- Linux-stable-mirror - lists.linaro.org

[Linux-stable-mirror] Patch "kaiser: x86_cr3_pcid_noflush and x86_cr3_pcid_user" has been added to the 4.4-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled kaiser: x86_cr3_pcid_noflush and x86_cr3_pcid_user to the 4.4-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-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch and it can be found in the queue-4.4 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 18:58:12 CET 2018 From: Hugh Dickins <hughd(a)google.com> Date: Sun, 27 Aug 2017 16:24:27 -0700 Subject: kaiser: x86_cr3_pcid_noflush and x86_cr3_pcid_user From: Hugh Dickins <hughd(a)google.com> Mostly this commit is just unshouting X86_CR3_PCID_KERN_VAR and X86_CR3_PCID_USER_VAR: we usually name variables in lower-case. But why does x86_cr3_pcid_noflush need to be __aligned(PAGE_SIZE)? Ah, it's a leftover from when kaiser_add_user_map() once complained about mapping the same page twice. Make it __read_mostly instead. (I'm a little uneasy about all the unrelated data which shares its page getting user-mapped too, but that was so before, and not a big deal: though we call it user-mapped, it's not mapped with _PAGE_USER.) And there is a little change around the two calls to do_nmi(). Previously they set the NOFLUSH bit (if PCID supported) when forcing to kernel context before do_nmi(); now they also have the NOFLUSH bit set (if PCID supported) when restoring context after: nothing done in do_nmi() should require a TLB to be flushed here. 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/entry/entry_64.S | 8 ++++---- arch/x86/include/asm/kaiser.h | 11 +++++------ arch/x86/mm/kaiser.c | 13 +++++++------ 3 files changed, 16 insertions(+), 16 deletions(-) --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -1290,11 +1290,11 @@ ENTRY(nmi) /* Unconditionally use kernel CR3 for do_nmi() */ /* %rax is saved above, so OK to clobber here */ movq %cr3, %rax + /* If PCID enabled, NOFLUSH now and NOFLUSH on return */ + orq x86_cr3_pcid_noflush, %rax pushq %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 @@ -1534,11 +1534,11 @@ end_repeat_nmi: /* Unconditionally use kernel CR3 for do_nmi() */ /* %rax is saved above, so OK to clobber here */ movq %cr3, %rax + /* If PCID enabled, NOFLUSH now and NOFLUSH on return */ + orq x86_cr3_pcid_noflush, %rax pushq %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/include/asm/kaiser.h +++ b/arch/x86/include/asm/kaiser.h @@ -25,7 +25,7 @@ .macro _SWITCH_TO_KERNEL_CR3 reg movq %cr3, \reg andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), \reg -orq X86_CR3_PCID_KERN_VAR, \reg +orq x86_cr3_pcid_noflush, \reg movq \reg, %cr3 .endm @@ -37,11 +37,10 @@ movq \reg, %cr3 * not enabled): so that the one register can update both memory and cr3. */ movq %cr3, \reg -andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), \reg -orq PER_CPU_VAR(X86_CR3_PCID_USER_VAR), \reg +orq PER_CPU_VAR(x86_cr3_pcid_user), \reg js 9f /* FLUSH this time, reset to NOFLUSH for next time (if PCID enabled) */ -movb \regb, PER_CPU_VAR(X86_CR3_PCID_USER_VAR+7) +movb \regb, PER_CPU_VAR(x86_cr3_pcid_user+7) 9: movq \reg, %cr3 .endm @@ -94,8 +93,8 @@ movq PER_CPU_VAR(unsafe_stack_register_b */ DECLARE_PER_CPU_USER_MAPPED(unsigned long, unsafe_stack_register_backup); -extern unsigned long X86_CR3_PCID_KERN_VAR; -DECLARE_PER_CPU(unsigned long, X86_CR3_PCID_USER_VAR); +extern unsigned long x86_cr3_pcid_noflush; +DECLARE_PER_CPU(unsigned long, x86_cr3_pcid_user); extern char __per_cpu_user_mapped_start[], __per_cpu_user_mapped_end[]; --- a/arch/x86/mm/kaiser.c +++ b/arch/x86/mm/kaiser.c @@ -29,8 +29,8 @@ DEFINE_PER_CPU_USER_MAPPED(unsigned long * 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; -DEFINE_PER_CPU(unsigned long, X86_CR3_PCID_USER_VAR); +unsigned long x86_cr3_pcid_noflush __read_mostly; +DEFINE_PER_CPU(unsigned long, x86_cr3_pcid_user); /* * At runtime, the only things we map are some things for CPU @@ -304,7 +304,8 @@ void __init kaiser_init(void) sizeof(gate_desc) * NR_VECTORS, __PAGE_KERNEL); - kaiser_add_user_map_early(&X86_CR3_PCID_KERN_VAR, PAGE_SIZE, + kaiser_add_user_map_early(&x86_cr3_pcid_noflush, + sizeof(x86_cr3_pcid_noflush), __PAGE_KERNEL); } @@ -384,8 +385,8 @@ void kaiser_setup_pcid(void) * These variables are used by the entry/exit * code to change PCID and pgd and TLB flushing. */ - X86_CR3_PCID_KERN_VAR = kern_cr3; - this_cpu_write(X86_CR3_PCID_USER_VAR, user_cr3); + x86_cr3_pcid_noflush = kern_cr3; + this_cpu_write(x86_cr3_pcid_user, user_cr3); } /* @@ -395,7 +396,7 @@ void kaiser_setup_pcid(void) */ void kaiser_flush_tlb_on_return_to_user(void) { - this_cpu_write(X86_CR3_PCID_USER_VAR, + this_cpu_write(x86_cr3_pcid_user, X86_CR3_PCID_USER_FLUSH | KAISER_SHADOW_PGD_OFFSET); } EXPORT_SYMBOL(kaiser_flush_tlb_on_return_to_user); Patches currently in stable-queue which might be from hughd(a)google.com are queue-4.4/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch queue-4.4/kaiser-add-nokaiser-boot-option-using-alternative.patch queue-4.4/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch queue-4.4/kaiser-_pgd_alloc-without-__gfp_repeat-to-avoid-stalls.patch queue-4.4/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch queue-4.4/kaiser-merged-update.patch queue-4.4/kaiser-delete-kaiser_real_switch-option.patch queue-4.4/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch queue-4.4/kaiser-fix-perf-crashes.patch queue-4.4/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch queue-4.4/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch queue-4.4/kaiser-enhanced-by-kernel-and-user-pcids.patch queue-4.4/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch queue-4.4/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch queue-4.4/kaiser-stack-map-page_size-at-thread_size-page_size.patch queue-4.4/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch queue-4.4/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch queue-4.4/kaiser-do-not-set-_page_nx-on-pgd_none.patch queue-4.4/kaiser-tidied-up-asm-kaiser.h-somewhat.patch queue-4.4/kaiser-cleanups-while-trying-for-gold-link.patch queue-4.4/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch queue-4.4/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch queue-4.4/kaiser-kernel-address-isolation.patch queue-4.4/kaiser-enomem-if-kaiser_pagetable_walk-null.patch queue-4.4/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch queue-4.4/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch queue-4.4/kaiser-kaiser-depends-on-smp.patch queue-4.4/kaiser-pcid-0-for-kernel-and-128-for-user.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "kaiser: vmstat show NR_KAISERTABLE as nr_overhead" has been added to the 4.4-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled kaiser: vmstat show NR_KAISERTABLE as nr_overhead to the 4.4-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-vmstat-show-nr_kaisertable-as-nr_overhead.patch and it can be found in the queue-4.4 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 18:58:12 CET 2018 From: Hugh Dickins <hughd(a)google.com> Date: Sat, 9 Sep 2017 21:27:32 -0700 Subject: kaiser: vmstat show NR_KAISERTABLE as nr_overhead From: Hugh Dickins <hughd(a)google.com> The kaiser update made an interesting choice, never to free any shadow page tables. Contention on global spinlock was worrying, particularly with it held across page table scans when freeing. Something had to be done: I was going to add refcounting; but simply never to free them is an appealing choice, minimizing contention without complicating the code (the more a page table is found already, the less the spinlock is used). But leaking pages in this way is also a worry: can we get away with it? At the very least, we need a count to show how bad it actually gets: in principle, one might end up wasting about 1/256 of memory that way (1/512 for when direct-mapped pages have to be user-mapped, plus 1/512 for when they are user-mapped from the vmalloc area on another occasion (but we don't have vmalloc'ed stacks, so only large ldts are vmalloc'ed). Add per-cpu stat NR_KAISERTABLE: including 256 at startup for the shared pgd entries, and 1 for each intermediate page table added thereafter for user-mapping - but leave out the 1 per mm, for its shadow pgd, because that distracts from the monotonic increase. Shown in /proc/vmstat as nr_overhead (0 if kaiser not enabled). In practice, it doesn't look so bad so far: more like 1/12000 after nine hours of gtests below; and movable pageblock segregation should tend to cluster the kaiser tables into a subset of the address space (if not, they will be bad for compaction too). But production may tell a different story: keep an eye on this number, and bring back lighter freeing if it gets out of control (maybe a shrinker). 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 | 16 +++++++++++----- include/linux/mmzone.h | 3 ++- mm/vmstat.c | 1 + 3 files changed, 14 insertions(+), 6 deletions(-) --- a/arch/x86/mm/kaiser.c +++ b/arch/x86/mm/kaiser.c @@ -122,9 +122,11 @@ static pte_t *kaiser_pagetable_walk(unsi if (!new_pmd_page) return NULL; spin_lock(&shadow_table_allocation_lock); - if (pud_none(*pud)) + if (pud_none(*pud)) { set_pud(pud, __pud(_KERNPG_TABLE | __pa(new_pmd_page))); - else + __inc_zone_page_state(virt_to_page((void *) + new_pmd_page), NR_KAISERTABLE); + } else free_page(new_pmd_page); spin_unlock(&shadow_table_allocation_lock); } @@ -140,9 +142,11 @@ static pte_t *kaiser_pagetable_walk(unsi if (!new_pte_page) return NULL; spin_lock(&shadow_table_allocation_lock); - if (pmd_none(*pmd)) + if (pmd_none(*pmd)) { set_pmd(pmd, __pmd(_KERNPG_TABLE | __pa(new_pte_page))); - else + __inc_zone_page_state(virt_to_page((void *) + new_pte_page), NR_KAISERTABLE); + } else free_page(new_pte_page); spin_unlock(&shadow_table_allocation_lock); } @@ -206,11 +210,13 @@ static void __init kaiser_init_all_pgds( pgd = native_get_shadow_pgd(pgd_offset_k((unsigned long )0)); for (i = PTRS_PER_PGD / 2; i < PTRS_PER_PGD; i++) { pgd_t new_pgd; - pud_t *pud = pud_alloc_one(&init_mm, PAGE_OFFSET + i * PGDIR_SIZE); + pud_t *pud = pud_alloc_one(&init_mm, + PAGE_OFFSET + i * PGDIR_SIZE); if (!pud) { WARN_ON(1); break; } + inc_zone_page_state(virt_to_page(pud), NR_KAISERTABLE); new_pgd = __pgd(_KERNPG_TABLE |__pa(pud)); /* * Make sure not to stomp on some other pgd entry. --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -131,8 +131,9 @@ enum zone_stat_item { NR_SLAB_RECLAIMABLE, NR_SLAB_UNRECLAIMABLE, NR_PAGETABLE, /* used for pagetables */ - NR_KERNEL_STACK, /* Second 128 byte cacheline */ + NR_KERNEL_STACK, + NR_KAISERTABLE, NR_UNSTABLE_NFS, /* NFS unstable pages */ NR_BOUNCE, NR_VMSCAN_WRITE, --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -736,6 +736,7 @@ const char * const vmstat_text[] = { "nr_slab_unreclaimable", "nr_page_table_pages", "nr_kernel_stack", + "nr_overhead", "nr_unstable", "nr_bounce", "nr_vmscan_write", Patches currently in stable-queue which might be from hughd(a)google.com are queue-4.4/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch queue-4.4/kaiser-add-nokaiser-boot-option-using-alternative.patch queue-4.4/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch queue-4.4/kaiser-_pgd_alloc-without-__gfp_repeat-to-avoid-stalls.patch queue-4.4/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch queue-4.4/kaiser-merged-update.patch queue-4.4/kaiser-delete-kaiser_real_switch-option.patch queue-4.4/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch queue-4.4/kaiser-fix-perf-crashes.patch queue-4.4/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch queue-4.4/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch queue-4.4/kaiser-enhanced-by-kernel-and-user-pcids.patch queue-4.4/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch queue-4.4/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch queue-4.4/kaiser-stack-map-page_size-at-thread_size-page_size.patch queue-4.4/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch queue-4.4/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch queue-4.4/kaiser-do-not-set-_page_nx-on-pgd_none.patch queue-4.4/kaiser-tidied-up-asm-kaiser.h-somewhat.patch queue-4.4/kaiser-cleanups-while-trying-for-gold-link.patch queue-4.4/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch queue-4.4/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch queue-4.4/kaiser-kernel-address-isolation.patch queue-4.4/kaiser-enomem-if-kaiser_pagetable_walk-null.patch queue-4.4/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch queue-4.4/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch queue-4.4/kaiser-kaiser-depends-on-smp.patch queue-4.4/kaiser-pcid-0-for-kernel-and-128-for-user.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "kaiser: use ALTERNATIVE instead of x86_cr3_pcid_noflush" has been added to the 4.4-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled kaiser: use ALTERNATIVE instead of x86_cr3_pcid_noflush to the 4.4-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-use-alternative-instead-of-x86_cr3_pcid_noflush.patch and it can be found in the queue-4.4 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 18:58:12 CET 2018 From: Hugh Dickins <hughd(a)google.com> Date: Tue, 3 Oct 2017 20:49:04 -0700 Subject: kaiser: use ALTERNATIVE instead of x86_cr3_pcid_noflush From: Hugh Dickins <hughd(a)google.com> Now that we're playing the ALTERNATIVE game, use that more efficient method: instead of user-mapping an extra page, and reading an extra cacheline each time for x86_cr3_pcid_noflush. Neel has found that __stringify(bts $X86_CR3_PCID_NOFLUSH_BIT, %rax) is a working substitute for the "bts $63, %rax" in these ALTERNATIVEs; but the one line with $63 in looks clearer, so let's stick with that. Worried about what happens with an ALTERNATIVE between the jump and jump label in another ALTERNATIVE? I was, but have checked the combinations in SWITCH_KERNEL_CR3_NO_STACK at entry_SYSCALL_64, and it does a good job. 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/entry/entry_64.S | 7 ++++--- arch/x86/include/asm/kaiser.h | 6 +++--- arch/x86/mm/kaiser.c | 11 +---------- 3 files changed, 8 insertions(+), 16 deletions(-) --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -1056,7 +1056,8 @@ ENTRY(paranoid_entry) jz 2f orl $2, %ebx andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), %rax - orq x86_cr3_pcid_noflush, %rax + /* If PCID enabled, set X86_CR3_PCID_NOFLUSH_BIT */ + ALTERNATIVE "", "bts $63, %rax", X86_FEATURE_PCID movq %rax, %cr3 2: #endif @@ -1318,7 +1319,7 @@ ENTRY(nmi) /* %rax is saved above, so OK to clobber here */ ALTERNATIVE "jmp 2f", "movq %cr3, %rax", X86_FEATURE_KAISER /* If PCID enabled, NOFLUSH now and NOFLUSH on return */ - orq x86_cr3_pcid_noflush, %rax + ALTERNATIVE "", "bts $63, %rax", X86_FEATURE_PCID pushq %rax /* mask off "user" bit of pgd address and 12 PCID bits: */ andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), %rax @@ -1562,7 +1563,7 @@ end_repeat_nmi: /* %rax is saved above, so OK to clobber here */ ALTERNATIVE "jmp 2f", "movq %cr3, %rax", X86_FEATURE_KAISER /* If PCID enabled, NOFLUSH now and NOFLUSH on return */ - orq x86_cr3_pcid_noflush, %rax + ALTERNATIVE "", "bts $63, %rax", X86_FEATURE_PCID pushq %rax /* mask off "user" bit of pgd address and 12 PCID bits: */ andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), %rax --- a/arch/x86/include/asm/kaiser.h +++ b/arch/x86/include/asm/kaiser.h @@ -25,7 +25,8 @@ .macro _SWITCH_TO_KERNEL_CR3 reg movq %cr3, \reg andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), \reg -orq x86_cr3_pcid_noflush, \reg +/* If PCID enabled, set X86_CR3_PCID_NOFLUSH_BIT */ +ALTERNATIVE "", "bts $63, \reg", X86_FEATURE_PCID movq \reg, %cr3 .endm @@ -39,7 +40,7 @@ movq \reg, %cr3 movq %cr3, \reg orq PER_CPU_VAR(x86_cr3_pcid_user), \reg js 9f -/* FLUSH this time, reset to NOFLUSH for next time (if PCID enabled) */ +/* If PCID enabled, FLUSH this time, reset to NOFLUSH for next time */ movb \regb, PER_CPU_VAR(x86_cr3_pcid_user+7) 9: movq \reg, %cr3 @@ -90,7 +91,6 @@ movq PER_CPU_VAR(unsafe_stack_register_b */ DECLARE_PER_CPU_USER_MAPPED(unsigned long, unsafe_stack_register_backup); -extern unsigned long x86_cr3_pcid_noflush; DECLARE_PER_CPU(unsigned long, x86_cr3_pcid_user); extern char __per_cpu_user_mapped_start[], __per_cpu_user_mapped_end[]; --- a/arch/x86/mm/kaiser.c +++ b/arch/x86/mm/kaiser.c @@ -32,7 +32,6 @@ DEFINE_PER_CPU_USER_MAPPED(unsigned long * 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. */ -unsigned long x86_cr3_pcid_noflush __read_mostly; DEFINE_PER_CPU(unsigned long, x86_cr3_pcid_user); /* @@ -357,10 +356,6 @@ 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_noflush, - sizeof(x86_cr3_pcid_noflush), - __PAGE_KERNEL); } /* Add a mapping to the shadow mapping, and synchronize the mappings */ @@ -434,18 +429,14 @@ pgd_t kaiser_set_shadow_pgd(pgd_t *pgdp, void kaiser_setup_pcid(void) { - unsigned long kern_cr3 = 0; unsigned long user_cr3 = KAISER_SHADOW_PGD_OFFSET; - if (this_cpu_has(X86_FEATURE_PCID)) { - kern_cr3 |= X86_CR3_PCID_KERN_NOFLUSH; + if (this_cpu_has(X86_FEATURE_PCID)) user_cr3 |= X86_CR3_PCID_USER_NOFLUSH; - } /* * These variables are used by the entry/exit * code to change PCID and pgd and TLB flushing. */ - x86_cr3_pcid_noflush = kern_cr3; this_cpu_write(x86_cr3_pcid_user, user_cr3); } Patches currently in stable-queue which might be from hughd(a)google.com are queue-4.4/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch queue-4.4/kaiser-add-nokaiser-boot-option-using-alternative.patch queue-4.4/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch queue-4.4/kaiser-_pgd_alloc-without-__gfp_repeat-to-avoid-stalls.patch queue-4.4/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch queue-4.4/kaiser-merged-update.patch queue-4.4/kaiser-delete-kaiser_real_switch-option.patch queue-4.4/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch queue-4.4/kaiser-fix-perf-crashes.patch queue-4.4/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch queue-4.4/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch queue-4.4/kaiser-enhanced-by-kernel-and-user-pcids.patch queue-4.4/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch queue-4.4/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch queue-4.4/kaiser-stack-map-page_size-at-thread_size-page_size.patch queue-4.4/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch queue-4.4/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch queue-4.4/kaiser-do-not-set-_page_nx-on-pgd_none.patch queue-4.4/kaiser-tidied-up-asm-kaiser.h-somewhat.patch queue-4.4/kaiser-cleanups-while-trying-for-gold-link.patch queue-4.4/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch queue-4.4/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch queue-4.4/kaiser-kernel-address-isolation.patch queue-4.4/kaiser-enomem-if-kaiser_pagetable_walk-null.patch queue-4.4/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch queue-4.4/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch queue-4.4/kaiser-kaiser-depends-on-smp.patch queue-4.4/kaiser-pcid-0-for-kernel-and-128-for-user.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "kaiser: tidied up kaiser_add/remove_mapping slightly" has been added to the 4.4-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled kaiser: tidied up kaiser_add/remove_mapping slightly to the 4.4-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-tidied-up-kaiser_add-remove_mapping-slightly.patch and it can be found in the queue-4.4 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 18:58:12 CET 2018 From: Hugh Dickins <hughd(a)google.com> Date: Sun, 3 Sep 2017 19:23:08 -0700 Subject: kaiser: tidied up kaiser_add/remove_mapping slightly From: Hugh Dickins <hughd(a)google.com> Yes, unmap_pud_range_nofree()'s declaration ought to be in a header file really, but I'm not sure we want to use it anyway: so for now just declare it inside kaiser_remove_mapping(). And there doesn't seem to be such a thing as unmap_p4d_range(), even in a 5-level paging tree. 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 | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) --- a/arch/x86/mm/kaiser.c +++ b/arch/x86/mm/kaiser.c @@ -286,8 +286,7 @@ void __init kaiser_init(void) __PAGE_KERNEL); } -extern void unmap_pud_range_nofree(pgd_t *pgd, unsigned long start, unsigned long end); -// add a mapping to the shadow-mapping, and synchronize the mappings +/* Add a mapping to the shadow mapping, and synchronize the mappings */ int kaiser_add_mapping(unsigned long addr, unsigned long size, unsigned long flags) { return kaiser_add_user_map((const void *)addr, size, flags); @@ -295,15 +294,13 @@ int kaiser_add_mapping(unsigned long add void kaiser_remove_mapping(unsigned long start, unsigned long size) { + extern void unmap_pud_range_nofree(pgd_t *pgd, + unsigned long start, unsigned long end); unsigned long end = start + size; unsigned long addr; for (addr = start; addr < end; addr += PGDIR_SIZE) { pgd_t *pgd = native_get_shadow_pgd(pgd_offset_k(addr)); - /* - * unmap_p4d_range() handles > P4D_SIZE unmaps, - * so no need to trim 'end'. - */ unmap_pud_range_nofree(pgd, addr, end); } } Patches currently in stable-queue which might be from hughd(a)google.com are queue-4.4/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch queue-4.4/kaiser-add-nokaiser-boot-option-using-alternative.patch queue-4.4/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch queue-4.4/kaiser-_pgd_alloc-without-__gfp_repeat-to-avoid-stalls.patch queue-4.4/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch queue-4.4/kaiser-merged-update.patch queue-4.4/kaiser-delete-kaiser_real_switch-option.patch queue-4.4/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch queue-4.4/kaiser-fix-perf-crashes.patch queue-4.4/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch queue-4.4/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch queue-4.4/kaiser-enhanced-by-kernel-and-user-pcids.patch queue-4.4/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch queue-4.4/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch queue-4.4/kaiser-stack-map-page_size-at-thread_size-page_size.patch queue-4.4/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch queue-4.4/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch queue-4.4/kaiser-do-not-set-_page_nx-on-pgd_none.patch queue-4.4/kaiser-tidied-up-asm-kaiser.h-somewhat.patch queue-4.4/kaiser-cleanups-while-trying-for-gold-link.patch queue-4.4/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch queue-4.4/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch queue-4.4/kaiser-kernel-address-isolation.patch queue-4.4/kaiser-enomem-if-kaiser_pagetable_walk-null.patch queue-4.4/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch queue-4.4/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch queue-4.4/kaiser-kaiser-depends-on-smp.patch queue-4.4/kaiser-pcid-0-for-kernel-and-128-for-user.