new file mode 100644
@@ -0,0 +1,35 @@
+#
+# Feature name: debug-vm-pgtable
+# Kconfig: ARCH_HAS_DEBUG_VM_PGTABLE
+# description: arch supports pgtable tests for semantics compliance
+#
+ -----------------------
+ | arch |status|
+ -----------------------
+ | alpha: | TODO |
+ | arc: | ok |
+ | arm: | TODO |
+ | arm64: | ok |
+ | c6x: | TODO |
+ | csky: | TODO |
+ | h8300: | TODO |
+ | hexagon: | TODO |
+ | ia64: | TODO |
+ | m68k: | TODO |
+ | microblaze: | TODO |
+ | mips: | TODO |
+ | nds32: | TODO |
+ | nios2: | TODO |
+ | openrisc: | TODO |
+ | parisc: | TODO |
+ | powerpc/32: | ok |
+ | powerpc/64: | TODO |
+ | riscv: | TODO |
+ | s390: | TODO |
+ | sh: | TODO |
+ | sparc: | TODO |
+ | um: | TODO |
+ | unicore32: | TODO |
+ | x86: | ok |
+ | xtensa: | TODO |
+ -----------------------
@@ -6,6 +6,7 @@
config ARC
def_bool y
select ARC_TIMERS
+ select ARCH_HAS_DEBUG_VM_PGTABLE
select ARCH_HAS_DMA_PREP_COHERENT
select ARCH_HAS_PTE_SPECIAL
select ARCH_HAS_SETUP_DMA_OPS
@@ -11,6 +11,7 @@ config ARM64
select ACPI_PPTT if ACPI
select ARCH_CLOCKSOURCE_DATA
select ARCH_HAS_DEBUG_VIRTUAL
+ select ARCH_HAS_DEBUG_VM_PGTABLE
select ARCH_HAS_DEVMEM_IS_ALLOWED
select ARCH_HAS_DMA_PREP_COHERENT
select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI
@@ -120,6 +120,7 @@ config PPC
#
select ARCH_32BIT_OFF_T if PPC32
select ARCH_HAS_DEBUG_VIRTUAL
+ select ARCH_HAS_DEBUG_VM_PGTABLE if PPC32
select ARCH_HAS_DEVMEM_IS_ALLOWED
select ARCH_HAS_ELF_RANDOMIZE
select ARCH_HAS_FORTIFY_SOURCE
@@ -61,6 +61,7 @@ config X86
select ARCH_CLOCKSOURCE_INIT
select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI
select ARCH_HAS_DEBUG_VIRTUAL
+ select ARCH_HAS_DEBUG_VM_PGTABLE
select ARCH_HAS_DEVMEM_IS_ALLOWED
select ARCH_HAS_ELF_RANDOMIZE
select ARCH_HAS_FAST_MULTIPLIER
@@ -53,6 +53,12 @@ static inline void sync_initial_page_table(void) { }
struct mm_struct;
+#define mm_p4d_folded mm_p4d_folded
+static inline bool mm_p4d_folded(struct mm_struct *mm)
+{
+ return !pgtable_l5_enabled();
+}
+
void set_pte_vaddr_p4d(p4d_t *p4d_page, unsigned long vaddr, pte_t new_pte);
void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte);
@@ -1208,6 +1208,12 @@ static inline bool arch_has_pfn_modify_check(void)
# define PAGE_KERNEL_EXEC PAGE_KERNEL
#endif
+#ifdef CONFIG_DEBUG_VM_PGTABLE
+extern void debug_vm_pgtable(void);
+#else
+static inline void debug_vm_pgtable(void) { }
+#endif
+
#endif /* !__ASSEMBLY__ */
#ifndef io_remap_pfn_range
@@ -1210,6 +1210,7 @@ static noinline void __init kernel_init_freeable(void)
sched_init_smp();
page_alloc_init_late();
+ debug_vm_pgtable();
/* Initialize page ext after all struct pages are initialized. */
page_ext_init();
@@ -653,6 +653,12 @@ config SCHED_STACK_END_CHECK
data corruption or a sporadic crash at a later stage once the region
is examined. The runtime overhead introduced is minimal.
+config ARCH_HAS_DEBUG_VM_PGTABLE
+ bool
+ help
+ An architecture should select this when it can successfully
+ build and run DEBUG_VM_PGTABLE.
