diff options
author | Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> | 2014-12-04 11:00:14 +0530 |
---|---|---|
committer | Michael Ellerman <mpe@ellerman.id.au> | 2014-12-05 16:26:15 +1100 |
commit | aefa5688c070727b8729de1aef85cad7b9933fc7 (patch) | |
tree | d6036007b0eca0b325aa3f050defb00f89341209 /arch/powerpc/mm/hash_low_64.S | |
parent | abb90ee7bca5af977b90a0c6be44f631fdacc932 (diff) |
powerpc/mm: don't do tlbie for updatepp request with NO HPTE fault
upatepp can get called for a nohpte fault when we find from the linux
page table that the translation was hashed before. In that case
we are sure that there is no existing translation, hence we could
avoid doing tlbie.
We could possibly race with a parallel fault filling the TLB. But
that should be ok because updatepp is only ever relaxing permissions.
We also look at linux pte permission bits when filling hash pte
permission bits. We also hold the linux pte busy bits while
inserting/updating a hashpte entry, hence a paralle update of
linux pte is not possible. On the other hand mprotect involves
ptep_modify_prot_start which cause a hpte invalidate and not updatepp.
Performance number:
We use randbox_access_bench written by Anton.
Kernel with THP disabled and smaller hash page table size.
86.60% random_access_b [kernel.kallsyms] [k] .native_hpte_updatepp
2.10% random_access_b random_access_bench [.] doit
1.99% random_access_b [kernel.kallsyms] [k] .do_raw_spin_lock
1.85% random_access_b [kernel.kallsyms] [k] .native_hpte_insert
1.26% random_access_b [kernel.kallsyms] [k] .native_flush_hash_range
1.18% random_access_b [kernel.kallsyms] [k] .__delay
0.69% random_access_b [kernel.kallsyms] [k] .native_hpte_remove
0.37% random_access_b [kernel.kallsyms] [k] .clear_user_page
0.34% random_access_b [kernel.kallsyms] [k] .__hash_page_64K
0.32% random_access_b [kernel.kallsyms] [k] fast_exception_return
0.30% random_access_b [kernel.kallsyms] [k] .hash_page_mm
With Fix:
27.54% random_access_b random_access_bench [.] doit
22.90% random_access_b [kernel.kallsyms] [k] .native_hpte_insert
5.76% random_access_b [kernel.kallsyms] [k] .native_hpte_remove
5.20% random_access_b [kernel.kallsyms] [k] fast_exception_return
5.12% random_access_b [kernel.kallsyms] [k] .__hash_page_64K
4.80% random_access_b [kernel.kallsyms] [k] .hash_page_mm
3.31% random_access_b [kernel.kallsyms] [k] data_access_common
1.84% random_access_b [kernel.kallsyms] [k] .trace_hardirqs_on_caller
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Diffstat (limited to 'arch/powerpc/mm/hash_low_64.S')
-rw-r--r-- | arch/powerpc/mm/hash_low_64.S | 15 |
1 files changed, 8 insertions, 7 deletions
diff --git a/arch/powerpc/mm/hash_low_64.S b/arch/powerpc/mm/hash_low_64.S index 5094f32b706e..463174a4a647 100644 --- a/arch/powerpc/mm/hash_low_64.S +++ b/arch/powerpc/mm/hash_low_64.S @@ -46,7 +46,8 @@ /* * _hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid, - * pte_t *ptep, unsigned long trap, int local, int ssize) + * pte_t *ptep, unsigned long trap, unsigned long flags, + * int ssize) * * Adds a 4K page to the hash table in a segment of 4K pages only */ @@ -298,7 +299,7 @@ htab_modify_pte: li r6,MMU_PAGE_4K /* base page size */ li r7,MMU_PAGE_4K /* actual page size */ ld r8,STK_PARAM(R9)(r1) /* segment size */ - ld r9,STK_PARAM(R8)(r1) /* get "local" param */ + ld r9,STK_PARAM(R8)(r1) /* get "flags" param */ .globl htab_call_hpte_updatepp htab_call_hpte_updatepp: bl . /* Patched by htab_finish_init() */ @@ -338,8 +339,8 @@ htab_pte_insert_failure: *****************************************************************************/ /* _hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid, - * pte_t *ptep, unsigned long trap, int local, int ssize, - * int subpg_prot) + * pte_t *ptep, unsigned long trap, unsigned local flags, + * int ssize, int subpg_prot) */ /* @@ -594,7 +595,7 @@ htab_inval_old_hpte: li r5,0 /* PTE.hidx */ li r6,MMU_PAGE_64K /* psize */ ld r7,STK_PARAM(R9)(r1) /* ssize */ - ld r8,STK_PARAM(R8)(r1) /* local */ + ld r8,STK_PARAM(R8)(r1) /* flags */ bl flush_hash_page /* Clear out _PAGE_HPTE_SUB bits in the new linux PTE */ lis r0,_PAGE_HPTE_SUB@h @@ -666,7 +667,7 @@ htab_modify_pte: li r6,MMU_PAGE_4K /* base page size */ li r7,MMU_PAGE_4K /* actual page size */ ld r8,STK_PARAM(R9)(r1) /* segment size */ - ld r9,STK_PARAM(R8)(r1) /* get "local" param */ + ld r9,STK_PARAM(R8)(r1) /* get "flags" param */ .globl htab_call_hpte_updatepp htab_call_hpte_updatepp: bl . /* patched by htab_finish_init() */ @@ -962,7 +963,7 @@ ht64_modify_pte: li r6,MMU_PAGE_64K /* base page size */ li r7,MMU_PAGE_64K /* actual page size */ ld r8,STK_PARAM(R9)(r1) /* segment size */ - ld r9,STK_PARAM(R8)(r1) /* get "local" param */ + ld r9,STK_PARAM(R8)(r1) /* get "flags" param */ .globl ht64_call_hpte_updatepp ht64_call_hpte_updatepp: bl . /* patched by htab_finish_init() */ |