Merge tag 'x86_bugs_retbleed' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 retbleed fixes from Borislav Petkov:
 "Just when you thought that all the speculation bugs were addressed and
  solved and the nightmare is complete, here's the next one: speculating
  after RET instructions and leaking privileged information using the
  now pretty much classical covert channels.

  It is called RETBleed and the mitigation effort and controlling
  functionality has been modelled similar to what already existing
  mitigations provide"

* tag 'x86_bugs_retbleed' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (54 commits)
  x86/speculation: Disable RRSBA behavior
  x86/kexec: Disable RET on kexec
  x86/bugs: Do not enable IBPB-on-entry when IBPB is not supported
  x86/entry: Move PUSH_AND_CLEAR_REGS() back into error_entry
  x86/bugs: Add Cannon lake to RETBleed affected CPU list
  x86/retbleed: Add fine grained Kconfig knobs
  x86/cpu/amd: Enumerate BTC_NO
  x86/common: Stamp out the stepping madness
  KVM: VMX: Prevent RSB underflow before vmenter
  x86/speculation: Fill RSB on vmexit for IBRS
  KVM: VMX: Fix IBRS handling after vmexit
  KVM: VMX: Prevent guest RSB poisoning attacks with eIBRS
  KVM: VMX: Convert launched argument to flags
  KVM: VMX: Flatten __vmx_vcpu_run()
  objtool: Re-add UNWIND_HINT_{SAVE_RESTORE}
  x86/speculation: Remove x86_spec_ctrl_mask
  x86/speculation: Use cached host SPEC_CTRL value for guest entry/exit
  x86/speculation: Fix SPEC_CTRL write on SMT state change
  x86/speculation: Fix firmware entry SPEC_CTRL handling
  x86/speculation: Fix RSB filling with CONFIG_RETPOLINE=n
  ...

2 files changed, 46 insertions, 6 deletions

diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index a97776ea9d99..4c98849577d4 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -570,6 +570,12 @@ ssize_t __weak cpu_show_mmio_stale_data(struct device *dev,
 	return sysfs_emit(buf, "Not affected\n");
 }
 
+ssize_t __weak cpu_show_retbleed(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "Not affected\n");
+}
+
 static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL);
 static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL);
 static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL);
@@ -580,6 +586,7 @@ static DEVICE_ATTR(tsx_async_abort, 0444, cpu_show_tsx_async_abort, NULL);
 static DEVICE_ATTR(itlb_multihit, 0444, cpu_show_itlb_multihit, NULL);
 static DEVICE_ATTR(srbds, 0444, cpu_show_srbds, NULL);
 static DEVICE_ATTR(mmio_stale_data, 0444, cpu_show_mmio_stale_data, NULL);
+static DEVICE_ATTR(retbleed, 0444, cpu_show_retbleed, NULL);
 
 static struct attribute *cpu_root_vulnerabilities_attrs[] = {
 	&dev_attr_meltdown.attr,
@@ -592,6 +599,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = {
 	&dev_attr_itlb_multihit.attr,
 	&dev_attr_srbds.attr,
 	&dev_attr_mmio_stale_data.attr,
+	&dev_attr_retbleed.attr,
 	NULL
 };
 
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 424ef470223d..f5c6802aa6c3 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -47,11 +47,13 @@
 #include <linux/tick.h>
 #include <trace/events/power.h>
 #include <linux/sched.h>
+#include <linux/sched/smt.h>
 #include <linux/notifier.h>
 #include <linux/cpu.h>
 #include <linux/moduleparam.h>
 #include <asm/cpu_device_id.h>
 #include <asm/intel-family.h>
+#include <asm/nospec-branch.h>
 #include <asm/mwait.h>
 #include <asm/msr.h>
 
@@ -106,6 +108,12 @@ static unsigned int mwait_substates __initdata;
 #define CPUIDLE_FLAG_ALWAYS_ENABLE	BIT(15)
 
 /*
+ * Disable IBRS across idle (when KERNEL_IBRS), is exclusive vs IRQ_ENABLE
+ * above.
+ */
+#define CPUIDLE_FLAG_IBRS		BIT(16)
+
+/*
  * MWAIT takes an 8-bit "hint" in EAX "suggesting"
  * the C-state (top nibble) and sub-state (bottom nibble)
  * 0x00 means "MWAIT(C1)", 0x10 means "MWAIT(C2)" etc.
@@ -159,6 +167,24 @@ static __cpuidle int intel_idle_irq(struct cpuidle_device *dev,
 	return ret;
 }
 
+static __cpuidle int intel_idle_ibrs(struct cpuidle_device *dev,
+				     struct cpuidle_driver *drv, int index)
+{
+	bool smt_active = sched_smt_active();
+	u64 spec_ctrl = spec_ctrl_current();
+	int ret;
+
+	if (smt_active)
+		wrmsrl(MSR_IA32_SPEC_CTRL, 0);
+
+	ret = __intel_idle(dev, drv, index);
+
+	if (smt_active)
+		wrmsrl(MSR_IA32_SPEC_CTRL, spec_ctrl);
+
+	return ret;
+}
+
 /**
  * intel_idle_s2idle - Ask the processor to enter the given idle state.
  * @dev: cpuidle device of the target CPU.
@@ -680,7 +706,7 @@ static struct cpuidle_state skl_cstates[] __initdata = {
 	{
 		.name = "C6",
 		.desc = "MWAIT 0x20",
-		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED | CPUIDLE_FLAG_IBRS,
 		.exit_latency = 85,
 		.target_residency = 200,
 		.enter = &intel_idle,
@@ -688,7 +714,7 @@ static struct cpuidle_state skl_cstates[] __initdata = {
 	{
 		.name = "C7s",
 		.desc = "MWAIT 0x33",
-		.flags = MWAIT2flg(0x33) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x33) | CPUIDLE_FLAG_TLB_FLUSHED | CPUIDLE_FLAG_IBRS,
 		.exit_latency = 124,
 		.target_residency = 800,
 		.enter = &intel_idle,
@@ -696,7 +722,7 @@ static struct cpuidle_state skl_cstates[] __initdata = {
 	{
 		.name = "C8",
 		.desc = "MWAIT 0x40",
-		.flags = MWAIT2flg(0x40) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x40) | CPUIDLE_FLAG_TLB_FLUSHED | CPUIDLE_FLAG_IBRS,
 		.exit_latency = 200,
 		.target_residency = 800,
 		.enter = &intel_idle,
@@ -704,7 +730,7 @@ static struct cpuidle_state skl_cstates[] __initdata = {
 	{
 		.name = "C9",
 		.desc = "MWAIT 0x50",
-		.flags = MWAIT2flg(0x50) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x50) | CPUIDLE_FLAG_TLB_FLUSHED | CPUIDLE_FLAG_IBRS,
 		.exit_latency = 480,
 		.target_residency = 5000,
 		.enter = &intel_idle,
@@ -712,7 +738,7 @@ static struct cpuidle_state skl_cstates[] __initdata = {
 	{
 		.name = "C10",
 		.desc = "MWAIT 0x60",
-		.flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED | CPUIDLE_FLAG_IBRS,
 		.exit_latency = 890,
 		.target_residency = 5000,
 		.enter = &intel_idle,
@@ -741,7 +767,7 @@ static struct cpuidle_state skx_cstates[] __initdata = {
 	{
 		.name = "C6",
 		.desc = "MWAIT 0x20",
-		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED | CPUIDLE_FLAG_IBRS,
 		.exit_latency = 133,
 		.target_residency = 600,
 		.enter = &intel_idle,
@@ -1819,6 +1845,12 @@ static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv)
 		if (cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_IRQ_ENABLE)
 			drv->states[drv->state_count].enter = intel_idle_irq;
 
+		if (cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS) &&
+		    cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_IBRS) {
+			WARN_ON_ONCE(cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_IRQ_ENABLE);
+			drv->states[drv->state_count].enter = intel_idle_ibrs;
+		}
+
 		if ((disabled_states_mask & BIT(drv->state_count)) ||
 		    ((icpu->use_acpi || force_use_acpi) &&
 		     intel_idle_off_by_default(mwait_hint) &&