diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2021-09-03 20:08:28 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2021-09-03 20:08:28 +0300 |
commit | 14726903c835101cd8d0a703b609305094350d61 (patch) | |
tree | 5cdcf5d2f06ca14be76efd33a4de0e3b28a70de0 /mm/debug_vm_pgtable.c | |
parent | a9c9a6f741cdaa2fa9ba24a790db8d07295761e3 (diff) | |
parent | d5fffc5aff269717a035baa087630adca612a6c4 (diff) | |
download | linux-14726903c835101cd8d0a703b609305094350d61.tar.xz |
Merge branch 'akpm' (patches from Andrew)
Merge misc updates from Andrew Morton:
"173 patches.
Subsystems affected by this series: ia64, ocfs2, block, and mm (debug,
pagecache, gup, swap, shmem, memcg, selftests, pagemap, mremap,
bootmem, sparsemem, vmalloc, kasan, pagealloc, memory-failure,
hugetlb, userfaultfd, vmscan, compaction, mempolicy, memblock,
oom-kill, migration, ksm, percpu, vmstat, and madvise)"
* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (173 commits)
mm/madvise: add MADV_WILLNEED to process_madvise()
mm/vmstat: remove unneeded return value
mm/vmstat: simplify the array size calculation
mm/vmstat: correct some wrong comments
mm/percpu,c: remove obsolete comments of pcpu_chunk_populated()
selftests: vm: add COW time test for KSM pages
selftests: vm: add KSM merging time test
mm: KSM: fix data type
selftests: vm: add KSM merging across nodes test
selftests: vm: add KSM zero page merging test
selftests: vm: add KSM unmerge test
selftests: vm: add KSM merge test
mm/migrate: correct kernel-doc notation
mm: wire up syscall process_mrelease
mm: introduce process_mrelease system call
memblock: make memblock_find_in_range method private
mm/mempolicy.c: use in_task() in mempolicy_slab_node()
mm/mempolicy: unify the create() func for bind/interleave/prefer-many policies
mm/mempolicy: advertise new MPOL_PREFERRED_MANY
mm/hugetlb: add support for mempolicy MPOL_PREFERRED_MANY
...
Diffstat (limited to 'mm/debug_vm_pgtable.c')
-rw-r--r-- | mm/debug_vm_pgtable.c | 918 |
1 files changed, 559 insertions, 359 deletions
diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c index 1c922691aa61..1403639302e4 100644 --- a/mm/debug_vm_pgtable.c +++ b/mm/debug_vm_pgtable.c @@ -29,6 +29,8 @@ #include <linux/start_kernel.h> #include <linux/sched/mm.h> #include <linux/io.h> + +#include <asm/cacheflush.h> #include <asm/pgalloc.h> #include <asm/tlbflush.h> @@ -58,10 +60,41 @@ #define RANDOM_ORVALUE (GENMASK(BITS_PER_LONG - 1, 0) & ~ARCH_SKIP_MASK) #define RANDOM_NZVALUE GENMASK(7, 0) -static void __init pte_basic_tests(unsigned long pfn, int idx) +struct pgtable_debug_args { + struct mm_struct *mm; + struct vm_area_struct *vma; + + pgd_t *pgdp; + p4d_t *p4dp; + pud_t *pudp; + pmd_t *pmdp; + pte_t *ptep; + + p4d_t *start_p4dp; + pud_t *start_pudp; + pmd_t *start_pmdp; + pgtable_t start_ptep; + + unsigned long vaddr; + pgprot_t page_prot; + pgprot_t page_prot_none; + + bool is_contiguous_page; + unsigned long pud_pfn; + unsigned long pmd_pfn; + unsigned long pte_pfn; + + unsigned long fixed_pgd_pfn; + unsigned long fixed_p4d_pfn; + unsigned long fixed_pud_pfn; + unsigned long fixed_pmd_pfn; + unsigned long fixed_pte_pfn; +}; + +static void __init pte_basic_tests(struct pgtable_debug_args *args, int idx) { pgprot_t prot = protection_map[idx]; - pte_t pte = pfn_pte(pfn, prot); + pte_t pte = pfn_pte(args->fixed_pte_pfn, prot); unsigned long val = idx, *ptr = &val; pr_debug("Validating PTE basic (%pGv)\n", ptr); @@ -86,53 +119,63 @@ static void __init pte_basic_tests(unsigned long pfn, int idx) WARN_ON(!pte_dirty(pte_wrprotect(pte_mkdirty(pte)))); } -static void __init pte_advanced_tests(struct mm_struct *mm, - struct vm_area_struct *vma, pte_t *ptep, - unsigned long pfn, unsigned long vaddr, - pgprot_t prot) +static void __init pte_advanced_tests(struct pgtable_debug_args *args) { + struct page *page; pte_t pte; /* * Architectures optimize set_pte_at by avoiding TLB flush. * This requires set_pte_at to be not used to update an * existing pte entry. Clear pte before we do set_pte_at + * + * flush_dcache_page() is called after set_pte_at() to clear + * PG_arch_1 for the page on ARM64. The page flag isn't cleared + * when it's released and page allocation check will fail when + * the page is allocated again. For architectures other than ARM64, + * the unexpected overhead of cache flushing is acceptable. */ + page = (args->pte_pfn != ULONG_MAX) ? pfn_to_page(args->pte_pfn) : NULL; + if (!page) + return; pr_debug("Validating PTE advanced\n"); - pte = pfn_pte(pfn, prot); - set_pte_at(mm, vaddr, ptep, pte); - ptep_set_wrprotect(mm, vaddr, ptep); - pte = ptep_get(ptep); + pte = pfn_pte(args->pte_pfn, args->page_prot); + set_pte_at(args->mm, args->vaddr, args->ptep, pte); + flush_dcache_page(page); + ptep_set_wrprotect(args->mm, args->vaddr, args->ptep); + pte = ptep_get(args->ptep); WARN_ON(pte_write(pte)); - ptep_get_and_clear(mm, vaddr, ptep); - pte = ptep_get(ptep); + ptep_get_and_clear(args->mm, args->vaddr, args->ptep); + pte = ptep_get(args->ptep); WARN_ON(!pte_none(pte)); - pte = pfn_pte(pfn, prot); + pte = pfn_pte(args->pte_pfn, args->page_prot); pte = pte_wrprotect(pte); pte = pte_mkclean(pte); - set_pte_at(mm, vaddr, ptep, pte); + set_pte_at(args->mm, args->vaddr, args->ptep, pte); + flush_dcache_page(page); pte = pte_mkwrite(pte); pte = pte_mkdirty(pte); - ptep_set_access_flags(vma, vaddr, ptep, pte, 1); - pte = ptep_get(ptep); + ptep_set_access_flags(args->vma, args->vaddr, args->ptep, pte, 1); + pte = ptep_get(args->ptep); WARN_ON(!