diff options
Diffstat (limited to 'arch/powerpc/mm')
-rw-r--r-- | arch/powerpc/mm/8xx_mmu.c | 4 | ||||
-rw-r--r-- | arch/powerpc/mm/Makefile | 11 | ||||
-rw-r--r-- | arch/powerpc/mm/dump_bats.c | 173 | ||||
-rw-r--r-- | arch/powerpc/mm/dump_sr.c | 64 | ||||
-rw-r--r-- | arch/powerpc/mm/fault.c | 4 | ||||
-rw-r--r-- | arch/powerpc/mm/hugetlbpage.c | 40 | ||||
-rw-r--r-- | arch/powerpc/mm/init-common.c | 56 | ||||
-rw-r--r-- | arch/powerpc/mm/mem.c | 4 | ||||
-rw-r--r-- | arch/powerpc/mm/mmu_context.c | 10 | ||||
-rw-r--r-- | arch/powerpc/mm/mmu_context_book3s64.c | 15 | ||||
-rw-r--r-- | arch/powerpc/mm/mmu_context_nohash.c | 2 | ||||
-rw-r--r-- | arch/powerpc/mm/mmu_decl.h | 2 | ||||
-rw-r--r-- | arch/powerpc/mm/numa.c | 2 | ||||
-rw-r--r-- | arch/powerpc/mm/pgtable-book3s64.c | 88 | ||||
-rw-r--r-- | arch/powerpc/mm/pgtable-frag.c | 119 | ||||
-rw-r--r-- | arch/powerpc/mm/pgtable.c | 6 | ||||
-rw-r--r-- | arch/powerpc/mm/pgtable_32.c | 27 | ||||
-rw-r--r-- | arch/powerpc/mm/pkeys.c | 15 |
18 files changed, 456 insertions, 186 deletions
diff --git a/arch/powerpc/mm/8xx_mmu.c b/arch/powerpc/mm/8xx_mmu.c index 01b7f5107c3a..e2b6687ebb50 100644 --- a/arch/powerpc/mm/8xx_mmu.c +++ b/arch/powerpc/mm/8xx_mmu.c @@ -175,12 +175,12 @@ void set_context(unsigned long id, pgd_t *pgd) *(ptr + 1) = pgd; #endif - /* Register M_TW will contain base address of level 1 table minus the + /* Register M_TWB will contain base address of level 1 table minus the * lower part of the kernel PGDIR base address, so that all accesses to * level 1 table are done relative to lower part of kernel PGDIR base * address. */ - mtspr(SPRN_M_TW, __pa(pgd) - offset); + mtspr(SPRN_M_TWB, __pa(pgd) - offset); /* Update context */ mtspr(SPRN_M_CASID, id - 1); diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile index ca96e7be4d0e..f965fc33a8b7 100644 --- a/arch/powerpc/mm/Makefile +++ b/arch/powerpc/mm/Makefile @@ -15,10 +15,13 @@ obj-$(CONFIG_PPC_MMU_NOHASH) += mmu_context_nohash.o tlb_nohash.o \ obj-$(CONFIG_PPC_BOOK3E) += tlb_low_$(BITS)e.o hash64-$(CONFIG_PPC_NATIVE) := hash_native_64.o obj-$(CONFIG_PPC_BOOK3E_64) += pgtable-book3e.o -obj-$(CONFIG_PPC_BOOK3S_64) += pgtable-hash64.o hash_utils_64.o slb.o $(hash64-y) mmu_context_book3s64.o pgtable-book3s64.o +obj-$(CONFIG_PPC_BOOK3S_64) += pgtable-hash64.o hash_utils_64.o slb.o \ + $(hash64-y) mmu_context_book3s64.o \ + pgtable-book3s64.o pgtable-frag.o +obj-$(CONFIG_PPC32) += pgtable-frag.o obj-$(CONFIG_PPC_RADIX_MMU) += pgtable-radix.o tlb-radix.o -obj-$(CONFIG_PPC_STD_MMU_32) += ppc_mmu_32.o hash_low_32.o mmu_context_hash32.o -obj-$(CONFIG_PPC_STD_MMU) += tlb_hash$(BITS).o +obj-$(CONFIG_PPC_BOOK3S_32) += ppc_mmu_32.o hash_low_32.o mmu_context_hash32.o +obj-$(CONFIG_PPC_BOOK3S) += tlb_hash$(BITS).o ifdef CONFIG_PPC_BOOK3S_64 obj-$(CONFIG_PPC_4K_PAGES) += hash64_4k.o obj-$(CONFIG_PPC_64K_PAGES) += hash64_64k.o @@ -47,7 +50,7 @@ ifdef CONFIG_PPC_PTDUMP obj-$(CONFIG_4xx) += dump_linuxpagetables-generic.o obj-$(CONFIG_PPC_8xx) += dump_linuxpagetables-8xx.o obj-$(CONFIG_PPC_BOOK3E_MMU) += dump_linuxpagetables-generic.o -obj-$(CONFIG_PPC_BOOK3S_32) += dump_linuxpagetables-generic.o +obj-$(CONFIG_PPC_BOOK3S_32) += dump_linuxpagetables-generic.o dump_bats.o dump_sr.o obj-$(CONFIG_PPC_BOOK3S_64) += dump_linuxpagetables-book3s64.o endif obj-$(CONFIG_PPC_HTDUMP) += dump_hashpagetable.o diff --git a/arch/powerpc/mm/dump_bats.c b/arch/powerpc/mm/dump_bats.c new file mode 100644 index 000000000000..a0d23e96e841 --- /dev/null +++ b/arch/powerpc/mm/dump_bats.c @@ -0,0 +1,173 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright 2018, Christophe Leroy CS