@@ -33,3 +33,33 @@ Description:
device cannot clear poison from the address, -ENXIO is returned.
The clear_poison attribute is only visible for devices
supporting the capability.
+
+What: /sys/kernel/debug/cxl/einj_types
+Date: January, 2024
+KernelVersion: v6.9
+Contact: linux-cxl@vger.kernel.org
+Description:
+ (RO) Prints the CXL protocol error types made available by
+ the platform in the format "0x<error number> <error type>".
+ The possible error types are (as of ACPI v6.5):
+ 0x1000 CXL.cache Protocol Correctable
+ 0x2000 CXL.cache Protocol Uncorrectable non-fatal
+ 0x4000 CXL.cache Protocol Uncorrectable fatal
+ 0x8000 CXL.mem Protocol Correctable
+ 0x10000 CXL.mem Protocol Uncorrectable non-fatal
+ 0x20000 CXL.mem Protocol Uncorrectable fatal
+
+ The <error number> can be written to einj_inject to inject
+ <error type> into a chosen dport.
+
+What: /sys/kernel/debug/cxl/$dport_dev/einj_inject
+Date: January, 2024
+KernelVersion: v6.9
+Contact: linux-cxl@vger.kernel.org
+Description:
+ (WO) Writing an integer to this file injects the corresponding
+ CXL protocol error into $dport_dev ($dport_dev will be a device
+ name from /sys/bus/pci/devices). The integer to type mapping for
+ injection can be found by reading from einj_types. If the dport
+ was enumerated in RCH mode, a CXL 1.1 error is injected, otherwise
+ a CXL 2.0 error is injected.
@@ -5291,6 +5291,7 @@ S: Maintained
F: drivers/cxl/
F: include/linux/cxl-event.h
F: include/uapi/linux/cxl_mem.h
+F: include/linux/einj-cxl.h
F: tools/testing/cxl/
COMPUTE EXPRESS LINK PMU (CPMU)
@@ -21,6 +21,7 @@
#include <linux/nmi.h>
#include <linux/delay.h>
#include <linux/mm.h>
+#include <linux/einj-cxl.h>
#include <linux/platform_device.h>
#include <asm/unaligned.h>
@@ -37,6 +38,20 @@
#define MEM_ERROR_MASK (ACPI_EINJ_MEMORY_CORRECTABLE | \
ACPI_EINJ_MEMORY_UNCORRECTABLE | \
ACPI_EINJ_MEMORY_FATAL)
+#ifndef ACPI_EINJ_CXL_CACHE_CORRECTABLE
+#define ACPI_EINJ_CXL_CACHE_CORRECTABLE BIT(12)
+#define ACPI_EINJ_CXL_CACHE_UNCORRECTABLE BIT(13)
+#define ACPI_EINJ_CXL_CACHE_FATAL BIT(14)
+#define ACPI_EINJ_CXL_MEM_CORRECTABLE BIT(15)
+#define ACPI_EINJ_CXL_MEM_UNCORRECTABLE BIT(16)
+#define ACPI_EINJ_CXL_MEM_FATAL BIT(17)
+#endif
+#define CXL_ERROR_MASK (ACPI_EINJ_CXL_CACHE_CORRECTABLE | \
+ ACPI_EINJ_CXL_CACHE_UNCORRECTABLE | \
+ ACPI_EINJ_CXL_CACHE_FATAL | \
+ ACPI_EINJ_CXL_MEM_CORRECTABLE | \
+ ACPI_EINJ_CXL_MEM_UNCORRECTABLE | \
+ ACPI_EINJ_CXL_MEM_FATAL)
/*
* ACPI version 5 provides a SET_ERROR_TYPE_WITH_ADDRESS action.
