Merge branch 'sfc-next'

Edward Cree says:

====================
sfc: add MCDI tracing

This patchset adds support for logging MCDI (Management-Controller-to-
 Driver Interface) interactions between the sfc driver and a bound device,
 to aid in debugging.
Solarflare has a tool to decode the resulting traces and will look to
 open-source this if there is any external interest, but the protocol is
 already detailed in drivers/net/ethernet/sfc/mcdi_pcol.h.
The logging buffer we allocate per MCDI context is a work area for
 constructing each individual message before logging it with netif_info.
The reason the buffer is long-lived is simply to avoid the overhead of
 allocating and freeing it every MCDI call, since MCDIs are already known
 to be serialised for other reasons.

--
v4: remove patch #4, which has already been applied via sshah
v3: add some explanations to cover letter and patch #4
v2: avoid long lines in cover letter; fix multiline comment style
====================

Signed-off-by: David S. Miller <[email protected]>

drivers/net/ethernet/sfc/Kconfig

@@ -36,3 +36,12 @@ config SFC_SRIOV
 	  This enables support for the SFC9000 I/O Virtualization
 	  features, allowing accelerated network performance in
 	  virtualized environments.
+config SFC_MCDI_LOGGING
+	bool "Solarflare SFC9000/SFC9100-family MCDI logging support"
+	depends on SFC
+	default y
+	---help---
+	  This enables support for tracing of MCDI (Management-Controller-to-
+	  Driver-Interface) commands and responses, allowing debugging of
+	  driver/firmware interaction.  The tracing is actually enabled by
+	  a sysfs file 'mcdi_logging' under the PCI device.

drivers/net/ethernet/sfc/ef10.c

@@ -267,6 +267,9 @@ static int efx_ef10_probe(struct efx_nic *efx)
 		return -ENOMEM;
 	efx->nic_data = nic_data;
 
+	/* we assume later that we can copy from this buffer in dwords */
+	BUILD_BUG_ON(MCDI_CTL_SDU_LEN_MAX_V2 % 4);
+
 	rc = efx_nic_alloc_buffer(efx, &nic_data->mcdi_buf,
 				  8 + MCDI_CTL_SDU_LEN_MAX_V2, GFP_KERNEL);
 	if (rc)

drivers/net/ethernet/sfc/efx.c

@@ -2326,6 +2326,28 @@ show_phy_type(struct device *dev, struct device_attribute *attr, char *buf)
 }
 static DEVICE_ATTR(phy_type, 0444, show_phy_type, NULL);
 
+#ifdef CONFIG_SFC_MCDI_LOGGING
+static ssize_t show_mcdi_log(struct device *dev, struct device_attribute *attr,
+			     char *buf)
+{
+	struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev));
+	struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
+
+	return scnprintf(buf, PAGE_SIZE, "%d\n", mcdi->logging_enabled);
+}
+static ssize_t set_mcdi_log(struct device *dev, struct device_attribute *attr,
+			    const char *buf, size_t count)
+{
+	struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev));
+	struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
+	bool enable = count > 0 && *buf != '0';
+
+	mcdi->logging_enabled = enable;
+	return count;
+}
+static DEVICE_ATTR(mcdi_logging, 0644, show_mcdi_log, set_mcdi_log);
+#endif
+
 static int efx_register_netdev(struct efx_nic *efx)
 {
 	struct net_device *net_dev = efx->net_dev;
@@ -2383,9 +2405,21 @@ static int efx_register_netdev(struct efx_nic *efx)
 			  "failed to init net dev attributes\n");
 		goto fail_registered;
 	}
+#ifdef CONFIG_SFC_MCDI_LOGGING
+	rc = device_create_file(&efx->pci_dev->dev, &dev_attr_mcdi_logging);
+	if (rc) {
+		netif_err(efx, drv, efx->net_dev,
+			  "failed to init net dev attributes\n");
+		goto fail_attr_mcdi_logging;
+	}
+#endif
 
 	return 0;
 
+#ifdef CONFIG_SFC_MCDI_LOGGING
+fail_attr_mcdi_logging:
+	device_remove_file(&efx->pci_dev->dev, &dev_attr_phy_type);
+#endif
 fail_registered:
 	rtnl_lock();
 	efx_dissociate(efx);
@@ -2404,13 +2438,14 @@ static void efx_unregister_netdev(struct efx_nic *efx)
 
 	BUG_ON(netdev_priv(efx->net_dev) != efx);
 