S.I. + * <christophe.leroy@c-s.fr> + * + * This dumps the content of BATS + */ + +#include <asm/debugfs.h> +#include <asm/pgtable.h> +#include <asm/cpu_has_feature.h> + +static char *pp_601(int k, int pp) +{ + if (pp == 0) + return k ? "NA" : "RWX"; + if (pp == 1) + return k ? "ROX" : "RWX"; + if (pp == 2) + return k ? "RWX" : "RWX"; + return k ? "ROX" : "ROX"; +} + +static void bat_show_601(struct seq_file *m, int idx, u32 lower, u32 upper) +{ + u32 blpi = upper & 0xfffe0000; + u32 k = (upper >> 2) & 3; + u32 pp = upper & 3; + phys_addr_t pbn = PHYS_BAT_ADDR(lower); + u32 bsm = lower & 0x3ff; + u32 size = (bsm + 1) << 17; + + seq_printf(m, "%d: ", idx); + if (!(lower & 0x40)) { + seq_puts(m, " -\n"); + return; + } + + seq_printf(m, "0x%08x-0x%08x ", blpi, blpi + size - 1); +#ifdef CONFIG_PHYS_64BIT + seq_printf(m, "0x%016llx ", pbn); +#else + seq_printf(m, "0x%08x ", pbn); +#endif + + seq_printf(m, "Kernel %s User %s", pp_601(k & 2, pp), pp_601(k & 1, pp)); + + if (lower & _PAGE_WRITETHRU) + seq_puts(m, "write through "); + if (lower & _PAGE_NO_CACHE) + seq_puts(m, "no cache "); + if (lower & _PAGE_COHERENT) + seq_puts(m, "coherent "); + seq_puts(m, "\n"); +} + +#define BAT_SHOW_601(_m, _n, _l, _u) bat_show_601(_m, _n, mfspr(_l), mfspr(_u)) + +static int bats_show_601(struct seq_file *m, void *v) +{ + seq_puts(m, "---[ Block Address Translation ]---\n"); + + BAT_SHOW_601(m, 0, SPRN_IBAT0L, SPRN_IBAT0U); + BAT_SHOW_601(m, 1, SPRN_IBAT1L, SPRN_IBAT1U); + BAT_SHOW_601(m, 2, SPRN_IBAT2L, SPRN_IBAT2U); + BAT_SHOW_601(m, 3, SPRN_IBAT3L, SPRN_IBAT3U); + + return 0; +} + +static void bat_show_603(struct seq_file *m, int idx, u32 lower, u32 upper, bool is_d) +{ + u32 bepi = upper & 0xfffe0000; + u32 bl = (upper >> 2) & 0x7ff; + u32 k = upper & 3; + phys_addr_t brpn = PHYS_BAT_ADDR(lower); + u32 size = (bl + 1) << 17; + + seq_printf(m, "%d: ", idx); + if (k == 0) { + seq_puts(m, " -\n"); + return; + } + + seq_printf(m, "0x%08x-0x%08x ", bepi, bepi + size - 1); +#ifdef CONFIG_PHYS_64BIT + seq_printf(m, "0x%016llx ", brpn); +#else + seq_printf(m, "0x%08x ", brpn); +#endif + + if (k == 1) + seq_puts(m, "User "); + else if (k == 2) + seq_puts(m, "Kernel "); + else + seq_puts(m, "Kernel/User "); + + if (lower & BPP_RX) + seq_puts(m, is_d ? "RO " : "EXEC "); + else if (lower & BPP_RW) + seq_puts(m, is_d ? "RW " : "EXEC "); + else + seq_puts(m, is_d ? "NA " : "NX "); + + if (lower & _PAGE_WRITETHRU) + seq_puts(m, "write through "); + if (lower & _PAGE_NO_CACHE) + seq_puts(m, "no cache "); + if (lower & _PAGE_COHERENT) + seq_puts(m, "coherent "); + if (lower & _PAGE_GUARDED) + seq_puts(m, "guarded "); + seq_puts(m, "\n"); +} + +#define BAT_SHOW_603(_m, _n, _l, _u, _d) bat_show_603(_m, _n, mfspr(_l), mfspr(_u), _d) + +static int bats_show_603(struct seq_file *m, void *v) +{ + seq_puts(m, "---[ Instruction Block Address Translation ]---\n"); + + BAT_SHOW_603(m, 0, SPRN_IBAT0L, SPRN_IBAT0U, false); + BAT_SHOW_603(m, 1, SPRN_IBAT1L, SPRN_IBAT1U, false); + BAT_SHOW_603(m, 2, SPRN_IBAT2L, SPRN_IBAT2U, false); + BAT_SHOW_603(m, 3, SPRN_IBAT3L, SPRN_IBAT3U, false); + if (mmu_has_feature(MMU_FTR_USE_HIGH_BATS)) { + BAT_SHOW_603(m, 4, SPRN_IBAT4L, SPRN_IBAT4U, false); + BAT_SHOW_603(m, 5, SPRN_IBAT5L, SPRN_IBAT5U, false); + BAT_SHOW_603(m, 6, SPRN_IBAT6L, SPRN_IBAT6U, false); + BAT_SHOW_603(m, 7, SPRN_IBAT7L, SPRN_IBAT7U, false); + } + + seq_puts(m, "\n---[ Data Block Address Translation ]---\n"); + + BAT_SHOW_603(m, 0, SPRN_DBAT0L, SPRN_DBAT0U, true); + BAT_SHOW_603(m, 1, SPRN_DBAT1L, SPRN_DBAT1U, true); + BAT_SHOW_603(m, 2, SPRN_DBAT2L, SPRN_DBAT2U, true); + BAT_SHOW_603(m, 3, SPRN_DBAT3L, SPRN_DBAT3U, true); + if (mmu_has_feature(MMU_FTR_USE_HIGH_BATS)) { + BAT_SHOW_603(m, 4, SPRN_DBAT4L, SPRN_DBAT4U, true); + BAT_SHOW_603(m, 5, SPRN_DBAT5L, SPRN_DBAT5U, true); + BAT_SHOW_603(m, 6, SPRN_DBAT6L, SPRN_DBAT6U, true); + BAT_SHOW_603(m, 7, SPRN_DBAT7L, SPRN_DBAT7U, true); + } + + return 0; +} + +static int bats_open(struct inode *inode, struct file *file) +{ + if (cpu_has_feature(CPU_FTR_601)) + return single_open(file, bats_show_601, NULL); + + return single_open(file, bats_show_603, NULL); +} + +static const struct file_operations bats_fops = { + .open = bats_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init bats_init(void) +{ + struct dentry *debugfs_file; + + debugfs_file = debugfs_create_file("block_address_translation", 0400, + powerpc_debugfs_root, NULL, &bats_fops); + return debugfs_file ? 0 : -ENOMEM; +} +device_initcall(bats_init); diff --git a/arch/powerpc/mm/dump_sr.c b/arch/powerpc/mm/dump_sr.c new file mode 100644 index 000000000000..501843664bb9 --- /dev/null +++ b/arch/powerpc/mm/dump_sr.c @@ -0,0 +1,64 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright 2018, Christophe Leroy CS S.I. + * <christophe.leroy@c-s.fr> + * + * This dumps the content of Segment Registers + */ + +#include <asm/debugfs.h> + +static void seg_show(struct seq_file *m, int i) +{ + u32 val = mfsrin(i << 28); + + seq_printf(m, "0x%01x0000000-0x%01xfffffff ", i, i); + seq_printf(m, "Kern key %d ", (val >> 30) & 1); + seq_printf(m, "User key %d ", (val >> 29) & 1); + if (val & 0x80000000) { + seq_printf(m, "Device 0x%03x", (val >> 20) & 0x1ff); + seq_printf(m, "-0x%05x", val & 0xfffff); + } else { + if (val & 0x10000000) + seq_puts(m, "No Exec "); + seq_printf(m, "VSID 0x%06x", val & 0xffffff); + } + seq_puts(m, "\n"); +} + +static int sr_show(struct seq_file *m, void *v) +{ + int i; + + seq_puts(m, "---[ User Segments ]---\n"); + for (i = 0; i < TASK_SIZE >> 28; i++) + seg_show(m, i); + + seq_puts(m, "\n---[ Kernel Segments ]---\n"); + for (; i < 16; i++) + seg_show(m, i); + + return 0; +} + +static int sr_open(struct inode *inode, struct file *file) +{ + return single_open(file, sr_show, NULL); +} + +static const struct file_operations sr_fops = { + .open = sr_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init sr_init(void) +{ + struct dentry *debugfs_file; + + debugfs_file = debugfs_create_file("segment_registers", 0400, + powerpc_debugfs_root, NULL, &sr_fops); + return debugfs_file ? 0 : -ENOMEM; +} +device_initcall(sr_init); diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 1697e903bbf2..01b9bcc7fa85 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -341,7 +341,7 @@ static inline void cmo_account_page_fault(void) static inline void cmo_account_page_fault(void) { } #endif /* CONFIG_PPC_SMLPAR */ -#ifdef CONFIG_PPC_STD_MMU +#ifdef CONFIG_PPC_BOOK3S static void sanity_check_fault(bool is_write, unsigned long error_code) { /* @@ -378,7 +378,7 @@ static void sanity_check_fault(bool is_write, unsigned long error_code) } #else static void sanity_check_fault(bool is_write, unsigned long error_code) { } -#endif /* CONFIG_PPC_STD_MMU */ +#endif /* CONFIG_PPC_BOOK3S */ /* * Define the correct "is_write" bit in error_code based diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 8cf035e68378..5b236621d302 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -42,6 +42,8 @@ EXPORT_SYMBOL(HPAGE_SHIFT); #define hugepd_none(hpd) (hpd_val(hpd) == 0) +#define PTE_T_ORDER (__builtin_ffs(sizeof(pte_t)) - __builtin_ffs(sizeof(void *))) + pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz) { /* @@ -61,14 +63,17 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp, int