Merge tag 'x86-fpu-2021-07-07' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 fpu updates from Thomas Gleixner:
 "Fixes and improvements for FPU handling on x86:

   - Prevent sigaltstack out of bounds writes.

     The kernel unconditionally writes the FPU state to the alternate
     stack without checking whether the stack is large enough to
     accomodate it.

     Check the alternate stack size before doing so and in case it's too
     small force a SIGSEGV instead of silently corrupting user space
     data.

   - MINSIGSTKZ and SIGSTKSZ are constants in signal.h and have never
     been updated despite the fact that the FPU state which is stored on
     the signal stack has grown over time which causes trouble in the
     field when AVX512 is available on a CPU. The kernel does not expose
     the minimum requirements for the alternate stack size depending on
     the available and enabled CPU features.

     ARM already added an aux vector AT_MINSIGSTKSZ for the same reason.
     Add it to x86 as well.

   - A major cleanup of the x86 FPU code. The recent discoveries of
     XSTATE related issues unearthed quite some inconsistencies,
     duplicated code and other issues.

     The fine granular overhaul addresses this, makes the code more
     robust and maintainable, which allows to integrate upcoming XSTATE
     related features in sane ways"

* tag 'x86-fpu-2021-07-07' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (74 commits)
  x86/fpu/xstate: Clear xstate header in copy_xstate_to_uabi_buf() again
  x86/fpu/signal: Let xrstor handle the features to init
  x86/fpu/signal: Handle #PF in the direct restore path
  x86/fpu: Return proper error codes from user access functions
  x86/fpu/signal: Split out the direct restore code
  x86/fpu/signal: Sanitize copy_user_to_fpregs_zeroing()
  x86/fpu/signal: Sanitize the xstate check on sigframe
  x86/fpu/signal: Remove the legacy alignment check
  x86/fpu/signal: Move initial checks into fpu__restore_sig()
  x86/fpu: Mark init_fpstate __ro_after_init
  x86/pkru: Remove xstate fiddling from write_pkru()
  x86/fpu: Don't store PKRU in xstate in fpu_reset_fpstate()
  x86/fpu: Remove PKRU handling from switch_fpu_finish()
  x86/fpu: Mask PKRU from kernel XRSTOR[S] operations
  x86/fpu: Hook up PKRU into ptrace()
  x86/fpu: Add PKRU storage outside of task XSAVE buffer
  x86/fpu: Dont restore PKRU in fpregs_restore_userspace()
  x86/fpu: Rename xfeatures_mask_user() to xfeatures_mask_uabi()
  x86/fpu: Move FXSAVE_LEAK quirk info __copy_kernel_to_fpregs()
  x86/fpu: Rename __fpregs_load_activate() to fpregs_restore_userregs()
  ...

4 files changed, 260 insertions, 7 deletions

diff --git a/tools/testing/selftests/sigaltstack/sas.c b/tools/testing/selftests/sigaltstack/sas.c
index 8934a3766d20..c53b070755b6 100644
--- a/tools/testing/selftests/sigaltstack/sas.c
+++ b/tools/testing/selftests/sigaltstack/sas.c
@@ -17,6 +17,7 @@
 #include <string.h>
 #include <assert.h>
 #include <errno.h>
+#include <sys/auxv.h>
 
 #include "../kselftest.h"
 
@@ -24,6 +25,11 @@
 #define SS_AUTODISARM  (1U << 31)
 #endif
 
+#ifndef AT_MINSIGSTKSZ
+#define AT_MINSIGSTKSZ	51
+#endif
+
+static unsigned int stack_size;
 static void *sstack, *ustack;
 static ucontext_t uc, sc;
 static const char *msg = "[OK]\tStack preserved";
@@ -47,7 +53,7 @@ void my_usr1(int sig, siginfo_t *si, void *u)
 #endif
 
 	if (sp < (unsigned long)sstack ||
-			sp >= (unsigned long)sstack + SIGSTKSZ) {
+			sp >= (unsigned long)sstack + stack_size) {
 		ksft_exit_fail_msg("SP is not on sigaltstack\n");
 	}
 	/* put some data on stack. other sighandler will try to overwrite it */
@@ -108,6 +114,10 @@ int main(void)
 	stack_t stk;
 	int err;
 
+	/* Make sure more than the required minimum. */
+	stack_size = getauxval(AT_MINSIGSTKSZ) + SIGSTKSZ;
+	ksft_print_msg("[NOTE]\tthe stack size is %lu\n", stack_size);
+
 	ksft_print_header();
 	ksft_set_plan(3);
 
