diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2021-08-31 01:00:33 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2021-08-31 01:00:33 +0300 |
commit | 0a096f240aa1992ddac65f8e704f7b0c0795fe1c (patch) | |
tree | 04c64aca17b94b0862214e09784fc23b413df578 /arch | |
parent | 7d6e3fa87e732ec1e7761bf325c0907685c8571b (diff) | |
parent | b7fe54f6c2d437082dcbecfbd832f38edd9caaf4 (diff) | |
download | linux-0a096f240aa1992ddac65f8e704f7b0c0795fe1c.tar.xz |
Merge tag 'x86-cpu-2021-08-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 cache flush updates from Thomas Gleixner:
"A reworked version of the opt-in L1D flush mechanism.
This is a stop gap for potential future speculation related hardware
vulnerabilities and a mechanism for truly security paranoid
applications.
It allows a task to request that the L1D cache is flushed when the
kernel switches to a different mm. This can be requested via prctl().
Changes vs the previous versions:
- Get rid of the software flush fallback
- Make the handling consistent with other mitigations
- Kill the task when it ends up on a SMT enabled core which defeats
the purpose of L1D flushing obviously"
* tag 'x86-cpu-2021-08-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
Documentation: Add L1D flushing Documentation
x86, prctl: Hook L1D flushing in via prctl
x86/mm: Prepare for opt-in based L1D flush in switch_mm()
x86/process: Make room for TIF_SPEC_L1D_FLUSH
sched: Add task_work callback for paranoid L1D flush
x86/mm: Refactor cond_ibpb() to support other use cases
x86/smp: Add a per-cpu view of SMT state
Diffstat (limited to 'arch')
-rw-r--r-- | arch/Kconfig | 3 | ||||
-rw-r--r-- | arch/x86/Kconfig | 1 | ||||
-rw-r--r-- | arch/x86/include/asm/nospec-branch.h | 2 | ||||
-rw-r--r-- | arch/x86/include/asm/processor.h | 2 | ||||
-rw-r--r-- | arch/x86/include/asm/thread_info.h | 6 | ||||
-rw-r--r-- | arch/x86/include/asm/tlbflush.h | 2 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/bugs.c | 70 | ||||
-rw-r--r-- | arch/x86/kernel/smpboot.c | 10 | ||||
-rw-r--r-- | arch/x86/mm/tlb.c | 107 |
9 files changed, 175 insertions, 28 deletions
diff --git a/arch/Kconfig b/arch/Kconfig index 129df498a8e1..98db63496bab 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -1282,6 +1282,9 @@ config ARCH_SPLIT_ARG64 config ARCH_HAS_ELFCORE_COMPAT bool +config ARCH_HAS_PARANOID_L1D_FLUSH + bool + source "kernel/gcov/Kconfig" source "scripts/gcc-plugins/Kconfig" diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 88fb922c23a0..421fa9e38c60 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -119,6 +119,7 @@ config X86 select ARCH_WANT_HUGE_PMD_SHARE select ARCH_WANT_LD_ORPHAN_WARN select ARCH_WANTS_THP_SWAP if X86_64 + select ARCH_HAS_PARANOID_L1D_FLUSH select BUILDTIME_TABLE_SORT select CLKEVT_I8253 select CLOCKSOURCE_VALIDATE_LAST_CYCLE diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 3ad8c6d3cbb3..ec2d5c8c6694 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -252,6 +252,8 @@ DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb); DECLARE_STATIC_KEY_FALSE(mds_user_clear); DECLARE_STATIC_KEY_FALSE(mds_idle_clear); +DECLARE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush); + #include <asm/segment.h> /** diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 33dd1575104e..9ad2acaaae9b 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -136,6 +136,8 @@ struct cpuinfo_x86 { u16 logical_die_id; /* Index into per_cpu list: */ u16 cpu_index; + /* Is SMT active on this core? */ + bool smt_active; u32 microcode; /* Address space bits used by the cache internally */ u8 x86_cache_bits; diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index de406d93b515..cf132663c219 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -81,7 +81,7 @@ struct thread_info { #define TIF_SINGLESTEP 4 /* reenable singlestep on user return*/ #define TIF_SSBD 5 /* Speculative store bypass disable */ #define TIF_SPEC_IB 9 /* Indirect branch speculation mitigation */ -#define TIF_SPEC_FORCE_UPDATE 10 /* Force speculation MSR update in context switch */ +#define TIF_SPEC_L1D_FLUSH 10 /* Flush L1D on mm switches (processes) */ #define TIF_USER_RETURN_NOTIFY 11 /* notify kernel of userspace return */ #define TIF_UPROBE 12 /* breakpointed or singlestepping */ #define TIF_PATCH_PENDING 13 /* pending live patching update */ @@ -93,6 +93,7 @@ struct thread_info { #define TIF_MEMDIE 20 /* is terminating due to OOM killer */ #define TIF_POLLING_NRFLAG 21 /* idle is polling for TIF_NEED_RESCHED */ #define TIF_IO_BITMAP 22 /* uses I/O bitmap */ +#define TIF_SPEC_FORCE_UPDATE 23 /* Force speculation MSR update in context switch */ #define TIF_FORCED_TF 24 /* true if TF in eflags artificially */ #define TIF_BLOCKSTEP 25 /* set when we want DEBUGCTLMSR_BTF */ #define TIF_LAZY_MMU_UPDATES 27 /* task is updating the mmu lazily */ @@ -104,7 +105,7 @@ struct thread_info { #define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP) #define _TIF_SSBD (1 << TIF_SSBD) #define _TIF_SPEC_IB (1 << TIF_SPEC_IB) -#define _TIF_SPEC_FORCE_UPDATE (1 << TIF_SPEC_FORCE_UPDATE) +#define _TIF_SPEC_L1D_FLUSH (1 << TIF_SPEC_L1D_FLUSH) #define _TIF_USER_RETURN_NOTIFY (1 << TIF_USER_RETURN_NOTIFY) #define _TIF_UPROBE (1 << TIF_UPROBE) #define _TIF_PATCH_PENDING (1 << TIF_PATCH_PENDING) @@ -115,6 +116,7 @@ struct thread_info { #define _TIF_SLD (1 << TIF_SLD) #define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG) #define _TIF_IO_BITMAP (1 << TIF_IO_BITMAP) +#define _TIF_SPEC_FORCE_UPDATE (1 << TIF_SPEC_FORCE_UPDATE) #define _TIF_FORCED_TF (1 << TIF_FORCED_TF) #define _TIF_BLOCKSTEP (1 << TIF_BLOCKSTEP) #define _TIF_LAZY_MMU_UPDATES (1 << TIF_LAZY_MMU_UPDATES) diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index fa952eadbc2e..b587a9ee9cb2 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -83,7 +83,7 @@ struct tlb_state { /* Last user mm for optimizing IBPB */ union { struct mm_struct *last_user_mm; - unsigned long last_user_mm_ibpb; + unsigned long last_user_mm_spec; }; u16 loaded_mm_asid; diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index d41b70fe4918..ecfca3bbcd96 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -43,6 +43,7 @@ static void __init mds_select_mitigation(void); static void __init mds_print_mitigation(void); static void __init taa_select_mitigation(void); static void __init srbds_select_mitigation(void); +static void __init l1d_flush_select_mitigation(void); /* The base value of the SPEC_CTRL MSR that always has to be preserved. */ u64 x86_spec_ctrl_base; @@ -76,6 +77,13 @@ EXPORT_SYMBOL_GPL(mds_user_clear); DEFINE_STATIC_KEY_FALSE(mds_idle_clear); EXPORT_SYMBOL_GPL(mds_idle_clear); +/* + * Controls whether l1d flush based mitigations are enabled, + * based on hw features and admin setting via boot parameter + * defaults to false + */ +DEFINE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush); + void __init check_bugs(void) { identify_boot_cpu(); @@ -111,6 +119,7 @@ void __init check_bugs(void) mds_select_mitigation(); taa_select_mitigation(); srbds_select_mitigation(); + l1d_flush_select_mitigation(); /* * As MDS and TAA mitigations are inter-related, print MDS @@ -492,6 +501,34 @@ static int __init srbds_parse_cmdline(char *str) early_param("srbds", srbds_parse_cmdline); #undef pr_fmt +#define pr_fmt(fmt) "L1D Flush : " fmt + +enum l1d_flush_mitigations { + L1D_FLUSH_OFF = 0, + L1D_FLUSH_ON, +}; + +static enum l1d_flush_mitigations l1d_flush_mitigation __initdata = L1D_FLUSH_OFF; + +static void __init l1d_flush_select_mitigation(void) +{ + if (!l1d_flush_mitigation || !boot_cpu_has(X86_FEATURE_FLUSH_L1D)) + return; + + static_branch_enable(&switch_mm_cond_l1d_flush); + pr_info("Conditional flush on switch_mm() enabled\n"); +} + +static int __init l1d_flush_parse_cmdline(char *str) +{ + if (!strcmp(str, "on")) + l1d_flush_mitigation = L1D_FLUSH_ON; + + return 0; +} +early_param("l1d_flush", l1d_flush_parse_cmdline); + +#undef pr_fmt #define pr_fmt(fmt) "Spectre V1 : " fmt enum spectre_v1_mitigation { @@ -1215,6 +1252,24 @@ static void task_update_spec_tif(struct task_struct *tsk) speculation_ctrl_update_current(); } +static int l1d_flush_prctl_set(struct task_struct *task, unsigned long ctrl) +{ + + if (!static_branch_unlikely(&switch_mm_cond_l1d_flush)) + return -EPERM; + + switch (ctrl) { + case PR_SPEC_ENABLE: + set_ti_thread_flag(&task->thread_info, TIF_SPEC_L1D_FLUSH); + return 0; + case PR_SPEC_DISABLE: + clear_ti_thread_flag(&task->thread_info, TIF_SPEC_L1D_FLUSH); + return 0; + default: + return -ERANGE; + } +} + static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl) { if (ssb_mode != SPEC_STORE_BYPASS_PRCTL && @@ -1324,6 +1379,8 @@ int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which, return ssb_prctl_set(task, ctrl); case PR_SPEC_INDIRECT_BRANCH: return ib_prctl_set(task, ctrl); + case PR_SPEC_L1D_FLUSH: + return l1d_flush_prctl_set(task, ctrl); default: return -ENODEV; } @@ -1340,6 +1397,17 @@ void arch_seccomp_spec_mitigate(struct task_struct *task) } #endif +static int l1d_flush_prctl_get(struct task_struct *task) +{ + if (!static_branch_unlikely(&switch_mm_cond_l1d_flush)) + return PR_SPEC_FORCE_DISABLE; + + if (test_ti_thread_flag(&task->thread_info, TIF_SPEC_L1D_FLUSH)) + return PR_SPEC_PRCTL | PR_SPEC_ENABLE; + else + return PR_SPEC_PRCTL | PR_SPEC_DISABLE; +} + static int ssb_prctl_get(struct task_struct *task) { switch (ssb_mode) { @@ -1390,6 +1458,8 @@ int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which) return ssb_prctl_get(task); case PR_SPEC_INDIRECT_BRANCH: return ib_prctl_get(task); + case PR_SPEC_L1D_FLUSH: + return l1d_flush_prctl_get(task); default: return -ENODEV; } diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 9320285a5e29..85f6e242b6b4 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -610,6 +610,9 @@ void set_cpu_sibling_map(int cpu) if (threads > __max_smt_threads) __max_smt_threads = threads; + for_each_cpu(i, topology_sibling_cpumask(cpu)) + cpu_data(i).smt_active = threads > 1; + /* * This needs a separate iteration over the cpus because we rely on all * topology_sibling_cpumask