Merge branch 'linus' into x86/delay

Conflicts:

	arch/x86/kernel/tsc_32.c

Signed-off-by: Ingo Molnar <mingo@elte.hu>

2 files changed, 22 insertions, 28 deletions

diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index 70bebd310408..ee1c3f635157 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -217,19 +217,19 @@ ENTRY(copy_user_generic_unrolled)
         /* table sorted by exception address */
         .section __ex_table,"a"
         .align 8
-        .quad .Ls1,.Ls1e
-        .quad .Ls2,.Ls2e
-        .quad .Ls3,.Ls3e
-        .quad .Ls4,.Ls4e
-        .quad .Ld1,.Ls1e
+        .quad .Ls1,.Ls1e        /* Ls1-Ls4 have copied zero bytes */
+        .quad .Ls2,.Ls1e
+        .quad .Ls3,.Ls1e
+        .quad .Ls4,.Ls1e
+        .quad .Ld1,.Ls1e        /* Ld1-Ld4 have copied 0-24 bytes */
         .quad .Ld2,.Ls2e
         .quad .Ld3,.Ls3e
         .quad .Ld4,.Ls4e
-        .quad .Ls5,.Ls5e
-        .quad .Ls6,.Ls6e
-        .quad .Ls7,.Ls7e
-        .quad .Ls8,.Ls8e
-        .quad .Ld5,.Ls5e
+        .quad .Ls5,.Ls5e        /* Ls5-Ls8 have copied 32 bytes */
+        .quad .Ls6,.Ls5e
+        .quad .Ls7,.Ls5e
+        .quad .Ls8,.Ls5e
+        .quad .Ld5,.Ls5e        /* Ld5-Ld8 have copied 32-56 bytes */
         .quad .Ld6,.Ls6e
         .quad .Ld7,.Ls7e
         .quad .Ld8,.Ls8e
@@ -244,11 +244,8 @@ ENTRY(copy_user_generic_unrolled)
         .quad .Le5,.Le_zero
         .previous
 
-        /* compute 64-offset for main loop. 8 bytes accuracy with error on the
-           pessimistic side. this is gross. it would be better to fix the
-           interface. */
         /* eax: zero, ebx: 64 */
-.Ls1e:  addl $8,%eax
+.Ls1e:  addl $8,%eax            /* eax is bytes left uncopied within the loop (Ls1e: 64 .. Ls8e: 8) */
 .Ls2e:  addl $8,%eax
 .Ls3e:  addl $8,%eax
 .Ls4e:  addl $8,%eax
diff --git a/arch/x86/lib/copy_user_nocache_64.S b/arch/x86/lib/copy_user_nocache_64.S
index 5196762b3b0e..9d3d1ab83763 100644
--- a/arch/x86/lib/copy_user_nocache_64.S
+++ b/arch/x86/lib/copy_user_nocache_64.S
@@ -145,19 +145,19 @@ ENTRY(__copy_user_nocache)
         /* table sorted by exception address */
         .section __ex_table,"a"
         .align 8
-        .quad .Ls1,.Ls1e
-        .quad .Ls2,.Ls2e
-        .quad .Ls3,.Ls3e
-        .quad .Ls4,.Ls4e
-        .quad .Ld1,.Ls1e
+        .quad .Ls1,.Ls1e        /* .Ls[1-4] - 0 bytes copied */
+        .quad .Ls2,.Ls1e
+        .quad .Ls3,.Ls1e
+        .quad .Ls4,.Ls1e
+        .quad .Ld1,.Ls1e        /* .Ld[1-4] - 0..24 bytes coped */
         .quad .Ld2,.Ls2e
         .quad .Ld3,.Ls3e
         .quad .Ld4,.Ls4e
-        .quad .Ls5,.Ls5e
-        .quad .Ls6,.Ls6e
-        .quad .Ls7,.Ls7e
-        .quad .Ls8,.Ls8e
-        .quad .Ld5,.Ls5e
+        .quad .Ls5,.Ls5e        /* .Ls[5-8] - 32 bytes copied */
+        .quad .Ls6,.Ls5e
+        .quad .Ls7,.Ls5e
+        .quad .Ls8,.Ls5e
+        .quad .Ld5,.Ls5e        /* .Ld[5-8] - 32..56 bytes copied */
         .quad .Ld6,.Ls6e
         .quad .Ld7,.Ls7e
         .quad .Ld8,.Ls8e
@@ -172,11 +172,8 @@ ENTRY(__copy_user_nocache)
         .quad .Le5,.Le_zero
         .previous
 
-        /* compute 64-offset for main loop. 8 bytes accuracy with error on the
-           pessimistic side. this is gross. it would be better to fix the
-           interface. */
         /* eax: zero, ebx: 64 */
-.Ls1e:  addl $8,%eax
+.Ls1e:  addl $8,%eax    /* eax: bytes left uncopied: Ls1e: 64 .. Ls8e: 8 */
 .Ls2e:  addl $8,%eax
 .Ls3e:  addl $8,%eax
 .Ls4e:  addl $8,%eax