1 files changed, 138 insertions, 92 deletions

diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index c8340156bfd2..117e74c44e75 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -39,26 +39,26 @@
  */
 static const char *xfeature_names[] =
 {
-	"x87 floating point registers"	,
-	"SSE registers"			,
-	"AVX registers"			,
-	"MPX bounds registers"		,
-	"MPX CSR"			,
-	"AVX-512 opmask"		,
-	"AVX-512 Hi256"			,
-	"AVX-512 ZMM_Hi256"		,
-	"Processor Trace (unused)"	,
+	"x87 floating point registers",
+	"SSE registers",
+	"AVX registers",
+	"MPX bounds registers",
+	"MPX CSR",
+	"AVX-512 opmask",
+	"AVX-512 Hi256",
+	"AVX-512 ZMM_Hi256",
+	"Processor Trace (unused)",
 	"Protection Keys User registers",
 	"PASID state",
-	"unknown xstate feature"	,
-	"unknown xstate feature"	,
-	"unknown xstate feature"	,
-	"unknown xstate feature"	,
-	"unknown xstate feature"	,
-	"unknown xstate feature"	,
-	"AMX Tile config"		,
-	"AMX Tile data"			,
-	"unknown xstate feature"	,
+	"Control-flow User registers",
+	"Control-flow Kernel registers (unused)",
+	"unknown xstate feature",
+	"unknown xstate feature",
+	"unknown xstate feature",
+	"unknown xstate feature",
+	"AMX Tile config",
+	"AMX Tile data",
+	"unknown xstate feature",
 };
 
 static unsigned short xsave_cpuid_features[] __initdata = {
@@ -71,8 +71,9 @@ static unsigned short xsave_cpuid_features[] __initdata = {
 	[XFEATURE_ZMM_Hi256]			= X86_FEATURE_AVX512F,
 	[XFEATURE_Hi16_ZMM]			= X86_FEATURE_AVX512F,
 	[XFEATURE_PT_UNIMPLEMENTED_SO_FAR]	= X86_FEATURE_INTEL_PT,
-	[XFEATURE_PKRU]				= X86_FEATURE_PKU,
+	[XFEATURE_PKRU]				= X86_FEATURE_OSPKE,
 	[XFEATURE_PASID]			= X86_FEATURE_ENQCMD,
+	[XFEATURE_CET_USER]			= X86_FEATURE_SHSTK,
 	[XFEATURE_XTILE_CFG]			= X86_FEATURE_AMX_TILE,
 	[XFEATURE_XTILE_DATA]			= X86_FEATURE_AMX_TILE,
 };
@@ -276,6 +277,7 @@ static void __init print_xstate_features(void)
 	print_xstate_feature(XFEATURE_MASK_Hi16_ZMM);
 	print_xstate_feature(XFEATURE_MASK_PKRU);
 	print_xstate_feature(XFEATURE_MASK_PASID);
+	print_xstate_feature(XFEATURE_MASK_CET_USER);
 	print_xstate_feature(XFEATURE_MASK_XTILE_CFG);
 	print_xstate_feature(XFEATURE_MASK_XTILE_DATA);
 }
@@ -344,6 +346,7 @@ static __init void os_xrstor_booting(struct xregs_state *xstate)
 	 XFEATURE_MASK_BNDREGS |		\
 	 XFEATURE_MASK_BNDCSR |			\
 	 XFEATURE_MASK_PASID |			\
+	 XFEATURE_MASK_CET_USER |		\
 	 XFEATURE_MASK_XTILE)
 
 /*
@@ -360,7 +363,7 @@ 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
@@ -440,20 +443,21 @@ 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)
 
-#define XCHECK_SZ(sz, nr, nr_macro, __struct) do {			\
-	if ((nr == nr_macro) &&						\
-	    WARN_ONCE(sz != sizeof(__struct),				\
-		"%s: struct is %zu bytes, cpu state %d bytes\n",	\
-		__stringify(nr_macro), sizeof(__struct), sz)) {		\
+#define XCHECK_SZ(sz, nr, __struct) ({					\
+	if (WARN_ONCE(sz != sizeof(__struct),				\
+	    "[%s]: struct is %zu bytes, cpu state %d bytes\n",		\
+	    xfeature_names[nr], sizeof(__struct), sz)) {		\
 		__xstate_dump_leaves();					\
 	}								\
-} while (0)
+	true;								\
+})
+
 
 /**
  * check_xtile_data_against_struct - Check tile data state size.
@@ -527,37 +531,28 @@ static bool __init check_xstate_against_struct(int nr)
 	 * Ask the CPU for the size of the state.
 	 */
 	int sz = xfeature_size(nr);
+
 	/*
 	 * Match each CPU state with the corresponding software
 	 * structure.
 	 */
-	XCHECK_SZ(sz, nr, XFEATURE_YMM,       struct ymmh_struct);
-	XCHECK_SZ(sz, nr, XFEATURE_BNDREGS,   struct mpx_bndreg_state);
-	XCHECK_SZ(sz, nr, XFEATURE_BNDCSR,    struct mpx_bndcsr_state);
-	XCHECK_SZ(sz, nr, XFEATURE_OPMASK,    struct avx_512_opmask_state);
-	XCHECK_SZ(sz, nr, XFEATURE_ZMM_Hi256, struct avx_512_zmm_uppers_state);
-	XCHECK_SZ(sz, nr, XFEATURE_Hi16_ZMM,  struct avx_512_hi16_state);
-	XCHECK_SZ(sz, nr, XFEATURE_PKRU,      struct pkru_state);
-	XCHECK_SZ(sz, nr, XFEATURE_PASID,     struct ia32_pasid_state);
-	XCHECK_SZ(sz, nr, XFEATURE_XTILE_CFG, struct xtile_cfg);
-
-	/* The tile data size varies between implementations. */
-	if (nr == XFEATURE_XTILE_DATA)
-		check_xtile_data_against_struct(sz);
-
-	/*
-	 * Make *SURE* to add any feature numbers in below if
-	 * there are "holes" in the xsave state component
-	 * numbers.
-	 */
-	if ((nr < XFEATURE_YMM) ||
-	    (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);
+	switch (nr) {
+	case XFEATURE_YMM:	  return XCHECK_SZ(sz, nr, struct ymmh_struct);
+	case XFEATURE_BNDREGS:	  return XCHECK_SZ(sz, nr, struct mpx_bndreg_state);
+	case XFEATURE_BNDCSR:	  return XCHECK_SZ(sz, nr, struct mpx_bndcsr_state);
+	case XFEATURE_OPMASK:	  return XCHECK_SZ(sz, nr, struct avx_512_opmask_state);
+	case XFEATURE_ZMM_Hi256:  return XCHECK_SZ(sz, nr, struct avx_512_zmm_uppers_state);
+	case XFEATURE_Hi16_ZMM:	  return XCHECK_SZ(sz, nr, struct avx_512_hi16_state);
+	case XFEATURE_PKRU:	  return XCHECK_SZ(sz, nr, struct pkru_state);
+	case XFEATURE_PASID:	  return XCHECK_SZ(sz, nr, struct ia32_pasid_state);
+	case XFEATURE_XTILE_CFG:  return XCHECK_SZ(sz, nr, struct xtile_cfg);
+	case XFEATURE_CET_USER:	  return XCHECK_SZ(sz, nr, struct cet_user_state);
+	case XFEATURE_XTILE_DATA: check_xtile_data_against_struct(sz); return true;
+	default:
+		XSTATE_WARN_ON(1, "No structure for xstate: %d\n", nr);
 		return false;
 	}
+
 	return true;
 }
 
@@ -598,12 +593,13 @@ 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 +674,6 @@ 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 +699,6 @@ 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 +853,19 @@ 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();
 
 	/*
@@ -887,6 +878,13 @@ void __init fpu__init_system_xstate(unsigned int legacy_size)
 		goto out_disable;
 	}
 
