Message ID | 20171013173214.27300-8-pasha.tatashin@oracle.com |
---|---|
State | Not Applicable |
Delegated to: | David Miller |
Headers | show |
Series | complete deferred page initialization | expand |
On 10/13/2017 08:32 PM, Pavel Tatashin wrote: > During early boot, kasan uses vmemmap_populate() to establish its shadow > memory. But, that interface is intended for struct pages use. > > Because of the current project, vmemmap won't be zeroed during allocation, > but kasan expects that memory to be zeroed. We are adding a new > kasan_map_populate() function to resolve this difference. > > Therefore, we must use a new interface to allocate and map kasan shadow > memory, that also zeroes memory for us. > Nah, we should do the same as with arm64 here. The patch bellow works for me. Could you please make sure that it works for you as well? Just in case. From: Andrey Ryabinin <aryabinin@virtuozzo.com> Subject: x86/mm/kasan: don't use vmemmap_populate() to initialize shadow The kasan shadow is currently mapped using vmemmap_populate() since that provides a semi-convenient way to map pages into init_top_pgt. However, since that no longer zeroes the mapped pages, it is not suitable for kasan, which requires zeroed shadow memory. Add kasan_populate_shadow() interface and use it instead of vmemmap_populate(). Besides, this allows us to take advantage of gigantic pages and use them to populate the shadow, which should save us some memory wasted on page tables and reduce TLB pressure. Signed-off-by: Andrey Ryabinin <aryabinin@virtuozzo.com> --- arch/x86/Kconfig | 2 +- arch/x86/mm/kasan_init_64.c | 141 ++++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 136 insertions(+), 7 deletions(-) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 8153cf40e5fe..e3847e472bd7 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -108,7 +108,7 @@ config X86 select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_HUGE_VMAP if X86_64 || X86_PAE select HAVE_ARCH_JUMP_LABEL - select HAVE_ARCH_KASAN if X86_64 && SPARSEMEM_VMEMMAP + select HAVE_ARCH_KASAN if X86_64 select HAVE_ARCH_KGDB select HAVE_ARCH_MMAP_RND_BITS if MMU select HAVE_ARCH_MMAP_RND_COMPAT_BITS if MMU && COMPAT diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index bc84b73684b7..f8ea02571494 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -3,19 +3,148 @@ #include <linux/bootmem.h> #include <linux/kasan.h> #include <linux/kdebug.h> +#include <linux/memblock.h> #include <linux/mm.h> #include <linux/sched.h> #include <linux/sched/task.h> #include <linux/vmalloc.h> #include <asm/e820/types.h> +#include <asm/pgalloc.h> #include <asm/tlbflush.h> #include <asm/sections.h> #include <asm/pgtable.h> extern struct range pfn_mapped[E820_MAX_ENTRIES]; -static int __init map_range(struct range *range) +static __init void *early_alloc(size_t size, int nid) +{ + return memblock_virt_alloc_try_nid_nopanic(size, size, + __pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid); +} + +static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr, + unsigned long end, int nid) +{ + pte_t *pte; + + if (pmd_none(*pmd)) { + void *p; + + if (boot_cpu_has(X86_FEATURE_PSE) && + ((end - addr) == PMD_SIZE) && + IS_ALIGNED(addr, PMD_SIZE)) { + p = early_alloc(PMD_SIZE, nid); + if (p && pmd_set_huge(pmd, __pa(p), PAGE_KERNEL)) + return; + else if (p) + memblock_free(__pa(p), PMD_SIZE); + } + + p = early_alloc(PAGE_SIZE, nid); + pmd_populate_kernel(&init_mm, pmd, p); + } + + pte = pte_offset_kernel(pmd, addr); + do { + pte_t entry; + void *p; + + if (!pte_none(*pte)) + continue; + + p = early_alloc(PAGE_SIZE, nid); + entry = pfn_pte(PFN_DOWN(__pa(p)), PAGE_KERNEL); + set_pte_at(&init_mm, addr, pte, entry); + } while (pte++, addr += PAGE_SIZE, addr != end); +} + + +static void __init kasan_populate_pud(pud_t *pud, unsigned long addr, + unsigned long end, int nid) +{ + pmd_t *pmd; + unsigned long next; + + if (pud_none(*pud)) { + void *p; + + if (boot_cpu_has(X86_FEATURE_GBPAGES) && + ((end - addr) == PUD_SIZE) && + IS_ALIGNED(addr, PUD_SIZE)) { + p = early_alloc(PUD_SIZE, nid); + if (p && pud_set_huge(pud, __pa(p), PAGE_KERNEL)) + return; + else if (p) + memblock_free(__pa(p), PUD_SIZE); + } + + p = early_alloc(PAGE_SIZE, nid); + pud_populate(&init_mm, pud, p); + } + + pmd = pmd_offset(pud, addr); + do { + next = pmd_addr_end(addr, end); + if (!pmd_large(*pmd)) + kasan_populate_pmd(pmd, addr, next, nid); + } while (pmd++, addr = next, addr != end); +} + +static void __init kasan_populate_p4d(p4d_t *p4d, unsigned long addr, + unsigned long end, int nid) +{ + pud_t *pud; + unsigned long next; + + if (p4d_none(*p4d)) { + void *p = early_alloc(PAGE_SIZE, nid); + p4d_populate(&init_mm, p4d, p); + } + + pud = pud_offset(p4d, addr); + do { + next = pud_addr_end(addr, end); + if (!pud_large(*pud)) + kasan_populate_pud(pud, addr, next, nid); + } while (pud++, addr = next, addr != end); +} + +static void __init kasan_populate_pgd(pgd_t *pgd, unsigned long addr, + unsigned long end, int nid) +{ + void *p; + p4d_t *p4d; + unsigned long next; + + if (pgd_none(*pgd)) { + p = early_alloc(PAGE_SIZE, nid); + pgd_populate(&init_mm, pgd, p); + } + + p4d = p4d_offset(pgd, addr); + do { + next = p4d_addr_end(addr, end); + kasan_populate_p4d(p4d, addr, next, nid); + } while (p4d++, addr = next, addr != end); +} + +static void __init kasan_populate_shadow(unsigned long addr, unsigned long end, + int nid) +{ + pgd_t *pgd; + unsigned long next; + + addr = addr & PAGE_MASK; + end = round_up(end, PAGE_SIZE); + pgd = pgd_offset_k(addr); + do { + next = pgd_addr_end(addr, end); + kasan_populate_pgd(pgd, addr, next, nid); + } while (pgd++, addr = next, addr != end); +} + +static void __init map_range(struct range *range) { unsigned long start; unsigned long end; @@ -23,7 +152,7 @@ static int __init map_range(struct range *range) start = (unsigned long)kasan_mem_to_shadow(pfn_to_kaddr(range->start)); end = (unsigned long)kasan_mem_to_shadow(pfn_to_kaddr(range->end)); - return vmemmap_populate(start, end, NUMA_NO_NODE); + kasan_populate_shadow(start, end, early_pfn_to_nid(range->start)); } static void __init clear_pgds(unsigned long start, @@ -129,16 +258,16 @@ void __init kasan_init(void) if (pfn_mapped[i].end == 0) break; - if (map_range(&pfn_mapped[i])) - panic("kasan: unable to allocate shadow!"); + map_range(&pfn_mapped[i]); } + kasan_populate_zero_shadow( kasan_mem_to_shadow((void *)PAGE_OFFSET + MAXMEM), kasan_mem_to_shadow((void *)__START_KERNEL_map)); - vmemmap_populate((unsigned long)kasan_mem_to_shadow(_stext), + kasan_populate_shadow((unsigned long)kasan_mem_to_shadow(_stext), (unsigned long)kasan_mem_to_shadow(_end), - NUMA_NO_NODE); + early_pfn_to_nid(__pa(_stext))); kasan_populate_zero_shadow(kasan_mem_to_shadow((void *)MODULES_END), (void *)KASAN_SHADOW_END);
Thank you Andrey, I will test this patch. Should it go on top or replace the existing patch in mm-tree? ARM and x86 should be done the same either both as follow-ups or both replace. Pavel -- To unsubscribe from this list: send the line "unsubscribe sparclinux" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On 10/18/2017 08:14 PM, Pavel Tatashin wrote: > Thank you Andrey, I will test this patch. Should it go on top or replace the existing patch in mm-tree? ARM and x86 should be done the same either both as follow-ups or both replace. > It's a replacement of your patch. > Pavel > > -- > To unsubscribe, send a message with 'unsubscribe linux-mm' in > the body to majordomo@kvack.org. For more info on Linux MM, > see: http://www.linux-mm.org/ . > Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a> -- To unsubscribe from this list: send the line "unsubscribe sparclinux" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index bc84b73684b7..9778fec8a5dc 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -15,6 +15,73 @@ extern struct range pfn_mapped[E820_MAX_ENTRIES]; +/* Creates mappings for kasan during early boot. The mapped memory is zeroed */ +static int __meminit kasan_map_populate(unsigned long start, unsigned long end, + int node) +{ + unsigned long addr, pfn, next; + unsigned long long size; + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + int ret; + + ret = vmemmap_populate(start, end, node); + /* + * We might have partially populated memory, so check for no entries, + * and zero only those that actually exist. + */ + for (addr = start; addr < end; addr = next) { + pgd = pgd_offset_k(addr); + if (pgd_none(*pgd)) { + next = pgd_addr_end(addr, end); + continue; + } + + p4d = p4d_offset(pgd, addr); + if (p4d_none(*p4d)) { + next = p4d_addr_end(addr, end); + continue; + } + + pud = pud_offset(p4d, addr); + if (pud_none(*pud)) { + next = pud_addr_end(addr, end); + continue; + } + if (pud_large(*pud)) { + /* This is PUD size page */ + next = pud_addr_end(addr, end); + size = PUD_SIZE; + pfn = pud_pfn(*pud); + } else { + pmd = pmd_offset(pud, addr); + if (pmd_none(*pmd)) { + next = pmd_addr_end(addr, end); + continue; + } + if (pmd_large(*pmd)) { + /* This is PMD size page */ + next = pmd_addr_end(addr, end); + size = PMD_SIZE; + pfn = pmd_pfn(*pmd); + } else { + pte = pte_offset_kernel(pmd, addr); + next = addr + PAGE_SIZE; + if (pte_none(*pte)) + continue; + /* This is base size page */ + size = PAGE_SIZE; + pfn = pte_pfn(*pte); + } + } + memset(phys_to_virt(PFN_PHYS(pfn)), 0, size); + } + return ret; +} + static int __init map_range(struct range *range) { unsigned long start; @@ -23,7 +90,7 @@ static int __init map_range(struct range *range) start = (unsigned long)kasan_mem_to_shadow(pfn_to_kaddr(range->start)); end = (unsigned long)kasan_mem_to_shadow(pfn_to_kaddr(range->end)); - return vmemmap_populate(start, end, NUMA_NO_NODE); + return kasan_map_populate(start, end, NUMA_NO_NODE); } static void __init clear_pgds(unsigned long start, @@ -136,9 +203,9 @@ void __init kasan_init(void) kasan_mem_to_shadow((void *)PAGE_OFFSET + MAXMEM), kasan_mem_to_shadow((void *)__START_KERNEL_map)); - vmemmap_populate((unsigned long)kasan_mem_to_shadow(_stext), - (unsigned long)kasan_mem_to_shadow(_end), - NUMA_NO_NODE); + kasan_map_populate((unsigned long)kasan_mem_to_shadow(_stext), + (unsigned long)kasan_mem_to_shadow(_end), + NUMA_NO_NODE); kasan_populate_zero_shadow(kasan_mem_to_shadow((void *)MODULES_END), (void *)KASAN_SHADOW_END);
During early boot, kasan uses vmemmap_populate() to establish its shadow memory. But, that interface is intended for struct pages use. Because of the current project, vmemmap won't be zeroed during allocation, but kasan expects that memory to be zeroed. We are adding a new kasan_map_populate() function to resolve this difference. Therefore, we must use a new interface to allocate and map kasan shadow memory, that also zeroes memory for us. Signed-off-by: Pavel Tatashin <pasha.tatashin@oracle.com> --- arch/x86/mm/kasan_init_64.c | 75 ++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 71 insertions(+), 4 deletions(-)