diff mbox series

[v14,3/4] cxl/core: Add CXL EINJ debugfs files

Message ID 20240226222704.1079449-4-Benjamin.Cheatham@amd.com (mailing list archive)
State Handled Elsewhere, archived
Headers show
Series cxl, EINJ: Update EINJ for CXL error types | expand

Commit Message

Ben Cheatham Feb. 26, 2024, 10:27 p.m. UTC
Export CXL helper functions in the einj_cxl module for getting/injecting
available CXL protocol error types 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_cxl 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 ++++++++++++++++++++
 drivers/cxl/core/port.c               | 41 +++++++++++++++++++++++++++
 2 files changed, 71 insertions(+)

Comments

Ben Cheatham Feb. 27, 2024, 8:14 p.m. UTC | #1
This patch also had an outdated commit message (still referenced the einj-cxl module).
The patch with the updated commit message is below. I also made a tiny change to
the format specifier of the einj_inject file to "0x%llx\n" from "%llx\n".

Thanks,
Ben

From 321129893da9129473c447772a461c1a4e9e0e9d Mon Sep 17 00:00:00 2001
From: Ben Cheatham <Benjamin.Cheatham@amd.com>
Date: Fri, 16 Feb 2024 11:17:01 -0600
Subject: [PATCH v14 3/4] cxl/core: Add CXL EINJ debugfs files

Export CXL helper functions in einj-cxl.c for getting/injecting
available CXL protocol error types 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 file 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 +++++++++++++++++++
 drivers/cxl/core/port.c               | 42 +++++++++++++++++++++++++++
 2 files changed, 72 insertions(+)

diff --git a/Documentation/ABI/testing/debugfs-cxl b/Documentation/ABI/testing/debugfs-cxl
index fe61d372e3fa..4c0f62f881ca 100644
--- a/Documentation/ABI/testing/debugfs-cxl
+++ b/Documentation/ABI/testing/debugfs-cxl
@@ -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.
diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
index e59d9d37aa65..eeeb6e53fdc4 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,
@@ -1149,6 +1184,8 @@ __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 +2258,11 @@ 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();
Jonathan Cameron March 7, 2024, 12:10 p.m. UTC | #2
On Tue, 27 Feb 2024 14:14:35 -0600
Ben Cheatham <benjamin.cheatham@amd.com> wrote:

> This patch also had an outdated commit message (still referenced the einj-cxl module).
> The patch with the updated commit message is below. I also made a tiny change to
> the format specifier of the einj_inject file to "0x%llx\n" from "%llx\n".
> 
> Thanks,
> Ben
> 
> From 321129893da9129473c447772a461c1a4e9e0e9d Mon Sep 17 00:00:00 2001
> From: Ben Cheatham <Benjamin.Cheatham@amd.com>
> Date: Fri, 16 Feb 2024 11:17:01 -0600
> Subject: [PATCH v14 3/4] cxl/core: Add CXL EINJ debugfs files
> 
> Export CXL helper functions in einj-cxl.c for getting/injecting
> available CXL protocol error types 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 file 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 $dport_dev.
> 
> Signed-off-by: Ben Cheatham <Benjamin.Cheatham@amd.com>
LGTM other than not sending patches like this as tooling won't pick them up!
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Ben Cheatham March 7, 2024, 2:46 p.m. UTC | #3
On 3/7/24 6:10 AM, Jonathan Cameron wrote:
> On Tue, 27 Feb 2024 14:14:35 -0600
> Ben Cheatham <benjamin.cheatham@amd.com> wrote:
> 
>> This patch also had an outdated commit message (still referenced the einj-cxl module).
>> The patch with the updated commit message is below. I also made a tiny change to
>> the format specifier of the einj_inject file to "0x%llx\n" from "%llx\n".
>>
>> Thanks,
>> Ben
>>
>> From 321129893da9129473c447772a461c1a4e9e0e9d Mon Sep 17 00:00:00 2001
>> From: Ben Cheatham <Benjamin.Cheatham@amd.com>
>> Date: Fri, 16 Feb 2024 11:17:01 -0600
>> Subject: [PATCH v14 3/4] cxl/core: Add CXL EINJ debugfs files
>>
>> Export CXL helper functions in einj-cxl.c for getting/injecting
>> available CXL protocol error types to sysfs under kernel/debug/cxl.
>>
>> The kernel/debug/cxl/einj_types file will print the available CXL
>> protocol errors in the same format as the available_error_types
>> file provided by the einj module. The
>> kernel/debug/cxl/$dport_dev/einj_inject file 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>
> LGTM other than not sending patches like this as tooling won't pick them up!
> Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
> 

Yeah I normally wouldn't send it in this way, but I caught what needed changes
before most people started to review and didn't want to make a whole new version
for them (especially since the version number is quite high already). I probably
should've just waited a day or two and double checked before sending it out in
hindsight.

Thanks,
Ben
diff mbox series

Patch

diff --git a/Documentation/ABI/testing/debugfs-cxl b/Documentation/ABI/testing/debugfs-cxl
index fe61d372e3fa..4c0f62f881ca 100644
--- a/Documentation/ABI/testing/debugfs-cxl
+++ b/Documentation/ABI/testing/debugfs-cxl
@@ -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.
diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
index e59d9d37aa65..3b579eef4d23 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 +794,39 @@  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_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,
@@ -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_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();