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "kaiser: tidied up asm/kaiser.h somewhat" has been added to the 4.4-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled kaiser: tidied up asm/kaiser.h somewhat to the 4.4-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-tidied-up-asm-kaiser.h-somewhat.patch and it can be found in the queue-4.4 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 18:58:12 CET 2018 From: Hugh Dickins <hughd(a)google.com> Date: Sun, 3 Sep 2017 19:18:07 -0700 Subject: kaiser: tidied up asm/kaiser.h somewhat From: Hugh Dickins <hughd(a)google.com> Mainly deleting a surfeit of blank lines, and reflowing header comment. 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/kaiser.h | 32 +++++++++++++------------------- 1 file changed, 13 insertions(+), 19 deletions(-) --- a/arch/x86/include/asm/kaiser.h +++ b/arch/x86/include/asm/kaiser.h @@ -1,15 +1,17 @@ #ifndef _ASM_X86_KAISER_H #define _ASM_X86_KAISER_H - -/* This file includes the definitions for the KAISER feature. - * KAISER is a counter measure against x86_64 side channel attacks on the kernel virtual memory. - * It has a shodow-pgd for every process. the shadow-pgd has a minimalistic kernel-set mapped, - * but includes the whole user memory. Within a kernel context switch, or when an interrupt is handled, - * the pgd is switched to the normal one. When the system switches to user mode, the shadow pgd is enabled. - * By this, the virtual memory chaches are freed, and the user may not attack the whole kernel memory. +/* + * This file includes the definitions for the KAISER feature. + * KAISER is a counter measure against x86_64 side channel attacks on + * the kernel virtual memory. It has a shadow pgd for every process: the + * shadow pgd has a minimalistic kernel-set mapped, but includes the whole + * user memory. Within a kernel context switch, or when an interrupt is handled, + * the pgd is switched to the normal one. When the system switches to user mode, + * the shadow pgd is enabled. By this, the virtual memory caches are freed, + * and the user may not attack the whole kernel memory. * - * A minimalistic kernel mapping holds the parts needed to be mapped in user mode, as the entry/exit functions - * of the user space, or the stacks. + * A minimalistic kernel mapping holds the parts needed to be mapped in user + * mode, such as the entry/exit functions of the user space, or the stacks. */ #ifdef __ASSEMBLY__ #ifdef CONFIG_KAISER @@ -48,13 +50,10 @@ _SWITCH_TO_KERNEL_CR3 %rax movq PER_CPU_VAR(unsafe_stack_register_backup), %rax .endm - .macro SWITCH_USER_CR3_NO_STACK - movq %rax, PER_CPU_VAR(unsafe_stack_register_backup) _SWITCH_TO_USER_CR3 %rax movq PER_CPU_VAR(unsafe_stack_register_backup), %rax - .endm #else /* CONFIG_KAISER */ @@ -72,7 +71,6 @@ movq PER_CPU_VAR(unsafe_stack_register_b #else /* __ASSEMBLY__ */ - #ifdef CONFIG_KAISER /* * Upon kernel/user mode switch, it may happen that the address @@ -80,7 +78,6 @@ movq PER_CPU_VAR(unsafe_stack_register_b * stored. To change the address space, another register is * needed. A register therefore has to be stored/restored. */ - DECLARE_PER_CPU_USER_MAPPED(unsigned long, unsafe_stack_register_backup); /** @@ -95,7 +92,6 @@ DECLARE_PER_CPU_USER_MAPPED(unsigned lon */ extern int kaiser_add_mapping(unsigned long addr, unsigned long size, unsigned long flags); - /** * kaiser_remove_mapping - unmap a virtual memory part of the shadow mapping * @addr: the start address of the range @@ -104,12 +100,12 @@ extern int kaiser_add_mapping(unsigned l extern void kaiser_remove_mapping(unsigned long start, unsigned long size); /** - * kaiser_initialize_mapping - Initalize the shadow mapping + * kaiser_init - Initialize the shadow mapping * * Most parts of the shadow mapping can be mapped upon boot * time. Only per-process things like the thread stacks * or a new LDT have to be mapped at runtime. These boot- - * time mappings are permanent and nevertunmapped. + * time mappings are permanent and never unmapped. */ extern void kaiser_init(void); @@ -117,6 +113,4 @@ extern void kaiser_init(void); #endif /* __ASSEMBLY */ - - #endif /* _ASM_X86_KAISER_H */ Patches currently in stable-queue which might be from hughd(a)google.com are queue-4.4/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch queue-4.4/kaiser-add-nokaiser-boot-option-using-alternative.patch queue-4.4/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch queue-4.4/kaiser-_pgd_alloc-without-__gfp_repeat-to-avoid-stalls.patch queue-4.4/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch queue-4.4/kaiser-merged-update.patch queue-4.4/kaiser-delete-kaiser_real_switch-option.patch queue-4.4/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch queue-4.4/kaiser-fix-perf-crashes.patch queue-4.4/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch queue-4.4/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch queue-4.4/kaiser-enhanced-by-kernel-and-user-pcids.patch queue-4.4/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch queue-4.4/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch queue-4.4/kaiser-stack-map-page_size-at-thread_size-page_size.patch queue-4.4/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch queue-4.4/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch queue-4.4/kaiser-do-not-set-_page_nx-on-pgd_none.patch queue-4.4/kaiser-tidied-up-asm-kaiser.h-somewhat.patch queue-4.4/kaiser-cleanups-while-trying-for-gold-link.patch queue-4.4/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch queue-4.4/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch queue-4.4/kaiser-kernel-address-isolation.patch queue-4.4/kaiser-enomem-if-kaiser_pagetable_walk-null.patch queue-4.4/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch queue-4.4/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch queue-4.4/kaiser-kaiser-depends-on-smp.patch queue-4.4/kaiser-pcid-0-for-kernel-and-128-for-user.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "kaiser: stack map PAGE_SIZE at THREAD_SIZE-PAGE_SIZE" has been added to the 4.4-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled kaiser: stack map PAGE_SIZE at THREAD_SIZE-PAGE_SIZE to the 4.4-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-stack-map-page_size-at-thread_size-page_size.patch and it can be found in the queue-4.4 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 18:58:12 CET 2018 From: Hugh Dickins <hughd(a)google.com> Date: Sun, 3 Sep 2017 18:57:03 -0700 Subject: kaiser: stack map PAGE_SIZE at THREAD_SIZE-PAGE_SIZE From: Hugh Dickins <hughd(a)google.com> Kaiser only needs to map one page of the stack; and kernel/fork.c did not build on powerpc (no __PAGE_KERNEL). It's all cleaner if linux/kaiser.h provides kaiser_map_thread_stack() and kaiser_unmap_thread_stack() wrappers around asm/kaiser.h's kaiser_add_mapping() and kaiser_remove_mapping(). And use linux/kaiser.h in init/main.c to avoid the #ifdefs there. 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> --- include/linux/kaiser.h | 40 +++++++++++++++++++++++++++++++++------- init/main.c | 6 +----- kernel/fork.c | 7 ++----- 3 files changed, 36 insertions(+), 17 deletions(-) --- a/include/linux/kaiser.h +++ b/include/linux/kaiser.h @@ -1,26 +1,52 @@ -#ifndef _INCLUDE_KAISER_H -#define _INCLUDE_KAISER_H +#ifndef _LINUX_KAISER_H +#define _LINUX_KAISER_H #ifdef CONFIG_KAISER #include <asm/kaiser.h> + +static inline int kaiser_map_thread_stack(void *stack) +{ + /* + * Map that page of kernel stack on which we enter from user context. + */ + return kaiser_add_mapping((unsigned long)stack + + THREAD_SIZE - PAGE_SIZE, PAGE_SIZE, __PAGE_KERNEL); +} + +static inline void kaiser_unmap_thread_stack(void *stack) +{ + /* + * Note: may be called even when kaiser_map_thread_stack() failed. + */ + kaiser_remove_mapping((unsigned long)stack + + THREAD_SIZE - PAGE_SIZE, PAGE_SIZE); +} #else /* * These stubs are used whenever CONFIG_KAISER is off, which - * includes architectures that support KAISER, but have it - * disabled. + * includes architectures that support KAISER, but have it disabled. */ static inline void kaiser_init(void) { } -static inline void kaiser_remove_mapping(unsigned long start, unsigned long size) +static inline int kaiser_add_mapping(unsigned long addr, + unsigned long size, unsigned long flags) +{ + return 0; +} +static inline void kaiser_remove_mapping(unsigned long start, + unsigned long size) { } -static inline int kaiser_add_mapping(unsigned long addr, unsigned long size, unsigned long flags) +static inline int kaiser_map_thread_stack(void *stack) { return 0; } +static inline void kaiser_unmap_thread_stack(void *stack) +{ +} #endif /* !CONFIG_KAISER */ -#endif /* _INCLUDE_KAISER_H */ +#endif /* _LINUX_KAISER_H */ --- a/init/main.c +++ b/init/main.c @@ -81,15 +81,13 @@ #include <linux/integrity.h> #include <linux/proc_ns.h> #include <linux/io.h> +#include <linux/kaiser.h> #include <asm/io.h> #include <asm/bugs.h> #include <asm/setup.h> #include <asm/sections.h> #include <asm/cacheflush.h> -#ifdef CONFIG_KAISER -#include <asm/kaiser.h> -#endif static int kernel_init(void *); @@ -495,9 +493,7 @@ static void __init mm_init(void) pgtable_init(); vmalloc_init(); ioremap_huge_init(); -#ifdef CONFIG_KAISER kaiser_init(); -#endif } asmlinkage __visible void __init start_kernel(void) --- a/kernel/fork.c +++ b/kernel/fork.c @@ -168,12 +168,9 @@ static struct thread_info *alloc_thread_ return page ? page_address(page) : NULL; } -extern void kaiser_remove_mapping(unsigned long start_addr, unsigned long size); static inline void free_thread_info(struct thread_info *ti) { -#ifdef CONFIG_KAISER - kaiser_remove_mapping((unsigned long)ti, THREAD_SIZE); -#endif + kaiser_unmap_thread_stack(ti); free_kmem_pages((unsigned long)ti, THREAD_SIZE_ORDER); } # else @@ -358,7 +355,7 @@ static struct task_struct *dup_task_stru tsk->stack = ti; - err= kaiser_add_mapping((unsigned long)tsk->stack, THREAD_SIZE, __PAGE_KERNEL); + err = kaiser_map_thread_stack(tsk->stack); if (err) goto free_ti; #ifdef CONFIG_SECCOMP Patches currently in stable-queue which might be from hughd(a)google.com are queue-4.4/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch queue-4.4/kaiser-add-nokaiser-boot-option-using-alternative.patch queue-4.4/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch queue-4.4/kaiser-_pgd_alloc-without-__gfp_repeat-to-avoid-stalls.patch queue-4.4/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch queue-4.4/kaiser-merged-update.patch queue-4.4/kaiser-delete-kaiser_real_switch-option.patch queue-4.4/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch queue-4.4/kaiser-fix-perf-crashes.patch queue-4.4/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch queue-4.4/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch queue-4.4/kaiser-enhanced-by-kernel-and-user-pcids.patch queue-4.4/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch queue-4.4/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch queue-4.4/kaiser-stack-map-page_size-at-thread_size-page_size.patch queue-4.4/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch queue-4.4/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch queue-4.4/kaiser-do-not-set-_page_nx-on-pgd_none.patch queue-4.4/kaiser-tidied-up-asm-kaiser.h-somewhat.patch queue-4.4/kaiser-cleanups-while-trying-for-gold-link.patch queue-4.4/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch queue-4.4/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch queue-4.4/kaiser-kernel-address-isolation.patch queue-4.4/kaiser-enomem-if-kaiser_pagetable_walk-null.patch queue-4.4/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch queue-4.4/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch queue-4.4/kaiser-kaiser-depends-on-smp.patch queue-4.4/kaiser-pcid-0-for-kernel-and-128-for-user.