diff options
Diffstat (limited to 'arch/powerpc/mm')
27 files changed, 895 insertions, 300 deletions
diff --git a/arch/powerpc/mm/dma-noncoherent.c b/arch/powerpc/mm/dma-noncoherent.c index 6747eece84a..7b6c1075017 100644 --- a/arch/powerpc/mm/dma-noncoherent.c +++ b/arch/powerpc/mm/dma-noncoherent.c @@ -287,9 +287,7 @@ void __dma_free_coherent(size_t size, void *vaddr) pte_clear(&init_mm, addr, ptep); if (pfn_valid(pfn)) { struct page *page = pfn_to_page(pfn); - - ClearPageReserved(page); - __free_page(page); + __free_reserved_page(page); } } addr += PAGE_SIZE; diff --git a/arch/powerpc/mm/fsl_booke_mmu.c b/arch/powerpc/mm/fsl_booke_mmu.c index 07ba45b0f07..94cd728166d 100644 --- a/arch/powerpc/mm/fsl_booke_mmu.c +++ b/arch/powerpc/mm/fsl_booke_mmu.c @@ -52,6 +52,7 @@ #include <asm/smp.h> #include <asm/machdep.h> #include <asm/setup.h> +#include <asm/paca.h> #include "mmu_decl.h" @@ -171,11 +172,10 @@ unsigned long calc_cam_sz(unsigned long ram, unsigned long virt, return 1UL << camsize; } -unsigned long map_mem_in_cams(unsigned long ram, int max_cam_idx) +static unsigned long map_mem_in_cams_addr(phys_addr_t phys, unsigned long virt, + unsigned long ram, int max_cam_idx) { int i; - unsigned long virt = PAGE_OFFSET; - phys_addr_t phys = memstart_addr; unsigned long amount_mapped = 0; /* Calculate CAM values */ @@ -192,9 +192,23 @@ unsigned long map_mem_in_cams(unsigned long ram, int max_cam_idx) } tlbcam_index = i; +#ifdef CONFIG_PPC64 + get_paca()->tcd.esel_next = i; + get_paca()->tcd.esel_max = mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY; + get_paca()->tcd.esel_first = i; +#endif + return amount_mapped; } +unsigned long map_mem_in_cams(unsigned long ram, int max_cam_idx) +{ + unsigned long virt = PAGE_OFFSET; + phys_addr_t phys = memstart_addr; + + return map_mem_in_cams_addr(phys, virt, ram, max_cam_idx); +} + #ifdef CONFIG_PPC32 #if defined(CONFIG_LOWMEM_CAM_NUM_BOOL) && (CONFIG_LOWMEM_CAM_NUM >= NUM_TLBCAMS) @@ -222,7 +236,9 @@ void __init adjust_total_lowmem(void) /* adjust lowmem size to __max_low_memory */ ram = min((phys_addr_t)__max_low_memory, (phys_addr_t)total_lowmem); + i = switch_to_as1(); __max_low_memory = map_mem_in_cams(ram, CONFIG_LOWMEM_CAM_NUM); + restore_to_as0(i, 0, 0, 1); pr_info("Memory CAM mapping: "); for (i = 0; i < tlbcam_index - 1; i++) @@ -241,4 +257,62 @@ void setup_initial_memory_limit(phys_addr_t first_memblock_base, /* 64M mapped initially according to head_fsl_booke.S */ memblock_set_current_limit(min_t(u64, limit, 0x04000000)); } + +#ifdef CONFIG_RELOCATABLE +int __initdata is_second_reloc; +notrace void __init relocate_init(u64 dt_ptr, phys_addr_t start) +{ + unsigned long base = KERNELBASE; + + kernstart_addr = start; + if (is_second_reloc) { + virt_phys_offset = PAGE_OFFSET - memstart_addr; + return; + } + + /* + * Relocatable kernel support based on processing of dynamic + * relocation entries. Before we get the real memstart_addr, + * We will compute the virt_phys_offset like this: + * virt_phys_offset = stext.run - kernstart_addr + * + * stext.run = (KERNELBASE & ~0x3ffffff) + + * (kernstart_addr & 0x3ffffff) + * When we relocate, we have : + * + * (kernstart_addr & 0x3ffffff) = (stext.run & 0x3ffffff) + * + * hence: + * virt_phys_offset = (KERNELBASE & ~0x3ffffff) - + * (kernstart_addr & ~0x3ffffff) + * + */ + start &= ~0x3ffffff; + base &= ~0x3ffffff; + virt_phys_offset = base - start; + early_get_first_memblock_info(__va(dt_ptr), NULL); + /* + * We now get the memstart_addr, then we should check if this + * address is the same as what the PAGE_OFFSET map to now. If + * not we have to change the map of PAGE_OFFSET to memstart_addr + * and do a second relocation. + */ + if (start != memstart_addr) { + int n; + long offset = start - memstart_addr; + + is_second_reloc = 1; + n = switch_to_as1(); + /* map a 64M area for the second relocation */ + if (memstart_addr > start) + map_mem_in_cams(0x4000000, CONFIG_LOWMEM_CAM_NUM); + else + map_mem_in_cams_addr(start, PAGE_OFFSET + offset, + 0x4000000, CONFIG_LOWMEM_CAM_NUM); + restore_to_as0(n, offset, __va(dt_ptr), 1); + /* We should never reach here */ + panic("Relocation error"); + } +} +#endif #endif diff --git a/arch/powerpc/mm/gup.c b/arch/powerpc/mm/gup.c index 6936547018b..d8746684f60 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; @@ -123,6 +136,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, struct mm_struct *mm = current->mm; unsigned long addr, len, end; unsigned long next; + unsigned long flags; pgd_t *pgdp; int nr = 0; @@ -156,7 +170,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, * So long as we atomically load page table pointers versus teardown, * we can follow the address down to the the page and take a ref on it. */ - local_irq_disable(); + local_irq_save(flags); pgdp = pgd_offset(mm, addr); do { @@ -179,7 +193,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, break; } while (pgdp++, addr = next, addr != end); - local_irq_enable(); + local_irq_restore(flags); return nr; } diff --git a/arch/powerpc/mm/hash_low_64.S b/arch/powerpc/mm/hash_low_64.S index d3cbda62857..057cbbb4c57 100644 --- a/arch/powerpc/mm/hash_low_64.S +++ b/arch/powerpc/mm/hash_low_64.S @@ -148,7 +148,10 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) and r0,r0,r4 /* _PAGE_RW & _PAGE_DIRTY ->r0 bit 30*/ andc r0,r30,r0 /* r0 = pte & ~r0 */ rlwimi r3,r0,32-1,31,31 /* Insert result into PP lsb */ - ori r3,r3,HPTE_R_C /* Always add "C" bit for perf. */ + /* + * Always add "C" bit for perf. Memory coherence is always enabled + */ + ori r3,r3,HPTE_R_C | HPTE_R_M /* We eventually do the icache sync here (maybe inline that * code rather than call a C function...) @@ -156,7 +159,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) BEGIN_FTR_SECTION mr r4,r30 mr r5,r7 - bl .hash_page_do_lazy_icache + bl hash_page_do_lazy_icache END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE) /* At this point, r3 contains new PP bits, save them in @@ -198,7 +201,8 @@ htab_insert_pte: li r8,MMU_PAGE_4K /* page size */ li r9,MMU_PAGE_4K /* actual page size */ ld r10,STK_PARAM(R9)(r1) /* segment size */ -_GLOBAL(htab_call_hpte_insert1) +.globl htab_call_hpte_insert1 +htab_call_hpte_insert1: bl . /* Patched by htab_finish_init() */ cmpdi 0,r3,0 bge htab_pte_insert_ok /* Insertion successful */ @@ -222,7 +226,8 @@ _GLOBAL(htab_call_hpte_insert1) li r8,MMU_PAGE_4K /* page size */ li r9,MMU_PAGE_4K /* actual page size */ ld r10,STK_PARAM(R9)(r1) /* segment size */ -_GLOBAL(htab_call_hpte_insert2) +.globl htab_call_hpte_insert2 +htab_call_hpte_insert2: bl . /* Patched by htab_finish_init() */ cmpdi 0,r3,0 bge+ htab_pte_insert_ok /* Insertion successful */ @@ -239,7 +244,8 @@ _GLOBAL(htab_call_hpte_insert2) 2: and r0,r5,r27 rldicr r3,r0,3,63-3 /* r0 = (hash & mask) << 3 */ /* Call ppc_md.hpte_remove */ -_GLOBAL(htab_call_hpte_remove) +.globl htab_call_hpte_remove +htab_call_hpte_remove: bl . /* Patched by htab_finish_init() */ /* Try all again */ @@ -293,7 +299,8 @@ htab_modify_pte: 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 */ -_GLOBAL(htab_call_hpte_updatepp) +.globl htab_call_hpte_updatepp +htab_call_hpte_updatepp: bl . /* Patched by htab_finish_init() */ /* if we failed because typically the HPTE wasn't really here @@ -457,7 +464,10 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) and r0,r0,r4 /* _PAGE_RW & _PAGE_DIRTY ->r0 bit 30*/ andc r0,r3,r0 /* r0 = pte & ~r0 */ rlwimi r3,r0,32-1,31,31 /* Insert result into PP lsb */ - ori r3,r3,HPTE_R_C /* Always add "C" bit for perf. */ + /* + * Always add "C" bit for perf. Memory coherence is always enabled + */ + ori r3,r3,HPTE_R_C | HPTE_R_M /* We eventually do the icache sync here (maybe inline that * code rather than call a C function...) @@ -465,7 +475,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) BEGIN_FTR_SECTION mr r4,r30 mr r5,r7 - bl .hash_page_do_lazy_icache + bl hash_page_do_lazy_icache END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE) /* At this point, r3 contains new PP bits, save them in @@ -520,7 +530,8 @@ htab_special_pfn: li r8,MMU_PAGE_4K /* page size */ li r9,MMU_PAGE_4K /* actual page size */ ld r10,STK_PARAM(R9)(r1) /* segment size */ -_GLOBAL(htab_call_hpte_insert1) +.globl htab_call_hpte_insert1 +htab_call_hpte_insert1: bl . /* patched by htab_finish_init() */ cmpdi 0,r3,0 bge htab_pte_insert_ok /* Insertion successful */ @@ -548,7 +559,8 @@ _GLOBAL(htab_call_hpte_insert1) li r8,MMU_PAGE_4K /* page size */ li r9,MMU_PAGE_4K /* actual page size */ ld r10,STK_PARAM(R9)(r1) /* segment size */ -_GLOBAL(htab_call_hpte_insert2) +.globl