[PATCH v2 1/2] x86/fpu: Combine fpu_ctxt and xsave_area in arch_vcpu

[Alejandro Vallejo <alejandro.vallejo@cloud.com>]

fpu_ctxt is either a pointer to the legacy x87/SSE save area (used by FXSAVE) or
a pointer aliased with xsave_area that points to its fpu_sse subfield. Such
subfield is at the base and is identical in size and layout to the legacy
buffer.

This patch merges the 2 pointers in the arch_vcpu into a single XSAVE area. In
the very rare case in which the host doesn't support XSAVE all we're doing is
wasting a tiny amount of memory and trading those for a lot more simplicity in
the code.

Signed-off-by: Alejandro Vallejo <alejandro.vallejo@cloud.com>
---
v2:

  * Added BUILD_BUG_ON(sizeof(x) != sizeof(fpusse_t)) on forceful casts
    involving fpusse_t.
  * Reworded comment on top of vcpu_arch->user_regs
  * Added missing whitespace in x86_emulate/blk.c
---
 xen/arch/x86/domctl.c             |  5 +++-
 xen/arch/x86/hvm/emulate.c        |  4 +--
 xen/arch/x86/hvm/hvm.c            |  5 +++-
 xen/arch/x86/i387.c               | 45 +++++--------------------------
 xen/arch/x86/include/asm/domain.h |  8 +++---
 xen/arch/x86/x86_emulate/blk.c    |  3 ++-
 xen/arch/x86/xstate.c             | 13 ++++++---
 7 files changed, 32 insertions(+), 51 deletions(-)

diff --git a/xen/arch/x86/domctl.c b/xen/arch/x86/domctl.c
index 68b5b46d1a83..bceff6be0ff3 100644
--- a/xen/arch/x86/domctl.c
+++ b/xen/arch/x86/domctl.c
@@ -1344,7 +1344,10 @@ void arch_get_info_guest(struct vcpu *v, vcpu_guest_context_u c)
 #define c(fld) (c.nat->fld)
 #endif
 
-    memcpy(&c.nat->fpu_ctxt, v->arch.fpu_ctxt, sizeof(c.nat->fpu_ctxt));
+    memcpy(&c.nat->fpu_ctxt, &v->arch.xsave_area->fpu_sse,
+           sizeof(c.nat->fpu_ctxt));
+    BUILD_BUG_ON(sizeof(c.nat->fpu_ctxt) != sizeof(fpusse_t));
+
     if ( is_pv_domain(d) )
         c(flags = v->arch.pv.vgc_flags & ~(VGCF_i387_valid|VGCF_in_kernel));
     else
diff --git a/xen/arch/x86/hvm/emulate.c b/xen/arch/x86/hvm/emulate.c
index feb4792cc567..03020542c3ba 100644
--- a/xen/arch/x86/hvm/emulate.c
+++ b/xen/arch/x86/hvm/emulate.c
@@ -2363,7 +2363,7 @@ static int cf_check hvmemul_get_fpu(
         alternative_vcall(hvm_funcs.fpu_dirty_intercept);
     else if ( type == X86EMUL_FPU_fpu )
     {
-        const fpusse_t *fpu_ctxt = curr->arch.fpu_ctxt;
+        const fpusse_t *fpu_ctxt = &curr->arch.xsave_area->fpu_sse;
 