+	/*
+	 * CPU capabilities initialization runs before FPU init. So
+	 * X86_FEATURE_OSXSAVE is not set. Now that XSAVE is completely
+	 * functional, set the feature bit so depending code works.
+	 */
+	setup_force_cpu_cap(X86_FEATURE_OSXSAVE);
+
 	print_xstate_offset_size();
 	pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is %d bytes, using '%s' format.\n",
 		fpu_kernel_cfg.max_features,
@@ -1051,6 +1049,7 @@ static void copy_feature(bool from_xstate, struct membuf *to, void *xstate,
  * __copy_xstate_to_uabi_buf - Copy kernel saved xstate to a UABI buffer
  * @to:		membuf descriptor
  * @fpstate:	The fpstate buffer from which to copy
+ * @xfeatures:	The mask of xfeatures to save (XSAVE mode only)
  * @pkru_val:	The PKRU value to store in the PKRU component
  * @copy_mode:	The requested copy mode
  *
@@ -1061,7 +1060,8 @@ static void copy_feature(bool from_xstate, struct membuf *to, void *xstate,
  * It supports partial copy but @to.pos always starts from zero.
  */
 void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
-			       u32 pkru_val, enum xstate_copy_mode copy_mode)
+			       u64 xfeatures, u32 pkru_val,
+			       enum xstate_copy_mode copy_mode)
 {
 	const unsigned int off_mxcsr = offsetof(struct fxregs_state, mxcsr);
 	struct xregs_state *xinit = &init_fpstate.regs.xsave;
@@ -1085,7 +1085,7 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
 		break;
 
 	case XSTATE_COPY_XSAVE:
-		header.xfeatures &= fpstate->user_xfeatures;
+		header.xfeatures &= fpstate->user_xfeatures & xfeatures;
 		break;
 	}
 
@@ -1123,12 +1123,20 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
 	zerofrom = offsetof(struct xregs_state, extended_state_area);
 
 	/*
-	 * The ptrace buffer is in non-compacted XSAVE format.  In
-	 * non-compacted format disabled features still occupy state space,
-	 * but there is no state to copy from in the compacted
-	 * init_fpstate. The gap tracking will zero these states.
+	 * This 'mask' indicates which states to copy from fpstate.
+	 * Those extended states that are not present in fpstate are
+	 * either disabled or initialized:
+	 *
+	 * In non-compacted format, disabled features still occupy
+	 * state space but there is no state to copy from in the
+	 * compacted init_fpstate. The gap tracking will zero these
+	 * states.
+	 *
+	 * The extended features have an all zeroes init state. Thus,
+	 * remove them from 'mask' to zero those features in the user
+	 * buffer instead of retrieving them from init_fpstate.
 	 */
-	mask = fpstate->user_xfeatures;
+	mask = header.xfeatures;
 
 	for_each_extended_xfeature(i, mask) {
 		/*
@@ -1147,9 +1155,8 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
 			pkru.pkru = pkru_val;
 			membuf_write(&to, &pkru, sizeof(pkru));
 		} else {
-			copy_feature(header.xfeatures & BIT_ULL(i), &to,
+			membuf_write(&to,
 				     __raw_xsave_addr(xsave, i),
-				     __raw_xsave_addr(xinit, i),
 				     xstate_sizes[i]);
 		}
 		/*
@@ -1180,6 +1187,7 @@ void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk,
 			     enum xstate_copy_mode copy_mode)
 {
 	__copy_xstate_to_uabi_buf(to, tsk->thread.fpu.fpstate,
+				  tsk->thread.fpu.fpstate->user_xfeatures,
 				  tsk->thread.pkru, copy_mode);
 }
 
@@ -1196,8 +1204,36 @@ 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 +1282,20 @@ 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 +1314,9 @@ 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 +1324,10 @@ 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)
@@ -1489,10 +1539,7 @@ static int fpstate_realloc(u64 xfeatures, unsigned int ksize,
 		fpregs_restore_userregs();
 
 	newfps->xfeatures = curfps->xfeatures | xfeatures;
-
-	if (!guest_fpu)
-		newfps->user_xfeatures = curfps->user_xfeatures | xfeatures;
-
+	newfps->user_xfeatures = curfps->user_xfeatures | xfeatures;
 	newfps->xfd = curfps->xfd & ~xfeatures;
 
 	/* Do the final updates within the locked region */
@@ -1689,7 +1736,6 @@ EXPORT_SYMBOL_GPL(xstate_get_guest_group_perm);
 
 /**
  * fpu_xstate_prctl - xstate permission operations
- * @tsk:	Redundant pointer to current
  * @option:	A subfunction of arch_prctl()
  * @arg2:	option argument
  * Return:	0 if successful; otherwise, an error code