htab_call_hpte_insert2 +htab_call_hpte_insert2: bl . /* patched by htab_finish_init() */ cmpdi 0,r3,0 bge+ htab_pte_insert_ok /* Insertion successful */ @@ -565,7 +577,8 @@ _GLOBAL(htab_call_hpte_insert2) 2: and r0,r5,r27 rldicr r3,r0,3,63-3 /* r0 = (hash & mask) << 3 */ /* Call ppc_md.hpte_remove */ -_GLOBAL(htab_call_hpte_remove) +.globl htab_call_hpte_remove +htab_call_hpte_remove: bl . /* patched by htab_finish_init() */ /* Try all again */ @@ -582,7 +595,7 @@ htab_inval_old_hpte: li r6,MMU_PAGE_64K /* psize */ ld r7,STK_PARAM(R9)(r1) /* ssize */ ld r8,STK_PARAM(R8)(r1) /* local */ - bl .flush_hash_page + bl flush_hash_page /* Clear out _PAGE_HPTE_SUB bits in the new linux PTE */ lis r0,_PAGE_HPTE_SUB@h ori r0,r0,_PAGE_HPTE_SUB@l @@ -654,7 +667,8 @@ htab_modify_pte: 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 */ -_GLOBAL(htab_call_hpte_updatepp) +.globl htab_call_hpte_updatepp +htab_call_hpte_updatepp: bl . /* patched by htab_finish_init() */ /* if we failed because typically the HPTE wasn't really here @@ -795,7 +809,10 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) and r0,r0,r4 /* _PAGE_RW & _PAGE_DIRTY ->r0 bit 30*/ andc r0,r30,r0 /* r0 = pte & ~r0 */ rlwimi r3,r0,32-1,31,31 /* Insert result into PP lsb */ - ori r3,r3,HPTE_R_C /* Always add "C" bit for perf. */ + /* + * Always add "C" bit for perf. Memory coherence is always enabled + */ + ori r3,r3,HPTE_R_C | HPTE_R_M /* We eventually do the icache sync here (maybe inline that * code rather than call a C function...) @@ -803,7 +820,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) BEGIN_FTR_SECTION mr r4,r30 mr r5,r7 - bl .hash_page_do_lazy_icache + bl hash_page_do_lazy_icache END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE) /* At this point, r3 contains new PP bits, save them in @@ -848,7 +865,8 @@ ht64_insert_pte: li r8,MMU_PAGE_64K li r9,MMU_PAGE_64K /* actual page size */ ld r10,STK_PARAM(R9)(r1) /* segment size */ -_GLOBAL(ht64_call_hpte_insert1) +.globl ht64_call_hpte_insert1 +ht64_call_hpte_insert1: bl . /* patched by htab_finish_init() */ cmpdi 0,r3,0 bge ht64_pte_insert_ok /* Insertion successful */ @@ -872,7 +890,8 @@ _GLOBAL(ht64_call_hpte_insert1) li r8,MMU_PAGE_64K li r9,MMU_PAGE_64K /* actual page size */ ld r10,STK_PARAM(R9)(r1) /* segment size */ -_GLOBAL(ht64_call_hpte_insert2) +.globl ht64_call_hpte_insert2 +ht64_call_hpte_insert2: bl . /* patched by htab_finish_init() */ cmpdi 0,r3,0 bge+ ht64_pte_insert_ok /* Insertion successful */ @@ -889,7 +908,8 @@ _GLOBAL(ht64_call_hpte_insert2) 2: and r0,r5,r27 rldicr r3,r0,3,63-3 /* r0 = (hash & mask) << 3 */ /* Call ppc_md.hpte_remove */ -_GLOBAL(ht64_call_hpte_remove) +.globl ht64_call_hpte_remove +ht64_call_hpte_remove: bl . /* patched by htab_finish_init() */ /* Try all again */ @@ -943,7 +963,8 @@ ht64_modify_pte: 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 */ -_GLOBAL(ht64_call_hpte_updatepp) +.globl ht64_call_hpte_updatepp +ht64_call_hpte_updatepp: bl . /* patched by htab_finish_init() */ /* if we failed because typically the HPTE wasn't really here diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c index c33d939120c..cf1d325eae8 100644 --- a/arch/powerpc/mm/hash_native_64.c +++ b/arch/powerpc/mm/hash_native_64.c @@ -35,7 +35,11 @@ #define DBG_LOW(fmt...) #endif +#ifdef __BIG_ENDIAN__ #define HPTE_LOCK_BIT 3 +#else +#define HPTE_LOCK_BIT (56+3) +#endif DEFINE_RAW_SPINLOCK(native_tlbie_lock); @@ -78,17 +82,14 @@ static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize) va &= ~((1ul << mmu_psize_defs[apsize].shift) - 1); va |= penc << 12; va |= ssize << 8; - /* Add AVAL part */ - if (psize != apsize) { - /* - * MPSS, 64K base page size and 16MB parge page size - * We don't need all the bits, but rest of the bits - * must be ignored by the processor. - * vpn cover upto 65 bits of va. (0...65) and we need - * 58..64 bits of va. - */ - va |= (vpn & 0xfe); - } + /* + * AVAL bits: + * We don't need all the bits, but rest of the bits + * must be ignored by the processor. + * vpn cover upto 65 bits of va. (0...65) and we need + * 58..64 bits of va. + */ + va |= (vpn & 0xfe); /* AVAL */ va |= 1; /* L */ asm volatile(ASM_FTR_IFCLR("tlbie %0,1", PPC_TLBIE(%1,%0), %2) : : "r" (va), "r"(0), "i" (CPU_FTR_ARCH_206) @@ -129,17 +130,14 @@ static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize) va &= ~((1ul << mmu_psize_defs[apsize].shift) - 1); va |= penc << 12; va |= ssize << 8; - /* Add AVAL part */ - if (psize != apsize) { - /* - * MPSS, 64K base page size and 16MB parge page size - * We don't need all the bits, but rest of the bits - * must be ignored by the processor. - * vpn cover upto 65 bits of va. (0...65) and we need - * 58..64 bits of va. - */ - va |= (vpn & 0xfe); - } + /* + * AVAL bits: + * We don't need all the bits, but rest of the bits + * must be ignored by the processor. + * vpn cover upto 65 bits of va. (0...65) and we need + * 58..64 bits of va. + */ + va |= (vpn & 0xfe); va |= 1; /* L */ asm volatile(".long 0x7c000224 | (%0 << 11) | (1 << 21)" : : "r"(va) : "memory"); @@ -172,7 +170,7 @@ static inline void tlbie(unsigned long vpn, int psize, int apsize, static inline void native_lock_hpte(struct hash_pte *hptep) { - unsigned long *word = &hptep->v; + unsigned long *word = (unsigned long *)&hptep->v; while (1) { if (!test_and_set_bit_lock(HPTE_LOCK_BIT, word)) @@ -184,7 +182,7 @@ static inline void native_lock_hpte(struct hash_pte *hptep) static inline void native_unlock_hpte(struct hash_pte *hptep) { - unsigned long *word = &hptep->v; + unsigned long *word = (unsigned long *)&hptep->v; clear_bit_unlock(HPTE_LOCK_BIT, word); } @@ -204,10 +202,10 @@ static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn, } for (i = 0; i < HPTES_PER_GROUP; i++) { - if (! (hptep->v & HPTE_V_VALID)) { + if (! (be64_to_cpu(hptep->v) & HPTE_V_VALID)) { /* retry with lock held */ native_lock_hpte(hptep); - if (! (hptep->v & HPTE_V_VALID)) + if (! (be64_to_cpu(hptep->v) & HPTE_V_VALID)) break; native_unlock_hpte(hptep); } @@ -226,14 +224,14 @@ static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn, i, hpte_v, hpte_r); } - hptep->r = hpte_r; + hptep->r = cpu_to_be64(hpte_r); /* Guarantee the second dword is visible before the valid bit */ eieio(); /* * Now set the first dword including the valid bit * NOTE: this also unlocks the hpte */ - hptep->v = hpte_v; + hptep->v = cpu_to_be64(hpte_v); __asm__ __volatile__ ("ptesync" : : : "memory"); @@ -254,12 +252,12 @@ static long native_hpte_remove(unsigned long hpte_group) for (i = 0; i < HPTES_PER_GROUP; i++) { hptep = htab_address + hpte_group + slot_offset; - hpte_v = hptep->v; + hpte_v = be64_to_cpu(hptep->v); if ((hpte_v & HPTE_V_VALID) && !(hpte_v & HPTE_V_BOLTED)) { /* retry with lock held */ native_lock_hpte(hptep); - hpte_v = hptep->v; + hpte_v = be64_to_cpu(hptep->v); if ((hpte_v & HPTE_V_VALID) && !(hpte_v & HPTE_V_BOLTED)) break; @@ -294,7 +292,7 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp, native_lock_hpte(hptep); - hpte_v = hptep->v; + hpte_v = be64_to_cpu(hptep->v); /* * We need to invalidate the TLB always because hpte_remove doesn't do * a tlb invalidate. If a hash bucket gets full, we "evict" a more/less @@ -308,8 +306,8 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp, } else { DBG_LOW(" -> hit\n"); /* Update the HPTE */ - hptep->r = (hptep->r & ~(HPTE_R_PP | HPTE_R_N)) | - (newpp & (HPTE_R_PP | HPTE_R_N | HPTE_R_C)); + hptep->r = cpu_to_be64((be64_to_cpu(hptep->r) & ~(HPTE_R_PP | HPTE_R_N)) | + (newpp & (HPTE_R_PP | HPTE_R_N | HPTE_R_C))); } native_unlock_hpte(hptep); @@ -334,7 +332,7 @@ static long native_hpte_find(unsigned long vpn, int psize, int ssize) slot = (hash & htab_hash_mask) * HPTES_PER_GROUP; for (i = 0; i < HPTES_PER_GROUP; i++) { hptep = htab_address + slot; - hpte_v = hptep->v; + hpte_v = be64_to_cpu(hptep->v); if (HPTE_V_COMPARE(hpte_v, want_v) && (hpte_v & HPTE_V_VALID)) /* HPTE matches */ @@ -369,8 +367,9 @@ static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea, hptep = htab_address + slot; /* Update the HPTE */ - hptep->r = (hptep->r & ~(HPTE_R_PP | HPTE_R_N)) | - (newpp & (HPTE_R_PP | HPTE_R_N)); + hptep->r = cpu_to_be64((be64_to_cpu(hptep->r) & + ~(HPTE_R_PP | HPTE_R_N)) | + (newpp & (HPTE_R_PP | HPTE_R_N))); /* * Ensure it is out of the tlb too. Bolted entries base and * actual page size will be same. @@ -392,7 +391,7 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn, want_v = hpte_encode_avpn(vpn, bpsize, ssize); native_lock_hpte(hptep); - hpte_v = hptep->v; + hpte_v = be64_to_cpu(hptep->v); /* * We need to invalidate the TLB always because hpte_remove doesn't do @@ -458,7 +457,7 @@ static void native_hugepage_invalidate(struct mm_struct *mm, hptep = htab_address + slot; want_v = hpte_encode_avpn(vpn, psize, ssize); native_lock_hpte(hptep); - hpte_v = hptep->v; + hpte_v = be64_to_cpu(hptep->v); /* Even if we miss, we need to invalidate the TLB */ if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID)) @@ -519,11 +518,12 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot, int *psize, int *apsize, int *ssize, unsigned long *vpn) { unsigned long avpn, pteg, vpi; - unsigned long hpte_v = hpte->v; + unsigned long hpte_v = be64_to_cpu(hpte->v); + unsigned long hpte_r = be64_to_cpu(hpte->r); unsigned long vsid, seg_off; int size, a_size, shift; /* Look at the 8 bit LP value */ - unsigned int lp = (hpte->r >> LP_SHIFT) & ((1 << LP_BITS) - 1); + unsigned int lp = (hpte_r >> LP_SHIFT) & ((1 << LP_BITS) - 1); if (!