From 1543e317f1da31b75942316931e8f491a8920811 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Thu, 04 Jan 2024 10:08:02 +0000
Subject: [PATCH] disable FB
---
kernel/drivers/acpi/apei/ghes.c | 935 ++++++++++++++++++++++++++++++++++++---------------------
1 files changed, 587 insertions(+), 348 deletions(-)
diff --git a/kernel/drivers/acpi/apei/ghes.c b/kernel/drivers/acpi/apei/ghes.c
index be6d233..8678e16 100644
--- a/kernel/drivers/acpi/apei/ghes.c
+++ b/kernel/drivers/acpi/apei/ghes.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* APEI Generic Hardware Error Source support
*
@@ -14,17 +15,9 @@
*
* Copyright 2010,2011 Intel Corp.
* Author: Huang Ying <ying.huang@intel.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version
- * 2 as published by the Free Software Foundation;
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
*/
+#include <linux/arm_sdei.h>
#include <linux/kernel.h>
#include <linux/moduleparam.h>
#include <linux/init.h>
@@ -41,11 +34,13 @@
#include <linux/llist.h>
#include <linux/genalloc.h>
#include <linux/pci.h>
+#include <linux/pfn.h>
#include <linux/aer.h>
#include <linux/nmi.h>
#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>
@@ -84,6 +79,21 @@
((struct acpi_hest_generic_status *) \
((struct ghes_estatus_node *)(estatus_node) + 1))
+#define GHES_VENDOR_ENTRY_LEN(gdata_len) \
+ (sizeof(struct ghes_vendor_record_entry) + (gdata_len))
+#define GHES_GDATA_FROM_VENDOR_ENTRY(vendor_entry) \
+ ((struct acpi_hest_generic_data *) \
+ ((struct ghes_vendor_record_entry *)(vendor_entry) + 1))
+
+/*
+ * NMI-like notifications vary by architecture, before the compiler can prune
+ * unused static functions it needs a value for these enums.
+ */
+#ifndef CONFIG_ARM_SDE_INTERFACE
+#define FIX_APEI_GHES_SDEI_NORMAL __end_of_fixed_addresses
+#define FIX_APEI_GHES_SDEI_CRITICAL __end_of_fixed_addresses
+#endif
+
static inline bool is_hest_type_generic_v2(struct ghes *ghes)
{
return ghes->generic->header.type == ACPI_HEST_TYPE_GENERIC_ERROR_V2;
@@ -114,11 +124,16 @@
* handler, but general ioremap can not be used in atomic context, so
* the fixmap is used instead.
*
- * These 2 spinlocks are used to prevent the fixmap entries from being used
+ * This spinlock is used to prevent the fixmap entry from being used
* simultaneously.
*/
-static DEFINE_RAW_SPINLOCK(ghes_ioremap_lock_nmi);
-static DEFINE_SPINLOCK(ghes_ioremap_lock_irq);
+static DEFINE_SPINLOCK(ghes_notify_lock_irq);
+
+struct ghes_vendor_record_entry {
+ struct work_struct work;
+ int error_severity;
+ char vendor_record[];
+};
static struct gen_pool *ghes_estatus_pool;
static unsigned long ghes_estatus_pool_size_request;
@@ -128,82 +143,56 @@
static int ghes_panic_timeout __read_mostly = 30;
-static void __iomem *ghes_ioremap_pfn_nmi(u64 pfn)
+static void __iomem *ghes_map(u64 pfn, enum fixed_addresses fixmap_idx)
{
phys_addr_t paddr;
pgprot_t prot;
- paddr = pfn << PAGE_SHIFT;
+ paddr = PFN_PHYS(pfn);
prot = arch_apei_get_mem_attribute(paddr);
- __set_fixmap(FIX_APEI_GHES_NMI, paddr, prot);
+ __set_fixmap(fixmap_idx, paddr, prot);
- return (void __iomem *) fix_to_virt(FIX_APEI_GHES_NMI);
+ return (void __iomem *) __fix_to_virt(fixmap_idx);
}
-static void __iomem *ghes_ioremap_pfn_irq(u64 pfn)
+static void ghes_unmap(void __iomem *vaddr, enum fixed_addresses fixmap_idx)
{
- phys_addr_t paddr;
- pgprot_t prot;
+ int _idx = virt_to_fix((unsigned long)vaddr);
- paddr = pfn << PAGE_SHIFT;
- prot = arch_apei_get_mem_attribute(paddr);
- __set_fixmap(FIX_APEI_GHES_IRQ, paddr, prot);
-
- return (void __iomem *) fix_to_virt(FIX_APEI_GHES_IRQ);
+ WARN_ON_ONCE(fixmap_idx != _idx);
+ clear_fixmap(fixmap_idx);
}
-static void ghes_iounmap_nmi(void)
+int ghes_estatus_pool_init(unsigned int num_ghes)
{
- clear_fixmap(FIX_APEI_GHES_NMI);
-}
+ unsigned long addr, len;
+ int rc;
-static void ghes_iounmap_irq(void)
-{
- clear_fixmap(FIX_APEI_GHES_IRQ);
-}
-
-static int ghes_estatus_pool_init(void)
-{
ghes_estatus_pool = gen_pool_create(GHES_ESTATUS_POOL_MIN_ALLOC_ORDER, -1);
if (!ghes_estatus_pool)
return -ENOMEM;
- return 0;
-}
-static void ghes_estatus_pool_free_chunk(struct gen_pool *pool,
- struct gen_pool_chunk *chunk,
- void *data)
-{
- vfree((void *)chunk->start_addr);
-}
+ len = GHES_ESTATUS_CACHE_AVG_SIZE * GHES_ESTATUS_CACHE_ALLOCED_MAX;
+ len += (num_ghes * GHES_ESOURCE_PREALLOC_MAX_SIZE);
-static void ghes_estatus_pool_exit(void)
-{
- gen_pool_for_each_chunk(ghes_estatus_pool,
- ghes_estatus_pool_free_chunk, NULL);
- gen_pool_destroy(ghes_estatus_pool);
-}
-
-static int ghes_estatus_pool_expand(unsigned long len)
-{
- unsigned long size, addr;
-
- ghes_estatus_pool_size_request += PAGE_ALIGN(len);
- size = gen_pool_size(ghes_estatus_pool);
- if (size >= ghes_estatus_pool_size_request)
- return 0;
-
+ ghes_estatus_pool_size_request = PAGE_ALIGN(len);
addr = (unsigned long)vmalloc(PAGE_ALIGN(len));
if (!addr)
- return -ENOMEM;
+ goto err_pool_alloc;
- /*
- * New allocation must be visible in all pgd before it can be found by
- * an NMI allocating from the pool.
