diff options
Diffstat (limited to 'tools')
75 files changed, 2370 insertions, 375 deletions
diff --git a/tools/Makefile b/tools/Makefile index f10b64d8c674..daa8fb3e4363 100644 --- a/tools/Makefile +++ b/tools/Makefile @@ -85,7 +85,7 @@ tmon: FORCE freefall: FORCE $(call descend,laptop/$@) -all: acpi cgroup cpupower hv firewire lguest \ +all: acpi cgroup cpupower gpio hv firewire lguest \ perf selftests turbostat usb \ virtio vm net x86_energy_perf_policy \ tmon freefall objtool @@ -96,7 +96,7 @@ acpi_install: cpupower_install: $(call descend,power/$(@:_install=),install) -cgroup_install firewire_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 lguest_install perf_install usb_install virtio_install vm_install net_install objtool_install: $(call descend,$(@:_install=),install) selftests_install: @@ -114,7 +114,8 @@ freefall_install: kvm_stat_install: $(call descend,kvm/$(@:_install=),install) -install: acpi_install cgroup_install cpupower_install hv_install firewire_install lguest_install \ +install: acpi_install cgroup_install cpupower_install gpio_install \ + hv_install firewire_install lguest_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 diff --git a/tools/gpio/Build b/tools/gpio/Build new file mode 100644 index 000000000000..620c1937d957 --- /dev/null +++ b/tools/gpio/Build @@ -0,0 +1,3 @@ +lsgpio-y += lsgpio.o gpio-utils.o +gpio-hammer-y += gpio-hammer.o gpio-utils.o +gpio-event-mon-y += gpio-event-mon.o gpio-utils.o diff --git a/tools/gpio/Makefile b/tools/gpio/Makefile index c155d6bc47a7..250a891e6ef0 100644 --- a/tools/gpio/Makefile +++ b/tools/gpio/Makefile @@ -1,12 +1,75 @@ +include ../scripts/Makefile.include + +bindir ?= /usr/bin + +ifeq ($(srctree),) +srctree := $(patsubst %/,%,$(dir $(shell pwd))) +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 += -O2 -Wall -g -D_GNU_SOURCE +LD = $(CROSS_COMPILE)ld +CFLAGS += -O2 -Wall -g -D_GNU_SOURCE -I$(OUTPUT)include + +ALL_TARGETS := lsgpio gpio-hammer gpio-event-mon +ALL_PROGRAMS := $(patsubst %,$(OUTPUT)%,$(ALL_TARGETS)) + +all: $(ALL_PROGRAMS) -all: lsgpio +export srctree OUTPUT CC LD CFLAGS +include $(srctree)/tools/build/Makefile.include -lsgpio: lsgpio.o gpio-utils.o +# +# We need the following to be outside of kernel tree +# +$(OUTPUT)include/linux/gpio.h: ../../include/uapi/linux/gpio.h + mkdir -p $(OUTPUT)include/linux 2>&1 || true + ln -sf $(CURDIR)/../../include/uapi/linux/gpio.h $@ -%.o: %.c gpio-utils.h +prepare: $(OUTPUT)include/linux/gpio.h + +# +# lsgpio +# +LSGPIO_IN := $(OUTPUT)lsgpio-in.o +$(LSGPIO_IN): prepare FORCE + $(Q)$(MAKE) $(build)=lsgpio +$(OUTPUT)lsgpio: $(LSGPIO_IN) + $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@ + +# +# gpio-hammer +# +GPIO_HAMMER_IN := $(OUTPUT)gpio-hammer-in.o +$(GPIO_HAMMER_IN): prepare FORCE + $(Q)$(MAKE) $(build)=gpio-hammer +$(OUTPUT)gpio-hammer: $(GPIO_HAMMER_IN) + $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@ + +# +# gpio-event-mon +# +GPIO_EVENT_MON_IN := $(OUTPUT)gpio-event-mon-in.o +$(GPIO_EVENT_MON_IN): prepare FORCE + $(Q)$(MAKE) $(build)=gpio-event-mon +$(OUTPUT)gpio-event-mon: $(GPIO_EVENT_MON_IN) + $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@ -.PHONY: clean clean: - rm -f *.o lsgpio + rm -f $(ALL_PROGRAMS) + rm -f $(OUTPUT)include/linux/gpio.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/gpio/gpio-event-mon.c b/tools/gpio/gpio-event-mon.c new file mode 100644 index 000000000000..448ed96b3b4f --- /dev/null +++ b/tools/gpio/gpio-event-mon.c @@ -0,0 +1,192 @@ +/* + * gpio-hammer - example swiss army knife to shake GPIO lines on a system + * + * Copyright (C) 2016 Linus Walleij + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + * + * Usage: + * gpio-event-mon -n <device-name> -o <offset> + */ + +#include <unistd.h> +#include <stdlib.h> +#include <stdbool.h> +#include <stdio.h> +#include <dirent.h> +#include <errno.h> +#include <string.h> +#include <poll.h> +#include <fcntl.h> +#include <getopt.h> +#include <inttypes.h> +#include <sys/ioctl.h> +#include <linux/gpio.h> + +int monitor_device(const char *device_name, + unsigned int line, + u_int32_t handleflags, + u_int32_t eventflags, + unsigned int loops) +{ + struct gpioevent_request req; + struct gpiohandle_data data; + char *chrdev_name; + int fd; + int ret; + int i = 0; + + ret = asprintf(&chrdev_name, "/dev/%s", device_name); + if (ret < 0) + return -ENOMEM; + + fd = open(chrdev_name, 0); + if (fd == -1) { + ret = -errno; + fprintf(stderr, "Failed to open %s\n", chrdev_name); + goto exit_close_error; + } + + req.lineoffset = line; + req.handleflags = handleflags; + req.eventflags = eventflags; + strcpy(req.consumer_label, "gpio-event-mon"); + + ret = ioctl(fd, GPIO_GET_LINEEVENT_IOCTL, &req); + if (ret == -1) { + ret = -errno; + fprintf(stderr, "Failed to issue GET EVENT " + "IOCTL (%d)\n", + ret); + goto exit_close_error; + } + + /* Read initial states */ + ret = ioctl(req.fd, GPIOHANDLE_GET_LINE_VALUES_IOCTL, &data); + if (ret == -1) { + ret = -errno; + fprintf(stderr, "Failed to issue GPIOHANDLE GET LINE " + "VALUES IOCTL (%d)\n", + ret); + goto exit_close_error; + } + + fprintf(stdout, "Monitoring line %d on %s\n", line, device_name); + fprintf(stdout, "Initial line value: %d\n", data.values[0]); + + while (1) { + struct gpioevent_data event; + + ret = read(req.fd, &event, sizeof(event)); + if (ret == -1) { + if (errno == -EAGAIN) { + fprintf(stderr, "nothing available\n"); + continue; + } else { + ret = -errno; + fprintf(stderr, "Failed to read event (%d)\n", + ret); + break; + } + } + + if (ret != sizeof(event)) { + fprintf(stderr, "Reading event failed\n"); + ret = -EIO; + break; + } + fprintf(stdout, "GPIO EVENT %" PRIu64 ": ", event.timestamp); + switch (event.id) { + case GPIOEVENT_EVENT_RISING_EDGE: + fprintf(stdout, "rising edge"); + break; + case GPIOEVENT_EVENT_FALLING_EDGE: + fprintf(stdout, "falling edge"); + break; + default: + fprintf(stdout, "unknown event"); + } + fprintf(stdout, "\n"); + + i++; + if (i == loops) + break; + } + +exit_close_error: + if (close(fd) == -1) + perror("Failed to close GPIO character device file"); + free(chrdev_name); + return ret; +} + +void print_usage(void) +{ + fprintf(stderr, "Usage: gpio-event-mon [options]...\n" + "Listen to events on GPIO lines, 0->1 1->0\n" + " -n <name> Listen on GPIOs on a named device (must be stated)\n" + " -o <n> Offset to monitor\n" + " -d Set line as open drain\n" + " -s Set line as open source\n" + " -r Listen for rising edges\n" + " -f Listen for falling edges\n" + " [-c <n>] Do <n> loops (optional, infinite loop if not stated)\n" + " -? This helptext\n" + "\n" + "Example:\n" + "gpio-event-mon -n gpiochip0 -o 4 -r -f\n" + ); +} + +int main(int argc, char **argv) +{ + const char *device_name = NULL; + unsigned int line = -1; + unsigned int loops = 0; + u_int32_t handleflags = GPIOHANDLE_REQUEST_INPUT; + u_int32_t eventflags = 0; + int c; + + while ((c = getopt(argc, argv, "c:n:o:dsrf?")) != -1) { + switch (c) { + case 'c': + loops = strtoul(optarg, NULL, 10); + break; + case 'n': + device_name = optarg; + break; + case 'o': + line = strtoul(optarg, NULL, 10); + break; + case 'd': + handleflags |= GPIOHANDLE_REQUEST_OPEN_DRAIN; + break; + case 's': + handleflags |= GPIOHANDLE_REQUEST_OPEN_SOURCE; + break; + case 'r': + eventflags |= GPIOEVENT_REQUEST_RISING_EDGE; + break; + case 'f': + eventflags |= GPIOEVENT_REQUEST_FALLING_EDGE; + break; + case '?': + print_usage(); + return -1; + } + } + + if (!device_name || line == -1) { + print_usage(); + return -1; + } + if (!eventflags) { + printf("No flags specified, listening on both rising and " + "falling edges\n"); + eventflags = GPIOEVENT_REQUEST_BOTH_EDGES; + } + return monitor_device(device_name, line, handleflags, + eventflags, loops); +} diff --git a/tools/gpio/gpio-hammer.c b/tools/gpio/gpio-hammer.c new file mode 100644 index 000000000000..37b3f141053d --- /dev/null +++ b/tools/gpio/gpio-hammer.c @@ -0,0 +1,189 @@ +/* + * gpio-hammer - example swiss army knife to shake GPIO lines on a system + * + * Copyright (C) 2016 Linus Walleij + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + * + * Usage: + * gpio-hammer -n <device-name> -o <offset1> -o <offset2> + */ + +#include <unistd.h> +#include <stdlib.h> +#include <stdbool.h> +#include <stdio.h> +#include <dirent.h> +#include <errno.h> +#include <string.h> +#include <poll.h> +#include <fcntl.h> +#include <getopt.h> +#include <sys/ioctl.h> +#include <linux/gpio.h> + +int hammer_device(const char *device_name, unsigned int *lines, int nlines, + unsigned int loops) +{ + struct gpiohandle_request req; + struct gpiohandle_data data; + char *chrdev_name; + char swirr[] = "-\\|/"; + int fd; + int ret; + int i, j; + unsigned int iteration = 0; + + ret = asprintf(&chrdev_name, "/dev/%s", device_name); + if (ret < 0) + return -ENOMEM; + + fd = open(chrdev_name, 0); + if (fd == -1) { + ret = -errno; + fprintf(stderr, "Failed to open %s\n", chrdev_name); + goto exit_close_error; + } + + /* Request lines as output */ + for (i = 0; i < nlines; i++) + req.lineoffsets[i] = lines[i]; + req.flags = GPIOHANDLE_REQUEST_OUTPUT; /* Request as output */ + strcpy(req.consumer_label, "gpio-hammer"); + req.lines = nlines; + ret = ioctl(fd, GPIO_GET_LINEHANDLE_IOCTL, &req); + if (ret == -1) { + ret = -errno; + fprintf(stderr, "Failed to issue GET LINEHANDLE " + "IOCTL (%d)\n", + ret); + goto exit_close_error; + } + + /* Read initial states */ + ret = ioctl(req.fd, GPIOHANDLE_GET_LINE_VALUES_IOCTL, &data); + if (ret == -1) { + ret = -errno; + fprintf(stderr, "Failed to issue GPIOHANDLE GET LINE " + "VALUES IOCTL (%d)\n", + ret); + goto exit_close_error; + } + fprintf(stdout, "Hammer lines ["); + for (i = 0; i < nlines; i++) { + fprintf(stdout, "%d", lines[i]); + if (i != (nlines - 1)) + fprintf(stdout, ", "); + } + fprintf(stdout, "] on %s, initial states: [", device_name); + for (i = 0; i < nlines; i++) { + fprintf(stdout, "%d", data.values[i]); + if (i != (nlines - 1)) + fprintf(stdout, ", "); + } + fprintf(stdout, "]\n"); + + /* Hammertime! */ + j = 0; + while (1) { + /* Invert all lines so we blink */ + for (i = 0; i < nlines; i++) + data.values[i] = !data.values[i]; + + ret = ioctl(req.fd, GPIOHANDLE_SET_LINE_VALUES_IOCTL, &data); + if (ret == -1) { + ret = -errno; + fprintf(stderr, "Failed to issue GPIOHANDLE SET LINE " + "VALUES IOCTL (%d)\n", + ret); + goto exit_close_error; + } + /* Re-read values to get status */ + ret = ioctl(req.fd, GPIOHANDLE_GET_LINE_VALUES_IOCTL, &data); + if (ret == -1) { + ret = -errno; + fprintf(stderr, "Failed to issue GPIOHANDLE GET LINE " + "VALUES IOCTL (%d)\n", + ret); + goto exit_close_error; + } + + fprintf(stdout, "[%c] ", swirr[j]); + j++; + if (j == sizeof(swirr)-1) + j = 0; + + fprintf(stdout, "["); + for (i = 0; i < nlines; i++) { + fprintf(stdout, "%d: %d", lines[i], data.values[i]); + if (i != (nlines - 1)) + fprintf(stdout, ", "); + } + fprintf(stdout, "]\r"); + fflush(stdout); + sleep(1); + iteration++; + if (loops && iteration == loops) + break; + } + fprintf(stdout, "\n"); + ret = 0; + +exit_close_error: + if (close(fd) == -1) + perror("Failed to close GPIO character device file"); + free(chrdev_name); + return ret; +} + +void print_usage(void) +{ + fprintf(stderr, "Usage: gpio-hammer [options]...\n" + "Hammer GPIO lines, 0->1->0->1...\n" + " -n <name> Hammer GPIOs on a named device (must be stated)\n" + " -o <n> Offset[s] to hammer, at least one, several can be stated\n" + " [-c <n>] Do <n> loops (optional, infinite loop if not stated)\n" + " -? This helptext\n" + "\n" + "Example:\n" + "gpio-hammer -n gpiochip0 -o 4\n" + ); +} + +int main(int argc, char **argv) +{ + const char *device_name = NULL; + unsigned int lines[GPIOHANDLES_MAX]; + unsigned int loops = 0; + int nlines; + int c; + int i; + + i = 0; + while ((c = getopt(argc, argv, "c:n:o:?")) != -1) { + switch (c) { + case 'c': + loops = strtoul(optarg, NULL, 10); + break; + case 'n': + device_name = optarg; + break; + case 'o': + lines[i] = strtoul(optarg, NULL, 10); + i++; + break; + case '?': + print_usage(); + return -1; + } + } + nlines = i; + + if (!device_name || !nlines) { + print_usage(); + return -1; + } + return hammer_device(device_name, lines, nlines, loops); +} diff --git a/tools/hv/bondvf.sh b/tools/hv/bondvf.sh new file mode 100755 index 000000000000..8e960234013d --- /dev/null +++ b/tools/hv/bondvf.sh @@ -0,0 +1,193 @@ +#!/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 ONBOOT=yes >>$fn + echo NM_CONTROLLED=no >>$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 ONBOOT=yes >>$fn + echo NM_CONTROLLED=no >>$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 create_eth_cfg_ubuntu { + local fn=$cfgdir/interfaces + + 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 + + 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/lib/api/Build b/tools/lib/api/Build index 954c644f7ad9..6e2373db5598 100644 --- a/tools/lib/api/Build +++ b/tools/lib/api/Build @@ -2,3 +2,8 @@ libapi-y += fd/ libapi-y += fs/ libapi-y += cpu.o libapi-y += debug.o +libapi-y += str_error_r.o + +$(OUTPUT)str_error_r.o: ../str_error_r.c FORCE + $(call rule_mkdir) + $(call if_changed_dep,cc_o_c) diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 32e6b6bc6f7d..b699aea9a025 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -37,6 +37,10 @@ #include "libbpf.h" #include "bpf.h" +#ifndef EM_BPF +#define EM_BPF 247 +#endif + #define __printf(a, b) __attribute__((format(printf, a, b))) __printf(1, 2) @@ -439,7 +443,8 @@ static int bpf_object__elf_init(struct bpf_object *obj) } ep = &obj->efile.ehdr; - if ((ep->e_type != ET_REL) || (ep->e_machine != 0)) { + /* Old LLVM set e_machine to EM_NONE */ + if ((ep->e_type != ET_REL) || (ep->e_machine && (ep->e_machine != EM_BPF))) { pr_warning("%s is not an eBPF object file\n", obj->path); err = -LIBBPF_ERRNO__FORMAT; diff --git a/tools/objtool/.gitignore b/tools/objtool/.gitignore index a0b3128bb31f..d3102c865a95 100644 --- a/tools/objtool/.gitignore +++ b/tools/objtool/.gitignore @@ -1,2 +1,3 @@ arch/x86/insn/inat-tables.c objtool +fixdep diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile index 0b437700f688..041b493ad3ab 100644 --- a/tools/objtool/Makefile +++ b/tools/objtool/Makefile @@ -51,7 +51,7 @@ $(OBJTOOL): $(LIBSUBCMD) $(OBJTOOL_IN) diff -I'^#include' arch/x86/insn/insn.h ../../arch/x86/include/asm/insn.h >/dev/null && \ 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 + || echo "warning: objtool: x86 instruction decoder differs from kernel" >&2 )) || true $(QUIET_LINK)$(CC) $(OBJTOOL_IN) $(LDFLAGS) -o $@ diff --git a/tools/objtool/arch/x86/insn/gen-insn-attr-x86.awk b/tools/objtool/arch/x86/insn/gen-insn-attr-x86.awk index 093a892026f9..a3d2c62fd805 100644 --- a/tools/objtool/arch/x86/insn/gen-insn-attr-x86.awk +++ b/tools/objtool/arch/x86/insn/gen-insn-attr-x86.awk @@ -72,12 +72,14 @@ BEGIN { lprefix_expr = "\\((66|F2|F3)\\)" max_lprefix = 4 - # All opcodes starting with lower-case 'v' or with (v1) superscript + # All opcodes starting with lower-case 'v', 'k' or with (v1) superscript # accepts VEX prefix - vexok_opcode_expr = "^v.*" + vexok_opcode_expr = "^[vk].*" vexok_expr = "\\(v1\\)" # All opcodes with (v) superscript supports *only* VEX prefix vexonly_expr = "\\(v\\)" + # All opcodes with (ev) superscript supports *only* EVEX prefix + evexonly_expr = "\\(ev\\)" prefix_expr = "\\(Prefix\\)" prefix_num["Operand-Size"] = "INAT_PFX_OPNDSZ" @@ -95,6 +97,7 @@ BEGIN { prefix_num["Address-Size"] = "INAT_PFX_ADDRSZ" prefix_num["VEX+1byte"] = "INAT_PFX_VEX2" prefix_num["VEX+2byte"] = "INAT_PFX_VEX3" + prefix_num["EVEX"] = "INAT_PFX_EVEX" clear_vars() } @@ -319,7 +322,9 @@ function convert_operands(count,opnd, i,j,imm,mod) flags = add_flags(flags, "INAT_MODRM") # check VEX codes - if (match(ext, vexonly_expr)) + if (match(ext, evexonly_expr)) + flags = add_flags(flags, "INAT_VEXOK | INAT_EVEXONLY") + else if (match(ext, vexonly_expr)) flags = add_flags(flags, "INAT_VEXOK | INAT_VEXONLY") else if (match(ext, vexok_expr) || match(opcode, vexok_opcode_expr)) flags = add_flags(flags, "INAT_VEXOK") diff --git a/tools/objtool/arch/x86/insn/inat.h b/tools/objtool/arch/x86/insn/inat.h index 611645e903a8..125ecd2a300d 100644 --- a/tools/objtool/arch/x86/insn/inat.h +++ b/tools/objtool/arch/x86/insn/inat.h @@ -48,6 +48,7 @@ /* AVX VEX prefixes */ #define INAT_PFX_VEX2 13 /* 2-bytes VEX prefix */ #define INAT_PFX_VEX3 14 /* 3-bytes VEX prefix */ +#define INAT_PFX_EVEX 15 /* EVEX prefix */ #define INAT_LSTPFX_MAX 3 #define INAT_LGCPFX_MAX 11 @@ -89,6 +90,7 @@ #define INAT_VARIANT (1 << (INAT_FLAG_OFFS + 4)) #define INAT_VEXOK (1 << (INAT_FLAG_OFFS + 5)) #define INAT_VEXONLY (1 << (INAT_FLAG_OFFS + 6)) +#define INAT_EVEXONLY (1 << (INAT_FLAG_OFFS + 7)) /* Attribute making macros for attribute tables */ #define INAT_MAKE_PREFIX(pfx) (pfx << INAT_PFX_OFFS) #define INAT_MAKE_ESCAPE(esc) (esc << INAT_ESC_OFFS) @@ -141,7 +143,13 @@ static inline int inat_last_prefix_id(insn_attr_t attr) static inline int inat_is_vex_prefix(insn_attr_t attr) { attr &= INAT_PFX_MASK; - return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3; + return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3 || + attr == INAT_PFX_EVEX; +} + +static inline int inat_is_evex_prefix(insn_attr_t attr) +{ + return (attr & INAT_PFX_MASK) == INAT_PFX_EVEX; } static inline int inat_is_vex3_prefix(insn_attr_t attr) @@ -216,6 +224,11 @@ static inline int inat_accept_vex(insn_attr_t attr) static inline int inat_must_vex(insn_attr_t attr) { - return attr & INAT_VEXONLY; + return attr & (INAT_VEXONLY | INAT_EVEXONLY); +} + +static inline int inat_must_evex(insn_attr_t attr) +{ + return attr & INAT_EVEXONLY; } #endif diff --git a/tools/objtool/arch/x86/insn/insn.c b/tools/objtool/arch/x86/insn/insn.c index 9f26eae6c9f0..ca983e2bea8b 100644 --- a/tools/objtool/arch/x86/insn/insn.c +++ b/tools/objtool/arch/x86/insn/insn.c @@ -155,14 +155,24 @@ found: /* * In 32-bits mode, if the [7:6] bits (mod bits of * ModRM) on the second byte are not 11b, it is - * LDS or LES. + * LDS or LES or BOUND. */ if (X86_MODRM_MOD(b2) != 3) goto vex_end; } insn->vex_prefix.bytes[0] = b; insn->vex_prefix.bytes[1] = b2; - if (inat_is_vex3_prefix(attr)) { + if (inat_is_evex_prefix(attr)) { + b2 = peek_nbyte_next(insn_byte_t, insn, 2); + insn->vex_prefix.bytes[2] = b2; + b2 = peek_nbyte_next(insn_byte_t, insn, 3); + insn->vex_prefix.bytes[3] = b2; + insn->vex_prefix.nbytes = 4; + insn->next_byte += 4; + if (insn->x86_64 && X86_VEX_W(b2)) + /* VEX.W overrides opnd_size */ + insn->opnd_bytes = 8; + } else if (inat_is_vex3_prefix(attr)) { b2 = peek_nbyte_next(insn_byte_t, insn, 2); insn->vex_prefix.bytes[2] = b2; insn->vex_prefix.nbytes = 3; @@ -221,7 +231,9 @@ void insn_get_opcode(struct insn *insn) m = insn_vex_m_bits(insn); p = insn_vex_p_bits(insn); insn->attr = inat_get_avx_attribute(op, m, p); - if (!inat_accept_vex(insn->attr) && !inat_is_group(insn->attr)) + if ((inat_must_evex(insn->attr) && !insn_is_evex(insn)) || + (!inat_accept_vex(insn->attr) && + !inat_is_group(insn->attr))) insn->attr = 0; /* This instruction is bad */ goto end; /* VEX has only 1 byte for opcode */ } diff --git a/tools/objtool/arch/x86/insn/insn.h b/tools/objtool/arch/x86/insn/insn.h index dd12da0f4593..e23578c7b1be 100644 --- a/tools/objtool/arch/x86/insn/insn.h +++ b/tools/objtool/arch/x86/insn/insn.h @@ -91,6 +91,7 @@ struct insn { #define X86_VEX_B(vex) ((vex) & 0x20) /* VEX3 Byte1 */ #define X86_VEX_L(vex) ((vex) & 0x04) /* VEX3 Byte2, VEX2 Byte1 */ /* VEX bit fields */ +#define X86_EVEX_M(vex) ((vex) & 0x03) /* EVEX Byte1 */ #define X86_VEX3_M(vex) ((vex) & 0x1f) /* VEX3 Byte1 */ #define X86_VEX2_M 1 /* VEX2.M always 1 */ #define X86_VEX_V(vex) (((vex) & 0x78) >> 3) /* VEX3 Byte2, VEX2 Byte1 */ @@ -133,6 +134,13 @@ static inline int insn_is_avx(struct insn *insn) return (insn->vex_prefix.value != 0); } +static inline int insn_is_evex(struct insn *insn) +{ + if (!insn->prefixes.got) + insn_get_prefixes(insn); + return (insn->vex_prefix.nbytes == 4); +} + /* Ensure this instruction is decoded completely */ static inline int insn_complete(struct insn *insn) { @@ -144,8 +152,10 @@ static inline insn_byte_t insn_vex_m_bits(struct insn *insn) { if (insn->vex_prefix.nbytes == 2) /* 2 bytes VEX */ return X86_VEX2_M; - else + else if (insn->vex_prefix.nbytes == 3) /* 3 bytes VEX */ return X86_VEX3_M(insn->vex_prefix.bytes[1]); + else /* EVEX */ + return X86_EVEX_M(insn->vex_prefix.bytes[1]); } static inline insn_byte_t insn_vex_p_bits(struct insn *insn) diff --git a/tools/objtool/arch/x86/insn/x86-opcode-map.txt b/tools/objtool/arch/x86/insn/x86-opcode-map.txt index d388de72eaca..767be7c76034 100644 --- a/tools/objtool/arch/x86/insn/x86-opcode-map.txt +++ b/tools/objtool/arch/x86/insn/x86-opcode-map.txt @@ -13,12 +13,17 @@ # opcode: escape # escaped-name # EndTable # +# mnemonics that begin with lowercase 'v' accept a VEX or EVEX prefix +# mnemonics that begin with lowercase 'k' accept a VEX prefix +# #<group maps> # GrpTable: GrpXXX # reg: mnemonic [operand1[,operand2...]] [(extra1)[,(extra2)...] [| 2nd-mnemonic ...] # EndTable # # AVX Superscripts +# (ev): this opcode requires EVEX prefix. +# (evo): this opcode is changed by EVEX prefix (EVEX opcode) # (v): this opcode requires VEX prefix. # (v1): this opcode only supports 128bit VEX. # @@ -137,7 +142,7 @@ AVXcode: # 0x60 - 0x6f 60: PUSHA/PUSHAD (i64) 61: POPA/POPAD (i64) -62: BOUND Gv,Ma (i64) +62: BOUND Gv,Ma (i64) | EVEX (Prefix) 63: ARPL Ew,Gw (i64) | MOVSXD Gv,Ev (o64) 64: SEG=FS (Prefix) 65: SEG=GS (Prefix) @@ -399,17 +404,17 @@ AVXcode: 1 3f: # 0x0f 0x40-0x4f 40: CMOVO Gv,Ev -41: CMOVNO Gv,Ev -42: CMOVB/C/NAE Gv,Ev +41: CMOVNO Gv,Ev | kandw/q Vk,Hk,Uk | kandb/d Vk,Hk,Uk (66) +42: CMOVB/C/NAE Gv,Ev | kandnw/q Vk,Hk,Uk | kandnb/d Vk,Hk,Uk (66) 43: CMOVAE/NB/NC Gv,Ev -44: CMOVE/Z Gv,Ev -45: CMOVNE/NZ Gv,Ev -46: CMOVBE/NA Gv,Ev -47: CMOVA/NBE Gv,Ev +44: CMOVE/Z Gv,Ev | knotw/q Vk,Uk | knotb/d Vk,Uk (66) +45: CMOVNE/NZ Gv,Ev | korw/q Vk,Hk,Uk | korb/d Vk,Hk,Uk (66) +46: CMOVBE/NA Gv,Ev | kxnorw/q Vk,Hk,Uk | kxnorb/d Vk,Hk,Uk (66) +47: CMOVA/NBE Gv,Ev | kxorw/q Vk,Hk,Uk | kxorb/d Vk,Hk,Uk (66) 48: CMOVS Gv,Ev 49: CMOVNS Gv,Ev -4a: CMOVP/PE Gv,Ev -4b: CMOVNP/PO Gv,Ev +4a: CMOVP/PE Gv,Ev | kaddw/q Vk,Hk,Uk | kaddb/d Vk,Hk,Uk (66) +4b: CMOVNP/PO Gv,Ev | kunpckbw Vk,Hk,Uk (66) | kunpckwd/dq Vk,Hk,Uk 4c: CMOVL/NGE Gv,Ev 4d: CMOVNL/GE Gv,Ev 4e: CMOVLE/NG Gv,Ev @@ -426,7 +431,7 @@ AVXcode: 1 58: vaddps Vps,Hps,Wps | vaddpd Vpd,Hpd,Wpd (66) | vaddss Vss,Hss,Wss (F3),(v1) | vaddsd Vsd,Hsd,Wsd (F2),(v1) 59: vmulps Vps,Hps,Wps | vmulpd Vpd,Hpd,Wpd (66) | vmulss Vss,Hss,Wss (F3),(v1) | vmulsd Vsd,Hsd,Wsd (F2),(v1) 5a: vcvtps2pd Vpd,Wps | vcvtpd2ps Vps,Wpd (66) | vcvtss2sd Vsd,Hx,Wss (F3),(v1) | vcvtsd2ss Vss,Hx,Wsd (F2),(v1) -5b: vcvtdq2ps Vps,Wdq | vcvtps2dq Vdq,Wps (66) | vcvttps2dq Vdq,Wps (F3) +5b: vcvtdq2ps Vps,Wdq | vcvtqq2ps Vps,Wqq (evo) | vcvtps2dq Vdq,Wps (66) | vcvttps2dq Vdq,Wps (F3) 5c: vsubps Vps,Hps,Wps | vsubpd Vpd,Hpd,Wpd (66) | vsubss Vss,Hss,Wss (F3),(v1) | vsubsd Vsd,Hsd,Wsd (F2),(v1) 5d: vminps Vps,Hps,Wps | vminpd Vpd,Hpd,Wpd (66) | vminss Vss,Hss,Wss (F3),(v1) | vminsd Vsd,Hsd,Wsd (F2),(v1) 5e: vdivps Vps,Hps,Wps | vdivpd Vpd,Hpd,Wpd (66) | vdivss Vss,Hss,Wss (F3),(v1) | vdivsd Vsd,Hsd,Wsd (F2),(v1) @@ -447,7 +452,7 @@ AVXcode: 1 6c: vpunpcklqdq Vx,Hx,Wx (66),(v1) 6d: vpunpckhqdq Vx,Hx,Wx (66),(v1) 6e: movd/q Pd,Ey | vmovd/q Vy,Ey (66),(v1) -6f: movq Pq,Qq | vmovdqa Vx,Wx (66) | vmovdqu Vx,Wx (F3) +6f: movq Pq,Qq | vmovdqa Vx,Wx (66) | vmovdqa32/64 Vx,Wx (66),(evo) | vmovdqu Vx,Wx (F3) | vmovdqu32/64 Vx,Wx (F3),(evo) | vmovdqu8/16 Vx,Wx (F2),(ev) # 0x0f 0x70-0x7f 70: pshufw Pq,Qq,Ib | vpshufd Vx,Wx,Ib (66),(v1) | vpshufhw Vx,Wx,Ib (F3),(v1) | vpshuflw Vx,Wx,Ib (F2),(v1) 71: Grp12 (1A) @@ -458,14 +463,14 @@ AVXcode: 1 76: pcmpeqd Pq,Qq | vpcmpeqd Vx,Hx,Wx (66),(v1) # Note: Remove (v), because vzeroall and vzeroupper becomes emms without VEX. 77: emms | vzeroupper | vzeroall -78: VMREAD Ey,Gy -79: VMWRITE Gy,Ey -7a: -7b: +78: VMREAD Ey,Gy | vcvttps2udq/pd2udq Vx,Wpd (evo) | vcvttsd2usi Gv,Wx (F2),(ev) | vcvttss2usi Gv,Wx (F3),(ev) | vcvttps2uqq/pd2uqq Vx,Wx (66),(ev) +79: VMWRITE Gy,Ey | vcvtps2udq/pd2udq Vx,Wpd (evo) | vcvtsd2usi Gv,Wx (F2),(ev) | vcvtss2usi Gv,Wx (F3),(ev) | vcvtps2uqq/pd2uqq Vx,Wx (66),(ev) +7a: vcvtudq2pd/uqq2pd Vpd,Wx (F3),(ev) | vcvtudq2ps/uqq2ps Vpd,Wx (F2),(ev) | vcvttps2qq/pd2qq Vx,Wx (66),(ev) +7b: vcvtusi2sd Vpd,Hpd,Ev (F2),(ev) | vcvtusi2ss Vps,Hps,Ev (F3),(ev) | vcvtps2qq/pd2qq Vx,Wx (66),(ev) 7c: vhaddpd Vpd,Hpd,Wpd (66) | vhaddps Vps,Hps,Wps (F2) 7d: vhsubpd Vpd,Hpd,Wpd (66) | vhsubps Vps,Hps,Wps (F2) 7e: movd/q Ey,Pd | vmovd/q Ey,Vy (66),(v1) | vmovq Vq,Wq (F3),(v1) -7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqu Wx,Vx (F3) +7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqa32/64 Wx,Vx (66),(evo) | vmovdqu Wx,Vx (F3) | vmovdqu32/64 Wx,Vx (F3),(evo) | vmovdqu8/16 Wx,Vx (F2),(ev) # 0x0f 0x80-0x8f # Note: "forced64" is Intel CPU behavior (see comment about CALL insn). 80: JO Jz (f64) @@ -485,16 +490,16 @@ AVXcode: 1 8e: JLE/JNG Jz (f64) 8f: JNLE/JG Jz (f64) # 0x0f 0x90-0x9f -90: SETO Eb -91: SETNO Eb -92: SETB/C/NAE Eb -93: SETAE/NB/NC Eb +90: SETO Eb | kmovw/q Vk,Wk | kmovb/d Vk,Wk (66) +91: SETNO Eb | kmovw/q Mv,Vk | kmovb/d Mv,Vk (66) +92: SETB/C/NAE Eb | kmovw Vk,Rv | kmovb Vk,Rv (66) | kmovq/d Vk,Rv (F2) +93: SETAE/NB/NC Eb | kmovw Gv,Uk | kmovb Gv,Uk (66) | kmovq/d Gv,Uk (F2) 94: SETE/Z Eb 95: SETNE/NZ Eb 96: SETBE/NA Eb 97: SETA/NBE Eb -98: SETS Eb -99: SETNS Eb +98: SETS Eb | kortestw/q Vk,Uk | kortestb/d Vk,Uk (66) +99: SETNS Eb | ktestw/q Vk,Uk | ktestb/d Vk,Uk (66) 9a: SETP/PE Eb 9b: SETNP/PO Eb 9c: SETL/NGE Eb @@ -564,11 +569,11 @@ d7: pmovmskb Gd,Nq | vpmovmskb Gd,Ux (66),(v1) d8: psubusb Pq,Qq | vpsubusb Vx,Hx,Wx (66),(v1) d9: psubusw Pq,Qq | vpsubusw Vx,Hx,Wx (66),(v1) da: pminub Pq,Qq | vpminub Vx,Hx,Wx (66),(v1) -db: pand Pq,Qq | vpand Vx,Hx,Wx (66),(v1) +db: pand Pq,Qq | vpand Vx,Hx,Wx (66),(v1) | vpandd/q Vx,Hx,Wx (66),(evo) dc: paddusb Pq,Qq | vpaddusb Vx,Hx,Wx (66),(v1) dd: paddusw Pq,Qq | vpaddusw Vx,Hx,Wx (66),(v1) de: pmaxub Pq,Qq | vpmaxub Vx,Hx,Wx (66),(v1) -df: pandn Pq,Qq | vpandn Vx,Hx,Wx (66),(v1) +df: pandn Pq,Qq | vpandn Vx,Hx,Wx (66),(v1) | vpandnd/q Vx,Hx,Wx (66),(evo) # 0x0f 0xe0-0xef e0: pavgb Pq,Qq | vpavgb Vx,Hx,Wx (66),(v1) e1: psraw Pq,Qq | vpsraw Vx,Hx,Wx (66),(v1) @@ -576,16 +581,16 @@ e2: psrad Pq,Qq | vpsrad Vx,Hx,Wx (66),(v1) e3: pavgw Pq,Qq | vpavgw Vx,Hx,Wx (66),(v1) e4: pmulhuw Pq,Qq | vpmulhuw Vx,Hx,Wx (66),(v1) e5: pmulhw Pq,Qq | vpmulhw Vx,Hx,Wx (66),(v1) -e6: vcvttpd2dq Vx,Wpd (66) | vcvtdq2pd Vx,Wdq (F3) | vcvtpd2dq Vx,Wpd (F2) +e6: vcvttpd2dq Vx,Wpd (66) | vcvtdq2pd Vx,Wdq (F3) | vcvtdq2pd/qq2pd Vx,Wdq (F3),(evo) | vcvtpd2dq Vx,Wpd (F2) e7: movntq Mq,Pq | vmovntdq Mx,Vx (66) e8: psubsb Pq,Qq | vpsubsb Vx,Hx,Wx (66),(v1) e9: psubsw Pq,Qq | vpsubsw Vx,Hx,Wx (66),(v1) ea: pminsw Pq,Qq | vpminsw Vx,Hx,Wx (66),(v1) -eb: por Pq,Qq | vpor Vx,Hx,Wx (66),(v1) +eb: por Pq,Qq | vpor Vx,Hx,Wx (66),(v1) | vpord/q Vx,Hx,Wx (66),(evo) ec: paddsb Pq,Qq | vpaddsb Vx,Hx,Wx (66),(v1) ed: paddsw Pq,Qq | vpaddsw Vx,Hx,Wx (66),(v1) ee: pmaxsw Pq,Qq | vpmaxsw Vx,Hx,Wx (66),(v1) -ef: pxor Pq,Qq | vpxor Vx,Hx,Wx (66),(v1) +ef: pxor Pq,Qq | vpxor Vx,Hx,Wx (66),(v1) | vpxord/q Vx,Hx,Wx (66),(evo) # 0x0f 0xf0-0xff f0: vlddqu Vx,Mx (F2) f1: psllw Pq,Qq | vpsllw Vx,Hx,Wx (66),(v1) @@ -626,81 +631,105 @@ AVXcode: 2 0e: vtestps Vx,Wx (66),(v) 0f: vtestpd Vx,Wx (66),(v) # 0x0f 0x38 0x10-0x1f -10: pblendvb Vdq,Wdq (66) -11: -12: -13: vcvtph2ps Vx,Wx,Ib (66),(v) -14: blendvps Vdq,Wdq (66) -15: blendvpd Vdq,Wdq (66) -16: vpermps Vqq,Hqq,Wqq (66),(v) +10: pblendvb Vdq,Wdq (66) | vpsrlvw Vx,Hx,Wx (66),(evo) | vpmovuswb Wx,Vx (F3),(ev) +11: vpmovusdb Wx,Vd (F3),(ev) | vpsravw Vx,Hx,Wx (66),(ev) +12: vpmovusqb Wx,Vq (F3),(ev) | vpsllvw Vx,Hx,Wx (66),(ev) +13: vcvtph2ps Vx,Wx (66),(v) | vpmovusdw Wx,Vd (F3),(ev) +14: blendvps Vdq,Wdq (66) | vpmovusqw Wx,Vq (F3),(ev) | vprorvd/q Vx,Hx,Wx (66),(evo) +15: blendvpd Vdq,Wdq (66) | vpmovusqd Wx,Vq (F3),(ev) | vprolvd/q Vx,Hx,Wx (66),(evo) +16: vpermps Vqq,Hqq,Wqq (66),(v) | vpermps/d Vqq,Hqq,Wqq (66),(evo) 17: vptest Vx,Wx (66) 18: vbroadcastss Vx,Wd (66),(v) -19: vbroadcastsd Vqq,Wq (66),(v) -1a: vbroadcastf128 Vqq,Mdq (66),(v) -1b: +19: vbroadcastsd Vqq,Wq (66),(v) | vbroadcastf32x2 Vqq,Wq (66),(evo) +1a: vbroadcastf128 Vqq,Mdq (66),(v) | vbroadcastf32x4/64x2 Vqq,Wq (66),(evo) +1b: vbroadcastf32x8/64x4 Vqq,Mdq (66),(ev) 1c: pabsb Pq,Qq | vpabsb Vx,Wx (66),(v1) 1d: pabsw Pq,Qq | vpabsw Vx,Wx (66),(v1) 1e: pabsd Pq,Qq | vpabsd Vx,Wx (66),(v1) -1f: +1f: vpabsq Vx,Wx (66),(ev) # 0x0f 0x38 0x20-0x2f -20: vpmovsxbw Vx,Ux/Mq (66),(v1) -21: vpmovsxbd Vx,Ux/Md (66),(v1) -22: vpmovsxbq Vx,Ux/Mw (66),(v1) -23: vpmovsxwd Vx,Ux/Mq (66),(v1) -24: vpmovsxwq Vx,Ux/Md (66),(v1) -25: vpmovsxdq Vx,Ux/Mq (66),(v1) -26: -27: -28: vpmuldq Vx,Hx,Wx (66),(v1) -29: vpcmpeqq Vx,Hx,Wx (66),(v1) -2a: vmovntdqa Vx,Mx (66),(v1) +20: vpmovsxbw Vx,Ux/Mq (66),(v1) | vpmovswb Wx,Vx (F3),(ev) +21: vpmovsxbd Vx,Ux/Md (66),(v1) | vpmovsdb Wx,Vd (F3),(ev) +22: vpmovsxbq Vx,Ux/Mw (66),(v1) | vpmovsqb Wx,Vq (F3),(ev) +23: vpmovsxwd Vx,Ux/Mq (66),(v1) | vpmovsdw Wx,Vd (F3),(ev) +24: vpmovsxwq Vx,Ux/Md (66),(v1) | vpmovsqw Wx,Vq (F3),(ev) +25: vpmovsxdq Vx,Ux/Mq (66),(v1) | vpmovsqd Wx,Vq (F3),(ev) +26: vptestmb/w Vk,Hx,Wx (66),(ev) | vptestnmb/w Vk,Hx,Wx (F3),(ev) +27: vptestmd/q Vk,Hx,Wx (66),(ev) | vptestnmd/q Vk,Hx,Wx (F3),(ev) +28: vpmuldq Vx,Hx,Wx (66),(v1) | vpmovm2b/w Vx,Uk (F3),(ev) +29: vpcmpeqq Vx,Hx,Wx (66),(v1) | vpmovb2m/w2m Vk,Ux (F3),(ev) +2a: vmovntdqa Vx,Mx (66),(v1) | vpbroadcastmb2q Vx,Uk (F3),(ev) 2b: vpackusdw Vx,Hx,Wx (66),(v1) -2c: vmaskmovps Vx,Hx,Mx (66),(v) -2d: vmaskmovpd Vx,Hx,Mx (66),(v) +2c: vmaskmovps Vx,Hx,Mx (66),(v) | vscalefps/d Vx,Hx,Wx (66),(evo) +2d: vmaskmovpd Vx,Hx,Mx (66),(v) | vscalefss/d Vx,Hx,Wx (66),(evo) 2e: vmaskmovps Mx,Hx,Vx (66),(v) 2f: vmaskmovpd Mx,Hx,Vx (66),(v) # 0x0f 0x38 0x30-0x3f -30: vpmovzxbw Vx,Ux/Mq (66),(v1) -31: vpmovzxbd Vx,Ux/Md (66),(v1) -32: vpmovzxbq Vx,Ux/Mw (66),(v1) -33: vpmovzxwd Vx,Ux/Mq (66),(v1) -34: vpmovzxwq Vx,Ux/Md (66),(v1) -35: vpmovzxdq Vx,Ux/Mq (66),(v1) -36: vpermd Vqq,Hqq,Wqq (66),(v) +30: vpmovzxbw Vx,Ux/Mq (66),(v1) | vpmovwb Wx,Vx (F3),(ev) +31: vpmovzxbd Vx,Ux/Md (66),(v1) | vpmovdb Wx,Vd (F3),(ev) +32: vpmovzxbq Vx,Ux/Mw (66),(v1) | vpmovqb Wx,Vq (F3),(ev) +33: vpmovzxwd Vx,Ux/Mq (66),(v1) | vpmovdw Wx,Vd (F3),(ev) +34: vpmovzxwq Vx,Ux/Md (66),(v1) | vpmovqw Wx,Vq (F3),(ev) +35: vpmovzxdq Vx,Ux/Mq (66),(v1) | vpmovqd Wx,Vq (F3),(ev) +36: vpermd Vqq,Hqq,Wqq (66),(v) | vpermd/q Vqq,Hqq,Wqq (66),(evo) 37: vpcmpgtq Vx,Hx,Wx (66),(v1) -38: vpminsb Vx,Hx,Wx (66),(v1) -39: vpminsd Vx,Hx,Wx (66),(v1) -3a: vpminuw Vx,Hx,Wx (66),(v1) -3b: vpminud Vx,Hx,Wx (66),(v1) +38: vpminsb Vx,Hx,Wx (66),(v1) | vpmovm2d/q Vx,Uk (F3),(ev) +39: vpminsd Vx,Hx,Wx (66),(v1) | vpminsd/q Vx,Hx,Wx (66),(evo) | vpmovd2m/q2m Vk,Ux (F3),(ev) +3a: vpminuw Vx,Hx,Wx (66),(v1) | vpbroadcastmw2d Vx,Uk (F3),(ev) +3b: vpminud Vx,Hx,Wx (66),(v1) | vpminud/q Vx,Hx,Wx (66),(evo) 3c: vpmaxsb Vx,Hx,Wx (66),(v1) -3d: vpmaxsd Vx,Hx,Wx (66),(v1) +3d: vpmaxsd Vx,Hx,Wx (66),(v1) | vpmaxsd/q Vx,Hx,Wx (66),(evo) 3e: vpmaxuw Vx,Hx,Wx (66),(v1) -3f: vpmaxud Vx,Hx,Wx (66),(v1) +3f: vpmaxud Vx,Hx,Wx (66),(v1) | vpmaxud/q Vx,Hx,Wx (66),(evo) # 0x0f 0x38 0x40-0x8f -40: vpmulld Vx,Hx,Wx (66),(v1) +40: vpmulld Vx,Hx,Wx (66),(v1) | vpmulld/q Vx,Hx,Wx (66),(evo) 41: vphminposuw Vdq,Wdq (66),(v1) -42: -43: -44: +42: vgetexpps/d Vx,Wx (66),(ev) +43: vgetexpss/d Vx,Hx,Wx (66),(ev) +44: vplzcntd/q Vx,Wx (66),(ev) 45: vpsrlvd/q Vx,Hx,Wx (66),(v) -46: vpsravd Vx,Hx,Wx (66),(v) +46: vpsravd Vx,Hx,Wx (66),(v) | vpsravd/q Vx,Hx,Wx (66),(evo) 47: vpsllvd/q Vx,Hx,Wx (66),(v) -# Skip 0x48-0x57 +# Skip 0x48-0x4b +4c: vrcp14ps/d Vpd,Wpd (66),(ev) +4d: vrcp14ss/d Vsd,Hpd,Wsd (66),(ev) +4e: vrsqrt14ps/d Vpd,Wpd (66),(ev) +4f: vrsqrt14ss/d Vsd,Hsd,Wsd (66),(ev) +# Skip 0x50-0x57 58: vpbroadcastd Vx,Wx (66),(v) -59: vpbroadcastq Vx,Wx (66),(v) -5a: vbroadcasti128 Vqq,Mdq (66),(v) -# Skip 0x5b-0x77 +59: vpbroadcastq Vx,Wx (66),(v) | vbroadcasti32x2 Vx,Wx (66),(evo) +5a: vbroadcasti128 Vqq,Mdq (66),(v) | vbroadcasti32x4/64x2 Vx,Wx (66),(evo) +5b: vbroadcasti32x8/64x4 Vqq,Mdq (66),(ev) +# Skip 0x5c-0x63 +64: vpblendmd/q Vx,Hx,Wx (66),(ev) +65: vblendmps/d Vx,Hx,Wx (66),(ev) +66: vpblendmb/w Vx,Hx,Wx (66),(ev) +# Skip 0x67-0x74 +75: vpermi2b/w Vx,Hx,Wx (66),(ev) +76: vpermi2d/q Vx,Hx,Wx (66),(ev) +77: vpermi2ps/d Vx,Hx,Wx (66),(ev) 78: vpbroadcastb Vx,Wx (66),(v) 79: vpbroadcastw Vx,Wx (66),(v) -# Skip 0x7a-0x7f +7a: vpbroadcastb Vx,Rv (66),(ev) +7b: vpbroadcastw Vx,Rv (66),(ev) +7c: vpbroadcastd/q Vx,Rv (66),(ev) +7d: vpermt2b/w Vx,Hx,Wx (66),(ev) +7e: vpermt2d/q Vx,Hx,Wx (66),(ev) +7f: vpermt2ps/d Vx,Hx,Wx (66),(ev) 80: INVEPT Gy,Mdq (66) 81: INVPID Gy,Mdq (66) 82: INVPCID Gy,Mdq (66) +83: vpmultishiftqb Vx,Hx,Wx (66),(ev) +88: vexpandps/d Vpd,Wpd (66),(ev) +89: vpexpandd/q Vx,Wx (66),(ev) +8a: vcompressps/d Wx,Vx (66),(ev) +8b: vpcompressd/q Wx,Vx (66),(ev) 8c: vpmaskmovd/q Vx,Hx,Mx (66),(v) +8d: vpermb/w Vx,Hx,Wx (66),(ev) 8e: vpmaskmovd/q Mx,Vx,Hx (66),(v) # 0x0f 0x38 0x90-0xbf (FMA) -90: vgatherdd/q Vx,Hx,Wx (66),(v) -91: vgatherqd/q Vx,Hx,Wx (66),(v) +90: vgatherdd/q Vx,Hx,Wx (66),(v) | vpgatherdd/q Vx,Wx (66),(evo) +91: vgatherqd/q Vx,Hx,Wx (66),(v) | vpgatherqd/q Vx,Wx (66),(evo) 92: vgatherdps/d Vx,Hx,Wx (66),(v) 93: vgatherqps/d Vx,Hx,Wx (66),(v) 94: @@ -715,6 +744,10 @@ AVXcode: 2 9d: vfnmadd132ss/d Vx,Hx,Wx (66),(v),(v1) 9e: vfnmsub132ps/d Vx,Hx,Wx (66),(v) 9f: vfnmsub132ss/d Vx,Hx,Wx (66),(v),(v1) +a0: vpscatterdd/q Wx,Vx (66),(ev) +a1: vpscatterqd/q Wx,Vx (66),(ev) +a2: vscatterdps/d Wx,Vx (66),(ev) +a3: vscatterqps/d Wx,Vx (66),(ev) a6: vfmaddsub213ps/d Vx,Hx,Wx (66),(v) a7: vfmsubadd213ps/d Vx,Hx,Wx (66),(v) a8: vfmadd213ps/d Vx,Hx,Wx (66),(v) @@ -725,6 +758,8 @@ ac: vfnmadd213ps/d Vx,Hx,Wx (66),(v) ad: vfnmadd213ss/d Vx,Hx,Wx (66),(v),(v1) ae: vfnmsub213ps/d Vx,Hx,Wx (66),(v) af: vfnmsub213ss/d Vx,Hx,Wx (66),(v),(v1) +b4: vpmadd52luq Vx,Hx,Wx (66),(ev) +b5: vpmadd52huq Vx,Hx,Wx (66),(ev) b6: vfmaddsub231ps/d Vx,Hx,Wx (66),(v) b7: vfmsubadd231ps/d Vx,Hx,Wx (66),(v) b8: vfmadd231ps/d Vx,Hx,Wx (66),(v) @@ -736,12 +771,15 @@ bd: vfnmadd231ss/d Vx,Hx,Wx (66),(v),(v1) be: vfnmsub231ps/d Vx,Hx,Wx (66),(v) bf: vfnmsub231ss/d Vx,Hx,Wx (66),(v),(v1) # 0x0f 0x38 0xc0-0xff -c8: sha1nexte Vdq,Wdq +c4: vpconflictd/q Vx,Wx (66),(ev) +c6: Grp18 (1A) +c7: Grp19 (1A) +c8: sha1nexte Vdq,Wdq | vexp2ps/d Vx,Wx (66),(ev) c9: sha1msg1 Vdq,Wdq -ca: sha1msg2 Vdq,Wdq -cb: sha256rnds2 Vdq,Wdq -cc: sha256msg1 Vdq,Wdq -cd: sha256msg2 Vdq,Wdq +ca: sha1msg2 Vdq,Wdq | vrcp28ps/d Vx,Wx (66),(ev) +cb: sha256rnds2 Vdq,Wdq | vrcp28ss/d Vx,Hx,Wx (66),(ev) +cc: sha256msg1 Vdq,Wdq | vrsqrt28ps/d Vx,Wx (66),(ev) +cd: sha256msg2 Vdq,Wdq | vrsqrt28ss/d Vx,Hx,Wx (66),(ev) db: VAESIMC Vdq,Wdq (66),(v1) dc: VAESENC Vdq,Hdq,Wdq (66),(v1) dd: VAESENCLAST Vdq,Hdq,Wdq (66),(v1) @@ -763,15 +801,15 @@ AVXcode: 3 00: vpermq Vqq,Wqq,Ib (66),(v) 01: vpermpd Vqq,Wqq,Ib (66),(v) 02: vpblendd Vx,Hx,Wx,Ib (66),(v) -03: +03: valignd/q Vx,Hx,Wx,Ib (66),(ev) 04: vpermilps Vx,Wx,Ib (66),(v) 05: vpermilpd Vx,Wx,Ib (66),(v) 06: vperm2f128 Vqq,Hqq,Wqq,Ib (66),(v) 07: -08: vroundps Vx,Wx,Ib (66) -09: vroundpd Vx,Wx,Ib (66) -0a: vroundss Vss,Wss,Ib (66),(v1) -0b: vroundsd Vsd,Wsd,Ib (66),(v1) +08: vroundps Vx,Wx,Ib (66) | vrndscaleps Vx,Wx,Ib (66),(evo) +09: vroundpd Vx,Wx,Ib (66) | vrndscalepd Vx,Wx,Ib (66),(evo) +0a: vroundss Vss,Wss,Ib (66),(v1) | vrndscaless Vx,Hx,Wx,Ib (66),(evo) +0b: vroundsd Vsd,Wsd,Ib (66),(v1) | vrndscalesd Vx,Hx,Wx,Ib (66),(evo) 0c: vblendps Vx,Hx,Wx,Ib (66) 0d: vblendpd Vx,Hx,Wx,Ib (66) 0e: vpblendw Vx,Hx,Wx,Ib (66),(v1) @@ -780,26 +818,51 @@ AVXcode: 3 15: vpextrw Rd/Mw,Vdq,Ib (66),(v1) 16: vpextrd/q Ey,Vdq,Ib (66),(v1) 17: vextractps Ed,Vdq,Ib (66),(v1) -18: vinsertf128 Vqq,Hqq,Wqq,Ib (66),(v) -19: vextractf128 Wdq,Vqq,Ib (66),(v) +18: vinsertf128 Vqq,Hqq,Wqq,Ib (66),(v) | vinsertf32x4/64x2 Vqq,Hqq,Wqq,Ib (66),(evo) +19: vextractf128 Wdq,Vqq,Ib (66),(v) | vextractf32x4/64x2 Wdq,Vqq,Ib (66),(evo) +1a: vinsertf32x8/64x4 Vqq,Hqq,Wqq,Ib (66),(ev) +1b: vextractf32x8/64x4 Wdq,Vqq,Ib (66),(ev) 1d: vcvtps2ph Wx,Vx,Ib (66),(v) +1e: vpcmpud/q Vk,Hd,Wd,Ib (66),(ev) +1f: vpcmpd/q Vk,Hd,Wd,Ib (66),(ev) 20: vpinsrb Vdq,Hdq,Ry/Mb,Ib (66),(v1) 21: vinsertps Vdq,Hdq,Udq/Md,Ib (66),(v1) 22: vpinsrd/q Vdq,Hdq,Ey,Ib (66),(v1) -38: vinserti128 Vqq,Hqq,Wqq,Ib (66),(v) -39: vextracti128 Wdq,Vqq,Ib (66),(v) +23: vshuff32x4/64x2 Vx,Hx,Wx,Ib (66),(ev) +25: vpternlogd/q Vx,Hx,Wx,Ib (66),(ev) +26: vgetmantps/d Vx,Wx,Ib (66),(ev) +27: vgetmantss/d Vx,Hx,Wx,Ib (66),(ev) +30: kshiftrb/w Vk,Uk,Ib (66),(v) +31: kshiftrd/q Vk,Uk,Ib (66),(v) +32: kshiftlb/w Vk,Uk,Ib (66),(v) +33: kshiftld/q Vk,Uk,Ib (66),(v) +38: vinserti128 Vqq,Hqq,Wqq,Ib (66),(v) | vinserti32x4/64x2 Vqq,Hqq,Wqq,Ib (66),(evo) +39: vextracti128 Wdq,Vqq,Ib (66),(v) | vextracti32x4/64x2 Wdq,Vqq,Ib (66),(evo) +3a: vinserti32x8/64x4 Vqq,Hqq,Wqq,Ib (66),(ev) +3b: vextracti32x8/64x4 Wdq,Vqq,Ib (66),(ev) +3e: vpcmpub/w Vk,Hk,Wx,Ib (66),(ev) +3f: vpcmpb/w Vk,Hk,Wx,Ib (66),(ev) 40: vdpps Vx,Hx,Wx,Ib (66) 41: vdppd Vdq,Hdq,Wdq,Ib (66),(v1) -42: vmpsadbw Vx,Hx,Wx,Ib (66),(v1) +42: vmpsadbw Vx,Hx,Wx,Ib (66),(v1) | vdbpsadbw Vx,Hx,Wx,Ib (66),(evo) +43: vshufi32x4/64x2 Vx,Hx,Wx,Ib (66),(ev) 44: vpclmulqdq Vdq,Hdq,Wdq,Ib (66),(v1) 46: vperm2i128 Vqq,Hqq,Wqq,Ib (66),(v) 4a: vblendvps Vx,Hx,Wx,Lx (66),(v) 4b: vblendvpd Vx,Hx,Wx,Lx (66),(v) 4c: vpblendvb Vx,Hx,Wx,Lx (66),(v1) +50: vrangeps/d Vx,Hx,Wx,Ib (66),(ev) +51: vrangess/d Vx,Hx,Wx,Ib (66),(ev) +54: vfixupimmps/d Vx,Hx,Wx,Ib (66),(ev) +55: vfixupimmss/d Vx,Hx,Wx,Ib (66),(ev) +56: vreduceps/d Vx,Wx,Ib (66),(ev) +57: vreducess/d Vx,Hx,Wx,Ib (66),(ev) 60: vpcmpestrm Vdq,Wdq,Ib (66),(v1) 61: vpcmpestri Vdq,Wdq,Ib (66),(v1) 62: vpcmpistrm Vdq,Wdq,Ib (66),(v1) 63: vpcmpistri Vdq,Wdq,Ib (66),(v1) +66: vfpclassps/d Vk,Wx,Ib (66),(ev) +67: vfpclassss/d Vk,Wx,Ib (66),(ev) cc: sha1rnds4 Vdq,Wdq,Ib df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1) f0: RORX Gy,Ey,Ib (F2),(v) @@ -927,8 +990,10 @@ GrpTable: Grp12 EndTable GrpTable: Grp13 +0: vprord/q Hx,Wx,Ib (66),(ev) +1: vprold/q Hx,Wx,Ib (66),(ev) 2: psrld Nq,Ib (11B) | vpsrld Hx,Ux,Ib (66),(11B),(v1) -4: psrad Nq,Ib (11B) | vpsrad Hx,Ux,Ib (66),(11B),(v1) +4: psrad Nq,Ib (11B) | vpsrad Hx,Ux,Ib (66),(11B),(v1) | vpsrad/q Hx,Ux,Ib (66),(evo) 6: pslld Nq,Ib (11B) | vpslld Hx,Ux,Ib (66),(11B),(v1) EndTable @@ -947,7 +1012,7 @@ GrpTable: Grp15 4: XSAVE 5: XRSTOR | lfence (11B) 6: XSAVEOPT | clwb (66) | mfence (11B) -7: clflush | clflushopt (66) | sfence (11B) | pcommit (66),(11B) +7: clflush | clflushopt (66) | sfence (11B) EndTable GrpTable: Grp16 @@ -963,6 +1028,20 @@ GrpTable: Grp17 3: BLSI By,Ey (v) EndTable +GrpTable: Grp18 +1: vgatherpf0dps/d Wx (66),(ev) +2: vgatherpf1dps/d Wx (66),(ev) +5: vscatterpf0dps/d Wx (66),(ev) +6: vscatterpf1dps/d Wx (66),(ev) +EndTable + +GrpTable: Grp19 +1: vgatherpf0qps/d Wx (66),(ev) +2: vgatherpf1qps/d Wx (66),(ev) +5: vscatterpf0qps/d Wx (66),(ev) +6: vscatterpf1qps/d Wx (66),(ev) +EndTable + # AMD's Prefetch Group GrpTable: GrpP 0: PREFETCH diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c index 17fa7fc34fdf..bd09d0effef8 100644 --- a/tools/objtool/builtin-check.c +++ b/tools/objtool/builtin-check.c @@ -107,6 +107,12 @@ static struct instruction *next_insn_same_sec(struct objtool_file *file, 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)) @@ -664,65 +670,95 @@ static int add_switch_table(struct objtool_file *file, struct symbol *func, return 0; } -static int add_func_switch_tables(struct objtool_file *file, - struct symbol *func) +/* + * 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 instruction *insn, *prev_jump; - struct rela *text_rela, *rodata_rela, *prev_rela = NULL; - int ret; + struct rela *text_rela, *rodata_rela; - prev_jump = NULL; + 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; - func_for_each_insn(file, func, insn) { - if (insn->type != INSN_JUMP_DYNAMIC) - continue; + /* 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_UNCONDITIONAL || + insn->type == INSN_JUMP_DYNAMIC) + break; text_rela = find_rela_by_dest_range(insn->sec, insn->offset, insn->len); - if (!text_rela || text_rela->sym != file->rodata->sym) - continue; + if (text_rela && text_rela->sym == file->rodata->sym) + return find_rela_by_dest(file->rodata, + text_rela->addend); + } - /* common case: jmpq *[addr](,%rax,8) */ - rodata_rela = find_rela_by_dest(file->rodata, - text_rela->addend); + return NULL; +} - /* - * rare case: jmpq *[addr](%rip) - * - * This check is for 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. - * - * kbuild reports: - * - https://lkml.kernel.org/r/201603231906.LWcVUpxm%25fengguang.wu@intel.com - * - https://lkml.kernel.org/r/201603271114.K9i45biy%25fengguang.wu@intel.com - * - https://lkml.kernel.org/r/201603291058.zuJ6ben1%25fengguang.wu@intel.com - * - * gcc bug: - * - https://gcc.gnu.org/bugzilla/show_bug.cgi?id=70604 - */ - if (!rodata_rela) { - rodata_rela = find_rela_by_dest(file->rodata, - text_rela->addend + 4); - if (rodata_rela) - file->ignore_unreachables = true; - } +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; - if (!rodata_rela) + func_for_each_insn(file, func, insn) { + if (insn->type != INSN_JUMP_DYNAMIC) + continue; + + rela = find_switch_table(file, func, insn); + if (!rela) continue; /* @@ -732,13 +768,13 @@ static int add_func_switch_tables(struct objtool_file *file, */ if (prev_jump) { ret = add_switch_table(file, func, prev_jump, prev_rela, - rodata_rela); + rela); if (ret) return ret; } prev_jump = insn; - prev_rela = rodata_rela; + prev_rela = rela; } if (prev_jump) { diff --git a/tools/perf/arch/s390/util/Build b/tools/perf/arch/s390/util/Build index 8a61372bb47a..5bd7b9260cc0 100644 --- a/tools/perf/arch/s390/util/Build +++ b/tools/perf/arch/s390/util/Build @@ -2,3 +2,5 @@ libperf-y += header.o libperf-y += kvm-stat.o libperf-$(CONFIG_DWARF) += dwarf-regs.o + +libperf-y += machine.o diff --git a/tools/perf/arch/s390/util/machine.c b/tools/perf/arch/s390/util/machine.c new file mode 100644 index 000000000000..b9a95a1a8e69 --- /dev/null +++ b/tools/perf/arch/s390/util/machine.c @@ -0,0 +1,19 @@ +#include <unistd.h> +#include <stdio.h> +#include <string.h> +#include "util.h" +#include "machine.h" +#include "api/fs/fs.h" + +int arch__fix_module_text_start(u64 *start, const char *name) +{ + char path[PATH_MAX]; + + snprintf(path, PATH_MAX, "module/%.