(pte_write(pte) && pte_dirty(pte))); - ptep_get_and_clear_full(mm, vaddr, ptep, 1); - pte = ptep_get(ptep); + ptep_get_and_clear_full(args->mm, args->vaddr, args->ptep, 1); + pte = ptep_get(args->ptep); WARN_ON(!pte_none(pte)); - pte = pfn_pte(pfn, prot); + pte = pfn_pte(args->pte_pfn, args->page_prot); pte = pte_mkyoung(pte); - set_pte_at(mm, vaddr, ptep, pte); - ptep_test_and_clear_young(vma, vaddr, ptep); - pte = ptep_get(ptep); + set_pte_at(args->mm, args->vaddr, args->ptep, pte); + flush_dcache_page(page); + ptep_test_and_clear_young(args->vma, args->vaddr, args->ptep); + pte = ptep_get(args->ptep); WARN_ON(pte_young(pte)); } -static void __init pte_savedwrite_tests(unsigned long pfn, pgprot_t prot) +static void __init pte_savedwrite_tests(struct pgtable_debug_args *args) { - pte_t pte = pfn_pte(pfn, prot); + pte_t pte = pfn_pte(args->fixed_pte_pfn, args->page_prot_none); if (!IS_ENABLED(CONFIG_NUMA_BALANCING)) return; @@ -143,7 +186,7 @@ static void __init pte_savedwrite_tests(unsigned long pfn, pgprot_t prot) } #ifdef CONFIG_TRANSPARENT_HUGEPAGE -static void __init pmd_basic_tests(unsigned long pfn, int idx) +static void __init pmd_basic_tests(struct pgtable_debug_args *args, int idx) { pgprot_t prot = protection_map[idx]; unsigned long val = idx, *ptr = &val; @@ -153,7 +196,7 @@ static void __init pmd_basic_tests(unsigned long pfn, int idx) return; pr_debug("Validating PMD basic (%pGv)\n", ptr); - pmd = pfn_pmd(pfn, prot); + pmd = pfn_pmd(args->fixed_pmd_pfn, prot); /* * This test needs to be executed after the given page table entry @@ -181,57 +224,70 @@ static void __init pmd_basic_tests(unsigned long pfn, int idx) WARN_ON(!pmd_bad(pmd_mkhuge(pmd))); } -static void __init pmd_advanced_tests(struct mm_struct *mm, - struct vm_area_struct *vma, pmd_t *pmdp, - unsigned long pfn, unsigned long vaddr, - pgprot_t prot, pgtable_t pgtable) +static void __init pmd_advanced_tests(struct pgtable_debug_args *args) { + struct page *page; pmd_t pmd; + unsigned long vaddr = args->vaddr; if (!has_transparent_hugepage()) return; + page = (args->pmd_pfn != ULONG_MAX) ? pfn_to_page(args->pmd_pfn) : NULL; + if (!page) + return; + + /* + * flush_dcache_page() is called after set_pmd_at() to clear + * PG_arch_1 for the page on ARM64. The page flag isn't cleared + * when it's released and page allocation check will fail when + * the page is allocated again. For architectures other than ARM64, + * the unexpected overhead of cache flushing is acceptable. + */ pr_debug("Validating PMD advanced\n"); /* Align the address wrt HPAGE_PMD_SIZE */ vaddr &= HPAGE_PMD_MASK; - pgtable_trans_huge_deposit(mm, pmdp, pgtable); + pgtable_trans_huge_deposit(args->mm, args->pmdp, args->start_ptep); - pmd = pfn_pmd(pfn, prot); - set_pmd_at(mm, vaddr, pmdp, pmd); - pmdp_set_wrprotect(mm, vaddr, pmdp); - pmd = READ_ONCE(*pmdp); + pmd = pfn_pmd(args->pmd_pfn, args->page_prot); + set_pmd_at(args->mm, vaddr, args->pmdp, pmd); + flush_dcache_page(page); + pmdp_set_wrprotect(args->mm, vaddr, args->pmdp); + pmd = READ_ONCE(*args->pmdp); WARN_ON(pmd_write(pmd)); - pmdp_huge_get_and_clear(mm, vaddr, pmdp); - pmd = READ_ONCE(*pmdp); + pmdp_huge_get_and_clear(args->mm, vaddr, args->pmdp); + pmd = READ_ONCE(*args->pmdp); WARN_ON(!pmd_none(pmd)); - pmd = pfn_pmd(pfn, prot); + pmd = pfn_pmd(args->pmd_pfn, args->page_prot); pmd = pmd_wrprotect(pmd); pmd = pmd_mkclean(pmd); - set_pmd_at(mm, vaddr, pmdp, pmd); + set_pmd_at(args->mm, vaddr, args->pmdp, pmd); + flush_dcache_page(page); pmd = pmd_mkwrite(pmd); pmd = pmd_mkdirty(pmd); - pmdp_set_access_flags(vma, vaddr, pmdp, pmd, 1); - pmd = READ_ONCE(*pmdp); + pmdp_set_access_flags(args->vma, vaddr, args->pmdp, pmd, 1); + pmd = READ_ONCE(*args->pmdp); WARN_ON(!(pmd_write(pmd) && pmd_dirty(pmd))); - pmdp_huge_get_and_clear_full(vma, vaddr, pmdp, 1); - pmd = READ_ONCE(*pmdp); + pmdp_huge_get_and_clear_full(args->vma, vaddr, args->pmdp, 1); + pmd = READ_ONCE(*args->pmdp); WARN_ON(!pmd_none(pmd)); - pmd = pmd_mkhuge(pfn_pmd(pfn, prot)); + pmd = pmd_mkhuge(pfn_pmd(args->pmd_pfn, args->page_prot)); pmd = pmd_mkyoung(pmd); - set_pmd_at(mm, vaddr, pmdp, pmd); - pmdp_test_and_clear_young(vma, vaddr, pmdp); - pmd = READ_ONCE(*pmdp); + set_pmd_at(args->mm, vaddr, args->pmdp, pmd); + flush_dcache_page(page); + pmdp_test_and_clear_young(args->vma, vaddr, args->pmdp); + pmd = READ_ONCE(*args->pmdp); WARN_ON(pmd_young(pmd)); /* Clear the pte entries */ - pmdp_huge_get_and_clear(mm, vaddr, pmdp); - pgtable = pgtable_trans_huge_withdraw(mm, pmdp); + pmdp_huge_get_and_clear(args->mm, vaddr, args->pmdp); + pgtable_trans_huge_withdraw(args->mm, args->pmdp); } -static void __init pmd_leaf_tests(unsigned long pfn, pgprot_t prot) +static void __init pmd_leaf_tests(struct pgtable_debug_args *args) { pmd_t pmd; @@ -239,7 +295,7 @@ static void __init pmd_leaf_tests(unsigned long pfn, pgprot_t prot) return; pr_debug("Validating PMD leaf\n"); - pmd = pfn_pmd(pfn, prot); + pmd = pfn_pmd(args->fixed_pmd_pfn, args->page_prot); /* * PMD based THP is a leaf entry. @@ -248,7 +304,7 @@ static void __init pmd_leaf_tests(unsigned long pfn, pgprot_t prot) WARN_ON(!pmd_leaf(pmd)); } -static void __init pmd_savedwrite_tests(unsigned long pfn, pgprot_t prot) +static void __init pmd_savedwrite_tests(struct pgtable_debug_args *args) { pmd_t pmd; @@ -259,13 +315,13 @@ static void __init pmd_savedwrite_tests(unsigned long pfn, pgprot_t prot) return; pr_debug("Validating PMD saved write\n"); - pmd = pfn_pmd(pfn, prot); + pmd = pfn_pmd(args->fixed_pmd_pfn, args->page_prot_none); WARN_ON(!pmd_savedwrite(pmd_mk_savedwrite(pmd_clear_savedwrite(pmd)))); WARN_ON(pmd_savedwrite(pmd_clear_savedwrite(pmd_mk_savedwrite(pmd)))); } #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD -static void __init pud_basic_tests(struct mm_struct *mm, unsigned long pfn, int idx) +static void __init pud_basic_tests(struct pgtable_debug_args *args, int idx) { pgprot_t prot = protection_map[idx]; unsigned long val = idx, *ptr = &val; @@ -275,7 +331,7 @@ static void __init pud_basic_tests(struct mm_struct *mm, unsigned long pfn, int return; pr_debug("Validating PUD basic (%pGv)\n", ptr); - pud = pfn_pud(pfn, prot); + pud = pfn_pud(args->fixed_pud_pfn, prot); /* * This test needs to be executed after the given page table entry @@ -296,7 +352,7 @@ static void __init pud_basic_tests(struct mm_struct *mm, unsigned long pfn, int WARN_ON(pud_dirty(pud_wrprotect(pud_mkclean(pud)))); WARN_ON(!pud_dirty(pud_wrprotect(pud_mkdirty(pud)))); - if (mm_pmd_folded(mm)) + if (mm_pmd_folded(args->mm)) return; /* @@ -306,58 +362,71 @@ static void __init pud_basic_tests(struct mm_struct *mm, unsigned long pfn, int WARN_ON(!pud_bad(pud_mkhuge(pud))); } -static void __init pud_advanced_tests(struct mm_struct *mm, - struct vm_area_struct *vma, pud_t *pudp, - unsigned long pfn, unsigned long vaddr, - pgprot_t