[PATCH net v2 0/3] nfp: wait more carefully for card init

[PATCH net v2 0/3] nfp: wait more carefully for card init

[Jakub Kicinski]

Hi!

The first patch is a small fix for flower offload, we need a whitelist
of supported matches, otherwise the unsupported ones will be ignored.

The second and the third patch are adding wait/polling to the probe path.
We had reports of driver failing probe because it couldn't find the 
control process (NSP) on the card.  Turns out the NSP will only announce
its existence after it's fully initialized.  Until now we assumed it 
will be reachable, just not processing commands (hence we wait for
a NOOP command to execute successfully).

v2:
 - fix a bad merge which resulted in a build warning and retest.

Jakub Kicinski (2):
  nfp: wait for board state before talking to the NSP
  nfp: wait for the NSP resource to appear on boot

Pieter Jansen van Vuuren (1):
  nfp: add whitelist of supported flow dissector

 .../net/ethernet/netronome/nfp/flower/offload.c    | 13 ++++++
 drivers/net/ethernet/netronome/nfp/nfp_main.c      | 47 ++++++++++++++++++++++
 drivers/net/ethernet/netronome/nfp/nfp_net_main.c  | 23 -----------
 drivers/net/ethernet/netronome/nfp/nfpcore/nfp.h   |  2 +
 .../ethernet/netronome/nfp/nfpcore/nfp_resource.c  | 45 +++++++++++++++++++++
 5 files changed, 107 insertions(+), 23 deletions(-)

-- 
2.14.1

[PATCH net v2 1/3] nfp: add whitelist of supported flow dissector

[Jakub Kicinski]

From: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>

Previously we did not check the flow dissector against a list of allowed
and supported flow key dissectors. This patch introduces such a list and
correctly rejects unsupported flow keys.

Fixes: 43f84b72c50d ("nfp: add metadata to each flow offload")
Signed-off-by: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/ethernet/netronome/nfp/flower/offload.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index d396183108f7..a18b4d2b1d3e 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -44,6 +44,16 @@
 #include "../nfp_net.h"
 #include "../nfp_port.h"
 
+#define NFP_FLOWER_WHITELIST_DISSECTOR \
+	(BIT(FLOW_DISSECTOR_KEY_CONTROL) | \
+	 BIT(FLOW_DISSECTOR_KEY_BASIC) | \
+	 BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | \
+	 BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | \
+	 BIT(FLOW_DISSECTOR_KEY_PORTS) | \
+	 BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | \
+	 BIT(FLOW_DISSECTOR_KEY_VLAN) | \
+	 BIT(FLOW_DISSECTOR_KEY_IP))
+
 static int
 nfp_flower_xmit_flow(struct net_device *netdev,
 		     struct nfp_fl_payload *nfp_flow, u8 mtype)
@@ -112,6 +122,9 @@ nfp_flower_calculate_key_layers(struct nfp_fl_key_ls *ret_key_ls,
 	u8 key_layer;
 	int key_size;
 
+	if (flow->dissector->used_keys & ~NFP_FLOWER_WHITELIST_DISSECTOR)
+		return -EOPNOTSUPP;
+
 	if (dissector_uses_key(flow->dissector,
 			       FLOW_DISSECTOR_KEY_ENC_CONTROL)) {
 		struct flow_dissector_key_control *mask_enc_ctl =
-- 
2.14.1

[PATCH net v2 2/3] nfp: wait for board state before talking to the NSP

[Jakub Kicinski]

Board state informs us which low-level initialization stages the card
has completed.  We should wait for the card to be fully initialized
before trying to communicate with it, not only before we configure
passing traffic.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/ethernet/netronome/nfp/nfp_main.c     | 43 +++++++++++++++++++++++
 drivers/net/ethernet/netronome/nfp/nfp_net_main.c | 23 ------------
 2 files changed, 43 insertions(+), 23 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.c b/drivers/net/ethernet/netronome/nfp/nfp_main.c
index f055b1774d65..424707d41fbd 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_main.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_main.c
@@ -74,6 +74,45 @@ static const struct pci_device_id nfp_pci_device_ids[] = {
 };
 MODULE_DEVICE_TABLE(pci, nfp_pci_device_ids);
 
+static bool nfp_board_ready(struct nfp_pf *pf)
+{
+	const char *cp;
+	long state;
+	int err;
+
+	cp = nfp_hwinfo_lookup(pf->hwinfo, "board.state");
+	if (!cp)
+		return false;
+
+	err = kstrtol(cp, 0, &state);
+	if (err < 0)
+		return false;
+
+	return state == 15;
+}
+
+static int nfp_pf_board_state_wait(struct nfp_pf *pf)
+{
+	const unsigned long wait_until = jiffies + 10 * HZ;
+
+	while (!nfp_board_ready(pf)) {
+		if (time_is_before_eq_jiffies(wait_until)) {
+			nfp_err(pf->cpp, "NFP board initialization timeout\n");
+			return -EINVAL;
+		}
+
+		nfp_info(pf->cpp, "waiting for board initialization\n");
+		if (msleep_interruptible(500))
+			return -ERESTARTSYS;
+
+		/* Refresh cached information */
+		kfree(pf->hwinfo);
+		pf->hwinfo = nfp_hwinfo_read(pf->cpp);
+	}
+
+	return 0;
+}
+
 static int nfp_pcie_sriov_read_nfd_limit(struct nfp_pf *pf)
 {
 	int err;
@@ -425,6 +464,10 @@ static int nfp_pci_probe(struct pci_dev *pdev,
 		 nfp_hwinfo_lookup(pf->hwinfo, "assembly.revision"),
 		 nfp_hwinfo_lookup(pf->hwinfo, "cpld.version"));
 
+	err = nfp_pf_board_state_wait(pf);
+	if (err)
+		goto err_hwinfo_free;
+
 	err = devlink_register(devlink, &pdev->dev);
 	if (err)
 		goto err_hwinfo_free;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c
index 5abb9ba31e7d..ff373acd28f3 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c
@@ -64,23 +64,6 @@
 
 #define NFP_PF_CSR_SLICE_SIZE	(32 * 1024)
 
-static int nfp_is_ready(struct nfp_pf *pf)
-{
-	const char *cp;
-	long state;
-	int err;
-
-	cp = nfp_hwinfo_lookup(pf->hwinfo, "board.state");
-	if (!cp)
-		return 0;
-
-	err = kstrtol(cp, 0, &state);
-	if (err < 0)
-		return 0;
-
-	return state == 15;
-}
-
 /**
  * nfp_net_get_mac_addr() - Get the MAC address.
  * @pf:       NFP PF handle
@@ -725,12 +708,6 @@ int nfp_net_pci_probe(struct nfp_pf *pf)
 
 	INIT_WORK(&pf->port_refresh_work, nfp_net_refresh_vnics);
 
-	/* Verify that the board has completed initialization */
-	if (!nfp_is_ready(pf)) {
-		nfp_err(pf->cpp, "NFP is not ready for NIC operation.\n");
-		return -EINVAL;
-	}
-
 	if (!pf->rtbl) {
 		nfp_err(pf->cpp, "No %s, giving up.\n",
 			pf->fw_loaded ? "symbol table" : "firmware found");
-- 
2.14.1

[PATCH net v2 3/3] nfp: wait for the NSP resource to appear on boot

[Jakub Kicinski]

The control process (NSP) may take some time to complete its
initialization.  This is not a problem on most servers, but
on very fast-booting machines it may not be ready for operation
when driver probes the device.  There is also a version of the
flash in the wild where NSP tries to train the links as part
of init.  To wait for NSP initialization we should make sure
its resource has already been added to the resource table.
NSP adds itself there as last step of init.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/ethernet/netronome/nfp/nfp_main.c      |  4 ++
 drivers/net/ethernet/netronome/nfp/nfpcore/nfp.h   |  2 +
 .../ethernet/netronome/nfp/nfpcore/nfp_resource.c  | 45 ++++++++++++++++++++++
 3 files changed, 51 insertions(+)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.c b/drivers/net/ethernet/netronome/nfp/nfp_main.c
index 424707d41fbd..f8fa63b66739 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_main.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_main.c
@@ -351,6 +351,10 @@ static int nfp_nsp_init(struct pci_dev *pdev, struct nfp_pf *pf)
 	struct nfp_nsp *nsp;
 	int err;
 
+	err = nfp_resource_wait(pf->cpp, NFP_RESOURCE_NSP, 30);
+	if (err)
+		return err;
+
 	nsp = nfp_nsp_open(pf->cpp);
 	if (IS_ERR(nsp)) {
 		err = PTR_ERR(nsp);
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp.h b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp.h
index 1a8d04a1e113..3ce51f03126f 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp.h
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp.h
@@ -97,6 +97,8 @@ nfp_resource_acquire(struct nfp_cpp *cpp, const char *name);
 
 void nfp_resource_release(struct nfp_resource *res);
 
+int nfp_resource_wait(struct nfp_cpp *cpp, const char *name, unsigned int secs);
+
 u32 nfp_resource_cpp_id(struct nfp_resource *res);
 
 const char *nfp_resource_name(struct nfp_resource *res);
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_resource.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_resource.c
index 072612263dab..b1dd13ff282b 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_resource.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_resource.c
@@ -249,6 +249,51 @@ void nfp_resource_release(struct nfp_resource *res)
 	kfree(res);
 }
 
+/**
+ * nfp_resource_wait() - Wait for resource to appear
+ * @cpp:	NFP CPP handle
+ * @name:	Name of the resource
+ * @secs:	Number of seconds to wait
+ *
+ * Wait for resource to appear in the resource table, grab and release
+ * its lock.  The wait is jiffies-based, don't expect fine granularity.
+ *
+ * Return: 0 on success, errno otherwise.
+ */
+int nfp_resource_wait(struct nfp_cpp *cpp, const char *name, unsigned int secs)
+{
+	unsigned long warn_at = jiffies + NFP_MUTEX_WAIT_FIRST_WARN * HZ;
+	unsigned long err_at = jiffies + secs * HZ;
+	struct nfp_resource *res;
+
+	while (true) {
+		res = nfp_resource_acquire(cpp, name);
+		if (!IS_ERR(res)) {
+			nfp_resource_release(res);
+			return 0;
+		}
+
+		if (PTR_ERR(res) != -ENOENT) {
+			nfp_err(cpp, "error waiting for resource %s: %ld\n",
+				name, PTR_ERR(res));
+			return PTR_ERR(res);
+		}
+		if (time_is_before_eq_jiffies(err_at)) {
+			nfp_err(cpp, "timeout waiting for resource %s\n", name);
+			return -ETIMEDOUT;
+		}
+		if (time_is_before_eq_jiffies(warn_at)) {
+			warn_at = jiffies + NFP_MUTEX_WAIT_NEXT_WARN * HZ;
+			nfp_info(cpp, "waiting for NFP resource %s\n", name);
+		}
+		if (msleep_interruptible(10)) {
+			nfp_err(cpp, "wait for resource %s interrupted\n",
+				name);
+			return -ERESTARTSYS;
+		}
+	}
+}
+
 /**
  * nfp_resource_cpp_id() - Return the cpp_id of a resource handle
  * @res:	NFP Resource handle
-- 
2.14.1