+
config DEBUG_VM
bool "Debug VM"
depends on DEBUG_KERNEL
@@ -688,6 +694,22 @@ config DEBUG_VM_PGFLAGS
If unsure, say N.
+config DEBUG_VM_PGTABLE
+ bool "Debug arch page table for semantics compliance"
+ depends on MMU
+ depends on DEBUG_VM
+ depends on ARCH_HAS_DEBUG_VM_PGTABLE
+ default y
+ help
+ This option provides a debug method which can be used to test
+ architecture page table helper functions on various platforms in
+ verifying if they comply with expected generic MM semantics. This
+ will help architecture code in making sure that any changes or
+ new additions of these helpers still conform to expected
+ semantics of the generic MM.
+
+ If unsure, say N.
+
config ARCH_HAS_DEBUG_VIRTUAL
bool
@@ -86,6 +86,7 @@ obj-$(CONFIG_HWPOISON_INJECT) += hwpoison-inject.o
obj-$(CONFIG_DEBUG_KMEMLEAK) += kmemleak.o
obj-$(CONFIG_DEBUG_KMEMLEAK_TEST) += kmemleak-test.o
obj-$(CONFIG_DEBUG_RODATA_TEST) += rodata_test.o
+obj-$(CONFIG_DEBUG_VM_PGTABLE) += debug_vm_pgtable.o
obj-$(CONFIG_PAGE_OWNER) += page_owner.o
obj-$(CONFIG_CLEANCACHE) += cleancache.o
obj-$(CONFIG_MEMORY_ISOLATION) += page_isolation.o
new file mode 100644
@@ -0,0 +1,388 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * This kernel test validates architecture page table helpers and
+ * accessors and helps in verifying their continued compliance with
+ * expected generic MM semantics.
+ *
+ * Copyright (C) 2019 ARM Ltd.
+ *
+ * Author: Anshuman Khandual <anshuman.khandual@arm.com>
+ */
+#define pr_fmt(fmt) "debug_vm_pgtable: %s: " fmt, __func__
+
+#include <linux/gfp.h>
+#include <linux/highmem.h>
+#include <linux/hugetlb.h>
+#include <linux/kernel.h>
+#include <linux/kconfig.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/mm_types.h>
+#include <linux/module.h>
+#include <linux/pfn_t.h>
+#include <linux/printk.h>
+#include <linux/random.h>
+#include <linux/spinlock.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
+#include <linux/start_kernel.h>
+#include <linux/sched/mm.h>
+#include <asm/pgalloc.h>
+#include <asm/pgtable.h>
+
+/*
+ * Basic operations
+ *
+ * mkold(entry) = An old and not a young entry
+ * mkyoung(entry) = A young and not an old entry
+ * mkdirty(entry) = A dirty and not a clean entry
+ * mkclean(entry) = A clean and not a dirty entry
+ * mkwrite(entry) = A write and not a write protected entry
+ * wrprotect(entry) = A write protected and not a write entry
+ * pxx_bad(entry) = A mapped and non-table entry
+ * pxx_same(entry1, entry2) = Both entries hold the exact same value
+ */
+#define VMFLAGS (VM_READ|VM_WRITE|VM_EXEC)
+
+/*
+ * On s390 platform, the lower 12 bits are used to identify given page table
+ * entry type and for other arch specific requirements. But these bits might
+ * affect the ability to clear entries with pxx_clear(). So while loading up
+ * the entries skip all lower 12 bits in order to accommodate s390 platform.
+ * It does not have affect any other platform.
