aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--Documentation/ABI/testing/debugfs-cxl34
-rw-r--r--Documentation/ABI/testing/sysfs-bus-cxl34
-rw-r--r--Documentation/firmware-guide/acpi/apei/einj.rst34
-rw-r--r--MAINTAINERS1
-rw-r--r--drivers/acpi/apei/Kconfig13
-rw-r--r--drivers/acpi/apei/Makefile2
-rw-r--r--drivers/acpi/apei/apei-internal.h18
-rw-r--r--drivers/acpi/apei/einj-core.c (renamed from drivers/acpi/apei/einj.c)122
-rw-r--r--drivers/acpi/apei/einj-cxl.c113
-rw-r--r--drivers/acpi/numa/hmat.c83
-rw-r--r--drivers/acpi/numa/srat.c11
-rw-r--r--drivers/acpi/tables.c2
-rw-r--r--drivers/base/node.c7
-rw-r--r--drivers/cxl/acpi.c8
-rw-r--r--drivers/cxl/core/cdat.c170
-rw-r--r--drivers/cxl/core/core.h4
-rw-r--r--drivers/cxl/core/pci.c99
-rw-r--r--drivers/cxl/core/port.c86
-rw-r--r--drivers/cxl/core/region.c169
-rw-r--r--drivers/cxl/cxl.h15
-rw-r--r--drivers/cxl/cxlpci.h24
-rw-r--r--include/linux/acpi.h21
-rw-r--r--include/linux/einj-cxl.h44
-rw-r--r--include/linux/fw_table.h4
-rw-r--r--include/linux/memory.h1
-rw-r--r--include/linux/node.h18
-rw-r--r--lib/fw_table.c15
27 files changed, 1004 insertions, 148 deletions
diff --git a/Documentation/ABI/testing/debugfs-cxl b/Documentation/ABI/testing/debugfs-cxl
index fe61d372e3fac..c61f9b8139730 100644
--- a/Documentation/ABI/testing/debugfs-cxl
+++ b/Documentation/ABI/testing/debugfs-cxl
@@ -33,3 +33,37 @@ 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.
diff --git a/Documentation/ABI/testing/sysfs-bus-cxl b/Documentation/ABI/testing/sysfs-bus-cxl
index fff2581b80335..3f5627a1210a1 100644
--- a/Documentation/ABI/testing/sysfs-bus-cxl
+++ b/Documentation/ABI/testing/sysfs-bus-cxl
@@ -552,3 +552,37 @@ Description:
attribute is only visible for devices supporting the
capability. The retrieved errors are logged as kernel
events when cxl_poison event tracing is enabled.
+
+
+What: /sys/bus/cxl/devices/regionZ/accessY/read_bandwidth
+ /sys/bus/cxl/devices/regionZ/accessY/write_banwidth
+Date: Jan, 2024
+KernelVersion: v6.9
+Contact: linux-cxl@vger.kernel.org
+Description:
+ (RO) The aggregated read or write bandwidth of the region. The
+ number is the accumulated read or write bandwidth of all CXL memory
+ devices that contributes to the region in MB/s. It is
+ identical data that should appear in
+ /sys/devices/system/node/nodeX/accessY/initiators/read_bandwidth or
+ /sys/devices/system/node/nodeX/accessY/initiators/write_bandwidth.
+ See Documentation/ABI/stable/sysfs-devices-node. access0 provides
+ the number to the closest initiator and access1 provides the
+ number to the closest CPU.
+
+
+What: /sys/bus/cxl/devices/regionZ/accessY/read_latency
+ /sys/bus/cxl/devices/regionZ/accessY/write_latency
+Date: Jan, 2024
+KernelVersion: v6.9
+Contact: linux-cxl@vger.kernel.org
+Description:
+ (RO) The read or write latency of the region. The number is
+ the worst read or write latency of all CXL memory devices that
+ contributes to the region in nanoseconds. It is identical data
+ that should appear in
+ /sys/devices/system/node/nodeX/accessY/initiators/read_latency or
+ /sys/devices/system/node/nodeX/accessY/initiators/write_latency.
+ See Documentation/ABI/stable/sysfs-devices-node. access0 provides
+ the number to the closest initiator and access1 provides the
+ number to the closest CPU.
diff --git a/Documentation/firmware-guide/acpi/apei/einj.rst b/Documentation/firmware-guide/acpi/apei/einj.rst
index d6b61d22f5258..c52b9da08fa9a 100644
--- a/Documentation/firmware-guide/acpi/apei/einj.rst
+++ b/Documentation/firmware-guide/acpi/apei/einj.rst
@@ -32,6 +32,10 @@ configuration::
CONFIG_ACPI_APEI
CONFIG_ACPI_APEI_EINJ
+...and to (optionally) enable CXL protocol error injection set::
+
+ CONFIG_ACPI_APEI_EINJ_CXL
+
The EINJ user interface is in <debugfs mount point>/apei/einj.
The following files belong to it:
@@ -118,6 +122,24 @@ The following files belong to it:
this actually works depends on what operations the BIOS actually
includes in the trigger phase.
+CXL error types are supported from ACPI 6.5 onwards (given a CXL port
+is present). The EINJ user interface for CXL error types is at
+<debugfs mount point>/cxl. The following files belong to it:
+
+- einj_types:
+
+ Provides the same functionality as available_error_types above, but
+ for CXL error types
+
+- $dport_dev/einj_inject:
+
+ Injects a CXL error type into the CXL port represented by $dport_dev,
+ where $dport_dev is the name of the CXL port (usually a PCIe device name).
+ Error injections targeting a CXL 2.0+ port can use the legacy interface
+ under <debugfs mount point>/apei/einj, while CXL 1.1/1.0 port injections
+ must use this file.
+
+
BIOS versions based on the ACPI 4.0 specification have limited options
in controlling where the errors are injected. Your BIOS may support an
extension (enabled with the param_extension=1 module parameter, or boot
@@ -181,6 +203,18 @@ You should see something like this in dmesg::
[22715.834759] EDAC sbridge MC3: PROCESSOR 0:306e7 TIME 1422553404 SOCKET 0 APIC 0
[22716.616173] EDAC MC3: 1 CE memory read error on CPU_SrcID#0_Channel#0_DIMM#0 (channel:0 slot:0 page:0x12345 offset:0x0 grain:32 syndrome:0x0 - area:DRAM err_code:0001:0090 socket:0 channel_mask:1 rank:0)
+A CXL error injection example with $dport_dev=0000:e0:01.1::
+
+ # cd /sys/kernel/debug/cxl/
+ # ls
+ 0000:e0:01.1 0000:0c:00.0
+ # cat einj_types # See which errors can be injected
+ 0x00008000 CXL.mem Protocol Correctable
+ 0x00010000 CXL.mem Protocol Uncorrectable non-fatal
+ 0x00020000 CXL.mem Protocol Uncorrectable fatal
+ # cd 0000:e0:01.1 # Navigate to dport to inject into
+ # echo 0x8000 > einj_inject # Inject error
+
Special notes for injection into SGX enclaves:
There may be a separate BIOS setup option to enable SGX injection.
diff --git a/MAINTAINERS b/MAINTAINERS
index 40489f0fc08f8..be59443034d0e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5321,6 +5321,7 @@ M: Dan Williams <dan.j.williams@intel.com>
L: linux-cxl@vger.kernel.org
S: Maintained
F: drivers/cxl/
+F: include/linux/cxl-einj.h
F: include/linux/cxl-event.h
F: include/uapi/linux/cxl_mem.h
F: tools/testing/cxl/
diff --git a/drivers/acpi/apei/Kconfig b/drivers/acpi/apei/Kconfig
index 6b18f8bc7be35..3cfe7e7475f2f 100644
--- a/drivers/acpi/apei/Kconfig
+++ b/drivers/acpi/apei/Kconfig
@@ -60,6 +60,19 @@ config ACPI_APEI_EINJ
mainly used for debugging and testing the other parts of
APEI and some other RAS features.
+config ACPI_APEI_EINJ_CXL
+ bool "CXL Error INJection Support"
+ default ACPI_APEI_EINJ
+ depends on ACPI_APEI_EINJ
+ depends on CXL_BUS && CXL_BUS <= ACPI_APEI_EINJ
+ help
+ Support for CXL protocol Error INJection through debugfs/cxl.
+ Availability and which errors are supported is dependent on
+ the host platform. Look to ACPI v6.5 section 18.6.4 and kernel
+ EINJ documentation for more information.
