x86/fpu/xstate: Align xstate components according to CPUID

CPUID function 0x0d, sub function (i, i > 1) returns in ecx[1] the
alignment requirement of component 'i' when the compacted format is used.

If ecx[1] is 0, component 'i' is located immediately following the preceding
component. If ecx[1] is 1, component 'i' is located on the next 64-byte
boundary following the preceding component.

Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
Reviewed-by: Dave Hansen <dave.hansen@intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Quentin Casasnovas <quentin.casasnovas@oracle.com>
Cc: Ravi V. Shankar <ravi.v.shankar@intel.com>
Cc: Sai Praneeth Prakhya <sai.praneeth.prakhya@intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/331e2bef1a0a7a584f06adde095b6bbfbe166472.1466179491.git.yu-cheng.yu@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 0b01f00..7963029 100644 (file)
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -269,6 +269,33 @@ static void __init print_xstate_features(void)
        print_xstate_feature(XFEATURE_MASK_PKRU);
 }
 
+/*
+ * This check is important because it is easy to get XSTATE_*
+ * confused with XSTATE_BIT_*.
+ */
+#define CHECK_XFEATURE(nr) do {                \
+       WARN_ON(nr < FIRST_EXTENDED_XFEATURE);  \
+       WARN_ON(nr >= XFEATURE_MAX);    \
+} 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);
+       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
@@ -306,10 +333,14 @@ static void __init setup_xstate_comp(void)
                else
                        xstate_comp_sizes[i] = 0;
 
-               if (i > FIRST_EXTENDED_XFEATURE)
+               if (i > FIRST_EXTENDED_XFEATURE) {
                        xstate_comp_offsets[i] = xstate_comp_offsets[i-1]
                                        + xstate_comp_sizes[i-1];
 
+                       if (xfeature_is_aligned(i))
+                               xstate_comp_offsets[i] =
+                                       ALIGN(xstate_comp_offsets[i], 64);
+               }
        }
 }
 
@@ -366,33 +397,6 @@ static int xfeature_is_user(int xfeature_nr)
 }
 */
 
-/*
- * This check is important because it is easy to get XSTATE_*
- * confused with XSTATE_BIT_*.
- */
-#define CHECK_XFEATURE(nr) do {                \
-       WARN_ON(nr < FIRST_EXTENDED_XFEATURE);  \
-       WARN_ON(nr >= XFEATURE_MAX);    \
-} 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);
-       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);
-}
-
 static int xfeature_uncompacted_offset(int xfeature_nr)
 {
        u32 eax, ebx, ecx, edx;