num_hugepd; if (pshift >= pdshift) { - cachep = hugepte_cache; + cachep = PGT_CACHE(PTE_T_ORDER); num_hugepd = 1 << (pshift - pdshift); + } else if (IS_ENABLED(CONFIG_PPC_8xx)) { + cachep = PGT_CACHE(PTE_INDEX_SIZE); + num_hugepd = 1; } else { cachep = PGT_CACHE(pdshift - pshift); num_hugepd = 1; } - new = kmem_cache_zalloc(cachep, pgtable_gfp_flags(mm, GFP_KERNEL)); + new = kmem_cache_alloc(cachep, pgtable_gfp_flags(mm, GFP_KERNEL)); BUG_ON(pshift > HUGEPD_SHIFT_MASK); BUG_ON((unsigned long)new & HUGEPD_SHIFT_MASK); @@ -264,7 +269,7 @@ static void hugepd_free_rcu_callback(struct rcu_head *head) unsigned int i; for (i = 0; i < batch->index; i++) - kmem_cache_free(hugepte_cache, batch->ptes[i]); + kmem_cache_free(PGT_CACHE(PTE_T_ORDER), batch->ptes[i]); free_page((unsigned long)batch); } @@ -277,7 +282,7 @@ static void hugepd_free(struct mmu_gather *tlb, void *hugepte) if (atomic_read(&tlb->mm->mm_users) < 2 || mm_is_thread_local(tlb->mm)) { - kmem_cache_free(hugepte_cache, hugepte); + kmem_cache_free(PGT_CACHE(PTE_T_ORDER), hugepte); put_cpu_var(hugepd_freelist_cur); return; } @@ -329,6 +334,9 @@ static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshif if (shift >= pdshift) hugepd_free(tlb, hugepte); + else if (IS_ENABLED(CONFIG_PPC_8xx)) + pgtable_free_tlb(tlb, hugepte, + get_hugepd_cache_index(PTE_INDEX_SIZE)); else pgtable_free_tlb(tlb, hugepte, get_hugepd_cache_index(pdshift - shift)); @@ -652,7 +660,6 @@ static int __init hugepage_setup_sz(char *str) } __setup("hugepagesz=", hugepage_setup_sz); -struct kmem_cache *hugepte_cache; static int __init hugetlbpage_init(void) { int psize; @@ -699,24 +706,13 @@ static int __init hugetlbpage_init(void) * if we have pdshift and shift value same, we don't * use pgt cache for hugepd. */ - if (pdshift > shift) - pgtable_cache_add(pdshift - shift, NULL); + if (pdshift > shift && IS_ENABLED(CONFIG_PPC_8xx)) + pgtable_cache_add(PTE_INDEX_SIZE); + else if (pdshift > shift) + pgtable_cache_add(pdshift - shift); #if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_8xx) - else if (!hugepte_cache) { - /* - * Create a kmem cache for hugeptes. The bottom bits in - * the pte have size information encoded in them, so - * align them to allow this - */ - hugepte_cache = kmem_cache_create("hugepte-cache", - sizeof(pte_t), - HUGEPD_SHIFT_MASK + 1, - 0, NULL); - if (hugepte_cache == NULL) - panic("%s: Unable to create kmem cache " - "for hugeptes\n", __func__); - - } + else + pgtable_cache_add(PTE_T_ORDER); #endif } diff --git a/arch/powerpc/mm/init-common.c b/arch/powerpc/mm/init-common.c index 2b656e67f2ea..1e6910eb70ed 100644 --- a/arch/powerpc/mm/init-common.c +++ b/arch/powerpc/mm/init-common.c @@ -25,22 +25,40 @@ #include <asm/pgalloc.h> #include <asm/pgtable.h> -static void pgd_ctor(void *addr) -{ - memset(addr, 0, PGD_TABLE_SIZE); +#define CTOR(shift) static void ctor_##shift(void *addr) \ +{ \ + memset(addr, 0, sizeof(void *) << (shift)); \ } -static void pud_ctor(void *addr) -{ - memset(addr, 0, PUD_TABLE_SIZE); -} +CTOR(0); CTOR(1); CTOR(2); CTOR(3); CTOR(4); CTOR(5); CTOR(6); CTOR(7); +CTOR(8); CTOR(9); CTOR(10); CTOR(11); CTOR(12); CTOR(13); CTOR(14); CTOR(15); -static void pmd_ctor(void *addr) +static inline void (*ctor(int shift))(void *) { - memset(addr, 0, PMD_TABLE_SIZE); + BUILD_BUG_ON(MAX_PGTABLE_INDEX_SIZE != 15); + + switch (shift) { + case 0: return ctor_0; + case 1: return ctor_1; + case 2: return ctor_2; + case 3: return ctor_3; + case 4: return ctor_4; + case 5: return ctor_5; + case 6: return ctor_6; + case 7: return ctor_7; + case 8: return ctor_8; + case 9: return ctor_9; + case 