aboutsummaryrefslogtreecommitdiffstats
path: root/tools
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2020-08-04 21:16:22 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2020-08-04 21:16:22 -0700
commit4da9f3302615f4191814f826054846bf843e24fa (patch)
tree52d9a697999df80eaae9c35cf57827d842138191 /tools
parentMerge tag 'x86-entry-2020-08-04' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip (diff)
parentx86/fsgsbase: Fix Xen PV support (diff)
downloadlinux-dev-4da9f3302615f4191814f826054846bf843e24fa.tar.xz
linux-dev-4da9f3302615f4191814f826054846bf843e24fa.zip
Merge tag 'x86-fsgsbase-2020-08-04' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 fsgsbase from Thomas Gleixner: "Support for FSGSBASE. Almost 5 years after the first RFC to support it, this has been brought into a shape which is maintainable and actually works. This final version was done by Sasha Levin who took it up after Intel dropped the ball. Sasha discovered that the SGX (sic!) offerings out there ship rogue kernel modules enabling FSGSBASE behind the kernels back which opens an instantanious unpriviledged root hole. The FSGSBASE instructions provide a considerable speedup of the context switch path and enable user space to write GSBASE without kernel interaction. This enablement requires careful handling of the exception entries which go through the paranoid entry path as they can no longer rely on the assumption that user GSBASE is positive (as enforced via prctl() on non FSGSBASE enabled systemn). All other entries (syscalls, interrupts and exceptions) can still just utilize SWAPGS unconditionally when the entry comes from user space. Converting these entries to use FSGSBASE has no benefit as SWAPGS is only marginally slower than WRGSBASE and locating and retrieving the kernel GSBASE value is not a free operation either. The real benefit of RD/WRGSBASE is the avoidance of the MSR reads and writes. The changes come with appropriate selftests and have held up in field testing against the (sanitized) Graphene-SGX driver" * tag 'x86-fsgsbase-2020-08-04' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (21 commits) x86/fsgsbase: Fix Xen PV support x86/ptrace: Fix 32-bit PTRACE_SETREGS vs fsbase and gsbase selftests/x86/fsgsbase: Add a missing memory constraint selftests/x86/fsgsbase: Fix a comment in the ptrace_write_gsbase test selftests/x86: Add a syscall_arg_fault_64 test for negative GSBASE selftests/x86/fsgsbase: Test ptracer-induced GS base write with FSGSBASE selftests/x86/fsgsbase: Test GS selector on ptracer-induced GS base write Documentation/x86/64: Add documentation for GS/FS addressing mode x86/elf: Enumerate kernel FSGSBASE capability in AT_HWCAP2 x86/cpu: Enable FSGSBASE on 64bit by default and add a chicken bit x86/entry/64: Handle FSGSBASE enabled paranoid entry/exit x86/entry/64: Introduce the FIND_PERCPU_BASE macro x86/entry/64: Switch CR3 before SWAPGS in paranoid entry x86/speculation/swapgs: Check FSGSBASE in enabling SWAPGS mitigation x86/process/64: Use FSGSBASE instructions on thread copy and ptrace x86/process/64: Use FSBSBASE in switch_to() if available x86/process/64: Make save_fsgs_for_kvm() ready for FSGSBASE x86/fsgsbase/64: Enable FSGSBASE instructions in helper functions x86/fsgsbase/64: Add intrinsics for FSGSBASE instructions x86/cpu: Add 'unsafe_fsgsbase' to enable CR4.FSGSBASE ...
