February 2018 - Linux-stable-mirror

Patch "x86/mm: Rename flush_tlb_single() and flush_tlb_one() to __flush_tlb_one_[user|kernel]()" has been added to the 4.15-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/mm: Rename flush_tlb_single() and flush_tlb_one() to __flush_tlb_one_[user|kernel]() to the 4.15-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-mm-rename-flush_tlb_single-and-flush_tlb_one-to-__flush_tlb_one_.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(a)vger.kernel.org> know about it. >From 1299ef1d8870d2d9f09a5aadf2f8b2c887c2d033 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski <luto(a)kernel.org> Date: Wed, 31 Jan 2018 08:03:10 -0800 Subject: x86/mm: Rename flush_tlb_single() and flush_tlb_one() to __flush_tlb_one_[user|kernel]() From: Andy Lutomirski <luto(a)kernel.org> commit 1299ef1d8870d2d9f09a5aadf2f8b2c887c2d033 upstream. flush_tlb_single() and flush_tlb_one() sound almost identical, but they really mean "flush one user translation" and "flush one kernel translation". Rename them to flush_tlb_one_user() and flush_tlb_one_kernel() to make the semantics more obvious. [ I was looking at some PTI-related code, and the flush-one-address code is unnecessarily hard to understand because the names of the helpers are uninformative. This came up during PTI review, but no one got around to doing it. ] Signed-off-by: Andy Lutomirski <luto(a)kernel.org> Acked-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Cc: Boris Ostrovsky <boris.ostrovsky(a)oracle.com> Cc: Borislav Petkov <bp(a)alien8.de> Cc: Brian Gerst <brgerst(a)gmail.com> Cc: Dave Hansen <dave.hansen(a)intel.com> Cc: Eduardo Valentin <eduval(a)amazon.com> Cc: Hugh Dickins <hughd(a)google.com> Cc: Josh Poimboeuf <jpoimboe(a)redhat.com> Cc: Juergen Gross <jgross(a)suse.com> Cc: Kees Cook <keescook(a)google.com> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Linux-MM <linux-mm(a)kvack.org> Cc: Rik van Riel <riel(a)redhat.com> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: Will Deacon <will.deacon(a)arm.com> Link: http://lkml.kernel.org/r/3303b02e3c3d049dc5235d5651e0ae6d29a34354.151741437… Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/include/asm/paravirt.h | 4 ++-- arch/x86/include/asm/paravirt_types.h | 2 +- arch/x86/include/asm/pgtable_32.h | 2 +- arch/x86/include/asm/tlbflush.h | 27 ++++++++++++++++++++------- arch/x86/kernel/paravirt.c | 6 +++--- arch/x86/mm/init_64.c | 2 +- arch/x86/mm/ioremap.c | 2 +- arch/x86/mm/kmmio.c | 2 +- arch/x86/mm/pgtable_32.c | 2 +- arch/x86/mm/tlb.c | 6 +++--- arch/x86/platform/uv/tlb_uv.c | 2 +- arch/x86/xen/mmu_pv.c | 6 +++--- include/trace/events/xen.h | 2 +- 13 files changed, 39 insertions(+), 26 deletions(-) --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -297,9 +297,9 @@ static inline void __flush_tlb_global(vo { PVOP_VCALL0(pv_mmu_ops.flush_tlb_kernel); } -static inline void __flush_tlb_single(unsigned long addr) +static inline void __flush_tlb_one_user(unsigned long addr) { - PVOP_VCALL1(pv_mmu_ops.flush_tlb_single, addr); + PVOP_VCALL1(pv_mmu_ops.flush_tlb_one_user, addr); } static inline void flush_tlb_others(const struct cpumask *cpumask, --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -217,7 +217,7 @@ struct pv_mmu_ops { /* TLB operations */ void (*flush_tlb_user)(void); void (*flush_tlb_kernel)(void); - void (*flush_tlb_single)(unsigned long addr); + void (*flush_tlb_one_user)(unsigned long addr); void (*flush_tlb_others)(const struct cpumask *cpus, const struct flush_tlb_info *info); --- a/arch/x86/include/asm/pgtable_32.h +++ b/arch/x86/include/asm/pgtable_32.h @@ -61,7 +61,7 @@ void paging_init(void); #define kpte_clear_flush(ptep, vaddr) \ do { \ pte_clear(&init_mm, (vaddr), (ptep)); \ - __flush_tlb_one((vaddr)); \ + __flush_tlb_one_kernel((vaddr)); \ } while (0) #endif /* !__ASSEMBLY__ */ --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -140,7 +140,7 @@ static inline unsigned long build_cr3_no #else #define __flush_tlb() __native_flush_tlb() #define __flush_tlb_global() __native_flush_tlb_global() -#define __flush_tlb_single(addr) __native_flush_tlb_single(addr) +#define __flush_tlb_one_user(addr) __native_flush_tlb_one_user(addr) #endif static inline bool tlb_defer_switch_to_init_mm(void) @@ -400,7 +400,7 @@ static inline void __native_flush_tlb_gl /* * flush one page in the user mapping */ -static inline void __native_flush_tlb_single(unsigned long addr) +static inline void __native_flush_tlb_one_user(unsigned long addr) { u32 loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid); @@ -437,18 +437,31 @@ static inline void __flush_tlb_all(void) /* * flush one page in the kernel mapping */ -static inline void __flush_tlb_one(unsigned long addr) +static inline void __flush_tlb_one_kernel(unsigned long addr) { count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE); - __flush_tlb_single(addr); + + /* + * If PTI is off, then __flush_tlb_one_user() is just INVLPG or its + * paravirt equivalent. Even with PCID, this is sufficient: we only + * use PCID if we also use global PTEs for the kernel mapping, and + * INVLPG flushes global translations across all address spaces. + * + * If PTI is on, then the kernel is mapped with non-global PTEs, and + * __flush_tlb_one_user() will flush the given address for the current + * kernel address space and for its usermode counterpart, but it does + * not flush it for other address spaces. + */ + __flush_tlb_one_user(addr); if (!static_cpu_has(X86_FEATURE_PTI)) return; /* - * __flush_tlb_single() will have cleared the TLB entry for this ASID, - * but since kernel space is replicated across all, we must also - * invalidate all others. + * See above. We need to propagate the flush to all other address + * spaces. In principle, we only need to propagate it to kernelmode + * address spaces, but the extra bookkeeping we would need is not + * worth it. */ invalidate_other_asid(); } --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -200,9 +200,9 @@ static void native_flush_tlb_global(void __native_flush_tlb_global(); } -static void native_flush_tlb_single(unsigned long addr) +static void native_flush_tlb_one_user(unsigned long addr) { - __native_flush_tlb_single(addr); + __native_flush_tlb_one_user(addr); } struct static_key paravirt_steal_enabled; @@ -401,7 +401,7 @@ struct pv_mmu_ops pv_mmu_ops __ro_after_ .flush_tlb_user = native_flush_tlb, .flush_tlb_kernel = native_flush_tlb_global, - .flush_tlb_single = native_flush_tlb_single, + .flush_tlb_one_user = native_flush_tlb_one_user, .flush_tlb_others = native_flush_tlb_others, .pgd_alloc = __paravirt_pgd_alloc, --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -256,7 +256,7 @@ static void __set_pte_vaddr(pud_t *pud, * It's enough to flush this one mapping. * (PGE mappings get flushed as well) */ - __flush_tlb_one(vaddr); + __flush_tlb_one_kernel(vaddr); } void set_pte_vaddr_p4d(p4d_t *p4d_page, unsigned long vaddr, pte_t new_pte) --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -820,5 +820,5 @@ void __init __early_set_fixmap(enum fixe set_pte(pte, pfn_pte(phys >> PAGE_SHIFT, flags)); else pte_clear(&init_mm, addr, pte); - __flush_tlb_one(addr); + __flush_tlb_one_kernel(addr); } --- a/arch/x86/mm/kmmio.c +++ b/arch/x86/mm/kmmio.c @@ -168,7 +168,7 @@ static int clear_page_presence(struct km return -1; } - __flush_tlb_one(f->addr); + __flush_tlb_one_kernel(f->addr); return 0; } --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -63,7 +63,7 @@ void set_pte_vaddr(unsigned long vaddr, * It's enough to flush this one mapping. * (PGE mappings get flushed as well) */ - __flush_tlb_one(vaddr); + __flush_tlb_one_kernel(vaddr); } unsigned long __FIXADDR_TOP = 0xfffff000; --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -492,7 +492,7 @@ static void flush_tlb_func_common(const * flush that changes context.tlb_gen from 2 to 3. If they get * processed on this CPU in reverse order, we'll see * local_tlb_gen == 1, mm_tlb_gen == 3, and end != TLB_FLUSH_ALL. - * If we were to use __flush_tlb_single() and set local_tlb_gen to + * If we were to use __flush_tlb_one_user() and set local_tlb_gen to * 3, we'd be break the invariant: we'd update local_tlb_gen above * 1 without the full flush that's needed for tlb_gen 2. * @@ -513,7 +513,7 @@ static void flush_tlb_func_common(const addr = f->start; while (addr < f->end) { - __flush_tlb_single(addr); + __flush_tlb_one_user(addr); addr += PAGE_SIZE; } if (local) @@ -660,7 +660,7 @@ static void do_kernel_range_flush(void * /* flush range by one by one 'invlpg' */ for (addr = f->start; addr < f->end; addr += PAGE_SIZE) - __flush_tlb_one(addr); + __flush_tlb_one_kernel(addr); } void flush_tlb_kernel_range(unsigned long start, unsigned long end) --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -299,7 +299,7 @@ static void bau_process_message(struct m local_flush_tlb(); stat->d_alltlb++; } else { - __flush_tlb_single(msg->address); + __flush_tlb_one_user(msg->address); stat->d_onetlb++; } stat->d_requestee++; --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -1300,12 +1300,12 @@ static void xen_flush_tlb(void) preempt_enable(); } -static void xen_flush_tlb_single(unsigned long addr) +static void xen_flush_tlb_one_user(unsigned long addr) { struct mmuext_op *op; struct multicall_space mcs; - trace_xen_mmu_flush_tlb_single(addr); + trace_xen_mmu_flush_tlb_one_user(addr); preempt_disable(); @@ -2370,7 +2370,7 @@ static const struct pv_mmu_ops xen_mmu_o .flush_tlb_user = xen_flush_tlb, .flush_tlb_kernel = xen_flush_tlb, - .flush_tlb_single = xen_flush_tlb_single, + .flush_tlb_one_user = xen_flush_tlb_one_user, .flush_tlb_others = xen_flush_tlb_others, .pgd_alloc = xen_pgd_alloc, --- a/include/trace/events/xen.h +++ b/include/trace/events/xen.h @@ -368,7 +368,7 @@ TRACE_EVENT(xen_mmu_flush_tlb, TP_printk("%s", "") ); -TRACE_EVENT(xen_mmu_flush_tlb_single, +TRACE_EVENT(xen_mmu_flush_tlb_one_user, TP_PROTO(unsigned long addr), TP_ARGS(addr), TP_STRUCT__entry( Patches currently in stable-queue which might be from luto(a)kernel.org are queue-4.15/x86-entry-64-interleave-xor-register-clearing-with-push-instructions.patch queue-4.15/x86-spectre-fix-an-error-message.patch queue-4.15/x86-entry-64-merge-the-pop_c_regs-and-pop_extra_regs-macros-into-a-single-pop_regs-macro.patch queue-4.15/x86-entry-64-remove-the-unused-icebp-macro.patch queue-4.15/kvm-nvmx-set-the-cpu_based_use_msr_bitmaps-if-we-have-a-valid-l02-msr-bitmap.patch queue-4.15/x86-nvmx-properly-set-spec_ctrl-and-pred_cmd-before-merging-msrs.patch queue-4.15/x86-speculation-add-asm-msr-index.h-dependency.patch queue-4.15/x86-entry-64-use-push_and_clean_regs-in-more-cases.patch queue-4.15/selftests-x86-disable-tests-requiring-32-bit-support-on-pure-64-bit-systems.patch queue-4.15/x86-debug-use-ud2-for-warn.patch queue-4.15/x86-speculation-update-speculation-control-microcode-blacklist.patch queue-4.15/x86-entry-64-clear-registers-for-exceptions-interrupts-to-reduce-speculation-attack-surface.patch queue-4.15/x86-speculation-correct-speculation-control-microcode-blacklist-again.patch queue-4.15/x86-entry-64-merge-save_c_regs-and-save_extra_regs-remove-unused-extensions.patch queue-4.15/selftests-x86-do-not-rely-on-int-0x80-in-single_step_syscall.c.patch queue-4.15/selftests-x86-fix-vdso-selftest-segfault-for-vsyscall-none.patch queue-4.15/x86-debug-objtool-annotate-warn-related-ud2-as-reachable.patch queue-4.15/objtool-fix-segfault-in-ignore_unreachable_insn.patch queue-4.15/x86-entry-64-indent-push_and_clear_regs-and-pop_regs-properly.patch queue-4.15/selftests-x86-pkeys-remove-unused-functions.patch queue-4.15/selftests-x86-clean-up-and-document-sscanf-usage.patch queue-4.15/x86-speculation-fix-up-array_index_nospec_mask-asm-constraint.patch queue-4.15/x86-entry-64-clear-extra-registers-beyond-syscall-arguments-to-reduce-speculation-attack-surface.patch queue-4.15/kvm-x86-reduce-retpoline-performance-impact-in-slot_handle_level_range-by-always-inlining-iterator-helper-methods.patch queue-4.15/selftests-x86-do-not-rely-on-int-0x80-in-test_mremap_vdso.c.patch queue-4.15/x86-mm-pti-fix-pti-comment-in-entry_syscall_64.patch queue-4.15/x86-entry-64-get-rid-of-the-alloc_pt_gpregs_on_stack-and-save_and_clear_regs-macros.patch queue-4.15/x86-speculation-clean-up-various-spectre-related-details.patch queue-4.15/x86-entry-64-introduce-the-push_and_clean_regs-macro.patch queue-4.15/revert-x86-speculation-simplify-indirect_branch_prediction_barrier.patch queue-4.15/x86-entry-64-compat-clear-registers-for-compat-syscalls-to-reduce-speculation-attack-surface.patch queue-4.15/x86-mm-rename-flush_tlb_single-and-flush_tlb_one-to-__flush_tlb_one_.patch queue-4.15/x86-entry-64-fix-cr3-restore-in-paranoid_exit.patch

