This is a note to let you know that I've just added the patch titled x86/mm/pti: Add functions to clone kernel PMDs to the 4.14-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary The filename of the patch is: x86-mm-pti-add-functions-to-clone-kernel-pmds.patch and it can be found in the queue-4.14 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable@xxxxxxxxxxxxxxx> know about it. >From 03f4424f348e8be95eb1bbeba09461cd7b867828 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski <luto@xxxxxxxxxx> Date: Mon, 4 Dec 2017 15:07:42 +0100 Subject: x86/mm/pti: Add functions to clone kernel PMDs From: Andy Lutomirski <luto@xxxxxxxxxx> commit 03f4424f348e8be95eb1bbeba09461cd7b867828 upstream. Provide infrastructure to: - find a kernel PMD for a mapping which must be visible to user space for the entry/exit code to work. - walk an address range and share the kernel PMD with it. This reuses a small part of the original KAISER patches to populate the user space page table. [ tglx: Made it universally usable so it can be used for any kind of shared mapping. Add a mechanism to clear specific bits in the user space visible PMD entry. Folded Andys simplifactions ] Originally-by: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx> Signed-off-by: Andy Lutomirski <luto@xxxxxxxxxx> Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx> Cc: Boris Ostrovsky <boris.ostrovsky@xxxxxxxxxx> Cc: Borislav Petkov <bp@xxxxxxxxx> Cc: Borislav Petkov <bpetkov@xxxxxxx> Cc: Brian Gerst <brgerst@xxxxxxxxx> Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx> Cc: David Laight <David.Laight@xxxxxxxxxx> Cc: Denys Vlasenko <dvlasenk@xxxxxxxxxx> Cc: Eduardo Valentin <eduval@xxxxxxxxxx> Cc: Greg KH <gregkh@xxxxxxxxxxxxxxxxxxx> Cc: H. Peter Anvin <hpa@xxxxxxxxx> Cc: Josh Poimboeuf <jpoimboe@xxxxxxxxxx> Cc: Juergen Gross <jgross@xxxxxxxx> Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx> Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx> Cc: Will Deacon <will.deacon@xxxxxxx> Cc: aliguori@xxxxxxxxxx Cc: daniel.gruss@xxxxxxxxxxxxxx Cc: hughd@xxxxxxxxxx Cc: keescook@xxxxxxxxxx Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx> Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> --- arch/x86/mm/pti.c | 127 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 127 insertions(+) --- a/arch/x86/mm/pti.c +++ b/arch/x86/mm/pti.c @@ -48,6 +48,11 @@ #undef pr_fmt #define pr_fmt(fmt) "Kernel/User page tables isolation: " fmt +/* Backporting helper */ +#ifndef __GFP_NOTRACK +#define __GFP_NOTRACK 0 +#endif + static void __init pti_print_if_insecure(const char *reason) { if (boot_cpu_has_bug(X86_BUG_CPU_INSECURE)) @@ -138,6 +143,128 @@ pgd_t __pti_set_user_pgd(pgd_t *pgdp, pg } /* + * Walk the user copy of the page tables (optionally) trying to allocate + * page table pages on the way down. + * + * Returns a pointer to a P4D on success, or NULL on failure. + */ +static p4d_t *pti_user_pagetable_walk_p4d(unsigned long address) +{ + pgd_t *pgd = kernel_to_user_pgdp(pgd_offset_k(address)); + gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO); + + if (address < PAGE_OFFSET) { + WARN_ONCE(1, "attempt to walk user address\n"); + return NULL; + } + + if (pgd_none(*pgd)) { + unsigned long new_p4d_page = __get_free_page(gfp); + if (!new_p4d_page) + return NULL; + + if (pgd_none(*pgd)) { + set_pgd(pgd, __pgd(_KERNPG_TABLE | __pa(new_p4d_page))); + new_p4d_page = 0; + } + if (new_p4d_page) + free_page(new_p4d_page); + } + BUILD_BUG_ON(pgd_large(*pgd) != 0); + + return p4d_offset(pgd, address); +} + +/* + * Walk the user copy of the page tables (optionally) trying to allocate + * page table pages on the way down. + * + * Returns a pointer to a PMD on success, or NULL on failure. + */ +static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address) +{ + gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO); + p4d_t *p4d = pti_user_pagetable_walk_p4d(address); + pud_t *pud; + + BUILD_BUG_ON(p4d_large(*p4d) != 