IB/hfi1, core, rdmavt: Driver fixes for 10/2/2017

index 5aea8f4..9471c40 100644
@@ -113,6 +113,12 @@ struct css_header {
 #define MU_SIZE		8
 #define EXPONENT_SIZE	4
 
+/* size of platform configuration partition */
+#define MAX_PLATFORM_CONFIG_FILE_SIZE 4096
+
+/* size of file of plaform configuration encoded in format version 4 */
+#define PLATFORM_CONFIG_FORMAT_4_FILE_SIZE 528
+
 /* the file itself */
 struct firmware_file {
 	struct css_header css_header;

@@ -1774,7 +1780,20 @@ int parse_platform_config(struct hfi1_devdata *dd)
 
 	/* Field is file size in DWORDs */
 	file_length = (*ptr) * 4;
-	ptr++;
+
+	/*
+	 * Length can't be larger than partition size. Assume platform
+	 * config format version 4 is being used. Interpret the file size
+	 * field as header instead by not moving the pointer.
+	 */
+	if (file_length > MAX_PLATFORM_CONFIG_FILE_SIZE) {
+		dd_dev_info(dd,
+			    "%s:File length out of bounds, using alternative format\n",
+			    __func__);
+		file_length = PLATFORM_CONFIG_FORMAT_4_FILE_SIZE;
+	} else {
+		ptr++;
+	}
 
 	if (file_length > dd->platform_config.size) {
 		dd_dev_info(dd, "%s:File claims to be larger than read size\n",

@@ -1789,7 +1808,8 @@ int parse_platform_config(struct hfi1_devdata *dd)
 
 	/*
 	 * In both cases where we proceed, using the self-reported file length
-	 * is the safer option
+	 * is the safer option. In case of old format a predefined value is
+	 * being used.
 	 */
 	while (ptr < (u32 *)(dd->platform_config.data + file_length)) {
 		header1 = *ptr;

index cb74ae8..44a2c8f 100644
@@ -390,6 +390,7 @@ struct hfi1_packet {
 /*
  * OPA 16B L2/L4 Encodings
  */
+#define OPA_16B_L4_9B		0x00
 #define OPA_16B_L2_TYPE		0x02
 #define OPA_16B_L4_IB_LOCAL	0x09
 #define OPA_16B_L4_IB_GLOBAL	0x0A

index 6dd0d63..fb63127 100644
@@ -334,7 +334,7 @@ void hfi1_trace_parse_16b_hdr(struct hfi1_16b_header *hdr,
 							 &__entry->dlid,
 							 &__entry->slid);
 
-				if (entry->l4 == OPA_16B_L4_IB_LOCAL)
+				if (__entry->l4 == OPA_16B_L4_IB_LOCAL)
 					ohdr = &opah->opah.u.oth;
 				else
 					ohdr = &opah->opah.u.l.oth;

@@ -348,6 +348,7 @@ void hfi1_trace_parse_16b_hdr(struct hfi1_16b_header *hdr,
 							 &__entry->psn,
 							 &__entry->qpn);
 			} else {
+				__entry->l4 = OPA_16B_L4_9B;
 				hfi1_trace_parse_9b_hdr(&opah->ibh, sc5,
 							&__entry->lnh,
 							&__entry->lver,

@@ -356,7 +357,7 @@ void hfi1_trace_parse_16b_hdr(struct hfi1_16b_header *hdr,
 							&__entry->len,
 							&__entry->dlid,
 							&__entry->slid);
-				if (entry->lnh == HFI1_LRH_BTH)
+				if (__entry->lnh == HFI1_LRH_BTH)
 					ohdr = &opah->ibh.u.oth;
 				else
 					ohdr = &opah->ibh.u.l.oth;

index 764a066..56bba8d 100644
@@ -6520,12 +6520,11 @@ static void _dc_start(struct hfi1_devdata *dd)
 	if (!dd->dc_shutdown)
 		return;
 
