aboutsummaryrefslogtreecommitdiffstats
path: root/include/asm-s390/pgalloc.h
diff options
context:
space:
mode:
authorMartin Schwidefsky <schwidefsky@de.ibm.com>2007-10-22 06:52:44 -0400
committerMartin Schwidefsky <schwidefsky@de.ibm.com>2007-10-22 06:52:48 -0400
commitba8a9229ab9e80278c28ad68b15053f65b2b0a7c (patch)
treed73e4f7d352d3b3edf8888973528cb7dd3e953f9 /include/asm-s390/pgalloc.h
parente3d3683d1402c1737687cb698451d545f57c32a7 (diff)
[S390] tlb flush fix.
The current tlb flushing code for page table entries violates the s390 architecture in a small detail. The relevant section from the principles of operation (SA22-7832-02 page 3-47): "A valid table entry must not be changed while it is attached to any CPU and may be used for translation by that CPU except to (1) invalidate the entry by using INVALIDATE PAGE TABLE ENTRY or INVALIDATE DAT TABLE ENTRY, (2) alter bits 56-63 of a page-table entry, or (3) make a change by means of a COMPARE AND SWAP AND PURGE instruction that purges the TLB." That means if one thread of a multithreaded applciation uses a vma while another thread does an unmap on it, the page table entries of that vma needs to get removed with IPTE, IDTE or CSP. In some strange and rare situations a cpu could check-stop (die) because a entry has been pushed out of the TLB that is still needed to complete a (milli-coded) instruction. I've never seen it happen with the current code on any of the supported machines, so right now this is a theoretical problem. But I want to fix it nevertheless, to avoid headaches in the futures. To get this implemented correctly without changing common code the primitives ptep_get_and_clear, ptep_get_and_clear_full and ptep_set_wrprotect need to use the IPTE instruction to invalidate the pte before the new pte value gets stored. If IPTE is always used for the three primitives three important operations will have a performace hit: fork, mprotect and exit_mmap. Time for some workarounds: * 1: ptep_get_and_clear_full is used in unmap_vmas to remove page tables entries in a batched tlb gather operation. If the mmu_gather context passed to unmap_vmas has been started with full_mm_flush==1 or if only one cpu is online or if the only user of a mm_struct is the current process then the fullmm indication in the mmu_gather context is set to one. All TLBs for mm_struct are flushed by the tlb_gather_mmu call. No new TLBs can be created while the unmap is in progress. In this case ptep_get_and_clear_full clears the ptes with a simple store. * 2: ptep_get_and_clear is used in change_protection to clear the ptes from the page tables before they are reentered with the new access flags. At the end of the update flush_tlb_range clears the remaining TLBs. In general the ptep_get_and_clear has to issue IPTE for each pte and flush_tlb_range is a nop. But if there is only one user of the mm_struct then ptep_get_and_clear uses simple stores to do the update and flush_tlb_range will flush the TLBs. * 3: Similar to 2, ptep_set_wrprotect is used in copy_page_range for a fork to make all ptes of a cow mapping read-only. At the end of of copy_page_range dup_mmap will flush the TLBs with a call to flush_tlb_mm. Check for mm->mm_users and if there is only one user avoid using IPTE in ptep_set_wrprotect and let flush_tlb_mm clear the TLBs. Overall for single threaded programs the tlb flush code now performs better, for multi threaded programs it is slightly worse. In particular exit_mmap() now does a single IDTE for the mm and then just frees every page cache reference and every page table page directly without a delay over the mmu_gather structure. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Diffstat (limited to 'include/asm-s390/pgalloc.h')
-rw-r--r--include/asm-s390/pgalloc.h17
1 files changed, 0 insertions, 17 deletions
diff --git a/include/asm-s390/pgalloc.h b/include/asm-s390/pgalloc.h
index e45d3c9a4b7e..6cbbfe4f6749 100644
--- a/include/asm-s390/pgalloc.h
+++ b/include/asm-s390/pgalloc.h
@@ -82,7 +82,6 @@ static inline void pgd_free(pgd_t *pgd)
82 */ 82 */
83#define pmd_alloc_one(mm,address) ({ BUG(); ((pmd_t *)2); }) 83#define pmd_alloc_one(mm,address) ({ BUG(); ((pmd_t *)2); })
84#define pmd_free(x) do { } while (0) 84#define pmd_free(x) do { } while (0)
85#define __pmd_free_tlb(tlb,x) do { } while (0)
86#define pgd_populate(mm, pmd, pte) BUG() 85#define pgd_populate(mm, pmd, pte) BUG()
87#define pgd_populate_kernel(mm, pmd, pte) BUG() 86#define pgd_populate_kernel(mm, pmd, pte) BUG()
88#else /* __s390x__ */ 87#else /* __s390x__ */
@@ -118,12 +117,6 @@ static inline void pmd_free (pmd_t *pmd)
118 free_pages((unsigned long) pmd, PMD_ALLOC_ORDER); 117 free_pages((unsigned long) pmd, PMD_ALLOC_ORDER);
119} 118}
120 119
121#define __pmd_free_tlb(tlb,pmd) \
122 do { \
123 tlb_flush_mmu(tlb, 0, 0); \
124 pmd_free(pmd); \
125 } while (0)
126
127static inline void 120static inline void
128pgd_populate_kernel(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmd) 121pgd_populate_kernel(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmd)
129{ 122{
@@ -224,14 +217,4 @@ static inline void pte_free(struct page *pte)
224 __free_page(pte); 217 __free_page(pte);
225} 218}
226 219
227#define __pte_free_tlb(tlb, pte) \
228({ \
229 struct mmu_gather *__tlb = (tlb); \
230 struct page *__pte = (pte); \
231 struct page *shadow_page = get_shadow_page(__pte); \
232 if (shadow_page) \
233 tlb_remove_page(__tlb, shadow_page); \
234 tlb_remove_page(__tlb, __pte); \
235})
236
237#endif /* _S390_PGALLOC_H */ 220#endif /* _S390_PGALLOC_H */