* [PATCH v3 13/27] powerpc/powernv/pmem: Read the capability registers & wait for device ready
From: Alastair D'Silva @ 2020-02-21 3:27 UTC (permalink / raw)
To: alastair
Cc: Madhavan Srinivasan, Alexey Kardashevskiy, Masahiro Yamada,
Oliver O'Halloran, Mauro Carvalho Chehab, Ira Weiny,
Thomas Gleixner, Rob Herring, Dave Jiang, linux-nvdimm,
Aneesh Kumar K . V, Krzysztof Kozlowski, Anju T Sudhakar,
Mahesh Salgaonkar, Andrew Donnellan, Arnd Bergmann, Greg Kurz,
Nicholas Piggin, Cédric Le Goater, Dan Williams,
Hari Bathini, linux-mm, Greg Kroah-Hartman, linux-kernel,
Vishal Verma, Frederic Barrat, Paul Mackerras, Andrew Morton,
linuxppc-dev, David S. Miller
In-Reply-To: <20200221032720.33893-1-alastair@au1.ibm.com>
From: Alastair D'Silva <alastair@d-silva.org>
This patch reads timeouts & firmware version from the controller, and
uses those timeouts to wait for the controller to report that it is ready
before handing the memory over to libnvdimm.
Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
---
arch/powerpc/platforms/powernv/pmem/Makefile | 2 +-
arch/powerpc/platforms/powernv/pmem/ocxl.c | 92 +++++++++++++++++++
.../platforms/powernv/pmem/ocxl_internal.c | 19 ++++
.../platforms/powernv/pmem/ocxl_internal.h | 24 +++++
4 files changed, 136 insertions(+), 1 deletion(-)
create mode 100644 arch/powerpc/platforms/powernv/pmem/ocxl_internal.c
diff --git a/arch/powerpc/platforms/powernv/pmem/Makefile b/arch/powerpc/platforms/powernv/pmem/Makefile
index 1c55c4193175..4ceda25907d4 100644
--- a/arch/powerpc/platforms/powernv/pmem/Makefile
+++ b/arch/powerpc/platforms/powernv/pmem/Makefile
@@ -4,4 +4,4 @@ ccflags-$(CONFIG_PPC_WERROR) += -Werror
obj-$(CONFIG_OCXL_PMEM) += ocxlpmem.o
-ocxlpmem-y := ocxl.o
+ocxlpmem-y := ocxl.o ocxl_internal.o
diff --git a/arch/powerpc/platforms/powernv/pmem/ocxl.c b/arch/powerpc/platforms/powernv/pmem/ocxl.c
index 3c4eeb5dcc0f..431212c9f0cc 100644
--- a/arch/powerpc/platforms/powernv/pmem/ocxl.c
+++ b/arch/powerpc/platforms/powernv/pmem/ocxl.c
@@ -8,6 +8,7 @@
#include <linux/module.h>
#include <misc/ocxl.h>
+#include <linux/delay.h>
#include <linux/ndctl.h>
#include <linux/mm_types.h>
#include <linux/memory_hotplug.h>
@@ -215,6 +216,36 @@ static int register_lpc_mem(struct ocxlpmem *ocxlpmem)
return 0;
}
+/**
+ * is_usable() - Is a controller usable?
+ * @ocxlpmem: the device metadata
+ * @verbose: True to log errors
+ * Return: true if the controller is usable
+ */
+static bool is_usable(const struct ocxlpmem *ocxlpmem, bool verbose)
+{
+ u64 chi = 0;
+ int rc = ocxlpmem_chi(ocxlpmem, &chi);
+
+ if (rc < 0)
+ return false;
+
+ if (!(chi & GLOBAL_MMIO_CHI_CRDY)) {
+ if (verbose)
+ dev_err(&ocxlpmem->dev, "controller is not ready.\n");
+ return false;
+ }
+
+ if (!(chi & GLOBAL_MMIO_CHI_MA)) {
+ if (verbose)
+ dev_err(&ocxlpmem->dev,
+ "controller does not have memory available.\n");
+ return false;
+ }
+
+ return true;
+}
+
/**
* allocate_minor() - Allocate a minor number to use for an OpenCAPI pmem device
* @ocxlpmem: the device metadata
@@ -328,6 +359,48 @@ static void ocxlpmem_remove(struct pci_dev *pdev)
}
}
+/**
+ * read_device_metadata() - Retrieve config information from the AFU and save it for future use
+ * @ocxlpmem: the device metadata
+ * Return: 0 on success, negative on failure
+ */
+static int read_device_metadata(struct ocxlpmem *ocxlpmem)
+{
+ u64 val;
+ int rc;
+
+ rc = ocxl_global_mmio_read64(ocxlpmem->ocxl_afu, GLOBAL_MMIO_CCAP0,
+ OCXL_LITTLE_ENDIAN, &val);
+ if (rc)
+ return rc;
+
+ ocxlpmem->scm_revision = val & 0xFFFF;
+ ocxlpmem->read_latency = (val >> 32) & 0xFF;
+ ocxlpmem->readiness_timeout = (val >> 48) & 0x0F;
+ ocxlpmem->memory_available_timeout = val >> 52;
+
+ rc = ocxl_global_mmio_read64(ocxlpmem->ocxl_afu, GLOBAL_MMIO_CCAP1,
+ OCXL_LITTLE_ENDIAN, &val);
+ if (rc)
+ return rc;
+
+ ocxlpmem->max_controller_dump_size = val & 0xFFFFFFFF;
+
+ // Extract firmware version text
+ rc = ocxl_global_mmio_read64(ocxlpmem->ocxl_afu, GLOBAL_MMIO_FWVER,
+ OCXL_HOST_ENDIAN, (u64 *)ocxlpmem->fw_version);
+ if (rc)
+ return rc;
+
+ ocxlpmem->fw_version[8] = '\0';
+
+ dev_info(&ocxlpmem->dev,
+ "Firmware version '%s' SCM revision %d:%d\n", ocxlpmem->fw_version,
+ ocxlpmem->scm_revision >> 4, ocxlpmem->scm_revision & 0x0F);
+
+ return 0;
+}
+
/**
* probe_function0() - Set up function 0 for an OpenCAPI persistent memory device
* This is important as it enables templates higher than 0 across all other functions,
@@ -368,6 +441,7 @@ static int probe(struct pci_dev *pdev, const struct pci_device_id *ent)
{
struct ocxlpmem *ocxlpmem;
int rc;
+ u16 elapsed, timeout;
if (PCI_FUNC(pdev->devfn) == 0)
return probe_function0(pdev);
@@ -422,6 +496,24 @@ static int probe(struct pci_dev *pdev, const struct pci_device_id *ent)
goto err;
}
+ if (read_device_metadata(ocxlpmem)) {
+ dev_err(&pdev->dev, "Could not read metadata\n");
+ goto err;
+ }
+
+ elapsed = 0;
+ timeout = ocxlpmem->readiness_timeout + ocxlpmem->memory_available_timeout;
+ while (!is_usable(ocxlpmem, false)) {
+ if (elapsed++ > timeout) {
+ dev_warn(&ocxlpmem->dev, "OpenCAPI Persistent Memory ready timeout.\n");
+ (void)is_usable(ocxlpmem, true);
+ rc = -ENXIO;
+ goto err;
+ }
+
+ msleep(1000);
+ }
+
rc = register_lpc_mem(ocxlpmem);
if (rc) {
dev_err(&pdev->dev, "Could not register OpenCAPI persistent memory with libnvdimm\n");
diff --git a/arch/powerpc/platforms/powernv/pmem/ocxl_internal.c b/arch/powerpc/platforms/powernv/pmem/ocxl_internal.c
new file mode 100644
index 000000000000..617ca943b1b8
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/pmem/ocxl_internal.c
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright 2019 IBM Corp.
+
+#include <misc/ocxl.h>
+#include <linux/delay.h>
+#include "ocxl_internal.h"
+
+int ocxlpmem_chi(const struct ocxlpmem *ocxlpmem, u64 *chi)
+{
+ u64 val;
+ int rc = ocxl_global_mmio_read64(ocxlpmem->ocxl_afu, GLOBAL_MMIO_CHI,
+ OCXL_LITTLE_ENDIAN, &val);
+ if (rc)
+ return rc;
+
+ *chi = val;
+
+ return 0;
+}
diff --git a/arch/powerpc/platforms/powernv/pmem/ocxl_internal.h b/arch/powerpc/platforms/powernv/pmem/ocxl_internal.h
index 9cf3e42750e7..ba0301533d00 100644
--- a/arch/powerpc/platforms/powernv/pmem/ocxl_internal.h
+++ b/arch/powerpc/platforms/powernv/pmem/ocxl_internal.h
@@ -97,4 +97,28 @@ struct ocxlpmem {
void *metadata_addr;
struct resource pmem_res;
struct nd_region *nd_region;
+ char fw_version[8+1];
+
+ u32 max_controller_dump_size;
+ u16 scm_revision; // major/minor
+ u8 readiness_timeout; /* The worst case time (in seconds) that the host shall
+ * wait for the controller to become operational following a reset (CHI.CRDY).
+ */
+ u8 memory_available_timeout; /* The worst case time (in seconds) that the host shall
+ * wait for memory to become available following a reset (CHI.MA).
+ */
+
+ u16 read_latency; /* The nominal measure of latency (in nanoseconds)
+ * associated with an unassisted read of a memory block.
+ * This represents the capability of the raw media technology without assistance
+ */
};
+
+/**
+ * ocxlpmem_chi() - Get the value of the CHI register
+ * @ocxlpmem: the device metadata
+ * @chi: returns the CHI value
+ *
+ * Returns 0 on success, negative on error
+ */
+int ocxlpmem_chi(const struct ocxlpmem *ocxlpmem, u64 *chi);
--
2.24.1
^ permalink raw reply related
* [PATCH v3 24/27] powerpc/powernv/pmem: Expose SMART data via ndctl
From: Alastair D'Silva @ 2020-02-21 3:27 UTC (permalink / raw)
To: alastair
Cc: Madhavan Srinivasan, Alexey Kardashevskiy, Masahiro Yamada,
Oliver O'Halloran, Mauro Carvalho Chehab, Ira Weiny,
Thomas Gleixner, Rob Herring, Dave Jiang, linux-nvdimm,
Aneesh Kumar K . V, Krzysztof Kozlowski, Anju T Sudhakar,
Mahesh Salgaonkar, Andrew Donnellan, Arnd Bergmann, Greg Kurz,
Nicholas Piggin, Cédric Le Goater, Dan Williams,
Hari Bathini, linux-mm, Greg Kroah-Hartman, linux-kernel,
Vishal Verma, Frederic Barrat, Paul Mackerras, Andrew Morton,
linuxppc-dev, David S. Miller
In-Reply-To: <20200221032720.33893-1-alastair@au1.ibm.com>
From: Alastair D'Silva <alastair@d-silva.org>
This patch retrieves proprietary formatted SMART data and makes it
available via ndctl. A later contribution will be made to ndctl to
parse this data.
Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
---
arch/powerpc/platforms/powernv/pmem/ocxl.c | 128 ++++++++++++++++++
.../platforms/powernv/pmem/ocxl_internal.h | 18 +++
include/uapi/linux/ndctl.h | 1 +
3 files changed, 147 insertions(+)
diff --git a/arch/powerpc/platforms/powernv/pmem/ocxl.c b/arch/powerpc/platforms/powernv/pmem/ocxl.c
index d4ce5e9e0521..5cd1b6d78dd6 100644
--- a/arch/powerpc/platforms/powernv/pmem/ocxl.c
+++ b/arch/powerpc/platforms/powernv/pmem/ocxl.c
@@ -81,6 +81,129 @@ static int ndctl_config_size(struct nd_cmd_get_config_size *command)
return 0;
}
+/**
+ * smart_header_parse() - Parse the first 64 bits of the SMART admin command response
+ * @ocxlpmem: the device metadata
+ * @length: out, returns the number of bytes in the response (excluding the 64 bit header)
+ */
+static int smart_header_parse(struct ocxlpmem *ocxlpmem, u32 *length)
+{
+ int rc;
+ u64 val;
+
+ u16 data_identifier;
+ u32 data_length;
+
+ rc = ocxl_global_mmio_read64(ocxlpmem->ocxl_afu,
+ ocxlpmem->admin_command.data_offset,
+ OCXL_LITTLE_ENDIAN, &val);
+ if (rc)
+ return rc;
+
+ data_identifier = val >> 48;
+ data_length = val & 0xFFFFFFFF;
+
+ if (data_identifier != 0x534D) { // 'SM'
+ dev_err(&ocxlpmem->dev,
+ "Bad data identifier for smart data, expected 'SM', got '%-.*s'\n",
+ 2, (char *)&data_identifier);
+ return -EINVAL;
+ }
+
+ *length = data_length;
+ return 0;
+}
+
+static int ndctl_smart(struct ocxlpmem *ocxlpmem, struct nd_cmd_pkg *pkg)
+{
+ u32 length, i;
+ struct nd_ocxl_smart *out;
+ int rc;
+
+ mutex_lock(&ocxlpmem->admin_command.lock);
+
+ rc = admin_command_request(ocxlpmem, ADMIN_COMMAND_SMART);
+ if (rc)
+ goto out;
+
+ rc = admin_command_execute(ocxlpmem);
+ if (rc)
+ goto out;
+
+ rc = admin_command_complete_timeout(ocxlpmem, ADMIN_COMMAND_SMART);
+ if (rc < 0) {
+ dev_err(&ocxlpmem->dev, "SMART timeout\n");
+ goto out;
+ }
+
+ rc = admin_response(ocxlpmem);
+ if (rc < 0)
+ goto out;
+ if (rc != STATUS_SUCCESS) {
+ warn_status(ocxlpmem, "Unexpected status from SMART", rc);
+ goto out;
+ }
+
+ rc = smart_header_parse(ocxlpmem, &length);
+ if (rc)
+ goto out;
+
+ pkg->nd_fw_size = length;
+
+ length = min(length, pkg->nd_size_out); // bytes
+ out = (struct nd_ocxl_smart *)pkg->nd_payload;
+ // Each SMART attribute is 2 * 64 bits
+ out->count = length / (2 * sizeof(u64)); // attributes
+
+ for (i = 0; i < length; i += sizeof(u64)) {
+ rc = ocxl_global_mmio_read64(ocxlpmem->ocxl_afu,
+ ocxlpmem->admin_command.data_offset + sizeof(u64) + i,
+ OCXL_LITTLE_ENDIAN,
+ &out->attribs[i/sizeof(u64)]);
+ if (rc)
+ goto out;
+ }
+
+ rc = admin_response_handled(ocxlpmem);
+ if (rc)
+ goto out;
+
+ rc = 0;
+ goto out;
+
+out:
+ mutex_unlock(&ocxlpmem->admin_command.lock);
+ return rc;
+}
+
+static int ndctl_call(struct ocxlpmem *ocxlpmem, void *buf, unsigned int buf_len)
+{
+ struct nd_cmd_pkg *pkg = buf;
+
+ if (buf_len < sizeof(struct nd_cmd_pkg)) {
+ dev_err(&ocxlpmem->dev, "Invalid ND_CALL size=%u\n", buf_len);
+ return -EINVAL;
+ }
+
+ if (pkg->nd_family != NVDIMM_FAMILY_OCXL) {
+ dev_err(&ocxlpmem->dev, "Invalid ND_CALL family=0x%llx\n", pkg->nd_family);
+ return -EINVAL;
+ }
+
+ switch (pkg->nd_command) {
+ case ND_CMD_OCXL_SMART:
+ ndctl_smart(ocxlpmem, pkg);
+ break;
+
+ default:
+ dev_err(&ocxlpmem->dev, "Invalid ND_CALL command=0x%llx\n", pkg->nd_command);
+ return -EINVAL;
+ }
+
+
+ return 0;
+}
+
static int ndctl(struct nvdimm_bus_descriptor *nd_desc,
struct nvdimm *nvdimm,
unsigned int cmd, void *buf, unsigned int buf_len, int *cmd_rc)
@@ -88,6 +211,10 @@ static int ndctl(struct nvdimm_bus_descriptor *nd_desc,
struct ocxlpmem *ocxlpmem = container_of(nd_desc, struct ocxlpmem, bus_desc);
switch (cmd) {
+ case ND_CMD_CALL:
+ *cmd_rc = ndctl_call(ocxlpmem, buf, buf_len);
+ return 0;
+
case ND_CMD_GET_CONFIG_SIZE:
*cmd_rc = ndctl_config_size(buf);
return 0;
@@ -171,6 +298,7 @@ static int register_lpc_mem(struct ocxlpmem *ocxlpmem)
set_bit(ND_CMD_GET_CONFIG_SIZE, &nvdimm_cmd_mask);
set_bit(ND_CMD_GET_CONFIG_DATA, &nvdimm_cmd_mask);
set_bit(ND_CMD_SET_CONFIG_DATA, &nvdimm_cmd_mask);
+ set_bit(ND_CMD_CALL, &nvdimm_cmd_mask);
set_bit(NDD_ALIASING, &nvdimm_flags);
diff --git a/arch/powerpc/platforms/powernv/pmem/ocxl_internal.h b/arch/powerpc/platforms/powernv/pmem/ocxl_internal.h
index 927690f4888f..0eb7a35d24ae 100644
--- a/arch/powerpc/platforms/powernv/pmem/ocxl_internal.h
+++ b/arch/powerpc/platforms/powernv/pmem/ocxl_internal.h
@@ -7,6 +7,7 @@
#include <linux/libnvdimm.h>
#include <uapi/nvdimm/ocxl-pmem.h>
#include <linux/mm.h>
+#include <linux/ndctl.h>
#define LABEL_AREA_SIZE (1UL << PA_SECTION_SHIFT)
#define DEFAULT_TIMEOUT 100
@@ -98,6 +99,23 @@ struct ocxlpmem_function0 {
struct ocxl_fn *ocxl_fn;
};
+struct nd_ocxl_smart {
+ __u8 count;
+ __u8 reserved[7];
+ __u64 attribs[0];
+} __packed;
+
+struct nd_pkg_ocxl {
+ struct nd_cmd_pkg gen;
+ union {
+ struct nd_ocxl_smart smart;
+ };
+};
+
+enum nd_cmd_ocxl {
+ ND_CMD_OCXL_SMART = 1,
+};
+
struct ocxlpmem {
struct device dev;
struct pci_dev *pdev;
diff --git a/include/uapi/linux/ndctl.h b/include/uapi/linux/ndctl.h
index de5d90212409..2885052e7f40 100644
--- a/include/uapi/linux/ndctl.h
+++ b/include/uapi/linux/ndctl.h
@@ -244,6 +244,7 @@ struct nd_cmd_pkg {
#define NVDIMM_FAMILY_HPE2 2
#define NVDIMM_FAMILY_MSFT 3
#define NVDIMM_FAMILY_HYPERV 4
+#define NVDIMM_FAMILY_OCXL 6
#define ND_IOCTL_CALL _IOWR(ND_IOCTL, ND_CMD_CALL,\
struct nd_cmd_pkg)
--
2.24.1
^ permalink raw reply related
* [PATCH v3 11/27] powerpc: Enable the OpenCAPI Persistent Memory driver for powernv_defconfig
From: Alastair D'Silva @ 2020-02-21 3:27 UTC (permalink / raw)
To: alastair
Cc: Madhavan Srinivasan, Alexey Kardashevskiy, Masahiro Yamada,
Oliver O'Halloran, Mauro Carvalho Chehab, Ira Weiny,
Thomas Gleixner, Rob Herring, Dave Jiang, linux-nvdimm,
Aneesh Kumar K . V, Krzysztof Kozlowski, Anju T Sudhakar,
Mahesh Salgaonkar, Andrew Donnellan, Arnd Bergmann, Greg Kurz,
Nicholas Piggin, Cédric Le Goater, Dan Williams,
Hari Bathini, linux-mm, Greg Kroah-Hartman, linux-kernel,
Vishal Verma, Frederic Barrat, Paul Mackerras, Andrew Morton,
linuxppc-dev, David S. Miller
In-Reply-To: <20200221032720.33893-1-alastair@au1.ibm.com>
From: Alastair D'Silva <alastair@d-silva.org>
This patch enables the OpenCAPI Persistent Memory driver, as well
as DAX support, for the 'powernv' platform.
DAX is not a strict requirement for the functioning of the driver, but it
is likely that a user will want to create a DAX device on top of their
persistent memory device.
Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
---
arch/powerpc/configs/powernv_defconfig | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/arch/powerpc/configs/powernv_defconfig b/arch/powerpc/configs/powernv_defconfig
index 71749377d164..921d77bbd3d2 100644
--- a/arch/powerpc/configs/powernv_defconfig
+++ b/arch/powerpc/configs/powernv_defconfig
@@ -348,3 +348,8 @@ CONFIG_KVM_BOOK3S_64=m
CONFIG_KVM_BOOK3S_64_HV=m
CONFIG_VHOST_NET=m
CONFIG_PRINTK_TIME=y
+CONFIG_ZONE_DEVICE=y
+CONFIG_OCXL_PMEM=m
+CONFIG_DEV_DAX=m
+CONFIG_DEV_DAX_PMEM=m
+CONFIG_FS_DAX=y
--
2.24.1
^ permalink raw reply related
* [PATCH v3 18/27] powerpc/powernv/pmem: Add controller dump IOCTLs
From: Alastair D'Silva @ 2020-02-21 3:27 UTC (permalink / raw)
To: alastair
Cc: Madhavan Srinivasan, Alexey Kardashevskiy, Masahiro Yamada,
Oliver O'Halloran, Mauro Carvalho Chehab, Ira Weiny,
Thomas Gleixner, Rob Herring, Dave Jiang, linux-nvdimm,
Aneesh Kumar K . V, Krzysztof Kozlowski, Anju T Sudhakar,
Mahesh Salgaonkar, Andrew Donnellan, Arnd Bergmann, Greg Kurz,
Nicholas Piggin, Cédric Le Goater, Dan Williams,
Hari Bathini, linux-mm, Greg Kroah-Hartman, linux-kernel,
Vishal Verma, Frederic Barrat, Paul Mackerras, Andrew Morton,
linuxppc-dev, David S. Miller
In-Reply-To: <20200221032720.33893-1-alastair@au1.ibm.com>
From: Alastair D'Silva <alastair@d-silva.org>
This patch adds IOCTLs to allow userspace to request & fetch dumps
of the internal controller state.
This is useful during debugging or when a fatal error on the controller
has occurred.
Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
---
arch/powerpc/platforms/powernv/pmem/ocxl.c | 132 +++++++++++++++++++++
include/uapi/nvdimm/ocxl-pmem.h | 15 +++
2 files changed, 147 insertions(+)
diff --git a/arch/powerpc/platforms/powernv/pmem/ocxl.c b/arch/powerpc/platforms/powernv/pmem/ocxl.c
index 2b64504f9129..2cabafe1fc58 100644
--- a/arch/powerpc/platforms/powernv/pmem/ocxl.c
+++ b/arch/powerpc/platforms/powernv/pmem/ocxl.c
@@ -640,6 +640,124 @@ static int ioctl_error_log(struct ocxlpmem *ocxlpmem,
return 0;
}
+static int ioctl_controller_dump_data(struct ocxlpmem *ocxlpmem,
+ struct ioctl_ocxl_pmem_controller_dump_data __user *uarg)
+{
+ struct ioctl_ocxl_pmem_controller_dump_data args;
+ u16 i;
+ u64 val;
+ int rc;
+
+ if (copy_from_user(&args, uarg, sizeof(args)))
+ return -EFAULT;
+
+ if (args.buf_size % 8)
+ return -EINVAL;
+
+ if (args.buf_size > ocxlpmem->admin_command.data_size)
+ return -EINVAL;
+
+ mutex_lock(&ocxlpmem->admin_command.lock);
+
+ rc = admin_command_request(ocxlpmem, ADMIN_COMMAND_CONTROLLER_DUMP);
+ if (rc)
+ goto out;
+
+ val = ((u64)args.offset) << 32;
+ val |= args.buf_size;
+ rc = ocxl_global_mmio_write64(ocxlpmem->ocxl_afu,
+ ocxlpmem->admin_command.request_offset + 0x08,
+ OCXL_LITTLE_ENDIAN, val);
+ if (rc)
+ goto out;
+
+ rc = admin_command_execute(ocxlpmem);
+ if (rc)
+ goto out;
+
+ rc = admin_command_complete_timeout(ocxlpmem,
+ ADMIN_COMMAND_CONTROLLER_DUMP);
+ if (rc < 0) {
+ dev_warn(&ocxlpmem->dev, "Controller dump timed out\n");
+ goto out;
+ }
+
+ rc = admin_response(ocxlpmem);
+ if (rc < 0)
+ goto out;
+ if (rc != STATUS_SUCCESS) {
+ warn_status(ocxlpmem,
+ "Unexpected status from retrieve error log",
+ rc);
+ goto out;
+ }
+
+ for (i = 0; i < args.buf_size; i += 8) {
+ u64 val;
+
+ rc = ocxl_global_mmio_read64(ocxlpmem->ocxl_afu,
+ ocxlpmem->admin_command.data_offset + i,
+ OCXL_HOST_ENDIAN, &val);
+ if (rc)
+ goto out;
+
+ if (copy_to_user(&args.buf[i], &val, sizeof(u64))) {
+ rc = -EFAULT;
+ goto out;
+ }
+ }
+
+ if (copy_to_user(uarg, &args, sizeof(args))) {
+ rc = -EFAULT;
+ goto out;
+ }
+
+ rc = admin_response_handled(ocxlpmem);
+ if (rc)
+ goto out;
+
+out:
+ mutex_unlock(&ocxlpmem->admin_command.lock);
+ return rc;
+}
+
+int request_controller_dump(struct ocxlpmem *ocxlpmem)
+{
+ int rc;
+ u64 busy = 1;
+
+ rc = ocxl_global_mmio_set64(ocxlpmem->ocxl_afu, GLOBAL_MMIO_CHIC,
+ OCXL_LITTLE_ENDIAN,
+ GLOBAL_MMIO_CHI_CDA);
+
+
+ rc = ocxl_global_mmio_set64(ocxlpmem->ocxl_afu, GLOBAL_MMIO_HCI,
+ OCXL_LITTLE_ENDIAN,
+ GLOBAL_MMIO_HCI_CONTROLLER_DUMP);
+ if (rc)
+ return rc;
+
+ while (busy) {
+ rc = ocxl_global_mmio_read64(ocxlpmem->ocxl_afu,
+ GLOBAL_MMIO_HCI,
+ OCXL_LITTLE_ENDIAN, &busy);
+ if (rc)
+ return rc;
+
+ busy &= GLOBAL_MMIO_HCI_CONTROLLER_DUMP;
+ cond_resched();
+ }
+
+ return 0;
+}
+
+static int ioctl_controller_dump_complete(struct ocxlpmem *ocxlpmem)
+{
+ return ocxl_global_mmio_set64(ocxlpmem->ocxl_afu, GLOBAL_MMIO_HCI,
+ OCXL_LITTLE_ENDIAN,
+ GLOBAL_MMIO_HCI_CONTROLLER_DUMP_COLLECTED);
+}
+
static long file_ioctl(struct file *file, unsigned int cmd, unsigned long args)
{
struct ocxlpmem *ocxlpmem = file->private_data;
@@ -650,7 +768,21 @@ static long file_ioctl(struct file *file, unsigned int cmd, unsigned long args)
rc = ioctl_error_log(ocxlpmem,
(struct ioctl_ocxl_pmem_error_log __user *)args);
break;
+
+ case IOCTL_OCXL_PMEM_CONTROLLER_DUMP:
+ rc = request_controller_dump(ocxlpmem);
+ break;
+
+ case IOCTL_OCXL_PMEM_CONTROLLER_DUMP_DATA:
+ rc = ioctl_controller_dump_data(ocxlpmem,
+ (struct ioctl_ocxl_pmem_controller_dump_data __user *)args);
+ break;
+
+ case IOCTL_OCXL_PMEM_CONTROLLER_DUMP_COMPLETE:
+ rc = ioctl_controller_dump_complete(ocxlpmem);
+ break;
}
+
return rc;
}
diff --git a/include/uapi/nvdimm/ocxl-pmem.h b/include/uapi/nvdimm/ocxl-pmem.h
index b10f8ac0c20f..d4d8512d03f7 100644
--- a/include/uapi/nvdimm/ocxl-pmem.h
+++ b/include/uapi/nvdimm/ocxl-pmem.h
@@ -38,9 +38,24 @@ struct ioctl_ocxl_pmem_error_log {
__u8 *buf; /* pointer to output buffer */
};
+struct ioctl_ocxl_pmem_controller_dump_data {
+ __u8 *buf; /* pointer to output buffer */
+ __u16 buf_size; /* in/out, buffer size provided/required.
+ * If required is greater than provided, the buffer
+ * will be truncated to the amount provided. If its
+ * less, then only the required bytes will be populated.
+ * If it is 0, then there is no more dump data available.
+ */
+ __u32 offset; /* in, Offset within the dump */
+ __u64 reserved[8];
+};
+
/* ioctl numbers */
#define OCXL_PMEM_MAGIC 0x5C
/* SCM devices */
#define IOCTL_OCXL_PMEM_ERROR_LOG _IOWR(OCXL_PMEM_MAGIC, 0x01, struct ioctl_ocxl_pmem_error_log)
+#define IOCTL_OCXL_PMEM_CONTROLLER_DUMP _IO(OCXL_PMEM_MAGIC, 0x02)
+#define IOCTL_OCXL_PMEM_CONTROLLER_DUMP_DATA _IOWR(OCXL_PMEM_MAGIC, 0x03, struct ioctl_ocxl_pmem_controller_dump_data)
+#define IOCTL_OCXL_PMEM_CONTROLLER_DUMP_COMPLETE _IO(OCXL_PMEM_MAGIC, 0x04)
#endif /* _UAPI_OCXL_SCM_H */
--
2.24.1
^ permalink raw reply related
* [PATCH v3 15/27] powerpc/powernv/pmem: Add support for near storage commands
From: Alastair D'Silva @ 2020-02-21 3:27 UTC (permalink / raw)
To: alastair
Cc: Madhavan Srinivasan, Alexey Kardashevskiy, Masahiro Yamada,
Oliver O'Halloran, Mauro Carvalho Chehab, Ira Weiny,
Thomas Gleixner, Rob Herring, Dave Jiang, linux-nvdimm,
Aneesh Kumar K . V, Krzysztof Kozlowski, Anju T Sudhakar,
Mahesh Salgaonkar, Andrew Donnellan, Arnd Bergmann, Greg Kurz,
Nicholas Piggin, Cédric Le Goater, Dan Williams,
Hari Bathini, linux-mm, Greg Kroah-Hartman, linux-kernel,
Vishal Verma, Frederic Barrat, Paul Mackerras, Andrew Morton,
linuxppc-dev, David S. Miller
In-Reply-To: <20200221032720.33893-1-alastair@au1.ibm.com>
From: Alastair D'Silva <alastair@d-silva.org>
Similar to the previous patch, this adds support for near storage commands.
Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
---
arch/powerpc/platforms/powernv/pmem/ocxl.c | 6 +++
.../platforms/powernv/pmem/ocxl_internal.c | 41 +++++++++++++++++++
.../platforms/powernv/pmem/ocxl_internal.h | 37 +++++++++++++++++
3 files changed, 84 insertions(+)
diff --git a/arch/powerpc/platforms/powernv/pmem/ocxl.c b/arch/powerpc/platforms/powernv/pmem/ocxl.c
index 4e782d22605b..b8bd7e703b19 100644
--- a/arch/powerpc/platforms/powernv/pmem/ocxl.c
+++ b/arch/powerpc/platforms/powernv/pmem/ocxl.c
@@ -259,12 +259,18 @@ static int setup_command_metadata(struct ocxlpmem *ocxlpmem)
int rc;
mutex_init(&ocxlpmem->admin_command.lock);
+ mutex_init(&ocxlpmem->ns_command.lock);
rc = extract_command_metadata(ocxlpmem, GLOBAL_MMIO_ACMA_CREQO,
&ocxlpmem->admin_command);
if (rc)
return rc;
+ rc = extract_command_metadata(ocxlpmem, GLOBAL_MMIO_NSCMA_CREQO,
+ &ocxlpmem->ns_command);
+ if (rc)
+ return rc;
+
return 0;
}
diff --git a/arch/powerpc/platforms/powernv/pmem/ocxl_internal.c b/arch/powerpc/platforms/powernv/pmem/ocxl_internal.c
index 583f48023025..3e0b133feddf 100644
--- a/arch/powerpc/platforms/powernv/pmem/ocxl_internal.c
+++ b/arch/powerpc/platforms/powernv/pmem/ocxl_internal.c
@@ -133,6 +133,47 @@ int admin_response_handled(const struct ocxlpmem *ocxlpmem)
OCXL_LITTLE_ENDIAN, GLOBAL_MMIO_CHI_ACRA);
}
+int ns_command_request(struct ocxlpmem *ocxlpmem, u8 op_code)
+{
+ u64 val;
+ int rc = ocxl_global_mmio_read64(ocxlpmem->ocxl_afu, GLOBAL_MMIO_CHI,
+ OCXL_LITTLE_ENDIAN, &val);
+ if (rc)
+ return rc;
+
+ if (!(val & GLOBAL_MMIO_CHI_NSCRA))
+ return -EBUSY;
+
+ return scm_command_request(ocxlpmem, &ocxlpmem->ns_command, op_code);
+}
+
+int ns_response(const struct ocxlpmem *ocxlpmem)
+{
+ return command_response(ocxlpmem, &ocxlpmem->ns_command);
+}
+
+int ns_command_execute(const struct ocxlpmem *ocxlpmem)
+{
+ return ocxl_global_mmio_set64(ocxlpmem->ocxl_afu, GLOBAL_MMIO_HCI,
+ OCXL_LITTLE_ENDIAN, GLOBAL_MMIO_HCI_NSCRW);
+}
+
+bool ns_command_complete(const struct ocxlpmem *ocxlpmem)
+{
+ u64 val = 0;
+ int rc = ocxlpmem_chi(ocxlpmem, &val);
+
+ WARN_ON(rc);
+
+ return (val & GLOBAL_MMIO_CHI_NSCRA) != 0;
+}
+
+int ns_response_handled(const struct ocxlpmem *ocxlpmem)
+{
+ return ocxl_global_mmio_set64(ocxlpmem->ocxl_afu, GLOBAL_MMIO_CHIC,
+ OCXL_LITTLE_ENDIAN, GLOBAL_MMIO_CHI_NSCRA);
+}
+
void warn_status(const struct ocxlpmem *ocxlpmem, const char *message,
u8 status)
{
diff --git a/arch/powerpc/platforms/powernv/pmem/ocxl_internal.h b/arch/powerpc/platforms/powernv/pmem/ocxl_internal.h
index 2fef68c71271..28e2020f6355 100644
--- a/arch/powerpc/platforms/powernv/pmem/ocxl_internal.h
+++ b/arch/powerpc/platforms/powernv/pmem/ocxl_internal.h
@@ -107,6 +107,7 @@ struct ocxlpmem {
struct ocxl_context *ocxl_context;
void *metadata_addr;
struct command_metadata admin_command;
+ struct command_metadata ns_command;
struct resource pmem_res;
struct nd_region *nd_region;
char fw_version[8+1];
@@ -175,6 +176,42 @@ int admin_command_complete_timeout(const struct ocxlpmem *ocxlpmem,
*/
int admin_response_handled(const struct ocxlpmem *ocxlpmem);
+/**
+ * ns_command_request() - Issue a near storage command request
+ * @ocxlpmem: the device metadata
+ * @op_code: The op-code for the command
+ * Returns an identifier for the command, or negative on error
+ */
+int ns_command_request(struct ocxlpmem *ocxlpmem, u8 op_code);
+
+/**
+ * ns_response() - Validate a near storage response
+ * @ocxlpmem: the device metadata
+ * Returns the status code of the command, or negative on error
+ */
+int ns_response(const struct ocxlpmem *ocxlpmem);
+
+/**
+ * ns_command_execute() - Notify the controller to start processing a pending near storage command
+ * @ocxlpmem: the device metadata
+ * Returns 0 on success, negative on error
+ */
+int ns_command_execute(const struct ocxlpmem *ocxlpmem);
+
+/**
+ * ns_command_complete() - Is a near storage command executing
+ * @ocxlpmem: the device metadata
+ * Returns true if the previous admin command has completed
+ */
+bool ns_command_complete(const struct ocxlpmem *ocxlpmem);
+
+/**
+ * ns_response_handled() - Notify the controller that the near storage response has been handled
+ * @ocxlpmem: the device metadata
+ * Returns 0 on success, negative on failure
+ */
+int ns_response_handled(const struct ocxlpmem *ocxlpmem);
+
/**
* warn_status() - Emit a kernel warning showing a command status.
* @ocxlpmem: the device metadata
--
2.24.1
^ permalink raw reply related
* [PATCH v3 14/27] powerpc/powernv/pmem: Add support for Admin commands
From: Alastair D'Silva @ 2020-02-21 3:27 UTC (permalink / raw)
To: alastair
Cc: Madhavan Srinivasan, Alexey Kardashevskiy, Masahiro Yamada,
Oliver O'Halloran, Mauro Carvalho Chehab, Ira Weiny,
Thomas Gleixner, Rob Herring, Dave Jiang, linux-nvdimm,
Aneesh Kumar K . V, Krzysztof Kozlowski, Anju T Sudhakar,
Mahesh Salgaonkar, Andrew Donnellan, Arnd Bergmann, Greg Kurz,
Nicholas Piggin, Cédric Le Goater, Dan Williams,
Hari Bathini, linux-mm, Greg Kroah-Hartman, linux-kernel,
Vishal Verma, Frederic Barrat, Paul Mackerras, Andrew Morton,
linuxppc-dev, David S. Miller
In-Reply-To: <20200221032720.33893-1-alastair@au1.ibm.com>
From: Alastair D'Silva <alastair@d-silva.org>
This patch requests the metadata required to issue admin commands, as well
as some helper functions to construct and check the completion of the
commands.
Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
---
arch/powerpc/platforms/powernv/pmem/ocxl.c | 65 ++++++++
.../platforms/powernv/pmem/ocxl_internal.c | 153 ++++++++++++++++++
.../platforms/powernv/pmem/ocxl_internal.h | 61 +++++++
3 files changed, 279 insertions(+)
diff --git a/arch/powerpc/platforms/powernv/pmem/ocxl.c b/arch/powerpc/platforms/powernv/pmem/ocxl.c
index 431212c9f0cc..4e782d22605b 100644
--- a/arch/powerpc/platforms/powernv/pmem/ocxl.c
+++ b/arch/powerpc/platforms/powernv/pmem/ocxl.c
@@ -216,6 +216,58 @@ static int register_lpc_mem(struct ocxlpmem *ocxlpmem)
return 0;
}
+/**
+ * extract_command_metadata() - Extract command data from MMIO & save it for further use
+ * @ocxlpmem: the device metadata
+ * @offset: The base address of the command data structures (address of CREQO)
+ * @command_metadata: A pointer to the command metadata to populate
+ * Return: 0 on success, negative on failure
+ */
+static int extract_command_metadata(struct ocxlpmem *ocxlpmem, u32 offset,
+ struct command_metadata *command_metadata)
+{
+ int rc;
+ u64 tmp;
+
+ rc = ocxl_global_mmio_read64(ocxlpmem->ocxl_afu, offset, OCXL_LITTLE_ENDIAN,
+ &tmp);
+ if (rc)
+ return rc;
+
+ command_metadata->request_offset = tmp >> 32;
+ command_metadata->response_offset = tmp & 0xFFFFFFFF;
+
+ rc = ocxl_global_mmio_read64(ocxlpmem->ocxl_afu, offset + 8, OCXL_LITTLE_ENDIAN,
+ &tmp);
+ if (rc)
+ return rc;
+
+ command_metadata->data_offset = tmp >> 32;
+ command_metadata->data_size = tmp & 0xFFFFFFFF;
+
+ command_metadata->id = 0;
+
+ return 0;
+}
+
+/**
+ * setup_command_metadata() - Set up the command metadata
+ * @ocxlpmem: the device metadata
+ */
+static int setup_command_metadata(struct ocxlpmem *ocxlpmem)
+{
+ int rc;
+
+ mutex_init(&ocxlpmem->admin_command.lock);
+
+ rc = extract_command_metadata(ocxlpmem, GLOBAL_MMIO_ACMA_CREQO,
+ &ocxlpmem->admin_command);
+ if (rc)
+ return rc;
+
+ return 0;
+}
+
/**
* is_usable() - Is a controller usable?
* @ocxlpmem: the device metadata
@@ -456,6 +508,14 @@ static int probe(struct pci_dev *pdev, const struct pci_device_id *ent)
}
ocxlpmem->pdev = pdev;
+ ocxlpmem->timeouts[ADMIN_COMMAND_ERRLOG] = 2000; // ms
+ ocxlpmem->timeouts[ADMIN_COMMAND_HEARTBEAT] = 100; // ms
+ ocxlpmem->timeouts[ADMIN_COMMAND_SMART] = 100; // ms
+ ocxlpmem->timeouts[ADMIN_COMMAND_CONTROLLER_DUMP] = 1000; // ms
+ ocxlpmem->timeouts[ADMIN_COMMAND_CONTROLLER_STATS] = 100; // ms
+ ocxlpmem->timeouts[ADMIN_COMMAND_SHUTDOWN] = 1000; // ms
+ ocxlpmem->timeouts[ADMIN_COMMAND_FW_UPDATE] = 16000; // ms
+
pci_set_drvdata(pdev, ocxlpmem);
ocxlpmem->ocxl_fn = ocxl_function_open(pdev);
@@ -501,6 +561,11 @@ static int probe(struct pci_dev *pdev, const struct pci_device_id *ent)
goto err;
}
+ if (setup_command_metadata(ocxlpmem)) {
+ dev_err(&pdev->dev, "Could not read OCXL command matada\n");
+ goto err;
+ }
+
elapsed = 0;
timeout = ocxlpmem->readiness_timeout + ocxlpmem->memory_available_timeout;
while (!is_usable(ocxlpmem, false)) {
diff --git a/arch/powerpc/platforms/powernv/pmem/ocxl_internal.c b/arch/powerpc/platforms/powernv/pmem/ocxl_internal.c
index 617ca943b1b8..583f48023025 100644
--- a/arch/powerpc/platforms/powernv/pmem/ocxl_internal.c
+++ b/arch/powerpc/platforms/powernv/pmem/ocxl_internal.c
@@ -17,3 +17,156 @@ int ocxlpmem_chi(const struct ocxlpmem *ocxlpmem, u64 *chi)
return 0;
}
+
+#define COMMAND_REQUEST_SIZE (8 * sizeof(u64))
+static int scm_command_request(const struct ocxlpmem *ocxlpmem,
+ struct command_metadata *cmd, u8 op_code)
+{
+ u64 val = op_code;
+ int rc;
+ u8 i;
+
+ cmd->op_code = op_code;
+ cmd->id++;
+
+ val |= ((u64)cmd->id) << 16;
+
+ rc = ocxl_global_mmio_write64(ocxlpmem->ocxl_afu, cmd->request_offset,
+ OCXL_LITTLE_ENDIAN, val);
+ if (rc)
+ return rc;
+
+ for (i = sizeof(u64); i < COMMAND_REQUEST_SIZE; i += sizeof(u64)) {
+ rc = ocxl_global_mmio_write64(ocxlpmem->ocxl_afu,
+ cmd->request_offset + i,
+ OCXL_LITTLE_ENDIAN, 0);
+ if (rc)
+ return rc;
+ }
+
+ return 0;
+}
+
+int admin_command_request(struct ocxlpmem *ocxlpmem, u8 op_code)
+{
+ u64 val;
+ int rc = ocxl_global_mmio_read64(ocxlpmem->ocxl_afu, GLOBAL_MMIO_CHI,
+ OCXL_LITTLE_ENDIAN, &val);
+ if (rc)
+ return rc;
+
+ return scm_command_request(ocxlpmem, &ocxlpmem->admin_command, op_code);
+}
+
+static int command_response(const struct ocxlpmem *ocxlpmem,
+ const struct command_metadata *cmd)
+{
+ u64 val;
+ u16 id;
+ u8 status;
+ int rc = ocxl_global_mmio_read64(ocxlpmem->ocxl_afu,
+ cmd->response_offset,
+ OCXL_LITTLE_ENDIAN, &val);
+ if (rc)
+ return rc;
+
+ status = val & 0xff;
+ id = (val >> 16) & 0xffff;
+
+ if (id != cmd->id) {
+ dev_warn(&ocxlpmem->dev,
+ "Expected response for command %d, but received response for command %d instead.\n",
+ cmd->id, id);
+ }
+
+ return status;
+}
+
+int admin_response(const struct ocxlpmem *ocxlpmem)
+{
+ return command_response(ocxlpmem, &ocxlpmem->admin_command);
+}
+
+
+int admin_command_execute(const struct ocxlpmem *ocxlpmem)
+{
+ return ocxl_global_mmio_set64(ocxlpmem->ocxl_afu, GLOBAL_MMIO_HCI,
+ OCXL_LITTLE_ENDIAN, GLOBAL_MMIO_HCI_ACRW);
+}
+
+static bool admin_command_complete(const struct ocxlpmem *ocxlpmem)
+{
+ u64 val = 0;
+
+ int rc = ocxlpmem_chi(ocxlpmem, &val);
+
+ WARN_ON(rc);
+
+ return (val & GLOBAL_MMIO_CHI_ACRA) != 0;
+}
+
+int admin_command_complete_timeout(const struct ocxlpmem *ocxlpmem,
+ int command)
+{
+ u32 timeout = ocxlpmem->timeouts[command];
+ // 32 is the next power of 2 greater than the 20ms minimum for msleep
+#define TIMEOUT_SLEEP_MILLIS 32
+ timeout /= TIMEOUT_SLEEP_MILLIS;
+ if (!timeout)
+ timeout = DEFAULT_TIMEOUT / TIMEOUT_SLEEP_MILLIS;
+
+ while (timeout-- > 0) {
+ if (admin_command_complete(ocxlpmem))
+ return 0;
+ msleep(TIMEOUT_SLEEP_MILLIS);
+ }
+
+ if (admin_command_complete(ocxlpmem))
+ return 0;
+
+ return -EBUSY;
+}
+
+int admin_response_handled(const struct ocxlpmem *ocxlpmem)
+{
+ return ocxl_global_mmio_set64(ocxlpmem->ocxl_afu, GLOBAL_MMIO_CHIC,
+ OCXL_LITTLE_ENDIAN, GLOBAL_MMIO_CHI_ACRA);
+}
+
+void warn_status(const struct ocxlpmem *ocxlpmem, const char *message,
+ u8 status)
+{
+ const char *text = "Unknown";
+
+ switch (status) {
+ case STATUS_SUCCESS:
+ text = "Success";
+ break;
+
+ case STATUS_MEM_UNAVAILABLE:
+ text = "Persistent memory unavailable";
+ break;
+
+ case STATUS_BAD_OPCODE:
+ text = "Bad opcode";
+ break;
+
+ case STATUS_BAD_REQUEST_PARM:
+ text = "Bad request parameter";
+ break;
+
+ case STATUS_BAD_DATA_PARM:
+ text = "Bad data parameter";
+ break;
+
+ case STATUS_DEBUG_BLOCKED:
+ text = "Debug action blocked";
+ break;
+
+ case STATUS_FAIL:
+ text = "Failed";
+ break;
+ }
+
+ dev_warn(&ocxlpmem->dev, "%s: %s (%x)\n", message, text, status);
+}
diff --git a/arch/powerpc/platforms/powernv/pmem/ocxl_internal.h b/arch/powerpc/platforms/powernv/pmem/ocxl_internal.h
index ba0301533d00..2fef68c71271 100644
--- a/arch/powerpc/platforms/powernv/pmem/ocxl_internal.h
+++ b/arch/powerpc/platforms/powernv/pmem/ocxl_internal.h
@@ -7,6 +7,7 @@
#include <linux/mm.h>
#define LABEL_AREA_SIZE (1UL << PA_SECTION_SHIFT)
+#define DEFAULT_TIMEOUT 100
#define GLOBAL_MMIO_CHI 0x000
#define GLOBAL_MMIO_CHIC 0x008
@@ -80,6 +81,16 @@
#define STATUS_FW_ARG_INVALID 0x51
#define STATUS_FW_INVALID 0x52
+struct command_metadata {
+ u32 request_offset;
+ u32 response_offset;
+ u32 data_offset;
+ u32 data_size;
+ struct mutex lock;
+ u16 id;
+ u8 op_code;
+};
+
struct ocxlpmem_function0 {
struct pci_dev *pdev;
struct ocxl_fn *ocxl_fn;
@@ -95,9 +106,11 @@ struct ocxlpmem {
struct ocxl_afu *ocxl_afu;
struct ocxl_context *ocxl_context;
void *metadata_addr;
+ struct command_metadata admin_command;
struct resource pmem_res;
struct nd_region *nd_region;
char fw_version[8+1];
+ u32 timeouts[ADMIN_COMMAND_MAX+1];
u32 max_controller_dump_size;
u16 scm_revision; // major/minor
@@ -122,3 +135,51 @@ struct ocxlpmem {
* Returns 0 on success, negative on error
*/
int ocxlpmem_chi(const struct ocxlpmem *ocxlpmem, u64 *chi);
+
+/**
+ * admin_command_request() - Issue an admin command request
+ * @ocxlpmem: the device metadata
+ * @op_code: The op-code for the command
+ *
+ * Returns an identifier for the command, or negative on error
+ */
+int admin_command_request(struct ocxlpmem *ocxlpmem, u8 op_code);
+
+/**
+ * admin_response() - Validate an admin response
+ * @ocxlpmem: the device metadata
+ * Returns the status code of the command, or negative on error
+ */
+int admin_response(const struct ocxlpmem *ocxlpmem);
+
+/**
+ * admin_command_execute() - Notify the controller to start processing a pending admin command
+ * @ocxlpmem: the device metadata
+ * Returns 0 on success, negative on error
+ */
+int admin_command_execute(const struct ocxlpmem *ocxlpmem);
+
+/**
+ * admin_command_complete_timeout() - Wait for an admin command to finish executing
+ * @ocxlpmem: the device metadata
+ * @command: the admin command to wait for completion (determines the timeout)
+ * Returns 0 on success, -EBUSY on timeout
+ */
+int admin_command_complete_timeout(const struct ocxlpmem *ocxlpmem,
+ int command);
+
+/**
+ * admin_response_handled() - Notify the controller that the admin response has been handled
+ * @ocxlpmem: the device metadata
+ * Returns 0 on success, negative on failure
+ */
+int admin_response_handled(const struct ocxlpmem *ocxlpmem);
+
+/**
+ * warn_status() - Emit a kernel warning showing a command status.
+ * @ocxlpmem: the device metadata
+ * @message: A message to accompany the warning
+ * @status: The command status
+ */
+void warn_status(const struct ocxlpmem *ocxlpmem, const char *message,
+ u8 status);
--
2.24.1
^ permalink raw reply related
* [PATCH v3 27/27] MAINTAINERS: Add myself & nvdimm/ocxl to ocxl
From: Alastair D'Silva @ 2020-02-21 3:27 UTC (permalink / raw)
To: alastair
Cc: Madhavan Srinivasan, Alexey Kardashevskiy, Masahiro Yamada,
Oliver O'Halloran, Mauro Carvalho Chehab, Ira Weiny,
Thomas Gleixner, Rob Herring, Dave Jiang, linux-nvdimm,
Aneesh Kumar K . V, Krzysztof Kozlowski, Anju T Sudhakar,
Mahesh Salgaonkar, Andrew Donnellan, Arnd Bergmann, Greg Kurz,
Nicholas Piggin, Cédric Le Goater, Dan Williams,
Hari Bathini, linux-mm, Greg Kroah-Hartman, linux-kernel,
Vishal Verma, Frederic Barrat, Paul Mackerras, Andrew Morton,
linuxppc-dev, David S. Miller
In-Reply-To: <20200221032720.33893-1-alastair@au1.ibm.com>
From: Alastair D'Silva <alastair@d-silva.org>
The OpenCAPI Persistent Memory driver will be maintained as part ofi
the ppc tree.
I'm also adding myself as an author of the driver & contributor to
the generic ocxl driver.
Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
---
MAINTAINERS | 3 +++
1 file changed, 3 insertions(+)
diff --git a/MAINTAINERS b/MAINTAINERS
index f8670989ec91..3fb9a9f576a7 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -12064,13 +12064,16 @@ F: tools/objtool/
OCXL (Open Coherent Accelerator Processor Interface OpenCAPI) DRIVER
M: Frederic Barrat <fbarrat@linux.ibm.com>
M: Andrew Donnellan <ajd@linux.ibm.com>
+M: Alastair D'Silva <alastair@d-silva.org>
L: linuxppc-dev@lists.ozlabs.org
S: Supported
F: arch/powerpc/platforms/powernv/ocxl.c
+F: arch/powerpc/platforms/powernv/pmem/*
F: arch/powerpc/include/asm/pnv-ocxl.h
F: drivers/misc/ocxl/
F: include/misc/ocxl*
F: include/uapi/misc/ocxl.h
+F: include/uapi/nvdimm/ocxl-pmem.h
F: Documentation/userspace-api/accelerators/ocxl.rst
OMAP AUDIO SUPPORT
--
2.24.1
^ permalink raw reply related
* [PATCH v3 08/27] ocxl: Emit a log message showing how much LPC memory was detected
From: Alastair D'Silva @ 2020-02-21 3:27 UTC (permalink / raw)
To: alastair
Cc: Madhavan Srinivasan, Alexey Kardashevskiy, Masahiro Yamada,
Oliver O'Halloran, Mauro Carvalho Chehab, Ira Weiny,
Thomas Gleixner, Rob Herring, Dave Jiang, linux-nvdimm,
Aneesh Kumar K . V, Krzysztof Kozlowski, Anju T Sudhakar,
Mahesh Salgaonkar, Andrew Donnellan, Arnd Bergmann, Greg Kurz,
Nicholas Piggin, Cédric Le Goater, Dan Williams,
Hari Bathini, linux-mm, Greg Kroah-Hartman, linux-kernel,
Vishal Verma, Frederic Barrat, Paul Mackerras, Andrew Morton,
linuxppc-dev, David S. Miller
In-Reply-To: <20200221032720.33893-1-alastair@au1.ibm.com>
From: Alastair D'Silva <alastair@d-silva.org>
This patch emits a message showing how much LPC memory & special purpose
memory was detected on an OCXL device.
Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
---
drivers/misc/ocxl/config.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/drivers/misc/ocxl/config.c b/drivers/misc/ocxl/config.c
index a62e3d7db2bf..701ae6216abf 100644
--- a/drivers/misc/ocxl/config.c
+++ b/drivers/misc/ocxl/config.c
@@ -568,6 +568,10 @@ static int read_afu_lpc_memory_info(struct pci_dev *dev,
afu->special_purpose_mem_size =
total_mem_size - lpc_mem_size;
}
+
+ dev_info(&dev->dev, "Probed LPC memory of %#llx bytes and special purpose memory of %#llx bytes\n",
+ afu->lpc_mem_size, afu->special_purpose_mem_size);
+
return 0;
}
--
2.24.1
^ permalink raw reply related
* [PATCH v3 17/27] powerpc/powernv/pmem: Implement the Read Error Log command
From: Alastair D'Silva @ 2020-02-21 3:27 UTC (permalink / raw)
To: alastair
Cc: Madhavan Srinivasan, Alexey Kardashevskiy, Masahiro Yamada,
Oliver O'Halloran, Mauro Carvalho Chehab, Ira Weiny,
Thomas Gleixner, Rob Herring, Dave Jiang, linux-nvdimm,
Aneesh Kumar K . V, Krzysztof Kozlowski, Anju T Sudhakar,
Mahesh Salgaonkar, Andrew Donnellan, Arnd Bergmann, Greg Kurz,
Nicholas Piggin, Cédric Le Goater, Dan Williams,
Hari Bathini, linux-mm, Greg Kroah-Hartman, linux-kernel,
Vishal Verma, Frederic Barrat, Paul Mackerras, Andrew Morton,
linuxppc-dev, David S. Miller
In-Reply-To: <20200221032720.33893-1-alastair@au1.ibm.com>
From: Alastair D'Silva <alastair@d-silva.org>
The read error log command extracts information from the controller's
internal error log.
This patch exposes this information in 2 ways:
- During probe, if an error occurs & a log is available, print it to the
console
- After probe, make the error log available to userspace via an IOCTL.
Userspace is notified of pending error logs in a later patch
("powerpc/powernv/pmem: Forward events to userspace")
Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
---
arch/powerpc/platforms/powernv/pmem/ocxl.c | 269 ++++++++++++++++++
.../platforms/powernv/pmem/ocxl_internal.h | 1 +
include/uapi/nvdimm/ocxl-pmem.h | 46 +++
3 files changed, 316 insertions(+)
create mode 100644 include/uapi/nvdimm/ocxl-pmem.h
diff --git a/arch/powerpc/platforms/powernv/pmem/ocxl.c b/arch/powerpc/platforms/powernv/pmem/ocxl.c
index 63109a870d2c..2b64504f9129 100644
--- a/arch/powerpc/platforms/powernv/pmem/ocxl.c
+++ b/arch/powerpc/platforms/powernv/pmem/ocxl.c
@@ -447,10 +447,219 @@ static int file_release(struct inode *inode, struct file *file)
return 0;
}
+/**
+ * error_log_header_parse() - Parse the first 64 bits of the error log command response
+ * @ocxlpmem: the device metadata
+ * @length: out, returns the number of bytes in the response (excluding the 64 bit header)
+ */
+static int error_log_header_parse(struct ocxlpmem *ocxlpmem, u16 *length)
+{
+ int rc;
+ u64 val;
+
+ u16 data_identifier;
+ u32 data_length;
+
+ rc = ocxl_global_mmio_read64(ocxlpmem->ocxl_afu,
+ ocxlpmem->admin_command.data_offset,
+ OCXL_LITTLE_ENDIAN, &val);
+ if (rc)
+ return rc;
+
+ data_identifier = val >> 48;
+ data_length = val & 0xFFFF;
+
+ if (data_identifier != 0x454C) { // 'EL'
+ dev_err(&ocxlpmem->dev,
+ "Bad data identifier for error log data, expected 'EL', got '%2s' (%#x), data_length=%u\n",
+ (char *)&data_identifier,
+ (unsigned int)data_identifier, data_length);
+ return -EINVAL;
+ }
+
+ *length = data_length;
+ return 0;
+}
+
+static int error_log_offset_0x08(struct ocxlpmem *ocxlpmem,
+ u32 *log_identifier, u32 *program_ref_code)
+{
+ int rc;
+ u64 val;
+
+ rc = ocxl_global_mmio_read64(ocxlpmem->ocxl_afu,
+ ocxlpmem->admin_command.data_offset + 0x08,
+ OCXL_LITTLE_ENDIAN, &val);
+ if (rc)
+ return rc;
+
+ *log_identifier = val >> 32;
+ *program_ref_code = val & 0xFFFFFFFF;
+
+ return 0;
+}
+
+static int read_error_log(struct ocxlpmem *ocxlpmem,
+ struct ioctl_ocxl_pmem_error_log *log, bool buf_is_user)
+{
+ u64 val;
+ u16 user_buf_length;
+ u16 buf_length;
+ u16 i;
+ int rc;
+
+ if (log->buf_size % 8)
+ return -EINVAL;
+
+ rc = ocxlpmem_chi(ocxlpmem, &val);
+ if (rc)
+ goto out;
+
+ if (!(val & GLOBAL_MMIO_CHI_ELA))
+ return -EAGAIN;
+
+ user_buf_length = log->buf_size;
+
+ mutex_lock(&ocxlpmem->admin_command.lock);
+
+ rc = admin_command_request(ocxlpmem, ADMIN_COMMAND_ERRLOG);
+ if (rc)
+ goto out;
+
+ rc = admin_command_execute(ocxlpmem);
+ if (rc)
+ goto out;
+
+ rc = admin_command_complete_timeout(ocxlpmem, ADMIN_COMMAND_ERRLOG);
+ if (rc < 0) {
+ dev_warn(&ocxlpmem->dev, "Read error log timed out\n");
+ goto out;
+ }
+
+ rc = admin_response(ocxlpmem);
+ if (rc < 0)
+ goto out;
+ if (rc != STATUS_SUCCESS) {
+ warn_status(ocxlpmem, "Unexpected status from retrieve error log", rc);
+ goto out;
+ }
+
+
+ rc = error_log_header_parse(ocxlpmem, &log->buf_size);
+ if (rc)
+ goto out;
+ // log->buf_size now contains the returned buffer size, not the user size
+
+ rc = error_log_offset_0x08(ocxlpmem, &log->log_identifier,
+ &log->program_reference_code);
+ if (rc)
+ goto out;
+
+ rc = ocxl_global_mmio_read64(ocxlpmem->ocxl_afu,
+ ocxlpmem->admin_command.data_offset + 0x10,
+ OCXL_LITTLE_ENDIAN, &val);
+ if (rc)
+ goto out;
+
+ log->error_log_type = val >> 56;
+ log->action_flags = (log->error_log_type == OCXL_PMEM_ERROR_LOG_TYPE_GENERAL) ?
+ (val >> 32) & 0xFFFFFF : 0;
+ log->power_on_seconds = val & 0xFFFFFFFF;
+
+ rc = ocxl_global_mmio_read64(ocxlpmem->ocxl_afu,
+ ocxlpmem->admin_command.data_offset + 0x18,
+ OCXL_LITTLE_ENDIAN, &log->timestamp);
+ if (rc)
+ goto out;
+
+ rc = ocxl_global_mmio_read64(ocxlpmem->ocxl_afu,
+ ocxlpmem->admin_command.data_offset + 0x20,
+ OCXL_HOST_ENDIAN, &log->wwid[0]);
+ if (rc)
+ goto out;
+
+ rc = ocxl_global_mmio_read64(ocxlpmem->ocxl_afu,
+ ocxlpmem->admin_command.data_offset + 0x28,
+ OCXL_HOST_ENDIAN, &log->wwid[1]);
+ if (rc)
+ goto out;
+
+ rc = ocxl_global_mmio_read64(ocxlpmem->ocxl_afu,
+ ocxlpmem->admin_command.data_offset + 0x30,
+ OCXL_HOST_ENDIAN, (u64 *)log->fw_revision);
+ if (rc)
+ goto out;
+ log->fw_revision[8] = '\0';
+
+ buf_length = (user_buf_length < log->buf_size) ?
+ user_buf_length : log->buf_size;
+ for (i = 0; i < buf_length + 0x48; i += 8) {
+ u64 val;
+
+ rc = ocxl_global_mmio_read64(ocxlpmem->ocxl_afu,
+ ocxlpmem->admin_command.data_offset + i,
+ OCXL_HOST_ENDIAN, &val);
+ if (rc)
+ goto out;
+
+ if (buf_is_user) {
+ if (copy_to_user(&log->buf[i], &val, sizeof(u64))) {
+ rc = -EFAULT;
+ goto out;
+ }
+ } else
+ log->buf[i] = val;
+ }
+
+ rc = admin_response_handled(ocxlpmem);
+ if (rc)
+ goto out;
+
+out:
+ mutex_unlock(&ocxlpmem->admin_command.lock);
+ return rc;
+
+}
+
+static int ioctl_error_log(struct ocxlpmem *ocxlpmem,
+ struct ioctl_ocxl_pmem_error_log __user *uarg)
+{
+ struct ioctl_ocxl_pmem_error_log args;
+ int rc;
+
+ if (copy_from_user(&args, uarg, sizeof(args)))
+ return -EFAULT;
+
+ rc = read_error_log(ocxlpmem, &args, true);
+ if (rc)
+ return rc;
+
+ if (copy_to_user(uarg, &args, sizeof(args)))
+ return -EFAULT;
+
+ return 0;
+}
+
+static long file_ioctl(struct file *file, unsigned int cmd, unsigned long args)
+{
+ struct ocxlpmem *ocxlpmem = file->private_data;
+ int rc = -EINVAL;
+
+ switch (cmd) {
+ case IOCTL_OCXL_PMEM_ERROR_LOG:
+ rc = ioctl_error_log(ocxlpmem,
+ (struct ioctl_ocxl_pmem_error_log __user *)args);
+ break;
+ }
+ return rc;
+}
+
static const struct file_operations fops = {
.owner = THIS_MODULE,
.open = file_open,
.release = file_release,
+ .unlocked_ioctl = file_ioctl,
+ .compat_ioctl = file_ioctl,
};
/**
@@ -527,6 +736,60 @@ static int read_device_metadata(struct ocxlpmem *ocxlpmem)
return 0;
}
+static const char *decode_error_log_type(u8 error_log_type)
+{
+ switch (error_log_type) {
+ case 0x00:
+ return "general";
+ case 0x01:
+ return "predictive failure";
+ case 0x02:
+ return "thermal warning";
+ case 0x03:
+ return "data loss";
+ case 0x04:
+ return "health & performance";
+ default:
+ return "unknown";
+ }
+}
+
+static void dump_error_log(struct ocxlpmem *ocxlpmem)
+{
+ struct ioctl_ocxl_pmem_error_log log;
+ u32 buf_size;
+ u8 *buf;
+ int rc;
+
+ if (ocxlpmem->admin_command.data_size == 0)
+ return;
+
+ buf_size = ocxlpmem->admin_command.data_size - 0x48;
+ buf = kzalloc(buf_size, GFP_KERNEL);
+ if (!buf)
+ return;
+
+ log.buf = buf;
+ log.buf_size = buf_size;
+
+ rc = read_error_log(ocxlpmem, &log, false);
+ if (rc < 0)
+ goto out;
+
+ dev_warn(&ocxlpmem->dev,
+ "OCXL PMEM Error log: WWID=0x%016llx%016llx LID=0x%x PRC=%x type=0x%x %s, Uptime=%u seconds timestamp=0x%llx\n",
+ log.wwid[0], log.wwid[1],
+ log.log_identifier, log.program_reference_code,
+ log.error_log_type,
+ decode_error_log_type(log.error_log_type),
+ log.power_on_seconds, log.timestamp);
+ print_hex_dump(KERN_WARNING, "buf", DUMP_PREFIX_OFFSET, 16, 1, buf,
+ log.buf_size, false);
+
+out:
+ kfree(buf);
+}
+
/**
* probe_function0() - Set up function 0 for an OpenCAPI persistent memory device
* This is important as it enables templates higher than 0 across all other functions,
@@ -568,6 +831,7 @@ static int probe(struct pci_dev *pdev, const struct pci_device_id *ent)
struct ocxlpmem *ocxlpmem;
int rc;
u16 elapsed, timeout;
+ u64 chi;
if (PCI_FUNC(pdev->devfn) == 0)
return probe_function0(pdev);
@@ -667,6 +931,11 @@ static int probe(struct pci_dev *pdev, const struct pci_device_id *ent)
return 0;
err:
+ if (ocxlpmem &&
+ (ocxlpmem_chi(ocxlpmem, &chi) == 0) &&
+ (chi & GLOBAL_MMIO_CHI_ELA))
+ dump_error_log(ocxlpmem);
+
/*
* Further cleanup is done in the release handler via free_ocxlpmem()
* This allows us to keep the character device live to handle IOCTLs to
diff --git a/arch/powerpc/platforms/powernv/pmem/ocxl_internal.h b/arch/powerpc/platforms/powernv/pmem/ocxl_internal.h
index d2d81fec7bb1..b953ee522ed4 100644
--- a/arch/powerpc/platforms/powernv/pmem/ocxl_internal.h
+++ b/arch/powerpc/platforms/powernv/pmem/ocxl_internal.h
@@ -5,6 +5,7 @@
#include <linux/cdev.h>
#include <misc/ocxl.h>
#include <linux/libnvdimm.h>
+#include <uapi/nvdimm/ocxl-pmem.h>
#include <linux/mm.h>
#define LABEL_AREA_SIZE (1UL << PA_SECTION_SHIFT)
diff --git a/include/uapi/nvdimm/ocxl-pmem.h b/include/uapi/nvdimm/ocxl-pmem.h
new file mode 100644
index 000000000000..b10f8ac0c20f
--- /dev/null
+++ b/include/uapi/nvdimm/ocxl-pmem.h
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/* Copyright 2017 IBM Corp. */
+#ifndef _UAPI_OCXL_SCM_H
+#define _UAPI_OCXL_SCM_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+#define OCXL_PMEM_ERROR_LOG_ACTION_RESET (1 << (32-32))
+#define OCXL_PMEM_ERROR_LOG_ACTION_CHKFW (1 << (53-32))
+#define OCXL_PMEM_ERROR_LOG_ACTION_REPLACE (1 << (54-32))
+#define OCXL_PMEM_ERROR_LOG_ACTION_DUMP (1 << (55-32))
+
+#define OCXL_PMEM_ERROR_LOG_TYPE_GENERAL (0x00)
+#define OCXL_PMEM_ERROR_LOG_TYPE_PREDICTIVE_FAILURE (0x01)
+#define OCXL_PMEM_ERROR_LOG_TYPE_THERMAL_WARNING (0x02)
+#define OCXL_PMEM_ERROR_LOG_TYPE_DATA_LOSS (0x03)
+#define OCXL_PMEM_ERROR_LOG_TYPE_HEALTH_PERFORMANCE (0x04)
+
+struct ioctl_ocxl_pmem_error_log {
+ __u32 log_identifier; /* out */
+ __u32 program_reference_code; /* out */
+ __u32 action_flags; /* out, recommended course of action */
+ __u32 power_on_seconds; /* out, Number of seconds the controller has been on when the error occurred */
+ __u64 timestamp; /* out, relative time since the current IPL */
+ __u64 wwid[2]; /* out, the NAA formatted WWID associated with the controller */
+ char fw_revision[8+1]; /* out, firmware revision as null terminated text */
+ __u16 buf_size; /* in/out, buffer size provided/required.
+ * If required is greater than provided, the buffer
+ * will be truncated to the amount provided. If its
+ * less, then only the required bytes will be populated.
+ * If it is 0, then there are no more error log entries.
+ */
+ __u8 error_log_type;
+ __u8 reserved1;
+ __u32 reserved2;
+ __u64 reserved3[2];
+ __u8 *buf; /* pointer to output buffer */
+};
+
+/* ioctl numbers */
+#define OCXL_PMEM_MAGIC 0x5C
+/* SCM devices */
+#define IOCTL_OCXL_PMEM_ERROR_LOG _IOWR(OCXL_PMEM_MAGIC, 0x01, struct ioctl_ocxl_pmem_error_log)
+
+#endif /* _UAPI_OCXL_SCM_H */
--
2.24.1
^ permalink raw reply related
* [PATCH v3 10/27] powerpc: Add driver for OpenCAPI Persistent Memory
From: Alastair D'Silva @ 2020-02-21 3:27 UTC (permalink / raw)
To: alastair
Cc: Madhavan Srinivasan, Alexey Kardashevskiy, Masahiro Yamada,
Oliver O'Halloran, Mauro Carvalho Chehab, Ira Weiny,
Thomas Gleixner, Rob Herring, Dave Jiang, linux-nvdimm,
Aneesh Kumar K . V, Krzysztof Kozlowski, Anju T Sudhakar,
Mahesh Salgaonkar, Andrew Donnellan, Arnd Bergmann, Greg Kurz,
Nicholas Piggin, Cédric Le Goater, Dan Williams,
Hari Bathini, linux-mm, Greg Kroah-Hartman, linux-kernel,
Vishal Verma, Frederic Barrat, Paul Mackerras, Andrew Morton,
linuxppc-dev, David S. Miller
In-Reply-To: <20200221032720.33893-1-alastair@au1.ibm.com>
From: Alastair D'Silva <alastair@d-silva.org>
This driver exposes LPC memory on OpenCAPI pmem cards
as an NVDIMM, allowing the existing nvram infrastructure
to be used.
Namespace metadata is stored on the media itself, so
scm_reserve_metadata() maps 1 section's worth of PMEM storage
at the start to hold this. The rest of the PMEM range is registered
with libnvdimm as an nvdimm. scm_ndctl_config_read/write/size() provide
callbacks to libnvdimm to access the metadata.
Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
---
arch/powerpc/platforms/powernv/Kconfig | 3 +
arch/powerpc/platforms/powernv/Makefile | 1 +
arch/powerpc/platforms/powernv/pmem/Kconfig | 15 +
arch/powerpc/platforms/powernv/pmem/Makefile | 7 +
arch/powerpc/platforms/powernv/pmem/ocxl.c | 473 ++++++++++++++++++
.../platforms/powernv/pmem/ocxl_internal.h | 28 ++
6 files changed, 527 insertions(+)
create mode 100644 arch/powerpc/platforms/powernv/pmem/Kconfig
create mode 100644 arch/powerpc/platforms/powernv/pmem/Makefile
create mode 100644 arch/powerpc/platforms/powernv/pmem/ocxl.c
create mode 100644 arch/powerpc/platforms/powernv/pmem/ocxl_internal.h
diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig
index 938803eab0ad..fc8976af0e52 100644
--- a/arch/powerpc/platforms/powernv/Kconfig
+++ b/arch/powerpc/platforms/powernv/Kconfig
@@ -50,3 +50,6 @@ config PPC_VAS
config SCOM_DEBUGFS
bool "Expose SCOM controllers via debugfs"
depends on DEBUG_FS
+
+source "arch/powerpc/platforms/powernv/pmem/Kconfig"
+
diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile
index c0f8120045c3..0bbd72988b6f 100644
--- a/arch/powerpc/platforms/powernv/Makefile
+++ b/arch/powerpc/platforms/powernv/Makefile
@@ -21,3 +21,4 @@ obj-$(CONFIG_PPC_VAS) += vas.o vas-window.o vas-debug.o
obj-$(CONFIG_OCXL_BASE) += ocxl.o
obj-$(CONFIG_SCOM_DEBUGFS) += opal-xscom.o
obj-$(CONFIG_PPC_SECURE_BOOT) += opal-secvar.o
+obj-$(CONFIG_LIBNVDIMM) += pmem/
diff --git a/arch/powerpc/platforms/powernv/pmem/Kconfig b/arch/powerpc/platforms/powernv/pmem/Kconfig
new file mode 100644
index 000000000000..c5d927520920
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/pmem/Kconfig
@@ -0,0 +1,15 @@
+# SPDX-License-Identifier: GPL-2.0-only
+if LIBNVDIMM
+
+config OCXL_PMEM
+ tristate "OpenCAPI Persistent Memory"
+ depends on LIBNVDIMM && PPC_POWERNV && PCI && EEH && ZONE_DEVICE && OCXL
+ help
+ Exposes devices that implement the OpenCAPI Storage Class Memory
+ specification as persistent memory regions. You may also want
+ DEV_DAX, DEV_DAX_PMEM & FS_DAX if you plan on using DAX devices
+ stacked on top of this driver.
+
+ Select N if unsure.
+
+endif
diff --git a/arch/powerpc/platforms/powernv/pmem/Makefile b/arch/powerpc/platforms/powernv/pmem/Makefile
new file mode 100644
index 000000000000..1c55c4193175
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/pmem/Makefile
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0
+
+ccflags-$(CONFIG_PPC_WERROR) += -Werror
+
+obj-$(CONFIG_OCXL_PMEM) += ocxlpmem.o
+
+ocxlpmem-y := ocxl.o
diff --git a/arch/powerpc/platforms/powernv/pmem/ocxl.c b/arch/powerpc/platforms/powernv/pmem/ocxl.c
new file mode 100644
index 000000000000..3c4eeb5dcc0f
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/pmem/ocxl.c
@@ -0,0 +1,473 @@
+// SPDX-License-Id
+// Copyright 2019 IBM Corp.
+
+/*
+ * A driver for OpenCAPI devices that implement the Storage Class
+ * Memory specification.
+ */
+
+#include <linux/module.h>
+#include <misc/ocxl.h>
+#include <linux/ndctl.h>
+#include <linux/mm_types.h>
+#include <linux/memory_hotplug.h>
+#include "ocxl_internal.h"
+
+
+static const struct pci_device_id ocxlpmem_pci_tbl[] = {
+ { PCI_DEVICE(PCI_VENDOR_ID_IBM, 0x0625), },
+ { }
+};
+
+MODULE_DEVICE_TABLE(pci, ocxlpmem_pci_tbl);
+
+#define NUM_MINORS 256 // Total to reserve
+
+static dev_t ocxlpmem_dev;
+static struct class *ocxlpmem_class;
+static struct mutex minors_idr_lock;
+static struct idr minors_idr;
+
+/**
+ * ndctl_config_write() - Handle a ND_CMD_SET_CONFIG_DATA command from ndctl
+ * @ocxlpmem: the device metadata
+ * @command: the incoming data to write
+ * Return: 0 on success, negative on failure
+ */
+static int ndctl_config_write(struct ocxlpmem *ocxlpmem,
+ struct nd_cmd_set_config_hdr *command)
+{
+ if (command->in_offset + command->in_length > LABEL_AREA_SIZE)
+ return -EINVAL;
+
+ memcpy_flushcache(ocxlpmem->metadata_addr + command->in_offset, command->in_buf,
+ command->in_length);
+
+ return 0;
+}
+
+/**
+ * ndctl_config_read() - Handle a ND_CMD_GET_CONFIG_DATA command from ndctl
+ * @ocxlpmem: the device metadata
+ * @command: the read request
+ * Return: 0 on success, negative on failure
+ */
+static int ndctl_config_read(struct ocxlpmem *ocxlpmem,
+ struct nd_cmd_get_config_data_hdr *command)
+{
+ if (command->in_offset + command->in_length > LABEL_AREA_SIZE)
+ return -EINVAL;
+
+ memcpy_mcsafe(command->out_buf, ocxlpmem->metadata_addr + command->in_offset,
+ command->in_length);
+
+ return 0;
+}
+
+/**
+ * ndctl_config_size() - Handle a ND_CMD_GET_CONFIG_SIZE command from ndctl
+ * @command: the read request
+ * Return: 0 on success, negative on failure
+ */
+static int ndctl_config_size(struct nd_cmd_get_config_size *command)
+{
+ command->status = 0;
+ command->config_size = LABEL_AREA_SIZE;
+ command->max_xfer = PAGE_SIZE;
+
+ return 0;
+}
+
+static int ndctl(struct nvdimm_bus_descriptor *nd_desc,
+ struct nvdimm *nvdimm,
+ unsigned int cmd, void *buf, unsigned int buf_len, int *cmd_rc)
+{
+ struct ocxlpmem *ocxlpmem = container_of(nd_desc, struct ocxlpmem, bus_desc);
+
+ switch (cmd) {
+ case ND_CMD_GET_CONFIG_SIZE:
+ *cmd_rc = ndctl_config_size(buf);
+ return 0;
+
+ case ND_CMD_GET_CONFIG_DATA:
+ *cmd_rc = ndctl_config_read(ocxlpmem, buf);
+ return 0;
+
+ case ND_CMD_SET_CONFIG_DATA:
+ *cmd_rc = ndctl_config_write(ocxlpmem, buf);
+ return 0;
+
+ default:
+ return -ENOTTY;
+ }
+}
+
+/**
+ * reserve_metadata() - Reserve space for nvdimm metadata
+ * @ocxlpmem: the device metadata
+ * @lpc_mem: The resource representing the LPC memory of the OpenCAPI device
+ */
+static int reserve_metadata(struct ocxlpmem *ocxlpmem,
+ struct resource *lpc_mem)
+{
+ ocxlpmem->metadata_addr = devm_memremap(&ocxlpmem->dev, lpc_mem->start,
+ LABEL_AREA_SIZE, MEMREMAP_WB);
+ if (IS_ERR(ocxlpmem->metadata_addr))
+ return PTR_ERR(ocxlpmem->metadata_addr);
+
+ return 0;
+}
+
+/**
+ * register_lpc_mem() - Discover persistent memory on a device and register it with the NVDIMM subsystem
+ * @ocxlpmem: the device metadata
+ * Return: 0 on success
+ */
+static int register_lpc_mem(struct ocxlpmem *ocxlpmem)
+{
+ struct nd_region_desc region_desc;
+ struct nd_mapping_desc nd_mapping_desc;
+ struct resource *lpc_mem;
+ const struct ocxl_afu_config *config;
+ const struct ocxl_fn_config *fn_config;
+ int rc;
+ unsigned long nvdimm_cmd_mask = 0;
+ unsigned long nvdimm_flags = 0;
+ int target_node;
+ char serial[16+1];
+
+ // Set up the reserved metadata area
+ rc = ocxl_afu_map_lpc_mem(ocxlpmem->ocxl_afu);
+ if (rc < 0)
+ return rc;
+
+ lpc_mem = ocxl_afu_lpc_mem(ocxlpmem->ocxl_afu);
+ if (lpc_mem == NULL || lpc_mem->start == 0)
+ return -EINVAL;
+
+ config = ocxl_afu_config(ocxlpmem->ocxl_afu);
+ fn_config = ocxl_function_config(ocxlpmem->ocxl_fn);
+
+ rc = reserve_metadata(ocxlpmem, lpc_mem);
+ if (rc)
+ return rc;
+
+ ocxlpmem->bus_desc.provider_name = "ocxl-pmem";
+ ocxlpmem->bus_desc.ndctl = ndctl;
+ ocxlpmem->bus_desc.module = THIS_MODULE;
+
+ ocxlpmem->nvdimm_bus = nvdimm_bus_register(&ocxlpmem->dev,
+ &ocxlpmem->bus_desc);
+ if (!ocxlpmem->nvdimm_bus)
+ return -EINVAL;
+
+ ocxlpmem->pmem_res.start = (u64)lpc_mem->start + LABEL_AREA_SIZE;
+ ocxlpmem->pmem_res.end = (u64)lpc_mem->start + config->lpc_mem_size - 1;
+ ocxlpmem->pmem_res.name = "OpenCAPI persistent memory";
+
+ set_bit(ND_CMD_GET_CONFIG_SIZE, &nvdimm_cmd_mask);
+ set_bit(ND_CMD_GET_CONFIG_DATA, &nvdimm_cmd_mask);
+ set_bit(ND_CMD_SET_CONFIG_DATA, &nvdimm_cmd_mask);
+
+ set_bit(NDD_ALIASING, &nvdimm_flags);
+
+ snprintf(serial, sizeof(serial), "%llx", fn_config->serial);
+ nd_mapping_desc.nvdimm = nvdimm_create(ocxlpmem->nvdimm_bus, ocxlpmem,
+ NULL, nvdimm_flags, nvdimm_cmd_mask,
+ 0, NULL);
+ if (!nd_mapping_desc.nvdimm)
+ return -ENOMEM;
+
+ if (nvdimm_bus_check_dimm_count(ocxlpmem->nvdimm_bus, 1))
+ return -EINVAL;
+
+ nd_mapping_desc.start = ocxlpmem->pmem_res.start;
+ nd_mapping_desc.size = resource_size(&ocxlpmem->pmem_res);
+ nd_mapping_desc.position = 0;
+
+ ocxlpmem->nd_set.cookie1 = fn_config->serial + 1; // allow for empty serial
+ ocxlpmem->nd_set.cookie2 = fn_config->serial + 1;
+
+ target_node = of_node_to_nid(ocxlpmem->pdev->dev.of_node);
+
+ memset(®ion_desc, 0, sizeof(region_desc));
+ region_desc.res = &ocxlpmem->pmem_res;
+ region_desc.numa_node = NUMA_NO_NODE;
+ region_desc.target_node = target_node;
+ region_desc.num_mappings = 1;
+ region_desc.mapping = &nd_mapping_desc;
+ region_desc.nd_set = &ocxlpmem->nd_set;
+
+ set_bit(ND_REGION_PAGEMAP, ®ion_desc.flags);
+ /*
+ * NB: libnvdimm copies the data from ndr_desc into it's own
+ * structures so passing a stack pointer is fine.
+ */
+ ocxlpmem->nd_region = nvdimm_pmem_region_create(ocxlpmem->nvdimm_bus,
+ ®ion_desc);
+ if (!ocxlpmem->nd_region)
+ return -EINVAL;
+
+ dev_info(&ocxlpmem->dev,
+ "Onlining %lluMB of persistent memory\n",
+ nd_mapping_desc.size / SZ_1M);
+
+ return 0;
+}
+
+/**
+ * allocate_minor() - Allocate a minor number to use for an OpenCAPI pmem device
+ * @ocxlpmem: the device metadata
+ * Return: the allocated minor number
+ */
+static int allocate_minor(struct ocxlpmem *ocxlpmem)
+{
+ int minor;
+
+ mutex_lock(&minors_idr_lock);
+ minor = idr_alloc(&minors_idr, ocxlpmem, 0, NUM_MINORS, GFP_KERNEL);
+ mutex_unlock(&minors_idr_lock);
+ return minor;
+}
+
+static void free_minor(struct ocxlpmem *ocxlpmem)
+{
+ mutex_lock(&minors_idr_lock);
+ idr_remove(&minors_idr, MINOR(ocxlpmem->dev.devt));
+ mutex_unlock(&minors_idr_lock);
+}
+
+/**
+ * free_ocxlpmem() - Free all members of an ocxlpmem struct
+ * @ocxlpmem: the device struct to clear
+ */
+static void free_ocxlpmem(struct ocxlpmem *ocxlpmem)
+{
+ int rc;
+
+ if (ocxlpmem->nvdimm_bus)
+ nvdimm_bus_unregister(ocxlpmem->nvdimm_bus);
+
+ free_minor(ocxlpmem);
+
+ if (ocxlpmem->metadata_addr)
+ devm_memunmap(&ocxlpmem->dev, ocxlpmem->metadata_addr);
+
+ if (ocxlpmem->ocxl_context) {
+ rc = ocxl_context_detach(ocxlpmem->ocxl_context);
+ if (rc == -EBUSY)
+ dev_warn(&ocxlpmem->dev, "Timeout detaching ocxl context\n");
+ else
+ ocxl_context_free(ocxlpmem->ocxl_context);
+
+ }
+
+ if (ocxlpmem->ocxl_afu)
+ ocxl_afu_put(ocxlpmem->ocxl_afu);
+
+ if (ocxlpmem->ocxl_fn)
+ ocxl_function_close(ocxlpmem->ocxl_fn);
+
+ kfree(ocxlpmem);
+}
+
+/**
+ * free_ocxlpmem_dev() - Free an OpenCAPI persistent memory device
+ * @dev: The device struct
+ */
+static void free_ocxlpmem_dev(struct device *dev)
+{
+ struct ocxlpmem *ocxlpmem = container_of(dev, struct ocxlpmem, dev);
+
+ free_ocxlpmem(ocxlpmem);
+}
+
+/**
+ * ocxlpmem_register() - Register an OpenCAPI pmem device with the kernel
+ * @ocxlpmem: the device metadata
+ * Return: 0 on success, negative on failure
+ */
+static int ocxlpmem_register(struct ocxlpmem *ocxlpmem)
+{
+ int rc;
+ int minor = allocate_minor(ocxlpmem);
+
+ if (minor < 0)
+ return minor;
+
+ ocxlpmem->dev.release = free_ocxlpmem_dev;
+ rc = dev_set_name(&ocxlpmem->dev, "ocxlpmem%d", minor);
+ if (rc < 0)
+ return rc;
+
+ ocxlpmem->dev.devt = MKDEV(MAJOR(ocxlpmem_dev), minor);
+ ocxlpmem->dev.class = ocxlpmem_class;
+ ocxlpmem->dev.parent = &ocxlpmem->pdev->dev;
+
+ return device_register(&ocxlpmem->dev);
+}
+
+/**
+ * ocxlpmem_remove() - Free an OpenCAPI persistent memory device
+ * @pdev: the PCI device information struct
+ */
+static void ocxlpmem_remove(struct pci_dev *pdev)
+{
+ if (PCI_FUNC(pdev->devfn) == 0) {
+ struct ocxlpmem_function0 *func0 = pci_get_drvdata(pdev);
+
+ if (func0) {
+ ocxl_function_close(func0->ocxl_fn);
+ func0->ocxl_fn = NULL;
+ }
+ } else {
+ struct ocxlpmem *ocxlpmem = pci_get_drvdata(pdev);
+
+ if (ocxlpmem)
+ device_unregister(&ocxlpmem->dev);
+ }
+}
+
+/**
+ * probe_function0() - Set up function 0 for an OpenCAPI persistent memory device
+ * This is important as it enables templates higher than 0 across all other functions,
+ * which in turn enables higher bandwidth accesses
+ * @pdev: the PCI device information struct
+ * Return: 0 on success, negative on failure
+ */
+static int probe_function0(struct pci_dev *pdev)
+{
+ struct ocxlpmem_function0 *func0 = NULL;
+ struct ocxl_fn *fn;
+
+ func0 = kzalloc(sizeof(*func0), GFP_KERNEL);
+ if (!func0)
+ return -ENOMEM;
+
+ func0->pdev = pdev;
+ fn = ocxl_function_open(pdev);
+ if (IS_ERR(fn)) {
+ kfree(func0);
+ dev_err(&pdev->dev, "failed to open OCXL function\n");
+ return PTR_ERR(fn);
+ }
+ func0->ocxl_fn = fn;
+
+ pci_set_drvdata(pdev, func0);
+
+ return 0;
+}
+
+/**
+ * probe() - Init an OpenCAPI persistent memory device
+ * @pdev: the PCI device information struct
+ * @ent: The entry from ocxlpmem_pci_tbl
+ * Return: 0 on success, negative on failure
+ */
+static int probe(struct pci_dev *pdev, const struct pci_device_id *ent)
+{
+ struct ocxlpmem *ocxlpmem;
+ int rc;
+
+ if (PCI_FUNC(pdev->devfn) == 0)
+ return probe_function0(pdev);
+ else if (PCI_FUNC(pdev->devfn) != 1)
+ return 0;
+
+ ocxlpmem = kzalloc(sizeof(*ocxlpmem), GFP_KERNEL);
+ if (!ocxlpmem) {
+ dev_err(&pdev->dev, "Could not allocate OpenCAPI persistent memory metadata\n");
+ rc = -ENOMEM;
+ goto err;
+ }
+ ocxlpmem->pdev = pdev;
+
+ pci_set_drvdata(pdev, ocxlpmem);
+
+ ocxlpmem->ocxl_fn = ocxl_function_open(pdev);
+ if (IS_ERR(ocxlpmem->ocxl_fn)) {
+ kfree(ocxlpmem);
+ pci_set_drvdata(pdev, NULL);
+ dev_err(&pdev->dev, "failed to open OCXL function\n");
+ rc = PTR_ERR(ocxlpmem->ocxl_fn);
+ goto err;
+ }
+
+ ocxlpmem->ocxl_afu = ocxl_function_fetch_afu(ocxlpmem->ocxl_fn, 0);
+ if (ocxlpmem->ocxl_afu == NULL) {
+ dev_err(&pdev->dev, "Could not get OCXL AFU from function\n");
+ rc = -ENXIO;
+ goto err;
+ }
+
+ ocxl_afu_get(ocxlpmem->ocxl_afu);
+
+ // Resources allocated below here are cleaned up in the release handler
+
+ rc = ocxlpmem_register(ocxlpmem);
+ if (rc) {
+ dev_err(&pdev->dev, "Could not register OpenCAPI persistent memory device with the kernel\n");
+ goto err;
+ }
+
+ rc = ocxl_context_alloc(&ocxlpmem->ocxl_context, ocxlpmem->ocxl_afu, NULL);
+ if (rc) {
+ dev_err(&pdev->dev, "Could not allocate OCXL context\n");
+ goto err;
+ }
+
+ rc = ocxl_context_attach(ocxlpmem->ocxl_context, 0, NULL);
+ if (rc) {
+ dev_err(&pdev->dev, "Could not attach ocxl context\n");
+ goto err;
+ }
+
+ rc = register_lpc_mem(ocxlpmem);
+ if (rc) {
+ dev_err(&pdev->dev, "Could not register OpenCAPI persistent memory with libnvdimm\n");
+ goto err;
+ }
+
+ return 0;
+
+err:
+ /*
+ * Further cleanup is done in the release handler via free_ocxlpmem()
+ * This allows us to keep the character device live to handle IOCTLs to
+ * investigate issues if the card has an error
+ */
+
+ dev_err(&pdev->dev,
+ "Error detected, will not register OpenCAPI persistent memory\n");
+ return rc;
+}
+
+static struct pci_driver pci_driver = {
+ .name = "ocxl-pmem",
+ .id_table = ocxlpmem_pci_tbl,
+ .probe = probe,
+ .remove = ocxlpmem_remove,
+ .shutdown = ocxlpmem_remove,
+};
+
+static int __init ocxlpmem_init(void)
+{
+ int rc = 0;
+
+ rc = pci_register_driver(&pci_driver);
+ if (rc)
+ return rc;
+
+ return 0;
+}
+
+static void ocxlpmem_exit(void)
+{
+ pci_unregister_driver(&pci_driver);
+}
+
+module_init(ocxlpmem_init);
+module_exit(ocxlpmem_exit);
+
+MODULE_DESCRIPTION("OpenCAPI Persistent Memory");
+MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/platforms/powernv/pmem/ocxl_internal.h b/arch/powerpc/platforms/powernv/pmem/ocxl_internal.h
new file mode 100644
index 000000000000..0faf3740e9b8
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/pmem/ocxl_internal.h
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright 2019 IBM Corp.
+
+#include <linux/pci.h>
+#include <misc/ocxl.h>
+#include <linux/libnvdimm.h>
+#include <linux/mm.h>
+
+#define LABEL_AREA_SIZE (1UL << PA_SECTION_SHIFT)
+
+struct ocxlpmem_function0 {
+ struct pci_dev *pdev;
+ struct ocxl_fn *ocxl_fn;
+};
+
+struct ocxlpmem {
+ struct device dev;
+ struct pci_dev *pdev;
+ struct ocxl_fn *ocxl_fn;
+ struct nd_interleave_set nd_set;
+ struct nvdimm_bus_descriptor bus_desc;
+ struct nvdimm_bus *nvdimm_bus;
+ struct ocxl_afu *ocxl_afu;
+ struct ocxl_context *ocxl_context;
+ void *metadata_addr;
+ struct resource pmem_res;
+ struct nd_region *nd_region;
+};
--
2.24.1
^ permalink raw reply related
* [PATCH v3 20/27] powerpc/powernv/pmem: Forward events to userspace
From: Alastair D'Silva @ 2020-02-21 3:27 UTC (permalink / raw)
To: alastair
Cc: Madhavan Srinivasan, Alexey Kardashevskiy, Masahiro Yamada,
Oliver O'Halloran, Mauro Carvalho Chehab, Ira Weiny,
Thomas Gleixner, Rob Herring, Dave Jiang, linux-nvdimm,
Aneesh Kumar K . V, Krzysztof Kozlowski, Anju T Sudhakar,
Mahesh Salgaonkar, Andrew Donnellan, Arnd Bergmann, Greg Kurz,
Nicholas Piggin, Cédric Le Goater, Dan Williams,
Hari Bathini, linux-mm, Greg Kroah-Hartman, linux-kernel,
Vishal Verma, Frederic Barrat, Paul Mackerras, Andrew Morton,
linuxppc-dev, David S. Miller
In-Reply-To: <20200221032720.33893-1-alastair@au1.ibm.com>
From: Alastair D'Silva <alastair@d-silva.org>
Some of the interrupts that the card generates are better handled
by the userspace daemon, in particular:
Controller Hardware/Firmware Fatal
Controller Dump Available
Error Log available
This patch allows a userspace application to register an eventfd with
the driver via SCM_IOCTL_EVENTFD to receive notifications of these
interrupts.
Userspace can then identify what events have occurred by calling
SCM_IOCTL_EVENT_CHECK and checking against the SCM_IOCTL_EVENT_FOO
masks.
Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
---
arch/powerpc/platforms/powernv/pmem/ocxl.c | 216 ++++++++++++++++++
.../platforms/powernv/pmem/ocxl_internal.h | 5 +
include/uapi/nvdimm/ocxl-pmem.h | 16 ++
3 files changed, 237 insertions(+)
diff --git a/arch/powerpc/platforms/powernv/pmem/ocxl.c b/arch/powerpc/platforms/powernv/pmem/ocxl.c
index 009d4fd29e7d..e46696d3cc36 100644
--- a/arch/powerpc/platforms/powernv/pmem/ocxl.c
+++ b/arch/powerpc/platforms/powernv/pmem/ocxl.c
@@ -10,6 +10,7 @@
#include <misc/ocxl.h>
#include <linux/delay.h>
#include <linux/ndctl.h>
+#include <linux/eventfd.h>
#include <linux/fs.h>
#include <linux/mm_types.h>
#include <linux/memory_hotplug.h>
@@ -335,11 +336,22 @@ static void free_ocxlpmem(struct ocxlpmem *ocxlpmem)
{
int rc;
+ // Disable doorbells
+ (void)ocxl_global_mmio_set64(ocxlpmem->ocxl_afu, GLOBAL_MMIO_CHIEC,
+ OCXL_LITTLE_ENDIAN,
+ GLOBAL_MMIO_CHI_ALL);
+
if (ocxlpmem->nvdimm_bus)
nvdimm_bus_unregister(ocxlpmem->nvdimm_bus);
free_minor(ocxlpmem);
+ if (ocxlpmem->irq_addr[1])
+ iounmap(ocxlpmem->irq_addr[1]);
+
+ if (ocxlpmem->irq_addr[0])
+ iounmap(ocxlpmem->irq_addr[0]);
+
if (ocxlpmem->cdev.owner)
cdev_del(&ocxlpmem->cdev);
@@ -443,6 +455,11 @@ static int file_release(struct inode *inode, struct file *file)
{
struct ocxlpmem *ocxlpmem = file->private_data;
+ if (ocxlpmem->ev_ctx) {
+ eventfd_ctx_put(ocxlpmem->ev_ctx);
+ ocxlpmem->ev_ctx = NULL;
+ }
+
ocxlpmem_put(ocxlpmem);
return 0;
}
@@ -938,6 +955,51 @@ static int ioctl_controller_stats(struct ocxlpmem *ocxlpmem,
return rc;
}
+static int ioctl_eventfd(struct ocxlpmem *ocxlpmem,
+ struct ioctl_ocxl_pmem_eventfd __user *uarg)
+{
+ struct ioctl_ocxl_pmem_eventfd args;
+
+ if (copy_from_user(&args, uarg, sizeof(args)))
+ return -EFAULT;
+
+ if (ocxlpmem->ev_ctx)
+ return -EINVAL;
+
+ ocxlpmem->ev_ctx = eventfd_ctx_fdget(args.eventfd);
+ if (!ocxlpmem->ev_ctx)
+ return -EFAULT;
+
+ return 0;
+}
+
+static int ioctl_event_check(struct ocxlpmem *ocxlpmem, u64 __user *uarg)
+{
+ u64 val = 0;
+ int rc;
+ u64 chi = 0;
+
+ rc = ocxlpmem_chi(ocxlpmem, &chi);
+ if (rc < 0)
+ return rc;
+
+ if (chi & GLOBAL_MMIO_CHI_ELA)
+ val |= IOCTL_OCXL_PMEM_EVENT_ERROR_LOG_AVAILABLE;
+
+ if (chi & GLOBAL_MMIO_CHI_CDA)
+ val |= IOCTL_OCXL_PMEM_EVENT_CONTROLLER_DUMP_AVAILABLE;
+
+ if (chi & GLOBAL_MMIO_CHI_CFFS)
+ val |= IOCTL_OCXL_PMEM_EVENT_FIRMWARE_FATAL;
+
+ if (chi & GLOBAL_MMIO_CHI_CHFS)
+ val |= IOCTL_OCXL_PMEM_EVENT_HARDWARE_FATAL;
+
+ rc = copy_to_user((u64 __user *) uarg, &val, sizeof(val));
+
+ return rc;
+}
+
static long file_ioctl(struct file *file, unsigned int cmd, unsigned long args)
{
struct ocxlpmem *ocxlpmem = file->private_data;
@@ -966,6 +1028,15 @@ static long file_ioctl(struct file *file, unsigned int cmd, unsigned long args)
rc = ioctl_controller_stats(ocxlpmem,
(struct ioctl_ocxl_pmem_controller_stats __user *)args);
break;
+
+ case IOCTL_OCXL_PMEM_EVENTFD:
+ rc = ioctl_eventfd(ocxlpmem,
+ (struct ioctl_ocxl_pmem_eventfd __user *)args);
+ break;
+
+ case IOCTL_OCXL_PMEM_EVENT_CHECK:
+ rc = ioctl_event_check(ocxlpmem, (u64 __user *)args);
+ break;
}
return rc;
@@ -1107,6 +1178,146 @@ static void dump_error_log(struct ocxlpmem *ocxlpmem)
kfree(buf);
}
+static irqreturn_t imn0_handler(void *private)
+{
+ struct ocxlpmem *ocxlpmem = private;
+ u64 chi = 0;
+
+ (void)ocxlpmem_chi(ocxlpmem, &chi);
+
+ if (chi & GLOBAL_MMIO_CHI_ELA) {
+ dev_warn(&ocxlpmem->dev, "Error log is available\n");
+
+ if (ocxlpmem->ev_ctx)
+ eventfd_signal(ocxlpmem->ev_ctx, 1);
+ }
+
+ if (chi & GLOBAL_MMIO_CHI_CDA) {
+ dev_warn(&ocxlpmem->dev, "Controller dump is available\n");
+
+ if (ocxlpmem->ev_ctx)
+ eventfd_signal(ocxlpmem->ev_ctx, 1);
+ }
+
+
+ return IRQ_HANDLED;
+}
+
+static irqreturn_t imn1_handler(void *private)
+{
+ struct ocxlpmem *ocxlpmem = private;
+ u64 chi = 0;
+
+ (void)ocxlpmem_chi(ocxlpmem, &chi);
+
+ if (chi & (GLOBAL_MMIO_CHI_CFFS | GLOBAL_MMIO_CHI_CHFS)) {
+ dev_err(&ocxlpmem->dev,
+ "Controller status is fatal, chi=0x%llx, going offline\n", chi);
+
+ if (ocxlpmem->nvdimm_bus) {
+ nvdimm_bus_unregister(ocxlpmem->nvdimm_bus);
+ ocxlpmem->nvdimm_bus = NULL;
+ }
+
+ if (ocxlpmem->ev_ctx)
+ eventfd_signal(ocxlpmem->ev_ctx, 1);
+ }
+
+ return IRQ_HANDLED;
+}
+
+
+/**
+ * ocxlpmem_setup_irq() - Set up the IRQs for the OpenCAPI Persistent Memory device
+ * @ocxlpmem: the device metadata
+ * Return: 0 on success, negative on failure
+ */
+static int ocxlpmem_setup_irq(struct ocxlpmem *ocxlpmem)
+{
+ int rc;
+ u64 irq_addr;
+
+ rc = ocxl_afu_irq_alloc(ocxlpmem->ocxl_context, &ocxlpmem->irq_id[0]);
+ if (rc)
+ return rc;
+
+ rc = ocxl_irq_set_handler(ocxlpmem->ocxl_context, ocxlpmem->irq_id[0],
+ imn0_handler, NULL, ocxlpmem);
+
+ irq_addr = ocxl_afu_irq_get_addr(ocxlpmem->ocxl_context, ocxlpmem->irq_id[0]);
+ if (!irq_addr)
+ return -EINVAL;
+
+ ocxlpmem->irq_addr[0] = ioremap(irq_addr, PAGE_SIZE);
+ if (!ocxlpmem->irq_addr[0])
+ return -EINVAL;
+
+ rc = ocxl_global_mmio_write64(ocxlpmem->ocxl_afu, GLOBAL_MMIO_IMA0_OHP,
+ OCXL_LITTLE_ENDIAN,
+ (u64)ocxlpmem->irq_addr[0]);
+ if (rc)
+ goto out_irq0;
+
+ rc = ocxl_global_mmio_write64(ocxlpmem->ocxl_afu, GLOBAL_MMIO_IMA0_CFP,
+ OCXL_LITTLE_ENDIAN, 0);
+ if (rc)
+ goto out_irq0;
+
+ rc = ocxl_afu_irq_alloc(ocxlpmem->ocxl_context, &ocxlpmem->irq_id[1]);
+ if (rc)
+ goto out_irq0;
+
+
+ rc = ocxl_irq_set_handler(ocxlpmem->ocxl_context, ocxlpmem->irq_id[1],
+ imn1_handler, NULL, ocxlpmem);
+ if (rc)
+ goto out_irq0;
+
+ irq_addr = ocxl_afu_irq_get_addr(ocxlpmem->ocxl_context, ocxlpmem->irq_id[1]);
+ if (!irq_addr) {
+ rc = -EFAULT;
+ goto out_irq0;
+ }
+
+ ocxlpmem->irq_addr[1] = ioremap(irq_addr, PAGE_SIZE);
+ if (!ocxlpmem->irq_addr[1]) {
+ rc = -EINVAL;
+ goto out_irq0;
+ }
+
+ rc = ocxl_global_mmio_write64(ocxlpmem->ocxl_afu, GLOBAL_MMIO_IMA1_OHP,
+ OCXL_LITTLE_ENDIAN,
+ (u64)ocxlpmem->irq_addr[1]);
+ if (rc)
+ goto out_irq1;
+
+ rc = ocxl_global_mmio_write64(ocxlpmem->ocxl_afu, GLOBAL_MMIO_IMA1_CFP,
+ OCXL_LITTLE_ENDIAN, 0);
+ if (rc)
+ goto out_irq1;
+
+ // Enable doorbells
+ rc = ocxl_global_mmio_set64(ocxlpmem->ocxl_afu, GLOBAL_MMIO_CHIE,
+ OCXL_LITTLE_ENDIAN,
+ GLOBAL_MMIO_CHI_ELA | GLOBAL_MMIO_CHI_CDA |
+ GLOBAL_MMIO_CHI_CFFS | GLOBAL_MMIO_CHI_CHFS |
+ GLOBAL_MMIO_CHI_NSCRA);
+ if (rc)
+ goto out_irq1;
+
+ return 0;
+
+out_irq1:
+ iounmap(ocxlpmem->irq_addr[1]);
+ ocxlpmem->irq_addr[1] = NULL;
+
+out_irq0:
+ iounmap(ocxlpmem->irq_addr[0]);
+ ocxlpmem->irq_addr[0] = NULL;
+
+ return rc;
+}
+
/**
* probe_function0() - Set up function 0 for an OpenCAPI persistent memory device
* This is important as it enables templates higher than 0 across all other functions,
@@ -1216,6 +1427,11 @@ static int probe(struct pci_dev *pdev, const struct pci_device_id *ent)
goto err;
}
+ if (ocxlpmem_setup_irq(ocxlpmem)) {
+ dev_err(&pdev->dev, "Could not set up OCXL IRQs\n");
+ goto err;
+ }
+
if (setup_command_metadata(ocxlpmem)) {
dev_err(&pdev->dev, "Could not read OCXL command matada\n");
goto err;
diff --git a/arch/powerpc/platforms/powernv/pmem/ocxl_internal.h b/arch/powerpc/platforms/powernv/pmem/ocxl_internal.h
index b953ee522ed4..927690f4888f 100644
--- a/arch/powerpc/platforms/powernv/pmem/ocxl_internal.h
+++ b/arch/powerpc/platforms/powernv/pmem/ocxl_internal.h
@@ -103,6 +103,10 @@ struct ocxlpmem {
struct pci_dev *pdev;
struct cdev cdev;
struct ocxl_fn *ocxl_fn;
+#define SCM_IRQ_COUNT 2
+ int irq_id[SCM_IRQ_COUNT];
+ struct dev_pagemap irq_pgmap[SCM_IRQ_COUNT];
+ void *irq_addr[SCM_IRQ_COUNT];
struct nd_interleave_set nd_set;
struct nvdimm_bus_descriptor bus_desc;
struct nvdimm_bus *nvdimm_bus;
@@ -113,6 +117,7 @@ struct ocxlpmem {
struct command_metadata ns_command;
struct resource pmem_res;
struct nd_region *nd_region;
+ struct eventfd_ctx *ev_ctx;
char fw_version[8+1];
u32 timeouts[ADMIN_COMMAND_MAX+1];
diff --git a/include/uapi/nvdimm/ocxl-pmem.h b/include/uapi/nvdimm/ocxl-pmem.h
index add223aa2fdb..988eb0bc413d 100644
--- a/include/uapi/nvdimm/ocxl-pmem.h
+++ b/include/uapi/nvdimm/ocxl-pmem.h
@@ -66,6 +66,20 @@ struct ioctl_ocxl_pmem_controller_stats {
__u64 cache_write_latency; /* nanoseconds */
};
+struct ioctl_ocxl_pmem_eventfd {
+ __s32 eventfd;
+ __u32 reserved;
+};
+
+#ifndef BIT_ULL
+#define BIT_ULL(nr) (1ULL << (nr))
+#endif
+
+#define IOCTL_OCXL_PMEM_EVENT_CONTROLLER_DUMP_AVAILABLE BIT_ULL(0)
+#define IOCTL_OCXL_PMEM_EVENT_ERROR_LOG_AVAILABLE BIT_ULL(1)
+#define IOCTL_OCXL_PMEM_EVENT_HARDWARE_FATAL BIT_ULL(2)
+#define IOCTL_OCXL_PMEM_EVENT_FIRMWARE_FATAL BIT_ULL(3)
+
/* ioctl numbers */
#define OCXL_PMEM_MAGIC 0x5C
/* SCM devices */
@@ -74,5 +88,7 @@ struct ioctl_ocxl_pmem_controller_stats {
#define IOCTL_OCXL_PMEM_CONTROLLER_DUMP_DATA _IOWR(OCXL_PMEM_MAGIC, 0x03, struct ioctl_ocxl_pmem_controller_dump_data)
#define IOCTL_OCXL_PMEM_CONTROLLER_DUMP_COMPLETE _IO(OCXL_PMEM_MAGIC, 0x04)
#define IOCTL_OCXL_PMEM_CONTROLLER_STATS _IO(OCXL_PMEM_MAGIC, 0x05)
+#define IOCTL_OCXL_PMEM_EVENTFD _IOW(OCXL_PMEM_MAGIC, 0x06, struct ioctl_ocxl_pmem_eventfd)
+#define IOCTL_OCXL_PMEM_EVENT_CHECK _IOR(OCXL_PMEM_MAGIC, 0x07, __u64)
#endif /* _UAPI_OCXL_SCM_H */
--
2.24.1
^ permalink raw reply related
* [PATCH v3 23/27] powerpc/powernv/pmem: Add debug IOCTLs
From: Alastair D'Silva @ 2020-02-21 3:27 UTC (permalink / raw)
To: alastair
Cc: Madhavan Srinivasan, Alexey Kardashevskiy, Masahiro Yamada,
Oliver O'Halloran, Mauro Carvalho Chehab, Ira Weiny,
Thomas Gleixner, Rob Herring, Dave Jiang, linux-nvdimm,
Aneesh Kumar K . V, Krzysztof Kozlowski, Anju T Sudhakar,
Mahesh Salgaonkar, Andrew Donnellan, Arnd Bergmann, Greg Kurz,
Nicholas Piggin, Cédric Le Goater, Dan Williams,
Hari Bathini, linux-mm, Greg Kroah-Hartman, linux-kernel,
Vishal Verma, Frederic Barrat, Paul Mackerras, Andrew Morton,
linuxppc-dev, David S. Miller
In-Reply-To: <20200221032720.33893-1-alastair@au1.ibm.com>
From: Alastair D'Silva <alastair@d-silva.org>
These IOCTLs provide low level access to the card to aid in debugging
controller/FPGA firmware.
Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
---
arch/powerpc/platforms/powernv/pmem/Kconfig | 6 +
arch/powerpc/platforms/powernv/pmem/ocxl.c | 249 ++++++++++++++++++++
include/uapi/nvdimm/ocxl-pmem.h | 32 +++
3 files changed, 287 insertions(+)
diff --git a/arch/powerpc/platforms/powernv/pmem/Kconfig b/arch/powerpc/platforms/powernv/pmem/Kconfig
index c5d927520920..3f44429d70c9 100644
--- a/arch/powerpc/platforms/powernv/pmem/Kconfig
+++ b/arch/powerpc/platforms/powernv/pmem/Kconfig
@@ -12,4 +12,10 @@ config OCXL_PMEM
Select N if unsure.
+config OCXL_PMEM_DEBUG
+ bool "OpenCAPI Persistent Memory debugging"
+ depends on OCXL_PMEM
+ help
+ Enables low level IOCTLs for OpenCAPI Persistent Memory firmware development
+
endif
diff --git a/arch/powerpc/platforms/powernv/pmem/ocxl.c b/arch/powerpc/platforms/powernv/pmem/ocxl.c
index e01f6f9fc180..d4ce5e9e0521 100644
--- a/arch/powerpc/platforms/powernv/pmem/ocxl.c
+++ b/arch/powerpc/platforms/powernv/pmem/ocxl.c
@@ -1050,6 +1050,235 @@ int req_controller_health_perf(struct ocxlpmem *ocxlpmem)
GLOBAL_MMIO_HCI_REQ_HEALTH_PERF);
}
+#ifdef CONFIG_OCXL_PMEM_DEBUG
+/**
+ * enable_fwdebug() - Enable FW debug on the controller
+ * @ocxlpmem: the device metadata
+ * Return: 0 on success, negative on failure
+ */
+static int enable_fwdebug(const struct ocxlpmem *ocxlpmem)
+{
+ return ocxl_global_mmio_set64(ocxlpmem->ocxl_afu, GLOBAL_MMIO_HCI,
+ OCXL_LITTLE_ENDIAN,
+ GLOBAL_MMIO_HCI_FW_DEBUG);
+}
+
+/**
+ * disable_fwdebug() - Disable FW debug on the controller
+ * @ocxlpmem: the device metadata
+ * Return: 0 on success, negative on failure
+ */
+static int disable_fwdebug(const struct ocxlpmem *ocxlpmem)
+{
+ return ocxl_global_mmio_set64(ocxlpmem->ocxl_afu, GLOBAL_MMIO_HCIC,
+ OCXL_LITTLE_ENDIAN,
+ GLOBAL_MMIO_HCI_FW_DEBUG);
+}
+
+static int ioctl_fwdebug(struct ocxlpmem *ocxlpmem,
+ struct ioctl_ocxl_pmem_fwdebug __user *uarg)
+{
+ struct ioctl_ocxl_pmem_fwdebug args;
+ u64 val;
+ int i;
+ int rc;
+
+ if (copy_from_user(&args, uarg, sizeof(args)))
+ return -EFAULT;
+
+ // Buffer size must be a multiple of 8
+ if ((args.buf_size & 0x07))
+ return -EINVAL;
+
+ if (args.buf_size > ocxlpmem->admin_command.data_size)
+ return -EINVAL;
+
+ mutex_lock(&ocxlpmem->admin_command.lock);
+
+ rc = enable_fwdebug(ocxlpmem);
+ if (rc)
+ goto out;
+
+ rc = admin_command_request(ocxlpmem, ADMIN_COMMAND_FW_DEBUG);
+ if (rc)
+ goto out;
+
+ // Write DebugAction & FunctionCode
+ val = ((u64)args.debug_action << 56) | ((u64)args.function_code << 40);
+
+ rc = ocxl_global_mmio_write64(ocxlpmem->ocxl_afu,
+ ocxlpmem->admin_command.request_offset + 0x08,
+ OCXL_LITTLE_ENDIAN, val);
+ if (rc)
+ goto out;
+
+ rc = ocxl_global_mmio_write64(ocxlpmem->ocxl_afu,
+ ocxlpmem->admin_command.request_offset + 0x10,
+ OCXL_LITTLE_ENDIAN, args.debug_parameter_1);
+ if (rc)
+ goto out;
+
+ rc = ocxl_global_mmio_write64(ocxlpmem->ocxl_afu,
+ ocxlpmem->admin_command.request_offset + 0x18,
+ OCXL_LITTLE_ENDIAN, args.debug_parameter_2);
+ if (rc)
+ goto out;
+
+ for (i = 0x20; i < 0x38; i += 0x08)
+ rc = ocxl_global_mmio_write64(ocxlpmem->ocxl_afu,
+ ocxlpmem->admin_command.request_offset + i,
+ OCXL_LITTLE_ENDIAN, 0);
+ if (rc)
+ goto out;
+
+
+ // Populate admin command buffer
+ if (args.buf_size) {
+ for (i = 0; i < args.buf_size; i += sizeof(u64)) {
+ u64 val;
+
+ if (copy_from_user(&val, &args.buf[i], sizeof(u64)))
+ return -EFAULT;
+
+ rc = ocxl_global_mmio_write64(ocxlpmem->ocxl_afu,
+ ocxlpmem->admin_command.data_offset + i,
+ OCXL_HOST_ENDIAN, val);
+ if (rc)
+ goto out;
+ }
+ }
+
+ rc = admin_command_execute(ocxlpmem);
+ if (rc)
+ goto out;
+
+ rc = admin_command_complete_timeout(ocxlpmem,
+ ocxlpmem->timeouts[ADMIN_COMMAND_FW_DEBUG]);
+ if (rc < 0)
+ goto out;
+
+ rc = admin_response(ocxlpmem);
+ if (rc < 0)
+ goto out;
+ if (rc != STATUS_SUCCESS) {
+ warn_status(ocxlpmem, "Unexpected status from FW Debug", rc);
+ goto out;
+ }
+
+ if (args.buf_size) {
+ for (i = 0; i < args.buf_size; i += sizeof(u64)) {
+ u64 val;
+
+ rc = ocxl_global_mmio_read64(ocxlpmem->ocxl_afu,
+ ocxlpmem->admin_command.data_offset + i,
+ OCXL_HOST_ENDIAN, &val);
+ if (rc)
+ goto out;
+
+ if (copy_to_user(&args.buf[i], &val, sizeof(u64))) {
+ rc = -EFAULT;
+ goto out;
+ }
+ }
+ }
+
+ rc = admin_response_handled(ocxlpmem);
+ if (rc)
+ goto out;
+
+ rc = disable_fwdebug(ocxlpmem);
+ if (rc)
+ goto out;
+
+out:
+ mutex_unlock(&ocxlpmem->admin_command.lock);
+ return rc;
+}
+
+static int ioctl_shutdown(struct ocxlpmem *ocxlpmem)
+{
+ int rc;
+
+ mutex_lock(&ocxlpmem->admin_command.lock);
+
+ rc = admin_command_request(ocxlpmem, ADMIN_COMMAND_SHUTDOWN);
+ if (rc)
+ goto out;
+
+ rc = admin_command_execute(ocxlpmem);
+ if (rc)
+ goto out;
+
+ rc = admin_command_complete_timeout(ocxlpmem, ADMIN_COMMAND_SHUTDOWN);
+ if (rc < 0) {
+ dev_warn(&ocxlpmem->dev, "Shutdown timed out\n");
+ goto out;
+ }
+
+ rc = 0;
+ goto out;
+
+out:
+ mutex_unlock(&ocxlpmem->admin_command.lock);
+ return rc;
+}
+
+static int ioctl_mmio_write(struct ocxlpmem *ocxlpmem,
+ struct ioctl_ocxl_pmem_mmio __user *uarg)
+{
+ struct scm_ioctl_mmio args;
+
+ if (copy_from_user(&args, uarg, sizeof(args)))
+ return -EFAULT;
+
+ return ocxl_global_mmio_write64(ocxlpmem->ocxl_afu, args.address,
+ OCXL_LITTLE_ENDIAN, args.val);
+}
+
+static int ioctl_mmio_read(struct ocxlpmem *ocxlpmem,
+ struct ioctl_ocxl_pmem_mmio __user *uarg)
+{
+ struct ioctl_ocxl_pmem_mmio args;
+ int rc;
+
+ if (copy_from_user(&args, uarg, sizeof(args)))
+ return -EFAULT;
+
+ rc = ocxl_global_mmio_read64(ocxlpmem->ocxl_afu, args.address,
+ OCXL_LITTLE_ENDIAN, &args.val);
+ if (rc)
+ return rc;
+
+ if (copy_to_user(uarg, &args, sizeof(args)))
+ return -EFAULT;
+
+ return 0;
+}
+#else /* CONFIG_OCXL_PMEM_DEBUG */
+static int ioctl_fwdebug(struct ocxlpmem *ocxlpmem,
+ struct ioctl_ocxl_pmem_fwdebug __user *uarg)
+{
+ return -EPERM;
+}
+
+static int ioctl_shutdown(struct ocxlpmem *ocxlpmem)
+{
+ return -EPERM;
+}
+
+static int ioctl_mmio_write(struct ocxlpmem *ocxlpmem,
+ struct ioctl_ocxl_pmem_mmio __user *uarg)
+{
+ return -EPERM;
+}
+
+static int ioctl_mmio_read(struct ocxlpmem *ocxlpmem,
+ struct ioctl_ocxl_pmem_mmio __user *uarg)
+{
+ return -EPERM;
+}
+#endif /* CONFIG_OCXL_PMEM_DEBUG */
+
static long file_ioctl(struct file *file, unsigned int cmd, unsigned long args)
{
struct ocxlpmem *ocxlpmem = file->private_data;
@@ -1091,6 +1320,26 @@ static long file_ioctl(struct file *file, unsigned int cmd, unsigned long args)
case IOCTL_OCXL_PMEM_REQUEST_HEALTH:
rc = req_controller_health_perf(ocxlpmem);
break;
+
+ case IOCTL_OCXL_PMEM_FWDEBUG:
+ rc = ioctl_fwdebug(ocxlpmem,
+ (struct ioctl_ocxl_pmem_fwdebug __user *)args);
+ break;
+
+ case IOCTL_OCXL_PMEM_SHUTDOWN:
+ rc = ioctl_shutdown(ocxlpmem);
+ break;
+
+ case IOCTL_OCXL_PMEM_MMIO_WRITE:
+ rc = ioctl_mmio_write(ocxlpmem,
+ (struct ioctl_ocxl_pmem_mmio __user *)args);
+ break;
+
+ case IOCTL_OCXL_PMEM_MMIO_READ:
+ rc = ioctl_mmio_read(ocxlpmem,
+ (struct ioctl_ocxl_pmem_mmio __user *)args);
+ break;
+
}
return rc;
diff --git a/include/uapi/nvdimm/ocxl-pmem.h b/include/uapi/nvdimm/ocxl-pmem.h
index 0d03abb44001..e20a4f8be82a 100644
--- a/include/uapi/nvdimm/ocxl-pmem.h
+++ b/include/uapi/nvdimm/ocxl-pmem.h
@@ -6,6 +6,28 @@
#include <linux/types.h>
#include <linux/ioctl.h>
+enum ocxlpmem_fwdebug_action {
+ OCXL_PMEM_FWDEBUG_READ_CONTROLLER_MEMORY = 0x01,
+ OCXL_PMEM_FWDEBUG_WRITE_CONTROLLER_MEMORY = 0x02,
+ OCXL_PMEM_FWDEBUG_ENABLE_FUNCTION = 0x03,
+ OCXL_PMEM_FWDEBUG_DISABLE_FUNCTION = 0x04,
+ OCXL_PMEM_FWDEBUG_GET_PEL = 0x05, // Retrieve Persistent Error Log
+};
+
+struct ioctl_ocxl_pmem_buffer_info {
+ __u32 admin_command_buffer_size; // out
+ __u32 near_storage_buffer_size; // out
+};
+
+struct ioctl_ocxl_pmem_fwdebug { // All args are inputs
+ enum ocxlpmem_fwdebug_action debug_action;
+ __u16 function_code;
+ __u16 buf_size; // Size of optional data buffer
+ __u64 debug_parameter_1;
+ __u64 debug_parameter_2;
+ __u8 *buf; // Pointer to optional in/out data buffer
+};
+
#define OCXL_PMEM_ERROR_LOG_ACTION_RESET (1 << (32-32))
#define OCXL_PMEM_ERROR_LOG_ACTION_CHKFW (1 << (53-32))
#define OCXL_PMEM_ERROR_LOG_ACTION_REPLACE (1 << (54-32))
@@ -66,6 +88,11 @@ struct ioctl_ocxl_pmem_controller_stats {
__u64 cache_write_latency; /* nanoseconds */
};
+struct ioctl_ocxl_pmem_mmio {
+ __u64 address; /* Offset in global MMIO space */
+ __u64 val; /* value to write/was read */
+};
+
struct ioctl_ocxl_pmem_eventfd {
__s32 eventfd;
__u32 reserved;
@@ -92,4 +119,9 @@ struct ioctl_ocxl_pmem_eventfd {
#define IOCTL_OCXL_PMEM_EVENT_CHECK _IOR(OCXL_PMEM_MAGIC, 0x07, __u64)
#define IOCTL_OCXL_PMEM_REQUEST_HEALTH _IO(OCXL_PMEM_MAGIC, 0x08)
+#define IOCTL_OCXL_PMEM_FWDEBUG _IOWR(OCXL_PMEM_MAGIC, 0xf0, struct ioctl_ocxl_pmem_fwdebug)
+#define IOCTL_OCXL_PMEM_MMIO_WRITE _IOW(OCXL_PMEM_MAGIC, 0xf1, struct ioctl_ocxl_pmem_mmio)
+#define IOCTL_OCXL_PMEM_MMIO_READ _IOWR(OCXL_PMEM_MAGIC, 0xf2, struct ioctl_ocxl_pmem_mmio)
+#define IOCTL_OCXL_PMEM_SHUTDOWN _IO(OCXL_PMEM_MAGIC, 0xf3)
+
#endif /* _UAPI_OCXL_SCM_H */
--
2.24.1
^ permalink raw reply related
* [PATCH v3 25/27] powerpc/powernv/pmem: Expose the serial number in sysfs
From: Alastair D'Silva @ 2020-02-21 3:27 UTC (permalink / raw)
To: alastair
Cc: Madhavan Srinivasan, Alexey Kardashevskiy, Masahiro Yamada,
Oliver O'Halloran, Mauro Carvalho Chehab, Ira Weiny,
Thomas Gleixner, Rob Herring, Dave Jiang, linux-nvdimm,
Aneesh Kumar K . V, Krzysztof Kozlowski, Anju T Sudhakar,
Mahesh Salgaonkar, Andrew Donnellan, Arnd Bergmann, Greg Kurz,
Nicholas Piggin, Cédric Le Goater, Dan Williams,
Hari Bathini, linux-mm, Greg Kroah-Hartman, linux-kernel,
Vishal Verma, Frederic Barrat, Paul Mackerras, Andrew Morton,
linuxppc-dev, David S. Miller
In-Reply-To: <20200221032720.33893-1-alastair@au1.ibm.com>
From: Alastair D'Silva <alastair@d-silva.org>
This information will be used by ndctl in userspace to help users identify
the device.
Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
---
arch/powerpc/platforms/powernv/pmem/Makefile | 2 +-
arch/powerpc/platforms/powernv/pmem/ocxl.c | 5 +++
.../platforms/powernv/pmem/ocxl_internal.h | 6 +++
.../platforms/powernv/pmem/ocxl_sysfs.c | 37 +++++++++++++++++++
4 files changed, 49 insertions(+), 1 deletion(-)
create mode 100644 arch/powerpc/platforms/powernv/pmem/ocxl_sysfs.c
diff --git a/arch/powerpc/platforms/powernv/pmem/Makefile b/arch/powerpc/platforms/powernv/pmem/Makefile
index 4ceda25907d4..d02870806f30 100644
--- a/arch/powerpc/platforms/powernv/pmem/Makefile
+++ b/arch/powerpc/platforms/powernv/pmem/Makefile
@@ -4,4 +4,4 @@ ccflags-$(CONFIG_PPC_WERROR) += -Werror
obj-$(CONFIG_OCXL_PMEM) += ocxlpmem.o
-ocxlpmem-y := ocxl.o ocxl_internal.o
+ocxlpmem-y := ocxl.o ocxl_internal.o ocxl_sysfs.o
diff --git a/arch/powerpc/platforms/powernv/pmem/ocxl.c b/arch/powerpc/platforms/powernv/pmem/ocxl.c
index 5cd1b6d78dd6..ec73713d05ad 100644
--- a/arch/powerpc/platforms/powernv/pmem/ocxl.c
+++ b/arch/powerpc/platforms/powernv/pmem/ocxl.c
@@ -1878,6 +1878,11 @@ static int probe(struct pci_dev *pdev, const struct pci_device_id *ent)
goto err;
}
+ if (ocxlpmem_sysfs_add(ocxlpmem)) {
+ dev_err(&pdev->dev, "Could not create sysfs entries\n");
+ goto err;
+ }
+
elapsed = 0;
timeout = ocxlpmem->readiness_timeout + ocxlpmem->memory_available_timeout;
while (!is_usable(ocxlpmem, false)) {
diff --git a/arch/powerpc/platforms/powernv/pmem/ocxl_internal.h b/arch/powerpc/platforms/powernv/pmem/ocxl_internal.h
index 0eb7a35d24ae..12304ceace61 100644
--- a/arch/powerpc/platforms/powernv/pmem/ocxl_internal.h
+++ b/arch/powerpc/platforms/powernv/pmem/ocxl_internal.h
@@ -246,3 +246,9 @@ int ns_response_handled(const struct ocxlpmem *ocxlpmem);
*/
void warn_status(const struct ocxlpmem *ocxlpmem, const char *message,
u8 status);
+
+/**
+ * ocxlpmem_sysfs_add() - Create sysfs entries for an OpenCAPI persistent memory device
+ * @ocxlpmem: the device metadata
+ */
+int ocxlpmem_sysfs_add(struct ocxlpmem *ocxlpmem);
diff --git a/arch/powerpc/platforms/powernv/pmem/ocxl_sysfs.c b/arch/powerpc/platforms/powernv/pmem/ocxl_sysfs.c
new file mode 100644
index 000000000000..7829e4bc887d
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/pmem/ocxl_sysfs.c
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright 2018 IBM Corp.
+
+#include <linux/sysfs.h>
+#include <linux/capability.h>
+#include <linux/limits.h>
+#include <linux/firmware.h>
+#include "ocxl_internal.h"
+
+static ssize_t serial_show(struct device *device, struct device_attribute *attr,
+ char *buf)
+{
+ struct ocxlpmem *ocxlpmem = container_of(device, struct ocxlpmem, dev);
+ const struct ocxl_fn_config *fn_config = ocxl_function_config(ocxlpmem->ocxl_fn);
+
+ return scnprintf(buf, PAGE_SIZE, "%llu\n", fn_config->serial);
+}
+
+static struct device_attribute attrs[] = {
+ __ATTR_RO(serial),
+};
+
+int ocxlpmem_sysfs_add(struct ocxlpmem *ocxlpmem)
+{
+ int i, rc;
+
+ for (i = 0; i < ARRAY_SIZE(attrs); i++) {
+ rc = device_create_file(&ocxlpmem->dev, &attrs[i]);
+ if (rc) {
+ for (; --i >= 0;)
+ device_remove_file(&ocxlpmem->dev, &attrs[i]);
+
+ return rc;
+ }
+ }
+ return 0;
+}
--
2.24.1
^ permalink raw reply related
* [PATCH v3 22/27] powerpc/powernv/pmem: Implement the heartbeat command
From: Alastair D'Silva @ 2020-02-21 3:27 UTC (permalink / raw)
To: alastair
Cc: Madhavan Srinivasan, Alexey Kardashevskiy, Masahiro Yamada,
Oliver O'Halloran, Mauro Carvalho Chehab, Ira Weiny,
Thomas Gleixner, Rob Herring, Dave Jiang, linux-nvdimm,
Aneesh Kumar K . V, Krzysztof Kozlowski, Anju T Sudhakar,
Mahesh Salgaonkar, Andrew Donnellan, Arnd Bergmann, Greg Kurz,
Nicholas Piggin, Cédric Le Goater, Dan Williams,
Hari Bathini, linux-mm, Greg Kroah-Hartman, linux-kernel,
Vishal Verma, Frederic Barrat, Paul Mackerras, Andrew Morton,
linuxppc-dev, David S. Miller
In-Reply-To: <20200221032720.33893-1-alastair@au1.ibm.com>
From: Alastair D'Silva <alastair@d-silva.org>
The heartbeat admin command is a simple admin command that exercises
the communication mechanisms within the controller.
This patch issues a heartbeat command to the card during init to ensure
we can communicate with the card's controller.
Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
---
arch/powerpc/platforms/powernv/pmem/ocxl.c | 43 ++++++++++++++++++++++
1 file changed, 43 insertions(+)
diff --git a/arch/powerpc/platforms/powernv/pmem/ocxl.c b/arch/powerpc/platforms/powernv/pmem/ocxl.c
index 081883a8247a..e01f6f9fc180 100644
--- a/arch/powerpc/platforms/powernv/pmem/ocxl.c
+++ b/arch/powerpc/platforms/powernv/pmem/ocxl.c
@@ -306,6 +306,44 @@ static bool is_usable(const struct ocxlpmem *ocxlpmem, bool verbose)
return true;
}
+/**
+ * heartbeat() - Issue a heartbeat command to the controller
+ * @ocxlpmem: the device metadata
+ * Return: 0 if the controller responded correctly, negative on error
+ */
+static int heartbeat(struct ocxlpmem *ocxlpmem)
+{
+ int rc;
+
+ mutex_lock(&ocxlpmem->admin_command.lock);
+
+ rc = admin_command_request(ocxlpmem, ADMIN_COMMAND_HEARTBEAT);
+ if (rc)
+ goto out;
+
+ rc = admin_command_execute(ocxlpmem);
+ if (rc)
+ goto out;
+
+ rc = admin_command_complete_timeout(ocxlpmem, ADMIN_COMMAND_HEARTBEAT);
+ if (rc < 0) {
+ dev_err(&ocxlpmem->dev, "Heartbeat timeout\n");
+ goto out;
+ }
+
+ rc = admin_response(ocxlpmem);
+ if (rc < 0)
+ goto out;
+ if (rc != STATUS_SUCCESS)
+ warn_status(ocxlpmem, "Unexpected status from heartbeat", rc);
+
+ (void)admin_response_handled(ocxlpmem);
+
+out:
+ mutex_unlock(&ocxlpmem->admin_command.lock);
+ return rc;
+}
+
/**
* allocate_minor() - Allocate a minor number to use for an OpenCAPI pmem device
* @ocxlpmem: the device metadata
@@ -1458,6 +1496,11 @@ static int probe(struct pci_dev *pdev, const struct pci_device_id *ent)
goto err;
}
+ if (heartbeat(ocxlpmem)) {
+ dev_err(&pdev->dev, "Heartbeat failed\n");
+ goto err;
+ }
+
elapsed = 0;
timeout = ocxlpmem->readiness_timeout + ocxlpmem->memory_available_timeout;
while (!is_usable(ocxlpmem, false)) {
--
2.24.1
^ permalink raw reply related
* [PATCH v3 19/27] powerpc/powernv/pmem: Add an IOCTL to report controller statistics
From: Alastair D'Silva @ 2020-02-21 3:27 UTC (permalink / raw)
To: alastair
Cc: Madhavan Srinivasan, Alexey Kardashevskiy, Masahiro Yamada,
Oliver O'Halloran, Mauro Carvalho Chehab, Ira Weiny,
Thomas Gleixner, Rob Herring, Dave Jiang, linux-nvdimm,
Aneesh Kumar K . V, Krzysztof Kozlowski, Anju T Sudhakar,
Mahesh Salgaonkar, Andrew Donnellan, Arnd Bergmann, Greg Kurz,
Nicholas Piggin, Cédric Le Goater, Dan Williams,
Hari Bathini, linux-mm, Greg Kroah-Hartman, linux-kernel,
Vishal Verma, Frederic Barrat, Paul Mackerras, Andrew Morton,
linuxppc-dev, David S. Miller
In-Reply-To: <20200221032720.33893-1-alastair@au1.ibm.com>
From: Alastair D'Silva <alastair@d-silva.org>
The controller can report a number of statistics that are useful
in evaluating the performance and reliability of the card.
This patch exposes this information via an IOCTL.
Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
---
arch/powerpc/platforms/powernv/pmem/ocxl.c | 185 +++++++++++++++++++++
include/uapi/nvdimm/ocxl-pmem.h | 17 ++
2 files changed, 202 insertions(+)
diff --git a/arch/powerpc/platforms/powernv/pmem/ocxl.c b/arch/powerpc/platforms/powernv/pmem/ocxl.c
index 2cabafe1fc58..009d4fd29e7d 100644
--- a/arch/powerpc/platforms/powernv/pmem/ocxl.c
+++ b/arch/powerpc/platforms/powernv/pmem/ocxl.c
@@ -758,6 +758,186 @@ static int ioctl_controller_dump_complete(struct ocxlpmem *ocxlpmem)
GLOBAL_MMIO_HCI_CONTROLLER_DUMP_COLLECTED);
}
+/**
+ * controller_stats_header_parse() - Parse the first 64 bits of the controller stats admin command response
+ * @ocxlpmem: the device metadata
+ * @length: out, returns the number of bytes in the response (excluding the 64 bit header)
+ */
+static int controller_stats_header_parse(struct ocxlpmem *ocxlpmem,
+ u32 *length)
+{
+ int rc;
+ u64 val;
+
+ u16 data_identifier;
+ u32 data_length;
+
+ rc = ocxl_global_mmio_read64(ocxlpmem->ocxl_afu,
+ ocxlpmem->admin_command.data_offset,
+ OCXL_LITTLE_ENDIAN, &val);
+ if (rc)
+ return rc;
+
+ data_identifier = val >> 48;
+ data_length = val & 0xFFFFFFFF;
+
+ if (data_identifier != 0x4353) { // 'CS'
+ dev_err(&ocxlpmem->dev,
+ "Bad data identifier for controller stats, expected 'CS', got '%-.*s'\n",
+ 2, (char *)&data_identifier);
+ return -EINVAL;
+ }
+
+ *length = data_length;
+ return 0;
+}
+
+static int ioctl_controller_stats(struct ocxlpmem *ocxlpmem,
+ struct ioctl_ocxl_pmem_controller_stats __user *uarg)
+{
+ struct ioctl_ocxl_pmem_controller_stats args;
+ u32 length;
+ int rc;
+ u64 val;
+
+ memset(&args, '\0', sizeof(args));
+
+ mutex_lock(&ocxlpmem->admin_command.lock);
+
+ rc = admin_command_request(ocxlpmem, ADMIN_COMMAND_CONTROLLER_STATS);
+ if (rc)
+ goto out;
+
+ rc = ocxl_global_mmio_write64(ocxlpmem->ocxl_afu,
+ ocxlpmem->admin_command.request_offset + 0x08,
+ OCXL_LITTLE_ENDIAN, 0);
+ if (rc)
+ goto out;
+
+ rc = admin_command_execute(ocxlpmem);
+ if (rc)
+ goto out;
+
+
+ rc = admin_command_complete_timeout(ocxlpmem,
+ ADMIN_COMMAND_CONTROLLER_STATS);
+ if (rc < 0) {
+ dev_warn(&ocxlpmem->dev, "Controller stats timed out\n");
+ goto out;
+ }
+
+ rc = admin_response(ocxlpmem);
+ if (rc < 0)
+ goto out;
+ if (rc != STATUS_SUCCESS) {
+ warn_status(ocxlpmem,
+ "Unexpected status from controller stats", rc);
+ goto out;
+ }
+
+ rc = controller_stats_header_parse(ocxlpmem, &length);
+ if (rc)
+ goto out;
+
+ if (length != 0x140)
+ warn_status(ocxlpmem,
+ "Unexpected length for controller stats data, expected 0x140, got 0x%x",
+ length);
+
+ rc = ocxl_global_mmio_read64(ocxlpmem->ocxl_afu,
+ ocxlpmem->admin_command.data_offset + 0x08 + 0x08,
+ OCXL_LITTLE_ENDIAN, &val);
+ if (rc)
+ goto out;
+
+ args.reset_count = val >> 32;
+ args.reset_uptime = val & 0xFFFFFFFF;
+
+ rc = ocxl_global_mmio_read64(ocxlpmem->ocxl_afu,
+ ocxlpmem->admin_command.data_offset + 0x08 + 0x10,
+ OCXL_LITTLE_ENDIAN, &val);
+ if (rc)
+ goto out;
+
+ args.power_on_uptime = val >> 32;
+
+ rc = ocxl_global_mmio_read64(ocxlpmem->ocxl_afu,
+ ocxlpmem->admin_command.data_offset + 0x08 + 0x40 + 0x08,
+ OCXL_LITTLE_ENDIAN, &args.host_load_count);
+ if (rc)
+ goto out;
+
+ rc = ocxl_global_mmio_read64(ocxlpmem->ocxl_afu,
+ ocxlpmem->admin_command.data_offset + 0x08 + 0x40 + 0x10,
+ OCXL_LITTLE_ENDIAN, &args.host_store_count);
+ if (rc)
+ goto out;
+
+ rc = ocxl_global_mmio_read64(ocxlpmem->ocxl_afu,
+ ocxlpmem->admin_command.data_offset + 0x08 + 0x40 + 0x18,
+ OCXL_LITTLE_ENDIAN, &args.media_read_count);
+ if (rc)
+ goto out;
+
+ rc = ocxl_global_mmio_read64(ocxlpmem->ocxl_afu,
+ ocxlpmem->admin_command.data_offset + 0x08 + 0x40 + 0x20,
+ OCXL_LITTLE_ENDIAN, &args.media_write_count);
+ if (rc)
+ goto out;
+
+ rc = ocxl_global_mmio_read64(ocxlpmem->ocxl_afu,
+ ocxlpmem->admin_command.data_offset + 0x08 + 0x40 + 0x28,
+ OCXL_LITTLE_ENDIAN, &args.cache_hit_count);
+ if (rc)
+ goto out;
+
+ rc = ocxl_global_mmio_read64(ocxlpmem->ocxl_afu,
+ ocxlpmem->admin_command.data_offset + 0x08 + 0x40 + 0x30,
+ OCXL_LITTLE_ENDIAN, &args.cache_miss_count);
+ if (rc)
+ goto out;
+
+ rc = ocxl_global_mmio_read64(ocxlpmem->ocxl_afu,
+ ocxlpmem->admin_command.data_offset + 0x08 + 0x40 + 0x38,
+ OCXL_LITTLE_ENDIAN, &args.media_read_latency);
+ if (rc)
+ goto out;
+
+ rc = ocxl_global_mmio_read64(ocxlpmem->ocxl_afu,
+ ocxlpmem->admin_command.data_offset + 0x08 + 0x40 + 0x40,
+ OCXL_LITTLE_ENDIAN, &args.media_write_latency);
+ if (rc)
+ goto out;
+
+ rc = ocxl_global_mmio_read64(ocxlpmem->ocxl_afu,
+ ocxlpmem->admin_command.data_offset + 0x08 + 0x40 + 0x48,
+ OCXL_LITTLE_ENDIAN, &args.cache_read_latency);
+ if (rc)
+ goto out;
+
+ rc = ocxl_global_mmio_read64(ocxlpmem->ocxl_afu,
+ ocxlpmem->admin_command.data_offset + 0x08 + 0x40 + 0x50,
+ OCXL_LITTLE_ENDIAN, &args.cache_write_latency);
+ if (rc)
+ goto out;
+
+ if (copy_to_user(uarg, &args, sizeof(args))) {
+ rc = -EFAULT;
+ goto out;
+ }
+
+ rc = admin_response_handled(ocxlpmem);
+ if (rc)
+ goto out;
+
+ rc = 0;
+ goto out;
+
+out:
+ mutex_unlock(&ocxlpmem->admin_command.lock);
+ return rc;
+}
+
static long file_ioctl(struct file *file, unsigned int cmd, unsigned long args)
{
struct ocxlpmem *ocxlpmem = file->private_data;
@@ -781,6 +961,11 @@ static long file_ioctl(struct file *file, unsigned int cmd, unsigned long args)
case IOCTL_OCXL_PMEM_CONTROLLER_DUMP_COMPLETE:
rc = ioctl_controller_dump_complete(ocxlpmem);
break;
+
+ case IOCTL_OCXL_PMEM_CONTROLLER_STATS:
+ rc = ioctl_controller_stats(ocxlpmem,
+ (struct ioctl_ocxl_pmem_controller_stats __user *)args);
+ break;
}
return rc;
diff --git a/include/uapi/nvdimm/ocxl-pmem.h b/include/uapi/nvdimm/ocxl-pmem.h
index d4d8512d03f7..add223aa2fdb 100644
--- a/include/uapi/nvdimm/ocxl-pmem.h
+++ b/include/uapi/nvdimm/ocxl-pmem.h
@@ -50,6 +50,22 @@ struct ioctl_ocxl_pmem_controller_dump_data {
__u64 reserved[8];
};
+struct ioctl_ocxl_pmem_controller_stats {
+ __u32 reset_count;
+ __u32 reset_uptime; /* seconds */
+ __u32 power_on_uptime; /* seconds */
+ __u64 host_load_count;
+ __u64 host_store_count;
+ __u64 media_read_count;
+ __u64 media_write_count;
+ __u64 cache_hit_count;
+ __u64 cache_miss_count;
+ __u64 media_read_latency; /* nanoseconds */
+ __u64 media_write_latency; /* nanoseconds */
+ __u64 cache_read_latency; /* nanoseconds */
+ __u64 cache_write_latency; /* nanoseconds */
+};
+
/* ioctl numbers */
#define OCXL_PMEM_MAGIC 0x5C
/* SCM devices */
@@ -57,5 +73,6 @@ struct ioctl_ocxl_pmem_controller_dump_data {
#define IOCTL_OCXL_PMEM_CONTROLLER_DUMP _IO(OCXL_PMEM_MAGIC, 0x02)
#define IOCTL_OCXL_PMEM_CONTROLLER_DUMP_DATA _IOWR(OCXL_PMEM_MAGIC, 0x03, struct ioctl_ocxl_pmem_controller_dump_data)
#define IOCTL_OCXL_PMEM_CONTROLLER_DUMP_COMPLETE _IO(OCXL_PMEM_MAGIC, 0x04)
+#define IOCTL_OCXL_PMEM_CONTROLLER_STATS _IO(OCXL_PMEM_MAGIC, 0x05)
#endif /* _UAPI_OCXL_SCM_H */
--
2.24.1
^ permalink raw reply related
* [PATCH v3 21/27] powerpc/powernv/pmem: Add an IOCTL to request controller health & perf data
From: Alastair D'Silva @ 2020-02-21 3:27 UTC (permalink / raw)
To: alastair
Cc: Madhavan Srinivasan, Alexey Kardashevskiy, Masahiro Yamada,
Oliver O'Halloran, Mauro Carvalho Chehab, Ira Weiny,
Thomas Gleixner, Rob Herring, Dave Jiang, linux-nvdimm,
Aneesh Kumar K . V, Krzysztof Kozlowski, Anju T Sudhakar,
Mahesh Salgaonkar, Andrew Donnellan, Arnd Bergmann, Greg Kurz,
Nicholas Piggin, Cédric Le Goater, Dan Williams,
Hari Bathini, linux-mm, Greg Kroah-Hartman, linux-kernel,
Vishal Verma, Frederic Barrat, Paul Mackerras, Andrew Morton,
linuxppc-dev, David S. Miller
In-Reply-To: <20200221032720.33893-1-alastair@au1.ibm.com>
From: Alastair D'Silva <alastair@d-silva.org>
When health & performance data is requested from the controller,
it responds with an error log containing the requested information.
This patch allows the request to me issued via an IOCTL.
Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
---
arch/powerpc/platforms/powernv/pmem/ocxl.c | 16 ++++++++++++++++
include/uapi/nvdimm/ocxl-pmem.h | 1 +
2 files changed, 17 insertions(+)
diff --git a/arch/powerpc/platforms/powernv/pmem/ocxl.c b/arch/powerpc/platforms/powernv/pmem/ocxl.c
index e46696d3cc36..081883a8247a 100644
--- a/arch/powerpc/platforms/powernv/pmem/ocxl.c
+++ b/arch/powerpc/platforms/powernv/pmem/ocxl.c
@@ -1000,6 +1000,18 @@ static int ioctl_event_check(struct ocxlpmem *ocxlpmem, u64 __user *uarg)
return rc;
}
+/**
+ * req_controller_health_perf() - Request controller health & performance data
+ * @ocxlpmem: the device metadata
+ * Return: 0 on success, negative on failure
+ */
+int req_controller_health_perf(struct ocxlpmem *ocxlpmem)
+{
+ return ocxl_global_mmio_set64(ocxlpmem->ocxl_afu, GLOBAL_MMIO_HCI,
+ OCXL_LITTLE_ENDIAN,
+ GLOBAL_MMIO_HCI_REQ_HEALTH_PERF);
+}
+
static long file_ioctl(struct file *file, unsigned int cmd, unsigned long args)
{
struct ocxlpmem *ocxlpmem = file->private_data;
@@ -1037,6 +1049,10 @@ static long file_ioctl(struct file *file, unsigned int cmd, unsigned long args)
case IOCTL_OCXL_PMEM_EVENT_CHECK:
rc = ioctl_event_check(ocxlpmem, (u64 __user *)args);
break;
+
+ case IOCTL_OCXL_PMEM_REQUEST_HEALTH:
+ rc = req_controller_health_perf(ocxlpmem);
+ break;
}
return rc;
diff --git a/include/uapi/nvdimm/ocxl-pmem.h b/include/uapi/nvdimm/ocxl-pmem.h
index 988eb0bc413d..0d03abb44001 100644
--- a/include/uapi/nvdimm/ocxl-pmem.h
+++ b/include/uapi/nvdimm/ocxl-pmem.h
@@ -90,5 +90,6 @@ struct ioctl_ocxl_pmem_eventfd {
#define IOCTL_OCXL_PMEM_CONTROLLER_STATS _IO(OCXL_PMEM_MAGIC, 0x05)
#define IOCTL_OCXL_PMEM_EVENTFD _IOW(OCXL_PMEM_MAGIC, 0x06, struct ioctl_ocxl_pmem_eventfd)
#define IOCTL_OCXL_PMEM_EVENT_CHECK _IOR(OCXL_PMEM_MAGIC, 0x07, __u64)
+#define IOCTL_OCXL_PMEM_REQUEST_HEALTH _IO(OCXL_PMEM_MAGIC, 0x08)
#endif /* _UAPI_OCXL_SCM_H */
--
2.24.1
^ permalink raw reply related
* [PATCH v3 12/27] powerpc/powernv/pmem: Add register addresses & status values to the header
From: Alastair D'Silva @ 2020-02-21 3:27 UTC (permalink / raw)
To: alastair
Cc: Madhavan Srinivasan, Alexey Kardashevskiy, Masahiro Yamada,
Oliver O'Halloran, Mauro Carvalho Chehab, Ira Weiny,
Thomas Gleixner, Rob Herring, Dave Jiang, linux-nvdimm,
Aneesh Kumar K . V, Krzysztof Kozlowski, Anju T Sudhakar,
Mahesh Salgaonkar, Andrew Donnellan, Arnd Bergmann, Greg Kurz,
Nicholas Piggin, Cédric Le Goater, Dan Williams,
Hari Bathini, linux-mm, Greg Kroah-Hartman, linux-kernel,
Vishal Verma, Frederic Barrat, Paul Mackerras, Andrew Morton,
linuxppc-dev, David S. Miller
In-Reply-To: <20200221032720.33893-1-alastair@au1.ibm.com>
From: Alastair D'Silva <alastair@d-silva.org>
These values have been taken from the device specifications.
Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
---
.../platforms/powernv/pmem/ocxl_internal.h | 72 +++++++++++++++++++
1 file changed, 72 insertions(+)
diff --git a/arch/powerpc/platforms/powernv/pmem/ocxl_internal.h b/arch/powerpc/platforms/powernv/pmem/ocxl_internal.h
index 0faf3740e9b8..9cf3e42750e7 100644
--- a/arch/powerpc/platforms/powernv/pmem/ocxl_internal.h
+++ b/arch/powerpc/platforms/powernv/pmem/ocxl_internal.h
@@ -8,6 +8,78 @@
#define LABEL_AREA_SIZE (1UL << PA_SECTION_SHIFT)
+#define GLOBAL_MMIO_CHI 0x000
+#define GLOBAL_MMIO_CHIC 0x008
+#define GLOBAL_MMIO_CHIE 0x010
+#define GLOBAL_MMIO_CHIEC 0x018
+#define GLOBAL_MMIO_HCI 0x020
+#define GLOBAL_MMIO_HCIC 0x028
+#define GLOBAL_MMIO_IMA0_OHP 0x040
+#define GLOBAL_MMIO_IMA0_CFP 0x048
+#define GLOBAL_MMIO_IMA1_OHP 0x050
+#define GLOBAL_MMIO_IMA1_CFP 0x058
+#define GLOBAL_MMIO_ACMA_CREQO 0x100
+#define GLOBAL_MMIO_ACMA_CRSPO 0x104
+#define GLOBAL_MMIO_ACMA_CDBO 0x108
+#define GLOBAL_MMIO_ACMA_CDBS 0x10c
+#define GLOBAL_MMIO_NSCMA_CREQO 0x120
+#define GLOBAL_MMIO_NSCMA_CRSPO 0x124
+#define GLOBAL_MMIO_NSCMA_CDBO 0x128
+#define GLOBAL_MMIO_NSCMA_CDBS 0x12c
+#define GLOBAL_MMIO_CSTS 0x140
+#define GLOBAL_MMIO_FWVER 0x148
+#define GLOBAL_MMIO_CCAP0 0x160
+#define GLOBAL_MMIO_CCAP1 0x168
+
+#define GLOBAL_MMIO_CHI_ACRA BIT_ULL(0)
+#define GLOBAL_MMIO_CHI_NSCRA BIT_ULL(1)
+#define GLOBAL_MMIO_CHI_CRDY BIT_ULL(4)
+#define GLOBAL_MMIO_CHI_CFFS BIT_ULL(5)
+#define GLOBAL_MMIO_CHI_MA BIT_ULL(6)
+#define GLOBAL_MMIO_CHI_ELA BIT_ULL(7)
+#define GLOBAL_MMIO_CHI_CDA BIT_ULL(8)
+#define GLOBAL_MMIO_CHI_CHFS BIT_ULL(9)
+
+#define GLOBAL_MMIO_CHI_ALL (GLOBAL_MMIO_CHI_ACRA | \
+ GLOBAL_MMIO_CHI_NSCRA | \
+ GLOBAL_MMIO_CHI_CRDY | \
+ GLOBAL_MMIO_CHI_CFFS | \
+ GLOBAL_MMIO_CHI_MA | \
+ GLOBAL_MMIO_CHI_ELA | \
+ GLOBAL_MMIO_CHI_CDA | \
+ GLOBAL_MMIO_CHI_CHFS)
+
+#define GLOBAL_MMIO_HCI_ACRW BIT_ULL(0)
+#define GLOBAL_MMIO_HCI_NSCRW BIT_ULL(1)
+#define GLOBAL_MMIO_HCI_AFU_RESET BIT_ULL(2)
+#define GLOBAL_MMIO_HCI_FW_DEBUG BIT_ULL(3)
+#define GLOBAL_MMIO_HCI_CONTROLLER_DUMP BIT_ULL(4)
+#define GLOBAL_MMIO_HCI_CONTROLLER_DUMP_COLLECTED BIT_ULL(5)
+#define GLOBAL_MMIO_HCI_REQ_HEALTH_PERF BIT_ULL(6)
+
+#define ADMIN_COMMAND_HEARTBEAT 0x00u
+#define ADMIN_COMMAND_SHUTDOWN 0x01u
+#define ADMIN_COMMAND_FW_UPDATE 0x02u
+#define ADMIN_COMMAND_FW_DEBUG 0x03u
+#define ADMIN_COMMAND_ERRLOG 0x04u
+#define ADMIN_COMMAND_SMART 0x05u
+#define ADMIN_COMMAND_CONTROLLER_STATS 0x06u
+#define ADMIN_COMMAND_CONTROLLER_DUMP 0x07u
+#define ADMIN_COMMAND_CMD_CAPS 0x08u
+#define ADMIN_COMMAND_MAX 0x08u
+
+#define STATUS_SUCCESS 0x00
+#define STATUS_MEM_UNAVAILABLE 0x20
+#define STATUS_BAD_OPCODE 0x50
+#define STATUS_BAD_REQUEST_PARM 0x51
+#define STATUS_BAD_DATA_PARM 0x52
+#define STATUS_DEBUG_BLOCKED 0x70
+#define STATUS_FAIL 0xFF
+
+#define STATUS_FW_UPDATE_BLOCKED 0x21
+#define STATUS_FW_ARG_INVALID 0x51
+#define STATUS_FW_INVALID 0x52
+
struct ocxlpmem_function0 {
struct pci_dev *pdev;
struct ocxl_fn *ocxl_fn;
--
2.24.1
^ permalink raw reply related
* [PATCH v3 16/27] powerpc/powernv/pmem: Register a character device for userspace to interact with
From: Alastair D'Silva @ 2020-02-21 3:27 UTC (permalink / raw)
To: alastair
Cc: Madhavan Srinivasan, Alexey Kardashevskiy, Masahiro Yamada,
Oliver O'Halloran, Mauro Carvalho Chehab, Ira Weiny,
Thomas Gleixner, Rob Herring, Dave Jiang, linux-nvdimm,
Aneesh Kumar K . V, Krzysztof Kozlowski, Anju T Sudhakar,
Mahesh Salgaonkar, Andrew Donnellan, Arnd Bergmann, Greg Kurz,
Nicholas Piggin, Cédric Le Goater, Dan Williams,
Hari Bathini, linux-mm, Greg Kroah-Hartman, linux-kernel,
Vishal Verma, Frederic Barrat, Paul Mackerras, Andrew Morton,
linuxppc-dev, David S. Miller
In-Reply-To: <20200221032720.33893-1-alastair@au1.ibm.com>
From: Alastair D'Silva <alastair@d-silva.org>
This patch introduces a character device (/dev/ocxl-scmX) which further
patches will use to interact with userspace.
Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
---
arch/powerpc/platforms/powernv/pmem/ocxl.c | 116 +++++++++++++++++-
.../platforms/powernv/pmem/ocxl_internal.h | 2 +
2 files changed, 116 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/platforms/powernv/pmem/ocxl.c b/arch/powerpc/platforms/powernv/pmem/ocxl.c
index b8bd7e703b19..63109a870d2c 100644
--- a/arch/powerpc/platforms/powernv/pmem/ocxl.c
+++ b/arch/powerpc/platforms/powernv/pmem/ocxl.c
@@ -10,6 +10,7 @@
#include <misc/ocxl.h>
#include <linux/delay.h>
#include <linux/ndctl.h>
+#include <linux/fs.h>
#include <linux/mm_types.h>
#include <linux/memory_hotplug.h>
#include "ocxl_internal.h"
@@ -339,6 +340,9 @@ static void free_ocxlpmem(struct ocxlpmem *ocxlpmem)
free_minor(ocxlpmem);
+ if (ocxlpmem->cdev.owner)
+ cdev_del(&ocxlpmem->cdev);
+
if (ocxlpmem->metadata_addr)
devm_memunmap(&ocxlpmem->dev, ocxlpmem->metadata_addr);
@@ -396,6 +400,70 @@ static int ocxlpmem_register(struct ocxlpmem *ocxlpmem)
return device_register(&ocxlpmem->dev);
}
+static void ocxlpmem_put(struct ocxlpmem *ocxlpmem)
+{
+ put_device(&ocxlpmem->dev);
+}
+
+static struct ocxlpmem *ocxlpmem_get(struct ocxlpmem *ocxlpmem)
+{
+ return (get_device(&ocxlpmem->dev) == NULL) ? NULL : ocxlpmem;
+}
+
+static struct ocxlpmem *find_and_get_ocxlpmem(dev_t devno)
+{
+ struct ocxlpmem *ocxlpmem;
+ int minor = MINOR(devno);
+ /*
+ * We don't declare an RCU critical section here, as our AFU
+ * is protected by a reference counter on the device. By the time the
+ * minor number of a device is removed from the idr, the ref count of
+ * the device is already at 0, so no user API will access that AFU and
+ * this function can't return it.
+ */
+ ocxlpmem = idr_find(&minors_idr, minor);
+ if (ocxlpmem)
+ ocxlpmem_get(ocxlpmem);
+ return ocxlpmem;
+}
+
+static int file_open(struct inode *inode, struct file *file)
+{
+ struct ocxlpmem *ocxlpmem;
+
+ ocxlpmem = find_and_get_ocxlpmem(inode->i_rdev);
+ if (!ocxlpmem)
+ return -ENODEV;
+
+ file->private_data = ocxlpmem;
+ return 0;
+}
+
+static int file_release(struct inode *inode, struct file *file)
+{
+ struct ocxlpmem *ocxlpmem = file->private_data;
+
+ ocxlpmem_put(ocxlpmem);
+ return 0;
+}
+
+static const struct file_operations fops = {
+ .owner = THIS_MODULE,
+ .open = file_open,
+ .release = file_release,
+};
+
+/**
+ * create_cdev() - Create the chardev in /dev for the device
+ * @ocxlpmem: the SCM metadata
+ * Return: 0 on success, negative on failure
+ */
+static int create_cdev(struct ocxlpmem *ocxlpmem)
+{
+ cdev_init(&ocxlpmem->cdev, &fops);
+ return cdev_add(&ocxlpmem->cdev, ocxlpmem->dev.devt, 1);
+}
+
/**
* ocxlpmem_remove() - Free an OpenCAPI persistent memory device
* @pdev: the PCI device information struct
@@ -572,6 +640,11 @@ static int probe(struct pci_dev *pdev, const struct pci_device_id *ent)
goto err;
}
+ if (create_cdev(ocxlpmem)) {
+ dev_err(&pdev->dev, "Could not create character device\n");
+ goto err;
+ }
+
elapsed = 0;
timeout = ocxlpmem->readiness_timeout + ocxlpmem->memory_available_timeout;
while (!is_usable(ocxlpmem, false)) {
@@ -613,20 +686,59 @@ static struct pci_driver pci_driver = {
.shutdown = ocxlpmem_remove,
};
+static int file_init(void)
+{
+ int rc;
+
+ mutex_init(&minors_idr_lock);
+ idr_init(&minors_idr);
+
+ rc = alloc_chrdev_region(&ocxlpmem_dev, 0, NUM_MINORS, "ocxl-pmem");
+ if (rc) {
+ idr_destroy(&minors_idr);
+ pr_err("Unable to allocate OpenCAPI persistent memory major number: %d\n", rc);
+ return rc;
+ }
+
+ ocxlpmem_class = class_create(THIS_MODULE, "ocxl-pmem");
+ if (IS_ERR(ocxlpmem_class)) {
+ idr_destroy(&minors_idr);
+ pr_err("Unable to create ocxl-pmem class\n");
+ unregister_chrdev_region(ocxlpmem_dev, NUM_MINORS);
+ return PTR_ERR(ocxlpmem_class);
+ }
+
+ return 0;
+}
+
+static void file_exit(void)
+{
+ class_destroy(ocxlpmem_class);
+ unregister_chrdev_region(ocxlpmem_dev, NUM_MINORS);
+ idr_destroy(&minors_idr);
+}
+
static int __init ocxlpmem_init(void)
{
- int rc = 0;
+ int rc;
- rc = pci_register_driver(&pci_driver);
+ rc = file_init();
if (rc)
return rc;
+ rc = pci_register_driver(&pci_driver);
+ if (rc) {
+ file_exit();
+ return rc;
+ }
+
return 0;
}
static void ocxlpmem_exit(void)
{
pci_unregister_driver(&pci_driver);
+ file_exit();
}
module_init(ocxlpmem_init);
diff --git a/arch/powerpc/platforms/powernv/pmem/ocxl_internal.h b/arch/powerpc/platforms/powernv/pmem/ocxl_internal.h
index 28e2020f6355..d2d81fec7bb1 100644
--- a/arch/powerpc/platforms/powernv/pmem/ocxl_internal.h
+++ b/arch/powerpc/platforms/powernv/pmem/ocxl_internal.h
@@ -2,6 +2,7 @@
// Copyright 2019 IBM Corp.
#include <linux/pci.h>
+#include <linux/cdev.h>
#include <misc/ocxl.h>
#include <linux/libnvdimm.h>
#include <linux/mm.h>
@@ -99,6 +100,7 @@ struct ocxlpmem_function0 {
struct ocxlpmem {
struct device dev;
struct pci_dev *pdev;
+ struct cdev cdev;
struct ocxl_fn *ocxl_fn;
struct nd_interleave_set nd_set;
struct nvdimm_bus_descriptor bus_desc;
--
2.24.1
^ permalink raw reply related
* [PATCH v3 04/27] ocxl: Remove unnecessary externs
From: Alastair D'Silva @ 2020-02-21 3:26 UTC (permalink / raw)
To: alastair
Cc: Madhavan Srinivasan, Alexey Kardashevskiy, Masahiro Yamada,
Oliver O'Halloran, Mauro Carvalho Chehab, Ira Weiny,
Thomas Gleixner, Rob Herring, Dave Jiang, linux-nvdimm,
Aneesh Kumar K . V, Krzysztof Kozlowski, Anju T Sudhakar,
Mahesh Salgaonkar, Andrew Donnellan, Arnd Bergmann, Greg Kurz,
Nicholas Piggin, Cédric Le Goater, Dan Williams,
Hari Bathini, linux-mm, Greg Kroah-Hartman, linux-kernel,
Vishal Verma, Frederic Barrat, Paul Mackerras, Andrew Morton,
linuxppc-dev, David S. Miller
In-Reply-To: <20200221032720.33893-1-alastair@au1.ibm.com>
From: Alastair D'Silva <alastair@d-silva.org>
Function declarations don't need externs, remove the existing ones
so they are consistent with newer code
Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
---
arch/powerpc/include/asm/pnv-ocxl.h | 32 ++++++++++++++---------------
include/misc/ocxl.h | 6 +++---
2 files changed, 18 insertions(+), 20 deletions(-)
diff --git a/arch/powerpc/include/asm/pnv-ocxl.h b/arch/powerpc/include/asm/pnv-ocxl.h
index 0b2a6707e555..b23c99bc0c84 100644
--- a/arch/powerpc/include/asm/pnv-ocxl.h
+++ b/arch/powerpc/include/asm/pnv-ocxl.h
@@ -9,29 +9,27 @@
#define PNV_OCXL_TL_BITS_PER_RATE 4
#define PNV_OCXL_TL_RATE_BUF_SIZE ((PNV_OCXL_TL_MAX_TEMPLATE+1) * PNV_OCXL_TL_BITS_PER_RATE / 8)
-extern int pnv_ocxl_get_actag(struct pci_dev *dev, u16 *base, u16 *enabled,
- u16 *supported);
-extern int pnv_ocxl_get_pasid_count(struct pci_dev *dev, int *count);
+int pnv_ocxl_get_actag(struct pci_dev *dev, u16 *base, u16 *enabled, u16 *supported);
+int pnv_ocxl_get_pasid_count(struct pci_dev *dev, int *count);
-extern int pnv_ocxl_get_tl_cap(struct pci_dev *dev, long *cap,
+int pnv_ocxl_get_tl_cap(struct pci_dev *dev, long *cap,
char *rate_buf, int rate_buf_size);
-extern int pnv_ocxl_set_tl_conf(struct pci_dev *dev, long cap,
+int pnv_ocxl_set_tl_conf(struct pci_dev *dev, long cap,
uint64_t rate_buf_phys, int rate_buf_size);
-extern int pnv_ocxl_get_xsl_irq(struct pci_dev *dev, int *hwirq);
-extern void pnv_ocxl_unmap_xsl_regs(void __iomem *dsisr, void __iomem *dar,
- void __iomem *tfc, void __iomem *pe_handle);
-extern int pnv_ocxl_map_xsl_regs(struct pci_dev *dev, void __iomem **dsisr,
- void __iomem **dar, void __iomem **tfc,
- void __iomem **pe_handle);
+int pnv_ocxl_get_xsl_irq(struct pci_dev *dev, int *hwirq);
+void pnv_ocxl_unmap_xsl_regs(void __iomem *dsisr, void __iomem *dar,
+ void __iomem *tfc, void __iomem *pe_handle);
+int pnv_ocxl_map_xsl_regs(struct pci_dev *dev, void __iomem **dsisr,
+ void __iomem **dar, void __iomem **tfc,
+ void __iomem **pe_handle);
-extern int pnv_ocxl_spa_setup(struct pci_dev *dev, void *spa_mem, int PE_mask,
- void **platform_data);
-extern void pnv_ocxl_spa_release(void *platform_data);
-extern int pnv_ocxl_spa_remove_pe_from_cache(void *platform_data, int pe_handle);
+int pnv_ocxl_spa_setup(struct pci_dev *dev, void *spa_mem, int PE_mask, void **platform_data);
+void pnv_ocxl_spa_release(void *platform_data);
+int pnv_ocxl_spa_remove_pe_from_cache(void *platform_data, int pe_handle);
-extern int pnv_ocxl_alloc_xive_irq(u32 *irq, u64 *trigger_addr);
-extern void pnv_ocxl_free_xive_irq(u32 irq);
+int pnv_ocxl_alloc_xive_irq(u32 *irq, u64 *trigger_addr);
+void pnv_ocxl_free_xive_irq(u32 irq);
#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
u64 pnv_ocxl_platform_lpc_setup(struct pci_dev *pdev, u64 size);
void pnv_ocxl_platform_lpc_release(struct pci_dev *pdev);
diff --git a/include/misc/ocxl.h b/include/misc/ocxl.h
index 06dd5839e438..0a762e387418 100644
--- a/include/misc/ocxl.h
+++ b/include/misc/ocxl.h
@@ -173,7 +173,7 @@ int ocxl_context_detach(struct ocxl_context *ctx);
*
* Returns 0 on success, negative on failure
*/
-extern int ocxl_afu_irq_alloc(struct ocxl_context *ctx, int *irq_id);
+int ocxl_afu_irq_alloc(struct ocxl_context *ctx, int *irq_id);
/**
* Frees an IRQ associated with an AFU context
@@ -182,7 +182,7 @@ extern int ocxl_afu_irq_alloc(struct ocxl_context *ctx, int *irq_id);
*
* Returns 0 on success, negative on failure
*/
-extern int ocxl_afu_irq_free(struct ocxl_context *ctx, int irq_id);
+int ocxl_afu_irq_free(struct ocxl_context *ctx, int irq_id);
/**
* Gets the address of the trigger page for an IRQ
@@ -193,7 +193,7 @@ extern int ocxl_afu_irq_free(struct ocxl_context *ctx, int irq_id);
*
* returns the trigger page address, or 0 if the IRQ is not valid
*/
-extern u64 ocxl_afu_irq_get_addr(struct ocxl_context *ctx, int irq_id);
+u64 ocxl_afu_irq_get_addr(struct ocxl_context *ctx, int irq_id);
/**
* Provide a callback to be called when an IRQ is triggered
--
2.24.1
^ permalink raw reply related
* [PATCH v3 03/27] powerpc: Map & release OpenCAPI LPC memory
From: Alastair D'Silva @ 2020-02-21 3:26 UTC (permalink / raw)
To: alastair
Cc: Madhavan Srinivasan, Alexey Kardashevskiy, Masahiro Yamada,
Oliver O'Halloran, Mauro Carvalho Chehab, Ira Weiny,
Thomas Gleixner, Rob Herring, Dave Jiang, linux-nvdimm,
Aneesh Kumar K . V, Krzysztof Kozlowski, Anju T Sudhakar,
Mahesh Salgaonkar, Andrew Donnellan, Arnd Bergmann, Greg Kurz,
Nicholas Piggin, Cédric Le Goater, Dan Williams,
Hari Bathini, linux-mm, Greg Kroah-Hartman, linux-kernel,
Vishal Verma, Frederic Barrat, Paul Mackerras, Andrew Morton,
linuxppc-dev, David S. Miller
In-Reply-To: <20200221032720.33893-1-alastair@au1.ibm.com>
From: Alastair D'Silva <alastair@d-silva.org>
This patch adds platform support to map & release LPC memory.
Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
---
arch/powerpc/include/asm/pnv-ocxl.h | 4 +++
arch/powerpc/platforms/powernv/ocxl.c | 43 +++++++++++++++++++++++++++
2 files changed, 47 insertions(+)
diff --git a/arch/powerpc/include/asm/pnv-ocxl.h b/arch/powerpc/include/asm/pnv-ocxl.h
index 7de82647e761..0b2a6707e555 100644
--- a/arch/powerpc/include/asm/pnv-ocxl.h
+++ b/arch/powerpc/include/asm/pnv-ocxl.h
@@ -32,5 +32,9 @@ extern int pnv_ocxl_spa_remove_pe_from_cache(void *platform_data, int pe_handle)
extern int pnv_ocxl_alloc_xive_irq(u32 *irq, u64 *trigger_addr);
extern void pnv_ocxl_free_xive_irq(u32 irq);
+#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
+u64 pnv_ocxl_platform_lpc_setup(struct pci_dev *pdev, u64 size);
+void pnv_ocxl_platform_lpc_release(struct pci_dev *pdev);
+#endif
#endif /* _ASM_PNV_OCXL_H */
diff --git a/arch/powerpc/platforms/powernv/ocxl.c b/arch/powerpc/platforms/powernv/ocxl.c
index 8c65aacda9c8..f2edbcc67361 100644
--- a/arch/powerpc/platforms/powernv/ocxl.c
+++ b/arch/powerpc/platforms/powernv/ocxl.c
@@ -475,6 +475,49 @@ void pnv_ocxl_spa_release(void *platform_data)
}
EXPORT_SYMBOL_GPL(pnv_ocxl_spa_release);
+#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
+u64 pnv_ocxl_platform_lpc_setup(struct pci_dev *pdev, u64 size)
+{
+ struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+ struct pnv_phb *phb = hose->private_data;
+ u32 bdfn = pci_dev_id(pdev);
+ __be64 base_addr_be64;
+ u64 base_addr;
+ int rc;
+
+ rc = opal_npu_mem_alloc(phb->opal_id, bdfn, size, &base_addr_be64);
+ if (rc) {
+ dev_warn(&pdev->dev,
+ "OPAL could not allocate LPC memory, rc=%d\n", rc);
+ return 0;
+ }
+
+ base_addr = be64_to_cpu(base_addr_be64);
+
+ rc = check_hotplug_memory_addressable(base_addr >> PAGE_SHIFT,
+ size >> PAGE_SHIFT);
+ if (rc)
+ return 0;
+
+ return base_addr;
+}
+EXPORT_SYMBOL_GPL(pnv_ocxl_platform_lpc_setup);
+
+void pnv_ocxl_platform_lpc_release(struct pci_dev *pdev)
+{
+ struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+ struct pnv_phb *phb = hose->private_data;
+ u32 bdfn = pci_dev_id(pdev);
+ int rc;
+
+ rc = opal_npu_mem_release(phb->opal_id, bdfn);
+ if (rc)
+ dev_warn(&pdev->dev,
+ "OPAL reported rc=%d when releasing LPC memory\n", rc);
+}
+EXPORT_SYMBOL_GPL(pnv_ocxl_platform_lpc_release);
+#endif
+
int pnv_ocxl_spa_remove_pe_from_cache(void *platform_data, int pe_handle)
{
struct spa_data *data = (struct spa_data *) platform_data;
--
2.24.1
^ permalink raw reply related
* [PATCH v2 2/5] powerpc/idle: Add accessor function to always read latest idle PURR
From: Gautham R. Shenoy @ 2020-02-21 5:18 UTC (permalink / raw)
To: Nathan Lynch, Michael Ellerman, Vaidyanathan Srinivasan,
Kamalesh Babulal, Naveen N. Rao, Tyrel Datwyler
Cc: Gautham R. Shenoy, linuxppc-dev, linux-kernel
In-Reply-To: <1582262314-8319-1-git-send-email-ego@linux.vnet.ibm.com>
From: "Gautham R. Shenoy" <ego@linux.vnet.ibm.com>
Currently when CPU goes idle, we take a snapshot of PURR via
idle_loop_prolog() which is used at the CPU idle exit to compute the
idle PURR cycles via the function idle_loop_epilog(). Thus, the value
of idle PURR cycle thus read before idle_loop_prolog() and after
idle_loop_epilog() is always correct.
However, if we were to read the idle PURR cycles from an interrupt
context between idle_loop_prolog() and idle_loop_epilog() (this will
be done in a future patch), then, the value of the idle PURR thus read
will not include the cycles spent in the most recent idle period.
This patch addresses the issue by providing accessor function to read
the idle PURR such such that it includes the cycles spent in the most
recent idle period, if we read it between idle_loop_prolog() and
idle_loop_epilog(). In order to achieve it, the patch saves the
snapshot of PURR in idle_loop_prolog() in a per-cpu variable, instead
of on the stack, so that it can be accessed from an interrupt context.
Signed-off-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/idle.h | 46 +++++++++++++++++++++++++++-------
arch/powerpc/platforms/pseries/setup.c | 7 +++---
drivers/cpuidle/cpuidle-pseries.c | 15 +++++------
3 files changed, 46 insertions(+), 22 deletions(-)
diff --git a/arch/powerpc/include/asm/idle.h b/arch/powerpc/include/asm/idle.h
index f32a7d8..126a217 100644
--- a/arch/powerpc/include/asm/idle.h
+++ b/arch/powerpc/include/asm/idle.h
@@ -2,10 +2,27 @@
#define _ASM_POWERPC_IDLE_H
#include <asm/runlatch.h>
-static inline void idle_loop_prolog(unsigned long *in_purr)
+DECLARE_PER_CPU(u64, idle_entry_purr_snap);
+
+static inline void snapshot_purr_idle_entry(void)
+{
+ *this_cpu_ptr(&idle_entry_purr_snap) = mfspr(SPRN_PURR);
+}
+
+static inline void update_idle_purr_accounting(void)
+{
+ u64 wait_cycles;
+ u64 in_purr = *this_cpu_ptr(&idle_entry_purr_snap);
+
+ wait_cycles = be64_to_cpu(get_lppaca()->wait_state_cycles);
+ wait_cycles += mfspr(SPRN_PURR) - in_purr;
+ get_lppaca()->wait_state_cycles = cpu_to_be64(wait_cycles);
+}
+
+static inline void idle_loop_prolog(void)
{
ppc64_runlatch_off();
- *in_purr = mfspr(SPRN_PURR);
+ snapshot_purr_idle_entry();
/*
* Indicate to the HV that we are idle. Now would be
* a good time to find other work to dispatch.
@@ -13,15 +30,26 @@ static inline void idle_loop_prolog(unsigned long *in_purr)
get_lppaca()->idle = 1;
}
-static inline void idle_loop_epilog(unsigned long in_purr)
+static inline void idle_loop_epilog(void)
{
- u64 wait_cycles;
-
- wait_cycles = be64_to_cpu(get_lppaca()->wait_state_cycles);
- wait_cycles += mfspr(SPRN_PURR) - in_purr;
- get_lppaca()->wait_state_cycles = cpu_to_be64(wait_cycles);
+ update_idle_purr_accounting();
get_lppaca()->idle = 0;
-
ppc64_runlatch_on();
}
+
+static inline u64 read_this_idle_purr(void)
+{
+ /*
+ * If we are reading from an idle context, update the
+ * idle-purr cycles corresponding to the last idle period.
+ * Since the idle context is not yet over, take a fresh
+ * snapshot of the idle-purr.
+ */
+ if (unlikely(get_lppaca()->idle == 1)) {
+ update_idle_purr_accounting();
+ snapshot_purr_idle_entry();
+ }
+
+ return be64_to_cpu(get_lppaca()->wait_state_cycles);
+}
#endif
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index ffd4d59..e9f2cefa 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -318,10 +318,9 @@ static int alloc_dispatch_log_kmem_cache(void)
}
machine_early_initcall(pseries, alloc_dispatch_log_kmem_cache);
+DEFINE_PER_CPU(u64, idle_entry_purr_snap);
static void pseries_lpar_idle(void)
{
- unsigned long in_purr;
-
/*
* Default handler to go into low thread priority and possibly
* low power mode by ceding processor to hypervisor
@@ -331,7 +330,7 @@ static void pseries_lpar_idle(void)
return;
/* Indicate to hypervisor that we are idle. */
- idle_loop_prolog(&in_purr);
+ idle_loop_prolog();
/*
* Yield the processor to the hypervisor. We return if
@@ -342,7 +341,7 @@ static void pseries_lpar_idle(void)
*/
cede_processor();
- idle_loop_epilog(in_purr);
+ idle_loop_epilog();
}
/*
diff --git a/drivers/cpuidle/cpuidle-pseries.c b/drivers/cpuidle/cpuidle-pseries.c
index fc9dee9c..98d3832 100644
--- a/drivers/cpuidle/cpuidle-pseries.c
+++ b/drivers/cpuidle/cpuidle-pseries.c
@@ -36,12 +36,11 @@ static int snooze_loop(struct cpuidle_device *dev,
struct cpuidle_driver *drv,
int index)
{
- unsigned long in_purr;
u64 snooze_exit_time;
set_thread_flag(TIF_POLLING_NRFLAG);
- idle_loop_prolog(&in_purr);
+ idle_loop_prolog();
local_irq_enable();
snooze_exit_time = get_tb() + snooze_timeout;
@@ -65,7 +64,7 @@ static int snooze_loop(struct cpuidle_device *dev,
local_irq_disable();
- idle_loop_epilog(in_purr);
+ idle_loop_epilog();
return index;
}
@@ -91,9 +90,8 @@ static int dedicated_cede_loop(struct cpuidle_device *dev,
struct cpuidle_driver *drv,
int index)
{
- unsigned long in_purr;
- idle_loop_prolog(&in_purr);
+ idle_loop_prolog();
get_lppaca()->donate_dedicated_cpu = 1;
HMT_medium();
@@ -102,7 +100,7 @@ static int dedicated_cede_loop(struct cpuidle_device *dev,
local_irq_disable();
get_lppaca()->donate_dedicated_cpu = 0;
- idle_loop_epilog(in_purr);
+ idle_loop_epilog();
return index;
}
@@ -111,9 +109,8 @@ static int shared_cede_loop(struct cpuidle_device *dev,
struct cpuidle_driver *drv,
int index)
{
- unsigned long in_purr;
- idle_loop_prolog(&in_purr);
+ idle_loop_prolog();
/*
* Yield the processor to the hypervisor. We return if
@@ -125,7 +122,7 @@ static int shared_cede_loop(struct cpuidle_device *dev,
check_and_cede_processor();
local_irq_disable();
- idle_loop_epilog(in_purr);
+ idle_loop_epilog();
return index;
}
--
1.9.4
^ permalink raw reply related
* [PATCH v2 1/5] powerpc: Move idle_loop_prolog()/epilog() functions to header file
From: Gautham R. Shenoy @ 2020-02-21 5:18 UTC (permalink / raw)
To: Nathan Lynch, Michael Ellerman, Vaidyanathan Srinivasan,
Kamalesh Babulal, Naveen N. Rao, Tyrel Datwyler
Cc: Gautham R. Shenoy, linuxppc-dev, linux-kernel
In-Reply-To: <1582262314-8319-1-git-send-email-ego@linux.vnet.ibm.com>
From: "Gautham R. Shenoy" <ego@linux.vnet.ibm.com>
Currently prior to entering an idle state on a Linux Guest, the
pseries cpuidle driver implement an idle_loop_prolog() and
idle_loop_epilog() functions which ensure that idle_purr is correctly
computed, and the hypervisor is informed that the CPU cycles have been
donated.
These prolog and epilog functions are also required in the default
idle call, i.e pseries_lpar_idle(). Hence move these accessor
functions to a common header file and call them from
pseries_lpar_idle(). Since the existing header files such as
asm/processor.h have enough clutter, create a new header file
asm/idle.h.
Signed-off-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/idle.h | 27 +++++++++++++++++++++++++++
arch/powerpc/platforms/pseries/setup.c | 7 +++++--
drivers/cpuidle/cpuidle-pseries.c | 24 +-----------------------
3 files changed, 33 insertions(+), 25 deletions(-)
create mode 100644 arch/powerpc/include/asm/idle.h
diff --git a/arch/powerpc/include/asm/idle.h b/arch/powerpc/include/asm/idle.h
new file mode 100644
index 0000000..f32a7d8
--- /dev/null
+++ b/arch/powerpc/include/asm/idle.h
@@ -0,0 +1,27 @@
+#ifndef _ASM_POWERPC_IDLE_H
+#define _ASM_POWERPC_IDLE_H
+#include <asm/runlatch.h>
+
+static inline void idle_loop_prolog(unsigned long *in_purr)
+{
+ ppc64_runlatch_off();
+ *in_purr = mfspr(SPRN_PURR);
+ /*
+ * Indicate to the HV that we are idle. Now would be
+ * a good time to find other work to dispatch.
+ */
+ get_lppaca()->idle = 1;
+}
+
+static inline void idle_loop_epilog(unsigned long in_purr)
+{
+ u64 wait_cycles;
+
+ wait_cycles = be64_to_cpu(get_lppaca()->wait_state_cycles);
+ wait_cycles += mfspr(SPRN_PURR) - in_purr;
+ get_lppaca()->wait_state_cycles = cpu_to_be64(wait_cycles);
+ get_lppaca()->idle = 0;
+
+ ppc64_runlatch_on();
+}
+#endif
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 0c8421d..ffd4d59 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -68,6 +68,7 @@
#include <asm/isa-bridge.h>
#include <asm/security_features.h>
#include <asm/asm-const.h>
+#include <asm/idle.h>
#include <asm/swiotlb.h>
#include <asm/svm.h>
@@ -319,6 +320,8 @@ static int alloc_dispatch_log_kmem_cache(void)
static void pseries_lpar_idle(void)
{
+ unsigned long in_purr;
+
/*
* Default handler to go into low thread priority and possibly
* low power mode by ceding processor to hypervisor
@@ -328,7 +331,7 @@ static void pseries_lpar_idle(void)
return;
/* Indicate to hypervisor that we are idle. */
- get_lppaca()->idle = 1;
+ idle_loop_prolog(&in_purr);
/*
* Yield the processor to the hypervisor. We return if
@@ -339,7 +342,7 @@ static void pseries_lpar_idle(void)
*/
cede_processor();
- get_lppaca()->idle = 0;
+ idle_loop_epilog(in_purr);
}
/*
diff --git a/drivers/cpuidle/cpuidle-pseries.c b/drivers/cpuidle/cpuidle-pseries.c
index 74c2479..fc9dee9c 100644
--- a/drivers/cpuidle/cpuidle-pseries.c
+++ b/drivers/cpuidle/cpuidle-pseries.c
@@ -19,6 +19,7 @@
#include <asm/machdep.h>
#include <asm/firmware.h>
#include <asm/runlatch.h>
+#include <asm/idle.h>
#include <asm/plpar_wrappers.h>
struct cpuidle_driver pseries_idle_driver = {
@@ -31,29 +32,6 @@ struct cpuidle_driver pseries_idle_driver = {
static u64 snooze_timeout __read_mostly;
static bool snooze_timeout_en __read_mostly;
-static inline void idle_loop_prolog(unsigned long *in_purr)
-{
- ppc64_runlatch_off();
- *in_purr = mfspr(SPRN_PURR);
- /*
- * Indicate to the HV that we are idle. Now would be
- * a good time to find other work to dispatch.
- */
- get_lppaca()->idle = 1;
-}
-
-static inline void idle_loop_epilog(unsigned long in_purr)
-{
- u64 wait_cycles;
-
- wait_cycles = be64_to_cpu(get_lppaca()->wait_state_cycles);
- wait_cycles += mfspr(SPRN_PURR) - in_purr;
- get_lppaca()->wait_state_cycles = cpu_to_be64(wait_cycles);
- get_lppaca()->idle = 0;
-
- ppc64_runlatch_on();
-}
-
static int snooze_loop(struct cpuidle_device *dev,
struct cpuidle_driver *drv,
int index)
--
1.9.4
^ permalink raw reply related
* [PATCH v2 4/5] powerpc/sysfs: Show idle_purr and idle_spurr for every CPU
From: Gautham R. Shenoy @ 2020-02-21 5:18 UTC (permalink / raw)
To: Nathan Lynch, Michael Ellerman, Vaidyanathan Srinivasan,
Kamalesh Babulal, Naveen N. Rao, Tyrel Datwyler
Cc: Gautham R. Shenoy, linuxppc-dev, linux-kernel
In-Reply-To: <1582262314-8319-1-git-send-email-ego@linux.vnet.ibm.com>
From: "Gautham R. Shenoy" <ego@linux.vnet.ibm.com>
On Pseries LPARs, to calculate utilization, we need to know the
[S]PURR ticks when the CPUs were busy or idle.
The total PURR and SPURR ticks are already exposed via the per-cpu
sysfs files "purr" and "spurr". This patch adds support for exposing
the idle PURR and SPURR ticks via new per-cpu sysfs files named
"idle_purr" and "idle_spurr".
Signed-off-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
---
arch/powerpc/kernel/sysfs.c | 54 ++++++++++++++++++++++++++++++++++++++++++---
1 file changed, 51 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index 80a676d..5b4b450 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -19,6 +19,7 @@
#include <asm/smp.h>
#include <asm/pmc.h>
#include <asm/firmware.h>
+#include <asm/idle.h>
#include <asm/svm.h>
#include "cacheinfo.h"
@@ -733,6 +734,42 @@ static void create_svm_file(void)
}
#endif /* CONFIG_PPC_SVM */
+static void read_idle_purr(void *val)
+{
+ u64 *ret = (u64 *)val;
+
+ *ret = read_this_idle_purr();
+}
+
+static ssize_t idle_purr_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct cpu *cpu = container_of(dev, struct cpu, dev);
+ u64 val;
+
+ smp_call_function_single(cpu->dev.id, read_idle_purr, &val, 1);
+ return sprintf(buf, "%llx\n", val);
+}
+static DEVICE_ATTR(idle_purr, 0400, idle_purr_show, NULL);
+
+static void read_idle_spurr(void *val)
+{
+ u64 *ret = (u64 *)val;
+
+ *ret = read_this_idle_spurr();
+}
+
+static ssize_t idle_spurr_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct cpu *cpu = container_of(dev, struct cpu, dev);
+ u64 val;
+
+ smp_call_function_single(cpu->dev.id, read_idle_spurr, &val, 1);
+ return sprintf(buf, "%llx\n", val);
+}
+static DEVICE_ATTR(idle_spurr, 0400, idle_spurr_show, NULL);
+
static int register_cpu_online(unsigned int cpu)
{
struct cpu *c = &per_cpu(cpu_devices, cpu);
@@ -794,10 +831,15 @@ static int register_cpu_online(unsigned int cpu)
if (!firmware_has_feature(FW_FEATURE_LPAR))
add_write_permission_dev_attr(&dev_attr_purr);
device_create_file(s, &dev_attr_purr);
+ if (firmware_has_feature(FW_FEATURE_LPAR))
+ device_create_file(s, &dev_attr_idle_purr);
}
- if (cpu_has_feature(CPU_FTR_SPURR))
+ if (cpu_has_feature(CPU_FTR_SPURR)) {
device_create_file(s, &dev_attr_spurr);
+ if (firmware_has_feature(FW_FEATURE_LPAR))
+ device_create_file(s, &dev_attr_idle_spurr);
+ }
if (cpu_has_feature(CPU_FTR_DSCR))
device_create_file(s, &dev_attr_dscr);
@@ -879,11 +921,17 @@ static int unregister_cpu_online(unsigned int cpu)
if (cpu_has_feature(CPU_FTR_MMCRA))
device_remove_file(s, &dev_attr_mmcra);
- if (cpu_has_feature(CPU_FTR_PURR))
+ if (cpu_has_feature(CPU_FTR_PURR)) {
device_remove_file(s, &dev_attr_purr);
+ if (firmware_has_feature(FW_FEATURE_LPAR))
+ device_remove_file(s, &dev_attr_idle_purr);
+ }
- if (cpu_has_feature(CPU_FTR_SPURR))
+ if (cpu_has_feature(CPU_FTR_SPURR)) {
device_remove_file(s, &dev_attr_spurr);
+ if (firmware_has_feature(FW_FEATURE_LPAR))
+ device_remove_file(s, &dev_attr_idle_spurr);
+ }
if (cpu_has_feature(CPU_FTR_DSCR))
device_remove_file(s, &dev_attr_dscr);
--
1.9.4
^ permalink raw reply related
* [PATCH v2 0/5] Track and expose idle PURR and SPURR ticks
From: Gautham R. Shenoy @ 2020-02-21 5:18 UTC (permalink / raw)
To: Nathan Lynch, Michael Ellerman, Vaidyanathan Srinivasan,
Kamalesh Babulal, Naveen N. Rao, Tyrel Datwyler
Cc: Gautham R. Shenoy, linuxppc-dev, linux-kernel
From: "Gautham R. Shenoy" <ego@linux.vnet.ibm.com>
Hi,
This is the second version of the patches to track and expose idle
PURR and SPURR ticks. These patches are required by tools such as
lparstat to compute system utilization for capacity planning purposes.
v1 can be found here: https://lore.kernel.org/patchwork/cover/1159341/
The key changes from v1 are
- The sysfs reads of idle PURR and SPURR now send an
smp_call_function to the target CPU in order to read the most
recent value of idle PURR and SPURR. This is required if the
target CPU was idle for a long duration, in which case the
cycles corresponding to its latest idle duration would not be
updated in the variable tracking idle PURR/SPURR. Thus merely
reading the variable would not reflect the most accurate idle
PURR/SPURR ticks.
- Ensured that even when idle PURR/SPURR values are read in an
interrupt context in-between idle_loop_prolog() and
idle_loop_epilog(), we return the value that includes the cycles
spent in the most recent idle period.
- The sysfs files for idle_purr and idle_spurr are created only
when the FW_FEATURE_LPAR is enabled (the earlier version was
checking for FW_FEATURE_SPLPAR)
Motivation:
===========
On PSeries LPARs, the data centers planners desire a more accurate
view of system utilization per resource such as CPU to plan the system
capacity requirements better. Such accuracy can be obtained by reading
PURR/SPURR registers for CPU resource utilization.
Tools such as lparstat which are used to compute the utilization need
to know [S]PURR ticks when the cpu was busy or idle. The [S]PURR
counters are already exposed through sysfs. We already account for
PURR ticks when we go to idle so that we can update the VPA area. This
patchset extends support to account for SPURR ticks when idle, and
expose both via per-cpu sysfs files.
These patches are required for enhancement to the lparstat utility
that compute the CPU utilization based on PURR and SPURR which can be
found here :
https://groups.google.com/forum/#!topic/powerpc-utils-devel/fYRo69xO9r4
With the patches, when lparstat is run on a LPAR running CPU-Hogs,
=========================================================================
$sudo ./src/lparstat -E 1 3
System Configuration
type=Dedicated mode=Capped smt=8 lcpu=2 mem=4834176 kB cpus=0 ent=2.00
---Actual--- -Normalized-
%busy %idle Frequency %busy %idle
------ ------ ------------- ------ ------
99.99 0.00 3.35GHz[111%] 110.99 0.00
100.00 0.00 3.35GHz[111%] 111.00 0.00
100.00 0.00 3.35GHz[111%] 111.00 0.00
=========================================================================
When lparstat is run on an LPAR that is idle,
=========================================================================
$ sudo ./src/lparstat -E 1 3
System Configuration
type=Dedicated mode=Capped smt=8 lcpu=2 mem=4834176 kB cpus=0 ent=2.00
---Actual--- -Normalized-
%busy %idle Frequency %busy %idle
------ ------ ------------- ------ ------
0.09 99.91 2.11GHz[ 70%] 0.11 69.90
0.32 99.68 2.17GHz[ 72%] 0.25 71.75
0.56 99.44 2.18GHz[ 72%] 0.42 71.58
=========================================================================
Gautham R. Shenoy (5):
powerpc: Move idle_loop_prolog()/epilog() functions to header file
powerpc/idle: Add accessor function to always read latest idle PURR
powerpc/pseries: Account for SPURR ticks on idle CPUs
powerpc/sysfs: Show idle_purr and idle_spurr for every CPU
Documentation: Document sysfs interfaces purr, spurr, idle_purr,
idle_spurr
Documentation/ABI/testing/sysfs-devices-system-cpu | 39 ++++++++++
arch/powerpc/include/asm/idle.h | 88 ++++++++++++++++++++++
arch/powerpc/kernel/sysfs.c | 54 ++++++++++++-
arch/powerpc/platforms/pseries/setup.c | 8 +-
drivers/cpuidle/cpuidle-pseries.c | 39 ++--------
5 files changed, 191 insertions(+), 37 deletions(-)
create mode 100644 arch/powerpc/include/asm/idle.h
--
1.9.4
^ permalink raw reply
* [PATCH v2 3/5] powerpc/pseries: Account for SPURR ticks on idle CPUs
From: Gautham R. Shenoy @ 2020-02-21 5:18 UTC (permalink / raw)
To: Nathan Lynch, Michael Ellerman, Vaidyanathan Srinivasan,
Kamalesh Babulal, Naveen N. Rao, Tyrel Datwyler
Cc: Gautham R. Shenoy, linuxppc-dev, linux-kernel
In-Reply-To: <1582262314-8319-1-git-send-email-ego@linux.vnet.ibm.com>
From: "Gautham R. Shenoy" <ego@linux.vnet.ibm.com>
On Pseries LPARs, to calculate utilization, we need to know the
[S]PURR ticks when the CPUs were busy or idle.
Via idle_loop_prolog(), idle_loop_epilog(), we track the idle PURR
ticks in the VPA variable "wait_state_cycles". This patch extends the
support to account for the idle SPURR ticks. It also provides an
accessor function to accurately reads idle SPURR ticks.
Signed-off-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/idle.h | 33 +++++++++++++++++++++++++++++++++
arch/powerpc/platforms/pseries/setup.c | 2 ++
2 files changed, 35 insertions(+)
diff --git a/arch/powerpc/include/asm/idle.h b/arch/powerpc/include/asm/idle.h
index 126a217..db82fc1 100644
--- a/arch/powerpc/include/asm/idle.h
+++ b/arch/powerpc/include/asm/idle.h
@@ -2,13 +2,20 @@
#define _ASM_POWERPC_IDLE_H
#include <asm/runlatch.h>
+DECLARE_PER_CPU(u64, idle_spurr_cycles);
DECLARE_PER_CPU(u64, idle_entry_purr_snap);
+DECLARE_PER_CPU(u64, idle_entry_spurr_snap);
static inline void snapshot_purr_idle_entry(void)
{
*this_cpu_ptr(&idle_entry_purr_snap) = mfspr(SPRN_PURR);
}
+static inline void snapshot_spurr_idle_entry(void)
+{
+ *this_cpu_ptr(&idle_entry_spurr_snap) = mfspr(SPRN_SPURR);
+}
+
static inline void update_idle_purr_accounting(void)
{
u64 wait_cycles;
@@ -19,10 +26,19 @@ static inline void update_idle_purr_accounting(void)
get_lppaca()->wait_state_cycles = cpu_to_be64(wait_cycles);
}
+static inline void update_idle_spurr_accounting(void)
+{
+ u64 *idle_spurr_cycles_ptr = this_cpu_ptr(&idle_spurr_cycles);
+ u64 in_spurr = *this_cpu_ptr(&idle_entry_spurr_snap);
+
+ *idle_spurr_cycles_ptr += mfspr(SPRN_SPURR) - in_spurr;
+}
+
static inline void idle_loop_prolog(void)
{
ppc64_runlatch_off();
snapshot_purr_idle_entry();
+ snapshot_spurr_idle_entry();
/*
* Indicate to the HV that we are idle. Now would be
* a good time to find other work to dispatch.
@@ -33,6 +49,7 @@ static inline void idle_loop_prolog(void)
static inline void idle_loop_epilog(void)
{
update_idle_purr_accounting();
+ update_idle_spurr_accounting();
get_lppaca()->idle = 0;
ppc64_runlatch_on();
}
@@ -52,4 +69,20 @@ static inline u64 read_this_idle_purr(void)
return be64_to_cpu(get_lppaca()->wait_state_cycles);
}
+
+static inline u64 read_this_idle_spurr(void)
+{
+ /*
+ * If we are reading from an idle context, update the
+ * idle-spurr cycles corresponding to the last idle period.
+ * Since the idle context is not yet over, take a fresh
+ * snapshot of the idle-spurr.
+ */
+ if (get_lppaca()->idle == 1) {
+ update_idle_spurr_accounting();
+ snapshot_spurr_idle_entry();
+ }
+
+ return *this_cpu_ptr(&idle_spurr_cycles);
+}
#endif
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index e9f2cefa..5ef5c82 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -318,7 +318,9 @@ static int alloc_dispatch_log_kmem_cache(void)
}
machine_early_initcall(pseries, alloc_dispatch_log_kmem_cache);
+DEFINE_PER_CPU(u64, idle_spurr_cycles);
DEFINE_PER_CPU(u64, idle_entry_purr_snap);
+DEFINE_PER_CPU(u64, idle_entry_spurr_snap);
static void pseries_lpar_idle(void)
{
/*
--
1.9.4
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox