Merge tag 'x86_urgent_for_v5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 fixes from Borislav Petkov:
 "Two more urgent FPU fixes:

   - prevent unprivileged userspace from reinitializing supervisor
     states

   - prepare init_fpstate, which is the buffer used when initializing
     FPU state, properly in case the skip-writing-state-components
     XSAVE* variants are used"

* tag 'x86_urgent_for_v5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/fpu: Make init_fpstate correct with optimized XSAVE
  x86/fpu: Preserve supervisor states in sanitize_restored_user_xstate()

Author: torvalds

arch/x86/include/asm/fpu/internal.h

@@ -204,6 +204,14 @@ static inline void copy_fxregs_to_kernel(struct fpu *fpu)
 		asm volatile("fxsaveq %[fx]" : [fx] "=m" (fpu->state.fxsave));
 }
 
+static inline void fxsave(struct fxregs_state *fx)
+{
+	if (IS_ENABLED(CONFIG_X86_32))
+		asm volatile( "fxsave %[fx]" : [fx] "=m" (*fx));
+	else
+		asm volatile("fxsaveq %[fx]" : [fx] "=m" (*fx));
+}
+
 /* These macros all use (%edi)/(%rdi) as the single memory argument. */
 #define XSAVE		".byte " REX_PREFIX "0x0f,0xae,0x27"
 #define XSAVEOPT	".byte " REX_PREFIX "0x0f,0xae,0x37"
@@ -268,28 +276,6 @@ static inline void copy_fxregs_to_kernel(struct fpu *fpu)
 		     : "D" (st), "m" (*st), "a" (lmask), "d" (hmask)	\
 		     : "memory")
 
-/*
- * This function is called only during boot time when x86 caps are not set
- * up and alternative can not be used yet.
- */
-static inline void copy_xregs_to_kernel_booting(struct xregs_state *xstate)
-{
-	u64 mask = xfeatures_mask_all;
-	u32 lmask = mask;
-	u32 hmask = mask >> 32;
-	int err;
-
-	WARN_ON(system_state != SYSTEM_BOOTING);
-
-	if (boot_cpu_has(X86_FEATURE_XSAVES))
-		XSTATE_OP(XSAVES, xstate, lmask, hmask, err);
-	else
-		XSTATE_OP(XSAVE, xstate, lmask, hmask, err);
-
-	/* We should never fault when copying to a kernel buffer: */
-	WARN_ON_FPU(err);
-}
-
 /*
  * This function is called only during boot time when x86 caps are not set
  * up and alternative can not be used yet.

arch/x86/kernel/fpu/signal.c

@@ -221,28 +221,18 @@ sanitize_restored_user_xstate(union fpregs_state *state,
 
 	if (use_xsave()) {
 		/*
-		 * Note: we don't need to zero the reserved bits in the
-		 * xstate_header here because we either didn't copy them at all,
-		 * or we checked earlier that they aren't set.
+		 * Clear all feature bits which are not set in
+		 * user_xfeatures and clear all extended features
+		 * for fx_only mode.
 		 */
+		u64 mask = fx_only ? XFEATURE_MASK_FPSSE : user_xfeatures;
 
 		/*
-		 * 'user_xfeatures' might have bits clear which are
-		 * set in header->xfeatures. This represents features that
-		 * were in init state prior to a signal delivery, and need
-		 * to be reset back to the init state.  Clear any user
-		 * feature bits which are set in the kernel buffer to get
-		 * them back to the init state.
-		 *
-		 * Supervisor state is unchanged by input from userspace.
-		 * Ensure supervisor state bits stay set and supervisor
-		 * state is not modified.
+		 * Supervisor state has to be preserved. The sigframe
+		 * restore can only modify user features, i.e. @mask
+		 * cannot contain them.
 		 */
-		if (fx_only)
-			header->xfeatures = XFEATURE_MASK_FPSSE;
-		else
-			header->xfeatures &= user_xfeatures |
-					     xfeatures_mask_supervisor();
+		header->xfeatures &= mask | xfeatures_mask_supervisor();
 	}
 
 	if (use_fxsr()) {

arch/x86/kernel/fpu/xstate.c

@@ -440,13 +440,36 @@ static void __init print_xstate_offset_size(void)
 	}
 }
 
+/*
+ * All supported features have either init state all zeros or are
+ * handled in setup_init_fpu() individually. This is an explicit
+ * feature list and does not use XFEATURE_MASK*SUPPORTED to catch
+ * newly added supported features at build time and make people
+ * actually look at the init state for the new feature.
+ */
+#define XFEATURES_INIT_FPSTATE_HANDLED		\
+	(XFEATURE_MASK_FP |			\
+	 XFEATURE_MASK_SSE |			\
+	 XFEATURE_MASK_YMM |			\
+	 XFEATURE_MASK_OPMASK |			\
+	 XFEATURE_MASK_ZMM_Hi256 |		\
+	 XFEATURE_MASK_Hi16_ZMM	 |		\
+	 XFEATURE_MASK_PKRU |			\
+	 XFEATURE_MASK_BNDREGS |		\
+	 XFEATURE_MASK_BNDCSR |			\
+	 XFEATURE_MASK_PASID)
+
 /*
  * setup the xstate image representing the init state
  */
 static void __init setup_init_fpu_buf(void)
 {
 	static int on_boot_cpu __initdata = 1;
 
+	BUILD_BUG_ON((XFEATURE_MASK_USER_SUPPORTED |
+		      XFEATURE_MASK_SUPERVISOR_SUPPORTED) !=
+		     XFEATURES_INIT_FPSTATE_HANDLED);
+
 	WARN_ON_FPU(!on_boot_cpu);
 	on_boot_cpu = 0;
 
@@ -466,10 +489,22 @@ static void __init setup_init_fpu_buf(void)
 	copy_kernel_to_xregs_booting(&init_fpstate.xsave);
 
 	/*
-	 * Dump the init state again. This is to identify the init state
-	 * of any feature which is not represented by all zero's.
+	 * All components are now in init state. Read the state back so
+	 * that init_fpstate contains all non-zero init state. This only
+	 * works with XSAVE, but not with XSAVEOPT and XSAVES because
+	 * those use the init optimization which skips writing data for
+	 * components in init state.
+	 *
+	 * XSAVE could be used, but that would require to reshuffle the
+	 * data when XSAVES is available because XSAVES uses xstate
+	 * compaction. But doing so is a pointless exercise because most
+	 * components have an all zeros init state except for the legacy
+	 * ones (FP and SSE). Those can be saved with FXSAVE into the
+	 * legacy area. Adding new features requires to ensure that init
+	 * state is all zeroes or if not to add the necessary handling
+	 * here.
 	 */
-	copy_xregs_to_kernel_booting(&init_fpstate.xsave);
+	fxsave(&init_fpstate.fxsave);
 }
 
 static int xfeature_uncompacted_offset(int xfeature_nr)