0); + if (p4d_none(*p4d)) { + unsigned long new_pud_page = __get_free_page(gfp); + if (!new_pud_page) + return NULL; + + if (p4d_none(*p4d)) { + set_p4d(p4d, __p4d(_KERNPG_TABLE | __pa(new_pud_page))); + new_pud_page = 0; + } + if (new_pud_page) + free_page(new_pud_page); + } + + pud = pud_offset(p4d, address); + /* The user page tables do not use large mappings: */ + if (pud_large(*pud)) { + WARN_ON(1); + return NULL; + } + if (pud_none(*pud)) { + unsigned long new_pmd_page = __get_free_page(gfp); + if (!new_pmd_page) + return NULL; + + if (pud_none(*pud)) { + set_pud(pud, __pud(_KERNPG_TABLE | __pa(new_pmd_page))); + new_pmd_page = 0; + } + if (new_pmd_page) + free_page(new_pmd_page); + } + + return pmd_offset(pud, address); +} + +static void __init +pti_clone_pmds(unsigned long start, unsigned long end, pmdval_t clear) +{ + unsigned long addr; + + /* + * Clone the populated PMDs which cover start to end. These PMD areas + * can have holes. + */ + for (addr = start; addr < end; addr += PMD_SIZE) { + pmd_t *pmd, *target_pmd; + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + + pgd = pgd_offset_k(addr); + if (WARN_ON(pgd_none(*pgd))) + return; + p4d = p4d_offset(pgd, addr); + if (WARN_ON(p4d_none(*p4d))) + return; + pud = pud_offset(p4d, addr); + if (pud_none(*pud)) + continue; + pmd = pmd_offset(pud, addr); + if (pmd_none(*pmd)) + continue; + + target_pmd = pti_user_pagetable_walk_pmd(addr); + if (WARN_ON(!target_pmd)) + return; + + /* + * Copy the PMD. That is, the kernelmode and usermode + * tables will share the last-level page tables of this + * address range + */ + *target_pmd = pmd_clear_flags(*pmd, clear); + } +} + +/* * Initialize kernel page table isolation */ void __init pti_init(void) Patches currently in stable-queue which might be from luto@xxxxxxxxxx are queue-4.14/x86-mm-pti-allow-nx-poison-to-be-set-in-p4d-pgd.patch queue-4.14/x86-dumpstack-indicate-in-oops-whether-pti-is-configured-and-enabled.patch queue-4.14/x86-mm-clarify-the-whole-asid-kernel-pcid-user-pcid-naming.patch queue-4.14/x86-mm-abstract-switching-cr3.patch queue-4.14/x86-mm-optimize-restore_cr3.patch queue-4.14/x86-mm-pti-force-entry-through-trampoline-when-pti-active.patch queue-4.14/x86-entry-align-entry-text-section-to-pmd-boundary.patch queue-4.14/x86-mm-64-make-a-full-pgd-entry-size-hole-in-the-memory-map.patch queue-4.14/x86-cpu_entry_area-add-debugstore-entries-to-cpu_entry_area.patch queue-4.14/x86-mm-pti-share-entry-text-pmd.patch queue-4.14/x86-ldt-make-the-ldt-mapping-ro.patch queue-4.14/x86-mm-dump_pagetables-check-user-space-page-table-for-wx-pages.patch queue-4.14/x86-pti-map-the-vsyscall-page-if-needed.patch queue-4.14/x86-mm-pti-disable-global-pages-if-page_table_isolation-y.patch queue-4.14/x86-mm-dump_pagetables-allow-dumping-current-pagetables.patch queue-4.14/x86-mm-pti-add-infrastructure-for-page-table-isolation.patch queue-4.14/x86-cpufeatures-add-x86_bug_cpu_insecure.patch queue-4.14/x86-mm-use-fix-pcid-to-optimize-user-kernel-switches.patch queue-4.14/x86-mm-use-invpcid-for-__native_flush_tlb_single.patch queue-4.14/x86-mm-pti-prepare-the-x86-entry-assembly-code-for-entry-exit-cr3-switching.patch queue-4.14/x86-mm-allow-flushing-for-future-asid-switches.patch queue-4.14/x86-mm-pti-add-kconfig.patch queue-4.14/x86-mm-pti-add-mapping-helper-functions.patch queue-4.14/x86-mm-pti-map-espfix-into-user-space.patch queue-4.14/x86-mm-pti-share-cpu_entry_area-with-user-space-page-tables.patch queue-4.14/x86-mm-pti-add-functions-to-clone-kernel-pmds.patch queue-4.14/x86-pti-add-the-pti-cmdline-option-and-documentation.patch queue-4.14/x86-events-intel-ds-map-debug-buffers-in-cpu_entry_area.patch queue-4.14/x86-mm-pti-allocate-a-separate-user-pgd.patch queue-4.14/x86-pti-put-the-ldt-in-its-own-pgd-if-pti-is-on.patch queue-4.14/x86-mm-pti-populate-user-pgd.patch queue-4.14/x86-mm-dump_pagetables-add-page-table-directory-to-the-debugfs-vfs-hierarchy.patch