July 2018 - Linux-stable-mirror

[PATCH 4.4.y 046/101] x86/speculation: Move firmware_restrict_branch_speculation_*() from C to CPP

by Srivatsa S. Bhat

From: Ingo Molnar <mingo(a)kernel.org> commit d72f4e29e6d84b7ec02ae93088aa459ac70e733b upstream. firmware_restrict_branch_speculation_*() recently started using preempt_enable()/disable(), but those are relatively high level primitives and cause build failures on some 32-bit builds. Since we want to keep <asm/nospec-branch.h> low level, convert them to macros to avoid header hell... Cc: David Woodhouse <dwmw(a)amazon.co.uk> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: arjan.van.de.ven(a)intel.com Cc: bp(a)alien8.de Cc: dave.hansen(a)intel.com Cc: jmattson(a)google.com Cc: karahmed(a)amazon.de Cc: kvm(a)vger.kernel.org Cc: pbonzini(a)redhat.com Cc: rkrcmar(a)redhat.com Cc: linux-kernel(a)vger.kernel.org Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Srivatsa S. Bhat <srivatsa(a)csail.mit.edu> Reviewed-by: Matt Helsley (VMware) <matt.helsley(a)gmail.com> Reviewed-by: Alexey Makhalov <amakhalov(a)vmware.com> Reviewed-by: Bo Gan <ganb(a)vmware.com> --- arch/x86/include/asm/nospec-branch.h | 26 ++++++++++++++------------ 1 file changed, 14 insertions(+), 12 deletions(-) diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 36ded24..b9dd1d9 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -214,20 +214,22 @@ static inline void indirect_branch_prediction_barrier(void) /* * With retpoline, we must use IBRS to restrict branch prediction * before calling into firmware. + * + * (Implemented as CPP macros due to header hell.) */ -static inline void firmware_restrict_branch_speculation_start(void) -{ - preempt_disable(); - alternative_msr_write(MSR_IA32_SPEC_CTRL, SPEC_CTRL_IBRS, - X86_FEATURE_USE_IBRS_FW); -} +#define firmware_restrict_branch_speculation_start() \ +do { \ + preempt_disable(); \ + alternative_msr_write(MSR_IA32_SPEC_CTRL, SPEC_CTRL_IBRS, \ + X86_FEATURE_USE_IBRS_FW); \ +} while (0) -static inline void firmware_restrict_branch_speculation_end(void) -{ - alternative_msr_write(MSR_IA32_SPEC_CTRL, 0, - X86_FEATURE_USE_IBRS_FW); - preempt_enable(); -} +#define firmware_restrict_branch_speculation_end() \ +do { \ + alternative_msr_write(MSR_IA32_SPEC_CTRL, 0, \ + X86_FEATURE_USE_IBRS_FW); \ + preempt_enable(); \ +} while (0) #endif /* __ASSEMBLY__ */

6 years, 7 months

1
0
0 0

[PATCH 4.4.y 045/101] x86/speculation: Use IBRS if available before calling into firmware

