[xen staging] x86/xstate: Switch back to for_each_set_bit()

[patchbot@xxxxxxx]

commit 20885a36ce114f235d9d38cfcf4952c72ecda051
Author:     Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
AuthorDate: Wed Jun 19 20:39:54 2024 +0100
Commit:     Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
CommitDate: Fri Aug 23 21:50:57 2024 +0100

    x86/xstate: Switch back to for_each_set_bit()
    
    In all 3 examples, we're iterating over a scaler.  They have an upper bound 
of
    63 which is to exclude the top bit; the COMPRESSED bit.
    
    recalculate_xstate() calculates xstates directly and doesn't set the
    COMPRESSED bit.  Both xstate_{un,}compressed_size() take architectural
    register values, neither of which permit the COMPRESSED bit either.
    
    xstate_uncompressed_size() has an ASSERT() covering this properly; add a
    equivelent ASSERT() to xstate_compressed_size() too.
    
    This alone produces:
    
      add/remove: 0/0 grow/shrink: 0/4 up/down: 0/-161 (-161)
      Function                                     old     new   delta
      compress_xsave_states                         66      58      -8
      xstate_uncompressed_size                     119      71     -48
      xstate_compressed_size                       124      76     -48
      recalculate_xstate                           347     290     -57
    
    where xstate_{un,}compressed_size() have practically halved in size despite
    being small before.
    
    The change in compress_xsave_states() is unexpected.  The function is almost
    entirely dead code, and within what remains there's a smaller stack frame.  
I
    suspect it's leftovers that the optimiser couldn't fully discard.
    
    Signed-off-by: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
    Reviewed-by: Jan Beulich <jbeulich@xxxxxxxx>
---
 xen/arch/x86/cpu-policy.c |  4 ++--
 xen/arch/x86/xstate.c     | 10 ++++++----
 2 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/xen/arch/x86/cpu-policy.c b/xen/arch/x86/cpu-policy.c
index 649ab6088f..888e7ac4d4 100644
--- a/xen/arch/x86/cpu-policy.c
+++ b/xen/arch/x86/cpu-policy.c
@@ -193,7 +193,7 @@ static void sanitise_featureset(uint32_t *fs)
 static void recalculate_xstate(struct cpu_policy *p)
 {
     uint64_t xstates = XSTATE_FP_SSE;
-    unsigned int i, ecx_mask = 0, Da1 = p->xstate.Da1;
+    unsigned int ecx_mask = 0, Da1 = p->xstate.Da1;
 
     /*
      * The Da1 leaf is the only piece of information preserved in the common
@@ -237,7 +237,7 @@ static void recalculate_xstate(struct cpu_policy *p)
     /* Subleafs 2+ */
     xstates &= ~XSTATE_FP_SSE;
     BUILD_BUG_ON(ARRAY_SIZE(p->xstate.comp) < 63);
-    bitmap_for_each ( i, &xstates, 63 )
+    for_each_set_bit ( i, xstates )
     {
         /*
          * Pass through size (eax) and offset (ebx) directly.  Visbility of
diff --git a/xen/arch/x86/xstate.c b/xen/arch/x86/xstate.c
index 13fae41504..57a0749f0d 100644
--- a/xen/arch/x86/xstate.c
+++ b/xen/arch/x86/xstate.c
@@ -589,7 +589,7 @@ static bool valid_xcr0(uint64_t xcr0)
 
 unsigned int xstate_uncompressed_size(uint64_t xcr0)
 {
-    unsigned int size = XSTATE_AREA_MIN_SIZE, i;
+    unsigned int size = XSTATE_AREA_MIN_SIZE;
 
     /* Non-XCR0 states don't exist in an uncompressed image. */
     ASSERT((xcr0 & ~X86_XCR0_STATES) == 0);
@@ -606,7 +606,7 @@ unsigned int xstate_uncompressed_size(uint64_t xcr0)
      * with respect their index.
      */
     xcr0 &= ~(X86_XCR0_SSE | X86_XCR0_X87);
-    bitmap_for_each ( i, &xcr0, 63 )
+    for_each_set_bit ( i, xcr0 )
     {
         const struct xstate_component *c = &raw_cpu_policy.xstate.comp[i];
         unsigned int s = c->offset + c->size;
@@ -621,7 +621,9 @@ unsigned int xstate_uncompressed_size(uint64_t xcr0)
 
 unsigned int xstate_compressed_size(uint64_t xstates)
 {
-    unsigned int i, size = XSTATE_AREA_MIN_SIZE;
+    unsigned int size = XSTATE_AREA_MIN_SIZE;
+
+    ASSERT((xstates & ~(X86_XCR0_STATES | X86_XSS_STATES)) == 0);
 
     if ( xstates == 0 )
         return 0;
@@ -634,7 +636,7 @@ unsigned int xstate_compressed_size(uint64_t xstates)
      * componenets require aligning to 64 first.
      */
     xstates &= ~(X86_XCR0_SSE | X86_XCR0_X87);
-    bitmap_for_each ( i, &xstates, 63 )
+    for_each_set_bit ( i, xstates )
     {
         const struct xstate_component *c = &raw_cpu_policy.xstate.comp[i];
 
--
generated by git-patchbot for /home/xen/git/xen.git#staging