diff options
Diffstat (limited to 'arch/powerpc/mm')
| -rw-r--r-- | arch/powerpc/mm/gup.c | 13 | ||||
| -rw-r--r-- | arch/powerpc/mm/mem.c | 7 | ||||
| -rw-r--r-- | arch/powerpc/mm/numa.c | 16 | ||||
| -rw-r--r-- | arch/powerpc/mm/pgtable_64.c | 5 | ||||
| -rw-r--r-- | arch/powerpc/mm/tlb_low_64e.S | 66 | ||||
| -rw-r--r-- | arch/powerpc/mm/tlb_nohash.c | 11 |
6 files changed, 93 insertions, 25 deletions
diff --git a/arch/powerpc/mm/gup.c b/arch/powerpc/mm/gup.c index c5f734e20b0f..d8746684f606 100644 --- a/arch/powerpc/mm/gup.c +++ b/arch/powerpc/mm/gup.c @@ -36,6 +36,11 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, do { pte_t pte = ACCESS_ONCE(*ptep); struct page *page; + /* + * Similar to the PMD case, NUMA hinting must take slow path + */ + if (pte_numa(pte)) + return 0; if ((pte_val(pte) & mask) != result) return 0; @@ -75,6 +80,14 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, if (pmd_none(pmd) || pmd_trans_splitting(pmd)) return 0; if (pmd_huge(pmd) || pmd_large(pmd)) { + /* + * NUMA hinting faults need to be handled in the GUP + * slowpath for accounting purposes and so that they + * can be serialised against THP migration. + */ + if (pmd_numa(pmd)) + return 0; + if (!gup_hugepte((pte_t *)pmdp, PMD_SIZE, addr, next, write, pages, nr)) return 0; diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 4b5cd5c2594d..2c8e90f5789e 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -139,9 +139,14 @@ int arch_remove_memory(u64 start, u64 size) unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; struct zone *zone; + int ret; zone = page_zone(pfn_to_page(start_pfn)); - return __remove_pages(zone, start_pfn, nr_pages); + ret = __remove_pages(zone, start_pfn, nr_pages); + if (!ret && (ppc_md.remove_memory)) + ret = ppc_md.remove_memory(start, size); + + return ret; } #endif #endif /* CONFIG_MEMORY_HOTPLUG */ diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 30a42e24bf14..3b181b22cd46 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -232,6 +232,7 @@ int __node_distance(int a, int b) return distance; } +EXPORT_SYMBOL(__node_distance); static void initialize_distance_lookup_table(int nid, const __be32 *associativity) @@ -1591,6 +1592,20 @@ int arch_update_cpu_topology(void) cpu = cpu_last_thread_sibling(cpu); } + /* + * In cases where we have nothing to update (because the updates list + * is too short or because the new topology is same as the old one), + * skip invoking update_cpu_topology() via stop-machine(). This is + * necessary (and not just a fast-path optimization) since stop-machine + * can end up electing a random CPU to run update_cpu_topology(), and + * thus trick us into setting up incorrect cpu-node mappings (since + * 'updates' is kzalloc()'ed). + * + * And for the similar reason, we will skip all the following updating. + */ + if (!cpumask_weight(&updated_cpus)) + goto out; + stop_machine(update_cpu_topology, &updates[0], &updated_cpus); /* @@ -1612,6 +1627,7 @@ int arch_update_cpu_topology(void) changed = 1; } +out: kfree(updates); return changed; } diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index 62bf5e8e78da..f6ce1f111f5b 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -647,6 +647,11 @@ void pmdp_splitting_flush(struct vm_area_struct *vma, if (old & _PAGE_HASHPTE) hpte_do_hugepage_flush(vma->vm_mm, address, pmdp); } + /* + * This ensures that generic code that rely on IRQ disabling + * to prevent a parallel THP split work as expected. + */ + kick_all_cpus_sync(); } /* diff --git a/arch/powerpc/mm/tlb_low_64e.S b/arch/powerpc/mm/tlb_low_64e.S index c95eb323e9ae..356e8b41fb09 100644 --- a/arch/powerpc/mm/tlb_low_64e.S +++ b/arch/powerpc/mm/tlb_low_64e.S @@ -39,37 +39,49 @@ * * **********************************************************************/ +/* + * Note that, unlike non-bolted handlers, TLB_EXFRAME is not + * modified by the TLB miss handlers themselves, since the TLB miss + * handler code will not itself cause a recursive TLB