by Srivatsa S. Bhat

From: David Woodhouse <dwmw(a)amazon.co.uk> commit dd84441a797150dcc49298ec95c459a8891d8bb1 upstream. Retpoline means the kernel is safe because it has no indirect branches. But firmware isn't, so use IBRS for firmware calls if it's available. Block preemption while IBRS is set, although in practice the call sites already had to be doing that. Ignore hpwdt.c for now. It's taking spinlocks and calling into firmware code, from an NMI handler. I don't want to touch that with a bargepole. Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Reviewed-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: arjan.van.de.ven(a)intel.com Cc: bp(a)alien8.de Cc: dave.hansen(a)intel.com Cc: jmattson(a)google.com Cc: karahmed(a)amazon.de Cc: kvm(a)vger.kernel.org Cc: pbonzini(a)redhat.com Cc: rkrcmar(a)redhat.com Link: http://lkml.kernel.org/r/1519037457-7643-2-git-send-email-dwmw@amazon.co.uk Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> [ Srivatsa: Backported to 4.4.y, patching the efi_call_virt() family of functions, which are the 4.4.y-equivalents of arch_efi_call_virt_setup()/teardown() ] Signed-off-by: Srivatsa S. Bhat <srivatsa(a)csail.mit.edu> Reviewed-by: Matt Helsley (VMware) <matt.helsley(a)gmail.com> Reviewed-by: Alexey Makhalov <amakhalov(a)vmware.com> Reviewed-by: Bo Gan <ganb(a)vmware.com> --- arch/x86/include/asm/apm.h | 6 +++++ arch/x86/include/asm/cpufeatures.h | 1 + arch/x86/include/asm/efi.h | 7 ++++++ arch/x86/include/asm/nospec-branch.h | 39 ++++++++++++++++++++++++++-------- arch/x86/kernel/cpu/bugs.c | 12 ++++++++++ arch/x86/platform/efi/efi_64.c | 3 +++ 6 files changed, 58 insertions(+), 10 deletions(-) diff --git a/arch/x86/include/asm/apm.h b/arch/x86/include/asm/apm.h index 20370c6..3d1ec41 100644 --- a/arch/x86/include/asm/apm.h +++ b/arch/x86/include/asm/apm.h @@ -6,6 +6,8 @@ #ifndef _ASM_X86_MACH_DEFAULT_APM_H #define _ASM_X86_MACH_DEFAULT_APM_H +#include <asm/nospec-branch.h> + #ifdef APM_ZERO_SEGS # define APM_DO_ZERO_SEGS \ "pushl %%ds\n\t" \ @@ -31,6 +33,7 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in, * N.B. We do NOT need a cld after the BIOS call * because we always save and restore the flags. */ + firmware_restrict_branch_speculation_start(); __asm__ __volatile__(APM_DO_ZERO_SEGS "pushl %%edi\n\t" "pushl %%ebp\n\t" @@ -43,6 +46,7 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in, "=S" (*esi) : "a" (func), "b" (ebx_in), "c" (ecx_in) : "memory", "cc"); + firmware_restrict_branch_speculation_end(); } static inline u8 apm_bios_call_simple_asm(u32 func, u32 ebx_in, @@ -55,6 +59,7 @@ static inline u8 apm_bios_call_simple_asm(u32 func, u32 ebx_in, * N.B. We do NOT need a cld after the BIOS call * because we always save and restore the flags. */ + firmware_restrict_branch_speculation_start(); __asm__ __volatile__(APM_DO_ZERO_SEGS "pushl %%edi\n\t" "pushl %%ebp\n\t" @@ -67,6 +72,7 @@ static inline u8 apm_bios_call_simple_asm(u32 func, u32 ebx_in, "=S" (si) : "a" (func), "b" (ebx_in), "c" (ecx_in) : "memory", "cc"); + firmware_restrict_branch_speculation_end(); return error; } diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 782005d..bc76bf3 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -202,6 +202,7 @@ #define X86_FEATURE_KAISER ( 7*32+31) /* CONFIG_PAGE_TABLE_ISOLATION w/o nokaiser */ #define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled*/ +#define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* "" Use IBRS during runtime firmware calls */ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 0010c78..7e5a2ff 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -3,6 +3,7 @@ #include <asm/fpu/api.h> #include <asm/pgtable.h> +#include <asm/nospec-branch.h> /* * We map the EFI regions needed for runtime services non-contiguously, @@ -39,8 +40,10 @@ extern unsigned long asmlinkage efi_call_phys(void *, ...); ({ \ efi_status_t __s; \ kernel_fpu_begin(); \ + firmware_restrict_branch_speculation_start(); \ __s = ((efi_##f##_t __attribute__((regparm(0)))*) \ efi.systab->runtime->f)(args); \ + firmware_restrict_branch_speculation_end(); \ kernel_fpu_end(); \ __s; \ }) @@ -49,8 +52,10 @@ extern unsigned long asmlinkage efi_call_phys(void *, ...); #define __efi_call_virt(f, args...) \ ({ \ kernel_fpu_begin(); \ + firmware_restrict_branch_speculation_start(); \ ((efi_##f##_t __attribute__((regparm(0)))*) \ efi.systab->runtime->f)(args); \ + firmware_restrict_branch_speculation_end(); \ kernel_fpu_end(); \ }) @@ -71,7 +76,9 @@ extern u64 asmlinkage efi_call(void *fp, ...); efi_sync_low_kernel_mappings(); \ preempt_disable(); \ __kernel_fpu_begin(); \ + firmware_restrict_branch_speculation_start(); \ __s = efi_call((void *)efi.systab->runtime->f, __VA_ARGS__); \ + firmware_restrict_branch_speculation_end(); \ __kernel_fpu_end(); \ preempt_enable(); \ __s; \ diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index bca2860..36ded24 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -195,17 +195,38 @@ static inline void vmexit_fill_RSB(void) #endif } +#define alternative_msr_write(_msr, _val, _feature) \ + asm volatile(ALTERNATIVE("", \ + "movl %[msr], %%ecx\n\t" \ + "movl %[val], %%eax\n\t" \ + "movl $0, %%edx\n\t" \ + "wrmsr", \ + _feature) \ + : : [msr] "i" (_msr), [val] "i" (_val) \ + : "eax", "ecx", "edx", "memory") + static inline void indirect_branch_prediction_barrier(void) { - asm volatile(ALTERNATIVE("", - "movl %[msr], %%ecx\n\t" - "movl %[val], %%eax\n\t" - "movl $0, %%edx\n\t" - "wrmsr", - X86_FEATURE_USE_IBPB) - : : [msr] "i" (MSR_IA32_PRED_CMD), - [val] "i" (PRED_CMD_IBPB) - : "eax", "ecx", "edx", "memory"); + alternative_msr_write(MSR_IA32_PRED_CMD, PRED_CMD_IBPB, + X86_FEATURE_USE_IBPB); +} + +/* + * With retpoline, we must use IBRS to restrict branch prediction + * before calling into firmware. + */ +static inline void firmware_restrict_branch_speculation_start(void) +{ + preempt_disable(); + alternative_msr_write(MSR_IA32_SPEC_CTRL, SPEC_CTRL_IBRS, + X86_FEATURE_USE_IBRS_FW); +} + +static inline void firmware_restrict_branch_speculation_end(void) +{ + alternative_msr_write(MSR_IA32_SPEC_CTRL, 0, + X86_FEATURE_USE_IBRS_FW); + preempt_enable(); } #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index fea368d..b294fdc 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -300,6 +300,15 @@ retpoline_auto: setup_force_cpu_cap(X86_FEATURE_USE_IBPB); pr_info("Spectre v2 mitigation: Enabling Indirect Branch Prediction Barrier\n"); } + + /* + * Retpoline means the kernel is safe because it has no indirect + * branches. But firmware isn't, so use IBRS to protect that. + */ + if (boot_cpu_has(X86_FEATURE_IBRS)) { + setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW); + pr_info("Enabling Restricted Speculation for firmware calls\n"); + } } #undef pr_fmt @@ -326,8 +335,9 @@ ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, c if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) return sprintf(buf, "Not affected\n"); - return sprintf(buf, "%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], + return sprintf(buf, "%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "", + boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "", spectre_v2_module_string()); } #endif diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index a0ac0f9..f5a8cd9 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -40,6 +40,7 @@ #include <asm/fixmap.h> #include <asm/realmode.h> #include <asm/time.h> +#include <asm/nospec-branch.h> /* * We allocate runtime services regions bottom-up, starting from -4G, i.e. @@ -347,6 +348,7 @@ extern efi_status_t efi64_thunk(u32, ...); \ efi_sync_low_kernel_mappings(); \ local_irq_save(flags); \ + firmware_restrict_branch_speculation_start(); \ \ efi_scratch.prev_cr3 = read_cr3(); \ write_cr3((unsigned long)efi_scratch.efi_pgt); \ @@ -357,6 +359,7 @@ extern efi_status_t efi64_thunk(u32, ...); \ write_cr3(efi_scratch.prev_cr3); \ __flush_tlb_all(); \ + firmware_restrict_branch_speculation_end(); \ local_irq_restore(flags); \ \ __s; \

6 years, 7 months

1
0
0 0

[PATCH 4.4.y 044/101] x86/spectre_v2: Don't check microcode versions when running under hypervisors

by Srivatsa S. Bhat

From: Konrad Rzeszutek Wilk <konrad.wilk(a)oracle.com> commit 36268223c1e9981d6cfc33aff8520b3bde4b8114 upstream. As: 1) It's known that hypervisors lie about the environment anyhow (host mismatch) 2) Even if the hypervisor (Xen, KVM, VMWare, etc) provided a valid "correct" value, it all gets to be very murky when migration happens (do you provide the "new" microcode of the machine?). And in reality the cloud vendors are the ones that should make sure that the microcode that is running is correct and we should just sing lalalala and trust them. Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk(a)oracle.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Reviewed-by: Paolo Bonzini <pbonzini(a)redhat.com> Cc: Wanpeng Li <kernellwp(a)gmail.com> Cc: kvm <kvm(a)vger.kernel.org> Cc: Krčmář <rkrcmar(a)redhat.com> Cc: Borislav Petkov <bp(a)alien8.de> CC: "H. Peter Anvin" <hpa(a)zytor.com> CC: stable(a)vger.kernel.org Link: https://lkml.kernel.org/r/20180226213019.GE9497@char.us.oracle.com Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Srivatsa S. Bhat <srivatsa(a)csail.mit.edu> Reviewed-by: Matt Helsley (VMware) <matt.helsley(a)gmail.com> Reviewed-by: Alexey Makhalov <amakhalov(a)vmware.com> Reviewed-by: Bo Gan <ganb(a)vmware.com> --- arch/x86/kernel/cpu/intel.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index b69d258..dcc0349 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -68,6 +68,13 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c) { int i; + /* + * We know that the hypervisor lie to us on the microcode version so + * we may as well hope that it is running the correct version. + */ + if (cpu_has(c, X86_FEATURE_HYPERVISOR)) + return false; + for (i = 0; i < ARRAY_SIZE(spectre_bad_microcodes); i++) { if (c->x86_model == spectre_bad_microcodes[i].model && c->x86_mask == spectre_bad_microcodes[i].stepping)