+
+ If unsure say 'n'
+
config ACPI_APEI_ERST_DEBUG
tristate "APEI Error Record Serialization Table (ERST) Debug Support"
depends on ACPI_APEI
diff --git a/drivers/acpi/apei/Makefile b/drivers/acpi/apei/Makefile
index 4dfac2128737c..2c474e6477e12 100644
--- a/drivers/acpi/apei/Makefile
+++ b/drivers/acpi/apei/Makefile
@@ -2,6 +2,8 @@
obj-$(CONFIG_ACPI_APEI) += apei.o
obj-$(CONFIG_ACPI_APEI_GHES) += ghes.o
obj-$(CONFIG_ACPI_APEI_EINJ) += einj.o
+einj-y := einj-core.o
+einj-$(CONFIG_ACPI_APEI_EINJ_CXL) += einj-cxl.o
obj-$(CONFIG_ACPI_APEI_ERST_DEBUG) += erst-dbg.o
apei-y := apei-base.o hest.o erst.o bert.o
diff --git a/drivers/acpi/apei/apei-internal.h b/drivers/acpi/apei/apei-internal.h
index 67c2c3b959e15..cd2766c69d78d 100644
--- a/drivers/acpi/apei/apei-internal.h
+++ b/drivers/acpi/apei/apei-internal.h
@@ -130,4 +130,22 @@ static inline u32 cper_estatus_len(struct acpi_hest_generic_status *estatus)
}
int apei_osc_setup(void);
+
+int einj_get_available_error_type(u32 *type);
+int einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2, u64 param3,
+ u64 param4);
+int einj_cxl_rch_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
+ u64 param3, u64 param4);
+bool einj_is_cxl_error_type(u64 type);
+int einj_validate_error_type(u64 type);
+
+#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
+
#endif
diff --git a/drivers/acpi/apei/einj.c b/drivers/acpi/apei/einj-core.c
index 89fb9331c611e..66e7f529e92fc 100644
--- a/drivers/acpi/apei/einj.c
+++ b/drivers/acpi/apei/einj-core.c
@@ -21,6 +21,7 @@
#include <linux/nmi.h>
#include <linux/delay.h>
#include <linux/mm.h>
+#include <linux/platform_device.h>
#include <asm/unaligned.h>
#include "apei-internal.h"
@@ -36,6 +37,12 @@
#define MEM_ERROR_MASK (ACPI_EINJ_MEMORY_CORRECTABLE | \
ACPI_EINJ_MEMORY_UNCORRECTABLE | \
ACPI_EINJ_MEMORY_FATAL)
+#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.
@@ -137,6 +144,11 @@ static struct apei_exec_ins_type einj_ins_type[] = {
*/
static DEFINE_MUTEX(einj_mutex);
+/*
+ * Exported APIs use this flag to exit early if einj_probe() failed.
+ */
+bool einj_initialized __ro_after_init;
+
static void *einj_param;
static void einj_exec_ctx_init(struct apei_exec_context *ctx)
@@ -160,7 +172,7 @@ static int __einj_get_available_error_type(u32 *type)
}
/* Get error injection capabilities of the platform */
-static int einj_get_available_error_type(u32 *type)
+int einj_get_available_error_type(u32 *type)
{
int rc;
@@ -530,8 +542,8 @@ static int __einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
}
/* Inject the specified hardware error */
-static int einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
- u64 param3, u64 param4)
+int einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2, u64 param3,
+ u64 param4)
{
int rc;
u64 base_addr, size;
@@ -554,8 +566,17 @@ 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;
+ }
+
+ /*
+ * Injections targeting a CXL 1.0/1.1 port have to be injected
+ * via the einj_cxl_rch_error_inject() path as that does the proper
+ * validation of the given RCRB base (MMIO) address.
+ */
+ if (einj_is_cxl_error_type(type) && (flags & SETWA_FLAGS_MEM))
+ return -EINVAL;
/*
* Disallow crazy address masks that give BIOS leeway to pick
@@ -587,6 +608,21 @@ inject:
return rc;
}
+int einj_cxl_rch_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
+ u64 param3, u64 param4)
+{
+ int rc;
+
+ if (!(einj_is_cxl_error_type(type) && (flags & SETWA_FLAGS_MEM)))
+ return -EINVAL;
+
+ mutex_lock(&einj_mutex);
+ rc = __einj_error_inject(type, flags, param1, param2, param3, param4);
+ mutex_unlock(&einj_mutex);
+
+ return rc;
+}
+
static u32 error_type;
static u32 error_flags;
static u64 error_param1;
@@ -607,12 +643,6 @@ 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(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" },
};
@@ -641,22 +671,26 @@ static int error_type_get(void *data, u64 *val)
return 0;
}
-static int error_type_set(void *data, u64 val)
+bool einj_is_cxl_error_type(u64 type)
{
+ return (type & CXL_ERROR_MASK) && (!(type & ACPI5_VENDOR_BIT));
+}
+
+int einj_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))
@@ -665,9 +699,21 @@ 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 error_type_set(void *data, u64 val)
+{
+ int rc;
+
+ rc = einj_validate_error_type(val);
+ if (rc)
+ return rc;
+
error_type = val;
return 0;
@@ -703,21 +749,21 @@ static int einj_check_table(struct acpi_table_einj *einj_tab)
return 0;
}
-static int __init einj_init(void)
+static int __init einj_probe(struct platform_device *pdev)
{
int rc;
acpi_status status;
struct apei_exec_context ctx;
if (acpi_disabled) {
- pr_info("ACPI disabled.\n");
+ pr_debug("ACPI disabled.\n");
return -ENODEV;
}
status = acpi_get_table(ACPI_SIG_EINJ, 0,
(struct acpi_table_header **)&einj_tab);
if (status == AE_NOT_FOUND) {
- pr_warn("EINJ table not found.\n");
+ pr_debug("EINJ table not found.\n");
return -ENODEV;
} else if (ACPI_FAILURE(status)) {
pr_err("Failed to get EINJ table: %s\n",
@@ -805,7 +851,7 @@ err_put_table:
return rc;
}
-static void __exit einj_exit(void)
+static void __exit einj_remove(struct platform_device *pdev)
{
struct apei_exec_context ctx;
@@ -826,6 +872,40 @@ static void __exit einj_exit(void)
acpi_put_table((struct acpi_table_header *)einj_tab);
}
+static struct platform_device *einj_dev;
+static struct platform_driver einj_driver = {
+ .remove_new = einj_remove,
+ .driver = {
+ .name = "acpi-einj",
+ },
+};
+
+static int __init einj_init(void)
+{
+ struct platform_device_info einj_dev_info = {
+ .name = "acpi-einj",
+ .id = -1,
+ };
+ int rc;
+
+ einj_dev = platform_device_register_full(&einj_dev_info);
+ if (IS_ERR(einj_dev))
+ return PTR_ERR(einj_dev);
+
+ rc = platform_driver_probe(&einj_driver, einj_probe);
+ einj_initialized = rc == 0;
+
+ return 0;
+}
+
+static void __exit einj_exit(void)
+{
+ if (einj_initialized)
+ platform_driver_unregister(&einj_driver);
+
+ platform_device_del(einj_dev);
+}
+
module_init(einj_init);
module_exit(einj_exit);
diff --git a/drivers/acpi/apei/einj-cxl.c b/drivers/acpi/apei/einj-cxl.c
new file mode 100644
index 0000000000000..8b8be0c90709f
--- /dev/null
+++ b/drivers/acpi/apei/einj-cxl.c
@@ -0,0 +1,113 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * CXL Error INJection support. Used by CXL core to inject
+ * protocol errors into CXL ports.
+ *
+ * Copyright (C) 2023 Advanced Micro Devices, Inc.
+ *
+ * Author: Ben Cheatham <benjamin.cheatham@amd.com>
+ */
+#include <linux/einj-cxl.h>
+#include <linux/seq_file.h>
+#include <linux/pci.h>
+
+#include "apei-internal.h"
+
+/* Defined in einj-core.c */
+extern bool einj_initialized;
+
+static struct { u32 mask; const char *str; } const einj_cxl_error_type_string[] = {
+ { ACPI_EINJ_CXL_CACHE_CORRECTABLE, "CXL.cache Protocol Correctable" },
+ { ACPI_EINJ_CXL_CACHE_UNCORRECTABLE, "CXL.cache Protocol Uncorrectable non-fatal" },
+ { ACPI_EINJ_CXL_CACHE_FATAL, "CXL.cache Protocol Uncorrectable fatal" },
+ { ACPI_EINJ_CXL_MEM_CORRECTABLE, "CXL.mem Protocol Correctable" },
+ { ACPI_EINJ_CXL_MEM_UNCORRECTABLE, "CXL.mem Protocol Uncorrectable non-fatal" },
+ { ACPI_EINJ_CXL_MEM_FATAL, "CXL.mem Protocol Uncorrectable fatal" },
+};
+
+int einj_cxl_available_error_type_show(struct seq_file *m, void *v)
+{
+ int cxl_err, rc;
+ u32 available_error_type = 0;
+
+ 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 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;
+}
+
+int einj_cxl_inject_rch_error(u64 rcrb, u64 type)
+{
+ int rc;
+
+ /* Only CXL error types can be specified */
+ if (!einj_is_cxl_error_type(type))
+ return -EINVAL;
+
+ rc = einj_validate_error_type(type);
+ if (rc)
+ return rc;
+
+ return einj_cxl_rch_error_inject(type, 0x2, rcrb, GENMASK_ULL(63, 0),
+ 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;
+
+ /* Only CXL error types can be specified */
+ if (!einj_is_cxl_error_type(type))
+ return -EINVAL;
+
+ rc = einj_validate_error_type(type);
+ if (rc)
+ return rc;
+
+ rc = cxl_dport_get_sbdf(dport, &param4);
+ if (rc)
+ return rc;
+
+ return einj_error_inject(type, 0x4, 0, 0, 0, param4);
+}
+EXPORT_SYMBOL_NS_GPL(einj_cxl_inject_error, CXL);
+
+bool einj_cxl_is_initialized(void)
+{
+ return einj_initialized;
+}
+EXPORT_SYMBOL_NS_GPL(einj_cxl_is_initialized, CXL);
diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c
index d6b85f0f6082f..2c8ccc91ebe6d 100644
--- a/drivers/acpi/numa/hmat.c
+++ b/drivers/acpi/numa/hmat.c
@@ -59,9 +59,8 @@ struct target_cache {
};
enum {
- NODE_ACCESS_CLASS_0 = 0,
- NODE_ACCESS_CLASS_1,
- NODE_ACCESS_CLASS_GENPORT_SINK,
+ NODE_ACCESS_CLASS_GENPORT_SINK_LOCAL = ACCESS_COORDINATE_MAX,
+ NODE_ACCESS_CLASS_GENPORT_SINK_CPU,
NODE_ACCESS_CLASS_MAX,
};
@@ -75,6 +74,7 @@ struct memory_target {
struct node_cache_attrs cache_attrs;
u8 gen_port_device_handle[ACPI_SRAT_DEVICE_HANDLE_SIZE];
bool registered;
+ bool ext_updated; /* externally updated */
};
struct memory_initiator {
@@ -127,7 +127,8 @@ static struct memory_target *acpi_find_genport_target(u32 uid)
/**
* acpi_get_genport_coordinates - Retrieve the access coordinates for a generic port
* @uid: ACPI unique id
- * @coord: The access coordinates written back out for the generic port
+ * @coord: The access coordinates written back out for the generic port.
