We want to allow multiple NMI-like notifications on arm64, but the GHES
driver only has one in_nmi() path. To support asynchronous notifications
we also need to use the estatus-queue.
First we move the estatus-queue code so that notification types other
than NOTFIY_NMI can use it.
This patch moves code around ... and makes the following trivial changes:
* Adds WANT_NMI_ESTATUS_QUEUE to allow this code to be built without
CONFIG_HAVE_ACPI_APEI_NMI. This symbol later comes to mean NOTIFY_NMI,
which would only be selected by x86.
* Freshen the dated comment above ghes_estatus_llist. printk() is no
longer the issue, its the helpers like memory_failure_queue() that
still aren't nmi safe.
If anyone prefers I can split this so these two non-code changes are a
separate patch.
Not-signed-off: James Morse <james.morse@xxxxxxx>
---
drivers/acpi/apei/ghes.c | 281 +++++++++++++++++++++++++----------------------
1 file changed, 148 insertions(+), 133 deletions(-)
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 6402f7fad3bb..fef59ca1f7a7 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -59,6 +59,10 @@
#define GHES_PFX "GHES: "
+#ifdef CONFIG_HAVE_ACPI_APEI_NMI
+#define WANT_NMI_ESTATUS_QUEUE 1
+#endif
+
#define GHES_ESTATUS_MAX_SIZE 65536
#define GHES_ESOURCE_PREALLOC_MAX_SIZE 65536
@@ -529,6 +533,16 @@ static int ghes_print_estatus(const char *pfx,
return 0;
}
+static void __ghes_panic(struct ghes *ghes)
+{
+ __ghes_print_estatus(KERN_EMERG, ghes->generic, ghes->estatus);
+
+ /* reboot to log the error! */
+ if (!panic_timeout)
+ panic_timeout = ghes_panic_timeout;
+ panic("Fatal hardware error!");
+}
+
/*
* GHES error status reporting throttle, to report more kinds of
* errors, instead of just most frequently occurred errors.
@@ -656,6 +670,138 @@ static void ghes_estatus_cache_add(
rcu_read_unlock();
}
+#ifdef WANT_NMI_ESTATUS_QUEUE
+/*
+ * While printk() now has an in_nmi() path, the handling for CPER records
+ * does not. For example, memory_failure_queue() takes spinlocks and calls
+ * schedule_work_on().
+ *
+ * So in any NMI-like handler, we allocate required memory from lock-less
+ * memory allocator (ghes_estatus_pool), save estatus into it, put them into
+ * lock-less list (ghes_estatus_llist), then delay printk into IRQ context via
+ * irq_work (ghes_proc_irq_work). ghes_estatus_size_request record
+ * required pool size by all NMI error source.
+ *
+ * Memory from the ghes_estatus_pool is also used with the ghes_estatus_cache
+ * to suppress frequent messages.
+ */
+static struct llist_head ghes_estatus_llist;
+static struct irq_work ghes_proc_irq_work;
+
+static void ghes_print_queued_estatus(void)
+{
+ struct llist_node *llnode;
+ struct ghes_estatus_node *estatus_node;
+ struct acpi_hest_generic *generic;
+ struct acpi_hest_generic_status *estatus;
+ u32 len, node_len;
+
+ llnode = llist_del_all(&ghes_estatus_llist);
+ /*
+ * Because the time order of estatus in list is reversed,
+ * revert it back to proper order.
+ */
+ llnode = llist_reverse_order(llnode);
+ while (llnode) {
+ estatus_node = llist_entry(llnode, struct ghes_estatus_node,
+ llnode);
+ estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
+ len = cper_estatus_len(estatus);
+ node_len = GHES_ESTATUS_NODE_LEN(len);
+ generic = estatus_node->generic;
+ ghes_print_estatus(NULL, generic, estatus);
+ llnode = llnode->next;
+ }
+}
+
+/* Save estatus for further processing in IRQ context */
+static void __process_error(struct ghes *ghes)
+{
+#ifdef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
+ u32 len, node_len;
+ struct ghes_estatus_node *estatus_node;
+ struct acpi_hest_generic_status *estatus;
+
+ if (ghes_estatus_cached(ghes->estatus))
+ return;
+
+ len = cper_estatus_len(ghes->estatus);
+ node_len = GHES_ESTATUS_NODE_LEN(len);
+
+ estatus_node = (void *)gen_pool_alloc(ghes_estatus_pool, node_len);
+ if (!estatus_node)
+ return;
+
+ estatus_node->ghes = ghes;
+ estatus_node->generic = ghes->generic;
+ estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
+ memcpy(estatus, ghes->estatus, len);
+ llist_add(&estatus_node->llnode, &ghes_estatus_llist);
+#endif
+}
+
+static unsigned long ghes_esource_prealloc_size(
+ const struct acpi_hest_generic *generic)
+{
+ unsigned long block_length, prealloc_records, prealloc_size;
+
+ block_length = min_t(unsigned long, generic->error_block_length,
+ GHES_ESTATUS_MAX_SIZE);
+ prealloc_records = max_t(unsigned long,
+ generic->records_to_preallocate, 1);
+ prealloc_size = min_t(unsigned long, block_length * prealloc_records,
+ GHES_ESOURCE_PREALLOC_MAX_SIZE);
+
+ return prealloc_size;
+}
+
+static void ghes_estatus_pool_shrink(unsigned long len)
+{
+ ghes_estatus_pool_size_request -= PAGE_ALIGN(len);
+}
+
+static void ghes_proc_in_irq(struct irq_work *irq_work)
+{
+ struct llist_node *llnode, *next;
+ struct ghes_estatus_node *estatus_node;
+ struct acpi_hest_generic *generic;
+ struct acpi_hest_generic_status *estatus;
+ u32 len, node_len;
+
+ llnode = llist_del_all(&ghes_estatus_llist);
+ /*
+ * Because the time order of estatus in list is reversed,
+ * revert it back to proper order.
+ */
+ llnode = llist_reverse_order(llnode);
+ while (llnode) {
+ next = llnode->next;
+ estatus_node = llist_entry(llnode, struct ghes_estatus_node,
+ llnode);
+ estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
+ len = cper_estatus_len(estatus);
+ node_len = GHES_ESTATUS_NODE_LEN(len);
+ ghes_do_proc(estatus_node->ghes, estatus);
+ if (!ghes_estatus_cached(estatus)) {
+ generic = estatus_node->generic;
+ if (ghes_print_estatus(NULL, generic, estatus))
+ ghes_estatus_cache_add(generic, estatus);
+ }
+ gen_pool_free(ghes_estatus_pool, (unsigned long)estatus_node,
+ node_len);
+ llnode = next;
+ }
+}
+
+static void ghes_nmi_init_cxt(void)
+{
+ init_irq_work(&ghes_proc_irq_work, ghes_proc_in_irq);
+}
+
+#else
+static inline void ghes_nmi_init_cxt(void) { }
+#endif /* WANT_NMI_ESTATUS_QUEUE */
+
static int ghes_ack_error(struct acpi_hest_generic_v2 *gv2)
{
int rc;
@@ -671,16 +817,6 @@ static int ghes_ack_error(struct acpi_hest_generic_v2 *gv2)
return apei_write(val, &gv2->read_ack_register);
}
-static void __ghes_panic(struct ghes *ghes)
-{
- __ghes_print_estatus(KERN_EMERG, ghes->generic, ghes->estatus);
-
- /* reboot to log the error! */
- if (!panic_timeout)
- panic_timeout = ghes_panic_timeout;
- panic("Fatal hardware error!");
-}
-
static int ghes_proc(struct ghes *ghes)
{
int rc;
@@ -813,109 +949,13 @@ static inline void ghes_sea_remove(struct ghes *ghes) { }
#ifdef CONFIG_HAVE_ACPI_APEI_NMI
/*
- * printk is not safe in NMI context. So in NMI handler, we allocate
- * required memory from lock-less memory allocator
- * (ghes_estatus_pool), save estatus into it, put them into lock-less
- * list (ghes_estatus_llist), then delay printk into IRQ context via
- * irq_work (ghes_proc_irq_work). ghes_estatus_size_request record
- * required pool size by all NMI error source.
- */
-static struct llist_head ghes_estatus_llist;
-static struct irq_work ghes_proc_irq_work;
-
-/*
- * NMI may be triggered on any CPU, so ghes_in_nmi is used for
- * having only one concurrent reader.
+ * NOTIFY_NMI may be triggered on any CPU, so ghes_in_nmi is
+ * used for having only one concurrent reader.
*/
static atomic_t ghes_in_nmi = ATOMIC_INIT(0);
static LIST_HEAD(ghes_nmi);
-static void ghes_proc_in_irq(struct irq_work *irq_work)
-{
- struct llist_node *llnode, *next;
- struct ghes_estatus_node *estatus_node;
- struct acpi_hest_generic *generic;
- struct acpi_hest_generic_status *estatus;
- u32 len, node_len;
-
- llnode = llist_del_all(&ghes_estatus_llist);
- /*
- * Because the time order of estatus in list is reversed,
- * revert it back to proper order.
- */
- llnode = llist_reverse_order(llnode);
- while (llnode) {
- next = llnode->next;
- estatus_node = llist_entry(llnode, struct ghes_estatus_node,
- llnode);
- estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
- len = cper_estatus_len(estatus);
- node_len = GHES_ESTATUS_NODE_LEN(len);
- ghes_do_proc(estatus_node->ghes, estatus);
- if (!ghes_estatus_cached(estatus)) {
- generic = estatus_node->generic;
- if (ghes_print_estatus(NULL, generic, estatus))
- ghes_estatus_cache_add(generic, estatus);
- }
- gen_pool_free(ghes_estatus_pool, (unsigned long)estatus_node,
- node_len);
- llnode = next;
- }
-}
-
-static void ghes_print_queued_estatus(void)
-{
- struct llist_node *llnode;
- struct ghes_estatus_node *estatus_node;
- struct acpi_hest_generic *generic;
- struct acpi_hest_generic_status *estatus;
- u32 len, node_len;
-
- llnode = llist_del_all(&ghes_estatus_llist);
- /*
- * Because the time order of estatus in list is reversed,
- * revert it back to proper order.
- */
- llnode = llist_reverse_order(llnode);
- while (llnode) {
- estatus_node = llist_entry(llnode, struct ghes_estatus_node,
- llnode);
- estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
- len = cper_estatus_len(estatus);
- node_len = GHES_ESTATUS_NODE_LEN(len);
- generic = estatus_node->generic;
- ghes_print_estatus(NULL, generic, estatus);
- llnode = llnode->next;
- }
-}
-
-/* Save estatus for further processing in IRQ context */
-static void __process_error(struct ghes *ghes)
-{
-#ifdef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
- u32 len, node_len;
- struct ghes_estatus_node *estatus_node;
- struct acpi_hest_generic_status *estatus;
-
- if (ghes_estatus_cached(ghes->estatus))
- return;
-
- len = cper_estatus_len(ghes->estatus);
- node_len = GHES_ESTATUS_NODE_LEN(len);
-
- estatus_node = (void *)gen_pool_alloc(ghes_estatus_pool, node_len);
- if (!estatus_node)
- return;
-
- estatus_node->ghes = ghes;
- estatus_node->generic = ghes->generic;
- estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
- memcpy(estatus, ghes->estatus, len);
- llist_add(&estatus_node->llnode, &ghes_estatus_llist);
-#endif
-}
-
static int ghes_notify_nmi(unsigned int cmd, struct pt_regs *regs)
{
struct ghes *ghes;
@@ -954,26 +994,6 @@ static int ghes_notify_nmi(unsigned int cmd, struct pt_regs *regs)
return ret;
}
-static unsigned long ghes_esource_prealloc_size(
- const struct acpi_hest_generic *generic)
-{
- unsigned long block_length, prealloc_records, prealloc_size;
-
- block_length = min_t(unsigned long, generic->error_block_length,
- GHES_ESTATUS_MAX_SIZE);
- prealloc_records = max_t(unsigned long,
- generic->records_to_preallocate, 1);
- prealloc_size = min_t(unsigned long, block_length * prealloc_records,
- GHES_ESOURCE_PREALLOC_MAX_SIZE);
-
- return prealloc_size;
-}
-
-static void ghes_estatus_pool_shrink(unsigned long len)
-{
- ghes_estatus_pool_size_request -= PAGE_ALIGN(len);
-}
-
static void ghes_nmi_add(struct ghes *ghes)
{
unsigned long len;
@@ -1005,14 +1025,9 @@ static void ghes_nmi_remove(struct ghes *ghes)
ghes_estatus_pool_shrink(len);
}
-static void ghes_nmi_init_cxt(void)
-{
- init_irq_work(&ghes_proc_irq_work, ghes_proc_in_irq);
-}
#else /* CONFIG_HAVE_ACPI_APEI_NMI */
static inline void ghes_nmi_add(struct ghes *ghes) { }
static inline void ghes_nmi_remove(struct ghes *ghes) { }
-static inline void ghes_nmi_init_cxt(void) { }
#endif /* CONFIG_HAVE_ACPI_APEI_NMI */
static int ghes_probe(struct platform_device *ghes_dev)
--
2.15.1
--
To unsubscribe from this list: send the line "unsubscribe linux-acpi" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