Diffstat (limited to 'tools')
-rw-r--r--tools/testing/selftests/x86/Makefile2
-rw-r--r--tools/testing/selftests/x86/fsgsbase.c28
-rw-r--r--tools/testing/selftests/x86/fsgsbase_restore.c245
-rw-r--r--tools/testing/selftests/x86/syscall_arg_fault.c26
4 files changed, 295 insertions, 6 deletions
diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index d2796ea98c5a..6703c7906b71 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -13,7 +13,7 @@ CAN_BUILD_WITH_NOPIE := $(shell ./check_cc.sh $(CC) trivial_program.c -no-pie)
TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt test_mremap_vdso \
check_initial_reg_state sigreturn iopl ioperm \
test_vdso test_vsyscall mov_ss_trap \
- syscall_arg_fault
+ syscall_arg_fault fsgsbase_restore
TARGETS_C_32BIT_ONLY := entry_from_vm86 test_syscall_vdso unwind_vdso \
test_FCMOV test_FCOMI test_FISTTP \
vdso_restorer
diff --git a/tools/testing/selftests/x86/fsgsbase.c b/tools/testing/selftests/x86/fsgsbase.c
index 15a329da59fa..998319553523 100644
--- a/tools/testing/selftests/x86/fsgsbase.c
+++ b/tools/testing/selftests/x86/fsgsbase.c
@@ -285,7 +285,8 @@ static unsigned short load_gs(void)
/* 32-bit set_thread_area */
long ret;
asm volatile ("int $0x80"
- : "=a" (ret) : "a" (243), "b" (low_desc)
+ : "=a" (ret), "+m" (*low_desc)
+ : "a" (243), "b" (low_desc)
: "r8", "r9", "r10", "r11");
memcpy(&desc, low_desc, sizeof(desc));
munmap(low_desc, sizeof(desc));
@@ -489,11 +490,28 @@ static void test_ptrace_write_gsbase(void)
* selector value is changed or not by the GSBASE write in
* a ptracer.
*/
- if (gs == 0 && base == 0xFF) {
- printf("[OK]\tGS was reset as expected\n");
- } else {
+ if (gs != *shared_scratch) {
nerrs++;
- printf("[FAIL]\tGS=0x%lx, GSBASE=0x%lx (should be 0, 0xFF)\n", gs, base);
+ printf("[FAIL]\tGS changed to %lx\n", gs);
+
+ /*
+ * On older kernels, poking a nonzero value into the
+ * base would zero the selector. On newer kernels,
+ * this behavior has changed -- poking the base
+ * changes only the base and, if FSGSBASE is not
+ * available, this may have no effect once the tracee
+ * is resumed.
+ */
+ if (gs == 0)
+ printf("\tNote: this is expected behavior on older kernels.\n");
+ } else if (have_fsgsbase && (base != 0xFF)) {
+ nerrs++;
+ printf("[FAIL]\tGSBASE changed to %lx\n", base);
+ } else {
+ printf("[OK]\tGS remained 0x%hx", *shared_scratch);
+ if (have_fsgsbase)
+ printf(" and GSBASE changed to 0xFF");
+ printf("\n");
}
}
diff --git a/tools/testing/selftests/x86/fsgsbase_restore.c b/tools/testing/selftests/x86/fsgsbase_restore.c
new file mode 100644
index 000000000000..6fffadc51579
--- /dev/null
+++ b/tools/testing/selftests/x86/fsgsbase_restore.c
@@ -0,0 +1,245 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * fsgsbase_restore.c, test ptrace vs fsgsbase
+ * Copyright (c) 2020 Andy Lutomirski
+ *
+ * This test case simulates a tracer redirecting tracee execution to
+ * a function and then restoring tracee state using PTRACE_GETREGS and
+ * PTRACE_SETREGS. This is similar to what gdb does when doing
+ * 'p func()'. The catch is that this test has the called function
+ * modify a segment register. This makes sure that ptrace correctly
+ * restores segment state when using PTRACE_SETREGS.
+ *
+ * This is not part of fsgsbase.c, because that test is 64-bit only.