- */
- vmalloc_sync_mappings();
+ rc = gen_pool_add(ghes_estatus_pool, addr, PAGE_ALIGN(len), -1);
+ if (rc)
+ goto err_pool_add;
- return gen_pool_add(ghes_estatus_pool, addr, PAGE_ALIGN(len), -1);
+ return 0;
+
+err_pool_add:
+ vfree((void *)addr);
+
+err_pool_alloc:
+ gen_pool_destroy(ghes_estatus_pool);
+
+ return -ENOMEM;
}
static int map_gen_v2(struct ghes *ghes)
@@ -214,6 +203,21 @@
static void unmap_gen_v2(struct ghes *ghes)
{
apei_unmap_generic_address(&ghes->generic_v2->read_ack_register);
+}
+
+static void ghes_ack_error(struct acpi_hest_generic_v2 *gv2)
+{
+ int rc;
+ u64 val = 0;
+
+ rc = apei_read(&val, &gv2->read_ack_register);
+ if (rc)
+ return;
+
+ val &= gv2->read_ack_preserve << gv2->read_ack_register.bit_offset;
+ val |= gv2->read_ack_write << gv2->read_ack_register.bit_offset;
+
+ apei_write(val, &gv2->read_ack_register);
}
static struct ghes *ghes_new(struct acpi_hest_generic *generic)
@@ -238,10 +242,10 @@
goto err_unmap_read_ack_addr;
error_block_length = generic->error_block_length;
if (error_block_length > GHES_ESTATUS_MAX_SIZE) {
- pr_warning(FW_WARN GHES_PFX
- "Error status block length is too long: %u for "
- "generic hardware error source: %d.\n",
- error_block_length, generic->header.source_id);
+ pr_warn(FW_WARN GHES_PFX
+ "Error status block length is too long: %u for "
+ "generic hardware error source: %d.\n",
+ error_block_length, generic->header.source_id);
error_block_length = GHES_ESTATUS_MAX_SIZE;
}
ghes->estatus = kmalloc(error_block_length, GFP_KERNEL);
@@ -288,23 +292,16 @@
}
static void ghes_copy_tofrom_phys(void *buffer, u64 paddr, u32 len,
- int from_phys)
+ int from_phys,
+ enum fixed_addresses fixmap_idx)
{
void __iomem *vaddr;
- unsigned long flags = 0;
- int in_nmi = in_nmi();
u64 offset;
u32 trunk;
while (len > 0) {
offset = paddr - (paddr & PAGE_MASK);
- if (in_nmi) {
- raw_spin_lock(&ghes_ioremap_lock_nmi);
- vaddr = ghes_ioremap_pfn_nmi(paddr >> PAGE_SHIFT);
- } else {
- spin_lock_irqsave(&ghes_ioremap_lock_irq, flags);
- vaddr = ghes_ioremap_pfn_irq(paddr >> PAGE_SHIFT);
- }
+ vaddr = ghes_map(PHYS_PFN(paddr), fixmap_idx);
trunk = PAGE_SIZE - offset;
trunk = min(trunk, len);
if (from_phys)
@@ -314,92 +311,164 @@
len -= trunk;
paddr += trunk;
buffer += trunk;
- if (in_nmi) {
- ghes_iounmap_nmi();
- raw_spin_unlock(&ghes_ioremap_lock_nmi);
- } else {
- ghes_iounmap_irq();
- spin_unlock_irqrestore(&ghes_ioremap_lock_irq, flags);
- }
+ ghes_unmap(vaddr, fixmap_idx);
}
}
-static int ghes_read_estatus(struct ghes *ghes, int silent)
+/* Check the top-level record header has an appropriate size. */
+static int __ghes_check_estatus(struct ghes *ghes,
+ struct acpi_hest_generic_status *estatus)
+{
+ u32 len = cper_estatus_len(estatus);
+
+ if (len < sizeof(*estatus)) {
+ pr_warn_ratelimited(FW_WARN GHES_PFX "Truncated error status block!\n");
+ return -EIO;
+ }
+
+ if (len > ghes->generic->error_block_length) {
+ pr_warn_ratelimited(FW_WARN GHES_PFX "Invalid error status block length!\n");
+ return -EIO;
+ }
+
+ if (cper_estatus_check_header(estatus)) {
+ pr_warn_ratelimited(FW_WARN GHES_PFX "Invalid CPER header!\n");
+ return -EIO;
+ }
+
+ return 0;
+}
+