(hpte_v & HPTE_V_LARGE)) { size = MMU_PAGE_4K; @@ -612,7 +612,7 @@ static void native_hpte_clear(void) * running, right? and for crash dump, we probably * don't want to wait for a maybe bad cpu. */ - hpte_v = hptep->v; + hpte_v = be64_to_cpu(hptep->v); /* * Call __tlbie() here rather than tlbie() since we @@ -664,7 +664,7 @@ static void native_flush_hash_range(unsigned long number, int local) hptep = htab_address + slot; want_v = hpte_encode_avpn(vpn, psize, ssize); native_lock_hpte(hptep); - hpte_v = hptep->v; + hpte_v = be64_to_cpu(hptep->v); if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID)) native_unlock_hpte(hptep); diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index bde8b558975..88fdd9d2507 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -169,9 +169,10 @@ static unsigned long htab_convert_pte_flags(unsigned long pteflags) if ((pteflags & _PAGE_USER) && !((pteflags & _PAGE_RW) && (pteflags & _PAGE_DIRTY))) rflags |= 1; - - /* Always add C */ - return rflags | HPTE_R_C; + /* + * Always add "C" bit for perf. Memory coherence is always enabled + */ + return rflags | HPTE_R_C | HPTE_R_M; } int htab_bolt_mapping(unsigned long vstart, unsigned long vend, @@ -206,6 +207,24 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend, if (overlaps_kernel_text(vaddr, vaddr + step)) tprot &= ~HPTE_R_N; + /* Make kvm guest trampolines executable */ + if (overlaps_kvm_tmp(vaddr, vaddr + step)) + tprot &= ~HPTE_R_N; + + /* + * If relocatable, check if it overlaps interrupt vectors that + * are copied down to real 0. For relocatable kernel + * (e.g. kdump case) we copy interrupt vectors down to real + * address 0. Mark that region as executable. This is + * because on p8 system with relocation on exception feature + * enabled, exceptions are raised with MMU (IR=DR=1) ON. Hence + * in order to execute the interrupt handlers in virtual + * mode the vector region need to be marked as executable. + */ + if ((PHYSICAL_START > MEMORY_START) && + overlaps_interrupt_vector_text(vaddr, vaddr + step)) + tprot &= ~HPTE_R_N; + hash = hpt_hash(vpn, shift, ssize); hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP); @@ -250,20 +269,19 @@ static int __init htab_dt_scan_seg_sizes(unsigned long node, const char *uname, int depth, void *data) { - char *type = of_get_flat_dt_prop(node, "device_type", NULL); - u32 *prop; - unsigned long size = 0; + const char *type = of_get_flat_dt_prop(node, "device_type", NULL); + const __be32 *prop; + int size = 0; /* We are scanning "cpu" nodes only */ if (type == NULL || strcmp(type, "cpu") != 0) return 0; - prop = (u32 *)of_get_flat_dt_prop(node, "ibm,processor-segment-sizes", - &size); + prop = of_get_flat_dt_prop(node, "ibm,processor-segment-sizes", &size); if (prop == NULL) return 0; for (; size >= 4; size -= 4, ++prop) { - if (prop[0] == 40) { + if (be32_to_cpu(prop[0]) == 40) { DBG("1T segment support detected\n"); cur_cpu_spec->mmu_features |= MMU_FTR_1T_SEGMENT; return 1; @@ -306,24 +324,23 @@ static int __init htab_dt_scan_page_sizes(unsigned long node, const char *uname, int depth, void *data) { - char *type = of_get_flat_dt_prop(node, "device_type", NULL); - u32 *prop; - unsigned long size = 0; + const char *type = of_get_flat_dt_prop(node, "device_type", NULL); + const __be32 *prop; + int size = 0; /* We are scanning "cpu" nodes only */ if (type == NULL || strcmp(type, "cpu") != 0) return 0; - prop = (u32 *)of_get_flat_dt_prop(node, - "ibm,segment-page-sizes", &size); + prop = of_get_flat_dt_prop(node, "ibm,segment-page-sizes", &size); if (prop != NULL) { pr_info("Page sizes from device-tree:\n"); size /= 4; cur_cpu_spec->mmu_features &= ~(MMU_FTR_16M_PAGE); while(size > 0) { - unsigned int base_shift = prop[0]; - unsigned int slbenc = prop[1]; - unsigned int lpnum = prop[2]; + unsigned int base_shift = be32_to_cpu(prop[0]); + unsigned int slbenc = be32_to_cpu(prop[1]); + unsigned int lpnum = be32_to_cpu(prop[2]); struct mmu_psize_def *def; int idx, base_idx; @@ -356,8 +373,8 @@ static int __init htab_dt_scan_page_sizes(unsigned long node, def->tlbiel = 0; while (size > 0 && lpnum) { - unsigned int shift = prop[0]; - int penc = prop[1]; + unsigned int shift = be32_to_cpu(prop[0]); + int penc = be32_to_cpu(prop[1]); prop += 2; size -= 2; lpnum--; @@ -389,9 +406,9 @@ static int __init htab_dt_scan_page_sizes(unsigned long node, static int __init htab_dt_scan_hugepage_blocks(unsigned long node, const char *uname, int depth, void *data) { - char *type = of_get_flat_dt_prop(node, "device_type", NULL); - unsigned long *addr_prop; - u32 *page_count_prop; + const char *type = of_get_flat_dt_prop(node, "device_type", NULL); + const __be64 *addr_prop; + const __be32 *page_count_prop; unsigned int expected_pages; long unsigned int phys_addr; long unsigned int block_size; @@ -405,12 +422,12 @@ static int __init htab_dt_scan_hugepage_blocks(unsigned long node, page_count_prop = of_get_flat_dt_prop(node, "ibm,expected#pages", NULL); if (page_count_prop == NULL) return 0; - expected_pages = (1 << page_count_prop[0]); + expected_pages = (1 << be32_to_cpu(page_count_prop[0])); addr_prop = of_get_flat_dt_prop(node, "reg", NULL); if (addr_prop == NULL) return 0; - phys_addr = addr_prop[0]; - block_size = addr_prop[1]; + phys_addr = be64_to_cpu(addr_prop[0]); + block_size = be64_to_cpu(addr_prop[1]); if (block_size != (16 * GB)) return 0; printk(KERN_INFO "Huge page(16GB) memory: " @@ -432,6 +449,24 @@ static void mmu_psize_set_default_penc(void) mmu_psize_defs[bpsize].penc[apsize] = -1; } +#ifdef CONFIG_PPC_64K_PAGES + +static bool might_have_hea(void) +{ + /* + * The HEA ethernet adapter requires awareness of the + * GX bus. Without that awareness we can easily assume + * we will never see an HEA ethernet device. + */ +#ifdef CONFIG_IBMEBUS + return !cpu_has_feature(CPU_FTR_ARCH_207S); +#else + return false; +#endif +} + +#endif /* #ifdef CONFIG_PPC_64K_PAGES */ + static void __init htab_init_page_sizes(void) { int rc; @@ -486,10 +521,11 @@ static void __init htab_init_page_sizes(void) mmu_linear_psize = MMU_PAGE_64K; if (mmu_has_feature(MMU_FTR_CI_LARGE_PAGE)) { /* - * Don't use 64k pages for ioremap on pSeries, since - * that would stop us accessing the HEA ethernet. + * When running on pSeries using 64k pages for ioremap + * would stop us accessing the HEA ethernet. So if we + * have the chance of ever seeing one, stay at 4k. */ - if (!machine_is(pseries)) + if (!might_have_hea() || !machine_is(pseries)) mmu_io_psize = MMU_PAGE_64K; } else mmu_ci_restrictions = 1; @@ -533,17 +569,17 @@ static int __init htab_dt_scan_pftsize(unsigned long node, const char *uname, int depth, void *data) { - char *type = of_get_flat_dt_prop(node, "device_type", NULL); - u32 *prop; + const char *type = of_get_flat_dt_prop(node, "device_type", NULL); + const __be32 *prop; /* We are scanning "cpu" nodes only */ if (type == NULL || strcmp(type, "cpu") != 0) return 0; - prop = (u32 *)of_get_flat_dt_prop(node, "ibm,pft-size", NULL); + prop = of_get_flat_dt_prop(node, "ibm,pft-size", NULL); if (prop != NULL) { /* pft_size[0] is the NUMA CEC cookie */ - ppc64_pft_size = prop[1]; + ppc64_pft_size = be32_to_cpu(prop[1]); return 1; } return 0; @@ -590,47 +626,43 @@ int remove_section_mapping(unsigned long start, unsigned long end) } #endif /* CONFIG_MEMORY_HOTPLUG */ -#define FUNCTION_TEXT(A) ((*(unsigned long *)(A))) +extern u32 htab_call_hpte_insert1[]; +extern u32 htab_call_hpte_insert2[]; +extern u32 htab_call_hpte_remove[]; +extern u32 htab_call_hpte_updatepp[]; +extern u32 ht64_call_hpte_insert1[]; +extern u32 ht64_call_hpte_insert2[]; +extern u32 ht64_call_hpte_remove[]; +extern u32 ht64_call_hpte_updatepp[]; static