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

Documentation/admin-guide/hw-vuln/index.rst

@@ -16,3 +16,4 @@ are configurable at compile, boot or run time.
    multihit.rst
    special-register-buffer-data-sampling.rst
    core-scheduling.rst
+   l1d_flush.rst

Documentation/admin-guide/hw-vuln/l1d_flush.rst

@@ -0,0 +1,69 @@
+L1D Flushing
+============
+
+With an increasing number of vulnerabilities being reported around data
+leaks from the Level 1 Data cache (L1D) the kernel provides an opt-in
+mechanism to flush the L1D cache on context switch.
+
+This mechanism can be used to address e.g. CVE-2020-0550. For applications
+the mechanism keeps them safe from vulnerabilities, related to leaks
+(snooping of) from the L1D cache.
+
+
+Related CVEs
+------------
+The following CVEs can be addressed by this
+mechanism
+
+    =============       ========================     ==================
+    CVE-2020-0550       Improper Data Forwarding     OS related aspects
+    =============       ========================     ==================
+
+Usage Guidelines
+----------------
+
+Please see document: :ref:`Documentation/userspace-api/spec_ctrl.rst
+<set_spec_ctrl>` for details.
+
+**NOTE**: The feature is disabled by default, applications need to
+specifically opt into the feature to enable it.
+
+Mitigation
+----------
+
+When PR_SET_L1D_FLUSH is enabled for a task a flush of the L1D cache is
+performed when the task is scheduled out and the incoming task belongs to a
+different process and therefore to a different address space.
+
+If the underlying CPU supports L1D flushing in hardware, the hardware
+mechanism is used, software fallback for the mitigation, is not supported.
+
+Mitigation control on the kernel command line
+---------------------------------------------
+
+The kernel command line allows to control the L1D flush mitigations at boot
+time with the option "l1d_flush=". The valid arguments for this option are:
+
+  ============  =============================================================
+  on            Enables the prctl interface, applications trying to use
+                the prctl() will fail with an error if l1d_flush is not
+                enabled
+  ============  =============================================================
+
+By default the mechanism is disabled.
+
+Limitations
+-----------
+
+The mechanism does not mitigate L1D data leaks between tasks belonging to
+different processes which are concurrently executing on sibling threads of
+a physical CPU core when SMT is enabled on the system.
+
+This can be addressed by controlled placement of processes on physical CPU
+cores or by disabling SMT. See the relevant chapter in the L1TF mitigation
+document: :ref:`Documentation/admin-guide/hw-vuln/l1tf.rst <smt_control>`.
+
+**NOTE** : The opt-in of a task for L1D flushing works only when the task's
+affinity is limited to cores running in non-SMT mode. If a task which
+requested L1D flushing is scheduled on a SMT-enabled core the kernel sends
+a SIGBUS to the task.

Documentation/admin-guide/kernel-parameters.txt

@@ -2421,6 +2421,23 @@
 			feature (tagged TLBs) on capable Intel chips.
 			Default is 1 (enabled)
 
+	l1d_flush=	[X86,INTEL]
+			Control mitigation for L1D based snooping vulnerability.
+
+			Certain CPUs are vulnerable to an exploit against CPU
+			internal buffers which can forward information to a
+			disclosure gadget under certain conditions.
+
+			In vulnerable processors, the speculatively
+			forwarded data can be used in a cache side channel
+			attack, to access data to which the attacker does
+			not have direct access.
+
+			This parameter controls the mitigation. The
+			options are:
+
+			on         - enable the interface for the mitigation
+
 	l1tf=           [X86] Control mitigation of the L1TF vulnerability on
 			      affected CPUs
 

Documentation/userspace-api/spec_ctrl.rst

@@ -106,3 +106,11 @@ Speculation misfeature controls
    * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, PR_SPEC_ENABLE, 0, 0);
    * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, PR_SPEC_DISABLE, 0, 0);
    * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, PR_SPEC_FORCE_DISABLE, 0, 0);
+
+- PR_SPEC_L1D_FLUSH: Flush L1D Cache on context switch out of the task
+                        (works only when tasks run on non SMT cores)
+
+  Invocations:
+   * prctl(PR_GET_SPECULATION_CTRL, PR_SPEC_L1D_FLUSH, 0, 0, 0);
+   * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_L1D_FLUSH, PR_SPEC_ENABLE, 0, 0);
+   * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_L1D_FLUSH, PR_SPEC_DISABLE, 0, 0);

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"

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

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>
 
 /**

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;

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)

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;

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
@@ -491,6 +500,34 @@ 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
 
@@ -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;
 	}

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));