14 files changed, 246 insertions, 87 deletions

diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 8ad2e410974f..7c5538769f7e 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1603,7 +1603,7 @@ static void __init delay_with_tsc(void)
 	do {
 		rep_nop();
 		now = rdtsc();
-	} while ((now - start) < 40000000000UL / HZ &&
+	} while ((now - start) < 40000000000ULL / HZ &&
 		time_before_eq(jiffies, end));
 }
 
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index d71c8b54b696..bfca937bdcc3 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -300,6 +300,15 @@ retpoline_auto:
 		setup_force_cpu_cap(X86_FEATURE_USE_IBPB);
 		pr_info("Spectre v2 mitigation: Enabling Indirect Branch Prediction Barrier\n");
 	}
+
+	/*
+	 * Retpoline means the kernel is safe because it has no indirect
+	 * branches. But firmware isn't, so use IBRS to protect that.
+	 */
+	if (boot_cpu_has(X86_FEATURE_IBRS)) {
+		setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW);
+		pr_info("Enabling Restricted Speculation for firmware calls\n");
+	}
 }
 
 #undef pr_fmt
@@ -326,8 +335,9 @@ ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, c
 	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
 		return sprintf(buf, "Not affected\n");
 
-	return sprintf(buf, "%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
+	return sprintf(buf, "%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
 		       boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "",
+		       boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "",
 		       spectre_v2_module_string());
 }
 #endif
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 824aee0117bb..348cf4821240 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1749,3 +1749,33 @@ static int __init init_cpu_syscore(void)
 	return 0;
 }
 core_initcall(init_cpu_syscore);
+
+/*
+ * The microcode loader calls this upon late microcode load to recheck features,
+ * only when microcode has been updated. Caller holds microcode_mutex and CPU
+ * hotplug lock.
+ */
+void microcode_check(void)
+{
+	struct cpuinfo_x86 info;
+
+	perf_check_microcode();
+
+	/* Reload CPUID max function as it might've changed. */
+	info.cpuid_level = cpuid_eax(0);
+
+	/*
+	 * Copy all capability leafs to pick up the synthetic ones so that
+	 * memcmp() below doesn't fail on that. The ones coming from CPUID will
+	 * get overwritten in get_cpu_cap().
+	 */
+	memcpy(&info.x86_capability, &boot_cpu_data.x86_capability, sizeof(info.x86_capability));
+
+	get_cpu_cap(&info);
+
+	if (!memcmp(&info.x86_capability, &boot_cpu_data.x86_capability, sizeof(info.x86_capability)))
+		return;
+
+	pr_warn("x86/CPU: CPU features have changed after loading microcode, but might not take effect.\n");
+	pr_warn("x86/CPU: Please consider either early loading through initrd/built-in or a potential BIOS update.\n");
+}
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index d19e903214b4..4aa9fd379390 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -144,6 +144,13 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c)
 {
 	int i;
 
+	/*
+	 * We know that the hypervisor lie to us on the microcode version so
+	 * we may as well hope that it is running the correct version.
+	 */
+	if (cpu_has(c, X86_FEATURE_HYPERVISOR))
+		return false;
+
 	for (i = 0; i < ARRAY_SIZE(spectre_bad_microcodes); i++) {
 		if (c->x86_model == spectre_bad_microcodes[i].model &&
 		    c->x86_stepping == spectre_bad_microcodes[i].stepping)
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 330b8462d426..a998e1a7d46f 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -498,7 +498,7 @@ static unsigned int verify_patch_size(u8 family, u32 patch_size,
 	return patch_size;
 }
 
-static int apply_microcode_amd(int cpu)
+static enum ucode_state apply_microcode_amd(int cpu)
 {
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	struct microcode_amd *mc_amd;
@@ -512,7 +512,7 @@ static int apply_microcode_amd(int cpu)
 
 	p = find_patch(cpu);
 	if (!p)
-		return 0;
+		return UCODE_NFOUND;
 
 	mc_amd  = p->data;
 	uci->mc = p->data;
@@ -523,13 +523,13 @@ static int apply_microcode_amd(int cpu)
 	if (rev >= mc_amd->hdr.patch_id) {
 		c->microcode = rev;
 		uci->cpu_sig.rev = rev;
-		return 0;
+		return UCODE_OK;
 	}
 
 	if (__apply_microcode_amd(mc_amd)) {
 		pr_err("CPU%d: update failed for patch_level=0x%08x\n",
 			cpu, mc_amd->hdr.patch_id);
-		return -1;
+		return UCODE_ERROR;
 	}
 	pr_info("CPU%d: new patch_level=0x%08x\n", cpu,
 		mc_amd->hdr.patch_id);
@@ -537,7 +537,7 @@ static int apply_microcode_amd(int cpu)
 	uci->cpu_sig.rev = mc_amd->hdr.patch_id;
 	c->microcode = mc_amd->hdr.patch_id;
 
-	return 0;
+	return UCODE_UPDATED;
 }
 
 static int install_equiv_cpu_table(const u8 *buf)
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 319dd65f98a2..70ecbc8099c9 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -22,13 +22,16 @@
 #define pr_fmt(fmt) "microcode: " fmt
 
 #include <linux/platform_device.h>
+#include <linux/stop_machine.h>
 #include <linux/syscore_ops.h>
 #include <linux/miscdevice.h>
 #include <linux/capability.h>
 #include <linux/firmware.h>
 #include <linux/kernel.h>
+#include <linux/delay.h>
 #include <linux/mutex.h>
 #include <linux/cpu.h>
+#include <linux/nmi.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
 
@@ -64,6 +67,11 @@ LIST_HEAD(microcode_cache);
  */
 static DEFINE_MUTEX(microcode_mutex);
 
+/*
+ * Serialize late loading so that CPUs get updated one-by-one.
+ */
+static DEFINE_SPINLOCK(update_lock);
+
 struct ucode_cpu_info		ucode_cpu_info[NR_CPUS];
 
 struct cpu_info_ctx {
@@ -373,26 +381,23 @@ static int collect_cpu_info(int cpu)
 	return ret;
 }
 
-struct apply_microcode_ctx {
-	int err;
-};
-
 static void apply_microcode_local(void *arg)
 {
-	struct apply_microcode_ctx *ctx = arg;
+	enum ucode_state *err = arg;
 
-	ctx->err = microcode_ops->apply_microcode(smp_processor_id());
+	*err = microcode_ops->apply_microcode(smp_processor_id());
 }
 
 static int apply_microcode_on_target(int cpu)
 {
-	struct apply_microcode_ctx ctx = { .err = 0 };
+	enum ucode_state err;
 	int ret;
 
-	ret = smp_call_function_single(cpu, apply_microcode_local, &ctx, 1);
-	if (!ret)
-		ret = ctx.err;
-
+	ret = smp_call_function_single(cpu, apply_microcode_local, &err, 1);
+	if (!ret) {
+		if (err == UCODE_ERROR)
+			ret = 1;
+	}
 	return ret;
 }
 
@@ -489,31 +494,110 @@ static void __exit microcode_dev_exit(void)
 /* fake device for request_firmware */
 static struct platform_device	*microcode_pdev;
 
-static int reload_for_cpu(int cpu)
+/*
+ * Late loading dance. Why the heavy-handed stomp_machine effort?
+ *
+ * - HT siblings must be idle and not execute other code while the other sibling
+ *   is loading microcode in order to avoid any negative interactions caused by
+ *   the loading.
+ *
+ * - In addition, microcode update on the cores must be serialized until this
+ *   requirement can be relaxed in the future. Right now, this is conservative
+ *   and good.
+ */
+#define SPINUNIT 100 /* 100 nsec */
+
+static int check_online_cpus(void)
 {
-	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-	enum ucode_state ustate;
-	int err = 0;
+	if (num_online_cpus() == num_present_cpus())
+		return 0;
 
-	if (!uci->valid)
-		return err;
+	pr_err("Not all CPUs online, aborting microcode update.\n");
 
-	ustate = microcode_ops->request_microcode_fw(cpu, &microcode_pdev->dev, true);
-	if (ustate == UCODE_OK)
-		apply_microcode_on_target(cpu);
-	else
-		if (ustate == UCODE_ERROR)
-			err = -EINVAL;
-	return err;
+	return -EINVAL;
+}
+
+static atomic_t late_cpus;
+
+/*
+ * Returns:
+ * < 0 - on error
+ *   0 - no update done
+ *   1 - microcode was updated
+ */
+static int __reload_late(void *info)
+{
+	unsigned int timeout = NSEC_PER_SEC;
+	int all_cpus = num_online_cpus();
+	int cpu = smp_processor_id();
+	enum ucode_state err;
+	int ret = 0;
+
+	atomic_dec(&late_cpus);
+
+	/*
+	 * Wait for all CPUs to arrive. A load will not be attempted unless all
+	 * CPUs show up.
+	 * */
+	while (atomic_read(&late_cpus)) {
+		if (timeout < SPINUNIT) {
+			pr_err("Timeout while waiting for CPUs rendezvous, remaining: %d\n",
+				atomic_read(&late_cpus));
+			return -1;
+		}
+
+		ndelay(SPINUNIT);
+		timeout -= SPINUNIT;
+
+		touch_nmi_watchdog();
+	}
+
+	spin_lock(&update_lock);
+	apply_microcode_local(&err);
+	spin_unlock(&update_lock);
+
+	if (err > UCODE_NFOUND) {
+		pr_warn("Error reloading microcode on CPU %d\n", cpu);
+		ret = -1;
+	} else if (err == UCODE_UPDATED) {
+		ret = 1;
+	}
+
+	atomic_inc(&late_cpus);
+
+	while (atomic_read(&late_cpus) != all_cpus)
+		cpu_relax();
+
+	return ret;
+}
+
+/*
+ * Reload microcode late on all CPUs. Wait for a sec until they
+ * all gather together.
+ */
+static int microcode_reload_late(void)
+{
+	int ret;
+
+	atomic_set(&late_cpus, num_online_cpus());
+
+	ret = stop_machine_cpuslocked(__reload_late, NULL, cpu_online_mask);
+	if (ret < 0)
+		return ret;
+	else if (ret > 0)
+		microcode_check();
+
+	return ret;
 }
 
 static ssize_t reload_store(struct device *dev,
 			    struct device_attribute *attr,
 			    const char *buf, size_t size)
 {
+	enum ucode_state tmp_ret = UCODE_OK;
+	int bsp = boot_cpu_data.cpu_index;
 	unsigned long val;
-	int cpu;
-	ssize_t ret = 0, tmp_ret;
+	ssize_t ret = 0;
 
 	ret = kstrtoul(buf, 0, &val);
 	if (ret)
@@ -522,23 +606,24 @@ static ssize_t reload_store(struct device *dev,
 	if (val != 1)
 		return size;
 
+	tmp_ret = microcode_ops->request_microcode_fw(bsp, &microcode_pdev->dev, true);
+	if (tmp_ret != UCODE_OK)
+		return size;
+
 	get_online_cpus();
-	mutex_lock(&microcode_mutex);
-	for_each_online_cpu(cpu) {
-		tmp_ret = reload_for_cpu(cpu);
-		if (tmp_ret != 0)
-			pr_warn("Error reloading microcode on CPU %d\n", cpu);
 
-		/* save retval of the first encountered reload error */
-		if (!ret)
-			ret = tmp_ret;
-	}
-	if (!ret)
-		perf_check_microcode();
+	ret = check_online_cpus();
+	if (ret)
+		goto put;
+
+	mutex_lock(&microcode_mutex);
+	ret = microcode_reload_late();
 	mutex_unlock(&microcode_mutex);
+
+put:
 	put_online_cpus();
 
-	if (!ret)
+	if (ret >= 0)
 		ret = size;
 
 	return ret;
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index a15db2b4e0d6..2aded9db1d42 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -589,6 +589,23 @@ static int apply_microcode_early(struct ucode_cpu_info *uci, bool early)
 	if (!mc)
 		return 0;
 
+	/*
+	 * Save us the MSR write below - which is a particular expensive
+	 * operation - when the other hyperthread has updated the microcode
+	 * already.
+	 */
+	rev = intel_get_microcode_revision();
+	if (rev >= mc->hdr.rev) {
+		uci->cpu_sig.rev = rev;
+		return UCODE_OK;
+	}
+
+	/*
+	 * Writeback and invalidate caches before updating microcode to avoid
+	 * internal issues depending on what the microcode is updating.
+	 */
+	native_wbinvd();
+
 	/* write microcode via MSR 0x79 */
 	native_wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits);
 
@@ -772,27 +789,44 @@ static int collect_cpu_info(int cpu_num, struct cpu_signature *csig)
 	return 0;
 }
 
-static int apply_microcode_intel(int cpu)
+static enum ucode_state apply_microcode_intel(int cpu)
 {
+	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	struct microcode_intel *mc;
-	struct ucode_cpu_info *uci;
-	struct cpuinfo_x86 *c;
 	static int prev_rev;
 	u32 rev;
 
 	/* We should bind the task to the CPU */
 	if (WARN_ON(raw_smp_processor_id() != cpu))
-		return -1;
+		return UCODE_ERROR;
 
-	uci = ucode_cpu_info + cpu;
-	mc = uci->mc;
+	/* Look for a newer patch in our cache: */
+	mc = find_patch(uci);
 	if (!mc) {
-		/* Look for a newer patch in our cache: */
-		mc = find_patch(uci);
+		mc = uci->mc;
 		if (!mc)
-			return 0;
+			return UCODE_NFOUND;
 	}
 
+	/*
+	 * Save us the MSR write below - which is a particular expensive
+	 * operation - when the other hyperthread has updated the microcode
+	 * already.
+	 */
+	rev = intel_get_microcode_revision();
+	if (rev >= mc->hdr.rev) {
+		uci->cpu_sig.rev = rev;
+		c->microcode = rev;
+		return UCODE_OK;
+	}
+
+	/*
+	 * Writeback and invalidate caches before updating microcode to avoid
+	 * internal issues depending on what the microcode is updating.
+	 */
+	native_wbinvd();
+
 	/* write microcode via MSR 0x79 */
 	wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits);
 
@@ -801,7 +835,7 @@ static int apply_microcode_intel(int cpu)
 	if (rev != mc->hdr.rev) {
 		pr_err("CPU%d update to revision 0x%x failed\n",
 		       cpu, mc->hdr.rev);
-		return -1;
+		return UCODE_ERROR;
 	}
 
 	if (rev != prev_rev) {
@@ -813,12 +847,10 @@ static int apply_microcode_intel(int cpu)
 		prev_rev = rev;
 	}
 
-	c = &cpu_data(cpu);
-
 	uci->cpu_sig.rev = rev;
 	c->microcode = rev;
 
-	return 0;
+	return UCODE_UPDATED;
 }
 
 static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 326c63129417..48385c1074a5 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -23,6 +23,7 @@
 #include <asm/nops.h>
 #include "../entry/calling.h"
 #include <asm/export.h>
+#include <asm/nospec-branch.h>
 
 #ifdef CONFIG_PARAVIRT
 #include <asm/asm-offsets.h>
@@ -137,6 +138,7 @@ ENTRY(secondary_startup_64)
 
 	/* Ensure I am executing from virtual addresses */
 	movq	$1f, %rax
+	ANNOTATE_RETPOLINE_SAFE
 	jmp	*%rax
 1:
 	UNWIND_HINT_EMPTY
diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c
index 2f723301eb58..38deafebb21b 100644
--- a/arch/x86/kernel/ioport.c
+++ b/arch/x86/kernel/ioport.c
@@ -23,7 +23,7 @@
 /*
  * this changes the io permissions bitmap in the current task.
  */
-asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on)
+SYSCALL_DEFINE3(ioperm, unsigned long, from, unsigned long, num, int, turn_on)
 {
 	struct thread_struct *t = &current->thread;
 	struct tss_struct *tss;
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index bd36f3c33cd0..0715f827607c 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -1168,10 +1168,18 @@ NOKPROBE_SYMBOL(longjmp_break_handler);
 
 bool arch_within_kprobe_blacklist(unsigned long addr)
 {
+	bool is_in_entry_trampoline_section = false;
+
+#ifdef CONFIG_X86_64
+	is_in_entry_trampoline_section =
+		(addr >= (unsigned long)__entry_trampoline_start &&
+		 addr < (unsigned long)__entry_trampoline_end);
+#endif
 	return  (addr >= (unsigned long)__kprobes_text_start &&
 		 addr < (unsigned long)__kprobes_text_end) ||
 		(addr >= (unsigned long)__entry_text_start &&
-		 addr < (unsigned long)__entry_text_end);
+		 addr < (unsigned long)__entry_text_end) ||
+		is_in_entry_trampoline_section;
 }
 
 int __init arch_init_kprobes(void)
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 399d0f7fa8f1..6285697b6e56 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1203,20 +1203,13 @@ void __init setup_arch(char **cmdline_p)
 
 	kasan_init();
 
-#ifdef CONFIG_X86_32
-	/* sync back kernel address range */
-	clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY,
-			swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
-			KERNEL_PGD_PTRS);
-
 	/*
-	 * sync back low identity map too.  It is used for example
-	 * in the 32-bit EFI stub.
+	 * Sync back kernel address range.
+	 *
+	 * FIXME: Can the later sync in setup_cpu_entry_areas() replace
+	 * this call?
 	 */
-	clone_pgd_range(initial_page_table,
-			swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
-			min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY));
-#endif
+	sync_initial_page_table();
 
 	tboot_probe();
 
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 497aa766fab3..ea554f812ee1 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -287,24 +287,15 @@ void __init setup_per_cpu_areas(void)
 	/* Setup cpu initialized, callin, callout masks */
 	setup_cpu_local_masks();
 
-#ifdef CONFIG_X86_32
 	/*
 	 * Sync back kernel address range again.  We already did this in
 	 * setup_arch(), but percpu data also needs to be available in
 	 * the smpboot asm.  We can't reliably pick up percpu mappings
 	 * using vmalloc_fault(), because exception dispatch needs
 	 * percpu data.
+	 *
+	 * FIXME: Can the later sync in setup_cpu_entry_areas() replace
+	 * this call?
 	 */
-	clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY,
-			swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
-			KERNEL_PGD_PTRS);
-
-	/*
-	 * sync back low identity map too.  It is used for example
-	 * in the 32-bit EFI stub.
-	 */
-	clone_pgd_range(initial_page_table,
-			swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
-			min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY));
-#endif
+	sync_initial_page_table();
 }
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index 1f9188f5357c..feb28fee6cea 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -5,7 +5,6 @@
 #include <asm/unwind.h>
 #include <asm/orc_types.h>
 #include <asm/orc_lookup.h>
-#include <asm/sections.h>
 
 #define orc_warn(fmt, ...) \
 	printk_deferred_once(KERN_WARNING pr_fmt("WARNING: " fmt), ##__VA_ARGS__)
@@ -148,7 +147,7 @@ static struct orc_entry *orc_find(unsigned long ip)
 	}
 
 	/* vmlinux .init slow lookup: */
-	if (ip >= (unsigned long)_sinittext && ip < (unsigned long)_einittext)
+	if (init_kernel_text(ip))
 		return __orc_find(__start_orc_unwind_ip, __start_orc_unwind,
 				  __stop_orc_unwind_ip - __start_orc_unwind_ip, ip);
 
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 9b138a06c1a4..b854ebf5851b 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -118,9 +118,11 @@ SECTIONS
 
 #ifdef CONFIG_X86_64
 		. = ALIGN(PAGE_SIZE);
+		VMLINUX_SYMBOL(__entry_trampoline_start) = .;
 		_entry_trampoline = .;
 		*(.entry_trampoline)
 		. = ALIGN(PAGE_SIZE);
+		VMLINUX_SYMBOL(__entry_trampoline_end) = .;
 		ASSERT(. - _entry_trampoline == PAGE_SIZE, "entry trampoline is too big");
 #endif