+ */
+#define RANDOM_ORVALUE (0xfffffffffffff000UL)
+#define RANDOM_NZVALUE (0xff)
+
+static void __init pte_basic_tests(unsigned long pfn, pgprot_t prot)
+{
+ pte_t pte = pfn_pte(pfn, prot);
+
+ WARN_ON(!pte_same(pte, pte));
+ WARN_ON(!pte_young(pte_mkyoung(pte)));
+ WARN_ON(!pte_dirty(pte_mkdirty(pte)));
+ WARN_ON(!pte_write(pte_mkwrite(pte)));
+ WARN_ON(pte_young(pte_mkold(pte)));
+ WARN_ON(pte_dirty(pte_mkclean(pte)));
+ WARN_ON(pte_write(pte_wrprotect(pte)));
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static void __init pmd_basic_tests(unsigned long pfn, pgprot_t prot)
+{
+ pmd_t pmd = pfn_pmd(pfn, prot);
+
+ WARN_ON(!pmd_same(pmd, pmd));
+ WARN_ON(!pmd_young(pmd_mkyoung(pmd)));
+ WARN_ON(!pmd_dirty(pmd_mkdirty(pmd)));
+ WARN_ON(!pmd_write(pmd_mkwrite(pmd)));
+ WARN_ON(pmd_young(pmd_mkold(pmd)));
+ WARN_ON(pmd_dirty(pmd_mkclean(pmd)));
+ WARN_ON(pmd_write(pmd_wrprotect(pmd)));
+ /*
+ * A huge page does not point to next level page table
+ * entry. Hence this must qualify as pmd_bad().
+ */
+ WARN_ON(!pmd_bad(pmd_mkhuge(pmd)));
+}
+
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+static void __init pud_basic_tests(unsigned long pfn, pgprot_t prot)
+{
+ pud_t pud = pfn_pud(pfn, prot);
+
+ WARN_ON(!pud_same(pud, pud));
+ WARN_ON(!pud_young(pud_mkyoung(pud)));
+ WARN_ON(!pud_write(pud_mkwrite(pud)));
+ WARN_ON(pud_write(pud_wrprotect(pud)));
+ WARN_ON(pud_young(pud_mkold(pud)));
+
+ if (mm_pmd_folded(mm) || __is_defined(ARCH_HAS_4LEVEL_HACK))
+ return;
+
+ /*
+ * A huge page does not point to next level page table
+ * entry. Hence this must qualify as pud_bad().
+ */
+ WARN_ON(!pud_bad(pud_mkhuge(pud)));
+}
+#else
+static void __init pud_basic_tests(unsigned long pfn, pgprot_t prot) { }
+#endif
+#else
+static void __init pmd_basic_tests(unsigned long pfn, pgprot_t prot) { }
+static void __init pud_basic_tests(unsigned long pfn, pgprot_t prot) { }
+#endif
+
+static void __init p4d_basic_tests(unsigned long pfn, pgprot_t prot)
+{
+ p4d_t p4d;
+
+ memset(&p4d, RANDOM_NZVALUE, sizeof(p4d_t));
+ WARN_ON(!p4d_same(p4d, p4d));
+}
+
+static void __init pgd_basic_tests(unsigned long pfn, pgprot_t prot)
+{
+ pgd_t pgd;
+
+ memset(&pgd, RANDOM_NZVALUE, sizeof(pgd_t));
+ WARN_ON(!pgd_same(pgd, pgd));
+}
+
+#ifndef __ARCH_HAS_4LEVEL_HACK
+static void __init pud_clear_tests(struct mm_struct *mm, pud_t *pudp)
+{
+ pud_t pud = READ_ONCE(*pudp);
+
+ if (mm_pmd_folded(mm))
+ return;
+
+ pud = __pud(pud_val(pud) | RANDOM_ORVALUE);
+ WRITE_ONCE(*pudp, pud);
+ pud_clear(pudp);
+ pud = READ_ONCE(*pudp);
+ WARN_ON(!pud_none(pud));
+}
+
+static void __init pud_populate_tests(struct mm_struct *mm, pud_t *pudp,
+ pmd_t *pmdp)
+{
+ pud_t pud;
+
+ if (mm_pmd_folded(mm))
+ return;
+ /*
+ * This entry points to next level page table page.
+ * Hence this must not qualify as pud_bad().