void __init htab_finish_init(void) { - extern unsigned int *htab_call_hpte_insert1; - extern unsigned int *htab_call_hpte_insert2; - extern unsigned int *htab_call_hpte_remove; - extern unsigned int *htab_call_hpte_updatepp; - #ifdef CONFIG_PPC_HAS_HASH_64K - extern unsigned int *ht64_call_hpte_insert1; - extern unsigned int *ht64_call_hpte_insert2; - extern unsigned int *ht64_call_hpte_remove; - extern unsigned int *ht64_call_hpte_updatepp; - patch_branch(ht64_call_hpte_insert1, - FUNCTION_TEXT(ppc_md.hpte_insert), + ppc_function_entry(ppc_md.hpte_insert), BRANCH_SET_LINK); patch_branch(ht64_call_hpte_insert2, - FUNCTION_TEXT(ppc_md.hpte_insert), + ppc_function_entry(ppc_md.hpte_insert), BRANCH_SET_LINK); patch_branch(ht64_call_hpte_remove, - FUNCTION_TEXT(ppc_md.hpte_remove), + ppc_function_entry(ppc_md.hpte_remove), BRANCH_SET_LINK); patch_branch(ht64_call_hpte_updatepp, - FUNCTION_TEXT(ppc_md.hpte_updatepp), + ppc_function_entry(ppc_md.hpte_updatepp), BRANCH_SET_LINK); - #endif /* CONFIG_PPC_HAS_HASH_64K */ patch_branch(htab_call_hpte_insert1, - FUNCTION_TEXT(ppc_md.hpte_insert), + ppc_function_entry(ppc_md.hpte_insert), BRANCH_SET_LINK); patch_branch(htab_call_hpte_insert2, - FUNCTION_TEXT(ppc_md.hpte_insert), + ppc_function_entry(ppc_md.hpte_insert), BRANCH_SET_LINK); patch_branch(htab_call_hpte_remove, - FUNCTION_TEXT(ppc_md.hpte_remove), + ppc_function_entry(ppc_md.hpte_remove), BRANCH_SET_LINK); patch_branch(htab_call_hpte_updatepp, - FUNCTION_TEXT(ppc_md.hpte_updatepp), + ppc_function_entry(ppc_md.hpte_updatepp), BRANCH_SET_LINK); } @@ -947,6 +979,22 @@ void hash_failure_debug(unsigned long ea, unsigned long access, trap, vsid, ssize, psize, lpsize, pte); } +static void check_paca_psize(unsigned long ea, struct mm_struct *mm, + int psize, bool user_region) +{ + if (user_region) { + if (psize != get_paca_psize(ea)) { + get_paca()->context = mm->context; + slb_flush_and_rebolt(); + } + } else if (get_paca()->vmalloc_sllp != + mmu_psize_defs[mmu_vmalloc_psize].sllp) { + get_paca()->vmalloc_sllp = + mmu_psize_defs[mmu_vmalloc_psize].sllp; + slb_vmalloc_update(); + } +} + /* Result code is: * 0 - handled * 1 - normal page fault @@ -1068,6 +1116,8 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap) WARN_ON(1); } #endif + check_paca_psize(ea, mm, psize, user_region); + goto bail; } @@ -1108,17 +1158,8 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap) #endif } } - if (user_region) { - if (psize != get_paca_psize(ea)) { - get_paca()->context = mm->context; - slb_flush_and_rebolt(); - } - } else if (get_paca()->vmalloc_sllp != - mmu_psize_defs[mmu_vmalloc_psize].sllp) { - get_paca()->vmalloc_sllp = - mmu_psize_defs[mmu_vmalloc_psize].sllp; - slb_vmalloc_update(); - } + + check_paca_psize(ea, mm, psize, user_region); #endif /* CONFIG_PPC_64K_PAGES */ #ifdef CONFIG_PPC_HAS_HASH_64K diff --git a/arch/powerpc/mm/hugepage-hash64.c b/arch/powerpc/mm/hugepage-hash64.c index 34de9e0cdc3..826893fcb3a 100644 --- a/arch/powerpc/mm/hugepage-hash64.c +++ b/arch/powerpc/mm/hugepage-hash64.c @@ -127,7 +127,11 @@ repeat: /* Add in WIMG bits */ rflags |= (new_pmd & (_PAGE_WRITETHRU | _PAGE_NO_CACHE | - _PAGE_COHERENT | _PAGE_GUARDED)); + _PAGE_GUARDED)); + /* + * enable the memory coherence always + */ + rflags |= HPTE_R_M; /* Insert into the hash table, primary slot */ slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags, 0, diff --git a/arch/powerpc/mm/hugetlbpage-book3e.c b/arch/powerpc/mm/hugetlbpage-book3e.c index 3bc700655fc..5e4ee257390 100644 --- a/arch/powerpc/mm/hugetlbpage-book3e.c +++ b/arch/powerpc/mm/hugetlbpage-book3e.c @@ -8,6 +8,44 @@ #include <linux/mm.h> #include <linux/hugetlb.h> +#ifdef CONFIG_PPC_FSL_BOOK3E +#ifdef CONFIG_PPC64 +static inline int tlb1_next(void) +{ + struct paca_struct *paca = get_paca(); + struct tlb_core_data *tcd; + int this, next; + + tcd = paca->tcd_ptr; + this = tcd->esel_next; + + next = this + 1; + if (next >= tcd->esel_max) + next = tcd->esel_first; + + tcd->esel_next = next; + return this; +} +#else +static inline int tlb1_next(void) +{ + int index, ncams; + + ncams = mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY; + + index = __get_cpu_var(next_tlbcam_idx); + + /* Just round-robin the entries and wrap when we hit the end */ + if (unlikely(index == ncams - 1)) + __get_cpu_var(next_tlbcam_idx) = tlbcam_index; + else + __get_cpu_var(next_tlbcam_idx)++; + + return index; +} +#endif /* !PPC64 */ +#endif /* FSL */ + static inline int mmu_get_tsize(int psize) { return mmu_psize_defs[psize].enc; @@ -47,7 +85,7 @@ void book3e_hugetlb_preload(struct vm_area_struct *vma, unsigned long ea, struct mm_struct *mm; #ifdef CONFIG_PPC_FSL_BOOK3E - int index, ncams; + int index; #endif if (unlikely(is_kernel_addr(ea))) @@ -77,18 +115,11 @@ void book3e_hugetlb_preload(struct vm_area_struct *vma, unsigned long ea, } #ifdef CONFIG_PPC_FSL_BOOK3E - ncams = mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY; - /* We have to use the CAM(TLB1) on FSL parts for hugepages */ - index = __get_cpu_var(next_tlbcam_idx); + index = tlb1_next(); mtspr(SPRN_MAS0, MAS0_ESEL(index) | MAS0_TLBSEL(1)); - - /* Just round-robin the entries and wrap when we hit the end */ - if (unlikely(index == ncams - 1)) - __get_cpu_var(next_tlbcam_idx) = tlbcam_index; - else - __get_cpu_var(next_tlbcam_idx)++; #endif + mas1 = MAS1_VALID | MAS1_TID(mm->context.id) | MAS1_TSIZE(tsize); mas2 = ea & ~((1UL << shift) - 1); mas2 |= (pte_val(pte) >> PTE_WIMGE_SHIFT) & MAS2_WIMGE_MASK; @@ -103,7 +134,8 @@ void book3e_hugetlb_preload(struct vm_area_struct *vma, unsigned long ea, if (mmu_has_feature(MMU_FTR_USE_PAIRED_MAS)) { mtspr(SPRN_MAS7_MAS3, mas7_3); } else { - mtspr(SPRN_MAS7, upper_32_bits(mas7_3)); + if (mmu_has_feature(MMU_FTR_BIG_PHYS)) + mtspr(SPRN_MAS7, upper_32_bits(mas7_3)); mtspr(SPRN_MAS3, lower_32_bits(mas7_3)); } @@ -117,6 +149,5 @@ void flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr) struct hstate *hstate = hstate_file(vma->vm_file); unsigned long tsize = huge_page_shift(hstate) - 10; - __flush_tlb_page(vma ? vma->vm_mm : NULL, vmaddr, tsize, 0); - + __flush_tlb_page(vma->vm_mm, vmaddr, tsize, 0); } diff --git a/arch/powerpc/mm/hugetlbpage-hash64.c b/arch/powerpc/mm/hugetlbpage-hash64.c index 0b7fb676101..a5bcf930119 100644 --- a/arch/powerpc/mm/hugetlbpage-hash64.c +++ b/arch/powerpc/mm/hugetlbpage-hash64.c @@ -99,6 +99,10 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, /* Add in WIMG bits */ rflags |= (new_pte & (_PAGE_WRITETHRU | _PAGE_NO_CACHE | _PAGE_COHERENT | _PAGE_GUARDED)); + /* + * enable the memory coherence always + */ + rflags |= HPTE_R_M; slot = hpte_insert_repeating(hash, vpn, pa, rflags, 0, mmu_psize, ssize); diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index d67db4bd672..7e70ae968e5 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -86,11 +86,6 @@ int pgd_huge(pgd_t pgd) */ return ((pgd_val(pgd) & 0x3) != 0x0); } - -int pmd_huge_support(void) -{ - return 1; -} #else int pmd_huge(pmd_t pmd) { @@ -106,11 +101,6 @@ int pgd_huge(pgd_t pgd) { return 0; } - -int pmd_huge_support(void) -{ - return 0; -} #endif pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) @@ -472,12 +462,13 @@ static void hugepd_free(struct mmu_gather *tlb, void *hugepte) { struct hugepd_freelist **batchp; - batchp = &__get_cpu_var(hugepd_freelist_cur); + batchp = &get_cpu_var(hugepd_freelist_cur); if (atomic_read(&tlb->mm->mm_users) < 2 || cpumask_equal(mm_cpumask(tlb->mm), cpumask_of(smp_processor_id()))) { kmem_cache_free(hugepte_cache, hugepte); + put_cpu_var(hugepd_freelist_cur); return; } @@ -491,6 +482,7 @@ static void hugepd_free(struct mmu_gather *tlb, void *hugepte) call_rcu_sched(&(*batchp)->rcu, hugepd_free_rcu_callback); *batchp = NULL; } + put_cpu_var(hugepd_freelist_cur); } #endif @@ -633,8 +625,6 @@ static void hugetlb_free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, /* * This function frees user-level page tables of a process. - * - * Must be called with pagetable lock held. */ void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c index d47d3dab487..cff59f1bec2 100644 --- a/arch/powerpc/mm/init_32.c +++ b/arch/powerpc/mm/init_32.c @@ -213,7 +213,12 @@ void setup_initial_memory_limit(phys_addr_t first_memblock_base, */ BUG_ON(first_memblock_base != 0); +#ifdef CONFIG_PIN_TLB + /* 8xx can only access 24MB at the moment */ + memblock_set_current_limit(min_t(u64, first_memblock_size, 0x01800000)); +#else /* 8xx can only access 8MB at the moment */ memblock_set_current_limit(min_t(u64, first_memblock_size, 0x00800000)); +#endif } #endif /* CONFIG_8xx */ diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index d0cd9e4c683..e3734edffa6 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -300,5 +300,58 @@ void vmemmap_free(unsigned long start, unsigned long end) { } -#endif /* CONFIG_SPARSEMEM_VMEMMAP */ +void register_page_bootmem_memmap(unsigned long section_nr, + struct page *start_page, unsigned long size) +{ +} + +/* + * We do not have access to the sparsemem vmemmap, so we fallback to + * walking the list of sparsemem blocks which we already maintain for + * the sake of crashdump. In the long run, we might want to maintain + * a tree if performance of that linear walk becomes a problem. + * + * realmode_pfn_to_page functions can fail due to: + * 1) As real sparsemem blocks do not lay in RAM continously (they + * are in virtual address space which is not available in the real mode), + * the requested page struct can be split between blocks so get_page/put_page + * may fail. + * 2) When huge pages are used, the get_page/put_page API will fail + * in real mode as the linked addresses in the page struct are virtual + * too. + */ +struct page *realmode_pfn_to_page(unsigned long pfn) +{ + struct vmemmap_backing *vmem_back; + struct page *page; + unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift; + unsigned long pg_va = (unsigned long) pfn_to_page(pfn); + + for (vmem_back = vmemmap_list; vmem_back; vmem_back = vmem_back->list) { + if (pg_va < vmem_back->virt_addr) + continue; + + /* Check that page struct is not split between real pages */ + if ((pg_va + sizeof(struct page)) > + (vmem_back->virt_addr + page_size)) + return NULL; + + page = (struct page *) (vmem_back->phys + pg_va - + vmem_back->virt_addr); + return page; + } + + return NULL; +} +EXPORT_SYMBOL_GPL(realmode_pfn_to_page); + +#elif defined(CONFIG_FLATMEM) + +struct page *realmode_pfn_to_page(unsigned long pfn) +{ + struct page *page = pfn_to_page(pfn); + return page; +} +EXPORT_SYMBOL_GPL(realmode_pfn_to_page); +#endif /* CONFIG_SPARSEMEM_VMEMMAP/CONFIG_FLATMEM */ diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 1cf9c5b67f2..2c8e90f5789 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 */ @@ -209,7 +214,7 @@ void __init do_init_bootmem(void) /* Place all memblock_regions in the same node and merge contiguous * memblock_regions */ - memblock_set_node(0, (phys_addr_t)ULLONG_MAX, 0); + memblock_set_node(0, (phys_addr_t)ULLONG_MAX, &memblock.memory, 0); /* Add all physical memory to the bootmem map, mark each area * present. @@ -297,12 +302,27 @@ void __init paging_init(void) } #endif /* ! CONFIG_NEED_MULTIPLE_NODES */ +static void __init register_page_bootmem_info(void) +{ + int i; + + for_each_online_node(i) + register_page_bootmem_info_node(NODE_DATA(i)); +} + void __init mem_init(void) { + /* + * book3s is limited to 16 page sizes due to encoding this in + * a 4-bit field for slices. + */ + BUILD_BUG_ON(MMU_PAGE_COUNT > 16); + #ifdef CONFIG_SWIOTLB swiotlb_init(0); #endif + register_page_bootmem_info(); high_memory = (void *) __va(max_low_pfn * PAGE_SIZE); set_max_mapnr(max_pfn); free_all_bootmem(); @@ -498,7 +518,7 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, * System memory should not be in /proc/iomem but various tools expect it * (eg kdump). */ -static int add_system_ram_resources(void) +static int __init add_system_ram_resources(void) { struct memblock_region *reg; diff --git a/arch/powerpc/mm/mmu_context_nohash.c b/arch/powerpc/mm/mmu_context_nohash.c index af3d78e1930..928ebe79668 100644 --- a/arch/powerpc/mm/mmu_context_nohash.c +++ b/arch/powerpc/mm/mmu_context_nohash.c @@ -410,17 +410,7 @@ void __init mmu_context_init(void) } else if (mmu_has_feature(MMU_FTR_TYPE_47x)) { first_context = 1; last_context = 65535; - } else -#ifdef CONFIG_PPC_BOOK3E_MMU - if (mmu_has_feature(MMU_FTR_TYPE_3E)) { - u32 mmucfg = mfspr(SPRN_MMUCFG); - u32 pid_bits = (mmucfg & MMUCFG_PIDSIZE_MASK) - >> MMUCFG_PIDSIZE_SHIFT; - first_context = 1; - last_context = (1UL << (pid_bits + 1)) - 1; - } else -#endif - { + } else { first_context = 1; last_context = 255; } diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h index 83eb5d5f53d..9615d82919b 100644 --- a/arch/powerpc/mm/mmu_decl.h +++ b/arch/powerpc/mm/mmu_decl.h @@ -148,6 +148,8 @@ extern unsigned long calc_cam_sz(unsigned long ram, unsigned long virt, extern void MMU_init_hw(void); extern unsigned long mmu_mapin_ram(unsigned long top); extern void adjust_total_lowmem(void); +extern int switch_to_as1(void); +extern void restore_to_as0(int esel, int offset, void *dt_ptr, int bootcpu); #endif extern void loadcam_entry(unsigned int index); diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index c916127f10c..3b181b22cd4 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -31,6 +31,8 @@ #include <asm/sparsemem.h> #include <asm/prom.h> #include <asm/smp.h> +#include <asm/cputhreads.h> +#include <asm/topology.h> #include <asm/firmware.h> #include <asm/paca.h> #include <asm/hvcall.h> @@ -152,9 +154,22 @@ static void __init get_node_active_region(unsigned long pfn, } } -static void map_cpu_to_node(int cpu, int node) +static void reset_numa_cpu_lookup_table(void) +{ + unsigned int cpu; + + for_each_possible_cpu(cpu) + numa_cpu_lookup_table[cpu] = -1; +} + +static void update_numa_cpu_lookup_table(unsigned int cpu, int node) { numa_cpu_lookup_table[cpu] = node; +} + +static void map_cpu_to_node(int cpu, int node) +{ + update_numa_cpu_lookup_table(cpu, node); dbg("adding cpu %d to node %d\n", cpu, node); @@ -195,7 +210,7 @@ static const __be32 *of_get_usable_memory(struct device_node *memory) u32 len; prop = of_get_property(memory, "linux,drconf-usable-memory", &len); if (!prop || len < sizeof(unsigned int)) - return 0; + return NULL; return prop; } @@ -217,6 +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) @@ -522,11 +538,24 @@ static int of_drconf_to_nid_single(struct of_drconf_cell *drmem, */ static int numa_setup_cpu(unsigned long lcpu) { - int nid = 0; - struct device_node *cpu = of_get_cpu_node(lcpu, NULL); + int nid; + struct device_node *cpu; + + /* + * If a valid cpu-to-node mapping is already available, use it + * directly instead of querying the firmware, since it represents + * the most recent mapping notified to us by the platform (eg: VPHN). + */ + if ((nid = numa_cpu_lookup_table[lcpu]) >= 0) { + map_cpu_to_node(lcpu, nid); + return nid; + } + + cpu = of_get_cpu_node(lcpu, NULL); if (!cpu) { WARN_ON(1); + nid = 0; goto out; } @@ -542,16 +571,38 @@ out: return nid; } +static void verify_cpu_node_mapping(int cpu, int node) +{ + int base, sibling, i; + + /* Verify that all the threads in the core belong to the same node */ + base = cpu_first_thread_sibling(cpu); + + for (i = 0; i < threads_per_core; i++) { + sibling = base + i; + + if (sibling == cpu || cpu_is_offline(sibling)) + continue; + + if (cpu_to_node(sibling) != node) { + WARN(1, "CPU thread siblings %d and %d don't belong" + " to the same node!\n", cpu, sibling); + break; + } + } +} + static int cpu_numa_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { unsigned long lcpu = (unsigned long)hcpu; - int ret = NOTIFY_DONE; + int ret = NOTIFY_DONE, nid; switch (action) { case CPU_UP_PREPARE: case CPU_UP_PREPARE_FROZEN: - numa_setup_cpu(lcpu); + nid = numa_setup_cpu(lcpu); + verify_cpu_node_mapping((int)lcpu, nid); ret = NOTIFY_OK; break; #ifdef CONFIG_HOTPLUG_CPU @@ -670,7 +721,8 @@ static void __init parse_drconf_memory(struct device_node *memory) node_set_online(nid); sz = numa_enforce_memory_limit(base, size); if (sz) - memblock_set_node(base, sz, nid); + memblock_set_node(base, sz, + &memblock.memory, nid); } while (--ranges); } } @@ -760,7 +812,7 @@ new_range: continue; } - memblock_set_node(start, size, nid); + memblock_set_node(start, size, &memblock.memory, nid); if (--ranges) goto new_range; @@ -797,7 +849,8 @@ static void __init setup_nonnuma(void) fake_numa_create_new_node(end_pfn, &nid); memblock_set_node(PFN_PHYS(start_pfn), - PFN_PHYS(end_pfn - start_pfn), nid); + PFN_PHYS(end_pfn - start_pfn), + &memblock.memory, nid); node_set_online(nid); } } @@ -938,8 +991,7 @@ static void __init mark_reserved_regions_for_nid(int nid) unsigned long start_pfn = physbase >> PAGE_SHIFT; unsigned long end_pfn = PFN_UP(physbase + size); struct node_active_region node_ar; - unsigned long node_end_pfn = node->node_start_pfn + - node->node_spanned_pages; + unsigned long node_end_pfn = pgdat_end_pfn(node); /* * Check to make sure that this memblock.reserved area is @@ -1068,6 +1120,7 @@ void __init do_init_bootmem(void) */ setup_node_to_cpumask_map(); + reset_numa_cpu_lookup_table(); register_cpu_notifier(&ppc64_numa_nb); cpu_numa_callback(&ppc64_numa_nb, CPU_UP_PREPARE, (void *)(unsigned long)boot_cpuid); @@ -1154,7 +1207,7 @@ static int hot_add_drconf_scn_to_nid(struct device_node *memory, * represented in the device tree as a node (i.e. memory@XXXX) for * each memblock. */ -int hot_add_node_scn_to_nid(unsigned long scn_addr) +static int hot_add_node_scn_to_nid(unsigned long scn_addr) { struct device_node *memory; int nid = -1; @@ -1235,7 +1288,7 @@ static u64 hot_add_drconf_memory_max(void) struct device_node *memory = NULL; unsigned int drconf_cell_cnt = 0; u64 lmb_size = 0; - const __be32 *dm = 0; + const __be32 *dm = NULL; memory = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory"); if (memory) { @@ -1446,6 +1499,33 @@ static int update_cpu_topology(void *data) return 0; } +static int update_lookup_table(void *data) +{ + struct topology_update_data *update; + + if (!data) + return -EINVAL; + + /* + * Upon topology update, the numa-cpu lookup table needs to be updated + * for all threads in the core, including offline CPUs, to ensure that + * future hotplug operations respect the cpu-to-node associativity + * properly. + */ + for (update = data; update; update = update->next) { + int nid, base, j; + + nid = update->new_nid; + base = cpu_first_thread_sibling(update->cpu); + + for (j = 0; j < threads_per_core; j++) { + update_numa_cpu_lookup_table(base + j, nid); + } + } + + return 0; +} + /* * Update the node maps and sysfs entries for each cpu whose home node * has changed. Returns 1 when the topology has changed, and 0 otherwise. @@ -1512,8 +1592,30 @@ 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); + /* + * Update the numa-cpu lookup table with the new mappings, even for + * offline CPUs. It is best to perform this update from the stop- + * machine context. + */ + stop_machine(update_lookup_table, &updates[0], + cpumask_of(raw_smp_processor_id())); + for (ud = &updates[0]; ud; ud = ud->next) { unregister_cpu_under_node(ud->cpu, ud->old_nid); register_cpu_under_node(ud->cpu, ud->new_nid); @@ -1525,6 +1627,7 @@ int arch_update_cpu_topology(void) changed = 1; } +out: kfree(updates); return changed; } @@ -1535,7 +1638,7 @@ static void topology_work_fn(struct work_struct *work) } static DECLARE_WORK(topology_work, topology_work_fn); -void topology_schedule_update(void) +static void topology_schedule_update(void) { schedule_work(&topology_work); } @@ -1698,7 +1801,7 @@ static const struct file_operations topology_ops = { static int topology_update_init(void) { start_topology_update(); - proc_create("powerpc/topology_updates", 644, NULL, &topology_ops); + proc_create("powerpc/topology_updates", 0644, NULL, &topology_ops); return 0; } diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c index edda589795c..c695943a513 100644 --- a/arch/powerpc/mm/pgtable.c +++ b/arch/powerpc/mm/pgtable.c @@ -24,7 +24,6 @@ #include <linux/kernel.h> #include <linux/gfp.h> #include <linux/mm.h> -#include <linux/init.h> #include <linux/percpu.h> #include <linux/hardirq.h> #include <linux/hugetlb.h> @@ -32,8 +31,6 @@ #include <asm/tlbflush.h> #include <asm/tlb.h> -#include "mmu_decl.h" - static inline int is_exec_fault(void) { return current->thread.regs && TRAP(current->thread.regs) == 0x400; @@ -72,7 +69,7 @@ struct page * maybe_pte_to_page(pte_t pte) * support falls into the same category. */ -static pte_t set_pte_filter(pte_t pte, unsigned long addr) +static pte_t set_pte_filter(pte_t pte) { pte = __pte(pte_val(pte) & ~_PAGE_HPTEFLAGS); if (pte_looks_normal(pte) && !(cpu_has_feature(CPU_FTR_COHERENT_ICACHE) || @@ -81,17 +78,6 @@ static pte_t set_pte_filter(pte_t pte, unsigned long addr) if (!pg) return pte; if (!test_bit(PG_arch_1, &pg->flags)) { -#ifdef CONFIG_8xx - /* On 8xx, cache control instructions (particularly - * "dcbst" from flush_dcache_icache) fault as write - * operation if there is an unpopulated TLB entry - * for the address in question. To workaround that, - * we invalidate the TLB here, thus avoiding dcbst - * misbehaviour. - */ - /* 8xx doesn't care about PID, size or ind args */ - _tlbil_va(addr, 0, 0, 0); -#endif /* CONFIG_8xx */ flush_dcache_icache_page(pg); set_bit(PG_arch_1, &pg->flags); } @@ -111,7 +97,7 @@ static pte_t set_access_flags_filter(pte_t pte, struct vm_area_struct *vma, * as we don't have two bits to spare for _PAGE_EXEC and _PAGE_HWEXEC so * instead we "filter out" the exec permission for non clean pages. */ -static pte_t set_pte_filter(pte_t pte, unsigned long addr) +static pte_t set_pte_filter(pte_t pte) { struct page *pg; @@ -187,13 +173,13 @@ void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { #ifdef CONFIG_DEBUG_VM - WARN_ON(pte_present(*ptep)); + WARN_ON(pte_val(*ptep) & _PAGE_PRESENT); #endif /* Note: mm->context.id might not yet have been assigned as * this context might not have been activated yet when this * is called. */ - pte = set_pte_filter(pte, addr); + pte = set_pte_filter(pte); /* Perform the setting of the PTE */ __set_pte_at(mm, addr, ptep, pte, 0); diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c index 6c856fb8c15..343a87fa78b 100644 --- a/arch/powerpc/mm/pgtable_32.c +++ b/arch/powerpc/mm/pgtable_32.c @@ -121,7 +121,10 @@ pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) ptepage = alloc_pages(flags, 0); if (!ptepage) return NULL; - pgtable_page_ctor(ptepage); + if (!pgtable_page_ctor(ptepage)) { + __free_page(ptepage); + return NULL; + } return ptepage; } @@ -296,6 +299,7 @@ int map_page(unsigned long va, phys_addr_t pa, int flags) set_pte_at(&init_mm, va, pg, pfn_pte(pa >> PAGE_SHIFT, __pgprot(flags))); } + smp_wmb(); return err; } diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index 536eec72c0f..f6ce1f111f5 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -33,7 +33,6 @@ #include <linux/swap.h> #include <linux/stddef.h> #include <linux/vmalloc.h> -#include <linux/init.h> #include <linux/bootmem.h> #include <linux/memblock.h> #include <linux/slab.h> @@ -153,6 +152,18 @@ int map_kernel_page(unsigned long ea, unsigned long pa, int flags) } #endif /* !CONFIG_PPC_MMU_NOHASH */ } + +#ifdef CONFIG_PPC_BOOK3E_64 + /* + * With hardware tablewalk, a sync is needed to ensure that + * subsequent accesses see the PTE we just wrote. Unlike userspace + * mappings, we can't tolerate spurious faults, so make sure + * the new PTE will be seen the first time. + */ + mb(); +#else + smp_wmb(); +#endif return 0; } @@ -378,6 +389,10 @@ static pte_t *__alloc_for_cache(struct mm_struct *mm, int kernel) __GFP_REPEAT | __GFP_ZERO); if (!page) return NULL; + if (!kernel && !pgtable_page_ctor(page)) { + __free_page(page); + return NULL; + } ret = page_address(page); spin_lock(&mm->page_table_lock); @@ -392,9 +407,6 @@ static pte_t *__alloc_for_cache(struct mm_struct *mm, int kernel) } spin_unlock(&mm->page_table_lock); - if (!kernel) - pgtable_page_ctor(page); - return (pte_t *)ret; } @@ -498,7 +510,8 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, } unsigned long pmd_hugepage_update(struct mm_struct *mm, unsigned long addr, - pmd_t *pmdp, unsigned long clr) + pmd_t *pmdp, unsigned long clr, + unsigned long set) { unsigned long old, tmp; @@ -514,14 +527,15 @@ unsigned long pmd_hugepage_update(struct mm_struct *mm, unsigned long addr, andi. %1,%0,%6\n\ bne- 1b \n\ andc %1,%0,%4 \n\ + or %1,%1,%7\n\ stdcx. %1,0,%3 \n\ bne- 1b" : "=&r" (old), "=&r" (tmp), "=m" (*pmdp) - : "r" (pmdp), "r" (clr), "m" (*pmdp), "i" (_PAGE_BUSY) + : "r" (pmdp), "r" (clr), "m" (*pmdp), "i" (_PAGE_BUSY), "r" (set) : "cc" ); #else old = pmd_val(*pmdp); - *pmdp = __pmd(old & ~clr); + *pmdp = __pmd((old & ~clr) | set); #endif if (old & _PAGE_HASHPTE) hpte_do_hugepage_flush(mm, addr, pmdp); @@ -633,6 +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(); } /* @@ -686,7 +705,7 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd) { #ifdef CONFIG_DEBUG_VM - WARN_ON(!pmd_none(*pmdp)); + WARN_ON(pmd_val(*pmdp) & _PAGE_PRESENT); assert_spin_locked(&mm->page_table_lock); WARN_ON(!pmd_trans_huge(pmd)); #endif @@ -696,7 +715,7 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr, void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { - pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT); + pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT, 0); } /* @@ -823,7 +842,7 @@ pmd_t pmdp_get_and_clear(struct mm_struct *mm, unsigned long old; pgtable_t *pgtable_slot; - old = pmd_hugepage_update(mm, addr, pmdp, ~0UL); + old = pmd_hugepage_update(mm, addr, pmdp, ~0UL, 0); old_pmd = __pmd(old); /* * We have pmd == none and we are holding page_table_lock. diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c index 9d1d33cd2be..0399a670295 100644 --- a/arch/powerpc/mm/slb.c +++ b/arch/powerpc/mm/slb.c @@ -97,7 +97,7 @@ static inline void create_shadowed_slbe(unsigned long ea, int ssize, static void __slb_flush_and_rebolt(void) { /* If you change this make sure you change SLB_NUM_BOLTED - * appropriately too. */ + * and PR KVM appropriately too. */ unsigned long linear_llp, vmalloc_llp, lflags, vflags; unsigned long ksp_esid_data, ksp_vsid_data; @@ -256,10 +256,14 @@ static inline void patch_slb_encoding(unsigned int *insn_addr, patch_instruction(insn_addr, insn); } +extern u32 slb_compare_rr_to_size[]; +extern u32 slb_miss_kernel_load_linear[]; +extern u32 slb_miss_kernel_load_io[]; +extern u32 slb_compare_rr_to_size[]; +extern u32 slb_miss_kernel_load_vmemmap[]; + void slb_set_size(u16 size) { - extern unsigned int *slb_compare_rr_to_size; - if (mmu_slb_size == size) return; @@ -272,11 +276,7 @@ void slb_initialize(void) unsigned long linear_llp, vmalloc_llp, io_llp; unsigned long lflags, vflags; static int slb_encoding_inited; - extern unsigned int *slb_miss_kernel_load_linear; - extern unsigned int *slb_miss_kernel_load_io; - extern unsigned int *slb_compare_rr_to_size; #ifdef CONFIG_SPARSEMEM_VMEMMAP - extern unsigned int *slb_miss_kernel_load_vmemmap; unsigned long vmemmap_llp; #endif diff --git a/arch/powerpc/mm/slb_low.S b/arch/powerpc/mm/slb_low.S index 17aa6dfceb3..736d18b3cef 100644 --- a/arch/powerpc/mm/slb_low.S +++ b/arch/powerpc/mm/slb_low.S @@ -35,7 +35,7 @@ _GLOBAL(slb_allocate_realmode) * check for bad kernel/user address * (ea & ~REGION_MASK) >= PGTABLE_RANGE */ - rldicr. r9,r3,4,(63 - 46 - 4) + rldicr. r9,r3,4,(63 - PGTABLE_EADDR_SIZE - 4) bne- 8f srdi r9,r3,60 /* get region */ @@ -59,7 +59,8 @@ _GLOBAL(slb_allocate_realmode) /* Linear mapping encoding bits, the "li" instruction below will * be patched by the kernel at boot */ -_GLOBAL(slb_miss_kernel_load_linear) +.globl slb_miss_kernel_load_linear +slb_miss_kernel_load_linear: li r11,0 /* * context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1 @@ -79,7 +80,8 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT) /* Check virtual memmap region. To be patches at kernel boot */ cmpldi cr0,r9,0xf bne 1f -_GLOBAL(slb_miss_kernel_load_vmemmap) +.globl slb_miss_kernel_load_vmemmap +slb_miss_kernel_load_vmemmap: li r11,0 b 6f 1: @@ -95,7 +97,8 @@ _GLOBAL(slb_miss_kernel_load_vmemmap) b 6f 5: /* IO mapping */ - _GLOBAL(slb_miss_kernel_load_io) +.globl slb_miss_kernel_load_io +slb_miss_kernel_load_io: li r11,0 6: /* @@ -250,7 +253,8 @@ slb_finish_load: 7: ld r10,PACASTABRR(r13) addi r10,r10,1 /* This gets soft patched on boot. */ -_GLOBAL(slb_compare_rr_to_size) +.globl slb_compare_rr_to_size +slb_compare_rr_to_size: cmpldi r10,0 blt+ 4f diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c index 3e99c149271..b0c75cc15ef 100644 --- a/arch/powerpc/mm/slice.c +++ b/arch/powerpc/mm/slice.c @@ -258,7 +258,7 @@ static bool slice_scan_available(unsigned long addr, slice = GET_HIGH_SLICE_INDEX(addr); *boundary_addr = (slice + end) ? ((slice + end) << SLICE_HIGH_SHIFT) : SLICE_LOW_TOP; - return !!(available.high_slices & (1u << slice)); + return !!(available.high_slices & (1ul << slice)); } } @@ -408,7 +408,7 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, if (fixed && (addr & ((1ul << pshift) - 1))) return -EINVAL; if (fixed && addr > (mm->task_size - len)) - return -EINVAL; + return -ENOMEM; /* If hint, make sure it matches our alignment restrictions */ if (!fixed && addr) { diff --git a/arch/powerpc/mm/subpage-prot.c b/arch/powerpc/mm/subpage-prot.c index a770df2dae7..6c0b1f5f8d2 100644 --- a/arch/powerpc/mm/subpage-prot.c +++ b/arch/powerpc/mm/subpage-prot.c @@ -78,7 +78,7 @@ static void hpte_flush_range(struct mm_struct *mm, unsigned long addr, pte = pte_offset_map_lock(mm, pmd, addr, &ptl); arch_enter_lazy_mmu_mode(); for (; npages > 0; --npages) { - pte_update(mm, addr, pte, 0, 0); + pte_update(mm, addr, pte, 0, 0, 0); addr += PAGE_SIZE; ++pte; } diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c index 36e44b4260e..c99f6510a0b 100644 --- a/arch/powerpc/mm/tlb_hash64.c +++ b/arch/powerpc/mm/tlb_hash64.c @@ -23,7 +23,6 @@ #include <linux/kernel.h> #include <linux/mm.h> -#include <linux/init.h> #include <linux/percpu.h> #include <linux/hardirq.h> #include <asm/pgalloc.h> diff --git a/arch/powerpc/mm/tlb_low_64e.S b/arch/powerpc/mm/tlb_low_64e.S index b4113bf8635..356e8b41fb0 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 */ @@ -136,7 +148,7 @@ BEGIN_MMU_FTR_SECTION */ PPC_TLBSRX_DOT(0,R16) ldx r14,r14,r15 /* grab pgd entry */ - beq normal_tlb_miss_done /* tlb exists already, bail */ + beq tlb_miss_done_bolted /* tlb exists already, bail */ MMU_FTR_SECTION_ELSE ldx r14,r14,r15 /* grab pgd entry */ ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_USE_TLBRSRV) @@ -192,6 +204,7 @@ ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_USE_TLBRSRV) mtspr SPRN_MAS7_MAS3,r15 tlbwe +tlb_miss_done_bolted: TLB_MISS_STATS_X(MMSTAT_TLB_MISS_NORM_OK) tlb_epilog_bolted rfi @@ -239,6 +252,183 @@ itlb_miss_fault_bolted: beq tlb_miss_common_bolted b itlb_miss_kernel_bolted +#ifdef CONFIG_PPC_FSL_BOOK3E +/* + * TLB miss handling for e6500 and derivatives, using hardware tablewalk. + * + * Linear mapping is bolted: no virtual page table or nested TLB misses + * Indirect entries in TLB1, hardware loads resulting direct entries + * into TLB0 + * No HES or NV hint on TLB1, so we need to do software round-robin + * No tlbsrx. so we need a spinlock, and we have to deal + * with MAS-damage caused by tlbsx + * 4K pages only + */ + + START_EXCEPTION(instruction_tlb_miss_e6500) + tlb_prolog_bolted BOOKE_INTERRUPT_ITLB_MISS SPRN_SRR0 + + ld r11,PACA_TCD_PTR(r13) + srdi. r15,r16,60 /* get region */ + ori r16,r16,1 + + TLB_MISS_STATS_SAVE_INFO_BOLTED + bne tlb_miss_kernel_e6500 /* user/kernel test */ + + b tlb_miss_common_e6500 + + START_EXCEPTION(data_tlb_miss_e6500) + tlb_prolog_bolted BOOKE_INTERRUPT_DTLB_MISS SPRN_DEAR + + ld r11,PACA_TCD_PTR(r13) + srdi. r15,r16,60 /* get region */ + rldicr r16,r16,0,62 + + TLB_MISS_STATS_SAVE_INFO_BOLTED + bne tlb_miss_kernel_e6500 /* user vs kernel check */ + +/* + * This is the guts of the TLB miss handler for e6500 and derivatives. + * We are entered with: + * + * r16 = page of faulting address (low bit 0 if data, 1 if instruction) + * r15 = crap (free to use) + * r14 = page table base + * r13 = PACA + * r11 = tlb_per_core ptr + * r10 = cpu number + */ +tlb_miss_common_e6500: + /* + * Search if we already have an indirect entry for that virtual + * address, and if we do, bail out. + * + * MAS6:IND should be already set based on MAS4 + */ +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 + stbcx. r10,0,r11 + bne 1b +3: + .subsection 1 +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 + .previous + + mfspr r15,SPRN_MAS2 + + tlbsx 0,r16 + mfspr r10,SPRN_MAS1 + andis. r10,r10,MAS1_VALID@h + bne tlb_miss_done_e6500 + + /* Undo MAS-damage from the tlbsx */ + mfspr r10,SPRN_MAS1 + oris r10,r10,MAS1_VALID@h + mtspr SPRN_MAS1,r10 + mtspr SPRN_MAS2,r15 + + /* Now, we need to walk the page tables. First check if we are in + * range. + */ + rldicl. r10,r16,64-PGTABLE_EADDR_SIZE,PGTABLE_EADDR_SIZE+4 + bne- tlb_miss_fault_e6500 + + rldicl r15,r16,64-PGDIR_SHIFT+3,64-PGD_INDEX_SIZE-3 + cmpldi cr0,r14,0 + clrrdi r15,r15,3 + beq- tlb_miss_fault_e6500 /* No PGDIR, bail */ + ldx r14,r14,r15 /* grab pgd entry */ + + rldicl r15,r16,64-PUD_SHIFT+3,64-PUD_INDEX_SIZE-3 + clrrdi r15,r15,3 + cmpdi cr0,r14,0 + bge tlb_miss_fault_e6500 /* Bad pgd entry or hugepage; bail */ + ldx r14,r14,r15 /* grab pud entry */ + + rldicl r15,r16,64-PMD_SHIFT+3,64-PMD_INDEX_SIZE-3 + clrrdi r15,r15,3 + cmpdi cr0,r14,0 + bge tlb_miss_fault_e6500 + ldx r14,r14,r15 /* Grab pmd entry */ + + mfspr r10,SPRN_MAS0 + cmpdi cr0,r14,0 + bge tlb_miss_fault_e6500 + + /* Now we build the MAS for a 2M indirect page: + * + * MAS 0 : ESEL needs to be filled by software round-robin + * MAS 1 : Fully set up + * - PID already updated by caller if necessary + * - TSIZE for now is base ind page size always + * - TID already cleared if necessary + * MAS 2 : Default not 2M-aligned, need to be redone + * MAS 3+7 : Needs to be done + */ + + ori r14,r14,(BOOK3E_PAGESZ_4K << MAS3_SPSIZE_SHIFT) + mtspr SPRN_MAS7_MAS3,r14 + + clrrdi r15,r16,21 /* make EA 2M-aligned */ + mtspr SPRN_MAS2,r15 + + lbz r15,TCD_ESEL_NEXT(r11) + lbz r16,TCD_ESEL_MAX(r11) + lbz r14,TCD_ESEL_FIRST(r11) + rlwimi