*s/sections/.text", + (int)strlen(name) - 2, name + 1); + + if (sysfs__read_ull(path, (unsigned long long *)start) < 0) + return -1; + + return 0; +} 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 3918dd52e903..0f196eec9f48 100644 --- a/tools/perf/arch/x86/tests/insn-x86-dat-32.c +++ b/tools/perf/arch/x86/tests/insn-x86-dat-32.c @@ -1664,5 +1664,3 @@ "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)",}, -{{0x66, 0x0f, 0xae, 0xf8, }, 4, 0, "", "", -"66 0f ae f8 \tpcommit ",}, 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 9c8c61e06d5a..af25bc8240d0 100644 --- a/tools/perf/arch/x86/tests/insn-x86-dat-64.c +++ b/tools/perf/arch/x86/tests/insn-x86-dat-64.c @@ -1696,5 +1696,3 @@ "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)",}, -{{0x66, 0x0f, 0xae, 0xf8, }, 4, 0, "", "", -"66 0f ae f8 \tpcommit ",}, 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 76e0ec379c8b..979487dae8d4 100644 --- a/tools/perf/arch/x86/tests/insn-x86-dat-src.c +++ b/tools/perf/arch/x86/tests/insn-x86-dat-src.c @@ -2655,10 +2655,6 @@ int main(void) #endif /* #ifndef __x86_64__ */ - /* pcommit */ - - asm volatile("pcommit"); - /* Following line is a marker for the awk script - do not change */ asm volatile("rdtsc"); /* Stop here */ diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index b1d491c2e704..fdde1bd3e306 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -608,6 +608,7 @@ static const struct { const char *compact; } gfp_compact_table[] = { { "GFP_TRANSHUGE", "THP" }, + { "GFP_TRANSHUGE_LIGHT", "THL" }, { "GFP_HIGHUSER_MOVABLE", "HUM" }, { "GFP_HIGHUSER", "HU" }, { "GFP_USER", "U" }, diff --git a/tools/perf/scripts/python/netdev-times.py b/tools/perf/scripts/python/netdev-times.py index 4d21ef2d601d..4c6f09ac7d12 100644 --- a/tools/perf/scripts/python/netdev-times.py +++ b/tools/perf/scripts/python/netdev-times.py @@ -252,9 +252,10 @@ def irq__irq_handler_exit(name, context, cpu, sec, nsec, pid, comm, callchain, i event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, irq, ret) all_event_list.append(event_info) -def napi__napi_poll(name, context, cpu, sec, nsec, pid, comm, callchain, napi, dev_name): +def napi__napi_poll(name, context, cpu, sec, nsec, pid, comm, callchain, napi, + dev_name, work=None, budget=None): event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, - napi, dev_name) + napi, dev_name, work, budget) all_event_list.append(event_info) def net__netif_receive_skb(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr, @@ -354,11 +355,13 @@ def handle_irq_softirq_exit(event_info): receive_hunk_list.append(rec_data) def handle_napi_poll(event_info): - (name, context, cpu, time, pid, comm, napi, dev_name) = event_info + (name, context, cpu, time, pid, comm, napi, dev_name, + work, budget) = event_info if cpu in net_rx_dic.keys(): event_list = net_rx_dic[cpu]['event_list'] rec_data = {'event_name':'napi_poll', - 'dev':dev_name, 'event_t':time} + 'dev':dev_name, 'event_t':time, + 'work':work, 'budget':budget} event_list.append(rec_data) def handle_netif_rx(event_info): diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 2fa7d8b69873..91c5f6e1af59 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -70,7 +70,6 @@ libperf-y += stat.o libperf-y += stat-shadow.o libperf-y += record.o libperf-y += srcline.o -libperf-y += str_error_r.o libperf-y += data.o libperf-y += tsc.o libperf-y += cloexec.o @@ -176,10 +175,6 @@ $(OUTPUT)util/libstring.o: ../lib/string.c FORCE $(call rule_mkdir) $(call if_changed_dep,cc_o_c) -$(OUTPUT)util/str_error_r.o: ../lib/str_error_r.c FORCE - $(call rule_mkdir) - $(call if_changed_dep,cc_o_c) - $(OUTPUT)util/hweight.o: ../lib/hweight.c FORCE $(call rule_mkdir) $(call if_changed_dep,cc_o_c) 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 ec378cd7b71e..767be7c76034 100644 --- a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt +++ b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt @@ -1012,7 +1012,7 @@ GrpTable: Grp15 4: XSAVE 5: XRSTOR | lfence (11B) 6: XSAVEOPT | clwb (66) | mfence (11B) -7: clflush | clflushopt (66) | sfence (11B) | pcommit (66),(11B) +7: clflush | clflushopt (66) | sfence (11B) EndTable GrpTable: Grp16 diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index bc2cdbd09a25..cb6388dbdd98 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1093,12 +1093,20 @@ static int machine__set_modules_path(struct machine *machine) return map_groups__set_modules_path_dir(&machine->kmaps, modules_path, 0); } +int __weak arch__fix_module_text_start(u64 *start __maybe_unused, + const char *name __maybe_unused) +{ + return 0; +} static int machine__create_module(void *arg, const char *name, u64 start) { struct machine *machine = arg; struct map *map; + if (arch__fix_module_text_start(&start, name) < 0) + return -1; + map = machine__findnew_module_map(machine, start, name); if (map == NULL) return -1; diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index 41ac9cfd416b..20739f746bc4 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -216,6 +216,7 @@ struct symbol *machine__find_kernel_function_by_name(struct machine *machine, struct map *machine__findnew_module_map(struct machine *machine, u64 start, const char *filename); +int arch__fix_module_text_start(u64 *start, const char *name); int __machine__load_kallsyms(struct machine *machine, const char *filename, enum map_type type, bool no_kcore, symbol_filter_t filter); diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index 5065ec98049c..b7d4f4aeee61 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -13,7 +13,6 @@ util/cpumap.c ../lib/bitmap.c ../lib/find_bit.c ../lib/hweight.c -../lib/str_error_r.c ../lib/vsprintf.c util/thread_map.c util/util.c diff --git a/tools/power/acpi/Makefile.config b/tools/power/acpi/Makefile.config index 552af68d5414..a538ff44b108 100644 --- a/tools/power/acpi/Makefile.config +++ b/tools/power/acpi/Makefile.config @@ -54,9 +54,10 @@ INSTALL_SCRIPT = ${INSTALL_PROGRAM} # to something more interesting, like "arm-linux-". If you want # to compile vs uClibc, that can be done here as well. CROSS = #/usr/i386-linux-uclibc/usr/bin/i386-uclibc- -CC = $(CROSS)gcc -LD = $(CROSS)gcc -STRIP = $(CROSS)strip +CROSS_COMPILE ?= $(CROSS) +CC = $(CROSS_COMPILE)gcc +LD = $(CROSS_COMPILE)gcc +STRIP = $(CROSS_COMPILE)strip HOSTCC = gcc # check if compiler option is supported diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile index e367b1a85d70..8561e7ddca59 100644 --- a/tools/power/x86/turbostat/Makefile +++ b/tools/power/x86/turbostat/Makefile @@ -1,7 +1,7 @@ CC = $(CROSS_COMPILE)gcc BUILD_OUTPUT := $(CURDIR) -PREFIX := /usr -DESTDIR := +PREFIX ?= /usr +DESTDIR ?= ifeq ("$(origin O)", "command line") BUILD_OUTPUT := $(O) diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8 index 89a55d5e32f3..492e84fbebfa 100644 --- a/tools/power/x86/turbostat/turbostat.8 +++ b/tools/power/x86/turbostat/turbostat.8 @@ -123,7 +123,7 @@ cpu0: MSR_NHM_PLATFORM_INFO: 0x80838f3012300 35 * 100 = 3500 MHz TSC frequency cpu0: MSR_IA32_POWER_CTL: 0x0004005d (C1E auto-promotion: DISabled) cpu0: MSR_NHM_SNB_PKG_CST_CFG_CTL: 0x1e000400 (UNdemote-C3, UNdemote-C1, demote-C3, demote-C1, UNlocked: pkg-cstate-limit=0: pc0) -cpu0: MSR_NHM_TURBO_RATIO_LIMIT: 0x25262727 +cpu0: MSR_TURBO_RATIO_LIMIT: 0x25262727 37 * 100 = 3700 MHz max turbo 4 active cores 38 * 100 = 3800 MHz max turbo 3 active cores 39 * 100 = 3900 MHz max turbo 2 active cores diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index acbf7ff2ee6e..3e199b508a96 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -1480,7 +1480,7 @@ dump_knl_turbo_ratio_limits(void) unsigned int cores[buckets_no]; unsigned int ratio[buckets_no]; - get_msr(base_cpu, MSR_NHM_TURBO_RATIO_LIMIT, &msr); + get_msr(base_cpu, MSR_TURBO_RATIO_LIMIT, &msr); fprintf(outf, "cpu%d: MSR_TURBO_RATIO_LIMIT: 0x%08llx\n", base_cpu, msr); diff --git a/tools/testing/nvdimm/Kbuild b/tools/testing/nvdimm/Kbuild index 785985677159..ad6dd0543019 100644 --- a/tools/testing/nvdimm/Kbuild +++ b/tools/testing/nvdimm/Kbuild @@ -11,12 +11,14 @@ ldflags-y += --wrap=__devm_release_region ldflags-y += --wrap=__request_region ldflags-y += --wrap=__release_region ldflags-y += --wrap=devm_memremap_pages -ldflags-y += --wrap=phys_to_pfn_t +ldflags-y += --wrap=insert_resource +ldflags-y += --wrap=remove_resource DRIVERS := ../../../drivers NVDIMM_SRC := $(DRIVERS)/nvdimm -ACPI_SRC := $(DRIVERS)/acpi +ACPI_SRC := $(DRIVERS)/acpi/nfit DAX_SRC := $(DRIVERS)/dax +ccflags-y := -I$(src)/$(NVDIMM_SRC)/ obj-$(CONFIG_LIBNVDIMM) += libnvdimm.o obj-$(CONFIG_BLK_DEV_PMEM) += nd_pmem.o @@ -27,10 +29,12 @@ obj-$(CONFIG_ACPI_NFIT) += nfit.o obj-$(CONFIG_DEV_DAX) += dax.o obj-$(CONFIG_DEV_DAX_PMEM) += dax_pmem.o -nfit-y := $(ACPI_SRC)/nfit.o +nfit-y := $(ACPI_SRC)/core.o +nfit-$(CONFIG_X86_MCE) += $(ACPI_SRC)/mce.o nfit-y += config_check.o nd_pmem-y := $(NVDIMM_SRC)/pmem.o +nd_pmem-y += pmem-dax.o nd_pmem-y += config_check.o nd_btt-y := $(NVDIMM_SRC)/btt.o diff --git a/tools/testing/nvdimm/config_check.c b/tools/testing/nvdimm/config_check.c index adf18bfeca00..878daf3429e8 100644 --- a/tools/testing/nvdimm/config_check.c +++ b/tools/testing/nvdimm/config_check.c @@ -10,6 +10,7 @@ void check(void) BUILD_BUG_ON(!IS_MODULE(CONFIG_LIBNVDIMM)); BUILD_BUG_ON(!IS_MODULE(CONFIG_BLK_DEV_PMEM)); BUILD_BUG_ON(!IS_MODULE(CONFIG_ND_BTT)); + BUILD_BUG_ON(!IS_MODULE(CONFIG_ND_PFN)); BUILD_BUG_ON(!IS_MODULE(CONFIG_ND_BLK)); BUILD_BUG_ON(!IS_MODULE(CONFIG_ACPI_NFIT)); BUILD_BUG_ON(!IS_MODULE(CONFIG_DEV_DAX)); diff --git a/tools/testing/nvdimm/pmem-dax.c b/tools/testing/nvdimm/pmem-dax.c new file mode 100644 index 000000000000..c9b8c48f85fc --- /dev/null +++ b/tools/testing/nvdimm/pmem-dax.c @@ -0,0 +1,54 @@ +/* + * Copyright (c) 2014-2016, 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. + */ +#include "test/nfit_test.h" +#include <linux/blkdev.h> +#include <pmem.h> +#include <nd.h> + +long pmem_direct_access(struct block_device *bdev, sector_t sector, + void **kaddr, pfn_t *pfn, long size) +{ + struct pmem_device *pmem = bdev->bd_queue->queuedata; + resource_size_t offset = sector * 512 + pmem->data_offset; + + if (unlikely(is_bad_pmem(&pmem->bb, sector, size))) + return -EIO; + + /* + * Limit dax to a single page at a time given vmalloc()-backed + * in the nfit_test case. + */ + if (get_nfit_res(pmem->phys_addr + offset)) { + struct page *page; + + *kaddr = pmem->virt_addr + offset; + page = vmalloc_to_page(pmem->virt_addr + offset); + *pfn = page_to_pfn_t(page); + dev_dbg_ratelimited(disk_to_dev(bdev->bd_disk)->parent, + "%s: sector: %#llx pfn: %#lx\n", __func__, + (unsigned long long) sector, page_to_pfn(page)); + + return PAGE_SIZE; + } + + *kaddr = pmem->virt_addr + offset; + *pfn = phys_to_pfn_t(pmem->phys_addr + offset, pmem->pfn_flags); + + /* + * If badblocks are present, limit known good range to the + * requested range. + */ + if (unlikely(pmem->bb.count)) + return size; + return pmem->size - pmem->pfn_pad - offset; +} diff --git a/tools/testing/nvdimm/test/Kbuild b/tools/testing/nvdimm/test/Kbuild index 9241064970fe..d32f25bba42a 100644 --- a/tools/testing/nvdimm/test/Kbuild +++ b/tools/testing/nvdimm/test/Kbuild @@ -1,5 +1,5 @@ ccflags-y := -I$(src)/../../../../drivers/nvdimm/ -ccflags-y += -I$(src)/../../../../drivers/acpi/ +ccflags-y += -I$(src)/../../../../drivers/acpi/nfit/ obj-m += nfit_test.o obj-m += nfit_test_iomap.o diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c index c842095f2801..c29f8dca9e67 100644 --- a/tools/testing/nvdimm/test/iomap.c +++ b/tools/testing/nvdimm/test/iomap.c @@ -10,11 +10,13 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU * General Public License for more details. */ +#include <linux/memremap.h> #include <linux/rculist.h> #include <linux/export.h> #include <linux/ioport.h> #include <linux/module.h> #include <linux/types.h> +#include <linux/pfn_t.h> #include <linux/io.h> #include <linux/mm.h> #include "nfit_test.h" @@ -52,7 +54,7 @@ static struct nfit_test_resource *__get_nfit_res(resource_size_t resource) return NULL; } -static struct nfit_test_resource *get_nfit_res(resource_size_t resource) +struct nfit_test_resource *get_nfit_res(resource_size_t resource) { struct nfit_test_resource *res; @@ -62,6 +64,7 @@ static struct nfit_test_resource *get_nfit_res(resource_size_t resource) return res; } +EXPORT_SYMBOL(get_nfit_res); void __iomem *__nfit_test_ioremap(resource_size_t offset, unsigned long size, void __iomem *(*fallback_fn)(resource_size_t, unsigned long)) @@ -97,10 +100,6 @@ void *__wrap_devm_memremap(struct device *dev, resource_size_t offset, } EXPORT_SYMBOL(__wrap_devm_memremap); -#ifdef __HAVE_ARCH_PTE_DEVMAP -#include <linux/memremap.h> -#include <linux/pfn_t.h> - void *__wrap_devm_memremap_pages(struct device *dev, struct resource *res, struct percpu_ref *ref, struct vmem_altmap *altmap) { @@ -122,19 +121,6 @@ pfn_t __wrap_phys_to_pfn_t(phys_addr_t addr, unsigned long flags) return phys_to_pfn_t(addr, flags); } EXPORT_SYMBOL(__wrap_phys_to_pfn_t); -#else -/* to be removed post 4.5-rc1 */ -void *__wrap_devm_memremap_pages(struct device *dev, struct resource *res) -{ - resource_size_t offset = res->start; - struct nfit_test_resource *nfit_res = get_nfit_res(offset); - - if (nfit_res) - return nfit_res->buf + offset - nfit_res->res->start; - return devm_memremap_pages(dev, res); -} -EXPORT_SYMBOL(__wrap_devm_memremap_pages); -#endif void *__wrap_memremap(resource_size_t offset, size_t size, unsigned long flags) @@ -229,6 +215,22 @@ struct resource *__wrap___request_region(struct resource *parent, } EXPORT_SYMBOL(__wrap___request_region); +int __wrap_insert_resource(struct resource *parent, struct resource *res) +{ + if (get_nfit_res(res->start)) + return 0; + return insert_resource(parent, res); +} +EXPORT_SYMBOL(__wrap_insert_resource); + +int __wrap_remove_resource(struct resource *res) +{ + if (get_nfit_res(res->start)) + return 0; + return remove_resource(res); +} +EXPORT_SYMBOL(__wrap_remove_resource); + struct resource *__wrap___devm_request_region(struct device *dev, struct resource *parent, resource_size_t start, resource_size_t n, const char *name) diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index c919866853a0..5404efa578a3 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -98,11 +98,13 @@ enum { NUM_PM = 3, NUM_DCR = 5, + NUM_HINTS = 8, NUM_BDW = NUM_DCR, NUM_SPA = NUM_PM + NUM_DCR + NUM_BDW, NUM_MEM = NUM_DCR + NUM_BDW + 2 /* spa0 iset */ + 4 /* spa1 iset */, DIMM_SIZE = SZ_32M, LABEL_SIZE = SZ_128K, + SPA_VCD_SIZE = SZ_4M, SPA0_SIZE = DIMM_SIZE, SPA1_SIZE = DIMM_SIZE*2, SPA2_SIZE = DIMM_SIZE, @@ -470,11 +472,7 @@ static void release_nfit_res(void *data) list_del(&nfit_res->list); spin_unlock(&nfit_test_lock); - if (is_vmalloc_addr(nfit_res->buf)) - vfree(nfit_res->buf); - else - dma_free_coherent(nfit_res->dev, resource_size(res), - nfit_res->buf, res->start); + vfree(nfit_res->buf); kfree(res); kfree(nfit_res); } @@ -507,9 +505,7 @@ static void *__test_alloc(struct nfit_test *t, size_t size, dma_addr_t *dma, return nfit_res->buf; err: - if (buf && !is_vmalloc_addr(buf)) - dma_free_coherent(dev, size, buf, *dma); - else if (buf) + if (buf) vfree(buf); kfree(res); kfree(nfit_res); @@ -524,15 +520,6 @@ static void *test_alloc(struct nfit_test *t, size_t size, dma_addr_t *dma) return __test_alloc(t, size, dma, buf); } -static void *test_alloc_coherent(struct nfit_test *t, size_t size, - dma_addr_t *dma) -{ - struct device *dev = &t->pdev.dev; - void *buf = dma_alloc_coherent(dev, size, dma, GFP_KERNEL); - - return __test_alloc(t, size, dma, buf); -} - static struct nfit_test_resource *nfit_test_lookup(resource_size_t addr) { int i; @@ -584,7 +571,8 @@ static int nfit_test0_alloc(struct nfit_test *t) + offsetof(struct acpi_nfit_control_region, window_size) * NUM_DCR + sizeof(struct acpi_nfit_data_region) * NUM_BDW - + sizeof(struct acpi_nfit_flush_address) * NUM_DCR; + + (sizeof(struct acpi_nfit_flush_address) + + sizeof(u64) * NUM_HINTS) * NUM_DCR; int i; t->nfit_buf = test_alloc(t, nfit_size, &t->nfit_dma); @@ -592,15 +580,15 @@ static int nfit_test0_alloc(struct nfit_test *t) return -ENOMEM; t->nfit_size = nfit_size; - t->spa_set[0] = test_alloc_coherent(t, SPA0_SIZE, &t->spa_set_dma[0]); + t->spa_set[0] = test_alloc(t, SPA0_SIZE, &t->spa_set_dma[0]); if (!t->spa_set[0]) return -ENOMEM; - t->spa_set[1] = test_alloc_coherent(t, SPA1_SIZE, &t->spa_set_dma[1]); + t->spa_set[1] = test_alloc(t, SPA1_SIZE, &t->spa_set_dma[1]); if (!t->spa_set[1]) return -ENOMEM; - t->spa_set[2] = test_alloc_coherent(t, SPA0_SIZE, &t->spa_set_dma[2]); + t->spa_set[2] = test_alloc(t, SPA0_SIZE, &t->spa_set_dma[2]); if (!t->spa_set[2]) return -ENOMEM; @@ -614,7 +602,8 @@ static int nfit_test0_alloc(struct nfit_test *t) return -ENOMEM; sprintf(t->label[i], "label%d", i); - t->flush[i] = test_alloc(t, 8, &t->flush_dma[i]); + t->flush[i] = test_alloc(t, sizeof(u64) * NUM_HINTS, + &t->flush_dma[i]); if (!t->flush[i]) return -ENOMEM; } @@ -630,7 +619,7 @@ static int nfit_test0_alloc(struct nfit_test *t) static int nfit_test1_alloc(struct nfit_test *t) { - size_t nfit_size = sizeof(struct acpi_nfit_system_address) + size_t nfit_size = sizeof(struct acpi_nfit_system_address) * 2 + sizeof(struct acpi_nfit_memory_map) + offsetof(struct acpi_nfit_control_region, window_size); @@ -639,15 +628,31 @@ static int nfit_test1_alloc(struct nfit_test *t) return -ENOMEM; t->nfit_size = nfit_size; - t->spa_set[0] = test_alloc_coherent(t, SPA2_SIZE, &t->spa_set_dma[0]); + t->spa_set[0] = test_alloc(t, SPA2_SIZE, &t->spa_set_dma[0]); if (!t->spa_set[0]) return -ENOMEM; + t->spa_set[1] = test_alloc(t, SPA_VCD_SIZE, &t->spa_set_dma[1]); + if (!t->spa_set[1]) + return -ENOMEM; + return ars_state_init(&t->pdev.dev, &t->ars_state); } +static void dcr_common_init(struct acpi_nfit_control_region *dcr) +{ + dcr->vendor_id = 0xabcd; + dcr->device_id = 0; + dcr->revision_id = 1; + dcr->valid_fields = 1; + dcr->manufacturing_location = 0xa; + dcr->manufacturing_date = cpu_to_be16(2016); +} + static void nfit_test0_setup(struct nfit_test *t) { + const int flush_hint_size = sizeof(struct acpi_nfit_flush_address) + + (sizeof(u64) * NUM_HINTS); struct acpi_nfit_desc *acpi_desc; struct acpi_nfit_memory_map *memdev; void *nfit_buf = t->nfit_buf; @@ -655,7 +660,7 @@ static void nfit_test0_setup(struct nfit_test *t) struct acpi_nfit_control_region *dcr; struct acpi_nfit_data_region *bdw; struct acpi_nfit_flush_address *flush; - unsigned int offset; + unsigned int offset, i; /* * spa0 (interleave first half of dimm0 and dimm1, note storage @@ -972,9 +977,7 @@ static void nfit_test0_setup(struct nfit_test *t) dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION; dcr->header.length = sizeof(struct acpi_nfit_control_region); dcr->region_index = 0+1; - dcr->vendor_id = 0xabcd; - dcr->device_id = 0; - dcr->revision_id = 1; + dcr_common_init(dcr); dcr->serial_number = ~handle[0]; dcr->code = NFIT_FIC_BLK; dcr->windows = 1; @@ -989,9 +992,7 @@ static void nfit_test0_setup(struct nfit_test *t) dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION; dcr->header.length = sizeof(struct acpi_nfit_control_region); dcr->region_index = 1+1; - dcr->vendor_id = 0xabcd; - dcr->device_id = 0; - dcr->revision_id = 1; + dcr_common_init(dcr); dcr->serial_number = ~handle[1]; dcr->code = NFIT_FIC_BLK; dcr->windows = 1; @@ -1006,9 +1007,7 @@ static void nfit_test0_setup(struct nfit_test *t) dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION; dcr->header.length = sizeof(struct acpi_nfit_control_region); dcr->region_index = 2+1; - dcr->vendor_id = 0xabcd; - dcr->device_id = 0; - dcr->revision_id = 1; + dcr_common_init(dcr); dcr->serial_number = ~handle[2]; dcr->code = NFIT_FIC_BLK; dcr->windows = 1; @@ -1023,9 +1022,7 @@ static void nfit_test0_setup(struct nfit_test *t) dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION; dcr->header.length = sizeof(struct acpi_nfit_control_region); dcr->region_index = 3+1; - dcr->vendor_id = 0xabcd; - dcr->device_id = 0; - dcr->revision_id = 1; + dcr_common_init(dcr); dcr->serial_number = ~handle[3]; dcr->code = NFIT_FIC_BLK; dcr->windows = 1; @@ -1042,9 +1039,7 @@ static void nfit_test0_setup(struct nfit_test *t) dcr->header.length = offsetof(struct acpi_nfit_control_region, window_size); dcr->region_index = 4+1; - dcr->vendor_id = 0xabcd; - dcr->device_id = 0; - dcr->revision_id = 1; + dcr_common_init(dcr); dcr->serial_number = ~handle[0]; dcr->code = NFIT_FIC_BYTEN; dcr->windows = 0; @@ -1056,9 +1051,7 @@ static void nfit_test0_setup(struct nfit_test *t) dcr->header.length = offsetof(struct acpi_nfit_control_region, window_size); dcr->region_index = 5+1; - dcr->vendor_id = 0xabcd; - dcr->device_id = 0; - dcr->revision_id = 1; + dcr_common_init(dcr); dcr->serial_number = ~handle[1]; dcr->code = NFIT_FIC_BYTEN; dcr->windows = 0; @@ -1070,9 +1063,7 @@ static void nfit_test0_setup(struct nfit_test *t) dcr->header.length = offsetof(struct acpi_nfit_control_region, window_size); dcr->region_index = 6+1; - dcr->vendor_id = 0xabcd; - dcr->device_id = 0; - dcr->revision_id = 1; + dcr_common_init(dcr); dcr->serial_number = ~handle[2]; dcr->code = NFIT_FIC_BYTEN; dcr->windows = 0; @@ -1084,9 +1075,7 @@ static void nfit_test0_setup(struct nfit_test *t) dcr->header.length = offsetof(struct acpi_nfit_control_region, window_size); dcr->region_index = 7+1; - dcr->vendor_id = 0xabcd; - dcr->device_id = 0; - dcr->revision_id = 1; + dcr_common_init(dcr); dcr->serial_number = ~handle[3]; dcr->code = NFIT_FIC_BYTEN; dcr->windows = 0; @@ -1141,45 +1130,47 @@ static void nfit_test0_setup(struct nfit_test *t) /* flush0 (dimm0) */ flush = nfit_buf + offset; flush->header.type = ACPI_NFIT_TYPE_FLUSH_ADDRESS; - flush->header.length = sizeof(struct acpi_nfit_flush_address); + flush->header.length = flush_hint_size; flush->device_handle = handle[0]; - flush->hint_count = 1; - flush->hint_address[0] = t->flush_dma[0]; + flush->hint_count = NUM_HINTS; + for (i = 0; i < NUM_HINTS; i++) + flush->hint_address[i] = t->flush_dma[0] + i * sizeof(u64); /* flush1 (dimm1) */ - flush = nfit_buf + offset + sizeof(struct acpi_nfit_flush_address) * 1; + flush = nfit_buf + offset + flush_hint_size * 1; flush->header.type = ACPI_NFIT_TYPE_FLUSH_ADDRESS; - flush->header.length = sizeof(struct acpi_nfit_flush_address); + flush->header.length = flush_hint_size; flush->device_handle = handle[1]; - flush->hint_count = 1; - flush->hint_address[0] = t->flush_dma[1]; + flush->hint_count = NUM_HINTS; + for (i = 0; i < NUM_HINTS; i++) + flush->hint_address[i] = t->flush_dma[1] + i * sizeof(u64); /* flush2 (dimm2) */ - flush = nfit_buf + offset + sizeof(struct acpi_nfit_flush_address) * 2; + flush = nfit_buf + offset + flush_hint_size * 2; flush->header.type = ACPI_NFIT_TYPE_FLUSH_ADDRESS; - flush->header.length = sizeof(struct acpi_nfit_flush_address); + flush->header.length = flush_hint_size; flush->device_handle = handle[2]; - flush->hint_count = 1; - flush->hint_address[0] = t->flush_dma[2]; + flush->hint_count = NUM_HINTS; + for (i = 0; i < NUM_HINTS; i++) + flush->hint_address[i] = t->flush_dma[2] + i * sizeof(u64); /* flush3 (dimm3) */ - flush = nfit_buf + offset + sizeof(struct acpi_nfit_flush_address) * 3; + flush = nfit_buf + offset + flush_hint_size * 3; flush->header.type = ACPI_NFIT_TYPE_FLUSH_ADDRESS; - flush->header.length = sizeof(struct acpi_nfit_flush_address); + flush->header.length = flush_hint_size; flush->device_handle = handle[3]; - flush->hint_count = 1; - flush->hint_address[0] = t->flush_dma[3]; + flush->hint_count = NUM_HINTS; + for (i = 0; i < NUM_HINTS; i++) + flush->hint_address[i] = t->flush_dma[3] + i * sizeof(u64); if (t->setup_hotplug) { - offset = offset + sizeof(struct acpi_nfit_flush_address) * 4; + offset = offset + flush_hint_size * 4; /* dcr-descriptor4: blk */ dcr = nfit_buf + offset; dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION; dcr->header.length = sizeof(struct acpi_nfit_control_region); dcr->region_index = 8+1; - dcr->vendor_id = 0xabcd; - dcr->device_id = 0; - dcr->revision_id = 1; + dcr_common_init(dcr); dcr->serial_number = ~handle[4]; dcr->code = NFIT_FIC_BLK; dcr->windows = 1; @@ -1196,9 +1187,7 @@ static void nfit_test0_setup(struct nfit_test *t) dcr->header.length = offsetof(struct acpi_nfit_control_region, window_size); dcr->region_index = 9+1; - dcr->vendor_id = 0xabcd; - dcr->device_id = 0; - dcr->revision_id = 1; + dcr_common_init(dcr); dcr->serial_number = ~handle[4]; dcr->code = NFIT_FIC_BYTEN; dcr->windows = 0; @@ -1300,10 +1289,12 @@ static void nfit_test0_setup(struct nfit_test *t) /* flush3 (dimm4) */ flush = nfit_buf + offset; flush->header.type = ACPI_NFIT_TYPE_FLUSH_ADDRESS; - flush->header.length = sizeof(struct acpi_nfit_flush_address); + flush->header.length = flush_hint_size; flush->device_handle = handle[4]; - flush->hint_count = 1; - flush->hint_address[0] = t->flush_dma[4]; + flush->hint_count = NUM_HINTS; + for (i = 0; i < NUM_HINTS; i++) + flush->hint_address[i] = t->flush_dma[4] + + i * sizeof(u64); } post_ars_status(&t->ars_state, t->spa_set_dma[0], SPA0_SIZE); @@ -1339,7 +1330,16 @@ static void nfit_test1_setup(struct nfit_test *t) spa->address = t->spa_set_dma[0]; spa->length = SPA2_SIZE; - offset += sizeof(*spa); + /* virtual cd region */ + spa = nfit_buf + sizeof(*spa); + spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; + spa->header.length = sizeof(*spa); + memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_VCD), 16); + spa->range_index = 0; + spa->address = t->spa_set_dma[1]; + spa->length = SPA_VCD_SIZE; + + offset += sizeof(*spa) * 2; /* mem-region0 (spa0, dimm0) */ memdev = nfit_buf + offset; memdev->header.type = ACPI_NFIT_TYPE_MEMORY_MAP; @@ -1365,9 +1365,7 @@ static void nfit_test1_setup(struct nfit_test *t) dcr->header.length = offsetof(struct acpi_nfit_control_region, window_size); dcr->region_index = 0+1; - dcr->vendor_id = 0xabcd; - dcr->device_id = 0; - dcr->revision_id = 1; + dcr_common_init(dcr); dcr->serial_number = ~0; dcr->code = NFIT_FIC_BYTE; dcr->windows = 0; @@ -1462,20 +1460,16 @@ static int nfit_test_probe(struct platform_device *pdev) nfit_test->setup(nfit_test); acpi_desc = &nfit_test->acpi_desc; acpi_nfit_desc_init(acpi_desc, &pdev->dev); - acpi_desc->nfit = nfit_test->nfit_buf; acpi_desc->blk_do_io = nfit_test_blk_do_io; nd_desc = &acpi_desc->nd_desc; nd_desc->provider_name = NULL; + nd_desc->module = THIS_MODULE; nd_desc->ndctl = nfit_test_ctl; - acpi_desc->nvdimm_bus = nvdimm_bus_register(&pdev->dev, nd_desc); - if (!acpi_desc->nvdimm_bus) - return -ENXIO; - rc = acpi_nfit_init(acpi_desc, nfit_test->nfit_size); - if (rc) { - nvdimm_bus_unregister(acpi_desc->nvdimm_bus); + rc = acpi_nfit_init(acpi_desc, nfit_test->nfit_buf, + nfit_test->nfit_size); + if (rc) return rc; - } if (nfit_test->setup != nfit_test0_setup) return 0; @@ -1483,22 +1477,16 @@ static int nfit_test_probe(struct platform_device *pdev) nfit_test->setup_hotplug = 1; nfit_test->setup(nfit_test); - rc = acpi_nfit_init(acpi_desc, nfit_test->nfit_size); - if (rc) { - nvdimm_bus_unregister(acpi_desc->nvdimm_bus); + rc = acpi_nfit_init(acpi_desc, nfit_test->nfit_buf, + nfit_test->nfit_size); + if (rc) return rc; - } return 0; } static int nfit_test_remove(struct platform_device *pdev) { - struct nfit_test *nfit_test = to_nfit_test(&pdev->dev); - struct acpi_nfit_desc *acpi_desc = &nfit_test->acpi_desc; - - nvdimm_bus_unregister(acpi_desc->nvdimm_bus); - return 0; } @@ -1523,12 +1511,6 @@ static struct platform_driver nfit_test_driver = { .id_table = nfit_test_id, }; -#ifdef CONFIG_CMA_SIZE_MBYTES -#define CMA_SIZE_MBYTES CONFIG_CMA_SIZE_MBYTES -#else -#define CMA_SIZE_MBYTES 0 -#endif - static __init int nfit_test_init(void) { int rc, i; @@ -1538,7 +1520,6 @@ static __init int nfit_test_init(void) for (i = 0; i < NUM_NFITS; i++) { struct nfit_test *nfit_test; struct platform_device *pdev; - static int once; nfit_test = kzalloc(sizeof(*nfit_test), GFP_KERNEL); if (!nfit_test) { @@ -1577,20 +1558,6 @@ static __init int nfit_test_init(void) goto err_register; instances[i] = nfit_test; - - if (!once++) { - dma_addr_t dma; - void *buf; - - buf = dma_alloc_coherent(&pdev->dev, SZ_128M, &dma, - GFP_KERNEL); - if (!buf) { - rc = -ENOMEM; - dev_warn(&pdev->dev, "need 128M of free cma\n"); - goto err_register; - } - dma_free_coherent(&pdev->dev, SZ_128M, buf, dma); - } } rc = platform_driver_register(&nfit_test_driver); diff --git a/tools/testing/nvdimm/test/nfit_test.h b/tools/testing/nvdimm/test/nfit_test.h index 96c5e16d7db9..9f18e2a4a862 100644 --- a/tools/testing/nvdimm/test/nfit_test.h +++ b/tools/testing/nvdimm/test/nfit_test.h @@ -12,6 +12,7 @@ */ #ifndef __NFIT_TEST_H__ #define __NFIT_TEST_H__ +#include <linux/list.h> struct nfit_test_resource { struct list_head list; @@ -26,4 +27,5 @@ void __iomem *__wrap_ioremap_nocache(resource_size_t offset, void __wrap_iounmap(volatile void __iomem *addr); void nfit_test_setup(nfit_test_lookup_fn lookup); void nfit_test_teardown(void); +struct nfit_test_resource *get_nfit_res(resource_size_t resource); #endif diff --git a/tools/testing/selftests/powerpc/Makefile