From 282c335ad1bf4d21fcedff132e19995c24c09adc Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Wed, 8 May 2024 06:21:33 +0200 Subject: Adding upstream version 4.19.304. Signed-off-by: Daniel Baumann --- arch/powerpc/mm/Makefile | 10 +- arch/powerpc/mm/dump_hashpagetable.c | 550 ------------------------ arch/powerpc/mm/dump_linuxpagetables-8xx.c | 82 ---- arch/powerpc/mm/dump_linuxpagetables-book3s64.c | 115 ----- arch/powerpc/mm/dump_linuxpagetables-generic.c | 82 ---- arch/powerpc/mm/dump_linuxpagetables.c | 373 ---------------- arch/powerpc/mm/dump_linuxpagetables.h | 19 - arch/powerpc/mm/init_64.c | 3 +- arch/powerpc/mm/pgtable-radix.c | 4 +- arch/powerpc/mm/ptdump/8xx.c | 82 ++++ arch/powerpc/mm/ptdump/Makefile | 9 + arch/powerpc/mm/ptdump/bats.c | 173 ++++++++ arch/powerpc/mm/ptdump/book3s64.c | 115 +++++ arch/powerpc/mm/ptdump/hashpagetable.c | 550 ++++++++++++++++++++++++ arch/powerpc/mm/ptdump/ptdump.c | 373 ++++++++++++++++ arch/powerpc/mm/ptdump/ptdump.h | 19 + arch/powerpc/mm/ptdump/segment_regs.c | 64 +++ arch/powerpc/mm/ptdump/shared.c | 82 ++++ 18 files changed, 1471 insertions(+), 1234 deletions(-) delete mode 100644 arch/powerpc/mm/dump_hashpagetable.c delete mode 100644 arch/powerpc/mm/dump_linuxpagetables-8xx.c delete mode 100644 arch/powerpc/mm/dump_linuxpagetables-book3s64.c delete mode 100644 arch/powerpc/mm/dump_linuxpagetables-generic.c delete mode 100644 arch/powerpc/mm/dump_linuxpagetables.c delete mode 100644 arch/powerpc/mm/dump_linuxpagetables.h create mode 100644 arch/powerpc/mm/ptdump/8xx.c create mode 100644 arch/powerpc/mm/ptdump/Makefile create mode 100644 arch/powerpc/mm/ptdump/bats.c create mode 100644 arch/powerpc/mm/ptdump/book3s64.c create mode 100644 arch/powerpc/mm/ptdump/hashpagetable.c create mode 100644 arch/powerpc/mm/ptdump/ptdump.c create mode 100644 arch/powerpc/mm/ptdump/ptdump.h create mode 100644 arch/powerpc/mm/ptdump/segment_regs.c create mode 100644 arch/powerpc/mm/ptdump/shared.c (limited to 'arch/powerpc/mm') diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile index 3c844bdd1..d4648a1e6 100644 --- a/arch/powerpc/mm/Makefile +++ b/arch/powerpc/mm/Makefile @@ -42,13 +42,5 @@ obj-$(CONFIG_NOT_COHERENT_CACHE) += dma-noncoherent.o obj-$(CONFIG_HIGHMEM) += highmem.o obj-$(CONFIG_PPC_COPRO_BASE) += copro_fault.o obj-$(CONFIG_SPAPR_TCE_IOMMU) += mmu_context_iommu.o -obj-$(CONFIG_PPC_PTDUMP) += dump_linuxpagetables.o -ifdef CONFIG_PPC_PTDUMP -obj-$(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_64) += dump_linuxpagetables-book3s64.o -endif -obj-$(CONFIG_PPC_HTDUMP) += dump_hashpagetable.o +obj-$(CONFIG_PPC_PTDUMP) += ptdump/ obj-$(CONFIG_PPC_MEM_KEYS) += pkeys.o diff --git a/arch/powerpc/mm/dump_hashpagetable.c b/arch/powerpc/mm/dump_hashpagetable.c deleted file mode 100644 index b430e4e08..000000000 --- a/arch/powerpc/mm/dump_hashpagetable.c +++ /dev/null @@ -1,550 +0,0 @@ -/* - * Copyright 2016, Rashmica Gupta, IBM Corp. - * - * This traverses the kernel virtual memory and dumps the pages that are in - * the hash pagetable, along with their flags to - * /sys/kernel/debug/kernel_hash_pagetable. - * - * If radix is enabled then there is no hash page table and so no debugfs file - * is generated. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; version 2 - * of the License. - */ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -struct pg_state { - struct seq_file *seq; - const struct addr_marker *marker; - unsigned long start_address; - unsigned int level; - u64 current_flags; -}; - -struct addr_marker { - unsigned long start_address; - const char *name; -}; - -static struct addr_marker address_markers[] = { - { 0, "Start of kernel VM" }, - { 0, "vmalloc() Area" }, - { 0, "vmalloc() End" }, - { 0, "isa I/O start" }, - { 0, "isa I/O end" }, - { 0, "phb I/O start" }, - { 0, "phb I/O end" }, - { 0, "I/O remap start" }, - { 0, "I/O remap end" }, - { 0, "vmemmap start" }, - { -1, NULL }, -}; - -struct flag_info { - u64 mask; - u64 val; - const char *set; - const char *clear; - bool is_val; - int shift; -}; - -static const struct flag_info v_flag_array[] = { - { - .mask = SLB_VSID_B, - .val = SLB_VSID_B_256M, - .set = "ssize: 256M", - .clear = "ssize: 1T ", - }, { - .mask = HPTE_V_SECONDARY, - .val = HPTE_V_SECONDARY, - .set = "secondary", - .clear = "primary ", - }, { - .mask = HPTE_V_VALID, - .val = HPTE_V_VALID, - .set = "valid ", - .clear = "invalid", - }, { - .mask = HPTE_V_BOLTED, - .val = HPTE_V_BOLTED, - .set = "bolted", - .clear = "", - } -}; - -static const struct flag_info r_flag_array[] = { - { - .mask = HPTE_R_PP0 | HPTE_R_PP, - .val = PP_RWXX, - .set = "prot:RW--", - }, { - .mask = HPTE_R_PP0 | HPTE_R_PP, - .val = PP_RWRX, - .set = "prot:RWR-", - }, { - .mask = HPTE_R_PP0 | HPTE_R_PP, - .val = PP_RWRW, - .set = "prot:RWRW", - }, { - .mask = HPTE_R_PP0 | HPTE_R_PP, - .val = PP_RXRX, - .set = "prot:R-R-", - }, { - .mask = HPTE_R_PP0 | HPTE_R_PP, - .val = PP_RXXX, - .set = "prot:R---", - }, { - .mask = HPTE_R_KEY_HI | HPTE_R_KEY_LO, - .val = HPTE_R_KEY_HI | HPTE_R_KEY_LO, - .set = "key", - .clear = "", - .is_val = true, - }, { - .mask = HPTE_R_R, - .val = HPTE_R_R, - .set = "ref", - .clear = " ", - }, { - .mask = HPTE_R_C, - .val = HPTE_R_C, - .set = "changed", - .clear = " ", - }, { - .mask = HPTE_R_N, - .val = HPTE_R_N, - .set = "no execute", - }, { - .mask = HPTE_R_WIMG, - .val = HPTE_R_W, - .set = "writethru", - }, { - .mask = HPTE_R_WIMG, - .val = HPTE_R_I, - .set = "no cache", - }, { - .mask = HPTE_R_WIMG, - .val = HPTE_R_G, - .set = "guarded", - } -}; - -static int calculate_pagesize(struct pg_state *st, int ps, char s[]) -{ - static const char units[] = "BKMGTPE"; - const char *unit = units; - - while (ps > 9 && unit[1]) { - ps -= 10; - unit++; - } - seq_printf(st->seq, " %s_ps: %i%c\t", s, 1<mask == 0) - continue; - /* Some 'flags' are actually values */ - if (flag->is_val) { - val = pte & flag->val; - if (flag->shift) - val = val >> flag->shift; - seq_printf(st->seq, " %s:%llx", flag->set, val); - } else { - if ((pte & flag->mask) == flag->val) - s = flag->set; - else - s = flag->clear; - if (s) - seq_printf(st->seq, " %s", s); - } - } -} - -static void dump_hpte_info(struct pg_state *st, unsigned long ea, u64 v, u64 r, - unsigned long rpn, int bps, int aps, unsigned long lp) -{ - int aps_index; - - while (ea >= st->marker[1].start_address) { - st->marker++; - seq_printf(st->seq, "---[ %s ]---\n", st->marker->name); - } - seq_printf(st->seq, "0x%lx:\t", ea); - seq_printf(st->seq, "AVPN:%llx\t", HPTE_V_AVPN_VAL(v)); - dump_flag_info(st, v_flag_array, v, ARRAY_SIZE(v_flag_array)); - seq_printf(st->seq, " rpn: %lx\t", rpn); - dump_flag_info(st, r_flag_array, r, ARRAY_SIZE(r_flag_array)); - - calculate_pagesize(st, bps, "base"); - aps_index = calculate_pagesize(st, aps, "actual"); - if (aps_index != 2) - seq_printf(st->seq, "LP enc: %lx", lp); - seq_putc(st->seq, '\n'); -} - - -static int native_find(unsigned long ea, int psize, bool primary, u64 *v, u64 - *r) -{ - struct hash_pte *hptep; - unsigned long hash, vsid, vpn, hpte_group, want_v, hpte_v; - int i, ssize = mmu_kernel_ssize; - unsigned long shift = mmu_psize_defs[psize].shift; - - /* calculate hash */ - vsid = get_kernel_vsid(ea, ssize); - vpn = hpt_vpn(ea, vsid, ssize); - hash = hpt_hash(vpn, shift, ssize); - want_v = hpte_encode_avpn(vpn, psize, ssize); - - /* to check in the secondary hash table, we invert the hash */ - if (!primary) - hash = ~hash; - hpte_group = (hash & htab_hash_mask) * HPTES_PER_GROUP; - for (i = 0; i < HPTES_PER_GROUP; i++) { - hptep = htab_address + hpte_group; - hpte_v = be64_to_cpu(hptep->v); - - if (HPTE_V_COMPARE(hpte_v, want_v) && (hpte_v & HPTE_V_VALID)) { - /* HPTE matches */ - *v = be64_to_cpu(hptep->v); - *r = be64_to_cpu(hptep->r); - return 0; - } - ++hpte_group; - } - return -1; -} - -#ifdef CONFIG_PPC_PSERIES -static int pseries_find(unsigned long