LKML Archive on lore.kernel.org
 help / color / Atom feed
From: "Alastair D'Silva" <alastair@d-silva.org>
To: alastair@d-silva.org
Cc: "Aneesh Kumar K . V" <aneesh.kumar@linux.ibm.com>,
	"Oliver O\'Halloran" <oohall@gmail.com>,
	"Benjamin Herrenschmidt" <benh@kernel.crashing.org>,
	"Paul Mackerras" <paulus@samba.org>,
	"Michael Ellerman" <mpe@ellerman.id.au>,
	"Frederic Barrat" <fbarrat@linux.ibm.com>,
	"Andrew Donnellan" <ajd@linux.ibm.com>,
	"Arnd Bergmann" <arnd@arndb.de>,
	"Greg Kroah-Hartman" <gregkh@linuxfoundation.org>,
	"Dan Williams" <dan.j.williams@intel.com>,
	"Vishal Verma" <vishal.l.verma@intel.com>,
	"Dave Jiang" <dave.jiang@intel.com>,
	"Ira Weiny" <ira.weiny@intel.com>,
	"Andrew Morton" <akpm@linux-foundation.org>,
	"Mauro Carvalho Chehab" <mchehab+samsung@kernel.org>,
	"David S. Miller" <davem@davemloft.net>,
	"Rob Herring" <robh@kernel.org>,
	"Anton Blanchard" <anton@ozlabs.org>,
	"Krzysztof Kozlowski" <krzk@kernel.org>,
	"Mahesh Salgaonkar" <mahesh@linux.vnet.ibm.com>,
	"Madhavan Srinivasan" <maddy@linux.vnet.ibm.com>,
	"Cédric Le Goater" <clg@kaod.org>,
	"Anju T Sudhakar" <anju@linux.vnet.ibm.com>,
	"Hari Bathini" <hbathini@linux.ibm.com>,
	"Thomas Gleixner" <tglx@linutronix.de>,
	"Greg Kurz" <groug@kaod.org>,
	"Nicholas Piggin" <npiggin@gmail.com>,
	"Masahiro Yamada" <yamada.masahiro@socionext.com>,
	"Alexey Kardashevskiy" <aik@ozlabs.ru>,
	linux-kernel@vger.kernel.org, linuxppc-dev@lists.ozlabs.org,
	linux-nvdimm@lists.01.org, linux-mm@kvack.org
Subject: [PATCH v4 17/25] nvdimm/ocxl: Add controller dump IOCTLs
Date: Fri, 27 Mar 2020 18:11:54 +1100
Message-ID: <20200327071202.2159885-18-alastair@d-silva.org> (raw)
In-Reply-To: <20200327071202.2159885-1-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.

The expected flow of operations are:
1. IOCTL_OCXL_PMEM_CONTROLLER_DUMP to request the controller to take
   a dump. This IOCTL will complete after the dump is available for
   collection.
2. IOCTL_OCXL_PMEM_CONTROLLER_DUMP_DATA called repeatedly to fetch
   chunks from the buffer
3. IOCTL_OCXL_PMEM_CONTROLLER_DUMP_COMPLETE to notify the controller
   that it can free any internal resources used for the dump

Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
---
 drivers/nvdimm/ocxl/main.c     | 161 +++++++++++++++++++++++++++++++++
 include/uapi/nvdimm/ocxlpmem.h |  16 ++++
 2 files changed, 177 insertions(+)

diff --git a/drivers/nvdimm/ocxl/main.c b/drivers/nvdimm/ocxl/main.c
index e6be0029f658..d0db358ded43 100644
--- a/drivers/nvdimm/ocxl/main.c
+++ b/drivers/nvdimm/ocxl/main.c
@@ -566,6 +566,153 @@ static int ioctl_error_log(struct ocxlpmem *ocxlpmem,
 	return 0;
 }
 
+/**
+ * controller_dump_header_parse() - Parse the first 64 bits of the controller dump command response
+ * @ocxlpmem: the device metadata
+ * @length: out, returns the number of bytes in the response (excluding the 64 bit header)
+ */
+static int controller_dump_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 != 0x4344) { // 'CD'
+		dev_err(&ocxlpmem->dev,
+			"Bad data identifier for error log data, expected 'CD', 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 ioctl_controller_dump_data(struct ocxlpmem *ocxlpmem,
+				      struct ioctl_ocxlpmem_controller_dump_data __user *uarg)
+{
+	struct ioctl_ocxlpmem_controller_dump_data args;
+	u64 __user *buf;
+	u16 i, buf_size;
+	u64 val;
+	int rc;
+
+	if (copy_from_user(&args, uarg, sizeof(args)))
+		return -EFAULT;
+
+	if (args.buf_size % sizeof(u64))
+		return -EINVAL;
+
+	if (args.buf_size > ocxlpmem->admin_command.data_size)
+		return -EINVAL;
+
+	buf = (u64 *)args.buf_ptr;
+
+	mutex_lock(&ocxlpmem->admin_command.lock);
+
+	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, ADMIN_COMMAND_CONTROLLER_DUMP);
+	if (rc)
+		goto out;
+	if (rc != STATUS_SUCCESS) {
+		warn_status(ocxlpmem,
+			    "Unexpected status from controller dump",
+			    rc);
+		goto out;
+	}
+
+	rc = controller_dump_header_parse(ocxlpmem, &buf_size);
+	if (rc)
+		goto out;
+
+	buf_size = min((u16)(buf_size + sizeof(u64)), args.buf_size);
+
+	for (i = 0; i < buf_size / sizeof(u64); i++) {
+		rc = ocxl_global_mmio_read64(ocxlpmem->ocxl_afu,
+					     ocxlpmem->admin_command.data_offset +
+							i * sizeof(u64),
+					     OCXL_HOST_ENDIAN, &val);
+		if (rc)
+			goto out;
+
+		if (copy_to_user(&buf[i], &val, sizeof(u64))) {
+			rc = -EFAULT;
+			goto out;
+		}
+	}
+
+	args.buf_size = buf_size;
+
+	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);
+	if (rc)
+		return rc;
+
+	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;
@@ -576,7 +723,21 @@ static long file_ioctl(struct file *file, unsigned int cmd, unsigned long args)
 		rc = ioctl_error_log(ocxlpmem,
 				     (struct ioctl_ocxlpmem_error_log __user *)args);
 		break;
+
+	case IOCTL_OCXLPMEM_CONTROLLER_DUMP:
+		rc = request_controller_dump(ocxlpmem);
+		break;
+
+	case IOCTL_OCXLPMEM_CONTROLLER_DUMP_DATA:
+		rc = ioctl_controller_dump_data(ocxlpmem,
+						(struct ioctl_ocxlpmem_controller_dump_data __user *)args);
+		break;
+
+	case IOCTL_OCXLPMEM_CONTROLLER_DUMP_COMPLETE:
+		rc = ioctl_controller_dump_complete(ocxlpmem);
+		break;
 	}
+
 	return rc;
 }
 
diff --git a/include/uapi/nvdimm/ocxlpmem.h b/include/uapi/nvdimm/ocxlpmem.h
index 5d3a03ea1e08..05e2b3f7b27c 100644
--- a/include/uapi/nvdimm/ocxlpmem.h
+++ b/include/uapi/nvdimm/ocxlpmem.h
@@ -38,9 +38,25 @@ struct ioctl_ocxlpmem_error_log {
 	__u64 reserved2[2];
 };
 
+struct ioctl_ocxlpmem_controller_dump_data {
+	__u64 buf_ptr; /* coerced 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.
+			 */
+	__u16 reserved0;
+	__u32 offset; /* in, Offset within the dump */
+	__u64 reserved[8];
+};
+
 /* ioctl numbers */
 #define OCXLPMEM_MAGIC 0xCA
 /* OpenCAPI Persistent memory devices */
 #define IOCTL_OCXLPMEM_ERROR_LOG			_IOWR(OCXLPMEM_MAGIC, 0x30, struct ioctl_ocxlpmem_error_log)
+#define IOCTL_OCXLPMEM_CONTROLLER_DUMP			_IO(OCXLPMEM_MAGIC, 0x31)
+#define IOCTL_OCXLPMEM_CONTROLLER_DUMP_DATA		_IOWR(OCXLPMEM_MAGIC, 0x32, struct ioctl_ocxlpmem_controller_dump_data)
+#define IOCTL_OCXLPMEM_CONTROLLER_DUMP_COMPLETE		_IO(OCXLPMEM_MAGIC, 0x33)
 
