Commit e0847283 authored by Christophe Leroy's avatar Christophe Leroy Committed by Michael Ellerman

powerpc/ptdump: Convert powerpc to GENERIC_PTDUMP

This patch converts powerpc to the generic PTDUMP implementation.
Signed-off-by: default avatarChristophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: default avatarMichael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/03166d569526be70214fe9370a7bad219d2f41c8.1625762907.git.christophe.leroy@csgroup.eu
parent cf98d2b6
...@@ -123,6 +123,7 @@ config PPC ...@@ -123,6 +123,7 @@ config PPC
select ARCH_HAS_COPY_MC if PPC64 select ARCH_HAS_COPY_MC if PPC64
select ARCH_HAS_DEBUG_VIRTUAL select ARCH_HAS_DEBUG_VIRTUAL
select ARCH_HAS_DEBUG_VM_PGTABLE select ARCH_HAS_DEBUG_VM_PGTABLE
select ARCH_HAS_DEBUG_WX if STRICT_KERNEL_RWX
select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_DEVMEM_IS_ALLOWED
select ARCH_HAS_DMA_MAP_DIRECT if PPC_PSERIES select ARCH_HAS_DMA_MAP_DIRECT if PPC_PSERIES
select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_ELF_RANDOMIZE
...@@ -182,6 +183,7 @@ config PPC ...@@ -182,6 +183,7 @@ config PPC
select GENERIC_IRQ_SHOW select GENERIC_IRQ_SHOW
select GENERIC_IRQ_SHOW_LEVEL select GENERIC_IRQ_SHOW_LEVEL
select GENERIC_PCI_IOMAP if PCI select GENERIC_PCI_IOMAP if PCI
select GENERIC_PTDUMP
select GENERIC_SMP_IDLE_THREAD select GENERIC_SMP_IDLE_THREAD
select GENERIC_STRNCPY_FROM_USER select GENERIC_STRNCPY_FROM_USER
select GENERIC_STRNLEN_USER select GENERIC_STRNLEN_USER
......
...@@ -365,36 +365,6 @@ config FAIL_IOMMU ...@@ -365,36 +365,6 @@ config FAIL_IOMMU
If you are unsure, say N. If you are unsure, say N.
config PPC_PTDUMP
bool "Export kernel pagetable layout to userspace via debugfs"
depends on DEBUG_KERNEL && DEBUG_FS
help
This option exports the state of the kernel pagetables to a
debugfs file. This is only useful for kernel developers who are
working in architecture specific areas of the kernel - probably
not a good idea to enable this feature in a production kernel.
If you are unsure, say N.
config PPC_DEBUG_WX
bool "Warn on W+X mappings at boot"
depends on PPC_PTDUMP && STRICT_KERNEL_RWX
help
Generate a warning if any W+X mappings are found at boot.
This is useful for discovering cases where the kernel is leaving
W+X mappings after applying NX, as such mappings are a security risk.
Note that even if the check fails, your kernel is possibly
still fine, as W+X mappings are not a security hole in
themselves, what they do is that they make the exploitation
of other unfixed kernel bugs easier.
There is no runtime or memory usage effect of this option
once the kernel has booted up - it's a one time check.
If in doubt, say "Y".
config PPC_FAST_ENDIAN_SWITCH config PPC_FAST_ENDIAN_SWITCH
bool "Deprecated fast endian-switch syscall" bool "Deprecated fast endian-switch syscall"
depends on DEBUG_KERNEL && PPC_BOOK3S_64 depends on DEBUG_KERNEL && PPC_BOOK3S_64
......
...@@ -18,5 +18,5 @@ obj-$(CONFIG_PPC_MM_SLICES) += slice.o ...@@ -18,5 +18,5 @@ obj-$(CONFIG_PPC_MM_SLICES) += slice.o
obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
obj-$(CONFIG_NOT_COHERENT_CACHE) += dma-noncoherent.o obj-$(CONFIG_NOT_COHERENT_CACHE) += dma-noncoherent.o
obj-$(CONFIG_PPC_COPRO_BASE) += copro_fault.o obj-$(CONFIG_PPC_COPRO_BASE) += copro_fault.o
obj-$(CONFIG_PPC_PTDUMP) += ptdump/ obj-$(CONFIG_PTDUMP_CORE) += ptdump/
obj-$(CONFIG_KASAN) += kasan/ obj-$(CONFIG_KASAN) += kasan/
...@@ -180,7 +180,7 @@ static inline void mmu_mark_rodata_ro(void) { } ...@@ -180,7 +180,7 @@ static inline void mmu_mark_rodata_ro(void) { }
void __init mmu_mapin_immr(void); void __init mmu_mapin_immr(void);
#endif #endif
#ifdef CONFIG_PPC_DEBUG_WX #ifdef CONFIG_DEBUG_WX
void ptdump_check_wx(void); void ptdump_check_wx(void);
#else #else
static inline void ptdump_check_wx(void) { } static inline void ptdump_check_wx(void) { }
......