6 years, 7 months

1
0
0 0

[PATCH 4.4.y 043/101] x86/speculation: Use Indirect Branch Prediction Barrier in context switch

by Srivatsa S. Bhat

From: Tim Chen <tim.c.chen(a)linux.intel.com> commit 18bf3c3ea8ece8f03b6fc58508f2dfd23c7711c7 upstream. Flush indirect branches when switching into a process that marked itself non dumpable. This protects high value processes like gpg better, without having too high performance overhead. If done naïvely, we could switch to a kernel idle thread and then back to the original process, such as: process A -> idle -> process A In such scenario, we do not have to do IBPB here even though the process is non-dumpable, as we are switching back to the same process after a hiatus. To avoid the redundant IBPB, which is expensive, we track the last mm user context ID. The cost is to have an extra u64 mm context id to track the last mm we were using before switching to the init_mm used by idle. Avoiding the extra IBPB is probably worth the extra memory for this common scenario. For those cases where tlb_defer_switch_to_init_mm() returns true (non PCID), lazy tlb will defer switch to init_mm, so we will not be changing the mm for the process A -> idle -> process A switch. So IBPB will be skipped for this case. Thanks to the reviewers and Andy Lutomirski for the suggestion of using ctx_id which got rid of the problem of mm pointer recycling. Signed-off-by: Tim Chen <tim.c.chen(a)linux.intel.com> Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: ak(a)linux.intel.com Cc: karahmed(a)amazon.de Cc: arjan(a)linux.intel.com Cc: torvalds(a)linux-foundation.org Cc: linux(a)dominikbrodowski.net Cc: peterz(a)infradead.org Cc: bp(a)alien8.de Cc: luto(a)kernel.org Cc: pbonzini(a)redhat.com Link: https://lkml.kernel.org/r/1517263487-3708-1-git-send-email-dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Srivatsa S. Bhat <srivatsa(a)csail.mit.edu> Reviewed-by: Matt Helsley (VMware) <matt.helsley(a)gmail.com> Reviewed-by: Alexey Makhalov <amakhalov(a)vmware.com> Reviewed-by: Bo Gan <ganb(a)vmware.com> --- arch/x86/include/asm/tlbflush.h | 2 ++ arch/x86/mm/tlb.c | 31 +++++++++++++++++++++++++++++++ 2 files changed, 33 insertions(+) diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index e2a89d2..8ce07db 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -68,6 +68,8 @@ static inline void invpcid_flush_all_nonglobals(void) struct tlb_state { struct mm_struct *active_mm; int state; + /* last user mm's ctx id */ + u64 last_ctx_id; /* * Access to this CR4 shadow and to H/W CR4 is protected by diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index efec198..6d683bb 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -10,6 +10,7 @@ #include <asm/tlbflush.h> #include <asm/mmu_context.h> +#include <asm/nospec-branch.h> #include <asm/cache.h> #include <asm/apic.h> #include <asm/uv/uv.h> @@ -106,6 +107,36 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, unsigned cpu = smp_processor_id(); if (likely(prev != next)) { + u64 last_ctx_id = this_cpu_read(cpu_tlbstate.last_ctx_id); + + /* + * Avoid user/user BTB poisoning by flushing the branch + * predictor when switching between processes. This stops + * one process from doing Spectre-v2 attacks on another. + * + * As an optimization, flush indirect branches only when + * switching into processes that disable dumping. This + * protects high value processes like gpg, without having + * too high performance overhead. IBPB is *expensive*! + * + * This will not flush branches when switching into kernel + * threads. It will also not flush if we switch to idle + * thread and back to the same process. It will flush if we + * switch to a different non-dumpable process. + */ + if (tsk && tsk->mm && + tsk->mm->context.ctx_id != last_ctx_id && + get_dumpable(tsk->mm) != SUID_DUMP_USER) + indirect_branch_prediction_barrier(); + + /* + * Record last user mm's context id, so we can avoid + * flushing branch buffer with IBPB if we switch back + * to the same user. + */ + if (next != &init_mm) + this_cpu_write(cpu_tlbstate.last_ctx_id, next->context.ctx_id); + this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK); this_cpu_write(cpu_tlbstate.active_mm, next); cpumask_set_cpu(cpu, mm_cpumask(next));

6 years, 7 months

1
0
0 0

[PATCH 4.4.y 042/101] x86/mm: Give each mm TLB flush generation a unique ID

by Srivatsa S. Bhat

From: Andy Lutomirski <luto(a)kernel.org> commit f39681ed0f48498b80455095376f11535feea332 upstream. This adds two new variables to mmu_context_t: ctx_id and tlb_gen. ctx_id uniquely identifies the mm_struct and will never be reused. For a given mm_struct (and hence ctx_id), tlb_gen is a monotonic count of the number of times that a TLB flush has been requested. The pair (ctx_id, tlb_gen) can be used as an identifier for TLB flush actions and will be used in subsequent patches to reliably determine whether all needed TLB flushes have occurred on a given CPU. This patch is split out for ease of review. By itself, it has no real effect other than creating and updating the new variables. Signed-off-by: Andy Lutomirski <luto(a)kernel.org> Reviewed-by: Nadav Amit <nadav.amit(a)gmail.com> Reviewed-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: Andrew Morton <akpm(a)linux-foundation.org> Cc: Arjan van de Ven <arjan(a)linux.intel.com> Cc: Borislav Petkov <bp(a)alien8.de> Cc: Dave Hansen <dave.hansen(a)intel.com> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Mel Gorman <mgorman(a)suse.de> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Rik van Riel <riel(a)redhat.com> Cc: linux-mm(a)kvack.org Link: http://lkml.kernel.org/r/413a91c24dab3ed0caa5f4e4d017d87b0857f920.149875120… Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: Tim Chen <tim.c.chen(a)linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Srivatsa S. Bhat <srivatsa(a)csail.mit.edu> Reviewed-by: Matt Helsley (VMware) <matt.helsley(a)gmail.com> Reviewed-by: Alexey Makhalov <amakhalov(a)vmware.com> Reviewed-by: Bo Gan <ganb(a)vmware.com> --- arch/x86/include/asm/mmu.h | 15 +++++++++++++-- arch/x86/include/asm/mmu_context.h | 4 ++++ arch/x86/mm/tlb.c | 2 ++ 3 files changed, 19 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h index 7680b76..3359dfe 100644 --- a/arch/x86/include/asm/mmu.h +++ b/arch/x86/include/asm/mmu.h @@ -3,12 +3,18 @@ #include <linux/spinlock.h> #include <linux/mutex.h> +#include <linux/atomic.h> /* - * The x86 doesn't have a mmu context, but - * we put the segment information here. + * x86 has arch-specific MMU state beyond what lives in mm_struct. */ typedef struct { + /* + * ctx_id uniquely identifies this mm_struct. A ctx_id will never + * be reused, and zero is not a valid ctx_id. + */ + u64 ctx_id; + #ifdef CONFIG_MODIFY_LDT_SYSCALL struct ldt_struct *ldt; #endif @@ -24,6 +30,11 @@ typedef struct { atomic_t perf_rdpmc_allowed; /* nonzero if rdpmc is allowed */ } mm_context_t; +#define INIT_MM_CONTEXT(mm) \ + .context = { \ + .ctx_id = 1, \ + } + void leave_mm(int cpu); #endif /* _ASM_X86_MMU_H */ diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 1c4794f..effc127 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -11,6 +11,9 @@ #include <asm/tlbflush.h> #include <asm/paravirt.h> #include <asm/mpx.h> + +extern atomic64_t last_mm_ctx_id; + #ifndef CONFIG_PARAVIRT static inline void paravirt_activate_mm(struct mm_struct *prev, struct mm_struct *next) @@ -105,6 +108,7 @@ static inline 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) { + mm->context.ctx_id = atomic64_inc_return(&last_mm_ctx_id); init_new_context_ldt(tsk, mm); return 0; } diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 7cad01af..efec198 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -29,6 +29,8 @@ * Implement flush IPI by CALL_FUNCTION_VECTOR, Alex Shi */ +atomic64_t last_mm_ctx_id = ATOMIC64_INIT(1); + struct flush_tlb_info { struct mm_struct *flush_mm; unsigned long flush_start;

6 years, 7 months

1
0
0 0

[PATCH 4.4.y 041/101] x86/mm: Factor out LDT init from context init

by Srivatsa S. Bhat

From: Dave Hansen <dave.hansen(a)linux.intel.com> commit 39a0526fb3f7d93433d146304278477eb463f8af upstream The arch-specific mm_context_t is a great place to put protection-key allocation state. But, we need to initialize the allocation state because pkey 0 is always "allocated". All of the runtime initialization of mm_context_t is done in *_ldt() manipulation functions. This renames the existing LDT functions like this: init_new_context() -> init_new_context_ldt() destroy_context() -> destroy_context_ldt() and makes init_new_context() and destroy_context() available for generic use. Signed-off-by: Dave Hansen <dave.hansen(a)linux.intel.com> Reviewed-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: Andrew Morton <akpm(a)linux-foundation.org> Cc: Andy Lutomirski <luto(a)amacapital.net> Cc: Borislav Petkov <bp(a)alien8.de> Cc: Brian Gerst <brgerst(a)gmail.com> Cc: Dave Hansen <dave(a)sr71.net> Cc: Denys Vlasenko <dvlasenk(a)redhat.com> Cc: H. Peter Anvin <hpa(a)zytor.com> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Rik van Riel <riel(a)redhat.com> Cc: linux-mm(a)kvack.org Link: http://lkml.kernel.org/r/20160212210234.DB34FCC5@viggo.jf.intel.com Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: Srivatsa S. Bhat <srivatsa(a)csail.mit.edu> Reviewed-by: Matt Helsley (VMware) <matt.helsley(a)gmail.com> Reviewed-by: Alexey Makhalov <amakhalov(a)vmware.com> Reviewed-by: Bo Gan <ganb(a)vmware.com> --- arch/x86/include/asm/mmu_context.h | 21 ++++++++++++++++----- arch/x86/kernel/ldt.c | 4 ++-- 2 files changed, 18 insertions(+), 7 deletions(-) diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 9bfc5fd..1c4794f 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -52,15 +52,15 @@ struct ldt_struct { /* * Used for LDT copy/destruction. */ -int init_new_context(struct task_struct *tsk, struct mm_struct *mm); -void destroy_context(struct mm_struct *mm); +int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm); +void destroy_context_ldt(struct mm_struct *mm); #else /* CONFIG_MODIFY_LDT_SYSCALL */ -static inline int init_new_context(struct task_struct *tsk, - struct mm_struct *mm) +static inline int init_new_context_ldt(struct task_struct *tsk, + struct mm_struct *mm) { return 0; } -static inline void destroy_context(struct mm_struct *mm) {} +static inline void destroy_context_ldt(struct mm_struct *mm) {} #endif static inline void load_mm_ldt(struct mm_struct *mm) @@ -102,6 +102,17 @@ static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) this_cpu_write(cpu_tlbstate.state, TLBSTATE_LAZY); } +static inline int init_new_context(struct task_struct *tsk, + struct mm_struct *mm) +{ + init_new_context_ldt(tsk, mm); + return 0; +} +static inline void destroy_context(struct mm_struct *mm) +{ + destroy_context_ldt(mm); +} + extern void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk); diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index bc42936..8bc68cf 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -119,7 +119,7 @@ static void free_ldt_struct(struct ldt_struct *ldt) * we do not have to muck with descriptors here, that is * done in switch_mm() as needed. */ -int init_new_context(struct task_struct *tsk, struct mm_struct *mm) +int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm) { struct ldt_struct *new_ldt; struct mm_struct *old_mm; @@ -160,7 +160,7 @@ out_unlock: * * 64bit: Don't touch the LDT register - we're already in the next thread. */ -void destroy_context(struct mm_struct *mm) +void destroy_context_ldt(struct mm_struct *mm) { free_ldt_struct(mm->context.ldt); mm->context.ldt = NULL;

6 years, 7 months

1
0
0 0

[PATCH 4.4.y 040/101] x86/xen: Zero MSR_IA32_SPEC_CTRL before suspend

by Srivatsa S. Bhat

From: Juergen Gross <jgross(a)suse.com> commit 71c208dd54ab971036d83ff6d9837bae4976e623 upstream. Older Xen versions (4.5 and before) might have problems migrating pv guests with MSR_IA32_SPEC_CTRL having a non-zero value. So before suspending zero that MSR and restore it after being resumed. Signed-off-by: Juergen Gross <jgross(a)suse.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Reviewed-by: Jan Beulich <jbeulich(a)suse.com> Cc: stable(a)vger.kernel.org Cc: xen-devel(a)lists.xenproject.org Cc: boris.ostrovsky(a)oracle.com Link: https://lkml.kernel.org/r/20180226140818.4849-1-jgross@suse.com Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Srivatsa S. Bhat <srivatsa(a)csail.mit.edu> Reviewed-by: Matt Helsley (VMware) <matt.helsley(a)gmail.com> Reviewed-by: Alexey Makhalov <amakhalov(a)vmware.com> Reviewed-by: Bo Gan <ganb(a)vmware.com> --- arch/x86/xen/suspend.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index 7f664c4..4ecd0de 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -1,11 +1,14 @@ #include <linux/types.h> #include <linux/tick.h> +#include <linux/percpu-defs.h> #include <xen/xen.h> #include <xen/interface/xen.h> #include <xen/grant_table.h> #include <xen/events.h> +#include <asm/cpufeatures.h> +#include <asm/msr-index.h> #include <asm/xen/hypercall.h> #include <asm/xen/page.h> #include <asm/fixmap.h> @@ -68,6 +71,8 @@ static void xen_pv_post_suspend(int suspend_cancelled) xen_mm_unpin_all(); } +static DEFINE_PER_CPU(u64, spec_ctrl); + void xen_arch_pre_suspend(void) { if (xen_pv_domain()) @@ -84,6 +89,9 @@ void xen_arch_post_suspend(int cancelled) static void xen_vcpu_notify_restore(void *data) { + if (xen_pv_domain() && boot_cpu_has(X86_FEATURE_SPEC_CTRL)) + wrmsrl(MSR_IA32_SPEC_CTRL, this_cpu_read(spec_ctrl)); + /* Boot processor notified via generic timekeeping_resume() */ if (smp_processor_id() == 0) return; @@ -93,7 +101,15 @@ static void xen_vcpu_notify_restore(void *data) static void xen_vcpu_notify_suspend(void *data) { + u64 tmp; + tick_suspend_local(); + + if (xen_pv_domain() && boot_cpu_has(X86_FEATURE_SPEC_CTRL)) { + rdmsrl(MSR_IA32_SPEC_CTRL, tmp); + this_cpu_write(spec_ctrl, tmp); + wrmsrl(MSR_IA32_SPEC_CTRL, 0); + } } void xen_arch_resume(void)

6 years, 7 months

1
0
0 0

[PATCH 4.4.y 039/101] x86/speculation: Add <asm/msr-index.h> dependency

by Srivatsa S. Bhat

From: Peter Zijlstra <peterz(a)infradead.org> commit ea00f301285ea2f07393678cd2b6057878320c9d upstream. Joe Konno reported a compile failure resulting from using an MSR without inclusion of <asm/msr-index.h>, and while the current code builds fine (by accident) this needs fixing for future patches. Reported-by: Joe Konno <joe.konno(a)linux.intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: arjan(a)linux.intel.com Cc: bp(a)alien8.de Cc: dan.j.williams(a)intel.com Cc: dave.hansen(a)linux.intel.com Cc: dwmw2(a)infradead.org Cc: dwmw(a)amazon.co.uk Cc: gregkh(a)linuxfoundation.org Cc: hpa(a)zytor.com Cc: jpoimboe(a)redhat.com Cc: linux-tip-commits(a)vger.kernel.org Cc: luto(a)kernel.org Fixes: 20ffa1caecca ("x86/speculation: Add basic IBPB (Indirect Branch Prediction Barrier) support") Link: http://lkml.kernel.org/r/20180213132819.GJ25201@hirez.programming.kicks-ass… Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Srivatsa S. Bhat <srivatsa(a)csail.mit.edu> Reviewed-by: Matt Helsley (VMware) <matt.helsley(a)gmail.com> Reviewed-by: Alexey Makhalov <amakhalov(a)vmware.com> Reviewed-by: Bo Gan <ganb(a)vmware.com> --- arch/x86/include/asm/nospec-branch.h | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 8dcecb9..bca2860 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -6,6 +6,7 @@ #include <asm/alternative.h> #include <asm/alternative-asm.h> #include <asm/cpufeatures.h> +#include <asm/msr-index.h> /* * Fill the CPU return stack buffer.

6 years, 7 months

1
0
0 0

[PATCH 4.4.y 038/101] x86/speculation: Fix up array_index_nospec_mask() asm constraint

by Srivatsa S. Bhat

From: Dan Williams <dan.j.williams(a)intel.com> commit be3233fbfcb8f5acb6e3bcd0895c3ef9e100d470 upstream. Allow the compiler to handle @size as an immediate value or memory directly rather than allocating a register. Reported-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Dan Williams <dan.j.williams(a)intel.com> Cc: Andy Lutomirski <luto(a)kernel.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Link: http://lkml.kernel.org/r/151797010204.1289.1510000292250184993.stgit@dwilli… Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Srivatsa S. Bhat <srivatsa(a)csail.mit.edu> Reviewed-by: Matt Helsley (VMware) <matt.helsley(a)gmail.com> Reviewed-by: Alexey Makhalov <amakhalov(a)vmware.com> Reviewed-by: Bo Gan <ganb(a)vmware.com> --- arch/x86/include/asm/barrier.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index e3a6f66..7f5dcb6 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -40,7 +40,7 @@ static inline unsigned long array_index_mask_nospec(unsigned long index, asm volatile ("cmp %1,%2; sbb %0,%0;" :"=r" (mask) - :"r"(size),"r" (index) + :"g"(size),"r" (index) :"cc"); return mask; }

