Merge tag 'perf-core-for-mingo-4.18-20180516' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

- Add '-e intel_pt//u' test to the 'parse-events' 'perf test' entry,
  to help avoiding regressions in the events parser such as one
  that caused a revert in v4.17-rc (Arnaldo Carvalho de Melo)

- Fix NULL return handling in bpf__prepare_load() (YueHaibing)

- Warn about 'perf buildid-cache --purge-all' failures (Ravi Bangoria)

- Add infrastructure to help in writing eBPF C programs to be used
  with '-e name.c' type events in tools such as 'record' and 'trace',
  with headers for common constructs and an examples directory that
  will get populated as we add more such helpers and the 'perf bpf'
  branch that Jiri Olsa has been working on (Arnaldo Carvalho de Melo)

- Handle uncore event aliases in small groups properly (Kan Liang)

- Use the "_stest" symbol to identify the kernel map when loading kcore (Adrian Hunter)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

9 files changed, 100 insertions, 41 deletions

diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c
index a97055dd4fbd..b5fab55cc275 100644
--- a/drivers/infiniband/hw/hfi1/affinity.c
+++ b/drivers/infiniband/hw/hfi1/affinity.c
@@ -412,7 +412,6 @@ static void hfi1_cleanup_sdma_notifier(struct hfi1_msix_entry *msix)
 static int get_irq_affinity(struct hfi1_devdata *dd,
 			    struct hfi1_msix_entry *msix)
 {
-	int ret;
 	cpumask_var_t diff;
 	struct hfi1_affinity_node *entry;
 	struct cpu_mask_set *set = NULL;
@@ -424,10 +423,6 @@ static int get_irq_affinity(struct hfi1_devdata *dd,
 	extra[0] = '\0';
 	cpumask_clear(&msix->mask);
 
-	ret = zalloc_cpumask_var(&diff, GFP_KERNEL);
-	if (!ret)
-		return -ENOMEM;
-
 	entry = node_affinity_lookup(dd->node);
 
 	switch (msix->type) {
@@ -458,6 +453,9 @@ static int get_irq_affinity(struct hfi1_devdata *dd,
 	 * finds its CPU here.
 	 */
 	if (cpu == -1 && set) {
+		if (!zalloc_cpumask_var(&diff, GFP_KERNEL))
+			return -ENOMEM;
+
 		if (cpumask_equal(&set->mask, &set->used)) {
 			/*
 			 * We've used up all the CPUs, bump up the generation
@@ -469,6 +467,8 @@ static int get_irq_affinity(struct hfi1_devdata *dd,
 		cpumask_andnot(diff, &set->mask, &set->used);
 		cpu = cpumask_first(diff);
 		cpumask_set_cpu(cpu, &set->used);
+
+		free_cpumask_var(diff);
 	}
 
 	cpumask_set_cpu(cpu, &msix->mask);
@@ -482,7 +482,6 @@ static int get_irq_affinity(struct hfi1_devdata *dd,
 		hfi1_setup_sdma_notifier(msix);
 	}
 
-	free_cpumask_var(diff);
 	return 0;
 }
 
diff --git a/drivers/infiniband/hw/hfi1/driver.c b/drivers/infiniband/hw/hfi1/driver.c
index 46d1475b2154..bd837a048bf4 100644
--- a/drivers/infiniband/hw/hfi1/driver.c
+++ b/drivers/infiniband/hw/hfi1/driver.c
@@ -433,31 +433,43 @@ void hfi1_process_ecn_slowpath(struct rvt_qp *qp, struct hfi1_packet *pkt,
 			       bool do_cnp)
 {
 	struct hfi1_ibport *ibp = to_iport(qp->ibqp.device, qp->port_num);
+	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
 	struct ib_other_headers *ohdr = pkt->ohdr;
 	struct ib_grh *grh = pkt->grh;
 	u32 rqpn = 0, bth1;
-	u16 pkey, rlid, dlid = ib_get_dlid(pkt->hdr);
+	u16 pkey;
+	u32 rlid, slid, dlid = 0;
 	u8 hdr_type, sc, svc_type;
 	bool is_mcast = false;
 
