1 files changed, 66 insertions, 150 deletions

diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 7c7824ae7862..39e1c8626ab9 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -81,10 +81,10 @@ static unsigned int xstate_offsets[XFEATURE_MAX] __ro_after_init =
 	{ [ 0 ... XFEATURE_MAX - 1] = -1};
 static unsigned int xstate_sizes[XFEATURE_MAX] __ro_after_init =
 	{ [ 0 ... XFEATURE_MAX - 1] = -1};
-static unsigned int xstate_comp_offsets[XFEATURE_MAX] __ro_after_init =
-	{ [ 0 ... XFEATURE_MAX - 1] = -1};
-static unsigned int xstate_supervisor_only_offsets[XFEATURE_MAX] __ro_after_init =
-	{ [ 0 ... XFEATURE_MAX - 1] = -1};
+static unsigned int xstate_flags[XFEATURE_MAX] __ro_after_init;
+
+#define XSTATE_FLAG_SUPERVISOR	BIT(0)
+#define XSTATE_FLAG_ALIGNED64	BIT(1)
 
 /*
  * Return whether the system supports a given xfeature.
@@ -124,17 +124,41 @@ int cpu_has_xfeatures(u64 xfeatures_needed, const char **feature_name)
 }
 EXPORT_SYMBOL_GPL(cpu_has_xfeatures);
 
+static bool xfeature_is_aligned64(int xfeature_nr)
+{
+	return xstate_flags[xfeature_nr] & XSTATE_FLAG_ALIGNED64;
+}
+
 static bool xfeature_is_supervisor(int xfeature_nr)
 {
+	return xstate_flags[xfeature_nr] & XSTATE_FLAG_SUPERVISOR;
+}
+
+static unsigned int xfeature_get_offset(u64 xcomp_bv, int xfeature)
+{
+	unsigned int offs, i;
+
 	/*
-	 * Extended State Enumeration Sub-leaves (EAX = 0DH, ECX = n, n > 1)
-	 * returns ECX[0] set to (1) for a supervisor state, and cleared (0)
-	 * for a user state.
+	 * Non-compacted format and legacy features use the cached fixed
+	 * offsets.
 	 */
-	u32 eax, ebx, ecx, edx;
+	if (!cpu_feature_enabled(X86_FEATURE_XSAVES) || xfeature <= XFEATURE_SSE)
+		return xstate_offsets[xfeature];
 
-	cpuid_count(XSTATE_CPUID, xfeature_nr, &eax, &ebx, &ecx, &edx);
-	return ecx & 1;
+	/*
+	 * Compacted format offsets depend on the actual content of the
+	 * compacted xsave area which is determined by the xcomp_bv header
+	 * field.
+	 */
+	offs = FXSAVE_SIZE + XSAVE_HDR_SIZE;
+	for_each_extended_xfeature(i, xcomp_bv) {
+		if (xfeature_is_aligned64(i))
+			offs = ALIGN(offs, 64);
+		if (i == xfeature)
+			break;
+		offs += xstate_sizes[i];
+	}
+	return offs;
 }
 
 /*
@@ -182,7 +206,7 @@ static bool xfeature_enabled(enum xfeature xfeature)
  * Record the offsets and sizes of various xstates contained
  * in the XSAVE state memory layout.
  */
-static void __init setup_xstate_features(void)
+static void __init setup_xstate_cache(void)
 {
 	u32 eax, ebx, ecx, edx, i;
 	/* start at the beginning of the "extended state" */
@@ -205,6 +229,7 @@ static void __init setup_xstate_features(void)
 		cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx);
 
 		xstate_sizes[i] = eax;
+		xstate_flags[i] = ecx;
 
 		/*
 		 * If an xfeature is supervisor state, the offset in EBX is
@@ -264,94 +289,6 @@ static void __init print_xstate_features(void)
 } while (0)
 