links to be set-up. @@ -1552,8 +1555,13 @@ static void remove_siblinginfo(int cpu) for_each_cpu(sibling, topology_die_cpumask(cpu)) cpumask_clear_cpu(cpu, topology_die_cpumask(sibling)); - for_each_cpu(sibling, topology_sibling_cpumask(cpu)) + + for_each_cpu(sibling, topology_sibling_cpumask(cpu)) { cpumask_clear_cpu(cpu, topology_sibling_cpumask(sibling)); + if (cpumask_weight(topology_sibling_cpumask(sibling)) == 1) + cpu_data(sibling).smt_active = false; + } + for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) cpumask_clear_cpu(cpu, cpu_llc_shared_mask(sibling)); cpumask_clear(cpu_llc_shared_mask(cpu)); diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index cfe6b1e85fa6..59ba2968af1b 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -8,11 +8,13 @@ #include <linux/export.h> #include <linux/cpu.h> #include <linux/debugfs.h> +#include <linux/sched/smt.h> #include <asm/tlbflush.h> #include <asm/mmu_context.h> #include <asm/nospec-branch.h> #include <asm/cache.h> +#include <asm/cacheflush.h> #include <asm/apic.h> #include <asm/perf_event.h> @@ -43,10 +45,15 @@ */ /* - * Use bit 0 to mangle the TIF_SPEC_IB state into the mm pointer which is - * stored in cpu_tlb_state.last_user_mm_ibpb. + * Bits to mangle the TIF_SPEC_* state into the mm pointer which is + * stored in cpu_tlb_state.last_user_mm_spec. */ #define LAST_USER_MM_IBPB 0x1UL +#define LAST_USER_MM_L1D_FLUSH 0x2UL +#define LAST_USER_MM_SPEC_MASK (LAST_USER_MM_IBPB | LAST_USER_MM_L1D_FLUSH) + +/* Bits to set when tlbstate and flush is (re)initialized */ +#define LAST_USER_MM_INIT LAST_USER_MM_IBPB /* * The x86 feature is called PCID (Process Context IDentifier). It is similar @@ -317,20 +324,70 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next, local_irq_restore(flags); } -static unsigned long mm_mangle_tif_spec_ib(struct task_struct *next) +/* + * Invoked from return to user/guest by a task that opted-in to L1D + * flushing but ended up running on an SMT enabled core due to wrong + * affinity settings or CPU hotplug. This is part of the paranoid L1D flush + * contract which this task requested. + */ +static void l1d_flush_force_sigbus(struct callback_head *ch) +{ + force_sig(SIGBUS); +} + +static void l1d_flush_evaluate(unsigned long prev_mm, unsigned long next_mm, + struct task_struct *next) +{ + /* Flush L1D if the outgoing task requests it */ + if (prev_mm & LAST_USER_MM_L1D_FLUSH) + wrmsrl(MSR_IA32_FLUSH_CMD, L1D_FLUSH); + + /* Check whether the incoming task opted in for L1D flush */ + if (likely(!(next_mm & LAST_USER_MM_L1D_FLUSH))) + return; + + /* + * Validate that it is not running on an SMT sibling as this would + * make the excercise pointless because the siblings share L1D. If + * it runs on a SMT sibling, notify it with SIGBUS on return to + * user/guest + */ + if (this_cpu_read(cpu_info.smt_active)) { + clear_ti_thread_flag(&next->thread_info, TIF_SPEC_L1D_FLUSH); + next->l1d_flush_kill.func = l1d_flush_force_sigbus; + task_work_add(next, &next->l1d_flush_kill, TWA_RESUME); + } +} + +static unsigned long mm_mangle_tif_spec_bits(struct task_struct *next) { unsigned long next_tif = task_thread_info(next)->flags; - unsigned long ibpb = (next_tif >> TIF_SPEC_IB) & LAST_USER_MM_IBPB; + unsigned long spec_bits = (next_tif >> TIF_SPEC_IB) & LAST_USER_MM_SPEC_MASK; - return (unsigned long)next->mm | ibpb; + /* + * Ensure that the bit shift above works as expected and the two flags + * end up in bit 0 and 1. + */ + BUILD_BUG_ON(TIF_SPEC_L1D_FLUSH != TIF_SPEC_IB + 1); + + return (unsigned long)next->mm | spec_bits; } -static void cond_ibpb(struct task_struct *next) +static void cond_mitigation(struct task_struct *next) { + unsigned long prev_mm, next_mm; + if (!next || !next->mm) return; + next_mm = mm_mangle_tif_spec_bits(next); + prev_mm = this_cpu_read(cpu_tlbstate.last_user_mm_spec); + /* + * 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. + * * Both, the conditional and the always IBPB mode use the mm * pointer to avoid the IBPB when switching between tasks of the * same process. Using the mm pointer instead of mm->context.ctx_id @@ -340,8 +397,6 @@ static void cond_ibpb(struct task_struct *next) * exposed data is not really interesting. */ if (static_branch_likely(&switch_mm_cond_ibpb)) { - unsigned long prev_mm, next_mm; - /* * This is a bit more complex than the always mode because * it has to handle two cases: @@ -371,20 +426,14 @@ static void cond_ibpb(struct task_struct *next) * Optimize this with reasonably small overhead for the * above cases. Mangle the TIF_SPEC_IB bit into the mm * pointer of the incoming task which is stored in - * cpu_tlbstate.last_user_mm_ibpb for comparison. - */ - next_mm = mm_mangle_tif_spec_ib(next); - prev_mm = this_cpu_read(cpu_tlbstate.last_user_mm_ibpb); - - /* + * cpu_tlbstate.last_user_mm_spec for comparison. + * * Issue IBPB only if the mm's are different and one or * both have the IBPB bit set. */ if (next_mm != prev_mm && (next_mm | prev_mm) & LAST_USER_MM_IBPB) indirect_branch_prediction_barrier(); - - this_cpu_write(cpu_tlbstate.last_user_mm_ibpb, next_mm); } if (static_branch_unlikely(&switch_mm_always_ibpb)) { @@ -393,11 +442,22 @@ static void cond_ibpb(struct task_struct *next) * different context than the user space task which ran * last on this CPU. */ - if (this_cpu_read(cpu_tlbstate.last_user_mm) != next->mm) { + if ((prev_mm & ~LAST_USER_MM_SPEC_MASK) != + (unsigned long)next->mm) indirect_branch_prediction_barrier(); - this_cpu_write(cpu_tlbstate.last_user_mm, next->mm); - } } + + if (static_branch_unlikely(&switch_mm_cond_l1d_flush)) { + /* + * Flush L1D when the outgoing task requested it and/or + * check whether the incoming task requested L1D flushing + * and ended up on an SMT sibling. + */ + if (unlikely((prev_mm | next_mm) & LAST_USER_MM_L1D_FLUSH)) + l1d_flush_evaluate(prev_mm, next_mm, next); + } + + this_cpu_write(cpu_tlbstate.last_user_mm_spec, next_mm); } #ifdef CONFIG_PERF_EVENTS @@ -531,11 +591,10 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, need_flush = true; } else { /* - * 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. + * Apply process to process speculation vulnerability + * mitigations if applicable. */ - cond_ibpb(tsk); + cond_mitigation(tsk); /* * Stop remote flushes for the previous mm. @@ -643,7 +702,7 @@ void initialize_tlbstate_and_flush(void) write_cr3(build_cr3(mm->pgd, 0)); /* Reinitialize tlbstate. */ - this_cpu_write(cpu_tlbstate.last_user_mm_ibpb, LAST_USER_MM_IBPB); + this_cpu_write(cpu_tlbstate.last_user_mm_spec, LAST_USER_MM_INIT); this_cpu_write(cpu_tlbstate.loaded_mm_asid, 0); this_cpu_write(cpu_tlbstate.next_asid, 1); this_cpu_write(cpu_tlbstate.ctxs[0].ctx_id, mm->context.ctx_id); |