From 3382290ed2d5e275429cef510ab21889d3ccd164 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 24 Oct 2017 11:22:48 +0100 Subject: locking/barriers: Convert users of lockless_dereference() to READ_ONCE() [ Note, this is a Git cherry-pick of the following commit: 506458efaf15 ("locking/barriers: Convert users of lockless_dereference() to READ_ONCE()") ... for easier x86 PTI code testing and back-porting. ] READ_ONCE() now has an implicit smp_read_barrier_depends() call, so it can be used instead of lockless_dereference() without any change in semantics. Signed-off-by: Will Deacon Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1508840570-22169-4-git-send-email-will.deacon@arm.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/mmu_context.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86/include/asm/mmu_context.h') diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 6699fc441644..6d16d15d09a0 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -73,8 +73,8 @@ static inline void load_mm_ldt(struct mm_struct *mm) #ifdef CONFIG_MODIFY_LDT_SYSCALL struct ldt_struct *ldt; - /* lockless_dereference synchronizes with smp_store_release */ - ldt = lockless_dereference(mm->context.ldt); + /* READ_ONCE synchronizes with smp_store_release */ + ldt = READ_ONCE(mm->context.ldt); /* * Any change to mm->context.ldt is followed by an IPI to all -- cgit From c10e83f598d08046dd1ebc8360d4bb12d802d51b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 14 Dec 2017 12:27:29 +0100 Subject: arch, mm: Allow arch_dup_mmap() to fail In order to sanitize the LDT initialization on x86 arch_dup_mmap() must be allowed to fail. Fix up all instances. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Cc: Andy Lutomirski Cc: Andy Lutomirsky Cc: Boris Ostrovsky Cc: Borislav Petkov Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Hansen Cc: Dave Hansen Cc: David Laight Cc: Denys Vlasenko Cc: Eduardo Valentin Cc: Greg KH Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Juergen Gross Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Will Deacon Cc: aliguori@amazon.com Cc: dan.j.williams@intel.com Cc: hughd@google.com Cc: keescook@google.com Cc: kirill.shutemov@linux.intel.com Cc: linux-mm@kvack.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/mmu_context.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86/include/asm/mmu_context.h') diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 6d16d15d09a0..c76162439c8a 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -176,10 +176,10 @@ do { \ } while (0) #endif -static inline void arch_dup_mmap(struct mm_struct *oldmm, - struct mm_struct *mm) +static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) { paravirt_arch_dup_mmap(oldmm, mm); + return 0; } static inline void arch_exit_mmap(struct mm_struct *mm) -- cgit From c2b3496bb30bd159e9de42e5c952e1f1f33c9a77 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 14 Dec 2017 12:27:30 +0100 Subject: x86/ldt: Rework locking The LDT is duplicated on fork() and on exec(), which is wrong as exec() should start from a clean state, i.e. without LDT. To fix this the LDT duplication code will be moved into arch_dup_mmap() which is only called for fork(). This introduces a locking problem. arch_dup_mmap() holds mmap_sem of the parent process, but the LDT duplication code needs to acquire mm->context.lock to access the LDT data safely, which is the reverse lock order of write_ldt() where mmap_sem nests into context.lock. Solve this by introducing a new rw semaphore which serializes the read/write_ldt() syscall operations and use context.lock to protect the actual installment of the LDT descriptor. So context.lock stabilizes mm->context.ldt and can nest inside of the new semaphore or mmap_sem. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Cc: Andy Lutomirski Cc: Andy Lutomirsky Cc: Boris Ostrovsky Cc: Borislav Petkov Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Hansen Cc: Dave Hansen Cc: David Laight Cc: Denys Vlasenko Cc: Eduardo Valentin Cc: Greg KH Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Juergen Gross Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Will Deacon Cc: aliguori@amazon.com Cc: dan.j.williams@intel.com Cc: hughd@google.com Cc: keescook@google.com Cc: kirill.shutemov@linux.intel.com Cc: linux-mm@kvack.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/mmu_context.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/x86/include/asm/mmu_context.h') diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index c76162439c8a..4fdbe5efe535 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -132,6 +132,8 @@ void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk); static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { + mutex_init(&mm->context.lock); + mm->context.ctx_id = atomic64_inc_return(&last_mm_ctx_id); atomic64_set(&mm->context.tlb_gen, 0); -- cgit From a4828f81037f491b2cc986595e3a969a6eeb2fb5 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 14 Dec 2017 12:27:31 +0100 Subject: x86/ldt: Prevent LDT inheritance on exec The LDT is inherited across fork() or exec(), but that makes no sense at all because exec() is supposed to start the process clean. The reason why this happens is that init_new_context_ldt() is called from init_new_context() which obviously needs to be called for both fork() and exec(). It would be surprising if anything relies on that behaviour, so it seems to be safe to remove that misfeature. Split the context initialization into two parts. Clear the LDT pointer and initialize the mutex from the general context init and move the LDT duplication to arch_dup_mmap() which is only called on fork(). Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra Cc: Andy Lutomirski Cc: Andy Lutomirsky Cc: Boris Ostrovsky Cc: Borislav Petkov Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Hansen Cc: Dave Hansen Cc: David Laight Cc: Denys Vlasenko Cc: Eduardo Valentin Cc: Greg KH Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Juergen Gross Cc: Linus Torvalds Cc: Will Deacon Cc: aliguori@amazon.com Cc: dan.j.williams@intel.com Cc: hughd@google.com Cc: keescook@google.com Cc: kirill.shutemov@linux.intel.com Cc: linux-mm@kvack.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/mmu_context.h | 21 ++++++++++++++------- 1 file changed, 14 insertions(+), 7 deletions(-) (limited to 'arch/x86/include/asm/mmu_context.h') diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 4fdbe5efe535..5e25423bf9bb 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -57,11 +57,17 @@ struct ldt_struct { /* * Used for LDT copy/destruction. */ -int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm); +static inline void init_new_context_ldt(struct mm_struct *mm) +{ + mm->context.ldt = NULL; + init_rwsem(&mm->context.ldt_usr_sem); +} +int ldt_dup_context(struct mm_struct *oldmm, struct mm_struct *mm); void destroy_context_ldt(struct mm_struct *mm); #else /* CONFIG_MODIFY_LDT_SYSCALL */ -static inline int init_new_context_ldt(struct task_struct *tsk, - struct mm_struct *mm) +static inline void init_new_context_ldt(struct mm_struct *mm) { } +static inline int ldt_dup_context(struct mm_struct *oldmm, + struct mm_struct *mm) { return 0; } @@ -137,15 +143,16 @@ static inline int init_new_context(struct task_struct *tsk, mm->context.ctx_id = atomic64_inc_return(&last_mm_ctx_id); atomic64_set(&mm->context.tlb_gen, 0); - #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS +#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS if (cpu_feature_enabled(X86_FEATURE_OSPKE)) { /* pkey 0 is the default and always allocated */ mm->context.pkey_allocation_map = 0x1; /* -1 means unallocated or invalid */ mm->context.execute_only_pkey = -1; } - #endif - return init_new_context_ldt(tsk, mm); +#endif + init_new_context_ldt(mm); + return 0; } static inline void destroy_context(struct mm_struct *mm) { @@ -181,7 +188,7 @@ do { \ static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) { paravirt_arch_dup_mmap(oldmm, mm); - return 0; + return ldt_dup_context(oldmm, mm); } static inline void arch_exit_mmap(struct mm_struct *mm) -- cgit From 50fb83a62cf472dc53ba23bd3f7bd6c1b2b3b53e Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Mon, 4 Dec 2017 15:07:54 +0100 Subject: x86/mm: Move the CR3 construction functions to tlbflush.h For flushing the TLB, the ASID which has been programmed into the hardware must be known. That differs from what is in 'cpu_tlbstate'. Add functions to transform the 'cpu_tlbstate' values into to the one programmed into the hardware (CR3). It's not easy to include mmu_context.h into tlbflush.h, so just move the CR3 building over to tlbflush.h. Signed-off-by: Dave Hansen Signed-off-by: Thomas Gleixner Cc: Andy Lutomirski Cc: Boris Ostrovsky Cc: Borislav Petkov Cc: Brian Gerst Cc: David Laight Cc: Denys Vlasenko Cc: Eduardo Valentin Cc: Greg KH Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Juergen Gross Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Will Deacon Cc: aliguori@amazon.com Cc: daniel.gruss@iaik.tugraz.at Cc: hughd@google.com Cc: keescook@google.com Cc: linux-mm@kvack.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/mmu_context.h | 29 +---------------------------- 1 file changed, 1 insertion(+), 28 deletions(-) (limited to 'arch/x86/include/asm/mmu_context.h') diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 5e25423bf9bb..5ede7cae1d67 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -290,33 +290,6 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, return __pkru_allows_pkey(vma_pkey(vma), write); } -/* - * If PCID is on, ASID-aware code paths put the ASID+1 into the PCID - * bits. This serves two purposes. It prevents a nasty situation in - * which PCID-unaware code saves CR3, loads some other value (with PCID - * == 0), and then restores CR3, thus corrupting the TLB for ASID 0 if - * the saved ASID was nonzero. It also means that any bugs involving - * loading a PCID-enabled CR3 with CR4.PCIDE off will trigger - * deterministically. - */ - -static inline unsigned long build_cr3(struct mm_struct *mm, u16 asid) -{ - if (static_cpu_has(X86_FEATURE_PCID)) { - VM_WARN_ON_ONCE(asid > 4094); - return __sme_pa(mm->pgd) | (asid + 1); - } else { - VM_WARN_ON_ONCE(asid != 0); - return __sme_pa(mm->pgd); - } -} - -static inline unsigned long build_cr3_noflush(struct mm_struct *mm, u16 asid) -{ - VM_WARN_ON_ONCE(asid > 4094); - return __sme_pa(mm->pgd) | (asid + 1) | CR3_NOFLUSH; -} - /* * This can be used from process context to figure out what the value of * CR3 is without needing to do a (slow) __read_cr3(). @@ -326,7 +299,7 @@ static inline unsigned long build_cr3_noflush(struct mm_struct *mm, u16 asid) */ static inline unsigned long __get_current_cr3_fast(void) { - unsigned long cr3 = build_cr3(this_cpu_read(cpu_tlbstate.loaded_mm), + unsigned long cr3 = build_cr3(this_cpu_read(cpu_tlbstate.loaded_mm)->pgd, this_cpu_read(cpu_tlbstate.loaded_mm_asid)); /* For now, be very restrictive about when this can be called. */ -- cgit From f55f0501cbf65ec41cca5058513031b711730b1d Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Tue, 12 Dec 2017 07:56:45 -0800 Subject: x86/pti: Put the LDT in its own PGD if PTI is on With PTI enabled, the LDT must be mapped in the usermode tables somewhere. The LDT is per process, i.e. per mm. An earlier approach mapped the LDT on context switch into a fixmap area, but that's a big overhead and exhausted the fixmap space when NR_CPUS got big. Take advantage of the fact that there is an address space hole which provides a completely unused pgd. Use this pgd to manage per-mm LDT mappings. This has a down side: the LDT isn't (currently) randomized, and an attack