[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-ID: <20230919091543.794-1-shiju.jose@huawei.com>
Date: Tue, 19 Sep 2023 17:15:43 +0800
From: <shiju.jose@...wei.com>
To: <helgaas@...nel.org>, <rafael@...nel.org>, <lenb@...nel.org>,
<tony.luck@...el.com>, <james.morse@....com>, <bp@...en8.de>,
<ying.huang@...el.com>, <linux-acpi@...r.kernel.org>,
<linux-pci@...r.kernel.org>, <linux-kernel@...r.kernel.org>
CC: <linuxarm@...wei.com>, <jonathan.cameron@...wei.com>,
<tanxiaofei@...wei.com>, <prime.zeng@...ilicon.com>,
<shiju.jose@...wei.com>
Subject: [PATCH v2 1/1] ACPI / APEI: Fix for overwriting AER info when error status data has multiple sections
From: Shiju Jose <shiju.jose@...wei.com>
ghes_handle_aer() passes AER data to the PCI core for logging and
recovery by calling aer_recover_queue() with a pointer to struct
aer_capability_regs.
The problem was that aer_recover_queue() queues the pointer directly
without copying the aer_capability_regs data. The pointer was to
the ghes->estatus buffer, which could be reused before
aer_recover_work_func() reads the data.
To avoid this problem, allocate a new aer_capability_regs structure
from the ghes_estatus_pool, copy the AER data from the ghes->estatus
buffer into it, pass a pointer to the new struct to
aer_recover_queue(), and free it after aer_recover_work_func() has
processed it.
Reported-by: Bjorn Helgaas <helgaas@...nel.org>
Acked-by: Bjorn Helgaas <bhelgaas@...gle.com>
Signed-off-by: Shiju Jose <shiju.jose@...wei.com>
---
Changes from v1 to v2:
1. Updated patch description with the description Bjorn has suggested.
2. Add Acked-by: Bjorn Helgaas <bhelgaas@...gle.com>.
---
drivers/acpi/apei/ghes.c | 23 ++++++++++++++++++++++-
drivers/pci/pcie/aer.c | 10 ++++++++++
include/acpi/ghes.h | 1 +
3 files changed, 33 insertions(+), 1 deletion(-)
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index ef59d6ea16da..63ad0541db38 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -209,6 +209,20 @@ int ghes_estatus_pool_init(unsigned int num_ghes)
return -ENOMEM;
}
+/**
+ * ghes_estatus_pool_region_free - free previously allocated memory
+ * from the ghes_estatus_pool.
+ * @addr: address of memory to free.
+ * @size: size of memory to free.
+ *
+ * Returns none.
+ */
+void ghes_estatus_pool_region_free(unsigned long addr, u32 size)
+{
+ gen_pool_free(ghes_estatus_pool, addr, size);
+}
+EXPORT_SYMBOL_GPL(ghes_estatus_pool_region_free);
+
static int map_gen_v2(struct ghes *ghes)
{
return apei_map_generic_address(&ghes->generic_v2->read_ack_register);
@@ -564,6 +578,7 @@ static void ghes_handle_aer(struct acpi_hest_generic_data *gdata)
pcie_err->validation_bits & CPER_PCIE_VALID_AER_INFO) {
unsigned int devfn;
int aer_severity;
+ u8 *aer_info;
devfn = PCI_DEVFN(pcie_err->device_id.device,
pcie_err->device_id.function);
@@ -577,11 +592,17 @@ static void ghes_handle_aer(struct acpi_hest_generic_data *gdata)
if (gdata->flags & CPER_SEC_RESET)
aer_severity = AER_FATAL;
+ aer_info = (void *)gen_pool_alloc(ghes_estatus_pool,
+ sizeof(struct aer_capability_regs));
+ if (!aer_info)
+ return;
+ memcpy(aer_info, pcie_err->aer_info, sizeof(struct aer_capability_regs));
+
aer_recover_queue(pcie_err->device_id.segment,
pcie_err->device_id.bus,
devfn, aer_severity,
(struct aer_capability_regs *)
- pcie_err->aer_info);
+ aer_info);
}
#endif
}
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index e85ff946e8c8..388b614c11fd 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -29,6 +29,7 @@
#include <linux/kfifo.h>
#include <linux/slab.h>
#include <acpi/apei.h>
+#include <acpi/ghes.h>
#include <ras/ras_event.h>
#include "../pci.h"
@@ -996,6 +997,15 @@ static void aer_recover_work_func(struct work_struct *work)
continue;
}
cper_print_aer(pdev, entry.severity, entry.regs);
+ /*
+ * Memory for aer_capability_regs(entry.regs) is being allocated from the
+ * ghes_estatus_pool to protect it from overwriting when multiple sections
+ * are present in the error status. Thus free the same after processing
+ * the data.
+ */
+ ghes_estatus_pool_region_free((unsigned long)entry.regs,
+ sizeof(struct aer_capability_regs));
+
if (entry.severity == AER_NONFATAL)
pcie_do_recovery(pdev, pci_channel_io_normal,
aer_root_reset);
diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h
index 3c8bba9f1114..40d89e161076 100644
--- a/include/acpi/ghes.h
+++ b/include/acpi/ghes.h
@@ -78,6 +78,7 @@ static inline struct list_head *ghes_get_devices(void) { return NULL; }
#endif
int ghes_estatus_pool_init(unsigned int num_ghes);
+void ghes_estatus_pool_region_free(unsigned long addr, u32 size);
static inline int acpi_hest_get_version(struct acpi_hest_generic_data *gdata)
{
--
2.34.1
Powered by blists - more mailing lists