6 years, 10 months

1
0
0 0

Patch "x86/entry/64: Use PUSH_AND_CLEAN_REGS in more cases" has been added to the 4.15-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/entry/64: Use PUSH_AND_CLEAN_REGS in more cases to the 4.15-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-entry-64-use-push_and_clean_regs-in-more-cases.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(a)vger.kernel.org> know about it. >From 30907fd13bb593202574bb20af58d67c70a1ee14 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski <linux(a)dominikbrodowski.net> Date: Sun, 11 Feb 2018 11:49:46 +0100 Subject: x86/entry/64: Use PUSH_AND_CLEAN_REGS in more cases From: Dominik Brodowski <linux(a)dominikbrodowski.net> commit 30907fd13bb593202574bb20af58d67c70a1ee14 upstream. entry_SYSCALL_64_after_hwframe() and nmi() can be converted to use PUSH_AND_CLEAN_REGS instead of opencoded variants thereof. Due to the interleaving, the additional XOR-based clearing of R8 and R9 in entry_SYSCALL_64_after_hwframe() should not have any noticeable negative implications. Suggested-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Dominik Brodowski <linux(a)dominikbrodowski.net> Cc: Andy Lutomirski <luto(a)kernel.org> Cc: Borislav Petkov <bp(a)alien8.de> Cc: Brian Gerst <brgerst(a)gmail.com> Cc: Denys Vlasenko <dvlasenk(a)redhat.com> Cc: H. Peter Anvin <hpa(a)zytor.com> Cc: Josh Poimboeuf <jpoimboe(a)redhat.com> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: dan.j.williams(a)intel.com Link: http://lkml.kernel.org/r/20180211104949.12992-6-linux@dominikbrodowski.net Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/entry/calling.h | 6 ++-- arch/x86/entry/entry_64.S | 65 ++-------------------------------------------- 2 files changed, 6 insertions(+), 65 deletions(-) --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -137,7 +137,7 @@ For 32-bit we have the following convent UNWIND_HINT_REGS offset=\offset .endm - .macro PUSH_AND_CLEAR_REGS + .macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax /* * Push registers and sanitize registers of values that a * speculation attack might otherwise want to exploit. The @@ -147,9 +147,9 @@ For 32-bit we have the following convent */ pushq %rdi /* pt_regs->di */ pushq %rsi /* pt_regs->si */ - pushq %rdx /* pt_regs->dx */ + pushq \rdx /* pt_regs->dx */ pushq %rcx /* pt_regs->cx */ - pushq %rax /* pt_regs->ax */ + pushq \rax /* pt_regs->ax */ pushq %r8 /* pt_regs->r8 */ xorq %r8, %r8 /* nospec r8 */ pushq %r9 /* pt_regs->r9 */ --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -227,35 +227,8 @@ ENTRY(entry_SYSCALL_64) pushq %rcx /* pt_regs->ip */ GLOBAL(entry_SYSCALL_64_after_hwframe) pushq %rax /* pt_regs->orig_ax */ - pushq %rdi /* pt_regs->di */ - pushq %rsi /* pt_regs->si */ - pushq %rdx /* pt_regs->dx */ - pushq %rcx /* pt_regs->cx */ - pushq $-ENOSYS /* pt_regs->ax */ - pushq %r8 /* pt_regs->r8 */ - pushq %r9 /* pt_regs->r9 */ - pushq %r10 /* pt_regs->r10 */ - /* - * Clear extra registers that a speculation attack might - * otherwise want to exploit. Interleave XOR with PUSH - * for better uop scheduling: - */ - xorq %r10, %r10 /* nospec r10 */ - pushq %r11 /* pt_regs->r11 */ - xorq %r11, %r11 /* nospec r11 */ - pushq %rbx /* pt_regs->rbx */ - xorl %ebx, %ebx /* nospec rbx */ - pushq %rbp /* pt_regs->rbp */ - xorl %ebp, %ebp /* nospec rbp */ - pushq %r12 /* pt_regs->r12 */ - xorq %r12, %r12 /* nospec r12 */ - pushq %r13 /* pt_regs->r13 */ - xorq %r13, %r13 /* nospec r13 */ - pushq %r14 /* pt_regs->r14 */ - xorq %r14, %r14 /* nospec r14 */ - pushq %r15 /* pt_regs->r15 */ - xorq %r15, %r15 /* nospec r15 */ - UNWIND_HINT_REGS + + PUSH_AND_CLEAR_REGS rax=$-ENOSYS TRACE_IRQS_OFF @@ -1388,39 +1361,7 @@ ENTRY(nmi) pushq 1*8(%rdx) /* pt_regs->rip */ UNWIND_HINT_IRET_REGS pushq $-1 /* pt_regs->orig_ax */ - pushq %rdi /* pt_regs->di */ - pushq %rsi /* pt_regs->si */ - pushq (%rdx) /* pt_regs->dx */ - pushq %rcx /* pt_regs->cx */ - pushq %rax /* pt_regs->ax */ - /* - * Sanitize registers of values that a speculation attack - * might otherwise want to exploit. The lower registers are - * likely clobbered well before they could be put to use in - * a speculative execution gadget. Interleave XOR with PUSH - * for better uop scheduling: - */ - pushq %r8 /* pt_regs->r8 */ - xorq %r8, %r8 /* nospec r8 */ - pushq %r9 /* pt_regs->r9 */ - xorq %r9, %r9 /* nospec r9 */ - pushq %r10 /* pt_regs->r10 */ - xorq %r10, %r10 /* nospec r10 */ - pushq %r11 /* pt_regs->r11 */ - xorq %r11, %r11 /* nospec r11*/ - pushq %rbx /* pt_regs->rbx */ - xorl %ebx, %ebx /* nospec rbx*/ - pushq %rbp /* pt_regs->rbp */ - xorl %ebp, %ebp /* nospec rbp*/ - pushq %r12 /* pt_regs->r12 */ - xorq %r12, %r12 /* nospec r12*/ - pushq %r13 /* pt_regs->r13 */ - xorq %r13, %r13 /* nospec r13*/ - pushq %r14 /* pt_regs->r14 */ - xorq %r14, %r14 /* nospec r14*/ - pushq %r15 /* pt_regs->r15 */ - xorq %r15, %r15 /* nospec r15*/ - UNWIND_HINT_REGS + PUSH_AND_CLEAR_REGS rdx=(%rdx) ENCODE_FRAME_POINTER /* Patches currently in stable-queue which might be from linux(a)dominikbrodowski.net are queue-4.15/selftests-x86-fix-build-bug-caused-by-the-5lvl-test-which-has-been-moved-to-the-vm-directory.patch queue-4.15/x86-entry-64-interleave-xor-register-clearing-with-push-instructions.patch queue-4.15/x86-entry-64-merge-the-pop_c_regs-and-pop_extra_regs-macros-into-a-single-pop_regs-macro.patch queue-4.15/x86-entry-64-remove-the-unused-icebp-macro.patch queue-4.15/x86-entry-64-use-push_and_clean_regs-in-more-cases.patch queue-4.15/selftests-x86-disable-tests-requiring-32-bit-support-on-pure-64-bit-systems.patch queue-4.15/x86-entry-64-fix-paranoid_entry-frame-pointer-warning.patch queue-4.15/x86-entry-64-merge-save_c_regs-and-save_extra_regs-remove-unused-extensions.patch queue-4.15/selftests-x86-do-not-rely-on-int-0x80-in-single_step_syscall.c.patch queue-4.15/selftests-x86-fix-vdso-selftest-segfault-for-vsyscall-none.patch queue-4.15/x86-entry-64-indent-push_and_clear_regs-and-pop_regs-properly.patch queue-4.15/selftests-x86-clean-up-and-document-sscanf-usage.patch queue-4.15/selftests-x86-do-not-rely-on-int-0x80-in-test_mremap_vdso.c.patch queue-4.15/x86-entry-64-get-rid-of-the-alloc_pt_gpregs_on_stack-and-save_and_clear_regs-macros.patch queue-4.15/x86-entry-64-introduce-the-push_and_clean_regs-macro.patch