@@ -560,8 +575,11 @@ static int einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
if (type & ACPI5_VENDOR_BIT) {
if (vendor_flags != SETWA_FLAGS_MEM)
goto inject;
- } else if (!(type & MEM_ERROR_MASK) && !(flags & SETWA_FLAGS_MEM))
+ } else if (!(type & MEM_ERROR_MASK) && !(flags & SETWA_FLAGS_MEM)) {
goto inject;
+ } else if ((type & CXL_ERROR_MASK) && (flags & SETWA_FLAGS_MEM)) {
+ goto inject;
+ }
/*
* Disallow crazy address masks that give BIOS leeway to pick
@@ -613,13 +631,16 @@ static struct { u32 mask; const char *str; } const einj_error_type_string[] = {
{ BIT(9), "Platform Correctable" },
{ BIT(10), "Platform Uncorrectable non-fatal" },
{ BIT(11), "Platform Uncorrectable fatal"},
+ { BIT(31), "Vendor Defined Error Types" },
+};
+
+static struct { u32 mask; const char *str; } const einj_cxl_error_type_string[] = {
{ BIT(12), "CXL.cache Protocol Correctable" },
{ BIT(13), "CXL.cache Protocol Uncorrectable non-fatal" },
{ BIT(14), "CXL.cache Protocol Uncorrectable fatal" },
{ BIT(15), "CXL.mem Protocol Correctable" },
{ BIT(16), "CXL.mem Protocol Uncorrectable non-fatal" },
{ BIT(17), "CXL.mem Protocol Uncorrectable fatal" },
- { BIT(31), "Vendor Defined Error Types" },
};
static int available_error_type_show(struct seq_file *m, void *v)
@@ -640,29 +661,46 @@ static int available_error_type_show(struct seq_file *m, void *v)
DEFINE_SHOW_ATTRIBUTE(available_error_type);
-static int error_type_get(void *data, u64 *val)
+int einj_cxl_available_error_type_show(struct seq_file *m, void *v)
{
- *val = error_type;
+ int cxl_err, rc;
+ u32 available_error_type = 0;
+
+ if (!einj_initialized)
+ return -ENXIO;
+
+ rc = einj_get_available_error_type(&available_error_type);
+ if (rc)
+ return rc;
+
+ for (int pos = 0; pos < ARRAY_SIZE(einj_cxl_error_type_string); pos++) {
+ cxl_err = ACPI_EINJ_CXL_CACHE_CORRECTABLE << pos;
+
+ if (available_error_type & cxl_err)
+ seq_printf(m, "0x%08x\t%s\n",
+ einj_cxl_error_type_string[pos].mask,
+ einj_cxl_error_type_string[pos].str);
+ }
return 0;
}
+EXPORT_SYMBOL_NS_GPL(einj_cxl_available_error_type_show, CXL);
-static int error_type_set(void *data, u64 val)
+static int validate_error_type(u64 type)
{
+ u32 tval, vendor, available_error_type = 0;
int rc;
- u32 available_error_type = 0;
- u32 tval, vendor;
/* Only low 32 bits for error type are valid */
- if (val & GENMASK_ULL(63, 32))
+ if (type & GENMASK_ULL(63, 32))
return -EINVAL;
/*
* Vendor defined types have 0x80000000 bit set, and
* are not enumerated by ACPI_EINJ_GET_ERROR_TYPE
*/
- vendor = val & ACPI5_VENDOR_BIT;
- tval = val & 0x7fffffff;
+ vendor = type & ACPI5_VENDOR_BIT;
+ tval = type & GENMASK(30, 0);
/* Only one error type can be specified */
if (tval & (tval - 1))
@@ -671,9 +709,101 @@ static int error_type_set(void *data, u64 val)
rc = einj_get_available_error_type(&available_error_type);
if (rc)
return rc;
- if (!(val & available_error_type))
+ if (!(type & available_error_type))
return -EINVAL;
}
+
+ return 0;
+}
+
+static int cxl_dport_get_sbdf(struct pci_dev *dport_dev, u64 *sbdf)
+{
+ struct pci_bus *pbus;
+ struct pci_host_bridge *bridge;
+ u64 seg = 0, bus;
+
+ pbus = dport_dev->bus;
+ bridge = pci_find_host_bridge(pbus);
+
+ if (!bridge)
+ return -ENODEV;
+
