Merge tag 'x86_fpu_for_6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 fpu updates from Dave Hansen:
 "There are two little fixes in here, one to give better XSAVE warnings
  and another to address some undefined behavior in offsetof().

  There is also a collection of patches to fix some issues with ptrace
  and the protection keys register (PKRU). PKRU is a real oddity because
  it is exposed in the XSAVE-related ABIs, but it is generally managed
  without using XSAVE in the kernel. This fix thankfully came with a
  selftest to ward off future regressions.

  Summary:

   - Clarify XSAVE consistency warnings

   - Fix up ptrace interface to protection keys register (PKRU)

   - Avoid undefined compiler behavior with TYPE_ALIGN"

* tag 'x86_fpu_for_6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/fpu: Use _Alignof to avoid undefined behavior in TYPE_ALIGN
  selftests/vm/pkeys: Add a regression test for setting PKRU through ptrace
  x86/fpu: Emulate XRSTOR's behavior if the xfeatures PKRU bit is not set
  x86/fpu: Allow PKRU to be (once again) written by ptrace.
  x86/fpu: Add a pkru argument to copy_uabi_to_xstate()
  x86/fpu: Add a pkru argument to copy_uabi_from_kernel_to_xstate().
  x86/fpu: Take task_struct* in copy_sigframe_from_user_to_xstate()
  x86/fpu/xstate: Fix XSTATE_WARN_ON() to emit relevant diagnostics

Author: torvalds

arch/x86/kernel/fpu/core.c

@@ -391,8 +391,6 @@ int fpu_copy_uabi_to_guest_fpstate(struct fpu_guest *gfpu, const void *buf,
 {
 	struct fpstate *kstate = gfpu->fpstate;
 	const union fpregs_state *ustate = buf;
-	struct pkru_state *xpkru;
-	int ret;
 
 	if (!cpu_feature_enabled(X86_FEATURE_XSAVE)) {
 		if (ustate->xsave.header.xfeatures & ~XFEATURE_MASK_FPSSE)
@@ -406,16 +404,15 @@ int fpu_copy_uabi_to_guest_fpstate(struct fpu_guest *gfpu, const void *buf,
 	if (ustate->xsave.header.xfeatures & ~xcr0)
 		return -EINVAL;
 
-	ret = copy_uabi_from_kernel_to_xstate(kstate, ustate);
-	if (ret)
-		return ret;
+	/*
+	 * Nullify @vpkru to preserve its current value if PKRU's bit isn't set
+	 * in the header.  KVM's odd ABI is to leave PKRU untouched in this
+	 * case (all other components are eventually re-initialized).
+	 */
+	if (!(ustate->xsave.header.xfeatures & XFEATURE_MASK_PKRU))
+		vpkru = NULL;
 
-	/* Retrieve PKRU if not in init state */
-	if (kstate->regs.xsave.header.xfeatures & XFEATURE_MASK_PKRU) {
-		xpkru = get_xsave_addr(&kstate->regs.xsave, XFEATURE_PKRU);
-		*vpkru = xpkru->pkru;
-	}
-	return 0;
+	return copy_uabi_from_kernel_to_xstate(kstate, ustate, vpkru);
 }
 EXPORT_SYMBOL_GPL(fpu_copy_uabi_to_guest_fpstate);
 #endif /* CONFIG_KVM */

arch/x86/kernel/fpu/init.c

@@ -133,18 +133,15 @@ static void __init fpu__init_system_generic(void)
 	fpu__init_system_mxcsr();
 }
 
-/* Get alignment of the TYPE. */
-#define TYPE_ALIGN(TYPE) offsetof(struct { char x; TYPE test; }, test)
-
 /*
  * Enforce that 'MEMBER' is the last field of 'TYPE'.
  *
  * Align the computed size with alignment of the TYPE,
  * because that's how C aligns structs.
  */
 #define CHECK_MEMBER_AT_END_OF(TYPE, MEMBER) \
-	BUILD_BUG_ON(sizeof(TYPE) != ALIGN(offsetofend(TYPE, MEMBER), \
-					   TYPE_ALIGN(TYPE)))
+	BUILD_BUG_ON(sizeof(TYPE) !=         \
+		     ALIGN(offsetofend(TYPE, MEMBER), _Alignof(TYPE)))
 