10: return ctor_10; + case 11: return ctor_11; + case 12: return ctor_12; + case 13: return ctor_13; + case 14: return ctor_14; + case 15: return ctor_15; + } + return NULL; } -struct kmem_cache *pgtable_cache[MAX_PGTABLE_INDEX_SIZE]; +struct kmem_cache *pgtable_cache[MAX_PGTABLE_INDEX_SIZE + 1]; EXPORT_SYMBOL_GPL(pgtable_cache); /* used by kvm_hv module */ /* @@ -50,7 +68,7 @@ EXPORT_SYMBOL_GPL(pgtable_cache); /* used by kvm_hv module */ * everything else. Caches created by this function are used for all * the higher level pagetables, and for hugepage pagetables. */ -void pgtable_cache_add(unsigned shift, void (*ctor)(void *)) +void pgtable_cache_add(unsigned int shift) { char *name; unsigned long table_size = sizeof(void *) << shift; @@ -71,19 +89,19 @@ void pgtable_cache_add(unsigned shift, void (*ctor)(void *)) * moment, gcc doesn't seem to recognize is_power_of_2 as a * constant expression, so so much for that. */ BUG_ON(!is_power_of_2(minalign)); - BUG_ON((shift < 1) || (shift > MAX_PGTABLE_INDEX_SIZE)); + BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE); if (PGT_CACHE(shift)) return; /* Already have a cache of this size */ align = max_t(unsigned long, align, minalign); name = kasprintf(GFP_KERNEL, "pgtable-2^%d", shift); - new = kmem_cache_create(name, table_size, align, 0, ctor); + new = kmem_cache_create(name, table_size, align, 0, ctor(shift)); if (!new) panic("Could not allocate pgtable cache for order %d", shift); kfree(name); - pgtable_cache[shift - 1] = new; + pgtable_cache[shift] = new; pr_debug("Allocated pgtable cache for order %d\n", shift); } @@ -91,15 +109,15 @@ EXPORT_SYMBOL_GPL(pgtable_cache_add); /* used by kvm_hv module */ void pgtable_cache_init(void) { - pgtable_cache_add(PGD_INDEX_SIZE, pgd_ctor); + pgtable_cache_add(PGD_INDEX_SIZE); - if (PMD_CACHE_INDEX && !PGT_CACHE(PMD_CACHE_INDEX)) - pgtable_cache_add(PMD_CACHE_INDEX, pmd_ctor); + if (PMD_CACHE_INDEX) + pgtable_cache_add(PMD_CACHE_INDEX); /* * In all current configs, when the PUD index exists it's the * same size as either the pgd or pmd index except with THP enabled * on book3s 64 */ - if (PUD_CACHE_INDEX && !PGT_CACHE(PUD_CACHE_INDEX)) - pgtable_cache_add(PUD_CACHE_INDEX, pud_ctor); + if (PUD_CACHE_INDEX) + pgtable_cache_add(PUD_CACHE_INDEX); } diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 0a64fffabee1..065c37d54b49 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -503,7 +503,7 @@ EXPORT_SYMBOL(flush_icache_user_range); void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { -#ifdef CONFIG_PPC_STD_MMU +#ifdef CONFIG_PPC_BOOK3S /* * We don't need to worry about _PAGE_PRESENT here because we are * called with either mm->page_table_lock held or ptl lock held @@ -541,7 +541,7 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, } hash_preload(vma->vm_mm, address, is_exec, trap); -#endif /* CONFIG_PPC_STD_MMU */ +#endif /* CONFIG_PPC_BOOK3S */ #if (defined(CONFIG_PPC_BOOK3E_64) || defined(CONFIG_PPC_FSL_BOOK3E)) \ && defined(CONFIG_HUGETLB_PAGE) if (is_vm_hugetlb_page(vma)) diff --git a/arch/powerpc/mm/mmu_context.c b/arch/powerpc/mm/mmu_context.c index f84e14f23e50..bb52320b7369 100644 --- a/arch/powerpc/mm/mmu_context.c +++ b/arch/powerpc/mm/mmu_context.c @@ -15,6 +15,7 @@ #include <linux/sched/mm.h> #include <asm/mmu_context.h> +#include <asm/pgalloc.h> #if defined(CONFIG_PPC32) static inline void switch_mm_pgdir(struct task_struct *tsk, @@ -97,3 +98,12 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, switch_mmu_context(prev, next, tsk); } +#ifdef CONFIG_PPC32 +void arch_exit_mmap(struct mm_struct *mm) +{ + void *frag = pte_frag_get(&mm->context); + + if (frag) + pte_frag_destroy(frag); +} +#endif diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c index 510f103d7813..f720c5cc0b5e 100644 --- a/arch/powerpc/mm/mmu_context_book3s64.c +++ b/arch/powerpc/mm/mmu_context_book3s64.c @@ -164,21 +164,6 @@ static void destroy_contexts(mm_context_t *ctx) } } -static void pte_frag_destroy(void *pte_frag) -{ - int count; - struct page *page; - - page = virt_to_page(pte_frag); - /* drop all the pending references */ - count = ((unsigned long)pte_frag & ~PAGE_MASK) >> PTE_FRAG_SIZE_SHIFT; - /* We allow PTE_FRAG_NR fragments from a PTE page */ - if (atomic_sub_and_test(PTE_FRAG_NR - count, &page->pt_frag_refcount)) { - pgtable_page_dtor(page); - __free_page(page); - } -} - static void pmd_frag_destroy(void *pmd_frag) { int count; diff --git a/arch/powerpc/mm/mmu_context_nohash.c b/arch/powerpc/mm/mmu_context_nohash.c index 2faca46ad720..431ecf37f17c 100644 --- a/arch/powerpc/mm/mmu_context_nohash.c +++ b/arch/powerpc/mm/mmu_context_nohash.c @@ -385,6 +385,7 @@ int init_new_context(struct task_struct *t, struct mm_struct *mm) #endif mm->context.id = MMU_NO_CONTEXT; mm->context.active = 0; + pte_frag_set(&mm->context, NULL); return 0; } @@ -487,4 +488,3 @@ void __init mmu_context_init(void) next_context = FIRST_CONTEXT; nr_free_contexts = LAST_CONTEXT - FIRST_CONTEXT + 1; } - diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h index 8574fbbc45e0..c4a717da65eb 100644 --- a/arch/powerpc/mm/mmu_decl.h +++ b/arch/powerpc/mm/mmu_decl.h @@ -155,7 +155,7 @@ struct tlbcam { }; #endif -#if defined(CONFIG_6xx) || defined(CONFIG_FSL_BOOKE) || defined(CONFIG_PPC_8xx) +#if defined(CONFIG_PPC_BOOK3S_32) || defined(CONFIG_FSL_BOOKE) || defined(CONFIG_PPC_8xx) /* 6xx have BATS */ /* FSL_BOOKE have TLBCAM */ /* 8xx have LTLB */ diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index ce28ae5ca080..87f0dd004295 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -1475,7 +1475,7 @@ static int dt_update_callback(struct notifier_block *nb, switch (action) { case OF_RECONFIG_UPDATE_PROPERTY: - if (!of_prop_cmp(update->dn->type, "cpu") && + if (of_node_is_type(update->dn, "cpu") && !of_prop_cmp(update->prop->name, "ibm,associativity")) { u32 core_id; of_property_read_u32(update->dn, "reg", &core_id); diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c index 9f93c9f985c5..f3c31f5e1026 100644 --- a/arch/powerpc/mm/pgtable-book3s64.c +++ b/arch/powerpc/mm/pgtable-book3s64.c @@ -244,6 +244,9 @@ static pmd_t *get_pmd_from_cache(struct mm_struct *mm) { void *pmd_frag, *ret; + if (PMD_FRAG_NR == 1) + return NULL; + spin_lock(&mm->page_table_lock); ret = mm->context.pmd_frag; if (ret) { @@ -322,91 +325,6 @@ void pmd_fragment_free(unsigned long *pmd) } } -static pte_t *get_pte_from_cache(struct mm_struct *mm) -{ - void *pte_frag, *ret; - - spin_lock(&mm->page_table_lock); - ret = mm->context.pte_frag; - if (ret) { - pte_frag = ret + PTE_FRAG_SIZE; - /* - * If we have taken up all the fragments mark PTE page NULL - */ - if (((unsigned long)pte_frag & ~PAGE_MASK) == 0) - pte_frag = NULL; - mm->context.pte_frag = pte_frag; - } - spin_unlock(&mm->page_table_lock); - return (pte_t *)ret; -} - -static pte_t *__alloc_for_ptecache(struct mm_struct *mm, int kernel) -{ - void *ret = NULL; - struct page *page; - - if (!kernel) { - page = alloc_page(PGALLOC_GFP | __GFP_ACCOUNT); - if (!page) - return NULL; - if (!pgtable_page_ctor(page)) { - __free_page(page); - return NULL; - } - } else { - page = alloc_page(PGALLOC_GFP); - if (!page) - return NULL; - } - - atomic_set(&page->pt_frag_refcount, 1); - - ret = page_address(page); - /* - * if we support