-	/* Take the 8051 out of reset */
-	write_csr(dd, DC_DC8051_CFG_RST, 0ull);
-	/* Wait until 8051 is ready */
-	if (wait_fm_ready(dd, TIMEOUT_8051_START))
-		dd_dev_err(dd, "%s: timeout starting 8051 firmware\n",
-			   __func__);
+	/*
+	 * Take the 8051 out of reset, wait until 8051 is ready, and set host
+	 * version bit.
+	 */
+	release_and_wait_ready_8051_firmware(dd);
 
 	/* Take away reset for LCB and RX FPE (set in lcb_shutdown). */
 	write_csr(dd, DCC_CFG_RESET, 0x10);

@@ -8595,30 +8594,23 @@ int write_lcb_csr(struct hfi1_devdata *dd, u32 addr, u64 data)
 }
 
 /*
+ * If the 8051 is in reset mode (dd->dc_shutdown == 1), this function
+ * will still continue executing.
+ *
  * Returns:
  *	< 0 = Linux error, not able to get access
  *	> 0 = 8051 command RETURN_CODE
  */
-static int do_8051_command(
-	struct hfi1_devdata *dd,
-	u32 type,
-	u64 in_data,
-	u64 *out_data)
+static int _do_8051_command(struct hfi1_devdata *dd, u32 type, u64 in_data,
+			    u64 *out_data)
 {
 	u64 reg, completed;
 	int return_code;
 	unsigned long timeout;
 
+	lockdep_assert_held(&dd->dc8051_lock);
 	hfi1_cdbg(DC8051, "type %d, data 0x%012llx", type, in_data);
 
-	mutex_lock(&dd->dc8051_lock);
-
-	/* We can't send any commands to the 8051 if it's in reset */
-	if (dd->dc_shutdown) {
-		return_code = -ENODEV;
-		goto fail;
-	}
-
 	/*
 	 * If an 8051 host command timed out previously, then the 8051 is
 	 * stuck.

@@ -8719,6 +8711,29 @@ static int do_8051_command(
 	write_csr(dd, DC_DC8051_CFG_HOST_CMD_0, 0);
 
 fail:
+	return return_code;
+}
+
+/*
+ * Returns:
+ *	< 0 = Linux error, not able to get access
+ *	> 0 = 8051 command RETURN_CODE
+ */
+static int do_8051_command(struct hfi1_devdata *dd, u32 type, u64 in_data,
+			   u64 *out_data)
+{
+	int return_code;
+
+	mutex_lock(&dd->dc8051_lock);
+	/* We can't send any commands to the 8051 if it's in reset */
+	if (dd->dc_shutdown) {
+		return_code = -ENODEV;
+		goto fail;
+	}
+
+	return_code = _do_8051_command(dd, type, in_data, out_data);
+
+fail:
 	mutex_unlock(&dd->dc8051_lock);
 	return return_code;
 }

@@ -8728,16 +8743,17 @@ static int set_physical_link_state(struct hfi1_devdata *dd, u64 state)
 	return do_8051_command(dd, HCMD_CHANGE_PHY_STATE, state, NULL);
 }
 
-int load_8051_config(struct hfi1_devdata *dd, u8 field_id,
-		     u8 lane_id, u32 config_data)
+int _load_8051_config(struct hfi1_devdata *dd, u8 field_id,
+		      u8 lane_id, u32 config_data)
 {
 	u64 data;
 	int ret;
 
+	lockdep_assert_held(&dd->dc8051_lock);
 	data = (u64)field_id << LOAD_DATA_FIELD_ID_SHIFT
 		| (u64)lane_id << LOAD_DATA_LANE_ID_SHIFT
 		| (u64)config_data << LOAD_DATA_DATA_SHIFT;
-	ret = do_8051_command(dd, HCMD_LOAD_CONFIG_DATA, data, NULL);
+	ret = _do_8051_command(dd, HCMD_LOAD_CONFIG_DATA, data, NULL);
 	if (ret != HCMD_SUCCESS) {
 		dd_dev_err(dd,
 			   "load 8051 config: field id %d, lane %d, err %d\n",

@@ -8746,6 +8762,18 @@ int load_8051_config(struct hfi1_devdata *dd, u8 field_id,
 	return ret;
 }
 
+int load_8051_config(struct hfi1_devdata *dd, u8 field_id,
+		     u8 lane_id, u32 config_data)
+{
+	int return_code;
+
+	mutex_lock(&dd->dc8051_lock);
+	return_code = _load_8051_config(dd, field_id, lane_id, config_data);
+	mutex_unlock(&dd->dc8051_lock);
+
+	return return_code;
+}
+
 /*
  * Read the 8051 firmware "registers".  Use the RAM directly.  Always
  * set the result, even on error.