 /*
  * We append the 'struct fpu' to the task_struct:

arch/x86/kernel/fpu/regset.c

@@ -167,7 +167,7 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset,
 	}
 
 	fpu_force_restore(fpu);
-	ret = copy_uabi_from_kernel_to_xstate(fpu->fpstate, kbuf ?: tmpbuf);
+	ret = copy_uabi_from_kernel_to_xstate(fpu->fpstate, kbuf ?: tmpbuf, &target->thread.pkru);
 
 out:
 	vfree(tmpbuf);

arch/x86/kernel/fpu/signal.c

@@ -396,7 +396,7 @@ static bool __fpu_restore_sig(void __user *buf, void __user *buf_fx,
 
 	fpregs = &fpu->fpstate->regs;
 	if (use_xsave() && !fx_only) {
-		if (copy_sigframe_from_user_to_xstate(fpu->fpstate, buf_fx))
+		if (copy_sigframe_from_user_to_xstate(tsk, buf_fx))
 			return false;
 	} else {
 		if (__copy_from_user(&fpregs->fxsave, buf_fx,

arch/x86/kernel/fpu/xstate.c

@@ -440,8 +440,8 @@ static void __init __xstate_dump_leaves(void)
 	}
 }
 
-#define XSTATE_WARN_ON(x) do {							\
-	if (WARN_ONCE(x, "XSAVE consistency problem, dumping leaves")) {	\
+#define XSTATE_WARN_ON(x, fmt, ...) do {					\
+	if (WARN_ONCE(x, "XSAVE consistency problem: " fmt, ##__VA_ARGS__)) {	\
 		__xstate_dump_leaves();						\
 	}									\
 } while (0)
@@ -554,8 +554,7 @@ static bool __init check_xstate_against_struct(int nr)
 	    (nr >= XFEATURE_MAX) ||
 	    (nr == XFEATURE_PT_UNIMPLEMENTED_SO_FAR) ||
 	    ((nr >= XFEATURE_RSRVD_COMP_11) && (nr <= XFEATURE_RSRVD_COMP_16))) {
-		WARN_ONCE(1, "no structure for xstate: %d\n", nr);
-		XSTATE_WARN_ON(1);
+		XSTATE_WARN_ON(1, "No structure for xstate: %d\n", nr);
 		return false;
 	}
 	return true;
@@ -598,12 +597,13 @@ static bool __init paranoid_xstate_size_valid(unsigned int kernel_size)
 		 * XSAVES.
 		 */
 		if (!xsaves && xfeature_is_supervisor(i)) {
-			XSTATE_WARN_ON(1);
+			XSTATE_WARN_ON(1, "Got supervisor feature %d, but XSAVES not advertised\n", i);
 			return false;
 		}
 	}
 	size = xstate_calculate_size(fpu_kernel_cfg.max_features, compacted);
-	XSTATE_WARN_ON(size != kernel_size);
+	XSTATE_WARN_ON(size != kernel_size,
+		       "size %u != kernel_size %u\n", size, kernel_size);
 	return size == kernel_size;
 }
 
@@ -1200,8 +1200,36 @@ static int copy_from_buffer(void *dst, unsigned int offset, unsigned int size,
 }
 
