1 files changed, 76 insertions, 30 deletions

diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index c8340156bfd2..714166cc25f2 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -360,7 +360,7 @@ static void __init setup_init_fpu_buf(void)
 
 	print_xstate_features();
 
-	xstate_init_xcomp_bv(&init_fpstate.regs.xsave, fpu_kernel_cfg.max_features);
+	xstate_init_xcomp_bv(&init_fpstate.regs.xsave, init_fpstate.xfeatures);
 
 	/*
 	 * Init all the features state with header.xfeatures being 0x0
@@ -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;
 }
 
@@ -678,20 +678,6 @@ static unsigned int __init get_xsave_size_user(void)
 	return ebx;
 }
 
-/*
- * Will the runtime-enumerated 'xstate_size' fit in the init
- * task's statically-allocated buffer?
- */
-static bool __init is_supported_xstate_size(unsigned int test_xstate_size)
-{
-	if (test_xstate_size <= sizeof(init_fpstate.regs))
-		return true;
-
-	pr_warn("x86/fpu: xstate buffer too small (%zu < %d), disabling xsave\n",
-			sizeof(init_fpstate.regs), test_xstate_size);
-	return false;
-}
-
 static int __init init_xstate_size(void)
 {
 	/* Recompute the context size for enabled features: */
@@ -717,10 +703,6 @@ static int __init init_xstate_size(void)
 	kernel_default_size =
 		xstate_calculate_size(fpu_kernel_cfg.default_features, compacted);
 
-	/* Ensure we have the space to store all default enabled features. */
-	if (!is_supported_xstate_size(kernel_default_size))
-		return -EINVAL;
-
 	if (!paranoid_xstate_size_valid(kernel_size))
 		return -EINVAL;
 
@@ -875,6 +857,19 @@ void __init fpu__init_system_xstate(unsigned int legacy_size)
 	update_regset_xstate_info(fpu_user_cfg.max_size,
 				  fpu_user_cfg.max_features);
 
+	/*
+	 * init_fpstate excludes dynamic states as they are large but init
+	 * state is zero.
+	 */
+	init_fpstate.size		= fpu_kernel_cfg.default_size;
+	init_fpstate.xfeatures		= fpu_kernel_cfg.default_features;
+
+	if (init_fpstate.size > sizeof(init_fpstate.regs)) {
+		pr_warn("x86/fpu: init_fpstate buffer too small (%zu < %d), disabling XSAVE\n",
+			sizeof(init_fpstate.regs), init_fpstate.size);
+		goto out_disable;
+	}
+
 	setup_init_fpu_buf();
 
 	/*
@@ -1130,6 +1125,15 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
 	 */
 	mask = fpstate->user_xfeatures;
 
+	/*
+	 * Dynamic features are not present in init_fpstate. When they are
+	 * in an all zeros init state, remove those from 'mask' to zero
+	 * those features in the user buffer instead of retrieving them
+	 * from init_fpstate.
+	 */
+	if (fpu_state_size_dynamic())
+		mask &= (header.xfeatures | xinit->header.xcomp_bv);
+
 	for_each_extended_xfeature(i, mask) {
 		/*
 		 * If there was a feature or alignment gap, zero the space
@@ -1196,8 +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;
@@ -1246,6 +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':
@@ -1264,9 +1310,9 @@ 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);
 }
 
 /*
@@ -1274,10 +1320,10 @@ int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf)
  * 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)