6 years, 10 months

1
0
0 0

Patch "x86/entry/64: Merge the POP_C_REGS and POP_EXTRA_REGS macros into a single POP_REGS macro" has been added to the 4.15-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/entry/64: Merge the POP_C_REGS and POP_EXTRA_REGS macros into a single POP_REGS macro to the 4.15-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-entry-64-merge-the-pop_c_regs-and-pop_extra_regs-macros-into-a-single-pop_regs-macro.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(a)vger.kernel.org> know about it. >From 502af0d70843c2a9405d7ba1f79b4b0305aaf5f5 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski <linux(a)dominikbrodowski.net> Date: Sun, 11 Feb 2018 11:49:43 +0100 Subject: x86/entry/64: Merge the POP_C_REGS and POP_EXTRA_REGS macros into a single POP_REGS macro From: Dominik Brodowski <linux(a)dominikbrodowski.net> commit 502af0d70843c2a9405d7ba1f79b4b0305aaf5f5 upstream. The two special, opencoded cases for POP_C_REGS can be handled by ASM macros. Signed-off-by: Dominik Brodowski <linux(a)dominikbrodowski.net> Cc: Andy Lutomirski <luto(a)kernel.org> Cc: Borislav Petkov <bp(a)alien8.de> Cc: Brian Gerst <brgerst(a)gmail.com> Cc: Denys Vlasenko <dvlasenk(a)redhat.com> Cc: H. Peter Anvin <hpa(a)zytor.com> Cc: Josh Poimboeuf <jpoimboe(a)redhat.com> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: dan.j.williams(a)intel.com Link: http://lkml.kernel.org/r/20180211104949.12992-3-linux@dominikbrodowski.net Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/entry/calling.h | 15 +++++++++++---- arch/x86/entry/entry_64.S | 26 ++++---------------------- 2 files changed, 15 insertions(+), 26 deletions(-) --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -139,25 +139,32 @@ For 32-bit we have the following convent xorq %r15, %r15 .endm - .macro POP_EXTRA_REGS + .macro POP_REGS pop_rdi=1 skip_r11rcx=0 popq %r15 popq %r14 popq %r13 popq %r12 popq %rbp popq %rbx - .endm - - .macro POP_C_REGS + .if \skip_r11rcx + popq %rsi + .else popq %r11 + .endif popq %r10 popq %r9 popq %r8 popq %rax + .if \skip_r11rcx + popq %rsi + .else popq %rcx + .endif popq %rdx popq %rsi + .if \pop_rdi popq %rdi + .endif .endm .macro icebp --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -334,15 +334,7 @@ GLOBAL(entry_SYSCALL_64_after_hwframe) syscall_return_via_sysret: /* rcx and r11 are already restored (see code above) */ UNWIND_HINT_EMPTY - POP_EXTRA_REGS - popq %rsi /* skip r11 */ - popq %r10 - popq %r9 - popq %r8 - popq %rax - popq %rsi /* skip rcx */ - popq %rdx - popq %rsi + POP_REGS pop_rdi=0 skip_r11rcx=1 /* * Now all regs are restored except RSP and RDI. @@ -635,15 +627,7 @@ GLOBAL(swapgs_restore_regs_and_return_to ud2 1: #endif - POP_EXTRA_REGS - popq %r11 - popq %r10 - popq %r9 - popq %r8 - popq %rax - popq %rcx - popq %rdx - popq %rsi + POP_REGS pop_rdi=0 /* * The stack is now user RDI, orig_ax, RIP, CS, EFLAGS, RSP, SS. @@ -701,8 +685,7 @@ GLOBAL(restore_regs_and_return_to_kernel ud2 1: #endif - POP_EXTRA_REGS - POP_C_REGS + POP_REGS addq $8, %rsp /* skip regs->orig_ax */ INTERRUPT_RETURN @@ -1661,8 +1644,7 @@ end_repeat_nmi: nmi_swapgs: SWAPGS_UNSAFE_STACK nmi_restore: - POP_EXTRA_REGS - POP_C_REGS + POP_REGS /* * Skip orig_ax and the "outermost" frame to point RSP at the "iret" Patches currently in stable-queue which might be from linux(a)dominikbrodowski.net are queue-4.15/selftests-x86-fix-build-bug-caused-by-the-5lvl-test-which-has-been-moved-to-the-vm-directory.patch queue-4.15/x86-entry-64-interleave-xor-register-clearing-with-push-instructions.patch queue-4.15/x86-entry-64-merge-the-pop_c_regs-and-pop_extra_regs-macros-into-a-single-pop_regs-macro.patch queue-4.15/x86-entry-64-remove-the-unused-icebp-macro.patch queue-4.15/x86-entry-64-use-push_and_clean_regs-in-more-cases.patch queue-4.15/selftests-x86-disable-tests-requiring-32-bit-support-on-pure-64-bit-systems.patch queue-4.15/x86-entry-64-fix-paranoid_entry-frame-pointer-warning.patch queue-4.15/x86-entry-64-merge-save_c_regs-and-save_extra_regs-remove-unused-extensions.patch queue-4.15/selftests-x86-do-not-rely-on-int-0x80-in-single_step_syscall.c.patch queue-4.15/selftests-x86-fix-vdso-selftest-segfault-for-vsyscall-none.patch queue-4.15/x86-entry-64-indent-push_and_clear_regs-and-pop_regs-properly.patch queue-4.15/selftests-x86-clean-up-and-document-sscanf-usage.patch queue-4.15/selftests-x86-do-not-rely-on-int-0x80-in-test_mremap_vdso.c.patch queue-4.15/x86-entry-64-get-rid-of-the-alloc_pt_gpregs_on_stack-and-save_and_clear_regs-macros.patch queue-4.15/x86-entry-64-introduce-the-push_and_clean_regs-macro.patch

6 years, 10 months

1
0
0 0

Patch "x86/entry/64: Remove the unused 'icebp' macro" has been added to the 4.15-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/entry/64: Remove the unused 'icebp' macro to the 4.15-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-entry-64-remove-the-unused-icebp-macro.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(a)vger.kernel.org> know about it. >From b498c261107461d5c42140dfddd05df83d8ca078 Mon Sep 17 00:00:00 2001 From: Borislav Petkov <bp(a)suse.de> Date: Mon, 12 Feb 2018 21:13:18 +0100 Subject: x86/entry/64: Remove the unused 'icebp' macro From: Borislav Petkov <bp(a)suse.de> commit b498c261107461d5c42140dfddd05df83d8ca078 upstream. That macro was touched around 2.5.8 times, judging by the full history linux repo, but it was unused even then. Get rid of it already. Signed-off-by: Borislav Petkov <bp(a)suse.de> Cc: Andy Lutomirski <luto(a)kernel.org> Cc: Borislav Petkov <bp(a)alien8.de> Cc: Brian Gerst <brgerst(a)gmail.com> Cc: Denys Vlasenko <dvlasenk(a)redhat.com> Cc: H. Peter Anvin <hpa(a)zytor.com> Cc: Josh Poimboeuf <jpoimboe(a)redhat.com> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: linux(a)dominikbrodowski.net Link: http://lkml.kernel.org/r/20180212201318.GD14640@pd.tnic Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/entry/calling.h | 4 ---- 1 file changed, 4 deletions(-) --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -159,10 +159,6 @@ For 32-bit we have the following convent .if \pop_rdi popq %rdi .endif - .endm - - .macro icebp - .byte 0xf1 .endm /* Patches currently in stable-queue which might be from bp(a)suse.de are queue-4.15/x86-spectre-fix-an-error-message.patch queue-4.15/x86-entry-64-remove-the-unused-icebp-macro.patch queue-4.15/x86-kexec-make-kexec-mostly-work-in-5-level-paging-mode.patch

6 years, 10 months

1
0
0 0

Patch "x86/entry/64: Merge SAVE_C_REGS and SAVE_EXTRA_REGS, remove unused extensions" has been added to the 4.15-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/entry/64: Merge SAVE_C_REGS and SAVE_EXTRA_REGS, remove unused extensions to the 4.15-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-entry-64-merge-save_c_regs-and-save_extra_regs-remove-unused-extensions.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(a)vger.kernel.org> know about it. >From 2e3f0098bc45f710a2f4cbcc94b80a1fae7a99a1 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski <linux(a)dominikbrodowski.net> Date: Sun, 11 Feb 2018 11:49:42 +0100 Subject: x86/entry/64: Merge SAVE_C_REGS and SAVE_EXTRA_REGS, remove unused extensions From: Dominik Brodowski <linux(a)dominikbrodowski.net> commit 2e3f0098bc45f710a2f4cbcc94b80a1fae7a99a1 upstream. All current code paths call SAVE_C_REGS and then immediately SAVE_EXTRA_REGS. Therefore, merge these two macros and order the MOV sequeneces properly. While at it, remove the macros to save all except specific registers, as these macros have been unused for a long time. Suggested-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Dominik Brodowski <linux(a)dominikbrodowski.net> Cc: Andy Lutomirski <luto(a)kernel.org> Cc: Borislav Petkov <bp(a)alien8.de> Cc: Brian Gerst <brgerst(a)gmail.com> Cc: Denys Vlasenko <dvlasenk(a)redhat.com> Cc: H. Peter Anvin <hpa(a)zytor.com> Cc: Josh Poimboeuf <jpoimboe(a)redhat.com> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: dan.j.williams(a)intel.com Link: http://lkml.kernel.org/r/20180211104949.12992-2-linux@dominikbrodowski.net Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/entry/calling.h | 57 ++++++++++++---------------------------------- arch/x86/entry/entry_64.S | 12 +++------ 2 files changed, 19 insertions(+), 50 deletions(-) --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -101,49 +101,22 @@ For 32-bit we have the following convent addq $-(15*8), %rsp .endm - .macro SAVE_C_REGS_HELPER offset=0 rax=1 rcx=1 r8910=1 r11=1 - .if \r11 - movq %r11, 6*8+\offset(%rsp) - .endif - .if \r8910 - movq %r10, 7*8+\offset(%rsp) - movq %r9, 8*8+\offset(%rsp) - movq %r8, 9*8+\offset(%rsp) - .endif - .if \rax - movq %rax, 10*8+\offset(%rsp) - .endif - .if \rcx - movq %rcx, 11*8+\offset(%rsp) - .endif - movq %rdx, 12*8+\offset(%rsp) - movq %rsi, 13*8+\offset(%rsp) + .macro SAVE_REGS offset=0 movq %rdi, 14*8+\offset(%rsp) - UNWIND_HINT_REGS offset=\offset extra=0 - .endm - .macro SAVE_C_REGS offset=0 - SAVE_C_REGS_HELPER \offset, 1, 1, 1, 1 - .endm - .macro SAVE_C_REGS_EXCEPT_RAX_RCX offset=0 - SAVE_C_REGS_HELPER \offset, 0, 0, 1, 1 - .endm - .macro SAVE_C_REGS_EXCEPT_R891011 - SAVE_C_REGS_HELPER 0, 1, 1, 0, 0 - .endm - .macro SAVE_C_REGS_EXCEPT_RCX_R891011 - SAVE_C_REGS_HELPER 0, 1, 0, 0, 0 - .endm - .macro SAVE_C_REGS_EXCEPT_RAX_RCX_R11 - SAVE_C_REGS_HELPER 0, 0, 0, 1, 0 - .endm - - .macro SAVE_EXTRA_REGS offset=0 - movq %r15, 0*8+\offset(%rsp) - movq %r14, 1*8+\offset(%rsp) - movq %r13, 2*8+\offset(%rsp) - movq %r12, 3*8+\offset(%rsp) - movq %rbp, 4*8+\offset(%rsp) + movq %rsi, 13*8+\offset(%rsp) + movq %rdx, 12*8+\offset(%rsp) + movq %rcx, 11*8+\offset(%rsp) + movq %rax, 10*8+\offset(%rsp) + movq %r8, 9*8+\offset(%rsp) + movq %r9, 8*8+\offset(%rsp) + movq %r10, 7*8+\offset(%rsp) + movq %r11, 6*8+\offset(%rsp) movq %rbx, 5*8+\offset(%rsp) + movq %rbp, 4*8+\offset(%rsp) + movq %r12, 3*8+\offset(%rsp) + movq %r13, 2*8+\offset(%rsp) + movq %r14, 1*8+\offset(%rsp) + movq %r15, 0*8+\offset(%rsp) UNWIND_HINT_REGS offset=\offset .endm @@ -197,7 +170,7 @@ For 32-bit we have the following convent * is just setting the LSB, which makes it an invalid stack address and is also * a signal to the unwinder that it's a pt_regs pointer in disguise. * - * NOTE: This macro must be used *after* SAVE_EXTRA_REGS because it corrupts + * NOTE: This macro must be used *after* SAVE_REGS because it corrupts * the original rbp. */ .macro ENCODE_FRAME_POINTER ptregs_offset=0 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -573,8 +573,7 @@ END(irq_entries_start) 1: ALLOC_PT_GPREGS_ON_STACK - SAVE_C_REGS - SAVE_EXTRA_REGS + SAVE_REGS CLEAR_REGS_NOSPEC ENCODE_FRAME_POINTER @@ -1132,8 +1131,7 @@ ENTRY(xen_failsafe_callback) UNWIND_HINT_IRET_REGS pushq $-1 /* orig_ax = -1 => not a system call */ ALLOC_PT_GPREGS_ON_STACK - SAVE_C_REGS - SAVE_EXTRA_REGS + SAVE_REGS CLEAR_REGS_NOSPEC ENCODE_FRAME_POINTER jmp error_exit @@ -1178,8 +1176,7 @@ idtentry machine_check do_mce has_err ENTRY(paranoid_entry) UNWIND_HINT_FUNC cld - SAVE_C_REGS 8 - SAVE_EXTRA_REGS 8 + SAVE_REGS 8 CLEAR_REGS_NOSPEC ENCODE_FRAME_POINTER 8 movl $1, %ebx @@ -1231,8 +1228,7 @@ END(paranoid_exit) ENTRY(error_entry) UNWIND_HINT_FUNC cld - SAVE_C_REGS 8 - SAVE_EXTRA_REGS 8 + SAVE_REGS 8 CLEAR_REGS_NOSPEC ENCODE_FRAME_POINTER 8 testb $3, CS+8(%rsp) Patches currently in stable-queue which might be from linux(a)dominikbrodowski.net are queue-4.15/selftests-x86-fix-build-bug-caused-by-the-5lvl-test-which-has-been-moved-to-the-vm-directory.patch queue-4.15/x86-entry-64-interleave-xor-register-clearing-with-push-instructions.patch queue-4.15/x86-entry-64-merge-the-pop_c_regs-and-pop_extra_regs-macros-into-a-single-pop_regs-macro.patch queue-4.15/x86-entry-64-remove-the-unused-icebp-macro.patch queue-4.15/x86-entry-64-use-push_and_clean_regs-in-more-cases.patch queue-4.15/selftests-x86-disable-tests-requiring-32-bit-support-on-pure-64-bit-systems.patch queue-4.15/x86-entry-64-fix-paranoid_entry-frame-pointer-warning.patch queue-4.15/x86-entry-64-merge-save_c_regs-and-save_extra_regs-remove-unused-extensions.patch queue-4.15/selftests-x86-do-not-rely-on-int-0x80-in-single_step_syscall.c.patch queue-4.15/selftests-x86-fix-vdso-selftest-segfault-for-vsyscall-none.patch queue-4.15/x86-entry-64-indent-push_and_clear_regs-and-pop_regs-properly.patch queue-4.15/selftests-x86-clean-up-and-document-sscanf-usage.patch queue-4.15/selftests-x86-do-not-rely-on-int-0x80-in-test_mremap_vdso.c.patch queue-4.15/x86-entry-64-get-rid-of-the-alloc_pt_gpregs_on_stack-and-save_and_clear_regs-macros.patch queue-4.15/x86-entry-64-introduce-the-push_and_clean_regs-macro.patch

6 years, 10 months

1
0
0 0

Patch "x86/entry/64: Interleave XOR register clearing with PUSH instructions" has been added to the 4.15-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/entry/64: Interleave XOR register clearing with PUSH instructions to the 4.15-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-entry-64-interleave-xor-register-clearing-with-push-instructions.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(a)vger.kernel.org> know about it. >From f7bafa2b05ef25eda1d9179fd930b0330cf2b7d1 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski <linux(a)dominikbrodowski.net> Date: Sun, 11 Feb 2018 11:49:44 +0100 Subject: x86/entry/64: Interleave XOR register clearing with PUSH instructions From: Dominik Brodowski <linux(a)dominikbrodowski.net> commit f7bafa2b05ef25eda1d9179fd930b0330cf2b7d1 upstream. Same as is done for syscalls, interleave XOR with PUSH instructions for exceptions/interrupts, in order to minimize the cost of the additional instructions required for register clearing. Signed-off-by: Dominik Brodowski <linux(a)dominikbrodowski.net> Cc: Andy Lutomirski <luto(a)kernel.org> Cc: Borislav Petkov <bp(a)alien8.de> Cc: Brian Gerst <brgerst(a)gmail.com> Cc: Denys Vlasenko <dvlasenk(a)redhat.com> Cc: H. Peter Anvin <hpa(a)zytor.com> Cc: Josh Poimboeuf <jpoimboe(a)redhat.com> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: dan.j.williams(a)intel.com Link: http://lkml.kernel.org/r/20180211104949.12992-4-linux@dominikbrodowski.net Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/entry/calling.h | 40 +++++++++++++++++++--------------------- arch/x86/entry/entry_64.S | 30 +++++++++++++++++++++--------- 2 files changed, 40 insertions(+), 30 deletions(-) --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -101,44 +101,42 @@ For 32-bit we have the following convent addq $-(15*8), %rsp .endm - .macro SAVE_REGS offset=0 + .macro SAVE_AND_CLEAR_REGS offset=0 + /* + * Save registers and sanitize registers of values that a + * speculation attack might otherwise want to exploit. The + * lower registers are likely clobbered well before they + * could be put to use in a speculative execution gadget. + * Interleave XOR with PUSH for better uop scheduling: + */ movq %rdi, 14*8+\offset(%rsp) movq %rsi, 13*8+\offset(%rsp) movq %rdx, 12*8+\offset(%rsp) movq %rcx, 11*8+\offset(%rsp) movq %rax, 10*8+\offset(%rsp) movq %r8, 9*8+\offset(%rsp) + xorq %r8, %r8 /* nospec r8 */ movq %r9, 8*8+\offset(%rsp) + xorq %r9, %r9 /* nospec r9 */ movq %r10, 7*8+\offset(%rsp) + xorq %r10, %r10 /* nospec r10 */ movq %r11, 6*8+\offset(%rsp) + xorq %r11, %r11 /* nospec r11 */ movq %rbx, 5*8+\offset(%rsp) + xorl %ebx, %ebx /* nospec rbx */ movq %rbp, 4*8+\offset(%rsp) + xorl %ebp, %ebp /* nospec rbp */ movq %r12, 3*8+\offset(%rsp) + xorq %r12, %r12 /* nospec r12 */ movq %r13, 2*8+\offset(%rsp) + xorq %r13, %r13 /* nospec r13 */ movq %r14, 1*8+\offset(%rsp) + xorq %r14, %r14 /* nospec r14 */ movq %r15, 0*8+\offset(%rsp) + xorq %r15, %r15 /* nospec r15 */ UNWIND_HINT_REGS offset=\offset .endm - /* - * Sanitize registers of values that a speculation attack - * might otherwise want to exploit. The lower registers are - * likely clobbered well before they could be put to use in - * a speculative execution gadget: - */ - .macro CLEAR_REGS_NOSPEC - xorl %ebp, %ebp - xorl %ebx, %ebx - xorq %r8, %r8 - xorq %r9, %r9 - xorq %r10, %r10 - xorq %r11, %r11 - xorq %r12, %r12 - xorq %r13, %r13 - xorq %r14, %r14 - xorq %r15, %r15 - .endm - .macro POP_REGS pop_rdi=1 skip_r11rcx=0 popq %r15 popq %r14 @@ -177,7 +175,7 @@ For 32-bit we have the following convent * is just setting the LSB, which makes it an invalid stack address and is also * a signal to the unwinder that it's a pt_regs pointer in disguise. * - * NOTE: This macro must be used *after* SAVE_REGS because it corrupts + * NOTE: This macro must be used *after* SAVE_AND_CLEAR_REGS because it corrupts * the original rbp. */ .macro ENCODE_FRAME_POINTER ptregs_offset=0 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -565,8 +565,7 @@ END(irq_entries_start) 1: ALLOC_PT_GPREGS_ON_STACK - SAVE_REGS - CLEAR_REGS_NOSPEC + SAVE_AND_CLEAR_REGS ENCODE_FRAME_POINTER testb $3, CS(%rsp) @@ -1114,8 +1113,7 @@ ENTRY(xen_failsafe_callback) UNWIND_HINT_IRET_REGS pushq $-1 /* orig_ax = -1 => not a system call */ ALLOC_PT_GPREGS_ON_STACK - SAVE_REGS - CLEAR_REGS_NOSPEC + SAVE_AND_CLEAR_REGS ENCODE_FRAME_POINTER jmp error_exit END(xen_failsafe_callback) @@ -1159,8 +1157,7 @@ idtentry machine_check do_mce has_err ENTRY(paranoid_entry) UNWIND_HINT_FUNC cld - SAVE_REGS 8 - CLEAR_REGS_NOSPEC + SAVE_AND_CLEAR_REGS 8 ENCODE_FRAME_POINTER 8 movl $1, %ebx movl $MSR_GS_BASE, %ecx @@ -1211,8 +1208,7 @@ END(paranoid_exit) ENTRY(error_entry) UNWIND_HINT_FUNC cld - SAVE_REGS 8 - CLEAR_REGS_NOSPEC + SAVE_AND_CLEAR_REGS 8 ENCODE_FRAME_POINTER 8 testb $3, CS+8(%rsp) jz .Lerror_kernelspace @@ -1399,18 +1395,34 @@ ENTRY(nmi) pushq (%rdx) /* pt_regs->dx */ pushq %rcx /* pt_regs->cx */ pushq %rax /* pt_regs->ax */ + /* + * Sanitize registers of values that a speculation attack + * might otherwise want to exploit. The lower registers are + * likely clobbered well before they could be put to use in + * a speculative execution gadget. Interleave XOR with PUSH + * for better uop scheduling: + */ pushq %r8 /* pt_regs->r8 */ + xorq %r8, %r8 /* nospec r8 */ pushq %r9 /* pt_regs->r9 */ + xorq %r9, %r9 /* nospec r9 */ pushq %r10 /* pt_regs->r10 */ + xorq %r10, %r10 /* nospec r10 */ pushq %r11 /* pt_regs->r11 */ + xorq %r11, %r11 /* nospec r11*/ pushq %rbx /* pt_regs->rbx */ + xorl %ebx, %ebx /* nospec rbx*/ pushq %rbp /* pt_regs->rbp */ + xorl %ebp, %ebp /* nospec rbp*/ pushq %r12 /* pt_regs->r12 */ + xorq %r12, %r12 /* nospec r12*/ pushq %r13 /* pt_regs->r13 */ + xorq %r13, %r13 /* nospec r13*/ pushq %r14 /* pt_regs->r14 */ + xorq %r14, %r14 /* nospec r14*/ pushq %r15 /* pt_regs->r15 */ + xorq %r15, %r15 /* nospec r15*/ UNWIND_HINT_REGS - CLEAR_REGS_NOSPEC ENCODE_FRAME_POINTER /* Patches currently in stable-queue which might be from linux(a)dominikbrodowski.net are queue-4.15/selftests-x86-fix-build-bug-caused-by-the-5lvl-test-which-has-been-moved-to-the-vm-directory.patch queue-4.15/x86-entry-64-interleave-xor-register-clearing-with-push-instructions.patch queue-4.15/x86-entry-64-merge-the-pop_c_regs-and-pop_extra_regs-macros-into-a-single-pop_regs-macro.patch queue-4.15/x86-entry-64-remove-the-unused-icebp-macro.patch queue-4.15/x86-entry-64-use-push_and_clean_regs-in-more-cases.patch queue-4.15/selftests-x86-disable-tests-requiring-32-bit-support-on-pure-64-bit-systems.patch queue-4.15/x86-entry-64-fix-paranoid_entry-frame-pointer-warning.patch queue-4.15/x86-entry-64-merge-save_c_regs-and-save_extra_regs-remove-unused-extensions.patch queue-4.15/selftests-x86-do-not-rely-on-int-0x80-in-single_step_syscall.c.patch queue-4.15/selftests-x86-fix-vdso-selftest-segfault-for-vsyscall-none.patch queue-4.15/x86-entry-64-indent-push_and_clear_regs-and-pop_regs-properly.patch queue-4.15/selftests-x86-clean-up-and-document-sscanf-usage.patch queue-4.15/selftests-x86-do-not-rely-on-int-0x80-in-test_mremap_vdso.c.patch queue-4.15/x86-entry-64-get-rid-of-the-alloc_pt_gpregs_on_stack-and-save_and_clear_regs-macros.patch queue-4.15/x86-entry-64-introduce-the-push_and_clean_regs-macro.patch

6 years, 10 months

1
0
0 0

Patch "x86/entry/64: Introduce the PUSH_AND_CLEAN_REGS macro" has been added to the 4.15-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/entry/64: Introduce the PUSH_AND_CLEAN_REGS macro to the 4.15-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-entry-64-introduce-the-push_and_clean_regs-macro.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(a)vger.kernel.org> know about it. >From 3f01daecd545e818098d84fd1ad43e19a508d705 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski <linux(a)dominikbrodowski.net> Date: Sun, 11 Feb 2018 11:49:45 +0100 Subject: x86/entry/64: Introduce the PUSH_AND_CLEAN_REGS macro From: Dominik Brodowski <linux(a)dominikbrodowski.net> commit 3f01daecd545e818098d84fd1ad43e19a508d705 upstream. Those instances where ALLOC_PT_GPREGS_ON_STACK is called just before SAVE_AND_CLEAR_REGS can trivially be replaced by PUSH_AND_CLEAN_REGS. This macro uses PUSH instead of MOV and should therefore be faster, at least on newer CPUs. Suggested-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Dominik Brodowski <linux(a)dominikbrodowski.net> Cc: Andy Lutomirski <luto(a)kernel.org> Cc: Borislav Petkov <bp(a)alien8.de> Cc: Brian Gerst <brgerst(a)gmail.com> Cc: Denys Vlasenko <dvlasenk(a)redhat.com> Cc: H. Peter Anvin <hpa(a)zytor.com> Cc: Josh Poimboeuf <jpoimboe(a)redhat.com> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: dan.j.williams(a)intel.com Link: http://lkml.kernel.org/r/20180211104949.12992-5-linux@dominikbrodowski.net Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/entry/calling.h | 36 ++++++++++++++++++++++++++++++++++++ arch/x86/entry/entry_64.S | 6 ++---- 2 files changed, 38 insertions(+), 4 deletions(-) --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -137,6 +137,42 @@ For 32-bit we have the following convent UNWIND_HINT_REGS offset=\offset .endm + .macro PUSH_AND_CLEAR_REGS + /* + * Push registers and sanitize registers of values that a + * speculation attack might otherwise want to exploit. The + * lower registers are likely clobbered well before they + * could be put to use in a speculative execution gadget. + * Interleave XOR with PUSH for better uop scheduling: + */ + pushq %rdi /* pt_regs->di */ + pushq %rsi /* pt_regs->si */ + pushq %rdx /* pt_regs->dx */ + pushq %rcx /* pt_regs->cx */ + pushq %rax /* pt_regs->ax */ + pushq %r8 /* pt_regs->r8 */ + xorq %r8, %r8 /* nospec r8 */ + pushq %r9 /* pt_regs->r9 */ + xorq %r9, %r9 /* nospec r9 */ + pushq %r10 /* pt_regs->r10 */ + xorq %r10, %r10 /* nospec r10 */ + pushq %r11 /* pt_regs->r11 */ + xorq %r11, %r11 /* nospec r11*/ + pushq %rbx /* pt_regs->rbx */ + xorl %ebx, %ebx /* nospec rbx*/ + pushq %rbp /* pt_regs->rbp */ + xorl %ebp, %ebp /* nospec rbp*/ + pushq %r12 /* pt_regs->r12 */ + xorq %r12, %r12 /* nospec r12*/ + pushq %r13 /* pt_regs->r13 */ + xorq %r13, %r13 /* nospec r13*/ + pushq %r14 /* pt_regs->r14 */ + xorq %r14, %r14 /* nospec r14*/ + pushq %r15 /* pt_regs->r15 */ + xorq %r15, %r15 /* nospec r15*/ + UNWIND_HINT_REGS + .endm + .macro POP_REGS pop_rdi=1 skip_r11rcx=0 popq %r15 popq %r14 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -564,8 +564,7 @@ END(irq_entries_start) call switch_to_thread_stack 1: - ALLOC_PT_GPREGS_ON_STACK - SAVE_AND_CLEAR_REGS + PUSH_AND_CLEAR_REGS ENCODE_FRAME_POINTER testb $3, CS(%rsp) @@ -1112,8 +1111,7 @@ ENTRY(xen_failsafe_callback) addq $0x30, %rsp UNWIND_HINT_IRET_REGS pushq $-1 /* orig_ax = -1 => not a system call */ - ALLOC_PT_GPREGS_ON_STACK - SAVE_AND_CLEAR_REGS + PUSH_AND_CLEAR_REGS ENCODE_FRAME_POINTER jmp error_exit END(xen_failsafe_callback) Patches currently in stable-queue which might be from linux(a)dominikbrodowski.net are queue-4.15/selftests-x86-fix-build-bug-caused-by-the-5lvl-test-which-has-been-moved-to-the-vm-directory.patch queue-4.15/x86-entry-64-interleave-xor-register-clearing-with-push-instructions.patch queue-4.15/x86-entry-64-merge-the-pop_c_regs-and-pop_extra_regs-macros-into-a-single-pop_regs-macro.patch queue-4.15/x86-entry-64-remove-the-unused-icebp-macro.patch queue-4.15/x86-entry-64-use-push_and_clean_regs-in-more-cases.patch queue-4.15/selftests-x86-disable-tests-requiring-32-bit-support-on-pure-64-bit-systems.patch queue-4.15/x86-entry-64-fix-paranoid_entry-frame-pointer-warning.patch queue-4.15/x86-entry-64-merge-save_c_regs-and-save_extra_regs-remove-unused-extensions.patch queue-4.15/selftests-x86-do-not-rely-on-int-0x80-in-single_step_syscall.c.patch queue-4.15/selftests-x86-fix-vdso-selftest-segfault-for-vsyscall-none.patch queue-4.15/x86-entry-64-indent-push_and_clear_regs-and-pop_regs-properly.patch queue-4.15/selftests-x86-clean-up-and-document-sscanf-usage.patch queue-4.15/selftests-x86-do-not-rely-on-int-0x80-in-test_mremap_vdso.c.patch queue-4.15/x86-entry-64-get-rid-of-the-alloc_pt_gpregs_on_stack-and-save_and_clear_regs-macros.patch queue-4.15/x86-entry-64-introduce-the-push_and_clean_regs-macro.patch

6 years, 10 months

1
0
0 0

Patch "x86/entry/64: Get rid of the ALLOC_PT_GPREGS_ON_STACK and SAVE_AND_CLEAR_REGS macros" has been added to the 4.15-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/entry/64: Get rid of the ALLOC_PT_GPREGS_ON_STACK and SAVE_AND_CLEAR_REGS macros to the 4.15-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-entry-64-get-rid-of-the-alloc_pt_gpregs_on_stack-and-save_and_clear_regs-macros.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(a)vger.kernel.org> know about it. >From dde3036d62ba3375840b10ab9ec0d568fd773b07 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski <linux(a)dominikbrodowski.net> Date: Sun, 11 Feb 2018 11:49:47 +0100 Subject: x86/entry/64: Get rid of the ALLOC_PT_GPREGS_ON_STACK and SAVE_AND_CLEAR_REGS macros From: Dominik Brodowski <linux(a)dominikbrodowski.net> commit dde3036d62ba3375840b10ab9ec0d568fd773b07 upstream. Previously, error_entry() and paranoid_entry() saved the GP registers onto stack space previously allocated by its callers. Combine these two steps in the callers, and use the generic PUSH_AND_CLEAR_REGS macro for that. This adds a significant amount ot text size. However, Ingo Molnar points out that: "these numbers also _very_ significantly over-represent the extra footprint. The assumptions that resulted in us compressing the IRQ entry code have changed very significantly with the new x86 IRQ allocation code we introduced in the last year: - IRQ vectors are usually populated in tightly clustered groups. With our new vector allocator code the typical per CPU allocation percentage on x86 systems is ~3 device vectors and ~10 fixed vectors out of ~220 vectors - i.e. a very low ~6% utilization (!). [...] The days where we allocated a lot of vectors on every CPU and the compression of the IRQ entry code text mattered are over. - Another issue is that only a small minority of vectors is frequent enough to actually matter to cache utilization in practice: 3-4 key IPIs and 1-2 device IRQs at most - and those vectors tend to be tightly clustered as well into about two groups, and are probably already on 2-3 cache lines in practice. For the common case of 'cache cold' IRQs it's the depth of the call chain and the fragmentation of the resulting I$ that should be the main performance limit - not the overall size of it. - The CPU side cost of IRQ delivery is still very expensive even in the best, most cached case, as in 'over a thousand cycles'. So much stuff is done that maybe contemporary x86 IRQ entry microcode already prefetches the IDT entry and its expected call target address."[*] [*] http://lkml.kernel.org/r/20180208094710.qnjixhm6hybebdv7@gmail.com The "testb $3, CS(%rsp)" instruction in the idtentry macro does not need modification. Previously, %rsp was manually decreased by 15*8; with this patch, %rsp is decreased by 15 pushq instructions. [jpoimboe(a)redhat.com: unwind hint improvements] Suggested-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Dominik Brodowski <linux(a)dominikbrodowski.net> Cc: Andy Lutomirski <luto(a)kernel.org> Cc: Borislav Petkov <bp(a)alien8.de> Cc: Brian Gerst <brgerst(a)gmail.com> Cc: Denys Vlasenko <dvlasenk(a)redhat.com> Cc: H. Peter Anvin <hpa(a)zytor.com> Cc: Josh Poimboeuf <jpoimboe(a)redhat.com> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: dan.j.williams(a)intel.com Link: http://lkml.kernel.org/r/20180211104949.12992-7-linux@dominikbrodowski.net Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/entry/calling.h | 42 +----------------------------------------- arch/x86/entry/entry_64.S | 20 +++++++++----------- 2 files changed, 10 insertions(+), 52 deletions(-) --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -97,46 +97,6 @@ For 32-bit we have the following convent #define SIZEOF_PTREGS 21*8 - .macro ALLOC_PT_GPREGS_ON_STACK - addq $-(15*8), %rsp - .endm - - .macro SAVE_AND_CLEAR_REGS offset=0 - /* - * Save registers and sanitize registers of values that a - * speculation attack might otherwise want to exploit. The - * lower registers are likely clobbered well before they - * could be put to use in a speculative execution gadget. - * Interleave XOR with PUSH for better uop scheduling: - */ - movq %rdi, 14*8+\offset(%rsp) - movq %rsi, 13*8+\offset(%rsp) - movq %rdx, 12*8+\offset(%rsp) - movq %rcx, 11*8+\offset(%rsp) - movq %rax, 10*8+\offset(%rsp) - movq %r8, 9*8+\offset(%rsp) - xorq %r8, %r8 /* nospec r8 */ - movq %r9, 8*8+\offset(%rsp) - xorq %r9, %r9 /* nospec r9 */ - movq %r10, 7*8+\offset(%rsp) - xorq %r10, %r10 /* nospec r10 */ - movq %r11, 6*8+\offset(%rsp) - xorq %r11, %r11 /* nospec r11 */ - movq %rbx, 5*8+\offset(%rsp) - xorl %ebx, %ebx /* nospec rbx */ - movq %rbp, 4*8+\offset(%rsp) - xorl %ebp, %ebp /* nospec rbp */ - movq %r12, 3*8+\offset(%rsp) - xorq %r12, %r12 /* nospec r12 */ - movq %r13, 2*8+\offset(%rsp) - xorq %r13, %r13 /* nospec r13 */ - movq %r14, 1*8+\offset(%rsp) - xorq %r14, %r14 /* nospec r14 */ - movq %r15, 0*8+\offset(%rsp) - xorq %r15, %r15 /* nospec r15 */ - UNWIND_HINT_REGS offset=\offset - .endm - .macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax /* * Push registers and sanitize registers of values that a @@ -211,7 +171,7 @@ For 32-bit we have the following convent * is just setting the LSB, which makes it an invalid stack address and is also * a signal to the unwinder that it's a pt_regs pointer in disguise. * - * NOTE: This macro must be used *after* SAVE_AND_CLEAR_REGS because it corrupts + * NOTE: This macro must be used *after* PUSH_AND_CLEAR_REGS because it corrupts * the original rbp. */ .macro ENCODE_FRAME_POINTER ptregs_offset=0 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -871,7 +871,9 @@ ENTRY(\sym) pushq $-1 /* ORIG_RAX: no syscall to restart */ .endif - ALLOC_PT_GPREGS_ON_STACK + /* Save all registers in pt_regs */ + PUSH_AND_CLEAR_REGS + ENCODE_FRAME_POINTER .if \paranoid < 2 testb $3, CS(%rsp) /* If coming from userspace, switch stacks */ @@ -1121,15 +1123,12 @@ idtentry machine_check do_mce has_err #endif /* - * Save all registers in pt_regs, and switch gs if needed. + * Switch gs if needed. * Use slow, but surefire "are we in kernel?" check. * Return: ebx=0: need swapgs on exit, ebx=1: otherwise */ ENTRY(paranoid_entry) - UNWIND_HINT_FUNC cld - SAVE_AND_CLEAR_REGS 8 - ENCODE_FRAME_POINTER 8 movl $1, %ebx movl $MSR_GS_BASE, %ecx rdmsr @@ -1142,7 +1141,7 @@ ENTRY(paranoid_entry) SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg=%rax save_reg=%r14 ret -END(paranoid_entry) +ENDPROC(paranoid_entry) /* * "Paranoid" exit path from exception stack. This is invoked @@ -1173,14 +1172,12 @@ ENTRY(paranoid_exit) END(paranoid_exit) /* - * Save all registers in pt_regs, and switch gs if needed. + * Switch gs if needed. * Return: EBX=0: came from user mode; EBX=1: otherwise */ ENTRY(error_entry) - UNWIND_HINT_FUNC + UNWIND_HINT_REGS offset=8 cld - SAVE_AND_CLEAR_REGS 8 - ENCODE_FRAME_POINTER 8 testb $3, CS+8(%rsp) jz .Lerror_kernelspace @@ -1571,7 +1568,8 @@ end_repeat_nmi: * frame to point back to repeat_nmi. */ pushq $-1 /* ORIG_RAX: no syscall to restart */ - ALLOC_PT_GPREGS_ON_STACK + PUSH_AND_CLEAR_REGS + ENCODE_FRAME_POINTER /* * Use paranoid_entry to handle SWAPGS, but no need to use paranoid_exit Patches currently in stable-queue which might be from linux(a)dominikbrodowski.net are queue-4.15/selftests-x86-fix-build-bug-caused-by-the-5lvl-test-which-has-been-moved-to-the-vm-directory.patch queue-4.15/x86-entry-64-interleave-xor-register-clearing-with-push-instructions.patch queue-4.15/x86-entry-64-merge-the-pop_c_regs-and-pop_extra_regs-macros-into-a-single-pop_regs-macro.patch queue-4.15/x86-entry-64-remove-the-unused-icebp-macro.patch queue-4.15/x86-entry-64-use-push_and_clean_regs-in-more-cases.patch queue-4.15/selftests-x86-disable-tests-requiring-32-bit-support-on-pure-64-bit-systems.patch queue-4.15/x86-entry-64-fix-paranoid_entry-frame-pointer-warning.patch queue-4.15/x86-entry-64-merge-save_c_regs-and-save_extra_regs-remove-unused-extensions.patch queue-4.15/selftests-x86-do-not-rely-on-int-0x80-in-single_step_syscall.c.patch queue-4.15/selftests-x86-fix-vdso-selftest-segfault-for-vsyscall-none.patch queue-4.15/x86-entry-64-indent-push_and_clear_regs-and-pop_regs-properly.patch queue-4.15/selftests-x86-clean-up-and-document-sscanf-usage.patch queue-4.15/selftests-x86-do-not-rely-on-int-0x80-in-test_mremap_vdso.c.patch queue-4.15/x86-entry-64-get-rid-of-the-alloc_pt_gpregs_on_stack-and-save_and_clear_regs-macros.patch queue-4.15/x86-entry-64-introduce-the-push_and_clean_regs-macro.patch