 
+/**
+ * copy_uabi_to_xstate - Copy a UABI format buffer to the kernel xstate
+ * @fpstate:	The fpstate buffer to copy to
+ * @kbuf:	The UABI format buffer, if it comes from the kernel
+ * @ubuf:	The UABI format buffer, if it comes from userspace
+ * @pkru:	The location to write the PKRU value to
+ *
+ * Converts from the UABI format into the kernel internal hardware
+ * dependent format.
+ *
+ * This function ultimately has three different callers with distinct PKRU
+ * behavior.
+ * 1.	When called from sigreturn the PKRU register will be restored from
+ *	@fpstate via an XRSTOR. Correctly copying the UABI format buffer to
+ *	@fpstate is sufficient to cover this case, but the caller will also
+ *	pass a pointer to the thread_struct's pkru field in @pkru and updating
+ *	it is harmless.
+ * 2.	When called from ptrace the PKRU register will be restored from the
+ *	thread_struct's pkru field. A pointer to that is passed in @pkru.
+ *	The kernel will restore it manually, so the XRSTOR behavior that resets
+ *	the PKRU register to the hardware init value (0) if the corresponding
+ *	xfeatures bit is not set is emulated here.
+ * 3.	When called from KVM the PKRU register will be restored from the vcpu's
+ *	pkru field. A pointer to that is passed in @pkru. KVM hasn't used
+ *	XRSTOR and hasn't had the PKRU resetting behavior described above. To
+ *	preserve that KVM behavior, it passes NULL for @pkru if the xfeatures
+ *	bit is not set.
+ */
 static int copy_uabi_to_xstate(struct fpstate *fpstate, const void *kbuf,
-			       const void __user *ubuf)
+			       const void __user *ubuf, u32 *pkru)
 {
 	struct xregs_state *xsave = &fpstate->regs.xsave;
 	unsigned int offset, size;
@@ -1250,6 +1278,20 @@ static int copy_uabi_to_xstate(struct fpstate *fpstate, const void *kbuf,
 		}
 	}
 
+	if (hdr.xfeatures & XFEATURE_MASK_PKRU) {
+		struct pkru_state *xpkru;
+
+		xpkru = __raw_xsave_addr(xsave, XFEATURE_PKRU);
+		*pkru = xpkru->pkru;
+	} else {
+		/*
+		 * KVM may pass NULL here to indicate that it does not need
+		 * PKRU updated.
+		 */
+		if (pkru)
+			*pkru = 0;
+	}
+
 	/*
 	 * The state that came in from userspace was user-state only.
 	 * Mask all the user states out of 'xfeatures':
@@ -1268,20 +1310,20 @@ static int copy_uabi_to_xstate(struct fpstate *fpstate, const void *kbuf,
  * Convert from a ptrace standard-format kernel buffer to kernel XSAVE[S]
  * format and copy to the target thread. Used by ptrace and KVM.
  */
-int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf)
+int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf, u32 *pkru)
 {
-	return copy_uabi_to_xstate(fpstate, kbuf, NULL);
+	return copy_uabi_to_xstate(fpstate, kbuf, NULL, pkru);
 }
 
 /*
  * Convert from a sigreturn standard-format user-space buffer to kernel
  * XSAVE[S] format and copy to the target thread. This is called from the
  * sigreturn() and rt_sigreturn() system calls.
  */
-int copy_sigframe_from_user_to_xstate(struct fpstate *fpstate,
+int copy_sigframe_from_user_to_xstate(struct task_struct *tsk,
 				      const void __user *ubuf)
 {
-	return copy_uabi_to_xstate(fpstate, NULL, ubuf);
+	return copy_uabi_to_xstate(tsk->thread.fpu.fpstate, NULL, ubuf, &tsk->thread.pkru);
 }
 
 static bool validate_independent_components(u64 mask)

arch/x86/kernel/fpu/xstate.h

@@ -46,8 +46,8 @@ extern void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
 				      u32 pkru_val, enum xstate_copy_mode copy_mode);
 extern void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk,
 				    enum xstate_copy_mode mode);
-extern int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf);
-extern int copy_sigframe_from_user_to_xstate(struct fpstate *fpstate, const void __user *ubuf);
+extern int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf, u32 *pkru);
+extern int copy_sigframe_from_user_to_xstate(struct task_struct *tsk, const void __user *ubuf);
 
 
 extern void fpu__init_cpu_xstate(void);

tools/testing/selftests/vm/pkey-x86.h

@@ -104,6 +104,18 @@ static inline int cpu_has_pkeys(void)
 	return 1;
 }
 
+static inline int cpu_max_xsave_size(void)
+{
+	unsigned long XSTATE_CPUID = 0xd;
+	unsigned int eax;
+	unsigned int ebx;
+	unsigned int ecx;
+	unsigned int edx;
+
+	__cpuid_count(XSTATE_CPUID, 0, eax, ebx, ecx, edx);
+	return ecx;
+}
+
 static inline u32 pkey_bit_position(int pkey)
 {
 	return pkey * PKEY_BITS_PER_PKEY;

tools/testing/selftests/vm/protection_keys.c

@@ -18,12 +18,13 @@
  *	do a plain mprotect() to a mprotect_pkey() area and make sure the pkey sticks
  *
  * Compile like this:
- *	gcc      -o protection_keys    -O2 -g -std=gnu99 -pthread -Wall protection_keys.c -lrt -ldl -lm
- *	gcc -m32 -o protection_keys_32 -O2 -g -std=gnu99 -pthread -Wall protection_keys.c -lrt -ldl -lm
+ *	gcc -mxsave      -o protection_keys    -O2 -g -std=gnu99 -pthread -Wall protection_keys.c -lrt -ldl -lm
+ *	gcc -mxsave -m32 -o protection_keys_32 -O2 -g -std=gnu99 -pthread -Wall protection_keys.c -lrt -ldl -lm
  */
 #define _GNU_SOURCE
 #define __SANE_USERSPACE_TYPES__
 #include <errno.h>
+#include <linux/elf.h>
 #include <linux/futex.h>
 #include <time.h>
 #include <sys/time.h>
@@ -1550,6 +1551,129 @@ void test_implicit_mprotect_exec_only_memory(int *ptr, u16 pkey)
 	do_not_expect_pkey_fault("plain read on recently PROT_EXEC area");
 }
 