@@ -117,7 +127,7 @@ int main(void)
 	sigaction(SIGUSR1, &act, NULL);
 	act.sa_sigaction = my_usr2;
 	sigaction(SIGUSR2, &act, NULL);
-	sstack = mmap(NULL, SIGSTKSZ, PROT_READ | PROT_WRITE,
+	sstack = mmap(NULL, stack_size, PROT_READ | PROT_WRITE,
 		      MAP_PRIVATE | MAP_ANONYMOUS | MAP_STACK, -1, 0);
 	if (sstack == MAP_FAILED) {
 		ksft_exit_fail_msg("mmap() - %s\n", strerror(errno));
@@ -139,7 +149,7 @@ int main(void)
 	}
 
 	stk.ss_sp = sstack;
-	stk.ss_size = SIGSTKSZ;
+	stk.ss_size = stack_size;
 	stk.ss_flags = SS_ONSTACK | SS_AUTODISARM;
 	err = sigaltstack(&stk, NULL);
 	if (err) {
@@ -161,7 +171,7 @@ int main(void)
 		}
 	}
 
-	ustack = mmap(NULL, SIGSTKSZ, PROT_READ | PROT_WRITE,
+	ustack = mmap(NULL, stack_size, PROT_READ | PROT_WRITE,
 		      MAP_PRIVATE | MAP_ANONYMOUS | MAP_STACK, -1, 0);
 	if (ustack == MAP_FAILED) {
 		ksft_exit_fail_msg("mmap() - %s\n", strerror(errno));
@@ -170,7 +180,7 @@ int main(void)
 	getcontext(&uc);
 	uc.uc_link = NULL;
 	uc.uc_stack.ss_sp = ustack;
-	uc.uc_stack.ss_size = SIGSTKSZ;
+	uc.uc_stack.ss_size = stack_size;
 	makecontext(&uc, switch_fn, 0);
 	raise(SIGUSR1);
 
diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index 333980375bc7..b4142cd1c5c2 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -13,11 +13,12 @@ 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_vsyscall mov_ss_trap \
-			syscall_arg_fault fsgsbase_restore
+			syscall_arg_fault fsgsbase_restore sigaltstack
 TARGETS_C_32BIT_ONLY := entry_from_vm86 test_syscall_vdso unwind_vdso \
 			test_FCMOV test_FCOMI test_FISTTP \
 			vdso_restorer
-TARGETS_C_64BIT_ONLY := fsgsbase sysret_rip syscall_numbering
+TARGETS_C_64BIT_ONLY := fsgsbase sysret_rip syscall_numbering \
+			corrupt_xstate_header
 # Some selftests require 32bit support enabled also on 64bit systems
 TARGETS_C_32BIT_NEEDED := ldt_gdt ptrace_syscall
 
diff --git a/tools/testing/selftests/x86/corrupt_xstate_header.c b/tools/testing/selftests/x86/corrupt_xstate_header.c
new file mode 100644
index 000000000000..ab8599c10ce5
--- /dev/null
+++ b/tools/testing/selftests/x86/corrupt_xstate_header.c
@@ -0,0 +1,114 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Corrupt the XSTATE header in a signal frame
+ *
+ * Based on analysis and a test case from Thomas Gleixner.
+ */
+
+#define _GNU_SOURCE
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <sched.h>
+#include <signal.h>
+#include <err.h>
+#include <unistd.h>
+#include <stdint.h>
+#include <sys/wait.h>
+
+static inline void __cpuid(unsigned int *eax, unsigned int *ebx,
+			   unsigned int *ecx, unsigned int *edx)
+{
+	asm volatile(
+		"cpuid;"
+		: "=a" (*eax),
+		  "=b" (*ebx),
+		  "=c" (*ecx),
+		  "=d" (*edx)
+		: "0" (*eax), "2" (*ecx));
+}
+
+static inline int xsave_enabled(void)
+{
+	unsigned int eax, ebx, ecx, edx;
+
+	eax = 0x1;
+	ecx = 0x0;
+	__cpuid(&eax, &ebx, &ecx, &edx);
+
+	/* Is CR4.OSXSAVE enabled ? */
+	return ecx & (1U << 27);
+}
+
+static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
+		       int flags)
+{
+	struct sigaction sa;
+
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_sigaction = handler;
+	sa.sa_flags = SA_SIGINFO | flags;
+	sigemptyset(&sa.sa_mask);
+	if (sigaction(sig, &sa, 0))
+		err(1, "sigaction");
+}
+
+static void sigusr1(int sig, siginfo_t *info, void *uc_void)
+{
+	ucontext_t *uc = uc_void;
+	uint8_t *fpstate = (uint8_t *)uc->uc_mcontext.fpregs;
+	uint64_t *xfeatures = (uint64_t *)(fpstate + 512);
+
+	printf("\tWreck XSTATE header\n");
+	/* Wreck the first reserved bytes in the header */
+	*(xfeatures + 2) = 0xfffffff;
+}
+
+static void sigsegv(int sig, siginfo_t *info, void *uc_void)
+{
+	printf("\tGot SIGSEGV\n");
+}
+
+int main(void)
+{
+	cpu_set_t set;
+
+	sethandler(SIGUSR1, sigusr1, 0);
+	sethandler(SIGSEGV, sigsegv, 0);
+
+	if (!xsave_enabled()) {
+		printf("[SKIP] CR4.OSXSAVE disabled.\n");
+		return 0;
+	}
+
+	CPU_ZERO(&set);
+	CPU_SET(0, &set);
+
+	/*
+	 * Enforce that the child runs on the same CPU
+	 * which in turn forces a schedule.
+	 */
+	sched_setaffinity(getpid(), sizeof(set), &set);
+
+	printf("[RUN]\tSend ourselves a signal\n");
+	raise(SIGUSR1);
+
+	printf("[OK]\tBack from the signal.  Now schedule.\n");
+	pid_t child = fork();
+	if (child < 0)
+		err(1, "fork");
+	if (child == 0)
+		return 0;
+	if (child)
+		waitpid(child, NULL, 0);
+	printf("[OK]\tBack in the main thread.\n");
+
+	/*
+	 * We could try to confirm that extended state is still preserved
+	 * when we schedule.  For now, the only indication of failure is
+	 * a warning in the kernel logs.
+	 */
+
+	return 0;
+}
diff --git a/tools/testing/selftests/x86/sigaltstack.c b/tools/testing/selftests/x86/sigaltstack.c
new file mode 100644
index 000000000000..f689af75e979
--- /dev/null
+++ b/tools/testing/selftests/x86/sigaltstack.c
@@ -0,0 +1,128 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#define _GNU_SOURCE
+#include <signal.h>
+#include <stdio.h>
+#include <stdbool.h>
+#include <string.h>
+#include <err.h>
+#include <errno.h>
+#include <limits.h>
+#include <sys/mman.h>
+#include <sys/auxv.h>
+#include <sys/prctl.h>
+#include <sys/resource.h>
+#include <setjmp.h>
+
+/* sigaltstack()-enforced minimum stack */
+#define ENFORCED_MINSIGSTKSZ	2048
+
+#ifndef AT_MINSIGSTKSZ
+#  define AT_MINSIGSTKSZ	51
+#endif
+
+static int nerrs;
+
+static bool sigalrm_expected;
+
+static unsigned long at_minstack_size;
+
+static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
+		       int flags)
+{
+	struct sigaction sa;
+
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_sigaction = handler;
+	sa.sa_flags = SA_SIGINFO | flags;
+	sigemptyset(&sa.sa_mask);
+	if (sigaction(sig, &sa, 0))
+		err(1, "sigaction");
+}
+
+static void clearhandler(int sig)
+{
+	struct sigaction sa;
+
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_handler = SIG_DFL;
+	sigemptyset(&sa.sa_mask);
+	if (sigaction(sig, &sa, 0))
+		err(1, "sigaction");
+}
+
+static int setup_altstack(void *start, unsigned long size)
+{
+	stack_t ss;
+
+	memset(&ss, 0, sizeof(ss));
+	ss.ss_size = size;
+	ss.ss_sp = start;
+
+	return sigaltstack(&ss, NULL);
+}
+
+static jmp_buf jmpbuf;
+
+static void sigsegv(int sig, siginfo_t *info, void *ctx_void)
+{
+	if (sigalrm_expected) {
+		printf("[FAIL]\tWrong signal delivered: SIGSEGV (expected SIGALRM).");
+		nerrs++;
+	} else {
+		printf("[OK]\tSIGSEGV signal delivered.\n");
+	}
+
+	siglongjmp(jmpbuf, 1);
+}
+
+static void sigalrm(int sig, siginfo_t *info, void *ctx_void)
+{
+	if (!sigalrm_expected) {
+		printf("[FAIL]\tWrong signal delivered: SIGALRM (expected SIGSEGV).");
+		nerrs++;
+	} else {
+		printf("[OK]\tSIGALRM signal delivered.\n");
+	}
+}
+
+static void test_sigaltstack(void *altstack, unsigned long size)
+{
+	if (setup_altstack(altstack, size))
+		err(1, "sigaltstack()");
+
+	sigalrm_expected = (size > at_minstack_size) ? true : false;
+
+	sethandler(SIGSEGV, sigsegv, 0);
+	sethandler(SIGALRM, sigalrm, SA_ONSTACK);
+
+	if (!sigsetjmp(jmpbuf, 1)) {
+		printf("[RUN]\tTest an alternate signal stack of %ssufficient size.\n",
+		       sigalrm_expected ? "" : "in");
+		printf("\tRaise SIGALRM. %s is expected to be delivered.\n",
+		       sigalrm_expected ? "It" : "SIGSEGV");
+		raise(SIGALRM);
+	}
+
+	clearhandler(SIGALRM);
+	clearhandler(SIGSEGV);
+}
+
+int main(void)
+{
+	void *altstack;
+
+	at_minstack_size = getauxval(AT_MINSIGSTKSZ);
+
+	altstack = mmap(NULL, at_minstack_size + SIGSTKSZ, PROT_READ | PROT_WRITE,
+			MAP_PRIVATE | MAP_ANONYMOUS | MAP_STACK, -1, 0);
+	if (altstack == MAP_FAILED)
+		err(1, "mmap()");
+
+	if ((ENFORCED_MINSIGSTKSZ + 1) < at_minstack_size)
+		test_sigaltstack(altstack, ENFORCED_MINSIGSTKSZ + 1);
+
+	test_sigaltstack(altstack, at_minstack_size + SIGSTKSZ);
+
+	return nerrs == 0 ? 0 : 1;
+}