...@@ -5,5 +5,10 @@ obj-y += ptdump.o ...@@ -5,5 +5,10 @@ obj-y += ptdump.o
obj-$(CONFIG_4xx) += shared.o obj-$(CONFIG_4xx) += shared.o
obj-$(CONFIG_PPC_8xx) += 8xx.o obj-$(CONFIG_PPC_8xx) += 8xx.o
obj-$(CONFIG_PPC_BOOK3E_MMU) += shared.o obj-$(CONFIG_PPC_BOOK3E_MMU) += shared.o
obj-$(CONFIG_PPC_BOOK3S_32) += shared.o bats.o segment_regs.o obj-$(CONFIG_PPC_BOOK3S_32) += shared.o
obj-$(CONFIG_PPC_BOOK3S_64) += book3s64.o hashpagetable.o obj-$(CONFIG_PPC_BOOK3S_64) += book3s64.o
ifdef CONFIG_PTDUMP_DEBUGFS
obj-$(CONFIG_PPC_BOOK3S_32) += bats.o segment_regs.o
obj-$(CONFIG_PPC_BOOK3S_64) += hashpagetable.o
endif
...@@ -16,6 +16,7 @@ ...@@ -16,6 +16,7 @@
#include <linux/io.h> #include <linux/io.h>
#include <linux/mm.h> #include <linux/mm.h>
#include <linux/highmem.h> #include <linux/highmem.h>
#include <linux/ptdump.h>
#include <linux/sched.h> #include <linux/sched.h>
#include <linux/seq_file.h> #include <linux/seq_file.h>
#include <asm/fixmap.h> #include <asm/fixmap.h>
...@@ -54,6 +55,7 @@ ...@@ -54,6 +55,7 @@
* *
*/ */
struct pg_state { struct pg_state {
struct ptdump_state ptdump;
struct seq_file *seq; struct seq_file *seq;
const struct addr_marker *marker; const struct addr_marker *marker;
unsigned long start_address; unsigned long start_address;
...@@ -102,6 +104,11 @@ static struct addr_marker address_markers[] = { ...@@ -102,6 +104,11 @@ static struct addr_marker address_markers[] = {
{ -1, NULL }, { -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...) \ #define pt_dump_seq_printf(m, fmt, args...) \
({ \ ({ \
if (m) \ if (m) \
...@@ -204,10 +211,10 @@ static void note_page_update_state(struct pg_state *st, unsigned long addr, int ...@@ -204,10 +211,10 @@ static void note_page_update_state(struct pg_state *st, unsigned long addr, int
} }
} }
static void note_page(struct pg_state *st, unsigned long addr, static void note_page(struct ptdump_state *pt_st, unsigned long addr, int level, u64 val)
int level, u64 val, unsigned long page_size)
{ {
u64 flag = level >= 0 ? val & pg_level[level].mask : 0; 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 */ /* At first no level is set */
if (st->level == -1) { if (st->level == -1) {
...@@ -245,94 +252,6 @@ static void note_page(struct pg_state *st, unsigned long addr, ...@@ -245,94 +252,6 @@ static void note_page(struct pg_state *st, unsigned long addr,
} }
} }
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), PAGE_SIZE);
}
}
static void walk_hugepd(struct pg_state *st, hugepd_t *phpd, unsigned long start,
int pdshift, int level)
{
#ifdef CONFIG_ARCH_HAS_HUGEPD
unsigned int i;
int shift = hugepd_shift(*phpd);
int ptrs_per_hpd = pdshift - shift > 0 ? 1 << (pdshift - shift) : 1;
if (start & ((1 << shift) - 1))
return;
for (i = 0; i < ptrs_per_hpd; i++) {
unsigned long addr = start + (i << shift);
pte_t *pte = hugepte_offset(*phpd, addr, pdshift);
note_page(st, addr, level + 1, pte_val(*pte), 1 << shift);
}
#endif
}
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_is_leaf(*pmd))
/* pmd exists */
walk_pte(st, pmd, addr);
else
note_page(st, addr, 3, pmd_val(*pmd), PMD_SIZE);
}
}
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_is_leaf(*pud))
/* pud exists */
walk_pmd(st, pud, addr);
else
note_page(st, addr, 2, pud_val(*pud), PUD_SIZE);
}
}
static void walk_pagetables(struct pg_state *st)
{
unsigned int i;
unsigned long addr = st->start_address & PGDIR_MASK;
pgd_t *pgd = pgd_offset_k(addr);
/*
* Traverse the linux pagetable structure and dump pages that are in
* the hash pagetable.
*/
for (i = pgd_index(addr); i < PTRS_PER_PGD; i++, pgd++, addr += PGDIR_SIZE) {
p4d_t *p4d = p4d_offset(pgd, 0);
if (p4d_none(*p4d) || p4d_is_leaf(*p4d))
note_page(st, addr, 1, p4d_val(*p4d), PGDIR_SIZE);
else if (is_hugepd(__hugepd(p4d_val(*p4d))))
walk_hugepd(st, (hugepd_t *)p4d, addr, PGDIR_SHIFT, 1);
else
/* p4d exists */
walk_pud(st, p4d, addr);
}
}
static void populate_markers(void) static void populate_markers(void)
{ {
int i = 0; int i = 0;
...@@ -383,17 +302,14 @@ static int ptdump_show(struct seq_file *m, void *v) ...@@ -383,17 +302,14 @@ static int ptdump_show(struct seq_file *m, void *v)
.seq = m, .seq = m,
.marker = address_markers, .marker = address_markers,
.level = -1, .level = -1,
.start_address = IS_ENABLED(CONFIG_PPC64) ? PAGE_OFFSET : TASK_SIZE, .ptdump = {
.note_page = note_page,
.range = ptdump_range,
}
}; };
#ifdef CONFIG_PPC64
if (!radix_enabled())
st.start_address = KERN_VIRT_START;
#endif
/* Traverse kernel page tables */ /* Traverse kernel page tables */
walk_pagetables(&st); ptdump_walk_pgd(&st.ptdump, &init_mm, NULL);
note_page(&st, 0, -1, 0, 0);
return 0; return 0;
} }
...@@ -409,23 +325,24 @@ static void build_pgtable_complete_mask(void) ...@@ -409,23 +325,24 @@ static void build_pgtable_complete_mask(void)
pg_level[i].mask |= pg_level[i].flag[j].mask; pg_level[i].mask |= pg_level[i].flag[j].mask;
} }
#ifdef CONFIG_PPC_DEBUG_WX #ifdef CONFIG_DEBUG_WX
void ptdump_check_wx(void) void ptdump_check_wx(void)
{ {
struct pg_state st = { struct pg_state st = {
.seq = NULL, .seq = NULL,
.marker = address_markers, .marker = (struct addr_marker[]) {
{ 0, NULL},
{ -1, NULL},
},
.level = -1, .level = -1,
.check_wx = true, .check_wx = true,
.start_address = IS_ENABLED(CONFIG_PPC64) ? PAGE_OFFSET : TASK_SIZE, .ptdump = {
.note_page = note_page,
.range = ptdump_range,
}
}; };
#ifdef CONFIG_PPC64 ptdump_walk_pgd(&st.ptdump, &init_mm, NULL);
if (!radix_enabled())
st.start_address = KERN_VIRT_START;
#endif
walk_pagetables(&st);
if (st.wx_pages) if (st.wx_pages)
pr_warn("Checked W+X mappings: FAILED, %lu W+X pages found\n", pr_warn("Checked W+X mappings: FAILED, %lu W+X pages found\n",
...@@ -435,12 +352,21 @@ void ptdump_check_wx(void) ...@@ -435,12 +352,21 @@ void ptdump_check_wx(void)
} }
#endif #endif
static int ptdump_init(void) 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;
#endif
populate_markers(); populate_markers();
build_pgtable_complete_mask(); build_pgtable_complete_mask();
debugfs_create_file("kernel_page_tables", 0400, NULL, NULL,
&ptdump_fops); if (IS_ENABLED(CONFIG_PTDUMP_DEBUGFS))
debugfs_create_file("kernel_page_tables", 0400, NULL, NULL, &ptdump_fops);
return 0; return 0;
} }
device_initcall(ptdump_init); device_initcall(ptdump_init);
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment