From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Google-Smtp-Source: AIpwx49o4ZjKr9eyVun14kXkXPRwLmX6NHSLdnDeTGwiqnkY/oYuIFmX6ZOIxAaR3J7N6MC0HfSy ARC-Seal: i=1; a=rsa-sha256; t=1523399922; cv=none; d=google.com; s=arc-20160816; b=Y4U+aD9O0TtPoawsnp2fVRuxeK1e6ipvjLdF9IAuim8jDcXYYNaB0bDzPQpRHZXoaH w69Zzwiu/Ae5vF8jxr3GZvjbDxgrlIAO1JIq0raA2/noJGz62NR7RphxTIiNVLYFAQBk Lv87eH2g+I9Cu3X76H5YfaAkMU9ST90irPdcspJItfYIoRGOMCrlngc3BG0StskFC+bw eSGoRwkM1W1JXVWnPfM9JrRoCqReSZlK84jZzsWc9Lbyc4/gC15Zuu4tKsrUn2ZNVVUB reoeysE2xBvTB7Dw2ULbsFVdYIgoUlrE1bjEz6AjYx4J7mNH5evNEtEiV3L7e6h4LUKq Oigg== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=mime-version:user-agent:references:in-reply-to:message-id:date :subject:cc:to:from:arc-authentication-results; bh=Ei/34cN+X9fBf/1lob2eAgABe/NoLPBmTTAhu9tRXFc=; b=jfYHLzwwnJtAswpXwFYEVbqsRzd55vMrd78vA2C/gJZbj7Y8NrcQo21qCPrQkX1DSB PywQ8PhUq2sB941bFhJJmC1sTbhMzSen+DzeW3res5h3K7qiz8GgtkxWT5EE2ulw0qUK xTCQVxfVS+TGslt4ysAoN1IpP05bz5zpFMREeU6eGRAQJtjH3+9v0JkJ3ZwjfFrjSIFh DKtfNSj3XKv40Xkb+DY7XHH0j7sgACPn7MEb0PwPtobUzHojF4nwvFDkZvWvsm3bgNAR NsJimxav6XQfQPensGqc2aE2ul9aOWzH1sI/Mt6TXwdhshhnKu7dQjER6kuoHINlGf9h e1bg== ARC-Authentication-Results: i=1; mx.google.com; spf=softfail (google.com: domain of transitioning gregkh@linuxfoundation.org does not designate 90.92.61.202 as permitted sender) smtp.mailfrom=gregkh@linuxfoundation.org Authentication-Results: mx.google.com; spf=softfail (google.com: domain of transitioning gregkh@linuxfoundation.org does not designate 90.92.61.202 as permitted sender) smtp.mailfrom=gregkh@linuxfoundation.org From: Greg Kroah-Hartman To: linux-kernel@vger.kernel.org Cc: Greg Kroah-Hartman , stable@vger.kernel.org, Ashok Raj , Borislav Petkov , Thomas Gleixner , Tom Lendacky , Arjan Van De Ven Subject: [PATCH 4.14 094/138] x86/microcode: Synchronize late microcode loading Date: Wed, 11 Apr 2018 00:24:44 +0200 Message-Id: <20180410212913.109294047@linuxfoundation.org> X-Mailer: git-send-email 2.17.0 In-Reply-To: <20180410212902.121524696@linuxfoundation.org> References: <20180410212902.121524696@linuxfoundation.org> User-Agent: quilt/0.65 X-stable: review MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 X-getmail-retrieved-from-mailbox: INBOX X-GMAIL-LABELS: =?utf-8?b?IlxcU2VudCI=?= X-GMAIL-THRID: =?utf-8?q?1597400170922459032?= X-GMAIL-MSGID: =?utf-8?q?1597400596930505690?= X-Mailing-List: linux-kernel@vger.kernel.org List-ID: 4.14-stable review patch. If anyone has any objections, please let me know. ------------------ From: Ashok Raj commit a5321aec6412b20b5ad15db2d6b916c05349dbff upstream. Original idea by Ashok, completely rewritten by Borislav. Before you read any further: the early loading method is still the preferred one and you should always do that. The following patch is improving the late loading mechanism for long running jobs and cloud use cases. Gather all cores and serialize the microcode update on them by doing it one-by-one to make the late update process as reliable as possible and avoid potential issues caused by the microcode update. [ Borislav: Rewrite completely. ] Co-developed-by: Borislav Petkov Signed-off-by: Ashok Raj Signed-off-by: Borislav Petkov Signed-off-by: Thomas Gleixner Tested-by: Tom Lendacky Tested-by: Ashok Raj Reviewed-by: Tom Lendacky Cc: Arjan Van De Ven Link: https://lkml.kernel.org/r/20180228102846.13447-8-bp@alien8.de Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/cpu/microcode/core.c | 118 +++++++++++++++++++++++++++-------- 1 file changed, 92 insertions(+), 26 deletions(-) --- 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 +#include #include #include #include #include #include +#include #include #include +#include #include #include @@ -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 { @@ -486,6 +494,19 @@ static void __exit microcode_dev_exit(vo /* fake device for request_firmware */ static struct platform_device *microcode_pdev; +/* + * 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) { if (num_online_cpus() == num_present_cpus()) @@ -496,23 +517,85 @@ static int check_online_cpus(void) return -EINVAL; } -static enum ucode_state reload_for_cpu(int cpu) +static atomic_t late_cpus; + +/* + * Returns: + * < 0 - on error + * 0 - no update done + * 1 - microcode was updated + */ +static int __reload_late(void *info) { - struct ucode_cpu_info *uci = ucode_cpu_info + cpu; + 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; + } - if (!uci->valid) - return UCODE_OK; + atomic_inc(&late_cpus); - return apply_microcode_on_target(cpu); + 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) { - int cpu, bsp = boot_cpu_data.cpu_index; 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; @@ -534,30 +617,13 @@ static ssize_t reload_store(struct devic goto put; mutex_lock(µcode_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; - } - - if (tmp_ret == UCODE_UPDATED) - do_callback = true; - } - - if (!ret && do_callback) - microcode_check(); - + ret = microcode_reload_late(); mutex_unlock(µcode_mutex); put: put_online_cpus(); - if (!ret) + if (ret >= 0) ret = size; return ret;