b/tools/testing/selftests/powerpc/Makefile index 4ca83fe80654..3c40c9d0e6c7 100644 --- a/tools/testing/selftests/powerpc/Makefile +++ b/tools/testing/selftests/powerpc/Makefile @@ -12,7 +12,8 @@ CFLAGS := -Wall -O2 -Wall -Werror -DGIT_VERSION='"$(GIT_VERSION)"' -I$(CURDIR) $ export CFLAGS -SUB_DIRS = benchmarks \ +SUB_DIRS = alignment \ + benchmarks \ copyloops \ context_switch \ dscr \ diff --git a/tools/testing/selftests/powerpc/alignment/.gitignore b/tools/testing/selftests/powerpc/alignment/.gitignore new file mode 100644 index 000000000000..1d980e3d7039 --- /dev/null +++ b/tools/testing/selftests/powerpc/alignment/.gitignore @@ -0,0 +1,5 @@ +copy_unaligned +copy_first_unaligned +paste_unaligned +paste_last_unaligned +copy_paste_unaligned_common diff --git a/tools/testing/selftests/powerpc/alignment/Makefile b/tools/testing/selftests/powerpc/alignment/Makefile new file mode 100644 index 000000000000..ad6a4e49da91 --- /dev/null +++ b/tools/testing/selftests/powerpc/alignment/Makefile @@ -0,0 +1,10 @@ +TEST_PROGS := copy_unaligned copy_first_unaligned paste_unaligned paste_last_unaligned + +all: $(TEST_PROGS) + +$(TEST_PROGS): ../harness.c ../utils.c copy_paste_unaligned_common.c + +include ../../lib.mk + +clean: + rm -f $(TEST_PROGS) diff --git a/tools/testing/selftests/powerpc/alignment/copy_first_unaligned.c b/tools/testing/selftests/powerpc/alignment/copy_first_unaligned.c new file mode 100644 index 000000000000..47b73b3a08bd --- /dev/null +++ b/tools/testing/selftests/powerpc/alignment/copy_first_unaligned.c @@ -0,0 +1,41 @@ +/* + * Copyright 2016, Chris Smart, IBM Corporation. + * + * 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. + * + * Calls to copy_first which are not 128-byte aligned should be + * caught and sent a SIGBUS. + * + */ + +#include <string.h> +#include <unistd.h> +#include "utils.h" +#include "instructions.h" +#include "copy_paste_unaligned_common.h" + +unsigned int expected_instruction = PPC_INST_COPY_FIRST; +unsigned int instruction_mask = 0xfc2007fe; + +int test_copy_first_unaligned(void) +{ + /* Only run this test on a P9 or later */ + SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_3_00)); + + /* Register our signal handler with SIGBUS */ + setup_signal_handler(); + + /* +1 makes buf unaligned */ + copy_first(cacheline_buf+1); + + /* We should not get here */ + return 1; +} + +int main(int argc, char *argv[]) +{ + return test_harness(test_copy_first_unaligned, "test_copy_first_unaligned"); +} diff --git a/tools/testing/selftests/powerpc/alignment/copy_paste_unaligned_common.c b/tools/testing/selftests/powerpc/alignment/copy_paste_unaligned_common.c new file mode 100644 index 000000000000..d35fa5f5d2d3 --- /dev/null +++ b/tools/testing/selftests/powerpc/alignment/copy_paste_unaligned_common.c @@ -0,0 +1,53 @@ +/* + * Copyright 2016, Chris Smart, IBM Corporation. + * + * 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. + * + * Common code for copy, copy_first, paste and paste_last unaligned + * tests. + * + */ + +#include <signal.h> +#include <string.h> +#include <unistd.h> +#include "utils.h" +#include "instructions.h" +#include "copy_paste_unaligned_common.h" + +unsigned int expected_instruction; +unsigned int instruction_mask; + +char cacheline_buf[128] __cacheline_aligned; + +void signal_action_handler(int signal_num, siginfo_t *info, void *ptr) +{ + ucontext_t *ctx = ptr; +#if defined(__powerpc64__) + unsigned int *pc = (unsigned int *)ctx->uc_mcontext.gp_regs[PT_NIP]; +#else + unsigned int *pc = (unsigned int *)ctx->uc_mcontext.uc_regs->gregs[PT_NIP]; +#endif + + /* + * Check that the signal was on the correct instruction, using a + * mask because the compiler assigns the register at RB. + */ + if ((*pc & instruction_mask) == expected_instruction) + _exit(0); /* We hit the right instruction */ + + _exit(1); +} + +void setup_signal_handler(void) +{ + struct sigaction signal_action; + + memset(&signal_action, 0, sizeof(signal_action)); + signal_action.sa_sigaction = signal_action_handler; + signal_action.sa_flags = SA_SIGINFO; + sigaction(SIGBUS, &signal_action, NULL); +} diff --git a/tools/testing/selftests/powerpc/alignment/copy_paste_unaligned_common.h b/tools/testing/selftests/powerpc/alignment/copy_paste_unaligned_common.h new file mode 100644 index 000000000000..053899fe506e --- /dev/null +++ b/tools/testing/selftests/powerpc/alignment/copy_paste_unaligned_common.h @@ -0,0 +1,26 @@ +/* + * Copyright 2016, Chris Smart, IBM Corporation. + * + * 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. + * + * Declarations for common code for copy, copy_first, paste and + * paste_last unaligned tests. + * + */ + +#ifndef _SELFTESTS_POWERPC_COPY_PASTE_H +#define _SELFTESTS_POWERPC_COPY_PASTE_H + +#include <signal.h> + +int main(int argc, char *argv[]); +void signal_action_handler(int signal_num, siginfo_t *info, void *ptr); +void setup_signal_handler(void); +extern char cacheline_buf[128] __cacheline_aligned; +extern unsigned int expected_instruction; +extern unsigned int instruction_mask; + +#endif /* _SELFTESTS_POWERPC_COPY_PASTE_H */ diff --git a/tools/testing/selftests/powerpc/alignment/copy_unaligned.c b/tools/testing/selftests/powerpc/alignment/copy_unaligned.c new file mode 100644 index 000000000000..3a4e26461554 --- /dev/null +++ b/tools/testing/selftests/powerpc/alignment/copy_unaligned.c @@ -0,0 +1,41 @@ +/* + * Copyright 2016, Chris Smart, IBM Corporation. + * + * 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. + * + * Calls to copy which are not 128-byte aligned should be caught + * and sent a SIGBUS. + * + */ + +#include <string.h> +#include <unistd.h> +#include "utils.h" +#include "instructions.h" +#include "copy_paste_unaligned_common.h" + +unsigned int expected_instruction = PPC_INST_COPY; +unsigned int instruction_mask = 0xfc0007fe; + +int test_copy_unaligned(void) +{ + /* Only run this test on a P9 or later */ + SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_3_00)); + + /* Register our signal handler with SIGBUS */ + setup_signal_handler(); + + /* +1 makes buf unaligned */ + copy(cacheline_buf+1); + + /* We should not get here */ + return 1; +} + +int main(int argc, char *argv[]) +{ + return test_harness(test_copy_unaligned, "test_copy_unaligned"); +} diff --git a/tools/testing/selftests/powerpc/alignment/paste_last_unaligned.c b/tools/testing/selftests/powerpc/alignment/paste_last_unaligned.c new file mode 100644 index 000000000000..6e0ad045fcc3 --- /dev/null +++ b/tools/testing/selftests/powerpc/alignment/paste_last_unaligned.c @@ -0,0 +1,43 @@ +/* + * Copyright 2016, Chris Smart, IBM Corporation. + * + * 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. + * + * Calls to paste_last which are not 128-byte aligned should be + * caught and sent a SIGBUS. + * + */ + +#include <string.h> +#include <unistd.h> +#include "utils.h" +#include "instructions.h" +#include "copy_paste_unaligned_common.h" + +unsigned int expected_instruction = PPC_INST_PASTE_LAST; +unsigned int instruction_mask = 0xfc2007ff; + +int test_paste_last_unaligned(void) +{ + /* Only run this test on a P9 or later */ + SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_3_00)); + + /* Register our signal handler with SIGBUS */ + setup_signal_handler(); + + copy(cacheline_buf); + + /* +1 makes buf unaligned */ + paste_last(cacheline_buf+1); + + /* We should not get here */ + return 1; +} + +int main(int argc, char *argv[]) +{ + return test_harness(test_paste_last_unaligned, "test_paste_last_unaligned"); +} diff --git a/tools/testing/selftests/powerpc/alignment/paste_unaligned.c b/tools/testing/selftests/powerpc/alignment/paste_unaligned.c new file mode 100644 index 000000000000..6f982b45e4bd --- /dev/null +++ b/tools/testing/selftests/powerpc/alignment/paste_unaligned.c @@ -0,0 +1,43 @@ +/* + * Copyright 2016, Chris Smart, IBM Corporation. + * + * 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. + * + * Calls to paste which are not 128-byte aligned should be caught + * and sent a SIGBUS. + * + */ + +#include <string.h> +#include <unistd.h> +#include "utils.h" +#include "instructions.h" +#include "copy_paste_unaligned_common.h" + +unsigned int expected_instruction = PPC_INST_PASTE; +unsigned int instruction_mask = 0xfc0007fe; + +int test_paste_unaligned(void) +{ + /* Only run this test on a P9 or later */ + SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_3_00)); + + /* Register our signal handler with SIGBUS */ + setup_signal_handler(); + + copy(cacheline_buf); + + /* +1 makes buf unaligned */ + paste(cacheline_buf+1); + + /* We should not get here */ + return 1; +} + +int main(int argc, char *argv[]) +{ + return test_harness(test_paste_unaligned, "test_paste_unaligned"); +} diff --git a/tools/testing/selftests/powerpc/benchmarks/.gitignore b/tools/testing/selftests/powerpc/benchmarks/.gitignore index 6fa673316ac2..bce49ebd869e 100644 --- a/tools/testing/selftests/powerpc/benchmarks/.gitignore +++ b/tools/testing/selftests/powerpc/benchmarks/.gitignore @@ -1,2 +1,4 @@ gettimeofday context_switch +mmap_bench +futex_bench
\ No newline at end of file diff --git a/tools/testing/selftests/powerpc/benchmarks/Makefile b/tools/testing/selftests/powerpc/benchmarks/Makefile index 912445ff7ce7..a9adfb7de78f 100644 --- a/tools/testing/selftests/powerpc/benchmarks/Makefile +++ b/tools/testing/selftests/powerpc/benchmarks/Makefile @@ -1,4 +1,4 @@ -TEST_PROGS := gettimeofday context_switch +TEST_PROGS := gettimeofday context_switch mmap_bench futex_bench CFLAGS += -O2 @@ -7,6 +7,7 @@ all: $(TEST_PROGS) $(TEST_PROGS): ../harness.c context_switch: ../utils.c +context_switch: CFLAGS += -maltivec -mvsx -mabi=altivec context_switch: LDLIBS += -lpthread include ../../lib.mk diff --git a/tools/testing/selftests/powerpc/benchmarks/context_switch.c b/tools/testing/selftests/powerpc/benchmarks/context_switch.c index 7b785941adec..a36883ad48a4 100644 --- a/tools/testing/selftests/powerpc/benchmarks/context_switch.c +++ b/tools/testing/selftests/powerpc/benchmarks/context_switch.c @@ -25,7 +25,9 @@ #include <sys/types.h> #include <sys/shm.h> #include <linux/futex.h> - +#ifdef __powerpc__ +#include <altivec.h> +#endif #include "../utils.h" static unsigned int timeout = 30; @@ -37,12 +39,15 @@ static int touch_fp = 1; double fp; static int touch_vector = 1; -typedef int v4si __attribute__ ((vector_size (16))); -v4si a, b, c; +vector int a, b, c; #ifdef __powerpc__ static int touch_altivec = 1; +/* + * Note: LTO (Link Time Optimisation) doesn't play well with this function + * attribute. Be very careful enabling LTO for this test. + */ static void __attribute__((__target__("no-vsx"))) altivec_touch_fn(void) { c = a + b; @@ -369,11 +374,11 @@ static void usage(void) fprintf(stderr, "\t\t--process\tUse processes (default threads)\n"); fprintf(stderr, "\t\t--timeout=X\tDuration in seconds to run (default 30)\n"); fprintf(stderr, "\t\t--vdso\t\ttouch VDSO\n"); - fprintf(stderr, "\t\t--fp\t\ttouch FP\n"); + fprintf(stderr, "\t\t--no-fp\t\tDon't touch FP\n"); #ifdef __powerpc__ - fprintf(stderr, "\t\t--altivec\ttouch altivec\n"); + fprintf(stderr, "\t\t--no-altivec\tDon't touch altivec\n"); #endif - fprintf(stderr, "\t\t--vector\ttouch vector\n"); + fprintf(stderr, "\t\t--no-vector\tDon't touch vector\n"); } int main(int argc, char *argv[]) diff --git a/tools/testing/selftests/powerpc/benchmarks/futex_bench.c b/tools/testing/selftests/powerpc/benchmarks/futex_bench.c new file mode 100644 index 000000000000..2fc711d9150d --- /dev/null +++ b/tools/testing/selftests/powerpc/benchmarks/futex_bench.c @@ -0,0 +1,42 @@ +/* + * Copyright 2016, Anton Blanchard, Michael Ellerman, IBM Corp. + * Licensed under GPLv2. + */ + +#define _GNU_SOURCE + +#include <stdio.h> +#include <sys/syscall.h> +#include <time.h> +#include <unistd.h> +#include <linux/futex.h> + +#include "utils.h" + +#define ITERATIONS 100000000 + +#define futex(A, B, C, D, E, F) syscall(__NR_futex, A, B, C, D, E, F) + +int test_futex(void) +{ + struct timespec ts_start, ts_end; + unsigned long i = ITERATIONS; + + clock_gettime(CLOCK_MONOTONIC, &ts_start); + + while (i--) { + unsigned int addr = 0; + futex(&addr, FUTEX_WAKE, 1, NULL, NULL, 0); + } + + clock_gettime(CLOCK_MONOTONIC, &ts_end); + + printf("time = %.6f\n", ts_end.tv_sec - ts_start.tv_sec + (ts_end.tv_nsec - ts_start.tv_nsec) / 1e9); + + return 0; +} + +int main(void) +{ + return test_harness(test_futex, "futex_bench"); +} diff --git a/tools/testing/selftests/powerpc/benchmarks/mmap_bench.c b/tools/testing/selftests/powerpc/benchmarks/mmap_bench.c new file mode 100644 index 000000000000..8d084a2d6e74 --- /dev/null +++ b/tools/testing/selftests/powerpc/benchmarks/mmap_bench.c @@ -0,0 +1,41 @@ +/* + * Copyright 2016, Anton Blanchard, Michael Ellerman, IBM Corp. + * Licensed under GPLv2. + */ + +#include <stdio.h> +#include <stdlib.h> +#include <sys/mman.h> +#include <time.h> + +#include "utils.h" + +#define ITERATIONS 5000000 + +#define MEMSIZE (128 * 1024 * 1024) + +int test_mmap(void) +{ + struct timespec ts_start, ts_end; + unsigned long i = ITERATIONS; + + clock_gettime(CLOCK_MONOTONIC, &ts_start); + + while (i--) { + char *c = mmap(NULL, MEMSIZE, PROT_READ|PROT_WRITE, + MAP_PRIVATE|MAP_ANONYMOUS, -1, 0); + FAIL_IF(c == MAP_FAILED); + munmap(c, MEMSIZE); + } + + clock_gettime(CLOCK_MONOTONIC, &ts_end); + + printf("time = %.6f\n", ts_end.tv_sec - ts_start.tv_sec + (ts_end.tv_nsec - ts_start.tv_nsec) / 1e9); + + return 0; +} + +int main(void) +{ + return test_harness(test_mmap, "mmap_bench"); +} diff --git a/tools/testing/selftests/powerpc/instructions.h b/tools/testing/selftests/powerpc/instructions.h new file mode 100644 index 000000000000..0fb0bd3b28c9 --- /dev/null +++ b/tools/testing/selftests/powerpc/instructions.h @@ -0,0 +1,68 @@ +#ifndef _SELFTESTS_POWERPC_INSTRUCTIONS_H +#define _SELFTESTS_POWERPC_INSTRUCTIONS_H + +#include <stdio.h> +#include <stdlib.h> + +/* This defines the "copy" instruction from Power ISA 3.0 Book II, section 4.4. */ +#define __COPY(RA, RB, L) \ + (0x7c00060c | (RA) << (31-15) | (RB) << (31-20) | (L) << (31-10)) +#define COPY(RA, RB, L) \ + .long __COPY((RA), (RB), (L)) + +static inline void copy(void *i) +{ + asm volatile(str(COPY(0, %0, 0))";" + : + : "b" (i) + : "memory" + ); +} + +static inline void copy_first(void *i) +{ + asm volatile(str(COPY(0, %0, 1))";" + : + : "b" (i) + : "memory" + ); +} + +/* This defines the "paste" instruction from Power ISA 3.0 Book II, section 4.4. */ +#define __PASTE(RA, RB, L, RC) \ + (0x7c00070c | (RA) << (31-15) | (RB) << (31-20) | (L) << (31-10) | (RC) << (31-31)) +#define PASTE(RA, RB, L, RC) \ + .long __PASTE((RA), (RB), (L), (RC)) + +static inline int paste(void *i) +{ + int cr; + + asm volatile(str(PASTE(0, %1, 0, 0))";" + "mfcr %0;" + : "=r" (cr) + : "b" (i) + : "memory" + ); + return cr; +} + +static inline int paste_last(void *i) +{ + int cr; + + asm volatile(str(PASTE(0, %1, 1, 1))";" + "mfcr %0;" + : "=r" (cr) + : "b" (i) + : "memory" + ); + return cr; +} + +#define PPC_INST_COPY __COPY(0, 0, 0) +#define PPC_INST_COPY_FIRST __COPY(0, 0, 1) +#define PPC_INST_PASTE __PASTE(0, 0, 0, 0) +#define PPC_INST_PASTE_LAST __PASTE(0, 0, 1, 1) + +#endif /* _SELFTESTS_POWERPC_INSTRUCTIONS_H */ diff --git a/tools/testing/selftests/powerpc/mm/.gitignore b/tools/testing/selftests/powerpc/mm/.gitignore index b43ade0ec861..e715a3f2fbf4 100644 --- a/tools/testing/selftests/powerpc/mm/.gitignore +++ b/tools/testing/selftests/powerpc/mm/.gitignore @@ -1,3 +1,4 @@ hugetlb_vs_thp_test subpage_prot tempfile +prot_sao