+ if (bridge->domain_nr != PCI_DOMAIN_NR_NOT_SET)
+ seg = bridge->domain_nr;
+
+ bus = pbus->number;
+ *sbdf = (seg << 24) | (bus << 16) | dport_dev->devfn;
+
+ return 0;
+}
+
+static bool is_cxl_error_type(u64 type)
+{
+ return (type & CXL_ERROR_MASK) && (!(type & ACPI5_VENDOR_BIT));
+}
+
+int einj_cxl_inject_rch_error(u64 rcrb, u64 type)
+{
+ int rc;
+
+ if (!einj_initialized)
+ return -ENXIO;
+
+ /* Only CXL error types can be specified */
+ if (!is_cxl_error_type(type))
+ return -EINVAL;
+
+ rc = validate_error_type(type);
+ if (rc)
+ return rc;
+
+ return einj_error_inject(type, 0x2, rcrb, GENMASK_ULL(63, 12), 0, 0);
+}
+EXPORT_SYMBOL_NS_GPL(einj_cxl_inject_rch_error, CXL);
+
+int einj_cxl_inject_error(struct pci_dev *dport, u64 type)
+{
+ u64 param4 = 0;
+ int rc;
+
+ if (!einj_initialized)
+ return -ENXIO;
+
+ /* Only CXL error types can be specified */
+ if (!is_cxl_error_type(type))
+ return -EINVAL;
+
+ rc = validate_error_type(type);
+ if (rc)
+ return rc;
+
+ rc = cxl_dport_get_sbdf(dport, ¶m4);
+ if (rc)
+ return rc;
+
+ return einj_error_inject(type, 0x4, 0, 0, 0, param4);
+}
+EXPORT_SYMBOL_NS_GPL(einj_cxl_inject_error, CXL);
+
+static int error_type_get(void *data, u64 *val)
+{
+ *val = error_type;
+
+ return 0;
+}
+
+static int error_type_set(void *data, u64 val)
+{
+ int rc;
+
+ /* CXL error types have to be injected from cxl debugfs */
+ if (is_cxl_error_type(val))
+ return -EINVAL;
+
+ rc = validate_error_type(val);
+ if (rc)
+ return rc;
+
error_type = val;
return 0;
@@ -709,6 +839,12 @@ static int einj_check_table(struct acpi_table_einj *einj_tab)
return 0;
}
+bool einj_is_initialized(void)
+{
+ return einj_initialized;
+}
+EXPORT_SYMBOL_GPL(einj_is_initialized);
+
static int __init einj_probe(struct platform_device *pdev)
{
int rc;
@@ -157,4 +157,16 @@ config CXL_PMU
monitoring units and provide standard perf based interfaces.
If unsure say 'm'.
+
+config CXL_EINJ
+ bool "CXL Error INJection Support"
+ default ACPI_APEI_EINJ
+ depends on ACPI_APEI_EINJ = CXL_BUS
+ help
+ Support for CXL protocol Error INJection through debugfs/cxl.
+ Availability and which errors are supported is dependent on
+ the host platform. Look to ACPI v6.5 section 18.6.4 and kernel
+ EINJ documentation for more information.
+
+ If unsure say 'n'
endif
@@ -3,6 +3,7 @@
#include <linux/platform_device.h>
#include <linux/memregion.h>
#include <linux/workqueue.h>
+#include <linux/einj-cxl.h>
#include <linux/debugfs.h>
#include <linux/device.h>
#include <linux/module.h>
@@ -793,6 +794,39 @@ static int cxl_dport_setup_regs(struct device *host, struct cxl_dport *dport,
return rc;
}
+DEFINE_SHOW_ATTRIBUTE(einj_cxl_available_error_type);
+
+static int cxl_einj_inject(void *data, u64 type)
+{
+ struct cxl_dport *dport = data;
+
+ if (dport->rch)
+ return einj_cxl_inject_rch_error(dport->rcrb.base, type);
+
+ return einj_cxl_inject_error(to_pci_dev(dport->dport_dev), type);
+}
+DEFINE_DEBUGFS_ATTRIBUTE(cxl_einj_inject_fops, NULL, cxl_einj_inject, "%llx\n");
+
+static void cxl_debugfs_create_dport_dir(struct cxl_dport *dport)
+{
+ struct dentry *dir;
+
+ if (!einj_is_initialized())
+ return;
+
+ /*
+ * dport_dev needs to be a PCIe port for CXL 2.0+ ports because
+ * EINJ expects a dport SBDF to be specified for 2.0 error injection.
