x86/fpu/xstate: Fix supervisor xstate component offset

CPUID function 0x0d, sub function (i, i > 1) returns in ebx the offset of
xstate component i. Zero is returned for a supervisor state. A supervisor
state can only be saved by XSAVES and XSAVES uses a compacted format.
There is no fixed offset for a supervisor state. This patch checks and
makes sure a supervisor state offset is not recorded or mis-used. This has
no effect in practice as we currently use no supervisor states, but it
would be good to fix.

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/81b29e40d35d4cec9f2511a856fe769f34935a3f.1466179491.git.yu-cheng.yu@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

3 files changed, 43 insertions, 23 deletions

diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
index 36b90bbfc69f..12dd648735b6 100644
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/types.h
@@ -122,6 +122,7 @@ enum xfeature {
 #define XFEATURE_MASK_OPMASK            (1 << XFEATURE_OPMASK)
 #define XFEATURE_MASK_ZMM_Hi256         (1 << XFEATURE_ZMM_Hi256)
 #define XFEATURE_MASK_Hi16_ZMM          (1 << XFEATURE_Hi16_ZMM)
+#define XFEATURE_MASK_PT                (1 << XFEATURE_PT_UNIMPLEMENTED_SO_FAR)
 #define XFEATURE_MASK_PKRU              (1 << XFEATURE_PKRU)
 
 #define XFEATURE_MASK_FPSSE             (XFEATURE_MASK_FP | XFEATURE_MASK_SSE)
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index d812cf361282..92f376ccc999 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -18,6 +18,9 @@
 #define XSAVE_YMM_SIZE      256
 #define XSAVE_YMM_OFFSET    (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET)
 
+/* Supervisor features */
+#define XFEATURE_MASK_SUPERVISOR (XFEATURE_MASK_PT)
+
 /* Supported features which support lazy state saving */
 #define XFEATURE_MASK_LAZY      (XFEATURE_MASK_FP | \
                                  XFEATURE_MASK_SSE | \
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 7963029cb4ad..02786fb7a1e8 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -112,6 +112,27 @@ int cpu_has_xfeatures(u64 xfeatures_needed, const char **feature_name)
 }
 EXPORT_SYMBOL_GPL(cpu_has_xfeatures);
 
+static int xfeature_is_supervisor(int xfeature_nr)
+{
+        /*
+         * We currently do not support supervisor states, but if
+         * we did, we could find out like this.
+         *
+         * SDM says: If state component 'i' is a user state component,
+         * ECX[0] return 0; if state component i is a supervisor
+         * state component, ECX[0] returns 1.
+         */
+        u32 eax, ebx, ecx, edx;
+
+        cpuid_count(XSTATE_CPUID, xfeature_nr, &eax, &ebx, &ecx, &edx);
+        return !!(ecx & 1);
+}
+
+static int xfeature_is_user(int xfeature_nr)
+{
+        return !xfeature_is_supervisor(xfeature_nr);
+}
+
 /*
  * When executing XSAVEOPT (or other optimized XSAVE instructions), if
  * a processor implementation detects that an FPU state component is still
@@ -230,7 +251,14 @@ static void __init setup_xstate_features(void)
                         continue;
 
                 cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx);
-                xstate_offsets[i] = ebx;
+
+                /*
+                 * If an xfeature is supervisor state, the offset
+                 * in EBX is invalid. We leave it to -1.
+                 */
+                if (xfeature_is_user(i))
+                        xstate_offsets[i] = ebx;
+
                 xstate_sizes[i] = eax;
                 /*
                  * In our xstate size checks, we assume that the
@@ -375,32 +403,20 @@ static void __init setup_init_fpu_buf(void)
         copy_xregs_to_kernel_booting(&init_fpstate.xsave);
 }
 
-static int xfeature_is_supervisor(int xfeature_nr)
-{
-        /*
-         * We currently do not support supervisor states, but if
-         * we did, we could find out like this.
-         *
-         * SDM says: If state component i is a user state component,
-         * ECX[0] return 0; if state component i is a supervisor
-         * state component, ECX[0] returns 1.
-        u32 eax, ebx, ecx, edx;
-        cpuid_count(XSTATE_CPUID, xfeature_nr, &eax, &ebx, &ecx, &edx;
-        return !!(ecx & 1);
-        */
-        return 0;
-}
-/*
-static int xfeature_is_user(int xfeature_nr)
-{
-        return !xfeature_is_supervisor(xfeature_nr);
-}
-*/
-
 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 & (1 << 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;