x86/fpu: Add FPU state copying quirk to handle XRSTOR failure on Intel Skylake CPUs

On Skylake CPUs I noticed that XRSTOR is unable to deal with states
created by copyout_from_xsaves() if the xstate has only SSE/YMM state, and
no FP state. That is, xfeatures had XFEATURE_MASK_SSE set, but not
XFEATURE_MASK_FP.

The reason is that part of the SSE/YMM state lives in the MXCSR and
MXCSR_FLAGS fields of the FP state.

Ensure that whenever we copy SSE or YMM state around, the MXCSR and
MXCSR_FLAGS fields are also copied around.

Signed-off-by: Rik van Riel <[email protected]>
Cc: Andrew Morton <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Borislav Petkov <[email protected]>
Cc: Borislav Petkov <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: Eric Biggers <[email protected]>
Cc: Fenghua Yu <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Oleg Nesterov <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Yu-cheng Yu <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>

Author: Rik van Riel

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

@@ -68,6 +68,9 @@ struct fxregs_state {
 /* Default value for fxregs_state.mxcsr: */
 #define MXCSR_DEFAULT		0x1f80
 
+/* Copy both mxcsr & mxcsr_flags with a single u64 memcpy: */
+#define MXCSR_AND_FLAGS_SIZE sizeof(u64)
+
 /*
  * Software based FPU emulation state. This is arbitrary really,
  * it matches the x87 format to make it easier to understand:

arch/x86/kernel/fpu/xstate.c

@@ -920,6 +920,23 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
 }
 #endif /* ! CONFIG_ARCH_HAS_PKEYS */
 
+/*
+ * Weird legacy quirk: SSE and YMM states store information in the
+ * MXCSR and MXCSR_FLAGS fields of the FP area. That means if the FP
+ * area is marked as unused in the xfeatures header, we need to copy
+ * MXCSR and MXCSR_FLAGS if either SSE or YMM are in use.
+ */
+static inline bool xfeatures_mxcsr_quirk(u64 xfeatures)
+{
+	if (!(xfeatures & (XFEATURE_MASK_SSE|XFEATURE_MASK_YMM)))
+		return 0;
+
+	if (xfeatures & XFEATURE_MASK_FP)
+		return 0;
+
+	return 1;
+}
+
 /*
  * This is similar to user_regset_copyout(), but will not add offset to
  * the source data pointer or increment pos, count, kbuf, and ubuf.
@@ -988,6 +1005,12 @@ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int of
 
 	}
 
+	if (xfeatures_mxcsr_quirk(header.xfeatures)) {
+		offset = offsetof(struct fxregs_state, mxcsr);
+		size = MXCSR_AND_FLAGS_SIZE;
+		__copy_xstate_to_kernel(kbuf, &xsave->i387.mxcsr, offset, size, size_total);
+	}
+
 	/*
 	 * Fill xsave->i387.sw_reserved value for ptrace frame:
 	 */
@@ -1070,6 +1093,12 @@ int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned i
 
 	}
 
+	if (xfeatures_mxcsr_quirk(header.xfeatures)) {
+		offset = offsetof(struct fxregs_state, mxcsr);
+		size = MXCSR_AND_FLAGS_SIZE;
+		__copy_xstate_to_user(ubuf, &xsave->i387.mxcsr, offset, size, size_total);
+	}
+
 	/*
 	 * Fill xsave->i387.sw_reserved value for ptrace frame:
 	 */
@@ -1122,6 +1151,12 @@ int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf)
 		}
 	}
 
+	if (xfeatures_mxcsr_quirk(xfeatures)) {
+		offset = offsetof(struct fxregs_state, mxcsr);
+		size = MXCSR_AND_FLAGS_SIZE;
+		memcpy(&xsave->i387.mxcsr, kbuf + offset, size);
+	}
+
 	/*
 	 * The state that came in from userspace was user-state only.
 	 * Mask all the user states out of 'xfeatures':
@@ -1177,6 +1212,13 @@ int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf)
 		}
 	}
 
+	if (xfeatures_mxcsr_quirk(xfeatures)) {
+		offset = offsetof(struct fxregs_state, mxcsr);
+		size = MXCSR_AND_FLAGS_SIZE;
+		if (__copy_from_user(&xsave->i387.mxcsr, ubuf + offset, size))
+			return -EFAULT;
+	}
+
 	/*
 	 * The state that came in from userspace was user-state only.
 	 * Mask all the user states out of 'xfeatures':