+	/* can be called from prescan */
 	if (pkt->etype == RHF_RCV_TYPE_BYPASS) {
 		is_mcast = hfi1_is_16B_mcast(dlid);
 		pkey = hfi1_16B_get_pkey(pkt->hdr);
 		sc = hfi1_16B_get_sc(pkt->hdr);
+		dlid = hfi1_16B_get_dlid(pkt->hdr);
+		slid = hfi1_16B_get_slid(pkt->hdr);
 		hdr_type = HFI1_PKT_TYPE_16B;
 	} else {
 		is_mcast = (dlid > be16_to_cpu(IB_MULTICAST_LID_BASE)) &&
 			   (dlid != be16_to_cpu(IB_LID_PERMISSIVE));
 		pkey = ib_bth_get_pkey(ohdr);
 		sc = hfi1_9B_get_sc5(pkt->hdr, pkt->rhf);
+		dlid = ib_get_dlid(pkt->hdr);
+		slid = ib_get_slid(pkt->hdr);
 		hdr_type = HFI1_PKT_TYPE_9B;
 	}
 
 	switch (qp->ibqp.qp_type) {
+	case IB_QPT_UD:
+		dlid = ppd->lid;
+		rlid = slid;
+		rqpn = ib_get_sqpn(pkt->ohdr);
+		svc_type = IB_CC_SVCTYPE_UD;
+		break;
 	case IB_QPT_SMI:
 	case IB_QPT_GSI:
-	case IB_QPT_UD:
-		rlid = ib_get_slid(pkt->hdr);
+		rlid = slid;
 		rqpn = ib_get_sqpn(pkt->ohdr);
 		svc_type = IB_CC_SVCTYPE_UD;
 		break;
@@ -482,7 +494,6 @@ void hfi1_process_ecn_slowpath(struct rvt_qp *qp, struct hfi1_packet *pkt,
 					      dlid, rlid, sc, grh);
 
 	if (!is_mcast && (bth1 & IB_BECN_SMASK)) {
-		struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
 		u32 lqpn = bth1 & RVT_QPN_MASK;
 		u8 sl = ibp->sc_to_sl[sc];
 
diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index 32c48265405e..cac2c62bc42d 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -1537,13 +1537,13 @@ void set_link_ipg(struct hfi1_pportdata *ppd);
 void process_becn(struct hfi1_pportdata *ppd, u8 sl, u32 rlid, u32 lqpn,
 		  u32 rqpn, u8 svc_type);
 void return_cnp(struct hfi1_ibport *ibp, struct rvt_qp *qp, u32 remote_qpn,
-		u32 pkey, u32 slid, u32 dlid, u8 sc5,
+		u16 pkey, u32 slid, u32 dlid, u8 sc5,
 		const struct ib_grh *old_grh);
 void return_cnp_16B(struct hfi1_ibport *ibp, struct rvt_qp *qp,
-		    u32 remote_qpn, u32 pkey, u32 slid, u32 dlid,
+		    u32 remote_qpn, u16 pkey, u32 slid, u32 dlid,
 		    u8 sc5, const struct ib_grh *old_grh);
 typedef void (*hfi1_handle_cnp)(struct hfi1_ibport *ibp, struct rvt_qp *qp,
-				u32 remote_qpn, u32 pkey, u32 slid, u32 dlid,
+				u32 remote_qpn, u16 pkey, u32 slid, u32 dlid,
 				u8 sc5, const struct ib_grh *old_grh);
 