6 years, 10 months

1
0
0 0

Patch "x86/entry/64: Indent PUSH_AND_CLEAR_REGS and POP_REGS properly" has been added to the 4.15-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/entry/64: Indent PUSH_AND_CLEAR_REGS and POP_REGS properly to the 4.15-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-entry-64-indent-push_and_clear_regs-and-pop_regs-properly.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(a)vger.kernel.org> know about it. >From 92816f571af81e9a71cc6f3dc8ce1e2fcdf7b6b8 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski <linux(a)dominikbrodowski.net> Date: Sun, 11 Feb 2018 11:49:48 +0100 Subject: x86/entry/64: Indent PUSH_AND_CLEAR_REGS and POP_REGS properly From: Dominik Brodowski <linux(a)dominikbrodowski.net> commit 92816f571af81e9a71cc6f3dc8ce1e2fcdf7b6b8 upstream. ... same as the other macros in arch/x86/entry/calling.h Signed-off-by: Dominik Brodowski <linux(a)dominikbrodowski.net> Cc: Andy Lutomirski <luto(a)kernel.org> Cc: Borislav Petkov <bp(a)alien8.de> Cc: Brian Gerst <brgerst(a)gmail.com> Cc: Denys Vlasenko <dvlasenk(a)redhat.com> Cc: H. Peter Anvin <hpa(a)zytor.com> Cc: Josh Poimboeuf <jpoimboe(a)redhat.com> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: dan.j.williams(a)intel.com Link: http://lkml.kernel.org/r/20180211104949.12992-8-linux@dominikbrodowski.net Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/entry/calling.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -97,7 +97,7 @@ For 32-bit we have the following convent #define SIZEOF_PTREGS 21*8 - .macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax +.macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax /* * Push registers and sanitize registers of values that a * speculation attack might otherwise want to exploit. The @@ -131,9 +131,9 @@ For 32-bit we have the following convent pushq %r15 /* pt_regs->r15 */ xorq %r15, %r15 /* nospec r15*/ UNWIND_HINT_REGS - .endm +.endm - .macro POP_REGS pop_rdi=1 skip_r11rcx=0 +.macro POP_REGS pop_rdi=1 skip_r11rcx=0 popq %r15 popq %r14 popq %r13 @@ -163,7 +163,7 @@ For 32-bit we have the following convent .macro icebp .byte 0xf1 - .endm +.endm /* * This is a sneaky trick to help the unwinder find pt_regs on the stack. The Patches currently in stable-queue which might be from linux(a)dominikbrodowski.net are queue-4.15/selftests-x86-fix-build-bug-caused-by-the-5lvl-test-which-has-been-moved-to-the-vm-directory.patch queue-4.15/x86-entry-64-interleave-xor-register-clearing-with-push-instructions.patch queue-4.15/x86-entry-64-merge-the-pop_c_regs-and-pop_extra_regs-macros-into-a-single-pop_regs-macro.patch queue-4.15/x86-entry-64-remove-the-unused-icebp-macro.patch queue-4.15/x86-entry-64-use-push_and_clean_regs-in-more-cases.patch queue-4.15/selftests-x86-disable-tests-requiring-32-bit-support-on-pure-64-bit-systems.patch queue-4.15/x86-entry-64-fix-paranoid_entry-frame-pointer-warning.patch queue-4.15/x86-entry-64-merge-save_c_regs-and-save_extra_regs-remove-unused-extensions.patch queue-4.15/selftests-x86-do-not-rely-on-int-0x80-in-single_step_syscall.c.patch queue-4.15/selftests-x86-fix-vdso-selftest-segfault-for-vsyscall-none.patch queue-4.15/x86-entry-64-indent-push_and_clear_regs-and-pop_regs-properly.patch queue-4.15/selftests-x86-clean-up-and-document-sscanf-usage.patch queue-4.15/selftests-x86-do-not-rely-on-int-0x80-in-test_mremap_vdso.c.patch queue-4.15/x86-entry-64-get-rid-of-the-alloc_pt_gpregs_on_stack-and-save_and_clear_regs-macros.patch queue-4.15/x86-entry-64-introduce-the-push_and_clean_regs-macro.patch

6 years, 10 months

1
0
0 0

Patch "x86/entry/64: Fix CR3 restore in paranoid_exit()" has been added to the 4.15-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/entry/64: Fix CR3 restore in paranoid_exit() to the 4.15-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-entry-64-fix-cr3-restore-in-paranoid_exit.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(a)vger.kernel.org> know about it. >From e48657573481a5dff7cfdc3d57005c80aa816500 Mon Sep 17 00:00:00 2001 From: Ingo Molnar <mingo(a)kernel.org> Date: Wed, 14 Feb 2018 08:39:11 +0100 Subject: x86/entry/64: Fix CR3 restore in paranoid_exit() From: Ingo Molnar <mingo(a)kernel.org> commit e48657573481a5dff7cfdc3d57005c80aa816500 upstream. Josh Poimboeuf noticed the following bug: "The paranoid exit code only restores the saved CR3 when it switches back to the user GS. However, even in the kernel GS case, it's possible that it needs to restore a user CR3, if for example, the paranoid exception occurred in the syscall exit path between SWITCH_TO_USER_CR3_STACK and SWAPGS." Josh also confirmed via targeted testing that it's possible to hit this bug. Fix the bug by also restoring CR3 in the paranoid_exit_no_swapgs branch. The reason we haven't seen this bug reported by users yet is probably because "paranoid" entry points are limited to the following cases: idtentry double_fault do_double_fault has_error_code=1 paranoid=2 idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK idtentry int3 do_int3 has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK idtentry machine_check do_mce has_error_code=0 paranoid=1 Amongst those entry points only machine_check is one that will interrupt an IRQS-off critical section asynchronously - and machine check events are rare. The other main asynchronous entries are NMI entries, which can be very high-freq with perf profiling, but they are special: they don't use the 'idtentry' macro but are open coded and restore user CR3 unconditionally so don't have this bug. Reported-and-tested-by: Josh Poimboeuf <jpoimboe(a)redhat.com> Reviewed-by: Andy Lutomirski <luto(a)kernel.org> Acked-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: Arjan van de Ven <arjan(a)linux.intel.com> Cc: Borislav Petkov <bp(a)alien8.de> Cc: Dan Williams <dan.j.williams(a)intel.com> Cc: Dave Hansen <dave.hansen(a)linux.intel.com> Cc: David Woodhouse <dwmw2(a)infradead.org> Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Link: http://lkml.kernel.org/r/20180214073910.boevmg65upbk3vqb@gmail.com Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/entry/entry_64.S | 1 + 1 file changed, 1 insertion(+) --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -1168,6 +1168,7 @@ ENTRY(paranoid_exit) jmp .Lparanoid_exit_restore .Lparanoid_exit_no_swapgs: TRACE_IRQS_IRETQ_DEBUG + RESTORE_CR3 scratch_reg=%rbx save_reg=%r14 .Lparanoid_exit_restore: jmp restore_regs_and_return_to_kernel END(paranoid_exit) Patches currently in stable-queue which might be from mingo(a)kernel.org are queue-4.15/selftests-x86-fix-build-bug-caused-by-the-5lvl-test-which-has-been-moved-to-the-vm-directory.patch queue-4.15/x86-entry-64-interleave-xor-register-clearing-with-push-instructions.patch queue-4.15/x86-spectre-fix-an-error-message.patch queue-4.15/nospec-move-array_index_nospec-parameter-checking-into-separate-macro.patch queue-4.15/x86-entry-64-merge-the-pop_c_regs-and-pop_extra_regs-macros-into-a-single-pop_regs-macro.patch queue-4.15/x86-gpu-add-cfl-to-early-quirks.patch queue-4.15/x86-entry-64-remove-the-unused-icebp-macro.patch queue-4.15/kvm-nvmx-set-the-cpu_based_use_msr_bitmaps-if-we-have-a-valid-l02-msr-bitmap.patch queue-4.15/x86-nvmx-properly-set-spec_ctrl-and-pred_cmd-before-merging-msrs.patch queue-4.15/x86-speculation-add-asm-msr-index.h-dependency.patch queue-4.15/x86-entry-64-use-push_and_clean_regs-in-more-cases.patch queue-4.15/x86-cpu-rename-cpu_data.x86_mask-to-cpu_data.x86_stepping.patch queue-4.15/selftests-x86-disable-tests-requiring-32-bit-support-on-pure-64-bit-systems.patch queue-4.15/x86-debug-use-ud2-for-warn.patch queue-4.15/x86-entry-64-fix-paranoid_entry-frame-pointer-warning.patch queue-4.15/x86-cpu-change-type-of-x86_cache_size-variable-to-unsigned-int.patch queue-4.15/x86-speculation-update-speculation-control-microcode-blacklist.patch queue-4.15/x86-entry-64-clear-registers-for-exceptions-interrupts-to-reduce-speculation-attack-surface.patch queue-4.15/x86-speculation-correct-speculation-control-microcode-blacklist-again.patch queue-4.15/x86-entry-64-merge-save_c_regs-and-save_extra_regs-remove-unused-extensions.patch queue-4.15/selftests-x86-do-not-rely-on-int-0x80-in-single_step_syscall.c.patch queue-4.15/selftests-x86-mpx-fix-incorrect-bounds-with-old-_sigfault.patch queue-4.15/selftests-x86-fix-vdso-selftest-segfault-for-vsyscall-none.patch queue-4.15/x86-debug-objtool-annotate-warn-related-ud2-as-reachable.patch queue-4.15/objtool-fix-segfault-in-ignore_unreachable_insn.patch queue-4.15/x86-entry-64-indent-push_and_clear_regs-and-pop_regs-properly.patch queue-4.15/selftests-x86-pkeys-remove-unused-functions.patch queue-4.15/selftests-x86-clean-up-and-document-sscanf-usage.patch queue-4.15/x86-speculation-fix-up-array_index_nospec_mask-asm-constraint.patch queue-4.15/x86-entry-64-clear-extra-registers-beyond-syscall-arguments-to-reduce-speculation-attack-surface.patch queue-4.15/kvm-x86-reduce-retpoline-performance-impact-in-slot_handle_level_range-by-always-inlining-iterator-helper-methods.patch queue-4.15/selftests-x86-do-not-rely-on-int-0x80-in-test_mremap_vdso.c.patch queue-4.15/x86-mm-pti-fix-pti-comment-in-entry_syscall_64.patch queue-4.15/x86-entry-64-get-rid-of-the-alloc_pt_gpregs_on_stack-and-save_and_clear_regs-macros.patch queue-4.15/x86-speculation-clean-up-various-spectre-related-details.patch queue-4.15/x86-kexec-make-kexec-mostly-work-in-5-level-paging-mode.patch queue-4.15/x86-entry-64-introduce-the-push_and_clean_regs-macro.patch queue-4.15/revert-x86-speculation-simplify-indirect_branch_prediction_barrier.patch queue-4.15/x86-entry-64-compat-clear-registers-for-compat-syscalls-to-reduce-speculation-attack-surface.patch queue-4.15/x86-mm-rename-flush_tlb_single-and-flush_tlb_one-to-__flush_tlb_one_.patch queue-4.15/x86-entry-64-fix-cr3-restore-in-paranoid_exit.patch

6 years, 10 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror February 2018