prot) +static void __init pud_advanced_tests(struct pgtable_debug_args *args) { + struct page *page; + unsigned long vaddr = args->vaddr; pud_t pud; if (!has_transparent_hugepage()) return; + page = (args->pud_pfn != ULONG_MAX) ? pfn_to_page(args->pud_pfn) : NULL; + if (!page) + return; + + /* + * flush_dcache_page() is called after set_pud_at() to clear + * PG_arch_1 for the page on ARM64. The page flag isn't cleared + * when it's released and page allocation check will fail when + * the page is allocated again. For architectures other than ARM64, + * the unexpected overhead of cache flushing is acceptable. + */ pr_debug("Validating PUD advanced\n"); /* Align the address wrt HPAGE_PUD_SIZE */ vaddr &= HPAGE_PUD_MASK; - pud = pfn_pud(pfn, prot); - set_pud_at(mm, vaddr, pudp, pud); - pudp_set_wrprotect(mm, vaddr, pudp); - pud = READ_ONCE(*pudp); + pud = pfn_pud(args->pud_pfn, args->page_prot); + set_pud_at(args->mm, vaddr, args->pudp, pud); + flush_dcache_page(page); + pudp_set_wrprotect(args->mm, vaddr, args->pudp); + pud = READ_ONCE(*args->pudp); WARN_ON(pud_write(pud)); #ifndef __PAGETABLE_PMD_FOLDED - pudp_huge_get_and_clear(mm, vaddr, pudp); - pud = READ_ONCE(*pudp); + pudp_huge_get_and_clear(args->mm, vaddr, args->pudp); + pud = READ_ONCE(*args->pudp); WARN_ON(!pud_none(pud)); #endif /* __PAGETABLE_PMD_FOLDED */ - pud = pfn_pud(pfn, prot); + pud = pfn_pud(args->pud_pfn, args->page_prot); pud = pud_wrprotect(pud); pud = pud_mkclean(pud); - set_pud_at(mm, vaddr, pudp, pud); + set_pud_at(args->mm, vaddr, args->pudp, pud); + flush_dcache_page(page); pud = pud_mkwrite(pud); pud = pud_mkdirty(pud); - pudp_set_access_flags(vma, vaddr, pudp, pud, 1); - pud = READ_ONCE(*pudp); + pudp_set_access_flags(args->vma, vaddr, args->pudp, pud, 1); + pud = READ_ONCE(*args->pudp); WARN_ON(!(pud_write(pud) && pud_dirty(pud))); #ifndef __PAGETABLE_PMD_FOLDED - pudp_huge_get_and_clear_full(mm, vaddr, pudp, 1); - pud = READ_ONCE(*pudp); + pudp_huge_get_and_clear_full(args->mm, vaddr, args->pudp, 1); + pud = READ_ONCE(*args->pudp); WARN_ON(!pud_none(pud)); #endif /* __PAGETABLE_PMD_FOLDED */ - pud = pfn_pud(pfn, prot); + pud = pfn_pud(args->pud_pfn, args->page_prot); pud = pud_mkyoung(pud); - set_pud_at(mm, vaddr, pudp, pud); - pudp_test_and_clear_young(vma, vaddr, pudp); - pud = READ_ONCE(*pudp); + set_pud_at(args->mm, vaddr, args->pudp, pud); + flush_dcache_page(page); + pudp_test_and_clear_young(args->vma, vaddr, args->pudp); + pud = READ_ONCE(*args->pudp); WARN_ON(pud_young(pud)); - pudp_huge_get_and_clear(mm, vaddr, pudp); + pudp_huge_get_and_clear(args->mm, vaddr, args->pudp); } -static void __init pud_leaf_tests(unsigned long pfn, pgprot_t prot) +static void __init pud_leaf_tests(struct pgtable_debug_args *args) { pud_t pud; @@ -365,7 +434,7 @@ static void __init pud_leaf_tests(unsigned long pfn, pgprot_t prot) return; pr_debug("Validating PUD leaf\n"); - pud = pfn_pud(pfn, prot); + pud = pfn_pud(args->fixed_pud_pfn, args->page_prot); /* * PUD based THP is a leaf entry. */ @@ -373,41 +442,26 @@ static void __init pud_leaf_tests(unsigned long pfn, pgprot_t prot) WARN_ON(!pud_leaf(pud)); } #else /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ -static void __init pud_basic_tests(struct mm_struct *mm, unsigned long pfn, int idx) { } -static void __init pud_advanced_tests(struct mm_struct *mm, - struct vm_area_struct *vma, pud_t *pudp, - unsigned long pfn, unsigned long vaddr, - pgprot_t prot) -{ -} -static void __init pud_leaf_tests(unsigned long pfn, pgprot_t prot) { } +static void __init pud_basic_tests(struct pgtable_debug_args *args, int idx) { } +static void __init pud_advanced_tests(struct pgtable_debug_args *args) { } +static void __init pud_leaf_tests(struct pgtable_debug_args *args) { } #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ #else /* !CONFIG_TRANSPARENT_HUGEPAGE */ -static void __init pmd_basic_tests(unsigned long pfn, int idx) { } -static void __init pud_basic_tests(struct mm_struct *mm, unsigned long pfn, int idx) { } -static void __init pmd_advanced_tests(struct mm_struct *mm, - struct vm_area_struct *vma, pmd_t *pmdp, - unsigned long pfn, unsigned long vaddr, - pgprot_t prot, pgtable_t pgtable) -{ -} -static void __init pud_advanced_tests(struct mm_struct *mm, - struct vm_area_struct *vma, pud_t *pudp, - unsigned long pfn, unsigned long vaddr, - pgprot_t prot) -{ -} -static void __init pmd_leaf_tests(unsigned long pfn, pgprot_t prot) { } -static void __init pud_leaf_tests(unsigned long pfn, pgprot_t prot) { } -static void __init pmd_savedwrite_tests(unsigned long pfn, pgprot_t prot) { } +static void __init pmd_basic_tests(struct pgtable_debug_args *args, int idx) { } +static void __init pud_basic_tests(struct pgtable_debug_args *args, int idx) { } +static void __init pmd_advanced_tests(struct pgtable_debug_args *args) { } +static void __init pud_advanced_tests(struct pgtable_debug_args *args) { } +static void __init pmd_leaf_tests(struct pgtable_debug_args *args) { } +static void __init pud_leaf_tests(struct pgtable_debug_args *args) { } +static void __init pmd_savedwrite_tests(struct pgtable_debug_args *args) { } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP -static void __init pmd_huge_tests(pmd_t *pmdp, unsigned long pfn, pgprot_t prot) +static void __init pmd_huge_tests(struct pgtable_debug_args *args) { pmd_t pmd; - if (!arch_vmap_pmd_supported(prot)) + if (!arch_vmap_pmd_supported(args->page_prot)) return; pr_debug("Validating PMD huge\n"); @@ -415,18 +469,18 @@ static void __init pmd_huge_tests(pmd_t *pmdp, unsigned long pfn, pgprot_t prot) * X86 defined pmd_set_huge() verifies that the given * PMD is not a populated non-leaf entry. */ - WRITE_ONCE(*pmdp, __pmd(0)); - WARN_ON(!pmd_set_huge(pmdp, __pfn_to_phys(pfn), prot)); - WARN_ON(!pmd_clear_huge(pmdp)); - pmd = READ_ONCE(*pmdp); + WRITE_ONCE(*args->pmdp, __pmd(0)); + WARN_ON(!pmd_set_huge(args->pmdp, __pfn_to_phys(args->fixed_pmd_pfn), args->page_prot)); + WARN_ON(!pmd_clear_huge(args->pmdp)); + pmd = READ_ONCE(*args->pmdp); WARN_ON(!pmd_none(pmd)); } -static void __init pud_huge_tests(pud_t *pudp, unsigned long pfn, pgprot_t prot) +static void __init pud_huge_tests(struct