\ No newline at end of file diff --git a/tools/testing/selftests/powerpc/mm/Makefile b/tools/testing/selftests/powerpc/mm/Makefile index ee179e22308c..3bdb96eae558 100644 --- a/tools/testing/selftests/powerpc/mm/Makefile +++ b/tools/testing/selftests/powerpc/mm/Makefile @@ -1,13 +1,15 @@ noarg: $(MAKE) -C ../ -TEST_PROGS := hugetlb_vs_thp_test subpage_prot +TEST_PROGS := hugetlb_vs_thp_test subpage_prot prot_sao TEST_FILES := tempfile all: $(TEST_PROGS) $(TEST_FILES) $(TEST_PROGS): ../harness.c +prot_sao: ../utils.c + include ../../lib.mk tempfile: diff --git a/tools/testing/selftests/powerpc/mm/prot_sao.c b/tools/testing/selftests/powerpc/mm/prot_sao.c new file mode 100644 index 000000000000..611530d43fa9 --- /dev/null +++ b/tools/testing/selftests/powerpc/mm/prot_sao.c @@ -0,0 +1,42 @@ +/* + * Copyright 2016, Michael Ellerman, IBM Corp. + * Licensed under GPLv2. + */ + +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/mman.h> + +#include <asm/cputable.h> + +#include "utils.h" + +#define SIZE (64 * 1024) + +int test_prot_sao(void) +{ + char *p; + + /* 2.06 or later should support SAO */ + SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06)); + + /* + * Ensure we can ask for PROT_SAO. + * We can't really verify that it does the right thing, but at least we + * confirm the kernel will accept it. + */ + p = mmap(NULL, SIZE, PROT_READ | PROT_WRITE | PROT_SAO, + MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + FAIL_IF(p == MAP_FAILED); + + /* Write to the mapping, to at least cause a fault */ + memset(p, 0xaa, SIZE); + + return 0; +} + +int main(void) +{ + return test_harness(test_prot_sao, "prot-sao"); +} diff --git a/tools/testing/selftests/powerpc/pmu/ebb/.gitignore b/tools/testing/selftests/powerpc/pmu/ebb/.gitignore index 42bddbed8b64..44b7df14a936 100644 --- a/tools/testing/selftests/powerpc/pmu/ebb/.gitignore +++ b/tools/testing/selftests/powerpc/pmu/ebb/.gitignore @@ -20,3 +20,5 @@ back_to_back_ebbs_test lost_exception_test no_handler_test cycles_with_mmcr2_test +ebb_lmr +ebb_lmr_regs
\ No newline at end of file diff --git a/tools/testing/selftests/powerpc/pmu/ebb/Makefile b/tools/testing/selftests/powerpc/pmu/ebb/Makefile index 8d2279c4bb4b..6b0453e60d53 100644 --- a/tools/testing/selftests/powerpc/pmu/ebb/Makefile +++ b/tools/testing/selftests/powerpc/pmu/ebb/Makefile @@ -14,7 +14,7 @@ TEST_PROGS := reg_access_test event_attributes_test cycles_test \ fork_cleanup_test ebb_on_child_test \ ebb_on_willing_child_test back_to_back_ebbs_test \ lost_exception_test no_handler_test \ - cycles_with_mmcr2_test + cycles_with_mmcr2_test ebb_lmr ebb_lmr_regs all: $(TEST_PROGS) diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb_lmr.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb_lmr.c new file mode 100644 index 000000000000..c47ebd55ba4d --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb_lmr.c @@ -0,0 +1,143 @@ +/* + * Copyright 2016, Jack Miller, IBM Corp. + * Licensed under GPLv2. + */ + +#include <stdlib.h> +#include <stdio.h> + +#include "ebb.h" +#include "ebb_lmr.h" + +#define SIZE (32 * 1024 * 1024) /* 32M */ +#define LM_SIZE 0 /* Smallest encoding, 32M */ + +#define SECTIONS 64 /* 1 per bit in LMSER */ +#define SECTION_SIZE (SIZE / SECTIONS) +#define SECTION_LONGS (SECTION_SIZE / sizeof(long)) + +static unsigned long *test_mem; + +static int lmr_count = 0; + +void ebb_lmr_handler(void) +{ + lmr_count++; +} + +void ldmx_full_section(unsigned long *mem, int section) +{ + unsigned long *ptr; + int i; + + for (i = 0; i < SECTION_LONGS; i++) { + ptr = &mem[(SECTION_LONGS * section) + i]; + ldmx((unsigned long) &ptr); + ebb_lmr_reset(); + } +} + +unsigned long section_masks[] = { + 0x8000000000000000, + 0xFF00000000000000, + 0x0000000F70000000, + 0x8000000000000001, + 0xF0F0F0F0F0F0F0F0, + 0x0F0F0F0F0F0F0F0F, + 0x0 +}; + +int ebb_lmr_section_test(unsigned long *mem) +{ + unsigned long *mask = section_masks; + int i; + + for (; *mask; mask++) { + mtspr(SPRN_LMSER, *mask); + printf("Testing mask 0x%016lx\n", mfspr(SPRN_LMSER)); + + for (i = 0; i < 64; i++) { + lmr_count = 0; + ldmx_full_section(mem, i); + if (*mask & (1UL << (63 - i))) + FAIL_IF(lmr_count != SECTION_LONGS); + else + FAIL_IF(lmr_count); + } + } + + return 0; +} + +int ebb_lmr(void) +{ + int i; + + SKIP_IF(!lmr_is_supported()); + + setup_ebb_handler(ebb_lmr_handler); + + ebb_global_enable(); + + FAIL_IF(posix_memalign((void **)&test_mem, SIZE, SIZE) != 0); + + mtspr(SPRN_LMSER, 0); + + FAIL_IF(mfspr(SPRN_LMSER) != 0); + + mtspr(SPRN_LMRR, ((unsigned long)test_mem | LM_SIZE)); + + FAIL_IF(mfspr(SPRN_LMRR) != ((unsigned long)test_mem | LM_SIZE)); + + /* Read every single byte to ensure we get no false positives */ + for (i = 0; i < SECTIONS; i++) + ldmx_full_section(test_mem, i); + + FAIL_IF(lmr_count != 0); + + /* Turn on the first section */ + + mtspr(SPRN_LMSER, (1UL << 63)); + FAIL_IF(mfspr(SPRN_LMSER) != (1UL << 63)); + + /* Enable LM (BESCR) */ + + mtspr(SPRN_BESCR, mfspr(SPRN_BESCR) | BESCR_LME); + FAIL_IF(!(mfspr(SPRN_BESCR) & BESCR_LME)); + + ldmx((unsigned long)&test_mem); + + FAIL_IF(lmr_count != 1); // exactly one exception + FAIL_IF(mfspr(SPRN_BESCR) & BESCR_LME); // LM now disabled + FAIL_IF(!(mfspr(SPRN_BESCR) & BESCR_LMEO)); // occurred bit set + + printf("Simple LMR EBB OK\n"); + + /* This shouldn't cause an EBB since it's been disabled */ + ldmx((unsigned long)&test_mem); + FAIL_IF(lmr_count != 1); + + printf("LMR disable on EBB OK\n"); + + ebb_lmr_reset(); + + /* This should cause an EBB or reset is broken */ + ldmx((unsigned long)&test_mem); + FAIL_IF(lmr_count != 2); + + printf("LMR reset EBB OK\n"); + + ebb_lmr_reset(); + + return ebb_lmr_section_test(test_mem); +} + +int main(void) +{ + int ret = test_harness(ebb_lmr, "ebb_lmr"); + + if (test_mem) + free(test_mem); + + return ret; +} diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb_lmr.h b/tools/testing/selftests/powerpc/pmu/ebb/ebb_lmr.h new file mode 100644 index 000000000000..ef50abd557cd --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb_lmr.h @@ -0,0 +1,39 @@ +#ifndef _SELFTESTS_POWERPC_PMU_EBB_LMR_H +#define _SELFTESTS_POWERPC_PMU_EBB_LMR_H + +#include "reg.h" + +#ifndef PPC_FEATURE2_ARCH_3_00 +#define PPC_FEATURE2_ARCH_3_00 0x00800000 +#endif + +#define lmr_is_supported() have_hwcap2(PPC_FEATURE2_ARCH_3_00) + +static inline void ebb_lmr_reset(void) +{ + unsigned long bescr = mfspr(SPRN_BESCR); + bescr &= ~(BESCR_LMEO); + bescr |= BESCR_LME; + mtspr(SPRN_BESCR, bescr); +} + +#define LDMX(t, a, b)\ + (0x7c00026a | \ + (((t) & 0x1f) << 21) | \ + (((a) & 0x1f) << 16) | \ + (((b) & 0x1f) << 11)) + +static inline unsigned long ldmx(unsigned long address) +{ + unsigned long ret; + + asm volatile ("mr 9, %1\r\n" + ".long " __stringify(LDMX(9, 0, 9)) "\r\n" + "mr %0, 9\r\n":"=r"(ret) + :"r"(address) + :"r9"); + + return ret; +} + +#endif diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb_lmr_regs.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb_lmr_regs.c new file mode 100644 index 000000000000..aff4241fd88a --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb_lmr_regs.c @@ -0,0 +1,37 @@ +/* + * Copyright 2016, Jack Miller, IBM Corp. + * Licensed under GPLv2. + */ + +#include <stdlib.h> +#include <stdio.h> +#include <unistd.h> + +#include "ebb.h" +#include "ebb_lmr.h" + +#define CHECKS 10000 + +int ebb_lmr_regs(void) +{ + int i; + + SKIP_IF(!lmr_is_supported()); + + ebb_global_enable(); + + for (i = 0; i < CHECKS; i++) { + mtspr(SPRN_LMRR, i << 25); // skip size and rsvd bits + mtspr(SPRN_LMSER, i); + + FAIL_IF(mfspr(SPRN_LMRR) != (i << 25)); + FAIL_IF(mfspr(SPRN_LMSER) != i); + } + + return 0; +} + +int main(void) +{ + return test_harness(ebb_lmr_regs, "ebb_lmr_regs"); +} diff --git a/tools/testing/selftests/powerpc/pmu/ebb/instruction_count_test.c b/tools/testing/selftests/powerpc/pmu/ebb/instruction_count_test.c index 5da355135df2..ae9a79086111 100644 --- a/tools/testing/selftests/powerpc/pmu/ebb/instruction_count_test.c +++ b/tools/testing/selftests/powerpc/pmu/ebb/instruction_count_test.c @@ -51,7 +51,7 @@ static int do_count_loop(struct event *event, uint64_t instructions, printf("Looped for %lu instructions, overhead %lu\n", instructions, overhead); printf("Expected %lu\n", expected); printf("Actual %llu\n", event->result.value); - printf("Error %ld, %f%%\n", difference, percentage); + printf("Delta %ld, %f%%\n", difference, percentage); printf("Took %d EBBs\n", ebb_state.stats.ebb_count); } diff --git a/tools/testing/selftests/powerpc/pmu/lib.c b/tools/testing/selftests/powerpc/pmu/lib.c index a361ad3334ce..8b992fa5b478 100644 --- a/tools/testing/selftests/powerpc/pmu/lib.c +++ b/tools/testing/selftests/powerpc/pmu/lib.c @@ -190,7 +190,7 @@ int parse_proc_maps(void) bool require_paranoia_below(int level) { - unsigned long current; + long current; char *end, buf[16]; FILE *f; int rc; @@ -208,7 +208,7 @@ bool require_paranoia_below(int level) goto out_close; } - current = strtoul(buf, &end, 10); + current = strtol(buf, &end, 10); if (end == buf) { printf("Couldn't parse " PARANOID_PATH "?\n"); @@ -216,7 +216,7 @@ bool require_paranoia_below(int level) } if (current >= level) - goto out; + goto out_close; rc = 0; out_close: diff --git a/tools/testing/selftests/powerpc/reg.h b/tools/testing/selftests/powerpc/reg.h index 65bfdeeebdee..fddf368ed82f 100644 --- a/tools/testing/selftests/powerpc/reg.h +++ b/tools/testing/selftests/powerpc/reg.h @@ -34,6 +34,11 @@ #define BESCR_PMEO 0x1 /* PMU Event-based exception Occurred */ #define BESCR_PME (0x1ul << 32) /* PMU Event-based exception Enable */ +#define BESCR_LME (0x1ul << 34) /* Load Monitor Enable */ +#define BESCR_LMEO (0x1ul << 2) /* Load Monitor Exception Occurred */ + +#define SPRN_LMRR 813 /* Load Monitor Region Register */ +#define SPRN_LMSER 814 /* Load Monitor Section Enable Register */ #define SPRN_PMC1 771 #define SPRN_PMC2 772 diff --git a/tools/testing/selftests/powerpc/tm/.gitignore b/tools/testing/selftests/powerpc/tm/.gitignore index bb942db845bf..82c0a9ce6e74 100644 --- a/tools/testing/selftests/powerpc/tm/.gitignore +++ b/tools/testing/selftests/powerpc/tm/.gitignore @@ -6,3 +6,4 @@ tm-vmxcopy tm-fork tm-tar tm-tmspr +tm-exec diff --git a/tools/testing/selftests/powerpc/tm/Makefile b/tools/testing/selftests/powerpc/tm/Makefile index d0505dbd22d5..9d301d785d9e 100644 --- a/tools/testing/selftests/powerpc/tm/Makefile +++ b/tools/testing/selftests/powerpc/tm/Makefile @@ -1,11 +1,14 @@ -TEST_PROGS := tm-resched-dscr tm-syscall tm-signal-msr-resv tm-signal-stack tm-vmxcopy tm-fork tm-tar tm-tmspr +TEST_PROGS := tm-resched-dscr tm-syscall tm-signal-msr-resv tm-signal-stack \ + tm-vmxcopy tm-fork tm-tar tm-tmspr tm-exec tm-execed all: $(TEST_PROGS) $(TEST_PROGS): ../harness.c ../utils.c +CFLAGS += -mhtm + tm-syscall: tm-syscall-asm.S -tm-syscall: CFLAGS += -mhtm -I../../../../../usr/include +tm-syscall: CFLAGS += -I../../../../../usr/include tm-tmspr: CFLAGS += -pthread include ../../lib.mk diff --git a/tools/testing/selftests/powerpc/tm/tm-exec.c b/tools/testing/selftests/powerpc/tm/tm-exec.c new file mode 100644 index 000000000000..3d27fa0ece04 --- /dev/null +++ b/tools/testing/selftests/powerpc/tm/tm-exec.c @@ -0,0 +1,70 @@ +/* + * Copyright 2016, Cyril Bur, IBM Corp. + * + * 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. + * + * Syscalls can be performed provided the transactions are suspended. + * The exec() class of syscall is unique as a new process is loaded. + * + * It makes little sense for after an exec() call for the previously + * suspended transaction to still exist. + */ + +#define _GNU_SOURCE +#include <errno.h> +#include <inttypes.h> +#include <libgen.h> +#include <pthread.