+ * Expect 2 levels array.
*
* Return: 0 on success. Errno on failure.
*
@@ -143,7 +144,10 @@ int acpi_get_genport_coordinates(u32 uid,
if (!target)
return -ENOENT;
- *coord = target->coord[NODE_ACCESS_CLASS_GENPORT_SINK];
+ coord[ACCESS_COORDINATE_LOCAL] =
+ target->coord[NODE_ACCESS_CLASS_GENPORT_SINK_LOCAL];
+ coord[ACCESS_COORDINATE_CPU] =
+ target->coord[NODE_ACCESS_CLASS_GENPORT_SINK_CPU];
return 0;
}
@@ -325,6 +329,35 @@ static void hmat_update_target_access(struct memory_target *target,
}
}
+int hmat_update_target_coordinates(int nid, struct access_coordinate *coord,
+ enum access_coordinate_class access)
+{
+ struct memory_target *target;
+ int pxm;
+
+ if (nid == NUMA_NO_NODE)
+ return -EINVAL;
+
+ pxm = node_to_pxm(nid);
+ guard(mutex)(&target_lock);
+ target = find_mem_target(pxm);
+ if (!target)
+ return -ENODEV;
+
+ hmat_update_target_access(target, ACPI_HMAT_READ_LATENCY,
+ coord->read_latency, access);
+ hmat_update_target_access(target, ACPI_HMAT_WRITE_LATENCY,
+ coord->write_latency, access);
+ hmat_update_target_access(target, ACPI_HMAT_READ_BANDWIDTH,
+ coord->read_bandwidth, access);
+ hmat_update_target_access(target, ACPI_HMAT_WRITE_BANDWIDTH,
+ coord->write_bandwidth, access);
+ target->ext_updated = true;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(hmat_update_target_coordinates);
+
static __init void hmat_add_locality(struct acpi_hmat_locality *hmat_loc)
{
struct memory_locality *loc;
@@ -374,11 +407,11 @@ static __init void hmat_update_target(unsigned int tgt_pxm, unsigned int init_px
if (target && target->processor_pxm == init_pxm) {
hmat_update_target_access(target, type, value,
- NODE_ACCESS_CLASS_0);
+ ACCESS_COORDINATE_LOCAL);
/* If the node has a CPU, update access 1 */
if (node_state(pxm_to_node(init_pxm), N_CPU))
hmat_update_target_access(target, type, value,
- NODE_ACCESS_CLASS_1);
+ ACCESS_COORDINATE_CPU);
}
}
@@ -696,8 +729,13 @@ static void hmat_update_target_attrs(struct memory_target *target,
u32 best = 0;
int i;
+ /* Don't update if an external agent has changed the data. */
+ if (target->ext_updated)
+ return;
+
/* Don't update for generic port if there's no device handle */
- if (access == NODE_ACCESS_CLASS_GENPORT_SINK &&
+ if ((access == NODE_ACCESS_CLASS_GENPORT_SINK_LOCAL ||
+ access == NODE_ACCESS_CLASS_GENPORT_SINK_CPU) &&
!(*(u16 *)target->gen_port_device_handle))
return;
@@ -709,7 +747,8 @@ static void hmat_update_target_attrs(struct memory_target *target,
*/
if (target->processor_pxm != PXM_INVAL) {
cpu_nid = pxm_to_node(target->processor_pxm);
- if (access == 0 || node_state(cpu_nid, N_CPU)) {
+ if (access == ACCESS_COORDINATE_LOCAL ||
+ node_state(cpu_nid, N_CPU)) {
set_bit(target->processor_pxm, p_nodes);
return;
}
@@ -737,7 +776,9 @@ static void hmat_update_target_attrs(struct memory_target *target,
list_for_each_entry(initiator, &initiators, node) {
u32 value;
- if (access == 1 && !initiator->has_cpu) {
+ if ((access == ACCESS_COORDINATE_CPU ||
+ access == NODE_ACCESS_CLASS_GENPORT_SINK_CPU) &&
+ !initiator->has_cpu) {
clear_bit(initiator->processor_pxm, p_nodes);
continue;
}
@@ -770,20 +811,24 @@ static void __hmat_register_target_initiators(struct memory_target *target,
}
}
-static void hmat_register_generic_target_initiators(struct memory_target *target)
+static void hmat_update_generic_target(struct memory_target *target)
{
static DECLARE_BITMAP(p_nodes, MAX_NUMNODES);
- __hmat_register_target_initiators(target, p_nodes,
- NODE_ACCESS_CLASS_GENPORT_SINK);
+ hmat_update_target_attrs(target, p_nodes,
+ NODE_ACCESS_CLASS_GENPORT_SINK_LOCAL);
+ hmat_update_target_attrs(target, p_nodes,
+ NODE_ACCESS_CLASS_GENPORT_SINK_CPU);
}
static void hmat_register_target_initiators(struct memory_target *target)
{
static DECLARE_BITMAP(p_nodes, MAX_NUMNODES);
- __hmat_register_target_initiators(target, p_nodes, 0);
- __hmat_register_target_initiators(target, p_nodes, 1);
+ __hmat_register_target_initiators(target, p_nodes,
+ ACCESS_COORDINATE_LOCAL);
+ __hmat_register_target_initiators(target, p_nodes,
+ ACCESS_COORDINATE_CPU);
}
static void hmat_register_target_cache(struct memory_target *target)
@@ -835,7 +880,7 @@ static void hmat_register_target(struct memory_target *target)
*/
mutex_lock(&target_lock);
if (*(u16 *)target->gen_port_device_handle) {
- hmat_register_generic_target_initiators(target);
+ hmat_update_generic_target(target);
target->registered = true;
}
mutex_unlock(&target_lock);
@@ -854,8 +899,8 @@ static void hmat_register_target(struct memory_target *target)
if (!target->registered) {
hmat_register_target_initiators(target);
hmat_register_target_cache(target);
- hmat_register_target_perf(target, NODE_ACCESS_CLASS_0);
- hmat_register_target_perf(target, NODE_ACCESS_CLASS_1);
+ hmat_register_target_perf(target, ACCESS_COORDINATE_LOCAL);
+ hmat_register_target_perf(target, ACCESS_COORDINATE_CPU);
target->registered = true;
}
mutex_unlock(&target_lock);
@@ -927,7 +972,7 @@ static int hmat_calculate_adistance(struct notifier_block *self,
return NOTIFY_OK;
mutex_lock(&target_lock);
- hmat_update_target_attrs(target, p_nodes, 1);
+ hmat_update_target_attrs(target, p_nodes, ACCESS_COORDINATE_CPU);
mutex_unlock(&target_lock);
perf = &target->coord[1];
diff --git a/drivers/acpi/numa/srat.c b/drivers/acpi/numa/srat.c
index 0214518fc582f..e45e64993c504 100644
--- a/drivers/acpi/numa/srat.c
+++ b/drivers/acpi/numa/srat.c
@@ -29,6 +29,8 @@ static int node_to_pxm_map[MAX_NUMNODES]
unsigned char acpi_srat_revision __initdata;
static int acpi_numa __initdata;
+static int last_real_pxm;
+
void __init disable_srat(void)
{
acpi_numa = -1;
@@ -536,6 +538,7 @@ int __init acpi_numa_init(void)
if (node_to_pxm_map[i] > fake_pxm)
fake_pxm = node_to_pxm_map[i];
}
+ last_real_pxm = fake_pxm;
fake_pxm++;
acpi_table_parse_cedt(ACPI_CEDT_TYPE_CFMWS, acpi_parse_cfmws,
&fake_pxm);
@@ -547,6 +550,14 @@ int __init acpi_numa_init(void)
return 0;
}
+bool acpi_node_backed_by_real_pxm(int nid)
+{
+ int pxm = node_to_pxm(nid);
+
+ return pxm <= last_real_pxm;
+}
+EXPORT_SYMBOL_GPL(acpi_node_backed_by_real_pxm);
+
static int acpi_get_pxm(acpi_handle h)
{
unsigned long long pxm;
diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c
index b07f7d091d133..b976e5fc3fbcd 100644
--- a/drivers/acpi/tables.c
+++ b/drivers/acpi/tables.c
@@ -253,7 +253,7 @@ int __init_or_acpilib acpi_table_parse_entries_array(
count = acpi_parse_entries_array(id, table_size,
(union fw_table_header *)table_header,
- proc, proc_num, max_entries);
+ 0, proc, proc_num, max_entries);
acpi_put_table(table_header);
return count;
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 1c05640461dd1..eb72580288e62 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -126,7 +126,7 @@ static void node_access_release(struct device *dev)
}
static struct node_access_nodes *node_init_node_access(struct node *node,
- unsigned int access)
+ enum access_coordinate_class access)
{
struct node_access_nodes *access_node;
struct device *dev;
@@ -191,7 +191,7 @@ static struct attribute *access_attrs[] = {
* @access: The access class the for the given attributes
*/
void node_set_perf_attrs(unsigned int nid, struct access_coordinate *coord,
- unsigned int access)
+ enum access_coordinate_class access)
{
struct node_access_nodes *c;
struct node *node;
@@ -215,6 +215,7 @@ void node_set_perf_attrs(unsigned int nid, struct access_coordinate *coord,
}
}
}
+EXPORT_SYMBOL_GPL(node_set_perf_attrs);
/**
* struct node_cache_info - Internal tracking for memory node caches
@@ -689,7 +690,7 @@ int register_cpu_under_node(unsigned int cpu, unsigned int nid)
*/
int register_memory_node_under_compute_node(unsigned int mem_nid,
unsigned int cpu_nid,
- unsigned int access)
+ enum access_coordinate_class access)
{
struct node *init_node, *targ_node;
struct node_access_nodes *initiator, *target;
diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c
index 1a3e6aafbdcc3..af5cb818f84d6 100644
--- a/drivers/cxl/acpi.c
+++ b/drivers/cxl/acpi.c
@@ -530,13 +530,15 @@ static int get_genport_coordinates(struct device *dev, struct cxl_dport *dport)
if (kstrtou32(acpi_device_uid(hb), 0, &uid))
return -EINVAL;
- rc = acpi_get_genport_coordinates(uid, &dport->hb_coord);
+ rc = acpi_get_genport_coordinates(uid, dport->hb_coord);
if (rc < 0)
return rc;
/* Adjust back to picoseconds from nanoseconds */
- dport->hb_coord.read_latency *= 1000;
- dport->hb_coord.write_latency *= 1000;
+ for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) {
+ dport->hb_coord[i].read_latency *= 1000;
+ dport->hb_coord[i].write_latency *= 1000;
+ }
return 0;
}
diff --git a/drivers/cxl/core/cdat.c b/drivers/cxl/core/cdat.c
index 08fd0baea7a0e..eddbbe21450ca 100644
--- a/drivers/cxl/core/cdat.c
+++ b/drivers/cxl/core/cdat.c
@@ -9,6 +9,7 @@
#include "cxlmem.h"
#include "core.h"
#include "cxl.h"
+#include "core.h"
struct dsmas_entry {
struct range dpa_range;
@@ -149,28 +150,35 @@ static int cxl_cdat_endpoint_process(struct cxl_port *port,
int rc;
rc = cdat_table_parse(ACPI_CDAT_TYPE_DSMAS, cdat_dsmas_handler,
- dsmas_xa, port->cdat.table);
+ dsmas_xa, port->cdat.table, port->cdat.length);
rc = cdat_table_parse_output(rc);
if (rc)
return rc;
rc = cdat_table_parse(ACPI_CDAT_TYPE_DSLBIS, cdat_dslbis_handler,
- dsmas_xa, port->cdat.table);
+ dsmas_xa, port->cdat.table, port->cdat.length);
return cdat_table_parse_output(rc);
}
static int cxl_port_perf_data_calculate(struct cxl_port *port,
struct xarray *dsmas_xa)
{
- struct access_coordinate c;
+ struct access_coordinate ep_c;
+ struct access_coordinate coord[ACCESS_COORDINATE_MAX];
struct dsmas_entry *dent;
int valid_entries = 0;
unsigned long index;
int rc;
- rc = cxl_endpoint_get_perf_coordinates(port, &c);
+ rc = cxl_endpoint_get_perf_coordinates(port, &ep_c);
if (rc) {
- dev_dbg(&port->dev, "Failed to retrieve perf coordinates.\n");
+ dev_dbg(&port->dev, "Failed to retrieve ep perf coordinates.\n");
+ return rc;
+ }
+
+ rc = cxl_hb_get_perf_coordinates(port, coord);
+ if (rc) {
+ dev_dbg(&port->dev, "Failed to retrieve hb perf coordinates.\n");
return rc;
}
@@ -185,18 +193,19 @@ static int cxl_port_perf_data_calculate(struct cxl_port *port,
xa_for_each(dsmas_xa, index, dent) {
int qos_class;
- dent->coord.read_latency = dent->coord.read_latency +
- c.read_latency;
- dent->coord.write_latency = dent->coord.write_latency +
- c.write_latency;
- dent->coord.read_bandwidth = min_t(int, c.read_bandwidth,
- dent->coord.read_bandwidth);
- dent->coord.write_bandwidth = min_t(int, c.write_bandwidth,
- dent->coord.write_bandwidth);
-
+ cxl_coordinates_combine(&dent->coord, &dent->coord, &ep_c);
+ /*
+ * Keeping the host bridge coordinates separate from the dsmas
+ * coordinates in order to allow calculation of access class
+ * 0 and 1 for region later.
+ */
+ cxl_coordinates_combine(&coord[ACCESS_COORDINATE_CPU],
+ &coord[ACCESS_COORDINATE_CPU],
+ &dent->coord);
dent->entries = 1;
- rc = cxl_root->ops->qos_class(cxl_root, &dent->coord, 1,
- &qos_class);
+ rc = cxl_root->ops->qos_class(cxl_root,
+ &coord[ACCESS_COORDINATE_CPU],
+ 1, &qos_class);
if (rc != 1)
continue;
@@ -389,36 +398,38 @@ EXPORT_SYMBOL_NS_GPL(cxl_endpoint_parse_cdat, CXL);
static int cdat_sslbis_handler(union acpi_subtable_headers *header, void *arg,
const unsigned long end)
{
+ struct acpi_cdat_sslbis_table {
+ struct acpi_cdat_header header;
+ struct acpi_cdat_sslbis sslbis_header;
+ struct acpi_cdat_sslbe entries[];
+ } *tbl = (struct acpi_cdat_sslbis_table *)header;
+ int size = sizeof(header->cdat) + sizeof(tbl->sslbis_header);
struct acpi_cdat_sslbis *sslbis;
- int size = sizeof(header->cdat) + sizeof(*sslbis);
struct cxl_port *port = arg;
struct device *dev = &port->dev;
- struct acpi_cdat_sslbe *entry;
int remain, entries, i;
u16 len;
len = le16_to_cpu((__force __le16)header->cdat.length);
remain = len - size;
- if (!remain || remain % sizeof(*entry) ||
+ if (!remain || remain % sizeof(tbl->entries[0]) ||
(unsigned long)header + len > end) {
dev_warn(dev, "Malformed SSLBIS table length: (%u)\n", len);
return -EINVAL;
}
- /* Skip common header */
- sslbis = (struct acpi_cdat_sslbis *)((unsigned long)header +
- sizeof(header->cdat));
-
+ sslbis = &tbl->sslbis_header;
/* Unrecognized data type, we can skip */
if (sslbis->data_type > ACPI_HMAT_WRITE_BANDWIDTH)
return 0;
- entries = remain / sizeof(*entry);
- entry = (struct acpi_cdat_sslbe *)((unsigned long)header + sizeof(*sslbis));
+ entries = remain / sizeof(tbl->entries[0]);
+ if (struct_size(tbl, entries, entries) != len)
+ return -EINVAL;
for (i = 0; i < entries; i++) {
- u16 x = le16_to_cpu((__force __le16)entry->portx_id);
- u16 y = le16_to_cpu((__force __le16)entry->porty_id);
+ u16 x = le16_to_cpu((__force __le16)tbl->entries[i].portx_id);
+ u16 y = le16_to_cpu((__force __le16)tbl->entries[i].porty_id);
__le64 le_base;
__le16 le_val;
struct cxl_dport *dport;
@@ -448,8 +459,8 @@ static int cdat_sslbis_handler(union acpi_subtable_headers *header, void *arg,
break;
}
- le_base = (__force __le64)sslbis->entry_base_unit;
- le_val = (__force __le16)entry->latency_or_bandwidth;
+ le_base = (__force __le64)tbl->sslbis_header.entry_base_unit;
+ le_val = (__force __le16)tbl->entries[i].latency_or_bandwidth;
if (check_mul_overflow(le64_to_cpu(le_base),
le16_to_cpu(le_val), &val))
@@ -462,8 +473,6 @@ static int cdat_sslbis_handler(union acpi_subtable_headers *header, void *arg,
sslbis->data_type,
val);
}
-
- entry++;
}
return 0;
@@ -477,11 +486,108 @@ void cxl_switch_parse_cdat(struct cxl_port *port)
return;
rc = cdat_table_parse(ACPI_CDAT_TYPE_SSLBIS, cdat_sslbis_handler,
- port, port->cdat.table);
+ port, port->cdat.table, port->cdat.length);
rc = cdat_table_parse_output(rc);
if (rc)
dev_dbg(&port->dev, "Failed to parse SSLBIS: %d\n", rc);
}
EXPORT_SYMBOL_NS_GPL(cxl_switch_parse_cdat, CXL);
+/**
+ * cxl_coordinates_combine - Combine the two input coordinates
+ *
+ * @out: Output coordinate of c1 and c2 combined
+ * @c1: input coordinates
+ * @c2: input coordinates
+ */
+void cxl_coordinates_combine(struct access_coordinate *out,
+ struct access_coordinate *c1,
+ struct access_coordinate *c2)
+{
+ if (c1->write_bandwidth && c2->write_bandwidth)
+ out->write_bandwidth = min(c1->write_bandwidth,
+ c2->write_bandwidth);
+ out->write_latency = c1->write_latency + c2->write_latency;
+
+ if (c1->read_bandwidth && c2->read_bandwidth)
+ out->read_bandwidth = min(c1->read_bandwidth,
+ c2->read_bandwidth);
+ out->read_latency = c1->read_latency + c2->read_latency;
+}
+
MODULE_IMPORT_NS(CXL);
+
+void cxl_region_perf_data_calculate(struct cxl_region *cxlr,
+ struct cxl_endpoint_decoder *cxled)
+{
+ struct cxl_memdev *cxlmd = cxled_to_memdev(cxled);
+ struct cxl_port *port = cxlmd->endpoint;
+ struct cxl_dev_state *cxlds = cxlmd->cxlds;
+ struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds);
+ struct access_coordinate hb_coord[ACCESS_COORDINATE_MAX];
+ struct access_coordinate coord;
+ struct range dpa = {
+ .start = cxled->dpa_res->start,
+ .end = cxled->dpa_res->end,
+ };
+ struct cxl_dpa_perf *perf;
+ int rc;
+
+ switch (cxlr->mode) {
+ case CXL_DECODER_RAM:
+ perf = &mds->ram_perf;
+ break;
+ case CXL_DECODER_PMEM:
+ perf = &mds->pmem_perf;
+ break;
+ default:
+ return;
+ }
+
+ lockdep_assert_held(&cxl_dpa_rwsem);
+
+ if (!range_contains(&perf->dpa_range, &dpa))
+ return;
+
+ rc = cxl_hb_get_perf_coordinates(port, hb_coord);
+ if (rc) {
+ dev_dbg(&port->dev, "Failed to retrieve hb perf coordinates.\n");
+ return;
+ }
+
+ for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) {
+ /* Pickup the host bridge coords */
+ cxl_coordinates_combine(&coord, &hb_coord[i], &perf->coord);
+
+ /* Get total bandwidth and the worst latency for the cxl region */
+ cxlr->coord[i].read_latency = max_t(unsigned int,
+ cxlr->coord[i].read_latency,
+ coord.read_latency);
+ cxlr->coord[i].write_latency = max_t(unsigned int,
+ cxlr->coord[i].write_latency,
+ coord.write_latency);
+ cxlr->coord[i].read_bandwidth += coord.read_bandwidth;
+ cxlr->coord[i].write_bandwidth += coord.write_bandwidth;
+
+ /*
+ * Convert latency to nanosec from picosec to be consistent
+ * with the resulting latency coordinates computed by the
+ * HMAT_REPORTING code.
+ */
+ cxlr->coord[i].read_latency =
+ DIV_ROUND_UP(cxlr->coord[i].read_latency, 1000);
+ cxlr->coord[i].write_latency =
+ DIV_ROUND_UP(cxlr->coord[i].write_latency, 1000);
+ }
+}
+
+int cxl_update_hmat_access_coordinates(int nid, struct cxl_region *cxlr,
+ enum access_coordinate_class access)
+{
+ return hmat_update_target_coordinates(nid, &cxlr->coord[access], access);
+}
+
+bool cxl_need_node_perf_attrs_update(int nid)
+{
+ return !acpi_node_backed_by_real_pxm(nid);
+}
diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h
index 3b64fb1b9ed05..bc5a95665aa0a 100644
--- a/drivers/cxl/core/core.h
+++ b/drivers/cxl/core/core.h
@@ -90,4 +90,8 @@ enum cxl_poison_trace_type {
long cxl_pci_get_latency(struct pci_dev *pdev);
+int cxl_update_hmat_access_coordinates(int nid, struct cxl_region *cxlr,
+ enum access_coordinate_class access);
+bool cxl_need_node_perf_attrs_update(int nid);
+
#endif /* __CXL_CORE_H__ */
diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
index e9e6c81ce034a..0df09bd794088 100644
--- a/drivers/cxl/core/pci.c
+++ b/drivers/cxl/core/pci.c
@@ -518,14 +518,14 @@ EXPORT_SYMBOL_NS_GPL(cxl_hdm_decode_init, CXL);
FIELD_PREP(CXL_DOE_TABLE_ACCESS_ENTRY_HANDLE, (entry_handle)))
static int cxl_cdat_get_length(struct device *dev,
- struct pci_doe_mb *cdat_doe,
+ struct pci_doe_mb *doe_mb,
size_t *length)
{
__le32 request = CDAT_DOE_REQ(0);
__le32 response[2];
int rc;
- rc = pci_doe(cdat_doe, PCI_DVSEC_VENDOR_ID_CXL,
+ rc = pci_doe(doe_mb, PCI_DVSEC_VENDOR_ID_CXL,
CXL_DOE_PROTOCOL_TABLE_ACCESS,
&request, sizeof(request),
&response, sizeof(response));
@@ -543,56 +543,58 @@ static int cxl_cdat_get_length(struct device *dev,
}
static int cxl_cdat_read_table(struct device *dev,
- struct pci_doe_mb *cdat_doe,
- void *cdat_table, size_t *cdat_length)
+ struct pci_doe_mb *doe_mb,
+ struct cdat_doe_rsp *rsp, size_t *length)
{
- size_t length = *cdat_length + sizeof(__le32);
- __le32 *data = cdat_table;
- int entry_handle = 0;
+ size_t received, remaining = *length;
+ unsigned int entry_handle = 0;
+ union cdat_data *data;
__le32 saved_dw = 0;
do {
__le32 request = CDAT_DOE_REQ(entry_handle);
- struct cdat_entry_header *entry;
- size_t entry_dw;
int rc;
- rc = pci_doe(cdat_doe, PCI_DVSEC_VENDOR_ID_CXL,
+ rc = pci_doe(doe_mb, PCI_DVSEC_VENDOR_ID_CXL,
CXL_DOE_PROTOCOL_TABLE_ACCESS,
&request, sizeof(request),
- data, length);
+ rsp, sizeof(*rsp) + remaining);
if (rc < 0) {
dev_err(dev, "DOE failed: %d", rc);
return rc;
}
- /* 1 DW Table Access Response Header + CDAT entry */
- entry = (struct cdat_entry_header *)(data + 1);
- if ((entry_handle == 0 &&
- rc != sizeof(__le32) + sizeof(struct cdat_header)) ||
- (entry_handle > 0 &&
- (rc < sizeof(__le32) + sizeof(*entry) ||
- rc != sizeof(__le32) + le16_to_cpu(entry->length))))
+ if (rc < sizeof(*rsp))
return -EIO;
+ data = (union cdat_data *)rsp->data;
+ received = rc - sizeof(*rsp);
+
+ if (entry_handle == 0) {
+ if (received != sizeof(data->header))
+ return -EIO;
+ } else {
+ if (received < sizeof(data->entry) ||
+ received != le16_to_cpu(data->entry.length))
+ return -EIO;
+ }
+
/* Get the CXL table access header entry handle */
entry_handle = FIELD_GET(CXL_DOE_TABLE_ACCESS_ENTRY_HANDLE,
- le32_to_cpu(data[0]));
- entry_dw = rc / sizeof(__le32);
- /* Skip Header */
- entry_dw -= 1;
+ le32_to_cpu(rsp->doe_header));
+
/*
* Table Access Response Header overwrote the last DW of
* previous entry, so restore that DW
*/
- *data = saved_dw;
- length -= entry_dw * sizeof(__le32);
- data += entry_dw;
- saved_dw = *data;
+ rsp->doe_header = saved_dw;
+ remaining -= received;
+ rsp = (void *)rsp + received;
+ saved_dw = rsp->doe_header;
} while (entry_handle != CXL_DOE_TABLE_ACCESS_LAST_ENTRY);
/* Length in CDAT header may exceed concatenation of CDAT entries */
- *cdat_length -= length - sizeof(__le32);
+ *length -= remaining;
return 0;
}
@@ -617,11 +619,11 @@ void read_cdat_data(struct cxl_port *port)
{
struct device *uport = port->uport_dev;
struct device *dev = &port->dev;
- struct pci_doe_mb *cdat_doe;
+ struct pci_doe_mb *doe_mb;
struct pci_dev *pdev = NULL;
struct cxl_memdev *cxlmd;
- size_t cdat_length;
- void *cdat_table, *cdat_buf;
+ struct cdat_doe_rsp *buf;
+ size_t table_length, length;
int rc;
if (is_cxl_memdev(uport)) {
@@ -638,39 +640,48 @@ void read_cdat_data(struct cxl_port *port)
if (!pdev)
return;
- cdat_doe = pci_find_doe_mailbox(pdev, PCI_DVSEC_VENDOR_ID_CXL,
- CXL_DOE_PROTOCOL_TABLE_ACCESS);
- if (!cdat_doe) {
+ doe_mb = pci_find_doe_mailbox(pdev, PCI_DVSEC_VENDOR_ID_CXL,
+ CXL_DOE_PROTOCOL_TABLE_ACCESS);
+ if (!doe_mb) {
dev_dbg(dev, "No CDAT mailbox\n");
return;
}
port->cdat_available = true;
- if (cxl_cdat_get_length(dev, cdat_doe, &cdat_length)) {
+ if (cxl_cdat_get_length(dev, doe_mb, &length)) {
dev_dbg(dev, "No CDAT length\n");
return;
}
- cdat_buf = devm_kzalloc(dev, cdat_length + sizeof(__le32), GFP_KERNEL);
- if (!cdat_buf)
- return;
+ /*
+ * The begin of the CDAT buffer needs space for additional 4
+ * bytes for the DOE header. Table data starts afterwards.
