From 5962dd22f0ff6f7d72fff974b3c637d52586643e Mon Sep 17 00:00:00 2001 From: Sinan Kaya Date: Wed, 2 Jan 2019 18:10:37 +0000 Subject: [PATCH 1/8] x86/intel/lpss: Make PCI dependency explicit After commit 5d32a66541c4 ("PCI/ACPI: Allow ACPI to be built without CONFIG_PCI set") dependencies on CONFIG_PCI that previously were satisfied implicitly through dependencies on CONFIG_ACPI have to be specified directly. LPSS code relies on PCI infrastructure but this dependency has not been explicitly called out so do that. Fixes: 5d32a66541c46 ("PCI/ACPI: Allow ACPI to be built without CONFIG_PCI set") Signed-off-by: Sinan Kaya Signed-off-by: Borislav Petkov Cc: "H. Peter Anvin" Cc: linux-acpi@vger.kernel.org Cc: x86-ml Link: https://lkml.kernel.org/r/20190102181038.4418-11-okaya@kernel.org --- arch/x86/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 15af091611e2..4b4a7f32b68e 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -617,7 +617,7 @@ config X86_INTEL_QUARK config X86_INTEL_LPSS bool "Intel Low Power Subsystem Support" - depends on X86 && ACPI + depends on X86 && ACPI && PCI select COMMON_CLK select PINCTRL select IOSF_MBI From 7e6fc2f50a3197d0e82d1c0e86282976c9e6c8a4 Mon Sep 17 00:00:00 2001 From: Daniel Drake Date: Mon, 7 Jan 2019 11:40:24 +0800 Subject: [PATCH 2/8] x86/kaslr: Fix incorrect i8254 outb() parameters The outb() function takes parameters value and port, in that order. Fix the parameters used in the kalsr i8254 fallback code. Fixes: 5bfce5ef55cb ("x86, kaslr: Provide randomness functions") Signed-off-by: Daniel Drake Signed-off-by: Thomas Gleixner Cc: bp@alien8.de Cc: hpa@zytor.com Cc: linux@endlessm.com Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20190107034024.15005-1-drake@endlessm.com --- arch/x86/lib/kaslr.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/lib/kaslr.c b/arch/x86/lib/kaslr.c index 79778ab200e4..a53665116458 100644 --- a/arch/x86/lib/kaslr.c +++ b/arch/x86/lib/kaslr.c @@ -36,8 +36,8 @@ static inline u16 i8254(void) u16 status, timer; do { - outb(I8254_PORT_CONTROL, - I8254_CMD_READBACK | I8254_SELECT_COUNTER0); + outb(I8254_CMD_READBACK | I8254_SELECT_COUNTER0, + I8254_PORT_CONTROL); status = inb(I8254_PORT_COUNTER0); timer = inb(I8254_PORT_COUNTER0); timer |= inb(I8254_PORT_COUNTER0) << 8; From a31e184e4f69965c99c04cc5eb8a4920e0c63737 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Wed, 2 Jan 2019 13:56:55 -0800 Subject: [PATCH 3/8] x86/pkeys: Properly copy pkey state at fork() Memory protection key behavior should be the same in a child as it was in the parent before a fork. But, there is a bug that resets the state in the child at fork instead of preserving it. The creation of new mm's is a bit convoluted. At fork(), the code does: 1. memcpy() the parent mm to initialize child 2. mm_init() to initalize some select stuff stuff 3. dup_mmap() to create true copies that memcpy() did not do right For pkeys two bits of state need to be preserved across a fork: 'execute_only_pkey' and 'pkey_allocation_map'. Those are preserved by the memcpy(), but mm_init() invokes init_new_context() which overwrites 'execute_only_pkey' and 'pkey_allocation_map' with "new" values. The author of the code erroneously believed that init_new_context is *only* called at execve()-time. But, alas, init_new_context() is used at execve() and fork(). The result is that, after a fork(), the child's pkey state ends up looking like it does after an execve(), which is totally wrong. pkeys that are already allocated can be allocated again, for instance. To fix this, add code called by dup_mmap() to copy the pkey state from parent to child explicitly. Also add a comment above init_new_context() to make it more clear to the next poor sod what this code is used for. Fixes: e8c24d3a23a ("x86/pkeys: Allocation/free syscalls") Signed-off-by: Dave Hansen Signed-off-by: Thomas Gleixner Reviewed-by: Thomas Gleixner Cc: bp@alien8.de Cc: hpa@zytor.com Cc: peterz@infradead.org Cc: mpe@ellerman.id.au Cc: will.deacon@arm.com Cc: luto@kernel.org Cc: jroedel@suse.de Cc: stable@vger.kernel.org Cc: Borislav Petkov Cc: "H. Peter Anvin" Cc: Peter Zijlstra Cc: Michael Ellerman Cc: Will Deacon Cc: Andy Lutomirski Cc: Joerg Roedel Link: https://lkml.kernel.org/r/20190102215655.7A69518C@viggo.jf.intel.com --- arch/x86/include/asm/mmu_context.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 0ca50611e8ce..19d18fae6ec6 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -178,6 +178,10 @@ static inline void switch_ldt(struct mm_struct *prev, struct mm_struct *next) void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk); +/* + * Init a new mm. Used on mm copies, like at fork() + * and on mm's that are brand-new, like at execve(). + */ static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { @@ -228,8 +232,22 @@ do { \ } while (0) #endif +static inline void arch_dup_pkeys(struct mm_struct *oldmm, + struct mm_struct *mm) +{ +#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS + if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) + return; + + /* Duplicate the oldmm pkey state in mm: */ + mm->context.pkey_allocation_map = oldmm->context.pkey_allocation_map; + mm->context.execute_only_pkey = oldmm->context.execute_only_pkey; +#endif +} + static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) { + arch_dup_pkeys(oldmm, mm); paravirt_arch_dup_mmap(oldmm, mm); return ldt_dup_context(oldmm, mm); } From e1812933b17be7814f51b6c310c5d1ced7a9a5f5 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Wed, 2 Jan 2019 13:56:57 -0800 Subject: [PATCH 4/8] x86/selftests/pkeys: Fork() to check for state being preserved There was a bug where the per-mm pkey state was not being preserved across fork() in the child. fork() is performed in the pkey selftests, but all of the pkey activity is performed in the parent. The child does not perform any actions sensitive to pkey state. To make the test more sensitive to these kinds of bugs, add a fork() where the parent exits, and execution continues in the child. To achieve this let the key exhaustion test not terminate at the first allocation failure and fork after 2*NR_PKEYS loops and continue in the child. Signed-off-by: Dave Hansen Signed-off-by: Thomas Gleixner Cc: bp@alien8.de Cc: hpa@zytor.com Cc: peterz@infradead.org Cc: mpe@ellerman.id.au Cc: will.deacon@arm.com Cc: luto@kernel.org Cc: jroedel@suse.de Cc: stable@vger.kernel.org Cc: Borislav Petkov Cc: "H. Peter Anvin" Cc: Peter Zijlstra Cc: Michael Ellerman Cc: Will Deacon Cc: Andy Lutomirski Cc: Joerg Roedel Link: https://lkml.kernel.org/r/20190102215657.585704B7@viggo.jf.intel.com --- tools/testing/selftests/x86/protection_keys.c | 41 ++++++++++++++----- 1 file changed, 31 insertions(+), 10 deletions(-) diff --git a/tools/testing/selftests/x86/protection_keys.c b/tools/testing/selftests/x86/protection_keys.c index 460b4bdf4c1e..5d546dcdbc80 100644 --- a/tools/testing/selftests/x86/protection_keys.c +++ b/tools/testing/selftests/x86/protection_keys.c @@ -1133,6 +1133,21 @@ void test_pkey_syscalls_bad_args(int *ptr, u16 pkey) pkey_assert(err); } +void become_child(void) +{ + pid_t forkret; + + forkret = fork(); + pkey_assert(forkret >= 0); + dprintf3("[%d] fork() ret: %d\n", getpid(), forkret); + + if (!forkret) { + /* in the child */ + return; + } + exit(0); +} + /* Assumes that all pkeys other than 'pkey' are unallocated */ void test_pkey_alloc_exhaust(int *ptr, u16 pkey) { @@ -1141,7 +1156,7 @@ void test_pkey_alloc_exhaust(int *ptr, u16 pkey) int nr_allocated_pkeys = 0; int i; - for (i = 0; i < NR_PKEYS*2; i++) { + for (i = 0; i < NR_PKEYS*3; i++) { int new_pkey; dprintf1("%s() alloc loop: %d\n", __func__, i); new_pkey = alloc_pkey(); @@ -1152,20 +1167,26 @@ void test_pkey_alloc_exhaust(int *ptr, u16 pkey) if ((new_pkey == -1) && (errno == ENOSPC)) { dprintf2("%s() failed to allocate pkey after %d tries\n", __func__, nr_allocated_pkeys); - break; + } else { + /* + * Ensure the number of successes never + * exceeds the number of keys supported + * in the hardware. + */ + pkey_assert(nr_allocated_pkeys < NR_PKEYS); + allocated_pkeys[nr_allocated_pkeys++] = new_pkey; } - pkey_assert(nr_allocated_pkeys < NR_PKEYS); - allocated_pkeys[nr_allocated_pkeys++] = new_pkey; + + /* + * Make sure that allocation state is properly + * preserved across fork(). + */ + if (i == NR_PKEYS*2) + become_child(); } dprintf3("%s()::%d\n", __func__, __LINE__); - /* - * ensure it did not reach the end of the loop without - * failure: - */ - pkey_assert(i < NR_PKEYS*2); - /* * There are 16 pkeys supported in hardware. Three are * allocated by the time we get here: From bf7d28c53453ea904584960de55e33e03b9d93b1 Mon Sep 17 00:00:00 2001 From: Peng Hao Date: Sat, 29 Dec 2018 14:34:12 +0800 Subject: [PATCH 5/8] x86/mm/mem_encrypt: Fix erroneous sizeof() Using sizeof(pointer) for determining the size of a memset() only works when the size of the pointer and the size of type to which it points are the same. For pte_t this is only true for 64bit and 32bit-NONPAE. On 32bit PAE systems this is wrong as the pointer size is 4 byte but the PTE entry is 8 bytes. It's actually not a real world issue as this code depends on 64bit, but it's wrong nevertheless. Use sizeof(*p) for correctness sake. Fixes: aad983913d77 ("x86/mm/encrypt: Simplify sme_populate_pgd() and sme_populate_pgd_large()") Signed-off-by: Peng Hao Signed-off-by: Thomas Gleixner Cc: Kirill A. Shutemov Cc: Tom Lendacky Cc: dave.hansen@linux.intel.com Cc: peterz@infradead.org Cc: luto@kernel.org Link: https://lkml.kernel.org/r/1546065252-97996-1-git-send-email-peng.hao2@zte.com.cn --- arch/x86/mm/mem_encrypt_identity.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c index a19ef1a416ff..4aa9b1480866 100644 --- a/arch/x86/mm/mem_encrypt_identity.c +++ b/arch/x86/mm/mem_encrypt_identity.c @@ -158,8 +158,8 @@ static void __init sme_populate_pgd(struct sme_populate_pgd_data *ppd) pmd = pmd_offset(pud, ppd->vaddr); if (pmd_none(*pmd)) { pte = ppd->pgtable_area; - memset(pte, 0, sizeof(pte) * PTRS_PER_PTE); - ppd->pgtable_area += sizeof(pte) * PTRS_PER_PTE; + memset(pte, 0, sizeof(*pte) * PTRS_PER_PTE); + ppd->pgtable_area += sizeof(*pte) * PTRS_PER_PTE; set_pmd(pmd, __pmd(PMD_FLAGS | __pa(pte))); } From 993a110319a4a60aadbd02f6defdebe048f7773b Mon Sep 17 00:00:00 2001 From: Dave Young Date: Fri, 28 Dec 2018 09:12:47 +0800 Subject: [PATCH 6/8] x86/kexec: Fix a kexec_file_load() failure Commit b6664ba42f14 ("s390, kexec_file: drop arch_kexec_mem_walk()") changed the behavior of kexec_locate_mem_hole(): it will try to allocate free memory only when kbuf.mem is initialized to zero. However, x86's kexec_file_load() implementation reuses a struct kexec_buf allocated on the stack and its kbuf.mem member gets set by each kexec_add_buffer() invocation. The second kexec_add_buffer() will reuse the same kbuf but not reinitialize kbuf.mem. Therefore, explictily reset kbuf.mem each time in order for kexec_locate_mem_hole() to locate a free memory region each time. [ bp: massage commit message. ] Fixes: b6664ba42f14 ("s390, kexec_file: drop arch_kexec_mem_walk()") Signed-off-by: Dave Young Signed-off-by: Borislav Petkov Acked-by: Baoquan He Cc: "Eric W. Biederman" Cc: "H. Peter Anvin" Cc: AKASHI Takahiro Cc: Andrew Morton Cc: Ingo Molnar Cc: Martin Schwidefsky Cc: Philipp Rudo Cc: Thomas Gleixner Cc: Vivek Goyal Cc: Yannik Sembritzki Cc: Yi Wang Cc: kexec@lists.infradead.org Cc: x86-ml Link: https://lkml.kernel.org/r/20181228011247.GA9999@dhcp-128-65.nay.redhat.com --- arch/x86/kernel/crash.c | 1 + arch/x86/kernel/kexec-bzimage64.c | 2 ++ 2 files changed, 3 insertions(+) diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index c8b07d8ea5a2..17ffc869cab8 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -470,6 +470,7 @@ int crash_load_segments(struct kimage *image) kbuf.memsz = kbuf.bufsz; kbuf.buf_align = ELF_CORE_HEADER_ALIGN; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; ret = kexec_add_buffer(&kbuf); if (ret) { vfree((void *)image->arch.elf_headers); diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index 278cd07228dd..0d5efa34f359 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -434,6 +434,7 @@ static void *bzImage64_load(struct