --- a/tools/perf/pmu-events/README +++ b/tools/perf/pmu-events/README @@ -85,10 +85,6 @@ users to specify events by their name: where 'pm_1plus_ppc_cmpl' is a Power8 PMU event. -In case of errors when processing files in the tools/perf/pmu-events/arch -directory, 'jevents' tries to create an empty mapping file to allow the perf -build to succeed even if the PMU event aliases cannot be used. - However some errors in processing may cause the perf build to fail. Mapfile format diff --git a/tools/perf/pmu-events/arch/powerpc/mapfile.csv b/tools/perf/pmu-events/arch/powerpc/mapfile.csv index e925baa0c30b..a0f3a11ca19f 100644 --- a/tools/perf/pmu-events/arch/powerpc/mapfile.csv +++ b/tools/perf/pmu-events/arch/powerpc/mapfile.csv @@ -13,9 +13,13 @@ # # Power8 entries -004b0000,1,power8.json,core -004b0201,1,power8.json,core -004c0000,1,power8.json,core -004d0000,1,power8.json,core -004d0100,1,power8.json,core -004d0200,1,power8.json,core +004b0000,1,power8,core +004b0201,1,power8,core +004c0000,1,power8,core +004d0000,1,power8,core +004d0100,1,power8,core +004d0200,1,power8,core +004c0100,1,power8,core +004e0100,1,power9,core +004e0200,1,power9,core +004e1200,1,power9,core diff --git a/tools/perf/pmu-events/arch/powerpc/power9/cache.json b/tools/perf/pmu-events/arch/powerpc/power9/cache.json new file mode 100644 index 000000000000..18f6645f2897 --- /dev/null +++ b/tools/perf/pmu-events/arch/powerpc/power9/cache.json @@ -0,0 +1,137 @@ +[ + {, + "EventCode": "0x300F4", + "EventName": "PM_THRD_CONC_RUN_INST", + "BriefDescription": "PPC Instructions Finished by this thread when all threads in the core had the run-latch set" + }, + {, + "EventCode": "0x1E056", + "EventName": "PM_CMPLU_STALL_FLUSH_ANY_THREAD", + "BriefDescription": "Cycles in which the NTC instruction is not allowed to complete because any of the 4 threads in the same core suffered a flush, which blocks completion" + }, + {, + "EventCode": "0x4D016", + "EventName": "PM_CMPLU_STALL_FXLONG", + "BriefDescription": "Completion stall due to a long latency scalar fixed point instruction (division, square root)" + }, + {, + "EventCode": "0x2D016", + "EventName": "PM_CMPLU_STALL_FXU", + "BriefDescription": "Finish stall due to a scalar fixed point or CR instruction in the execution pipeline. These instructions get routed to the ALU, ALU2, and DIV pipes" + }, + {, + "EventCode": "0x1D15C", + "EventName": "PM_MRK_DTLB_MISS_1G", + "BriefDescription": "Marked Data TLB reload (after a miss) page size 2M. Implies radix translation was used" + }, + {, + "EventCode": "0x4D12A", + "EventName": "PM_MRK_DATA_FROM_RL4_CYC", + "BriefDescription": "Duration in cycles to reload from another chip's L4 on the same Node or Group ( Remote) due to a marked load" + }, + {, + "EventCode": "0x1003C", + "EventName": "PM_CMPLU_STALL_DMISS_L2L3", + "BriefDescription": "Completion stall by Dcache miss which resolved in L2/L3" + }, + {, + "EventCode": "0x4C014", + "EventName": "PM_CMPLU_STALL_LMQ_FULL", + "BriefDescription": "Finish stall because the NTF instruction was a load that missed in the L1 and the LMQ was unable to accept this load miss request because it was full" + }, + {, + "EventCode": "0x14048", + "EventName": "PM_INST_FROM_ON_CHIP_CACHE", + "BriefDescription": "The processor's Instruction cache was reloaded either shared or modified data from another core's L2/L3 on the same chip due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x4D014", + "EventName": "PM_CMPLU_STALL_LOAD_FINISH", + "BriefDescription": "Finish stall because the NTF instruction was a load instruction with all its dependencies satisfied just going through the LSU pipe to finish" + }, + {, + "EventCode": "0x2404A", + "EventName": "PM_INST_FROM_RL4", + "BriefDescription": "The processor's Instruction cache was reloaded from another chip's L4 on the same Node or Group ( Remote) due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x1404A", + "EventName": "PM_INST_FROM_RL2L3_SHR", + "BriefDescription": "The processor's Instruction cache was reloaded with Shared (S) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x401EA", + "EventName": "PM_THRESH_EXC_128", + "BriefDescription": "Threshold counter exceeded a value of 128" + }, + {, + "EventCode": "0x400F6", + "EventName": "PM_BR_MPRED_CMPL", + "BriefDescription": "Number of Branch Mispredicts" + }, + {, + "EventCode": "0x2F140", + "EventName": "PM_MRK_DPTEG_FROM_L2_MEPF", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 hit without dispatch conflicts on Mepf state. due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x101E6", + "EventName": "PM_THRESH_EXC_4096", + "BriefDescription": "Threshold counter exceed a count of 4096" + }, + {, + "EventCode": "0x3D156", + "EventName": "PM_MRK_DTLB_MISS_64K", + "BriefDescription": "Marked Data TLB Miss page size 64K" + }, + {, + "EventCode": "0x4C15E", + "EventName": "PM_MRK_DTLB_MISS_16M", + "BriefDescription": "Marked Data TLB Miss page size 16M" + }, + {, + "EventCode": "0x2D15E", + "EventName": "PM_MRK_DTLB_MISS_16G", + "BriefDescription": "Marked Data TLB Miss page size 16G" + }, + {, + "EventCode": "0x3F14A", + "EventName": "PM_MRK_DPTEG_FROM_RMEM", + "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's memory on the same Node or Group ( Remote) due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x4C016", + "EventName": "PM_CMPLU_STALL_DMISS_L2L3_CONFLICT", + "BriefDescription": "Completion stall due to cache miss that resolves in the L2 or L3 with a conflict" + }, + {, + "EventCode": "0x2C01A", + "EventName": "PM_CMPLU_STALL_LHS", + "BriefDescription": "Finish stall because the NTF instruction was a load that hit on an older store and it was waiting for store data" + }, + {, + "EventCode": "0x401E4", + "EventName": "PM_MRK_DTLB_MISS", + "BriefDescription": "Marked dtlb miss" + }, + {, + "EventCode": "0x24046", + "EventName": "PM_INST_FROM_RL2L3_MOD", + "BriefDescription": "The processor's Instruction cache was reloaded with Modified (M) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x1002A", + "EventName": "PM_CMPLU_STALL_LARX", + "BriefDescription": "Finish stall because the NTF instruction was a larx waiting to be satisfied" + }, + {, + "EventCode": "0x3006C", + "EventName": "PM_RUN_CYC_SMT2_MODE", + "BriefDescription": "Cycles in which this thread's run latch is set and the core is in SMT2 mode" + }, + {, + "EventCode": "0x1C058", + "EventName": "PM_DTLB_MISS_16G", + "BriefDescription": "Data TLB Miss page size 16G" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/powerpc/power9/floating-point.json b/tools/perf/pmu-events/arch/powerpc/power9/floating-point.json new file mode 100644 index 000000000000..8a83bca26552 --- /dev/null +++ b/tools/perf/pmu-events/arch/powerpc/power9/floating-point.json @@ -0,0 +1,32 @@ +[ + {, + "EventCode": "0x1415A", + "EventName": "PM_MRK_DATA_FROM_L2_DISP_CONFLICT_LDHITST_CYC", + "BriefDescription": "Duration in cycles to reload from local core's L2 with load hit store conflict due to a marked load" + }, + {, + "EventCode": "0x10058", + "EventName": "PM_MEM_LOC_THRESH_IFU", + "BriefDescription": "Local Memory above threshold for IFU speculation control" + }, + {, + "EventCode": "0x2D028", + "EventName": "PM_RADIX_PWC_L2_PDE_FROM_L2", + "BriefDescription": "A Page Directory Entry was reloaded to a level 2 page walk cache from the core's L2 data cache" + }, + {, + "EventCode": "0x30012", + "EventName": "PM_FLUSH_COMPLETION", + "BriefDescription": "The instruction that was next to complete did not complete because it suffered a flush" + }, + {, + "EventCode": "0x2D154", + "EventName": "PM_MRK_DERAT_MISS_64K", + "BriefDescription": "Marked Data ERAT Miss (Data TLB Access) page size 64K" + }, + {, + "EventCode": "0x4016E", + "EventName": "PM_THRESH_NOT_MET", + "BriefDescription": "Threshold counter did not meet threshold" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/powerpc/power9/frontend.json b/tools/perf/pmu-events/arch/powerpc/power9/frontend.json new file mode 100644 index 000000000000..c63a919eda98 --- /dev/null +++ b/tools/perf/pmu-events/arch/powerpc/power9/frontend.json @@ -0,0 +1,372 @@ +[ + {, + "EventCode": "0x3E15C", + "EventName": "PM_MRK_L2_TM_ST_ABORT_SISTER", + "BriefDescription": "TM marked store abort for this thread" + }, + {, + "EventCode": "0x25044", + "EventName": "PM_IPTEG_FROM_L31_MOD", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's L3 on the same chip due to a instruction side request" + }, + {, + "EventCode": "0x101E8", + "EventName": "PM_THRESH_EXC_256", + "BriefDescription": "Threshold counter exceed a count of 256" + }, + {, + "EventCode": "0x4504E", + "EventName": "PM_IPTEG_FROM_L3MISS", + "BriefDescription": "A Page Table Entry was loaded into the TLB from a location other than the local core's L3 due to a instruction side request" + }, + {, + "EventCode": "0x1006A", + "EventName": "PM_NTC_ISSUE_HELD_DARQ_FULL", + "BriefDescription": "The NTC instruction is being held at dispatch because there are no slots in the DARQ for it" + }, + {, + "EventCode": "0x4E016", + "EventName": "PM_CMPLU_STALL_LSAQ_ARB", + "BriefDescription": "Finish stall because the NTF instruction was a load or store that was held in LSAQ because an older instruction from SRQ or LRQ won arbitration to the LSU pipe when this instruction tried to launch" + }, + {, + "EventCode": "0x1001A", + "EventName": "PM_LSU_SRQ_FULL_CYC", + "BriefDescription": "Cycles in which the Store Queue is full on all 4 slices. This is event is not per thread. All the threads will see the same count for this core resource" + }, + {, + "EventCode": "0x1E15E", + "EventName": "PM_MRK_L2_TM_REQ_ABORT", + "BriefDescription": "TM abort" + }, + {, + "EventCode": "0x34052", + "EventName": "PM_INST_SYS_PUMP_MPRED", + "BriefDescription": "Final Pump Scope (system) mispredicted. Either the original scope was too small (Chip/Group) or the original scope was System and it should have been smaller. Counts for an instruction fetch" + }, + {, + "EventCode": "0x20114", + "EventName": "PM_MRK_L2_RC_DISP", + "BriefDescription": "Marked Instruction RC dispatched in L2" + }, + {, + "EventCode": "0x4C044", + "EventName": "PM_DATA_FROM_L31_ECO_MOD", + "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another core's ECO L3 on the same chip due to a demand load" + }, + {, + "EventCode": "0x1C044", + "EventName": "PM_DATA_FROM_L3_NO_CONFLICT", + "BriefDescription": "The processor's data cache was reloaded from local core's L3 without conflict due to a demand load" + }, + {, + "EventCode": "0x44050", + "EventName": "PM_INST_SYS_PUMP_MPRED_RTY", + "BriefDescription": "Final Pump Scope (system) ended up larger than Initial Pump Scope (Chip/Group) for an instruction fetch" + }, + {, + "EventCode": "0x30154", + "EventName": "PM_MRK_FAB_RSP_DCLAIM", + "BriefDescription": "Marked store had to do a dclaim" + }, + {, + "EventCode": "0x30014", + "EventName": "PM_CMPLU_STALL_STORE_FIN_ARB", + "BriefDescription": "Finish stall because the NTF instruction was a store waiting for a slot in the store finish pipe. This means the instruction is ready to finish but there are instructions ahead of it, using the finish pipe" + }, + {, + "EventCode": "0x3E054", + "EventName": "PM_LD_MISS_L1", + "BriefDescription": "Load Missed L1, counted at execution time (can be greater than loads finished). LMQ merges are not included in this count. i.e. if a load instruction misses on an address that is already allocated on the LMQ, this event will not increment for that load). Note that this count is per slice, so if a load spans multiple slices this event will increment multiple times for a single load." + }, + {, + "EventCode": "0x2E01A", + "EventName": "PM_CMPLU_STALL_LSU_FLUSH_NEXT", + "BriefDescription": "Completion stall of one cycle because the LSU requested to flush the next iop in the sequence. It takes 1 cycle for the ISU to process this request before the LSU instruction is allowed to complete" + }, + {, + "EventCode": "0x2D01C", + "EventName": "PM_CMPLU_STALL_STCX", + "BriefDescription": "Finish stall because the NTF instruction was a stcx waiting for response from L2" + }, + {, + "EventCode": "0x2C010", + "EventName": "PM_CMPLU_STALL_LSU", + "BriefDescription": "Completion stall by LSU instruction" + }, + {, + "EventCode": "0x2C042", + "EventName": "PM_DATA_FROM_L3_MEPF", + "BriefDescription": "The processor's data cache was reloaded from local core's L3 without dispatch conflicts hit on Mepf state due to a demand load" + }, + {, + "EventCode": "0x4E012", + "EventName": "PM_CMPLU_STALL_MTFPSCR", + "BriefDescription": "Completion stall because the ISU is updating the register and notifying the Effective Address Table (EAT)" + }, + {, + "EventCode": "0x100F2", + "EventName": "PM_1PLUS_PPC_CMPL", + "BriefDescription": "1 or more ppc insts finished" + }, + {, + "EventCode": "0x3001C", + "EventName": "PM_LSU_REJECT_LMQ_FULL", + "BriefDescription": "LSU Reject due to LMQ full (up to 4 per cycles)" + }, + {, + "EventCode": "0x15046", + "EventName": "PM_IPTEG_FROM_L31_SHR", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another core's L3 on the same chip due to a instruction side request" + }, + {, + "EventCode": "0x1015E", + "EventName": "PM_MRK_FAB_RSP_RD_T_INTV", + "BriefDescription": "Sampled Read got a T intervention" + }, + {, + "EventCode": "0x101EC", + "EventName": "PM_THRESH_MET", + "BriefDescription": "threshold exceeded" + }, + {, + "EventCode": "0x10020", + "EventName": "PM_PMC4_REWIND", + "BriefDescription": "PMC4 Rewind Event" + }, + {, + "EventCode": "0x301EA", + "EventName": "PM_THRESH_EXC_1024", + "BriefDescription": "Threshold counter exceeded a value of 1024" + }, + {, + "EventCode": "0x34056", + "EventName": "PM_CMPLU_STALL_LSU_MFSPR", + "BriefDescription": "Finish stall because the NTF instruction was a mfspr instruction targeting an LSU SPR and it was waiting for the register data to be returned" + }, + {, + "EventCode": "0x44056", + "EventName": "PM_VECTOR_ST_CMPL", + "BriefDescription": "Number of vector store instructions completed" + }, + {, + "EventCode": "0x2C124", + "EventName": "PM_MRK_DATA_FROM_L2_DISP_CONFLICT_OTHER", + "BriefDescription": "The processor's data cache was reloaded from local core's L2 with dispatch conflict due to a marked load" + }, + {, + "EventCode": "0x4C12A", + "EventName": "PM_MRK_DATA_FROM_RL2L3_SHR_CYC", + "BriefDescription": "Duration in cycles to reload with Shared (S) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a marked load" + }, + {, + "EventCode": "0x3C056", + "EventName": "PM_DTLB_MISS_64K", + "BriefDescription": "Data TLB Miss page size 64K" + }, + {, + "EventCode": "0x30060", + "EventName": "PM_TM_TRANS_RUN_INST", + "BriefDescription": "Run instructions completed in transactional state (gated by the run latch)" + }, + {, + "EventCode": "0x2C014", + "EventName": "PM_CMPLU_STALL_STORE_FINISH", + "BriefDescription": "Finish stall because the NTF instruction was a store with all its dependencies met, just waiting to go through the LSU pipe to finish" + }, + {, + "EventCode": "0x3515A", + "EventName": "PM_MRK_DATA_FROM_ON_CHIP_CACHE_CYC", + "BriefDescription": "Duration in cycles to reload either shared or modified data from another core's L2/L3 on the same chip due to a marked load" + }, + {, + "EventCode": "0x34050", + "EventName": "PM_INST_SYS_PUMP_CPRED", + "BriefDescription": "Initial and Final Pump Scope was system pump (prediction=correct) for an instruction fetch" + }, + {, + "EventCode": "0x3015E", + "EventName": "PM_MRK_FAB_RSP_CLAIM_RTY", + "BriefDescription": "Sampled store did a rwitm and got a rty" + }, + {, + "EventCode": "0x0", + "EventName": "PM_SUSPENDED", + "BriefDescription": "Counter OFF" + }, + {, + "EventCode": "0x10010", + "EventName": "PM_PMC4_OVERFLOW", + "BriefDescription": "Overflow from counter 4" + }, + {, + "EventCode": "0x3E04A", + "EventName": "PM_DPTEG_FROM_RMEM", + "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's memory on the same Node or Group ( Remote) due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x2F152", + "EventName": "PM_MRK_FAB_RSP_DCLAIM_CYC", + "BriefDescription": "cycles L2 RC took for a dclaim" + }, + {, + "EventCode": "0x10004", + "EventName": "PM_CMPLU_STALL_LRQ_OTHER", + "BriefDescription": "Finish stall due to LRQ miscellaneous reasons, lost arbitration to LMQ slot, bank collisions, set prediction cleanup, set prediction multihit and others" + }, + {, + "EventCode": "0x4F150", + "EventName": "PM_MRK_FAB_RSP_RWITM_CYC", + "BriefDescription": "cycles L2 RC took for a rwitm" + }, + {, + "EventCode": "0x4E042", + "EventName": "PM_DPTEG_FROM_L3", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x1F054", + "EventName": "PM_TLB_HIT", + "BriefDescription": "Number of times the TLB had the data required by the instruction. Applies to both HPT and RPT" + }, + {, + "EventCode": "0x2C01E", + "EventName": "PM_CMPLU_STALL_SYNC_PMU_INT", + "BriefDescription": "Cycles in which the NTC instruction is waiting for a synchronous PMU interrupt" + }, + {, + "EventCode": "0x24050", + "EventName": "PM_IOPS_CMPL", + "BriefDescription": "Internal Operations completed" + }, + {, + "EventCode": "0x1515C", + "EventName": "PM_SYNC_MRK_BR_MPRED", + "BriefDescription": "Marked Branch mispredict that can cause a synchronous interrupt" + }, + {, + "EventCode": "0x300FA", + "EventName": "PM_INST_FROM_L3MISS", + "BriefDescription": "Marked instruction was reloaded from a location beyond the local chiplet" + }, + {, + "EventCode": "0x15044", + "EventName": "PM_IPTEG_FROM_L3_NO_CONFLICT", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 without conflict due to a instruction side request" + }, + {, + "EventCode": "0x15152", + "EventName": "PM_SYNC_MRK_BR_LINK", + "BriefDescription": "Marked Branch and link branch that can cause a synchronous interrupt" + }, + {, + "EventCode": "0x1E050", + "EventName": "PM_CMPLU_STALL_TEND", + "BriefDescription": "Finish stall because the NTF instruction was a tend instruction awaiting response from L2" + }, + {, + "EventCode": "0x1013E", + "EventName": "PM_MRK_LD_MISS_EXPOSED_CYC", + "BriefDescription": "Marked Load exposed Miss (use edge detect to count #)" + }, + {, + "EventCode": "0x25042", + "EventName": "PM_IPTEG_FROM_L3_MEPF", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 without dispatch conflicts hit on Mepf state. due to a instruction side request" + }, + {, + "EventCode": "0x14054", + "EventName": "PM_INST_PUMP_CPRED", + "BriefDescription": "Pump prediction correct. Counts across all types of pumps for an instruction fetch" + }, + {, + "EventCode": "0x4015E", + "EventName": "PM_MRK_FAB_RSP_RD_RTY", + "BriefDescription": "Sampled L2 reads retry count" + }, + {, + "EventCode": "0x45048", + "EventName": "PM_IPTEG_FROM_DL2L3_MOD", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a instruction side request" + }, + {, + "EventCode": "0x44052", + "EventName": "PM_INST_PUMP_MPRED", + "BriefDescription": "Pump misprediction. Counts across all types of pumps for an instruction fetch" + }, + {, + "EventCode": "0x30026", + "EventName": "PM_CMPLU_STALL_STORE_DATA", + "BriefDescription": "Finish stall because the next to finish instruction was a store waiting on data" + }, + {, + "EventCode": "0x301E6", + "EventName": "PM_MRK_DERAT_MISS", + "BriefDescription": "Erat Miss (TLB Access) All page sizes" + }, + {, + "EventCode": "0x24154", + "EventName": "PM_THRESH_ACC", + "BriefDescription": "This event increments every time the threshold event counter ticks. Thresholding must be enabled (via MMCRA) and the thresholding start event must occur for this counter to increment. It will stop incrementing when the thresholding stop event occurs or when thresholding is disabled, until the next time a configured thresholding start event occurs." + }, + {, + "EventCode": "0x2015E", + "EventName": "PM_MRK_FAB_RSP_RWITM_RTY", + "BriefDescription": "Sampled store did a rwitm and got a rty" + }, + {, + "EventCode": "0x200FA", + "EventName": "PM_BR_TAKEN_CMPL", + "BriefDescription": "New event for Branch Taken" + }, + {, + "EventCode": "0x35044", + "EventName": "PM_IPTEG_FROM_L31_ECO_SHR", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another core's ECO L3 on the same chip due to a instruction side request" + }, + {, + "EventCode": "0x4C010", + "EventName": "PM_CMPLU_STALL_STORE_PIPE_ARB", + "BriefDescription": "Finish stall because the NTF instruction was a store waiting for the next relaunch opportunity after an internal reject. This means the instruction is ready to relaunch and tried once but lost arbitration" + }, + {, + "EventCode": "0x4C01C", + "EventName": "PM_CMPLU_STALL_ST_FWD", + "BriefDescription": "Completion stall due to store forward" + }, + {, + "EventCode": "0x3515C", + "EventName": "PM_MRK_DATA_FROM_RL4", + "BriefDescription": "The processor's data cache was reloaded from another chip's L4 on the same Node or Group ( Remote) due to a marked load" + }, + {, + "EventCode": "0x2D14C", + "EventName": "PM_MRK_DATA_FROM_L31_ECO_SHR", + "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another core's ECO L3 on the same chip due to a marked load" + }, + {, + "EventCode": "0x40116", + "EventName": "PM_MRK_LARX_FIN", + "BriefDescription": "Larx finished" + }, + {, + "EventCode": "0x4C056", + "EventName": "PM_DTLB_MISS_16M", + "BriefDescription": "Data TLB Miss page size 16M" + }, + {, + "EventCode": "0x1003A", + "EventName": "PM_CMPLU_STALL_LSU_FIN", + "BriefDescription": "Finish stall because the NTF instruction was an LSU op (other than a load or a store) with all its dependencies met and just going through the LSU pipe to finish" + }, + {, + "EventCode": "0x3012A", + "EventName": "PM_MRK_L2_RC_DONE", + "BriefDescription": "Marked RC done" + }, + {, + "EventCode": "0x45044", + "EventName": "PM_IPTEG_FROM_L31_ECO_MOD", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's ECO L3 on the same chip due to a instruction side request" + } +] diff --git a/tools/perf/pmu-events/arch/powerpc/power9/marked.json b/tools/perf/pmu-events/arch/powerpc/power9/marked.json new file mode 100644 index 000000000000..b9df54fb37e3 --- /dev/null +++ b/tools/perf/pmu-events/arch/powerpc/power9/marked.json @@ -0,0 +1,647 @@ +[ + {, + "EventCode": "0x3C052", + "EventName": "PM_DATA_SYS_PUMP_MPRED", + "BriefDescription": "Final Pump Scope (system) mispredicted. Either the original scope was too small (Chip/Group) or the original scope was System and it should have been smaller. Counts for a demand load" + }, + {, + "EventCode": "0x3013E", + "EventName": "PM_MRK_STALL_CMPLU_CYC", + "BriefDescription": "Number of cycles the marked instruction is experiencing a stall while it is next to complete (NTC)" + }, + {, + "EventCode": "0x4F056", + "EventName": "PM_RADIX_PWC_L1_PDE_FROM_L3MISS", + "BriefDescription": "A Page Directory Entry was reloaded to a level 1 page walk cache from beyond the core's L3 data cache. The source could be local/remote/distant memory or another core's cache" + }, + {, + "EventCode": "0x24158", + "EventName": "PM_MRK_INST", + "BriefDescription": "An instruction was marked. Includes both Random Instruction Sampling (RIS) at decode time and Random Event Sampling (RES) at the time the configured event happens" + }, + {, + "EventCode": "0x1E046", + "EventName": "PM_DPTEG_FROM_L31_SHR", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another core's L3 on the same chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x3C04A", + "EventName": "PM_DATA_FROM_RMEM", + "BriefDescription": "The processor's data cache was reloaded from another chip's memory on the same Node or Group ( Remote) due to a demand load" + }, + {, + "EventCode": "0x2C01C", + "EventName": "PM_CMPLU_STALL_DMISS_REMOTE", + "BriefDescription": "Completion stall by Dcache miss which resolved from remote chip (cache or memory)" + }, + {, + "EventCode": "0x44040", + "EventName": "PM_INST_FROM_L2_DISP_CONFLICT_OTHER", + "BriefDescription": "The processor's Instruction cache was reloaded from local core's L2 with dispatch conflict due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x2E050", + "EventName": "PM_DARQ0_7_9_ENTRIES", + "BriefDescription": "Cycles in which 7,8, or 9 DARQ entries (out of 12) are in use" + }, + {, + "EventCode": "0x2D02E", + "EventName": "PM_RADIX_PWC_L3_PTE_FROM_L2", + "BriefDescription": "A Page Table Entry was reloaded to a level 3 page walk cache from the core's L2 data cache. This implies that a level 4 PWC access was not necessary for this translation" + }, + {, + "EventCode": "0x3F05E", + "EventName": "PM_RADIX_PWC_L3_PTE_FROM_L3", + "BriefDescription": "A Page Table Entry was reloaded to a level 3 page walk cache from the core's L3 data cache. This implies that a level 4 PWC access was not necessary for this translation" + }, + {, + "EventCode": "0x2E01E", + "EventName": "PM_CMPLU_STALL_NTC_FLUSH", + "BriefDescription": "Completion stall due to ntc flush" + }, + {, + "EventCode": "0x1F14C", + "EventName": "PM_MRK_DPTEG_FROM_LL4", + "BriefDescription": "A Page Table Entry was loaded into the TLB from the local chip's L4 cache due to a marked data side request.. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x20130", + "EventName": "PM_MRK_INST_DECODED", + "BriefDescription": "An instruction was marked at decode time. Random Instruction Sampling (RIS) only" + }, + {, + "EventCode": "0x3F144", + "EventName": "PM_MRK_DPTEG_FROM_L31_ECO_SHR", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another core's ECO L3 on the same chip due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x4D058", + "EventName": "PM_VECTOR_FLOP_CMPL", + "BriefDescription": "Vector FP instruction completed" + }, + {, + "EventCode": "0x14040", + "EventName": "PM_INST_FROM_L2_NO_CONFLICT", + "BriefDescription": "The processor's Instruction cache was reloaded from local core's L2 without conflict due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x4404E", + "EventName": "PM_INST_FROM_L3MISS_MOD", + "BriefDescription": "The processor's Instruction cache was reloaded from a location other than the local core's L3 due to a instruction fetch" + }, + {, + "EventCode": "0x3003A", + "EventName": "PM_CMPLU_STALL_EXCEPTION", + "BriefDescription": "Cycles in which the NTC instruction is not allowed to complete because it was interrupted by ANY exception, which has to be serviced before the instruction can complete" + }, + {, + "EventCode": "0x4F144", + "EventName": "PM_MRK_DPTEG_FROM_L31_ECO_MOD", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's ECO L3 on the same chip due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x3E044", + "EventName": "PM_DPTEG_FROM_L31_ECO_SHR", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another core's ECO L3 on the same chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x300F6", + "EventName": "PM_L1_DCACHE_RELOAD_VALID", + "BriefDescription": "DL1 reloaded due to Demand Load" + }, + {, + "EventCode": "0x1415E", + "EventName": "PM_MRK_DATA_FROM_L3MISS_CYC", + "BriefDescription": "Duration in cycles to reload from a location other than the local core's L3 due to a marked load" + }, + {, + "EventCode": "0x1E052", + "EventName": "PM_CMPLU_STALL_SLB", + "BriefDescription": "Finish stall because the NTF instruction was awaiting L2 response for an SLB" + }, + {, + "EventCode": "0x4404C", + "EventName": "PM_INST_FROM_DMEM", + "BriefDescription": "The processor's Instruction cache was reloaded from another chip's memory on the same Node or Group (Distant) due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x3000E", + "EventName": "PM_FXU_1PLUS_BUSY", + "BriefDescription": "At least one of the 4 FXU units is busy" + }, + {, + "EventCode": "0x2C048", + "EventName": "PM_DATA_FROM_LMEM", + "BriefDescription": "The processor's data cache was reloaded from the local chip's Memory due to a demand load" + }, + {, + "EventCode": "0x3000A", + "EventName": "PM_CMPLU_STALL_PM", + "BriefDescription": "Finish stall because the NTF instruction was issued to the Permute execution pipe and waiting to finish. Includes permute and decimal fixed point instructions (128 bit BCD arithmetic) + a few 128 bit fixpoint add/subtract instructions with carry. Not qualified by vector or multicycle" + }, + {, + "EventCode": "0x1504E", + "EventName": "PM_IPTEG_FROM_L2MISS", + "BriefDescription": "A Page Table Entry was loaded into the TLB from a location other than the local core's L2 due to a instruction side request" + }, + {, + "EventCode": "0x1C052", + "EventName": "PM_DATA_GRP_PUMP_MPRED_RTY", + "BriefDescription": "Final Pump Scope (Group) ended up larger than Initial Pump Scope (Chip) for a demand load" + }, + {, + "EventCode": "0x30008", + "EventName": "PM_DISP_STARVED", + "BriefDescription": "Dispatched Starved" + }, + {, + "EventCode": "0x14042", + "EventName": "PM_INST_FROM_L2", + "BriefDescription": "The processor's Instruction cache was reloaded from local core's L2 due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x4000C", + "EventName": "PM_FREQ_UP", + "BriefDescription": "Power Management: Above Threshold A" + }, + {, + "EventCode": "0x3C050", + "EventName": "PM_DATA_SYS_PUMP_CPRED", + "BriefDescription": "Initial and Final Pump Scope was system pump (prediction=correct) for a demand load" + }, + {, + "EventCode": "0x25040", + "EventName": "PM_IPTEG_FROM_L2_MEPF", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 hit without dispatch conflicts on Mepf state. due to a instruction side request" + }, + {, + "EventCode": "0x10132", + "EventName": "PM_MRK_INST_ISSUED", + "BriefDescription": "Marked instruction issued" + }, + {, + "EventCode": "0x1C046", + "EventName": "PM_DATA_FROM_L31_SHR", + "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another core's L3 on the same chip due to a demand load" + }, + {, + "EventCode": "0x2C044", + "EventName": "PM_DATA_FROM_L31_MOD", + "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another core's L3 on the same chip due to a demand load" + }, + {, + "EventCode": "0x2C04A", + "EventName": "PM_DATA_FROM_RL4", + "BriefDescription": "The processor's data cache was reloaded from another chip's L4 on the same Node or Group ( Remote) due to a demand load" + }, + {, + "EventCode": "0x24044", + "EventName": "PM_INST_FROM_L31_MOD", + "BriefDescription": "The processor's Instruction cache was reloaded with Modified (M) data from another core's L3 on the same chip due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x4C050", + "EventName": "PM_DATA_SYS_PUMP_MPRED_RTY", + "BriefDescription": "Final Pump Scope (system) ended up larger than Initial Pump Scope (Chip/Group) for a demand load" + }, + {, + "EventCode": "0x2C052", + "EventName": "PM_DATA_GRP_PUMP_MPRED", + "BriefDescription": "Final Pump Scope (Group) ended up either larger or smaller than Initial Pump Scope for a demand load" + }, + {, + "EventCode": "0x2F148", + "EventName": "PM_MRK_DPTEG_FROM_LMEM", + "BriefDescription": "A Page Table Entry was loaded into the TLB from the local chip's Memory due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x4D01A", + "EventName": "PM_CMPLU_STALL_EIEIO", + "BriefDescription": "Finish stall because the NTF instruction is an EIEIO waiting for response from L2" + }, + {, + "EventCode": "0x4F14E", + "EventName": "PM_MRK_DPTEG_FROM_L3MISS", + "BriefDescription": "A Page Table Entry was loaded into the TLB from a location other than the local core's L3 due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x4F05A", + "EventName": "PM_RADIX_PWC_L4_PTE_FROM_L3", + "BriefDescription": "A Page Table Entry was reloaded to a level 4 page walk cache from the core's L3 data cache. This is the deepest level of PWC possible for a translation" + }, + {, + "EventCode": "0x1F05A", + "EventName": "PM_RADIX_PWC_L4_PTE_FROM_L2", + "BriefDescription": "A Page Table Entry was reloaded to a level 4 page walk cache from the core's L2 data cache. This is the deepest level of PWC possible for a translation" + }, + {, + "EventCode": "0x30068", + "EventName": "PM_L1_ICACHE_RELOADED_PREF", + "BriefDescription": "Counts all Icache prefetch reloads ( includes demand turned into prefetch)" + }, + {, + "EventCode": "0x4C04A", + "EventName": "PM_DATA_FROM_OFF_CHIP_CACHE", + "BriefDescription": "The processor's data cache was reloaded either shared or modified data from another core's L2/L3 on a different chip (remote or distant) due to a demand load" + }, + {, + "EventCode": "0x400FE", + "EventName": "PM_DATA_FROM_MEMORY", + "BriefDescription": "The processor's data cache was reloaded from a memory location including L4 from local remote or distant due to a demand load" + }, + {, + "EventCode": "0x3F058", + "EventName": "PM_RADIX_PWC_L1_PDE_FROM_L3", + "BriefDescription": "A Page Directory Entry was reloaded to a level 1 page walk cache from the core's L3 data cache" + }, + {, + "EventCode": "0x4D142", + "EventName": "PM_MRK_DATA_FROM_L3", + "BriefDescription": "The processor's data cache was reloaded from local core's L3 due to a marked load" + }, + {, + "EventCode": "0x30050", + "EventName": "PM_SYS_PUMP_CPRED", + "BriefDescription": "Initial and Final Pump Scope was system pump for all data types excluding data prefetch (demand load,inst prefetch,inst fetch,xlate)" + }, + {, + "EventCode": "0x30028", + "EventName": "PM_CMPLU_STALL_SPEC_FINISH", + "BriefDescription": "Finish stall while waiting for the non-speculative finish of either a stcx waiting for its result or a load waiting for non-critical sectors of data and ECC" + }, + {, + "EventCode": "0x400F4", + "EventName": "PM_RUN_PURR", + "BriefDescription": "Run_PURR" + }, + {, + "EventCode": "0x3404C", + "EventName": "PM_INST_FROM_DL4", + "BriefDescription": "The processor's Instruction cache was reloaded from another chip's L4 on a different Node or Group (Distant) due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x3D05A", + "EventName": "PM_NTC_ISSUE_HELD_OTHER", + "BriefDescription": "The NTC instruction is being held at dispatch during regular pipeline cycles, or because the VSU is busy with multi-cycle instructions, or because of a write-back collision with VSU" + }, + {, + "EventCode": "0x2E048", + "EventName": "PM_DPTEG_FROM_LMEM", + "BriefDescription": "A Page Table Entry was loaded into the TLB from the local chip's Memory due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x2D02A", + "EventName": "PM_RADIX_PWC_L3_PDE_FROM_L2", + "BriefDescription": "A Page Directory Entry was reloaded to a level 3 page walk cache from the core's L2 data cache" + }, + {, + "EventCode": "0x1F05C", + "EventName": "PM_RADIX_PWC_L3_PDE_FROM_L3", + "BriefDescription": "A Page Directory Entry was reloaded to a level 3 page walk cache from the core's L3 data cache" + }, + {, + "EventCode": "0x4D04A", + "EventName": "PM_DARQ0_0_3_ENTRIES", + "BriefDescription": "Cycles in which 3 or less DARQ entries (out of 12) are in use" + }, + {, + "EventCode": "0x1404C", + "EventName": "PM_INST_FROM_LL4", + "BriefDescription": "The processor's Instruction cache was reloaded from the local chip's L4 cache due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x200FD", + "EventName": "PM_L1_ICACHE_MISS", + "BriefDescription": "Demand iCache Miss" + }, + {, + "EventCode": "0x34040", + "EventName": "PM_INST_FROM_L2_DISP_CONFLICT_LDHITST", + "BriefDescription": "The processor's Instruction cache was reloaded from local core's L2 with load hit store conflict due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x20138", + "EventName": "PM_MRK_ST_NEST", + "BriefDescription": "Marked store sent to nest" + }, + {, + "EventCode": "0x44048", + "EventName": "PM_INST_FROM_DL2L3_MOD", + "BriefDescription": "The processor's Instruction cache was reloaded with Modified (M) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x35046", + "EventName": "PM_IPTEG_FROM_L21_SHR", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another core's L2 on the same chip due to a instruction side request" + }, + {, + "EventCode": "0x4C04E", + "EventName": "PM_DATA_FROM_L3MISS_MOD", + "BriefDescription": "The processor's data cache was reloaded from a location other than the local core's L3 due to a demand load" + }, + {, + "EventCode": "0x401E0", + "EventName": "PM_MRK_INST_CMPL", + "BriefDescription": "marked instruction completed" + }, + {, + "EventCode": "0x2C128", + "EventName": "PM_MRK_DATA_FROM_DL2L3_SHR_CYC", + "BriefDescription": "Duration in cycles to reload with Shared (S) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a marked load" + }, + {, + "EventCode": "0x34044", + "EventName": "PM_INST_FROM_L31_ECO_SHR", + "BriefDescription": "The processor's Instruction cache was reloaded with Shared (S) data from another core's ECO L3 on the same chip due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x4E018", + "EventName": "PM_CMPLU_STALL_NTC_DISP_FIN", + "BriefDescription": "Finish stall because the NTF instruction was one that must finish at dispatch." + }, + {, + "EventCode": "0x2E05E", + "EventName": "PM_LMQ_EMPTY_CYC", + "BriefDescription": "Cycles in which the LMQ has no pending load misses for this thread" + }, + {, + "EventCode": "0x4C122", + "EventName": "PM_DARQ1_0_3_ENTRIES", + "BriefDescription": "Cycles in which 3 or fewer DARQ1 entries (out of 12) are in use" + }, + {, + "EventCode": "0x4F058", + "EventName": "PM_RADIX_PWC_L2_PTE_FROM_L3", + "BriefDescription": "A Page Table Entry was reloaded to a level 2 page walk cache from the core's L3 data cache. This implies that level 3 and level 4 PWC accesses were not necessary for this translation" + }, + {, + "EventCode": "0x14046", + "EventName": "PM_INST_FROM_L31_SHR", + "BriefDescription": "The processor's Instruction cache was reloaded with Shared (S) data from another core's L3 on the same chip due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x3012C", + "EventName": "PM_MRK_ST_FWD", + "BriefDescription": "Marked st forwards" + }, + {, + "EventCode": "0x101E0", + "EventName": "PM_MRK_INST_DISP", + "BriefDescription": "The thread has dispatched a randomly sampled marked instruction" + }, + {, + "EventCode": "0x1D058", + "EventName": "PM_DARQ0_10_12_ENTRIES", + "BriefDescription": "Cycles in which 10 or more DARQ entries (out of 12) are in use" + }, + {, + "EventCode": "0x300FE", + "EventName": "PM_DATA_FROM_L3MISS", + "BriefDescription": "Demand LD - L3 Miss (not L2 hit and not L3 hit)" + }, + {, + "EventCode": "0x30006", + "EventName": "PM_CMPLU_STALL_OTHER_CMPL", + "BriefDescription": "Instructions the core completed while this tread was stalled" + }, + {, + "EventCode": "0x1005C", + "EventName": "PM_CMPLU_STALL_DP", + "BriefDescription": "Finish stall because the NTF instruction was a scalar instruction issued to the Double Precision execution pipe and waiting to finish. Includes binary floating point instructions in 32 and 64 bit binary floating point format. Not qualified multicycle. Qualified by NOT vector" + }, + {, + "EventCode": "0x1E042", + "EventName": "PM_DPTEG_FROM_L2", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x1016E", + "EventName": "PM_MRK_BR_CMPL", + "BriefDescription": "Branch Instruction completed" + }, + {, + "EventCode": "0x2013A", + "EventName": "PM_MRK_BRU_FIN", + "BriefDescription": "bru marked instr finish" + }, + {, + "EventCode": "0x4F05E", + "EventName": "PM_RADIX_PWC_L3_PTE_FROM_L3MISS", + "BriefDescription": "A Page Table Entry was reloaded to a level 3 page walk cache from beyond the core's L3 data cache. This implies that a level 4 PWC access was not necessary for this translation. The source could be local/remote/distant memory or another core's cache" + }, + {, + "EventCode": "0x400FC", + "EventName": "PM_ITLB_MISS", + "BriefDescription": "ITLB Reloaded. Counts 1 per ITLB miss for HPT but multiple for radix depending on number of levels traveresed" + }, + {, + "EventCode": "0x2D024", + "EventName": "PM_RADIX_PWC_L2_HIT", + "BriefDescription": "A radix translation attempt missed in the TLB but hit on both the first and second levels of page walk cache." + }, + {, + "EventCode": "0x3F056", + "EventName": "PM_RADIX_PWC_L3_HIT", + "BriefDescription": "A radix translation attempt missed in the TLB but hit on the first, second, and third levels of page walk cache." + }, + {, + "EventCode": "0x4E014", + "EventName": "PM_TM_TX_PASS_RUN_INST", + "BriefDescription": "Run instructions spent in successful transactions" + }, + {, + "EventCode": "0x1E044", + "EventName": "PM_DPTEG_FROM_L3_NO_CONFLICT", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 without conflict due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x4D05A", + "EventName": "PM_NON_MATH_FLOP_CMPL", + "BriefDescription": "Non FLOP operation completed" + }, + {, + "EventCode": "0x101E2", + "EventName": "PM_MRK_BR_TAKEN_CMPL", + "BriefDescription": "Marked Branch Taken completed" + }, + {, + "EventCode": "0x3E158", + "EventName": "PM_MRK_STCX_FAIL", + "BriefDescription": "marked stcx failed" + }, + {, + "EventCode": "0x1C048", + "EventName": "PM_DATA_FROM_ON_CHIP_CACHE", + "BriefDescription": "The processor's data cache was reloaded either shared or modified data from another core's L2/L3 on the same chip due to a demand load" + }, + {, + "EventCode": "0x1C054", + "EventName": "PM_DATA_PUMP_CPRED", + "BriefDescription": "Pump prediction correct. Counts across all types of pumps for a demand load" + }, + {, + "EventCode": "0x4405E", + "EventName": "PM_DARQ_STORE_REJECT", + "BriefDescription": "The DARQ attempted to transmit a store into an LSAQ or SRQ entry but It was rejected. Divide by PM_DARQ_STORE_XMIT to get reject ratio" + }, + {, + "EventCode": "0x1C042", + "EventName": "PM_DATA_FROM_L2", + "BriefDescription": "The processor's data cache was reloaded from local core's L2 due to a demand load" + }, + {, + "EventCode": "0x1D14C", + "EventName": "PM_MRK_DATA_FROM_LL4", + "BriefDescription": "The processor's data cache was reloaded from the local chip's L4 cache due to a marked load" + }, + {, + "EventCode": "0x1006C", + "EventName": "PM_RUN_CYC_ST_MODE", + "BriefDescription": "Cycles run latch is set and core is in ST mode" + }, + {, + "EventCode": "0x3C044", + "EventName": "PM_DATA_FROM_L31_ECO_SHR", + "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another core's ECO L3 on the same chip due to a demand load" + }, + {, + "EventCode": "0x4C052", + "EventName": "PM_DATA_PUMP_MPRED", + "BriefDescription": "Pump misprediction. Counts across all types of pumps for a demand load" + }, + {, + "EventCode": "0x20050", + "EventName": "PM_GRP_PUMP_CPRED", + "BriefDescription": "Initial and Final Pump Scope and data sourced across this scope was group pump for all data types excluding data prefetch (demand load,inst prefetch,inst fetch,xlate)" + }, + {, + "EventCode": "0x1F150", + "EventName": "PM_MRK_ST_L2DISP_TO_CMPL_CYC", + "BriefDescription": "cycles from L2 rc disp to l2 rc completion" + }, + {, + "EventCode": "0x4505A", + "EventName": "PM_SP_FLOP_CMPL", + "BriefDescription": "SP instruction completed" + }, + {, + "EventCode": "0x4000A", + "EventName": "PM_ISQ_36_44_ENTRIES", + "BriefDescription": "Cycles in which 36 or more Issue Queue entries are in use. This is a shared event, not per thread. There are 44 issue queue entries across 4 slices in the whole core" + }, + {, + "EventCode": "0x2C12E", + "EventName": "PM_MRK_DATA_FROM_LL4_CYC", + "BriefDescription": "Duration in cycles to reload from the local chip's L4 cache due to a marked load" + }, + {, + "EventCode": "0x2C058", + "EventName": "PM_MEM_PREF", + "BriefDescription": "Memory prefetch for this thread. Includes L4" + }, + {, + "EventCode": "0x40012", + "EventName": "PM_L1_ICACHE_RELOADED_ALL", + "BriefDescription": "Counts all Icache reloads includes demand, prefetch, prefetch turned into demand and demand turned into prefetch" + }, + {, + "EventCode": "0x4003C", + "EventName": "PM_DISP_HELD_SYNC_HOLD", + "BriefDescription": "Cycles in which dispatch is held because of a synchronizing instruction in the pipeline" + }, + {, + "EventCode": "0x3003C", + "EventName": "PM_CMPLU_STALL_NESTED_TEND", + "BriefDescription": "Completion stall because the ISU is updating the TEXASR to keep track of the nested tend and decrement the TEXASR nested level. This is a short delay" + }, + {, + "EventCode": "0x3D05C", + "EventName": "PM_DISP_HELD_HB_FULL", + "BriefDescription": "Dispatch held due to History Buffer full. Could be GPR/VSR/VMR/FPR/CR/XVF; CR; XVF (XER/VSCR/FPSCR)" + }, + {, + "EventCode": "0x30052", + "EventName": "PM_SYS_PUMP_MPRED", + "BriefDescription": "Final Pump Scope (system) mispredicted. Either the original scope was too small (Chip/Group) or the original scope was System and it should have been smaller. Counts for all data types excluding data prefetch (demand load,inst prefetch,inst fetch,xlate)" + }, + {, + "EventCode": "0x2E044", + "EventName": "PM_DPTEG_FROM_L31_MOD", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's L3 on the same chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x34048", + "EventName": "PM_INST_FROM_DL2L3_SHR", + "BriefDescription": "The processor's Instruction cache was reloaded with Shared (S) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x45042", + "EventName": "PM_IPTEG_FROM_L3", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 due to a instruction side request" + }, + {, + "EventCode": "0x15042", + "EventName": "PM_IPTEG_FROM_L2", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 due to a instruction side request" + }, + {, + "EventCode": "0x1C05E", + "EventName": "PM_MEM_LOC_THRESH_LSU_MED", + "BriefDescription": "Local memory above threshold for data prefetch" + }, + {, + "EventCode": "0x40134", + "EventName": "PM_MRK_INST_TIMEO", + "BriefDescription": "marked Instruction finish timeout (instruction lost)" + }, + {, + "EventCode": "0x1002C", + "EventName": "PM_L1_DCACHE_RELOADED_ALL", + "BriefDescription": "L1 data cache reloaded for demand. If MMCR1[16] is 1, prefetches will be included as well" + }, + {, + "EventCode": "0x30130", + "EventName": "PM_MRK_INST_FIN", + "BriefDescription": "marked instruction finished" + }, + {, + "EventCode": "0x1F14A", + "EventName": "PM_MRK_DPTEG_FROM_RL2L3_SHR", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a marked data side request.. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x3504E", + "EventName": "PM_DARQ0_4_6_ENTRIES", + "BriefDescription": "Cycles in which 4, 5, or 6 DARQ entries (out of 12) are in use" + }, + {, + "EventCode": "0x30064", + "EventName": "PM_DARQ_STORE_XMIT", + "BriefDescription": "The DARQ attempted to transmit a store into an LSAQ or SRQ entry. Includes rejects. Not qualified by thread, so it includes counts for the whole core" + }, + {, + "EventCode": "0x45046", + "EventName": "PM_IPTEG_FROM_L21_MOD", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's L2 on the same chip due to a instruction side request" + }, + {, + "EventCode": "0x2C016", + "EventName": "PM_CMPLU_STALL_PASTE", + "BriefDescription": "Finish stall because the NTF instruction was a paste waiting for response from L2" + }, + {, + "EventCode": "0x24156", + "EventName": "PM_MRK_STCX_FIN", + "BriefDescription": "Number of marked stcx instructions finished. This includes instructions in the speculative path of a branch that may be flushed" + }, + {, + "EventCode": "0x15150", + "EventName": "PM_SYNC_MRK_PROBE_NOP", + "BriefDescription": "Marked probeNops which can cause synchronous interrupts" + }, + {, + "EventCode": "0x301E4", + "EventName": "PM_MRK_BR_MPRED_CMPL", + "BriefDescription": "Marked Branch Mispredicted" + } +] diff --git a/tools/perf/pmu-events/arch/powerpc/power9/memory.json b/tools/perf/pmu-events/arch/powerpc/power9/memory.json new file mode 100644 index 000000000000..9960d1c0dd44 --- /dev/null +++ b/tools/perf/pmu-events/arch/powerpc/power9/memory.json @@ -0,0 +1,132 @@ +[ + {, + "EventCode": "0x3006E", + "EventName": "PM_NEST_REF_CLK", + "BriefDescription": "Multiply by 4 to obtain the number of PB cycles" + }, + {, + "EventCode": "0x20010", + "EventName": "PM_PMC1_OVERFLOW", + "BriefDescription": "Overflow from counter 1" + }, + {, + "EventCode": "0x2005A", + "EventName": "PM_DARQ1_7_9_ENTRIES", + "BriefDescription": "Cycles in which 7 to 9 DARQ1 entries (out of 12) are in use" + }, + {, + "EventCode": "0x3C048", + "EventName": "PM_DATA_FROM_DL2L3_SHR", + "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a demand load" + }, + {, + "EventCode": "0x10008", + "EventName": "PM_RUN_SPURR", + "BriefDescription": "Run SPURR" + }, + {, + "EventCode": "0x200F6", + "EventName": "PM_LSU_DERAT_MISS", + "BriefDescription": "DERAT Reloaded due to a DERAT miss" + }, + {, + "EventCode": "0x4C048", + "EventName": "PM_DATA_FROM_DL2L3_MOD", + "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a demand load" + }, + {, + "EventCode": "0x1D15E", + "EventName": "PM_MRK_RUN_CYC", + "BriefDescription": "Run cycles in which a marked instruction is in the pipeline" + }, + {, + "EventCode": "0x4003E", + "EventName": "PM_LD_CMPL", + "BriefDescription": "count of Loads completed" + }, + {, + "EventCode": "0x2D156", + "EventName": "PM_MRK_DTLB_MISS_4K", + "BriefDescription": "Marked Data TLB Miss page size 4k" + }, + {, + "EventCode": "0x4C042", + "EventName": "PM_DATA_FROM_L3", + "BriefDescription": "The processor's data cache was reloaded from local core's L3 due to a demand load" + }, + {, + "EventCode": "0x4D02C", + "EventName": "PM_PMC1_REWIND", + "BriefDescription": "" + }, + {, + "EventCode": "0x15158", + "EventName": "PM_SYNC_MRK_L2HIT", + "BriefDescription": "Marked L2 Hits that can throw a synchronous interrupt" + }, + {, + "EventCode": "0x3404A", + "EventName": "PM_INST_FROM_RMEM", + "BriefDescription": "The processor's Instruction cache was reloaded from another chip's memory on the same Node or Group ( Remote) due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x301E2", + "EventName": "PM_MRK_ST_CMPL", + "BriefDescription": "Marked store completed and sent to nest" + }, + {, + "EventCode": "0x1C050", + "EventName": "PM_DATA_CHIP_PUMP_CPRED", + "BriefDescription": "Initial and Final Pump Scope was chip pump (prediction=correct) for a demand load" + }, + {, + "EventCode": "0x4C040", + "EventName": "PM_DATA_FROM_L2_DISP_CONFLICT_OTHER", + "BriefDescription": "The processor's data cache was reloaded from local core's L2 with dispatch conflict due to a demand load" + }, + {, + "EventCode": "0x2E05C", + "EventName": "PM_LSU_REJECT_ERAT_MISS", + "BriefDescription": "LSU Reject due to ERAT (up to 4 per cycles)" + }, + {, + "EventCode": "0x1000A", + "EventName": "PM_PMC3_REWIND", + "BriefDescription": "PMC3 rewind event. A rewind happens when a speculative event (such as latency or CPI stack) is selected on PMC3 and the stall reason or reload source did not match the one programmed in PMC3. When this occurs, the count in PMC3 will not change." + }, + {, + "EventCode": "0x3C058", + "EventName": "PM_LARX_FIN", + "BriefDescription": "Larx finished" + }, + {, + "EventCode": "0x1C040", + "EventName": "PM_DATA_FROM_L2_NO_CONFLICT", + "BriefDescription": "The processor's data cache was reloaded from local core's L2 without conflict due to a demand load" + }, + {, + "EventCode": "0x2C040", + "EventName": "PM_DATA_FROM_L2_MEPF", + "BriefDescription": "The processor's data cache was reloaded from local core's L2 hit without dispatch conflicts on Mepf state due to a demand load" + }, + {, + "EventCode": "0x2E05A", + "EventName": "PM_LRQ_REJECT", + "BriefDescription": "Internal LSU reject from LRQ. Rejects cause the load to go back to LRQ, but it stays contained within the LSU once it gets issued. This event counts the number of times the LRQ attempts to relaunch an instruction after a reject. Any load can suffer multiple rejects" + }, + {, + "EventCode": "0x2C05C", + "EventName": "PM_INST_GRP_PUMP_CPRED", + "BriefDescription": "Initial and Final Pump Scope was group pump (prediction=correct) for an instruction fetch (demand only)" + }, + {, + "EventCode": "0x4D056", + "EventName": "PM_NON_FMA_FLOP_CMPL", + "BriefDescription": "Non FMA instruction completed" + }, + {, + "EventCode": "0x3E050", + "EventName": "PM_DARQ1_4_6_ENTRIES", + "BriefDescription": "Cycles in which 4, 5, or 6 DARQ1 entries (out of 12) are in use" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/powerpc/power9/other.json b/tools/perf/pmu-events/arch/powerpc/power9/other.json new file mode 100644 index 000000000000..54cc3be00fc2 --- /dev/null +++ b/tools/perf/pmu-events/arch/powerpc/power9/other.json @@ -0,0 +1,2392 @@ +[ + {, + "EventCode": "0x3084", + "EventName": "PM_ISU1_ISS_HOLD_ALL", + "BriefDescription": "All ISU rejects" + }, + {, + "EventCode": "0xF880", + "EventName": "PM_SNOOP_TLBIE", + "BriefDescription": "TLBIE snoop" + }, + {, + "EventCode": "0x4088", + "EventName": "PM_IC_DEMAND_REQ", + "BriefDescription": "Demand Instruction fetch request" + }, + {, + "EventCode": "0x20A4", + "EventName": "PM_TM_TRESUME", + "BriefDescription": "TM resume instruction completed" + }, + {, + "EventCode": "0x40008", + "EventName": "PM_SRQ_EMPTY_CYC", + "BriefDescription": "Cycles in which the SRQ has at least one (out of four) empty slice" + }, + {, + "EventCode": "0x20064", + "EventName": "PM_IERAT_RELOAD_4K", + "BriefDescription": "IERAT reloaded (after a miss) for 4K pages" + }, + {, + "EventCode": "0x260B4", + "EventName": "PM_L3_P2_LCO_RTY", + "BriefDescription": "L3 initiated LCO received retry on port 2 (can try 4 times)" + }, + {, + "EventCode": "0x20006", + "EventName": "PM_DISP_HELD_ISSQ_FULL", + "BriefDescription": "Dispatch held due to Issue q full. Includes issue queue and branch queue" + }, + {, + "EventCode": "0x201E4", + "EventName": "PM_MRK_DATA_FROM_L3MISS", + "BriefDescription": "The processor's data cache was reloaded from a location other than the local core's L3 due to a marked load" + }, + {, + "EventCode": "0x4E044", + "EventName": "PM_DPTEG_FROM_L31_ECO_MOD", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's ECO L3 on the same chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x40B8", + "EventName": "PM_BR_MPRED_TAKEN_CR", + "BriefDescription": "A Conditional Branch that resolved to taken was mispredicted as not taken (due to the BHT Direction Prediction)." + }, + {, + "EventCode": "0xF8AC", + "EventName": "PM_DC_DEALLOC_NO_CONF", + "BriefDescription": "A demand load referenced a line in an active fuzzy prefetch stream. The stream could have been allocated through the hardware prefetch mechanism or through software.Fuzzy stream confirm (out of order effects, or pf cant keep up)" + }, + {, + "EventCode": "0xD090", + "EventName": "PM_LS0_DC_COLLISIONS", + "BriefDescription": "Read-write data cache collisions" + }, + {, + "EventCode": "0x40BC", + "EventName": "PM_THRD_PRIO_0_1_CYC", + "BriefDescription": "Cycles thread running at priority level 0 or 1" + }, + {, + "EventCode": "0x2084", + "EventName": "PM_FLUSH_HB_RESTORE_CYC", + "BriefDescription": "Cycles in which no new instructions can be dispatched to the ICT after a flush. History buffer recovery" + }, + {, + "EventCode": "0x4F054", + "EventName": "PM_RADIX_PWC_MISS", + "BriefDescription": "A radix translation attempt missed in the TLB and all levels of page walk cache." + }, + {, + "EventCode": "0x24048", + "EventName": "PM_INST_FROM_LMEM", + "BriefDescription": "The processor's Instruction cache was reloaded from the local chip's Memory due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0xD8B4", + "EventName": "PM_LSU0_LRQ_S0_VALID_CYC", + "BriefDescription": "Slot 0 of LRQ valid" + }, + {, + "EventCode": "0x2E052", + "EventName": "PM_TM_PASSED", + "BriefDescription": "Number of TM transactions that passed" + }, + {, + "EventCode": "0xD1A0", + "EventName": "PM_MRK_LSU_FLUSH_LHS", + "BriefDescription": "Effective Address alias flush : no EA match but Real Address match. If the data has not yet been returned for this load, the instruction will just be rejected, but if it has returned data, it will be flushed" + }, + {, + "EventCode": "0xF088", + "EventName": "PM_LSU0_STORE_REJECT", + "BriefDescription": "All internal store rejects cause the instruction to go back to the SRQ and go to sleep until woken up to try again after the condition has been met" + }, + {, + "EventCode": "0x360B2", + "EventName": "PM_L3_GRP_GUESS_WRONG_LOW", + "BriefDescription": "Initial scope=group (GS or NNS) but data from outside group (far or rem). Prediction too Low" + }, + {, + "EventCode": "0x168A6", + "EventName": "PM_TM_CAM_OVERFLOW", + "BriefDescription": "L3 TM cam overflow during L2 co of SC" + }, + {, + "EventCode": "0xE8B0", + "EventName": "PM_TEND_PEND_CYC", + "BriefDescription": "TEND latency per thread" + }, + {, + "EventCode": "0x4884", + "EventName": "PM_IBUF_FULL_CYC", + "BriefDescription": "Cycles No room in ibuff" + }, + {, + "EventCode": "0xD08C", + "EventName": "PM_LSU2_LDMX_FIN", + "BriefDescription": "New P9 instruction LDMX. The definition of this new PMU event is (from the ldmx RFC02491): The thread has executed an ldmx instruction that accessed a doubleword that contains an effective address within an enabled section of the Load Monitored region. This event, therefore, should not occur if the FSCR has disabled the load monitored facility (FSCR[52]) or disabled the EBB facility (FSCR[56])" + }, + {, + "EventCode": "0x300F8", + "EventName": "PM_TB_BIT_TRANS", + "BriefDescription": "timebase event" + }, + {, + "EventCode": "0x3C040", + "EventName": "PM_DATA_FROM_L2_DISP_CONFLICT_LDHITST", + "BriefDescription": "The processor's data cache was reloaded from local core's L2 with load hit store conflict due to a demand load" + }, + {, + "EventCode": "0xE0BC", + "EventName": "PM_LS0_PTE_TABLEWALK_CYC", + "BriefDescription": "Cycles when a tablewalk is pending on this thread on table 0" + }, + {, + "EventCode": "0x3884", + "EventName": "PM_ISU3_ISS_HOLD_ALL", + "BriefDescription": "All ISU rejects" + }, + {, + "EventCode": "0x460A6", + "EventName": "PM_RD_FORMING_SC", + "BriefDescription": "Read forming SC" + }, + {, + "EventCode": "0x468A0", + "EventName": "PM_L3_PF_OFF_CHIP_MEM", + "BriefDescription": "L3 PF from Off chip memory" + }, + {, + "EventCode": "0x268AA", + "EventName": "PM_L3_P1_LCO_DATA", + "BriefDescription": "LCO sent with data port 1" + }, + {, + "EventCode": "0xE894", + "EventName": "PM_LSU1_TM_L1_HIT", + "BriefDescription": "Load tm hit in L1" + }, + {, + "EventCode": "0x5888", + "EventName": "PM_IC_INVALIDATE", + "BriefDescription": "Ic line invalidated" + }, + {, + "EventCode": "0x2890", + "EventName": "PM_DISP_CLB_HELD_TLBIE", + "BriefDescription": "Dispatch Hold: Due to TLBIE" + }, + {, + "EventCode": "0x1001C", + "EventName": "PM_CMPLU_STALL_THRD", + "BriefDescription": "Completion Stalled because the thread was blocked" + }, + {, + "EventCode": "0x368A6", + "EventName": "PM_SNP_TM_HIT_T", + "BriefDescription": "Snp TM sthit T/Tn/Te" + }, + {, + "EventCode": "0x3001A", + "EventName": "PM_DATA_TABLEWALK_CYC", + "BriefDescription": "Data Tablewalk Cycles. Could be 1 or 2 active tablewalks. Includes data prefetches." + }, + {, + "EventCode": "0xD894", + "EventName": "PM_LS3_DC_COLLISIONS", + "BriefDescription": "Read-write data cache collisions" + }, + {, + "EventCode": "0x35158", + "EventName": "PM_MRK_DATA_FROM_L31_ECO_MOD_CYC", + "BriefDescription": "Duration in cycles to reload with Modified (M) data from another core's ECO L3 on the same chip due to a marked load" + }, + {, + "EventCode": "0xF0B4", + "EventName": "PM_DC_PREF_CONS_ALLOC", + "BriefDescription": "Prefetch stream allocated in the conservative phase by either the hardware prefetch mechanism or software prefetch" + }, + {, + "EventCode": "0xF894", + "EventName": "PM_LSU3_L1_CAM_CANCEL", + "BriefDescription": "ls3 l1 tm cam cancel" + }, + {, + "EventCode": "0x2888", + "EventName": "PM_FLUSH_DISP_TLBIE", + "BriefDescription": "Dispatch Flush: TLBIE" + }, + {, + "EventCode": "0xD1A4", + "EventName": "PM_MRK_LSU_FLUSH_SAO", + "BriefDescription": "A load-hit-load condition with Strong Address Ordering will have address compare disabled and flush" + }, + {, + "EventCode": "0x4E11E", + "EventName": "PM_MRK_DATA_FROM_DMEM_CYC", + "BriefDescription": "Duration in cycles to reload from another chip's memory on the same Node or Group (Distant) due to a marked load" + }, + {, + "EventCode": "0x5894", + "EventName": "PM_LWSYNC", + "BriefDescription": "Lwsync instruction decoded and transferred" + }, + {, + "EventCode": "0x14156", + "EventName": "PM_MRK_DATA_FROM_L2_CYC", + "BriefDescription": "Duration in cycles to reload from local core's L2 due to a marked load" + }, + {, + "EventCode": "0x468A6", + "EventName": "PM_RD_CLEARING_SC", + "BriefDescription": "Read clearing SC" + }, + {, + "EventCode": "0x50A0", + "EventName": "PM_HWSYNC", + "BriefDescription": "Hwsync instruction decoded and transferred" + }, + {, + "EventCode": "0x168B0", + "EventName": "PM_L3_P1_NODE_PUMP", + "BriefDescription": "L3 PF sent with nodal scope port 1, counts even retried requests" + }, + {, + "EventCode": "0xD0BC", + "EventName": "PM_LSU0_1_LRQF_FULL_CYC", + "BriefDescription": "Counts the number of cycles the LRQF is full. LRQF is the queue that holds loads between finish and completion. If it fills up, instructions stay in LRQ until completion, potentially backing up the LRQ" + }, + {, + "EventCode": "0x2D148", + "EventName": "PM_MRK_DATA_FROM_L2_DISP_CONFLICT_LDHITST", + "BriefDescription": "The processor's data cache was reloaded from local core's L2 with load hit store conflict due to a marked load" + }, + {, + "EventCode": "0x460A8", + "EventName": "PM_SN_HIT", + "BriefDescription": "Any port snooper hit L3. Up to 4 can happen in a cycle but we only count 1" + }, + {, + "EventCode": "0x360AA", + "EventName": "PM_L3_P0_CO_MEM", + "BriefDescription": "L3 CO to memory port 0 with or without data" + }, + {, + "EventCode": "0xF0A4", + "EventName": "PM_DC_PREF_HW_ALLOC", + "BriefDescription": "Prefetch stream allocated by the hardware prefetch mechanism" + }, + {, + "EventCode": "0xF0BC", + "EventName": "PM_LS2_UNALIGNED_ST", + "BriefDescription": "Store instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the Store of that size. If the Store wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty" + }, + {, + "EventCode": "0xD0AC", + "EventName": "PM_SRQ_SYNC_CYC", + "BriefDescription": "A sync is in the S2Q (edge detect to count)" + }, + {, + "EventCode": "0x401E6", + "EventName": "PM_MRK_INST_FROM_L3MISS", + "BriefDescription": "Marked instruction was reloaded from a location beyond the local chiplet" + }, + {, + "EventCode": "0x26082", + "EventName": "PM_L2_IC_INV", + "BriefDescription": "I-cache Invalidates sent over the realod bus to the core" + }, + {, + "EventCode": "0xC8AC", + "EventName": "PM_LSU_FLUSH_RELAUNCH_MISS", + "BriefDescription": "If a load that has already returned data and has to relaunch for any reason then gets a miss (erat, setp, data cache), it will often be flushed at relaunch time because the data might be inconsistent" + }, + {, + "EventCode": "0x260A4", + "EventName": "PM_L3_LD_HIT", + "BriefDescription": "L3 Hits for demand LDs" + }, + {, + "EventCode": "0xF0A0", + "EventName": "PM_DATA_STORE", + "BriefDescription": "All ops that drain from s2q to L2 containing data" + }, + {, + "EventCode": "0x1D148", + "EventName": "PM_MRK_DATA_FROM_RMEM", + "BriefDescription": "The processor's data cache was reloaded from another chip's memory on the same Node or Group ( Remote) due to a marked load" + }, + {, + "EventCode": "0x16088", + "EventName": "PM_L2_LOC_GUESS_CORRECT", + "BriefDescription": "L2 guess local (LNS) and guess was correct (ie data local)" + }, + {, + "EventCode": "0x160A4", + "EventName": "PM_L3_HIT", + "BriefDescription": "L3 Hits (L2 miss hitting L3, including data/instrn/xlate)" + }, + {, + "EventCode": "0xE09C", + "EventName": "PM_LSU0_TM_L1_MISS", + "BriefDescription": "Load tm L1 miss" + }, + {, + "EventCode": "0x168B4", + "EventName": "PM_L3_P1_LCO_RTY", + "BriefDescription": "L3 initiated LCO received retry on port 1 (can try 4 times)" + }, + {, + "EventCode": "0x268AC", + "EventName": "PM_L3_RD_USAGE", + "BriefDescription": "Rotating sample of 16 RD actives" + }, + {, + "EventCode": "0x1415C", + "EventName": "PM_MRK_DATA_FROM_L3_MEPF_CYC", + "BriefDescription": "Duration in cycles to reload from local core's L3 without dispatch conflicts hit on Mepf state due to a marked load" + }, + {, + "EventCode": "0xE880", + "EventName": "PM_L1_SW_PREF", + "BriefDescription": "Software L1 Prefetches, including SW Transient Prefetches" + }, + {, + "EventCode": "0x288C", + "EventName": "PM_DISP_CLB_HELD_BAL", + "BriefDescription": "Dispatch/CLB Hold: Balance Flush" + }, + {, + "EventCode": "0x101EA", + "EventName": "PM_MRK_L1_RELOAD_VALID", + "BriefDescription": "Marked demand reload" + }, + {, + "EventCode": "0x1D156", + "EventName": "PM_MRK_LD_MISS_L1_CYC", + "BriefDescription": "Marked ld latency" + }, + {, + "EventCode": "0x4C01A", + "EventName": "PM_CMPLU_STALL_DMISS_L3MISS", + "BriefDescription": "Completion stall due to cache miss resolving missed the L3" + }, + {, + "EventCode": "0x2006C", + "EventName": "PM_RUN_CYC_SMT4_MODE", + "BriefDescription": "Cycles in which this thread's run latch is set and the core is in SMT4 mode" + }, + {, + "EventCode": "0x5088", + "EventName": "PM_DECODE_FUSION_OP_PRESERV", + "BriefDescription": "Destructive op operand preservation" + }, + {, + "EventCode": "0x1D14E", + "EventName": "PM_MRK_DATA_FROM_OFF_CHIP_CACHE_CYC", + "BriefDescription": "Duration in cycles to reload either shared or modified data from another core's L2/L3 on a different chip (remote or distant) due to a marked load" + }, + {, + "EventCode": "0x509C", + "EventName": "PM_FORCED_NOP", + "BriefDescription": "Instruction was forced to execute as a nop because it was found to behave like a nop (have no effect) at decode time" + }, + {, + "EventCode": "0xC098", + "EventName": "PM_LS2_UNALIGNED_LD", + "BriefDescription": "Load instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the load of that size. If the load wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty" + }, + {, + "EventCode": "0x20058", + "EventName": "PM_DARQ1_10_12_ENTRIES", + "BriefDescription": "Cycles in which 10 or more DARQ1 entries (out of 12) are in use" + }, + {, + "EventCode": "0x360A6", + "EventName": "PM_SNP_TM_HIT_M", + "BriefDescription": "Snp TM st hit M/Mu" + }, + {, + "EventCode": "0x5898", + "EventName": "PM_LINK_STACK_INVALID_PTR", + "BriefDescription": "It is most often caused by certain types of flush where the pointer is not available. Can result in the data in the link stack becoming unusable." + }, + {, + "EventCode": "0x46088", + "EventName": "PM_L2_CHIP_PUMP", + "BriefDescription": "RC requests that were local (aka chip) pump attempts" + }, + {, + "EventCode": "0x28A0", + "EventName": "PM_TM_TSUSPEND", + "BriefDescription": "TM suspend instruction completed" + }, + {, + "EventCode": "0x20054", + "EventName": "PM_L1_PREF", + "BriefDescription": "A data line was written to the L1 due to a hardware or software prefetch" + }, + {, + "EventCode": "0xF888", + "EventName": "PM_LSU1_STORE_REJECT", + "BriefDescription": "All internal store rejects cause the instruction to go back to the SRQ and go to sleep until woken up to try again after the condition has been met" + }, + {, + "EventCode": "0x4505E", + "EventName": "PM_FLOP_CMPL", + "BriefDescription": "Floating Point Operation Finished" + }, + {, + "EventCode": "0x1D144", + "EventName": "PM_MRK_DATA_FROM_L3_DISP_CONFLICT", + "BriefDescription": "The processor's data cache was reloaded from local core's L3 with dispatch conflict due to a marked load" + }, + {, + "EventCode": "0x400FA", + "EventName": "PM_RUN_INST_CMPL", + "BriefDescription": "Run_Instructions" + }, + {, + "EventCode": "0x15154", + "EventName": "PM_SYNC_MRK_L3MISS", + "BriefDescription": "Marked L3 misses that can throw a synchronous interrupt" + }, + {, + "EventCode": "0xE0B4", + "EventName": "PM_LS0_TM_DISALLOW", + "BriefDescription": "A TM-ineligible instruction tries to execute inside a transaction and the LSU disallows it" + }, + {, + "EventCode": "0x26884", + "EventName": "PM_DSIDE_MRU_TOUCH", + "BriefDescription": "D-side L2 MRU touch sent to L2" + }, + {, + "EventCode": "0x30134", + "EventName": "PM_MRK_ST_CMPL_INT", + "BriefDescription": "marked store finished with intervention" + }, + {, + "EventCode": "0xC0B8", + "EventName": "PM_LSU_FLUSH_SAO", + "BriefDescription": "A load-hit-load condition with Strong Address Ordering will have address compare disabled and flush" + }, + {, + "EventCode": "0x50A8", + "EventName": "PM_EAT_FORCE_MISPRED", + "BriefDescription": "XL-form branch was mispredicted due to the predicted target address missing from EAT. The EAT forces a mispredict in this case since there is no predicated target to validate. This is a rare case that may occur when the EAT is full and a branch is issued" + }, + {, + "EventCode": "0xC094", + "EventName": "PM_LS0_UNALIGNED_LD", + "BriefDescription": "Load instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the load of that size. If the load wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty" + }, + {, + "EventCode": "0xF8BC", + "EventName": "PM_LS3_UNALIGNED_ST", + "BriefDescription": "Store instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the Store of that size. If the Store wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty" + }, + {, + "EventCode": "0x58B0", + "EventName": "PM_BTAC_GOOD_RESULT", + "BriefDescription": "BTAC predicts a taken branch and the BHT agrees, and the target address is correct" + }, + {, + "EventCode": "0x1C04C", + "EventName": "PM_DATA_FROM_LL4", + "BriefDescription": "The processor's data cache was reloaded from the local chip's L4 cache due to a demand load" + }, + {, + "EventCode": "0x3608E", + "EventName": "PM_TM_ST_CONF", + "BriefDescription": "TM Store (fav or non-fav) ran into conflict (failed)" + }, + {, + "EventCode": "0xD998", + "EventName": "PM_MRK_LSU_FLUSH_EMSH", + "BriefDescription": "An ERAT miss was detected after a set-p hit. Erat tracker indicates fail due to tlbmiss and the instruction gets flushed because the instruction was working on the wrong address" + }, + {, + "EventCode": "0xF8A0", + "EventName": "PM_NON_DATA_STORE", + "BriefDescription": "All ops that drain from s2q to L2 and contain no data" + }, + {, + "EventCode": "0x3F146", + "EventName": "PM_MRK_DPTEG_FROM_L21_SHR", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another core's L2 on the same chip due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x40A0", + "EventName": "PM_BR_UNCOND", + "BriefDescription": "Unconditional Branch Completed. HW branch prediction was not used for this branch. This can be an I-form branch, a B-form branch with BO-field set to branch always, or a B-form branch which was covenrted to a Resolve." + }, + {, + "EventCode": "0x1F056", + "EventName": "PM_RADIX_PWC_L1_HIT", + "BriefDescription": "A radix translation attempt missed in the TLB and only the first level page walk cache was a hit." + }, + {, + "EventCode": "0xF8A8", + "EventName": "PM_DC_PREF_FUZZY_CONF", + "BriefDescription": "A demand load referenced a line in an active fuzzy prefetch stream. The stream could have been allocated through the hardware prefetch mechanism or through software.Fuzzy stream confirm (out of order effects, or pf cant keep up)" + }, + {, + "EventCode": "0xF8A4", + "EventName": "PM_DC_PREF_SW_ALLOC", + "BriefDescription": "Prefetch stream allocated by software prefetching" + }, + {, + "EventCode": "0xE0A0", + "EventName": "PM_LSU2_TM_L1_MISS", + "BriefDescription": "Load tm L1 miss" + }, + {, + "EventCode": "0x2894", + "EventName": "PM_TM_OUTER_TEND", + "BriefDescription": "Completion time outer tend" + }, + {, + "EventCode": "0xF098", + "EventName": "PM_XLATE_HPT_MODE", + "BriefDescription": "LSU reports every cycle the thread is in HPT translation mode (as opposed to radix mode)" + }, + {, + "EventCode": "0x2C04E", + "EventName": "PM_LD_MISS_L1_FIN", + "BriefDescription": "Number of load instructions that finished with an L1 miss. Note that even if a load spans multiple slices this event will increment only once per load op." + }, + {, + "EventCode": "0x30162", + "EventName": "PM_MRK_LSU_DERAT_MISS", + "BriefDescription": "Marked derat reload (miss) for any page size" + }, + {, + "EventCode": "0x160A0", + "EventName": "PM_L3_PF_MISS_L3", + "BriefDescription": "L3 PF missed in L3" + }, + {, + "EventCode": "0x1C04A", + "EventName": "PM_DATA_FROM_RL2L3_SHR", + "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a demand load" + }, + {, + "EventCode": "0xD99C", + "EventName": "PM_MRK_LSU_FLUSH_UE", + "BriefDescription": "Correctable ECC error on reload data, reported at critical data forward time" + }, + {, + "EventCode": "0x268B0", + "EventName": "PM_L3_P1_GRP_PUMP", + "BriefDescription": "L3 PF sent with grp scope port 1, counts even retried requests" + }, + {, + "EventCode": "0x30016", + "EventName": "PM_CMPLU_STALL_SRQ_FULL", + "BriefDescription": "Finish stall because the NTF instruction was a store that was held in LSAQ because the SRQ was full" + }, + {, + "EventCode": "0x40B4", + "EventName": "PM_BR_PRED_TA", + "BriefDescription": "Conditional Branch Completed that had its target address predicted. Only XL-form branches set this event. This equal the sum of CCACHE, LSTACK, and PCACHE" + }, + {, + "EventCode": "0x40AC", + "EventName": "PM_BR_MPRED_CCACHE", + "BriefDescription": "Conditional Branch Completed that was Mispredicted due to the Count Cache Target Prediction" + }, + {, + "EventCode": "0x3688A", + "EventName": "PM_L2_RTY_LD", + "BriefDescription": "RC retries on PB for any load from core (excludes DCBFs)" + }, + {, + "EventCode": "0xE08C", + "EventName": "PM_LSU0_ERAT_HIT", + "BriefDescription": "Primary ERAT hit. There is no secondary ERAT" + }, + {, + "EventCode": "0xE088", + "EventName": "PM_LS2_ERAT_MISS_PREF", + "BriefDescription": "LS0 Erat miss due to prefetch" + }, + {, + "EventCode": "0xF0A8", + "EventName": "PM_DC_PREF_CONF", + "BriefDescription": "A demand load referenced a line in an active prefetch stream. The stream could have been allocated through the hardware prefetch mechanism or through software. Includes forwards and backwards streams" + }, + {, + "EventCode": "0x16888", + "EventName": "PM_L2_LOC_GUESS_WRONG", + "BriefDescription": "L2 guess local (LNS) and guess was not correct (ie data not on chip)" + }, + {, + "EventCode": "0xE0A4", + "EventName": "PM_TMA_REQ_L2", + "BriefDescription": "addrs only req to L2 only on the first one,Indication that Load footprint is not expanding" + }, + {, + "EventCode": "0x5884", + "EventName": "PM_DECODE_LANES_NOT_AVAIL", + "BriefDescription": "Decode has something to transmit but dispatch lanes are not available" + }, + {, + "EventCode": "0x3C042", + "EventName": "PM_DATA_FROM_L3_DISP_CONFLICT", + "BriefDescription": "The processor's data cache was reloaded from local core's L3 with dispatch conflict due to a demand load" + }, + {, + "EventCode": "0x168AA", + "EventName": "PM_L3_P1_LCO_NO_DATA", + "BriefDescription": "Dataless L3 LCO sent port 1" + }, + {, + "EventCode": "0x3D140", + "EventName": "PM_MRK_DATA_FROM_L2_DISP_CONFLICT_OTHER_CYC", + "BriefDescription": "Duration in cycles to reload from local core's L2 with dispatch conflict due to a marked load" + }, + {, + "EventCode": "0xC89C", + "EventName": "PM_LS1_LAUNCH_HELD_PREF", + "BriefDescription": "Number of times a load or store instruction was unable to launch/relaunch because a high priority prefetch used that relaunch cycle" + }, + {, + "EventCode": "0x4894", + "EventName": "PM_IC_RELOAD_PRIVATE", + "BriefDescription": "Reloading line was brought in private for a specific thread. Most lines are brought in shared for all eight threads. If RA does not match then invalidates and then brings it shared to other thread. In P7 line brought in private , then line was invalidat" + }, + {, + "EventCode": "0x1688E", + "EventName": "PM_TM_LD_CAUSED_FAIL", + "BriefDescription": "Non-TM Load caused any thread to fail" + }, + {, + "EventCode": "0x26084", + "EventName": "PM_L2_RCLD_DISP_FAIL_OTHER", + "BriefDescription": "All I-or-D side load dispatch attempts for this thread that failed due to reason other than address collision (excludes i_l2mru_tch_reqs)" + }, + {, + "EventCode": "0x101E4", + "EventName": "PM_MRK_L1_ICACHE_MISS", + "BriefDescription": "sampled Instruction suffered an icache Miss" + }, + {, + "EventCode": "0x20A0", + "EventName": "PM_TM_NESTED_TBEGIN", + "BriefDescription": "Completion Tm nested tbegin" + }, + {, + "EventCode": "0x368AA", + "EventName": "PM_L3_P1_CO_MEM", + "BriefDescription": "L3 CO to memory port 1 with or without data" + }, + {, + "EventCode": "0xC8A4", + "EventName": "PM_LSU3_FALSE_LHS", + "BriefDescription": "False LHS match detected" + }, + {, + "EventCode": "0xD9A4", + "EventName": "PM_MRK_LSU_FLUSH_LARX_STCX", + "BriefDescription": "A larx is flushed because an older larx has an LMQ reservation for the same thread. A stcx is flushed because an older stcx is in the LMQ. The flush happens when the older larx/stcx relaunches" + }, + {, + "EventCode": "0x4D012", + "EventName": "PM_PMC3_SAVED", + "BriefDescription": "PMC3 Rewind Value saved" + }, + {, + "EventCode": "0xE888", + "EventName": "PM_LS3_ERAT_MISS_PREF", + "BriefDescription": "LS1 Erat miss due to prefetch" + }, + {, + "EventCode": "0x368B4", + "EventName": "PM_L3_RD0_BUSY", + "BriefDescription": "Lifetime, sample of RD machine 0 valid" + }, + {, + "EventCode": "0x46080", + "EventName": "PM_L2_DISP_ALL_L2MISS", + "BriefDescription": "All successful Ld/St dispatches for this thread that were an L2 miss (excludes i_l2mru_tch_reqs)" + }, + {, + "EventCode": "0xF8B8", + "EventName": "PM_LS1_UNALIGNED_ST", + "BriefDescription": "Store instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the Store of that size. If the Store wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty" + }, + {, + "EventCode": "0x408C", + "EventName": "PM_L1_DEMAND_WRITE", + "BriefDescription": "Instruction Demand sectors written into IL1" + }, + {, + "EventCode": "0x368A8", + "EventName": "PM_SN_INVL", + "BriefDescription": "Any port snooper detects a store to a line in the Sx state and invalidates the line. Up to 4 can happen in a cycle but we only count 1" + }, + {, + "EventCode": "0x160B2", + "EventName": "PM_L3_LOC_GUESS_CORRECT", + "BriefDescription": "initial scope=node/chip (LNS) and data from local node (local) (pred successful) - always PFs only" + }, + {, + "EventCode": "0x48B4", + "EventName": "PM_DECODE_FUSION_CONST_GEN", + "BriefDescription": "32-bit constant generation" + }, + {, + "EventCode": "0x4D146", + "EventName": "PM_MRK_DATA_FROM_L21_MOD", + "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another core's L2 on the same chip due to a marked load" + }, + {, + "EventCode": "0xE080", + "EventName": "PM_S2Q_FULL", + "BriefDescription": "Cycles during which the S2Q is full" + }, + {, + "EventCode": "0x268B4", + "EventName": "PM_L3_P3_LCO_RTY", + "BriefDescription": "L3 initiated LCO received retry on port 3 (can try 4 times)" + }, + {, + "EventCode": "0xD8B8", + "EventName": "PM_LSU0_LMQ_S0_VALID", + "BriefDescription": "Slot 0 of LMQ valid" + }, + {, + "EventCode": "0x2098", + "EventName": "PM_TM_NESTED_TEND", + "BriefDescription": "Completion time nested tend" + }, + {, + "EventCode": "0x36084", + "EventName": "PM_L2_RCST_DISP", + "BriefDescription": "All D-side store dispatch attempts for this thread" + }, + {, + "EventCode": "0x368A0", + "EventName": "PM_L3_PF_OFF_CHIP_CACHE", + "BriefDescription": "L3 PF from Off chip cache" + }, + {, + "EventCode": "0x20056", + "EventName": "PM_TAKEN_BR_MPRED_CMPL", + "BriefDescription": "Total number of taken branches that were incorrectly predicted as not-taken. This event counts branches completed and does not include speculative instructions" + }, + {, + "EventCode": "0x4688A", + "EventName": "PM_L2_SYS_PUMP", + "BriefDescription": "RC requests that were system pump attempts" + }, + {, + "EventCode": "0xE090", + "EventName": "PM_LSU2_ERAT_HIT", + "BriefDescription": "Primary ERAT hit. There is no secondary ERAT" + }, + {, + "EventCode": "0x4001C", + "EventName": "PM_INST_IMC_MATCH_CMPL", + "BriefDescription": "IMC Match Count" + }, + {, + "EventCode": "0x40A8", + "EventName": "PM_BR_PRED_LSTACK", + "BriefDescription": "Conditional Branch Completed that used the Link Stack for Target Prediction" + }, + {, + "EventCode": "0x268A2", + "EventName": "PM_L3_CI_MISS", + "BriefDescription": "L3 castins miss (total count)" + }, + {, + "EventCode": "0x289C", + "EventName": "PM_TM_NON_FAV_TBEGIN", + "BriefDescription": "Dispatch time non favored tbegin" + }, + {, + "EventCode": "0xF08C", + "EventName": "PM_LSU2_STORE_REJECT", + "BriefDescription": "All internal store rejects cause the instruction to go back to the SRQ and go to sleep until woken up to try again after the condition has been met" + }, + {, + "EventCode": "0x360A0", + "EventName": "PM_L3_PF_ON_CHIP_CACHE", + "BriefDescription": "L3 PF from On chip cache" + }, + {, + "EventCode": "0x35152", + "EventName": "PM_MRK_DATA_FROM_L2MISS_CYC", + "BriefDescription": "Duration in cycles to reload from a location other than the local core's L2 due to a marked load" + }, + {, + "EventCode": "0x160AC", + "EventName": "PM_L3_SN_USAGE", + "BriefDescription": "Rotating sample of 16 snoop valids" + }, + {, + "EventCode": "0x16084", + "EventName": "PM_L2_RCLD_DISP", + "BriefDescription": "All I-or-D side load dispatch attempts for this thread (excludes i_l2mru_tch_reqs)" + }, + {, + "EventCode": "0x1608C", + "EventName": "PM_RC0_BUSY", + "BriefDescription": "RC mach 0 Busy. Used by PMU to sample ave RC lifetime (mach0 used as sample point)" + }, + {, + "EventCode": "0x36082", + "EventName": "PM_L2_LD_DISP", + "BriefDescription": "All successful I-or-D side load dispatches for this thread (excludes i_l2mru_tch_reqs)." + }, + {, + "EventCode": "0xF8B0", + "EventName": "PM_L3_SW_PREF", + "BriefDescription": "L3 load prefetch, sourced from a software prefetch stream, was sent to the nest" + }, + {, + "EventCode": "0xF884", + "EventName": "PM_TABLEWALK_CYC_PREF", + "BriefDescription": "tablewalk qualified for pte prefetches" + }, + {, + "EventCode": "0x4D144", + "EventName": "PM_MRK_DATA_FROM_L31_ECO_MOD", + "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another core's ECO L3 on the same chip due to a marked load" + }, + {, + "EventCode": "0x16884", + "EventName": "PM_L2_RCLD_DISP_FAIL_ADDR", + "BriefDescription": "All I-od-D side load dispatch attempts for this thread that failed due to address collision with RC/CO/SN/SQ machine (excludes i_l2mru_tch_reqs)" + }, + {, + "EventCode": "0x460A0", + "EventName": "PM_L3_PF_ON_CHIP_MEM", + "BriefDescription": "L3 PF from On chip memory" + }, + {, + "EventCode": "0xF084", + "EventName": "PM_PTE_PREFETCH", + "BriefDescription": "PTE prefetches" + }, + {, + "EventCode": "0x2D026", + "EventName": "PM_RADIX_PWC_L1_PDE_FROM_L2", + "BriefDescription": "A Page Directory Entry was reloaded to a level 1 page walk cache from the core's L2 data cache" + }, + {, + "EventCode": "0x48B0", + "EventName": "PM_BR_MPRED_PCACHE", + "BriefDescription": "Conditional Branch Completed that was Mispredicted due to pattern cache prediction" + }, + {, + "EventCode": "0x2C126", + "EventName": "PM_MRK_DATA_FROM_L2", + "BriefDescription": "The processor's data cache was reloaded from local core's L2 due to a marked load" + }, + {, + "EventCode": "0xE0AC", + "EventName": "PM_TM_FAIL_TLBIE", + "BriefDescription": "Transaction failed because there was a TLBIE hit in the bloom filter" + }, + {, + "EventCode": "0x260AA", + "EventName": "PM_L3_P0_LCO_DATA", + "BriefDescription": "LCO sent with data port 0" + }, + {, + "EventCode": "0x4888", + "EventName": "PM_IC_PREF_REQ", + "BriefDescription": "Instruction prefetch requests" + }, + {, + "EventCode": "0xC898", + "EventName": "PM_LS3_UNALIGNED_LD", + "BriefDescription": "Load instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the load of that size. If the load wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty" + }, + {, + "EventCode": "0x488C", + "EventName": "PM_IC_PREF_WRITE", + "BriefDescription": "Instruction prefetch written into IL1" + }, + {, + "EventCode": "0xF89C", + "EventName": "PM_XLATE_MISS", + "BriefDescription": "The LSU requested a line from L2 for translation. It may be satisfied from any source beyond L2. Includes speculative instructions" + }, + {, + "EventCode": "0x14158", + "EventName": "PM_MRK_DATA_FROM_L2_NO_CONFLICT_CYC", + "BriefDescription": "Duration in cycles to reload from local core's L2 without conflict due to a marked load" + }, + {, + "EventCode": "0x35156", + "EventName": "PM_MRK_DATA_FROM_L31_SHR_CYC", + "BriefDescription": "Duration in cycles to reload with Shared (S) data from another core's L3 on the same chip due to a marked load" + }, + {, + "EventCode": "0x268A6", + "EventName": "PM_TM_RST_SC", + "BriefDescription": "TM-snp rst RM SC" + }, + {, + "EventCode": "0x468A4", + "EventName": "PM_L3_TRANS_PF", + "BriefDescription": "L3 Transient prefetch received from L2" + }, + {, + "EventCode": "0x4094", + "EventName": "PM_IC_PREF_CANCEL_L2", + "BriefDescription": "L2 Squashed a demand or prefetch request" + }, + {, + "EventCode": "0x48AC", + "EventName": "PM_BR_MPRED_LSTACK", + "BriefDescription": "Conditional Branch Completed that was Mispredicted due to the Link Stack Target Prediction" + }, + {, + "EventCode": "0xE88C", + "EventName": "PM_LSU1_ERAT_HIT", + "BriefDescription": "Primary ERAT hit. There is no secondary ERAT" + }, + {, + "EventCode": "0xC0B4", + "EventName": "PM_LSU_FLUSH_WRK_ARND", + "BriefDescription": "LSU workaround flush. These flushes are setup with programmable scan only latches to perform various actions when the flush macro receives a trigger from the dbg macros. These actions include things like flushing the next op encountered for a particular thread or flushing the next op that is NTC op that is encountered on a particular slice. The kind of flush that the workaround is setup to perform is highly variable." + }, + {, + "EventCode": "0x34054", + "EventName": "PM_PARTIAL_ST_FIN", + "BriefDescription": "Any store finished by an LSU slice" + }, + {, + "EventCode": "0x5880", + "EventName": "PM_THRD_PRIO_6_7_CYC", + "BriefDescription": "Cycles thread running at priority level 6 or 7" + }, + {, + "EventCode": "0x4898", + "EventName": "PM_IC_DEMAND_L2_BR_REDIRECT", + "BriefDescription": "L2 I cache demand request due to branch Mispredict ( 15 cycle path)" + }, + {, + "EventCode": "0x4880", + "EventName": "PM_BANK_CONFLICT", + "BriefDescription": "Read blocked due to interleave conflict. The ifar logic will detect an interleave conflict and kill the data that was read that cycle." + }, + {, + "EventCode": "0x360B0", + "EventName": "PM_L3_P0_SYS_PUMP", + "BriefDescription": "L3 PF sent with sys scope port 0, counts even retried requests" + }, + {, + "EventCode": "0x3006A", + "EventName": "PM_IERAT_RELOAD_64K", + "BriefDescription": "IERAT Reloaded (Miss) for a 64k page" + }, + {, + "EventCode": "0xD8BC", + "EventName": "PM_LSU2_3_LRQF_FULL_CYC", + "BriefDescription": "Counts the number of cycles the LRQF is full. LRQF is the queue that holds loads between finish and completion. If it fills up, instructions stay in LRQ until completion, potentially backing up the LRQ" + }, + {, + "EventCode": "0x46086", + "EventName": "PM_L2_SN_M_RD_DONE", + "BriefDescription": "SNP dispatched for a read and was M (true M)" + }, + {, + "EventCode": "0x40154", + "EventName": "PM_MRK_FAB_RSP_BKILL", + "BriefDescription": "Marked store had to do a bkill" + }, + {, + "EventCode": "0xF094", + "EventName": "PM_LSU2_L1_CAM_CANCEL", + "BriefDescription": "ls2 l1 tm cam cancel" + }, + {, + "EventCode": "0x2D014", + "EventName": "PM_CMPLU_STALL_LRQ_FULL", + "BriefDescription": "Finish stall because the NTF instruction was a load that was held in LSAQ (load-store address queue) because the LRQ (load-reorder queue) was full" + }, + {, + "EventCode": "0x3E05E", + "EventName": "PM_L3_CO_MEPF", + "BriefDescription": "L3 castouts in Mepf state for this thread" + }, + {, + "EventCode": "0x460A2", + "EventName": "PM_L3_LAT_CI_HIT", + "BriefDescription": "L3 Lateral Castins Hit" + }, + {, + "EventCode": "0x3D14E", + "EventName": "PM_MRK_DATA_FROM_DL2L3_MOD", + "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a marked load" + }, + {, + "EventCode": "0x3D15E", + "EventName": "PM_MULT_MRK", + "BriefDescription": "mult marked instr" + }, + {, + "EventCode": "0x4084", + "EventName": "PM_EAT_FULL_CYC", + "BriefDescription": "Cycles No room in EAT" + }, + {, + "EventCode": "0x5098", + "EventName": "PM_LINK_STACK_WRONG_ADD_PRED", + "BriefDescription": "Link stack predicts wrong address, because of link stack design limitation or software violating the coding conventions" + }, + {, + "EventCode": "0x2C050", + "EventName": "PM_DATA_GRP_PUMP_CPRED", + "BriefDescription": "Initial and Final Pump Scope was group pump (prediction=correct) for a demand load" + }, + {, + "EventCode": "0xC0A4", + "EventName": "PM_LSU2_FALSE_LHS", + "BriefDescription": "False LHS match detected" + }, + {, + "EventCode": "0x58A0", + "EventName": "PM_LINK_STACK_CORRECT", + "BriefDescription": "Link stack predicts right address" + }, + {, + "EventCode": "0x4C05A", + "EventName": "PM_DTLB_MISS_1G", + "BriefDescription": "Data TLB reload (after a miss) page size 1G. Implies radix translation was used" + }, + {, + "EventCode": "0x36886", + "EventName": "PM_L2_SN_SX_I_DONE", + "BriefDescription": "SNP dispatched and went from Sx to Ix" + }, + {, + "EventCode": "0x4E04A", + "EventName": "PM_DPTEG_FROM_OFF_CHIP_CACHE", + "BriefDescription": "A Page Table Entry was loaded into the TLB either shared or modified data from another core's L2/L3 on a different chip (remote or distant) due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x2C12C", + "EventName": "PM_MRK_DATA_FROM_DL4_CYC", + "BriefDescription": "Duration in cycles to reload from another chip's L4 on a different Node or Group (Distant) due to a marked load" + }, + {, + "EventCode": "0x2608E", + "EventName": "PM_TM_LD_CONF", + "BriefDescription": "TM Load (fav or non-fav) ran into conflict (failed)" + }, + {, + "EventCode": "0x4080", + "EventName": "PM_INST_FROM_L1", + "BriefDescription": "Instruction fetches from L1. L1 instruction hit" + }, + {, + "EventCode": "0xE898", + "EventName": "PM_LSU3_TM_L1_HIT", + "BriefDescription": "Load tm hit in L1" + }, + {, + "EventCode": "0x260A0", + "EventName": "PM_L3_CO_MEM", + "BriefDescription": "L3 CO to memory OR of port 0 and 1 (lossy = may undercount if two cresp come in the same cyc)" + }, + {, + "EventCode": "0x16082", + "EventName": "PM_L2_CASTOUT_MOD", + "BriefDescription": "L2 Castouts - Modified (M,Mu,Me)" + }, + {, + "EventCode": "0xC09C", + "EventName": "PM_LS0_LAUNCH_HELD_PREF", + "BriefDescription": "Number of times a load or store instruction was unable to launch/relaunch because a high priority prefetch used that relaunch cycle" + }, + {, + "EventCode": "0xC8B8", + "EventName": "PM_LSU_FLUSH_LARX_STCX", + "BriefDescription": "A larx is flushed because an older larx has an LMQ reservation for the same thread. A stcx is flushed because an older stcx is in the LMQ. The flush happens when the older larx/stcx relaunches" + }, + {, + "EventCode": "0x260A6", + "EventName": "PM_NON_TM_RST_SC", + "BriefDescription": "Non-TM snp rst TM SC" + }, + {, + "EventCode": "0x3608A", + "EventName": "PM_L2_RTY_ST", + "BriefDescription": "RC retries on PB for any store from core (excludes DCBFs)" + }, + {, + "EventCode": "0x24040", + "EventName": "PM_INST_FROM_L2_MEPF", + "BriefDescription": "The processor's Instruction cache was reloaded from local core's L2 hit without dispatch conflicts on Mepf state. due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x209C", + "EventName": "PM_TM_FAV_TBEGIN", + "BriefDescription": "Dispatch time Favored tbegin" + }, + {, + "EventCode": "0x2D01E", + "EventName": "PM_ICT_NOSLOT_DISP_HELD_ISSQ", + "BriefDescription": "Ict empty for this thread due to dispatch hold on this thread due to Issue q full, BRQ full, XVCF Full, Count cache, Link, Tar full" + }, + {, + "EventCode": "0x50A4", + "EventName": "PM_FLUSH_MPRED", + "BriefDescription": "Branch mispredict flushes. Includes target and address misprecition" + }, + {, + "EventCode": "0x508C", + "EventName": "PM_SHL_CREATED", + "BriefDescription": "Store-Hit-Load Table Entry Created" + }, + {, + "EventCode": "0x1504C", + "EventName": "PM_IPTEG_FROM_LL4", + "BriefDescription": "A Page Table Entry was loaded into the TLB from the local chip's L4 cache due to a instruction side request" + }, + {, + "EventCode": "0x268A4", + "EventName": "PM_L3_LD_MISS", + "BriefDescription": "L3 Misses for demand LDs" + }, + {, + "EventCode": "0x26088", + "EventName": "PM_L2_GRP_GUESS_CORRECT", + "BriefDescription": "L2 guess grp (GS or NNS) and guess was correct (data intra-group AND ^on-chip)" + }, + {, + "EventCode": "0xD088", + "EventName": "PM_LSU0_LDMX_FIN", + "BriefDescription": "New P9 instruction LDMX. The definition of this new PMU event is (from the ldmx RFC02491): The thread has executed an ldmx instruction that accessed a doubleword that contains an effective address within an enabled section of the Load Monitored region. This event, therefore, should not occur if the FSCR has disabled the load monitored facility (FSCR[52]) or disabled the EBB facility (FSCR[56])." + }, + {, + "EventCode": "0xE8B4", + "EventName": "PM_LS1_TM_DISALLOW", + "BriefDescription": "A TM-ineligible instruction tries to execute inside a transaction and the LSU disallows it" + }, + {, + "EventCode": "0x1688C", + "EventName": "PM_RC_USAGE", + "BriefDescription": "Continuous 16 cycle (2to1) window where this signals rotates thru sampling each RC machine busy. PMU uses this wave to then do 16 cyc count to sample total number of machs running" + }, + {, + "EventCode": "0x3F054", + "EventName": "PM_RADIX_PWC_L4_PTE_FROM_L3MISS", + "BriefDescription": "A Page Table Entry was reloaded to a level 4 page walk cache from beyond the core's L3 data cache. This is the deepest level of PWC possible for a translation. The source could be local/remote/distant memory or another core's cache" + }, + {, + "EventCode": "0x2608A", + "EventName": "PM_ISIDE_DISP_FAIL_ADDR", + "BriefDescription": "All I-side dispatch attempts for this thread that failed due to a addr collision with another machine (excludes i_l2mru_tch_reqs)" + }, + {, + "EventCode": "0x50B4", + "EventName": "PM_TAGE_CORRECT_TAKEN_CMPL", + "BriefDescription": "The TAGE overrode BHT direction prediction and it was correct. Counted at completion for taken branches only" + }, + {, + "EventCode": "0x2090", + "EventName": "PM_DISP_CLB_HELD_SB", + "BriefDescription": "Dispatch/CLB Hold: Scoreboard" + }, + {, + "EventCode": "0xE0B0", + "EventName": "PM_TM_FAIL_NON_TX_CONFLICT", + "BriefDescription": "Non transactional conflict from LSU, gets reported to TEXASR" + }, + {, + "EventCode": "0xD198", + "EventName": "PM_MRK_LSU_FLUSH_ATOMIC", + "BriefDescription": "Quad-word loads (lq) are considered atomic because they always span at least 2 slices. If a snoop or store from another thread changes the data the load is accessing between the 2 or 3 pieces of the lq instruction, the lq will be flushed" + }, + {, + "EventCode": "0x201E0", + "EventName": "PM_MRK_DATA_FROM_MEMORY", + "BriefDescription": "The processor's data cache was reloaded from a memory location including L4 from local remote or distant due to a marked load" + }, + {, + "EventCode": "0x368A2", + "EventName": "PM_L3_L2_CO_MISS", + "BriefDescription": "L2 CO miss" + }, + {, + "EventCode": "0x3608C", + "EventName": "PM_CO0_BUSY", + "BriefDescription": "CO mach 0 Busy. Used by PMU to sample ave CO lifetime (mach0 used as sample point)" + }, + {, + "EventCode": "0x2C122", + "EventName": "PM_MRK_DATA_FROM_L3_DISP_CONFLICT_CYC", + "BriefDescription": "Duration in cycles to reload from local core's L3 with dispatch conflict due to a marked load" + }, + {, + "EventCode": "0x35154", + "EventName": "PM_MRK_DATA_FROM_L3_CYC", + "BriefDescription": "Duration in cycles to reload from local core's L3 due to a marked load" + }, + {, + "EventCode": "0x1D140", + "EventName": "PM_MRK_DATA_FROM_L31_MOD_CYC", + "BriefDescription": "Duration in cycles to reload with Modified (M) data from another core's L3 on the same chip due to a marked load" + }, + {, + "EventCode": "0x4404A", + "EventName": "PM_INST_FROM_OFF_CHIP_CACHE", + "BriefDescription": "The processor's Instruction cache was reloaded either shared or modified data from another core's L2/L3 on a different chip (remote or distant) due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x28AC", + "EventName": "PM_TM_FAIL_SELF", + "BriefDescription": "TM aborted because a self-induced conflict occurred in Suspended state, due to one of the following: a store to a storage location that was previously accessed transactionally; a dcbf, dcbi, or icbi specify- ing a block that was previously accessed transactionally; a dcbst specifying a block that was previously written transactionally; or a tlbie that specifies a translation that was pre- viously used transactionally" + }, + {, + "EventCode": "0x45056", + "EventName": "PM_SCALAR_FLOP_CMPL", + "BriefDescription": "Scalar flop operation completed" + }, + {, + "EventCode": "0x16092", + "EventName": "PM_L2_LD_MISS_128B", + "BriefDescription": "All successful D-side load dispatches that were an L2 miss (NOT Sx,Tx,Mx) for this thread and the RC calculated the request should be for 128B (i.e., M=0)" + }, + {, + "EventCode": "0x2E014", + "EventName": "PM_STCX_FIN", + "BriefDescription": "Number of stcx instructions finished. This includes instructions in the speculative path of a branch that may be flushed" + }, + {, + "EventCode": "0xE0B8", + "EventName": "PM_LS2_TM_DISALLOW", + "BriefDescription": "A TM-ineligible instruction tries to execute inside a transaction and the LSU disallows it" + }, + {, + "EventCode": "0x2094", + "EventName": "PM_TM_OUTER_TBEGIN", + "BriefDescription": "Completion time outer tbegin" + }, + {, + "EventCode": "0x160B4", + "EventName": "PM_L3_P0_LCO_RTY", + "BriefDescription": "L3 initiated LCO received retry on port 0 (can try 4 times)" + }, + {, + "EventCode": "0x36892", + "EventName": "PM_DSIDE_OTHER_64B_L2MEMACC", + "BriefDescription": "Valid when first beat of data comes in for an D-side fetch where data came EXCLUSIVELY from memory that was for hpc_read64, (RC had to fetch other 64B of a line from MC) i.e., number of times RC had to go to memory to get 'missing' 64B" + }, + {, + "EventCode": "0x20A8", + "EventName": "PM_TM_FAIL_FOOTPRINT_OVERFLOW", + "BriefDescription": "TM aborted because the tracking limit for transactional storage accesses was exceeded.. Asynchronous" + }, + {, + "EventCode": "0x30018", + "EventName": "PM_ICT_NOSLOT_DISP_HELD_HB_FULL", + "BriefDescription": "Ict empty for this thread due to dispatch holds because the History Buffer was full. Could be GPR/VSR/VMR/FPR/CR/XVF; CR; XVF (XER/VSCR/FPSCR)" + }, + {, + "EventCode": "0xC894", + "EventName": "PM_LS1_UNALIGNED_LD", + "BriefDescription": "Load instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the load of that size. If the load wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty" + }, + {, + "EventCode": "0x360A2", + "EventName": "PM_L3_L2_CO_HIT", + "BriefDescription": "L2 CO hits" + }, + {, + "EventCode": "0x36092", + "EventName": "PM_DSIDE_L2MEMACC", + "BriefDescription": "Valid when first beat of data comes in for an D-side fetch where data came EXCLUSIVELY from memory (excluding hpcread64 accesses), i.e., total memory accesses by RCs" + }, + {, + "EventCode": "0x10138", + "EventName": "PM_MRK_BR_2PATH", + "BriefDescription": "marked branches which are not strongly biased" + }, + {, + "EventCode": "0x2884", + "EventName": "PM_ISYNC", + "BriefDescription": "Isync completion count per thread" + }, + {, + "EventCode": "0x16882", + "EventName": "PM_L2_CASTOUT_SHR", + "BriefDescription": "L2 Castouts - Shared (Tx,Sx)" + }, + {, + "EventCode": "0xD884", + "EventName": "PM_LSU3_SET_MPRED", + "BriefDescription": "Set prediction(set-p) miss. The entry was not found in the Set prediction table" + }, + {, + "EventCode": "0x26092", + "EventName": "PM_L2_LD_MISS_64B", + "BriefDescription": "All successful D-side load dispatches that were an L2 miss (NOT Sx,Tx,Mx) for this thread and the RC calculated the request should be for 64B(i.e., M=1)" + }, + {, + "EventCode": "0x26080", + "EventName": "PM_L2_LD_MISS", + "BriefDescription": "All successful D-Side Load dispatches that were an L2 miss for this thread" + }, + {, + "EventCode": "0x3D14C", + "EventName": "PM_MRK_DATA_FROM_DMEM", + "BriefDescription": "The processor's data cache was reloaded from another chip's memory on the same Node or Group (Distant) due to a marked load" + }, + {, + "EventCode": "0x100FA", + "EventName": "PM_ANY_THRD_RUN_CYC", + "BriefDescription": "Cycles in which at least one thread has the run latch set" + }, + {, + "EventCode": "0x2C12A", + "EventName": "PM_MRK_DATA_FROM_RMEM_CYC", + "BriefDescription": "Duration in cycles to reload from another chip's memory on the same Node or Group ( Remote) due to a marked load" + }, + {, + "EventCode": "0x25048", + "EventName": "PM_IPTEG_FROM_LMEM", + "BriefDescription": "A Page Table Entry was loaded into the TLB from the local chip's Memory due to a instruction side request" + }, + {, + "EventCode": "0xD8A8", + "EventName": "PM_ISLB_MISS", + "BriefDescription": "Instruction SLB miss - Total of all segment sizes" + }, + {, + "EventCode": "0xD19C", + "EventName": "PM_MRK_LSU_FLUSH_RELAUNCH_MISS", + "BriefDescription": "If a load that has already returned data and has to relaunch for any reason then gets a miss (erat, setp, data cache), it will often be flushed at relaunch time because the data might be inconsistent" + }, + {, + "EventCode": "0x260A2", + "EventName": "PM_L3_CI_HIT", + "BriefDescription": "L3 Castins Hit (total count)" + }, + {, + "EventCode": "0x44054", + "EventName": "PM_VECTOR_LD_CMPL", + "BriefDescription": "Number of vector load instructions completed" + }, + {, + "EventCode": "0x1E05C", + "EventName": "PM_CMPLU_STALL_NESTED_TBEGIN", + "BriefDescription": "Completion stall because the ISU is updating the TEXASR to keep track of the nested tbegin. This is a short delay, and it includes ROT" + }, + {, + "EventCode": "0x1608E", + "EventName": "PM_ST_CAUSED_FAIL", + "BriefDescription": "Non-TM Store caused any thread to fail" + }, + {, + "EventCode": "0x3080", + "EventName": "PM_ISU0_ISS_HOLD_ALL", + "BriefDescription": "All ISU rejects" + }, + {, + "EventCode": "0x1515A", + "EventName": "PM_SYNC_MRK_L2MISS", + "BriefDescription": "Marked L2 Miss that can throw a synchronous interrupt" + }, + {, + "EventCode": "0x26892", + "EventName": "PM_L2_ST_MISS_64B", + "BriefDescription": "All successful D-side store dispatches that were an L2 miss (NOT Sx,Tx,Mx) for this thread and the RC calculated the request should be for 64B (i.e., M=1)" + }, + {, + "EventCode": "0x2688C", + "EventName": "PM_CO_USAGE", + "BriefDescription": "Continuous 16 cycle (2to1) window where this signals rotates thru sampling each CO machine busy. PMU uses this wave to then do 16 cyc count to sample total number of machs running" + }, + {, + "EventCode": "0xD084", + "EventName": "PM_LSU2_SET_MPRED", + "BriefDescription": "Set prediction(set-p) miss. The entry was not found in the Set prediction table" + }, + {, + "EventCode": "0x48B8", + "EventName": "PM_BR_MPRED_TAKEN_TA", + "BriefDescription": "Conditional Branch Completed that was Mispredicted due to the Target Address Prediction from the Count Cache or Link Stack. Only XL-form branches that resolved Taken set this event." + }, + {, + "EventCode": "0x50B0", + "EventName": "PM_BTAC_BAD_RESULT", + "BriefDescription": "BTAC thinks branch will be taken but it is either predicted not-taken by the BHT, or the target address is wrong (less common). In both cases, a redirect will happen" + }, + {, + "EventCode": "0xD888", + "EventName": "PM_LSU1_LDMX_FIN", + "BriefDescription": "New P9 instruction LDMX. The definition of this new PMU event is (from the ldmx RFC02491): The thread has executed an ldmx instruction that accessed a doubleword that contains an effective address within an enabled section of the Load Monitored region. This event, therefore, should not occur if the FSCR has disabled the load monitored facility (FSCR[52]) or disabled the EBB facility (FSCR[56])." + }, + {, + "EventCode": "0x58B4", + "EventName": "PM_TAGE_CORRECT", + "BriefDescription": "The TAGE overrode BHT direction prediction and it was correct. Includes taken and not taken and is counted at execution time" + }, + {, + "EventCode": "0x3688C", + "EventName": "PM_SN_USAGE", + "BriefDescription": "Continuous 16 cycle (2to1) window where this signals rotates thru sampling each SN machine busy. PMU uses this wave to then do 16 cyc count to sample total number of machs running" + }, + {, + "EventCode": "0x46084", + "EventName": "PM_L2_RCST_DISP_FAIL_OTHER", + "BriefDescription": "All D-side store dispatch attempts for this thread that failed due to reason other than address collision" + }, + {, + "EventCode": "0xF0AC", + "EventName": "PM_DC_PREF_STRIDED_CONF", + "BriefDescription": "A demand load referenced a line in an active strided prefetch stream. The stream could have been allocated through the hardware prefetch mechanism or through software." + }, + {, + "EventCode": "0x45054", + "EventName": "PM_FMA_CMPL", + "BriefDescription": "two flops operation completed (fmadd, fnmadd, fmsub, fnmsub) Scalar instructions only. " + }, + {, + "EventCode": "0x5090", + "EventName": "PM_SHL_ST_DISABLE", + "BriefDescription": "Store-Hit-Load Table Read Hit with entry Disabled (entry was disabled due to the entry shown to not prevent the flush)" + }, + {, + "EventCode": "0x201E8", + "EventName": "PM_THRESH_EXC_512", + "BriefDescription": "Threshold counter exceeded a value of 512" + }, + {, + "EventCode": "0x5084", + "EventName": "PM_DECODE_FUSION_EXT_ADD", + "BriefDescription": "32-bit extended addition" + }, + {, + "EventCode": "0x36080", + "EventName": "PM_L2_INST", + "BriefDescription": "All successful I-side dispatches for this thread (excludes i_l2mru_tch reqs)." + }, + {, + "EventCode": "0x3504C", + "EventName": "PM_IPTEG_FROM_DL4", + "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's L4 on a different Node or Group (Distant) due to a instruction side request" + }, + {, + "EventCode": "0xD890", + "EventName": "PM_LS1_DC_COLLISIONS", + "BriefDescription": "Read-write data cache collisions" + }, + {, + "EventCode": "0x1688A", + "EventName": "PM_ISIDE_DISP", + "BriefDescription": "All I-side dispatch attempts for this thread (excludes i_l2mru_tch_reqs)" + }, + {, + "EventCode": "0x468AA", + "EventName": "PM_L3_P1_CO_L31", + "BriefDescription": "L3 CO to L3.1 (LCO) port 1 with or without data" + }, + {, + "EventCode": "0x28B0", + "EventName": "PM_DISP_HELD_TBEGIN", + "BriefDescription": "This outer tbegin transaction cannot be dispatched until the previous tend instruction completes" + }, + {, + "EventCode": "0xE8A0", + "EventName": "PM_LSU3_TM_L1_MISS", + "BriefDescription": "Load tm L1 miss" + }, + {, + "EventCode": "0x2C05E", + "EventName": "PM_INST_GRP_PUMP_MPRED", + "BriefDescription": "Final Pump Scope (Group) ended up either larger or smaller than Initial Pump Scope for an instruction fetch (demand only)" + }, + {, + "EventCode": "0xC8BC", + "EventName": "PM_STCX_SUCCESS_CMPL", + "BriefDescription": "Number of stcx instructions that completed successfully" + }, + {, + "EventCode": "0xE098", + "EventName": "PM_LSU2_TM_L1_HIT", + "BriefDescription": "Load tm hit in L1" + }, + {, + "EventCode": "0x44044", + "EventName": "PM_INST_FROM_L31_ECO_MOD", + "BriefDescription": "The processor's Instruction cache was reloaded with Modified (M) data from another core's ECO L3 on the same chip due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x16886", + "EventName": "PM_CO_DISP_FAIL", + "BriefDescription": "CO dispatch failed due to all CO machines being busy" + }, + {, + "EventCode": "0x3D146", + "EventName": "PM_MRK_DATA_FROM_L3_NO_CONFLICT", + "BriefDescription": "The processor's data cache was reloaded from local core's L3 without conflict due to a marked load" + }, + {, + "EventCode": "0x16892", + "EventName": "PM_L2_ST_MISS_128B", + "BriefDescription": "All successful D-side store dispatches that were an L2 miss (NOT Sx,Tx,Mx) for this thread and the RC calculated the request should be for 128B (i.e., M=0)" + }, + {, + "EventCode": "0x26890", + "EventName": "PM_ISIDE_L2MEMACC", + "BriefDescription": "Valid when first beat of data comes in for an I-side fetch where data came from memory" + }, + {, + "EventCode": "0xD094", + "EventName": "PM_LS2_DC_COLLISIONS", + "BriefDescription": "Read-write data cache collisions" + }, + {, + "EventCode": "0x3C05E", + "EventName": "PM_MEM_RWITM", + "BriefDescription": "Memory Read With Intent to Modify for this thread" + }, + {, + "EventCode": "0x26882", + "EventName": "PM_L2_DC_INV", + "BriefDescription": "D-cache invalidates sent over the reload bus to the core" + }, + {, + "EventCode": "0xC090", + "EventName": "PM_LSU_STCX", + "BriefDescription": "STCX sent to nest, i.e. total" + }, + {, + "EventCode": "0xD080", + "EventName": "PM_LSU0_SET_MPRED", + "BriefDescription": "Set prediction(set-p) miss. The entry was not found in the Set prediction table" + }, + {, + "EventCode": "0x2C120", + "EventName": "PM_MRK_DATA_FROM_L2_NO_CONFLICT", + "BriefDescription": "The processor's data cache was reloaded from local core's L2 without conflict due to a marked load" + }, + {, + "EventCode": "0x36086", + "EventName": "PM_L2_RC_ST_DONE", + "BriefDescription": "RC did store to line that was Tx or Sx" + }, + {, + "EventCode": "0xE8AC", + "EventName": "PM_TM_FAIL_TX_CONFLICT", + "BriefDescription": "Transactional conflict from LSU, gets reported to TEXASR" + }, + {, + "EventCode": "0x48A8", + "EventName": "PM_DECODE_FUSION_LD_ST_DISP", + "BriefDescription": "32-bit displacement D-form and 16-bit displacement X-form" + }, + {, + "EventCode": "0x3D144", + "EventName": "PM_MRK_DATA_FROM_L2_MEPF_CYC", + "BriefDescription": "Duration in cycles to reload from local core's L2 hit without dispatch conflicts on Mepf state. due to a marked load" + }, + {, + "EventCode": "0x44046", + "EventName": "PM_INST_FROM_L21_MOD", + "BriefDescription": "The processor's Instruction cache was reloaded with Modified (M) data from another core's L2 on the same chip due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x40B0", + "EventName": "PM_BR_PRED_TAKEN_CR", + "BriefDescription": "Conditional Branch that had its direction predicted. I-form branches do not set this event. In addition, B-form branches which do not use the BHT do not set this event - these are branches with BO-field set to 'always taken' and branches" + }, + {, + "EventCode": "0x15040", + "EventName": "PM_IPTEG_FROM_L2_NO_CONFLICT", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 without conflict due to a instruction side request" + }, + {, + "EventCode": "0xD9A0", + "EventName": "PM_MRK_LSU_FLUSH_LHL_SHL", + "BriefDescription": "The instruction was flushed because of a sequential load/store consistency. If a load or store hits on an older load that has either been snooped (for loads) or has stale data (for stores)." + }, + {, + "EventCode": "0x35042", + "EventName": "PM_IPTEG_FROM_L3_DISP_CONFLICT", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 with dispatch conflict due to a instruction side request" + }, + {, + "EventCode": "0xF898", + "EventName": "PM_XLATE_RADIX_MODE", + "BriefDescription": "LSU reports every cycle the thread is in radix translation mode (as opposed to HPT mode)" + }, + {, + "EventCode": "0x2D142", + "EventName": "PM_MRK_DATA_FROM_L3_MEPF", + "BriefDescription": "The processor's data cache was reloaded from local core's L3 without dispatch conflicts hit on Mepf state. due to a marked load" + }, + {, + "EventCode": "0x160B0", + "EventName": "PM_L3_P0_NODE_PUMP", + "BriefDescription": "L3 PF sent with nodal scope port 0, counts even retried requests" + }, + {, + "EventCode": "0xD88C", + "EventName": "PM_LSU3_LDMX_FIN", + "BriefDescription": "New P9 instruction LDMX. The definition of this new PMU event is (from the ldmx RFC02491): The thread has executed an ldmx instruction that accessed a doubleword that contains an effective address within an enabled section of the Load Monitored region. This event, therefore, should not occur if the FSCR has disabled the load monitored facility (FSCR[52]) or disabled the EBB facility (FSCR[56])." + }, + {, + "EventCode": "0x36882", + "EventName": "PM_L2_LD_HIT", + "BriefDescription": "All successful I-or-D side load dispatches for this thread that were L2 hits (excludes i_l2mru_tch_reqs)" + }, + {, + "EventCode": "0x168AC", + "EventName": "PM_L3_CI_USAGE", + "BriefDescription": "Rotating sample of 16 CI or CO actives" + }, + {, + "EventCode": "0x20134", + "EventName": "PM_MRK_FXU_FIN", + "BriefDescription": "fxu marked instr finish" + }, + {, + "EventCode": "0x4608E", + "EventName": "PM_TM_CAP_OVERFLOW", + "BriefDescription": "TM Footprint Capacity Overflow" + }, + {, + "EventCode": "0x4F05C", + "EventName": "PM_RADIX_PWC_L2_PTE_FROM_L3MISS", + "BriefDescription": "A Page Table Entry was reloaded to a level 2 page walk cache from beyond the core's L3 data cache. This implies that level 3 and level 4 PWC accesses were not necessary for this translation. The source could be local/remote/distant memory or another core's cache" + }, + {, + "EventCode": "0x40014", + "EventName": "PM_PROBE_NOP_DISP", + "BriefDescription": "ProbeNops dispatched" + }, + {, + "EventCode": "0x58A8", + "EventName": "PM_DECODE_HOLD_ICT_FULL", + "BriefDescription": "Counts the number of cycles in which the IFU was not able to decode and transmit one or more instructions because all itags were in use. This means the ICT is full for this thread" + }, + {, + "EventCode": "0x10052", + "EventName": "PM_GRP_PUMP_MPRED_RTY", + "BriefDescription": "Final Pump Scope (Group) ended up larger than Initial Pump Scope (Chip) for all data types excluding data prefetch (demand load,inst prefetch,inst fetch,xlate)" + }, + {, + "EventCode": "0x2505E", + "EventName": "PM_BACK_BR_CMPL", + "BriefDescription": "Branch instruction completed with a target address less than current instruction address" + }, + {, + "EventCode": "0x2688A", + "EventName": "PM_ISIDE_DISP_FAIL_OTHER", + "BriefDescription": "All I-side dispatch attempts for this thread that failed due to a reason other than addrs collision (excludes i_l2mru_tch_reqs)" + }, + {, + "EventCode": "0x2001A", + "EventName": "PM_NTC_ALL_FIN", + "BriefDescription": "Cycles after all instructions have finished to group completed" + }, + {, + "EventCode": "0x3005A", + "EventName": "PM_ISQ_0_8_ENTRIES", + "BriefDescription": "Cycles in which 8 or less Issue Queue entries are in use. This is a shared event, not per thread" + }, + {, + "EventCode": "0x3515E", + "EventName": "PM_MRK_BACK_BR_CMPL", + "BriefDescription": "Marked branch instruction completed with a target address less than current instruction address" + }, + {, + "EventCode": "0xF890", + "EventName": "PM_LSU1_L1_CAM_CANCEL", + "BriefDescription": "ls1 l1 tm cam cancel" + }, + {, + "EventCode": "0xE884", + "EventName": "PM_LS1_ERAT_MISS_PREF", + "BriefDescription": "LS1 Erat miss due to prefetch" + }, + {, + "EventCode": "0xE89C", + "EventName": "PM_LSU1_TM_L1_MISS", + "BriefDescription": "Load tm L1 miss" + }, + {, + "EventCode": "0x28A8", + "EventName": "PM_TM_FAIL_CONF_NON_TM", + "BriefDescription": "TM aborted because a conflict occurred with a non-transactional access by another processor" + }, + {, + "EventCode": "0x16890", + "EventName": "PM_L1PF_L2MEMACC", + "BriefDescription": "Valid when first beat of data comes in for an L1PF where data came from memory" + }, + {, + "EventCode": "0x4504C", + "EventName": "PM_IPTEG_FROM_DMEM", + "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's memory on the same Node or Group (Distant) due to a instruction side request" + }, + {, + "EventCode": "0x1002E", + "EventName": "PM_LMQ_MERGE", + "BriefDescription": "A demand miss collides with a prefetch for the same line" + }, + {, + "EventCode": "0x160B6", + "EventName": "PM_L3_WI0_BUSY", + "BriefDescription": "Rotating sample of 8 WI valid" + }, + {, + "EventCode": "0x368AC", + "EventName": "PM_L3_CO0_BUSY", + "BriefDescription": "Lifetime, sample of CO machine 0 valid" + }, + {, + "EventCode": "0x2E040", + "EventName": "PM_DPTEG_FROM_L2_MEPF", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 hit without dispatch conflicts on Mepf state. due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x1D152", + "EventName": "PM_MRK_DATA_FROM_DL4", + "BriefDescription": "The processor's data cache was reloaded from another chip's L4 on a different Node or Group (Distant) due to a marked load" + }, + {, + "EventCode": "0x46880", + "EventName": "PM_ISIDE_MRU_TOUCH", + "BriefDescription": "I-side L2 MRU touch sent to L2 for this thread" + }, + {, + "EventCode": "0x1C05C", + "EventName": "PM_DTLB_MISS_2M", + "BriefDescription": "Data TLB reload (after a miss) page size 2M. Implies radix translation was used" + }, + {, + "EventCode": "0x50B8", + "EventName": "PM_TAGE_OVERRIDE_WRONG", + "BriefDescription": "The TAGE overrode BHT direction prediction but it was incorrect. Counted at completion for taken branches only" + }, + {, + "EventCode": "0x160AE", + "EventName": "PM_L3_P0_PF_RTY", + "BriefDescription": "L3 PF received retry port 0, every retry counted" + }, + {, + "EventCode": "0x268B2", + "EventName": "PM_L3_LOC_GUESS_WRONG", + "BriefDescription": "Initial scope=node (LNS) but data from out side local node (near or far or rem). Prediction too Low" + }, + {, + "EventCode": "0x36088", + "EventName": "PM_L2_SYS_GUESS_CORRECT", + "BriefDescription": "L2 guess system (VGS or RNS) and guess was correct (ie data beyond-group)" + }, + {, + "EventCode": "0x589C", + "EventName": "PM_PTESYNC", + "BriefDescription": "ptesync instruction counted when the instruction is decoded and transmitted" + }, + {, + "EventCode": "0x26086", + "EventName": "PM_CO_TM_SC_FOOTPRINT", + "BriefDescription": "L2 did a cleanifdirty CO to the L3 (ie created an SC line in the L3) OR L2 TM_store hit dirty HPC line and L3 indicated SC line formed in L3 on RDR bus" + }, + {, + "EventCode": "0x1E05A", + "EventName": "PM_CMPLU_STALL_ANY_SYNC", + "BriefDescription": "Cycles in which the NTC sync instruction (isync, lwsync or hwsync) is not allowed to complete" + }, + {, + "EventCode": "0xF090", + "EventName": "PM_LSU0_L1_CAM_CANCEL", + "BriefDescription": "ls0 l1 tm cam cancel" + }, + {, + "EventCode": "0xC0A8", + "EventName": "PM_LSU_FLUSH_CI", + "BriefDescription": "Load was not issued to LSU as a cache inhibited (non-cacheable) load but it was later determined to be cache inhibited" + }, + {, + "EventCode": "0x20AC", + "EventName": "PM_TM_FAIL_CONF_TM", + "BriefDescription": "TM aborted because a conflict occurred with another transaction." + }, + {, + "EventCode": "0x588C", + "EventName": "PM_SHL_ST_DEP_CREATED", + "BriefDescription": "Store-Hit-Load Table Read Hit with entry Enabled" + }, + {, + "EventCode": "0x360AC", + "EventName": "PM_L3_SN0_BUSY", + "BriefDescription": "Lifetime, sample of snooper machine 0 valid" + }, + {, + "EventCode": "0x3005C", + "EventName": "PM_BFU_BUSY", + "BriefDescription": "Cycles in which all 4 Binary Floating Point units are busy. The BFU is running at capacity" + }, + {, + "EventCode": "0x48A0", + "EventName": "PM_BR_PRED_PCACHE", + "BriefDescription": "Conditional branch completed that used pattern cache prediction" + }, + {, + "EventCode": "0x26880", + "EventName": "PM_L2_ST_MISS", + "BriefDescription": "All successful D-Side Store dispatches that were an L2 miss for this thread" + }, + {, + "EventCode": "0xF8B4", + "EventName": "PM_DC_PREF_XCONS_ALLOC", + "BriefDescription": "Prefetch stream allocated in the Ultra conservative phase by either the hardware prefetch mechanism or software prefetch" + }, + {, + "EventCode": "0x35048", + "EventName": "PM_IPTEG_FROM_DL2L3_SHR", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a instruction side request" + }, + {, + "EventCode": "0x260A8", + "EventName": "PM_L3_PF_HIT_L3", + "BriefDescription": "L3 PF hit in L3 (abandoned)" + }, + {, + "EventCode": "0x360B4", + "EventName": "PM_L3_PF0_BUSY", + "BriefDescription": "Lifetime, sample of PF machine 0 valid" + }, + {, + "EventCode": "0xC0B0", + "EventName": "PM_LSU_FLUSH_UE", + "BriefDescription": "Correctable ECC error on reload data, reported at critical data forward time" + }, + {, + "EventCode": "0x4013A", + "EventName": "PM_MRK_IC_MISS", + "BriefDescription": "Marked instruction experienced I cache miss" + }, + {, + "EventCode": "0x2088", + "EventName": "PM_FLUSH_DISP_SB", + "BriefDescription": "Dispatch Flush: Scoreboard" + }, + {, + "EventCode": "0x401E8", + "EventName": "PM_MRK_DATA_FROM_L2MISS", + "BriefDescription": "The processor's data cache was reloaded from a location other than the local core's L2 due to a marked load" + }, + {, + "EventCode": "0x3688E", + "EventName": "PM_TM_ST_CAUSED_FAIL", + "BriefDescription": "TM Store (fav or non-fav) caused another thread to fail" + }, + {, + "EventCode": "0x460B2", + "EventName": "PM_L3_SYS_GUESS_WRONG", + "BriefDescription": "Initial scope=system (VGS or RNS) but data from local or near. Prediction too high" + }, + {, + "EventCode": "0x58B8", + "EventName": "PM_TAGE_OVERRIDE_WRONG_SPEC", + "BriefDescription": "The TAGE overrode BHT direction prediction and it was correct. Includes taken and not taken and is counted at execution time" + }, + {, + "EventCode": "0xE890", + "EventName": "PM_LSU3_ERAT_HIT", + "BriefDescription": "Primary ERAT hit. There is no secondary ERAT" + }, + {, + "EventCode": "0x2898", + "EventName": "PM_TM_TABORT_TRECLAIM", + "BriefDescription": "Completion time tabortnoncd, tabortcd, treclaim" + }, + {, + "EventCode": "0x4C054", + "EventName": "PM_DERAT_MISS_16G", + "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 16G" + }, + {, + "EventCode": "0x268A0", + "EventName": "PM_L3_CO_L31", + "BriefDescription": "L3 CO to L3.1 OR of port 0 and 1 (lossy = may undercount if two cresps come in the same cyc)" + }, + {, + "EventCode": "0x5080", + "EventName": "PM_THRD_PRIO_4_5_CYC", + "BriefDescription": "Cycles thread running at priority level 4 or 5" + }, + {, + "EventCode": "0x2505C", + "EventName": "PM_VSU_FIN", + "BriefDescription": "VSU instruction finished. Up to 4 per cycle" + }, + {, + "EventCode": "0x40A4", + "EventName": "PM_BR_PRED_CCACHE", + "BriefDescription": "Conditional Branch Completed that used the Count Cache for Target Prediction" + }, + {, + "EventCode": "0x2E04A", + "EventName": "PM_DPTEG_FROM_RL4", + "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's L4 on the same Node or Group ( Remote) due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x4D12E", + "EventName": "PM_MRK_DATA_FROM_DL2L3_MOD_CYC", + "BriefDescription": "Duration in cycles to reload with Modified (M) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a marked load" + }, + {, + "EventCode": "0xC8B4", + "EventName": "PM_LSU_FLUSH_LHL_SHL", + "BriefDescription": "The instruction was flushed because of a sequential load/store consistency. If a load or store hits on an older load that has either been snooped (for loads) or has stale data (for stores)." + }, + {, + "EventCode": "0x58A4", + "EventName": "PM_FLUSH_LSU", + "BriefDescription": "LSU flushes. Includes all lsu flushes" + }, + {, + "EventCode": "0x1D150", + "EventName": "PM_MRK_DATA_FROM_DL2L3_SHR", + "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a marked load" + }, + {, + "EventCode": "0xC8A0", + "EventName": "PM_LSU1_FALSE_LHS", + "BriefDescription": "False LHS match detected" + }, + {, + "EventCode": "0x48BC", + "EventName": "PM_THRD_PRIO_2_3_CYC", + "BriefDescription": "Cycles thread running at priority level 2 or 3" + }, + {, + "EventCode": "0x10134", + "EventName": "PM_MRK_ST_DONE_L2", + "BriefDescription": "marked store completed in L2 ( RC machine done)" + }, + {, + "EventCode": "0x368B2", + "EventName": "PM_L3_GRP_GUESS_WRONG_HIGH", + "BriefDescription": "Initial scope=group (GS or NNS) but data from local node. Prediction too high" + }, + {, + "EventCode": "0xE8BC", + "EventName": "PM_LS1_PTE_TABLEWALK_CYC", + "BriefDescription": "Cycles when a tablewalk is pending on this thread on table 1" + }, + {, + "EventCode": "0x1F152", + "EventName": "PM_MRK_FAB_RSP_BKILL_CYC", + "BriefDescription": "cycles L2 RC took for a bkill" + }, + {, + "EventCode": "0x4C124", + "EventName": "PM_MRK_DATA_FROM_L3_NO_CONFLICT_CYC", + "BriefDescription": "Duration in cycles to reload from local core's L3 without conflict due to a marked load" + }, + {, + "EventCode": "0x2F14A", + "EventName": "PM_MRK_DPTEG_FROM_RL4", + "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's L4 on the same Node or Group ( Remote) due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x26888", + "EventName": "PM_L2_GRP_GUESS_WRONG", + "BriefDescription": "L2 guess grp (GS or NNS) and guess was not correct (ie data on-chip OR beyond-group)" + }, + {, + "EventCode": "0x368AE", + "EventName": "PM_L3_P1_CO_RTY", + "BriefDescription": "L3 CO received retry port 1 (memory only), every retry counted" + }, + {, + "EventCode": "0xC0AC", + "EventName": "PM_LSU_FLUSH_EMSH", + "BriefDescription": "An ERAT miss was detected after a set-p hit. Erat tracker indicates fail due to tlbmiss and the instruction gets flushed because the instruction was working on the wrong address" + }, + {, + "EventCode": "0x260B2", + "EventName": "PM_L3_SYS_GUESS_CORRECT", + "BriefDescription": "Initial scope=system (VGS or RNS) and data from outside group (far or rem)(pred successful)" + }, + {, + "EventCode": "0x1D146", + "EventName": "PM_MRK_DATA_FROM_MEMORY_CYC", + "BriefDescription": "Duration in cycles to reload from a memory location including L4 from local remote or distant due to a marked load" + }, + {, + "EventCode": "0xE094", + "EventName": "PM_LSU0_TM_L1_HIT", + "BriefDescription": "Load tm hit in L1" + }, + {, + "EventCode": "0x46888", + "EventName": "PM_L2_GROUP_PUMP", + "BriefDescription": "RC requests that were on group (aka nodel) pump attempts" + }, + {, + "EventCode": "0xF0B0", + "EventName": "PM_L3_LD_PREF", + "BriefDescription": "L3 load prefetch, sourced from a hardware or software stream, was sent to the nest" + }, + {, + "EventCode": "0x16080", + "EventName": "PM_L2_LD", + "BriefDescription": "All successful D-side Load dispatches for this thread (L2 miss + L2 hits)" + }, + {, + "EventCode": "0x4505C", + "EventName": "PM_MATH_FLOP_CMPL", + "BriefDescription": "Math flop instruction completed" + }, + {, + "EventCode": "0x368B0", + "EventName": "PM_L3_P1_SYS_PUMP", + "BriefDescription": "L3 PF sent with sys scope port 1, counts even retried requests" + }, + {, + "EventCode": "0x1F146", + "EventName": "PM_MRK_DPTEG_FROM_L31_SHR", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another core's L3 on the same chip due to a marked data side request.. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x2000C", + "EventName": "PM_THRD_ALL_RUN_CYC", + "BriefDescription": "Cycles in which all the threads have the run latch set" + }, + {, + "EventCode": "0xC0BC", + "EventName": "PM_LSU_FLUSH_OTHER", + "BriefDescription": "Other LSU flushes including: Sync (sync ack from L2 caused search of LRQ for oldest snooped load, This will either signal a Precise Flush of the oldest snooped loa or a Flush Next PPC); Data Valid Flush Next (several cases of this, one example is store and reload are lined up such that a store-hit-reload scenario exists and the CDF has already launched and has gotten bad/stale data); Bad Data Valid Flush Next (might be a few cases of this, one example is a larxa (D$ hit) return data and dval but can't allocate to LMQ (LMQ full or other reason). Already gave dval but can't watch it for snoop_hit_larx. Need to take the “bad dval” back and flush all younger ops)" + }, + {, + "EventCode": "0x5094", + "EventName": "PM_IC_MISS_ICBI", + "BriefDescription": "threaded version, IC Misses where we got EA dir hit but no sector valids were on. ICBI took line out" + }, + {, + "EventCode": "0xC8A8", + "EventName": "PM_LSU_FLUSH_ATOMIC", + "BriefDescription": "Quad-word loads (lq) are considered atomic because they always span at least 2 slices. If a snoop or store from another thread changes the data the load is accessing between the 2 or 3 pieces of the lq instruction, the lq will be flushed" + }, + {, + "EventCode": "0x1E04E", + "EventName": "PM_DPTEG_FROM_L2MISS", + "BriefDescription": "A Page Table Entry was loaded into the TLB from a location other than the local core's L2 due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x4D05E", + "EventName": "PM_BR_CMPL", + "BriefDescription": "Any Branch instruction completed" + }, + {, + "EventCode": "0x260B0", + "EventName": "PM_L3_P0_GRP_PUMP", + "BriefDescription": "L3 PF sent with grp scope port 0, counts even retried requests" + }, + {, + "EventCode": "0x30132", + "EventName": "PM_MRK_VSU_FIN", + "BriefDescription": "VSU marked instr finish" + }, + {, + "EventCode": "0x2D120", + "EventName": "PM_MRK_DATA_FROM_OFF_CHIP_CACHE", + "BriefDescription": "The processor's data cache was reloaded either shared or modified data from another core's L2/L3 on a different chip (remote or distant) due to a marked load" + }, + {, + "EventCode": "0x1E048", + "EventName": "PM_DPTEG_FROM_ON_CHIP_CACHE", + "BriefDescription": "A Page Table Entry was loaded into the TLB either shared or modified data from another core's L2/L3 on the same chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x16086", + "EventName": "PM_L2_SN_M_WR_DONE", + "BriefDescription": "SNP dispatched for a write and was M (true M); for DMA cacheinj this will pulse if rty/push is required (won't pulse if cacheinj is accepted)" + }, + {, + "EventCode": "0x489C", + "EventName": "PM_BR_CORECT_PRED_TAKEN_CMPL", + "BriefDescription": "Conditional Branch Completed in which the HW correctly predicted the direction as taken. Counted at completion time" + }, + {, + "EventCode": "0xF0B8", + "EventName": "PM_LS0_UNALIGNED_ST", + "BriefDescription": "Store instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the Store of that size. If the Store wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty" + }, + {, + "EventCode": "0x20132", + "EventName": "PM_MRK_DFU_FIN", + "BriefDescription": "Decimal Unit marked Instruction Finish" + }, + {, + "EventCode": "0x160A6", + "EventName": "PM_TM_SC_CO", + "BriefDescription": "L3 castout TM SC line" + }, + {, + "EventCode": "0xC8B0", + "EventName": "PM_LSU_FLUSH_LHS", + "BriefDescription": "Effective Address alias flush : no EA match but Real Address match. If the data has not yet been returned for this load, the instruction will just be rejected, but if it has returned data, it will be flushed" + }, + {, + "EventCode": "0x3F150", + "EventName": "PM_MRK_ST_DRAIN_TO_L2DISP_CYC", + "BriefDescription": "cycles to drain st from core to L2" + }, + {, + "EventCode": "0x168A4", + "EventName": "PM_L3_MISS", + "BriefDescription": "L3 Misses (L2 miss also missing L3, including data/instrn/xlate)" + }, + {, + "EventCode": "0xF080", + "EventName": "PM_LSU_STCX_FAIL", + "BriefDescription": "" + }, + {, + "EventCode": "0x30038", + "EventName": "PM_CMPLU_STALL_DMISS_LMEM", + "BriefDescription": "Completion stall due to cache miss that resolves in local memory" + }, + {, + "EventCode": "0x28A4", + "EventName": "PM_MRK_TEND_FAIL", + "BriefDescription": "Nested or not nested tend failed for a marked tend instruction" + }, + {, + "EventCode": "0x100FC", + "EventName": "PM_LD_REF_L1", + "BriefDescription": "All L1 D cache load references counted at finish, gated by reject" + }, + {, + "EventCode": "0xC0A0", + "EventName": "PM_LSU0_FALSE_LHS", + "BriefDescription": "False LHS match detected" + }, + {, + "EventCode": "0x468A8", + "EventName": "PM_SN_MISS", + "BriefDescription": "Any port snooper L3 miss or collision. Up to 4 can happen in a cycle but we only count 1" + }, + {, + "EventCode": "0x36888", + "EventName": "PM_L2_SYS_GUESS_WRONG", + "BriefDescription": "L2 guess system (VGS or RNS) and guess was not correct (ie data ^beyond-group)" + }, + {, + "EventCode": "0x2080", + "EventName": "PM_EE_OFF_EXT_INT", + "BriefDescription": "CyclesMSR[EE] is off and external interrupts are active" + }, + {, + "EventCode": "0xE8B8", + "EventName": "PM_LS3_TM_DISALLOW", + "BriefDescription": "A TM-ineligible instruction tries to execute inside a transaction and the LSU disallows it" + }, + {, + "EventCode": "0x2688E", + "EventName": "PM_TM_FAV_CAUSED_FAIL", + "BriefDescription": "TM Load (fav) caused another thread to fail" + }, + {, + "EventCode": "0x16090", + "EventName": "PM_SN0_BUSY", + "BriefDescription": "SN mach 0 Busy. Used by PMU to sample ave SN lifetime (mach0 used as sample point)" + }, + {, + "EventCode": "0x360AE", + "EventName": "PM_L3_P0_CO_RTY", + "BriefDescription": "L3 CO received retry port 0 (memory only), every retry counted" + }, + {, + "EventCode": "0x168A8", + "EventName": "PM_L3_WI_USAGE", + "BriefDescription": "Lifetime, sample of Write Inject machine 0 valid" + }, + {, + "EventCode": "0x468A2", + "EventName": "PM_L3_LAT_CI_MISS", + "BriefDescription": "L3 Lateral Castins Miss" + }, + {, + "EventCode": "0x4090", + "EventName": "PM_IC_PREF_CANCEL_PAGE", + "BriefDescription": "Prefetch Canceled due to page boundary" + }, + {, + "EventCode": "0xF09C", + "EventName": "PM_SLB_TABLEWALK_CYC", + "BriefDescription": "Cycles when a tablewalk is pending on this thread on the SLB table" + }, + {, + "EventCode": "0x460AA", + "EventName": "PM_L3_P0_CO_L31", + "BriefDescription": "L3 CO to L3.1 (LCO) port 0 with or without data" + }, + {, + "EventCode": "0x2880", + "EventName": "PM_FLUSH_DISP", + "BriefDescription": "Dispatch flush" + }, + {, + "EventCode": "0x168AE", + "EventName": "PM_L3_P1_PF_RTY", + "BriefDescription": "L3 PF received retry port 1, every retry counted" + }, + {, + "EventCode": "0x46082", + "EventName": "PM_L2_ST_DISP", + "BriefDescription": "All successful D-side store dispatches for this thread " + }, + {, + "EventCode": "0x4609E", + "EventName": "PM_L2_INST_MISS", + "BriefDescription": "All successful I-side dispatches that were an L2 miss for this thread (excludes i_l2mru_tch reqs)" + }, + {, + "EventCode": "0xE084", + "EventName": "PM_LS0_ERAT_MISS_PREF", + "BriefDescription": "LS0 Erat miss due to prefetch" + }, + {, + "EventCode": "0x409C", + "EventName": "PM_BR_PRED", + "BriefDescription": "Conditional Branch Executed in which the HW predicted the Direction or Target. Includes taken and not taken and is counted at execution time" + }, + {, + "EventCode": "0x2D144", + "EventName": "PM_MRK_DATA_FROM_L31_MOD", + "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another core's L3 on the same chip due to a marked load" + }, + {, + "EventCode": "0x360A4", + "EventName": "PM_L3_CO_LCO", + "BriefDescription": "Total L3 COs occurred on LCO L3.1 (good cresp, may end up in mem on a retry)" + }, + {, + "EventCode": "0x4890", + "EventName": "PM_IC_PREF_CANCEL_HIT", + "BriefDescription": "Prefetch Canceled due to icache hit" + }, + {, + "EventCode": "0x268A8", + "EventName": "PM_RD_HIT_PF", + "BriefDescription": "RD machine hit L3 PF machine" + }, + {, + "EventCode": "0x16880", + "EventName": "PM_L2_ST", + "BriefDescription": "All successful D-side store dispatches for this thread (L2 miss + L2 hits)" + }, + {, + "EventCode": "0x4098", + "EventName": "PM_IC_DEMAND_L2_BHT_REDIRECT", + "BriefDescription": "L2 I cache demand request due to BHT redirect, branch redirect ( 2 bubbles 3 cycles)" + }, + {, + "EventCode": "0xD0B4", + "EventName": "PM_LSU0_SRQ_S0_VALID_CYC", + "BriefDescription": "Slot 0 of SRQ valid" + }, + {, + "EventCode": "0x160AA", + "EventName": "PM_L3_P0_LCO_NO_DATA", + "BriefDescription": "Dataless L3 LCO sent port 0" + }, + {, + "EventCode": "0x208C", + "EventName": "PM_CLB_HELD", + "BriefDescription": "CLB (control logic block - indicates quadword fetch block) Hold: Any Reason" + }, + {, + "EventCode": "0xF88C", + "EventName": "PM_LSU3_STORE_REJECT", + "BriefDescription": "All internal store rejects cause the instruction to go back to the SRQ and go to sleep until woken up to try again after the condition has been met" + }, + {, + "EventCode": "0x200F2", + "EventName": "PM_INST_DISP", + "BriefDescription": "# PPC Dispatched" + }, + {, + "EventCode": "0x4E05E", + "EventName": "PM_TM_OUTER_TBEGIN_DISP", + "BriefDescription": "Number of outer tbegin instructions dispatched. The dispatch unit determines whether the tbegin instruction is outer or nested. This is a speculative count, which includes flushed instructions" + }, + {, + "EventCode": "0x2D018", + "EventName": "PM_CMPLU_STALL_EXEC_UNIT", + "BriefDescription": "Completion stall due to execution units (FXU/VSU/CRU)" + }, + {, + "EventCode": "0x20B0", + "EventName": "PM_LSU_FLUSH_NEXT", + "BriefDescription": "LSU flush next reported at flush time. Sometimes these also come with an exception" + }, + {, + "EventCode": "0x3880", + "EventName": "PM_ISU2_ISS_HOLD_ALL", + "BriefDescription": "All ISU rejects" + }, + {, + "EventCode": "0x46882", + "EventName": "PM_L2_ST_HIT", + "BriefDescription": "All successful D-side store dispatches for this thread that were L2 hits" + }, + {, + "EventCode": "0x360A8", + "EventName": "PM_L3_CO", + "BriefDescription": "L3 castout occurring (does not include casthrough or log writes (cinj/dmaw))" + }, + {, + "EventCode": "0x368A4", + "EventName": "PM_L3_CINJ", + "BriefDescription": "L3 castin of cache inject" + }, + {, + "EventCode": "0xC890", + "EventName": "PM_LSU_NCST", + "BriefDescription": "Asserts when a i=1 store op is sent to the nest. No record of issue pipe (LS0/LS1) is maintained so this is for both pipes. Probably don't need separate LS0 and LS1" + }, + {, + "EventCode": "0xD880", + "EventName": "PM_LSU1_SET_MPRED", + "BriefDescription": "Set prediction(set-p) miss. The entry was not found in the Set prediction table" + }, + {, + "EventCode": "0xD0B8", + "EventName": "PM_LSU_LMQ_FULL_CYC", + "BriefDescription": "Counts the number of cycles the LMQ is full" + }, + {, + "EventCode": "0x168B2", + "EventName": "PM_L3_GRP_GUESS_CORRECT", + "BriefDescription": "Initial scope=group (GS or NNS) and data from same group (near) (pred successful)" + }, + {, + "EventCode": "0x48A4", + "EventName": "PM_STOP_FETCH_PENDING_CYC", + "BriefDescription": "Fetching is stopped due to an incoming instruction that will result in a flush" + }, + {, + "EventCode": "0x36884", + "EventName": "PM_L2_RCST_DISP_FAIL_ADDR", + "BriefDescription": "All D-side store dispatch attempts for this thread that failed due to address collision with RC/CO/SN/SQ" + }, + {, + "EventCode": "0x260AC", + "EventName": "PM_L3_PF_USAGE", + "BriefDescription": "Rotating sample of 32 PF actives" + } +] diff --git a/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json b/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json new file mode 100644 index 000000000000..bc2db636dabf --- /dev/null +++ b/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json @@ -0,0 +1,552 @@ +[ + {, + "EventCode": "0x4D04C", + "EventName": "PM_DFU_BUSY", + "BriefDescription": "Cycles in which all 4 Decimal Floating Point units are busy. The DFU is running at capacity" + }, + {, + "EventCode": "0x100F6", + "EventName": "PM_IERAT_RELOAD", + "BriefDescription": "Number of I-ERAT reloads" + }, + {, + "EventCode": "0x201E2", + "EventName": "PM_MRK_LD_MISS_L1", + "BriefDescription": "Marked DL1 Demand Miss counted at exec time. Note that this count is per slice, so if a load spans multiple slices this event will increment multiple times for a single load." + }, + {, + "EventCode": "0x40010", + "EventName": "PM_PMC3_OVERFLOW", + "BriefDescription": "Overflow from counter 3" + }, + {, + "EventCode": "0x1005A", + "EventName": "PM_CMPLU_STALL_DFLONG", + "BriefDescription": "Finish stall because the NTF instruction was a multi-cycle instruction issued to the Decimal Floating Point execution pipe and waiting to finish. Includes decimal floating point instructions + 128 bit binary floating point instructions. Qualified by multicycle" + }, + {, + "EventCode": "0x4D140", + "EventName": "PM_MRK_DATA_FROM_ON_CHIP_CACHE", + "BriefDescription": "The processor's data cache was reloaded either shared or modified data from another core's L2/L3 on the same chip due to a marked load" + }, + {, + "EventCode": "0x3F14C", + "EventName": "PM_MRK_DPTEG_FROM_DL4", + "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's L4 on a different Node or Group (Distant) due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x1E040", + "EventName": "PM_DPTEG_FROM_L2_NO_CONFLICT", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 without conflict due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x24052", + "EventName": "PM_FXU_IDLE", + "BriefDescription": "Cycles in which FXU0, FXU1, FXU2, and FXU3 are all idle" + }, + {, + "EventCode": "0x1E054", + "EventName": "PM_CMPLU_STALL", + "BriefDescription": "Nothing completed and ICT not empty" + }, + {, + "EventCode": "0x2", + "EventName": "PM_INST_CMPL", + "BriefDescription": "Number of PowerPC Instructions that completed." + }, + {, + "EventCode": "0x3D058", + "EventName": "PM_VSU_DP_FSQRT_FDIV", + "BriefDescription": "vector versions of fdiv,fsqrt" + }, + {, + "EventCode": "0x10006", + "EventName": "PM_DISP_HELD", + "BriefDescription": "Dispatch Held" + }, + {, + "EventCode": "0x3D154", + "EventName": "PM_MRK_DERAT_MISS_16M", + "BriefDescription": "Marked Data ERAT Miss (Data TLB Access) page size 16M" + }, + {, + "EventCode": "0x200F8", + "EventName": "PM_EXT_INT", + "BriefDescription": "external interrupt" + }, + {, + "EventCode": "0x20008", + "EventName": "PM_ICT_EMPTY_CYC", + "BriefDescription": "Cycles in which the ICT is completely empty. No itags are assigned to any thread" + }, + {, + "EventCode": "0x4F146", + "EventName": "PM_MRK_DPTEG_FROM_L21_MOD", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's L2 on the same chip due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x10056", + "EventName": "PM_MEM_READ", + "BriefDescription": "Reads from Memory from this thread (includes data/inst/xlate/l1prefetch/inst prefetch). Includes L4" + }, + {, + "EventCode": "0x3C04C", + "EventName": "PM_DATA_FROM_DL4", + "BriefDescription": "The processor's data cache was reloaded from another chip's L4 on a different Node or Group (Distant) due to a demand load" + }, + {, + "EventCode": "0x4E046", + "EventName": "PM_DPTEG_FROM_L21_MOD", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's L2 on the same chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x2E016", + "EventName": "PM_NTC_ISSUE_HELD_ARB", + "BriefDescription": "The NTC instruction is being held at dispatch because it lost arbitration onto the issue pipe to another instruction (from the same thread or a different thread)" + }, + {, + "EventCode": "0x15156", + "EventName": "PM_SYNC_MRK_FX_DIVIDE", + "BriefDescription": "Marked fixed point divide that can cause a synchronous interrupt" + }, + {, + "EventCode": "0x1C056", + "EventName": "PM_DERAT_MISS_4K", + "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 4K" + }, + {, + "EventCode": "0x2F142", + "EventName": "PM_MRK_DPTEG_FROM_L3_MEPF", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 without dispatch conflicts hit on Mepf state. due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x10024", + "EventName": "PM_PMC5_OVERFLOW", + "BriefDescription": "Overflow from counter 5" + }, + {, + "EventCode": "0x2C018", + "EventName": "PM_CMPLU_STALL_DMISS_L21_L31", + "BriefDescription": "Completion stall by Dcache miss which resolved on chip ( excluding local L2/L3)" + }, + {, + "EventCode": "0x4006A", + "EventName": "PM_IERAT_RELOAD_16M", + "BriefDescription": "IERAT Reloaded (Miss) for a 16M page" + }, + {, + "EventCode": "0x4E010", + "EventName": "PM_ICT_NOSLOT_IC_L3MISS", + "BriefDescription": "Ict empty for this thread due to icache misses that were sourced from beyond the local L3. The source could be local/remote/distant memory or another core's cache" + }, + {, + "EventCode": "0x4D01C", + "EventName": "PM_ICT_NOSLOT_DISP_HELD_SYNC", + "BriefDescription": "Dispatch held due to a synchronizing instruction at dispatch" + }, + {, + "EventCode": "0x2D01A", + "EventName": "PM_ICT_NOSLOT_IC_MISS", + "BriefDescription": "Ict empty for this thread due to Icache Miss" + }, + {, + "EventCode": "0x3D152", + "EventName": "PM_MRK_DERAT_MISS_1G", + "BriefDescription": "Marked Data ERAT Miss (Data TLB Access) page size 1G. Implies radix translation" + }, + {, + "EventCode": "0x4F14A", + "EventName": "PM_MRK_DPTEG_FROM_OFF_CHIP_CACHE", + "BriefDescription": "A Page Table Entry was loaded into the TLB either shared or modified data from another core's L2/L3 on a different chip (remote or distant) due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x30058", + "EventName": "PM_TLBIE_FIN", + "BriefDescription": "tlbie finished" + }, + {, + "EventCode": "0x100F8", + "EventName": "PM_ICT_NOSLOT_CYC", + "BriefDescription": "Number of cycles the ICT has no itags assigned to this thread" + }, + {, + "EventCode": "0x3E042", + "EventName": "PM_DPTEG_FROM_L3_DISP_CONFLICT", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 with dispatch conflict due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x1F140", + "EventName": "PM_MRK_DPTEG_FROM_L2_NO_CONFLICT", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 without conflict due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x2C05A", + "EventName": "PM_DERAT_MISS_1G", + "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 1G. Implies radix translation" + }, + {, + "EventCode": "0x1F058", + "EventName": "PM_RADIX_PWC_L2_PTE_FROM_L2", + "BriefDescription": "A Page Table Entry was reloaded to a level 2 page walk cache from the core's L2 data cache. This implies that level 3 and level 4 PWC accesses were not necessary for this translation" + }, + {, + "EventCode": "0x1D14A", + "EventName": "PM_MRK_DATA_FROM_RL2L3_MOD", + "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a marked load" + }, + {, + "EventCode": "0x10050", + "EventName": "PM_CHIP_PUMP_CPRED", + "BriefDescription": "Initial and Final Pump Scope was chip pump (prediction=correct) for all data types excluding data prefetch (demand load,inst prefetch,inst fetch,xlate)" + }, + {, + "EventCode": "0x45058", + "EventName": "PM_IC_MISS_CMPL", + "BriefDescription": "Non-speculative icache miss, counted at completion" + }, + {, + "EventCode": "0x2D150", + "EventName": "PM_MRK_DERAT_MISS_4K", + "BriefDescription": "Marked Data ERAT Miss (Data TLB Access) page size 4K" + }, + {, + "EventCode": "0x34058", + "EventName": "PM_ICT_NOSLOT_BR_MPRED_ICMISS", + "BriefDescription": "Ict empty for this thread due to Icache Miss and branch mispred" + }, + {, + "EventCode": "0x10022", + "EventName": "PM_PMC2_SAVED", + "BriefDescription": "PMC2 Rewind Value saved" + }, + {, + "EventCode": "0x2000A", + "EventName": "PM_HV_CYC", + "BriefDescription": "Cycles in which msr_hv is high. Note that this event does not take msr_pr into consideration" + }, + {, + "EventCode": "0x1F144", + "EventName": "PM_MRK_DPTEG_FROM_L3_NO_CONFLICT", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 without conflict due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x300FC", + "EventName": "PM_DTLB_MISS", + "BriefDescription": "Data PTEG reload" + }, + {, + "EventCode": "0x2D152", + "EventName": "PM_MRK_DERAT_MISS_2M", + "BriefDescription": "Marked Data ERAT Miss (Data TLB Access) page size 2M. Implies radix translation" + }, + {, + "EventCode": "0x2C046", + "EventName": "PM_DATA_FROM_RL2L3_MOD", + "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a demand load" + }, + {, + "EventCode": "0x20052", + "EventName": "PM_GRP_PUMP_MPRED", + "BriefDescription": "Final Pump Scope (Group) ended up either larger or smaller than Initial Pump Scope for all data types excluding data prefetch (demand load,inst prefetch,inst fetch,xlate)" + }, + {, + "EventCode": "0x3F05A", + "EventName": "PM_RADIX_PWC_L2_PDE_FROM_L3", + "BriefDescription": "A Page Directory Entry was reloaded to a level 2 page walk cache from the core's L3 data cache" + }, + {, + "EventCode": "0x1E04A", + "EventName": "PM_DPTEG_FROM_RL2L3_SHR", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x10064", + "EventName": "PM_ICT_NOSLOT_DISP_HELD_TBEGIN", + "BriefDescription": "the NTC instruction is being held at dispatch because it is a tbegin instruction and there is an older tbegin in the pipeline that must complete before the younger tbegin can dispatch" + }, + {, + "EventCode": "0x2E046", + "EventName": "PM_DPTEG_FROM_RL2L3_MOD", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x4F14C", + "EventName": "PM_MRK_DPTEG_FROM_DMEM", + "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's memory on the same Node or Group (Distant) due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x2E042", + "EventName": "PM_DPTEG_FROM_L3_MEPF", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 without dispatch conflicts hit on Mepf state. due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x2D012", + "EventName": "PM_CMPLU_STALL_DFU", + "BriefDescription": "Finish stall because the NTF instruction was issued to the Decimal Floating Point execution pipe and waiting to finish. Includes decimal floating point instructions + 128 bit binary floating point instructions. Not qualified by multicycle" + }, + {, + "EventCode": "0x4C04C", + "EventName": "PM_DATA_FROM_DMEM", + "BriefDescription": "The processor's data cache was reloaded from another chip's memory on the same Node or Group (Distant) due to a demand load" + }, + {, + "EventCode": "0x30022", + "EventName": "PM_PMC4_SAVED", + "BriefDescription": "PMC4 Rewind Value saved (matched condition)" + }, + {, + "EventCode": "0x200F4", + "EventName": "PM_RUN_CYC", + "BriefDescription": "Run_cycles" + }, + {, + "EventCode": "0x400F2", + "EventName": "PM_1PLUS_PPC_DISP", + "BriefDescription": "Cycles at least one Instr Dispatched" + }, + {, + "EventCode": "0x3D148", + "EventName": "PM_MRK_DATA_FROM_L21_MOD_CYC", + "BriefDescription": "Duration in cycles to reload with Modified (M) data from another core's L2 on the same chip due to a marked load" + }, + {, + "EventCode": "0x2F146", + "EventName": "PM_MRK_DPTEG_FROM_RL2L3_MOD", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x4E01A", + "EventName": "PM_ICT_NOSLOT_DISP_HELD", + "BriefDescription": "Cycles in which the NTC instruction is held at dispatch for any reason" + }, + {, + "EventCode": "0x401EC", + "EventName": "PM_THRESH_EXC_2048", + "BriefDescription": "Threshold counter exceeded a value of 2048" + }, + {, + "EventCode": "0x35150", + "EventName": "PM_MRK_DATA_FROM_RL2L3_SHR", + "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a marked load" + }, + {, + "EventCode": "0x3E052", + "EventName": "PM_ICT_NOSLOT_IC_L3", + "BriefDescription": "Ict empty for this thread due to icache misses that were sourced from the local L3" + }, + {, + "EventCode": "0x2405A", + "EventName": "PM_NTC_FIN", + "BriefDescription": "Cycles in which the oldest instruction in the pipeline (NTC) finishes. This event is used to account for cycles in which work is being completed in the CPI stack" + }, + {, + "EventCode": "0x40052", + "EventName": "PM_PUMP_MPRED", + "BriefDescription": "Pump misprediction. Counts across all types of pumps for all data types excluding data prefetch (demand load,inst prefetch,inst fetch,xlate)" + }, + {, + "EventCode": "0x30056", + "EventName": "PM_TM_ABORTS", + "BriefDescription": "Number of TM transactions aborted" + }, + {, + "EventCode": "0x2404C", + "EventName": "PM_INST_FROM_MEMORY", + "BriefDescription": "The processor's Instruction cache was reloaded from a memory location including L4 from local remote or distant due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x1C05A", + "EventName": "PM_DERAT_MISS_2M", + "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 2M. Implies radix translation" + }, + {, + "EventCode": "0x30024", + "EventName": "PM_PMC6_OVERFLOW", + "BriefDescription": "Overflow from counter 6" + }, + {, + "EventCode": "0x10068", + "EventName": "PM_BRU_FIN", + "BriefDescription": "Branch Instruction Finished" + }, + {, + "EventCode": "0x30020", + "EventName": "PM_PMC2_REWIND", + "BriefDescription": "PMC2 Rewind Event (did not match condition)" + }, + {, + "EventCode": "0x40064", + "EventName": "PM_DUMMY2_REMOVE_ME", + "BriefDescription": "Space holder for LS_PC_RELOAD_RA" + }, + {, + "EventCode": "0x3F148", + "EventName": "PM_MRK_DPTEG_FROM_DL2L3_SHR", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x4D01E", + "EventName": "PM_ICT_NOSLOT_BR_MPRED", + "BriefDescription": "Ict empty for this thread due to branch mispred" + }, + {, + "EventCode": "0x3405E", + "EventName": "PM_IFETCH_THROTTLE", + "BriefDescription": "Cycles in which Instruction fetch throttle was active." + }, + {, + "EventCode": "0x1F148", + "EventName": "PM_MRK_DPTEG_FROM_ON_CHIP_CACHE", + "BriefDescription": "A Page Table Entry was loaded into the TLB either shared or modified data from another core's L2/L3 on the same chip due to a marked data side request.. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x3E046", + "EventName": "PM_DPTEG_FROM_L21_SHR", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another core's L2 on the same chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x2F144", + "EventName": "PM_MRK_DPTEG_FROM_L31_MOD", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's L3 on the same chip due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x4C15C", + "EventName": "PM_MRK_DERAT_MISS_16G", + "BriefDescription": "Marked Data ERAT Miss (Data TLB Access) page size 16G" + }, + {, + "EventCode": "0x14052", + "EventName": "PM_INST_GRP_PUMP_MPRED_RTY", + "BriefDescription": "Final Pump Scope (Group) ended up larger than Initial Pump Scope (Chip) for an instruction fetch" + }, + {, + "EventCode": "0xD0A8", + "EventName": "PM_DSLB_MISS", + "BriefDescription": "Data SLB Miss - Total of all segment sizes" + }, + {, + "EventCode": "0x4C058", + "EventName": "PM_MEM_CO", + "BriefDescription": "Memory castouts from this thread" + }, + {, + "EventCode": "0x40004", + "EventName": "PM_FXU_FIN", + "BriefDescription": "The fixed point unit Unit finished an instruction. Instructions that finish may not necessary complete." + }, + {, + "EventCode": "0x2C054", + "EventName": "PM_DERAT_MISS_64K", + "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 64K" + }, + {, + "EventCode": "0x10018", + "EventName": "PM_IC_DEMAND_CYC", + "BriefDescription": "Icache miss demand cycles" + }, + {, + "EventCode": "0x3C054", + "EventName": "PM_DERAT_MISS_16M", + "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 16M" + }, + {, + "EventCode": "0x2D14E", + "EventName": "PM_MRK_DATA_FROM_L21_SHR", + "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another core's L2 on the same chip due to a marked load" + }, + {, + "EventCode": "0x3405C", + "EventName": "PM_CMPLU_STALL_DPLONG", + "BriefDescription": "Finish stall because the NTF instruction was a scalar multi-cycle instruction issued to the Double Precision execution pipe and waiting to finish. Includes binary floating point instructions in 32 and 64 bit binary floating point format. Qualified by NOT vector AND multicycle" + }, + {, + "EventCode": "0x4D052", + "EventName": "PM_2FLOP_CMPL", + "BriefDescription": "DP vector version of fmul, fsub, fcmp, fsel, fabs, fnabs, fres ,fsqrte, fneg " + }, + {, + "EventCode": "0x1F142", + "EventName": "PM_MRK_DPTEG_FROM_L2", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x40062", + "EventName": "PM_DUMMY1_REMOVE_ME", + "BriefDescription": "Space holder for L2_PC_PM_MK_LDST_SCOPE_PRED_STATUS" + }, + {, + "EventCode": "0x4C012", + "EventName": "PM_CMPLU_STALL_ERAT_MISS", + "BriefDescription": "Finish stall because the NTF instruction was a load or store that suffered a translation miss" + }, + {, + "EventCode": "0x4D050", + "EventName": "PM_VSU_NON_FLOP_CMPL", + "BriefDescription": "Non FLOP operation completed" + }, + {, + "EventCode": "0x2E012", + "EventName": "PM_TM_TX_PASS_RUN_CYC", + "BriefDescription": "cycles spent in successful transactions" + }, + {, + "EventCode": "0x4D04E", + "EventName": "PM_VSU_FSQRT_FDIV", + "BriefDescription": "four flops operation (fdiv,fsqrt) Scalar Instructions only" + }, + {, + "EventCode": "0x4C120", + "EventName": "PM_MRK_DATA_FROM_L2_MEPF", + "BriefDescription": "The processor's data cache was reloaded from local core's L2 hit without dispatch conflicts on Mepf state. due to a marked load" + }, + {, + "EventCode": "0x10062", + "EventName": "PM_LD_L3MISS_PEND_CYC", + "BriefDescription": "Cycles L3 miss was pending for this thread" + }, + {, + "EventCode": "0x2F14C", + "EventName": "PM_MRK_DPTEG_FROM_MEMORY", + "BriefDescription": "A Page Table Entry was loaded into the TLB from a memory location including L4 from local remote or distant due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x14050", + "EventName": "PM_INST_CHIP_PUMP_CPRED", + "BriefDescription": "Initial and Final Pump Scope was chip pump (prediction=correct) for an instruction fetch" + }, + {, + "EventCode": "0x2000E", + "EventName": "PM_FXU_BUSY", + "BriefDescription": "Cycles in which all 4 FXUs are busy. The FXU is running at capacity" + }, + {, + "EventCode": "0x20066", + "EventName": "PM_TLB_MISS", + "BriefDescription": "TLB Miss (I + D)" + }, + {, + "EventCode": "0x10054", + "EventName": "PM_PUMP_CPRED", + "BriefDescription": "Pump prediction correct. Counts across all types of pumps for all data types excluding data prefetch (demand load,inst prefetch,inst fetch,xlate)" + }, + {, + "EventCode": "0x4D124", + "EventName": "PM_MRK_DATA_FROM_L31_SHR", + "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another core's L3 on the same chip due to a marked load" + }, + {, + "EventCode": "0x400F8", + "EventName": "PM_FLUSH", + "BriefDescription": "Flush (any type)" + }, + {, + "EventCode": "0x30004", + "EventName": "PM_CMPLU_STALL_EMQ_FULL", + "BriefDescription": "Finish stall because the next to finish instruction suffered an ERAT miss and the EMQ was full" + }, + {, + "EventCode": "0x1D154", + "EventName": "PM_MRK_DATA_FROM_L21_SHR_CYC", + "BriefDescription": "Duration in cycles to reload with Shared (S) data from another core's L2 on the same chip due to a marked load" + } +] diff --git a/tools/perf/pmu-events/arch/powerpc/power9/pmc.json b/tools/perf/pmu-events/arch/powerpc/power9/pmc.json new file mode 100644 index 000000000000..3ef8a10aac86 --- /dev/null +++ b/tools/perf/pmu-events/arch/powerpc/power9/pmc.json @@ -0,0 +1,122 @@ +[ + {, + "EventCode": "0x20036", + "EventName": "PM_BR_2PATH", + "BriefDescription": "Branches that are not strongly biased" + }, + {, + "EventCode": "0x40056", + "EventName": "PM_MEM_LOC_THRESH_LSU_HIGH", + "BriefDescription": "Local memory above threshold for LSU medium" + }, + {, + "EventCode": "0x2C056", + "EventName": "PM_DTLB_MISS_4K", + "BriefDescription": "Data TLB Miss page size 4k" + }, + {, + "EventCode": "0x40118", + "EventName": "PM_MRK_DCACHE_RELOAD_INTV", + "BriefDescription": "Combined Intervention event" + }, + {, + "EventCode": "0x4F148", + "EventName": "PM_MRK_DPTEG_FROM_DL2L3_MOD", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x301E8", + "EventName": "PM_THRESH_EXC_64", + "BriefDescription": "Threshold counter exceeded a value of 64" + }, + {, + "EventCode": "0x4E04E", + "EventName": "PM_DPTEG_FROM_L3MISS", + "BriefDescription": "A Page Table Entry was loaded into the TLB from a location other than the local core's L3 due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x40050", + "EventName": "PM_SYS_PUMP_MPRED_RTY", + "BriefDescription": "Final Pump Scope (system) ended up larger than Initial Pump Scope (Chip/Group) for all data types excluding data prefetch (demand load,inst prefetch,inst fetch,xlate)" + }, + {, + "EventCode": "0x1F14E", + "EventName": "PM_MRK_DPTEG_FROM_L2MISS", + "BriefDescription": "A Page Table Entry was loaded into the TLB from a location other than the local core's L2 due to a marked data side request.. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x4D018", + "EventName": "PM_CMPLU_STALL_BRU", + "BriefDescription": "Completion stall due to a Branch Unit" + }, + {, + "EventCode": "0x45052", + "EventName": "PM_4FLOP_CMPL", + "BriefDescription": "4 FLOP instruction completed" + }, + {, + "EventCode": "0x3D142", + "EventName": "PM_MRK_DATA_FROM_LMEM", + "BriefDescription": "The processor's data cache was reloaded from the local chip's Memory due to a marked load" + }, + {, + "EventCode": "0x4C01E", + "EventName": "PM_CMPLU_STALL_CRYPTO", + "BriefDescription": "Finish stall because the NTF instruction was routed to the crypto execution pipe and was waiting to finish" + }, + {, + "EventCode": "0x3000C", + "EventName": "PM_FREQ_DOWN", + "BriefDescription": "Power Management: Below Threshold B" + }, + {, + "EventCode": "0x4D128", + "EventName": "PM_MRK_DATA_FROM_LMEM_CYC", + "BriefDescription": "Duration in cycles to reload from the local chip's Memory due to a marked load" + }, + {, + "EventCode": "0x4D054", + "EventName": "PM_8FLOP_CMPL", + "BriefDescription": "8 FLOP instruction completed" + }, + {, + "EventCode": "0x10026", + "EventName": "PM_TABLEWALK_CYC", + "BriefDescription": "Cycles when an instruction tablewalk is active" + }, + {, + "EventCode": "0x2C012", + "EventName": "PM_CMPLU_STALL_DCACHE_MISS", + "BriefDescription": "Finish stall because the NTF instruction was a load that missed the L1 and was waiting for the data to return from the nest" + }, + {, + "EventCode": "0x2E04C", + "EventName": "PM_DPTEG_FROM_MEMORY", + "BriefDescription": "A Page Table Entry was loaded into the TLB from a memory location including L4 from local remote or distant due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x3F142", + "EventName": "PM_MRK_DPTEG_FROM_L3_DISP_CONFLICT", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 with dispatch conflict due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x4F142", + "EventName": "PM_MRK_DPTEG_FROM_L3", + "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x10060", + "EventName": "PM_TM_TRANS_RUN_CYC", + "BriefDescription": "run cycles in transactional state" + }, + {, + "EventCode": "0x1E04C", + "EventName": "PM_DPTEG_FROM_LL4", + "BriefDescription": "A Page Table Entry was loaded into the TLB from the local chip's L4 cache due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x45050", + "EventName": "PM_1FLOP_CMPL", + "BriefDescription": "one flop (fadd, fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg) operation completed" + } +] diff --git a/tools/perf/pmu-events/arch/powerpc/power9/translation.json b/tools/perf/pmu-events/arch/powerpc/power9/translation.json new file mode 100644 index 000000000000..8c0f12024afa --- /dev/null +++ b/tools/perf/pmu-events/arch/powerpc/power9/translation.json @@ -0,0 +1,232 @@ +[ + {, + "EventCode": "0x1E", + "EventName": "PM_CYC", + "BriefDescription": "Processor cycles" + }, + {, + "EventCode": "0x30010", + "EventName": "PM_PMC2_OVERFLOW", + "BriefDescription": "Overflow from counter 2" + }, + {, + "EventCode": "0x3C046", + "EventName": "PM_DATA_FROM_L21_SHR", + "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another core's L2 on the same chip due to a demand load" + }, + {, + "EventCode": "0x4D05C", + "EventName": "PM_DP_QP_FLOP_CMPL", + "BriefDescription": "Double-Precion or Quad-Precision instruction completed" + }, + {, + "EventCode": "0x4E04C", + "EventName": "PM_DPTEG_FROM_DMEM", + "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's memory on the same Node or Group (Distant) due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x20016", + "EventName": "PM_ST_FIN", + "BriefDescription": "Store finish count. Includes speculative activity" + }, + {, + "EventCode": "0x44042", + "EventName": "PM_INST_FROM_L3", + "BriefDescription": "The processor's Instruction cache was reloaded from local core's L3 due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x1504A", + "EventName": "PM_IPTEG_FROM_RL2L3_SHR", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a instruction side request" + }, + {, + "EventCode": "0x40132", + "EventName": "PM_MRK_LSU_FIN", + "BriefDescription": "lsu marked instr PPC finish" + }, + {, + "EventCode": "0x3C05C", + "EventName": "PM_CMPLU_STALL_VFXU", + "BriefDescription": "Finish stall due to a vector fixed point instruction in the execution pipeline. These instructions get routed to the ALU, ALU2, and DIV pipes" + }, + {, + "EventCode": "0x30066", + "EventName": "PM_LSU_FIN", + "BriefDescription": "LSU Finished a PPC instruction (up to 4 per cycle)" + }, + {, + "EventCode": "0x2011C", + "EventName": "PM_MRK_NTC_CYC", + "BriefDescription": "Cycles during which the marked instruction is next to complete (completion is held up because the marked instruction hasn't completed yet)" + }, + {, + "EventCode": "0x3E048", + "EventName": "PM_DPTEG_FROM_DL2L3_SHR", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x2E018", + "EventName": "PM_CMPLU_STALL_VFXLONG", + "BriefDescription": "Completion stall due to a long latency vector fixed point instruction (division, square root)" + }, + {, + "EventCode": "0x1C04E", + "EventName": "PM_DATA_FROM_L2MISS_MOD", + "BriefDescription": "The processor's data cache was reloaded from a location other than the local core's L2 due to a demand load" + }, + {, + "EventCode": "0x15048", + "EventName": "PM_IPTEG_FROM_ON_CHIP_CACHE", + "BriefDescription": "A Page Table Entry was loaded into the TLB either shared or modified data from another core's L2/L3 on the same chip due to a instruction side request" + }, + {, + "EventCode": "0x34046", + "EventName": "PM_INST_FROM_L21_SHR", + "BriefDescription": "The processor's Instruction cache was reloaded with Shared (S) data from another core's L2 on the same chip due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x1E058", + "EventName": "PM_STCX_FAIL", + "BriefDescription": "stcx failed" + }, + {, + "EventCode": "0x20112", + "EventName": "PM_MRK_NTF_FIN", + "BriefDescription": "Marked next to finish instruction finished" + }, + {, + "EventCode": "0x300F0", + "EventName": "PM_ST_MISS_L1", + "BriefDescription": "Store Missed L1" + }, + {, + "EventCode": "0x4C046", + "EventName": "PM_DATA_FROM_L21_MOD", + "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another core's L2 on the same chip due to a demand load" + }, + {, + "EventCode": "0x2504A", + "EventName": "PM_IPTEG_FROM_RL4", + "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's L4 on the same Node or Group ( Remote) due to a instruction side request" + }, + {, + "EventCode": "0x2003E", + "EventName": "PM_LSU_LMQ_SRQ_EMPTY_CYC", + "BriefDescription": "Cycles in which the LSU is empty for all threads (lmq and srq are completely empty)" + }, + {, + "EventCode": "0x201E6", + "EventName": "PM_THRESH_EXC_32", + "BriefDescription": "Threshold counter exceeded a value of 32" + }, + {, + "EventCode": "0x4405C", + "EventName": "PM_CMPLU_STALL_VDP", + "BriefDescription": "Finish stall because the NTF instruction was a vector instruction issued to the Double Precision execution pipe and waiting to finish. Includes binary floating point instructions in 32 and 64 bit binary floating point format. Not qualified multicycle. Qualified by vector" + }, + {, + "EventCode": "0x4D010", + "EventName": "PM_PMC1_SAVED", + "BriefDescription": "PMC1 Rewind Value saved" + }, + {, + "EventCode": "0x200FE", + "EventName": "PM_DATA_FROM_L2MISS", + "BriefDescription": "Demand LD - L2 Miss (not L2 hit)" + }, + {, + "EventCode": "0x2D14A", + "EventName": "PM_MRK_DATA_FROM_RL2L3_MOD_CYC", + "BriefDescription": "Duration in cycles to reload with Modified (M) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a marked load" + }, + {, + "EventCode": "0x10028", + "EventName": "PM_STALL_END_ICT_EMPTY", + "BriefDescription": "The number a times the core transitioned from a stall to ICT-empty for this thread" + }, + {, + "EventCode": "0x2504C", + "EventName": "PM_IPTEG_FROM_MEMORY", + "BriefDescription": "A Page Table Entry was loaded into the TLB from a memory location including L4 from local remote or distant due to a instruction side request" + }, + {, + "EventCode": "0x4504A", + "EventName": "PM_IPTEG_FROM_OFF_CHIP_CACHE", + "BriefDescription": "A Page Table Entry was loaded into the TLB either shared or modified data from another core's L2/L3 on a different chip (remote or distant) due to a instruction side request" + }, + {, + "EventCode": "0x1404E", + "EventName": "PM_INST_FROM_L2MISS", + "BriefDescription": "The processor's Instruction cache was reloaded from a location other than the local core's L2 due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x34042", + "EventName": "PM_INST_FROM_L3_DISP_CONFLICT", + "BriefDescription": "The processor's Instruction cache was reloaded from local core's L3 with dispatch conflict due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x4E048", + "EventName": "PM_DPTEG_FROM_DL2L3_MOD", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x200F0", + "EventName": "PM_ST_CMPL", + "BriefDescription": "Stores completed from S2Q (2nd-level store queue)." + }, + {, + "EventCode": "0x4E05C", + "EventName": "PM_LSU_REJECT_LHS", + "BriefDescription": "LSU Reject due to LHS (up to 4 per cycle)" + }, + {, + "EventCode": "0x14044", + "EventName": "PM_INST_FROM_L3_NO_CONFLICT", + "BriefDescription": "The processor's Instruction cache was reloaded from local core's L3 without conflict due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x3E04C", + "EventName": "PM_DPTEG_FROM_DL4", + "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's L4 on a different Node or Group (Distant) due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" + }, + {, + "EventCode": "0x1F15E", + "EventName": "PM_MRK_PROBE_NOP_CMPL", + "BriefDescription": "Marked probeNops completed" + }, + {, + "EventCode": "0x20018", + "EventName": "PM_ST_FWD", + "BriefDescription": "Store forwards that finished" + }, + {, + "EventCode": "0x1D142", + "EventName": "PM_MRK_DATA_FROM_L31_ECO_SHR_CYC", + "BriefDescription": "Duration in cycles to reload with Shared (S) data from another core's ECO L3 on the same chip due to a marked load" + }, + {, + "EventCode": "0x24042", + "EventName": "PM_INST_FROM_L3_MEPF", + "BriefDescription": "The processor's Instruction cache was reloaded from local core's L3 without dispatch conflicts hit on Mepf state. due to an instruction fetch (not prefetch)" + }, + {, + "EventCode": "0x25046", + "EventName": "PM_IPTEG_FROM_RL2L3_MOD", + "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a instruction side request" + }, + {, + "EventCode": "0x3504A", + "EventName": "PM_IPTEG_FROM_RMEM", + "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's memory on the same Node or Group ( Remote) due to a instruction side request" + }, + {, + "EventCode": "0x3C05A", + "EventName": "PM_CMPLU_STALL_VDPLONG", + "BriefDescription": "Finish stall because the NTF instruction was a scalar multi-cycle instruction issued to the Double Precision execution pipe and waiting to finish. Includes binary floating point instructions in 32 and 64 bit binary floating point format. Qualified by NOT vector AND multicycle" + }, + {, + "EventCode": "0x2E01C", + "EventName": "PM_CMPLU_STALL_TLBIE", + "BriefDescription": "Finish stall because the NTF instruction was a tlbie waiting for response from L2" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index d1a12e584c1b..4ea068366c3e 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -34,3 +34,4 @@ GenuineIntel-6-2C,v2,westmereep-dp,core GenuineIntel-6-2C,v2,westmereep-dp,core GenuineIntel-6-25,v2,westmereep-sp,core GenuineIntel-6-2F,v2,westmereex,core +GenuineIntel-6-55,v1,skylakex,core diff --git a/tools/perf/pmu-events/arch/x86/skylakex/cache.json b/tools/perf/pmu-events/arch/x86/skylakex/cache.json new file mode 100644 index 000000000000..b5bc742b6fbc --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/skylakex/cache.json @@ -0,0 +1,1672 @@ +[ + { + "EventCode": "0x24", + "UMask": "0x21", + "BriefDescription": "Demand Data Read miss L2, no rejects", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS", + "PublicDescription": "Counts the number of demand Data Read requests that miss L2 cache. Only not rejected loads are counted.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0x22", + "BriefDescription": "RFO requests that miss L2 cache", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.RFO_MISS", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0x24", + "BriefDescription": "L2 cache misses when fetching instructions", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.CODE_RD_MISS", + "PublicDescription": "Counts L2 cache misses when fetching instructions.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0x27", + "BriefDescription": "Demand requests that miss L2 cache", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.ALL_DEMAND_MISS", + "PublicDescription": "Demand requests that miss L2 cache.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0x38", + "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that miss L2 cache", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.PF_MISS", + "PublicDescription": "Counts requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that miss L2 cache.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0x3f", + "BriefDescription": "All requests that miss L2 cache", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.MISS", + "PublicDescription": "All requests that miss L2 cache.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0x41", + "BriefDescription": "Demand Data Read requests that hit L2 cache", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", + "PublicDescription": "Counts the number of demand Data Read requests that hit L2 cache. Only non rejected loads are counted.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0x42", + "BriefDescription": "RFO requests that hit L2 cache", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.RFO_HIT", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0x44", + "BriefDescription": "L2 cache hits when fetching instructions, code reads.", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.CODE_RD_HIT", + "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0xd8", + "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that hit L2 cache", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.PF_HIT", + "PublicDescription": "Counts requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that hit L2 cache.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0xe1", + "BriefDescription": "Demand Data Read requests", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", + "PublicDescription": "Counts the number of demand Data Read requests (including requests from L1D hardware prefetchers). These loads may hit or miss L2 cache. Only non rejected loads are counted.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0xe2", + "BriefDescription": "RFO requests to L2 cache", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.ALL_RFO", + "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0xe4", + "BriefDescription": "L2 code requests", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.ALL_CODE_RD", + "PublicDescription": "Counts the total number of L2 code requests.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0xe7", + "BriefDescription": "Demand requests to L2 cache", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES", + "PublicDescription": "Demand requests to L2 cache.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0xf8", + "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.ALL_PF", + "PublicDescription": "Counts the total number of requests from the L2 hardware prefetchers.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0xff", + "BriefDescription": "All L2 requests", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.REFERENCES", + "PublicDescription": "All L2 requests.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x2E", + "UMask": "0x41", + "BriefDescription": "Core-originated cacheable demand requests missed L3", + "Counter": "0,1,2,3", + "EventName": "LONGEST_LAT_CACHE.MISS", + "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2. It does not include all misses to the L3.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x2E", + "UMask": "0x4f", + "BriefDescription": "Core-originated cacheable demand requests that refer to L3", + "Counter": "0,1,2,3", + "EventName": "LONGEST_LAT_CACHE.REFERENCE", + "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2. It does not include all accesses to the L3.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x48", + "UMask": "0x1", + "BriefDescription": "L1D miss outstandings duration in cycles", + "Counter": "0,1,2,3", + "EventName": "L1D_PEND_MISS.PENDING", + "PublicDescription": "Counts duration of L1D miss outstanding, that is each cycle number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch.Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x48", + "UMask": "0x1", + "BriefDescription": "Cycles with L1D load Misses outstanding.", + "Counter": "0,1,2,3", + "EventName": "L1D_PEND_MISS.PENDING_CYCLES", + "CounterMask": "1", + "PublicDescription": "Counts duration of L1D miss outstanding in cycles.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x48", + "UMask": "0x1", + "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.", + "Counter": "0,1,2,3", + "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY", + "AnyThread": "1", + "CounterMask": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x48", + "UMask": "0x2", + "BriefDescription": "Number of times a request needed a FB entry but there was no entry available for it. That is the FB unavailability was dominant reason for blocking the request. A request includes cacheable/uncacheable demands that is load, store or SW prefetch.", + "Counter": "0,1,2,3", + "EventName": "L1D_PEND_MISS.FB_FULL", + "PublicDescription": "Number of times a request needed a FB (Fill Buffer) entry but there was no entry available for it. A request includes cacheable/uncacheable demands that are load, store or SW prefetch instructions.