miss. + * + * TLB_EXFRAME will be modified when crit/mc/debug exceptions are + * entered/exited. + */ .macro tlb_prolog_bolted intnum addr - mtspr SPRN_SPRG_GEN_SCRATCH,r13 + mtspr SPRN_SPRG_GEN_SCRATCH,r12 + mfspr r12,SPRN_SPRG_TLB_EXFRAME + std r13,EX_TLB_R13(r12) + std r10,EX_TLB_R10(r12) mfspr r13,SPRN_SPRG_PACA - std r10,PACA_EXTLB+EX_TLB_R10(r13) + mfcr r10 - std r11,PACA_EXTLB+EX_TLB_R11(r13) + std r11,EX_TLB_R11(r12) #ifdef CONFIG_KVM_BOOKE_HV BEGIN_FTR_SECTION mfspr r11, SPRN_SRR1 END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV) #endif DO_KVM \intnum, SPRN_SRR1 - std r16,PACA_EXTLB+EX_TLB_R16(r13) + std r16,EX_TLB_R16(r12) mfspr r16,\addr /* get faulting address */ - std r14,PACA_EXTLB+EX_TLB_R14(r13) + std r14,EX_TLB_R14(r12) ld r14,PACAPGD(r13) - std r15,PACA_EXTLB+EX_TLB_R15(r13) - std r10,PACA_EXTLB+EX_TLB_CR(r13) - TLB_MISS_PROLOG_STATS_BOLTED + std r15,EX_TLB_R15(r12) + std r10,EX_TLB_CR(r12) + TLB_MISS_PROLOG_STATS .endm .macro tlb_epilog_bolted - ld r14,PACA_EXTLB+EX_TLB_CR(r13) - ld r10,PACA_EXTLB+EX_TLB_R10(r13) - ld r11,PACA_EXTLB+EX_TLB_R11(r13) + ld r14,EX_TLB_CR(r12) + ld r10,EX_TLB_R10(r12) + ld r11,EX_TLB_R11(r12) + ld r13,EX_TLB_R13(r12) mtcr r14 - ld r14,PACA_EXTLB+EX_TLB_R14(r13) - ld r15,PACA_EXTLB+EX_TLB_R15(r13) - TLB_MISS_RESTORE_STATS_BOLTED - ld r16,PACA_EXTLB+EX_TLB_R16(r13) - mfspr r13,SPRN_SPRG_GEN_SCRATCH + ld r14,EX_TLB_R14(r12) + ld r15,EX_TLB_R15(r12) + TLB_MISS_RESTORE_STATS + ld r16,EX_TLB_R16(r12) + mfspr r12,SPRN_SPRG_GEN_SCRATCH .endm /* Data TLB miss */ @@ -284,7 +296,7 @@ itlb_miss_fault_bolted: * r14 = page table base * r13 = PACA * r11 = tlb_per_core ptr - * r10 = crap (free to use) + * r10 = cpu number */ tlb_miss_common_e6500: /* @@ -293,15 +305,18 @@ tlb_miss_common_e6500: * * MAS6:IND should be already set based on MAS4 */ - addi r10,r11,TCD_LOCK -1: lbarx r15,0,r10 +1: lbarx r15,0,r11 + lhz r10,PACAPACAINDEX(r13) cmpdi r15,0 + cmpdi cr1,r15,1 /* set cr1.eq = 0 for non-recursive */ bne 2f - li r15,1 - stbcx. r15,0,r10 + stbcx. r10,0,r11 bne 1b +3: .subsection 1 -2: lbz r15,0(r10) +2: cmpd cr1,r15,r10 /* recursive lock due to mcheck/crit/etc? */ + beq cr1,3b /* unlock will happen if cr1.eq = 0 */ + lbz r15,0(r11) cmpdi r15,0 bne 2b b 1b @@ -379,9 +394,11 @@ tlb_miss_common_e6500: tlb_miss_done_e6500: .macro tlb_unlock_e6500 + beq cr1,1f /* no unlock if lock was recursively grabbed */ li r15,0 isync - stb r15,TCD_LOCK(r11) + stb r15,0(r11) +1: .endm tlb_unlock_e6500 @@ -1091,7 +1108,8 @@ tlb_load_linear: ld r11,PACATOC(r13) ld r11,linear_map_top@got(r11) ld r10,0(r11) - cmpld cr0,r10,r16 + tovirt(10,10) + cmpld cr0,r16,r10 bge tlb_load_linear_fault /* MAS1 need whole new setup. */ diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c index b37a58e1c92d..ae3d5b799b90 100644 --- a/arch/powerpc/mm/tlb_nohash.c +++ b/arch/powerpc/mm/tlb_nohash.c @@ -144,6 +144,15 @@ int mmu_vmemmap_psize; /* Page size used for the virtual mem map */ int book3e_htw_mode; /* HW tablewalk? Value is PPC_HTW_* */ unsigned long linear_map_top; /* Top of linear mapping */ + +/* + * Number of bytes to add to SPRN_SPRG_TLB_EXFRAME on crit/mcheck/debug + * exceptions. This is used for bolted and e6500 TLB miss handlers which + * do not modify this SPRG in the TLB miss code; for other TLB miss handlers, + * this is set to zero. + */ +int extlb_level_exc; + #endif /* CONFIG_PPC64 */ #ifdef CONFIG_PPC_FSL_BOOK3E @@ -559,6 +568,7 @@ static void setup_mmu_htw(void) break; #ifdef CONFIG_PPC_FSL_BOOK3E case PPC_HTW_E6500: + extlb_level_exc = EX_TLB_SIZE; patch_exception(0x1c0, exc_data_tlb_miss_e6500_book3e); patch_exception(0x1e0, exc_instruction_tlb_miss_e6500_book3e); break; @@ -652,6 +662,7 @@ static void __early_init_mmu(int boot_cpu) memblock_enforce_memory_limit(linear_map_top); if (book3e_htw_mode == PPC_HTW_NONE) { + extlb_level_exc = EX_TLB_SIZE; patch_exception(0x1c0, exc_data_tlb_miss_bolted_book3e); patch_exception(0x1e0, exc_instruction_tlb_miss_bolted_book3e); |