+#if defined(__i386__) || defined(__x86_64__)
+void test_ptrace_modifies_pkru(int *ptr, u16 pkey)
+{
+	u32 new_pkru;
+	pid_t child;
+	int status, ret;
+	int pkey_offset = pkey_reg_xstate_offset();
+	size_t xsave_size = cpu_max_xsave_size();
+	void *xsave;
+	u32 *pkey_register;
+	u64 *xstate_bv;
+	struct iovec iov;
+
+	new_pkru = ~read_pkey_reg();
+	/* Don't make PROT_EXEC mappings inaccessible */
+	new_pkru &= ~3;
+
+	child = fork();
+	pkey_assert(child >= 0);
+	dprintf3("[%d] fork() ret: %d\n", getpid(), child);
+	if (!child) {
+		ptrace(PTRACE_TRACEME, 0, 0, 0);
+		/* Stop and allow the tracer to modify PKRU directly */
+		raise(SIGSTOP);
+
+		/*
+		 * need __read_pkey_reg() version so we do not do shadow_pkey_reg
+		 * checking
+		 */
+		if (__read_pkey_reg() != new_pkru)
+			exit(1);
+
+		/* Stop and allow the tracer to clear XSTATE_BV for PKRU */
+		raise(SIGSTOP);
+
+		if (__read_pkey_reg() != 0)
+			exit(1);
+
+		/* Stop and allow the tracer to examine PKRU */
+		raise(SIGSTOP);
+
+		exit(0);
+	}
+
+	pkey_assert(child == waitpid(child, &status, 0));
+	dprintf3("[%d] waitpid(%d) status: %x\n", getpid(), child, status);
+	pkey_assert(WIFSTOPPED(status) && WSTOPSIG(status) == SIGSTOP);
+
+	xsave = (void *)malloc(xsave_size);
+	pkey_assert(xsave > 0);
+
+	/* Modify the PKRU register directly */
+	iov.iov_base = xsave;
+	iov.iov_len = xsave_size;
+	ret = ptrace(PTRACE_GETREGSET, child, (void *)NT_X86_XSTATE, &iov);
+	pkey_assert(ret == 0);
+
+	pkey_register = (u32 *)(xsave + pkey_offset);
+	pkey_assert(*pkey_register == read_pkey_reg());
+
+	*pkey_register = new_pkru;
+
+	ret = ptrace(PTRACE_SETREGSET, child, (void *)NT_X86_XSTATE, &iov);
+	pkey_assert(ret == 0);
+
+	/* Test that the modification is visible in ptrace before any execution */
+	memset(xsave, 0xCC, xsave_size);
+	ret = ptrace(PTRACE_GETREGSET, child, (void *)NT_X86_XSTATE, &iov);
+	pkey_assert(ret == 0);
+	pkey_assert(*pkey_register == new_pkru);
+
+	/* Execute the tracee */
+	ret = ptrace(PTRACE_CONT, child, 0, 0);
+	pkey_assert(ret == 0);
+
+	/* Test that the tracee saw the PKRU value change */
+	pkey_assert(child == waitpid(child, &status, 0));
+	dprintf3("[%d] waitpid(%d) status: %x\n", getpid(), child, status);
+	pkey_assert(WIFSTOPPED(status) && WSTOPSIG(status) == SIGSTOP);
+
+	/* Test that the modification is visible in ptrace after execution */
+	memset(xsave, 0xCC, xsave_size);
+	ret = ptrace(PTRACE_GETREGSET, child, (void *)NT_X86_XSTATE, &iov);
+	pkey_assert(ret == 0);
+	pkey_assert(*pkey_register == new_pkru);
+
+	/* Clear the PKRU bit from XSTATE_BV */
+	xstate_bv = (u64 *)(xsave + 512);
+	*xstate_bv &= ~(1 << 9);
+
+	ret = ptrace(PTRACE_SETREGSET, child, (void *)NT_X86_XSTATE, &iov);
+	pkey_assert(ret == 0);
+
+	/* Test that the modification is visible in ptrace before any execution */
+	memset(xsave, 0xCC, xsave_size);
+	ret = ptrace(PTRACE_GETREGSET, child, (void *)NT_X86_XSTATE, &iov);
+	pkey_assert(ret == 0);
+	pkey_assert(*pkey_register == 0);
+
+	ret = ptrace(PTRACE_CONT, child, 0, 0);
+	pkey_assert(ret == 0);
+
+	/* Test that the tracee saw the PKRU value go to 0 */
+	pkey_assert(child == waitpid(child, &status, 0));
+	dprintf3("[%d] waitpid(%d) status: %x\n", getpid(), child, status);
+	pkey_assert(WIFSTOPPED(status) && WSTOPSIG(status) == SIGSTOP);
+
+	/* Test that the modification is visible in ptrace after execution */
+	memset(xsave, 0xCC, xsave_size);
+	ret = ptrace(PTRACE_GETREGSET, child, (void *)NT_X86_XSTATE, &iov);
+	pkey_assert(ret == 0);
+	pkey_assert(*pkey_register == 0);
+
+	ret = ptrace(PTRACE_CONT, child, 0, 0);
+	pkey_assert(ret == 0);
+	pkey_assert(child == waitpid(child, &status, 0));
+	dprintf3("[%d] waitpid(%d) status: %x\n", getpid(), child, status);
+	pkey_assert(WIFEXITED(status));
+	pkey_assert(WEXITSTATUS(status) == 0);
+	free(xsave);
+}
+#endif
+
 void test_mprotect_pkey_on_unsupported_cpu(int *ptr, u16 pkey)
 {
 	int size = PAGE_SIZE;
@@ -1585,6 +1709,9 @@ void (*pkey_tests[])(int *ptr, u16 pkey) = {
 	test_pkey_syscalls_bad_args,
 	test_pkey_alloc_exhaust,
 	test_pkey_alloc_free_attach_pkey0,
+#if defined(__i386__) || defined(__x86_64__)
+	test_ptrace_modifies_pkru,
+#endif
 };
 
 void run_tests_once(void)