diff options
Diffstat (limited to 'arch/powerpc/mm/ptdump')
| -rw-r--r-- | arch/powerpc/mm/ptdump/8xx.c | 94 | ||||
| -rw-r--r-- | arch/powerpc/mm/ptdump/Makefile | 14 | ||||
| -rw-r--r-- | arch/powerpc/mm/ptdump/bats.c | 99 | ||||
| -rw-r--r-- | arch/powerpc/mm/ptdump/book3s64.c | 122 | ||||
| -rw-r--r-- | arch/powerpc/mm/ptdump/hashpagetable.c | 543 | ||||
| -rw-r--r-- | arch/powerpc/mm/ptdump/ptdump.c | 375 | ||||
| -rw-r--r-- | arch/powerpc/mm/ptdump/ptdump.h | 22 | ||||
| -rw-r--r-- | arch/powerpc/mm/ptdump/segment_regs.c | 52 | ||||
| -rw-r--r-- | arch/powerpc/mm/ptdump/shared.c | 87 |
9 files changed, 1408 insertions, 0 deletions
diff --git a/arch/powerpc/mm/ptdump/8xx.c b/arch/powerpc/mm/ptdump/8xx.c new file mode 100644 index 000000000..fac932eb8 --- /dev/null +++ b/arch/powerpc/mm/ptdump/8xx.c @@ -0,0 +1,94 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * From split of dump_linuxpagetables.c + * Copyright 2016, Rashmica Gupta, IBM Corp. + * + */ +#include <linux/kernel.h> +#include <linux/pgtable.h> + +#include "ptdump.h" + +static const struct flag_info flag_array[] = { + { +#ifdef CONFIG_PPC_16K_PAGES + .mask = _PAGE_HUGE, + .val = _PAGE_HUGE, +#else + .mask = _PAGE_SPS, + .val = _PAGE_SPS, +#endif + .set = "huge", + .clear = " ", + }, { + .mask = _PAGE_SH, + .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), + }, { /* p4d */ + .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..dc896d287 --- /dev/null +++ b/arch/powerpc/mm/ptdump/Makefile @@ -0,0 +1,14 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-y += ptdump.o + +obj-$(CONFIG_4xx) += shared.o +obj-$(CONFIG_PPC_8xx) += 8xx.o +obj-$(CONFIG_PPC_E500) += shared.o +obj-$(CONFIG_PPC_BOOK3S_32) += shared.o +obj-$(CONFIG_PPC_BOOK3S_64) += book3s64.o + +ifdef CONFIG_PTDUMP_DEBUGFS +obj-$(CONFIG_PPC_BOOK3S_32) += bats.o segment_regs.o +obj-$(CONFIG_PPC_64S_HASH_MMU) += hashpagetable.o +endif diff --git a/arch/powerpc/mm/ptdump/bats.c b/arch/powerpc/mm/ptdump/bats.c new file mode 100644 index 000000000..820c11901 --- /dev/null +++ b/arch/powerpc/mm/ptdump/bats.c @@ -0,0 +1,99 @@ +// 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 <linux/pgtable.h> +#include <linux/debugfs.h> +#include <asm/cpu_has_feature.h> + +#include "ptdump.h" + +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 + pt_dump_size(m, size); + + 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 ? "r " : " x "); + else if (lower & BPP_RW) + seq_puts(m, is_d ? "rw " : " x "); + else + seq_puts(m, is_d ? " " : " "); + + seq_puts(m, lower & _PAGE_WRITETHRU ? "w " : " "); + seq_puts(m, lower & _PAGE_NO_CACHE ? "i " : " "); + seq_puts(m, lower & _PAGE_COHERENT ? "m " : " "); + seq_puts(m, lower & _PAGE_GUARDED ? "g " : " "); + 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(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; +} + +DEFINE_SHOW_ATTRIBUTE(bats); + +static int __init bats_init(void) +{ + debugfs_create_file("block_address_translation", 0400, + arch_debugfs_dir, NULL, &bats_fops); + return 0; +} +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..5ad92d9dc --- /dev/null +++ b/arch/powerpc/mm/ptdump/book3s64.c @@ -0,0 +1,122 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * From split of dump_linuxpagetables.c + * Copyright 2016, Rashmica Gupta, IBM Corp. + * + */ +#include <linux/kernel.h> +#include <linux/pgtable.h> + +#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 = "valid", + .clear = " ", + }, { + .mask = _PAGE_PRESENT | _PAGE_INVALID, + .val = 0, + .set = " ", + .clear = "present", + }, { + .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), + }, { /* p4d */ + .