+ */
+ pmd_clear(pmdp);
+ pud_clear(pudp);
+ pud_populate(mm, pudp, pmdp);
+ pud = READ_ONCE(*pudp);
+ WARN_ON(pud_bad(pud));
+}
+#else
+static void __init pud_clear_tests(struct mm_struct *mm, pud_t *pudp) { }
+static void __init pud_populate_tests(struct mm_struct *mm, pud_t *pudp,
+ pmd_t *pmdp)
+{
+}
+#endif
+
+#ifndef __ARCH_HAS_5LEVEL_HACK
+static void __init p4d_clear_tests(struct mm_struct *mm, p4d_t *p4dp)
+{
+ p4d_t p4d = READ_ONCE(*p4dp);
+
+ if (mm_pud_folded(mm))
+ return;
+
+ p4d = __p4d(p4d_val(p4d) | RANDOM_ORVALUE);
+ WRITE_ONCE(*p4dp, p4d);
+ p4d_clear(p4dp);
+ p4d = READ_ONCE(*p4dp);
+ WARN_ON(!p4d_none(p4d));
+}
+
+static void __init p4d_populate_tests(struct mm_struct *mm, p4d_t *p4dp,
+ pud_t *pudp)
+{
+ p4d_t p4d;
+
+ if (mm_pud_folded(mm))
+ return;
+
+ /*
+ * This entry points to next level page table page.
+ * Hence this must not qualify as p4d_bad().
+ */
+ pud_clear(pudp);
+ p4d_clear(p4dp);
+ p4d_populate(mm, p4dp, pudp);
+ p4d = READ_ONCE(*p4dp);
+ WARN_ON(p4d_bad(p4d));
+}
+
+static void __init pgd_clear_tests(struct mm_struct *mm, pgd_t *pgdp)
+{
+ pgd_t pgd = READ_ONCE(*pgdp);
+
+ if (mm_p4d_folded(mm))
+ return;
+
+ pgd = __pgd(pgd_val(pgd) | RANDOM_ORVALUE);
+ WRITE_ONCE(*pgdp, pgd);
+ pgd_clear(pgdp);
+ pgd = READ_ONCE(*pgdp);
+ WARN_ON(!pgd_none(pgd));
+}
+
+static void __init pgd_populate_tests(struct mm_struct *mm, pgd_t *pgdp,
+ p4d_t *p4dp)
+{
+ pgd_t pgd;
+
+ if (mm_p4d_folded(mm))
+ return;
+
+ /*
+ * This entry points to next level page table page.
+ * Hence this must not qualify as pgd_bad().
+ */
+ p4d_clear(p4dp);
+ pgd_clear(pgdp);
+ pgd_populate(mm, pgdp, p4dp);
+ pgd = READ_ONCE(*pgdp);
+ WARN_ON(pgd_bad(pgd));
+}
+#else
+static void __init p4d_clear_tests(struct mm_struct *mm, p4d_t *p4dp) { }
+static void __init pgd_clear_tests(struct mm_struct *mm, pgd_t *pgdp) { }
+static void __init p4d_populate_tests(struct mm_struct *mm, p4d_t *p4dp,
+ pud_t *pudp)
+{
+}
+static void __init pgd_populate_tests(struct mm_struct *mm, pgd_t *pgdp,
+ p4d_t *p4dp)
+{
+}
+#endif
+
+static void __init pte_clear_tests(struct mm_struct *mm, pte_t *ptep)
+{
+ pte_t pte = READ_ONCE(*ptep);
+
+ pte = __pte(pte_val(pte) | RANDOM_ORVALUE);
+ WRITE_ONCE(*ptep, pte);
+ pte_clear(mm, 0, ptep);
+ pte = READ_ONCE(*ptep);
+ WARN_ON(!pte_none(pte));
+}
+
+static void __init pmd_clear_tests(struct mm_struct *mm, pmd_t *pmdp)
+{
+ pmd_t pmd = READ_ONCE(*pmdp);
+
+ pmd = __pmd(pmd_val(pmd) | RANDOM_ORVALUE);
+ WRITE_ONCE(*pmdp, pmd);
+ pmd_clear(pmdp);
+ pmd = READ_ONCE(*pmdp);
+ WARN_ON(!pmd_none(pmd));
+}
+
+static void __init pmd_populate_tests(struct mm_struct *mm, pmd_t *pmdp,
+ pgtable_t pgtable)
+{
+ pmd_t pmd;
+
+ /*
+ * This entry points to next level page table page.
+ * Hence this must not qualify as pmd_bad().