@@ -8861,13 +8889,14 @@ int write_host_interface_version(struct hfi1_devdata *dd, u8 version)
 	u32 frame;
 	u32 mask;
 
+	lockdep_assert_held(&dd->dc8051_lock);
 	mask = (HOST_INTERFACE_VERSION_MASK << HOST_INTERFACE_VERSION_SHIFT);
 	read_8051_config(dd, RESERVED_REGISTERS, GENERAL_CONFIG, &frame);
 	/* Clear, then set field */
 	frame &= ~mask;
 	frame |= ((u32)version << HOST_INTERFACE_VERSION_SHIFT);
-	return load_8051_config(dd, RESERVED_REGISTERS, GENERAL_CONFIG,
-				frame);
+	return _load_8051_config(dd, RESERVED_REGISTERS, GENERAL_CONFIG,
+				 frame);
 }
 
 void read_misc_status(struct hfi1_devdata *dd, u8 *ver_major, u8 *ver_minor,

index 50b8645..213b6a3 100644
@@ -710,6 +710,7 @@ void read_misc_status(struct hfi1_devdata *dd, u8 *ver_major, u8 *ver_minor,
 		      u8 *ver_patch);
 int write_host_interface_version(struct hfi1_devdata *dd, u8 version);
 void read_guid(struct hfi1_devdata *dd);
+int release_and_wait_ready_8051_firmware(struct hfi1_devdata *dd);
 int wait_fm_ready(struct hfi1_devdata *dd, u32 mstimeout);
 void set_link_down_reason(struct hfi1_pportdata *ppd, u8 lcl_reason,
 			  u8 neigh_reason, u8 rem_reason);

84 lines not on this page · raw message

index e6e90f1..f68fca2 100644
@@ -97,15 +97,15 @@ static inline u32 opa_get_lid_from_gid(const union ib_gid *gid)
  * @dlid: The DLID
  * @slid: The SLID
  */
-static inline bool opa_is_extended_lid(u32 dlid, u32 slid)
+static inline bool opa_is_extended_lid(__be32 dlid, __be32 slid)
 {
 	if ((be32_to_cpu(dlid) >=
 	     be16_to_cpu(IB_MULTICAST_LID_BASE)) ||
 	    (be32_to_cpu(slid) >=
 	     be16_to_cpu(IB_MULTICAST_LID_BASE)))
 		return true;
-	else
-		return false;
+
+	return false;
 }
 
 /* Get multicast lid base */

index bcc4c2db81d0..234105716120 100644
@@ -4754,6 +4754,15 @@ static int __init mlx5_ib_init(void)
 {
 	int err;
 
+	uint32_t u1 = 0x2233;
+	uint32_t u2 = 0x4411;
+
+	__be32 b1 = cpu_to_be32(u1);
+	__be32 b2 = cpu_to_be32(u2);
+
+	printk(KERN_ERR "test: u1 %s u1\n", (u1 < u2 ) ? "<":">");
+	printk(KERN_ERR "test: b1 %s b1\n", (b1 < b2 ) ? "<":">");
+
 	mlx5_ib_odp_init();
 
 	err = mlx5_register_interface(&mlx5_ib_interface);

index 56bba8d..d2d72e0 100644
@@ -8743,8 +8743,8 @@ static int set_physical_link_state(struct hfi1_devdata *dd, u64 state)
 	return do_8051_command(dd, HCMD_CHANGE_PHY_STATE, state, NULL);
 }
 