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "kaiser: PCID 0 for kernel and 128 for user" has been added to the 4.4-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled kaiser: PCID 0 for kernel and 128 for user to the 4.4-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-pcid-0-for-kernel-and-128-for-user.patch and it can be found in the queue-4.4 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 18:58:12 CET 2018 From: Hugh Dickins <hughd(a)google.com> Date: Fri, 8 Sep 2017 19:26:30 -0700 Subject: kaiser: PCID 0 for kernel and 128 for user From: Hugh Dickins <hughd(a)google.com> Why was 4 chosen for kernel PCID and 6 for user PCID? No good reason in a backport where PCIDs are only used for Kaiser. If we continue with those, then we shall need to add Andy Lutomirski's 4.13 commit 6c690ee1039b ("x86/mm: Split read_cr3() into read_cr3_pa() and __read_cr3()"), which deals with the problem of read_cr3() callers finding stray bits in the cr3 that they expected to be page-aligned; and for hibernation, his 4.14 commit f34902c5c6c0 ("x86/hibernate/64: Mask off CR3's PCID bits in the saved CR3"). But if 0 is used for kernel PCID, then there's no need to add in those commits - whenever the kernel looks, it sees 0 in the lower bits; and 0 for kernel seems an obvious choice. And I naughtily propose 128 for user PCID. Because there's a place in _SWITCH_TO_USER_CR3 where it takes note of the need for TLB FLUSH, but needs to reset that to NOFLUSH for the next occasion. Currently it does so with a "movb $(0x80)" into the high byte of the per-cpu quadword, but that will cause a machine without PCID support to crash. Now, if %al just happened to have 0x80 in it at that point, on a machine with PCID support, but 0 on a machine without PCID support... (That will go badly wrong once the pgd can be at a physical address above 2^56, but even with 5-level paging, physical goes up to 2^52.) 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/kaiser.h | 19 ++++++++++++------- arch/x86/include/asm/pgtable_types.h | 7 ++++--- arch/x86/mm/tlb.c | 3 +++ 3 files changed, 19 insertions(+), 10 deletions(-) --- a/arch/x86/include/asm/kaiser.h +++ b/arch/x86/include/asm/kaiser.h @@ -29,14 +29,19 @@ orq X86_CR3_PCID_KERN_VAR, \reg movq \reg, %cr3 .endm -.macro _SWITCH_TO_USER_CR3 reg +.macro _SWITCH_TO_USER_CR3 reg regb +/* + * regb must be the low byte portion of reg: because we have arranged + * for the low byte of the user PCID to serve as the high byte of NOFLUSH + * (0x80 for each when PCID is enabled, or 0x00 when PCID and NOFLUSH are + * not enabled): so that the one register can update both memory and cr3. + */ movq %cr3, \reg andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), \reg orq PER_CPU_VAR(X86_CR3_PCID_USER_VAR), \reg js 9f -// FLUSH this time, reset to NOFLUSH for next time -// But if nopcid? Consider using 0x80 for user pcid? -movb $(0x80), PER_CPU_VAR(X86_CR3_PCID_USER_VAR+7) +/* FLUSH this time, reset to NOFLUSH for next time (if PCID enabled) */ +movb \regb, PER_CPU_VAR(X86_CR3_PCID_USER_VAR+7) 9: movq \reg, %cr3 .endm @@ -49,7 +54,7 @@ popq %rax .macro SWITCH_USER_CR3 pushq %rax -_SWITCH_TO_USER_CR3 %rax +_SWITCH_TO_USER_CR3 %rax %al popq %rax .endm @@ -61,7 +66,7 @@ movq PER_CPU_VAR(unsafe_stack_register_b .macro SWITCH_USER_CR3_NO_STACK movq %rax, PER_CPU_VAR(unsafe_stack_register_backup) -_SWITCH_TO_USER_CR3 %rax +_SWITCH_TO_USER_CR3 %rax %al movq PER_CPU_VAR(unsafe_stack_register_backup), %rax .endm @@ -69,7 +74,7 @@ movq PER_CPU_VAR(unsafe_stack_register_b .macro SWITCH_KERNEL_CR3 reg .endm -.macro SWITCH_USER_CR3 reg +.macro SWITCH_USER_CR3 reg regb .endm .macro SWITCH_USER_CR3_NO_STACK .endm --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -111,16 +111,17 @@ /* Mask for all the PCID-related bits in CR3: */ #define X86_CR3_PCID_MASK (X86_CR3_PCID_NOFLUSH | X86_CR3_PCID_ASID_MASK) +#define X86_CR3_PCID_ASID_KERN (_AC(0x0,UL)) + #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)) +/* Let X86_CR3_PCID_ASID_USER be usable for the X86_CR3_PCID_NOFLUSH bit */ +#define X86_CR3_PCID_ASID_USER (_AC(0x80,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 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -50,6 +50,9 @@ static void load_new_mm_cr3(pgd_t *pgdir * invpcid_flush_single_context(X86_CR3_PCID_ASID_USER) could * do it here, but can only be used if X86_FEATURE_INVPCID is * available - and many machines support pcid without invpcid. + * + * The line below is a no-op: X86_CR3_PCID_KERN_FLUSH is now 0; + * but keep that line in there in case something changes. */ new_mm_cr3 |= X86_CR3_PCID_KERN_FLUSH; kaiser_flush_tlb_on_return_to_user(); Patches currently in stable-queue which might be from hughd(a)google.com are queue-4.4/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch queue-4.4/kaiser-add-nokaiser-boot-option-using-alternative.patch queue-4.4/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch queue-4.4/kaiser-_pgd_alloc-without-__gfp_repeat-to-avoid-stalls.patch queue-4.4/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch queue-4.4/kaiser-merged-update.patch queue-4.4/kaiser-delete-kaiser_real_switch-option.patch queue-4.4/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch queue-4.4/kaiser-fix-perf-crashes.patch queue-4.4/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch queue-4.4/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch queue-4.4/kaiser-enhanced-by-kernel-and-user-pcids.patch queue-4.4/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch queue-4.4/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch queue-4.4/kaiser-stack-map-page_size-at-thread_size-page_size.patch queue-4.4/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch queue-4.4/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch queue-4.4/kaiser-do-not-set-_page_nx-on-pgd_none.patch queue-4.4/kaiser-tidied-up-asm-kaiser.h-somewhat.patch queue-4.4/kaiser-cleanups-while-trying-for-gold-link.patch queue-4.4/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch queue-4.4/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch queue-4.4/kaiser-kernel-address-isolation.patch queue-4.4/kaiser-enomem-if-kaiser_pagetable_walk-null.patch queue-4.4/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch queue-4.4/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch queue-4.4/kaiser-kaiser-depends-on-smp.patch queue-4.4/kaiser-pcid-0-for-kernel-and-128-for-user.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "kaiser: paranoid_entry pass cr3 need to paranoid_exit" has been added to the 4.4-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled kaiser: paranoid_entry pass cr3 need to paranoid_exit to the 4.4-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-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch and it can be found in the queue-4.4 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 18:58:12 CET 2018 From: Hugh Dickins <hughd(a)google.com> Date: Tue, 26 Sep 2017 18:43:07 -0700 Subject: kaiser: paranoid_entry pass cr3 need to paranoid_exit From: Hugh Dickins <hughd(a)google.com> Neel Natu points out that paranoid_entry() was wrong to assume that an entry that did not need swapgs would not need SWITCH_KERNEL_CR3: paranoid_entry (used for debug breakpoint, int3, double fault or MCE; though I think it's only the MCE case that is cause for concern here) can break in at an awkward time, between cr3 switch and swapgs, but its handling always needs kernel gs and kernel cr3. Easy to fix in itself, but paranoid_entry() also needs to convey to paranoid_exit() (and my reading of macro idtentry says paranoid_entry and paranoid_exit are always paired) how to restore the prior state. The swapgs state is already conveyed by %ebx (0 or 1), so extend that also to convey when SWITCH_USER_CR3 will be needed (2 or 3). (Yes, I'd much prefer that 0 meant no swapgs, whereas it's the other way round: and a convention shared with error_entry() and error_exit(), which I don't want to touch. Perhaps I should have inverted the bit for switch cr3 too, but did not.) paranoid_exit() would be straightforward, except for TRACE_IRQS: it did TRACE_IRQS_IRETQ when doing swapgs, but TRACE_IRQS_IRETQ_DEBUG when not: which is it supposed to use when SWITCH_USER_CR3 is split apart from that? As best as I can determine, commit 5963e317b1e9 ("ftrace/x86: Do not change stacks in DEBUG when calling lockdep") missed the swapgs case, and should have used TRACE_IRQS_IRETQ_DEBUG there too (the discrepancy has nothing to do with the liberal use of _NO_STACK and _UNSAFE_STACK hereabouts: TRACE_IRQS_OFF_DEBUG has just been used in all cases); discrepancy lovingly preserved across several paranoid_exit() cleanups, but I'm now removing it. Neel further indicates that to use SWITCH_USER_CR3_NO_STACK there in paranoid_exit() is now not only unnecessary but unsafe: might corrupt syscall entry's unsafe_stack_register_backup of %rax. Just use SWITCH_USER_CR3: and delete SWITCH_USER_CR3_NO_STACK altogether, before we make the mistake of using it again. hughd adds: this commit fixes an issue in the Kaiser-without-PCIDs part of the series, and ought to be moved earlier, if you decided to make a release of Kaiser-without-PCIDs. 