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..9a6015878 --- /dev/null +++ b/arch/powerpc/mm/ptdump/hashpagetable.c @@ -0,0 +1,543 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * 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. + */ +#include <linux/debugfs.h> +#include <linux/fs.h> +#include <linux/io.h> +#include <linux/mm.h> +#include <linux/sched.h> +#include <linux/seq_file.h> +#include <linux/const.h> +#include <asm/page.h> +#include <asm/plpar_wrappers.h> +#include <linux/memblock.h> +#include <asm/firmware.h> +#include <asm/pgalloc.h> + +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<<ps, *unit); + return ps; +} + +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); + } + } +} + +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; +} + +static int pseries_find(unsigned long ea, int psize, bool primary, u64 *v, u64 *r) +{ + struct { + unsigned long v; + unsigned long r; + } 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) + 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; +} + +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) +{ + if (IS_ENABLED(CONFIG_PPC_PSERIES) && firmware_has_feature(FW_FEATURE_LPAR)) + return pseries_find(ea, psize, primary, v, r); + + 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; + + /* check for secret 4K mappings */ + if (IS_ENABLED(CONFIG_PPC_64K_PAGES) && + ((pteval & H_PAGE_COMBO) == H_PAGE_COMBO || + (pteval & H_PAGE_4K_PFN) == H_PAGE_4K_PFN)) + psize = mmu_io_psize; + + /* 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, p4d_t *p4d, unsigned long start) +{ + pud_t *pud = pud_offset(p4d, 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_p4d(struct pg_state *st, pgd_t *pgd, unsigned long start) +{ + p4d_t *p4d = p4d_offset(pgd, 0); + unsigned long addr; + unsigned int i; + + for (i = 0; i < PTRS_PER_P4D; i++, p4d++) { + addr = start + i * P4D_SIZE; + if (!p4d_none(*p4d)) + /* p4d exists */ + walk_pud(st, p4d, 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_p4d(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) +{ + struct vmemmap_backing *ptr = vmemmap_list; + + if (!IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP)) + return; + /* + * 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"); +} + +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; + address_markers[9].start_address = H_VMEMMAP_START; +} + +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; +} + +DEFINE_SHOW_ATTRIBUTE(ptdump); + +static int ptdump_init(void) +{ + if (!radix_enabled()) { + populate_markers(); + debugfs_create_file("kernel_hash_pagetable", 0400, NULL, NULL, + &ptdump_fops); + } + 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..2313053fe --- /dev/null +++ b/arch/powerpc/mm/ptdump/ptdump.c @@ -0,0 +1,375 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * 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. + */ +#include <linux/debugfs.h> +#include <linux/fs.h> +#include <linux/hugetlb.h> +#include <linux/io.h> +#include <linux/mm.h> +#include <linux/highmem.h> +#include <linux/ptdump.h> +#include <linux/sched.h> +#include <linux/seq_file.h> +#include <asm/fixmap.h> +#include <linux/const.h> +#include <linux/kasan.h> +#include <asm/page.h> +#include <asm/hugetlb.h> + +#include <mm/mmu_decl.h> + +#include "ptdump.h" + +/* + * 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 ptdump_state ptdump; + struct seq_file *seq; + const struct addr_marker *marker; + unsigned long start_address; + unsigned long start_pa; + int level; + u64 current_flags; + bool check_wx; + unsigned long wx_pages; +}; + +struct addr_marker { + unsigned long start_address; + const char *name; +}; + +static struct addr_marker