This is a note to let you know that I've just added the patch titled
[Variant 3/Meltdown] arm64: kpti: Add ->enable callback to remap swapper using nG mappings
to the 4.15-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git%3Ba=su...
The filename of the patch is: arm64-kpti-add-enable-callback-to-remap-swapper-using-ng-mappings.patch and it can be found in the queue-4.15 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree, please let stable@vger.kernel.org know about it.
From foo@baz Tue Feb 13 17:25:10 CET 2018
From: Will Deacon will.deacon@arm.com Date: Tue, 6 Feb 2018 22:22:50 +0000 Subject: [Variant 3/Meltdown] arm64: kpti: Add ->enable callback to remap swapper using nG mappings
From: Will Deacon will.deacon@arm.com
Commit f992b4dfd58b upstream.
Defaulting to global mappings for kernel space is generally good for performance and appears to be necessary for Cavium ThunderX. If we subsequently decide that we need to enable kpti, then we need to rewrite our existing page table entries to be non-global. This is fiddly, and made worse by the possible use of contiguous mappings, which require a strict break-before-make sequence.
Since the enable callback runs on each online CPU from stop_machine context, we can have all CPUs enter the idmap, where secondaries can wait for the primary CPU to rewrite swapper with its MMU off. It's all fairly horrible, but at least it only runs once.
Tested-by: Marc Zyngier marc.zyngier@arm.com Reviewed-by: Marc Zyngier marc.zyngier@arm.com Signed-off-by: Will Deacon will.deacon@arm.com Signed-off-by: Catalin Marinas catalin.marinas@arm.com Conflicts: arch/arm64/mm/proc.S Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/arm64/include/asm/assembler.h | 4 arch/arm64/kernel/cpufeature.c | 25 ++++ arch/arm64/mm/proc.S | 202 +++++++++++++++++++++++++++++++++++-- 3 files changed, 224 insertions(+), 7 deletions(-)
--- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -489,6 +489,10 @@ alternative_else_nop_endif #endif .endm
+ .macro pte_to_phys, phys, pte + and \phys, \pte, #(((1 << (48 - PAGE_SHIFT)) - 1) << PAGE_SHIFT) + .endm + /** * Errata workaround prior to disable MMU. Insert an ISB immediately prior * to executing the MSR that will change SCTLR_ELn[M] from a value of 1 to 0. --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -878,6 +878,30 @@ static bool unmap_kernel_at_el0(const st ID_AA64PFR0_CSV3_SHIFT); }
+static int kpti_install_ng_mappings(void *__unused) +{ + typedef void (kpti_remap_fn)(int, int, phys_addr_t); + extern kpti_remap_fn idmap_kpti_install_ng_mappings; + kpti_remap_fn *remap_fn; + + static bool kpti_applied = false; + int cpu = smp_processor_id(); + + if (kpti_applied) + return 0; + + remap_fn = (void *)__pa_symbol(idmap_kpti_install_ng_mappings); + + cpu_install_idmap(); + remap_fn(cpu, num_online_cpus(), __pa_symbol(swapper_pg_dir)); + cpu_uninstall_idmap(); + + if (!cpu) + kpti_applied = true; + + return 0; +} + static int __init parse_kpti(char *str) { bool enabled; @@ -984,6 +1008,7 @@ static const struct arm64_cpu_capabiliti .capability = ARM64_UNMAP_KERNEL_AT_EL0, .def_scope = SCOPE_SYSTEM, .matches = unmap_kernel_at_el0, + .enable = kpti_install_ng_mappings, }, #endif { --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -153,6 +153,16 @@ ENTRY(cpu_do_switch_mm) ENDPROC(cpu_do_switch_mm)
.pushsection ".idmap.text", "ax" + +.macro __idmap_cpu_set_reserved_ttbr1, tmp1, tmp2 + adrp \tmp1, empty_zero_page + msr ttbr1_el1, \tmp2 + isb + tlbi vmalle1 + dsb nsh + isb +.endm + /* * void idmap_cpu_replace_ttbr1(phys_addr_t new_pgd) * @@ -162,13 +172,7 @@ ENDPROC(cpu_do_switch_mm) ENTRY(idmap_cpu_replace_ttbr1) save_and_disable_daif flags=x2
- adrp x1, empty_zero_page - msr ttbr1_el1, x1 - isb - - tlbi vmalle1 - dsb nsh - isb + __idmap_cpu_set_reserved_ttbr1 x1, x3
msr ttbr1_el1, x0 isb @@ -179,6 +183,190 @@ ENTRY(idmap_cpu_replace_ttbr1) ENDPROC(idmap_cpu_replace_ttbr1) .popsection
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0 + .pushsection ".idmap.text", "ax" + + .macro __idmap_kpti_get_pgtable_ent, type + dc cvac, cur_()\type()p // Ensure any existing dirty + dmb sy // lines are written back before + ldr \type, [cur_()\type()p] // loading the entry + tbz \type, #0, next_()\type // Skip invalid entries + .endm + + .macro __idmap_kpti_put_pgtable_ent_ng, type + orr \type, \type, #PTE_NG // Same bit for blocks and pages + str \type, [cur_()\type()p] // Update the entry and ensure it + dc civac, cur_()\type()p // is visible to all CPUs. + .endm + +/* + * void __kpti_install_ng_mappings(int cpu, int num_cpus, phys_addr_t swapper) + * + * Called exactly once from stop_machine context by each CPU found during boot. + */ +__idmap_kpti_flag: + .long 1 +ENTRY(idmap_kpti_install_ng_mappings) + cpu .req w0 + num_cpus .req w1 + swapper_pa .req x2 + swapper_ttb .req x3 + flag_ptr .req x4 + cur_pgdp .req x5 + end_pgdp .req x6 + pgd .req x7 + cur_pudp .req x8 + end_pudp .req x9 + pud .req x10 + cur_pmdp .req x11 + end_pmdp .req x12 + pmd .req x13 + cur_ptep .req x14 + end_ptep .req x15 + pte .req x16 + + mrs swapper_ttb, ttbr1_el1 + adr flag_ptr, __idmap_kpti_flag + + cbnz cpu, __idmap_kpti_secondary + + /* We're the boot CPU. Wait for the others to catch up */ + sevl +1: wfe + ldaxr w18, [flag_ptr] + eor w18, w18, num_cpus + cbnz w18, 1b + + /* We need to walk swapper, so turn off the MMU. */ + pre_disable_mmu_workaround + mrs x18, sctlr_el1 + bic x18, x18, #SCTLR_ELx_M + msr sctlr_el1, x18 + isb + + /* Everybody is enjoying the idmap, so we can rewrite swapper. */ + /* PGD */ + mov cur_pgdp, swapper_pa + add end_pgdp, cur_pgdp, #(PTRS_PER_PGD * 8) +do_pgd: __idmap_kpti_get_pgtable_ent pgd + tbnz pgd, #1, walk_puds + __idmap_kpti_put_pgtable_ent_ng pgd +next_pgd: + add cur_pgdp, cur_pgdp, #8 + cmp cur_pgdp, end_pgdp + b.ne do_pgd + + /* Publish the updated tables and nuke all the TLBs */ + dsb sy + tlbi vmalle1is + dsb ish + isb + + /* We're done: fire up the MMU again */ + mrs x18, sctlr_el1 + orr x18, x18, #SCTLR_ELx_M + msr sctlr_el1, x18 + isb + + /* Set the flag to zero to indicate that we're all done */ + str wzr, [flag_ptr] + ret + + /* PUD */ +walk_puds: + .if CONFIG_PGTABLE_LEVELS > 3 + pte_to_phys cur_pudp, pgd + add end_pudp, cur_pudp, #(PTRS_PER_PUD * 8) +do_pud: __idmap_kpti_get_pgtable_ent pud + tbnz pud, #1, walk_pmds + __idmap_kpti_put_pgtable_ent_ng pud +next_pud: + add cur_pudp, cur_pudp, 8 + cmp cur_pudp, end_pudp + b.ne do_pud + b next_pgd + .else /* CONFIG_PGTABLE_LEVELS <= 3 */ + mov pud, pgd + b walk_pmds +next_pud: + b next_pgd + .endif + + /* PMD */ +walk_pmds: + .if CONFIG_PGTABLE_LEVELS > 2 + pte_to_phys cur_pmdp, pud + add end_pmdp, cur_pmdp, #(PTRS_PER_PMD * 8) +do_pmd: __idmap_kpti_get_pgtable_ent pmd + tbnz pmd, #1, walk_ptes + __idmap_kpti_put_pgtable_ent_ng pmd +next_pmd: + add cur_pmdp, cur_pmdp, #8 + cmp cur_pmdp, end_pmdp + b.ne do_pmd + b next_pud + .else /* CONFIG_PGTABLE_LEVELS <= 2 */ + mov pmd, pud + b walk_ptes +next_pmd: + b next_pud + .endif + + /* PTE */ +walk_ptes: + pte_to_phys cur_ptep, pmd + add end_ptep, cur_ptep, #(PTRS_PER_PTE * 8) +do_pte: __idmap_kpti_get_pgtable_ent pte + __idmap_kpti_put_pgtable_ent_ng pte +next_pte: + add cur_ptep, cur_ptep, #8 + cmp cur_ptep, end_ptep + b.ne do_pte + b next_pmd + + /* Secondary CPUs end up here */ +__idmap_kpti_secondary: + /* Uninstall swapper before surgery begins */ + __idmap_cpu_set_reserved_ttbr1 x18, x17 + + /* Increment the flag to let the boot CPU we're ready */ +1: ldxr w18, [flag_ptr] + add w18, w18, #1 + stxr w17, w18, [flag_ptr] + cbnz w17, 1b + + /* Wait for the boot CPU to finish messing around with swapper */ + sevl +1: wfe + ldxr w18, [flag_ptr] + cbnz w18, 1b + + /* All done, act like nothing happened */ + msr ttbr1_el1, swapper_ttb + isb + ret + + .unreq cpu + .unreq num_cpus + .unreq swapper_pa + .unreq swapper_ttb + .unreq flag_ptr + .unreq cur_pgdp + .unreq end_pgdp + .unreq pgd + .unreq cur_pudp + .unreq end_pudp + .unreq pud + .unreq cur_pmdp + .unreq end_pmdp + .unreq pmd + .unreq cur_ptep + .unreq end_ptep + .unreq pte +ENDPROC(idmap_kpti_install_ng_mappings) + .popsection +#endif + /* * __cpu_setup *
Patches currently in stable-queue which might be from will.deacon@arm.com are
queue-4.15/arm64-make-user_ds-an-inclusive-limit.patch queue-4.15/arm64-mm-remove-pre_ttbr0_update_workaround-for-falkor-erratum-e1003.patch queue-4.15/arm64-uaccess-don-t-bother-eliding-access_ok-checks-in-__-get-put-_user.patch queue-4.15/arm64-cpufeature-pass-capability-structure-to-enable-callback.patch queue-4.15/arm64-uaccess-mask-__user-pointers-for-__arch_-clear-copy_-_user.patch queue-4.15/arm64-mm-add-arm64_kernel_unmapped_at_el0-helper.patch queue-4.15/arm64-entry-reword-comment-about-post_ttbr_update_workaround.patch queue-4.15/arm64-kaslr-put-kernel-vectors-address-in-separate-data-page.patch queue-4.15/arm-arm64-smccc-make-function-identifiers-an-unsigned-quantity.patch queue-4.15/arm64-move-bp-hardening-to-check_and_switch_context.patch queue-4.15/arm-arm64-kvm-advertise-smccc-v1.1.patch queue-4.15/arm64-move-post_ttbr_update_workaround-to-c-code.patch queue-4.15/arm64-turn-on-kpti-only-on-cpus-that-need-it.patch queue-4.15/firmware-psci-expose-psci-conduit.patch queue-4.15/arm64-force-kpti-to-be-disabled-on-cavium-thunderx.patch queue-4.15/arm64-entry-apply-bp-hardening-for-high-priority-synchronous-exceptions.patch queue-4.15/arm64-kpti-fix-the-interaction-between-asid-switching-and-software-pan.patch queue-4.15/firmware-psci-expose-smccc-version-through-psci_ops.patch queue-4.15/arm64-mm-permit-transitioning-from-global-to-non-global-without-bbm.patch queue-4.15/arm64-mm-allocate-asids-in-pairs.patch queue-4.15/arm64-tls-avoid-unconditional-zeroing-of-tpidrro_el0-for-native-tasks.patch queue-4.15/arm64-use-ret-instruction-for-exiting-the-trampoline.patch queue-4.15/arm64-futex-mask-__user-pointers-prior-to-dereference.patch queue-4.15/arm64-entry-explicitly-pass-exception-level-to-kernel_ventry-macro.patch queue-4.15/arm64-implement-branch-predictor-hardening-for-affected-cortex-a-cpus.patch queue-4.15/arm64-kpti-make-use-of-ng-dependent-on-arm64_kernel_unmapped_at_el0.patch queue-4.15/arm-arm64-kvm-add-psci_version-helper.patch