 #endif /* _UAPI_OCXL_SCM_H */
-- 
2.24.1


  parent reply index

Thread overview: 60+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-03-27  7:11 [PATCH v4 00/25] Add support for OpenCAPI Persistent Memory devices Alastair D'Silva
2020-03-27  7:11 ` [PATCH v4 01/25] powerpc/powernv: Add OPAL calls for LPC memory alloc/release Alastair D'Silva
2020-04-01  8:48   ` Dan Williams
2020-04-01 22:51     ` Alastair D'Silva
2020-03-27  7:11 ` [PATCH v4 02/25] mm/memory_hotplug: Allow check_hotplug_memory_addressable to be called from drivers Alastair D'Silva
2020-04-01  8:48   ` Dan Williams
2020-04-02  4:33     ` Alastair D'Silva
2020-03-27  7:11 ` [PATCH v4 03/25] powerpc/powernv: Map & release OpenCAPI LPC memory Alastair D'Silva
2020-04-01  8:48   ` Dan Williams
2020-04-02  4:36     ` Alastair D'Silva
2020-04-02 10:41     ` Benjamin Herrenschmidt
2020-04-03  4:27       ` Michael Ellerman
2020-03-27  7:11 ` [PATCH v4 04/25] ocxl: Remove unnecessary externs Alastair D'Silva
2020-04-01  8:48   ` Dan Williams
2020-03-27  7:11 ` [PATCH v4 05/25] ocxl: Address kernel doc errors & warnings Alastair D'Silva
2020-04-01  8:49   ` Dan Williams
2020-03-27  7:11 ` [PATCH v4 06/25] ocxl: Tally up the LPC memory on a link & allow it to be mapped Alastair D'Silva
2020-04-01  8:48   ` Dan Williams
2020-04-02  6:21     ` Andrew Donnellan
2020-03-27  7:11 ` [PATCH v4 07/25] ocxl: Add functions to map/unmap LPC memory Alastair D'Silva
2020-04-01  8:49   ` Dan Williams
2020-04-03  3:50     ` Alastair D'Silva
2020-03-27  7:11 ` [PATCH v4 08/25] ocxl: Emit a log message showing how much LPC memory was detected Alastair D'Silva
2020-04-01  8:49   ` Dan Williams
2020-04-02  1:29     ` Joe Perches
2020-04-03  3:52     ` Alastair D'Silva
2020-03-27  7:11 ` [PATCH v4 09/25] ocxl: Save the device serial number in ocxl_fn Alastair D'Silva
2020-03-27  7:11 ` [PATCH v4 10/25] nvdimm: Add driver for OpenCAPI Persistent Memory Alastair D'Silva
2020-03-29  2:56   ` Matthew Wilcox
2020-03-29  2:59     ` Matthew Wilcox
2020-04-01  8:49   ` Dan Williams
2020-04-01 19:35     ` Dan Williams
2020-03-27  7:11 ` [PATCH v4 11/25] powerpc: Enable the OpenCAPI Persistent Memory driver for powernv_defconfig Alastair D'Silva
2020-04-01 20:26   ` Dan Williams
2020-03-27  7:11 ` [PATCH v4 12/25] nvdimm/ocxl: Add register addresses & status values to the header Alastair D'Silva
2020-04-01 20:27   ` Dan Williams
2020-03-27  7:11 ` [PATCH v4 13/25] nvdimm/ocxl: Read the capability registers & wait for device ready Alastair D'Silva
2020-04-02  0:20   ` Dan Williams
2020-03-27  7:11 ` [PATCH v4 14/25] nvdimm/ocxl: Add support for Admin commands Alastair D'Silva
2020-04-02  6:41   ` Dan Williams
2020-03-27  7:11 ` [PATCH v4 15/25] nvdimm/ocxl: Register a character device for userspace to interact with Alastair D'Silva
2020-04-02  0:27   ` Dan Williams
2020-03-27  7:11 ` [PATCH v4 16/25] nvdimm/ocxl: Implement the Read Error Log command Alastair D'Silva
2020-04-03  0:54   ` Dan Williams
2020-03-27  7:11 ` Alastair D'Silva [this message]
2020-03-27  7:11 ` [PATCH v4 18/25] nvdimm/ocxl: Add an IOCTL to report controller statistics Alastair D'Silva
2020-03-27  7:11 ` [PATCH v4 19/25] nvdimm/ocxl: Forward events to userspace Alastair D'Silva
2020-04-02  2:08   ` Dan Williams
2020-03-27  7:11 ` [PATCH v4 20/25] nvdimm/ocxl: Add an IOCTL to request controller health & perf data Alastair D'Silva
2020-03-27  7:11 ` [PATCH v4 21/25] nvdimm/ocxl: Implement the heartbeat command Alastair D'Silva
2020-03-27  7:11 ` [PATCH v4 22/25] nvdimm/ocxl: Add debug IOCTLs Alastair D'Silva
2020-03-27  7:12 ` [PATCH v4 23/25] nvdimm/ocxl: Expose SMART data via ndctl Alastair D'Silva
2020-03-27  7:12 ` [PATCH v4 24/25] nvdimm/ocxl: Expose the serial number & firmware version in sysfs Alastair D'Silva
2020-03-27  7:12 ` [PATCH v4 25/25] MAINTAINERS: Add myself & nvdimm/ocxl to ocxl Alastair D'Silva
2020-04-01  8:47 ` [PATCH v4 00/25] Add support for OpenCAPI Persistent Memory devices Dan Williams
2020-04-01 22:44   ` Alastair D'Silva
2020-04-02  3:42     ` Michael Ellerman
2020-04-02  3:50       ` Oliver O'Halloran
2020-04-02 10:06         ` Michael Ellerman
2020-04-02 11:10           ` Greg Kurz