address_markers[] = { + { 0, "Start of kernel VM" }, +#ifdef MODULES_VADDR + { 0, "modules start" }, + { 0, "modules end" }, +#endif + { 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_HIGHMEM + { 0, "Highmem PTEs start" }, + { 0, "Highmem PTEs end" }, +#endif + { 0, "Fixmap start" }, + { 0, "Fixmap end" }, +#endif +#ifdef CONFIG_KASAN + { 0, "kasan shadow mem start" }, + { 0, "kasan shadow mem end" }, +#endif + { -1, NULL }, +}; + +static struct ptdump_range ptdump_range[] __ro_after_init = { + {TASK_SIZE_MAX, ~0UL}, + {0, 0} +}; + +#define pt_dump_seq_printf(m, fmt, args...) \ +({ \ + if (m) \ + seq_printf(m, fmt, ##args); \ +}) + +#define pt_dump_seq_putc(m, c) \ +({ \ + if (m) \ + seq_putc(m, c); \ +}) + +void pt_dump_size(struct seq_file *m, unsigned long size) +{ + static const char units[] = " KMGTPE"; + const char *unit = units; + + /* Work out what appropriate unit to use */ + while (!(size & 1023) && unit[1]) { + size >>= 10; + unit++; + } + pt_dump_seq_printf(m, "%9lu%c ", size, *unit); +} + +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; + pt_dump_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) + pt_dump_seq_printf(st->seq, " %s", s); + } + st->current_flags &= ~flag->mask; + } + if (st->current_flags != 0) + pt_dump_seq_printf(st->seq, " unknown flags:%llx", st->current_flags); +} + +static void dump_addr(struct pg_state *st, unsigned long addr) +{ +#ifdef CONFIG_PPC64 +#define REG "0x%016lx" +#else +#define REG "0x%08lx" +#endif + + pt_dump_seq_printf(st->seq, REG "-" REG " ", st->start_address, addr - 1); + pt_dump_seq_printf(st->seq, " " REG " ", st->start_pa); + pt_dump_size(st->seq, addr - st->start_address); +} + +static void note_prot_wx(struct pg_state *st, unsigned long addr) +{ + pte_t pte = __pte(st->current_flags); + + if (!IS_ENABLED(CONFIG_DEBUG_WX) || !st->check_wx) + return; + + if (!pte_write(pte) || !pte_exec(pte)) + return; + + WARN_ONCE(1, "powerpc/mm: Found insecure W+X mapping at address %p/%pS\n", + (void *)st->start_address, (void *)st->start_address); + + st->wx_pages += (addr - st->start_address) / PAGE_SIZE; +} + +static void note_page_update_state(struct pg_state *st, unsigned long addr, int level, u64 val) +{ + u64 flag = level >= 0 ? val & pg_level[level].mask : 0; + u64 pa = val & PTE_RPN_MASK; + + st->level = level; + st->current_flags = flag; + st->start_address = addr; + st->start_pa = pa; + + while (addr >= st->marker[1].start_address) { + st->marker++; + pt_dump_seq_printf(st->seq, "---[ %s ]---\n", st->marker->name); + } +} + +static void note_page(struct ptdump_state *pt_st, unsigned long addr, int level, u64 val) +{ + u64 flag = level >= 0 ? val & pg_level[level].mask : 0; + struct pg_state *st = container_of(pt_st, struct pg_state, ptdump); + + /* At first no level is set */ + if (st->level == -1) { + pt_dump_seq_printf(st->seq, "---[ %s ]---\n", st->marker->name); + note_page_update_state(st, addr, level, val); + /* + * 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. + */ + } else if (flag != st->current_flags || level != st->level || + addr >= st->marker[1].start_address) { + + /* Check the PTE flags */ + if (st->current_flags) { + note_prot_wx(st, addr); + 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); + + pt_dump_seq_putc(st->seq, '\n'); + } + + /* + * Address indicates we have passed the end of the + * current section of virtual memory + */ + note_page_update_state(st, addr, level, val); + } +} + +static void populate_markers(void) +{ + int i = 0; + +#ifdef CONFIG_PPC64 + address_markers[i++].start_address = PAGE_OFFSET; +#else + address_markers[i++].start_address = TASK_SIZE; +#endif +#ifdef MODULES_VADDR + address_markers[i++].start_address = MODULES_VADDR; + address_markers[i++].start_address = MODULES_END; +#endif + 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; + /* What is the ifdef about? */ +#ifdef CONFIG_PPC_BOOK3S_64 + address_markers[i++].start_address = H_VMEMMAP_START; +#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_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 */ +#ifdef CONFIG_KASAN + address_markers[i++].start_address = KASAN_SHADOW_START; + address_markers[i++].start_address = KASAN_SHADOW_END; +#endif +} + +static int ptdump_show(struct seq_file *m, void *v) +{ + struct pg_state st = { + .seq = m, + .marker = address_markers, + .level = -1, + .ptdump = { + .note_page = note_page, + .range = ptdump_range, + } + }; + + /* Traverse kernel page tables */ + ptdump_walk_pgd(&st.ptdump, &init_mm, NULL); + return 0; +} + +DEFINE_SHOW_ATTRIBUTE(ptdump); + +static void __init 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; +} + +#ifdef CONFIG_DEBUG_WX +void ptdump_check_wx(void) +{ + struct pg_state st = { + .seq = NULL, + .marker = (struct addr_marker[]) { + { 0, NULL}, + { -1, NULL}, + }, + .level = -1, + .check_wx = true, + .ptdump = { + .note_page = note_page, + .range = ptdump_range, + } + }; + + ptdump_walk_pgd(&st.ptdump, &init_mm, NULL); + + if (st.wx_pages) + pr_warn("Checked W+X mappings: FAILED, %lu W+X pages found\n", + st.wx_pages); + else + pr_info("Checked W+X mappings: passed, no W+X pages found\n"); +} +#endif + +static int __init ptdump_init(void) +{ +#ifdef CONFIG_PPC64 + if (!radix_enabled()) + ptdump_range[0].start = KERN_VIRT_START; + else + ptdump_range[0].start = PAGE_OFFSET; + + ptdump_range[0].end = PAGE_OFFSET + (PGDIR_SIZE * PTRS_PER_PGD); +#endif + + populate_markers(); + build_pgtable_complete_mask(); + + if (IS_ENABLED(CONFIG_PTDUMP_DEBUGFS)) + debugfs_create_file("kernel_page_tables", 0400, NULL, NULL, &ptdump_fops); + + return 0; +} +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..154efae96 --- /dev/null +++ b/arch/powerpc/mm/ptdump/ptdump.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <linux/types.h> +#include <linux/seq_file.h> + +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]; + +void pt_dump_size(struct seq_file *m, unsigned long delta); diff --git a/arch/powerpc/mm/ptdump/segment_regs.c b/arch/powerpc/mm/ptdump/segment_regs.c new file mode 100644 index 000000000..9df3af8d4 --- /dev/null +++ b/arch/powerpc/mm/ptdump/segment_regs.c @@ -0,0 +1,52 @@ +// 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 <linux/debugfs.h> + +static void seg_show(struct seq_file *m, int i) +{ + u32 val = mfsr(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; +} + +DEFINE_SHOW_ATTRIBUTE(sr); + +static int __init sr_init(void) +{ + debugfs_create_file("segment_registers", 0400, arch_debugfs_dir, + NULL, &sr_fops); + return 0; +} +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..f884760ca --- /dev/null +++ b/arch/powerpc/mm/ptdump/shared.c @@ -0,0 +1,87 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * From split of dump_linuxpagetables.c + * Copyright 2016, Rashmica Gupta, IBM Corp. + * + */ +#include <linux/kernel.h> +#include <linux/pgtable.h> + +#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", + }, { + .mask = _PAGE_EXEC, + .val = _PAGE_EXEC, + .set = " X ", + .clear = " ", + }, { + .mask = _PAGE_PRESENT, + .val = _PAGE_PRESENT, + .set = "present", + .clear = " ", + }, { + .mask = _PAGE_COHERENT, + .val = _PAGE_COHERENT, + .set = "coherent", + .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), + }, { /* p4d */ + .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), + }, +}; |