+ */
+ buf = devm_kzalloc(dev, sizeof(*buf) + length, GFP_KERNEL);
+ if (!buf)
+ goto err;
+
+ table_length = length;
- rc = cxl_cdat_read_table(dev, cdat_doe, cdat_buf, &cdat_length);
+ rc = cxl_cdat_read_table(dev, doe_mb, buf, &length);
if (rc)
goto err;
- cdat_table = cdat_buf + sizeof(__le32);
- if (cdat_checksum(cdat_table, cdat_length))
+ if (table_length != length)
+ dev_warn(dev, "Malformed CDAT table length (%zu:%zu), discarding trailing data\n",
+ table_length, length);
+
+ if (cdat_checksum(buf->data, length))
goto err;
- port->cdat.table = cdat_table;
- port->cdat.length = cdat_length;
- return;
+ port->cdat.table = buf->data;
+ port->cdat.length = length;
+ return;
err:
/* Don't leave table data allocated on error */
- devm_kfree(dev, cdat_buf);
+ devm_kfree(dev, buf);
dev_err(dev, "Failed to read/validate CDAT.\n");
}
EXPORT_SYMBOL_NS_GPL(read_cdat_data, CXL);
diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
index e59d9d37aa650..2b0cab556072f 100644
--- a/drivers/cxl/core/port.c
+++ b/drivers/cxl/core/port.c
@@ -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 +794,40 @@ 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,
+ "0x%llx\n");
+
+static void cxl_debugfs_create_dport_dir(struct cxl_dport *dport)
+{
+ struct dentry *dir;
+
+ if (!einj_cxl_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,
@@ -822,6 +857,7 @@ static struct cxl_port *__devm_cxl_add_port(struct device *host,
*/
port->reg_map = cxlds->reg_map;
port->reg_map.host = &port->dev;
+ cxlmd->endpoint = port;
} else if (parent_dport) {
rc = dev_set_name(dev, "port%d", port->id);
if (rc)
@@ -1149,6 +1185,8 @@ __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;
}
@@ -1374,7 +1412,6 @@ int cxl_endpoint_autoremove(struct cxl_memdev *cxlmd, struct cxl_port *endpoint)
get_device(host);
get_device(&endpoint->dev);
- cxlmd->endpoint = endpoint;
cxlmd->depth = endpoint->depth;
return devm_add_action_or_reset(dev, delete_endpoint, cxlmd);
}
@@ -2096,18 +2133,36 @@ bool schedule_cxl_memdev_detach(struct cxl_memdev *cxlmd)
}
EXPORT_SYMBOL_NS_GPL(schedule_cxl_memdev_detach, CXL);
-static void combine_coordinates(struct access_coordinate *c1,
- struct access_coordinate *c2)
+/**
+ * cxl_hb_get_perf_coordinates - Retrieve performance numbers between initiator
+ * and host bridge
+ *
+ * @port: endpoint cxl_port
+ * @coord: output access coordinates
+ *
+ * Return: errno on failure, 0 on success.
+ */
+int cxl_hb_get_perf_coordinates(struct cxl_port *port,
+ struct access_coordinate *coord)
{
- if (c2->write_bandwidth)
- c1->write_bandwidth = min(c1->write_bandwidth,
- c2->write_bandwidth);
- c1->write_latency += c2->write_latency;
+ struct cxl_port *iter = port;
+ struct cxl_dport *dport;
+
+ if (!is_cxl_endpoint(port))
+ return -EINVAL;
- if (c2->read_bandwidth)
- c1->read_bandwidth = min(c1->read_bandwidth,
- c2->read_bandwidth);
- c1->read_latency += c2->read_latency;
+ dport = iter->parent_dport;
+ while (iter && !is_cxl_root(to_cxl_port(iter->dev.parent))) {
+ iter = to_cxl_port(iter->dev.parent);
+ dport = iter->parent_dport;
+ }
+
+ coord[ACCESS_COORDINATE_LOCAL] =
+ dport->hb_coord[ACCESS_COORDINATE_LOCAL];
+ coord[ACCESS_COORDINATE_CPU] =
+ dport->hb_coord[ACCESS_COORDINATE_CPU];
+
+ return 0;
}
/**
@@ -2143,7 +2198,7 @@ int cxl_endpoint_get_perf_coordinates(struct cxl_port *port,
* nothing to gather.
*/
while (iter && !is_cxl_root(to_cxl_port(iter->dev.parent))) {
- combine_coordinates(&c, &dport->sw_coord);
+ cxl_coordinates_combine(&c, &c, &dport->sw_coord);
c.write_latency += dport->link_latency;
c.read_latency += dport->link_latency;
@@ -2151,9 +2206,6 @@ int cxl_endpoint_get_perf_coordinates(struct cxl_port *port,
dport = iter->parent_dport;
}
- /* Augment with the generic port (host bridge) perf data */
- combine_coordinates(&c, &dport->hb_coord);
-
/* Get the calculated PCI paths bandwidth */
pdev = to_pci_dev(port->uport_dev->parent);
bw = pcie_bandwidth_available(pdev, NULL, NULL, NULL);
@@ -2221,6 +2273,10 @@ static __init int cxl_core_init(void)
cxl_debugfs = debugfs_create_dir("cxl", NULL);
+ if (einj_cxl_is_initialized())
+ debugfs_create_file("einj_types", 0400, cxl_debugfs, NULL,
+ &einj_cxl_available_error_type_fops);
+
cxl_mbox_init();
rc = cxl_memdev_init();
diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index 4c7fd2d5cccb2..5c186e0a39b96 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -4,6 +4,7 @@
#include <linux/genalloc.h>
#include <linux/device.h>
#include <linux/module.h>
+#include <linux/memory.h>
#include <linux/slab.h>
#include <linux/uuid.h>
#include <linux/sort.h>
@@ -30,6 +31,108 @@
static struct cxl_region *to_cxl_region(struct device *dev);
+#define __ACCESS_ATTR_RO(_level, _name) { \
+ .attr = { .name = __stringify(_name), .mode = 0444 }, \
+ .show = _name##_access##_level##_show, \
+}
+
+#define ACCESS_DEVICE_ATTR_RO(level, name) \
+ struct device_attribute dev_attr_access##level##_##name = __ACCESS_ATTR_RO(level, name)
+
+#define ACCESS_ATTR_RO(level, attrib) \
+static ssize_t attrib##_access##level##_show(struct device *dev, \
+ struct device_attribute *attr, \
+ char *buf) \
+{ \
+ struct cxl_region *cxlr = to_cxl_region(dev); \
+ \
+ if (cxlr->coord[level].attrib == 0) \
+ return -ENOENT; \
+ \
+ return sysfs_emit(buf, "%u\n", cxlr->coord[level].attrib); \
+} \
+static ACCESS_DEVICE_ATTR_RO(level, attrib)
+
+ACCESS_ATTR_RO(0, read_bandwidth);
+ACCESS_ATTR_RO(0, read_latency);
+ACCESS_ATTR_RO(0, write_bandwidth);
+ACCESS_ATTR_RO(0, write_latency);
+
+#define ACCESS_ATTR_DECLARE(level, attrib) \
+ (&dev_attr_access##level##_##attrib.attr)
+
+static struct attribute *access0_coordinate_attrs[] = {
+ ACCESS_ATTR_DECLARE(0, read_bandwidth),
+ ACCESS_ATTR_DECLARE(0, write_bandwidth),
+ ACCESS_ATTR_DECLARE(0, read_latency),
+ ACCESS_ATTR_DECLARE(0, write_latency),
+ NULL
+};
+
+ACCESS_ATTR_RO(1, read_bandwidth);
+ACCESS_ATTR_RO(1, read_latency);
+ACCESS_ATTR_RO(1, write_bandwidth);
+ACCESS_ATTR_RO(1, write_latency);
+
+static struct attribute *access1_coordinate_attrs[] = {
+ ACCESS_ATTR_DECLARE(1, read_bandwidth),
+ ACCESS_ATTR_DECLARE(1, write_bandwidth),
+ ACCESS_ATTR_DECLARE(1, read_latency),
+ ACCESS_ATTR_DECLARE(1, write_latency),
+ NULL
+};
+
+#define ACCESS_VISIBLE(level) \
+static umode_t cxl_region_access##level##_coordinate_visible( \
+ struct kobject *kobj, struct attribute *a, int n) \
+{ \
+ struct device *dev = kobj_to_dev(kobj); \
+ struct cxl_region *cxlr = to_cxl_region(dev); \
+ \
+ if (a == &dev_attr_access##level##_read_latency.attr && \
+ cxlr->coord[level].read_latency == 0) \
+ return 0; \
+ \
+ if (a == &dev_attr_access##level##_write_latency.attr && \
+ cxlr->coord[level].write_latency == 0) \
+ return 0; \
+ \
+ if (a == &dev_attr_access##level##_read_bandwidth.attr && \
+ cxlr->coord[level].read_bandwidth == 0) \
+ return 0; \
+ \
+ if (a == &dev_attr_access##level##_write_bandwidth.attr && \
+ cxlr->coord[level].write_bandwidth == 0) \
+ return 0; \
+ \
+ return a->mode; \
+}
+
+ACCESS_VISIBLE(0);
+ACCESS_VISIBLE(1);
+
+static const struct attribute_group cxl_region_access0_coordinate_group = {
+ .name = "access0",
+ .attrs = access0_coordinate_attrs,
+ .is_visible = cxl_region_access0_coordinate_visible,
+};
+
+static const struct attribute_group *get_cxl_region_access0_group(void)
+{
+ return &cxl_region_access0_coordinate_group;
+}
+
+static const struct attribute_group cxl_region_access1_coordinate_group = {
+ .name = "access1",
+ .attrs = access1_coordinate_attrs,
+ .is_visible = cxl_region_access1_coordinate_visible,
+};
+
+static const struct attribute_group *get_cxl_region_access1_group(void)
+{
+ return &cxl_region_access1_coordinate_group;
+}
+
static ssize_t uuid_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
@@ -1752,6 +1855,8 @@ static int cxl_region_attach(struct cxl_region *cxlr,
return -EINVAL;
}
+ cxl_region_perf_data_calculate(cxlr, cxled);
+
if (test_bit(CXL_REGION_F_AUTO, &cxlr->flags)) {
int i;
@@ -2067,6 +2172,8 @@ static const struct attribute_group *region_groups[] = {
&cxl_base_attribute_group,
&cxl_region_group,
&cxl_region_target_group,
+ &cxl_region_access0_coordinate_group,
+ &cxl_region_access1_coordinate_group,
NULL,
};
@@ -2120,6 +2227,7 @@ static void unregister_region(void *_cxlr)
struct cxl_region_params *p = &cxlr->params;
int i;
+ unregister_memory_notifier(&cxlr->memory_notifier);
device_del(&cxlr->dev);
/*
@@ -2164,6 +2272,63 @@ static struct cxl_region *cxl_region_alloc(struct cxl_root_decoder *cxlrd, int i
return cxlr;
}
+static bool cxl_region_update_coordinates(struct cxl_region *cxlr, int nid)
+{
+ int cset = 0;
+ int rc;
+
+ for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) {
+ if (cxlr->coord[i].read_bandwidth) {
+ rc = 0;
+ if (cxl_need_node_perf_attrs_update(nid))
+ node_set_perf_attrs(nid, &cxlr->coord[i], i);
+ else
+ rc = cxl_update_hmat_access_coordinates(nid, cxlr, i);
+
+ if (rc == 0)
+ cset++;
+ }
+ }
+
+ if (!cset)
+ return false;
+
+ rc = sysfs_update_group(&cxlr->dev.kobj, get_cxl_region_access0_group());
+ if (rc)
+ dev_dbg(&cxlr->dev, "Failed to update access0 group\n");
+
+ rc = sysfs_update_group(&cxlr->dev.kobj, get_cxl_region_access1_group());
+ if (rc)
+ dev_dbg(&cxlr->dev, "Failed to update access1 group\n");
+
+ return true;
+}
+
+static int cxl_region_perf_attrs_callback(struct notifier_block *nb,
+ unsigned long action, void *arg)
+{
+ struct cxl_region *cxlr = container_of(nb, struct cxl_region,
+ memory_notifier);
+ struct cxl_region_params *p = &cxlr->params;
+ struct cxl_endpoint_decoder *cxled = p->targets[0];
+ struct cxl_decoder *cxld = &cxled->cxld;
+ struct memory_notify *mnb = arg;
+ int nid = mnb->status_change_nid;
+ int region_nid;
+
+ if (nid == NUMA_NO_NODE || action != MEM_ONLINE)
+ return NOTIFY_DONE;
+
+ region_nid = phys_to_target_node(cxld->hpa_range.start);
+ if (nid != region_nid)
+ return NOTIFY_DONE;
+
+ if (!cxl_region_update_coordinates(cxlr, nid))
+ return NOTIFY_DONE;
+
+ return NOTIFY_OK;
+}
+
/**
* devm_cxl_add_region - Adds a region to a decoder
* @cxlrd: root decoder
@@ -2211,6 +2376,10 @@ static struct cxl_region *devm_cxl_add_region(struct cxl_root_decoder *cxlrd,
if (rc)
goto err;
+ cxlr->memory_notifier.notifier_call = cxl_region_perf_attrs_callback;
+ cxlr->memory_notifier.priority = CXL_CALLBACK_PRI;
+ register_memory_notifier(&cxlr->memory_notifier);
+
rc = devm_add_action_or_reset(port->uport_dev, unregister_region, cxlr);
if (rc)
return ERR_PTR(rc);
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index 003feebab79b5..534e25e2f0a48 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -6,6 +6,7 @@
#include <linux/libnvdimm.h>
#include <linux/bitfield.h>
+#include <linux/notifier.h>
#include <linux/bitops.h>
#include <linux/log2.h>
#include <linux/node.h>
@@ -517,6 +518,8 @@ struct cxl_region_params {
* @cxlr_pmem: (for pmem regions) cached copy of the nvdimm bridge
* @flags: Region state flags
* @params: active + config params for the region
+ * @coord: QoS access coordinates for the region
+ * @memory_notifier: notifier for setting the access coordinates to node
*/
struct cxl_region {
struct device dev;
@@ -527,6 +530,8 @@ struct cxl_region {
struct cxl_pmem_region *cxlr_pmem;
unsigned long flags;
struct cxl_region_params params;
+ struct access_coordinate coord[ACCESS_COORDINATE_MAX];
+ struct notifier_block memory_notifier;
};
struct cxl_nvdimm_bridge {
@@ -671,7 +676,7 @@ struct cxl_dport {
struct cxl_port *port;
struct cxl_regs regs;
struct access_coordinate sw_coord;
- struct access_coordinate hb_coord;
+ struct access_coordinate hb_coord[ACCESS_COORDINATE_MAX];
long link_latency;
};
@@ -879,9 +884,17 @@ void cxl_switch_parse_cdat(struct cxl_port *port);
int cxl_endpoint_get_perf_coordinates(struct cxl_port *port,
struct access_coordinate *coord);
+int cxl_hb_get_perf_coordinates(struct cxl_port *port,
+ struct access_coordinate *coord);
+void cxl_region_perf_data_calculate(struct cxl_region *cxlr,
+ struct cxl_endpoint_decoder *cxled);
void cxl_memdev_update_perf(struct cxl_memdev *cxlmd);
+void cxl_coordinates_combine(struct access_coordinate *out,
+ struct access_coordinate *c1,
+ struct access_coordinate *c2);
+
/*
* Unit test builds overrides this to __weak, find the 'strong' version
* of these symbols in tools/testing/cxl/.
diff --git a/drivers/cxl/cxlpci.h b/drivers/cxl/cxlpci.h
index 711b05d9a370e..93992a1c8eecf 100644
--- a/drivers/cxl/cxlpci.h
+++ b/drivers/cxl/cxlpci.h
@@ -71,6 +71,15 @@ enum cxl_regloc_type {
CXL_REGLOC_RBI_TYPES
};
+/*
+ * Table Access DOE, CDAT Read Entry Response
+ *
+ * Spec refs:
+ *
+ * CXL 3.1 8.1.11, Table 8-14: Read Entry Response
+ * CDAT Specification 1.03: 2 CDAT Data Structures
+ */
+
struct cdat_header {
__le32 length;
u8 revision;
@@ -86,6 +95,21 @@ struct cdat_entry_header {
} __packed;
/*
+ * The DOE CDAT read response contains a CDAT read entry (either the
+ * CDAT header or a structure).
+ */
+union cdat_data {
+ struct cdat_header header;
+ struct cdat_entry_header entry;
+} __packed;
+
+/* There is an additional CDAT response header of 4 bytes. */
+struct cdat_doe_rsp {
+ __le32 doe_header;
+ u8 data[];
+} __packed;
+
+/*
* CXL v3.0 6.2.3 Table 6-4
* The table indicates that if PCIe Flit Mode is set, then CXL is in 256B flits
* mode, otherwise it's 68B flits mode.
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index a170c389dd746..34829f2c517ac 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -1548,4 +1548,25 @@ static inline void acpi_use_parent_companion(struct device *dev)
ACPI_COMPANION_SET(dev, ACPI_COMPANION(dev->parent));
}
+#ifdef CONFIG_ACPI_HMAT
+int hmat_update_target_coordinates(int nid, struct access_coordinate *coord,
+ enum access_coordinate_class access);
+#else
+static inline int hmat_update_target_coordinates(int nid,
+ struct access_coordinate *coord,
+ enum access_coordinate_class access)
+{
+ return -EOPNOTSUPP;
+}
+#endif
+
+#ifdef CONFIG_ACPI_NUMA
+bool acpi_node_backed_by_real_pxm(int nid);
+#else
+static inline bool acpi_node_backed_by_real_pxm(int nid)
+{
+ return false;
+}
+#endif
+
#endif /*_LINUX_ACPI_H*/
diff --git a/include/linux/einj-cxl.h b/include/linux/einj-cxl.h
new file mode 100644
index 0000000000000..624ff6ff41f96
--- /dev/null
+++ b/include/linux/einj-cxl.h
@@ -0,0 +1,44 @@
+/* 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 EINJ_CXL_H
+#define EINJ_CXL_H
+
+#include <linux/errno.h>
+#include <linux/types.h>
+
+struct pci_dev;
+struct seq_file;
+
+#if IS_ENABLED(CONFIG_ACPI_APEI_EINJ_CXL)
+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_cxl_is_initialized(void);
+#else /* !IS_ENABLED(CONFIG_ACPI_APEI_EINJ_CXL) */
+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_cxl_is_initialized(void) { return false; }
+#endif /* CONFIG_ACPI_APEI_EINJ_CXL */
+
+#endif /* EINJ_CXL_H */
diff --git a/include/linux/fw_table.h b/include/linux/fw_table.h
index 95421860397a2..3ff4c277296fb 100644
--- a/include/linux/fw_table.h
+++ b/include/linux/fw_table.h
@@ -40,12 +40,14 @@ union acpi_subtable_headers {
int acpi_parse_entries_array(char *id, unsigned long table_size,
union fw_table_header *table_header,
+ unsigned long max_length,
struct acpi_subtable_proc *proc,
int proc_num, unsigned int max_entries);
int cdat_table_parse(enum acpi_cdat_type type,
acpi_tbl_entry_handler_arg handler_arg, void *arg,
- struct acpi_table_cdat *table_header);
+ struct acpi_table_cdat *table_header,
+ unsigned long length);
/* CXL is the only non-ACPI consumer of the FIRMWARE_TABLE library */
#if IS_ENABLED(CONFIG_ACPI) && !IS_ENABLED(CONFIG_CXL_BUS)
diff --git a/include/linux/memory.h b/include/linux/memory.h
index 939a16bd5cea1..c0afee5d126ef 100644
--- a/include/linux/memory.h
+++ b/include/linux/memory.h
@@ -123,6 +123,7 @@ struct mem_section;
#define DEFAULT_CALLBACK_PRI 0
#define SLAB_CALLBACK_PRI 1
#define HMAT_CALLBACK_PRI 2
+#define CXL_CALLBACK_PRI 5
#define MM_COMPUTE_BATCH_PRI 10
#define CPUSET_CALLBACK_PRI 10
#define MEMTIER_HOTPLUG_PRI 100
diff --git a/include/linux/node.h b/include/linux/node.h
index 25b66d705ee2e..dfc004e4bee74 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -34,6 +34,18 @@ struct access_coordinate {
unsigned int write_latency;
};
+/*
+ * ACCESS_COORDINATE_LOCAL correlates to ACCESS CLASS 0
+ * - access_coordinate between target node and nearest initiator node
+ * ACCESS_COORDINATE_CPU correlates to ACCESS CLASS 1
+ * - access_coordinate between target node and nearest CPU node
+ */
+enum access_coordinate_class {
+ ACCESS_COORDINATE_LOCAL,
+ ACCESS_COORDINATE_CPU,
+ ACCESS_COORDINATE_MAX
+};
+
enum cache_indexing {
NODE_CACHE_DIRECT_MAP,
NODE_CACHE_INDEXED,
@@ -66,7 +78,7 @@ struct node_cache_attrs {
#ifdef CONFIG_HMEM_REPORTING
void node_add_cache(unsigned int nid, struct node_cache_attrs *cache_attrs);
void node_set_perf_attrs(unsigned int nid, struct access_coordinate *coord,
- unsigned access);
+ enum access_coordinate_class access);
#else
static inline void node_add_cache(unsigned int nid,
struct node_cache_attrs *cache_attrs)
@@ -75,7 +87,7 @@ static inline void node_add_cache(unsigned int nid,
static inline void node_set_perf_attrs(unsigned int nid,
struct access_coordinate *coord,
- unsigned access)
+ enum access_coordinate_class access)
{
}
#endif
@@ -137,7 +149,7 @@ extern void unregister_memory_block_under_nodes(struct memory_block *mem_blk);
extern int register_memory_node_under_compute_node(unsigned int mem_nid,
unsigned int cpu_nid,
- unsigned access);
+ enum access_coordinate_class access);
#else
static inline void node_dev_init(void)
{
diff --git a/lib/fw_table.c b/lib/fw_table.c
index c3569d2ba503f..16291814450ee 100644
--- a/lib/fw_table.c
+++ b/lib/fw_table.c
@@ -127,6 +127,7 @@ static __init_or_fwtbl_lib int call_handler(struct acpi_subtable_proc *proc,
*
* @id: table id (for debugging purposes)
* @table_size: size of the root table
+ * @max_length: maximum size of the table (ignore if 0)
* @table_header: where does the table start?
* @proc: array of acpi_subtable_proc struct containing entry id
* and associated handler with it
@@ -148,18 +149,21 @@ static __init_or_fwtbl_lib int call_handler(struct acpi_subtable_proc *proc,
int __init_or_fwtbl_lib
acpi_parse_entries_array(char *id, unsigned long table_size,
union fw_table_header *table_header,
+ unsigned long max_length,
struct acpi_subtable_proc *proc,
int proc_num, unsigned int max_entries)
{
- unsigned long table_end, subtable_len, entry_len;
+ unsigned long table_len, table_end, subtable_len, entry_len;
struct acpi_subtable_entry entry;
enum acpi_subtable_type type;
int count = 0;
int i;
type = acpi_get_subtable_type(id);
- table_end = (unsigned long)table_header +
- acpi_table_get_length(type, table_header);
+ table_len = acpi_table_get_length(type, table_header);
+ if (max_length && max_length < table_len)
+ table_len = max_length;
+ table_end = (unsigned long)table_header + table_len;
/* Parse all entries looking for a match. */
@@ -208,7 +212,8 @@ int __init_or_fwtbl_lib
cdat_table_parse(enum acpi_cdat_type type,
acpi_tbl_entry_handler_arg handler_arg,
void *arg,
- struct acpi_table_cdat *table_header)
+ struct acpi_table_cdat *table_header,
+ unsigned long length)
{
struct acpi_subtable_proc proc = {
.id = type,
@@ -222,6 +227,6 @@ cdat_table_parse(enum acpi_cdat_type type,
return acpi_parse_entries_array(ACPI_SIG_CDAT,
sizeof(struct acpi_table_cdat),
(union fw_table_header *)table_header,
- &proc, 1, 0);
+ length, &proc, 1, 0);
}
EXPORT_SYMBOL_FWTBL_LIB(cdat_table_parse);