r10,r15,16,0x00ff0000 /* insert esel_next into MAS0 */ + addi r15,r15,1 /* increment esel_next */ + mtspr SPRN_MAS0,r10 + cmpw r15,r16 + iseleq r15,r14,r15 /* if next == last use first */ + stb r15,TCD_ESEL_NEXT(r11) + + tlbwe + +tlb_miss_done_e6500: + .macro tlb_unlock_e6500 + beq cr1,1f /* no unlock if lock was recursively grabbed */ + li r15,0 + isync + stb r15,0(r11) +1: + .endm + + tlb_unlock_e6500 + TLB_MISS_STATS_X(MMSTAT_TLB_MISS_NORM_OK) + tlb_epilog_bolted + rfi + +tlb_miss_kernel_e6500: + mfspr r10,SPRN_MAS1 + ld r14,PACA_KERNELPGD(r13) + cmpldi cr0,r15,8 /* Check for vmalloc region */ + rlwinm r10,r10,0,16,1 /* Clear TID */ + mtspr SPRN_MAS1,r10 + beq+ tlb_miss_common_e6500 + +tlb_miss_fault_e6500: + tlb_unlock_e6500 + /* We need to check if it was an instruction miss */ + andi. r16,r16,1 + bne itlb_miss_fault_e6500 +dtlb_miss_fault_e6500: + TLB_MISS_STATS_D(MMSTAT_TLB_MISS_NORM_FAULT) + tlb_epilog_bolted + b exc_data_storage_book3e +itlb_miss_fault_e6500: + TLB_MISS_STATS_I(MMSTAT_TLB_MISS_NORM_FAULT) + tlb_epilog_bolted + b exc_instruction_storage_book3e +#endif /* CONFIG_PPC_FSL_BOOK3E */ + /********************************************************************** * * * TLB miss handling for Book3E with TLB reservation and HES support * @@ -918,7 +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 41cd68dee68..92cb18d52ea 100644 --- a/arch/powerpc/mm/tlb_nohash.c +++ b/arch/powerpc/mm/tlb_nohash.c @@ -43,6 +43,7 @@ #include <asm/tlb.h> #include <asm/code-patching.h> #include <asm/hugetlb.h> +#include <asm/paca.h> #include "mmu_decl.h" @@ -58,6 +59,10 @@ struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = { .shift = 12, .enc = BOOK3E_PAGESZ_4K, }, + [MMU_PAGE_2M] = { + .shift = 21, + .enc = BOOK3E_PAGESZ_2M, + }, [MMU_PAGE_4M] = { .shift = 22, .enc = BOOK3E_PAGESZ_4M, @@ -136,9 +141,18 @@ static inline int mmu_get_tsize(int psize) int mmu_linear_psize; /* Page size used for the linear mapping */ int mmu_pte_psize; /* Page size used for PTE pages */ int mmu_vmemmap_psize; /* Page size used for the virtual mem map */ -int book3e_htw_enabled; /* Is HW tablewalk enabled ? */ +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 @@ -305,7 +319,7 @@ void __flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr, void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr) { #ifdef CONFIG_HUGETLB_PAGE - if (is_vm_hugetlb_page(vma)) + if (vma && is_vm_hugetlb_page(vma)) flush_hugetlb_page(vma, vmaddr); #endif @@ -377,7 +391,7 @@ void tlb_flush_pgtable(struct mmu_gather *tlb, unsigned long address) { int tsize = mmu_psize_defs[mmu_pte_psize].enc; - if (book3e_htw_enabled) { + if (book3e_htw_mode != PPC_HTW_NONE) { unsigned long start = address & PMD_MASK; unsigned long end = address + PMD_SIZE; unsigned long size = 1UL << mmu_psize_defs[mmu_pte_psize].shift; @@ -430,7 +444,7 @@ static void setup_page_sizes(void) def = &mmu_psize_defs[psize]; shift = def->shift; - if (shift == 0) + if (shift == 0 || shift & 1) continue; /* adjust to be in terms of 4^shift Kb */ @@ -440,21 +454,40 @@ static void setup_page_sizes(void) def->flags |= MMU_PAGE_SIZE_DIRECT; } - goto no_indirect; + goto out; } if (fsl_mmu && (mmucfg & MMUCFG_MAVN) == MMUCFG_MAVN_V2) { - u32 tlb1ps = mfspr(SPRN_TLB1PS); + u32 tlb1cfg, tlb1ps; + + tlb0cfg = mfspr(SPRN_TLB0CFG); + tlb1cfg = mfspr(SPRN_TLB1CFG); + tlb1ps = mfspr(SPRN_TLB1PS); + eptcfg = mfspr(SPRN_EPTCFG); + + if ((tlb1cfg & TLBnCFG_IND) && (tlb0cfg & TLBnCFG_PT)) + book3e_htw_mode = PPC_HTW_E6500; + + /* + * We expect 4K subpage size and unrestricted indirect size. + * The lack of a restriction on indirect size is a Freescale + * extension, indicated by PSn = 0 but SPSn != 0. + */ + if (eptcfg != 2) + book3e_htw_mode = PPC_HTW_NONE; for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) { struct mmu_psize_def *def = &mmu_psize_defs[psize]; if (tlb1ps & (1U << (def->shift - 10))) { def->flags |= MMU_PAGE_SIZE_DIRECT; + + if (book3e_htw_mode && psize == MMU_PAGE_2M) + def->flags |= MMU_PAGE_SIZE_INDIRECT; } } - goto no_indirect; + goto out; } #endif @@ -471,8 +504,11 @@ static void setup_page_sizes(void) } /* Indirect page sizes supported ? */ - if ((tlb0cfg & TLBnCFG_IND) == 0) - goto no_indirect; + if ((tlb0cfg & TLBnCFG_IND) == 0 || + (tlb0cfg & TLBnCFG_PT) == 0) + goto out; + + book3e_htw_mode = PPC_HTW_IBM; /* Now, we only deal with one IND page size for each * direct size. Hopefully all implementations today are @@ -497,8 +533,8 @@ static void setup_page_sizes(void) def->ind = ps + 10; } } - no_indirect: +out: /* Cleanup array and print summary */ pr_info("MMU: Supported page sizes\n"); for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) { @@ -518,44 +554,28 @@ static void setup_page_sizes(void) } } -static void __patch_exception(int exc, unsigned long addr) -{ - extern unsigned int interrupt_base_book3e; - unsigned int *ibase = &interrupt_base_book3e; - - /* Our exceptions vectors start with a NOP and -then- a branch - * to deal with single stepping from userspace which stops on - * the second instruction. Thus we need to patch the second - * instruction of the exception, not the first one - */ - - patch_branch(ibase + (exc / 4) + 1, addr, 0); -} - -#define patch_exception(exc, name) do { \ - extern unsigned int name; \ - __patch_exception((exc), (unsigned long)&name); \ -} while (0) - static void setup_mmu_htw(void) { - /* Check if HW tablewalk is present, and if yes, enable it by: - * - * - patching the TLB miss handlers to branch to the - * one dedicates to it - * - * - setting the global book3e_htw_enabled - */ - unsigned int tlb0cfg = mfspr(SPRN_TLB0CFG); + /* + * If we want to use HW tablewalk, enable it by patching the TLB miss + * handlers to branch to the one dedicated to it. + */ - if ((tlb0cfg & TLBnCFG_IND) && - (tlb0cfg & TLBnCFG_PT)) { + switch (book3e_htw_mode) { + case PPC_HTW_IBM: patch_exception(0x1c0, exc_data_tlb_miss_htw_book3e); patch_exception(0x1e0, exc_instruction_tlb_miss_htw_book3e); - book3e_htw_enabled = 1; + 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; +#endif } pr_info("MMU: Book3E HW tablewalk %s\n", - book3e_htw_enabled ? "enabled" : "not supported"); + book3e_htw_mode != PPC_HTW_NONE ? "enabled" : "not supported"); } /* @@ -576,8 +596,13 @@ static void __early_init_mmu(int boot_cpu) /* XXX This should be decided at runtime based on supported * page sizes in the TLB, but for now let's assume 16M is * always there and a good fit (which it probably is) + * + * Freescale booke only supports 4K pages in TLB0, so use that. */ - mmu_vmemmap_psize = MMU_PAGE_16M; + if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) + mmu_vmemmap_psize = MMU_PAGE_4K; + else + mmu_vmemmap_psize = MMU_PAGE_16M; /* XXX This code only checks for TLB 0 capabilities and doesn't * check what page size combos are supported by the HW. It @@ -595,8 +620,16 @@ static void __early_init_mmu(int boot_cpu) /* Set MAS4 based on page table setting */ mas4 = 0x4 << MAS4_WIMGED_SHIFT; - if (book3e_htw_enabled) { - mas4 |= mas4 | MAS4_INDD; + switch (book3e_htw_mode) { + case PPC_HTW_E6500: + mas4 |= MAS4_INDD; + mas4 |= BOOK3E_PAGESZ_2M << MAS4_TSIZED_SHIFT; + mas4 |= MAS4_TLBSELD(1); + mmu_pte_psize = MMU_PAGE_2M; + break; + + case PPC_HTW_IBM: + mas4 |= MAS4_INDD; #ifdef CONFIG_PPC_64K_PAGES mas4 |= BOOK3E_PAGESZ_256M << MAS4_TSIZED_SHIFT; mmu_pte_psize = MMU_PAGE_256M; @@ -604,13 +637,16 @@ static void __early_init_mmu(int boot_cpu) mas4 |= BOOK3E_PAGESZ_1M << MAS4_TSIZED_SHIFT; mmu_pte_psize = MMU_PAGE_1M; #endif - } else { + break; + + case PPC_HTW_NONE: #ifdef CONFIG_PPC_64K_PAGES mas4 |= BOOK3E_PAGESZ_64K << MAS4_TSIZED_SHIFT; #else mas4 |= BOOK3E_PAGESZ_4K << MAS4_TSIZED_SHIFT; #endif mmu_pte_psize = mmu_virtual_psize; + break; } mtspr(SPRN_MAS4, mas4); @@ -630,8 +666,12 @@ static void __early_init_mmu(int boot_cpu) /* limit memory so we dont have linear faults */ memblock_enforce_memory_limit(linear_map_top); - patch_exception(0x1c0, exc_data_tlb_miss_bolted_book3e); - patch_exception(0x1e0, exc_instruction_tlb_miss_bolted_book3e); + 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); + } } #endif diff --git a/arch/powerpc/mm/tlb_nohash_low.S b/arch/powerpc/mm/tlb_nohash_low.S index 626ad081639..43ff3c797fb 100644 --- a/arch/powerpc/mm/tlb_nohash_low.S +++ b/arch/powerpc/mm/tlb_nohash_low.S @@ -402,7 +402,9 @@ _GLOBAL(set_context) * Load TLBCAM[index] entry in to the L2 CAM MMU */ _GLOBAL(loadcam_entry) - LOAD_REG_ADDR(r4, TLBCAM) + mflr r5 + LOAD_REG_ADDR_PIC(r4, TLBCAM) + mtlr r5 mulli r5,r3,TLBCAM_SIZE add r3,r5,r4 lwz r4,TLBCAM_MAS0(r3) |