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/entry/entry_64.S | 46 ++++++++++++++++++++++++++++++++---------- arch/x86/include/asm/kaiser.h | 8 ------- 2 files changed, 36 insertions(+), 18 deletions(-) --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -1025,7 +1025,11 @@ idtentry machine_check has_error_cod /* * Save all registers in pt_regs, and switch gs if needed. * Use slow, but surefire "are we in kernel?" check. - * Return: ebx=0: need swapgs on exit, ebx=1: otherwise + * + * Return: ebx=0: needs swapgs but not SWITCH_USER_CR3 in paranoid_exit + * ebx=1: needs neither swapgs nor SWITCH_USER_CR3 in paranoid_exit + * ebx=2: needs both swapgs and SWITCH_USER_CR3 in paranoid_exit + * ebx=3: needs SWITCH_USER_CR3 but not swapgs in paranoid_exit */ ENTRY(paranoid_entry) cld @@ -1037,9 +1041,26 @@ ENTRY(paranoid_entry) testl %edx, %edx js 1f /* negative -> in kernel */ SWAPGS - SWITCH_KERNEL_CR3 xorl %ebx, %ebx -1: ret +1: +#ifdef CONFIG_KAISER + /* + * We might have come in between a swapgs and a SWITCH_KERNEL_CR3 + * on entry, or between a SWITCH_USER_CR3 and a swapgs on exit. + * Do a conditional SWITCH_KERNEL_CR3: this could safely be done + * unconditionally, but we need to find out whether the reverse + * should be done on return (conveyed to paranoid_exit in %ebx). + */ + movq %cr3, %rax + testl $KAISER_SHADOW_PGD_OFFSET, %eax + jz 2f + orl $2, %ebx + andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), %rax + orq x86_cr3_pcid_noflush, %rax + movq %rax, %cr3 +2: +#endif + ret END(paranoid_entry) /* @@ -1052,20 +1073,25 @@ END(paranoid_entry) * be complicated. Fortunately, we there's no good reason * to try to handle preemption here. * - * On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it) + * On entry: ebx=0: needs swapgs but not SWITCH_USER_CR3 + * ebx=1: needs neither swapgs nor SWITCH_USER_CR3 + * ebx=2: needs both swapgs and SWITCH_USER_CR3 + * ebx=3: needs SWITCH_USER_CR3 but not swapgs */ ENTRY(paranoid_exit) DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF_DEBUG - testl %ebx, %ebx /* swapgs needed? */ + TRACE_IRQS_IRETQ_DEBUG +#ifdef CONFIG_KAISER + testl $2, %ebx /* SWITCH_USER_CR3 needed? */ + jz paranoid_exit_no_switch + SWITCH_USER_CR3 +paranoid_exit_no_switch: +#endif + testl $1, %ebx /* swapgs needed? */ jnz paranoid_exit_no_swapgs - TRACE_IRQS_IRETQ - SWITCH_USER_CR3_NO_STACK SWAPGS_UNSAFE_STACK - jmp paranoid_exit_restore paranoid_exit_no_swapgs: - TRACE_IRQS_IRETQ_DEBUG -paranoid_exit_restore: RESTORE_EXTRA_REGS RESTORE_C_REGS REMOVE_PT_GPREGS_FROM_STACK 8 --- a/arch/x86/include/asm/kaiser.h +++ b/arch/x86/include/asm/kaiser.h @@ -63,20 +63,12 @@ _SWITCH_TO_KERNEL_CR3 %rax movq PER_CPU_VAR(unsafe_stack_register_backup), %rax .endm -.macro SWITCH_USER_CR3_NO_STACK -movq %rax, PER_CPU_VAR(unsafe_stack_register_backup) -_SWITCH_TO_USER_CR3 %rax %al -movq PER_CPU_VAR(unsafe_stack_register_backup), %rax -.endm - #else /* CONFIG_KAISER */ .macro SWITCH_KERNEL_CR3 reg .endm .macro SWITCH_USER_CR3 reg regb .endm -.macro SWITCH_USER_CR3_NO_STACK -.endm .macro SWITCH_KERNEL_CR3_NO_STACK .endm Patches currently in stable-queue which might be from hughd(a)google.com are queue-4.4/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch queue-4.4/kaiser-add-nokaiser-boot-option-using-alternative.patch queue-4.4/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch queue-4.4/kaiser-_pgd_alloc-without-__gfp_repeat-to-avoid-stalls.patch queue-4.4/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch queue-4.4/kaiser-merged-update.patch queue-4.4/kaiser-delete-kaiser_real_switch-option.patch queue-4.4/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch queue-4.4/kaiser-fix-perf-crashes.patch queue-4.4/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch queue-4.4/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch queue-4.4/kaiser-enhanced-by-kernel-and-user-pcids.patch queue-4.4/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch queue-4.4/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch queue-4.4/kaiser-stack-map-page_size-at-thread_size-page_size.patch queue-4.4/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch queue-4.4/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch queue-4.4/kaiser-do-not-set-_page_nx-on-pgd_none.patch queue-4.4/kaiser-tidied-up-asm-kaiser.h-somewhat.patch queue-4.4/kaiser-cleanups-while-trying-for-gold-link.patch queue-4.4/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch queue-4.4/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch queue-4.4/kaiser-kernel-address-isolation.patch queue-4.4/kaiser-enomem-if-kaiser_pagetable_walk-null.patch queue-4.4/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch queue-4.4/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch queue-4.4/kaiser-kaiser-depends-on-smp.patch queue-4.4/kaiser-pcid-0-for-kernel-and-128-for-user.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "kaiser: name that 0x1000 KAISER_SHADOW_PGD_OFFSET" has been added to the 4.4-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled kaiser: name that 0x1000 KAISER_SHADOW_PGD_OFFSET to the 4.4-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-name-that-0x1000-kaiser_shadow_pgd_offset.patch and it can be found in the queue-4.4 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 18:58:12 CET 2018 From: Hugh Dickins <hughd(a)google.com> Date: Sat, 9 Sep 2017 17:31:18 -0700 Subject: kaiser: name that 0x1000 KAISER_SHADOW_PGD_OFFSET From: Hugh Dickins <hughd(a)google.com> There's a 0x1000 in various places, which looks better with a name. 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/entry/entry_64.S | 4 ++-- arch/x86/include/asm/kaiser.h | 7 +++++-- 2 files changed, 7 insertions(+), 4 deletions(-) --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -1292,7 +1292,7 @@ ENTRY(nmi) movq %cr3, %rax pushq %rax #ifdef CONFIG_KAISER_REAL_SWITCH - andq $(~0x1000), %rax + andq $(~KAISER_SHADOW_PGD_OFFSET), %rax #endif movq %rax, %cr3 #endif @@ -1535,7 +1535,7 @@ end_repeat_nmi: movq %cr3, %rax pushq %rax #ifdef CONFIG_KAISER_REAL_SWITCH - andq $(~0x1000), %rax + 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 @@ -13,13 +13,16 @@ * A minimalistic kernel mapping holds the parts needed to be mapped in user * mode, such as the entry/exit functions of the user space, or the stacks. */ + +#define KAISER_SHADOW_PGD_OFFSET 0x1000 + #ifdef __ASSEMBLY__ #ifdef CONFIG_KAISER .macro _SWITCH_TO_KERNEL_CR3 reg movq %cr3, \reg #ifdef CONFIG_KAISER_REAL_SWITCH -andq $(~0x1000), \reg +andq $(~KAISER_SHADOW_PGD_OFFSET), \reg #endif movq \reg, %cr3 .endm @@ -27,7 +30,7 @@ movq \reg, %cr3 .macro _SWITCH_TO_USER_CR3 reg movq %cr3, \reg #ifdef CONFIG_KAISER_REAL_SWITCH -orq $(0x1000), \reg +orq $(KAISER_SHADOW_PGD_OFFSET), \reg #endif movq \reg, %cr3 .endm Patches currently in stable-queue which might be from hughd(a)google.com are queue-4.4/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch queue-4.4/kaiser-add-nokaiser-boot-option-using-alternative.patch queue-4.4/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch queue-4.4/kaiser-_pgd_alloc-without-__gfp_repeat-to-avoid-stalls.patch queue-4.4/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch queue-4.4/kaiser-merged-update.patch queue-4.4/kaiser-delete-kaiser_real_switch-option.patch queue-4.4/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch queue-4.4/kaiser-fix-perf-crashes.patch queue-4.4/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch queue-4.4/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch queue-4.4/kaiser-enhanced-by-kernel-and-user-pcids.patch queue-4.4/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch queue-4.4/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch queue-4.4/kaiser-stack-map-page_size-at-thread_size-page_size.patch queue-4.4/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch queue-4.4/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch queue-4.4/kaiser-do-not-set-_page_nx-on-pgd_none.patch queue-4.4/kaiser-tidied-up-asm-kaiser.h-somewhat.patch queue-4.4/kaiser-cleanups-while-trying-for-gold-link.patch queue-4.4/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch queue-4.4/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch queue-4.4/kaiser-kernel-address-isolation.patch queue-4.4/kaiser-enomem-if-kaiser_pagetable_walk-null.patch queue-4.4/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch queue-4.4/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch queue-4.4/kaiser-kaiser-depends-on-smp.patch queue-4.4/kaiser-pcid-0-for-kernel-and-128-for-user.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "kaiser: merged update" has been added to the 4.4-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled kaiser: merged update to the 4.4-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-merged-update.patch and it can be found in the queue-4.4 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 18:58:12 CET 2018 From: Dave Hansen <dave.hansen(a)linux.intel.com> Date: Wed, 30 Aug 2017 16:23:00 -0700 Subject: kaiser: merged update From: Dave Hansen <dave.hansen(a)linux.intel.com> Merged fixes and cleanups, rebased to 4.4.89 tree (no 5-level paging). 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/entry/entry_64.S | 106 ++++++++++- arch/x86/include/asm/kaiser.h | 43 ++-- arch/x86/include/asm/pgtable.h | 18 + arch/x86/include/asm/pgtable_64.h | 48 ++++- arch/x86/include/asm/pgtable_types.h | 6 arch/x86/kernel/espfix_64.c | 13 - arch/x86/kernel/head_64.S | 19 +- arch/x86/kernel/ldt.c | 27 ++ arch/x86/kernel/tracepoint.c | 2 arch/x86/mm/kaiser.c | 318 +++++++++++++++++++++++++---------- arch/x86/mm/pageattr.c | 63 +++++- arch/x86/mm/pgtable.c | 40 +--- include/linux/kaiser.h | 26 ++ kernel/fork.c | 9 security/Kconfig | 5 15 files changed, 553 insertions(+), 190 deletions(-) create mode 100644 include/linux/kaiser.h --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -212,6 +212,13 @@ entry_SYSCALL_64_fastpath: movq RIP(%rsp), %rcx movq EFLAGS(%rsp), %r11 RESTORE_C_REGS_EXCEPT_RCX_R11 + /* + * This opens a window where we have a user CR3, but are + * running in the kernel. This makes using the CS + * register useless for telling whether or not we need to + * switch CR3 in NMIs. Normal interrupts are OK because + * they are off here. + */ SWITCH_USER_CR3 movq RSP(%rsp), %rsp /* @@ -350,11 +357,25 @@ GLOBAL(int_ret_from_sys_call) syscall_return_via_sysret: /* rcx and r11 are already restored (see code above) */ RESTORE_C_REGS_EXCEPT_RCX_R11 + /* + * This opens a window where we have a user CR3, but are + * running in the kernel. This makes using the CS + * register useless for telling whether or not we need to + * switch CR3 in NMIs. Normal interrupts are OK because + * they are off here. + */ SWITCH_USER_CR3 movq RSP(%rsp), %rsp USERGS_SYSRET64 opportunistic_sysret_failed: + /* + * This opens a window where we have a user CR3, but are + * running in the kernel. This makes using the CS + * register useless for telling whether or not we need to + * switch CR3 in NMIs. Normal interrupts are OK because + * they are off here. + */ SWITCH_USER_CR3 SWAPGS jmp restore_c_regs_and_iret @@ -1059,6 +1080,13 @@ ENTRY(error_entry) cld SAVE_C_REGS 8 SAVE_EXTRA_REGS 8 + /* + * error_entry() always returns with a kernel gsbase and + * CR3. We must also have a kernel CR3/gsbase before + * calling TRACE_IRQS_*. Just unconditionally switch to + * the kernel CR3 here. + */ + SWITCH_KERNEL_CR3 xorl %ebx, %ebx testb $3, CS+8(%rsp) jz .Lerror_kernelspace @@ -1069,7 +1097,6 @@ ENTRY(error_entry) * from user mode due to an IRET fault. */ SWAPGS - SWITCH_KERNEL_CR3 .Lerror_entry_from_usermode_after_swapgs: /* @@ -1122,7 +1149,7 @@ ENTRY(error_entry) * Switch to kernel gsbase: */ SWAPGS - SWITCH_KERNEL_CR3 + /* * Pretend that the exception came from user mode: set up pt_regs * as if we faulted immediately after IRET and clear EBX so that @@ -1222,7 +1249,10 @@ ENTRY(nmi) */ SWAPGS_UNSAFE_STACK - SWITCH_KERNEL_CR3_NO_STACK + /* + * percpu variables are mapped with user CR3, so no need + * to switch CR3 here. + */ cld movq %rsp, %rdx movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp @@ -1256,14 +1286,33 @@ ENTRY(nmi) movq %rsp, %rdi movq $-1, %rsi +#ifdef CONFIG_KAISER + /* Unconditionally use kernel CR3 for do_nmi() */ + /* %rax is saved above, so OK to clobber here */ + movq %cr3, %rax + pushq %rax +#ifdef CONFIG_KAISER_REAL_SWITCH + andq $(~0x1000), %rax +#endif + movq %rax, %cr3 +#endif call do_nmi + /* + * Unconditionally restore CR3. I know we return to + * kernel code that needs user CR3, but do we ever return + * to "user mode" where we need the kernel CR3? + */ +#ifdef CONFIG_KAISER + popq %rax + mov %rax, %cr3 +#endif /* * Return back to user mode. We must *not* do the normal exit - * work, because we don't want to enable interrupts. Fortunately, - * do_nmi doesn't modify pt_regs. + * work, because we don't want to enable interrupts. Do not + * switch to user CR3: we might be going back to kernel code + * that had a user CR3 set. */ - SWITCH_USER_CR3 SWAPGS jmp restore_c_regs_and_iret @@ -1459,23 +1508,54 @@ end_repeat_nmi: ALLOC_PT_GPREGS_ON_STACK /* - * Use paranoid_entry to handle SWAPGS, but no need to use paranoid_exit - * as we should not be calling schedule in NMI context. - * Even with normal interrupts enabled. An NMI should not be - * setting NEED_RESCHED or anything that normal interrupts and - * exceptions might do. + * Use the same approach as paranoid_entry to handle SWAPGS, but + * without CR3 handling since we do that differently in NMIs. No + * need to use paranoid_exit as we should not be calling schedule + * in NMI context. Even with normal interrupts enabled. An NMI + * should not be setting NEED_RESCHED or anything that normal + * interrupts and exceptions might do. */ - call paranoid_entry + cld + SAVE_C_REGS + SAVE_EXTRA_REGS + movl $1, %ebx + movl $MSR_GS_BASE, %ecx + rdmsr + testl %edx, %edx + js 1f /* negative -> in kernel */ + SWAPGS + xorl %ebx, %ebx +1: +#ifdef CONFIG_KAISER + /* Unconditionally use kernel CR3 for do_nmi() */ + /* %rax is saved above, so OK to clobber here */ + movq %cr3, %rax + pushq %rax +#ifdef CONFIG_KAISER_REAL_SWITCH + andq $(~0x1000), %rax +#endif + movq %rax, %cr3 +#endif /* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */ movq %rsp, %rdi + addq $8, %rdi /* point %rdi at ptregs, fixed up for CR3 */ movq $-1, %rsi call do_nmi + /* + * Unconditionally restore CR3. We might be returning to + * kernel code that needs user CR3, like just just before + * a sysret. + */ +#ifdef CONFIG_KAISER + popq %rax + mov %rax, %cr3 +#endif testl %ebx, %ebx /* swapgs needed? */ jnz nmi_restore nmi_swapgs: - SWITCH_USER_CR3_NO_STACK + /* We fixed up CR3 above, so no need to switch it here */ SWAPGS_UNSAFE_STACK nmi_restore: RESTORE_EXTRA_REGS --- a/arch/x86/include/asm/kaiser.h +++ b/arch/x86/include/asm/kaiser.h @@ -16,13 +16,17 @@ .macro _SWITCH_TO_KERNEL_CR3 reg movq %cr3, \reg +#ifdef CONFIG_KAISER_REAL_SWITCH andq $(~0x1000), \reg +#endif movq \reg, %cr3 .endm .macro _SWITCH_TO_USER_CR3 reg movq %cr3, \reg +#ifdef CONFIG_KAISER_REAL_SWITCH orq $(0x1000), \reg +#endif movq \reg, %cr3 .endm @@ -65,48 +69,53 @@ movq PER_CPU_VAR(unsafe_stack_register_b .endm #endif /* CONFIG_KAISER */ + #else /* __ASSEMBLY__ */ #ifdef CONFIG_KAISER -// Upon kernel/user mode switch, it may happen that -// the address space has to be switched before the registers have been stored. -// To change the address space, another register is needed. -// A register therefore has to be stored/restored. -// -DECLARE_PER_CPU_USER_MAPPED(unsigned long, unsafe_stack_register_backup); +/* + * Upon kernel/user mode switch, it may happen that the address + * space has to be switched before the registers have been + * stored. To change the address space, another register is + * needed. A register therefore has to be stored/restored. +*/ -#endif /* CONFIG_KAISER */ +DECLARE_PER_CPU_USER_MAPPED(unsigned long, unsafe_stack_register_backup); /** - * shadowmem_add_mapping - map a virtual memory part to the shadow mapping + * kaiser_add_mapping - map a virtual memory part to the shadow (user) mapping * @addr: the start address of the range * @size: the size of the range * @flags: The mapping flags of the pages * - * the mapping is done on a global scope, so no bigger synchronization has to be done. - * the pages have to be manually unmapped again when they are not needed any longer. + * The mapping is done on a global scope, so no bigger + * synchronization has to be done. the pages have to be + * manually unmapped again when they are not needed any longer. */ -extern void kaiser_add_mapping(unsigned long addr, unsigned long size, unsigned long flags); +extern int kaiser_add_mapping(unsigned long addr, unsigned long size, unsigned long flags); /** - * shadowmem_remove_mapping - unmap a virtual memory part of the shadow mapping + * kaiser_remove_mapping - unmap a virtual memory part of the shadow mapping * @addr: the start address of the range * @size: the size of the range */ extern void kaiser_remove_mapping(unsigned long start, unsigned long size); /** - * shadowmem_initialize_mapping - Initalize the shadow mapping + * kaiser_initialize_mapping - Initalize the shadow mapping * - * most parts of the shadow mapping can be mapped upon boot time. - * only the thread stacks have to be mapped on runtime. - * the mapped regions are not unmapped at all. + * Most parts of the shadow mapping can be mapped upon boot + * time. Only per-process things like the thread stacks + * or a new LDT have to be mapped at runtime. These boot- + * time mappings are permanent and nevertunmapped. */ extern void kaiser_init(void); -#endif +#endif /* CONFIG_KAISER */ + +#endif /* __ASSEMBLY */ --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -653,7 +653,17 @@ static inline pud_t *pud_offset(pgd_t *p static inline int pgd_bad(pgd_t pgd) { - return (pgd_flags(pgd) & ~_PAGE_USER) != _KERNPG_TABLE; + pgdval_t ignore_flags = _PAGE_USER; + /* + * We set NX on KAISER pgds that map userspace memory so + * that userspace can not meaningfully use the kernel + * page table by accident; it will fault on the first + * instruction it tries to run. See native_set_pgd(). + */ + if (IS_ENABLED(CONFIG_KAISER)) + ignore_flags |= _PAGE_NX; + + return (pgd_flags(pgd) & ~ignore_flags) != _KERNPG_TABLE; } static inline int pgd_none(pgd_t pgd) @@ -857,8 +867,10 @@ static inline void clone_pgd_range(pgd_t { memcpy(dst, src, count * sizeof(pgd_t)); #ifdef CONFIG_KAISER - // clone the shadow pgd part as well - memcpy(native_get_shadow_pgd(dst), native_get_shadow_pgd(src), count * sizeof(pgd_t)); + /* Clone the shadow pgd part as well */ + memcpy(native_get_shadow_pgd(dst), + native_get_shadow_pgd(src), + count * sizeof(pgd_t)); #endif } --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -107,26 +107,58 @@ static inline void native_pud_clear(pud_ } #ifdef CONFIG_KAISER -static inline pgd_t * native_get_shadow_pgd(pgd_t *pgdp) { +static inline pgd_t * native_get_shadow_pgd(pgd_t *pgdp) +{ return (pgd_t *)(void*)((unsigned long)(void*)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); } +#else +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) +{ + 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 - // We know that a pgd is page aligned. - // Therefore the lower indices have to be mapped to user space. - // These pages are mapped to the shadow mapping. - if ((((unsigned long)pgdp) % PAGE_SIZE) < (PAGE_SIZE / 2)) { + 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 & ~_PAGE_USER; + pgdp->pgd = pgd.pgd; + pgdp->pgd |= extra_kern_pgd_flags; #else /* CONFIG_KAISER */ *pgdp = pgd; #endif --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -42,7 +42,7 @@ #ifdef CONFIG_KAISER #define _PAGE_GLOBAL (_AT(pteval_t, 0)) #else -#define _PAGE_GLOBAL (_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL) +#define _PAGE_GLOBAL (_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL) #endif #define _PAGE_SOFTW1 (_AT(pteval_t, 1) << _PAGE_BIT_SOFTW1) #define _PAGE_SOFTW2 (_AT(pteval_t, 1) << _PAGE_BIT_SOFTW2) @@ -93,11 +93,7 @@ #define _PAGE_NX (_AT(pteval_t, 0)) #endif -#ifdef CONFIG_KAISER -#define _PAGE_PROTNONE (_AT(pteval_t, 0)) -#else #define _PAGE_PROTNONE (_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE) -#endif #define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | \ _PAGE_ACCESSED | _PAGE_DIRTY) --- a/arch/x86/kernel/espfix_64.c +++ b/arch/x86/kernel/espfix_64.c @@ -127,11 +127,14 @@ void __init init_espfix_bsp(void) /* Install the espfix pud into the kernel page directory */ pgd_p = &init_level4_pgt[pgd_index(ESPFIX_BASE_ADDR)]; pgd_populate(&init_mm, pgd_p, (pud_t *)espfix_pud_page); -#ifdef CONFIG_KAISER - // add the esp stack pud to the shadow mapping here. - // This can be done directly, because the fixup stack has its own pud - set_pgd(native_get_shadow_pgd(pgd_p), __pgd(_PAGE_TABLE | __pa((pud_t *)espfix_pud_page))); -#endif + /* + * Just copy the top-level PGD that is mapping the espfix + * area to ensure it is mapped into the shadow user page + * tables. + */ + if (IS_ENABLED(CONFIG_KAISER)) + set_pgd(native_get_shadow_pgd(pgd_p), + __pgd(_KERNPG_TABLE | __pa((pud_t *)espfix_pud_page))); /* Randomize the locations */ init_espfix_random(); --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -442,11 +442,24 @@ early_idt_ripmsg: GLOBAL(name) #ifdef CONFIG_KAISER +/* + * Each PGD needs to be 8k long and 8k aligned. We do not + * ever go out to userspace with these, so we do not + * strictly *need* the second page, but this allows us to + * have a single set_pgd() implementation that does not + * need to worry about whether it has 4k or 8k to work + * with. + * + * This ensures PGDs are 8k long: + */ +#define KAISER_USER_PGD_FILL 512 +/* This ensures they are 8k-aligned: */ #define NEXT_PGD_PAGE(name) \ .balign 2 * PAGE_SIZE; \ GLOBAL(name) #else #define NEXT_PGD_PAGE(name) NEXT_PAGE(name) +#define KAISER_USER_PGD_FILL 0 #endif /* Automate the creation of 1 to 1 mapping pmd entries */ @@ -461,6 +474,7 @@ GLOBAL(name) NEXT_PGD_PAGE(early_level4_pgt) .fill 511,8,0 .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE + .fill KAISER_USER_PGD_FILL,8,0 NEXT_PAGE(early_dynamic_pgts) .fill 512*EARLY_DYNAMIC_PAGE_TABLES,8,0 @@ -469,7 +483,8 @@ NEXT_PAGE(early_dynamic_pgts) #ifndef CONFIG_XEN NEXT_PGD_PAGE(init_level4_pgt) - .fill 2*512,8,0 + .fill 512,8,0 + .fill KAISER_USER_PGD_FILL,8,0 #else NEXT_PGD_PAGE(init_level4_pgt) .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE @@ -478,6 +493,7 @@ NEXT_PGD_PAGE(init_level4_pgt) .org init_level4_pgt + L4_START_KERNEL*8, 0 /* (2^48-(2*1024*1024*1024))/(2^39) = 511 */ .