BACKPORT: ACPI / APEI: Kick the memory_failure() queue for synchronou…

…s errors

memory_failure() offlines or repairs pages of memory that have been
discovered to be corrupt. These may be detected by an external
component, (e.g. the memory controller), and notified via an IRQ.
In this case the work is queued as not all of memory_failure()s work
can happen in IRQ context.

If the error was detected as a result of user-space accessing a
corrupt memory location the CPU may take an abort instead. On arm64
this is a 'synchronous external abort', and on a firmware first
system it is replayed using NOTIFY_SEA.

This notification has NMI like properties, (it can interrupt
IRQ-masked code), so the memory_failure() work is queued. If we
return to user-space before the queued memory_failure() work is
processed, we will take the fault again. This loop may cause platform
firmware to exceed some threshold and reboot when Linux could have
recovered from this error.

For NMIlike notifications keep track of whether memory_failure() work
was queued, and make task_work pending to flush out the queue.
To save memory allocations, the task_work is allocated as part of
the ghes_estatus_node, and free()ing it back to the pool is deferred.

This patch is needed because Quicksilver firmware-first error handling
uses the SDEI notification type for communication between trusted
firmware and the OS. This adds needed NMI and SDEI functionality so
that the SDEI path in the kernel through APEI acts as an NMI and is
properly wired up to the APEI interfaces.

Backported from: https://patchwork.kernel.org/patch/10786981/

Signed-off-by: James Morse <[email protected]>
Signed-off-by: Tyler Baicar <[email protected]>

drivers/acpi/apei/ghes.c

@@ -47,6 +47,7 @@
 #include <linux/sched/clock.h>
 #include <linux/uuid.h>
 #include <linux/ras.h>
+#include <linux/task_work.h>
 
 #include <acpi/actbl1.h>
 #include <acpi/ghes.h>
@@ -399,23 +400,46 @@ static void ghes_clear_estatus(struct ghes *ghes,
 		ghes_ack_error(ghes->generic_v2);
 }
 
-static void ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, int sev)
+/*
+ * Called as task_work before returning to user-space.
+ * Ensure any queued work has been done before we return to the context that
+ * triggered the notification.
+ */
+static void ghes_kick_task_work(struct callback_head *head)
+{
+	struct acpi_hest_generic_status *estatus;
+	struct ghes_estatus_node *estatus_node;
+	u32 node_len;
+
+	estatus_node = container_of(head, struct ghes_estatus_node, task_work);
+	memory_failure_queue_kick(estatus_node->task_work_cpu);
+
+	estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
+	node_len = GHES_ESTATUS_NODE_LEN(cper_estatus_len(estatus));
+	gen_pool_free(ghes_estatus_pool, (unsigned long)estatus_node, node_len);
+}
+
+static bool ghes_handle_memory_failure(struct ghes *ghes,
+				       struct acpi_hest_generic_data *gdata,
+				       int sev)
 {
-#ifdef CONFIG_ACPI_APEI_MEMORY_FAILURE
 	unsigned long pfn;
 	int flags = -1;
 	int sec_sev = ghes_severity(gdata->error_severity);
 	struct cper_sec_mem_err *mem_err = acpi_hest_get_payload(gdata);
 
+	if (!IS_ENABLED(CONFIG_ACPI_APEI_MEMORY_FAILURE))
+		return false;
+
 	if (!(mem_err->validation_bits & CPER_MEM_VALID_PA))
-		return;
+		return false;
 
 	pfn = mem_err->physical_addr >> PAGE_SHIFT;
 	if (!pfn_valid(pfn)) {
 		pr_warn_ratelimited(FW_WARN GHES_PFX
 		"Invalid address in generic error data: %#llx\n",
 		mem_err->physical_addr);
-		return;
+		return false;
 	}
 
 	/* iff following two events can be handled properly by now */
@@ -425,9 +449,12 @@ static void ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, int
 	if (sev == GHES_SEV_RECOVERABLE && sec_sev == GHES_SEV_RECOVERABLE)
 		flags = 0;
 
-	if (flags != -1)
+	if (flags != -1) {
 		memory_failure_queue(pfn, flags);
-#endif
+		return true;
+	}
+
+	return false;
 }
 
 /*
@@ -475,11 +502,12 @@ static void ghes_handle_aer(struct acpi_hest_generic_data *gdata)
 #endif
 }
 
-static void ghes_do_proc(struct ghes *ghes,
+static bool ghes_do_proc(struct ghes *ghes,
 			 const struct acpi_hest_generic_status *estatus)
 {
 	int sev, sec_sev;
 	struct acpi_hest_generic_data *gdata;
+	bool work_queued = false;
 	guid_t *sec_type;
 	guid_t *fru_id = &NULL_UUID_LE;
 	char *fru_text = "";
@@ -500,7 +528,8 @@ static void ghes_do_proc(struct ghes *ghes,
 			ghes_edac_report_mem_error(sev, mem_err);
 
 			arch_apei_report_mem_error(sev, mem_err);
-			ghes_handle_memory_failure(gdata, sev);
+			if (ghes_handle_memory_failure(ghes, gdata, sev))
+				work_queued = true;
 		}
 		else if (guid_equal(sec_type, &CPER_SEC_PCIE)) {
 			ghes_handle_aer(gdata);
@@ -517,6 +546,8 @@ static void ghes_do_proc(struct ghes *ghes,
 					       gdata->error_data_length);
 		}
 	}
+
+	return work_queued;
 }
 
 static void __ghes_print_estatus(const char *pfx,
@@ -812,7 +843,9 @@ static void ghes_proc_in_irq(struct irq_work *irq_work)
 	struct ghes_estatus_node *estatus_node;
 	struct acpi_hest_generic *generic;
 	struct acpi_hest_generic_status *estatus;
+	bool task_work_pending;
 	u32 len, node_len;
+	int ret;
 
 	llnode = llist_del_all(&ghes_estatus_llist);
 	/*
@@ -827,14 +860,26 @@ static void ghes_proc_in_irq(struct irq_work *irq_work)
 		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);
+		task_work_pending = 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);
+
+		if (task_work_pending && current->mm != &init_mm) {
+			estatus_node->task_work.func = ghes_kick_task_work;
+			estatus_node->task_work_cpu = smp_processor_id();
+			ret = task_work_add(current, &estatus_node->task_work,
+					    true);
+			if (ret)
+				estatus_node->task_work.func = NULL;
+		}
+
+		if (!estatus_node->task_work.func)
+			gen_pool_free(ghes_estatus_pool,
+				      (unsigned long)estatus_node, node_len);
+
 		llnode = next;
 	}
 }
@@ -894,6 +939,7 @@ static int ghes_in_nmi_queue_one_entry(struct ghes *ghes,
 
 	estatus_node->ghes = ghes;
 	estatus_node->generic = ghes->generic;
+	estatus_node->task_work.func = NULL;
 	estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
 
 	if (__ghes_read_estatus(estatus, buf_paddr, fixmap_idx, len)) {

include/acpi/ghes.h

@@ -33,6 +33,9 @@ struct ghes_estatus_node {
 	struct llist_node llnode;
 	struct acpi_hest_generic *generic;
 	struct ghes *ghes;
+
+	int task_work_cpu;
+	struct callback_head task_work;
 };
 
 struct ghes_estatus_cache {