pgtable_debug_args *args) { pud_t pud; - if (!arch_vmap_pud_supported(prot)) + if (!arch_vmap_pud_supported(args->page_prot)) return; pr_debug("Validating PUD huge\n"); @@ -434,18 +488,18 @@ static void __init pud_huge_tests(pud_t *pudp, unsigned long pfn, pgprot_t prot) * X86 defined pud_set_huge() verifies that the given * PUD is not a populated non-leaf entry. */ - WRITE_ONCE(*pudp, __pud(0)); - WARN_ON(!pud_set_huge(pudp, __pfn_to_phys(pfn), prot)); - WARN_ON(!pud_clear_huge(pudp)); - pud = READ_ONCE(*pudp); + WRITE_ONCE(*args->pudp, __pud(0)); + WARN_ON(!pud_set_huge(args->pudp, __pfn_to_phys(args->fixed_pud_pfn), args->page_prot)); + WARN_ON(!pud_clear_huge(args->pudp)); + pud = READ_ONCE(*args->pudp); WARN_ON(!pud_none(pud)); } #else /* !CONFIG_HAVE_ARCH_HUGE_VMAP */ -static void __init pmd_huge_tests(pmd_t *pmdp, unsigned long pfn, pgprot_t prot) { } -static void __init pud_huge_tests(pud_t *pudp, unsigned long pfn, pgprot_t prot) { } +static void __init pmd_huge_tests(struct pgtable_debug_args *args) { } +static void __init pud_huge_tests(struct pgtable_debug_args *args) { } #endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ -static void __init p4d_basic_tests(unsigned long pfn, pgprot_t prot) +static void __init p4d_basic_tests(struct pgtable_debug_args *args) { p4d_t p4d; @@ -454,7 +508,7 @@ static void __init p4d_basic_tests(unsigned long pfn, pgprot_t prot) WARN_ON(!p4d_same(p4d, p4d)); } -static void __init pgd_basic_tests(unsigned long pfn, pgprot_t prot) +static void __init pgd_basic_tests(struct pgtable_debug_args *args) { pgd_t pgd; @@ -464,27 +518,26 @@ static void __init pgd_basic_tests(unsigned long pfn, pgprot_t prot) } #ifndef __PAGETABLE_PUD_FOLDED -static void __init pud_clear_tests(struct mm_struct *mm, pud_t *pudp) +static void __init pud_clear_tests(struct pgtable_debug_args *args) { - pud_t pud = READ_ONCE(*pudp); + pud_t pud = READ_ONCE(*args->pudp); - if (mm_pmd_folded(mm)) + if (mm_pmd_folded(args->mm)) return; pr_debug("Validating PUD clear\n"); pud = __pud(pud_val(pud) | RANDOM_ORVALUE); - WRITE_ONCE(*pudp, pud); - pud_clear(pudp); - pud = READ_ONCE(*pudp); + WRITE_ONCE(*args->pudp, pud); + pud_clear(args->pudp); + pud = READ_ONCE(*args->pudp); WARN_ON(!pud_none(pud)); } -static void __init pud_populate_tests(struct mm_struct *mm, pud_t *pudp, - pmd_t *pmdp) +static void __init pud_populate_tests(struct pgtable_debug_args *args) { pud_t pud; - if (mm_pmd_folded(mm)) + if (mm_pmd_folded(args->mm)) return; pr_debug("Validating PUD populate\n"); @@ -492,40 +545,36 @@ static void __init pud_populate_tests(struct mm_struct *mm, pud_t *pudp, * This entry points to next level page table page. * Hence this must not qualify as pud_bad(). */ - pud_populate(mm, pudp, pmdp); - pud = READ_ONCE(*pudp); + pud_populate(args->mm, args->pudp, args->start_pmdp); + pud = READ_ONCE(*args->pudp); WARN_ON(pud_bad(pud)); } #else /* !__PAGETABLE_PUD_FOLDED */ -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) -{ -} +static void __init pud_clear_tests(struct pgtable_debug_args *args) { } +static void __init pud_populate_tests(struct pgtable_debug_args *args) { } #endif /* PAGETABLE_PUD_FOLDED */ #ifndef __PAGETABLE_P4D_FOLDED -static void __init p4d_clear_tests(struct mm_struct *mm, p4d_t *p4dp) +static void __init p4d_clear_tests(struct pgtable_debug_args *args) { - p4d_t p4d = READ_ONCE(*p4dp); + p4d_t p4d = READ_ONCE(*args->p4dp); - if (mm_pud_folded(mm)) + if (mm_pud_folded(args->mm)) return; pr_debug("Validating P4D clear\n"); p4d = __p4d(p4d_val(p4d) | RANDOM_ORVALUE); - WRITE_ONCE(*p4dp, p4d); - p4d_clear(p4dp); - p4d = READ_ONCE(*p4dp); + WRITE_ONCE(*args->p4dp, p4d); + p4d_clear(args->p4dp); + p4d = READ_ONCE(*args->p4dp); WARN_ON(!p4d_none(p4d)); } -static void __init p4d_populate_tests(struct mm_struct *mm, p4d_t *p4dp, - pud_t *pudp) +static void __init p4d_populate_tests(struct pgtable_debug_args *args) { p4d_t p4d; - if (mm_pud_folded(mm)) + if (mm_pud_folded(args->mm)) return; pr_debug("Validating P4D populate\n"); @@ -533,34 +582,33 @@ static void __init p4d_populate_tests(struct mm_struct *mm, p4d_t *p4dp, * 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); + pud_clear(args->pudp); + p4d_clear(args->p4dp); + p4d_populate(args->mm, args->p4dp, args->start_pudp); + p4d = READ_ONCE(*args->p4dp); WARN_ON(p4d_bad(p4d)); } -static void __init pgd_clear_tests(struct mm_struct *mm, pgd_t *pgdp) +static void __init pgd_clear_tests(struct pgtable_debug_args *args) { - pgd_t pgd = READ_ONCE(*pgdp); + pgd_t pgd = READ_ONCE(*(args->pgdp)); - if (mm_p4d_folded(mm)) + if (mm_p4d_folded(args->mm)) return; pr_debug("Validating PGD clear\n"); pgd = __pgd(pgd_val(pgd) | RANDOM_ORVALUE); - WRITE_ONCE(*pgdp, pgd); - pgd_clear(pgdp); - pgd = READ_ONCE(*pgdp); + WRITE_ONCE(*args->pgdp, pgd); + pgd_clear(args->pgdp); + pgd = READ_ONCE(*args->pgdp); WARN_ON(!pgd_none(pgd)); } -static void __init pgd_populate_tests(struct mm_struct *mm, pgd_t *pgdp, - p4d_t *p4dp) +static void __init pgd_populate_tests(struct pgtable_debug_args *args) { pgd_t pgd; - if (mm_p4d_folded(mm)) + if (mm_p4d_folded(args->mm)) return; pr_debug("Validating PGD populate\n"); @@ -568,56 +616,60 @@ static void __init pgd_populate_tests(struct mm_struct *mm, pgd_t *pgdp, * 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); + p4d_clear(args->p4dp); + pgd_clear(args->pgdp); + pgd_populate(args->mm, args->pgdp, args->start_p4dp); + pgd = READ_ONCE(*args->pgdp); WARN_ON(pgd_bad(pgd)); } #else /* !