January 2018 - Linux-stable-mirror

[Linux-stable-mirror] Patch "kaiser: fix perf crashes" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled kaiser: fix perf crashes to the 4.9-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: kaiser-fix-perf-crashes.patch and it can be found in the queue-4.9 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 foo@baz Wed Jan 3 20:37:21 CET 2018 From: Hugh Dickins <hughd(a)google.com> Date: Wed, 23 Aug 2017 14:21:14 -0700 Subject: kaiser: fix perf crashes From: Hugh Dickins <hughd(a)google.com> Avoid perf crashes: place debug_store in the user-mapped per-cpu area instead of allocating, and use page allocator plus kaiser_add_mapping() to keep the BTS and PEBS buffers user-mapped (that is, present in the user mapping, though visible only to kernel and hardware). The PEBS fixup buffer does not need this treatment. The need for a user-mapped struct debug_store showed up before doing any conscious perf testing: in a couple of kernel paging oopses on Westmere, implicating the debug_store offset of the per-cpu area. Signed-off-by: Hugh Dickins <hughd(a)google.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/events/intel/ds.c | 57 +++++++++++++++++++++++++++++++++++---------- 1 file changed, 45 insertions(+), 12 deletions(-) --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -2,11 +2,15 @@ #include <linux/types.h> #include <linux/slab.h> +#include <asm/kaiser.h> #include <asm/perf_event.h> #include <asm/insn.h> #include "../perf_event.h" +static +DEFINE_PER_CPU_SHARED_ALIGNED_USER_MAPPED(struct debug_store, cpu_debug_store); + /* The size of a BTS record in bytes: */ #define BTS_RECORD_SIZE 24 @@ -268,6 +272,39 @@ void fini_debug_store_on_cpu(int cpu) static DEFINE_PER_CPU(void *, insn_buffer); +static void *dsalloc(size_t size, gfp_t flags, int node) +{ +#ifdef CONFIG_KAISER + unsigned int order = get_order(size); + struct page *page; + unsigned long addr; + + page = __alloc_pages_node(node, flags | __GFP_ZERO, order); + if (!page) + return NULL; + addr = (unsigned long)page_address(page); + if (kaiser_add_mapping(addr, size, __PAGE_KERNEL) < 0) { + __free_pages(page, order); + addr = 0; + } + return (void *)addr; +#else + return kmalloc_node(size, flags | __GFP_ZERO, node); +#endif +} + +static void dsfree(const void *buffer, size_t size) +{ +#ifdef CONFIG_KAISER + if (!buffer) + return; + kaiser_remove_mapping((unsigned long)buffer, size); + free_pages((unsigned long)buffer, get_order(size)); +#else + kfree(buffer); +#endif +} + static int alloc_pebs_buffer(int cpu) { struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; @@ -278,7 +315,7 @@ static int alloc_pebs_buffer(int cpu) if (!x86_pmu.pebs) return 0; - buffer = kzalloc_node(x86_pmu.pebs_buffer_size, GFP_KERNEL, node); + buffer = dsalloc(x86_pmu.pebs_buffer_size, GFP_KERNEL, node); if (unlikely(!buffer)) return -ENOMEM; @@ -289,7 +326,7 @@ static int alloc_pebs_buffer(int cpu) if (x86_pmu.intel_cap.pebs_format < 2) { ibuffer = kzalloc_node(PEBS_FIXUP_SIZE, GFP_KERNEL, node); if (!ibuffer) { - kfree(buffer); + dsfree(buffer, x86_pmu.pebs_buffer_size); return -ENOMEM; } per_cpu(insn_buffer, cpu) = ibuffer; @@ -315,7 +352,8 @@ static void release_pebs_buffer(int cpu) kfree(per_cpu(insn_buffer, cpu)); per_cpu(insn_buffer, cpu) = NULL; - kfree((void *)(unsigned long)ds->pebs_buffer_base); + dsfree((void *)(unsigned long)ds->pebs_buffer_base, + x86_pmu.pebs_buffer_size); ds->pebs_buffer_base = 0; } @@ -329,7 +367,7 @@ static int alloc_bts_buffer(int cpu) if (!x86_pmu.bts) return 0; - buffer = kzalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_NOWARN, node); + buffer = dsalloc(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_NOWARN, node); if (unlikely(!buffer)) { WARN_ONCE(1, "%s: BTS buffer allocation failure\n", __func__); return -ENOMEM; @@ -355,19 +393,15 @@ static void release_bts_buffer(int cpu) if (!ds || !x86_pmu.bts) return; - kfree((void *)(unsigned long)ds->bts_buffer_base); + dsfree((void *)(unsigned long)ds->bts_buffer_base, BTS_BUFFER_SIZE); ds->bts_buffer_base = 0; } static int alloc_ds_buffer(int cpu) { - int node = cpu_to_node(cpu); - struct debug_store *ds; - - ds = kzalloc_node(sizeof(*ds), GFP_KERNEL, node); - if (unlikely(!ds)) - return -ENOMEM; + struct debug_store *ds = per_cpu_ptr(&cpu_debug_store, cpu); + memset(ds, 0, sizeof(*ds)); per_cpu(cpu_hw_events, cpu).ds = ds; return 0; @@ -381,7 +415,6 @@ static void release_ds_buffer(int cpu) return; per_cpu(cpu_hw_events, cpu).ds = NULL; - kfree(ds); } void release_ds_buffers(void) Patches currently in stable-queue which might be from hughd(a)google.com are queue-4.9/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch queue-4.9/kaiser-add-nokaiser-boot-option-using-alternative.patch queue-4.9/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch queue-4.9/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch queue-4.9/x86-paravirt-dont-patch-flush_tlb_single.patch queue-4.9/kaiser-merged-update.patch queue-4.9/kaiser-delete-kaiser_real_switch-option.patch queue-4.9/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch queue-4.9/kaiser-fix-perf-crashes.patch queue-4.9/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch queue-4.9/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch queue-4.9/kaiser-enhanced-by-kernel-and-user-pcids.patch queue-4.9/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch queue-4.9/kaiser-align-addition-to-x86-mm-makefile.patch queue-4.9/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch queue-4.9/kaiser-stack-map-page_size-at-thread_size-page_size.patch queue-4.9/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch queue-4.9/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch queue-4.9/kaiser-do-not-set-_page_nx-on-pgd_none.patch queue-4.9/kaiser-tidied-up-asm-kaiser.h-somewhat.patch queue-4.9/kaiser-cleanups-while-trying-for-gold-link.patch queue-4.9/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch queue-4.9/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch queue-4.9/kaiser-kernel-address-isolation.patch queue-4.9/kaiser-enomem-if-kaiser_pagetable_walk-null.patch queue-4.9/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch queue-4.9/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch queue-4.9/kaiser-kaiser-depends-on-smp.patch queue-4.9/kaiser-pcid-0-for-kernel-and-128-for-user.patch

6 years, 11 months

1
0
0 0

[Linux-stable-mirror] Patch "kaiser: fix build and FIXME in alloc_ldt_struct()" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled kaiser: fix build and FIXME in alloc_ldt_struct() to the 4.9-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: kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch and it can be found in the queue-4.9 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 foo@baz Wed Jan 3 20:37:21 CET 2018 From: Hugh Dickins <hughd(a)google.com> Date: Sun, 3 Sep 2017 17:09:44 -0700 Subject: kaiser: fix build and FIXME in alloc_ldt_struct() From: Hugh Dickins <hughd(a)google.com> Include linux/kaiser.h instead of asm/kaiser.h to build ldt.c without CONFIG_KAISER. kaiser_add_mapping() does already return an error code, so fix the FIXME. Signed-off-by: Hugh Dickins <hughd(a)google.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/kernel/ldt.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -16,9 +16,9 @@ #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/uaccess.h> +#include <linux/kaiser.h> #include <asm/ldt.h> -#include <asm/kaiser.h> #include <asm/desc.h> #include <asm/mmu_context.h> #include <asm/syscalls.h> @@ -49,7 +49,7 @@ static struct ldt_struct *alloc_ldt_stru { struct ldt_struct *new_ldt; int alloc_size; - int ret = 0; + int ret; if (size > LDT_ENTRIES) return NULL; @@ -77,10 +77,8 @@ static struct ldt_struct *alloc_ldt_stru return NULL; } - // FIXME: make kaiser_add_mapping() return an error code - // when it fails - kaiser_add_mapping((unsigned long)new_ldt->entries, alloc_size, - __PAGE_KERNEL); + ret = kaiser_add_mapping((unsigned long)new_ldt->entries, alloc_size, + __PAGE_KERNEL); if (ret) { __free_ldt_struct(new_ldt); return NULL; Patches currently in stable-queue which might be from hughd(a)google.com are queue-4.9/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch queue-4.9/kaiser-add-nokaiser-boot-option-using-alternative.patch queue-4.9/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch queue-4.9/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch queue-4.9/x86-paravirt-dont-patch-flush_tlb_single.patch queue-4.9/kaiser-merged-update.patch queue-4.9/kaiser-delete-kaiser_real_switch-option.patch queue-4.9/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch queue-4.9/kaiser-fix-perf-crashes.patch queue-4.9/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch queue-4.9/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch queue-4.9/kaiser-enhanced-by-kernel-and-user-pcids.patch queue-4.9/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch queue-4.9/kaiser-align-addition-to-x86-mm-makefile.patch queue-4.9/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch queue-4.9/kaiser-stack-map-page_size-at-thread_size-page_size.patch queue-4.9/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch queue-4.9/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch queue-4.9/kaiser-do-not-set-_page_nx-on-pgd_none.patch queue-4.9/kaiser-tidied-up-asm-kaiser.h-somewhat.patch queue-4.9/kaiser-cleanups-while-trying-for-gold-link.patch queue-4.9/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch queue-4.9/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch queue-4.9/kaiser-kernel-address-isolation.patch queue-4.9/kaiser-enomem-if-kaiser_pagetable_walk-null.patch queue-4.9/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch queue-4.9/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch queue-4.9/kaiser-kaiser-depends-on-smp.patch queue-4.9/kaiser-pcid-0-for-kernel-and-128-for-user.patch

6 years, 11 months

1
0
0 0

[Linux-stable-mirror] Patch "kaiser: ENOMEM if kaiser_pagetable_walk() NULL" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled kaiser: ENOMEM if kaiser_pagetable_walk() NULL to the 4.9-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: kaiser-enomem-if-kaiser_pagetable_walk-null.patch and it can be found in the queue-4.9 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 foo@baz Wed Jan 3 20:37:21 CET 2018 From: Hugh Dickins <hughd(a)google.com> Date: Sun, 3 Sep 2017 18:48:02 -0700 Subject: kaiser: ENOMEM if kaiser_pagetable_walk() NULL From: Hugh Dickins <hughd(a)google.com> kaiser_add_user_map() took no notice when kaiser_pagetable_walk() failed. And avoid its might_sleep() when atomic (though atomic at present unused). Signed-off-by: Hugh Dickins <hughd(a)google.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/mm/kaiser.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) --- a/arch/x86/mm/kaiser.c +++ b/arch/x86/mm/kaiser.c @@ -98,11 +98,11 @@ static pte_t *kaiser_pagetable_walk(unsi pgd_t *pgd = native_get_shadow_pgd(pgd_offset_k(address)); gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO); - might_sleep(); if (is_atomic) { gfp &= ~GFP_KERNEL; gfp |= __GFP_HIGH | __GFP_ATOMIC; - } + } else + might_sleep(); if (pgd_none(*pgd)) { WARN_ONCE(1, "All shadow pgds should have been populated"); @@ -159,13 +159,17 @@ int kaiser_add_user_map(const void *__st unsigned long end_addr = PAGE_ALIGN(start_addr + size); unsigned long target_address; - for (;address < end_addr; address += PAGE_SIZE) { + for (; address < end_addr; address += PAGE_SIZE) { target_address = get_pa_from_mapping(address); if (target_address == -1) { ret = -EIO; break; } pte = kaiser_pagetable_walk(address, false); + if (!pte) { + ret = -ENOMEM; + break; + } if (pte_none(*pte)) { set_pte(pte, __pte(flags | target_address)); } else { Patches currently in stable-queue which might be from hughd(a)google.com are queue-4.9/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch queue-4.9/kaiser-add-nokaiser-boot-option-using-alternative.patch queue-4.9/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch queue-4.9/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch queue-4.9/x86-paravirt-dont-patch-flush_tlb_single.patch queue-4.9/kaiser-merged-update.patch queue-4.9/kaiser-delete-kaiser_real_switch-option.patch queue-4.9/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch queue-4.9/kaiser-fix-perf-crashes.patch queue-4.9/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch queue-4.9/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch queue-4.9/kaiser-enhanced-by-kernel-and-user-pcids.patch queue-4.9/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch queue-4.9/kaiser-align-addition-to-x86-mm-makefile.patch queue-4.9/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch queue-4.9/kaiser-stack-map-page_size-at-thread_size-page_size.patch queue-4.9/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch queue-4.9/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch queue-4.9/kaiser-do-not-set-_page_nx-on-pgd_none.patch queue-4.9/kaiser-tidied-up-asm-kaiser.h-somewhat.patch queue-4.9/kaiser-cleanups-while-trying-for-gold-link.patch queue-4.9/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch queue-4.9/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch queue-4.9/kaiser-kernel-address-isolation.patch queue-4.9/kaiser-enomem-if-kaiser_pagetable_walk-null.patch queue-4.9/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch queue-4.9/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch queue-4.9/kaiser-kaiser-depends-on-smp.patch queue-4.9/kaiser-pcid-0-for-kernel-and-128-for-user.patch

6 years, 11 months

1
0
0 0

[Linux-stable-mirror] Patch "kaiser: enhanced by kernel and user PCIDs" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled kaiser: enhanced by kernel and user PCIDs to the 4.9-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: kaiser-enhanced-by-kernel-and-user-pcids.patch and it can be found in the queue-4.9 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 foo@baz Wed Jan 3 20:37:21 CET 2018 From: Hugh Dickins <hughd(a)google.com> Date: Wed, 30 Aug 2017 16:23:00 -0700 Subject: kaiser: enhanced by kernel and user PCIDs From: Hugh Dickins <hughd(a)google.com> Merged performance improvements to Kaiser, using distinct kernel and user Process Context Identifiers to minimize the TLB flushing. [This work actually all from Dave Hansen 2017-08-30: still omitting trackswitch mods, and KAISER_REAL_SWITCH deleted.] Signed-off-by: Hugh Dickins <hughd(a)google.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/entry/entry_64.S | 10 ++++- arch/x86/entry/entry_64_compat.S | 1 arch/x86/include/asm/cpufeatures.h | 1 arch/x86/include/asm/kaiser.h | 15 ++++++- arch/x86/include/asm/pgtable_types.h | 26 +++++++++++++ arch/x86/include/asm/tlbflush.h | 54 +++++++++++++++++++++++----- arch/x86/include/uapi/asm/processor-flags.h | 3 + arch/x86/kernel/cpu/common.c | 34 +++++++++++++++++ arch/x86/kvm/x86.c | 3 + arch/x86/mm/kaiser.c | 7 +++ arch/x86/mm/tlb.c | 46 ++++++++++++++++++++++- 11 files changed, 182 insertions(+), 18 deletions(-) --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -1317,7 +1317,10 @@ ENTRY(nmi) /* %rax is saved above, so OK to clobber here */ movq %cr3, %rax pushq %rax - andq $(~KAISER_SHADOW_PGD_OFFSET), %rax + /* mask off "user" bit of pgd address and 12 PCID bits: */ + andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), %rax + /* Add back kernel PCID and "no flush" bit */ + orq X86_CR3_PCID_KERN_VAR, %rax movq %rax, %cr3 #endif call do_nmi @@ -1558,7 +1561,10 @@ end_repeat_nmi: /* %rax is saved above, so OK to clobber here */ movq %cr3, %rax pushq %rax - andq $(~KAISER_SHADOW_PGD_OFFSET), %rax + /* mask off "user" bit of pgd address and 12 PCID bits: */ + andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), %rax + /* Add back kernel PCID and "no flush" bit */ + orq X86_CR3_PCID_KERN_VAR, %rax movq %rax, %cr3 #endif --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -13,6 +13,7 @@ #include <asm/irqflags.h> #include <asm/asm.h> #include <asm/smap.h> +#include <asm/pgtable_types.h> #include <asm/kaiser.h> #include <linux/linkage.h> #include <linux/err.h> --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -189,6 +189,7 @@ #define X86_FEATURE_CPB ( 7*32+ 2) /* AMD Core Performance Boost */ #define X86_FEATURE_EPB ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */ +#define X86_FEATURE_INVPCID_SINGLE ( 7*32+ 4) /* Effectively INVPCID && CR4.PCIDE=1 */ #define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ --- a/arch/x86/include/asm/kaiser.h +++ b/arch/x86/include/asm/kaiser.h @@ -1,5 +1,8 @@ #ifndef _ASM_X86_KAISER_H #define _ASM_X86_KAISER_H + +#include <uapi/asm/processor-flags.h> /* For PCID constants */ + /* * This file includes the definitions for the KAISER feature. * KAISER is a counter measure against x86_64 side channel attacks on @@ -21,13 +24,21 @@ .macro _SWITCH_TO_KERNEL_CR3 reg movq %cr3, \reg -andq $(~KAISER_SHADOW_PGD_OFFSET), \reg +andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), \reg +orq X86_CR3_PCID_KERN_VAR, \reg movq \reg, %cr3 .endm .macro _SWITCH_TO_USER_CR3 reg movq %cr3, \reg -orq $(KAISER_SHADOW_PGD_OFFSET), \reg +andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), \reg +/* + * This can obviously be one instruction by putting the + * KAISER_SHADOW_PGD_OFFSET bit in the X86_CR3_PCID_USER_VAR. + * But, just leave it now for simplicity. + */ +orq X86_CR3_PCID_USER_VAR, \reg +orq $(KAISER_SHADOW_PGD_OFFSET), \reg movq \reg, %cr3 .endm --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -141,6 +141,32 @@ _PAGE_SOFT_DIRTY) #define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE) +/* The ASID is the lower 12 bits of CR3 */ +#define X86_CR3_PCID_ASID_MASK (_AC((1<<12)-1,UL)) + +/* Mask for all the PCID-related bits in CR3: */ +#define X86_CR3_PCID_MASK (X86_CR3_PCID_NOFLUSH | X86_CR3_PCID_ASID_MASK) +#if defined(CONFIG_KAISER) && defined(CONFIG_X86_64) +#define X86_CR3_PCID_ASID_KERN (_AC(0x4,UL)) +#define X86_CR3_PCID_ASID_USER (_AC(0x6,UL)) + +#define X86_CR3_PCID_KERN_FLUSH (X86_CR3_PCID_ASID_KERN) +#define X86_CR3_PCID_USER_FLUSH (X86_CR3_PCID_ASID_USER) +#define X86_CR3_PCID_KERN_NOFLUSH (X86_CR3_PCID_NOFLUSH | X86_CR3_PCID_ASID_KERN) +#define X86_CR3_PCID_USER_NOFLUSH (X86_CR3_PCID_NOFLUSH | X86_CR3_PCID_ASID_USER) +#else +#define X86_CR3_PCID_ASID_KERN (_AC(0x0,UL)) +#define X86_CR3_PCID_ASID_USER (_AC(0x0,UL)) +/* + * PCIDs are unsupported on 32-bit and none of these bits can be + * set in CR3: + */ +#define X86_CR3_PCID_KERN_FLUSH (0) +#define X86_CR3_PCID_USER_FLUSH (0) +#define X86_CR3_PCID_KERN_NOFLUSH (0) +#define X86_CR3_PCID_USER_NOFLUSH (0) +#endif + /* * The cache modes defined here are used to translate between pure SW usage * and the HW defined cache mode bits and/or PAT entries. --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -13,7 +13,6 @@ static inline void __invpcid(unsigned lo unsigned long type) { struct { u64 d[2]; } desc = { { pcid, addr } }; - /* * The memory clobber is because the whole point is to invalidate * stale TLB entries and, especially if we're flushing global @@ -134,14 +133,25 @@ static inline void cr4_set_bits_and_upda static inline void __native_flush_tlb(void) { + if (!cpu_feature_enabled(X86_FEATURE_INVPCID)) { + /* + * If current->mm == NULL then we borrow a mm which may change during a + * task switch and therefore we must not be preempted while we write CR3 + * back: + */ + preempt_disable(); + native_write_cr3(native_read_cr3()); + preempt_enable(); + return; + } /* - * If current->mm == NULL then we borrow a mm which may change during a - * task switch and therefore we must not be preempted while we write CR3 - * back: - */ - preempt_disable(); - native_write_cr3(native_read_cr3()); - preempt_enable(); + * We are no longer using globals with KAISER, so a + * "nonglobals" flush would work too. But, this is more + * conservative. + * + * Note, this works with CR4.PCIDE=0 or 1. + */ + invpcid_flush_all(); } static inline void __native_flush_tlb_global_irq_disabled(void) @@ -163,6 +173,8 @@ static inline void __native_flush_tlb_gl /* * Using INVPCID is considerably faster than a pair of writes * to CR4 sandwiched inside an IRQ flag save/restore. + * + * Note, this works with CR4.PCIDE=0 or 1. */ invpcid_flush_all(); return; @@ -182,7 +194,31 @@ static inline void __native_flush_tlb_gl static inline void __native_flush_tlb_single(unsigned long addr) { - asm volatile("invlpg (%0)" ::"r" (addr) : "memory"); + /* + * SIMICS #GP's if you run INVPCID with type 2/3 + * and X86_CR4_PCIDE clear. Shame! + * + * The ASIDs used below are hard-coded. But, we must not + * call invpcid(type=1/2) before CR4.PCIDE=1. Just call + * invpcid in the case we are called early. + */ + if (!this_cpu_has(X86_FEATURE_INVPCID_SINGLE)) { + asm volatile("invlpg (%0)" ::"r" (addr) : "memory"); + return; + } + /* Flush the address out of both PCIDs. */ + /* + * An optimization here might be to determine addresses + * that are only kernel-mapped and only flush the kernel + * ASID. But, userspace flushes are probably much more + * important performance-wise. + * + * Make sure to do only a single invpcid when KAISER is + * disabled and we have only a single ASID. + */ + if (X86_CR3_PCID_ASID_KERN != X86_CR3_PCID_ASID_USER) + invpcid_flush_one(X86_CR3_PCID_ASID_KERN, addr); + invpcid_flush_one(X86_CR3_PCID_ASID_USER, addr); } static inline void __flush_tlb_all(void) --- a/arch/x86/include/uapi/asm/processor-flags.h +++ b/arch/x86/include/uapi/asm/processor-flags.h @@ -77,7 +77,8 @@ #define X86_CR3_PWT _BITUL(X86_CR3_PWT_BIT) #define X86_CR3_PCD_BIT 4 /* Page Cache Disable */ #define X86_CR3_PCD _BITUL(X86_CR3_PCD_BIT) -#define X86_CR3_PCID_MASK _AC(0x00000fff,UL) /* PCID Mask */ +#define X86_CR3_PCID_NOFLUSH_BIT 63 /* Preserve old PCID */ +#define X86_CR3_PCID_NOFLUSH _BITULL(X86_CR3_PCID_NOFLUSH_BIT) /* * Intel CPU features in CR4 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -324,11 +324,45 @@ static __always_inline void setup_smap(s } } +/* + * These can have bit 63 set, so we can not just use a plain "or" + * instruction to get their value or'd into CR3. It would take + * another register. So, we use a memory reference to these + * instead. + * + * This is also handy because systems that do not support + * PCIDs just end up or'ing a 0 into their CR3, which does + * no harm. + */ +__aligned(PAGE_SIZE) unsigned long X86_CR3_PCID_KERN_VAR = 0; +__aligned(PAGE_SIZE) unsigned long X86_CR3_PCID_USER_VAR = 0; + static void setup_pcid(struct cpuinfo_x86 *c) { if (cpu_has(c, X86_FEATURE_PCID)) { if (cpu_has(c, X86_FEATURE_PGE)) { cr4_set_bits(X86_CR4_PCIDE); + /* + * These variables are used by the entry/exit + * code to change PCIDs. + */ +#ifdef CONFIG_KAISER + X86_CR3_PCID_KERN_VAR = X86_CR3_PCID_KERN_NOFLUSH; + X86_CR3_PCID_USER_VAR = X86_CR3_PCID_USER_NOFLUSH; +#endif + /* + * INVPCID has two "groups" of types: + * 1/2: Invalidate an individual address + * 3/4: Invalidate all contexts + * + * 1/2 take a PCID, but 3/4 do not. So, 3/4 + * ignore the PCID argument in the descriptor. + * But, we have to be careful not to call 1/2 + * with an actual non-zero PCID in them before + * we do the above cr4_set_bits(). + */ + if (cpu_has(c, X86_FEATURE_INVPCID)) + set_cpu_cap(c, X86_FEATURE_INVPCID_SINGLE); } else { /* * flush_tlb_all(), as currently implemented, won't --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -773,7 +773,8 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, u return 1; /* PCID can not be enabled when cr3[11:0]!=000H or EFER.LMA=0 */ - if ((kvm_read_cr3(vcpu) & X86_CR3_PCID_MASK) || !is_long_mode(vcpu)) + if ((kvm_read_cr3(vcpu) & X86_CR3_PCID_ASID_MASK) || + !is_long_mode(vcpu)) return 1; } --- a/arch/x86/mm/kaiser.c +++ b/arch/x86/mm/kaiser.c @@ -239,6 +239,8 @@ static void __init kaiser_init_all_pgds( } while (0) extern char __per_cpu_user_mapped_start[], __per_cpu_user_mapped_end[]; +extern unsigned long X86_CR3_PCID_KERN_VAR; +extern unsigned long X86_CR3_PCID_USER_VAR; /* * If anything in here fails, we will likely die on one of the * first kernel->user transitions and init will die. But, we @@ -289,6 +291,11 @@ void __init kaiser_init(void) kaiser_add_user_map_early(&debug_idt_table, sizeof(gate_desc) * NR_VECTORS, __PAGE_KERNEL); + + kaiser_add_user_map_early(&X86_CR3_PCID_KERN_VAR, PAGE_SIZE, + __PAGE_KERNEL); + kaiser_add_user_map_early(&X86_CR3_PCID_USER_VAR, PAGE_SIZE, + __PAGE_KERNEL); } /* Add a mapping to the shadow mapping, and synchronize the mappings */ --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -34,6 +34,46 @@ struct flush_tlb_info { unsigned long flush_end; }; +static void load_new_mm_cr3(pgd_t *pgdir) +{ + unsigned long new_mm_cr3 = __pa(pgdir); + + /* + * KAISER, plus PCIDs needs some extra work here. But, + * if either of features is not present, we need no + * PCIDs here and just do a normal, full TLB flush with + * the write_cr3() + */ + if (!IS_ENABLED(CONFIG_KAISER) || + !cpu_feature_enabled(X86_FEATURE_PCID)) + goto out_set_cr3; + /* + * We reuse the same PCID for different tasks, so we must + * flush all the entires for the PCID out when we change + * tasks. + */ + new_mm_cr3 = X86_CR3_PCID_KERN_FLUSH | __pa(pgdir); + + /* + * The flush from load_cr3() may leave old TLB entries + * for userspace in place. We must flush that context + * separately. We can theoretically delay doing this + * until we actually load up the userspace CR3, but + * that's a bit tricky. We have to have the "need to + * flush userspace PCID" bit per-cpu and check it in the + * exit-to-userspace paths. + */ + invpcid_flush_single_context(X86_CR3_PCID_ASID_USER); + +out_set_cr3: + /* + * Caution: many callers of this function expect + * that load_cr3() is serializing and orders TLB + * fills with respect to the mm_cpumask writes. + */ + write_cr3(new_mm_cr3); +} + /* * We cannot call mmdrop() because we are in interrupt context, * instead update mm->cpu_vm_mask. @@ -45,7 +85,7 @@ void leave_mm(int cpu) BUG(); if (cpumask_test_cpu(cpu, mm_cpumask(active_mm))) { cpumask_clear_cpu(cpu, mm_cpumask(active_mm)); - load_cr3(swapper_pg_dir); + load_new_mm_cr3(swapper_pg_dir); /* * This gets called in the idle path where RCU * functions differently. Tracing normally @@ -120,7 +160,7 @@ void switch_mm_irqs_off(struct mm_struct * ordering guarantee we need. * */ - load_cr3(next->pgd); + load_new_mm_cr3(next->pgd); trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); @@ -167,7 +207,7 @@ void switch_mm_irqs_off(struct mm_struct * As above, load_cr3() is serializing and orders TLB * fills with respect to the mm_cpumask write. */ - load_cr3(next->pgd); + load_new_mm_cr3(next->pgd); trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); load_mm_cr4(next); load_mm_ldt(next); Patches currently in stable-queue which might be from hughd(a)google.com are queue-4.9/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch queue-4.9/kaiser-add-nokaiser-boot-option-using-alternative.patch queue-4.9/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch queue-4.9/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch queue-4.9/x86-paravirt-dont-patch-flush_tlb_single.patch queue-4.9/kaiser-merged-update.patch queue-4.9/kaiser-delete-kaiser_real_switch-option.patch queue-4.9/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch queue-4.9/kaiser-fix-perf-crashes.patch queue-4.9/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch queue-4.9/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch queue-4.9/kaiser-enhanced-by-kernel-and-user-pcids.patch queue-4.9/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch queue-4.9/kaiser-align-addition-to-x86-mm-makefile.patch queue-4.9/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch queue-4.9/kaiser-stack-map-page_size-at-thread_size-page_size.patch queue-4.9/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch queue-4.9/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch queue-4.9/kaiser-do-not-set-_page_nx-on-pgd_none.patch queue-4.9/kaiser-tidied-up-asm-kaiser.h-somewhat.patch queue-4.9/kaiser-cleanups-while-trying-for-gold-link.patch queue-4.9/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch queue-4.9/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch queue-4.9/kaiser-kernel-address-isolation.patch queue-4.9/kaiser-enomem-if-kaiser_pagetable_walk-null.patch queue-4.9/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch queue-4.9/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch queue-4.9/kaiser-kaiser-depends-on-smp.patch queue-4.9/kaiser-pcid-0-for-kernel-and-128-for-user.patch

6 years, 11 months

1
0
0 0

[Linux-stable-mirror] Patch "kaiser: drop is_atomic arg to kaiser_pagetable_walk()" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled kaiser: drop is_atomic arg to kaiser_pagetable_walk() to the 4.9-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: kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch and it can be found in the queue-4.9 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 foo@baz Wed Jan 3 20:37:21 CET 2018 From: Hugh Dickins <hughd(a)google.com> Date: Sun, 29 Oct 2017 11:36:19 -0700 Subject: kaiser: drop is_atomic arg to kaiser_pagetable_walk() From: Hugh Dickins <hughd(a)google.com> I have not observed a might_sleep() warning from setup_fixmap_gdt()'s use of kaiser_add_mapping() in our tree (why not?), but like upstream we have not provided a way for that to pass is_atomic true down to kaiser_pagetable_walk(), and at startup it's far from a likely source of trouble: so just delete the walk's is_atomic arg and might_sleep(). Signed-off-by: Hugh Dickins <hughd(a)google.com> Acked-by: Jiri Kosina <jkosina(a)suse.cz> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/mm/kaiser.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) --- a/arch/x86/mm/kaiser.c +++ b/arch/x86/mm/kaiser.c @@ -107,19 +107,13 @@ static inline unsigned long get_pa_from_ * * Returns a pointer to a PTE on success, or NULL on failure. */ -static pte_t *kaiser_pagetable_walk(unsigned long address, bool is_atomic) +static pte_t *kaiser_pagetable_walk(unsigned long address) { pmd_t *pmd; pud_t *pud; pgd_t *pgd = native_get_shadow_pgd(pgd_offset_k(address)); gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO); - if (is_atomic) { - gfp &= ~GFP_KERNEL; - gfp |= __GFP_HIGH | __GFP_ATOMIC; - } else - might_sleep(); - if (pgd_none(*pgd)) { WARN_ONCE(1, "All shadow pgds should have been populated"); return NULL; @@ -194,7 +188,7 @@ static int kaiser_add_user_map(const voi ret = -EIO; break; } - pte = kaiser_pagetable_walk(address, false); + pte = kaiser_pagetable_walk(address); if (!pte) { ret = -ENOMEM; break; Patches currently in stable-queue which might be from hughd(a)google.com are queue-4.9/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch queue-4.9/kaiser-add-nokaiser-boot-option-using-alternative.patch queue-4.9/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch queue-4.9/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch queue-4.9/x86-paravirt-dont-patch-flush_tlb_single.patch queue-4.9/kaiser-merged-update.patch queue-4.9/kaiser-delete-kaiser_real_switch-option.patch queue-4.9/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch queue-4.9/kaiser-fix-perf-crashes.patch queue-4.9/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch queue-4.9/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch queue-4.9/kaiser-enhanced-by-kernel-and-user-pcids.patch queue-4.9/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch queue-4.9/kaiser-align-addition-to-x86-mm-makefile.patch queue-4.9/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch queue-4.9/kaiser-stack-map-page_size-at-thread_size-page_size.patch queue-4.9/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch queue-4.9/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch queue-4.9/kaiser-do-not-set-_page_nx-on-pgd_none.patch queue-4.9/kaiser-tidied-up-asm-kaiser.h-somewhat.patch queue-4.9/kaiser-cleanups-while-trying-for-gold-link.patch queue-4.9/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch queue-4.9/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch queue-4.9/kaiser-kernel-address-isolation.patch queue-4.9/kaiser-enomem-if-kaiser_pagetable_walk-null.patch queue-4.9/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch queue-4.9/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch queue-4.9/kaiser-kaiser-depends-on-smp.patch queue-4.9/kaiser-pcid-0-for-kernel-and-128-for-user.patch

6 years, 11 months

1
0
0 0

[Linux-stable-mirror] Patch "kaiser: do not set _PAGE_NX on pgd_none" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled kaiser: do not set _PAGE_NX on pgd_none to the 4.9-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: kaiser-do-not-set-_page_nx-on-pgd_none.patch and it can be found in the queue-4.9 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 foo@baz Wed Jan 3 20:37:21 CET 2018 From: Hugh Dickins <hughd(a)google.com> Date: Tue, 5 Sep 2017 12:05:01 -0700 Subject: kaiser: do not set _PAGE_NX on pgd_none From: Hugh Dickins <hughd(a)google.com> native_pgd_clear() uses native_set_pgd(), so native_set_pgd() must avoid setting the _PAGE_NX bit on an otherwise pgd_none() entry: usually that just generated a warning on exit, but sometimes more mysterious and damaging failures (our production machines could not complete booting). The original fix to this just avoided adding _PAGE_NX to an empty entry; but eventually more problems surfaced with kexec, and EFI mapping expected to be a problem too. So now instead change native_set_pgd() to update shadow only if _PAGE_USER: A few places (kernel/machine_kexec_64.c, platform/efi/efi_64.c for sure) use set_pgd() to set up a temporary internal virtual address space, with physical pages remapped at what Kaiser regards as userspace addresses: Kaiser then assumes a shadow pgd follows, which it will try to corrupt. This appears to be responsible for the recent kexec and kdump failures; though it's unclear how those did not manifest as a problem before. Ah, the shadow pgd will only be assumed to "follow" if the requested pgd is on an even-numbered page: so I suppose it was going wrong 50% of the time all along. What we need is a flag to set_pgd(), to tell it we're dealing with userspace. Er, isn't that what the pgd's _PAGE_USER bit is saying? Add a test for that. But we cannot do the same for pgd_clear() (which may be called to clear corrupted entries - set aside the question of "corrupt in which pgd?" until later), so there just rely on pgd_clear() not being called in the problematic cases - with a WARN_ON_ONCE() which should fire half the time if it is. But this is getting too big for an inline function: move it into arch/x86/mm/kaiser.c (which then demands a boot/compressed mod); and de-void and de-space native_get_shadow/normal_pgd() while here. Also make an unnecessary change to KASLR's init_trampoline(): it was using set_pgd() to assign a pgd-value to a global variable (not in a pg directory page), which was rather scary given Kaiser's previous set_pgd() implementation: not a problem now, but too scary to leave as was, it could easily blow up if we have to change set_pgd() again. Signed-off-by: Hugh Dickins <hughd(a)google.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/boot/compressed/misc.h | 1 arch/x86/include/asm/pgtable_64.h | 51 +++++++++----------------------------- arch/x86/mm/kaiser.c | 42 +++++++++++++++++++++++++++++++ arch/x86/mm/kaslr.c | 4 +- 4 files changed, 58 insertions(+), 40 deletions(-) --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -9,6 +9,7 @@ */ #undef CONFIG_PARAVIRT #undef CONFIG_PARAVIRT_SPINLOCKS +#undef CONFIG_KAISER #undef CONFIG_KASAN #include <linux/linkage.h> --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -107,61 +107,36 @@ static inline void native_pud_clear(pud_ } #ifdef CONFIG_KAISER -static inline pgd_t * native_get_shadow_pgd(pgd_t *pgdp) +extern pgd_t kaiser_set_shadow_pgd(pgd_t *pgdp, pgd_t pgd); + +static inline pgd_t *native_get_shadow_pgd(pgd_t *pgdp) { - return (pgd_t *)(void*)((unsigned long)(void*)pgdp | (unsigned long)PAGE_SIZE); + return (pgd_t *)((unsigned long)pgdp | (unsigned long)PAGE_SIZE); } -static inline pgd_t * native_get_normal_pgd(pgd_t *pgdp) +static inline pgd_t *native_get_normal_pgd(pgd_t *pgdp) { - return (pgd_t *)(void*)((unsigned long)(void*)pgdp & ~(unsigned long)PAGE_SIZE); + return (pgd_t *)((unsigned long)pgdp & ~(unsigned long)PAGE_SIZE); } #else -static inline pgd_t * native_get_shadow_pgd(pgd_t *pgdp) +static inline pgd_t kaiser_set_shadow_pgd(pgd_t *pgdp, pgd_t pgd) +{ + return pgd; +} +static inline pgd_t *native_get_shadow_pgd(pgd_t *pgdp) { BUILD_BUG_ON(1); return NULL; } -static inline pgd_t * native_get_normal_pgd(pgd_t *pgdp) +static inline pgd_t *native_get_normal_pgd(pgd_t *pgdp) { return pgdp; } #endif /* CONFIG_KAISER */ -/* - * Page table pages are page-aligned. The lower half of the top - * level is used for userspace and the top half for the kernel. - * This returns true for user pages that need to get copied into - * both the user and kernel copies of the page tables, and false - * for kernel pages that should only be in the kernel copy. - */ -static inline bool is_userspace_pgd(void *__ptr) -{ - unsigned long ptr = (unsigned long)__ptr; - - return ((ptr % PAGE_SIZE) < (PAGE_SIZE / 2)); -} - static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd) { -#ifdef CONFIG_KAISER - pteval_t extra_kern_pgd_flags = 0; - /* Do we need to also populate the shadow pgd? */ - if (is_userspace_pgd(pgdp)) { - native_get_shadow_pgd(pgdp)->pgd = pgd.pgd; - /* - * Even if the entry is *mapping* userspace, ensure - * that userspace can not use it. This way, if we - * get out to userspace running on the kernel CR3, - * userspace will crash instead of running. - */ - extra_kern_pgd_flags = _PAGE_NX; - } - pgdp->pgd = pgd.pgd; - pgdp->pgd |= extra_kern_pgd_flags; -#else /* CONFIG_KAISER */ - *pgdp = pgd; -#endif + *pgdp = kaiser_set_shadow_pgd(pgdp, pgd); } static inline void native_pgd_clear(pgd_t *pgd) --- a/arch/x86/mm/kaiser.c +++ b/arch/x86/mm/kaiser.c @@ -302,4 +302,46 @@ void kaiser_remove_mapping(unsigned long unmap_pud_range_nofree(pgd, addr, end); } } + +/* + * Page table pages are page-aligned. The lower half of the top + * level is used for userspace and the top half for the kernel. + * This returns true for user pages that need to get copied into + * both the user and kernel copies of the page tables, and false + * for kernel pages that should only be in the kernel copy. + */ +static inline bool is_userspace_pgd(pgd_t *pgdp) +{ + return ((unsigned long)pgdp % PAGE_SIZE) < (PAGE_SIZE / 2); +} + +pgd_t kaiser_set_shadow_pgd(pgd_t *pgdp, pgd_t pgd) +{ + /* + * Do we need to also populate the shadow pgd? Check _PAGE_USER to + * skip cases like kexec and EFI which make temporary low mappings. + */ + if (pgd.pgd & _PAGE_USER) { + if (is_userspace_pgd(pgdp)) { + native_get_shadow_pgd(pgdp)->pgd = pgd.pgd; + /* + * Even if the entry is *mapping* userspace, ensure + * that userspace can not use it. This way, if we + * get out to userspace running on the kernel CR3, + * userspace will crash instead of running. + */ + pgd.pgd |= _PAGE_NX; + } + } else if (!pgd.pgd) { + /* + * pgd_clear() cannot check _PAGE_USER, and is even used to + * clear corrupted pgd entries: so just rely on cases like + * kexec and EFI never to be using pgd_clear(). + */ + if (!WARN_ON_ONCE((unsigned long)pgdp & PAGE_SIZE) && + is_userspace_pgd(pgdp)) + native_get_shadow_pgd(pgdp)->pgd = pgd.pgd; + } + return pgd; +} #endif /* CONFIG_KAISER */ --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -189,6 +189,6 @@ void __meminit init_trampoline(void) *pud_tramp = *pud; } - set_pgd(&trampoline_pgd_entry, - __pgd(_KERNPG_TABLE | __pa(pud_page_tramp))); + /* Avoid set_pgd(), in case it's complicated by CONFIG_KAISER */ + trampoline_pgd_entry = __pgd(_KERNPG_TABLE | __pa(pud_page_tramp)); } Patches currently in stable-queue which might be from hughd(a)google.com are queue-4.9/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch queue-4.9/kaiser-add-nokaiser-boot-option-using-alternative.patch queue-4.9/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch queue-4.9/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch queue-4.9/x86-paravirt-dont-patch-flush_tlb_single.patch queue-4.9/kaiser-merged-update.patch queue-4.9/kaiser-delete-kaiser_real_switch-option.patch queue-4.9/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch queue-4.9/kaiser-fix-perf-crashes.patch queue-4.9/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch queue-4.9/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch queue-4.9/kaiser-enhanced-by-kernel-and-user-pcids.patch queue-4.9/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch queue-4.9/kaiser-align-addition-to-x86-mm-makefile.patch queue-4.9/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch queue-4.9/kaiser-stack-map-page_size-at-thread_size-page_size.patch queue-4.9/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch queue-4.9/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch queue-4.9/kaiser-do-not-set-_page_nx-on-pgd_none.patch queue-4.9/kaiser-tidied-up-asm-kaiser.h-somewhat.patch queue-4.9/kaiser-cleanups-while-trying-for-gold-link.patch queue-4.9/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch queue-4.9/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch queue-4.9/kaiser-kernel-address-isolation.patch queue-4.9/kaiser-enomem-if-kaiser_pagetable_walk-null.patch queue-4.9/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch queue-4.9/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch queue-4.9/kaiser-kaiser-depends-on-smp.patch queue-4.9/kaiser-pcid-0-for-kernel-and-128-for-user.patch

6 years, 11 months

1
0
0 0

[Linux-stable-mirror] Patch "kaiser: disabled on Xen PV" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled kaiser: disabled on Xen PV to the 4.9-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: kaiser-disabled-on-xen-pv.patch and it can be found in the queue-4.9 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 foo@baz Wed Jan 3 20:37:21 CET 2018 From: Jiri Kosina <jkosina(a)suse.cz> Date: Tue, 2 Jan 2018 14:19:49 +0100 Subject: kaiser: disabled on Xen PV From: Jiri Kosina <jkosina(a)suse.cz> Kaiser cannot be used on paravirtualized MMUs (namely reading and writing CR3). This does not work with KAISER as the CR3 switch from and to user space PGD would require to map the whole XEN_PV machinery into both. More importantly, enabling KAISER on Xen PV doesn't make too much sense, as PV guests use distinct %cr3 values for kernel and user already. Signed-off-by: Jiri Kosina <jkosina(a)suse.cz> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/mm/kaiser.c | 5 +++++ 1 file changed, 5 insertions(+) --- a/arch/x86/mm/kaiser.c +++ b/arch/x86/mm/kaiser.c @@ -263,6 +263,9 @@ void __init kaiser_check_boottime_disabl char arg[5]; int ret; + if (boot_cpu_has(X86_FEATURE_XENPV)) + goto silent_disable; + ret = cmdline_find_option(boot_command_line, "pti", arg, sizeof(arg)); if (ret > 0) { if (!strncmp(arg, "on", 2)) @@ -290,6 +293,8 @@ enable: disable: pr_info("Kernel/User page tables isolation: disabled\n"); + +silent_disable: kaiser_enabled = 0; setup_clear_cpu_cap(X86_FEATURE_KAISER); } Patches currently in stable-queue which might be from jkosina(a)suse.cz are queue-4.9/kaiser-add-nokaiser-boot-option-using-alternative.patch queue-4.9/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch queue-4.9/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch queue-4.9/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch queue-4.9/kaiser-disabled-on-xen-pv.patch queue-4.9/kaiser-kernel-address-isolation.patch queue-4.9/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch

6 years, 11 months

1
0
0 0

[Linux-stable-mirror] Patch "kaiser: asm/tlbflush.h handle noPGE at lower level" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled kaiser: asm/tlbflush.h handle noPGE at lower level to the 4.9-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: kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch and it can be found in the queue-4.9 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 foo@baz Wed Jan 3 20:37:21 CET 2018 From: Hugh Dickins <hughd(a)google.com> Date: Sat, 4 Nov 2017 18:23:24 -0700 Subject: kaiser: asm/tlbflush.h handle noPGE at lower level From: Hugh Dickins <hughd(a)google.com> I found asm/tlbflush.h too twisty, and think it safer not to avoid __native_flush_tlb_global_irq_disabled() in the kaiser_enabled case, but instead let it handle kaiser_enabled along with cr3: it can just use __native_flush_tlb() for that, no harm in re-disabling preemption. (This is not the same change as Kirill and Dave have suggested for upstream, flipping PGE in cr4: that's neat, but needs a cpu_has_pge check; cr3 is enough for kaiser, and thought to be cheaper than cr4.) Also delete the X86_FEATURE_INVPCID invpcid_flush_all_nonglobals() preference from __native_flush_tlb(): unlike the invpcid_flush_all() preference in __native_flush_tlb_global(), it's not seen in upstream 4.14, and was recently reported to be surprisingly slow. Signed-off-by: Hugh Dickins <hughd(a)google.com> Acked-by: Jiri Kosina <jkosina(a)suse.cz> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/include/asm/tlbflush.h | 27 +++------------------------ 1 file changed, 3 insertions(+), 24 deletions(-) --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -152,14 +152,6 @@ static inline void kaiser_flush_tlb_on_r static inline void __native_flush_tlb(void) { - if (this_cpu_has(X86_FEATURE_INVPCID)) { - /* - * Note, this works with CR4.PCIDE=0 or 1. - */ - invpcid_flush_all_nonglobals(); - return; - } - /* * If current->mm == NULL then we borrow a mm which may change during a * task switch and therefore we must not be preempted while we write CR3 @@ -183,11 +175,8 @@ static inline void __native_flush_tlb_gl /* restore PGE as it was before */ native_write_cr4(cr4); } else { - /* - * x86_64 microcode update comes this way when CR4.PGE is not - * enabled, and it's safer for all callers to allow this case. - */ - native_write_cr3(native_read_cr3()); + /* do it with cr3, letting kaiser flush user PCID */ + __native_flush_tlb(); } } @@ -195,12 +184,6 @@ static inline void __native_flush_tlb_gl { unsigned long flags; - if (kaiser_enabled) { - /* Globals are not used at all */ - __native_flush_tlb(); - return; - } - if (this_cpu_has(X86_FEATURE_INVPCID)) { /* * Using INVPCID is considerably faster than a pair of writes @@ -256,11 +239,7 @@ static inline void __native_flush_tlb_si static inline void __flush_tlb_all(void) { - if (boot_cpu_has(X86_FEATURE_PGE)) - __flush_tlb_global(); - else - __flush_tlb(); - + __flush_tlb_global(); /* * Note: if we somehow had PCID but not PGE, then this wouldn't work -- * we'd end up flushing kernel translations for the current ASID but Patches currently in stable-queue which might be from hughd(a)google.com are queue-4.9/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch queue-4.9/kaiser-add-nokaiser-boot-option-using-alternative.patch queue-4.9/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch queue-4.9/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch queue-4.9/x86-paravirt-dont-patch-flush_tlb_single.patch queue-4.9/kaiser-merged-update.patch queue-4.9/kaiser-delete-kaiser_real_switch-option.patch queue-4.9/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch queue-4.9/kaiser-fix-perf-crashes.patch queue-4.9/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch queue-4.9/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch queue-4.9/kaiser-enhanced-by-kernel-and-user-pcids.patch queue-4.9/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch queue-4.9/kaiser-align-addition-to-x86-mm-makefile.patch queue-4.9/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch queue-4.9/kaiser-stack-map-page_size-at-thread_size-page_size.patch queue-4.9/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch queue-4.9/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch queue-4.9/kaiser-do-not-set-_page_nx-on-pgd_none.patch queue-4.9/kaiser-tidied-up-asm-kaiser.h-somewhat.patch queue-4.9/kaiser-cleanups-while-trying-for-gold-link.patch queue-4.9/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch queue-4.9/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch queue-4.9/kaiser-kernel-address-isolation.patch queue-4.9/kaiser-enomem-if-kaiser_pagetable_walk-null.patch queue-4.9/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch queue-4.9/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch queue-4.9/kaiser-kaiser-depends-on-smp.patch queue-4.9/kaiser-pcid-0-for-kernel-and-128-for-user.patch

6 years, 11 months

1
0
0 0

[Linux-stable-mirror] Patch "kaiser: delete KAISER_REAL_SWITCH option" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled kaiser: delete KAISER_REAL_SWITCH option to the 4.9-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: kaiser-delete-kaiser_real_switch-option.patch and it can be found in the queue-4.9 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 foo@baz Wed Jan 3 20:37:21 CET 2018 From: Hugh Dickins <hughd(a)google.com> Date: Sun, 3 Sep 2017 18:30:43 -0700 Subject: kaiser: delete KAISER_REAL_SWITCH option From: Hugh Dickins <hughd(a)google.com> We fail to see what CONFIG_KAISER_REAL_SWITCH is for: it seems to be left over from early development, and now just obscures tricky parts of the code. Delete it before adding PCIDs, or nokaiser boot option. (Or if there is some good reason to keep the option, then it needs a help text - and a "depends on KAISER", so that all those without KAISER are not asked the question. But we'd much rather delete it.) Signed-off-by: Hugh Dickins <hughd(a)google.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/entry/entry_64.S | 4 ---- arch/x86/include/asm/kaiser.h | 4 ---- security/Kconfig | 4 ---- 3 files changed, 12 deletions(-) --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -1317,9 +1317,7 @@ ENTRY(nmi) /* %rax is saved above, so OK to clobber here */ movq %cr3, %rax pushq %rax -#ifdef CONFIG_KAISER_REAL_SWITCH andq $(~KAISER_SHADOW_PGD_OFFSET), %rax -#endif movq %rax, %cr3 #endif call do_nmi @@ -1560,9 +1558,7 @@ end_repeat_nmi: /* %rax is saved above, so OK to clobber here */ movq %cr3, %rax pushq %rax -#ifdef CONFIG_KAISER_REAL_SWITCH andq $(~KAISER_SHADOW_PGD_OFFSET), %rax -#endif movq %rax, %cr3 #endif --- a/arch/x86/include/asm/kaiser.h +++ b/arch/x86/include/asm/kaiser.h @@ -21,17 +21,13 @@ .macro _SWITCH_TO_KERNEL_CR3 reg movq %cr3, \reg -#ifdef CONFIG_KAISER_REAL_SWITCH andq $(~KAISER_SHADOW_PGD_OFFSET), \reg -#endif movq \reg, %cr3 .endm .macro _SWITCH_TO_USER_CR3 reg movq %cr3, \reg -#ifdef CONFIG_KAISER_REAL_SWITCH orq $(KAISER_SHADOW_PGD_OFFSET), \reg -#endif movq \reg, %cr3 .endm --- a/security/Kconfig +++ b/security/Kconfig @@ -41,10 +41,6 @@ config KAISER If you are unsure how to answer this question, answer Y. -config KAISER_REAL_SWITCH - bool "KAISER: actually switch page tables" - default y - config SECURITYFS bool "Enable the securityfs filesystem" help Patches currently in stable-queue which might be from hughd(a)google.com are queue-4.9/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch queue-4.9/kaiser-add-nokaiser-boot-option-using-alternative.patch queue-4.9/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch queue-4.9/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch queue-4.9/x86-paravirt-dont-patch-flush_tlb_single.patch queue-4.9/kaiser-merged-update.patch queue-4.9/kaiser-delete-kaiser_real_switch-option.patch queue-4.9/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch queue-4.9/kaiser-fix-perf-crashes.patch queue-4.9/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch queue-4.9/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch queue-4.9/kaiser-enhanced-by-kernel-and-user-pcids.patch queue-4.9/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch queue-4.9/kaiser-align-addition-to-x86-mm-makefile.patch queue-4.9/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch queue-4.9/kaiser-stack-map-page_size-at-thread_size-page_size.patch queue-4.9/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch queue-4.9/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch queue-4.9/kaiser-do-not-set-_page_nx-on-pgd_none.patch queue-4.9/kaiser-tidied-up-asm-kaiser.h-somewhat.patch queue-4.9/kaiser-cleanups-while-trying-for-gold-link.patch queue-4.9/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch queue-4.9/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch queue-4.9/kaiser-kernel-address-isolation.patch queue-4.9/kaiser-enomem-if-kaiser_pagetable_walk-null.patch queue-4.9/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch queue-4.9/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch queue-4.9/kaiser-kaiser-depends-on-smp.patch queue-4.9/kaiser-pcid-0-for-kernel-and-128-for-user.patch

