Re: [PATCH v3 19/27] powerpc/powernv/pmem: Add an IOCTL to report controller statistics
From: Andrew Donnellan
Date: Wed Mar 04 2020 - 19:46:44 EST
On 21/2/20 2:27 pm, Alastair D'Silva wrote:
From: Alastair D'Silva <alastair@xxxxxxxxxxx>
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@xxxxxxxxxxx>
---
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;
Same comment as earlier patches re 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);
Might be worth a comment to explain where 0x140 comes from (it looks
correct from my reading of the spec)
+
+ 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;
We're not collecting life remaining?
+
+ rc = ocxl_global_mmio_read64(ocxlpmem->ocxl_afu,
+ ocxlpmem->admin_command.data_offset + 0x08 + 0x40 + 0x08,
+ OCXL_LITTLE_ENDIAN, &args.host_load_count);
My reading of the spec says HLC is at +0x10
+ 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);
HSC at +0x18
+ 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);
MRC is at +0x50
And you're missing CRU, HLD, HSD
+ 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);
MWC at +0x58
+ 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);
CRHC at +0x90
+ 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);
This field doesn't seem to exist at all in my copy of the spec
+ 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);
Nor this one
+ 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);
Nor this one
+ 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);
Nor this one
+ 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);
Nor this one
+ 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;
Per Fred this pattern isn't common in the kernel, but perhaps this is
just personal taste
+
+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 */
--
Andrew Donnellan OzLabs, ADL Canberra
ajd@xxxxxxxxxxxxx IBM Australia Limited