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> + +#include "utils.h" +#include "tm.h" + +static char *path; + +static int test_exec(void) +{ + SKIP_IF(!have_htm()); + + asm __volatile__( + "tbegin.;" + "blt 1f; " + "tsuspend.;" + "1: ;" + : : : "memory"); + + execl(path, "tm-exec", "--child", NULL); + + /* Shouldn't get here */ + perror("execl() failed"); + return 1; +} + +static int after_exec(void) +{ + asm __volatile__( + "tbegin.;" + "blt 1f;" + "tsuspend.;" + "1: ;" + : : : "memory"); + + FAIL_IF(failure_is_nesting()); + return 0; +} + +int main(int argc, char *argv[]) +{ + path = argv[0]; + + if (argc > 1 && strcmp(argv[1], "--child") == 0) + return after_exec(); + + return test_harness(test_exec, "tm_exec"); +} diff --git a/tools/testing/selftests/powerpc/tm/tm-syscall.c b/tools/testing/selftests/powerpc/tm/tm-syscall.c index 60560cb20e38..454b965a2db3 100644 --- a/tools/testing/selftests/powerpc/tm/tm-syscall.c +++ b/tools/testing/selftests/powerpc/tm/tm-syscall.c @@ -27,21 +27,6 @@ unsigned retries = 0; #define TEST_DURATION 10 /* seconds */ #define TM_RETRIES 100 -long failure_code(void) -{ - return __builtin_get_texasru() >> 24; -} - -bool failure_is_persistent(void) -{ - return (failure_code() & TM_CAUSE_PERSISTENT) == TM_CAUSE_PERSISTENT; -} - -bool failure_is_syscall(void) -{ - return (failure_code() & TM_CAUSE_SYSCALL) == TM_CAUSE_SYSCALL; -} - pid_t getppid_tm(bool suspend) { int i; diff --git a/tools/testing/selftests/powerpc/tm/tm.h b/tools/testing/selftests/powerpc/tm/tm.h index 24144b25772c..60318bad7d7a 100644 --- a/tools/testing/selftests/powerpc/tm/tm.h +++ b/tools/testing/selftests/powerpc/tm/tm.h @@ -6,8 +6,9 @@ #ifndef _SELFTESTS_POWERPC_TM_TM_H #define _SELFTESTS_POWERPC_TM_TM_H -#include <stdbool.h> +#include <asm/tm.h> #include <asm/cputable.h> +#include <stdbool.h> #include "../utils.h" @@ -31,4 +32,24 @@ static inline bool have_htm_nosc(void) #endif } +static inline long failure_code(void) +{ + return __builtin_get_texasru() >> 24; +} + +static inline bool failure_is_persistent(void) +{ + return (failure_code() & TM_CAUSE_PERSISTENT) == TM_CAUSE_PERSISTENT; +} + +static inline bool failure_is_syscall(void) +{ + return (failure_code() & TM_CAUSE_SYSCALL) == TM_CAUSE_SYSCALL; +} + +static inline bool failure_is_nesting(void) +{ + return (__builtin_get_texasru() & 0x400000); +} + #endif /* _SELFTESTS_POWERPC_TM_TM_H */ diff --git a/tools/testing/selftests/powerpc/utils.h b/tools/testing/selftests/powerpc/utils.h index a985cfaa535e..fbd33e52ef8f 100644 --- a/tools/testing/selftests/powerpc/utils.h +++ b/tools/testing/selftests/powerpc/utils.h @@ -27,6 +27,11 @@ int test_harness(int (test_function)(void), char *name); extern void *get_auxv_entry(int type); int pick_online_cpu(void); +static inline bool have_hwcap(unsigned long ftr) +{ + return ((unsigned long)get_auxv_entry(AT_HWCAP) & ftr) == ftr; +} + static inline bool have_hwcap2(unsigned long ftr2) { return ((unsigned long)get_auxv_entry(AT_HWCAP2) & ftr2) == ftr2; diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 2e58549b2f02..03f1fa495d74 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -1021,8 +1021,8 @@ void tracer_stop(int sig) typedef void tracer_func_t(struct __test_metadata *_metadata, pid_t tracee, int status, void *args); -void tracer(struct __test_metadata *_metadata, int fd, pid_t tracee, - tracer_func_t tracer_func, void *args) +void start_tracer(struct __test_metadata *_metadata, int fd, pid_t tracee, + tracer_func_t tracer_func, void *args, bool ptrace_syscall) { int ret = -1; struct sigaction action = { @@ -1042,12 +1042,16 @@ void tracer(struct __test_metadata *_metadata, int fd, pid_t tracee, /* Wait for attach stop */ wait(NULL); - ret = ptrace(PTRACE_SETOPTIONS, tracee, NULL, PTRACE_O_TRACESECCOMP); + ret = ptrace(PTRACE_SETOPTIONS, tracee, NULL, ptrace_syscall ? + PTRACE_O_TRACESYSGOOD : + PTRACE_O_TRACESECCOMP); ASSERT_EQ(0, ret) { TH_LOG("Failed to set PTRACE_O_TRACESECCOMP"); kill(tracee, SIGKILL); } - ptrace(PTRACE_CONT, tracee, NULL, 0); + ret = ptrace(ptrace_syscall ? PTRACE_SYSCALL : PTRACE_CONT, + tracee, NULL, 0); + ASSERT_EQ(0, ret); /* Unblock the tracee */ ASSERT_EQ(1, write(fd, "A", 1)); @@ -1063,12 +1067,13 @@ void tracer(struct __test_metadata *_metadata, int fd, pid_t tracee, /* Child is dead. Time to go. */ return; - /* Make sure this is a seccomp event. */ - ASSERT_EQ(true, IS_SECCOMP_EVENT(status)); + /* Check if this is a seccomp event. */ + ASSERT_EQ(!ptrace_syscall, IS_SECCOMP_EVENT(status)); tracer_func(_metadata, tracee, status, args); - ret = ptrace(PTRACE_CONT, tracee, NULL, NULL); + ret = ptrace(ptrace_syscall ? PTRACE_SYSCALL : PTRACE_CONT, + tracee, NULL, 0); ASSERT_EQ(0, ret); } /* Directly report the status of our test harness results. */ @@ -1079,7 +1084,7 @@ void tracer(struct __test_metadata *_metadata, int fd, pid_t tracee, void cont_handler(int num) { } pid_t setup_trace_fixture(struct __test_metadata *_metadata, - tracer_func_t func, void *args) + tracer_func_t func, void *args, bool ptrace_syscall) { char sync; int pipefd[2]; @@ -1095,7 +1100,8 @@ pid_t setup_trace_fixture(struct __test_metadata *_metadata, signal(SIGALRM, cont_handler); if (tracer_pid == 0) { close(pipefd[0]); - tracer(_metadata, pipefd[1], tracee, func, args); + start_tracer(_metadata, pipefd[1], tracee, func, args, + ptrace_syscall); syscall(__NR_exit, 0); } close(pipefd[1]); @@ -1177,7 +1183,7 @@ FIXTURE_SETUP(TRACE_poke) /* Launch tracer. */ self->tracer = setup_trace_fixture(_metadata, tracer_poke, - &self->tracer_args); + &self->tracer_args, false); } FIXTURE_TEARDOWN(TRACE_poke) @@ -1399,6 +1405,29 @@ void tracer_syscall(struct __test_metadata *_metadata, pid_t tracee, } +void tracer_ptrace(struct __test_metadata *_metadata, pid_t tracee, + int status, void *args) +{ + int ret, nr; + unsigned long msg; + static bool entry; + + /* Make sure we got an empty message. */ + ret = ptrace(PTRACE_GETEVENTMSG, tracee, NULL, &msg); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, msg); + + /* The only way to tell PTRACE_SYSCALL entry/exit is by counting. */ + entry = !entry; + if (!entry) + return; + + nr = get_syscall(_metadata, tracee); + + if (nr == __NR_getpid) + change_syscall(_metadata, tracee, __NR_getppid); +} + FIXTURE_DATA(TRACE_syscall) { struct sock_fprog prog; pid_t tracer, mytid, mypid, parent; @@ -1440,7 +1469,8 @@ FIXTURE_SETUP(TRACE_syscall) ASSERT_NE(self->parent, self->mypid); /* Launch tracer. */ - self->tracer = setup_trace_fixture(_metadata, tracer_syscall, NULL); + self->tracer = setup_trace_fixture(_metadata, tracer_syscall, NULL, + false); } FIXTURE_TEARDOWN(TRACE_syscall) @@ -1500,6 +1530,130 @@ TEST_F(TRACE_syscall, syscall_dropped) EXPECT_NE(self->mytid, syscall(__NR_gettid)); } +TEST_F(TRACE_syscall, skip_after_RET_TRACE) +{ + struct sock_filter filter[] = { + BPF_STMT(BPF_LD|BPF_W|BPF_ABS, + offsetof(struct seccomp_data, nr)), + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getppid, 0, 1), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ERRNO | EPERM), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), + }; + struct sock_fprog prog = { + .len = (unsigned short)ARRAY_SIZE(filter), + .filter = filter, + }; + long ret; + + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret); + + /* Install fixture filter. */ + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0); + ASSERT_EQ(0, ret); + + /* Install "errno on getppid" filter. */ + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0); + ASSERT_EQ(0, ret); + + /* Tracer will redirect getpid to getppid, and we should see EPERM. */ + EXPECT_EQ(-1, syscall(__NR_getpid)); + EXPECT_EQ(EPERM, errno); +} + +TEST_F_SIGNAL(TRACE_syscall, kill_after_RET_TRACE, SIGSYS) +{ + struct sock_filter filter[] = { + BPF_STMT(BPF_LD|BPF_W|BPF_ABS, + offsetof(struct seccomp_data, nr)), + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getppid, 0, 1), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), + }; + struct sock_fprog prog = { + .len = (unsigned short)ARRAY_SIZE(filter), + .filter = filter, + }; + long ret; + + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret); + + /* Install fixture filter. */ + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0); + ASSERT_EQ(0, ret); + + /* Install "death on getppid" filter. */ + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0); + ASSERT_EQ(0, ret); + + /* Tracer will redirect getpid to getppid, and we should die. */ + EXPECT_NE(self->mypid, syscall(__NR_getpid)); +} + +TEST_F(TRACE_syscall, skip_after_ptrace) +{ + struct sock_filter filter[] = { + BPF_STMT(BPF_LD|BPF_W|BPF_ABS, + offsetof(struct seccomp_data, nr)), + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getppid, 0, 1), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ERRNO | EPERM), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), + }; + struct sock_fprog prog = { + .len = (unsigned short)ARRAY_SIZE(filter), + .filter = filter, + }; + long ret; + + /* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */ + teardown_trace_fixture(_metadata, self->tracer); + self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL, + true); + + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret); + + /* Install "errno on getppid" filter. */ + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0); + ASSERT_EQ(0, ret); + + /* Tracer will redirect getpid to getppid, and we should see EPERM. */ + EXPECT_EQ(-1, syscall(__NR_getpid)); + EXPECT_EQ(EPERM, errno); +} + +TEST_F_SIGNAL(TRACE_syscall, kill_after_ptrace, SIGSYS) +{ + struct sock_filter filter[] = { + BPF_STMT(BPF_LD|BPF_W|BPF_ABS, + offsetof(struct seccomp_data, nr)), + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getppid, 0, 1), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), + }; + struct sock_fprog prog = { + .len = (unsigned short)ARRAY_SIZE(filter), + .filter = filter, + }; + long ret; + + /* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */ + teardown_trace_fixture(_metadata, self->tracer); + self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL, + true); + + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret); + + /* Install "death on getppid" filter. */ + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0); + ASSERT_EQ(0, ret); + + /* Tracer will redirect getpid to getppid, and we should die. */ + EXPECT_NE(self->mypid, syscall(__NR_getpid)); +} + #ifndef __NR_seccomp # if defined(__i386__) # define __NR_seccomp 354 diff --git a/tools/virtio/ringtest/Makefile b/tools/virtio/ringtest/Makefile index 6173adae9f08..877a8a4721b6 100644 --- a/tools/virtio/ringtest/Makefile +++ b/tools/virtio/ringtest/Makefile @@ -1,6 +1,6 @@ all: -all: ring virtio_ring_0_9 virtio_ring_poll virtio_ring_inorder noring +all: ring virtio_ring_0_9 virtio_ring_poll virtio_ring_inorder ptr_ring noring CFLAGS += -Wall CFLAGS += -pthread -O2 -ggdb @@ -8,6 +8,7 @@ LDFLAGS += -pthread -O2 -ggdb main.o: main.c main.h ring.o: ring.c main.h +ptr_ring.o: ptr_ring.c main.h ../../../include/linux/ptr_ring.h virtio_ring_0_9.o: virtio_ring_0_9.c main.h virtio_ring_poll.o: virtio_ring_poll.c virtio_ring_0_9.c main.h virtio_ring_inorder.o: virtio_ring_inorder.c virtio_ring_0_9.c main.h @@ -15,6 +16,7 @@ ring: ring.o main.o virtio_ring_0_9: virtio_ring_0_9.o main.o virtio_ring_poll: virtio_ring_poll.o main.o virtio_ring_inorder: virtio_ring_inorder.o main.o +ptr_ring: ptr_ring.o main.o noring: noring.o main.o clean: -rm main.o @@ -22,6 +24,7 @@ clean: -rm virtio_ring_0_9.o virtio_ring_0_9 -rm virtio_ring_poll.o virtio_ring_poll -rm virtio_ring_inorder.o virtio_ring_inorder + -rm ptr_ring.o ptr_ring -rm noring.o noring .PHONY: all clean diff --git a/tools/virtio/ringtest/ptr_ring.c b/tools/virtio/ringtest/ptr_ring.c new file mode 100644 index 000000000000..68e4f9f0da3a --- /dev/null +++ b/tools/virtio/ringtest/ptr_ring.c @@ -0,0 +1,197 @@ +#define _GNU_SOURCE +#include "main.h" +#include <stdlib.h> +#include <stdio.h> +#include <string.h> +#include <pthread.h> +#include <malloc.h> +#include <assert.h> +#include <errno.h> +#include <limits.h> + +#define SMP_CACHE_BYTES 64 +#define cache_line_size() SMP_CACHE_BYTES +#define ____cacheline_aligned_in_smp __attribute__ ((aligned (SMP_CACHE_BYTES))) +#define unlikely(x) (__builtin_expect(!!(x), 0)) +#define ALIGN(x, a) (((x) + (a) - 1) / (a) * (a)) +typedef pthread_spinlock_t spinlock_t; + +typedef int gfp_t; +static void *kmalloc(unsigned size, gfp_t gfp) +{ + return memalign(64, size); +} + +static void *kzalloc(unsigned size, gfp_t gfp) +{ + void *p = memalign(64, size); + if (!p) + return p; + memset(p, 0, size); + + return p; +} + +static void kfree(void *p) +{ + if (p) + free(p); +} + +static void spin_lock_init(spinlock_t *lock) +{ + int r = pthread_spin_init(lock, 0); + assert(!r); +} + +static void spin_lock(spinlock_t *lock) +{ + int ret = pthread_spin_lock(lock); + assert(!ret); +} + +static void spin_unlock(spinlock_t *lock) +{ + int ret = pthread_spin_unlock(lock); + assert(!ret); +} + +static void spin_lock_bh(spinlock_t *lock) +{ + spin_lock(lock); +} + +static void spin_unlock_bh(spinlock_t *lock) +{ + spin_unlock(lock); +} + +static void spin_lock_irq(spinlock_t *lock) +{ + spin_lock(lock); +} + +static void spin_unlock_irq(spinlock_t *lock) +{ + spin_unlock(lock); +} + +static void spin_lock_irqsave(spinlock_t *lock, unsigned long f) +{ + spin_lock(lock); +} + +static void spin_unlock_irqrestore(spinlock_t *lock, unsigned long f) +{ + spin_unlock(lock); +} + +#include "../../../include/linux/ptr_ring.h" + +static unsigned long long headcnt, tailcnt; +static struct ptr_ring array ____cacheline_aligned_in_smp; + +/* implemented by ring */ +void alloc_ring(void) +{ + int ret = ptr_ring_init(&array, ring_size, 0); + assert(!ret); +} + +/* guest side */ +int add_inbuf(unsigned len, void *buf, void *datap) +{ + int ret; + + ret = __ptr_ring_produce(&array, buf); + if (ret >= 0) { + ret = 0; + headcnt++; + } + + return ret; +} + +/* + * ptr_ring API provides no way for producer to find out whether a given + * buffer was consumed. Our tests merely require that a successful get_buf + * implies that add_inbuf succeed in the past, and that add_inbuf will succeed, + * fake it accordingly. + */ +void *get_buf(unsigned *lenp, void **bufp) +{ + void *datap; + + if (tailcnt == headcnt || __ptr_ring_full(&array)) + datap = NULL; + else { + datap = "Buffer\n"; + ++tailcnt; + } + + return datap; +} + +void poll_used(void) +{ + void *b; + + do { + if (tailcnt == headcnt || __ptr_ring_full(&array)) { + b = NULL; + barrier(); + } else { + b = "Buffer\n"; + } + } while (!b); +} + +void disable_call() +{ + assert(0); +} + +bool enable_call() +{ + assert(0); +} + +void kick_available(void) +{ + assert(0); +} + +/* host side */ +void disable_kick() +{ + assert(0); +} + +bool enable_kick() +{ + assert(0); +} + +void poll_avail(void) +{ + void *b; + + do { + barrier(); + b = __ptr_ring_peek(&array); + } while (!b); +} + +bool use_buf(unsigned *lenp, void **bufp) +{ + void *ptr; + + ptr = __ptr_ring_consume(&array); + + return ptr; +} + +void call_used(void) +{ + assert(0); +} diff --git a/tools/vm/page_owner_sort.c b/tools/vm/page_owner_sort.c index 77147b42d598..f1c055f3c243 100644 --- a/tools/vm/page_owner_sort.c +++ b/tools/vm/page_owner_sort.c @@ -79,12 +79,12 @@ static void add_list(char *buf, int len) } } -#define BUF_SIZE 1024 +#define BUF_SIZE (128 * 1024) int main(int argc, char **argv) { FILE *fin, *fout; - char buf[BUF_SIZE]; + char *buf; int ret, i, count; struct block_list *list2; struct stat st; @@ -107,6 +107,11 @@ int main(int argc, char **argv) max_size = st.st_size / 100; /* hack ... */ list = malloc(max_size * sizeof(*list)); + buf = malloc(BUF_SIZE); + if (!list || !buf) { + printf("Out of memory\n"); + exit(1); + } for ( ; ; ) { ret = read_block(buf, BUF_SIZE, fin); |