queue-4.15/arm64-kill-psci_get_version-as-a-variant-2-workaround.patch queue-4.15/arm64-entry-ensure-branch-through-syscall-table-is-bounded-under-speculation.patch queue-4.15/arm64-mm-use-non-global-mappings-for-kernel-space.patch queue-4.15/arm64-entry-apply-bp-hardening-for-suspicious-interrupts-from-el0.patch queue-4.15/arm64-capabilities-handle-duplicate-entries-for-a-capability.patch queue-4.15/arm64-entry-hook-up-entry-trampoline-to-exception-vectors.patch queue-4.15/arm64-branch-predictor-hardening-for-cavium-thunderx2.patch queue-4.15/arm64-uaccess-prevent-speculative-use-of-the-current-addr_limit.patch queue-4.15/arm64-use-pointer-masking-to-limit-uaccess-speculation.patch queue-4.15/arm64-add-arm_smccc_arch_workaround_1-bp-hardening-support.patch queue-4.15/arm64-erratum-work-around-falkor-erratum-e1003-in-trampoline-code.patch queue-4.15/arm64-mm-fix-and-re-enable-arm64_sw_ttbr0_pan.patch queue-4.15/arm64-mm-invalidate-both-kernel-and-user-asids-when-performing-tlbi.patch queue-4.15/drivers-firmware-expose-psci_get_version-through-psci_ops-structure.patch queue-4.15/arm64-mm-rename-post_ttbr0_update_workaround.patch queue-4.15/arm64-mm-map-entry-trampoline-into-trampoline-and-kernel-page-tables.patch queue-4.15/arm-arm64-kvm-turn-kvm_psci_version-into-a-static-inline.patch queue-4.15/arm-arm64-kvm-implement-psci-1.0-support.patch queue-4.15/arm64-kconfig-reword-unmap_kernel_at_el0-kconfig-entry.patch queue-4.15/arm64-mm-move-asid-from-ttbr0-to-ttbr1.patch queue-4.15/arm64-mm-introduce-ttbr_asid_mask-for-getting-at-the-asid-in-the-ttbr.patch queue-4.15/arm64-kvm-add-smccc_arch_workaround_1-fast-handling.patch queue-4.15/arm64-take-into-account-id_aa64pfr0_el1.csv3.patch queue-4.15/arm64-cputype-add-missing-midr-values-for-cortex-a72-and-cortex-a75.patch queue-4.15/arm64-kvm-report-smccc_arch_workaround_1-bp-hardening-support.patch queue-4.15/arm64-barrier-add-csdb-macros-to-control-data-value-prediction.patch queue-4.15/arm-arm64-smccc-implement-smccc-v1.1-inline-primitive.patch queue-4.15/perf-arm_spe-fail-device-probe-when-arm64_kernel_unmapped_at_el0.patch queue-4.15/arm64-implement-branch-predictor-hardening-for-falkor.patch queue-4.15/arm64-kconfig-add-config_unmap_kernel_at_el0.patch queue-4.15/arm64-idmap-use-awx-flags-for-.idmap.text-.pushsection-directives.patch queue-4.15/arm64-run-enable-method-for-errata-work-arounds-on-late-cpus.patch queue-4.15/arm64-mm-temporarily-disable-arm64_sw_ttbr0_pan.patch queue-4.15/arm64-entry-add-exception-trampoline-page-for-exceptions-from-el0.patch queue-4.15/arm64-kvm-make-psci_version-a-fast-path.patch queue-4.15/arm64-cpufeature-__this_cpu_has_cap-shouldn-t-stop-early.patch queue-4.15/arm64-implement-array_index_mask_nospec.patch queue-4.15/arm64-kpti-add-enable-callback-to-remap-swapper-using-ng-mappings.patch queue-4.15/arm-arm64-kvm-consolidate-the-psci-include-files.patch queue-4.15/arm64-add-skeleton-to-harden-the-branch-predictor-against-aliasing-attacks.patch queue-4.15/arm64-cpu_errata-add-kryo-to-falkor-1003-errata.patch queue-4.15/arm-arm64-kvm-add-smccc-accessors-to-psci-code.patch queue-4.15/arm64-entry-add-fake-cpu-feature-for-unmapping-the-kernel-at-el0.patch queue-4.15/arm64-kvm-use-per-cpu-vector-when-bp-hardening-is-enabled.patch queue-4.15/arm64-cputype-add-midr-values-for-cavium-thunderx2-cpus.patch queue-4.15/arm64-kvm-increment-pc-after-handling-an-smc-trap.patch