ea, int psize, bool primary, u64 *v, u64 *r) -{ - struct hash_pte ptes[4]; - unsigned long vsid, vpn, hash, hpte_group, want_v; - int i, j, ssize = mmu_kernel_ssize; - long lpar_rc = 0; - unsigned long shift = mmu_psize_defs[psize].shift; - - /* calculate hash */ - vsid = get_kernel_vsid(ea, ssize); - vpn = hpt_vpn(ea, vsid, ssize); - hash = hpt_hash(vpn, shift, ssize); - want_v = hpte_encode_avpn(vpn, psize, ssize); - - /* to check in the secondary hash table, we invert the hash */ - if (!primary) - hash = ~hash; - hpte_group = (hash & htab_hash_mask) * HPTES_PER_GROUP; - /* see if we can find an entry in the hpte with this hash */ - for (i = 0; i < HPTES_PER_GROUP; i += 4, hpte_group += 4) { - lpar_rc = plpar_pte_read_4(0, hpte_group, (void *)ptes); - - if (lpar_rc != H_SUCCESS) - continue; - for (j = 0; j < 4; j++) { - if (HPTE_V_COMPARE(ptes[j].v, want_v) && - (ptes[j].v & HPTE_V_VALID)) { - /* HPTE matches */ - *v = ptes[j].v; - *r = ptes[j].r; - return 0; - } - } - } - return -1; -} -#endif - -static void decode_r(int bps, unsigned long r, unsigned long *rpn, int *aps, - unsigned long *lp_bits) -{ - struct mmu_psize_def entry; - unsigned long arpn, mask, lp; - int penc = -2, idx = 0, shift; - - /*. - * The LP field has 8 bits. Depending on the actual page size, some of - * these bits are concatenated with the APRN to get the RPN. The rest - * of the bits in the LP field is the LP value and is an encoding for - * the base page size and the actual page size. - * - * - find the mmu entry for our base page size - * - go through all page encodings and use the associated mask to - * find an encoding that matches our encoding in the LP field. - */ - arpn = (r & HPTE_R_RPN) >> HPTE_R_RPN_SHIFT; - lp = arpn & 0xff; - - entry = mmu_psize_defs[bps]; - while (idx < MMU_PAGE_COUNT) { - penc = entry.penc[idx]; - if ((penc != -1) && (mmu_psize_defs[idx].shift)) { - shift = mmu_psize_defs[idx].shift - HPTE_R_RPN_SHIFT; - mask = (0x1 << (shift)) - 1; - if ((lp & mask) == penc) { - *aps = mmu_psize_to_shift(idx); - *lp_bits = lp & mask; - *rpn = arpn >> shift; - return; - } - } - idx++; - } -} - -static int base_hpte_find(unsigned long ea, int psize, bool primary, u64 *v, - u64 *r) -{ -#ifdef CONFIG_PPC_PSERIES - if (firmware_has_feature(FW_FEATURE_LPAR)) - return pseries_find(ea, psize, primary, v, r); -#endif - return native_find(ea, psize, primary, v, r); -} - -static unsigned long hpte_find(struct pg_state *st, unsigned long ea, int psize) -{ - unsigned long slot; - u64 v = 0, r = 0; - unsigned long rpn, lp_bits; - int base_psize = 0, actual_psize = 0; - - if (ea < PAGE_OFFSET) - return -1; - - /* Look in primary table */ - slot = base_hpte_find(ea, psize, true, &v, &r); - - /* Look in secondary table */ - if (slot == -1) - slot = base_hpte_find(ea, psize, false, &v, &r); - - /* No entry found */ - if (slot == -1) - return -1; - - /* - * We found an entry in the hash page table: - * - check that this has the same base page - * - find the actual page size - * - find the RPN - */ - base_psize = mmu_psize_to_shift(psize); - - if ((v & HPTE_V_LARGE) == HPTE_V_LARGE) { - decode_r(psize, r, &rpn, &actual_psize, &lp_bits); - } else { - /* 4K actual page size */ - actual_psize = 12; - rpn = (r & HPTE_R_RPN) >> HPTE_R_RPN_SHIFT; - /* In this case there are no LP bits */ - lp_bits = -1; - } - /* - * We didn't find a matching encoding, so the PTE we found isn't for - * this address. - */ - if (actual_psize == -1) - return -1; - - dump_hpte_info(st, ea, v, r, rpn, base_psize, actual_psize, lp_bits); - return 0; -} - -static void walk_pte(struct pg_state *st, pmd_t *pmd, unsigned long start) -{ - pte_t *pte = pte_offset_kernel(pmd, 0); - unsigned long addr, pteval, psize; - int i, status; - - for (i = 0; i < PTRS_PER_PTE; i++, pte++) { - addr = start + i * PAGE_SIZE; - pteval = pte_val(*pte); - - if (addr < VMALLOC_END) - psize = mmu_vmalloc_psize; - else - psize = mmu_io_psize; -#ifdef CONFIG_PPC_64K_PAGES - /* check for secret 4K mappings */ - if (((pteval & H_PAGE_COMBO) == H_PAGE_COMBO) || - ((pteval & H_PAGE_4K_PFN) == H_PAGE_4K_PFN)) - psize = mmu_io_psize; -#endif - /* check for hashpte */ - status = hpte_find(st, addr, psize); - - if (((pteval & H_PAGE_HASHPTE) != H_PAGE_HASHPTE) - && (status != -1)) { - /* found a hpte that is not in the linux page tables */ - seq_printf(st->seq, "page probably bolted before linux" - " pagetables were set: addr:%lx, pteval:%lx\n", - addr, pteval); - } - } -} - -static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start) -{ - pmd_t *pmd = pmd_offset(pud, 0); - unsigned long addr; - unsigned int i; - - for (i = 0; i < PTRS_PER_PMD; i++, pmd++) { - addr = start + i * PMD_SIZE; - if (!pmd_none(*pmd)) - /* pmd exists */ - walk_pte(st, pmd, addr); - } -} - -static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start) -{ - pud_t *pud = pud_offset(pgd, 0); - unsigned long addr; - unsigned int i; - - for (i = 0; i < PTRS_PER_PUD; i++, pud++) { - addr = start + i * PUD_SIZE; - if (!pud_none(*pud)) - /* pud exists */ - walk_pmd(st, pud, addr); - } -} - -static void walk_pagetables(struct pg_state *st) -{ - pgd_t *pgd = pgd_offset_k(0UL); - unsigned int i; - unsigned long addr; - - /* - * Traverse the linux pagetable structure and dump pages that are in - * the hash pagetable. - */ - for (i = 0; i < PTRS_PER_PGD; i++, pgd++) { - addr = KERN_VIRT_START + i * PGDIR_SIZE; - if (!pgd_none(*pgd)) - /* pgd exists */ - walk_pud(st, pgd, addr); - } -} - - -static void walk_linearmapping(struct pg_state *st) -{ - unsigned long addr; - - /* - * Traverse the linear mapping section of virtual memory and dump pages - * that are in the hash pagetable. - */ - unsigned long psize = 1 << mmu_psize_defs[mmu_linear_psize].shift; - - for (addr = PAGE_OFFSET; addr < PAGE_OFFSET + - memblock_end_of_DRAM(); addr += psize) - hpte_find(st, addr, mmu_linear_psize); -} - -static void walk_vmemmap(struct pg_state *st) -{ -#ifdef CONFIG_SPARSEMEM_VMEMMAP - struct vmemmap_backing *ptr = vmemmap_list; - - /* - * Traverse the vmemmaped memory and dump pages that are in the hash - * pagetable. - */ - while (ptr->list) { - hpte_find(st, ptr->virt_addr, mmu_vmemmap_psize); - ptr = ptr->list; - } - seq_puts(st->seq, "---[ vmemmap end ]---\n"); -#endif -} - -static void populate_markers(void) -{ - address_markers[0].start_address = PAGE_OFFSET; - address_markers[1].start_address = VMALLOC_START; - address_markers[2].start_address = VMALLOC_END; - address_markers[3].start_address = ISA_IO_BASE; - address_markers[4].start_address = ISA_IO_END; - address_markers[5].start_address = PHB_IO_BASE; - address_markers[6].start_address = PHB_IO_END; - address_markers[7].start_address = IOREMAP_BASE; - address_markers[8].start_address = IOREMAP_END; -#ifdef CONFIG_PPC_BOOK3S_64 - address_markers[9].start_address = H_VMEMMAP_BASE; -#else - address_markers[9].start_address = VMEMMAP_BASE; -#endif -} - -static int ptdump_show(struct seq_file *m, void *v) -{ - struct pg_state st = { - .seq = m, - .start_address = PAGE_OFFSET, - .marker = address_markers, - }; - /* - * Traverse the 0xc, 0xd and 0xf areas of the kernel virtual memory and - * dump pages that are in the hash pagetable. - */ - walk_linearmapping(&st); - walk_pagetables(&st); - walk_vmemmap(&st); - return 0; -} - -static int ptdump_open(struct inode *inode, struct file *file) -{ - return single_open(file, ptdump_show, NULL); -} - -static const struct file_operations ptdump_fops = { - .open = ptdump_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - -static int ptdump_init(void) -{ - struct dentry *debugfs_file; - - if (!radix_enabled()) { - populate_markers(); - debugfs_file = debugfs_create_file("kernel_hash_pagetable", - 0400, NULL, NULL, &ptdump_fops); - return debugfs_file ? 