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x51", + "UMask": "0x1", + "BriefDescription": "L1D data line replacements", + "Counter": "0,1,2,3", + "EventName": "L1D.REPLACEMENT", + "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x60", + "UMask": "0x1", + "BriefDescription": "Offcore outstanding Demand Data Read transactions in uncore queue.", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", + "PublicDescription": "Counts the number of offcore outstanding Demand Data Read transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor. See the corresponding Umask under OFFCORE_REQUESTS.Note: A prefetch promoted to Demand is counted from the promotion point.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x60", + "UMask": "0x1", + "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", + "CounterMask": "1", + "PublicDescription": "Counts cycles when offcore outstanding Demand Data Read transactions are present in the super queue (SQ). A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation).", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x60", + "UMask": "0x1", + "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6", + "CounterMask": "6", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x60", + "UMask": "0x2", + "BriefDescription": "Offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore, every cycle. ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x60", + "UMask": "0x2", + "BriefDescription": "Cycles with offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore.", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD", + "CounterMask": "1", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x60", + "UMask": "0x4", + "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO", + "PublicDescription": "Counts the number of offcore outstanding RFO (store) transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x60", + "UMask": "0x4", + "BriefDescription": "Cycles with offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore.", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", + "CounterMask": "1", + "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x60", + "UMask": "0x8", + "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", + "PublicDescription": "Counts the number of offcore outstanding cacheable Core Data Read transactions in the super queue every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x60", + "UMask": "0x8", + "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "CounterMask": "1", + "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB0", + "UMask": "0x1", + "BriefDescription": "Demand Data Read requests sent to uncore", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD", + "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB0", + "UMask": "0x2", + "BriefDescription": "Cacheable and noncachaeble code read requests", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", + "PublicDescription": "Counts both cacheable and non-cacheable code read requests.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB0", + "UMask": "0x4", + "BriefDescription": "Demand RFO requests including regular RFOs, locks, ItoM", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS.DEMAND_RFO", + "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB0", + "UMask": "0x8", + "BriefDescription": "Demand and prefetch data reads", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS.ALL_DATA_RD", + "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB0", + "UMask": "0x80", + "BriefDescription": "Any memory transaction that reached the SQ.", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS", + "PublicDescription": "Counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, etc..", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB2", + "UMask": "0x1", + "BriefDescription": "Offcore requests buffer cannot take more entries for this thread core.", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS_BUFFER.SQ_FULL", + "PublicDescription": "Counts the number of cases when the offcore requests buffer cannot take more entries for the core. This can happen when the superqueue does not contain eligible entries, or when L1D writeback pending FIFO requests is full.Note: Writeback pending FIFO has six entries.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD0", + "UMask": "0x11", + "BriefDescription": "Retired load instructions that miss the STLB.", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD0", + "UMask": "0x12", + "BriefDescription": "Retired store instructions that miss the STLB.", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES", + "SampleAfterValue": "100003", + "L1_Hit_Indication": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD0", + "UMask": "0x21", + "BriefDescription": "Retired load instructions with locked access.", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_INST_RETIRED.LOCK_LOADS", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD0", + "UMask": "0x41", + "BriefDescription": "Retired load instructions that split across a cacheline boundary.", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_INST_RETIRED.SPLIT_LOADS", + "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD0", + "UMask": "0x42", + "BriefDescription": "Retired store instructions that split across a cacheline boundary.", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_INST_RETIRED.SPLIT_STORES", + "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.", + "SampleAfterValue": "100003", + "L1_Hit_Indication": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD0", + "UMask": "0x81", + "BriefDescription": "All retired load instructions.", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_INST_RETIRED.ALL_LOADS", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD0", + "UMask": "0x82", + "BriefDescription": "All retired store instructions.", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_INST_RETIRED.ALL_STORES", + "SampleAfterValue": "2000003", + "L1_Hit_Indication": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD1", + "UMask": "0x1", + "BriefDescription": "Retired load instructions with L1 cache hits as data sources", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_LOAD_RETIRED.L1_HIT", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD1", + "UMask": "0x2", + "BriefDescription": "Retired load instructions with L2 cache hits as data sources", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_LOAD_RETIRED.L2_HIT", + "PublicDescription": "Retired load instructions with L2 cache hits as data sources.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD1", + "UMask": "0x4", + "BriefDescription": "Retired load instructions with L3 cache hits as data sources", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_LOAD_RETIRED.L3_HIT", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache. ", + "SampleAfterValue": "50021", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD1", + "UMask": "0x8", + "BriefDescription": "Retired load instructions missed L1 cache as data sources", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_LOAD_RETIRED.L1_MISS", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD1", + "UMask": "0x10", + "BriefDescription": "Retired load instructions missed L2 cache as data sources", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_LOAD_RETIRED.L2_MISS", + "PublicDescription": "Retired load instructions missed L2 cache as data sources.", + "SampleAfterValue": "50021", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD1", + "UMask": "0x20", + "BriefDescription": "Retired load instructions missed L3 cache as data sources", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_LOAD_RETIRED.L3_MISS", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache. ", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD1", + "UMask": "0x40", + "BriefDescription": "Retired load instructions which data sources were load missed L1 but hit FB due to preceding miss to the same cache line with data not ready", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_LOAD_RETIRED.FB_HIT", + "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. ", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD2", + "UMask": "0x1", + "BriefDescription": "Retired load instructions which data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", + "SampleAfterValue": "20011", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD2", + "UMask": "0x2", + "BriefDescription": "Retired load instructions which data sources were L3 and cross-core snoop hits in on-pkg core cache", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT", + "PublicDescription": "Retired load instructions which data sources were L3 and cross-core snoop hits in on-pkg core cache.", + "SampleAfterValue": "20011", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD2", + "UMask": "0x4", + "BriefDescription": "Retired load instructions which data sources were HitM responses from shared L3", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM", + "PublicDescription": "Retired load instructions which data sources were HitM responses from shared L3.", + "SampleAfterValue": "20011", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD2", + "UMask": "0x8", + "BriefDescription": "Retired load instructions which data sources were hits in L3 without snoops required", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE", + "PublicDescription": "Retired load instructions which data sources were hits in L3 without snoops required.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD3", + "UMask": "0x1", + "BriefDescription": "Retired load instructions which data sources missed L3 but serviced from local dram", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM", + "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM.", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD3", + "UMask": "0x2", + "BriefDescription": "Retired load instructions which data sources missed L3 but serviced from remote dram", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD3", + "UMask": "0x4", + "BriefDescription": "Retired load instructions whose data sources was remote HITM", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM", + "PublicDescription": "Retired load instructions whose data sources was remote HITM.", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD3", + "UMask": "0x8", + "BriefDescription": "Retired load instructions whose data sources was forwarded from a remote cache", + "Data_LA": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD", + "PublicDescription": "Retired load instructions whose data sources was forwarded from a remote cache.", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD4", + "UMask": "0x4", + "BriefDescription": "Retired instructions with at least 1 uncacheable load or lock.", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "MEM_LOAD_MISC_RETIRED.UC", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xF0", + "UMask": "0x40", + "BriefDescription": "L2 writebacks that access L2 cache", + "Counter": "0,1,2,3", + "EventName": "L2_TRANS.L2_WB", + "PublicDescription": "Counts L2 writebacks that access L2 cache.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xF1", + "UMask": "0x1f", + "BriefDescription": "L2 cache lines filling L2", + "Counter": "0,1,2,3", + "EventName": "L2_LINES_IN.ALL", + "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xF2", + "UMask": "0x1", + "BriefDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared state. A non-threaded event.", + "Counter": "0,1,2,3", + "EventName": "L2_LINES_OUT.SILENT", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xF2", + "UMask": "0x2", + "BriefDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines can be either in modified state or clean state. Modified lines may either be written back to L3 or directly written to memory and not allocated in L3. Clean lines may either be allocated in L3 or dropped ", + "Counter": "0,1,2,3", + "EventName": "L2_LINES_OUT.NON_SILENT", + "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines can be either in modified state or clean state. Modified lines may either be written back to L3 or directly written to memory and not allocated in L3. Clean lines may either be allocated in L3 or dropped.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xF2", + "UMask": "0x4", + "BriefDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache", + "Counter": "0,1,2,3", + "EventName": "L2_LINES_OUT.USELESS_PREF", + "PublicDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xF2", + "UMask": "0x4", + "BriefDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache", + "Counter": "0,1,2,3", + "EventName": "L2_LINES_OUT.USELESS_HWPF", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xF4", + "UMask": "0x10", + "BriefDescription": "Number of cache line split locks sent to uncore.", + "Counter": "0,1,2,3", + "EventName": "SQ_MISC.SPLIT_LOCK", + "PublicDescription": "Counts the number of cache line split locks sent to the uncore.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts demand data reads that have any response type.", + "MSRValue": "0x0000010001 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts demand data reads that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "MSRValue": "0x01003c0001 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "MSRValue": "0x04003c0001 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "DEMAND_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD", + "MSRValue": "0x08003c0001 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "MSRValue": "0x10003c0001 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts demand data reads that hit in the L3.", + "MSRValue": "0x3f803c0001 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts demand data reads that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand data writes (RFOs) that have any response type.", + "MSRValue": "0x0000010002 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand data writes (RFOs) that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "MSRValue": "0x01003c0002 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "MSRValue": "0x04003c0002 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "DEMAND_RFO & L3_HIT & SNOOP_HIT_WITH_FWD", + "MSRValue": "0x08003c0002 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "MSRValue": "0x10003c0002 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3.", + "MSRValue": "0x3f803c0002 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand code reads that have any response type.", + "MSRValue": "0x0000010004 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand code reads that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "MSRValue": "0x01003c0004 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "MSRValue": "0x04003c0004 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "DEMAND_CODE_RD & L3_HIT & SNOOP_HIT_WITH_FWD", + "MSRValue": "0x08003c0004 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "MSRValue": "0x10003c0004 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand code reads that hit in the L3.", + "MSRValue": "0x3f803c0004 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand code reads that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that have any response type.", + "MSRValue": "0x0000010010 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "MSRValue": "0x01003c0010 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "MSRValue": "0x04003c0010 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "PF_L2_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD", + "MSRValue": "0x08003c0010 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "MSRValue": "0x10003c0010 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3.", + "MSRValue": "0x3f803c0010 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that have any response type.", + "MSRValue": "0x0000010020 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "MSRValue": "0x01003c0020 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "MSRValue": "0x04003c0020 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "PF_L2_RFO & L3_HIT & SNOOP_HIT_WITH_FWD", + "MSRValue": "0x08003c0020 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "MSRValue": "0x10003c0020 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3.", + "MSRValue": "0x3f803c0020 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that have any response type.", + "MSRValue": "0x0000010080 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "MSRValue": "0x01003c0080 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "MSRValue": "0x04003c0080 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "PF_L3_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD", + "MSRValue": "0x08003c0080 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "MSRValue": "0x10003c0080 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3.", + "MSRValue": "0x3f803c0080 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that have any response type.", + "MSRValue": "0x0000010100 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "MSRValue": "0x01003c0100 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "MSRValue": "0x04003c0100 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "PF_L3_RFO & L3_HIT & SNOOP_HIT_WITH_FWD", + "MSRValue": "0x08003c0100 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "MSRValue": "0x10003c0100 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3.", + "MSRValue": "0x3f803c0100 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that have any response type.", + "MSRValue": "0x0000010400 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "MSRValue": "0x01003c0400 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "MSRValue": "0x04003c0400 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "PF_L1D_AND_SW & L3_HIT & SNOOP_HIT_WITH_FWD", + "MSRValue": "0x08003c0400 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "MSRValue": "0x10003c0400 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3.", + "MSRValue": "0x3f803c0400 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch data reads that have any response type.", + "MSRValue": "0x0000010490 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch data reads that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "MSRValue": "0x01003c0490 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "MSRValue": "0x04003c0490 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "ALL_PF_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD", + "MSRValue": "0x08003c0490 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "MSRValue": "0x10003c0490 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch data reads that hit in the L3.", + "MSRValue": "0x3f803c0490 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch data reads that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts prefetch RFOs that have any response type.", + "MSRValue": "0x0000010120 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts prefetch RFOs that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "MSRValue": "0x01003c0120 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "MSRValue": "0x04003c0120 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "ALL_PF_RFO & L3_HIT & SNOOP_HIT_WITH_FWD", + "MSRValue": "0x08003c0120 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "MSRValue": "0x10003c0120 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts prefetch RFOs that hit in the L3.", + "MSRValue": "0x3f803c0120 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts prefetch RFOs that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand & prefetch data reads that have any response type.", + "MSRValue": "0x0000010491 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand & prefetch data reads that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "MSRValue": "0x01003c0491 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "MSRValue": "0x04003c0491 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "ALL_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD", + "MSRValue": "0x08003c0491 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "MSRValue": "0x10003c0491 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3.", + "MSRValue": "0x3f803c0491 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand & prefetch RFOs that have any response type.", + "MSRValue": "0x0000010122 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand & prefetch RFOs that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "MSRValue": "0x01003c0122 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "MSRValue": "0x04003c0122 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "ALL_RFO & L3_HIT & SNOOP_HIT_WITH_FWD", + "MSRValue": "0x08003c0122 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "MSRValue": "0x10003c0122 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3.", + "MSRValue": "0x3f803c0122 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json b/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json new file mode 100644 index 000000000000..1c09a328df36 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json @@ -0,0 +1,88 @@ +[ + { + "EventCode": "0xC7", + "UMask": "0x1", + "BriefDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired. Each count represents 1 computation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "Counter": "0,1,2,3", + "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC7", + "UMask": "0x2", + "BriefDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired. Each count represents 1 computation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "Counter": "0,1,2,3", + "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC7", + "UMask": "0x4", + "BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired. Each count represents 2 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "Counter": "0,1,2,3", + "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC7", + "UMask": "0x8", + "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired. Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. ", + "Counter": "0,1,2,3", + "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired. Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC7", + "UMask": "0x10", + "BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired. Each count represents 4 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "Counter": "0,1,2,3", + "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC7", + "UMask": "0x20", + "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired. Each count represents 8 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "Counter": "0,1,2,3", + "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC7", + "UMask": "0x40", + "BriefDescription": "Number of Packed Double-Precision FP arithmetic instructions (Use operation multiplier of 8)", + "Counter": "0,1,2,3", + "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE", + "PublicDescription": "Number of Packed Double-Precision FP arithmetic instructions (Use operation multiplier of 8).", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC7", + "UMask": "0x80", + "BriefDescription": "Number of Packed Single-Precision FP arithmetic instructions (Use operation multiplier of 16)", + "Counter": "0,1,2,3", + "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE", + "PublicDescription": "Number of Packed Single-Precision FP arithmetic instructions (Use operation multiplier of 16).", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xCA", + "UMask": "0x1e", + "BriefDescription": "Cycles with any input/output SSE or FP assist", + "Counter": "0,1,2,3", + "EventName": "FP_ASSIST.ANY", + "CounterMask": "1", + "PublicDescription": "Counts cycles with any input and output SSE or x87 FP assist. If an input and output assist are detected on the same cycle the event increments by 1.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylakex/frontend.json b/tools/perf/pmu-events/arch/x86/skylakex/frontend.json new file mode 100644 index 000000000000..40abc0852cd6 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/skylakex/frontend.json @@ -0,0 +1,482 @@ +[ + { + "EventCode": "0x79", + "UMask": "0x4", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path", + "Counter": "0,1,2,3", + "EventName": "IDQ.MITE_UOPS", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x79", + "UMask": "0x4", + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path", + "Counter": "0,1,2,3", + "EventName": "IDQ.MITE_CYCLES", + "CounterMask": "1", + "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x79", + "UMask": "0x8", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path", + "Counter": "0,1,2,3", + "EventName": "IDQ.DSB_UOPS", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x79", + "UMask": "0x8", + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path", + "Counter": "0,1,2,3", + "EventName": "IDQ.DSB_CYCLES", + "CounterMask": "1", + "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x79", + "UMask": "0x10", + "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "Counter": "0,1,2,3", + "EventName": "IDQ.MS_DSB_CYCLES", + "CounterMask": "1", + "PublicDescription": "Counts cycles during which uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x79", + "UMask": "0x18", + "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops", + "Counter": "0,1,2,3", + "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS", + "CounterMask": "4", + "PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x79", + "UMask": "0x18", + "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop", + "Counter": "0,1,2,3", + "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS", + "CounterMask": "1", + "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x79", + "UMask": "0x20", + "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "Counter": "0,1,2,3", + "EventName": "IDQ.MS_MITE_UOPS", + "PublicDescription": "Counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x79", + "UMask": "0x24", + "BriefDescription": "Cycles MITE is delivering 4 Uops", + "Counter": "0,1,2,3", + "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS", + "CounterMask": "4", + "PublicDescription": "Counts the number of cycles 4 uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x79", + "UMask": "0x24", + "BriefDescription": "Cycles MITE is delivering any Uop", + "Counter": "0,1,2,3", + "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS", + "CounterMask": "1", + "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x79", + "UMask": "0x30", + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "Counter": "0,1,2,3", + "EventName": "IDQ.MS_CYCLES", + "CounterMask": "1", + "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EdgeDetect": "1", + "EventCode": "0x79", + "UMask": "0x30", + "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer", + "Counter": "0,1,2,3", + "EventName": "IDQ.MS_SWITCHES", + "CounterMask": "1", + "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x79", + "UMask": "0x30", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "Counter": "0,1,2,3", + "EventName": "IDQ.MS_UOPS", + "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Any instruction over 4 uops will be delivered by the MS. Some instructions such as transcendentals may additionally generate uops from the MS.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x80", + "UMask": "0x4", + "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss.", + "Counter": "0,1,2,3", + "EventName": "ICACHE_16B.IFDATA_STALL", + "PublicDescription": "Cycles where a code line fetch is stalled due to an L1 instruction cache miss. The legacy decode pipeline works at a 16 Byte granularity.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x83", + "UMask": "0x1", + "BriefDescription": "Instruction fetch tag lookups that hit in the instruction cache (L1I). Counts at 64-byte cache-line granularity.", + "Counter": "0,1,2,3", + "EventName": "ICACHE_64B.IFTAG_HIT", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x83", + "UMask": "0x2", + "BriefDescription": "Instruction fetch tag lookups that miss in the instruction cache (L1I). Counts at 64-byte cache-line granularity.", + "Counter": "0,1,2,3", + "EventName": "ICACHE_64B.IFTAG_MISS", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x83", + "UMask": "0x4", + "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss.", + "Counter": "0,1,2,3", + "EventName": "ICACHE_64B.IFTAG_STALL", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x9C", + "UMask": "0x1", + "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled", + "Counter": "0,1,2,3", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", + "PublicDescription": "Counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding \u201c4 \u2013 x\u201d when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread. b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions). c. Instruction Decode Queue (IDQ) delivers four uops.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x9C", + "UMask": "0x1", + "BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled", + "Counter": "0,1,2,3", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE", + "CounterMask": "4", + "PublicDescription": "Counts, on the per-thread basis, cycles when no uops are delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core =4.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x9C", + "UMask": "0x1", + "BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled", + "Counter": "0,1,2,3", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE", + "CounterMask": "3", + "PublicDescription": "Counts, on the per-thread basis, cycles when less than 1 uop is delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core >= 3.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x9C", + "UMask": "0x1", + "BriefDescription": "Cycles with less than 2 uops delivered by the front end.", + "Counter": "0,1,2,3", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_2_UOP_DELIV.CORE", + "CounterMask": "2", + "PublicDescription": "Cycles with less than 2 uops delivered by the front-end.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x9C", + "UMask": "0x1", + "BriefDescription": "Cycles with less than 3 uops delivered by the front end.", + "Counter": "0,1,2,3", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE", + "CounterMask": "1", + "PublicDescription": "Cycles with less than 3 uops delivered by the front-end.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "Invert": "1", + "EventCode": "0x9C", + "UMask": "0x1", + "BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.", + "Counter": "0,1,2,3", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK", + "CounterMask": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xAB", + "UMask": "0x2", + "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.", + "Counter": "0,1,2,3", + "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", + "PublicDescription": "Counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 0\u20132 cycles.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC6", + "UMask": "0x1", + "BriefDescription": "Retired Instructions who experienced decode stream buffer (DSB - the decoded instruction-cache) miss.", + "PEBS": "1", + "MSRValue": "0x11", + "Counter": "0,1,2,3", + "EventName": "FRONTEND_RETIRED.DSB_MISS", + "MSRIndex": "0x3F7", + "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. ", + "TakenAlone": "1", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xC6", + "UMask": "0x1", + "BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss.", + "PEBS": "1", + "MSRValue": "0x12", + "Counter": "0,1,2,3", + "EventName": "FRONTEND_RETIRED.L1I_MISS", + "MSRIndex": "0x3F7", + "TakenAlone": "1", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xC6", + "UMask": "0x1", + "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss.", + "PEBS": "1", + "MSRValue": "0x13", + "Counter": "0,1,2,3", + "EventName": "FRONTEND_RETIRED.L2_MISS", + "MSRIndex": "0x3F7", + "TakenAlone": "1", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xC6", + "UMask": "0x1", + "BriefDescription": "Retired Instructions who experienced iTLB true miss.", + "PEBS": "1", + "MSRValue": "0x14", + "Counter": "0,1,2,3", + "EventName": "FRONTEND_RETIRED.ITLB_MISS", + "MSRIndex": "0x3F7", + "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.", + "TakenAlone": "1", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xC6", + "UMask": "0x1", + "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss.", + "PEBS": "1", + "MSRValue": "0x15", + "Counter": "0,1,2,3", + "EventName": "FRONTEND_RETIRED.STLB_MISS", + "MSRIndex": "0x3F7", + "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss. ", + "TakenAlone": "1", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xC6", + "UMask": "0x1", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 2 cycles which was not interrupted by a back-end stall.", + "PEBS": "1", + "MSRValue": "0x400206", + "Counter": "0,1,2,3", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2", + "MSRIndex": "0x3F7", + "TakenAlone": "1", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xC6", + "UMask": "0x1", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 2 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall.", + "PEBS": "1", + "MSRValue": "0x200206", + "Counter": "0,1,2,3", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_2", + "MSRIndex": "0x3F7", + "TakenAlone": "1", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xC6", + "UMask": "0x1", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.", + "PEBS": "1", + "MSRValue": "0x400406", + "Counter": "0,1,2,3", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", + "MSRIndex": "0x3F7", + "TakenAlone": "1", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xC6", + "UMask": "0x1", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 8 cycles which was not interrupted by a back-end stall.", + "PEBS": "1", + "MSRValue": "0x400806", + "Counter": "0,1,2,3", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", + "MSRIndex": "0x3F7", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.", + "TakenAlone": "1", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xC6", + "UMask": "0x1", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall.", + "PEBS": "1", + "MSRValue": "0x401006", + "Counter": "0,1,2,3", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", + "MSRIndex": "0x3F7", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.", + "TakenAlone": "1", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xC6", + "UMask": "0x1", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 32 cycles which was not interrupted by a back-end stall.", + "PEBS": "1", + "MSRValue": "0x402006", + "Counter": "0,1,2,3", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", + "MSRIndex": "0x3F7", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.", + "TakenAlone": "1", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xC6", + "UMask": "0x1", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.", + "PEBS": "1", + "MSRValue": "0x404006", + "Counter": "0,1,2,3", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", + "MSRIndex": "0x3F7", + "TakenAlone": "1", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xC6", + "UMask": "0x1", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.", + "PEBS": "1", + "MSRValue": "0x408006", + "Counter": "0,1,2,3", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_128", + "MSRIndex": "0x3F7", + "TakenAlone": "1", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xC6", + "UMask": "0x1", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.", + "PEBS": "1", + "MSRValue": "0x410006", + "Counter": "0,1,2,3", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", + "MSRIndex": "0x3F7", + "TakenAlone": "1", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xC6", + "UMask": "0x1", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.", + "PEBS": "1", + "MSRValue": "0x420006", + "Counter": "0,1,2,3", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", + "MSRIndex": "0x3F7", + "TakenAlone": "1", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xC6", + "UMask": "0x1", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 1 bubble-slot for a period of 2 cycles which was not interrupted by a back-end stall.", + "PEBS": "1", + "MSRValue": "0x100206", + "Counter": "0,1,2,3", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1", + "MSRIndex": "0x3F7", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.", + "TakenAlone": "1", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xC6", + "UMask": "0x1", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 3 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall.", + "PEBS": "1", + "MSRValue": "0x300206", + "Counter": "0,1,2,3", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_3", + "MSRIndex": "0x3F7", + "TakenAlone": "1", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylakex/memory.json b/tools/perf/pmu-events/arch/x86/skylakex/memory.json new file mode 100644 index 000000000000..ca22a22c1abd --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/skylakex/memory.json @@ -0,0 +1,1396 @@ +[ + { + "EventCode": "0x54", + "UMask": "0x1", + "BriefDescription": "Number of times a transactional abort was signaled due to a data conflict on a transactionally accessed address", + "Counter": "0,1,2,3", + "EventName": "TX_MEM.ABORT_CONFLICT", + "PublicDescription": "Number of times a TSX line had a cache conflict.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x54", + "UMask": "0x2", + "BriefDescription": "Number of times a transactional abort was signaled due to a data capacity limitation for transactional reads or writes.", + "Counter": "0,1,2,3", + "EventName": "TX_MEM.ABORT_CAPACITY", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x54", + "UMask": "0x4", + "BriefDescription": "Number of times a HLE transactional region aborted due to a non XRELEASE prefixed instruction writing to an elided lock in the elision buffer", + "Counter": "0,1,2,3", + "EventName": "TX_MEM.ABORT_HLE_STORE_TO_ELIDED_LOCK", + "PublicDescription": "Number of times a TSX Abort was triggered due to a non-release/commit store to lock.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x54", + "UMask": "0x8", + "BriefDescription": "Number of times an HLE transactional execution aborted due to NoAllocatedElisionBuffer being non-zero.", + "Counter": "0,1,2,3", + "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_NOT_EMPTY", + "PublicDescription": "Number of times a TSX Abort was triggered due to commit but Lock Buffer not empty.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x54", + "UMask": "0x10", + "BriefDescription": "Number of times an HLE transactional execution aborted due to XRELEASE lock not satisfying the address and value requirements in the elision buffer", + "Counter": "0,1,2,3", + "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_MISMATCH", + "PublicDescription": "Number of times a TSX Abort was triggered due to release/commit but data and address mismatch.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x54", + "UMask": "0x20", + "BriefDescription": "Number of times an HLE transactional execution aborted due to an unsupported read alignment from the elision buffer.", + "Counter": "0,1,2,3", + "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_UNSUPPORTED_ALIGNMENT", + "PublicDescription": "Number of times a TSX Abort was triggered due to attempting an unsupported alignment from Lock Buffer.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x54", + "UMask": "0x40", + "BriefDescription": "Number of times HLE lock could not be elided due to ElisionBufferAvailable being zero.", + "Counter": "0,1,2,3", + "EventName": "TX_MEM.HLE_ELISION_BUFFER_FULL", + "PublicDescription": "Number of times we could not allocate Lock Buffer.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x5d", + "UMask": "0x1", + "BriefDescription": "Counts the number of times a class of instructions that may cause a transactional abort was executed. Since this is the count of execution, it may not always cause a transactional abort.", + "Counter": "0,1,2,3", + "EventName": "TX_EXEC.MISC1", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x5d", + "UMask": "0x2", + "BriefDescription": "Counts the number of times a class of instructions (e.g., vzeroupper) that may cause a transactional abort was executed inside a transactional region", + "Counter": "0,1,2,3", + "EventName": "TX_EXEC.MISC2", + "PublicDescription": "Unfriendly TSX abort triggered by a vzeroupper instruction.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x5d", + "UMask": "0x4", + "BriefDescription": "Counts the number of times an instruction execution caused the transactional nest count supported to be exceeded", + "Counter": "0,1,2,3", + "EventName": "TX_EXEC.MISC3", + "PublicDescription": "Unfriendly TSX abort triggered by a nest count that is too deep.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x5d", + "UMask": "0x8", + "BriefDescription": "Counts the number of times a XBEGIN instruction was executed inside an HLE transactional region.", + "Counter": "0,1,2,3", + "EventName": "TX_EXEC.MISC4", + "PublicDescription": "RTM region detected inside HLE.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x5d", + "UMask": "0x10", + "BriefDescription": "Counts the number of times an HLE XACQUIRE instruction was executed inside an RTM transactional region", + "Counter": "0,1,2,3", + "EventName": "TX_EXEC.MISC5", + "PublicDescription": "Counts the number of times an HLE XACQUIRE instruction was executed inside an RTM transactional region.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x60", + "UMask": "0x10", + "BriefDescription": "Counts number of Offcore outstanding Demand Data Read requests that miss L3 cache in the superQ every cycle.", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x60", + "UMask": "0x10", + "BriefDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD", + "CounterMask": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x60", + "UMask": "0x10", + "BriefDescription": "Cycles with at least 6 Demand Data Read requests that miss L3 cache in the superQ.", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD_GE_6", + "CounterMask": "6", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA3", + "UMask": "0x2", + "BriefDescription": "Cycles while L3 cache miss demand load is outstanding.", + "Counter": "0,1,2,3", + "EventName": "CYCLE_ACTIVITY.CYCLES_L3_MISS", + "CounterMask": "2", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA3", + "UMask": "0x6", + "BriefDescription": "Execution stalls while L3 cache miss demand load is outstanding.", + "Counter": "0,1,2,3", + "EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS", + "CounterMask": "6", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB0", + "UMask": "0x10", + "BriefDescription": "Demand Data Read requests who miss L3 cache", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", + "PublicDescription": "Demand Data Read requests who miss L3 cache.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC3", + "UMask": "0x2", + "BriefDescription": "Counts the number of machine clears due to memory order conflicts.", + "Counter": "0,1,2,3", + "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", + "Errata": "SKL089", + "PublicDescription": "Counts the number of memory ordering Machine Clears detected. Memory Ordering Machine Clears can result from one of the following:a. memory disambiguation,b. external snoop, orc. cross SMT-HW-thread snoop (stores) hitting load buffer.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC8", + "UMask": "0x1", + "BriefDescription": "Number of times an HLE execution started.", + "Counter": "0,1,2,3", + "EventName": "HLE_RETIRED.START", + "PublicDescription": "Number of times we entered an HLE region. Does not count nested transactions.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC8", + "UMask": "0x2", + "BriefDescription": "Number of times an HLE execution successfully committed", + "Counter": "0,1,2,3", + "EventName": "HLE_RETIRED.COMMIT", + "PublicDescription": "Number of times HLE commit succeeded.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC8", + "UMask": "0x4", + "BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one). ", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "HLE_RETIRED.ABORTED", + "PublicDescription": "Number of times HLE abort was triggered.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC8", + "UMask": "0x8", + "BriefDescription": "Number of times an HLE execution aborted due to various memory events (e.g., read/write capacity and conflicts).", + "Counter": "0,1,2,3", + "EventName": "HLE_RETIRED.ABORTED_MEM", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC8", + "UMask": "0x10", + "BriefDescription": "Number of times an HLE execution aborted due to hardware timer expiration.", + "Counter": "0,1,2,3", + "EventName": "HLE_RETIRED.ABORTED_TIMER", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC8", + "UMask": "0x20", + "BriefDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.). ", + "Counter": "0,1,2,3", + "EventName": "HLE_RETIRED.ABORTED_UNFRIENDLY", + "PublicDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC8", + "UMask": "0x40", + "BriefDescription": "Number of times an HLE execution aborted due to incompatible memory type", + "Counter": "0,1,2,3", + "EventName": "HLE_RETIRED.ABORTED_MEMTYPE", + "PublicDescription": "Number of times an HLE execution aborted due to incompatible memory type.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC8", + "UMask": "0x80", + "BriefDescription": "Number of times an HLE execution aborted due to unfriendly events (such as interrupts).", + "Counter": "0,1,2,3", + "EventName": "HLE_RETIRED.ABORTED_EVENTS", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC9", + "UMask": "0x1", + "BriefDescription": "Number of times an RTM execution started.", + "Counter": "0,1,2,3", + "EventName": "RTM_RETIRED.START", + "PublicDescription": "Number of times we entered an RTM region. Does not count nested transactions.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC9", + "UMask": "0x2", + "BriefDescription": "Number of times an RTM execution successfully committed", + "Counter": "0,1,2,3", + "EventName": "RTM_RETIRED.COMMIT", + "PublicDescription": "Number of times RTM commit succeeded.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC9", + "UMask": "0x4", + "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one). ", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "RTM_RETIRED.ABORTED", + "PublicDescription": "Number of times RTM abort was triggered.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC9", + "UMask": "0x8", + "BriefDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts)", + "Counter": "0,1,2,3", + "EventName": "RTM_RETIRED.ABORTED_MEM", + "PublicDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts).", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC9", + "UMask": "0x10", + "BriefDescription": "Number of times an RTM execution aborted due to uncommon conditions.", + "Counter": "0,1,2,3", + "EventName": "RTM_RETIRED.ABORTED_TIMER", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC9", + "UMask": "0x20", + "BriefDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions", + "Counter": "0,1,2,3", + "EventName": "RTM_RETIRED.ABORTED_UNFRIENDLY", + "PublicDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC9", + "UMask": "0x40", + "BriefDescription": "Number of times an RTM execution aborted due to incompatible memory type", + "Counter": "0,1,2,3", + "EventName": "RTM_RETIRED.ABORTED_MEMTYPE", + "PublicDescription": "Number of times an RTM execution aborted due to incompatible memory type.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC9", + "UMask": "0x80", + "BriefDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt)", + "Counter": "0,1,2,3", + "EventName": "RTM_RETIRED.ABORTED_EVENTS", + "PublicDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt).", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xCD", + "UMask": "0x1", + "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 4 cycles.", + "PEBS": "2", + "MSRValue": "0x4", + "Counter": "0,1,2,3", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", + "MSRIndex": "0x3F6", + "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", + "TakenAlone": "1", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xCD", + "UMask": "0x1", + "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 8 cycles.", + "PEBS": "2", + "MSRValue": "0x8", + "Counter": "0,1,2,3", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", + "MSRIndex": "0x3F6", + "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", + "TakenAlone": "1", + "SampleAfterValue": "50021", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xCD", + "UMask": "0x1", + "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 16 cycles.", + "PEBS": "2", + "MSRValue": "0x10", + "Counter": "0,1,2,3", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", + "MSRIndex": "0x3F6", + "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", + "TakenAlone": "1", + "SampleAfterValue": "20011", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xCD", + "UMask": "0x1", + "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 32 cycles.", + "PEBS": "2", + "MSRValue": "0x20", + "Counter": "0,1,2,3", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", + "MSRIndex": "0x3F6", + "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", + "TakenAlone": "1", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xCD", + "UMask": "0x1", + "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 64 cycles.", + "PEBS": "2", + "MSRValue": "0x40", + "Counter": "0,1,2,3", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", + "MSRIndex": "0x3F6", + "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", + "TakenAlone": "1", + "SampleAfterValue": "2003", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xCD", + "UMask": "0x1", + "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 128 cycles.", + "PEBS": "2", + "MSRValue": "0x80", + "Counter": "0,1,2,3", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", + "MSRIndex": "0x3F6", + "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", + "TakenAlone": "1", + "SampleAfterValue": "1009", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xCD", + "UMask": "0x1", + "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 256 cycles.", + "PEBS": "2", + "MSRValue": "0x100", + "Counter": "0,1,2,3", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", + "MSRIndex": "0x3F6", + "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", + "TakenAlone": "1", + "SampleAfterValue": "503", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xCD", + "UMask": "0x1", + "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 512 cycles.", + "PEBS": "2", + "MSRValue": "0x200", + "Counter": "0,1,2,3", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", + "MSRIndex": "0x3F6", + "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", + "TakenAlone": "1", + "SampleAfterValue": "101", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts demand data reads that miss in the L3.", + "MSRValue": "0x3fbc000001 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts demand data reads that miss in the L3. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts demand data reads that miss the L3 and clean or shared data is transferred from remote cache.", + "MSRValue": "0x083fc00001 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts demand data reads that miss the L3 and clean or shared data is transferred from remote cache. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts demand data reads that miss the L3 and the modified data is transferred from remote cache.", + "MSRValue": "0x103fc00001 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts demand data reads that miss the L3 and the modified data is transferred from remote cache. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from local or remote dram.", + "MSRValue": "0x063fc00001 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from local or remote dram. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from remote dram.", + "MSRValue": "0x063b800001 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from remote dram. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram.", + "MSRValue": "0x0604000001 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand data writes (RFOs) that miss in the L3.", + "MSRValue": "0x3fbc000002 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand data writes (RFOs) that miss in the L3. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and clean or shared data is transferred from remote cache.", + "MSRValue": "0x083fc00002 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and clean or shared data is transferred from remote cache. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache.", + "MSRValue": "0x103fc00002 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local or remote dram.", + "MSRValue": "0x063fc00002 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local or remote dram. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from remote dram.", + "MSRValue": "0x063b800002 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from remote dram. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram.", + "MSRValue": "0x0604000002 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand code reads that miss in the L3.", + "MSRValue": "0x3fbc000004 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand code reads that miss in the L3. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand code reads that miss the L3 and clean or shared data is transferred from remote cache.", + "MSRValue": "0x083fc00004 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand code reads that miss the L3 and clean or shared data is transferred from remote cache. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand code reads that miss the L3 and the modified data is transferred from remote cache.", + "MSRValue": "0x103fc00004 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand code reads that miss the L3 and the modified data is transferred from remote cache. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from local or remote dram.", + "MSRValue": "0x063fc00004 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from local or remote dram. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from remote dram.", + "MSRValue": "0x063b800004 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from remote dram. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram.", + "MSRValue": "0x0604000004 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3.", + "MSRValue": "0x3fbc000010 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and clean or shared data is transferred from remote cache.", + "MSRValue": "0x083fc00010 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and clean or shared data is transferred from remote cache. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the modified data is transferred from remote cache.", + "MSRValue": "0x103fc00010 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the modified data is transferred from remote cache. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local or remote dram.", + "MSRValue": "0x063fc00010 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local or remote dram. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from remote dram.", + "MSRValue": "0x063b800010 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from remote dram. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local dram.", + "MSRValue": "0x0604000010 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local dram. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3.", + "MSRValue": "0x3fbc000020 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and clean or shared data is transferred from remote cache.", + "MSRValue": "0x083fc00020 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and clean or shared data is transferred from remote cache. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the modified data is transferred from remote cache.", + "MSRValue": "0x103fc00020 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the modified data is transferred from remote cache. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local or remote dram.", + "MSRValue": "0x063fc00020 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local or remote dram. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from remote dram.", + "MSRValue": "0x063b800020 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from remote dram. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local dram.", + "MSRValue": "0x0604000020 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local dram. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3.", + "MSRValue": "0x3fbc000080 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and clean or shared data is transferred from remote cache.", + "MSRValue": "0x083fc00080 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and clean or shared data is transferred from remote cache. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the modified data is transferred from remote cache.", + "MSRValue": "0x103fc00080 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the modified data is transferred from remote cache. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local or remote dram.", + "MSRValue": "0x063fc00080 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local or remote dram. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from remote dram.", + "MSRValue": "0x063b800080 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from remote dram. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local dram.", + "MSRValue": "0x0604000080 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local dram. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3.", + "MSRValue": "0x3fbc000100 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and clean or shared data is transferred from remote cache.", + "MSRValue": "0x083fc00100 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and clean or shared data is transferred from remote cache. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the modified data is transferred from remote cache.", + "MSRValue": "0x103fc00100 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the modified data is transferred from remote cache. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local or remote dram.", + "MSRValue": "0x063fc00100 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local or remote dram. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from remote dram.", + "MSRValue": "0x063b800100 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from remote dram. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local dram.", + "MSRValue": "0x0604000100 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local dram. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss in the L3.", + "MSRValue": "0x3fbc000400 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss in the L3. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and clean or shared data is transferred from remote cache.", + "MSRValue": "0x083fc00400 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and clean or shared data is transferred from remote cache. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the modified data is transferred from remote cache.", + "MSRValue": "0x103fc00400 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the modified data is transferred from remote cache. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local or remote dram.", + "MSRValue": "0x063fc00400 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local or remote dram. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from remote dram.", + "MSRValue": "0x063b800400 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from remote dram. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local dram.", + "MSRValue": "0x0604000400 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local dram. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch data reads that miss in the L3.", + "MSRValue": "0x3fbc000490 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch data reads that miss in the L3. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache.", + "MSRValue": "0x083fc00490 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch data reads that miss the L3 and the modified data is transferred from remote cache.", + "MSRValue": "0x103fc00490 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch data reads that miss the L3 and the modified data is transferred from remote cache. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local or remote dram.", + "MSRValue": "0x063fc00490 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local or remote dram. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from remote dram.", + "MSRValue": "0x063b800490 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from remote dram. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local dram.", + "MSRValue": "0x0604000490 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local dram. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts prefetch RFOs that miss in the L3.", + "MSRValue": "0x3fbc000120 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts prefetch RFOs that miss in the L3. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache.", + "MSRValue": "0x083fc00120 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts prefetch RFOs that miss the L3 and the modified data is transferred from remote cache.", + "MSRValue": "0x103fc00120 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts prefetch RFOs that miss the L3 and the modified data is transferred from remote cache. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local or remote dram.", + "MSRValue": "0x063fc00120 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local or remote dram. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from remote dram.", + "MSRValue": "0x063b800120 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from remote dram. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local dram.", + "MSRValue": "0x0604000120 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local dram. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand & prefetch data reads that miss in the L3.", + "MSRValue": "0x3fbc000491 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand & prefetch data reads that miss in the L3. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache.", + "MSRValue": "0x083fc00491 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache.", + "MSRValue": "0x103fc00491 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local or remote dram.", + "MSRValue": "0x063fc00491 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local or remote dram. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram.", + "MSRValue": "0x063b800491 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram.", + "MSRValue": "0x0604000491 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand & prefetch RFOs that miss in the L3.", + "MSRValue": "0x3fbc000122 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand & prefetch RFOs that miss in the L3. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache.", + "MSRValue": "0x083fc00122 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the modified data is transferred from remote cache.", + "MSRValue": "0x103fc00122 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the modified data is transferred from remote cache. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local or remote dram.", + "MSRValue": "0x063fc00122 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local or remote dram. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from remote dram.", + "MSRValue": "0x063b800122 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from remote dram. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { + "Offcore": "1", + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram.", + "MSRValue": "0x0604000122 ", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + } +] diff --git a/tools/perf/pmu-events/arch/x86/skylakex/other.json b/tools/perf/pmu-events/arch/x86/skylakex/other.json new file mode 100644 index 000000000000..70243b0b0586 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/skylakex/other.json @@ -0,0 +1,72 @@ +[ + { + "EventCode": "0x28", + "UMask": "0x7", + "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the Non-AVX turbo schedule.", + "Counter": "0,1,2,3", + "EventName": "CORE_POWER.LVL0_TURBO_LICENSE", + "PublicDescription": "Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x28", + "UMask": "0x18", + "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the AVX2 turbo schedule.", + "Counter": "0,1,2,3", + "EventName": "CORE_POWER.LVL1_TURBO_LICENSE", + "PublicDescription": "Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x28", + "UMask": "0x20", + "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the AVX512 turbo schedule.", + "Counter": "0,1,2,3", + "EventName": "CORE_POWER.LVL2_TURBO_LICENSE", + "PublicDescription": "Core cycles where the core was running with power-delivery for license level 2 (introduced in Skylake Server michroarchtecture). This includes high current AVX 512-bit instructions.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x28", + "UMask": "0x40", + "BriefDescription": "Core cycles the core was throttled due to a pending power level request.", + "Counter": "0,1,2,3", + "EventName": "CORE_POWER.THROTTLE", + "PublicDescription": "Core cycles the out-of-order engine was throttled due to a pending power level request.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xCB", + "UMask": "0x1", + "BriefDescription": "Number of hardware interrupts received by the processor.", + "Counter": "0,1,2,3", + "EventName": "HW_INTERRUPTS.RECEIVED", + "PublicDescription": "Counts the number of hardware interruptions received by the processor.", + "SampleAfterValue": "203", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xFE", + "UMask": "0x2", + "BriefDescription": "Counts number of cache lines that are allocated and written back to L3 with the intention that they are more likely to be reused shortly", + "Counter": "0,1,2,3", + "EventName": "IDI_MISC.WB_UPGRADE", + "PublicDescription": "Counts number of cache lines that are allocated and written back to L3 with the intention that they are more likely to be reused shortly.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xFE", + "UMask": "0x4", + "BriefDescription": "Counts number of cache lines that are dropped and not written back to L3 as they are deemed to be less likely to be reused shortly", + "Counter": "0,1,2,3", + "EventName": "IDI_MISC.WB_DOWNGRADE", + "PublicDescription": "Counts number of cache lines that are dropped and not written back to L3 as they are deemed to be less likely to be reused shortly.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + } +] diff --git a/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json b/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json new file mode 100644 index 000000000000..0895d1e52a4a --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json @@ -0,0 +1,950 @@ +[ + { + "EventCode": "0x00", + "UMask": "0x1", + "BriefDescription": "Instructions retired from execution.", + "Counter": "Fixed counter 1", + "EventName": "INST_RETIRED.ANY", + "PublicDescription": "Counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, Counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. INST_RETIRED.ANY_P is counted by a programmable counter and it is an architectural performance event. Counting: Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.", + "SampleAfterValue": "2000003", + "CounterHTOff": "Fixed counter 1" + }, + { + "EventCode": "0x00", + "UMask": "0x2", + "BriefDescription": "Core cycles when the thread is not in halt state", + "Counter": "Fixed counter 2", + "EventName": "CPU_CLK_UNHALTED.THREAD", + "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.", + "SampleAfterValue": "2000003", + "CounterHTOff": "Fixed counter 2" + }, + { + "EventCode": "0x00", + "UMask": "0x2", + "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", + "Counter": "Fixed counter 2", + "EventName": "CPU_CLK_UNHALTED.THREAD_ANY", + "AnyThread": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "Fixed counter 2" + }, + { + "EventCode": "0x00", + "UMask": "0x3", + "BriefDescription": "Reference cycles when the core is not in halt state.", + "Counter": "Fixed counter 3", + "EventName": "CPU_CLK_UNHALTED.REF_TSC", + "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", + "SampleAfterValue": "2000003", + "CounterHTOff": "Fixed counter 3" + }, + { + "EventCode": "0x03", + "UMask": "0x2", + "BriefDescription": "Loads blocked by overlapping with store buffer that cannot be forwarded .", + "Counter": "0,1,2,3", + "EventName": "LD_BLOCKS.STORE_FORWARD", + "PublicDescription": "Counts how many times the load operation got the true Block-on-Store blocking code preventing store forwarding. This includes cases when:a. preceding store conflicts with the load (incomplete overlap),b. store forwarding is impossible due to u-arch limitations,c. preceding lock RMW operations are not forwarded,d. store has the no-forward bit set (uncacheable/page-split/masked stores),e. all-blocking stores are used (mostly, fences and port I/O), and others.The most common case is a load blocked due to its address range overlapping with a preceding smaller uncompleted store. Note: This event does not take into account cases of out-of-SW-control (for example, SbTailHit), unknown physical STA, and cases of blocking loads on store due to being non-WB memory type or a lock. These cases are covered by other events. See the table of not supported store forwards in the Optimization Guide.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x03", + "UMask": "0x8", + "BriefDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use", + "Counter": "0,1,2,3", + "EventName": "LD_BLOCKS.NO_SR", + "PublicDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x07", + "UMask": "0x1", + "BriefDescription": "False dependencies in MOB due to partial compare on address.", + "Counter": "0,1,2,3", + "EventName": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS", + "PublicDescription": "Counts false dependencies in MOB when the partial comparison upon loose net check and dependency was resolved by the Enhanced Loose net mechanism. This may not result in high performance penalties. Loose net checks can fail when loads and stores are 4k aliased.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x0D", + "UMask": "0x1", + "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for this thread (e.g. misprediction or memory nuke)", + "Counter": "0,1,2,3", + "EventName": "INT_MISC.RECOVERY_CYCLES", + "PublicDescription": "Core cycles the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x0D", + "UMask": "0x1", + "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).", + "Counter": "0,1,2,3", + "EventName": "INT_MISC.RECOVERY_CYCLES_ANY", + "AnyThread": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x0D", + "UMask": "0x80", + "BriefDescription": "Cycles the issue-stage is waiting for front-end to fetch from resteered path following branch misprediction or machine clear events.", + "Counter": "0,1,2,3", + "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x0E", + "UMask": "0x1", + "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS)", + "Counter": "0,1,2,3", + "EventName": "UOPS_ISSUED.ANY", + "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "Invert": "1", + "EventCode": "0x0E", + "UMask": "0x1", + "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread", + "Counter": "0,1,2,3", + "EventName": "UOPS_ISSUED.STALL_CYCLES", + "CounterMask": "1", + "PublicDescription": "Counts cycles during which the Resource Allocation Table (RAT) does not issue any Uops to the reservation station (RS) for the current thread.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x0E", + "UMask": "0x2", + "BriefDescription": "Uops inserted at issue-stage in order to preserve upper bits of vector registers.", + "Counter": "0,1,2,3", + "EventName": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH", + "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to \u201cMixing Intel AVX and Intel SSE Code\u201d section of the Optimization Guide.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x0E", + "UMask": "0x20", + "BriefDescription": "Number of slow LEA uops being allocated. A uop is generally considered SlowLea if it has 3 sources (e.g. 2 sources + immediate) regardless if as a result of LEA instruction or not.", + "Counter": "0,1,2,3", + "EventName": "UOPS_ISSUED.SLOW_LEA", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x14", + "UMask": "0x1", + "BriefDescription": "Cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.", + "Counter": "0,1,2,3", + "EventName": "ARITH.DIVIDER_ACTIVE", + "CounterMask": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x3C", + "UMask": "0x0", + "BriefDescription": "Thread cycles when thread is not in halt state", + "Counter": "0,1,2,3", + "EventName": "CPU_CLK_UNHALTED.THREAD_P", + "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x3C", + "UMask": "0x0", + "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", + "Counter": "0,1,2,3", + "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY", + "AnyThread": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EdgeDetect": "1", + "EventCode": "0x3C", + "UMask": "0x0", + "BriefDescription": "Counts when there is a transition from ring 1, 2 or 3 to ring 0.", + "Counter": "0,1,2,3", + "EventName": "CPU_CLK_UNHALTED.RING0_TRANS", + "CounterMask": "1", + "PublicDescription": "Counts when the Current Privilege Level (CPL) transitions from ring 1, 2 or 3 to ring 0 (Kernel).", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x3C", + "UMask": "0x1", + "BriefDescription": "Core crystal clock cycles when the thread is unhalted.", + "Counter": "0,1,2,3", + "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK", + "SampleAfterValue": "2503", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x3C", + "UMask": "0x1", + "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.", + "Counter": "0,1,2,3", + "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY", + "AnyThread": "1", + "SampleAfterValue": "2503", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x3C", + "UMask": "0x1", + "BriefDescription": "Core crystal clock cycles when the thread is unhalted.", + "Counter": "0,1,2,3", + "EventName": "CPU_CLK_UNHALTED.REF_XCLK", + "SampleAfterValue": "2503", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x3C", + "UMask": "0x1", + "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.", + "Counter": "0,1,2,3", + "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY", + "AnyThread": "1", + "SampleAfterValue": "2503", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x3C", + "UMask": "0x2", + "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.", + "Counter": "0,1,2,3", + "EventName": "CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x3C", + "UMask": "0x2", + "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.", + "Counter": "0,1,2,3", + "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE", + "SampleAfterValue": "2503", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x4C", + "UMask": "0x1", + "BriefDescription": "Demand load dispatches that hit L1D fill buffer (FB) allocated for software prefetch.", + "Counter": "0,1,2,3", + "EventName": "LOAD_HIT_PRE.SW_PF", + "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x5E", + "UMask": "0x1", + "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread", + "Counter": "0,1,2,3", + "EventName": "RS_EVENTS.EMPTY_CYCLES", + "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for the thread.; Note: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EdgeDetect": "1", + "Invert": "1", + "EventCode": "0x5E", + "UMask": "0x1", + "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.", + "Counter": "0,1,2,3", + "EventName": "RS_EVENTS.EMPTY_END", + "CounterMask": "1", + "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate front-end Latency Bound issues.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x87", + "UMask": "0x1", + "BriefDescription": "Stalls caused by changing prefix length of the instruction.", + "Counter": "0,1,2,3", + "EventName": "ILD_STALL.LCP", + "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "UMask": "0x1", + "BriefDescription": "Cycles per thread when uops are executed in port 0", + "Counter": "0,1,2,3", + "EventName": "UOPS_DISPATCHED_PORT.PORT_0", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 0.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "UMask": "0x2", + "BriefDescription": "Cycles per thread when uops are executed in port 1", + "Counter": "0,1,2,3", + "EventName": "UOPS_DISPATCHED_PORT.PORT_1", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 1.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "UMask": "0x4", + "BriefDescription": "Cycles per thread when uops are executed in port 2", + "Counter": "0,1,2,3", + "EventName": "UOPS_DISPATCHED_PORT.PORT_2", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 2.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "UMask": "0x8", + "BriefDescription": "Cycles per thread when uops are executed in port 3", + "Counter": "0,1,2,3", + "EventName": "UOPS_DISPATCHED_PORT.PORT_3", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 3.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "UMask": "0x10", + "BriefDescription": "Cycles per thread when uops are executed in port 4", + "Counter": "0,1,2,3", + "EventName": "UOPS_DISPATCHED_PORT.PORT_4", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 4.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "UMask": "0x20", + "BriefDescription": "Cycles per thread when uops are executed in port 5", + "Counter": "0,1,2,3", + "EventName": "UOPS_DISPATCHED_PORT.PORT_5", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 5.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "UMask": "0x40", + "BriefDescription": "Cycles per thread when uops are executed in port 6", + "Counter": "0,1,2,3", + "EventName": "UOPS_DISPATCHED_PORT.PORT_6", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 6.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "UMask": "0x80", + "BriefDescription": "Cycles per thread when uops are executed in port 7", + "Counter": "0,1,2,3", + "EventName": "UOPS_DISPATCHED_PORT.PORT_7", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 7.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA2", + "UMask": "0x1", + "BriefDescription": "Resource-related stall cycles", + "Counter": "0,1,2,3", + "EventName": "RESOURCE_STALLS.ANY", + "PublicDescription": "Counts resource-related stall cycles. Reasons for stalls can be as follows:a. *any* u-arch structure got full (LB, SB, RS, ROB, BOB, LM, Physical Register Reclaim Table (PRRT), or Physical History Table (PHT) slots).b. *any* u-arch structure got empty (like INT/SIMD FreeLists).c. FPU control word (FPCW), MXCSR.and others. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA2", + "UMask": "0x8", + "BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).", + "Counter": "0,1,2,3", + "EventName": "RESOURCE_STALLS.SB", + "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA3", + "UMask": "0x1", + "BriefDescription": "Cycles while L2 cache miss demand load is outstanding.", + "Counter": "0,1,2,3", + "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS", + "CounterMask": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA3", + "UMask": "0x4", + "BriefDescription": "Total execution stalls.", + "Counter": "0,1,2,3", + "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL", + "CounterMask": "4", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA3", + "UMask": "0x5", + "BriefDescription": "Execution stalls while L2 cache miss demand load is outstanding.", + "Counter": "0,1,2,3", + "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS", + "CounterMask": "5", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA3", + "UMask": "0x8", + "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.", + "Counter": "0,1,2,3", + "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS", + "CounterMask": "8", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA3", + "UMask": "0xc", + "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.", + "Counter": "0,1,2,3", + "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS", + "CounterMask": "12", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA3", + "UMask": "0x10", + "BriefDescription": "Cycles while memory subsystem has an outstanding load.", + "Counter": "0,1,2,3", + "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY", + "CounterMask": "16", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA3", + "UMask": "0x14", + "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.", + "Counter": "0,1,2,3", + "EventName": "CYCLE_ACTIVITY.STALLS_MEM_ANY", + "CounterMask": "20", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xA6", + "UMask": "0x1", + "BriefDescription": "Cycles where no uops were executed, the Reservation Station was not empty, the Store Buffer was full and there was no outstanding load.", + "Counter": "0,1,2,3", + "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS", + "PublicDescription": "Counts cycles during which no uops were executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA6", + "UMask": "0x2", + "BriefDescription": "Cycles total of 1 uop is executed on all ports and Reservation Station was not empty.", + "Counter": "0,1,2,3", + "EventName": "EXE_ACTIVITY.1_PORTS_UTIL", + "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA6", + "UMask": "0x4", + "BriefDescription": "Cycles total of 2 uops are executed on all ports and Reservation Station was not empty.", + "Counter": "0,1,2,3", + "EventName": "EXE_ACTIVITY.2_PORTS_UTIL", + "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA6", + "UMask": "0x8", + "BriefDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station was not empty.", + "Counter": "0,1,2,3", + "EventName": "EXE_ACTIVITY.3_PORTS_UTIL", + "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA6", + "UMask": "0x10", + "BriefDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station was not empty.", + "Counter": "0,1,2,3", + "EventName": "EXE_ACTIVITY.4_PORTS_UTIL", + "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA6", + "UMask": "0x40", + "BriefDescription": "Cycles where the Store Buffer was full and no outstanding load.", + "Counter": "0,1,2,3", + "EventName": "EXE_ACTIVITY.BOUND_ON_STORES", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA8", + "UMask": "0x1", + "BriefDescription": "Number of Uops delivered by the LSD.", + "Counter": "0,1,2,3", + "EventName": "LSD.UOPS", + "PublicDescription": "Number of uops delivered to the back-end by the LSD(Loop Stream Detector).", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA8", + "UMask": "0x1", + "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.", + "Counter": "0,1,2,3", + "EventName": "LSD.CYCLES_ACTIVE", + "CounterMask": "1", + "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA8", + "UMask": "0x1", + "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.", + "Counter": "0,1,2,3", + "EventName": "LSD.CYCLES_4_UOPS", + "CounterMask": "4", + "PublicDescription": "Counts the cycles when 4 uops are delivered by the LSD (Loop-stream detector).", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB1", + "UMask": "0x1", + "BriefDescription": "Counts the number of uops to be executed per-thread each cycle.", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED.THREAD", + "PublicDescription": "Number of uops to be executed per-thread each cycle.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "Invert": "1", + "EventCode": "0xB1", + "UMask": "0x1", + "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED.STALL_CYCLES", + "CounterMask": "1", + "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB1", + "UMask": "0x1", + "BriefDescription": "Cycles where at least 1 uop was executed per-thread", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC", + "CounterMask": "1", + "PublicDescription": "Cycles where at least 1 uop was executed per-thread.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB1", + "UMask": "0x1", + "BriefDescription": "Cycles where at least 2 uops were executed per-thread", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC", + "CounterMask": "2", + "PublicDescription": "Cycles where at least 2 uops were executed per-thread.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB1", + "UMask": "0x1", + "BriefDescription": "Cycles where at least 3 uops were executed per-thread", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC", + "CounterMask": "3", + "PublicDescription": "Cycles where at least 3 uops were executed per-thread.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB1", + "UMask": "0x1", + "BriefDescription": "Cycles where at least 4 uops were executed per-thread", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC", + "CounterMask": "4", + "PublicDescription": "Cycles where at least 4 uops were executed per-thread.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB1", + "UMask": "0x2", + "BriefDescription": "Number of uops executed on the core.", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED.CORE", + "PublicDescription": "Number of uops executed from any thread.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB1", + "UMask": "0x2", + "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", + "CounterMask": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB1", + "UMask": "0x2", + "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", + "CounterMask": "2", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB1", + "UMask": "0x2", + "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3", + "CounterMask": "3", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB1", + "UMask": "0x2", + "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4", + "CounterMask": "4", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "Invert": "1", + "EventCode": "0xB1", + "UMask": "0x2", + "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE", + "CounterMask": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB1", + "UMask": "0x10", + "BriefDescription": "Counts the number of x87 uops dispatched.", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED.X87", + "PublicDescription": "Counts the number of x87 uops executed.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC0", + "UMask": "0x0", + "BriefDescription": "Number of instructions retired. General Counter - architectural event", + "Counter": "0,1,2,3", + "EventName": "INST_RETIRED.ANY_P", + "Errata": "SKL091, SKL044", + "PublicDescription": "Counts the number of instructions (EOMs) retired. Counting covers macro-fused instructions individually (that is, increments by two).", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC0", + "UMask": "0x1", + "BriefDescription": "Precise instruction retired event with HW to reduce effect of PEBS shadow in IP distribution", + "PEBS": "2", + "Counter": "1", + "EventName": "INST_RETIRED.PREC_DIST", + "Errata": "SKL091, SKL044", + "PublicDescription": "A version of INST_RETIRED that allows for a more unbiased distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR) feature to mitigate some bias in how retired instructions get sampled.", + "SampleAfterValue": "2000003", + "CounterHTOff": "1" + }, + { + "Invert": "1", + "EventCode": "0xC0", + "UMask": "0x1", + "BriefDescription": "Number of cycles using always true condition applied to PEBS instructions retired event.", + "PEBS": "2", + "Counter": "0,2,3", + "EventName": "INST_RETIRED.TOTAL_CYCLES_PS", + "CounterMask": "10", + "Errata": "SKL091, SKL044", + "PublicDescription": "Number of cycles using an always true condition applied to PEBS instructions retired event. (inst_ret< 16)", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,2,3" + }, + { + "EventCode": "0xC1", + "UMask": "0x3f", + "BriefDescription": "Number of times a microcode assist is invoked by HW other than FP-assist. Examples include AD (page Access Dirty) and AVX* related assists.", + "Counter": "0,1,2,3", + "EventName": "OTHER_ASSISTS.ANY", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC2", + "UMask": "0x2", + "BriefDescription": "Retirement slots used.", + "Counter": "0,1,2,3", + "EventName": "UOPS_RETIRED.RETIRE_SLOTS", + "PublicDescription": "Counts the retirement slots used.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "Invert": "1", + "EventCode": "0xC2", + "UMask": "0x2", + "BriefDescription": "Cycles without actually retired uops.", + "Counter": "0,1,2,3", + "EventName": "UOPS_RETIRED.STALL_CYCLES", + "CounterMask": "1", + "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts cycles without actually retired uops.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "Invert": "1", + "EventCode": "0xC2", + "UMask": "0x2", + "BriefDescription": "Cycles with less than 10 actually retired uops.", + "Counter": "0,1,2,3", + "EventName": "UOPS_RETIRED.TOTAL_CYCLES", + "CounterMask": "10", + "PublicDescription": "Number of cycles using always true condition (uops_ret < 16) applied to non PEBS uops retired event.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EdgeDetect": "1", + "EventCode": "0xC3", + "UMask": "0x1", + "BriefDescription": "Number of machine clears (nukes) of any type. ", + "Counter": "0,1,2,3", + "EventName": "MACHINE_CLEARS.COUNT", + "CounterMask": "1", + "PublicDescription": "Number of machine clears (nukes) of any type.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC3", + "UMask": "0x4", + "BriefDescription": "Self-modifying code (SMC) detected.", + "Counter": "0,1,2,3", + "EventName": "MACHINE_CLEARS.SMC", + "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC4", + "UMask": "0x0", + "BriefDescription": "All (macro) branch instructions retired.", + "Counter": "0,1,2,3", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES", + "Errata": "SKL091", + "PublicDescription": "Counts all (macro) branch instructions retired.", + "SampleAfterValue": "400009", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC4", + "UMask": "0x1", + "BriefDescription": "Conditional branch instructions retired.", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "BR_INST_RETIRED.CONDITIONAL", + "Errata": "SKL091", + "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts conditional branch instructions retired.", + "SampleAfterValue": "400009", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC4", + "UMask": "0x2", + "BriefDescription": "Direct and indirect near call instructions retired.", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "BR_INST_RETIRED.NEAR_CALL", + "Errata": "SKL091", + "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts both direct and indirect near call instructions retired.", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC4", + "UMask": "0x4", + "BriefDescription": "All (macro) branch instructions retired. ", + "PEBS": "2", + "Counter": "0,1,2,3", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS", + "Errata": "SKL091", + "PublicDescription": "This is a precise version of BR_INST_RETIRED.ALL_BRANCHES that counts all (macro) branch instructions retired.", + "SampleAfterValue": "400009", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xC4", + "UMask": "0x8", + "BriefDescription": "Return instructions retired.", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "BR_INST_RETIRED.NEAR_RETURN", + "Errata": "SKL091", + "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts return instructions retired.", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC4", + "UMask": "0x10", + "BriefDescription": "Not taken branch instructions retired.", + "Counter": "0,1,2,3", + "EventName": "BR_INST_RETIRED.NOT_TAKEN", + "Errata": "SKL091", + "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts not taken branch instructions retired.", + "SampleAfterValue": "400009", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC4", + "UMask": "0x20", + "BriefDescription": "Taken branch instructions retired.", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "BR_INST_RETIRED.NEAR_TAKEN", + "Errata": "SKL091", + "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts taken branch instructions retired.", + "SampleAfterValue": "400009", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC4", + "UMask": "0x40", + "BriefDescription": "Far branch instructions retired.", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "BR_INST_RETIRED.FAR_BRANCH", + "Errata": "SKL091", + "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts far branch instructions retired.", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC5", + "UMask": "0x0", + "BriefDescription": "All mispredicted macro branch instructions retired.", + "Counter": "0,1,2,3", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", + "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.", + "SampleAfterValue": "400009", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC5", + "UMask": "0x1", + "BriefDescription": "Mispredicted conditional branch instructions retired.", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "BR_MISP_RETIRED.CONDITIONAL", + "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted conditional branch instructions retired.", + "SampleAfterValue": "400009", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC5", + "UMask": "0x2", + "BriefDescription": "Mispredicted direct and indirect near call instructions retired.", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "BR_MISP_RETIRED.NEAR_CALL", + "PublicDescription": "Counts both taken and not taken retired mispredicted direct and indirect near calls, including both register and memory indirect.", + "SampleAfterValue": "400009", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC5", + "UMask": "0x4", + "BriefDescription": "Mispredicted macro branch instructions retired. ", + "PEBS": "2", + "Counter": "0,1,2,3", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_PEBS", + "PublicDescription": "This is a precise version of BR_MISP_RETIRED.ALL_BRANCHES that counts all mispredicted macro branch instructions retired.", + "SampleAfterValue": "400009", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xC5", + "UMask": "0x20", + "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", + "SampleAfterValue": "400009", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xCC", + "UMask": "0x20", + "BriefDescription": "Increments whenever there is an update to the LBR array.", + "Counter": "0,1,2,3", + "EventName": "ROB_MISC_EVENTS.LBR_INSERTS", + "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xE6", + "UMask": "0x1", + "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.", + "Counter": "0,1,2,3", + "EventName": "BACLEARS.ANY", + "PublicDescription": "Counts the number of times the front-end is resteered when it finds a branch instruction in a fetch line. This occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylakex/uncore-memory.json b/tools/perf/pmu-events/arch/x86/skylakex/uncore-memory.json new file mode 100644 index 000000000000..9c7e5f8beee2 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/skylakex/uncore-memory.json @@ -0,0 +1,172 @@ +[ + { + "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "LLC_MISSES.MEM_READ", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "iMC" + }, + { + "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "LLC_MISSES.MEM_WRITE", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0xC", + "Unit": "iMC" + }, + { + "BriefDescription": "Memory controller clock ticks", + "Counter": "0,1,2,3", + "EventName": "UNC_M_CLOCKTICKS", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode", + "Counter": "0,1,2,3", + "EventCode": "0x85", + "EventName": "UNC_M_POWER_CHANNEL_PPD", + "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.", + "MetricName": "power_channel_ppd %", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles Memory is in self refresh power mode", + "Counter": "0,1,2,3", + "EventCode": "0x43", + "EventName": "UNC_M_POWER_SELF_REFRESH", + "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.", + "MetricName": "power_self_refresh %", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Pre-charges due to page misses", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.PAGE_MISS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Pre-charge for reads", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.RD", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "Pre-charge for writes", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.WR", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Page Activate commands sent due to a write request", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_M_ACT_COUNT.WR", + "PerPkg": "1", + "PublicDescription": "Counts DRAM Page Activate commands sent on this channel due to a write request to the iMC (Memory Controller). Activate commands are issued to open up a page on the DRAM devices so that it can be read or written to with a CAS (Column Access Select) command.", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "All DRAM CAS Commands issued", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_M_CAS_COUNT.ALL", + "PerPkg": "1", + "PublicDescription": "Counts all CAS (Column Address Select) commands issued to DRAM per memory channel. CAS commands are issued to specify the address to read or write on DRAM, so this event increments for every read and write. This event counts whether AutoPrecharge (which closes the DRAM Page automatically after a read/write) is enabled or not.", + "UMask": "0xF", + "Unit": "iMC" + }, + { + "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "LLC_MISSES.MEM_READ", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "iMC" + }, + { + "BriefDescription": "All DRAM Read CAS Commands issued (does not include underfills) ", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_M_CAS_COUNT.RD_REG", + "PerPkg": "1", + "PublicDescription": "Counts CAS (Column Access Select) regular read commands issued to DRAM on a per channel basis. CAS commands are issued to specify the address to read or write on DRAM, and this event increments for every regular read. This event only counts regular reads and does not includes underfill reads due to partial write requests. This event counts whether AutoPrecharge (which closes the DRAM Page automatically after a read/write) is enabled or not.", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Underfill Read CAS Commands issued", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_M_CAS_COUNT.RD_UNDERFILL", + "PerPkg": "1", + "PublicDescription": "Counts CAS (Column Access Select) underfill read commands issued to DRAM due to a partial write, on a per channel basis. CAS commands are issued to specify the address to read or write on DRAM, and this command counts underfill reads. Partial writes must be completed by first reading in the underfill from DRAM and then merging in the partial write data before writing the full line back to DRAM. This event will generally count about the same as the number of partial writes, but may be slightly less because of partials hitting in the WPQ (due to a previous write request). ", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "LLC_MISSES.MEM_WRITE", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0xC", + "Unit": "iMC" + }, + { + "BriefDescription": "Read Pending Queue Allocations", + "Counter": "0,1,2,3", + "EventCode": "0x10", + "EventName": "UNC_M_RPQ_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts the number of read requests allocated into the Read Pending Queue (RPQ). This queue is used to schedule reads out to the memory controller and to track the requests. Requests allocate into the RPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the CHA to the iMC. The requests deallocate after the read CAS command has been issued to DRAM. This event counts both Isochronous and non-Isochronous requests which were issued to the RPQ. ", + "Unit": "iMC" + }, + { + "BriefDescription": "Read Pending Queue Occupancy", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_M_RPQ_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries in the Read Pending Queue (RPQ) at each cycle. This can then be used to calculate both the average occupancy of the queue (in conjunction with the number of cycles not empty) and the average latency in the queue (in conjunction with the number of allocations). The RPQ is used to schedule reads out to the memory controller and to track the requests. Requests allocate into the RPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the CHA to the iMC. They deallocate from the RPQ after the CAS command has been issued to memory.", + "Unit": "iMC" + }, + { + "BriefDescription": "Write Pending Queue Allocations", + "Counter": "0,1,2,3", + "EventCode": "0x20", + "EventName": "UNC_M_WPQ_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts the number of writes requests allocated into the Write Pending Queue (WPQ). The WPQ is used to schedule writes out to the memory controller and to track the requests. Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the CHA to the iMC (Memory Controller). The write requests deallocate after being issued to DRAM. Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have 'posted' to the iMC.", + "Unit": "iMC" + }, + { + "BriefDescription": "Write Pending Queue Occupancy", + "Counter": "0,1,2,3", + "EventCode": "0x81", + "EventName": "UNC_M_WPQ_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries in the Write Pending Queue (WPQ) at each cycle. This can then be used to calculate both the average queue occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The WPQ is used to schedule writes out to the memory controller and to track the requests.", + "Unit": "iMC" + } +] diff --git a/tools/perf/pmu-events/arch/x86/skylakex/uncore-other.json b/tools/perf/pmu-events/arch/x86/skylakex/uncore-other.json new file mode 100644 index 000000000000..de6e70e552e2 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/skylakex/uncore-other.json @@ -0,0 +1,1156 @@ +[ + { + "BriefDescription": "Uncore cache clock ticks", + "Counter": "0,1,2,3", + "EventName": "UNC_CHA_CLOCKTICKS", + "PerPkg": "1", + "Unit": "CHA" + }, + { + "BriefDescription": "LLC misses - Uncacheable reads (from cpu) . Derived from unc_cha_tor_inserts.ia_miss", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.UNCACHEABLE", + "Filter": "config1=0x40e33", + "PerPkg": "1", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "MMIO reads. Derived from unc_cha_tor_inserts.ia_miss", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.MMIO_READ", + "Filter": "config1=0x40040e33", + "PerPkg": "1", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "MMIO writes. Derived from unc_cha_tor_inserts.ia_miss", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.MMIO_WRITE", + "Filter": "config1=0x40041e33", + "PerPkg": "1", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "Streaming stores (full cache line). Derived from unc_cha_tor_inserts.ia_miss", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_FULL", + "Filter": "config1=0x41833", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "Streaming stores (partial cache line). Derived from unc_cha_tor_inserts.ia_miss", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_PARTIAL", + "Filter": "config1=0x41a33", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "read requests from home agent", + "Counter": "0,1,2,3", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.READS", + "PerPkg": "1", + "UMask": "0x03", + "Unit": "CHA" + }, + { + "BriefDescription": "read requests from local home agent", + "Counter": "0,1,2,3", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.READS_LOCAL", + "PerPkg": "1", + "UMask": "0x01", + "Unit": "CHA" + }, + { + "BriefDescription": "read requests from remote home agent", + "Counter": "0,1,2,3", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.READS_REMOTE", + "PerPkg": "1", + "UMask": "0x02", + "Unit": "CHA" + }, + { + "BriefDescription": "write requests from home agent", + "Counter": "0,1,2,3", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.WRITES", + "PerPkg": "1", + "UMask": "0x0C", + "Unit": "CHA" + }, + { + "BriefDescription": "write requests from local home agent", + "Counter": "0,1,2,3", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.WRITES_LOCAL", + "PerPkg": "1", + "UMask": "0x04", + "Unit": "CHA" + }, + { + "BriefDescription": "write requests from remote home agent", + "Counter": "0,1,2,3", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.WRITES_REMOTE", + "PerPkg": "1", + "UMask": "0x08", + "Unit": "CHA" + }, + { + "BriefDescription": "UPI interconnect send bandwidth for payload. Derived from unc_upi_txl_flits.all_data", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UPI_DATA_BANDWIDTH_TX", + "PerPkg": "1", + "ScaleUnit": "7.11E-06Bytes", + "UMask": "0x0F", + "Unit": "UPI LL" + }, + { + "BriefDescription": "PCI Express bandwidth reading at IIO. Derived from unc_iio_data_req_of_cpu.mem_read.part0", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "LLC_MISSES.PCIE_READ", + "FCMask": "0x07", + "Filter": "ch_mask=0x1f", + "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3", + "MetricName": "LLC_MISSES.PCIE_READ", + "PerPkg": "1", + "PortMask": "0x01", + "ScaleUnit": "4Bytes", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth writing at IIO. Derived from unc_iio_data_req_of_cpu.mem_write.part0", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "LLC_MISSES.PCIE_WRITE", + "FCMask": "0x07", + "Filter": "ch_mask=0x1f", + "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3", + "MetricName": "LLC_MISSES.PCIE_WRITE", + "PerPkg": "1", + "PortMask": "0x01", + "ScaleUnit": "4Bytes", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth writing at IIO, part 0", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3", + "MetricName": "LLC_MISSES.PCIE_WRITE", + "PerPkg": "1", + "PortMask": "0x01", + "ScaleUnit": "4Bytes", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth writing at IIO, part 1", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "ScaleUnit": "4Bytes", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth writing at IIO, part 2", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "ScaleUnit": "4Bytes", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth writing at IIO, part 3", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "ScaleUnit": "4Bytes", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth reading at IIO, part 0", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0", + "FCMask": "0x07", + "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3", + "MetricName": "LLC_MISSES.PCIE_READ", + "PerPkg": "1", + "PortMask": "0x01", + "ScaleUnit": "4Bytes", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth reading at IIO, part 1", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "ScaleUnit": "4Bytes", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth reading at IIO, part 2", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "ScaleUnit": "4Bytes", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth reading at IIO, part 3", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "ScaleUnit": "4Bytes", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Core Cross Snoops Issued; Multiple Core Requests", + "Counter": "0,1,2,3", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.CORE_GTONE", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x42", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued; Multiple Eviction", + "Counter": "0,1,2,3", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.EVICT_GTONE", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x82", + "Unit": "CHA" + }, + { + "BriefDescription": "Multi-socket cacheline Directory state lookups; Snoop Not Needed", + "Counter": "0,1,2,3", + "EventCode": "0x53", + "EventName": "UNC_CHA_DIR_LOOKUP.NO_SNP", + "PerPkg": "1", + "PublicDescription": "Counts transactions that looked into the multi-socket cacheline Directory state, and therefore did not send a snoop because the Directory indicated it was not needed", + "UMask": "0x02", + "Unit": "CHA" + }, + { + "BriefDescription": "Multi-socket cacheline Directory state lookups; Snoop Needed", + "Counter": "0,1,2,3", + "EventCode": "0x53", + "EventName": "UNC_CHA_DIR_LOOKUP.SNP", + "PerPkg": "1", + "PublicDescription": "Counts transactions that looked into the multi-socket cacheline Directory state, and sent one or more snoops, because the Directory indicated it was needed", + "UMask": "0x01", + "Unit": "CHA" + }, + { + "BriefDescription": "Multi-socket cacheline Directory state updates; Directory Updated memory write from the HA pipe", + "Counter": "0,1,2,3", + "EventCode": "0x54", + "EventName": "UNC_CHA_DIR_UPDATE.HA", + "PerPkg": "1", + "PublicDescription": "Counts only multi-socket cacheline Directory state updates memory writes issued from the HA pipe. This does not include memory write requests which are for I (Invalid) or E (Exclusive) cachelines.", + "UMask": "0x01", + "Unit": "CHA" + }, + { + "BriefDescription": "Multi-socket cacheline Directory state updates; Directory Updated memory write from TOR pipe", + "Counter": "0,1,2,3", + "EventCode": "0x54", + "EventName": "UNC_CHA_DIR_UPDATE.TOR", + "PerPkg": "1", + "PublicDescription": "Counts only multi-socket cacheline Directory state updates due to memory writes issued from the TOR pipe which are the result of remote transaction hitting the SF/LLC and returning data Core2Core. This does not include memory write requests which are for I (Invalid) or E (Exclusive) cachelines.", + "UMask": "0x02", + "Unit": "CHA" + }, + { + "BriefDescription": "Read request from a remote socket which hit in the HitMe Cache to a line In the E state", + "Counter": "0,1,2,3", + "EventCode": "0x5F", + "EventName": "UNC_CHA_HITME_HIT.EX_RDS", + "PerPkg": "1", + "PublicDescription": "Counts read requests from a remote socket which hit in the HitME cache (used to cache the multi-socket Directory state) to a line in the E(Exclusive) state. This includes the following read opcodes (RdCode, RdData, RdDataMigratory, RdCur, RdInv*, Inv*)", + "UMask": "0x01", + "Unit": "CHA" + }, + { + "BriefDescription": "Normal priority reads issued to the memory controller from the CHA", + "Counter": "0,1,2,3", + "EventCode": "0x59", + "EventName": "UNC_CHA_IMC_READS_COUNT.NORMAL", + "PerPkg": "1", + "PublicDescription": "Counts when a normal (Non-Isochronous) read is issued to any of the memory controller channels from the CHA.", + "UMask": "0x01", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA to iMC Full Line Writes Issued; Full Line Non-ISOCH", + "Counter": "0,1,2,3", + "EventCode": "0x5B", + "EventName": "UNC_CHA_IMC_WRITES_COUNT.FULL", + "PerPkg": "1", + "PublicDescription": "Counts when a normal (Non-Isochronous) full line write is issued from the CHA to the any of the memory controller channels.", + "UMask": "0x01", + "Unit": "CHA" + }, + { + "BriefDescription": "Number of times that an RFO hit in S state.", + "Counter": "0,1,2,3", + "EventCode": "0x39", + "EventName": "UNC_CHA_MISC.RFO_HIT_S", + "PerPkg": "1", + "PublicDescription": "Counts when a RFO (the Read for Ownership issued before a write) request hit a cacheline in the S (Shared) state.", + "UMask": "0x08", + "Unit": "CHA" + }, + { + "BriefDescription": "Local requests for exclusive ownership of a cache line without receiving data", + "Counter": "0,1,2,3", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.INVITOE_LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts the total number of requests coming from a unit on this socket for exclusive ownership of a cache line without receiving data (INVITOE) to the CHA.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Local requests for exclusive ownership of a cache line without receiving data", + "Counter": "0,1,2,3", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.INVITOE_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the total number of requests coming from a remote socket for exclusive ownership of a cache line without receiving data (INVITOE) to the CHA.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "RspCnflct* Snoop Responses Received", + "Counter": "0,1,2,3", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSPCNFLCTS", + "PerPkg": "1", + "PublicDescription": "Counts when a a transaction with the opcode type RspCnflct* Snoop Response was received. This is returned when a snoop finds an existing outstanding transaction in a remote caching agent. This triggers conflict resolution hardware. This covers both the opcode RspCnflct and RspCnflctWbI.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "RspI Snoop Responses Received", + "Counter": "0,1,2,3", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSPI", + "PerPkg": "1", + "PublicDescription": "Counts when a transaction with the opcode type RspI Snoop Response was received which indicates the remote cache does not have the data, or when the remote cache silently evicts data (such as when an RFO: the Read for Ownership issued before a write hits non-modified data).", + "UMask": "0x01", + "Unit": "CHA" + }, + { + "BriefDescription": "RspIFwd Snoop Responses Received", + "Counter": "0,1,2,3", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSPIFWD", + "PerPkg": "1", + "PublicDescription": "Counts when a a transaction with the opcode type RspIFwd Snoop Response was received which indicates a remote caching agent forwarded the data and the requesting agent is able to acquire the data in E (Exclusive) or M (modified) states. This is commonly returned with RFO (the Read for Ownership issued before a write) transactions. The snoop could have either been to a cacheline in the M,E,F (Modified, Exclusive or Forward) states.", + "UMask": "0x04", + "Unit": "CHA" + }, + { + "BriefDescription": "RspSFwd Snoop Responses Received", + "Counter": "0,1,2,3", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSPSFWD", + "PerPkg": "1", + "PublicDescription": "Counts when a a transaction with the opcode type RspSFwd Snoop Response was received which indicates a remote caching agent forwarded the data but held on to its current copy. This is common for data and code reads that hit in a remote socket in E (Exclusive) or F (Forward) state.", + "UMask": "0x08", + "Unit": "CHA" + }, + { + "BriefDescription": "Rsp*Fwd*WB Snoop Responses Received", + "Counter": "0,1,2,3", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSP_FWD_WB", + "PerPkg": "1", + "PublicDescription": "Counts when a transaction with the opcode type Rsp*Fwd*WB Snoop Response was received which indicates the data was written back to it's home socket, and the cacheline was forwarded to the requestor socket. This snoop response is only used in >= 4 socket systems. It is used when a snoop HITM's in a remote caching agent and it directly forwards data to a requestor, and simultaneously returns data to it's home socket to be written back to memory.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Rsp*WB Snoop Responses Received", + "Counter": "0,1,2,3", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSP_WBWB", + "PerPkg": "1", + "PublicDescription": "Counts when a transaction with the opcode type Rsp*WB Snoop Response was received which indicates which indicates the data was written back to it's home. This is returned when a non-RFO request hits a cacheline in the Modified state. The Cache can either downgrade the cacheline to a S (Shared) or I (Invalid) state depending on how the system has been configured. This reponse will also be sent when a cache requests E (Exclusive) ownership of a cache line without receiving data, because the cache must acquire ownership.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Clockticks of the IIO Traffic Controller", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_IIO_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Counts clockticks of the 1GHz trafiic controller clock in the IIO unit.", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part0", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part0. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part1", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part1. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part2", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part2. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part3", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part3. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made to IIO Part0 by the CPU", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part0 by a unit on the main die (generally a core). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made to IIO Part1 by the CPU", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part1 by a unit on the main die (generally a core). In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made to IIO Part2 by the CPU ", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part2 by a unit on the main die (generally a core). In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made to IIO Part3 by the CPU ", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part3 by a unit on the main die (generally a core). In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part0", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part0. In the general case, part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part1", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part1. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part2", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part2. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part3", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part3. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part0 by the CPU", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part0 by a unit on the main die (generally a core). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part1 by the CPU", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part1 by a unit on the main die (generally a core). In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part2 by the CPU ", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part2 by a unit on the main die (generally a core). In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part3 by the CPU ", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part3 by a unit on the main die (generally a core). In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part0 to Memory", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by IIO Part0 to a unit on the main die (generally memory). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part1 to Memory", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by IIO Part1 to a unit on the main die (generally memory). In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part2 to Memory", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by IIO Part2 to a unit on the main die (generally memory). In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part3 to Memory", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by IIO Part3 to a unit on the main die (generally memory). In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part0 to Memory", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made by IIO Part0 to a unit on the main die (generally memory). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part1 to Memory", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made by IIO Part1 to a unit on the main die (generally memory). In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part2 to Memory", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made by IIO Part2 to a unit on the main die (generally memory). In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part3 to Memory", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made by IIO Part3 to a unit on the main die (generally memory). In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Traffic in which the M2M to iMC Bypass was not taken", + "Counter": "0,1,2,3", + "EventCode": "0x22", + "EventName": "UNC_M2M_BYPASS_M2M_Egress.NOT_TAKEN", + "PerPkg": "1", + "PublicDescription": "Counts traffic in which the M2M (Mesh to Memory) to iMC (Memory Controller) bypass was not taken", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles when direct to core mode (which bypasses the CHA) was disabled", + "Counter": "0,1,2,3", + "EventCode": "0x24", + "EventName": "UNC_M2M_DIRECT2CORE_NOT_TAKEN_DIRSTATE", + "PerPkg": "1", + "PublicDescription": "Counts cycles when direct to core mode (which bypasses the CHA) was disabled", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages sent direct to core (bypassing the CHA)", + "Counter": "0,1,2,3", + "EventCode": "0x23", + "EventName": "UNC_M2M_DIRECT2CORE_TAKEN", + "PerPkg": "1", + "PublicDescription": "Counts when messages were sent direct to core (bypassing the CHA)", + "Unit": "M2M" + }, + { + "BriefDescription": "Number of reads in which direct to core transaction were overridden", + "Counter": "0,1,2,3", + "EventCode": "0x25", + "EventName": "UNC_M2M_DIRECT2CORE_TXN_OVERRIDE", + "PerPkg": "1", + "PublicDescription": "Counts reads in which direct to core transactions (which would have bypassed the CHA) were overridden", + "Unit": "M2M" + }, + { + "BriefDescription": "Number of reads in which direct to Intel UPI transactions were overridden", + "Counter": "0,1,2,3", + "EventCode": "0x28", + "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_CREDITS", + "PerPkg": "1", + "PublicDescription": "Counts reads in which direct to Intel Ultra Path Interconnect (UPI) transactions (which would have bypassed the CHA) were overridden", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles when direct to Intel UPI was disabled", + "Counter": "0,1,2,3", + "EventCode": "0x27", + "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_DIRSTATE", + "PerPkg": "1", + "PublicDescription": "Counts cycles when the ability to send messages direct to the Intel Ultra Path Interconnect (bypassing the CHA) was disabled", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages sent direct to the Intel UPI", + "Counter": "0,1,2,3", + "EventCode": "0x26", + "EventName": "UNC_M2M_DIRECT2UPI_TAKEN", + "PerPkg": "1", + "PublicDescription": "Counts when messages were sent direct to the Intel Ultra Path Interconnect (bypassing the CHA)", + "Unit": "M2M" + }, + { + "BriefDescription": "Number of reads that a message sent direct2 Intel UPI was overridden", + "Counter": "0,1,2,3", + "EventCode": "0x29", + "EventName": "UNC_M2M_DIRECT2UPI_TXN_OVERRIDE", + "PerPkg": "1", + "PublicDescription": "Counts when a read message that was sent direct to the Intel Ultra Path Interconnect (bypassing the CHA) was overridden", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookups (any state found)", + "Counter": "0,1,2,3", + "EventCode": "0x2D", + "EventName": "UNC_M2M_DIRECTORY_LOOKUP.ANY", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) looks into the multi-socket cacheline Directory state, and found the cacheline marked in Any State (A, I, S or unused)", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookups (cacheline found in A state) ", + "Counter": "0,1,2,3", + "EventCode": "0x2D", + "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_A", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) looks into the multi-socket cacheline Directory state, and found the cacheline marked in the A (SnoopAll) state, indicating the cacheline is stored in another socket in any state, and we must snoop the other sockets to make sure we get the latest data. The data may be stored in any state in the local socket.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookup (cacheline found in I state) ", + "Counter": "0,1,2,3", + "EventCode": "0x2D", + "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_I", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) looks into the multi-socket cacheline Directory state , and found the cacheline marked in the I (Invalid) state indicating the cacheline is not stored in another socket, and so there is no need to snoop the other sockets for the latest data. The data may be stored in any state in the local socket.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookup (cacheline found in S state) ", + "Counter": "0,1,2,3", + "EventCode": "0x2D", + "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_S", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) looks into the multi-socket cacheline Directory state , and found the cacheline marked in the S (Shared) state indicating the cacheline is either stored in another socket in the S(hared) state , and so there is no need to snoop the other sockets for the latest data. The data may be stored in any state in the local socket.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from A to I", + "Counter": "0,1,2,3", + "EventCode": "0x2E", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.A2I", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from from A (SnoopAll) to I (Invalid)", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from A to S", + "Counter": "0,1,2,3", + "EventCode": "0x2E", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.A2S", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from from A (SnoopAll) to S (Shared)", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from/to Any state ", + "Counter": "0,1,2,3", + "EventCode": "0x2E", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.ANY", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory to a new state", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from I to A", + "Counter": "0,1,2,3", + "EventCode": "0x2E", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.I2A", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from from I (Invalid) to A (SnoopAll)", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from I to S", + "Counter": "0,1,2,3", + "EventCode": "0x2E", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.I2S", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from from I (Invalid) to S (Shared)", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from S to A", + "Counter": "0,1,2,3", + "EventCode": "0x2E", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.S2A", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from from S (Shared) to A (SnoopAll)", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from S to I", + "Counter": "0,1,2,3", + "EventCode": "0x2E", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.S2I", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from from S (Shared) to I (Invalid)", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Reads to iMC issued", + "Counter": "0,1,2,3", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.ALL", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) issues reads to the iMC (Memory Controller). ", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Reads to iMC issued at Normal Priority (Non-Isochronous)", + "Counter": "0,1,2,3", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.NORMAL", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) issues reads to the iMC (Memory Controller). It only counts normal priority non-isochronous reads.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Writes to iMC issued", + "Counter": "0,1,2,3", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.ALL", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) issues writes to the iMC (Memory Controller).", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Partial Non-Isochronous writes to the iMC", + "Counter": "0,1,2,3", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.PARTIAL", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) issues partial writes to the iMC (Memory Controller). It only counts normal priority non-isochronous writes.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefecth requests that got turn into a demand request", + "Counter": "0,1,2,3", + "EventCode": "0x56", + "EventName": "UNC_M2M_PREFCAM_DEMAND_PROMOTIONS", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) promotes a outstanding request in the prefetch queue due to a subsequent demand read request that entered the M2M with the same address. Explanatory Side Note: The Prefecth queue is made of CAM (Content Addressable Memory)", + "Unit": "M2M" + }, + { + "BriefDescription": "Inserts into the Memory Controller Prefetch Queue", + "Counter": "0,1,2,3", + "EventCode": "0x57", + "EventName": "UNC_M2M_PREFCAM_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) recieves a prefetch request and inserts it into its outstanding prefetch queue. Explanatory Side Note: the prefect queue is made from CAM: Content Addressable Memory", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Ingress (from CMS) Queue Inserts", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_M2M_RxC_AD_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts when the a new entry is Received(RxC) and then added to the AD (Address Ring) Ingress Queue from the CMS (Common Mesh Stop). This is generally used for reads, and ", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetches generated by the flow control queue of the M3UPI unit.", + "Counter": "0,1,2,3", + "EventCode": "0x29", + "EventName": "UNC_M3UPI_UPI_PREFETCH_SPAWN", + "PerPkg": "1", + "PublicDescription": "Count cases where flow control queue that sits between the Intel Ultra Path Interconnect (UPI) and the mesh spawns a prefetch to the iMC (Memory Controller)", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Clocks of the Intel Ultra Path Interconnect (UPI)", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_UPI_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Counts clockticks of the fixed frequency clock controlling the Intel Ultra Path Interconnect (UPI). This clock runs at1/8th the 'GT/s' speed of the UPI link. For example, a 9.6GT/s link will have a fixed Frequency of 1.2 Ghz.", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Data Response packets that go direct to core", + "Counter": "0,1,2,3", + "EventCode": "0x12", + "EventName": "UNC_UPI_DIRECT_ATTEMPTS.D2C", + "PerPkg": "1", + "PublicDescription": "Counts Data Response (DRS) packets that attempted to go direct to core bypassing the CHA.", + "UMask": "0x1", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Data Response packets that go direct to Intel UPI", + "Counter": "0,1,2,3", + "EventCode": "0x12", + "EventName": "UNC_UPI_DIRECT_ATTEMPTS.D2U", + "PerPkg": "1", + "PublicDescription": "Counts Data Response (DRS) packets that attempted to go direct to Intel Ultra Path Interconnect (UPI) bypassing the CHA .", + "UMask": "0x2", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Cycles Intel UPI is in L1 power mode (shutdown)", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_UPI_L1_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts cycles when the Intel Ultra Path Interconnect (UPI) is in L1 power mode. L1 is a mode that totally shuts down the UPI link. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another, this event only coutns when both links are shutdown.", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Cycles the Rx of the Intel UPI is in L0p power mode", + "Counter": "0,1,2,3", + "EventCode": "0x25", + "EventName": "UNC_UPI_RxL0P_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts cycles when the the receive side (Rx) of the Intel Ultra Path Interconnect(UPI) is in L0p power mode. L0p is a mode where we disable 60% of the UPI lanes, decreasing our bandwidth in order to save power.", + "Unit": "UPI LL" + }, + { + "BriefDescription": "FLITs received which bypassed the Slot0 Receive Buffer", + "Counter": "0,1,2,3", + "EventCode": "0x31", + "EventName": "UNC_UPI_RxL_BYPASSED.SLOT0", + "PerPkg": "1", + "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the slot0 RxQ buffer (Receive Queue) and passed directly to the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of FLITs transfered, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", + "UMask": "0x1", + "Unit": "UPI LL" + }, + { + "BriefDescription": "FLITs received which bypassed the Slot0 Receive Buffer", + "Counter": "0,1,2,3", + "EventCode": "0x31", + "EventName": "UNC_UPI_RxL_BYPASSED.SLOT1", + "PerPkg": "1", + "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the slot1 RxQ buffer (Receive Queue) and passed directly across the BGF and into the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of FLITs transfered, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", + "UMask": "0x2", + "Unit": "UPI LL" + }, + { + "BriefDescription": "FLITs received which bypassed the Slot0 Recieve Buffer", + "Counter": "0,1,2,3", + "EventCode": "0x31", + "EventName": "UNC_UPI_RxL_BYPASSED.SLOT2", + "PerPkg": "1", + "PublicDescription": "Counts incoming FLITs (FLow control unITs) whcih bypassed the slot2 RxQ buffer (Receive Queue) and passed directly to the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of FLITs transfered, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", + "UMask": "0x4", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Valid data FLITs received from any slot", + "Counter": "0,1,2,3", + "EventCode": "0x3", + "EventName": "UNC_UPI_RxL_FLITS.ALL_DATA", + "PerPkg": "1", + "PublicDescription": "Counts valid data FLITs (80 bit FLow control unITs: 64bits of data) received from any of the 3 Intel Ultra Path Interconnect (UPI) Receive Queue slots on this UPI unit.", + "UMask": "0x0F", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Null FLITs received from any slot", + "Counter": "0,1,2,3", + "EventCode": "0x3", + "EventName": "UNC_UPI_RxL_FLITS.ALL_NULL", + "PerPkg": "1", + "PublicDescription": "Counts null FLITs (80 bit FLow control unITs) received from any of the 3 Intel Ultra Path Interconnect (UPI) Receive Queue slots on this UPI unit.", + "UMask": "0x27", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Protocol header and credit FLITs received from any slot", + "Counter": "0,1,2,3", + "EventCode": "0x3", + "EventName": "UNC_UPI_RxL_FLITS.NON_DATA", + "PerPkg": "1", + "PublicDescription": "Counts protocol header and credit FLITs (80 bit FLow control unITs) received from any of the 3 UPI slots on this UPI unit.", + "UMask": "0x97", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Cycles in which the Tx of the Intel Ultra Path Interconnect (UPI) is in L0p power mode", + "Counter": "0,1,2,3", + "EventCode": "0x27", + "EventName": "UNC_UPI_TxL0P_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts cycles when the transmit side (Tx) of the Intel Ultra Path Interconnect(UPI) is in L0p power mode. L0p is a mode where we disable 60% of the UPI lanes, decreasing our bandwidth in order to save power.", + "Unit": "UPI LL" + }, + { + "BriefDescription": "FLITs that bypassed the TxL Buffer", + "Counter": "0,1,2,3", + "EventCode": "0x41", + "EventName": "UNC_UPI_TxL_BYPASSED", + "PerPkg": "1", + "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the TxL(transmit) FLIT buffer and pass directly out the UPI Link. Generally, when data is transmitted across the Intel Ultra Path Interconnect (UPI), it will bypass the TxQ and pass directly to the link. However, the TxQ will be used in L0p (Low Power) mode and (Link Layer Retry) LLR mode, increasing latency to transfer out to the link.", + "Unit": "UPI LL" + }, + { + "BriefDescription": "UPI interconnect send bandwidth for payload. Derived from unc_upi_txl_flits.all_data", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UPI_DATA_BANDWIDTH_TX", + "PerPkg": "1", + "ScaleUnit": "7.11E-06Bytes", + "UMask": "0x0F", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Null FLITs transmitted from any slot", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_UPI_TxL_FLITS.ALL_NULL", + "PerPkg": "1", + "PublicDescription": "Counts null FLITs (80 bit FLow control unITs) transmitted via any of the 3 Intel Ulra Path Interconnect (UPI) slots on this UPI unit.", + "UMask": "0x27", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Idle FLITs transmitted", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_UPI_TxL_FLITS.IDLE", + "PerPkg": "1", + "PublicDescription": "Counts when the Intel Ultra Path Interconnect(UPI) transmits an idle FLIT(80 bit FLow control unITs). Every UPI cycle must be sending either data FLITs, protocol/credit FLITs or idle FLITs.", + "UMask": "0x47", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Protocol header and credit FLITs transmitted across any slot", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_UPI_TxL_FLITS.NON_DATA", + "PerPkg": "1", + "PublicDescription": "Counts protocol header and credit FLITs (80 bit FLow control unITs) transmitted across any of the 3 UPI (Ultra Path Interconnect) slots on this UPI unit.", + "UMask": "0x97", + "Unit": "UPI LL" + } +] diff --git a/tools/perf/pmu-events/arch/x86/skylakex/virtual-memory.json b/tools/perf/pmu-events/arch/x86/skylakex/virtual-memory.json new file mode 100644 index 000000000000..70750dab7ead --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/skylakex/virtual-memory.json @@ -0,0 +1,284 @@ +[ + { + "EventCode": "0x08", + "UMask": "0x1", + "BriefDescription": "Load misses in all DTLB levels that cause page walks", + "Counter": "0,1,2,3", + "EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK", + "PublicDescription": "Counts demand data loads that caused a page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels, but the walk need not have completed.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x08", + "UMask": "0x2", + "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes (4K).", + "Counter": "0,1,2,3", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts demand data loads that caused a completed page walk (4K page size). This implies it missed in all TLB levels. The page walk can end with or without a fault.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x08", + "UMask": "0x4", + "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes (2M/4M).", + "Counter": "0,1,2,3", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts demand data loads that caused a completed page walk (2M and 4M page sizes). This implies it missed in all TLB levels. The page walk can end with or without a fault.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x08", + "UMask": "0x8", + "BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (1G)", + "Counter": "0,1,2,3", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G", + "PublicDescription": "Counts load misses in all DTLB levels that cause a completed page walk (1G page size). The page walk can end with or without a fault.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x08", + "UMask": "0xe", + "BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (All page sizes)", + "Counter": "0,1,2,3", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts demand data loads that caused a completed page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x08", + "UMask": "0x10", + "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a load. EPT page walk duration are excluded in Skylake. ", + "Counter": "0,1,2,3", + "EventName": "DTLB_LOAD_MISSES.WALK_PENDING", + "PublicDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a load. EPT page walk duration are excluded in Skylake microarchitecture. ", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x08", + "UMask": "0x10", + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a load. EPT page walk duration are excluded in Skylake. ", + "Counter": "0,1,2,3", + "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE", + "CounterMask": "1", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a load.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x08", + "UMask": "0x20", + "BriefDescription": "Loads that miss the DTLB and hit the STLB.", + "Counter": "0,1,2,3", + "EventName": "DTLB_LOAD_MISSES.STLB_HIT", + "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x49", + "UMask": "0x1", + "BriefDescription": "Store misses in all DTLB levels that cause page walks", + "Counter": "0,1,2,3", + "EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK", + "PublicDescription": "Counts demand data stores that caused a page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels, but the walk need not have completed.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x49", + "UMask": "0x2", + "BriefDescription": "Store miss in all TLB levels causes a page walk that completes. (4K)", + "Counter": "0,1,2,3", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts demand data stores that caused a completed page walk (4K page size). This implies it missed in all TLB levels. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x49", + "UMask": "0x4", + "BriefDescription": "Store misses in all DTLB levels that cause completed page walks (2M/4M)", + "Counter": "0,1,2,3", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts demand data stores that caused a completed page walk (2M and 4M page sizes). This implies it missed in all TLB levels. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x49", + "UMask": "0x8", + "BriefDescription": "Store misses in all DTLB levels that cause completed page walks (1G)", + "Counter": "0,1,2,3", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G", + "PublicDescription": "Counts store misses in all DTLB levels that cause a completed page walk (1G page size). The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x49", + "UMask": "0xe", + "BriefDescription": "Store misses in all TLB levels causes a page walk that completes. (All page sizes)", + "Counter": "0,1,2,3", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts demand data stores that caused a completed page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x49", + "UMask": "0x10", + "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake. ", + "Counter": "0,1,2,3", + "EventName": "DTLB_STORE_MISSES.WALK_PENDING", + "PublicDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake microarchitecture. ", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x49", + "UMask": "0x10", + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a store. EPT page walk duration are excluded in Skylake. ", + "Counter": "0,1,2,3", + "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE", + "CounterMask": "1", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x49", + "UMask": "0x20", + "BriefDescription": "Stores that miss the DTLB and hit the STLB.", + "Counter": "0,1,2,3", + "EventName": "DTLB_STORE_MISSES.STLB_HIT", + "PublicDescription": "Stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x4F", + "UMask": "0x10", + "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a EPT (Extended Page Table) walk for any request type.", + "Counter": "0,1,2,3", + "EventName": "EPT.WALK_PENDING", + "PublicDescription": "Counts cycles for each PMH (Page Miss Handler) that is busy with an EPT (Extended Page Table) walk for any request type.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x85", + "UMask": "0x1", + "BriefDescription": "Misses at all ITLB levels that cause page walks", + "Counter": "0,1,2,3", + "EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK", + "PublicDescription": "Counts page walks of any page size (4K/2M/4M/1G) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB, but the walk need not have completed.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x85", + "UMask": "0x2", + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)", + "Counter": "0,1,2,3", + "EventName": "ITLB_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts completed page walks (4K page size) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x85", + "UMask": "0x4", + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)", + "Counter": "0,1,2,3", + "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts completed page walks of any page size (4K/2M/4M/1G) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x85", + "UMask": "0x8", + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (1G)", + "Counter": "0,1,2,3", + "EventName": "ITLB_MISSES.WALK_COMPLETED_1G", + "PublicDescription": "Counts store misses in all DTLB levels that cause a completed page walk (1G page size). The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x85", + "UMask": "0xe", + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (All page sizes)", + "Counter": "0,1,2,3", + "EventName": "ITLB_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts completed page walks (2M and 4M page sizes) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x85", + "UMask": "0x10", + "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake. ", + "Counter": "0,1,2,3", + "EventName": "ITLB_MISSES.WALK_PENDING", + "PublicDescription": "Counts 1 per cycle for each PMH (Page Miss Handler) that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake michroarchitecture. ", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x85", + "UMask": "0x10", + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request. EPT page walk duration are excluded in Skylake.", + "Counter": "0,1,2,3", + "EventName": "ITLB_MISSES.WALK_ACTIVE", + "CounterMask": "1", + "PublicDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request. EPT page walk duration are excluded in Skylake microarchitecture.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x85", + "UMask": "0x20", + "BriefDescription": "Instruction fetch requests that miss the ITLB and hit the STLB.", + "Counter": "0,1,2,3", + "EventName": "ITLB_MISSES.STLB_HIT", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xAE", + "UMask": "0x1", + "BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.", + "Counter": "0,1,2,3", + "EventName": "ITLB.ITLB_FLUSH", + "PublicDescription": "Counts the number of flushes of the big or small ITLB pages. Counting include both TLB Flush (covering all sets) and TLB Set Clear (set-specific).", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xBD", + "UMask": "0x1", + "BriefDescription": "DTLB flush attempts of the thread-specific entries", + "Counter": "0,1,2,3", + "EventName": "TLB_FLUSH.DTLB_THREAD", + "PublicDescription": "Counts the number of DTLB flush attempts of the thread-specific entries.", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xBD", + "UMask": "0x20", + "BriefDescription": "STLB flush attempts", + "Counter": "0,1,2,3", + "EventName": "TLB_FLUSH.STLB_ANY", + "PublicDescription": "Counts the number of any STLB flush attempts (such as entire, VPID, PCID, InvPage, CR3 write, etc.).", + "SampleAfterValue": "100007", + "CounterHTOff": "0,1,2,3,4,5,6,7" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index baa073f38334..d51dc9ca8861 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -48,10 +48,6 @@ #include "json.h" #include "jevents.h" -#ifndef __maybe_unused -#define __maybe_unused __attribute__((unused)) -#endif - int verbose; char *prog; @@ -141,6 +137,8 @@ static struct field { { "AnyThread", "any=" }, { "EdgeDetect", "edge=" }, { "SampleAfterValue", "period=" }, + { "FCMask", "fc_mask=" }, + { "PortMask", "ch_mask=" }, { NULL, NULL } }; @@ -826,10 +824,6 @@ static int process_one_file(const char *fpath, const struct stat *sb, * PMU event tables (see struct pmu_events_map). * * Write out the PMU events tables and the mapping table to pmu-event.c. - * - * If unable to process the JSON or arch files, create an empty mapping - * table so we can continue to build/use perf even if we cannot use the - * PMU event aliases. */ int main(int argc, char *argv[]) { @@ -840,6 +834,7 @@ int main(int argc, char *argv[]) const char *arch; const char *output_file; const char *start_dirname; + struct stat stbuf; prog = basename(argv[0]); if (argc < 4) { @@ -861,11 +856,17 @@ int main(int argc, char *argv[]) return 2; } + sprintf(ldirname, "%s/%s", start_dirname, arch); + + /* If architecture does not have any event lists, bail out */ + if (stat(ldirname, &stbuf) < 0) { + pr_info("%s: Arch %s has no PMU event lists\n", prog, arch); + goto empty_map; + } + /* Include pmu-events.h first */ fprintf(eventsfp, "#include \"../../pmu-events/pmu-events.h\"\n"); - sprintf(ldirname, "%s/%s", start_dirname, arch); - /* * The mapfile allows multiple CPUids to point to the same JSON file, * so, not sure if there is a need for symlinks within the pmu-events @@ -882,6 +883,9 @@ int main(int argc, char *argv[]) if (rc && verbose) { pr_info("%s: Error walking file tree %s\n", prog, ldirname); goto empty_map; + } else if (rc < 0) { + /* Make build fail */ + return 1; } else if (rc) { goto empty_map; } @@ -896,7 +900,8 @@ int main(int argc, char *argv[]) if (process_mapfile(eventsfp, mapfile)) { pr_info("%s: Error processing mapfile %s\n", prog, mapfile); - goto empty_map; + /* Make build fail */ + return 1; } return 0; diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py index 1d95009592eb..f6c84966e4f8 100644 --- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py +++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py @@ -57,6 +57,7 @@ try: 'ia64' : audit.MACH_IA64, 'ppc' : audit.MACH_PPC, 'ppc64' : audit.MACH_PPC64, + 'ppc64le' : audit.MACH_PPC64LE, 's390' : audit.MACH_S390, 's390x' : audit.MACH_S390X, 'i386' : audit.MACH_X86, diff --git a/tools/perf/scripts/python/bin/export-to-sqlite-record b/tools/perf/scripts/python/bin/export-to-sqlite-record new file mode 100644 index 000000000000..070204fd6d00 --- /dev/null +++ b/tools/perf/scripts/python/bin/export-to-sqlite-record @@ -0,0 +1,8 @@ +#!/bin/bash + +# +# export perf data to a sqlite3 database. Can cover +# perf ip samples (excluding the tracepoints). No special +# record requirements, just record what you want to export. +# +perf record $@ diff --git a/tools/perf/scripts/python/bin/export-to-sqlite-report b/tools/perf/scripts/python/bin/export-to-sqlite-report new file mode 100644 index 000000000000..5ff6033e70ba --- /dev/null +++ b/tools/perf/scripts/python/bin/export-to-sqlite-report @@ -0,0 +1,29 @@ +#!/bin/bash +# description: export perf data to a sqlite3 database +# args: [database name] [columns] [calls] +n_args=0 +for i in "$@" +do + if expr match "$i" "-" > /dev/null ; then + break + fi + n_args=$(( $n_args + 1 )) +done +if [ "$n_args" -gt 3 ] ; then + echo "usage: export-to-sqlite-report [database name] [columns] [calls]" + exit +fi +if [ "$n_args" -gt 2 ] ; then + dbname=$1 + columns=$2 + calls=$3 + shift 3 +elif [ "$n_args" -gt 1 ] ; then + dbname=$1 + columns=$2 + shift 2 +elif [ "$n_args" -gt 0 ] ; then + dbname=$1 + shift +fi +perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/export-to-sqlite.py $dbname $columns $calls diff --git a/tools/perf/scripts/python/bin/intel-pt-events-record b/tools/perf/scripts/python/bin/intel-pt-events-record new file mode 100644 index 000000000000..10fe2b6977d4 --- /dev/null +++ b/tools/perf/scripts/python/bin/intel-pt-events-record @@ -0,0 +1,13 @@ +#!/bin/bash + +# +# print Intel PT Power Events and PTWRITE. The intel_pt PMU event needs +# to be specified with appropriate config terms. +# +if ! echo "$@" | grep -q intel_pt ; then + echo "Options must include the Intel PT event e.g. -e intel_pt/pwr_evt,ptw/" + echo "and for power events it probably needs to be system wide i.e. -a option" + echo "For example: -a -e intel_pt/pwr_evt,branch=0/ sleep 1" + exit 1 +fi +perf record $@ diff --git a/tools/perf/scripts/python/bin/intel-pt-events-report b/tools/perf/scripts/python/bin/intel-pt-events-report new file mode 100644 index 000000000000..9a9c92fcd026 --- /dev/null +++ b/tools/perf/scripts/python/bin/intel-pt-events-report @@ -0,0 +1,3 @@ +#!/bin/bash +# description: print Intel PT Power Events and PTWRITE +perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/intel-pt-events.py