-int _load_8051_config(struct hfi1_devdata *dd, u8 field_id,
-		      u8 lane_id, u32 config_data)
+static int _load_8051_config(struct hfi1_devdata *dd, u8 field_id,
+			     u8 lane_id, u32 config_data)
 {
 	u64 data;
 	int ret;

index 0eed3d8..89ab88c 100644
@@ -282,7 +282,6 @@ struct rvt_qp {
 	u32 remote_qpn;
 	u32 qkey;               /* QKEY for this QP (for UD or RD) */
 	u32 s_size;             /* send work queue size */
-	u32 s_ahgpsn;           /* set to the psn in the copy of the header */
 
 	u16 pmtu;		/* decoded from path_mtu */
 	u8 log_pmtu;		/* shift for pmtu */

@@ -344,7 +343,6 @@ struct rvt_qp {
 	struct rvt_swqe *s_wqe;
 	struct rvt_sge_state s_sge;     /* current send request data */
 	struct rvt_mregion *s_rdma_mr;
-	u32 s_cur_size;         /* size of send packet in bytes */
 	u32 s_len;              /* total length of s_sge */
 	u32 s_rdma_read_len;    /* total length of s_rdma_read_sge */
 	u32 s_last_psn;         /* last response PSN processed */

@@ -358,8 +356,10 @@ struct rvt_qp {
 	u32 s_acked;            /* last un-ACK'ed entry */
 	u32 s_last;             /* last completed entry */
 	u32 s_lsn;              /* limit sequence number (credit) */
-	u16 s_hdrwords;         /* size of s_hdr in 32 bit words */
+	u32 s_ahgpsn;           /* set to the psn in the copy of the header */
+	u16 s_cur_size;         /* size of send packet in bytes */
 	u16 s_rdma_ack_cnt;
+	u8 s_hdrwords;         /* size of s_hdr in 32 bit words */
 	s8 s_ahgidx;
 	u8 s_state;             /* opcode of last packet sent */
 	u8 s_ack_state;         /* opcode of packet to ACK */

index c1696e6..603acaf 100644
@@ -229,7 +229,16 @@ static void recv_handler(struct ib_mad_agent *agent,
 	packet->mad.hdr.status	   = 0;
 	packet->mad.hdr.length	   = hdr_size(file) + mad_recv_wc->mad_len;
 	packet->mad.hdr.qpn	   = cpu_to_be32(mad_recv_wc->wc->src_qp);
-	packet->mad.hdr.lid	   = ib_lid_be16(mad_recv_wc->wc->slid);
+	/*
+	 * On OPA devices it is okay to lose the upper 16 bits of LID as this
+	 * information is obtained elsewhere. Mask off the upper 16 bits.
+	 */
+	if (agent->device->port_immutable[agent->port_num].core_cap_flags &
+	    RDMA_CORE_PORT_INTEL_OPA)
+		packet->mad.hdr.lid = ib_lid_be16(0xFFFF &
+						  mad_recv_wc->wc->slid);
+	else
+		packet->mad.hdr.lid = ib_lid_be16(mad_recv_wc->wc->slid);
 	packet->mad.hdr.sl	   = mad_recv_wc->wc->sl;
 	packet->mad.hdr.path_bits  = mad_recv_wc->wc->dlid_path_bits;
 	packet->mad.hdr.pkey_index = mad_recv_wc->wc->pkey_index;

index f4c0ffc..07b80fa 100644
@@ -4293,7 +4293,6 @@ static int opa_local_smp_check(struct hfi1_ibport *ibp,
 			       const struct ib_wc *in_wc)
 {
 	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
-	u16 slid = ib_lid_cpu16(in_wc->slid);
 	u16 pkey;
 
 	if (in_wc->pkey_index >= ARRAY_SIZE(ppd->pkeys))