kimage *image, char *kernel, kbuf.memsz = PAGE_ALIGN(header->init_size); kbuf.buf_align = header->kernel_alignment; kbuf.buf_min = MIN_KERNEL_LOAD_ADDR; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; ret = kexec_add_buffer(&kbuf); if (ret) goto out_free_params; @@ -448,6 +449,7 @@ static void *bzImage64_load(struct kimage *image, char *kernel, kbuf.bufsz = kbuf.memsz = initrd_len; kbuf.buf_align = PAGE_SIZE; kbuf.buf_min = MIN_INITRD_LOAD_ADDR; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; ret = kexec_add_buffer(&kbuf); if (ret) goto out_free_params; From fc24d75a7f91837d7918e40719575951820b2b8f Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Tue, 15 Jan 2019 09:58:16 -0700 Subject: [PATCH 7/8] x86/entry/64/compat: Fix stack switching for XEN PV While in the native case entry into the kernel happens on the trampoline stack, PV Xen kernels get entered with the current thread stack right away. Hence source and destination stacks are identical in that case, and special care is needed. Other than in sync_regs() the copying done on the INT80 path isn't NMI / #MC safe, as either of these events occurring in the middle of the stack copying would clobber data on the (source) stack. There is similar code in interrupt_entry() and nmi(), but there is no fixup required because those code paths are unreachable in XEN PV guests. [ tglx: Sanitized subject, changelog, Fixes tag and stable mail address. Sigh ] Fixes: 7f2590a110b8 ("x86/entry/64: Use a per-CPU trampoline stack for IDT entries") Signed-off-by: Jan Beulich Signed-off-by: Thomas Gleixner Reviewed-by: Juergen Gross Acked-by: Andy Lutomirski Cc: Peter Anvin Cc: xen-devel@lists.xenproject.org> Cc: Boris Ostrovsky Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/5C3E1128020000780020DFAD@prv1-mh.provo.novell.com --- arch/x86/entry/entry_64_compat.S | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 8eaf8952c408..39913770a44d 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -361,7 +361,8 @@ ENTRY(entry_INT80_compat) /* Need to switch before accessing the thread stack. */ SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi - movq %rsp, %rdi + /* In the Xen PV case we already run on the thread stack. */ + ALTERNATIVE "movq %rsp, %rdi", "jmp .Lint80_keep_stack", X86_FEATURE_XENPV movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp pushq 6*8(%rdi) /* regs->ss */ @@ -370,8 +371,9 @@ ENTRY(entry_INT80_compat) pushq 3*8(%rdi) /* regs->cs */ pushq 2*8(%rdi) /* regs->ip */ pushq 1*8(%rdi) /* regs->orig_ax */ - pushq (%rdi) /* pt_regs->di */ +.Lint80_keep_stack: + pushq %rsi /* pt_regs->si */ xorl %esi, %esi /* nospec si */ pushq %rdx /* pt_regs->dx */ From 625210cfa6c0c26ea422f655bf68288176f174e6 Mon Sep 17 00:00:00 2001 From: Sinan Kaya Date: Mon, 21 Jan 2019 23:19:58 +0000 Subject: [PATCH 8/8] x86/Kconfig: Select PCI_LOCKLESS_CONFIG if PCI is enabled After commit 5d32a66541c4 ("PCI/ACPI: Allow ACPI to be built without CONFIG_PCI set") dependencies on CONFIG_PCI that previously were satisfied implicitly through dependencies on CONFIG_ACPI have to be specified directly. PCI_LOCKLESS_CONFIG depends on PCI but this dependency has not been mentioned in the Kconfig so add an explicit dependency here and fix WARNING: unmet direct dependencies detected for PCI_LOCKLESS_CONFIG Depends on [n]: PCI [=n] Selected by [y]: - X86 [=y] Fixes: 5d32a66541c46 ("PCI/ACPI: Allow ACPI to be built without CONFIG_PCI set") Signed-off-by: Sinan Kaya Signed-off-by: Borislav Petkov Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Thomas Gleixner Cc: linux-acpi@vger.kernel.org Cc: x86-ml Link: https://lkml.kernel.org/r/20190121231958.28255-2-okaya@kernel.org --- arch/x86/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 4b4a7f32b68e..26387c7bf305 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -198,7 +198,7 @@ config X86 select IRQ_FORCED_THREADING select NEED_SG_DMA_LENGTH select PCI_DOMAINS if PCI - select PCI_LOCKLESS_CONFIG + select PCI_LOCKLESS_CONFIG if PCI select PERF_EVENTS select RTC_LIB select RTC_MC146818_LIB