+/* Read the CPER block, returning its address, and header in estatus. */
+static int __ghes_peek_estatus(struct ghes *ghes,
+ struct acpi_hest_generic_status *estatus,
+ u64 *buf_paddr, enum fixed_addresses fixmap_idx)
{
struct acpi_hest_generic *g = ghes->generic;
- u64 buf_paddr;
- u32 len;
int rc;
- rc = apei_read(&buf_paddr, &g->error_status_address);
+ rc = apei_read(buf_paddr, &g->error_status_address);
if (rc) {
- if (!silent && printk_ratelimit())
- pr_warning(FW_WARN GHES_PFX
+ *buf_paddr = 0;
+ pr_warn_ratelimited(FW_WARN GHES_PFX
"Failed to read error status block address for hardware error source: %d.\n",
g->header.source_id);
return -EIO;
}
+ if (!*buf_paddr)
+ return -ENOENT;
+
+ ghes_copy_tofrom_phys(estatus, *buf_paddr, sizeof(*estatus), 1,
+ fixmap_idx);
+ if (!estatus->block_status) {
+ *buf_paddr = 0;
+ return -ENOENT;
+ }
+
+ return 0;
+}
+
+static int __ghes_read_estatus(struct acpi_hest_generic_status *estatus,
+ u64 buf_paddr, enum fixed_addresses fixmap_idx,
+ size_t buf_len)
+{
+ ghes_copy_tofrom_phys(estatus, buf_paddr, buf_len, 1, fixmap_idx);
+ if (cper_estatus_check(estatus)) {
+ pr_warn_ratelimited(FW_WARN GHES_PFX
+ "Failed to read error status block!\n");
+ return -EIO;
+ }
+
+ return 0;
+}
+
+static int ghes_read_estatus(struct ghes *ghes,
+ struct acpi_hest_generic_status *estatus,
+ u64 *buf_paddr, enum fixed_addresses fixmap_idx)
+{
+ int rc;
+
+ rc = __ghes_peek_estatus(ghes, estatus, buf_paddr, fixmap_idx);
+ if (rc)
+ return rc;
+
+ rc = __ghes_check_estatus(ghes, estatus);
+ if (rc)
+ return rc;
+
+ return __ghes_read_estatus(estatus, *buf_paddr, fixmap_idx,
+ cper_estatus_len(estatus));
+}
+
+static void ghes_clear_estatus(struct ghes *ghes,
+ struct acpi_hest_generic_status *estatus,
+ u64 buf_paddr, enum fixed_addresses fixmap_idx)
+{
+ estatus->block_status = 0;
+
if (!buf_paddr)
- return -ENOENT;
-
- ghes_copy_tofrom_phys(ghes->estatus, buf_paddr,
- sizeof(*ghes->estatus), 1);
- if (!ghes->estatus->block_status)
- return -ENOENT;
-
- ghes->buffer_paddr = buf_paddr;
- ghes->flags |= GHES_TO_CLEAR;
-
- rc = -EIO;
- len = cper_estatus_len(ghes->estatus);
- if (len < sizeof(*ghes->estatus))
- goto err_read_block;
- if (len > ghes->generic->error_block_length)
- goto err_read_block;
- if (cper_estatus_check_header(ghes->estatus))
- goto err_read_block;
- ghes_copy_tofrom_phys(ghes->estatus + 1,
- buf_paddr + sizeof(*ghes->estatus),
- len - sizeof(*ghes->estatus), 1);
- if (cper_estatus_check(ghes->estatus))
- goto err_read_block;
- rc = 0;
-
-err_read_block:
- if (rc && !silent && printk_ratelimit())
- pr_warning(FW_WARN GHES_PFX
- "Failed to read error status block!\n");
- return rc;
-}
-
-static void ghes_clear_estatus(struct ghes *ghes)
-{
- ghes->estatus->block_status = 0;
- if (!(ghes->flags & GHES_TO_CLEAR))
return;
- ghes_copy_tofrom_phys(ghes->estatus, ghes->buffer_paddr,
- sizeof(ghes->estatus->block_status), 0);
- ghes->flags &= ~GHES_TO_CLEAR;
+
+ ghes_copy_tofrom_phys(estatus, buf_paddr,
+ sizeof(estatus->block_status), 0,
+ fixmap_idx);
+
+ /*
+ * GHESv2 type HEST entries introduce support for error acknowledgment,
+ * so only acknowledge the error if this support is present.
+ */
+ if (is_hest_type_generic_v2(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)
{
-#ifdef CONFIG_ACPI_APEI_MEMORY_FAILURE
+ 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);
+ if (IS_ENABLED(CONFIG_ACPI_APEI_MEMORY_FAILURE))
+ 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_do_memory_failure(u64 physical_addr, int flags)
+{
unsigned long pfn;
+
+ if (!IS_ENABLED(CONFIG_ACPI_APEI_MEMORY_FAILURE))
+ return false;
+
+ pfn = PHYS_PFN(physical_addr);
+ if (!pfn_valid(pfn)) {
+ pr_warn_ratelimited(FW_WARN GHES_PFX
+ "Invalid address in generic error data: %#llx\n",
+ physical_addr);
+ return false;
+ }
+
+ memory_failure_queue(pfn, flags);
+ return true;
+}
+
+static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata,
+ int sev)
+{
int flags = -1;
int sec_sev = ghes_severity(gdata->error_severity);
struct cper_sec_mem_err *mem_err = acpi_hest_get_payload(gdata);
if (!(mem_err->validation_bits & CPER_MEM_VALID_PA))
- return;
-
- 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 */
if (sec_sev == GHES_SEV_CORRECTED &&
@@ -409,8 +478,53 @@
flags = 0;
if (flags != -1)
- memory_failure_queue(pfn, flags);
-#endif
+ return ghes_do_memory_failure(mem_err->physical_addr, flags);
+
+ return false;
+}
+
+static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata, int sev)
+{
+ struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata);
+ bool queued = false;
+ int sec_sev, i;
+ char *p;
+
+ log_arm_hw_error(err);
+
+ sec_sev = ghes_severity(gdata->error_severity);
+ if (sev != GHES_SEV_RECOVERABLE || sec_sev != GHES_SEV_RECOVERABLE)
+ return false;
+
+ p = (char *)(err + 1);
+ for (i = 0; i < err->err_info_num; i++) {
+ struct cper_arm_err_info *err_info = (struct cper_arm_err_info *)p;
+ bool is_cache = (err_info->type == CPER_ARM_CACHE_ERROR);
+ bool has_pa = (err_info->validation_bits & CPER_ARM_INFO_VALID_PHYSICAL_ADDR);
+ const char *error_type = "unknown error";
+
+ /*
+ * The field (err_info->error_info & BIT(26)) is fixed to set to
+ * 1 in some old firmware of HiSilicon Kunpeng920. We assume that
+ * firmware won't mix corrected errors in an uncorrected section,
+ * and don't filter out 'corrected' error here.
+ */
+ if (is_cache && has_pa) {
+ queued = ghes_do_memory_failure(err_info->physical_fault_addr, 0);
+ p += err_info->length;
+ continue;
+ }
+
+ if (err_info->type < ARRAY_SIZE(cper_proc_error_type_strs))
+ error_type = cper_proc_error_type_strs[err_info->type];
+
+ pr_warn_ratelimited(FW_WARN GHES_PFX
+ "Unhandled processor error type: %s\n",
+ error_type);
+ p += err_info->length;
+ }
+
+ return queued;
}
/*
@@ -458,14 +572,65 @@
#endif
}
-static void ghes_do_proc(struct ghes *ghes,
+static BLOCKING_NOTIFIER_HEAD(vendor_record_notify_list);
+
+int ghes_register_vendor_record_notifier(struct notifier_block *nb)
+{
+ return blocking_notifier_chain_register(&vendor_record_notify_list, nb);
+}
+EXPORT_SYMBOL_GPL(ghes_register_vendor_record_notifier);
+
+void ghes_unregister_vendor_record_notifier(struct notifier_block *nb)
+{
+ blocking_notifier_chain_unregister(&vendor_record_notify_list, nb);
+}
+EXPORT_SYMBOL_GPL(ghes_unregister_vendor_record_notifier);
+
+static void ghes_vendor_record_work_func(struct work_struct *work)
+{
+ struct ghes_vendor_record_entry *entry;
+ struct acpi_hest_generic_data *gdata;
+ u32 len;
+
+ entry = container_of(work, struct ghes_vendor_record_entry, work);
+ gdata = GHES_GDATA_FROM_VENDOR_ENTRY(entry);
+
+ blocking_notifier_call_chain(&vendor_record_notify_list,
+ entry->error_severity, gdata);
+
+ len = GHES_VENDOR_ENTRY_LEN(acpi_hest_get_record_size(gdata));
+ gen_pool_free(ghes_estatus_pool, (unsigned long)entry, len);
+}
+
+static void ghes_defer_non_standard_event(struct acpi_hest_generic_data *gdata,
+ int sev)
+{
+ struct acpi_hest_generic_data *copied_gdata;
+ struct ghes_vendor_record_entry *entry;
+ u32 len;
+
+ len = GHES_VENDOR_ENTRY_LEN(acpi_hest_get_record_size(gdata));
+ entry = (void *)gen_pool_alloc(ghes_estatus_pool, len);
+ if (!entry)
+ return;
+
+ copied_gdata = GHES_GDATA_FROM_VENDOR_ENTRY(entry);
+ memcpy(copied_gdata, gdata, acpi_hest_get_record_size(gdata));
+ entry->error_severity = sev;
+
+ INIT_WORK(&entry->work, ghes_vendor_record_work_func);
+ schedule_work(&entry->work);
+}
+
+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;
guid_t *sec_type;
- guid_t *fru_id = &NULL_UUID_LE;
+ const guid_t *fru_id = &guid_null;
char *fru_text = "";
+ bool queued = false;
sev = ghes_severity(estatus->error_severity);
apei_estatus_for_each_section(estatus, gdata) {
@@ -483,23 +648,24 @@
ghes_edac_report_mem_error(sev, mem_err);
arch_apei_report_mem_error(sev, mem_err);
- ghes_handle_memory_failure(gdata, sev);
+ queued = ghes_handle_memory_failure(gdata, sev);
}
else if (guid_equal(sec_type, &CPER_SEC_PCIE)) {
ghes_handle_aer(gdata);
}
else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) {
- struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata);
-
- log_arm_hw_error(err);
+ queued = ghes_handle_arm_hw_error(gdata, sev);
} else {
void *err = acpi_hest_get_payload(gdata);
+ ghes_defer_non_standard_event(gdata, sev);
log_non_standard_event(sec_type, fru_id, fru_text,
sec_sev, err,
gdata->error_data_length);
}
}
+
+ return queued;
}
static void __ghes_print_estatus(const char *pfx,
@@ -671,26 +837,13 @@
rcu_read_unlock();
}
-static int ghes_ack_error(struct acpi_hest_generic_v2 *gv2)
+static void __ghes_panic(struct ghes *ghes,
+ struct acpi_hest_generic_status *estatus,
+ u64 buf_paddr, enum fixed_addresses fixmap_idx)
{
- int rc;
- u64 val = 0;
+ __ghes_print_estatus(KERN_EMERG, ghes->generic, estatus);
- rc = apei_read(&val, &gv2->read_ack_register);
- if (rc)
- return rc;
-
- val &= gv2->read_ack_preserve << gv2->read_ack_register.bit_offset;
- val |= gv2->read_ack_write << gv2->read_ack_register.bit_offset;
-
- return apei_write(val, &gv2->read_ack_register);
-}
-
-static void __ghes_panic(struct ghes *ghes)
-{
- __ghes_print_estatus(KERN_EMERG, ghes->generic, ghes->estatus);
-
- ghes_clear_estatus(ghes);
+ ghes_clear_estatus(ghes, estatus, buf_paddr, fixmap_idx);
/* reboot to log the error! */
if (!panic_timeout)
@@ -700,34 +853,25 @@
static int ghes_proc(struct ghes *ghes)
{
+ struct acpi_hest_generic_status *estatus = ghes->estatus;
+ u64 buf_paddr;
int rc;
- rc = ghes_read_estatus(ghes, 0);
+ rc = ghes_read_estatus(ghes, estatus, &buf_paddr, FIX_APEI_GHES_IRQ);
if (rc)
goto out;
- if (ghes_severity(ghes->estatus->error_severity) >= GHES_SEV_PANIC) {
- __ghes_panic(ghes);
- }
+ if (ghes_severity(estatus->error_severity) >= GHES_SEV_PANIC)
+ __ghes_panic(ghes, estatus, buf_paddr, FIX_APEI_GHES_IRQ);
- if (!ghes_estatus_cached(ghes->estatus)) {
- if (ghes_print_estatus(NULL, ghes->generic, ghes->estatus))
- ghes_estatus_cache_add(ghes->generic, ghes->estatus);
+ if (!ghes_estatus_cached(estatus)) {
+ if (ghes_print_estatus(NULL, ghes->generic, estatus))
+ ghes_estatus_cache_add(ghes->generic, estatus);
}
- ghes_do_proc(ghes, ghes->estatus);
+ ghes_do_proc(ghes, estatus);
out:
- ghes_clear_estatus(ghes);
-
- if (rc == -ENOENT)
- return rc;
-
- /*
- * GHESv2 type HEST entries introduce support for error acknowledgment,
- * so only acknowledge the error if this support is present.
- */
- if (is_hest_type_generic_v2(ghes))
- return ghes_ack_error(ghes->generic_v2);
+ ghes_clear_estatus(ghes, estatus, buf_paddr, FIX_APEI_GHES_IRQ);
return rc;
}
@@ -738,8 +882,8 @@
unsigned long expire;
if (!g->notify.poll_interval) {
- pr_warning(FW_WARN GHES_PFX "Poll interval is 0 for generic hardware error source: %d, disabled.\n",
- g->header.source_id);
+ pr_warn(FW_WARN GHES_PFX "Poll interval is 0 for generic hardware error source: %d, disabled.\n",
+ g->header.source_id);
return;
}
expire = jiffies + msecs_to_jiffies(g->notify.poll_interval);
@@ -750,8 +894,11 @@
static void ghes_poll_func(struct timer_list *t)
{
struct ghes *ghes = from_timer(ghes, t, timer);
+ unsigned long flags;
+ spin_lock_irqsave(&ghes_notify_lock_irq, flags);
ghes_proc(ghes);
+ spin_unlock_irqrestore(&ghes_notify_lock_irq, flags);
if (!(ghes->flags & GHES_EXITING))
ghes_add_timer(ghes);
}
@@ -759,9 +906,12 @@
static irqreturn_t ghes_irq_func(int irq, void *data)
{
struct ghes *ghes = data;
+ unsigned long flags;
int rc;
+ spin_lock_irqsave(&ghes_notify_lock_irq, flags);
rc = ghes_proc(ghes);
+ spin_unlock_irqrestore(&ghes_notify_lock_irq, flags);
if (rc)
return IRQ_NONE;
@@ -772,14 +922,17 @@
void *data)
{
struct ghes *ghes;
+ unsigned long flags;
int ret = NOTIFY_DONE;
+ spin_lock_irqsave(&ghes_notify_lock_irq, flags);
rcu_read_lock();
list_for_each_entry_rcu(ghes, &ghes_hed, list) {
if (!ghes_proc(ghes))
ret = NOTIFY_OK;
}
rcu_read_unlock();
+ spin_unlock_irqrestore(&ghes_notify_lock_irq, flags);
return ret;
}
@@ -788,65 +941,19 @@
.notifier_call = ghes_notify_hed,
};
-#ifdef CONFIG_ACPI_APEI_SEA
-static LIST_HEAD(ghes_sea);
-
/*
- * Return 0 only if one of the SEA error sources successfully reported an error
- * record sent from the firmware.
- */
-int ghes_notify_sea(void)
-{
- struct ghes *ghes;
- int ret = -ENOENT;
-
- rcu_read_lock();
- list_for_each_entry_rcu(ghes, &ghes_sea, list) {
- if (!ghes_proc(ghes))
- ret = 0;
- }
- rcu_read_unlock();
- return ret;
-}
-
-static void ghes_sea_add(struct ghes *ghes)
-{
- mutex_lock(&ghes_list_mutex);
- list_add_rcu(&ghes->list, &ghes_sea);
- mutex_unlock(&ghes_list_mutex);
-}
-
-static void ghes_sea_remove(struct ghes *ghes)
-{
- mutex_lock(&ghes_list_mutex);
- list_del_rcu(&ghes->list);
- mutex_unlock(&ghes_list_mutex);
- synchronize_rcu();
-}
-#else /* CONFIG_ACPI_APEI_SEA */
-static inline void ghes_sea_add(struct ghes *ghes) { }
-static inline void ghes_sea_remove(struct ghes *ghes) { }
-#endif /* CONFIG_ACPI_APEI_SEA */
-
-#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.
+ * Handlers for CPER records may not be NMI safe. For example,
+ * memory_failure_queue() takes spinlocks and calls schedule_work_on().
+ * In any NMI-like handler, memory from ghes_estatus_pool is used to save
+ * estatus, and added to the ghes_estatus_llist. irq_work_queue() causes
+ * ghes_proc_in_irq() to run in IRQ context where each estatus in
+ * ghes_estatus_llist is processed.
+ *
+ * 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;
-
-/*
- * 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)
{
@@ -854,7 +961,9 @@
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);
/*
@@ -869,14 +978,26 @@
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) {
+ 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,
+ TWA_RESUME);
+ 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;
}
}
@@ -904,95 +1025,155 @@
}
}
-/* Save estatus for further processing in IRQ context */
-static void __process_error(struct ghes *ghes)
+static int ghes_in_nmi_queue_one_entry(struct ghes *ghes,
+ enum fixed_addresses fixmap_idx)
{
-#ifdef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
- u32 len, node_len;
+ struct acpi_hest_generic_status *estatus, tmp_header;
struct ghes_estatus_node *estatus_node;
- struct acpi_hest_generic_status *estatus;
+ u32 len, node_len;
+ u64 buf_paddr;
+ int sev, rc;
- if (ghes_estatus_cached(ghes->estatus))
- return;
+ if (!IS_ENABLED(CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG))
+ return -EOPNOTSUPP;
- len = cper_estatus_len(ghes->estatus);
+ rc = __ghes_peek_estatus(ghes, &tmp_header, &buf_paddr, fixmap_idx);
+ if (rc) {
+ ghes_clear_estatus(ghes, &tmp_header, buf_paddr, fixmap_idx);
+ return rc;
+ }
+
+ rc = __ghes_check_estatus(ghes, &tmp_header);
+ if (rc) {
+ ghes_clear_estatus(ghes, &tmp_header, buf_paddr, fixmap_idx);
+ return rc;
+ }
+
+ len = cper_estatus_len(&tmp_header);
node_len = GHES_ESTATUS_NODE_LEN(len);
-
estatus_node = (void *)gen_pool_alloc(ghes_estatus_pool, node_len);
if (!estatus_node)
- return;
+ return -ENOMEM;
estatus_node->ghes = ghes;
estatus_node->generic = ghes->generic;
+ estatus_node->task_work.func = NULL;
estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
- memcpy(estatus, ghes->estatus, len);
+
+ if (__ghes_read_estatus(estatus, buf_paddr, fixmap_idx, len)) {
+ ghes_clear_estatus(ghes, estatus, buf_paddr, fixmap_idx);
+ rc = -ENOENT;
+ goto no_work;
+ }
+
+ sev = ghes_severity(estatus->error_severity);
+ if (sev >= GHES_SEV_PANIC) {
+ ghes_print_queued_estatus();
+ __ghes_panic(ghes, estatus, buf_paddr, fixmap_idx);
+ }
+
+ ghes_clear_estatus(ghes, &tmp_header, buf_paddr, fixmap_idx);
+
+ /* This error has been reported before, don't process it again. */
+ if (ghes_estatus_cached(estatus))
+ goto no_work;
+
llist_add(&estatus_node->llnode, &ghes_estatus_llist);
-#endif
+
+ return rc;
+
+no_work:
+ gen_pool_free(ghes_estatus_pool, (unsigned long)estatus_node,
+ node_len);
+
+ return rc;
}
+
+static int ghes_in_nmi_spool_from_list(struct list_head *rcu_list,
+ enum fixed_addresses fixmap_idx)
+{
+ int ret = -ENOENT;
+ struct ghes *ghes;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(ghes, rcu_list, list) {
+ if (!ghes_in_nmi_queue_one_entry(ghes, fixmap_idx))
+ ret = 0;
+ }
+ rcu_read_unlock();
+
+ if (IS_ENABLED(CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG) && !ret)
+ irq_work_queue(&ghes_proc_irq_work);
+
+ return ret;
+}
+
+#ifdef CONFIG_ACPI_APEI_SEA
+static LIST_HEAD(ghes_sea);
+
+/*
+ * Return 0 only if one of the SEA error sources successfully reported an error
+ * record sent from the firmware.