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200327071202.2159885-18-alastair@d-silva.org \
    --to=alastair@d-silva.org \
    --cc=aik@ozlabs.ru \
    --cc=ajd@linux.ibm.com \
    --cc=akpm@linux-foundation.org \
    --cc=aneesh.kumar@linux.ibm.com \
    --cc=anju@linux.vnet.ibm.com \
    --cc=anton@ozlabs.org \
    --cc=arnd@arndb.de \
    --cc=benh@kernel.crashing.org \
    --cc=clg@kaod.org \
    --cc=dan.j.williams@intel.com \
    --cc=dave.jiang@intel.com \
    --cc=davem@davemloft.net \
    --cc=fbarrat@linux.ibm.com \
    --cc=gregkh@linuxfoundation.org \
    --cc=groug@kaod.org \
    --cc=hbathini@linux.ibm.com \
    --cc=ira.weiny@intel.com \
    --cc=krzk@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-nvdimm@lists.01.org \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=maddy@linux.vnet.ibm.com \
    --cc=mahesh@linux.vnet.ibm.com \
    --cc=mchehab+samsung@kernel.org \
    --cc=mpe@ellerman.id.au \
    --cc=npiggin@gmail.com \
    --cc=oohall@gmail.com \
    --cc=paulus@samba.org \
    --cc=robh@kernel.org \
    --cc=tglx@linutronix.de \
    --cc=vishal.l.verma@intel.com \
    --cc=yamada.masahiro@socionext.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lkml.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lkml.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lkml.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lkml.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lkml.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lkml.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lkml.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lkml.kernel.org/lkml/7 lkml/git/7.git
	git clone --mirror https://lkml.kernel.org/lkml/8 lkml/git/8.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 lkml lkml/ https://lkml.kernel.org/lkml \
		linux-kernel@vger.kernel.org
	public-inbox-index lkml

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git