that can write the LDT is instant root due to call gates (thanks, AMD, for leaving call gates in AMD64 but designing them wrong so they're only useful for exploits). This can be mitigated by making the LDT read-only or randomizing the mapping, either of which is strightforward on top of this patch. This will significantly slow down LDT users, but that shouldn't matter for important workloads -- the LDT is only used by DOSEMU(2), Wine, and very old libc implementations. [ tglx: Cleaned it up. ] Signed-off-by: Andy Lutomirski Signed-off-by: Thomas Gleixner Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Hansen Cc: Dave Hansen Cc: David Laight Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Juergen Gross Cc: Kees Cook Cc: Kirill A. Shutemov Cc: Linus Torvalds Cc: Peter Zijlstra Signed-off-by: Ingo Molnar --- arch/x86/include/asm/mmu_context.h | 59 ++++++++++++++++++++++++++++++++++---- 1 file changed, 53 insertions(+), 6 deletions(-) (limited to 'arch/x86/include/asm/mmu_context.h') diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 5ede7cae1d67..c931b88982a0 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -50,10 +50,33 @@ struct ldt_struct { * call gates. On native, we could merge the ldt_struct and LDT * allocations, but it's not worth trying to optimize. */ - struct desc_struct *entries; - unsigned int nr_entries; + struct desc_struct *entries; + unsigned int nr_entries; + + /* + * If PTI is in use, then the entries array is not mapped while we're + * in user mode. The whole array will be aliased at the addressed + * given by ldt_slot_va(slot). We use two slots so that we can allocate + * and map, and enable a new LDT without invalidating the mapping + * of an older, still-in-use LDT. + * + * slot will be -1 if this LDT doesn't have an alias mapping. + */ + int slot; }; +/* This is a multiple of PAGE_SIZE. */ +#define LDT_SLOT_STRIDE (LDT_ENTRIES * LDT_ENTRY_SIZE) + +static inline void *ldt_slot_va(int slot) +{ +#ifdef CONFIG_X86_64 + return (void *)(LDT_BASE_ADDR + LDT_SLOT_STRIDE * slot); +#else + BUG(); +#endif +} + /* * Used for LDT copy/destruction. */ @@ -64,6 +87,7 @@ static inline void init_new_context_ldt(struct mm_struct *mm) } int ldt_dup_context(struct mm_struct *oldmm, struct mm_struct *mm); void destroy_context_ldt(struct mm_struct *mm); +void ldt_arch_exit_mmap(struct mm_struct *mm); #else /* CONFIG_MODIFY_LDT_SYSCALL */ static inline void init_new_context_ldt(struct mm_struct *mm) { } static inline int ldt_dup_context(struct mm_struct *oldmm, @@ -71,7 +95,8 @@ static inline int ldt_dup_context(struct mm_struct *oldmm, { return 0; } -static inline void destroy_context_ldt(struct mm_struct *mm) {} +static inline void destroy_context_ldt(struct mm_struct *mm) { } +static inline void ldt_arch_exit_mmap(struct mm_struct *mm) { } #endif static inline void load_mm_ldt(struct mm_struct *mm) @@ -96,10 +121,31 @@ static inline void load_mm_ldt(struct mm_struct *mm) * that we can see. */ - if (unlikely(ldt)) - set_ldt(ldt->entries, ldt->nr_entries); - else + if (unlikely(ldt)) { + if (static_cpu_has(X86_FEATURE_PTI)) { + if (WARN_ON_ONCE((unsigned long)ldt->slot > 1)) { + /* + * Whoops -- either the new LDT isn't mapped + * (if slot == -1) or is mapped into a bogus + * slot (if slot > 1). + */ + clear_LDT(); + return; + } + + /* + * If page table isolation is enabled, ldt->entries + * will not be mapped in the userspace pagetables. + * Tell the CPU to access the LDT through the alias + * at ldt_slot_va(ldt->slot). + */ + set_ldt(ldt_slot_va(ldt->slot), ldt->nr_entries); + } else { + set_ldt(ldt->entries, ldt->nr_entries); + } + } else { clear_LDT(); + } #else clear_LDT(); #endif @@ -194,6 +240,7 @@ static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) static inline void arch_exit_mmap(struct mm_struct *mm) { paravirt_arch_exit_mmap(mm); + ldt_arch_exit_mmap(mm); } #ifdef CONFIG_X86_64 -- cgit