only one fragment just return the - * allocated page. - */ - if (PTE_FRAG_NR == 1) - return ret; - spin_lock(&mm->page_table_lock); - /* - * If we find pgtable_page set, we return - * the allocated page with single fragement - * count. - */ - if (likely(!mm->context.pte_frag)) { - atomic_set(&page->pt_frag_refcount, PTE_FRAG_NR); - mm->context.pte_frag = ret + PTE_FRAG_SIZE; - } - spin_unlock(&mm->page_table_lock); - - return (pte_t *)ret; -} - -pte_t *pte_fragment_alloc(struct mm_struct *mm, unsigned long vmaddr, int kernel) -{ - pte_t *pte; - - pte = get_pte_from_cache(mm); - if (pte) - return pte; - - return __alloc_for_ptecache(mm, kernel); -} - -void pte_fragment_free(unsigned long *table, int kernel) -{ - struct page *page = virt_to_page(table); - - BUG_ON(atomic_read(&page->pt_frag_refcount) <= 0); - if (atomic_dec_and_test(&page->pt_frag_refcount)) { - if (!kernel) - pgtable_page_dtor(page); - __free_page(page); - } -} - static inline void pgtable_free(void *table, int index) { switch (index) { diff --git a/arch/powerpc/mm/pgtable-frag.c b/arch/powerpc/mm/pgtable-frag.c new file mode 100644 index 000000000000..af23a587f019 --- /dev/null +++ b/arch/powerpc/mm/pgtable-frag.c @@ -0,0 +1,119 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Handling Page Tables through page fragments + * + */ + +#include <linux/kernel.h> +#include <linux/gfp.h> +#include <linux/mm.h> +#include <linux/percpu.h> +#include <linux/hardirq.h> +#include <linux/hugetlb.h> +#include <asm/pgalloc.h> +#include <asm/tlbflush.h> +#include <asm/tlb.h> + +void pte_frag_destroy(void *pte_frag) +{ + int count; + struct page *page; + + page = virt_to_page(pte_frag); + /* drop all the pending references */ + count = ((unsigned long)pte_frag & ~PAGE_MASK) >> PTE_FRAG_SIZE_SHIFT; + /* We allow PTE_FRAG_NR fragments from a PTE page */ + if (atomic_sub_and_test(PTE_FRAG_NR - count, &page->pt_frag_refcount)) { + pgtable_page_dtor(page); + __free_page(page); + } +} + +static pte_t *get_pte_from_cache(struct mm_struct *mm) +{ + void *pte_frag, *ret; + + if (PTE_FRAG_NR == 1) + return NULL; + + spin_lock(&mm->page_table_lock); + ret = pte_frag_get(&mm->context); + if (ret) { + pte_frag = ret + PTE_FRAG_SIZE; + /* + * If we have taken up all the fragments mark PTE page NULL + */ + if (((unsigned long)pte_frag & ~PAGE_MASK) == 0) + pte_frag = NULL; + pte_frag_set(&mm->context, pte_frag); + } + spin_unlock(&mm->page_table_lock); + return (pte_t *)ret; +} + +static pte_t *__alloc_for_ptecache(struct mm_struct *mm, int kernel) +{ + void *ret = NULL; + struct page *page; + + if (!kernel) { + page = alloc_page(PGALLOC_GFP | __GFP_ACCOUNT); + if (!page) + return NULL; + if (!pgtable_page_ctor(page)) { + __free_page(page); + return NULL; + } + } else { + page = alloc_page(PGALLOC_GFP); + if (!page) + return NULL; + } + + atomic_set(&page->pt_frag_refcount, 1); + + ret = page_address(page); + /* + * if we support only one fragment just return the + * allocated page. + */ + if (PTE_FRAG_NR == 1) + return ret; + spin_lock(&mm->page_table_lock); + /* + * If we find pgtable_page set, we return + * the allocated page with single fragement + * count. + */ + if (likely(!pte_frag_get(&mm->context))) { + atomic_set(&page->pt_frag_refcount, PTE_FRAG_NR); + pte_frag_set(&mm->context, ret + PTE_FRAG_SIZE); + } + spin_unlock(&mm->page_table_lock); + + return (pte_t *)ret; +} + +pte_t *pte_fragment_alloc(struct mm_struct *mm, unsigned long vmaddr, int kernel) +{ + pte_t *pte; + + pte = get_pte_from_cache(mm); + if (pte) + return pte; + + return __alloc_for_ptecache(mm, kernel); +} + +void pte_fragment_free(unsigned long *table, int kernel) +{ + struct page *page = virt_to_page(table); + + BUG_ON(atomic_read(&page->pt_frag_refcount) <= 0); + if (atomic_dec_and_test(&page->pt_frag_refcount)) { + if (!kernel) + pgtable_page_dtor(page); + __free_page(page); + } +} diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c index 010e1c616cb2..1e33dccbd176 100644 --- a/arch/powerpc/mm/pgtable.c +++ b/arch/powerpc/mm/pgtable.c @@ -221,9 +221,9 @@ int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, } #ifdef CONFIG_HUGETLB_PAGE -extern int huge_ptep_set_access_flags(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep, - pte_t pte, int dirty) +int huge_ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t pte, int dirty) { #ifdef HUGETLB_NEED_PRELOAD /* diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c index bda3c6f1bd32..4fc77a99c9bf 100644 --- a/arch/powerpc/mm/pgtable_32.c +++ b/arch/powerpc/mm/pgtable_32.c @@ -45,32 +45,15 @@ extern char etext[], _stext[], _sinittext[], _einittext[]; __ref pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { - pte_t *pte; + if (!slab_is_available()) + return memblock_alloc(PTE_FRAG_SIZE, PTE_FRAG_SIZE); - if (slab_is_available()) { - pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO); - } else { - pte = __va(memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE)); - if (pte) - clear_page(pte); - } - return pte; + return (pte_t *)pte_fragment_alloc(mm, address, 1); } pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) { - struct page *ptepage; - - gfp_t flags = GFP_KERNEL | __GFP_ZERO | __GFP_ACCOUNT; - - ptepage = alloc_pages(flags, 0); - if (!ptepage) - return NULL; - if (!pgtable_page_ctor(ptepage)) { - __free_page(ptepage); - return NULL; - } - return ptepage; + return (pgtable_t)pte_fragment_alloc(mm, address, 0); } void __iomem * @@ -260,7 +243,7 @@ static void __init __mapin_ram_chunk(unsigned long offset, unsigned long top) ktext = ((char *)v >= _stext && (char *)v < etext) || ((char *)v >= _sinittext && (char *)v < _einittext); map_kernel_page(v, p, ktext ? PAGE_KERNEL_TEXT : PAGE_KERNEL); -#ifdef CONFIG_PPC_STD_MMU_32 +#ifdef CONFIG_PPC_BOOK3S_32 if (ktext) hash_preload(&init_mm, v, false, 0x300); #endif diff --git a/arch/powerpc/mm/pkeys.c b/arch/powerpc/mm/pkeys.c index b271b283c785..04b60a8f6e69 100644 --- a/arch/powerpc/mm/pkeys.c +++ b/arch/powerpc/mm/pkeys.c @@ -6,20 +6,21 @@ */ #include <asm/mman.h> +#include <asm/mmu_context.h> #include <asm/setup.h> #include <linux/pkeys.h> #include <linux/of_device.h> DEFINE_STATIC_KEY_TRUE(pkey_disabled); -bool pkey_execute_disable_supported; int pkeys_total; /* Total pkeys as per device tree */ -bool pkeys_devtree_defined; /* pkey property exported by device tree */ u32 initial_allocation_mask; /* Bits set for the initially allocated keys */ u32 reserved_allocation_mask; /* Bits set for reserved keys */ -u64 pkey_amr_mask; /* Bits in AMR not to be touched */ -u64 pkey_iamr_mask; /* Bits in AMR not to be touched */ -u64 pkey_uamor_mask; /* Bits in UMOR not to be touched */ -int execute_only_key = 2; +static bool pkey_execute_disable_supported; +static bool pkeys_devtree_defined; /* property exported by device tree */ +static u64 pkey_amr_mask; /* Bits in AMR not to be touched */ +static u64 pkey_iamr_mask; /* Bits in AMR not to be touched */ +static u64 pkey_uamor_mask; /* Bits in UMOR not to be touched */ +static int execute_only_key = 2; #define AMR_BITS_PER_PKEY 2 #define AMR_RD_BIT 0x1UL @@ -57,7 +58,7 @@ static inline bool pkey_mmu_enabled(void) return cpu_has_feature(CPU_FTR_PKEY); } -int pkey_initialize(void) +static int pkey_initialize(void) { int os_reserved, i; |