__PAGETABLE_P4D_FOLDED */ -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) -{ -} +static void __init p4d_clear_tests(struct pgtable_debug_args *args) { } +static void __init pgd_clear_tests(struct pgtable_debug_args *args) { } +static void __init p4d_populate_tests(struct pgtable_debug_args *args) { } +static void __init pgd_populate_tests(struct pgtable_debug_args *args) { } #endif /* PAGETABLE_P4D_FOLDED */ -static void __init pte_clear_tests(struct mm_struct *mm, pte_t *ptep, - unsigned long pfn, unsigned long vaddr, - pgprot_t prot) +static void __init pte_clear_tests(struct pgtable_debug_args *args) { - pte_t pte = pfn_pte(pfn, prot); + struct page *page; + pte_t pte = pfn_pte(args->pte_pfn, args->page_prot); + + page = (args->pte_pfn != ULONG_MAX) ? pfn_to_page(args->pte_pfn) : NULL; + if (!page) + return; + /* + * flush_dcache_page() is called after set_pte_at() to clear + * PG_arch_1 for the page on ARM64. The page flag isn't cleared + * when it's released and page allocation check will fail when + * the page is allocated again. For architectures other than ARM64, + * the unexpected overhead of cache flushing is acceptable. + */ pr_debug("Validating PTE clear\n"); #ifndef CONFIG_RISCV pte = __pte(pte_val(pte) | RANDOM_ORVALUE); #endif - set_pte_at(mm, vaddr, ptep, pte); + set_pte_at(args->mm, args->vaddr, args->ptep, pte); + flush_dcache_page(page); barrier(); - pte_clear(mm, vaddr, ptep); - pte = ptep_get(ptep); + pte_clear(args->mm, args->vaddr, args->ptep); + pte = ptep_get(args->ptep); WARN_ON(!pte_none(pte)); } -static void __init pmd_clear_tests(struct mm_struct *mm, pmd_t *pmdp) +static void __init pmd_clear_tests(struct pgtable_debug_args *args) { - pmd_t pmd = READ_ONCE(*pmdp); + pmd_t pmd = READ_ONCE(*args->pmdp); pr_debug("Validating PMD clear\n"); pmd = __pmd(pmd_val(pmd) | RANDOM_ORVALUE); - WRITE_ONCE(*pmdp, pmd); - pmd_clear(pmdp); - pmd = READ_ONCE(*pmdp); + WRITE_ONCE(*args->pmdp, pmd); + pmd_clear(args->pmdp); + pmd = READ_ONCE(*args->pmdp); WARN_ON(!pmd_none(pmd)); } -static void __init pmd_populate_tests(struct mm_struct *mm, pmd_t *pmdp, - pgtable_t pgtable) +static void __init pmd_populate_tests(struct pgtable_debug_args *args) { pmd_t pmd; @@ -626,14 +678,14 @@ static void __init pmd_populate_tests(struct mm_struct *mm, pmd_t *pmdp, * This entry points to next level page table page. * Hence this must not qualify as pmd_bad(). */ - pmd_populate(mm, pmdp, pgtable); - pmd = READ_ONCE(*pmdp); + pmd_populate(args->mm, args->pmdp, args->start_ptep); + pmd = READ_ONCE(*args->pmdp); WARN_ON(pmd_bad(pmd)); } -static void __init pte_special_tests(unsigned long pfn, pgprot_t prot) +static void __init pte_special_tests(struct pgtable_debug_args *args) { - pte_t pte = pfn_pte(pfn, prot); + pte_t pte = pfn_pte(args->fixed_pte_pfn, args->page_prot); if (!IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL)) return; @@ -642,9 +694,9 @@ static void __init pte_special_tests(unsigned long pfn, pgprot_t prot) WARN_ON(!pte_special(pte_mkspecial(pte))); } -static void __init pte_protnone_tests(unsigned long pfn, pgprot_t prot) +static void __init pte_protnone_tests(struct pgtable_debug_args *args) { - pte_t pte = pfn_pte(pfn, prot); + pte_t pte = pfn_pte(args->fixed_pte_pfn, args->page_prot_none); if (!IS_ENABLED(CONFIG_NUMA_BALANCING)) return; @@ -655,7 +707,7 @@ static void __init pte_protnone_tests(unsigned long pfn, pgprot_t prot) } #ifdef CONFIG_TRANSPARENT_HUGEPAGE -static void __init pmd_protnone_tests(unsigned long pfn, pgprot_t prot) +static void __init pmd_protnone_tests(struct pgtable_debug_args *args) { pmd_t pmd; @@ -666,25 +718,25 @@ static void __init pmd_protnone_tests(unsigned long pfn, pgprot_t prot) return; pr_debug("Validating PMD protnone\n"); - pmd = pmd_mkhuge(pfn_pmd(pfn, prot)); + pmd = pmd_mkhuge(pfn_pmd(args->fixed_pmd_pfn, args->page_prot_none)); WARN_ON(!pmd_protnone(pmd)); WARN_ON(!pmd_present(pmd)); } #else /* !CONFIG_TRANSPARENT_HUGEPAGE */ -static void __init pmd_protnone_tests(unsigned long pfn, pgprot_t prot) { } +static void __init pmd_protnone_tests(struct pgtable_debug_args *args) { } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #ifdef CONFIG_ARCH_HAS_PTE_DEVMAP -static void __init pte_devmap_tests(unsigned long pfn, pgprot_t prot) +static void __init pte_devmap_tests(struct pgtable_debug_args *args) { - pte_t pte = pfn_pte(pfn, prot); + pte_t pte = pfn_pte(args->fixed_pte_pfn, args->page_prot); pr_debug("Validating PTE devmap\n"); WARN_ON(!pte_devmap(pte_mkdevmap(pte))); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE -static void __init pmd_devmap_tests(unsigned long pfn, pgprot_t prot) +static void __init pmd_devmap_tests(struct pgtable_debug_args *args) { pmd_t pmd; @@ -692,12 +744,12 @@ static void __init pmd_devmap_tests(unsigned long pfn, pgprot_t prot) return; pr_debug("Validating PMD devmap\n"); - pmd = pfn_pmd(pfn, prot); + pmd = pfn_pmd(args->fixed_pmd_pfn, args->page_prot); WARN_ON(!pmd_devmap(pmd_mkdevmap(pmd))); } #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD -static void __init pud_devmap_tests(unsigned long pfn, pgprot_t prot) +static void __init pud_devmap_tests(struct pgtable_debug_args *args) { pud_t pud; @@ -705,25 +757,25 @@ static void __init pud_devmap_tests(unsigned long pfn, pgprot_t prot) return; pr_debug("Validating PUD devmap\n"); - pud = pfn_pud(pfn, prot); + pud = pfn_pud(args->fixed_pud_pfn, args->page_prot); WARN_ON(!pud_devmap(pud_mkdevmap(pud))); } #else /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ -static void __init pud_devmap_tests(unsigned long pfn, pgprot_t prot) { } +static void __init pud_devmap_tests(struct pgtable_debug_args *args) { } #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ #else /* CONFIG_TRANSPARENT_HUGEPAGE */ -static void __init pmd_devmap_tests(unsigned long pfn, pgprot_t prot) { } -static void __init pud_devmap_tests(unsigned long pfn, pgprot_t prot) { } +static void __init pmd_devmap_tests(struct pgtable_debug_args *args) { } +static void __init pud_devmap_tests(struct pgtable_debug_args *args) { } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #else -static void __init pte_devmap_tests(unsigned long pfn, pgprot_t prot) { } -static void __init pmd_devmap_tests(unsigned long pfn, pgprot_t prot) { } -static void __init pud_devmap_tests(unsigned long pfn, pgprot_t prot) { } +static void __init pte_devmap_tests(struct pgtable_debug_args *args) { } +static void __init pmd_devmap_tests(struct pgtable_debug_args *args) { } +static void __init pud_devmap_tests(struct pgtable_debug_args *args) { } #endif /* CONFIG_ARCH_HAS_PTE_DEVMAP */ -static void __init pte_soft_dirty_tests(unsigned long pfn, pgprot_t prot) +static void __init pte_soft_dirty_tests(struct pgtable_debug_args *args) { - pte_t pte = pfn_pte(pfn, prot); + pte_t pte = pfn_pte(args->fixed_pte_pfn, args->page_prot); if (!IS_ENABLED(CONFIG_MEM_SOFT_DIRTY)) return; @@ -733,9 +785,9 @@ static void __init pte_soft_dirty_tests(unsigned long pfn, pgprot_t prot) WARN_ON(pte_soft_dirty(pte_clear_soft_dirty(pte))); } -static void __init pte_swap_soft_dirty_tests(unsigned long pfn, pgprot_t prot) +static void __init pte_swap_soft_dirty_tests(struct pgtable_debug_args *args) { - pte_t pte = pfn_pte(pfn, prot); + pte_t pte = pfn_pte(args->fixed_pte_pfn, args->page_prot); if (!IS_ENABLED(CONFIG_MEM_SOFT_DIRTY)) return; @@ -746,7 +798,7 @@ static void __init pte_swap_soft_dirty_tests(unsigned long pfn, pgprot_t prot) } #ifdef CONFIG_TRANSPARENT_HUGEPAGE -static void __init pmd_soft_dirty_tests(unsigned long pfn, pgprot_t prot) +static void __init pmd_soft_dirty_tests(struct pgtable_debug_args *args) { pmd_t pmd; @@ -757,12 +809,12 @@ static void __init pmd_soft_dirty_tests(unsigned long pfn, pgprot_t prot) return; pr_debug("Validating PMD soft dirty\n"); - pmd = pfn_pmd(pfn, prot); + pmd = pfn_pmd(args->fixed_pmd_pfn, args->page_prot); WARN_ON(!pmd_soft_dirty(pmd_mksoft_dirty(pmd))); WARN_ON(pmd_soft_dirty(pmd_clear_soft_dirty(pmd))); } -static void __init pmd_swap_soft_dirty_tests(unsigned long pfn, pgprot_t prot) +static void __init pmd_swap_soft_dirty_tests(struct pgtable_debug_args *args) { pmd_t pmd; @@ -774,31 +826,29 @@ static void __init pmd_swap_soft_dirty_tests(unsigned long pfn, pgprot_t prot) return; pr_debug("Validating PMD swap soft dirty\n"); - pmd = pfn_pmd(pfn, prot); + pmd = pfn_pmd(args->fixed_pmd_pfn, args->page_prot); WARN_ON(!pmd_swp_soft_dirty(pmd_swp_mksoft_dirty(pmd))); WARN_ON(pmd_swp_soft_dirty(pmd_swp_clear_soft_dirty(pmd))); } #else /* !CONFIG_TRANSPARENT_HUGEPAGE */ -static void __init pmd_soft_dirty_tests(unsigned long pfn, pgprot_t prot) { } -static void __init pmd_swap_soft_dirty_tests(unsigned long pfn, pgprot_t prot) -{ -} +static void __init pmd_soft_dirty_tests(struct pgtable_debug_args *args) { } +static void __init pmd_swap_soft_dirty_tests(struct pgtable_debug_args *args) { } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ -static void __init pte_swap_tests(unsigned long pfn, pgprot_t prot) +static void __init pte_swap_tests(struct pgtable_debug_args *args) { swp_entry_t swp; pte_t pte; pr_debug("Validating PTE swap\n"); - pte = pfn_pte(pfn, prot); + pte = pfn_pte(args->fixed_pte_pfn, args->page_prot); swp = __pte_to_swp_entry(pte); pte = __swp_entry_to_pte(swp); - WARN_ON(pfn != pte_pfn(pte)); + WARN_ON(args->fixed_pte_pfn != pte_pfn(pte)); } #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION -static void __init pmd_swap_tests(unsigned long pfn, pgprot_t prot) +static void __init pmd_swap_tests(struct pgtable_debug_args *args) { swp_entry_t swp; pmd_t pmd; @@ -807,16 +857,16 @@ static void __init pmd_swap_tests(unsigned long pfn, pgprot_t prot) return; pr_debug("Validating PMD swap\n"); - pmd = pfn_pmd(pfn, prot); + pmd = pfn_pmd(args->fixed_pmd_pfn, args->page_prot); swp = __pmd_to_swp_entry(pmd); pmd = __swp_entry_to_pmd(swp); - WARN_ON(pfn != pmd_pfn(pmd)); + WARN_ON(args->fixed_pmd_pfn != pmd_pfn(pmd)); } #else /* !CONFIG_ARCH_ENABLE_THP_MIGRATION */ -static void __init pmd_swap_tests(unsigned long pfn, pgprot_t prot) { } +static void __init pmd_swap_tests(struct pgtable_debug_args *args) { } #endif /* CONFIG_ARCH_ENABLE_THP_MIGRATION */ -static void __init swap_migration_tests(void) +static void __init swap_migration_tests(struct pgtable_debug_args *args) { struct page *page; swp_entry_t swp; @@ -824,19 +874,18 @@ static void __init swap_migration_tests(void) if (!IS_ENABLED(CONFIG_MIGRATION)) return; - pr_debug("Validating swap migration\n"); /* * swap_migration_tests() requires a dedicated page as it needs to * be locked before creating a migration entry from it. Locking the * page that actually maps kernel text ('start_kernel') can be real - * problematic. Lets allocate a dedicated page explicitly for this - * purpose that will be freed subsequently. + * problematic. Lets use the allocated page explicitly for this + * purpose. */ - page = alloc_page(GFP_KERNEL); - if (!page) { - pr_err("page allocation failed\n"); + page = (args->pte_pfn != ULONG_MAX) ? pfn_to_page(args->pte_pfn) : NULL; + if (!page) return; - } + + pr_debug("Validating swap migration\n"); /* * make_migration_entry() expects given page to be @@ -855,11 +904,10 @@ static void __init swap_migration_tests(void) WARN_ON(!is_migration_entry(swp)); WARN_ON(is_writable_migration_entry(swp)); __ClearPageLocked(page); - __free_page(page); } #ifdef CONFIG_HUGETLB_PAGE -static void __init hugetlb_basic_tests(unsigned long pfn, pgprot_t prot) +static void __init hugetlb_basic_tests(struct pgtable_debug_args *args) { struct page *page; pte_t pte; @@ -869,25 +917,25 @@ static void __init hugetlb_basic_tests(unsigned long pfn, pgprot_t prot) * Accessing the page associated with the pfn is safe here, * as it was previously derived from a real kernel symbol. */ - page = pfn_to_page(pfn); - pte = mk_huge_pte(page, prot); + page = pfn_to_page(args->fixed_pmd_pfn); + pte = mk_huge_pte(page, args->page_prot); WARN_ON(!huge_pte_dirty(huge_pte_mkdirty(pte))); WARN_ON(!huge_pte_write(huge_pte_mkwrite(huge_pte_wrprotect(pte)))); WARN_ON(huge_pte_write(huge_pte_wrprotect(huge_pte_mkwrite(pte)))); #ifdef CONFIG_ARCH_WANT_GENERAL_HUGETLB - pte = pfn_pte(pfn, prot); + pte = pfn_pte(args->fixed_pmd_pfn, args->page_prot); WARN_ON(!pte_huge(pte_mkhuge(pte))); #endif /* CONFIG_ARCH_WANT_GENERAL_HUGETLB */ } #else /* !CONFIG_HUGETLB_PAGE */ -static void __init hugetlb_basic_tests(unsigned long pfn, pgprot_t prot) { } +static void __init hugetlb_basic_tests(struct pgtable_debug_args *args) { } #endif /* CONFIG_HUGETLB_PAGE */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE -static void __init pmd_thp_tests(unsigned long pfn, pgprot_t prot) +static void __init pmd_thp_tests(struct pgtable_debug_args *args) { pmd_t pmd; @@ -906,7 +954,7 @@ static void __init pmd_thp_tests(unsigned long pfn, pgprot_t prot) * needs to return true. pmd_present() should be true whenever * pmd_trans_huge() returns true. */ - pmd = pfn_pmd(pfn, prot); + pmd = pfn_pmd(args->fixed_pmd_pfn, args->page_prot); WARN_ON(!pmd_trans_huge(pmd_mkhuge(pmd))); #ifndef __HAVE_ARCH_PMDP_INVALIDATE @@ -916,7 +964,7 @@ static void __init pmd_thp_tests(unsigned long pfn, pgprot_t prot) } #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD -static void __init pud_thp_tests(unsigned long pfn, pgprot_t prot) +static void __init pud_thp_tests(struct pgtable_debug_args *args) { pud_t pud; @@ -924,7 +972,7 @@ static void __init pud_thp_tests(unsigned long pfn, pgprot_t prot) return; pr_debug("Validating PUD based THP\n"); - pud = pfn_pud(pfn, prot); + pud = pfn_pud(args->fixed_pud_pfn, args->page_prot); WARN_ON(!pud_trans_huge(pud_mkhuge(pud))); /* @@ -936,11 +984,11 @@ static void __init pud_thp_tests(unsigned long pfn, pgprot_t prot) */ } #else /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ -static void __init pud_thp_tests(unsigned long pfn, pgprot_t prot) { } +static void __init pud_thp_tests(struct pgtable_debug_args *args) { } #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ #else /* !CONFIG_TRANSPARENT_HUGEPAGE */ -static void __init pmd_thp_tests(unsigned long pfn, pgprot_t prot) { } -static void __init pud_thp_tests(unsigned long pfn, pgprot_t prot) { } +static void __init pmd_thp_tests(struct pgtable_debug_args *args) { } +static void __init pud_thp_tests(struct pgtable_debug_args *args) { } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static unsigned long __init get_random_vaddr(void) @@ -955,43 +1003,179 @@ static unsigned long __init get_random_vaddr(void) return random_vaddr; } -static int __init debug_vm_pgtable(void) +static void __init destroy_args(struct pgtable_debug_args *args) { - struct vm_area_struct *vma; - 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, protnone; - phys_addr_t paddr; - unsigned long vaddr, pte_aligned, pmd_aligned; - unsigned long pud_aligned, p4d_aligned, pgd_aligned; - spinlock_t *ptl = NULL; - int idx; + struct page *page = NULL; + + /* Free (huge) page */ + if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && + IS_ENABLED(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) && + has_transparent_hugepage() && + args->pud_pfn != ULONG_MAX) { + if (args->is_contiguous_page) { + free_contig_range(args->pud_pfn, + (1 << (HPAGE_PUD_SHIFT - PAGE_SHIFT))); + } else { + page = pfn_to_page(args->pud_pfn); + __free_pages(page, HPAGE_PUD_SHIFT - PAGE_SHIFT); + } + + args->pud_pfn = ULONG_MAX; + args->pmd_pfn = ULONG_MAX; + args->pte_pfn = ULONG_MAX; + } - 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 1; + if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && + has_transparent_hugepage() && + args->pmd_pfn != ULONG_MAX) { + if (args->is_contiguous_page) { + free_contig_range(args->pmd_pfn, (1 << HPAGE_PMD_ORDER)); + } else { + page = pfn_to_page(args->pmd_pfn); + __free_pages(page, HPAGE_PMD_ORDER); + } + + args->pmd_pfn = ULONG_MAX; + args->pte_pfn = ULONG_MAX; } + if (args->pte_pfn != ULONG_MAX) { + page = pfn_to_page(args->pte_pfn); + __free_pages(page, 0); + + args->pte_pfn = ULONG_MAX; + } + + /* Free page table entries */ + if (args->start_ptep) { + pte_free(args->mm, args->start_ptep); + mm_dec_nr_ptes(args->mm); + } + + if (args->start_pmdp) { + pmd_free(args->mm, args->start_pmdp); + mm_dec_nr_pmds(args->mm); + } + + if (args->start_pudp) { + pud_free(args->mm, args->start_pudp); + mm_dec_nr_puds(args->mm); + } + + if (args->start_p4dp) + p4d_free(args->mm, args->start_p4dp); + + /* Free vma and mm struct */ + if (args->vma) + vm_area_free(args->vma); + + if (args->mm) + mmdrop(args->mm); +} + +static struct page * __init +debug_vm_pgtable_alloc_huge_page(struct pgtable_debug_args *args, int order) +{ + struct page *page = NULL; + +#ifdef CONFIG_CONTIG_ALLOC + if (order >= MAX_ORDER) { + page = alloc_contig_pages((1 << order), GFP_KERNEL, + first_online_node, NULL); + if (page) { + args->is_contiguous_page = true; + return page; + } + } +#endif + + if (order < MAX_ORDER) + page = alloc_pages(GFP_KERNEL, order); + + return page; +} + +static int __init init_args(struct pgtable_debug_args *args) +{ + struct page *page = NULL; + phys_addr_t phys; + int ret = 0; + /* + * Initialize the debugging data. + * * __P000 (or even __S000) will help create page table entries with * PROT_NONE permission as required for pxx_protnone_tests(). */ - protnone = __P000; + memset(args, 0, sizeof(*args)); + args->vaddr = get_random_vaddr(); + args->page_prot = vm_get_page_prot(VMFLAGS); + args->page_prot_none = __P000; + args->is_contiguous_page = false; + args->pud_pfn = ULONG_MAX; + args->pmd_pfn = ULONG_MAX; + args->pte_pfn = ULONG_MAX; + args->fixed_pgd_pfn = ULONG_MAX; + args->fixed_p4d_pfn = ULONG_MAX; + args->fixed_pud_pfn = ULONG_MAX; + args->fixed_pmd_pfn = ULONG_MAX; + args->fixed_pte_pfn = ULONG_MAX; + + /* Allocate mm and vma */ + args->mm = mm_alloc(); + if (!args->mm) { + pr_err("Failed to allocate mm struct\n"); + ret = -ENOMEM; + goto error; + } + + args->vma = vm_area_alloc(args->mm); + if (!args->vma) { + pr_err("Failed to allocate vma\n"); + ret = -ENOMEM; + goto error; + } + + /* + * Allocate page table entries. They will be modified in the tests. + * Lets save the page table entries so that they can be released + * when the tests are completed. + */ + args->pgdp = pgd_offset(args->mm, args->vaddr); + args->p4dp = p4d_alloc(args->mm, args->pgdp, args->vaddr); + if (!args->p4dp) { + pr_err("Failed to allocate p4d entries\n"); + ret = -ENOMEM; + goto error; + } + args->start_p4dp = p4d_offset(args->pgdp, 0UL); + WARN_ON(!args->start_p4dp); + + args->pudp = pud_alloc(args->mm, args->p4dp, args->vaddr); + if (!args->pudp) { + pr_err("Failed to allocate pud entries\n"); + ret = -ENOMEM; + goto error; + } + args->start_pudp = pud_offset(args->p4dp, 0UL); + WARN_ON(!args->start_pudp); + + args->pmdp = pmd_alloc(args->mm, args->pudp, args->vaddr); + if (!args->pmdp) { + pr_err("Failed to allocate pmd entries\n"); + ret = -ENOMEM; + goto error; + } + args->start_pmdp = pmd_offset(args->pudp, 0UL); + WARN_ON(!args->start_pmdp); - vma = vm_area_alloc(mm); - if (!vma) { - pr_err("vma allocation failed\n"); - return 1; + if (pte_alloc(args->mm, args->pmdp)) { + pr_err("Failed to allocate pte entries\n"); + ret = -ENOMEM; + goto error; } + args->start_ptep = pmd_pgtable(READ_ONCE(*args->pmdp)); + WARN_ON(!args->start_ptep); /* * PFN for mapping at PTE level is determined from a standard kernel @@ -1000,40 +1184,65 @@ static int __init debug_vm_pgtable(void) * 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. + * at higher page table levels in some of the tests. */ - paddr = __pa_symbol(&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); + phys = __pa_symbol(&start_kernel); + args->fixed_pgd_pfn = __phys_to_pfn(phys & PGDIR_MASK); + args->fixed_p4d_pfn = __phys_to_pfn(phys & P4D_MASK); + args->fixed_pud_pfn = __phys_to_pfn(phys & PUD_MASK); + args->fixed_pmd_pfn = __phys_to_pfn(phys & PMD_MASK); + args->fixed_pte_pfn = __phys_to_pfn(phys & PAGE_MASK); + WARN_ON(!pfn_valid(args->fixed_pte_pfn)); + /* - * Allocate pgtable_t + * Allocate (huge) pages because some of the tests need to access + * the data in the pages. The corresponding tests will be skipped + * if we fail to allocate (huge) pages. */ - if (pte_alloc(mm, pmdp)) { - pr_err("pgtable allocation failed\n"); - return 1; + if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && + IS_ENABLED(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) && + has_transparent_hugepage()) { + page = debug_vm_pgtable_alloc_huge_page(args, + HPAGE_PUD_SHIFT - PAGE_SHIFT); + if (page) { + args->pud_pfn = page_to_pfn(page); + args->pmd_pfn = args->pud_pfn; + args->pte_pfn = args->pud_pfn; + return 0; + } } - /* - * 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); + if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && + has_transparent_hugepage()) { + page = debug_vm_pgtable_alloc_huge_page(args, HPAGE_PMD_ORDER); + if (page) { + args->pmd_pfn = page_to_pfn(page); + args->pte_pfn = args->pmd_pfn; + return 0; + } + } + + page = alloc_pages(GFP_KERNEL, 0); + if (page) + args->pte_pfn = page_to_pfn(page); + + return 0; + +error: + destroy_args(args); + return ret; +} + +static int __init debug_vm_pgtable(void) +{ + struct pgtable_debug_args args; + spinlock_t *ptl = NULL; + int idx, ret; + + pr_info("Validating architecture page table helpers\n"); + ret = init_args(&args); + if (ret) + return ret; /* * Iterate over the protection_map[] to make sure that all @@ -1042,9 +1251,9 @@ static int __init debug_vm_pgtable(void) * given page table entry. */ for (idx = 0; idx < ARRAY_SIZE(protection_map); idx++) { - pte_basic_tests(pte_aligned, idx); - pmd_basic_tests(pmd_aligned, idx); - pud_basic_tests(mm, pud_aligned, idx); + pte_basic_tests(&args, idx); + pmd_basic_tests(&args, idx); + pud_basic_tests(&args, idx); } /* @@ -1054,79 +1263,70 @@ static int __init debug_vm_pgtable(void) * the above iteration for now to save some test execution * time. */ - p4d_basic_tests(p4d_aligned, prot); - pgd_basic_tests(pgd_aligned, prot); + p4d_basic_tests(&args); + pgd_basic_tests(&args); - pmd_leaf_tests(pmd_aligned, prot); - pud_leaf_tests(pud_aligned, prot); + pmd_leaf_tests(&args); + pud_leaf_tests(&args); - pte_savedwrite_tests(pte_aligned, protnone); - pmd_savedwrite_tests(pmd_aligned, protnone); + pte_savedwrite_tests(&args); + pmd_savedwrite_tests(&args); - pte_special_tests(pte_aligned, prot); - pte_protnone_tests(pte_aligned, protnone); - pmd_protnone_tests(pmd_aligned, protnone); + pte_special_tests(&args); + pte_protnone_tests(&args); + pmd_protnone_tests(&args); - pte_devmap_tests(pte_aligned, prot); - pmd_devmap_tests(pmd_aligned, prot); - pud_devmap_tests(pud_aligned, prot); + pte_devmap_tests(&args); + pmd_devmap_tests(&args); + pud_devmap_tests(&args); - pte_soft_dirty_tests(pte_aligned, prot); - pmd_soft_dirty_tests(pmd_aligned, prot); - pte_swap_soft_dirty_tests(pte_aligned, prot); - pmd_swap_soft_dirty_tests(pmd_aligned, prot); + pte_soft_dirty_tests(&args); + pmd_soft_dirty_tests(&args); + pte_swap_soft_dirty_tests(&args); + pmd_swap_soft_dirty_tests(&args); - pte_swap_tests(pte_aligned, prot); - pmd_swap_tests(pmd_aligned, prot); + pte_swap_tests(&args); + pmd_swap_tests(&args); - swap_migration_tests(); + swap_migration_tests(&args); - pmd_thp_tests(pmd_aligned, prot); - pud_thp_tests(pud_aligned, prot); + pmd_thp_tests(&args); + pud_thp_tests(&args); - hugetlb_basic_tests(pte_aligned, prot); + hugetlb_basic_tests(&args); /* * Page table modifying tests. They need to hold * proper page table lock. */ - ptep = pte_offset_map_lock(mm, pmdp, vaddr, &ptl); - pte_clear_tests(mm, ptep, pte_aligned, vaddr, prot); - pte_advanced_tests(mm, vma, ptep, pte_aligned, vaddr, prot); - pte_unmap_unlock(ptep, ptl); + args.ptep = pte_offset_map_lock(args.mm, args.pmdp, args.vaddr, &ptl); + pte_clear_tests(&args); + pte_advanced_tests(&args); + pte_unmap_unlock(args.ptep, ptl); - ptl = pmd_lock(mm, pmdp); - pmd_clear_tests(mm, pmdp); - pmd_advanced_tests(mm, vma, pmdp, pmd_aligned, vaddr, prot, saved_ptep); - pmd_huge_tests(pmdp, pmd_aligned, prot); - pmd_populate_tests(mm, pmdp, saved_ptep); + ptl = pmd_lock(args.mm, args.pmdp); + pmd_clear_tests(&args); + pmd_advanced_tests(&args); + pmd_huge_tests(&args); + pmd_populate_tests(&args); spin_unlock(ptl); - ptl = pud_lock(mm, pudp); - pud_clear_tests(mm, pudp); - pud_advanced_tests(mm, vma, pudp, pud_aligned, vaddr, prot); - pud_huge_tests(pudp, pud_aligned, prot); - pud_populate_tests(mm, pudp, saved_pmdp); + ptl = pud_lock(args.mm, args.pudp); + pud_clear_tests(&args); + pud_advanced_tests(&args); + pud_huge_tests(&args); + pud_populate_tests(&args); spin_unlock(ptl); - spin_lock(&mm->page_table_lock); - p4d_clear_tests(mm, p4dp); - pgd_clear_tests(mm, pgdp); - p4d_populate_tests(mm, p4dp, saved_pudp); - pgd_populate_tests(mm, pgdp, saved_p4dp); - spin_unlock(&mm->page_table_lock); - - p4d_free(mm, saved_p4dp); - pud_free(mm, saved_pudp); - pmd_free(mm, saved_pmdp); - pte_free(mm, saved_ptep); - - vm_area_free(vma); - mm_dec_nr_puds(mm); - mm_dec_nr_pmds(mm); - mm_dec_nr_ptes(mm); - mmdrop(mm); + spin_lock(&(args.mm->page_table_lock)); + p4d_clear_tests(&args); + pgd_clear_tests(&args); + p4d_populate_tests(&args); + pgd_populate_tests(&args); + spin_unlock(&(args.mm->page_table_lock)); + + destroy_args(&args); return 0; } late_initcall(debug_vm_pgtable); |