Merge branch 'speck-v20' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Merge speculative store buffer bypass fixes from Thomas Gleixner:

 - rework of the SPEC_CTRL MSR management to accomodate the new fancy
   SSBD (Speculative Store Bypass Disable) bit handling.

 - the CPU bug and sysfs infrastructure for the exciting new Speculative
   Store Bypass 'feature'.

 - support for disabling SSB via LS_CFG MSR on AMD CPUs including
   Hyperthread synchronization on ZEN.

 - PRCTL support for dynamic runtime control of SSB

 - SECCOMP integration to automatically disable SSB for sandboxed
   processes with a filter flag for opt-out.

 - KVM integration to allow guests fiddling with SSBD including the new
   software MSR VIRT_SPEC_CTRL to handle the LS_CFG based oddities on
   AMD.

 - BPF protection against SSB

.. this is just the core and x86 side, other architecture support will
come separately.

* 'speck-v20' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (49 commits)
  bpf: Prevent memory disambiguation attack
  x86/bugs: Rename SSBD_NO to SSB_NO
  KVM: SVM: Implement VIRT_SPEC_CTRL support for SSBD
  x86/speculation, KVM: Implement support for VIRT_SPEC_CTRL/LS_CFG
  x86/bugs: Rework spec_ctrl base and mask logic
  x86/bugs: Remove x86_spec_ctrl_set()
  x86/bugs: Expose x86_spec_ctrl_base directly
  x86/bugs: Unify x86_spec_ctrl_{set_guest,restore_host}
  x86/speculation: Rework speculative_store_bypass_update()
  x86/speculation: Add virtualized speculative store bypass disable support
  x86/bugs, KVM: Extend speculation control for VIRT_SPEC_CTRL
  x86/speculation: Handle HT correctly on AMD
  x86/cpufeatures: Add FEATURE_ZEN
  x86/cpufeatures: Disentangle SSBD enumeration
  x86/cpufeatures: Disentangle MSR_SPEC_CTRL enumeration from IBRS
  x86/speculation: Use synthetic bits for IBRS/IBPB/STIBP
  KVM: SVM: Move spec control call after restore of GS
  x86/cpu: Make alternative_msr_write work for 32-bit code
  x86/bugs: Fix the parameters alignment and missing void
  x86/bugs: Make cpu_show_common() static
  ...

3 files changed, 94 insertions, 9 deletions

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 5dd1dcb902bf..2ce967a63ede 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -978,7 +978,7 @@ static bool register_is_null(struct bpf_reg_state *reg)
  */
 static int check_stack_write(struct bpf_verifier_env *env,
 			     struct bpf_func_state *state, /* func where register points to */
-			     int off, int size, int value_regno)
+			     int off, int size, int value_regno, int insn_idx)
 {
 	struct bpf_func_state *cur; /* state of the current function */
 	int i, slot = -off - 1, spi = slot / BPF_REG_SIZE, err;
@@ -1017,8 +1017,33 @@ static int check_stack_write(struct bpf_verifier_env *env,
 		state->stack[spi].spilled_ptr = cur->regs[value_regno];
 		state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN;
 
-		for (i = 0; i < BPF_REG_SIZE; i++)
+		for (i = 0; i < BPF_REG_SIZE; i++) {
+			if (state->stack[spi].slot_type[i] == STACK_MISC &&
+			    !env->allow_ptr_leaks) {
+				int *poff = &env->insn_aux_data[insn_idx].sanitize_stack_off;
+				int soff = (-spi - 1) * BPF_REG_SIZE;
+
+				/* detected reuse of integer stack slot with a pointer
+				 * which means either llvm is reusing stack slot or
+				 * an attacker is trying to exploit CVE-2018-3639
+				 * (speculative store bypass)
+				 * Have to sanitize that slot with preemptive
+				 * store of zero.
+				 */
+				if (*poff && *poff != soff) {
+					/* disallow programs where single insn stores
+					 * into two different stack slots, since verifier
+					 * cannot sanitize them
+					 */
+					verbose(env,
+						"insn %d cannot access two stack slots fp%d and fp%d",
+						insn_idx, *poff, soff);
+					return -EINVAL;
+				}
+				*poff = soff;
+			}
 			state->stack[spi].slot_type[i] = STACK_SPILL;
+		}
 	} else {
 		u8 type = STACK_MISC;
 
@@ -1694,7 +1719,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 
 		if (t == BPF_WRITE)
 			err = check_stack_write(env, state, off, size,
-						value_regno);
+						value_regno, insn_idx);
 		else
 			err = check_stack_read(env, state, off, size,
 					       value_regno);
@@ -5169,6 +5194,34 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 		else
 			continue;
 
+		if (type == BPF_WRITE &&
+		    env->insn_aux_data[i + delta].sanitize_stack_off) {
+			struct bpf_insn patch[] = {
+				/* Sanitize suspicious stack slot with zero.
+				 * There are no memory dependencies for this store,
+				 * since it's only using frame pointer and immediate
+				 * constant of zero
+				 */
+				BPF_ST_MEM(BPF_DW, BPF_REG_FP,
+					   env->insn_aux_data[i + delta].sanitize_stack_off,
+					   0),
+				/* the original STX instruction will immediately
+				 * overwrite the same stack slot with appropriate value
+				 */
+				*insn,
+			};
+
+			cnt = ARRAY_SIZE(patch);
+			new_prog = bpf_patch_insn_data(env, i + delta, patch, cnt);
+			if (!new_prog)
+				return -ENOMEM;
+
+			delta    += cnt - 1;
+			env->prog = new_prog;
+			insn      = new_prog->insnsi + i + delta;
+			continue;
+		}
+
 		if (env->insn_aux_data[i + delta].ptr_type != PTR_TO_CTX)
 			continue;
 
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index dc77548167ef..e691d9a6c58d 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -19,6 +19,8 @@
 #include <linux/compat.h>
 #include <linux/coredump.h>
 #include <linux/kmemleak.h>
+#include <linux/nospec.h>
+#include <linux/prctl.h>
 #include <linux/sched.h>
 #include <linux/sched/task_stack.h>
 #include <linux/seccomp.h>
@@ -227,8 +229,11 @@ static inline bool seccomp_may_assign_mode(unsigned long seccomp_mode)
 	return true;
 }
 
+void __weak arch_seccomp_spec_mitigate(struct task_struct *task) { }
+
 static inline void seccomp_assign_mode(struct task_struct *task,
-				       unsigned long seccomp_mode)
+				       unsigned long seccomp_mode,
+				       unsigned long flags)
 {
 	assert_spin_locked(&task->sighand->siglock);
 
@@ -238,6 +243,9 @@ static inline void seccomp_assign_mode(struct task_struct *task,
 	 * filter) is set.
 	 */
 	smp_mb__before_atomic();
+	/* Assume default seccomp processes want spec flaw mitigation. */
+	if ((flags & SECCOMP_FILTER_FLAG_SPEC_ALLOW) == 0)
+		arch_seccomp_spec_mitigate(task);
 	set_tsk_thread_flag(task, TIF_SECCOMP);
 }
 
@@ -305,7 +313,7 @@ static inline pid_t seccomp_can_sync_threads(void)
  * without dropping the locks.
  *
  */
-static inline void seccomp_sync_threads(void)
+static inline void seccomp_sync_threads(unsigned long flags)
 {
 	struct task_struct *thread, *caller;
 
@@ -346,7 +354,8 @@ static inline void seccomp_sync_threads(void)
 		 * allow one thread to transition the other.
 		 */
 		if (thread->seccomp.mode == SECCOMP_MODE_DISABLED)
-			seccomp_assign_mode(thread, SECCOMP_MODE_FILTER);
+			seccomp_assign_mode(thread, SECCOMP_MODE_FILTER,
+					    flags);
 	}
 }
 
@@ -469,7 +478,7 @@ static long seccomp_attach_filter(unsigned int flags,
 
 	/* Now that the new filter is in place, synchronize to all threads. */
 	if (flags & SECCOMP_FILTER_FLAG_TSYNC)
-		seccomp_sync_threads();
+		seccomp_sync_threads(flags);
 
 	return 0;
 }
@@ -818,7 +827,7 @@ static long seccomp_set_mode_strict(void)
 #ifdef TIF_NOTSC
 	disable_TSC();
 #endif
-	seccomp_assign_mode(current, seccomp_mode);
+	seccomp_assign_mode(current, seccomp_mode, 0);
 	ret = 0;
 
 out:
@@ -876,7 +885,7 @@ static long seccomp_set_mode_filter(unsigned int flags,
 	/* Do not free the successfully attached filter. */
 	prepared = NULL;
 
-	seccomp_assign_mode(current, seccomp_mode);
+	seccomp_assign_mode(current, seccomp_mode, flags);
 out:
 	spin_unlock_irq(&current->sighand->siglock);
 	if (flags & SECCOMP_FILTER_FLAG_TSYNC)
diff --git a/kernel/sys.c b/kernel/sys.c
index ad692183dfe9..b0eee418ee0d 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -61,6 +61,8 @@
 #include <linux/uidgid.h>
 #include <linux/cred.h>
 
+#include <linux/nospec.h>
+
 #include <linux/kmsg_dump.h>
 /* Move somewhere else to avoid recompiling? */
 #include <generated/utsrelease.h>
@@ -2242,6 +2244,17 @@ static int propagate_has_child_subreaper(struct task_struct *p, void *data)
 	return 1;
 }
 
+int __weak arch_prctl_spec_ctrl_get(struct task_struct *t, unsigned long which)
+{
+	return -EINVAL;
+}
+
+int __weak arch_prctl_spec_ctrl_set(struct task_struct *t, unsigned long which,
+				    unsigned long ctrl)
+{
+	return -EINVAL;
+}
+
 SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 		unsigned long, arg4, unsigned long, arg5)
 {
@@ -2450,6 +2463,16 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 	case PR_SVE_GET_VL:
 		error = SVE_GET_VL();
 		break;
+	case PR_GET_SPECULATION_CTRL:
+		if (arg3 || arg4 || arg5)
+			return -EINVAL;
+		error = arch_prctl_spec_ctrl_get(me, arg2);
+		break;
+	case PR_SET_SPECULATION_CTRL:
+		if (arg4 || arg5)
+			return -EINVAL;
+		error = arch_prctl_spec_ctrl_set(me, arg2, arg3);
+		break;
 	default:
 		error = -EINVAL;
 		break;