6 years, 7 months

1
0
0 0

[PATCH 4.4.y 037/101] x86/speculation: Clean up various Spectre related details

by Srivatsa S. Bhat

From: Ingo Molnar <mingo(a)kernel.org> commit 21e433bdb95bdf3aa48226fd3d33af608437f293 upstream. Harmonize all the Spectre messages so that a: dmesg | grep -i spectre ... gives us most Spectre related kernel boot messages. Also fix a few other details: - clarify a comment about firmware speculation control - s/KPTI/PTI - remove various line-breaks that made the code uglier Acked-by: David Woodhouse <dwmw(a)amazon.co.uk> Cc: Andy Lutomirski <luto(a)kernel.org> Cc: Arjan van de Ven <arjan(a)linux.intel.com> Cc: Borislav Petkov <bp(a)alien8.de> Cc: Dan Williams <dan.j.williams(a)intel.com> Cc: Dave Hansen <dave.hansen(a)linux.intel.com> Cc: David Woodhouse <dwmw2(a)infradead.org> Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: Josh Poimboeuf <jpoimboe(a)redhat.com> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: linux-kernel(a)vger.kernel.org Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Srivatsa S. Bhat <srivatsa(a)csail.mit.edu> Reviewed-by: Matt Helsley (VMware) <matt.helsley(a)gmail.com> Reviewed-by: Alexey Makhalov <amakhalov(a)vmware.com> Reviewed-by: Bo Gan <ganb(a)vmware.com> --- arch/x86/kernel/cpu/bugs.c | 25 ++++++++++--------------- 1 file changed, 10 insertions(+), 15 deletions(-) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 1968baf..fea368d 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -162,8 +162,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) if (cmdline_find_option_bool(boot_command_line, "nospectre_v2")) return SPECTRE_V2_CMD_NONE; else { - ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, - sizeof(arg)); + ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, sizeof(arg)); if (ret < 0) return SPECTRE_V2_CMD_AUTO; @@ -184,8 +183,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) cmd == SPECTRE_V2_CMD_RETPOLINE_AMD || cmd == SPECTRE_V2_CMD_RETPOLINE_GENERIC) && !IS_ENABLED(CONFIG_RETPOLINE)) { - pr_err("%s selected but not compiled in. Switching to AUTO select\n", - mitigation_options[i].option); + pr_err("%s selected but not compiled in. Switching to AUTO select\n", mitigation_options[i].option); return SPECTRE_V2_CMD_AUTO; } @@ -255,14 +253,14 @@ static void __init spectre_v2_select_mitigation(void) goto retpoline_auto; break; } - pr_err("kernel not compiled with retpoline; no mitigation available!"); + pr_err("Spectre mitigation: kernel not compiled with retpoline; no mitigation available!"); return; retpoline_auto: if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { retpoline_amd: if (!boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) { - pr_err("LFENCE not serializing. Switching to generic retpoline\n"); + pr_err("Spectre mitigation: LFENCE not serializing, switching to generic retpoline\n"); goto retpoline_generic; } mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_AMD : @@ -280,7 +278,7 @@ retpoline_auto: pr_info("%s\n", spectre_v2_strings[mode]); /* - * If neither SMEP or KPTI are available, there is a risk of + * If neither SMEP nor PTI are available, there is a risk of * hitting userspace addresses in the RSB after a context switch * from a shallow call stack to a deeper one. To prevent this fill * the entire RSB, even when using IBRS. @@ -294,21 +292,20 @@ retpoline_auto: if ((!boot_cpu_has(X86_FEATURE_KAISER) && !boot_cpu_has(X86_FEATURE_SMEP)) || is_skylake_era()) { setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW); - pr_info("Filling RSB on context switch\n"); + pr_info("Spectre v2 mitigation: Filling RSB on context switch\n"); } /* Initialize Indirect Branch Prediction Barrier if supported */ if (boot_cpu_has(X86_FEATURE_IBPB)) { setup_force_cpu_cap(X86_FEATURE_USE_IBPB); - pr_info("Enabling Indirect Branch Prediction Barrier\n"); + pr_info("Spectre v2 mitigation: Enabling Indirect Branch Prediction Barrier\n"); } } #undef pr_fmt #ifdef CONFIG_SYSFS -ssize_t cpu_show_meltdown(struct device *dev, - struct device_attribute *attr, char *buf) +ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) { if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) return sprintf(buf, "Not affected\n"); @@ -317,16 +314,14 @@ ssize_t cpu_show_meltdown(struct device *dev, return sprintf(buf, "Vulnerable\n"); } -ssize_t cpu_show_spectre_v1(struct device *dev, - struct device_attribute *attr, char *buf) +ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, char *buf) { if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1)) return sprintf(buf, "Not affected\n"); return sprintf(buf, "Mitigation: __user pointer sanitization\n"); } -ssize_t cpu_show_spectre_v2(struct device *dev, - struct device_attribute *attr, char *buf) +ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, char *buf) { if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) return sprintf(buf, "Not affected\n");

6 years, 7 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror July 2018