[PATCH v2 07/17] x86/xstate: replace xsave_cntxt_size and drop XCNTXT_MASK

[Jan Beulich <jbeulich@xxxxxxxx>]

XCNTXT_MASK is effectively embedded in recalculate_xstate(), and
xsave_cntxt_size was redundant with the host CPUID policy's
xstate.max_size field.

Use the host CPUID policy as input (requiring it to be calculated
earlier), thus allowing e.g. "cpuid=no-avx512f" to also result in
avoiding allocation of space for ZMM and mask register state.

Also drop a stale part of an adjacent comment.

Signed-off-by: Jan Beulich <jbeulich@xxxxxxxx>
---
v2: New.

--- a/xen/arch/x86/xstate.c
+++ b/xen/arch/x86/xstate.c
@@ -20,9 +20,10 @@
 /*
  * Maximum size (in byte) of the XSAVE/XRSTOR save area required by all
  * the supported and enabled features on the processor, including the
- * XSAVE.HEADER. We only enable XCNTXT_MASK that we have known.
+ * XSAVE.HEADER. We only enable cpuid_policy_xcr0_max(&host_cpuid_policy).
+ * Note that this identifier should not be usable as an lvalue.
  */
-static u32 __read_mostly xsave_cntxt_size;
+#define xsave_cntxt_size (host_cpuid_policy.xstate.max_size | 0)
 
 /* A 64-bit bitmask of the XSAVE/XRSTOR features supported by processor. */
 u64 __read_mostly xfeature_mask;
@@ -577,8 +578,23 @@ static unsigned int _xstate_ctxt_size(u6
     ASSERT(ok);
     cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
     ASSERT(ebx <= ecx);
-    ok = set_xcr0(act_xcr0);
-    ASSERT(ok);
+
+    /*
+     * When called the very first time from xstate_init(), act_xcr0 (as read
+     * from per-CPU data) is still zero. xstate_init() wants this function to
+     * leave xfeature_mask in place, so avoid restoration in this case (which
+     * would fail anyway).
+     */
+    if ( act_xcr0 )
+    {
+        ok = set_xcr0(act_xcr0);
+        ASSERT(ok);
+    }
+    else
+    {
+        BUG_ON(!ok);
+        ASSERT(xcr0 == xfeature_mask);
+    }
 
     return ebx;
 }
@@ -650,42 +666,35 @@ void xstate_init(struct cpuinfo_x86 *c)
         return;
 
     if ( (bsp && !use_xsave) ||
-         boot_cpu_data.cpuid_level < XSTATE_CPUID )
+         c->cpuid_level < XSTATE_CPUID )
     {
         BUG_ON(!bsp);
         setup_clear_cpu_cap(X86_FEATURE_XSAVE);
         return;
     }
 
-    cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
-    feature_mask = (((u64)edx << 32) | eax) & XCNTXT_MASK;
-    BUG_ON(!valid_xcr0(feature_mask));
-    BUG_ON(!(feature_mask & X86_XCR0_SSE));
-
-    /*
-     * Set CR4_OSXSAVE and run "cpuid" to get xsave_cntxt_size.
-     */
-    set_in_cr4(X86_CR4_OSXSAVE);
-    if ( !set_xcr0(feature_mask) )
-        BUG();
-
     if ( bsp )
     {
+        feature_mask = cpuid_policy_xcr0_max(&host_cpuid_policy);
+        BUG_ON(!valid_xcr0(feature_mask));
+        BUG_ON(!(feature_mask & X86_XCR0_SSE));
+
         xfeature_mask = feature_mask;
-        /*
-         * xsave_cntxt_size is the max size required by enabled features.
-         * We know FP/SSE and YMM about eax, and nothing about edx at present.
-         */
-        xsave_cntxt_size = _xstate_ctxt_size(feature_mask);
+        /* xsave_cntxt_size is the max size required by enabled features. */
         printk("xstate: size: %#x and states: %#"PRIx64"\n",
-               xsave_cntxt_size, xfeature_mask);
-    }
-    else
-    {
-        BUG_ON(xfeature_mask != feature_mask);
-        BUG_ON(xsave_cntxt_size != _xstate_ctxt_size(feature_mask));
+               xsave_cntxt_size, feature_mask);
+
+        set_in_cr4(X86_CR4_OSXSAVE);
     }
 
+    cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
+    feature_mask = (((uint64_t)edx << 32) | eax) & xfeature_mask;
+    BUG_ON(xfeature_mask != feature_mask);
+
+    /* This has the side effect of set_xcr0(feature_mask). */
+    if ( xsave_cntxt_size != _xstate_ctxt_size(feature_mask) )
+        BUG();
+
     if ( setup_xstate_features(bsp) && bsp )
         BUG();
 }
--- a/xen/include/asm-x86/xstate.h
+++ b/xen/include/asm-x86/xstate.h
@@ -30,9 +30,6 @@ extern uint32_t mxcsr_mask;
 #define XSTATE_AREA_MIN_SIZE      (FXSAVE_SIZE + XSAVE_HDR_SIZE)
 
 #define XSTATE_FP_SSE  (X86_XCR0_FP | X86_XCR0_SSE)
-#define XCNTXT_MASK    (X86_XCR0_FP | X86_XCR0_SSE | X86_XCR0_YMM | \
-                        X86_XCR0_OPMASK | X86_XCR0_ZMM | X86_XCR0_HI_ZMM | \
-                        XSTATE_NONLAZY)
 
 #define XSTATE_ALL     (~(1ULL << 63))
 #define XSTATE_NONLAZY (X86_XCR0_BNDREGS | X86_XCR0_BNDCSR | X86_XCR0_PKRU)