+ */
+
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <string.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+#include <err.h>
+#include <sys/user.h>
+#include <asm/prctl.h>
+#include <sys/prctl.h>
+#include <asm/ldt.h>
+#include <sys/mman.h>
+#include <stddef.h>
+#include <sys/ptrace.h>
+#include <sys/wait.h>
+#include <stdint.h>
+
+#define EXPECTED_VALUE 0x1337f00d
+
+#ifdef __x86_64__
+# define SEG "%gs"
+#else
+# define SEG "%fs"
+#endif
+
+static unsigned int dereference_seg_base(void)
+{
+ int ret;
+ asm volatile ("mov %" SEG ":(0), %0" : "=rm" (ret));
+ return ret;
+}
+
+static void init_seg(void)
+{
+ unsigned int *target = mmap(
+ NULL, sizeof(unsigned int),
+ PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS | MAP_32BIT, -1, 0);
+ if (target == MAP_FAILED)
+ err(1, "mmap");
+
+ *target = EXPECTED_VALUE;
+
+ printf("\tsegment base address = 0x%lx\n", (unsigned long)target);
+
+ struct user_desc desc = {
+ .entry_number = 0,
+ .base_addr = (unsigned int)(uintptr_t)target,
+ .limit = sizeof(unsigned int) - 1,
+ .seg_32bit = 1,
+ .contents = 0, /* Data, grow-up */
+ .read_exec_only = 0,
+ .limit_in_pages = 0,
+ .seg_not_present = 0,
+ .useable = 0
+ };
+ if (syscall(SYS_modify_ldt, 1, &desc, sizeof(desc)) == 0) {
+ printf("\tusing LDT slot 0\n");
+ asm volatile ("mov %0, %" SEG :: "rm" ((unsigned short)0x7));
+ } else {
+ /* No modify_ldt for us (configured out, perhaps) */
+
+ struct user_desc *low_desc = mmap(
+ NULL, sizeof(desc),
+ PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS | MAP_32BIT, -1, 0);
+ memcpy(low_desc, &desc, sizeof(desc));
+
+ low_desc->entry_number = -1;
+
+ /* 32-bit set_thread_area */
+ long ret;
+ asm volatile ("int $0x80"
+ : "=a" (ret), "+m" (*low_desc)
+ : "a" (243), "b" (low_desc)
+#ifdef __x86_64__
+ : "r8", "r9", "r10", "r11"
+#endif
+ );
+ memcpy(&desc, low_desc, sizeof(desc));
+ munmap(low_desc, sizeof(desc));
+
+ if (ret != 0) {
+ printf("[NOTE]\tcould not create a segment -- can't test anything\n");
+ exit(0);
+ }
+ printf("\tusing GDT slot %d\n", desc.entry_number);
+
+ unsigned short sel = (unsigned short)((desc.entry_number << 3) | 0x3);
+ asm volatile ("mov %0, %" SEG :: "rm" (sel));
+ }
+}
+
+static void tracee_zap_segment(void)
+{
+ /*
+ * The tracer will redirect execution here. This is meant to
+ * work like gdb's 'p func()' feature. The tricky bit is that
+ * we modify a segment register in order to make sure that ptrace
+ * can correctly restore segment registers.
+ */
+ printf("\tTracee: in tracee_zap_segment()\n");
+
+ /*
+ * Write a nonzero selector with base zero to the segment register.
+ * Using a null selector would defeat the test on AMD pre-Zen2
+ * CPUs, as such CPUs don't clear the base when loading a null
+ * selector.
+ */
+ unsigned short sel;
+ asm volatile ("mov %%ss, %0\n\t"
+ "mov %0, %" SEG
+ : "=rm" (sel));
+
+ pid_t pid = getpid(), tid = syscall(SYS_gettid);
+
+ printf("\tTracee is going back to sleep\n");
+ syscall(SYS_tgkill, pid, tid, SIGSTOP);
+
+ /* Should not get here. */
+ while (true) {
+ printf("[FAIL]\tTracee hit unreachable code\n");
+ pause();
+ }
+}
+
+int main()
+{
+ printf("\tSetting up a segment\n");
+ init_seg();
+
+ unsigned int val = dereference_seg_base();
+ if (val != EXPECTED_VALUE) {
+ printf("[FAIL]\tseg[0] == %x; should be %x\n", val, EXPECTED_VALUE);
+ return 1;
+ }
+ printf("[OK]\tThe segment points to the right place.\n");
+
+ pid_t chld = fork();
+ if (chld < 0)
+ err(1, "fork");
+
+ if (chld == 0) {
+ prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0, 0);
+
+ if (ptrace(PTRACE_TRACEME, 0, 0, 0) != 0)
+ err(1, "PTRACE_TRACEME");
+
+ pid_t pid = getpid(), tid = syscall(SYS_gettid);
+
+ printf("\tTracee will take a nap until signaled\n");
+ syscall(SYS_tgkill, pid, tid, SIGSTOP);
+
+ printf("\tTracee was resumed. Will re-check segment.\n");
+
+ val = dereference_seg_base();
+ if (val != EXPECTED_VALUE) {
+ printf("[FAIL]\tseg[0] == %x; should be %x\n", val, EXPECTED_VALUE);
+ exit(1);
+ }
+
+ printf("[OK]\tThe segment points to the right place.\n");
+ exit(0);
+ }
+
+ int status;
+
+ /* Wait for SIGSTOP. */
+ if (waitpid(chld, &status, 0) != chld || !WIFSTOPPED(status))
+ err(1, "waitpid");
+
+ struct user_regs_struct regs;
+
+ if (ptrace(PTRACE_GETREGS, chld, NULL, &regs) != 0)
+ err(1, "PTRACE_GETREGS");
+
+#ifdef __x86_64__
+ printf("\tChild GS=0x%lx, GSBASE=0x%lx\n", (unsigned long)regs.gs, (unsigned long)regs.gs_base);
+#else
+ printf("\tChild FS=0x%lx\n", (unsigned long)regs.xfs);
+#endif
+
+ struct user_regs_struct regs2 = regs;
+#ifdef __x86_64__
+ regs2.rip = (unsigned long)tracee_zap_segment;
+ regs2.rsp -= 128; /* Don't clobber the redzone. */
+#else
+ regs2.eip = (unsigned long)tracee_zap_segment;
+#endif
+
+ printf("\tTracer: redirecting tracee to tracee_zap_segment()\n");
+ if (ptrace(PTRACE_SETREGS, chld, NULL, &regs2) != 0)
+ err(1, "PTRACE_GETREGS");
+ if (ptrace(PTRACE_CONT, chld, NULL, NULL) != 0)
+ err(1, "PTRACE_GETREGS");
+
+ /* Wait for SIGSTOP. */
+ if (waitpid(chld, &status, 0) != chld || !WIFSTOPPED(status))
+ err(1, "waitpid");
+
+ printf("\tTracer: restoring tracee state\n");
+ if (ptrace(PTRACE_SETREGS, chld, NULL, &regs) != 0)
+ err(1, "PTRACE_GETREGS");
+ if (ptrace(PTRACE_DETACH, chld, NULL, NULL) != 0)
+ err(1, "PTRACE_GETREGS");
+
+ /* Wait for SIGSTOP. */
+ if (waitpid(chld, &status, 0) != chld)
+ err(1, "waitpid");
+
+ if (WIFSIGNALED(status)) {
+ printf("[FAIL]\tTracee crashed\n");
+ return 1;
+ }
+
+ if (!WIFEXITED(status)) {
+ printf("[FAIL]\tTracee stopped for an unexpected reason: %d\n", status);
+ return 1;
+ }
+
+ int exitcode = WEXITSTATUS(status);
+ if (exitcode != 0) {
+ printf("[FAIL]\tTracee reported failure\n");
+ return 1;
+ }
+
+ printf("[OK]\tAll is well.\n");
+ return 0;
+}
diff --git a/tools/testing/selftests/x86/syscall_arg_fault.c b/tools/testing/selftests/x86/syscall_arg_fault.c
index 5b7abebbcbb9..bff474b5efc6 100644
--- a/tools/testing/selftests/x86/syscall_arg_fault.c
+++ b/tools/testing/selftests/x86/syscall_arg_fault.c
@@ -53,6 +53,7 @@ static void sigsegv_or_sigbus(int sig, siginfo_t *info, void *ctx_void)
if (ax != -EFAULT && ax != -ENOSYS) {
printf("[FAIL]\tAX had the wrong value: 0x%lx\n",
(unsigned long)ax);
+ printf("\tIP = 0x%lx\n", (unsigned long)ctx->uc_mcontext.gregs[REG_IP]);
n_errs++;
} else {
printf("[OK]\tSeems okay\n");
@@ -207,5 +208,30 @@ int main()
}
set_eflags(get_eflags() & ~X86_EFLAGS_TF);
+#ifdef __x86_64__
+ printf("[RUN]\tSYSENTER with TF, invalid state, and GSBASE < 0\n");
+
+ if (sigsetjmp(jmpbuf, 1) == 0) {
+ sigtrap_consecutive_syscalls = 0;
+
+ asm volatile ("wrgsbase %%rax\n\t"
+ :: "a" (0xffffffffffff0000UL));
+
+ set_eflags(get_eflags() | X86_EFLAGS_TF);
+ asm volatile (
+ "movl $-1, %%eax\n\t"
+ "movl $-1, %%ebx\n\t"
+ "movl $-1, %%ecx\n\t"
+ "movl $-1, %%edx\n\t"
+ "movl $-1, %%esi\n\t"
+ "movl $-1, %%edi\n\t"
+ "movl $-1, %%ebp\n\t"
+ "movl $-1, %%esp\n\t"
+ "sysenter"
+ : : : "memory", "flags");
+ }
+ set_eflags(get_eflags() & ~X86_EFLAGS_TF);
+#endif
+
return 0;
}