@@ -4320,7 +4319,11 @@ static int opa_local_smp_check(struct hfi1_ibport *ibp,
 	 */
 	if (pkey == LIM_MGMT_P_KEY || pkey == FULL_MGMT_P_KEY)
 		return 0;
-	ingress_pkey_table_fail(ppd, pkey, slid);
+	/*
+	 * On OPA devices it is okay to lose the upper 16 bits of LID as this
+	 * information is obtained elsewhere. Mask off the upper 16 bits.
+	 */
+	ingress_pkey_table_fail(ppd, pkey, ib_lid_cpu16(0xFFFF & in_wc->slid));
 	return 1;
 }
 

index 680cfd4..764a066 100644
@@ -13076,7 +13076,7 @@ static int request_msix_irqs(struct hfi1_devdata *dd)
 	first_sdma = last_general;
 	last_sdma = first_sdma + dd->num_sdma;
 	first_rx = last_sdma;
-	last_rx = first_rx + dd->n_krcv_queues + HFI1_NUM_VNIC_CTXT;
+	last_rx = first_rx + dd->n_krcv_queues + dd->num_vnic_contexts;
 
 	/* VNIC MSIx interrupts get mapped when VNIC contexts are created */
 	dd->first_dyn_msix_idx = first_rx + dd->n_krcv_queues;

@@ -13282,8 +13282,9 @@ static int set_up_interrupts(struct hfi1_devdata *dd)
 	 *		slow source, SDMACleanupDone)
 	 *	N interrupts - one per used SDMA engine
 	 *	M interrupt - one per kernel receive context
+	 *	V interrupt - one for each VNIC context
 	 */
-	total = 1 + dd->num_sdma + dd->n_krcv_queues + HFI1_NUM_VNIC_CTXT;
+	total = 1 + dd->num_sdma + dd->n_krcv_queues + dd->num_vnic_contexts;
 
 	/* ask for MSI-X interrupts */
 	request = request_msix(dd, total);

@@ -13344,10 +13345,12 @@ static int set_up_interrupts(struct hfi1_devdata *dd)
  *                             in array of contexts
  *	freectxts  - number of free user contexts
  *	num_send_contexts - number of PIO send contexts being used
+ *	num_vnic_contexts - number of contexts reserved for VNIC
  */
 static int set_up_context_variables(struct hfi1_devdata *dd)
 {
 	unsigned long num_kernel_contexts;
+	u16 num_vnic_contexts = HFI1_NUM_VNIC_CTXT;
 	int total_contexts;
 	int ret;
 	unsigned ngroups;

@@ -13381,6 +13384,14 @@ static int set_up_context_variables(struct hfi1_devdata *dd)
 			   num_kernel_contexts);
 		num_kernel_contexts = dd->chip_send_contexts - num_vls - 1;
 	}
+
+	/* Accommodate VNIC contexts if possible */
+	if ((num_kernel_contexts + num_vnic_contexts) > dd->chip_rcv_contexts) {
+		dd_dev_err(dd, "No receive contexts available for VNIC\n");
+		num_vnic_contexts = 0;
+	}
+	total_contexts = num_kernel_contexts + num_vnic_contexts;
+
 	/*
 	 * User contexts:
 	 *	- default to 1 user context per real (non-HT) CPU core if

@@ -13390,19 +13401,16 @@ static int set_up_context_variables(struct hfi1_devdata *dd)
 		num_user_contexts =
 			cpumask_weight(&node_affinity.real_cpu_mask);
 
-	total_contexts = num_kernel_contexts + num_user_contexts;
-
 	/*
 	 * Adjust the counts given a global max.
 	 */
-	if (total_contexts > dd->chip_rcv_contexts) {
+	if (total_contexts + num_user_contexts > dd->chip_rcv_contexts) {
 		dd_dev_err(dd,
 			   "Reducing # user receive contexts to: %d, from %d\n",
-			   (int)(dd->chip_rcv_contexts - num_kernel_contexts),
+			   (int)(dd->chip_rcv_contexts - total_contexts),
 			   (int)num_user_contexts);
-		num_user_contexts = dd->chip_rcv_contexts - num_kernel_contexts;
 		/* recalculate */
-		total_contexts = num_kernel_contexts + num_user_contexts;
+		num_user_contexts = dd->chip_rcv_contexts - total_contexts;
 	}
 
 	/* each user context requires an entry in the RMT */

@@ -13415,25 +13423,24 @@ static int set_up_context_variables(struct hfi1_devdata *dd)
 			   user_rmt_reduced);
 		/* recalculate */
 		num_user_contexts = user_rmt_reduced;
-		total_contexts = num_kernel_contexts + num_user_contexts;
 	}
 
-	/* Accommodate VNIC contexts */
-	if ((total_contexts + HFI1_NUM_VNIC_CTXT) <= dd->chip_rcv_contexts)
-		total_contexts += HFI1_NUM_VNIC_CTXT;
+	total_contexts += num_user_contexts;
 
 	/* the first N are kernel contexts, the rest are user/vnic contexts */
 	dd->num_rcv_contexts = total_contexts;
 	dd->n_krcv_queues = num_kernel_contexts;
 	dd->first_dyn_alloc_ctxt = num_kernel_contexts;
+	dd->num_vnic_contexts = num_vnic_contexts;
 	dd->num_user_contexts = num_user_contexts;
 	dd->freectxts = num_user_contexts;
 	dd_dev_info(dd,
-		    "rcv contexts: chip %d, used %d (kernel %d, user %d)\n",
+		    "rcv contexts: chip %d, used %d (kernel %d, vnic %u, user %u)\n",
 		    (int)dd->chip_rcv_contexts,
 		    (int)dd->num_rcv_contexts,
 		    (int)dd->n_krcv_queues,
-		    (int)dd->num_rcv_contexts - dd->n_krcv_queues);
+		    dd->num_vnic_contexts,
+		    dd->num_user_contexts);
 
 	/*
 	 * Receive array allocation:

index 44a2c8f..2f3c830 100644
@@ -1049,6 +1049,8 @@ struct hfi1_devdata {
 	u64 z_send_schedule;
 
 	u64 __percpu *send_schedule;
+	/* number of reserved contexts for VNIC usage */
+	u16 num_vnic_contexts;
 	/* number of receive contexts in use by the driver */
 	u32 num_rcv_contexts;
 	/* number of pio send contexts in use by the driver */

index 6d2702e..25e8673 100644
@@ -543,7 +543,7 @@ static ssize_t show_nctxts(struct device *device,
 	 * give a more accurate picture of total contexts available.
 	 */
 	return scnprintf(buf, PAGE_SIZE, "%u\n",
-			 min(dd->num_rcv_contexts - dd->first_dyn_alloc_ctxt,
+			 min(dd->num_user_contexts,
 			     (u32)dd->sc_sizes[SC_USER].count));
 }
 

index f419cbb..1a17708 100644
@@ -840,6 +840,9 @@ struct net_device *hfi1_vnic_alloc_rn(struct ib_device *device,
 	struct rdma_netdev *rn;
 	int i, size, rc;
 
+	if (!dd->num_vnic_contexts)
+		return ERR_PTR(-ENOMEM);
+
 	if (!port_num || (port_num > dd->num_pports))
 		return ERR_PTR(-EINVAL);
 

@@ -848,7 +851,7 @@ struct net_device *hfi1_vnic_alloc_rn(struct ib_device *device,
 
 	size = sizeof(struct opa_vnic_rdma_netdev) + sizeof(*vinfo);
 	netdev = alloc_netdev_mqs(size, name, name_assign_type, setup,
-				  dd->chip_sdma_engines, HFI1_NUM_VNIC_CTXT);
+				  dd->chip_sdma_engines, dd->num_vnic_contexts);
 	if (!netdev)
 		return ERR_PTR(-ENOMEM);
 

@@ -856,7 +859,7 @@ struct net_device *hfi1_vnic_alloc_rn(struct ib_device *device,
 	vinfo = opa_vnic_dev_priv(netdev);
 	vinfo->dd = dd;
 	vinfo->num_tx_q = dd->chip_sdma_engines;
-	vinfo->num_rx_q = HFI1_NUM_VNIC_CTXT;
+	vinfo->num_rx_q = dd->num_vnic_contexts;
 	vinfo->netdev = netdev;
 	rn->free_rdma_netdev = hfi1_vnic_free_rn;
 	rn->set_id = hfi1_vnic_set_vesw_id;