\ No newline at end of file diff --git a/tools/perf/scripts/python/call-graph-from-postgresql.py b/tools/perf/scripts/python/call-graph-from-sql.py index e78fdc2a5a9d..b494a67a1c67 100644 --- a/tools/perf/scripts/python/call-graph-from-postgresql.py +++ b/tools/perf/scripts/python/call-graph-from-sql.py @@ -1,6 +1,6 @@ #!/usr/bin/python2 -# call-graph-from-postgresql.py: create call-graph from postgresql database -# Copyright (c) 2014, Intel Corporation. +# call-graph-from-sql.py: create call-graph from sql database +# Copyright (c) 2014-2017, Intel Corporation. # # This program is free software; you can redistribute it and/or modify it # under the terms and conditions of the GNU General Public License, @@ -11,18 +11,19 @@ # FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for # more details. -# To use this script you will need to have exported data using the -# export-to-postgresql.py script. Refer to that script for details. +# To use this script you will need to have exported data using either the +# export-to-sqlite.py or the export-to-postgresql.py script. Refer to those +# scripts for details. # -# Following on from the example in the export-to-postgresql.py script, a +# Following on from the example in the export scripts, a # call-graph can be displayed for the pt_example database like this: # -# python tools/perf/scripts/python/call-graph-from-postgresql.py pt_example +# python tools/perf/scripts/python/call-graph-from-sql.py pt_example # -# Note this script supports connecting to remote databases by setting hostname, -# port, username, password, and dbname e.g. +# Note that for PostgreSQL, this script supports connecting to remote databases +# by setting hostname, port, username, password, and dbname e.g. # -# python tools/perf/scripts/python/call-graph-from-postgresql.py "hostname=myhost username=myuser password=mypassword dbname=pt_example" +# python tools/perf/scripts/python/call-graph-from-sql.py "hostname=myhost username=myuser password=mypassword dbname=pt_example" # # The result is a GUI window with a tree representing a context-sensitive # call-graph. Expanding a couple of levels of the tree and adjusting column @@ -160,7 +161,7 @@ class TreeItem(): '( SELECT short_name FROM dsos WHERE id = ( SELECT dso_id FROM symbols WHERE id = ( SELECT symbol_id FROM call_paths WHERE id = call_path_id ) ) ), ' '( SELECT ip FROM call_paths where id = call_path_id ) ' 'FROM calls WHERE parent_call_path_id = ' + str(self.call_path_id) + ' AND comm_id = ' + str(self.comm_id) + ' AND thread_id = ' + str(self.thread_id) + - 'ORDER BY call_path_id') + ' ORDER BY call_path_id') if not ret: raise Exception("Query failed: " + query.lastError().text()) last_call_path_id = 0 @@ -291,29 +292,40 @@ class MainWindow(QMainWindow): if __name__ == '__main__': if (len(sys.argv) < 2): - print >> sys.stderr, "Usage is: call-graph-from-postgresql.py <database name>" + print >> sys.stderr, "Usage is: call-graph-from-sql.py <database name>" raise Exception("Too few arguments") dbname = sys.argv[1] - db = QSqlDatabase.addDatabase('QPSQL') - - opts = dbname.split() - for opt in opts: - if '=' in opt: - opt = opt.split('=') - if opt[0] == 'hostname': - db.setHostName(opt[1]) - elif opt[0] == 'port': - db.setPort(int(opt[1])) - elif opt[0] == 'username': - db.setUserName(opt[1]) - elif opt[0] == 'password': - db.setPassword(opt[1]) - elif opt[0] == 'dbname': - dbname = opt[1] - else: - dbname = opt + is_sqlite3 = False + try: + f = open(dbname) + if f.read(15) == "SQLite format 3": + is_sqlite3 = True + f.close() + except: + pass + + if is_sqlite3: + db = QSqlDatabase.addDatabase('QSQLITE') + else: + db = QSqlDatabase.addDatabase('QPSQL') + opts = dbname.split() + for opt in opts: + if '=' in opt: + opt = opt.split('=') + if opt[0] == 'hostname': + db.setHostName(opt[1]) + elif opt[0] == 'port': + db.setPort(int(opt[1])) + elif opt[0] == 'username': + db.setUserName(opt[1]) + elif opt[0] == 'password': + db.setPassword(opt[1]) + elif opt[0] == 'dbname': + dbname = opt[1] + else: + dbname = opt db.setDatabaseName(dbname) if not db.open(): diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py index 7656ff8aa066..efcaf6cac2eb 100644 --- a/tools/perf/scripts/python/export-to-postgresql.py +++ b/tools/perf/scripts/python/export-to-postgresql.py @@ -59,7 +59,7 @@ import datetime # pt_example=# \q # # An example of using the database is provided by the script -# call-graph-from-postgresql.py. Refer to that script for details. +# call-graph-from-sql.py. Refer to that script for details. # # Tables: # @@ -340,7 +340,8 @@ if branches: 'to_sym_offset bigint,' 'to_ip bigint,' 'branch_type integer,' - 'in_tx boolean)') + 'in_tx boolean,' + 'call_path_id bigint)') else: do_query(query, 'CREATE TABLE samples (' 'id bigint NOT NULL,' diff --git a/tools/perf/scripts/python/export-to-sqlite.py b/tools/perf/scripts/python/export-to-sqlite.py new file mode 100644 index 000000000000..f827bf77e9d2 --- /dev/null +++ b/tools/perf/scripts/python/export-to-sqlite.py @@ -0,0 +1,451 @@ +# export-to-sqlite.py: export perf data to a sqlite3 database +# Copyright (c) 2017, Intel Corporation. +# +# This program is free software; you can redistribute it and/or modify it +# under the terms and conditions of the GNU General Public License, +# version 2, as published by the Free Software Foundation. +# +# This program is distributed in the hope it will be useful, but WITHOUT +# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or +# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for +# more details. + +import os +import sys +import struct +import datetime + +# To use this script you will need to have installed package python-pyside which +# provides LGPL-licensed Python bindings for Qt. You will also need the package +# libqt4-sql-sqlite for Qt sqlite3 support. +# +# An example of using this script with Intel PT: +# +# $ perf record -e intel_pt//u ls +# $ perf script -s ~/libexec/perf-core/scripts/python/export-to-sqlite.py pt_example branches calls +# 2017-07-31 14:26:07.326913 Creating database... +# 2017-07-31 14:26:07.538097 Writing records... +# 2017-07-31 14:26:09.889292 Adding indexes +# 2017-07-31 14:26:09.958746 Done +# +# To browse the database, sqlite3 can be used e.g. +# +# $ sqlite3 pt_example +# sqlite> .header on +# sqlite> select * from samples_view where id < 10; +# sqlite> .mode column +# sqlite> select * from samples_view where id < 10; +# sqlite> .tables +# sqlite> .schema samples_view +# sqlite> .quit +# +# An example of using the database is provided by the script +# call-graph-from-sql.py. Refer to that script for details. +# +# The database structure is practically the same as created by the script +# export-to-postgresql.py. Refer to that script for details. A notable +# difference is the 'transaction' column of the 'samples' table which is +# renamed 'transaction_' in sqlite because 'transaction' is a reserved word. + +from PySide.QtSql import * + +sys.path.append(os.environ['PERF_EXEC_PATH'] + \ + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') + +# These perf imports are not used at present +#from perf_trace_context import * +#from Core import * + +perf_db_export_mode = True +perf_db_export_calls = False +perf_db_export_callchains = False + +def usage(): + print >> sys.stderr, "Usage is: export-to-sqlite.py <database name> [<columns>] [<calls>] [<callchains>]" + print >> sys.stderr, "where: columns 'all' or 'branches'" + print >> sys.stderr, " calls 'calls' => create calls and call_paths table" + print >> sys.stderr, " callchains 'callchains' => create call_paths table" + raise Exception("Too few arguments") + +if (len(sys.argv) < 2): + usage() + +dbname = sys.argv[1] + +if (len(sys.argv) >= 3): + columns = sys.argv[2] +else: + columns = "all" + +if columns not in ("all", "branches"): + usage() + +branches = (columns == "branches") + +for i in range(3,len(sys.argv)): + if (sys.argv[i] == "calls"): + perf_db_export_calls = True + elif (sys.argv[i] == "callchains"): + perf_db_export_callchains = True + else: + usage() + +def do_query(q, s): + if (q.exec_(s)): + return + raise Exception("Query failed: " + q.lastError().text()) + +def do_query_(q): + if (q.exec_()): + return + raise Exception("Query failed: " + q.lastError().text()) + +print datetime.datetime.today(), "Creating database..." + +db_exists = False +try: + f = open(dbname) + f.close() + db_exists = True +except: + pass + +if db_exists: + raise Exception(dbname + " already exists") + +db = QSqlDatabase.addDatabase('QSQLITE') +db.setDatabaseName(dbname) +db.open() + +query = QSqlQuery(db) + +do_query(query, 'PRAGMA journal_mode = OFF') +do_query(query, 'BEGIN TRANSACTION') + +do_query(query, 'CREATE TABLE selected_events (' + 'id integer NOT NULL PRIMARY KEY,' + 'name varchar(80))') +do_query(query, 'CREATE TABLE machines (' + 'id integer NOT NULL PRIMARY KEY,' + 'pid integer,' + 'root_dir varchar(4096))') +do_query(query, 'CREATE TABLE threads (' + 'id integer NOT NULL PRIMARY KEY,' + 'machine_id bigint,' + 'process_id bigint,' + 'pid integer,' + 'tid integer)') +do_query(query, 'CREATE TABLE comms (' + 'id integer NOT NULL PRIMARY KEY,' + 'comm varchar(16))') +do_query(query, 'CREATE TABLE comm_threads (' + 'id integer NOT NULL PRIMARY KEY,' + 'comm_id bigint,' + 'thread_id bigint)') +do_query(query, 'CREATE TABLE dsos (' + 'id integer NOT NULL PRIMARY KEY,' + 'machine_id bigint,' + 'short_name varchar(256),' + 'long_name varchar(4096),' + 'build_id varchar(64))') +do_query(query, 'CREATE TABLE symbols (' + 'id integer NOT NULL PRIMARY KEY,' + 'dso_id bigint,' + 'sym_start bigint,' + 'sym_end bigint,' + 'binding integer,' + 'name varchar(2048))') +do_query(query, 'CREATE TABLE branch_types (' + 'id integer NOT NULL PRIMARY KEY,' + 'name varchar(80))') + +if branches: + do_query(query, 'CREATE TABLE samples (' + 'id integer NOT NULL PRIMARY KEY,' + 'evsel_id bigint,' + 'machine_id bigint,' + 'thread_id bigint,' + 'comm_id bigint,' + 'dso_id bigint,' + 'symbol_id bigint,' + 'sym_offset bigint,' + 'ip bigint,' + 'time bigint,' + 'cpu integer,' + 'to_dso_id bigint,' + 'to_symbol_id bigint,' + 'to_sym_offset bigint,' + 'to_ip bigint,' + 'branch_type integer,' + 'in_tx boolean,' + 'call_path_id bigint)') +else: + do_query(query, 'CREATE TABLE samples (' + 'id integer NOT NULL PRIMARY KEY,' + 'evsel_id bigint,' + 'machine_id bigint,' + 'thread_id bigint,' + 'comm_id bigint,' + 'dso_id bigint,' + 'symbol_id bigint,' + 'sym_offset bigint,' + 'ip bigint,' + 'time bigint,' + 'cpu integer,' + 'to_dso_id bigint,' + 'to_symbol_id bigint,' + 'to_sym_offset bigint,' + 'to_ip bigint,' + 'period bigint,' + 'weight bigint,' + 'transaction_ bigint,' + 'data_src bigint,' + 'branch_type integer,' + 'in_tx boolean,' + 'call_path_id bigint)') + +if perf_db_export_calls or perf_db_export_callchains: + do_query(query, 'CREATE TABLE call_paths (' + 'id integer NOT NULL PRIMARY KEY,' + 'parent_id bigint,' + 'symbol_id bigint,' + 'ip bigint)') +if perf_db_export_calls: + do_query(query, 'CREATE TABLE calls (' + 'id integer NOT NULL PRIMARY KEY,' + 'thread_id bigint,' + 'comm_id bigint,' + 'call_path_id bigint,' + 'call_time bigint,' + 'return_time bigint,' + 'branch_count bigint,' + 'call_id bigint,' + 'return_id bigint,' + 'parent_call_path_id bigint,' + 'flags integer)') + +# printf was added to sqlite in version 3.8.3 +sqlite_has_printf = False +try: + do_query(query, 'SELECT printf("") FROM machines') + sqlite_has_printf = True +except: + pass + +def emit_to_hex(x): + if sqlite_has_printf: + return 'printf("%x", ' + x + ')' + else: + return x + +do_query(query, 'CREATE VIEW machines_view AS ' + 'SELECT ' + 'id,' + 'pid,' + 'root_dir,' + 'CASE WHEN id=0 THEN \'unknown\' WHEN pid=-1 THEN \'host\' ELSE \'guest\' END AS host_or_guest' + ' FROM machines') + +do_query(query, 'CREATE VIEW dsos_view AS ' + 'SELECT ' + 'id,' + 'machine_id,' + '(SELECT host_or_guest FROM machines_view WHERE id = machine_id) AS host_or_guest,' + 'short_name,' + 'long_name,' + 'build_id' + ' FROM dsos') + +do_query(query, 'CREATE VIEW symbols_view AS ' + 'SELECT ' + 'id,' + 'name,' + '(SELECT short_name FROM dsos WHERE id=dso_id) AS dso,' + 'dso_id,' + 'sym_start,' + 'sym_end,' + 'CASE WHEN binding=0 THEN \'local\' WHEN binding=1 THEN \'global\' ELSE \'weak\' END AS binding' + ' FROM symbols') + +do_query(query, 'CREATE VIEW threads_view AS ' + 'SELECT ' + 'id,' + 'machine_id,' + '(SELECT host_or_guest FROM machines_view WHERE id = machine_id) AS host_or_guest,' + 'process_id,' + 'pid,' + 'tid' + ' FROM threads') + +do_query(query, 'CREATE VIEW comm_threads_view AS ' + 'SELECT ' + 'comm_id,' + '(SELECT comm FROM comms WHERE id = comm_id) AS command,' + 'thread_id,' + '(SELECT pid FROM threads WHERE id = thread_id) AS pid,' + '(SELECT tid FROM threads WHERE id = thread_id) AS tid' + ' FROM comm_threads') + +if perf_db_export_calls or perf_db_export_callchains: + do_query(query, 'CREATE VIEW call_paths_view AS ' + 'SELECT ' + 'c.id,' + + emit_to_hex('c.ip') + ' AS ip,' + 'c.symbol_id,' + '(SELECT name FROM symbols WHERE id = c.symbol_id) AS symbol,' + '(SELECT dso_id FROM symbols WHERE id = c.symbol_id) AS dso_id,' + '(SELECT dso FROM symbols_view WHERE id = c.symbol_id) AS dso_short_name,' + 'c.parent_id,' + + emit_to_hex('p.ip') + ' AS parent_ip,' + 'p.symbol_id AS parent_symbol_id,' + '(SELECT name FROM symbols WHERE id = p.symbol_id) AS parent_symbol,' + '(SELECT dso_id FROM symbols WHERE id = p.symbol_id) AS parent_dso_id,' + '(SELECT dso FROM symbols_view WHERE id = p.symbol_id) AS parent_dso_short_name' + ' FROM call_paths c INNER JOIN call_paths p ON p.id = c.parent_id') +if perf_db_export_calls: + do_query(query, 'CREATE VIEW calls_view AS ' + 'SELECT ' + 'calls.id,' + 'thread_id,' + '(SELECT pid FROM threads WHERE id = thread_id) AS pid,' + '(SELECT tid FROM threads WHERE id = thread_id) AS tid,' + '(SELECT comm FROM comms WHERE id = comm_id) AS command,' + 'call_path_id,' + + emit_to_hex('ip') + ' AS ip,' + 'symbol_id,' + '(SELECT name FROM symbols WHERE id = symbol_id) AS symbol,' + 'call_time,' + 'return_time,' + 'return_time - call_time AS elapsed_time,' + 'branch_count,' + 'call_id,' + 'return_id,' + 'CASE WHEN flags=1 THEN \'no call\' WHEN flags=2 THEN \'no return\' WHEN flags=3 THEN \'no call/return\' ELSE \'\' END AS flags,' + 'parent_call_path_id' + ' FROM calls INNER JOIN call_paths ON call_paths.id = call_path_id') + +do_query(query, 'CREATE VIEW samples_view AS ' + 'SELECT ' + 'id,' + 'time,' + 'cpu,' + '(SELECT pid FROM threads WHERE id = thread_id) AS pid,' + '(SELECT tid FROM threads WHERE id = thread_id) AS tid,' + '(SELECT comm FROM comms WHERE id = comm_id) AS command,' + '(SELECT name FROM selected_events WHERE id = evsel_id) AS event,' + + emit_to_hex('ip') + ' AS ip_hex,' + '(SELECT name FROM symbols WHERE id = symbol_id) AS symbol,' + 'sym_offset,' + '(SELECT short_name FROM dsos WHERE id = dso_id) AS dso_short_name,' + + emit_to_hex('to_ip') + ' AS to_ip_hex,' + '(SELECT name FROM symbols WHERE id = to_symbol_id) AS to_symbol,' + 'to_sym_offset,' + '(SELECT short_name FROM dsos WHERE id = to_dso_id) AS to_dso_short_name,' + '(SELECT name FROM branch_types WHERE id = branch_type) AS branch_type_name,' + 'in_tx' + ' FROM samples') + +do_query(query, 'END TRANSACTION') + +evsel_query = QSqlQuery(db) +evsel_query.prepare("INSERT INTO selected_events VALUES (?, ?)") +machine_query = QSqlQuery(db) +machine_query.prepare("INSERT INTO machines VALUES (?, ?, ?)") +thread_query = QSqlQuery(db) +thread_query.prepare("INSERT INTO threads VALUES (?, ?, ?, ?, ?)") +comm_query = QSqlQuery(db) +comm_query.prepare("INSERT INTO comms VALUES (?, ?)") +comm_thread_query = QSqlQuery(db) +comm_thread_query.prepare("INSERT INTO comm_threads VALUES (?, ?, ?)") +dso_query = QSqlQuery(db) +dso_query.prepare("INSERT INTO dsos VALUES (?, ?, ?, ?, ?)") +symbol_query = QSqlQuery(db) +symbol_query.prepare("INSERT INTO symbols VALUES (?, ?, ?, ?, ?, ?)") +branch_type_query = QSqlQuery(db) +branch_type_query.prepare("INSERT INTO branch_types VALUES (?, ?)") +sample_query = QSqlQuery(db) +if branches: + sample_query.prepare("INSERT INTO samples VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)") +else: + sample_query.prepare("INSERT INTO samples VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)") +if perf_db_export_calls or perf_db_export_callchains: + call_path_query = QSqlQuery(db) + call_path_query.prepare("INSERT INTO call_paths VALUES (?, ?, ?, ?)") +if perf_db_export_calls: + call_query = QSqlQuery(db) + call_query.prepare("INSERT INTO calls VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)") + +def trace_begin(): + print datetime.datetime.today(), "Writing records..." + do_query(query, 'BEGIN TRANSACTION') + # id == 0 means unknown. It is easier to create records for them than replace the zeroes with NULLs + evsel_table(0, "unknown") + machine_table(0, 0, "unknown") + thread_table(0, 0, 0, -1, -1) + comm_table(0, "unknown") + dso_table(0, 0, "unknown", "unknown", "") + symbol_table(0, 0, 0, 0, 0, "unknown") + sample_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) + if perf_db_export_calls or perf_db_export_callchains: + call_path_table(0, 0, 0, 0) + +unhandled_count = 0 + +def trace_end(): + do_query(query, 'END TRANSACTION') + + print datetime.datetime.today(), "Adding indexes" + if perf_db_export_calls: + do_query(query, 'CREATE INDEX pcpid_idx ON calls (parent_call_path_id)') + + if (unhandled_count): + print datetime.datetime.today(), "Warning: ", unhandled_count, " unhandled events" + print datetime.datetime.today(), "Done" + +def trace_unhandled(event_name, context, event_fields_dict): + global unhandled_count + unhandled_count += 1 + +def sched__sched_switch(*x): + pass + +def bind_exec(q, n, x): + for xx in x[0:n]: + q.addBindValue(str(xx)) + do_query_(q) + +def evsel_table(*x): + bind_exec(evsel_query, 2, x) + +def machine_table(*x): + bind_exec(machine_query, 3, x) + +def thread_table(*x): + bind_exec(thread_query, 5, x) + +def comm_table(*x): + bind_exec(comm_query, 2, x) + +def comm_thread_table(*x): + bind_exec(comm_thread_query, 3, x) + +def dso_table(*x): + bind_exec(dso_query, 5, x) + +def symbol_table(*x): + bind_exec(symbol_query, 6, x) + +def branch_type_table(*x): + bind_exec(branch_type_query, 2, x) + +def sample_table(*x): + if branches: + bind_exec(sample_query, 18, x) + else: + bind_exec(sample_query, 22, x) + +def call_path_table(*x): + bind_exec(call_path_query, 4, x) + +def call_return_table(*x): + bind_exec(call_query, 11, x) diff --git a/tools/perf/scripts/python/intel-pt-events.py b/tools/perf/scripts/python/intel-pt-events.py new file mode 100644 index 000000000000..b19172d673af --- /dev/null +++ b/tools/perf/scripts/python/intel-pt-events.py @@ -0,0 +1,128 @@ +# intel-pt-events.py: Print Intel PT Power Events and PTWRITE +# Copyright (c) 2017, Intel Corporation. +# +# This program is free software; you can redistribute it and/or modify it +# under the terms and conditions of the GNU General Public License, +# version 2, as published by the Free Software Foundation. +# +# This program is distributed in the hope it will be useful, but WITHOUT +# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or +# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for +# more details. + +import os +import sys +import struct + +sys.path.append(os.environ['PERF_EXEC_PATH'] + \ + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') + +# These perf imports are not used at present +#from perf_trace_context import * +#from Core import * + +def trace_begin(): + print "Intel PT Power Events and PTWRITE" + +def trace_end(): + print "End" + +def trace_unhandled(event_name, context, event_fields_dict): + print ' '.join(['%s=%s'%(k,str(v))for k,v in sorted(event_fields_dict.items())]) + +def print_ptwrite(raw_buf): + data = struct.unpack_from("<IQ", raw_buf) + flags = data[0] + payload = data[1] + exact_ip = flags & 1 + print "IP: %u payload: %#x" % (exact_ip, payload), + +def print_cbr(raw_buf): + data = struct.unpack_from("<BBBBII", raw_buf) + cbr = data[0] + f = (data[4] + 500) / 1000 + p = ((cbr * 1000 / data[2]) + 5) / 10 + print "%3u freq: %4u MHz (%3u%%)" % (cbr, f, p), + +def print_mwait(raw_buf): + data = struct.unpack_from("<IQ", raw_buf) + payload = data[1] + hints = payload & 0xff + extensions = (payload >> 32) & 0x3 + print "hints: %#x extensions: %#x" % (hints, extensions), + +def print_pwre(raw_buf): + data = struct.unpack_from("<IQ", raw_buf) + payload = data[1] + hw = (payload >> 7) & 1 + cstate = (payload >> 12) & 0xf + subcstate = (payload >> 8) & 0xf + print "hw: %u cstate: %u sub-cstate: %u" % (hw, cstate, subcstate), + +def print_exstop(raw_buf): + data = struct.unpack_from("<I", raw_buf) + flags = data[0] + exact_ip = flags & 1 + print "IP: %u" % (exact_ip), + +def print_pwrx(raw_buf): + data = struct.unpack_from("<IQ", raw_buf) + payload = data[1] + deepest_cstate = payload & 0xf + last_cstate = (payload >> 4) & 0xf + wake_reason = (payload >> 8) & 0xf + print "deepest cstate: %u last cstate: %u wake reason: %#x" % (deepest_cstate, last_cstate, wake_reason), + +def print_common_start(comm, sample, name): + ts = sample["time"] + cpu = sample["cpu"] + pid = sample["pid"] + tid = sample["tid"] + print "%16s %5u/%-5u [%03u] %9u.%09u %7s:" % (comm, pid, tid, cpu, ts / 1000000000, ts %1000000000, name), + +def print_common_ip(sample, symbol, dso): + ip = sample["ip"] + print "%16x %s (%s)" % (ip, symbol, dso) + +def process_event(param_dict): + event_attr = param_dict["attr"] + sample = param_dict["sample"] + raw_buf = param_dict["raw_buf"] + comm = param_dict["comm"] + name = param_dict["ev_name"] + + # Symbol and dso info are not always resolved + if (param_dict.has_key("dso")): + dso = param_dict["dso"] + else: + dso = "[unknown]" + + if (param_dict.has_key("symbol")): + symbol = param_dict["symbol"] + else: + symbol = "[unknown]" + + if name == "ptwrite": + print_common_start(comm, sample, name) + print_ptwrite(raw_buf) + print_common_ip(sample, symbol, dso) + elif name == "cbr": + print_common_start(comm, sample, name) + print_cbr(raw_buf) + print_common_ip(sample, symbol, dso) + elif name == "mwait": + print_common_start(comm, sample, name) + print_mwait(raw_buf) + print_common_ip(sample, symbol, dso) + elif name == "pwre": + print_common_start(comm, sample, name) + print_pwre(raw_buf) + print_common_ip(sample, symbol, dso) + elif name == "exstop": + print_common_start(comm, sample, name) + print_exstop(raw_buf) + print_common_ip(sample, symbol, dso) + elif name == "pwrx": + print_common_start(comm, sample, name) + print_pwrx(raw_buf) + print_common_ip(sample, symbol, dso) diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build index 84222bdb8689..87bf3edb037c 100644 --- a/tools/perf/tests/Build +++ b/tools/perf/tests/Build @@ -34,6 +34,7 @@ perf-y += thread-map.o perf-y += llvm.o llvm-src-base.o llvm-src-kbuild.o llvm-src-prologue.o llvm-src-relocation.o perf-y += bpf.o perf-y += topology.o +perf-y += mem.o perf-y += cpumap.o perf-y += stat.o perf-y += event_update.o diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c index 0dd77494bb58..c9aafed7da15 100644 --- a/tools/perf/tests/attr.c +++ b/tools/perf/tests/attr.c @@ -18,6 +18,7 @@ * permissions. All the event text files are stored there. */ +#include <debug.h> #include <errno.h> #include <inttypes.h> #include <stdlib.h> @@ -29,15 +30,13 @@ #include <sys/stat.h> #include <unistd.h> #include "../perf.h" -#include "util.h" #include <subcmd/exec-cmd.h> #include "tests.h" #define ENV "PERF_TEST_ATTR" -extern int verbose; - static char *dir; +static bool ready; void test_attr__init(void) { @@ -69,6 +68,9 @@ static int store_event(struct perf_event_attr *attr, pid_t pid, int cpu, FILE *file; char path[PATH_MAX]; + if (!ready) + return 0; + snprintf(path, PATH_MAX, "%s/event-%d-%llu-%d", dir, attr->type, attr->config, fd); @@ -138,12 +140,20 @@ void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu, { int errno_saved = errno; - if (store_event(attr, pid, cpu, fd, group_fd, flags)) - die("test attr FAILED"); + if ((fd != -1) && store_event(attr, pid, cpu, fd, group_fd, flags)) { + pr_err("test attr FAILED"); + exit(128); + } errno = errno_saved; } +void test_attr__ready(void) +{ + if (unlikely(test_attr__enabled) && !ready) + ready = true; +} + static int run_dir(const char *d, const char *perf) { char v[] = "-vvvvv"; @@ -159,7 +169,7 @@ static int run_dir(const char *d, const char *perf) return system(cmd); } -int test__attr(int subtest __maybe_unused) +int test__attr(struct test *test __maybe_unused, int subtest __maybe_unused) { struct stat st; char path_perf[PATH_MAX]; diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/attr.py index 1091bd47adfd..6bb50e82a3e3 100644 --- a/tools/perf/tests/attr.py +++ b/tools/perf/tests/attr.py @@ -9,6 +9,20 @@ import logging import shutil import ConfigParser +def data_equal(a, b): + # Allow multiple values in assignment separated by '|' + a_list = a.split('|') + b_list = b.split('|') + + for a_item in a_list: + for b_item in b_list: + if (a_item == b_item): + return True + elif (a_item == '*') or (b_item == '*'): + return True + + return False + class Fail(Exception): def __init__(self, test, msg): self.msg = msg @@ -16,6 +30,13 @@ class Fail(Exception): def getMsg(self): return '\'%s\' - %s' % (self.test.path, self.msg) +class Notest(Exception): + def __init__(self, test, arch): + self.arch = arch + self.test = test + def getMsg(self): + return '[%s] \'%s\'' % (self.arch, self.test.path) + class Unsup(Exception): def __init__(self, test): self.test = test @@ -75,34 +96,25 @@ class Event(dict): self.add(base) self.add(data) - def compare_data(self, a, b): - # Allow multiple values in assignment separated by '|' - a_list = a.split('|') - b_list = b.split('|') - - for a_item in a_list: - for b_item in b_list: - if (a_item == b_item): - return True - elif (a_item == '*') or (b_item == '*'): - return True - - return False - def equal(self, other): for t in Event.terms: log.debug(" [%s] %s %s" % (t, self[t], other[t])); if not self.has_key(t) or not other.has_key(t): return False - if not self.compare_data(self[t], other[t]): + if not data_equal(self[t], other[t]): return False return True + def optional(self): + if self.has_key('optional') and self['optional'] == '1': + return True + return False + def diff(self, other): for t in Event.terms: if not self.has_key(t) or not other.has_key(t): continue - if not self.compare_data(self[t], other[t]): + if not data_equal(self[t], other[t]): log.warning("expected %s=%s, got %s" % (t, self[t], other[t])) # Test file description needs to have following sections: @@ -112,6 +124,9 @@ class Event(dict): # 'command' - perf command name # 'args' - special command arguments # 'ret' - expected command return value (0 by default) +# 'arch' - architecture specific test (optional) +# comma separated list, ! at the beginning +# negates it. # # [eventX:base] # - one or multiple instances in file @@ -134,6 +149,12 @@ class Test(object): except: self.ret = 0 + try: + self.arch = parser.get('config', 'arch') + log.warning("test limitation '%s'" % self.arch) + except: + self.arch = '' + self.expect = {} self.result = {} log.debug(" loading expected events"); @@ -145,6 +166,31 @@ class Test(object): else: return True + def skip_test(self, myarch): + # If architecture not set always run test + if self.arch == '': + # log.warning("test for arch %s is ok" % myarch) + return False + + # Allow multiple values in assignment separated by ',' + arch_list = self.arch.split(',') + + # Handle negated list such as !s390x,ppc + if arch_list[0][0] == '!': + arch_list[0] = arch_list[0][1:] + log.warning("excluded architecture list %s" % arch_list) + for arch_item in arch_list: + # log.warning("test for %s arch is %s" % (arch_item, myarch)) + if arch_item == myarch: + return True + return False + + for arch_item in arch_list: + # log.warning("test for architecture '%s' current '%s'" % (arch_item, myarch)) + if arch_item == myarch: + return False + return True + def load_events(self, path, events): parser_event = ConfigParser.SafeConfigParser() parser_event.read(path) @@ -168,13 +214,18 @@ class Test(object): events[section] = e def run_cmd(self, tempdir): + junk1, junk2, junk3, junk4, myarch = (os.uname()) + + if self.skip_test(myarch): + raise Notest(self, myarch) + cmd = "PERF_TEST_ATTR=%s %s %s -o %s/perf.data %s" % (tempdir, self.perf, self.command, tempdir, self.args) ret = os.WEXITSTATUS(os.system(cmd)) - log.info(" '%s' ret %d " % (cmd, ret)) + log.info(" '%s' ret '%s', expected '%s'" % (cmd, str(ret), str(self.ret))) - if ret != int(self.ret): + if not data_equal(str(ret), str(self.ret)): raise Unsup(self) def compare(self, expect, result): @@ -198,9 +249,12 @@ class Test(object): log.debug(" match: [%s] matches %s" % (exp_name, str(exp_list))) # we did not any matching event - fail - if (not exp_list): - exp_event.diff(res_event) - raise Fail(self, 'match failure'); + if not exp_list: + if exp_event.optional(): + log.debug(" %s does not match, but is optional" % exp_name) + else: + exp_event.diff(res_event) + raise Fail(self, 'match failure'); match[exp_name] = exp_list @@ -265,6 +319,8 @@ def run_tests(options): Test(f, options).run() except Unsup, obj: log.warning("unsupp %s" % obj.getMsg()) + except Notest, obj: + log.warning("skipped %s" % obj.getMsg()) def setup_log(verbose): global log diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/attr/base-record index 7e6d74946e04..31e0b1da830b 100644 --- a/tools/perf/tests/attr/base-record +++ b/tools/perf/tests/attr/base-record @@ -7,7 +7,7 @@ cpu=* type=0|1 size=112 config=0 -sample_period=4000 +sample_period=* sample_type=263 read_format=0 disabled=1 @@ -15,7 +15,7 @@ inherit=1 pinned=0 exclusive=0 exclude_user=0 -exclude_kernel=0 +exclude_kernel=0|1 exclude_hv=0 exclude_idle=0 mmap=1 @@ -25,7 +25,7 @@ inherit_stat=0 enable_on_exec=1 task=0 watermark=0 -precise_ip=0 +precise_ip=0|1|2|3 mmap_data=0 sample_id_all=1 exclude_host=0|1 diff --git a/tools/perf/tests/attr/base-stat b/tools/perf/tests/attr/base-stat index f4cf148f14cb..4d0c2e42b64e 100644 --- a/tools/perf/tests/attr/base-stat +++ b/tools/perf/tests/attr/base-stat @@ -8,14 +8,14 @@ type=0 size=112 config=0 sample_period=0 -sample_type=0 +sample_type=65536 read_format=3 disabled=1 inherit=1 pinned=0 exclusive=0 exclude_user=0 -exclude_kernel=0 +exclude_kernel=0|1 exclude_hv=0 exclude_idle=0 mmap=0 diff --git a/tools/perf/tests/attr/test-record-C0 b/tools/perf/tests/attr/test-record-C0 index d6a7e43f61b3..cb0a3138fa54 100644 --- a/tools/perf/tests/attr/test-record-C0 +++ b/tools/perf/tests/attr/test-record-C0 @@ -1,6 +1,7 @@ [config] command = record args = -C 0 kill >/dev/null 2>&1 +ret = 1 [event:base-record] cpu=0 diff --git a/tools/perf/tests/attr/test-record-basic b/tools/perf/tests/attr/test-record-basic index 55c0428370ca..85a23cf35ba1 100644 --- a/tools/perf/tests/attr/test-record-basic +++ b/tools/perf/tests/attr/test-record-basic @@ -1,5 +1,6 @@ [config] command = record args = kill >/dev/null 2>&1 +ret = 1 [event:base-record] diff --git a/tools/perf/tests/attr/test-record-branch-any b/tools/perf/tests/attr/test-record-branch-any index 1421960ed4e9..81f839e2fad0 100644 --- a/tools/perf/tests/attr/test-record-branch-any +++ b/tools/perf/tests/attr/test-record-branch-any @@ -1,8 +1,8 @@ [config] command = record args = -b kill >/dev/null 2>&1 +ret = 1 [event:base-record] -sample_period=4000 sample_type=2311 branch_sample_type=8 diff --git a/tools/perf/tests/attr/test-record-branch-filter-any b/tools/perf/tests/attr/test-record-branch-filter-any index 915c4df0e0c2..357421f4dfce 100644 --- a/tools/perf/tests/attr/test-record-branch-filter-any +++ b/tools/perf/tests/attr/test-record-branch-filter-any @@ -1,8 +1,8 @@ [config] command = record args = -j any kill >/dev/null 2>&1 +ret = 1 [event:base-record] -sample_period=4000 sample_type=2311 branch_sample_type=8 diff --git a/tools/perf/tests/attr/test-record-branch-filter-any_call b/tools/perf/tests/attr/test-record-branch-filter-any_call index 8708dbd4f373..dbc55f2ab845 100644 --- a/tools/perf/tests/attr/test-record-branch-filter-any_call +++ b/tools/perf/tests/attr/test-record-branch-filter-any_call @@ -1,8 +1,8 @@ [config] command = record args = -j any_call kill >/dev/null 2>&1 +ret = 1 [event:base-record] -sample_period=4000 sample_type=2311 branch_sample_type=16 diff --git a/tools/perf/tests/attr/test-record-branch-filter-any_ret b/tools/perf/tests/attr/test-record-branch-filter-any_ret index 0d3607a6dcbe..a0824ff8e131 100644 --- a/tools/perf/tests/attr/test-record-branch-filter-any_ret +++ b/tools/perf/tests/attr/test-record-branch-filter-any_ret @@ -1,8 +1,8 @@ [config] command = record args = -j any_ret kill >/dev/null 2>&1 +ret = 1 [event:base-record] -sample_period=4000 sample_type=2311 branch_sample_type=32 diff --git a/tools/perf/tests/attr/test-record-branch-filter-hv b/tools/perf/tests/attr/test-record-branch-filter-hv index f25526740cec..f34d6f120181 100644 --- a/tools/perf/tests/attr/test-record-branch-filter-hv +++ b/tools/perf/tests/attr/test-record-branch-filter-hv @@ -1,8 +1,8 @@ [config] command = record args = -j hv kill >/dev/null 2>&1 +ret = 1 [event:base-record] -sample_period=4000 sample_type=2311 branch_sample_type=8 diff --git a/tools/perf/tests/attr/test-record-branch-filter-ind_call b/tools/perf/tests/attr/test-record-branch-filter-ind_call index e862dd179128..b86a35232248 100644 --- a/tools/perf/tests/attr/test-record-branch-filter-ind_call +++ b/tools/perf/tests/attr/test-record-branch-filter-ind_call @@ -1,8 +1,8 @@ [config] command = record args = -j ind_call kill >/dev/null 2>&1 +ret = 1 [event:base-record] -sample_period=4000 sample_type=2311 branch_sample_type=64 diff --git a/tools/perf/tests/attr/test-record-branch-filter-k b/tools/perf/tests/attr/test-record-branch-filter-k index 182971e898f5..d3fbc5e1858a 100644 --- a/tools/perf/tests/attr/test-record-branch-filter-k +++ b/tools/perf/tests/attr/test-record-branch-filter-k @@ -1,8 +1,8 @@ [config] command = record args = -j k kill >/dev/null 2>&1 +ret = 1 [event:base-record] -sample_period=4000 sample_type=2311 branch_sample_type=8 diff --git a/tools/perf/tests/attr/test-record-branch-filter-u b/tools/perf/tests/attr/test-record-branch-filter-u index 83449ef9e687..a318f0dda173 100644 --- a/tools/perf/tests/attr/test-record-branch-filter-u +++ b/tools/perf/tests/attr/test-record-branch-filter-u @@ -1,8 +1,8 @@ [config] command = record args = -j u kill >/dev/null 2>&1 +ret = 1 [event:base-record] -sample_period=4000 sample_type=2311 branch_sample_type=8 diff --git a/tools/perf/tests/attr/test-record-count b/tools/perf/tests/attr/test-record-count index 2f841de56f6b..34f6cc577263 100644 --- a/tools/perf/tests/attr/test-record-count +++ b/tools/perf/tests/attr/test-record-count @@ -1,6 +1,7 @@ [config] command = record args = -c 123 kill >/dev/null 2>&1 +ret = 1 [event:base-record] sample_period=123 diff --git a/tools/perf/tests/attr/test-record-data b/tools/perf/tests/attr/test-record-data index 716e143b5291..a9cf2233b0ce 100644 --- a/tools/perf/tests/attr/test-record-data +++ b/tools/perf/tests/attr/test-record-data @@ -1,10 +1,9 @@ [config] command = record args = -d kill >/dev/null 2>&1 +ret = 1 [event:base-record] -sample_period=4000 - # sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_TIME | # PERF_SAMPLE_ADDR | PERF_SAMPLE_PERIOD | PERF_SAMPLE_DATA_SRC sample_type=33039 diff --git a/tools/perf/tests/attr/test-record-freq b/tools/perf/tests/attr/test-record-freq index 600d0f8f2583..bf4cb459f0d5 100644 --- a/tools/perf/tests/attr/test-record-freq +++ b/tools/perf/tests/attr/test-record-freq @@ -1,6 +1,7 @@ [config] command = record args = -F 100 kill >/dev/null 2>&1 +ret = 1 [event:base-record] sample_period=100 diff --git a/tools/perf/tests/attr/test-record-graph-default b/tools/perf/tests/attr/test-record-graph-default index 853597a9a8f6..0b216e69760c 100644 --- a/tools/perf/tests/attr/test-record-graph-default +++ b/tools/perf/tests/attr/test-record-graph-default @@ -1,6 +1,7 @@ [config] command = record args = -g kill >/dev/null 2>&1 +ret = 1 [event:base-record] sample_type=295 diff --git a/tools/perf/tests/attr/test-record-graph-dwarf b/tools/perf/tests/attr/test-record-graph-dwarf index d6f324ea578c..da2fa73bd0a2 100644 --- a/tools/perf/tests/attr/test-record-graph-dwarf +++ b/tools/perf/tests/attr/test-record-graph-dwarf @@ -1,10 +1,12 @@ [config] command = record args = --call-graph dwarf -- kill >/dev/null 2>&1 +ret = 1 [event:base-record] -sample_type=12583 +sample_type=45359 exclude_callchain_user=1 sample_stack_user=8192 # TODO different for each arch, no support for that now sample_regs_user=* +mmap_data=1 diff --git a/tools/perf/tests/attr/test-record-graph-fp b/tools/perf/tests/attr/test-record-graph-fp index 055e3bee7993..625d190bb798 100644 --- a/tools/perf/tests/attr/test-record-graph-fp +++ b/tools/perf/tests/attr/test-record-graph-fp @@ -1,6 +1,7 @@ [config] command = record args = --call-graph fp kill >/dev/null 2>&1 +ret = 1 [event:base-record] sample_type=295 diff --git a/tools/perf/tests/attr/test-record-group b/tools/perf/tests/attr/test-record-group index 57739cacdb2a..6e7961f6f7a5 100644 --- a/tools/perf/tests/attr/test-record-group +++ b/tools/perf/tests/attr/test-record-group @@ -1,6 +1,7 @@ [config] command = record args = --group -e cycles,instructions kill >/dev/null 2>&1 +ret = 1 [event-1:base-record] fd=1 diff --git a/tools/perf/tests/attr/test-record-group-sampling b/tools/perf/tests/attr/test-record-group-sampling index 658f5d60c873..ef59afd6d635 100644 --- a/tools/perf/tests/attr/test-record-group-sampling +++ b/tools/perf/tests/attr/test-record-group-sampling @@ -1,6 +1,7 @@ [config] command = record args = -e '{cycles,cache-misses}:S' kill >/dev/null 2>&1 +ret = 1 [event-1:base-record] fd=1 diff --git a/tools/perf/tests/attr/test-record-group1 b/tools/perf/tests/attr/test-record-group1 index c5548d054aff..87a222d014d8 100644 --- a/tools/perf/tests/attr/test-record-group1 +++ b/tools/perf/tests/attr/test-record-group1 @@ -1,6 +1,7 @@ [config] command = record args = -e '{cycles,instructions}' kill >/dev/null 2>&1 +ret = 1 [event-1:base-record] fd=1 diff --git a/tools/perf/tests/attr/test-record-no-delay b/tools/perf/tests/attr/test-record-no-buffering index f253b78cdbf2..aa3956d8fe20 100644 --- a/tools/perf/tests/attr/test-record-no-delay +++ b/tools/perf/tests/attr/test-record-no-buffering @@ -1,9 +1,9 @@ [config] command = record -args = -D kill >/dev/null 2>&1 +args = --no-buffering kill >/dev/null 2>&1 +ret = 1 [event:base-record] -sample_period=4000 sample_type=263 watermark=0 wakeup_events=1 diff --git a/tools/perf/tests/attr/test-record-no-inherit b/tools/perf/tests/attr/test-record-no-inherit index 44edcb2edcd5..560943decb87 100644 --- a/tools/perf/tests/attr/test-record-no-inherit +++ b/tools/perf/tests/attr/test-record-no-inherit @@ -1,6 +1,7 @@ [config] command = record args = -i kill >/dev/null 2>&1 +ret = 1 [event:base-record] sample_type=263 diff --git a/tools/perf/tests/attr/test-record-no-samples b/tools/perf/tests/attr/test-record-no-samples index d0141b2418b5..8eb73ab639e0 100644 --- a/tools/perf/tests/attr/test-record-no-samples +++ b/tools/perf/tests/attr/test-record-no-samples @@ -1,6 +1,7 @@ [config] command = record args = -n kill >/dev/null 2>&1 +ret = 1 [event:base-record] sample_period=0 diff --git a/tools/perf/tests/attr/test-record-period b/tools/perf/tests/attr/test-record-period index 8abc5314fc52..69bc748f0f27 100644 --- a/tools/perf/tests/attr/test-record-period +++ b/tools/perf/tests/attr/test-record-period @@ -1,6 +1,7 @@ [config] command = record args = -c 100 -P kill >/dev/null 2>&1 +ret = 1 [event:base-record] sample_period=100 diff --git a/tools/perf/tests/attr/test-record-raw b/tools/perf/tests/attr/test-record-raw index 4a8ef25b5f49..a188a614a44c 100644 --- a/tools/perf/tests/attr/test-record-raw +++ b/tools/perf/tests/attr/test-record-raw @@ -1,7 +1,7 @@ [config] command = record args = -R kill >/dev/null 2>&1 +ret = 1 [event:base-record] -sample_period=4000 sample_type=1415 diff --git a/tools/perf/tests/attr/test-stat-C0 b/tools/perf/tests/attr/test-stat-C0 index aa835950751f..67717fe6a65d 100644 --- a/tools/perf/tests/attr/test-stat-C0 +++ b/tools/perf/tests/attr/test-stat-C0 @@ -4,6 +4,6 @@ args = -e cycles -C 0 kill >/dev/null 2>&1 ret = 1 [event:base-stat] -# events are enabled by default when attached to cpu -disabled=0 +# events are disabled by default when attached to cpu +disabled=1 enable_on_exec=0 diff --git a/tools/perf/tests/attr/test-stat-default b/tools/perf/tests/attr/test-stat-default index 19270f54c96e..e911dbd4eb47 100644 --- a/tools/perf/tests/attr/test-stat-default +++ b/tools/perf/tests/attr/test-stat-default @@ -38,12 +38,14 @@ config=0 fd=6 type=0 config=7 +optional=1 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND [event7:base-stat] fd=7 type=0 config=8 +optional=1 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_INSTRUCTIONS [event8:base-stat] diff --git a/tools/perf/tests/attr/test-stat-detailed-1 b/tools/perf/tests/attr/test-stat-detailed-1 index 51426b87153b..b39270a08e74 100644 --- a/tools/perf/tests/attr/test-stat-detailed-1 +++ b/tools/perf/tests/attr/test-stat-detailed-1 @@ -39,12 +39,14 @@ config=0 fd=6 type=0 config=7 +optional=1 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND [event7:base-stat] fd=7 type=0 config=8 +optional=1 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_INSTRUCTIONS [event8:base-stat] diff --git a/tools/perf/tests/attr/test-stat-detailed-2 b/tools/perf/tests/attr/test-stat-detailed-2 index 8de5acc31c27..45f8e6ea34f8 100644 --- a/tools/perf/tests/attr/test-stat-detailed-2 +++ b/tools/perf/tests/attr/test-stat-detailed-2 @@ -39,12 +39,14 @@ config=0 fd=6 type=0 config=7 +optional=1 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND [event7:base-stat] fd=7 type=0 config=8 +optional=1 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_INSTRUCTIONS [event8:base-stat] @@ -108,6 +110,7 @@ config=65538 fd=15 type=3 config=1 +optional=1 # PERF_TYPE_HW_CACHE, # PERF_COUNT_HW_CACHE_L1I << 0 | diff --git a/tools/perf/tests/attr/test-stat-detailed-3 b/tools/perf/tests/attr/test-stat-detailed-3 index 0a1f45bf7d79..30ae0fb7a3fd 100644 --- a/tools/perf/tests/attr/test-stat-detailed-3 +++ b/tools/perf/tests/attr/test-stat-detailed-3 @@ -39,12 +39,14 @@ config=0 fd=6 type=0 config=7 +optional=1 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND [event7:base-stat] fd=7 type=0 config=8 +optional=1 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_INSTRUCTIONS [event8:base-stat] @@ -108,6 +110,7 @@ config=65538 fd=15 type=3 config=1 +optional=1 # PERF_TYPE_HW_CACHE, # PERF_COUNT_HW_CACHE_L1I << 0 | @@ -162,6 +165,7 @@ config=65540 fd=21 type=3 config=512 +optional=1 # PERF_TYPE_HW_CACHE, # PERF_COUNT_HW_CACHE_L1D << 0 | @@ -171,3 +175,4 @@ config=512 fd=22 type=3 config=66048 +optional=1 diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c index 50f6d7afee58..d233ad336463 100644 --- a/tools/perf/tests/backward-ring-buffer.c +++ b/tools/perf/tests/backward-ring-buffer.c @@ -75,7 +75,7 @@ static int do_test(struct perf_evlist *evlist, int mmap_pages, } -int test__backward_ring_buffer(int subtest __maybe_unused) +int test__backward_ring_buffer(struct test *test __maybe_unused, int subtest __maybe_unused) { int ret = TEST_SKIP, err, sample_count = 0, comm_count = 0; char pid[16], sbuf[STRERR_BUFSIZE]; diff --git a/tools/perf/tests/bitmap.c b/tools/perf/tests/bitmap.c index 9abe6c13090f..0d7c06584905 100644 --- a/tools/perf/tests/bitmap.c +++ b/tools/perf/tests/bitmap.c @@ -40,7 +40,7 @@ static int test_bitmap(const char *str) return ret; } -int test__bitmap_print(int subtest __maybe_unused) +int test__bitmap_print(struct test *test __maybe_unused, int subtest __maybe_unused) { TEST_ASSERT_VAL("failed to convert map", test_bitmap("1")); TEST_ASSERT_VAL("failed to convert map", test_bitmap("1,5")); diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c index 8ba2c4618fe9..97937e1bc53a 100644 --- a/tools/perf/tests/bp_signal.c +++ b/tools/perf/tests/bp_signal.c @@ -62,8 +62,7 @@ static void __test_function(volatile long *ptr) } #endif -__attribute__ ((noinline)) -static int test_function(void) +static noinline int test_function(void) { __test_function(&the_var); the_var++; @@ -165,7 +164,7 @@ static long long bp_count(int fd) return count; } -int test__bp_signal(int subtest __maybe_unused) +int test__bp_signal(struct test *test __maybe_unused, int subtest __maybe_unused) { struct sigaction sa; long long count1, count2, count3; diff --git a/tools/perf/tests/bp_signal_overflow.c b/tools/perf/tests/bp_signal_overflow.c index 89f92fa67cc4..61ecd8021f49 100644 --- a/tools/perf/tests/bp_signal_overflow.c +++ b/tools/perf/tests/bp_signal_overflow.c @@ -28,8 +28,7 @@ static int overflows; -__attribute__ ((noinline)) -static int test_function(void) +static noinline int test_function(void) { return time(NULL); } @@ -58,7 +57,7 @@ static long long bp_count(int fd) #define EXECUTIONS 10000 #define THRESHOLD 100 -int test__bp_signal_overflow(int subtest __maybe_unused) +int test__bp_signal_overflow(struct test *test __maybe_unused, int subtest __maybe_unused) { struct perf_event_attr pe; struct sigaction sa; diff --git a/tools/perf/tests/bpf-script-test-prologue.c b/tools/perf/tests/bpf-script-test-prologue.c index 7230e62c70fc..43f1e16486f4 100644 --- a/tools/perf/tests/bpf-script-test-prologue.c +++ b/tools/perf/tests/bpf-script-test-prologue.c @@ -10,6 +10,15 @@ #include <uapi/linux/fs.h> +/* + * If CONFIG_PROFILE_ALL_BRANCHES is selected, + * 'if' is redefined after include kernel header. + * Recover 'if' for BPF object code. + */ +#ifdef if +# undef if +#endif + #define FMODE_READ 0x1 #define FMODE_WRITE 0x2 @@ -17,9 +26,11 @@ static void (*bpf_trace_printk)(const char *fmt, int fmt_size, ...) = (void *) 6; SEC("func=null_lseek file->f_mode offset orig") -int bpf_func__null_lseek(void *ctx, int err, unsigned long f_mode, +int bpf_func__null_lseek(void *ctx, int err, unsigned long _f_mode, unsigned long offset, unsigned long orig) { + fmode_t f_mode = (fmode_t)_f_mode; + if (err) return 0; if (f_mode & FMODE_WRITE) diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c index 5876da126b58..34c22cdf4d5d 100644 --- a/tools/perf/tests/bpf.c +++ b/tools/perf/tests/bpf.c @@ -124,16 +124,16 @@ static int do_test(struct bpf_object *obj, int (*func)(void), struct perf_evlist *evlist; int i, ret = TEST_FAIL, err = 0, count = 0; - struct parse_events_evlist parse_evlist; + struct parse_events_state parse_state; struct parse_events_error parse_error; bzero(&parse_error, sizeof(parse_error)); - bzero(&parse_evlist, sizeof(parse_evlist)); - parse_evlist.error = &parse_error; - INIT_LIST_HEAD(&parse_evlist.list); + bzero(&parse_state, sizeof(parse_state)); + parse_state.error = &parse_error; + INIT_LIST_HEAD(&parse_state.list); - err = parse_events_load_bpf_obj(&parse_evlist, &parse_evlist.list, obj, NULL); - if (err || list_empty(&parse_evlist.list)) { + err = parse_events_load_bpf_obj(&parse_state, &parse_state.list, obj, NULL); + if (err || list_empty(&parse_state.list)) { pr_debug("Failed to add events selected by BPF\n"); return TEST_FAIL; } @@ -155,8 +155,8 @@ static int do_test(struct bpf_object *obj, int (*func)(void), goto out_delete_evlist; } - perf_evlist__splice_list_tail(evlist, &parse_evlist.list); - evlist->nr_groups = parse_evlist.nr_groups; + perf_evlist__splice_list_tail(evlist, &parse_state.list); + evlist->nr_groups = parse_state.nr_groups; perf_evlist__config(evlist, &opts, NULL); @@ -321,7 +321,7 @@ static int check_env(void) return 0; } -int test__bpf(int i) +int test__bpf(struct test *test __maybe_unused, int i) { int err; @@ -351,7 +351,7 @@ const char *test__bpf_subtest_get_desc(int i __maybe_unused) return NULL; } -int test__bpf(int i __maybe_unused) +int test__bpf(struct test *test __maybe_unused, int i __maybe_unused) { pr_debug("Skip BPF test because BPF support is not compiled\n"); return TEST_SKIP; diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index 3ccfd58a8c3c..377bea009163 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -6,7 +6,10 @@ #include <errno.h> #include <unistd.h> #include <string.h> +#include <sys/types.h> +#include <dirent.h> #include <sys/wait.h> +#include <sys/stat.h> #include "builtin.h" #include "hist.h" #include "intlist.h" @@ -14,8 +17,10 @@ #include "debug.h" #include "color.h" #include <subcmd/parse-options.h> +#include "string2.h" #include "symbol.h" #include <linux/kernel.h> +#include <subcmd/exec-cmd.h> static bool dont_fork; @@ -43,6 +48,10 @@ static struct test generic_tests[] = { .func = test__basic_mmap, }, { + .desc = "Test data source output", + .func = test__mem, + }, + { .desc = "Parse event definition strings", .func = test__parse_events, }, @@ -179,7 +188,7 @@ static struct test generic_tests[] = { }, { .desc = "Session topology", - .func = test_session_topology, + .func = test__session_topology, }, { .desc = "BPF filter", @@ -325,7 +334,7 @@ static int run_test(struct test *test, int subtest) } } - err = test->func(subtest); + err = test->func(test, subtest); if (!dont_fork) exit(err); } @@ -383,12 +392,143 @@ static int test_and_print(struct test *t, bool force_skip, int subtest) return err; } +static const char *shell_test__description(char *description, size_t size, + const char *path, const char *name) +{ + FILE *fp; + char filename[PATH_MAX]; + + path__join(filename, sizeof(filename), path, name); + fp = fopen(filename, "r"); + if (!fp) + return NULL; + + description = fgets(description, size, fp); + fclose(fp); + + return description ? trim(description + 1) : NULL; +} + +#define for_each_shell_test(dir, ent) \ + while ((ent = readdir(dir)) != NULL) \ + if (ent->d_type == DT_REG && ent->d_name[0] != '.') + +static const char *shell_tests__dir(char *path, size_t size) +{ + const char *devel_dirs[] = { "./tools/perf/tests", "./tests", }; + char *exec_path; + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(devel_dirs); ++i) { + struct stat st; + if (!lstat(devel_dirs[i], &st)) { + scnprintf(path, size, "%s/shell", devel_dirs[i]); + if (!lstat(devel_dirs[i], &st)) + return path; + } + } + + /* Then installed path. */ + exec_path = get_argv_exec_path(); + scnprintf(path, size, "%s/tests/shell", exec_path); + free(exec_path); + return path; +} + +static int shell_tests__max_desc_width(void) +{ + DIR *dir; + struct dirent *ent; + char path_dir[PATH_MAX]; + const char *path = shell_tests__dir(path_dir, sizeof(path_dir)); + int width = 0; + + if (path == NULL) + return -1; + + dir = opendir(path); + if (!dir) + return -1; + + for_each_shell_test(dir, ent) { + char bf[256]; + const char *desc = shell_test__description(bf, sizeof(bf), path, ent->d_name); + + if (desc) { + int len = strlen(desc); + + if (width < len) + width = len; + } + } + + closedir(dir); + return width; +} + +struct shell_test { + const char *dir; + const char *file; +}; + +static int shell_test__run(struct test *test, int subdir __maybe_unused) +{ + int err; + char script[PATH_MAX]; + struct shell_test *st = test->priv; + + path__join(script, sizeof(script), st->dir, st->file); + + err = system(script); + if (!err) + return TEST_OK; + + return WEXITSTATUS(err) == 2 ? TEST_SKIP : TEST_FAIL; +} + +static int run_shell_tests(int argc, const char *argv[], int i, int width) +{ + DIR *dir; + struct dirent *ent; + char path_dir[PATH_MAX]; + struct shell_test st = { + .dir = shell_tests__dir(path_dir, sizeof(path_dir)), + }; + + if (st.dir == NULL) + return -1; + + dir = opendir(st.dir); + if (!dir) + return -1; + + for_each_shell_test(dir, ent) { + int curr = i++; + char desc[256]; + struct test test = { + .desc = shell_test__description(desc, sizeof(desc), st.dir, ent->d_name), + .func = shell_test__run, + .priv = &st, + }; + + if (!perf_test__matches(&test, curr, argc, argv)) + continue; + + st.file = ent->d_name; + pr_info("%2d: %-*s:", i, width, test.desc); + test_and_print(&test, false, -1); + } + + closedir(dir); + return 0; +} + static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist) { struct test *t; unsigned int j; int i = 0; - int width = 0; + int width = shell_tests__max_desc_width(); for_each_test(j, t) { int len = strlen(t->desc); @@ -455,6 +595,37 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist) } } + return run_shell_tests(argc, argv, i, width); +} + +static int perf_test__list_shell(int argc, const char **argv, int i) +{ + DIR *dir; + struct dirent *ent; + char path_dir[PATH_MAX]; + const char *path = shell_tests__dir(path_dir, sizeof(path_dir)); + + if (path == NULL) + return -1; + + dir = opendir(path); + if (!dir) + return -1; + + for_each_shell_test(dir, ent) { + int curr = i++; + char bf[256]; + struct test t = { + .desc = shell_test__description(bf, sizeof(bf), path, ent->d_name), + }; + + if (!perf_test__matches(&t, curr, argc, argv)) + continue; + + pr_info("%2d: %s\n", i, t.desc); + } + + closedir(dir); return 0; } @@ -465,12 +636,17 @@ static int perf_test__list(int argc, const char **argv) int i = 0; for_each_test(j, t) { - if (argc > 1 && !strstr(t->desc, argv[1])) + int curr = i++; + + if (!perf_test__matches(t, curr, argc, argv) || + (t->is_supported && !t->is_supported())) continue; - pr_info("%2d: %s\n", ++i, t->desc); + pr_info("%2d: %s\n", i, t->desc); } + perf_test__list_shell(argc, argv, i); + return 0; } @@ -498,7 +674,7 @@ int cmd_test(int argc, const char **argv) argc = parse_options_subcommand(argc, argv, test_options, test_subcommands, test_usage, 0); if (argc >= 1 && !strcmp(argv[0], "list")) - return perf_test__list(argc, argv); + return perf_test__list(argc - 1, argv + 1); symbol_conf.priv_size = sizeof(int); symbol_conf.sort_by_name = true; diff --git a/tools/perf/tests/clang.c b/tools/perf/tests/clang.c index c5bb2203f5a9..c60ec916f0f2 100644 --- a/tools/perf/tests/clang.c +++ b/tools/perf/tests/clang.c @@ -33,12 +33,12 @@ const char *test__clang_subtest_get_desc(int i) } #ifndef HAVE_LIBCLANGLLVM_SUPPORT -int test__clang(int i __maybe_unused) +int test__clang(struct test *test __maybe_unused, int i __maybe_unused) { return TEST_SKIP; } #else -int test__clang(int i) +int test__clang(struct test *test __maybe_unused, int i) { if (i < 0 || i >= (int)ARRAY_SIZE(clang_testcase_table)) return TEST_FAIL; diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index 94b7c7b02bde..466a462b26d1 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -237,6 +237,11 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, thread__find_addr_map(thread, cpumode, MAP__FUNCTION, addr, &al); if (!al.map || !al.map->dso) { + if (cpumode == PERF_RECORD_MISC_HYPERVISOR) { + pr_debug("Hypervisor address can not be resolved - skipping\n"); + return 0; + } + pr_debug("thread__find_addr_map failed\n"); return -1; } @@ -673,7 +678,7 @@ out_err: return err; } -int test__code_reading(int subtest __maybe_unused) +int test__code_reading(struct test *test __maybe_unused, int subtest __maybe_unused) { int ret; diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c index 4478773cdb97..199702252270 100644 --- a/tools/perf/tests/cpumap.c +++ b/tools/perf/tests/cpumap.c @@ -72,7 +72,7 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused, } -int test__cpu_map_synthesize(int subtest __maybe_unused) +int test__cpu_map_synthesize(struct test *test __maybe_unused, int subtest __maybe_unused) { struct cpu_map *cpus; @@ -106,7 +106,7 @@ static int cpu_map_print(const char *str) return !strcmp(buf, str); } -int test__cpu_map_print(int subtest __maybe_unused) +int test__cpu_map_print(struct test *test __maybe_unused, int subtest __maybe_unused) { TEST_ASSERT_VAL("failed to convert map", cpu_map_print("1")); TEST_ASSERT_VAL("failed to convert map", cpu_map_print("1,5")); diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c index 8f08df5861cb..30aead42d136 100644 --- a/tools/perf/tests/dso-data.c +++ b/tools/perf/tests/dso-data.c @@ -112,7 +112,7 @@ static int dso__data_fd(struct dso *dso, struct machine *machine) return fd; } -int test__dso_data(int subtest __maybe_unused) +int test__dso_data(struct test *test __maybe_unused, int subtest __maybe_unused) { struct machine machine; struct dso *dso; @@ -247,7 +247,7 @@ static int set_fd_limit(int n) return setrlimit(RLIMIT_NOFILE, &rlim); } -int test__dso_data_cache(int subtest __maybe_unused) +int test__dso_data_cache(struct test *test __maybe_unused, int subtest __maybe_unused) { struct machine machine; long nr_end, nr = open_files_cnt(); @@ -307,7 +307,7 @@ int test__dso_data_cache(int subtest __maybe_unused) return 0; } -int test__dso_data_reopen(int subtest __maybe_unused) +int test__dso_data_reopen(struct test *test __maybe_unused, int subtest __maybe_unused) { struct machine machine; long nr_end, nr = open_files_cnt(); diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c index dfe5c89e2049..9ba1d216a89f 100644 --- a/tools/perf/tests/dwarf-unwind.c +++ b/tools/perf/tests/dwarf-unwind.c @@ -6,7 +6,7 @@ #include "debug.h" #include "machine.h" #include "event.h" -#include "unwind.h" +#include "../util/unwind.h" #include "perf_regs.h" #include "map.h" #include "thread.h" @@ -76,8 +76,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) return strcmp((const char *) symbol, funcs[idx]); } -__attribute__ ((noinline)) -static int unwind_thread(struct thread *thread) +static noinline int unwind_thread(struct thread *thread) { struct perf_sample sample; unsigned long cnt = 0; @@ -108,8 +107,7 @@ static int unwind_thread(struct thread *thread) static int global_unwind_retval = -INT_MAX; -__attribute__ ((noinline)) -static int compare(void *p1, void *p2) +static noinline int compare(void *p1, void *p2) { /* Any possible value should be 'thread' */ struct thread *thread = *(struct thread **)p1; @@ -128,8 +126,7 @@ static int compare(void *p1, void *p2) return p1 - p2; } -__attribute__ ((noinline)) -static int krava_3(struct thread *thread) +static noinline int krava_3(struct thread *thread) { struct thread *array[2] = {thread, thread}; void *fp = &bsearch; @@ -147,19 +144,17 @@ static int krava_3(struct thread *thread) return global_unwind_retval; } -__attribute__ ((noinline)) -static int krava_2(struct thread *thread) +static noinline int krava_2(struct thread *thread) { return krava_3(thread); } -__attribute__ ((noinline)) -static int krava_1(struct thread *thread) +static noinline int krava_1(struct thread *thread) { return krava_2(thread); } -int test__dwarf_unwind(int subtest __maybe_unused) +int test__dwarf_unwind(struct test *test __maybe_unused, int subtest __maybe_unused) { struct machine *machine; struct thread *thread; diff --git a/tools/perf/tests/event-times.c b/tools/perf/tests/event-times.c index 634f20c631d8..b82b981c3259 100644 --- a/tools/perf/tests/event-times.c +++ b/tools/perf/tests/event-times.c @@ -213,7 +213,7 @@ out_err: * and checks that enabled and running times * match. */ -int test__event_times(int subtest __maybe_unused) +int test__event_times(struct test *test __maybe_unused, int subtest __maybe_unused) { int err, ret = 0; diff --git a/tools/perf/tests/event_update.c b/tools/perf/tests/event_update.c index 63ecf21750eb..9484da2ec6b4 100644 --- a/tools/perf/tests/event_update.c +++ b/tools/perf/tests/event_update.c @@ -76,7 +76,7 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused, return 0; } -int test__event_update(int subtest __maybe_unused) +int test__event_update(struct test *test __maybe_unused, int subtest __maybe_unused) { struct perf_evlist *evlist; struct perf_evsel *evsel; diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c index d2bea6f780f8..d32759b6e38a 100644 --- a/tools/perf/tests/evsel-roundtrip-name.c +++ b/tools/perf/tests/evsel-roundtrip-name.c @@ -97,7 +97,7 @@ out_delete_evlist: #define perf_evsel__name_array_test(names) \ __perf_evsel__name_array_test(names, ARRAY_SIZE(names)) -int test__perf_evsel__roundtrip_name_test(int subtest __maybe_unused) +int test__perf_evsel__roundtrip_name_test(struct test *test __maybe_unused, int subtest __maybe_unused) { int err = 0, ret = 0; diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c index 1984b3bbfe15..5fc906d26c5c 100644 --- a/tools/perf/tests/evsel-tp-sched.c +++ b/tools/perf/tests/evsel-tp-sched.c @@ -32,7 +32,7 @@ static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name, return ret; } -int test__perf_evsel__tp_sched_test(int subtest __maybe_unused) +int test__perf_evsel__tp_sched_test(struct test *test __maybe_unused, int subtest __maybe_unused) { struct perf_evsel *evsel = perf_evsel__newtp("sched", "sched_switch"); int ret = 0; diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c index 6c6a3749aaf6..cb251bf523e7 100644 --- a/tools/perf/tests/expr.c +++ b/tools/perf/tests/expr.c @@ -13,7 +13,7 @@ static int test(struct parse_ctx *ctx, const char *e, double val2) return 0; } -int test__expr(int subtest __maybe_unused) +int test__expr(struct test *t __maybe_unused, int subtest __maybe_unused) { const char *p; const char **other; @@ -31,6 +31,11 @@ int test__expr(int subtest __maybe_unused) ret |= test(&ctx, "(BAR/2)%2", 1); ret |= test(&ctx, "1 - -4", 5); ret |= test(&ctx, "(FOO-1)*2 + (BAR/2)%2 - -4", 5); + ret |= test(&ctx, "1-1 | 1", 1); + ret |= test(&ctx, "1-1 & 1", 0); + ret |= test(&ctx, "min(1,2) + 1", 2); + ret |= test(&ctx, "max(1,2) + 1", 3); + ret |= test(&ctx, "1+1 if 3*4 else 0", 2); if (ret) return ret; diff --git a/tools/perf/tests/fdarray.c b/tools/perf/tests/fdarray.c index bc5982f42dc3..7d3a9e2ff897 100644 --- a/tools/perf/tests/fdarray.c +++ b/tools/perf/tests/fdarray.c @@ -26,7 +26,7 @@ static int fdarray__fprintf_prefix(struct fdarray *fda, const char *prefix, FILE return printed + fdarray__fprintf(fda, fp); } -int test__fdarray__filter(int subtest __maybe_unused) +int test__fdarray__filter(struct test *test __maybe_unused, int subtest __maybe_unused) { int nr_fds, expected_fd[2], fd, err = TEST_FAIL; struct fdarray *fda = fdarray__new(5, 5); @@ -104,7 +104,7 @@ out: return err; } -int test__fdarray__add(int subtest __maybe_unused) +int test__fdarray__add(struct test *test __maybe_unused, int subtest __maybe_unused) { int err = TEST_FAIL; struct fdarray *fda = fdarray__new(2, 2); diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c index d549a9f2c41b..8d19c0200cb7 100644 --- a/tools/perf/tests/hists_cumulate.c +++ b/tools/perf/tests/hists_cumulate.c @@ -687,7 +687,7 @@ out: return err; } -int test__hists_cumulate(int subtest __maybe_unused) +int test__hists_cumulate(struct test *test __maybe_unused, int subtest __maybe_unused) { int err = TEST_FAIL; struct machines machines; diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c index df9c91f49af1..755ca551b810 100644 --- a/tools/perf/tests/hists_filter.c +++ b/tools/perf/tests/hists_filter.c @@ -101,7 +101,7 @@ out: return TEST_FAIL; } -int test__hists_filter(int subtest __maybe_unused) +int test__hists_filter(struct test *test __maybe_unused, int subtest __maybe_unused) { int err = TEST_FAIL; struct machines machines; diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c index a26cbb79e988..073c9c2856bc 100644 --- a/tools/perf/tests/hists_link.c +++ b/tools/perf/tests/hists_link.c @@ -264,7 +264,7 @@ static int validate_link(struct hists *leader, struct hists *other) return __validate_link(leader, 0) || __validate_link(other, 1); } -int test__hists_link(int subtest __maybe_unused) +int test__hists_link(struct test *test __maybe_unused, int subtest __maybe_unused) { int err = -1; struct hists *hists, *first_hists; diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c index 06e5080182d3..282d62eaebe2 100644 --- a/tools/perf/tests/hists_output.c +++ b/tools/perf/tests/hists_output.c @@ -573,7 +573,7 @@ out: return err; } -int test__hists_output(int subtest __maybe_unused) +int test__hists_output(struct test *test __maybe_unused, int subtest __maybe_unused) { int err = TEST_FAIL; struct machines machines; diff --git a/tools/perf/tests/is_printable_array.c b/tools/perf/tests/is_printable_array.c index a5192f6a20d7..38f765767587 100644 --- a/tools/perf/tests/is_printable_array.c +++ b/tools/perf/tests/is_printable_array.c @@ -4,7 +4,7 @@ #include "debug.h" #include "print_binary.h" -int test__is_printable_array(int subtest __maybe_unused) +int test__is_printable_array(struct test *test __maybe_unused, int subtest __maybe_unused) { char buf1[] = { 'k', 'r', 4, 'v', 'a', 0 }; char buf2[] = { 'k', 'r', 'a', 'v', 4, 0 }; diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c index 614e45a3c603..739428603b71 100644 --- a/tools/perf/tests/keep-tracking.c +++ b/tools/perf/tests/keep-tracking.c @@ -49,7 +49,7 @@ static int find_comm(struct perf_evlist *evlist, const char *comm) * when an event is disabled but a dummy software event is not disabled. If the * test passes %0 is returned, otherwise %-1 is returned. */ -int test__keep_tracking(int subtest __maybe_unused) +int test__keep_tracking(struct test *test __maybe_unused, int subtest __maybe_unused) { struct record_opts opts = { .mmap_pages = UINT_MAX, diff --git a/tools/perf/tests/kmod-path.c b/tools/perf/tests/kmod-path.c index 6cd9e5107f77..8b9d4ba06c0e 100644 --- a/tools/perf/tests/kmod-path.c +++ b/tools/perf/tests/kmod-path.c @@ -50,7 +50,7 @@ static int test_is_kernel_module(const char *path, int cpumode, bool expect) #define M(path, c, e) \ TEST_ASSERT_VAL("failed", !test_is_kernel_module(path, c, e)) -int test__kmod_path__parse(int subtest __maybe_unused) +int test__kmod_path__parse(struct test *t __maybe_unused, int subtest __maybe_unused) { /* path alloc_name alloc_ext kmod comp name ext */ T("/xxxx/xxxx/x-x.ko", true , true , true, false, "[x_x]", NULL); diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c index 482b5365e68d..5187b50dbafe 100644 --- a/tools/perf/tests/llvm.c +++ b/tools/perf/tests/llvm.c @@ -132,7 +132,7 @@ out: return ret; } -int test__llvm(int subtest) +int test__llvm(struct test *test __maybe_unused, int subtest) { int ret; void *obj_buf = NULL; diff --git a/tools/perf/tests/mem.c b/tools/perf/tests/mem.c new file mode 100644 index 000000000000..21952e1e6e6d --- /dev/null +++ b/tools/perf/tests/mem.c @@ -0,0 +1,56 @@ +#include "util/mem-events.h" +#include "util/symbol.h" +#include "linux/perf_event.h" +#include "util/debug.h" +#include "tests.h" +#include <string.h> + +static int check(union perf_mem_data_src data_src, + const char *string) +{ + char out[100]; + char failure[100]; + struct mem_info mi = { .data_src = data_src }; + + int n; + + n = perf_mem__snp_scnprintf(out, sizeof out, &mi); + n += perf_mem__lvl_scnprintf(out + n, sizeof out - n, &mi); + snprintf(failure, sizeof failure, "unexpected %s", out); + TEST_ASSERT_VAL(failure, !strcmp(string, out)); + return 0; +} + +int test__mem(struct test *text __maybe_unused, int subtest __maybe_unused) +{ + int ret = 0; + union perf_mem_data_src src; + + memset(&src, 0, sizeof(src)); + + src.mem_lvl = PERF_MEM_LVL_HIT; + src.mem_lvl_num = 4; + + ret |= check(src, "N/AL4 hit"); + + src.mem_remote = 1; + + ret |= check(src, "N/ARemote L4 hit"); + + src.mem_lvl = PERF_MEM_LVL_MISS; + src.mem_lvl_num = PERF_MEM_LVLNUM_PMEM; + src.mem_remote = 0; + + ret |= check(src, "N/APMEM miss"); + + src.mem_remote = 1; + + ret |= check(src, "N/ARemote PMEM miss"); + + src.mem_snoopx = PERF_MEM_SNOOPX_FWD; + src.mem_lvl_num = PERF_MEM_LVLNUM_RAM; + + ret |= check(src , "FwdRemote RAM miss"); + + return ret; +} diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c index 15c770856aac..bc8a70ee46d8 100644 --- a/tools/perf/tests/mmap-basic.c +++ b/tools/perf/tests/mmap-basic.c @@ -22,7 +22,7 @@ * Then it checks if the number of syscalls reported as perf events by * the kernel corresponds to the number of syscalls made. */ -int test__basic_mmap(int subtest __maybe_unused) +int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unused) { int err = -1; union perf_event *event; diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c index 6ea4d8a5d26b..f94a4196e7c9 100644 --- a/tools/perf/tests/mmap-thread-lookup.c +++ b/tools/perf/tests/mmap-thread-lookup.c @@ -221,7 +221,7 @@ static int mmap_events(synth_cb synth) * * by using all thread objects. */ -int test__mmap_thread_lookup(int subtest __maybe_unused) +int test__mmap_thread_lookup(struct test *test __maybe_unused, int subtest __maybe_unused) { /* perf_event__synthesize_threads synthesize */ TEST_ASSERT_VAL("failed with sythesizing all", diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c index 1a74dd9fd067..9cf1c35f2ad0 100644 --- a/tools/perf/tests/openat-syscall-all-cpus.c +++ b/tools/perf/tests/openat-syscall-all-cpus.c @@ -16,7 +16,7 @@ #include "debug.h" #include "stat.h" -int test__openat_syscall_event_on_all_cpus(int subtest __maybe_unused) +int test__openat_syscall_event_on_all_cpus(struct test *test __maybe_unused, int subtest __maybe_unused) { int err = -1, fd, cpu; struct cpu_map *cpus; @@ -115,7 +115,7 @@ int test__openat_syscall_event_on_all_cpus(int subtest __maybe_unused) perf_evsel__free_counts(evsel); out_close_fd: - perf_evsel__close_fd(evsel, 1, threads->nr); + perf_evsel__close_fd(evsel); out_evsel_delete: perf_evsel__delete(evsel); out_thread_map_delete: diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c index 9788fac91095..b6ee1c41f45d 100644 --- a/tools/perf/tests/openat-syscall-tp-fields.c +++ b/tools/perf/tests/openat-syscall-tp-fields.c @@ -14,7 +14,7 @@ #define AT_FDCWD -100 #endif -int test__syscall_openat_tp_fields(int subtest __maybe_unused) +int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest __maybe_unused) { struct record_opts opts = { .target = { diff --git a/tools/perf/tests/openat-syscall.c b/tools/perf/tests/openat-syscall.c index e44506e21ee7..9dc5c5d37553 100644 --- a/tools/perf/tests/openat-syscall.c +++ b/tools/perf/tests/openat-syscall.c @@ -10,7 +10,7 @@ #include "debug.h" #include "tests.h" -int test__openat_syscall_event(int subtest __maybe_unused) +int test__openat_syscall_event(struct test *test __maybe_unused, int subtest __maybe_unused) { int err = -1, fd; struct perf_evsel *evsel; @@ -56,7 +56,7 @@ int test__openat_syscall_event(int subtest __maybe_unused) err = 0; out_close_fd: - perf_evsel__close_fd(evsel, 1, threads->nr); + perf_evsel__close_fd(evsel); out_evsel_delete: perf_evsel__delete(evsel); out_thread_map_delete: diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index 7fad885491c5..0f0b025faa4b 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -1810,18 +1810,7 @@ static int test_pmu_events(void) return ret; } -static void debug_warn(const char *warn, va_list params) -{ - char msg[1024]; - - if (verbose <= 0) - return; - - vsnprintf(msg, sizeof(msg), warn, params); - fprintf(stderr, " Warning: %s\n", msg); -} - -int test__parse_events(int subtest __maybe_unused) +int test__parse_events(struct test *test __maybe_unused, int subtest __maybe_unused) { int ret1, ret2 = 0; @@ -1832,8 +1821,6 @@ do { \ ret2 = ret1; \ } while (0) - set_warning_routine(debug_warn); - TEST_EVENTS(test__events); if (test_pmu()) diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c index c6207db09f12..91867dcc39f0 100644 --- a/tools/perf/tests/parse-no-sample-id-all.c +++ b/tools/perf/tests/parse-no-sample-id-all.c @@ -68,7 +68,7 @@ struct test_attr_event { * * Return: %0 on success, %-1 if the test fails. */ -int test__parse_no_sample_id_all(int subtest __maybe_unused) +int test__parse_no_sample_id_all(struct test *test __maybe_unused, int subtest __maybe_unused) { int err; diff --git a/tools/perf/tests/perf-hooks.c b/tools/perf/tests/perf-hooks.c index 665ecc19671c..bf2517d6de70 100644 --- a/tools/perf/tests/perf-hooks.c +++ b/tools/perf/tests/perf-hooks.c @@ -27,7 +27,7 @@ static void the_hook(void *_hook_flags) *p = 0; } -int test__perf_hooks(int subtest __maybe_unused) +int test__perf_hooks(struct test *test __maybe_unused, int subtest __maybe_unused) { int hook_flags = 0; diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c index d37cd9588cc0..19b650064b70 100644 --- a/tools/perf/tests/perf-record.c +++ b/tools/perf/tests/perf-record.c @@ -37,7 +37,7 @@ realloc: return cpu; } -int test__PERF_RECORD(int subtest __maybe_unused) +int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unused) { struct record_opts opts = { .target = { diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c index a6d7aef30030..9f7f589f9c54 100644 --- a/tools/perf/tests/pmu.c +++ b/tools/perf/tests/pmu.c @@ -135,7 +135,7 @@ static struct list_head *test_terms_list(void) return &terms; } -int test__pmu(int subtest __maybe_unused) +int test__pmu(struct test *test __maybe_unused, int subtest __maybe_unused) { char *format = test_format_dir_get(); LIST_HEAD(formats); diff --git a/tools/perf/tests/python-use.c b/tools/perf/tests/python-use.c index fa79509da535..598a7e058ad4 100644 --- a/tools/perf/tests/python-use.c +++ b/tools/perf/tests/python-use.c @@ -9,7 +9,7 @@ extern int verbose; -int test__python_use(int subtest __maybe_unused) +int test__python_use(struct test *test __maybe_unused, int subtest __maybe_unused) { char *cmd; int ret; diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c index bac5c3885b3b..c3858487159d 100644 --- a/tools/perf/tests/sample-parsing.c +++ b/tools/perf/tests/sample-parsing.c @@ -141,6 +141,9 @@ static bool samples_same(const struct perf_sample *s1, } } + if (type & PERF_SAMPLE_PHYS_ADDR) + COMP(phys_addr); + return true; } @@ -206,6 +209,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format) .mask = sample_regs, .regs = regs, }, + .phys_addr = 113, }; struct sample_read_value values[] = {{1, 5}, {9, 3}, {2, 7}, {6, 4},}; struct perf_sample sample_out; @@ -292,7 +296,7 @@ out_free: * checks sample format bits separately and together. If the test passes %0 is * returned, otherwise %-1 is returned. */ -int test__sample_parsing(int subtest __maybe_unused) +int test__sample_parsing(struct test *test __maybe_unused, int subtest __maybe_unused) { const u64 rf[] = {4, 5, 6, 7, 12, 13, 14, 15}; u64 sample_type; @@ -305,7 +309,7 @@ int test__sample_parsing(int subtest __maybe_unused) * were added. Please actually update the test rather than just change * the condition below. */ - if (PERF_SAMPLE_MAX > PERF_SAMPLE_REGS_INTR << 1) { + if (PERF_SAMPLE_MAX > PERF_SAMPLE_PHYS_ADDR << 1) { pr_debug("sample format has changed, some new PERF_SAMPLE_ bit was introduced - test needs updating\n"); return -1; } diff --git a/tools/perf/tests/sdt.c b/tools/perf/tests/sdt.c index 06eda675ae2c..a9903d9b8bc2 100644 --- a/tools/perf/tests/sdt.c +++ b/tools/perf/tests/sdt.c @@ -33,7 +33,7 @@ static int build_id_cache__add_file(const char *filename) } build_id__sprintf(build_id, sizeof(build_id), sbuild_id); - err = build_id_cache__add_s(sbuild_id, filename, false, false); + err = build_id_cache__add_s(sbuild_id, filename, NULL, false, false); if (err < 0) pr_debug("Failed to add build id cache of %s\n", filename); return err; @@ -54,7 +54,7 @@ static char *get_self_path(void) static int search_cached_probe(const char *target, const char *group, const char *event) { - struct probe_cache *cache = probe_cache__new(target); + struct probe_cache *cache = probe_cache__new(target, NULL); int ret = 0; if (!cache) { @@ -71,7 +71,7 @@ static int search_cached_probe(const char *target, return ret; } -int test__sdt_event(int subtests __maybe_unused) +int test__sdt_event(struct test *test __maybe_unused, int subtests __maybe_unused) { int ret = TEST_FAIL; char __tempdir[] = "./test-buildid-XXXXXX"; @@ -83,6 +83,8 @@ int test__sdt_event(int subtests __maybe_unused) } /* Note that buildid_dir must be an absolute path */ tempdir = realpath(__tempdir, NULL); + if (tempdir == NULL) + goto error_rmdir; /* At first, scan itself */ set_buildid_dir(tempdir); @@ -100,14 +102,14 @@ int test__sdt_event(int subtests __maybe_unused) error_rmdir: /* Cleanup temporary buildid dir */ - rm_rf(tempdir); + rm_rf(__tempdir); error: free(tempdir); free(myself); return ret; } #else -int test__sdt_event(int subtests __maybe_unused) +int test__sdt_event(struct test *test __maybe_unused, int subtests __maybe_unused) { pr_debug("Skip SDT event test because SDT support is not compiled\n"); return TEST_SKIP; diff --git a/tools/perf/tests/shell/lib/probe.sh b/tools/perf/tests/shell/lib/probe.sh new file mode 100644 index 000000000000..6293cc660947 --- /dev/null +++ b/tools/perf/tests/shell/lib/probe.sh @@ -0,0 +1,6 @@ +# Arnaldo Carvalho de Melo <acme@kernel.org>, 2017 + +skip_if_no_perf_probe() { + perf probe 2>&1 | grep -q 'is not a perf-command' && return 2 + return 0 +} diff --git a/tools/perf/tests/shell/lib/probe_vfs_getname.sh b/tools/perf/tests/shell/lib/probe_vfs_getname.sh new file mode 100644 index 000000000000..30a950c9d407 --- /dev/null +++ b/tools/perf/tests/shell/lib/probe_vfs_getname.sh @@ -0,0 +1,23 @@ +# Arnaldo Carvalho de Melo <acme@kernel.org>, 2017 + +perf probe -l 2>&1 | grep -q probe:vfs_getname +had_vfs_getname=$? + +cleanup_probe_vfs_getname() { + if [ $had_vfs_getname -eq 1 ] ; then + perf probe -q -d probe:vfs_getname + fi +} + +add_probe_vfs_getname() { + local verbose=$1 + if [ $had_vfs_getname -eq 1 ] ; then + line=$(perf probe -L getname_flags 2>&1 | egrep 'result.*=.*filename;' | sed -r 's/[[:space:]]+([[:digit:]]+)[[:space:]]+result->uptr.*/\1/') + perf probe $verbose "vfs_getname=getname_flags:${line} pathname=result->name:string" + fi +} + +skip_if_no_debuginfo() { + add_probe_vfs_getname -v 2>&1 | egrep -q "^(Failed to find the path for kernel|Debuginfo-analysis is not supported)" && return 2 + return 1 +} diff --git a/tools/perf/tests/shell/probe_vfs_getname.sh b/tools/perf/tests/shell/probe_vfs_getname.sh new file mode 100755 index 000000000000..9b7635184dc2 --- /dev/null +++ b/tools/perf/tests/shell/probe_vfs_getname.sh @@ -0,0 +1,14 @@ +# Add vfs_getname probe to get syscall args filenames +# +# Arnaldo Carvalho de Melo <acme@kernel.org>, 2017 + +. $(dirname $0)/lib/probe.sh + +skip_if_no_perf_probe || exit 2 + +. $(dirname $0)/lib/probe_vfs_getname.sh + +add_probe_vfs_getname || skip_if_no_debuginfo +err=$? +cleanup_probe_vfs_getname +exit $err diff --git a/tools/perf/tests/shell/record+script_probe_vfs_getname.sh b/tools/perf/tests/shell/record+script_probe_vfs_getname.sh new file mode 100755 index 000000000000..ba29535b8580 --- /dev/null +++ b/tools/perf/tests/shell/record+script_probe_vfs_getname.sh @@ -0,0 +1,41 @@ +# Use vfs_getname probe to get syscall args filenames + +# Uses the 'perf test shell' library to add probe:vfs_getname to the system +# then use it with 'perf record' using 'touch' to write to a temp file, then +# checks that that was captured by the vfs_getname probe in the generated +# perf.data file, with the temp file name as the pathname argument. + +# Arnaldo Carvalho de Melo <acme@kernel.org>, 2017 + +. $(dirname $0)/lib/probe.sh + +skip_if_no_perf_probe || exit 2 + +. $(dirname $0)/lib/probe_vfs_getname.sh + +perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX) +file=$(mktemp /tmp/temporary_file.XXXXX) + +record_open_file() { + echo "Recording open file:" + perf record -o ${perfdata} -e probe:vfs_getname touch $file +} + +perf_script_filenames() { + echo "Looking at perf.data file for vfs_getname records for the file we touched:" + perf script -i ${perfdata} | \ + egrep " +touch +[0-9]+ +\[[0-9]+\] +[0-9]+\.[0-9]+: +probe:vfs_getname: +\([[:xdigit:]]+\) +pathname=\"${file}\"" +} + +add_probe_vfs_getname || skip_if_no_debuginfo +err=$? +if [ $err -ne 0 ] ; then + exit $err +fi + +record_open_file && perf_script_filenames +err=$? +rm -f ${perfdata} +rm -f ${file} +cleanup_probe_vfs_getname +exit $err diff --git a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh new file mode 100755 index 000000000000..462fc755092e --- /dev/null +++ b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh @@ -0,0 +1,43 @@ +# probe libc's inet_pton & backtrace it with ping + +# Installs a probe on libc's inet_pton function, that will use uprobes, +# then use 'perf trace' on a ping to localhost asking for just one packet +# with the a backtrace 3 levels deep, check that it is what we expect. +# This needs no debuginfo package, all is done using the libc ELF symtab +# and the CFI info in the binaries. + +# Arnaldo Carvalho de Melo <acme@kernel.org>, 2017 + +. $(dirname $0)/lib/probe.sh + +trace_libc_inet_pton_backtrace() { + idx=0 + expected[0]="PING.*bytes" + expected[1]="64 bytes from ::1.*" + expected[2]=".*ping statistics.*" + expected[3]=".*packets transmitted.*" + expected[4]="rtt min.*" + expected[5]="[0-9]+\.[0-9]+[[:space:]]+probe_libc:inet_pton:\([[:xdigit:]]+\)" + expected[6]=".*inet_pton[[:space:]]\(/usr/lib.*/libc-[0-9]+\.[0-9]+\.so\)$" + expected[7]="getaddrinfo[[:space:]]\(/usr/lib.*/libc-[0-9]+\.[0-9]+\.so\)$" + expected[8]=".*\(.*/bin/ping.*\)$" + + perf trace --no-syscalls -e probe_libc:inet_pton/max-stack=3/ ping -6 -c 1 ::1 2>&1 | grep -v ^$ | while read line ; do + echo $line + echo "$line" | egrep -q "${expected[$idx]}" + if [ $? -ne 0 ] ; then + printf "FAIL: expected backtrace entry %d \"%s\" got \"%s\"\n" $idx "${expected[$idx]}" "$line" + exit 1 + fi + let idx+=1 + [ $idx -eq 9 ] && break + done +} + +skip_if_no_perf_probe && \ +perf probe -q /lib64/libc-*.so inet_pton && \ +trace_libc_inet_pton_backtrace +err=$? +rm -f ${file} +perf probe -q -d probe_libc:inet_pton +exit $err diff --git a/tools/perf/tests/shell/trace+probe_vfs_getname.sh b/tools/perf/tests/shell/trace+probe_vfs_getname.sh new file mode 100755 index 000000000000..2e68c5f120da --- /dev/null +++ b/tools/perf/tests/shell/trace+probe_vfs_getname.sh @@ -0,0 +1,35 @@ +# Check open filename arg using perf trace + vfs_getname + +# Uses the 'perf test shell' library to add probe:vfs_getname to the system +# then use it with 'perf trace' using 'touch' to write to a temp file, then +# checks that that was captured by the vfs_getname was used by 'perf trace', +# that already handles "probe:vfs_getname" if present, and used in the +# "open" syscall "filename" argument beautifier. + +# Arnaldo Carvalho de Melo <acme@kernel.org>, 2017 + +. $(dirname $0)/lib/probe.sh + +skip_if_no_perf_probe || exit 2 + +. $(dirname $0)/lib/probe_vfs_getname.sh + +file=$(mktemp /tmp/temporary_file.XXXXX) + +trace_open_vfs_getname() { + perf trace -e open touch $file 2>&1 | \ + egrep " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch\/[0-9]+ open\(filename: +${file}, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$" +} + + +add_probe_vfs_getname || skip_if_no_debuginfo +err=$? +if [ $err -ne 0 ] ; then + exit $err +fi + +trace_open_vfs_getname +err=$? +rm -f ${file} +cleanup_probe_vfs_getname +exit $err diff --git a/tools/perf/tests/stat.c b/tools/perf/tests/stat.c index 6a20ff2326bb..7f988a939036 100644 --- a/tools/perf/tests/stat.c +++ b/tools/perf/tests/stat.c @@ -45,7 +45,7 @@ static int process_stat_config_event(struct perf_tool *tool __maybe_unused, return 0; } -int test__synthesize_stat_config(int subtest __maybe_unused) +int test__synthesize_stat_config(struct test *test __maybe_unused, int subtest __maybe_unused) { struct perf_stat_config stat_config = { .aggr_mode = AGGR_CORE, @@ -75,7 +75,7 @@ static int process_stat_event(struct perf_tool *tool __maybe_unused, return 0; } -int test__synthesize_stat(int subtest __maybe_unused) +int test__synthesize_stat(struct test *test __maybe_unused, int subtest __maybe_unused) { struct perf_counts_values count; @@ -101,7 +101,7 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused, return 0; } -int test__synthesize_stat_round(int subtest __maybe_unused) +int test__synthesize_stat_round(struct test *test __maybe_unused, int subtest __maybe_unused) { TEST_ASSERT_VAL("failed to synthesize stat_config", !perf_event__synthesize_stat_round(NULL, 0xdeadbeef, PERF_STAT_ROUND_TYPE__INTERVAL, diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c index 828494db4a19..d88511f6072c 100644 --- a/tools/perf/tests/sw-clock.c +++ b/tools/perf/tests/sw-clock.c @@ -124,7 +124,7 @@ out_delete_evlist: return err; } -int test__sw_clock_freq(int subtest __maybe_unused) +int test__sw_clock_freq(struct test *test __maybe_unused, int subtest __maybe_unused) { int ret; diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c index 65474fd80da7..2acd78555192 100644 --- a/tools/perf/tests/switch-tracking.c +++ b/tools/perf/tests/switch-tracking.c @@ -306,7 +306,7 @@ out_free_nodes: * evsel->system_wide and evsel->tracking flags (respectively) with other events * sometimes enabled or disabled. */ -int test__switch_tracking(int subtest __maybe_unused) +int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_unused) { const char *sched_switch = "sched:sched_switch"; struct switch_tracking switch_tracking = { .tids = NULL, }; diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c index cf00ebad2ef5..f0881d0dd9c9 100644 --- a/tools/perf/tests/task-exit.c +++ b/tools/perf/tests/task-exit.c @@ -32,7 +32,7 @@ static void workload_exec_failed_signal(int signo __maybe_unused, * if the number of exit event reported by the kernel is 1 or not * in order to check the kernel returns correct number of event. */ -int test__task_exit(int subtest __maybe_unused) +int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused) { int err = -1; union perf_event *event; diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index 577363809c9b..921412a6a880 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -28,77 +28,79 @@ enum { struct test { const char *desc; - int (*func)(int subtest); + int (*func)(struct test *test, int subtest); struct { bool skip_if_fail; int (*get_nr)(void); const char *(*get_desc)(int subtest); } subtest; bool (*is_supported)(void); + void *priv; }; /* Tests */ -int test__vmlinux_matches_kallsyms(int subtest); -int test__openat_syscall_event(int subtest); -int test__openat_syscall_event_on_all_cpus(int subtest); -int test__basic_mmap(int subtest); -int test__PERF_RECORD(int subtest); -int test__perf_evsel__roundtrip_name_test(int subtest); -int test__perf_evsel__tp_sched_test(int subtest); -int test__syscall_openat_tp_fields(int subtest); -int test__pmu(int subtest); -int test__attr(int subtest); -int test__dso_data(int subtest); -int test__dso_data_cache(int subtest); -int test__dso_data_reopen(int subtest); -int test__parse_events(int subtest); -int test__hists_link(int subtest); -int test__python_use(int subtest); -int test__bp_signal(int subtest); -int test__bp_signal_overflow(int subtest); -int test__task_exit(int subtest); -int test__sw_clock_freq(int subtest); -int test__code_reading(int subtest); -int test__sample_parsing(int subtest); -int test__keep_tracking(int subtest); -int test__parse_no_sample_id_all(int subtest); -int test__dwarf_unwind(int subtest); -int test__expr(int subtest); -int test__hists_filter(int subtest); -int test__mmap_thread_lookup(int subtest); -int test__thread_mg_share(int subtest); -int test__hists_output(int subtest); -int test__hists_cumulate(int subtest); -int test__switch_tracking(int subtest); -int test__fdarray__filter(int subtest); -int test__fdarray__add(int subtest); -int test__kmod_path__parse(int subtest); -int test__thread_map(int subtest); -int test__llvm(int subtest); +int test__vmlinux_matches_kallsyms(struct test *test, int subtest); +int test__openat_syscall_event(struct test *test, int subtest); +int test__openat_syscall_event_on_all_cpus(struct test *test, int subtest); +int test__basic_mmap(struct test *test, int subtest); +int test__PERF_RECORD(struct test *test, int subtest); +int test__perf_evsel__roundtrip_name_test(struct test *test, int subtest); +int test__perf_evsel__tp_sched_test(struct test *test, int subtest); +int test__syscall_openat_tp_fields(struct test *test, int subtest); +int test__pmu(struct test *test, int subtest); +int test__attr(struct test *test, int subtest); +int test__dso_data(struct test *test, int subtest); +int test__dso_data_cache(struct test *test, int subtest); +int test__dso_data_reopen(struct test *test, int subtest); +int test__parse_events(struct test *test, int subtest); +int test__hists_link(struct test *test, int subtest); +int test__python_use(struct test *test, int subtest); +int test__bp_signal(struct test *test, int subtest); +int test__bp_signal_overflow(struct test *test, int subtest); +int test__task_exit(struct test *test, int subtest); +int test__mem(struct test *test, int subtest); +int test__sw_clock_freq(struct test *test, int subtest); +int test__code_reading(struct test *test, int subtest); +int test__sample_parsing(struct test *test, int subtest); +int test__keep_tracking(struct test *test, int subtest); +int test__parse_no_sample_id_all(struct test *test, int subtest); +int test__dwarf_unwind(struct test *test, int subtest); +int test__expr(struct test *test, int subtest); +int test__hists_filter(struct test *test, int subtest); +int test__mmap_thread_lookup(struct test *test, int subtest); +int test__thread_mg_share(struct test *test, int subtest); +int test__hists_output(struct test *test, int subtest); +int test__hists_cumulate(struct test *test, int subtest); +int test__switch_tracking(struct test *test, int subtest); +int test__fdarray__filter(struct test *test, int subtest); +int test__fdarray__add(struct test *test, int subtest); +int test__kmod_path__parse(struct test *test, int subtest); +int test__thread_map(struct test *test, int subtest); +int test__llvm(struct test *test, int subtest); const char *test__llvm_subtest_get_desc(int subtest); int test__llvm_subtest_get_nr(void); -int test__bpf(int subtest); +int test__bpf(struct test *test, int subtest); const char *test__bpf_subtest_get_desc(int subtest); int test__bpf_subtest_get_nr(void); -int test_session_topology(int subtest); -int test__thread_map_synthesize(int subtest); -int test__thread_map_remove(int subtest); -int test__cpu_map_synthesize(int subtest); -int test__synthesize_stat_config(int subtest); -int test__synthesize_stat(int subtest); -int test__synthesize_stat_round(int subtest); -int test__event_update(int subtest); -int test__event_times(int subtest); -int test__backward_ring_buffer(int subtest); -int test__cpu_map_print(int subtest); -int test__sdt_event(int subtest); -int test__is_printable_array(int subtest); -int test__bitmap_print(int subtest); -int test__perf_hooks(int subtest); -int test__clang(int subtest); +int test__session_topology(struct test *test, int subtest); +int test__thread_map_synthesize(struct test *test, int subtest); +int test__thread_map_remove(struct test *test, int subtest); +int test__cpu_map_synthesize(struct test *test, int subtest); +int test__synthesize_stat_config(struct test *test, int subtest); +int test__synthesize_stat(struct test *test, int subtest); +int test__synthesize_stat_round(struct test *test, int subtest); +int test__event_update(struct test *test, int subtest); +int test__event_times(struct test *test, int subtest); +int test__backward_ring_buffer(struct test *test, int subtest); +int test__cpu_map_print(struct test *test, int subtest); +int test__sdt_event(struct test *test, int subtest); +int test__is_printable_array(struct test *test, int subtest); +int test__bitmap_print(struct test *test, int subtest); +int test__perf_hooks(struct test *test, int subtest); +int test__clang(struct test *test, int subtest); const char *test__clang_subtest_get_desc(int subtest); int test__clang_subtest_get_nr(void); -int test__unit_number__scnprint(int subtest); +int test__unit_number__scnprint(struct test *test, int subtest); bool test__bp_signal_is_supported(void); diff --git a/tools/perf/tests/thread-map.c b/tools/perf/tests/thread-map.c index a63d6945807b..b3423c744f46 100644 --- a/tools/perf/tests/thread-map.c +++ b/tools/perf/tests/thread-map.c @@ -9,7 +9,7 @@ #define NAME (const char *) "perf" #define NAMEUL (unsigned long) NAME -int test__thread_map(int subtest __maybe_unused) +int test__thread_map(struct test *test __maybe_unused, int subtest __maybe_unused) { struct thread_map *map; @@ -76,7 +76,7 @@ static int process_event(struct perf_tool *tool __maybe_unused, return 0; } -int test__thread_map_synthesize(int subtest __maybe_unused) +int test__thread_map_synthesize(struct test *test __maybe_unused, int subtest __maybe_unused) { struct thread_map *threads; @@ -95,7 +95,7 @@ int test__thread_map_synthesize(int subtest __maybe_unused) return 0; } -int test__thread_map_remove(int subtest __maybe_unused) +int test__thread_map_remove(struct test *test __maybe_unused, int subtest __maybe_unused) { struct thread_map *threads; char *str; diff --git a/tools/perf/tests/thread-mg-share.c b/tools/perf/tests/thread-mg-share.c index 76686dd6f5ec..b9c7f58db6c4 100644 --- a/tools/perf/tests/thread-mg-share.c +++ b/tools/perf/tests/thread-mg-share.c @@ -4,7 +4,7 @@ #include "map.h" #include "debug.h" -int test__thread_mg_share(int subtest __maybe_unused) +int test__thread_mg_share(struct test *test __maybe_unused, int subtest __maybe_unused) { struct machines machines; struct machine *machine; diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c index 803f893550d6..19b0561fd6f6 100644 --- a/tools/perf/tests/topology.c +++ b/tools/perf/tests/topology.c @@ -86,7 +86,7 @@ static int check_cpu_topology(char *path, struct cpu_map *map) return 0; } -int test_session_topology(int subtest __maybe_unused) +int test__session_topology(struct test *test __maybe_unused, int subtest __maybe_unused) { char path[PATH_MAX]; struct cpu_map *map; diff --git a/tools/perf/tests/unit_number__scnprintf.c b/tools/perf/tests/unit_number__scnprintf.c index 44589de084b8..15cd1cf8c129 100644 --- a/tools/perf/tests/unit_number__scnprintf.c +++ b/tools/perf/tests/unit_number__scnprintf.c @@ -5,7 +5,7 @@ #include "units.h" #include "debug.h" -int test__unit_number__scnprint(int subtest __maybe_unused) +int test__unit_number__scnprint(struct test *t __maybe_unused, int subtest __maybe_unused) { struct { u64 n; diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c index 8456175fc234..86cb8868f67f 100644 --- a/tools/perf/tests/vmlinux-kallsyms.c +++ b/tools/perf/tests/vmlinux-kallsyms.c @@ -11,7 +11,7 @@ #define UM(x) kallsyms_map->unmap_ip(kallsyms_map, (x)) -int test__vmlinux_matches_kallsyms(int subtest __maybe_unused) +int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest __maybe_unused) { int err = -1; struct rb_node *nd; diff --git a/tools/perf/trace/beauty/Build b/tools/perf/trace/beauty/Build index be95ac6ce845..175d633c6b49 100644 --- a/tools/perf/trace/beauty/Build +++ b/tools/perf/trace/beauty/Build @@ -1 +1,7 @@ +libperf-y += clone.o +libperf-y += fcntl.o +ifeq ($(SRCARCH),$(filter $(SRCARCH),x86)) +libperf-y += ioctl.o +endif +libperf-y += pkey_alloc.o libperf-y += statx.o diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h index cf50be3f17a4..4b58581a6053 100644 --- a/tools/perf/trace/beauty/beauty.h +++ b/tools/perf/trace/beauty/beauty.h @@ -1,13 +1,44 @@ #ifndef _PERF_TRACE_BEAUTY_H #define _PERF_TRACE_BEAUTY_H +#include <linux/kernel.h> #include <linux/types.h> +struct strarray { + int offset; + int nr_entries; + const char **entries; +}; + +#define DEFINE_STRARRAY(array) struct strarray strarray__##array = { \ + .nr_entries = ARRAY_SIZE(array), \ + .entries = array, \ +} + +#define DEFINE_STRARRAY_OFFSET(array, off) struct strarray strarray__##array = { \ + .offset = off, \ + .nr_entries = ARRAY_SIZE(array), \ + .entries = array, \ +} + +size_t strarray__scnprintf(struct strarray *sa, char *bf, size_t size, const char *intfmt, int val); + struct trace; struct thread; +/** + * @val: value of syscall argument being formatted + * @args: All the args, use syscall_args__val(arg, nth) to access one + * @thread: tid state (maps, pid, tid, etc) + * @trace: 'perf trace' internals: all threads, etc + * @parm: private area, may be an strarray, for instance + * @idx: syscall arg idx (is this the first?) + * @mask: a syscall arg may mask another arg, see syscall_arg__scnprintf_futex_op + */ + struct syscall_arg { unsigned long val; + unsigned char *args; struct thread *thread; struct trace *trace; void *parm; @@ -15,10 +46,53 @@ struct syscall_arg { u8 mask; }; +unsigned long syscall_arg__val(struct syscall_arg *arg, u8 idx); + +size_t syscall_arg__scnprintf_strarrays(char *bf, size_t size, struct syscall_arg *arg); +#define SCA_STRARRAYS syscall_arg__scnprintf_strarrays + +size_t syscall_arg__scnprintf_fd(char *bf, size_t size, struct syscall_arg *arg); +#define SCA_FD syscall_arg__scnprintf_fd + +size_t syscall_arg__scnprintf_hex(char *bf, size_t size, struct syscall_arg *arg); +#define SCA_HEX syscall_arg__scnprintf_hex + +size_t syscall_arg__scnprintf_int(char *bf, size_t size, struct syscall_arg *arg); +#define SCA_INT syscall_arg__scnprintf_int + +size_t syscall_arg__scnprintf_long(char *bf, size_t size, struct syscall_arg *arg); +#define SCA_LONG syscall_arg__scnprintf_long + +size_t syscall_arg__scnprintf_pid(char *bf, size_t size, struct syscall_arg *arg); +#define SCA_PID syscall_arg__scnprintf_pid + +size_t syscall_arg__scnprintf_clone_flags(char *bf, size_t size, struct syscall_arg *arg); +#define SCA_CLONE_FLAGS syscall_arg__scnprintf_clone_flags + +size_t syscall_arg__scnprintf_fcntl_cmd(char *bf, size_t size, struct syscall_arg *arg); +#define SCA_FCNTL_CMD syscall_arg__scnprintf_fcntl_cmd + +size_t syscall_arg__scnprintf_fcntl_arg(char *bf, size_t size, struct syscall_arg *arg); +#define SCA_FCNTL_ARG syscall_arg__scnprintf_fcntl_arg + +size_t syscall_arg__scnprintf_ioctl_cmd(char *bf, size_t size, struct syscall_arg *arg); +#define SCA_IOCTL_CMD syscall_arg__scnprintf_ioctl_cmd + +size_t syscall_arg__scnprintf_pkey_alloc_access_rights(char *bf, size_t size, struct syscall_arg *arg); +#define SCA_PKEY_ALLOC_ACCESS_RIGHTS syscall_arg__scnprintf_pkey_alloc_access_rights + +size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size, struct syscall_arg *arg); +#define SCA_OPEN_FLAGS syscall_arg__scnprintf_open_flags + size_t syscall_arg__scnprintf_statx_flags(char *bf, size_t size, struct syscall_arg *arg); #define SCA_STATX_FLAGS syscall_arg__scnprintf_statx_flags size_t syscall_arg__scnprintf_statx_mask(char *bf, size_t size, struct syscall_arg *arg); #define SCA_STATX_MASK syscall_arg__scnprintf_statx_mask +size_t open__scnprintf_flags(unsigned long flags, char *bf, size_t size); + +void syscall_arg__set_ret_scnprintf(struct syscall_arg *arg, + size_t (*ret_scnprintf)(char *bf, size_t size, struct syscall_arg *arg)); + #endif /* _PERF_TRACE_BEAUTY_H */ diff --git a/tools/perf/trace/beauty/clone.c b/tools/perf/trace/beauty/clone.c new file mode 100644 index 000000000000..d64d049ab991 --- /dev/null +++ b/tools/perf/trace/beauty/clone.c @@ -0,0 +1,75 @@ +/* + * trace/beauty/cone.c + * + * Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> + * + * Released under the GPL v2. (and only v2, not any later version) + */ + +#include "trace/beauty/beauty.h" +#include <linux/kernel.h> +#include <sys/types.h> +#include <uapi/linux/sched.h> + +static size_t clone__scnprintf_flags(unsigned long flags, char *bf, size_t size) +{ + int printed = 0; + +#define P_FLAG(n) \ + if (flags & CLONE_##n) { \ + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ + flags &= ~CLONE_##n; \ + } + + P_FLAG(VM); + P_FLAG(FS); + P_FLAG(FILES); + P_FLAG(SIGHAND); + P_FLAG(PTRACE); + P_FLAG(VFORK); + P_FLAG(PARENT); + P_FLAG(THREAD); + P_FLAG(NEWNS); + P_FLAG(SYSVSEM); + P_FLAG(SETTLS); + P_FLAG(PARENT_SETTID); + P_FLAG(CHILD_CLEARTID); + P_FLAG(DETACHED); + P_FLAG(UNTRACED); + P_FLAG(CHILD_SETTID); + P_FLAG(NEWCGROUP); + P_FLAG(NEWUTS); + P_FLAG(NEWIPC); + P_FLAG(NEWUSER); + P_FLAG(NEWPID); + P_FLAG(NEWNET); + P_FLAG(IO); +#undef P_FLAG + + if (flags) + printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags); + + return printed; +} + +size_t syscall_arg__scnprintf_clone_flags(char *bf, size_t size, struct syscall_arg *arg) +{ + unsigned long flags = arg->val; + enum syscall_clone_args { + SCC_FLAGS = (1 << 0), + SCC_CHILD_STACK = (1 << 1), + SCC_PARENT_TIDPTR = (1 << 2), + SCC_CHILD_TIDPTR = (1 << 3), + SCC_TLS = (1 << 4), + }; + if (!(flags & CLONE_PARENT_SETTID)) + arg->mask |= SCC_PARENT_TIDPTR; + + if (!(flags & (CLONE_CHILD_SETTID | CLONE_CHILD_CLEARTID))) + arg->mask |= SCC_CHILD_TIDPTR; + + if (!(flags & CLONE_SETTLS)) + arg->mask |= SCC_TLS; + + return clone__scnprintf_flags(flags, bf, size); +} diff --git a/tools/perf/trace/beauty/drm_ioctl.sh b/tools/perf/trace/beauty/drm_ioctl.sh new file mode 100755 index 000000000000..2149d3a98e42 --- /dev/null +++ b/tools/perf/trace/beauty/drm_ioctl.sh @@ -0,0 +1,13 @@ +#!/bin/sh + +drm_header_dir=$1 +printf "#ifndef DRM_COMMAND_BASE\n" +grep "#define DRM_COMMAND_BASE" $drm_header_dir/drm.h +printf "#endif\n" + +printf "static const char *drm_ioctl_cmds[] = {\n" +grep "^#define DRM_IOCTL.*DRM_IO" $drm_header_dir/drm.h | \ + sed -r 's/^#define +DRM_IOCTL_([A-Z0-9_]+)[ ]+DRM_IO[A-Z]* *\( *(0x[[:xdigit:]]+),*.*/ [\2] = "\1",/g' +grep "^#define DRM_I915_[A-Z_0-9]\+[ ]\+0x" $drm_header_dir/i915_drm.h | \ + sed -r 's/^#define +DRM_I915_([A-Z0-9_]+)[ ]+(0x[[:xdigit:]]+)/\t[DRM_COMMAND_BASE + \2] = "I915_\1",/g' +printf "};\n" diff --git a/tools/perf/trace/beauty/fcntl.c b/tools/perf/trace/beauty/fcntl.c new file mode 100644 index 000000000000..9e8900c13cb1 --- /dev/null +++ b/tools/perf/trace/beauty/fcntl.c @@ -0,0 +1,100 @@ +/* + * trace/beauty/fcntl.c + * + * Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> + * + * Released under the GPL v2. (and only v2, not any later version) + */ + +#include "trace/beauty/beauty.h" +#include <linux/kernel.h> +#include <uapi/linux/fcntl.h> + +static size_t fcntl__scnprintf_getfd(unsigned long val, char *bf, size_t size) +{ + return scnprintf(bf, size, "%s", val ? "CLOEXEC" : "0"); +} + +static size_t syscall_arg__scnprintf_fcntl_getfd(char *bf, size_t size, struct syscall_arg *arg) +{ + return fcntl__scnprintf_getfd(arg->val, bf, size); +} + +static size_t fcntl__scnprintf_getlease(unsigned long val, char *bf, size_t size) +{ + static const char *fcntl_setlease[] = { "RDLCK", "WRLCK", "UNLCK", }; + static DEFINE_STRARRAY(fcntl_setlease); + + return strarray__scnprintf(&strarray__fcntl_setlease, bf, size, "%x", val); +} + +static size_t syscall_arg__scnprintf_fcntl_getlease(char *bf, size_t size, struct syscall_arg *arg) +{ + return fcntl__scnprintf_getlease(arg->val, bf, size); +} + +size_t syscall_arg__scnprintf_fcntl_cmd(char *bf, size_t size, struct syscall_arg *arg) +{ + if (arg->val == F_GETFL) { + syscall_arg__set_ret_scnprintf(arg, syscall_arg__scnprintf_open_flags); + goto mask_arg; + } + if (arg->val == F_GETFD) { + syscall_arg__set_ret_scnprintf(arg, syscall_arg__scnprintf_fcntl_getfd); + goto mask_arg; + } + if (arg->val == F_DUPFD_CLOEXEC || arg->val == F_DUPFD) { + syscall_arg__set_ret_scnprintf(arg, syscall_arg__scnprintf_fd); + goto out; + } + if (arg->val == F_GETOWN) { + syscall_arg__set_ret_scnprintf(arg, syscall_arg__scnprintf_pid); + goto mask_arg; + } + if (arg->val == F_GETLEASE) { + syscall_arg__set_ret_scnprintf(arg, syscall_arg__scnprintf_fcntl_getlease); + goto mask_arg; + } + /* + * Some commands ignore the third fcntl argument, "arg", so mask it + */ + if (arg->val == F_GET_SEALS || + arg->val == F_GETSIG) { +mask_arg: + arg->mask |= (1 << 2); + } +out: + return syscall_arg__scnprintf_strarrays(bf, size, arg); +} + +size_t syscall_arg__scnprintf_fcntl_arg(char *bf, size_t size, struct syscall_arg *arg) +{ + int cmd = syscall_arg__val(arg, 1); + + if (cmd == F_DUPFD) + return syscall_arg__scnprintf_fd(bf, size, arg); + + if (cmd == F_SETFD) + return fcntl__scnprintf_getfd(arg->val, bf, size); + + if (cmd == F_SETFL) + return open__scnprintf_flags(arg->val, bf, size); + + if (cmd == F_SETOWN) + return syscall_arg__scnprintf_pid(bf, size, arg); + + if (cmd == F_SETLEASE) + return fcntl__scnprintf_getlease(arg->val, bf, size); + /* + * We still don't grab the contents of pointers on entry or exit, + * so just print them as hex numbers + */ + if (cmd == F_SETLK || cmd == F_SETLKW || cmd == F_GETLK || + cmd == F_OFD_SETLK || cmd == F_OFD_SETLKW || cmd == F_OFD_GETLK || + cmd == F_GETOWN_EX || cmd == F_SETOWN_EX || + cmd == F_GET_RW_HINT || cmd == F_SET_RW_HINT || + cmd == F_GET_FILE_RW_HINT || cmd == F_SET_FILE_RW_HINT) + return syscall_arg__scnprintf_hex(bf, size, arg); + + return syscall_arg__scnprintf_long(bf, size, arg); +} diff --git a/tools/perf/trace/beauty/ioctl.c b/tools/perf/trace/beauty/ioctl.c new file mode 100644 index 000000000000..1be3b4cf0827 --- /dev/null +++ b/tools/perf/trace/beauty/ioctl.c @@ -0,0 +1,162 @@ +/* + * trace/beauty/ioctl.c + * + * Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> + * + * Released under the GPL v2. (and only v2, not any later version) + */ + +#include "trace/beauty/beauty.h" +#include <linux/kernel.h> + +/* + * FIXME: to support all arches we have to improve this, for + * now, to build on older systems without things like TIOCGEXCL, + * get it directly from our copy. + * + * Right now only x86 is being supported for beautifying ioctl args + * in 'perf trace', see tools/perf/trace/beauty/Build and builtin-trace.c + */ +#include <uapi/asm-generic/ioctls.h> + +static size_t ioctl__scnprintf_tty_cmd(int nr, int dir, char *bf, size_t size) +{ + static const char *ioctl_tty_cmd[] = { + "TCGETS", "TCSETS", "TCSETSW", "TCSETSF", "TCGETA", "TCSETA", "TCSETAW", + "TCSETAF", "TCSBRK", "TCXONC", "TCFLSH", "TIOCEXCL", "TIOCNXCL", "TIOCSCTTY", + "TIOCGPGRP", "TIOCSPGRP", "TIOCOUTQ", "TIOCSTI", "TIOCGWINSZ", "TIOCSWINSZ", + "TIOCMGET", "TIOCMBIS", "TIOCMBIC", "TIOCMSET", "TIOCGSOFTCAR", "TIOCSSOFTCAR", + "FIONREAD", "TIOCLINUX", "TIOCCONS", "TIOCGSERIAL", "TIOCSSERIAL", "TIOCPKT", + "FIONBIO", "TIOCNOTTY", "TIOCSETD", "TIOCGETD", "TCSBRKP", + [_IOC_NR(TIOCSBRK)] = "TIOCSBRK", "TIOCCBRK", "TIOCGSID", "TCGETS2", "TCSETS2", + "TCSETSW2", "TCSETSF2", "TIOCGRS48", "TIOCSRS485", "TIOCGPTN", "TIOCSPTLCK", + "TIOCGDEV", "TCSETX", "TCSETXF", "TCSETXW", "TIOCSIG", "TIOCVHANGUP", "TIOCGPKT", + "TIOCGPTLCK", [_IOC_NR(TIOCGEXCL)] = "TIOCGEXCL", "TIOCGPTPEER", + [_IOC_NR(FIONCLEX)] = "FIONCLEX", "FIOCLEX", "FIOASYNC", "TIOCSERCONFIG", + "TIOCSERGWILD", "TIOCSERSWILD", "TIOCGLCKTRMIOS", "TIOCSLCKTRMIOS", + "TIOCSERGSTRUCT", "TIOCSERGETLSR", "TIOCSERGETMULTI", "TIOCSERSETMULTI", + "TIOCMIWAIT", "TIOCGICOUNT", }; + static DEFINE_STRARRAY(ioctl_tty_cmd); + + if (nr < strarray__ioctl_tty_cmd.nr_entries && strarray__ioctl_tty_cmd.entries[nr] != NULL) + return scnprintf(bf, size, "%s", strarray__ioctl_tty_cmd.entries[nr]); + + return scnprintf(bf, size, "(%#x, %#x, %#x)", 'T', nr, dir); +} + +static size_t ioctl__scnprintf_drm_cmd(int nr, int dir, char *bf, size_t size) +{ +#include "trace/beauty/generated/ioctl/drm_ioctl_array.c" + static DEFINE_STRARRAY(drm_ioctl_cmds); + + if (nr < strarray__drm_ioctl_cmds.nr_entries && strarray__drm_ioctl_cmds.entries[nr] != NULL) + return scnprintf(bf, size, "DRM_%s", strarray__drm_ioctl_cmds.entries[nr]); + + return scnprintf(bf, size, "(%#x, %#x, %#x)", 'd', nr, dir); +} + +static size_t ioctl__scnprintf_sndrv_pcm_cmd(int nr, int dir, char *bf, size_t size) +{ +#include "trace/beauty/generated/ioctl/sndrv_pcm_ioctl_array.c" + static DEFINE_STRARRAY(sndrv_pcm_ioctl_cmds); + + if (nr < strarray__sndrv_pcm_ioctl_cmds.nr_entries && strarray__sndrv_pcm_ioctl_cmds.entries[nr] != NULL) + return scnprintf(bf, size, "SNDRV_PCM_%s", strarray__sndrv_pcm_ioctl_cmds.entries[nr]); + + return scnprintf(bf, size, "(%#x, %#x, %#x)", 'A', nr, dir); +} + +static size_t ioctl__scnprintf_sndrv_ctl_cmd(int nr, int dir, char *bf, size_t size) +{ +#include "trace/beauty/generated/ioctl/sndrv_ctl_ioctl_array.c" + static DEFINE_STRARRAY(sndrv_ctl_ioctl_cmds); + + if (nr < strarray__sndrv_ctl_ioctl_cmds.nr_entries && strarray__sndrv_ctl_ioctl_cmds.entries[nr] != NULL) + return scnprintf(bf, size, "SNDRV_CTL_%s", strarray__sndrv_ctl_ioctl_cmds.entries[nr]); + + return scnprintf(bf, size, "(%#x, %#x, %#x)", 'U', nr, dir); +} + +static size_t ioctl__scnprintf_kvm_cmd(int nr, int dir, char *bf, size_t size) +{ +#include "trace/beauty/generated/ioctl/kvm_ioctl_array.c" + static DEFINE_STRARRAY(kvm_ioctl_cmds); + + if (nr < strarray__kvm_ioctl_cmds.nr_entries && strarray__kvm_ioctl_cmds.entries[nr] != NULL) + return scnprintf(bf, size, "KVM_%s", strarray__kvm_ioctl_cmds.entries[nr]); + + return scnprintf(bf, size, "(%#x, %#x, %#x)", 0xAE, nr, dir); +} + +static size_t ioctl__scnprintf_vhost_virtio_cmd(int nr, int dir, char *bf, size_t size) +{ +#include "trace/beauty/generated/ioctl/vhost_virtio_ioctl_array.c" + static DEFINE_STRARRAY(vhost_virtio_ioctl_cmds); + static DEFINE_STRARRAY(vhost_virtio_ioctl_read_cmds); + struct strarray *s = (dir & _IOC_READ) ? &strarray__vhost_virtio_ioctl_read_cmds : &strarray__vhost_virtio_ioctl_cmds; + + if (nr < s->nr_entries && s->entries[nr] != NULL) + return scnprintf(bf, size, "VHOST_%s", s->entries[nr]); + + return scnprintf(bf, size, "(%#x, %#x, %#x)", 0xAF, nr, dir); +} + +static size_t ioctl__scnprintf_perf_cmd(int nr, int dir, char *bf, size_t size) +{ +#include "trace/beauty/generated/ioctl/perf_ioctl_array.c" + static DEFINE_STRARRAY(perf_ioctl_cmds); + + if (nr < strarray__perf_ioctl_cmds.nr_entries && strarray__perf_ioctl_cmds.entries[nr] != NULL) + return scnprintf(bf, size, "PERF_%s", strarray__perf_ioctl_cmds.entries[nr]); + + return scnprintf(bf, size, "(%#x, %#x, %#x)", 0xAE, nr, dir); +} + +static size_t ioctl__scnprintf_cmd(unsigned long cmd, char *bf, size_t size) +{ + int dir = _IOC_DIR(cmd), + type = _IOC_TYPE(cmd), + nr = _IOC_NR(cmd), + sz = _IOC_SIZE(cmd); + int printed = 0; + static const struct ioctl_type { + int type; + size_t (*scnprintf)(int nr, int dir, char *bf, size_t size); + } ioctl_types[] = { /* Must be ordered by type */ + { .type = '$', .scnprintf = ioctl__scnprintf_perf_cmd, }, + ['A' - '$'] = { .type = 'A', .scnprintf = ioctl__scnprintf_sndrv_pcm_cmd, }, + ['T' - '$'] = { .type = 'T', .scnprintf = ioctl__scnprintf_tty_cmd, }, + ['U' - '$'] = { .type = 'U', .scnprintf = ioctl__scnprintf_sndrv_ctl_cmd, }, + ['d' - '$'] = { .type = 'd', .scnprintf = ioctl__scnprintf_drm_cmd, }, + [0xAE - '$'] = { .type = 0xAE, .scnprintf = ioctl__scnprintf_kvm_cmd, }, + [0xAF - '$'] = { .type = 0xAF, .scnprintf = ioctl__scnprintf_vhost_virtio_cmd, }, + }; + const int nr_types = ARRAY_SIZE(ioctl_types); + + if (type >= ioctl_types[0].type && type <= ioctl_types[nr_types - 1].type) { + const int index = type - ioctl_types[0].type; + + if (ioctl_types[index].scnprintf != NULL) + return ioctl_types[index].scnprintf(nr, dir, bf, size); + } + + printed += scnprintf(bf + printed, size - printed, "%c", '('); + + if (dir == _IOC_NONE) { + printed += scnprintf(bf + printed, size - printed, "%s", "NONE"); + } else { + if (dir & _IOC_READ) + printed += scnprintf(bf + printed, size - printed, "%s", "READ"); + if (dir & _IOC_WRITE) + printed += scnprintf(bf + printed, size - printed, "%s%s", dir & _IOC_READ ? "|" : "", "WRITE"); + } + + return printed + scnprintf(bf + printed, size - printed, ", %#x, %#x, %#x)", type, nr, sz); +} + +size_t syscall_arg__scnprintf_ioctl_cmd(char *bf, size_t size, struct syscall_arg *arg) +{ + unsigned long cmd = arg->val; + + return ioctl__scnprintf_cmd(cmd, bf, size); +} diff --git a/tools/perf/trace/beauty/kvm_ioctl.sh b/tools/perf/trace/beauty/kvm_ioctl.sh new file mode 100755 index 000000000000..bd28817afced --- /dev/null +++ b/tools/perf/trace/beauty/kvm_ioctl.sh @@ -0,0 +1,11 @@ +#!/bin/sh + +kvm_header_dir=$1 + +printf "static const char *kvm_ioctl_cmds[] = {\n" +regex='^#[[:space:]]*define[[:space:]]+KVM_(\w+)[[:space:]]+_IO[RW]*\([[:space:]]*KVMIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*' +egrep $regex ${kvm_header_dir}/kvm.h | \ + sed -r "s/$regex/\2 \1/g" | \ + egrep -v " ((ARM|PPC|S390)_|[GS]ET_(DEBUGREGS|PIT2|XSAVE|TSC_KHZ)|CREATE_SPAPR_TCE_64)" | \ + sort | xargs printf "\t[%s] = \"%s\",\n" +printf "};\n" diff --git a/tools/perf/trace/beauty/mmap.c b/tools/perf/trace/beauty/mmap.c index af1cfde6b97b..754558f9009d 100644 --- a/tools/perf/trace/beauty/mmap.c +++ b/tools/perf/trace/beauty/mmap.c @@ -34,6 +34,9 @@ static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size, { int printed = 0, flags = arg->val; + if (flags & MAP_ANONYMOUS) + arg->mask |= (1 << 4) | (1 << 5); /* Mask 4th ('fd') and 5th ('offset') args, ignored */ + #define P_MMAP_FLAG(n) \ if (flags & MAP_##n) { \ printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ diff --git a/tools/perf/trace/beauty/open_flags.c b/tools/perf/trace/beauty/open_flags.c index f55a4597fc38..e359e041dc0e 100644 --- a/tools/perf/trace/beauty/open_flags.c +++ b/tools/perf/trace/beauty/open_flags.c @@ -14,13 +14,16 @@ #define O_NOATIME 01000000 #endif -static size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size, - struct syscall_arg *arg) -{ - int printed = 0, flags = arg->val; +#ifndef O_TMPFILE +#define O_TMPFILE 020000000 +#endif - if (!(flags & O_CREAT)) - arg->mask |= 1 << (arg->idx + 1); /* Mask the mode parm */ +#undef O_LARGEFILE +#define O_LARGEFILE 00100000 + +size_t open__scnprintf_flags(unsigned long flags, char *bf, size_t size) +{ + int printed = 0; if (flags == 0) return scnprintf(bf, size, "RDONLY"); @@ -30,6 +33,7 @@ static size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size, flags &= ~O_##n; \ } + P_FLAG(RDWR); P_FLAG(APPEND); P_FLAG(ASYNC); P_FLAG(CLOEXEC); @@ -38,6 +42,8 @@ static size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size, P_FLAG(DIRECTORY); P_FLAG(EXCL); P_FLAG(LARGEFILE); + P_FLAG(NOFOLLOW); + P_FLAG(TMPFILE); P_FLAG(NOATIME); P_FLAG(NOCTTY); #ifdef O_NONBLOCK @@ -48,7 +54,6 @@ static size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size, #ifdef O_PATH P_FLAG(PATH); #endif - P_FLAG(RDWR); #ifdef O_DSYNC if ((flags & O_SYNC) == O_SYNC) printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", "SYNC"); @@ -68,4 +73,12 @@ static size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size, return printed; } -#define SCA_OPEN_FLAGS syscall_arg__scnprintf_open_flags +size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size, struct syscall_arg *arg) +{ + int flags = arg->val; + + if (!(flags & O_CREAT)) + arg->mask |= 1 << (arg->idx + 1); /* Mask the mode parm */ + + return open__scnprintf_flags(flags, bf, size); +} diff --git a/tools/perf/trace/beauty/perf_ioctl.sh b/tools/perf/trace/beauty/perf_ioctl.sh new file mode 100755 index 000000000000..faea4237c793 --- /dev/null +++ b/tools/perf/trace/beauty/perf_ioctl.sh @@ -0,0 +1,10 @@ +#!/bin/sh + +header_dir=$1 + +printf "static const char *perf_ioctl_cmds[] = {\n" +regex='^#[[:space:]]*define[[:space:]]+PERF_EVENT_IOC_(\w+)[[:space:]]+_IO[RW]*[[:space:]]*\([[:space:]]*.\$.[[:space:]]*,[[:space:]]*([[:digit:]]+).*' +egrep $regex ${header_dir}/perf_event.h | \ + sed -r "s/$regex/\2 \1/g" | \ + sort | xargs printf "\t[%s] = \"%s\",\n" +printf "};\n" diff --git a/tools/perf/trace/beauty/pid.c b/tools/perf/trace/beauty/pid.c index 07486ea65ae3..b6d419e16dcf 100644 --- a/tools/perf/trace/beauty/pid.c +++ b/tools/perf/trace/beauty/pid.c @@ -1,4 +1,4 @@ -static size_t syscall_arg__scnprintf_pid(char *bf, size_t size, struct syscall_arg *arg) +size_t syscall_arg__scnprintf_pid(char *bf, size_t size, struct syscall_arg *arg) { int pid = arg->val; struct trace *trace = arg->trace; @@ -17,5 +17,3 @@ static size_t syscall_arg__scnprintf_pid(char *bf, size_t size, struct syscall_a return printed; } - -#define SCA_PID syscall_arg__scnprintf_pid diff --git a/tools/perf/trace/beauty/pkey_alloc.c b/tools/perf/trace/beauty/pkey_alloc.c new file mode 100644 index 000000000000..2ba784a3734a --- /dev/null +++ b/tools/perf/trace/beauty/pkey_alloc.c @@ -0,0 +1,50 @@ +/* + * trace/beauty/pkey_alloc.c + * + * Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> + * + * Released under the GPL v2. (and only v2, not any later version) + */ + +#include "trace/beauty/beauty.h" +#include <linux/kernel.h> +#include <linux/log2.h> + +static size_t pkey_alloc__scnprintf_access_rights(int access_rights, char *bf, size_t size) +{ + int i, printed = 0; + +#include "trace/beauty/generated/pkey_alloc_access_rights_array.c" + static DEFINE_STRARRAY(pkey_alloc_access_rights); + + if (access_rights == 0) { + const char *s = strarray__pkey_alloc_access_rights.entries[0]; + if (s) + return scnprintf(bf, size, "%s", s); + return scnprintf(bf, size, "%d", 0); + } + + for (i = 1; i < strarray__pkey_alloc_access_rights.nr_entries; ++i) { + int bit = 1 << (i - 1); + + if (!(access_rights & bit)) + continue; + + if (printed != 0) + printed += scnprintf(bf + printed, size - printed, "|"); + + if (strarray__pkey_alloc_access_rights.entries[i] != NULL) + printed += scnprintf(bf + printed, size - printed, "%s", strarray__pkey_alloc_access_rights.entries[i]); + else + printed += scnprintf(bf + printed, size - printed, "0x%#", bit); + } + + return printed; +} + +size_t syscall_arg__scnprintf_pkey_alloc_access_rights(char *bf, size_t size, struct syscall_arg *arg) +{ + unsigned long cmd = arg->val; + + return pkey_alloc__scnprintf_access_rights(cmd, bf, size); +} diff --git a/tools/perf/trace/beauty/pkey_alloc_access_rights.sh b/tools/perf/trace/beauty/pkey_alloc_access_rights.sh new file mode 100755 index 000000000000..62e51a02b839 --- /dev/null +++ b/tools/perf/trace/beauty/pkey_alloc_access_rights.sh @@ -0,0 +1,10 @@ +#!/bin/sh + +header_dir=$1 + +printf "static const char *pkey_alloc_access_rights[] = {\n" +regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+PKEY_([[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*' +egrep $regex ${header_dir}/mman-common.h | \ + sed -r "s/$regex/\2 \2 \1/g" | \ + sort | xargs printf "\t[%s ? (ilog2(%s) + 1) : 0] = \"%s\",\n" +printf "};\n" diff --git a/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh new file mode 100755 index 000000000000..aad5ab130539 --- /dev/null +++ b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh @@ -0,0 +1,8 @@ +#!/bin/sh + +sound_header_dir=$1 + +printf "static const char *sndrv_ctl_ioctl_cmds[] = {\n" +grep "^#define[\t ]\+SNDRV_CTL_IOCTL_" $sound_header_dir/asound.h | \ + sed -r 's/^#define +SNDRV_CTL_IOCTL_([A-Z0-9_]+)[\t ]+_IO[RW]*\( *.U., *(0x[[:xdigit:]]+),?.*/\t[\2] = \"\1\",/g' +printf "};\n" diff --git a/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh new file mode 100755 index 000000000000..b7e9ef6b2f55 --- /dev/null +++ b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh @@ -0,0 +1,8 @@ +#!/bin/sh + +sound_header_dir=$1 + +printf "static const char *sndrv_pcm_ioctl_cmds[] = {\n" +grep "^#define[\t ]\+SNDRV_PCM_IOCTL_" $sound_header_dir/asound.h | \ + sed -r 's/^#define +SNDRV_PCM_IOCTL_([A-Z0-9_]+)[\t ]+_IO[RW]*\( *.A., *(0x[[:xdigit:]]+),?.*/\t[\2] = \"\1\",/g' +printf "};\n" diff --git a/tools/perf/trace/beauty/vhost_virtio_ioctl.sh b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh new file mode 100755 index 000000000000..76f1de697787 --- /dev/null +++ b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh @@ -0,0 +1,17 @@ +#!/bin/sh + +vhost_virtio_header_dir=$1 + +printf "static const char *vhost_virtio_ioctl_cmds[] = {\n" +regex='^#[[:space:]]*define[[:space:]]+VHOST_(\w+)[[:space:]]+_IOW?\([[:space:]]*VHOST_VIRTIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*' +egrep $regex ${vhost_virtio_header_dir}/vhost.h | \ + sed -r "s/$regex/\2 \1/g" | \ + sort | xargs printf "\t[%s] = \"%s\",\n" +printf "};\n" + +printf "static const char *vhost_virtio_ioctl_read_cmds[] = {\n" +regex='^#[[:space:]]*define[[:space:]]+VHOST_(\w+)[[:space:]]+_IOW?R\([[:space:]]*VHOST_VIRTIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*' +egrep $regex ${vhost_virtio_header_dir}/vhost.h | \ + sed -r "s/$regex/\2 \1/g" | \ + sort | xargs printf "\t[%s] = \"%s\",\n" +printf "};\n" diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c index a4d3762cd825..d0c2007c307b 100644 --- a/tools/perf/ui/browser.c +++ b/tools/perf/ui/browser.c @@ -8,6 +8,7 @@ #include <linux/compiler.h> #include <linux/list.h> #include <linux/rbtree.h> +#include <linux/string.h> #include <stdlib.h> #include <sys/ttydefaults.h> #include "browser.h" @@ -563,7 +564,7 @@ static int ui_browser__color_config(const char *var, const char *value, int i; /* same dir for all commands */ - if (prefixcmp(var, "colors.") != 0) + if (!strstarts(var, "colors.") != 0) return 0; for (i = 0; ui_browser__colorsets[i].name != NULL; ++i) { @@ -704,7 +705,7 @@ static void __ui_browser__line_arrow_down(struct ui_browser *browser, ui_browser__gotorc(browser, row, column + 1); SLsmg_draw_hline(2); - if (row++ == 0) + if (++row == 0) goto out; } else row = 0; @@ -738,6 +739,35 @@ void __ui_browser__line_arrow(struct ui_browser *browser, unsigned int column, __ui_browser__line_arrow_down(browser, column, start, end); } +void ui_browser__mark_fused(struct ui_browser *browser, unsigned int column, + unsigned int row, bool arrow_down) +{ + unsigned int end_row; + + if (row >= browser->top_idx) + end_row = row - browser->top_idx; + else + return; + + SLsmg_set_char_set(1); + + if (arrow_down) { + ui_browser__gotorc(browser, end_row, column - 1); + SLsmg_write_char(SLSMG_ULCORN_CHAR); + ui_browser__gotorc(browser, end_row, column); + SLsmg_draw_hline(2); + ui_browser__gotorc(browser, end_row + 1, column - 1); + SLsmg_write_char(SLSMG_LTEE_CHAR); + } else { + ui_browser__gotorc(browser, end_row, column - 1); + SLsmg_write_char(SLSMG_LTEE_CHAR); + ui_browser__gotorc(browser, end_row, column); + SLsmg_draw_hline(2); + } + + SLsmg_set_char_set(0); +} + void ui_browser__init(void) { int i = 0; diff --git a/tools/perf/ui/browser.h b/tools/perf/ui/browser.h index be3b70eb5fca..a12eff75638b 100644 --- a/tools/perf/ui/browser.h +++ b/tools/perf/ui/browser.h @@ -43,6 +43,8 @@ void ui_browser__printf(struct ui_browser *browser, const char *fmt, ...); void ui_browser__write_graph(struct ui_browser *browser, int graph); void __ui_browser__line_arrow(struct ui_browser *browser, unsigned int column, u64 start, u64 end); +void ui_browser__mark_fused(struct ui_browser *browser, unsigned int column, + unsigned int row, bool arrow_down); void __ui_browser__show_title(struct ui_browser *browser, const char *title); void ui_browser__show_title(struct ui_browser *browser, const char *title); int ui_browser__show(struct ui_browser *browser, const char *title, diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index d990ad08a3c6..786fecaf578e 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -9,14 +9,16 @@ #include "../../util/symbol.h" #include "../../util/evsel.h" #include "../../util/config.h" +#include "../../util/evlist.h" #include <inttypes.h> #include <pthread.h> #include <linux/kernel.h> +#include <linux/string.h> #include <sys/ttydefaults.h> struct disasm_line_samples { - double percent; - u64 nr; + double percent; + struct sym_hist_entry he; }; #define IPC_WIDTH 6 @@ -40,18 +42,22 @@ static struct annotate_browser_opt { jump_arrows, show_linenr, show_nr_jumps, + show_nr_samples, show_total_period; } annotate_browser__opts = { .use_offset = true, .jump_arrows = true, }; +struct arch; + struct annotate_browser { struct ui_browser b; struct rb_root entries; struct rb_node *curr_hot; struct disasm_line *selection; struct disasm_line **offsets; + struct arch *arch; int nr_events; u64 start; int nr_asm_entries; @@ -105,11 +111,12 @@ static int annotate_browser__set_jumps_percent_color(struct annotate_browser *br static int annotate_browser__pcnt_width(struct annotate_browser *ab) { - int w = 7 * ab->nr_events; + return (annotate_browser__opts.show_total_period ? 12 : 7) * ab->nr_events; +} - if (ab->have_cycles) - w += IPC_WIDTH + CYCLES_WIDTH; - return w; +static int annotate_browser__cycles_width(struct annotate_browser *ab) +{ + return ab->have_cycles ? IPC_WIDTH + CYCLES_WIDTH : 0; } static void annotate_browser__write(struct ui_browser *browser, void *entry, int row) @@ -122,46 +129,67 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int (!current_entry || (browser->use_navkeypressed && !browser->navkeypressed))); int width = browser->width, printed; - int i, pcnt_width = annotate_browser__pcnt_width(ab); + int i, pcnt_width = annotate_browser__pcnt_width(ab), + cycles_width = annotate_browser__cycles_width(ab); double percent_max = 0.0; char bf[256]; + bool show_title = false; for (i = 0; i < ab->nr_events; i++) { if (bdl->samples[i].percent > percent_max) percent_max = bdl->samples[i].percent; } + if ((row == 0) && (dl->offset == -1 || percent_max == 0.0)) { + if (ab->have_cycles) { + if (dl->ipc == 0.0 && dl->cycles == 0) + show_title = true; + } else + show_title = true; + } + if (dl->offset != -1 && percent_max != 0.0) { - if (percent_max != 0.0) { - for (i = 0; i < ab->nr_events; i++) { - ui_browser__set_percent_color(browser, - bdl->samples[i].percent, - current_entry); - if (annotate_browser__opts.show_total_period) { - ui_browser__printf(browser, "%6" PRIu64 " ", - bdl->samples[i].nr); - } else { - ui_browser__printf(browser, "%6.2f ", - bdl->samples[i].percent); - } + for (i = 0; i < ab->nr_events; i++) { + ui_browser__set_percent_color(browser, + bdl->samples[i].percent, + current_entry); + if (annotate_browser__opts.show_total_period) { + ui_browser__printf(browser, "%11" PRIu64 " ", + bdl->samples[i].he.period); + } else if (annotate_browser__opts.show_nr_samples) { + ui_browser__printf(browser, "%6" PRIu64 " ", + bdl->samples[i].he.nr_samples); + } else { + ui_browser__printf(browser, "%6.2f ", + bdl->samples[i].percent); } - } else { - ui_browser__write_nstring(browser, " ", 7 * ab->nr_events); } } else { ui_browser__set_percent_color(browser, 0, current_entry); - ui_browser__write_nstring(browser, " ", 7 * ab->nr_events); + + if (!show_title) + ui_browser__write_nstring(browser, " ", pcnt_width); + else { + ui_browser__printf(browser, "%*s", pcnt_width, + annotate_browser__opts.show_total_period ? "Period" : + annotate_browser__opts.show_nr_samples ? "Samples" : "Percent"); + } } if (ab->have_cycles) { if (dl->ipc) ui_browser__printf(browser, "%*.2f ", IPC_WIDTH - 1, dl->ipc); - else + else if (!show_title) ui_browser__write_nstring(browser, " ", IPC_WIDTH); + else + ui_browser__printf(browser, "%*s ", IPC_WIDTH - 1, "IPC"); + if (dl->cycles) ui_browser__printf(browser, "%*" PRIu64 " ", CYCLES_WIDTH - 1, dl->cycles); - else + else if (!show_title) ui_browser__write_nstring(browser, " ", CYCLES_WIDTH); + else + ui_browser__printf(browser, "%*s ", CYCLES_WIDTH - 1, "Cycle"); } SLsmg_write_char(' '); @@ -171,7 +199,7 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int width += 1; if (!*dl->line) - ui_browser__write_nstring(browser, " ", width - pcnt_width); + ui_browser__write_nstring(browser, " ", width - pcnt_width - cycles_width); else if (dl->offset == -1) { if (dl->line_nr && annotate_browser__opts.show_linenr) printed = scnprintf(bf, sizeof(bf), "%-*d ", @@ -180,7 +208,7 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int printed = scnprintf(bf, sizeof(bf), "%*s ", ab->addr_width, " "); ui_browser__write_nstring(browser, bf, printed); - ui_browser__write_nstring(browser, dl->line, width - printed - pcnt_width + 1); + ui_browser__write_nstring(browser, dl->line, width - printed - pcnt_width - cycles_width + 1); } else { u64 addr = dl->offset; int color = -1; @@ -237,7 +265,7 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int } disasm_line__scnprintf(dl, bf, sizeof(bf), !annotate_browser__opts.use_offset); - ui_browser__write_nstring(browser, bf, width - pcnt_width - 3 - printed); + ui_browser__write_nstring(browser, bf, width - pcnt_width - cycles_width - 3 - printed); } if (current_entry) @@ -255,6 +283,25 @@ static bool disasm_line__is_valid_jump(struct disasm_line *dl, struct symbol *sy return true; } +static bool is_fused(struct annotate_browser *ab, struct disasm_line *cursor) +{ + struct disasm_line *pos = list_prev_entry(cursor, node); + const char *name; + + if (!pos) + return false; + + if (ins__is_lock(&pos->ins)) + name = pos->ops.locked.ins.name; + else + name = pos->ins.name; + + if (!name || !cursor->ins.name) + return false; + + return ins__is_fused(ab->arch, name, cursor->ins.name); +} + static void annotate_browser__draw_current_jump(struct ui_browser *browser) { struct annotate_browser *ab = container_of(browser, struct annotate_browser, b); @@ -290,6 +337,13 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser) ui_browser__set_color(browser, HE_COLORSET_JUMP_ARROWS); __ui_browser__line_arrow(browser, pcnt_width + 2 + ab->addr_width, from, to); + + if (is_fused(ab, cursor)) { + ui_browser__mark_fused(browser, + pcnt_width + 3 + ab->addr_width, + from - 1, + to > from ? true : false); + } } static unsigned int annotate_browser__refresh(struct ui_browser *browser) @@ -405,14 +459,14 @@ static void annotate_browser__calc_percent(struct annotate_browser *browser, next = disasm__get_next_ip_line(¬es->src->source, pos); for (i = 0; i < browser->nr_events; i++) { - u64 nr_samples; + struct sym_hist_entry sample; bpos->samples[i].percent = disasm__calc_percent(notes, evsel->idx + i, pos->offset, next ? next->offset : len, - &path, &nr_samples); - bpos->samples[i].nr = nr_samples; + &path, &sample); + bpos->samples[i].he = sample; if (max_percent < bpos->samples[i].percent) max_percent = bpos->samples[i].percent; @@ -775,13 +829,14 @@ static int annotate_browser__run(struct annotate_browser *browser, "q/ESC/CTRL+C Exit\n\n" "ENTER Go to target\n" "ESC Exit\n" - "H Cycle thru hottest instructions\n" + "H Go to hottest instruction\n" + "TAB/shift+TAB Cycle thru hottest instructions\n" "j Toggle showing jump to target arrows\n" "J Toggle showing number of jump sources on targets\n" "n Search next string\n" "o Toggle disassembler output/simplified view\n" "s Toggle source code view\n" - "t Toggle total period view\n" + "t Circulate percent, total period, samples view\n" "/ Search string\n" "k Toggle line numbers\n" "r Run available scripts\n" @@ -858,8 +913,13 @@ show_sup_ins: } continue; case 't': - annotate_browser__opts.show_total_period = - !annotate_browser__opts.show_total_period; + if (annotate_browser__opts.show_total_period) { + annotate_browser__opts.show_total_period = false; + annotate_browser__opts.show_nr_samples = true; + } else if (annotate_browser__opts.show_nr_samples) + annotate_browser__opts.show_nr_samples = false; + else + annotate_browser__opts.show_total_period = true; annotate_browser__update_addr_width(browser); continue; case K_LEFT: @@ -882,9 +942,11 @@ out: int map_symbol__tui_annotate(struct map_symbol *ms, struct perf_evsel *evsel, struct hist_browser_timer *hbt) { - /* Set default value for show_total_period. */ + /* Set default value for show_total_period and show_nr_samples */ annotate_browser__opts.show_total_period = - symbol_conf.show_total_period; + symbol_conf.show_total_period; + annotate_browser__opts.show_nr_samples = + symbol_conf.show_nr_samples; return symbol__tui_annotate(ms->sym, ms->map, evsel, hbt); } @@ -1056,7 +1118,9 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, (nr_pcnt - 1); } - err = symbol__disassemble(sym, map, perf_evsel__env_arch(evsel), sizeof_bdl); + err = symbol__disassemble(sym, map, perf_evsel__env_arch(evsel), + sizeof_bdl, &browser.arch, + perf_evsel__env_cpuid(evsel)); if (err) { char msg[BUFSIZ]; symbol__strerror_disassemble(sym, map, err, msg, sizeof(msg)); @@ -1133,6 +1197,7 @@ static struct annotate_config { ANNOTATE_CFG(jump_arrows), ANNOTATE_CFG(show_linenr), ANNOTATE_CFG(show_nr_jumps), + ANNOTATE_CFG(show_nr_samples), ANNOTATE_CFG(show_total_period), ANNOTATE_CFG(use_offset), }; @@ -1152,7 +1217,7 @@ static int annotate__config(const char *var, const char *value, struct annotate_config *cfg; const char *name; - if (prefixcmp(var, "annotate.") != 0) + if (!strstarts(var, "annotate.")) return 0; name = var + 9; diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 69f4570bd4f9..13dfb0a0bdeb 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -166,9 +166,6 @@ static struct inline_node *inline_node__create(struct map *map, u64 ip) if (dso == NULL) return NULL; - if (dso->kernel != DSO_TYPE_USER) - return NULL; - node = dso__parse_addr_inlines(dso, map__rip_2objdump(map, ip)); @@ -934,12 +931,8 @@ static int hist_browser__show_callchain_list(struct hist_browser *browser, browser->show_dso); if (symbol_conf.show_branchflag_count) { - if (need_percent) - callchain_list_counts__printf_value(node, chain, NULL, - buf, sizeof(buf)); - else - callchain_list_counts__printf_value(NULL, chain, NULL, - buf, sizeof(buf)); + callchain_list_counts__printf_value(chain, NULL, + buf, sizeof(buf)); if (asprintf(&alloc_str2, "%s%s", str, buf) < 0) str = "Not enough memory!"; diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c index e99ba86158d2..02176193f427 100644 --- a/tools/perf/ui/gtk/annotate.c +++ b/tools/perf/ui/gtk/annotate.c @@ -34,10 +34,10 @@ static int perf_gtk__get_percent(char *buf, size_t size, struct symbol *sym, return 0; symhist = annotation__histogram(symbol__annotation(sym), evidx); - if (!symbol_conf.event_group && !symhist->addr[dl->offset]) + if (!symbol_conf.event_group && !symhist->addr[dl->offset].nr_samples) return 0; - percent = 100.0 * symhist->addr[dl->offset] / symhist->sum; + percent = 100.0 * symhist->addr[dl->offset].nr_samples / symhist->nr_samples; markup = perf_gtk__get_percent_color(percent); if (markup) @@ -168,7 +168,8 @@ static int symbol__gtk_annotate(struct symbol *sym, struct map *map, if (map->dso->annotate_warned) return -1; - err = symbol__disassemble(sym, map, perf_evsel__env_arch(evsel), 0); + err = symbol__disassemble(sym, map, perf_evsel__env_arch(evsel), + 0, NULL, NULL); if (err) { char msg[BUFSIZ]; symbol__strerror_disassemble(sym, map, err, msg, sizeof(msg)); diff --git a/tools/perf/ui/progress.c b/tools/perf/ui/progress.c index a0f24c7115c5..ae91c8148edf 100644 --- a/tools/perf/ui/progress.c +++ b/tools/perf/ui/progress.c @@ -1,3 +1,4 @@ +#include <linux/kernel.h> #include "../cache.h" #include "progress.h" @@ -14,10 +15,14 @@ struct ui_progress_ops *ui_progress__ops = &null_progress__ops; void ui_progress__update(struct ui_progress *p, u64 adv) { + u64 last = p->curr; + p->curr += adv; if (p->curr >= p->next) { - p->next += p->step; + u64 nr = DIV_ROUND_UP(p->curr - last, p->step); + + p->next += nr * p->step; ui_progress__ops->update(p); } } @@ -25,7 +30,7 @@ void ui_progress__update(struct ui_progress *p, u64 adv) void ui_progress__init(struct ui_progress *p, u64 total, const char *title) { p->curr = 0; - p->next = p->step = total / 16; + p->next = p->step = total / 16 ?: 1; p->total = total; p->title = title; diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c index 42e432bd2eb4..8bdb7a500181 100644 --- a/tools/perf/ui/stdio/hist.c +++ b/tools/perf/ui/stdio/hist.c @@ -1,4 +1,5 @@ #include <stdio.h> +#include <linux/string.h> #include "../../util/util.h" #include "../../util/hist.h" @@ -35,9 +36,6 @@ static size_t inline__fprintf(struct map *map, u64 ip, int left_margin, if (dso == NULL) return 0; - if (dso->kernel != DSO_TYPE_USER) - return 0; - node = dso__parse_addr_inlines(dso, map__rip_2objdump(map, ip)); if (node == NULL) @@ -126,12 +124,8 @@ static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_node *node, str = callchain_list__sym_name(chain, bf, sizeof(bf), false); if (symbol_conf.show_branchflag_count) { - if (!period) - callchain_list_counts__printf_value(node, chain, NULL, - buf, sizeof(buf)); - else - callchain_list_counts__printf_value(NULL, chain, NULL, - buf, sizeof(buf)); + callchain_list_counts__printf_value(chain, NULL, + buf, sizeof(buf)); if (asprintf(&alloc_str, "%s%s", str, buf) < 0) str = "Not enough memory!"; @@ -295,7 +289,7 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root, * displayed twice. */ if (!i++ && field_order == NULL && - sort_order && !prefixcmp(sort_order, "sym")) + sort_order && strstarts(sort_order, "sym")) continue; if (!printed) { @@ -315,7 +309,7 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root, if (symbol_conf.show_branchflag_count) ret += callchain_list_counts__printf_value( - NULL, chain, fp, NULL, 0); + chain, fp, NULL, 0); ret += fprintf(fp, "\n"); if (++entries_printed == callchain_param.print_limit) diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 79dea95a7f68..94518c1bf8b6 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -22,6 +22,7 @@ libperf-y += rbtree.o libperf-y += libstring.o libperf-y += bitmap.o libperf-y += hweight.o +libperf-y += smt.o libperf-y += quote.o libperf-y += strbuf.o libperf-y += string.o @@ -93,6 +94,7 @@ libperf-y += drv_configs.o libperf-y += units.o libperf-y += time-utils.o libperf-y += expr-bison.o +libperf-y += branch.o libperf-$(CONFIG_LIBBPF) += bpf-loader.o libperf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o @@ -104,6 +106,10 @@ ifndef CONFIG_LIBELF libperf-y += symbol-minimal.o endif +ifndef CONFIG_SETNS +libperf-y += setns.o +endif + libperf-$(CONFIG_DWARF) += probe-finder.o libperf-$(CONFIG_DWARF) += dwarf-aux.o libperf-$(CONFIG_DWARF) += dwarf-regs.o diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index ddbd56df9187..4397a8b6e6cd 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -47,7 +47,12 @@ struct arch { bool sorted_instructions; bool initialized; void *priv; + unsigned int model; + unsigned int family; int (*init)(struct arch *arch); + bool (*ins_is_fused)(struct arch *arch, const char *ins1, + const char *ins2); + int (*cpuid_parse)(struct arch *arch, char *cpuid); struct { char comment_char; char skip_functions_char; @@ -129,6 +134,8 @@ static struct arch architectures[] = { .name = "x86", .instructions = x86__instructions, .nr_instructions = ARRAY_SIZE(x86__instructions), + .ins_is_fused = x86__ins_is_fused, + .cpuid_parse = x86__cpuid_parse, .objdump = { .comment_char = '#', }, @@ -171,6 +178,14 @@ int ins__scnprintf(struct ins *ins, char *bf, size_t size, return ins__raw_scnprintf(ins, bf, size, ops); } +bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2) +{ + if (!arch || !arch->ins_is_fused) + return false; + + return arch->ins_is_fused(arch, ins1, ins2); +} + static int call__parse(struct arch *arch, struct ins_operands *ops, struct map *map) { char *endptr, *tok, *name; @@ -502,6 +517,11 @@ bool ins__is_ret(const struct ins *ins) return ins->ops == &ret_ops; } +bool ins__is_lock(const struct ins *ins) +{ + return ins->ops == &lock_ops; +} + static int ins__key_cmp(const void *name, const void *insp) { const struct ins *ins = insp; @@ -590,10 +610,10 @@ int symbol__alloc_hist(struct symbol *sym) size_t sizeof_sym_hist; /* Check for overflow when calculating sizeof_sym_hist */ - if (size > (SIZE_MAX - sizeof(struct sym_hist)) / sizeof(u64)) + if (size > (SIZE_MAX - sizeof(struct sym_hist)) / sizeof(struct sym_hist_entry)) return -1; - sizeof_sym_hist = (sizeof(struct sym_hist) + size * sizeof(u64)); + sizeof_sym_hist = (sizeof(struct sym_hist) + size * sizeof(struct sym_hist_entry)); /* Check for overflow in zalloc argument */ if (sizeof_sym_hist > (SIZE_MAX - sizeof(*notes->src)) @@ -677,7 +697,8 @@ static int __symbol__account_cycles(struct annotation *notes, } static int __symbol__inc_addr_samples(struct symbol *sym, struct map *map, - struct annotation *notes, int evidx, u64 addr) + struct annotation *notes, int evidx, u64 addr, + struct perf_sample *sample) { unsigned offset; struct sym_hist *h; @@ -693,12 +714,15 @@ static int __symbol__inc_addr_samples(struct symbol *sym, struct map *map, offset = addr - sym->start; h = annotation__histogram(notes, evidx); - h->sum++; - h->addr[offset]++; + h->nr_samples++; + h->addr[offset].nr_samples++; + h->period += sample->period; + h->addr[offset].period += sample->period; pr_debug3("%#" PRIx64 " %s: period++ [addr: %#" PRIx64 ", %#" PRIx64 - ", evidx=%d] => %" PRIu64 "\n", sym->start, sym->name, - addr, addr - sym->start, evidx, h->addr[offset]); + ", evidx=%d] => nr_samples: %" PRIu64 ", period: %" PRIu64 "\n", + sym->start, sym->name, addr, addr - sym->start, evidx, + h->addr[offset].nr_samples, h->addr[offset].period); return 0; } @@ -718,7 +742,8 @@ static struct annotation *symbol__get_annotation(struct symbol *sym, bool cycles } static int symbol__inc_addr_samples(struct symbol *sym, struct map *map, - int evidx, u64 addr) + int evidx, u64 addr, + struct perf_sample *sample) { struct annotation *notes; @@ -727,7 +752,7 @@ static int symbol__inc_addr_samples(struct symbol *sym, struct map *map, notes = symbol__get_annotation(sym, false); if (notes == NULL) return -ENOMEM; - return __symbol__inc_addr_samples(sym, map, notes, evidx, addr); + return __symbol__inc_addr_samples(sym, map, notes, evidx, addr, sample); } static int symbol__account_cycles(u64 addr, u64 start, @@ -791,14 +816,16 @@ int addr_map_symbol__account_cycles(struct addr_map_symbol *ams, return err; } -int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, int evidx) +int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, struct perf_sample *sample, + int evidx) { - return symbol__inc_addr_samples(ams->sym, ams->map, evidx, ams->al_addr); + return symbol__inc_addr_samples(ams->sym, ams->map, evidx, ams->al_addr, sample); } -int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 ip) +int hist_entry__inc_addr_samples(struct hist_entry *he, struct perf_sample *sample, + int evidx, u64 ip) { - return symbol__inc_addr_samples(he->ms.sym, he->ms.map, evidx, ip); + return symbol__inc_addr_samples(he->ms.sym, he->ms.map, evidx, ip, sample); } static void disasm_line__init_ins(struct disasm_line *dl, struct arch *arch, struct map *map) @@ -908,11 +935,12 @@ struct disasm_line *disasm__get_next_ip_line(struct list_head *head, struct disa } double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset, - s64 end, const char **path, u64 *nr_samples) + s64 end, const char **path, struct sym_hist_entry *sample) { struct source_line *src_line = notes->src->lines; double percent = 0.0; - *nr_samples = 0; + + sample->nr_samples = sample->period = 0; if (src_line) { size_t sizeof_src_line = sizeof(*src_line) + @@ -926,19 +954,24 @@ double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset, *path = src_line->path; percent += src_line->samples[evidx].percent; - *nr_samples += src_line->samples[evidx].nr; + sample->nr_samples += src_line->samples[evidx].nr; offset++; } } else { struct sym_hist *h = annotation__histogram(notes, evidx); unsigned int hits = 0; + u64 period = 0; - while (offset < end) - hits += h->addr[offset++]; + while (offset < end) { + hits += h->addr[offset].nr_samples; + period += h->addr[offset].period; + ++offset; + } - if (h->sum) { - *nr_samples = hits; - percent = 100.0 * hits / h->sum; + if (h->nr_samples) { + sample->period = period; + sample->nr_samples = hits; + percent = 100.0 * hits / h->nr_samples; } } @@ -1037,10 +1070,10 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st if (dl->offset != -1) { const char *path = NULL; - u64 nr_samples; double percent, max_percent = 0.0; double *ppercents = &percent; - u64 *psamples = &nr_samples; + struct sym_hist_entry sample; + struct sym_hist_entry *psamples = &sample; int i, nr_percent = 1; const char *color; struct annotation *notes = symbol__annotation(sym); @@ -1054,7 +1087,7 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st if (perf_evsel__is_group_event(evsel)) { nr_percent = evsel->nr_members; ppercents = calloc(nr_percent, sizeof(double)); - psamples = calloc(nr_percent, sizeof(u64)); + psamples = calloc(nr_percent, sizeof(struct sym_hist_entry)); if (ppercents == NULL || psamples == NULL) { return -1; } @@ -1065,10 +1098,10 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st notes->src->lines ? i : evsel->idx + i, offset, next ? next->offset : (s64) len, - &path, &nr_samples); + &path, &sample); ppercents[i] = percent; - psamples[i] = nr_samples; + psamples[i] = sample; if (percent > max_percent) max_percent = percent; } @@ -1106,12 +1139,15 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st for (i = 0; i < nr_percent; i++) { percent = ppercents[i]; - nr_samples = psamples[i]; + sample = psamples[i]; color = get_percent_color(percent); if (symbol_conf.show_total_period) + color_fprintf(stdout, color, " %11" PRIu64, + sample.period); + else if (symbol_conf.show_nr_samples) color_fprintf(stdout, color, " %7" PRIu64, - nr_samples); + sample.nr_samples); else color_fprintf(stdout, color, " %7.2f", percent); } @@ -1127,13 +1163,13 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st if (ppercents != &percent) free(ppercents); - if (psamples != &nr_samples) + if (psamples != &sample) free(psamples); } else if (max_lines && printed >= max_lines) return 1; else { - int width = 8; + int width = symbol_conf.show_total_period ? 12 : 8; if (queue) return -1; @@ -1327,7 +1363,7 @@ static int dso__disassemble_filename(struct dso *dso, char *filename, size_t fil !dso__is_kcore(dso)) return SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX; - build_id_filename = dso__build_id_filename(dso, NULL, 0); + build_id_filename = dso__build_id_filename(dso, NULL, 0, false); if (build_id_filename) { __symbol__join_symfs(filename, filename_size, build_id_filename); free(build_id_filename); @@ -1379,7 +1415,9 @@ static const char *annotate__norm_arch(const char *arch_name) return normalize_arch((char *)arch_name); } -int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_name, size_t privsize) +int symbol__disassemble(struct symbol *sym, struct map *map, + const char *arch_name, size_t privsize, + struct arch **parch, char *cpuid) { struct dso *dso = map->dso; char command[PATH_MAX * 2]; @@ -1405,6 +1443,9 @@ int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_na if (arch == NULL) return -ENOTSUP; + if (parch) + *parch = arch; + if (arch->init) { err = arch->init(arch); if (err) { @@ -1413,6 +1454,9 @@ int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_na } } + if (arch->cpuid_parse && cpuid) + arch->cpuid_parse(arch, cpuid); + pr_debug("%s: filename=%s, sym=%s, start=%#" PRIx64 ", end=%#" PRIx64 "\n", __func__, symfs_filename, sym->name, map->unmap_ip(map, sym->start), map->unmap_ip(map, sym->end)); @@ -1643,19 +1687,19 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map, struct sym_hist *h = annotation__histogram(notes, evidx); struct rb_root tmp_root = RB_ROOT; int nr_pcnt = 1; - u64 h_sum = h->sum; + u64 nr_samples = h->nr_samples; size_t sizeof_src_line = sizeof(struct source_line); if (perf_evsel__is_group_event(evsel)) { for (i = 1; i < evsel->nr_members; i++) { h = annotation__histogram(notes, evidx + i); - h_sum += h->sum; + nr_samples += h->nr_samples; } nr_pcnt = evsel->nr_members; sizeof_src_line += (nr_pcnt - 1) * sizeof(src_line->samples); } - if (!h_sum) + if (!nr_samples) return 0; src_line = notes->src->lines = calloc(len, sizeof_src_line); @@ -1665,7 +1709,7 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map, start = map__rip_2objdump(map, sym->start); for (i = 0; i < len; i++) { - u64 offset, nr_samples; + u64 offset; double percent_max = 0.0; src_line->nr_pcnt = nr_pcnt; @@ -1674,9 +1718,9 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map, double percent = 0.0; h = annotation__histogram(notes, evidx + k); - nr_samples = h->addr[i]; - if (h->sum) - percent = 100.0 * nr_samples / h->sum; + nr_samples = h->addr[i].nr_samples; + if (h->nr_samples) + percent = 100.0 * nr_samples / h->nr_samples; if (percent > percent_max) percent_max = percent; @@ -1745,10 +1789,10 @@ static void symbol__annotate_hits(struct symbol *sym, struct perf_evsel *evsel) u64 len = symbol__size(sym), offset; for (offset = 0; offset < len; ++offset) - if (h->addr[offset] != 0) + if (h->addr[offset].nr_samples != 0) printf("%*" PRIx64 ": %" PRIu64 "\n", BITS_PER_LONG / 2, - sym->start + offset, h->addr[offset]); - printf("%*s: %" PRIu64 "\n", BITS_PER_LONG / 2, "h->sum", h->sum); + sym->start + offset, h->addr[offset].nr_samples); + printf("%*s: %" PRIu64 "\n", BITS_PER_LONG / 2, "h->nr_samples", h->nr_samples); } int symbol__annotate_printf(struct symbol *sym, struct map *map, @@ -1766,7 +1810,7 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map, int printed = 2, queue_len = 0; int more = 0; u64 len; - int width = 8; + int width = symbol_conf.show_total_period ? 12 : 8; int graph_dotted_len; filename = strdup(dso->long_name); @@ -1784,7 +1828,9 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map, width *= evsel->nr_members; graph_dotted_len = printf(" %-*.*s| Source code & Disassembly of %s for %s (%" PRIu64 " samples)\n", - width, width, "Percent", d_filename, evsel_name, h->sum); + width, width, symbol_conf.show_total_period ? "Period" : + symbol_conf.show_nr_samples ? "Samples" : "Percent", + d_filename, evsel_name, h->nr_samples); printf("%-*.*s----\n", graph_dotted_len, graph_dotted_len, graph_dotted_line); @@ -1848,10 +1894,10 @@ void symbol__annotate_decay_histogram(struct symbol *sym, int evidx) struct sym_hist *h = annotation__histogram(notes, evidx); int len = symbol__size(sym), offset; - h->sum = 0; + h->nr_samples = 0; for (offset = 0; offset < len; ++offset) { - h->addr[offset] = h->addr[offset] * 7 / 8; - h->sum += h->addr[offset]; + h->addr[offset].nr_samples = h->addr[offset].nr_samples * 7 / 8; + h->nr_samples += h->addr[offset].nr_samples; } } @@ -1901,7 +1947,8 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map, struct rb_root source_line = RB_ROOT; u64 len; - if (symbol__disassemble(sym, map, perf_evsel__env_arch(evsel), 0) < 0) + if (symbol__disassemble(sym, map, perf_evsel__env_arch(evsel), + 0, NULL, NULL) < 0) return -1; len = symbol__size(sym); diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 948aa8e6fd39..9ce575c25fd9 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -52,7 +52,9 @@ struct ins_ops { bool ins__is_jump(const struct ins *ins); bool ins__is_call(const struct ins *ins); bool ins__is_ret(const struct ins *ins); +bool ins__is_lock(const struct ins *ins); int ins__scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops); +bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2); struct annotation; @@ -72,16 +74,22 @@ static inline bool disasm_line__has_offset(const struct disasm_line *dl) return dl->ops.target.offset_avail; } +struct sym_hist_entry { + u64 nr_samples; + u64 period; +}; + void disasm_line__free(struct disasm_line *dl); struct disasm_line *disasm__get_next_ip_line(struct list_head *head, struct disasm_line *pos); int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw); size_t disasm__fprintf(struct list_head *head, FILE *fp); double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset, - s64 end, const char **path, u64 *nr_samples); + s64 end, const char **path, struct sym_hist_entry *sample); struct sym_hist { - u64 sum; - u64 addr[0]; + u64 nr_samples; + u64 period; + struct sym_hist_entry addr[0]; }; struct cyc_hist { @@ -147,18 +155,22 @@ static inline struct annotation *symbol__annotation(struct symbol *sym) return (void *)sym - symbol_conf.priv_size; } -int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, int evidx); +int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, struct perf_sample *sample, + int evidx); int addr_map_symbol__account_cycles(struct addr_map_symbol *ams, struct addr_map_symbol *start, unsigned cycles); -int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 addr); +int hist_entry__inc_addr_samples(struct hist_entry *he, struct perf_sample *sample, + int evidx, u64 addr); int symbol__alloc_hist(struct symbol *sym); void symbol__annotate_zero_histograms(struct symbol *sym); -int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_name, size_t privsize); +int symbol__disassemble(struct symbol *sym, struct map *map, + const char *arch_name, size_t privsize, + struct arch **parch, char *cpuid); enum symbol_disassemble_errno { SYMBOL_ANNOTATE_ERRNO__SUCCESS = 0, diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index 0daf63b9ee3e..5547457566a7 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -322,6 +322,13 @@ static int auxtrace_queues__add_event_buffer(struct auxtrace_queues *queues, return auxtrace_queues__add_buffer(queues, idx, buffer); } +static bool filter_cpu(struct perf_session *session, int cpu) +{ + unsigned long *cpu_bitmap = session->itrace_synth_opts->cpu_bitmap; + + return cpu_bitmap && cpu != -1 && !test_bit(cpu, cpu_bitmap); +} + int auxtrace_queues__add_event(struct auxtrace_queues *queues, struct perf_session *session, union perf_event *event, off_t data_offset, @@ -331,6 +338,9 @@ int auxtrace_queues__add_event(struct auxtrace_queues *queues, unsigned int idx; int err; + if (filter_cpu(session, event->auxtrace.cpu)) + return 0; + buffer = zalloc(sizeof(struct auxtrace_buffer)); if (!buffer) return -ENOMEM; @@ -947,6 +957,8 @@ void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts) synth_opts->instructions = true; synth_opts->branches = true; synth_opts->transactions = true; + synth_opts->ptwrites = true; + synth_opts->pwr_events = true; synth_opts->errors = true; synth_opts->period_type = PERF_ITRACE_DEFAULT_PERIOD_TYPE; synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD; @@ -1030,6 +1042,12 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str, case 'x': synth_opts->transactions = true; break; + case 'w': + synth_opts->ptwrites = true; + break; + case 'p': + synth_opts->pwr_events = true; + break; case 'e': synth_opts->errors = true; break; diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h index 9f0de72d58e2..33b5e6cdf38c 100644 --- a/tools/perf/util/auxtrace.h +++ b/tools/perf/util/auxtrace.h @@ -59,6 +59,8 @@ enum itrace_period_type { * @instructions: whether to synthesize 'instructions' events * @branches: whether to synthesize 'branches' events * @transactions: whether to synthesize events for transactions + * @ptwrites: whether to synthesize events for ptwrites + * @pwr_events: whether to synthesize power events * @errors: whether to synthesize decoder error events * @dont_decode: whether to skip decoding entirely * @log: write a decoding log @@ -72,6 +74,7 @@ enum itrace_period_type { * @period: 'instructions' events period * @period_type: 'instructions' events period type * @initial_skip: skip N events at the beginning. + * @cpu_bitmap: CPUs for which to synthesize events, or NULL for all */ struct itrace_synth_opts { bool set; @@ -79,6 +82,8 @@ struct itrace_synth_opts { bool instructions; bool branches; bool transactions; + bool ptwrites; + bool pwr_events; bool errors; bool dont_decode; bool log; @@ -92,6 +97,7 @@ struct itrace_synth_opts { unsigned long long period; enum itrace_period_type period_type; unsigned long initial_skip; + unsigned long *cpu_bitmap; }; /** diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c index 4bd2d1d882af..4a1264c66101 100644 --- a/tools/perf/util/bpf-loader.c +++ b/tools/perf/util/bpf-loader.c @@ -1246,7 +1246,7 @@ int bpf__config_obj(struct bpf_object *obj, if (!obj || !term || !term->config) return -EINVAL; - if (!prefixcmp(term->config, "map:")) { + if (strstarts(term->config, "map:")) { key_scan_pos = sizeof("map:") - 1; err = bpf__obj_config_map(obj, term, evlist, &key_scan_pos); goto out; diff --git a/tools/perf/util/bpf-prologue.c b/tools/perf/util/bpf-prologue.c index 1356220a9f1b..827f9140f3b8 100644 --- a/tools/perf/util/bpf-prologue.c +++ b/tools/perf/util/bpf-prologue.c @@ -58,6 +58,46 @@ check_pos(struct bpf_insn_pos *pos) return 0; } +/* + * Convert type string (u8/u16/u32/u64/s8/s16/s32/s64 ..., see + * Documentation/trace/kprobetrace.txt) to size field of BPF_LDX_MEM + * instruction (BPF_{B,H,W,DW}). + */ +static int +argtype_to_ldx_size(const char *type) +{ + int arg_size = type ? atoi(&type[1]) : 64; + + switch (arg_size) { + case 8: + return BPF_B; + case 16: + return BPF_H; + case 32: + return BPF_W; + case 64: + default: + return BPF_DW; + } +} + +static const char * +insn_sz_to_str(int insn_sz) +{ + switch (insn_sz) { + case BPF_B: + return "BPF_B"; + case BPF_H: + return "BPF_H"; + case BPF_W: + return "BPF_W"; + case BPF_DW: + return "BPF_DW"; + default: + return "UNKNOWN"; + } +} + /* Give it a shorter name */ #define ins(i, p) append_insn((i), (p)) @@ -258,9 +298,14 @@ gen_prologue_slowpath(struct bpf_insn_pos *pos, } /* Final pass: read to registers */ - for (i = 0; i < nargs; i++) - ins(BPF_LDX_MEM(BPF_DW, BPF_PROLOGUE_START_ARG_REG + i, + for (i = 0; i < nargs; i++) { + int insn_sz = (args[i].ref) ? argtype_to_ldx_size(args[i].type) : BPF_DW; + + pr_debug("prologue: load arg %d, insn_sz is %s\n", + i, insn_sz_to_str(insn_sz)); + ins(BPF_LDX_MEM(insn_sz, BPF_PROLOGUE_START_ARG_REG + i, BPF_REG_FP, -BPF_REG_SIZE * (i + 1)), pos); + } ins(BPF_JMP_IMM(BPF_JA, BPF_REG_0, 0, JMP_TO_SUCCESS_CODE), pos); diff --git a/tools/perf/util/branch.c b/tools/perf/util/branch.c new file mode 100644 index 000000000000..a4fce2729e50 --- /dev/null +++ b/tools/perf/util/branch.c @@ -0,0 +1,147 @@ +#include "perf.h" +#include "util/util.h" +#include "util/debug.h" +#include "util/branch.h" + +static bool cross_area(u64 addr1, u64 addr2, int size) +{ + u64 align1, align2; + + align1 = addr1 & ~(size - 1); + align2 = addr2 & ~(size - 1); + + return (align1 != align2) ? true : false; +} + +#define AREA_4K 4096 +#define AREA_2M (2 * 1024 * 1024) + +void branch_type_count(struct branch_type_stat *st, struct branch_flags *flags, + u64 from, u64 to) +{ + if (flags->type == PERF_BR_UNKNOWN || from == 0) + return; + + st->counts[flags->type]++; + + if (flags->type == PERF_BR_COND) { + if (to > from) + st->cond_fwd++; + else + st->cond_bwd++; + } + + if (cross_area(from, to, AREA_2M)) + st->cross_2m++; + else if (cross_area(from, to, AREA_4K)) + st->cross_4k++; +} + +const char *branch_type_name(int type) +{ + const char *branch_names[PERF_BR_MAX] = { + "N/A", + "COND", + "UNCOND", + "IND", + "CALL", + "IND_CALL", + "RET", + "SYSCALL", + "SYSRET", + "COND_CALL", + "COND_RET" + }; + + if (type >= 0 && type < PERF_BR_MAX) + return branch_names[type]; + + return NULL; +} + +void branch_type_stat_display(FILE *fp, struct branch_type_stat *st) +{ + u64 total = 0; + int i; + + for (i = 0; i < PERF_BR_MAX; i++) + total += st->counts[i]; + + if (total == 0) + return; + + fprintf(fp, "\n#"); + fprintf(fp, "\n# Branch Statistics:"); + fprintf(fp, "\n#"); + + if (st->cond_fwd > 0) { + fprintf(fp, "\n%8s: %5.1f%%", + "COND_FWD", + 100.0 * (double)st->cond_fwd / (double)total); + } + + if (st->cond_bwd > 0) { + fprintf(fp, "\n%8s: %5.1f%%", + "COND_BWD", + 100.0 * (double)st->cond_bwd / (double)total); + } + + if (st->cross_4k > 0) { + fprintf(fp, "\n%8s: %5.1f%%", + "CROSS_4K", + 100.0 * (double)st->cross_4k / (double)total); + } + + if (st->cross_2m > 0) { + fprintf(fp, "\n%8s: %5.1f%%", + "CROSS_2M", + 100.0 * (double)st->cross_2m / (double)total); + } + + for (i = 0; i < PERF_BR_MAX; i++) { + if (st->counts[i] > 0) + fprintf(fp, "\n%8s: %5.1f%%", + branch_type_name(i), + 100.0 * + (double)st->counts[i] / (double)total); + } +} + +static int count_str_scnprintf(int idx, const char *str, char *bf, int size) +{ + return scnprintf(bf, size, "%s%s", (idx) ? " " : " (", str); +} + +int branch_type_str(struct branch_type_stat *st, char *bf, int size) +{ + int i, j = 0, printed = 0; + u64 total = 0; + + for (i = 0; i < PERF_BR_MAX; i++) + total += st->counts[i]; + + if (total == 0) + return 0; + + if (st->cond_fwd > 0) + printed += count_str_scnprintf(j++, "COND_FWD", bf + printed, size - printed); + + if (st->cond_bwd > 0) + printed += count_str_scnprintf(j++, "COND_BWD", bf + printed, size - printed); + + for (i = 0; i < PERF_BR_MAX; i++) { + if (i == PERF_BR_COND) + continue; + + if (st->counts[i] > 0) + printed += count_str_scnprintf(j++, branch_type_name(i), bf + printed, size - printed); + } + + if (st->cross_4k > 0) + printed += count_str_scnprintf(j++, "CROSS_4K", bf + printed, size - printed); + + if (st->cross_2m > 0) + printed += count_str_scnprintf(j++, "CROSS_2M", bf + printed, size - printed); + + return printed; +} diff --git a/tools/perf/util/branch.h b/tools/perf/util/branch.h new file mode 100644 index 000000000000..1e3c7c5cdc63 --- /dev/null +++ b/tools/perf/util/branch.h @@ -0,0 +1,25 @@ +#ifndef _PERF_BRANCH_H +#define _PERF_BRANCH_H 1 + +#include <stdint.h> +#include "../perf.h" + +struct branch_type_stat { + bool branch_to; + u64 counts[PERF_BR_MAX]; + u64 cond_fwd; + u64 cond_bwd; + u64 cross_4k; + u64 cross_2m; +}; + +struct branch_flags; + +void branch_type_count(struct branch_type_stat *st, struct branch_flags *flags, + u64 from, u64 to); + +const char *branch_type_name(int type); +void branch_type_stat_display(FILE *fp, struct branch_type_stat *st); +int branch_type_str(struct branch_type_stat *st, char *bf, int bfsize); + +#endif /* _PERF_BRANCH_H */ diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index e0148b081bdf..c1a06fcd7e70 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -243,12 +243,15 @@ static bool build_id_cache__valid_id(char *sbuild_id) return result; } -static const char *build_id_cache__basename(bool is_kallsyms, bool is_vdso) +static const char *build_id_cache__basename(bool is_kallsyms, bool is_vdso, + bool is_debug) { - return is_kallsyms ? "kallsyms" : (is_vdso ? "vdso" : "elf"); + return is_kallsyms ? "kallsyms" : (is_vdso ? "vdso" : (is_debug ? + "debug" : "elf")); } -char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size) +char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size, + bool is_debug) { bool is_kallsyms = dso__is_kallsyms((struct dso *)dso); bool is_vdso = dso__is_vdso((struct dso *)dso); @@ -270,7 +273,8 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size) ret = asnprintf(&bf, size, "%s", linkname); else ret = asnprintf(&bf, size, "%s/%s", linkname, - build_id_cache__basename(is_kallsyms, is_vdso)); + build_id_cache__basename(is_kallsyms, is_vdso, + is_debug)); if (ret < 0 || (!alloc && size < (unsigned int)ret)) bf = NULL; free(linkname); @@ -285,7 +289,7 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size) else static int write_buildid(const char *name, size_t name_len, u8 *build_id, - pid_t pid, u16 misc, int fd) + pid_t pid, u16 misc, struct feat_fd *fd) { int err; struct build_id_event b; @@ -300,14 +304,15 @@ static int write_buildid(const char *name, size_t name_len, u8 *build_id, b.header.misc = misc; b.header.size = sizeof(b) + len; - err = writen(fd, &b, sizeof(b)); + err = do_write(fd, &b, sizeof(b)); if (err < 0) return err; return write_padded(fd, name, name_len + 1, len); } -static int machine__write_buildid_table(struct machine *machine, int fd) +static int machine__write_buildid_table(struct machine *machine, + struct feat_fd *fd) { int err = 0; char nm[PATH_MAX]; @@ -352,7 +357,8 @@ static int machine__write_buildid_table(struct machine *machine, int fd) return err; } -int perf_session__write_buildid_table(struct perf_session *session, int fd) +int perf_session__write_buildid_table(struct perf_session *session, + struct feat_fd *fd) { struct rb_node *nd; int err = machine__write_buildid_table(&session->machines.host, fd); @@ -534,13 +540,14 @@ char *build_id_cache__complement(const char *incomplete_sbuild_id) } char *build_id_cache__cachedir(const char *sbuild_id, const char *name, - bool is_kallsyms, bool is_vdso) + struct nsinfo *nsi, bool is_kallsyms, + bool is_vdso) { char *realname = (char *)name, *filename; bool slash = is_kallsyms || is_vdso; if (!slash) { - realname = realpath(name, NULL); + realname = nsinfo__realpath(name, nsi); if (!realname) return NULL; } @@ -556,13 +563,13 @@ char *build_id_cache__cachedir(const char *sbuild_id, const char *name, return filename; } -int build_id_cache__list_build_ids(const char *pathname, +int build_id_cache__list_build_ids(const char *pathname, struct nsinfo *nsi, struct strlist **result) { char *dir_name; int ret = 0; - dir_name = build_id_cache__cachedir(NULL, pathname, false, false); + dir_name = build_id_cache__cachedir(NULL, pathname, nsi, false, false); if (!dir_name) return -ENOMEM; @@ -576,16 +583,20 @@ int build_id_cache__list_build_ids(const char *pathname, #if defined(HAVE_LIBELF_SUPPORT) && defined(HAVE_GELF_GETNOTE_SUPPORT) static int build_id_cache__add_sdt_cache(const char *sbuild_id, - const char *realname) + const char *realname, + struct nsinfo *nsi) { struct probe_cache *cache; int ret; + struct nscookie nsc; - cache = probe_cache__new(sbuild_id); + cache = probe_cache__new(sbuild_id, nsi); if (!cache) return -1; + nsinfo__mountns_enter(nsi, &nsc); ret = probe_cache__scan_sdt(cache, realname); + nsinfo__mountns_exit(&nsc); if (ret >= 0) { pr_debug4("Found %d SDTs in %s\n", ret, realname); if (probe_cache__commit(cache) < 0) @@ -595,25 +606,56 @@ static int build_id_cache__add_sdt_cache(const char *sbuild_id, return ret; } #else -#define build_id_cache__add_sdt_cache(sbuild_id, realname) (0) +#define build_id_cache__add_sdt_cache(sbuild_id, realname, nsi) (0) #endif +static char *build_id_cache__find_debug(const char *sbuild_id, + struct nsinfo *nsi) +{ + char *realname = NULL; + char *debugfile; + struct nscookie nsc; + size_t len = 0; + + debugfile = calloc(1, PATH_MAX); + if (!debugfile) + goto out; + + len = __symbol__join_symfs(debugfile, PATH_MAX, + "/usr/lib/debug/.build-id/"); + snprintf(debugfile + len, PATH_MAX - len, "%.2s/%s.debug", sbuild_id, + sbuild_id + 2); + + nsinfo__mountns_enter(nsi, &nsc); + realname = realpath(debugfile, NULL); + if (realname && access(realname, R_OK)) + zfree(&realname); + nsinfo__mountns_exit(&nsc); +out: + free(debugfile); + return realname; +} + int build_id_cache__add_s(const char *sbuild_id, const char *name, - bool is_kallsyms, bool is_vdso) + struct nsinfo *nsi, bool is_kallsyms, bool is_vdso) { const size_t size = PATH_MAX; char *realname = NULL, *filename = NULL, *dir_name = NULL, *linkname = zalloc(size), *tmp; + char *debugfile = NULL; int err = -1; if (!is_kallsyms) { - realname = realpath(name, NULL); + if (!is_vdso) + realname = nsinfo__realpath(name, nsi); + else + realname = realpath(name, NULL); if (!realname) goto out_free; } - dir_name = build_id_cache__cachedir(sbuild_id, name, - is_kallsyms, is_vdso); + dir_name = build_id_cache__cachedir(sbuild_id, name, nsi, is_kallsyms, + is_vdso); if (!dir_name) goto out_free; @@ -627,20 +669,52 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name, /* Save the allocated buildid dirname */ if (asprintf(&filename, "%s/%s", dir_name, - build_id_cache__basename(is_kallsyms, is_vdso)) < 0) { + build_id_cache__basename(is_kallsyms, is_vdso, + false)) < 0) { filename = NULL; goto out_free; } if (access(filename, F_OK)) { if (is_kallsyms) { - if (copyfile("/proc/kallsyms", filename)) + if (copyfile("/proc/kallsyms", filename)) + goto out_free; + } else if (nsi && nsi->need_setns) { + if (copyfile_ns(name, filename, nsi)) goto out_free; } else if (link(realname, filename) && errno != EEXIST && copyfile(name, filename)) goto out_free; } + /* Some binaries are stripped, but have .debug files with their symbol + * table. Check to see if we can locate one of those, since the elf + * file itself may not be very useful to users of our tools without a + * symtab. + */ + if (!is_kallsyms && !is_vdso && + strncmp(".ko", name + strlen(name) - 3, 3)) { + debugfile = build_id_cache__find_debug(sbuild_id, nsi); + if (debugfile) { + zfree(&filename); + if (asprintf(&filename, "%s/%s", dir_name, + build_id_cache__basename(false, false, true)) < 0) { + filename = NULL; + goto out_free; + } + if (access(filename, F_OK)) { + if (nsi && nsi->need_setns) { + if (copyfile_ns(debugfile, filename, + nsi)) + goto out_free; + } else if (link(debugfile, filename) && + errno != EEXIST && + copyfile(debugfile, filename)) + goto out_free; + } + } + } + if (!build_id_cache__linkname(sbuild_id, linkname, size)) goto out_free; tmp = strrchr(linkname, '/'); @@ -657,27 +731,30 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name, err = 0; /* Update SDT cache : error is just warned */ - if (realname && build_id_cache__add_sdt_cache(sbuild_id, realname) < 0) + if (realname && + build_id_cache__add_sdt_cache(sbuild_id, realname, nsi) < 0) pr_debug4("Failed to update/scan SDT cache for %s\n", realname); out_free: if (!is_kallsyms) free(realname); free(filename); + free(debugfile); free(dir_name); free(linkname); return err; } static int build_id_cache__add_b(const u8 *build_id, size_t build_id_size, - const char *name, bool is_kallsyms, - bool is_vdso) + const char *name, struct nsinfo *nsi, + bool is_kallsyms, bool is_vdso) { char sbuild_id[SBUILD_ID_SIZE]; build_id__sprintf(build_id, build_id_size, sbuild_id); - return build_id_cache__add_s(sbuild_id, name, is_kallsyms, is_vdso); + return build_id_cache__add_s(sbuild_id, name, nsi, is_kallsyms, + is_vdso); } bool build_id_cache__cached(const char *sbuild_id) @@ -743,7 +820,7 @@ static int dso__cache_build_id(struct dso *dso, struct machine *machine) name = nm; } return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id), name, - is_kallsyms, is_vdso); + dso->nsinfo, is_kallsyms, is_vdso); } static int __dsos__cache_build_ids(struct list_head *head, diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h index 96690a55c62c..c94b0dcbfd74 100644 --- a/tools/perf/util/build-id.h +++ b/tools/perf/util/build-id.h @@ -5,10 +5,12 @@ #define SBUILD_ID_SIZE (BUILD_ID_SIZE * 2 + 1) #include "tool.h" +#include "namespaces.h" #include <linux/types.h> extern struct perf_tool build_id__mark_dso_hit_ops; struct dso; +struct feat_fd; int build_id__sprintf(const u8 *build_id, int len, char *bf); int sysfs__sprintf_build_id(const char *root_dir, char *sbuild_id); @@ -16,7 +18,8 @@ int filename__sprintf_build_id(const char *pathname, char *sbuild_id); char *build_id_cache__kallsyms_path(const char *sbuild_id, char *bf, size_t size); -char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size); +char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size, + bool is_debug); int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct perf_evsel *evsel, @@ -25,23 +28,26 @@ int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event, int dsos__hit_all(struct perf_session *session); bool perf_session__read_build_ids(struct perf_session *session, bool with_hits); -int perf_session__write_buildid_table(struct perf_session *session, int fd); +int perf_session__write_buildid_table(struct perf_session *session, + struct feat_fd *fd); int perf_session__cache_build_ids(struct perf_session *session); char *build_id_cache__origname(const char *sbuild_id); char *build_id_cache__linkname(const char *sbuild_id, char *bf, size_t size); char *build_id_cache__cachedir(const char *sbuild_id, const char *name, - bool is_kallsyms, bool is_vdso); + struct nsinfo *nsi, bool is_kallsyms, + bool is_vdso); struct strlist; struct strlist *build_id_cache__list_all(bool validonly); char *build_id_cache__complement(const char *incomplete_sbuild_id); -int build_id_cache__list_build_ids(const char *pathname, +int build_id_cache__list_build_ids(const char *pathname, struct nsinfo *nsi, struct strlist **result); bool build_id_cache__cached(const char *sbuild_id); int build_id_cache__add_s(const char *sbuild_id, - const char *name, bool is_kallsyms, bool is_vdso); + const char *name, struct nsinfo *nsi, + bool is_kallsyms, bool is_vdso); int build_id_cache__remove_s(const char *sbuild_id); extern char buildid_dir[]; diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h index 0328f297a748..0175765c05b9 100644 --- a/tools/perf/util/cache.h +++ b/tools/perf/util/cache.h @@ -5,6 +5,7 @@ #include <subcmd/pager.h> #include "../ui/ui.h" +#include <linux/compiler.h> #include <linux/string.h> #define CMD_EXEC_PATH "--exec-path" @@ -24,6 +25,6 @@ static inline int is_absolute_path(const char *path) return path[0] == '/'; } -char *mkpath(const char *fmt, ...) __attribute__((format (printf, 1, 2))); +char *mkpath(const char *fmt, ...) __printf(1, 2); #endif /* __PERF_CACHE_H */ diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index b4204b43ed58..510b513e0f01 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -23,6 +23,7 @@ #include "sort.h" #include "machine.h" #include "callchain.h" +#include "branch.h" #define CALLCHAIN_PARAM_DEFAULT \ .mode = CHAIN_GRAPH_ABS, \ @@ -303,7 +304,7 @@ int perf_callchain_config(const char *var, const char *value) { char *endptr; - if (prefixcmp(var, "call-graph.")) + if (!strstarts(var, "call-graph.")) return 0; var += sizeof("call-graph.") - 1; @@ -562,15 +563,33 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor) if (cursor_node->branch) { call->branch_count = 1; - if (cursor_node->branch_flags.predicted) - call->predicted_count = 1; - - if (cursor_node->branch_flags.abort) - call->abort_count = 1; - - call->cycles_count = cursor_node->branch_flags.cycles; - call->iter_count = cursor_node->nr_loop_iter; - call->samples_count = cursor_node->samples; + if (cursor_node->branch_from) { + /* + * branch_from is set with value somewhere else + * to imply it's "to" of a branch. + */ + call->brtype_stat.branch_to = true; + + if (cursor_node->branch_flags.predicted) + call->predicted_count = 1; + + if (cursor_node->branch_flags.abort) + call->abort_count = 1; + + branch_type_count(&call->brtype_stat, + &cursor_node->branch_flags, + cursor_node->branch_from, + cursor_node->ip); + } else { + /* + * It's "from" of a branch + */ + call->brtype_stat.branch_to = false; + call->cycles_count = + cursor_node->branch_flags.cycles; + call->iter_count = cursor_node->nr_loop_iter; + call->iter_cycles = cursor_node->iter_cycles; + } } list_add_tail(&call->list, &node->val); @@ -679,15 +698,32 @@ static enum match_result match_chain(struct callchain_cursor_node *node, if (node->branch) { cnode->branch_count++; - if (node->branch_flags.predicted) - cnode->predicted_count++; - - if (node->branch_flags.abort) - cnode->abort_count++; - - cnode->cycles_count += node->branch_flags.cycles; - cnode->iter_count += node->nr_loop_iter; - cnode->samples_count += node->samples; + if (node->branch_from) { + /* + * It's "to" of a branch + */ + cnode->brtype_stat.branch_to = true; + + if (node->branch_flags.predicted) + cnode->predicted_count++; + + if (node->branch_flags.abort) + cnode->abort_count++; + + branch_type_count(&cnode->brtype_stat, + &node->branch_flags, + node->branch_from, + node->ip); + } else { + /* + * It's "from" of a branch + */ + cnode->brtype_stat.branch_to = false; + cnode->cycles_count += + node->branch_flags.cycles; + cnode->iter_count += node->nr_loop_iter; + cnode->iter_cycles += node->iter_cycles; + } } return MATCH_EQ; @@ -922,7 +958,7 @@ merge_chain_branch(struct callchain_cursor *cursor, list_for_each_entry_safe(list, next_list, &src->val, list) { callchain_cursor_append(cursor, list->ip, list->ms.map, list->ms.sym, - false, NULL, 0, 0); + false, NULL, 0, 0, 0); list_del(&list->list); map__zput(list->ms.map); free(list); @@ -962,7 +998,7 @@ int callchain_merge(struct callchain_cursor *cursor, int callchain_cursor_append(struct callchain_cursor *cursor, u64 ip, struct map *map, struct symbol *sym, bool branch, struct branch_flags *flags, - int nr_loop_iter, int samples) + int nr_loop_iter, u64 iter_cycles, u64 branch_from) { struct callchain_cursor_node *node = *cursor->last; @@ -980,12 +1016,13 @@ int callchain_cursor_append(struct callchain_cursor *cursor, node->sym = sym; node->branch = branch; node->nr_loop_iter = nr_loop_iter; - node->samples = samples; + node->iter_cycles = iter_cycles; if (flags) memcpy(&node->branch_flags, flags, sizeof(struct branch_flags)); + node->branch_from = branch_from; cursor->nr++; cursor->last = &node->next; @@ -998,11 +1035,11 @@ int sample__resolve_callchain(struct perf_sample *sample, struct perf_evsel *evsel, struct addr_location *al, int max_stack) { - if (sample->callchain == NULL) + if (sample->callchain == NULL && !symbol_conf.show_branchflag_count) return 0; if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain || - perf_hpp_list.parent) { + perf_hpp_list.parent || symbol_conf.show_branchflag_count) { return thread__resolve_callchain(al->thread, cursor, evsel, sample, parent, al, max_stack); } @@ -1011,7 +1048,8 @@ int sample__resolve_callchain(struct perf_sample *sample, int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample) { - if (!symbol_conf.use_callchain || sample->callchain == NULL) + if ((!symbol_conf.use_callchain || sample->callchain == NULL) && + !symbol_conf.show_branchflag_count) return 0; return callchain_append(he->callchain, &callchain_cursor, sample->period); } @@ -1214,95 +1252,124 @@ int callchain_branch_counts(struct callchain_root *root, cycles_count); } -static int counts_str_build(char *bf, int bfsize, - u64 branch_count, u64 predicted_count, - u64 abort_count, u64 cycles_count, - u64 iter_count, u64 samples_count) +static int count_pri64_printf(int idx, const char *str, u64 value, char *bf, int bfsize) { - double predicted_percent = 0.0; - const char *null_str = ""; - char iter_str[32]; - char cycle_str[32]; - char *istr, *cstr; - u64 cycles; + int printed; - if (branch_count == 0) - return scnprintf(bf, bfsize, " (calltrace)"); + printed = scnprintf(bf, bfsize, "%s%s:%" PRId64 "", (idx) ? " " : " (", str, value); - cycles = cycles_count / branch_count; + return printed; +} - if (iter_count && samples_count) { - if (cycles > 0) - scnprintf(iter_str, sizeof(iter_str), - " iterations:%" PRId64 "", - iter_count / samples_count); - else - scnprintf(iter_str, sizeof(iter_str), - "iterations:%" PRId64 "", - iter_count / samples_count); - istr = iter_str; - } else - istr = (char *)null_str; +static int count_float_printf(int idx, const char *str, float value, + char *bf, int bfsize, float threshold) +{ + int printed; - if (cycles > 0) { - scnprintf(cycle_str, sizeof(cycle_str), - "cycles:%" PRId64 "", cycles); - cstr = cycle_str; - } else - cstr = (char *)null_str; + if (threshold != 0.0 && value < threshold) + return 0; - predicted_percent = predicted_count * 100.0 / branch_count; + printed = scnprintf(bf, bfsize, "%s%s:%.1f%%", (idx) ? " " : " (", str, value); - if ((predicted_count == branch_count) && (abort_count == 0)) { - if ((cycles > 0) || (istr != (char *)null_str)) - return scnprintf(bf, bfsize, " (%s%s)", cstr, istr); - else - return scnprintf(bf, bfsize, "%s", (char *)null_str); + return printed; +} + +static int branch_to_str(char *bf, int bfsize, + u64 branch_count, u64 predicted_count, + u64 abort_count, + struct branch_type_stat *brtype_stat) +{ + int printed, i = 0; + + printed = branch_type_str(brtype_stat, bf, bfsize); + if (printed) + i++; + + if (predicted_count < branch_count) { + printed += count_float_printf(i++, "predicted", + predicted_count * 100.0 / branch_count, + bf + printed, bfsize - printed, 0.0); } - if ((predicted_count < branch_count) && (abort_count == 0)) { - if ((cycles > 0) || (istr != (char *)null_str)) - return scnprintf(bf, bfsize, - " (predicted:%.1f%% %s%s)", - predicted_percent, cstr, istr); - else { - return scnprintf(bf, bfsize, - " (predicted:%.1f%%)", - predicted_percent); - } + if (abort_count) { + printed += count_float_printf(i++, "abort", + abort_count * 100.0 / branch_count, + bf + printed, bfsize - printed, 0.1); } - if ((predicted_count == branch_count) && (abort_count > 0)) { - if ((cycles > 0) || (istr != (char *)null_str)) - return scnprintf(bf, bfsize, - " (abort:%" PRId64 " %s%s)", - abort_count, cstr, istr); - else - return scnprintf(bf, bfsize, - " (abort:%" PRId64 ")", - abort_count); + if (i) + printed += scnprintf(bf + printed, bfsize - printed, ")"); + + return printed; +} + +static int branch_from_str(char *bf, int bfsize, + u64 branch_count, + u64 cycles_count, u64 iter_count, + u64 iter_cycles) +{ + int printed = 0, i = 0; + u64 cycles; + + cycles = cycles_count / branch_count; + if (cycles) { + printed += count_pri64_printf(i++, "cycles", + cycles, + bf + printed, bfsize - printed); } - if ((cycles > 0) || (istr != (char *)null_str)) - return scnprintf(bf, bfsize, - " (predicted:%.1f%% abort:%" PRId64 " %s%s)", - predicted_percent, abort_count, cstr, istr); + if (iter_count) { + printed += count_pri64_printf(i++, "iter", + iter_count, + bf + printed, bfsize - printed); + + printed += count_pri64_printf(i++, "avg_cycles", + iter_cycles / iter_count, + bf + printed, bfsize - printed); + } - return scnprintf(bf, bfsize, - " (predicted:%.1f%% abort:%" PRId64 ")", - predicted_percent, abort_count); + if (i) + printed += scnprintf(bf + printed, bfsize - printed, ")"); + + return printed; +} + +static int counts_str_build(char *bf, int bfsize, + u64 branch_count, u64 predicted_count, + u64 abort_count, u64 cycles_count, + u64 iter_count, u64 iter_cycles, + struct branch_type_stat *brtype_stat) +{ + int printed; + + if (branch_count == 0) + return scnprintf(bf, bfsize, " (calltrace)"); + + if (brtype_stat->branch_to) { + printed = branch_to_str(bf, bfsize, branch_count, + predicted_count, abort_count, brtype_stat); + } else { + printed = branch_from_str(bf, bfsize, branch_count, + cycles_count, iter_count, iter_cycles); + } + + if (!printed) + bf[0] = 0; + + return printed; } static int callchain_counts_printf(FILE *fp, char *bf, int bfsize, u64 branch_count, u64 predicted_count, u64 abort_count, u64 cycles_count, - u64 iter_count, u64 samples_count) + u64 iter_count, u64 iter_cycles, + struct branch_type_stat *brtype_stat) { - char str[128]; + char str[256]; counts_str_build(str, sizeof(str), branch_count, predicted_count, abort_count, cycles_count, - iter_count, samples_count); + iter_count, iter_cycles, brtype_stat); if (fp) return fprintf(fp, "%s", str); @@ -1310,31 +1377,24 @@ static int callchain_counts_printf(FILE *fp, char *bf, int bfsize, return scnprintf(bf, bfsize, "%s", str); } -int callchain_list_counts__printf_value(struct callchain_node *node, - struct callchain_list *clist, +int callchain_list_counts__printf_value(struct callchain_list *clist, FILE *fp, char *bf, int bfsize) { u64 branch_count, predicted_count; u64 abort_count, cycles_count; - u64 iter_count = 0, samples_count = 0; + u64 iter_count, iter_cycles; branch_count = clist->branch_count; predicted_count = clist->predicted_count; abort_count = clist->abort_count; cycles_count = clist->cycles_count; - - if (node) { - struct callchain_list *call; - - list_for_each_entry(call, &node->val, list) { - iter_count += call->iter_count; - samples_count += call->samples_count; - } - } + iter_count = clist->iter_count; + iter_cycles = clist->iter_cycles; return callchain_counts_printf(fp, bf, bfsize, branch_count, predicted_count, abort_count, - cycles_count, iter_count, samples_count); + cycles_count, iter_count, iter_cycles, + &clist->brtype_stat); } static void free_callchain_node(struct callchain_node *node) @@ -1459,7 +1519,9 @@ int callchain_cursor__copy(struct callchain_cursor *dst, rc = callchain_cursor_append(dst, node->ip, node->map, node->sym, node->branch, &node->branch_flags, - node->nr_loop_iter, node->samples); + node->nr_loop_iter, + node->iter_cycles, + node->branch_from); if (rc) break; diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index c56c23dbbf72..1ed6fc61d0a5 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -7,6 +7,7 @@ #include "event.h" #include "map.h" #include "symbol.h" +#include "branch.h" #define HELP_PAD "\t\t\t\t" @@ -118,7 +119,8 @@ struct callchain_list { u64 abort_count; u64 cycles_count; u64 iter_count; - u64 samples_count; + u64 iter_cycles; + struct branch_type_stat brtype_stat; char *srcline; struct list_head list; }; @@ -135,8 +137,9 @@ struct callchain_cursor_node { struct symbol *sym; bool branch; struct branch_flags branch_flags; + u64 branch_from; int nr_loop_iter; - int samples; + u64 iter_cycles; struct callchain_cursor_node *next; }; @@ -198,7 +201,7 @@ static inline void callchain_cursor_reset(struct callchain_cursor *cursor) int callchain_cursor_append(struct callchain_cursor *cursor, u64 ip, struct map *map, struct symbol *sym, bool branch, struct branch_flags *flags, - int nr_loop_iter, int samples); + int nr_loop_iter, u64 iter_cycles, u64 branch_from); /* Close a cursor writing session. Initialize for the reader */ static inline void callchain_cursor_commit(struct callchain_cursor *cursor) @@ -279,8 +282,7 @@ char *callchain_node__scnprintf_value(struct callchain_node *node, int callchain_node__fprintf_value(struct callchain_node *node, FILE *fp, u64 total); -int callchain_list_counts__printf_value(struct callchain_node *node, - struct callchain_list *clist, +int callchain_list_counts__printf_value(struct callchain_list *clist, FILE *fp, char *bf, int bfsize); void free_callchain(struct callchain_root *root); diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c index 03347748f3fa..0e77bc9e5f3c 100644 --- a/tools/perf/util/cgroup.c +++ b/tools/perf/util/cgroup.c @@ -98,8 +98,10 @@ static int add_cgroup(struct perf_evlist *evlist, char *str) cgrp = counter->cgrp; if (!cgrp) continue; - if (!strcmp(cgrp->name, str)) + if (!strcmp(cgrp->name, str)) { + refcount_inc(&cgrp->refcnt); break; + } cgrp = NULL; } @@ -110,6 +112,7 @@ static int add_cgroup(struct perf_evlist *evlist, char *str) return -1; cgrp->name = str; + refcount_set(&cgrp->refcnt, 1); cgrp->fd = open_cgroup(str); if (cgrp->fd == -1) { @@ -128,12 +131,11 @@ static int add_cgroup(struct perf_evlist *evlist, char *str) goto found; n++; } - if (refcount_read(&cgrp->refcnt) == 0) + if (refcount_dec_and_test(&cgrp->refcnt)) free(cgrp); return -1; found: - refcount_inc(&cgrp->refcnt); counter->cgrp = cgrp; return 0; } diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 8d724f0fa5a8..bc75596f9e79 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -19,6 +19,7 @@ #include <sys/types.h> #include <sys/stat.h> #include <unistd.h> +#include <linux/string.h> #include "sane_ctype.h" @@ -335,32 +336,42 @@ static int perf_parse_long(const char *value, long *ret) return 0; } -static void die_bad_config(const char *name) +static void bad_config(const char *name) { if (config_file_name) - die("bad config value for '%s' in %s", name, config_file_name); - die("bad config value for '%s'", name); + pr_warning("bad config value for '%s' in %s, ignoring...\n", name, config_file_name); + else + pr_warning("bad config value for '%s', ignoring...\n", name); } -u64 perf_config_u64(const char *name, const char *value) +int perf_config_u64(u64 *dest, const char *name, const char *value) { long long ret = 0; - if (!perf_parse_llong(value, &ret)) - die_bad_config(name); - return (u64) ret; + if (!perf_parse_llong(value, &ret)) { + bad_config(name); + return -1; + } + + *dest = ret; + return 0; } -int perf_config_int(const char *name, const char *value) +int perf_config_int(int *dest, const char *name, const char *value) { long ret = 0; - if (!perf_parse_long(value, &ret)) - die_bad_config(name); - return ret; + if (!perf_parse_long(value, &ret)) { + bad_config(name); + return -1; + } + *dest = ret; + return 0; } static int perf_config_bool_or_int(const char *name, const char *value, int *is_bool) { + int ret; + *is_bool = 1; if (!value) return 1; @@ -371,7 +382,7 @@ static int perf_config_bool_or_int(const char *name, const char *value, int *is_ if (!strcasecmp(value, "false") || !strcasecmp(value, "no") || !strcasecmp(value, "off")) return 0; *is_bool = 0; - return perf_config_int(name, value); + return perf_config_int(&ret, name, value) < 0 ? -1 : ret; } int perf_config_bool(const char *name, const char *value) @@ -423,22 +434,22 @@ static int perf_ui_config(const char *var, const char *value) int perf_default_config(const char *var, const char *value, void *dummy __maybe_unused) { - if (!prefixcmp(var, "core.")) + if (strstarts(var, "core.")) return perf_default_core_config(var, value); - if (!prefixcmp(var, "hist.")) + if (strstarts(var, "hist.")) return perf_hist_config(var, value); - if (!prefixcmp(var, "ui.")) + if (strstarts(var, "ui.")) return perf_ui_config(var, value); - if (!prefixcmp(var, "call-graph.")) + if (strstarts(var, "call-graph.")) return perf_callchain_config(var, value); - if (!prefixcmp(var, "llvm.")) + if (strstarts(var, "llvm.")) return perf_llvm_config(var, value); - if (!prefixcmp(var, "buildid.")) + if (strstarts(var, "buildid.")) return perf_buildid_config(var, value); /* Add other config variables here. */ @@ -657,8 +668,7 @@ static int perf_config_set__init(struct perf_config_set *set) user_config = strdup(mkpath("%s/.perfconfig", home)); if (user_config == NULL) { - warning("Not enough memory to process %s/.perfconfig, " - "ignoring it.", home); + pr_warning("Not enough memory to process %s/.perfconfig, ignoring it.", home); goto out; } @@ -671,8 +681,7 @@ static int perf_config_set__init(struct perf_config_set *set) ret = 0; if (st.st_uid && (st.st_uid != geteuid())) { - warning("File %s not owned by current user or root, " - "ignoring it.", user_config); + pr_warning("File %s not owned by current user or root, ignoring it.", user_config); goto out_free; } @@ -795,7 +804,8 @@ void perf_config_set__delete(struct perf_config_set *set) */ int config_error_nonbool(const char *var) { - return error("Missing value for '%s'", var); + pr_err("Missing value for '%s'", var); + return -1; } void set_buildid_dir(const char *dir) diff --git a/tools/perf/util/config.h b/tools/perf/util/config.h index 1a59a6b43f8b..b6bb11f3f165 100644 --- a/tools/perf/util/config.h +++ b/tools/perf/util/config.h @@ -27,8 +27,8 @@ extern const char *config_exclusive_filename; typedef int (*config_fn_t)(const char *, const char *, void *); int perf_default_config(const char *, const char *, void *); int perf_config(config_fn_t fn, void *); -int perf_config_int(const char *, const char *); -u64 perf_config_u64(const char *, const char *); +int perf_config_int(int *dest, const char *, const char *); +int perf_config_u64(u64 *dest, const char *, const char *); int perf_config_bool(const char *, const char *); int config_error_nonbool(const char *); const char *perf_etc_perfconfig(void); diff --git a/tools/perf/util/counts.h b/tools/perf/util/counts.h index 34d8baaf558a..cb45a6aecf9d 100644 --- a/tools/perf/util/counts.h +++ b/tools/perf/util/counts.h @@ -12,6 +12,7 @@ struct perf_counts_values { }; u64 values[3]; }; + bool loaded; }; struct perf_counts { diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c index 89d50318833d..2346cecb8ea2 100644 --- a/tools/perf/util/data-convert-bt.c +++ b/tools/perf/util/data-convert-bt.c @@ -76,6 +76,8 @@ struct ctf_writer { struct bt_ctf_event_class *comm_class; struct bt_ctf_event_class *exit_class; struct bt_ctf_event_class *fork_class; + struct bt_ctf_event_class *mmap_class; + struct bt_ctf_event_class *mmap2_class; }; struct convert { @@ -506,6 +508,81 @@ put_len_type: return ret; } +static int +add_callchain_output_values(struct bt_ctf_event_class *event_class, + struct bt_ctf_event *event, + struct ip_callchain *callchain) +{ + struct bt_ctf_field_type *len_type, *seq_type; + struct bt_ctf_field *len_field, *seq_field; + unsigned int nr_elements = callchain->nr; + unsigned int i; + int ret; + + len_type = bt_ctf_event_class_get_field_by_name( + event_class, "perf_callchain_size"); + len_field = bt_ctf_field_create(len_type); + if (!len_field) { + pr_err("failed to create 'perf_callchain_size' for callchain output event\n"); + ret = -1; + goto put_len_type; + } + + ret = bt_ctf_field_unsigned_integer_set_value(len_field, nr_elements); + if (ret) { + pr_err("failed to set field value for perf_callchain_size\n"); + goto put_len_field; + } + ret = bt_ctf_event_set_payload(event, "perf_callchain_size", len_field); + if (ret) { + pr_err("failed to set payload to perf_callchain_size\n"); + goto put_len_field; + } + + seq_type = bt_ctf_event_class_get_field_by_name( + event_class, "perf_callchain"); + seq_field = bt_ctf_field_create(seq_type); + if (!seq_field) { + pr_err("failed to create 'perf_callchain' for callchain output event\n"); + ret = -1; + goto put_seq_type; + } + + ret = bt_ctf_field_sequence_set_length(seq_field, len_field); + if (ret) { + pr_err("failed to set length of 'perf_callchain'\n"); + goto put_seq_field; + } + + for (i = 0; i < nr_elements; i++) { + struct bt_ctf_field *elem_field = + bt_ctf_field_sequence_get_field(seq_field, i); + + ret = bt_ctf_field_unsigned_integer_set_value(elem_field, + ((u64 *)(callchain->ips))[i]); + + bt_ctf_field_put(elem_field); + if (ret) { + pr_err("failed to set callchain[%d]\n", i); + goto put_seq_field; + } + } + + ret = bt_ctf_event_set_payload(event, "perf_callchain", seq_field); + if (ret) + pr_err("failed to set payload for raw_data\n"); + +put_seq_field: + bt_ctf_field_put(seq_field); +put_seq_type: + bt_ctf_field_type_put(seq_type); +put_len_field: + bt_ctf_field_put(len_field); +put_len_type: + bt_ctf_field_type_put(len_type); + return ret; +} + static int add_generic_values(struct ctf_writer *cw, struct bt_ctf_event *event, struct perf_evsel *evsel, @@ -519,7 +596,6 @@ static int add_generic_values(struct ctf_writer *cw, * PERF_SAMPLE_TIME - not needed as we have it in * ctf event header * PERF_SAMPLE_READ - TODO - * PERF_SAMPLE_CALLCHAIN - TODO * PERF_SAMPLE_RAW - tracepoint fields are handled separately * PERF_SAMPLE_BRANCH_STACK - TODO * PERF_SAMPLE_REGS_USER - TODO @@ -720,6 +796,7 @@ static int process_sample_event(struct perf_tool *tool, struct bt_ctf_event_class *event_class; struct bt_ctf_event *event; int ret; + unsigned long type = evsel->attr.sample_type; if (WARN_ONCE(!priv, "Failed to setup all events.\n")) return 0; @@ -751,6 +828,13 @@ static int process_sample_event(struct perf_tool *tool, return -1; } + if (type & PERF_SAMPLE_CALLCHAIN) { + ret = add_callchain_output_values(event_class, + event, sample->callchain); + if (ret) + return -1; + } + if (perf_evsel__is_bpf_output(evsel)) { ret = add_bpf_output_values(event_class, event, sample); if (ret) @@ -833,6 +917,18 @@ __FUNC_PROCESS_NON_SAMPLE(exit, __NON_SAMPLE_SET_FIELD(fork, u32, ptid); __NON_SAMPLE_SET_FIELD(fork, u64, time); ) +__FUNC_PROCESS_NON_SAMPLE(mmap, + __NON_SAMPLE_SET_FIELD(mmap, u32, pid); + __NON_SAMPLE_SET_FIELD(mmap, u32, tid); + __NON_SAMPLE_SET_FIELD(mmap, u64_hex, start); + __NON_SAMPLE_SET_FIELD(mmap, string, filename); +) +__FUNC_PROCESS_NON_SAMPLE(mmap2, + __NON_SAMPLE_SET_FIELD(mmap2, u32, pid); + __NON_SAMPLE_SET_FIELD(mmap2, u32, tid); + __NON_SAMPLE_SET_FIELD(mmap2, u64_hex, start); + __NON_SAMPLE_SET_FIELD(mmap2, string, filename); +) #undef __NON_SAMPLE_SET_FIELD #undef __FUNC_PROCESS_NON_SAMPLE @@ -1043,6 +1139,14 @@ static int add_generic_types(struct ctf_writer *cw, struct perf_evsel *evsel, if (type & PERF_SAMPLE_TRANSACTION) ADD_FIELD(event_class, cw->data.u64, "perf_transaction"); + if (type & PERF_SAMPLE_CALLCHAIN) { + ADD_FIELD(event_class, cw->data.u32, "perf_callchain_size"); + ADD_FIELD(event_class, + bt_ctf_field_type_sequence_create( + cw->data.u64_hex, "perf_callchain_size"), + "perf_callchain"); + } + #undef ADD_FIELD return 0; } @@ -1164,6 +1268,19 @@ __FUNC_ADD_NON_SAMPLE_EVENT_CLASS(exit, __NON_SAMPLE_ADD_FIELD(u64, time); ) +__FUNC_ADD_NON_SAMPLE_EVENT_CLASS(mmap, + __NON_SAMPLE_ADD_FIELD(u32, pid); + __NON_SAMPLE_ADD_FIELD(u32, tid); + __NON_SAMPLE_ADD_FIELD(u64_hex, start); + __NON_SAMPLE_ADD_FIELD(string, filename); +) + +__FUNC_ADD_NON_SAMPLE_EVENT_CLASS(mmap2, + __NON_SAMPLE_ADD_FIELD(u32, pid); + __NON_SAMPLE_ADD_FIELD(u32, tid); + __NON_SAMPLE_ADD_FIELD(u64_hex, start); + __NON_SAMPLE_ADD_FIELD(string, filename); +) #undef __NON_SAMPLE_ADD_FIELD #undef __FUNC_ADD_NON_SAMPLE_EVENT_CLASS @@ -1181,6 +1298,12 @@ static int setup_non_sample_events(struct ctf_writer *cw, ret = add_fork_event(cw); if (ret) return ret; + ret = add_mmap_event(cw); + if (ret) + return ret; + ret = add_mmap2_event(cw); + if (ret) + return ret; return 0; } @@ -1444,10 +1567,8 @@ static int convert__config(const char *var, const char *value, void *cb) { struct convert *c = cb; - if (!strcmp(var, "convert.queue-size")) { - c->queue_size = perf_config_u64(var, value); - return 0; - } + if (!strcmp(var, "convert.queue-size")) + return perf_config_u64(&c->queue_size, var, value); return 0; } @@ -1484,6 +1605,8 @@ int bt_convert__perf2ctf(const char *input, const char *path, c.tool.comm = process_comm_event; c.tool.exit = process_exit_event; c.tool.fork = process_fork_event; + c.tool.mmap = process_mmap_event; + c.tool.mmap2 = process_mmap2_event; } err = perf_config(convert__config, &c); diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index e84bbc8ec058..263f5a906ba5 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -10,6 +10,16 @@ #include "util.h" #include "debug.h" +#ifndef O_CLOEXEC +#ifdef __sparc__ +#define O_CLOEXEC 0x400000 +#elif defined(__alpha__) || defined(__hppa__) +#define O_CLOEXEC 010000000 +#else +#define O_CLOEXEC 02000000 +#endif +#endif + static bool check_pipe(struct perf_data_file *file) { struct stat st; @@ -96,7 +106,8 @@ static int open_file_write(struct perf_data_file *file) if (check_backup(file)) return -1; - fd = open(file->path, O_CREAT|O_RDWR|O_TRUNC, S_IRUSR|S_IWUSR); + fd = open(file->path, O_CREAT|O_RDWR|O_TRUNC|O_CLOEXEC, + S_IRUSR|S_IWUSR); if (fd < 0) pr_err("failed to open %s : %s\n", file->path, diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h index 8a23ea1a71c7..c818bdb1c1ab 100644 --- a/tools/perf/util/debug.h +++ b/tools/perf/util/debug.h @@ -4,6 +4,7 @@ #include <stdbool.h> #include <string.h> +#include <linux/compiler.h> #include "event.h" #include "../ui/helpline.h" #include "../ui/progress.h" @@ -40,16 +41,16 @@ extern int debug_data_convert; #define STRERR_BUFSIZE 128 /* For the buffer size of str_error_r */ -int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2))); +int dump_printf(const char *fmt, ...) __printf(1, 2); void trace_event(union perf_event *event); -int ui__error(const char *format, ...) __attribute__((format(printf, 1, 2))); -int ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2))); +int ui__error(const char *format, ...) __printf(1, 2); +int ui__warning(const char *format, ...) __printf(1, 2); void pr_stat(const char *fmt, ...); -int eprintf(int level, int var, const char *fmt, ...) __attribute__((format(printf, 3, 4))); -int eprintf_time(int level, int var, u64 t, const char *fmt, ...) __attribute__((format(printf, 4, 5))); +int eprintf(int level, int var, const char *fmt, ...) __printf(3, 4); +int eprintf_time(int level, int var, u64 t, const char *fmt, ...) __printf(4, 5); int veprintf(int level, int var, const char *fmt, va_list args); int perf_debug_option(const char *str); diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index 4e7ab611377a..b9e087fb8247 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -32,6 +32,7 @@ char dso__symtab_origin(const struct dso *dso) [DSO_BINARY_TYPE__JAVA_JIT] = 'j', [DSO_BINARY_TYPE__DEBUGLINK] = 'l', [DSO_BINARY_TYPE__BUILD_ID_CACHE] = 'B', + [DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO] = 'D', [DSO_BINARY_TYPE__FEDORA_DEBUGINFO] = 'f', [DSO_BINARY_TYPE__UBUNTU_DEBUGINFO] = 'u', [DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO] = 'o', @@ -97,7 +98,12 @@ int dso__read_binary_type_filename(const struct dso *dso, break; } case DSO_BINARY_TYPE__BUILD_ID_CACHE: - if (dso__build_id_filename(dso, filename, size) == NULL) + if (dso__build_id_filename(dso, filename, size, false) == NULL) + ret = -1; + break; + + case DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO: + if (dso__build_id_filename(dso, filename, size, true) == NULL) ret = -1; break; @@ -504,7 +510,14 @@ static void check_data_close(void); */ static int open_dso(struct dso *dso, struct machine *machine) { - int fd = __open_dso(dso, machine); + int fd; + struct nscookie nsc; + + if (dso->binary_type != DSO_BINARY_TYPE__BUILD_ID_CACHE) + nsinfo__mountns_enter(dso->nsinfo, &nsc); + fd = __open_dso(dso, machine); + if (dso->binary_type != DSO_BINARY_TYPE__BUILD_ID_CACHE) + nsinfo__mountns_exit(&nsc); if (fd >= 0) { dso__list_add(dso); @@ -1236,6 +1249,7 @@ void dso__delete(struct dso *dso) dso_cache__free(dso); dso__free_a2l(dso); zfree(&dso->symsrc_filename); + nsinfo__zput(dso->nsinfo); pthread_mutex_destroy(&dso->lock); free(dso); } @@ -1301,6 +1315,7 @@ bool __dsos__read_build_ids(struct list_head *head, bool with_hits) { bool have_build_id = false; struct dso *pos; + struct nscookie nsc; list_for_each_entry(pos, head, node) { if (with_hits && !pos->hit && !dso__is_vdso(pos)) @@ -1309,11 +1324,13 @@ bool __dsos__read_build_ids(struct list_head *head, bool with_hits) have_build_id = true; continue; } + nsinfo__mountns_enter(pos->nsinfo, &nsc); if (filename__read_build_id(pos->long_name, pos->build_id, sizeof(pos->build_id)) > 0) { have_build_id = true; pos->has_build_id = true; } + nsinfo__mountns_exit(&nsc); } return have_build_id; diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index bd061ba7b47c..f886141678eb 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -10,6 +10,7 @@ #include <linux/types.h> #include <linux/bitops.h> #include "map.h" +#include "namespaces.h" #include "build-id.h" enum dso_binary_type { @@ -20,6 +21,7 @@ enum dso_binary_type { DSO_BINARY_TYPE__JAVA_JIT, DSO_BINARY_TYPE__DEBUGLINK, DSO_BINARY_TYPE__BUILD_ID_CACHE, + DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO, DSO_BINARY_TYPE__FEDORA_DEBUGINFO, DSO_BINARY_TYPE__UBUNTU_DEBUGINFO, DSO_BINARY_TYPE__BUILDID_DEBUGINFO, @@ -187,6 +189,7 @@ struct dso { void *priv; u64 db_id; }; + struct nsinfo *nsinfo; refcount_t refcnt; char name[0]; }; diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index dc5c3bb69d73..1c905ba3641b 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -57,6 +57,7 @@ static const char *perf_event__names[] = { [PERF_RECORD_STAT_ROUND] = "STAT_ROUND", [PERF_RECORD_EVENT_UPDATE] = "EVENT_UPDATE", [PERF_RECORD_TIME_CONV] = "TIME_CONV", + [PERF_RECORD_HEADER_FEATURE] = "FEATURE", }; static const char *perf_ns__names[] = { diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 7c3fa1c8cbcd..ee7bcc898d35 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -142,7 +142,8 @@ struct branch_flags { u64 in_tx:1; u64 abort:1; u64 cycles:16; - u64 reserved:44; + u64 type:4; + u64 reserved:40; }; struct branch_entry { @@ -199,6 +200,7 @@ struct perf_sample { u32 cpu; u32 raw_size; u64 data_src; + u64 phys_addr; u32 flags; u16 insn_len; u8 cpumode; @@ -244,6 +246,7 @@ enum perf_user_event_type { /* above any possible kernel type */ PERF_RECORD_STAT_ROUND = 77, PERF_RECORD_EVENT_UPDATE = 78, PERF_RECORD_TIME_CONV = 79, + PERF_RECORD_HEADER_FEATURE = 80, PERF_RECORD_HEADER_MAX }; @@ -252,6 +255,127 @@ enum auxtrace_error_type { PERF_AUXTRACE_ERROR_MAX }; +/* Attribute type for custom synthesized events */ +#define PERF_TYPE_SYNTH (INT_MAX + 1U) + +/* Attribute config for custom synthesized events */ +enum perf_synth_id { + PERF_SYNTH_INTEL_PTWRITE, + PERF_SYNTH_INTEL_MWAIT, + PERF_SYNTH_INTEL_PWRE, + PERF_SYNTH_INTEL_EXSTOP, + PERF_SYNTH_INTEL_PWRX, + PERF_SYNTH_INTEL_CBR, +}; + +/* + * Raw data formats for synthesized events. Note that 4 bytes of padding are + * present to match the 'size' member of PERF_SAMPLE_RAW data which is always + * 8-byte aligned. That means we must dereference raw_data with an offset of 4. + * Refer perf_sample__synth_ptr() and perf_synth__raw_data(). It also means the + * structure sizes are 4 bytes bigger than the raw_size, refer + * perf_synth__raw_size(). + */ + +struct perf_synth_intel_ptwrite { + u32 padding; + union { + struct { + u32 ip : 1, + reserved : 31; + }; + u32 flags; + }; + u64 payload; +}; + +struct perf_synth_intel_mwait { + u32 padding; + u32 reserved; + union { + struct { + u64 hints : 8, + reserved1 : 24, + extensions : 2, + reserved2 : 30; + }; + u64 payload; + }; +}; + +struct perf_synth_intel_pwre { + u32 padding; + u32 reserved; + union { + struct { + u64 reserved1 : 7, + hw : 1, + subcstate : 4, + cstate : 4, + reserved2 : 48; + }; + u64 payload; + }; +}; + +struct perf_synth_intel_exstop { + u32 padding; + union { + struct { + u32 ip : 1, + reserved : 31; + }; + u32 flags; + }; +}; + +struct perf_synth_intel_pwrx { + u32 padding; + u32 reserved; + union { + struct { + u64 deepest_cstate : 4, + last_cstate : 4, + wake_reason : 4, + reserved1 : 52; + }; + u64 payload; + }; +}; + +struct perf_synth_intel_cbr { + u32 padding; + union { + struct { + u32 cbr : 8, + reserved1 : 8, + max_nonturbo : 8, + reserved2 : 8; + }; + u32 flags; + }; + u32 freq; + u32 reserved3; +}; + +/* + * raw_data is always 4 bytes from an 8-byte boundary, so subtract 4 to get + * 8-byte alignment. + */ +static inline void *perf_sample__synth_ptr(struct perf_sample *sample) +{ + return sample->raw_data - 4; +} + +static inline void *perf_synth__raw_data(void *p) +{ + return p + 4; +} + +#define perf_synth__raw_size(d) (sizeof(d) - 4) + +#define perf_sample__bad_synth_size(s, d) ((s)->raw_size < sizeof(d) - 4) + /* * The kernel collects the number of events it couldn't send in a stretch and * when possible sends this number in a PERF_RECORD_LOST event. The number of @@ -488,6 +612,12 @@ struct time_conv_event { u64 time_zero; }; +struct feature_event { + struct perf_event_header header; + u64 feat_id; + char data[]; +}; + union perf_event { struct perf_event_header header; struct mmap_event mmap; @@ -518,6 +648,7 @@ union perf_event { struct stat_event stat; struct stat_round_event stat_round; struct time_conv_event time_conv; + struct feature_event feat; }; void perf_event__print_totals(void); diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 46c0faf6c502..6a0d7ffbeba0 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -242,9 +242,9 @@ void perf_event_attr__set_max_precise_ip(struct perf_event_attr *attr) } } -int perf_evlist__add_default(struct perf_evlist *evlist) +int __perf_evlist__add_default(struct perf_evlist *evlist, bool precise) { - struct perf_evsel *evsel = perf_evsel__new_cycles(); + struct perf_evsel *evsel = perf_evsel__new_cycles(precise); if (evsel == NULL) return -ENOMEM; @@ -1419,8 +1419,6 @@ int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **e { struct perf_evsel *evsel; int err = 0; - const int ncpus = cpu_map__nr(evlist->cpus), - nthreads = thread_map__nr(evlist->threads); evlist__for_each_entry(evlist, evsel) { if (evsel->filter == NULL) @@ -1430,7 +1428,7 @@ int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **e * filters only work for tracepoint event, which doesn't have cpu limit. * So evlist and evsel should always be same. */ - err = perf_evsel__apply_filter(evsel, ncpus, nthreads, evsel->filter); + err = perf_evsel__apply_filter(evsel, evsel->filter); if (err) { *err_evsel = evsel; break; @@ -1623,13 +1621,9 @@ void perf_evlist__set_selected(struct perf_evlist *evlist, void perf_evlist__close(struct perf_evlist *evlist) { struct perf_evsel *evsel; - int ncpus = cpu_map__nr(evlist->cpus); - int nthreads = thread_map__nr(evlist->threads); - evlist__for_each_entry_reverse(evlist, evsel) { - int n = evsel->cpus ? evsel->cpus->nr : ncpus; - perf_evsel__close(evsel, n, nthreads); - } + evlist__for_each_entry_reverse(evlist, evsel) + perf_evsel__close(evsel); } static int perf_evlist__create_syswide_maps(struct perf_evlist *evlist) diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 94cea4398a13..bf2c4936e35f 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -1,6 +1,7 @@ #ifndef __PERF_EVLIST_H #define __PERF_EVLIST_H 1 +#include <linux/compiler.h> #include <linux/kernel.h> #include <linux/refcount.h> #include <linux/list.h> @@ -34,7 +35,7 @@ struct perf_mmap { refcount_t refcnt; u64 prev; struct auxtrace_mmap auxtrace_mmap; - char event_copy[PERF_SAMPLE_MAX_SIZE] __attribute__((aligned(8))); + char event_copy[PERF_SAMPLE_MAX_SIZE] __aligned(8); }; static inline size_t @@ -114,7 +115,14 @@ void perf_evlist__delete(struct perf_evlist *evlist); void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry); void perf_evlist__remove(struct perf_evlist *evlist, struct perf_evsel *evsel); -int perf_evlist__add_default(struct perf_evlist *evlist); + +int __perf_evlist__add_default(struct perf_evlist *evlist, bool precise); + +static inline int perf_evlist__add_default(struct perf_evlist *evlist) +{ + return __perf_evlist__add_default(evlist, true); +} + int __perf_evlist__add_default_attrs(struct perf_evlist *evlist, struct perf_event_attr *attrs, size_t nr_attrs); @@ -257,6 +265,11 @@ bool perf_evlist__valid_read_format(struct perf_evlist *evlist); void perf_evlist__splice_list_tail(struct perf_evlist *evlist, struct list_head *list); +static inline bool perf_evlist__empty(struct perf_evlist *evlist) +{ + return list_empty(&evlist->entries); +} + static inline struct perf_evsel *perf_evlist__first(struct perf_evlist *evlist) { return list_entry(evlist->entries.next, struct perf_evsel, node); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index cda44b0e821c..4bb89373eb52 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -11,13 +11,17 @@ #include <errno.h> #include <inttypes.h> #include <linux/bitops.h> +#include <api/fs/fs.h> #include <api/fs/tracing_path.h> #include <traceevent/event-parse.h> #include <linux/hw_breakpoint.h> #include <linux/perf_event.h> +#include <linux/compiler.h> #include <linux/err.h> #include <sys/ioctl.h> #include <sys/resource.h> +#include <sys/types.h> +#include <dirent.h> #include "asm/bug.h" #include "callchain.h" #include "cgroup.h" @@ -45,6 +49,7 @@ static struct { bool clockid_wrong; bool lbr_flags; bool write_backward; + bool group_read; } perf_missing_features; static clockid_t clockid; @@ -54,6 +59,8 @@ static int perf_evsel__no_extra_init(struct perf_evsel *evsel __maybe_unused) return 0; } +void __weak test_attr__ready(void) { } + static void perf_evsel__no_extra_fini(struct perf_evsel *evsel __maybe_unused) { } @@ -264,15 +271,19 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx) return evsel; } -struct perf_evsel *perf_evsel__new_cycles(void) +struct perf_evsel *perf_evsel__new_cycles(bool precise) { struct perf_event_attr attr = { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES, + .exclude_kernel = geteuid() != 0, }; struct perf_evsel *evsel; event_attr_init(&attr); + + if (!precise) + goto new_event; /* * Unnamed union member, not supported as struct member named * initializer in older compilers such as gcc 4.4.7 @@ -287,14 +298,16 @@ struct perf_evsel *perf_evsel__new_cycles(void) * to kick in when we return and before perf_evsel__open() is called. */ attr.sample_period = 0; - +new_event: evsel = perf_evsel__new(&attr); if (evsel == NULL) goto out; /* use asprintf() because free(evsel) assumes name is allocated */ - if (asprintf(&evsel->name, "cycles%.