 /*
- * We could cache this like xstate_size[], but we only use
- * it here, so it would be a waste of space.
- */
-static int xfeature_is_aligned(int xfeature_nr)
-{
-	u32 eax, ebx, ecx, edx;
-
-	CHECK_XFEATURE(xfeature_nr);
-
-	if (!xfeature_enabled(xfeature_nr)) {
-		WARN_ONCE(1, "Checking alignment of disabled xfeature %d\n",
-			  xfeature_nr);
-		return 0;
-	}
-
-	cpuid_count(XSTATE_CPUID, xfeature_nr, &eax, &ebx, &ecx, &edx);
-	/*
-	 * The value returned by ECX[1] indicates the alignment
-	 * of state component 'i' when the compacted format
-	 * of the extended region of an XSAVE area is used:
-	 */
-	return !!(ecx & 2);
-}
-
-/*
- * This function sets up offsets and sizes of all extended states in
- * xsave area. This supports both standard format and compacted format
- * of the xsave area.
- */
-static void __init setup_xstate_comp_offsets(void)
-{
-	unsigned int next_offset;
-	int i;
-
-	/*
-	 * The FP xstates and SSE xstates are legacy states. They are always
-	 * in the fixed offsets in the xsave area in either compacted form
-	 * or standard form.
-	 */
-	xstate_comp_offsets[XFEATURE_FP] = 0;
-	xstate_comp_offsets[XFEATURE_SSE] = offsetof(struct fxregs_state,
-						     xmm_space);
-
-	if (!cpu_feature_enabled(X86_FEATURE_XSAVES)) {
-		for_each_extended_xfeature(i, fpu_kernel_cfg.max_features)
-			xstate_comp_offsets[i] = xstate_offsets[i];
-		return;
-	}
-
-	next_offset = FXSAVE_SIZE + XSAVE_HDR_SIZE;
-
-	for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) {
-		if (xfeature_is_aligned(i))
-			next_offset = ALIGN(next_offset, 64);
-
-		xstate_comp_offsets[i] = next_offset;
-		next_offset += xstate_sizes[i];
-	}
-}
-
-/*
- * Setup offsets of a supervisor-state-only XSAVES buffer:
- *
- * The offsets stored in xstate_comp_offsets[] only work for one specific
- * value of the Requested Feature BitMap (RFBM).  In cases where a different
- * RFBM value is used, a different set of offsets is required.  This set of
- * offsets is for when RFBM=xfeatures_mask_supervisor().
- */
-static void __init setup_supervisor_only_offsets(void)
-{
-	unsigned int next_offset;
-	int i;
-
-	next_offset = FXSAVE_SIZE + XSAVE_HDR_SIZE;
-
-	for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) {
-		if (!xfeature_is_supervisor(i))
-			continue;
-
-		if (xfeature_is_aligned(i))
-			next_offset = ALIGN(next_offset, 64);
-
-		xstate_supervisor_only_offsets[i] = next_offset;
-		next_offset += xstate_sizes[i];
-	}
-}
-
-/*
  * Print out xstate component offsets and sizes
  */
 static void __init print_xstate_offset_size(void)
@@ -360,7 +297,8 @@ static void __init print_xstate_offset_size(void)
 
 	for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) {
 		pr_info("x86/fpu: xstate_offset[%d]: %4d, xstate_sizes[%d]: %4d\n",
-			 i, xstate_comp_offsets[i], i, xstate_sizes[i]);
+			i, xfeature_get_offset(fpu_kernel_cfg.max_features, i),
+			i, xstate_sizes[i]);
 	}
 }
 
@@ -419,7 +357,6 @@ static void __init setup_init_fpu_buf(void)
 	if (!boot_cpu_has(X86_FEATURE_XSAVE))
 		return;
 
-	setup_xstate_features();
 	print_xstate_features();
 
 	xstate_init_xcomp_bv(&init_fpstate.regs.xsave, fpu_kernel_cfg.max_features);
@@ -448,25 +385,6 @@ static void __init setup_init_fpu_buf(void)
 	fxsave(&init_fpstate.regs.fxsave);
 }
 
-static int xfeature_uncompacted_offset(int xfeature_nr)
-{
-	u32 eax, ebx, ecx, edx;
-
-	/*
-	 * Only XSAVES supports supervisor states and it uses compacted
-	 * format. Checking a supervisor state's uncompacted offset is
-	 * an error.
-	 */
-	if (XFEATURE_MASK_SUPERVISOR_ALL & BIT_ULL(xfeature_nr)) {
-		WARN_ONCE(1, "No fixed offset for xstate %d\n", xfeature_nr);
-		return -1;
-	}
-
-	CHECK_XFEATURE(xfeature_nr);
-	cpuid_count(XSTATE_CPUID, xfeature_nr, &eax, &ebx, &ecx, &edx);
-	return ebx;
-}
-
 int xfeature_size(int xfeature_nr)
 {
 	u32 eax, ebx, ecx, edx;
@@ -644,29 +562,15 @@ static bool __init check_xstate_against_struct(int nr)
 
 static unsigned int xstate_calculate_size(u64 xfeatures, bool compacted)
 {
-	unsigned int size = FXSAVE_SIZE + XSAVE_HDR_SIZE;
-	int i;
+	unsigned int topmost = fls64(xfeatures) -  1;
+	unsigned int offset = xstate_offsets[topmost];
 
-	for_each_extended_xfeature(i, xfeatures) {
-		/* Align from the end of the previous feature */
-		if (xfeature_is_aligned(i))
-			size = ALIGN(size, 64);
-		/*
-		 * In compacted format the enabled features are packed,
-		 * i.e. disabled features do not occupy space.
-		 *
-		 * In non-compacted format the offsets are fixed and
-		 * disabled states still occupy space in the memory buffer.
-		 */
-		if (!compacted)
-			size = xfeature_uncompacted_offset(i);
-		/*
-		 * Add the feature size even for non-compacted format
-		 * to make the end result correct
-		 */
-		size += xfeature_size(i);
-	}
-	return size;
+	if (topmost <= XFEATURE_SSE)
+		return sizeof(struct xregs_state);
+
+	if (compacted)
+		offset = xfeature_get_offset(xfeatures, topmost);
+	return offset + xstate_sizes[topmost];
 }
 
 /*
@@ -935,6 +839,10 @@ void __init fpu__init_system_xstate(unsigned int legacy_size)
 
 	/* Enable xstate instructions to be able to continue with initialization: */
 	fpu__init_cpu_xstate();
+
+	/* Cache size, offset and flags for initialization */
+	setup_xstate_cache();
+
 	err = init_xstate_size();
 	if (err)
 		goto out_disable;
@@ -950,8 +858,6 @@ void __init fpu__init_system_xstate(unsigned int legacy_size)
 				  fpu_user_cfg.max_features);
 
 	setup_init_fpu_buf();
-	setup_xstate_comp_offsets();
-	setup_supervisor_only_offsets();
 
 	/*
 	 * Paranoia check whether something in the setup modified the
@@ -1006,13 +912,19 @@ void fpu__resume_cpu(void)
  */
 static void *__raw_xsave_addr(struct xregs_state *xsave, int xfeature_nr)
 {
-	if (!xfeature_enabled(xfeature_nr)) {
-		WARN_ON_FPU(1);
+	u64 xcomp_bv = xsave->header.xcomp_bv;
+
+	if (WARN_ON_ONCE(!xfeature_enabled(xfeature_nr)))
 		return NULL;
+
+	if (cpu_feature_enabled(X86_FEATURE_XSAVES)) {
+		if (WARN_ON_ONCE(!(xcomp_bv & BIT_ULL(xfeature_nr))))
+			return NULL;
 	}
 
-	return (void *)xsave + xstate_comp_offsets[xfeature_nr];
+	return (void *)xsave + xfeature_get_offset(xcomp_bv, xfeature_nr);
 }
+
 /*
  * Given the xsave area and a state inside, this function returns the
  * address of the state.
@@ -1043,8 +955,9 @@ void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr)
 	 * We should not ever be requesting features that we
 	 * have not enabled.
 	 */
-	WARN_ONCE(!(fpu_kernel_cfg.max_features & BIT_ULL(xfeature_nr)),
-		  "get of unsupported state");
+	if (WARN_ON_ONCE(!xfeature_enabled(xfeature_nr)))
+		return NULL;
+
 	/*
 	 * This assumes the last 'xsave*' instruction to
 	 * have requested that 'xfeature_nr' be saved.
@@ -1625,6 +1538,9 @@ static int __xstate_request_perm(u64 permitted, u64 requested, bool guest)
 
 	/* Calculate the resulting kernel state size */
 	mask = permitted | requested;
+	/* Take supervisor states into account on the host */
+	if (!guest)
+		mask |= xfeatures_mask_supervisor();
 	ksize = xstate_calculate_size(mask, compacted);
 
 	/* Calculate the resulting user state size */
@@ -1639,7 +1555,7 @@ static int __xstate_request_perm(u64 permitted, u64 requested, bool guest)
 
 	perm = guest ? &fpu->guest_perm : &fpu->perm;
 	/* Pairs with the READ_ONCE() in xstate_get_group_perm() */
-	WRITE_ONCE(perm->__state_perm, requested);
+	WRITE_ONCE(perm->__state_perm, mask);
 	/* Protected by sighand lock */
 	perm->__state_size = ksize;
 	perm->__user_state_size = usize;