summaryrefslogtreecommitdiff
path: root/arch/x86/kernel
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2021-08-30 15:00:33 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2021-08-30 15:00:33 -0700
commit0a096f240aa1992ddac65f8e704f7b0c0795fe1c (patch)
tree04c64aca17b94b0862214e09784fc23b413df578 /arch/x86/kernel
parent7d6e3fa87e732ec1e7761bf325c0907685c8571b (diff)
parentb7fe54f6c2d437082dcbecfbd832f38edd9caaf4 (diff)
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/x86/kernel')
-rw-r--r--arch/x86/kernel/cpu/bugs.c70
-rw-r--r--arch/x86/kernel/smpboot.c10
2 files changed, 79 insertions, 1 deletions
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));