0 : -ENOMEM; - } - return 0; -} -device_initcall(ptdump_init); diff --git a/arch/powerpc/mm/dump_linuxpagetables-8xx.c b/arch/powerpc/mm/dump_linuxpagetables-8xx.c deleted file mode 100644 index 33f52a979..000000000 --- a/arch/powerpc/mm/dump_linuxpagetables-8xx.c +++ /dev/null @@ -1,82 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * From split of dump_linuxpagetables.c - * Copyright 2016, Rashmica Gupta, IBM Corp. - * - */ -#include -#include - -#include "dump_linuxpagetables.h" - -static const struct flag_info flag_array[] = { - { - .mask = _PAGE_PRIVILEGED, - .val = 0, - .set = "user", - .clear = " ", - }, { - .mask = _PAGE_RO | _PAGE_NA, - .val = 0, - .set = "rw", - }, { - .mask = _PAGE_RO | _PAGE_NA, - .val = _PAGE_RO, - .set = "r ", - }, { - .mask = _PAGE_RO | _PAGE_NA, - .val = _PAGE_NA, - .set = " ", - }, { - .mask = _PAGE_EXEC, - .val = _PAGE_EXEC, - .set = " X ", - .clear = " ", - }, { - .mask = _PAGE_PRESENT, - .val = _PAGE_PRESENT, - .set = "present", - .clear = " ", - }, { - .mask = _PAGE_GUARDED, - .val = _PAGE_GUARDED, - .set = "guarded", - .clear = " ", - }, { - .mask = _PAGE_DIRTY, - .val = _PAGE_DIRTY, - .set = "dirty", - .clear = " ", - }, { - .mask = _PAGE_ACCESSED, - .val = _PAGE_ACCESSED, - .set = "accessed", - .clear = " ", - }, { - .mask = _PAGE_NO_CACHE, - .val = _PAGE_NO_CACHE, - .set = "no cache", - .clear = " ", - }, { - .mask = _PAGE_SPECIAL, - .val = _PAGE_SPECIAL, - .set = "special", - } -}; - -struct pgtable_level pg_level[5] = { - { - }, { /* pgd */ - .flag = flag_array, - .num = ARRAY_SIZE(flag_array), - }, { /* pud */ - .flag = flag_array, - .num = ARRAY_SIZE(flag_array), - }, { /* pmd */ - .flag = flag_array, - .num = ARRAY_SIZE(flag_array), - }, { /* pte */ - .flag = flag_array, - .num = ARRAY_SIZE(flag_array), - }, -}; diff --git a/arch/powerpc/mm/dump_linuxpagetables-book3s64.c b/arch/powerpc/mm/dump_linuxpagetables-book3s64.c deleted file mode 100644 index a637e612b..000000000 --- a/arch/powerpc/mm/dump_linuxpagetables-book3s64.c +++ /dev/null @@ -1,115 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * From split of dump_linuxpagetables.c - * Copyright 2016, Rashmica Gupta, IBM Corp. - * - */ -#include -#include - -#include "dump_linuxpagetables.h" - -static const struct flag_info flag_array[] = { - { - .mask = _PAGE_PRIVILEGED, - .val = 0, - .set = "user", - .clear = " ", - }, { - .mask = _PAGE_READ, - .val = _PAGE_READ, - .set = "r", - .clear = " ", - }, { - .mask = _PAGE_WRITE, - .val = _PAGE_WRITE, - .set = "w", - .clear = " ", - }, { - .mask = _PAGE_EXEC, - .val = _PAGE_EXEC, - .set = " X ", - .clear = " ", - }, { - .mask = _PAGE_PTE, - .val = _PAGE_PTE, - .set = "pte", - .clear = " ", - }, { - .mask = _PAGE_PRESENT, - .val = _PAGE_PRESENT, - .set = "present", - .clear = " ", - }, { - .mask = H_PAGE_HASHPTE, - .val = H_PAGE_HASHPTE, - .set = "hpte", - .clear = " ", - }, { - .mask = _PAGE_DIRTY, - .val = _PAGE_DIRTY, - .set = "dirty", - .clear = " ", - }, { - .mask = _PAGE_ACCESSED, - .val = _PAGE_ACCESSED, - .set = "accessed", - .clear = " ", - }, { - .mask = _PAGE_NON_IDEMPOTENT, - .val = _PAGE_NON_IDEMPOTENT, - .set = "non-idempotent", - .clear = " ", - }, { - .mask = _PAGE_TOLERANT, - .val = _PAGE_TOLERANT, - .set = "tolerant", - .clear = " ", - }, { - .mask = H_PAGE_BUSY, - .val = H_PAGE_BUSY, - .set = "busy", - }, { -#ifdef CONFIG_PPC_64K_PAGES - .mask = H_PAGE_COMBO, - .val = H_PAGE_COMBO, - .set = "combo", - }, { - .mask = H_PAGE_4K_PFN, - .val = H_PAGE_4K_PFN, - .set = "4K_pfn", - }, { -#else /* CONFIG_PPC_64K_PAGES */ - .mask = H_PAGE_F_GIX, - .val = H_PAGE_F_GIX, - .set = "f_gix", - .is_val = true, - .shift = H_PAGE_F_GIX_SHIFT, - }, { - .mask = H_PAGE_F_SECOND, - .val = H_PAGE_F_SECOND, - .set = "f_second", - }, { -#endif /* CONFIG_PPC_64K_PAGES */ - .mask = _PAGE_SPECIAL, - .val = _PAGE_SPECIAL, - .set = "special", - } -}; - -struct pgtable_level pg_level[5] = { - { - }, { /* pgd */ - .flag = flag_array, - .num = ARRAY_SIZE(flag_array), - }, { /* pud */ - .flag = flag_array, - .num = ARRAY_SIZE(flag_array), - }, { /* pmd */ - .flag = flag_array, - .num = ARRAY_SIZE(flag_array), - }, { /* pte */ - .flag = flag_array, - .num = ARRAY_SIZE(flag_array), - }, -}; diff --git a/arch/powerpc/mm/dump_linuxpagetables-generic.c b/arch/powerpc/mm/dump_linuxpagetables-generic.c deleted file mode 100644 index fed6923bc..000000000 --- a/arch/powerpc/mm/dump_linuxpagetables-generic.c +++ /dev/null @@ -1,82 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * From split of dump_linuxpagetables.c - * Copyright 2016, Rashmica Gupta, IBM Corp. - * - */ -#include -#include - -#include "dump_linuxpagetables.h" - -static const struct flag_info flag_array[] = { - { - .mask = _PAGE_USER, - .val = _PAGE_USER, - .set = "user", - .clear = " ", - }, { - .mask = _PAGE_RW, - .val = 0, - .set = "r ", - .clear = "rw", - }, { -#ifndef CONFIG_PPC_BOOK3S_32 - .mask = _PAGE_EXEC, - .val = _PAGE_EXEC, - .set = " X ", - .clear = " ", - }, { -#endif - .mask = _PAGE_PRESENT, - .val = _PAGE_PRESENT, - .set = "present", - .clear = " ", - }, { - .mask = _PAGE_GUARDED, - .val = _PAGE_GUARDED, - .set = "guarded", - .clear = " ", - }, { - .mask = _PAGE_DIRTY, - .val = _PAGE_DIRTY, - .set = "dirty", - .clear = " ", - }, { - .mask = _PAGE_ACCESSED, - .val = _PAGE_ACCESSED, - .set = "accessed", - .clear = " ", - }, { - .mask = _PAGE_WRITETHRU, - .val = _PAGE_WRITETHRU, - .set = "write through", - .clear = " ", - }, { - .mask = _PAGE_NO_CACHE, - .val = _PAGE_NO_CACHE, - .set = "no cache", - .clear = " ", - }, { - .mask = _PAGE_SPECIAL, - .val = _PAGE_SPECIAL, - .set = "special", - } -}; - -struct pgtable_level pg_level[5] = { - { - }, { /* pgd */ - .flag = flag_array, - .num = ARRAY_SIZE(flag_array), - }, { /* pud */ - .flag = flag_array, - .num = ARRAY_SIZE(flag_array), - }, { /* pmd */ - .flag = flag_array, - .num = ARRAY_SIZE(flag_array), - }, { /* pte */ - .flag = flag_array, - .num = ARRAY_SIZE(flag_array), - }, -}; diff --git a/arch/powerpc/mm/dump_linuxpagetables.c b/arch/powerpc/mm/dump_linuxpagetables.c deleted file mode 100644 index 6aa41669a..000000000 --- a/arch/powerpc/mm/dump_linuxpagetables.c +++ /dev/null @@ -1,373 +0,0 @@ -/* - * Copyright 2016, Rashmica Gupta, IBM Corp. - * - * This traverses the kernel pagetables and dumps the - * information about the used sections of memory to - * /sys/kernel/debug/kernel_pagetables. - * - * Derived from the arm64 implementation: - * Copyright (c) 2014, The Linux Foundation, Laura Abbott. - * (C) Copyright 2008 Intel Corporation, Arjan van de Ven. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; version 2 - * of the License. - */ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "dump_linuxpagetables.h" - -#ifdef CONFIG_PPC32 -#define KERN_VIRT_START 0 -#endif - -/* - * To visualise what is happening, - * - * - PTRS_PER_P** = how many entries there are in the corresponding P** - * - P**_SHIFT = how many bits of the address we use to index into the - * corresponding P** - * - P**_SIZE is how much memory we can access through the table - not the - * size of the table itself. - * P**={PGD, PUD, PMD, PTE} - * - * - * Each entry of the PGD points to a PUD. Each entry of a PUD points to a - * PMD. Each entry of a PMD points to a PTE. And every PTE entry points to - * a page. - * - * In the case where there are only 3 levels, the PUD is folded into the - * PGD: every PUD has only one entry which points to the PMD. - * - * The page dumper groups page table entries of the same type into a single - * description. It uses pg_state to track the range information while - * iterating over the PTE entries. When the continuity is broken it then - * dumps out a description of the range - ie PTEs that are virtually contiguous - * with the same PTE flags are chunked together. This is to make it clear how - * different areas of the kernel virtual memory are used. - * - */ -struct pg_state { - struct seq_file *seq; - const struct addr_marker *marker; - unsigned long