diff options
| author | Christophe Leroy <christophe.leroy@c-s.fr> | 2019-12-02 07:57:30 +0000 |
|---|---|---|
| committer | Michael Ellerman <mpe@ellerman.id.au> | 2020-01-23 21:31:15 +1100 |
| commit | ec0895f08f99515194e9fcfe1338becf6f759d38 (patch) | |
| tree | 7cc3179bddb320ffaac953354f910a27f4bf939f /arch/powerpc/kernel/vdso32/cacheflush.S | |
| parent | 654abc69ef2e69712e6d4e8a6cb9292b97a4aa39 (diff) | |
powerpc/vdso32: inline __get_datapage()
__get_datapage() is only a few instructions to retrieve the
address of the page where the kernel stores data to the VDSO.
By inlining this function into its users, a bl/blr pair and
a mflr/mtlr pair is avoided, plus a few reg moves.
The improvement is noticeable (about 55 nsec/call on an 8xx)
vdsotest before the patch:
gettimeofday: vdso: 731 nsec/call
clock-gettime-realtime-coarse: vdso: 668 nsec/call
clock-gettime-monotonic-coarse: vdso: 745 nsec/call
vdsotest after the patch:
gettimeofday: vdso: 677 nsec/call
clock-gettime-realtime-coarse: vdso: 613 nsec/call
clock-gettime-monotonic-coarse: vdso: 690 nsec/call
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/c39ef7f3dfa25356b01e211d539671f279086c09.1575273217.git.christophe.leroy@c-s.fr
Diffstat (limited to 'arch/powerpc/kernel/vdso32/cacheflush.S')
| -rw-r--r-- | arch/powerpc/kernel/vdso32/cacheflush.S | 9 |
1 files changed, 4 insertions, 5 deletions
diff --git a/arch/powerpc/kernel/vdso32/cacheflush.S b/arch/powerpc/kernel/vdso32/cacheflush.S index 7f882e7b9f43..d178ec8c279d 100644 --- a/arch/powerpc/kernel/vdso32/cacheflush.S +++ b/arch/powerpc/kernel/vdso32/cacheflush.S @@ -8,6 +8,7 @@ #include <asm/processor.h> #include <asm/ppc_asm.h> #include <asm/vdso.h> +#include <asm/vdso_datapage.h> #include <asm/asm-offsets.h> .text @@ -24,14 +25,12 @@ V_FUNCTION_BEGIN(__kernel_sync_dicache) .cfi_startproc mflr r12 .cfi_register lr,r12 - mr r11,r3 - bl __get_datapage@local + get_datapage r10, r0 mtlr r12 - mr r10,r3 lwz r7,CFG_DCACHE_BLOCKSZ(r10) addi r5,r7,-1 - andc r6,r11,r5 /* round low to line bdy */ + andc r6,r3,r5 /* round low to line bdy */ subf r8,r6,r4 /* compute length */ add r8,r8,r5 /* ensure we get enough */ lwz r9,CFG_DCACHE_LOGBLOCKSZ(r10) @@ -48,7 +47,7 @@ V_FUNCTION_BEGIN(__kernel_sync_dicache) lwz r7,CFG_ICACHE_BLOCKSZ(r10) addi r5,r7,-1 - andc r6,r11,r5 /* round low to line bdy */ + andc r6,r3,r5 /* round low to line bdy */ subf r8,r6,r4 /* compute length */ add r8,r8,r5 lwz r9,CFG_ICACHE_LOGBLOCKSZ(r10) |