*s", - attr.precise_ip ? attr.precise_ip + 1 : 0, ":ppp") < 0) + if (asprintf(&evsel->name, "cycles%s%s%.*s", + (attr.precise_ip || attr.exclude_kernel) ? ":" : "", + attr.exclude_kernel ? "u" : "", + attr.precise_ip ? attr.precise_ip + 1 : 0, "ppp") < 0) goto error_free; out: return evsel; @@ -889,8 +902,13 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, if (opts->no_samples) attr->sample_freq = 0; - if (opts->inherit_stat) + if (opts->inherit_stat) { + evsel->attr.read_format |= + PERF_FORMAT_TOTAL_TIME_ENABLED | + PERF_FORMAT_TOTAL_TIME_RUNNING | + PERF_FORMAT_ID; attr->inherit_stat = 1; + } if (opts->sample_address) { perf_evsel__set_sample_bit(evsel, ADDR); @@ -937,6 +955,9 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, if (opts->sample_address) perf_evsel__set_sample_bit(evsel, DATA_SRC); + if (opts->sample_phys_addr) + perf_evsel__set_sample_bit(evsel, PHYS_ADDR); + if (opts->no_buffering) { attr->watermark = 0; attr->wakeup_events = 1; @@ -1038,16 +1059,13 @@ static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthread return evsel->fd != NULL ? 0 : -ENOMEM; } -static int perf_evsel__run_ioctl(struct perf_evsel *evsel, int ncpus, int nthreads, +static int perf_evsel__run_ioctl(struct perf_evsel *evsel, int ioc, void *arg) { int cpu, thread; - if (evsel->system_wide) - nthreads = 1; - - for (cpu = 0; cpu < ncpus; cpu++) { - for (thread = 0; thread < nthreads; thread++) { + for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) { + for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) { int fd = FD(evsel, cpu, thread), err = ioctl(fd, ioc, arg); @@ -1059,10 +1077,9 @@ static int perf_evsel__run_ioctl(struct perf_evsel *evsel, int ncpus, int nthrea return 0; } -int perf_evsel__apply_filter(struct perf_evsel *evsel, int ncpus, int nthreads, - const char *filter) +int perf_evsel__apply_filter(struct perf_evsel *evsel, const char *filter) { - return perf_evsel__run_ioctl(evsel, ncpus, nthreads, + return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_SET_FILTER, (void *)filter); } @@ -1109,20 +1126,14 @@ int perf_evsel__append_addr_filter(struct perf_evsel *evsel, const char *filter) int perf_evsel__enable(struct perf_evsel *evsel) { - int nthreads = thread_map__nr(evsel->threads); - int ncpus = cpu_map__nr(evsel->cpus); - - return perf_evsel__run_ioctl(evsel, ncpus, nthreads, + return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, 0); } int perf_evsel__disable(struct perf_evsel *evsel) { - int nthreads = thread_map__nr(evsel->threads); - int ncpus = cpu_map__nr(evsel->cpus); - - return perf_evsel__run_ioctl(evsel, ncpus, nthreads, + return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, 0); } @@ -1172,15 +1183,12 @@ static void perf_evsel__free_config_terms(struct perf_evsel *evsel) } } -void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads) +void perf_evsel__close_fd(struct perf_evsel *evsel) { int cpu, thread; - if (evsel->system_wide) - nthreads = 1; - - for (cpu = 0; cpu < ncpus; cpu++) - for (thread = 0; thread < nthreads; ++thread) { + for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) + for (thread = 0; thread < xyarray__max_y(evsel->fd); ++thread) { close(FD(evsel, cpu, thread)); FD(evsel, cpu, thread) = -1; } @@ -1249,20 +1257,148 @@ void perf_counts_values__scale(struct perf_counts_values *count, *pscaled = scaled; } +static int perf_evsel__read_size(struct perf_evsel *evsel) +{ + u64 read_format = evsel->attr.read_format; + int entry = sizeof(u64); /* value */ + int size = 0; + int nr = 1; + + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + size += sizeof(u64); + + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + size += sizeof(u64); + + if (read_format & PERF_FORMAT_ID) + entry += sizeof(u64); + + if (read_format & PERF_FORMAT_GROUP) { + nr = evsel->nr_members; + size += sizeof(u64); + } + + size += entry * nr; + return size; +} + int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread, struct perf_counts_values *count) { + size_t size = perf_evsel__read_size(evsel); + memset(count, 0, sizeof(*count)); if (FD(evsel, cpu, thread) < 0) return -EINVAL; - if (readn(FD(evsel, cpu, thread), count, sizeof(*count)) <= 0) + if (readn(FD(evsel, cpu, thread), count->values, size) <= 0) return -errno; return 0; } +static int +perf_evsel__read_one(struct perf_evsel *evsel, int cpu, int thread) +{ + struct perf_counts_values *count = perf_counts(evsel->counts, cpu, thread); + + return perf_evsel__read(evsel, cpu, thread, count); +} + +static void +perf_evsel__set_count(struct perf_evsel *counter, int cpu, int thread, + u64 val, u64 ena, u64 run) +{ + struct perf_counts_values *count; + + count = perf_counts(counter->counts, cpu, thread); + + count->val = val; + count->ena = ena; + count->run = run; + count->loaded = true; +} + +static int +perf_evsel__process_group_data(struct perf_evsel *leader, + int cpu, int thread, u64 *data) +{ + u64 read_format = leader->attr.read_format; + struct sample_read_value *v; + u64 nr, ena = 0, run = 0, i; + + nr = *data++; + + if (nr != (u64) leader->nr_members) + return -EINVAL; + + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + ena = *data++; + + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + run = *data++; + + v = (struct sample_read_value *) data; + + perf_evsel__set_count(leader, cpu, thread, + v[0].value, ena, run); + + for (i = 1; i < nr; i++) { + struct perf_evsel *counter; + + counter = perf_evlist__id2evsel(leader->evlist, v[i].id); + if (!counter) + return -EINVAL; + + perf_evsel__set_count(counter, cpu, thread, + v[i].value, ena, run); + } + + return 0; +} + +static int +perf_evsel__read_group(struct perf_evsel *leader, int cpu, int thread) +{ + struct perf_stat_evsel *ps = leader->priv; + u64 read_format = leader->attr.read_format; + int size = perf_evsel__read_size(leader); + u64 *data = ps->group_data; + + if (!(read_format & PERF_FORMAT_ID)) + return -EINVAL; + + if (!perf_evsel__is_group_leader(leader)) + return -EINVAL; + + if (!data) { + data = zalloc(size); + if (!data) + return -ENOMEM; + + ps->group_data = data; + } + + if (FD(leader, cpu, thread) < 0) + return -EINVAL; + + if (readn(FD(leader, cpu, thread), data, size) <= 0) + return -errno; + + return perf_evsel__process_group_data(leader, cpu, thread, data); +} + +int perf_evsel__read_counter(struct perf_evsel *evsel, int cpu, int thread) +{ + u64 read_format = evsel->attr.read_format; + + if (read_format & PERF_FORMAT_GROUP) + return perf_evsel__read_group(evsel, cpu, thread); + else + return perf_evsel__read_one(evsel, cpu, thread); +} + int __perf_evsel__read_on_cpu(struct perf_evsel *evsel, int cpu, int thread, bool scale) { @@ -1331,7 +1467,7 @@ static void __p_sample_type(char *buf, size_t size, u64 value) bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW), bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER), bit_name(IDENTIFIER), bit_name(REGS_INTR), bit_name(DATA_SRC), - bit_name(WEIGHT), + bit_name(WEIGHT), bit_name(PHYS_ADDR), { .name = NULL, } }; #undef bit_name @@ -1441,7 +1577,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr, } static int __open_attr__fprintf(FILE *fp, const char *name, const char *val, - void *priv __attribute__((unused))) + void *priv __maybe_unused) { return fprintf(fp, " %-32s %s\n", name, val); } @@ -1538,6 +1674,8 @@ fallback_missing_features: if (perf_missing_features.lbr_flags) evsel->attr.branch_sample_type &= ~(PERF_SAMPLE_BRANCH_NO_FLAGS | PERF_SAMPLE_BRANCH_NO_CYCLES); + if (perf_missing_features.group_read && evsel->attr.inherit) + evsel->attr.read_format &= ~(PERF_FORMAT_GROUP|PERF_FORMAT_ID); retry_sample_id: if (perf_missing_features.sample_id_all) evsel->attr.sample_id_all = 0; @@ -1562,6 +1700,8 @@ retry_open: pr_debug2("sys_perf_event_open: pid %d cpu %d group_fd %d flags %#lx", pid, cpus->map[cpu], group_fd, flags); + test_attr__ready(); + fd = sys_perf_event_open(&evsel->attr, pid, cpus->map[cpu], group_fd, flags); @@ -1657,31 +1797,45 @@ try_fallback: */ if (!perf_missing_features.write_backward && evsel->attr.write_backward) { perf_missing_features.write_backward = true; + pr_debug2("switching off write_backward\n"); goto out_close; } else if (!perf_missing_features.clockid_wrong && evsel->attr.use_clockid) { perf_missing_features.clockid_wrong = true; + pr_debug2("switching off clockid\n"); goto fallback_missing_features; } else if (!perf_missing_features.clockid && evsel->attr.use_clockid) { perf_missing_features.clockid = true; + pr_debug2("switching off use_clockid\n"); goto fallback_missing_features; } else if (!perf_missing_features.cloexec && (flags & PERF_FLAG_FD_CLOEXEC)) { perf_missing_features.cloexec = true; + pr_debug2("switching off cloexec flag\n"); goto fallback_missing_features; } else if (!perf_missing_features.mmap2 && evsel->attr.mmap2) { perf_missing_features.mmap2 = true; + pr_debug2("switching off mmap2\n"); goto fallback_missing_features; } else if (!perf_missing_features.exclude_guest && (evsel->attr.exclude_guest || evsel->attr.exclude_host)) { perf_missing_features.exclude_guest = true; + pr_debug2("switching off exclude_guest, exclude_host\n"); goto fallback_missing_features; } else if (!perf_missing_features.sample_id_all) { perf_missing_features.sample_id_all = true; + pr_debug2("switching off sample_id_all\n"); goto retry_sample_id; } else if (!perf_missing_features.lbr_flags && (evsel->attr.branch_sample_type & (PERF_SAMPLE_BRANCH_NO_CYCLES | PERF_SAMPLE_BRANCH_NO_FLAGS))) { perf_missing_features.lbr_flags = true; + pr_debug2("switching off branch sample type no (cycles/flags)\n"); + goto fallback_missing_features; + } else if (!perf_missing_features.group_read && + evsel->attr.inherit && + (evsel->attr.read_format & PERF_FORMAT_GROUP)) { + perf_missing_features.group_read = true; + pr_debug2("switching off group read\n"); goto fallback_missing_features; } out_close: @@ -1695,12 +1849,12 @@ out_close: return err; } -void perf_evsel__close(struct perf_evsel *evsel, int ncpus, int nthreads) +void perf_evsel__close(struct perf_evsel *evsel) { if (evsel->fd == NULL) return; - perf_evsel__close_fd(evsel, ncpus, nthreads); + perf_evsel__close_fd(evsel); perf_evsel__free_fd(evsel); } @@ -2055,6 +2209,12 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, } } + data->phys_addr = 0; + if (type & PERF_SAMPLE_PHYS_ADDR) { + data->phys_addr = *array; + array++; + } + return 0; } @@ -2160,6 +2320,9 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, } } + if (type & PERF_SAMPLE_PHYS_ADDR) + result += sizeof(u64); + return result; } @@ -2349,6 +2512,11 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, } } + if (type & PERF_SAMPLE_PHYS_ADDR) { + *array = sample->phys_addr; + array++; + } + return 0; } @@ -2471,6 +2639,42 @@ bool perf_evsel__fallback(struct perf_evsel *evsel, int err, return false; } +static bool find_process(const char *name) +{ + size_t len = strlen(name); + DIR *dir; + struct dirent *d; + int ret = -1; + + dir = opendir(procfs__mountpoint()); + if (!dir) + return false; + + /* Walk through the directory. */ + while (ret && (d = readdir(dir)) != NULL) { + char path[PATH_MAX]; + char *data; + size_t size; + + if ((d->d_type != DT_DIR) || + !strcmp(".", d->d_name) || + !strcmp("..", d->d_name)) + continue; + + scnprintf(path, sizeof(path), "%s/%s/comm", + procfs__mountpoint(), d->d_name); + + if (filename__read_str(path, &data, &size)) + continue; + + ret = strncmp(name, data, len); + free(data); + } + + closedir(dir); + return ret ? false : true; +} + int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, int err, char *msg, size_t size) { @@ -2492,7 +2696,9 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, "unprivileged users (without CAP_SYS_ADMIN).\n\n" "The current value is %d:\n\n" " -1: Allow use of (almost) all events by all users\n" - ">= 0: Disallow raw tracepoint access by users without CAP_IOC_LOCK\n" + " Ignore mlock limit after perf_event_mlock_kb without CAP_IPC_LOCK\n" + ">= 0: Disallow ftrace function tracepoint by users without CAP_SYS_ADMIN\n" + " Disallow raw tracepoint access by users without CAP_SYS_ADMIN\n" ">= 1: Disallow CPU event access by users without CAP_SYS_ADMIN\n" ">= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN\n\n" "To make this setting permanent, edit /etc/sysctl.conf too, e.g.:\n\n" @@ -2567,3 +2773,10 @@ char *perf_evsel__env_arch(struct perf_evsel *evsel) return evsel->evlist->env->arch; return NULL; } + +char *perf_evsel__env_cpuid(struct perf_evsel *evsel) +{ + if (evsel && evsel->evlist && evsel->evlist->env) + return evsel->evlist->env->cpuid; + return NULL; +} diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index d101695c482c..dd2c4b5112a5 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -131,6 +131,7 @@ struct perf_evsel { bool cmdline_group_boundary; struct list_head config_terms; int bpf_fd; + bool auto_merge_stats; bool merged_stat; const char * metric_expr; const char * metric_name; @@ -185,7 +186,7 @@ static inline struct perf_evsel *perf_evsel__newtp(const char *sys, const char * return perf_evsel__newtp_idx(sys, name, 0); } -struct perf_evsel *perf_evsel__new_cycles(void); +struct perf_evsel *perf_evsel__new_cycles(bool precise); struct event_format *event_format__new(const char *sys, const char *name); @@ -226,7 +227,7 @@ const char *perf_evsel__group_name(struct perf_evsel *evsel); int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size); int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads); -void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads); +void perf_evsel__close_fd(struct perf_evsel *evsel); void __perf_evsel__set_sample_bit(struct perf_evsel *evsel, enum perf_event_sample_format bit); @@ -246,8 +247,7 @@ int perf_evsel__set_filter(struct perf_evsel *evsel, const char *filter); int perf_evsel__append_tp_filter(struct perf_evsel *evsel, const char *filter); int perf_evsel__append_addr_filter(struct perf_evsel *evsel, const char *filter); -int perf_evsel__apply_filter(struct perf_evsel *evsel, int ncpus, int nthreads, - const char *filter); +int perf_evsel__apply_filter(struct perf_evsel *evsel, const char *filter); int perf_evsel__enable(struct perf_evsel *evsel); int perf_evsel__disable(struct perf_evsel *evsel); @@ -257,7 +257,7 @@ int perf_evsel__open_per_thread(struct perf_evsel *evsel, struct thread_map *threads); int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, struct thread_map *threads); -void perf_evsel__close(struct perf_evsel *evsel, int ncpus, int nthreads); +void perf_evsel__close(struct perf_evsel *evsel); struct perf_sample; @@ -299,6 +299,8 @@ static inline bool perf_evsel__match2(struct perf_evsel *e1, int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread, struct perf_counts_values *count); +int perf_evsel__read_counter(struct perf_evsel *evsel, int cpu, int thread); + int __perf_evsel__read_on_cpu(struct perf_evsel *evsel, int cpu, int thread, bool scale); @@ -436,5 +438,6 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr, attr__fprintf_f attr__fprintf, void *priv); char *perf_evsel__env_arch(struct perf_evsel *evsel); +char *perf_evsel__env_cpuid(struct perf_evsel *evsel); #endif /* __PERF_EVSEL_H */ diff --git a/tools/perf/util/expr.h b/tools/perf/util/expr.h index 9c2760a1a96e..400ef9eab00a 100644 --- a/tools/perf/util/expr.h +++ b/tools/perf/util/expr.h @@ -1,7 +1,7 @@ #ifndef PARSE_CTX_H #define PARSE_CTX_H 1 -#define EXPR_MAX_OTHER 8 +#define EXPR_MAX_OTHER 15 #define MAX_PARSE_ID EXPR_MAX_OTHER struct parse_id { diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y index 954556bea36e..432b8560cf51 100644 --- a/tools/perf/util/expr.y +++ b/tools/perf/util/expr.y @@ -4,6 +4,7 @@ #include "util/debug.h" #define IN_EXPR_Y 1 #include "expr.h" +#include "smt.h" #include <string.h> #define MAXIDLEN 256 @@ -22,13 +23,15 @@ %token <num> NUMBER %token <id> ID +%token MIN MAX IF ELSE SMT_ON +%left MIN MAX IF %left '|' %left '^' %left '&' %left '-' '+' %left '*' '/' '%' %left NEG NOT -%type <num> expr +%type <num> expr if_expr %{ static int expr__lex(YYSTYPE *res, const char **pp); @@ -57,22 +60,33 @@ static int lookup_id(struct parse_ctx *ctx, char *id, double *val) %} %% -all_expr: expr { *final_val = $1; } +all_expr: if_expr { *final_val = $1; } + ; + +if_expr: + expr IF expr ELSE expr { $$ = $3 ? $1 : $5; } + | expr ; expr: NUMBER | ID { if (lookup_id(ctx, $1, &$$) < 0) { - pr_debug("%s not found", $1); + pr_debug("%s not found\n", $1); YYABORT; } } + | expr '|' expr { $$ = (long)$1 | (long)$3; } + | expr '&' expr { $$ = (long)$1 & (long)$3; } + | expr '^' expr { $$ = (long)$1 ^ (long)$3; } | expr '+' expr { $$ = $1 + $3; } | expr '-' expr { $$ = $1 - $3; } | expr '*' expr { $$ = $1 * $3; } | expr '/' expr { if ($3 == 0) YYABORT; $$ = $1 / $3; } | expr '%' expr { if ((long)$3 == 0) YYABORT; $$ = (long)$1 % (long)$3; } | '-' expr %prec NEG { $$ = -$2; } - | '(' expr ')' { $$ = $2; } + | '(' if_expr ')' { $$ = $2; } + | MIN '(' expr ',' expr ')' { $$ = $3 < $5 ? $3 : $5; } + | MAX '(' expr ',' expr ')' { $$ = $3 > $5 ? $3 : $5; } + | SMT_ON { $$ = smt_on() > 0; } ; %% @@ -82,13 +96,47 @@ static int expr__symbol(YYSTYPE *res, const char *p, const char **pp) char *dst = res->id; const char *s = p; - while (isalnum(*p) || *p == '_' || *p == '.') { + if (*p == '#') + *dst++ = *p++; + + while (isalnum(*p) || *p == '_' || *p == '.' || *p == ':' || *p == '@' || *p == '\\') { if (p - s >= MAXIDLEN) return -1; - *dst++ = *p++; + /* + * Allow @ instead of / to be able to specify pmu/event/ without + * conflicts with normal division. + */ + if (*p == '@') + *dst++ = '/'; + else if (*p == '\\') + *dst++ = *++p; + else + *dst++ = *p; + p++; } *dst = 0; *pp = p; + dst = res->id; + switch (dst[0]) { + case 'm': + if (!strcmp(dst, "min")) + return MIN; + if (!strcmp(dst, "max")) + return MAX; + break; + case 'i': + if (!strcmp(dst, "if")) + return IF; + break; + case 'e': + if (!strcmp(dst, "else")) + return ELSE; + break; + case '#': + if (!strcasecmp(dst, "#smt_on")) + return SMT_ON; + break; + } return ID; } @@ -102,6 +150,7 @@ static int expr__lex(YYSTYPE *res, const char **pp) p++; s = p; switch (*p++) { + case '#': case 'a' ... 'z': case 'A' ... 'Z': return expr__symbol(res, p - 1, pp); @@ -132,6 +181,19 @@ void expr__ctx_init(struct parse_ctx *ctx) ctx->num_ids = 0; } +static bool already_seen(const char *val, const char *one, const char **other, + int num_other) +{ + int i; + + if (one && !strcasecmp(one, val)) + return true; + for (i = 0; i < num_other; i++) + if (!strcasecmp(other[i], val)) + return true; + return false; +} + int expr__find_other(const char *p, const char *one, const char ***other, int *num_otherp) { @@ -151,7 +213,7 @@ int expr__find_other(const char *p, const char *one, const char ***other, err = 0; break; } - if (tok == ID && strcasecmp(one, val.id)) { + if (tok == ID && !already_seen(val.id, one, *other, num_other)) { if (num_other >= EXPR_MAX_OTHER - 1) { pr_debug("Too many extra events in %s\n", orig); break; diff --git a/tools/perf/util/genelf_debug.c b/tools/perf/util/genelf_debug.c index 5980f7d256b1..40789d8603d0 100644 --- a/tools/perf/util/genelf_debug.c +++ b/tools/perf/util/genelf_debug.c @@ -11,6 +11,7 @@ * @remark Copyright 2007 OProfile authors * @author Philippe Elie */ +#include <linux/compiler.h> #include <sys/types.h> #include <stdio.h> #include <getopt.h> @@ -125,7 +126,7 @@ struct debug_line_header { * and filesize, last entry is followed by en empty string. */ /* follow the first program statement */ -} __attribute__((packed)); +} __packed; /* DWARF 2 spec talk only about one possible compilation unit header while * binutils can handle two flavours of dwarf 2, 32 and 64 bits, this is not @@ -138,7 +139,7 @@ struct compilation_unit_header { uhalf version; uword debug_abbrev_offset; ubyte pointer_size; -} __attribute__((packed)); +} __packed; #define DW_LNS_num_opcode (DW_LNS_set_isa + 1) diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index b5baff3007bb..605bbd5404fb 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -8,9 +8,11 @@ #include <unistd.h> #include <stdio.h> #include <stdlib.h> +#include <linux/compiler.h> #include <linux/list.h> #include <linux/kernel.h> #include <linux/bitops.h> +#include <linux/stringify.h> #include <sys/stat.h> #include <sys/types.h> #include <sys/utsname.h> @@ -33,6 +35,7 @@ #include "data.h" #include <api/fs/fs.h> #include "asm/bug.h" +#include "tool.h" #include "sane_ctype.h" @@ -58,6 +61,15 @@ struct perf_file_attr { struct perf_file_section ids; }; +struct feat_fd { + struct perf_header *ph; + int fd; + void *buf; /* Either buf != NULL or fd >= 0 */ + ssize_t offset; + size_t size; + struct perf_evsel *events; +}; + void perf_header__set_feat(struct perf_header *header, int feat) { set_bit(feat, header->adds_features); @@ -73,28 +85,60 @@ bool perf_header__has_feat(const struct perf_header *header, int feat) return test_bit(feat, header->adds_features); } -static int do_write(int fd, const void *buf, size_t size) +static int __do_write_fd(struct feat_fd *ff, const void *buf, size_t size) { - while (size) { - int ret = write(fd, buf, size); + ssize_t ret = writen(ff->fd, buf, size); - if (ret < 0) - return -errno; + if (ret != (ssize_t)size) + return ret < 0 ? (int)ret : -1; + return 0; +} + +static int __do_write_buf(struct feat_fd *ff, const void *buf, size_t size) +{ + /* struct perf_event_header::size is u16 */ + const size_t max_size = 0xffff - sizeof(struct perf_event_header); + size_t new_size = ff->size; + void *addr; - size -= ret; - buf += ret; + if (size + ff->offset > max_size) + return -E2BIG; + + while (size > (new_size - ff->offset)) + new_size <<= 1; + new_size = min(max_size, new_size); + + if (ff->size < new_size) { + addr = realloc(ff->buf, new_size); + if (!addr) + return -ENOMEM; + ff->buf = addr; + ff->size = new_size; } + memcpy(ff->buf + ff->offset, buf, size); + ff->offset += size; + return 0; } -int write_padded(int fd, const void *bf, size_t count, size_t count_aligned) +/* Return: 0 if succeded, -ERR if failed. */ +int do_write(struct feat_fd *ff, const void *buf, size_t size) +{ + if (!ff->buf) + return __do_write_fd(ff, buf, size); + return __do_write_buf(ff, buf, size); +} + +/* Return: 0 if succeded, -ERR if failed. */ +int write_padded(struct feat_fd *ff, const void *bf, + size_t count, size_t count_aligned) { static const char zero_buf[NAME_ALIGN]; - int err = do_write(fd, bf, count); + int err = do_write(ff, bf, count); if (!err) - err = do_write(fd, zero_buf, count_aligned - count); + err = do_write(ff, zero_buf, count_aligned - count); return err; } @@ -102,7 +146,8 @@ int write_padded(int fd, const void *bf, size_t count, size_t count_aligned) #define string_size(str) \ (PERF_ALIGN((strlen(str) + 1), NAME_ALIGN) + sizeof(u32)) -static int do_write_string(int fd, const char *str) +/* Return: 0 if succeded, -ERR if failed. */ +static int do_write_string(struct feat_fd *ff, const char *str) { u32 len, olen; int ret; @@ -111,32 +156,80 @@ static int do_write_string(int fd, const char *str) len = PERF_ALIGN(olen, NAME_ALIGN); /* write len, incl. \0 */ - ret = do_write(fd, &len, sizeof(len)); + ret = do_write(ff, &len, sizeof(len)); if (ret < 0) return ret; - return write_padded(fd, str, olen, len); + return write_padded(ff, str, olen, len); } -static char *do_read_string(int fd, struct perf_header *ph) +static int __do_read_fd(struct feat_fd *ff, void *addr, ssize_t size) +{ + ssize_t ret = readn(ff->fd, addr, size); + + if (ret != size) + return ret < 0 ? (int)ret : -1; + return 0; +} + +static int __do_read_buf(struct feat_fd *ff, void *addr, ssize_t size) +{ + if (size > (ssize_t)ff->size - ff->offset) + return -1; + + memcpy(addr, ff->buf + ff->offset, size); + ff->offset += size; + + return 0; + +} + +static int __do_read(struct feat_fd *ff, void *addr, ssize_t size) +{ + if (!ff->buf) + return __do_read_fd(ff, addr, size); + return __do_read_buf(ff, addr, size); +} + +static int do_read_u32(struct feat_fd *ff, u32 *addr) +{ + int ret; + + ret = __do_read(ff, addr, sizeof(*addr)); + if (ret) + return ret; + + if (ff->ph->needs_swap) + *addr = bswap_32(*addr); + return 0; +} + +static int do_read_u64(struct feat_fd *ff, u64 *addr) +{ + int ret; + + ret = __do_read(ff, addr, sizeof(*addr)); + if (ret) + return ret; + + if (ff->ph->needs_swap) + *addr = bswap_64(*addr); + return 0; +} + +static char *do_read_string(struct feat_fd *ff) { - ssize_t sz, ret; u32 len; char *buf; - sz = readn(fd, &len, sizeof(len)); - if (sz < (ssize_t)sizeof(len)) + if (do_read_u32(ff, &len)) return NULL; - if (ph->needs_swap) - len = bswap_32(len); - buf = malloc(len); if (!buf) return NULL; - ret = readn(fd, buf, len); - if (ret == (ssize_t)len) { + if (!__do_read(ff, buf, len)) { /* * strings are padded by zeroes * thus the actual strlen of buf @@ -149,25 +242,30 @@ static char *do_read_string(int fd, struct perf_header *ph) return NULL; } -static int write_tracing_data(int fd, struct perf_header *h __maybe_unused, - struct perf_evlist *evlist) +static int write_tracing_data(struct feat_fd *ff, + struct perf_evlist *evlist) { - return read_tracing_data(fd, &evlist->entries); -} + if (WARN(ff->buf, "Error: calling %s in pipe-mode.\n", __func__)) + return -1; + return read_tracing_data(ff->fd, &evlist->entries); +} -static int write_build_id(int fd, struct perf_header *h, +static int write_build_id(struct feat_fd *ff, struct perf_evlist *evlist __maybe_unused) { struct perf_session *session; int err; - session = container_of(h, struct perf_session, header); + session = container_of(ff->ph, struct perf_session, header); if (!perf_session__read_build_ids(session, true)) return -1; - err = perf_session__write_buildid_table(session, fd); + if (WARN(ff->buf, "Error: calling %s in pipe-mode.\n", __func__)) + return -1; + + err = perf_session__write_buildid_table(session, ff); if (err < 0) { pr_debug("failed to write buildid table\n"); return err; @@ -177,7 +275,7 @@ static int write_build_id(int fd, struct perf_header *h, return 0; } -static int write_hostname(int fd, struct perf_header *h __maybe_unused, +static int write_hostname(struct feat_fd *ff, struct perf_evlist *evlist __maybe_unused) { struct utsname uts; @@ -187,10 +285,10 @@ static int write_hostname(int fd, struct perf_header *h __maybe_unused, if (ret < 0) return -1; - return do_write_string(fd, uts.nodename); + return do_write_string(ff, uts.nodename); } -static int write_osrelease(int fd, struct perf_header *h __maybe_unused, +static int write_osrelease(struct feat_fd *ff, struct perf_evlist *evlist __maybe_unused) { struct utsname uts; @@ -200,10 +298,10 @@ static int write_osrelease(int fd, struct perf_header *h __maybe_unused, if (ret < 0) return -1; - return do_write_string(fd, uts.release); + return do_write_string(ff, uts.release); } -static int write_arch(int fd, struct perf_header *h __maybe_unused, +static int write_arch(struct feat_fd *ff, struct perf_evlist *evlist __maybe_unused) { struct utsname uts; @@ -213,16 +311,16 @@ static int write_arch(int fd, struct perf_header *h __maybe_unused, if (ret < 0) return -1; - return do_write_string(fd, uts.machine); + return do_write_string(ff, uts.machine); } -static int write_version(int fd, struct perf_header *h __maybe_unused, +static int write_version(struct feat_fd *ff, struct perf_evlist *evlist __maybe_unused) { - return do_write_string(fd, perf_version_string); + return do_write_string(ff, perf_version_string); } -static int __write_cpudesc(int fd, const char *cpuinfo_proc) +static int __write_cpudesc(struct feat_fd *ff, const char *cpuinfo_proc) { FILE *file; char *buf = NULL; @@ -272,25 +370,22 @@ static int __write_cpudesc(int fd, const char *cpuinfo_proc) } p++; } - ret = do_write_string(fd, s); + ret = do_write_string(ff, s); done: free(buf); fclose(file); return ret; } -static int write_cpudesc(int fd, struct perf_header *h __maybe_unused, +static int write_cpudesc(struct feat_fd *ff, struct perf_evlist *evlist __maybe_unused) { -#ifndef CPUINFO_PROC -#define CPUINFO_PROC {"model name", } -#endif const char *cpuinfo_procs[] = CPUINFO_PROC; unsigned int i; for (i = 0; i < ARRAY_SIZE(cpuinfo_procs); i++) { int ret; - ret = __write_cpudesc(fd, cpuinfo_procs[i]); + ret = __write_cpudesc(ff, cpuinfo_procs[i]); if (ret >= 0) return ret; } @@ -298,7 +393,7 @@ static int write_cpudesc(int fd, struct perf_header *h __maybe_unused, } -static int write_nrcpus(int fd, struct perf_header *h __maybe_unused, +static int write_nrcpus(struct feat_fd *ff, struct perf_evlist *evlist __maybe_unused) { long nr; @@ -313,14 +408,14 @@ static int write_nrcpus(int fd, struct perf_header *h __maybe_unused, nra = (u32)(nr & UINT_MAX); - ret = do_write(fd, &nrc, sizeof(nrc)); + ret = do_write(ff, &nrc, sizeof(nrc)); if (ret < 0) return ret; - return do_write(fd, &nra, sizeof(nra)); + return do_write(ff, &nra, sizeof(nra)); } -static int write_event_desc(int fd, struct perf_header *h __maybe_unused, +static int write_event_desc(struct feat_fd *ff, struct perf_evlist *evlist) { struct perf_evsel *evsel; @@ -332,7 +427,7 @@ static int write_event_desc(int fd, struct perf_header *h __maybe_unused, /* * write number of events */ - ret = do_write(fd, &nre, sizeof(nre)); + ret = do_write(ff, &nre, sizeof(nre)); if (ret < 0) return ret; @@ -340,12 +435,12 @@ static int write_event_desc(int fd, struct perf_header *h __maybe_unused, * size of perf_event_attr struct */ sz = (u32)sizeof(evsel->attr); - ret = do_write(fd, &sz, sizeof(sz)); + ret = do_write(ff, &sz, sizeof(sz)); if (ret < 0) return ret; evlist__for_each_entry(evlist, evsel) { - ret = do_write(fd, &evsel->attr, sz); + ret = do_write(ff, &evsel->attr, sz); if (ret < 0) return ret; /* @@ -356,27 +451,27 @@ static int write_event_desc(int fd, struct perf_header *h __maybe_unused, * type of ids, */ nri = evsel->ids; - ret = do_write(fd, &nri, sizeof(nri)); + ret = do_write(ff, &nri, sizeof(nri)); if (ret < 0) return ret; /* * write event string as passed on cmdline */ - ret = do_write_string(fd, perf_evsel__name(evsel)); + ret = do_write_string(ff, perf_evsel__name(evsel)); if (ret < 0) return ret; /* * write unique ids for this event */ - ret = do_write(fd, evsel->id, evsel->ids * sizeof(u64)); + ret = do_write(ff, evsel->id, evsel->ids * sizeof(u64)); if (ret < 0) return ret; } return 0; } -static int write_cmdline(int fd, struct perf_header *h __maybe_unused, +static int write_cmdline(struct feat_fd *ff, struct perf_evlist *evlist __maybe_unused) { char buf[MAXPATHLEN]; @@ -394,16 +489,16 @@ static int write_cmdline(int fd, struct perf_header *h __maybe_unused, /* account for binary path */ n = perf_env.nr_cmdline + 1; - ret = do_write(fd, &n, sizeof(n)); + ret = do_write(ff, &n, sizeof(n)); if (ret < 0) return ret; - ret = do_write_string(fd, buf); + ret = do_write_string(ff, buf); if (ret < 0) return ret; for (i = 0 ; i < perf_env.nr_cmdline; i++) { - ret = do_write_string(fd, perf_env.cmdline_argv[i]); + ret = do_write_string(ff, perf_env.cmdline_argv[i]); if (ret < 0) return ret; } @@ -556,8 +651,8 @@ out_free: return tp; } -static int write_cpu_topology(int fd, struct perf_header *h __maybe_unused, - struct perf_evlist *evlist __maybe_unused) +static int write_cpu_topology(struct feat_fd *ff, + struct perf_evlist *evlist __maybe_unused) { struct cpu_topo *tp; u32 i; @@ -567,21 +662,21 @@ static int write_cpu_topology(int fd, struct perf_header *h __maybe_unused, if (!tp) return -1; - ret = do_write(fd, &tp->core_sib, sizeof(tp->core_sib)); + ret = do_write(ff, &tp->core_sib, sizeof(tp->core_sib)); if (ret < 0) goto done; for (i = 0; i < tp->core_sib; i++) { - ret = do_write_string(fd, tp->core_siblings[i]); + ret = do_write_string(ff, tp->core_siblings[i]); if (ret < 0) goto done; } - ret = do_write(fd, &tp->thread_sib, sizeof(tp->thread_sib)); + ret = do_write(ff, &tp->thread_sib, sizeof(tp->thread_sib)); if (ret < 0) goto done; for (i = 0; i < tp->thread_sib; i++) { - ret = do_write_string(fd, tp->thread_siblings[i]); + ret = do_write_string(ff, tp->thread_siblings[i]); if (ret < 0) break; } @@ -591,11 +686,11 @@ static int write_cpu_topology(int fd, struct perf_header *h __maybe_unused, goto done; for (j = 0; j < perf_env.nr_cpus_avail; j++) { - ret = do_write(fd, &perf_env.cpu[j].core_id, + ret = do_write(ff, &perf_env.cpu[j].core_id, sizeof(perf_env.cpu[j].core_id)); if (ret < 0) return ret; - ret = do_write(fd, &perf_env.cpu[j].socket_id, + ret = do_write(ff, &perf_env.cpu[j].socket_id, sizeof(perf_env.cpu[j].socket_id)); if (ret < 0) return ret; @@ -607,8 +702,8 @@ done: -static int write_total_mem(int fd, struct perf_header *h __maybe_unused, - struct perf_evlist *evlist __maybe_unused) +static int write_total_mem(struct feat_fd *ff, + struct perf_evlist *evlist __maybe_unused) { char *buf = NULL; FILE *fp; @@ -628,7 +723,7 @@ static int write_total_mem(int fd, struct perf_header *h __maybe_unused, if (!ret) { n = sscanf(buf, "%*s %"PRIu64, &mem); if (n == 1) - ret = do_write(fd, &mem, sizeof(mem)); + ret = do_write(ff, &mem, sizeof(mem)); } else ret = -1; free(buf); @@ -636,7 +731,7 @@ static int write_total_mem(int fd, struct perf_header *h __maybe_unused, return ret; } -static int write_topo_node(int fd, int node) +static int write_topo_node(struct feat_fd *ff, int node) { char str[MAXPATHLEN]; char field[32]; @@ -666,11 +761,11 @@ static int write_topo_node(int fd, int node) fclose(fp); fp = NULL; - ret = do_write(fd, &mem_total, sizeof(u64)); + ret = do_write(ff, &mem_total, sizeof(u64)); if (ret) goto done; - ret = do_write(fd, &mem_free, sizeof(u64)); + ret = do_write(ff, &mem_free, sizeof(u64)); if (ret) goto done; @@ -688,7 +783,7 @@ static int write_topo_node(int fd, int node) if (p) *p = '\0'; - ret = do_write_string(fd, buf); + ret = do_write_string(ff, buf); done: free(buf); if (fp) @@ -696,8 +791,8 @@ done: return ret; } -static int write_numa_topology(int fd, struct perf_header *h __maybe_unused, - struct perf_evlist *evlist __maybe_unused) +static int write_numa_topology(struct feat_fd *ff, + struct perf_evlist *evlist __maybe_unused) { char *buf = NULL; size_t len = 0; @@ -724,17 +819,17 @@ static int write_numa_topology(int fd, struct perf_header *h __maybe_unused, nr = (u32)node_map->nr; - ret = do_write(fd, &nr, sizeof(nr)); + ret = do_write(ff, &nr, sizeof(nr)); if (ret < 0) goto done; for (i = 0; i < nr; i++) { j = (u32)node_map->map[i]; - ret = do_write(fd, &j, sizeof(j)); + ret = do_write(ff, &j, sizeof(j)); if (ret < 0) break; - ret = write_topo_node(fd, i); + ret = write_topo_node(ff, i); if (ret < 0) break; } @@ -757,39 +852,40 @@ done: * }; */ -static int write_pmu_mappings(int fd, struct perf_header *h __maybe_unused, +static int write_pmu_mappings(struct feat_fd *ff, struct perf_evlist *evlist __maybe_unused) { struct perf_pmu *pmu = NULL; - off_t offset = lseek(fd, 0, SEEK_CUR); - __u32 pmu_num = 0; + u32 pmu_num = 0; int ret; - /* write real pmu_num later */ - ret = do_write(fd, &pmu_num, sizeof(pmu_num)); + /* + * Do a first pass to count number of pmu to avoid lseek so this + * works in pipe mode as well. + */ + while ((pmu = perf_pmu__scan(pmu))) { + if (!pmu->name) + continue; + pmu_num++; + } + + ret = do_write(ff, &pmu_num, sizeof(pmu_num)); if (ret < 0) return ret; while ((pmu = perf_pmu__scan(pmu))) { if (!pmu->name) continue; - pmu_num++; - ret = do_write(fd, &pmu->type, sizeof(pmu->type)); + ret = do_write(ff, &pmu->type, sizeof(pmu->type)); if (ret < 0) return ret; - ret = do_write_string(fd, pmu->name); + ret = do_write_string(ff, pmu->name); if (ret < 0) return ret; } - if (pwrite(fd, &pmu_num, sizeof(pmu_num), offset) != sizeof(pmu_num)) { - /* discard all */ - lseek(fd, offset, SEEK_SET); - return -1; - } - return 0; } @@ -805,14 +901,14 @@ static int write_pmu_mappings(int fd, struct perf_header *h __maybe_unused, * }[nr_groups]; * }; */ -static int write_group_desc(int fd, struct perf_header *h __maybe_unused, +static int write_group_desc(struct feat_fd *ff, struct perf_evlist *evlist) { u32 nr_groups = evlist->nr_groups; struct perf_evsel *evsel; int ret; - ret = do_write(fd, &nr_groups, sizeof(nr_groups)); + ret = do_write(ff, &nr_groups, sizeof(nr_groups)); if (ret < 0) return ret; @@ -823,15 +919,15 @@ static int write_group_desc(int fd, struct perf_header *h __maybe_unused, u32 leader_idx = evsel->idx; u32 nr_members = evsel->nr_members; - ret = do_write_string(fd, name); + ret = do_write_string(ff, name); if (ret < 0) return ret; - ret = do_write(fd, &leader_idx, sizeof(leader_idx)); + ret = do_write(ff, &leader_idx, sizeof(leader_idx)); if (ret < 0) return ret; - ret = do_write(fd, &nr_members, sizeof(nr_members)); + ret = do_write(ff, &nr_members, sizeof(nr_members)); if (ret < 0) return ret; } @@ -848,7 +944,7 @@ int __weak get_cpuid(char *buffer __maybe_unused, size_t sz __maybe_unused) return -1; } -static int write_cpuid(int fd, struct perf_header *h __maybe_unused, +static int write_cpuid(struct feat_fd *ff, struct perf_evlist *evlist __maybe_unused) { char buffer[64]; @@ -860,25 +956,27 @@ static int write_cpuid(int fd, struct perf_header *h __maybe_unused, return -1; write_it: - return do_write_string(fd, buffer); + return do_write_string(ff, buffer); } -static int write_branch_stack(int fd __maybe_unused, - struct perf_header *h __maybe_unused, - struct perf_evlist *evlist __maybe_unused) +static int write_branch_stack(struct feat_fd *ff __maybe_unused, + struct perf_evlist *evlist __maybe_unused) { return 0; } -static int write_auxtrace(int fd, struct perf_header *h, +static int write_auxtrace(struct feat_fd *ff, struct perf_evlist *evlist __maybe_unused) { struct perf_session *session; int err; - session = container_of(h, struct perf_session, header); + if (WARN(ff->buf, "Error: calling %s in pipe-mode.\n", __func__)) + return -1; + + session = container_of(ff->ph, struct perf_session, header); - err = auxtrace_index__write(fd, &session->auxtrace_index); + err = auxtrace_index__write(ff->fd, &session->auxtrace_index); if (err < 0) pr_err("Failed to write auxtrace index\n"); return err; @@ -1025,8 +1123,8 @@ static int build_caches(struct cpu_cache_level caches[], u32 size, u32 *cntp) #define MAX_CACHES 2000 -static int write_cache(int fd, struct perf_header *h __maybe_unused, - struct perf_evlist *evlist __maybe_unused) +static int write_cache(struct feat_fd *ff, + struct perf_evlist *evlist __maybe_unused) { struct cpu_cache_level caches[MAX_CACHES]; u32 cnt = 0, i, version = 1; @@ -1038,11 +1136,11 @@ static int write_cache(int fd, struct perf_header *h __maybe_unused, qsort(&caches, cnt, sizeof(struct cpu_cache_level), cpu_cache_level__sort); - ret = do_write(fd, &version, sizeof(u32)); + ret = do_write(ff, &version, sizeof(u32)); if (ret < 0) goto out; - ret = do_write(fd, &cnt, sizeof(u32)); + ret = do_write(ff, &cnt, sizeof(u32)); if (ret < 0) goto out; @@ -1050,7 +1148,7 @@ static int write_cache(int fd, struct perf_header *h __maybe_unused, struct cpu_cache_level *c = &caches[i]; #define _W(v) \ - ret = do_write(fd, &c->v, sizeof(u32)); \ + ret = do_write(ff, &c->v, sizeof(u32)); \ if (ret < 0) \ goto out; @@ -1061,7 +1159,7 @@ static int write_cache(int fd, struct perf_header *h __maybe_unused, #undef _W #define _W(v) \ - ret = do_write_string(fd, (const char *) c->v); \ + ret = do_write_string(ff, (const char *) c->v); \ if (ret < 0) \ goto out; @@ -1077,69 +1175,62 @@ out: return ret; } -static int write_stat(int fd __maybe_unused, - struct perf_header *h __maybe_unused, +static int write_stat(struct feat_fd *ff __maybe_unused, struct perf_evlist *evlist __maybe_unused) { return 0; } -static void print_hostname(struct perf_header *ph, int fd __maybe_unused, - FILE *fp) +static void print_hostname(struct feat_fd *ff, FILE *fp) { - fprintf(fp, "# hostname : %s\n", ph->env.hostname); + fprintf(fp, "# hostname : %s\n", ff->ph->env.hostname); } -static void print_osrelease(struct perf_header *ph, int fd __maybe_unused, - FILE *fp) +static void print_osrelease(struct feat_fd *ff, FILE *fp) { - fprintf(fp, "# os release : %s\n", ph->env.os_release); + fprintf(fp, "# os release : %s\n", ff->ph->env.os_release); } -static void print_arch(struct perf_header *ph, int fd __maybe_unused, FILE *fp) +static void print_arch(struct feat_fd *ff, FILE *fp) { - fprintf(fp, "# arch : %s\n", ph->env.arch); + fprintf(fp, "# arch : %s\n", ff->ph->env.arch); } -static void print_cpudesc(struct perf_header *ph, int fd __maybe_unused, - FILE *fp) +static void print_cpudesc(struct feat_fd *ff, FILE *fp) { - fprintf(fp, "# cpudesc : %s\n", ph->env.cpu_desc); + fprintf(fp, "# cpudesc : %s\n", ff->ph->env.cpu_desc); } -static void print_nrcpus(struct perf_header *ph, int fd __maybe_unused, - FILE *fp) +static void print_nrcpus(struct feat_fd *ff, FILE *fp) { - fprintf(fp, "# nrcpus online : %u\n", ph->env.nr_cpus_online); - fprintf(fp, "# nrcpus avail : %u\n", ph->env.nr_cpus_avail); + fprintf(fp, "# nrcpus online : %u\n", ff->ph->env.nr_cpus_online); + fprintf(fp, "# nrcpus avail : %u\n", ff->ph->env.nr_cpus_avail); } -static void print_version(struct perf_header *ph, int fd __maybe_unused, - FILE *fp) +static void print_version(struct feat_fd *ff, FILE *fp) { - fprintf(fp, "# perf version : %s\n", ph->env.version); + fprintf(fp, "# perf version : %s\n", ff->ph->env.version); } -static void print_cmdline(struct perf_header *ph, int fd __maybe_unused, - FILE *fp) +static void print_cmdline(struct feat_fd *ff, FILE *fp) { int nr, i; - nr = ph->env.nr_cmdline; + nr = ff->ph->env.nr_cmdline; fprintf(fp, "# cmdline : "); for (i = 0; i < nr; i++) - fprintf(fp, "%s ", ph->env.cmdline_argv[i]); + fprintf(fp, "%s ", ff->ph->env.cmdline_argv[i]); fputc('\n', fp); } -static void print_cpu_topology(struct perf_header *ph, int fd __maybe_unused, - FILE *fp) +static void print_cpu_topology(struct feat_fd *ff, FILE *fp) { + struct perf_header *ph = ff->ph; + int cpu_nr = ph->env.nr_cpus_avail; int nr, i; char *str; - int cpu_nr = ph->env.nr_cpus_avail; nr = ph->env.nr_sibling_cores; str = ph->env.sibling_cores; @@ -1180,31 +1271,21 @@ static void free_event_desc(struct perf_evsel *events) free(events); } -static struct perf_evsel * -read_event_desc(struct perf_header *ph, int fd) +static struct perf_evsel *read_event_desc(struct feat_fd *ff) { struct perf_evsel *evsel, *events = NULL; u64 *id; void *buf = NULL; u32 nre, sz, nr, i, j; - ssize_t ret; size_t msz; /* number of events */ - ret = readn(fd, &nre, sizeof(nre)); - if (ret != (ssize_t)sizeof(nre)) + if (do_read_u32(ff, &nre)) goto error; - if (ph->needs_swap) - nre = bswap_32(nre); - - ret = readn(fd, &sz, sizeof(sz)); - if (ret != (ssize_t)sizeof(sz)) + if (do_read_u32(ff, &sz)) goto error; - if (ph->needs_swap) - sz = bswap_32(sz); - /* buffer to hold on file attr struct */ buf = malloc(sz); if (!buf) @@ -1226,25 +1307,23 @@ read_event_desc(struct perf_header *ph, int fd) * must read entire on-file attr struct to * sync up with layout. */ - ret = readn(fd, buf, sz); - if (ret != (ssize_t)sz) + if (__do_read(ff, buf, sz)) goto error; - if (ph->needs_swap) + if (ff->ph->needs_swap) perf_event__attr_swap(buf); memcpy(&evsel->attr, buf, msz); - ret = readn(fd, &nr, sizeof(nr)); - if (ret != (ssize_t)sizeof(nr)) + if (do_read_u32(ff, &nr)) goto error; - if (ph->needs_swap) { - nr = bswap_32(nr); + if (ff->ph->needs_swap) evsel->needs_swap = true; - } - evsel->name = do_read_string(fd, ph); + evsel->name = do_read_string(ff); + if (!evsel->name) + goto error; if (!nr) continue; @@ -1256,11 +1335,8 @@ read_event_desc(struct perf_header *ph, int fd) evsel->id = id; for (j = 0 ; j < nr; j++) { - ret = readn(fd, id, sizeof(*id)); - if (ret != (ssize_t)sizeof(*id)) + if (do_read_u64(ff, id)) goto error; - if (ph->needs_swap) - *id = bswap_64(*id); id++; } } @@ -1274,17 +1350,22 @@ error: } static int __desc_attr__fprintf(FILE *fp, const char *name, const char *val, - void *priv __attribute__((unused))) + void *priv __maybe_unused) { return fprintf(fp, ", %s = %s", name, val); } -static void print_event_desc(struct perf_header *ph, int fd, FILE *fp) +static void print_event_desc(struct feat_fd *ff, FILE *fp) { - struct perf_evsel *evsel, *events = read_event_desc(ph, fd); + struct perf_evsel *evsel, *events; u32 j; u64 *id; + if (ff->events) + events = ff->events; + else + events = read_event_desc(ff); + if (!events) { fprintf(fp, "# event desc: not available or unable to read\n"); return; @@ -1309,22 +1390,21 @@ static void print_event_desc(struct perf_header *ph, int fd, FILE *fp) } free_event_desc(events); + ff->events = NULL; } -static void print_total_mem(struct perf_header *ph, int fd __maybe_unused, - FILE *fp) +static void print_total_mem(struct feat_fd *ff, FILE *fp) { - fprintf(fp, "# total memory : %Lu kB\n", ph->env.total_mem); + fprintf(fp, "# total memory : %llu kB\n", ff->ph->env.total_mem); } -static void print_numa_topology(struct perf_header *ph, int fd __maybe_unused, - FILE *fp) +static void print_numa_topology(struct feat_fd *ff, FILE *fp) { int i; struct numa_node *n; - for (i = 0; i < ph->env.nr_numa_nodes; i++) { - n = &ph->env.numa_nodes[i]; + for (i = 0; i < ff->ph->env.nr_numa_nodes; i++) { + n = &ff->ph->env.numa_nodes[i]; fprintf(fp, "# node%u meminfo : total = %"PRIu64" kB," " free = %"PRIu64" kB\n", @@ -1335,56 +1415,51 @@ static void print_numa_topology(struct perf_header *ph, int fd __maybe_unused, } } -static void print_cpuid(struct perf_header *ph, int fd __maybe_unused, FILE *fp) +static void print_cpuid(struct feat_fd *ff, FILE *fp) { - fprintf(fp, "# cpuid : %s\n", ph->env.cpuid); + fprintf(fp, "# cpuid : %s\n", ff->ph->env.cpuid); } -static void print_branch_stack(struct perf_header *ph __maybe_unused, - int fd __maybe_unused, FILE *fp) +static void print_branch_stack(struct feat_fd *ff __maybe_unused, FILE *fp) { fprintf(fp, "# contains samples with branch stack\n"); } -static void print_auxtrace(struct perf_header *ph __maybe_unused, - int fd __maybe_unused, FILE *fp) +static void print_auxtrace(struct feat_fd *ff __maybe_unused, FILE *fp) { fprintf(fp, "# contains AUX area data (e.g. instruction trace)\n"); } -static void print_stat(struct perf_header *ph __maybe_unused, - int fd __maybe_unused, FILE *fp) +static void print_stat(struct feat_fd *ff __maybe_unused, FILE *fp) { fprintf(fp, "# contains stat data\n"); } -static void print_cache(struct perf_header *ph __maybe_unused, - int fd __maybe_unused, FILE *fp __maybe_unused) +static void print_cache(struct feat_fd *ff, FILE *fp __maybe_unused) { int i; fprintf(fp, "# CPU cache info:\n"); - for (i = 0; i < ph->env.caches_cnt; i++) { + for (i = 0; i < ff->ph->env.caches_cnt; i++) { fprintf(fp, "# "); - cpu_cache_level__fprintf(fp, &ph->env.caches[i]); + cpu_cache_level__fprintf(fp, &ff->ph->env.caches[i]); } } -static void print_pmu_mappings(struct perf_header *ph, int fd __maybe_unused, - FILE *fp) +static void print_pmu_mappings(struct feat_fd *ff, FILE *fp) { const char *delimiter = "# pmu mappings: "; char *str, *tmp; u32 pmu_num; u32 type; - pmu_num = ph->env.nr_pmu_mappings; + pmu_num = ff->ph->env.nr_pmu_mappings; if (!pmu_num) { fprintf(fp, "# pmu mappings: not available\n"); return; } - str = ph->env.pmu_mappings; + str = ff->ph->env.pmu_mappings; while (pmu_num) { type = strtoul(str, &tmp, 0); @@ -1407,14 +1482,13 @@ error: fprintf(fp, "# pmu mappings: unable to read\n"); } -static void print_group_desc(struct perf_header *ph, int fd __maybe_unused, - FILE *fp) +static void print_group_desc(struct feat_fd *ff, FILE *fp) { struct perf_session *session; struct perf_evsel *evsel; u32 nr = 0; - session = container_of(ph, struct perf_session, header); + session = container_of(ff->ph, struct perf_session, header); evlist__for_each_entry(session->evlist, evsel) { if (perf_evsel__is_group_leader(evsel) && @@ -1587,113 +1661,61 @@ out: return err; } -static int process_tracing_data(struct perf_file_section *section __maybe_unused, - struct perf_header *ph __maybe_unused, - int fd, void *data) -{ - ssize_t ret = trace_report(fd, data, false); - return ret < 0 ? -1 : 0; -} - -static int process_build_id(struct perf_file_section *section, - struct perf_header *ph, int fd, - void *data __maybe_unused) -{ - if (perf_header__read_build_ids(ph, fd, section->offset, section->size)) - pr_debug("Failed to read buildids, continuing...\n"); - return 0; +/* Macro for features that simply need to read and store a string. */ +#define FEAT_PROCESS_STR_FUN(__feat, __feat_env) \ +static int process_##__feat(struct feat_fd *ff, void *data __maybe_unused) \ +{\ + ff->ph->env.__feat_env = do_read_string(ff); \ + return ff->ph->env.__feat_env ? 0 : -ENOMEM; \ } -static int process_hostname(struct perf_file_section *section __maybe_unused, - struct perf_header *ph, int fd, - void *data __maybe_unused) -{ - ph->env.hostname = do_read_string(fd, ph); - return ph->env.hostname ? 0 : -ENOMEM; -} +FEAT_PROCESS_STR_FUN(hostname, hostname); +FEAT_PROCESS_STR_FUN(osrelease, os_release); +FEAT_PROCESS_STR_FUN(version, version); +FEAT_PROCESS_STR_FUN(arch, arch); +FEAT_PROCESS_STR_FUN(cpudesc, cpu_desc); +FEAT_PROCESS_STR_FUN(cpuid, cpuid); -static int process_osrelease(struct perf_file_section *section __maybe_unused, - struct perf_header *ph, int fd, - void *data __maybe_unused) +static int process_tracing_data(struct feat_fd *ff, void *data) { - ph->env.os_release = do_read_string(fd, ph); - return ph->env.os_release ? 0 : -ENOMEM; -} + ssize_t ret = trace_report(ff->fd, data, false); -static int process_version(struct perf_file_section *section __maybe_unused, - struct perf_header *ph, int fd, - void *data __maybe_unused) -{ - ph->env.version = do_read_string(fd, ph); - return ph->env.version ? 0 : -ENOMEM; + return ret < 0 ? -1 : 0; } -static int process_arch(struct perf_file_section *section __maybe_unused, - struct perf_header *ph, int fd, - void *data __maybe_unused) +static int process_build_id(struct feat_fd *ff, void *data __maybe_unused) { - ph->env.arch = do_read_string(fd, ph); - return ph->env.arch ? 0 : -ENOMEM; + if (perf_header__read_build_ids(ff->ph, ff->fd, ff->offset, ff->size)) + pr_debug("Failed to read buildids, continuing...\n"); + return 0; } -static int process_nrcpus(struct perf_file_section *section __maybe_unused, - struct perf_header *ph, int fd, - void *data __maybe_unused) +static int process_nrcpus(struct feat_fd *ff, void *data __maybe_unused) { - ssize_t ret; - u32 nr; - - ret = readn(fd, &nr, sizeof(nr)); - if (ret != sizeof(nr)) - return -1; - - if (ph->needs_swap) - nr = bswap_32(nr); - - ph->env.nr_cpus_avail = nr; - - ret = readn(fd, &nr, sizeof(nr)); - if (ret != sizeof(nr)) - return -1; + int ret; + u32 nr_cpus_avail, nr_cpus_online; - if (ph->needs_swap) - nr = bswap_32(nr); + ret = do_read_u32(ff, &nr_cpus_avail); + if (ret) + return ret; - ph->env.nr_cpus_online = nr; + ret = do_read_u32(ff, &nr_cpus_online); + if (ret) + return ret; + ff->ph->env.nr_cpus_avail = (int)nr_cpus_avail; + ff->ph->env.nr_cpus_online = (int)nr_cpus_online; return 0; } -static int process_cpudesc(struct perf_file_section *section __maybe_unused, - struct perf_header *ph, int fd, - void *data __maybe_unused) -{ - ph->env.cpu_desc = do_read_string(fd, ph); - return ph->env.cpu_desc ? 0 : -ENOMEM; -} - -static int process_cpuid(struct perf_file_section *section __maybe_unused, - struct perf_header *ph, int fd, - void *data __maybe_unused) -{ - ph->env.cpuid = do_read_string(fd, ph); - return ph->env.cpuid ? 0 : -ENOMEM; -} - -static int process_total_mem(struct perf_file_section *section __maybe_unused, - struct perf_header *ph, int fd, - void *data __maybe_unused) +static int process_total_mem(struct feat_fd *ff, void *data __maybe_unused) { - uint64_t mem; - ssize_t ret; + u64 total_mem; + int ret; - ret = readn(fd, &mem, sizeof(mem)); - if (ret != sizeof(mem)) + ret = do_read_u64(ff, &total_mem); + if (ret) return -1; - - if (ph->needs_swap) - mem = bswap_64(mem); - - ph->env.total_mem = mem; + ff->ph->env.total_mem = (unsigned long long)total_mem; return 0; } @@ -1730,43 +1752,42 @@ perf_evlist__set_event_name(struct perf_evlist *evlist, } static int -process_event_desc(struct perf_file_section *section __maybe_unused, - struct perf_header *header, int fd, - void *data __maybe_unused) +process_event_desc(struct feat_fd *ff, void *data __maybe_unused) { struct perf_session *session; - struct perf_evsel *evsel, *events = read_event_desc(header, fd); + struct perf_evsel *evsel, *events = read_event_desc(ff); if (!events) return 0; - session = container_of(header, struct perf_session, header); + session = container_of(ff->ph, struct perf_session, header); + + if (session->file->is_pipe) { + /* Save events for reading later by print_event_desc, + * since they can't be read again in pipe mode. */ + ff->events = events; + } + for (evsel = events; evsel->attr.size; evsel++) perf_evlist__set_event_name(session->evlist, evsel); - free_event_desc(events); + if (!session->file->is_pipe) + free_event_desc(events); return 0; } -static int process_cmdline(struct perf_file_section *section, - struct perf_header *ph, int fd, - void *data __maybe_unused) +static int process_cmdline(struct feat_fd *ff, void *data __maybe_unused) { - ssize_t ret; char *str, *cmdline = NULL, **argv = NULL; u32 nr, i, len = 0; - ret = readn(fd, &nr, sizeof(nr)); - if (ret != sizeof(nr)) + if (do_read_u32(ff, &nr)) return -1; - if (ph->needs_swap) - nr = bswap_32(nr); - - ph->env.nr_cmdline = nr; + ff->ph->env.nr_cmdline = nr; - cmdline = zalloc(section->size + nr + 1); + cmdline = zalloc(ff->size + nr + 1); if (!cmdline) return -1; @@ -1775,7 +1796,7 @@ static int process_cmdline(struct perf_file_section *section, goto error; for (i = 0; i < nr; i++) { - str = do_read_string(fd, ph); + str = do_read_string(ff); if (!str) goto error; @@ -1784,8 +1805,8 @@ static int process_cmdline(struct perf_file_section *section, len += strlen(str) + 1; free(str); } - ph->env.cmdline = cmdline; - ph->env.cmdline_argv = (const char **) argv; + ff->ph->env.cmdline = cmdline; + ff->ph->env.cmdline_argv = (const char **) argv; return 0; error: @@ -1794,35 +1815,29 @@ error: return -1; } -static int process_cpu_topology(struct perf_file_section *section, - struct perf_header *ph, int fd, - void *data __maybe_unused) +static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused) { - ssize_t ret; u32 nr, i; char *str; struct strbuf sb; - int cpu_nr = ph->env.nr_cpus_avail; + int cpu_nr = ff->ph->env.nr_cpus_avail; u64 size = 0; + struct perf_header *ph = ff->ph; ph->env.cpu = calloc(cpu_nr, sizeof(*ph->env.cpu)); if (!ph->env.cpu) return -1; - ret = readn(fd, &nr, sizeof(nr)); - if (ret != sizeof(nr)) + if (do_read_u32(ff, &nr)) goto free_cpu; - if (ph->needs_swap) - nr = bswap_32(nr); - ph->env.nr_sibling_cores = nr; size += sizeof(u32); if (strbuf_init(&sb, 128) < 0) goto free_cpu; for (i = 0; i < nr; i++) { - str = do_read_string(fd, ph); + str = do_read_string(ff); if (!str) goto error; @@ -1834,18 +1849,14 @@ static int process_cpu_topology(struct perf_file_section *section, } ph->env.sibling_cores = strbuf_detach(&sb, NULL); - ret = readn(fd, &nr, sizeof(nr)); - if (ret != sizeof(nr)) + if (do_read_u32(ff, &nr)) return -1; - if (ph->needs_swap) - nr = bswap_32(nr); - ph->env.nr_sibling_threads = nr; size += sizeof(u32); for (i = 0; i < nr; i++) { - str = do_read_string(fd, ph); + str = do_read_string(ff); if (!str) goto error; @@ -1861,28 +1872,20 @@ static int process_cpu_topology(struct perf_file_section *section, * The header may be from old perf, * which doesn't include core id and socket id information. */ - if (section->size <= size) { + if (ff->size <= size) { zfree(&ph->env.cpu); return 0; } for (i = 0; i < (u32)cpu_nr; i++) { - ret = readn(fd, &nr, sizeof(nr)); - if (ret != sizeof(nr)) + if (do_read_u32(ff, &nr)) goto free_cpu; - if (ph->needs_swap) - nr = bswap_32(nr); - ph->env.cpu[i].core_id = nr; - ret = readn(fd, &nr, sizeof(nr)); - if (ret != sizeof(nr)) + if (do_read_u32(ff, &nr)) goto free_cpu; - if (ph->needs_swap) - nr = bswap_32(nr); - if (nr != (u32)-1 && nr > (u32)cpu_nr) { pr_debug("socket_id number is too big." "You may need to upgrade the perf tool.\n"); @@ -1901,23 +1904,16 @@ free_cpu: return -1; } -static int process_numa_topology(struct perf_file_section *section __maybe_unused, - struct perf_header *ph, int fd, - void *data __maybe_unused) +static int process_numa_topology(struct feat_fd *ff, void *data __maybe_unused) { struct numa_node *nodes, *n; - ssize_t ret; u32 nr, i; char *str; /* nr nodes */ - ret = readn(fd, &nr, sizeof(nr)); - if (ret != sizeof(nr)) + if (do_read_u32(ff, &nr)) return -1; - if (ph->needs_swap) - nr = bswap_32(nr); - nodes = zalloc(sizeof(*nodes) * nr); if (!nodes) return -ENOMEM; @@ -1926,25 +1922,16 @@ static int process_numa_topology(struct perf_file_section *section __maybe_unuse n = &nodes[i]; /* node number */ - ret = readn(fd, &n->node, sizeof(u32)); - if (ret != sizeof(n->node)) + if (do_read_u32(ff, &n->node)) goto error; - ret = readn(fd, &n->mem_total, sizeof(u64)); - if (ret != sizeof(u64)) + if (do_read_u64(ff, &n->mem_total)) goto error; - ret = readn(fd, &n->mem_free, sizeof(u64)); - if (ret != sizeof(u64)) + if (do_read_u64(ff, &n->mem_free)) goto error; - if (ph->needs_swap) { - n->node = bswap_32(n->node); - n->mem_total = bswap_64(n->mem_total); - n->mem_free = bswap_64(n->mem_free); - } - - str = do_read_string(fd, ph); + str = do_read_string(ff); if (!str) goto error; @@ -1954,8 +1941,8 @@ static int process_numa_topology(struct perf_file_section *section __maybe_unuse free(str); } - ph->env.nr_numa_nodes = nr; - ph->env.numa_nodes = nodes; + ff->ph->env.nr_numa_nodes = nr; + ff->ph->env.numa_nodes = nodes; return 0; error: @@ -1963,39 +1950,30 @@ error: return -1; } -static int process_pmu_mappings(struct perf_file_section *section __maybe_unused, - struct perf_header *ph, int fd, - void *data __maybe_unused) +static int process_pmu_mappings(struct feat_fd *ff, void *data __maybe_unused) { - ssize_t ret; char *name; u32 pmu_num; u32 type; struct strbuf sb; - ret = readn(fd, &pmu_num, sizeof(pmu_num)); - if (ret != sizeof(pmu_num)) + if (do_read_u32(ff, &pmu_num)) return -1; - if (ph->needs_swap) - pmu_num = bswap_32(pmu_num); - if (!pmu_num) { pr_debug("pmu mappings not available\n"); return 0; } - ph->env.nr_pmu_mappings = pmu_num; + ff->ph->env.nr_pmu_mappings = pmu_num; if (strbuf_init(&sb, 128) < 0) return -1; while (pmu_num) { - if (readn(fd, &type, sizeof(type)) != sizeof(type)) + if (do_read_u32(ff, &type)) goto error; - if (ph->needs_swap) - type = bswap_32(type); - name = do_read_string(fd, ph); + name = do_read_string(ff); if (!name) goto error; @@ -2006,12 +1984,12 @@ static int process_pmu_mappings(struct perf_file_section *section __maybe_unused goto error; if (!strcmp(name, "msr")) - ph->env.msr_pmu_type = type; + ff->ph->env.msr_pmu_type = type; free(name); pmu_num--; } - ph->env.pmu_mappings = strbuf_detach(&sb, NULL); + ff->ph->env.pmu_mappings = strbuf_detach(&sb, NULL); return 0; error: @@ -2019,9 +1997,7 @@ error: return -1; } -static int process_group_desc(struct perf_file_section *section __maybe_unused, - struct perf_header *ph, int fd, - void *data __maybe_unused) +static int process_group_desc(struct feat_fd *ff, void *data __maybe_unused) { size_t ret = -1; u32 i, nr, nr_groups; @@ -2033,13 +2009,10 @@ static int process_group_desc(struct perf_file_section *section __maybe_unused, u32 nr_members; } *desc; - if (readn(fd, &nr_groups, sizeof(nr_groups)) != sizeof(nr_groups)) + if (do_read_u32(ff, &nr_groups)) return -1; - if (ph->needs_swap) - nr_groups = bswap_32(nr_groups); - - ph->env.nr_groups = nr_groups; + ff->ph->env.nr_groups = nr_groups; if (!nr_groups) { pr_debug("group desc not available\n"); return 0; @@ -2050,26 +2023,21 @@ static int process_group_desc(struct perf_file_section *section __maybe_unused, return -1; for (i = 0; i < nr_groups; i++) { - desc[i].name = do_read_string(fd, ph); + desc[i].name = do_read_string(ff); if (!desc[i].name) goto out_free; - if (readn(fd, &desc[i].leader_idx, sizeof(u32)) != sizeof(u32)) + if (do_read_u32(ff, &desc[i].leader_idx)) goto out_free; - if (readn(fd, &desc[i].nr_members, sizeof(u32)) != sizeof(u32)) + if (do_read_u32(ff, &desc[i].nr_members)) goto out_free; - - if (ph->needs_swap) { - desc[i].leader_idx = bswap_32(desc[i].leader_idx); - desc[i].nr_members = bswap_32(desc[i].nr_members); - } } /* * Rebuild group relationship based on the group_desc */ - session = container_of(ph, struct perf_session, header); + session = container_of(ff->ph, struct perf_session, header); session->evlist->nr_groups = nr_groups; i = nr = 0; @@ -2113,44 +2081,34 @@ out_free: return ret; } -static int process_auxtrace(struct perf_file_section *section, - struct perf_header *ph, int fd, - void *data __maybe_unused) +static int process_auxtrace(struct feat_fd *ff, void *data __maybe_unused) { struct perf_session *session; int err; - session = container_of(ph, struct perf_session, header); + session = container_of(ff->ph, struct perf_session, header); - err = auxtrace_index__process(fd, section->size, session, - ph->needs_swap); + err = auxtrace_index__process(ff->fd, ff->size, session, + ff->ph->needs_swap); if (err < 0) pr_err("Failed to process auxtrace index\n"); return err; } -static int process_cache(struct perf_file_section *section __maybe_unused, - struct perf_header *ph __maybe_unused, int fd __maybe_unused, - void *data __maybe_unused) +static int process_cache(struct feat_fd *ff, void *data __maybe_unused) { struct cpu_cache_level *caches; u32 cnt, i, version; - if (readn(fd, &version, sizeof(version)) != sizeof(version)) + if (do_read_u32(ff, &version)) return -1; - if (ph->needs_swap) - version = bswap_32(version); - if (version != 1) return -1; - if (readn(fd, &cnt, sizeof(cnt)) != sizeof(cnt)) + if (do_read_u32(ff, &cnt)) return -1; - if (ph->needs_swap) - cnt = bswap_32(cnt); - caches = zalloc(sizeof(*caches) * cnt); if (!caches) return -1; @@ -2159,10 +2117,8 @@ static int process_cache(struct perf_file_section *section __maybe_unused, struct cpu_cache_level c; #define _R(v) \ - if (readn(fd, &c.v, sizeof(u32)) != sizeof(u32))\ + if (do_read_u32(ff, &c.v))\ goto out_free_caches; \ - if (ph->needs_swap) \ - c.v = bswap_32(c.v); \ _R(level) _R(line_size) @@ -2170,9 +2126,9 @@ static int process_cache(struct perf_file_section *section __maybe_unused, _R(ways) #undef _R - #define _R(v) \ - c.v = do_read_string(fd, ph); \ - if (!c.v) \ + #define _R(v) \ + c.v = do_read_string(ff); \ + if (!c.v) \ goto out_free_caches; _R(type) @@ -2183,8 +2139,8 @@ static int process_cache(struct perf_file_section *section __maybe_unused, caches[i] = c; } - ph->env.caches = caches; - ph->env.caches_cnt = cnt; + ff->ph->env.caches = caches; + ff->ph->env.caches_cnt = cnt; return 0; out_free_caches: free(caches); @@ -2192,48 +2148,62 @@ out_free_caches: } struct feature_ops { - int (*write)(int fd, struct perf_header *h, struct perf_evlist *evlist); - void (*print)(struct perf_header *h, int fd, FILE *fp); - int (*process)(struct perf_file_section *section, - struct perf_header *h, int fd, void *data); + int (*write)(struct feat_fd *ff, struct perf_evlist *evlist); + void (*print)(struct feat_fd *ff, FILE *fp); + int (*process)(struct feat_fd *ff, void *data); const char *name; bool full_only; + bool synthesize; }; -#define FEAT_OPA(n, func) \ - [n] = { .name = #n, .write = write_##func, .print = print_##func } -#define FEAT_OPP(n, func) \ - [n] = { .name = #n, .write = write_##func, .print = print_##func, \ - .process = process_##func } -#define FEAT_OPF(n, func) \ - [n] = { .name = #n, .write = write_##func, .print = print_##func, \ - .process = process_##func, .full_only = true } +#define FEAT_OPR(n, func, __full_only) \ + [HEADER_##n] = { \ + .name = __stringify(n), \ + .write = write_##func, \ + .print = print_##func, \ + .full_only = __full_only, \ + .process = process_##func, \ + .synthesize = true \ + } + +#define FEAT_OPN(n, func, __full_only) \ + [HEADER_##n] = { \ + .name = __stringify(n), \ + .write = write_##func, \ + .print = print_##func, \ + .full_only = __full_only, \ + .process = process_##func \ + } /* feature_ops not implemented: */ #define print_tracing_data NULL #define print_build_id NULL +#define process_branch_stack NULL +#define process_stat NULL + + static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = { - FEAT_OPP(HEADER_TRACING_DATA, tracing_data), - FEAT_OPP(HEADER_BUILD_ID, build_id), - FEAT_OPP(HEADER_HOSTNAME, hostname), - FEAT_OPP(HEADER_OSRELEASE, osrelease), - FEAT_OPP(HEADER_VERSION, version), - FEAT_OPP(HEADER_ARCH, arch), - FEAT_OPP(HEADER_NRCPUS, nrcpus), - FEAT_OPP(HEADER_CPUDESC, cpudesc), - FEAT_OPP(HEADER_CPUID, cpuid), - FEAT_OPP(HEADER_TOTAL_MEM, total_mem), - FEAT_OPP(HEADER_EVENT_DESC, event_desc), - FEAT_OPP(HEADER_CMDLINE, cmdline), - FEAT_OPF(HEADER_CPU_TOPOLOGY, cpu_topology), - FEAT_OPF(HEADER_NUMA_TOPOLOGY, numa_topology), - FEAT_OPA(HEADER_BRANCH_STACK, branch_stack), - FEAT_OPP(HEADER_PMU_MAPPINGS, pmu_mappings), - FEAT_OPP(HEADER_GROUP_DESC, group_desc), - FEAT_OPP(HEADER_AUXTRACE, auxtrace), - FEAT_OPA(HEADER_STAT, stat), - FEAT_OPF(HEADER_CACHE, cache), + FEAT_OPN(TRACING_DATA, tracing_data, false), + FEAT_OPN(BUILD_ID, build_id, false), + FEAT_OPR(HOSTNAME, hostname, false), + FEAT_OPR(OSRELEASE, osrelease, false), + FEAT_OPR(VERSION, version, false), + FEAT_OPR(ARCH, arch, false), + FEAT_OPR(NRCPUS, nrcpus, false), + FEAT_OPR(CPUDESC, cpudesc, false), + FEAT_OPR(CPUID, cpuid, false), + FEAT_OPR(TOTAL_MEM, total_mem, false), + FEAT_OPR(EVENT_DESC, event_desc, false), + FEAT_OPR(CMDLINE, cmdline, false), + FEAT_OPR(CPU_TOPOLOGY, cpu_topology, true), + FEAT_OPR(NUMA_TOPOLOGY, numa_topology, true), + FEAT_OPN(BRANCH_STACK, branch_stack, false), + FEAT_OPR(PMU_MAPPINGS, pmu_mappings, false), + FEAT_OPN(GROUP_DESC, group_desc, false), + FEAT_OPN(AUXTRACE, auxtrace, false), + FEAT_OPN(STAT, stat, false), + FEAT_OPN(CACHE, cache, true), }; struct header_print_data { @@ -2246,6 +2216,7 @@ static int perf_file_section__fprintf_info(struct perf_file_section *section, int feat, int fd, void *data) { struct header_print_data *hd = data; + struct feat_fd ff; if (lseek(fd, section->offset, SEEK_SET) == (off_t)-1) { pr_debug("Failed to lseek to %" PRIu64 " offset for feature " @@ -2259,8 +2230,13 @@ static int perf_file_section__fprintf_info(struct perf_file_section *section, if (!feat_ops[feat].print) return 0; + ff = (struct feat_fd) { + .fd = fd, + .ph = ph, + }; + if (!feat_ops[feat].full_only || hd->full) - feat_ops[feat].print(ph, fd, hd->fp); + feat_ops[feat].print(&ff, hd->fp); else fprintf(hd->fp, "# %s info available, use -I to display\n", feat_ops[feat].name); @@ -2301,29 +2277,32 @@ int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full) return 0; } -static int do_write_feat(int fd, struct perf_header *h, int type, +static int do_write_feat(struct feat_fd *ff, int type, struct perf_file_section **p, struct perf_evlist *evlist) { int err; int ret = 0; - if (perf_header__has_feat(h, type)) { + if (perf_header__has_feat(ff->ph, type)) { if (!feat_ops[type].write) return -1; - (*p)->offset = lseek(fd, 0, SEEK_CUR); + if (WARN(ff->buf, "Error: calling %s in pipe-mode.\n", __func__)) + return -1; - err = feat_ops[type].write(fd, h, evlist); + (*p)->offset = lseek(ff->fd, 0, SEEK_CUR); + + err = feat_ops[type].write(ff, evlist); if (err < 0) { pr_debug("failed to write feature %s\n", feat_ops[type].name); /* undo anything written */ - lseek(fd, (*p)->offset, SEEK_SET); + lseek(ff->fd, (*p)->offset, SEEK_SET); return -1; } - (*p)->size = lseek(fd, 0, SEEK_CUR) - (*p)->offset; + (*p)->size = lseek(ff->fd, 0, SEEK_CUR) - (*p)->offset; (*p)++; } return ret; @@ -2333,12 +2312,18 @@ static int perf_header__adds_write(struct perf_header *header, struct perf_evlist *evlist, int fd) { int nr_sections; + struct feat_fd ff; struct perf_file_section *feat_sec, *p; int sec_size; u64 sec_start; int feat; int err; + ff = (struct feat_fd){ + .fd = fd, + .ph = header, + }; + nr_sections = bitmap_weight(header->adds_features, HEADER_FEAT_BITS); if (!nr_sections) return 0; @@ -2353,7 +2338,7 @@ static int perf_header__adds_write(struct perf_header *header, lseek(fd, sec_start + sec_size, SEEK_SET); for_each_set_bit(feat, header->adds_features, HEADER_FEAT_BITS) { - if (do_write_feat(fd, header, feat, &p, evlist)) + if (do_write_feat(&ff, feat, &p, evlist)) perf_header__clear_feat(header, feat); } @@ -2362,7 +2347,7 @@ static int perf_header__adds_write(struct perf_header *header, * may write more than needed due to dropped feature, but * this is okay, reader will skip the mising entries */ - err = do_write(fd, feat_sec, sec_size); + err = do_write(&ff, feat_sec, sec_size); if (err < 0) pr_debug("failed to write feature section\n"); free(feat_sec); @@ -2372,14 +2357,17 @@ static int perf_header__adds_write(struct perf_header *header, int perf_header__write_pipe(int fd) { struct perf_pipe_file_header f_header; + struct feat_fd ff; int err; + ff = (struct feat_fd){ .fd = fd }; + f_header = (struct perf_pipe_file_header){ .magic = PERF_MAGIC, .size = sizeof(f_header), }; - err = do_write(fd, &f_header, sizeof(f_header)); + err = do_write(&ff, &f_header, sizeof(f_header)); if (err < 0) { pr_debug("failed to write perf pipe header\n"); return err; @@ -2396,21 +2384,23 @@ int perf_session__write_header(struct perf_session *session, struct perf_file_attr f_attr; struct perf_header *header = &session->header; struct perf_evsel *evsel; + struct feat_fd ff; u64 attr_offset; int err; + ff = (struct feat_fd){ .fd = fd}; lseek(fd, sizeof(f_header), SEEK_SET); evlist__for_each_entry(session->evlist, evsel) { evsel->id_offset = lseek(fd, 0, SEEK_CUR); - err = do_write(fd, evsel->id, evsel->ids * sizeof(u64)); + err = do_write(&ff, evsel->id, evsel->ids * sizeof(u64)); if (err < 0) { pr_debug("failed to write perf header\n"); return err; } } - attr_offset = lseek(fd, 0, SEEK_CUR); + attr_offset = lseek(ff.fd, 0, SEEK_CUR); evlist__for_each_entry(evlist, evsel) { f_attr = (struct perf_file_attr){ @@ -2420,7 +2410,7 @@ int perf_session__write_header(struct perf_session *session, .size = evsel->ids * sizeof(u64), } }; - err = do_write(fd, &f_attr, sizeof(f_attr)); + err = do_write(&ff, &f_attr, sizeof(f_attr)); if (err < 0) { pr_debug("failed to write perf header attribute\n"); return err; @@ -2455,7 +2445,7 @@ int perf_session__write_header(struct perf_session *session, memcpy(&f_header.adds_features, &header->adds_features, sizeof(header->adds_features)); lseek(fd, 0, SEEK_SET); - err = do_write(fd, &f_header, sizeof(f_header)); + err = do_write(&ff, &f_header, sizeof(f_header)); if (err < 0) { pr_debug("failed to write perf header\n"); return err; @@ -2709,6 +2699,13 @@ static int perf_file_section__process(struct perf_file_section *section, struct perf_header *ph, int feat, int fd, void *data) { + struct feat_fd fdd = { + .fd = fd, + .ph = ph, + .size = section->size, + .offset = section->offset, + }; + if (lseek(fd, section->offset, SEEK_SET) == (off_t)-1) { pr_debug("Failed to lseek to %" PRIu64 " offset for feature " "%d, continuing...\n", section->offset, feat); @@ -2723,13 +2720,17 @@ static int perf_file_section__process(struct perf_file_section *section, if (!feat_ops[feat].process) return 0; - return feat_ops[feat].process(section, ph, fd, data); + return feat_ops[feat].process(&fdd, data); } static int perf_file_header__read_pipe(struct perf_pipe_file_header *header, struct perf_header *ph, int fd, bool repipe) { + struct feat_fd ff = { + .fd = STDOUT_FILENO, + .ph = ph, + }; ssize_t ret; ret = readn(fd, header, sizeof(*header)); @@ -2744,7 +2745,7 @@ static int perf_file_header__read_pipe(struct perf_pipe_file_header *header, if (ph->needs_swap) header->size = bswap_64(header->size); - if (repipe && do_write(STDOUT_FILENO, header, sizeof(*header)) < 0) + if (repipe && do_write(&ff, header, sizeof(*header)) < 0) return -1; return 0; @@ -2994,6 +2995,103 @@ int perf_event__synthesize_attr(struct perf_tool *tool, return err; } +int perf_event__synthesize_features(struct perf_tool *tool, + struct perf_session *session, + struct perf_evlist *evlist, + perf_event__handler_t process) +{ + struct perf_header *header = &session->header; + struct feat_fd ff; + struct feature_event *fe; + size_t sz, sz_hdr; + int feat, ret; + + sz_hdr = sizeof(fe->header); + sz = sizeof(union perf_event); + /* get a nice alignment */ + sz = PERF_ALIGN(sz, page_size); + + memset(&ff, 0, sizeof(ff)); + + ff.buf = malloc(sz); + if (!ff.buf) + return -ENOMEM; + + ff.size = sz - sz_hdr; + + for_each_set_bit(feat, header->adds_features, HEADER_FEAT_BITS) { + if (!feat_ops[feat].synthesize) { + pr_debug("No record header feature for header :%d\n", feat); + continue; + } + + ff.offset = sizeof(*fe); + + ret = feat_ops[feat].write(&ff, evlist); + if (ret || ff.offset <= (ssize_t)sizeof(*fe)) { + pr_debug("Error writing feature\n"); + continue; + } + /* ff.buf may have changed due to realloc in do_write() */ + fe = ff.buf; + memset(fe, 0, sizeof(*fe)); + + fe->feat_id = feat; + fe->header.type = PERF_RECORD_HEADER_FEATURE; + fe->header.size = ff.offset; + + ret = process(tool, ff.buf, NULL, NULL); + if (ret) { + free(ff.buf); + return ret; + } + } + free(ff.buf); + return 0; +} + +int perf_event__process_feature(struct perf_tool *tool, + union perf_event *event, + struct perf_session *session __maybe_unused) +{ + struct feat_fd ff = { .fd = 0 }; + struct feature_event *fe = (struct feature_event *)event; + int type = fe->header.type; + u64 feat = fe->feat_id; + + if (type < 0 || type >= PERF_RECORD_HEADER_MAX) { + pr_warning("invalid record type %d in pipe-mode\n", type); + return 0; + } + if (feat == HEADER_RESERVED || feat > HEADER_LAST_FEATURE) { + pr_warning("invalid record type %d in pipe-mode\n", type); + return -1; + } + + if (!feat_ops[feat].process) + return 0; + + ff.buf = (void *)fe->data; + ff.size = event->header.size - sizeof(event->header); + ff.ph = &session->header; + + if (feat_ops[feat].process(&ff, NULL)) + return -1; + + if (!feat_ops[feat].print || !tool->show_feat_hdr) + return 0; + + if (!feat_ops[feat].full_only || + tool->show_feat_hdr >= SHOW_FEAT_HEADER_FULL_INFO) { + feat_ops[feat].print(&ff, stdout); + } else { + fprintf(stdout, "# %s info available, use -I to display\n", + feat_ops[feat].name); + } + + return 0; +} + static struct event_update_event * event_update_event__new(size_t size, u64 type, u64 id) { @@ -3252,6 +3350,7 @@ int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd, union perf_event ev; struct tracing_data *tdata; ssize_t size = 0, aligned_size = 0, padding; + struct feat_fd ff; int err __maybe_unused = 0; /* @@ -3286,7 +3385,9 @@ int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd, */ tracing_data_put(tdata); - write_padded(fd, NULL, 0, padding); + ff = (struct feat_fd){ .fd = fd }; + if (write_padded(&ff, NULL, 0, padding)) + return -1; return aligned_size; } diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index d30109b421ee..f7a16ee527b8 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -101,6 +101,15 @@ int perf_header__process_sections(struct perf_header *header, int fd, int perf_header__fprintf_info(struct perf_session *s, FILE *fp, bool full); +int perf_event__synthesize_features(struct perf_tool *tool, + struct perf_session *session, + struct perf_evlist *evlist, + perf_event__handler_t process); + +int perf_event__process_feature(struct perf_tool *tool, + union perf_event *event, + struct perf_session *session); + int perf_event__synthesize_attr(struct perf_tool *tool, struct perf_event_attr *attr, u32 ids, u64 *id, perf_event__handler_t process); @@ -144,7 +153,12 @@ bool is_perf_magic(u64 magic); #define NAME_ALIGN 64 -int write_padded(int fd, const void *bf, size_t count, size_t count_aligned); +struct feat_fd; + +int do_write(struct feat_fd *fd, const void *buf, size_t size); + +int write_padded(struct feat_fd *fd, const void *bf, + size_t count, size_t count_aligned); /* * arch specific callback diff --git a/tools/perf/util/help-unknown-cmd.c b/tools/perf/util/help-unknown-cmd.c index 1c88ad6425b8..15b95300d7f3 100644 --- a/tools/perf/util/help-unknown-cmd.c +++ b/tools/perf/util/help-unknown-cmd.c @@ -12,7 +12,7 @@ static int perf_unknown_cmd_config(const char *var, const char *value, void *cb __maybe_unused) { if (!strcmp(var, "help.autocorrect")) - autocorrect = perf_config_int(var,value); + return perf_config_int(&autocorrect, var,value); return 0; } diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index cf0186a088c1..e60d8d8ea4c2 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -167,6 +167,10 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) symlen = unresolved_col_width + 4 + 2; hists__set_unres_dso_col_len(hists, HISTC_MEM_DADDR_DSO); } + + hists__new_col_len(hists, HISTC_MEM_PHYS_DADDR, + unresolved_col_width + 4 + 2); + } else { symlen = unresolved_col_width + 4 + 2; hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL, symlen); @@ -749,12 +753,9 @@ iter_prepare_branch_entry(struct hist_entry_iter *iter, struct addr_location *al } static int -iter_add_single_branch_entry(struct hist_entry_iter *iter, +iter_add_single_branch_entry(struct hist_entry_iter *iter __maybe_unused, struct addr_location *al __maybe_unused) { - /* to avoid calling callback function */ - iter->he = NULL; - return 0; } @@ -1762,6 +1763,8 @@ void perf_evsel__output_resort(struct perf_evsel *evsel, struct ui_progress *pro else use_callchain = symbol_conf.use_callchain; + use_callchain |= symbol_conf.show_branchflag_count; + output_resort(evsel__hists(evsel), prog, use_callchain, NULL); } diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index ee3670a388df..e60dda26a920 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -47,6 +47,7 @@ enum hist_column { HISTC_GLOBAL_WEIGHT, HISTC_MEM_DADDR_SYMBOL, HISTC_MEM_DADDR_DSO, + HISTC_MEM_PHYS_DADDR, HISTC_MEM_LOCKED, HISTC_MEM_TLB, HISTC_MEM_LVL, diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c index b2834ac7b1f5..218ee2bac9a5 100644 --- a/tools/perf/util/intel-bts.c +++ b/tools/perf/util/intel-bts.c @@ -866,8 +866,6 @@ static void intel_bts_print_info(u64 *arr, int start, int finish) fprintf(stdout, intel_bts_info_fmts[i], arr[i]); } -u64 intel_bts_auxtrace_info_priv[INTEL_BTS_AUXTRACE_PRIV_SIZE]; - int intel_bts_process_auxtrace_info(union perf_event *event, struct perf_session *session) { diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build index 7aca5d6d7e1f..10e0814bb8d2 100644 --- a/tools/perf/util/intel-pt-decoder/Build +++ b/tools/perf/util/intel-pt-decoder/Build @@ -25,6 +25,6 @@ $(OUTPUT)util/intel-pt-decoder/intel-pt-insn-decoder.o: util/intel-pt-decoder/in CFLAGS_intel-pt-insn-decoder.o += -I$(OUTPUT)util/intel-pt-decoder -ifneq ($(CC), clang) +ifeq ($(CC_NO_CLANG), 1) CFLAGS_intel-pt-insn-decoder.o += -Wno-override-init endif diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c index 7cf7f7aca4d2..aa1593ce551d 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -64,6 +64,25 @@ enum intel_pt_pkt_state { INTEL_PT_STATE_FUP_NO_TIP, }; +static inline bool intel_pt_sample_time(enum intel_pt_pkt_state pkt_state) +{ + switch (pkt_state) { + case INTEL_PT_STATE_NO_PSB: + case INTEL_PT_STATE_NO_IP: + case INTEL_PT_STATE_ERR_RESYNC: + case INTEL_PT_STATE_IN_SYNC: + case INTEL_PT_STATE_TNT: + return true; + case INTEL_PT_STATE_TIP: + case INTEL_PT_STATE_TIP_PGD: + case INTEL_PT_STATE_FUP: + case INTEL_PT_STATE_FUP_NO_TIP: + return false; + default: + return true; + }; +} + #ifdef INTEL_PT_STRICT #define INTEL_PT_STATE_ERR1 INTEL_PT_STATE_NO_PSB #define INTEL_PT_STATE_ERR2 INTEL_PT_STATE_NO_PSB @@ -87,11 +106,13 @@ struct intel_pt_decoder { const unsigned char *buf; size_t len; bool return_compression; + bool branch_enable; bool mtc_insn; bool pge; bool have_tma; bool have_cyc; bool fixup_last_mtc; + bool have_last_ip; uint64_t pos; uint64_t last_ip; uint64_t ip; @@ -99,6 +120,7 @@ struct intel_pt_decoder { uint64_t timestamp; uint64_t tsc_timestamp; uint64_t ref_timestamp; + uint64_t sample_timestamp; uint64_t ret_addr; uint64_t ctc_timestamp; uint64_t ctc_delta; @@ -119,6 +141,7 @@ struct intel_pt_decoder { int pkt_len; int last_packet_type; unsigned int cbr; + unsigned int cbr_seen; unsigned int max_non_turbo_ratio; double max_non_turbo_ratio_fp; double cbr_cyc_to_tsc; @@ -136,9 +159,18 @@ struct intel_pt_decoder { bool continuous_period; bool overflow; bool set_fup_tx_flags; + bool set_fup_ptw; + bool set_fup_mwait; + bool set_fup_pwre; + bool set_fup_exstop; unsigned int fup_tx_flags; unsigned int tx_flags; + uint64_t fup_ptw_payload; + uint64_t fup_mwait_payload; + uint64_t fup_pwre_payload; + uint64_t cbr_payload; uint64_t timestamp_insn_cnt; + uint64_t sample_insn_cnt; uint64_t stuck_ip; int no_progress; int stuck_ip_prd; @@ -192,6 +224,7 @@ struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params) decoder->pgd_ip = params->pgd_ip; decoder->data = params->data; decoder->return_compression = params->return_compression; + decoder->branch_enable = params->branch_enable; decoder->period = params->period; decoder->period_type = params->period_type; @@ -398,6 +431,7 @@ static uint64_t intel_pt_calc_ip(const struct intel_pt_pkt *packet, static inline void intel_pt_set_last_ip(struct intel_pt_decoder *decoder) { decoder->last_ip = intel_pt_calc_ip(&decoder->packet, decoder->last_ip); + decoder->have_last_ip = true; } static inline void intel_pt_set_ip(struct intel_pt_decoder *decoder) @@ -635,6 +669,8 @@ static int intel_pt_calc_cyc_cb(struct intel_pt_pkt_info *pkt_info) case INTEL_PT_PAD: case INTEL_PT_VMCS: case INTEL_PT_MNT: + case INTEL_PT_PTWRITE: + case INTEL_PT_PTWRITE_IP: return 0; case INTEL_PT_MTC: @@ -675,6 +711,12 @@ static int intel_pt_calc_cyc_cb(struct intel_pt_pkt_info *pkt_info) break; case INTEL_PT_TSC: + /* + * For now, do not support using TSC packets - refer + * intel_pt_calc_cyc_to_tsc(). + */ + if (data->from_mtc) + return 1; timestamp = pkt_info->packet.payload | (data->timestamp & (0xffULL << 56)); if (data->from_mtc && timestamp < data->timestamp && @@ -733,6 +775,11 @@ static int intel_pt_calc_cyc_cb(struct intel_pt_pkt_info *pkt_info) case INTEL_PT_TIP_PGD: case INTEL_PT_TRACESTOP: + case INTEL_PT_EXSTOP: + case INTEL_PT_EXSTOP_IP: + case INTEL_PT_MWAIT: + case INTEL_PT_PWRE: + case INTEL_PT_PWRX: case INTEL_PT_OVF: case INTEL_PT_BAD: /* Does not happen */ default: @@ -787,6 +834,14 @@ static void intel_pt_calc_cyc_to_tsc(struct intel_pt_decoder *decoder, .cbr_cyc_to_tsc = 0, }; + /* + * For now, do not support using TSC packets for at least the reasons: + * 1) timing might have stopped + * 2) TSC packets within PSB+ can slip against CYC packets + */ + if (!from_mtc) + return; + intel_pt_pkt_lookahead(decoder, intel_pt_calc_cyc_cb, &data); } @@ -898,6 +953,7 @@ static int intel_pt_walk_insn(struct intel_pt_decoder *decoder, decoder->tot_insn_cnt += insn_cnt; decoder->timestamp_insn_cnt += insn_cnt; + decoder->sample_insn_cnt += insn_cnt; decoder->period_insn_cnt += insn_cnt; if (err) { @@ -990,6 +1046,57 @@ out_no_progress: return err; } +static bool intel_pt_fup_event(struct intel_pt_decoder *decoder) +{ + bool ret = false; + + if (decoder->set_fup_tx_flags) { + decoder->set_fup_tx_flags = false; + decoder->tx_flags = decoder->fup_tx_flags; + decoder->state.type = INTEL_PT_TRANSACTION; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + decoder->state.flags = decoder->fup_tx_flags; + return true; + } + if (decoder->set_fup_ptw) { + decoder->set_fup_ptw = false; + decoder->state.type = INTEL_PT_PTW; + decoder->state.flags |= INTEL_PT_FUP_IP; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + decoder->state.ptw_payload = decoder->fup_ptw_payload; + return true; + } + if (decoder->set_fup_mwait) { + decoder->set_fup_mwait = false; + decoder->state.type = INTEL_PT_MWAIT_OP; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + decoder->state.mwait_payload = decoder->fup_mwait_payload; + ret = true; + } + if (decoder->set_fup_pwre) { + decoder->set_fup_pwre = false; + decoder->state.type |= INTEL_PT_PWR_ENTRY; + decoder->state.type &= ~INTEL_PT_BRANCH; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + decoder->state.pwre_payload = decoder->fup_pwre_payload; + ret = true; + } + if (decoder->set_fup_exstop) { + decoder->set_fup_exstop = false; + decoder->state.type |= INTEL_PT_EX_STOP; + decoder->state.type &= ~INTEL_PT_BRANCH; + decoder->state.flags |= INTEL_PT_FUP_IP; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + ret = true; + } + return ret; +} + static int intel_pt_walk_fup(struct intel_pt_decoder *decoder) { struct intel_pt_insn intel_pt_insn; @@ -1003,15 +1110,8 @@ static int intel_pt_walk_fup(struct intel_pt_decoder *decoder) if (err == INTEL_PT_RETURN) return 0; if (err == -EAGAIN) { - if (decoder->set_fup_tx_flags) { - decoder->set_fup_tx_flags = false; - decoder->tx_flags = decoder->fup_tx_flags; - decoder->state.type = INTEL_PT_TRANSACTION; - decoder->state.from_ip = decoder->ip; - decoder->state.to_ip = 0; - decoder->state.flags = decoder->fup_tx_flags; + if (intel_pt_fup_event(decoder)) return 0; - } return err; } decoder->set_fup_tx_flags = false; @@ -1360,7 +1460,9 @@ static void intel_pt_calc_mtc_timestamp(struct intel_pt_decoder *decoder) static void intel_pt_calc_cbr(struct intel_pt_decoder *decoder) { - unsigned int cbr = decoder->packet.payload; + unsigned int cbr = decoder->packet.payload & 0xff; + + decoder->cbr_payload = decoder->packet.payload; if (decoder->cbr == cbr) return; @@ -1417,6 +1519,13 @@ static int intel_pt_walk_psbend(struct intel_pt_decoder *decoder) case INTEL_PT_TRACESTOP: case INTEL_PT_BAD: case INTEL_PT_PSB: + case INTEL_PT_PTWRITE: + case INTEL_PT_PTWRITE_IP: + case INTEL_PT_EXSTOP: + case INTEL_PT_EXSTOP_IP: + case INTEL_PT_MWAIT: + case INTEL_PT_PWRE: + case INTEL_PT_PWRX: decoder->have_tma = false; intel_pt_log("ERROR: Unexpected packet\n"); return -EAGAIN; @@ -1446,7 +1555,8 @@ static int intel_pt_walk_psbend(struct intel_pt_decoder *decoder) case INTEL_PT_FUP: decoder->pge = true; - intel_pt_set_last_ip(decoder); + if (decoder->packet.count) + intel_pt_set_last_ip(decoder); break; case INTEL_PT_MODE_TSX: @@ -1497,6 +1607,13 @@ static int intel_pt_walk_fup_tip(struct intel_pt_decoder *decoder) case INTEL_PT_MODE_TSX: case INTEL_PT_BAD: case INTEL_PT_PSBEND: + case INTEL_PT_PTWRITE: + case INTEL_PT_PTWRITE_IP: + case INTEL_PT_EXSTOP: + case INTEL_PT_EXSTOP_IP: + case INTEL_PT_MWAIT: + case INTEL_PT_PWRE: + case INTEL_PT_PWRX: intel_pt_log("ERROR: Missing TIP after FUP\n"); decoder->pkt_state = INTEL_PT_STATE_ERR3; return -ENOENT; @@ -1625,6 +1742,15 @@ next: break; } intel_pt_set_last_ip(decoder); + if (!decoder->branch_enable) { + decoder->ip = decoder->last_ip; + if (intel_pt_fup_event(decoder)) + return 0; + no_tip = false; + break; + } + if (decoder->set_fup_mwait) + no_tip = true; err = intel_pt_walk_fup(decoder); if (err != -EAGAIN) { if (err) @@ -1650,6 +1776,8 @@ next: break; case INTEL_PT_PSB: + decoder->last_ip = 0; + decoder->have_last_ip = true; intel_pt_clear_stack(&decoder->stack); err = intel_pt_walk_psbend(decoder); if (err == -EAGAIN) @@ -1696,6 +1824,16 @@ next: case INTEL_PT_CBR: intel_pt_calc_cbr(decoder); + if (!decoder->branch_enable && + decoder->cbr != decoder->cbr_seen) { + decoder->cbr_seen = decoder->cbr; + decoder->state.type = INTEL_PT_CBR_CHG; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + decoder->state.cbr_payload = + decoder->packet.payload; + return 0; + } break; case INTEL_PT_MODE_EXEC: @@ -1722,6 +1860,71 @@ next: case INTEL_PT_PAD: break; + case INTEL_PT_PTWRITE_IP: + decoder->fup_ptw_payload = decoder->packet.payload; + err = intel_pt_get_next_packet(decoder); + if (err) + return err; + if (decoder->packet.type == INTEL_PT_FUP) { + decoder->set_fup_ptw = true; + no_tip = true; + } else { + intel_pt_log_at("ERROR: Missing FUP after PTWRITE", + decoder->pos); + } + goto next; + + case INTEL_PT_PTWRITE: + decoder->state.type = INTEL_PT_PTW; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + decoder->state.ptw_payload = decoder->packet.payload; + return 0; + + case INTEL_PT_MWAIT: + decoder->fup_mwait_payload = decoder->packet.payload; + decoder->set_fup_mwait = true; + break; + + case INTEL_PT_PWRE: + if (decoder->set_fup_mwait) { + decoder->fup_pwre_payload = + decoder->packet.payload; + decoder->set_fup_pwre = true; + break; + } + decoder->state.type = INTEL_PT_PWR_ENTRY; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + decoder->state.pwrx_payload = decoder->packet.payload; + return 0; + + case INTEL_PT_EXSTOP_IP: + err = intel_pt_get_next_packet(decoder); + if (err) + return err; + if (decoder->packet.type == INTEL_PT_FUP) { + decoder->set_fup_exstop = true; + no_tip = true; + } else { + intel_pt_log_at("ERROR: Missing FUP after EXSTOP", + decoder->pos); + } + goto next; + + case INTEL_PT_EXSTOP: + decoder->state.type = INTEL_PT_EX_STOP; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + return 0; + + case INTEL_PT_PWRX: + decoder->state.type = INTEL_PT_PWR_EXIT; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + decoder->state.pwrx_payload = decoder->packet.payload; + return 0; + default: return intel_pt_bug(decoder); } @@ -1730,8 +1933,9 @@ next: static inline bool intel_pt_have_ip(struct intel_pt_decoder *decoder) { - return decoder->last_ip || decoder->packet.count == 0 || - decoder->packet.count == 3 || decoder->packet.count == 6; + return decoder->packet.count && + (decoder->have_last_ip || decoder->packet.count == 3 || + decoder->packet.count == 6); } /* Walk PSB+ packets to get in sync. */ @@ -1750,6 +1954,13 @@ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder) __fallthrough; case INTEL_PT_TIP_PGE: case INTEL_PT_TIP: + case INTEL_PT_PTWRITE: + case INTEL_PT_PTWRITE_IP: + case INTEL_PT_EXSTOP: + case INTEL_PT_EXSTOP_IP: + case INTEL_PT_MWAIT: + case INTEL_PT_PWRE: + case INTEL_PT_PWRX: intel_pt_log("ERROR: Unexpected packet\n"); return -ENOENT; @@ -1854,14 +2065,10 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder) break; case INTEL_PT_FUP: - if (decoder->overflow) { - if (intel_pt_have_ip(decoder)) - intel_pt_set_ip(decoder); - if (decoder->ip) - return 0; - } - if (decoder->packet.count) - intel_pt_set_last_ip(decoder); + if (intel_pt_have_ip(decoder)) + intel_pt_set_ip(decoder); + if (decoder->ip) + return 0; break; case INTEL_PT_MTC: @@ -1910,6 +2117,9 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder) break; case INTEL_PT_PSB: + decoder->last_ip = 0; + decoder->have_last_ip = true; + intel_pt_clear_stack(&decoder->stack); err = intel_pt_walk_psb(decoder); if (err) return err; @@ -1925,6 +2135,13 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder) case INTEL_PT_VMCS: case INTEL_PT_MNT: case INTEL_PT_PAD: + case INTEL_PT_PTWRITE: + case INTEL_PT_PTWRITE_IP: + case INTEL_PT_EXSTOP: + case INTEL_PT_EXSTOP_IP: + case INTEL_PT_MWAIT: + case INTEL_PT_PWRE: + case INTEL_PT_PWRX: default: break; } @@ -1935,6 +2152,19 @@ static int intel_pt_sync_ip(struct intel_pt_decoder *decoder) { int err; + decoder->set_fup_tx_flags = false; + decoder->set_fup_ptw = false; + decoder->set_fup_mwait = false; + decoder->set_fup_pwre = false; + decoder->set_fup_exstop = false; + + if (!decoder->branch_enable) { + decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; + decoder->overflow = false; + decoder->state.type = 0; /* Do not have a sample */ + return 0; + } + intel_pt_log("Scanning for full IP\n"); err = intel_pt_walk_to_ip(decoder); if (err) @@ -2043,6 +2273,7 @@ static int intel_pt_sync(struct intel_pt_decoder *decoder) decoder->pge = false; decoder->continuous_period = false; + decoder->have_last_ip = false; decoder->last_ip = 0; decoder->ip = 0; intel_pt_clear_stack(&decoder->stack); @@ -2051,6 +2282,7 @@ static int intel_pt_sync(struct intel_pt_decoder *decoder) if (err) return err; + decoder->have_last_ip = true; decoder->pkt_state = INTEL_PT_STATE_NO_IP; err = intel_pt_walk_psb(decoder); @@ -2069,7 +2301,7 @@ static int intel_pt_sync(struct intel_pt_decoder *decoder) static uint64_t intel_pt_est_timestamp(struct intel_pt_decoder *decoder) { - uint64_t est = decoder->timestamp_insn_cnt << 1; + uint64_t est = decoder->sample_insn_cnt << 1; if (!decoder->cbr || !decoder->max_non_turbo_ratio) goto out; @@ -2077,7 +2309,7 @@ static uint64_t intel_pt_est_timestamp(struct intel_pt_decoder *decoder) est *= decoder->max_non_turbo_ratio; est /= decoder->cbr; out: - return decoder->timestamp + est; + return decoder->sample_timestamp + est; } const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder) @@ -2093,8 +2325,10 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder) err = intel_pt_sync(decoder); break; case INTEL_PT_STATE_NO_IP: + decoder->have_last_ip = false; decoder->last_ip = 0; - /* Fall through */ + decoder->ip = 0; + __fallthrough; case INTEL_PT_STATE_ERR_RESYNC: err = intel_pt_sync_ip(decoder); break; @@ -2130,15 +2364,29 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder) } } while (err == -ENOLINK); - decoder->state.err = err ? intel_pt_ext_err(err) : 0; - decoder->state.timestamp = decoder->timestamp; + if (err) { + decoder->state.err = intel_pt_ext_err(err); + decoder->state.from_ip = decoder->ip; + decoder->sample_timestamp = decoder->timestamp; + decoder->sample_insn_cnt = decoder->timestamp_insn_cnt; + } else { + decoder->state.err = 0; + if (decoder->cbr != decoder->cbr_seen && decoder->state.type) { + decoder->cbr_seen = decoder->cbr; + decoder->state.type |= INTEL_PT_CBR_CHG; + decoder->state.cbr_payload = decoder->cbr_payload; + } + if (intel_pt_sample_time(decoder->pkt_state)) { + decoder->sample_timestamp = decoder->timestamp; + decoder->sample_insn_cnt = decoder->timestamp_insn_cnt; + } + } + + decoder->state.timestamp = decoder->sample_timestamp; decoder->state.est_timestamp = intel_pt_est_timestamp(decoder); decoder->state.cr3 = decoder->cr3; decoder->state.tot_insn_cnt = decoder->tot_insn_cnt; - if (err) - decoder->state.from_ip = decoder->ip; - return &decoder->state; } diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h index e90619a43c0c..921b22e8ca0e 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h @@ -25,11 +25,18 @@ #define INTEL_PT_IN_TX (1 << 0) #define INTEL_PT_ABORT_TX (1 << 1) #define INTEL_PT_ASYNC (1 << 2) +#define INTEL_PT_FUP_IP (1 << 3) enum intel_pt_sample_type { INTEL_PT_BRANCH = 1 << 0, INTEL_PT_INSTRUCTION = 1 << 1, INTEL_PT_TRANSACTION = 1 << 2, + INTEL_PT_PTW = 1 << 3, + INTEL_PT_MWAIT_OP = 1 << 4, + INTEL_PT_PWR_ENTRY = 1 << 5, + INTEL_PT_EX_STOP = 1 << 6, + INTEL_PT_PWR_EXIT = 1 << 7, + INTEL_PT_CBR_CHG = 1 << 8, }; enum intel_pt_period_type { @@ -63,6 +70,11 @@ struct intel_pt_state { uint64_t timestamp; uint64_t est_timestamp; uint64_t trace_nr; + uint64_t ptw_payload; + uint64_t mwait_payload; + uint64_t pwre_payload; + uint64_t pwrx_payload; + uint64_t cbr_payload; uint32_t flags; enum intel_pt_insn_op insn_op; int insn_len; @@ -87,6 +99,7 @@ struct intel_pt_params { bool (*pgd_ip)(uint64_t ip, void *data); void *data; bool return_compression; + bool branch_enable; uint64_t period; enum intel_pt_period_type period_type; unsigned max_non_turbo_ratio; diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-log.h b/tools/perf/util/intel-pt-decoder/intel-pt-log.h index debe751dc3d6..45b64f93f358 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-log.h +++ b/tools/perf/util/intel-pt-decoder/intel-pt-log.h @@ -16,6 +16,7 @@ #ifndef INCLUDE__INTEL_PT_LOG_H__ #define INCLUDE__INTEL_PT_LOG_H__ +#include <linux/compiler.h> #include <stdint.h> #include <inttypes.h> @@ -34,8 +35,7 @@ void __intel_pt_log_insn(struct intel_pt_insn *intel_pt_insn, uint64_t ip); void __intel_pt_log_insn_no_data(struct intel_pt_insn *intel_pt_insn, uint64_t ip); -__attribute__((format(printf, 1, 2))) -void __intel_pt_log(const char *fmt, ...); +void __intel_pt_log(const char *fmt, ...) __printf(1, 2); #define intel_pt_log(fmt, ...) \ do { \ diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c index 7528ae4f7e28..ba4c9dd18643 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c @@ -64,6 +64,13 @@ static const char * const packet_name[] = { [INTEL_PT_PIP] = "PIP", [INTEL_PT_OVF] = "OVF", [INTEL_PT_MNT] = "MNT", + [INTEL_PT_PTWRITE] = "PTWRITE", + [INTEL_PT_PTWRITE_IP] = "PTWRITE", + [INTEL_PT_EXSTOP] = "EXSTOP", + [INTEL_PT_EXSTOP_IP] = "EXSTOP", + [INTEL_PT_MWAIT] = "MWAIT", + [INTEL_PT_PWRE] = "PWRE", + [INTEL_PT_PWRX] = "PWRX", }; const char *intel_pt_pkt_name(enum intel_pt_pkt_type type) @@ -123,7 +130,7 @@ static int intel_pt_get_cbr(const unsigned char *buf, size_t len, if (len < 4) return INTEL_PT_NEED_MORE_BYTES; packet->type = INTEL_PT_CBR; - packet->payload = buf[2]; + packet->payload = le16_to_cpu(*(uint16_t *)(buf + 2)); return 4; } @@ -217,12 +224,80 @@ static int intel_pt_get_3byte(const unsigned char *buf, size_t len, } } +static int intel_pt_get_ptwrite(const unsigned char *buf, size_t len, + struct intel_pt_pkt *packet) +{ + packet->count = (buf[1] >> 5) & 0x3; + packet->type = buf[1] & BIT(7) ? INTEL_PT_PTWRITE_IP : + INTEL_PT_PTWRITE; + + switch (packet->count) { + case 0: + if (len < 6) + return INTEL_PT_NEED_MORE_BYTES; + packet->payload = le32_to_cpu(*(uint32_t *)(buf + 2)); + return 6; + case 1: + if (len < 10) + return INTEL_PT_NEED_MORE_BYTES; + packet->payload = le64_to_cpu(*(uint64_t *)(buf + 2)); + return 10; + default: + return INTEL_PT_BAD_PACKET; + } +} + +static int intel_pt_get_exstop(struct intel_pt_pkt *packet) +{ + packet->type = INTEL_PT_EXSTOP; + return 2; +} + +static int intel_pt_get_exstop_ip(struct intel_pt_pkt *packet) +{ + packet->type = INTEL_PT_EXSTOP_IP; + return 2; +} + +static int intel_pt_get_mwait(const unsigned char *buf, size_t len, + struct intel_pt_pkt *packet) +{ + if (len < 10) + return INTEL_PT_NEED_MORE_BYTES; + packet->type = INTEL_PT_MWAIT; + packet->payload = le64_to_cpu(*(uint64_t *)(buf + 2)); + return 10; +} + +static int intel_pt_get_pwre(const unsigned char *buf, size_t len, + struct intel_pt_pkt *packet) +{ + if (len < 4) + return INTEL_PT_NEED_MORE_BYTES; + packet->type = INTEL_PT_PWRE; + memcpy_le64(&packet->payload, buf + 2, 2); + return 4; +} + +static int intel_pt_get_pwrx(const unsigned char *buf, size_t len, + struct intel_pt_pkt *packet) +{ + if (len < 7) + return INTEL_PT_NEED_MORE_BYTES; + packet->type = INTEL_PT_PWRX; + memcpy_le64(&packet->payload, buf + 2, 5); + return 7; +} + static int intel_pt_get_ext(const unsigned char *buf, size_t len, struct intel_pt_pkt *packet) { if (len < 2) return INTEL_PT_NEED_MORE_BYTES; + if ((buf[1] & 0x1f) == 0x12) + return intel_pt_get_ptwrite(buf, len, packet); + switch (buf[1]) { case 0xa3: /* Long TNT */ return intel_pt_get_long_tnt(buf, len, packet); @@ -244,6 +319,16 @@ static int intel_pt_get_ext(const unsigned char *buf, size_t len, return intel_pt_get_tma(buf, len, packet); case 0xC3: /* 3-byte header */ return intel_pt_get_3byte(buf, len, packet); + case 0x62: /* EXSTOP no IP */ + return intel_pt_get_exstop(packet); + case 0xE2: /* EXSTOP with IP */ + return intel_pt_get_exstop_ip(packet); + case 0xC2: /* MWAIT */ + return intel_pt_get_mwait(buf, len, packet); + case 0x22: /* PWRE */ + return intel_pt_get_pwre(buf, len, packet); + case 0xA2: /* PWRX */ + return intel_pt_get_pwrx(buf, len, packet); default: return INTEL_PT_BAD_PACKET; } @@ -522,6 +607,29 @@ int intel_pt_pkt_desc(const struct intel_pt_pkt *packet, char *buf, ret = snprintf(buf, buf_len, "%s 0x%llx (NR=%d)", name, payload, nr); return ret; + case INTEL_PT_PTWRITE: + return snprintf(buf, buf_len, "%s 0x%llx IP:0", name, payload); + case INTEL_PT_PTWRITE_IP: + return snprintf(buf, buf_len, "%s 0x%llx IP:1", name, payload); + case INTEL_PT_EXSTOP: + return snprintf(buf, buf_len, "%s IP:0", name); + case INTEL_PT_EXSTOP_IP: + return snprintf(buf, buf_len, "%s IP:1", name); + case INTEL_PT_MWAIT: + return snprintf(buf, buf_len, "%s 0x%llx Hints 0x%x Extensions 0x%x", + name, payload, (unsigned int)(payload & 0xff), + (unsigned int)((payload >> 32) & 0x3)); + case INTEL_PT_PWRE: + return snprintf(buf, buf_len, "%s 0x%llx HW:%u CState:%u Sub-CState:%u", + name, payload, !!(payload & 0x80), + (unsigned int)((payload >> 12) & 0xf), + (unsigned int)((payload >> 8) & 0xf)); + case INTEL_PT_PWRX: + return snprintf(buf, buf_len, "%s 0x%llx Last CState:%u Deepest CState:%u Wake Reason 0x%x", + name, payload, + (unsigned int)((payload >> 4) & 0xf), + (unsigned int)(payload & 0xf), + (unsigned int)((payload >> 8) & 0xf)); default: break; } diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.h b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.h index 781bb79883bd..73ddc3a88d07 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.h +++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.h @@ -52,6 +52,13 @@ enum intel_pt_pkt_type { INTEL_PT_PIP, INTEL_PT_OVF, INTEL_PT_MNT, + INTEL_PT_PTWRITE, + INTEL_PT_PTWRITE_IP, + INTEL_PT_EXSTOP, + INTEL_PT_EXSTOP_IP, + INTEL_PT_MWAIT, + INTEL_PT_PWRE, + INTEL_PT_PWRX, }; struct intel_pt_pkt { diff --git a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt index 767be7c76034..12e377184ee4 100644 --- a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt +++ b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt @@ -1009,7 +1009,7 @@ GrpTable: Grp15 1: fxstor | RDGSBASE Ry (F3),(11B) 2: vldmxcsr Md (v1) | WRFSBASE Ry (F3),(11B) 3: vstmxcsr Md (v1) | WRGSBASE Ry (F3),(11B) -4: XSAVE +4: XSAVE | ptwrite Ey (F3),(11B) 5: XRSTOR | lfence (11B) 6: XSAVEOPT | clwb (66) | mfence (11B) 7: clflush | clflushopt (66) | sfence (11B) diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 4c7718f87a08..b58f9fd1e2ee 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -81,7 +81,6 @@ struct intel_pt { bool sample_instructions; u64 instructions_sample_type; - u64 instructions_sample_period; u64 instructions_id; bool sample_branches; @@ -93,6 +92,18 @@ struct intel_pt { u64 transactions_sample_type; u64 transactions_id; + bool sample_ptwrites; + u64 ptwrites_sample_type; + u64 ptwrites_id; + + bool sample_pwr_events; + u64 pwr_events_sample_type; + u64 mwait_id; + u64 pwre_id; + u64 exstop_id; + u64 pwrx_id; + u64 cbr_id; + bool synth_needs_swap; u64 tsc_bit; @@ -103,6 +114,7 @@ struct intel_pt { u64 cyc_bit; u64 noretcomp_bit; unsigned max_non_turbo_ratio; + unsigned cbr2khz; unsigned long num_events; @@ -668,6 +680,19 @@ static bool intel_pt_return_compression(struct intel_pt *pt) return true; } +static bool intel_pt_branch_enable(struct intel_pt *pt) +{ + struct perf_evsel *evsel; + u64 config; + + evlist__for_each_entry(pt->session->evlist, evsel) { + if (intel_pt_get_config(pt, &evsel->attr, &config) && + (config & 1) && !(config & 0x2000)) + return false; + } + return true; +} + static unsigned int intel_pt_mtc_period(struct intel_pt *pt) { struct perf_evsel *evsel; @@ -799,6 +824,7 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt, params.walk_insn = intel_pt_walk_next_insn; params.data = ptq; params.return_compression = intel_pt_return_compression(pt); + params.branch_enable = intel_pt_branch_enable(pt); params.max_non_turbo_ratio = pt->max_non_turbo_ratio; params.mtc_period = intel_pt_mtc_period(pt); params.tsc_ctc_ratio_n = pt->tsc_ctc_ratio_n; @@ -1044,6 +1070,36 @@ static void intel_pt_update_last_branch_rb(struct intel_pt_queue *ptq) bs->nr += 1; } +static inline bool intel_pt_skip_event(struct intel_pt *pt) +{ + return pt->synth_opts.initial_skip && + pt->num_events++ < pt->synth_opts.initial_skip; +} + +static void intel_pt_prep_b_sample(struct intel_pt *pt, + struct intel_pt_queue *ptq, + union perf_event *event, + struct perf_sample *sample) +{ + event->sample.header.type = PERF_RECORD_SAMPLE; + event->sample.header.misc = PERF_RECORD_MISC_USER; + event->sample.header.size = sizeof(struct perf_event_header); + + if (!pt->timeless_decoding) + sample->time = tsc_to_perf_time(ptq->timestamp, &pt->tc); + + sample->cpumode = PERF_RECORD_MISC_USER; + sample->ip = ptq->state->from_ip; + sample->pid = ptq->pid; + sample->tid = ptq->tid; + sample->addr = ptq->state->to_ip; + sample->period = 1; + sample->cpu = ptq->cpu; + sample->flags = ptq->flags; + sample->insn_len = ptq->insn_len; + memcpy(sample->insn, ptq->insn, INTEL_PT_INSN_BUF_SZ); +} + static int intel_pt_inject_event(union perf_event *event, struct perf_sample *sample, u64 type, bool swapped) @@ -1052,9 +1108,35 @@ static int intel_pt_inject_event(union perf_event *event, return perf_event__synthesize_sample(event, type, 0, sample, swapped); } -static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq) +static inline int intel_pt_opt_inject(struct intel_pt *pt, + union perf_event *event, + struct perf_sample *sample, u64 type) +{ + if (!pt->synth_opts.inject) + return 0; + + return intel_pt_inject_event(event, sample, type, pt->synth_needs_swap); +} + +static int intel_pt_deliver_synth_b_event(struct intel_pt *pt, + union perf_event *event, + struct perf_sample *sample, u64 type) { int ret; + + ret = intel_pt_opt_inject(pt, event, sample, type); + if (ret) + return ret; + + ret = perf_session__deliver_synth_event(pt->session, event, sample); + if (ret) + pr_err("Intel PT: failed to deliver event, error %d\n", ret); + + return ret; +} + +static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq) +{ struct intel_pt *pt = ptq->pt; union perf_event *event = ptq->event_buf; struct perf_sample sample = { .ip = 0, }; @@ -1066,29 +1148,13 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq) if (pt->branches_filter && !(pt->branches_filter & ptq->flags)) return 0; - if (pt->synth_opts.initial_skip && - pt->num_events++ < pt->synth_opts.initial_skip) + if (intel_pt_skip_event(pt)) return 0; - event->sample.header.type = PERF_RECORD_SAMPLE; - event->sample.header.misc = PERF_RECORD_MISC_USER; - event->sample.header.size = sizeof(struct perf_event_header); + intel_pt_prep_b_sample(pt, ptq, event, &sample); - if (!pt->timeless_decoding) - sample.time = tsc_to_perf_time(ptq->timestamp, &pt->tc); - - sample.cpumode = PERF_RECORD_MISC_USER; - sample.ip = ptq->state->from_ip; - sample.pid = ptq->pid; - sample.tid = ptq->tid; - sample.addr = ptq->state->to_ip; sample.id = ptq->pt->branches_id; sample.stream_id = ptq->pt->branches_id; - sample.period = 1; - sample.cpu = ptq->cpu; - sample.flags = ptq->flags; - sample.insn_len = ptq->insn_len; - memcpy(sample.insn, ptq->insn, INTEL_PT_INSN_BUF_SZ); /* * perf report cannot handle events without a branch stack when using @@ -1105,144 +1171,251 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq) sample.branch_stack = (struct branch_stack *)&dummy_bs; } - if (pt->synth_opts.inject) { - ret = intel_pt_inject_event(event, &sample, - pt->branches_sample_type, - pt->synth_needs_swap); - if (ret) - return ret; + return intel_pt_deliver_synth_b_event(pt, event, &sample, + pt->branches_sample_type); +} + +static void intel_pt_prep_sample(struct intel_pt *pt, + struct intel_pt_queue *ptq, + union perf_event *event, + struct perf_sample *sample) +{ + intel_pt_prep_b_sample(pt, ptq, event, sample); + + if (pt->synth_opts.callchain) { + thread_stack__sample(ptq->thread, ptq->chain, + pt->synth_opts.callchain_sz, sample->ip); + sample->callchain = ptq->chain; } - ret = perf_session__deliver_synth_event(pt->session, event, &sample); - if (ret) - pr_err("Intel Processor Trace: failed to deliver branch event, error %d\n", - ret); + if (pt->synth_opts.last_branch) { + intel_pt_copy_last_branch_rb(ptq); + sample->branch_stack = ptq->last_branch; + } +} + +static inline int intel_pt_deliver_synth_event(struct intel_pt *pt, + struct intel_pt_queue *ptq, + union perf_event *event, + struct perf_sample *sample, + u64 type) +{ + int ret; + + ret = intel_pt_deliver_synth_b_event(pt, event, sample, type); + + if (pt->synth_opts.last_branch) + intel_pt_reset_last_branch_rb(ptq); return ret; } static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq) { - int ret; struct intel_pt *pt = ptq->pt; union perf_event *event = ptq->event_buf; struct perf_sample sample = { .ip = 0, }; - if (pt->synth_opts.initial_skip && - pt->num_events++ < pt->synth_opts.initial_skip) + if (intel_pt_skip_event(pt)) return 0; - event->sample.header.type = PERF_RECORD_SAMPLE; - event->sample.header.misc = PERF_RECORD_MISC_USER; - event->sample.header.size = sizeof(struct perf_event_header); - - if (!pt->timeless_decoding) - sample.time = tsc_to_perf_time(ptq->timestamp, &pt->tc); + intel_pt_prep_sample(pt, ptq, event, &sample); - sample.cpumode = PERF_RECORD_MISC_USER; - sample.ip = ptq->state->from_ip; - sample.pid = ptq->pid; - sample.tid = ptq->tid; - sample.addr = ptq->state->to_ip; sample.id = ptq->pt->instructions_id; sample.stream_id = ptq->pt->instructions_id; sample.period = ptq->state->tot_insn_cnt - ptq->last_insn_cnt; - sample.cpu = ptq->cpu; - sample.flags = ptq->flags; - sample.insn_len = ptq->insn_len; - memcpy(sample.insn, ptq->insn, INTEL_PT_INSN_BUF_SZ); ptq->last_insn_cnt = ptq->state->tot_insn_cnt; - if (pt->synth_opts.callchain) { - thread_stack__sample(ptq->thread, ptq->chain, - pt->synth_opts.callchain_sz, sample.ip); - sample.callchain = ptq->chain; - } + return intel_pt_deliver_synth_event(pt, ptq, event, &sample, + pt->instructions_sample_type); +} - if (pt->synth_opts.last_branch) { - intel_pt_copy_last_branch_rb(ptq); - sample.branch_stack = ptq->last_branch; - } +static int intel_pt_synth_transaction_sample(struct intel_pt_queue *ptq) +{ + struct intel_pt *pt = ptq->pt; + union perf_event *event = ptq->event_buf; + struct perf_sample sample = { .ip = 0, }; - if (pt->synth_opts.inject) { - ret = intel_pt_inject_event(event, &sample, - pt->instructions_sample_type, - pt->synth_needs_swap); - if (ret) - return ret; - } + if (intel_pt_skip_event(pt)) + return 0; - ret = perf_session__deliver_synth_event(pt->session, event, &sample); - if (ret) - pr_err("Intel Processor Trace: failed to deliver instruction event, error %d\n", - ret); + intel_pt_prep_sample(pt, ptq, event, &sample); - if (pt->synth_opts.last_branch) - intel_pt_reset_last_branch_rb(ptq); + sample.id = ptq->pt->transactions_id; + sample.stream_id = ptq->pt->transactions_id; - return ret; + return intel_pt_deliver_synth_event(pt, ptq, event, &sample, + pt->transactions_sample_type); } -static int intel_pt_synth_transaction_sample(struct intel_pt_queue *ptq) +static void intel_pt_prep_p_sample(struct intel_pt *pt, + struct intel_pt_queue *ptq, + union perf_event *event, + struct perf_sample *sample) +{ + intel_pt_prep_sample(pt, ptq, event, sample); + + /* + * Zero IP is used to mean "trace start" but that is not the case for + * power or PTWRITE events with no IP, so clear the flags. + */ + if (!sample->ip) + sample->flags = 0; +} + +static int intel_pt_synth_ptwrite_sample(struct intel_pt_queue *ptq) { - int ret; struct intel_pt *pt = ptq->pt; union perf_event *event = ptq->event_buf; struct perf_sample sample = { .ip = 0, }; + struct perf_synth_intel_ptwrite raw; - if (pt->synth_opts.initial_skip && - pt->num_events++ < pt->synth_opts.initial_skip) + if (intel_pt_skip_event(pt)) return 0; - event->sample.header.type = PERF_RECORD_SAMPLE; - event->sample.header.misc = PERF_RECORD_MISC_USER; - event->sample.header.size = sizeof(struct perf_event_header); + intel_pt_prep_p_sample(pt, ptq, event, &sample); - if (!pt->timeless_decoding) - sample.time = tsc_to_perf_time(ptq->timestamp, &pt->tc); + sample.id = ptq->pt->ptwrites_id; + sample.stream_id = ptq->pt->ptwrites_id; - sample.cpumode = PERF_RECORD_MISC_USER; - sample.ip = ptq->state->from_ip; - sample.pid = ptq->pid; - sample.tid = ptq->tid; - sample.addr = ptq->state->to_ip; - sample.id = ptq->pt->transactions_id; - sample.stream_id = ptq->pt->transactions_id; - sample.period = 1; - sample.cpu = ptq->cpu; - sample.flags = ptq->flags; - sample.insn_len = ptq->insn_len; - memcpy(sample.insn, ptq->insn, INTEL_PT_INSN_BUF_SZ); + raw.flags = 0; + raw.ip = !!(ptq->state->flags & INTEL_PT_FUP_IP); + raw.payload = cpu_to_le64(ptq->state->ptw_payload); - if (pt->synth_opts.callchain) { - thread_stack__sample(ptq->thread, ptq->chain, - pt->synth_opts.callchain_sz, sample.ip); - sample.callchain = ptq->chain; - } + sample.raw_size = perf_synth__raw_size(raw); + sample.raw_data = perf_synth__raw_data(&raw); - if (pt->synth_opts.last_branch) { - intel_pt_copy_last_branch_rb(ptq); - sample.branch_stack = ptq->last_branch; - } + return intel_pt_deliver_synth_event(pt, ptq, event, &sample, + pt->ptwrites_sample_type); +} - if (pt->synth_opts.inject) { - ret = intel_pt_inject_event(event, &sample, - pt->transactions_sample_type, - pt->synth_needs_swap); - if (ret) - return ret; - } +static int intel_pt_synth_cbr_sample(struct intel_pt_queue *ptq) +{ + struct intel_pt *pt = ptq->pt; + union perf_event *event = ptq->event_buf; + struct perf_sample sample = { .ip = 0, }; + struct perf_synth_intel_cbr raw; + u32 flags; - ret = perf_session__deliver_synth_event(pt->session, event, &sample); - if (ret) - pr_err("Intel Processor Trace: failed to deliver transaction event, error %d\n", - ret); + if (intel_pt_skip_event(pt)) + return 0; - if (pt->synth_opts.last_branch) - intel_pt_reset_last_branch_rb(ptq); + intel_pt_prep_p_sample(pt, ptq, event, &sample); - return ret; + sample.id = ptq->pt->cbr_id; + sample.stream_id = ptq->pt->cbr_id; + + flags = (u16)ptq->state->cbr_payload | (pt->max_non_turbo_ratio << 16); + raw.flags = cpu_to_le32(flags); + raw.freq = cpu_to_le32(raw.cbr * pt->cbr2khz); + raw.reserved3 = 0; + + sample.raw_size = perf_synth__raw_size(raw); + sample.raw_data = perf_synth__raw_data(&raw); + + return intel_pt_deliver_synth_event(pt, ptq, event, &sample, + pt->pwr_events_sample_type); +} + +static int intel_pt_synth_mwait_sample(struct intel_pt_queue *ptq) +{ + struct intel_pt *pt = ptq->pt; + union perf_event *event = ptq->event_buf; + struct perf_sample sample = { .ip = 0, }; + struct perf_synth_intel_mwait raw; + + if (intel_pt_skip_event(pt)) + return 0; + + intel_pt_prep_p_sample(pt, ptq, event, &sample); + + sample.id = ptq->pt->mwait_id; + sample.stream_id = ptq->pt->mwait_id; + + raw.reserved = 0; + raw.payload = cpu_to_le64(ptq->state->mwait_payload); + + sample.raw_size = perf_synth__raw_size(raw); + sample.raw_data = perf_synth__raw_data(&raw); + + return intel_pt_deliver_synth_event(pt, ptq, event, &sample, + pt->pwr_events_sample_type); +} + +static int intel_pt_synth_pwre_sample(struct intel_pt_queue *ptq) +{ + struct intel_pt *pt = ptq->pt; + union perf_event *event = ptq->event_buf; + struct perf_sample sample = { .ip = 0, }; + struct perf_synth_intel_pwre raw; + + if (intel_pt_skip_event(pt)) + return 0; + + intel_pt_prep_p_sample(pt, ptq, event, &sample); + + sample.id = ptq->pt->pwre_id; + sample.stream_id = ptq->pt->pwre_id; + + raw.reserved = 0; + raw.payload = cpu_to_le64(ptq->state->pwre_payload); + + sample.raw_size = perf_synth__raw_size(raw); + sample.raw_data = perf_synth__raw_data(&raw); + + return intel_pt_deliver_synth_event(pt, ptq, event, &sample, + pt->pwr_events_sample_type); +} + +static int intel_pt_synth_exstop_sample(struct intel_pt_queue *ptq) +{ + struct intel_pt *pt = ptq->pt; + union perf_event *event = ptq->event_buf; + struct perf_sample sample = { .ip = 0, }; + struct perf_synth_intel_exstop raw; + + if (intel_pt_skip_event(pt)) + return 0; + + intel_pt_prep_p_sample(pt, ptq, event, &sample); + + sample.id = ptq->pt->exstop_id; + sample.stream_id = ptq->pt->exstop_id; + + raw.flags = 0; + raw.ip = !!(ptq->state->flags & INTEL_PT_FUP_IP); + + sample.raw_size = perf_synth__raw_size(raw); + sample.raw_data = perf_synth__raw_data(&raw); + + return intel_pt_deliver_synth_event(pt, ptq, event, &sample, + pt->pwr_events_sample_type); +} + +static int intel_pt_synth_pwrx_sample(struct intel_pt_queue *ptq) +{ + struct intel_pt *pt = ptq->pt; + union perf_event *event = ptq->event_buf; + struct perf_sample sample = { .ip = 0, }; + struct perf_synth_intel_pwrx raw; + + if (intel_pt_skip_event(pt)) + return 0; + + intel_pt_prep_p_sample(pt, ptq, event, &sample); + + sample.id = ptq->pt->pwrx_id; + sample.stream_id = ptq->pt->pwrx_id; + + raw.reserved = 0; + raw.payload = cpu_to_le64(ptq->state->pwrx_payload); + + sample.raw_size = perf_synth__raw_size(raw); + sample.raw_data = perf_synth__raw_data(&raw); + + return intel_pt_deliver_synth_event(pt, ptq, event, &sample, + pt->pwr_events_sample_type); } static int intel_pt_synth_error(struct intel_pt *pt, int code, int cpu, @@ -1296,6 +1469,10 @@ static inline bool intel_pt_is_switch_ip(struct intel_pt_queue *ptq, u64 ip) PERF_IP_FLAG_INTERRUPT | PERF_IP_FLAG_TX_ABORT)); } +#define INTEL_PT_PWR_EVT (INTEL_PT_MWAIT_OP | INTEL_PT_PWR_ENTRY | \ + INTEL_PT_EX_STOP | INTEL_PT_PWR_EXIT | \ + INTEL_PT_CBR_CHG) + static int intel_pt_sample(struct intel_pt_queue *ptq) { const struct intel_pt_state *state = ptq->state; @@ -1307,24 +1484,52 @@ static int intel_pt_sample(struct intel_pt_queue *ptq) ptq->have_sample = false; - if (pt->sample_instructions && - (state->type & INTEL_PT_INSTRUCTION) && - (!pt->synth_opts.initial_skip || - pt->num_events++ >= pt->synth_opts.initial_skip)) { + if (pt->sample_pwr_events && (state->type & INTEL_PT_PWR_EVT)) { + if (state->type & INTEL_PT_CBR_CHG) { + err = intel_pt_synth_cbr_sample(ptq); + if (err) + return err; + } + if (state->type & INTEL_PT_MWAIT_OP) { + err = intel_pt_synth_mwait_sample(ptq); + if (err) + return err; + } + if (state->type & INTEL_PT_PWR_ENTRY) { + err = intel_pt_synth_pwre_sample(ptq); + if (err) + return err; + } + if (state->type & INTEL_PT_EX_STOP) { + err = intel_pt_synth_exstop_sample(ptq); + if (err) + return err; + } + if (state->type & INTEL_PT_PWR_EXIT) { + err = intel_pt_synth_pwrx_sample(ptq); + if (err) + return err; + } + } + + if (pt->sample_instructions && (state->type & INTEL_PT_INSTRUCTION)) { err = intel_pt_synth_instruction_sample(ptq); if (err) return err; } - if (pt->sample_transactions && - (state->type & INTEL_PT_TRANSACTION) && - (!pt->synth_opts.initial_skip || - pt->num_events++ >= pt->synth_opts.initial_skip)) { + if (pt->sample_transactions && (state->type & INTEL_PT_TRANSACTION)) { err = intel_pt_synth_transaction_sample(ptq); if (err) return err; } + if (pt->sample_ptwrites && (state->type & INTEL_PT_PTW)) { + err = intel_pt_synth_ptwrite_sample(ptq); + if (err) + return err; + } + if (!(state->type & INTEL_PT_BRANCH)) return 0; @@ -1925,36 +2130,65 @@ static int intel_pt_event_synth(struct perf_tool *tool, NULL); } -static int intel_pt_synth_event(struct perf_session *session, +static int intel_pt_synth_event(struct perf_session *session, const char *name, struct perf_event_attr *attr, u64 id) { struct intel_pt_synth intel_pt_synth; + int err; + + pr_debug("Synthesizing '%s' event with id %" PRIu64 " sample type %#" PRIx64 "\n", + name, id, (u64)attr->sample_type); memset(&intel_pt_synth, 0, sizeof(struct intel_pt_synth)); intel_pt_synth.session = session; - return perf_event__synthesize_attr(&intel_pt_synth.dummy_tool, attr, 1, - &id, intel_pt_event_synth); + err = perf_event__synthesize_attr(&intel_pt_synth.dummy_tool, attr, 1, + &id, intel_pt_event_synth); + if (err) + pr_err("%s: failed to synthesize '%s' event type\n", + __func__, name); + + return err; } -static int intel_pt_synth_events(struct intel_pt *pt, - struct perf_session *session) +static void intel_pt_set_event_name(struct perf_evlist *evlist, u64 id, + const char *name) { - struct perf_evlist *evlist = session->evlist; struct perf_evsel *evsel; - struct perf_event_attr attr; - bool found = false; - u64 id; - int err; evlist__for_each_entry(evlist, evsel) { - if (evsel->attr.type == pt->pmu_type && evsel->ids) { - found = true; + if (evsel->id && evsel->id[0] == id) { + if (evsel->name) + zfree(&evsel->name); + evsel->name = strdup(name); break; } } +} - if (!found) { +static struct perf_evsel *intel_pt_evsel(struct intel_pt *pt, + struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + + evlist__for_each_entry(evlist, evsel) { + if (evsel->attr.type == pt->pmu_type && evsel->ids) + return evsel; + } + + return NULL; +} + +static int intel_pt_synth_events(struct intel_pt *pt, + struct perf_session *session) +{ + struct perf_evlist *evlist = session->evlist; + struct perf_evsel *evsel = intel_pt_evsel(pt, evlist); + struct perf_event_attr attr; + u64 id; + int err; + + if (!evsel) { pr_debug("There are no selected events with Intel Processor Trace data\n"); return 0; } @@ -1983,6 +2217,25 @@ static int intel_pt_synth_events(struct intel_pt *pt, if (!id) id = 1; + if (pt->synth_opts.branches) { + attr.config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS; + attr.sample_period = 1; + attr.sample_type |= PERF_SAMPLE_ADDR; + err = intel_pt_synth_event(session, "branches", &attr, id); + if (err) + return err; + pt->sample_branches = true; + pt->branches_sample_type = attr.sample_type; + pt->branches_id = id; + id += 1; + attr.sample_type &= ~(u64)PERF_SAMPLE_ADDR; + } + + if (pt->synth_opts.callchain) + attr.sample_type |= PERF_SAMPLE_CALLCHAIN; + if (pt->synth_opts.last_branch) + attr.sample_type |= PERF_SAMPLE_BRANCH_STACK; + if (pt->synth_opts.instructions) { attr.config = PERF_COUNT_HW_INSTRUCTIONS; if (pt->synth_opts.period_type == PERF_ITRACE_PERIOD_NANOSECS) @@ -1990,70 +2243,90 @@ static int intel_pt_synth_events(struct intel_pt *pt, intel_pt_ns_to_ticks(pt, pt->synth_opts.period); else attr.sample_period = pt->synth_opts.period; - pt->instructions_sample_period = attr.sample_period; - if (pt->synth_opts.callchain) - attr.sample_type |= PERF_SAMPLE_CALLCHAIN; - if (pt->synth_opts.last_branch) - attr.sample_type |= PERF_SAMPLE_BRANCH_STACK; - pr_debug("Synthesizing 'instructions' event with id %" PRIu64 " sample type %#" PRIx64 "\n", - id, (u64)attr.sample_type); - err = intel_pt_synth_event(session, &attr, id); - if (err) { - pr_err("%s: failed to synthesize 'instructions' event type\n", - __func__); + err = intel_pt_synth_event(session, "instructions", &attr, id); + if (err) return err; - } pt->sample_instructions = true; pt->instructions_sample_type = attr.sample_type; pt->instructions_id = id; id += 1; } + attr.sample_type &= ~(u64)PERF_SAMPLE_PERIOD; + attr.sample_period = 1; + if (pt->synth_opts.transactions) { attr.config = PERF_COUNT_HW_INSTRUCTIONS; - attr.sample_period = 1; - if (pt->synth_opts.callchain) - attr.sample_type |= PERF_SAMPLE_CALLCHAIN; - if (pt->synth_opts.last_branch) - attr.sample_type |= PERF_SAMPLE_BRANCH_STACK; - pr_debug("Synthesizing 'transactions' event with id %" PRIu64 " sample type %#" PRIx64 "\n", - id, (u64)attr.sample_type); - err = intel_pt_synth_event(session, &attr, id); - if (err) { - pr_err("%s: failed to synthesize 'transactions' event type\n", - __func__); + err = intel_pt_synth_event(session, "transactions", &attr, id); + if (err) return err; - } pt->sample_transactions = true; + pt->transactions_sample_type = attr.sample_type; pt->transactions_id = id; + intel_pt_set_event_name(evlist, id, "transactions"); id += 1; - evlist__for_each_entry(evlist, evsel) { - if (evsel->id && evsel->id[0] == pt->transactions_id) { - if (evsel->name) - zfree(&evsel->name); - evsel->name = strdup("transactions"); - break; - } - } } - if (pt->synth_opts.branches) { - attr.config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS; - attr.sample_period = 1; - attr.sample_type |= PERF_SAMPLE_ADDR; - attr.sample_type &= ~(u64)PERF_SAMPLE_CALLCHAIN; - attr.sample_type &= ~(u64)PERF_SAMPLE_BRANCH_STACK; - pr_debug("Synthesizing 'branches' event with id %" PRIu64 " sample type %#" PRIx64 "\n", - id, (u64)attr.sample_type); - err = intel_pt_synth_event(session, &attr, id); - if (err) { - pr_err("%s: failed to synthesize 'branches' event type\n", - __func__); + attr.type = PERF_TYPE_SYNTH; + attr.sample_type |= PERF_SAMPLE_RAW; + + if (pt->synth_opts.ptwrites) { + attr.config = PERF_SYNTH_INTEL_PTWRITE; + err = intel_pt_synth_event(session, "ptwrite", &attr, id); + if (err) return err; - } - pt->sample_branches = true; - pt->branches_sample_type = attr.sample_type; - pt->branches_id = id; + pt->sample_ptwrites = true; + pt->ptwrites_sample_type = attr.sample_type; + pt->ptwrites_id = id; + intel_pt_set_event_name(evlist, id, "ptwrite"); + id += 1; + } + + if (pt->synth_opts.pwr_events) { + pt->sample_pwr_events = true; + pt->pwr_events_sample_type = attr.sample_type; + + attr.config = PERF_SYNTH_INTEL_CBR; + err = intel_pt_synth_event(session, "cbr", &attr, id); + if (err) + return err; + pt->cbr_id = id; + intel_pt_set_event_name(evlist, id, "cbr"); + id += 1; + } + + if (pt->synth_opts.pwr_events && (evsel->attr.config & 0x10)) { + attr.config = PERF_SYNTH_INTEL_MWAIT; + err = intel_pt_synth_event(session, "mwait", &attr, id); + if (err) + return err; + pt->mwait_id = id; + intel_pt_set_event_name(evlist, id, "mwait"); + id += 1; + + attr.config = PERF_SYNTH_INTEL_PWRE; + err = intel_pt_synth_event(session, "pwre", &attr, id); + if (err) + return err; + pt->pwre_id = id; + intel_pt_set_event_name(evlist, id, "pwre"); + id += 1; + + attr.config = PERF_SYNTH_INTEL_EXSTOP; + err = intel_pt_synth_event(session, "exstop", &attr, id); + if (err) + return err; + pt->exstop_id = id; + intel_pt_set_event_name(evlist, id, "exstop"); + id += 1; + + attr.config = PERF_SYNTH_INTEL_PWRX; + err = intel_pt_synth_event(session, "pwrx", &attr, id); + if (err) + return err; + pt->pwrx_id = id; + intel_pt_set_event_name(evlist, id, "pwrx"); + id += 1; } pt->synth_needs_swap = evsel->needs_swap; @@ -2322,6 +2595,7 @@ int intel_pt_process_auxtrace_info(union perf_event *event, intel_pt_log("TSC frequency %"PRIu64"\n", tsc_freq); intel_pt_log("Maximum non-turbo ratio %u\n", pt->max_non_turbo_ratio); + pt->cbr2khz = tsc_freq / pt->max_non_turbo_ratio / 1000; } if (pt->synth_opts.calls) diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c index c6a15f204c03..209b0c82eff4 100644 --- a/tools/perf/util/llvm-utils.c +++ b/tools/perf/util/llvm-utils.c @@ -33,7 +33,7 @@ struct llvm_param llvm_param = { int perf_llvm_config(const char *var, const char *value) { - if (prefixcmp(var, "llvm.")) + if (!strstarts(var, "llvm.")) return 0; var += sizeof("llvm.") - 1; diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 5de2b86b9880..df709363ef69 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -705,7 +705,8 @@ size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp) if (kdso->has_build_id) { char filename[PATH_MAX]; - if (dso__build_id_filename(kdso, filename, sizeof(filename))) + if (dso__build_id_filename(kdso, filename, sizeof(filename), + false)) printed += fprintf(fp, "[0] %s\n", filename); } @@ -1137,7 +1138,8 @@ int __weak arch__fix_module_text_start(u64 *start __maybe_unused, return 0; } -static int machine__create_module(void *arg, const char *name, u64 start) +static int machine__create_module(void *arg, const char *name, u64 start, + u64 size) { struct machine *machine = arg; struct map *map; @@ -1148,6 +1150,7 @@ static int machine__create_module(void *arg, const char *name, u64 start) map = machine__findnew_module_map(machine, start, name); if (map == NULL) return -1; + map->end = start + size; dso__kernel_module_get_build_id(map->dso, machine->root_dir); @@ -1392,7 +1395,7 @@ int machine__process_mmap2_event(struct machine *machine, map = map__new(machine, event->mmap2.start, event->mmap2.len, event->mmap2.pgoff, - event->mmap2.pid, event->mmap2.maj, + event->mmap2.maj, event->mmap2.min, event->mmap2.ino, event->mmap2.ino_generation, event->mmap2.prot, @@ -1450,7 +1453,7 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event map = map__new(machine, event->mmap.start, event->mmap.len, event->mmap.pgoff, - event->mmap.pid, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, event->mmap.filename, type, thread); @@ -1632,10 +1635,12 @@ static void ip__resolve_ams(struct thread *thread, ams->al_addr = al.addr; ams->sym = al.sym; ams->map = al.map; + ams->phys_addr = 0; } static void ip__resolve_data(struct thread *thread, - u8 m, struct addr_map_symbol *ams, u64 addr) + u8 m, struct addr_map_symbol *ams, + u64 addr, u64 phys_addr) { struct addr_location al; @@ -1655,6 +1660,7 @@ static void ip__resolve_data(struct thread *thread, ams->al_addr = al.addr; ams->sym = al.sym; ams->map = al.map; + ams->phys_addr = phys_addr; } struct mem_info *sample__resolve_mem(struct perf_sample *sample, @@ -1666,12 +1672,18 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample, return NULL; ip__resolve_ams(al->thread, &mi->iaddr, sample->ip); - ip__resolve_data(al->thread, al->cpumode, &mi->daddr, sample->addr); + ip__resolve_data(al->thread, al->cpumode, &mi->daddr, + sample->addr, sample->phys_addr); mi->data_src.val = sample->data_src; return mi; } +struct iterations { + int nr_loop_iter; + u64 cycles; +}; + static int add_callchain_ip(struct thread *thread, struct callchain_cursor *cursor, struct symbol **parent, @@ -1680,10 +1692,12 @@ static int add_callchain_ip(struct thread *thread, u64 ip, bool branch, struct branch_flags *flags, - int nr_loop_iter, - int samples) + struct iterations *iter, + u64 branch_from) { struct addr_location al; + int nr_loop_iter = 0; + u64 iter_cycles = 0; al.filtered = 0; al.sym = NULL; @@ -1733,8 +1747,15 @@ static int add_callchain_ip(struct thread *thread, if (symbol_conf.hide_unresolved && al.sym == NULL) return 0; + + if (iter) { + nr_loop_iter = iter->nr_loop_iter; + iter_cycles = iter->cycles; + } + return callchain_cursor_append(cursor, al.addr, al.map, al.sym, - branch, flags, nr_loop_iter, samples); + branch, flags, nr_loop_iter, + iter_cycles, branch_from); } struct branch_info *sample__resolve_bstack(struct perf_sample *sample, @@ -1755,6 +1776,18 @@ struct branch_info *sample__resolve_bstack(struct perf_sample *sample, return bi; } +static void save_iterations(struct iterations *iter, + struct branch_entry *be, int nr) +{ + int i; + + iter->nr_loop_iter = nr; + iter->cycles = 0; + + for (i = 0; i < nr; i++) + iter->cycles += be[i].flags.cycles; +} + #define CHASHSZ 127 #define CHASHBITS 7 #define NO_ENTRY 0xff @@ -1762,7 +1795,8 @@ struct branch_info *sample__resolve_bstack(struct perf_sample *sample, #define PERF_MAX_BRANCH_DEPTH 127 /* Remove loops. */ -static int remove_loops(struct branch_entry *l, int nr) +static int remove_loops(struct branch_entry *l, int nr, + struct iterations *iter) { int i, j, off; unsigned char chash[CHASHSZ]; @@ -1787,8 +1821,18 @@ static int remove_loops(struct branch_entry *l, int nr) break; } if (is_loop) { - memmove(l + i, l + i + off, - (nr - (i + off)) * sizeof(*l)); + j = nr - (i + off); + if (j > 0) { + save_iterations(iter + i + off, + l + i, off); + + memmove(iter + i, iter + i + off, + j * sizeof(*iter)); + + memmove(l + i, l + i + off, + j * sizeof(*l)); + } + nr -= off; } } @@ -1813,7 +1857,7 @@ static int resolve_lbr_callchain_sample(struct thread *thread, struct ip_callchain *chain = sample->callchain; int chain_nr = min(max_stack, (int)chain->nr), i; u8 cpumode = PERF_RECORD_MISC_USER; - u64 ip; + u64 ip, branch_from = 0; for (i = 0; i < chain_nr; i++) { if (chain->ips[i] == PERF_CONTEXT_USER) @@ -1855,6 +1899,8 @@ static int resolve_lbr_callchain_sample(struct thread *thread, ip = lbr_stack->entries[0].to; branch = true; flags = &lbr_stack->entries[0].flags; + branch_from = + lbr_stack->entries[0].from; } } else { if (j < lbr_nr) { @@ -1869,12 +1915,15 @@ static int resolve_lbr_callchain_sample(struct thread *thread, ip = lbr_stack->entries[0].to; branch = true; flags = &lbr_stack->entries[0].flags; + branch_from = + lbr_stack->entries[0].from; } } err = add_callchain_ip(thread, cursor, parent, root_al, &cpumode, ip, - branch, flags, 0, 0); + branch, flags, NULL, + branch_from); if (err) return (err < 0) ? err : 0; } @@ -1894,12 +1943,14 @@ static int thread__resolve_callchain_sample(struct thread *thread, { struct branch_stack *branch = sample->branch_stack; struct ip_callchain *chain = sample->callchain; - int chain_nr = chain->nr; + int chain_nr = 0; u8 cpumode = PERF_RECORD_MISC_USER; int i, j, err, nr_entries; int skip_idx = -1; int first_call = 0; - int nr_loop_iter; + + if (chain) + chain_nr = chain->nr; if (perf_evsel__has_branch_callstack(evsel)) { err = resolve_lbr_callchain_sample(thread, cursor, sample, parent, @@ -1929,6 +1980,7 @@ static int thread__resolve_callchain_sample(struct thread *thread, if (branch && callchain_param.branch_callstack) { int nr = min(max_stack, (int)branch->nr); struct branch_entry be[nr]; + struct iterations iter[nr]; if (branch->nr > PERF_MAX_BRANCH_DEPTH) { pr_warning("corrupted branch chain. skipping...\n"); @@ -1938,6 +1990,10 @@ static int thread__resolve_callchain_sample(struct thread *thread, for (i = 0; i < nr; i++) { if (callchain_param.order == ORDER_CALLEE) { be[i] = branch->entries[i]; + + if (chain == NULL) + continue; + /* * Check for overlap into the callchain. * The return address is one off compared to @@ -1955,42 +2011,30 @@ static int thread__resolve_callchain_sample(struct thread *thread, be[i] = branch->entries[branch->nr - i - 1]; } - nr_loop_iter = nr; - nr = remove_loops(be, nr); - - /* - * Get the number of iterations. - * It's only approximation, but good enough in practice. - */ - if (nr_loop_iter > nr) - nr_loop_iter = nr_loop_iter - nr + 1; - else - nr_loop_iter = 0; + memset(iter, 0, sizeof(struct iterations) * nr); + nr = remove_loops(be, nr, iter); for (i = 0; i < nr; i++) { - if (i == nr - 1) - err = add_callchain_ip(thread, cursor, parent, - root_al, - NULL, be[i].to, - true, &be[i].flags, - nr_loop_iter, 1); - else - err = add_callchain_ip(thread, cursor, parent, - root_al, - NULL, be[i].to, - true, &be[i].flags, - 0, 0); + err = add_callchain_ip(thread, cursor, parent, + root_al, + NULL, be[i].to, + true, &be[i].flags, + NULL, be[i].from); if (!err) err = add_callchain_ip(thread, cursor, parent, root_al, NULL, be[i].from, true, &be[i].flags, - 0, 0); + &iter[i], 0); if (err == -EINVAL) break; if (err) return err; } + + if (chain_nr == 0) + return 0; + chain_nr -= nr; } @@ -2015,7 +2059,7 @@ check_calls: err = add_callchain_ip(thread, cursor, parent, root_al, &cpumode, ip, - false, NULL, 0, 0); + false, NULL, NULL, 0); if (err) return (err < 0) ? err : 0; @@ -2032,7 +2076,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) return 0; return callchain_cursor_append(cursor, entry->ip, entry->map, entry->sym, - false, NULL, 0, 0); + false, NULL, 0, 0, 0); } static int thread__resolve_callchain_unwind(struct thread *thread, @@ -2209,7 +2253,7 @@ int machine__get_kernel_start(struct machine *machine) machine->kernel_start = 1ULL << 63; if (map) { err = map__load(map); - if (map->start) + if (!err) machine->kernel_start = map->start; } return err; diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 2179b2deb730..bdaa0a4edc17 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -16,6 +16,7 @@ #include "machine.h" #include <linux/string.h> #include "srcline.h" +#include "namespaces.h" #include "unwind.h" static void __maps__insert(struct maps *maps, struct map *map); @@ -145,11 +146,13 @@ void map__init(struct map *map, enum map_type type, } struct map *map__new(struct machine *machine, u64 start, u64 len, - u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino, + u64 pgoff, u32 d_maj, u32 d_min, u64 ino, u64 ino_gen, u32 prot, u32 flags, char *filename, enum map_type type, struct thread *thread) { struct map *map = malloc(sizeof(*map)); + struct nsinfo *nsi = NULL; + struct nsinfo *nnsi; if (map != NULL) { char newfilename[PATH_MAX]; @@ -167,9 +170,11 @@ struct map *map__new(struct machine *machine, u64 start, u64 len, map->ino_generation = ino_gen; map->prot = prot; map->flags = flags; + nsi = nsinfo__get(thread->nsinfo); - if ((anon || no_dso) && type == MAP__FUNCTION) { - snprintf(newfilename, sizeof(newfilename), "/tmp/perf-%d.map", pid); + if ((anon || no_dso) && nsi && type == MAP__FUNCTION) { + snprintf(newfilename, sizeof(newfilename), + "/tmp/perf-%d.map", nsi->pid); filename = newfilename; } @@ -179,6 +184,16 @@ struct map *map__new(struct machine *machine, u64 start, u64 len, } if (vdso) { + /* The vdso maps are always on the host and not the + * container. Ensure that we don't use setns to look + * them up. + */ + nnsi = nsinfo__copy(nsi); + if (nnsi) { + nsinfo__put(nsi); + nnsi->need_setns = false; + nsi = nnsi; + } pgoff = 0; dso = machine__findnew_vdso(machine, thread); } else @@ -200,10 +215,12 @@ struct map *map__new(struct machine *machine, u64 start, u64 len, if (type != MAP__FUNCTION) dso__set_loaded(dso, map->type); } + dso->nsinfo = nsi; dso__put(dso); } return map; out_delete: + nsinfo__put(nsi); free(map); return NULL; } diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index f9e8ac8a52cd..73aacf7a7dc4 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -141,7 +141,7 @@ struct thread; void map__init(struct map *map, enum map_type type, u64 start, u64 end, u64 pgoff, struct dso *dso); struct map *map__new(struct machine *machine, u64 start, u64 len, - u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino, + u64 pgoff, u32 d_maj, u32 d_min, u64 ino, u64 ino_gen, u32 prot, u32 flags, char *filename, enum map_type type, struct thread *thread); struct map *map__new2(u64 start, struct dso *dso, enum map_type type); diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c index 06f5a3a4295c..28afe5fa84d6 100644 --- a/tools/perf/util/mem-events.c +++ b/tools/perf/util/mem-events.c @@ -166,11 +166,20 @@ static const char * const mem_lvl[] = { "Uncached", }; +static const char * const mem_lvlnum[] = { + [PERF_MEM_LVLNUM_ANY_CACHE] = "Any cache", + [PERF_MEM_LVLNUM_LFB] = "LFB", + [PERF_MEM_LVLNUM_RAM] = "RAM", + [PERF_MEM_LVLNUM_PMEM] = "PMEM", + [PERF_MEM_LVLNUM_NA] = "N/A", +}; + int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info) { size_t i, l = 0; u64 m = PERF_MEM_LVL_NA; u64 hit, miss; + int printed; if (mem_info) m = mem_info->data_src.mem_lvl; @@ -184,17 +193,37 @@ int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info) /* already taken care of */ m &= ~(PERF_MEM_LVL_HIT|PERF_MEM_LVL_MISS); + + if (mem_info && mem_info->data_src.mem_remote) { + strcat(out, "Remote "); + l += 7; + } + + printed = 0; for (i = 0; m && i < ARRAY_SIZE(mem_lvl); i++, m >>= 1) { if (!(m & 0x1)) continue; - if (l) { + if (printed++) { strcat(out, " or "); l += 4; } l += scnprintf(out + l, sz - l, mem_lvl[i]); } - if (*out == '\0') - l += scnprintf(out, sz - l, "N/A"); + + if (mem_info && mem_info->data_src.mem_lvl_num) { + int lvl = mem_info->data_src.mem_lvl_num; + if (printed++) { + strcat(out, " or "); + l += 4; + } + if (mem_lvlnum[lvl]) + l += scnprintf(out + l, sz - l, mem_lvlnum[lvl]); + else + l += scnprintf(out + l, sz - l, "L%d", lvl); + } + + if (l == 0) + l += scnprintf(out + l, sz - l, "N/A"); if (hit) l += scnprintf(out + l, sz - l, " hit"); if (miss) @@ -231,6 +260,14 @@ int perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info) } l += scnprintf(out + l, sz - l, snoop_access[i]); } + if (mem_info && + (mem_info->data_src.mem_snoopx & PERF_MEM_SNOOPX_FWD)) { + if (l) { + strcat(out, " or "); + l += 4; + } + l += scnprintf(out + l, sz - l, "Fwd"); + } if (*out == '\0') l += scnprintf(out, sz - l, "N/A"); @@ -279,6 +316,11 @@ int c2c_decode_stats(struct c2c_stats *stats, struct mem_info *mi) u64 lvl = data_src->mem_lvl; u64 snoop = data_src->mem_snoop; u64 lock = data_src->mem_lock; + /* + * Skylake might report unknown remote level via this + * bit, consider it when evaluating remote HITMs. + */ + bool mrem = data_src->mem_remote; int err = 0; #define HITM_INC(__f) \ @@ -324,7 +366,8 @@ do { \ } if ((lvl & P(LVL, REM_RAM1)) || - (lvl & P(LVL, REM_RAM2))) { + (lvl & P(LVL, REM_RAM2)) || + mrem) { stats->rmt_dram++; if (snoop & P(SNOOP, HIT)) stats->ld_shared++; @@ -334,7 +377,8 @@ do { \ } if ((lvl & P(LVL, REM_CCE1)) || - (lvl & P(LVL, REM_CCE2))) { + (lvl & P(LVL, REM_CCE2)) || + mrem) { if (snoop & P(SNOOP, HIT)) stats->rmt_hit++; else if (snoop & P(SNOOP, HITM)) diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c index 67dcbcc73c7d..a58e91197729 100644 --- a/tools/perf/util/namespaces.c +++ b/tools/perf/util/namespaces.c @@ -9,9 +9,14 @@ #include "namespaces.h" #include "util.h" #include "event.h" +#include <sys/types.h> +#include <sys/stat.h> +#include <limits.h> +#include <sched.h> #include <stdlib.h> #include <stdio.h> #include <string.h> +#include <unistd.h> struct namespaces *namespaces__new(struct namespaces_event *event) { @@ -35,3 +40,209 @@ void namespaces__free(struct namespaces *namespaces) { free(namespaces); } + +int nsinfo__init(struct nsinfo *nsi) +{ + char oldns[PATH_MAX]; + char spath[PATH_MAX]; + char *newns = NULL; + char *statln = NULL; + struct stat old_stat; + struct stat new_stat; + FILE *f = NULL; + size_t linesz = 0; + int rv = -1; + + if (snprintf(oldns, PATH_MAX, "/proc/self/ns/mnt") >= PATH_MAX) + return rv; + + if (asprintf(&newns, "/proc/%d/ns/mnt", nsi->pid) == -1) + return rv; + + if (stat(oldns, &old_stat) < 0) + goto out; + + if (stat(newns, &new_stat) < 0) + goto out; + + /* Check if the mount namespaces differ, if so then indicate that we + * want to switch as part of looking up dso/map data. + */ + if (old_stat.st_ino != new_stat.st_ino) { + nsi->need_setns = true; + nsi->mntns_path = newns; + newns = NULL; + } + + /* If we're dealing with a process that is in a different PID namespace, + * attempt to work out the innermost tgid for the process. + */ + if (snprintf(spath, PATH_MAX, "/proc/%d/status", nsi->pid) >= PATH_MAX) + goto out; + + f = fopen(spath, "r"); + if (f == NULL) + goto out; + + while (getline(&statln, &linesz, f) != -1) { + /* Use tgid if CONFIG_PID_NS is not defined. */ + if (strstr(statln, "Tgid:") != NULL) { + nsi->tgid = (pid_t)strtol(strrchr(statln, '\t'), + NULL, 10); + nsi->nstgid = nsi->tgid; + } + + if (strstr(statln, "NStgid:") != NULL) { + nsi->nstgid = (pid_t)strtol(strrchr(statln, '\t'), + NULL, 10); + break; + } + } + rv = 0; + +out: + if (f != NULL) + (void) fclose(f); + free(statln); + free(newns); + return rv; +} + +struct nsinfo *nsinfo__new(pid_t pid) +{ + struct nsinfo *nsi; + + if (pid == 0) + return NULL; + + nsi = calloc(1, sizeof(*nsi)); + if (nsi != NULL) { + nsi->pid = pid; + nsi->tgid = pid; + nsi->nstgid = pid; + nsi->need_setns = false; + /* Init may fail if the process exits while we're trying to look + * at its proc information. In that case, save the pid but + * don't try to enter the namespace. + */ + if (nsinfo__init(nsi) == -1) + nsi->need_setns = false; + + refcount_set(&nsi->refcnt, 1); + } + + return nsi; +} + +struct nsinfo *nsinfo__copy(struct nsinfo *nsi) +{ + struct nsinfo *nnsi; + + nnsi = calloc(1, sizeof(*nnsi)); + if (nnsi != NULL) { + nnsi->pid = nsi->pid; + nnsi->tgid = nsi->tgid; + nnsi->nstgid = nsi->nstgid; + nnsi->need_setns = nsi->need_setns; + if (nsi->mntns_path) { + nnsi->mntns_path = strdup(nsi->mntns_path); + if (!nnsi->mntns_path) { + free(nnsi); + return NULL; + } + } + refcount_set(&nnsi->refcnt, 1); + } + + return nnsi; +} + +void nsinfo__delete(struct nsinfo *nsi) +{ + zfree(&nsi->mntns_path); + free(nsi); +} + +struct nsinfo *nsinfo__get(struct nsinfo *nsi) +{ + if (nsi) + refcount_inc(&nsi->refcnt); + return nsi; +} + +void nsinfo__put(struct nsinfo *nsi) +{ + if (nsi && refcount_dec_and_test(&nsi->refcnt)) + nsinfo__delete(nsi); +} + +void nsinfo__mountns_enter(struct nsinfo *nsi, + struct nscookie *nc) +{ + char curpath[PATH_MAX]; + int oldns = -1; + int newns = -1; + + if (nc == NULL) + return; + + nc->oldns = -1; + nc->newns = -1; + + if (!nsi || !nsi->need_setns) + return; + + if (snprintf(curpath, PATH_MAX, "/proc/self/ns/mnt") >= PATH_MAX) + return; + + oldns = open(curpath, O_RDONLY); + if (oldns < 0) + return; + + newns = open(nsi->mntns_path, O_RDONLY); + if (newns < 0) + goto errout; + + if (setns(newns, CLONE_NEWNS) < 0) + goto errout; + + nc->oldns = oldns; + nc->newns = newns; + return; + +errout: + if (oldns > -1) + close(oldns); + if (newns > -1) + close(newns); +} + +void nsinfo__mountns_exit(struct nscookie *nc) +{ + if (nc == NULL || nc->oldns == -1 || nc->newns == -1) + return; + + setns(nc->oldns, CLONE_NEWNS); + + if (nc->oldns > -1) { + close(nc->oldns); + nc->oldns = -1; + } + + if (nc->newns > -1) { + close(nc->newns); + nc->newns = -1; + } +} + +char *nsinfo__realpath(const char *path, struct nsinfo *nsi) +{ + char *rpath; + struct nscookie nsc; + + nsinfo__mountns_enter(nsi, &nsc); + rpath = realpath(path, NULL); + nsinfo__mountns_exit(&nsc); + + return rpath; +} diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h index 468f1e9a1484..05d82601c9a6 100644 --- a/tools/perf/util/namespaces.h +++ b/tools/perf/util/namespaces.h @@ -11,6 +11,7 @@ #include "../perf.h" #include <linux/list.h> +#include <linux/refcount.h> struct namespaces_event; @@ -23,4 +24,41 @@ struct namespaces { struct namespaces *namespaces__new(struct namespaces_event *event); void namespaces__free(struct namespaces *namespaces); +struct nsinfo { + pid_t pid; + pid_t tgid; + pid_t nstgid; + bool need_setns; + char *mntns_path; + refcount_t refcnt; +}; + +struct nscookie { + int oldns; + int newns; +}; + +int nsinfo__init(struct nsinfo *nsi); +struct nsinfo *nsinfo__new(pid_t pid); +struct nsinfo *nsinfo__copy(struct nsinfo *nsi); +void nsinfo__delete(struct nsinfo *nsi); + +struct nsinfo *nsinfo__get(struct nsinfo *nsi); +void nsinfo__put(struct nsinfo *nsi); + +void nsinfo__mountns_enter(struct nsinfo *nsi, struct nscookie *nc); +void nsinfo__mountns_exit(struct nscookie *nc); + +char *nsinfo__realpath(const char *path, struct nsinfo *nsi); + +static inline void __nsinfo__zput(struct nsinfo **nsip) +{ + if (nsip) { + nsinfo__put(*nsip); + *nsip = NULL; + } +} + +#define nsinfo__zput(nsi) __nsinfo__zput(&nsi) + #endif /* __PERF_NAMESPACES_H */ diff --git a/tools/perf/util/parse-branch-options.c b/tools/perf/util/parse-branch-options.c index 38fd11504015..e71fb5f31e84 100644 --- a/tools/perf/util/parse-branch-options.c +++ b/tools/perf/util/parse-branch-options.c @@ -28,6 +28,7 @@ static const struct branch_mode branch_modes[] = { BRANCH_OPT("cond", PERF_SAMPLE_BRANCH_COND), BRANCH_OPT("ind_jmp", PERF_SAMPLE_BRANCH_IND_JUMP), BRANCH_OPT("call", PERF_SAMPLE_BRANCH_CALL), + BRANCH_OPT("save_type", PERF_SAMPLE_BRANCH_TYPE_SAVE), BRANCH_END }; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 01e779b91c8e..f6257fb4f08c 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -34,7 +34,7 @@ #ifdef PARSER_DEBUG extern int parse_events_debug; #endif -int parse_events_parse(void *data, void *scanner); +int parse_events_parse(void *parse_state, void *scanner); static int get_config_terms(struct list_head *head_config, struct list_head *head_terms __maybe_unused); @@ -310,7 +310,7 @@ static struct perf_evsel * __add_event(struct list_head *list, int *idx, struct perf_event_attr *attr, char *name, struct cpu_map *cpus, - struct list_head *config_terms) + struct list_head *config_terms, bool auto_merge_stats) { struct perf_evsel *evsel; @@ -324,6 +324,7 @@ __add_event(struct list_head *list, int *idx, evsel->cpus = cpu_map__get(cpus); evsel->own_cpus = cpu_map__get(cpus); evsel->system_wide = !!cpus; + evsel->auto_merge_stats = auto_merge_stats; if (name) evsel->name = strdup(name); @@ -339,7 +340,7 @@ static int add_event(struct list_head *list, int *idx, struct perf_event_attr *attr, char *name, struct list_head *config_terms) { - return __add_event(list, idx, attr, name, NULL, config_terms) ? 0 : -ENOMEM; + return __add_event(list, idx, attr, name, NULL, config_terms, false) ? 0 : -ENOMEM; } static int parse_aliases(char *str, const char *names[][PERF_EVSEL__MAX_ALIASES], int size) @@ -589,7 +590,7 @@ static int add_tracepoint_multi_sys(struct list_head *list, int *idx, } struct __add_bpf_event_param { - struct parse_events_evlist *data; + struct parse_events_state *parse_state; struct list_head *list; struct list_head *head_config; }; @@ -599,7 +600,7 @@ static int add_bpf_event(const char *group, const char *event, int fd, { LIST_HEAD(new_evsels); struct __add_bpf_event_param *param = _param; - struct parse_events_evlist *evlist = param->data; + struct parse_events_state *parse_state = param->parse_state; struct list_head *list = param->list; struct perf_evsel *pos; int err; @@ -607,8 +608,8 @@ static int add_bpf_event(const char *group, const char *event, int fd, pr_debug("add bpf event %s:%s and attach bpf program %d\n", group, event, fd); - err = parse_events_add_tracepoint(&new_evsels, &evlist->idx, group, - event, evlist->error, + err = parse_events_add_tracepoint(&new_evsels, &parse_state->idx, group, + event, parse_state->error, param->head_config); if (err) { struct perf_evsel *evsel, *tmp; @@ -632,14 +633,14 @@ static int add_bpf_event(const char *group, const char *event, int fd, return 0; } -int parse_events_load_bpf_obj(struct parse_events_evlist *data, +int parse_events_load_bpf_obj(struct parse_events_state *parse_state, struct list_head *list, struct bpf_object *obj, struct list_head *head_config) { int err; char errbuf[BUFSIZ]; - struct __add_bpf_event_param param = {data, list, head_config}; + struct __add_bpf_event_param param = {parse_state, list, head_config}; static bool registered_unprobe_atexit = false; if (IS_ERR(obj) || !obj) { @@ -680,13 +681,13 @@ int parse_events_load_bpf_obj(struct parse_events_evlist *data, return 0; errout: - data->error->help = strdup("(add -v to see detail)"); - data->error->str = strdup(errbuf); + parse_state->error->help = strdup("(add -v to see detail)"); + parse_state->error->str = strdup(errbuf); return err; } static int -parse_events_config_bpf(struct parse_events_evlist *data, +parse_events_config_bpf(struct parse_events_state *parse_state, struct bpf_object *obj, struct list_head *head_config) { @@ -705,28 +706,28 @@ parse_events_config_bpf(struct parse_events_evlist *data, "Invalid config term for BPF object"); errbuf[BUFSIZ - 1] = '\0'; - data->error->idx = term->err_term; - data->error->str = strdup(errbuf); + parse_state->error->idx = term->err_term; + parse_state->error->str = strdup(errbuf); return -EINVAL; } - err = bpf__config_obj(obj, term, data->evlist, &error_pos); + err = bpf__config_obj(obj, term, parse_state->evlist, &error_pos); if (err) { - bpf__strerror_config_obj(obj, term, data->evlist, + bpf__strerror_config_obj(obj, term, parse_state->evlist, &error_pos, err, errbuf, sizeof(errbuf)); - data->error->help = strdup( + parse_state->error->help = strdup( "Hint:\tValid config terms:\n" " \tmap:[<arraymap>].value<indices>=[value]\n" " \tmap:[<eventmap>].event<indices>=[event]\n" "\n" " \twhere <indices> is something like [0,3...5] or [all]\n" " \t(add -v to see detail)"); - data->error->str = strdup(errbuf); + parse_state->error->str = strdup(errbuf); if (err == -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE) - data->error->idx = term->err_val; + parse_state->error->idx = term->err_val; else - data->error->idx = term->err_term + error_pos; + parse_state->error->idx = term->err_term + error_pos; return err; } } @@ -762,7 +763,7 @@ split_bpf_config_terms(struct list_head *evt_head_config, list_move_tail(&term->list, obj_head_config); } -int parse_events_load_bpf(struct parse_events_evlist *data, +int parse_events_load_bpf(struct parse_events_state *parse_state, struct list_head *list, char *bpf_file_name, bool source, @@ -790,15 +791,15 @@ int parse_events_load_bpf(struct parse_events_evlist *data, -err, errbuf, sizeof(errbuf)); - data->error->help = strdup("(add -v to see detail)"); - data->error->str = strdup(errbuf); + parse_state->error->help = strdup("(add -v to see detail)"); + parse_state->error->str = strdup(errbuf); return err; } - err = parse_events_load_bpf_obj(data, list, obj, head_config); + err = parse_events_load_bpf_obj(parse_state, list, obj, head_config); if (err) return err; - err = parse_events_config_bpf(data, obj, &obj_head_config); + err = parse_events_config_bpf(parse_state, obj, &obj_head_config); /* * Caller doesn't know anything about obj_head_config, @@ -1184,7 +1185,7 @@ int parse_events_add_tracepoint(struct list_head *list, int *idx, err, head_config); } -int parse_events_add_numeric(struct parse_events_evlist *data, +int parse_events_add_numeric(struct parse_events_state *parse_state, struct list_head *list, u32 type, u64 config, struct list_head *head_config) @@ -1197,7 +1198,7 @@ int parse_events_add_numeric(struct parse_events_evlist *data, attr.config = config; if (head_config) { - if (config_attr(&attr, head_config, data->error, + if (config_attr(&attr, head_config, parse_state->error, config_term_common)) return -EINVAL; @@ -1205,13 +1206,13 @@ int parse_events_add_numeric(struct parse_events_evlist *data, return -ENOMEM; } - return add_event(list, &data->idx, &attr, + return add_event(list, &parse_state->idx, &attr, get_config_name(head_config), &config_terms); } -int parse_events_add_pmu(struct parse_events_evlist *data, +static int __parse_events_add_pmu(struct parse_events_state *parse_state, struct list_head *list, char *name, - struct list_head *head_config) + struct list_head *head_config, bool auto_merge_stats) { struct perf_event_attr attr; struct perf_pmu_info info; @@ -1232,7 +1233,7 @@ int parse_events_add_pmu(struct parse_events_evlist *data, if (!head_config) { attr.type = pmu->type; - evsel = __add_event(list, &data->idx, &attr, NULL, pmu->cpus, NULL); + evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu->cpus, NULL, auto_merge_stats); return evsel ? 0 : -ENOMEM; } @@ -1243,18 +1244,18 @@ int parse_events_add_pmu(struct parse_events_evlist *data, * Configure hardcoded terms first, no need to check * return value when called with fail == 0 ;) */ - if (config_attr(&attr, head_config, data->error, config_term_pmu)) + if (config_attr(&attr, head_config, parse_state->error, config_term_pmu)) return -EINVAL; if (get_config_terms(head_config, &config_terms)) return -ENOMEM; - if (perf_pmu__config(pmu, &attr, head_config, data->error)) + if (perf_pmu__config(pmu, &attr, head_config, parse_state->error)) return -EINVAL; - evsel = __add_event(list, &data->idx, &attr, + evsel = __add_event(list, &parse_state->idx, &attr, get_config_name(head_config), pmu->cpus, - &config_terms); + &config_terms, auto_merge_stats); if (evsel) { evsel->unit = info.unit; evsel->scale = info.scale; @@ -1267,7 +1268,14 @@ int parse_events_add_pmu(struct parse_events_evlist *data, return evsel ? 0 : -ENOMEM; } -int parse_events_multi_pmu_add(struct parse_events_evlist *data, +int parse_events_add_pmu(struct parse_events_state *parse_state, + struct list_head *list, char *name, + struct list_head *head_config) +{ + return __parse_events_add_pmu(parse_state, list, name, head_config, false); +} + +int parse_events_multi_pmu_add(struct parse_events_state *parse_state, char *str, struct list_head **listp) { struct list_head *head; @@ -1296,8 +1304,8 @@ int parse_events_multi_pmu_add(struct parse_events_evlist *data, return -1; list_add_tail(&term->list, head); - if (!parse_events_add_pmu(data, list, - pmu->name, head)) { + if (!__parse_events_add_pmu(parse_state, list, + pmu->name, head, true)) { pr_debug("%s -> %s/%s/\n", str, pmu->name, alias->str); ok++; @@ -1628,7 +1636,7 @@ perf_pmu__parse_check(const char *name) return r ? r->type : PMU_EVENT_SYMBOL_ERR; } -static int parse_events__scanner(const char *str, void *data, int start_token) +static int parse_events__scanner(const char *str, void *parse_state, int start_token) { YY_BUFFER_STATE buffer; void *scanner; @@ -1643,7 +1651,7 @@ static int parse_events__scanner(const char *str, void *data, int start_token) #ifdef PARSER_DEBUG parse_events_debug = 1; #endif - ret = parse_events_parse(data, scanner); + ret = parse_events_parse(parse_state, scanner); parse_events__flush_buffer(buffer, scanner); parse_events__delete_buffer(buffer, scanner); @@ -1656,45 +1664,45 @@ static int parse_events__scanner(const char *str, void *data, int start_token) */ int parse_events_terms(struct list_head *terms, const char *str) { - struct parse_events_terms data = { + struct parse_events_state parse_state = { .terms = NULL, }; int ret; - ret = parse_events__scanner(str, &data, PE_START_TERMS); + ret = parse_events__scanner(str, &parse_state, PE_START_TERMS); if (!ret) { - list_splice(data.terms, terms); - zfree(&data.terms); + list_splice(parse_state.terms, terms); + zfree(&parse_state.terms); return 0; } - parse_events_terms__delete(data.terms); + parse_events_terms__delete(parse_state.terms); return ret; } int parse_events(struct perf_evlist *evlist, const char *str, struct parse_events_error *err) { - struct parse_events_evlist data = { - .list = LIST_HEAD_INIT(data.list), + struct parse_events_state parse_state = { + .list = LIST_HEAD_INIT(parse_state.list), .idx = evlist->nr_entries, .error = err, .evlist = evlist, }; int ret; - ret = parse_events__scanner(str, &data, PE_START_EVENTS); + ret = parse_events__scanner(str, &parse_state, PE_START_EVENTS); perf_pmu__parse_cleanup(); if (!ret) { struct perf_evsel *last; - if (list_empty(&data.list)) { + if (list_empty(&parse_state.list)) { WARN_ONCE(true, "WARNING: event parser found nothing"); return -1; } - perf_evlist__splice_list_tail(evlist, &data.list); - evlist->nr_groups += data.nr_groups; + perf_evlist__splice_list_tail(evlist, &parse_state.list); + evlist->nr_groups += parse_state.nr_groups; last = perf_evlist__last(evlist); last->cmdline_group_boundary = true; @@ -2124,7 +2132,7 @@ void print_sdt_events(const char *subsys_glob, const char *event_glob, return; } strlist__for_each_entry(nd, bidlist) { - pcache = probe_cache__new(nd->s); + pcache = probe_cache__new(nd->s, NULL); if (!pcache) continue; list_for_each_entry(ent, &pcache->entries, node) { @@ -2520,10 +2528,10 @@ void parse_events__clear_array(struct parse_events_array *a) zfree(&a->ranges); } -void parse_events_evlist_error(struct parse_events_evlist *data, +void parse_events_evlist_error(struct parse_events_state *parse_state, int idx, const char *str) { - struct parse_events_error *err = data->error; + struct parse_events_error *err = parse_state->error; if (!err) return; diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index a235f4d6d5e5..635135125111 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -108,16 +108,13 @@ struct parse_events_error { char *help; /* optional help string */ }; -struct parse_events_evlist { +struct parse_events_state { struct list_head list; int idx; int nr_groups; struct parse_events_error *error; struct perf_evlist *evlist; -}; - -struct parse_events_terms { - struct list_head *terms; + struct list_head *terms; }; void parse_events__shrink_config_terms(void); @@ -143,18 +140,18 @@ int parse_events_add_tracepoint(struct list_head *list, int *idx, const char *sys, const char *event, struct parse_events_error *error, struct list_head *head_config); -int parse_events_load_bpf(struct parse_events_evlist *data, +int parse_events_load_bpf(struct parse_events_state *parse_state, struct list_head *list, char *bpf_file_name, bool source, struct list_head *head_config); /* Provide this function for perf test */ struct bpf_object; -int parse_events_load_bpf_obj(struct parse_events_evlist *data, +int parse_events_load_bpf_obj(struct parse_events_state *parse_state, struct list_head *list, struct bpf_object *obj, struct list_head *head_config); -int parse_events_add_numeric(struct parse_events_evlist *data, +int parse_events_add_numeric(struct parse_events_state *parse_state, struct list_head *list, u32 type, u64 config, struct list_head *head_config); @@ -164,11 +161,11 @@ int parse_events_add_cache(struct list_head *list, int *idx, struct list_head *head_config); int parse_events_add_breakpoint(struct list_head *list, int *idx, void *ptr, char *type, u64 len); -int parse_events_add_pmu(struct parse_events_evlist *data, +int parse_events_add_pmu(struct parse_events_state *parse_state, struct list_head *list, char *name, struct list_head *head_config); -int parse_events_multi_pmu_add(struct parse_events_evlist *data, +int parse_events_multi_pmu_add(struct parse_events_state *parse_state, char *str, struct list_head **listp); @@ -180,7 +177,7 @@ perf_pmu__parse_check(const char *name); void parse_events__set_leader(char *name, struct list_head *list); void parse_events_update_lists(struct list_head *list_event, struct list_head *list_all); -void parse_events_evlist_error(struct parse_events_evlist *data, +void parse_events_evlist_error(struct parse_events_state *parse_state, int idx, const char *str); void print_events(const char *event_glob, bool name_only, bool quiet, diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index 660fca05bc93..c42edeac451f 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -53,6 +53,21 @@ static int str(yyscan_t scanner, int token) return token; } +static bool isbpf(yyscan_t scanner) +{ + char *text = parse_events_get_text(scanner); + int len = strlen(text); + + if (len < 2) + return false; + if ((text[len - 1] == 'c' || text[len - 1] == 'o') && + text[len - 2] == '.') + return true; + if (len > 4 && !strcmp(text + len - 4, ".obj")) + return true; + return false; +} + /* * This function is called when the parser gets two kind of input: * @@ -136,8 +151,8 @@ do { \ group [^,{}/]*[{][^}]*[}][^,{}/]* event_pmu [^,{}/]+[/][^/]*[/][^,{}/]* event [^,{}/]+ -bpf_object [^,{}]+\.(o|bpf) -bpf_source [^,{}]+\.c +bpf_object [^,{}]+\.(o|bpf)[a-zA-Z0-9._]* +bpf_source [^,{}]+\.c[a-zA-Z0-9._]* num_dec [0-9]+ num_hex 0x[a-fA-F0-9]+ @@ -307,8 +322,8 @@ r{num_raw_hex} { return raw(yyscanner); } {num_hex} { return value(yyscanner, 16); } {modifier_event} { return str(yyscanner, PE_MODIFIER_EVENT); } -{bpf_object} { return str(yyscanner, PE_BPF_OBJECT); } -{bpf_source} { return str(yyscanner, PE_BPF_SOURCE); } +{bpf_object} { if (!isbpf(yyscanner)) REJECT; return str(yyscanner, PE_BPF_OBJECT); } +{bpf_source} { if (!isbpf(yyscanner)) REJECT; return str(yyscanner, PE_BPF_SOURCE); } {name} { return pmu_str_check(yyscanner); } "/" { BEGIN(config); return '/'; } - { return '-'; } diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index 04fd8c9af9f9..e81a20ea8d7d 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -1,5 +1,5 @@ %pure-parser -%parse-param {void *_data} +%parse-param {void *_parse_state} %parse-param {void *scanner} %lex-param {void* scanner} %locations @@ -17,7 +17,7 @@ #include "parse-events.h" #include "parse-events-bison.h" -void parse_events_error(YYLTYPE *loc, void *data, void *scanner, char const *msg); +void parse_events_error(YYLTYPE *loc, void *parse_state, void *scanner, char const *msg); #define ABORT_ON(val) \ do { \ @@ -33,11 +33,11 @@ do { \ } while (0) static void inc_group_count(struct list_head *list, - struct parse_events_evlist *data) + struct parse_events_state *parse_state) { /* Count groups only have more than 1 members */ if (!list_is_last(list->next, list)) - data->nr_groups++; + parse_state->nr_groups++; } %} @@ -115,9 +115,9 @@ PE_START_TERMS start_terms start_events: groups { - struct parse_events_evlist *data = _data; + struct parse_events_state *parse_state = _parse_state; - parse_events_update_lists($1, &data->list); + parse_events_update_lists($1, &parse_state->list); } groups: @@ -159,7 +159,7 @@ PE_NAME '{' events '}' { struct list_head *list = $3; - inc_group_count(list, _data); + inc_group_count(list, _parse_state); parse_events__set_leader($1, list); $$ = list; } @@ -168,7 +168,7 @@ PE_NAME '{' events '}' { struct list_head *list = $2; - inc_group_count(list, _data); + inc_group_count(list, _parse_state); parse_events__set_leader(NULL, list); $$ = list; } @@ -225,14 +225,13 @@ event_def: event_pmu | event_pmu: PE_NAME opt_event_config { - struct parse_events_evlist *data = _data; struct list_head *list, *orig_terms, *terms; if (parse_events_copy_term_list($2, &orig_terms)) YYABORT; ALLOC_LIST(list); - if (parse_events_add_pmu(data, list, $1, $2)) { + if (parse_events_add_pmu(_parse_state, list, $1, $2)) { struct perf_pmu *pmu = NULL; int ok = 0; @@ -245,7 +244,7 @@ PE_NAME opt_event_config if (!strncmp($1, name, strlen($1))) { if (parse_events_copy_term_list(orig_terms, &terms)) YYABORT; - if (!parse_events_add_pmu(data, list, pmu->name, terms)) + if (!parse_events_add_pmu(_parse_state, list, pmu->name, terms)) ok++; parse_events_terms__delete(terms); } @@ -262,7 +261,7 @@ PE_KERNEL_PMU_EVENT sep_dc { struct list_head *list; - if (parse_events_multi_pmu_add(_data, $1, &list) < 0) + if (parse_events_multi_pmu_add(_parse_state, $1, &list) < 0) YYABORT; $$ = list; } @@ -273,7 +272,7 @@ PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc char pmu_name[128]; snprintf(&pmu_name, 128, "%s-%s", $1, $3); - if (parse_events_multi_pmu_add(_data, pmu_name, &list) < 0) + if (parse_events_multi_pmu_add(_parse_state, pmu_name, &list) < 0) YYABORT; $$ = list; } @@ -286,62 +285,60 @@ PE_VALUE_SYM_SW event_legacy_symbol: value_sym '/' event_config '/' { - struct parse_events_evlist *data = _data; struct list_head *list; int type = $1 >> 16; int config = $1 & 255; ALLOC_LIST(list); - ABORT_ON(parse_events_add_numeric(data, list, type, config, $3)); + ABORT_ON(parse_events_add_numeric(_parse_state, list, type, config, $3)); parse_events_terms__delete($3); $$ = list; } | value_sym sep_slash_dc { - struct parse_events_evlist *data = _data; struct list_head *list; int type = $1 >> 16; int config = $1 & 255; ALLOC_LIST(list); - ABORT_ON(parse_events_add_numeric(data, list, type, config, NULL)); + ABORT_ON(parse_events_add_numeric(_parse_state, list, type, config, NULL)); $$ = list; } event_legacy_cache: PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT opt_event_config { - struct parse_events_evlist *data = _data; - struct parse_events_error *error = data->error; + struct parse_events_state *parse_state = _parse_state; + struct parse_events_error *error = parse_state->error; struct list_head *list; ALLOC_LIST(list); - ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, $5, error, $6)); + ABORT_ON(parse_events_add_cache(list, &parse_state->idx, $1, $3, $5, error, $6)); parse_events_terms__delete($6); $$ = list; } | PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT opt_event_config { - struct parse_events_evlist *data = _data; - struct parse_events_error *error = data->error; + struct parse_events_state *parse_state = _parse_state; + struct parse_events_error *error = parse_state->error; struct list_head *list; ALLOC_LIST(list); - ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, NULL, error, $4)); + ABORT_ON(parse_events_add_cache(list, &parse_state->idx, $1, $3, NULL, error, $4)); parse_events_terms__delete($4); $$ = list; } | PE_NAME_CACHE_TYPE opt_event_config { - struct parse_events_evlist *data = _data; - struct parse_events_error *error = data->error; + struct parse_events_state *parse_state = _parse_state; + struct parse_events_error *error = parse_state->error; struct list_head *list; ALLOC_LIST(list); - ABORT_ON(parse_events_add_cache(list, &data->idx, $1, NULL, NULL, error, $2)); + ABORT_ON(parse_events_add_cache(list, &parse_state->idx, $1, NULL, NULL, error, $2)); parse_events_terms__delete($2); $$ = list; } @@ -349,44 +346,44 @@ PE_NAME_CACHE_TYPE opt_event_config event_legacy_mem: PE_PREFIX_MEM PE_VALUE '/' PE_VALUE ':' PE_MODIFIER_BP sep_dc { - struct parse_events_evlist *data = _data; + struct parse_events_state *parse_state = _parse_state; struct list_head *list; ALLOC_LIST(list); - ABORT_ON(parse_events_add_breakpoint(list, &data->idx, + ABORT_ON(parse_events_add_breakpoint(list, &parse_state->idx, (void *) $2, $6, $4)); $$ = list; } | PE_PREFIX_MEM PE_VALUE '/' PE_VALUE sep_dc { - struct parse_events_evlist *data = _data; + struct parse_events_state *parse_state = _parse_state; struct list_head *list; ALLOC_LIST(list); - ABORT_ON(parse_events_add_breakpoint(list, &data->idx, + ABORT_ON(parse_events_add_breakpoint(list, &parse_state->idx, (void *) $2, NULL, $4)); $$ = list; } | PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc { - struct parse_events_evlist *data = _data; + struct parse_events_state *parse_state = _parse_state; struct list_head *list; ALLOC_LIST(list); - ABORT_ON(parse_events_add_breakpoint(list, &data->idx, + ABORT_ON(parse_events_add_breakpoint(list, &parse_state->idx, (void *) $2, $4, 0)); $$ = list; } | PE_PREFIX_MEM PE_VALUE sep_dc { - struct parse_events_evlist *data = _data; + struct parse_events_state *parse_state = _parse_state; struct list_head *list; ALLOC_LIST(list); - ABORT_ON(parse_events_add_breakpoint(list, &data->idx, + ABORT_ON(parse_events_add_breakpoint(list, &parse_state->idx, (void *) $2, NULL, 0)); $$ = list; } @@ -394,15 +391,15 @@ PE_PREFIX_MEM PE_VALUE sep_dc event_legacy_tracepoint: tracepoint_name opt_event_config { - struct parse_events_evlist *data = _data; - struct parse_events_error *error = data->error; + struct parse_events_state *parse_state = _parse_state; + struct parse_events_error *error = parse_state->error; struct list_head *list; ALLOC_LIST(list); if (error) error->idx = @1.first_column; - if (parse_events_add_tracepoint(list, &data->idx, $1.sys, $1.event, + if (parse_events_add_tracepoint(list, &parse_state->idx, $1.sys, $1.event, error, $2)) return -1; @@ -432,11 +429,10 @@ PE_NAME ':' PE_NAME event_legacy_numeric: PE_VALUE ':' PE_VALUE opt_event_config { - struct parse_events_evlist *data = _data; struct list_head *list; ALLOC_LIST(list); - ABORT_ON(parse_events_add_numeric(data, list, (u32)$1, $3, $4)); + ABORT_ON(parse_events_add_numeric(_parse_state, list, (u32)$1, $3, $4)); parse_events_terms__delete($4); $$ = list; } @@ -444,11 +440,10 @@ PE_VALUE ':' PE_VALUE opt_event_config event_legacy_raw: PE_RAW opt_event_config { - struct parse_events_evlist *data = _data; struct list_head *list; ALLOC_LIST(list); - ABORT_ON(parse_events_add_numeric(data, list, PERF_TYPE_RAW, $1, $2)); + ABORT_ON(parse_events_add_numeric(_parse_state, list, PERF_TYPE_RAW, $1, $2)); parse_events_terms__delete($2); $$ = list; } @@ -456,23 +451,22 @@ PE_RAW opt_event_config event_bpf_file: PE_BPF_OBJECT opt_event_config { - struct parse_events_evlist *data = _data; - struct parse_events_error *error = data->error; + struct parse_events_state *parse_state = _parse_state; + struct parse_events_error *error = parse_state->error; struct list_head *list; ALLOC_LIST(list); - ABORT_ON(parse_events_load_bpf(data, list, $1, false, $2)); + ABORT_ON(parse_events_load_bpf(parse_state, list, $1, false, $2)); parse_events_terms__delete($2); $$ = list; } | PE_BPF_SOURCE opt_event_config { - struct parse_events_evlist *data = _data; struct list_head *list; ALLOC_LIST(list); - ABORT_ON(parse_events_load_bpf(data, list, $1, true, $2)); + ABORT_ON(parse_events_load_bpf(_parse_state, list, $1, true, $2)); parse_events_terms__delete($2); $$ = list; } @@ -494,8 +488,8 @@ opt_event_config: start_terms: event_config { - struct parse_events_terms *data = _data; - data->terms = $1; + struct parse_events_state *parse_state = _parse_state; + parse_state->terms = $1; } event_config: @@ -685,9 +679,9 @@ sep_slash_dc: '/' | ':' | %% -void parse_events_error(YYLTYPE *loc, void *data, +void parse_events_error(YYLTYPE *loc, void *parse_state, void *scanner __maybe_unused, char const *msg __maybe_unused) { - parse_events_evlist_error(data, loc->last_column, "parser error"); + parse_events_evlist_error(parse_state, loc->last_column, "parser error"); } diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index ea7f450dc609..389e9729331f 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -2,6 +2,7 @@ #define __PMU_H #include <linux/bitmap.h> +#include <linux/compiler.h> #include <linux/perf_event.h> #include <stdbool.h> #include "evsel.h" @@ -83,8 +84,7 @@ void print_pmu_events(const char *event_glob, bool name_only, bool quiet, bool long_desc, bool details_flag); bool pmu_have_event(const char *pname, const char *name); -int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt, - ...) __attribute__((format(scanf, 3, 4))); +int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt, ...) __scanf(3, 4); int perf_pmu__test(void); diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index a2670e9d652d..b7aaf9b2294d 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -184,13 +184,19 @@ static struct map *kernel_get_module_map(const char *module) return NULL; } -struct map *get_target_map(const char *target, bool user) +struct map *get_target_map(const char *target, struct nsinfo *nsi, bool user) { /* Init maps of given executable or kernel */ - if (user) - return dso__new_map(target); - else + if (user) { + struct map *map; + + map = dso__new_map(target); + if (map && map->dso) + map->dso->nsinfo = nsinfo__get(nsi); + return map; + } else { return kernel_get_module_map(target); + } } static int convert_exec_to_group(const char *exec, char **result) @@ -366,7 +372,8 @@ found: static int find_alternative_probe_point(struct debuginfo *dinfo, struct perf_probe_point *pp, struct perf_probe_point *result, - const char *target, bool uprobes) + const char *target, struct nsinfo *nsi, + bool uprobes) { struct map *map = NULL; struct symbol *sym; @@ -377,7 +384,7 @@ static int find_alternative_probe_point(struct debuginfo *dinfo, if (!pp->function || pp->file) return -ENOTSUP; - map = get_target_map(target, uprobes); + map = get_target_map(target, nsi, uprobes); if (!map) return -EINVAL; @@ -421,8 +428,8 @@ static int get_alternative_probe_event(struct debuginfo *dinfo, memcpy(tmp, &pev->point, sizeof(*tmp)); memset(&pev->point, 0, sizeof(pev->point)); - ret = find_alternative_probe_point(dinfo, tmp, &pev->point, - pev->target, pev->uprobes); + ret = find_alternative_probe_point(dinfo, tmp, &pev->point, pev->target, + pev->nsi, pev->uprobes); if (ret < 0) memcpy(&pev->point, tmp, sizeof(*tmp)); @@ -444,7 +451,7 @@ static int get_alternative_line_range(struct debuginfo *dinfo, if (lr->end != INT_MAX) len = lr->end - lr->start; ret = find_alternative_probe_point(dinfo, &pp, &result, - target, user); + target, NULL, user); if (!ret) { lr->function = result.function; lr->file = result.file; @@ -457,12 +464,14 @@ static int get_alternative_line_range(struct debuginfo *dinfo, } /* Open new debuginfo of given module */ -static struct debuginfo *open_debuginfo(const char *module, bool silent) +static struct debuginfo *open_debuginfo(const char *module, struct nsinfo *nsi, + bool silent) { const char *path = module; char reason[STRERR_BUFSIZE]; struct debuginfo *ret = NULL; struct dso *dso = NULL; + struct nscookie nsc; int err; if (!module || !strchr(module, '/')) { @@ -480,6 +489,7 @@ static struct debuginfo *open_debuginfo(const char *module, bool silent) } path = dso->long_name; } + nsinfo__mountns_enter(nsi, &nsc); ret = debuginfo__new(path); if (!ret && !silent) { pr_warning("The %s file has no debug information.\n", path); @@ -489,6 +499,7 @@ static struct debuginfo *open_debuginfo(const char *module, bool silent) pr_warning("Rebuild with -g, "); pr_warning("or install an appropriate debuginfo package.\n"); } + nsinfo__mountns_exit(&nsc); return ret; } @@ -516,7 +527,7 @@ static struct debuginfo *debuginfo_cache__open(const char *module, bool silent) goto out; } - debuginfo_cache = open_debuginfo(module, silent); + debuginfo_cache = open_debuginfo(module, NULL, silent); if (!debuginfo_cache) zfree(&debuginfo_cache_path); out: @@ -531,14 +542,18 @@ static void debuginfo_cache__exit(void) } -static int get_text_start_address(const char *exec, unsigned long *address) +static int get_text_start_address(const char *exec, unsigned long *address, + struct nsinfo *nsi) { Elf *elf; GElf_Ehdr ehdr; GElf_Shdr shdr; int fd, ret = -ENOENT; + struct nscookie nsc; + nsinfo__mountns_enter(nsi, &nsc); fd = open(exec, O_RDONLY); + nsinfo__mountns_exit(&nsc); if (fd < 0) return -errno; @@ -582,7 +597,7 @@ static int find_perf_probe_point_from_dwarf(struct probe_trace_point *tp, ret = -EINVAL; goto error; } - ret = get_text_start_address(tp->module, &stext); + ret = get_text_start_address(tp->module, &stext, NULL); if (ret < 0) goto error; addr += stext; @@ -659,7 +674,7 @@ post_process_offline_probe_trace_events(struct probe_trace_event *tevs, /* Prepare a map for offline binary */ map = dso__new_map(pathname); - if (!map || get_text_start_address(pathname, &stext) < 0) { + if (!map || get_text_start_address(pathname, &stext, NULL) < 0) { pr_warning("Failed to get ELF symbols for %s\n", pathname); return -EINVAL; } @@ -676,7 +691,8 @@ post_process_offline_probe_trace_events(struct probe_trace_event *tevs, } static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs, - int ntevs, const char *exec) + int ntevs, const char *exec, + struct nsinfo *nsi) { int i, ret = 0; unsigned long stext = 0; @@ -684,7 +700,7 @@ static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs, if (!exec) return 0; - ret = get_text_start_address(exec, &stext); + ret = get_text_start_address(exec, &stext, nsi); if (ret < 0) return ret; @@ -715,7 +731,7 @@ post_process_module_probe_trace_events(struct probe_trace_event *tevs, if (!module) return 0; - map = get_target_map(module, false); + map = get_target_map(module, NULL, false); if (!map || debuginfo__get_text_offset(dinfo, &text_offs, true) < 0) { pr_warning("Failed to get ELF symbols for %s\n", module); return -EINVAL; @@ -802,7 +818,8 @@ static int post_process_probe_trace_events(struct perf_probe_event *pev, int ret; if (uprobe) - ret = add_exec_to_probe_trace_events(tevs, ntevs, module); + ret = add_exec_to_probe_trace_events(tevs, ntevs, module, + pev->nsi); else if (module) /* Currently ref_reloc_sym based probe is not for drivers */ ret = post_process_module_probe_trace_events(tevs, ntevs, @@ -825,7 +842,7 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev, struct debuginfo *dinfo; int ntevs, ret = 0; - dinfo = open_debuginfo(pev->target, !need_dwarf); + dinfo = open_debuginfo(pev->target, pev->nsi, !need_dwarf); if (!dinfo) { if (need_dwarf) return -ENOENT; @@ -945,7 +962,7 @@ static int __show_line_range(struct line_range *lr, const char *module, char sbuf[STRERR_BUFSIZE]; /* Search a line range */ - dinfo = open_debuginfo(module, false); + dinfo = open_debuginfo(module, NULL, false); if (!dinfo) return -ENOENT; @@ -1021,14 +1038,18 @@ end: return ret; } -int show_line_range(struct line_range *lr, const char *module, bool user) +int show_line_range(struct line_range *lr, const char *module, + struct nsinfo *nsi, bool user) { int ret; + struct nscookie nsc; ret = init_probe_symbol_maps(user); if (ret < 0) return ret; + nsinfo__mountns_enter(nsi, &nsc); ret = __show_line_range(lr, module, user); + nsinfo__mountns_exit(&nsc); exit_probe_symbol_maps(); return ret; @@ -1111,7 +1132,7 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs, if (ret < 0) return ret; - dinfo = open_debuginfo(pevs->target, false); + dinfo = open_debuginfo(pevs->target, pevs->nsi, false); if (!dinfo) { ret = -ENOENT; goto out; @@ -1155,6 +1176,7 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev, int show_line_range(struct line_range *lr __maybe_unused, const char *module __maybe_unused, + struct nsinfo *nsi __maybe_unused, bool user __maybe_unused) { pr_warning("Debuginfo-analysis is not supported.\n"); @@ -2373,7 +2395,7 @@ kprobe_blacklist__find_by_address(struct list_head *blacklist, struct kprobe_blacklist_node *node; list_for_each_entry(node, blacklist, list) { - if (node->start <= address && address <= node->end) + if (node->start <= address && address < node->end) return node; } @@ -2703,6 +2725,7 @@ static int __add_probe_trace_events(struct perf_probe_event *pev, struct probe_trace_event *tev = NULL; struct probe_cache *cache = NULL; struct strlist *namelist[2] = {NULL, NULL}; + struct nscookie nsc; up = pev->uprobes ? 1 : 0; fd[up] = __open_probe_file_and_namelist(up, &namelist[up]); @@ -2729,7 +2752,9 @@ static int __add_probe_trace_events(struct perf_probe_event *pev, if (ret < 0) break; + nsinfo__mountns_enter(pev->nsi, &nsc); ret = probe_file__add_event(fd[up], tev); + nsinfo__mountns_exit(&nsc); if (ret < 0) break; @@ -2744,7 +2769,7 @@ static int __add_probe_trace_events(struct perf_probe_event *pev, if (ret == -EINVAL && pev->uprobes) warn_uprobe_event_compat(tev); if (ret == 0 && probe_conf.cache) { - cache = probe_cache__new(pev->target); + cache = probe_cache__new(pev->target, pev->nsi); if (!cache || probe_cache__add_entry(cache, pev, tevs, ntevs) < 0 || probe_cache__commit(cache) < 0) @@ -2805,7 +2830,7 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, int ret, i, j, skipped = 0; char *mod_name; - map = get_target_map(pev->target, pev->uprobes); + map = get_target_map(pev->target, pev->nsi, pev->uprobes); if (!map) { ret = -EINVAL; goto out; @@ -3094,7 +3119,7 @@ static int find_cached_events(struct perf_probe_event *pev, int ntevs = 0; int ret = 0; - cache = probe_cache__new(target); + cache = probe_cache__new(target, pev->nsi); /* Return 0 ("not found") if the target has no probe cache. */ if (!cache) return 0; @@ -3184,7 +3209,7 @@ static int find_probe_trace_events_from_cache(struct perf_probe_event *pev, else return find_cached_events(pev, tevs, pev->target); } - cache = probe_cache__new(pev->target); + cache = probe_cache__new(pev->target, pev->nsi); if (!cache) return 0; @@ -3345,13 +3370,16 @@ int apply_perf_probe_events(struct perf_probe_event *pevs, int npevs) void cleanup_perf_probe_events(struct perf_probe_event *pevs, int npevs) { int i, j; + struct perf_probe_event *pev; /* Loop 3: cleanup and free trace events */ for (i = 0; i < npevs; i++) { + pev = &pevs[i]; for (j = 0; j < pevs[i].ntevs; j++) clear_probe_trace_event(&pevs[i].tevs[j]); zfree(&pevs[i].tevs); pevs[i].ntevs = 0; + nsinfo__zput(pev->nsi); clear_perf_probe_event(&pevs[i]); } } @@ -3409,8 +3437,8 @@ out: return ret; } -int show_available_funcs(const char *target, struct strfilter *_filter, - bool user) +int show_available_funcs(const char *target, struct nsinfo *nsi, + struct strfilter *_filter, bool user) { struct rb_node *nd; struct map *map; @@ -3421,7 +3449,7 @@ int show_available_funcs(const char *target, struct strfilter *_filter, return ret; /* Get a symbol map */ - map = get_target_map(target, user); + map = get_target_map(target, nsi, user); if (!map) { pr_err("Failed to get a map for %s\n", (target) ? : "kernel"); return -EINVAL; diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h index 373842656fb6..078681d12168 100644 --- a/tools/perf/util/probe-event.h +++ b/tools/perf/util/probe-event.h @@ -1,8 +1,10 @@ #ifndef _PROBE_EVENT_H #define _PROBE_EVENT_H +#include <linux/compiler.h> #include <stdbool.h> #include "intlist.h" +#include "namespaces.h" /* Probe related configurations */ struct probe_conf { @@ -91,6 +93,7 @@ struct perf_probe_event { struct perf_probe_arg *args; /* Arguments */ struct probe_trace_event *tevs; int ntevs; + struct nsinfo *nsi; /* Target namespace */ }; /* Line range */ @@ -162,17 +165,18 @@ int show_perf_probe_event(const char *group, const char *event, struct perf_probe_event *pev, const char *module, bool use_stdout); int show_perf_probe_events(struct strfilter *filter); -int show_line_range(struct line_range *lr, const char *module, bool user); +int show_line_range(struct line_range *lr, const char *module, + struct nsinfo *nsi, bool user); int show_available_vars(struct perf_probe_event *pevs, int npevs, struct strfilter *filter); -int show_available_funcs(const char *module, struct strfilter *filter, bool user); +int show_available_funcs(const char *module, struct nsinfo *nsi, + struct strfilter *filter, bool user); void arch__fix_tev_from_maps(struct perf_probe_event *pev, struct probe_trace_event *tev, struct map *map, struct symbol *sym); /* If there is no space to write, returns -E2BIG. */ -int e_snprintf(char *str, size_t size, const char *format, ...) - __attribute__((format(printf, 3, 4))); +int e_snprintf(char *str, size_t size, const char *format, ...) __printf(3, 4); /* Maximum index number of event-name postfix */ #define MAX_EVENT_INDEX 1024 @@ -180,7 +184,7 @@ int e_snprintf(char *str, size_t size, const char *format, ...) int copy_to_probe_trace_arg(struct probe_trace_arg *tvar, struct perf_probe_arg *pvar); -struct map *get_target_map(const char *target, bool user); +struct map *get_target_map(const char *target, struct nsinfo *nsi, bool user); void arch__post_process_probe_trace_events(struct perf_probe_event *pev, int ntevs); diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c index d679389e627c..cdf8d83a484c 100644 --- a/tools/perf/util/probe-file.c +++ b/tools/perf/util/probe-file.c @@ -412,13 +412,15 @@ int probe_cache_entry__get_event(struct probe_cache_entry *entry, } /* For the kernel probe caches, pass target = NULL or DSO__NAME_KALLSYMS */ -static int probe_cache__open(struct probe_cache *pcache, const char *target) +static int probe_cache__open(struct probe_cache *pcache, const char *target, + struct nsinfo *nsi) { char cpath[PATH_MAX]; char sbuildid[SBUILD_ID_SIZE]; char *dir_name = NULL; bool is_kallsyms = false; int ret, fd; + struct nscookie nsc; if (target && build_id_cache__cached(target)) { /* This is a cached buildid */ @@ -431,8 +433,11 @@ static int probe_cache__open(struct probe_cache *pcache, const char *target) target = DSO__NAME_KALLSYMS; is_kallsyms = true; ret = sysfs__sprintf_build_id("/", sbuildid); - } else + } else { + nsinfo__mountns_enter(nsi, &nsc); ret = filename__sprintf_build_id(target, sbuildid); + nsinfo__mountns_exit(&nsc); + } if (ret < 0) { pr_debug("Failed to get build-id from %s.\n", target); @@ -441,7 +446,7 @@ static int probe_cache__open(struct probe_cache *pcache, const char *target) /* If we have no buildid cache, make it */ if (!build_id_cache__cached(sbuildid)) { - ret = build_id_cache__add_s(sbuildid, target, + ret = build_id_cache__add_s(sbuildid, target, nsi, is_kallsyms, NULL); if (ret < 0) { pr_debug("Failed to add build-id cache: %s\n", target); @@ -449,7 +454,7 @@ static int probe_cache__open(struct probe_cache *pcache, const char *target) } } - dir_name = build_id_cache__cachedir(sbuildid, target, is_kallsyms, + dir_name = build_id_cache__cachedir(sbuildid, target, nsi, is_kallsyms, false); found: if (!dir_name) { @@ -554,7 +559,7 @@ void probe_cache__delete(struct probe_cache *pcache) free(pcache); } -struct probe_cache *probe_cache__new(const char *target) +struct probe_cache *probe_cache__new(const char *target, struct nsinfo *nsi) { struct probe_cache *pcache = probe_cache__alloc(); int ret; @@ -562,7 +567,7 @@ struct probe_cache *probe_cache__new(const char *target) if (!pcache) return NULL; - ret = probe_cache__open(pcache, target); + ret = probe_cache__open(pcache, target, nsi); if (ret < 0) { pr_debug("Cache open error: %d\n", ret); goto out_err; @@ -974,7 +979,7 @@ int probe_cache__show_all_caches(struct strfilter *filter) return -EINVAL; } strlist__for_each_entry(nd, bidlist) { - pcache = probe_cache__new(nd->s); + pcache = probe_cache__new(nd->s, NULL); if (!pcache) continue; if (!list_empty(&pcache->entries)) { diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h index 5ecc9d3925db..2ca4163abafe 100644 --- a/tools/perf/util/probe-file.h +++ b/tools/perf/util/probe-file.h @@ -51,7 +51,7 @@ int probe_file__del_strlist(int fd, struct strlist *namelist); int probe_cache_entry__get_event(struct probe_cache_entry *entry, struct probe_trace_event **tevs); -struct probe_cache *probe_cache__new(const char *target); +struct probe_cache *probe_cache__new(const char *target, struct nsinfo *nsi); int probe_cache__add_entry(struct probe_cache *pcache, struct perf_probe_event *pev, struct probe_trace_event *tevs, int ntevs); @@ -69,7 +69,7 @@ int probe_cache__show_all_caches(struct strfilter *filter); bool probe_type_is_available(enum probe_type type); bool kretprobe_offset_is_supported(void); #else /* ! HAVE_LIBELF_SUPPORT */ -static inline struct probe_cache *probe_cache__new(const char *tgt __maybe_unused) +static inline struct probe_cache *probe_cache__new(const char *tgt __maybe_unused, struct nsinfo *nsi __maybe_unused) { return NULL; } diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index 9f3b0d9754a8..e66dc495809a 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -10,6 +10,7 @@ util/ctype.c util/evlist.c util/evsel.c util/cpumap.c +util/namespaces.c ../lib/bitmap.c ../lib/find_bit.c ../lib/hweight.c diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 40de3cb40d21..c7187f067d31 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -28,6 +28,7 @@ #include <stdbool.h> #include <errno.h> #include <linux/bitmap.h> +#include <linux/compiler.h> #include <linux/time64.h> #include "../../perf.h" @@ -84,7 +85,7 @@ struct tables { static struct tables tables_global; -static void handler_call_die(const char *handler_name) NORETURN; +static void handler_call_die(const char *handler_name) __noreturn; static void handler_call_die(const char *handler_name) { PyErr_Print(); @@ -115,6 +116,34 @@ static PyObject *get_handler(const char *handler_name) return handler; } +static int get_argument_count(PyObject *handler) +{ + int arg_count = 0; + + /* + * The attribute for the code object is func_code in Python 2, + * whereas it is __code__ in Python 3.0+. + */ + PyObject *code_obj = PyObject_GetAttrString(handler, + "func_code"); + if (PyErr_Occurred()) { + PyErr_Clear(); + code_obj = PyObject_GetAttrString(handler, + "__code__"); + } + PyErr_Clear(); + if (code_obj) { + PyObject *arg_count_obj = PyObject_GetAttrString(code_obj, + "co_argcount"); + if (arg_count_obj) { + arg_count = (int) PyInt_AsLong(arg_count_obj); + Py_DECREF(arg_count_obj); + } + Py_DECREF(code_obj); + } + return arg_count; +} + static void call_object(PyObject *handler, PyObject *args, const char *die_msg) { PyObject *retval; @@ -390,13 +419,115 @@ exit: return pylist; } +static PyObject *get_sample_value_as_tuple(struct sample_read_value *value) +{ + PyObject *t; + + t = PyTuple_New(2); + if (!t) + Py_FatalError("couldn't create Python tuple"); + PyTuple_SetItem(t, 0, PyLong_FromUnsignedLongLong(value->id)); + PyTuple_SetItem(t, 1, PyLong_FromUnsignedLongLong(value->value)); + return t; +} + +static void set_sample_read_in_dict(PyObject *dict_sample, + struct perf_sample *sample, + struct perf_evsel *evsel) +{ + u64 read_format = evsel->attr.read_format; + PyObject *values; + unsigned int i; + + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) { + pydict_set_item_string_decref(dict_sample, "time_enabled", + PyLong_FromUnsignedLongLong(sample->read.time_enabled)); + } + + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) { + pydict_set_item_string_decref(dict_sample, "time_running", + PyLong_FromUnsignedLongLong(sample->read.time_running)); + } + + if (read_format & PERF_FORMAT_GROUP) + values = PyList_New(sample->read.group.nr); + else + values = PyList_New(1); + + if (!values) + Py_FatalError("couldn't create Python list"); + + if (read_format & PERF_FORMAT_GROUP) { + for (i = 0; i < sample->read.group.nr; i++) { + PyObject *t = get_sample_value_as_tuple(&sample->read.group.values[i]); + PyList_SET_ITEM(values, i, t); + } + } else { + PyObject *t = get_sample_value_as_tuple(&sample->read.one); + PyList_SET_ITEM(values, 0, t); + } + pydict_set_item_string_decref(dict_sample, "values", values); +} + +static PyObject *get_perf_sample_dict(struct perf_sample *sample, + struct perf_evsel *evsel, + struct addr_location *al, + PyObject *callchain) +{ + PyObject *dict, *dict_sample; + + dict = PyDict_New(); + if (!dict) + Py_FatalError("couldn't create Python dictionary"); + + dict_sample = PyDict_New(); + if (!dict_sample) + Py_FatalError("couldn't create Python dictionary"); + + pydict_set_item_string_decref(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel))); + pydict_set_item_string_decref(dict, "attr", PyString_FromStringAndSize( + (const char *)&evsel->attr, sizeof(evsel->attr))); + + pydict_set_item_string_decref(dict_sample, "pid", + PyInt_FromLong(sample->pid)); + pydict_set_item_string_decref(dict_sample, "tid", + PyInt_FromLong(sample->tid)); + pydict_set_item_string_decref(dict_sample, "cpu", + PyInt_FromLong(sample->cpu)); + pydict_set_item_string_decref(dict_sample, "ip", + PyLong_FromUnsignedLongLong(sample->ip)); + pydict_set_item_string_decref(dict_sample, "time", + PyLong_FromUnsignedLongLong(sample->time)); + pydict_set_item_string_decref(dict_sample, "period", + PyLong_FromUnsignedLongLong(sample->period)); + set_sample_read_in_dict(dict_sample, sample, evsel); + pydict_set_item_string_decref(dict, "sample", dict_sample); + + pydict_set_item_string_decref(dict, "raw_buf", PyString_FromStringAndSize( + (const char *)sample->raw_data, sample->raw_size)); + pydict_set_item_string_decref(dict, "comm", + PyString_FromString(thread__comm_str(al->thread))); + if (al->map) { + pydict_set_item_string_decref(dict, "dso", + PyString_FromString(al->map->dso->name)); + } + if (al->sym) { + pydict_set_item_string_decref(dict, "symbol", + PyString_FromString(al->sym->name)); + } + + pydict_set_item_string_decref(dict, "callchain", callchain); + + return dict; +} + static void python_process_tracepoint(struct perf_sample *sample, struct perf_evsel *evsel, struct addr_location *al) { struct event_format *event = evsel->tp_format; PyObject *handler, *context, *t, *obj = NULL, *callchain; - PyObject *dict = NULL; + PyObject *dict = NULL, *all_entries_dict = NULL; static char handler_name[256]; struct format_field *field; unsigned long s, ns; @@ -406,10 +537,7 @@ static void python_process_tracepoint(struct perf_sample *sample, void *data = sample->raw_data; unsigned long long nsecs = sample->time; const char *comm = thread__comm_str(al->thread); - - t = PyTuple_New(MAX_FIELDS); - if (!t) - Py_FatalError("couldn't create Python tuple"); + const char *default_handler_name = "trace_unhandled"; if (!event) { snprintf(handler_name, sizeof(handler_name), @@ -426,10 +554,19 @@ static void python_process_tracepoint(struct perf_sample *sample, handler = get_handler(handler_name); if (!handler) { + handler = get_handler(default_handler_name); + if (!handler) + return; dict = PyDict_New(); if (!dict) Py_FatalError("couldn't create Python dict"); } + + t = PyTuple_New(MAX_FIELDS); + if (!t) + Py_FatalError("couldn't create Python tuple"); + + s = nsecs / NSEC_PER_SEC; ns = nsecs - s * NSEC_PER_SEC; @@ -443,8 +580,10 @@ static void python_process_tracepoint(struct perf_sample *sample, /* ip unwinding */ callchain = python_process_callchain(sample, evsel, al); + /* Need an additional reference for the perf_sample dict */ + Py_INCREF(callchain); - if (handler) { + if (!dict) { PyTuple_SetItem(t, n++, PyInt_FromLong(cpu)); PyTuple_SetItem(t, n++, PyInt_FromLong(s)); PyTuple_SetItem(t, n++, PyInt_FromLong(ns)); @@ -483,26 +622,35 @@ static void python_process_tracepoint(struct perf_sample *sample, } else { /* FIELD_IS_NUMERIC */ obj = get_field_numeric_entry(event, field, data); } - if (handler) + if (!dict) PyTuple_SetItem(t, n++, obj); else pydict_set_item_string_decref(dict, field->name, obj); } - if (!handler) + if (dict) PyTuple_SetItem(t, n++, dict); + if (get_argument_count(handler) == (int) n + 1) { + all_entries_dict = get_perf_sample_dict(sample, evsel, al, + callchain); + PyTuple_SetItem(t, n++, all_entries_dict); + } else { + Py_DECREF(callchain); + } + if (_PyTuple_Resize(&t, n) == -1) Py_FatalError("error resizing Python tuple"); - if (handler) { + if (!dict) { call_object(handler, t, handler_name); } else { - try_call_object("trace_unhandled", t); + call_object(handler, t, default_handler_name); Py_DECREF(dict); } + Py_XDECREF(all_entries_dict); Py_DECREF(t); } @@ -794,10 +942,16 @@ static void python_process_general_event(struct perf_sample *sample, struct perf_evsel *evsel, struct addr_location *al) { - PyObject *handler, *t, *dict, *callchain, *dict_sample; + PyObject *handler, *t, *dict, *callchain; static char handler_name[64]; unsigned n = 0; + snprintf(handler_name, sizeof(handler_name), "%s", "process_event"); + + handler = get_handler(handler_name); + if (!handler) + return; + /* * Use the MAX_FIELDS to make the function expandable, though * currently there is only one item for the tuple. @@ -806,61 +960,16 @@ static void python_process_general_event(struct perf_sample *sample, if (!t) Py_FatalError("couldn't create Python tuple"); - dict = PyDict_New(); - if (!dict) - Py_FatalError("couldn't create Python dictionary"); - - dict_sample = PyDict_New(); - if (!dict_sample) - Py_FatalError("couldn't create Python dictionary"); - - snprintf(handler_name, sizeof(handler_name), "%s", "process_event"); - - handler = get_handler(handler_name); - if (!handler) - goto exit; - - pydict_set_item_string_decref(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel))); - pydict_set_item_string_decref(dict, "attr", PyString_FromStringAndSize( - (const char *)&evsel->attr, sizeof(evsel->attr))); - - pydict_set_item_string_decref(dict_sample, "pid", - PyInt_FromLong(sample->pid)); - pydict_set_item_string_decref(dict_sample, "tid", - PyInt_FromLong(sample->tid)); - pydict_set_item_string_decref(dict_sample, "cpu", - PyInt_FromLong(sample->cpu)); - pydict_set_item_string_decref(dict_sample, "ip", - PyLong_FromUnsignedLongLong(sample->ip)); - pydict_set_item_string_decref(dict_sample, "time", - PyLong_FromUnsignedLongLong(sample->time)); - pydict_set_item_string_decref(dict_sample, "period", - PyLong_FromUnsignedLongLong(sample->period)); - pydict_set_item_string_decref(dict, "sample", dict_sample); - - pydict_set_item_string_decref(dict, "raw_buf", PyString_FromStringAndSize( - (const char *)sample->raw_data, sample->raw_size)); - pydict_set_item_string_decref(dict, "comm", - PyString_FromString(thread__comm_str(al->thread))); - if (al->map) { - pydict_set_item_string_decref(dict, "dso", - PyString_FromString(al->map->dso->name)); - } - if (al->sym) { - pydict_set_item_string_decref(dict, "symbol", - PyString_FromString(al->sym->name)); - } - /* ip unwinding */ callchain = python_process_callchain(sample, evsel, al); - pydict_set_item_string_decref(dict, "callchain", callchain); + dict = get_perf_sample_dict(sample, evsel, al, callchain); PyTuple_SetItem(t, n++, dict); if (_PyTuple_Resize(&t, n) == -1) Py_FatalError("error resizing Python tuple"); call_object(handler, t, handler_name); -exit: + Py_DECREF(dict); Py_DECREF(t); } @@ -1258,6 +1367,12 @@ static int python_generate_script(struct pevent *pevent, const char *outfile) fprintf(ofp, "%s", f->name); } + if (not_first++) + fprintf(ofp, ", "); + if (++count % 5 == 0) + fprintf(ofp, "\n\t\t"); + fprintf(ofp, "perf_sample_dict"); + fprintf(ofp, "):\n"); fprintf(ofp, "\t\tprint_header(event_name, common_cpu, " @@ -1327,6 +1442,9 @@ static int python_generate_script(struct pevent *pevent, const char *outfile) fprintf(ofp, ")\n\n"); + fprintf(ofp, "\t\tprint 'Sample: {'+" + "get_dict_as_string(perf_sample_dict['sample'], ', ')+'}'\n\n"); + fprintf(ofp, "\t\tfor node in common_callchain:"); fprintf(ofp, "\n\t\t\tif 'sym' in node:"); fprintf(ofp, "\n\t\t\t\tprint \"\\t[%%x] %%s\" %% (node['ip'], node['sym']['name'])"); @@ -1337,15 +1455,20 @@ static int python_generate_script(struct pevent *pevent, const char *outfile) } fprintf(ofp, "def trace_unhandled(event_name, context, " - "event_fields_dict):\n"); + "event_fields_dict, perf_sample_dict):\n"); - fprintf(ofp, "\t\tprint ' '.join(['%%s=%%s'%%(k,str(v))" - "for k,v in sorted(event_fields_dict.items())])\n\n"); + fprintf(ofp, "\t\tprint get_dict_as_string(event_fields_dict)\n"); + fprintf(ofp, "\t\tprint 'Sample: {'+" + "get_dict_as_string(perf_sample_dict['sample'], ', ')+'}'\n\n"); fprintf(ofp, "def print_header(" "event_name, cpu, secs, nsecs, pid, comm):\n" "\tprint \"%%-20s %%5u %%05u.%%09u %%8u %%-20s \" %% \\\n\t" - "(event_name, cpu, secs, nsecs, pid, comm),\n"); + "(event_name, cpu, secs, nsecs, pid, comm),\n\n"); + + fprintf(ofp, "def get_dict_as_string(a_dict, delimiter=' '):\n" + "\treturn delimiter.join" + "(['%%s=%%s'%%(k,str(v))for k,v in sorted(a_dict.items())])\n"); fclose(ofp); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 7dc1096264c5..a7ebd9fe8e40 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -428,6 +428,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool) tool->stat_round = process_stat_round_stub; if (tool->time_conv == NULL) tool->time_conv = process_event_op2_stub; + if (tool->feature == NULL) + tool->feature = process_event_op2_stub; } static void swap_sample_id_all(union perf_event *event, void *data) @@ -1118,6 +1120,9 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event, if (sample_type & PERF_SAMPLE_DATA_SRC) printf(" . data_src: 0x%"PRIx64"\n", sample->data_src); + if (sample_type & PERF_SAMPLE_PHYS_ADDR) + printf(" .. phys_addr: 0x%"PRIx64"\n", sample->phys_addr); + if (sample_type & PERF_SAMPLE_TRANSACTION) printf("... transaction: %" PRIx64 "\n", sample->transaction); @@ -1125,6 +1130,30 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event, sample_read__printf(sample, evsel->attr.read_format); } +static void dump_read(struct perf_evsel *evsel, union perf_event *event) +{ + struct read_event *read_event = &event->read; + u64 read_format; + + if (!dump_trace) + return; + + printf(": %d %d %s %" PRIu64 "\n", event->read.pid, event->read.tid, + evsel ? perf_evsel__name(evsel) : "FAIL", + event->read.value); + + read_format = evsel->attr.read_format; + + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + printf("... time enabled : %" PRIu64 "\n", read_event->time_enabled); + + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + printf("... time running : %" PRIu64 "\n", read_event->time_running); + + if (read_format & PERF_FORMAT_ID) + printf("... id : %" PRIu64 "\n", read_event->id); +} + static struct machine *machines__find_for_cpumode(struct machines *machines, union perf_event *event, struct perf_sample *sample) @@ -1269,6 +1298,7 @@ static int machines__deliver_event(struct machines *machines, evlist->stats.total_lost_samples += event->lost_samples.lost; return tool->lost_samples(tool, event, sample, machine); case PERF_RECORD_READ: + dump_read(evsel, event); return tool->read(tool, event, sample, evsel, machine); case PERF_RECORD_THROTTLE: return tool->throttle(tool, event, sample, machine); @@ -1371,6 +1401,8 @@ static s64 perf_session__process_user_event(struct perf_session *session, case PERF_RECORD_TIME_CONV: session->time_conv = event->time_conv; return tool->time_conv(tool, event, session); + case PERF_RECORD_HEADER_FEATURE: + return tool->feature(tool, event, session); default: return -EINVAL; } @@ -2035,7 +2067,7 @@ int perf_session__cpu_bitmap(struct perf_session *session, if (!(evsel->attr.sample_type & PERF_SAMPLE_CPU)) { pr_err("File does not contain CPU events. " - "Remove -c option to proceed.\n"); + "Remove -C option to proceed.\n"); return -1; } } diff --git a/tools/perf/util/setns.c b/tools/perf/util/setns.c new file mode 100644 index 000000000000..ce8fc290fce8 --- /dev/null +++ b/tools/perf/util/setns.c @@ -0,0 +1,8 @@ +#include "util.h" +#include <unistd.h> +#include <sys/syscall.h> + +int setns(int fd, int nstype) +{ + return syscall(__NR_setns, fd, nstype); +} diff --git a/tools/perf/util/smt.c b/tools/perf/util/smt.c new file mode 100644 index 000000000000..453f6f6f29f3 --- /dev/null +++ b/tools/perf/util/smt.c @@ -0,0 +1,44 @@ +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <linux/bitops.h> +#include "api/fs/fs.h" +#include "smt.h" + +int smt_on(void) +{ + static bool cached; + static int cached_result; + int cpu; + int ncpu; + + if (cached) + return cached_result; + + ncpu = sysconf(_SC_NPROCESSORS_CONF); + for (cpu = 0; cpu < ncpu; cpu++) { + unsigned long long siblings; + char *str; + size_t strlen; + char fn[256]; + + snprintf(fn, sizeof fn, + "devices/system/cpu/cpu%d/topology/thread_siblings", + cpu); + if (sysfs__read_str(fn, &str, &strlen) < 0) + continue; + /* Entry is hex, but does not have 0x, so need custom parser */ + siblings = strtoull(str, NULL, 16); + free(str); + if (hweight64(siblings) > 1) { + cached_result = 1; + cached = true; + break; + } + } + if (!cached) { + cached_result = 0; + cached = true; + } + return cached_result; +} diff --git a/tools/perf/util/smt.h b/tools/perf/util/smt.h new file mode 100644 index 000000000000..b8414b7bcbc8 --- /dev/null +++ b/tools/perf/util/smt.h @@ -0,0 +1,6 @@ +#ifndef SMT_H +#define SMT_H 1 + +int smt_on(void); + +#endif diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 5762ae4e9e91..eb3ab902a1c0 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -1316,6 +1316,47 @@ struct sort_entry sort_mem_dcacheline = { }; static int64_t +sort__phys_daddr_cmp(struct hist_entry *left, struct hist_entry *right) +{ + uint64_t l = 0, r = 0; + + if (left->mem_info) + l = left->mem_info->daddr.phys_addr; + if (right->mem_info) + r = right->mem_info->daddr.phys_addr; + + return (int64_t)(r - l); +} + +static int hist_entry__phys_daddr_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + uint64_t addr = 0; + size_t ret = 0; + size_t len = BITS_PER_LONG / 4; + + addr = he->mem_info->daddr.phys_addr; + + ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", he->level); + + ret += repsep_snprintf(bf + ret, size - ret, "%-#.*llx", len, addr); + + ret += repsep_snprintf(bf + ret, size - ret, "%-*s", width - ret, ""); + + if (ret > width) + bf[width] = '\0'; + + return width; +} + +struct sort_entry sort_mem_phys_daddr = { + .se_header = "Data Physical Address", + .se_cmp = sort__phys_daddr_cmp, + .se_snprintf = hist_entry__phys_daddr_snprintf, + .se_width_idx = HISTC_MEM_PHYS_DADDR, +}; + +static int64_t sort__abort_cmp(struct hist_entry *left, struct hist_entry *right) { if (!left->branch_info || !right->branch_info) @@ -1547,6 +1588,7 @@ static struct sort_dimension memory_sort_dimensions[] = { DIM(SORT_MEM_LVL, "mem", sort_mem_lvl), DIM(SORT_MEM_SNOOP, "snoop", sort_mem_snoop), DIM(SORT_MEM_DCACHELINE, "dcacheline", sort_mem_dcacheline), + DIM(SORT_MEM_PHYS_DADDR, "phys_daddr", sort_mem_phys_daddr), }; #undef DIM @@ -2532,12 +2574,12 @@ static int setup_sort_list(struct perf_hpp_list *list, char *str, ret = sort_dimension__add(list, tok, evlist, level); if (ret == -EINVAL) { if (!cacheline_size && !strncasecmp(tok, "dcacheline", strlen(tok))) - error("The \"dcacheline\" --sort key needs to know the cacheline size and it couldn't be determined on this system"); + pr_err("The \"dcacheline\" --sort key needs to know the cacheline size and it couldn't be determined on this system"); else - error("Invalid --sort key: `%s'", tok); + pr_err("Invalid --sort key: `%s'", tok); break; } else if (ret == -ESRCH) { - error("Unknown --sort key: `%s'", tok); + pr_err("Unknown --sort key: `%s'", tok); break; } } @@ -2563,7 +2605,7 @@ static const char *get_default_sort_order(struct perf_evlist *evlist) BUG_ON(sort__mode >= ARRAY_SIZE(default_sort_orders)); - if (evlist == NULL) + if (evlist == NULL || perf_evlist__empty(evlist)) goto out_no_evlist; evlist__for_each_entry(evlist, evsel) { @@ -2594,7 +2636,7 @@ static int setup_sort_order(struct perf_evlist *evlist) return 0; if (sort_order[1] == '\0') { - error("Invalid --sort key: `+'"); + pr_err("Invalid --sort key: `+'"); return -EINVAL; } @@ -2604,7 +2646,7 @@ static int setup_sort_order(struct perf_evlist *evlist) */ if (asprintf(&new_sort_order, "%s,%s", get_default_sort_order(evlist), sort_order + 1) < 0) { - error("Not enough memory to set up --sort"); + pr_err("Not enough memory to set up --sort"); return -ENOMEM; } @@ -2668,7 +2710,7 @@ static int __setup_sorting(struct perf_evlist *evlist) str = strdup(sort_keys); if (str == NULL) { - error("Not enough memory to setup sort keys"); + pr_err("Not enough memory to setup sort keys"); return -ENOMEM; } @@ -2678,7 +2720,7 @@ static int __setup_sorting(struct perf_evlist *evlist) if (!is_strict_order(field_order)) { str = setup_overhead(str); if (str == NULL) { - error("Not enough memory to setup overhead keys"); + pr_err("Not enough memory to setup overhead keys"); return -ENOMEM; } } @@ -2834,10 +2876,10 @@ static int setup_output_list(struct perf_hpp_list *list, char *str) tok; tok = strtok_r(NULL, ", ", &tmp)) { ret = output_field_add(list, tok); if (ret == -EINVAL) { - error("Invalid --fields key: `%s'", tok); + pr_err("Invalid --fields key: `%s'", tok); break; } else if (ret == -ESRCH) { - error("Unknown --fields key: `%s'", tok); + pr_err("Unknown --fields key: `%s'", tok); break; } } @@ -2877,7 +2919,7 @@ static int __setup_output_field(void) strp = str = strdup(field_order); if (str == NULL) { - error("Not enough memory to setup output fields"); + pr_err("Not enough memory to setup output fields"); return -ENOMEM; } @@ -2885,7 +2927,7 @@ static int __setup_output_field(void) strp++; if (!strlen(strp)) { - error("Invalid --fields key: `+'"); + pr_err("Invalid --fields key: `+'"); goto out; } diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index b7c75597e18f..f36dc4980a6c 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -245,6 +245,7 @@ enum sort_type { SORT_MEM_SNOOP, SORT_MEM_DCACHELINE, SORT_MEM_IADDR_SYMBOL, + SORT_MEM_PHYS_DADDR, }; /* diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c index ebc88a74e67b..ed8e8d2de942 100644 --- a/tools/perf/util/srcline.c +++ b/tools/perf/util/srcline.c @@ -155,6 +155,9 @@ static void find_address_in_section(bfd *abfd, asection *section, void *data) a2l->found = bfd_find_nearest_line(abfd, section, a2l->syms, pc - vma, &a2l->filename, &a2l->funcname, &a2l->line); + + if (a2l->filename && !strlen(a2l->filename)) + a2l->filename = NULL; } static struct a2l_data *addr2line_init(const char *path) @@ -248,6 +251,9 @@ static int addr2line(const char *dso_name, u64 addr, &a2l->funcname, &a2l->line) && cnt++ < MAX_INLINE_NEST) { + if (a2l->filename && !strlen(a2l->filename)) + a2l->filename = NULL; + if (node != NULL) { if (inline_list__append_dso_a2l(dso, node)) return 0; diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index ac10cc675d39..a04cf56d3517 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -44,6 +44,8 @@ static struct stats runtime_topdown_slots_issued[NUM_CTX][MAX_NR_CPUS]; static struct stats runtime_topdown_slots_retired[NUM_CTX][MAX_NR_CPUS]; static struct stats runtime_topdown_fetch_bubbles[NUM_CTX][MAX_NR_CPUS]; static struct stats runtime_topdown_recovery_bubbles[NUM_CTX][MAX_NR_CPUS]; +static struct stats runtime_smi_num_stats[NUM_CTX][MAX_NR_CPUS]; +static struct stats runtime_aperf_stats[NUM_CTX][MAX_NR_CPUS]; static struct rblist runtime_saved_values; static bool have_frontend_stalled; @@ -68,7 +70,11 @@ static int saved_value_cmp(struct rb_node *rb_node, const void *entry) return a->ctx - b->ctx; if (a->cpu != b->cpu) return a->cpu - b->cpu; - return a->evsel - b->evsel; + if (a->evsel == b->evsel) + return 0; + if ((char *)a->evsel < (char *)b->evsel) + return -1; + return +1; } static struct rb_node *saved_value_new(struct rblist *rblist __maybe_unused, @@ -157,6 +163,8 @@ void perf_stat__reset_shadow_stats(void) memset(runtime_topdown_slots_issued, 0, sizeof(runtime_topdown_slots_issued)); memset(runtime_topdown_fetch_bubbles, 0, sizeof(runtime_topdown_fetch_bubbles)); memset(runtime_topdown_recovery_bubbles, 0, sizeof(runtime_topdown_recovery_bubbles)); + memset(runtime_smi_num_stats, 0, sizeof(runtime_smi_num_stats)); + memset(runtime_aperf_stats, 0, sizeof(runtime_aperf_stats)); next = rb_first(&runtime_saved_values.entries); while (next) { @@ -217,6 +225,10 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count, update_stats(&runtime_dtlb_cache_stats[ctx][cpu], count[0]); else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_ITLB)) update_stats(&runtime_itlb_cache_stats[ctx][cpu], count[0]); + else if (perf_stat_evsel__is(counter, SMI_NUM)) + update_stats(&runtime_smi_num_stats[ctx][cpu], count[0]); + else if (perf_stat_evsel__is(counter, APERF)) + update_stats(&runtime_aperf_stats[ctx][cpu], count[0]); if (counter->collect_stat) { struct saved_value *v = saved_value_lookup(counter, cpu, ctx, @@ -592,6 +604,29 @@ static double td_be_bound(int ctx, int cpu) return sanitize_val(1.0 - sum); } +static void print_smi_cost(int cpu, struct perf_evsel *evsel, + struct perf_stat_output_ctx *out) +{ + double smi_num, aperf, cycles, cost = 0.0; + int ctx = evsel_context(evsel); + const char *color = NULL; + + smi_num = avg_stats(&runtime_smi_num_stats[ctx][cpu]); + aperf = avg_stats(&runtime_aperf_stats[ctx][cpu]); + cycles = avg_stats(&runtime_cycles_stats[ctx][cpu]); + + if ((cycles == 0) || (aperf == 0)) + return; + + if (smi_num) + cost = (aperf - cycles) / aperf * 100.00; + + if (cost > 10) + color = PERF_COLOR_RED; + out->print_metric(out->ctx, color, "%8.1f%%", "SMI cycles%", cost); + out->print_metric(out->ctx, NULL, "%4.0f", "SMI#", smi_num); +} + void perf_stat__print_shadow_stats(struct perf_evsel *evsel, double avg, int cpu, struct perf_stat_output_ctx *out) @@ -825,6 +860,8 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel, } snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit); print_metric(ctxp, NULL, "%8.3f", unit_buf, ratio); + } else if (perf_stat_evsel__is(evsel, SMI_NUM)) { + print_smi_cost(cpu, evsel, out); } else { print_metric(ctxp, NULL, NULL, NULL, 0); } diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index c58174443dc1..35e9848734d6 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -86,6 +86,8 @@ static const char *id_str[PERF_STAT_EVSEL_ID__MAX] = { ID(TOPDOWN_SLOTS_RETIRED, topdown-slots-retired), ID(TOPDOWN_FETCH_BUBBLES, topdown-fetch-bubbles), ID(TOPDOWN_RECOVERY_BUBBLES, topdown-recovery-bubbles), + ID(SMI_NUM, msr/smi/), + ID(APERF, msr/aperf/), }; #undef ID @@ -126,6 +128,10 @@ static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel) static void perf_evsel__free_stat_priv(struct perf_evsel *evsel) { + struct perf_stat_evsel *ps = evsel->priv; + + if (ps) + free(ps->group_data); zfree(&evsel->priv); } diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 0a65ae23f495..eacaf958e19d 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -22,12 +22,15 @@ enum perf_stat_evsel_id { PERF_STAT_EVSEL_ID__TOPDOWN_SLOTS_RETIRED, PERF_STAT_EVSEL_ID__TOPDOWN_FETCH_BUBBLES, PERF_STAT_EVSEL_ID__TOPDOWN_RECOVERY_BUBBLES, + PERF_STAT_EVSEL_ID__SMI_NUM, + PERF_STAT_EVSEL_ID__APERF, PERF_STAT_EVSEL_ID__MAX, }; struct perf_stat_evsel { - struct stats res_stats[3]; - enum perf_stat_evsel_id id; + struct stats res_stats[3]; + enum perf_stat_evsel_id id; + u64 *group_data; }; enum aggr_mode { diff --git a/tools/perf/util/strbuf.h b/tools/perf/util/strbuf.h index 318424ea561d..802d743378af 100644 --- a/tools/perf/util/strbuf.h +++ b/tools/perf/util/strbuf.h @@ -42,6 +42,7 @@ #include <stdarg.h> #include <stddef.h> #include <string.h> +#include <linux/compiler.h> #include <sys/types.h> extern char strbuf_slopbuf[]; @@ -85,8 +86,7 @@ static inline int strbuf_addstr(struct strbuf *sb, const char *s) { return strbuf_add(sb, s, strlen(s)); } -__attribute__((format(printf,2,3))) -int strbuf_addf(struct strbuf *sb, const char *fmt, ...); +int strbuf_addf(struct strbuf *sb, const char *fmt, ...) __printf(2, 3); /* XXX: if read fails, any partial read is undone */ ssize_t strbuf_read(struct strbuf *, int fd, ssize_t hint); diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 502505cf236a..5c39f420111e 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -259,7 +259,7 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map * { uint32_t nr_rel_entries, idx; GElf_Sym sym; - u64 plt_offset; + u64 plt_offset, plt_header_size, plt_entry_size; GElf_Shdr shdr_plt; struct symbol *f; GElf_Shdr shdr_rel_plt, shdr_dynsym; @@ -326,6 +326,23 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map * nr_rel_entries = shdr_rel_plt.sh_size / shdr_rel_plt.sh_entsize; plt_offset = shdr_plt.sh_offset; + switch (ehdr.e_machine) { + case EM_ARM: + plt_header_size = 20; + plt_entry_size = 12; + break; + + case EM_AARCH64: + plt_header_size = 32; + plt_entry_size = 16; + break; + + default: /* FIXME: s390/alpha/mips/parisc/poperpc/sh/sparc/xtensa need to be checked */ + plt_header_size = shdr_plt.sh_entsize; + plt_entry_size = shdr_plt.sh_entsize; + break; + } + plt_offset += plt_header_size; if (shdr_rel_plt.sh_type == SHT_RELA) { GElf_Rela pos_mem, *pos; @@ -335,7 +352,6 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map * const char *elf_name = NULL; char *demangled = NULL; symidx = GELF_R_SYM(pos->r_info); - plt_offset += shdr_plt.sh_entsize; gelf_getsym(syms, symidx, &sym); elf_name = elf_sym__name(&sym, symstrs); @@ -346,11 +362,12 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map * "%s@plt", elf_name); free(demangled); - f = symbol__new(plt_offset, shdr_plt.sh_entsize, + f = symbol__new(plt_offset, plt_entry_size, STB_GLOBAL, sympltname); if (!f) goto out_elf_end; + plt_offset += plt_entry_size; symbols__insert(&dso->symbols[map->type], f); ++nr; } @@ -361,7 +378,6 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map * const char *elf_name = NULL; char *demangled = NULL; symidx = GELF_R_SYM(pos->r_info); - plt_offset += shdr_plt.sh_entsize; gelf_getsym(syms, symidx, &sym); elf_name = elf_sym__name(&sym, symstrs); @@ -372,11 +388,12 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map * "%s@plt", elf_name); free(demangled); - f = symbol__new(plt_offset, shdr_plt.sh_entsize, + f = symbol__new(plt_offset, plt_entry_size, STB_GLOBAL, sympltname); if (!f) goto out_elf_end; + plt_offset += plt_entry_size; symbols__insert(&dso->symbols[map->type], f); ++nr; } @@ -391,7 +408,7 @@ out_elf_end: return 0; } -char *dso__demangle_sym(struct dso *dso, int kmodule, char *elf_name) +char *dso__demangle_sym(struct dso *dso, int kmodule, const char *elf_name) { return demangle_sym(dso, kmodule, elf_name); } @@ -793,6 +810,12 @@ static u64 ref_reloc(struct kmap *kmap) void __weak arch__sym_update(struct symbol *s __maybe_unused, GElf_Sym *sym __maybe_unused) { } +void __weak arch__adjust_sym_map_offset(GElf_Sym *sym, GElf_Shdr *shdr, + struct map *map __maybe_unused) +{ + sym->st_value -= shdr->sh_addr - shdr->sh_offset; +} + int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, struct symsrc *runtime_ss, int kmodule) { @@ -973,7 +996,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, /* Adjust symbol to map to file offset */ if (adjust_kernel_syms) - sym.st_value -= shdr.sh_addr - shdr.sh_offset; + arch__adjust_sym_map_offset(&sym, &shdr, map); if (strcmp(section_name, (curr_dso->short_name + @@ -1442,7 +1465,7 @@ static int kcore_copy__parse_kallsyms(struct kcore_copy_info *kci, static int kcore_copy__process_modules(void *arg, const char *name __maybe_unused, - u64 start) + u64 start, u64 size __maybe_unused) { struct kcore_copy_info *kci = arg; diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c index 40bf5d4c0bfd..1a5aa35b0100 100644 --- a/tools/perf/util/symbol-minimal.c +++ b/tools/perf/util/symbol-minimal.c @@ -377,7 +377,7 @@ void symbol__elf_init(void) char *dso__demangle_sym(struct dso *dso __maybe_unused, int kmodule __maybe_unused, - char *elf_name __maybe_unused) + const char *elf_name __maybe_unused) { return NULL; } diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index e7a98dbd2aed..5909ee4c7ade 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -18,6 +18,7 @@ #include "symbol.h" #include "strlist.h" #include "intlist.h" +#include "namespaces.h" #include "header.h" #include "path.h" #include "sane_ctype.h" @@ -52,6 +53,7 @@ static enum dso_binary_type binary_type_symtab[] = { DSO_BINARY_TYPE__JAVA_JIT, DSO_BINARY_TYPE__DEBUGLINK, DSO_BINARY_TYPE__BUILD_ID_CACHE, + DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO, DSO_BINARY_TYPE__FEDORA_DEBUGINFO, DSO_BINARY_TYPE__UBUNTU_DEBUGINFO, DSO_BINARY_TYPE__BUILDID_DEBUGINFO, @@ -231,7 +233,8 @@ void __map_groups__fixup_end(struct map_groups *mg, enum map_type type) goto out_unlock; for (next = map__next(curr); next; next = map__next(curr)) { - curr->end = next->start; + if (!curr->end) + curr->end = next->start; curr = next; } @@ -239,7 +242,8 @@ void __map_groups__fixup_end(struct map_groups *mg, enum map_type type) * We still haven't the actual symbols, so guess the * last map final address. */ - curr->end = ~0ULL; + if (!curr->end) + curr->end = ~0ULL; out_unlock: pthread_rwlock_unlock(&maps->lock); @@ -550,7 +554,7 @@ void dso__sort_by_name(struct dso *dso, enum map_type type) int modules__parse(const char *filename, void *arg, int (*process_module)(void *arg, const char *name, - u64 start)) + u64 start, u64 size)) { char *line = NULL; size_t n; @@ -563,8 +567,8 @@ int modules__parse(const char *filename, void *arg, while (1) { char name[PATH_MAX]; - u64 start; - char *sep; + u64 start, size; + char *sep, *endptr; ssize_t line_len; line_len = getline(&line, &n, file); @@ -596,7 +600,11 @@ int modules__parse(const char *filename, void *arg, scnprintf(name, sizeof(name), "[%s]", line); - err = process_module(arg, name, start); + size = strtoul(sep + 1, &endptr, 0); + if (*endptr != ' ' && *endptr != '\t') + continue; + + err = process_module(arg, name, start, size); if (err) break; } @@ -943,7 +951,8 @@ static struct module_info *find_module(const char *name, return NULL; } -static int __read_proc_modules(void *arg, const char *name, u64 start) +static int __read_proc_modules(void *arg, const char *name, u64 start, + u64 size __maybe_unused) { struct rb_root *modules = arg; struct module_info *mi; @@ -1325,14 +1334,15 @@ int dso__load_kallsyms(struct dso *dso, const char *filename, return __dso__load_kallsyms(dso, filename, map, false); } -static int dso__load_perf_map(struct dso *dso, struct map *map) +static int dso__load_perf_map(const char *map_path, struct dso *dso, + struct map *map) { char *line = NULL; size_t n; FILE *file; int nr_syms = 0; - file = fopen(dso->long_name, "r"); + file = fopen(map_path, "r"); if (file == NULL) goto out_failure; @@ -1416,6 +1426,7 @@ static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod, return kmod && dso->symtab_type == type; case DSO_BINARY_TYPE__BUILD_ID_CACHE: + case DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO: return true; case DSO_BINARY_TYPE__NOT_FOUND: @@ -1424,6 +1435,44 @@ static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod, } } +/* Checks for the existence of the perf-<pid>.map file in two different + * locations. First, if the process is a separate mount namespace, check in + * that namespace using the pid of the innermost pid namespace. If's not in a + * namespace, or the file can't be found there, try in the mount namespace of + * the tracing process using our view of its pid. + */ +static int dso__find_perf_map(char *filebuf, size_t bufsz, + struct nsinfo **nsip) +{ + struct nscookie nsc; + struct nsinfo *nsi; + struct nsinfo *nnsi; + int rc = -1; + + nsi = *nsip; + + if (nsi->need_setns) { + snprintf(filebuf, bufsz, "/tmp/perf-%d.map", nsi->nstgid); + nsinfo__mountns_enter(nsi, &nsc); + rc = access(filebuf, R_OK); + nsinfo__mountns_exit(&nsc); + if (rc == 0) + return rc; + } + + nnsi = nsinfo__copy(nsi); + if (nnsi) { + nsinfo__put(nsi); + + nnsi->need_setns = false; + snprintf(filebuf, bufsz, "/tmp/perf-%d.map", nnsi->tgid); + *nsip = nnsi; + rc = 0; + } + + return rc; +} + int dso__load(struct dso *dso, struct map *map) { char *name; @@ -1435,8 +1484,21 @@ int dso__load(struct dso *dso, struct map *map) struct symsrc ss_[2]; struct symsrc *syms_ss = NULL, *runtime_ss = NULL; bool kmod; + bool perfmap; unsigned char build_id[BUILD_ID_SIZE]; + struct nscookie nsc; + char newmapname[PATH_MAX]; + const char *map_path = dso->long_name; + + perfmap = strncmp(dso->name, "/tmp/perf-", 10) == 0; + if (perfmap) { + if (dso->nsinfo && (dso__find_perf_map(newmapname, + sizeof(newmapname), &dso->nsinfo) == 0)) { + map_path = newmapname; + } + } + nsinfo__mountns_enter(dso->nsinfo, &nsc); pthread_mutex_lock(&dso->lock); /* check again under the dso->lock */ @@ -1461,19 +1523,19 @@ int dso__load(struct dso *dso, struct map *map) dso->adjust_symbols = 0; - if (strncmp(dso->name, "/tmp/perf-", 10) == 0) { + if (perfmap) { struct stat st; - if (lstat(dso->name, &st) < 0) + if (lstat(map_path, &st) < 0) goto out; if (!symbol_conf.force && st.st_uid && (st.st_uid != geteuid())) { pr_warning("File %s not owned by current user or root, " - "ignoring it (use -f to override).\n", dso->name); + "ignoring it (use -f to override).\n", map_path); goto out; } - ret = dso__load_perf_map(dso, map); + ret = dso__load_perf_map(map_path, dso, map); dso->symtab_type = ret > 0 ? DSO_BINARY_TYPE__JAVA_JIT : DSO_BINARY_TYPE__NOT_FOUND; goto out; @@ -1511,9 +1573,15 @@ int dso__load(struct dso *dso, struct map *map) for (i = 0; i < DSO_BINARY_TYPE__SYMTAB_CNT; i++) { struct symsrc *ss = &ss_[ss_pos]; bool next_slot = false; + bool is_reg; + bool nsexit; + int sirc; enum dso_binary_type symtab_type = binary_type_symtab[i]; + nsexit = (symtab_type == DSO_BINARY_TYPE__BUILD_ID_CACHE || + symtab_type == DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO); + if (!dso__is_compatible_symtab_type(dso, kmod, symtab_type)) continue; @@ -1521,12 +1589,20 @@ int dso__load(struct dso *dso, struct map *map) root_dir, name, PATH_MAX)) continue; - if (!is_regular_file(name)) - continue; + if (nsexit) + nsinfo__mountns_exit(&nsc); + + is_reg = is_regular_file(name); + sirc = symsrc__init(ss, dso, name, symtab_type); - /* Name is now the name of the next image to try */ - if (symsrc__init(ss, dso, name, symtab_type) < 0) + if (nsexit) + nsinfo__mountns_enter(dso->nsinfo, &nsc); + + if (!is_reg || sirc < 0) { + if (sirc >= 0) + symsrc__destroy(ss); continue; + } if (!syms_ss && symsrc__has_symtab(ss)) { syms_ss = ss; @@ -1584,6 +1660,7 @@ out_free: out: dso__set_loaded(dso, map->type); pthread_mutex_unlock(&dso->lock); + nsinfo__mountns_exit(&nsc); return ret; } @@ -1660,7 +1737,7 @@ int dso__load_vmlinux_path(struct dso *dso, struct map *map) } if (!symbol_conf.ignore_vmlinux_buildid) - filename = dso__build_id_filename(dso, NULL, 0); + filename = dso__build_id_filename(dso, NULL, 0, false); if (filename != NULL) { err = dso__load_vmlinux(dso, map, filename, true); if (err > 0) diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 41ebba9a2eb2..2bd6a1f01a1c 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -186,6 +186,7 @@ struct addr_map_symbol { struct symbol *sym; u64 addr; u64 al_addr; + u64 phys_addr; }; struct branch_info { @@ -273,7 +274,7 @@ int filename__read_build_id(const char *filename, void *bf, size_t size); int sysfs__read_build_id(const char *filename, void *bf, size_t size); int modules__parse(const char *filename, void *arg, int (*process_module)(void *arg, const char *name, - u64 start)); + u64 start, u64 size)); int filename__read_debuglink(const char *filename, char *debuglink, size_t size); @@ -306,7 +307,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *map); -char *dso__demangle_sym(struct dso *dso, int kmodule, char *elf_name); +char *dso__demangle_sym(struct dso *dso, int kmodule, const char *elf_name); void __symbols__insert(struct rb_root *symbols, struct symbol *sym, bool kernel); void symbols__insert(struct rb_root *symbols, struct symbol *sym); @@ -343,6 +344,9 @@ int setup_intlist(struct intlist **list, const char *list_str, #ifdef HAVE_LIBELF_SUPPORT bool elf__needs_adjust_symbols(GElf_Ehdr ehdr); void arch__sym_update(struct symbol *s, GElf_Sym *sym); +void arch__adjust_sym_map_offset(GElf_Sym *sym, + GElf_Shdr *shdr __maybe_unused, + struct map *map __maybe_unused); #endif #define SYMBOL_A 0 diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c index bbb4c1957578..19e5db90394c 100644 --- a/tools/perf/util/syscalltbl.c +++ b/tools/perf/util/syscalltbl.c @@ -19,6 +19,7 @@ #ifdef HAVE_SYSCALL_TABLE #include <linux/compiler.h> #include <string.h> +#include "string2.h" #include "util.h" #if defined(__x86_64__) @@ -105,6 +106,27 @@ int syscalltbl__id(struct syscalltbl *tbl, const char *name) return sc ? sc->id : -1; } +int syscalltbl__strglobmatch_next(struct syscalltbl *tbl, const char *syscall_glob, int *idx) +{ + int i; + struct syscall *syscalls = tbl->syscalls.entries; + + for (i = *idx + 1; i < tbl->syscalls.nr_entries; ++i) { + if (strglobmatch(syscalls[i].name, syscall_glob)) { + *idx = i; + return syscalls[i].id; + } + } + + return -1; +} + +int syscalltbl__strglobmatch_first(struct syscalltbl *tbl, const char *syscall_glob, int *idx) +{ + *idx = -1; + return syscalltbl__strglobmatch_next(tbl, syscall_glob, idx); +} + #else /* HAVE_SYSCALL_TABLE */ #include <libaudit.h> @@ -131,4 +153,15 @@ int syscalltbl__id(struct syscalltbl *tbl, const char *name) { return audit_name_to_syscall(name, tbl->audit_machine); } + +int syscalltbl__strglobmatch_next(struct syscalltbl *tbl __maybe_unused, + const char *syscall_glob __maybe_unused, int *idx __maybe_unused) +{ + return -1; +} + +int syscalltbl__strglobmatch_first(struct syscalltbl *tbl, const char *syscall_glob, int *idx) +{ + return syscalltbl__strglobmatch_next(tbl, syscall_glob, idx); +} #endif /* HAVE_SYSCALL_TABLE */ diff --git a/tools/perf/util/syscalltbl.h b/tools/perf/util/syscalltbl.h index e2951510484f..e9fb8786da7c 100644 --- a/tools/perf/util/syscalltbl.h +++ b/tools/perf/util/syscalltbl.h @@ -17,4 +17,7 @@ void syscalltbl__delete(struct syscalltbl *tbl); const char *syscalltbl__name(const struct syscalltbl *tbl, int id); int syscalltbl__id(struct syscalltbl *tbl, const char *name); +int syscalltbl__strglobmatch_first(struct syscalltbl *tbl, const char *syscall_glob, int *idx); +int syscalltbl__strglobmatch_next(struct syscalltbl *tbl, const char *syscall_glob, int *idx); + #endif /* __PERF_SYSCALLTBL_H */ diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 378c418ca0c1..aee9a42102ba 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -59,6 +59,8 @@ struct thread *thread__new(pid_t pid, pid_t tid) list_add(&comm->list, &thread->comm_list); refcount_set(&thread->refcnt, 1); RB_CLEAR_NODE(&thread->rb_node); + /* Thread holds first ref to nsdata. */ + thread->nsinfo = nsinfo__new(pid); } return thread; @@ -91,6 +93,7 @@ void thread__delete(struct thread *thread) comm__free(comm); } unwind__finish_access(thread); + nsinfo__zput(thread->nsinfo); free(thread); } diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index 4eb849e9098f..cb1a5dd5c2b9 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -34,6 +34,7 @@ struct thread { void *priv; struct thread_stack *ts; + struct nsinfo *nsinfo; #ifdef HAVE_LIBUNWIND_SUPPORT void *addr_space; struct unwind_libunwind_ops *unwind_libunwind_ops; diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h index 829471a1c6d7..d549e50db397 100644 --- a/tools/perf/util/tool.h +++ b/tools/perf/util/tool.h @@ -34,6 +34,12 @@ typedef int (*event_oe)(struct perf_tool *tool, union perf_event *event, typedef s64 (*event_op3)(struct perf_tool *tool, union perf_event *event, struct perf_session *session); +enum show_feature_header { + SHOW_FEAT_NO_HEADER = 0, + SHOW_FEAT_HEADER, + SHOW_FEAT_HEADER_FULL_INFO, +}; + struct perf_tool { event_sample sample, read; @@ -63,11 +69,13 @@ struct perf_tool { cpu_map, stat_config, stat, - stat_round; + stat_round, + feature; event_op3 auxtrace; bool ordered_events; bool ordering_requires_timestamps; bool namespace_events; + enum show_feature_header show_feat_hdr; }; #endif /* __PERF_TOOL_H */ diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index 746bbee645d9..e0a6e9a6a053 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -24,7 +24,7 @@ #include <errno.h> #include "../perf.h" -#include "util.h" +#include "debug.h" #include "trace-event.h" #include "sane_ctype.h" @@ -150,7 +150,7 @@ void parse_ftrace_printk(struct pevent *pevent, while (line) { addr_str = strtok_r(line, ":", &fmt); if (!addr_str) { - warning("printk format with empty entry"); + pr_warning("printk format with empty entry"); break; } addr = strtoull(addr_str, NULL, 16); diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c index 6d542a4e0648..8aef572d0889 100644 --- a/tools/perf/util/unwind-libunwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -50,7 +50,7 @@ int unwind__prepare_access(struct thread *thread, struct map *map, if (!ops) { pr_err("unwind: target platform=%s is not supported\n", arch); - return -1; + return 0; } out_register: unwind__register_ops(thread, ops); diff --git a/tools/perf/util/usage.c b/tools/perf/util/usage.c index 996046a66fe5..6cc9d9888ce0 100644 --- a/tools/perf/util/usage.c +++ b/tools/perf/util/usage.c @@ -9,75 +9,17 @@ #include "util.h" #include "debug.h" -static void report(const char *prefix, const char *err, va_list params) -{ - char msg[1024]; - vsnprintf(msg, sizeof(msg), err, params); - fprintf(stderr, " %s%s\n", prefix, msg); -} - -static NORETURN void usage_builtin(const char *err) +static __noreturn void usage_builtin(const char *err) { fprintf(stderr, "\n Usage: %s\n", err); exit(129); } -static NORETURN void die_builtin(const char *err, va_list params) -{ - report(" Fatal: ", err, params); - exit(128); -} - -static void error_builtin(const char *err, va_list params) -{ - report(" Error: ", err, params); -} - -static void warn_builtin(const char *warn, va_list params) -{ - report(" Warning: ", warn, params); -} - /* If we are in a dlopen()ed .so write to a global variable would segfault * (ugh), so keep things static. */ -static void (*usage_routine)(const char *err) NORETURN = usage_builtin; -static void (*error_routine)(const char *err, va_list params) = error_builtin; -static void (*warn_routine)(const char *err, va_list params) = warn_builtin; - -void set_warning_routine(void (*routine)(const char *err, va_list params)) -{ - warn_routine = routine; -} +static void (*usage_routine)(const char *err) __noreturn = usage_builtin; void usage(const char *err) { usage_routine(err); } - -void die(const char *err, ...) -{ - va_list params; - - va_start(params, err); - die_builtin(err, params); - va_end(params); -} - -int error(const char *err, ...) -{ - va_list params; - - va_start(params, err); - error_routine(err, params); - va_end(params); - return -1; -} - -void warning(const char *warn, ...) -{ - va_list params; - - va_start(params, warn); - warn_routine(warn, params); - va_end(params); -} diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 28c9f335006c..4c360daa4e24 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -143,13 +143,17 @@ out: return list; } -static int slow_copyfile(const char *from, const char *to) +static int slow_copyfile(const char *from, const char *to, struct nsinfo *nsi) { int err = -1; char *line = NULL; size_t n; - FILE *from_fp = fopen(from, "r"), *to_fp; + FILE *from_fp, *to_fp; + struct nscookie nsc; + nsinfo__mountns_enter(nsi, &nsc); + from_fp = fopen(from, "r"); + nsinfo__mountns_exit(&nsc); if (from_fp == NULL) goto out; @@ -198,15 +202,21 @@ int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size) return size ? -1 : 0; } -int copyfile_mode(const char *from, const char *to, mode_t mode) +static int copyfile_mode_ns(const char *from, const char *to, mode_t mode, + struct nsinfo *nsi) { int fromfd, tofd; struct stat st; - int err = -1; + int err; char *tmp = NULL, *ptr = NULL; + struct nscookie nsc; - if (stat(from, &st)) + nsinfo__mountns_enter(nsi, &nsc); + err = stat(from, &st); + nsinfo__mountns_exit(&nsc); + if (err) goto out; + err = -1; /* extra 'x' at the end is to reserve space for '.' */ if (asprintf(&tmp, "%s.XXXXXXx", to) < 0) { @@ -227,11 +237,13 @@ int copyfile_mode(const char *from, const char *to, mode_t mode) goto out_close_to; if (st.st_size == 0) { /* /proc? do it slowly... */ - err = slow_copyfile(from, tmp); + err = slow_copyfile(from, tmp, nsi); goto out_close_to; } + nsinfo__mountns_enter(nsi, &nsc); fromfd = open(from, O_RDONLY); + nsinfo__mountns_exit(&nsc); if (fromfd < 0) goto out_close_to; @@ -248,6 +260,16 @@ out: return err; } +int copyfile_ns(const char *from, const char *to, struct nsinfo *nsi) +{ + return copyfile_mode_ns(from, to, 0755, nsi); +} + +int copyfile_mode(const char *from, const char *to, mode_t mode) +{ + return copyfile_mode_ns(from, to, mode, NULL); +} + int copyfile(const char *from, const char *to) { return copyfile_mode(from, to, 0755); @@ -259,6 +281,7 @@ static ssize_t ion(bool is_read, int fd, void *buf, size_t n) size_t left = n; while (left) { + /* buf must be treated as const if !is_read. */ ssize_t ret = is_read ? read(fd, buf, left) : write(fd, buf, left); @@ -286,9 +309,10 @@ ssize_t readn(int fd, void *buf, size_t n) /* * Write exactly 'n' bytes or return an error. */ -ssize_t writen(int fd, void *buf, size_t n) +ssize_t writen(int fd, const void *buf, size_t n) { - return ion(false, fd, buf, n); + /* ion does not modify buf. */ + return ion(false, fd, (void *)buf, n); } size_t hex_width(u64 v) @@ -343,43 +367,6 @@ int perf_event_paranoid(void) return value; } - -bool find_process(const char *name) -{ - size_t len = strlen(name); - DIR *dir; - struct dirent *d; - int ret = -1; - - dir = opendir(procfs__mountpoint()); - if (!dir) - return false; - - /* Walk through the directory. */ - while (ret && (d = readdir(dir)) != NULL) { - char path[PATH_MAX]; - char *data; - size_t size; - - if ((d->d_type != DT_DIR) || - !strcmp(".", d->d_name) || - !strcmp("..", d->d_name)) - continue; - - scnprintf(path, sizeof(path), "%s/%s/comm", - procfs__mountpoint(), d->d_name); - - if (filename__read_str(path, &data, &size)) - continue; - - ret = strncmp(name, data, len); - free(data); - } - - closedir(dir); - return ret ? false : true; -} - static int fetch_ubuntu_kernel_version(unsigned int *puint) { @@ -387,8 +374,12 @@ fetch_ubuntu_kernel_version(unsigned int *puint) size_t line_len = 0; char *ptr, *line = NULL; int version, patchlevel, sublevel, err; - FILE *vsig = fopen("/proc/version_signature", "r"); + FILE *vsig; + if (!puint) + return 0; + + vsig = fopen("/proc/version_signature", "r"); if (!vsig) { pr_debug("Open /proc/version_signature failed: %s\n", strerror(errno)); @@ -418,8 +409,7 @@ fetch_ubuntu_kernel_version(unsigned int *puint) goto errout; } - if (puint) - *puint = (version << 16) + (patchlevel << 8) + sublevel; + *puint = (version << 16) + (patchlevel << 8) + sublevel; err = 0; errout: free(line); @@ -446,6 +436,9 @@ fetch_kernel_version(unsigned int *puint, char *str, str[str_size - 1] = '\0'; } + if (!puint || int_ver_ready) + return 0; + err = sscanf(utsname.release, "%d.%d.%d", &version, &patchlevel, &sublevel); @@ -455,8 +448,7 @@ fetch_kernel_version(unsigned int *puint, char *str, return -1; } - if (puint && !int_ver_ready) - *puint = (version << 16) + (patchlevel << 8) + sublevel; + *puint = (version << 16) + (patchlevel << 8) + sublevel; return 0; } diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 5dfb9bb6482d..b136c271125f 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -1,7 +1,6 @@ #ifndef GIT_COMPAT_UTIL_H #define GIT_COMPAT_UTIL_H -#define _ALL_SOURCE 1 #define _BSD_SOURCE 1 /* glibc 2.20 deprecates _BSD_SOURCE in favour of _DEFAULT_SOURCE */ #define _DEFAULT_SOURCE 1 @@ -11,24 +10,13 @@ #include <stddef.h> #include <stdlib.h> #include <stdarg.h> +#include <linux/compiler.h> #include <linux/types.h> - -#ifdef __GNUC__ -#define NORETURN __attribute__((__noreturn__)) -#else -#define NORETURN -#ifndef __attribute__ -#define __attribute__(x) -#endif -#endif +#include "namespaces.h" /* General helper functions */ -void usage(const char *err) NORETURN; -void die(const char *err, ...) NORETURN __attribute__((format (printf, 1, 2))); -int error(const char *err, ...) __attribute__((format (printf, 1, 2))); -void warning(const char *err, ...) __attribute__((format (printf, 1, 2))); - -void set_warning_routine(void (*routine)(const char *err, va_list params)); +void usage(const char *err) __noreturn; +void die(const char *err, ...) __noreturn __printf(1, 2); static inline void *zalloc(size_t size) { @@ -46,10 +34,11 @@ struct strlist *lsdir(const char *name, bool (*filter)(const char *, struct dire bool lsdir_no_dot_filter(const char *name, struct dirent *d); int copyfile(const char *from, const char *to); int copyfile_mode(const char *from, const char *to, mode_t mode); +int copyfile_ns(const char *from, const char *to, struct nsinfo *nsi); int copyfile_offset(int fromfd, loff_t from_ofs, int tofd, loff_t to_ofs, u64 size); ssize_t readn(int fd, void *buf, size_t n); -ssize_t writen(int fd, void *buf, size_t n); +ssize_t writen(int fd, const void *buf, size_t n); size_t hex_width(u64 v); int hex2u64(const char *ptr, u64 *val); @@ -57,8 +46,6 @@ int hex2u64(const char *ptr, u64 *val); extern unsigned int page_size; extern int cacheline_size; -bool find_process(const char *name); - int fetch_kernel_version(unsigned int *puint, char *str, size_t str_sz); #define KVER_VERSION(x) (((x) >> 16) & 0xff) @@ -73,4 +60,8 @@ const char *perf_tip(const char *dirpath); int sched_getcpu(void); #endif +#ifndef HAVE_SETNS_SUPPORT +int setns(int fd, int nstype); +#endif + #endif /* GIT_COMPAT_UTIL_H */ diff --git a/tools/perf/util/values.c b/tools/perf/util/values.c index 5de2e15e2eda..8a32bb0095e5 100644 --- a/tools/perf/util/values.c +++ b/tools/perf/util/values.c @@ -12,7 +12,7 @@ int perf_read_values_init(struct perf_read_values *values) values->threads_max = 16; values->pid = malloc(values->threads_max * sizeof(*values->pid)); values->tid = malloc(values->threads_max * sizeof(*values->tid)); - values->value = malloc(values->threads_max * sizeof(*values->value)); + values->value = zalloc(values->threads_max * sizeof(*values->value)); if (!values->pid || !values->tid || !values->value) { pr_debug("failed to allocate read_values threads arrays"); goto out_free_pid; @@ -98,15 +98,16 @@ static int perf_read_values__findnew_thread(struct perf_read_values *values, return i; } - i = values->threads + 1; - values->value[i] = malloc(values->counters_max * sizeof(**values->value)); + i = values->threads; + + values->value[i] = zalloc(values->counters_max * sizeof(**values->value)); if (!values->value[i]) { pr_debug("failed to allocate read_values counters array"); return -ENOMEM; } values->pid[i] = pid; values->tid[i] = tid; - values->threads = i; + values->threads = i + 1; return i; } @@ -130,12 +131,16 @@ static int perf_read_values__enlarge_counters(struct perf_read_values *values) for (i = 0; i < values->threads; i++) { u64 *value = realloc(values->value[i], counters_max * sizeof(**values->value)); + int j; - if (value) { + if (!value) { pr_debug("failed to enlarge read_values ->values array"); goto out_free_name; } + for (j = values->counters_max; j < counters_max; j++) + value[j] = 0; + values->value[i] = value; } @@ -187,7 +192,7 @@ int perf_read_values_add_value(struct perf_read_values *values, if (cindex < 0) return cindex; - values->value[tindex][cindex] = value; + values->value[tindex][cindex] += value; return 0; } diff --git a/tools/perf/util/xyarray.c b/tools/perf/util/xyarray.c index 7251fdbabced..c8f415d9877b 100644 --- a/tools/perf/util/xyarray.c +++ b/tools/perf/util/xyarray.c @@ -12,6 +12,8 @@ struct xyarray *xyarray__new(int xlen, int ylen, size_t entry_size) xy->entry_size = entry_size; xy->row_size = row_size; xy->entries = xlen * ylen; + xy->max_x = xlen; + xy->max_y = ylen; } return xy; diff --git a/tools/perf/util/xyarray.h b/tools/perf/util/xyarray.h index 7f30af371b7e..4ba726c90870 100644 --- a/tools/perf/util/xyarray.h +++ b/tools/perf/util/xyarray.h @@ -7,6 +7,8 @@ struct xyarray { size_t row_size; size_t entry_size; size_t entries; + size_t max_x; + size_t max_y; char contents[]; }; @@ -19,4 +21,14 @@ static inline void *xyarray__entry(struct xyarray *xy, int x, int y) return &xy->contents[x * xy->row_size + y * xy->entry_size]; } +static inline int xyarray__max_y(struct xyarray *xy) +{ + return xy->max_x; +} + +static inline int xyarray__max_x(struct xyarray *xy) +{ + return xy->max_y; +} + #endif /* _PERF_XYARRAY_H_ */ diff --git a/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c b/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c index 82a2ff896a95..52a39ecf5ca1 100644 --- a/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c +++ b/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c @@ -759,7 +759,7 @@ static acpi_status osl_list_bios_tables(void) /* Skip NULL entries in RSDT/XSDT */ - if (!table_address) { + if (table_address == 0) { continue; } @@ -808,7 +808,8 @@ osl_get_bios_table(char *signature, u8 number_of_tables; u8 item_size; u32 current_instance = 0; - acpi_physical_address table_address = 0; + acpi_physical_address table_address; + acpi_physical_address first_table_address = 0; u32 table_length = 0; acpi_status status = AE_OK; u32 i; @@ -820,9 +821,10 @@ osl_get_bios_table(char *signature, ACPI_COMPARE_NAME(signature, ACPI_SIG_XSDT) || ACPI_COMPARE_NAME(signature, ACPI_SIG_DSDT) || ACPI_COMPARE_NAME(signature, ACPI_SIG_FACS)) { - if (instance > 0) { - return (AE_LIMIT); - } + +find_next_instance: + + table_address = 0; /* * Get the appropriate address, either 32-bit or 64-bit. Be very @@ -830,41 +832,66 @@ osl_get_bios_table(char *signature, * Note: The 64-bit addresses have priority. */ if (ACPI_COMPARE_NAME(signature, ACPI_SIG_DSDT)) { - if ((gbl_fadt->header.length >= MIN_FADT_FOR_XDSDT) && - gbl_fadt->Xdsdt) { - table_address = - (acpi_physical_address)gbl_fadt->Xdsdt; - } else - if ((gbl_fadt->header.length >= MIN_FADT_FOR_DSDT) - && gbl_fadt->dsdt) { - table_address = - (acpi_physical_address)gbl_fadt->dsdt; + if (current_instance < 2) { + if ((gbl_fadt->header.length >= + MIN_FADT_FOR_XDSDT) && gbl_fadt->Xdsdt + && current_instance == 0) { + table_address = + (acpi_physical_address)gbl_fadt-> + Xdsdt; + } else + if ((gbl_fadt->header.length >= + MIN_FADT_FOR_DSDT) + && gbl_fadt->dsdt != + first_table_address) { + table_address = + (acpi_physical_address)gbl_fadt-> + dsdt; + } } } else if (ACPI_COMPARE_NAME(signature, ACPI_SIG_FACS)) { - if ((gbl_fadt->header.length >= MIN_FADT_FOR_XFACS) && - gbl_fadt->Xfacs) { - table_address = - (acpi_physical_address)gbl_fadt->Xfacs; - } else - if ((gbl_fadt->header.length >= MIN_FADT_FOR_FACS) - && gbl_fadt->facs) { - table_address = - (acpi_physical_address)gbl_fadt->facs; + if (current_instance < 2) { + if ((gbl_fadt->header.length >= + MIN_FADT_FOR_XFACS) && gbl_fadt->Xfacs + && current_instance == 0) { + table_address = + (acpi_physical_address)gbl_fadt-> + Xfacs; + } else + if ((gbl_fadt->header.length >= + MIN_FADT_FOR_FACS) + && gbl_fadt->facs != + first_table_address) { + table_address = + (acpi_physical_address)gbl_fadt-> + facs; + } } } else if (ACPI_COMPARE_NAME(signature, ACPI_SIG_XSDT)) { if (!gbl_revision) { return (AE_BAD_SIGNATURE); } - table_address = - (acpi_physical_address)gbl_rsdp. - xsdt_physical_address; + if (current_instance == 0) { + table_address = + (acpi_physical_address)gbl_rsdp. + xsdt_physical_address; + } } else if (ACPI_COMPARE_NAME(signature, ACPI_SIG_RSDT)) { - table_address = - (acpi_physical_address)gbl_rsdp. - rsdt_physical_address; + if (current_instance == 0) { + table_address = + (acpi_physical_address)gbl_rsdp. + rsdt_physical_address; + } } else { - table_address = (acpi_physical_address)gbl_rsdp_address; - signature = ACPI_SIG_RSDP; + if (current_instance == 0) { + table_address = + (acpi_physical_address)gbl_rsdp_address; + signature = ACPI_SIG_RSDP; + } + } + + if (table_address == 0) { + goto exit_find_table; } /* Now we can get the requested special table */ @@ -875,6 +902,18 @@ osl_get_bios_table(char *signature, } table_length = ap_get_table_length(mapped_table); + if (first_table_address == 0) { + first_table_address = table_address; + } + + /* Match table instance */ + + if (current_instance != instance) { + osl_unmap_table(mapped_table); + mapped_table = NULL; + current_instance++; + goto find_next_instance; + } } else { /* Case for a normal ACPI table */ if (osl_can_use_xsdt()) { @@ -913,7 +952,7 @@ osl_get_bios_table(char *signature, /* Skip NULL entries in RSDT/XSDT */ - if (!table_address) { + if (table_address == 0) { continue; } @@ -946,6 +985,8 @@ osl_get_bios_table(char *signature, } } +exit_find_table: + if (!mapped_table) { return (AE_LIMIT); } diff --git a/tools/power/acpi/os_specific/service_layers/osunixxf.c b/tools/power/acpi/os_specific/service_layers/osunixxf.c index c04e8fea2c60..025c1b07049d 100644 --- a/tools/power/acpi/os_specific/service_layers/osunixxf.c +++ b/tools/power/acpi/os_specific/service_layers/osunixxf.c @@ -750,9 +750,9 @@ acpi_os_wait_semaphore(acpi_handle handle, u32 units, u16 msec_timeout) { acpi_status status = AE_OK; sem_t *sem = (sem_t *) handle; + int ret_val; #ifndef ACPI_USE_ALTERNATE_TIMEOUT struct timespec time; - int ret_val; #endif if (!sem) { @@ -778,7 +778,10 @@ acpi_os_wait_semaphore(acpi_handle handle, u32 units, u16 msec_timeout) case ACPI_WAIT_FOREVER: - if (sem_wait(sem)) { + while (((ret_val = sem_wait(sem)) == -1) && (errno == EINTR)) { + continue; /* Restart if interrupted */ + } + if (ret_val != 0) { status = (AE_TIME); } break; @@ -831,7 +834,8 @@ acpi_os_wait_semaphore(acpi_handle handle, u32 units, u16 msec_timeout) while (((ret_val = sem_timedwait(sem, &time)) == -1) && (errno == EINTR)) { - continue; + continue; /* Restart if interrupted */ + } if (ret_val != 0) { diff --git a/tools/power/acpi/tools/acpidump/apfiles.c b/tools/power/acpi/tools/acpidump/apfiles.c index 31b5a7f74015..d686e11936c4 100644 --- a/tools/power/acpi/tools/acpidump/apfiles.c +++ b/tools/power/acpi/tools/acpidump/apfiles.c @@ -61,7 +61,7 @@ static int ap_is_existing_file(char *pathname); static int ap_is_existing_file(char *pathname) { -#ifndef _GNU_EFI +#if !defined(_GNU_EFI) && !defined(_EDK2_EFI) struct stat stat_info; if (!stat(pathname, &stat_info)) { diff --git a/tools/power/acpi/tools/acpidump/apmain.c b/tools/power/acpi/tools/acpidump/apmain.c index dd82afa897bd..943b6b614683 100644 --- a/tools/power/acpi/tools/acpidump/apmain.c +++ b/tools/power/acpi/tools/acpidump/apmain.c @@ -300,7 +300,7 @@ static int ap_do_options(int argc, char **argv) * ******************************************************************************/ -#ifndef _GNU_EFI +#if !defined(_GNU_EFI) && !defined(_EDK2_EFI) int ACPI_SYSTEM_XFACE main(int argc, char *argv[]) #else int ACPI_SYSTEM_XFACE acpi_main(int argc, char *argv[]) diff --git a/tools/power/cpupower/Makefile b/tools/power/cpupower/Makefile index d6e1c02ddcfe..4c5a481a850c 100644 --- a/tools/power/cpupower/Makefile +++ b/tools/power/cpupower/Makefile @@ -26,7 +26,7 @@ endif ifneq ($(OUTPUT),) # check that the output directory actually exists -OUTDIR := $(shell cd $(OUTPUT) && /bin/pwd) +OUTDIR := $(realpath $(OUTPUT)) $(if $(OUTDIR),, $(error output directory "$(OUTPUT)" does not exist)) endif diff --git a/tools/power/cpupower/utils/cpupower.c b/tools/power/cpupower/utils/cpupower.c index 9ea914378985..2dccf4998599 100644 --- a/tools/power/cpupower/utils/cpupower.c +++ b/tools/power/cpupower/utils/cpupower.c @@ -12,6 +12,7 @@ #include <string.h> #include <unistd.h> #include <errno.h> +#include <sched.h> #include <sys/types.h> #include <sys/stat.h> #include <sys/utsname.h> @@ -31,6 +32,7 @@ static int cmd_help(int argc, const char **argv); */ struct cpupower_cpu_info cpupower_cpu_info; int run_as_root; +int base_cpu; /* Affected cpus chosen by -c/--cpu param */ struct bitmask *cpus_chosen; @@ -174,6 +176,7 @@ int main(int argc, const char *argv[]) unsigned int i, ret; struct stat statbuf; struct utsname uts; + char pathname[32]; cpus_chosen = bitmask_alloc(sysconf(_SC_NPROCESSORS_CONF)); @@ -198,17 +201,23 @@ int main(int argc, const char *argv[]) argv[0] = cmd = "help"; } - get_cpu_info(0, &cpupower_cpu_info); + base_cpu = sched_getcpu(); + if (base_cpu < 0) { + fprintf(stderr, _("No valid cpus found.\n")); + return EXIT_FAILURE; + } + + get_cpu_info(&cpupower_cpu_info); run_as_root = !geteuid(); if (run_as_root) { ret = uname(&uts); + sprintf(pathname, "/dev/cpu/%d/msr", base_cpu); if (!ret && !strcmp(uts.machine, "x86_64") && - stat("/dev/cpu/0/msr", &statbuf) != 0) { + stat(pathname, &statbuf) != 0) { if (system("modprobe msr") == -1) fprintf(stderr, _("MSR access not available.\n")); } } - for (i = 0; i < ARRAY_SIZE(commands); i++) { struct cmd_struct *p = commands + i; diff --git a/tools/power/cpupower/utils/helpers/amd.c b/tools/power/cpupower/utils/helpers/amd.c index 6437ef39aeea..5fd5c5b8c7b8 100644 --- a/tools/power/cpupower/utils/helpers/amd.c +++ b/tools/power/cpupower/utils/helpers/amd.c @@ -26,6 +26,15 @@ union msr_pstate { unsigned res3:21; unsigned en:1; } bits; + struct { + unsigned fid:8; + unsigned did:6; + unsigned vid:8; + unsigned iddval:8; + unsigned idddiv:2; + unsigned res1:30; + unsigned en:1; + } fam17h_bits; unsigned long long val; }; @@ -35,6 +44,8 @@ static int get_did(int family, union msr_pstate pstate) if (family == 0x12) t = pstate.val & 0xf; + else if (family == 0x17) + t = pstate.fam17h_bits.did; else t = pstate.bits.did; @@ -44,16 +55,20 @@ static int get_did(int family, union msr_pstate pstate) static int get_cof(int family, union msr_pstate pstate) { int t; - int fid, did; + int fid, did, cof; did = get_did(family, pstate); - - t = 0x10; - fid = pstate.bits.fid; - if (family == 0x11) - t = 0x8; - - return (100 * (fid + t)) >> did; + if (family == 0x17) { + fid = pstate.fam17h_bits.fid; + cof = 200 * fid / did; + } else { + t = 0x10; + fid = pstate.bits.fid; + if (family == 0x11) + t = 0x8; + cof = (100 * (fid + t)) >> did; + } + return cof; } /* Needs: diff --git a/tools/power/cpupower/utils/helpers/cpuid.c b/tools/power/cpupower/utils/helpers/cpuid.c index 39c2c7d067bb..32d37c9be791 100644 --- a/tools/power/cpupower/utils/helpers/cpuid.c +++ b/tools/power/cpupower/utils/helpers/cpuid.c @@ -42,7 +42,7 @@ cpuid_func(edx); * * TBD: Should there be a cpuid alternative for this if /proc is not mounted? */ -int get_cpu_info(unsigned int cpu, struct cpupower_cpu_info *cpu_info) +int get_cpu_info(struct cpupower_cpu_info *cpu_info) { FILE *fp; char value[64]; @@ -70,7 +70,7 @@ int get_cpu_info(unsigned int cpu, struct cpupower_cpu_info *cpu_info) if (!strncmp(value, "processor\t: ", 12)) sscanf(value, "processor\t: %u", &proc); - if (proc != cpu) + if (proc != (unsigned int)base_cpu) continue; /* Get CPU vendor */ diff --git a/tools/power/cpupower/utils/helpers/helpers.h b/tools/power/cpupower/utils/helpers/helpers.h index afb66f80554e..41da392be448 100644 --- a/tools/power/cpupower/utils/helpers/helpers.h +++ b/tools/power/cpupower/utils/helpers/helpers.h @@ -34,6 +34,7 @@ /* Internationalization ****************************/ extern int run_as_root; +extern int base_cpu; extern struct bitmask *cpus_chosen; /* Global verbose (-d) stuff *********************************/ @@ -70,6 +71,8 @@ enum cpupower_cpu_vendor {X86_VENDOR_UNKNOWN = 0, X86_VENDOR_INTEL, #define CPUPOWER_CAP_IS_SNB 0x00000020 #define CPUPOWER_CAP_INTEL_IDA 0x00000040 +#define CPUPOWER_AMD_CPBDIS 0x02000000 + #define MAX_HW_PSTATES 10 struct cpupower_cpu_info { @@ -85,11 +88,11 @@ struct cpupower_cpu_info { * * Extract CPU vendor, family, model, stepping info from /proc/cpuinfo * - * Returns 0 on success or a negativ error code + * Returns 0 on success or a negative error code * Only used on x86, below global's struct values are zero/unknown on * other archs */ -extern int get_cpu_info(unsigned int cpu, struct cpupower_cpu_info *cpu_info); +extern int get_cpu_info(struct cpupower_cpu_info *cpu_info); extern struct cpupower_cpu_info cpupower_cpu_info; /* cpuid and cpuinfo helpers **************************/ diff --git a/tools/power/cpupower/utils/helpers/misc.c b/tools/power/cpupower/utils/helpers/misc.c index 1609243f5c64..a5e7ddf19dbd 100644 --- a/tools/power/cpupower/utils/helpers/misc.c +++ b/tools/power/cpupower/utils/helpers/misc.c @@ -2,24 +2,39 @@ #include "helpers/helpers.h" +#define MSR_AMD_HWCR 0xc0010015 + int cpufreq_has_boost_support(unsigned int cpu, int *support, int *active, int *states) { struct cpupower_cpu_info cpu_info; int ret; + unsigned long long val; *support = *active = *states = 0; - ret = get_cpu_info(0, &cpu_info); + ret = get_cpu_info(&cpu_info); if (ret) return ret; if (cpupower_cpu_info.caps & CPUPOWER_CAP_AMD_CBP) { *support = 1; - amd_pci_get_num_boost_states(active, states); - if (ret <= 0) - return ret; - *support = 1; + + /* AMD Family 0x17 does not utilize PCI D18F4 like prior + * families and has no fixed discrete boost states but + * has Hardware determined variable increments instead. + */ + + if (cpu_info.family == 0x17) { + if (!read_msr(cpu, MSR_AMD_HWCR, &val)) { + if (!(val & CPUPOWER_AMD_CPBDIS)) + *active = 1; + } + } else { + ret = amd_pci_get_num_boost_states(active, states); + if (ret) + return ret; + } } else if (cpupower_cpu_info.caps & CPUPOWER_CAP_INTEL_IDA) *support = *active = 1; return 0; diff --git a/tools/power/cpupower/utils/idle_monitor/hsw_ext_idle.c b/tools/power/cpupower/utils/idle_monitor/hsw_ext_idle.c index ebeaba6571a3..f794d6bbb7e9 100644 --- a/tools/power/cpupower/utils/idle_monitor/hsw_ext_idle.c +++ b/tools/power/cpupower/utils/idle_monitor/hsw_ext_idle.c @@ -123,7 +123,7 @@ static int hsw_ext_start(void) previous_count[num][cpu] = val; } } - hsw_ext_get_count(TSC, &tsc_at_measure_start, 0); + hsw_ext_get_count(TSC, &tsc_at_measure_start, base_cpu); return 0; } @@ -132,7 +132,7 @@ static int hsw_ext_stop(void) unsigned long long val; int num, cpu; - hsw_ext_get_count(TSC, &tsc_at_measure_end, 0); + hsw_ext_get_count(TSC, &tsc_at_measure_end, base_cpu); for (num = 0; num < HSW_EXT_CSTATE_COUNT; num++) { for (cpu = 0; cpu < cpu_count; cpu++) { diff --git a/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c b/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c index c83f1606970b..d7c2a6d13dea 100644 --- a/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c +++ b/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c @@ -80,7 +80,8 @@ static int *is_valid; static int mperf_get_tsc(unsigned long long *tsc) { int ret; - ret = read_msr(0, MSR_TSC, tsc); + + ret = read_msr(base_cpu, MSR_TSC, tsc); if (ret) dprint("Reading TSC MSR failed, returning %llu\n", *tsc); return ret; diff --git a/tools/power/cpupower/utils/idle_monitor/nhm_idle.c b/tools/power/cpupower/utils/idle_monitor/nhm_idle.c index d2a91dd0d563..abf8cb5f7349 100644 --- a/tools/power/cpupower/utils/idle_monitor/nhm_idle.c +++ b/tools/power/cpupower/utils/idle_monitor/nhm_idle.c @@ -129,7 +129,7 @@ static int nhm_start(void) int num, cpu; unsigned long long dbg, val; - nhm_get_count(TSC, &tsc_at_measure_start, 0); + nhm_get_count(TSC, &tsc_at_measure_start, base_cpu); for (num = 0; num < NHM_CSTATE_COUNT; num++) { for (cpu = 0; cpu < cpu_count; cpu++) { @@ -137,7 +137,7 @@ static int nhm_start(void) previous_count[num][cpu] = val; } } - nhm_get_count(TSC, &dbg, 0); + nhm_get_count(TSC, &dbg, base_cpu); dprint("TSC diff: %llu\n", dbg - tsc_at_measure_start); return 0; } @@ -148,7 +148,7 @@ static int nhm_stop(void) unsigned long long dbg; int num, cpu; - nhm_get_count(TSC, &tsc_at_measure_end, 0); + nhm_get_count(TSC, &tsc_at_measure_end, base_cpu); for (num = 0; num < NHM_CSTATE_COUNT; num++) { for (cpu = 0; cpu < cpu_count; cpu++) { @@ -156,7 +156,7 @@ static int nhm_stop(void) current_count[num][cpu] = val; } } - nhm_get_count(TSC, &dbg, 0); + nhm_get_count(TSC, &dbg, base_cpu); dprint("TSC diff: %llu\n", dbg - tsc_at_measure_end); return 0; diff --git a/tools/power/cpupower/utils/idle_monitor/snb_idle.c b/tools/power/cpupower/utils/idle_monitor/snb_idle.c index efc8a69c9aba..a2b45219648d 100644 --- a/tools/power/cpupower/utils/idle_monitor/snb_idle.c +++ b/tools/power/cpupower/utils/idle_monitor/snb_idle.c @@ -120,7 +120,7 @@ static int snb_start(void) previous_count[num][cpu] = val; } } - snb_get_count(TSC, &tsc_at_measure_start, 0); + snb_get_count(TSC, &tsc_at_measure_start, base_cpu); return 0; } @@ -129,7 +129,7 @@ static int snb_stop(void) unsigned long long val; int num, cpu; - snb_get_count(TSC, &tsc_at_measure_end, 0); + snb_get_count(TSC, &tsc_at_measure_end, base_cpu); for (num = 0; num < SNB_CSTATE_COUNT; num++) { for (cpu = 0; cpu < cpu_count; cpu++) { diff --git a/tools/power/pm-graph/Makefile b/tools/power/pm-graph/Makefile index 4d0ccc89e6c6..32f40eacdafe 100644 --- a/tools/power/pm-graph/Makefile +++ b/tools/power/pm-graph/Makefile @@ -4,7 +4,7 @@ DESTDIR ?= all: @echo "Nothing to build" -install : +install : uninstall install -d $(DESTDIR)$(PREFIX)/lib/pm-graph install analyze_suspend.py $(DESTDIR)$(PREFIX)/lib/pm-graph install analyze_boot.py $(DESTDIR)$(PREFIX)/lib/pm-graph @@ -17,12 +17,15 @@ install : install sleepgraph.8 $(DESTDIR)$(PREFIX)/share/man/man8 uninstall : - rm $(DESTDIR)$(PREFIX)/share/man/man8/bootgraph.8 - rm $(DESTDIR)$(PREFIX)/share/man/man8/sleepgraph.8 + rm -f $(DESTDIR)$(PREFIX)/share/man/man8/bootgraph.8 + rm -f $(DESTDIR)$(PREFIX)/share/man/man8/sleepgraph.8 - rm $(DESTDIR)$(PREFIX)/bin/bootgraph - rm $(DESTDIR)$(PREFIX)/bin/sleepgraph + rm -f $(DESTDIR)$(PREFIX)/bin/bootgraph + rm -f $(DESTDIR)$(PREFIX)/bin/sleepgraph - rm $(DESTDIR)$(PREFIX)/lib/pm-graph/analyze_boot.py - rm $(DESTDIR)$(PREFIX)/lib/pm-graph/analyze_suspend.py - rmdir $(DESTDIR)$(PREFIX)/lib/pm-graph + rm -f $(DESTDIR)$(PREFIX)/lib/pm-graph/analyze_boot.py + rm -f $(DESTDIR)$(PREFIX)/lib/pm-graph/analyze_suspend.py + rm -f $(DESTDIR)$(PREFIX)/lib/pm-graph/*.pyc + if [ -d $(DESTDIR)$(PREFIX)/lib/pm-graph ] ; then \ + rmdir $(DESTDIR)$(PREFIX)/lib/pm-graph; \ + fi; diff --git a/tools/power/pm-graph/analyze_boot.py b/tools/power/pm-graph/analyze_boot.py index 3e1dcbbf1adc..e83df141a597 100755 --- a/tools/power/pm-graph/analyze_boot.py +++ b/tools/power/pm-graph/analyze_boot.py @@ -42,7 +42,7 @@ import analyze_suspend as aslib # store system values and test parameters class SystemValues(aslib.SystemValues): title = 'BootGraph' - version = 2.0 + version = '2.1' hostname = 'localhost' testtime = '' kernel = '' @@ -50,9 +50,14 @@ class SystemValues(aslib.SystemValues): ftracefile = '' htmlfile = 'bootgraph.html' outfile = '' - phoronix = False - addlogs = False + testdir = '' + testdirprefix = 'boot' + embedded = False + testlog = False + dmesglog = False + ftracelog = False useftrace = False + usecallgraph = False usedevsrc = True suspendmode = 'boot' max_graph_depth = 2 @@ -61,10 +66,12 @@ class SystemValues(aslib.SystemValues): manual = False iscronjob = False timeformat = '%.6f' + bootloader = 'grub' + blexec = [] def __init__(self): if('LOG_FILE' in os.environ and 'TEST_RESULTS_IDENTIFIER' in os.environ): - self.phoronix = True - self.addlogs = True + self.embedded = True + self.dmesglog = True self.outfile = os.environ['LOG_FILE'] self.htmlfile = os.environ['LOG_FILE'] self.hostname = platform.node() @@ -76,42 +83,80 @@ class SystemValues(aslib.SystemValues): self.kernel = self.kernelVersion(val) else: self.kernel = 'unknown' + self.testdir = datetime.now().strftime('boot-%y%m%d-%H%M%S') def kernelVersion(self, msg): return msg.split()[2] + def checkFtraceKernelVersion(self): + val = tuple(map(int, self.kernel.split('-')[0].split('.'))) + if val >= (4, 10, 0): + return True + return False def kernelParams(self): cmdline = 'initcall_debug log_buf_len=32M' if self.useftrace: - cmdline += ' trace_buf_size=128M trace_clock=global '\ + if self.cpucount > 0: + bs = min(self.memtotal / 2, 2*1024*1024) / self.cpucount + else: + bs = 131072 + cmdline += ' trace_buf_size=%dK trace_clock=global '\ 'trace_options=nooverwrite,funcgraph-abstime,funcgraph-cpu,'\ 'funcgraph-duration,funcgraph-proc,funcgraph-tail,'\ 'nofuncgraph-overhead,context-info,graph-time '\ 'ftrace=function_graph '\ 'ftrace_graph_max_depth=%d '\ 'ftrace_graph_filter=%s' % \ - (self.max_graph_depth, self.graph_filter) + (bs, self.max_graph_depth, self.graph_filter) return cmdline def setGraphFilter(self, val): - fp = open(self.tpath+'available_filter_functions') - master = fp.read().split('\n') - fp.close() + master = self.getBootFtraceFilterFunctions() + fs = '' for i in val.split(','): func = i.strip() + if func == '': + doError('badly formatted filter function string') + if '[' in func or ']' in func: + doError('loadable module functions not allowed - "%s"' % func) + if ' ' in func: + doError('spaces found in filter functions - "%s"' % func) if func not in master: doError('function "%s" not available for ftrace' % func) - self.graph_filter = val + if not fs: + fs = func + else: + fs += ','+func + if not fs: + doError('badly formatted filter function string') + self.graph_filter = fs + def getBootFtraceFilterFunctions(self): + self.rootCheck(True) + fp = open(self.tpath+'available_filter_functions') + fulllist = fp.read().split('\n') + fp.close() + list = [] + for i in fulllist: + if not i or ' ' in i or '[' in i or ']' in i: + continue + list.append(i) + return list + def myCronJob(self, line): + if '@reboot' not in line: + return False + if 'bootgraph' in line or 'analyze_boot.py' in line or '-cronjob' in line: + return True + return False def cronjobCmdString(self): cmdline = '%s -cronjob' % os.path.abspath(sys.argv[0]) args = iter(sys.argv[1:]) for arg in args: if arg in ['-h', '-v', '-cronjob', '-reboot']: continue - elif arg in ['-o', '-dmesg', '-ftrace', '-filter']: + elif arg in ['-o', '-dmesg', '-ftrace', '-func']: args.next() continue cmdline += ' '+arg if self.graph_filter != 'do_one_initcall': - cmdline += ' -filter "%s"' % self.graph_filter - cmdline += ' -o "%s"' % os.path.abspath(self.htmlfile) + cmdline += ' -func "%s"' % self.graph_filter + cmdline += ' -o "%s"' % os.path.abspath(self.testdir) return cmdline def manualRebootRequired(self): cmdline = self.kernelParams() @@ -121,6 +166,39 @@ class SystemValues(aslib.SystemValues): print '3. After reboot, re-run this tool with the same arguments but no command (w/o -reboot or -manual).\n' print 'CMDLINE="%s"' % cmdline sys.exit() + def getExec(self, cmd): + dirlist = ['/sbin', '/bin', '/usr/sbin', '/usr/bin', + '/usr/local/sbin', '/usr/local/bin'] + for path in dirlist: + cmdfull = os.path.join(path, cmd) + if os.path.exists(cmdfull): + return cmdfull + return '' + def blGrub(self): + blcmd = '' + for cmd in ['update-grub', 'grub-mkconfig', 'grub2-mkconfig']: + if blcmd: + break + blcmd = self.getExec(cmd) + if not blcmd: + doError('[GRUB] missing update command') + if not os.path.exists('/etc/default/grub'): + doError('[GRUB] missing /etc/default/grub') + if 'grub2' in blcmd: + cfg = '/boot/grub2/grub.cfg' + else: + cfg = '/boot/grub/grub.cfg' + if not os.path.exists(cfg): + doError('[GRUB] missing %s' % cfg) + if 'update-grub' in blcmd: + self.blexec = [blcmd] + else: + self.blexec = [blcmd, '-o', cfg] + def getBootLoader(self): + if self.bootloader == 'grub': + self.blGrub() + else: + doError('unknown boot loader: %s' % self.bootloader) sysvals = SystemValues() @@ -136,20 +214,23 @@ class Data(aslib.Data): idstr = '' html_device_id = 0 valid = False - initstart = 0.0 + tUserMode = 0.0 boottime = '' - phases = ['boot'] + phases = ['kernel', 'user'] do_one_initcall = False def __init__(self, num): self.testnumber = num self.idstr = 'a' self.dmesgtext = [] self.dmesg = { - 'boot': {'list': dict(), 'start': -1.0, 'end': -1.0, 'row': 0, 'color': '#dddddd'} + 'kernel': {'list': dict(), 'start': -1.0, 'end': -1.0, 'row': 0, + 'order': 0, 'color': 'linear-gradient(to bottom, #fff, #bcf)'}, + 'user': {'list': dict(), 'start': -1.0, 'end': -1.0, 'row': 0, + 'order': 1, 'color': '#fff'} } def deviceTopology(self): return '' - def newAction(self, phase, name, start, end, ret, ulen): + def newAction(self, phase, name, pid, start, end, ret, ulen): # new device callback for a specific phase self.html_device_id += 1 devid = '%s%d' % (self.idstr, self.html_device_id) @@ -163,41 +244,46 @@ class Data(aslib.Data): name = '%s[%d]' % (origname, i) i += 1 list[name] = {'name': name, 'start': start, 'end': end, - 'pid': 0, 'length': length, 'row': 0, 'id': devid, + 'pid': pid, 'length': length, 'row': 0, 'id': devid, 'ret': ret, 'ulen': ulen } return name - def deviceMatch(self, cg): + def deviceMatch(self, pid, cg): if cg.end - cg.start == 0: return True - list = self.dmesg['boot']['list'] - for devname in list: - dev = list[devname] - if cg.name == 'do_one_initcall': - if(cg.start <= dev['start'] and cg.end >= dev['end'] and dev['length'] > 0): - dev['ftrace'] = cg - self.do_one_initcall = True - return True - else: - if(cg.start > dev['start'] and cg.end < dev['end']): - if 'ftraces' not in dev: - dev['ftraces'] = [] - dev['ftraces'].append(cg) - return True + for p in data.phases: + list = self.dmesg[p]['list'] + for devname in list: + dev = list[devname] + if pid != dev['pid']: + continue + if cg.name == 'do_one_initcall': + if(cg.start <= dev['start'] and cg.end >= dev['end'] and dev['length'] > 0): + dev['ftrace'] = cg + self.do_one_initcall = True + return True + else: + if(cg.start > dev['start'] and cg.end < dev['end']): + if 'ftraces' not in dev: + dev['ftraces'] = [] + dev['ftraces'].append(cg) + return True return False # ----------------- FUNCTIONS -------------------- -# Function: loadKernelLog +# Function: parseKernelLog # Description: -# Load a raw kernel log from dmesg -def loadKernelLog(): +# parse a kernel log for boot data +def parseKernelLog(): + phase = 'kernel' data = Data(0) - data.dmesg['boot']['start'] = data.start = ktime = 0.0 + data.dmesg['kernel']['start'] = data.start = ktime = 0.0 sysvals.stamp = { 'time': datetime.now().strftime('%B %d %Y, %I:%M:%S %p'), 'host': sysvals.hostname, 'mode': 'boot', 'kernel': ''} + tp = aslib.TestProps() devtemp = dict() if(sysvals.dmesgfile): lf = open(sysvals.dmesgfile, 'r') @@ -205,6 +291,13 @@ def loadKernelLog(): lf = Popen('dmesg', stdout=PIPE).stdout for line in lf: line = line.replace('\r\n', '') + # grab the stamp and sysinfo + if re.match(tp.stampfmt, line): + tp.stamp = line + continue + elif re.match(tp.sysinfofmt, line): + tp.sysinfo = line + continue idx = line.find('[') if idx > 1: line = line[idx:] @@ -215,7 +308,6 @@ def loadKernelLog(): if(ktime > 120): break msg = m.group('msg') - data.end = data.initstart = ktime data.dmesgtext.append(line) if(ktime == 0.0 and re.match('^Linux version .*', msg)): if(not sysvals.stamp['kernel']): @@ -228,43 +320,39 @@ def loadKernelLog(): data.boottime = bt.strftime('%Y-%m-%d_%H:%M:%S') sysvals.stamp['time'] = bt.strftime('%B %d %Y, %I:%M:%S %p') continue - m = re.match('^calling *(?P<f>.*)\+.*', msg) + m = re.match('^calling *(?P<f>.*)\+.* @ (?P<p>[0-9]*)', msg) if(m): - devtemp[m.group('f')] = ktime + func = m.group('f') + pid = int(m.group('p')) + devtemp[func] = (ktime, pid) continue m = re.match('^initcall *(?P<f>.*)\+.* returned (?P<r>.*) after (?P<t>.*) usecs', msg) if(m): data.valid = True + data.end = ktime f, r, t = m.group('f', 'r', 't') if(f in devtemp): - data.newAction('boot', f, devtemp[f], ktime, int(r), int(t)) - data.end = ktime + start, pid = devtemp[f] + data.newAction(phase, f, pid, start, ktime, int(r), int(t)) del devtemp[f] continue if(re.match('^Freeing unused kernel memory.*', msg)): - break - - data.dmesg['boot']['end'] = data.end + data.tUserMode = ktime + data.dmesg['kernel']['end'] = ktime + data.dmesg['user']['start'] = ktime + phase = 'user' + + if tp.stamp: + sysvals.stamp = 0 + tp.parseStamp(data, sysvals) + data.dmesg['user']['end'] = data.end lf.close() return data -# Function: loadTraceLog +# Function: parseTraceLog # Description: # Check if trace is available and copy to a temp file -def loadTraceLog(data): - # load the data to a temp file if none given - if not sysvals.ftracefile: - lib = aslib.sysvals - aslib.rootCheck(True) - if not lib.verifyFtrace(): - doError('ftrace not available') - if lib.fgetVal('current_tracer').strip() != 'function_graph': - doError('ftrace not configured for a boot callgraph') - sysvals.ftracefile = '/tmp/boot_ftrace.%s.txt' % os.getpid() - call('cat '+lib.tpath+'trace > '+sysvals.ftracefile, shell=True) - if not sysvals.ftracefile: - doError('No trace data available') - +def parseTraceLog(data): # parse the trace log ftemp = dict() tp = aslib.TestProps() @@ -306,9 +394,29 @@ def loadTraceLog(data): print('Sanity check failed for %s-%d' % (proc, pid)) continue # match cg data to devices - if not data.deviceMatch(cg): + if not data.deviceMatch(pid, cg): print ' BAD: %s %s-%d [%f - %f]' % (cg.name, proc, pid, cg.start, cg.end) +# Function: retrieveLogs +# Description: +# Create copies of dmesg and/or ftrace for later processing +def retrieveLogs(): + # check ftrace is configured first + if sysvals.useftrace: + tracer = sysvals.fgetVal('current_tracer').strip() + if tracer != 'function_graph': + doError('ftrace not configured for a boot callgraph') + # create the folder and get dmesg + sysvals.systemInfo(aslib.dmidecode(sysvals.mempath)) + sysvals.initTestOutput('boot') + sysvals.writeDatafileHeader(sysvals.dmesgfile) + call('dmesg >> '+sysvals.dmesgfile, shell=True) + if not sysvals.useftrace: + return + # get ftrace + sysvals.writeDatafileHeader(sysvals.ftracefile) + call('cat '+sysvals.tpath+'trace >> '+sysvals.ftracefile, shell=True) + # Function: colorForName # Description: # Generate a repeatable color from a list for a given name @@ -353,18 +461,19 @@ def cgOverview(cg, minlen): # testruns: array of Data objects from parseKernelLog or parseTraceLog # Output: # True if the html file was created, false if it failed -def createBootGraph(data, embedded): +def createBootGraph(data): # html function templates html_srccall = '<div id={6} title="{5}" class="srccall" style="left:{1}%;top:{2}px;height:{3}px;width:{4}%;line-height:{3}px;">{0}</div>\n' html_timetotal = '<table class="time1">\n<tr>'\ - '<td class="blue">Time from Kernel Boot to start of User Mode: <b>{0} ms</b></td>'\ + '<td class="blue">Init process starts @ <b>{0} ms</b></td>'\ + '<td class="blue">Last initcall ends @ <b>{1} ms</b></td>'\ '</tr>\n</table>\n' # device timeline devtl = aslib.Timeline(100, 20) # write the test title and general info header - devtl.createHeader(sysvals, 'noftrace') + devtl.createHeader(sysvals) # Generate the header for this timeline t0 = data.start @@ -373,84 +482,98 @@ def createBootGraph(data, embedded): if(tTotal == 0): print('ERROR: No timeline data') return False - boot_time = '%.0f'%(tTotal*1000) - devtl.html += html_timetotal.format(boot_time) + user_mode = '%.0f'%(data.tUserMode*1000) + last_init = '%.0f'%(tTotal*1000) + devtl.html += html_timetotal.format(user_mode, last_init) # determine the maximum number of rows we need to draw - phase = 'boot' - list = data.dmesg[phase]['list'] devlist = [] - for devname in list: - d = aslib.DevItem(0, phase, list[devname]) - devlist.append(d) - devtl.getPhaseRows(devlist) + for p in data.phases: + list = data.dmesg[p]['list'] + for devname in list: + d = aslib.DevItem(0, p, list[devname]) + devlist.append(d) + devtl.getPhaseRows(devlist, 0, 'start') devtl.calcTotalRows() # draw the timeline background devtl.createZoomBox() - boot = data.dmesg[phase] - length = boot['end']-boot['start'] - left = '%.3f' % (((boot['start']-t0)*100.0)/tTotal) - width = '%.3f' % ((length*100.0)/tTotal) - devtl.html += devtl.html_tblock.format(phase, left, width, devtl.scaleH) - devtl.html += devtl.html_phase.format('0', '100', \ - '%.3f'%devtl.scaleH, '%.3f'%devtl.bodyH, \ - 'white', '') + devtl.html += devtl.html_tblock.format('boot', '0', '100', devtl.scaleH) + for p in data.phases: + phase = data.dmesg[p] + length = phase['end']-phase['start'] + left = '%.3f' % (((phase['start']-t0)*100.0)/tTotal) + width = '%.3f' % ((length*100.0)/tTotal) + devtl.html += devtl.html_phase.format(left, width, \ + '%.3f'%devtl.scaleH, '%.3f'%devtl.bodyH, \ + phase['color'], '') # draw the device timeline num = 0 devstats = dict() - for devname in sorted(list): - cls, color = colorForName(devname) - dev = list[devname] - info = '@|%.3f|%.3f|%.3f|%d' % (dev['start']*1000.0, dev['end']*1000.0, - dev['ulen']/1000.0, dev['ret']) - devstats[dev['id']] = {'info':info} - dev['color'] = color - height = devtl.phaseRowHeight(0, phase, dev['row']) - top = '%.6f' % ((dev['row']*height) + devtl.scaleH) - left = '%.6f' % (((dev['start']-t0)*100)/tTotal) - width = '%.6f' % (((dev['end']-dev['start'])*100)/tTotal) - length = ' (%0.3f ms) ' % ((dev['end']-dev['start'])*1000) - devtl.html += devtl.html_device.format(dev['id'], - devname+length+'kernel_mode', left, top, '%.3f'%height, - width, devname, ' '+cls, '') - rowtop = devtl.phaseRowTop(0, phase, dev['row']) - height = '%.6f' % (devtl.rowH / 2) - top = '%.6f' % (rowtop + devtl.scaleH + (devtl.rowH / 2)) - if data.do_one_initcall: - if('ftrace' not in dev): + for phase in data.phases: + list = data.dmesg[phase]['list'] + for devname in sorted(list): + cls, color = colorForName(devname) + dev = list[devname] + info = '@|%.3f|%.3f|%.3f|%d' % (dev['start']*1000.0, dev['end']*1000.0, + dev['ulen']/1000.0, dev['ret']) + devstats[dev['id']] = {'info':info} + dev['color'] = color + height = devtl.phaseRowHeight(0, phase, dev['row']) + top = '%.6f' % ((dev['row']*height) + devtl.scaleH) + left = '%.6f' % (((dev['start']-t0)*100)/tTotal) + width = '%.6f' % (((dev['end']-dev['start'])*100)/tTotal) + length = ' (%0.3f ms) ' % ((dev['end']-dev['start'])*1000) + devtl.html += devtl.html_device.format(dev['id'], + devname+length+phase+'_mode', left, top, '%.3f'%height, + width, devname, ' '+cls, '') + rowtop = devtl.phaseRowTop(0, phase, dev['row']) + height = '%.6f' % (devtl.rowH / 2) + top = '%.6f' % (rowtop + devtl.scaleH + (devtl.rowH / 2)) + if data.do_one_initcall: + if('ftrace' not in dev): + continue + cg = dev['ftrace'] + large, stats = cgOverview(cg, 0.001) + devstats[dev['id']]['fstat'] = stats + for l in large: + left = '%f' % (((l.time-t0)*100)/tTotal) + width = '%f' % (l.length*100/tTotal) + title = '%s (%0.3fms)' % (l.name, l.length * 1000.0) + devtl.html += html_srccall.format(l.name, left, + top, height, width, title, 'x%d'%num) + num += 1 + continue + if('ftraces' not in dev): continue - cg = dev['ftrace'] - large, stats = cgOverview(cg, 0.001) - devstats[dev['id']]['fstat'] = stats - for l in large: - left = '%f' % (((l.time-t0)*100)/tTotal) - width = '%f' % (l.length*100/tTotal) - title = '%s (%0.3fms)' % (l.name, l.length * 1000.0) - devtl.html += html_srccall.format(l.name, left, - top, height, width, title, 'x%d'%num) + for cg in dev['ftraces']: + left = '%f' % (((cg.start-t0)*100)/tTotal) + width = '%f' % ((cg.end-cg.start)*100/tTotal) + cglen = (cg.end - cg.start) * 1000.0 + title = '%s (%0.3fms)' % (cg.name, cglen) + cg.id = 'x%d' % num + devtl.html += html_srccall.format(cg.name, left, + top, height, width, title, dev['id']+cg.id) num += 1 - continue - if('ftraces' not in dev): - continue - for cg in dev['ftraces']: - left = '%f' % (((cg.start-t0)*100)/tTotal) - width = '%f' % ((cg.end-cg.start)*100/tTotal) - cglen = (cg.end - cg.start) * 1000.0 - title = '%s (%0.3fms)' % (cg.name, cglen) - cg.id = 'x%d' % num - devtl.html += html_srccall.format(cg.name, left, - top, height, width, title, dev['id']+cg.id) - num += 1 # draw the time scale, try to make the number of labels readable - devtl.createTimeScale(t0, tMax, tTotal, phase) + devtl.createTimeScale(t0, tMax, tTotal, 'boot') devtl.html += '</div>\n' # timeline is finished devtl.html += '</div>\n</div>\n' + # draw a legend which describes the phases by color + devtl.html += '<div class="legend">\n' + pdelta = 20.0 + pmargin = 36.0 + for phase in data.phases: + order = '%.2f' % ((data.dmesg[phase]['order'] * pdelta) + pmargin) + devtl.html += devtl.html_legend.format(order, \ + data.dmesg[phase]['color'], phase+'_mode', phase[0]) + devtl.html += '</div>\n' + if(sysvals.outfile == sysvals.htmlfile): hf = open(sysvals.htmlfile, 'a') else: @@ -474,7 +597,7 @@ def createBootGraph(data, embedded): .fstat td {text-align:left;width:35px;}\n\ .srccall {position:absolute;font-size:10px;z-index:7;overflow:hidden;color:black;text-align:center;white-space:nowrap;border-radius:5px;border:1px solid black;background:linear-gradient(to bottom right,#CCC,#969696);}\n\ .srccall:hover {color:white;font-weight:bold;border:1px solid white;}\n' - if(not embedded): + if(not sysvals.embedded): aslib.addCSS(hf, sysvals, 1, False, extra) # write the device timeline @@ -495,9 +618,11 @@ def createBootGraph(data, embedded): html = \ '<div id="devicedetailtitle"></div>\n'\ '<div id="devicedetail" style="display:none;">\n'\ - '<div id="devicedetail0">\n'\ - '<div id="kernel_mode" class="phaselet" style="left:0%;width:100%;background:#DDDDDD"></div>\n'\ - '</div>\n</div>\n'\ + '<div id="devicedetail0">\n' + for p in data.phases: + phase = data.dmesg[p] + html += devtl.html_phaselet.format(p+'_mode', '0', '100', phase['color']) + html += '</div>\n</div>\n'\ '<script type="text/javascript">\n'+statinfo+\ '</script>\n' hf.write(html) @@ -507,21 +632,21 @@ def createBootGraph(data, embedded): aslib.addCallgraphs(sysvals, hf, data) # add the dmesg log as a hidden div - if sysvals.addlogs: + if sysvals.dmesglog: hf.write('<div id="dmesglog" style="display:none;">\n') for line in data.dmesgtext: line = line.replace('<', '<').replace('>', '>') hf.write(line) hf.write('</div>\n') - if(not embedded): + if(not sysvals.embedded): # write the footer and close aslib.addScriptCode(hf, [data]) hf.write('</body>\n</html>\n') else: # embedded out will be loaded in a page, skip the js hf.write('<div id=bounds style=display:none>%f,%f</div>' % \ - (data.start*1000, data.initstart*1000)) + (data.start*1000, data.end*1000)) hf.close() return True @@ -533,17 +658,20 @@ def updateCron(restore=False): if not restore: sysvals.rootUser(True) crondir = '/var/spool/cron/crontabs/' - cronfile = crondir+'root' - backfile = crondir+'root-analyze_boot-backup' + if not os.path.exists(crondir): + crondir = '/var/spool/cron/' if not os.path.exists(crondir): doError('%s not found' % crondir) - out = Popen(['which', 'crontab'], stdout=PIPE).stdout.read() - if not out: + cronfile = crondir+'root' + backfile = crondir+'root-analyze_boot-backup' + cmd = sysvals.getExec('crontab') + if not cmd: doError('crontab not found') # on restore: move the backup cron back into place if restore: if os.path.exists(backfile): shutil.move(backfile, cronfile) + call([cmd, cronfile]) return # backup current cron and install new one with reboot if os.path.exists(cronfile): @@ -556,13 +684,13 @@ def updateCron(restore=False): fp = open(backfile, 'r') op = open(cronfile, 'w') for line in fp: - if '@reboot' not in line: + if not sysvals.myCronJob(line): op.write(line) continue fp.close() op.write('@reboot python %s\n' % sysvals.cronjobCmdString()) op.close() - res = call('crontab %s' % cronfile, shell=True) + res = call([cmd, cronfile]) except Exception, e: print 'Exception: %s' % str(e) shutil.move(backfile, cronfile) @@ -577,25 +705,16 @@ def updateGrub(restore=False): # call update-grub on restore if restore: try: - call(['update-grub'], stderr=PIPE, stdout=PIPE, + call(sysvals.blexec, stderr=PIPE, stdout=PIPE, env={'PATH': '.:/sbin:/usr/sbin:/usr/bin:/sbin:/bin'}) except Exception, e: print 'Exception: %s\n' % str(e) return - # verify we can do this - sysvals.rootUser(True) - grubfile = '/etc/default/grub' - if not os.path.exists(grubfile): - print 'ERROR: Unable to set the kernel parameters via grub.\n' - sysvals.manualRebootRequired() - out = Popen(['which', 'update-grub'], stdout=PIPE).stdout.read() - if not out: - print 'ERROR: Unable to set the kernel parameters via grub.\n' - sysvals.manualRebootRequired() - # extract the option and create a grub config without it + sysvals.rootUser(True) tgtopt = 'GRUB_CMDLINE_LINUX_DEFAULT' cmdline = '' + grubfile = '/etc/default/grub' tempfile = '/etc/default/grub.analyze_boot' shutil.move(grubfile, tempfile) res = -1 @@ -622,7 +741,7 @@ def updateGrub(restore=False): # if the target option value is in quotes, strip them sp = '"' val = cmdline.strip() - if val[0] == '\'' or val[0] == '"': + if val and (val[0] == '\'' or val[0] == '"'): sp = val[0] val = val.strip(sp) cmdline = val @@ -633,7 +752,7 @@ def updateGrub(restore=False): # write out the updated target option op.write('\n%s=%s%s%s\n' % (tgtopt, sp, cmdline, sp)) op.close() - res = call('update-grub') + res = call(sysvals.blexec) os.remove(grubfile) except Exception, e: print 'Exception: %s' % str(e) @@ -641,10 +760,18 @@ def updateGrub(restore=False): # cleanup shutil.move(tempfile, grubfile) if res != 0: - doError('update-grub failed') + doError('update grub failed') -# Function: doError +# Function: updateKernelParams # Description: +# update boot conf for all kernels with our parameters +def updateKernelParams(restore=False): + # find the boot loader + sysvals.getBootLoader() + if sysvals.bootloader == 'grub': + updateGrub(restore) + +# Function: doError Description: # generic error function for catastrphic failures # Arguments: # msg: the error message to print @@ -660,7 +787,7 @@ def doError(msg, help=False): # print out the help text def printHelp(): print('') - print('%s v%.1f' % (sysvals.title, sysvals.version)) + print('%s v%s' % (sysvals.title, sysvals.version)) print('Usage: bootgraph <options> <command>') print('') print('Description:') @@ -669,13 +796,19 @@ def printHelp(): print(' the start of the init process.') print('') print(' If no specific command is given the tool reads the current dmesg') - print(' and/or ftrace log and outputs bootgraph.html') + print(' and/or ftrace log and creates a timeline') + print('') + print(' Generates output files in subdirectory: boot-yymmdd-HHMMSS') + print(' HTML output: <hostname>_boot.html') + print(' raw dmesg output: <hostname>_boot_dmesg.txt') + print(' raw ftrace output: <hostname>_boot_ftrace.txt') print('') print('Options:') print(' -h Print this help text') print(' -v Print the current tool version') print(' -addlogs Add the dmesg log to the html output') - print(' -o file Html timeline name (default: bootgraph.html)') + print(' -o name Overrides the output subdirectory name when running a new test') + print(' default: boot-{date}-{time}') print(' [advanced]') print(' -f Use ftrace to add function detail (default: disabled)') print(' -callgraph Add callgraph detail, can be very large (default: disabled)') @@ -683,13 +816,18 @@ def printHelp(): print(' -mincg ms Discard all callgraphs shorter than ms milliseconds (e.g. 0.001 for us)') print(' -timeprec N Number of significant digits in timestamps (0:S, 3:ms, [6:us])') print(' -expandcg pre-expand the callgraph data in the html output (default: disabled)') - print(' -filter list Limit ftrace to comma-delimited list of functions (default: do_one_initcall)') - print(' [commands]') + print(' -func list Limit ftrace to comma-delimited list of functions (default: do_one_initcall)') + print(' -cgfilter S Filter the callgraph output in the timeline') + print(' -bl name Use the following boot loader for kernel params (default: grub)') print(' -reboot Reboot the machine automatically and generate a new timeline') - print(' -manual Show the requirements to generate a new timeline manually') - print(' -dmesg file Load a stored dmesg file (used with -ftrace)') - print(' -ftrace file Load a stored ftrace file (used with -dmesg)') + print(' -manual Show the steps to generate a new timeline manually (used with -reboot)') + print('') + print('Other commands:') print(' -flistall Print all functions capable of being captured in ftrace') + print(' -sysinfo Print out system info extracted from BIOS') + print(' [redo]') + print(' -dmesg file Create HTML output using dmesg input (used with -ftrace)') + print(' -ftrace file Create HTML output using ftrace input (used with -dmesg)') print('') return True @@ -698,14 +836,15 @@ def printHelp(): if __name__ == '__main__': # loop through the command line arguments cmd = '' - simplecmds = ['-updategrub', '-flistall'] + testrun = True + simplecmds = ['-sysinfo', '-kpupdate', '-flistall', '-checkbl'] args = iter(sys.argv[1:]) for arg in args: if(arg == '-h'): printHelp() sys.exit() elif(arg == '-v'): - print("Version %.1f" % sysvals.version) + print("Version %s" % sysvals.version) sys.exit() elif(arg in simplecmds): cmd = arg[1:] @@ -716,16 +855,32 @@ if __name__ == '__main__': sysvals.usecallgraph = True elif(arg == '-mincg'): sysvals.mincglen = aslib.getArgFloat('-mincg', args, 0.0, 10000.0) + elif(arg == '-cgfilter'): + try: + val = args.next() + except: + doError('No callgraph functions supplied', True) + sysvals.setDeviceFilter(val) + elif(arg == '-bl'): + try: + val = args.next() + except: + doError('No boot loader name supplied', True) + if val.lower() not in ['grub']: + doError('Unknown boot loader: %s' % val, True) + sysvals.bootloader = val.lower() elif(arg == '-timeprec'): sysvals.setPrecision(aslib.getArgInt('-timeprec', args, 0, 6)) elif(arg == '-maxdepth'): sysvals.max_graph_depth = aslib.getArgInt('-maxdepth', args, 0, 1000) - elif(arg == '-filter'): + elif(arg == '-func'): try: val = args.next() except: doError('No filter functions supplied', True) - aslib.rootCheck(True) + sysvals.useftrace = True + sysvals.usecallgraph = True + sysvals.rootCheck(True) sysvals.setGraphFilter(val) elif(arg == '-ftrace'): try: @@ -734,9 +889,10 @@ if __name__ == '__main__': doError('No ftrace file supplied', True) if(os.path.exists(val) == False): doError('%s does not exist' % val) + testrun = False sysvals.ftracefile = val elif(arg == '-addlogs'): - sysvals.addlogs = True + sysvals.dmesglog = True elif(arg == '-expandcg'): sysvals.cgexp = True elif(arg == '-dmesg'): @@ -748,18 +904,15 @@ if __name__ == '__main__': doError('%s does not exist' % val) if(sysvals.htmlfile == val or sysvals.outfile == val): doError('Output filename collision') + testrun = False sysvals.dmesgfile = val elif(arg == '-o'): try: val = args.next() except: - doError('No HTML filename supplied', True) - if(sysvals.dmesgfile == val or sysvals.ftracefile == val): - doError('Output filename collision') - sysvals.htmlfile = val + doError('No subdirectory name supplied', True) + sysvals.testdir = sysvals.setOutputFolder(val) elif(arg == '-reboot'): - if sysvals.iscronjob: - doError('-reboot and -cronjob are incompatible') sysvals.reboot = True elif(arg == '-manual'): sysvals.reboot = True @@ -767,58 +920,93 @@ if __name__ == '__main__': # remaining options are only for cron job use elif(arg == '-cronjob'): sysvals.iscronjob = True - if sysvals.reboot: - doError('-reboot and -cronjob are incompatible') else: doError('Invalid argument: '+arg, True) + # compatibility errors and access checks + if(sysvals.iscronjob and (sysvals.reboot or \ + sysvals.dmesgfile or sysvals.ftracefile or cmd)): + doError('-cronjob is meant for batch purposes only') + if(sysvals.reboot and (sysvals.dmesgfile or sysvals.ftracefile)): + doError('-reboot and -dmesg/-ftrace are incompatible') + if cmd or sysvals.reboot or sysvals.iscronjob or testrun: + sysvals.rootCheck(True) + if (testrun and sysvals.useftrace) or cmd == 'flistall': + if not sysvals.verifyFtrace(): + doError('Ftrace is not properly enabled') + + # run utility commands + sysvals.cpuInfo() if cmd != '': - if cmd == 'updategrub': - updateGrub() + if cmd == 'kpupdate': + updateKernelParams() elif cmd == 'flistall': - sysvals.getFtraceFilterFunctions(False) + for f in sysvals.getBootFtraceFilterFunctions(): + print f + elif cmd == 'checkbl': + sysvals.getBootLoader() + print 'Boot Loader: %s\n%s' % (sysvals.bootloader, sysvals.blexec) + elif(cmd == 'sysinfo'): + sysvals.printSystemInfo() sys.exit() - # update grub, setup a cronjob, and reboot + # reboot: update grub, setup a cronjob, and reboot if sysvals.reboot: + if (sysvals.useftrace or sysvals.usecallgraph) and \ + not sysvals.checkFtraceKernelVersion(): + doError('Ftrace functionality requires kernel v4.10 or newer') if not sysvals.manual: - updateGrub() + updateKernelParams() updateCron() call('reboot') else: sysvals.manualRebootRequired() sys.exit() - # disable the cronjob + # cronjob: remove the cronjob, grub changes, and disable ftrace if sysvals.iscronjob: updateCron(True) - updateGrub(True) + updateKernelParams(True) + try: + sysvals.fsetVal('0', 'tracing_on') + except: + pass - data = loadKernelLog() - if sysvals.useftrace: - loadTraceLog(data) - if sysvals.iscronjob: - try: - sysvals.fsetVal('0', 'tracing_on') - except: - pass + # testrun: generate copies of the logs + if testrun: + retrieveLogs() + else: + sysvals.setOutputFile() - if(sysvals.outfile and sysvals.phoronix): - fp = open(sysvals.outfile, 'w') - fp.write('pass %s initstart %.3f end %.3f boot %s\n' % - (data.valid, data.initstart*1000, data.end*1000, data.boottime)) - fp.close() - if(not data.valid): - if sysvals.dmesgfile: + # process the log data + if sysvals.dmesgfile: + data = parseKernelLog() + if(not data.valid): doError('No initcall data found in %s' % sysvals.dmesgfile) - else: - doError('No initcall data found, is initcall_debug enabled?') + if sysvals.useftrace and sysvals.ftracefile: + parseTraceLog(data) + else: + doError('dmesg file required') print(' Host: %s' % sysvals.hostname) print(' Test time: %s' % sysvals.testtime) print(' Boot time: %s' % data.boottime) print('Kernel Version: %s' % sysvals.kernel) print(' Kernel start: %.3f' % (data.start * 1000)) - print(' init start: %.3f' % (data.initstart * 1000)) + print('Usermode start: %.3f' % (data.tUserMode * 1000)) + print('Last Init Call: %.3f' % (data.end * 1000)) + + # handle embedded output logs + if(sysvals.outfile and sysvals.embedded): + fp = open(sysvals.outfile, 'w') + fp.write('pass %s initstart %.3f end %.3f boot %s\n' % + (data.valid, data.tUserMode*1000, data.end*1000, data.boottime)) + fp.close() + + createBootGraph(data) - createBootGraph(data, sysvals.phoronix) + # if running as root, change output dir owner to sudo_user + if testrun and os.path.isdir(sysvals.testdir) and \ + os.getuid() == 0 and 'SUDO_USER' in os.environ: + cmd = 'chown -R {0}:{0} {1} > /dev/null 2>&1' + call(cmd.format(os.environ['SUDO_USER'], sysvals.testdir), shell=True) diff --git a/tools/power/pm-graph/analyze_suspend.py b/tools/power/pm-graph/analyze_suspend.py index a9206e67fc1f..1b60fe203741 100755 --- a/tools/power/pm-graph/analyze_suspend.py +++ b/tools/power/pm-graph/analyze_suspend.py @@ -68,10 +68,12 @@ from subprocess import call, Popen, PIPE # store system values and test parameters class SystemValues: title = 'SleepGraph' - version = '4.6' + version = '4.7' ansi = False verbose = False - addlogs = False + testlog = True + dmesglog = False + ftracelog = False mindevlen = 0.0 mincglen = 0.0 cgphase = '' @@ -79,10 +81,11 @@ class SystemValues: max_graph_depth = 0 callloopmaxgap = 0.0001 callloopmaxlen = 0.005 + cpucount = 0 + memtotal = 204800 srgap = 0 cgexp = False - outdir = '' - testdir = '.' + testdir = '' tpath = '/sys/kernel/debug/tracing/' fpdtpath = '/sys/firmware/acpi/tables/FPDT' epath = '/sys/kernel/debug/tracing/events/power/' @@ -95,14 +98,17 @@ class SystemValues: testcommand = '' mempath = '/dev/mem' powerfile = '/sys/power/state' + mempowerfile = '/sys/power/mem_sleep' suspendmode = 'mem' + memmode = '' hostname = 'localhost' prefix = 'test' teststamp = '' + sysstamp = '' dmesgstart = 0.0 dmesgfile = '' ftracefile = '' - htmlfile = '' + htmlfile = 'output.html' embedded = False rtcwake = True rtcwaketime = 15 @@ -127,9 +133,6 @@ class SystemValues: devpropfmt = '# Device Properties: .*' tracertypefmt = '# tracer: (?P<t>.*)' firmwarefmt = '# fwsuspend (?P<s>[0-9]*) fwresume (?P<r>[0-9]*)$' - stampfmt = '# suspend-(?P<m>[0-9]{2})(?P<d>[0-9]{2})(?P<y>[0-9]{2})-'+\ - '(?P<H>[0-9]{2})(?P<M>[0-9]{2})(?P<S>[0-9]{2})'+\ - ' (?P<host>.*) (?P<mode>.*) (?P<kernel>.*)$' tracefuncs = { 'sys_sync': dict(), 'pm_prepare_console': dict(), @@ -218,7 +221,7 @@ class SystemValues: # if this is a phoronix test run, set some default options if('LOG_FILE' in os.environ and 'TEST_RESULTS_IDENTIFIER' in os.environ): self.embedded = True - self.addlogs = True + self.dmesglog = self.ftracelog = True self.htmlfile = os.environ['LOG_FILE'] self.archargs = 'args_'+platform.machine() self.hostname = platform.node() @@ -233,6 +236,13 @@ class SystemValues: self.rtcpath = rtc if (hasattr(sys.stdout, 'isatty') and sys.stdout.isatty()): self.ansi = True + self.testdir = datetime.now().strftime('suspend-%y%m%d-%H%M%S') + def rootCheck(self, fatal=True): + if(os.access(self.powerfile, os.W_OK)): + return True + if fatal: + doError('This command requires sysfs mount and root access') + return False def rootUser(self, fatal=False): if 'USER' in os.environ and os.environ['USER'] == 'root': return True @@ -249,30 +259,60 @@ class SystemValues: args['date'] = n.strftime('%y%m%d') args['time'] = n.strftime('%H%M%S') args['hostname'] = self.hostname - self.outdir = value.format(**args) + return value.format(**args) def setOutputFile(self): - if((self.htmlfile == '') and (self.dmesgfile != '')): + if self.dmesgfile != '': m = re.match('(?P<name>.*)_dmesg\.txt$', self.dmesgfile) if(m): self.htmlfile = m.group('name')+'.html' - if((self.htmlfile == '') and (self.ftracefile != '')): + if self.ftracefile != '': m = re.match('(?P<name>.*)_ftrace\.txt$', self.ftracefile) if(m): self.htmlfile = m.group('name')+'.html' - if(self.htmlfile == ''): - self.htmlfile = 'output.html' - def initTestOutput(self, subdir, testpath=''): + def systemInfo(self, info): + p = c = m = b = '' + if 'baseboard-manufacturer' in info: + m = info['baseboard-manufacturer'] + elif 'system-manufacturer' in info: + m = info['system-manufacturer'] + if 'baseboard-product-name' in info: + p = info['baseboard-product-name'] + elif 'system-product-name' in info: + p = info['system-product-name'] + if 'processor-version' in info: + c = info['processor-version'] + if 'bios-version' in info: + b = info['bios-version'] + self.sysstamp = '# sysinfo | man:%s | plat:%s | cpu:%s | bios:%s | numcpu:%d | memsz:%d' % \ + (m, p, c, b, self.cpucount, self.memtotal) + def printSystemInfo(self): + self.rootCheck(True) + out = dmidecode(self.mempath, True) + fmt = '%-24s: %s' + for name in sorted(out): + print fmt % (name, out[name]) + print fmt % ('cpucount', ('%d' % self.cpucount)) + print fmt % ('memtotal', ('%d kB' % self.memtotal)) + def cpuInfo(self): + self.cpucount = 0 + fp = open('/proc/cpuinfo', 'r') + for line in fp: + if re.match('^processor[ \t]*:[ \t]*[0-9]*', line): + self.cpucount += 1 + fp.close() + fp = open('/proc/meminfo', 'r') + for line in fp: + m = re.match('^MemTotal:[ \t]*(?P<sz>[0-9]*) *kB', line) + if m: + self.memtotal = int(m.group('sz')) + break + fp.close() + def initTestOutput(self, name): self.prefix = self.hostname v = open('/proc/version', 'r').read().strip() kver = string.split(v)[2] - n = datetime.now() - testtime = n.strftime('suspend-%m%d%y-%H%M%S') - if not testpath: - testpath = n.strftime('suspend-%y%m%d-%H%M%S') - if(subdir != "."): - self.testdir = subdir+"/"+testpath - else: - self.testdir = testpath + fmt = name+'-%m%d%y-%H%M%S' + testtime = datetime.now().strftime(fmt) self.teststamp = \ '# '+testtime+' '+self.prefix+' '+self.suspendmode+' '+kver if(self.embedded): @@ -355,7 +395,7 @@ class SystemValues: continue self.tracefuncs[i] = dict() def getFtraceFilterFunctions(self, current): - rootCheck(True) + self.rootCheck(True) if not current: call('cat '+self.tpath+'available_filter_functions', shell=True) return @@ -453,7 +493,7 @@ class SystemValues: val += '\nr:%s_ret %s $retval\n' % (name, func) return val def addKprobes(self, output=False): - if len(sysvals.kprobes) < 1: + if len(self.kprobes) < 1: return if output: print(' kprobe functions in this kernel:') @@ -525,7 +565,7 @@ class SystemValues: fp.flush() fp.close() except: - pass + return False return True def fgetVal(self, path): file = self.tpath+path @@ -566,9 +606,15 @@ class SystemValues: self.cleanupFtrace() # set the trace clock to global self.fsetVal('global', 'trace_clock') - # set trace buffer to a huge value self.fsetVal('nop', 'current_tracer') - self.fsetVal('131073', 'buffer_size_kb') + # set trace buffer to a huge value + if self.usecallgraph or self.usedevsrc: + tgtsize = min(self.memtotal / 2, 2*1024*1024) + maxbuf = '%d' % (tgtsize / max(1, self.cpucount)) + if self.cpucount < 1 or not self.fsetVal(maxbuf, 'buffer_size_kb'): + self.fsetVal('131072', 'buffer_size_kb') + else: + self.fsetVal('16384', 'buffer_size_kb') # go no further if this is just a status check if testing: return @@ -641,6 +687,15 @@ class SystemValues: if not self.ansi: return str return '\x1B[%d;40m%s\x1B[m' % (color, str) + def writeDatafileHeader(self, filename, fwdata=[]): + fp = open(filename, 'w') + fp.write(self.teststamp+'\n') + fp.write(self.sysstamp+'\n') + if(self.suspendmode == 'mem' or self.suspendmode == 'command'): + for fw in fwdata: + if(fw): + fp.write('# fwsuspend %u fwresume %u\n' % (fw[0], fw[1])) + fp.close() sysvals = SystemValues() suspendmodename = { @@ -1008,6 +1063,12 @@ class Data: else: self.trimTime(self.tSuspended, \ self.tResumed-self.tSuspended, False) + def getTimeValues(self): + sktime = (self.dmesg['suspend_machine']['end'] - \ + self.tKernSus) * 1000 + rktime = (self.dmesg['resume_complete']['end'] - \ + self.dmesg['resume_machine']['start']) * 1000 + return (sktime, rktime) def setPhase(self, phase, ktime, isbegin): if(isbegin): self.dmesg[phase]['start'] = ktime @@ -1517,7 +1578,7 @@ class FTraceCallGraph: prelinedep += 1 last = 0 lasttime = line.time - virtualfname = 'execution_misalignment' + virtualfname = 'missing_function_name' if len(self.list) > 0: last = self.list[-1] lasttime = last.time @@ -1773,24 +1834,30 @@ class Timeline: html_device = '<div id="{0}" title="{1}" class="thread{7}" style="left:{2}%;top:{3}px;height:{4}px;width:{5}%;{8}">{6}</div>\n' html_phase = '<div class="phase" style="left:{0}%;width:{1}%;top:{2}px;height:{3}px;background:{4}">{5}</div>\n' html_phaselet = '<div id="{0}" class="phaselet" style="left:{1}%;width:{2}%;background:{3}"></div>\n' + html_legend = '<div id="p{3}" class="square" style="left:{0}%;background:{1}"> {2}</div>\n' def __init__(self, rowheight, scaleheight): self.rowH = rowheight self.scaleH = scaleheight self.html = '' - def createHeader(self, sv, suppress=''): + def createHeader(self, sv): if(not sv.stamp['time']): return self.html += '<div class="version"><a href="https://01.org/suspendresume">%s v%s</a></div>' \ % (sv.title, sv.version) - if sv.logmsg and 'log' not in suppress: - self.html += '<button id="showtest" class="logbtn">log</button>' - if sv.addlogs and 'dmesg' not in suppress: - self.html += '<button id="showdmesg" class="logbtn">dmesg</button>' - if sv.addlogs and sv.ftracefile and 'ftrace' not in suppress: - self.html += '<button id="showftrace" class="logbtn">ftrace</button>' + if sv.logmsg and sv.testlog: + self.html += '<button id="showtest" class="logbtn btnfmt">log</button>' + if sv.dmesglog: + self.html += '<button id="showdmesg" class="logbtn btnfmt">dmesg</button>' + if sv.ftracelog: + self.html += '<button id="showftrace" class="logbtn btnfmt">ftrace</button>' headline_stamp = '<div class="stamp">{0} {1} {2} {3}</div>\n' self.html += headline_stamp.format(sv.stamp['host'], sv.stamp['kernel'], sv.stamp['mode'], sv.stamp['time']) + if 'man' in sv.stamp and 'plat' in sv.stamp and 'cpu' in sv.stamp: + headline_sysinfo = '<div class="stamp sysinfo">{0} {1} <i>with</i> {2}</div>\n' + self.html += headline_sysinfo.format(sv.stamp['man'], + sv.stamp['plat'], sv.stamp['cpu']) + # Function: getDeviceRows # Description: # determine how may rows the device funcs will take @@ -1839,7 +1906,7 @@ class Timeline: # devlist: the list of devices/actions in a group of contiguous phases # Output: # The total number of rows needed to display this phase of the timeline - def getPhaseRows(self, devlist, row=0): + def getPhaseRows(self, devlist, row=0, sortby='length'): # clear all rows and set them to undefined remaining = len(devlist) rowdata = dict() @@ -1852,8 +1919,12 @@ class Timeline: if tp not in myphases: myphases.append(tp) dev['row'] = -1 - # sort by length 1st, then name 2nd - sortdict[item] = (float(dev['end']) - float(dev['start']), item.dev['name']) + if sortby == 'start': + # sort by start 1st, then length 2nd + sortdict[item] = (-1*float(dev['start']), float(dev['end']) - float(dev['start'])) + else: + # sort by length 1st, then name 2nd + sortdict[item] = (float(dev['end']) - float(dev['start']), item.dev['name']) if 'src' in dev: dev['devrows'] = self.getDeviceRows(dev['src']) # sort the devlist by length so that large items graph on top @@ -1995,8 +2066,13 @@ class Timeline: # A list of values describing the properties of these test runs class TestProps: stamp = '' + sysinfo = '' S0i3 = False fwdata = [] + stampfmt = '# [a-z]*-(?P<m>[0-9]{2})(?P<d>[0-9]{2})(?P<y>[0-9]{2})-'+\ + '(?P<H>[0-9]{2})(?P<M>[0-9]{2})(?P<S>[0-9]{2})'+\ + ' (?P<host>.*) (?P<mode>.*) (?P<kernel>.*)$' + sysinfofmt = '^# sysinfo .*' ftrace_line_fmt_fg = \ '^ *(?P<time>[0-9\.]*) *\| *(?P<cpu>[0-9]*)\)'+\ ' *(?P<proc>.*)-(?P<pid>[0-9]*) *\|'+\ @@ -2019,6 +2095,36 @@ class TestProps: self.ftrace_line_fmt = self.ftrace_line_fmt_nop else: doError('Invalid tracer format: [%s]' % tracer) + def parseStamp(self, data, sv): + m = re.match(self.stampfmt, self.stamp) + data.stamp = {'time': '', 'host': '', 'mode': ''} + dt = datetime(int(m.group('y'))+2000, int(m.group('m')), + int(m.group('d')), int(m.group('H')), int(m.group('M')), + int(m.group('S'))) + data.stamp['time'] = dt.strftime('%B %d %Y, %I:%M:%S %p') + data.stamp['host'] = m.group('host') + data.stamp['mode'] = m.group('mode') + data.stamp['kernel'] = m.group('kernel') + if re.match(self.sysinfofmt, self.sysinfo): + for f in self.sysinfo.split('|'): + if '#' in f: + continue + tmp = f.strip().split(':', 1) + key = tmp[0] + val = tmp[1] + data.stamp[key] = val + sv.hostname = data.stamp['host'] + sv.suspendmode = data.stamp['mode'] + if sv.suspendmode == 'command' and sv.ftracefile != '': + modes = ['on', 'freeze', 'standby', 'mem'] + out = Popen(['grep', 'suspend_enter', sv.ftracefile], + stderr=PIPE, stdout=PIPE).stdout.read() + m = re.match('.* suspend_enter\[(?P<mode>.*)\]', out) + if m and m.group('mode') in ['1', '2', '3']: + sv.suspendmode = modes[int(m.group('mode'))] + data.stamp['mode'] = sv.suspendmode + if not sv.stamp: + sv.stamp = data.stamp # Class: TestRun # Description: @@ -2090,35 +2196,6 @@ def vprint(msg): if(sysvals.verbose): print(msg) -# Function: parseStamp -# Description: -# Pull in the stamp comment line from the data file(s), -# create the stamp, and add it to the global sysvals object -# Arguments: -# m: the valid re.match output for the stamp line -def parseStamp(line, data): - m = re.match(sysvals.stampfmt, line) - data.stamp = {'time': '', 'host': '', 'mode': ''} - dt = datetime(int(m.group('y'))+2000, int(m.group('m')), - int(m.group('d')), int(m.group('H')), int(m.group('M')), - int(m.group('S'))) - data.stamp['time'] = dt.strftime('%B %d %Y, %I:%M:%S %p') - data.stamp['host'] = m.group('host') - data.stamp['mode'] = m.group('mode') - data.stamp['kernel'] = m.group('kernel') - sysvals.hostname = data.stamp['host'] - sysvals.suspendmode = data.stamp['mode'] - if sysvals.suspendmode == 'command' and sysvals.ftracefile != '': - modes = ['on', 'freeze', 'standby', 'mem'] - out = Popen(['grep', 'suspend_enter', sysvals.ftracefile], - stderr=PIPE, stdout=PIPE).stdout.read() - m = re.match('.* suspend_enter\[(?P<mode>.*)\]', out) - if m and m.group('mode') in ['1', '2', '3']: - sysvals.suspendmode = modes[int(m.group('mode'))] - data.stamp['mode'] = sysvals.suspendmode - if not sysvals.stamp: - sysvals.stamp = data.stamp - # Function: doesTraceLogHaveTraceEvents # Description: # Quickly determine if the ftrace log has some or all of the trace events @@ -2136,11 +2213,6 @@ def doesTraceLogHaveTraceEvents(): sysvals.usekprobes = True out = Popen(['head', '-1', sysvals.ftracefile], stderr=PIPE, stdout=PIPE).stdout.read().replace('\n', '') - m = re.match(sysvals.stampfmt, out) - if m and m.group('mode') == 'command': - sysvals.usetraceeventsonly = True - sysvals.usetraceevents = True - return # figure out what level of trace events are supported sysvals.usetraceeventsonly = True sysvals.usetraceevents = False @@ -2182,11 +2254,13 @@ def appendIncompleteTraceLog(testruns): for line in tf: # remove any latent carriage returns line = line.replace('\r\n', '') - # grab the time stamp - m = re.match(sysvals.stampfmt, line) - if(m): + # grab the stamp and sysinfo + if re.match(tp.stampfmt, line): tp.stamp = line continue + elif re.match(tp.sysinfofmt, line): + tp.sysinfo = line + continue # determine the trace data type (required for further parsing) m = re.match(sysvals.tracertypefmt, line) if(m): @@ -2219,7 +2293,7 @@ def appendIncompleteTraceLog(testruns): # look for the suspend start marker if(t.startMarker()): data = testrun[testidx].data - parseStamp(tp.stamp, data) + tp.parseStamp(data, sysvals) data.setStart(t.time) continue if(not data): @@ -2389,11 +2463,13 @@ def parseTraceLog(): for line in tf: # remove any latent carriage returns line = line.replace('\r\n', '') - # stamp line: each stamp means a new test run - m = re.match(sysvals.stampfmt, line) - if(m): + # stamp and sysinfo lines + if re.match(tp.stampfmt, line): tp.stamp = line continue + elif re.match(tp.sysinfofmt, line): + tp.sysinfo = line + continue # firmware line: pull out any firmware data m = re.match(sysvals.firmwarefmt, line) if(m): @@ -2439,7 +2515,7 @@ def parseTraceLog(): testdata.append(data) testrun = TestRun(data) testruns.append(testrun) - parseStamp(tp.stamp, data) + tp.parseStamp(data, sysvals) data.setStart(t.time) data.tKernSus = t.time continue @@ -2820,10 +2896,13 @@ def loadKernelLog(justtext=False): idx = line.find('[') if idx > 1: line = line[idx:] - m = re.match(sysvals.stampfmt, line) - if(m): + # grab the stamp and sysinfo + if re.match(tp.stampfmt, line): tp.stamp = line continue + elif re.match(tp.sysinfofmt, line): + tp.sysinfo = line + continue m = re.match(sysvals.firmwarefmt, line) if(m): tp.fwdata.append((int(m.group('s')), int(m.group('r')))) @@ -2839,7 +2918,7 @@ def loadKernelLog(justtext=False): if(data): testruns.append(data) data = Data(len(testruns)) - parseStamp(tp.stamp, data) + tp.parseStamp(data, sysvals) if len(tp.fwdata) > data.testnumber: data.fwSuspend, data.fwResume = tp.fwdata[data.testnumber] if(data.fwSuspend > 0 or data.fwResume > 0): @@ -3170,6 +3249,8 @@ def addCallgraphs(sv, hf, data): continue list = data.dmesg[p]['list'] for devname in data.sortedDevices(p): + if len(sv.devicefilter) > 0 and devname not in sv.devicefilter: + continue dev = list[devname] color = 'white' if 'color' in data.dmesg[p]: @@ -3309,7 +3390,6 @@ def createHTML(testruns): html_error = '<div id="{1}" title="kernel error/warning" class="err" style="right:{0}%">ERROR→</div>\n' html_traceevent = '<div title="{0}" class="traceevent{6}" style="left:{1}%;top:{2}px;height:{3}px;width:{4}%;line-height:{3}px;{7}">{5}</div>\n' html_cpuexec = '<div class="jiffie" style="left:{0}%;top:{1}px;height:{2}px;width:{3}%;background:{4};"></div>\n' - html_legend = '<div id="p{3}" class="square" style="left:{0}%;background:{1}"> {2}</div>\n' html_timetotal = '<table class="time1">\n<tr>'\ '<td class="green" title="{3}">{2} Suspend Time: <b>{0} ms</b></td>'\ '<td class="yellow" title="{4}">{2} Resume Time: <b>{1} ms</b></td>'\ @@ -3346,10 +3426,7 @@ def createHTML(testruns): # Generate the header for this timeline for data in testruns: tTotal = data.end - data.start - sktime = (data.dmesg['suspend_machine']['end'] - \ - data.tKernSus) * 1000 - rktime = (data.dmesg['resume_complete']['end'] - \ - data.dmesg['resume_machine']['start']) * 1000 + sktime, rktime = data.getTimeValues() if(tTotal == 0): print('ERROR: No timeline data') sys.exit() @@ -3581,7 +3658,7 @@ def createHTML(testruns): id += tmp[1][0] order = '%.2f' % ((data.dmesg[phase]['order'] * pdelta) + pmargin) name = string.replace(phase, '_', ' ') - devtl.html += html_legend.format(order, \ + devtl.html += devtl.html_legend.format(order, \ data.dmesg[phase]['color'], name, id) devtl.html += '</div>\n' @@ -3628,10 +3705,10 @@ def createHTML(testruns): addCallgraphs(sysvals, hf, data) # add the test log as a hidden div - if sysvals.logmsg: + if sysvals.testlog and sysvals.logmsg: hf.write('<div id="testlog" style="display:none;">\n'+sysvals.logmsg+'</div>\n') # add the dmesg log as a hidden div - if sysvals.addlogs and sysvals.dmesgfile: + if sysvals.dmesglog and sysvals.dmesgfile: hf.write('<div id="dmesglog" style="display:none;">\n') lf = open(sysvals.dmesgfile, 'r') for line in lf: @@ -3640,7 +3717,7 @@ def createHTML(testruns): lf.close() hf.write('</div>\n') # add the ftrace log as a hidden div - if sysvals.addlogs and sysvals.ftracefile: + if sysvals.ftracelog and sysvals.ftracefile: hf.write('<div id="ftracelog" style="display:none;">\n') lf = open(sysvals.ftracefile, 'r') for line in lf: @@ -3701,6 +3778,7 @@ def addCSS(hf, sv, testcount=1, kerror=False, extra=''): <style type=\'text/css\'>\n\ body {overflow-y:scroll;}\n\ .stamp {width:100%;text-align:center;background:gray;line-height:30px;color:white;font:25px Arial;}\n\ + .stamp.sysinfo {font:10px Arial;}\n\ .callgraph {margin-top:30px;box-shadow:5px 5px 20px black;}\n\ .callgraph article * {padding-left:28px;}\n\ h1 {color:black;font:bold 30px Times;}\n\ @@ -3746,7 +3824,7 @@ def addCSS(hf, sv, testcount=1, kerror=False, extra=''): .legend {position:relative; width:100%; height:40px; text-align:center;margin-bottom:20px}\n\ .legend .square {position:absolute;cursor:pointer;top:10px; width:0px;height:20px;border:1px solid;padding-left:20px;}\n\ button {height:40px;width:200px;margin-bottom:20px;margin-top:20px;font-size:24px;}\n\ - .logbtn {position:relative;float:right;height:25px;width:50px;margin-top:3px;margin-bottom:0;font-size:10px;text-align:center;}\n\ + .btnfmt {position:relative;float:right;height:25px;width:auto;margin-top:3px;margin-bottom:0;font-size:10px;text-align:center;}\n\ .devlist {position:'+devlistpos+';width:190px;}\n\ a:link {color:white;text-decoration:none;}\n\ a:visited {color:white;}\n\ @@ -4084,8 +4162,6 @@ def addScriptCode(hf, testruns): ' win.document.write(title+"<pre>"+log.innerHTML+"</pre>");\n'\ ' win.document.close();\n'\ ' }\n'\ - ' function onClickPhase(e) {\n'\ - ' }\n'\ ' function onMouseDown(e) {\n'\ ' dragval[0] = e.clientX;\n'\ ' dragval[1] = document.getElementById("dmesgzoombox").scrollLeft;\n'\ @@ -4120,9 +4196,6 @@ def addScriptCode(hf, testruns): ' document.getElementById("zoomin").onclick = zoomTimeline;\n'\ ' document.getElementById("zoomout").onclick = zoomTimeline;\n'\ ' document.getElementById("zoomdef").onclick = zoomTimeline;\n'\ - ' var list = document.getElementsByClassName("square");\n'\ - ' for (var i = 0; i < list.length; i++)\n'\ - ' list[i].onclick = onClickPhase;\n'\ ' var list = document.getElementsByClassName("err");\n'\ ' for (var i = 0; i < list.length; i++)\n'\ ' list[i].onclick = errWindow;\n'\ @@ -4193,8 +4266,14 @@ def executeSuspend(): if sysvals.testcommand != '': call(sysvals.testcommand+' 2>&1', shell=True); else: + mode = sysvals.suspendmode + if sysvals.memmode and os.path.exists(sysvals.mempowerfile): + mode = 'mem' + pf = open(sysvals.mempowerfile, 'w') + pf.write(sysvals.memmode) + pf.close() pf = open(sysvals.powerfile, 'w') - pf.write(sysvals.suspendmode) + pf.write(mode) # execution will pause here try: pf.close() @@ -4219,24 +4298,15 @@ def executeSuspend(): pm.stop() sysvals.fsetVal('0', 'tracing_on') print('CAPTURING TRACE') - writeDatafileHeader(sysvals.ftracefile, fwdata) + sysvals.writeDatafileHeader(sysvals.ftracefile, fwdata) call('cat '+tp+'trace >> '+sysvals.ftracefile, shell=True) sysvals.fsetVal('', 'trace') devProps() # grab a copy of the dmesg output print('CAPTURING DMESG') - writeDatafileHeader(sysvals.dmesgfile, fwdata) + sysvals.writeDatafileHeader(sysvals.dmesgfile, fwdata) sysvals.getdmesg() -def writeDatafileHeader(filename, fwdata): - fp = open(filename, 'a') - fp.write(sysvals.teststamp+'\n') - if(sysvals.suspendmode == 'mem' or sysvals.suspendmode == 'command'): - for fw in fwdata: - if(fw): - fp.write('# fwsuspend %u fwresume %u\n' % (fw[0], fw[1])) - fp.close() - # Function: setUSBDevicesAuto # Description: # Set the autosuspend control parameter of all USB devices to auto @@ -4244,7 +4314,7 @@ def writeDatafileHeader(filename, fwdata): # to always-on since the kernel cant determine if the device can # properly autosuspend def setUSBDevicesAuto(): - rootCheck(True) + sysvals.rootCheck(True) for dirname, dirnames, filenames in os.walk('/sys/devices'): if(re.match('.*/usb[0-9]*.*', dirname) and 'idVendor' in filenames and 'idProduct' in filenames): @@ -4467,13 +4537,146 @@ def devProps(data=0): # Output: # A string list of the available modes def getModes(): - modes = '' + modes = [] if(os.path.exists(sysvals.powerfile)): fp = open(sysvals.powerfile, 'r') modes = string.split(fp.read()) fp.close() + if(os.path.exists(sysvals.mempowerfile)): + deep = False + fp = open(sysvals.mempowerfile, 'r') + for m in string.split(fp.read()): + memmode = m.strip('[]') + if memmode == 'deep': + deep = True + else: + modes.append('mem-%s' % memmode) + fp.close() + if 'mem' in modes and not deep: + modes.remove('mem') return modes +# Function: dmidecode +# Description: +# Read the bios tables and pull out system info +# Arguments: +# mempath: /dev/mem or custom mem path +# fatal: True to exit on error, False to return empty dict +# Output: +# A dict object with all available key/values +def dmidecode(mempath, fatal=False): + out = dict() + + # the list of values to retrieve, with hardcoded (type, idx) + info = { + 'bios-vendor': (0, 4), + 'bios-version': (0, 5), + 'bios-release-date': (0, 8), + 'system-manufacturer': (1, 4), + 'system-product-name': (1, 5), + 'system-version': (1, 6), + 'system-serial-number': (1, 7), + 'baseboard-manufacturer': (2, 4), + 'baseboard-product-name': (2, 5), + 'baseboard-version': (2, 6), + 'baseboard-serial-number': (2, 7), + 'chassis-manufacturer': (3, 4), + 'chassis-type': (3, 5), + 'chassis-version': (3, 6), + 'chassis-serial-number': (3, 7), + 'processor-manufacturer': (4, 7), + 'processor-version': (4, 16), + } + if(not os.path.exists(mempath)): + if(fatal): + doError('file does not exist: %s' % mempath) + return out + if(not os.access(mempath, os.R_OK)): + if(fatal): + doError('file is not readable: %s' % mempath) + return out + + # by default use legacy scan, but try to use EFI first + memaddr = 0xf0000 + memsize = 0x10000 + for ep in ['/sys/firmware/efi/systab', '/proc/efi/systab']: + if not os.path.exists(ep) or not os.access(ep, os.R_OK): + continue + fp = open(ep, 'r') + buf = fp.read() + fp.close() + i = buf.find('SMBIOS=') + if i >= 0: + try: + memaddr = int(buf[i+7:], 16) + memsize = 0x20 + except: + continue + + # read in the memory for scanning + fp = open(mempath, 'rb') + try: + fp.seek(memaddr) + buf = fp.read(memsize) + except: + if(fatal): + doError('DMI table is unreachable, sorry') + else: + return out + fp.close() + + # search for either an SM table or DMI table + i = base = length = num = 0 + while(i < memsize): + if buf[i:i+4] == '_SM_' and i < memsize - 16: + length = struct.unpack('H', buf[i+22:i+24])[0] + base, num = struct.unpack('IH', buf[i+24:i+30]) + break + elif buf[i:i+5] == '_DMI_': + length = struct.unpack('H', buf[i+6:i+8])[0] + base, num = struct.unpack('IH', buf[i+8:i+14]) + break + i += 16 + if base == 0 and length == 0 and num == 0: + if(fatal): + doError('Neither SMBIOS nor DMI were found') + else: + return out + + # read in the SM or DMI table + fp = open(mempath, 'rb') + try: + fp.seek(base) + buf = fp.read(length) + except: + if(fatal): + doError('DMI table is unreachable, sorry') + else: + return out + fp.close() + + # scan the table for the values we want + count = i = 0 + while(count < num and i <= len(buf) - 4): + type, size, handle = struct.unpack('BBH', buf[i:i+4]) + n = i + size + while n < len(buf) - 1: + if 0 == struct.unpack('H', buf[n:n+2])[0]: + break + n += 1 + data = buf[i+size:n+2].split('\0') + for name in info: + itype, idxadr = info[name] + if itype == type: + idx = struct.unpack('B', buf[i+idxadr])[0] + if idx > 0 and idx < len(data) - 1: + s = data[idx-1].strip() + if s and s.lower() != 'to be filled by o.e.m.': + out[name] = data[idx-1] + i = n + 2 + count += 1 + return out + # Function: getFPDT # Description: # Read the acpi bios tables and pull out FPDT, the firmware data @@ -4487,7 +4690,7 @@ def getFPDT(output): prectype[0] = 'Basic S3 Resume Performance Record' prectype[1] = 'Basic S3 Suspend Performance Record' - rootCheck(True) + sysvals.rootCheck(True) if(not os.path.exists(sysvals.fpdtpath)): if(output): doError('file does not exist: %s' % sysvals.fpdtpath) @@ -4617,7 +4820,7 @@ def statusCheck(probecheck=False): # check we have root access res = sysvals.colorText('NO (No features of this tool will work!)') - if(rootCheck(False)): + if(sysvals.rootCheck(False)): res = 'YES' print(' have root access: %s' % res) if(res != 'YES'): @@ -4716,16 +4919,6 @@ def doError(msg, help=False): print('ERROR: %s\n') % msg sys.exit() -# Function: rootCheck -# Description: -# quick check to see if we have root access -def rootCheck(fatal): - if(os.access(sysvals.powerfile, os.W_OK)): - return True - if fatal: - doError('This command requires sysfs mount and root access') - return False - # Function: getArgInt # Description: # pull out an integer argument from the command line with checks @@ -4779,6 +4972,7 @@ def processData(): if(sysvals.ftracefile and (sysvals.usecallgraph or sysvals.usetraceevents)): appendIncompleteTraceLog(testruns) createHTML(testruns) + return testruns # Function: rerunTest # Description: @@ -4790,17 +4984,20 @@ def rerunTest(): doError('recreating this html output requires a dmesg file') sysvals.setOutputFile() vprint('Output file: %s' % sysvals.htmlfile) - if(os.path.exists(sysvals.htmlfile) and not os.access(sysvals.htmlfile, os.W_OK)): - doError('missing permission to write to %s' % sysvals.htmlfile) - processData() + if os.path.exists(sysvals.htmlfile): + if not os.path.isfile(sysvals.htmlfile): + doError('a directory already exists with this name: %s' % sysvals.htmlfile) + elif not os.access(sysvals.htmlfile, os.W_OK): + doError('missing permission to write to %s' % sysvals.htmlfile) + return processData() # Function: runTest # Description: # execute a suspend/resume, gather the logs, and generate the output -def runTest(subdir, testpath=''): +def runTest(): # prepare for the test sysvals.initFtrace() - sysvals.initTestOutput(subdir, testpath) + sysvals.initTestOutput('suspend') vprint('Output files:\n\t%s\n\t%s\n\t%s' % \ (sysvals.dmesgfile, sysvals.ftracefile, sysvals.htmlfile)) @@ -4897,7 +5094,7 @@ def configFromFile(file): if(opt.lower() == 'verbose'): sysvals.verbose = checkArgBool(value) elif(opt.lower() == 'addlogs'): - sysvals.addlogs = checkArgBool(value) + sysvals.dmesglog = sysvals.ftracelog = checkArgBool(value) elif(opt.lower() == 'dev'): sysvals.usedevsrc = checkArgBool(value) elif(opt.lower() == 'proc'): @@ -4947,7 +5144,7 @@ def configFromFile(file): elif(opt.lower() == 'mincg'): sysvals.mincglen = getArgFloat('-mincg', value, 0.0, 10000.0, False) elif(opt.lower() == 'output-dir'): - sysvals.setOutputFolder(value) + sysvals.testdir = sysvals.setOutputFolder(value) if sysvals.suspendmode == 'command' and not sysvals.testcommand: doError('No command supplied for mode "command"') @@ -5030,8 +5227,6 @@ def configFromFile(file): # Description: # print out the help text def printHelp(): - modes = getModes() - print('') print('%s v%s' % (sysvals.title, sysvals.version)) print('Usage: sudo sleepgraph <options> <commands>') @@ -5048,7 +5243,7 @@ def printHelp(): print(' If no specific command is given, the default behavior is to initiate') print(' a suspend/resume and capture the dmesg/ftrace output as an html timeline.') print('') - print(' Generates output files in subdirectory: suspend-mmddyy-HHMMSS') + print(' Generates output files in subdirectory: suspend-yymmdd-HHMMSS') print(' HTML output: <hostname>_<mode>.html') print(' raw dmesg output: <hostname>_<mode>_dmesg.txt') print(' raw ftrace output: <hostname>_<mode>_ftrace.txt') @@ -5058,8 +5253,9 @@ def printHelp(): print(' -v Print the current tool version') print(' -config fn Pull arguments and config options from file fn') print(' -verbose Print extra information during execution and analysis') - print(' -m mode Mode to initiate for suspend %s (default: %s)') % (modes, sysvals.suspendmode) - print(' -o subdir Override the output subdirectory') + print(' -m mode Mode to initiate for suspend (default: %s)') % (sysvals.suspendmode) + print(' -o name Overrides the output subdirectory name when running a new test') + print(' default: suspend-{date}-{time}') print(' -rtcwake t Wakeup t seconds after suspend, set t to "off" to disable (default: 15)') print(' -addlogs Add the dmesg and ftrace logs to the html output') print(' -srgap Add a visible gap in the timeline between sus/res (default: disabled)') @@ -5084,17 +5280,20 @@ def printHelp(): print(' -cgphase P Only show callgraph data for phase P (e.g. suspend_late)') print(' -cgtest N Only show callgraph data for test N (e.g. 0 or 1 in an x2 run)') print(' -timeprec N Number of significant digits in timestamps (0:S, [3:ms], 6:us)') - print(' [commands]') - print(' -ftrace ftracefile Create HTML output using ftrace input (used with -dmesg)') - print(' -dmesg dmesgfile Create HTML output using dmesg (used with -ftrace)') - print(' -summary directory Create a summary of all test in this dir') + print('') + print('Other commands:') print(' -modes List available suspend modes') print(' -status Test to see if the system is enabled to run this tool') print(' -fpdt Print out the contents of the ACPI Firmware Performance Data Table') + print(' -sysinfo Print out system info extracted from BIOS') print(' -usbtopo Print out the current USB topology with power info') print(' -usbauto Enable autosuspend for all connected USB devices') print(' -flist Print the list of functions currently being captured in ftrace') print(' -flistall Print all functions capable of being captured in ftrace') + print(' -summary directory Create a summary of all test in this dir') + print(' [redo]') + print(' -ftrace ftracefile Create HTML output using ftrace input (used with -dmesg)') + print(' -dmesg dmesgfile Create HTML output using dmesg (used with -ftrace)') print('') return True @@ -5102,9 +5301,9 @@ def printHelp(): # exec start (skipped if script is loaded as library) if __name__ == '__main__': cmd = '' - cmdarg = '' + outdir = '' multitest = {'run': False, 'count': 0, 'delay': 0} - simplecmds = ['-modes', '-fpdt', '-flist', '-flistall', '-usbtopo', '-usbauto', '-status'] + simplecmds = ['-sysinfo', '-modes', '-fpdt', '-flist', '-flistall', '-usbtopo', '-usbauto', '-status'] # loop through the command line arguments args = iter(sys.argv[1:]) for arg in args: @@ -5135,7 +5334,7 @@ if __name__ == '__main__': elif(arg == '-f'): sysvals.usecallgraph = True elif(arg == '-addlogs'): - sysvals.addlogs = True + sysvals.dmesglog = sysvals.ftracelog = True elif(arg == '-verbose'): sysvals.verbose = True elif(arg == '-proc'): @@ -5195,7 +5394,7 @@ if __name__ == '__main__': val = args.next() except: doError('No subdirectory name supplied', True) - sysvals.setOutputFolder(val) + outdir = sysvals.setOutputFolder(val) elif(arg == '-config'): try: val = args.next() @@ -5236,7 +5435,7 @@ if __name__ == '__main__': except: doError('No directory supplied', True) cmd = 'summary' - cmdarg = val + outdir = val sysvals.notestrun = True if(os.path.isdir(val) == False): doError('%s is not accesible' % val) @@ -5260,11 +5459,14 @@ if __name__ == '__main__': sysvals.mincglen = sysvals.mindevlen # just run a utility command and exit + sysvals.cpuInfo() if(cmd != ''): if(cmd == 'status'): statusCheck(True) elif(cmd == 'fpdt'): getFPDT(True) + elif(cmd == 'sysinfo'): + sysvals.printSystemInfo() elif(cmd == 'usbtopo'): detectUSB() elif(cmd == 'modes'): @@ -5276,7 +5478,7 @@ if __name__ == '__main__': elif(cmd == 'usbauto'): setUSBDevicesAuto() elif(cmd == 'summary'): - runSummary(cmdarg, True) + runSummary(outdir, True) sys.exit() # if instructed, re-analyze existing data files @@ -5289,21 +5491,43 @@ if __name__ == '__main__': print('Check FAILED, aborting the test run!') sys.exit() + # extract mem modes and convert + mode = sysvals.suspendmode + if 'mem' == mode[:3]: + if '-' in mode: + memmode = mode.split('-')[-1] + else: + memmode = 'deep' + if memmode == 'shallow': + mode = 'standby' + elif memmode == 's2idle': + mode = 'freeze' + else: + mode = 'mem' + sysvals.memmode = memmode + sysvals.suspendmode = mode + + sysvals.systemInfo(dmidecode(sysvals.mempath)) + if multitest['run']: # run multiple tests in a separate subdirectory - s = 'x%d' % multitest['count'] - if not sysvals.outdir: - sysvals.outdir = datetime.now().strftime('suspend-'+s+'-%m%d%y-%H%M%S') - if not os.path.isdir(sysvals.outdir): - os.mkdir(sysvals.outdir) + if not outdir: + s = 'suspend-x%d' % multitest['count'] + outdir = datetime.now().strftime(s+'-%y%m%d-%H%M%S') + if not os.path.isdir(outdir): + os.mkdir(outdir) for i in range(multitest['count']): if(i != 0): print('Waiting %d seconds...' % (multitest['delay'])) time.sleep(multitest['delay']) print('TEST (%d/%d) START' % (i+1, multitest['count'])) - runTest(sysvals.outdir) + fmt = 'suspend-%y%m%d-%H%M%S' + sysvals.testdir = os.path.join(outdir, datetime.now().strftime(fmt)) + runTest() print('TEST (%d/%d) COMPLETE' % (i+1, multitest['count'])) - runSummary(sysvals.outdir, False) + runSummary(outdir, False) else: + if outdir: + sysvals.testdir = outdir # run the test in the current directory - runTest('.', sysvals.outdir) + runTest() diff --git a/tools/power/pm-graph/bootgraph.8 b/tools/power/pm-graph/bootgraph.8 index 55272a67b0e7..dbdafcf546df 100644 --- a/tools/power/pm-graph/bootgraph.8 +++ b/tools/power/pm-graph/bootgraph.8 @@ -8,14 +8,23 @@ bootgraph \- Kernel boot timing analysis .RB [ COMMAND ] .SH DESCRIPTION \fBbootgraph \fP reads the dmesg log from kernel boot and -creates an html representation of the initcall timeline up to the start -of the init process. +creates an html representation of the initcall timeline. It graphs +every module init call found, through both kernel and user modes. The +timeline is split into two phases: kernel mode & user mode. kernel mode +represents a single process run on a single cpu with serial init calls. +Once user mode begins, the init process is called, and the init calls +start working in parallel. .PP If no specific command is given, the tool reads the current dmesg log and -outputs bootgraph.html. +outputs a new timeline. .PP The tool can also augment the timeline with ftrace data on custom target functions as well as full trace callgraphs. +.PP +Generates output files in subdirectory: boot-yymmdd-HHMMSS + html timeline : <hostname>_boot.html + raw dmesg file : <hostname>_boot_dmesg.txt + raw ftrace file : <hostname>_boot_ftrace.txt .SH OPTIONS .TP \fB-h\fR @@ -28,15 +37,18 @@ Print the current tool version Add the dmesg log to the html output. It will be viewable by clicking a button in the timeline. .TP -\fB-o \fIfile\fR -Override the HTML output filename (default: bootgraph.html) -.SS "Ftrace Debug" +\fB-o \fIname\fR +Overrides the output subdirectory name when running a new test. +Use {date}, {time}, {hostname} for current values. +.sp +e.g. boot-{hostname}-{date}-{time} +.SS "advanced" .TP \fB-f\fR Use ftrace to add function detail (default: disabled) .TP \fB-callgraph\fR -Use ftrace to create initcall callgraphs (default: disabled). If -filter +Use ftrace to create initcall callgraphs (default: disabled). If -func is not used there will be one callgraph per initcall. This can produce very large outputs, i.e. 10MB - 100MB. .TP @@ -50,16 +62,19 @@ This reduces the html file size as there can be many tiny callgraphs which are barely visible in the timeline. The value is a float: e.g. 0.001 represents 1 us. .TP +\fB-cgfilter \fI"func1,func2,..."\fR +Reduce callgraph output in the timeline by limiting it to a list of calls. The +argument can be a single function name or a comma delimited list. +(default: none) +.TP \fB-timeprec \fIn\fR Number of significant digits in timestamps (0:S, 3:ms, [6:us]) .TP \fB-expandcg\fR pre-expand the callgraph data in the html output (default: disabled) .TP -\fB-filter \fI"func1,func2,..."\fR +\fB-func \fI"func1,func2,..."\fR Instead of tracing each initcall, trace a custom list of functions (default: do_one_initcall) - -.SH COMMANDS .TP \fB-reboot\fR Reboot the machine and generate a new timeline automatically. Works in 4 steps. @@ -73,16 +88,23 @@ Show the requirements to generate a new timeline manually. Requires 3 steps. 1. append the string to the kernel command line via your native boot manager. 2. reboot the system 3. after startup, re-run the tool with the same arguments and no command + +.SH COMMANDS +.SS "rebuild" .TP \fB-dmesg \fIfile\fR Create HTML output from an existing dmesg file. .TP \fB-ftrace \fIfile\fR Create HTML output from an existing ftrace file (used with -dmesg). +.SS "other" .TP \fB-flistall\fR Print all ftrace functions capable of being captured. These are all the -possible values you can add to trace via the -filter argument. +possible values you can add to trace via the -func argument. +.TP +\fB-sysinfo\fR +Print out system info extracted from BIOS. Reads /dev/mem directly instead of going through dmidecode. .SH EXAMPLES Create a timeline using the current dmesg log. @@ -93,13 +115,13 @@ Create a timeline using the current dmesg and ftrace log. .IP \f(CW$ bootgraph -callgraph\fR .PP -Create a timeline using the current dmesg, add the log to the html and change the name. +Create a timeline using the current dmesg, add the log to the html and change the folder. .IP -\f(CW$ bootgraph -addlogs -o myboot.html\fR +\f(CW$ bootgraph -addlogs -o "myboot-{date}-{time}"\fR .PP Capture a new boot timeline by automatically rebooting the machine. .IP -\f(CW$ sudo bootgraph -reboot -addlogs -o latestboot.html\fR +\f(CW$ sudo bootgraph -reboot -addlogs -o "latest-{hostname)"\fR .PP Capture a new boot timeline with function trace data. .IP @@ -111,7 +133,7 @@ Capture a new boot timeline with trace & callgraph data. Skip callgraphs smaller .PP Capture a new boot timeline with callgraph data over custom functions. .IP -\f(CW$ sudo bootgraph -reboot -callgraph -filter "acpi_ps_parse_aml,msleep"\fR +\f(CW$ sudo bootgraph -reboot -callgraph -func "acpi_ps_parse_aml,msleep"\fR .PP Capture a brand new boot timeline with manual reboot. .IP @@ -123,6 +145,15 @@ Capture a brand new boot timeline with manual reboot. .IP \f(CW$ sudo bootgraph -callgraph # re-run the tool after restart\fR .PP +.SS "rebuild timeline from logs" +.PP +Rebuild the html from a previous run's logs, using the same options. +.IP +\f(CW$ bootgraph -dmesg dmesg.txt -ftrace ftrace.txt -callgraph\fR +.PP +Rebuild the html with different options. +.IP +\f(CW$ bootgraph -dmesg dmesg.txt -ftrace ftrace.txt -addlogs\fR .SH "SEE ALSO" dmesg(1), update-grub(8), crontab(1), reboot(8) diff --git a/tools/power/pm-graph/sleepgraph.8 b/tools/power/pm-graph/sleepgraph.8 index 610e72ebbc06..fbe7bd3eae8e 100644 --- a/tools/power/pm-graph/sleepgraph.8 +++ b/tools/power/pm-graph/sleepgraph.8 @@ -39,8 +39,9 @@ Pull arguments and config options from a file. \fB-m \fImode\fR Mode to initiate for suspend e.g. standby, freeze, mem (default: mem). .TP -\fB-o \fIsubdir\fR -Override the output subdirectory. Use {date}, {time}, {hostname} for current values. +\fB-o \fIname\fR +Overrides the output subdirectory name when running a new test. +Use {date}, {time}, {hostname} for current values. .sp e.g. suspend-{hostname}-{date}-{time} .TP @@ -52,7 +53,7 @@ disable rtcwake and require a user keypress to resume. Add the dmesg and ftrace logs to the html output. They will be viewable by clicking buttons in the timeline. -.SS "Advanced" +.SS "advanced" .TP \fB-cmd \fIstr\fR Run the timeline over a custom suspend command, e.g. pm-suspend. By default @@ -91,7 +92,7 @@ Include \fIt\fR ms delay after last resume (default: 0 ms). Execute \fIn\fR consecutive tests at \fId\fR seconds intervals. The outputs will be created in a new subdirectory with a summary page: suspend-xN-{date}-{time}. -.SS "Ftrace Debug" +.SS "ftrace debug" .TP \fB-f\fR Use ftrace to create device callgraphs (default: disabled). This can produce @@ -124,12 +125,6 @@ Number of significant digits in timestamps (0:S, [3:ms], 6:us). .SH COMMANDS .TP -\fB-ftrace \fIfile\fR -Create HTML output from an existing ftrace file. -.TP -\fB-dmesg \fIfile\fR -Create HTML output from an existing dmesg file. -.TP \fB-summary \fIindir\fR Create a summary page of all tests in \fIindir\fR. Creates summary.html in the current folder. The output page is a table of tests with @@ -146,6 +141,9 @@ with any options you intend to use to see if they will work. \fB-fpdt\fR Print out the contents of the ACPI Firmware Performance Data Table. .TP +\fB-sysinfo\fR +Print out system info extracted from BIOS. Reads /dev/mem directly instead of going through dmidecode. +.TP \fB-usbtopo\fR Print out the current USB topology with power info. .TP @@ -162,9 +160,16 @@ with -fadd they will also be checked. \fB-flistall\fR Print all ftrace functions capable of being captured. These are all the possible values you can add to trace via the -fadd argument. +.SS "rebuild" +.TP +\fB-ftrace \fIfile\fR +Create HTML output from an existing ftrace file. +.TP +\fB-dmesg \fIfile\fR +Create HTML output from an existing dmesg file. .SH EXAMPLES -.SS "Simple Commands" +.SS "simple commands" Check which suspend modes are currently supported. .IP \f(CW$ sleepgraph -modes\fR @@ -185,12 +190,8 @@ Generate a summary of all timelines in a particular folder. .IP \f(CW$ sleepgraph -summary ~/workspace/myresults/\fR .PP -Re-generate the html output from a previous run's dmesg and ftrace log. -.IP -\f(CW$ sleepgraph -dmesg myhost_mem_dmesg.txt -ftrace myhost_mem_ftrace.txt\fR -.PP -.SS "Capturing Simple Timelines" +.SS "capturing basic timelines" Execute a mem suspend with a 15 second wakeup. Include the logs in the html. .IP \f(CW$ sudo sleepgraph -rtcwake 15 -addlogs\fR @@ -204,7 +205,7 @@ Execute a freeze with no wakeup (require keypress). Change output folder name. \f(CW$ sudo sleepgraph -m freeze -rtcwake off -o "freeze-{hostname}-{date}-{time}"\fR .PP -.SS "Capturing Advanced Timelines" +.SS "capturing advanced timelines" Execute a suspend & include dev mode source calls, limit callbacks to 5ms or larger. .IP \f(CW$ sudo sleepgraph -m mem -rtcwake 15 -dev -mindev 5\fR @@ -222,8 +223,7 @@ Execute a suspend using a custom command. \f(CW$ sudo sleepgraph -cmd "echo mem > /sys/power/state" -rtcwake 15\fR .PP - -.SS "Capturing Timelines with Callgraph Data" +.SS "adding callgraph data" Add device callgraphs. Limit the trace depth and only show callgraphs 10ms or larger. .IP \f(CW$ sudo sleepgraph -m mem -rtcwake 15 -f -maxdepth 5 -mincg 10\fR @@ -235,6 +235,16 @@ Capture a full callgraph across all suspend, then filter the html by a single ph \f(CW$ sleepgraph -dmesg host_mem_dmesg.txt -ftrace host_mem_ftrace.txt -f -cgphase resume .PP +.SS "rebuild timeline from logs" +.PP +Rebuild the html from a previous run's logs, using the same options. +.IP +\f(CW$ sleepgraph -dmesg dmesg.txt -ftrace ftrace.txt -callgraph\fR +.PP +Rebuild the html with different options. +.IP +\f(CW$ sleepgraph -dmesg dmesg.txt -ftrace ftrace.txt -addlogs -srgap\fR + .SH "SEE ALSO" dmesg(1) .PP diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index b11294730771..0dafba2c1e7d 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -57,7 +57,6 @@ unsigned int list_header_only; unsigned int dump_only; unsigned int do_snb_cstates; unsigned int do_knl_cstates; -unsigned int do_skl_residency; unsigned int do_slm_cstates; unsigned int use_c1_residency_msr; unsigned int has_aperf; @@ -93,6 +92,7 @@ unsigned int do_ring_perf_limit_reasons; unsigned int crystal_hz; unsigned long long tsc_hz; int base_cpu; +int do_migrate; double discover_bclk(unsigned int family, unsigned int model); unsigned int has_hwp; /* IA32_PM_ENABLE, IA32_HWP_CAPABILITIES */ /* IA32_HWP_REQUEST, IA32_HWP_STATUS */ @@ -151,6 +151,8 @@ size_t cpu_present_setsize, cpu_affinity_setsize, cpu_subset_size; #define MAX_ADDED_COUNTERS 16 struct thread_data { + struct timeval tv_begin; + struct timeval tv_end; unsigned long long tsc; unsigned long long aperf; unsigned long long mperf; @@ -301,6 +303,9 @@ int for_all_cpus(int (func)(struct thread_data *, struct core_data *, struct pkg int cpu_migrate(int cpu) { + if (!do_migrate) + return 0; + CPU_ZERO_S(cpu_affinity_setsize, cpu_affinity_set); CPU_SET_S(cpu, cpu_affinity_setsize, cpu_affinity_set); if (sched_setaffinity(0, cpu_affinity_setsize, cpu_affinity_set) == -1) @@ -384,8 +389,14 @@ struct msr_counter bic[] = { { 0x0, "CPU" }, { 0x0, "Mod%c6" }, { 0x0, "sysfs" }, + { 0x0, "Totl%C0" }, + { 0x0, "Any%C0" }, + { 0x0, "GFX%C0" }, + { 0x0, "CPUGFX%" }, }; + + #define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter)) #define BIC_Package (1ULL << 0) #define BIC_Avg_MHz (1ULL << 1) @@ -426,6 +437,10 @@ struct msr_counter bic[] = { #define BIC_CPU (1ULL << 36) #define BIC_Mod_c6 (1ULL << 37) #define BIC_sysfs (1ULL << 38) +#define BIC_Totl_c0 (1ULL << 39) +#define BIC_Any_c0 (1ULL << 40) +#define BIC_GFX_c0 (1ULL << 41) +#define BIC_CPUGFX (1ULL << 42) unsigned long long bic_enabled = 0xFFFFFFFFFFFFFFFFULL; unsigned long long bic_present = BIC_sysfs; @@ -521,6 +536,8 @@ void print_header(char *delim) struct msr_counter *mp; int printed = 0; + if (debug) + outp += sprintf(outp, "usec %s", delim); if (DO_BIC(BIC_Package)) outp += sprintf(outp, "%sPackage", (printed++ ? delim : "")); if (DO_BIC(BIC_Core)) @@ -599,12 +616,14 @@ void print_header(char *delim) if (DO_BIC(BIC_GFXMHz)) outp += sprintf(outp, "%sGFXMHz", (printed++ ? delim : "")); - if (do_skl_residency) { + if (DO_BIC(BIC_Totl_c0)) outp += sprintf(outp, "%sTotl%%C0", (printed++ ? delim : "")); + if (DO_BIC(BIC_Any_c0)) outp += sprintf(outp, "%sAny%%C0", (printed++ ? delim : "")); + if (DO_BIC(BIC_GFX_c0)) outp += sprintf(outp, "%sGFX%%C0", (printed++ ? delim : "")); + if (DO_BIC(BIC_CPUGFX)) outp += sprintf(outp, "%sCPUGFX%%", (printed++ ? delim : "")); - } if (DO_BIC(BIC_Pkgpc2)) outp += sprintf(outp, "%sPkg%%pc2", (printed++ ? delim : "")); @@ -771,6 +790,14 @@ int format_counters(struct thread_data *t, struct core_data *c, (cpu_subset && !CPU_ISSET_S(t->cpu_id, cpu_subset_size, cpu_subset))) return 0; + if (debug) { + /* on each row, print how many usec each timestamp took to gather */ + struct timeval tv; + + timersub(&t->tv_end, &t->tv_begin, &tv); + outp += sprintf(outp, "%5ld\t", tv.tv_sec * 1000000 + tv.tv_usec); + } + interval_float = tv_delta.tv_sec + tv_delta.tv_usec/1000000.0; tsc = t->tsc * tsc_tweak; @@ -912,12 +939,14 @@ int format_counters(struct thread_data *t, struct core_data *c, outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->gfx_mhz); /* Totl%C0, Any%C0 GFX%C0 CPUGFX% */ - if (do_skl_residency) { + if (DO_BIC(BIC_Totl_c0)) outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pkg_wtd_core_c0/tsc); + if (DO_BIC(BIC_Any_c0)) outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pkg_any_core_c0/tsc); + if (DO_BIC(BIC_GFX_c0)) outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pkg_any_gfxe_c0/tsc); + if (DO_BIC(BIC_CPUGFX)) outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pkg_both_core_gfxe_c0/tsc); - } if (DO_BIC(BIC_Pkgpc2)) outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc2/tsc); @@ -1038,12 +1067,16 @@ delta_package(struct pkg_data *new, struct pkg_data *old) int i; struct msr_counter *mp; - if (do_skl_residency) { + + if (DO_BIC(BIC_Totl_c0)) old->pkg_wtd_core_c0 = new->pkg_wtd_core_c0 - old->pkg_wtd_core_c0; + if (DO_BIC(BIC_Any_c0)) old->pkg_any_core_c0 = new->pkg_any_core_c0 - old->pkg_any_core_c0; + if (DO_BIC(BIC_GFX_c0)) old->pkg_any_gfxe_c0 = new->pkg_any_gfxe_c0 - old->pkg_any_gfxe_c0; + if (DO_BIC(BIC_CPUGFX)) old->pkg_both_core_gfxe_c0 = new->pkg_both_core_gfxe_c0 - old->pkg_both_core_gfxe_c0; - } + old->pc2 = new->pc2 - old->pc2; if (DO_BIC(BIC_Pkgpc3)) old->pc3 = new->pc3 - old->pc3; @@ -1292,12 +1325,14 @@ int sum_counters(struct thread_data *t, struct core_data *c, if (!(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE)) return 0; - if (do_skl_residency) { + if (DO_BIC(BIC_Totl_c0)) average.packages.pkg_wtd_core_c0 += p->pkg_wtd_core_c0; + if (DO_BIC(BIC_Any_c0)) average.packages.pkg_any_core_c0 += p->pkg_any_core_c0; + if (DO_BIC(BIC_GFX_c0)) average.packages.pkg_any_gfxe_c0 += p->pkg_any_gfxe_c0; + if (DO_BIC(BIC_CPUGFX)) average.packages.pkg_both_core_gfxe_c0 += p->pkg_both_core_gfxe_c0; - } average.packages.pc2 += p->pc2; if (DO_BIC(BIC_Pkgpc3)) @@ -1357,12 +1392,14 @@ void compute_average(struct thread_data *t, struct core_data *c, average.cores.c7 /= topo.num_cores; average.cores.mc6_us /= topo.num_cores; - if (do_skl_residency) { + if (DO_BIC(BIC_Totl_c0)) average.packages.pkg_wtd_core_c0 /= topo.num_packages; + if (DO_BIC(BIC_Any_c0)) average.packages.pkg_any_core_c0 /= topo.num_packages; + if (DO_BIC(BIC_GFX_c0)) average.packages.pkg_any_gfxe_c0 /= topo.num_packages; + if (DO_BIC(BIC_CPUGFX)) average.packages.pkg_both_core_gfxe_c0 /= topo.num_packages; - } average.packages.pc2 /= topo.num_packages; if (DO_BIC(BIC_Pkgpc3)) @@ -1482,6 +1519,9 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) struct msr_counter *mp; int i; + + gettimeofday(&t->tv_begin, (struct timezone *)NULL); + if (cpu_migrate(cpu)) { fprintf(outf, "Could not migrate to CPU %d\n", cpu); return -1; @@ -1565,7 +1605,7 @@ retry: /* collect core counters only for 1st thread in core */ if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE)) - return 0; + goto done; if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates) { if (get_msr(cpu, MSR_CORE_C3_RESIDENCY, &c->c3)) @@ -1601,15 +1641,21 @@ retry: /* collect package counters only for 1st core in package */ if (!(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE)) - return 0; + goto done; - if (do_skl_residency) { + if (DO_BIC(BIC_Totl_c0)) { if (get_msr(cpu, MSR_PKG_WEIGHTED_CORE_C0_RES, &p->pkg_wtd_core_c0)) return -10; + } + if (DO_BIC(BIC_Any_c0)) { if (get_msr(cpu, MSR_PKG_ANY_CORE_C0_RES, &p->pkg_any_core_c0)) return -11; + } + if (DO_BIC(BIC_GFX_c0)) { if (get_msr(cpu, MSR_PKG_ANY_GFXE_C0_RES, &p->pkg_any_gfxe_c0)) return -12; + } + if (DO_BIC(BIC_CPUGFX)) { if (get_msr(cpu, MSR_PKG_BOTH_CORE_GFXE_C0_RES, &p->pkg_both_core_gfxe_c0)) return -13; } @@ -1688,6 +1734,8 @@ retry: if (get_mp(cpu, mp, &p->counter[i])) return -10; } +done: + gettimeofday(&t->tv_end, (struct timezone *)NULL); return 0; } @@ -3895,6 +3943,9 @@ void decode_misc_enable_msr(void) { unsigned long long msr; + if (!genuine_intel) + return; + if (!get_msr(base_cpu, MSR_IA32_MISC_ENABLE, &msr)) fprintf(outf, "cpu%d: MSR_IA32_MISC_ENABLE: 0x%08llx (%sTCC %sEIST %sMWAIT %sPREFETCH %sTURBO)\n", base_cpu, msr, @@ -4198,7 +4249,12 @@ void process_cpuid() BIC_PRESENT(BIC_Pkgpc10); } do_irtl_hsw = has_hsw_msrs(family, model); - do_skl_residency = has_skl_msrs(family, model); + if (has_skl_msrs(family, model)) { + BIC_PRESENT(BIC_Totl_c0); + BIC_PRESENT(BIC_Any_c0); + BIC_PRESENT(BIC_GFX_c0); + BIC_PRESENT(BIC_CPUGFX); + } do_slm_cstates = is_slm(family, model); do_knl_cstates = is_knl(family, model); @@ -4578,7 +4634,7 @@ int get_and_dump_counters(void) } void print_version() { - fprintf(outf, "turbostat version 17.04.12" + fprintf(outf, "turbostat version 17.06.23" " - Len Brown <lenb@kernel.org>\n"); } @@ -4951,6 +5007,7 @@ void cmdline(int argc, char **argv) {"hide", required_argument, 0, 'H'}, // meh, -h taken by --help {"Joules", no_argument, 0, 'J'}, {"list", no_argument, 0, 'l'}, + {"migrate", no_argument, 0, 'm'}, {"out", required_argument, 0, 'o'}, {"quiet", no_argument, 0, 'q'}, {"show", required_argument, 0, 's'}, @@ -4962,7 +5019,7 @@ void cmdline(int argc, char **argv) progname = argv[0]; - while ((opt = getopt_long_only(argc, argv, "+C:c:Ddhi:JM:m:o:qST:v", + while ((opt = getopt_long_only(argc, argv, "+C:c:Ddhi:Jmo:qST:v", long_options, &option_index)) != -1) { switch (opt) { case 'a': @@ -5005,6 +5062,9 @@ void cmdline(int argc, char **argv) list_header_only++; quiet++; break; + case 'm': + do_migrate = 1; + break; case 'o': outf = fopen_or_die(optarg, "w"); break; diff --git a/tools/power/x86/x86_energy_perf_policy/Makefile b/tools/power/x86/x86_energy_perf_policy/Makefile index 971c9ffdcb50..a711eec0c895 100644 --- a/tools/power/x86/x86_energy_perf_policy/Makefile +++ b/tools/power/x86/x86_energy_perf_policy/Makefile @@ -1,10 +1,27 @@ -DESTDIR ?= +CC = $(CROSS_COMPILE)gcc +BUILD_OUTPUT := $(CURDIR) +PREFIX := /usr +DESTDIR := + +ifeq ("$(origin O)", "command line") + BUILD_OUTPUT := $(O) +endif x86_energy_perf_policy : x86_energy_perf_policy.c +CFLAGS += -Wall +CFLAGS += -DMSRHEADER='"../../../../arch/x86/include/asm/msr-index.h"' + +%: %.c + @mkdir -p $(BUILD_OUTPUT) + $(CC) $(CFLAGS) $< -o $(BUILD_OUTPUT)/$@ +.PHONY : clean clean : - rm -f x86_energy_perf_policy + @rm -f $(BUILD_OUTPUT)/x86_energy_perf_policy + +install : x86_energy_perf_policy + install -d $(DESTDIR)$(PREFIX)/bin + install $(BUILD_OUTPUT)/x86_energy_perf_policy $(DESTDIR)$(PREFIX)/bin/x86_energy_perf_policy + install -d $(DESTDIR)$(PREFIX)/share/man/man8 + install x86_energy_perf_policy.8 $(DESTDIR)$(PREFIX)/share/man/man8 -install : - install x86_energy_perf_policy ${DESTDIR}/usr/bin/ - install x86_energy_perf_policy.8 ${DESTDIR}/usr/share/man/man8/ diff --git a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.8 b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.8 index 8eaaad648cdb..17db1c3af4d0 100644 --- a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.8 +++ b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.8 @@ -1,104 +1,213 @@ -.\" This page Copyright (C) 2010 Len Brown <len.brown@intel.com> +.\" This page Copyright (C) 2010 - 2015 Len Brown <len.brown@intel.com> .\" Distributed under the GPL, Copyleft 1994. .TH X86_ENERGY_PERF_POLICY 8 .SH NAME -x86_energy_perf_policy \- read or write MSR_IA32_ENERGY_PERF_BIAS +x86_energy_perf_policy \- Manage Energy vs. Performance Policy via x86 Model Specific Registers .SH SYNOPSIS -.ft B .B x86_energy_perf_policy -.RB [ "\-c cpu" ] -.RB [ "\-v" ] -.RB "\-r" +.RB "[ options ] [ scope ] [field \ value]" .br -.B x86_energy_perf_policy -.RB [ "\-c cpu" ] -.RB [ "\-v" ] -.RB 'performance' +.RB "scope: \-\-cpu\ cpu-list | \-\-pkg\ pkg-list" .br -.B x86_energy_perf_policy -.RB [ "\-c cpu" ] -.RB [ "\-v" ] -.RB 'normal' +.RB "cpu-list, pkg-list: # | #,# | #-# | all" .br -.B x86_energy_perf_policy -.RB [ "\-c cpu" ] -.RB [ "\-v" ] -.RB 'powersave' +.RB "field: \-\-all | \-\-epb | \-\-hwp-epp | \-\-hwp-min | \-\-hwp-max | \-\-hwp-desired" .br -.B x86_energy_perf_policy -.RB [ "\-c cpu" ] -.RB [ "\-v" ] -.RB n +.RB "other: (\-\-force | \-\-hwp-enable | \-\-turbo-enable) value)" .br +.RB "value: # | default | performance | balance-performance | balance-power | power" .SH DESCRIPTION \fBx86_energy_perf_policy\fP -allows software to convey -its policy for the relative importance of performance -versus energy savings to the processor. +displays and updates energy-performance policy settings specific to +Intel Architecture Processors. Settings are accessed via Model Specific Register (MSR) +updates, no matter if the Linux cpufreq sub-system is enabled or not. -The processor uses this information in model-specific ways -when it must select trade-offs between performance and -energy efficiency. +Policy in MSR_IA32_ENERGY_PERF_BIAS (EPB) +may affect a wide range of hardware decisions, +such as how aggressively the hardware enters and exits CPU idle states (C-states) +and Processor Performance States (P-states). +This policy hint does not replace explicit OS C-state and P-state selection. +Rather, it tells the hardware how aggressively to implement those selections. +Further, it allows the OS to influence energy/performance trade-offs where there +is no software interface, such as in the opportunistic "turbo-mode" P-state range. +Note that MSR_IA32_ENERGY_PERF_BIAS is defined per CPU, +but some implementations +share a single MSR among all CPUs in each processor package. +On those systems, a write to EPB on one processor will +be visible, and will have an effect, on all CPUs +in the same processor package. -This policy hint does not supersede Processor Performance states -(P-states) or CPU Idle power states (C-states), but allows -software to have influence where it would otherwise be unable -to express a preference. +Hardware P-States (HWP) are effectively an expansion of hardware +P-state control from the opportunistic turbo-mode P-state range +to include the entire range of available P-states. +On Broadwell Xeon, the initial HWP implementation, EBP influenced HWP. +That influence was removed in subsequent generations, +where it was moved to the +Energy_Performance_Preference (EPP) field in +a pair of dedicated MSRs -- MSR_IA32_HWP_REQUEST and MSR_IA32_HWP_REQUEST_PKG. -For example, this setting may tell the hardware how -aggressively or conservatively to control frequency -in the "turbo range" above the explicitly OS-controlled -P-state frequency range. It may also tell the hardware -how aggressively is should enter the OS requested C-states. +EPP is the most commonly managed knob in HWP mode, +but MSR_IA32_HWP_REQUEST also allows the user to specify +minimum-frequency for Quality-of-Service, +and maximum-frequency for power-capping. +MSR_IA32_HWP_REQUEST is defined per-CPU. -Support for this feature is indicated by CPUID.06H.ECX.bit3 -per the Intel Architectures Software Developer's Manual. +MSR_IA32_HWP_REQUEST_PKG has the same capability as MSR_IA32_HWP_REQUEST, +but it can simultaneously set the default policy for all CPUs within a package. +A bit in per-CPU MSR_IA32_HWP_REQUEST indicates whether it is +over-ruled-by or exempt-from MSR_IA32_HWP_REQUEST_PKG. -.SS Options -\fB-c\fP limits operation to a single CPU. -The default is to operate on all CPUs. -Note that MSR_IA32_ENERGY_PERF_BIAS is defined per -logical processor, but that the initial implementations -of the MSR were shared among all processors in each package. -.PP -\fB-v\fP increases verbosity. By default -x86_energy_perf_policy is silent. -.PP -\fB-r\fP is for "read-only" mode - the unchanged state -is read and displayed. +MSR_HWP_CAPABILITIES shows the default values for the fields +in MSR_IA32_HWP_REQUEST. It is displayed when no values +are being written. + +.SS SCOPE OPTIONS .PP -.I performance -Set a policy where performance is paramount. -The processor will be unwilling to sacrifice any performance -for the sake of energy saving. This is the hardware default. +\fB-c, --cpu\fP Operate on the MSR_IA32_HWP_REQUEST for each CPU in a CPU-list. +The CPU-list may be comma-separated CPU numbers, with dash for range +or the string "all". Eg. '--cpu 1,4,6-8' or '--cpu all'. +When --cpu is used, \fB--hwp-use-pkg\fP is available, which specifies whether the per-cpu +MSR_IA32_HWP_REQUEST should be over-ruled by MSR_IA32_HWP_REQUEST_PKG (1), +or exempt from MSR_IA32_HWP_REQUEST_PKG (0). + +\fB-p, --pkg\fP Operate on the MSR_IA32_HWP_REQUEST_PKG for each package in the package-list. +The list is a string of individual package numbers separated +by commas, and or ranges of package numbers separated by a dash, +or the string "all". +For example '--pkg 1,3' or '--pkg all' + +.SS VALUE OPTIONS .PP -.I normal +.I normal | default Set a policy with a normal balance between performance and energy efficiency. The processor will tolerate minor performance compromise for potentially significant energy savings. -This reasonable default for most desktops and servers. +This is a reasonable default for most desktops and servers. +"default" is a synonym for "normal". .PP -.I powersave +.I performance +Set a policy for maximum performance, +accepting no performance sacrifice for the benefit of energy efficiency. +.PP +.I balance-performance +Set a policy with a high priority on performance, +but allowing some performance loss to benefit energy efficiency. +.PP +.I balance-power +Set a policy where the performance and power are balanced. +This is the default. +.PP +.I power Set a policy where the processor can accept -a measurable performance hit to maximize energy efficiency. +a measurable performance impact to maximize energy efficiency. + .PP -.I n -Set MSR_IA32_ENERGY_PERF_BIAS to the specified number. -The range of valid numbers is 0-15, where 0 is maximum -performance and 15 is maximum energy efficiency. +The following table shows the mapping from the value strings above to actual MSR values. +This mapping is defined in the Linux-kernel header, msr-index.h. +.nf +VALUE STRING EPB EPP +performance 0 0 +balance-performance 4 128 +normal, default 6 128 +balance-power 8 192 +power 15 255 +.fi +.PP +For MSR_IA32_HWP_REQUEST performance fields +(--hwp-min, --hwp-max, --hwp-desired), the value option +is in units of 100 MHz, Eg. 12 signifies 1200 MHz. + +.SS FIELD OPTIONS +\fB-a, --all value-string\fP Sets all EPB and EPP and HWP limit fields to the value associated with +the value-string. In addition, enables turbo-mode and HWP-mode, if they were previous disabled. +Thus "--all normal" will set a system without cpufreq into a well known configuration. +.PP +\fB-B, --epb\fP set EPB per-core or per-package. +See value strings in the table above. +.PP +\fB-d, --debug\fP debug increases verbosity. By default +x86_energy_perf_policy is silent for updates, +and verbose for read-only mode. +.PP +\fB-P, --hwp-epp\fP set HWP.EPP per-core or per-package. +See value strings in the table above. +.PP +\fB-m, --hwp-min\fP request HWP to not go below the specified core/bus ratio. +The "default" is the value found in IA32_HWP_CAPABILITIES.min. +.PP +\fB-M, --hwp-max\fP request HWP not exceed a the specified core/bus ratio. +The "default" is the value found in IA32_HWP_CAPABILITIES.max. +.PP +\fB-D, --hwp-desired\fP request HWP 'desired' frequency. +The "normal" setting is 0, which +corresponds to 'full autonomous' HWP control. +Non-zero performance values request a specific performance +level on this processor, specified in multiples of 100 MHz. +.PP +\fB-w, --hwp-window\fP specify integer number of microsec +in the sliding window that HWP uses to maintain average frequency. +This parameter is meaningful only when the "desired" field above is non-zero. +Default is 0, allowing the HW to choose. +.SH OTHER OPTIONS +.PP +\fB-f, --force\fP writes the specified values without bounds checking. +.PP +\fB-U, --hwp-use-pkg\fP (0 | 1), when used in conjunction with --cpu, +indicates whether the per-CPU MSR_IA32_HWP_REQUEST should be overruled (1) +or exempt (0) from per-Package MSR_IA32_HWP_REQUEST_PKG settings. +The default is exempt. +.PP +\fB-H, --hwp-enable\fP enable HardWare-P-state (HWP) mode. Once enabled, system RESET is required to disable HWP mode. +.PP +\fB-t, --turbo-enable\fP enable (1) or disable (0) turbo mode. +.PP +\fB-v, --version\fP print version and exit. +.PP +If no request to change policy is made, +the default behavior is to read +and display the current system state, +including the default capabilities. +.SH WARNING +.PP +This utility writes directly to Model Specific Registers. +There is no locking or coordination should this utility +be used to modify HWP limit fields at the same time that +intel_pstate's sysfs attributes access the same MSRs. +.PP +Note that --hwp-desired and --hwp-window are considered experimental. +Future versions of Linux reserve the right to access these +fields internally -- potentially conflicting with user-space access. +.SH EXAMPLE +.nf +# sudo x86_energy_perf_policy +cpu0: EPB 6 +cpu0: HWP_REQ: min 6 max 35 des 0 epp 128 window 0x0 (0*10^0us) use_pkg 0 +cpu0: HWP_CAP: low 1 eff 8 guar 27 high 35 +cpu1: EPB 6 +cpu1: HWP_REQ: min 6 max 35 des 0 epp 128 window 0x0 (0*10^0us) use_pkg 0 +cpu1: HWP_CAP: low 1 eff 8 guar 27 high 35 +cpu2: EPB 6 +cpu2: HWP_REQ: min 6 max 35 des 0 epp 128 window 0x0 (0*10^0us) use_pkg 0 +cpu2: HWP_CAP: low 1 eff 8 guar 27 high 35 +cpu3: EPB 6 +cpu3: HWP_REQ: min 6 max 35 des 0 epp 128 window 0x0 (0*10^0us) use_pkg 0 +cpu3: HWP_CAP: low 1 eff 8 guar 27 high 35 +.fi .SH NOTES -.B "x86_energy_perf_policy " +.B "x86_energy_perf_policy" runs only as root. .SH FILES .ta .nf /dev/cpu/*/msr .fi - .SH "SEE ALSO" +.nf msr(4) +Intel(R) 64 and IA-32 Architectures Software Developer's Manual +.fi .PP .SH AUTHORS .nf -Written by Len Brown <len.brown@intel.com> +Len Brown diff --git a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c index 40b3e5482f8a..65bbe627a425 100644 --- a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c +++ b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c @@ -3,322 +3,1424 @@ * policy preference bias on recent X86 processors. */ /* - * Copyright (c) 2010, Intel Corporation. + * Copyright (c) 2010 - 2017 Intel Corporation. * Len Brown <len.brown@intel.com> * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + * This program is released under GPL v2 */ +#define _GNU_SOURCE +#include MSRHEADER #include <stdio.h> #include <unistd.h> #include <sys/types.h> +#include <sched.h> #include <sys/stat.h> #include <sys/resource.h> +#include <getopt.h> +#include <err.h> #include <fcntl.h> #include <signal.h> #include <sys/time.h> +#include <limits.h> #include <stdlib.h> #include <string.h> +#include <cpuid.h> +#include <errno.h> + +#define OPTARG_NORMAL (INT_MAX - 1) +#define OPTARG_POWER (INT_MAX - 2) +#define OPTARG_BALANCE_POWER (INT_MAX - 3) +#define OPTARG_BALANCE_PERFORMANCE (INT_MAX - 4) +#define OPTARG_PERFORMANCE (INT_MAX - 5) + +struct msr_hwp_cap { + unsigned char highest; + unsigned char guaranteed; + unsigned char efficient; + unsigned char lowest; +}; -unsigned int verbose; /* set with -v */ -unsigned int read_only; /* set with -r */ +struct msr_hwp_request { + unsigned char hwp_min; + unsigned char hwp_max; + unsigned char hwp_desired; + unsigned char hwp_epp; + unsigned int hwp_window; + unsigned char hwp_use_pkg; +} req_update; + +unsigned int debug; +unsigned int verbose; +unsigned int force; char *progname; -unsigned long long new_bias; -int cpu = -1; +int base_cpu; +unsigned char update_epb; +unsigned long long new_epb; +unsigned char turbo_is_enabled; +unsigned char update_turbo; +unsigned char turbo_update_value; +unsigned char update_hwp_epp; +unsigned char update_hwp_min; +unsigned char update_hwp_max; +unsigned char update_hwp_desired; +unsigned char update_hwp_window; +unsigned char update_hwp_use_pkg; +unsigned char update_hwp_enable; +#define hwp_update_enabled() (update_hwp_enable | update_hwp_epp | update_hwp_max | update_hwp_min | update_hwp_desired | update_hwp_window | update_hwp_use_pkg) +int max_cpu_num; +int max_pkg_num; +#define MAX_PACKAGES 64 +unsigned int first_cpu_in_pkg[MAX_PACKAGES]; +unsigned long long pkg_present_set; +unsigned long long pkg_selected_set; +cpu_set_t *cpu_present_set; +cpu_set_t *cpu_selected_set; +int genuine_intel; + +size_t cpu_setsize; + +char *proc_stat = "/proc/stat"; + +unsigned int has_epb; /* MSR_IA32_ENERGY_PERF_BIAS */ +unsigned int has_hwp; /* IA32_PM_ENABLE, IA32_HWP_CAPABILITIES */ + /* IA32_HWP_REQUEST, IA32_HWP_STATUS */ +unsigned int has_hwp_notify; /* IA32_HWP_INTERRUPT */ +unsigned int has_hwp_activity_window; /* IA32_HWP_REQUEST[bits 41:32] */ +unsigned int has_hwp_epp; /* IA32_HWP_REQUEST[bits 31:24] */ +unsigned int has_hwp_request_pkg; /* IA32_HWP_REQUEST_PKG */ + +unsigned int bdx_highest_ratio; /* - * Usage: - * - * -c cpu: limit action to a single CPU (default is all CPUs) - * -v: verbose output (can invoke more than once) - * -r: read-only, don't change any settings - * - * performance - * Performance is paramount. - * Unwilling to sacrifice any performance - * for the sake of energy saving. (hardware default) - * - * normal - * Can tolerate minor performance compromise - * for potentially significant energy savings. - * (reasonable default for most desktops and servers) - * - * powersave - * Can tolerate significant performance hit - * to maximize energy savings. - * - * n - * a numerical value to write to the underlying MSR. + * maintain compatibility with original implementation, but don't document it: */ void usage(void) { - printf("%s: [-c cpu] [-v] " - "(-r | 'performance' | 'normal' | 'powersave' | n)\n", - progname); + fprintf(stderr, "%s [options] [scope][field value]\n", progname); + fprintf(stderr, "scope: --cpu cpu-list [--hwp-use-pkg #] | --pkg pkg-list\n"); + fprintf(stderr, "field: --all | --epb | --hwp-epp | --hwp-min | --hwp-max | --hwp-desired\n"); + fprintf(stderr, "other: --hwp-enable | --turbo-enable (0 | 1) | --help | --force\n"); + fprintf(stderr, + "value: ( # | \"normal\" | \"performance\" | \"balance-performance\" | \"balance-power\"| \"power\")\n"); + fprintf(stderr, "--hwp-window usec\n"); + + fprintf(stderr, "Specify only Energy Performance BIAS (legacy usage):\n"); + fprintf(stderr, "%s: [-c cpu] [-v] (-r | policy-value )\n", progname); + exit(1); } -#define MSR_IA32_ENERGY_PERF_BIAS 0x000001b0 +/* + * If bdx_highest_ratio is set, + * then we must translate between MSR format and simple ratio + * used on the cmdline. + */ +int ratio_2_msr_perf(int ratio) +{ + int msr_perf; + + if (!bdx_highest_ratio) + return ratio; + + msr_perf = ratio * 255 / bdx_highest_ratio; + + if (debug) + fprintf(stderr, "%d = ratio_to_msr_perf(%d)\n", msr_perf, ratio); + + return msr_perf; +} +int msr_perf_2_ratio(int msr_perf) +{ + int ratio; + double d; + + if (!bdx_highest_ratio) + return msr_perf; + + d = (double)msr_perf * (double) bdx_highest_ratio / 255.0; + d = d + 0.5; /* round */ + ratio = (int)d; + + if (debug) + fprintf(stderr, "%d = msr_perf_ratio(%d) {%f}\n", ratio, msr_perf, d); + + return ratio; +} +int parse_cmdline_epb(int i) +{ + if (!has_epb) + errx(1, "EPB not enabled on this platform"); + + update_epb = 1; + + switch (i) { + case OPTARG_POWER: + return ENERGY_PERF_BIAS_POWERSAVE; + case OPTARG_BALANCE_POWER: + return ENERGY_PERF_BIAS_BALANCE_POWERSAVE; + case OPTARG_NORMAL: + return ENERGY_PERF_BIAS_NORMAL; + case OPTARG_BALANCE_PERFORMANCE: + return ENERGY_PERF_BIAS_BALANCE_PERFORMANCE; + case OPTARG_PERFORMANCE: + return ENERGY_PERF_BIAS_PERFORMANCE; + } + if (i < 0 || i > ENERGY_PERF_BIAS_POWERSAVE) + errx(1, "--epb must be from 0 to 15"); + return i; +} + +#define HWP_CAP_LOWEST 0 +#define HWP_CAP_HIGHEST 255 + +/* + * "performance" changes hwp_min to cap.highest + * All others leave it at cap.lowest + */ +int parse_cmdline_hwp_min(int i) +{ + update_hwp_min = 1; + + switch (i) { + case OPTARG_POWER: + case OPTARG_BALANCE_POWER: + case OPTARG_NORMAL: + case OPTARG_BALANCE_PERFORMANCE: + return HWP_CAP_LOWEST; + case OPTARG_PERFORMANCE: + return HWP_CAP_HIGHEST; + } + return i; +} +/* + * "power" changes hwp_max to cap.lowest + * All others leave it at cap.highest + */ +int parse_cmdline_hwp_max(int i) +{ + update_hwp_max = 1; + + switch (i) { + case OPTARG_POWER: + return HWP_CAP_LOWEST; + case OPTARG_NORMAL: + case OPTARG_BALANCE_POWER: + case OPTARG_BALANCE_PERFORMANCE: + case OPTARG_PERFORMANCE: + return HWP_CAP_HIGHEST; + } + return i; +} +/* + * for --hwp-des, all strings leave it in autonomous mode + * If you want to change it, you need to explicitly pick a value + */ +int parse_cmdline_hwp_desired(int i) +{ + update_hwp_desired = 1; + + switch (i) { + case OPTARG_POWER: + case OPTARG_BALANCE_POWER: + case OPTARG_BALANCE_PERFORMANCE: + case OPTARG_NORMAL: + case OPTARG_PERFORMANCE: + return 0; /* autonomous */ + } + return i; +} + +int parse_cmdline_hwp_window(int i) +{ + unsigned int exponent; + + update_hwp_window = 1; + + switch (i) { + case OPTARG_POWER: + case OPTARG_BALANCE_POWER: + case OPTARG_NORMAL: + case OPTARG_BALANCE_PERFORMANCE: + case OPTARG_PERFORMANCE: + return 0; + } + if (i < 0 || i > 1270000000) { + fprintf(stderr, "--hwp-window: 0 for auto; 1 - 1270000000 usec for window duration\n"); + usage(); + } + for (exponent = 0; ; ++exponent) { + if (debug) + printf("%d 10^%d\n", i, exponent); + + if (i <= 127) + break; + + i = i / 10; + } + if (debug) + fprintf(stderr, "%d*10^%d: 0x%x\n", i, exponent, (exponent << 7) | i); + + return (exponent << 7) | i; +} +int parse_cmdline_hwp_epp(int i) +{ + update_hwp_epp = 1; + + switch (i) { + case OPTARG_POWER: + return HWP_EPP_POWERSAVE; + case OPTARG_BALANCE_POWER: + return HWP_EPP_BALANCE_POWERSAVE; + case OPTARG_NORMAL: + case OPTARG_BALANCE_PERFORMANCE: + return HWP_EPP_BALANCE_PERFORMANCE; + case OPTARG_PERFORMANCE: + return HWP_EPP_PERFORMANCE; + } + if (i < 0 || i > 0xff) { + fprintf(stderr, "--hwp-epp must be from 0 to 0xff\n"); + usage(); + } + return i; +} +int parse_cmdline_turbo(int i) +{ + update_turbo = 1; + + switch (i) { + case OPTARG_POWER: + return 0; + case OPTARG_NORMAL: + case OPTARG_BALANCE_POWER: + case OPTARG_BALANCE_PERFORMANCE: + case OPTARG_PERFORMANCE: + return 1; + } + if (i < 0 || i > 1) { + fprintf(stderr, "--turbo-enable: 1 to enable, 0 to disable\n"); + usage(); + } + return i; +} + +int parse_optarg_string(char *s) +{ + int i; + char *endptr; + + if (!strncmp(s, "default", 7)) + return OPTARG_NORMAL; + + if (!strncmp(s, "normal", 6)) + return OPTARG_NORMAL; + + if (!strncmp(s, "power", 9)) + return OPTARG_POWER; + + if (!strncmp(s, "balance-power", 17)) + return OPTARG_BALANCE_POWER; + + if (!strncmp(s, "balance-performance", 19)) + return OPTARG_BALANCE_PERFORMANCE; + + if (!strncmp(s, "performance", 11)) + return OPTARG_PERFORMANCE; + + i = strtol(s, &endptr, 0); + if (s == endptr) { + fprintf(stderr, "no digits in \"%s\"\n", s); + usage(); + } + if (i == LONG_MIN || i == LONG_MAX) + errx(-1, "%s", s); + + if (i > 0xFF) + errx(-1, "%d (0x%x) must be < 256", i, i); + + if (i < 0) + errx(-1, "%d (0x%x) must be >= 0", i, i); + return i; +} + +void parse_cmdline_all(char *s) +{ + force++; + update_hwp_enable = 1; + req_update.hwp_min = parse_cmdline_hwp_min(parse_optarg_string(s)); + req_update.hwp_max = parse_cmdline_hwp_max(parse_optarg_string(s)); + req_update.hwp_epp = parse_cmdline_hwp_epp(parse_optarg_string(s)); + if (has_epb) + new_epb = parse_cmdline_epb(parse_optarg_string(s)); + turbo_update_value = parse_cmdline_turbo(parse_optarg_string(s)); + req_update.hwp_desired = parse_cmdline_hwp_desired(parse_optarg_string(s)); + req_update.hwp_window = parse_cmdline_hwp_window(parse_optarg_string(s)); +} + +void validate_cpu_selected_set(void) +{ + int cpu; + + if (CPU_COUNT_S(cpu_setsize, cpu_selected_set) == 0) + errx(0, "no CPUs requested"); + + for (cpu = 0; cpu <= max_cpu_num; ++cpu) { + if (CPU_ISSET_S(cpu, cpu_setsize, cpu_selected_set)) + if (!CPU_ISSET_S(cpu, cpu_setsize, cpu_present_set)) + errx(1, "Requested cpu% is not present", cpu); + } +} + +void parse_cmdline_cpu(char *s) +{ + char *startp, *endp; + int cpu = 0; + + if (pkg_selected_set) { + usage(); + errx(1, "--cpu | --pkg"); + } + cpu_selected_set = CPU_ALLOC((max_cpu_num + 1)); + if (cpu_selected_set == NULL) + err(1, "cpu_selected_set"); + CPU_ZERO_S(cpu_setsize, cpu_selected_set); + + for (startp = s; startp && *startp;) { + + if (*startp == ',') { + startp++; + continue; + } + + if (*startp == '-') { + int end_cpu; -#define BIAS_PERFORMANCE 0 -#define BIAS_BALANCE 6 -#define BIAS_POWERSAVE 15 + startp++; + end_cpu = strtol(startp, &endp, 10); + if (startp == endp) + continue; + + while (cpu <= end_cpu) { + if (cpu > max_cpu_num) + errx(1, "Requested cpu%d exceeds max cpu%d", cpu, max_cpu_num); + CPU_SET_S(cpu, cpu_setsize, cpu_selected_set); + cpu++; + } + startp = endp; + continue; + } + + if (strncmp(startp, "all", 3) == 0) { + for (cpu = 0; cpu <= max_cpu_num; cpu += 1) { + if (CPU_ISSET_S(cpu, cpu_setsize, cpu_present_set)) + CPU_SET_S(cpu, cpu_setsize, cpu_selected_set); + } + startp += 3; + if (*startp == 0) + break; + } + /* "--cpu even" is not documented */ + if (strncmp(startp, "even", 4) == 0) { + for (cpu = 0; cpu <= max_cpu_num; cpu += 2) { + if (CPU_ISSET_S(cpu, cpu_setsize, cpu_present_set)) + CPU_SET_S(cpu, cpu_setsize, cpu_selected_set); + } + startp += 4; + if (*startp == 0) + break; + } + + /* "--cpu odd" is not documented */ + if (strncmp(startp, "odd", 3) == 0) { + for (cpu = 1; cpu <= max_cpu_num; cpu += 2) { + if (CPU_ISSET_S(cpu, cpu_setsize, cpu_present_set)) + CPU_SET_S(cpu, cpu_setsize, cpu_selected_set); + } + startp += 3; + if (*startp == 0) + break; + } + + cpu = strtol(startp, &endp, 10); + if (startp == endp) + errx(1, "--cpu cpu-set: confused by '%s'", startp); + if (cpu > max_cpu_num) + errx(1, "Requested cpu%d exceeds max cpu%d", cpu, max_cpu_num); + CPU_SET_S(cpu, cpu_setsize, cpu_selected_set); + startp = endp; + } + + validate_cpu_selected_set(); + +} + +void parse_cmdline_pkg(char *s) +{ + char *startp, *endp; + int pkg = 0; + + if (cpu_selected_set) { + usage(); + errx(1, "--pkg | --cpu"); + } + pkg_selected_set = 0; + + for (startp = s; startp && *startp;) { + + if (*startp == ',') { + startp++; + continue; + } + + if (*startp == '-') { + int end_pkg; + + startp++; + end_pkg = strtol(startp, &endp, 10); + if (startp == endp) + continue; + + while (pkg <= end_pkg) { + if (pkg > max_pkg_num) + errx(1, "Requested pkg%d exceeds max pkg%d", pkg, max_pkg_num); + pkg_selected_set |= 1 << pkg; + pkg++; + } + startp = endp; + continue; + } + + if (strncmp(startp, "all", 3) == 0) { + pkg_selected_set = pkg_present_set; + return; + } + + pkg = strtol(startp, &endp, 10); + if (pkg > max_pkg_num) + errx(1, "Requested pkg%d Exceeds max pkg%d", pkg, max_pkg_num); + pkg_selected_set |= 1 << pkg; + startp = endp; + } +} + +void for_packages(unsigned long long pkg_set, int (func)(int)) +{ + int pkg_num; + + for (pkg_num = 0; pkg_num <= max_pkg_num; ++pkg_num) { + if (pkg_set & (1UL << pkg_num)) + func(pkg_num); + } +} + +void print_version(void) +{ + printf("x86_energy_perf_policy 17.05.11 (C) Len Brown <len.brown@intel.com>\n"); +} void cmdline(int argc, char **argv) { int opt; + int option_index = 0; + + static struct option long_options[] = { + {"all", required_argument, 0, 'a'}, + {"cpu", required_argument, 0, 'c'}, + {"pkg", required_argument, 0, 'p'}, + {"debug", no_argument, 0, 'd'}, + {"hwp-desired", required_argument, 0, 'D'}, + {"epb", required_argument, 0, 'B'}, + {"force", no_argument, 0, 'f'}, + {"hwp-enable", no_argument, 0, 'e'}, + {"help", no_argument, 0, 'h'}, + {"hwp-epp", required_argument, 0, 'P'}, + {"hwp-min", required_argument, 0, 'm'}, + {"hwp-max", required_argument, 0, 'M'}, + {"read", no_argument, 0, 'r'}, + {"turbo-enable", required_argument, 0, 't'}, + {"hwp-use-pkg", required_argument, 0, 'u'}, + {"version", no_argument, 0, 'v'}, + {"hwp-window", required_argument, 0, 'w'}, + {0, 0, 0, 0 } + }; progname = argv[0]; - while ((opt = getopt(argc, argv, "+rvc:")) != -1) { + while ((opt = getopt_long_only(argc, argv, "+a:c:dD:E:e:f:m:M:rt:u:vw", + long_options, &option_index)) != -1) { switch (opt) { + case 'a': + parse_cmdline_all(optarg); + break; + case 'B': + new_epb = parse_cmdline_epb(parse_optarg_string(optarg)); + break; case 'c': - cpu = atoi(optarg); + parse_cmdline_cpu(optarg); + break; + case 'e': + update_hwp_enable = 1; + break; + case 'h': + usage(); + break; + case 'd': + debug++; + verbose++; + break; + case 'f': + force++; + break; + case 'D': + req_update.hwp_desired = parse_cmdline_hwp_desired(parse_optarg_string(optarg)); + break; + case 'm': + req_update.hwp_min = parse_cmdline_hwp_min(parse_optarg_string(optarg)); + break; + case 'M': + req_update.hwp_max = parse_cmdline_hwp_max(parse_optarg_string(optarg)); + break; + case 'p': + parse_cmdline_pkg(optarg); + break; + case 'P': + req_update.hwp_epp = parse_cmdline_hwp_epp(parse_optarg_string(optarg)); break; case 'r': - read_only = 1; + /* v1 used -r to specify read-only mode, now the default */ + break; + case 't': + turbo_update_value = parse_cmdline_turbo(parse_optarg_string(optarg)); + break; + case 'u': + update_hwp_use_pkg++; + if (atoi(optarg) == 0) + req_update.hwp_use_pkg = 0; + else + req_update.hwp_use_pkg = 1; break; case 'v': - verbose++; + print_version(); + exit(0); + break; + case 'w': + req_update.hwp_window = parse_cmdline_hwp_window(parse_optarg_string(optarg)); break; default: usage(); } } - /* if -r, then should be no additional optind */ - if (read_only && (argc > optind)) - usage(); - /* - * if no -r , then must be one additional optind + * v1 allowed "performance"|"normal"|"power" with no policy specifier + * to update BIAS. Continue to support that, even though no longer documented. */ - if (!read_only) { + if (argc == optind + 1) + new_epb = parse_cmdline_epb(parse_optarg_string(argv[optind])); - if (argc != optind + 1) { - printf("must supply -r or policy param\n"); - usage(); - } + if (argc > optind + 1) { + fprintf(stderr, "stray parameter '%s'\n", argv[optind + 1]); + usage(); + } +} - if (!strcmp("performance", argv[optind])) { - new_bias = BIAS_PERFORMANCE; - } else if (!strcmp("normal", argv[optind])) { - new_bias = BIAS_BALANCE; - } else if (!strcmp("powersave", argv[optind])) { - new_bias = BIAS_POWERSAVE; - } else { - char *endptr; - - new_bias = strtoull(argv[optind], &endptr, 0); - if (endptr == argv[optind] || - new_bias > BIAS_POWERSAVE) { - fprintf(stderr, "invalid value: %s\n", - argv[optind]); - usage(); - } - } + +int get_msr(int cpu, int offset, unsigned long long *msr) +{ + int retval; + char pathname[32]; + int fd; + + sprintf(pathname, "/dev/cpu/%d/msr", cpu); + fd = open(pathname, O_RDONLY); + if (fd < 0) + err(-1, "%s open failed, try chown or chmod +r /dev/cpu/*/msr, or run as root", pathname); + + retval = pread(fd, msr, sizeof(*msr), offset); + if (retval != sizeof(*msr)) + err(-1, "%s offset 0x%llx read failed", pathname, (unsigned long long)offset); + + if (debug > 1) + fprintf(stderr, "get_msr(cpu%d, 0x%X, 0x%llX)\n", cpu, offset, *msr); + + close(fd); + return 0; +} + +int put_msr(int cpu, int offset, unsigned long long new_msr) +{ + char pathname[32]; + int retval; + int fd; + + sprintf(pathname, "/dev/cpu/%d/msr", cpu); + fd = open(pathname, O_RDWR); + if (fd < 0) + err(-1, "%s open failed, try chown or chmod +r /dev/cpu/*/msr, or run as root", pathname); + + retval = pwrite(fd, &new_msr, sizeof(new_msr), offset); + if (retval != sizeof(new_msr)) + err(-2, "pwrite(cpu%d, offset 0x%x, 0x%llx) = %d", cpu, offset, new_msr, retval); + + close(fd); + + if (debug > 1) + fprintf(stderr, "put_msr(cpu%d, 0x%X, 0x%llX)\n", cpu, offset, new_msr); + + return 0; +} + +void print_hwp_cap(int cpu, struct msr_hwp_cap *cap, char *str) +{ + if (cpu != -1) + printf("cpu%d: ", cpu); + + printf("HWP_CAP: low %d eff %d guar %d high %d\n", + cap->lowest, cap->efficient, cap->guaranteed, cap->highest); +} +void read_hwp_cap(int cpu, struct msr_hwp_cap *cap, unsigned int msr_offset) +{ + unsigned long long msr; + + get_msr(cpu, msr_offset, &msr); + + cap->highest = msr_perf_2_ratio(HWP_HIGHEST_PERF(msr)); + cap->guaranteed = msr_perf_2_ratio(HWP_GUARANTEED_PERF(msr)); + cap->efficient = msr_perf_2_ratio(HWP_MOSTEFFICIENT_PERF(msr)); + cap->lowest = msr_perf_2_ratio(HWP_LOWEST_PERF(msr)); +} + +void print_hwp_request(int cpu, struct msr_hwp_request *h, char *str) +{ + if (cpu != -1) + printf("cpu%d: ", cpu); + + if (str) + printf("%s", str); + + printf("HWP_REQ: min %d max %d des %d epp %d window 0x%x (%d*10^%dus) use_pkg %d\n", + h->hwp_min, h->hwp_max, h->hwp_desired, h->hwp_epp, + h->hwp_window, h->hwp_window & 0x7F, (h->hwp_window >> 7) & 0x7, h->hwp_use_pkg); +} +void print_hwp_request_pkg(int pkg, struct msr_hwp_request *h, char *str) +{ + printf("pkg%d: ", pkg); + + if (str) + printf("%s", str); + + printf("HWP_REQ_PKG: min %d max %d des %d epp %d window 0x%x (%d*10^%dus)\n", + h->hwp_min, h->hwp_max, h->hwp_desired, h->hwp_epp, + h->hwp_window, h->hwp_window & 0x7F, (h->hwp_window >> 7) & 0x7); +} +void read_hwp_request(int cpu, struct msr_hwp_request *hwp_req, unsigned int msr_offset) +{ + unsigned long long msr; + + get_msr(cpu, msr_offset, &msr); + + hwp_req->hwp_min = msr_perf_2_ratio((((msr) >> 0) & 0xff)); + hwp_req->hwp_max = msr_perf_2_ratio((((msr) >> 8) & 0xff)); + hwp_req->hwp_desired = msr_perf_2_ratio((((msr) >> 16) & 0xff)); + hwp_req->hwp_epp = (((msr) >> 24) & 0xff); + hwp_req->hwp_window = (((msr) >> 32) & 0x3ff); + hwp_req->hwp_use_pkg = (((msr) >> 42) & 0x1); +} + +void write_hwp_request(int cpu, struct msr_hwp_request *hwp_req, unsigned int msr_offset) +{ + unsigned long long msr = 0; + + if (debug > 1) + printf("cpu%d: requesting min %d max %d des %d epp %d window 0x%0x use_pkg %d\n", + cpu, hwp_req->hwp_min, hwp_req->hwp_max, + hwp_req->hwp_desired, hwp_req->hwp_epp, + hwp_req->hwp_window, hwp_req->hwp_use_pkg); + + msr |= HWP_MIN_PERF(ratio_2_msr_perf(hwp_req->hwp_min)); + msr |= HWP_MAX_PERF(ratio_2_msr_perf(hwp_req->hwp_max)); + msr |= HWP_DESIRED_PERF(ratio_2_msr_perf(hwp_req->hwp_desired)); + msr |= HWP_ENERGY_PERF_PREFERENCE(hwp_req->hwp_epp); + msr |= HWP_ACTIVITY_WINDOW(hwp_req->hwp_window); + msr |= HWP_PACKAGE_CONTROL(hwp_req->hwp_use_pkg); + + put_msr(cpu, msr_offset, msr); +} + +int print_cpu_msrs(int cpu) +{ + unsigned long long msr; + struct msr_hwp_request req; + struct msr_hwp_cap cap; + + if (has_epb) { + get_msr(cpu, MSR_IA32_ENERGY_PERF_BIAS, &msr); + + printf("cpu%d: EPB %u\n", cpu, (unsigned int) msr); } + + if (!has_hwp) + return 0; + + read_hwp_request(cpu, &req, MSR_HWP_REQUEST); + print_hwp_request(cpu, &req, ""); + + read_hwp_cap(cpu, &cap, MSR_HWP_CAPABILITIES); + print_hwp_cap(cpu, &cap, ""); + + return 0; +} + +int print_pkg_msrs(int pkg) +{ + struct msr_hwp_request req; + unsigned long long msr; + + if (!has_hwp) + return 0; + + read_hwp_request(first_cpu_in_pkg[pkg], &req, MSR_HWP_REQUEST_PKG); + print_hwp_request_pkg(pkg, &req, ""); + + if (has_hwp_notify) { + get_msr(first_cpu_in_pkg[pkg], MSR_HWP_INTERRUPT, &msr); + fprintf(stderr, + "pkg%d: MSR_HWP_INTERRUPT: 0x%08llx (Excursion_Min-%sabled, Guaranteed_Perf_Change-%sabled)\n", + pkg, msr, + ((msr) & 0x2) ? "EN" : "Dis", + ((msr) & 0x1) ? "EN" : "Dis"); + } + get_msr(first_cpu_in_pkg[pkg], MSR_HWP_STATUS, &msr); + fprintf(stderr, + "pkg%d: MSR_HWP_STATUS: 0x%08llx (%sExcursion_Min, %sGuaranteed_Perf_Change)\n", + pkg, msr, + ((msr) & 0x4) ? "" : "No-", + ((msr) & 0x1) ? "" : "No-"); + + return 0; } /* - * validate_cpuid() - * returns on success, quietly exits on failure (make verbose with -v) + * Assumption: All HWP systems have 100 MHz bus clock */ -void validate_cpuid(void) +int ratio_2_sysfs_khz(int ratio) { - unsigned int eax, ebx, ecx, edx, max_level; - unsigned int fms, family, model, stepping; + int bclk_khz = 100 * 1000; /* 100,000 KHz = 100 MHz */ - eax = ebx = ecx = edx = 0; + return ratio * bclk_khz; +} +/* + * If HWP is enabled and cpufreq sysfs attribtes are present, + * then update sysfs, so that it will not become + * stale when we write to MSRs. + * (intel_pstate's max_perf_pct and min_perf_pct will follow cpufreq, + * so we don't have to touch that.) + */ +void update_cpufreq_scaling_freq(int is_max, int cpu, unsigned int ratio) +{ + char pathname[64]; + FILE *fp; + int retval; + int khz; - asm("cpuid" : "=a" (max_level), "=b" (ebx), "=c" (ecx), - "=d" (edx) : "a" (0)); + sprintf(pathname, "/sys/devices/system/cpu/cpu%d/cpufreq/scaling_%s_freq", + cpu, is_max ? "max" : "min"); - if (ebx != 0x756e6547 || edx != 0x49656e69 || ecx != 0x6c65746e) { - if (verbose) - fprintf(stderr, "%.4s%.4s%.4s != GenuineIntel", - (char *)&ebx, (char *)&edx, (char *)&ecx); - exit(1); + fp = fopen(pathname, "w"); + if (!fp) { + if (debug) + perror(pathname); + return; } - asm("cpuid" : "=a" (fms), "=c" (ecx), "=d" (edx) : "a" (1) : "ebx"); - family = (fms >> 8) & 0xf; - model = (fms >> 4) & 0xf; - stepping = fms & 0xf; - if (family == 6 || family == 0xf) - model += ((fms >> 16) & 0xf) << 4; + khz = ratio_2_sysfs_khz(ratio); + retval = fprintf(fp, "%d", khz); + if (retval < 0) + if (debug) + perror("fprintf"); + if (debug) + printf("echo %d > %s\n", khz, pathname); - if (verbose > 1) - printf("CPUID %d levels family:model:stepping " - "0x%x:%x:%x (%d:%d:%d)\n", max_level, - family, model, stepping, family, model, stepping); + fclose(fp); +} - if (!(edx & (1 << 5))) { - if (verbose) - printf("CPUID: no MSR\n"); - exit(1); +/* + * We update all sysfs before updating any MSRs because of + * bugs in cpufreq/intel_pstate where the sysfs writes + * for a CPU may change the min/max values on other CPUS. + */ + +int update_sysfs(int cpu) +{ + if (!has_hwp) + return 0; + + if (!hwp_update_enabled()) + return 0; + + if (access("/sys/devices/system/cpu/cpu0/cpufreq", F_OK)) + return 0; + + if (update_hwp_min) + update_cpufreq_scaling_freq(0, cpu, req_update.hwp_min); + + if (update_hwp_max) + update_cpufreq_scaling_freq(1, cpu, req_update.hwp_max); + + return 0; +} + +int verify_hwp_req_self_consistency(int cpu, struct msr_hwp_request *req) +{ + /* fail if min > max requested */ + if (req->hwp_min > req->hwp_max) { + errx(1, "cpu%d: requested hwp-min %d > hwp_max %d", + cpu, req->hwp_min, req->hwp_max); } - /* - * Support for MSR_IA32_ENERGY_PERF_BIAS - * is indicated by CPUID.06H.ECX.bit3 - */ - asm("cpuid" : "=a" (eax), "=b" (ebx), "=c" (ecx), "=d" (edx) : "a" (6)); - if (verbose) - printf("CPUID.06H.ECX: 0x%x\n", ecx); - if (!(ecx & (1 << 3))) { - if (verbose) - printf("CPUID: No MSR_IA32_ENERGY_PERF_BIAS\n"); - exit(1); + /* fail if desired > max requestd */ + if (req->hwp_desired && (req->hwp_desired > req->hwp_max)) { + errx(1, "cpu%d: requested hwp-desired %d > hwp_max %d", + cpu, req->hwp_desired, req->hwp_max); } - return; /* success */ + /* fail if desired < min requestd */ + if (req->hwp_desired && (req->hwp_desired < req->hwp_min)) { + errx(1, "cpu%d: requested hwp-desired %d < requested hwp_min %d", + cpu, req->hwp_desired, req->hwp_min); + } + + return 0; } -unsigned long long get_msr(int cpu, int offset) +int check_hwp_request_v_hwp_capabilities(int cpu, struct msr_hwp_request *req, struct msr_hwp_cap *cap) { - unsigned long long msr; - char msr_path[32]; - int retval; - int fd; + if (update_hwp_max) { + if (req->hwp_max > cap->highest) + errx(1, "cpu%d: requested max %d > capabilities highest %d, use --force?", + cpu, req->hwp_max, cap->highest); + if (req->hwp_max < cap->lowest) + errx(1, "cpu%d: requested max %d < capabilities lowest %d, use --force?", + cpu, req->hwp_max, cap->lowest); + } - sprintf(msr_path, "/dev/cpu/%d/msr", cpu); - fd = open(msr_path, O_RDONLY); - if (fd < 0) { - printf("Try \"# modprobe msr\"\n"); - perror(msr_path); - exit(1); + if (update_hwp_min) { + if (req->hwp_min > cap->highest) + errx(1, "cpu%d: requested min %d > capabilities highest %d, use --force?", + cpu, req->hwp_min, cap->highest); + if (req->hwp_min < cap->lowest) + errx(1, "cpu%d: requested min %d < capabilities lowest %d, use --force?", + cpu, req->hwp_min, cap->lowest); } - retval = pread(fd, &msr, sizeof msr, offset); + if (update_hwp_min && update_hwp_max && (req->hwp_min > req->hwp_max)) + errx(1, "cpu%d: requested min %d > requested max %d", + cpu, req->hwp_min, req->hwp_max); - if (retval != sizeof msr) { - printf("pread cpu%d 0x%x = %d\n", cpu, offset, retval); - exit(-2); + if (update_hwp_desired && req->hwp_desired) { + if (req->hwp_desired > req->hwp_max) + errx(1, "cpu%d: requested desired %d > requested max %d, use --force?", + cpu, req->hwp_desired, req->hwp_max); + if (req->hwp_desired < req->hwp_min) + errx(1, "cpu%d: requested desired %d < requested min %d, use --force?", + cpu, req->hwp_desired, req->hwp_min); + if (req->hwp_desired < cap->lowest) + errx(1, "cpu%d: requested desired %d < capabilities lowest %d, use --force?", + cpu, req->hwp_desired, cap->lowest); + if (req->hwp_desired > cap->highest) + errx(1, "cpu%d: requested desired %d > capabilities highest %d, use --force?", + cpu, req->hwp_desired, cap->highest); } - close(fd); - return msr; + + return 0; } -unsigned long long put_msr(int cpu, unsigned long long new_msr, int offset) +int update_hwp_request(int cpu) { - unsigned long long old_msr; - char msr_path[32]; - int retval; - int fd; + struct msr_hwp_request req; + struct msr_hwp_cap cap; + + int msr_offset = MSR_HWP_REQUEST; + + read_hwp_request(cpu, &req, msr_offset); + if (debug) + print_hwp_request(cpu, &req, "old: "); + + if (update_hwp_min) + req.hwp_min = req_update.hwp_min; + + if (update_hwp_max) + req.hwp_max = req_update.hwp_max; + + if (update_hwp_desired) + req.hwp_desired = req_update.hwp_desired; + + if (update_hwp_window) + req.hwp_window = req_update.hwp_window; + + if (update_hwp_epp) + req.hwp_epp = req_update.hwp_epp; + + req.hwp_use_pkg = req_update.hwp_use_pkg; + + read_hwp_cap(cpu, &cap, MSR_HWP_CAPABILITIES); + if (debug) + print_hwp_cap(cpu, &cap, ""); + + if (!force) + check_hwp_request_v_hwp_capabilities(cpu, &req, &cap); + + verify_hwp_req_self_consistency(cpu, &req); - sprintf(msr_path, "/dev/cpu/%d/msr", cpu); - fd = open(msr_path, O_RDWR); - if (fd < 0) { - perror(msr_path); - exit(1); + write_hwp_request(cpu, &req, msr_offset); + + if (debug) { + read_hwp_request(cpu, &req, msr_offset); + print_hwp_request(cpu, &req, "new: "); } + return 0; +} +int update_hwp_request_pkg(int pkg) +{ + struct msr_hwp_request req; + struct msr_hwp_cap cap; + int cpu = first_cpu_in_pkg[pkg]; + + int msr_offset = MSR_HWP_REQUEST_PKG; + + read_hwp_request(cpu, &req, msr_offset); + if (debug) + print_hwp_request_pkg(pkg, &req, "old: "); + + if (update_hwp_min) + req.hwp_min = req_update.hwp_min; + + if (update_hwp_max) + req.hwp_max = req_update.hwp_max; + + if (update_hwp_desired) + req.hwp_desired = req_update.hwp_desired; + + if (update_hwp_window) + req.hwp_window = req_update.hwp_window; + + if (update_hwp_epp) + req.hwp_epp = req_update.hwp_epp; + + read_hwp_cap(cpu, &cap, MSR_HWP_CAPABILITIES); + if (debug) + print_hwp_cap(cpu, &cap, ""); + + if (!force) + check_hwp_request_v_hwp_capabilities(cpu, &req, &cap); + + verify_hwp_req_self_consistency(cpu, &req); + + write_hwp_request(cpu, &req, msr_offset); - retval = pread(fd, &old_msr, sizeof old_msr, offset); - if (retval != sizeof old_msr) { - perror("pwrite"); - printf("pread cpu%d 0x%x = %d\n", cpu, offset, retval); - exit(-2); + if (debug) { + read_hwp_request(cpu, &req, msr_offset); + print_hwp_request_pkg(pkg, &req, "new: "); } + return 0; +} + +int enable_hwp_on_cpu(int cpu) +{ + unsigned long long msr; + + get_msr(cpu, MSR_PM_ENABLE, &msr); + put_msr(cpu, MSR_PM_ENABLE, 1); + + if (verbose) + printf("cpu%d: MSR_PM_ENABLE old: %d new: %d\n", cpu, (unsigned int) msr, 1); + + return 0; +} + +int update_cpu_msrs(int cpu) +{ + unsigned long long msr; + - retval = pwrite(fd, &new_msr, sizeof new_msr, offset); - if (retval != sizeof new_msr) { - perror("pwrite"); - printf("pwrite cpu%d 0x%x = %d\n", cpu, offset, retval); - exit(-2); + if (update_epb) { + get_msr(cpu, MSR_IA32_ENERGY_PERF_BIAS, &msr); + put_msr(cpu, MSR_IA32_ENERGY_PERF_BIAS, new_epb); + + if (verbose) + printf("cpu%d: ENERGY_PERF_BIAS old: %d new: %d\n", + cpu, (unsigned int) msr, (unsigned int) new_epb); } - close(fd); + if (update_turbo) { + int turbo_is_present_and_disabled; + + get_msr(cpu, MSR_IA32_MISC_ENABLE, &msr); + + turbo_is_present_and_disabled = ((msr & MSR_IA32_MISC_ENABLE_TURBO_DISABLE) != 0); + + if (turbo_update_value == 1) { + if (turbo_is_present_and_disabled) { + msr &= ~MSR_IA32_MISC_ENABLE_TURBO_DISABLE; + put_msr(cpu, MSR_IA32_MISC_ENABLE, msr); + if (verbose) + printf("cpu%d: turbo ENABLE\n", cpu); + } + } else { + /* + * if "turbo_is_enabled" were known to be describe this cpu + * then we could use it here to skip redundant disable requests. + * but cpu may be in a different package, so we always write. + */ + msr |= MSR_IA32_MISC_ENABLE_TURBO_DISABLE; + put_msr(cpu, MSR_IA32_MISC_ENABLE, msr); + if (verbose) + printf("cpu%d: turbo DISABLE\n", cpu); + } + } + + if (!has_hwp) + return 0; + + if (!hwp_update_enabled()) + return 0; + + update_hwp_request(cpu); + return 0; +} + +/* + * Open a file, and exit on failure + */ +FILE *fopen_or_die(const char *path, const char *mode) +{ + FILE *filep = fopen(path, "r"); - return old_msr; + if (!filep) + err(1, "%s: open failed", path); + return filep; } -void print_msr(int cpu) +unsigned int get_pkg_num(int cpu) { - printf("cpu%d: 0x%016llx\n", - cpu, get_msr(cpu, MSR_IA32_ENERGY_PERF_BIAS)); + FILE *fp; + char pathname[128]; + unsigned int pkg; + int retval; + + sprintf(pathname, "/sys/devices/system/cpu/cpu%d/topology/physical_package_id", cpu); + + fp = fopen_or_die(pathname, "r"); + retval = fscanf(fp, "%d\n", &pkg); + if (retval != 1) + errx(1, "%s: failed to parse", pathname); + return pkg; } -void update_msr(int cpu) +int set_max_cpu_pkg_num(int cpu) { - unsigned long long previous_msr; + unsigned int pkg; - previous_msr = put_msr(cpu, new_bias, MSR_IA32_ENERGY_PERF_BIAS); + if (max_cpu_num < cpu) + max_cpu_num = cpu; - if (verbose) - printf("cpu%d msr0x%x 0x%016llx -> 0x%016llx\n", - cpu, MSR_IA32_ENERGY_PERF_BIAS, previous_msr, new_bias); + pkg = get_pkg_num(cpu); + + if (pkg >= MAX_PACKAGES) + errx(1, "cpu%d: %d >= MAX_PACKAGES (%d)", cpu, pkg, MAX_PACKAGES); + + if (pkg > max_pkg_num) + max_pkg_num = pkg; - return; + if ((pkg_present_set & (1ULL << pkg)) == 0) { + pkg_present_set |= (1ULL << pkg); + first_cpu_in_pkg[pkg] = cpu; + } + + return 0; +} +int mark_cpu_present(int cpu) +{ + CPU_SET_S(cpu, cpu_setsize, cpu_present_set); + return 0; } -char *proc_stat = "/proc/stat"; /* - * run func() on every cpu in /dev/cpu + * run func(cpu) on every cpu in /proc/stat + * return max_cpu number */ -void for_every_cpu(void (func)(int)) +int for_all_proc_cpus(int (func)(int)) { FILE *fp; + int cpu_num; int retval; - fp = fopen(proc_stat, "r"); - if (fp == NULL) { - perror(proc_stat); - exit(1); - } + fp = fopen_or_die(proc_stat, "r"); retval = fscanf(fp, "cpu %*d %*d %*d %*d %*d %*d %*d %*d %*d %*d\n"); - if (retval != 0) { - perror("/proc/stat format"); - exit(1); - } + if (retval != 0) + err(1, "%s: failed to parse format", proc_stat); while (1) { - int cpu; - - retval = fscanf(fp, - "cpu%u %*d %*d %*d %*d %*d %*d %*d %*d %*d %*d\n", - &cpu); + retval = fscanf(fp, "cpu%u %*d %*d %*d %*d %*d %*d %*d %*d %*d %*d\n", &cpu_num); if (retval != 1) break; - func(cpu); + retval = func(cpu_num); + if (retval) { + fclose(fp); + return retval; + } } fclose(fp); + return 0; +} + +void for_all_cpus_in_set(size_t set_size, cpu_set_t *cpu_set, int (func)(int)) +{ + int cpu_num; + + for (cpu_num = 0; cpu_num <= max_cpu_num; ++cpu_num) + if (CPU_ISSET_S(cpu_num, set_size, cpu_set)) + func(cpu_num); +} + +void init_data_structures(void) +{ + for_all_proc_cpus(set_max_cpu_pkg_num); + + cpu_setsize = CPU_ALLOC_SIZE((max_cpu_num + 1)); + + cpu_present_set = CPU_ALLOC((max_cpu_num + 1)); + if (cpu_present_set == NULL) + err(3, "CPU_ALLOC"); + CPU_ZERO_S(cpu_setsize, cpu_present_set); + for_all_proc_cpus(mark_cpu_present); +} + +/* clear has_hwp if it is not enable (or being enabled) */ + +void verify_hwp_is_enabled(void) +{ + unsigned long long msr; + + if (!has_hwp) /* set in early_cpuid() */ + return; + + /* MSR_PM_ENABLE[1] == 1 if HWP is enabled and MSRs visible */ + get_msr(base_cpu, MSR_PM_ENABLE, &msr); + if ((msr & 1) == 0) { + fprintf(stderr, "HWP can be enabled using '--hwp-enable'\n"); + has_hwp = 0; + return; + } +} + +int req_update_bounds_check(void) +{ + if (!hwp_update_enabled()) + return 0; + + /* fail if min > max requested */ + if ((update_hwp_max && update_hwp_min) && + (req_update.hwp_min > req_update.hwp_max)) { + printf("hwp-min %d > hwp_max %d\n", req_update.hwp_min, req_update.hwp_max); + return -EINVAL; + } + + /* fail if desired > max requestd */ + if (req_update.hwp_desired && update_hwp_max && + (req_update.hwp_desired > req_update.hwp_max)) { + printf("hwp-desired cannot be greater than hwp_max\n"); + return -EINVAL; + } + /* fail if desired < min requestd */ + if (req_update.hwp_desired && update_hwp_min && + (req_update.hwp_desired < req_update.hwp_min)) { + printf("hwp-desired cannot be less than hwp_min\n"); + return -EINVAL; + } + + return 0; +} + +void set_base_cpu(void) +{ + base_cpu = sched_getcpu(); + if (base_cpu < 0) + err(-ENODEV, "No valid cpus found"); +} + + +void probe_dev_msr(void) +{ + struct stat sb; + char pathname[32]; + + sprintf(pathname, "/dev/cpu/%d/msr", base_cpu); + if (stat(pathname, &sb)) + if (system("/sbin/modprobe msr > /dev/null 2>&1")) + err(-5, "no /dev/cpu/0/msr, Try \"# modprobe msr\" "); +} +/* + * early_cpuid() + * initialize turbo_is_enabled, has_hwp, has_epb + * before cmdline is parsed + */ +void early_cpuid(void) +{ + unsigned int eax, ebx, ecx, edx, max_level; + unsigned int fms, family, model; + + __get_cpuid(0, &max_level, &ebx, &ecx, &edx); + + if (max_level < 6) + errx(1, "Processor not supported\n"); + + __get_cpuid(1, &fms, &ebx, &ecx, &edx); + family = (fms >> 8) & 0xf; + model = (fms >> 4) & 0xf; + if (family == 6 || family == 0xf) + model += ((fms >> 16) & 0xf) << 4; + + if (model == 0x4F) { + unsigned long long msr; + + get_msr(base_cpu, MSR_TURBO_RATIO_LIMIT, &msr); + + bdx_highest_ratio = msr & 0xFF; + } + + __get_cpuid(0x6, &eax, &ebx, &ecx, &edx); + turbo_is_enabled = (eax >> 1) & 1; + has_hwp = (eax >> 7) & 1; + has_epb = (ecx >> 3) & 1; +} + +/* + * parse_cpuid() + * set + * has_hwp, has_hwp_notify, has_hwp_activity_window, has_hwp_epp, has_hwp_request_pkg, has_epb + */ +void parse_cpuid(void) +{ + unsigned int eax, ebx, ecx, edx, max_level; + unsigned int fms, family, model, stepping; + + eax = ebx = ecx = edx = 0; + + __get_cpuid(0, &max_level, &ebx, &ecx, &edx); + + if (ebx == 0x756e6547 && edx == 0x49656e69 && ecx == 0x6c65746e) + genuine_intel = 1; + + if (debug) + fprintf(stderr, "CPUID(0): %.4s%.4s%.4s ", + (char *)&ebx, (char *)&edx, (char *)&ecx); + + __get_cpuid(1, &fms, &ebx, &ecx, &edx); + family = (fms >> 8) & 0xf; + model = (fms >> 4) & 0xf; + stepping = fms & 0xf; + if (family == 6 || family == 0xf) + model += ((fms >> 16) & 0xf) << 4; + + if (debug) { + fprintf(stderr, "%d CPUID levels; family:model:stepping 0x%x:%x:%x (%d:%d:%d)\n", + max_level, family, model, stepping, family, model, stepping); + fprintf(stderr, "CPUID(1): %s %s %s %s %s %s %s %s\n", + ecx & (1 << 0) ? "SSE3" : "-", + ecx & (1 << 3) ? "MONITOR" : "-", + ecx & (1 << 7) ? "EIST" : "-", + ecx & (1 << 8) ? "TM2" : "-", + edx & (1 << 4) ? "TSC" : "-", + edx & (1 << 5) ? "MSR" : "-", + edx & (1 << 22) ? "ACPI-TM" : "-", + edx & (1 << 29) ? "TM" : "-"); + } + + if (!(edx & (1 << 5))) + errx(1, "CPUID: no MSR"); + + + __get_cpuid(0x6, &eax, &ebx, &ecx, &edx); + /* turbo_is_enabled already set */ + /* has_hwp already set */ + has_hwp_notify = eax & (1 << 8); + has_hwp_activity_window = eax & (1 << 9); + has_hwp_epp = eax & (1 << 10); + has_hwp_request_pkg = eax & (1 << 11); + + if (!has_hwp_request_pkg && update_hwp_use_pkg) + errx(1, "--hwp-use-pkg is not available on this hardware"); + + /* has_epb already set */ + + if (debug) + fprintf(stderr, + "CPUID(6): %sTURBO, %sHWP, %sHWPnotify, %sHWPwindow, %sHWPepp, %sHWPpkg, %sEPB\n", + turbo_is_enabled ? "" : "No-", + has_hwp ? "" : "No-", + has_hwp_notify ? "" : "No-", + has_hwp_activity_window ? "" : "No-", + has_hwp_epp ? "" : "No-", + has_hwp_request_pkg ? "" : "No-", + has_epb ? "" : "No-"); + + return; /* success */ } int main(int argc, char **argv) { + set_base_cpu(); + probe_dev_msr(); + init_data_structures(); + + early_cpuid(); /* initial cpuid parse before cmdline */ + cmdline(argc, argv); - if (verbose > 1) - printf("x86_energy_perf_policy Nov 24, 2010" - " - Len Brown <lenb@kernel.org>\n"); - if (verbose > 1 && !read_only) - printf("new_bias %lld\n", new_bias); - - validate_cpuid(); - - if (cpu != -1) { - if (read_only) - print_msr(cpu); - else - update_msr(cpu); - } else { - if (read_only) - for_every_cpu(print_msr); - else - for_every_cpu(update_msr); + if (debug) + print_version(); + + parse_cpuid(); + + /* If CPU-set and PKG-set are not initialized, default to all CPUs */ + if ((cpu_selected_set == 0) && (pkg_selected_set == 0)) + cpu_selected_set = cpu_present_set; + + /* + * If HWP is being enabled, do it now, so that subsequent operations + * that access HWP registers can work. + */ + if (update_hwp_enable) + for_all_cpus_in_set(cpu_setsize, cpu_selected_set, enable_hwp_on_cpu); + + /* If HWP present, but disabled, warn and ignore from here forward */ + verify_hwp_is_enabled(); + + if (req_update_bounds_check()) + return -EINVAL; + + /* display information only, no updates to settings */ + if (!update_epb && !update_turbo && !hwp_update_enabled()) { + if (cpu_selected_set) + for_all_cpus_in_set(cpu_setsize, cpu_selected_set, print_cpu_msrs); + + if (has_hwp_request_pkg) { + if (pkg_selected_set == 0) + pkg_selected_set = pkg_present_set; + + for_packages(pkg_selected_set, print_pkg_msrs); + } + + return 0; } + /* update CPU set */ + if (cpu_selected_set) { + for_all_cpus_in_set(cpu_setsize, cpu_selected_set, update_sysfs); + for_all_cpus_in_set(cpu_setsize, cpu_selected_set, update_cpu_msrs); + } else if (pkg_selected_set) + for_packages(pkg_selected_set, update_hwp_request_pkg); + return 0; } diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include index fc74db62fef4..9dc8f078a83c 100644 --- a/tools/scripts/Makefile.include +++ b/tools/scripts/Makefile.include @@ -1,7 +1,7 @@ ifneq ($(O),) ifeq ($(origin O), command line) - dummy := $(if $(shell test -d $(O) || echo $(O)),$(error O=$(O) does not exist),) - ABSOLUTE_O := $(shell cd $(O) ; pwd) + ABSOLUTE_O := $(realpath $(O)) + dummy := $(if $(ABSOLUTE_O),,$(error O=$(O) does not exist)) OUTPUT := $(ABSOLUTE_O)/$(if $(subdir),$(subdir)/) COMMAND_O := O=$(ABSOLUTE_O) ifeq ($(objtree),) @@ -12,7 +12,7 @@ endif # check that the output directory actually exists ifneq ($(OUTPUT),) -OUTDIR := $(shell cd $(OUTPUT) && /bin/pwd) +OUTDIR := $(realpath $(OUTPUT)) $(if $(OUTDIR),, $(error output directory "$(OUTPUT)" does not exist)) endif @@ -39,7 +39,9 @@ EXTRA_WARNINGS += -Wundef EXTRA_WARNINGS += -Wwrite-strings EXTRA_WARNINGS += -Wformat -ifneq ($(CC), clang) +CC_NO_CLANG := $(shell $(CC) -dM -E -x c /dev/null | grep -Fq "__clang__"; echo $$?) + +ifeq ($(CC_NO_CLANG), 1) EXTRA_WARNINGS += -Wstrict-aliasing=3 endif @@ -58,15 +60,9 @@ else NO_SUBDIR = : endif -ifneq ($(filter 4.%,$(MAKE_VERSION)),) # make-4 -ifneq ($(filter %s ,$(firstword x$(MAKEFLAGS))),) - silent=1 -endif -else # make-3.8x -ifneq ($(filter s% -s%,$(MAKEFLAGS)),) +ifneq ($(findstring s,$(filter-out --%,$(MAKEFLAGS))),) silent=1 endif -endif # # Define a callable command for descending to a new directory diff --git a/tools/spi/Build b/tools/spi/Build new file mode 100644 index 000000000000..8e8466033d99 --- /dev/null +++ b/tools/spi/Build @@ -0,0 +1,2 @@ +spidev_test-y += spidev_test.o +spidev_fdx-y += spidev_fdx.o diff --git a/tools/spi/Makefile b/tools/spi/Makefile index 3815b18ba070..90615e10c79a 100644 --- a/tools/spi/Makefile +++ b/tools/spi/Makefile @@ -1,6 +1,66 @@ +include ../scripts/Makefile.include + +bindir ?= /usr/bin + +ifeq ($(srctree),) +srctree := $(patsubst %/,%,$(dir $(CURDIR))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +endif + +# Do not use make's built-in rules +# (this improves performance and avoids hard-to-debug behaviour); +MAKEFLAGS += -r + CC = $(CROSS_COMPILE)gcc +LD = $(CROSS_COMPILE)ld +CFLAGS += -O2 -Wall -g -D_GNU_SOURCE -I$(OUTPUT)include + +ALL_TARGETS := spidev_test spidev_fdx +ALL_PROGRAMS := $(patsubst %,$(OUTPUT)%,$(ALL_TARGETS)) + +all: $(ALL_PROGRAMS) + +export srctree OUTPUT CC LD CFLAGS +include $(srctree)/tools/build/Makefile.include -all: spidev_test spidev_fdx +# +# We need the following to be outside of kernel tree +# +$(OUTPUT)include/linux/spi/spidev.h: ../../include/uapi/linux/spi/spidev.h + mkdir -p $(OUTPUT)include/linux/spi 2>&1 || true + ln -sf $(CURDIR)/../../include/uapi/linux/spi/spidev.h $@ + +prepare: $(OUTPUT)include/linux/spi/spidev.h + +# +# spidev_test +# +SPIDEV_TEST_IN := $(OUTPUT)spidev_test-in.o +$(SPIDEV_TEST_IN): prepare FORCE + $(Q)$(MAKE) $(build)=spidev_test +$(OUTPUT)spidev_test: $(SPIDEV_TEST_IN) + $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@ + +# +# spidev_fdx +# +SPIDEV_FDX_IN := $(OUTPUT)spidev_fdx-in.o +$(SPIDEV_FDX_IN): prepare FORCE + $(Q)$(MAKE) $(build)=spidev_fdx +$(OUTPUT)spidev_fdx: $(SPIDEV_FDX_IN) + $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@ clean: - $(RM) spidev_test spidev_fdx + rm -f $(ALL_PROGRAMS) + rm -f $(OUTPUT)include/linux/spi/spidev.h + find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete + +install: $(ALL_PROGRAMS) + install -d -m 755 $(DESTDIR)$(bindir); \ + for program in $(ALL_PROGRAMS); do \ + install $$program $(DESTDIR)$(bindir); \ + done + +FORCE: + +.PHONY: all install clean FORCE prepare diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c index 64cae1a5deff..e1f75a1914a1 100644 --- a/tools/testing/nvdimm/test/iomap.c +++ b/tools/testing/nvdimm/test/iomap.c @@ -370,7 +370,7 @@ acpi_status __wrap_acpi_evaluate_object(acpi_handle handle, acpi_string path, } EXPORT_SYMBOL(__wrap_acpi_evaluate_object); -union acpi_object * __wrap_acpi_evaluate_dsm(acpi_handle handle, const u8 *uuid, +union acpi_object * __wrap_acpi_evaluate_dsm(acpi_handle handle, const guid_t *guid, u64 rev, u64 func, union acpi_object *argv4) { union acpi_object *obj = ERR_PTR(-ENXIO); @@ -379,11 +379,11 @@ union acpi_object * __wrap_acpi_evaluate_dsm(acpi_handle handle, const u8 *uuid, rcu_read_lock(); ops = list_first_or_null_rcu(&iomap_head, typeof(*ops), list); if (ops) - obj = ops->evaluate_dsm(handle, uuid, rev, func, argv4); + obj = ops->evaluate_dsm(handle, guid, rev, func, argv4); rcu_read_unlock(); if (IS_ERR(obj)) - return acpi_evaluate_dsm(handle, uuid, rev, func, argv4); + return acpi_evaluate_dsm(handle, guid, rev, func, argv4); return obj; } EXPORT_SYMBOL(__wrap_acpi_evaluate_dsm); diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index c2187178fb13..d20791c3f499 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -1546,8 +1546,8 @@ static int nfit_test_blk_do_io(struct nd_blk_region *ndbr, resource_size_t dpa, else { memcpy(iobuf, mmio->addr.base + dpa, len); - /* give us some some coverage of the mmio_flush_range() API */ - mmio_flush_range(mmio->addr.base + dpa, len); + /* give us some some coverage of the arch_invalidate_pmem() API */ + arch_invalidate_pmem(mmio->addr.base + dpa, len); } nd_region_release_lane(nd_region, lane); @@ -1559,7 +1559,7 @@ static unsigned long nfit_ctl_handle; union acpi_object *result; static union acpi_object *nfit_test_evaluate_dsm(acpi_handle handle, - const u8 *uuid, u64 rev, u64 func, union acpi_object *argv4) + const guid_t *guid, u64 rev, u64 func, union acpi_object *argv4) { if (handle != &nfit_ctl_handle) return ERR_PTR(-ENXIO); @@ -1943,7 +1943,7 @@ static __init int nfit_test_init(void) nfit_test->setup = nfit_test0_setup; break; case 1: - nfit_test->num_pm = 1; + nfit_test->num_pm = 2; nfit_test->dcr_idx = NUM_DCR; nfit_test->num_dcr = 2; nfit_test->alloc = nfit_test1_alloc; diff --git a/tools/testing/nvdimm/test/nfit_test.h b/tools/testing/nvdimm/test/nfit_test.h index f54c0032c6ff..d3d63dd5ed38 100644 --- a/tools/testing/nvdimm/test/nfit_test.h +++ b/tools/testing/nvdimm/test/nfit_test.h @@ -13,6 +13,7 @@ #ifndef __NFIT_TEST_H__ #define __NFIT_TEST_H__ #include <linux/list.h> +#include <linux/uuid.h> #include <linux/ioport.h> #include <linux/spinlock_types.h> @@ -36,7 +37,8 @@ typedef void *acpi_handle; typedef struct nfit_test_resource *(*nfit_test_lookup_fn)(resource_size_t); typedef union acpi_object *(*nfit_test_evaluate_dsm_fn)(acpi_handle handle, - const u8 *uuid, u64 rev, u64 func, union acpi_object *argv4); + const guid_t *guid, u64 rev, u64 func, + union acpi_object *argv4); void __iomem *__wrap_ioremap_nocache(resource_size_t offset, unsigned long size); void __wrap_iounmap(volatile void __iomem *addr); diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index f389b02d43a0..f4b23d697448 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -14,9 +14,10 @@ LDLIBS += -lcap -lelf TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \ test_align -TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o +TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \ + test_pkt_md_access.o test_xdp_redirect.o sockmap_parse_prog.o sockmap_verdict_prog.o -TEST_PROGS := test_kmod.sh +TEST_PROGS := test_kmod.sh test_xdp_redirect.sh include ../lib.mk @@ -36,6 +37,5 @@ CLANG ?= clang %.o: %.c $(CLANG) -I. -I./include/uapi -I../../../include/uapi \ - -I../../../../samples/bpf/ \ -Wno-compare-distinct-pointer-types \ -O2 -target bpf -c $< -o $@ diff --git a/tools/testing/selftests/bpf/bpf_endian.h b/tools/testing/selftests/bpf/bpf_endian.h index 487cbfb89beb..74af266aa512 100644 --- a/tools/testing/selftests/bpf/bpf_endian.h +++ b/tools/testing/selftests/bpf/bpf_endian.h @@ -23,11 +23,19 @@ # define __bpf_htons(x) __builtin_bswap16(x) # define __bpf_constant_ntohs(x) ___constant_swab16(x) # define __bpf_constant_htons(x) ___constant_swab16(x) +# define __bpf_ntohl(x) __builtin_bswap32(x) +# define __bpf_htonl(x) __builtin_bswap32(x) +# define __bpf_constant_ntohl(x) ___constant_swab32(x) +# define __bpf_constant_htonl(x) ___constant_swab32(x) #elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ # define __bpf_ntohs(x) (x) # define __bpf_htons(x) (x) # define __bpf_constant_ntohs(x) (x) # define __bpf_constant_htons(x) (x) +# define __bpf_ntohl(x) (x) +# define __bpf_htonl(x) (x) +# define __bpf_constant_ntohl(x) (x) +# define __bpf_constant_htonl(x) (x) #else # error "Fix your compiler's __BYTE_ORDER__?!" #endif @@ -38,5 +46,11 @@ #define bpf_ntohs(x) \ (__builtin_constant_p(x) ? \ __bpf_constant_ntohs(x) : __bpf_ntohs(x)) +#define bpf_htonl(x) \ + (__builtin_constant_p(x) ? \ + __bpf_constant_htonl(x) : __bpf_htonl(x)) +#define bpf_ntohl(x) \ + (__builtin_constant_p(x) ? \ + __bpf_constant_ntohl(x) : __bpf_ntohl(x)) #endif /* __BPF_ENDIAN__ */ diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h new file mode 100644 index 000000000000..36fb9161b34a --- /dev/null +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -0,0 +1,207 @@ +#ifndef __BPF_HELPERS_H +#define __BPF_HELPERS_H + +/* helper macro to place programs, maps, license in + * different sections in elf_bpf file. Section names + * are interpreted by elf_bpf loader + */ +#define SEC(NAME) __attribute__((section(NAME), used)) + +/* helper functions called from eBPF programs written in C */ +static void *(*bpf_map_lookup_elem)(void *map, void *key) = + (void *) BPF_FUNC_map_lookup_elem; +static int (*bpf_map_update_elem)(void *map, void *key, void *value, + unsigned long long flags) = + (void *) BPF_FUNC_map_update_elem; +static int (*bpf_map_delete_elem)(void *map, void *key) = + (void *) BPF_FUNC_map_delete_elem; +static int (*bpf_probe_read)(void *dst, int size, void *unsafe_ptr) = + (void *) BPF_FUNC_probe_read; +static unsigned long long (*bpf_ktime_get_ns)(void) = + (void *) BPF_FUNC_ktime_get_ns; +static int (*bpf_trace_printk)(const char *fmt, int fmt_size, ...) = + (void *) BPF_FUNC_trace_printk; +static void (*bpf_tail_call)(void *ctx, void *map, int index) = + (void *) BPF_FUNC_tail_call; +static unsigned long long (*bpf_get_smp_processor_id)(void) = + (void *) BPF_FUNC_get_smp_processor_id; +static unsigned long long (*bpf_get_current_pid_tgid)(void) = + (void *) BPF_FUNC_get_current_pid_tgid; +static unsigned long long (*bpf_get_current_uid_gid)(void) = + (void *) BPF_FUNC_get_current_uid_gid; +static int (*bpf_get_current_comm)(void *buf, int buf_size) = + (void *) BPF_FUNC_get_current_comm; +static unsigned long long (*bpf_perf_event_read)(void *map, + unsigned long long flags) = + (void *) BPF_FUNC_perf_event_read; +static int (*bpf_clone_redirect)(void *ctx, int ifindex, int flags) = + (void *) BPF_FUNC_clone_redirect; +static int (*bpf_redirect)(int ifindex, int flags) = + (void *) BPF_FUNC_redirect; +static int (*bpf_redirect_map)(void *map, int key, int flags) = + (void *) BPF_FUNC_redirect_map; +static int (*bpf_perf_event_output)(void *ctx, void *map, + unsigned long long flags, void *data, + int size) = + (void *) BPF_FUNC_perf_event_output; +static int (*bpf_get_stackid)(void *ctx, void *map, int flags) = + (void *) BPF_FUNC_get_stackid; +static int (*bpf_probe_write_user)(void *dst, void *src, int size) = + (void *) BPF_FUNC_probe_write_user; +static int (*bpf_current_task_under_cgroup)(void *map, int index) = + (void *) BPF_FUNC_current_task_under_cgroup; +static int (*bpf_skb_get_tunnel_key)(void *ctx, void *key, int size, int flags) = + (void *) BPF_FUNC_skb_get_tunnel_key; +static int (*bpf_skb_set_tunnel_key)(void *ctx, void *key, int size, int flags) = + (void *) BPF_FUNC_skb_set_tunnel_key; +static int (*bpf_skb_get_tunnel_opt)(void *ctx, void *md, int size) = + (void *) BPF_FUNC_skb_get_tunnel_opt; +static int (*bpf_skb_set_tunnel_opt)(void *ctx, void *md, int size) = + (void *) BPF_FUNC_skb_set_tunnel_opt; +static unsigned long long (*bpf_get_prandom_u32)(void) = + (void *) BPF_FUNC_get_prandom_u32; +static int (*bpf_xdp_adjust_head)(void *ctx, int offset) = + (void *) BPF_FUNC_xdp_adjust_head; +static int (*bpf_setsockopt)(void *ctx, int level, int optname, void *optval, + int optlen) = + (void *) BPF_FUNC_setsockopt; +static int (*bpf_sk_redirect_map)(void *map, int key, int flags) = + (void *) BPF_FUNC_sk_redirect_map; +static int (*bpf_sock_map_update)(void *map, void *key, void *value, + unsigned long long flags) = + (void *) BPF_FUNC_sock_map_update; + + +/* llvm builtin functions that eBPF C program may use to + * emit BPF_LD_ABS and BPF_LD_IND instructions + */ +struct sk_buff; +unsigned long long load_byte(void *skb, + unsigned long long off) asm("llvm.bpf.load.byte"); +unsigned long long load_half(void *skb, + unsigned long long off) asm("llvm.bpf.load.half"); +unsigned long long load_word(void *skb, + unsigned long long off) asm("llvm.bpf.load.word"); + +/* a helper structure used by eBPF C program + * to describe map attributes to elf_bpf loader + */ +struct bpf_map_def { + unsigned int type; + unsigned int key_size; + unsigned int value_size; + unsigned int max_entries; + unsigned int map_flags; + unsigned int inner_map_idx; + unsigned int numa_node; +}; + +static int (*bpf_skb_load_bytes)(void *ctx, int off, void *to, int len) = + (void *) BPF_FUNC_skb_load_bytes; +static int (*bpf_skb_store_bytes)(void *ctx, int off, void *from, int len, int flags) = + (void *) BPF_FUNC_skb_store_bytes; +static int (*bpf_l3_csum_replace)(void *ctx, int off, int from, int to, int flags) = + (void *) BPF_FUNC_l3_csum_replace; +static int (*bpf_l4_csum_replace)(void *ctx, int off, int from, int to, int flags) = + (void *) BPF_FUNC_l4_csum_replace; +static int (*bpf_skb_under_cgroup)(void *ctx, void *map, int index) = + (void *) BPF_FUNC_skb_under_cgroup; +static int (*bpf_skb_change_head)(void *, int len, int flags) = + (void *) BPF_FUNC_skb_change_head; + +#if defined(__x86_64__) + +#define PT_REGS_PARM1(x) ((x)->di) +#define PT_REGS_PARM2(x) ((x)->si) +#define PT_REGS_PARM3(x) ((x)->dx) +#define PT_REGS_PARM4(x) ((x)->cx) +#define PT_REGS_PARM5(x) ((x)->r8) +#define PT_REGS_RET(x) ((x)->sp) +#define PT_REGS_FP(x) ((x)->bp) +#define PT_REGS_RC(x) ((x)->ax) +#define PT_REGS_SP(x) ((x)->sp) +#define PT_REGS_IP(x) ((x)->ip) + +#elif defined(__s390x__) + +#define PT_REGS_PARM1(x) ((x)->gprs[2]) +#define PT_REGS_PARM2(x) ((x)->gprs[3]) +#define PT_REGS_PARM3(x) ((x)->gprs[4]) +#define PT_REGS_PARM4(x) ((x)->gprs[5]) +#define PT_REGS_PARM5(x) ((x)->gprs[6]) +#define PT_REGS_RET(x) ((x)->gprs[14]) +#define PT_REGS_FP(x) ((x)->gprs[11]) /* Works only with CONFIG_FRAME_POINTER */ +#define PT_REGS_RC(x) ((x)->gprs[2]) +#define PT_REGS_SP(x) ((x)->gprs[15]) +#define PT_REGS_IP(x) ((x)->psw.addr) + +#elif defined(__aarch64__) + +#define PT_REGS_PARM1(x) ((x)->regs[0]) +#define PT_REGS_PARM2(x) ((x)->regs[1]) +#define PT_REGS_PARM3(x) ((x)->regs[2]) +#define PT_REGS_PARM4(x) ((x)->regs[3]) +#define PT_REGS_PARM5(x) ((x)->regs[4]) +#define PT_REGS_RET(x) ((x)->regs[30]) +#define PT_REGS_FP(x) ((x)->regs[29]) /* Works only with CONFIG_FRAME_POINTER */ +#define PT_REGS_RC(x) ((x)->regs[0]) +#define PT_REGS_SP(x) ((x)->sp) +#define PT_REGS_IP(x) ((x)->pc) + +#elif defined(__mips__) + +#define PT_REGS_PARM1(x) ((x)->regs[4]) +#define PT_REGS_PARM2(x) ((x)->regs[5]) +#define PT_REGS_PARM3(x) ((x)->regs[6]) +#define PT_REGS_PARM4(x) ((x)->regs[7]) +#define PT_REGS_PARM5(x) ((x)->regs[8]) +#define PT_REGS_RET(x) ((x)->regs[31]) +#define PT_REGS_FP(x) ((x)->regs[30]) /* Works only with CONFIG_FRAME_POINTER */ +#define PT_REGS_RC(x) ((x)->regs[1]) +#define PT_REGS_SP(x) ((x)->regs[29]) +#define PT_REGS_IP(x) ((x)->cp0_epc) + +#elif defined(__powerpc__) + +#define PT_REGS_PARM1(x) ((x)->gpr[3]) +#define PT_REGS_PARM2(x) ((x)->gpr[4]) +#define PT_REGS_PARM3(x) ((x)->gpr[5]) +#define PT_REGS_PARM4(x) ((x)->gpr[6]) +#define PT_REGS_PARM5(x) ((x)->gpr[7]) +#define PT_REGS_RC(x) ((x)->gpr[3]) +#define PT_REGS_SP(x) ((x)->sp) +#define PT_REGS_IP(x) ((x)->nip) + +#elif defined(__sparc__) + +#define PT_REGS_PARM1(x) ((x)->u_regs[UREG_I0]) +#define PT_REGS_PARM2(x) ((x)->u_regs[UREG_I1]) +#define PT_REGS_PARM3(x) ((x)->u_regs[UREG_I2]) +#define PT_REGS_PARM4(x) ((x)->u_regs[UREG_I3]) +#define PT_REGS_PARM5(x) ((x)->u_regs[UREG_I4]) +#define PT_REGS_RET(x) ((x)->u_regs[UREG_I7]) +#define PT_REGS_RC(x) ((x)->u_regs[UREG_I0]) +#define PT_REGS_SP(x) ((x)->u_regs[UREG_FP]) +#if defined(__arch64__) +#define PT_REGS_IP(x) ((x)->tpc) +#else +#define PT_REGS_IP(x) ((x)->pc) +#endif + +#endif + +#ifdef __powerpc__ +#define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ (ip) = (ctx)->link; }) +#define BPF_KRETPROBE_READ_RET_IP BPF_KPROBE_READ_RET_IP +#elif defined(__sparc__) +#define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ (ip) = PT_REGS_RET(ctx); }) +#define BPF_KRETPROBE_READ_RET_IP BPF_KPROBE_READ_RET_IP +#else +#define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ \ + bpf_probe_read(&(ip), sizeof(ip), (void *)PT_REGS_RET(ctx)); }) +#define BPF_KRETPROBE_READ_RET_IP(ip, ctx) ({ \ + bpf_probe_read(&(ip), sizeof(ip), \ + (void *)(PT_REGS_FP(ctx) + sizeof(ip))); }) +#endif + +#endif diff --git a/tools/testing/selftests/bpf/sockmap_parse_prog.c b/tools/testing/selftests/bpf/sockmap_parse_prog.c new file mode 100644 index 000000000000..fae3b96c3aa4 --- /dev/null +++ b/tools/testing/selftests/bpf/sockmap_parse_prog.c @@ -0,0 +1,38 @@ +#include <linux/bpf.h> +#include "bpf_helpers.h" +#include "bpf_util.h" +#include "bpf_endian.h" + +int _version SEC("version") = 1; + +#define bpf_printk(fmt, ...) \ +({ \ + char ____fmt[] = fmt; \ + bpf_trace_printk(____fmt, sizeof(____fmt), \ + ##__VA_ARGS__); \ +}) + +SEC("sk_skb1") +int bpf_prog1(struct __sk_buff *skb) +{ + void *data_end = (void *)(long) skb->data_end; + void *data = (void *)(long) skb->data; + __u32 lport = skb->local_port; + __u32 rport = skb->remote_port; + __u8 *d = data; + + if (data + 10 > data_end) + return skb->len; + + /* This write/read is a bit pointless but tests the verifier and + * strparser handler for read/write pkt data and access into sk + * fields. + */ + d[7] = 1; + + bpf_printk("parse: data[0] = (%u): local_port %i remote %i\n", + d[0], lport, bpf_ntohl(rport)); + return skb->len; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/sockmap_verdict_prog.c b/tools/testing/selftests/bpf/sockmap_verdict_prog.c new file mode 100644 index 000000000000..9b99bd10807d --- /dev/null +++ b/tools/testing/selftests/bpf/sockmap_verdict_prog.c @@ -0,0 +1,68 @@ +#include <linux/bpf.h> +#include "bpf_helpers.h" +#include "bpf_util.h" +#include "bpf_endian.h" + +int _version SEC("version") = 1; + +#define bpf_printk(fmt, ...) \ +({ \ + char ____fmt[] = fmt; \ + bpf_trace_printk(____fmt, sizeof(____fmt), \ + ##__VA_ARGS__); \ +}) + +struct bpf_map_def SEC("maps") sock_map_rx = { + .type = BPF_MAP_TYPE_SOCKMAP, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 20, +}; + +struct bpf_map_def SEC("maps") sock_map_tx = { + .type = BPF_MAP_TYPE_SOCKMAP, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 20, +}; + +struct bpf_map_def SEC("maps") sock_map_break = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 20, +}; + +SEC("sk_skb2") +int bpf_prog2(struct __sk_buff *skb) +{ + void *data_end = (void *)(long) skb->data_end; + void *data = (void *)(long) skb->data; + __u32 lport = skb->local_port; + __u32 rport = skb->remote_port; + __u8 *d = data; + __u8 sk, map; + + if (data + 8 > data_end) + return SK_DROP; + + map = d[0]; + sk = d[1]; + + d[0] = 0xd; + d[1] = 0xe; + d[2] = 0xa; + d[3] = 0xd; + d[4] = 0xb; + d[5] = 0xe; + d[6] = 0xe; + d[7] = 0xf; + + bpf_printk("verdict: data[0] = redir(%u:%u)\n", map, sk); + + if (!map) + return bpf_sk_redirect_map(&sock_map_rx, sk, 0); + return bpf_sk_redirect_map(&sock_map_tx, sk, 0); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_align.c b/tools/testing/selftests/bpf/test_align.c index 9644d4e069de..8591c89c0828 100644 --- a/tools/testing/selftests/bpf/test_align.c +++ b/tools/testing/selftests/bpf/test_align.c @@ -9,6 +9,8 @@ #include <stddef.h> #include <stdbool.h> +#include <sys/resource.h> + #include <linux/unistd.h> #include <linux/filter.h> #include <linux/bpf_perf_event.h> @@ -25,6 +27,11 @@ #define MAX_INSNS 512 #define MAX_MATCHES 16 +struct bpf_reg_match { + unsigned int line; + const char *match; +}; + struct bpf_align_test { const char *descr; struct bpf_insn insns[MAX_INSNS]; @@ -34,10 +41,14 @@ struct bpf_align_test { REJECT } result; enum bpf_prog_type prog_type; - const char *matches[MAX_MATCHES]; + /* Matches must be in order of increasing line */ + struct bpf_reg_match matches[MAX_MATCHES]; }; static struct bpf_align_test tests[] = { + /* Four tests of known constants. These aren't staggeringly + * interesting since we track exact values now. + */ { .descr = "mov", .insns = { @@ -51,11 +62,13 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - "1: R1=ctx R3=imm2,min_value=2,max_value=2,min_align=2 R10=fp", - "2: R1=ctx R3=imm4,min_value=4,max_value=4,min_align=4 R10=fp", - "3: R1=ctx R3=imm8,min_value=8,max_value=8,min_align=8 R10=fp", - "4: R1=ctx R3=imm16,min_value=16,max_value=16,min_align=16 R10=fp", - "5: R1=ctx R3=imm32,min_value=32,max_value=32,min_align=32 R10=fp", + {1, "R1=ctx(id=0,off=0,imm=0)"}, + {1, "R10=fp0"}, + {1, "R3=inv2"}, + {2, "R3=inv4"}, + {3, "R3=inv8"}, + {4, "R3=inv16"}, + {5, "R3=inv32"}, }, }, { @@ -77,17 +90,19 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - "1: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R10=fp", - "2: R1=ctx R3=imm2,min_value=2,max_value=2,min_align=2 R10=fp", - "3: R1=ctx R3=imm4,min_value=4,max_value=4,min_align=4 R10=fp", - "4: R1=ctx R3=imm8,min_value=8,max_value=8,min_align=8 R10=fp", - "5: R1=ctx R3=imm16,min_value=16,max_value=16,min_align=16 R10=fp", - "6: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R10=fp", - "7: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm32,min_value=32,max_value=32,min_align=32 R10=fp", - "8: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm16,min_value=16,max_value=16,min_align=16 R10=fp", - "9: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm8,min_value=8,max_value=8,min_align=8 R10=fp", - "10: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm4,min_value=4,max_value=4,min_align=4 R10=fp", - "11: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm2,min_value=2,max_value=2,min_align=2 R10=fp", + {1, "R1=ctx(id=0,off=0,imm=0)"}, + {1, "R10=fp0"}, + {1, "R3=inv1"}, + {2, "R3=inv2"}, + {3, "R3=inv4"}, + {4, "R3=inv8"}, + {5, "R3=inv16"}, + {6, "R3=inv1"}, + {7, "R4=inv32"}, + {8, "R4=inv16"}, + {9, "R4=inv8"}, + {10, "R4=inv4"}, + {11, "R4=inv2"}, }, }, { @@ -104,12 +119,14 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - "1: R1=ctx R3=imm4,min_value=4,max_value=4,min_align=4 R10=fp", - "2: R1=ctx R3=imm8,min_value=8,max_value=8,min_align=4 R10=fp", - "3: R1=ctx R3=imm10,min_value=10,max_value=10,min_align=2 R10=fp", - "4: R1=ctx R3=imm10,min_value=10,max_value=10,min_align=2 R4=imm8,min_value=8,max_value=8,min_align=8 R10=fp", - "5: R1=ctx R3=imm10,min_value=10,max_value=10,min_align=2 R4=imm12,min_value=12,max_value=12,min_align=4 R10=fp", - "6: R1=ctx R3=imm10,min_value=10,max_value=10,min_align=2 R4=imm14,min_value=14,max_value=14,min_align=2 R10=fp", + {1, "R1=ctx(id=0,off=0,imm=0)"}, + {1, "R10=fp0"}, + {1, "R3=inv4"}, + {2, "R3=inv8"}, + {3, "R3=inv10"}, + {4, "R4=inv8"}, + {5, "R4=inv12"}, + {6, "R4=inv14"}, }, }, { @@ -124,13 +141,16 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - "1: R1=ctx R3=imm7,min_value=7,max_value=7,min_align=1 R10=fp", - "2: R1=ctx R3=imm7,min_value=7,max_value=7,min_align=1 R10=fp", - "3: R1=ctx R3=imm14,min_value=14,max_value=14,min_align=2 R10=fp", - "4: R1=ctx R3=imm56,min_value=56,max_value=56,min_align=4 R10=fp", + {1, "R1=ctx(id=0,off=0,imm=0)"}, + {1, "R10=fp0"}, + {1, "R3=inv7"}, + {2, "R3=inv7"}, + {3, "R3=inv14"}, + {4, "R3=inv56"}, }, }, + /* Tests using unknown values */ #define PREP_PKT_POINTERS \ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, \ offsetof(struct __sk_buff, data)), \ @@ -164,17 +184,19 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - "7: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R10=fp", - "8: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv55,min_align=2 R10=fp", - "9: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv54,min_align=4 R10=fp", - "10: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv53,min_align=8 R10=fp", - "11: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv52,min_align=16 R10=fp", - "18: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv56 R10=fp", - "19: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv51,min_align=32 R10=fp", - "20: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv52,min_align=16 R10=fp", - "21: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv53,min_align=8 R10=fp", - "22: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv54,min_align=4 R10=fp", - "23: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv55,min_align=2 R10=fp", + {7, "R0=pkt(id=0,off=8,r=8,imm=0)"}, + {7, "R3=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, + {8, "R3=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"}, + {9, "R3=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {10, "R3=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"}, + {11, "R3=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"}, + {18, "R3=pkt_end(id=0,off=0,imm=0)"}, + {18, "R4=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, + {19, "R4=inv(id=0,umax_value=8160,var_off=(0x0; 0x1fe0))"}, + {20, "R4=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"}, + {21, "R4=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"}, + {22, "R4=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {23, "R4=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"}, }, }, { @@ -195,16 +217,16 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - "7: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R10=fp", - "8: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv56 R10=fp", - "9: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv55,min_align=1 R10=fp", - "10: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv56 R10=fp", - "11: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv54,min_align=2 R10=fp", - "12: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv56 R10=fp", - "13: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv53,min_align=4 R10=fp", - "14: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv56 R10=fp", - "15: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv52,min_align=8 R10=fp", - "16: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv50,min_align=8 R10=fp" + {7, "R3=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, + {8, "R4=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, + {9, "R4=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, + {10, "R4=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, + {11, "R4=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"}, + {12, "R4=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, + {13, "R4=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {14, "R4=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, + {15, "R4=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"}, + {16, "R4=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"}, }, }, { @@ -235,12 +257,14 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - "4: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=0) R3=pkt_end R5=pkt(id=0,off=0,r=0) R10=fp", - "5: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=0) R3=pkt_end R5=pkt(id=0,off=14,r=0) R10=fp", - "6: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=0) R3=pkt_end R4=pkt(id=0,off=14,r=0) R5=pkt(id=0,off=14,r=0) R10=fp", - "10: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=18) R3=pkt_end R4=inv56 R5=pkt(id=0,off=14,r=18) R10=fp", - "14: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=18) R3=pkt_end R4=inv48 R5=pkt(id=0,off=14,r=18) R10=fp", - "15: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=18) R3=pkt_end R4=inv48 R5=pkt(id=0,off=14,r=18) R10=fp", + {4, "R5=pkt(id=0,off=0,r=0,imm=0)"}, + {5, "R5=pkt(id=0,off=14,r=0,imm=0)"}, + {6, "R4=pkt(id=0,off=14,r=0,imm=0)"}, + {10, "R2=pkt(id=0,off=0,r=18,imm=0)"}, + {10, "R5=pkt(id=0,off=14,r=18,imm=0)"}, + {10, "R4=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, + {14, "R4=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff))"}, + {15, "R4=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff))"}, }, }, { @@ -295,62 +319,286 @@ static struct bpf_align_test tests[] = { /* Calculated offset in R6 has unknown value, but known * alignment of 4. */ - "8: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R6=inv54,min_align=4 R10=fp", - - /* Offset is added to packet pointer R5, resulting in known - * auxiliary alignment and offset. + {8, "R2=pkt(id=0,off=0,r=8,imm=0)"}, + {8, "R6=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + /* Offset is added to packet pointer R5, resulting in + * known fixed offset, and variable offset from R6. */ - "11: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R5=pkt(id=1,off=0,r=0),aux_off=14,aux_off_align=4 R6=inv54,min_align=4 R10=fp", - + {11, "R5=pkt(id=1,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* At the time the word size load is performed from R5, * it's total offset is NET_IP_ALIGN + reg->off (0) + * reg->aux_off (14) which is 16. Then the variable * offset is considered using reg->aux_off_align which * is 4 and meets the load's requirements. */ - "15: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=pkt(id=1,off=4,r=4),aux_off=14,aux_off_align=4 R5=pkt(id=1,off=0,r=4),aux_off=14,aux_off_align=4 R6=inv54,min_align=4 R10=fp", - - + {15, "R4=pkt(id=1,off=18,r=18,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {15, "R5=pkt(id=1,off=14,r=18,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* Variable offset is added to R5 packet pointer, * resulting in auxiliary alignment of 4. */ - "18: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off=14,aux_off_align=4 R5=pkt(id=2,off=0,r=0),aux_off_align=4 R6=inv54,min_align=4 R10=fp", - + {18, "R5=pkt(id=2,off=0,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* Constant offset is added to R5, resulting in * reg->off of 14. */ - "19: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off=14,aux_off_align=4 R5=pkt(id=2,off=14,r=0),aux_off_align=4 R6=inv54,min_align=4 R10=fp", - + {19, "R5=pkt(id=2,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* At the time the word size load is performed from R5, - * it's total offset is NET_IP_ALIGN + reg->off (14) which - * is 16. Then the variable offset is considered using - * reg->aux_off_align which is 4 and meets the load's - * requirements. + * its total fixed offset is NET_IP_ALIGN + reg->off + * (14) which is 16. Then the variable offset is 4-byte + * aligned, so the total offset is 4-byte aligned and + * meets the load's requirements. */ - "23: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=pkt(id=2,off=18,r=18),aux_off_align=4 R5=pkt(id=2,off=14,r=18),aux_off_align=4 R6=inv54,min_align=4 R10=fp", - + {23, "R4=pkt(id=2,off=18,r=18,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {23, "R5=pkt(id=2,off=14,r=18,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* Constant offset is added to R5 packet pointer, * resulting in reg->off value of 14. */ - "26: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off_align=4 R5=pkt(id=0,off=14,r=8) R6=inv54,min_align=4 R10=fp", - /* Variable offset is added to R5, resulting in an - * auxiliary offset of 14, and an auxiliary alignment of 4. + {26, "R5=pkt(id=0,off=14,r=8"}, + /* Variable offset is added to R5, resulting in a + * variable offset of (4n). */ - "27: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off_align=4 R5=pkt(id=3,off=0,r=0),aux_off=14,aux_off_align=4 R6=inv54,min_align=4 R10=fp", - /* Constant is added to R5 again, setting reg->off to 4. */ - "28: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off_align=4 R5=pkt(id=3,off=4,r=0),aux_off=14,aux_off_align=4 R6=inv54,min_align=4 R10=fp", - /* And once more we add a variable, which causes an accumulation - * of reg->off into reg->aux_off_align, with resulting value of - * 18. The auxiliary alignment stays at 4. + {27, "R5=pkt(id=3,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + /* Constant is added to R5 again, setting reg->off to 18. */ + {28, "R5=pkt(id=3,off=18,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + /* And once more we add a variable; resulting var_off + * is still (4n), fixed offset is not changed. + * Also, we create a new reg->id. */ - "29: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off_align=4 R5=pkt(id=4,off=0,r=0),aux_off=18,aux_off_align=4 R6=inv54,min_align=4 R10=fp", + {29, "R5=pkt(id=4,off=18,r=0,umax_value=2040,var_off=(0x0; 0x7fc))"}, /* At the time the word size load is performed from R5, - * it's total offset is NET_IP_ALIGN + reg->off (0) + - * reg->aux_off (18) which is 20. Then the variable offset - * is considered using reg->aux_off_align which is 4 and meets - * the load's requirements. + * its total fixed offset is NET_IP_ALIGN + reg->off (18) + * which is 20. Then the variable offset is (4n), so + * the total offset is 4-byte aligned and meets the + * load's requirements. + */ + {33, "R4=pkt(id=4,off=22,r=22,umax_value=2040,var_off=(0x0; 0x7fc))"}, + {33, "R5=pkt(id=4,off=18,r=22,umax_value=2040,var_off=(0x0; 0x7fc))"}, + }, + }, + { + .descr = "packet variable offset 2", + .insns = { + /* Create an unknown offset, (4n+2)-aligned */ + LOAD_UNKNOWN(BPF_REG_6), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_6, 2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 14), + /* Add it to the packet pointer */ + BPF_MOV64_REG(BPF_REG_5, BPF_REG_2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6), + /* Check bounds and perform a read */ + BPF_MOV64_REG(BPF_REG_4, BPF_REG_5), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_5, 0), + /* Make a (4n) offset from the value we just read */ + BPF_ALU64_IMM(BPF_AND, BPF_REG_6, 0xff), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_6, 2), + /* Add it to the packet pointer */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6), + /* Check bounds and perform a read */ + BPF_MOV64_REG(BPF_REG_4, BPF_REG_5), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_5, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .matches = { + /* Calculated offset in R6 has unknown value, but known + * alignment of 4. + */ + {8, "R2=pkt(id=0,off=0,r=8,imm=0)"}, + {8, "R6=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + /* Adding 14 makes R6 be (4n+2) */ + {9, "R6=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, + /* Packet pointer has (4n+2) offset */ + {11, "R5=pkt(id=1,off=0,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, + {13, "R4=pkt(id=1,off=4,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, + /* At the time the word size load is performed from R5, + * its total fixed offset is NET_IP_ALIGN + reg->off (0) + * which is 2. Then the variable offset is (4n+2), so + * the total offset is 4-byte aligned and meets the + * load's requirements. + */ + {15, "R5=pkt(id=1,off=0,r=4,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, + /* Newly read value in R6 was shifted left by 2, so has + * known alignment of 4. + */ + {18, "R6=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + /* Added (4n) to packet pointer's (4n+2) var_off, giving + * another (4n+2). + */ + {19, "R5=pkt(id=2,off=0,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc))"}, + {21, "R4=pkt(id=2,off=4,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc))"}, + /* At the time the word size load is performed from R5, + * its total fixed offset is NET_IP_ALIGN + reg->off (0) + * which is 2. Then the variable offset is (4n+2), so + * the total offset is 4-byte aligned and meets the + * load's requirements. + */ + {23, "R5=pkt(id=2,off=0,r=4,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc))"}, + }, + }, + { + .descr = "dubious pointer arithmetic", + .insns = { + PREP_PKT_POINTERS, + BPF_MOV64_IMM(BPF_REG_0, 0), + /* ptr & const => unknown & const */ + BPF_MOV64_REG(BPF_REG_5, BPF_REG_2), + BPF_ALU64_IMM(BPF_AND, BPF_REG_5, 0x40), + /* ptr << const => unknown << const */ + BPF_MOV64_REG(BPF_REG_5, BPF_REG_2), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_5, 2), + /* We have a (4n) value. Let's make a packet offset + * out of it. First add 14, to make it a (4n+2) + */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 14), + /* Then make sure it's nonnegative */ + BPF_JMP_IMM(BPF_JSGE, BPF_REG_5, 0, 1), + BPF_EXIT_INSN(), + /* Add it to packet pointer */ + BPF_MOV64_REG(BPF_REG_6, BPF_REG_2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_6, BPF_REG_5), + /* Check bounds and perform a read */ + BPF_MOV64_REG(BPF_REG_4, BPF_REG_6), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_6, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .matches = { + {4, "R5=pkt(id=0,off=0,r=0,imm=0)"}, + /* ptr & 0x40 == either 0 or 0x40 */ + {5, "R5=inv(id=0,umax_value=64,var_off=(0x0; 0x40))"}, + /* ptr << 2 == unknown, (4n) */ + {7, "R5=inv(id=0,smax_value=9223372036854775804,umax_value=18446744073709551612,var_off=(0x0; 0xfffffffffffffffc))"}, + /* (4n) + 14 == (4n+2). We blow our bounds, because + * the add could overflow. + */ + {8, "R5=inv(id=0,var_off=(0x2; 0xfffffffffffffffc))"}, + /* Checked s>=0 */ + {10, "R5=inv(id=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"}, + /* packet pointer + nonnegative (4n+2) */ + {12, "R6=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"}, + {14, "R4=pkt(id=1,off=4,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"}, + /* NET_IP_ALIGN + (4n+2) == (4n), alignment is fine. + * We checked the bounds, but it might have been able + * to overflow if the packet pointer started in the + * upper half of the address space. + * So we did not get a 'range' on R6, and the access + * attempt will fail. + */ + {16, "R6=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"}, + } + }, + { + .descr = "variable subtraction", + .insns = { + /* Create an unknown offset, (4n+2)-aligned */ + LOAD_UNKNOWN(BPF_REG_6), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_6), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_6, 2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 14), + /* Create another unknown, (4n)-aligned, and subtract + * it from the first one + */ + BPF_ALU64_IMM(BPF_LSH, BPF_REG_7, 2), + BPF_ALU64_REG(BPF_SUB, BPF_REG_6, BPF_REG_7), + /* Bounds-check the result */ + BPF_JMP_IMM(BPF_JSGE, BPF_REG_6, 0, 1), + BPF_EXIT_INSN(), + /* Add it to the packet pointer */ + BPF_MOV64_REG(BPF_REG_5, BPF_REG_2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6), + /* Check bounds and perform a read */ + BPF_MOV64_REG(BPF_REG_4, BPF_REG_5), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_5, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .matches = { + /* Calculated offset in R6 has unknown value, but known + * alignment of 4. + */ + {7, "R2=pkt(id=0,off=0,r=8,imm=0)"}, + {9, "R6=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + /* Adding 14 makes R6 be (4n+2) */ + {10, "R6=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, + /* New unknown value in R7 is (4n) */ + {11, "R7=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + /* Subtracting it from R6 blows our unsigned bounds */ + {12, "R6=inv(id=0,smin_value=-1006,smax_value=1034,var_off=(0x2; 0xfffffffffffffffc))"}, + /* Checked s>= 0 */ + {14, "R6=inv(id=0,umin_value=2,umax_value=1034,var_off=(0x2; 0x7fc))"}, + /* At the time the word size load is performed from R5, + * its total fixed offset is NET_IP_ALIGN + reg->off (0) + * which is 2. Then the variable offset is (4n+2), so + * the total offset is 4-byte aligned and meets the + * load's requirements. */ - "33: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=pkt(id=4,off=4,r=4),aux_off=18,aux_off_align=4 R5=pkt(id=4,off=0,r=4),aux_off=18,aux_off_align=4 R6=inv54,min_align=4 R10=fp", + {20, "R5=pkt(id=1,off=0,r=4,umin_value=2,umax_value=1034,var_off=(0x2; 0x7fc))"}, + }, + }, + { + .descr = "pointer variable subtraction", + .insns = { + /* Create an unknown offset, (4n+2)-aligned and bounded + * to [14,74] + */ + LOAD_UNKNOWN(BPF_REG_6), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_6), + BPF_ALU64_IMM(BPF_AND, BPF_REG_6, 0xf), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_6, 2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 14), + /* Subtract it from the packet pointer */ + BPF_MOV64_REG(BPF_REG_5, BPF_REG_2), + BPF_ALU64_REG(BPF_SUB, BPF_REG_5, BPF_REG_6), + /* Create another unknown, (4n)-aligned and >= 74. + * That in fact means >= 76, since 74 % 4 == 2 + */ + BPF_ALU64_IMM(BPF_LSH, BPF_REG_7, 2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, 76), + /* Add it to the packet pointer */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_7), + /* Check bounds and perform a read */ + BPF_MOV64_REG(BPF_REG_4, BPF_REG_5), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_5, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .matches = { + /* Calculated offset in R6 has unknown value, but known + * alignment of 4. + */ + {7, "R2=pkt(id=0,off=0,r=8,imm=0)"}, + {10, "R6=inv(id=0,umax_value=60,var_off=(0x0; 0x3c))"}, + /* Adding 14 makes R6 be (4n+2) */ + {11, "R6=inv(id=0,umin_value=14,umax_value=74,var_off=(0x2; 0x7c))"}, + /* Subtracting from packet pointer overflows ubounds */ + {13, "R5=pkt(id=1,off=0,r=8,umin_value=18446744073709551542,umax_value=18446744073709551602,var_off=(0xffffffffffffff82; 0x7c))"}, + /* New unknown value in R7 is (4n), >= 76 */ + {15, "R7=inv(id=0,umin_value=76,umax_value=1096,var_off=(0x0; 0x7fc))"}, + /* Adding it to packet pointer gives nice bounds again */ + {16, "R5=pkt(id=2,off=0,r=0,umin_value=2,umax_value=1082,var_off=(0x2; 0x7fc))"}, + /* At the time the word size load is performed from R5, + * its total fixed offset is NET_IP_ALIGN + reg->off (0) + * which is 2. Then the variable offset is (4n+2), so + * the total offset is 4-byte aligned and meets the + * load's requirements. + */ + {20, "R5=pkt(id=2,off=0,r=4,umin_value=2,umax_value=1082,var_off=(0x2; 0x7fc))"}, }, }, }; @@ -371,6 +619,9 @@ static int do_test_single(struct bpf_align_test *test) { struct bpf_insn *prog = test->insns; int prog_type = test->prog_type; + char bpf_vlog_copy[32768]; + const char *line_ptr; + int cur_line = -1; int prog_len, i; int fd_prog; int ret; @@ -378,27 +629,50 @@ static int do_test_single(struct bpf_align_test *test) prog_len = probe_filter_length(prog); fd_prog = bpf_verify_program(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER, prog, prog_len, 1, "GPL", 0, - bpf_vlog, sizeof(bpf_vlog)); - if (fd_prog < 0) { + bpf_vlog, sizeof(bpf_vlog), 2); + if (fd_prog < 0 && test->result != REJECT) { printf("Failed to load program.\n"); printf("%s", bpf_vlog); ret = 1; + } else if (fd_prog >= 0 && test->result == REJECT) { + printf("Unexpected success to load!\n"); + printf("%s", bpf_vlog); + ret = 1; + close(fd_prog); } else { ret = 0; + /* We make a local copy so that we can strtok() it */ + strncpy(bpf_vlog_copy, bpf_vlog, sizeof(bpf_vlog_copy)); + line_ptr = strtok(bpf_vlog_copy, "\n"); for (i = 0; i < MAX_MATCHES; i++) { - const char *t, *m = test->matches[i]; + struct bpf_reg_match m = test->matches[i]; - if (!m) + if (!m.match) break; - t = strstr(bpf_vlog, m); - if (!t) { - printf("Failed to find match: %s\n", m); + while (line_ptr) { + cur_line = -1; + sscanf(line_ptr, "%u: ", &cur_line); + if (cur_line == m.line) + break; + line_ptr = strtok(NULL, "\n"); + } + if (!line_ptr) { + printf("Failed to find line %u for match: %s\n", + m.line, m.match); + ret = 1; + printf("%s", bpf_vlog); + break; + } + if (!strstr(line_ptr, m.match)) { + printf("Failed to find match %u: %s\n", + m.line, m.match); ret = 1; printf("%s", bpf_vlog); break; } } - close(fd_prog); + if (fd_prog >= 0) + close(fd_prog); } return ret; } @@ -426,12 +700,15 @@ static int do_test(unsigned int from, unsigned int to) } printf("Results: %d pass %d fail\n", all_pass, all_fail); - return 0; + return all_fail ? EXIT_FAILURE : EXIT_SUCCESS; } int main(int argc, char **argv) { unsigned int from = 0, to = ARRAY_SIZE(tests); + struct rlimit rinf = { RLIM_INFINITY, RLIM_INFINITY }; + + setrlimit(RLIMIT_MEMLOCK, &rinf); if (argc == 3) { unsigned int l = atoi(argv[argc - 2]); diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index 93314524de0d..fe3a443a1102 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -22,6 +22,7 @@ #include <linux/bpf.h> #include <bpf/bpf.h> +#include <bpf/libbpf.h> #include "bpf_util.h" static int map_flags; @@ -239,6 +240,54 @@ static void test_hashmap_percpu(int task, void *data) close(fd); } +static void test_hashmap_walk(int task, void *data) +{ + int fd, i, max_entries = 100000; + long long key, value, next_key; + bool next_key_valid = true; + + fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value), + max_entries, map_flags); + if (fd < 0) { + printf("Failed to create hashmap '%s'!\n", strerror(errno)); + exit(1); + } + + for (i = 0; i < max_entries; i++) { + key = i; value = key; + assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) == 0); + } + + for (i = 0; bpf_map_get_next_key(fd, !i ? NULL : &key, + &next_key) == 0; i++) { + key = next_key; + assert(bpf_map_lookup_elem(fd, &key, &value) == 0); + } + + assert(i == max_entries); + + assert(bpf_map_get_next_key(fd, NULL, &key) == 0); + for (i = 0; next_key_valid; i++) { + next_key_valid = bpf_map_get_next_key(fd, &key, &next_key) == 0; + assert(bpf_map_lookup_elem(fd, &key, &value) == 0); + value++; + assert(bpf_map_update_elem(fd, &key, &value, BPF_EXIST) == 0); + key = next_key; + } + + assert(i == max_entries); + + for (i = 0; bpf_map_get_next_key(fd, !i ? NULL : &key, + &next_key) == 0; i++) { + key = next_key; + assert(bpf_map_lookup_elem(fd, &key, &value) == 0); + assert(value - 1 == key); + } + + assert(i == max_entries); + close(fd); +} + static void test_arraymap(int task, void *data) { int key, next_key, fd; @@ -390,6 +439,444 @@ static void test_arraymap_percpu_many_keys(void) close(fd); } +static void test_devmap(int task, void *data) +{ + int fd; + __u32 key, value; + + fd = bpf_create_map(BPF_MAP_TYPE_DEVMAP, sizeof(key), sizeof(value), + 2, 0); + if (fd < 0) { + printf("Failed to create arraymap '%s'!\n", strerror(errno)); + exit(1); + } + + close(fd); +} + +#include <sys/socket.h> +#include <sys/ioctl.h> +#include <arpa/inet.h> +#include <sys/select.h> +#include <linux/err.h> +#define SOCKMAP_PARSE_PROG "./sockmap_parse_prog.o" +#define SOCKMAP_VERDICT_PROG "./sockmap_verdict_prog.o" +static void test_sockmap(int tasks, void *data) +{ + int one = 1, map_fd_rx, map_fd_tx, map_fd_break, s, sc, rc; + struct bpf_map *bpf_map_rx, *bpf_map_tx, *bpf_map_break; + int ports[] = {50200, 50201, 50202, 50204}; + int err, i, fd, sfd[6] = {0xdeadbeef}; + u8 buf[20] = {0x0, 0x5, 0x3, 0x2, 0x1, 0x0}; + int parse_prog, verdict_prog; + struct sockaddr_in addr; + struct bpf_object *obj; + struct timeval to; + __u32 key, value; + pid_t pid[tasks]; + fd_set w; + + /* Create some sockets to use with sockmap */ + for (i = 0; i < 2; i++) { + sfd[i] = socket(AF_INET, SOCK_STREAM, 0); + if (sfd[i] < 0) + goto out; + err = setsockopt(sfd[i], SOL_SOCKET, SO_REUSEADDR, + (char *)&one, sizeof(one)); + if (err) { + printf("failed to setsockopt\n"); + goto out; + } + err = ioctl(sfd[i], FIONBIO, (char *)&one); + if (err < 0) { + printf("failed to ioctl\n"); + goto out; + } + memset(&addr, 0, sizeof(struct sockaddr_in)); + addr.sin_family = AF_INET; + addr.sin_addr.s_addr = inet_addr("127.0.0.1"); + addr.sin_port = htons(ports[i]); + err = bind(sfd[i], (struct sockaddr *)&addr, sizeof(addr)); + if (err < 0) { + printf("failed to bind: err %i: %i:%i\n", + err, i, sfd[i]); + goto out; + } + err = listen(sfd[i], 32); + if (err < 0) { + printf("failed to listen\n"); + goto out; + } + } + + for (i = 2; i < 4; i++) { + sfd[i] = socket(AF_INET, SOCK_STREAM, 0); + if (sfd[i] < 0) + goto out; + err = setsockopt(sfd[i], SOL_SOCKET, SO_REUSEADDR, + (char *)&one, sizeof(one)); + if (err) { + printf("set sock opt\n"); + goto out; + } + memset(&addr, 0, sizeof(struct sockaddr_in)); + addr.sin_family = AF_INET; + addr.sin_addr.s_addr = inet_addr("127.0.0.1"); + addr.sin_port = htons(ports[i - 2]); + err = connect(sfd[i], (struct sockaddr *)&addr, sizeof(addr)); + if (err) { + printf("failed to connect\n"); + goto out; + } + } + + + for (i = 4; i < 6; i++) { + sfd[i] = accept(sfd[i - 4], NULL, NULL); + if (sfd[i] < 0) { + printf("accept failed\n"); + goto out; + } + } + + /* Test sockmap with connected sockets */ + fd = bpf_create_map(BPF_MAP_TYPE_SOCKMAP, + sizeof(key), sizeof(value), + 6, 0); + if (fd < 0) { + printf("Failed to create sockmap %i\n", fd); + goto out_sockmap; + } + + /* Test update without programs */ + for (i = 0; i < 6; i++) { + err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_ANY); + if (err) { + printf("Failed noprog update sockmap '%i:%i'\n", + i, sfd[i]); + goto out_sockmap; + } + } + + /* Test attaching/detaching bad fds */ + err = bpf_prog_attach(-1, fd, BPF_SK_SKB_STREAM_PARSER, 0); + if (!err) { + printf("Failed invalid parser prog attach\n"); + goto out_sockmap; + } + + err = bpf_prog_attach(-1, fd, BPF_SK_SKB_STREAM_VERDICT, 0); + if (!err) { + printf("Failed invalid verdict prog attach\n"); + goto out_sockmap; + } + + err = bpf_prog_attach(-1, fd, __MAX_BPF_ATTACH_TYPE, 0); + if (!err) { + printf("Failed unknown prog attach\n"); + goto out_sockmap; + } + + err = bpf_prog_detach(fd, BPF_SK_SKB_STREAM_PARSER); + if (err) { + printf("Failed empty parser prog detach\n"); + goto out_sockmap; + } + + err = bpf_prog_detach(fd, BPF_SK_SKB_STREAM_VERDICT); + if (err) { + printf("Failed empty verdict prog detach\n"); + goto out_sockmap; + } + + err = bpf_prog_detach(fd, __MAX_BPF_ATTACH_TYPE); + if (!err) { + printf("Detach invalid prog successful\n"); + goto out_sockmap; + } + + /* Load SK_SKB program and Attach */ + err = bpf_prog_load(SOCKMAP_PARSE_PROG, + BPF_PROG_TYPE_SK_SKB, &obj, &parse_prog); + if (err) { + printf("Failed to load SK_SKB parse prog\n"); + goto out_sockmap; + } + + err = bpf_prog_load(SOCKMAP_VERDICT_PROG, + BPF_PROG_TYPE_SK_SKB, &obj, &verdict_prog); + if (err) { + printf("Failed to load SK_SKB verdict prog\n"); + goto out_sockmap; + } + + bpf_map_rx = bpf_object__find_map_by_name(obj, "sock_map_rx"); + if (IS_ERR(bpf_map_rx)) { + printf("Failed to load map rx from verdict prog\n"); + goto out_sockmap; + } + + map_fd_rx = bpf_map__fd(bpf_map_rx); + if (map_fd_rx < 0) { + printf("Failed to get map fd\n"); + goto out_sockmap; + } + + bpf_map_tx = bpf_object__find_map_by_name(obj, "sock_map_tx"); + if (IS_ERR(bpf_map_tx)) { + printf("Failed to load map tx from verdict prog\n"); + goto out_sockmap; + } + + map_fd_tx = bpf_map__fd(bpf_map_tx); + if (map_fd_tx < 0) { + printf("Failed to get map tx fd\n"); + goto out_sockmap; + } + + bpf_map_break = bpf_object__find_map_by_name(obj, "sock_map_break"); + if (IS_ERR(bpf_map_break)) { + printf("Failed to load map tx from verdict prog\n"); + goto out_sockmap; + } + + map_fd_break = bpf_map__fd(bpf_map_break); + if (map_fd_break < 0) { + printf("Failed to get map tx fd\n"); + goto out_sockmap; + } + + err = bpf_prog_attach(parse_prog, map_fd_break, + BPF_SK_SKB_STREAM_PARSER, 0); + if (!err) { + printf("Allowed attaching SK_SKB program to invalid map\n"); + goto out_sockmap; + } + + err = bpf_prog_attach(parse_prog, map_fd_rx, + BPF_SK_SKB_STREAM_PARSER, 0); + if (err) { + printf("Failed stream parser bpf prog attach\n"); + goto out_sockmap; + } + + err = bpf_prog_attach(verdict_prog, map_fd_rx, + BPF_SK_SKB_STREAM_VERDICT, 0); + if (err) { + printf("Failed stream verdict bpf prog attach\n"); + goto out_sockmap; + } + + err = bpf_prog_attach(verdict_prog, map_fd_rx, + __MAX_BPF_ATTACH_TYPE, 0); + if (!err) { + printf("Attached unknown bpf prog\n"); + goto out_sockmap; + } + + /* Test map update elem afterwards fd lives in fd and map_fd */ + for (i = 0; i < 6; i++) { + err = bpf_map_update_elem(map_fd_rx, &i, &sfd[i], BPF_ANY); + if (err) { + printf("Failed map_fd_rx update sockmap %i '%i:%i'\n", + err, i, sfd[i]); + goto out_sockmap; + } + err = bpf_map_update_elem(map_fd_tx, &i, &sfd[i], BPF_ANY); + if (err) { + printf("Failed map_fd_tx update sockmap %i '%i:%i'\n", + err, i, sfd[i]); + goto out_sockmap; + } + } + + /* Test map delete elem and remove send/recv sockets */ + for (i = 2; i < 4; i++) { + err = bpf_map_delete_elem(map_fd_rx, &i); + if (err) { + printf("Failed delete sockmap rx %i '%i:%i'\n", + err, i, sfd[i]); + goto out_sockmap; + } + err = bpf_map_delete_elem(map_fd_tx, &i); + if (err) { + printf("Failed delete sockmap tx %i '%i:%i'\n", + err, i, sfd[i]); + goto out_sockmap; + } + } + + /* Test map send/recv */ + for (i = 0; i < 2; i++) { + buf[0] = i; + buf[1] = 0x5; + sc = send(sfd[2], buf, 20, 0); + if (sc < 0) { + printf("Failed sockmap send\n"); + goto out_sockmap; + } + + FD_ZERO(&w); + FD_SET(sfd[3], &w); + to.tv_sec = 1; + to.tv_usec = 0; + s = select(sfd[3] + 1, &w, NULL, NULL, &to); + if (s == -1) { + perror("Failed sockmap select()"); + goto out_sockmap; + } else if (!s) { + printf("Failed sockmap unexpected timeout\n"); + goto out_sockmap; + } + + if (!FD_ISSET(sfd[3], &w)) { + printf("Failed sockmap select/recv\n"); + goto out_sockmap; + } + + rc = recv(sfd[3], buf, sizeof(buf), 0); + if (rc < 0) { + printf("Failed sockmap recv\n"); + goto out_sockmap; + } + } + + /* Negative null entry lookup from datapath should be dropped */ + buf[0] = 1; + buf[1] = 12; + sc = send(sfd[2], buf, 20, 0); + if (sc < 0) { + printf("Failed sockmap send\n"); + goto out_sockmap; + } + + /* Push fd into same slot */ + i = 2; + err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_NOEXIST); + if (!err) { + printf("Failed allowed sockmap dup slot BPF_NOEXIST\n"); + goto out_sockmap; + } + + err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_ANY); + if (err) { + printf("Failed sockmap update new slot BPF_ANY\n"); + goto out_sockmap; + } + + err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_EXIST); + if (err) { + printf("Failed sockmap update new slot BPF_EXIST\n"); + goto out_sockmap; + } + + /* Delete the elems without programs */ + for (i = 0; i < 6; i++) { + err = bpf_map_delete_elem(fd, &i); + if (err) { + printf("Failed delete sockmap %i '%i:%i'\n", + err, i, sfd[i]); + } + } + + /* Test having multiple maps open and set with programs on same fds */ + err = bpf_prog_attach(parse_prog, fd, + BPF_SK_SKB_STREAM_PARSER, 0); + if (err) { + printf("Failed fd bpf parse prog attach\n"); + goto out_sockmap; + } + err = bpf_prog_attach(verdict_prog, fd, + BPF_SK_SKB_STREAM_VERDICT, 0); + if (err) { + printf("Failed fd bpf verdict prog attach\n"); + goto out_sockmap; + } + + for (i = 4; i < 6; i++) { + err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_ANY); + if (!err) { + printf("Failed allowed duplicate programs in update ANY sockmap %i '%i:%i'\n", + err, i, sfd[i]); + goto out_sockmap; + } + err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_NOEXIST); + if (!err) { + printf("Failed allowed duplicate program in update NOEXIST sockmap %i '%i:%i'\n", + err, i, sfd[i]); + goto out_sockmap; + } + err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_EXIST); + if (!err) { + printf("Failed allowed duplicate program in update EXIST sockmap %i '%i:%i'\n", + err, i, sfd[i]); + goto out_sockmap; + } + } + + /* Test tasks number of forked operations */ + for (i = 0; i < tasks; i++) { + pid[i] = fork(); + if (pid[i] == 0) { + for (i = 0; i < 6; i++) { + bpf_map_delete_elem(map_fd_tx, &i); + bpf_map_delete_elem(map_fd_rx, &i); + bpf_map_update_elem(map_fd_tx, &i, + &sfd[i], BPF_ANY); + bpf_map_update_elem(map_fd_rx, &i, + &sfd[i], BPF_ANY); + } + exit(0); + } else if (pid[i] == -1) { + printf("Couldn't spawn #%d process!\n", i); + exit(1); + } + } + + for (i = 0; i < tasks; i++) { + int status; + + assert(waitpid(pid[i], &status, 0) == pid[i]); + assert(status == 0); + } + + err = bpf_prog_detach(map_fd_rx, __MAX_BPF_ATTACH_TYPE); + if (!err) { + printf("Detached an invalid prog type.\n"); + goto out_sockmap; + } + + err = bpf_prog_detach(map_fd_rx, BPF_SK_SKB_STREAM_PARSER); + if (err) { + printf("Failed parser prog detach\n"); + goto out_sockmap; + } + + err = bpf_prog_detach(map_fd_rx, BPF_SK_SKB_STREAM_VERDICT); + if (err) { + printf("Failed parser prog detach\n"); + goto out_sockmap; + } + + /* Test map close sockets */ + for (i = 0; i < 6; i++) + close(sfd[i]); + close(fd); + close(map_fd_rx); + bpf_object__close(obj); + return; +out: + for (i = 0; i < 6; i++) + close(sfd[i]); + printf("Failed to create sockmap '%i:%s'!\n", i, strerror(errno)); + exit(1); +out_sockmap: + for (i = 0; i < 6; i++) + close(sfd[i]); + close(fd); + exit(1); +} + #define MAP_SIZE (32 * 1024) static void test_map_large(void) @@ -464,6 +951,7 @@ static void test_map_stress(void) run_parallel(100, test_hashmap, NULL); run_parallel(100, test_hashmap_percpu, NULL); run_parallel(100, test_hashmap_sizes, NULL); + run_parallel(100, test_hashmap_walk, NULL); run_parallel(100, test_arraymap, NULL); run_parallel(100, test_arraymap_percpu, NULL); @@ -549,12 +1037,16 @@ static void run_all_tests(void) { test_hashmap(0, NULL); test_hashmap_percpu(0, NULL); + test_hashmap_walk(0, NULL); test_arraymap(0, NULL); test_arraymap_percpu(0, NULL); test_arraymap_percpu_many_keys(); + test_devmap(0, NULL); + test_sockmap(0, NULL); + test_map_large(); test_map_parallel(); test_map_stress(); diff --git a/tools/testing/selftests/bpf/test_obj_id.c b/tools/testing/selftests/bpf/test_obj_id.c new file mode 100644 index 000000000000..880d2963b472 --- /dev/null +++ b/tools/testing/selftests/bpf/test_obj_id.c @@ -0,0 +1,35 @@ +/* Copyright (c) 2017 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <stddef.h> +#include <linux/bpf.h> +#include <linux/pkt_cls.h> +#include "bpf_helpers.h" + +/* It is a dumb bpf program such that it must have no + * issue to be loaded since testing the verifier is + * not the focus here. + */ + +int _version SEC("version") = 1; + +struct bpf_map_def SEC("maps") test_map_id = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(__u64), + .max_entries = 1, +}; + +SEC("test_obj_id_dummy") +int test_obj_id(struct __sk_buff *skb) +{ + __u32 key = 0; + __u64 *value; + + value = bpf_map_lookup_elem(&test_map_id, &key); + + return TC_ACT_OK; +} diff --git a/tools/testing/selftests/bpf/test_pkt_md_access.c b/tools/testing/selftests/bpf/test_pkt_md_access.c new file mode 100644 index 000000000000..7956302ecdf2 --- /dev/null +++ b/tools/testing/selftests/bpf/test_pkt_md_access.c @@ -0,0 +1,46 @@ +/* Copyright (c) 2017 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <stddef.h> +#include <string.h> +#include <linux/bpf.h> +#include <linux/pkt_cls.h> +#include "bpf_helpers.h" + +int _version SEC("version") = 1; + +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ +#define TEST_FIELD(TYPE, FIELD, MASK) \ + { \ + TYPE tmp = *(volatile TYPE *)&skb->FIELD; \ + if (tmp != ((*(volatile __u32 *)&skb->FIELD) & MASK)) \ + return TC_ACT_SHOT; \ + } +#else +#define TEST_FIELD_OFFSET(a, b) ((sizeof(a) - sizeof(b)) / sizeof(b)) +#define TEST_FIELD(TYPE, FIELD, MASK) \ + { \ + TYPE tmp = *((volatile TYPE *)&skb->FIELD + \ + TEST_FIELD_OFFSET(skb->FIELD, TYPE)); \ + if (tmp != ((*(volatile __u32 *)&skb->FIELD) & MASK)) \ + return TC_ACT_SHOT; \ + } +#endif + +SEC("test1") +int process(struct __sk_buff *skb) +{ + TEST_FIELD(__u8, len, 0xFF); + TEST_FIELD(__u16, len, 0xFFFF); + TEST_FIELD(__u32, len, 0xFFFFFFFF); + TEST_FIELD(__u16, protocol, 0xFFFF); + TEST_FIELD(__u32, protocol, 0xFFFFFFFF); + TEST_FIELD(__u8, hash, 0xFF); + TEST_FIELD(__u16, hash, 0xFFFF); + TEST_FIELD(__u32, hash, 0xFFFFFFFF); + + return TC_ACT_OK; +} diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index b59f5ed4ae40..11ee25cea227 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -22,6 +22,8 @@ typedef __u16 __sum16; #include <sys/wait.h> #include <sys/resource.h> +#include <sys/types.h> +#include <fcntl.h> #include <linux/bpf.h> #include <linux/err.h> @@ -70,41 +72,9 @@ static struct { pass_cnt++; \ printf("%s:PASS:%s %d nsec\n", __func__, tag, duration);\ } \ + __ret; \ }) -static int bpf_prog_load(const char *file, enum bpf_prog_type type, - struct bpf_object **pobj, int *prog_fd) -{ - struct bpf_program *prog; - struct bpf_object *obj; - int err; - - obj = bpf_object__open(file); - if (IS_ERR(obj)) { - error_cnt++; - return -ENOENT; - } - - prog = bpf_program__next(NULL, obj); - if (!prog) { - bpf_object__close(obj); - error_cnt++; - return -ENOENT; - } - - bpf_program__set_type(prog, type); - err = bpf_object__load(obj); - if (err) { - bpf_object__close(obj); - error_cnt++; - return -EINVAL; - } - - *pobj = obj; - *prog_fd = bpf_program__fd(prog); - return 0; -} - static int bpf_find_map(const char *test, struct bpf_object *obj, const char *name) { @@ -127,8 +97,10 @@ static void test_pkt_access(void) int err, prog_fd; err = bpf_prog_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); - if (err) + if (err) { + error_cnt++; return; + } err = bpf_prog_test_run(prog_fd, 100000, &pkt_v4, sizeof(pkt_v4), NULL, NULL, &retval, &duration); @@ -159,8 +131,10 @@ static void test_xdp(void) int err, prog_fd, map_fd; err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); - if (err) + if (err) { + error_cnt++; return; + } map_fd = bpf_find_map(__func__, obj, "vip2tnl"); if (map_fd < 0) @@ -220,8 +194,10 @@ static void test_l4lb(void) u32 *magic = (u32 *)buf; err = bpf_prog_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); - if (err) + if (err) { + error_cnt++; return; + } map_fd = bpf_find_map(__func__, obj, "vip_map"); if (map_fd < 0) @@ -277,8 +253,244 @@ static void test_tcp_estats(void) err = bpf_prog_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd); CHECK(err, "", "err %d errno %d\n", err, errno); - if (err) + if (err) { + error_cnt++; return; + } + + bpf_object__close(obj); +} + +static inline __u64 ptr_to_u64(const void *ptr) +{ + return (__u64) (unsigned long) ptr; +} + +static void test_bpf_obj_id(void) +{ + const __u64 array_magic_value = 0xfaceb00c; + const __u32 array_key = 0; + const int nr_iters = 2; + const char *file = "./test_obj_id.o"; + const char *jit_sysctl = "/proc/sys/net/core/bpf_jit_enable"; + + struct bpf_object *objs[nr_iters]; + int prog_fds[nr_iters], map_fds[nr_iters]; + /* +1 to test for the info_len returned by kernel */ + struct bpf_prog_info prog_infos[nr_iters + 1]; + struct bpf_map_info map_infos[nr_iters + 1]; + char jited_insns[128], xlated_insns[128], zeros[128]; + __u32 i, next_id, info_len, nr_id_found, duration = 0; + int sysctl_fd, jit_enabled = 0, err = 0; + __u64 array_value; + + sysctl_fd = open(jit_sysctl, 0, O_RDONLY); + if (sysctl_fd != -1) { + char tmpc; + + if (read(sysctl_fd, &tmpc, sizeof(tmpc)) == 1) + jit_enabled = (tmpc != '0'); + close(sysctl_fd); + } + + err = bpf_prog_get_fd_by_id(0); + CHECK(err >= 0 || errno != ENOENT, + "get-fd-by-notexist-prog-id", "err %d errno %d\n", err, errno); + + err = bpf_map_get_fd_by_id(0); + CHECK(err >= 0 || errno != ENOENT, + "get-fd-by-notexist-map-id", "err %d errno %d\n", err, errno); + + for (i = 0; i < nr_iters; i++) + objs[i] = NULL; + + /* Check bpf_obj_get_info_by_fd() */ + bzero(zeros, sizeof(zeros)); + for (i = 0; i < nr_iters; i++) { + err = bpf_prog_load(file, BPF_PROG_TYPE_SOCKET_FILTER, + &objs[i], &prog_fds[i]); + /* test_obj_id.o is a dumb prog. It should never fail + * to load. + */ + if (err) + error_cnt++; + assert(!err); + + /* Check getting prog info */ + info_len = sizeof(struct bpf_prog_info) * 2; + bzero(&prog_infos[i], info_len); + bzero(jited_insns, sizeof(jited_insns)); + bzero(xlated_insns, sizeof(xlated_insns)); + prog_infos[i].jited_prog_insns = ptr_to_u64(jited_insns); + prog_infos[i].jited_prog_len = sizeof(jited_insns); + prog_infos[i].xlated_prog_insns = ptr_to_u64(xlated_insns); + prog_infos[i].xlated_prog_len = sizeof(xlated_insns); + err = bpf_obj_get_info_by_fd(prog_fds[i], &prog_infos[i], + &info_len); + if (CHECK(err || + prog_infos[i].type != BPF_PROG_TYPE_SOCKET_FILTER || + info_len != sizeof(struct bpf_prog_info) || + (jit_enabled && !prog_infos[i].jited_prog_len) || + (jit_enabled && + !memcmp(jited_insns, zeros, sizeof(zeros))) || + !prog_infos[i].xlated_prog_len || + !memcmp(xlated_insns, zeros, sizeof(zeros)), + "get-prog-info(fd)", + "err %d errno %d i %d type %d(%d) info_len %u(%lu) jit_enabled %d jited_prog_len %u xlated_prog_len %u jited_prog %d xlated_prog %d\n", + err, errno, i, + prog_infos[i].type, BPF_PROG_TYPE_SOCKET_FILTER, + info_len, sizeof(struct bpf_prog_info), + jit_enabled, + prog_infos[i].jited_prog_len, + prog_infos[i].xlated_prog_len, + !!memcmp(jited_insns, zeros, sizeof(zeros)), + !!memcmp(xlated_insns, zeros, sizeof(zeros)))) + goto done; + + map_fds[i] = bpf_find_map(__func__, objs[i], "test_map_id"); + assert(map_fds[i] >= 0); + err = bpf_map_update_elem(map_fds[i], &array_key, + &array_magic_value, 0); + assert(!err); + + /* Check getting map info */ + info_len = sizeof(struct bpf_map_info) * 2; + bzero(&map_infos[i], info_len); + err = bpf_obj_get_info_by_fd(map_fds[i], &map_infos[i], + &info_len); + if (CHECK(err || + map_infos[i].type != BPF_MAP_TYPE_ARRAY || + map_infos[i].key_size != sizeof(__u32) || + map_infos[i].value_size != sizeof(__u64) || + map_infos[i].max_entries != 1 || + map_infos[i].map_flags != 0 || + info_len != sizeof(struct bpf_map_info), + "get-map-info(fd)", + "err %d errno %d type %d(%d) info_len %u(%lu) key_size %u value_size %u max_entries %u map_flags %X\n", + err, errno, + map_infos[i].type, BPF_MAP_TYPE_ARRAY, + info_len, sizeof(struct bpf_map_info), + map_infos[i].key_size, + map_infos[i].value_size, + map_infos[i].max_entries, + map_infos[i].map_flags)) + goto done; + } + + /* Check bpf_prog_get_next_id() */ + nr_id_found = 0; + next_id = 0; + while (!bpf_prog_get_next_id(next_id, &next_id)) { + struct bpf_prog_info prog_info = {}; + int prog_fd; + + info_len = sizeof(prog_info); + + prog_fd = bpf_prog_get_fd_by_id(next_id); + if (prog_fd < 0 && errno == ENOENT) + /* The bpf_prog is in the dead row */ + continue; + if (CHECK(prog_fd < 0, "get-prog-fd(next_id)", + "prog_fd %d next_id %d errno %d\n", + prog_fd, next_id, errno)) + break; + + for (i = 0; i < nr_iters; i++) + if (prog_infos[i].id == next_id) + break; + + if (i == nr_iters) + continue; + + nr_id_found++; + + err = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &info_len); + prog_infos[i].jited_prog_insns = 0; + prog_infos[i].xlated_prog_insns = 0; + CHECK(err || info_len != sizeof(struct bpf_prog_info) || + memcmp(&prog_info, &prog_infos[i], info_len), + "get-prog-info(next_id->fd)", + "err %d errno %d info_len %u(%lu) memcmp %d\n", + err, errno, info_len, sizeof(struct bpf_prog_info), + memcmp(&prog_info, &prog_infos[i], info_len)); + + close(prog_fd); + } + CHECK(nr_id_found != nr_iters, + "check total prog id found by get_next_id", + "nr_id_found %u(%u)\n", + nr_id_found, nr_iters); + + /* Check bpf_map_get_next_id() */ + nr_id_found = 0; + next_id = 0; + while (!bpf_map_get_next_id(next_id, &next_id)) { + struct bpf_map_info map_info = {}; + int map_fd; + + info_len = sizeof(map_info); + + map_fd = bpf_map_get_fd_by_id(next_id); + if (map_fd < 0 && errno == ENOENT) + /* The bpf_map is in the dead row */ + continue; + if (CHECK(map_fd < 0, "get-map-fd(next_id)", + "map_fd %d next_id %u errno %d\n", + map_fd, next_id, errno)) + break; + + for (i = 0; i < nr_iters; i++) + if (map_infos[i].id == next_id) + break; + + if (i == nr_iters) + continue; + + nr_id_found++; + + err = bpf_map_lookup_elem(map_fd, &array_key, &array_value); + assert(!err); + + err = bpf_obj_get_info_by_fd(map_fd, &map_info, &info_len); + CHECK(err || info_len != sizeof(struct bpf_map_info) || + memcmp(&map_info, &map_infos[i], info_len) || + array_value != array_magic_value, + "check get-map-info(next_id->fd)", + "err %d errno %d info_len %u(%lu) memcmp %d array_value %llu(%llu)\n", + err, errno, info_len, sizeof(struct bpf_map_info), + memcmp(&map_info, &map_infos[i], info_len), + array_value, array_magic_value); + + close(map_fd); + } + CHECK(nr_id_found != nr_iters, + "check total map id found by get_next_id", + "nr_id_found %u(%u)\n", + nr_id_found, nr_iters); + +done: + for (i = 0; i < nr_iters; i++) + bpf_object__close(objs[i]); +} + +static void test_pkt_md_access(void) +{ + const char *file = "./test_pkt_md_access.o"; + struct bpf_object *obj; + __u32 duration, retval; + int err, prog_fd; + + err = bpf_prog_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); + if (err) { + error_cnt++; + return; + } + + err = bpf_prog_test_run(prog_fd, 10, &pkt_v4, sizeof(pkt_v4), + NULL, NULL, &retval, &duration); + CHECK(err || retval, "", + "err %d errno %d retval %d duration %d\n", + err, errno, retval, duration); bpf_object__close(obj); } @@ -293,7 +505,9 @@ int main(void) test_xdp(); test_l4lb(); test_tcp_estats(); + test_bpf_obj_id(); + test_pkt_md_access(); printf("Summary: %d PASSED, %d FAILED\n", pass_cnt, error_cnt); - return 0; + return error_cnt ? EXIT_FAILURE : EXIT_SUCCESS; } diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 0ff8c55c0464..8eb09950258b 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -8,6 +8,7 @@ * License as published by the Free Software Foundation. */ +#include <endian.h> #include <asm/types.h> #include <linux/types.h> #include <stdint.h> @@ -421,7 +422,7 @@ static struct bpf_test tests[] = { BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R1 pointer arithmetic", + .errstr_unpriv = "R1 subtraction from stack pointer", .result_unpriv = REJECT, .errstr = "R1 invalid mem access", .result = REJECT, @@ -603,8 +604,9 @@ static struct bpf_test tests[] = { BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, -4), BPF_EXIT_INSN(), }, - .errstr = "misaligned access", + .errstr = "misaligned stack access", .result = REJECT, + .flags = F_LOAD_WITH_STRICT_ALIGNMENT, }, { "invalid map_fd for function call", @@ -650,8 +652,9 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 3 }, - .errstr = "misaligned access", + .errstr = "misaligned value access", .result = REJECT, + .flags = F_LOAD_WITH_STRICT_ALIGNMENT, }, { "sometimes access memory with incorrect alignment", @@ -672,6 +675,7 @@ static struct bpf_test tests[] = { .errstr = "R0 invalid mem access", .errstr_unpriv = "R0 leaks addr", .result = REJECT, + .flags = F_LOAD_WITH_STRICT_ALIGNMENT, }, { "jump test 1", @@ -963,6 +967,256 @@ static struct bpf_test tests[] = { .result = REJECT, }, { + "invalid access __sk_buff family", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, family)), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + }, + { + "invalid access __sk_buff remote_ip4", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, remote_ip4)), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + }, + { + "invalid access __sk_buff local_ip4", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, local_ip4)), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + }, + { + "invalid access __sk_buff remote_ip6", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, remote_ip6)), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + }, + { + "invalid access __sk_buff local_ip6", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, local_ip6)), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + }, + { + "invalid access __sk_buff remote_port", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, remote_port)), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + }, + { + "invalid access __sk_buff remote_port", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, local_port)), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + }, + { + "valid access __sk_buff family", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, family)), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_SKB, + }, + { + "valid access __sk_buff remote_ip4", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, remote_ip4)), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_SKB, + }, + { + "valid access __sk_buff local_ip4", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, local_ip4)), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_SKB, + }, + { + "valid access __sk_buff remote_ip6", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, remote_ip6[0])), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, remote_ip6[1])), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, remote_ip6[2])), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, remote_ip6[3])), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_SKB, + }, + { + "valid access __sk_buff local_ip6", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, local_ip6[0])), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, local_ip6[1])), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, local_ip6[2])), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, local_ip6[3])), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_SKB, + }, + { + "valid access __sk_buff remote_port", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, remote_port)), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_SKB, + }, + { + "valid access __sk_buff remote_port", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, local_port)), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_SKB, + }, + { + "invalid access of tc_classid for SK_SKB", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, tc_classid)), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_SKB, + .errstr = "invalid bpf_context access", + }, + { + "check skb->mark is writeable by SK_SKB", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, mark)), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_SKB, + }, + { + "check skb->tc_index is writeable by SK_SKB", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, tc_index)), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_SKB, + }, + { + "check skb->priority is writeable by SK_SKB", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, priority)), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_SKB, + }, + { + "direct packet read for SK_SKB", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_SKB, + }, + { + "direct packet write for SK_SKB", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + BPF_STX_MEM(BPF_B, BPF_REG_2, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_SKB, + }, + { + "overlapping checks for direct packet access SK_SKB", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_2, 6), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_SKB, + }, + { "check skb->mark is not writeable by sockets", .insns = { BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_1, @@ -1073,44 +1327,75 @@ static struct bpf_test tests[] = { .result = ACCEPT, }, { - "check cb access: byte, oob 1", + "__sk_buff->hash, offset 0, byte store not permitted", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, - offsetof(struct __sk_buff, cb[4]) + 4), + offsetof(struct __sk_buff, hash)), BPF_EXIT_INSN(), }, .errstr = "invalid bpf_context access", .result = REJECT, }, { - "check cb access: byte, oob 2", + "__sk_buff->tc_index, offset 3, byte store not permitted", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, - offsetof(struct __sk_buff, cb[0]) - 1), + offsetof(struct __sk_buff, tc_index) + 3), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + }, + { + "check skb->hash byte load permitted", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), +#if __BYTE_ORDER == __LITTLE_ENDIAN + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, hash)), +#else + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, hash) + 3), +#endif + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + }, + { + "check skb->hash byte load not permitted 1", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, hash) + 1), BPF_EXIT_INSN(), }, .errstr = "invalid bpf_context access", .result = REJECT, }, { - "check cb access: byte, oob 3", + "check skb->hash byte load not permitted 2", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, - offsetof(struct __sk_buff, cb[4]) + 4), + offsetof(struct __sk_buff, hash) + 2), BPF_EXIT_INSN(), }, .errstr = "invalid bpf_context access", .result = REJECT, }, { - "check cb access: byte, oob 4", + "check skb->hash byte load not permitted 3", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), +#if __BYTE_ORDER == __LITTLE_ENDIAN BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, - offsetof(struct __sk_buff, cb[0]) - 1), + offsetof(struct __sk_buff, hash) + 3), +#else + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, hash)), +#endif BPF_EXIT_INSN(), }, .errstr = "invalid bpf_context access", @@ -1184,48 +1469,58 @@ static struct bpf_test tests[] = { offsetof(struct __sk_buff, cb[0]) + 1), BPF_EXIT_INSN(), }, - .errstr = "misaligned access", + .errstr = "misaligned context access", .result = REJECT, + .flags = F_LOAD_WITH_STRICT_ALIGNMENT, }, { - "check cb access: half, oob 1", + "check __sk_buff->hash, offset 0, half store not permitted", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_STX_MEM(BPF_H, BPF_REG_1, BPF_REG_0, - offsetof(struct __sk_buff, cb[4]) + 4), + offsetof(struct __sk_buff, hash)), BPF_EXIT_INSN(), }, .errstr = "invalid bpf_context access", .result = REJECT, }, { - "check cb access: half, oob 2", + "check __sk_buff->tc_index, offset 2, half store not permitted", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_STX_MEM(BPF_H, BPF_REG_1, BPF_REG_0, - offsetof(struct __sk_buff, cb[0]) - 2), + offsetof(struct __sk_buff, tc_index) + 2), BPF_EXIT_INSN(), }, .errstr = "invalid bpf_context access", .result = REJECT, }, { - "check cb access: half, oob 3", + "check skb->hash half load permitted", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), +#if __BYTE_ORDER == __LITTLE_ENDIAN BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, - offsetof(struct __sk_buff, cb[4]) + 4), + offsetof(struct __sk_buff, hash)), +#else + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, hash) + 2), +#endif BPF_EXIT_INSN(), }, - .errstr = "invalid bpf_context access", - .result = REJECT, + .result = ACCEPT, }, { - "check cb access: half, oob 4", + "check skb->hash half load not permitted", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), +#if __BYTE_ORDER == __LITTLE_ENDIAN + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, hash) + 2), +#else BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, - offsetof(struct __sk_buff, cb[0]) - 2), + offsetof(struct __sk_buff, hash)), +#endif BPF_EXIT_INSN(), }, .errstr = "invalid bpf_context access", @@ -1279,8 +1574,9 @@ static struct bpf_test tests[] = { offsetof(struct __sk_buff, cb[0]) + 2), BPF_EXIT_INSN(), }, - .errstr = "misaligned access", + .errstr = "misaligned context access", .result = REJECT, + .flags = F_LOAD_WITH_STRICT_ALIGNMENT, }, { "check cb access: word, unaligned 2", @@ -1290,8 +1586,9 @@ static struct bpf_test tests[] = { offsetof(struct __sk_buff, cb[4]) + 1), BPF_EXIT_INSN(), }, - .errstr = "misaligned access", + .errstr = "misaligned context access", .result = REJECT, + .flags = F_LOAD_WITH_STRICT_ALIGNMENT, }, { "check cb access: word, unaligned 3", @@ -1301,8 +1598,9 @@ static struct bpf_test tests[] = { offsetof(struct __sk_buff, cb[4]) + 2), BPF_EXIT_INSN(), }, - .errstr = "misaligned access", + .errstr = "misaligned context access", .result = REJECT, + .flags = F_LOAD_WITH_STRICT_ALIGNMENT, }, { "check cb access: word, unaligned 4", @@ -1312,8 +1610,9 @@ static struct bpf_test tests[] = { offsetof(struct __sk_buff, cb[4]) + 3), BPF_EXIT_INSN(), }, - .errstr = "misaligned access", + .errstr = "misaligned context access", .result = REJECT, + .flags = F_LOAD_WITH_STRICT_ALIGNMENT, }, { "check cb access: double", @@ -1339,8 +1638,9 @@ static struct bpf_test tests[] = { offsetof(struct __sk_buff, cb[1])), BPF_EXIT_INSN(), }, - .errstr = "misaligned access", + .errstr = "misaligned context access", .result = REJECT, + .flags = F_LOAD_WITH_STRICT_ALIGNMENT, }, { "check cb access: double, unaligned 2", @@ -1350,8 +1650,9 @@ static struct bpf_test tests[] = { offsetof(struct __sk_buff, cb[3])), BPF_EXIT_INSN(), }, - .errstr = "misaligned access", + .errstr = "misaligned context access", .result = REJECT, + .flags = F_LOAD_WITH_STRICT_ALIGNMENT, }, { "check cb access: double, oob 1", @@ -1368,28 +1669,6 @@ static struct bpf_test tests[] = { "check cb access: double, oob 2", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, - offsetof(struct __sk_buff, cb[4]) + 8), - BPF_EXIT_INSN(), - }, - .errstr = "invalid bpf_context access", - .result = REJECT, - }, - { - "check cb access: double, oob 3", - .insns = { - BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, - offsetof(struct __sk_buff, cb[0]) - 8), - BPF_EXIT_INSN(), - }, - .errstr = "invalid bpf_context access", - .result = REJECT, - }, - { - "check cb access: double, oob 4", - .insns = { - BPF_MOV64_IMM(BPF_REG_0, 0), BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, offsetof(struct __sk_buff, cb[4])), BPF_EXIT_INSN(), @@ -1398,22 +1677,22 @@ static struct bpf_test tests[] = { .result = REJECT, }, { - "check cb access: double, oob 5", + "check __sk_buff->ifindex dw store not permitted", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, - offsetof(struct __sk_buff, cb[4]) + 8), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, ifindex)), BPF_EXIT_INSN(), }, .errstr = "invalid bpf_context access", .result = REJECT, }, { - "check cb access: double, oob 6", + "check __sk_buff->ifindex dw load not permitted", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, - offsetof(struct __sk_buff, cb[0]) - 8), + offsetof(struct __sk_buff, ifindex)), BPF_EXIT_INSN(), }, .errstr = "invalid bpf_context access", @@ -1505,7 +1784,8 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .result = REJECT, - .errstr = "misaligned access off -6 size 8", + .errstr = "misaligned stack access off (0x0; 0x0)+-8+2 size 8", + .flags = F_LOAD_WITH_STRICT_ALIGNMENT, }, { "PTR_TO_STACK store/load - bad alignment on reg", @@ -1517,7 +1797,8 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .result = REJECT, - .errstr = "misaligned access off -2 size 8", + .errstr = "misaligned stack access off (0x0; 0x0)+-10+8 size 8", + .flags = F_LOAD_WITH_STRICT_ALIGNMENT, }, { "PTR_TO_STACK store/load - out of bounds low", @@ -1561,8 +1842,6 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .result = ACCEPT, - .result_unpriv = REJECT, - .errstr_unpriv = "R1 pointer arithmetic", }, { "unpriv: add pointer to pointer", @@ -1573,7 +1852,7 @@ static struct bpf_test tests[] = { }, .result = ACCEPT, .result_unpriv = REJECT, - .errstr_unpriv = "R1 pointer arithmetic", + .errstr_unpriv = "R1 pointer += pointer", }, { "unpriv: neg pointer", @@ -1914,10 +2193,7 @@ static struct bpf_test tests[] = { BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, -8), BPF_EXIT_INSN(), }, - .errstr_unpriv = "pointer arithmetic prohibited", - .result_unpriv = REJECT, - .errstr = "R1 invalid mem access", - .result = REJECT, + .result = ACCEPT, }, { "unpriv: cmp of stack pointer", @@ -1981,7 +2257,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .result = REJECT, - .errstr = "invalid stack type R3", + .errstr = "R4 min value is negative", .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, { @@ -1998,7 +2274,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .result = REJECT, - .errstr = "invalid stack type R3", + .errstr = "R4 min value is negative", .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, { @@ -2200,7 +2476,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .result = REJECT, - .errstr = "invalid stack type R3 off=-1 access_size=-1", + .errstr = "R4 min value is negative", .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, { @@ -2217,7 +2493,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .result = REJECT, - .errstr = "invalid stack type R3 off=-1 access_size=2147483647", + .errstr = "R4 unbounded memory access, use 'var &= const' or 'if (var < const)'", .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, { @@ -2234,7 +2510,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .result = REJECT, - .errstr = "invalid stack type R3 off=-512 access_size=2147483647", + .errstr = "R4 unbounded memory access, use 'var &= const' or 'if (var < const)'", .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, { @@ -2305,8 +2581,8 @@ static struct bpf_test tests[] = { offsetof(struct __sk_buff, data)), BPF_ALU64_REG(BPF_ADD, BPF_REG_3, BPF_REG_4), BPF_MOV64_REG(BPF_REG_2, BPF_REG_1), - BPF_ALU64_IMM(BPF_LSH, BPF_REG_2, 48), - BPF_ALU64_IMM(BPF_RSH, BPF_REG_2, 48), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_2, 49), + BPF_ALU64_IMM(BPF_RSH, BPF_REG_2, 49), BPF_ALU64_REG(BPF_ADD, BPF_REG_3, BPF_REG_2), BPF_MOV64_REG(BPF_REG_2, BPF_REG_3), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 8), @@ -2634,12 +2910,250 @@ static struct bpf_test tests[] = { BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1), BPF_JMP_A(-6), }, - .errstr = "misaligned packet access off 2+15+-4 size 4", + .errstr = "misaligned packet access off 2+(0x0; 0x0)+15+-4 size 4", .result = REJECT, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .flags = F_LOAD_WITH_STRICT_ALIGNMENT, }, { + "direct packet access: test18 (imm += pkt_ptr, 1)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_IMM(BPF_REG_0, 8), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_2), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + BPF_STX_MEM(BPF_B, BPF_REG_2, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "direct packet access: test19 (imm += pkt_ptr, 2)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 3), + BPF_MOV64_IMM(BPF_REG_4, 4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_4, BPF_REG_2), + BPF_STX_MEM(BPF_B, BPF_REG_4, BPF_REG_4, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "direct packet access: test20 (x += pkt_ptr, 1)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_IMM(BPF_REG_0, 0xffffffff), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8), + BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 0x7fff), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_0), + BPF_ALU64_REG(BPF_ADD, BPF_REG_4, BPF_REG_2), + BPF_MOV64_REG(BPF_REG_5, BPF_REG_4), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 0x7fff - 1), + BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 1), + BPF_STX_MEM(BPF_DW, BPF_REG_5, BPF_REG_4, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + }, + { + "direct packet access: test21 (x += pkt_ptr, 2)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 9), + BPF_MOV64_IMM(BPF_REG_4, 0xffffffff), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_4, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8), + BPF_ALU64_IMM(BPF_AND, BPF_REG_4, 0x7fff), + BPF_ALU64_REG(BPF_ADD, BPF_REG_4, BPF_REG_2), + BPF_MOV64_REG(BPF_REG_5, BPF_REG_4), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 0x7fff - 1), + BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 1), + BPF_STX_MEM(BPF_DW, BPF_REG_5, BPF_REG_4, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + }, + { + "direct packet access: test22 (x += pkt_ptr, 3)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_3, -16), + BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_10, -16), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 11), + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -8), + BPF_MOV64_IMM(BPF_REG_4, 0xffffffff), + BPF_STX_XADD(BPF_DW, BPF_REG_10, BPF_REG_4, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8), + BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 49), + BPF_ALU64_REG(BPF_ADD, BPF_REG_4, BPF_REG_2), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_4), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 2), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 2), + BPF_MOV64_IMM(BPF_REG_2, 1), + BPF_STX_MEM(BPF_H, BPF_REG_4, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + }, + { + "direct packet access: test23 (x += pkt_ptr, 4)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_IMM(BPF_REG_0, 0xffffffff), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8), + BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 0xffff), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_0, 31), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_2), + BPF_MOV64_REG(BPF_REG_5, BPF_REG_0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 0xffff - 1), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + BPF_STX_MEM(BPF_DW, BPF_REG_5, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "invalid access to packet, off=0 size=8, R5(id=1,off=0,r=0)", + }, + { + "direct packet access: test24 (x += pkt_ptr, 5)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_IMM(BPF_REG_0, 0xffffffff), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8), + BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 0xff), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_0, 64), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_2), + BPF_MOV64_REG(BPF_REG_5, BPF_REG_0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 0x7fff - 1), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + BPF_STX_MEM(BPF_DW, BPF_REG_5, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + }, + { + "direct packet access: test25 (marking on <, good access)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JLT, BPF_REG_0, BPF_REG_3, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0), + BPF_JMP_IMM(BPF_JA, 0, 0, -4), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "direct packet access: test26 (marking on <, bad access)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JLT, BPF_REG_0, BPF_REG_3, 3), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JA, 0, 0, -3), + }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "direct packet access: test27 (marking on <=, good access)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_0, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "direct packet access: test28 (marking on <=, bad access)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_0, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0), + BPF_JMP_IMM(BPF_JA, 0, 0, -4), + }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { "helper access to packet: test1, valid packet_ptr range", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, @@ -2929,7 +3443,7 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, { - "helper access to packet: test14, cls helper fail sub", + "helper access to packet: test14, cls helper ok sub", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, offsetof(struct __sk_buff, data)), @@ -2949,12 +3463,36 @@ static struct bpf_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "helper access to packet: test15, cls helper fail sub", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_7, 6), + BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 12), + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_MOV64_IMM(BPF_REG_5, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_csum_diff), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, .result = REJECT, - .errstr = "type=inv expected=fp", + .errstr = "invalid access to packet", .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, { - "helper access to packet: test15, cls helper fail range 1", + "helper access to packet: test16, cls helper fail range 1", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, offsetof(struct __sk_buff, data)), @@ -2979,7 +3517,7 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, { - "helper access to packet: test16, cls helper fail range 2", + "helper access to packet: test17, cls helper fail range 2", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, offsetof(struct __sk_buff, data)), @@ -3000,11 +3538,11 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .result = REJECT, - .errstr = "invalid access to packet", + .errstr = "R2 min value is negative", .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, { - "helper access to packet: test17, cls helper fail range 3", + "helper access to packet: test18, cls helper fail range 3", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, offsetof(struct __sk_buff, data)), @@ -3025,11 +3563,11 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .result = REJECT, - .errstr = "invalid access to packet", + .errstr = "R2 min value is negative", .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, { - "helper access to packet: test18, cls helper fail range zero", + "helper access to packet: test19, cls helper fail range zero", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, offsetof(struct __sk_buff, data)), @@ -3054,7 +3592,7 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, { - "helper access to packet: test19, pkt end as input", + "helper access to packet: test20, pkt end as input", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, offsetof(struct __sk_buff, data)), @@ -3079,7 +3617,7 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, { - "helper access to packet: test20, wrong reg", + "helper access to packet: test21, wrong reg", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, offsetof(struct __sk_buff, data)), @@ -3139,7 +3677,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr_unpriv = "R0 leaks addr", .result_unpriv = REJECT, .result = ACCEPT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, @@ -3163,7 +3701,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr_unpriv = "R0 leaks addr", .result_unpriv = REJECT, .result = ACCEPT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, @@ -3191,7 +3729,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr_unpriv = "R0 leaks addr", .result_unpriv = REJECT, .result = ACCEPT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, @@ -3232,9 +3770,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", .errstr = "R0 min value is outside of the array range", - .result_unpriv = REJECT, .result = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, @@ -3256,9 +3792,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", - .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.", - .result_unpriv = REJECT, + .errstr = "R0 unbounded memory access, make sure to bounds check any array access into a map", .result = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, @@ -3272,7 +3806,7 @@ static struct bpf_test tests[] = { BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), - BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0), BPF_MOV32_IMM(BPF_REG_2, MAX_ENTRIES), BPF_JMP_REG(BPF_JSGT, BPF_REG_2, BPF_REG_1, 1), BPF_MOV32_IMM(BPF_REG_1, 0), @@ -3283,8 +3817,8 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", - .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.", + .errstr_unpriv = "R0 leaks addr", + .errstr = "R0 unbounded memory access", .result_unpriv = REJECT, .result = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, @@ -3310,7 +3844,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr_unpriv = "R0 leaks addr", .errstr = "invalid access to map value, value_size=48 off=44 size=8", .result_unpriv = REJECT, .result = REJECT, @@ -3340,8 +3874,8 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3, 11 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", - .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.", + .errstr_unpriv = "R0 pointer += pointer", + .errstr = "R0 invalid mem access 'inv'", .result_unpriv = REJECT, .result = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, @@ -3483,34 +4017,6 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_SCHED_CLS }, { - "multiple registers share map_lookup_elem bad reg type", - .insns = { - BPF_MOV64_IMM(BPF_REG_1, 10), - BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8), - BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), - BPF_LD_MAP_FD(BPF_REG_1, 0), - BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, - BPF_FUNC_map_lookup_elem), - BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), - BPF_MOV64_REG(BPF_REG_3, BPF_REG_0), - BPF_MOV64_REG(BPF_REG_4, BPF_REG_0), - BPF_MOV64_REG(BPF_REG_5, BPF_REG_0), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), - BPF_MOV64_IMM(BPF_REG_1, 1), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), - BPF_MOV64_IMM(BPF_REG_1, 2), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_3, 0, 1), - BPF_ST_MEM(BPF_DW, BPF_REG_3, 0, 0), - BPF_MOV64_IMM(BPF_REG_1, 3), - BPF_EXIT_INSN(), - }, - .fixup_map1 = { 4 }, - .result = REJECT, - .errstr = "R3 invalid mem access 'inv'", - .prog_type = BPF_PROG_TYPE_SCHED_CLS - }, - { "invalid map access from else condition", .insns = { BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), @@ -3528,9 +4034,9 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr = "R0 unbounded memory access, make sure to bounds check any array access into a map", + .errstr = "R0 unbounded memory access", .result = REJECT, - .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr_unpriv = "R0 leaks addr", .result_unpriv = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, @@ -3908,7 +4414,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr = "invalid access to map value, value_size=48 off=0 size=-8", + .errstr = "R2 min value is negative", .result = REJECT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, @@ -3974,7 +4480,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr = "R1 min value is outside of the array range", + .errstr = "invalid access to map value, value_size=48 off=4 size=0", .result = REJECT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, @@ -4020,7 +4526,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr = "invalid access to map value, value_size=48 off=4 size=-8", + .errstr = "R2 min value is negative", .result = REJECT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, @@ -4042,7 +4548,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr = "R1 min value is outside of the array range", + .errstr = "R2 min value is negative", .result = REJECT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, @@ -4158,7 +4664,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr = "invalid access to map value, value_size=48 off=4 size=-8", + .errstr = "R2 min value is negative", .result = REJECT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, @@ -4181,7 +4687,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr = "R1 min value is outside of the array range", + .errstr = "R2 min value is negative", .result = REJECT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, @@ -4269,13 +4775,13 @@ static struct bpf_test tests[] = { BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3), - BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_2, 1), BPF_MOV64_IMM(BPF_REG_3, 0), BPF_EMIT_CALL(BPF_FUNC_probe_read), BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr = "R1 min value is negative, either use unsigned index or do a if (index >=0) check", + .errstr = "R1 unbounded memory access", .result = REJECT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, @@ -4306,6 +4812,246 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, { + "helper access to map: bounds check using <, good access", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JLT, BPF_REG_3, 32, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3), + BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to map: bounds check using <, bad access", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JLT, BPF_REG_3, 32, 4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3), + BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .result = REJECT, + .errstr = "R1 unbounded memory access", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to map: bounds check using <=, good access", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JLE, BPF_REG_3, 32, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3), + BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to map: bounds check using <=, bad access", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JLE, BPF_REG_3, 32, 4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3), + BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .result = REJECT, + .errstr = "R1 unbounded memory access", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to map: bounds check using s<, good access", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JSLT, BPF_REG_3, 32, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JSLT, BPF_REG_3, 0, -3), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3), + BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to map: bounds check using s<, good access 2", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JSLT, BPF_REG_3, 32, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JSLT, BPF_REG_3, -3, -3), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3), + BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to map: bounds check using s<, bad access", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JSLT, BPF_REG_3, 32, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JSLT, BPF_REG_3, -3, -3), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3), + BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .result = REJECT, + .errstr = "R1 min value is negative", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to map: bounds check using s<=, good access", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JSLE, BPF_REG_3, 32, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JSLE, BPF_REG_3, 0, -3), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3), + BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to map: bounds check using s<=, good access 2", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JSLE, BPF_REG_3, 32, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JSLE, BPF_REG_3, -3, -3), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3), + BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to map: bounds check using s<=, bad access", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JSLE, BPF_REG_3, 32, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JSLE, BPF_REG_3, -3, -3), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3), + BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .result = REJECT, + .errstr = "R1 min value is negative", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { "map element value is preserved across register spilling", .insns = { BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), @@ -4395,7 +5141,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr_unpriv = "R0 leaks addr", .result = ACCEPT, .result_unpriv = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, @@ -4423,7 +5169,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr_unpriv = "R0 leaks addr", .result = ACCEPT, .result_unpriv = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, @@ -4442,7 +5188,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr_unpriv = "R0 bitwise operator &= on pointer", .errstr = "invalid mem access 'inv'", .result = REJECT, .result_unpriv = REJECT, @@ -4461,7 +5207,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr_unpriv = "R0 32-bit pointer arithmetic prohibited", .errstr = "invalid mem access 'inv'", .result = REJECT, .result_unpriv = REJECT, @@ -4480,7 +5226,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr_unpriv = "R0 pointer arithmetic with /= operator", .errstr = "invalid mem access 'inv'", .result = REJECT, .result_unpriv = REJECT, @@ -4523,10 +5269,8 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr_unpriv = "R0 invalid mem access 'inv'", .errstr = "R0 invalid mem access 'inv'", .result = REJECT, - .result_unpriv = REJECT, }, { "map element value is preserved across register spilling", @@ -4548,7 +5292,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr_unpriv = "R0 leaks addr", .result = ACCEPT, .result_unpriv = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, @@ -4730,7 +5474,8 @@ static struct bpf_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr = "R2 unbounded memory access", + /* because max wasn't checked, signed min is negative */ + .errstr = "R2 min value is negative, either use unsigned or 'var &= const'", .result = REJECT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, @@ -4786,7 +5531,7 @@ static struct bpf_test tests[] = { BPF_JMP_IMM(BPF_JSGT, BPF_REG_2, sizeof(struct test_val), 4), BPF_MOV64_IMM(BPF_REG_4, 0), - BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2), + BPF_JMP_REG(BPF_JSGE, BPF_REG_4, BPF_REG_2, 2), BPF_MOV64_IMM(BPF_REG_3, 0), BPF_EMIT_CALL(BPF_FUNC_probe_read), BPF_MOV64_IMM(BPF_REG_0, 0), @@ -4812,7 +5557,7 @@ static struct bpf_test tests[] = { BPF_JMP_IMM(BPF_JSGT, BPF_REG_2, sizeof(struct test_val) + 1, 4), BPF_MOV64_IMM(BPF_REG_4, 0), - BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2), + BPF_JMP_REG(BPF_JSGE, BPF_REG_4, BPF_REG_2, 2), BPF_MOV64_IMM(BPF_REG_3, 0), BPF_EMIT_CALL(BPF_FUNC_probe_read), BPF_MOV64_IMM(BPF_REG_0, 0), @@ -4840,7 +5585,7 @@ static struct bpf_test tests[] = { BPF_JMP_IMM(BPF_JSGT, BPF_REG_2, sizeof(struct test_val) - 20, 4), BPF_MOV64_IMM(BPF_REG_4, 0), - BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2), + BPF_JMP_REG(BPF_JSGE, BPF_REG_4, BPF_REG_2, 2), BPF_MOV64_IMM(BPF_REG_3, 0), BPF_EMIT_CALL(BPF_FUNC_probe_read), BPF_MOV64_IMM(BPF_REG_0, 0), @@ -4867,7 +5612,7 @@ static struct bpf_test tests[] = { BPF_JMP_IMM(BPF_JSGT, BPF_REG_2, sizeof(struct test_val) - 19, 4), BPF_MOV64_IMM(BPF_REG_4, 0), - BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2), + BPF_JMP_REG(BPF_JSGE, BPF_REG_4, BPF_REG_2, 2), BPF_MOV64_IMM(BPF_REG_3, 0), BPF_EMIT_CALL(BPF_FUNC_probe_read), BPF_MOV64_IMM(BPF_REG_0, 0), @@ -4879,6 +5624,20 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, { + "helper access to variable memory: size = 0 allowed on NULL", + .insns = { + BPF_MOV64_IMM(BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_MOV64_IMM(BPF_REG_5, 0), + BPF_EMIT_CALL(BPF_FUNC_csum_diff), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { "helper access to variable memory: size > 0 not allowed on NULL", .insns = { BPF_MOV64_IMM(BPF_REG_1, 0), @@ -4892,7 +5651,7 @@ static struct bpf_test tests[] = { BPF_EMIT_CALL(BPF_FUNC_csum_diff), BPF_EXIT_INSN(), }, - .errstr = "R1 type=imm expected=fp", + .errstr = "R1 type=inv expected=fp", .result = REJECT, .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, @@ -4977,7 +5736,7 @@ static struct bpf_test tests[] = { BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), - BPF_MOV64_IMM(BPF_REG_1, 6), + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), BPF_ALU64_IMM(BPF_AND, BPF_REG_1, -4), BPF_ALU64_IMM(BPF_LSH, BPF_REG_1, 2), BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), @@ -4986,10 +5745,8 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", - .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.", + .errstr = "R0 max value is outside of the array range", .result = REJECT, - .result_unpriv = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { @@ -5018,10 +5775,8 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", - .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.", + .errstr = "R0 max value is outside of the array range", .result = REJECT, - .result_unpriv = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { @@ -5068,7 +5823,7 @@ static struct bpf_test tests[] = { }, .fixup_map_in_map = { 3 }, .errstr = "R1 type=inv expected=map_ptr", - .errstr_unpriv = "R1 pointer arithmetic prohibited", + .errstr_unpriv = "R1 pointer arithmetic on CONST_PTR_TO_MAP prohibited", .result = REJECT, }, { @@ -5235,6 +5990,645 @@ static struct bpf_test tests[] = { }, .result = ACCEPT, }, + { + "check bpf_perf_event_data->sample_period byte load permitted", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), +#if __BYTE_ORDER == __LITTLE_ENDIAN + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_perf_event_data, sample_period)), +#else + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_perf_event_data, sample_period) + 7), +#endif + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_PERF_EVENT, + }, + { + "check bpf_perf_event_data->sample_period half load permitted", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), +#if __BYTE_ORDER == __LITTLE_ENDIAN + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_perf_event_data, sample_period)), +#else + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_perf_event_data, sample_period) + 6), +#endif + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_PERF_EVENT, + }, + { + "check bpf_perf_event_data->sample_period word load permitted", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), +#if __BYTE_ORDER == __LITTLE_ENDIAN + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_perf_event_data, sample_period)), +#else + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_perf_event_data, sample_period) + 4), +#endif + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_PERF_EVENT, + }, + { + "check bpf_perf_event_data->sample_period dword load permitted", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, + offsetof(struct bpf_perf_event_data, sample_period)), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_PERF_EVENT, + }, + { + "check skb->data half load not permitted", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), +#if __BYTE_ORDER == __LITTLE_ENDIAN + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, data)), +#else + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, data) + 2), +#endif + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid bpf_context access", + }, + { + "check skb->tc_classid half load not permitted for lwt prog", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), +#if __BYTE_ORDER == __LITTLE_ENDIAN + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, tc_classid)), +#else + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, tc_classid) + 2), +#endif + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid bpf_context access", + .prog_type = BPF_PROG_TYPE_LWT_IN, + }, + { + "bounds checks mixing signed and unsigned, positive bounds", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, 2), + BPF_JMP_REG(BPF_JGE, BPF_REG_2, BPF_REG_1, 3), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 4, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr = "R0 min value is negative", + .result = REJECT, + }, + { + "bounds checks mixing signed and unsigned", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, -1), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 3), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr = "R0 min value is negative", + .result = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 2", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, -1), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 5), + BPF_MOV64_IMM(BPF_REG_8, 0), + BPF_ALU64_REG(BPF_ADD, BPF_REG_8, BPF_REG_1), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_8, 1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_8), + BPF_ST_MEM(BPF_B, BPF_REG_8, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr = "R8 invalid mem access 'inv'", + .result = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 3", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, -1), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 4), + BPF_MOV64_REG(BPF_REG_8, BPF_REG_1), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_8, 1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_8), + BPF_ST_MEM(BPF_B, BPF_REG_8, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr = "R8 invalid mem access 'inv'", + .result = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 4", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, 1), + BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .result = ACCEPT, + }, + { + "bounds checks mixing signed and unsigned, variant 5", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, -1), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 5), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 4), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 4), + BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr = "R0 min value is negative", + .result = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 6", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -512), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_6, -1), + BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_6, 5), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_4, 1, 4), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 1), + BPF_MOV64_IMM(BPF_REG_5, 0), + BPF_ST_MEM(BPF_H, BPF_REG_10, -512, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_load_bytes), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R4 min value is negative, either use unsigned", + .result = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 7", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, 1024 * 1024 * 1024), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 3), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .result = ACCEPT, + }, + { + "bounds checks mixing signed and unsigned, variant 8", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, -1), + BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_1, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr = "R0 min value is negative", + .result = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 9", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 10), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_LD_IMM64(BPF_REG_2, -9223372036854775808ULL), + BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_1, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .result = ACCEPT, + }, + { + "bounds checks mixing signed and unsigned, variant 10", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_1, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr = "R0 min value is negative", + .result = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 11", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, -1), + BPF_JMP_REG(BPF_JGE, BPF_REG_2, BPF_REG_1, 2), + /* Dead branch. */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr = "R0 min value is negative", + .result = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 12", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, -6), + BPF_JMP_REG(BPF_JGE, BPF_REG_2, BPF_REG_1, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr = "R0 min value is negative", + .result = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 13", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, 2), + BPF_JMP_REG(BPF_JGE, BPF_REG_2, BPF_REG_1, 2), + BPF_MOV64_IMM(BPF_REG_7, 1), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_7, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_1), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_7, 4, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_7), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr = "R0 min value is negative", + .result = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 14", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_1, + offsetof(struct __sk_buff, mark)), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, -1), + BPF_MOV64_IMM(BPF_REG_8, 2), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_9, 42, 6), + BPF_JMP_REG(BPF_JSGT, BPF_REG_8, BPF_REG_1, 3), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, -3), + BPF_JMP_IMM(BPF_JA, 0, 0, -7), + }, + .fixup_map1 = { 4 }, + .errstr = "R0 min value is negative", + .result = REJECT, + }, + { + "bounds checks mixing signed and unsigned, variant 15", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_MOV64_IMM(BPF_REG_2, -6), + BPF_JMP_REG(BPF_JGE, BPF_REG_2, BPF_REG_1, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_JMP_IMM(BPF_JGT, BPF_REG_0, 1, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr_unpriv = "R0 pointer comparison prohibited", + .errstr = "R0 min value is negative", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "subtraction bounds (map value) variant 1", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JGT, BPF_REG_1, 0xff, 7), + BPF_LDX_MEM(BPF_B, BPF_REG_3, BPF_REG_0, 1), + BPF_JMP_IMM(BPF_JGT, BPF_REG_3, 0xff, 5), + BPF_ALU64_REG(BPF_SUB, BPF_REG_1, BPF_REG_3), + BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 56), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr = "R0 max value is outside of the array range", + .result = REJECT, + }, + { + "subtraction bounds (map value) variant 2", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8), + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JGT, BPF_REG_1, 0xff, 6), + BPF_LDX_MEM(BPF_B, BPF_REG_3, BPF_REG_0, 1), + BPF_JMP_IMM(BPF_JGT, BPF_REG_3, 0xff, 4), + BPF_ALU64_REG(BPF_SUB, BPF_REG_1, BPF_REG_3), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.", + .result = REJECT, + }, + { + "variable-offset ctx access", + .insns = { + /* Get an unknown value */ + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0), + /* Make it small and 4-byte aligned */ + BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 4), + /* add it to skb. We now have either &skb->len or + * &skb->pkt_type, but we don't know which + */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_2), + /* dereference it */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0), + BPF_EXIT_INSN(), + }, + .errstr = "variable ctx access var_off=(0x0; 0x4)", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_LWT_IN, + }, + { + "variable-offset stack access", + .insns = { + /* Fill the top 8 bytes of the stack */ + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + /* Get an unknown value */ + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0), + /* Make it small and 4-byte aligned */ + BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 4), + BPF_ALU64_IMM(BPF_SUB, BPF_REG_2, 8), + /* add it to fp. We now have either fp-4 or fp-8, but + * we don't know which + */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_10), + /* dereference it */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0), + BPF_EXIT_INSN(), + }, + .errstr = "variable stack access var_off=(0xfffffffffffffff8; 0x4)", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_LWT_IN, + }, + { + "liveness pruning and write screening", + .insns = { + /* Get an unknown value */ + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0), + /* branch conditions teach us nothing about R2 */ + BPF_JMP_IMM(BPF_JGE, BPF_REG_2, 0, 1), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JGE, BPF_REG_2, 0, 1), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R0 !read_ok", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_LWT_IN, + }, + { + "varlen_map_value_access pruning", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0), + BPF_MOV32_IMM(BPF_REG_2, MAX_ENTRIES), + BPF_JMP_REG(BPF_JSGT, BPF_REG_2, BPF_REG_1, 1), + BPF_MOV32_IMM(BPF_REG_1, 0), + BPF_ALU32_IMM(BPF_LSH, BPF_REG_1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_JMP_IMM(BPF_JA, 0, 0, 0), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, + offsetof(struct test_val, foo)), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr_unpriv = "R0 leaks addr", + .errstr = "R0 unbounded memory access", + .result_unpriv = REJECT, + .result = REJECT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, + }, }; static int probe_filter_length(const struct bpf_insn *fp) @@ -5358,7 +6752,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv, fd_prog = bpf_verify_program(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER, prog, prog_len, test->flags & F_LOAD_WITH_STRICT_ALIGNMENT, - "GPL", 0, bpf_vlog, sizeof(bpf_vlog)); + "GPL", 0, bpf_vlog, sizeof(bpf_vlog), 1); expected_ret = unpriv && test->result_unpriv != UNDEF ? test->result_unpriv : test->result; @@ -5484,7 +6878,7 @@ static int do_test(bool unpriv, unsigned int from, unsigned int to) } printf("Summary: %d PASSED, %d FAILED\n", passes, errors); - return errors ? -errors : 0; + return errors ? EXIT_FAILURE : EXIT_SUCCESS; } int main(int argc, char **argv) diff --git a/tools/testing/selftests/bpf/test_xdp_redirect.c b/tools/testing/selftests/bpf/test_xdp_redirect.c new file mode 100644 index 000000000000..ef9e704be140 --- /dev/null +++ b/tools/testing/selftests/bpf/test_xdp_redirect.c @@ -0,0 +1,28 @@ +/* Copyright (c) 2017 VMware + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ +#include <linux/bpf.h> +#include "bpf_helpers.h" + +int _version SEC("version") = 1; + +SEC("redirect_to_111") +int xdp_redirect_to_111(struct xdp_md *xdp) +{ + return bpf_redirect(111, 0); +} +SEC("redirect_to_222") +int xdp_redirect_to_222(struct xdp_md *xdp) +{ + return bpf_redirect(222, 0); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_xdp_redirect.sh b/tools/testing/selftests/bpf/test_xdp_redirect.sh new file mode 100755 index 000000000000..344a3656dea6 --- /dev/null +++ b/tools/testing/selftests/bpf/test_xdp_redirect.sh @@ -0,0 +1,59 @@ +#!/bin/sh +# Create 2 namespaces with two veth peers, and +# forward packets in-between using generic XDP +# +# NS1(veth11) NS2(veth22) +# | | +# | | +# (veth1, ------ (veth2, +# id:111) id:222) +# | xdp forwarding | +# ------------------ + +cleanup() +{ + if [ "$?" = "0" ]; then + echo "selftests: test_xdp_redirect [PASS]"; + else + echo "selftests: test_xdp_redirect [FAILED]"; + fi + + set +e + ip netns del ns1 2> /dev/null + ip netns del ns2 2> /dev/null +} + +ip link set dev lo xdpgeneric off 2>/dev/null > /dev/null +if [ $? -ne 0 ];then + echo "selftests: [SKIP] Could not run test without the ip xdpgeneric support" + exit 0 +fi +set -e + +ip netns add ns1 +ip netns add ns2 + +trap cleanup 0 2 3 6 9 + +ip link add veth1 index 111 type veth peer name veth11 +ip link add veth2 index 222 type veth peer name veth22 + +ip link set veth11 netns ns1 +ip link set veth22 netns ns2 + +ip link set veth1 up +ip link set veth2 up + +ip netns exec ns1 ip addr add 10.1.1.11/24 dev veth11 +ip netns exec ns2 ip addr add 10.1.1.22/24 dev veth22 + +ip netns exec ns1 ip link set dev veth11 up +ip netns exec ns2 ip link set dev veth22 up + +ip link set dev veth1 xdpgeneric obj test_xdp_redirect.o sec redirect_to_222 +ip link set dev veth2 xdpgeneric obj test_xdp_redirect.o sec redirect_to_111 + +ip netns exec ns1 ping -c 1 10.1.1.22 +ip netns exec ns2 ping -c 1 10.1.1.11 + +exit 0 diff --git a/tools/testing/selftests/breakpoints/breakpoint_test.c b/tools/testing/selftests/breakpoints/breakpoint_test.c index 120895ab5505..901b85ea6a59 100644 --- a/tools/testing/selftests/breakpoints/breakpoint_test.c +++ b/tools/testing/selftests/breakpoints/breakpoint_test.c @@ -16,6 +16,8 @@ #include <signal.h> #include <sys/types.h> #include <sys/wait.h> +#include <errno.h> +#include <string.h> #include "../kselftest.h" @@ -42,10 +44,9 @@ static void set_breakpoint_addr(void *addr, int n) ret = ptrace(PTRACE_POKEUSER, child_pid, offsetof(struct user, u_debugreg[n]), addr); - if (ret) { - perror("Can't set breakpoint addr\n"); - ksft_exit_fail(); - } + if (ret) + ksft_exit_fail_msg("Can't set breakpoint addr: %s\n", + strerror(errno)); } static void toggle_breakpoint(int n, int type, int len, @@ -106,8 +107,8 @@ static void toggle_breakpoint(int n, int type, int len, ret = ptrace(PTRACE_POKEUSER, child_pid, offsetof(struct user, u_debugreg[7]), dr7); if (ret) { - perror("Can't set dr7"); - ksft_exit_fail(); + ksft_print_msg("Can't set dr7: %s\n", strerror(errno)); + exit(-1); } } @@ -206,7 +207,7 @@ static void trigger_tests(void) ret = ptrace(PTRACE_TRACEME, 0, NULL, 0); if (ret) { - perror("Can't be traced?\n"); + ksft_print_msg("Can't be traced? %s\n", strerror(errno)); return; } @@ -261,29 +262,30 @@ static void trigger_tests(void) static void check_success(const char *msg) { - const char *msg2; int child_nr_tests; int status; + int ret; /* Wait for the child to SIGTRAP */ wait(&status); - msg2 = "Failed"; + ret = 0; if (WSTOPSIG(status) == SIGTRAP) { child_nr_tests = ptrace(PTRACE_PEEKDATA, child_pid, &nr_tests, 0); if (child_nr_tests == nr_tests) - msg2 = "Ok"; - if (ptrace(PTRACE_POKEDATA, child_pid, &trapped, 1)) { - perror("Can't poke\n"); - ksft_exit_fail(); - } + ret = 1; + if (ptrace(PTRACE_POKEDATA, child_pid, &trapped, 1)) + ksft_exit_fail_msg("Can't poke: %s\n", strerror(errno)); } nr_tests++; - printf("%s [%s]\n", msg, msg2); + if (ret) + ksft_test_result_pass(msg); + else + ksft_test_result_fail(msg); } static void launch_instruction_breakpoints(char *buf, int local, int global) @@ -294,7 +296,7 @@ static void launch_instruction_breakpoints(char *buf, int local, int global) set_breakpoint_addr(dummy_funcs[i], i); toggle_breakpoint(i, BP_X, 1, local, global, 1); ptrace(PTRACE_CONT, child_pid, NULL, 0); - sprintf(buf, "Test breakpoint %d with local: %d global: %d", + sprintf(buf, "Test breakpoint %d with local: %d global: %d\n", i, local, global); check_success(buf); toggle_breakpoint(i, BP_X, 1, local, global, 0); @@ -316,8 +318,9 @@ static void launch_watchpoints(char *buf, int mode, int len, set_breakpoint_addr(&dummy_var[i], i); toggle_breakpoint(i, mode, len, local, global, 1); ptrace(PTRACE_CONT, child_pid, NULL, 0); - sprintf(buf, "Test %s watchpoint %d with len: %d local: " - "%d global: %d", mode_str, i, len, local, global); + sprintf(buf, + "Test %s watchpoint %d with len: %d local: %d global: %d\n", + mode_str, i, len, local, global); check_success(buf); toggle_breakpoint(i, mode, len, local, global, 0); } @@ -364,11 +367,11 @@ static void launch_tests(void) /* Icebp traps */ ptrace(PTRACE_CONT, child_pid, NULL, 0); - check_success("Test icebp"); + check_success("Test icebp\n"); /* Int 3 traps */ ptrace(PTRACE_CONT, child_pid, NULL, 0); - check_success("Test int 3 trap"); + check_success("Test int 3 trap\n"); ptrace(PTRACE_CONT, child_pid, NULL, 0); } @@ -378,10 +381,12 @@ int main(int argc, char **argv) pid_t pid; int ret; + ksft_print_header(); + pid = fork(); if (!pid) { trigger_tests(); - return 0; + exit(0); } child_pid = pid; @@ -392,5 +397,5 @@ int main(int argc, char **argv) wait(NULL); - return ksft_exit_pass(); + ksft_exit_pass(); } diff --git a/tools/testing/selftests/breakpoints/breakpoint_test_arm64.c b/tools/testing/selftests/breakpoints/breakpoint_test_arm64.c index 3897e996541e..960d02100c26 100644 --- a/tools/testing/selftests/breakpoints/breakpoint_test_arm64.c +++ b/tools/testing/selftests/breakpoints/breakpoint_test_arm64.c @@ -43,19 +43,25 @@ static void child(int size, int wr) volatile uint8_t *addr = &var[32 + wr]; if (ptrace(PTRACE_TRACEME, 0, NULL, NULL) != 0) { - perror("ptrace(PTRACE_TRACEME) failed"); + ksft_print_msg( + "ptrace(PTRACE_TRACEME) failed: %s\n", + strerror(errno)); _exit(1); } if (raise(SIGSTOP) != 0) { - perror("raise(SIGSTOP) failed"); + ksft_print_msg( + "raise(SIGSTOP) failed: %s\n", strerror(errno)); _exit(1); } if ((uintptr_t) addr % size) { - perror("Wrong address write for the given size\n"); + ksft_print_msg( + "Wrong address write for the given size: %s\n", + strerror(errno)); _exit(1); } + switch (size) { case 1: *addr = 47; @@ -100,12 +106,14 @@ static bool set_watchpoint(pid_t pid, int size, int wp) if (ptrace(PTRACE_SETREGSET, pid, NT_ARM_HW_WATCH, &iov) == 0) return true; - if (errno == EIO) { - printf("ptrace(PTRACE_SETREGSET, NT_ARM_HW_WATCH) " - "not supported on this hardware\n"); - ksft_exit_skip(); - } - perror("ptrace(PTRACE_SETREGSET, NT_ARM_HW_WATCH) failed"); + if (errno == EIO) + ksft_print_msg( + "ptrace(PTRACE_SETREGSET, NT_ARM_HW_WATCH) not supported on this hardware: %s\n", + strerror(errno)); + + ksft_print_msg( + "ptrace(PTRACE_SETREGSET, NT_ARM_HW_WATCH) failed: %s\n", + strerror(errno)); return false; } @@ -117,7 +125,8 @@ static bool run_test(int wr_size, int wp_size, int wr, int wp) pid_t wpid; if (pid < 0) { - perror("fork() failed"); + ksft_test_result_fail( + "fork() failed: %s\n", strerror(errno)); return false; } if (pid == 0) @@ -125,15 +134,17 @@ static bool run_test(int wr_size, int wp_size, int wr, int wp) wpid = waitpid(pid, &status, __WALL); if (wpid != pid) { - perror("waitpid() failed"); + ksft_print_msg( + "waitpid() failed: %s\n", strerror(errno)); return false; } if (!WIFSTOPPED(status)) { - printf("child did not stop\n"); + ksft_print_msg( + "child did not stop: %s\n", strerror(errno)); return false; } if (WSTOPSIG(status) != SIGSTOP) { - printf("child did not stop with SIGSTOP\n"); + ksft_print_msg("child did not stop with SIGSTOP\n"); return false; } @@ -141,42 +152,49 @@ static bool run_test(int wr_size, int wp_size, int wr, int wp) return false; if (ptrace(PTRACE_CONT, pid, NULL, NULL) < 0) { - perror("ptrace(PTRACE_SINGLESTEP) failed"); + ksft_print_msg( + "ptrace(PTRACE_SINGLESTEP) failed: %s\n", + strerror(errno)); return false; } alarm(3); wpid = waitpid(pid, &status, __WALL); if (wpid != pid) { - perror("waitpid() failed"); + ksft_print_msg( + "waitpid() failed: %s\n", strerror(errno)); return false; } alarm(0); if (WIFEXITED(status)) { - printf("child did not single-step\t"); + ksft_print_msg("child did not single-step\n"); return false; } if (!WIFSTOPPED(status)) { - printf("child did not stop\n"); + ksft_print_msg("child did not stop\n"); return false; } if (WSTOPSIG(status) != SIGTRAP) { - printf("child did not stop with SIGTRAP\n"); + ksft_print_msg("child did not stop with SIGTRAP\n"); return false; } if (ptrace(PTRACE_GETSIGINFO, pid, NULL, &siginfo) != 0) { - perror("ptrace(PTRACE_GETSIGINFO)"); + ksft_print_msg( + "ptrace(PTRACE_GETSIGINFO): %s\n", + strerror(errno)); return false; } if (siginfo.si_code != TRAP_HWBKPT) { - printf("Unexpected si_code %d\n", siginfo.si_code); + ksft_print_msg( + "Unexpected si_code %d\n", siginfo.si_code); return false; } kill(pid, SIGKILL); wpid = waitpid(pid, &status, 0); if (wpid != pid) { - perror("waitpid() failed"); + ksft_print_msg( + "waitpid() failed: %s\n", strerror(errno)); return false; } return true; @@ -194,6 +212,8 @@ int main(int argc, char **argv) int wr, wp, size; bool result; + ksft_print_header(); + act.sa_handler = sigalrm; sigemptyset(&act.sa_mask); act.sa_flags = 0; @@ -201,14 +221,16 @@ int main(int argc, char **argv) for (size = 1; size <= 32; size = size*2) { for (wr = 0; wr <= 32; wr = wr + size) { for (wp = wr - size; wp <= wr + size; wp = wp + size) { - printf("Test size = %d write offset = %d watchpoint offset = %d\t", size, wr, wp); result = run_test(size, MIN(size, 8), wr, wp); - if ((result && wr == wp) || (!result && wr != wp)) { - printf("[OK]\n"); - ksft_inc_pass_cnt(); - } else { - printf("[FAILED]\n"); - ksft_inc_fail_cnt(); + if ((result && wr == wp) || + (!result && wr != wp)) + ksft_test_result_pass( + "Test size = %d write offset = %d watchpoint offset = %d\n", + size, wr, wp); + else { + ksft_test_result_fail( + "Test size = %d write offset = %d watchpoint offset = %d\n", + size, wr, wp); succeeded = false; } } @@ -216,19 +238,18 @@ int main(int argc, char **argv) } for (size = 1; size <= 32; size = size*2) { - printf("Test size = %d write offset = %d watchpoint offset = -8\t", size, -size); - - if (run_test(size, 8, -size, -8)) { - printf("[OK]\n"); - ksft_inc_pass_cnt(); - } else { - printf("[FAILED]\n"); - ksft_inc_fail_cnt(); + if (run_test(size, 8, -size, -8)) + ksft_test_result_pass( + "Test size = %d write offset = %d watchpoint offset = -8\n", + size, -size); + else { + ksft_test_result_fail( + "Test size = %d write offset = %d watchpoint offset = -8\n", + size, -size); succeeded = false; } } - ksft_print_cnts(); if (succeeded) ksft_exit_pass(); else diff --git a/tools/testing/selftests/breakpoints/step_after_suspend_test.c b/tools/testing/selftests/breakpoints/step_after_suspend_test.c index 60b8a95dac26..3fece06e9f64 100644 --- a/tools/testing/selftests/breakpoints/step_after_suspend_test.c +++ b/tools/testing/selftests/breakpoints/step_after_suspend_test.c @@ -37,17 +37,19 @@ void child(int cpu) CPU_ZERO(&set); CPU_SET(cpu, &set); if (sched_setaffinity(0, sizeof(set), &set) != 0) { - perror("sched_setaffinity() failed"); + ksft_print_msg("sched_setaffinity() failed: %s\n", + strerror(errno)); _exit(1); } if (ptrace(PTRACE_TRACEME, 0, NULL, NULL) != 0) { - perror("ptrace(PTRACE_TRACEME) failed"); + ksft_print_msg("ptrace(PTRACE_TRACEME) failed: %s\n", + strerror(errno)); _exit(1); } if (raise(SIGSTOP) != 0) { - perror("raise(SIGSTOP) failed"); + ksft_print_msg("raise(SIGSTOP) failed: %s\n", strerror(errno)); _exit(1); } @@ -61,7 +63,7 @@ bool run_test(int cpu) pid_t wpid; if (pid < 0) { - perror("fork() failed"); + ksft_print_msg("fork() failed: %s\n", strerror(errno)); return false; } if (pid == 0) @@ -69,57 +71,64 @@ bool run_test(int cpu) wpid = waitpid(pid, &status, __WALL); if (wpid != pid) { - perror("waitpid() failed"); + ksft_print_msg("waitpid() failed: %s\n", strerror(errno)); return false; } if (!WIFSTOPPED(status)) { - printf("child did not stop\n"); + ksft_print_msg("child did not stop: %s\n", strerror(errno)); return false; } if (WSTOPSIG(status) != SIGSTOP) { - printf("child did not stop with SIGSTOP\n"); + ksft_print_msg("child did not stop with SIGSTOP: %s\n", + strerror(errno)); return false; } if (ptrace(PTRACE_SINGLESTEP, pid, NULL, NULL) < 0) { if (errno == EIO) { - printf("ptrace(PTRACE_SINGLESTEP) not supported on this architecture\n"); - ksft_exit_skip(); + ksft_exit_skip( + "ptrace(PTRACE_SINGLESTEP) not supported on this architecture: %s\n", + strerror(errno)); } - perror("ptrace(PTRACE_SINGLESTEP) failed"); + ksft_print_msg("ptrace(PTRACE_SINGLESTEP) failed: %s\n", + strerror(errno)); return false; } wpid = waitpid(pid, &status, __WALL); if (wpid != pid) { - perror("waitpid() failed"); + ksft_print_msg("waitpid() failed: $s\n", strerror(errno)); return false; } if (WIFEXITED(status)) { - printf("child did not single-step\n"); + ksft_print_msg("child did not single-step: %s\n", + strerror(errno)); return false; } if (!WIFSTOPPED(status)) { - printf("child did not stop\n"); + ksft_print_msg("child did not stop: %s\n", strerror(errno)); return false; } if (WSTOPSIG(status) != SIGTRAP) { - printf("child did not stop with SIGTRAP\n"); + ksft_print_msg("child did not stop with SIGTRAP: %s\n", + strerror(errno)); return false; } if (ptrace(PTRACE_CONT, pid, NULL, NULL) < 0) { - perror("ptrace(PTRACE_CONT) failed"); + ksft_print_msg("ptrace(PTRACE_CONT) failed: %s\n", + strerror(errno)); return false; } wpid = waitpid(pid, &status, __WALL); if (wpid != pid) { - perror("waitpid() failed"); + ksft_print_msg("waitpid() failed: %s\n", strerror(errno)); return false; } if (!WIFEXITED(status)) { - printf("child did not exit after PTRACE_CONT\n"); + ksft_print_msg("child did not exit after PTRACE_CONT: %s\n", + strerror(errno)); return false; } @@ -135,28 +144,21 @@ void suspend(void) struct itimerspec spec = {}; power_state_fd = open("/sys/power/state", O_RDWR); - if (power_state_fd < 0) { - perror("open(\"/sys/power/state\") failed (is this test running as root?)"); - ksft_exit_fail(); - } + if (power_state_fd < 0) + ksft_exit_fail_msg( + "open(\"/sys/power/state\") failed (is this test running as root?)\n"); timerfd = timerfd_create(CLOCK_BOOTTIME_ALARM, 0); - if (timerfd < 0) { - perror("timerfd_create() failed"); - ksft_exit_fail(); - } + if (timerfd < 0) + ksft_exit_fail_msg("timerfd_create() failed\n"); spec.it_value.tv_sec = 5; err = timerfd_settime(timerfd, 0, &spec, NULL); - if (err < 0) { - perror("timerfd_settime() failed"); - ksft_exit_fail(); - } + if (err < 0) + ksft_exit_fail_msg("timerfd_settime() failed\n"); - if (write(power_state_fd, "mem", strlen("mem")) != strlen("mem")) { - perror("entering suspend failed"); - ksft_exit_fail(); - } + if (write(power_state_fd, "mem", strlen("mem")) != strlen("mem")) + ksft_exit_fail_msg("Failed to enter Suspend state\n"); close(timerfd); close(power_state_fd); @@ -171,6 +173,8 @@ int main(int argc, char **argv) int err; int cpu; + ksft_print_header(); + while ((opt = getopt(argc, argv, "n")) != -1) { switch (opt) { case 'n': @@ -187,10 +191,8 @@ int main(int argc, char **argv) suspend(); err = sched_getaffinity(0, sizeof(available_cpus), &available_cpus); - if (err < 0) { - perror("sched_getaffinity() failed"); - ksft_exit_fail(); - } + if (err < 0) + ksft_exit_fail_msg("sched_getaffinity() failed\n"); for (cpu = 0; cpu < CPU_SETSIZE; cpu++) { bool test_success; @@ -199,18 +201,14 @@ int main(int argc, char **argv) continue; test_success = run_test(cpu); - printf("CPU %d: ", cpu); if (test_success) { - printf("[OK]\n"); - ksft_inc_pass_cnt(); + ksft_test_result_pass("CPU %d\n", cpu); } else { - printf("[FAILED]\n"); - ksft_inc_fail_cnt(); + ksft_test_result_fail("CPU %d\n", cpu); succeeded = false; } } - ksft_print_cnts(); if (succeeded) ksft_exit_pass(); else diff --git a/tools/testing/selftests/capabilities/test_execve.c b/tools/testing/selftests/capabilities/test_execve.c index 10a21a958aaf..cf6778441381 100644 --- a/tools/testing/selftests/capabilities/test_execve.c +++ b/tools/testing/selftests/capabilities/test_execve.c @@ -1,7 +1,6 @@ #define _GNU_SOURCE #include <cap-ng.h> -#include <err.h> #include <linux/capability.h> #include <stdbool.h> #include <string.h> @@ -18,6 +17,8 @@ #include <sys/prctl.h> #include <sys/stat.h> +#include "../kselftest.h" + #ifndef PR_CAP_AMBIENT #define PR_CAP_AMBIENT 47 # define PR_CAP_AMBIENT_IS_SET 1 @@ -27,6 +28,7 @@ #endif static int nerrs; +static pid_t mpid; /* main() pid is used to avoid duplicate test counts */ static void vmaybe_write_file(bool enoent_ok, char *filename, char *fmt, va_list ap) { @@ -36,29 +38,32 @@ static void vmaybe_write_file(bool enoent_ok, char *filename, char *fmt, va_list int buf_len; buf_len = vsnprintf(buf, sizeof(buf), fmt, ap); - if (buf_len < 0) { - err(1, "vsnprintf failed"); - } - if (buf_len >= sizeof(buf)) { - errx(1, "vsnprintf output truncated"); - } + if (buf_len < 0) + ksft_exit_fail_msg("vsnprintf failed - %s\n", strerror(errno)); + + if (buf_len >= sizeof(buf)) + ksft_exit_fail_msg("vsnprintf output truncated\n"); + fd = open(filename, O_WRONLY); if (fd < 0) { if ((errno == ENOENT) && enoent_ok) return; - err(1, "open of %s failed", filename); + ksft_exit_fail_msg("open of %s failed - %s\n", + filename, strerror(errno)); } written = write(fd, buf, buf_len); if (written != buf_len) { if (written >= 0) { - errx(1, "short write to %s", filename); + ksft_exit_fail_msg("short write to %s\n", filename); } else { - err(1, "write to %s failed", filename); + ksft_exit_fail_msg("write to %s failed - %s\n", + filename, strerror(errno)); } } if (close(fd) != 0) { - err(1, "close of %s failed", filename); + ksft_exit_fail_msg("close of %s failed - %s\n", + filename, strerror(errno)); } } @@ -95,11 +100,12 @@ static bool create_and_enter_ns(uid_t inner_uid) */ if (unshare(CLONE_NEWNS) == 0) { - printf("[NOTE]\tUsing global UIDs for tests\n"); + ksft_print_msg("[NOTE]\tUsing global UIDs for tests\n"); if (prctl(PR_SET_KEEPCAPS, 1, 0, 0, 0) != 0) - err(1, "PR_SET_KEEPCAPS"); + ksft_exit_fail_msg("PR_SET_KEEPCAPS - %s\n", + strerror(errno)); if (setresuid(inner_uid, inner_uid, -1) != 0) - err(1, "setresuid"); + ksft_exit_fail_msg("setresuid - %s\n", strerror(errno)); // Re-enable effective caps capng_get_caps_process(); @@ -107,22 +113,24 @@ static bool create_and_enter_ns(uid_t inner_uid) if (capng_have_capability(CAPNG_PERMITTED, i)) capng_update(CAPNG_ADD, CAPNG_EFFECTIVE, i); if (capng_apply(CAPNG_SELECT_CAPS) != 0) - err(1, "capng_apply"); + ksft_exit_fail_msg( + "capng_apply - %s\n", strerror(errno)); have_outer_privilege = true; } else if (unshare(CLONE_NEWUSER | CLONE_NEWNS) == 0) { - printf("[NOTE]\tUsing a user namespace for tests\n"); + ksft_print_msg("[NOTE]\tUsing a user namespace for tests\n"); maybe_write_file("/proc/self/setgroups", "deny"); write_file("/proc/self/uid_map", "%d %d 1", inner_uid, outer_uid); write_file("/proc/self/gid_map", "0 %d 1", outer_gid); have_outer_privilege = false; } else { - errx(1, "must be root or be able to create a userns"); + ksft_exit_skip("must be root or be able to create a userns\n"); } if (mount("none", "/", NULL, MS_REC | MS_PRIVATE, NULL) != 0) - err(1, "remount everything private"); + ksft_exit_fail_msg("remount everything private - %s\n", + strerror(errno)); return have_outer_privilege; } @@ -131,23 +139,22 @@ static void chdir_to_tmpfs(void) { char cwd[PATH_MAX]; if (getcwd(cwd, sizeof(cwd)) != cwd) - err(1, "getcwd"); + ksft_exit_fail_msg("getcwd - %s\n", strerror(errno)); if (mount("private_tmp", ".", "tmpfs", 0, "mode=0777") != 0) - err(1, "mount private tmpfs"); + ksft_exit_fail_msg("mount private tmpfs - %s\n", + strerror(errno)); if (chdir(cwd) != 0) - err(1, "chdir to private tmpfs"); - - if (umount2(".", MNT_DETACH) != 0) - err(1, "detach private tmpfs"); + ksft_exit_fail_msg("chdir to private tmpfs - %s\n", + strerror(errno)); } static void copy_fromat_to(int fromfd, const char *fromname, const char *toname) { int from = openat(fromfd, fromname, O_RDONLY); if (from == -1) - err(1, "open copy source"); + ksft_exit_fail_msg("open copy source - %s\n", strerror(errno)); int to = open(toname, O_CREAT | O_WRONLY | O_EXCL, 0700); @@ -157,10 +164,11 @@ static void copy_fromat_to(int fromfd, const char *fromname, const char *toname) if (sz == 0) break; if (sz < 0) - err(1, "read"); + ksft_exit_fail_msg("read - %s\n", strerror(errno)); if (write(to, buf, sz) != sz) - err(1, "write"); /* no short writes on tmpfs */ + /* no short writes on tmpfs */ + ksft_exit_fail_msg("write - %s\n", strerror(errno)); } close(from); @@ -177,18 +185,20 @@ static bool fork_wait(void) int status; if (waitpid(child, &status, 0) != child || !WIFEXITED(status)) { - printf("[FAIL]\tChild died\n"); + ksft_print_msg("Child died\n"); nerrs++; } else if (WEXITSTATUS(status) != 0) { - printf("[FAIL]\tChild failed\n"); + ksft_print_msg("Child failed\n"); nerrs++; } else { - printf("[OK]\tChild succeeded\n"); + /* don't print this message for mpid */ + if (getpid() != mpid) + ksft_test_result_pass("Passed\n"); } - return false; } else { - err(1, "fork"); + ksft_exit_fail_msg("fork - %s\n", strerror(errno)); + return false; } } @@ -198,7 +208,7 @@ static void exec_other_validate_cap(const char *name, execl(name, name, (eff ? "1" : "0"), (perm ? "1" : "0"), (inh ? "1" : "0"), (ambient ? "1" : "0"), NULL); - err(1, "execl"); + ksft_exit_fail_msg("execl - %s\n", strerror(errno)); } static void exec_validate_cap(bool eff, bool perm, bool inh, bool ambient) @@ -212,7 +222,8 @@ static int do_tests(int uid, const char *our_path) int ourpath_fd = open(our_path, O_RDONLY | O_DIRECTORY); if (ourpath_fd == -1) - err(1, "open '%s'", our_path); + ksft_exit_fail_msg("open '%s' - %s\n", + our_path, strerror(errno)); chdir_to_tmpfs(); @@ -224,178 +235,193 @@ static int do_tests(int uid, const char *our_path) copy_fromat_to(ourpath_fd, "validate_cap", "validate_cap_suidroot"); if (chown("validate_cap_suidroot", 0, -1) != 0) - err(1, "chown"); + ksft_exit_fail_msg("chown - %s\n", strerror(errno)); if (chmod("validate_cap_suidroot", S_ISUID | 0700) != 0) - err(1, "chmod"); + ksft_exit_fail_msg("chmod - %s\n", strerror(errno)); copy_fromat_to(ourpath_fd, "validate_cap", "validate_cap_suidnonroot"); if (chown("validate_cap_suidnonroot", uid + 1, -1) != 0) - err(1, "chown"); + ksft_exit_fail_msg("chown - %s\n", strerror(errno)); if (chmod("validate_cap_suidnonroot", S_ISUID | 0700) != 0) - err(1, "chmod"); + ksft_exit_fail_msg("chmod - %s\n", strerror(errno)); copy_fromat_to(ourpath_fd, "validate_cap", "validate_cap_sgidroot"); if (chown("validate_cap_sgidroot", -1, 0) != 0) - err(1, "chown"); + ksft_exit_fail_msg("chown - %s\n", strerror(errno)); if (chmod("validate_cap_sgidroot", S_ISGID | 0710) != 0) - err(1, "chmod"); + ksft_exit_fail_msg("chmod - %s\n", strerror(errno)); copy_fromat_to(ourpath_fd, "validate_cap", "validate_cap_sgidnonroot"); if (chown("validate_cap_sgidnonroot", -1, gid + 1) != 0) - err(1, "chown"); + ksft_exit_fail_msg("chown - %s\n", strerror(errno)); if (chmod("validate_cap_sgidnonroot", S_ISGID | 0710) != 0) - err(1, "chmod"); -} + ksft_exit_fail_msg("chmod - %s\n", strerror(errno)); + } capng_get_caps_process(); /* Make sure that i starts out clear */ capng_update(CAPNG_DROP, CAPNG_INHERITABLE, CAP_NET_BIND_SERVICE); if (capng_apply(CAPNG_SELECT_CAPS) != 0) - err(1, "capng_apply"); + ksft_exit_fail_msg("capng_apply - %s\n", strerror(errno)); if (uid == 0) { - printf("[RUN]\tRoot => ep\n"); + ksft_print_msg("[RUN]\tRoot => ep\n"); if (fork_wait()) exec_validate_cap(true, true, false, false); } else { - printf("[RUN]\tNon-root => no caps\n"); + ksft_print_msg("[RUN]\tNon-root => no caps\n"); if (fork_wait()) exec_validate_cap(false, false, false, false); } - printf("[OK]\tCheck cap_ambient manipulation rules\n"); + ksft_print_msg("Check cap_ambient manipulation rules\n"); /* We should not be able to add ambient caps yet. */ if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_RAISE, CAP_NET_BIND_SERVICE, 0, 0, 0) != -1 || errno != EPERM) { if (errno == EINVAL) - printf("[FAIL]\tPR_CAP_AMBIENT_RAISE isn't supported\n"); + ksft_test_result_fail( + "PR_CAP_AMBIENT_RAISE isn't supported\n"); else - printf("[FAIL]\tPR_CAP_AMBIENT_RAISE should have failed eith EPERM on a non-inheritable cap\n"); + ksft_test_result_fail( + "PR_CAP_AMBIENT_RAISE should have failed eith EPERM on a non-inheritable cap\n"); return 1; } - printf("[OK]\tPR_CAP_AMBIENT_RAISE failed on non-inheritable cap\n"); + ksft_test_result_pass( + "PR_CAP_AMBIENT_RAISE failed on non-inheritable cap\n"); capng_update(CAPNG_ADD, CAPNG_INHERITABLE, CAP_NET_RAW); capng_update(CAPNG_DROP, CAPNG_PERMITTED, CAP_NET_RAW); capng_update(CAPNG_DROP, CAPNG_EFFECTIVE, CAP_NET_RAW); if (capng_apply(CAPNG_SELECT_CAPS) != 0) - err(1, "capng_apply"); + ksft_exit_fail_msg("capng_apply - %s\n", strerror(errno)); if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_RAISE, CAP_NET_RAW, 0, 0, 0) != -1 || errno != EPERM) { - printf("[FAIL]\tPR_CAP_AMBIENT_RAISE should have failed on a non-permitted cap\n"); + ksft_test_result_fail( + "PR_CAP_AMBIENT_RAISE should have failed on a non-permitted cap\n"); return 1; } - printf("[OK]\tPR_CAP_AMBIENT_RAISE failed on non-permitted cap\n"); + ksft_test_result_pass( + "PR_CAP_AMBIENT_RAISE failed on non-permitted cap\n"); capng_update(CAPNG_ADD, CAPNG_INHERITABLE, CAP_NET_BIND_SERVICE); if (capng_apply(CAPNG_SELECT_CAPS) != 0) - err(1, "capng_apply"); + ksft_exit_fail_msg("capng_apply - %s\n", strerror(errno)); if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_RAISE, CAP_NET_BIND_SERVICE, 0, 0, 0) != 0) { - printf("[FAIL]\tPR_CAP_AMBIENT_RAISE should have succeeded\n"); + ksft_test_result_fail( + "PR_CAP_AMBIENT_RAISE should have succeeded\n"); return 1; } - printf("[OK]\tPR_CAP_AMBIENT_RAISE worked\n"); + ksft_test_result_pass("PR_CAP_AMBIENT_RAISE worked\n"); if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_IS_SET, CAP_NET_BIND_SERVICE, 0, 0, 0) != 1) { - printf("[FAIL]\tPR_CAP_AMBIENT_IS_SET is broken\n"); + ksft_test_result_fail("PR_CAP_AMBIENT_IS_SET is broken\n"); return 1; } if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_CLEAR_ALL, 0, 0, 0, 0) != 0) - err(1, "PR_CAP_AMBIENT_CLEAR_ALL"); + ksft_exit_fail_msg("PR_CAP_AMBIENT_CLEAR_ALL - %s\n", + strerror(errno)); if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_IS_SET, CAP_NET_BIND_SERVICE, 0, 0, 0) != 0) { - printf("[FAIL]\tPR_CAP_AMBIENT_CLEAR_ALL didn't work\n"); + ksft_test_result_fail( + "PR_CAP_AMBIENT_CLEAR_ALL didn't work\n"); return 1; } if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_RAISE, CAP_NET_BIND_SERVICE, 0, 0, 0) != 0) - err(1, "PR_CAP_AMBIENT_RAISE"); + ksft_exit_fail_msg("PR_CAP_AMBIENT_RAISE - %s\n", + strerror(errno)); capng_update(CAPNG_DROP, CAPNG_INHERITABLE, CAP_NET_BIND_SERVICE); if (capng_apply(CAPNG_SELECT_CAPS) != 0) - err(1, "capng_apply"); + ksft_exit_fail_msg("capng_apply - %s\n", strerror(errno)); if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_IS_SET, CAP_NET_BIND_SERVICE, 0, 0, 0) != 0) { - printf("[FAIL]\tDropping I should have dropped A\n"); + ksft_test_result_fail("Dropping I should have dropped A\n"); return 1; } - printf("[OK]\tBasic manipulation appears to work\n"); + ksft_test_result_pass("Basic manipulation appears to work\n"); capng_update(CAPNG_ADD, CAPNG_INHERITABLE, CAP_NET_BIND_SERVICE); if (capng_apply(CAPNG_SELECT_CAPS) != 0) - err(1, "capng_apply"); + ksft_exit_fail_msg("capng_apply - %s\n", strerror(errno)); if (uid == 0) { - printf("[RUN]\tRoot +i => eip\n"); + ksft_print_msg("[RUN]\tRoot +i => eip\n"); if (fork_wait()) exec_validate_cap(true, true, true, false); } else { - printf("[RUN]\tNon-root +i => i\n"); + ksft_print_msg("[RUN]\tNon-root +i => i\n"); if (fork_wait()) exec_validate_cap(false, false, true, false); } if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_RAISE, CAP_NET_BIND_SERVICE, 0, 0, 0) != 0) - err(1, "PR_CAP_AMBIENT_RAISE"); + ksft_exit_fail_msg("PR_CAP_AMBIENT_RAISE - %s\n", + strerror(errno)); - printf("[RUN]\tUID %d +ia => eipa\n", uid); + ksft_print_msg("[RUN]\tUID %d +ia => eipa\n", uid); if (fork_wait()) exec_validate_cap(true, true, true, true); /* The remaining tests need real privilege */ if (!have_outer_privilege) { - printf("[SKIP]\tSUID/SGID tests (needs privilege)\n"); + ksft_test_result_skip("SUID/SGID tests (needs privilege)\n"); goto done; } if (uid == 0) { - printf("[RUN]\tRoot +ia, suidroot => eipa\n"); + ksft_print_msg("[RUN]\tRoot +ia, suidroot => eipa\n"); if (fork_wait()) exec_other_validate_cap("./validate_cap_suidroot", true, true, true, true); - printf("[RUN]\tRoot +ia, suidnonroot => ip\n"); + ksft_print_msg("[RUN]\tRoot +ia, suidnonroot => ip\n"); if (fork_wait()) exec_other_validate_cap("./validate_cap_suidnonroot", false, true, true, false); - printf("[RUN]\tRoot +ia, sgidroot => eipa\n"); + ksft_print_msg("[RUN]\tRoot +ia, sgidroot => eipa\n"); if (fork_wait()) exec_other_validate_cap("./validate_cap_sgidroot", true, true, true, true); if (fork_wait()) { - printf("[RUN]\tRoot, gid != 0, +ia, sgidroot => eip\n"); + ksft_print_msg( + "[RUN]\tRoot, gid != 0, +ia, sgidroot => eip\n"); if (setresgid(1, 1, 1) != 0) - err(1, "setresgid"); + ksft_exit_fail_msg("setresgid - %s\n", + strerror(errno)); exec_other_validate_cap("./validate_cap_sgidroot", true, true, true, false); } - printf("[RUN]\tRoot +ia, sgidnonroot => eip\n"); + ksft_print_msg("[RUN]\tRoot +ia, sgidnonroot => eip\n"); if (fork_wait()) exec_other_validate_cap("./validate_cap_sgidnonroot", true, true, true, false); } else { - printf("[RUN]\tNon-root +ia, sgidnonroot => i\n"); - exec_other_validate_cap("./validate_cap_sgidnonroot", - false, false, true, false); + ksft_print_msg("[RUN]\tNon-root +ia, sgidnonroot => i\n"); + if (fork_wait()) + exec_other_validate_cap("./validate_cap_sgidnonroot", + false, false, true, false); if (fork_wait()) { - printf("[RUN]\tNon-root +ia, sgidroot => i\n"); + ksft_print_msg("[RUN]\tNon-root +ia, sgidroot => i\n"); if (setresgid(1, 1, 1) != 0) - err(1, "setresgid"); + ksft_exit_fail_msg("setresgid - %s\n", + strerror(errno)); exec_other_validate_cap("./validate_cap_sgidroot", false, false, true, false); } } done: + ksft_print_cnts(); return nerrs ? 1 : 0; } @@ -403,23 +429,29 @@ int main(int argc, char **argv) { char *tmp1, *tmp2, *our_path; + ksft_print_header(); + /* Find our path */ tmp1 = strdup(argv[0]); if (!tmp1) - err(1, "strdup"); + ksft_exit_fail_msg("strdup - %s\n", strerror(errno)); tmp2 = dirname(tmp1); our_path = strdup(tmp2); if (!our_path) - err(1, "strdup"); + ksft_exit_fail_msg("strdup - %s\n", strerror(errno)); free(tmp1); + mpid = getpid(); + if (fork_wait()) { - printf("[RUN]\t+++ Tests with uid == 0 +++\n"); + ksft_print_msg("[RUN]\t+++ Tests with uid == 0 +++\n"); return do_tests(0, our_path); } + ksft_print_msg("==================================================\n"); + if (fork_wait()) { - printf("[RUN]\t+++ Tests with uid != 0 +++\n"); + ksft_print_msg("[RUN]\t+++ Tests with uid != 0 +++\n"); return do_tests(1, our_path); } diff --git a/tools/testing/selftests/capabilities/validate_cap.c b/tools/testing/selftests/capabilities/validate_cap.c index dd3c45f7b23c..694cd73d4493 100644 --- a/tools/testing/selftests/capabilities/validate_cap.c +++ b/tools/testing/selftests/capabilities/validate_cap.c @@ -1,5 +1,4 @@ #include <cap-ng.h> -#include <err.h> #include <linux/capability.h> #include <stdbool.h> #include <string.h> @@ -7,6 +6,8 @@ #include <sys/prctl.h> #include <sys/auxv.h> +#include "../kselftest.h" + #ifndef PR_CAP_AMBIENT #define PR_CAP_AMBIENT 47 # define PR_CAP_AMBIENT_IS_SET 1 @@ -25,8 +26,10 @@ static bool bool_arg(char **argv, int i) return false; else if (!strcmp(argv[i], "1")) return true; - else - errx(1, "wrong argv[%d]", i); + else { + ksft_exit_fail_msg("wrong argv[%d]\n", i); + return false; + } } int main(int argc, char **argv) @@ -39,7 +42,7 @@ int main(int argc, char **argv) */ if (argc != 5) - errx(1, "wrong argc"); + ksft_exit_fail_msg("wrong argc\n"); #ifdef HAVE_GETAUXVAL if (getauxval(AT_SECURE)) @@ -51,23 +54,26 @@ int main(int argc, char **argv) capng_get_caps_process(); if (capng_have_capability(CAPNG_EFFECTIVE, CAP_NET_BIND_SERVICE) != bool_arg(argv, 1)) { - printf("[FAIL]\tWrong effective state%s\n", atsec); + ksft_print_msg("Wrong effective state%s\n", atsec); return 1; } + if (capng_have_capability(CAPNG_PERMITTED, CAP_NET_BIND_SERVICE) != bool_arg(argv, 2)) { - printf("[FAIL]\tWrong permitted state%s\n", atsec); + ksft_print_msg("Wrong permitted state%s\n", atsec); return 1; } + if (capng_have_capability(CAPNG_INHERITABLE, CAP_NET_BIND_SERVICE) != bool_arg(argv, 3)) { - printf("[FAIL]\tWrong inheritable state%s\n", atsec); + ksft_print_msg("Wrong inheritable state%s\n", atsec); return 1; } if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_IS_SET, CAP_NET_BIND_SERVICE, 0, 0, 0) != bool_arg(argv, 4)) { - printf("[FAIL]\tWrong ambient state%s\n", atsec); + ksft_print_msg("Wrong ambient state%s\n", atsec); return 1; } - printf("[OK]\tCapabilities after execve were correct\n"); + ksft_print_msg("%s: Capabilities after execve were correct\n", + "validate_cap:"); return 0; } diff --git a/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh b/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh index 98b1d6565f2c..b18b253d7bfb 100755 --- a/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh +++ b/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh @@ -28,6 +28,12 @@ prerequisite() echo "CPU online/offline summary:" online_cpus=`cat $SYSFS/devices/system/cpu/online` online_max=${online_cpus##*-} + + if [[ "$online_cpus" = "$online_max" ]]; then + echo "$msg: since there is only one cpu: $online_cpus" + exit 0 + fi + echo -e "\t Cpus in online state: $online_cpus" offline_cpus=`cat $SYSFS/devices/system/cpu/offline` @@ -89,8 +95,10 @@ online_cpu_expect_success() if ! online_cpu $cpu; then echo $FUNCNAME $cpu: unexpected fail >&2 + exit 1 elif ! cpu_is_online $cpu; then echo $FUNCNAME $cpu: unexpected offline >&2 + exit 1 fi } @@ -100,8 +108,10 @@ online_cpu_expect_fail() if online_cpu $cpu 2> /dev/null; then echo $FUNCNAME $cpu: unexpected success >&2 + exit 1 elif ! cpu_is_offline $cpu; then echo $FUNCNAME $cpu: unexpected online >&2 + exit 1 fi } @@ -111,8 +121,10 @@ offline_cpu_expect_success() if ! offline_cpu $cpu; then echo $FUNCNAME $cpu: unexpected fail >&2 + exit 1 elif ! cpu_is_offline $cpu; then echo $FUNCNAME $cpu: unexpected offline >&2 + exit 1 fi } @@ -122,8 +134,10 @@ offline_cpu_expect_fail() if offline_cpu $cpu 2> /dev/null; then echo $FUNCNAME $cpu: unexpected success >&2 + exit 1 elif ! cpu_is_online $cpu; then echo $FUNCNAME $cpu: unexpected offline >&2 + exit 1 fi } diff --git a/tools/testing/selftests/firmware/fw_fallback.sh b/tools/testing/selftests/firmware/fw_fallback.sh index 2e4c22d5abf7..8f511035f783 100755 --- a/tools/testing/selftests/firmware/fw_fallback.sh +++ b/tools/testing/selftests/firmware/fw_fallback.sh @@ -134,6 +134,27 @@ load_fw_custom_cancel() wait } +load_fw_fallback_with_child() +{ + local name="$1" + local file="$2" + + # This is the value already set but we want to be explicit + echo 4 >/sys/class/firmware/timeout + + sleep 1 & + SECONDS_BEFORE=$(date +%s) + echo -n "$name" >"$DIR"/trigger_request 2>/dev/null + SECONDS_AFTER=$(date +%s) + SECONDS_DELTA=$(($SECONDS_AFTER - $SECONDS_BEFORE)) + if [ "$SECONDS_DELTA" -lt 4 ]; then + RET=1 + else + RET=0 + fi + wait + return $RET +} trap "test_finish" EXIT @@ -221,4 +242,14 @@ else echo "$0: cancelling custom fallback mechanism works" fi +set +e +load_fw_fallback_with_child "nope-signal-$NAME" "$FW" +if [ "$?" -eq 0 ]; then + echo "$0: SIGCHLD on sync ignored as expected" >&2 +else + echo "$0: error - sync firmware request cancelled due to SIGCHLD" >&2 + exit 1 +fi +set -e + exit 0 diff --git a/tools/testing/selftests/firmware/fw_filesystem.sh b/tools/testing/selftests/firmware/fw_filesystem.sh index e35691239350..7d8fd2e3695a 100755 --- a/tools/testing/selftests/firmware/fw_filesystem.sh +++ b/tools/testing/selftests/firmware/fw_filesystem.sh @@ -25,8 +25,9 @@ if [ ! -d $DIR ]; then fi # CONFIG_FW_LOADER_USER_HELPER has a sysfs class under /sys/class/firmware/ -# These days no one enables CONFIG_FW_LOADER_USER_HELPER so check for that -# as an indicator for CONFIG_FW_LOADER_USER_HELPER. +# These days most distros enable CONFIG_FW_LOADER_USER_HELPER but disable +# CONFIG_FW_LOADER_USER_HELPER_FALLBACK. We use /sys/class/firmware/ as an +# indicator for CONFIG_FW_LOADER_USER_HELPER. HAS_FW_LOADER_USER_HELPER=$(if [ -d /sys/class/firmware/ ]; then echo yes; else echo no; fi) if [ "$HAS_FW_LOADER_USER_HELPER" = "yes" ]; then @@ -116,4 +117,240 @@ else echo "$0: async filesystem loading works" fi +### Batched requests tests +test_config_present() +{ + if [ ! -f $DIR/reset ]; then + echo "Configuration triggers not present, ignoring test" + exit 0 + fi +} + +# Defaults : +# +# send_uevent: 1 +# sync_direct: 0 +# name: test-firmware.bin +# num_requests: 4 +config_reset() +{ + echo 1 > $DIR/reset +} + +release_all_firmware() +{ + echo 1 > $DIR/release_all_firmware +} + +config_set_name() +{ + echo -n $1 > $DIR/config_name +} + +config_set_sync_direct() +{ + echo 1 > $DIR/config_sync_direct +} + +config_unset_sync_direct() +{ + echo 0 > $DIR/config_sync_direct +} + +config_set_uevent() +{ + echo 1 > $DIR/config_send_uevent +} + +config_unset_uevent() +{ + echo 0 > $DIR/config_send_uevent +} + +config_trigger_sync() +{ + echo -n 1 > $DIR/trigger_batched_requests 2>/dev/null +} + +config_trigger_async() +{ + echo -n 1 > $DIR/trigger_batched_requests_async 2> /dev/null +} + +config_set_read_fw_idx() +{ + echo -n $1 > $DIR/config_read_fw_idx 2> /dev/null +} + +read_firmwares() +{ + for i in $(seq 0 3); do + config_set_read_fw_idx $i + # Verify the contents are what we expect. + # -Z required for now -- check for yourself, md5sum + # on $FW and DIR/read_firmware will yield the same. Even + # cmp agrees, so something is off. + if ! diff -q -Z "$FW" $DIR/read_firmware 2>/dev/null ; then + echo "request #$i: firmware was not loaded" >&2 + exit 1 + fi + done +} + +read_firmwares_expect_nofile() +{ + for i in $(seq 0 3); do + config_set_read_fw_idx $i + # Ensures contents differ + if diff -q -Z "$FW" $DIR/read_firmware 2>/dev/null ; then + echo "request $i: file was not expected to match" >&2 + exit 1 + fi + done +} + +test_batched_request_firmware_nofile() +{ + echo -n "Batched request_firmware() nofile try #$1: " + config_reset + config_set_name nope-test-firmware.bin + config_trigger_sync + read_firmwares_expect_nofile + release_all_firmware + echo "OK" +} + +test_batched_request_firmware_direct_nofile() +{ + echo -n "Batched request_firmware_direct() nofile try #$1: " + config_reset + config_set_name nope-test-firmware.bin + config_set_sync_direct + config_trigger_sync + release_all_firmware + echo "OK" +} + +test_request_firmware_nowait_uevent_nofile() +{ + echo -n "Batched request_firmware_nowait(uevent=true) nofile try #$1: " + config_reset + config_set_name nope-test-firmware.bin + config_trigger_async + release_all_firmware + echo "OK" +} + +test_wait_and_cancel_custom_load() +{ + if [ "$HAS_FW_LOADER_USER_HELPER" != "yes" ]; then + return + fi + local timeout=10 + name=$1 + while [ ! -e "$DIR"/"$name"/loading ]; do + sleep 0.1 + timeout=$(( $timeout - 1 )) + if [ "$timeout" -eq 0 ]; then + echo "firmware interface never appeared:" >&2 + echo "$DIR/$name/loading" >&2 + exit 1 + fi + done + echo -1 >"$DIR"/"$name"/loading +} + +test_request_firmware_nowait_custom_nofile() +{ + echo -n "Batched request_firmware_nowait(uevent=false) nofile try #$1: " + config_unset_uevent + config_set_name nope-test-firmware.bin + config_trigger_async & + test_wait_and_cancel_custom_load nope-test-firmware.bin + wait + release_all_firmware + echo "OK" +} + +test_batched_request_firmware() +{ + echo -n "Batched request_firmware() try #$1: " + config_reset + config_trigger_sync + read_firmwares + release_all_firmware + echo "OK" +} + +test_batched_request_firmware_direct() +{ + echo -n "Batched request_firmware_direct() try #$1: " + config_reset + config_set_sync_direct + config_trigger_sync + release_all_firmware + echo "OK" +} + +test_request_firmware_nowait_uevent() +{ + echo -n "Batched request_firmware_nowait(uevent=true) try #$1: " + config_reset + config_trigger_async + release_all_firmware + echo "OK" +} + +test_request_firmware_nowait_custom() +{ + echo -n "Batched request_firmware_nowait(uevent=false) try #$1: " + config_unset_uevent + config_trigger_async + release_all_firmware + echo "OK" +} + +# Only continue if batched request triggers are present on the +# test-firmware driver +test_config_present + +# test with the file present +echo +echo "Testing with the file present..." +for i in $(seq 1 5); do + test_batched_request_firmware $i +done + +for i in $(seq 1 5); do + test_batched_request_firmware_direct $i +done + +for i in $(seq 1 5); do + test_request_firmware_nowait_uevent $i +done + +for i in $(seq 1 5); do + test_request_firmware_nowait_custom $i +done + +# Test for file not found, errors are expected, the failure would be +# a hung task, which would require a hard reset. +echo +echo "Testing with the file missing..." +for i in $(seq 1 5); do + test_batched_request_firmware_nofile $i +done + +for i in $(seq 1 5); do + test_batched_request_firmware_direct_nofile $i +done + +for i in $(seq 1 5); do + test_request_firmware_nowait_uevent_nofile $i +done + +for i in $(seq 1 5); do + test_request_firmware_nowait_custom_nofile $i +done + exit 0 diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest index 717581145cfc..abc706cf7702 100755 --- a/tools/testing/selftests/ftrace/ftracetest +++ b/tools/testing/selftests/ftrace/ftracetest @@ -8,15 +8,18 @@ # Released under the terms of the GPL v2. usage() { # errno [message] -[ "$2" ] && echo $2 +[ ! -z "$2" ] && echo $2 echo "Usage: ftracetest [options] [testcase(s)] [testcase-directory(s)]" echo " Options:" echo " -h|--help Show help message" echo " -k|--keep Keep passed test logs" echo " -v|--verbose Increase verbosity of test messages" echo " -vv Alias of -v -v (Show all results in stdout)" +echo " -vvv Alias of -v -v -v (Show all commands immediately)" +echo " --fail-unsupported Treat UNSUPPORTED as a failure" echo " -d|--debug Debug mode (trace all shell commands)" echo " -l|--logdir <dir> Save logs on the <dir>" +echo " If <dir> is -, all logs output in console only" exit $1 } @@ -47,7 +50,7 @@ parse_opts() { # opts local OPT_TEST_CASES= local OPT_TEST_DIR= - while [ "$1" ]; do + while [ ! -z "$1" ]; do case "$1" in --help|-h) usage 0 @@ -56,15 +59,20 @@ parse_opts() { # opts KEEP_LOG=1 shift 1 ;; - --verbose|-v|-vv) + --verbose|-v|-vv|-vvv) VERBOSE=$((VERBOSE + 1)) [ $1 = '-vv' ] && VERBOSE=$((VERBOSE + 1)) + [ $1 = '-vvv' ] && VERBOSE=$((VERBOSE + 2)) shift 1 ;; --debug|-d) DEBUG=1 shift 1 ;; + --fail-unsupported) + UNSUPPORTED_RESULT=1 + shift 1 + ;; --logdir|-l) LOG_DIR=$2 shift 2 @@ -88,7 +96,7 @@ parse_opts() { # opts ;; esac done - if [ "$OPT_TEST_CASES" ]; then + if [ ! -z "$OPT_TEST_CASES" ]; then TEST_CASES=$OPT_TEST_CASES fi } @@ -108,6 +116,7 @@ LOG_DIR=$TOP_DIR/logs/`date +%Y%m%d-%H%M%S`/ KEEP_LOG=0 DEBUG=0 VERBOSE=0 +UNSUPPORTED_RESULT=0 # Parse command-line options parse_opts $* @@ -119,14 +128,20 @@ if [ -z "$TRACING_DIR" -o ! -d "$TRACING_DIR" ]; then fi # Preparing logs -LOG_FILE=$LOG_DIR/ftracetest.log -mkdir -p $LOG_DIR || errexit "Failed to make a log directory: $LOG_DIR" -date > $LOG_FILE +if [ "x$LOG_DIR" = "x-" ]; then + LOG_FILE= + date +else + LOG_FILE=$LOG_DIR/ftracetest.log + mkdir -p $LOG_DIR || errexit "Failed to make a log directory: $LOG_DIR" + date > $LOG_FILE +fi + prlog() { # messages - echo "$@" | tee -a $LOG_FILE + [ -z "$LOG_FILE" ] && echo "$@" || echo "$@" | tee -a $LOG_FILE } catlog() { #file - cat $1 | tee -a $LOG_FILE + [ -z "$LOG_FILE" ] && cat $1 || cat $1 | tee -a $LOG_FILE } prlog "=== Ftrace unit tests ===" @@ -187,7 +202,7 @@ eval_result() { # sigval $UNSUPPORTED) prlog " [UNSUPPORTED]" UNSUPPORTED_CASES="$UNSUPPORTED_CASES $CASENO" - return 1 # this is not a bug, but the result should be reported. + return $UNSUPPORTED_RESULT # depends on use case ;; $XFAIL) prlog " [XFAIL]" @@ -247,12 +262,20 @@ __run_test() { # testfile # Run one test case run_test() { # testfile local testname=`basename $1` - local testlog=`mktemp $LOG_DIR/${testname}-log.XXXXXX` + if [ ! -z "$LOG_FILE" ] ; then + local testlog=`mktemp $LOG_DIR/${testname}-log.XXXXXX` + else + local testlog=/proc/self/fd/1 + fi export TMPDIR=`mktemp -d /tmp/ftracetest-dir.XXXXXX` testcase $1 - echo "execute: "$1 > $testlog + echo "execute$INSTANCE: "$1 > $testlog SIG_RESULT=0 - if [ $VERBOSE -ge 2 ]; then + if [ -z "$LOG_FILE" ]; then + __run_test $1 2>&1 + elif [ $VERBOSE -ge 3 ]; then + __run_test $1 | tee -a $testlog 2>&1 + elif [ $VERBOSE -eq 2 ]; then __run_test $1 2>> $testlog | tee -a $testlog else __run_test $1 >> $testlog 2>&1 @@ -260,9 +283,9 @@ run_test() { # testfile eval_result $SIG_RESULT if [ $? -eq 0 ]; then # Remove test log if the test was done as it was expected. - [ $KEEP_LOG -eq 0 ] && rm $testlog + [ $KEEP_LOG -eq 0 -a ! -z "$LOG_FILE" ] && rm $testlog else - [ $VERBOSE -ge 1 ] && catlog $testlog + [ $VERBOSE -eq 1 -o $VERBOSE -eq 2 ] && catlog $testlog TOTAL_RESULT=1 fi rm -rf $TMPDIR diff --git a/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc b/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc index 0bb5df3c00d4..15e2d3fe1731 100644 --- a/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc +++ b/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc @@ -28,7 +28,9 @@ echo '*:*' > set_event yield -count=`cat trace | grep -v ^# | wc -l` +echo 0 > tracing_on + +count=`head -n 128 trace | grep -v ^# | wc -l` if [ $count -eq 0 ]; then fail "none of events are recorded" fi @@ -36,10 +38,12 @@ fi do_reset echo 1 > events/enable +echo 1 > tracing_on yield -count=`cat trace | grep -v ^# | wc -l` +echo 0 > tracing_on +count=`head -n 128 trace | grep -v ^# | wc -l` if [ $count -eq 0 ]; then fail "none of events are recorded" fi diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc index 9dcd0ca1f49c..8095e122daa9 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc @@ -11,17 +11,6 @@ fi disable_tracing clear_trace -# filter by ?, schedule is always good -if ! echo "sch?dule" > set_ftrace_filter; then - # test for powerpc 64 - if ! echo ".sch?dule" > set_ftrace_filter; then - fail "can not enable schedule filter" - fi - cat set_ftrace_filter | grep '^.schedule$' -else - cat set_ftrace_filter | grep '^schedule$' -fi - ftrace_filter_check() { # glob grep echo "$1" > set_ftrace_filter cut -f1 -d" " set_ftrace_filter > $TMPDIR/actual @@ -39,11 +28,28 @@ ftrace_filter_check '*schedule*' '^.*schedule.*$' # filter by *, end match ftrace_filter_check 'schedule*' '^schedule.*$' +# Advanced full-glob matching feature is recently supported. +# Skip the tests if we are sure the kernel does not support it. +if grep -q 'accepts: .* glob-matching-pattern' README ; then + # filter by *, both side match ftrace_filter_check 'sch*ule' '^sch.*ule$' # filter by char class. ftrace_filter_check '[Ss]y[Ss]_*' '^[Ss]y[Ss]_.*$' +# filter by ?, schedule is always good +if ! echo "sch?dule" > set_ftrace_filter; then + # test for powerpc 64 + if ! echo ".sch?dule" > set_ftrace_filter; then + fail "can not enable schedule filter" + fi + cat set_ftrace_filter | grep '^.schedule$' +else + cat set_ftrace_filter | grep '^schedule$' +fi + +fi + echo > set_ftrace_filter enable_tracing diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc index aa31368851c9..77dfb6b48186 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc @@ -72,6 +72,15 @@ run_enable_disable() { test_event_enabled $check_disable echo "schedule:${enable}_event:$EVENT" > set_ftrace_filter + if [ -d ../../instances ]; then # Check instances + cur=`cat set_ftrace_filter` + top=`cat ../../set_ftrace_filter` + if [ "$cur" = "$top" ]; then + echo "This kernel is too old to support per instance filter" + reset_ftrace_filter + exit_unsupported + fi + fi echo " make sure it works 5 times" diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc index c8e02ec01eaf..7a9ab4ff83b6 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc @@ -63,6 +63,10 @@ fi # powerpc uses .schedule func="schedule" +available_file=available_filter_functions +if [ -d ../../instances -a -f ../../available_filter_functions ]; then + available_file=../../available_filter_functions +fi x=`grep '^\.schedule$' available_filter_functions | wc -l` if [ "$x" -eq 1 ]; then func=".schedule" @@ -71,6 +75,15 @@ fi echo '** SET TRACEOFF' echo "$func:traceoff" > set_ftrace_filter +if [ -d ../../instances ]; then # Check instances + cur=`cat set_ftrace_filter` + top=`cat ../../set_ftrace_filter` + if [ "$cur" = "$top" ]; then + echo "This kernel is too old to support per instance filter" + reset_ftrace_filter + exit_unsupported + fi +fi cnt=`grep schedule set_ftrace_filter | wc -l` if [ $cnt -ne 1 ]; then @@ -90,11 +103,11 @@ if [ $on != "0" ]; then fail "Tracing is not off" fi -line1=`cat trace | tail -1` +csum1=`md5sum trace` sleep $SLEEP_TIME -line2=`cat trace | tail -1` +csum2=`md5sum trace` -if [ "$line1" != "$line2" ]; then +if [ "$csum1" != "$csum2" ]; then fail "Tracing file is still changing" fi diff --git a/tools/testing/selftests/ftrace/test.d/instances/instance-event.tc b/tools/testing/selftests/ftrace/test.d/instances/instance-event.tc index c73db7863adb..8a353314dc9b 100644 --- a/tools/testing/selftests/ftrace/test.d/instances/instance-event.tc +++ b/tools/testing/selftests/ftrace/test.d/instances/instance-event.tc @@ -82,7 +82,10 @@ rmdir foo if [ -d foo ]; then fail "foo still exists" fi - +if grep -q "schedule:enable_event:sched:sched_switch" ../set_ftrace_filter; then + echo "Older kernel detected. Cleanup filter" + echo '!schedule:enable_event:sched:sched_switch' > ../set_ftrace_filter +fi instance_slam() { while :; do diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_eventname.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_eventname.tc new file mode 100644 index 000000000000..b9302cc82c12 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_eventname.tc @@ -0,0 +1,36 @@ +#!/bin/sh +# description: Kprobe event auto/manual naming + +[ -f kprobe_events ] || exit_unsupported # this is configurable + +disable_events +echo > kprobe_events + +:;: "Add an event on function without name" ;: + +FUNC=`grep " [tT] .*vfs_read$" /proc/kallsyms | tail -n 1 | cut -f 3 -d " "` +[ "x" != "x$FUNC" ] || exit_unresolved +echo "p $FUNC" > kprobe_events +PROBE_NAME=`echo $FUNC | tr ".:" "_"` +test -d events/kprobes/p_${PROBE_NAME}_0 || exit_failure + +:;: "Add an event on function with new name" ;: + +echo "p:event1 $FUNC" > kprobe_events +test -d events/kprobes/event1 || exit_failure + +:;: "Add an event on function with new name and group" ;: + +echo "p:kprobes2/event2 $FUNC" > kprobe_events +test -d events/kprobes2/event2 || exit_failure + +:;: "Add an event on dot function without name" ;: + +FUNC=`grep -m 10 " [tT] .*\.isra\..*$" /proc/kallsyms | tail -n 1 | cut -f 3 -d " "` +[ "x" != "x$FUNC" ] || exit_unresolved +echo "p $FUNC" > kprobe_events +EVENT=`grep $FUNC kprobe_events | cut -f 1 -d " " | cut -f 2 -d:` +[ "x" != "x$EVENT" ] || exit_failure +test -d events/$EVENT || exit_failure + +echo > kprobe_events diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_module.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_module.tc new file mode 100644 index 000000000000..6d634e4b7680 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_module.tc @@ -0,0 +1,28 @@ +#!/bin/sh +# description: Kprobe dynamic event - probing module + +[ -f kprobe_events ] || exit_unsupported # this is configurable + +disable_events +echo > kprobe_events + +:;: "Add an event on a module function without specifying event name" ;: + +MOD=`lsmod | head -n 2 | tail -n 1 | cut -f1 -d" "` +FUNC=`grep -m 1 ".* t .*\\[$MOD\\]" /proc/kallsyms | xargs | cut -f3 -d" "` +[ "x" != "x$MOD" -a "y" != "y$FUNC" ] || exit_unresolved +echo "p $MOD:$FUNC" > kprobe_events +PROBE_NAME=`echo $MOD:$FUNC | tr ".:" "_"` +test -d events/kprobes/p_${PROBE_NAME}_0 || exit_failure + +:;: "Add an event on a module function with new event name" ;: + +echo "p:event1 $MOD:$FUNC" > kprobe_events +test -d events/kprobes/event1 || exit_failure + +:;: "Add an event on a module function with new event and group name" ;: + +echo "p:kprobes1/event1 $MOD:$FUNC" > kprobe_events +test -d events/kprobes1/event1 || exit_failure + +echo > kprobe_events diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_maxactive.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_maxactive.tc index 57abdf1caabf..7ec6f2639ad6 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_maxactive.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_maxactive.tc @@ -2,6 +2,7 @@ # description: Kretprobe dynamic event with maxactive [ -f kprobe_events ] || exit_unsupported # this is configurable +grep -q 'r\[maxactive\]' README || exit_unsupported # this is older version echo > kprobe_events diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc b/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc index f4d1ff785d67..2a1cb9908746 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc @@ -2,10 +2,10 @@ # description: Register/unregister many kprobe events # ftrace fentry skip size depends on the machine architecture. -# Currently HAVE_KPROBES_ON_FTRACE defined on x86 and powerpc +# Currently HAVE_KPROBES_ON_FTRACE defined on x86 and powerpc64le case `uname -m` in x86_64|i[3456]86) OFFS=5;; - ppc*) OFFS=4;; + ppc64le) OFFS=8;; *) OFFS=0;; esac diff --git a/tools/testing/selftests/futex/Makefile b/tools/testing/selftests/futex/Makefile index e2fbb890aef9..7c647f619d63 100644 --- a/tools/testing/selftests/futex/Makefile +++ b/tools/testing/selftests/futex/Makefile @@ -14,7 +14,7 @@ all: done override define RUN_TESTS - @if [ `dirname $(OUTPUT)` = $(PWD) ]; then ./run.sh; fi + $(OUTPUT)/run.sh endef override define INSTALL_RULE diff --git a/tools/testing/selftests/futex/functional/futex_requeue_pi.c b/tools/testing/selftests/futex/functional/futex_requeue_pi.c index 3da06ad23996..54cd5c414e82 100644 --- a/tools/testing/selftests/futex/functional/futex_requeue_pi.c +++ b/tools/testing/selftests/futex/functional/futex_requeue_pi.c @@ -32,6 +32,7 @@ #include "futextest.h" #include "logging.h" +#define TEST_NAME "futex-requeue-pi" #define MAX_WAKE_ITERS 1000 #define THREAD_MAX 10 #define SIGNAL_PERIOD_US 100 @@ -393,9 +394,11 @@ int main(int argc, char *argv[]) } } - printf("%s: Test requeue functionality\n", basename(argv[0])); - printf("\tArguments: broadcast=%d locked=%d owner=%d timeout=%ldns\n", - broadcast, locked, owner, timeout_ns); + ksft_print_header(); + ksft_print_msg("%s: Test requeue functionality\n", basename(argv[0])); + ksft_print_msg( + "\tArguments: broadcast=%d locked=%d owner=%d timeout=%ldns\n", + broadcast, locked, owner, timeout_ns); /* * FIXME: unit_test is obsolete now that we parse options and the @@ -404,6 +407,6 @@ int main(int argc, char *argv[]) */ ret = unit_test(broadcast, locked, owner, timeout_ns); - print_result(ret); + print_result(TEST_NAME, ret); return ret; } diff --git a/tools/testing/selftests/futex/functional/futex_requeue_pi_mismatched_ops.c b/tools/testing/selftests/futex/functional/futex_requeue_pi_mismatched_ops.c index d5e4f2c4da2a..08187a16507f 100644 --- a/tools/testing/selftests/futex/functional/futex_requeue_pi_mismatched_ops.c +++ b/tools/testing/selftests/futex/functional/futex_requeue_pi_mismatched_ops.c @@ -30,6 +30,8 @@ #include "futextest.h" #include "logging.h" +#define TEST_NAME "futex-requeue-pi-mismatched-ops" + futex_t f1 = FUTEX_INITIALIZER; futex_t f2 = FUTEX_INITIALIZER; int child_ret = 0; @@ -76,7 +78,8 @@ int main(int argc, char *argv[]) } } - printf("%s: Detect mismatched requeue_pi operations\n", + ksft_print_header(); + ksft_print_msg("%s: Detect mismatched requeue_pi operations\n", basename(argv[0])); if (pthread_create(&child, NULL, blocking_child, NULL)) { @@ -130,6 +133,6 @@ int main(int argc, char *argv[]) out: /* If the kernel crashes, we shouldn't return at all. */ - print_result(ret); + print_result(TEST_NAME, ret); return ret; } diff --git a/tools/testing/selftests/futex/functional/futex_requeue_pi_signal_restart.c b/tools/testing/selftests/futex/functional/futex_requeue_pi_signal_restart.c index 3d7dc6afc3f8..f0542a344d95 100644 --- a/tools/testing/selftests/futex/functional/futex_requeue_pi_signal_restart.c +++ b/tools/testing/selftests/futex/functional/futex_requeue_pi_signal_restart.c @@ -32,6 +32,7 @@ #include "futextest.h" #include "logging.h" +#define TEST_NAME "futex-requeue-pi-signal-restart" #define DELAY_US 100 futex_t f1 = FUTEX_INITIALIZER; @@ -142,9 +143,10 @@ int main(int argc, char *argv[]) } } - printf("%s: Test signal handling during requeue_pi\n", + ksft_print_header(); + ksft_print_msg("%s: Test signal handling during requeue_pi\n", basename(argv[0])); - printf("\tArguments: <none>\n"); + ksft_print_msg("\tArguments: <none>\n"); sa.sa_handler = handle_signal; sigemptyset(&sa.sa_mask); @@ -218,6 +220,6 @@ int main(int argc, char *argv[]) if (ret == RET_PASS && waiter_ret) ret = waiter_ret; - print_result(ret); + print_result(TEST_NAME, ret); return ret; } diff --git a/tools/testing/selftests/futex/functional/futex_wait_private_mapped_file.c b/tools/testing/selftests/futex/functional/futex_wait_private_mapped_file.c index 5f687f247454..6216de828093 100644 --- a/tools/testing/selftests/futex/functional/futex_wait_private_mapped_file.c +++ b/tools/testing/selftests/futex/functional/futex_wait_private_mapped_file.c @@ -34,6 +34,7 @@ #include "logging.h" #include "futextest.h" +#define TEST_NAME "futex-wait-private-mapped-file" #define PAGE_SZ 4096 char pad[PAGE_SZ] = {1}; @@ -60,7 +61,7 @@ void *thr_futex_wait(void *arg) ret = futex_wait(&val, 1, &wait_timeout, 0); if (ret && errno != EWOULDBLOCK && errno != ETIMEDOUT) { error("futex error.\n", errno); - print_result(RET_ERROR); + print_result(TEST_NAME, RET_ERROR); exit(RET_ERROR); } @@ -96,8 +97,10 @@ int main(int argc, char **argv) } } - printf("%s: Test the futex value of private file mappings in FUTEX_WAIT\n", - basename(argv[0])); + ksft_print_header(); + ksft_print_msg( + "%s: Test the futex value of private file mappings in FUTEX_WAIT\n", + basename(argv[0])); ret = pthread_create(&thr, NULL, thr_futex_wait, NULL); if (ret < 0) { @@ -120,6 +123,6 @@ int main(int argc, char **argv) pthread_join(thr, NULL); out: - print_result(ret); + print_result(TEST_NAME, ret); return ret; } diff --git a/tools/testing/selftests/futex/functional/futex_wait_timeout.c b/tools/testing/selftests/futex/functional/futex_wait_timeout.c index ab428ca894de..bab3dfe1787f 100644 --- a/tools/testing/selftests/futex/functional/futex_wait_timeout.c +++ b/tools/testing/selftests/futex/functional/futex_wait_timeout.c @@ -27,6 +27,8 @@ #include "futextest.h" #include "logging.h" +#define TEST_NAME "futex-wait-timeout" + static long timeout_ns = 100000; /* 100us default timeout */ void usage(char *prog) @@ -66,9 +68,10 @@ int main(int argc, char *argv[]) } } - printf("%s: Block on a futex and wait for timeout\n", + ksft_print_header(); + ksft_print_msg("%s: Block on a futex and wait for timeout\n", basename(argv[0])); - printf("\tArguments: timeout=%ldns\n", timeout_ns); + ksft_print_msg("\tArguments: timeout=%ldns\n", timeout_ns); /* initialize timeout */ to.tv_sec = 0; @@ -81,6 +84,6 @@ int main(int argc, char *argv[]) ret = RET_FAIL; } - print_result(ret); + print_result(TEST_NAME, ret); return ret; } diff --git a/tools/testing/selftests/futex/functional/futex_wait_uninitialized_heap.c b/tools/testing/selftests/futex/functional/futex_wait_uninitialized_heap.c index fe7aee96844b..26975322545b 100644 --- a/tools/testing/selftests/futex/functional/futex_wait_uninitialized_heap.c +++ b/tools/testing/selftests/futex/functional/futex_wait_uninitialized_heap.c @@ -36,6 +36,7 @@ #include "logging.h" #include "futextest.h" +#define TEST_NAME "futex-wait-uninitialized-heap" #define WAIT_US 5000000 static int child_blocked = 1; @@ -98,7 +99,8 @@ int main(int argc, char **argv) exit(1); } - printf("%s: Test the uninitialized futex value in FUTEX_WAIT\n", + ksft_print_header(); + ksft_print_msg("%s: Test the uninitialized futex value in FUTEX_WAIT\n", basename(argv[0])); @@ -119,6 +121,6 @@ int main(int argc, char **argv) } out: - print_result(ret); + print_result(TEST_NAME, ret); return ret; } diff --git a/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c b/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c index b6b027448825..da15a63269b4 100644 --- a/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c +++ b/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c @@ -28,6 +28,7 @@ #include "futextest.h" #include "logging.h" +#define TEST_NAME "futex-wait-wouldblock" #define timeout_ns 100000 void usage(char *prog) @@ -63,7 +64,8 @@ int main(int argc, char *argv[]) } } - printf("%s: Test the unexpected futex value in FUTEX_WAIT\n", + ksft_print_header(); + ksft_print_msg("%s: Test the unexpected futex value in FUTEX_WAIT\n", basename(argv[0])); info("Calling futex_wait on f1: %u @ %p with val=%u\n", f1, &f1, f1+1); @@ -74,6 +76,6 @@ int main(int argc, char *argv[]) ret = RET_FAIL; } - print_result(ret); + print_result(TEST_NAME, ret); return ret; } diff --git a/tools/testing/selftests/futex/include/logging.h b/tools/testing/selftests/futex/include/logging.h index e14469103f07..01989644e50a 100644 --- a/tools/testing/selftests/futex/include/logging.h +++ b/tools/testing/selftests/futex/include/logging.h @@ -107,24 +107,22 @@ void log_verbosity(int level) * * print_result() is primarily intended for functional tests. */ -void print_result(int ret) +void print_result(const char *test_name, int ret) { - const char *result = "Unknown return code"; - switch (ret) { case RET_PASS: - ksft_inc_pass_cnt(); - result = PASS; - break; + ksft_test_result_pass("%s\n", test_name); + ksft_print_cnts(); + return; case RET_ERROR: - result = ERROR; - break; + ksft_test_result_error("%s\n", test_name); + ksft_print_cnts(); + return; case RET_FAIL: - ksft_inc_fail_cnt(); - result = FAIL; - break; + ksft_test_result_fail("%s\n", test_name); + ksft_print_cnts(); + return; } - printf("Result: %s\n", result); } /* log level macros */ diff --git a/tools/testing/selftests/intel_pstate/.gitignore b/tools/testing/selftests/intel_pstate/.gitignore new file mode 100644 index 000000000000..3bfcbae5fa13 --- /dev/null +++ b/tools/testing/selftests/intel_pstate/.gitignore @@ -0,0 +1,2 @@ +aperf +msr diff --git a/tools/testing/selftests/intel_pstate/Makefile b/tools/testing/selftests/intel_pstate/Makefile index 19678e90efb2..849a90ffe8dd 100644 --- a/tools/testing/selftests/intel_pstate/Makefile +++ b/tools/testing/selftests/intel_pstate/Makefile @@ -1,5 +1,5 @@ CFLAGS := $(CFLAGS) -Wall -D_GNU_SOURCE -LDFLAGS := $(LDFLAGS) -lm +LDLIBS := $(LDLIBS) -lm TEST_GEN_FILES := msr aperf diff --git a/tools/testing/selftests/kcmp/kcmp_test.c b/tools/testing/selftests/kcmp/kcmp_test.c index a5a4da856dfe..73684c4a1ed6 100644 --- a/tools/testing/selftests/kcmp/kcmp_test.c +++ b/tools/testing/selftests/kcmp/kcmp_test.c @@ -8,7 +8,6 @@ #include <errno.h> #include <string.h> #include <fcntl.h> - #include <linux/unistd.h> #include <linux/kcmp.h> @@ -16,20 +15,28 @@ #include <sys/types.h> #include <sys/stat.h> #include <sys/wait.h> +#include <sys/epoll.h> #include "../kselftest.h" -static long sys_kcmp(int pid1, int pid2, int type, int fd1, int fd2) +static long sys_kcmp(int pid1, int pid2, int type, unsigned long fd1, unsigned long fd2) { return syscall(__NR_kcmp, pid1, pid2, type, fd1, fd2); } +static const unsigned int duped_num = 64; + int main(int argc, char **argv) { const char kpath[] = "kcmp-test-file"; + struct kcmp_epoll_slot epoll_slot; + struct epoll_event ev; int pid1, pid2; + int pipefd[2]; int fd1, fd2; + int epollfd; int status; + int fddup; fd1 = open(kpath, O_RDWR | O_CREAT | O_TRUNC, 0644); pid1 = getpid(); @@ -39,6 +46,37 @@ int main(int argc, char **argv) ksft_exit_fail(); } + if (pipe(pipefd)) { + perror("Can't create pipe"); + ksft_exit_fail(); + } + + epollfd = epoll_create1(0); + if (epollfd < 0) { + perror("epoll_create1 failed"); + ksft_exit_fail(); + } + + memset(&ev, 0xff, sizeof(ev)); + ev.events = EPOLLIN | EPOLLOUT; + + if (epoll_ctl(epollfd, EPOLL_CTL_ADD, pipefd[0], &ev)) { + perror("epoll_ctl failed"); + ksft_exit_fail(); + } + + fddup = dup2(pipefd[1], duped_num); + if (fddup < 0) { + perror("dup2 failed"); + ksft_exit_fail(); + } + + if (epoll_ctl(epollfd, EPOLL_CTL_ADD, fddup, &ev)) { + perror("epoll_ctl failed"); + ksft_exit_fail(); + } + close(fddup); + pid2 = fork(); if (pid2 < 0) { perror("fork failed"); @@ -95,6 +133,24 @@ int main(int argc, char **argv) ksft_inc_pass_cnt(); } + /* Compare epoll target */ + epoll_slot = (struct kcmp_epoll_slot) { + .efd = epollfd, + .tfd = duped_num, + .toff = 0, + }; + ret = sys_kcmp(pid1, pid1, KCMP_EPOLL_TFD, pipefd[1], + (unsigned long)(void *)&epoll_slot); + if (ret) { + printf("FAIL: 0 expected but %d returned (%s)\n", + ret, strerror(errno)); + ksft_inc_fail_cnt(); + ret = -1; + } else { + printf("PASS: 0 returned as expected\n"); + ksft_inc_pass_cnt(); + } + ksft_print_cnts(); if (ret) diff --git a/tools/testing/selftests/kmod/Makefile b/tools/testing/selftests/kmod/Makefile new file mode 100644 index 000000000000..fa2ccc5fb3de --- /dev/null +++ b/tools/testing/selftests/kmod/Makefile @@ -0,0 +1,11 @@ +# Makefile for kmod loading selftests + +# No binaries, but make sure arg-less "make" doesn't trigger "run_tests" +all: + +TEST_PROGS := kmod.sh + +include ../lib.mk + +# Nothing to clean up. +clean: diff --git a/tools/testing/selftests/kmod/config b/tools/testing/selftests/kmod/config new file mode 100644 index 000000000000..259f4fd6b5e2 --- /dev/null +++ b/tools/testing/selftests/kmod/config @@ -0,0 +1,7 @@ +CONFIG_TEST_KMOD=m +CONFIG_TEST_LKM=m +CONFIG_XFS_FS=m + +# For the module parameter force_init_test is used +CONFIG_TUN=m +CONFIG_BTRFS_FS=m diff --git a/tools/testing/selftests/kmod/kmod.sh b/tools/testing/selftests/kmod/kmod.sh new file mode 100755 index 000000000000..7956ea3be667 --- /dev/null +++ b/tools/testing/selftests/kmod/kmod.sh @@ -0,0 +1,615 @@ +#!/bin/bash +# +# Copyright (C) 2017 Luis R. Rodriguez <mcgrof@kernel.org> +# +# This program is free software; you can redistribute it and/or modify it +# under the terms of the GNU General Public License as published by the Free +# Software Foundation; either version 2 of the License, or at your option any +# later version; or, when distributed separately from the Linux kernel or +# when incorporated into other software packages, subject to the following +# license: +# +# This program is free software; you can redistribute it and/or modify it +# under the terms of copyleft-next (version 0.3.1 or later) as published +# at http://copyleft-next.org/. + +# This is a stress test script for kmod, the kernel module loader. It uses +# test_kmod which exposes a series of knobs for the API for us so we can +# tweak each test in userspace rather than in kernelspace. +# +# The way kmod works is it uses the kernel's usermode helper API to eventually +# call /sbin/modprobe. It has a limit of the number of concurrent calls +# possible. The kernel interface to load modules is request_module(), however +# mount uses get_fs_type(). Both behave slightly differently, but the +# differences are important enough to test each call separately. For this +# reason test_kmod starts by providing tests for both calls. +# +# The test driver test_kmod assumes a series of defaults which you can +# override by exporting to your environment prior running this script. +# For instance this script assumes you do not have xfs loaded upon boot. +# If this is false, export DEFAULT_KMOD_FS="ext4" prior to running this +# script if the filesyste module you don't have loaded upon bootup +# is ext4 instead. Refer to allow_user_defaults() for a list of user +# override variables possible. +# +# You'll want at least 4 GiB of RAM to expect to run these tests +# without running out of memory on them. For other requirements refer +# to test_reqs() + +set -e + +TEST_NAME="kmod" +TEST_DRIVER="test_${TEST_NAME}" +TEST_DIR=$(dirname $0) + +# This represents +# +# TEST_ID:TEST_COUNT:ENABLED +# +# TEST_ID: is the test id number +# TEST_COUNT: number of times we should run the test +# ENABLED: 1 if enabled, 0 otherwise +# +# Once these are enabled please leave them as-is. Write your own test, +# we have tons of space. +ALL_TESTS="0001:3:1" +ALL_TESTS="$ALL_TESTS 0002:3:1" +ALL_TESTS="$ALL_TESTS 0003:1:1" +ALL_TESTS="$ALL_TESTS 0004:1:1" +ALL_TESTS="$ALL_TESTS 0005:10:1" +ALL_TESTS="$ALL_TESTS 0006:10:1" +ALL_TESTS="$ALL_TESTS 0007:5:1" +ALL_TESTS="$ALL_TESTS 0008:150:1" +ALL_TESTS="$ALL_TESTS 0009:150:1" + +test_modprobe() +{ + if [ ! -d $DIR ]; then + echo "$0: $DIR not present" >&2 + echo "You must have the following enabled in your kernel:" >&2 + cat $TEST_DIR/config >&2 + exit 1 + fi +} + +function allow_user_defaults() +{ + if [ -z $DEFAULT_KMOD_DRIVER ]; then + DEFAULT_KMOD_DRIVER="test_module" + fi + + if [ -z $DEFAULT_KMOD_FS ]; then + DEFAULT_KMOD_FS="xfs" + fi + + if [ -z $PROC_DIR ]; then + PROC_DIR="/proc/sys/kernel/" + fi + + if [ -z $MODPROBE_LIMIT ]; then + MODPROBE_LIMIT=50 + fi + + if [ -z $DIR ]; then + DIR="/sys/devices/virtual/misc/${TEST_DRIVER}0/" + fi + + if [ -z $DEFAULT_NUM_TESTS ]; then + DEFAULT_NUM_TESTS=150 + fi + + MODPROBE_LIMIT_FILE="${PROC_DIR}/kmod-limit" +} + +test_reqs() +{ + if ! which modprobe 2> /dev/null > /dev/null; then + echo "$0: You need modprobe installed" >&2 + exit 1 + fi + + if ! which kmod 2> /dev/null > /dev/null; then + echo "$0: You need kmod installed" >&2 + exit 1 + fi + + # kmod 19 has a bad bug where it returns 0 when modprobe + # gets called *even* if the module was not loaded due to + # some bad heuristics. For details see: + # + # A work around is possible in-kernel but its rather + # complex. + KMOD_VERSION=$(kmod --version | awk '{print $3}') + if [[ $KMOD_VERSION -le 19 ]]; then + echo "$0: You need at least kmod 20" >&2 + echo "kmod <= 19 is buggy, for details see:" >&2 + echo "http://git.kernel.org/cgit/utils/kernel/kmod/kmod.git/commit/libkmod/libkmod-module.c?id=fd44a98ae2eb5eb32161088954ab21e58e19dfc4" >&2 + exit 1 + fi + + uid=$(id -u) + if [ $uid -ne 0 ]; then + echo $msg must be run as root >&2 + exit 0 + fi +} + +function load_req_mod() +{ + trap "test_modprobe" EXIT + + if [ ! -d $DIR ]; then + # Alanis: "Oh isn't it ironic?" + modprobe $TEST_DRIVER + fi +} + +test_finish() +{ + echo "Test completed" +} + +errno_name_to_val() +{ + case "$1" in + # kmod calls modprobe and upon of a module not found + # modprobe returns just 1... However in the kernel we + # *sometimes* see 256... + MODULE_NOT_FOUND) + echo 256;; + SUCCESS) + echo 0;; + -EPERM) + echo -1;; + -ENOENT) + echo -2;; + -EINVAL) + echo -22;; + -ERR_ANY) + echo -123456;; + *) + echo invalid;; + esac +} + +errno_val_to_name() + case "$1" in + 256) + echo MODULE_NOT_FOUND;; + 0) + echo SUCCESS;; + -1) + echo -EPERM;; + -2) + echo -ENOENT;; + -22) + echo -EINVAL;; + -123456) + echo -ERR_ANY;; + *) + echo invalid;; + esac + +config_set_test_case_driver() +{ + if ! echo -n 1 >$DIR/config_test_case; then + echo "$0: Unable to set to test case to driver" >&2 + exit 1 + fi +} + +config_set_test_case_fs() +{ + if ! echo -n 2 >$DIR/config_test_case; then + echo "$0: Unable to set to test case to fs" >&2 + exit 1 + fi +} + +config_num_threads() +{ + if ! echo -n $1 >$DIR/config_num_threads; then + echo "$0: Unable to set to number of threads" >&2 + exit 1 + fi +} + +config_get_modprobe_limit() +{ + if [[ -f ${MODPROBE_LIMIT_FILE} ]] ; then + MODPROBE_LIMIT=$(cat $MODPROBE_LIMIT_FILE) + fi + echo $MODPROBE_LIMIT +} + +config_num_thread_limit_extra() +{ + MODPROBE_LIMIT=$(config_get_modprobe_limit) + let EXTRA_LIMIT=$MODPROBE_LIMIT+$1 + config_num_threads $EXTRA_LIMIT +} + +# For special characters use printf directly, +# refer to kmod_test_0001 +config_set_driver() +{ + if ! echo -n $1 >$DIR/config_test_driver; then + echo "$0: Unable to set driver" >&2 + exit 1 + fi +} + +config_set_fs() +{ + if ! echo -n $1 >$DIR/config_test_fs; then + echo "$0: Unable to set driver" >&2 + exit 1 + fi +} + +config_get_driver() +{ + cat $DIR/config_test_driver +} + +config_get_test_result() +{ + cat $DIR/test_result +} + +config_reset() +{ + if ! echo -n "1" >"$DIR"/reset; then + echo "$0: reset shuld have worked" >&2 + exit 1 + fi +} + +config_show_config() +{ + echo "----------------------------------------------------" + cat "$DIR"/config + echo "----------------------------------------------------" +} + +config_trigger() +{ + if ! echo -n "1" >"$DIR"/trigger_config 2>/dev/null; then + echo "$1: FAIL - loading should have worked" + config_show_config + exit 1 + fi + echo "$1: OK! - loading kmod test" +} + +config_trigger_want_fail() +{ + if echo "1" > $DIR/trigger_config 2>/dev/null; then + echo "$1: FAIL - test case was expected to fail" + config_show_config + exit 1 + fi + echo "$1: OK! - kmod test case failed as expected" +} + +config_expect_result() +{ + RC=$(config_get_test_result) + RC_NAME=$(errno_val_to_name $RC) + + ERRNO_NAME=$2 + ERRNO=$(errno_name_to_val $ERRNO_NAME) + + if [[ $ERRNO_NAME = "-ERR_ANY" ]]; then + if [[ $RC -ge 0 ]]; then + echo "$1: FAIL, test expects $ERRNO_NAME - got $RC_NAME ($RC)" >&2 + config_show_config + exit 1 + fi + elif [[ $RC != $ERRNO ]]; then + echo "$1: FAIL, test expects $ERRNO_NAME ($ERRNO) - got $RC_NAME ($RC)" >&2 + config_show_config + exit 1 + fi + echo "$1: OK! - Return value: $RC ($RC_NAME), expected $ERRNO_NAME" +} + +kmod_defaults_driver() +{ + config_reset + modprobe -r $DEFAULT_KMOD_DRIVER + config_set_driver $DEFAULT_KMOD_DRIVER +} + +kmod_defaults_fs() +{ + config_reset + modprobe -r $DEFAULT_KMOD_FS + config_set_fs $DEFAULT_KMOD_FS + config_set_test_case_fs +} + +kmod_test_0001_driver() +{ + NAME='\000' + + kmod_defaults_driver + config_num_threads 1 + printf '\000' >"$DIR"/config_test_driver + config_trigger ${FUNCNAME[0]} + config_expect_result ${FUNCNAME[0]} MODULE_NOT_FOUND +} + +kmod_test_0001_fs() +{ + NAME='\000' + + kmod_defaults_fs + config_num_threads 1 + printf '\000' >"$DIR"/config_test_fs + config_trigger ${FUNCNAME[0]} + config_expect_result ${FUNCNAME[0]} -EINVAL +} + +kmod_test_0001() +{ + kmod_test_0001_driver + kmod_test_0001_fs +} + +kmod_test_0002_driver() +{ + NAME="nope-$DEFAULT_KMOD_DRIVER" + + kmod_defaults_driver + config_set_driver $NAME + config_num_threads 1 + config_trigger ${FUNCNAME[0]} + config_expect_result ${FUNCNAME[0]} MODULE_NOT_FOUND +} + +kmod_test_0002_fs() +{ + NAME="nope-$DEFAULT_KMOD_FS" + + kmod_defaults_fs + config_set_fs $NAME + config_trigger ${FUNCNAME[0]} + config_expect_result ${FUNCNAME[0]} -EINVAL +} + +kmod_test_0002() +{ + kmod_test_0002_driver + kmod_test_0002_fs +} + +kmod_test_0003() +{ + kmod_defaults_fs + config_num_threads 1 + config_trigger ${FUNCNAME[0]} + config_expect_result ${FUNCNAME[0]} SUCCESS +} + +kmod_test_0004() +{ + kmod_defaults_fs + config_num_threads 2 + config_trigger ${FUNCNAME[0]} + config_expect_result ${FUNCNAME[0]} SUCCESS +} + +kmod_test_0005() +{ + kmod_defaults_driver + config_trigger ${FUNCNAME[0]} + config_expect_result ${FUNCNAME[0]} SUCCESS +} + +kmod_test_0006() +{ + kmod_defaults_fs + config_trigger ${FUNCNAME[0]} + config_expect_result ${FUNCNAME[0]} SUCCESS +} + +kmod_test_0007() +{ + kmod_test_0005 + kmod_test_0006 +} + +kmod_test_0008() +{ + kmod_defaults_driver + MODPROBE_LIMIT=$(config_get_modprobe_limit) + let EXTRA=$MODPROBE_LIMIT/6 + config_num_thread_limit_extra $EXTRA + config_trigger ${FUNCNAME[0]} + config_expect_result ${FUNCNAME[0]} SUCCESS +} + +kmod_test_0009() +{ + kmod_defaults_fs + MODPROBE_LIMIT=$(config_get_modprobe_limit) + let EXTRA=$MODPROBE_LIMIT/4 + config_num_thread_limit_extra $EXTRA + config_trigger ${FUNCNAME[0]} + config_expect_result ${FUNCNAME[0]} SUCCESS +} + +list_tests() +{ + echo "Test ID list:" + echo + echo "TEST_ID x NUM_TEST" + echo "TEST_ID: Test ID" + echo "NUM_TESTS: Number of recommended times to run the test" + echo + echo "0001 x $(get_test_count 0001) - Simple test - 1 thread for empty string" + echo "0002 x $(get_test_count 0002) - Simple test - 1 thread for modules/filesystems that do not exist" + echo "0003 x $(get_test_count 0003) - Simple test - 1 thread for get_fs_type() only" + echo "0004 x $(get_test_count 0004) - Simple test - 2 threads for get_fs_type() only" + echo "0005 x $(get_test_count 0005) - multithreaded tests with default setup - request_module() only" + echo "0006 x $(get_test_count 0006) - multithreaded tests with default setup - get_fs_type() only" + echo "0007 x $(get_test_count 0007) - multithreaded tests with default setup test request_module() and get_fs_type()" + echo "0008 x $(get_test_count 0008) - multithreaded - push kmod_concurrent over max_modprobes for request_module()" + echo "0009 x $(get_test_count 0009) - multithreaded - push kmod_concurrent over max_modprobes for get_fs_type()" +} + +usage() +{ + NUM_TESTS=$(grep -o ' ' <<<"$ALL_TESTS" | grep -c .) + let NUM_TESTS=$NUM_TESTS+1 + MAX_TEST=$(printf "%04d\n" $NUM_TESTS) + echo "Usage: $0 [ -t <4-number-digit> ] | [ -w <4-number-digit> ] |" + echo " [ -s <4-number-digit> ] | [ -c <4-number-digit> <test- count>" + echo " [ all ] [ -h | --help ] [ -l ]" + echo "" + echo "Valid tests: 0001-$MAX_TEST" + echo "" + echo " all Runs all tests (default)" + echo " -t Run test ID the number amount of times is recommended" + echo " -w Watch test ID run until it runs into an error" + echo " -s Run test ID once" + echo " -c Run test ID x test-count number of times" + echo " -l List all test ID list" + echo " -h|--help Help" + echo + echo "If an error every occurs execution will immediately terminate." + echo "If you are adding a new test try using -w <test-ID> first to" + echo "make sure the test passes a series of tests." + echo + echo Example uses: + echo + echo "${TEST_NAME}.sh -- executes all tests" + echo "${TEST_NAME}.sh -t 0008 -- Executes test ID 0008 number of times is recomended" + echo "${TEST_NAME}.sh -w 0008 -- Watch test ID 0008 run until an error occurs" + echo "${TEST_NAME}.sh -s 0008 -- Run test ID 0008 once" + echo "${TEST_NAME}.sh -c 0008 3 -- Run test ID 0008 three times" + echo + list_tests + exit 1 +} + +function test_num() +{ + re='^[0-9]+$' + if ! [[ $1 =~ $re ]]; then + usage + fi +} + +function get_test_count() +{ + test_num $1 + TEST_DATA=$(echo $ALL_TESTS | awk '{print $'$1'}') + LAST_TWO=${TEST_DATA#*:*} + echo ${LAST_TWO%:*} +} + +function get_test_enabled() +{ + test_num $1 + TEST_DATA=$(echo $ALL_TESTS | awk '{print $'$1'}') + echo ${TEST_DATA#*:*:} +} + +function run_all_tests() +{ + for i in $ALL_TESTS ; do + TEST_ID=${i%:*:*} + ENABLED=$(get_test_enabled $TEST_ID) + TEST_COUNT=$(get_test_count $TEST_ID) + if [[ $ENABLED -eq "1" ]]; then + test_case $TEST_ID $TEST_COUNT + fi + done +} + +function watch_log() +{ + if [ $# -ne 3 ]; then + clear + fi + date + echo "Running test: $2 - run #$1" +} + +function watch_case() +{ + i=0 + while [ 1 ]; do + + if [ $# -eq 1 ]; then + test_num $1 + watch_log $i ${TEST_NAME}_test_$1 + ${TEST_NAME}_test_$1 + else + watch_log $i all + run_all_tests + fi + let i=$i+1 + done +} + +function test_case() +{ + NUM_TESTS=$DEFAULT_NUM_TESTS + if [ $# -eq 2 ]; then + NUM_TESTS=$2 + fi + + i=0 + while [ $i -lt $NUM_TESTS ]; do + test_num $1 + watch_log $i ${TEST_NAME}_test_$1 noclear + RUN_TEST=${TEST_NAME}_test_$1 + $RUN_TEST + let i=$i+1 + done +} + +function parse_args() +{ + if [ $# -eq 0 ]; then + run_all_tests + else + if [[ "$1" = "all" ]]; then + run_all_tests + elif [[ "$1" = "-w" ]]; then + shift + watch_case $@ + elif [[ "$1" = "-t" ]]; then + shift + test_num $1 + test_case $1 $(get_test_count $1) + elif [[ "$1" = "-c" ]]; then + shift + test_num $1 + test_num $2 + test_case $1 $2 + elif [[ "$1" = "-s" ]]; then + shift + test_case $1 1 + elif [[ "$1" = "-l" ]]; then + list_tests + elif [[ "$1" = "-h" || "$1" = "--help" ]]; then + usage + else + usage + fi + fi +} + +test_reqs +allow_user_defaults +load_req_mod + +trap "test_finish" EXIT + +parse_args $@ + +exit 0 diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h index ef1c80d67ac7..1ae565ed9bf0 100644 --- a/tools/testing/selftests/kselftest.h +++ b/tools/testing/selftests/kselftest.h @@ -12,13 +12,15 @@ #include <stdlib.h> #include <unistd.h> +#include <stdarg.h> /* define kselftest exit codes */ #define KSFT_PASS 0 #define KSFT_FAIL 1 #define KSFT_XFAIL 2 #define KSFT_XPASS 3 -#define KSFT_SKIP 4 +/* Treat skip as pass */ +#define KSFT_SKIP KSFT_PASS /* counters */ struct ksft_count { @@ -27,42 +29,154 @@ struct ksft_count { unsigned int ksft_xfail; unsigned int ksft_xpass; unsigned int ksft_xskip; + unsigned int ksft_error; }; static struct ksft_count ksft_cnt; +static inline int ksft_test_num(void) +{ + return ksft_cnt.ksft_pass + ksft_cnt.ksft_fail + + ksft_cnt.ksft_xfail + ksft_cnt.ksft_xpass + + ksft_cnt.ksft_xskip + ksft_cnt.ksft_error; +} + static inline void ksft_inc_pass_cnt(void) { ksft_cnt.ksft_pass++; } static inline void ksft_inc_fail_cnt(void) { ksft_cnt.ksft_fail++; } static inline void ksft_inc_xfail_cnt(void) { ksft_cnt.ksft_xfail++; } static inline void ksft_inc_xpass_cnt(void) { ksft_cnt.ksft_xpass++; } static inline void ksft_inc_xskip_cnt(void) { ksft_cnt.ksft_xskip++; } +static inline void ksft_inc_error_cnt(void) { ksft_cnt.ksft_error++; } + +static inline int ksft_get_pass_cnt(void) { return ksft_cnt.ksft_pass; } +static inline int ksft_get_fail_cnt(void) { return ksft_cnt.ksft_fail; } +static inline int ksft_get_xfail_cnt(void) { return ksft_cnt.ksft_xfail; } +static inline int ksft_get_xpass_cnt(void) { return ksft_cnt.ksft_xpass; } +static inline int ksft_get_xskip_cnt(void) { return ksft_cnt.ksft_xskip; } +static inline int ksft_get_error_cnt(void) { return ksft_cnt.ksft_error; } + +static inline void ksft_print_header(void) +{ + printf("TAP version 13\n"); +} static inline void ksft_print_cnts(void) { - printf("Pass: %d Fail: %d Xfail: %d Xpass: %d, Xskip: %d\n", + printf("Pass %d Fail %d Xfail %d Xpass %d Skip %d Error %d\n", ksft_cnt.ksft_pass, ksft_cnt.ksft_fail, ksft_cnt.ksft_xfail, ksft_cnt.ksft_xpass, - ksft_cnt.ksft_xskip); + ksft_cnt.ksft_xskip, ksft_cnt.ksft_error); + printf("1..%d\n", ksft_test_num()); +} + +static inline void ksft_print_msg(const char *msg, ...) +{ + va_list args; + + va_start(args, msg); + printf("# "); + vprintf(msg, args); + va_end(args); +} + +static inline void ksft_test_result_pass(const char *msg, ...) +{ + va_list args; + + ksft_cnt.ksft_pass++; + + va_start(args, msg); + printf("ok %d ", ksft_test_num()); + vprintf(msg, args); + va_end(args); +} + +static inline void ksft_test_result_fail(const char *msg, ...) +{ + va_list args; + + ksft_cnt.ksft_fail++; + + va_start(args, msg); + printf("not ok %d ", ksft_test_num()); + vprintf(msg, args); + va_end(args); +} + +static inline void ksft_test_result_skip(const char *msg, ...) +{ + va_list args; + + ksft_cnt.ksft_xskip++; + + va_start(args, msg); + printf("ok %d # skip ", ksft_test_num()); + vprintf(msg, args); + va_end(args); +} + +static inline void ksft_test_result_error(const char *msg, ...) +{ + va_list args; + + ksft_cnt.ksft_error++; + + va_start(args, msg); + printf("not ok %d # error ", ksft_test_num()); + vprintf(msg, args); + va_end(args); } static inline int ksft_exit_pass(void) { + ksft_print_cnts(); exit(KSFT_PASS); } + static inline int ksft_exit_fail(void) { + printf("Bail out!\n"); + ksft_print_cnts(); exit(KSFT_FAIL); } + +static inline int ksft_exit_fail_msg(const char *msg, ...) +{ + va_list args; + + va_start(args, msg); + printf("Bail out! "); + vprintf(msg, args); + va_end(args); + + ksft_print_cnts(); + exit(KSFT_FAIL); +} + static inline int ksft_exit_xfail(void) { + ksft_print_cnts(); exit(KSFT_XFAIL); } + static inline int ksft_exit_xpass(void) { + ksft_print_cnts(); exit(KSFT_XPASS); } -static inline int ksft_exit_skip(void) + +static inline int ksft_exit_skip(const char *msg, ...) { + if (msg) { + va_list args; + + va_start(args, msg); + printf("1..%d # Skipped: ", ksft_test_num()); + vprintf(msg, args); + va_end(args); + } else { + ksft_print_cnts(); + } exit(KSFT_SKIP); } diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h new file mode 100644 index 000000000000..e81bd28bdd89 --- /dev/null +++ b/tools/testing/selftests/kselftest_harness.h @@ -0,0 +1,755 @@ +/* + * Copyright (c) 2012 The Chromium OS Authors. All rights reserved. + * Use of this source code is governed by the GPLv2 license. + * + * kselftest_harness.h: simple C unit test helper. + * + * See documentation in Documentation/dev-tools/kselftest.rst + * + * API inspired by code.google.com/p/googletest + */ + +/** + * DOC: example + * + * .. code-block:: c + * + * #include "../kselftest_harness.h" + * + * TEST(standalone_test) { + * do_some_stuff; + * EXPECT_GT(10, stuff) { + * stuff_state_t state; + * enumerate_stuff_state(&state); + * TH_LOG("expectation failed with state: %s", state.msg); + * } + * more_stuff; + * ASSERT_NE(some_stuff, NULL) TH_LOG("how did it happen?!"); + * last_stuff; + * EXPECT_EQ(0, last_stuff); + * } + * + * FIXTURE(my_fixture) { + * mytype_t *data; + * int awesomeness_level; + * }; + * FIXTURE_SETUP(my_fixture) { + * self->data = mytype_new(); + * ASSERT_NE(NULL, self->data); + * } + * FIXTURE_TEARDOWN(my_fixture) { + * mytype_free(self->data); + * } + * TEST_F(my_fixture, data_is_good) { + * EXPECT_EQ(1, is_my_data_good(self->data)); + * } + * + * TEST_HARNESS_MAIN + */ + +#ifndef __KSELFTEST_HARNESS_H +#define __KSELFTEST_HARNESS_H + +#define _GNU_SOURCE +#include <asm/types.h> +#include <errno.h> +#include <stdbool.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <unistd.h> + + +/* Utilities exposed to the test definitions */ +#ifndef TH_LOG_STREAM +# define TH_LOG_STREAM stderr +#endif + +#ifndef TH_LOG_ENABLED +# define TH_LOG_ENABLED 1 +#endif + +/** + * TH_LOG(fmt, ...) + * + * @fmt: format string + * @...: optional arguments + * + * .. code-block:: c + * + * TH_LOG(format, ...) + * + * Optional debug logging function available for use in tests. + * Logging may be enabled or disabled by defining TH_LOG_ENABLED. + * E.g., #define TH_LOG_ENABLED 1 + * + * If no definition is provided, logging is enabled by default. + * + * If there is no way to print an error message for the process running the + * test (e.g. not allowed to write to stderr), it is still possible to get the + * ASSERT_* number for which the test failed. This behavior can be enabled by + * writing `_metadata->no_print = true;` before the check sequence that is + * unable to print. When an error occur, instead of printing an error message + * and calling `abort(3)`, the test process call `_exit(2)` with the assert + * number as argument, which is then printed by the parent process. + */ +#define TH_LOG(fmt, ...) do { \ + if (TH_LOG_ENABLED) \ + __TH_LOG(fmt, ##__VA_ARGS__); \ +} while (0) + +/* Unconditional logger for internal use. */ +#define __TH_LOG(fmt, ...) \ + fprintf(TH_LOG_STREAM, "%s:%d:%s:" fmt "\n", \ + __FILE__, __LINE__, _metadata->name, ##__VA_ARGS__) + +/** + * TEST(test_name) - Defines the test function and creates the registration + * stub + * + * @test_name: test name + * + * .. code-block:: c + * + * TEST(name) { implementation } + * + * Defines a test by name. + * Names must be unique and tests must not be run in parallel. The + * implementation containing block is a function and scoping should be treated + * as such. Returning early may be performed with a bare "return;" statement. + * + * EXPECT_* and ASSERT_* are valid in a TEST() { } context. + */ +#define TEST(test_name) __TEST_IMPL(test_name, -1) + +/** + * TEST_SIGNAL(test_name, signal) + * + * @test_name: test name + * @signal: signal number + * + * .. code-block:: c + * + * TEST_SIGNAL(name, signal) { implementation } + * + * Defines a test by name and the expected term signal. + * Names must be unique and tests must not be run in parallel. The + * implementation containing block is a function and scoping should be treated + * as such. Returning early may be performed with a bare "return;" statement. + * + * EXPECT_* and ASSERT_* are valid in a TEST() { } context. + */ +#define TEST_SIGNAL(test_name, signal) __TEST_IMPL(test_name, signal) + +#define __TEST_IMPL(test_name, _signal) \ + static void test_name(struct __test_metadata *_metadata); \ + static struct __test_metadata _##test_name##_object = \ + { name: "global." #test_name, \ + fn: &test_name, termsig: _signal }; \ + static void __attribute__((constructor)) _register_##test_name(void) \ + { \ + __register_test(&_##test_name##_object); \ + } \ + static void test_name( \ + struct __test_metadata __attribute__((unused)) *_metadata) + +/** + * FIXTURE_DATA(datatype_name) - Wraps the struct name so we have one less + * argument to pass around + * + * @datatype_name: datatype name + * + * .. code-block:: c + * + * FIXTURE_DATA(datatype name) + * + * This call may be used when the type of the fixture data + * is needed. In general, this should not be needed unless + * the *self* is being passed to a helper directly. + */ +#define FIXTURE_DATA(datatype_name) struct _test_data_##datatype_name + +/** + * FIXTURE(fixture_name) - Called once per fixture to setup the data and + * register + * + * @fixture_name: fixture name + * + * .. code-block:: c + * + * FIXTURE(datatype name) { + * type property1; + * ... + * }; + * + * Defines the data provided to TEST_F()-defined tests as *self*. It should be + * populated and cleaned up using FIXTURE_SETUP() and FIXTURE_TEARDOWN(). + */ +#define FIXTURE(fixture_name) \ + static void __attribute__((constructor)) \ + _register_##fixture_name##_data(void) \ + { \ + __fixture_count++; \ + } \ + FIXTURE_DATA(fixture_name) + +/** + * FIXTURE_SETUP(fixture_name) - Prepares the setup function for the fixture. + * *_metadata* is included so that ASSERT_* work as a convenience + * + * @fixture_name: fixture name + * + * .. code-block:: c + * + * FIXTURE_SETUP(fixture name) { implementation } + * + * Populates the required "setup" function for a fixture. An instance of the + * datatype defined with FIXTURE_DATA() will be exposed as *self* for the + * implementation. + * + * ASSERT_* are valid for use in this context and will prempt the execution + * of any dependent fixture tests. + * + * A bare "return;" statement may be used to return early. + */ +#define FIXTURE_SETUP(fixture_name) \ + void fixture_name##_setup( \ + struct __test_metadata __attribute__((unused)) *_metadata, \ + FIXTURE_DATA(fixture_name) __attribute__((unused)) *self) +/** + * FIXTURE_TEARDOWN(fixture_name) + * + * @fixture_name: fixture name + * + * .. code-block:: c + * + * FIXTURE_TEARDOWN(fixture name) { implementation } + * + * Populates the required "teardown" function for a fixture. An instance of the + * datatype defined with FIXTURE_DATA() will be exposed as *self* for the + * implementation to clean up. + * + * A bare "return;" statement may be used to return early. + */ +#define FIXTURE_TEARDOWN(fixture_name) \ + void fixture_name##_teardown( \ + struct __test_metadata __attribute__((unused)) *_metadata, \ + FIXTURE_DATA(fixture_name) __attribute__((unused)) *self) + +/** + * TEST_F(fixture_name, test_name) - Emits test registration and helpers for + * fixture-based test cases + * + * @fixture_name: fixture name + * @test_name: test name + * + * .. code-block:: c + * + * TEST_F(fixture, name) { implementation } + * + * Defines a test that depends on a fixture (e.g., is part of a test case). + * Very similar to TEST() except that *self* is the setup instance of fixture's + * datatype exposed for use by the implementation. + */ +/* TODO(wad) register fixtures on dedicated test lists. */ +#define TEST_F(fixture_name, test_name) \ + __TEST_F_IMPL(fixture_name, test_name, -1) + +#define TEST_F_SIGNAL(fixture_name, test_name, signal) \ + __TEST_F_IMPL(fixture_name, test_name, signal) + +#define __TEST_F_IMPL(fixture_name, test_name, signal) \ + static void fixture_name##_##test_name( \ + struct __test_metadata *_metadata, \ + FIXTURE_DATA(fixture_name) *self); \ + static inline void wrapper_##fixture_name##_##test_name( \ + struct __test_metadata *_metadata) \ + { \ + /* fixture data is alloced, setup, and torn down per call. */ \ + FIXTURE_DATA(fixture_name) self; \ + memset(&self, 0, sizeof(FIXTURE_DATA(fixture_name))); \ + fixture_name##_setup(_metadata, &self); \ + /* Let setup failure terminate early. */ \ + if (!_metadata->passed) \ + return; \ + fixture_name##_##test_name(_metadata, &self); \ + fixture_name##_teardown(_metadata, &self); \ + } \ + static struct __test_metadata \ + _##fixture_name##_##test_name##_object = { \ + name: #fixture_name "." #test_name, \ + fn: &wrapper_##fixture_name##_##test_name, \ + termsig: signal, \ + }; \ + static void __attribute__((constructor)) \ + _register_##fixture_name##_##test_name(void) \ + { \ + __register_test(&_##fixture_name##_##test_name##_object); \ + } \ + static void fixture_name##_##test_name( \ + struct __test_metadata __attribute__((unused)) *_metadata, \ + FIXTURE_DATA(fixture_name) __attribute__((unused)) *self) + +/** + * TEST_HARNESS_MAIN - Simple wrapper to run the test harness + * + * .. code-block:: c + * + * TEST_HARNESS_MAIN + * + * Use once to append a main() to the test file. + */ +#define TEST_HARNESS_MAIN \ + static void __attribute__((constructor)) \ + __constructor_order_last(void) \ + { \ + if (!__constructor_order) \ + __constructor_order = _CONSTRUCTOR_ORDER_BACKWARD; \ + } \ + int main(int argc, char **argv) { \ + return test_harness_run(argc, argv); \ + } + +/** + * DOC: operators + * + * Operators for use in TEST() and TEST_F(). + * ASSERT_* calls will stop test execution immediately. + * EXPECT_* calls will emit a failure warning, note it, and continue. + */ + +/** + * ASSERT_EQ(expected, seen) + * + * @expected: expected value + * @seen: measured value + * + * ASSERT_EQ(expected, measured): expected == measured + */ +#define ASSERT_EQ(expected, seen) \ + __EXPECT(expected, seen, ==, 1) + +/** + * ASSERT_NE(expected, seen) + * + * @expected: expected value + * @seen: measured value + * + * ASSERT_NE(expected, measured): expected != measured + */ +#define ASSERT_NE(expected, seen) \ + __EXPECT(expected, seen, !=, 1) + +/** + * ASSERT_LT(expected, seen) + * + * @expected: expected value + * @seen: measured value + * + * ASSERT_LT(expected, measured): expected < measured + */ +#define ASSERT_LT(expected, seen) \ + __EXPECT(expected, seen, <, 1) + +/** + * ASSERT_LE(expected, seen) + * + * @expected: expected value + * @seen: measured value + * + * ASSERT_LE(expected, measured): expected <= measured + */ +#define ASSERT_LE(expected, seen) \ + __EXPECT(expected, seen, <=, 1) + +/** + * ASSERT_GT(expected, seen) + * + * @expected: expected value + * @seen: measured value + * + * ASSERT_GT(expected, measured): expected > measured + */ +#define ASSERT_GT(expected, seen) \ + __EXPECT(expected, seen, >, 1) + +/** + * ASSERT_GE(expected, seen) + * + * @expected: expected value + * @seen: measured value + * + * ASSERT_GE(expected, measured): expected >= measured + */ +#define ASSERT_GE(expected, seen) \ + __EXPECT(expected, seen, >=, 1) + +/** + * ASSERT_NULL(seen) + * + * @seen: measured value + * + * ASSERT_NULL(measured): NULL == measured + */ +#define ASSERT_NULL(seen) \ + __EXPECT(NULL, seen, ==, 1) + +/** + * ASSERT_TRUE(seen) + * + * @seen: measured value + * + * ASSERT_TRUE(measured): measured != 0 + */ +#define ASSERT_TRUE(seen) \ + ASSERT_NE(0, seen) + +/** + * ASSERT_FALSE(seen) + * + * @seen: measured value + * + * ASSERT_FALSE(measured): measured == 0 + */ +#define ASSERT_FALSE(seen) \ + ASSERT_EQ(0, seen) + +/** + * ASSERT_STREQ(expected, seen) + * + * @expected: expected value + * @seen: measured value + * + * ASSERT_STREQ(expected, measured): !strcmp(expected, measured) + */ +#define ASSERT_STREQ(expected, seen) \ + __EXPECT_STR(expected, seen, ==, 1) + +/** + * ASSERT_STRNE(expected, seen) + * + * @expected: expected value + * @seen: measured value + * + * ASSERT_STRNE(expected, measured): strcmp(expected, measured) + */ +#define ASSERT_STRNE(expected, seen) \ + __EXPECT_STR(expected, seen, !=, 1) + +/** + * EXPECT_EQ(expected, seen) + * + * @expected: expected value + * @seen: measured value + * + * EXPECT_EQ(expected, measured): expected == measured + */ +#define EXPECT_EQ(expected, seen) \ + __EXPECT(expected, seen, ==, 0) + +/** + * EXPECT_NE(expected, seen) + * + * @expected: expected value + * @seen: measured value + * + * EXPECT_NE(expected, measured): expected != measured + */ +#define EXPECT_NE(expected, seen) \ + __EXPECT(expected, seen, !=, 0) + +/** + * EXPECT_LT(expected, seen) + * + * @expected: expected value + * @seen: measured value + * + * EXPECT_LT(expected, measured): expected < measured + */ +#define EXPECT_LT(expected, seen) \ + __EXPECT(expected, seen, <, 0) + +/** + * EXPECT_LE(expected, seen) + * + * @expected: expected value + * @seen: measured value + * + * EXPECT_LE(expected, measured): expected <= measured + */ +#define EXPECT_LE(expected, seen) \ + __EXPECT(expected, seen, <=, 0) + +/** + * EXPECT_GT(expected, seen) + * + * @expected: expected value + * @seen: measured value + * + * EXPECT_GT(expected, measured): expected > measured + */ +#define EXPECT_GT(expected, seen) \ + __EXPECT(expected, seen, >, 0) + +/** + * EXPECT_GE(expected, seen) + * + * @expected: expected value + * @seen: measured value + * + * EXPECT_GE(expected, measured): expected >= measured + */ +#define EXPECT_GE(expected, seen) \ + __EXPECT(expected, seen, >=, 0) + +/** + * EXPECT_NULL(seen) + * + * @seen: measured value + * + * EXPECT_NULL(measured): NULL == measured + */ +#define EXPECT_NULL(seen) \ + __EXPECT(NULL, seen, ==, 0) + +/** + * EXPECT_TRUE(seen) + * + * @seen: measured value + * + * EXPECT_TRUE(measured): 0 != measured + */ +#define EXPECT_TRUE(seen) \ + EXPECT_NE(0, seen) + +/** + * EXPECT_FALSE(seen) + * + * @seen: measured value + * + * EXPECT_FALSE(measured): 0 == measured + */ +#define EXPECT_FALSE(seen) \ + EXPECT_EQ(0, seen) + +/** + * EXPECT_STREQ(expected, seen) + * + * @expected: expected value + * @seen: measured value + * + * EXPECT_STREQ(expected, measured): !strcmp(expected, measured) + */ +#define EXPECT_STREQ(expected, seen) \ + __EXPECT_STR(expected, seen, ==, 0) + +/** + * EXPECT_STRNE(expected, seen) + * + * @expected: expected value + * @seen: measured value + * + * EXPECT_STRNE(expected, measured): strcmp(expected, measured) + */ +#define EXPECT_STRNE(expected, seen) \ + __EXPECT_STR(expected, seen, !=, 0) + +#define ARRAY_SIZE(a) (sizeof(a) / sizeof(a[0])) + +/* Support an optional handler after and ASSERT_* or EXPECT_*. The approach is + * not thread-safe, but it should be fine in most sane test scenarios. + * + * Using __bail(), which optionally abort()s, is the easiest way to early + * return while still providing an optional block to the API consumer. + */ +#define OPTIONAL_HANDLER(_assert) \ + for (; _metadata->trigger; _metadata->trigger = \ + __bail(_assert, _metadata->no_print, _metadata->step)) + +#define __INC_STEP(_metadata) \ + if (_metadata->passed && _metadata->step < 255) \ + _metadata->step++; + +#define __EXPECT(_expected, _seen, _t, _assert) do { \ + /* Avoid multiple evaluation of the cases */ \ + __typeof__(_expected) __exp = (_expected); \ + __typeof__(_seen) __seen = (_seen); \ + if (_assert) __INC_STEP(_metadata); \ + if (!(__exp _t __seen)) { \ + unsigned long long __exp_print = (uintptr_t)__exp; \ + unsigned long long __seen_print = (uintptr_t)__seen; \ + __TH_LOG("Expected %s (%llu) %s %s (%llu)", \ + #_expected, __exp_print, #_t, \ + #_seen, __seen_print); \ + _metadata->passed = 0; \ + /* Ensure the optional handler is triggered */ \ + _metadata->trigger = 1; \ + } \ +} while (0); OPTIONAL_HANDLER(_assert) + +#define __EXPECT_STR(_expected, _seen, _t, _assert) do { \ + const char *__exp = (_expected); \ + const char *__seen = (_seen); \ + if (_assert) __INC_STEP(_metadata); \ + if (!(strcmp(__exp, __seen) _t 0)) { \ + __TH_LOG("Expected '%s' %s '%s'.", __exp, #_t, __seen); \ + _metadata->passed = 0; \ + _metadata->trigger = 1; \ + } \ +} while (0); OPTIONAL_HANDLER(_assert) + +/* Contains all the information for test execution and status checking. */ +struct __test_metadata { + const char *name; + void (*fn)(struct __test_metadata *); + int termsig; + int passed; + int trigger; /* extra handler after the evaluation */ + __u8 step; + bool no_print; /* manual trigger when TH_LOG_STREAM is not available */ + struct __test_metadata *prev, *next; +}; + +/* Storage for the (global) tests to be run. */ +static struct __test_metadata *__test_list; +static unsigned int __test_count; +static unsigned int __fixture_count; +static int __constructor_order; + +#define _CONSTRUCTOR_ORDER_FORWARD 1 +#define _CONSTRUCTOR_ORDER_BACKWARD -1 + +/* + * Since constructors are called in reverse order, reverse the test + * list so tests are run in source declaration order. + * https://gcc.gnu.org/onlinedocs/gccint/Initialization.html + * However, it seems not all toolchains do this correctly, so use + * __constructor_order to detect which direction is called first + * and adjust list building logic to get things running in the right + * direction. + */ +static inline void __register_test(struct __test_metadata *t) +{ + __test_count++; + /* Circular linked list where only prev is circular. */ + if (__test_list == NULL) { + __test_list = t; + t->next = NULL; + t->prev = t; + return; + } + if (__constructor_order == _CONSTRUCTOR_ORDER_FORWARD) { + t->next = NULL; + t->prev = __test_list->prev; + t->prev->next = t; + __test_list->prev = t; + } else { + t->next = __test_list; + t->next->prev = t; + t->prev = t; + __test_list = t; + } +} + +static inline int __bail(int for_realz, bool no_print, __u8 step) +{ + if (for_realz) { + if (no_print) + _exit(step); + abort(); + } + return 0; +} + +void __run_test(struct __test_metadata *t) +{ + pid_t child_pid; + int status; + + t->passed = 1; + t->trigger = 0; + printf("[ RUN ] %s\n", t->name); + child_pid = fork(); + if (child_pid < 0) { + printf("ERROR SPAWNING TEST CHILD\n"); + t->passed = 0; + } else if (child_pid == 0) { + t->fn(t); + /* return the step that failed or 0 */ + _exit(t->passed ? 0 : t->step); + } else { + /* TODO(wad) add timeout support. */ + waitpid(child_pid, &status, 0); + if (WIFEXITED(status)) { + t->passed = t->termsig == -1 ? !WEXITSTATUS(status) : 0; + if (t->termsig != -1) { + fprintf(TH_LOG_STREAM, + "%s: Test exited normally " + "instead of by signal (code: %d)\n", + t->name, + WEXITSTATUS(status)); + } else if (!t->passed) { + fprintf(TH_LOG_STREAM, + "%s: Test failed at step #%d\n", + t->name, + WEXITSTATUS(status)); + } + } else if (WIFSIGNALED(status)) { + t->passed = 0; + if (WTERMSIG(status) == SIGABRT) { + fprintf(TH_LOG_STREAM, + "%s: Test terminated by assertion\n", + t->name); + } else if (WTERMSIG(status) == t->termsig) { + t->passed = 1; + } else { + fprintf(TH_LOG_STREAM, + "%s: Test terminated unexpectedly " + "by signal %d\n", + t->name, + WTERMSIG(status)); + } + } else { + fprintf(TH_LOG_STREAM, + "%s: Test ended in some other way [%u]\n", + t->name, + status); + } + } + printf("[ %4s ] %s\n", (t->passed ? "OK" : "FAIL"), t->name); +} + +static int test_harness_run(int __attribute__((unused)) argc, + char __attribute__((unused)) **argv) +{ + struct __test_metadata *t; + int ret = 0; + unsigned int count = 0; + unsigned int pass_count = 0; + + /* TODO(wad) add optional arguments similar to gtest. */ + printf("[==========] Running %u tests from %u test cases.\n", + __test_count, __fixture_count + 1); + for (t = __test_list; t; t = t->next) { + count++; + __run_test(t); + if (t->passed) + pass_count++; + else + ret = 1; + } + printf("[==========] %u / %u tests passed.\n", pass_count, count); + printf("[ %s ]\n", (ret ? "FAILED" : "PASSED")); + return ret; +} + +static void __attribute__((constructor)) __constructor_order_first(void) +{ + if (!__constructor_order) + __constructor_order = _CONSTRUCTOR_ORDER_FORWARD; +} + +#endif /* __KSELFTEST_HARNESS_H */ diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index 959273c3a52e..693616651da5 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -11,15 +11,26 @@ TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES)) all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) +.ONESHELL: define RUN_TESTS - @for TEST in $(TEST_GEN_PROGS) $(TEST_PROGS); do \ + @test_num=`echo 0`; + @echo "TAP version 13"; + @for TEST in $(1); do \ BASENAME_TEST=`basename $$TEST`; \ - cd `dirname $$TEST`; (./$$BASENAME_TEST && echo "selftests: $$BASENAME_TEST [PASS]") || echo "selftests: $$BASENAME_TEST [FAIL]"; cd -;\ + test_num=`echo $$test_num+1 | bc`; \ + echo "selftests: $$BASENAME_TEST"; \ + echo "========================================"; \ + if [ ! -x $$BASENAME_TEST ]; then \ + echo "selftests: Warning: file $$BASENAME_TEST is not executable, correct this.";\ + echo "not ok 1..$$test_num selftests: $$BASENAME_TEST [FAIL]"; \ + else \ + cd `dirname $$TEST` > /dev/null; (./$$BASENAME_TEST && echo "ok 1..$$test_num selftests: $$BASENAME_TEST [PASS]") || echo "not ok 1..$$test_num selftests: $$BASENAME_TEST [FAIL]"; cd - > /dev/null;\ + fi; \ done; endef run_tests: all - $(RUN_TESTS) + $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_PROGS)) define INSTALL_RULE @if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)" != "X" ]; then \ diff --git a/tools/testing/selftests/lib/bitmap.sh b/tools/testing/selftests/lib/bitmap.sh index 2da187b6ddad..b073c22a3435 100755 --- a/tools/testing/selftests/lib/bitmap.sh +++ b/tools/testing/selftests/lib/bitmap.sh @@ -1,5 +1,9 @@ #!/bin/sh # Runs bitmap infrastructure tests using test_bitmap kernel module +if ! /sbin/modprobe -q -n test_bitmap; then + echo "bitmap: [SKIP]" + exit 77 +fi if /sbin/modprobe -q test_bitmap; then /sbin/modprobe -q -r test_bitmap diff --git a/tools/testing/selftests/lib/printf.sh b/tools/testing/selftests/lib/printf.sh index 4fdc70fe6980..cbf3b124bd94 100755 --- a/tools/testing/selftests/lib/printf.sh +++ b/tools/testing/selftests/lib/printf.sh @@ -1,5 +1,9 @@ #!/bin/sh # Runs printf infrastructure using test_printf kernel module +if ! /sbin/modprobe -q -n test_printf; then + echo "printf: [SKIP]" + exit 77 +fi if /sbin/modprobe -q test_printf; then /sbin/modprobe -q -r test_printf diff --git a/tools/testing/selftests/membarrier/membarrier_test.c b/tools/testing/selftests/membarrier/membarrier_test.c index 535f0fef4d0b..21399fcf1a59 100644 --- a/tools/testing/selftests/membarrier/membarrier_test.c +++ b/tools/testing/selftests/membarrier/membarrier_test.c @@ -7,56 +7,63 @@ #include "../kselftest.h" -enum test_membarrier_status { - TEST_MEMBARRIER_PASS = 0, - TEST_MEMBARRIER_FAIL, - TEST_MEMBARRIER_SKIP, -}; - static int sys_membarrier(int cmd, int flags) { return syscall(__NR_membarrier, cmd, flags); } -static enum test_membarrier_status test_membarrier_cmd_fail(void) +static int test_membarrier_cmd_fail(void) { int cmd = -1, flags = 0; if (sys_membarrier(cmd, flags) != -1) { - printf("membarrier: Wrong command should fail but passed.\n"); - return TEST_MEMBARRIER_FAIL; + ksft_exit_fail_msg( + "sys membarrier invalid command test: command = %d, flags = %d. Should fail, but passed\n", + cmd, flags); } - return TEST_MEMBARRIER_PASS; + + ksft_test_result_pass( + "sys membarrier invalid command test: command = %d, flags = %d. Failed as expected\n", + cmd, flags); + return 0; } -static enum test_membarrier_status test_membarrier_flags_fail(void) +static int test_membarrier_flags_fail(void) { int cmd = MEMBARRIER_CMD_QUERY, flags = 1; if (sys_membarrier(cmd, flags) != -1) { - printf("membarrier: Wrong flags should fail but passed.\n"); - return TEST_MEMBARRIER_FAIL; + ksft_exit_fail_msg( + "sys membarrier MEMBARRIER_CMD_QUERY invalid flags test: flags = %d. Should fail, but passed\n", + flags); } - return TEST_MEMBARRIER_PASS; + + ksft_test_result_pass( + "sys membarrier MEMBARRIER_CMD_QUERY invalid flags test: flags = %d. Failed as expected\n", + flags); + return 0; } -static enum test_membarrier_status test_membarrier_success(void) +static int test_membarrier_success(void) { int cmd = MEMBARRIER_CMD_SHARED, flags = 0; + const char *test_name = "sys membarrier MEMBARRIER_CMD_SHARED\n"; if (sys_membarrier(cmd, flags) != 0) { - printf("membarrier: Executing MEMBARRIER_CMD_SHARED failed. %s.\n", - strerror(errno)); - return TEST_MEMBARRIER_FAIL; + ksft_exit_fail_msg( + "sys membarrier MEMBARRIER_CMD_SHARED test: flags = %d\n", + flags); } - printf("membarrier: MEMBARRIER_CMD_SHARED success.\n"); - return TEST_MEMBARRIER_PASS; + ksft_test_result_pass( + "sys membarrier MEMBARRIER_CMD_SHARED test: flags = %d\n", + flags); + return 0; } -static enum test_membarrier_status test_membarrier(void) +static int test_membarrier(void) { - enum test_membarrier_status status; + int status; status = test_membarrier_cmd_fail(); if (status) @@ -67,52 +74,38 @@ static enum test_membarrier_status test_membarrier(void) status = test_membarrier_success(); if (status) return status; - return TEST_MEMBARRIER_PASS; + return 0; } -static enum test_membarrier_status test_membarrier_query(void) +static int test_membarrier_query(void) { int flags = 0, ret; - printf("membarrier MEMBARRIER_CMD_QUERY "); ret = sys_membarrier(MEMBARRIER_CMD_QUERY, flags); if (ret < 0) { - printf("failed. %s.\n", strerror(errno)); - switch (errno) { - case ENOSYS: + if (errno == ENOSYS) { /* * It is valid to build a kernel with * CONFIG_MEMBARRIER=n. However, this skips the tests. */ - return TEST_MEMBARRIER_SKIP; - case EINVAL: - default: - return TEST_MEMBARRIER_FAIL; + ksft_exit_skip( + "sys membarrier (CONFIG_MEMBARRIER) is disabled.\n"); } + ksft_exit_fail_msg("sys_membarrier() failed\n"); } - if (!(ret & MEMBARRIER_CMD_SHARED)) { - printf("command MEMBARRIER_CMD_SHARED is not supported.\n"); - return TEST_MEMBARRIER_FAIL; - } - printf("syscall available.\n"); - return TEST_MEMBARRIER_PASS; + if (!(ret & MEMBARRIER_CMD_SHARED)) + ksft_exit_fail_msg("sys_membarrier is not supported.\n"); + + ksft_test_result_pass("sys_membarrier available\n"); + return 0; } int main(int argc, char **argv) { - switch (test_membarrier_query()) { - case TEST_MEMBARRIER_FAIL: - return ksft_exit_fail(); - case TEST_MEMBARRIER_SKIP: - return ksft_exit_skip(); - } - switch (test_membarrier()) { - case TEST_MEMBARRIER_FAIL: - return ksft_exit_fail(); - case TEST_MEMBARRIER_SKIP: - return ksft_exit_skip(); - } + ksft_print_header(); + + test_membarrier_query(); + test_membarrier(); - printf("membarrier: tests done!\n"); - return ksft_exit_pass(); + ksft_exit_pass(); } diff --git a/tools/testing/selftests/memfd/Makefile b/tools/testing/selftests/memfd/Makefile index 79891d033de1..bc9d02d615da 100644 --- a/tools/testing/selftests/memfd/Makefile +++ b/tools/testing/selftests/memfd/Makefile @@ -3,11 +3,11 @@ CFLAGS += -I../../../../include/uapi/ CFLAGS += -I../../../../include/ CFLAGS += -I../../../../usr/include/ -TEST_PROGS := run_fuse_test.sh +TEST_PROGS := run_tests.sh TEST_GEN_FILES := memfd_test fuse_mnt fuse_test fuse_mnt.o: CFLAGS += $(shell pkg-config fuse --cflags) -fuse_mnt: LDFLAGS += $(shell pkg-config fuse --libs) include ../lib.mk +$(OUTPUT)/fuse_mnt: LDLIBS += $(shell pkg-config fuse --libs) diff --git a/tools/testing/selftests/memfd/fuse_test.c b/tools/testing/selftests/memfd/fuse_test.c index 67908b18f035..7f3617274bf5 100644 --- a/tools/testing/selftests/memfd/fuse_test.c +++ b/tools/testing/selftests/memfd/fuse_test.c @@ -33,7 +33,7 @@ #include <unistd.h> #define MFD_DEF_SIZE 8192 -#define STACK_SIZE 65535 +#define STACK_SIZE 65536 static int sys_memfd_create(const char *name, unsigned int flags) diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c index 26546892cd54..f94c6d1fb46f 100644 --- a/tools/testing/selftests/memfd/memfd_test.c +++ b/tools/testing/selftests/memfd/memfd_test.c @@ -18,12 +18,48 @@ #include <sys/wait.h> #include <unistd.h> +#define MEMFD_STR "memfd:" +#define SHARED_FT_STR "(shared file-table)" + #define MFD_DEF_SIZE 8192 #define STACK_SIZE 65536 +/* + * Default is not to test hugetlbfs + */ +static int hugetlbfs_test; +static size_t mfd_def_size = MFD_DEF_SIZE; + +/* + * Copied from mlock2-tests.c + */ +static unsigned long default_huge_page_size(void) +{ + unsigned long hps = 0; + char *line = NULL; + size_t linelen = 0; + FILE *f = fopen("/proc/meminfo", "r"); + + if (!f) + return 0; + while (getline(&line, &linelen, f) > 0) { + if (sscanf(line, "Hugepagesize: %lu kB", &hps) == 1) { + hps <<= 10; + break; + } + } + + free(line); + fclose(f); + return hps; +} + static int sys_memfd_create(const char *name, unsigned int flags) { + if (hugetlbfs_test) + flags |= MFD_HUGETLB; + return syscall(__NR_memfd_create, name, flags); } @@ -150,7 +186,7 @@ static void *mfd_assert_mmap_shared(int fd) void *p; p = mmap(NULL, - MFD_DEF_SIZE, + mfd_def_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, @@ -168,7 +204,7 @@ static void *mfd_assert_mmap_private(int fd) void *p; p = mmap(NULL, - MFD_DEF_SIZE, + mfd_def_size, PROT_READ, MAP_PRIVATE, fd, @@ -223,7 +259,7 @@ static void mfd_assert_read(int fd) /* verify PROT_READ *is* allowed */ p = mmap(NULL, - MFD_DEF_SIZE, + mfd_def_size, PROT_READ, MAP_PRIVATE, fd, @@ -232,11 +268,11 @@ static void mfd_assert_read(int fd) printf("mmap() failed: %m\n"); abort(); } - munmap(p, MFD_DEF_SIZE); + munmap(p, mfd_def_size); /* verify MAP_PRIVATE is *always* allowed (even writable) */ p = mmap(NULL, - MFD_DEF_SIZE, + mfd_def_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, @@ -245,7 +281,7 @@ static void mfd_assert_read(int fd) printf("mmap() failed: %m\n"); abort(); } - munmap(p, MFD_DEF_SIZE); + munmap(p, mfd_def_size); } static void mfd_assert_write(int fd) @@ -254,16 +290,22 @@ static void mfd_assert_write(int fd) void *p; int r; - /* verify write() succeeds */ - l = write(fd, "\0\0\0\0", 4); - if (l != 4) { - printf("write() failed: %m\n"); - abort(); + /* + * huegtlbfs does not support write, but we want to + * verify everything else here. + */ + if (!hugetlbfs_test) { + /* verify write() succeeds */ + l = write(fd, "\0\0\0\0", 4); + if (l != 4) { + printf("write() failed: %m\n"); + abort(); + } } /* verify PROT_READ | PROT_WRITE is allowed */ p = mmap(NULL, - MFD_DEF_SIZE, + mfd_def_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, @@ -273,11 +315,11 @@ static void mfd_assert_write(int fd) abort(); } *(char *)p = 0; - munmap(p, MFD_DEF_SIZE); + munmap(p, mfd_def_size); /* verify PROT_WRITE is allowed */ p = mmap(NULL, - MFD_DEF_SIZE, + mfd_def_size, PROT_WRITE, MAP_SHARED, fd, @@ -287,12 +329,12 @@ static void mfd_assert_write(int fd) abort(); } *(char *)p = 0; - munmap(p, MFD_DEF_SIZE); + munmap(p, mfd_def_size); /* verify PROT_READ with MAP_SHARED is allowed and a following * mprotect(PROT_WRITE) allows writing */ p = mmap(NULL, - MFD_DEF_SIZE, + mfd_def_size, PROT_READ, MAP_SHARED, fd, @@ -302,20 +344,20 @@ static void mfd_assert_write(int fd) abort(); } - r = mprotect(p, MFD_DEF_SIZE, PROT_READ | PROT_WRITE); + r = mprotect(p, mfd_def_size, PROT_READ | PROT_WRITE); if (r < 0) { printf("mprotect() failed: %m\n"); abort(); } *(char *)p = 0; - munmap(p, MFD_DEF_SIZE); + munmap(p, mfd_def_size); /* verify PUNCH_HOLE works */ r = fallocate(fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0, - MFD_DEF_SIZE); + mfd_def_size); if (r < 0) { printf("fallocate(PUNCH_HOLE) failed: %m\n"); abort(); @@ -337,7 +379,7 @@ static void mfd_fail_write(int fd) /* verify PROT_READ | PROT_WRITE is not allowed */ p = mmap(NULL, - MFD_DEF_SIZE, + mfd_def_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, @@ -349,7 +391,7 @@ static void mfd_fail_write(int fd) /* verify PROT_WRITE is not allowed */ p = mmap(NULL, - MFD_DEF_SIZE, + mfd_def_size, PROT_WRITE, MAP_SHARED, fd, @@ -362,13 +404,13 @@ static void mfd_fail_write(int fd) /* Verify PROT_READ with MAP_SHARED with a following mprotect is not * allowed. Note that for r/w the kernel already prevents the mmap. */ p = mmap(NULL, - MFD_DEF_SIZE, + mfd_def_size, PROT_READ, MAP_SHARED, fd, 0); if (p != MAP_FAILED) { - r = mprotect(p, MFD_DEF_SIZE, PROT_READ | PROT_WRITE); + r = mprotect(p, mfd_def_size, PROT_READ | PROT_WRITE); if (r >= 0) { printf("mmap()+mprotect() didn't fail as expected\n"); abort(); @@ -379,7 +421,7 @@ static void mfd_fail_write(int fd) r = fallocate(fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0, - MFD_DEF_SIZE); + mfd_def_size); if (r >= 0) { printf("fallocate(PUNCH_HOLE) didn't fail as expected\n"); abort(); @@ -390,13 +432,13 @@ static void mfd_assert_shrink(int fd) { int r, fd2; - r = ftruncate(fd, MFD_DEF_SIZE / 2); + r = ftruncate(fd, mfd_def_size / 2); if (r < 0) { printf("ftruncate(SHRINK) failed: %m\n"); abort(); } - mfd_assert_size(fd, MFD_DEF_SIZE / 2); + mfd_assert_size(fd, mfd_def_size / 2); fd2 = mfd_assert_open(fd, O_RDWR | O_CREAT | O_TRUNC, @@ -410,7 +452,7 @@ static void mfd_fail_shrink(int fd) { int r; - r = ftruncate(fd, MFD_DEF_SIZE / 2); + r = ftruncate(fd, mfd_def_size / 2); if (r >= 0) { printf("ftruncate(SHRINK) didn't fail as expected\n"); abort(); @@ -425,31 +467,31 @@ static void mfd_assert_grow(int fd) { int r; - r = ftruncate(fd, MFD_DEF_SIZE * 2); + r = ftruncate(fd, mfd_def_size * 2); if (r < 0) { printf("ftruncate(GROW) failed: %m\n"); abort(); } - mfd_assert_size(fd, MFD_DEF_SIZE * 2); + mfd_assert_size(fd, mfd_def_size * 2); r = fallocate(fd, 0, 0, - MFD_DEF_SIZE * 4); + mfd_def_size * 4); if (r < 0) { printf("fallocate(ALLOC) failed: %m\n"); abort(); } - mfd_assert_size(fd, MFD_DEF_SIZE * 4); + mfd_assert_size(fd, mfd_def_size * 4); } static void mfd_fail_grow(int fd) { int r; - r = ftruncate(fd, MFD_DEF_SIZE * 2); + r = ftruncate(fd, mfd_def_size * 2); if (r >= 0) { printf("ftruncate(GROW) didn't fail as expected\n"); abort(); @@ -458,7 +500,7 @@ static void mfd_fail_grow(int fd) r = fallocate(fd, 0, 0, - MFD_DEF_SIZE * 4); + mfd_def_size * 4); if (r >= 0) { printf("fallocate(ALLOC) didn't fail as expected\n"); abort(); @@ -467,25 +509,37 @@ static void mfd_fail_grow(int fd) static void mfd_assert_grow_write(int fd) { - static char buf[MFD_DEF_SIZE * 8]; + static char *buf; ssize_t l; - l = pwrite(fd, buf, sizeof(buf), 0); - if (l != sizeof(buf)) { + buf = malloc(mfd_def_size * 8); + if (!buf) { + printf("malloc(%d) failed: %m\n", mfd_def_size * 8); + abort(); + } + + l = pwrite(fd, buf, mfd_def_size * 8, 0); + if (l != (mfd_def_size * 8)) { printf("pwrite() failed: %m\n"); abort(); } - mfd_assert_size(fd, MFD_DEF_SIZE * 8); + mfd_assert_size(fd, mfd_def_size * 8); } static void mfd_fail_grow_write(int fd) { - static char buf[MFD_DEF_SIZE * 8]; + static char *buf; ssize_t l; - l = pwrite(fd, buf, sizeof(buf), 0); - if (l == sizeof(buf)) { + buf = malloc(mfd_def_size * 8); + if (!buf) { + printf("malloc(%d) failed: %m\n", mfd_def_size * 8); + abort(); + } + + l = pwrite(fd, buf, mfd_def_size * 8, 0); + if (l == (mfd_def_size * 8)) { printf("pwrite() didn't fail as expected\n"); abort(); } @@ -543,6 +597,8 @@ static void test_create(void) char buf[2048]; int fd; + printf("%s CREATE\n", MEMFD_STR); + /* test NULL name */ mfd_fail_new(NULL, 0); @@ -570,13 +626,18 @@ static void test_create(void) fd = mfd_assert_new("", 0, MFD_CLOEXEC); close(fd); - /* verify MFD_ALLOW_SEALING is allowed */ - fd = mfd_assert_new("", 0, MFD_ALLOW_SEALING); - close(fd); - - /* verify MFD_ALLOW_SEALING | MFD_CLOEXEC is allowed */ - fd = mfd_assert_new("", 0, MFD_ALLOW_SEALING | MFD_CLOEXEC); - close(fd); + if (!hugetlbfs_test) { + /* verify MFD_ALLOW_SEALING is allowed */ + fd = mfd_assert_new("", 0, MFD_ALLOW_SEALING); + close(fd); + + /* verify MFD_ALLOW_SEALING | MFD_CLOEXEC is allowed */ + fd = mfd_assert_new("", 0, MFD_ALLOW_SEALING | MFD_CLOEXEC); + close(fd); + } else { + /* sealing is not supported on hugetlbfs */ + mfd_fail_new("", MFD_ALLOW_SEALING); + } } /* @@ -587,8 +648,14 @@ static void test_basic(void) { int fd; + /* hugetlbfs does not contain sealing support */ + if (hugetlbfs_test) + return; + + printf("%s BASIC\n", MEMFD_STR); + fd = mfd_assert_new("kern_memfd_basic", - MFD_DEF_SIZE, + mfd_def_size, MFD_CLOEXEC | MFD_ALLOW_SEALING); /* add basic seals */ @@ -619,7 +686,7 @@ static void test_basic(void) /* verify sealing does not work without MFD_ALLOW_SEALING */ fd = mfd_assert_new("kern_memfd_basic", - MFD_DEF_SIZE, + mfd_def_size, MFD_CLOEXEC); mfd_assert_has_seals(fd, F_SEAL_SEAL); mfd_fail_add_seals(fd, F_SEAL_SHRINK | @@ -630,6 +697,28 @@ static void test_basic(void) } /* + * hugetlbfs doesn't support seals or write, so just verify grow and shrink + * on a hugetlbfs file created via memfd_create. + */ +static void test_hugetlbfs_grow_shrink(void) +{ + int fd; + + printf("%s HUGETLBFS-GROW-SHRINK\n", MEMFD_STR); + + fd = mfd_assert_new("kern_memfd_seal_write", + mfd_def_size, + MFD_CLOEXEC); + + mfd_assert_read(fd); + mfd_assert_write(fd); + mfd_assert_shrink(fd); + mfd_assert_grow(fd); + + close(fd); +} + +/* * Test SEAL_WRITE * Test whether SEAL_WRITE actually prevents modifications. */ @@ -637,8 +726,17 @@ static void test_seal_write(void) { int fd; + /* + * hugetlbfs does not contain sealing or write support. Just test + * basic grow and shrink via test_hugetlbfs_grow_shrink. + */ + if (hugetlbfs_test) + return test_hugetlbfs_grow_shrink(); + + printf("%s SEAL-WRITE\n", MEMFD_STR); + fd = mfd_assert_new("kern_memfd_seal_write", - MFD_DEF_SIZE, + mfd_def_size, MFD_CLOEXEC | MFD_ALLOW_SEALING); mfd_assert_has_seals(fd, 0); mfd_assert_add_seals(fd, F_SEAL_WRITE); @@ -661,8 +759,14 @@ static void test_seal_shrink(void) { int fd; + /* hugetlbfs does not contain sealing support */ + if (hugetlbfs_test) + return; + + printf("%s SEAL-SHRINK\n", MEMFD_STR); + fd = mfd_assert_new("kern_memfd_seal_shrink", - MFD_DEF_SIZE, + mfd_def_size, MFD_CLOEXEC | MFD_ALLOW_SEALING); mfd_assert_has_seals(fd, 0); mfd_assert_add_seals(fd, F_SEAL_SHRINK); @@ -685,8 +789,14 @@ static void test_seal_grow(void) { int fd; + /* hugetlbfs does not contain sealing support */ + if (hugetlbfs_test) + return; + + printf("%s SEAL-GROW\n", MEMFD_STR); + fd = mfd_assert_new("kern_memfd_seal_grow", - MFD_DEF_SIZE, + mfd_def_size, MFD_CLOEXEC | MFD_ALLOW_SEALING); mfd_assert_has_seals(fd, 0); mfd_assert_add_seals(fd, F_SEAL_GROW); @@ -709,8 +819,14 @@ static void test_seal_resize(void) { int fd; + /* hugetlbfs does not contain sealing support */ + if (hugetlbfs_test) + return; + + printf("%s SEAL-RESIZE\n", MEMFD_STR); + fd = mfd_assert_new("kern_memfd_seal_resize", - MFD_DEF_SIZE, + mfd_def_size, MFD_CLOEXEC | MFD_ALLOW_SEALING); mfd_assert_has_seals(fd, 0); mfd_assert_add_seals(fd, F_SEAL_SHRINK | F_SEAL_GROW); @@ -726,15 +842,52 @@ static void test_seal_resize(void) } /* + * hugetlbfs does not support seals. Basic test to dup the memfd created + * fd and perform some basic operations on it. + */ +static void hugetlbfs_dup(char *b_suffix) +{ + int fd, fd2; + + printf("%s HUGETLBFS-DUP %s\n", MEMFD_STR, b_suffix); + + fd = mfd_assert_new("kern_memfd_share_dup", + mfd_def_size, + MFD_CLOEXEC); + + fd2 = mfd_assert_dup(fd); + + mfd_assert_read(fd); + mfd_assert_write(fd); + + mfd_assert_shrink(fd2); + mfd_assert_grow(fd2); + + close(fd2); + close(fd); +} + +/* * Test sharing via dup() * Test that seals are shared between dupped FDs and they're all equal. */ -static void test_share_dup(void) +static void test_share_dup(char *banner, char *b_suffix) { int fd, fd2; + /* + * hugetlbfs does not contain sealing support. Perform some + * basic testing on dup'ed fd instead via hugetlbfs_dup. + */ + if (hugetlbfs_test) { + hugetlbfs_dup(b_suffix); + return; + } + + printf("%s %s %s\n", MEMFD_STR, banner, b_suffix); + fd = mfd_assert_new("kern_memfd_share_dup", - MFD_DEF_SIZE, + mfd_def_size, MFD_CLOEXEC | MFD_ALLOW_SEALING); mfd_assert_has_seals(fd, 0); @@ -768,13 +921,19 @@ static void test_share_dup(void) * Test sealing with active mmap()s * Modifying seals is only allowed if no other mmap() refs exist. */ -static void test_share_mmap(void) +static void test_share_mmap(char *banner, char *b_suffix) { int fd; void *p; + /* hugetlbfs does not contain sealing support */ + if (hugetlbfs_test) + return; + + printf("%s %s %s\n", MEMFD_STR, banner, b_suffix); + fd = mfd_assert_new("kern_memfd_share_mmap", - MFD_DEF_SIZE, + mfd_def_size, MFD_CLOEXEC | MFD_ALLOW_SEALING); mfd_assert_has_seals(fd, 0); @@ -784,14 +943,40 @@ static void test_share_mmap(void) mfd_assert_has_seals(fd, 0); mfd_assert_add_seals(fd, F_SEAL_SHRINK); mfd_assert_has_seals(fd, F_SEAL_SHRINK); - munmap(p, MFD_DEF_SIZE); + munmap(p, mfd_def_size); /* readable ref allows sealing */ p = mfd_assert_mmap_private(fd); mfd_assert_add_seals(fd, F_SEAL_WRITE); mfd_assert_has_seals(fd, F_SEAL_WRITE | F_SEAL_SHRINK); - munmap(p, MFD_DEF_SIZE); + munmap(p, mfd_def_size); + + close(fd); +} + +/* + * Basic test to make sure we can open the hugetlbfs fd via /proc and + * perform some simple operations on it. + */ +static void hugetlbfs_proc_open(char *b_suffix) +{ + int fd, fd2; + + printf("%s HUGETLBFS-PROC-OPEN %s\n", MEMFD_STR, b_suffix); + fd = mfd_assert_new("kern_memfd_share_open", + mfd_def_size, + MFD_CLOEXEC); + + fd2 = mfd_assert_open(fd, O_RDWR, 0); + + mfd_assert_read(fd); + mfd_assert_write(fd); + + mfd_assert_shrink(fd2); + mfd_assert_grow(fd2); + + close(fd2); close(fd); } @@ -801,12 +986,23 @@ static void test_share_mmap(void) * This is *not* like dup(), but like a real separate open(). Make sure the * semantics are as expected and we correctly check for RDONLY / WRONLY / RDWR. */ -static void test_share_open(void) +static void test_share_open(char *banner, char *b_suffix) { int fd, fd2; + /* + * hugetlbfs does not contain sealing support. So test basic + * functionality of using /proc fd via hugetlbfs_proc_open + */ + if (hugetlbfs_test) { + hugetlbfs_proc_open(b_suffix); + return; + } + + printf("%s %s %s\n", MEMFD_STR, banner, b_suffix); + fd = mfd_assert_new("kern_memfd_share_open", - MFD_DEF_SIZE, + mfd_def_size, MFD_CLOEXEC | MFD_ALLOW_SEALING); mfd_assert_has_seals(fd, 0); @@ -841,13 +1037,19 @@ static void test_share_open(void) * Test sharing via fork() * Test whether seal-modifications work as expected with forked childs. */ -static void test_share_fork(void) +static void test_share_fork(char *banner, char *b_suffix) { int fd; pid_t pid; + /* hugetlbfs does not contain sealing support */ + if (hugetlbfs_test) + return; + + printf("%s %s %s\n", MEMFD_STR, banner, b_suffix); + fd = mfd_assert_new("kern_memfd_share_fork", - MFD_DEF_SIZE, + mfd_def_size, MFD_CLOEXEC | MFD_ALLOW_SEALING); mfd_assert_has_seals(fd, 0); @@ -870,40 +1072,40 @@ int main(int argc, char **argv) { pid_t pid; - printf("memfd: CREATE\n"); + if (argc == 2) { + if (!strcmp(argv[1], "hugetlbfs")) { + unsigned long hpage_size = default_huge_page_size(); + + if (!hpage_size) { + printf("Unable to determine huge page size\n"); + abort(); + } + + hugetlbfs_test = 1; + mfd_def_size = hpage_size * 2; + } + } + test_create(); - printf("memfd: BASIC\n"); test_basic(); - printf("memfd: SEAL-WRITE\n"); test_seal_write(); - printf("memfd: SEAL-SHRINK\n"); test_seal_shrink(); - printf("memfd: SEAL-GROW\n"); test_seal_grow(); - printf("memfd: SEAL-RESIZE\n"); test_seal_resize(); - printf("memfd: SHARE-DUP\n"); - test_share_dup(); - printf("memfd: SHARE-MMAP\n"); - test_share_mmap(); - printf("memfd: SHARE-OPEN\n"); - test_share_open(); - printf("memfd: SHARE-FORK\n"); - test_share_fork(); + test_share_dup("SHARE-DUP", ""); + test_share_mmap("SHARE-MMAP", ""); + test_share_open("SHARE-OPEN", ""); + test_share_fork("SHARE-FORK", ""); /* Run test-suite in a multi-threaded environment with a shared * file-table. */ pid = spawn_idle_thread(CLONE_FILES | CLONE_FS | CLONE_VM); - printf("memfd: SHARE-DUP (shared file-table)\n"); - test_share_dup(); - printf("memfd: SHARE-MMAP (shared file-table)\n"); - test_share_mmap(); - printf("memfd: SHARE-OPEN (shared file-table)\n"); - test_share_open(); - printf("memfd: SHARE-FORK (shared file-table)\n"); - test_share_fork(); + test_share_dup("SHARE-DUP", SHARED_FT_STR); + test_share_mmap("SHARE-MMAP", SHARED_FT_STR); + test_share_open("SHARE-OPEN", SHARED_FT_STR); + test_share_fork("SHARE-FORK", SHARED_FT_STR); join_idle_thread(pid); printf("memfd: DONE\n"); diff --git a/tools/testing/selftests/memfd/run_tests.sh b/tools/testing/selftests/memfd/run_tests.sh new file mode 100644 index 000000000000..daabb350697c --- /dev/null +++ b/tools/testing/selftests/memfd/run_tests.sh @@ -0,0 +1,69 @@ +#!/bin/bash +# please run as root + +# +# Normal tests requiring no special resources +# +./run_fuse_test.sh +./memfd_test + +# +# To test memfd_create with hugetlbfs, there needs to be hpages_test +# huge pages free. Attempt to allocate enough pages to test. +# +hpages_test=8 + +# +# Get count of free huge pages from /proc/meminfo +# +while read name size unit; do + if [ "$name" = "HugePages_Free:" ]; then + freepgs=$size + fi +done < /proc/meminfo + +# +# If not enough free huge pages for test, attempt to increase +# +if [ -n "$freepgs" ] && [ $freepgs -lt $hpages_test ]; then + nr_hugepgs=`cat /proc/sys/vm/nr_hugepages` + hpages_needed=`expr $hpages_test - $freepgs` + + echo 3 > /proc/sys/vm/drop_caches + echo $(( $hpages_needed + $nr_hugepgs )) > /proc/sys/vm/nr_hugepages + if [ $? -ne 0 ]; then + echo "Please run this test as root" + exit 1 + fi + while read name size unit; do + if [ "$name" = "HugePages_Free:" ]; then + freepgs=$size + fi + done < /proc/meminfo +fi + +# +# If still not enough huge pages available, exit. But, give back any huge +# pages potentially allocated above. +# +if [ $freepgs -lt $hpages_test ]; then + # nr_hugepgs non-zero only if we attempted to increase + if [ -n "$nr_hugepgs" ]; then + echo $nr_hugepgs > /proc/sys/vm/nr_hugepages + fi + printf "Not enough huge pages available (%d < %d)\n" \ + $freepgs $needpgs + exit 1 +fi + +# +# Run the hugetlbfs test +# +./memfd_test hugetlbfs + +# +# Give back any huge pages allocated for the test +# +if [ -n "$nr_hugepgs" ]; then + echo $nr_hugepgs > /proc/sys/vm/nr_hugepages +fi diff --git a/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh b/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh index 6cddde0b96f8..35025ce9ca66 100755 --- a/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh +++ b/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh @@ -22,6 +22,11 @@ prerequisite() echo $msg memory hotplug is not supported >&2 exit 0 fi + + if ! grep -q 1 $SYSFS/devices/system/memory/memory*/removable; then + echo $msg no hot-pluggable memory >&2 + exit 0 + fi } # @@ -39,7 +44,7 @@ hotpluggable_memory() done } -hotplaggable_offline_memory() +hotpluggable_offline_memory() { hotpluggable_memory offline } @@ -75,9 +80,12 @@ online_memory_expect_success() if ! online_memory $memory; then echo $FUNCNAME $memory: unexpected fail >&2 + return 1 elif ! memory_is_online $memory; then echo $FUNCNAME $memory: unexpected offline >&2 + return 1 fi + return 0 } online_memory_expect_fail() @@ -86,9 +94,12 @@ online_memory_expect_fail() if online_memory $memory 2> /dev/null; then echo $FUNCNAME $memory: unexpected success >&2 + return 1 elif ! memory_is_offline $memory; then echo $FUNCNAME $memory: unexpected online >&2 + return 1 fi + return 0 } offline_memory_expect_success() @@ -97,9 +108,12 @@ offline_memory_expect_success() if ! offline_memory $memory; then echo $FUNCNAME $memory: unexpected fail >&2 + return 1 elif ! memory_is_offline $memory; then echo $FUNCNAME $memory: unexpected offline >&2 + return 1 fi + return 0 } offline_memory_expect_fail() @@ -108,14 +122,18 @@ offline_memory_expect_fail() if offline_memory $memory 2> /dev/null; then echo $FUNCNAME $memory: unexpected success >&2 + return 1 elif ! memory_is_online $memory; then echo $FUNCNAME $memory: unexpected offline >&2 + return 1 fi + return 0 } error=-12 priority=0 ratio=10 +retval=0 while getopts e:hp:r: opt; do case $opt in @@ -131,6 +149,10 @@ while getopts e:hp:r: opt; do ;; r) ratio=$OPTARG + if [ "$ratio" -gt 100 ] || [ "$ratio" -lt 0 ]; then + echo "The percentage should be an integer within 0~100 range" + exit 1 + fi ;; esac done @@ -143,35 +165,58 @@ fi prerequisite echo "Test scope: $ratio% hotplug memory" -echo -e "\t online all hotplug memory in offline state" -echo -e "\t offline $ratio% hotplug memory in online state" -echo -e "\t online all hotplug memory in offline state" # # Online all hot-pluggable memory # -for memory in `hotplaggable_offline_memory`; do - echo offline-online $memory - online_memory_expect_success $memory -done +hotpluggable_num=`hotpluggable_offline_memory | wc -l` +echo -e "\t online all hot-pluggable memory in offline state:" +if [ "$hotpluggable_num" -gt 0 ]; then + for memory in `hotpluggable_offline_memory`; do + echo "offline->online memory$memory" + if ! online_memory_expect_success $memory; then + retval=1 + fi + done +else + echo -e "\t\t SKIPPED - no hot-pluggable memory in offline state" +fi # # Offline $ratio percent of hot-pluggable memory # +hotpluggable_num=`hotpluggable_online_memory | wc -l` +target=`echo "a=$hotpluggable_num*$ratio; if ( a%100 ) a/100+1 else a/100" | bc` +echo -e "\t offline $ratio% hot-pluggable memory in online state" +echo -e "\t trying to offline $target out of $hotpluggable_num memory block(s):" for memory in `hotpluggable_online_memory`; do - if [ $((RANDOM % 100)) -lt $ratio ]; then - echo online-offline $memory - offline_memory_expect_success $memory + if [ "$target" -gt 0 ]; then + echo "online->offline memory$memory" + if offline_memory_expect_success $memory; then + target=$(($target - 1)) + fi fi done +if [ "$target" -gt 0 ]; then + retval=1 + echo -e "\t\t FAILED - unable to offline some memory blocks, device busy?" +fi # # Online all hot-pluggable memory again # -for memory in `hotplaggable_offline_memory`; do - echo offline-online $memory - online_memory_expect_success $memory -done +hotpluggable_num=`hotpluggable_offline_memory | wc -l` +echo -e "\t online all hot-pluggable memory in offline state:" +if [ "$hotpluggable_num" -gt 0 ]; then + for memory in `hotpluggable_offline_memory`; do + echo "offline->online memory$memory" + if ! online_memory_expect_success $memory; then + retval=1 + fi + done +else + echo -e "\t\t SKIPPED - no hot-pluggable memory in offline state" +fi # # Test with memory notifier error injection @@ -189,15 +234,16 @@ prerequisite_extra() if [ ! -d "$DEBUGFS" ]; then echo $msg debugfs is not mounted >&2 - exit 0 + exit $retval fi if [ ! -d $NOTIFIER_ERR_INJECT_DIR ]; then echo $msg memory-notifier-error-inject module is not available >&2 - exit 0 + exit $retval fi } +echo -e "\t Test with memory notifier error injection" prerequisite_extra # @@ -214,7 +260,7 @@ done # Test memory hot-add error handling (offline => online) # echo $error > $NOTIFIER_ERR_INJECT_DIR/actions/MEM_GOING_ONLINE/error -for memory in `hotplaggable_offline_memory`; do +for memory in `hotpluggable_offline_memory`; do online_memory_expect_fail $memory done @@ -222,7 +268,7 @@ done # Online all hot-pluggable memory # echo 0 > $NOTIFIER_ERR_INJECT_DIR/actions/MEM_GOING_ONLINE/error -for memory in `hotplaggable_offline_memory`; do +for memory in `hotpluggable_offline_memory`; do online_memory_expect_success $memory done @@ -236,3 +282,5 @@ done echo 0 > $NOTIFIER_ERR_INJECT_DIR/actions/MEM_GOING_OFFLINE/error /sbin/modprobe -q -r memory-notifier-error-inject + +exit $retval diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index afe109e5508a..9801253e4802 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -1,3 +1,4 @@ +msg_zerocopy socket psock_fanout psock_tpacket diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 35cbb4cba410..de1f5772b878 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -3,13 +3,12 @@ CFLAGS = -Wall -Wl,--no-as-needed -O2 -g CFLAGS += -I../../../../usr/include/ -reuseport_bpf_numa: LDFLAGS += -lnuma - -TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh +TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh TEST_GEN_FILES = socket TEST_GEN_FILES += psock_fanout psock_tpacket TEST_GEN_FILES += reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa -TEST_GEN_FILES += reuseport_dualstack +TEST_GEN_FILES += reuseport_dualstack msg_zerocopy include ../lib.mk +$(OUTPUT)/reuseport_bpf_numa: LDFLAGS += -lnuma diff --git a/tools/testing/selftests/net/msg_zerocopy.c b/tools/testing/selftests/net/msg_zerocopy.c new file mode 100644 index 000000000000..40232af5b023 --- /dev/null +++ b/tools/testing/selftests/net/msg_zerocopy.c @@ -0,0 +1,697 @@ +/* Evaluate MSG_ZEROCOPY + * + * Send traffic between two processes over one of the supported + * protocols and modes: + * + * PF_INET/PF_INET6 + * - SOCK_STREAM + * - SOCK_DGRAM + * - SOCK_DGRAM with UDP_CORK + * - SOCK_RAW + * - SOCK_RAW with IP_HDRINCL + * + * PF_PACKET + * - SOCK_DGRAM + * - SOCK_RAW + * + * Start this program on two connected hosts, one in send mode and + * the other with option '-r' to put it in receiver mode. + * + * If zerocopy mode ('-z') is enabled, the sender will verify that + * the kernel queues completions on the error queue for all zerocopy + * transfers. + */ + +#define _GNU_SOURCE + +#include <arpa/inet.h> +#include <error.h> +#include <errno.h> +#include <limits.h> +#include <linux/errqueue.h> +#include <linux/if_packet.h> +#include <linux/ipv6.h> +#include <linux/socket.h> +#include <linux/sockios.h> +#include <net/ethernet.h> +#include <net/if.h> +#include <netinet/ip.h> +#include <netinet/ip6.h> +#include <netinet/tcp.h> +#include <netinet/udp.h> +#include <poll.h> +#include <sched.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdint.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> +#include <sys/socket.h> +#include <sys/stat.h> +#include <sys/time.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <unistd.h> + +#ifndef SO_EE_ORIGIN_ZEROCOPY +#define SO_EE_ORIGIN_ZEROCOPY SO_EE_ORIGIN_UPAGE +#endif + +#ifndef SO_ZEROCOPY +#define SO_ZEROCOPY 60 +#endif + +#ifndef SO_EE_CODE_ZEROCOPY_COPIED +#define SO_EE_CODE_ZEROCOPY_COPIED 1 +#endif + +#ifndef MSG_ZEROCOPY +#define MSG_ZEROCOPY 0x4000000 +#endif + +static int cfg_cork; +static bool cfg_cork_mixed; +static int cfg_cpu = -1; /* default: pin to last cpu */ +static int cfg_family = PF_UNSPEC; +static int cfg_ifindex = 1; +static int cfg_payload_len; +static int cfg_port = 8000; +static bool cfg_rx; +static int cfg_runtime_ms = 4200; +static int cfg_verbose; +static int cfg_waittime_ms = 500; +static bool cfg_zerocopy; + +static socklen_t cfg_alen; +static struct sockaddr_storage cfg_dst_addr; +static struct sockaddr_storage cfg_src_addr; + +static char payload[IP_MAXPACKET]; +static long packets, bytes, completions, expected_completions; +static int zerocopied = -1; +static uint32_t next_completion; + +static unsigned long gettimeofday_ms(void) +{ + struct timeval tv; + + gettimeofday(&tv, NULL); + return (tv.tv_sec * 1000) + (tv.tv_usec / 1000); +} + +static uint16_t get_ip_csum(const uint16_t *start, int num_words) +{ + unsigned long sum = 0; + int i; + + for (i = 0; i < num_words; i++) + sum += start[i]; + + while (sum >> 16) + sum = (sum & 0xFFFF) + (sum >> 16); + + return ~sum; +} + +static int do_setcpu(int cpu) +{ + cpu_set_t mask; + + CPU_ZERO(&mask); + CPU_SET(cpu, &mask); + if (sched_setaffinity(0, sizeof(mask), &mask)) + error(1, 0, "setaffinity %d", cpu); + + if (cfg_verbose) + fprintf(stderr, "cpu: %u\n", cpu); + + return 0; +} + +static void do_setsockopt(int fd, int level, int optname, int val) +{ + if (setsockopt(fd, level, optname, &val, sizeof(val))) + error(1, errno, "setsockopt %d.%d: %d", level, optname, val); +} + +static int do_poll(int fd, int events) +{ + struct pollfd pfd; + int ret; + + pfd.events = events; + pfd.revents = 0; + pfd.fd = fd; + + ret = poll(&pfd, 1, cfg_waittime_ms); + if (ret == -1) + error(1, errno, "poll"); + + return ret && (pfd.revents & events); +} + +static int do_accept(int fd) +{ + int fda = fd; + + fd = accept(fda, NULL, NULL); + if (fd == -1) + error(1, errno, "accept"); + if (close(fda)) + error(1, errno, "close listen sock"); + + return fd; +} + +static bool do_sendmsg(int fd, struct msghdr *msg, bool do_zerocopy) +{ + int ret, len, i, flags; + + len = 0; + for (i = 0; i < msg->msg_iovlen; i++) + len += msg->msg_iov[i].iov_len; + + flags = MSG_DONTWAIT; + if (do_zerocopy) + flags |= MSG_ZEROCOPY; + + ret = sendmsg(fd, msg, flags); + if (ret == -1 && errno == EAGAIN) + return false; + if (ret == -1) + error(1, errno, "send"); + if (cfg_verbose && ret != len) + fprintf(stderr, "send: ret=%u != %u\n", ret, len); + + if (len) { + packets++; + bytes += ret; + if (do_zerocopy && ret) + expected_completions++; + } + + return true; +} + +static void do_sendmsg_corked(int fd, struct msghdr *msg) +{ + bool do_zerocopy = cfg_zerocopy; + int i, payload_len, extra_len; + + /* split up the packet. for non-multiple, make first buffer longer */ + payload_len = cfg_payload_len / cfg_cork; + extra_len = cfg_payload_len - (cfg_cork * payload_len); + + do_setsockopt(fd, IPPROTO_UDP, UDP_CORK, 1); + + for (i = 0; i < cfg_cork; i++) { + + /* in mixed-frags mode, alternate zerocopy and copy frags + * start with non-zerocopy, to ensure attach later works + */ + if (cfg_cork_mixed) + do_zerocopy = (i & 1); + + msg->msg_iov[0].iov_len = payload_len + extra_len; + extra_len = 0; + + do_sendmsg(fd, msg, do_zerocopy); + } + + do_setsockopt(fd, IPPROTO_UDP, UDP_CORK, 0); +} + +static int setup_iph(struct iphdr *iph, uint16_t payload_len) +{ + struct sockaddr_in *daddr = (void *) &cfg_dst_addr; + struct sockaddr_in *saddr = (void *) &cfg_src_addr; + + memset(iph, 0, sizeof(*iph)); + + iph->version = 4; + iph->tos = 0; + iph->ihl = 5; + iph->ttl = 2; + iph->saddr = saddr->sin_addr.s_addr; + iph->daddr = daddr->sin_addr.s_addr; + iph->protocol = IPPROTO_EGP; + iph->tot_len = htons(sizeof(*iph) + payload_len); + iph->check = get_ip_csum((void *) iph, iph->ihl << 1); + + return sizeof(*iph); +} + +static int setup_ip6h(struct ipv6hdr *ip6h, uint16_t payload_len) +{ + struct sockaddr_in6 *daddr = (void *) &cfg_dst_addr; + struct sockaddr_in6 *saddr = (void *) &cfg_src_addr; + + memset(ip6h, 0, sizeof(*ip6h)); + + ip6h->version = 6; + ip6h->payload_len = htons(payload_len); + ip6h->nexthdr = IPPROTO_EGP; + ip6h->hop_limit = 2; + ip6h->saddr = saddr->sin6_addr; + ip6h->daddr = daddr->sin6_addr; + + return sizeof(*ip6h); +} + +static void setup_sockaddr(int domain, const char *str_addr, void *sockaddr) +{ + struct sockaddr_in6 *addr6 = (void *) sockaddr; + struct sockaddr_in *addr4 = (void *) sockaddr; + + switch (domain) { + case PF_INET: + addr4->sin_family = AF_INET; + addr4->sin_port = htons(cfg_port); + if (inet_pton(AF_INET, str_addr, &(addr4->sin_addr)) != 1) + error(1, 0, "ipv4 parse error: %s", str_addr); + break; + case PF_INET6: + addr6->sin6_family = AF_INET6; + addr6->sin6_port = htons(cfg_port); + if (inet_pton(AF_INET6, str_addr, &(addr6->sin6_addr)) != 1) + error(1, 0, "ipv6 parse error: %s", str_addr); + break; + default: + error(1, 0, "illegal domain"); + } +} + +static int do_setup_tx(int domain, int type, int protocol) +{ + int fd; + + fd = socket(domain, type, protocol); + if (fd == -1) + error(1, errno, "socket t"); + + do_setsockopt(fd, SOL_SOCKET, SO_SNDBUF, 1 << 21); + if (cfg_zerocopy) + do_setsockopt(fd, SOL_SOCKET, SO_ZEROCOPY, 1); + + if (domain != PF_PACKET) + if (connect(fd, (void *) &cfg_dst_addr, cfg_alen)) + error(1, errno, "connect"); + + return fd; +} + +static bool do_recv_completion(int fd) +{ + struct sock_extended_err *serr; + struct msghdr msg = {}; + struct cmsghdr *cm; + uint32_t hi, lo, range; + int ret, zerocopy; + char control[100]; + + msg.msg_control = control; + msg.msg_controllen = sizeof(control); + + ret = recvmsg(fd, &msg, MSG_ERRQUEUE); + if (ret == -1 && errno == EAGAIN) + return false; + if (ret == -1) + error(1, errno, "recvmsg notification"); + if (msg.msg_flags & MSG_CTRUNC) + error(1, errno, "recvmsg notification: truncated"); + + cm = CMSG_FIRSTHDR(&msg); + if (!cm) + error(1, 0, "cmsg: no cmsg"); + if (!((cm->cmsg_level == SOL_IP && cm->cmsg_type == IP_RECVERR) || + (cm->cmsg_level == SOL_IPV6 && cm->cmsg_type == IPV6_RECVERR) || + (cm->cmsg_level == SOL_PACKET && cm->cmsg_type == PACKET_TX_TIMESTAMP))) + error(1, 0, "serr: wrong type: %d.%d", + cm->cmsg_level, cm->cmsg_type); + + serr = (void *) CMSG_DATA(cm); + if (serr->ee_origin != SO_EE_ORIGIN_ZEROCOPY) + error(1, 0, "serr: wrong origin: %u", serr->ee_origin); + if (serr->ee_errno != 0) + error(1, 0, "serr: wrong error code: %u", serr->ee_errno); + + hi = serr->ee_data; + lo = serr->ee_info; + range = hi - lo + 1; + + /* Detect notification gaps. These should not happen often, if at all. + * Gaps can occur due to drops, reordering and retransmissions. + */ + if (lo != next_completion) + fprintf(stderr, "gap: %u..%u does not append to %u\n", + lo, hi, next_completion); + next_completion = hi + 1; + + zerocopy = !(serr->ee_code & SO_EE_CODE_ZEROCOPY_COPIED); + if (zerocopied == -1) + zerocopied = zerocopy; + else if (zerocopied != zerocopy) { + fprintf(stderr, "serr: inconsistent\n"); + zerocopied = zerocopy; + } + + if (cfg_verbose >= 2) + fprintf(stderr, "completed: %u (h=%u l=%u)\n", + range, hi, lo); + + completions += range; + return true; +} + +/* Read all outstanding messages on the errqueue */ +static void do_recv_completions(int fd) +{ + while (do_recv_completion(fd)) {} +} + +/* Wait for all remaining completions on the errqueue */ +static void do_recv_remaining_completions(int fd) +{ + int64_t tstop = gettimeofday_ms() + cfg_waittime_ms; + + while (completions < expected_completions && + gettimeofday_ms() < tstop) { + if (do_poll(fd, POLLERR)) + do_recv_completions(fd); + } + + if (completions < expected_completions) + fprintf(stderr, "missing notifications: %lu < %lu\n", + completions, expected_completions); +} + +static void do_tx(int domain, int type, int protocol) +{ + struct iovec iov[3] = { {0} }; + struct sockaddr_ll laddr; + struct msghdr msg = {0}; + struct ethhdr eth; + union { + struct ipv6hdr ip6h; + struct iphdr iph; + } nh; + uint64_t tstop; + int fd; + + fd = do_setup_tx(domain, type, protocol); + + if (domain == PF_PACKET) { + uint16_t proto = cfg_family == PF_INET ? ETH_P_IP : ETH_P_IPV6; + + /* sock_raw passes ll header as data */ + if (type == SOCK_RAW) { + memset(eth.h_dest, 0x06, ETH_ALEN); + memset(eth.h_source, 0x02, ETH_ALEN); + eth.h_proto = htons(proto); + iov[0].iov_base = ð + iov[0].iov_len = sizeof(eth); + msg.msg_iovlen++; + } + + /* both sock_raw and sock_dgram expect name */ + memset(&laddr, 0, sizeof(laddr)); + laddr.sll_family = AF_PACKET; + laddr.sll_ifindex = cfg_ifindex; + laddr.sll_protocol = htons(proto); + laddr.sll_halen = ETH_ALEN; + + memset(laddr.sll_addr, 0x06, ETH_ALEN); + + msg.msg_name = &laddr; + msg.msg_namelen = sizeof(laddr); + } + + /* packet and raw sockets with hdrincl must pass network header */ + if (domain == PF_PACKET || protocol == IPPROTO_RAW) { + if (cfg_family == PF_INET) + iov[1].iov_len = setup_iph(&nh.iph, cfg_payload_len); + else + iov[1].iov_len = setup_ip6h(&nh.ip6h, cfg_payload_len); + + iov[1].iov_base = (void *) &nh; + msg.msg_iovlen++; + } + + iov[2].iov_base = payload; + iov[2].iov_len = cfg_payload_len; + msg.msg_iovlen++; + msg.msg_iov = &iov[3 - msg.msg_iovlen]; + + tstop = gettimeofday_ms() + cfg_runtime_ms; + do { + if (cfg_cork) + do_sendmsg_corked(fd, &msg); + else + do_sendmsg(fd, &msg, cfg_zerocopy); + + while (!do_poll(fd, POLLOUT)) { + if (cfg_zerocopy) + do_recv_completions(fd); + } + + } while (gettimeofday_ms() < tstop); + + if (cfg_zerocopy) + do_recv_remaining_completions(fd); + + if (close(fd)) + error(1, errno, "close"); + + fprintf(stderr, "tx=%lu (%lu MB) txc=%lu zc=%c\n", + packets, bytes >> 20, completions, + zerocopied == 1 ? 'y' : 'n'); +} + +static int do_setup_rx(int domain, int type, int protocol) +{ + int fd; + + /* If tx over PF_PACKET, rx over PF_INET(6)/SOCK_RAW, + * to recv the only copy of the packet, not a clone + */ + if (domain == PF_PACKET) + error(1, 0, "Use PF_INET/SOCK_RAW to read"); + + if (type == SOCK_RAW && protocol == IPPROTO_RAW) + error(1, 0, "IPPROTO_RAW: not supported on Rx"); + + fd = socket(domain, type, protocol); + if (fd == -1) + error(1, errno, "socket r"); + + do_setsockopt(fd, SOL_SOCKET, SO_RCVBUF, 1 << 21); + do_setsockopt(fd, SOL_SOCKET, SO_RCVLOWAT, 1 << 16); + do_setsockopt(fd, SOL_SOCKET, SO_REUSEPORT, 1); + + if (bind(fd, (void *) &cfg_dst_addr, cfg_alen)) + error(1, errno, "bind"); + + if (type == SOCK_STREAM) { + if (listen(fd, 1)) + error(1, errno, "listen"); + fd = do_accept(fd); + } + + return fd; +} + +/* Flush all outstanding bytes for the tcp receive queue */ +static void do_flush_tcp(int fd) +{ + int ret; + + /* MSG_TRUNC flushes up to len bytes */ + ret = recv(fd, NULL, 1 << 21, MSG_TRUNC | MSG_DONTWAIT); + if (ret == -1 && errno == EAGAIN) + return; + if (ret == -1) + error(1, errno, "flush"); + if (!ret) + return; + + packets++; + bytes += ret; +} + +/* Flush all outstanding datagrams. Verify first few bytes of each. */ +static void do_flush_datagram(int fd, int type) +{ + int ret, off = 0; + char buf[64]; + + /* MSG_TRUNC will return full datagram length */ + ret = recv(fd, buf, sizeof(buf), MSG_DONTWAIT | MSG_TRUNC); + if (ret == -1 && errno == EAGAIN) + return; + + /* raw ipv4 return with header, raw ipv6 without */ + if (cfg_family == PF_INET && type == SOCK_RAW) { + off += sizeof(struct iphdr); + ret -= sizeof(struct iphdr); + } + + if (ret == -1) + error(1, errno, "recv"); + if (ret != cfg_payload_len) + error(1, 0, "recv: ret=%u != %u", ret, cfg_payload_len); + if (ret > sizeof(buf) - off) + ret = sizeof(buf) - off; + if (memcmp(buf + off, payload, ret)) + error(1, 0, "recv: data mismatch"); + + packets++; + bytes += cfg_payload_len; +} + +static void do_rx(int domain, int type, int protocol) +{ + uint64_t tstop; + int fd; + + fd = do_setup_rx(domain, type, protocol); + + tstop = gettimeofday_ms() + cfg_runtime_ms; + do { + if (type == SOCK_STREAM) + do_flush_tcp(fd); + else + do_flush_datagram(fd, type); + + do_poll(fd, POLLIN); + + } while (gettimeofday_ms() < tstop); + + if (close(fd)) + error(1, errno, "close"); + + fprintf(stderr, "rx=%lu (%lu MB)\n", packets, bytes >> 20); +} + +static void do_test(int domain, int type, int protocol) +{ + int i; + + if (cfg_cork && (domain == PF_PACKET || type != SOCK_DGRAM)) + error(1, 0, "can only cork udp sockets"); + + do_setcpu(cfg_cpu); + + for (i = 0; i < IP_MAXPACKET; i++) + payload[i] = 'a' + (i % 26); + + if (cfg_rx) + do_rx(domain, type, protocol); + else + do_tx(domain, type, protocol); +} + +static void usage(const char *filepath) +{ + error(1, 0, "Usage: %s [options] <test>", filepath); +} + +static void parse_opts(int argc, char **argv) +{ + const int max_payload_len = sizeof(payload) - + sizeof(struct ipv6hdr) - + sizeof(struct tcphdr) - + 40 /* max tcp options */; + int c; + + cfg_payload_len = max_payload_len; + + while ((c = getopt(argc, argv, "46c:C:D:i:mp:rs:S:t:vz")) != -1) { + switch (c) { + case '4': + if (cfg_family != PF_UNSPEC) + error(1, 0, "Pass one of -4 or -6"); + cfg_family = PF_INET; + cfg_alen = sizeof(struct sockaddr_in); + break; + case '6': + if (cfg_family != PF_UNSPEC) + error(1, 0, "Pass one of -4 or -6"); + cfg_family = PF_INET6; + cfg_alen = sizeof(struct sockaddr_in6); + break; + case 'c': + cfg_cork = strtol(optarg, NULL, 0); + break; + case 'C': + cfg_cpu = strtol(optarg, NULL, 0); + break; + case 'D': + setup_sockaddr(cfg_family, optarg, &cfg_dst_addr); + break; + case 'i': + cfg_ifindex = if_nametoindex(optarg); + if (cfg_ifindex == 0) + error(1, errno, "invalid iface: %s", optarg); + break; + case 'm': + cfg_cork_mixed = true; + break; + case 'p': + cfg_port = htons(strtoul(optarg, NULL, 0)); + break; + case 'r': + cfg_rx = true; + break; + case 's': + cfg_payload_len = strtoul(optarg, NULL, 0); + break; + case 'S': + setup_sockaddr(cfg_family, optarg, &cfg_src_addr); + break; + case 't': + cfg_runtime_ms = 200 + strtoul(optarg, NULL, 10) * 1000; + break; + case 'v': + cfg_verbose++; + break; + case 'z': + cfg_zerocopy = true; + break; + } + } + + if (cfg_payload_len > max_payload_len) + error(1, 0, "-s: payload exceeds max (%d)", max_payload_len); + if (cfg_cork_mixed && (!cfg_zerocopy || !cfg_cork)) + error(1, 0, "-m: cork_mixed requires corking and zerocopy"); + + if (optind != argc - 1) + usage(argv[0]); +} + +int main(int argc, char **argv) +{ + const char *cfg_test; + + parse_opts(argc, argv); + + cfg_test = argv[argc - 1]; + + if (!strcmp(cfg_test, "packet")) + do_test(PF_PACKET, SOCK_RAW, 0); + else if (!strcmp(cfg_test, "packet_dgram")) + do_test(PF_PACKET, SOCK_DGRAM, 0); + else if (!strcmp(cfg_test, "raw")) + do_test(cfg_family, SOCK_RAW, IPPROTO_EGP); + else if (!strcmp(cfg_test, "raw_hdrincl")) + do_test(cfg_family, SOCK_RAW, IPPROTO_RAW); + else if (!strcmp(cfg_test, "tcp")) + do_test(cfg_family, SOCK_STREAM, 0); + else if (!strcmp(cfg_test, "udp")) + do_test(cfg_family, SOCK_DGRAM, 0); + else + error(1, 0, "unknown cfg_test %s", cfg_test); + + return 0; +} diff --git a/tools/testing/selftests/net/msg_zerocopy.sh b/tools/testing/selftests/net/msg_zerocopy.sh new file mode 100755 index 000000000000..d571d213418d --- /dev/null +++ b/tools/testing/selftests/net/msg_zerocopy.sh @@ -0,0 +1,112 @@ +#!/bin/bash +# +# Send data between two processes across namespaces +# Run twice: once without and once with zerocopy + +set -e + +readonly DEV="veth0" +readonly DEV_MTU=65535 +readonly BIN="./msg_zerocopy" + +readonly RAND="$(mktemp -u XXXXXX)" +readonly NSPREFIX="ns-${RAND}" +readonly NS1="${NSPREFIX}1" +readonly NS2="${NSPREFIX}2" + +readonly SADDR4='192.168.1.1' +readonly DADDR4='192.168.1.2' +readonly SADDR6='fd::1' +readonly DADDR6='fd::2' + +readonly path_sysctl_mem="net.core.optmem_max" + +# Argument parsing +if [[ "$#" -lt "2" ]]; then + echo "Usage: $0 [4|6] [tcp|udp|raw|raw_hdrincl|packet|packet_dgram] <args>" + exit 1 +fi + +readonly IP="$1" +shift +readonly TXMODE="$1" +shift +readonly EXTRA_ARGS="$@" + +# Argument parsing: configure addresses +if [[ "${IP}" == "4" ]]; then + readonly SADDR="${SADDR4}" + readonly DADDR="${DADDR4}" +elif [[ "${IP}" == "6" ]]; then + readonly SADDR="${SADDR6}" + readonly DADDR="${DADDR6}" +else + echo "Invalid IP version ${IP}" + exit 1 +fi + +# Argument parsing: select receive mode +# +# This differs from send mode for +# - packet: use raw recv, because packet receives skb clones +# - raw_hdrinc: use raw recv, because hdrincl is a tx-only option +case "${TXMODE}" in +'packet' | 'packet_dgram' | 'raw_hdrincl') + RXMODE='raw' + ;; +*) + RXMODE="${TXMODE}" + ;; +esac + +# Start of state changes: install cleanup handler +save_sysctl_mem="$(sysctl -n ${path_sysctl_mem})" + +cleanup() { + ip netns del "${NS2}" + ip netns del "${NS1}" + sysctl -w -q "${path_sysctl_mem}=${save_sysctl_mem}" +} + +trap cleanup EXIT + +# Configure system settings +sysctl -w -q "${path_sysctl_mem}=1000000" + +# Create virtual ethernet pair between network namespaces +ip netns add "${NS1}" +ip netns add "${NS2}" + +ip link add "${DEV}" mtu "${DEV_MTU}" netns "${NS1}" type veth \ + peer name "${DEV}" mtu "${DEV_MTU}" netns "${NS2}" + +# Bring the devices up +ip -netns "${NS1}" link set "${DEV}" up +ip -netns "${NS2}" link set "${DEV}" up + +# Set fixed MAC addresses on the devices +ip -netns "${NS1}" link set dev "${DEV}" address 02:02:02:02:02:02 +ip -netns "${NS2}" link set dev "${DEV}" address 06:06:06:06:06:06 + +# Add fixed IP addresses to the devices +ip -netns "${NS1}" addr add 192.168.1.1/24 dev "${DEV}" +ip -netns "${NS2}" addr add 192.168.1.2/24 dev "${DEV}" +ip -netns "${NS1}" addr add fd::1/64 dev "${DEV}" nodad +ip -netns "${NS2}" addr add fd::2/64 dev "${DEV}" nodad + +# Optionally disable sg or csum offload to test edge cases +# ip netns exec "${NS1}" ethtool -K "${DEV}" sg off + +do_test() { + local readonly ARGS="$1" + + echo "ipv${IP} ${TXMODE} ${ARGS}" + ip netns exec "${NS2}" "${BIN}" "-${IP}" -i "${DEV}" -t 2 -C 2 -S "${SADDR}" -D "${DADDR}" ${ARGS} -r "${RXMODE}" & + sleep 0.2 + ip netns exec "${NS1}" "${BIN}" "-${IP}" -i "${DEV}" -t 1 -C 3 -S "${SADDR}" -D "${DADDR}" ${ARGS} "${TXMODE}" + wait +} + +do_test "${EXTRA_ARGS}" +do_test "-z ${EXTRA_ARGS}" +echo ok diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh new file mode 100755 index 000000000000..57b5ff576240 --- /dev/null +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -0,0 +1,272 @@ +#!/bin/sh +# +# This test is for checking rtnetlink callpaths, and get as much coverage as possible. +# +# set -e + +devdummy="test-dummy0" +ret=0 + +# set global exit status, but never reset nonzero one. +check_err() +{ + if [ $ret -eq 0 ]; then + ret=$1 + fi +} + +kci_add_dummy() +{ + ip link add name "$devdummy" type dummy + check_err $? + ip link set "$devdummy" up + check_err $? +} + +kci_del_dummy() +{ + ip link del dev "$devdummy" + check_err $? +} + +# add a bridge with vlans on top +kci_test_bridge() +{ + devbr="test-br0" + vlandev="testbr-vlan1" + + ret=0 + ip link add name "$devbr" type bridge + check_err $? + + ip link set dev "$devdummy" master "$devbr" + check_err $? + + ip link set "$devbr" up + check_err $? + + ip link add link "$devbr" name "$vlandev" type vlan id 1 + check_err $? + ip addr add dev "$vlandev" 10.200.7.23/30 + check_err $? + ip -6 addr add dev "$vlandev" dead:42::1234/64 + check_err $? + ip -d link > /dev/null + check_err $? + ip r s t all > /dev/null + check_err $? + ip -6 addr del dev "$vlandev" dead:42::1234/64 + check_err $? + + ip link del dev "$vlandev" + check_err $? + ip link del dev "$devbr" + check_err $? + + if [ $ret -ne 0 ];then + echo "FAIL: bridge setup" + return 1 + fi + echo "PASS: bridge setup" + +} + +kci_test_gre() +{ + gredev=neta + rem=10.42.42.1 + loc=10.0.0.1 + + ret=0 + ip tunnel add $gredev mode gre remote $rem local $loc ttl 1 + check_err $? + ip link set $gredev up + check_err $? + ip addr add 10.23.7.10 dev $gredev + check_err $? + ip route add 10.23.8.0/30 dev $gredev + check_err $? + ip addr add dev "$devdummy" 10.23.7.11/24 + check_err $? + ip link > /dev/null + check_err $? + ip addr > /dev/null + check_err $? + ip addr del dev "$devdummy" 10.23.7.11/24 + check_err $? + + ip link del $gredev + check_err $? + + if [ $ret -ne 0 ];then + echo "FAIL: gre tunnel endpoint" + return 1 + fi + echo "PASS: gre tunnel endpoint" +} + +# tc uses rtnetlink too, for full tc testing +# please see tools/testing/selftests/tc-testing. +kci_test_tc() +{ + dev=lo + ret=0 + + tc qdisc add dev "$dev" root handle 1: htb + check_err $? + tc class add dev "$dev" parent 1: classid 1:10 htb rate 1mbit + check_err $? + tc filter add dev "$dev" parent 1:0 prio 5 handle ffe: protocol ip u32 divisor 256 + check_err $? + tc filter add dev "$dev" parent 1:0 prio 5 handle ffd: protocol ip u32 divisor 256 + check_err $? + tc filter add dev "$dev" parent 1:0 prio 5 handle ffc: protocol ip u32 divisor 256 + check_err $? + tc filter add dev "$dev" protocol ip parent 1: prio 5 handle ffe:2:3 u32 ht ffe:2: match ip src 10.0.0.3 flowid 1:10 + check_err $? + tc filter add dev "$dev" protocol ip parent 1: prio 5 handle ffe:2:2 u32 ht ffe:2: match ip src 10.0.0.2 flowid 1:10 + check_err $? + tc filter show dev "$dev" parent 1:0 > /dev/null + check_err $? + tc filter del dev "$dev" protocol ip parent 1: prio 5 handle ffe:2:3 u32 + check_err $? + tc filter show dev "$dev" parent 1:0 > /dev/null + check_err $? + tc qdisc del dev "$dev" root handle 1: htb + check_err $? + + if [ $ret -ne 0 ];then + echo "FAIL: tc htb hierarchy" + return 1 + fi + echo "PASS: tc htb hierarchy" + +} + +kci_test_polrouting() +{ + ret=0 + ip rule add fwmark 1 lookup 100 + check_err $? + ip route add local 0.0.0.0/0 dev lo table 100 + check_err $? + ip r s t all > /dev/null + check_err $? + ip rule del fwmark 1 lookup 100 + check_err $? + ip route del local 0.0.0.0/0 dev lo table 100 + check_err $? + + if [ $ret -ne 0 ];then + echo "FAIL: policy route test" + return 1 + fi + echo "PASS: policy routing" +} + +kci_test_route_get() +{ + ret=0 + + ip route get 127.0.0.1 > /dev/null + check_err $? + ip route get 127.0.0.1 dev "$devdummy" > /dev/null + check_err $? + ip route get ::1 > /dev/null + check_err $? + ip route get fe80::1 dev "$devdummy" > /dev/null + check_err $? + ip route get 127.0.0.1 from 127.0.0.1 oif lo tos 0x1 mark 0x1 > /dev/null + check_err $? + ip route get ::1 from ::1 iif lo oif lo tos 0x1 mark 0x1 > /dev/null + check_err $? + ip addr add dev "$devdummy" 10.23.7.11/24 + check_err $? + ip route get 10.23.7.11 from 10.23.7.12 iif "$devdummy" > /dev/null + check_err $? + ip addr del dev "$devdummy" 10.23.7.11/24 + check_err $? + + if [ $ret -ne 0 ];then + echo "FAIL: route get" + return 1 + fi + + echo "PASS: route get" +} + +kci_test_addrlabel() +{ + ret=0 + + ip addrlabel add prefix dead::/64 dev lo label 1 + check_err $? + + ip addrlabel list |grep -q "prefix dead::/64 dev lo label 1" + check_err $? + + ip addrlabel del prefix dead::/64 dev lo label 1 2> /dev/null + check_err $? + + ip addrlabel add prefix dead::/64 label 1 2> /dev/null + check_err $? + + ip addrlabel del prefix dead::/64 label 1 2> /dev/null + check_err $? + + # concurrent add/delete + for i in $(seq 1 1000); do + ip addrlabel add prefix 1c3::/64 label 12345 2>/dev/null + done & + + for i in $(seq 1 1000); do + ip addrlabel del prefix 1c3::/64 label 12345 2>/dev/null + done + + wait + + ip addrlabel del prefix 1c3::/64 label 12345 2>/dev/null + + if [ $ret -ne 0 ];then + echo "FAIL: ipv6 addrlabel" + return 1 + fi + + echo "PASS: ipv6 addrlabel" +} + +kci_test_rtnl() +{ + kci_add_dummy + if [ $ret -ne 0 ];then + echo "FAIL: cannot add dummy interface" + return 1 + fi + + kci_test_polrouting + kci_test_route_get + kci_test_tc + kci_test_gre + kci_test_bridge + kci_test_addrlabel + + kci_del_dummy +} + +#check for needed privileges +if [ "$(id -u)" -ne 0 ];then + echo "SKIP: Need root privileges" + exit 0 +fi + +for x in ip tc;do + $x -Version 2>/dev/null >/dev/null + if [ $? -ne 0 ];then + echo "SKIP: Could not run test without the $x tool" + exit 0 + fi +done + +kci_test_rtnl + +exit $ret diff --git a/tools/testing/selftests/networking/timestamping/.gitignore b/tools/testing/selftests/networking/timestamping/.gitignore index 9e69e982fb38..d9355035e746 100644 --- a/tools/testing/selftests/networking/timestamping/.gitignore +++ b/tools/testing/selftests/networking/timestamping/.gitignore @@ -1,3 +1,4 @@ timestamping +rxtimestamp txtimestamp hwtstamp_config diff --git a/tools/testing/selftests/networking/timestamping/Makefile b/tools/testing/selftests/networking/timestamping/Makefile index ccbb9edbbbb9..92fb8ee917c5 100644 --- a/tools/testing/selftests/networking/timestamping/Makefile +++ b/tools/testing/selftests/networking/timestamping/Makefile @@ -1,4 +1,6 @@ -TEST_PROGS := hwtstamp_config timestamping txtimestamp +CFLAGS += -I../../../../../usr/include + +TEST_PROGS := hwtstamp_config rxtimestamp timestamping txtimestamp all: $(TEST_PROGS) diff --git a/tools/testing/selftests/networking/timestamping/rxtimestamp.c b/tools/testing/selftests/networking/timestamping/rxtimestamp.c new file mode 100644 index 000000000000..00f286661dcd --- /dev/null +++ b/tools/testing/selftests/networking/timestamping/rxtimestamp.c @@ -0,0 +1,389 @@ +#include <errno.h> +#include <error.h> +#include <getopt.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> + +#include <sys/time.h> +#include <sys/socket.h> +#include <sys/select.h> +#include <sys/ioctl.h> +#include <arpa/inet.h> +#include <net/if.h> + +#include <asm/types.h> +#include <linux/net_tstamp.h> +#include <linux/errqueue.h> + +#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) + +struct options { + int so_timestamp; + int so_timestampns; + int so_timestamping; +}; + +struct tstamps { + bool tstamp; + bool tstampns; + bool swtstamp; + bool hwtstamp; +}; + +struct socket_type { + char *friendly_name; + int type; + int protocol; + bool enabled; +}; + +struct test_case { + struct options sockopt; + struct tstamps expected; + bool enabled; +}; + +struct sof_flag { + int mask; + char *name; +}; + +static struct sof_flag sof_flags[] = { +#define SOF_FLAG(f) { f, #f } + SOF_FLAG(SOF_TIMESTAMPING_SOFTWARE), + SOF_FLAG(SOF_TIMESTAMPING_RX_SOFTWARE), + SOF_FLAG(SOF_TIMESTAMPING_RX_HARDWARE), +}; + +static struct socket_type socket_types[] = { + { "ip", SOCK_RAW, IPPROTO_EGP }, + { "udp", SOCK_DGRAM, IPPROTO_UDP }, + { "tcp", SOCK_STREAM, IPPROTO_TCP }, +}; + +static struct test_case test_cases[] = { + { {}, {} }, + { + { so_timestamp: 1 }, + { tstamp: true } + }, + { + { so_timestampns: 1 }, + { tstampns: true } + }, + { + { so_timestamp: 1, so_timestampns: 1 }, + { tstampns: true } + }, + { + { so_timestamping: SOF_TIMESTAMPING_RX_SOFTWARE }, + {} + }, + { + /* Loopback device does not support hw timestamps. */ + { so_timestamping: SOF_TIMESTAMPING_RX_HARDWARE }, + {} + }, + { + { so_timestamping: SOF_TIMESTAMPING_SOFTWARE }, + {} + }, + { + { so_timestamping: SOF_TIMESTAMPING_RX_SOFTWARE + | SOF_TIMESTAMPING_RX_HARDWARE }, + {} + }, + { + { so_timestamping: SOF_TIMESTAMPING_SOFTWARE + | SOF_TIMESTAMPING_RX_SOFTWARE }, + { swtstamp: true } + }, + { + { so_timestamp: 1, so_timestamping: SOF_TIMESTAMPING_SOFTWARE + | SOF_TIMESTAMPING_RX_SOFTWARE }, + { tstamp: true, swtstamp: true } + }, +}; + +static struct option long_options[] = { + { "list_tests", no_argument, 0, 'l' }, + { "test_num", required_argument, 0, 'n' }, + { "op_size", required_argument, 0, 's' }, + { "tcp", no_argument, 0, 't' }, + { "udp", no_argument, 0, 'u' }, + { "ip", no_argument, 0, 'i' }, +}; + +static int next_port = 19999; +static int op_size = 10 * 1024; + +void print_test_case(struct test_case *t) +{ + int f = 0; + + printf("sockopts {"); + if (t->sockopt.so_timestamp) + printf(" SO_TIMESTAMP "); + if (t->sockopt.so_timestampns) + printf(" SO_TIMESTAMPNS "); + if (t->sockopt.so_timestamping) { + printf(" SO_TIMESTAMPING: {"); + for (f = 0; f < ARRAY_SIZE(sof_flags); f++) + if (t->sockopt.so_timestamping & sof_flags[f].mask) + printf(" %s |", sof_flags[f].name); + printf("}"); + } + printf("} expected cmsgs: {"); + if (t->expected.tstamp) + printf(" SCM_TIMESTAMP "); + if (t->expected.tstampns) + printf(" SCM_TIMESTAMPNS "); + if (t->expected.swtstamp || t->expected.hwtstamp) { + printf(" SCM_TIMESTAMPING {"); + if (t->expected.swtstamp) + printf("0"); + if (t->expected.swtstamp && t->expected.hwtstamp) + printf(","); + if (t->expected.hwtstamp) + printf("2"); + printf("}"); + } + printf("}\n"); +} + +void do_send(int src) +{ + int r; + char *buf = malloc(op_size); + + memset(buf, 'z', op_size); + r = write(src, buf, op_size); + if (r < 0) + error(1, errno, "Failed to sendmsg"); + + free(buf); +} + +bool do_recv(int rcv, int read_size, struct tstamps expected) +{ + const int CMSG_SIZE = 1024; + + struct scm_timestamping *ts; + struct tstamps actual = {}; + char cmsg_buf[CMSG_SIZE]; + struct iovec recv_iov; + struct cmsghdr *cmsg; + bool failed = false; + struct msghdr hdr; + int flags = 0; + int r; + + memset(&hdr, 0, sizeof(hdr)); + hdr.msg_iov = &recv_iov; + hdr.msg_iovlen = 1; + recv_iov.iov_base = malloc(read_size); + recv_iov.iov_len = read_size; + + hdr.msg_control = cmsg_buf; + hdr.msg_controllen = sizeof(cmsg_buf); + + r = recvmsg(rcv, &hdr, flags); + if (r < 0) + error(1, errno, "Failed to recvmsg"); + if (r != read_size) + error(1, 0, "Only received %d bytes of payload.", r); + + if (hdr.msg_flags & (MSG_TRUNC | MSG_CTRUNC)) + error(1, 0, "Message was truncated."); + + for (cmsg = CMSG_FIRSTHDR(&hdr); cmsg != NULL; + cmsg = CMSG_NXTHDR(&hdr, cmsg)) { + if (cmsg->cmsg_level != SOL_SOCKET) + error(1, 0, "Unexpected cmsg_level %d", + cmsg->cmsg_level); + switch (cmsg->cmsg_type) { + case SCM_TIMESTAMP: + actual.tstamp = true; + break; + case SCM_TIMESTAMPNS: + actual.tstampns = true; + break; + case SCM_TIMESTAMPING: + ts = (struct scm_timestamping *)CMSG_DATA(cmsg); + actual.swtstamp = !!ts->ts[0].tv_sec; + if (ts->ts[1].tv_sec != 0) + error(0, 0, "ts[1] should not be set."); + actual.hwtstamp = !!ts->ts[2].tv_sec; + break; + default: + error(1, 0, "Unexpected cmsg_type %d", cmsg->cmsg_type); + } + } + +#define VALIDATE(field) \ + do { \ + if (expected.field != actual.field) { \ + if (expected.field) \ + error(0, 0, "Expected " #field " to be set."); \ + else \ + error(0, 0, \ + "Expected " #field " to not be set."); \ + failed = true; \ + } \ + } while (0) + + VALIDATE(tstamp); + VALIDATE(tstampns); + VALIDATE(swtstamp); + VALIDATE(hwtstamp); +#undef VALIDATE + + free(recv_iov.iov_base); + + return failed; +} + +void config_so_flags(int rcv, struct options o) +{ + int on = 1; + + if (setsockopt(rcv, SOL_SOCKET, SO_REUSEADDR, &on, sizeof(on)) < 0) + error(1, errno, "Failed to enable SO_REUSEADDR"); + + if (o.so_timestamp && + setsockopt(rcv, SOL_SOCKET, SO_TIMESTAMP, + &o.so_timestamp, sizeof(o.so_timestamp)) < 0) + error(1, errno, "Failed to enable SO_TIMESTAMP"); + + if (o.so_timestampns && + setsockopt(rcv, SOL_SOCKET, SO_TIMESTAMPNS, + &o.so_timestampns, sizeof(o.so_timestampns)) < 0) + error(1, errno, "Failed to enable SO_TIMESTAMPNS"); + + if (o.so_timestamping && + setsockopt(rcv, SOL_SOCKET, SO_TIMESTAMPING, + &o.so_timestamping, sizeof(o.so_timestamping)) < 0) + error(1, errno, "Failed to set SO_TIMESTAMPING"); +} + +bool run_test_case(struct socket_type s, struct test_case t) +{ + int port = (s.type == SOCK_RAW) ? 0 : next_port++; + int read_size = op_size; + struct sockaddr_in addr; + bool failed = false; + int src, dst, rcv; + + src = socket(AF_INET, s.type, s.protocol); + if (src < 0) + error(1, errno, "Failed to open src socket"); + + dst = socket(AF_INET, s.type, s.protocol); + if (dst < 0) + error(1, errno, "Failed to open dst socket"); + + memset(&addr, 0, sizeof(addr)); + addr.sin_family = AF_INET; + addr.sin_addr.s_addr = htonl(INADDR_LOOPBACK); + addr.sin_port = htons(port); + + if (bind(dst, (struct sockaddr *)&addr, sizeof(addr)) < 0) + error(1, errno, "Failed to bind to port %d", port); + + if (s.type == SOCK_STREAM && (listen(dst, 1) < 0)) + error(1, errno, "Failed to listen"); + + if (connect(src, (struct sockaddr *)&addr, sizeof(addr)) < 0) + error(1, errno, "Failed to connect"); + + if (s.type == SOCK_STREAM) { + rcv = accept(dst, NULL, NULL); + if (rcv < 0) + error(1, errno, "Failed to accept"); + close(dst); + } else { + rcv = dst; + } + + config_so_flags(rcv, t.sockopt); + usleep(20000); /* setsockopt for SO_TIMESTAMPING is asynchronous */ + do_send(src); + + if (s.type == SOCK_RAW) + read_size += 20; /* for IP header */ + failed = do_recv(rcv, read_size, t.expected); + + close(rcv); + close(src); + + return failed; +} + +int main(int argc, char **argv) +{ + bool all_protocols = true; + bool all_tests = true; + int arg_index = 0; + int failures = 0; + int s, t; + char opt; + + while ((opt = getopt_long(argc, argv, "", long_options, + &arg_index)) != -1) { + switch (opt) { + case 'l': + for (t = 0; t < ARRAY_SIZE(test_cases); t++) { + printf("%d\t", t); + print_test_case(&test_cases[t]); + } + return 0; + case 'n': + t = atoi(optarg); + if (t > ARRAY_SIZE(test_cases)) + error(1, 0, "Invalid test case: %d", t); + all_tests = false; + test_cases[t].enabled = true; + break; + case 's': + op_size = atoi(optarg); + break; + case 't': + all_protocols = false; + socket_types[2].enabled = true; + break; + case 'u': + all_protocols = false; + socket_types[1].enabled = true; + break; + case 'i': + all_protocols = false; + socket_types[0].enabled = true; + break; + default: + error(1, 0, "Failed to parse parameters."); + } + } + + for (s = 0; s < ARRAY_SIZE(socket_types); s++) { + if (!all_protocols && !socket_types[s].enabled) + continue; + + printf("Testing %s...\n", socket_types[s].friendly_name); + for (t = 0; t < ARRAY_SIZE(test_cases); t++) { + if (!all_tests && !test_cases[t].enabled) + continue; + + printf("Starting testcase %d...\n", t); + if (run_test_case(socket_types[s], test_cases[t])) { + failures++; + printf("FAILURE in test case "); + print_test_case(&test_cases[t]); + } + } + } + if (!failures) + printf("PASSED.\n"); + return failures; +} diff --git a/tools/testing/selftests/nsfs/config b/tools/testing/selftests/nsfs/config new file mode 100644 index 000000000000..598d0a225fc9 --- /dev/null +++ b/tools/testing/selftests/nsfs/config @@ -0,0 +1,3 @@ +CONFIG_USER_NS=y +CONFIG_UTS_NS=y +CONFIG_PID_NS=y diff --git a/tools/testing/selftests/ntb/ntb_test.sh b/tools/testing/selftests/ntb/ntb_test.sh index 13f5198ba0ee..5fc7ad359e21 100755 --- a/tools/testing/selftests/ntb/ntb_test.sh +++ b/tools/testing/selftests/ntb/ntb_test.sh @@ -18,6 +18,7 @@ LIST_DEVS=FALSE DEBUGFS=${DEBUGFS-/sys/kernel/debug} +DB_BITMASK=0x7FFF PERF_RUN_ORDER=32 MAX_MW_SIZE=0 RUN_DMA_TESTS= @@ -38,6 +39,7 @@ function show_help() echo "be highly recommended." echo echo "Options:" + echo " -b BITMASK doorbell clear bitmask for ntb_tool" echo " -C don't cleanup ntb modules on exit" echo " -d run dma tests" echo " -h show this help message" @@ -52,8 +54,9 @@ function show_help() function parse_args() { OPTIND=0 - while getopts "Cdhlm:r:p:w:" opt; do + while getopts "b:Cdhlm:r:p:w:" opt; do case "$opt" in + b) DB_BITMASK=${OPTARG} ;; C) DONT_CLEANUP=1 ;; d) RUN_DMA_TESTS=1 ;; h) show_help; exit 0 ;; @@ -85,6 +88,10 @@ set -e function _modprobe() { modprobe "$@" + + if [[ "$REMOTE_HOST" != "" ]]; then + ssh "$REMOTE_HOST" modprobe "$@" + fi } function split_remote() @@ -154,7 +161,7 @@ function doorbell_test() echo "Running db tests on: $(basename $LOC) / $(basename $REM)" - write_file "c 0xFFFFFFFF" "$REM/db" + write_file "c $DB_BITMASK" "$REM/db" for ((i=1; i <= 8; i++)); do let DB=$(read_file "$REM/db") || true @@ -326,6 +333,10 @@ function ntb_tool_tests() link_test $LOCAL_TOOL $REMOTE_TOOL link_test $REMOTE_TOOL $LOCAL_TOOL + #Ensure the link is up on both sides before continuing + write_file Y $LOCAL_TOOL/link_event + write_file Y $REMOTE_TOOL/link_event + for PEER_TRANS in $(ls $LOCAL_TOOL/peer_trans*); do PT=$(basename $PEER_TRANS) write_file $MW_SIZE $LOCAL_TOOL/$PT diff --git a/tools/testing/selftests/powerpc/benchmarks/context_switch.c b/tools/testing/selftests/powerpc/benchmarks/context_switch.c index 778f5fbfd784..f4241339edd2 100644 --- a/tools/testing/selftests/powerpc/benchmarks/context_switch.c +++ b/tools/testing/selftests/powerpc/benchmarks/context_switch.c @@ -258,9 +258,14 @@ static unsigned long xchg(unsigned long *p, unsigned long val) return __atomic_exchange_n(p, val, __ATOMIC_SEQ_CST); } +static int processes; + static int mutex_lock(unsigned long *m) { int c; + int flags = FUTEX_WAIT; + if (!processes) + flags |= FUTEX_PRIVATE_FLAG; c = cmpxchg(m, 0, 1); if (!c) @@ -270,7 +275,7 @@ static int mutex_lock(unsigned long *m) c = xchg(m, 2); while (c) { - sys_futex(m, FUTEX_WAIT, 2, NULL, NULL, 0); + sys_futex(m, flags, 2, NULL, NULL, 0); c = xchg(m, 2); } @@ -279,12 +284,16 @@ static int mutex_lock(unsigned long *m) static int mutex_unlock(unsigned long *m) { + int flags = FUTEX_WAKE; + if (!processes) + flags |= FUTEX_PRIVATE_FLAG; + if (*m == 2) *m = 0; else if (xchg(m, 0) == 1) return 0; - sys_futex(m, FUTEX_WAKE, 1, NULL, NULL, 0); + sys_futex(m, flags, 1, NULL, NULL, 0); return 0; } @@ -293,26 +302,32 @@ static unsigned long *m1, *m2; static void futex_setup(int cpu1, int cpu2) { - int shmid; - void *shmaddr; + if (!processes) { + static unsigned long _m1, _m2; + m1 = &_m1; + m2 = &_m2; + } else { + int shmid; + void *shmaddr; - shmid = shmget(IPC_PRIVATE, getpagesize(), SHM_R | SHM_W); - if (shmid < 0) { - perror("shmget"); - exit(1); - } + shmid = shmget(IPC_PRIVATE, getpagesize(), SHM_R | SHM_W); + if (shmid < 0) { + perror("shmget"); + exit(1); + } - shmaddr = shmat(shmid, NULL, 0); - if (shmaddr == (char *)-1) { - perror("shmat"); - shmctl(shmid, IPC_RMID, NULL); - exit(1); - } + shmaddr = shmat(shmid, NULL, 0); + if (shmaddr == (char *)-1) { + perror("shmat"); + shmctl(shmid, IPC_RMID, NULL); + exit(1); + } - shmctl(shmid, IPC_RMID, NULL); + shmctl(shmid, IPC_RMID, NULL); - m1 = shmaddr; - m2 = shmaddr + sizeof(*m1); + m1 = shmaddr; + m2 = shmaddr + sizeof(*m1); + } *m1 = 0; *m2 = 0; @@ -352,8 +367,6 @@ static struct actions futex_actions = { .thread2 = futex_thread2, }; -static int processes; - static struct option options[] = { { "test", required_argument, 0, 't' }, { "process", no_argument, &processes, 1 }, diff --git a/tools/testing/selftests/powerpc/ptrace/Makefile b/tools/testing/selftests/powerpc/ptrace/Makefile index fe6bc60dfc60..8932263e5a74 100644 --- a/tools/testing/selftests/powerpc/ptrace/Makefile +++ b/tools/testing/selftests/powerpc/ptrace/Makefile @@ -6,7 +6,7 @@ include ../../lib.mk all: $(TEST_PROGS) -CFLAGS += -m64 -I../../../../../usr/include -I../tm -mhtm +CFLAGS += -m64 -I../../../../../usr/include -I../tm -mhtm -fno-pie $(TEST_PROGS): ../harness.c ../utils.c ../lib/reg.S ptrace.h diff --git a/tools/testing/selftests/powerpc/switch_endian/switch_endian_test.S b/tools/testing/selftests/powerpc/switch_endian/switch_endian_test.S index ef7c971abb67..bceb53f57573 100644 --- a/tools/testing/selftests/powerpc/switch_endian/switch_endian_test.S +++ b/tools/testing/selftests/powerpc/switch_endian/switch_endian_test.S @@ -8,7 +8,7 @@ message: .section ".toc" .balign 8 pattern: - .llong 0x5555AAAA5555AAAA + .8byte 0x5555AAAA5555AAAA .text FUNC_START(_start) diff --git a/tools/testing/selftests/powerpc/tm/Makefile b/tools/testing/selftests/powerpc/tm/Makefile index 958c11c14acd..7bfcd454fb2a 100644 --- a/tools/testing/selftests/powerpc/tm/Makefile +++ b/tools/testing/selftests/powerpc/tm/Makefile @@ -15,6 +15,7 @@ $(OUTPUT)/tm-syscall: tm-syscall-asm.S $(OUTPUT)/tm-syscall: CFLAGS += -I../../../../../usr/include $(OUTPUT)/tm-tmspr: CFLAGS += -pthread $(OUTPUT)/tm-vmx-unavail: CFLAGS += -pthread -m64 +$(OUTPUT)/tm-resched-dscr: ../pmu/lib.o SIGNAL_CONTEXT_CHK_TESTS := $(patsubst %,$(OUTPUT)/%,$(SIGNAL_CONTEXT_CHK_TESTS)) $(SIGNAL_CONTEXT_CHK_TESTS): tm-signal.S diff --git a/tools/testing/selftests/powerpc/tm/tm-resched-dscr.c b/tools/testing/selftests/powerpc/tm/tm-resched-dscr.c index e79ccd6aada1..a7ac2e4c60d9 100644 --- a/tools/testing/selftests/powerpc/tm/tm-resched-dscr.c +++ b/tools/testing/selftests/powerpc/tm/tm-resched-dscr.c @@ -30,6 +30,7 @@ #include "utils.h" #include "tm.h" +#include "../pmu/lib.h" #define SPRN_DSCR 0x03 @@ -75,8 +76,6 @@ int test_body(void) ); assert(rv); /* make sure the transaction aborted */ if ((texasr >> 56) != TM_CAUSE_RESCHED) { - putchar('.'); - fflush(stdout); continue; } if (dscr2 != dscr1) { @@ -89,7 +88,12 @@ int test_body(void) } } -int main(void) +static int tm_resched_dscr(void) { - return test_harness(test_body, "tm_resched_dscr"); + return eat_cpu(test_body); +} + +int main(int argc, const char *argv[]) +{ + return test_harness(tm_resched_dscr, "tm_resched_dscr"); } diff --git a/tools/testing/selftests/pstore/.gitignore b/tools/testing/selftests/pstore/.gitignore new file mode 100644 index 000000000000..5a4a26e5464b --- /dev/null +++ b/tools/testing/selftests/pstore/.gitignore @@ -0,0 +1,2 @@ +logs +*uuid diff --git a/tools/testing/selftests/ptp/Makefile b/tools/testing/selftests/ptp/Makefile index 83dd42b2129e..d4064c742c26 100644 --- a/tools/testing/selftests/ptp/Makefile +++ b/tools/testing/selftests/ptp/Makefile @@ -1,3 +1,4 @@ +CFLAGS += -I../../../../usr/include/ TEST_PROGS := testptp LDLIBS += -lrt all: $(TEST_PROGS) diff --git a/tools/testing/selftests/rcutorture/bin/config_override.sh b/tools/testing/selftests/rcutorture/bin/config_override.sh new file mode 100755 index 000000000000..49fa51726ce3 --- /dev/null +++ b/tools/testing/selftests/rcutorture/bin/config_override.sh @@ -0,0 +1,61 @@ +#!/bin/bash +# +# config_override.sh base override +# +# Combines base and override, removing any Kconfig options from base +# that conflict with any in override, concatenating what remains and +# sending the result to standard output. +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program; if not, you can access it online at +# http://www.gnu.org/licenses/gpl-2.0.html. +# +# Copyright (C) IBM Corporation, 2017 +# +# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com> + +base=$1 +if test -r $base +then + : +else + echo Base file $base unreadable!!! + exit 1 +fi + +override=$2 +if test -r $override +then + : +else + echo Override file $override unreadable!!! + exit 1 +fi + +T=/tmp/config_override.sh.$$ +trap 'rm -rf $T' 0 +mkdir $T + +sed < $override -e 's/^/grep -v "/' -e 's/=.*$/="/' | + awk ' + { + if (last) + print last " |"; + last = $0; + } + END { + if (last) + print last; + }' > $T/script +sh $T/script < $base +cat $override diff --git a/tools/testing/selftests/rcutorture/bin/configcheck.sh b/tools/testing/selftests/rcutorture/bin/configcheck.sh index eee31e261bf7..70fca318a82b 100755 --- a/tools/testing/selftests/rcutorture/bin/configcheck.sh +++ b/tools/testing/selftests/rcutorture/bin/configcheck.sh @@ -27,7 +27,7 @@ cat $1 > $T/.config cat $2 | sed -e 's/\(.*\)=n/# \1 is not set/' -e 's/^#CHECK#//' | awk ' -BEGIN { +{ print "if grep -q \"" $0 "\" < '"$T/.config"'"; print "then"; print "\t:"; diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh index 1426a9b97494..07a13779eece 100644 --- a/tools/testing/selftests/rcutorture/bin/functions.sh +++ b/tools/testing/selftests/rcutorture/bin/functions.sh @@ -66,9 +66,34 @@ configfrag_boot_params () { # configfrag_boot_cpus bootparam-string config-fragment-file config-cpus # -# Decreases number of CPUs based on any maxcpus= boot parameters specified. +# Decreases number of CPUs based on any nr_cpus= boot parameters specified. configfrag_boot_cpus () { local bootargs="`configfrag_boot_params "$1" "$2"`" + local nr_cpus + if echo "${bootargs}" | grep -q 'nr_cpus=[0-9]' + then + nr_cpus="`echo "${bootargs}" | sed -e 's/^.*nr_cpus=\([0-9]*\).*$/\1/'`" + if test "$3" -gt "$nr_cpus" + then + echo $nr_cpus + else + echo $3 + fi + else + echo $3 + fi +} + +# configfrag_boot_maxcpus bootparam-string config-fragment-file config-cpus +# +# Decreases number of CPUs based on any maxcpus= boot parameters specified. +# This allows tests where additional CPUs come online later during the +# test run. However, the torture parameters will be set based on the +# number of CPUs initially present, so the scripting should schedule +# test runs based on the maxcpus= boot parameter controlling the initial +# number of CPUs instead of on the ultimate number of CPUs. +configfrag_boot_maxcpus () { + local bootargs="`configfrag_boot_params "$1" "$2"`" local maxcpus if echo "${bootargs}" | grep -q 'maxcpus=[0-9]' then diff --git a/tools/testing/selftests/rcutorture/bin/kvm-build.sh b/tools/testing/selftests/rcutorture/bin/kvm-build.sh index 00cb0db2643d..46752c164676 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-build.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-build.sh @@ -2,7 +2,7 @@ # # Build a kvm-ready Linux kernel from the tree in the current directory. # -# Usage: kvm-build.sh config-template build-dir more-configs +# Usage: kvm-build.sh config-template build-dir # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by @@ -34,24 +34,17 @@ then echo "kvm-build.sh :$builddir: Not a writable directory, cannot build into it" exit 1 fi -moreconfigs=${3} -if test -z "$moreconfigs" -o ! -r "$moreconfigs" -then - echo "kvm-build.sh :$moreconfigs: Not a readable file" - exit 1 -fi T=/tmp/test-linux.sh.$$ trap 'rm -rf $T' 0 mkdir $T -grep -v 'CONFIG_[A-Z]*_TORTURE_TEST' < ${config_template} > $T/config +cp ${config_template} $T/config cat << ___EOF___ >> $T/config CONFIG_INITRAMFS_SOURCE="$TORTURE_INITRD" CONFIG_VIRTIO_PCI=y CONFIG_VIRTIO_CONSOLE=y ___EOF___ -cat $moreconfigs >> $T/config configinit.sh $T/config O=$builddir retval=$? diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh index 93eede4e8fbe..0af36a721b9c 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh @@ -40,7 +40,7 @@ T=/tmp/kvm-test-1-run.sh.$$ trap 'rm -rf $T' 0 -touch $T +mkdir $T . $KVM/bin/functions.sh . $CONFIGFRAG/ver_functions.sh @@ -60,37 +60,33 @@ then echo "kvm-test-1-run.sh :$resdir: Not a writable directory, cannot store results into it" exit 1 fi -cp $config_template $resdir/ConfigFragment echo ' ---' `date`: Starting build echo ' ---' Kconfig fragment at: $config_template >> $resdir/log +touch $resdir/ConfigFragment.input $resdir/ConfigFragment if test -r "$config_dir/CFcommon" then - cat < $config_dir/CFcommon >> $T + echo " --- $config_dir/CFcommon" >> $resdir/ConfigFragment.input + cat < $config_dir/CFcommon >> $resdir/ConfigFragment.input + config_override.sh $config_dir/CFcommon $config_template > $T/Kc1 + grep '#CHECK#' $config_dir/CFcommon >> $resdir/ConfigFragment +else + cp $config_template $T/Kc1 fi -# Optimizations below this point -# CONFIG_USB=n -# CONFIG_SECURITY=n -# CONFIG_NFS_FS=n -# CONFIG_SOUND=n -# CONFIG_INPUT_JOYSTICK=n -# CONFIG_INPUT_TABLET=n -# CONFIG_INPUT_TOUCHSCREEN=n -# CONFIG_INPUT_MISC=n -# CONFIG_INPUT_MOUSE=n -# # CONFIG_NET=n # disables console access, so accept the slower build. -# CONFIG_SCSI=n -# CONFIG_ATA=n -# CONFIG_FAT_FS=n -# CONFIG_MSDOS_FS=n -# CONFIG_VFAT_FS=n -# CONFIG_ISO9660_FS=n -# CONFIG_QUOTA=n -# CONFIG_HID=n -# CONFIG_CRYPTO=n -# CONFIG_PCCARD=n -# CONFIG_PCMCIA=n -# CONFIG_CARDBUS=n -# CONFIG_YENTA=n +echo " --- $config_template" >> $resdir/ConfigFragment.input +cat $config_template >> $resdir/ConfigFragment.input +grep '#CHECK#' $config_template >> $resdir/ConfigFragment +if test -n "$TORTURE_KCONFIG_ARG" +then + echo $TORTURE_KCONFIG_ARG | tr -s " " "\012" > $T/cmdline + echo " --- --kconfig argument" >> $resdir/ConfigFragment.input + cat $T/cmdline >> $resdir/ConfigFragment.input + config_override.sh $T/Kc1 $T/cmdline > $T/Kc2 + # Note that "#CHECK#" is not permitted on commandline. +else + cp $T/Kc1 $T/Kc2 +fi +cat $T/Kc2 >> $resdir/ConfigFragment + base_resdir=`echo $resdir | sed -e 's/\.[0-9]\+$//'` if test "$base_resdir" != "$resdir" -a -f $base_resdir/bzImage -a -f $base_resdir/vmlinux then @@ -100,7 +96,9 @@ then KERNEL=$base_resdir/${BOOT_IMAGE##*/} # use the last component of ${BOOT_IMAGE} ln -s $base_resdir/Make*.out $resdir # for kvm-recheck.sh ln -s $base_resdir/.config $resdir # for kvm-recheck.sh -elif kvm-build.sh $config_template $builddir $T + # Arch-independent indicator + touch $resdir/builtkernel +elif kvm-build.sh $T/Kc2 $builddir then # Had to build a kernel for this test. QEMU="`identify_qemu $builddir/vmlinux`" @@ -112,6 +110,8 @@ then then cp $builddir/$BOOT_IMAGE $resdir KERNEL=$resdir/${BOOT_IMAGE##*/} + # Arch-independent indicator + touch $resdir/builtkernel else echo No identifiable boot image, not running KVM, see $resdir. echo Do the torture scripts know about your architecture? @@ -149,7 +149,7 @@ fi # Generate -smp qemu argument. qemu_args="-enable-kvm -nographic $qemu_args" -cpu_count=`configNR_CPUS.sh $config_template` +cpu_count=`configNR_CPUS.sh $resdir/ConfigFragment` cpu_count=`configfrag_boot_cpus "$boot_args" "$config_template" "$cpu_count"` vcpus=`identify_qemu_vcpus` if test $cpu_count -gt $vcpus diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh index 3b3c1b693ee1..b55895fb10ed 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm.sh @@ -41,6 +41,7 @@ PATH=${KVM}/bin:$PATH; export PATH TORTURE_DEFCONFIG=defconfig TORTURE_BOOT_IMAGE="" TORTURE_INITRD="$KVM/initrd"; export TORTURE_INITRD +TORTURE_KCONFIG_ARG="" TORTURE_KMAKE_ARG="" TORTURE_SHUTDOWN_GRACE=180 TORTURE_SUITE=rcu @@ -65,6 +66,7 @@ usage () { echo " --duration minutes" echo " --interactive" echo " --jitter N [ maxsleep (us) [ maxspin (us) ] ]" + echo " --kconfig Kconfig-options" echo " --kmake-arg kernel-make-arguments" echo " --mac nn:nn:nn:nn:nn:nn" echo " --no-initrd" @@ -129,6 +131,11 @@ do jitter="$2" shift ;; + --kconfig) + checkarg --kconfig "(Kconfig options)" $# "$2" '^CONFIG_[A-Z0-9_]\+=\([ynm]\|[0-9]\+\)\( CONFIG_[A-Z0-9_]\+=\([ynm]\|[0-9]\+\)\)*$' '^error$' + TORTURE_KCONFIG_ARG="$2" + shift + ;; --kmake-arg) checkarg --kmake-arg "(kernel make arguments)" $# "$2" '.*' '^error$' TORTURE_KMAKE_ARG="$2" @@ -205,6 +212,7 @@ do then cpu_count=`configNR_CPUS.sh $CONFIGFRAG/$CF1` cpu_count=`configfrag_boot_cpus "$TORTURE_BOOTARGS" "$CONFIGFRAG/$CF1" "$cpu_count"` + cpu_count=`configfrag_boot_maxcpus "$TORTURE_BOOTARGS" "$CONFIGFRAG/$CF1" "$cpu_count"` for ((cur_rep=0;cur_rep<$config_reps;cur_rep++)) do echo $CF1 $cpu_count >> $T/cfgcpu @@ -275,6 +283,7 @@ TORTURE_BOOT_IMAGE="$TORTURE_BOOT_IMAGE"; export TORTURE_BOOT_IMAGE TORTURE_BUILDONLY="$TORTURE_BUILDONLY"; export TORTURE_BUILDONLY TORTURE_DEFCONFIG="$TORTURE_DEFCONFIG"; export TORTURE_DEFCONFIG TORTURE_INITRD="$TORTURE_INITRD"; export TORTURE_INITRD +TORTURE_KCONFIG_ARG="$TORTURE_KCONFIG_ARG"; export TORTURE_KCONFIG_ARG TORTURE_KMAKE_ARG="$TORTURE_KMAKE_ARG"; export TORTURE_KMAKE_ARG TORTURE_QEMU_CMD="$TORTURE_QEMU_CMD"; export TORTURE_QEMU_CMD TORTURE_QEMU_INTERACTIVE="$TORTURE_QEMU_INTERACTIVE"; export TORTURE_QEMU_INTERACTIVE @@ -296,10 +305,7 @@ if test -d .git then git status >> $resdir/$ds/testid.txt git rev-parse HEAD >> $resdir/$ds/testid.txt - if ! git diff HEAD > $T/git-diff 2>&1 - then - cp $T/git-diff $resdir/$ds - fi + git diff HEAD >> $resdir/$ds/testid.txt fi ___EOF___ awk < $T/cfgcpu.pack \ @@ -327,6 +333,7 @@ function dump(first, pastlast, batchnum) { print "echo ----Start batch " batchnum ": `date`"; print "echo ----Start batch " batchnum ": `date` >> " rd "/log"; + print "needqemurun=" jn=1 for (j = first; j < pastlast; j++) { builddir=KVM "/b" jn @@ -362,10 +369,11 @@ function dump(first, pastlast, batchnum) for (j = 1; j < jn; j++) { builddir=KVM "/b" j print "rm -f " builddir ".ready" - print "if test -z \"$TORTURE_BUILDONLY\"" + print "if test -f \"" rd cfr[j] "/builtkernel\"" print "then" - print "\techo ----", cfr[j], cpusr[j] ovf ": Starting kernel. `date`"; - print "\techo ----", cfr[j], cpusr[j] ovf ": Starting kernel. `date` >> " rd "/log"; + print "\techo ----", cfr[j], cpusr[j] ovf ": Kernel present. `date`"; + print "\techo ----", cfr[j], cpusr[j] ovf ": Kernel present. `date` >> " rd "/log"; + print "\tneedqemurun=1" print "fi" } njitter = 0; @@ -380,13 +388,22 @@ function dump(first, pastlast, batchnum) njitter = 0; print "echo Build-only run, so suppressing jitter >> " rd "/log" } - for (j = 0; j < njitter; j++) - print "jitter.sh " j " " dur " " ja[2] " " ja[3] "&" - print "wait" - print "if test -z \"$TORTURE_BUILDONLY\"" + if (TORTURE_BUILDONLY) { + print "needqemurun=" + } + print "if test -n \"$needqemurun\"" print "then" + print "\techo ---- Starting kernels. `date`"; + print "\techo ---- Starting kernels. `date` >> " rd "/log"; + for (j = 0; j < njitter; j++) + print "\tjitter.sh " j " " dur " " ja[2] " " ja[3] "&" + print "\twait" print "\techo ---- All kernel runs complete. `date`"; print "\techo ---- All kernel runs complete. `date` >> " rd "/log"; + print "else" + print "\twait" + print "\techo ---- No kernel runs. `date`"; + print "\techo ---- No kernel runs. `date` >> " rd "/log"; print "fi" for (j = 1; j < jn; j++) { builddir=KVM "/b" j diff --git a/tools/testing/selftests/rcutorture/configs/rcu/BUSTED.boot b/tools/testing/selftests/rcutorture/configs/rcu/BUSTED.boot index 6804f9dcfc1b..be7728db42fd 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/BUSTED.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/BUSTED.boot @@ -1 +1 @@ -rcutorture.torture_type=rcu_busted +rcutorture.torture_type=busted diff --git a/tools/testing/selftests/rcutorture/configs/rcu/CFLIST b/tools/testing/selftests/rcutorture/configs/rcu/CFLIST index a3a1a05a2b5c..6a0b9f69faad 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/CFLIST +++ b/tools/testing/selftests/rcutorture/configs/rcu/CFLIST @@ -9,6 +9,8 @@ TREE08 TREE09 SRCU-N SRCU-P +SRCU-t +SRCU-u TINY01 TINY02 TASKS01 diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N index 1a087c3c8bb8..2da8b49589a0 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N +++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N @@ -5,4 +5,4 @@ CONFIG_HOTPLUG_CPU=y CONFIG_PREEMPT_NONE=y CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n -CONFIG_RCU_EXPERT=y +#CHECK#CONFIG_RCU_EXPERT=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P index 4837430a71c0..ab7ccd38232b 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P +++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P @@ -2,7 +2,11 @@ CONFIG_RCU_TRACE=n CONFIG_SMP=y CONFIG_NR_CPUS=8 CONFIG_HOTPLUG_CPU=y +CONFIG_RCU_EXPERT=y +CONFIG_RCU_FANOUT=2 +CONFIG_RCU_FANOUT_LEAF=2 CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=y -#CHECK#CONFIG_RCU_EXPERT=n +CONFIG_DEBUG_LOCK_ALLOC=y +CONFIG_PROVE_LOCKING=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-t b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-t new file mode 100644 index 000000000000..6c78022c8cd8 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-t @@ -0,0 +1,10 @@ +CONFIG_SMP=n +CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=n +#CHECK#CONFIG_TINY_SRCU=y +CONFIG_RCU_TRACE=n +CONFIG_DEBUG_LOCK_ALLOC=n +CONFIG_DEBUG_OBJECTS_RCU_HEAD=n +CONFIG_DEBUG_ATOMIC_SLEEP=y +#CHECK#CONFIG_PREEMPT_COUNT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-t.boot b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-t.boot new file mode 100644 index 000000000000..238bfe3bd0cc --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-t.boot @@ -0,0 +1 @@ +rcutorture.torture_type=srcu diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-u b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-u new file mode 100644 index 000000000000..c15ada821e45 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-u @@ -0,0 +1,10 @@ +CONFIG_SMP=n +CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=n +#CHECK#CONFIG_TINY_SRCU=y +CONFIG_RCU_TRACE=n +CONFIG_DEBUG_LOCK_ALLOC=y +CONFIG_PROVE_LOCKING=y +CONFIG_DEBUG_OBJECTS_RCU_HEAD=n +CONFIG_PREEMPT_COUNT=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-u.boot b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-u.boot new file mode 100644 index 000000000000..84a7d51b7481 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-u.boot @@ -0,0 +1 @@ +rcutorture.torture_type=srcud diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TINY02 b/tools/testing/selftests/rcutorture/configs/rcu/TINY02 index a59f7686e219..d8674264318d 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TINY02 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TINY02 @@ -6,10 +6,9 @@ CONFIG_PREEMPT=n CONFIG_HZ_PERIODIC=y CONFIG_NO_HZ_IDLE=n CONFIG_NO_HZ_FULL=n -CONFIG_RCU_TRACE=y CONFIG_PROVE_LOCKING=y -CONFIG_PROVE_RCU_REPEATEDLY=y #CHECK#CONFIG_PROVE_RCU=y CONFIG_DEBUG_LOCK_ALLOC=y +CONFIG_DEBUG_OBJECTS=y CONFIG_DEBUG_OBJECTS_RCU_HEAD=y -CONFIG_PREEMPT_COUNT=y +CONFIG_DEBUG_ATOMIC_SLEEP=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE01 b/tools/testing/selftests/rcutorture/configs/rcu/TREE01 index 359cb258f639..b5b53973c01e 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE01 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE01 @@ -10,12 +10,9 @@ CONFIG_RCU_FAST_NO_HZ=y CONFIG_RCU_TRACE=y CONFIG_HOTPLUG_CPU=y CONFIG_MAXSMP=y +CONFIG_CPUMASK_OFFSTACK=y CONFIG_RCU_NOCB_CPU=y -CONFIG_RCU_NOCB_CPU_ZERO=y CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y -CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y -CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y -CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot index adc3abc82fb8..9f3a4d28e508 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot @@ -1 +1,5 @@ -rcutorture.torture_type=rcu_bh maxcpus=8 +rcutorture.torture_type=rcu_bh maxcpus=8 nr_cpus=43 +rcutree.gp_preinit_delay=3 +rcutree.gp_init_delay=3 +rcutree.gp_cleanup_delay=3 +rcu_nocbs=0 diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE02 b/tools/testing/selftests/rcutorture/configs/rcu/TREE02 index c1ab5926568b..35e639e39366 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE02 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE02 @@ -18,9 +18,6 @@ CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=n CONFIG_RCU_BOOST=n -CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y -CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y -CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y -CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y +CONFIG_DEBUG_OBJECTS=y CONFIG_DEBUG_OBJECTS_RCU_HEAD=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE03 b/tools/testing/selftests/rcutorture/configs/rcu/TREE03 index 3b93ee544e70..2dc31b16e506 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE03 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE03 @@ -14,9 +14,5 @@ CONFIG_RCU_FANOUT_LEAF=2 CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_RCU_BOOST=y -CONFIG_RCU_KTHREAD_PRIO=2 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y -CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y -CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y -CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot index 120c0c88d100..5d2cc0bd50a0 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot @@ -1 +1,5 @@ rcutorture.onoff_interval=1 rcutorture.onoff_holdoff=30 +rcutree.gp_preinit_delay=3 +rcutree.gp_init_delay=3 +rcutree.gp_cleanup_delay=3 +rcutree.kthread_prio=2 diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 b/tools/testing/selftests/rcutorture/configs/rcu/TREE04 index 5af758e783c7..27d22695d64c 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE04 @@ -15,11 +15,7 @@ CONFIG_SUSPEND=n CONFIG_HIBERNATION=n CONFIG_RCU_FANOUT=4 CONFIG_RCU_FANOUT_LEAF=3 -CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y -CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y -CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y -CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y CONFIG_RCU_EQS_DEBUG=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE05 b/tools/testing/selftests/rcutorture/configs/rcu/TREE05 index d4cdc0d74e16..2dde0d9964e3 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE05 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE05 @@ -13,12 +13,8 @@ CONFIG_HOTPLUG_CPU=y CONFIG_RCU_FANOUT=6 CONFIG_RCU_FANOUT_LEAF=6 CONFIG_RCU_NOCB_CPU=y -CONFIG_RCU_NOCB_CPU_NONE=y CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=y #CHECK#CONFIG_PROVE_RCU=y CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y -CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y -CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y -CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE05.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE05.boot index 15b3e1a86f74..c7fd050dfcd9 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE05.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE05.boot @@ -1,2 +1,5 @@ rcutorture.torture_type=sched rcupdate.rcu_self_test_sched=1 +rcutree.gp_preinit_delay=3 +rcutree.gp_init_delay=3 +rcutree.gp_cleanup_delay=3 diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE06 b/tools/testing/selftests/rcutorture/configs/rcu/TREE06 index 4cb02bd28f08..05a4eec3f27b 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE06 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE06 @@ -18,8 +18,6 @@ CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=y #CHECK#CONFIG_PROVE_RCU=y +CONFIG_DEBUG_OBJECTS=y CONFIG_DEBUG_OBJECTS_RCU_HEAD=y CONFIG_RCU_EXPERT=y -CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y -CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y -CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE06.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE06.boot index dd90f28ed700..ad18b52a2cad 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE06.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE06.boot @@ -2,3 +2,6 @@ rcupdate.rcu_self_test=1 rcupdate.rcu_self_test_bh=1 rcupdate.rcu_self_test_sched=1 rcutree.rcu_fanout_exact=1 +rcutree.gp_preinit_delay=3 +rcutree.gp_init_delay=3 +rcutree.gp_cleanup_delay=3 diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE07 b/tools/testing/selftests/rcutorture/configs/rcu/TREE07 index b12a3ea1867e..0f4759f4232e 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE07 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE07 @@ -1,6 +1,5 @@ CONFIG_SMP=y CONFIG_NR_CPUS=16 -CONFIG_CPUMASK_OFFSTACK=y CONFIG_PREEMPT_NONE=y CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n @@ -9,16 +8,11 @@ CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=n CONFIG_NO_HZ_FULL=y CONFIG_NO_HZ_FULL_ALL=n -CONFIG_NO_HZ_FULL_SYSIDLE=y CONFIG_RCU_FAST_NO_HZ=n CONFIG_RCU_TRACE=y CONFIG_HOTPLUG_CPU=y CONFIG_RCU_FANOUT=2 CONFIG_RCU_FANOUT_LEAF=2 -CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y -CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y -CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y -CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08 b/tools/testing/selftests/rcutorture/configs/rcu/TREE08 index 099cc63c6a3b..fb1c763c10c5 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08 @@ -15,7 +15,6 @@ CONFIG_HIBERNATION=n CONFIG_RCU_FANOUT=3 CONFIG_RCU_FANOUT_LEAF=2 CONFIG_RCU_NOCB_CPU=y -CONFIG_RCU_NOCB_CPU_ALL=y CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_PROVE_LOCKING=n CONFIG_RCU_BOOST=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T b/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T deleted file mode 100644 index 2ad13f0d29cc..000000000000 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T +++ /dev/null @@ -1,21 +0,0 @@ -CONFIG_SMP=y -CONFIG_NR_CPUS=16 -CONFIG_PREEMPT_NONE=n -CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=y -#CHECK#CONFIG_PREEMPT_RCU=y -CONFIG_HZ_PERIODIC=n -CONFIG_NO_HZ_IDLE=y -CONFIG_NO_HZ_FULL=n -CONFIG_RCU_FAST_NO_HZ=n -CONFIG_RCU_TRACE=y -CONFIG_HOTPLUG_CPU=n -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -CONFIG_RCU_FANOUT=3 -CONFIG_RCU_FANOUT_LEAF=2 -CONFIG_RCU_NOCB_CPU=y -CONFIG_RCU_NOCB_CPU_ALL=y -CONFIG_DEBUG_LOCK_ALLOC=n -CONFIG_RCU_BOOST=n -CONFIG_DEBUG_OBJECTS_RCU_HEAD=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE08.boot index fb066dc82769..1bd8efc4141e 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08.boot @@ -2,3 +2,4 @@ rcutorture.torture_type=sched rcupdate.rcu_self_test=1 rcupdate.rcu_self_test_sched=1 rcutree.rcu_fanout_exact=1 +rcu_nocbs=0-7 diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T b/tools/testing/selftests/rcutorture/configs/rcuperf/TINY index 917d2517b5b5..fb05ef5279b4 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T +++ b/tools/testing/selftests/rcutorture/configs/rcuperf/TINY @@ -1,21 +1,16 @@ -CONFIG_SMP=y -CONFIG_NR_CPUS=8 -CONFIG_PREEMPT_NONE=n +CONFIG_SMP=n +CONFIG_PREEMPT_NONE=y CONFIG_PREEMPT_VOLUNTARY=n -CONFIG_PREEMPT=y -#CHECK#CONFIG_PREEMPT_RCU=y +CONFIG_PREEMPT=n +#CHECK#CONFIG_TINY_RCU=y CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=y CONFIG_NO_HZ_FULL=n CONFIG_RCU_FAST_NO_HZ=n -CONFIG_RCU_TRACE=y -CONFIG_HOTPLUG_CPU=n -CONFIG_SUSPEND=n -CONFIG_HIBERNATION=n -CONFIG_RCU_FANOUT=3 -CONFIG_RCU_FANOUT_LEAF=3 CONFIG_RCU_NOCB_CPU=n -CONFIG_DEBUG_LOCK_ALLOC=y +CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_PROVE_LOCKING=n CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n +CONFIG_RCU_EXPERT=y +CONFIG_RCU_TRACE=y diff --git a/tools/testing/selftests/rcutorture/configs/rcuperf/TREE b/tools/testing/selftests/rcutorture/configs/rcuperf/TREE index a312f671a29a..721cfda76ab2 100644 --- a/tools/testing/selftests/rcutorture/configs/rcuperf/TREE +++ b/tools/testing/selftests/rcutorture/configs/rcuperf/TREE @@ -7,7 +7,6 @@ CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=y CONFIG_NO_HZ_FULL=n CONFIG_RCU_FAST_NO_HZ=n -CONFIG_RCU_TRACE=n CONFIG_HOTPLUG_CPU=n CONFIG_SUSPEND=n CONFIG_HIBERNATION=n diff --git a/tools/testing/selftests/rcutorture/configs/rcuperf/TREE54 b/tools/testing/selftests/rcutorture/configs/rcuperf/TREE54 index 985fb170d13c..7629f5dd73b2 100644 --- a/tools/testing/selftests/rcutorture/configs/rcuperf/TREE54 +++ b/tools/testing/selftests/rcutorture/configs/rcuperf/TREE54 @@ -8,7 +8,6 @@ CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=y CONFIG_NO_HZ_FULL=n CONFIG_RCU_FAST_NO_HZ=n -CONFIG_RCU_TRACE=n CONFIG_HOTPLUG_CPU=n CONFIG_SUSPEND=n CONFIG_HIBERNATION=n diff --git a/tools/testing/selftests/rcutorture/doc/TINY_RCU.txt b/tools/testing/selftests/rcutorture/doc/TINY_RCU.txt index 24396ae8355b..a75b16991a92 100644 --- a/tools/testing/selftests/rcutorture/doc/TINY_RCU.txt +++ b/tools/testing/selftests/rcutorture/doc/TINY_RCU.txt @@ -18,7 +18,6 @@ CONFIG_PROVE_RCU In common code tested by TREE_RCU test cases. -CONFIG_NO_HZ_FULL_SYSIDLE CONFIG_RCU_NOCB_CPU Meaningless for TINY_RCU. diff --git a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt index 364801b1a230..af6fca03602f 100644 --- a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt +++ b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt @@ -9,28 +9,20 @@ CONFIG_DEBUG_OBJECTS_RCU_HEAD -- Do one. CONFIG_HOTPLUG_CPU -- Do half. (Every second.) CONFIG_HZ_PERIODIC -- Do one. CONFIG_NO_HZ_IDLE -- Do those not otherwise specified. (Groups of two.) -CONFIG_NO_HZ_FULL -- Do two, one with CONFIG_NO_HZ_FULL_SYSIDLE. -CONFIG_NO_HZ_FULL_SYSIDLE -- Do one. +CONFIG_NO_HZ_FULL -- Do two, one with partial CPU enablement. CONFIG_PREEMPT -- Do half. (First three and #8.) CONFIG_PROVE_LOCKING -- Do several, covering CONFIG_DEBUG_LOCK_ALLOC=y and not. CONFIG_PROVE_RCU -- Hardwired to CONFIG_PROVE_LOCKING. -CONFIG_PROVE_RCU_REPEATEDLY -- Do one. CONFIG_RCU_BOOST -- one of PREEMPT_RCU. -CONFIG_RCU_KTHREAD_PRIO -- set to 2 for _BOOST testing. CONFIG_RCU_FANOUT -- Cover hierarchy, but overlap with others. CONFIG_RCU_FANOUT_LEAF -- Do one non-default. -CONFIG_RCU_FAST_NO_HZ -- Do one, but not with CONFIG_RCU_NOCB_CPU_ALL. -CONFIG_RCU_NOCB_CPU -- Do three, see below. -CONFIG_RCU_NOCB_CPU_ALL -- Do one. -CONFIG_RCU_NOCB_CPU_NONE -- Do one. -CONFIG_RCU_NOCB_CPU_ZERO -- Do one. +CONFIG_RCU_FAST_NO_HZ -- Do one, but not with all nohz_full CPUs. +CONFIG_RCU_NOCB_CPU -- Do three, one with no rcu_nocbs CPUs, one with + rcu_nocbs=0, and one with all rcu_nocbs CPUs. CONFIG_RCU_TRACE -- Do half. CONFIG_SMP -- Need one !SMP for PREEMPT_RCU. CONFIG_RCU_EXPERT=n -- Do a few, but these have to be vanilla configurations. CONFIG_RCU_EQS_DEBUG -- Do at least one for CONFIG_NO_HZ_FULL and not. -CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP -- Do for all but a couple TREE scenarios. -CONFIG_RCU_TORTURE_TEST_SLOW_INIT -- Do for all but a couple TREE scenarios. -CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT -- Do for all but a couple TREE scenarios. RCU-bh: Do one with PREEMPT and one with !PREEMPT. RCU-sched: Do one with PREEMPT but not BOOST. @@ -52,10 +44,6 @@ CONFIG_64BIT Used only to check CONFIG_RCU_FANOUT value, inspection suffices. -CONFIG_NO_HZ_FULL_SYSIDLE_SMALL - - Defer until Frederic uses this. - CONFIG_PREEMPT_COUNT CONFIG_PREEMPT_RCU @@ -78,30 +66,16 @@ CONFIG_RCU_TORTURE_TEST_RUNNABLE Always used in KVM testing. -CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT_DELAY -CONFIG_RCU_TORTURE_TEST_SLOW_INIT_DELAY -CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP_DELAY - - Inspection suffices, ignore. - CONFIG_PREEMPT_RCU CONFIG_TREE_RCU CONFIG_TINY_RCU +CONFIG_TASKS_RCU These are controlled by CONFIG_PREEMPT and/or CONFIG_SMP. -CONFIG_SPARSE_RCU_POINTER - - Makes sense only for sparse runs, not for kernel builds. - CONFIG_SRCU -CONFIG_TASKS_RCU Selected by CONFIG_RCU_TORTURE_TEST, so cannot disable. -CONFIG_RCU_TRACE - - Implied by CONFIG_RCU_TRACE for Tree RCU. - boot parameters ignored: TBD diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/modify_srcu.awk b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/modify_srcu.awk index 8ff89043d0a9..c9e8bc5082a7 100755 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/modify_srcu.awk +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/modify_srcu.awk @@ -1,4 +1,4 @@ -#!/bin/awk -f +#!/usr/bin/awk -f # Modify SRCU for formal verification. The first argument should be srcu.h and # the second should be srcu.c. Outputs modified srcu.h and srcu.c into the diff --git a/tools/testing/selftests/seccomp/Makefile b/tools/testing/selftests/seccomp/Makefile index 5fa6fd2246b1..aeb0c805f3ca 100644 --- a/tools/testing/selftests/seccomp/Makefile +++ b/tools/testing/selftests/seccomp/Makefile @@ -4,3 +4,5 @@ LDFLAGS += -lpthread include ../lib.mk +$(TEST_GEN_PROGS): seccomp_bpf.c ../kselftest_harness.h + $(CC) $(CFLAGS) $(LDFLAGS) $< -o $@ diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 03f1fa495d74..4d6f92a9df6b 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -37,7 +37,7 @@ #include <unistd.h> #include <sys/syscall.h> -#include "test_harness.h" +#include "../kselftest_harness.h" #ifndef PR_SET_PTRACER # define PR_SET_PTRACER 0x59616d61 @@ -107,7 +107,7 @@ TEST(mode_strict_support) ASSERT_EQ(0, ret) { TH_LOG("Kernel does not support CONFIG_SECCOMP"); } - syscall(__NR_exit, 1); + syscall(__NR_exit, 0); } TEST_SIGNAL(mode_strict_cannot_call_prctl, SIGKILL) @@ -1310,7 +1310,7 @@ void change_syscall(struct __test_metadata *_metadata, iov.iov_len = sizeof(regs); ret = ptrace(PTRACE_GETREGSET, tracee, NT_PRSTATUS, &iov); #endif - EXPECT_EQ(0, ret); + EXPECT_EQ(0, ret) {} #if defined(__x86_64__) || defined(__i386__) || defined(__powerpc__) || \ defined(__s390__) || defined(__hppa__) @@ -1822,6 +1822,23 @@ struct tsync_sibling { struct __test_metadata *metadata; }; +/* + * To avoid joining joined threads (which is not allowed by Bionic), + * make sure we both successfully join and clear the tid to skip a + * later join attempt during fixture teardown. Any remaining threads + * will be directly killed during teardown. + */ +#define PTHREAD_JOIN(tid, status) \ + do { \ + int _rc = pthread_join(tid, status); \ + if (_rc) { \ + TH_LOG("pthread_join of tid %u failed: %d\n", \ + (unsigned int)tid, _rc); \ + } else { \ + tid = 0; \ + } \ + } while (0) + FIXTURE_DATA(TSYNC) { struct sock_fprog root_prog, apply_prog; struct tsync_sibling sibling[TSYNC_SIBLINGS]; @@ -1890,14 +1907,14 @@ FIXTURE_TEARDOWN(TSYNC) for ( ; sib < self->sibling_count; ++sib) { struct tsync_sibling *s = &self->sibling[sib]; - void *status; if (!s->tid) continue; - if (pthread_kill(s->tid, 0)) { - pthread_cancel(s->tid); - pthread_join(s->tid, &status); - } + /* + * If a thread is still running, it may be stuck, so hit + * it over the head really hard. + */ + pthread_kill(s->tid, 9); } pthread_mutex_destroy(&self->mutex); pthread_cond_destroy(&self->cond); @@ -1987,9 +2004,9 @@ TEST_F(TSYNC, siblings_fail_prctl) pthread_mutex_unlock(&self->mutex); /* Ensure diverging sibling failed to call prctl. */ - pthread_join(self->sibling[0].tid, &status); + PTHREAD_JOIN(self->sibling[0].tid, &status); EXPECT_EQ(SIBLING_EXIT_FAILURE, (long)status); - pthread_join(self->sibling[1].tid, &status); + PTHREAD_JOIN(self->sibling[1].tid, &status); EXPECT_EQ(SIBLING_EXIT_UNKILLED, (long)status); } @@ -2029,9 +2046,9 @@ TEST_F(TSYNC, two_siblings_with_ancestor) } pthread_mutex_unlock(&self->mutex); /* Ensure they are both killed and don't exit cleanly. */ - pthread_join(self->sibling[0].tid, &status); + PTHREAD_JOIN(self->sibling[0].tid, &status); EXPECT_EQ(0x0, (long)status); - pthread_join(self->sibling[1].tid, &status); + PTHREAD_JOIN(self->sibling[1].tid, &status); EXPECT_EQ(0x0, (long)status); } @@ -2055,9 +2072,9 @@ TEST_F(TSYNC, two_sibling_want_nnp) pthread_mutex_unlock(&self->mutex); /* Ensure they are both upset about lacking nnp. */ - pthread_join(self->sibling[0].tid, &status); + PTHREAD_JOIN(self->sibling[0].tid, &status); EXPECT_EQ(SIBLING_EXIT_NEWPRIVS, (long)status); - pthread_join(self->sibling[1].tid, &status); + PTHREAD_JOIN(self->sibling[1].tid, &status); EXPECT_EQ(SIBLING_EXIT_NEWPRIVS, (long)status); } @@ -2095,9 +2112,9 @@ TEST_F(TSYNC, two_siblings_with_no_filter) pthread_mutex_unlock(&self->mutex); /* Ensure they are both killed and don't exit cleanly. */ - pthread_join(self->sibling[0].tid, &status); + PTHREAD_JOIN(self->sibling[0].tid, &status); EXPECT_EQ(0x0, (long)status); - pthread_join(self->sibling[1].tid, &status); + PTHREAD_JOIN(self->sibling[1].tid, &status); EXPECT_EQ(0x0, (long)status); } @@ -2140,9 +2157,9 @@ TEST_F(TSYNC, two_siblings_with_one_divergence) pthread_mutex_unlock(&self->mutex); /* Ensure they are both unkilled. */ - pthread_join(self->sibling[0].tid, &status); + PTHREAD_JOIN(self->sibling[0].tid, &status); EXPECT_EQ(SIBLING_EXIT_UNKILLED, (long)status); - pthread_join(self->sibling[1].tid, &status); + PTHREAD_JOIN(self->sibling[1].tid, &status); EXPECT_EQ(SIBLING_EXIT_UNKILLED, (long)status); } @@ -2199,7 +2216,7 @@ TEST_F(TSYNC, two_siblings_not_under_filter) TH_LOG("cond broadcast non-zero"); } pthread_mutex_unlock(&self->mutex); - pthread_join(self->sibling[sib].tid, &status); + PTHREAD_JOIN(self->sibling[sib].tid, &status); EXPECT_EQ(SIBLING_EXIT_UNKILLED, (long)status); /* Poll for actual task death. pthread_join doesn't guarantee it. */ while (!kill(self->sibling[sib].system_tid, 0)) @@ -2224,7 +2241,7 @@ TEST_F(TSYNC, two_siblings_not_under_filter) TH_LOG("cond broadcast non-zero"); } pthread_mutex_unlock(&self->mutex); - pthread_join(self->sibling[sib].tid, &status); + PTHREAD_JOIN(self->sibling[sib].tid, &status); EXPECT_EQ(0, (long)status); /* Poll for actual task death. pthread_join doesn't guarantee it. */ while (!kill(self->sibling[sib].system_tid, 0)) diff --git a/tools/testing/selftests/seccomp/test_harness.h b/tools/testing/selftests/seccomp/test_harness.h deleted file mode 100644 index a786c69c7584..000000000000 --- a/tools/testing/selftests/seccomp/test_harness.h +++ /dev/null @@ -1,535 +0,0 @@ -/* - * Copyright (c) 2012 The Chromium OS Authors. All rights reserved. - * Use of this source code is governed by the GPLv2 license. - * - * test_harness.h: simple C unit test helper. - * - * Usage: - * #include "test_harness.h" - * TEST(standalone_test) { - * do_some_stuff; - * EXPECT_GT(10, stuff) { - * stuff_state_t state; - * enumerate_stuff_state(&state); - * TH_LOG("expectation failed with state: %s", state.msg); - * } - * more_stuff; - * ASSERT_NE(some_stuff, NULL) TH_LOG("how did it happen?!"); - * last_stuff; - * EXPECT_EQ(0, last_stuff); - * } - * - * FIXTURE(my_fixture) { - * mytype_t *data; - * int awesomeness_level; - * }; - * FIXTURE_SETUP(my_fixture) { - * self->data = mytype_new(); - * ASSERT_NE(NULL, self->data); - * } - * FIXTURE_TEARDOWN(my_fixture) { - * mytype_free(self->data); - * } - * TEST_F(my_fixture, data_is_good) { - * EXPECT_EQ(1, is_my_data_good(self->data)); - * } - * - * TEST_HARNESS_MAIN - * - * API inspired by code.google.com/p/googletest - */ -#ifndef TEST_HARNESS_H_ -#define TEST_HARNESS_H_ - -#define _GNU_SOURCE -#include <stdint.h> -#include <stdio.h> -#include <stdlib.h> -#include <string.h> -#include <sys/types.h> -#include <sys/wait.h> -#include <unistd.h> - -/* All exported functionality should be declared through this macro. */ -#define TEST_API(x) _##x - -/* - * Exported APIs - */ - -/* TEST(name) { implementation } - * Defines a test by name. - * Names must be unique and tests must not be run in parallel. The - * implementation containing block is a function and scoping should be treated - * as such. Returning early may be performed with a bare "return;" statement. - * - * EXPECT_* and ASSERT_* are valid in a TEST() { } context. - */ -#define TEST TEST_API(TEST) - -/* TEST_SIGNAL(name, signal) { implementation } - * Defines a test by name and the expected term signal. - * Names must be unique and tests must not be run in parallel. The - * implementation containing block is a function and scoping should be treated - * as such. Returning early may be performed with a bare "return;" statement. - * - * EXPECT_* and ASSERT_* are valid in a TEST() { } context. - */ -#define TEST_SIGNAL TEST_API(TEST_SIGNAL) - -/* FIXTURE(datatype name) { - * type property1; - * ... - * }; - * Defines the data provided to TEST_F()-defined tests as |self|. It should be - * populated and cleaned up using FIXTURE_SETUP and FIXTURE_TEARDOWN. - */ -#define FIXTURE TEST_API(FIXTURE) - -/* FIXTURE_DATA(datatype name) - * This call may be used when the type of the fixture data - * is needed. In general, this should not be needed unless - * the |self| is being passed to a helper directly. - */ -#define FIXTURE_DATA TEST_API(FIXTURE_DATA) - -/* FIXTURE_SETUP(fixture name) { implementation } - * Populates the required "setup" function for a fixture. An instance of the - * datatype defined with _FIXTURE_DATA will be exposed as |self| for the - * implementation. - * - * ASSERT_* are valid for use in this context and will prempt the execution - * of any dependent fixture tests. - * - * A bare "return;" statement may be used to return early. - */ -#define FIXTURE_SETUP TEST_API(FIXTURE_SETUP) - -/* FIXTURE_TEARDOWN(fixture name) { implementation } - * Populates the required "teardown" function for a fixture. An instance of the - * datatype defined with _FIXTURE_DATA will be exposed as |self| for the - * implementation to clean up. - * - * A bare "return;" statement may be used to return early. - */ -#define FIXTURE_TEARDOWN TEST_API(FIXTURE_TEARDOWN) - -/* TEST_F(fixture, name) { implementation } - * Defines a test that depends on a fixture (e.g., is part of a test case). - * Very similar to TEST() except that |self| is the setup instance of fixture's - * datatype exposed for use by the implementation. - */ -#define TEST_F TEST_API(TEST_F) - -#define TEST_F_SIGNAL TEST_API(TEST_F_SIGNAL) - -/* Use once to append a main() to the test file. E.g., - * TEST_HARNESS_MAIN - */ -#define TEST_HARNESS_MAIN TEST_API(TEST_HARNESS_MAIN) - -/* - * Operators for use in TEST and TEST_F. - * ASSERT_* calls will stop test execution immediately. - * EXPECT_* calls will emit a failure warning, note it, and continue. - */ - -/* ASSERT_EQ(expected, measured): expected == measured */ -#define ASSERT_EQ TEST_API(ASSERT_EQ) -/* ASSERT_NE(expected, measured): expected != measured */ -#define ASSERT_NE TEST_API(ASSERT_NE) -/* ASSERT_LT(expected, measured): expected < measured */ -#define ASSERT_LT TEST_API(ASSERT_LT) -/* ASSERT_LE(expected, measured): expected <= measured */ -#define ASSERT_LE TEST_API(ASSERT_LE) -/* ASSERT_GT(expected, measured): expected > measured */ -#define ASSERT_GT TEST_API(ASSERT_GT) -/* ASSERT_GE(expected, measured): expected >= measured */ -#define ASSERT_GE TEST_API(ASSERT_GE) -/* ASSERT_NULL(measured): NULL == measured */ -#define ASSERT_NULL TEST_API(ASSERT_NULL) -/* ASSERT_TRUE(measured): measured != 0 */ -#define ASSERT_TRUE TEST_API(ASSERT_TRUE) -/* ASSERT_FALSE(measured): measured == 0 */ -#define ASSERT_FALSE TEST_API(ASSERT_FALSE) -/* ASSERT_STREQ(expected, measured): !strcmp(expected, measured) */ -#define ASSERT_STREQ TEST_API(ASSERT_STREQ) -/* ASSERT_STRNE(expected, measured): strcmp(expected, measured) */ -#define ASSERT_STRNE TEST_API(ASSERT_STRNE) -/* EXPECT_EQ(expected, measured): expected == measured */ -#define EXPECT_EQ TEST_API(EXPECT_EQ) -/* EXPECT_NE(expected, measured): expected != measured */ -#define EXPECT_NE TEST_API(EXPECT_NE) -/* EXPECT_LT(expected, measured): expected < measured */ -#define EXPECT_LT TEST_API(EXPECT_LT) -/* EXPECT_LE(expected, measured): expected <= measured */ -#define EXPECT_LE TEST_API(EXPECT_LE) -/* EXPECT_GT(expected, measured): expected > measured */ -#define EXPECT_GT TEST_API(EXPECT_GT) -/* EXPECT_GE(expected, measured): expected >= measured */ -#define EXPECT_GE TEST_API(EXPECT_GE) -/* EXPECT_NULL(measured): NULL == measured */ -#define EXPECT_NULL TEST_API(EXPECT_NULL) -/* EXPECT_TRUE(measured): 0 != measured */ -#define EXPECT_TRUE TEST_API(EXPECT_TRUE) -/* EXPECT_FALSE(measured): 0 == measured */ -#define EXPECT_FALSE TEST_API(EXPECT_FALSE) -/* EXPECT_STREQ(expected, measured): !strcmp(expected, measured) */ -#define EXPECT_STREQ TEST_API(EXPECT_STREQ) -/* EXPECT_STRNE(expected, measured): strcmp(expected, measured) */ -#define EXPECT_STRNE TEST_API(EXPECT_STRNE) - -/* TH_LOG(format, ...) - * Optional debug logging function available for use in tests. - * Logging may be enabled or disabled by defining TH_LOG_ENABLED. - * E.g., #define TH_LOG_ENABLED 1 - * If no definition is provided, logging is enabled by default. - */ -#define TH_LOG TEST_API(TH_LOG) - -/* - * Internal implementation. - * - */ - -/* Utilities exposed to the test definitions */ -#ifndef TH_LOG_STREAM -# define TH_LOG_STREAM stderr -#endif - -#ifndef TH_LOG_ENABLED -# define TH_LOG_ENABLED 1 -#endif - -#define _TH_LOG(fmt, ...) do { \ - if (TH_LOG_ENABLED) \ - __TH_LOG(fmt, ##__VA_ARGS__); \ -} while (0) - -/* Unconditional logger for internal use. */ -#define __TH_LOG(fmt, ...) \ - fprintf(TH_LOG_STREAM, "%s:%d:%s:" fmt "\n", \ - __FILE__, __LINE__, _metadata->name, ##__VA_ARGS__) - -/* Defines the test function and creates the registration stub. */ -#define _TEST(test_name) __TEST_IMPL(test_name, -1) - -#define _TEST_SIGNAL(test_name, signal) __TEST_IMPL(test_name, signal) - -#define __TEST_IMPL(test_name, _signal) \ - static void test_name(struct __test_metadata *_metadata); \ - static struct __test_metadata _##test_name##_object = \ - { name: "global." #test_name, \ - fn: &test_name, termsig: _signal }; \ - static void __attribute__((constructor)) _register_##test_name(void) \ - { \ - __register_test(&_##test_name##_object); \ - } \ - static void test_name( \ - struct __test_metadata __attribute__((unused)) *_metadata) - -/* Wraps the struct name so we have one less argument to pass around. */ -#define _FIXTURE_DATA(fixture_name) struct _test_data_##fixture_name - -/* Called once per fixture to setup the data and register. */ -#define _FIXTURE(fixture_name) \ - static void __attribute__((constructor)) \ - _register_##fixture_name##_data(void) \ - { \ - __fixture_count++; \ - } \ - _FIXTURE_DATA(fixture_name) - -/* Prepares the setup function for the fixture. |_metadata| is included - * so that ASSERT_* work as a convenience. - */ -#define _FIXTURE_SETUP(fixture_name) \ - void fixture_name##_setup( \ - struct __test_metadata __attribute__((unused)) *_metadata, \ - _FIXTURE_DATA(fixture_name) __attribute__((unused)) *self) -#define _FIXTURE_TEARDOWN(fixture_name) \ - void fixture_name##_teardown( \ - struct __test_metadata __attribute__((unused)) *_metadata, \ - _FIXTURE_DATA(fixture_name) __attribute__((unused)) *self) - -/* Emits test registration and helpers for fixture-based test - * cases. - * TODO(wad) register fixtures on dedicated test lists. - */ -#define _TEST_F(fixture_name, test_name) \ - __TEST_F_IMPL(fixture_name, test_name, -1) - -#define _TEST_F_SIGNAL(fixture_name, test_name, signal) \ - __TEST_F_IMPL(fixture_name, test_name, signal) - -#define __TEST_F_IMPL(fixture_name, test_name, signal) \ - static void fixture_name##_##test_name( \ - struct __test_metadata *_metadata, \ - _FIXTURE_DATA(fixture_name) *self); \ - static inline void wrapper_##fixture_name##_##test_name( \ - struct __test_metadata *_metadata) \ - { \ - /* fixture data is alloced, setup, and torn down per call. */ \ - _FIXTURE_DATA(fixture_name) self; \ - memset(&self, 0, sizeof(_FIXTURE_DATA(fixture_name))); \ - fixture_name##_setup(_metadata, &self); \ - /* Let setup failure terminate early. */ \ - if (!_metadata->passed) \ - return; \ - fixture_name##_##test_name(_metadata, &self); \ - fixture_name##_teardown(_metadata, &self); \ - } \ - static struct __test_metadata \ - _##fixture_name##_##test_name##_object = { \ - name: #fixture_name "." #test_name, \ - fn: &wrapper_##fixture_name##_##test_name, \ - termsig: signal, \ - }; \ - static void __attribute__((constructor)) \ - _register_##fixture_name##_##test_name(void) \ - { \ - __register_test(&_##fixture_name##_##test_name##_object); \ - } \ - static void fixture_name##_##test_name( \ - struct __test_metadata __attribute__((unused)) *_metadata, \ - _FIXTURE_DATA(fixture_name) __attribute__((unused)) *self) - -/* Exports a simple wrapper to run the test harness. */ -#define _TEST_HARNESS_MAIN \ - static void __attribute__((constructor)) \ - __constructor_order_last(void) \ - { \ - if (!__constructor_order) \ - __constructor_order = _CONSTRUCTOR_ORDER_BACKWARD; \ - } \ - int main(int argc, char **argv) { \ - return test_harness_run(argc, argv); \ - } - -#define _ASSERT_EQ(_expected, _seen) \ - __EXPECT(_expected, _seen, ==, 1) -#define _ASSERT_NE(_expected, _seen) \ - __EXPECT(_expected, _seen, !=, 1) -#define _ASSERT_LT(_expected, _seen) \ - __EXPECT(_expected, _seen, <, 1) -#define _ASSERT_LE(_expected, _seen) \ - __EXPECT(_expected, _seen, <=, 1) -#define _ASSERT_GT(_expected, _seen) \ - __EXPECT(_expected, _seen, >, 1) -#define _ASSERT_GE(_expected, _seen) \ - __EXPECT(_expected, _seen, >=, 1) -#define _ASSERT_NULL(_seen) \ - __EXPECT(NULL, _seen, ==, 1) - -#define _ASSERT_TRUE(_seen) \ - _ASSERT_NE(0, _seen) -#define _ASSERT_FALSE(_seen) \ - _ASSERT_EQ(0, _seen) -#define _ASSERT_STREQ(_expected, _seen) \ - __EXPECT_STR(_expected, _seen, ==, 1) -#define _ASSERT_STRNE(_expected, _seen) \ - __EXPECT_STR(_expected, _seen, !=, 1) - -#define _EXPECT_EQ(_expected, _seen) \ - __EXPECT(_expected, _seen, ==, 0) -#define _EXPECT_NE(_expected, _seen) \ - __EXPECT(_expected, _seen, !=, 0) -#define _EXPECT_LT(_expected, _seen) \ - __EXPECT(_expected, _seen, <, 0) -#define _EXPECT_LE(_expected, _seen) \ - __EXPECT(_expected, _seen, <=, 0) -#define _EXPECT_GT(_expected, _seen) \ - __EXPECT(_expected, _seen, >, 0) -#define _EXPECT_GE(_expected, _seen) \ - __EXPECT(_expected, _seen, >=, 0) - -#define _EXPECT_NULL(_seen) \ - __EXPECT(NULL, _seen, ==, 0) -#define _EXPECT_TRUE(_seen) \ - _EXPECT_NE(0, _seen) -#define _EXPECT_FALSE(_seen) \ - _EXPECT_EQ(0, _seen) - -#define _EXPECT_STREQ(_expected, _seen) \ - __EXPECT_STR(_expected, _seen, ==, 0) -#define _EXPECT_STRNE(_expected, _seen) \ - __EXPECT_STR(_expected, _seen, !=, 0) - -#define ARRAY_SIZE(a) (sizeof(a) / sizeof(a[0])) - -/* Support an optional handler after and ASSERT_* or EXPECT_*. The approach is - * not thread-safe, but it should be fine in most sane test scenarios. - * - * Using __bail(), which optionally abort()s, is the easiest way to early - * return while still providing an optional block to the API consumer. - */ -#define OPTIONAL_HANDLER(_assert) \ - for (; _metadata->trigger; _metadata->trigger = __bail(_assert)) - -#define __EXPECT(_expected, _seen, _t, _assert) do { \ - /* Avoid multiple evaluation of the cases */ \ - __typeof__(_expected) __exp = (_expected); \ - __typeof__(_seen) __seen = (_seen); \ - if (!(__exp _t __seen)) { \ - unsigned long long __exp_print = (uintptr_t)__exp; \ - unsigned long long __seen_print = (uintptr_t)__seen; \ - __TH_LOG("Expected %s (%llu) %s %s (%llu)", \ - #_expected, __exp_print, #_t, \ - #_seen, __seen_print); \ - _metadata->passed = 0; \ - /* Ensure the optional handler is triggered */ \ - _metadata->trigger = 1; \ - } \ -} while (0); OPTIONAL_HANDLER(_assert) - -#define __EXPECT_STR(_expected, _seen, _t, _assert) do { \ - const char *__exp = (_expected); \ - const char *__seen = (_seen); \ - if (!(strcmp(__exp, __seen) _t 0)) { \ - __TH_LOG("Expected '%s' %s '%s'.", __exp, #_t, __seen); \ - _metadata->passed = 0; \ - _metadata->trigger = 1; \ - } \ -} while (0); OPTIONAL_HANDLER(_assert) - -/* Contains all the information for test execution and status checking. */ -struct __test_metadata { - const char *name; - void (*fn)(struct __test_metadata *); - int termsig; - int passed; - int trigger; /* extra handler after the evaluation */ - struct __test_metadata *prev, *next; -}; - -/* Storage for the (global) tests to be run. */ -static struct __test_metadata *__test_list; -static unsigned int __test_count; -static unsigned int __fixture_count; -static int __constructor_order; - -#define _CONSTRUCTOR_ORDER_FORWARD 1 -#define _CONSTRUCTOR_ORDER_BACKWARD -1 - -/* - * Since constructors are called in reverse order, reverse the test - * list so tests are run in source declaration order. - * https://gcc.gnu.org/onlinedocs/gccint/Initialization.html - * However, it seems not all toolchains do this correctly, so use - * __constructor_order to detect which direction is called first - * and adjust list building logic to get things running in the right - * direction. - */ -static inline void __register_test(struct __test_metadata *t) -{ - __test_count++; - /* Circular linked list where only prev is circular. */ - if (__test_list == NULL) { - __test_list = t; - t->next = NULL; - t->prev = t; - return; - } - if (__constructor_order == _CONSTRUCTOR_ORDER_FORWARD) { - t->next = NULL; - t->prev = __test_list->prev; - t->prev->next = t; - __test_list->prev = t; - } else { - t->next = __test_list; - t->next->prev = t; - t->prev = t; - __test_list = t; - } -} - -static inline int __bail(int for_realz) -{ - if (for_realz) - abort(); - return 0; -} - -void __run_test(struct __test_metadata *t) -{ - pid_t child_pid; - int status; - - t->passed = 1; - t->trigger = 0; - printf("[ RUN ] %s\n", t->name); - child_pid = fork(); - if (child_pid < 0) { - printf("ERROR SPAWNING TEST CHILD\n"); - t->passed = 0; - } else if (child_pid == 0) { - t->fn(t); - _exit(t->passed); - } else { - /* TODO(wad) add timeout support. */ - waitpid(child_pid, &status, 0); - if (WIFEXITED(status)) { - t->passed = t->termsig == -1 ? WEXITSTATUS(status) : 0; - if (t->termsig != -1) { - fprintf(TH_LOG_STREAM, - "%s: Test exited normally " - "instead of by signal (code: %d)\n", - t->name, - WEXITSTATUS(status)); - } - } else if (WIFSIGNALED(status)) { - t->passed = 0; - if (WTERMSIG(status) == SIGABRT) { - fprintf(TH_LOG_STREAM, - "%s: Test terminated by assertion\n", - t->name); - } else if (WTERMSIG(status) == t->termsig) { - t->passed = 1; - } else { - fprintf(TH_LOG_STREAM, - "%s: Test terminated unexpectedly " - "by signal %d\n", - t->name, - WTERMSIG(status)); - } - } else { - fprintf(TH_LOG_STREAM, - "%s: Test ended in some other way [%u]\n", - t->name, - status); - } - } - printf("[ %4s ] %s\n", (t->passed ? "OK" : "FAIL"), t->name); -} - -static int test_harness_run(int __attribute__((unused)) argc, - char __attribute__((unused)) **argv) -{ - struct __test_metadata *t; - int ret = 0; - unsigned int count = 0; - unsigned int pass_count = 0; - - /* TODO(wad) add optional arguments similar to gtest. */ - printf("[==========] Running %u tests from %u test cases.\n", - __test_count, __fixture_count + 1); - for (t = __test_list; t; t = t->next) { - count++; - __run_test(t); - if (t->passed) - pass_count++; - else - ret = 1; - } - printf("[==========] %u / %u tests passed.\n", pass_count, count); - printf("[ %s ]\n", (ret ? "FAILED" : "PASSED")); - return ret; -} - -static void __attribute__((constructor)) __constructor_order_first(void) -{ - if (!__constructor_order) - __constructor_order = _CONSTRUCTOR_ORDER_FORWARD; -} - -#endif /* TEST_HARNESS_H_ */ diff --git a/tools/testing/selftests/sigaltstack/sas.c b/tools/testing/selftests/sigaltstack/sas.c index ccd07343d418..7d406c3973ba 100644 --- a/tools/testing/selftests/sigaltstack/sas.c +++ b/tools/testing/selftests/sigaltstack/sas.c @@ -17,6 +17,8 @@ #include <assert.h> #include <errno.h> +#include "../kselftest.h" + #ifndef SS_AUTODISARM #define SS_AUTODISARM (1U << 31) #endif @@ -41,8 +43,7 @@ void my_usr1(int sig, siginfo_t *si, void *u) if (sp < (unsigned long)sstack || sp >= (unsigned long)sstack + SIGSTKSZ) { - printf("[FAIL]\tSP is not on sigaltstack\n"); - exit(EXIT_FAILURE); + ksft_exit_fail_msg("SP is not on sigaltstack\n"); } /* put some data on stack. other sighandler will try to overwrite it */ aa = alloca(1024); @@ -50,21 +51,22 @@ void my_usr1(int sig, siginfo_t *si, void *u) p = (struct stk_data *)(aa + 512); strcpy(p->msg, msg); p->flag = 1; - printf("[RUN]\tsignal USR1\n"); + ksft_print_msg("[RUN]\tsignal USR1\n"); err = sigaltstack(NULL, &stk); if (err) { - perror("[FAIL]\tsigaltstack()"); + ksft_exit_fail_msg("sigaltstack() - %s\n", strerror(errno)); exit(EXIT_FAILURE); } if (stk.ss_flags != SS_DISABLE) - printf("[FAIL]\tss_flags=%x, should be SS_DISABLE\n", + ksft_test_result_fail("tss_flags=%x, should be SS_DISABLE\n", stk.ss_flags); else - printf("[OK]\tsigaltstack is disabled in sighandler\n"); + ksft_test_result_pass( + "sigaltstack is disabled in sighandler\n"); swapcontext(&sc, &uc); - printf("%s\n", p->msg); + ksft_print_msg("%s\n", p->msg); if (!p->flag) { - printf("[RUN]\tAborting\n"); + ksft_exit_skip("[RUN]\tAborting\n"); exit(EXIT_FAILURE); } } @@ -74,13 +76,13 @@ void my_usr2(int sig, siginfo_t *si, void *u) char *aa; struct stk_data *p; - printf("[RUN]\tsignal USR2\n"); + ksft_print_msg("[RUN]\tsignal USR2\n"); aa = alloca(1024); /* dont run valgrind on this */ /* try to find the data stored by previous sighandler */ p = memmem(aa, 1024, msg, strlen(msg)); if (p) { - printf("[FAIL]\tsigaltstack re-used\n"); + ksft_test_result_fail("sigaltstack re-used\n"); /* corrupt the data */ strcpy(p->msg, msg2); /* tell other sighandler that his data is corrupted */ @@ -90,7 +92,7 @@ void my_usr2(int sig, siginfo_t *si, void *u) static void switch_fn(void) { - printf("[RUN]\tswitched to user ctx\n"); + ksft_print_msg("[RUN]\tswitched to user ctx\n"); raise(SIGUSR2); setcontext(&sc); } @@ -101,6 +103,8 @@ int main(void) stack_t stk; int err; + ksft_print_header(); + sigemptyset(&act.sa_mask); act.sa_flags = SA_ONSTACK | SA_SIGINFO; act.sa_sigaction = my_usr1; @@ -110,19 +114,20 @@ int main(void) sstack = mmap(NULL, SIGSTKSZ, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS | MAP_STACK, -1, 0); if (sstack == MAP_FAILED) { - perror("mmap()"); + ksft_exit_fail_msg("mmap() - %s\n", strerror(errno)); return EXIT_FAILURE; } err = sigaltstack(NULL, &stk); if (err) { - perror("[FAIL]\tsigaltstack()"); + ksft_exit_fail_msg("sigaltstack() - %s\n", strerror(errno)); exit(EXIT_FAILURE); } if (stk.ss_flags == SS_DISABLE) { - printf("[OK]\tInitial sigaltstack state was SS_DISABLE\n"); + ksft_test_result_pass( + "Initial sigaltstack state was SS_DISABLE\n"); } else { - printf("[FAIL]\tInitial sigaltstack state was %x; " + ksft_exit_fail_msg("Initial sigaltstack state was %x; " "should have been SS_DISABLE\n", stk.ss_flags); return EXIT_FAILURE; } @@ -133,7 +138,8 @@ int main(void) err = sigaltstack(&stk, NULL); if (err) { if (errno == EINVAL) { - printf("[NOTE]\tThe running kernel doesn't support SS_AUTODISARM\n"); + ksft_exit_skip( + "[NOTE]\tThe running kernel doesn't support SS_AUTODISARM\n"); /* * If test cases for the !SS_AUTODISARM variant were * added, we could still run them. We don't have any @@ -142,7 +148,9 @@ int main(void) */ return 0; } else { - perror("[FAIL]\tsigaltstack(SS_ONSTACK | SS_AUTODISARM)"); + ksft_exit_fail_msg( + "sigaltstack(SS_ONSTACK | SS_AUTODISARM) %s\n", + strerror(errno)); return EXIT_FAILURE; } } @@ -150,7 +158,7 @@ int main(void) ustack = mmap(NULL, SIGSTKSZ, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS | MAP_STACK, -1, 0); if (ustack == MAP_FAILED) { - perror("mmap()"); + ksft_exit_fail_msg("mmap() - %s\n", strerror(errno)); return EXIT_FAILURE; } getcontext(&uc); @@ -162,16 +170,17 @@ int main(void) err = sigaltstack(NULL, &stk); if (err) { - perror("[FAIL]\tsigaltstack()"); + ksft_exit_fail_msg("sigaltstack() - %s\n", strerror(errno)); exit(EXIT_FAILURE); } if (stk.ss_flags != SS_AUTODISARM) { - printf("[FAIL]\tss_flags=%x, should be SS_AUTODISARM\n", + ksft_exit_fail_msg("ss_flags=%x, should be SS_AUTODISARM\n", stk.ss_flags); exit(EXIT_FAILURE); } - printf("[OK]\tsigaltstack is still SS_AUTODISARM after signal\n"); + ksft_test_result_pass( + "sigaltstack is still SS_AUTODISARM after signal\n"); - printf("[OK]\tTest passed\n"); + ksft_exit_pass(); return 0; } diff --git a/tools/testing/selftests/size/get_size.c b/tools/testing/selftests/size/get_size.c index 2d1af7cca463..d4b59ab979a0 100644 --- a/tools/testing/selftests/size/get_size.c +++ b/tools/testing/selftests/size/get_size.c @@ -75,26 +75,31 @@ void _start(void) int ccode; struct sysinfo info; unsigned long used; + static const char *test_name = " get runtime memory use\n"; - print("Testing system size.\n"); - print("1..1\n"); + print("TAP version 13\n"); + print("# Testing system size.\n"); ccode = sysinfo(&info); if (ccode < 0) { - print("not ok 1 get runtime memory use\n"); - print("# could not get sysinfo\n"); + print("not ok 1"); + print(test_name); + print(" ---\n reason: \"could not get sysinfo\"\n ...\n"); _exit(ccode); } + print("ok 1"); + print(test_name); + /* ignore cache complexities for now */ used = info.totalram - info.freeram - info.bufferram; - print_k_value("ok 1 get runtime memory use # size = ", used, - info.mem_unit); - print("# System runtime memory report (units in Kilobytes):\n"); - print_k_value("# Total: ", info.totalram, info.mem_unit); - print_k_value("# Free: ", info.freeram, info.mem_unit); - print_k_value("# Buffer: ", info.bufferram, info.mem_unit); - print_k_value("# In use: ", used, info.mem_unit); + print(" ---\n"); + print_k_value(" Total: ", info.totalram, info.mem_unit); + print_k_value(" Free: ", info.freeram, info.mem_unit); + print_k_value(" Buffer: ", info.bufferram, info.mem_unit); + print_k_value(" In use: ", used, info.mem_unit); + print(" ...\n"); + print("1..1\n"); _exit(0); } diff --git a/tools/testing/selftests/splice/.gitignore b/tools/testing/selftests/splice/.gitignore new file mode 100644 index 000000000000..1e23fefd68e8 --- /dev/null +++ b/tools/testing/selftests/splice/.gitignore @@ -0,0 +1 @@ +default_file_splice_read diff --git a/tools/testing/selftests/splice/Makefile b/tools/testing/selftests/splice/Makefile index 9fc78e5e5451..7e1187e007fa 100644 --- a/tools/testing/selftests/splice/Makefile +++ b/tools/testing/selftests/splice/Makefile @@ -1,7 +1,4 @@ TEST_PROGS := default_file_splice_read.sh -EXTRA := default_file_splice_read -all: $(TEST_PROGS) $(EXTRA) +TEST_GEN_PROGS_EXTENDED := default_file_splice_read include ../lib.mk - -EXTRA_CLEAN := $(EXTRA) diff --git a/tools/testing/selftests/sync/sync_test.c b/tools/testing/selftests/sync/sync_test.c index 9ea08d9f0b13..7f7938263c5c 100644 --- a/tools/testing/selftests/sync/sync_test.c +++ b/tools/testing/selftests/sync/sync_test.c @@ -29,51 +29,85 @@ #include <unistd.h> #include <stdlib.h> #include <sys/types.h> +#include <sys/stat.h> #include <sys/wait.h> +#include <errno.h> +#include <string.h> +#include "../kselftest.h" #include "synctest.h" static int run_test(int (*test)(void), char *name) { int result; pid_t childpid; + int ret; fflush(stdout); childpid = fork(); if (childpid) { waitpid(childpid, &result, 0); - if (WIFEXITED(result)) - return WEXITSTATUS(result); + if (WIFEXITED(result)) { + ret = WEXITSTATUS(result); + if (!ret) + ksft_test_result_pass("[RUN]\t%s\n", name); + else + ksft_test_result_fail("[RUN]\t%s\n", name); + return ret; + } return 1; } - printf("[RUN]\tExecuting %s\n", name); exit(test()); } +static void sync_api_supported(void) +{ + struct stat sbuf; + int ret; + + ret = stat("/sys/kernel/debug/sync/sw_sync", &sbuf); + if (!ret) + return; + + if (errno == ENOENT) + ksft_exit_skip("Sync framework not supported by kernel\n"); + + if (errno == EACCES) + ksft_exit_skip("Run Sync test as root.\n"); + + ksft_exit_fail_msg("stat failed on /sys/kernel/debug/sync/sw_sync: %s", + strerror(errno)); +} + int main(void) { - int err = 0; + int err; + + ksft_print_header(); + + sync_api_supported(); - printf("[RUN]\tTesting sync framework\n"); + ksft_print_msg("[RUN]\tTesting sync framework\n"); - err += RUN_TEST(test_alloc_timeline); - err += RUN_TEST(test_alloc_fence); - err += RUN_TEST(test_alloc_fence_negative); + RUN_TEST(test_alloc_timeline); + RUN_TEST(test_alloc_fence); + RUN_TEST(test_alloc_fence_negative); - err += RUN_TEST(test_fence_one_timeline_wait); - err += RUN_TEST(test_fence_one_timeline_merge); - err += RUN_TEST(test_fence_merge_same_fence); - err += RUN_TEST(test_fence_multi_timeline_wait); - err += RUN_TEST(test_stress_two_threads_shared_timeline); - err += RUN_TEST(test_consumer_stress_multi_producer_single_consumer); - err += RUN_TEST(test_merge_stress_random_merge); + RUN_TEST(test_fence_one_timeline_wait); + RUN_TEST(test_fence_one_timeline_merge); + RUN_TEST(test_fence_merge_same_fence); + RUN_TEST(test_fence_multi_timeline_wait); + RUN_TEST(test_stress_two_threads_shared_timeline); + RUN_TEST(test_consumer_stress_multi_producer_single_consumer); + RUN_TEST(test_merge_stress_random_merge); + err = ksft_get_fail_cnt(); if (err) - printf("[FAIL]\tsync errors: %d\n", err); - else - printf("[OK]\tsync\n"); + ksft_exit_fail_msg("%d out of %d sync tests failed\n", + err, ksft_test_num()); - return !!err; + /* need this return to keep gcc happy */ + return ksft_exit_pass(); } diff --git a/tools/testing/selftests/sync/synctest.h b/tools/testing/selftests/sync/synctest.h index e7d1d57dba7a..90a8e5369914 100644 --- a/tools/testing/selftests/sync/synctest.h +++ b/tools/testing/selftests/sync/synctest.h @@ -29,10 +29,11 @@ #define SELFTESTS_SYNCTEST_H #include <stdio.h> +#include "../kselftest.h" #define ASSERT(cond, msg) do { \ if (!(cond)) { \ - printf("[ERROR]\t%s", (msg)); \ + ksft_print_msg("[ERROR]\t%s", (msg)); \ return 1; \ } \ } while (0) diff --git a/tools/testing/selftests/sysctl/Makefile b/tools/testing/selftests/sysctl/Makefile index b3c33e071f10..95c320b354e8 100644 --- a/tools/testing/selftests/sysctl/Makefile +++ b/tools/testing/selftests/sysctl/Makefile @@ -4,8 +4,7 @@ # No binaries, but make sure arg-less "make" doesn't trigger "run_tests". all: -TEST_PROGS := run_numerictests run_stringtests -TEST_FILES := common_tests +TEST_PROGS := sysctl.sh include ../lib.mk diff --git a/tools/testing/selftests/sysctl/common_tests b/tools/testing/selftests/sysctl/common_tests deleted file mode 100644 index 17d534b1b7b4..000000000000 --- a/tools/testing/selftests/sysctl/common_tests +++ /dev/null @@ -1,109 +0,0 @@ -#!/bin/sh - -TEST_FILE=$(mktemp) - -echo "== Testing sysctl behavior against ${TARGET} ==" - -set_orig() -{ - echo "${ORIG}" > "${TARGET}" -} - -set_test() -{ - echo "${TEST_STR}" > "${TARGET}" -} - -verify() -{ - local seen - seen=$(cat "$1") - if [ "${seen}" != "${TEST_STR}" ]; then - return 1 - fi - return 0 -} - -trap 'set_orig; rm -f "${TEST_FILE}"' EXIT - -rc=0 - -echo -n "Writing test file ... " -echo "${TEST_STR}" > "${TEST_FILE}" -if ! verify "${TEST_FILE}"; then - echo "FAIL" >&2 - exit 1 -else - echo "ok" -fi - -echo -n "Checking sysctl is not set to test value ... " -if verify "${TARGET}"; then - echo "FAIL" >&2 - exit 1 -else - echo "ok" -fi - -echo -n "Writing sysctl from shell ... " -set_test -if ! verify "${TARGET}"; then - echo "FAIL" >&2 - exit 1 -else - echo "ok" -fi - -echo -n "Resetting sysctl to original value ... " -set_orig -if verify "${TARGET}"; then - echo "FAIL" >&2 - exit 1 -else - echo "ok" -fi - -# Now that we've validated the sanity of "set_test" and "set_orig", -# we can use those functions to set starting states before running -# specific behavioral tests. - -echo -n "Writing entire sysctl in single write ... " -set_orig -dd if="${TEST_FILE}" of="${TARGET}" bs=4096 2>/dev/null -if ! verify "${TARGET}"; then - echo "FAIL" >&2 - rc=1 -else - echo "ok" -fi - -echo -n "Writing middle of sysctl after synchronized seek ... " -set_test -dd if="${TEST_FILE}" of="${TARGET}" bs=1 seek=1 skip=1 2>/dev/null -if ! verify "${TARGET}"; then - echo "FAIL" >&2 - rc=1 -else - echo "ok" -fi - -echo -n "Writing beyond end of sysctl ... " -set_orig -dd if="${TEST_FILE}" of="${TARGET}" bs=20 seek=2 2>/dev/null -if verify "${TARGET}"; then - echo "FAIL" >&2 - rc=1 -else - echo "ok" -fi - -echo -n "Writing sysctl with multiple long writes ... " -set_orig -(perl -e 'print "A" x 50;'; echo "${TEST_STR}") | \ - dd of="${TARGET}" bs=50 2>/dev/null -if verify "${TARGET}"; then - echo "FAIL" >&2 - rc=1 -else - echo "ok" -fi diff --git a/tools/testing/selftests/sysctl/config b/tools/testing/selftests/sysctl/config new file mode 100644 index 000000000000..6ca14800d755 --- /dev/null +++ b/tools/testing/selftests/sysctl/config @@ -0,0 +1 @@ +CONFIG_TEST_SYSCTL=y diff --git a/tools/testing/selftests/sysctl/run_numerictests b/tools/testing/selftests/sysctl/run_numerictests deleted file mode 100755 index 8510f93f2d14..000000000000 --- a/tools/testing/selftests/sysctl/run_numerictests +++ /dev/null @@ -1,10 +0,0 @@ -#!/bin/sh - -SYSCTL="/proc/sys" -TARGET="${SYSCTL}/vm/swappiness" -ORIG=$(cat "${TARGET}") -TEST_STR=$(( $ORIG + 1 )) - -. ./common_tests - -exit $rc diff --git a/tools/testing/selftests/sysctl/run_stringtests b/tools/testing/selftests/sysctl/run_stringtests deleted file mode 100755 index 90a9293d520c..000000000000 --- a/tools/testing/selftests/sysctl/run_stringtests +++ /dev/null @@ -1,77 +0,0 @@ -#!/bin/sh - -SYSCTL="/proc/sys" -TARGET="${SYSCTL}/kernel/domainname" -ORIG=$(cat "${TARGET}") -TEST_STR="Testing sysctl" - -. ./common_tests - -# Only string sysctls support seeking/appending. -MAXLEN=65 - -echo -n "Writing entire sysctl in short writes ... " -set_orig -dd if="${TEST_FILE}" of="${TARGET}" bs=1 2>/dev/null -if ! verify "${TARGET}"; then - echo "FAIL" >&2 - rc=1 -else - echo "ok" -fi - -echo -n "Writing middle of sysctl after unsynchronized seek ... " -set_test -dd if="${TEST_FILE}" of="${TARGET}" bs=1 seek=1 2>/dev/null -if verify "${TARGET}"; then - echo "FAIL" >&2 - rc=1 -else - echo "ok" -fi - -echo -n "Checking sysctl maxlen is at least $MAXLEN ... " -set_orig -perl -e 'print "A" x ('"${MAXLEN}"'-2), "B";' | \ - dd of="${TARGET}" bs="${MAXLEN}" 2>/dev/null -if ! grep -q B "${TARGET}"; then - echo "FAIL" >&2 - rc=1 -else - echo "ok" -fi - -echo -n "Checking sysctl keeps original string on overflow append ... " -set_orig -perl -e 'print "A" x ('"${MAXLEN}"'-1), "B";' | \ - dd of="${TARGET}" bs=$(( MAXLEN - 1 )) 2>/dev/null -if grep -q B "${TARGET}"; then - echo "FAIL" >&2 - rc=1 -else - echo "ok" -fi - -echo -n "Checking sysctl stays NULL terminated on write ... " -set_orig -perl -e 'print "A" x ('"${MAXLEN}"'-1), "B";' | \ - dd of="${TARGET}" bs="${MAXLEN}" 2>/dev/null -if grep -q B "${TARGET}"; then - echo "FAIL" >&2 - rc=1 -else - echo "ok" -fi - -echo -n "Checking sysctl stays NULL terminated on overwrite ... " -set_orig -perl -e 'print "A" x ('"${MAXLEN}"'-1), "BB";' | \ - dd of="${TARGET}" bs=$(( $MAXLEN + 1 )) 2>/dev/null -if grep -q B "${TARGET}"; then - echo "FAIL" >&2 - rc=1 -else - echo "ok" -fi - -exit $rc diff --git a/tools/testing/selftests/sysctl/sysctl.sh b/tools/testing/selftests/sysctl/sysctl.sh new file mode 100755 index 000000000000..ec232c3cfcaa --- /dev/null +++ b/tools/testing/selftests/sysctl/sysctl.sh @@ -0,0 +1,774 @@ +#!/bin/bash +# Copyright (C) 2017 Luis R. Rodriguez <mcgrof@kernel.org> +# +# This program is free software; you can redistribute it and/or modify it +# under the terms of the GNU General Public License as published by the Free +# Software Foundation; either version 2 of the License, or at your option any +# later version; or, when distributed separately from the Linux kernel or +# when incorporated into other software packages, subject to the following +# license: +# +# This program is free software; you can redistribute it and/or modify it +# under the terms of copyleft-next (version 0.3.1 or later) as published +# at http://copyleft-next.org/. + +# This performs a series tests against the proc sysctl interface. + +TEST_NAME="sysctl" +TEST_DRIVER="test_${TEST_NAME}" +TEST_DIR=$(dirname $0) +TEST_FILE=$(mktemp) + +# This represents +# +# TEST_ID:TEST_COUNT:ENABLED +# +# TEST_ID: is the test id number +# TEST_COUNT: number of times we should run the test +# ENABLED: 1 if enabled, 0 otherwise +# +# Once these are enabled please leave them as-is. Write your own test, +# we have tons of space. +ALL_TESTS="0001:1:1" +ALL_TESTS="$ALL_TESTS 0002:1:1" +ALL_TESTS="$ALL_TESTS 0003:1:1" +ALL_TESTS="$ALL_TESTS 0004:1:1" +ALL_TESTS="$ALL_TESTS 0005:3:1" + +test_modprobe() +{ + if [ ! -d $DIR ]; then + echo "$0: $DIR not present" >&2 + echo "You must have the following enabled in your kernel:" >&2 + cat $TEST_DIR/config >&2 + exit 1 + fi +} + +function allow_user_defaults() +{ + if [ -z $DIR ]; then + DIR="/sys/module/test_sysctl/" + fi + if [ -z $DEFAULT_NUM_TESTS ]; then + DEFAULT_NUM_TESTS=50 + fi + if [ -z $SYSCTL ]; then + SYSCTL="/proc/sys/debug/test_sysctl" + fi + if [ -z $PROD_SYSCTL ]; then + PROD_SYSCTL="/proc/sys" + fi + if [ -z $WRITES_STRICT ]; then + WRITES_STRICT="${PROD_SYSCTL}/kernel/sysctl_writes_strict" + fi +} + +function check_production_sysctl_writes_strict() +{ + echo -n "Checking production write strict setting ... " + if [ ! -e ${WRITES_STRICT} ]; then + echo "FAIL, but skip in case of old kernel" >&2 + else + old_strict=$(cat ${WRITES_STRICT}) + if [ "$old_strict" = "1" ]; then + echo "ok" + else + echo "FAIL, strict value is 0 but force to 1 to continue" >&2 + echo "1" > ${WRITES_STRICT} + fi + fi + + if [ -z $PAGE_SIZE ]; then + PAGE_SIZE=$(getconf PAGESIZE) + fi + if [ -z $MAX_DIGITS ]; then + MAX_DIGITS=$(($PAGE_SIZE/8)) + fi + if [ -z $INT_MAX ]; then + INT_MAX=$(getconf INT_MAX) + fi + if [ -z $UINT_MAX ]; then + UINT_MAX=$(getconf UINT_MAX) + fi +} + +test_reqs() +{ + uid=$(id -u) + if [ $uid -ne 0 ]; then + echo $msg must be run as root >&2 + exit 0 + fi + + if ! which perl 2> /dev/null > /dev/null; then + echo "$0: You need perl installed" + exit 1 + fi + if ! which getconf 2> /dev/null > /dev/null; then + echo "$0: You need getconf installed" + exit 1 + fi + if ! which diff 2> /dev/null > /dev/null; then + echo "$0: You need diff installed" + exit 1 + fi +} + +function load_req_mod() +{ + trap "test_modprobe" EXIT + + if [ ! -d $DIR ]; then + modprobe $TEST_DRIVER + if [ $? -ne 0 ]; then + exit + fi + fi +} + +reset_vals() +{ + VAL="" + TRIGGER=$(basename ${TARGET}) + case "$TRIGGER" in + int_0001) + VAL="60" + ;; + int_0002) + VAL="1" + ;; + uint_0001) + VAL="314" + ;; + string_0001) + VAL="(none)" + ;; + *) + ;; + esac + echo -n $VAL > $TARGET +} + +set_orig() +{ + if [ ! -z $TARGET ]; then + echo "${ORIG}" > "${TARGET}" + fi +} + +set_test() +{ + echo "${TEST_STR}" > "${TARGET}" +} + +verify() +{ + local seen + seen=$(cat "$1") + if [ "${seen}" != "${TEST_STR}" ]; then + return 1 + fi + return 0 +} + +verify_diff_w() +{ + echo "$TEST_STR" | diff -q -w -u - $1 + return $? +} + +test_rc() +{ + if [[ $rc != 0 ]]; then + echo "Failed test, return value: $rc" >&2 + exit $rc + fi +} + +test_finish() +{ + set_orig + rm -f "${TEST_FILE}" + + if [ ! -z ${old_strict} ]; then + echo ${old_strict} > ${WRITES_STRICT} + fi + exit $rc +} + +run_numerictests() +{ + echo "== Testing sysctl behavior against ${TARGET} ==" + + rc=0 + + echo -n "Writing test file ... " + echo "${TEST_STR}" > "${TEST_FILE}" + if ! verify "${TEST_FILE}"; then + echo "FAIL" >&2 + exit 1 + else + echo "ok" + fi + + echo -n "Checking sysctl is not set to test value ... " + if verify "${TARGET}"; then + echo "FAIL" >&2 + exit 1 + else + echo "ok" + fi + + echo -n "Writing sysctl from shell ... " + set_test + if ! verify "${TARGET}"; then + echo "FAIL" >&2 + exit 1 + else + echo "ok" + fi + + echo -n "Resetting sysctl to original value ... " + set_orig + if verify "${TARGET}"; then + echo "FAIL" >&2 + exit 1 + else + echo "ok" + fi + + # Now that we've validated the sanity of "set_test" and "set_orig", + # we can use those functions to set starting states before running + # specific behavioral tests. + + echo -n "Writing entire sysctl in single write ... " + set_orig + dd if="${TEST_FILE}" of="${TARGET}" bs=4096 2>/dev/null + if ! verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + + echo -n "Writing middle of sysctl after synchronized seek ... " + set_test + dd if="${TEST_FILE}" of="${TARGET}" bs=1 seek=1 skip=1 2>/dev/null + if ! verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + + echo -n "Writing beyond end of sysctl ... " + set_orig + dd if="${TEST_FILE}" of="${TARGET}" bs=20 seek=2 2>/dev/null + if verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + + echo -n "Writing sysctl with multiple long writes ... " + set_orig + (perl -e 'print "A" x 50;'; echo "${TEST_STR}") | \ + dd of="${TARGET}" bs=50 2>/dev/null + if verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + test_rc +} + +# Your test must accept digits 3 and 4 to use this +run_limit_digit() +{ + echo -n "Checking ignoring spaces up to PAGE_SIZE works on write ..." + reset_vals + + LIMIT=$((MAX_DIGITS -1)) + TEST_STR="3" + (perl -e 'print " " x '$LIMIT';'; echo "${TEST_STR}") | \ + dd of="${TARGET}" 2>/dev/null + + if ! verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + test_rc + + echo -n "Checking passing PAGE_SIZE of spaces fails on write ..." + reset_vals + + LIMIT=$((MAX_DIGITS)) + TEST_STR="4" + (perl -e 'print " " x '$LIMIT';'; echo "${TEST_STR}") | \ + dd of="${TARGET}" 2>/dev/null + + if verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + test_rc +} + +# You are using an int +run_limit_digit_int() +{ + echo -n "Testing INT_MAX works ..." + reset_vals + TEST_STR="$INT_MAX" + echo -n $TEST_STR > $TARGET + + if ! verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + test_rc + + echo -n "Testing INT_MAX + 1 will fail as expected..." + reset_vals + let TEST_STR=$INT_MAX+1 + echo -n $TEST_STR > $TARGET 2> /dev/null + + if verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + test_rc + + echo -n "Testing negative values will work as expected..." + reset_vals + TEST_STR="-3" + echo -n $TEST_STR > $TARGET 2> /dev/null + if ! verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + test_rc +} + +# You used an int array +run_limit_digit_int_array() +{ + echo -n "Testing array works as expected ... " + TEST_STR="4 3 2 1" + echo -n $TEST_STR > $TARGET + + if ! verify_diff_w "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + test_rc + + echo -n "Testing skipping trailing array elements works ... " + # Do not reset_vals, carry on the values from the last test. + # If we only echo in two digits the last two are left intact + TEST_STR="100 101" + echo -n $TEST_STR > $TARGET + # After we echo in, to help diff we need to set on TEST_STR what + # we expect the result to be. + TEST_STR="100 101 2 1" + + if ! verify_diff_w "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + test_rc + + echo -n "Testing PAGE_SIZE limit on array works ... " + # Do not reset_vals, carry on the values from the last test. + # Even if you use an int array, you are still restricted to + # MAX_DIGITS, this is a known limitation. Test limit works. + LIMIT=$((MAX_DIGITS -1)) + TEST_STR="9" + (perl -e 'print " " x '$LIMIT';'; echo "${TEST_STR}") | \ + dd of="${TARGET}" 2>/dev/null + + TEST_STR="9 101 2 1" + if ! verify_diff_w "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + test_rc + + echo -n "Testing exceeding PAGE_SIZE limit fails as expected ... " + # Do not reset_vals, carry on the values from the last test. + # Now go over limit. + LIMIT=$((MAX_DIGITS)) + TEST_STR="7" + (perl -e 'print " " x '$LIMIT';'; echo "${TEST_STR}") | \ + dd of="${TARGET}" 2>/dev/null + + TEST_STR="7 101 2 1" + if verify_diff_w "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + test_rc +} + +# You are using an unsigned int +run_limit_digit_uint() +{ + echo -n "Testing UINT_MAX works ..." + reset_vals + TEST_STR="$UINT_MAX" + echo -n $TEST_STR > $TARGET + + if ! verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + test_rc + + echo -n "Testing UINT_MAX + 1 will fail as expected..." + reset_vals + TEST_STR=$(($UINT_MAX+1)) + echo -n $TEST_STR > $TARGET 2> /dev/null + + if verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + test_rc + + echo -n "Testing negative values will not work as expected ..." + reset_vals + TEST_STR="-3" + echo -n $TEST_STR > $TARGET 2> /dev/null + + if verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + test_rc +} + +run_stringtests() +{ + echo -n "Writing entire sysctl in short writes ... " + set_orig + dd if="${TEST_FILE}" of="${TARGET}" bs=1 2>/dev/null + if ! verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + + echo -n "Writing middle of sysctl after unsynchronized seek ... " + set_test + dd if="${TEST_FILE}" of="${TARGET}" bs=1 seek=1 2>/dev/null + if verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + + echo -n "Checking sysctl maxlen is at least $MAXLEN ... " + set_orig + perl -e 'print "A" x ('"${MAXLEN}"'-2), "B";' | \ + dd of="${TARGET}" bs="${MAXLEN}" 2>/dev/null + if ! grep -q B "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + + echo -n "Checking sysctl keeps original string on overflow append ... " + set_orig + perl -e 'print "A" x ('"${MAXLEN}"'-1), "B";' | \ + dd of="${TARGET}" bs=$(( MAXLEN - 1 )) 2>/dev/null + if grep -q B "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + + echo -n "Checking sysctl stays NULL terminated on write ... " + set_orig + perl -e 'print "A" x ('"${MAXLEN}"'-1), "B";' | \ + dd of="${TARGET}" bs="${MAXLEN}" 2>/dev/null + if grep -q B "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + + echo -n "Checking sysctl stays NULL terminated on overwrite ... " + set_orig + perl -e 'print "A" x ('"${MAXLEN}"'-1), "BB";' | \ + dd of="${TARGET}" bs=$(( $MAXLEN + 1 )) 2>/dev/null + if grep -q B "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + + test_rc +} + +sysctl_test_0001() +{ + TARGET="${SYSCTL}/int_0001" + reset_vals + ORIG=$(cat "${TARGET}") + TEST_STR=$(( $ORIG + 1 )) + + run_numerictests + run_limit_digit +} + +sysctl_test_0002() +{ + TARGET="${SYSCTL}/string_0001" + reset_vals + ORIG=$(cat "${TARGET}") + TEST_STR="Testing sysctl" + # Only string sysctls support seeking/appending. + MAXLEN=65 + + run_numerictests + run_stringtests +} + +sysctl_test_0003() +{ + TARGET="${SYSCTL}/int_0002" + reset_vals + ORIG=$(cat "${TARGET}") + TEST_STR=$(( $ORIG + 1 )) + + run_numerictests + run_limit_digit + run_limit_digit_int +} + +sysctl_test_0004() +{ + TARGET="${SYSCTL}/uint_0001" + reset_vals + ORIG=$(cat "${TARGET}") + TEST_STR=$(( $ORIG + 1 )) + + run_numerictests + run_limit_digit + run_limit_digit_uint +} + +sysctl_test_0005() +{ + TARGET="${SYSCTL}/int_0003" + reset_vals + ORIG=$(cat "${TARGET}") + + run_limit_digit_int_array +} + +list_tests() +{ + echo "Test ID list:" + echo + echo "TEST_ID x NUM_TEST" + echo "TEST_ID: Test ID" + echo "NUM_TESTS: Number of recommended times to run the test" + echo + echo "0001 x $(get_test_count 0001) - tests proc_dointvec_minmax()" + echo "0002 x $(get_test_count 0002) - tests proc_dostring()" + echo "0003 x $(get_test_count 0003) - tests proc_dointvec()" + echo "0004 x $(get_test_count 0004) - tests proc_douintvec()" + echo "0005 x $(get_test_count 0005) - tests proc_douintvec() array" +} + +test_reqs + +usage() +{ + NUM_TESTS=$(grep -o ' ' <<<"$ALL_TESTS" | grep -c .) + let NUM_TESTS=$NUM_TESTS+1 + MAX_TEST=$(printf "%04d\n" $NUM_TESTS) + echo "Usage: $0 [ -t <4-number-digit> ] | [ -w <4-number-digit> ] |" + echo " [ -s <4-number-digit> ] | [ -c <4-number-digit> <test- count>" + echo " [ all ] [ -h | --help ] [ -l ]" + echo "" + echo "Valid tests: 0001-$MAX_TEST" + echo "" + echo " all Runs all tests (default)" + echo " -t Run test ID the number amount of times is recommended" + echo " -w Watch test ID run until it runs into an error" + echo " -c Run test ID once" + echo " -s Run test ID x test-count number of times" + echo " -l List all test ID list" + echo " -h|--help Help" + echo + echo "If an error every occurs execution will immediately terminate." + echo "If you are adding a new test try using -w <test-ID> first to" + echo "make sure the test passes a series of tests." + echo + echo Example uses: + echo + echo "$TEST_NAME.sh -- executes all tests" + echo "$TEST_NAME.sh -t 0002 -- Executes test ID 0002 number of times is recomended" + echo "$TEST_NAME.sh -w 0002 -- Watch test ID 0002 run until an error occurs" + echo "$TEST_NAME.sh -s 0002 -- Run test ID 0002 once" + echo "$TEST_NAME.sh -c 0002 3 -- Run test ID 0002 three times" + echo + list_tests + exit 1 +} + +function test_num() +{ + re='^[0-9]+$' + if ! [[ $1 =~ $re ]]; then + usage + fi +} + +function get_test_count() +{ + test_num $1 + TEST_DATA=$(echo $ALL_TESTS | awk '{print $'$1'}') + LAST_TWO=${TEST_DATA#*:*} + echo ${LAST_TWO%:*} +} + +function get_test_enabled() +{ + test_num $1 + TEST_DATA=$(echo $ALL_TESTS | awk '{print $'$1'}') + echo ${TEST_DATA#*:*:} +} + +function run_all_tests() +{ + for i in $ALL_TESTS ; do + TEST_ID=${i%:*:*} + ENABLED=$(get_test_enabled $TEST_ID) + TEST_COUNT=$(get_test_count $TEST_ID) + if [[ $ENABLED -eq "1" ]]; then + test_case $TEST_ID $TEST_COUNT + fi + done +} + +function watch_log() +{ + if [ $# -ne 3 ]; then + clear + fi + date + echo "Running test: $2 - run #$1" +} + +function watch_case() +{ + i=0 + while [ 1 ]; do + + if [ $# -eq 1 ]; then + test_num $1 + watch_log $i ${TEST_NAME}_test_$1 + ${TEST_NAME}_test_$1 + else + watch_log $i all + run_all_tests + fi + let i=$i+1 + done +} + +function test_case() +{ + NUM_TESTS=$DEFAULT_NUM_TESTS + if [ $# -eq 2 ]; then + NUM_TESTS=$2 + fi + + i=0 + while [ $i -lt $NUM_TESTS ]; do + test_num $1 + watch_log $i ${TEST_NAME}_test_$1 noclear + RUN_TEST=${TEST_NAME}_test_$1 + $RUN_TEST + let i=$i+1 + done +} + +function parse_args() +{ + if [ $# -eq 0 ]; then + run_all_tests + else + if [[ "$1" = "all" ]]; then + run_all_tests + elif [[ "$1" = "-w" ]]; then + shift + watch_case $@ + elif [[ "$1" = "-t" ]]; then + shift + test_num $1 + test_case $1 $(get_test_count $1) + elif [[ "$1" = "-c" ]]; then + shift + test_num $1 + test_num $2 + test_case $1 $2 + elif [[ "$1" = "-s" ]]; then + shift + test_case $1 1 + elif [[ "$1" = "-l" ]]; then + list_tests + elif [[ "$1" = "-h" || "$1" = "--help" ]]; then + usage + else + usage + fi + fi +} + +test_reqs +allow_user_defaults +check_production_sysctl_writes_strict +load_req_mod + +trap "test_finish" EXIT + +parse_args $@ + +exit 0 diff --git a/tools/testing/selftests/tc-testing/.gitignore b/tools/testing/selftests/tc-testing/.gitignore new file mode 100644 index 000000000000..c18dd8d83cee --- /dev/null +++ b/tools/testing/selftests/tc-testing/.gitignore @@ -0,0 +1 @@ +__pycache__/ diff --git a/tools/testing/selftests/tc-testing/README b/tools/testing/selftests/tc-testing/README new file mode 100644 index 000000000000..970ff294fec8 --- /dev/null +++ b/tools/testing/selftests/tc-testing/README @@ -0,0 +1,102 @@ +tdc - Linux Traffic Control (tc) unit testing suite + +Author: Lucas Bates - lucasb@mojatatu.com + +tdc is a Python script to load tc unit tests from a separate JSON file and +execute them inside a network namespace dedicated to the task. + + +REQUIREMENTS +------------ + +* Minimum Python version of 3.4. Earlier 3.X versions may work but are not + guaranteed. + +* The kernel must have network namespace support + +* The kernel must have veth support available, as a veth pair is created + prior to running the tests. + +* All tc-related features must be built in or available as modules. + To check what is required in current setup run: + ./tdc.py -c + + Note: + In the current release, tdc run will abort due to a failure in setup or + teardown commands - which includes not being able to run a test simply + because the kernel did not support a specific feature. (This will be + handled in a future version - the current workaround is to run the tests + on specific test categories that your kernel supports) + + +BEFORE YOU RUN +-------------- + +The path to the tc executable that will be most commonly tested can be defined +in the tdc_config.py file. Find the 'TC' entry in the NAMES dictionary and +define the path. + +If you need to test a different tc executable on the fly, you can do so by +using the -p option when running tdc: + ./tdc.py -p /path/to/tc + + +RUNNING TDC +----------- + +To use tdc, root privileges are required. tdc will not run otherwise. + +All tests are executed inside a network namespace to prevent conflicts +within the host. + +Running tdc without any arguments will run all tests. Refer to the section +on command line arguments for more information, or run: + ./tdc.py -h + +tdc will list the test names as they are being run, and print a summary in +TAP (Test Anything Protocol) format when they are done. If tests fail, +output captured from the failing test will be printed immediately following +the failed test in the TAP output. + + +USER-DEFINED CONSTANTS +---------------------- + +The tdc_config.py file contains multiple values that can be altered to suit +your needs. Any value in the NAMES dictionary can be altered without affecting +the tests to be run. These values are used in the tc commands that will be +executed as part of the test. More will be added as test cases require. + +Example: + $TC qdisc add dev $DEV1 ingress + + +COMMAND LINE ARGUMENTS +---------------------- + +Run tdc.py -h to see the full list of available arguments. + +-p PATH Specify the tc executable located at PATH to be used on this + test run +-c Show the available test case categories in this test file +-c CATEGORY Run only tests that belong to CATEGORY +-f FILE Read test cases from the JSON file named FILE +-l [CATEGORY] List all test cases in the JSON file. If CATEGORY is + specified, list test cases matching that category. +-s ID Show the test case matching ID +-e ID Execute the test case identified by ID +-i Generate unique ID numbers for test cases with no existing + ID number + + +ACKNOWLEDGEMENTS +---------------- + +Thanks to: + +Jamal Hadi Salim, for providing valuable test cases +Keara Leibovitz, who wrote the CLI test driver that I used as a base for the + first version of the tc testing suite. This work was presented at + Netdev 1.2 Tokyo in October 2016. +Samir Hussain, for providing help while I dove into Python for the first time + and being a second eye for this code. diff --git a/tools/testing/selftests/tc-testing/TODO.txt b/tools/testing/selftests/tc-testing/TODO.txt new file mode 100644 index 000000000000..6a266d811a78 --- /dev/null +++ b/tools/testing/selftests/tc-testing/TODO.txt @@ -0,0 +1,10 @@ +tc Testing Suite To-Do list: + +- Determine what tc features are supported in the kernel. If features are not + present, prevent the related categories from running. + +- Add support for multiple versions of tc to run successively + +- Improve error messages when tdc aborts its run + +- Allow tdc to write its results to file diff --git a/tools/testing/selftests/tc-testing/creating-testcases/AddingTestCases.txt b/tools/testing/selftests/tc-testing/creating-testcases/AddingTestCases.txt new file mode 100644 index 000000000000..4e09257bc443 --- /dev/null +++ b/tools/testing/selftests/tc-testing/creating-testcases/AddingTestCases.txt @@ -0,0 +1,69 @@ +tdc - Adding test cases for tdc + +Author: Lucas Bates - lucasb@mojatatu.com + +ADDING TEST CASES +----------------- + +User-defined tests should be added by defining a separate JSON file. This +will help prevent conflicts when updating the repository. Refer to +template.json for the required JSON format for test cases. + +Include the 'id' field, but do not assign a value. Running tdc with the -i +option will generate a unique ID for that test case. + +tdc will recursively search the 'tc' subdirectory for .json files. Any +test case files you create in these directories will automatically be included. +If you wish to store your custom test cases elsewhere, be sure to run tdc +with the -f argument and the path to your file. + +Be aware of required escape characters in the JSON data - particularly when +defining the match pattern. Refer to the tctests.json file for examples when +in doubt. + + +TEST CASE STRUCTURE +------------------- + +Each test case has required data: + +id: A unique alphanumeric value to identify a particular test case +name: Descriptive name that explains the command under test +category: A list of single-word descriptions covering what the command + under test is testing. Example: filter, actions, u32, gact, etc. +setup: The list of commands required to ensure the command under test + succeeds. For example: if testing a filter, the command to create + the qdisc would appear here. +cmdUnderTest: The tc command being tested itself. +expExitCode: The code returned by the command under test upon its termination. + tdc will compare this value against the actual returned value. +verifyCmd: The tc command to be run to verify successful execution. + For example: if the command under test creates a gact action, + verifyCmd should be "$TC actions show action gact" +matchPattern: A regular expression to be applied against the output of the + verifyCmd to prove the command under test succeeded. This pattern + should be as specific as possible so that a false positive is not + matched. +matchCount: How many times the regex in matchPattern should match. A value + of 0 is acceptable. +teardown: The list of commands to clean up after the test is completed. + The environment should be returned to the same state as when + this test was started: qdiscs deleted, actions flushed, etc. + + +SETUP/TEARDOWN ERRORS +--------------------- + +If an error is detected during the setup/teardown process, execution of the +tests will immediately stop with an error message and the namespace in which +the tests are run will be destroyed. This is to prevent inaccurate results +in the test cases. + +Repeated failures of the setup/teardown may indicate a problem with the test +case, or possibly even a bug in one of the commands that are not being tested. + +It's possible to include acceptable exit codes with the setup/teardown command +so that it doesn't halt the script for an error that doesn't matter. Turn the +individual command into a list, with the command being first, followed by all +acceptable exit codes for the command. + diff --git a/tools/testing/selftests/tc-testing/creating-testcases/template.json b/tools/testing/selftests/tc-testing/creating-testcases/template.json new file mode 100644 index 000000000000..87971744bdd4 --- /dev/null +++ b/tools/testing/selftests/tc-testing/creating-testcases/template.json @@ -0,0 +1,40 @@ +[ + { + "id": "", + "name": "", + "category": [ + "", + "" + ], + "setup": [ + "" + ], + "cmdUnderTest": "", + "expExitCode": "", + "verifyCmd": "", + "matchPattern": "", + "matchCount": "", + "teardown": [ + "" + ] + }, + { + "id": "", + "name": "", + "category": [ + "", + "" + ], + "setup": [ + "" + ], + "cmdUnderTest": "", + "expExitCode": "", + "verifyCmd": "", + "matchPattern": "", + "matchCount": "", + "teardown": [ + "" + ] + } +] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/tests.json b/tools/testing/selftests/tc-testing/tc-tests/actions/tests.json new file mode 100644 index 000000000000..6973bdc5b5bf --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/tests.json @@ -0,0 +1,1165 @@ +[ + { + "id": "e89a", + "name": "Add valid pass action", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action pass index 8", + "expExitCode": "0", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action pass.*index 8 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "a02c", + "name": "Add valid pipe action", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action pipe index 6", + "expExitCode": "0", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action pipe.*index 6 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "feef", + "name": "Add valid reclassify action", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action reclassify index 5", + "expExitCode": "0", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action reclassify.*index 5 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "8a7a", + "name": "Add valid drop action", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action drop index 30", + "expExitCode": "0", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action drop.*index 30 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "9a52", + "name": "Add valid continue action", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action continue index 432", + "expExitCode": "0", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action continue.*index 432 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "d700", + "name": "Add invalid action", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action pump index 386", + "expExitCode": "255", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action.*index 386 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "9215", + "name": "Add action with duplicate index", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ], + "$TC actions add action pipe index 15" + ], + "cmdUnderTest": "$TC actions add action drop index 15", + "expExitCode": "255", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action drop.*index 15 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "798e", + "name": "Add action with index exceeding 32-bit maximum", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action drop index 4294967296", + "expExitCode": "255", + "verifyCmd": "actions list action gact", + "matchPattern": "action order [0-9]*: gact action drop.*index 4294967296 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "22be", + "name": "Add action with index at 32-bit maximum", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action drop index 4294967295", + "expExitCode": "0", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action drop.*index 4294967295 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "ac2a", + "name": "List actions", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ], + "$TC actions add action reclassify index 101", + "$TC actions add action reclassify index 102", + "$TC actions add action reclassify index 103", + "$TC actions add action reclassify index 104", + "$TC actions add action reclassify index 105" + ], + "cmdUnderTest": "$TC actions list action gact", + "expExitCode": "0", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action reclassify", + "matchCount": "5", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "63ec", + "name": "Delete pass action", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ], + "$TC actions add action pass index 1" + ], + "cmdUnderTest": "$TC actions del action gact index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action pass.*index 1 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "46be", + "name": "Delete pipe action", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ], + "$TC actions add action pipe index 9" + ], + "cmdUnderTest": "$TC actions del action gact index 9", + "expExitCode": "0", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action pipe.*index 9 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "2e08", + "name": "Delete reclassify action", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ], + "$TC actions add action reclassify index 65536" + ], + "cmdUnderTest": "$TC actions del action gact index 65536", + "expExitCode": "0", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action reclassify.*index 65536 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "99c4", + "name": "Delete drop action", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ], + "$TC actions add action drop index 16" + ], + "cmdUnderTest": "$TC actions del action gact index 16", + "expExitCode": "0", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action drop.*index 16 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "fb6b", + "name": "Delete continue action", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ], + "$TC actions add action continue index 32" + ], + "cmdUnderTest": "$TC actions del action gact index 32", + "expExitCode": "0", + "verifyCmd": "actions list action gact", + "matchPattern": "action order [0-9]*: gact action continue.*index 32 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "0eb3", + "name": "Delete non-existent action", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions del action gact index 2", + "expExitCode": "255", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action", + "matchCount": "0", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "5124", + "name": "Add mirred mirror to egress action", + "category": [ + "actions", + "mirred" + ], + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action mirred egress mirror index 1 dev lo", + "expExitCode": "0", + "verifyCmd": "$TC actions list action mirred", + "matchPattern": "action order [0-9]*: mirred \\(Egress Mirror to device lo\\).*index 1 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action mirred" + ] + }, + { + "id": "6fb4", + "name": "Add mirred redirect to egress action", + "category": [ + "actions", + "mirred" + ], + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action mirred egress redirect index 2 dev lo action pipe", + "expExitCode": "0", + "verifyCmd": "$TC actions list action mirred", + "matchPattern": "action order [0-9]*: mirred \\(Egress Redirect to device lo\\).*index 2 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action mirred" + ] + }, + { + "id": "ba38", + "name": "Get mirred actions", + "category": [ + "actions", + "mirred" + ], + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ], + "$TC actions add action mirred egress mirror index 1 dev lo", + "$TC actions add action mirred egress redirect index 2 dev lo" + ], + "cmdUnderTest": "$TC actions show action mirred", + "expExitCode": "0", + "verifyCmd": "$TC actions list action mirred", + "matchPattern": "[Mirror|Redirect] to device lo", + "matchCount": "2", + "teardown": [ + "$TC actions flush action mirred" + ] + }, + { + "id": "d7c0", + "name": "Add invalid mirred direction", + "category": [ + "actions", + "mirred" + ], + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action mirred inbound mirror index 20 dev lo", + "expExitCode": "255", + "verifyCmd": "$TC actions list action mirred", + "matchPattern": "action order [0-9]*: mirred \\(.*to device lo\\).*index 20 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action mirred" + ] + }, + { + "id": "e213", + "name": "Add invalid mirred action", + "category": [ + "actions", + "mirred" + ], + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action mirred egress remirror index 20 dev lo", + "expExitCode": "255", + "verifyCmd": "$TC actions list action mirred", + "matchPattern": "action order [0-9]*: mirred \\(Egress.*to device lo\\).*index 20 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action mirred" + ] + }, + { + "id": "2d89", + "name": "Add mirred action with invalid device", + "category": [ + "actions", + "mirred" + ], + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action mirred egress mirror index 20 dev eltoh", + "expExitCode": "255", + "verifyCmd": "$TC actions list action mirred", + "matchPattern": "action order [0-9]*: mirred \\(.*to device eltoh\\).*index 20 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action mirred" + ] + }, + { + "id": "300b", + "name": "Add mirred action with duplicate index", + "category": [ + "actions", + "mirred" + ], + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ], + "$TC actions add action mirred egress redirect index 15 dev lo" + ], + "cmdUnderTest": "$TC actions add action mirred egress mirror index 15 dev lo", + "expExitCode": "255", + "verifyCmd": "$TC actions list action mirred", + "matchPattern": "action order [0-9]*: mirred \\(.*to device lo\\).*index 15 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action mirred" + ] + }, + { + "id": "a70e", + "name": "Delete mirred mirror action", + "category": [ + "actions", + "mirred" + ], + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ], + "$TC actions add action mirred egress mirror index 5 dev lo" + ], + "cmdUnderTest": "$TC actions del action mirred index 5", + "expExitCode": "0", + "verifyCmd": "$TC actions list action mirred", + "matchPattern": "action order [0-9]*: mirred \\(Egress Mirror to device lo\\).*index 5 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action mirred" + ] + }, + { + "id": "3fb3", + "name": "Delete mirred redirect action", + "category": [ + "actions", + "mirred" + ], + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ], + "$TC actions add action mirred egress redirect index 5 dev lo" + ], + "cmdUnderTest": "$TC actions del action mirred index 5", + "expExitCode": "0", + "verifyCmd": "$TC actions list action mirred", + "matchPattern": "action order [0-9]*: mirred \\(Egress Redirect to device lo\\).*index 5 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action mirred" + ] + }, + { + "id": "b078", + "name": "Add simple action", + "category": [ + "actions", + "simple" + ], + "setup": [ + [ + "$TC actions flush action simple", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action simple sdata \"A triumph\" index 60", + "expExitCode": "0", + "verifyCmd": "$TC actions list action simple", + "matchPattern": "action order [0-9]*: Simple <A triumph>.*index 60 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action simple" + ] + }, + { + "id": "6d4c", + "name": "Add simple action with duplicate index", + "category": [ + "actions", + "simple" + ], + "setup": [ + [ + "$TC actions flush action simple", + 0, + 1, + 255 + ], + "$TC actions add action simple sdata \"Aruba\" index 4" + ], + "cmdUnderTest": "$TC actions add action simple sdata \"Jamaica\" index 4", + "expExitCode": "255", + "verifyCmd": "$TC actions list action simple", + "matchPattern": "action order [0-9]*: Simple <Jamaica>.*ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action simple" + ] + }, + { + "id": "2542", + "name": "List simple actions", + "category": [ + "actions", + "simple" + ], + "setup": [ + [ + "$TC actions flush action simple", + 0, + 1, + 255 + ], + "$TC actions add action simple sdata \"Rock\"", + "$TC actions add action simple sdata \"Paper\"", + "$TC actions add action simple sdata \"Scissors\" index 98" + ], + "cmdUnderTest": "$TC actions list action simple", + "expExitCode": "0", + "verifyCmd": "$TC actions list action simple", + "matchPattern": "action order [0-9]*: Simple <[A-Z][a-z]*>", + "matchCount": "3", + "teardown": [ + "$TC actions flush action simple" + ] + }, + { + "id": "ea67", + "name": "Delete simple action", + "category": [ + "actions", + "simple" + ], + "setup": [ + [ + "$TC actions flush action simple", + 0, + 1, + 255 + ], + "$TC actions add action simple sdata \"Blinkenlights\" index 1" + ], + "cmdUnderTest": "$TC actions delete action simple index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions list action simple", + "matchPattern": "action order [0-9]*: Simple <Blinkenlights>.*index 1 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action simple" + ] + }, + { + "id": "8ff1", + "name": "Flush simple actions", + "category": [ + "actions", + "simple" + ], + "setup": [ + [ + "$TC actions flush action simple", + 0, + 1, + 255 + ], + "$TC actions add action simple sdata \"Kirk\"", + "$TC actions add action simple sdata \"Spock\" index 50", + "$TC actions add action simple sdata \"McCoy\" index 9" + ], + "cmdUnderTest": "$TC actions flush action simple", + "expExitCode": "0", + "verifyCmd": "$TC actions list action simple", + "matchPattern": "action order [0-9]*: Simple <[A-Z][a-z]*>", + "matchCount": "0", + "teardown": [ + "" + ] + }, + { + "id": "6236", + "name": "Add skbedit action with valid mark", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbedit mark 1", + "expExitCode": "0", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit mark 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "407b", + "name": "Add skbedit action with invalid mark", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbedit mark 666777888999", + "expExitCode": "255", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit mark", + "matchCount": "0", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "081d", + "name": "Add skbedit action with priority", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbedit prio 99", + "expExitCode": "0", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit priority :99", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "cc37", + "name": "Add skbedit action with invalid priority", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbedit prio foo", + "expExitCode": "255", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit priority", + "matchCount": "0", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "3c95", + "name": "Add skbedit action with queue_mapping", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbedit queue_mapping 909", + "expExitCode": "0", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit queue_mapping 909", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "985c", + "name": "Add skbedit action with invalid queue_mapping", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbedit queue_mapping 67000", + "expExitCode": "255", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit queue_mapping", + "matchCount": "0", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "224f", + "name": "Add skbedit action with ptype host", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbedit ptype host", + "expExitCode": "0", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit ptype host", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "d1a3", + "name": "Add skbedit action with ptype otherhost", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbedit ptype otherhost", + "expExitCode": "0", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit ptype otherhost", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "b9c6", + "name": "Add skbedit action with invalid ptype", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbedit ptype openair", + "expExitCode": "255", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit ptype openair", + "matchCount": "0", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "5172", + "name": "List skbedit actions", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ], + "$TC actions add action skbedit ptype otherhost", + "$TC actions add action skbedit ptype broadcast", + "$TC actions add action skbedit mark 59", + "$TC actions add action skbedit mark 409" + ], + "cmdUnderTest": "$TC actions list action skbedit", + "expExitCode": "0", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit", + "matchCount": "4", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "a6d6", + "name": "Add skbedit action with index", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbedit mark 808 index 4040404040", + "expExitCode": "0", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "index 4040404040", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "38f3", + "name": "Delete skbedit action", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ], + "$TC actions add action skbedit mark 42 index 9009" + ], + "cmdUnderTest": "$TC actions del action skbedit index 9009", + "expExitCode": "0", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit mark 42", + "matchCount": "0", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "ce97", + "name": "Flush skbedit actions", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + "$TC actions add action skbedit mark 500", + "$TC actions add action skbedit mark 501", + "$TC actions add action skbedit mark 502", + "$TC actions add action skbedit mark 503", + "$TC actions add action skbedit mark 504", + "$TC actions add action skbedit mark 505", + "$TC actions add action skbedit mark 506" + ], + "cmdUnderTest": "$TC actions flush action skbedit", + "expExitCode": "0", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit", + "matchCount": "0", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "f02c", + "name": "Replace gact action", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ], + "$TC actions add action drop index 10", + "$TC actions add action drop index 12" + ], + "cmdUnderTest": "$TC actions replace action ok index 12", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action gact", + "matchPattern": "action order [0-9]*: gact action pass", + "matchCount": "1", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "525f", + "name": "Get gact action by index", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ], + "$TC actions add action drop index 3900800700" + ], + "cmdUnderTest": "$TC actions get action gact index 3900800700", + "expExitCode": "0", + "verifyCmd": "$TC actions get action gact index 3900800700", + "matchPattern": "index 3900800700", + "matchCount": "1", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "a568", + "name": "Add action with ife type", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ], + "$TC actions add action ife encode type 0xDEAD index 1" + ], + "cmdUnderTest": "$TC actions get action ife index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "type 0xDEAD", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "b983", + "name": "Add action without ife type", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ], + "$TC actions add action ife encode index 1" + ], + "cmdUnderTest": "$TC actions get action ife index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "type 0xED3E", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + } +]
\ No newline at end of file diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json new file mode 100644 index 000000000000..c727b96a59b0 --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json @@ -0,0 +1,21 @@ +[ + { + "id": "e9a3", + "name": "Add u32 with source match", + "category": [ + "filter", + "u32" + ], + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: protocol ip prio 1 u32 match ip src 127.0.0.1/32 flowid 1:1 action ok", + "expExitCode": "0", + "verifyCmd": "$TC filter show dev $DEV1 parent ffff:", + "matchPattern": "match 7f000002/ffffffff at 12", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + } +]
\ No newline at end of file diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py new file mode 100755 index 000000000000..cd61b7844c0d --- /dev/null +++ b/tools/testing/selftests/tc-testing/tdc.py @@ -0,0 +1,413 @@ +#!/usr/bin/env python3 + +""" +tdc.py - Linux tc (Traffic Control) unit test driver + +Copyright (C) 2017 Lucas Bates <lucasb@mojatatu.com> +""" + +import re +import os +import sys +import argparse +import json +import subprocess +from collections import OrderedDict +from string import Template + +from tdc_config import * +from tdc_helper import * + + +USE_NS = True + + +def replace_keywords(cmd): + """ + For a given executable command, substitute any known + variables contained within NAMES with the correct values + """ + tcmd = Template(cmd) + subcmd = tcmd.safe_substitute(NAMES) + return subcmd + + +def exec_cmd(command, nsonly=True): + """ + Perform any required modifications on an executable command, then run + it in a subprocess and return the results. + """ + if (USE_NS and nsonly): + command = 'ip netns exec $NS ' + command + + if '$' in command: + command = replace_keywords(command) + + proc = subprocess.Popen(command, + shell=True, + stdout=subprocess.PIPE, + stderr=subprocess.PIPE) + (rawout, serr) = proc.communicate() + + if proc.returncode != 0: + foutput = serr.decode("utf-8") + else: + foutput = rawout.decode("utf-8") + + proc.stdout.close() + proc.stderr.close() + return proc, foutput + + +def prepare_env(cmdlist): + """ + Execute the setup/teardown commands for a test case. Optionally + terminate test execution if the command fails. + """ + for cmdinfo in cmdlist: + if (type(cmdinfo) == list): + exit_codes = cmdinfo[1:] + cmd = cmdinfo[0] + else: + exit_codes = [0] + cmd = cmdinfo + + if (len(cmd) == 0): + continue + + (proc, foutput) = exec_cmd(cmd) + + if proc.returncode not in exit_codes: + print + print("Could not execute:") + print(cmd) + print("\nError message:") + print(foutput) + print("\nAborting test run.") + ns_destroy() + exit(1) + + +def test_runner(filtered_tests): + """ + Driver function for the unit tests. + + Prints information about the tests being run, executes the setup and + teardown commands and the command under test itself. Also determines + success/failure based on the information in the test case and generates + TAP output accordingly. + """ + testlist = filtered_tests + tcount = len(testlist) + index = 1 + tap = str(index) + ".." + str(tcount) + "\n" + + for tidx in testlist: + result = True + tresult = "" + print("Test " + tidx["id"] + ": " + tidx["name"]) + prepare_env(tidx["setup"]) + (p, procout) = exec_cmd(tidx["cmdUnderTest"]) + exit_code = p.returncode + + if (exit_code != int(tidx["expExitCode"])): + result = False + print("exit:", exit_code, int(tidx["expExitCode"])) + print(procout) + else: + match_pattern = re.compile(str(tidx["matchPattern"]), re.DOTALL) + (p, procout) = exec_cmd(tidx["verifyCmd"]) + match_index = re.findall(match_pattern, procout) + if len(match_index) != int(tidx["matchCount"]): + result = False + + if result == True: + tresult += "ok " + else: + tresult += "not ok " + tap += tresult + str(index) + " " + tidx["id"] + " " + tidx["name"] + "\n" + + if result == False: + tap += procout + + prepare_env(tidx["teardown"]) + index += 1 + + return tap + + +def ns_create(): + """ + Create the network namespace in which the tests will be run and set up + the required network devices for it. + """ + if (USE_NS): + cmd = 'ip netns add $NS' + exec_cmd(cmd, False) + cmd = 'ip link add $DEV0 type veth peer name $DEV1' + exec_cmd(cmd, False) + cmd = 'ip link set $DEV1 netns $NS' + exec_cmd(cmd, False) + cmd = 'ip link set $DEV0 up' + exec_cmd(cmd, False) + cmd = 'ip -s $NS link set $DEV1 up' + exec_cmd(cmd, False) + + +def ns_destroy(): + """ + Destroy the network namespace for testing (and any associated network + devices as well) + """ + if (USE_NS): + cmd = 'ip netns delete $NS' + exec_cmd(cmd, False) + + +def has_blank_ids(idlist): + """ + Search the list for empty ID fields and return true/false accordingly. + """ + return not(all(k for k in idlist)) + + +def load_from_file(filename): + """ + Open the JSON file containing the test cases and return them as an + ordered dictionary object. + """ + with open(filename) as test_data: + testlist = json.load(test_data, object_pairs_hook=OrderedDict) + idlist = get_id_list(testlist) + if (has_blank_ids(idlist)): + for k in testlist: + k['filename'] = filename + return testlist + + +def args_parse(): + """ + Create the argument parser. + """ + parser = argparse.ArgumentParser(description='Linux TC unit tests') + return parser + + +def set_args(parser): + """ + Set the command line arguments for tdc. + """ + parser.add_argument('-p', '--path', type=str, + help='The full path to the tc executable to use') + parser.add_argument('-c', '--category', type=str, nargs='?', const='+c', + help='Run tests only from the specified category, or if no category is specified, list known categories.') + parser.add_argument('-f', '--file', type=str, + help='Run tests from the specified file') + parser.add_argument('-l', '--list', type=str, nargs='?', const="", metavar='CATEGORY', + help='List all test cases, or those only within the specified category') + parser.add_argument('-s', '--show', type=str, nargs=1, metavar='ID', dest='showID', + help='Display the test case with specified id') + parser.add_argument('-e', '--execute', type=str, nargs=1, metavar='ID', + help='Execute the single test case with specified ID') + parser.add_argument('-i', '--id', action='store_true', dest='gen_id', + help='Generate ID numbers for new test cases') + return parser + return parser + + +def check_default_settings(args): + """ + Process any arguments overriding the default settings, and ensure the + settings are correct. + """ + # Allow for overriding specific settings + global NAMES + + if args.path != None: + NAMES['TC'] = args.path + if not os.path.isfile(NAMES['TC']): + print("The specified tc path " + NAMES['TC'] + " does not exist.") + exit(1) + + +def get_id_list(alltests): + """ + Generate a list of all IDs in the test cases. + """ + return [x["id"] for x in alltests] + + +def check_case_id(alltests): + """ + Check for duplicate test case IDs. + """ + idl = get_id_list(alltests) + return [x for x in idl if idl.count(x) > 1] + + +def does_id_exist(alltests, newid): + """ + Check if a given ID already exists in the list of test cases. + """ + idl = get_id_list(alltests) + return (any(newid == x for x in idl)) + + +def generate_case_ids(alltests): + """ + If a test case has a blank ID field, generate a random hex ID for it + and then write the test cases back to disk. + """ + import random + for c in alltests: + if (c["id"] == ""): + while True: + newid = str('%04x' % random.randrange(16**4)) + if (does_id_exist(alltests, newid)): + continue + else: + c['id'] = newid + break + + ufilename = [] + for c in alltests: + if ('filename' in c): + ufilename.append(c['filename']) + ufilename = get_unique_item(ufilename) + for f in ufilename: + testlist = [] + for t in alltests: + if 'filename' in t: + if t['filename'] == f: + del t['filename'] + testlist.append(t) + outfile = open(f, "w") + json.dump(testlist, outfile, indent=4) + outfile.close() + + +def get_test_cases(args): + """ + If a test case file is specified, retrieve tests from that file. + Otherwise, glob for all json files in subdirectories and load from + each one. + """ + import fnmatch + if args.file != None: + if not os.path.isfile(args.file): + print("The specified test case file " + args.file + " does not exist.") + exit(1) + flist = [args.file] + else: + flist = [] + for root, dirnames, filenames in os.walk('tc-tests'): + for filename in fnmatch.filter(filenames, '*.json'): + flist.append(os.path.join(root, filename)) + alltests = list() + for casefile in flist: + alltests = alltests + (load_from_file(casefile)) + return alltests + + +def set_operation_mode(args): + """ + Load the test case data and process remaining arguments to determine + what the script should do for this run, and call the appropriate + function. + """ + alltests = get_test_cases(args) + + if args.gen_id: + idlist = get_id_list(alltests) + if (has_blank_ids(idlist)): + alltests = generate_case_ids(alltests) + else: + print("No empty ID fields found in test files.") + exit(0) + + duplicate_ids = check_case_id(alltests) + if (len(duplicate_ids) > 0): + print("The following test case IDs are not unique:") + print(str(set(duplicate_ids))) + print("Please correct them before continuing.") + exit(1) + + ucat = get_test_categories(alltests) + + if args.showID: + show_test_case_by_id(alltests, args.showID[0]) + exit(0) + + if args.execute: + target_id = args.execute[0] + else: + target_id = "" + + if args.category: + if (args.category == '+c'): + print("Available categories:") + print_sll(ucat) + exit(0) + else: + target_category = args.category + else: + target_category = "" + + + testcases = get_categorized_testlist(alltests, ucat) + + if args.list: + if (len(args.list) == 0): + list_test_cases(alltests) + exit(0) + elif(len(args.list > 0)): + if (args.list not in ucat): + print("Unknown category " + args.list) + print("Available categories:") + print_sll(ucat) + exit(1) + list_test_cases(testcases[args.list]) + exit(0) + + if (os.geteuid() != 0): + print("This script must be run with root privileges.\n") + exit(1) + + ns_create() + + if (len(target_category) == 0): + if (len(target_id) > 0): + alltests = list(filter(lambda x: target_id in x['id'], alltests)) + if (len(alltests) == 0): + print("Cannot find a test case with ID matching " + target_id) + exit(1) + catresults = test_runner(alltests) + print("All test results: " + "\n\n" + catresults) + elif (len(target_category) > 0): + if (target_category not in ucat): + print("Specified category is not present in this file.") + exit(1) + else: + catresults = test_runner(testcases[target_category]) + print("Category " + target_category + "\n\n" + catresults) + + ns_destroy() + + +def main(): + """ + Start of execution; set up argument parser and get the arguments, + and start operations. + """ + parser = args_parse() + parser = set_args(parser) + (args, remaining) = parser.parse_known_args() + check_default_settings(args) + + set_operation_mode(args) + + exit(0) + + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/tc-testing/tdc_config.py b/tools/testing/selftests/tc-testing/tdc_config.py new file mode 100644 index 000000000000..01087375a7c3 --- /dev/null +++ b/tools/testing/selftests/tc-testing/tdc_config.py @@ -0,0 +1,17 @@ +""" +tdc_config.py - tdc user-specified values + +Copyright (C) 2017 Lucas Bates <lucasb@mojatatu.com> +""" + +# Dictionary containing all values that can be substituted in executable +# commands. +NAMES = { + # Substitute your own tc path here + 'TC': '/sbin/tc', + # Name of veth devices to be created for the namespace + 'DEV0': 'v0p0', + 'DEV1': 'v0p1', + # Name of the namespace to use + 'NS': 'tcut' + } diff --git a/tools/testing/selftests/tc-testing/tdc_helper.py b/tools/testing/selftests/tc-testing/tdc_helper.py new file mode 100644 index 000000000000..c3254f861fb2 --- /dev/null +++ b/tools/testing/selftests/tc-testing/tdc_helper.py @@ -0,0 +1,75 @@ +""" +tdc_helper.py - tdc helper functions + +Copyright (C) 2017 Lucas Bates <lucasb@mojatatu.com> +""" + +def get_categorized_testlist(alltests, ucat): + """ Sort the master test list into categories. """ + testcases = dict() + + for category in ucat: + testcases[category] = list(filter(lambda x: category in x['category'], alltests)) + + return(testcases) + + +def get_unique_item(lst): + """ For a list, return a set of the unique items in the list. """ + return list(set(lst)) + + +def get_test_categories(alltests): + """ Discover all unique test categories present in the test case file. """ + ucat = [] + for t in alltests: + ucat.extend(get_unique_item(t['category'])) + ucat = get_unique_item(ucat) + return ucat + +def list_test_cases(testlist): + """ Print IDs and names of all test cases. """ + for curcase in testlist: + print(curcase['id'] + ': (' + ', '.join(curcase['category']) + ") " + curcase['name']) + + +def list_categories(testlist): + """ Show all categories that are present in a test case file. """ + categories = set(map(lambda x: x['category'], testlist)) + print("Available categories:") + print(", ".join(str(s) for s in categories)) + print("") + + +def print_list(cmdlist): + """ Print a list of strings prepended with a tab. """ + for l in cmdlist: + if (type(l) == list): + print("\t" + str(l[0])) + else: + print("\t" + str(l)) + + +def print_sll(items): + print("\n".join(str(s) for s in items)) + + +def print_test_case(tcase): + """ Pretty-printing of a given test case. """ + for k in tcase.keys(): + if (type(tcase[k]) == list): + print(k + ":") + print_list(tcase[k]) + else: + print(k + ": " + tcase[k]) + + +def show_test_case_by_id(testlist, caseID): + """ Find the specified test case to pretty-print. """ + if not any(d.get('id', None) == caseID for d in testlist): + print("That ID does not exist.") + exit(1) + else: + print_test_case(next((d for d in testlist if d['id'] == caseID))) + + diff --git a/tools/testing/selftests/timers/Makefile b/tools/testing/selftests/timers/Makefile index 5fa1d7e9a915..ae4593115408 100644 --- a/tools/testing/selftests/timers/Makefile +++ b/tools/testing/selftests/timers/Makefile @@ -1,16 +1,17 @@ -BUILD_FLAGS = -DKTEST -CFLAGS += -O3 -Wl,-no-as-needed -Wall $(BUILD_FLAGS) -LDFLAGS += -lrt -lpthread +CFLAGS += -O3 -Wl,-no-as-needed -Wall +LDFLAGS += -lrt -lpthread -lm # these are all "safe" tests that don't modify # system time or require escalated privileges TEST_GEN_PROGS = posix_timers nanosleep nsleep-lat set-timer-lat mqueue-lat \ inconsistency-check raw_skew threadtest rtctest -TEST_GEN_PROGS_EXTENDED = alarmtimer-suspend valid-adjtimex adjtick change_skew \ - skew_consistency clocksource-switch leap-a-day \ +DESTRUCTIVE_TESTS = alarmtimer-suspend valid-adjtimex adjtick change_skew \ + skew_consistency clocksource-switch freq-step leap-a-day \ leapcrash set-tai set-2038 set-tz +TEST_GEN_PROGS_EXTENDED = $(DESTRUCTIVE_TESTS) rtctest_setdate + include ../lib.mk @@ -18,15 +19,4 @@ include ../lib.mk # and may modify the system time or trigger # other behavior like suspend run_destructive_tests: run_tests - ./alarmtimer-suspend - ./valid-adjtimex - ./adjtick - ./change_skew - ./skew_consistency - ./clocksource-switch - ./leap-a-day -s -i 10 - ./leapcrash - ./set-tz - ./set-tai - ./set-2038 - + $(call RUN_TESTS, $(DESTRUCTIVE_TESTS)) diff --git a/tools/testing/selftests/timers/adjtick.c b/tools/testing/selftests/timers/adjtick.c index 9887fd538fec..0caca3a06bd2 100644 --- a/tools/testing/selftests/timers/adjtick.c +++ b/tools/testing/selftests/timers/adjtick.c @@ -23,18 +23,7 @@ #include <sys/timex.h> #include <time.h> -#ifdef KTEST #include "../kselftest.h" -#else -static inline int ksft_exit_pass(void) -{ - exit(0); -} -static inline int ksft_exit_fail(void) -{ - exit(1); -} -#endif #define CLOCK_MONOTONIC_RAW 4 diff --git a/tools/testing/selftests/timers/alarmtimer-suspend.c b/tools/testing/selftests/timers/alarmtimer-suspend.c index 2b361b830395..4da09dbf83ba 100644 --- a/tools/testing/selftests/timers/alarmtimer-suspend.c +++ b/tools/testing/selftests/timers/alarmtimer-suspend.c @@ -28,18 +28,7 @@ #include <signal.h> #include <stdlib.h> #include <pthread.h> -#ifdef KTEST #include "../kselftest.h" -#else -static inline int ksft_exit_pass(void) -{ - exit(0); -} -static inline int ksft_exit_fail(void) -{ - exit(1); -} -#endif #define CLOCK_REALTIME 0 #define CLOCK_MONOTONIC 1 diff --git a/tools/testing/selftests/timers/change_skew.c b/tools/testing/selftests/timers/change_skew.c index cb1968977c04..c4eab7124990 100644 --- a/tools/testing/selftests/timers/change_skew.c +++ b/tools/testing/selftests/timers/change_skew.c @@ -28,18 +28,7 @@ #include <sys/time.h> #include <sys/timex.h> #include <time.h> -#ifdef KTEST #include "../kselftest.h" -#else -static inline int ksft_exit_pass(void) -{ - exit(0); -} -static inline int ksft_exit_fail(void) -{ - exit(1); -} -#endif #define NSEC_PER_SEC 1000000000LL diff --git a/tools/testing/selftests/timers/clocksource-switch.c b/tools/testing/selftests/timers/clocksource-switch.c index 5ff165373f8b..bfc974b4572d 100644 --- a/tools/testing/selftests/timers/clocksource-switch.c +++ b/tools/testing/selftests/timers/clocksource-switch.c @@ -34,18 +34,7 @@ #include <fcntl.h> #include <string.h> #include <sys/wait.h> -#ifdef KTEST #include "../kselftest.h" -#else -static inline int ksft_exit_pass(void) -{ - exit(0); -} -static inline int ksft_exit_fail(void) -{ - exit(1); -} -#endif int get_clocksources(char list[][30]) @@ -61,7 +50,7 @@ int get_clocksources(char list[][30]) close(fd); - for (i = 0; i < 30; i++) + for (i = 0; i < 10; i++) list[i][0] = '\0'; head = buf; diff --git a/tools/testing/selftests/timers/freq-step.c b/tools/testing/selftests/timers/freq-step.c new file mode 100644 index 000000000000..14a2b77fd012 --- /dev/null +++ b/tools/testing/selftests/timers/freq-step.c @@ -0,0 +1,271 @@ +/* + * This test checks the response of the system clock to frequency + * steps made with adjtimex(). The frequency error and stability of + * the CLOCK_MONOTONIC clock relative to the CLOCK_MONOTONIC_RAW clock + * is measured in two intervals following the step. The test fails if + * values from the second interval exceed specified limits. + * + * Copyright (C) Miroslav Lichvar <mlichvar@redhat.com> 2017 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +#include <math.h> +#include <stdio.h> +#include <sys/timex.h> +#include <time.h> +#include <unistd.h> + +#include "../kselftest.h" + +#define SAMPLES 100 +#define SAMPLE_READINGS 10 +#define MEAN_SAMPLE_INTERVAL 0.1 +#define STEP_INTERVAL 1.0 +#define MAX_PRECISION 100e-9 +#define MAX_FREQ_ERROR 10e-6 +#define MAX_STDDEV 1000e-9 + +#ifndef ADJ_SETOFFSET + #define ADJ_SETOFFSET 0x0100 +#endif + +struct sample { + double offset; + double time; +}; + +static time_t mono_raw_base; +static time_t mono_base; +static long user_hz; +static double precision; +static double mono_freq_offset; + +static double diff_timespec(struct timespec *ts1, struct timespec *ts2) +{ + return ts1->tv_sec - ts2->tv_sec + (ts1->tv_nsec - ts2->tv_nsec) / 1e9; +} + +static double get_sample(struct sample *sample) +{ + double delay, mindelay = 0.0; + struct timespec ts1, ts2, ts3; + int i; + + for (i = 0; i < SAMPLE_READINGS; i++) { + clock_gettime(CLOCK_MONOTONIC_RAW, &ts1); + clock_gettime(CLOCK_MONOTONIC, &ts2); + clock_gettime(CLOCK_MONOTONIC_RAW, &ts3); + + ts1.tv_sec -= mono_raw_base; + ts2.tv_sec -= mono_base; + ts3.tv_sec -= mono_raw_base; + + delay = diff_timespec(&ts3, &ts1); + if (delay <= 1e-9) { + i--; + continue; + } + + if (!i || delay < mindelay) { + sample->offset = diff_timespec(&ts2, &ts1); + sample->offset -= delay / 2.0; + sample->time = ts1.tv_sec + ts1.tv_nsec / 1e9; + mindelay = delay; + } + } + + return mindelay; +} + +static void reset_ntp_error(void) +{ + struct timex txc; + + txc.modes = ADJ_SETOFFSET; + txc.time.tv_sec = 0; + txc.time.tv_usec = 0; + + if (adjtimex(&txc) < 0) { + perror("[FAIL] adjtimex"); + ksft_exit_fail(); + } +} + +static void set_frequency(double freq) +{ + struct timex txc; + int tick_offset; + + tick_offset = 1e6 * freq / user_hz; + + txc.modes = ADJ_TICK | ADJ_FREQUENCY; + txc.tick = 1000000 / user_hz + tick_offset; + txc.freq = (1e6 * freq - user_hz * tick_offset) * (1 << 16); + + if (adjtimex(&txc) < 0) { + perror("[FAIL] adjtimex"); + ksft_exit_fail(); + } +} + +static void regress(struct sample *samples, int n, double *intercept, + double *slope, double *r_stddev, double *r_max) +{ + double x, y, r, x_sum, y_sum, xy_sum, x2_sum, r2_sum; + int i; + + x_sum = 0.0, y_sum = 0.0, xy_sum = 0.0, x2_sum = 0.0; + + for (i = 0; i < n; i++) { + x = samples[i].time; + y = samples[i].offset; + + x_sum += x; + y_sum += y; + xy_sum += x * y; + x2_sum += x * x; + } + + *slope = (xy_sum - x_sum * y_sum / n) / (x2_sum - x_sum * x_sum / n); + *intercept = (y_sum - *slope * x_sum) / n; + + *r_max = 0.0, r2_sum = 0.0; + + for (i = 0; i < n; i++) { + x = samples[i].time; + y = samples[i].offset; + r = fabs(x * *slope + *intercept - y); + if (*r_max < r) + *r_max = r; + r2_sum += r * r; + } + + *r_stddev = sqrt(r2_sum / n); +} + +static int run_test(int calibration, double freq_base, double freq_step) +{ + struct sample samples[SAMPLES]; + double intercept, slope, stddev1, max1, stddev2, max2; + double freq_error1, freq_error2; + int i; + + set_frequency(freq_base); + + for (i = 0; i < 10; i++) + usleep(1e6 * MEAN_SAMPLE_INTERVAL / 10); + + reset_ntp_error(); + + set_frequency(freq_base + freq_step); + + for (i = 0; i < 10; i++) + usleep(rand() % 2000000 * STEP_INTERVAL / 10); + + set_frequency(freq_base); + + for (i = 0; i < SAMPLES; i++) { + usleep(rand() % 2000000 * MEAN_SAMPLE_INTERVAL); + get_sample(&samples[i]); + } + + if (calibration) { + regress(samples, SAMPLES, &intercept, &slope, &stddev1, &max1); + mono_freq_offset = slope; + printf("CLOCK_MONOTONIC_RAW frequency offset: %11.3f ppm\n", + 1e6 * mono_freq_offset); + return 0; + } + + regress(samples, SAMPLES / 2, &intercept, &slope, &stddev1, &max1); + freq_error1 = slope * (1.0 - mono_freq_offset) - mono_freq_offset - + freq_base; + + regress(samples + SAMPLES / 2, SAMPLES / 2, &intercept, &slope, + &stddev2, &max2); + freq_error2 = slope * (1.0 - mono_freq_offset) - mono_freq_offset - + freq_base; + + printf("%6.0f %+10.3f %6.0f %7.0f %+10.3f %6.0f %7.0f\t", + 1e6 * freq_step, + 1e6 * freq_error1, 1e9 * stddev1, 1e9 * max1, + 1e6 * freq_error2, 1e9 * stddev2, 1e9 * max2); + + if (fabs(freq_error2) > MAX_FREQ_ERROR || stddev2 > MAX_STDDEV) { + printf("[FAIL]\n"); + return 1; + } + + printf("[OK]\n"); + return 0; +} + +static void init_test(void) +{ + struct timespec ts; + struct sample sample; + + if (clock_gettime(CLOCK_MONOTONIC_RAW, &ts)) { + perror("[FAIL] clock_gettime(CLOCK_MONOTONIC_RAW)"); + ksft_exit_fail(); + } + + mono_raw_base = ts.tv_sec; + + if (clock_gettime(CLOCK_MONOTONIC, &ts)) { + perror("[FAIL] clock_gettime(CLOCK_MONOTONIC)"); + ksft_exit_fail(); + } + + mono_base = ts.tv_sec; + + user_hz = sysconf(_SC_CLK_TCK); + + precision = get_sample(&sample) / 2.0; + printf("CLOCK_MONOTONIC_RAW+CLOCK_MONOTONIC precision: %.0f ns\t\t", + 1e9 * precision); + + if (precision > MAX_PRECISION) + ksft_exit_skip("precision: %.0f ns > MAX_PRECISION: %.0f ns\n", + 1e9 * precision, 1e9 * MAX_PRECISION); + + printf("[OK]\n"); + srand(ts.tv_sec ^ ts.tv_nsec); + + run_test(1, 0.0, 0.0); +} + +int main(int argc, char **argv) +{ + double freq_base, freq_step; + int i, j, fails = 0; + + init_test(); + + printf("Checking response to frequency step:\n"); + printf(" Step 1st interval 2nd interval\n"); + printf(" Freq Dev Max Freq Dev Max\n"); + + for (i = 2; i >= 0; i--) { + for (j = 0; j < 5; j++) { + freq_base = (rand() % (1 << 24) - (1 << 23)) / 65536e6; + freq_step = 10e-6 * (1 << (6 * i)); + fails += run_test(0, freq_base, freq_step); + } + } + + set_frequency(0.0); + + if (fails) + return ksft_exit_fail(); + + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/timers/inconsistency-check.c b/tools/testing/selftests/timers/inconsistency-check.c index caf1bc9257c4..022d3ffe3fbf 100644 --- a/tools/testing/selftests/timers/inconsistency-check.c +++ b/tools/testing/selftests/timers/inconsistency-check.c @@ -28,18 +28,7 @@ #include <sys/timex.h> #include <string.h> #include <signal.h> -#ifdef KTEST #include "../kselftest.h" -#else -static inline int ksft_exit_pass(void) -{ - exit(0); -} -static inline int ksft_exit_fail(void) -{ - exit(1); -} -#endif #define CALLS_PER_LOOP 64 #define NSEC_PER_SEC 1000000000ULL @@ -118,7 +107,7 @@ int consistency_test(int clock_type, unsigned long seconds) start_str = ctime(&t); while (seconds == -1 || now - then < seconds) { - inconsistent = 0; + inconsistent = -1; /* Fill list */ for (i = 0; i < CALLS_PER_LOOP; i++) @@ -130,7 +119,7 @@ int consistency_test(int clock_type, unsigned long seconds) inconsistent = i; /* display inconsistency */ - if (inconsistent) { + if (inconsistent >= 0) { unsigned long long delta; printf("\%s\n", start_str); diff --git a/tools/testing/selftests/timers/leap-a-day.c b/tools/testing/selftests/timers/leap-a-day.c index fb46ad6ac92c..19e46ed5dfb5 100644 --- a/tools/testing/selftests/timers/leap-a-day.c +++ b/tools/testing/selftests/timers/leap-a-day.c @@ -48,18 +48,7 @@ #include <string.h> #include <signal.h> #include <unistd.h> -#ifdef KTEST #include "../kselftest.h" -#else -static inline int ksft_exit_pass(void) -{ - exit(0); -} -static inline int ksft_exit_fail(void) -{ - exit(1); -} -#endif #define NSEC_PER_SEC 1000000000ULL #define CLOCK_TAI 11 @@ -190,18 +179,18 @@ int main(int argc, char **argv) struct sigevent se; struct sigaction act; int signum = SIGRTMAX; - int settime = 0; + int settime = 1; int tai_time = 0; int insert = 1; - int iterations = -1; + int iterations = 10; int opt; /* Process arguments */ while ((opt = getopt(argc, argv, "sti:")) != -1) { switch (opt) { - case 's': - printf("Setting time to speed up testing\n"); - settime = 1; + case 'w': + printf("Only setting leap-flag, not changing time. It could take up to a day for leap to trigger.\n"); + settime = 0; break; case 'i': iterations = atoi(optarg); @@ -210,9 +199,10 @@ int main(int argc, char **argv) tai_time = 1; break; default: - printf("Usage: %s [-s] [-i <iterations>]\n", argv[0]); - printf(" -s: Set time to right before leap second each iteration\n"); - printf(" -i: Number of iterations\n"); + printf("Usage: %s [-w] [-i <iterations>]\n", argv[0]); + printf(" -w: Set flag and wait for leap second each iteration"); + printf(" (default sets time to right before leapsecond)\n"); + printf(" -i: Number of iterations (-1 = infinite, default is 10)\n"); printf(" -t: Print TAI time\n"); exit(-1); } diff --git a/tools/testing/selftests/timers/leapcrash.c b/tools/testing/selftests/timers/leapcrash.c index a1071bdbdeb7..830c462f605d 100644 --- a/tools/testing/selftests/timers/leapcrash.c +++ b/tools/testing/selftests/timers/leapcrash.c @@ -22,20 +22,7 @@ #include <sys/timex.h> #include <string.h> #include <signal.h> -#ifdef KTEST #include "../kselftest.h" -#else -static inline int ksft_exit_pass(void) -{ - exit(0); -} -static inline int ksft_exit_fail(void) -{ - exit(1); -} -#endif - - /* clear NTP time_status & time_state */ int clear_time_state(void) diff --git a/tools/testing/selftests/timers/mqueue-lat.c b/tools/testing/selftests/timers/mqueue-lat.c index a2a3924d0b41..1867db5d6f5e 100644 --- a/tools/testing/selftests/timers/mqueue-lat.c +++ b/tools/testing/selftests/timers/mqueue-lat.c @@ -29,18 +29,7 @@ #include <signal.h> #include <errno.h> #include <mqueue.h> -#ifdef KTEST #include "../kselftest.h" -#else -static inline int ksft_exit_pass(void) -{ - exit(0); -} -static inline int ksft_exit_fail(void) -{ - exit(1); -} -#endif #define NSEC_PER_SEC 1000000000ULL diff --git a/tools/testing/selftests/timers/nanosleep.c b/tools/testing/selftests/timers/nanosleep.c index ff942ff7c9b3..8adb0bb51d4d 100644 --- a/tools/testing/selftests/timers/nanosleep.c +++ b/tools/testing/selftests/timers/nanosleep.c @@ -27,18 +27,7 @@ #include <sys/timex.h> #include <string.h> #include <signal.h> -#ifdef KTEST #include "../kselftest.h" -#else -static inline int ksft_exit_pass(void) -{ - exit(0); -} -static inline int ksft_exit_fail(void) -{ - exit(1); -} -#endif #define NSEC_PER_SEC 1000000000ULL diff --git a/tools/testing/selftests/timers/nsleep-lat.c b/tools/testing/selftests/timers/nsleep-lat.c index 2d7898fda0f1..c3c3dc10db17 100644 --- a/tools/testing/selftests/timers/nsleep-lat.c +++ b/tools/testing/selftests/timers/nsleep-lat.c @@ -24,18 +24,7 @@ #include <sys/timex.h> #include <string.h> #include <signal.h> -#ifdef KTEST #include "../kselftest.h" -#else -static inline int ksft_exit_pass(void) -{ - exit(0); -} -static inline int ksft_exit_fail(void) -{ - exit(1); -} -#endif #define NSEC_PER_SEC 1000000000ULL diff --git a/tools/testing/selftests/timers/raw_skew.c b/tools/testing/selftests/timers/raw_skew.c index 30906bfd9c1b..ca6cd146aafe 100644 --- a/tools/testing/selftests/timers/raw_skew.c +++ b/tools/testing/selftests/timers/raw_skew.c @@ -25,19 +25,7 @@ #include <sys/time.h> #include <sys/timex.h> #include <time.h> -#ifdef KTEST #include "../kselftest.h" -#else -static inline int ksft_exit_pass(void) -{ - exit(0); -} -static inline int ksft_exit_fail(void) -{ - exit(1); -} -#endif - #define CLOCK_MONOTONIC_RAW 4 #define NSEC_PER_SEC 1000000000LL diff --git a/tools/testing/selftests/timers/rtctest.c b/tools/testing/selftests/timers/rtctest.c index 4230d3052e5d..411eff625e66 100644 --- a/tools/testing/selftests/timers/rtctest.c +++ b/tools/testing/selftests/timers/rtctest.c @@ -21,6 +21,9 @@ #include <stdlib.h> #include <errno.h> +#ifndef ARRAY_SIZE +# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#endif /* * This expects the new RTC class driver framework, working with @@ -29,23 +32,84 @@ */ static const char default_rtc[] = "/dev/rtc0"; +static struct rtc_time cutoff_dates[] = { + { + .tm_year = 70, /* 1970 -1900 */ + .tm_mday = 1, + }, + /* signed time_t 19/01/2038 3:14:08 */ + { + .tm_year = 138, + .tm_mday = 19, + }, + { + .tm_year = 138, + .tm_mday = 20, + }, + { + .tm_year = 199, /* 2099 -1900 */ + .tm_mday = 1, + }, + { + .tm_year = 200, /* 2100 -1900 */ + .tm_mday = 1, + }, + /* unsigned time_t 07/02/2106 7:28:15*/ + { + .tm_year = 205, + .tm_mon = 1, + .tm_mday = 7, + }, + { + .tm_year = 206, + .tm_mon = 1, + .tm_mday = 8, + }, + /* signed time on 64bit in nanoseconds 12/04/2262 01:47:16*/ + { + .tm_year = 362, + .tm_mon = 3, + .tm_mday = 12, + }, + { + .tm_year = 362, /* 2262 -1900 */ + .tm_mon = 3, + .tm_mday = 13, + }, +}; + +static int compare_dates(struct rtc_time *a, struct rtc_time *b) +{ + if (a->tm_year != b->tm_year || + a->tm_mon != b->tm_mon || + a->tm_mday != b->tm_mday || + a->tm_hour != b->tm_hour || + a->tm_min != b->tm_min || + ((b->tm_sec - a->tm_sec) > 1)) + return 1; + + return 0; +} int main(int argc, char **argv) { - int i, fd, retval, irqcount = 0; + int i, fd, retval, irqcount = 0, dangerous = 0; unsigned long tmp, data; struct rtc_time rtc_tm; const char *rtc = default_rtc; struct timeval start, end, diff; switch (argc) { + case 3: + if (*argv[2] == 'd') + dangerous = 1; case 2: rtc = argv[1]; /* FALLTHROUGH */ case 1: break; default: - fprintf(stderr, "usage: rtctest [rtcdev]\n"); + fprintf(stderr, "usage: rtctest [rtcdev] [d]\n"); return 1; } @@ -157,6 +221,11 @@ test_READ: /* Read the current alarm settings */ retval = ioctl(fd, RTC_ALM_READ, &rtc_tm); if (retval == -1) { + if (errno == EINVAL) { + fprintf(stderr, + "\n...EINVAL reading current alarm setting.\n"); + goto test_PIE; + } perror("RTC_ALM_READ ioctl"); exit(errno); } @@ -167,7 +236,7 @@ test_READ: /* Enable alarm interrupts */ retval = ioctl(fd, RTC_AIE_ON, 0); if (retval == -1) { - if (errno == EINVAL) { + if (errno == EINVAL || errno == EIO) { fprintf(stderr, "\n...Alarm IRQs not supported.\n"); goto test_PIE; @@ -202,7 +271,7 @@ test_PIE: /* not all RTCs support periodic IRQs */ if (errno == EINVAL) { fprintf(stderr, "\nNo periodic IRQ support\n"); - goto done; + goto test_DATE; } perror("RTC_IRQP_READ ioctl"); exit(errno); @@ -221,7 +290,7 @@ test_PIE: if (errno == EINVAL) { fprintf(stderr, "\n...Periodic IRQ rate is fixed\n"); - goto done; + goto test_DATE; } perror("RTC_IRQP_SET ioctl"); exit(errno); @@ -269,6 +338,62 @@ test_PIE: } } +test_DATE: + if (!dangerous) + goto done; + + fprintf(stderr, "\nTesting problematic dates\n"); + + for (i = 0; i < ARRAY_SIZE(cutoff_dates); i++) { + struct rtc_time current; + + /* Write the new date in RTC */ + retval = ioctl(fd, RTC_SET_TIME, &cutoff_dates[i]); + if (retval == -1) { + perror("RTC_SET_TIME ioctl"); + close(fd); + exit(errno); + } + + /* Read back */ + retval = ioctl(fd, RTC_RD_TIME, ¤t); + if (retval == -1) { + perror("RTC_RD_TIME ioctl"); + exit(errno); + } + + if(compare_dates(&cutoff_dates[i], ¤t)) { + fprintf(stderr,"Setting date %d failed\n", + cutoff_dates[i].tm_year + 1900); + goto done; + } + + cutoff_dates[i].tm_sec += 5; + + /* Write the new alarm in RTC */ + retval = ioctl(fd, RTC_ALM_SET, &cutoff_dates[i]); + if (retval == -1) { + perror("RTC_ALM_SET ioctl"); + close(fd); + exit(errno); + } + + /* Read back */ + retval = ioctl(fd, RTC_ALM_READ, ¤t); + if (retval == -1) { + perror("RTC_ALM_READ ioctl"); + exit(errno); + } + + if(compare_dates(&cutoff_dates[i], ¤t)) { + fprintf(stderr,"Setting alarm %d failed\n", + cutoff_dates[i].tm_year + 1900); + goto done; + } + + fprintf(stderr, "Setting year %d is OK \n", + cutoff_dates[i].tm_year + 1900); + } done: fprintf(stderr, "\n\n\t\t\t *** Test complete ***\n"); diff --git a/tools/testing/selftests/timers/rtctest_setdate.c b/tools/testing/selftests/timers/rtctest_setdate.c new file mode 100644 index 000000000000..2cb78489eca4 --- /dev/null +++ b/tools/testing/selftests/timers/rtctest_setdate.c @@ -0,0 +1,86 @@ +/* Real Time Clock Driver Test + * by: Benjamin Gaignard (benjamin.gaignard@linaro.org) + * + * To build + * gcc rtctest_setdate.c -o rtctest_setdate + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <stdio.h> +#include <linux/rtc.h> +#include <sys/ioctl.h> +#include <sys/time.h> +#include <sys/types.h> +#include <fcntl.h> +#include <unistd.h> +#include <stdlib.h> +#include <errno.h> + +static const char default_time[] = "00:00:00"; + +int main(int argc, char **argv) +{ + int fd, retval; + struct rtc_time new, current; + const char *rtc, *date; + const char *time = default_time; + + switch (argc) { + case 4: + time = argv[3]; + /* FALLTHROUGH */ + case 3: + date = argv[2]; + rtc = argv[1]; + break; + default: + fprintf(stderr, "usage: rtctest_setdate <rtcdev> <DD-MM-YYYY> [HH:MM:SS]\n"); + return 1; + } + + fd = open(rtc, O_RDONLY); + if (fd == -1) { + perror(rtc); + exit(errno); + } + + sscanf(date, "%d-%d-%d", &new.tm_mday, &new.tm_mon, &new.tm_year); + new.tm_mon -= 1; + new.tm_year -= 1900; + sscanf(time, "%d:%d:%d", &new.tm_hour, &new.tm_min, &new.tm_sec); + + fprintf(stderr, "Test will set RTC date/time to %d-%d-%d, %02d:%02d:%02d.\n", + new.tm_mday, new.tm_mon + 1, new.tm_year + 1900, + new.tm_hour, new.tm_min, new.tm_sec); + + /* Write the new date in RTC */ + retval = ioctl(fd, RTC_SET_TIME, &new); + if (retval == -1) { + perror("RTC_SET_TIME ioctl"); + close(fd); + exit(errno); + } + + /* Read back */ + retval = ioctl(fd, RTC_RD_TIME, ¤t); + if (retval == -1) { + perror("RTC_RD_TIME ioctl"); + exit(errno); + } + + fprintf(stderr, "\n\nCurrent RTC date/time is %d-%d-%d, %02d:%02d:%02d.\n", + current.tm_mday, current.tm_mon + 1, current.tm_year + 1900, + current.tm_hour, current.tm_min, current.tm_sec); + + close(fd); + return 0; +} diff --git a/tools/testing/selftests/timers/set-2038.c b/tools/testing/selftests/timers/set-2038.c index c8a7e14446b1..688cfd81b531 100644 --- a/tools/testing/selftests/timers/set-2038.c +++ b/tools/testing/selftests/timers/set-2038.c @@ -27,18 +27,7 @@ #include <unistd.h> #include <time.h> #include <sys/time.h> -#ifdef KTEST #include "../kselftest.h" -#else -static inline int ksft_exit_pass(void) -{ - exit(0); -} -static inline int ksft_exit_fail(void) -{ - exit(1); -} -#endif #define NSEC_PER_SEC 1000000000LL diff --git a/tools/testing/selftests/timers/set-tai.c b/tools/testing/selftests/timers/set-tai.c index dc88dbc8831f..70fed27d8fd3 100644 --- a/tools/testing/selftests/timers/set-tai.c +++ b/tools/testing/selftests/timers/set-tai.c @@ -23,18 +23,7 @@ #include <string.h> #include <signal.h> #include <unistd.h> -#ifdef KTEST #include "../kselftest.h" -#else -static inline int ksft_exit_pass(void) -{ - exit(0); -} -static inline int ksft_exit_fail(void) -{ - exit(1); -} -#endif int set_tai(int offset) { diff --git a/tools/testing/selftests/timers/set-timer-lat.c b/tools/testing/selftests/timers/set-timer-lat.c index 4fc98c5b0899..9c92b7bd5641 100644 --- a/tools/testing/selftests/timers/set-timer-lat.c +++ b/tools/testing/selftests/timers/set-timer-lat.c @@ -20,6 +20,7 @@ */ +#include <errno.h> #include <stdio.h> #include <unistd.h> #include <time.h> @@ -27,18 +28,7 @@ #include <signal.h> #include <stdlib.h> #include <pthread.h> -#ifdef KTEST #include "../kselftest.h" -#else -static inline int ksft_exit_pass(void) -{ - exit(0); -} -static inline int ksft_exit_fail(void) -{ - exit(1); -} -#endif #define CLOCK_REALTIME 0 #define CLOCK_MONOTONIC 1 @@ -63,6 +53,7 @@ int alarmcount; int clock_id; struct timespec start_time; long long max_latency_ns; +int timer_fired_early; char *clockstring(int clockid) { @@ -115,16 +106,23 @@ void sigalarm(int signo) delta_ns -= NSEC_PER_SEC * TIMER_SECS * alarmcount; if (delta_ns < 0) - printf("%s timer fired early: FAIL\n", clockstring(clock_id)); + timer_fired_early = 1; if (delta_ns > max_latency_ns) max_latency_ns = delta_ns; } -int do_timer(int clock_id, int flags) +void describe_timer(int flags, int interval) +{ + printf("%-22s %s %s ", + clockstring(clock_id), + flags ? "ABSTIME":"RELTIME", + interval ? "PERIODIC":"ONE-SHOT"); +} + +int setup_timer(int clock_id, int flags, int interval, timer_t *tm1) { struct sigevent se; - timer_t tm1; struct itimerspec its1, its2; int err; @@ -136,8 +134,9 @@ int do_timer(int clock_id, int flags) max_latency_ns = 0; alarmcount = 0; + timer_fired_early = 0; - err = timer_create(clock_id, &se, &tm1); + err = timer_create(clock_id, &se, tm1); if (err) { if ((clock_id == CLOCK_REALTIME_ALARM) || (clock_id == CLOCK_BOOTTIME_ALARM)) { @@ -158,32 +157,97 @@ int do_timer(int clock_id, int flags) its1.it_value.tv_sec = TIMER_SECS; its1.it_value.tv_nsec = 0; } - its1.it_interval.tv_sec = TIMER_SECS; + its1.it_interval.tv_sec = interval; its1.it_interval.tv_nsec = 0; - err = timer_settime(tm1, flags, &its1, &its2); + err = timer_settime(*tm1, flags, &its1, &its2); if (err) { printf("%s - timer_settime() failed\n", clockstring(clock_id)); return -1; } - while (alarmcount < 5) - sleep(1); + return 0; +} - printf("%-22s %s max latency: %10lld ns : ", - clockstring(clock_id), - flags ? "ABSTIME":"RELTIME", - max_latency_ns); +int check_timer_latency(int flags, int interval) +{ + int err = 0; + + describe_timer(flags, interval); + printf("timer fired early: %7d : ", timer_fired_early); + if (!timer_fired_early) { + printf("[OK]\n"); + } else { + printf("[FAILED]\n"); + err = -1; + } + + describe_timer(flags, interval); + printf("max latency: %10lld ns : ", max_latency_ns); - timer_delete(tm1); if (max_latency_ns < UNRESONABLE_LATENCY) { printf("[OK]\n"); + } else { + printf("[FAILED]\n"); + err = -1; + } + return err; +} + +int check_alarmcount(int flags, int interval) +{ + describe_timer(flags, interval); + printf("count: %19d : ", alarmcount); + if (alarmcount == 1) { + printf("[OK]\n"); return 0; } printf("[FAILED]\n"); return -1; } +int do_timer(int clock_id, int flags) +{ + timer_t tm1; + const int interval = TIMER_SECS; + int err; + + err = setup_timer(clock_id, flags, interval, &tm1); + if (err) + return err; + + while (alarmcount < 5) + sleep(1); + + timer_delete(tm1); + return check_timer_latency(flags, interval); +} + +int do_timer_oneshot(int clock_id, int flags) +{ + timer_t tm1; + const int interval = 0; + struct timeval timeout; + fd_set fds; + int err; + + err = setup_timer(clock_id, flags, interval, &tm1); + if (err) + return err; + + memset(&timeout, 0, sizeof(timeout)); + timeout.tv_sec = 5; + FD_ZERO(&fds); + do { + err = select(FD_SETSIZE, &fds, NULL, NULL, &timeout); + } while (err == -1 && errno == EINTR); + + timer_delete(tm1); + err = check_timer_latency(flags, interval); + err |= check_alarmcount(flags, interval); + return err; +} + int main(void) { struct sigaction act; @@ -209,6 +273,8 @@ int main(void) ret |= do_timer(clock_id, TIMER_ABSTIME); ret |= do_timer(clock_id, 0); + ret |= do_timer_oneshot(clock_id, TIMER_ABSTIME); + ret |= do_timer_oneshot(clock_id, 0); } if (ret) return ksft_exit_fail(); diff --git a/tools/testing/selftests/timers/set-tz.c b/tools/testing/selftests/timers/set-tz.c index f4184928b16b..877fd5532fee 100644 --- a/tools/testing/selftests/timers/set-tz.c +++ b/tools/testing/selftests/timers/set-tz.c @@ -23,18 +23,7 @@ #include <string.h> #include <signal.h> #include <unistd.h> -#ifdef KTEST #include "../kselftest.h" -#else -static inline int ksft_exit_pass(void) -{ - exit(0); -} -static inline int ksft_exit_fail(void) -{ - exit(1); -} -#endif int set_tz(int min, int dst) { diff --git a/tools/testing/selftests/timers/skew_consistency.c b/tools/testing/selftests/timers/skew_consistency.c index 2a996e072259..022b711c78ee 100644 --- a/tools/testing/selftests/timers/skew_consistency.c +++ b/tools/testing/selftests/timers/skew_consistency.c @@ -35,18 +35,7 @@ #include <stdlib.h> #include <string.h> #include <sys/wait.h> -#ifdef KTEST #include "../kselftest.h" -#else -static inline int ksft_exit_pass(void) -{ - exit(0); -} -static inline int ksft_exit_fail(void) -{ - exit(1); -} -#endif #define NSEC_PER_SEC 1000000000LL diff --git a/tools/testing/selftests/timers/threadtest.c b/tools/testing/selftests/timers/threadtest.c index e632e116f05e..759c9c06f1a0 100644 --- a/tools/testing/selftests/timers/threadtest.c +++ b/tools/testing/selftests/timers/threadtest.c @@ -21,19 +21,7 @@ #include <stdlib.h> #include <sys/time.h> #include <pthread.h> -#ifdef KTEST #include "../kselftest.h" -#else -static inline int ksft_exit_pass(void) -{ - exit(0); -} -static inline int ksft_exit_fail(void) -{ - exit(1); -} -#endif - /* serializes shared list access */ pthread_mutex_t list_lock = PTHREAD_MUTEX_INITIALIZER; diff --git a/tools/testing/selftests/timers/valid-adjtimex.c b/tools/testing/selftests/timers/valid-adjtimex.c index 60fe3c569bd9..d9d3ab93b31a 100644 --- a/tools/testing/selftests/timers/valid-adjtimex.c +++ b/tools/testing/selftests/timers/valid-adjtimex.c @@ -32,18 +32,7 @@ #include <string.h> #include <signal.h> #include <unistd.h> -#ifdef KTEST #include "../kselftest.h" -#else -static inline int ksft_exit_pass(void) -{ - exit(0); -} -static inline int ksft_exit_fail(void) -{ - exit(1); -} -#endif #define NSEC_PER_SEC 1000000000LL #define USEC_PER_SEC 1000000LL diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c index 1eae79ae5b4e..a2c53a3d223d 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -66,6 +66,8 @@ #include <sys/wait.h> #include <pthread.h> #include <linux/userfaultfd.h> +#include <setjmp.h> +#include <stdbool.h> #ifdef __NR_userfaultfd @@ -82,11 +84,17 @@ static int bounces; #define TEST_SHMEM 3 static int test_type; +/* exercise the test_uffdio_*_eexist every ALARM_INTERVAL_SECS */ +#define ALARM_INTERVAL_SECS 10 +static volatile bool test_uffdio_copy_eexist = true; +static volatile bool test_uffdio_zeropage_eexist = true; + +static bool map_shared; static int huge_fd; static char *huge_fd_off0; static unsigned long long *count_verify; static int uffd, uffd_flags, finished, *pipefd; -static char *area_src, *area_dst; +static char *area_src, *area_src_alias, *area_dst, *area_dst_alias; static char *zeropage; pthread_attr_t attr; @@ -125,6 +133,9 @@ static void anon_allocate_area(void **alloc_area) } } +static void noop_alias_mapping(__u64 *start, size_t len, unsigned long offset) +{ +} /* HugeTLB memory */ static int hugetlb_release_pages(char *rel_area) @@ -145,17 +156,51 @@ static int hugetlb_release_pages(char *rel_area) static void hugetlb_allocate_area(void **alloc_area) { + void *area_alias = NULL; + char **alloc_area_alias; *alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE, - MAP_PRIVATE | MAP_HUGETLB, huge_fd, - *alloc_area == area_src ? 0 : - nr_pages * page_size); + (map_shared ? MAP_SHARED : MAP_PRIVATE) | + MAP_HUGETLB, + huge_fd, *alloc_area == area_src ? 0 : + nr_pages * page_size); if (*alloc_area == MAP_FAILED) { fprintf(stderr, "mmap of hugetlbfs file failed\n"); *alloc_area = NULL; } - if (*alloc_area == area_src) + if (map_shared) { + area_alias = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_HUGETLB, + huge_fd, *alloc_area == area_src ? 0 : + nr_pages * page_size); + if (area_alias == MAP_FAILED) { + if (munmap(*alloc_area, nr_pages * page_size) < 0) + perror("hugetlb munmap"), exit(1); + *alloc_area = NULL; + return; + } + } + if (*alloc_area == area_src) { huge_fd_off0 = *alloc_area; + alloc_area_alias = &area_src_alias; + } else { + alloc_area_alias = &area_dst_alias; + } + if (area_alias) + *alloc_area_alias = area_alias; +} + +static void hugetlb_alias_mapping(__u64 *start, size_t len, unsigned long offset) +{ + if (!map_shared) + return; + /* + * We can't zap just the pagetable with hugetlbfs because + * MADV_DONTEED won't work. So exercise -EEXIST on a alias + * mapping where the pagetables are not established initially, + * this way we'll exercise the -EEXEC at the fs level. + */ + *start = (unsigned long) area_dst_alias + offset; } /* Shared memory */ @@ -185,6 +230,7 @@ struct uffd_test_ops { unsigned long expected_ioctls; void (*allocate_area)(void **alloc_area); int (*release_pages)(char *rel_area); + void (*alias_mapping)(__u64 *start, size_t len, unsigned long offset); }; #define ANON_EXPECTED_IOCTLS ((1 << _UFFDIO_WAKE) | \ @@ -195,18 +241,21 @@ static struct uffd_test_ops anon_uffd_test_ops = { .expected_ioctls = ANON_EXPECTED_IOCTLS, .allocate_area = anon_allocate_area, .release_pages = anon_release_pages, + .alias_mapping = noop_alias_mapping, }; static struct uffd_test_ops shmem_uffd_test_ops = { - .expected_ioctls = UFFD_API_RANGE_IOCTLS_BASIC, + .expected_ioctls = ANON_EXPECTED_IOCTLS, .allocate_area = shmem_allocate_area, .release_pages = shmem_release_pages, + .alias_mapping = noop_alias_mapping, }; static struct uffd_test_ops hugetlb_uffd_test_ops = { .expected_ioctls = UFFD_API_RANGE_IOCTLS_BASIC, .allocate_area = hugetlb_allocate_area, .release_pages = hugetlb_release_pages, + .alias_mapping = hugetlb_alias_mapping, }; static struct uffd_test_ops *uffd_test_ops; @@ -331,6 +380,23 @@ static void *locking_thread(void *arg) return NULL; } +static void retry_copy_page(int ufd, struct uffdio_copy *uffdio_copy, + unsigned long offset) +{ + uffd_test_ops->alias_mapping(&uffdio_copy->dst, + uffdio_copy->len, + offset); + if (ioctl(ufd, UFFDIO_COPY, uffdio_copy)) { + /* real retval in ufdio_copy.copy */ + if (uffdio_copy->copy != -EEXIST) + fprintf(stderr, "UFFDIO_COPY retry error %Ld\n", + uffdio_copy->copy), exit(1); + } else { + fprintf(stderr, "UFFDIO_COPY retry unexpected %Ld\n", + uffdio_copy->copy), exit(1); + } +} + static int copy_page(int ufd, unsigned long offset) { struct uffdio_copy uffdio_copy; @@ -351,8 +417,13 @@ static int copy_page(int ufd, unsigned long offset) } else if (uffdio_copy.copy != page_size) { fprintf(stderr, "UFFDIO_COPY unexpected copy %Ld\n", uffdio_copy.copy), exit(1); - } else + } else { + if (test_uffdio_copy_eexist) { + test_uffdio_copy_eexist = false; + retry_copy_page(ufd, &uffdio_copy, offset); + } return 1; + } return 0; } @@ -408,6 +479,7 @@ static void *uffd_poll_thread(void *arg) userfaults++; break; case UFFD_EVENT_FORK: + close(uffd); uffd = msg.arg.fork.ufd; pollfd[0].fd = uffd; break; @@ -572,6 +644,17 @@ static int userfaultfd_open(int features) return 0; } +sigjmp_buf jbuf, *sigbuf; + +static void sighndl(int sig, siginfo_t *siginfo, void *ptr) +{ + if (sig == SIGBUS) { + if (sigbuf) + siglongjmp(*sigbuf, 1); + abort(); + } +} + /* * For non-cooperative userfaultfd test we fork() a process that will * generate pagefaults, will mremap the area monitored by the @@ -585,19 +668,59 @@ static int userfaultfd_open(int features) * The release of the pages currently generates event for shmem and * anonymous memory (UFFD_EVENT_REMOVE), hence it is not checked * for hugetlb. + * For signal test(UFFD_FEATURE_SIGBUS), signal_test = 1, we register + * monitored area, generate pagefaults and test that signal is delivered. + * Use UFFDIO_COPY to allocate missing page and retry. For signal_test = 2 + * test robustness use case - we release monitored area, fork a process + * that will generate pagefaults and verify signal is generated. + * This also tests UFFD_FEATURE_EVENT_FORK event along with the signal + * feature. Using monitor thread, verify no userfault events are generated. */ -static int faulting_process(void) +static int faulting_process(int signal_test) { unsigned long nr; unsigned long long count; unsigned long split_nr_pages; + unsigned long lastnr; + struct sigaction act; + unsigned long signalled = 0; if (test_type != TEST_HUGETLB) split_nr_pages = (nr_pages + 1) / 2; else split_nr_pages = nr_pages; + if (signal_test) { + sigbuf = &jbuf; + memset(&act, 0, sizeof(act)); + act.sa_sigaction = sighndl; + act.sa_flags = SA_SIGINFO; + if (sigaction(SIGBUS, &act, 0)) { + perror("sigaction"); + return 1; + } + lastnr = (unsigned long)-1; + } + for (nr = 0; nr < split_nr_pages; nr++) { + if (signal_test) { + if (sigsetjmp(*sigbuf, 1) != 0) { + if (nr == lastnr) { + fprintf(stderr, "Signal repeated\n"); + return 1; + } + + lastnr = nr; + if (signal_test == 1) { + if (copy_page(uffd, nr * page_size)) + signalled++; + } else { + signalled++; + continue; + } + } + } + count = *area_count(area_dst, nr); if (count != count_verify[nr]) { fprintf(stderr, @@ -607,6 +730,9 @@ static int faulting_process(void) } } + if (signal_test) + return signalled != split_nr_pages; + if (test_type == TEST_HUGETLB) return 0; @@ -636,6 +762,23 @@ static int faulting_process(void) return 0; } +static void retry_uffdio_zeropage(int ufd, + struct uffdio_zeropage *uffdio_zeropage, + unsigned long offset) +{ + uffd_test_ops->alias_mapping(&uffdio_zeropage->range.start, + uffdio_zeropage->range.len, + offset); + if (ioctl(ufd, UFFDIO_ZEROPAGE, uffdio_zeropage)) { + if (uffdio_zeropage->zeropage != -EEXIST) + fprintf(stderr, "UFFDIO_ZEROPAGE retry error %Ld\n", + uffdio_zeropage->zeropage), exit(1); + } else { + fprintf(stderr, "UFFDIO_ZEROPAGE retry unexpected %Ld\n", + uffdio_zeropage->zeropage), exit(1); + } +} + static int uffdio_zeropage(int ufd, unsigned long offset) { struct uffdio_zeropage uffdio_zeropage; @@ -670,8 +813,14 @@ static int uffdio_zeropage(int ufd, unsigned long offset) if (uffdio_zeropage.zeropage != page_size) { fprintf(stderr, "UFFDIO_ZEROPAGE unexpected %Ld\n", uffdio_zeropage.zeropage), exit(1); - } else + } else { + if (test_uffdio_zeropage_eexist) { + test_uffdio_zeropage_eexist = false; + retry_uffdio_zeropage(ufd, &uffdio_zeropage, + offset); + } return 1; + } } else { fprintf(stderr, "UFFDIO_ZEROPAGE succeeded %Ld\n", @@ -761,7 +910,7 @@ static int userfaultfd_events_test(void) perror("fork"), exit(1); if (!pid) - return faulting_process(); + return faulting_process(0); waitpid(pid, &err, 0); if (err) @@ -778,6 +927,72 @@ static int userfaultfd_events_test(void) return userfaults != nr_pages; } +static int userfaultfd_sig_test(void) +{ + struct uffdio_register uffdio_register; + unsigned long expected_ioctls; + unsigned long userfaults; + pthread_t uffd_mon; + int err, features; + pid_t pid; + char c; + + printf("testing signal delivery: "); + fflush(stdout); + + if (uffd_test_ops->release_pages(area_dst)) + return 1; + + features = UFFD_FEATURE_EVENT_FORK|UFFD_FEATURE_SIGBUS; + if (userfaultfd_open(features) < 0) + return 1; + fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK); + + uffdio_register.range.start = (unsigned long) area_dst; + uffdio_register.range.len = nr_pages * page_size; + uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING; + if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) + fprintf(stderr, "register failure\n"), exit(1); + + expected_ioctls = uffd_test_ops->expected_ioctls; + if ((uffdio_register.ioctls & expected_ioctls) != + expected_ioctls) + fprintf(stderr, + "unexpected missing ioctl for anon memory\n"), + exit(1); + + if (faulting_process(1)) + fprintf(stderr, "faulting process failed\n"), exit(1); + + if (uffd_test_ops->release_pages(area_dst)) + return 1; + + if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, NULL)) + perror("uffd_poll_thread create"), exit(1); + + pid = fork(); + if (pid < 0) + perror("fork"), exit(1); + + if (!pid) + exit(faulting_process(2)); + + waitpid(pid, &err, 0); + if (err) + fprintf(stderr, "faulting process failed\n"), exit(1); + + if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) + perror("pipe write"), exit(1); + if (pthread_join(uffd_mon, (void **)&userfaults)) + return 1; + + printf("done.\n"); + if (userfaults) + fprintf(stderr, "Signal test failed, userfaults: %ld\n", + userfaults); + close(uffd); + return userfaults != 0; +} static int userfaultfd_stress(void) { void *area; @@ -879,6 +1094,15 @@ static int userfaultfd_stress(void) return 1; } + if (area_dst_alias) { + uffdio_register.range.start = (unsigned long) + area_dst_alias; + if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) { + fprintf(stderr, "register failure alias\n"); + return 1; + } + } + /* * The madvise done previously isn't enough: some * uffd_thread could have read userfaults (one of @@ -912,9 +1136,17 @@ static int userfaultfd_stress(void) /* unregister */ if (ioctl(uffd, UFFDIO_UNREGISTER, &uffdio_register.range)) { - fprintf(stderr, "register failure\n"); + fprintf(stderr, "unregister failure\n"); return 1; } + if (area_dst_alias) { + uffdio_register.range.start = (unsigned long) area_dst; + if (ioctl(uffd, UFFDIO_UNREGISTER, + &uffdio_register.range)) { + fprintf(stderr, "unregister failure alias\n"); + return 1; + } + } /* verification */ if (bounces & BOUNCE_VERIFY) { @@ -936,6 +1168,10 @@ static int userfaultfd_stress(void) area_src = area_dst; area_dst = tmp_area; + tmp_area = area_src_alias; + area_src_alias = area_dst_alias; + area_dst_alias = tmp_area; + printf("userfaults:"); for (cpu = 0; cpu < nr_cpus; cpu++) printf(" %lu", userfaults[cpu]); @@ -946,7 +1182,8 @@ static int userfaultfd_stress(void) return err; close(uffd); - return userfaultfd_zeropage_test() || userfaultfd_events_test(); + return userfaultfd_zeropage_test() || userfaultfd_sig_test() + || userfaultfd_events_test(); } /* @@ -981,7 +1218,12 @@ static void set_test_type(const char *type) } else if (!strcmp(type, "hugetlb")) { test_type = TEST_HUGETLB; uffd_test_ops = &hugetlb_uffd_test_ops; + } else if (!strcmp(type, "hugetlb_shared")) { + map_shared = true; + test_type = TEST_HUGETLB; + uffd_test_ops = &hugetlb_uffd_test_ops; } else if (!strcmp(type, "shmem")) { + map_shared = true; test_type = TEST_SHMEM; uffd_test_ops = &shmem_uffd_test_ops; } else { @@ -1001,12 +1243,25 @@ static void set_test_type(const char *type) fprintf(stderr, "Impossible to run this test\n"), exit(2); } +static void sigalrm(int sig) +{ + if (sig != SIGALRM) + abort(); + test_uffdio_copy_eexist = true; + test_uffdio_zeropage_eexist = true; + alarm(ALARM_INTERVAL_SECS); +} + int main(int argc, char **argv) { if (argc < 4) fprintf(stderr, "Usage: <test type> <MiB> <bounces> [hugetlbfs_file]\n"), exit(1); + if (signal(SIGALRM, sigalrm) == SIG_ERR) + fprintf(stderr, "failed to arm SIGALRM"), exit(1); + alarm(ALARM_INTERVAL_SECS); + set_test_type(argv[1]); nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); diff --git a/tools/testing/selftests/vm/virtual_address_range.c b/tools/testing/selftests/vm/virtual_address_range.c index 3b02aa6eb9da..1830d66a6f0e 100644 --- a/tools/testing/selftests/vm/virtual_address_range.c +++ b/tools/testing/selftests/vm/virtual_address_range.c @@ -10,7 +10,6 @@ #include <string.h> #include <unistd.h> #include <errno.h> -#include <numaif.h> #include <sys/mman.h> #include <sys/time.h> @@ -32,15 +31,33 @@ * different areas one below 128TB and one above 128TB * till it reaches 512TB. One with size 128TB and the * other being 384TB. + * + * On Arm64 the address space is 256TB and no high mappings + * are supported so far. */ + #define NR_CHUNKS_128TB 8192UL /* Number of 16GB chunks for 128TB */ -#define NR_CHUNKS_384TB 24576UL /* Number of 16GB chunks for 384TB */ +#define NR_CHUNKS_256TB (NR_CHUNKS_128TB * 2UL) +#define NR_CHUNKS_384TB (NR_CHUNKS_128TB * 3UL) #define ADDR_MARK_128TB (1UL << 47) /* First address beyond 128TB */ +#define ADDR_MARK_256TB (1UL << 48) /* First address beyond 256TB */ + +#ifdef __aarch64__ +#define HIGH_ADDR_MARK ADDR_MARK_256TB +#define HIGH_ADDR_SHIFT 49 +#define NR_CHUNKS_LOW NR_CHUNKS_256TB +#define NR_CHUNKS_HIGH 0 +#else +#define HIGH_ADDR_MARK ADDR_MARK_128TB +#define HIGH_ADDR_SHIFT 48 +#define NR_CHUNKS_LOW NR_CHUNKS_128TB +#define NR_CHUNKS_HIGH NR_CHUNKS_384TB +#endif static char *hind_addr(void) { - int bits = 48 + rand() % 15; + int bits = HIGH_ADDR_SHIFT + rand() % (63 - HIGH_ADDR_SHIFT); return (char *) (1UL << bits); } @@ -50,14 +67,14 @@ static int validate_addr(char *ptr, int high_addr) unsigned long addr = (unsigned long) ptr; if (high_addr) { - if (addr < ADDR_MARK_128TB) { + if (addr < HIGH_ADDR_MARK) { printf("Bad address %lx\n", addr); return 1; } return 0; } - if (addr > ADDR_MARK_128TB) { + if (addr > HIGH_ADDR_MARK) { printf("Bad address %lx\n", addr); return 1; } @@ -79,12 +96,12 @@ static int validate_lower_address_hint(void) int main(int argc, char *argv[]) { - char *ptr[NR_CHUNKS_128TB]; - char *hptr[NR_CHUNKS_384TB]; + char *ptr[NR_CHUNKS_LOW]; + char *hptr[NR_CHUNKS_HIGH]; char *hint; unsigned long i, lchunks, hchunks; - for (i = 0; i < NR_CHUNKS_128TB; i++) { + for (i = 0; i < NR_CHUNKS_LOW; i++) { ptr[i] = mmap(NULL, MAP_CHUNK_SIZE, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); @@ -99,7 +116,7 @@ int main(int argc, char *argv[]) } lchunks = i; - for (i = 0; i < NR_CHUNKS_384TB; i++) { + for (i = 0; i < NR_CHUNKS_HIGH; i++) { hint = hind_addr(); hptr[i] = mmap(hint, MAP_CHUNK_SIZE, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); diff --git a/tools/testing/selftests/watchdog/watchdog-test.c b/tools/testing/selftests/watchdog/watchdog-test.c index a74c9d739d07..a1391be2dc1e 100644 --- a/tools/testing/selftests/watchdog/watchdog-test.c +++ b/tools/testing/selftests/watchdog/watchdog-test.c @@ -9,12 +9,25 @@ #include <unistd.h> #include <fcntl.h> #include <signal.h> +#include <getopt.h> #include <sys/ioctl.h> #include <linux/types.h> #include <linux/watchdog.h> +#define DEFAULT_PING_RATE 1 + int fd; const char v = 'V'; +static const char sopts[] = "bdehp:t:"; +static const struct option lopts[] = { + {"bootstatus", no_argument, NULL, 'b'}, + {"disable", no_argument, NULL, 'd'}, + {"enable", no_argument, NULL, 'e'}, + {"help", no_argument, NULL, 'h'}, + {"pingrate", required_argument, NULL, 'p'}, + {"timeout", required_argument, NULL, 't'}, + {NULL, no_argument, NULL, 0x0} +}; /* * This function simply sends an IOCTL to the driver, which in turn ticks @@ -23,12 +36,12 @@ const char v = 'V'; */ static void keep_alive(void) { - int dummy; - int ret; + int dummy; + int ret; - ret = ioctl(fd, WDIOC_KEEPALIVE, &dummy); - if (!ret) - printf("."); + ret = ioctl(fd, WDIOC_KEEPALIVE, &dummy); + if (!ret) + printf("."); } /* @@ -38,75 +51,110 @@ static void keep_alive(void) static void term(int sig) { - int ret = write(fd, &v, 1); - - close(fd); - if (ret < 0) - printf("\nStopping watchdog ticks failed (%d)...\n", errno); - else - printf("\nStopping watchdog ticks...\n"); - exit(0); + int ret = write(fd, &v, 1); + + close(fd); + if (ret < 0) + printf("\nStopping watchdog ticks failed (%d)...\n", errno); + else + printf("\nStopping watchdog ticks...\n"); + exit(0); +} + +static void usage(char *progname) +{ + printf("Usage: %s [options]\n", progname); + printf(" -b, --bootstatus Get last boot status (Watchdog/POR)\n"); + printf(" -d, --disable Turn off the watchdog timer\n"); + printf(" -e, --enable Turn on the watchdog timer\n"); + printf(" -h, --help Print the help message\n"); + printf(" -p, --pingrate=P Set ping rate to P seconds (default %d)\n", DEFAULT_PING_RATE); + printf(" -t, --timeout=T Set timeout to T seconds\n"); + printf("\n"); + printf("Parameters are parsed left-to-right in real-time.\n"); + printf("Example: %s -d -t 10 -p 5 -e\n", progname); } int main(int argc, char *argv[]) { - int flags; - unsigned int ping_rate = 1; - int ret; - int i; - - setbuf(stdout, NULL); - - fd = open("/dev/watchdog", O_WRONLY); - - if (fd == -1) { - printf("Watchdog device not enabled.\n"); - exit(-1); - } - - for (i = 1; i < argc; i++) { - if (!strncasecmp(argv[i], "-d", 2)) { - flags = WDIOS_DISABLECARD; - ret = ioctl(fd, WDIOC_SETOPTIONS, &flags); - if (!ret) - printf("Watchdog card disabled.\n"); - } else if (!strncasecmp(argv[i], "-e", 2)) { - flags = WDIOS_ENABLECARD; - ret = ioctl(fd, WDIOC_SETOPTIONS, &flags); - if (!ret) - printf("Watchdog card enabled.\n"); - } else if (!strncasecmp(argv[i], "-t", 2) && argv[2]) { - flags = atoi(argv[i + 1]); - ret = ioctl(fd, WDIOC_SETTIMEOUT, &flags); - if (!ret) - printf("Watchdog timeout set to %u seconds.\n", flags); - i++; - } else if (!strncasecmp(argv[i], "-p", 2) && argv[2]) { - ping_rate = strtoul(argv[i + 1], NULL, 0); - printf("Watchdog ping rate set to %u seconds.\n", ping_rate); - i++; - } else { - printf("-d to disable, -e to enable, -t <n> to set " - "the timeout,\n-p <n> to set the ping rate, and "); - printf("run by itself to tick the card.\n"); - printf("Parameters are parsed left-to-right in real-time.\n"); - printf("Example: %s -d -t 10 -p 5 -e\n", argv[0]); - goto end; - } - } - - printf("Watchdog Ticking Away!\n"); - - signal(SIGINT, term); - - while(1) { - keep_alive(); - sleep(ping_rate); - } + int flags; + unsigned int ping_rate = DEFAULT_PING_RATE; + int ret; + int c; + int oneshot = 0; + + setbuf(stdout, NULL); + + fd = open("/dev/watchdog", O_WRONLY); + + if (fd == -1) { + printf("Watchdog device not enabled.\n"); + exit(-1); + } + + while ((c = getopt_long(argc, argv, sopts, lopts, NULL)) != -1) { + switch (c) { + case 'b': + flags = 0; + oneshot = 1; + ret = ioctl(fd, WDIOC_GETBOOTSTATUS, &flags); + if (!ret) + printf("Last boot is caused by: %s.\n", (flags != 0) ? + "Watchdog" : "Power-On-Reset"); + else + printf("WDIOC_GETBOOTSTATUS errno '%s'\n", strerror(errno)); + break; + case 'd': + flags = WDIOS_DISABLECARD; + ret = ioctl(fd, WDIOC_SETOPTIONS, &flags); + if (!ret) + printf("Watchdog card disabled.\n"); + else + printf("WDIOS_DISABLECARD errno '%s'\n", strerror(errno)); + break; + case 'e': + flags = WDIOS_ENABLECARD; + ret = ioctl(fd, WDIOC_SETOPTIONS, &flags); + if (!ret) + printf("Watchdog card enabled.\n"); + else + printf("WDIOS_ENABLECARD errno '%s'\n", strerror(errno)); + break; + case 'p': + ping_rate = strtoul(optarg, NULL, 0); + if (!ping_rate) + ping_rate = DEFAULT_PING_RATE; + printf("Watchdog ping rate set to %u seconds.\n", ping_rate); + break; + case 't': + flags = strtoul(optarg, NULL, 0); + ret = ioctl(fd, WDIOC_SETTIMEOUT, &flags); + if (!ret) + printf("Watchdog timeout set to %u seconds.\n", flags); + else + printf("WDIOC_SETTIMEOUT errno '%s'\n", strerror(errno)); + break; + default: + usage(argv[0]); + goto end; + } + } + + if (oneshot) + goto end; + + printf("Watchdog Ticking Away!\n"); + + signal(SIGINT, term); + + while (1) { + keep_alive(); + sleep(ping_rate); + } end: - ret = write(fd, &v, 1); - if (ret < 0) - printf("Stopping watchdog ticks failed (%d)...\n", errno); - close(fd); - return 0; + ret = write(fd, &v, 1); + if (ret < 0) + printf("Stopping watchdog ticks failed (%d)...\n", errno); + close(fd); + return 0; } diff --git a/tools/testing/selftests/x86/fsgsbase.c b/tools/testing/selftests/x86/fsgsbase.c index b4967d875236..f249e042b3b5 100644 --- a/tools/testing/selftests/x86/fsgsbase.c +++ b/tools/testing/selftests/x86/fsgsbase.c @@ -285,9 +285,12 @@ static void *threadproc(void *ctx) } } -static void set_gs_and_switch_to(unsigned long local, unsigned long remote) +static void set_gs_and_switch_to(unsigned long local, + unsigned short force_sel, + unsigned long remote) { unsigned long base; + unsigned short sel_pre_sched, sel_post_sched; bool hard_zero = false; if (local == HARD_ZERO) { @@ -297,6 +300,8 @@ static void set_gs_and_switch_to(unsigned long local, unsigned long remote) printf("[RUN]\tARCH_SET_GS(0x%lx)%s, then schedule to 0x%lx\n", local, hard_zero ? " and clear gs" : "", remote); + if (force_sel) + printf("\tBefore schedule, set selector to 0x%hx\n", force_sel); if (syscall(SYS_arch_prctl, ARCH_SET_GS, local) != 0) err(1, "ARCH_SET_GS"); if (hard_zero) @@ -307,18 +312,35 @@ static void set_gs_and_switch_to(unsigned long local, unsigned long remote) printf("[FAIL]\tGSBASE wasn't set as expected\n"); } + if (force_sel) { + asm volatile ("mov %0, %%gs" : : "rm" (force_sel)); + sel_pre_sched = force_sel; + local = read_base(GS); + + /* + * Signal delivery seems to mess up weird selectors. Put it + * back. + */ + asm volatile ("mov %0, %%gs" : : "rm" (force_sel)); + } else { + asm volatile ("mov %%gs, %0" : "=rm" (sel_pre_sched)); + } + remote_base = remote; ftx = 1; syscall(SYS_futex, &ftx, FUTEX_WAKE, 0, NULL, NULL, 0); while (ftx != 0) syscall(SYS_futex, &ftx, FUTEX_WAIT, 1, NULL, NULL, 0); + asm volatile ("mov %%gs, %0" : "=rm" (sel_post_sched)); base = read_base(GS); - if (base == local) { - printf("[OK]\tGSBASE remained 0x%lx\n", local); + if (base == local && sel_pre_sched == sel_post_sched) { + printf("[OK]\tGS/BASE remained 0x%hx/0x%lx\n", + sel_pre_sched, local); } else { nerrs++; - printf("[FAIL]\tGSBASE changed to 0x%lx\n", base); + printf("[FAIL]\tGS/BASE changed from 0x%hx/0x%lx to 0x%hx/0x%lx\n", + sel_pre_sched, local, sel_post_sched, base); } } @@ -381,8 +403,15 @@ int main() for (int local = 0; local < 4; local++) { for (int remote = 0; remote < 4; remote++) { - set_gs_and_switch_to(bases_with_hard_zero[local], - bases_with_hard_zero[remote]); + for (unsigned short s = 0; s < 5; s++) { + unsigned short sel = s; + if (s == 4) + asm ("mov %%ss, %0" : "=rm" (sel)); + set_gs_and_switch_to( + bases_with_hard_zero[local], + sel, + bases_with_hard_zero[remote]); + } } } diff --git a/tools/testing/selftests/x86/mpx-mini-test.c b/tools/testing/selftests/x86/mpx-mini-test.c index a8df159a8924..ec0f6b45ce8b 100644 --- a/tools/testing/selftests/x86/mpx-mini-test.c +++ b/tools/testing/selftests/x86/mpx-mini-test.c @@ -391,8 +391,7 @@ void handler(int signum, siginfo_t *si, void *vucontext) br_count++; dprintf1("#BR 0x%jx (total seen: %d)\n", status, br_count); -#define __SI_FAULT (3 << 16) -#define SEGV_BNDERR (__SI_FAULT|3) /* failed address bound checks */ +#define SEGV_BNDERR 3 /* failed address bound checks */ dprintf2("Saw a #BR! status 0x%jx at %016lx br_reason: %jx\n", status, ip, br_reason); diff --git a/tools/testing/selftests/x86/protection_keys.c b/tools/testing/selftests/x86/protection_keys.c index 3237bc010e1c..23927845518d 100644 --- a/tools/testing/selftests/x86/protection_keys.c +++ b/tools/testing/selftests/x86/protection_keys.c @@ -212,19 +212,18 @@ void dump_mem(void *dumpme, int len_bytes) } } -#define __SI_FAULT (3 << 16) -#define SEGV_BNDERR (__SI_FAULT|3) /* failed address bound checks */ -#define SEGV_PKUERR (__SI_FAULT|4) +#define SEGV_BNDERR 3 /* failed address bound checks */ +#define SEGV_PKUERR 4 static char *si_code_str(int si_code) { - if (si_code & SEGV_MAPERR) + if (si_code == SEGV_MAPERR) return "SEGV_MAPERR"; - if (si_code & SEGV_ACCERR) + if (si_code == SEGV_ACCERR) return "SEGV_ACCERR"; - if (si_code & SEGV_BNDERR) + if (si_code == SEGV_BNDERR) return "SEGV_BNDERR"; - if (si_code & SEGV_PKUERR) + if (si_code == SEGV_PKUERR) return "SEGV_PKUERR"; return "UNKNOWN"; } diff --git a/tools/usb/testusb.c b/tools/usb/testusb.c index 0692d99b6d8f..2d89b5f686b1 100644 --- a/tools/usb/testusb.c +++ b/tools/usb/testusb.c @@ -387,15 +387,17 @@ int main (int argc, char **argv) /* pick defaults that works with all speeds, without short packets. * * Best per-frame data rates: - * high speed, bulk 512 * 13 * 8 = 53248 - * interrupt 1024 * 3 * 8 = 24576 - * full speed, bulk/intr 64 * 19 = 1216 - * interrupt 64 * 1 = 64 - * low speed, interrupt 8 * 1 = 8 + * super speed,bulk 1024 * 16 * 8 = 131072 + * interrupt 1024 * 3 * 8 = 24576 + * high speed, bulk 512 * 13 * 8 = 53248 + * interrupt 1024 * 3 * 8 = 24576 + * full speed, bulk/intr 64 * 19 = 1216 + * interrupt 64 * 1 = 64 + * low speed, interrupt 8 * 1 = 8 */ param.iterations = 1000; param.length = 1024; - param.vary = 512; + param.vary = 1024; param.sglen = 32; /* for easy use when hotplugging */ @@ -457,7 +459,7 @@ usage: "\t-c iterations default 1000\n" "\t-s transfer length default 1024\n" "\t-g sglen default 32\n" - "\t-v vary default 512\n", + "\t-v vary default 1024\n", argv[0]); return 1; } diff --git a/tools/usb/usbip/libsrc/vhci_driver.c b/tools/usb/usbip/libsrc/vhci_driver.c index f659c146cdc8..9bd2cd71645d 100644 --- a/tools/usb/usbip/libsrc/vhci_driver.c +++ b/tools/usb/usbip/libsrc/vhci_driver.c @@ -7,6 +7,7 @@ #include <limits.h> #include <netdb.h> #include <libudev.h> +#include <dirent.h> #include "sysfs_utils.h" #undef PROGNAME @@ -35,18 +36,11 @@ err: return NULL; } - - static int parse_status(const char *value) { int ret = 0; char *c; - - for (int i = 0; i < vhci_driver->nports; i++) - memset(&vhci_driver->idev[i], 0, sizeof(vhci_driver->idev[i])); - - /* skip a header line */ c = strchr(value, '\n'); if (!c) @@ -57,9 +51,11 @@ static int parse_status(const char *value) int port, status, speed, devid; unsigned long socket; char lbusid[SYSFS_BUS_ID_SIZE]; + struct usbip_imported_device *idev; + char hub[3]; - ret = sscanf(c, "%d %d %d %x %lx %31s\n", - &port, &status, &speed, + ret = sscanf(c, "%2s %d %d %d %x %lx %31s\n", + hub, &port, &status, &speed, &devid, &socket, lbusid); if (ret < 5) { @@ -67,34 +63,36 @@ static int parse_status(const char *value) BUG(); } - dbg("port %d status %d speed %d devid %x", - port, status, speed, devid); + dbg("hub %s port %d status %d speed %d devid %x", + hub, port, status, speed, devid); dbg("socket %lx lbusid %s", socket, lbusid); - /* if a device is connected, look at it */ - { - struct usbip_imported_device *idev = &vhci_driver->idev[port]; + idev = &vhci_driver->idev[port]; + memset(idev, 0, sizeof(*idev)); + + if (strncmp("hs", hub, 2) == 0) + idev->hub = HUB_SPEED_HIGH; + else /* strncmp("ss", hub, 2) == 0 */ + idev->hub = HUB_SPEED_SUPER; - idev->port = port; - idev->status = status; + idev->port = port; + idev->status = status; - idev->devid = devid; + idev->devid = devid; - idev->busnum = (devid >> 16); - idev->devnum = (devid & 0x0000ffff); + idev->busnum = (devid >> 16); + idev->devnum = (devid & 0x0000ffff); - if (idev->status != VDEV_ST_NULL - && idev->status != VDEV_ST_NOTASSIGNED) { - idev = imported_device_init(idev, lbusid); - if (!idev) { - dbg("imported_device_init failed"); - return -1; - } + if (idev->status != VDEV_ST_NULL + && idev->status != VDEV_ST_NOTASSIGNED) { + idev = imported_device_init(idev, lbusid); + if (!idev) { + dbg("imported_device_init failed"); + return -1; } } - /* go to the next line */ c = strchr(c, '\n'); if (!c) @@ -107,18 +105,33 @@ static int parse_status(const char *value) return 0; } +#define MAX_STATUS_NAME 16 + static int refresh_imported_device_list(void) { const char *attr_status; + char status[MAX_STATUS_NAME+1] = "status"; + int i, ret; - attr_status = udev_device_get_sysattr_value(vhci_driver->hc_device, - "status"); - if (!attr_status) { - err("udev_device_get_sysattr_value failed"); - return -1; + for (i = 0; i < vhci_driver->ncontrollers; i++) { + if (i > 0) + snprintf(status, sizeof(status), "status.%d", i); + + attr_status = udev_device_get_sysattr_value(vhci_driver->hc_device, + status); + if (!attr_status) { + err("udev_device_get_sysattr_value failed"); + return -1; + } + + dbg("controller %d", i); + + ret = parse_status(attr_status); + if (ret != 0) + return ret; } - return parse_status(attr_status); + return 0; } static int get_nports(void) @@ -134,6 +147,33 @@ static int get_nports(void) return (int)strtoul(attr_nports, NULL, 10); } +static int vhci_hcd_filter(const struct dirent *dirent) +{ + return strcmp(dirent->d_name, "vhci_hcd") >= 0; +} + +static int get_ncontrollers(void) +{ + struct dirent **namelist; + struct udev_device *platform; + int n; + + platform = udev_device_get_parent(vhci_driver->hc_device); + if (platform == NULL) + return -1; + + n = scandir(udev_device_get_syspath(platform), &namelist, vhci_hcd_filter, NULL); + if (n < 0) + err("scandir failed"); + else { + for (int i = 0; i < n; i++) + free(namelist[i]); + free(namelist); + } + + return n; +} + /* * Read the given port's record. * @@ -213,16 +253,31 @@ int usbip_vhci_driver_open(void) vhci_driver->hc_device = udev_device_new_from_subsystem_sysname(udev_context, USBIP_VHCI_BUS_TYPE, - USBIP_VHCI_DRV_NAME); + USBIP_VHCI_DEVICE_NAME); if (!vhci_driver->hc_device) { err("udev_device_new_from_subsystem_sysname failed"); goto err; } vhci_driver->nports = get_nports(); - dbg("available ports: %d", vhci_driver->nports); + if (vhci_driver->nports <= 0) { + err("no available ports"); + goto err; + } else if (vhci_driver->nports > MAXNPORT) { + err("port number exceeds %d", MAXNPORT); + goto err; + } + + vhci_driver->ncontrollers = get_ncontrollers(); + dbg("available controllers: %d", vhci_driver->ncontrollers); + + if (vhci_driver->ncontrollers <=0) { + err("no available usb controllers"); + goto err; + } + if (refresh_imported_device_list()) goto err; @@ -270,11 +325,15 @@ err: } -int usbip_vhci_get_free_port(void) +int usbip_vhci_get_free_port(uint32_t speed) { for (int i = 0; i < vhci_driver->nports; i++) { + if (speed == USB_SPEED_SUPER && + vhci_driver->idev[i].hub != HUB_SPEED_SUPER) + continue; + if (vhci_driver->idev[i].status == VDEV_ST_NULL) - return i; + return vhci_driver->idev[i].port; } return -1; diff --git a/tools/usb/usbip/libsrc/vhci_driver.h b/tools/usb/usbip/libsrc/vhci_driver.h index fa2316cf2cac..4898d3bafb10 100644 --- a/tools/usb/usbip/libsrc/vhci_driver.h +++ b/tools/usb/usbip/libsrc/vhci_driver.h @@ -11,9 +11,16 @@ #include "usbip_common.h" #define USBIP_VHCI_BUS_TYPE "platform" +#define USBIP_VHCI_DEVICE_NAME "vhci_hcd.0" #define MAXNPORT 128 +enum hub_speed { + HUB_SPEED_HIGH = 0, + HUB_SPEED_SUPER, +}; + struct usbip_imported_device { + enum hub_speed hub; uint8_t port; uint32_t status; @@ -31,6 +38,7 @@ struct usbip_vhci_driver { /* /sys/devices/platform/vhci_hcd */ struct udev_device *hc_device; + int ncontrollers; int nports; struct usbip_imported_device idev[MAXNPORT]; }; @@ -44,7 +52,7 @@ void usbip_vhci_driver_close(void); int usbip_vhci_refresh_device_list(void); -int usbip_vhci_get_free_port(void); +int usbip_vhci_get_free_port(uint32_t speed); int usbip_vhci_attach_device2(uint8_t port, int sockfd, uint32_t devid, uint32_t speed); diff --git a/tools/usb/usbip/src/usbip_attach.c b/tools/usb/usbip/src/usbip_attach.c index 70a6b507fb62..7f07b2d50f59 100644 --- a/tools/usb/usbip/src/usbip_attach.c +++ b/tools/usb/usbip/src/usbip_attach.c @@ -94,31 +94,39 @@ static int import_device(int sockfd, struct usbip_usb_device *udev) { int rc; int port; + uint32_t speed = udev->speed; rc = usbip_vhci_driver_open(); if (rc < 0) { err("open vhci_driver"); - return -1; + goto err_out; } - port = usbip_vhci_get_free_port(); - if (port < 0) { - err("no free port"); - usbip_vhci_driver_close(); - return -1; - } + do { + port = usbip_vhci_get_free_port(speed); + if (port < 0) { + err("no free port"); + goto err_driver_close; + } - rc = usbip_vhci_attach_device(port, sockfd, udev->busnum, - udev->devnum, udev->speed); - if (rc < 0) { - err("import device"); - usbip_vhci_driver_close(); - return -1; - } + dbg("got free port %d", port); + + rc = usbip_vhci_attach_device(port, sockfd, udev->busnum, + udev->devnum, udev->speed); + if (rc < 0 && errno != EBUSY) { + err("import device"); + goto err_driver_close; + } + } while (rc < 0); usbip_vhci_driver_close(); return port; + +err_driver_close: + usbip_vhci_driver_close(); +err_out: + return -1; } static int query_import_device(int sockfd, char *busid) |