start_address; - unsigned long start_pa; - unsigned long last_pa; - unsigned int level; - u64 current_flags; -}; - -struct addr_marker { - unsigned long start_address; - const char *name; -}; - -static struct addr_marker address_markers[] = { - { 0, "Start of kernel VM" }, - { 0, "vmalloc() Area" }, - { 0, "vmalloc() End" }, -#ifdef CONFIG_PPC64 - { 0, "isa I/O start" }, - { 0, "isa I/O end" }, - { 0, "phb I/O start" }, - { 0, "phb I/O end" }, - { 0, "I/O remap start" }, - { 0, "I/O remap end" }, - { 0, "vmemmap start" }, -#else - { 0, "Early I/O remap start" }, - { 0, "Early I/O remap end" }, -#ifdef CONFIG_NOT_COHERENT_CACHE - { 0, "Consistent mem start" }, - { 0, "Consistent mem end" }, -#endif -#ifdef CONFIG_HIGHMEM - { 0, "Highmem PTEs start" }, - { 0, "Highmem PTEs end" }, -#endif - { 0, "Fixmap start" }, - { 0, "Fixmap end" }, -#endif - { -1, NULL }, -}; - -static void dump_flag_info(struct pg_state *st, const struct flag_info - *flag, u64 pte, int num) -{ - unsigned int i; - - for (i = 0; i < num; i++, flag++) { - const char *s = NULL; - u64 val; - - /* flag not defined so don't check it */ - if (flag->mask == 0) - continue; - /* Some 'flags' are actually values */ - if (flag->is_val) { - val = pte & flag->val; - if (flag->shift) - val = val >> flag->shift; - seq_printf(st->seq, " %s:%llx", flag->set, val); - } else { - if ((pte & flag->mask) == flag->val) - s = flag->set; - else - s = flag->clear; - if (s) - seq_printf(st->seq, " %s", s); - } - st->current_flags &= ~flag->mask; - } - if (st->current_flags != 0) - seq_printf(st->seq, " unknown flags:%llx", st->current_flags); -} - -static void dump_addr(struct pg_state *st, unsigned long addr) -{ - static const char units[] = "KMGTPE"; - const char *unit = units; - unsigned long delta; - -#ifdef CONFIG_PPC64 - seq_printf(st->seq, "0x%016lx-0x%016lx ", st->start_address, addr-1); - seq_printf(st->seq, "0x%016lx ", st->start_pa); -#else - seq_printf(st->seq, "0x%08lx-0x%08lx ", st->start_address, addr - 1); - seq_printf(st->seq, "0x%08lx ", st->start_pa); -#endif - - delta = (addr - st->start_address) >> 10; - /* Work out what appropriate unit to use */ - while (!(delta & 1023) && unit[1]) { - delta >>= 10; - unit++; - } - seq_printf(st->seq, "%9lu%c", delta, *unit); - -} - -static void note_page(struct pg_state *st, unsigned long addr, - unsigned int level, u64 val) -{ - u64 flag = val & pg_level[level].mask; - u64 pa = val & PTE_RPN_MASK; - - /* At first no level is set */ - if (!st->level) { - st->level = level; - st->current_flags = flag; - st->start_address = addr; - st->start_pa = pa; - st->last_pa = pa; - seq_printf(st->seq, "---[ %s ]---\n", st->marker->name); - /* - * Dump the section of virtual memory when: - * - the PTE flags from one entry to the next differs. - * - we change levels in the tree. - * - the address is in a different section of memory and is thus - * used for a different purpose, regardless of the flags. - * - the pa of this page is not adjacent to the last inspected page - */ - } else if (flag != st->current_flags || level != st->level || - addr >= st->marker[1].start_address || - pa != st->last_pa + PAGE_SIZE) { - - /* Check the PTE flags */ - if (st->current_flags) { - dump_addr(st, addr); - - /* Dump all the flags */ - if (pg_level[st->level].flag) - dump_flag_info(st, pg_level[st->level].flag, - st->current_flags, - pg_level[st->level].num); - - seq_putc(st->seq, '\n'); - } - - /* - * Address indicates we have passed the end of the - * current section of virtual memory - */ - while (addr >= st->marker[1].start_address) { - st->marker++; - seq_printf(st->seq, "---[ %s ]---\n", st->marker->name); - } - st->start_address = addr; - st->start_pa = pa; - st->last_pa = pa; - st->current_flags = flag; - st->level = level; - } else { - st->last_pa = pa; - } -} - -static void walk_pte(struct pg_state *st, pmd_t *pmd, unsigned long start) -{ - pte_t *pte = pte_offset_kernel(pmd, 0); - unsigned long addr; - unsigned int i; - - for (i = 0; i < PTRS_PER_PTE; i++, pte++) { - addr = start + i * PAGE_SIZE; - note_page(st, addr, 4, pte_val(*pte)); - - } -} - -static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start) -{ - pmd_t *pmd = pmd_offset(pud, 0); - unsigned long addr; - unsigned int i; - - for (i = 0; i < PTRS_PER_PMD; i++, pmd++) { - addr = start + i * PMD_SIZE; - if (!pmd_none(*pmd) && !pmd_huge(*pmd)) - /* pmd exists */ - walk_pte(st, pmd, addr); - else - note_page(st, addr, 3, pmd_val(*pmd)); - } -} - -static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start) -{ - pud_t *pud = pud_offset(pgd, 0); - unsigned long addr; - unsigned int i; - - for (i = 0; i < PTRS_PER_PUD; i++, pud++) { - addr = start + i * PUD_SIZE; - if (!pud_none(*pud) && !pud_huge(*pud)) - /* pud exists */ - walk_pmd(st, pud, addr); - else - note_page(st, addr, 2, pud_val(*pud)); - } -} - -static void walk_pagetables(struct pg_state *st) -{ - pgd_t *pgd = pgd_offset_k(0UL); - unsigned int i; - unsigned long addr; - - addr = st->start_address; - - /* - * Traverse the linux pagetable structure and dump pages that are in - * the hash pagetable. - */ - for (i = 0; i < PTRS_PER_PGD; i++, pgd++, addr += PGDIR_SIZE) { - if (!pgd_none(*pgd) && !pgd_huge(*pgd)) - /* pgd exists */ - walk_pud(st, pgd, addr); - else - note_page(st, addr, 1, pgd_val(*pgd)); - } -} - -static void populate_markers(void) -{ - int i = 0; - - address_markers[i++].start_address = PAGE_OFFSET; - address_markers[i++].start_address = VMALLOC_START; - address_markers[i++].start_address = VMALLOC_END; -#ifdef CONFIG_PPC64 - address_markers[i++].start_address = ISA_IO_BASE; - address_markers[i++].start_address = ISA_IO_END; - address_markers[i++].start_address = PHB_IO_BASE; - address_markers[i++].start_address = PHB_IO_END; - address_markers[i++].start_address = IOREMAP_BASE; - address_markers[i++].start_address = IOREMAP_END; -#ifdef CONFIG_PPC_BOOK3S_64 - address_markers[i++].start_address = H_VMEMMAP_BASE; -#else - address_markers[i++].start_address = VMEMMAP_BASE; -#endif -#else /* !CONFIG_PPC64 */ - address_markers[i++].start_address = ioremap_bot; - address_markers[i++].start_address = IOREMAP_TOP; -#ifdef CONFIG_NOT_COHERENT_CACHE - address_markers[i++].start_address = IOREMAP_TOP; - address_markers[i++].start_address = IOREMAP_TOP + - CONFIG_CONSISTENT_SIZE; -#endif -#ifdef CONFIG_HIGHMEM - address_markers[i++].start_address = PKMAP_BASE; - address_markers[i++].start_address = PKMAP_ADDR(LAST_PKMAP); -#endif - address_markers[i++].start_address = FIXADDR_START; - address_markers[i++].start_address = FIXADDR_TOP; -#endif /* CONFIG_PPC64 */ -} - -static int ptdump_show(struct seq_file *m, void *v) -{ - struct pg_state st = { - .seq = m, - .marker = address_markers, - }; - - if (radix_enabled()) - st.start_address = PAGE_OFFSET; - else - st.start_address = KERN_VIRT_START; - - /* Traverse kernel page tables */ - walk_pagetables(&st); - note_page(&st, 0, 0, 0); - return 0; -} - - -static int ptdump_open(struct inode *inode, struct file *file) -{ - return single_open(file, ptdump_show, NULL); -} - -static const struct file_operations ptdump_fops = { - .open = ptdump_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - -static void build_pgtable_complete_mask(void) -{ - unsigned int i, j; - - for (i = 0; i < ARRAY_SIZE(pg_level); i++) - if (pg_level[i].flag) - for (j = 0; j < pg_level[i].num; j++) - pg_level[i].mask |= pg_level[i].flag[j].mask; -} - -static int ptdump_init(void) -{ - struct dentry *debugfs_file; - - populate_markers(); - build_pgtable_complete_mask(); - debugfs_file = debugfs_create_file("kernel_page_tables", 0400, NULL, - NULL, &ptdump_fops); - return debugfs_file ? 