+ */
+int ghes_notify_sea(void)
+{
+ static DEFINE_RAW_SPINLOCK(ghes_notify_lock_sea);
+ int rv;
+
+ raw_spin_lock(&ghes_notify_lock_sea);
+ rv = ghes_in_nmi_spool_from_list(&ghes_sea, FIX_APEI_GHES_SEA);
+ raw_spin_unlock(&ghes_notify_lock_sea);
+
+ return rv;
+}
+
+static void ghes_sea_add(struct ghes *ghes)
+{
+ mutex_lock(&ghes_list_mutex);
+ list_add_rcu(&ghes->list, &ghes_sea);
+ mutex_unlock(&ghes_list_mutex);
+}
+
+static void ghes_sea_remove(struct ghes *ghes)
+{
+ mutex_lock(&ghes_list_mutex);
+ list_del_rcu(&ghes->list);
+ mutex_unlock(&ghes_list_mutex);
+ synchronize_rcu();
+}
+#else /* CONFIG_ACPI_APEI_SEA */
+static inline void ghes_sea_add(struct ghes *ghes) { }
+static inline void ghes_sea_remove(struct ghes *ghes) { }
+#endif /* CONFIG_ACPI_APEI_SEA */
+
+#ifdef CONFIG_HAVE_ACPI_APEI_NMI
+/*
+ * 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 int ghes_notify_nmi(unsigned int cmd, struct pt_regs *regs)
{
- struct ghes *ghes;
- int sev, ret = NMI_DONE;
+ static DEFINE_RAW_SPINLOCK(ghes_notify_lock_nmi);
+ int ret = NMI_DONE;
if (!atomic_add_unless(&ghes_in_nmi, 1, 1))
return ret;
- list_for_each_entry_rcu(ghes, &ghes_nmi, list) {
- if (ghes_read_estatus(ghes, 1)) {
- ghes_clear_estatus(ghes);
- continue;
- } else {
- ret = NMI_HANDLED;
- }
+ raw_spin_lock(&ghes_notify_lock_nmi);
+ if (!ghes_in_nmi_spool_from_list(&ghes_nmi, FIX_APEI_GHES_NMI))
+ ret = NMI_HANDLED;
+ raw_spin_unlock(&ghes_notify_lock_nmi);
- sev = ghes_severity(ghes->estatus->error_severity);
- if (sev >= GHES_SEV_PANIC) {
- ghes_print_queued_estatus();
- __ghes_panic(ghes);
- }
-
- if (!(ghes->flags & GHES_TO_CLEAR))
- continue;
-
- __process_error(ghes);
- ghes_clear_estatus(ghes);
- }
-
-#ifdef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
- if (ret == NMI_HANDLED)
- irq_work_queue(&ghes_proc_irq_work);
-#endif
atomic_dec(&ghes_in_nmi);
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;
-
- len = ghes_esource_prealloc_size(ghes->generic);
- ghes_estatus_pool_expand(len);
mutex_lock(&ghes_list_mutex);
if (list_empty(&ghes_nmi))
register_nmi_handler(NMI_LOCAL, ghes_notify_nmi, 0, "ghes");
@@ -1002,8 +1183,6 @@
static void ghes_nmi_remove(struct ghes *ghes)
{
- unsigned long len;
-
mutex_lock(&ghes_list_mutex);
list_del_rcu(&ghes->list);
if (list_empty(&ghes_nmi))
@@ -1014,24 +1193,79 @@
* freed after NMI handler finishes.
*/
synchronize_rcu();
- len = ghes_esource_prealloc_size(ghes->generic);
- ghes_estatus_pool_shrink(len);
}
+#else /* CONFIG_HAVE_ACPI_APEI_NMI */
+static inline void ghes_nmi_add(struct ghes *ghes) { }
+static inline void ghes_nmi_remove(struct ghes *ghes) { }
+#endif /* CONFIG_HAVE_ACPI_APEI_NMI */
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_sdei_callback(struct ghes *ghes,
+ enum fixed_addresses fixmap_idx)
+{
+ if (!ghes_in_nmi_queue_one_entry(ghes, fixmap_idx)) {
+ irq_work_queue(&ghes_proc_irq_work);
+
+ return 0;
+ }
+
+ return -ENOENT;
+}
+
+static int ghes_sdei_normal_callback(u32 event_num, struct pt_regs *regs,
+ void *arg)
+{
+ static DEFINE_RAW_SPINLOCK(ghes_notify_lock_sdei_normal);
+ struct ghes *ghes = arg;
+ int err;
+
+ raw_spin_lock(&ghes_notify_lock_sdei_normal);
+ err = __ghes_sdei_callback(ghes, FIX_APEI_GHES_SDEI_NORMAL);
+ raw_spin_unlock(&ghes_notify_lock_sdei_normal);
+
+ return err;
+}
+
+static int ghes_sdei_critical_callback(u32 event_num, struct pt_regs *regs,
+ void *arg)
+{
+ static DEFINE_RAW_SPINLOCK(ghes_notify_lock_sdei_critical);
+ struct ghes *ghes = arg;
+ int err;
+
+ raw_spin_lock(&ghes_notify_lock_sdei_critical);
+ err = __ghes_sdei_callback(ghes, FIX_APEI_GHES_SDEI_CRITICAL);
+ raw_spin_unlock(&ghes_notify_lock_sdei_critical);
+
+ return err;
+}
+
+static int apei_sdei_register_ghes(struct ghes *ghes)
+{
+ if (!IS_ENABLED(CONFIG_ARM_SDE_INTERFACE))
+ return -EOPNOTSUPP;
+
+ return sdei_register_ghes(ghes, ghes_sdei_normal_callback,
+ ghes_sdei_critical_callback);
+}
+
+static int apei_sdei_unregister_ghes(struct ghes *ghes)
+{
+ if (!IS_ENABLED(CONFIG_ARM_SDE_INTERFACE))
+ return -EOPNOTSUPP;
+
+ return sdei_unregister_ghes(ghes);
+}
static int ghes_probe(struct platform_device *ghes_dev)
{
struct acpi_hest_generic *generic;
struct ghes *ghes = NULL;
+ unsigned long flags;
int rc = -EINVAL;
@@ -1062,22 +1296,28 @@
goto err;
}
break;
+ case ACPI_HEST_NOTIFY_SOFTWARE_DELEGATED:
+ if (!IS_ENABLED(CONFIG_ARM_SDE_INTERFACE)) {
+ pr_warn(GHES_PFX "Generic hardware error source: %d notified via SDE Interface is not supported!\n",
+ generic->header.source_id);
+ goto err;
+ }
+ break;
case ACPI_HEST_NOTIFY_LOCAL:
- pr_warning(GHES_PFX "Generic hardware error source: %d notified via local interrupt is not supported!\n",
- generic->header.source_id);
+ pr_warn(GHES_PFX "Generic hardware error source: %d notified via local interrupt is not supported!\n",
+ generic->header.source_id);
goto err;
default:
- pr_warning(FW_WARN GHES_PFX "Unknown notification type: %u for generic hardware error source: %d\n",
- generic->notify.type, generic->header.source_id);
+ pr_warn(FW_WARN GHES_PFX "Unknown notification type: %u for generic hardware error source: %d\n",
+ generic->notify.type, generic->header.source_id);
goto err;
}
rc = -EIO;
if (generic->error_block_length <
sizeof(struct acpi_hest_generic_status)) {
- pr_warning(FW_BUG GHES_PFX "Invalid error block length: %u for generic hardware error source: %d\n",
- generic->error_block_length,
- generic->header.source_id);
+ pr_warn(FW_BUG GHES_PFX "Invalid error block length: %u for generic hardware error source: %d\n",
+ generic->error_block_length, generic->header.source_id);
goto err;
}
ghes = ghes_new(generic);
@@ -1089,7 +1329,7 @@
switch (generic->notify.type) {
case ACPI_HEST_NOTIFY_POLLED:
- timer_setup(&ghes->timer, ghes_poll_func, TIMER_DEFERRABLE);
+ timer_setup(&ghes->timer, ghes_poll_func, 0);
ghes_add_timer(ghes);
break;
case ACPI_HEST_NOTIFY_EXTERNAL:
@@ -1125,6 +1365,11 @@
case ACPI_HEST_NOTIFY_NMI:
ghes_nmi_add(ghes);
break;
+ case ACPI_HEST_NOTIFY_SOFTWARE_DELEGATED:
+ rc = apei_sdei_register_ghes(ghes);
+ if (rc)
+ goto err;
+ break;
default:
BUG();
}
@@ -1134,7 +1379,9 @@
ghes_edac_register(ghes, &ghes_dev->dev);
/* Handle any pending errors right away */
+ spin_lock_irqsave(&ghes_notify_lock_irq, flags);
ghes_proc(ghes);
+ spin_unlock_irqrestore(&ghes_notify_lock_irq, flags);
return 0;
@@ -1148,6 +1395,7 @@
static int ghes_remove(struct platform_device *ghes_dev)
{
+ int rc;
struct ghes *ghes;
struct acpi_hest_generic *generic;
@@ -1180,6 +1428,11 @@
case ACPI_HEST_NOTIFY_NMI:
ghes_nmi_remove(ghes);
break;
+ case ACPI_HEST_NOTIFY_SOFTWARE_DELEGATED:
+ rc = apei_sdei_unregister_ghes(ghes);
+ if (rc)
+ return rc;
+ break;
default:
BUG();
break;
@@ -1204,42 +1457,35 @@
.remove = ghes_remove,
};
-static int __init ghes_init(void)
+void __init ghes_init(void)
{
int rc;
+ sdei_init();
+
if (acpi_disabled)
- return -ENODEV;
+ return;
switch (hest_disable) {
case HEST_NOT_FOUND:
- return -ENODEV;
+ return;
case HEST_DISABLED:
pr_info(GHES_PFX "HEST is not enabled!\n");
- return -EINVAL;
+ return;
default:
break;
}
if (ghes_disable) {
pr_info(GHES_PFX "GHES is not enabled!\n");
- return -EINVAL;
+ return;
}
ghes_nmi_init_cxt();
- rc = ghes_estatus_pool_init();
- if (rc)
- goto err;
-
- rc = ghes_estatus_pool_expand(GHES_ESTATUS_CACHE_AVG_SIZE *
- GHES_ESTATUS_CACHE_ALLOCED_MAX);
- if (rc)
- goto err_pool_exit;
-
rc = platform_driver_register(&ghes_platform_driver);
if (rc)
- goto err_pool_exit;
+ return;
rc = apei_osc_setup();
if (rc == 0 && osc_sb_apei_support_acked)
@@ -1250,11 +1496,4 @@
pr_info(GHES_PFX "APEI firmware first mode is enabled by APEI bit.\n");
else
pr_info(GHES_PFX "Failed to enable APEI firmware first mode.\n");
-
- return 0;
-err_pool_exit:
- ghes_estatus_pool_exit();
-err:
- return rc;
}
-device_initcall(ghes_init);
--
Gitblit v1.6.2