+ */
+ if (!dport->rch && !dev_is_pci(dport->dport_dev))
+ return;
+
+ dir = cxl_debugfs_create_dir(dev_name(dport->dport_dev));
+
+ debugfs_create_file("einj_inject", 0200, dir, dport,
+ &cxl_einj_inject_fops);
+}
+
static struct cxl_port *__devm_cxl_add_port(struct device *host,
struct device *uport_dev,
resource_size_t component_reg_phys,
@@ -1149,6 +1183,8 @@ __devm_cxl_add_dport(struct cxl_port *port, struct device *dport_dev,
if (dev_is_pci(dport_dev))
dport->link_latency = cxl_pci_get_latency(to_pci_dev(dport_dev));
+ cxl_debugfs_create_dport_dir(dport);
+
return dport;
}
@@ -2221,6 +2257,11 @@ static __init int cxl_core_init(void)
cxl_debugfs = debugfs_create_dir("cxl", NULL);
+ if (einj_is_initialized()) {
+ debugfs_create_file("einj_types", 0400, cxl_debugfs, NULL,
+ &einj_cxl_available_error_type_fops);
+ }
+
cxl_mbox_init();
rc = cxl_memdev_init();
new file mode 100644
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * CXL protocol Error INJection support.
+ *
+ * Copyright (c) 2023 Advanced Micro Devices, Inc.
+ * All Rights Reserved.
+ *
+ * Author: Ben Cheatham <benjamin.cheatham@amd.com>
+ */
+#ifndef CXL_EINJ_H
+#define CXL_EINJ_H
+
+#include <linux/pci.h>
+
+#if IS_ENABLED(CONFIG_ACPI_APEI_EINJ)
+int einj_cxl_available_error_type_show(struct seq_file *m, void *v);
+int einj_cxl_inject_error(struct pci_dev *dport_dev, u64 type);
+int einj_cxl_inject_rch_error(u64 rcrb, u64 type);
+bool einj_is_initialized(void);
+#else // !IS_ENABLED(CONFIG_ACPI_APEI_EINJ)
+static inline int einj_cxl_available_error_type_show(struct seq_file *m,
+ void *v)
+{
+ return -ENXIO;
+}
+
+static inline int einj_cxl_inject_error(struct pci_dev *dport_dev, u64 type)
+{
+ return -ENXIO;
+}
+
+static inline int einj_cxl_inject_rch_error(u64 rcrb, u64 type)
+{
+ return -ENXIO;
+}
+
+static inline bool einj_is_initialized(void) { return false; }
+#endif // CONFIG_ACPI_APEI_EINJ
+
+#endif // CXL_EINJ_H
Implement CXL helper functions in the EINJ module for getting/injecting available CXL protocol error types and export them to sysfs under kernel/debug/cxl. The kernel/debug/cxl/einj_types file will print the available CXL protocol errors in the same format as the available_error_types file provided by the EINJ module. The kernel/debug/cxl/$dport_dev/einj_inject is functionally the same as the error_type and error_inject files provided by the EINJ module, i.e.: writing an error type into $dport_dev/einj_inject will inject said error type into the CXL dport represented by $dport_dev. Signed-off-by: Ben Cheatham <Benjamin.Cheatham@amd.com> --- Documentation/ABI/testing/debugfs-cxl | 30 +++++ MAINTAINERS | 1 + drivers/acpi/apei/einj.c | 158 ++++++++++++++++++++++++-- drivers/cxl/Kconfig | 12 ++ drivers/cxl/core/port.c | 41 +++++++ include/linux/einj-cxl.h | 40 +++++++ 6 files changed, 271 insertions(+), 11 deletions(-) create mode 100644 include/linux/einj-cxl.h