0 : -ENOMEM; -} -device_initcall(ptdump_init); diff --git a/arch/powerpc/mm/dump_linuxpagetables.h b/arch/powerpc/mm/dump_linuxpagetables.h deleted file mode 100644 index 5d513636d..000000000 --- a/arch/powerpc/mm/dump_linuxpagetables.h +++ /dev/null @@ -1,19 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#include - -struct flag_info { - u64 mask; - u64 val; - const char *set; - const char *clear; - bool is_val; - int shift; -}; - -struct pgtable_level { - const struct flag_info *flag; - size_t num; - u64 mask; -}; - -extern struct pgtable_level pg_level[5]; diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index a5091c034..aff86679a 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -266,8 +266,7 @@ void __ref vmemmap_free(unsigned long start, unsigned long end, start = _ALIGN_DOWN(start, page_size); if (altmap) { alt_start = altmap->base_pfn; - alt_end = altmap->base_pfn + altmap->reserve + - altmap->free + altmap->alloc + altmap->align; + alt_end = altmap->base_pfn + altmap->reserve + altmap->free; } pr_debug("vmemmap_free %lx...%lx\n", start, end); diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index 9ee235fca..75cbedaac 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -1041,8 +1041,8 @@ void radix__ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep, pte_t entry, unsigned long address, int psize) { struct mm_struct *mm = vma->vm_mm; - unsigned long set = pte_val(entry) & (_PAGE_DIRTY | _PAGE_ACCESSED | - _PAGE_RW | _PAGE_EXEC); + unsigned long set = pte_val(entry) & (_PAGE_DIRTY | _PAGE_SOFT_DIRTY | + _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC); unsigned long change = pte_val(entry) ^ pte_val(*ptep); /* diff --git a/arch/powerpc/mm/ptdump/8xx.c b/arch/powerpc/mm/ptdump/8xx.c new file mode 100644 index 000000000..80b4f73f7 --- /dev/null +++ b/arch/powerpc/mm/ptdump/8xx.c @@ -0,0 +1,82 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * From split of dump_linuxpagetables.c + * Copyright 2016, Rashmica Gupta, IBM Corp. + * + */ +#include +#include + +#include "ptdump.h" + +static const struct flag_info flag_array[] = { + { + .mask = _PAGE_PRIVILEGED, + .val = 0, + .set = "user", + .clear = " ", + }, { + .mask = _PAGE_RO | _PAGE_NA, + .val = 0, + .set = "rw", + }, { + .mask = _PAGE_RO | _PAGE_NA, + .val = _PAGE_RO, + .set = "r ", + }, { + .mask = _PAGE_RO | _PAGE_NA, + .val = _PAGE_NA, + .set = " ", + }, { + .mask = _PAGE_EXEC, + .val = _PAGE_EXEC, + .set = " X ", + .clear = " ", + }, { + .mask = _PAGE_PRESENT, + .val = _PAGE_PRESENT, + .set = "present", + .clear = " ", + }, { + .mask = _PAGE_GUARDED, + .val = _PAGE_GUARDED, + .set = "guarded", + .clear = " ", + }, { + .mask = _PAGE_DIRTY, + .val = _PAGE_DIRTY, + .set = "dirty", + .clear = " ", + }, { + .mask = _PAGE_ACCESSED, + .val = _PAGE_ACCESSED, + .set = "accessed", + .clear = " ", + }, { + .mask = _PAGE_NO_CACHE, + .val = _PAGE_NO_CACHE, + .set = "no cache", + .clear = " ", + }, { + .mask = _PAGE_SPECIAL, + .val = _PAGE_SPECIAL, + .set = "special", + } +}; + +struct pgtable_level pg_level[5] = { + { + }, { /* pgd */ + .flag = flag_array, + .num = ARRAY_SIZE(flag_array), + }, { /* pud */ + .flag = flag_array, + .num = ARRAY_SIZE(flag_array), + }, { /* pmd */ + .flag = flag_array, + .num = ARRAY_SIZE(flag_array), + }, { /* pte */ + .flag = flag_array, + .num = ARRAY_SIZE(flag_array), + }, +}; diff --git a/arch/powerpc/mm/ptdump/Makefile b/arch/powerpc/mm/ptdump/Makefile new file mode 100644 index 000000000..712762be3 --- /dev/null +++ b/arch/powerpc/mm/ptdump/Makefile @@ -0,0 +1,9 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-y += ptdump.o + +obj-$(CONFIG_4xx) += shared.o +obj-$(CONFIG_PPC_8xx) += 8xx.o +obj-$(CONFIG_PPC_BOOK3E_MMU) += shared.o +obj-$(CONFIG_PPC_BOOK3S_32) += shared.o bats.o segment_regs.o +obj-$(CONFIG_PPC_BOOK3S_64) += book3s64.o hashpagetable.o diff --git a/arch/powerpc/mm/ptdump/bats.c b/arch/powerpc/mm/ptdump/bats.c new file mode 100644 index 000000000..a0d23e96e --- /dev/null +++ b/arch/powerpc/mm/ptdump/bats.c @@ -0,0 +1,173 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright 2018, Christophe Leroy CS S.I. + * + * + * This dumps the content of BATS + */ + +#include +#include +#include + +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/ptdump/book3s64.c b/arch/powerpc/mm/ptdump/book3s64.c new file mode 100644 index 000000000..0bce5b85d --- /dev/null +++ b/arch/powerpc/mm/ptdump/book3s64.c @@ -0,0 +1,115 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * From split of dump_linuxpagetables.c + * Copyright 2016, Rashmica Gupta, IBM Corp. + * + */ +#include +#include + +#include "ptdump.h" + +static const struct flag_info flag_array[] = { + { + .mask = _PAGE_PRIVILEGED, + .val = 0, + .set = "user", + .clear = " ", + }, { + .mask = _PAGE_READ, + .val = _PAGE_READ, + .set = "r", + .clear = " ", + }, { + .mask = _PAGE_WRITE, + .val = _PAGE_WRITE, + .set = "w", + .clear = " ", + }, { + .mask = _PAGE_EXEC, + .val = _PAGE_EXEC, + .set = " X ", + .clear = " ", + }, { + .mask = _PAGE_PTE, + .val = _PAGE_PTE, + .set = "pte", + .clear = " ", + }, { + .mask = _PAGE_PRESENT, + .val = _PAGE_PRESENT, + .set = "present", + .clear = " ", + }, { + .mask = H_PAGE_HASHPTE, + .val = H_PAGE_HASHPTE, + .set = "hpte", + .clear = " ", + }, { + .mask = _PAGE_DIRTY, + .val = _PAGE_DIRTY, + .set = "dirty", + .clear = " ", + }, { + .mask = _PAGE_ACCESSED, + .val = _PAGE_ACCESSED, + .set = "accessed", + .clear = " ", + }, { + .mask = _PAGE_NON_IDEMPOTENT, + .val = _PAGE_NON_IDEMPOTENT, + .set = "non-idempotent", + .clear = " ", + }, { + .mask = _PAGE_TOLERANT, + .val = _PAGE_TOLERANT, + .set = "tolerant", + .clear = " ", + }, { + .mask = H_PAGE_BUSY, + .val = H_PAGE_BUSY, + .set = "busy", + }, { +#ifdef CONFIG_PPC_64K_PAGES + .mask = H_PAGE_COMBO, + .val = H_PAGE_COMBO, + .set = "combo", + }, { + .mask = H_PAGE_4K_PFN, + .val = H_PAGE_4K_PFN, + .set = "4K_pfn", + }, { +#else /* CONFIG_PPC_64K_PAGES */ + .mask = H_PAGE_F_GIX, + .val = H_PAGE_F_GIX, + .set = "f_gix", + .is_val = true, + .shift = H_PAGE_F_GIX_SHIFT, + }, { + .mask = H_PAGE_F_SECOND, + .val = H_PAGE_F_SECOND, + .set = "f_second", + }, { +#endif /* CONFIG_PPC_64K_PAGES */ + .mask = _PAGE_SPECIAL, + .val = _PAGE_SPECIAL, + .set = "special", + } +}; + +struct pgtable_level pg_level[5] = { + { + }, { /* pgd */ + .flag = flag_array, + .num = ARRAY_SIZE(flag_array), + }, { /* pud */ + .flag = flag_array, + .num = ARRAY_SIZE(flag_array), + }, { /* pmd */ + .flag = flag_array, + .num = ARRAY_SIZE(flag_array), + }, { /* pte */ + .flag = flag_array, + .num = ARRAY_SIZE(flag_array), + }, +}; diff --git a/arch/powerpc/mm/ptdump/hashpagetable.c b/arch/powerpc/mm/ptdump/hashpagetable.c new file mode 100644 index 000000000..b430e4e08 --- /dev/null +++ b/arch/powerpc/mm/ptdump/hashpagetable.c @@ -0,0 +1,550 @@ +/* + * Copyright 2016, Rashmica Gupta, IBM Corp. + * + * This traverses the kernel virtual memory and dumps the pages that are in + * the hash pagetable, along with their flags to + * /sys/kernel/debug/kernel_hash_pagetable. + * + * If radix is enabled then there is no hash page table and so no debugfs file + * is generated. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +struct pg_state { + struct seq_file *seq; + const struct addr_marker *marker; + unsigned long start_address; + unsigned int level; + u64 current_flags; +}; + +struct addr_marker { + unsigned long start_address; + const char *name; +}; + +static struct addr_marker address_markers[] = { + { 0, "Start of kernel VM" }, + { 0, "vmalloc() Area" }, + { 0, "vmalloc() End" }, + { 0, "isa I/O start" }, + { 0, "isa I/O end" }, + { 0, "phb I/O start" }, + { 0, "phb I/O end" }, + { 0, "I/O remap start" }, + { 0, "I/O remap end" }, + { 0, "vmemmap start" }, + { -1, NULL }, +}; + +struct flag_info { + u64 mask; + u64 val; + const char *set; + const char *clear; + bool is_val; + int shift; +}; + +static const struct flag_info v_flag_array[] = { + { + .mask = SLB_VSID_B, + .val = SLB_VSID_B_256M, + .set = "ssize: 256M", + .clear = "ssize: 1T ", + }, { + .mask = HPTE_V_SECONDARY, + .val = HPTE_V_SECONDARY, + .set = "secondary", + .clear = "primary ", + }, { + .mask = HPTE_V_VALID, + .val = HPTE_V_VALID, + .set = "valid ", + .clear = "invalid", + }, { + .mask = HPTE_V_BOLTED, + .val = HPTE_V_BOLTED, + .set = "bolted", + .clear = "", + } +}; + +static const struct flag_info r_flag_array[] = { + { + .mask = HPTE_R_PP0 | HPTE_R_PP, + .val = PP_RWXX, + .set = "prot:RW--", + }, { + .mask = HPTE_R_PP0 | HPTE_R_PP, + .val = PP_RWRX, + .set = "prot:RWR-", + }, { + .mask = HPTE_R_PP0 | HPTE_R_PP, + .val = PP_RWRW, + .set = "prot:RWRW", + }, { + .mask = HPTE_R_PP0 | HPTE_R_PP, + .val = PP_RXRX, + .set = "prot:R-R-", + }, { + .mask = HPTE_R_PP0 | HPTE_R_PP, + .val = PP_RXXX, + .set = "prot:R---", + }, { + .mask = HPTE_R_KEY_HI | HPTE_R_KEY_LO, + .val = HPTE_R_KEY_HI | HPTE_R_KEY_LO, + .set = "key", + .clear = "", + .is_val = true, + }, { + .mask = HPTE_R_R, + .val = HPTE_R_R, + .set = "ref", + .clear = " ", + }, { + .mask = HPTE_R_C, + .val = HPTE_R_C, + .set = "changed", + .clear = " ", + }, { + .mask = HPTE_R_N, + .val = HPTE_R_N, + .set = "no execute", + }, { + .mask = HPTE_R_WIMG, + .val = HPTE_R_W, + .set = "writethru", + }, { + .mask = HPTE_R_WIMG, + .val = HPTE_R_I, + .set = "no cache", + }, { + .mask = HPTE_R_WIMG, + .val = HPTE_R_G, + .set = "guarded", + } +}; + +static int calculate_pagesize(struct pg_state *st, int ps, char s[]) +{ + static const char units[] = "BKMGTPE"; + const char *unit = units; + + while (ps > 9 && unit[1]) { + ps -= 10; + unit++; + } + seq_printf(st->seq, " %s_ps: %i%c\t", s, 1<mask == 0) + continue; + /* Some 'flags' are actually values */ + if (flag->is_val) { + val = pte & flag->val; + if (flag->shift) + val = val >> flag->shift; + seq_printf(st->seq, " %s:%llx", flag->set, val); + } else { + if ((pte & flag->mask) == flag->val) + s = flag->set; + else + s = flag->clear; + if (s) + seq_printf(st->seq, " %s", s); + } + } +} + +static void dump_hpte_info(struct pg_state *st, unsigned long ea, u64 v, u64 r, + unsigned long rpn, int bps, int aps, unsigned long lp) +{ + int aps_index; + + while (ea >= st->marker[1].start_address) { + st->marker++; + seq_printf(st->seq, "---[ %s ]---\n", st->marker->name); + } + seq_printf(st->seq, "0x%lx:\t", ea); + seq_printf(st->seq, "AVPN:%llx\t", HPTE_V_AVPN_VAL(v)); + dump_flag_info(st, v_flag_array, v, ARRAY_SIZE(v_flag_array)); + seq_printf(st->seq, " rpn: %lx\t", rpn); + dump_flag_info(st, r_flag_array, r, ARRAY_SIZE(r_flag_array)); + + calculate_pagesize(st, bps, "base"); + aps_index = calculate_pagesize(st, aps, "actual"); + if (aps_index != 2) + seq_printf(st->seq, "LP enc: %lx", lp); + seq_putc(st->seq, '\n'); +} + + +static int native_find(unsigned long ea, int psize, bool primary, u64 *v, u64 + *r) +{ + struct hash_pte *hptep; + unsigned long hash, vsid, vpn, hpte_group, want_v, hpte_v; + int i, ssize = mmu_kernel_ssize; + unsigned long shift = mmu_psize_defs[psize].shift; + + /* calculate hash */ + vsid = get_kernel_vsid(ea, ssize); + vpn = hpt_vpn(ea, vsid, ssize); + hash = hpt_hash(vpn, shift, ssize); + want_v = hpte_encode_avpn(vpn, psize, ssize); + + /* to check in the secondary hash table, we invert the hash */ + if (!primary) + hash = ~hash; + hpte_group = (hash & htab_hash_mask) * HPTES_PER_GROUP; + for (i = 0; i < HPTES_PER_GROUP; i++) { + hptep = htab_address + hpte_group; + hpte_v = be64_to_cpu(hptep->v); + + if (HPTE_V_COMPARE(hpte_v, want_v) && (hpte_v & HPTE_V_VALID)) { + /* HPTE matches */ + *v = be64_to_cpu(hptep->v); + *r = be64_to_cpu(hptep->r); + return 0; + } + ++hpte_group; + } + return -1; +} + +#ifdef CONFIG_PPC_PSERIES +static int pseries_find(unsigned long ea, int psize, bool primary, u64 *v, u64 *r) +{ + struct hash_pte ptes[4]; + unsigned long vsid, vpn, hash, hpte_group, want_v; + int i, j, ssize = mmu_kernel_ssize; + long lpar_rc = 0; + unsigned long shift = mmu_psize_defs[psize].shift; + + /* calculate hash */ + vsid = get_kernel_vsid(ea, ssize); + vpn = hpt_vpn(ea, vsid, ssize); + hash = hpt_hash(vpn, shift, ssize); + want_v = hpte_encode_avpn(vpn, psize, ssize); + + /* to check in the secondary hash table, we invert the hash */ + if (!primary) + hash = ~hash; + hpte_group = (hash & htab_hash_mask) * HPTES_PER_GROUP; + /* see if we can find an entry in the hpte with this hash */ + for (i = 0; i < HPTES_PER_GROUP; i += 4, hpte_group += 4) { + lpar_rc = plpar_pte_read_4(0, hpte_group, (void *)ptes); + + if (lpar_rc != H_SUCCESS) + continue; + for (j = 0; j < 4; j++) { + if (HPTE_V_COMPARE(ptes[j].v, want_v) && + (ptes[j].v & HPTE_V_VALID)) { + /* HPTE matches */ + *v = ptes[j].v; + *r = ptes[j].r; + return 0; + } + } + } + return -1; +} +#endif + +static void decode_r(int bps, unsigned long r, unsigned long *rpn, int *aps, + unsigned long *lp_bits) +{ + struct mmu_psize_def entry; + unsigned long arpn, mask, lp; + int penc = -2, idx = 0, shift; + + /*. + * The LP field has 8 bits. Depending on the actual page size, some of + * these bits are concatenated with the APRN to get the RPN. The rest + * of the bits in the LP field is the LP value and is an encoding for + * the base page size and the actual page size. + * + * - find the mmu entry for our base page size + * - go through all page encodings and use the associated mask to + * find an encoding that matches our encoding in the LP field. + */ + arpn = (r & HPTE_R_RPN) >> HPTE_R_RPN_SHIFT; + lp = arpn & 0xff; + + entry = mmu_psize_defs[bps]; + while (idx < MMU_PAGE_COUNT) { + penc = entry.penc[idx]; + if ((penc != -1) && (mmu_psize_defs[idx].shift)) { + shift = mmu_psize_defs[idx].shift - HPTE_R_RPN_SHIFT; + mask = (0x1 << (shift)) - 1; + if ((lp & mask) == penc) { + *aps = mmu_psize_to_shift(idx); + *lp_bits = lp & mask; + *rpn = arpn >> shift; + return; + } + } + idx++; + } +} + +static int base_hpte_find(unsigned long ea, int psize, bool primary, u64 *v, + u64 *r) +{ +#ifdef CONFIG_PPC_PSERIES + if (firmware_has_feature(FW_FEATURE_LPAR)) + return pseries_find(ea, psize, primary, v, r); +#endif + return native_find(ea, psize, primary, v, r); +} + +static unsigned long hpte_find(struct pg_state *st, unsigned long ea, int psize) +{ + unsigned long slot; + u64 v = 0, r = 0; + unsigned long rpn, lp_bits; + int base_psize = 0, actual_psize = 0; + + if (ea < PAGE_OFFSET) + return -1; + + /* Look in primary table */ + slot = base_hpte_find(ea, psize, true, &v, &r); + + /* Look in secondary table */ + if (slot == -1) + slot = base_hpte_find(ea, psize, false, &v, &r); + + /* No entry found */ + if (slot == -1) + return -1; + + /* + * We found an entry in the hash page table: + * - check that this has the same base page + * - find the actual page size + * - find the RPN + */ + base_psize = mmu_psize_to_shift(psize); + + if ((v & HPTE_V_LARGE) == HPTE_V_LARGE) { + decode_r(psize, r, &rpn, &actual_psize, &lp_bits); + } else { + /* 4K actual page size */ + actual_psize = 12; + rpn = (r & HPTE_R_RPN) >> HPTE_R_RPN_SHIFT; + /* In this case there are no LP bits */ + lp_bits = -1; + } + /* + * We didn't find a matching encoding, so the PTE we found isn't for + * this address. + */ + if (actual_psize == -1) + return -1; + + dump_hpte_info(st, ea, v, r, rpn, base_psize, actual_psize, lp_bits); + return 0; +} + +static void walk_pte(struct pg_state *st, pmd_t *pmd, unsigned long start) +{ + pte_t *pte = pte_offset_kernel(pmd, 0); + unsigned long addr, pteval, psize; + int i, status; + + for (i = 0; i < PTRS_PER_PTE; i++, pte++) { + addr = start + i * PAGE_SIZE; + pteval = pte_val(*pte); + + if (addr < VMALLOC_END) + psize = mmu_vmalloc_psize; + else + psize = mmu_io_psize; +#ifdef CONFIG_PPC_64K_PAGES + /* check for secret 4K mappings */ + if (((pteval & H_PAGE_COMBO) == H_PAGE_COMBO) || + ((pteval & H_PAGE_4K_PFN) == H_PAGE_4K_PFN)) + psize = mmu_io_psize; +#endif + /* check for hashpte */ + status = hpte_find(st, addr, psize); + + if (((pteval & H_PAGE_HASHPTE) != H_PAGE_HASHPTE) + && (status != -1)) { + /* found a hpte that is not in the linux page tables */ + seq_printf(st->seq, "page probably bolted before linux" + " pagetables were set: addr:%lx, pteval:%lx\n", + addr, pteval); + } + } +} + +static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start) +{ + pmd_t *pmd = pmd_offset(pud, 0); + unsigned long addr; + unsigned int i; + + for (i = 0; i < PTRS_PER_PMD; i++, pmd++) { + addr = start + i * PMD_SIZE; + if (!pmd_none(*pmd)) + /* pmd exists */ + walk_pte(st, pmd, addr); + } +} + +static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start) +{ + pud_t *pud = pud_offset(pgd, 0); + unsigned long addr; + unsigned int i; + + for (i = 0; i < PTRS_PER_PUD; i++, pud++) { + addr = start + i * PUD_SIZE; + if (!pud_none(*pud)) + /* pud exists */ + walk_pmd(st, pud, addr); + } +} + +static void walk_pagetables(struct pg_state *st) +{ + pgd_t *pgd = pgd_offset_k(0UL); + unsigned int i; + unsigned long addr; + + /* + * Traverse the linux pagetable structure and dump pages that are in + * the hash pagetable. + */ + for (i = 0; i < PTRS_PER_PGD; i++, pgd++) { + addr = KERN_VIRT_START + i * PGDIR_SIZE; + if (!pgd_none(*pgd)) + /* pgd exists */ + walk_pud(st, pgd, addr); + } +} + + +static void walk_linearmapping(struct pg_state *st) +{ + unsigned long addr; + + /* + * Traverse the linear mapping section of virtual memory and dump pages + * that are in the hash pagetable. + */ + unsigned long psize = 1 << mmu_psize_defs[mmu_linear_psize].shift; + + for (addr = PAGE_OFFSET; addr < PAGE_OFFSET + + memblock_end_of_DRAM(); addr += psize) + hpte_find(st, addr, mmu_linear_psize); +} + +static void walk_vmemmap(struct pg_state *st) +{ +#ifdef CONFIG_SPARSEMEM_VMEMMAP + struct vmemmap_backing *ptr = vmemmap_list; + + /* + * Traverse the vmemmaped memory and dump pages that are in the hash + * pagetable. + */ + while (ptr->list) { + hpte_find(st, ptr->virt_addr, mmu_vmemmap_psize); + ptr = ptr->list; + } + seq_puts(st->seq, "---[ vmemmap end ]---\n"); +#endif +} + +static void populate_markers(void) +{ + address_markers[0].start_address = PAGE_OFFSET; + address_markers[1].start_address = VMALLOC_START; + address_markers[2].start_address = VMALLOC_END; + address_markers[3].start_address = ISA_IO_BASE; + address_markers[4].start_address = ISA_IO_END; + address_markers[5].start_address = PHB_IO_BASE; + address_markers[6].start_address = PHB_IO_END; + address_markers[7].start_address = IOREMAP_BASE; + address_markers[8].start_address = IOREMAP_END; +#ifdef CONFIG_PPC_BOOK3S_64 + address_markers[9].start_address = H_VMEMMAP_BASE; +#else + address_markers[9].start_address = VMEMMAP_BASE; +#endif +} + +static int ptdump_show(struct seq_file *m, void *v) +{ + struct pg_state st = { + .seq = m, + .start_address = PAGE_OFFSET, + .marker = address_markers, + }; + /* + * Traverse the 0xc, 0xd and 0xf areas of the kernel virtual memory and + * dump pages that are in the hash pagetable. + */ + walk_linearmapping(&st); + walk_pagetables(&st); + walk_vmemmap(&st); + return 0; +} + +static int ptdump_open(struct inode *inode, struct file *file) +{ + return single_open(file, ptdump_show, NULL); +} + +static const struct file_operations ptdump_fops = { + .open = ptdump_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int ptdump_init(void) +{ + struct dentry *debugfs_file; + + if (!radix_enabled()) { + populate_markers(); + debugfs_file = debugfs_create_file("kernel_hash_pagetable", + 0400, NULL, NULL, &ptdump_fops); + return debugfs_file ? 0 : -ENOMEM; + } + return 0; +} +device_initcall(ptdump_init); diff --git a/arch/powerpc/mm/ptdump/ptdump.c b/arch/powerpc/mm/ptdump/ptdump.c new file mode 100644 index 000000000..76be98988 --- /dev/null +++ b/arch/powerpc/mm/ptdump/ptdump.c @@ -0,0 +1,373 @@ +/* + * Copyright 2016, Rashmica Gupta, IBM Corp. + * + * This traverses the kernel pagetables and dumps the + * information about the used sections of memory to + * /sys/kernel/debug/kernel_pagetables. + * + * Derived from the arm64 implementation: + * Copyright (c) 2014, The Linux Foundation, Laura Abbott. + * (C) Copyright 2008 Intel Corporation, Arjan van de Ven. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "ptdump.h" + +#ifdef CONFIG_PPC32 +#define KERN_VIRT_START 0 +#endif + +/* + * To visualise what is happening, + * + * - PTRS_PER_P** = how many entries there are in the corresponding P** + * - P**_SHIFT = how many bits of the address we use to index into the + * corresponding P** + * - P**_SIZE is how much memory we can access through the table - not the + * size of the table itself. + * P**={PGD, PUD, PMD, PTE} + * + * + * Each entry of the PGD points to a PUD. Each entry of a PUD points to a + * PMD. Each entry of a PMD points to a PTE. And every PTE entry points to + * a page. + * + * In the case where there are only 3 levels, the PUD is folded into the + * PGD: every PUD has only one entry which points to the PMD. + * + * The page dumper groups page table entries of the same type into a single + * description. It uses pg_state to track the range information while + * iterating over the PTE entries. When the continuity is broken it then + * dumps out a description of the range - ie PTEs that are virtually contiguous + * with the same PTE flags are chunked together. This is to make it clear how + * different areas of the kernel virtual memory are used. + * + */ +struct pg_state { + struct seq_file *seq; + const struct addr_marker *marker; + unsigned long start_address; + unsigned long start_pa; + unsigned long last_pa; + unsigned int level; + u64 current_flags; +}; + +struct addr_marker { + unsigned long start_address; + const char *name; +}; + +static struct addr_marker address_markers[] = { + { 0, "Start of kernel VM" }, + { 0, "vmalloc() Area" }, + { 0, "vmalloc() End" }, +#ifdef CONFIG_PPC64 + { 0, "isa I/O start" }, + { 0, "isa I/O end" }, + { 0, "phb I/O start" }, + { 0, "phb I/O end" }, + { 0, "I/O remap start" }, + { 0, "I/O remap end" }, + { 0, "vmemmap start" }, +#else + { 0, "Early I/O remap start" }, + { 0, "Early I/O remap end" }, +#ifdef CONFIG_NOT_COHERENT_CACHE + { 0, "Consistent mem start" }, + { 0, "Consistent mem end" }, +#endif +#ifdef CONFIG_HIGHMEM + { 0, "Highmem PTEs start" }, + { 0, "Highmem PTEs end" }, +#endif + { 0, "Fixmap start" }, + { 0, "Fixmap end" }, +#endif + { -1, NULL }, +}; + +static void dump_flag_info(struct pg_state *st, const struct flag_info + *flag, u64 pte, int num) +{ + unsigned int i; + + for (i = 0; i < num; i++, flag++) { + const char *s = NULL; + u64 val; + + /* flag not defined so don't check it */ + if (flag->mask == 0) + continue; + /* Some 'flags' are actually values */ + if (flag->is_val) { + val = pte & flag->val; + if (flag->shift) + val = val >> flag->shift; + seq_printf(st->seq, " %s:%llx", flag->set, val); + } else { + if ((pte & flag->mask) == flag->val) + s = flag->set; + else + s = flag->clear; + if (s) + seq_printf(st->seq, " %s", s); + } + st->current_flags &= ~flag->mask; + } + if (st->current_flags != 0) + seq_printf(st->seq, " unknown flags:%llx", st->current_flags); +} + +static void dump_addr(struct pg_state *st, unsigned long addr) +{ + static const char units[] = "KMGTPE"; + const char *unit = units; + unsigned long delta; + +#ifdef CONFIG_PPC64 + seq_printf(st->seq, "0x%016lx-0x%016lx ", st->start_address, addr-1); + seq_printf(st->seq, "0x%016lx ", st->start_pa); +#else + seq_printf(st->seq, "0x%08lx-0x%08lx ", st->start_address, addr - 1); + seq_printf(st->seq, "0x%08lx ", st->start_pa); +#endif + + delta = (addr - st->start_address) >> 10; + /* Work out what appropriate unit to use */ + while (!