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE + .fill KAISER_USER_PGD_FILL,8,0 NEXT_PAGE(level3_ident_pgt) .quad level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE @@ -488,6 +504,7 @@ NEXT_PAGE(level2_ident_pgt) */ PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD) #endif + .fill KAISER_USER_PGD_FILL,8,0 NEXT_PAGE(level3_kernel_pgt) .fill L3_START_KERNEL,8,0 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -18,6 +18,7 @@ #include <linux/uaccess.h> #include <asm/ldt.h> +#include <asm/kaiser.h> #include <asm/desc.h> #include <asm/mmu_context.h> #include <asm/syscalls.h> @@ -34,11 +35,21 @@ static void flush_ldt(void *current_mm) set_ldt(pc->ldt->entries, pc->ldt->size); } +static void __free_ldt_struct(struct ldt_struct *ldt) +{ + if (ldt->size * LDT_ENTRY_SIZE > PAGE_SIZE) + vfree(ldt->entries); + else + free_page((unsigned long)ldt->entries); + kfree(ldt); +} + /* The caller must call finalize_ldt_struct on the result. LDT starts zeroed. */ static struct ldt_struct *alloc_ldt_struct(int size) { struct ldt_struct *new_ldt; int alloc_size; + int ret = 0; if (size > LDT_ENTRIES) return NULL; @@ -66,6 +77,14 @@ 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); + if (ret) { + __free_ldt_struct(new_ldt); + return NULL; + } new_ldt->size = size; return new_ldt; } @@ -92,12 +111,10 @@ static void free_ldt_struct(struct ldt_s if (likely(!ldt)) return; + kaiser_remove_mapping((unsigned long)ldt->entries, + ldt->size * LDT_ENTRY_SIZE); paravirt_free_ldt(ldt->entries, ldt->size); - if (ldt->size * LDT_ENTRY_SIZE > PAGE_SIZE) - vfree(ldt->entries); - else - free_page((unsigned long)ldt->entries); - kfree(ldt); + __free_ldt_struct(ldt); } /* --- a/arch/x86/kernel/tracepoint.c +++ b/arch/x86/kernel/tracepoint.c @@ -9,10 +9,12 @@ #include <linux/atomic.h> atomic_t trace_idt_ctr = ATOMIC_INIT(0); +__aligned(PAGE_SIZE) struct desc_ptr trace_idt_descr = { NR_VECTORS * 16 - 1, (unsigned long) trace_idt_table }; /* No need to be aligned, but done to keep all IDTs defined the same way. */ +__aligned(PAGE_SIZE) gate_desc trace_idt_table[NR_VECTORS] __page_aligned_bss; static int trace_irq_vector_refcount; --- a/arch/x86/mm/kaiser.c +++ b/arch/x86/mm/kaiser.c @@ -1,160 +1,306 @@ - - +#include <linux/bug.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/string.h> #include <linux/types.h> #include <linux/bug.h> #include <linux/init.h> +#include <linux/interrupt.h> #include <linux/spinlock.h> #include <linux/mm.h> - #include <linux/uaccess.h> +#include <linux/ftrace.h> + +#include <asm/kaiser.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> #include <asm/desc.h> #ifdef CONFIG_KAISER __visible DEFINE_PER_CPU_USER_MAPPED(unsigned long, unsafe_stack_register_backup); +/* + * At runtime, the only things we map are some things for CPU + * hotplug, and stacks for new processes. No two CPUs will ever + * be populating the same addresses, so we only need to ensure + * that we protect between two CPUs trying to allocate and + * populate the same page table page. + * + * Only take this lock when doing a set_p[4um]d(), but it is not + * needed for doing a set_pte(). We assume that only the *owner* + * of a given allocation will be doing this for _their_ + * allocation. + * + * This ensures that once a system has been running for a while + * and there have been stacks all over and these page tables + * are fully populated, there will be no further acquisitions of + * this lock. + */ +static DEFINE_SPINLOCK(shadow_table_allocation_lock); -/** - * Get the real ppn from a address in kernel mapping. - * @param address The virtual adrress - * @return the physical address +/* + * Returns -1 on error. */ -static inline unsigned long get_pa_from_mapping (unsigned long address) +static inline unsigned long get_pa_from_mapping(unsigned long vaddr) { pgd_t *pgd; pud_t *pud; pmd_t *pmd; pte_t *pte; - pgd = pgd_offset_k(address); - BUG_ON(pgd_none(*pgd) || pgd_large(*pgd)); + pgd = pgd_offset_k(vaddr); + /* + * We made all the kernel PGDs present in kaiser_init(). + * We expect them to stay that way. + */ + BUG_ON(pgd_none(*pgd)); + /* + * PGDs are either 512GB or 128TB on all x86_64 + * configurations. We don't handle these. + */ + BUG_ON(pgd_large(*pgd)); + + pud = pud_offset(pgd, vaddr); + if (pud_none(*pud)) { + WARN_ON_ONCE(1); + return -1; + } - pud = pud_offset(pgd, address); - BUG_ON(pud_none(*pud)); + if (pud_large(*pud)) + return (pud_pfn(*pud) << PAGE_SHIFT) | (vaddr & ~PUD_PAGE_MASK); - if (pud_large(*pud)) { - return (pud_pfn(*pud) << PAGE_SHIFT) | (address & ~PUD_PAGE_MASK); + pmd = pmd_offset(pud, vaddr); + if (pmd_none(*pmd)) { + WARN_ON_ONCE(1); + return -1; } - pmd = pmd_offset(pud, address); - BUG_ON(pmd_none(*pmd)); + if (pmd_large(*pmd)) + return (pmd_pfn(*pmd) << PAGE_SHIFT) | (vaddr & ~PMD_PAGE_MASK); - if (pmd_large(*pmd)) { - return (pmd_pfn(*pmd) << PAGE_SHIFT) | (address & ~PMD_PAGE_MASK); + pte = pte_offset_kernel(pmd, vaddr); + if (pte_none(*pte)) { + WARN_ON_ONCE(1); + return -1; } - pte = pte_offset_kernel(pmd, address); - BUG_ON(pte_none(*pte)); - - return (pte_pfn(*pte) << PAGE_SHIFT) | (address & ~PAGE_MASK); + return (pte_pfn(*pte) << PAGE_SHIFT) | (vaddr & ~PAGE_MASK); } -void _kaiser_copy (unsigned long start_addr, unsigned long size, - unsigned long flags) +/* + * This is a relatively normal page table walk, except that it + * also tries to allocate page tables pages along the way. + * + * Returns a pointer to a PTE on success, or NULL on failure. + */ +static pte_t *kaiser_pagetable_walk(unsigned long address, bool is_atomic) { - pgd_t *pgd; - pud_t *pud; pmd_t *pmd; - pte_t *pte; - unsigned long address; - unsigned long end_addr = start_addr + size; - unsigned long target_address; + pud_t *pud; + pgd_t *pgd = native_get_shadow_pgd(pgd_offset_k(address)); + gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO); - for (address = PAGE_ALIGN(start_addr - (PAGE_SIZE - 1)); - address < PAGE_ALIGN(end_addr); address += PAGE_SIZE) { - target_address = get_pa_from_mapping(address); + might_sleep(); + if (is_atomic) { + gfp &= ~GFP_KERNEL; + gfp |= __GFP_HIGH | __GFP_ATOMIC; + } - pgd = native_get_shadow_pgd(pgd_offset_k(address)); + if (pgd_none(*pgd)) { + WARN_ONCE(1, "All shadow pgds should have been populated"); + return NULL; + } + BUILD_BUG_ON(pgd_large(*pgd) != 0); - BUG_ON(pgd_none(*pgd) && "All shadow pgds should be mapped at this time\n"); - BUG_ON(pgd_large(*pgd)); + pud = pud_offset(pgd, address); + /* The shadow page tables do not use large mappings: */ + if (pud_large(*pud)) { + WARN_ON(1); + return NULL; + } + if (pud_none(*pud)) { + unsigned long new_pmd_page = __get_free_page(gfp); + if (!new_pmd_page) + return NULL; + spin_lock(&shadow_table_allocation_lock); + if (pud_none(*pud)) + set_pud(pud, __pud(_KERNPG_TABLE | __pa(new_pmd_page))); + else + free_page(new_pmd_page); + spin_unlock(&shadow_table_allocation_lock); + } - pud = pud_offset(pgd, address); - if (pud_none(*pud)) { - set_pud(pud, __pud(_PAGE_TABLE | __pa(pmd_alloc_one(0, address)))); - } - BUG_ON(pud_large(*pud)); + pmd = pmd_offset(pud, address); + /* The shadow page tables do not use large mappings: */ + if (pmd_large(*pmd)) { + WARN_ON(1); + return NULL; + } + if (pmd_none(*pmd)) { + unsigned long new_pte_page = __get_free_page(gfp); + if (!new_pte_page) + return NULL; + spin_lock(&shadow_table_allocation_lock); + if (pmd_none(*pmd)) + set_pmd(pmd, __pmd(_KERNPG_TABLE | __pa(new_pte_page))); + else + free_page(new_pte_page); + spin_unlock(&shadow_table_allocation_lock); + } - pmd = pmd_offset(pud, address); - if (pmd_none(*pmd)) { - set_pmd(pmd, __pmd(_PAGE_TABLE | __pa(pte_alloc_one_kernel(0, address)))); - } - BUG_ON(pmd_large(*pmd)); + return pte_offset_kernel(pmd, address); +} - pte = pte_offset_kernel(pmd, address); +int kaiser_add_user_map(const void *__start_addr, unsigned long size, + unsigned long flags) +{ + int ret = 0; + pte_t *pte; + unsigned long start_addr = (unsigned long )__start_addr; + unsigned long address = start_addr & PAGE_MASK; + unsigned long end_addr = PAGE_ALIGN(start_addr + size); + unsigned long target_address; + + 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_none(*pte)) { set_pte(pte, __pte(flags | target_address)); } else { - BUG_ON(__pa(pte_page(*pte)) != target_address); + pte_t tmp; + set_pte(&tmp, __pte(flags | target_address)); + WARN_ON_ONCE(!pte_same(*pte, tmp)); } } + return ret; } -// at first, add a pmd for every pgd entry in the shadowmem-kernel-part of the kernel mapping -static inline void __init _kaiser_init(void) +static int kaiser_add_user_map_ptrs(const void *start, const void *end, unsigned long flags) +{ + unsigned long size = end - start; + + return kaiser_add_user_map(start, size, flags); +} + +/* + * Ensure that the top level of the (shadow) page tables are + * entirely populated. This ensures that all processes that get + * forked have the same entries. This way, we do not have to + * ever go set up new entries in older processes. + * + * Note: we never free these, so there are no updates to them + * after this. + */ +static void __init kaiser_init_all_pgds(void) { pgd_t *pgd; int i = 0; pgd = native_get_shadow_pgd(pgd_offset_k((unsigned long )0)); for (i = PTRS_PER_PGD / 2; i < PTRS_PER_PGD; i++) { - set_pgd(pgd + i, __pgd(_PAGE_TABLE |__pa(pud_alloc_one(0, 0)))); + pgd_t new_pgd; + pud_t *pud = pud_alloc_one(&init_mm, PAGE_OFFSET + i * PGDIR_SIZE); + if (!pud) { + WARN_ON(1); + break; + } + new_pgd = __pgd(_KERNPG_TABLE |__pa(pud)); + /* + * Make sure not to stomp on some other pgd entry. + */ + if (!pgd_none(pgd[i])) { + WARN_ON(1); + continue; + } + set_pgd(pgd + i, new_pgd); } } +#define kaiser_add_user_map_early(start, size, flags) do { \ + int __ret = kaiser_add_user_map(start, size, flags); \ + WARN_ON(__ret); \ +} while (0) + +#define kaiser_add_user_map_ptrs_early(start, end, flags) do { \ + int __ret = kaiser_add_user_map_ptrs(start, end, flags); \ + WARN_ON(__ret); \ +} while (0) + extern char __per_cpu_user_mapped_start[], __per_cpu_user_mapped_end[]; -spinlock_t shadow_table_lock; +/* + * If anything in here fails, we will likely die on one of the + * first kernel->user transitions and init will die. But, we + * will have most of the kernel up by then and should be able to + * get a clean warning out of it. If we BUG_ON() here, we run + * the risk of being before we have good console output. + */ void __init kaiser_init(void) { int cpu; - spin_lock_init(&shadow_table_lock); - - spin_lock(&shadow_table_lock); - _kaiser_init(); + kaiser_init_all_pgds(); for_each_possible_cpu(cpu) { - // map the per cpu user variables - _kaiser_copy( - (unsigned long) (__per_cpu_user_mapped_start + per_cpu_offset(cpu)), - (unsigned long) __per_cpu_user_mapped_end - (unsigned long) __per_cpu_user_mapped_start, - __PAGE_KERNEL); - } - - // map the entry/exit text section, which is responsible to switch between user- and kernel mode - _kaiser_copy( - (unsigned long) __entry_text_start, - (unsigned long) __entry_text_end - (unsigned long) __entry_text_start, - __PAGE_KERNEL_RX); - - // the fixed map address of the idt_table - _kaiser_copy( - (unsigned long) idt_descr.address, - sizeof(gate_desc) * NR_VECTORS, - __PAGE_KERNEL_RO); + void *percpu_vaddr = __per_cpu_user_mapped_start + + per_cpu_offset(cpu); + unsigned long percpu_sz = __per_cpu_user_mapped_end - + __per_cpu_user_mapped_start; + kaiser_add_user_map_early(percpu_vaddr, percpu_sz, + __PAGE_KERNEL); + } - spin_unlock(&shadow_table_lock); + /* + * Map the entry/exit text section, which is needed at + * switches from user to and from kernel. + */ + kaiser_add_user_map_ptrs_early(__entry_text_start, __entry_text_end, + __PAGE_KERNEL_RX); + +#if defined(CONFIG_FUNCTION_GRAPH_TRACER) || defined(CONFIG_KASAN) + kaiser_add_user_map_ptrs_early(__irqentry_text_start, + __irqentry_text_end, + __PAGE_KERNEL_RX); +#endif + kaiser_add_user_map_early((void *)idt_descr.address, + sizeof(gate_desc) * NR_VECTORS, + __PAGE_KERNEL_RO); +#ifdef CONFIG_TRACING + kaiser_add_user_map_early(&trace_idt_descr, + sizeof(trace_idt_descr), + __PAGE_KERNEL); + kaiser_add_user_map_early(&trace_idt_table, + sizeof(gate_desc) * NR_VECTORS, + __PAGE_KERNEL); +#endif + kaiser_add_user_map_early(&debug_idt_descr, sizeof(debug_idt_descr), + __PAGE_KERNEL); + kaiser_add_user_map_early(&debug_idt_table, + sizeof(gate_desc) * NR_VECTORS, + __PAGE_KERNEL); } +extern void unmap_pud_range_nofree(pgd_t *pgd, unsigned long start, unsigned long end); // add a mapping to the shadow-mapping, and synchronize the mappings -void kaiser_add_mapping(unsigned long addr, unsigned long size, unsigned long flags) +int kaiser_add_mapping(unsigned long addr, unsigned long size, unsigned long flags) { - spin_lock(&shadow_table_lock); - _kaiser_copy(addr, size, flags); - spin_unlock(&shadow_table_lock); + return kaiser_add_user_map((const void *)addr, size, flags); } -extern void unmap_pud_range(pgd_t *pgd, unsigned long start, unsigned long end); void kaiser_remove_mapping(unsigned long start, unsigned long size) { - pgd_t *pgd = native_get_shadow_pgd(pgd_offset_k(start)); - spin_lock(&shadow_table_lock); - do { - unmap_pud_range(pgd, start, start + size); - } while (pgd++ != native_get_shadow_pgd(pgd_offset_k(start + size))); - spin_unlock(&shadow_table_lock); + unsigned long end = start + size; + unsigned long addr; + + for (addr = start; addr < end; addr += PGDIR_SIZE) { + pgd_t *pgd = native_get_shadow_pgd(pgd_offset_k(addr)); + /* + * unmap_p4d_range() handles > P4D_SIZE unmaps, + * so no need to trim 'end'. + */ + unmap_pud_range_nofree(pgd, addr, end); + } } #endif /* CONFIG_KAISER */ --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -52,6 +52,7 @@ static DEFINE_SPINLOCK(cpa_lock); #define CPA_FLUSHTLB 1 #define CPA_ARRAY 2 #define CPA_PAGES_ARRAY 4 +#define CPA_FREE_PAGETABLES 8 #ifdef CONFIG_PROC_FS static unsigned long direct_pages_count[PG_LEVEL_NUM]; @@ -723,10 +724,13 @@ static int split_large_page(struct cpa_d return 0; } -static bool try_to_free_pte_page(pte_t *pte) +static bool try_to_free_pte_page(struct cpa_data *cpa, pte_t *pte) { int i; + if (!(cpa->flags & CPA_FREE_PAGETABLES)) + return false; + for (i = 0; i < PTRS_PER_PTE; i++) if (!pte_none(pte[i])) return false; @@ -735,10 +739,13 @@ static bool try_to_free_pte_page(pte_t * return true; } -static bool try_to_free_pmd_page(pmd_t *pmd) +static bool try_to_free_pmd_page(struct cpa_data *cpa, pmd_t *pmd) { int i; + if (!(cpa->flags & CPA_FREE_PAGETABLES)) + return false; + for (i = 0; i < PTRS_PER_PMD; i++) if (!pmd_none(pmd[i])) return false; @@ -759,7 +766,9 @@ static bool try_to_free_pud_page(pud_t * return true; } -static bool unmap_pte_range(pmd_t *pmd, unsigned long start, unsigned long end) +static bool unmap_pte_range(struct cpa_data *cpa, pmd_t *pmd, + unsigned long start, + unsigned long end) { pte_t *pte = pte_offset_kernel(pmd, start); @@ -770,22 +779,23 @@ static bool unmap_pte_range(pmd_t *pmd, pte++; } - if (try_to_free_pte_page((pte_t *)pmd_page_vaddr(*pmd))) { + if (try_to_free_pte_page(cpa, (pte_t *)pmd_page_vaddr(*pmd))) { pmd_clear(pmd); return true; } return false; } -static void __unmap_pmd_range(pud_t *pud, pmd_t *pmd, +static void __unmap_pmd_range(struct cpa_data *cpa, pud_t *pud, pmd_t *pmd, unsigned long start, unsigned long end) { - if (unmap_pte_range(pmd, start, end)) - if (try_to_free_pmd_page((pmd_t *)pud_page_vaddr(*pud))) + if (unmap_pte_range(cpa, pmd, start, end)) + if (try_to_free_pmd_page(cpa, (pmd_t *)pud_page_vaddr(*pud))) pud_clear(pud); } -static void unmap_pmd_range(pud_t *pud, unsigned long start, unsigned long end) +static void unmap_pmd_range(struct cpa_data *cpa, pud_t *pud, + unsigned long start, unsigned long end) { pmd_t *pmd = pmd_offset(pud, start); @@ -796,7 +806,7 @@ static void unmap_pmd_range(pud_t *pud, unsigned long next_page = (start + PMD_SIZE) & PMD_MASK; unsigned long pre_end = min_t(unsigned long, end, next_page); - __unmap_pmd_range(pud, pmd, start, pre_end); + __unmap_pmd_range(cpa, pud, pmd, start, pre_end); start = pre_end; pmd++; @@ -809,7 +819,8 @@ static void unmap_pmd_range(pud_t *pud, if (pmd_large(*pmd)) pmd_clear(pmd); else - __unmap_pmd_range(pud, pmd, start, start + PMD_SIZE); + __unmap_pmd_range(cpa, pud, pmd, + start, start + PMD_SIZE); start += PMD_SIZE; pmd++; @@ -819,17 +830,19 @@ static void unmap_pmd_range(pud_t *pud, * 4K leftovers? */ if (start < end) - return __unmap_pmd_range(pud, pmd, start, end); + return __unmap_pmd_range(cpa, pud, pmd, start, end); /* * Try again to free the PMD page if haven't succeeded above. */ if (!pud_none(*pud)) - if (try_to_free_pmd_page((pmd_t *)pud_page_vaddr(*pud))) + if (try_to_free_pmd_page(cpa, (pmd_t *)pud_page_vaddr(*pud))) pud_clear(pud); } -void unmap_pud_range(pgd_t *pgd, unsigned long start, unsigned long end) +static void __unmap_pud_range(struct cpa_data *cpa, pgd_t *pgd, + unsigned long start, + unsigned long end) { pud_t *pud = pud_offset(pgd, start); @@ -840,7 +853,7 @@ void unmap_pud_range(pgd_t *pgd, unsigne unsigned long next_page = (start + PUD_SIZE) & PUD_MASK; unsigned long pre_end = min_t(unsigned long, end, next_page); - unmap_pmd_range(pud, start, pre_end); + unmap_pmd_range(cpa, pud, start, pre_end); start = pre_end; pud++; @@ -854,7 +867,7 @@ void unmap_pud_range(pgd_t *pgd, unsigne if (pud_large(*pud)) pud_clear(pud); else - unmap_pmd_range(pud, start, start + PUD_SIZE); + unmap_pmd_range(cpa, pud, start, start + PUD_SIZE); start += PUD_SIZE; pud++; @@ -864,7 +877,7 @@ void unmap_pud_range(pgd_t *pgd, unsigne * 2M leftovers? */ if (start < end) - unmap_pmd_range(pud, start, end); + unmap_pmd_range(cpa, pud, start, end); /* * No need to try to free the PUD page because we'll free it in @@ -872,6 +885,24 @@ void unmap_pud_range(pgd_t *pgd, unsigne */ } +static void unmap_pud_range(pgd_t *pgd, unsigned long start, unsigned long end) +{ + struct cpa_data cpa = { + .flags = CPA_FREE_PAGETABLES, + }; + + __unmap_pud_range(&cpa, pgd, start, end); +} + +void unmap_pud_range_nofree(pgd_t *pgd, unsigned long start, unsigned long end) +{ + struct cpa_data cpa = { + .flags = 0, + }; + + __unmap_pud_range(&cpa, pgd, start, end); +} + static void unmap_pgd_range(pgd_t *root, unsigned long addr, unsigned long end) { pgd_t *pgd_entry = root + pgd_index(addr); --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -340,40 +340,26 @@ static inline void _pgd_free(pgd_t *pgd) kmem_cache_free(pgd_cache, pgd); } #else -static inline pgd_t *_pgd_alloc(void) -{ -#ifdef CONFIG_KAISER - // Instead of one PML4, we aquire two PML4s and, thus, an 8kb-aligned memory - // block. Therefore, we have to allocate at least 3 pages. However, the - // __get_free_pages returns us 4 pages. Hence, we store the base pointer at - // the beginning of the page of our 8kb-aligned memory block in order to - // correctly free it afterwars. - unsigned long pages = __get_free_pages(PGALLOC_GFP, get_order(4*PAGE_SIZE)); - - if(native_get_normal_pgd((pgd_t*) pages) == (pgd_t*) pages) - { - *((unsigned long*)(pages + 2 * PAGE_SIZE)) = pages; - return (pgd_t *) pages; - } - else - { - *((unsigned long*)(pages + 3 * PAGE_SIZE)) = pages; - return (pgd_t *) (pages + PAGE_SIZE); - } +#ifdef CONFIG_KAISER +/* + * Instead of one pmd, we aquire two pmds. Being order-1, it is + * both 8k in size and 8k-aligned. That lets us just flip bit 12 + * in a pointer to swap between the two 4k halves. + */ +#define PGD_ALLOCATION_ORDER 1 #else - return (pgd_t *)__get_free_page(PGALLOC_GFP); +#define PGD_ALLOCATION_ORDER 0 #endif + +static inline pgd_t *_pgd_alloc(void) +{ + return (pgd_t *)__get_free_pages(PGALLOC_GFP, PGD_ALLOCATION_ORDER); } static inline void _pgd_free(pgd_t *pgd) { -#ifdef CONFIG_KAISER - unsigned long pages = *((unsigned long*) ((char*) pgd + 2 * PAGE_SIZE)); - free_pages(pages, get_order(4*PAGE_SIZE)); -#else - free_page((unsigned long)pgd); -#endif + free_pages((unsigned long)pgd, PGD_ALLOCATION_ORDER); } #endif /* CONFIG_X86_PAE */ --- /dev/null +++ b/include/linux/kaiser.h @@ -0,0 +1,26 @@ +#ifndef _INCLUDE_KAISER_H +#define _INCLUDE_KAISER_H + +#ifdef CONFIG_KAISER +#include <asm/kaiser.h> +#else + +/* + * These stubs are used whenever CONFIG_KAISER is off, which + * includes architectures that support KAISER, but have it + * disabled. + */ + +static inline void kaiser_init(void) +{ +} +static inline void kaiser_remove_mapping(unsigned long start, unsigned long size) +{ +} +static inline int kaiser_add_mapping(unsigned long addr, unsigned long size, unsigned long flags) +{ + return 0; +} + +#endif /* !CONFIG_KAISER */ +#endif /* _INCLUDE_KAISER_H */ --- a/kernel/fork.c +++ b/kernel/fork.c @@ -58,6 +58,7 @@ #include <linux/tsacct_kern.h> #include <linux/cn_proc.h> #include <linux/freezer.h> +#include <linux/kaiser.h> #include <linux/delayacct.h> #include <linux/taskstats_kern.h> #include <linux/random.h> @@ -335,7 +336,6 @@ void set_task_stack_end_magic(struct tas *stackend = STACK_END_MAGIC; /* for overflow detection */ } -extern void kaiser_add_mapping(unsigned long addr, unsigned long size, unsigned long flags); static struct task_struct *dup_task_struct(struct task_struct *orig, int node) { struct task_struct *tsk; @@ -357,9 +357,10 @@ static struct task_struct *dup_task_stru goto free_ti; tsk->stack = ti; -#ifdef CONFIG_KAISER - kaiser_add_mapping((unsigned long)tsk->stack, THREAD_SIZE, __PAGE_KERNEL); -#endif + + err= kaiser_add_mapping((unsigned long)tsk->stack, THREAD_SIZE, __PAGE_KERNEL); + if (err) + goto free_ti; #ifdef CONFIG_SECCOMP /* * We must handle setting up seccomp filters once we're under --- a/security/Kconfig +++ b/security/Kconfig @@ -32,12 +32,17 @@ config SECURITY If you are unsure how to answer this question, answer N. config KAISER bool "Remove the kernel mapping in user mode" + default y depends on X86_64 depends on !PARAVIRT help This enforces a strict kernel and user space isolation in order to close hardware side channels on kernel address information. +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 dave.hansen(a)linux.intel.com are queue-4.4/x86-paravirt-dont-patch-flush_tlb_single.patch queue-4.4/kaiser-merged-update.patch queue-4.4/kaiser-enhanced-by-kernel-and-user-pcids.patch

7 years, 4 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror