x86/mce: Provide a lockless memory pool to save error records

printk() is not safe to use in MCE context. Add a lockless
memory allocator pool to save error records in MCE context.
Those records will be issued later, in a printk-safe context.
The idea is inspired by the APEI/GHES driver.

We're very conservative and allocate only two pages for it but
since we're going to use those pages throughout the system's
lifetime, we allocate them statically to avoid early boot time
allocation woes.

Signed-off-by: Chen, Gong <gong.chen@linux.intel.com>
[ Rewrite. ]
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tony Luck <tony.luck@intel.com>
Link: http://lkml.kernel.org/r/1439396985-12812-3-git-send-email-bp@alien8.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>

4 files changed, 119 insertions, 2 deletions

diff --git a/arch/x86/kernel/cpu/mcheck/Makefile b/arch/x86/kernel/cpu/mcheck/Makefile
index bb34b03af252..a3311c886194 100644
--- a/arch/x86/kernel/cpu/mcheck/Makefile
+++ b/arch/x86/kernel/cpu/mcheck/Makefile
@@ -1,4 +1,4 @@
-obj-y				=  mce.o mce-severity.o
+obj-y				=  mce.o mce-severity.o mce-genpool.o
 
 obj-$(CONFIG_X86_ANCIENT_MCE)	+= winchip.o p5.o
 obj-$(CONFIG_X86_MCE_INTEL)	+= mce_intel.o
diff --git a/arch/x86/kernel/cpu/mcheck/mce-genpool.c b/arch/x86/kernel/cpu/mcheck/mce-genpool.c
new file mode 100644
index 000000000000..0a850100c594
--- /dev/null
+++ b/arch/x86/kernel/cpu/mcheck/mce-genpool.c
@@ -0,0 +1,99 @@
+/*
+ * MCE event pool management in MCE context
+ *
+ * Copyright (C) 2015 Intel Corp.
+ * Author: Chen, Gong <gong.chen@linux.intel.com>
+ *
+ * This file is licensed under GPLv2.
+ */
+#include <linux/smp.h>
+#include <linux/mm.h>
+#include <linux/genalloc.h>
+#include <linux/llist.h>
+#include "mce-internal.h"
+
+/*
+ * printk() is not safe in MCE context. This is a lock-less memory allocator
+ * used to save error information organized in a lock-less list.
+ *
+ * This memory pool is only to be used to save MCE records in MCE context.
+ * MCE events are rare, so a fixed size memory pool should be enough. Use
+ * 2 pages to save MCE events for now (~80 MCE records at most).
+ */
+#define MCE_POOLSZ	(2 * PAGE_SIZE)
+
+static struct gen_pool *mce_evt_pool;
+static LLIST_HEAD(mce_event_llist);
+static char gen_pool_buf[MCE_POOLSZ];
+
+void mce_gen_pool_process(void)
+{
+	struct llist_node *head;
+	struct mce_evt_llist *node;
+	struct mce *mce;
+
+	head = llist_del_all(&mce_event_llist);
+	if (!head)
+		return;
+
+	head = llist_reverse_order(head);
+	llist_for_each_entry(node, head, llnode) {
+		mce = &node->mce;
+		atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, mce);
+		gen_pool_free(mce_evt_pool, (unsigned long)node, sizeof(*node));
+	}
+}
+
+bool mce_gen_pool_empty(void)
+{
+	return llist_empty(&mce_event_llist);
+}
+
+int mce_gen_pool_add(struct mce *mce)
+{
+	struct mce_evt_llist *node;
+
+	if (!mce_evt_pool)
+		return -EINVAL;
+
+	node = (void *)gen_pool_alloc(mce_evt_pool, sizeof(*node));
+	if (!node) {
+		pr_warn_ratelimited("MCE records pool full!\n");
+		return -ENOMEM;
+	}
+
+	memcpy(&node->mce, mce, sizeof(*mce));
+	llist_add(&node->llnode, &mce_event_llist);
+
+	return 0;
+}
+
+static int mce_gen_pool_create(void)
+{
+	struct gen_pool *tmpp;
+	int ret = -ENOMEM;
+
+	tmpp = gen_pool_create(ilog2(sizeof(struct mce_evt_llist)), -1);
+	if (!tmpp)
+		goto out;
+
+	ret = gen_pool_add(tmpp, (unsigned long)gen_pool_buf, MCE_POOLSZ, -1);
+	if (ret) {
+		gen_pool_destroy(tmpp);
+		goto out;
+	}
+
+	mce_evt_pool = tmpp;
+
+out:
+	return ret;
+}
+
+int mce_gen_pool_init(void)
+{
+	/* Just init mce_gen_pool once. */
+	if (mce_evt_pool)
+		return 0;
+
+	return mce_gen_pool_create();
+}
diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h
index fe32074b865b..ea8b62264c14 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-internal.h
+++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h
@@ -13,6 +13,8 @@ enum severity_level {
 	MCE_PANIC_SEVERITY,
 };
 
+extern struct atomic_notifier_head x86_mce_decoder_chain;
+
 #define ATTR_LEN		16
 #define INITIAL_CHECK_INTERVAL	5 * 60 /* 5 minutes */
 
@@ -24,6 +26,16 @@ struct mce_bank {
 	char			attrname[ATTR_LEN];	/* attribute name */
 };
 
+struct mce_evt_llist {
+	struct llist_node llnode;
+	struct mce mce;
+};
+
+void mce_gen_pool_process(void);
+bool mce_gen_pool_empty(void);
+int mce_gen_pool_add(struct mce *mce);
+int mce_gen_pool_init(void);
+
 extern int (*mce_severity)(struct mce *a, int tolerant, char **msg, bool is_excp);
 struct dentry *mce_get_debugfs_dir(void);
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index df919ff103c3..a41c014e5cde 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -118,7 +118,7 @@ static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs);
  * CPU/chipset specific EDAC code can register a notifier call here to print
  * MCE errors in a human-readable form.
  */
-static ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain);
+ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain);
 
 /* Do initial initialization of a struct mce */
 void mce_setup(struct mce *m)
@@ -1731,6 +1731,12 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c)
 		return;
 	}
 
+	if (mce_gen_pool_init()) {
+		mca_cfg.disabled = true;
+		pr_emerg("Couldn't allocate MCE records pool!\n");
+		return;
+	}
+
 	machine_check_vector = do_machine_check;
 
 	__mcheck_cpu_init_generic();