6 years, 11 months

1
0
0 0

[Linux-stable-mirror] Patch "kaiser: cleanups while trying for gold link" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled kaiser: cleanups while trying for gold link to the 4.9-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: kaiser-cleanups-while-trying-for-gold-link.patch and it can be found in the queue-4.9 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 foo@baz Wed Jan 3 20:37:21 CET 2018 From: Hugh Dickins <hughd(a)google.com> Date: Mon, 21 Aug 2017 20:11:43 -0700 Subject: kaiser: cleanups while trying for gold link From: Hugh Dickins <hughd(a)google.com> While trying to get our gold link to work, four cleanups: matched the gdt_page declaration to its definition; in fiddling unsuccessfully with PERCPU_INPUT(), lined up backslashes; lined up the backslashes according to convention in percpu-defs.h; deleted the unused irq_stack_pointer addition to irq_stack_union. Sad to report that aligning backslashes does not appear to help gold align to 8192: but while these did not help, they are worth keeping. Signed-off-by: Hugh Dickins <hughd(a)google.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/include/asm/desc.h | 2 +- arch/x86/include/asm/processor.h | 5 ----- include/asm-generic/vmlinux.lds.h | 18 ++++++++---------- include/linux/percpu-defs.h | 24 ++++++++++++------------ 4 files changed, 21 insertions(+), 28 deletions(-) --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -43,7 +43,7 @@ struct gdt_page { struct desc_struct gdt[GDT_ENTRIES]; } __attribute__((aligned(PAGE_SIZE))); -DECLARE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page); +DECLARE_PER_CPU_PAGE_ALIGNED_USER_MAPPED(struct gdt_page, gdt_page); static inline struct desc_struct *get_cpu_gdt_table(unsigned int cpu) { --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -335,11 +335,6 @@ union irq_stack_union { char gs_base[40]; unsigned long stack_canary; }; - - struct { - char irq_stack_pointer[64]; - char unused[IRQ_STACK_SIZE - 64]; - }; }; DECLARE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union) __visible; --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -778,16 +778,14 @@ */ #define PERCPU_INPUT(cacheline) \ VMLINUX_SYMBOL(__per_cpu_start) = .; \ - \ - VMLINUX_SYMBOL(__per_cpu_user_mapped_start) = .; \ - *(.data..percpu..first) \ - . = ALIGN(cacheline); \ - *(.data..percpu..user_mapped) \ - *(.data..percpu..user_mapped..shared_aligned) \ - . = ALIGN(PAGE_SIZE); \ - *(.data..percpu..user_mapped..page_aligned) \ - VMLINUX_SYMBOL(__per_cpu_user_mapped_end) = .; \ - \ + VMLINUX_SYMBOL(__per_cpu_user_mapped_start) = .; \ + *(.data..percpu..first) \ + . = ALIGN(cacheline); \ + *(.data..percpu..user_mapped) \ + *(.data..percpu..user_mapped..shared_aligned) \ + . = ALIGN(PAGE_SIZE); \ + *(.data..percpu..user_mapped..page_aligned) \ + VMLINUX_SYMBOL(__per_cpu_user_mapped_end) = .; \ . = ALIGN(PAGE_SIZE); \ *(.data..percpu..page_aligned) \ . = ALIGN(cacheline); \ --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -121,10 +121,10 @@ #define DEFINE_PER_CPU(type, name) \ DEFINE_PER_CPU_SECTION(type, name, "") -#define DECLARE_PER_CPU_USER_MAPPED(type, name) \ +#define DECLARE_PER_CPU_USER_MAPPED(type, name) \ DECLARE_PER_CPU_SECTION(type, name, USER_MAPPED_SECTION) -#define DEFINE_PER_CPU_USER_MAPPED(type, name) \ +#define DEFINE_PER_CPU_USER_MAPPED(type, name) \ DEFINE_PER_CPU_SECTION(type, name, USER_MAPPED_SECTION) /* @@ -156,11 +156,11 @@ DEFINE_PER_CPU_SECTION(type, name, PER_CPU_SHARED_ALIGNED_SECTION) \ ____cacheline_aligned_in_smp -#define DECLARE_PER_CPU_SHARED_ALIGNED_USER_MAPPED(type, name) \ +#define DECLARE_PER_CPU_SHARED_ALIGNED_USER_MAPPED(type, name) \ DECLARE_PER_CPU_SECTION(type, name, USER_MAPPED_SECTION PER_CPU_SHARED_ALIGNED_SECTION) \ ____cacheline_aligned_in_smp -#define DEFINE_PER_CPU_SHARED_ALIGNED_USER_MAPPED(type, name) \ +#define DEFINE_PER_CPU_SHARED_ALIGNED_USER_MAPPED(type, name) \ DEFINE_PER_CPU_SECTION(type, name, USER_MAPPED_SECTION PER_CPU_SHARED_ALIGNED_SECTION) \ ____cacheline_aligned_in_smp @@ -185,18 +185,18 @@ /* * Declaration/definition used for per-CPU variables that must be page aligned and need to be mapped in user mode. */ -#define DECLARE_PER_CPU_PAGE_ALIGNED_USER_MAPPED(type, name) \ - DECLARE_PER_CPU_SECTION(type, name, USER_MAPPED_SECTION"..page_aligned") \ - __aligned(PAGE_SIZE) - -#define DEFINE_PER_CPU_PAGE_ALIGNED_USER_MAPPED(type, name) \ - DEFINE_PER_CPU_SECTION(type, name, USER_MAPPED_SECTION"..page_aligned") \ - __aligned(PAGE_SIZE) +#define DECLARE_PER_CPU_PAGE_ALIGNED_USER_MAPPED(type, name) \ + DECLARE_PER_CPU_SECTION(type, name, USER_MAPPED_SECTION"..page_aligned") \ + __aligned(PAGE_SIZE) + +#define DEFINE_PER_CPU_PAGE_ALIGNED_USER_MAPPED(type, name) \ + DEFINE_PER_CPU_SECTION(type, name, USER_MAPPED_SECTION"..page_aligned") \ + __aligned(PAGE_SIZE) /* * Declaration/definition used for per-CPU variables that must be read mostly. */ -#define DECLARE_PER_CPU_READ_MOSTLY(type, name) \ +#define DECLARE_PER_CPU_READ_MOSTLY(type, name) \ DECLARE_PER_CPU_SECTION(type, name, "..read_mostly") #define DEFINE_PER_CPU_READ_MOSTLY(type, name) \ Patches currently in stable-queue which might be from hughd(a)google.com are queue-4.9/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch queue-4.9/kaiser-add-nokaiser-boot-option-using-alternative.patch queue-4.9/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch queue-4.9/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch queue-4.9/x86-paravirt-dont-patch-flush_tlb_single.patch queue-4.9/kaiser-merged-update.patch queue-4.9/kaiser-delete-kaiser_real_switch-option.patch queue-4.9/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch queue-4.9/kaiser-fix-perf-crashes.patch queue-4.9/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch queue-4.9/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch queue-4.9/kaiser-enhanced-by-kernel-and-user-pcids.patch queue-4.9/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch queue-4.9/kaiser-align-addition-to-x86-mm-makefile.patch queue-4.9/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch queue-4.9/kaiser-stack-map-page_size-at-thread_size-page_size.patch queue-4.9/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch queue-4.9/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch queue-4.9/kaiser-do-not-set-_page_nx-on-pgd_none.patch queue-4.9/kaiser-tidied-up-asm-kaiser.h-somewhat.patch queue-4.9/kaiser-cleanups-while-trying-for-gold-link.patch queue-4.9/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch queue-4.9/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch queue-4.9/kaiser-kernel-address-isolation.patch queue-4.9/kaiser-enomem-if-kaiser_pagetable_walk-null.patch queue-4.9/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch queue-4.9/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch queue-4.9/kaiser-kaiser-depends-on-smp.patch queue-4.9/kaiser-pcid-0-for-kernel-and-128-for-user.patch

6 years, 11 months

1
0
0 0

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror January 2018