(delta & 1023) && unit[1]) { + delta >>= 10; + unit++; + } + seq_printf(st->seq, "%9lu%c", delta, *unit); + +} + +static void note_page(struct pg_state *st, unsigned long addr, + unsigned int level, u64 val) +{ + u64 flag = val & pg_level[level].mask; + u64 pa = val & PTE_RPN_MASK; + + /* At first no level is set */ + if (!st->level) { + st->level = level; + st->current_flags = flag; + st->start_address = addr; + st->start_pa = pa; + st->last_pa = pa; + seq_printf(st->seq, "---[ %s ]---\n", st->marker->name); + /* + * Dump the section of virtual memory when: + * - the PTE flags from one entry to the next differs. + * - we change levels in the tree. + * - the address is in a different section of memory and is thus + * used for a different purpose, regardless of the flags. + * - the pa of this page is not adjacent to the last inspected page + */ + } else if (flag != st->current_flags || level != st->level || + addr >= st->marker[1].start_address || + pa != st->last_pa + PAGE_SIZE) { + + /* Check the PTE flags */ + if (st->current_flags) { + dump_addr(st, addr); + + /* Dump all the flags */ + if (pg_level[st->level].flag) + dump_flag_info(st, pg_level[st->level].flag, + st->current_flags, + pg_level[st->level].num); + + seq_putc(st->seq, '\n'); + } + + /* + * Address indicates we have passed the end of the + * current section of virtual memory + */ + while (addr >= st->marker[1].start_address) { + st->marker++; + seq_printf(st->seq, "---[ %s ]---\n", st->marker->name); + } + st->start_address = addr; + st->start_pa = pa; + st->last_pa = pa; + st->current_flags = flag; + st->level = level; + } else { + st->last_pa = pa; + } +} + +static void walk_pte(struct pg_state *st, pmd_t *pmd, unsigned long start) +{ + pte_t *pte = pte_offset_kernel(pmd, 0); + unsigned long addr; + unsigned int i; + + for (i = 0; i < PTRS_PER_PTE; i++, pte++) { + addr = start + i * PAGE_SIZE; + note_page(st, addr, 4, pte_val(*pte)); + + } +} + +static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start) +{ + pmd_t *pmd = pmd_offset(pud, 0); + unsigned long addr; + unsigned int i; + + for (i = 0; i < PTRS_PER_PMD; i++, pmd++) { + addr = start + i * PMD_SIZE; + if (!pmd_none(*pmd) && !pmd_huge(*pmd)) + /* pmd exists */ + walk_pte(st, pmd, addr); + else + note_page(st, addr, 3, pmd_val(*pmd)); + } +} + +static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start) +{ + pud_t *pud = pud_offset(pgd, 0); + unsigned long addr; + unsigned int i; + + for (i = 0; i < PTRS_PER_PUD; i++, pud++) { + addr = start + i * PUD_SIZE; + if (!pud_none(*pud) && !pud_huge(*pud)) + /* pud exists */ + walk_pmd(st, pud, addr); + else + note_page(st, addr, 2, pud_val(*pud)); + } +} + +static void walk_pagetables(struct pg_state *st) +{ + pgd_t *pgd = pgd_offset_k(0UL); + unsigned int i; + unsigned long addr; + + addr = st->start_address; + + /* + * Traverse the linux pagetable structure and dump pages that are in + * the hash pagetable. + */ + for (i = 0; i < PTRS_PER_PGD; i++, pgd++, addr += PGDIR_SIZE) { + if (!pgd_none(*pgd) && !pgd_huge(*pgd)) + /* pgd exists */ + walk_pud(st, pgd, addr); + else + note_page(st, addr, 1, pgd_val(*pgd)); + } +} + +static void populate_markers(void) +{ + int i = 0; + + address_markers[i++].start_address = PAGE_OFFSET; + address_markers[i++].start_address = VMALLOC_START; + address_markers[i++].start_address = VMALLOC_END; +#ifdef CONFIG_PPC64 + address_markers[i++].start_address = ISA_IO_BASE; + address_markers[i++].start_address = ISA_IO_END; + address_markers[i++].start_address = PHB_IO_BASE; + address_markers[i++].start_address = PHB_IO_END; + address_markers[i++].start_address = IOREMAP_BASE; + address_markers[i++].start_address = IOREMAP_END; +#ifdef CONFIG_PPC_BOOK3S_64 + address_markers[i++].start_address = H_VMEMMAP_BASE; +#else + address_markers[i++].start_address = VMEMMAP_BASE; +#endif +#else /* !CONFIG_PPC64 */ + address_markers[i++].start_address = ioremap_bot; + address_markers[i++].start_address = IOREMAP_TOP; +#ifdef CONFIG_NOT_COHERENT_CACHE + address_markers[i++].start_address = IOREMAP_TOP; + address_markers[i++].start_address = IOREMAP_TOP + + CONFIG_CONSISTENT_SIZE; +#endif +#ifdef CONFIG_HIGHMEM + address_markers[i++].start_address = PKMAP_BASE; + address_markers[i++].start_address = PKMAP_ADDR(LAST_PKMAP); +#endif + address_markers[i++].start_address = FIXADDR_START; + address_markers[i++].start_address = FIXADDR_TOP; +#endif /* CONFIG_PPC64 */ +} + +static int ptdump_show(struct seq_file *m, void *v) +{ + struct pg_state st = { + .seq = m, + .marker = address_markers, + }; + + if (radix_enabled()) + st.start_address = PAGE_OFFSET; + else + st.start_address = KERN_VIRT_START; + + /* Traverse kernel page tables */ + walk_pagetables(&st); + note_page(&st, 0, 0, 0); + return 0; +} + + +static int ptdump_open(struct inode *inode, struct file *file) +{ + return single_open(file, ptdump_show, NULL); +} + +static const struct file_operations ptdump_fops = { + .open = ptdump_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static void build_pgtable_complete_mask(void) +{ + unsigned int i, j; + + for (i = 0; i < ARRAY_SIZE(pg_level); i++) + if (pg_level[i].flag) + for (j = 0; j < pg_level[i].num; j++) + pg_level[i].mask |= pg_level[i].flag[j].mask; +} + +static int ptdump_init(void) +{ + struct dentry *debugfs_file; + + populate_markers(); + build_pgtable_complete_mask(); + debugfs_file = debugfs_create_file("kernel_page_tables", 0400, NULL, + NULL, &ptdump_fops); + return debugfs_file ? 0 : -ENOMEM; +} +device_initcall(ptdump_init); diff --git a/arch/powerpc/mm/ptdump/ptdump.h b/arch/powerpc/mm/ptdump/ptdump.h new file mode 100644 index 000000000..5d513636d --- /dev/null +++ b/arch/powerpc/mm/ptdump/ptdump.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include + +struct flag_info { + u64 mask; + u64 val; + const char *set; + const char *clear; + bool is_val; + int shift; +}; + +struct pgtable_level { + const struct flag_info *flag; + size_t num; + u64 mask; +}; + +extern struct pgtable_level pg_level[5]; diff --git a/arch/powerpc/mm/ptdump/segment_regs.c b/arch/powerpc/mm/ptdump/segment_regs.c new file mode 100644 index 000000000..501843664 --- /dev/null +++ b/arch/powerpc/mm/ptdump/segment_regs.c @@ -0,0 +1,64 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright 2018, Christophe Leroy CS S.I. + * + * + * This dumps the content of Segment Registers + */ + +#include + +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/ptdump/shared.c b/arch/powerpc/mm/ptdump/shared.c new file mode 100644 index 000000000..1cda3d91c --- /dev/null +++ b/arch/powerpc/mm/ptdump/shared.c @@ -0,0 +1,82 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * From split of dump_linuxpagetables.c + * Copyright 2016, Rashmica Gupta, IBM Corp. + * + */ +#include +#include + +#include "ptdump.h" + +static const struct flag_info flag_array[] = { + { + .mask = _PAGE_USER, + .val = _PAGE_USER, + .set = "user", + .clear = " ", + }, { + .mask = _PAGE_RW, + .val = 0, + .set = "r ", + .clear = "rw", + }, { +#ifndef CONFIG_PPC_BOOK3S_32 + .mask = _PAGE_EXEC, + .val = _PAGE_EXEC, + .set = " X ", + .clear = " ", + }, { +#endif + .mask = _PAGE_PRESENT, + .val = _PAGE_PRESENT, + .set = "present", + .clear = " ", + }, { + .mask = _PAGE_GUARDED, + .val = _PAGE_GUARDED, + .set = "guarded", + .clear = " ", + }, { + .mask = _PAGE_DIRTY, + .val = _PAGE_DIRTY, + .set = "dirty", + .clear = " ", + }, { + .mask = _PAGE_ACCESSED, + .val = _PAGE_ACCESSED, + .set = "accessed", + .clear = " ", + }, { + .mask = _PAGE_WRITETHRU, + .val = _PAGE_WRITETHRU, + .set = "write through", + .clear = " ", + }, { + .mask = _PAGE_NO_CACHE, + .val = _PAGE_NO_CACHE, + .set = "no cache", + .clear = " ", + }, { + .mask = _PAGE_SPECIAL, + .val = _PAGE_SPECIAL, + .set = "special", + } +}; + +struct pgtable_level pg_level[5] = { + { + }, { /* pgd */ + .flag = flag_array, + .num = ARRAY_SIZE(flag_array), + }, { /* pud */ + .flag = flag_array, + .num = ARRAY_SIZE(flag_array), + }, { /* pmd */ + .flag = flag_array, + .num = ARRAY_SIZE(flag_array), + }, { /* pte */ + .flag = flag_array, + .num = ARRAY_SIZE(flag_array), + }, +}; -- cgit v1.2.3