+ */
+ pmd_clear(pmdp);
+ pmd_populate(mm, pmdp, pgtable);
+ pmd = READ_ONCE(*pmdp);
+ WARN_ON(pmd_bad(pmd));
+}
+
+static unsigned long __init get_random_vaddr(void)
+{
+ unsigned long random_vaddr, random_pages, total_user_pages;
+
+ total_user_pages = (TASK_SIZE - FIRST_USER_ADDRESS) / PAGE_SIZE;
+
+ random_pages = get_random_long() % total_user_pages;
+ random_vaddr = FIRST_USER_ADDRESS + random_pages * PAGE_SIZE;
+
+ return random_vaddr;
+}
+
+void __init debug_vm_pgtable(void)
+{
+ struct mm_struct *mm;
+ pgd_t *pgdp;
+ p4d_t *p4dp, *saved_p4dp;
+ pud_t *pudp, *saved_pudp;
+ pmd_t *pmdp, *saved_pmdp, pmd;
+ pte_t *ptep;
+ pgtable_t saved_ptep;
+ pgprot_t prot;
+ phys_addr_t paddr;
+ unsigned long vaddr, pte_aligned, pmd_aligned;
+ unsigned long pud_aligned, p4d_aligned, pgd_aligned;
+
+ pr_info("Validating architecture page table helpers\n");
+ prot = vm_get_page_prot(VMFLAGS);
+ vaddr = get_random_vaddr();
+ mm = mm_alloc();
+ if (!mm) {
+ pr_err("mm_struct allocation failed\n");
+ return;
+ }
+
+ /*
+ * PFN for mapping at PTE level is determined from a standard kernel
+ * text symbol. But pfns for higher page table levels are derived by
+ * masking lower bits of this real pfn. These derived pfns might not
+ * exist on the platform but that does not really matter as pfn_pxx()
+ * helpers will still create appropriate entries for the test. This
+ * helps avoid large memory block allocations to be used for mapping
+ * at higher page table levels.
+ */
+ paddr = __pa(&start_kernel);
+
+ pte_aligned = (paddr & PAGE_MASK) >> PAGE_SHIFT;
+ pmd_aligned = (paddr & PMD_MASK) >> PAGE_SHIFT;
+ pud_aligned = (paddr & PUD_MASK) >> PAGE_SHIFT;
+ p4d_aligned = (paddr & P4D_MASK) >> PAGE_SHIFT;
+ pgd_aligned = (paddr & PGDIR_MASK) >> PAGE_SHIFT;
+ WARN_ON(!pfn_valid(pte_aligned));
+
+ pgdp = pgd_offset(mm, vaddr);
+ p4dp = p4d_alloc(mm, pgdp, vaddr);
+ pudp = pud_alloc(mm, p4dp, vaddr);
+ pmdp = pmd_alloc(mm, pudp, vaddr);
+ ptep = pte_alloc_map(mm, pmdp, vaddr);
+
+ /*
+ * Save all the page table page addresses as the page table
+ * entries will be used for testing with random or garbage
+ * values. These saved addresses will be used for freeing
+ * page table pages.
+ */
+ pmd = READ_ONCE(*pmdp);
+ saved_p4dp = p4d_offset(pgdp, 0UL);
+ saved_pudp = pud_offset(p4dp, 0UL);
+ saved_pmdp = pmd_offset(pudp, 0UL);
+ saved_ptep = pmd_pgtable(pmd);
+
+ pte_basic_tests(pte_aligned, prot);
+ pmd_basic_tests(pmd_aligned, prot);
+ pud_basic_tests(pud_aligned, prot);
+ p4d_basic_tests(p4d_aligned, prot);
+ pgd_basic_tests(pgd_aligned, prot);
+
+ pte_clear_tests(mm, ptep);
+ pmd_clear_tests(mm, pmdp);
+ pud_clear_tests(mm, pudp);
+ p4d_clear_tests(mm, p4dp);
+ pgd_clear_tests(mm, pgdp);
+
+ pte_unmap(ptep);
+
+ pmd_populate_tests(mm, pmdp, saved_ptep);
+ pud_populate_tests(mm, pudp, saved_pmdp);
+ p4d_populate_tests(mm, p4dp, saved_pudp);
+ pgd_populate_tests(mm, pgdp, saved_p4dp);
+
+ p4d_free(mm, saved_p4dp);
+ pud_free(mm, saved_pudp);
+ pmd_free(mm, saved_pmdp);
+ pte_free(mm, saved_ptep);
+
+ mm_dec_nr_puds(mm);
+ mm_dec_nr_pmds(mm);
+ mm_dec_nr_ptes(mm);
+ __mmdrop(mm);
+}