summaryrefslogtreecommitdiff
path: root/arch/x86/kernel/cpu/microcode/core.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2018-03-11 14:59:23 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2018-03-11 14:59:23 -0700
commited58d66f60b3dd5b5c9307a65e8cd9b777b55078 (patch)
tree922909b470994d074529b46cbd9c3577baa1ec1d /arch/x86/kernel/cpu/microcode/core.c
parent1ad5daa65395740d80aa7b2ac11887791142e018 (diff)
parentc07a8f8b08ba683ea24f3ac9159f37ae94daf47f (diff)
Merge branch 'x86-pti-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86/pti updates from Thomas Gleixner: "Yet another pile of melted spectrum related updates: - Drop native vsyscall support finally as it causes more trouble than benefit. - Make microcode loading more robust. There were a few issues especially related to late loading which are now surfacing because late loading of the IB* microcodes addressing spectre issues has become more widely used. - Simplify and robustify the syscall handling in the entry code - Prevent kprobes on the entry trampoline code which lead to kernel crashes when the probe hits before CR3 is updated - Don't check microcode versions when running on hypervisors as they are considered as lying anyway. - Fix the 32bit objtool build and a coment typo" * 'x86-pti-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: x86/kprobes: Fix kernel crash when probing .entry_trampoline code x86/pti: Fix a comment typo x86/microcode: Synchronize late microcode loading x86/microcode: Request microcode on the BSP x86/microcode/intel: Look into the patch cache first x86/microcode: Do not upload microcode if CPUs are offline x86/microcode/intel: Writeback and invalidate caches before updating microcode x86/microcode/intel: Check microcode revision before updating sibling threads x86/microcode: Get rid of struct apply_microcode_ctx x86/spectre_v2: Don't check microcode versions when running under hypervisors x86/vsyscall/64: Drop "native" vsyscalls x86/entry/64/compat: Save one instruction in entry_INT80_compat() x86/entry: Do not special-case clone(2) in compat entry x86/syscalls: Use COMPAT_SYSCALL_DEFINEx() macros for x86-only compat syscalls x86/syscalls: Use proper syscall definition for sys_ioperm() x86/entry: Remove stale syscall prototype x86/syscalls/32: Simplify $entry == $compat entries objtool: Fix 32-bit build
Diffstat (limited to 'arch/x86/kernel/cpu/microcode/core.c')
-rw-r--r--arch/x86/kernel/cpu/microcode/core.c158
1 files changed, 119 insertions, 39 deletions
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index aa1b9a422f2b..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 {
- enum ucode_state 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;
}
@@ -489,19 +494,100 @@ static void __exit microcode_dev_exit(void)
/* fake device for request_firmware */
static struct platform_device *microcode_pdev;
-static enum ucode_state 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;
+ if (num_online_cpus() == num_present_cpus())
+ return 0;
- if (!uci->valid)
- return UCODE_OK;
+ pr_err("Not all CPUs online, aborting microcode update.\n");
+
+ 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;
+ }
- ustate = microcode_ops->request_microcode_fw(cpu, &microcode_pdev->dev, true);
- if (ustate != UCODE_OK)
- return ustate;
+ ndelay(SPINUNIT);
+ timeout -= SPINUNIT;
- return apply_microcode_on_target(cpu);
+ 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,
@@ -509,10 +595,9 @@ static ssize_t reload_store(struct device *dev,
const char *buf, size_t size)
{
enum ucode_state tmp_ret = UCODE_OK;
- bool do_callback = false;
+ int bsp = boot_cpu_data.cpu_index;
unsigned long val;
ssize_t ret = 0;
- int cpu;
ret = kstrtoul(buf, 0, &val);
if (ret)
@@ -521,29 +606,24 @@ static ssize_t reload_store(struct device *dev,
if (val != 1)
return size;
- get_online_cpus();
- mutex_lock(&microcode_mutex);
- for_each_online_cpu(cpu) {
- tmp_ret = reload_for_cpu(cpu);
- if (tmp_ret > UCODE_NFOUND) {
- pr_warn("Error reloading microcode on CPU %d\n", cpu);
-
- /* set retval for the first encountered reload error */
- if (!ret)
- ret = -EINVAL;
- }
+ tmp_ret = microcode_ops->request_microcode_fw(bsp, &microcode_pdev->dev, true);
+ if (tmp_ret != UCODE_OK)
+ return size;
- if (tmp_ret == UCODE_UPDATED)
- do_callback = true;
- }
+ get_online_cpus();
- if (!ret && do_callback)
- microcode_check();
+ 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;