-	strlcpy(efx->name, pci_name(efx->pci_dev), sizeof(efx->name));
-	device_remove_file(&efx->pci_dev->dev, &dev_attr_phy_type);
-
-	rtnl_lock();
-	unregister_netdevice(efx->net_dev);
-	efx->state = STATE_UNINIT;
-	rtnl_unlock();
+	if (efx_dev_registered(efx)) {
+		strlcpy(efx->name, pci_name(efx->pci_dev), sizeof(efx->name));
+#ifdef CONFIG_SFC_MCDI_LOGGING
+		device_remove_file(&efx->pci_dev->dev, &dev_attr_mcdi_logging);
+#endif
+		device_remove_file(&efx->pci_dev->dev, &dev_attr_phy_type);
+		unregister_netdev(efx->net_dev);
+	}
 }
 
 /**************************************************************************

drivers/net/ethernet/sfc/mcdi.c

@@ -8,6 +8,7 @@
  */
 
 #include <linux/delay.h>
+#include <linux/moduleparam.h>
 #include <asm/cmpxchg.h>
 #include "net_driver.h"
 #include "nic.h"
@@ -54,18 +55,32 @@ static int efx_mcdi_drv_attach(struct efx_nic *efx, bool driver_operating,
 static bool efx_mcdi_poll_once(struct efx_nic *efx);
 static void efx_mcdi_abandon(struct efx_nic *efx);
 
+#ifdef CONFIG_SFC_MCDI_LOGGING
+static bool mcdi_logging_default;
+module_param(mcdi_logging_default, bool, 0644);
+MODULE_PARM_DESC(mcdi_logging_default,
+		 "Enable MCDI logging on newly-probed functions");
+#endif
+
 int efx_mcdi_init(struct efx_nic *efx)
 {
 	struct efx_mcdi_iface *mcdi;
 	bool already_attached;
-	int rc;
+	int rc = -ENOMEM;
 
 	efx->mcdi = kzalloc(sizeof(*efx->mcdi), GFP_KERNEL);
 	if (!efx->mcdi)
-		return -ENOMEM;
+		goto fail;
 
 	mcdi = efx_mcdi(efx);
 	mcdi->efx = efx;
+#ifdef CONFIG_SFC_MCDI_LOGGING
+	/* consuming code assumes buffer is page-sized */
+	mcdi->logging_buffer = (char *)__get_free_page(GFP_KERNEL);
+	if (!mcdi->logging_buffer)
+		goto fail1;
+	mcdi->logging_enabled = mcdi_logging_default;
+#endif
 	init_waitqueue_head(&mcdi->wq);
 	spin_lock_init(&mcdi->iface_lock);
 	mcdi->state = MCDI_STATE_QUIESCENT;
@@ -81,7 +96,7 @@ int efx_mcdi_init(struct efx_nic *efx)
 	/* Recover from a failed assertion before probing */
 	rc = efx_mcdi_handle_assertion(efx);
 	if (rc)
-		return rc;
+		goto fail2;
 
 	/* Let the MC (and BMC, if this is a LOM) know that the driver
 	 * is loaded. We should do this before we reset the NIC.
@@ -90,7 +105,7 @@ int efx_mcdi_init(struct efx_nic *efx)
 	if (rc) {
 		netif_err(efx, probe, efx->net_dev,
 			  "Unable to register driver with MCPU\n");
-		return rc;
+		goto fail2;
 	}
 	if (already_attached)
 		/* Not a fatal error */
@@ -102,6 +117,15 @@ int efx_mcdi_init(struct efx_nic *efx)
 		efx->primary = efx;
 
 	return 0;
+fail2:
+#ifdef CONFIG_SFC_MCDI_LOGGING
+	free_page((unsigned long)mcdi->logging_buffer);
+fail1:
+#endif
+	kfree(efx->mcdi);
+	efx->mcdi = NULL;
+fail:
+	return rc;
 }
 
 void efx_mcdi_fini(struct efx_nic *efx)
@@ -114,13 +138,20 @@ void efx_mcdi_fini(struct efx_nic *efx)
 	/* Relinquish the device (back to the BMC, if this is a LOM) */
 	efx_mcdi_drv_attach(efx, false, NULL);
 
+#ifdef CONFIG_SFC_MCDI_LOGGING
+	free_page((unsigned long)efx->mcdi->iface.logging_buffer);
+#endif
+
 	kfree(efx->mcdi);
 }
 
 static void efx_mcdi_send_request(struct efx_nic *efx, unsigned cmd,
 				  const efx_dword_t *inbuf, size_t inlen)
 {
 	struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
+#ifdef CONFIG_SFC_MCDI_LOGGING
+	char *buf = mcdi->logging_buffer; /* page-sized */
+#endif
 	efx_dword_t hdr[2];
 	size_t hdr_len;
 	u32 xflags, seqno;
@@ -165,6 +196,31 @@ static void efx_mcdi_send_request(struct efx_nic *efx, unsigned cmd,
 		hdr_len = 8;
 	}
 
+#ifdef CONFIG_SFC_MCDI_LOGGING
+	if (mcdi->logging_enabled && !WARN_ON_ONCE(!buf)) {
+		int bytes = 0;
+		int i;
+		/* Lengths should always be a whole number of dwords, so scream
+		 * if they're not.
+		 */
+		WARN_ON_ONCE(hdr_len % 4);
+		WARN_ON_ONCE(inlen % 4);
+
+		/* We own the logging buffer, as only one MCDI can be in
+		 * progress on a NIC at any one time.  So no need for locking.
+		 */
+		for (i = 0; i < hdr_len / 4 && bytes < PAGE_SIZE; i++)
+			bytes += snprintf(buf + bytes, PAGE_SIZE - bytes,
+					  " %08x", le32_to_cpu(hdr[i].u32[0]));
+
+		for (i = 0; i < inlen / 4 && bytes < PAGE_SIZE; i++)
+			bytes += snprintf(buf + bytes, PAGE_SIZE - bytes,
+					  " %08x", le32_to_cpu(inbuf[i].u32[0]));
+
+		netif_info(efx, hw, efx->net_dev, "MCDI RPC REQ:%s\n", buf);
+	}
+#endif
+
 	efx->type->mcdi_request(efx, hdr, hdr_len, inbuf, inlen);
 
 	mcdi->new_epoch = false;
@@ -206,6 +262,9 @@ static void efx_mcdi_read_response_header(struct efx_nic *efx)
 {
 	struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
 	unsigned int respseq, respcmd, error;
+#ifdef CONFIG_SFC_MCDI_LOGGING
+	char *buf = mcdi->logging_buffer; /* page-sized */
+#endif
 	efx_dword_t hdr;
 
 	efx->type->mcdi_read_response(efx, &hdr, 0, 4);
@@ -223,6 +282,39 @@ static void efx_mcdi_read_response_header(struct efx_nic *efx)
 			EFX_DWORD_FIELD(hdr, MC_CMD_V2_EXTN_IN_ACTUAL_LEN);
 	}
 
+#ifdef CONFIG_SFC_MCDI_LOGGING
+	if (mcdi->logging_enabled && !WARN_ON_ONCE(!buf)) {
+		size_t hdr_len, data_len;
+		int bytes = 0;
+		int i;
+
+		WARN_ON_ONCE(mcdi->resp_hdr_len % 4);
+		hdr_len = mcdi->resp_hdr_len / 4;
+		/* MCDI_DECLARE_BUF ensures that underlying buffer is padded
+		 * to dword size, and the MCDI buffer is always dword size
+		 */
+		data_len = DIV_ROUND_UP(mcdi->resp_data_len, 4);
+
+		/* We own the logging buffer, as only one MCDI can be in
+		 * progress on a NIC at any one time.  So no need for locking.
+		 */
+		for (i = 0; i < hdr_len && bytes < PAGE_SIZE; i++) {
+			efx->type->mcdi_read_response(efx, &hdr, (i * 4), 4);
+			bytes += snprintf(buf + bytes, PAGE_SIZE - bytes,
+					  " %08x", le32_to_cpu(hdr.u32[0]));
+		}
+
+		for (i = 0; i < data_len && bytes < PAGE_SIZE; i++) {
+			efx->type->mcdi_read_response(efx, &hdr,
+					mcdi->resp_hdr_len + (i * 4), 4);
+			bytes += snprintf(buf + bytes, PAGE_SIZE - bytes,
+					  " %08x", le32_to_cpu(hdr.u32[0]));
+		}
+
+		netif_info(efx, hw, efx->net_dev, "MCDI RPC RESP:%s\n", buf);
+	}
+#endif
+
 	if (error && mcdi->resp_data_len == 0) {
 		netif_err(efx, hw, efx->net_dev, "MC rebooted\n");
 		mcdi->resprc = -EIO;

drivers/net/ethernet/sfc/mcdi.h

@@ -58,6 +58,8 @@ enum efx_mcdi_mode {
  *	enabled
  * @async_list: Queue of asynchronous requests
  * @async_timer: Timer for asynchronous request timeout
+ * @logging_buffer: buffer that may be used to build MCDI tracing messages
+ * @logging_enabled: whether to trace MCDI
  */
 struct efx_mcdi_iface {
 	struct efx_nic *efx;
@@ -74,6 +76,10 @@ struct efx_mcdi_iface {
 	spinlock_t async_lock;
 	struct list_head async_list;
 	struct timer_list async_timer;
+#ifdef CONFIG_SFC_MCDI_LOGGING
+	char *logging_buffer;
+	bool logging_enabled;
+#endif
 };
 
 struct efx_mcdi_mon {