         /*
          * Latch current register state so that we can back out changes
@@ -2403,7 +2403,7 @@ static void cf_check hvmemul_put_fpu(
 
     if ( aux )
     {
-        fpusse_t *fpu_ctxt = curr->arch.fpu_ctxt;
+        fpusse_t *fpu_ctxt = &curr->arch.xsave_area->fpu_sse;
         bool dval = aux->dval;
         int mode = hvm_guest_x86_mode(curr);
 
diff --git a/xen/arch/x86/hvm/hvm.c b/xen/arch/x86/hvm/hvm.c
index f49e29faf753..6607dba562a4 100644
--- a/xen/arch/x86/hvm/hvm.c
+++ b/xen/arch/x86/hvm/hvm.c
@@ -916,7 +916,10 @@ static int cf_check hvm_save_cpu_ctxt(struct vcpu *v, hvm_domain_context_t *h)
 
     if ( v->fpu_initialised )
     {
-        memcpy(ctxt.fpu_regs, v->arch.fpu_ctxt, sizeof(ctxt.fpu_regs));
+        memcpy(ctxt.fpu_regs, &v->arch.xsave_area->fpu_sse,
+               sizeof(ctxt.fpu_regs));
+        BUILD_BUG_ON(sizeof(ctxt.fpu_regs) != sizeof(fpusse_t));
+
         ctxt.flags = XEN_X86_FPU_INITIALISED;
     }
 
diff --git a/xen/arch/x86/i387.c b/xen/arch/x86/i387.c
index 134e0bece519..fbb9d3584a3d 100644
--- a/xen/arch/x86/i387.c
+++ b/xen/arch/x86/i387.c
@@ -39,7 +39,7 @@ static inline void fpu_xrstor(struct vcpu *v, uint64_t mask)
 /* Restore x87 FPU, MMX, SSE and SSE2 state */
 static inline void fpu_fxrstor(struct vcpu *v)
 {
-    const fpusse_t *fpu_ctxt = v->arch.fpu_ctxt;
+    const fpusse_t *fpu_ctxt = &v->arch.xsave_area->fpu_sse;
 
     /*
      * Some CPUs don't save/restore FDP/FIP/FOP unless an exception
@@ -151,7 +151,7 @@ static inline void fpu_xsave(struct vcpu *v)
 /* Save x87 FPU, MMX, SSE and SSE2 state */
 static inline void fpu_fxsave(struct vcpu *v)
 {
-    fpusse_t *fpu_ctxt = v->arch.fpu_ctxt;
+    fpusse_t *fpu_ctxt = &v->arch.xsave_area->fpu_sse;
     unsigned int fip_width = v->domain->arch.x87_fip_width;
 
     if ( fip_width != 4 )
@@ -212,7 +212,7 @@ void vcpu_restore_fpu_nonlazy(struct vcpu *v, bool need_stts)
      * above) we also need to restore full state, to prevent subsequently
      * saving state belonging to another vCPU.
      */
-    if ( v->arch.fully_eager_fpu || (v->arch.xsave_area && xstate_all(v)) )
+    if ( v->arch.fully_eager_fpu || xstate_all(v) )
     {
         if ( cpu_has_xsave )
             fpu_xrstor(v, XSTATE_ALL);
@@ -299,44 +299,14 @@ void save_fpu_enable(void)
 /* Initialize FPU's context save area */
 int vcpu_init_fpu(struct vcpu *v)
 {
-    int rc;
-
     v->arch.fully_eager_fpu = opt_eager_fpu;
-
-    if ( (rc = xstate_alloc_save_area(v)) != 0 )
-        return rc;
-
-    if ( v->arch.xsave_area )
-        v->arch.fpu_ctxt = &v->arch.xsave_area->fpu_sse;
-    else
-    {
-        BUILD_BUG_ON(__alignof(v->arch.xsave_area->fpu_sse) < 16);
-        v->arch.fpu_ctxt = _xzalloc(sizeof(v->arch.xsave_area->fpu_sse),
-                                    __alignof(v->arch.xsave_area->fpu_sse));
-        if ( v->arch.fpu_ctxt )
-        {
-            fpusse_t *fpu_sse = v->arch.fpu_ctxt;
-
-            fpu_sse->fcw = FCW_DEFAULT;
-            fpu_sse->mxcsr = MXCSR_DEFAULT;
-        }
-        else
-            rc = -ENOMEM;
-    }
-
-    return rc;
+    return xstate_alloc_save_area(v);
 }
 
 void vcpu_setup_fpu(struct vcpu *v, struct xsave_struct *xsave_area,
                     const void *data, unsigned int fcw_default)
 {
-    /*
-     * For the entire function please note that vcpu_init_fpu() (above) points
-     * v->arch.fpu_ctxt into v->arch.xsave_area when XSAVE is available. Hence
-     * accesses through both pointers alias one another, and the shorter form
-     * is used here.
-     */
-    fpusse_t *fpu_sse = v->arch.fpu_ctxt;
+    fpusse_t *fpu_sse = &v->arch.xsave_area->fpu_sse;
 
     ASSERT(!xsave_area || xsave_area == v->arch.xsave_area);
 
@@ -373,10 +343,7 @@ void vcpu_setup_fpu(struct vcpu *v, struct xsave_struct *xsave_area,
 /* Free FPU's context save area */
 void vcpu_destroy_fpu(struct vcpu *v)
 {
-    if ( v->arch.xsave_area )
-        xstate_free_save_area(v);
-    else
-        xfree(v->arch.fpu_ctxt);
+    xstate_free_save_area(v);
 }
 
 /*
diff --git a/xen/arch/x86/include/asm/domain.h b/xen/arch/x86/include/asm/domain.h
index bca3258d69ac..3da60af2a44a 100644
--- a/xen/arch/x86/include/asm/domain.h
+++ b/xen/arch/x86/include/asm/domain.h
@@ -592,11 +592,11 @@ struct pv_vcpu
 struct arch_vcpu
 {
     /*
-     * guest context (mirroring struct vcpu_guest_context) common
-     * between pv and hvm guests
+     * Guest context common between PV and HVM guests. Includes general purpose
+     * registers, segment registers and other parts of the exception frame.
+     *
+     * It doesn't contain FPU state, as that lives in xsave_area instead.
      */
-
-    void              *fpu_ctxt;
     struct cpu_user_regs user_regs;
 
     /* Debug registers. */
diff --git a/xen/arch/x86/x86_emulate/blk.c b/xen/arch/x86/x86_emulate/blk.c
index e790f4f90056..28b54f26fe29 100644
--- a/xen/arch/x86/x86_emulate/blk.c
+++ b/xen/arch/x86/x86_emulate/blk.c
@@ -11,7 +11,8 @@
     !defined(X86EMUL_NO_SIMD)
 # ifdef __XEN__
 #  include <asm/xstate.h>
-#  define FXSAVE_AREA current->arch.fpu_ctxt
+#  define FXSAVE_AREA ((struct x86_fxsr *) \
+                           (void *)&current->arch.xsave_area->fpu_sse)
 # else
 #  define FXSAVE_AREA get_fpu_save_area()
 # endif
diff --git a/xen/arch/x86/xstate.c b/xen/arch/x86/xstate.c
index 5c4144d55e89..850ee31bd18c 100644
--- a/xen/arch/x86/xstate.c
+++ b/xen/arch/x86/xstate.c
@@ -507,9 +507,16 @@ int xstate_alloc_save_area(struct vcpu *v)
     unsigned int size;
 
     if ( !cpu_has_xsave )
-        return 0;
-
-    if ( !is_idle_vcpu(v) || !cpu_has_xsavec )
+    {
+        /*
+         * This is bigger than FXSAVE_SIZE by 64 bytes, but it helps treating
+         * the FPU state uniformly as an XSAVE buffer even if XSAVE is not
+         * available in the host. Note the alignment restriction of the XSAVE
+         * area are stricter than those of the FXSAVE area.
+         */
+        size = XSTATE_AREA_MIN_SIZE;
+    }
+    else if ( !is_idle_vcpu(v) || !cpu_has_xsavec )
     {
         size = xsave_cntxt_size;
         BUG_ON(size < XSTATE_AREA_MIN_SIZE);
-- 
2.45.2