 #define PKEY_CHECK_INVALID -1
@@ -2437,7 +2437,7 @@ static inline void hfi1_make_16b_hdr(struct hfi1_16b_header *hdr,
 		((slid >> OPA_16B_SLID_SHIFT) << OPA_16B_SLID_HIGH_SHIFT);
 	lrh2 = (lrh2 & ~OPA_16B_DLID_MASK) |
 		((dlid >> OPA_16B_DLID_SHIFT) << OPA_16B_DLID_HIGH_SHIFT);
-	lrh2 = (lrh2 & ~OPA_16B_PKEY_MASK) | (pkey << OPA_16B_PKEY_SHIFT);
+	lrh2 = (lrh2 & ~OPA_16B_PKEY_MASK) | ((u32)pkey << OPA_16B_PKEY_SHIFT);
 	lrh2 = (lrh2 & ~OPA_16B_L4_MASK) | l4;
 
 	hdr->lrh[0] = lrh0;
diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c
index 33eba2356742..6309edf811df 100644
--- a/drivers/infiniband/hw/hfi1/init.c
+++ b/drivers/infiniband/hw/hfi1/init.c
@@ -88,9 +88,9 @@
  * pio buffers per ctxt, etc.)  Zero means use one user context per CPU.
  */
 int num_user_contexts = -1;
-module_param_named(num_user_contexts, num_user_contexts, uint, S_IRUGO);
+module_param_named(num_user_contexts, num_user_contexts, int, 0444);
 MODULE_PARM_DESC(
-	num_user_contexts, "Set max number of user contexts to use");
+	num_user_contexts, "Set max number of user contexts to use (default: -1 will use the real (non-HT) CPU count)");
 
 uint krcvqs[RXE_NUM_DATA_VL];
 int krcvqsset;
@@ -1209,30 +1209,49 @@ static void finalize_asic_data(struct hfi1_devdata *dd,
 	kfree(ad);
 }
 
-static void __hfi1_free_devdata(struct kobject *kobj)
+/**
+ * hfi1_clean_devdata - cleans up per-unit data structure
+ * @dd: pointer to a valid devdata structure
+ *
+ * It cleans up all data structures set up by
+ * by hfi1_alloc_devdata().
+ */
+static void hfi1_clean_devdata(struct hfi1_devdata *dd)
 {
-	struct hfi1_devdata *dd =
-		container_of(kobj, struct hfi1_devdata, kobj);
 	struct hfi1_asic_data *ad;
 	unsigned long flags;
 
 	spin_lock_irqsave(&hfi1_devs_lock, flags);
-	idr_remove(&hfi1_unit_table, dd->unit);
-	list_del(&dd->list);
+	if (!list_empty(&dd->list)) {
+		idr_remove(&hfi1_unit_table, dd->unit);
+		list_del_init(&dd->list);
+	}
 	ad = release_asic_data(dd);
 	spin_unlock_irqrestore(&hfi1_devs_lock, flags);
-	if (ad)
-		finalize_asic_data(dd, ad);
+
+	finalize_asic_data(dd, ad);
 	free_platform_config(dd);
 	rcu_barrier(); /* wait for rcu callbacks to complete */
 	free_percpu(dd->int_counter);
 	free_percpu(dd->rcv_limit);
 	free_percpu(dd->send_schedule);
 	free_percpu(dd->tx_opstats);
+	dd->int_counter   = NULL;
+	dd->rcv_limit     = NULL;
+	dd->send_schedule = NULL;
+	dd->tx_opstats    = NULL;
 	sdma_clean(dd, dd->num_sdma);
 	rvt_dealloc_device(&dd->verbs_dev.rdi);
 }
 
+static void __hfi1_free_devdata(struct kobject *kobj)
+{
+	struct hfi1_devdata *dd =
+		container_of(kobj, struct hfi1_devdata, kobj);
+
+	hfi1_clean_devdata(dd);
+}
+
 static struct kobj_type hfi1_devdata_type = {
 	.release = __hfi1_free_devdata,
 };
@@ -1265,6 +1284,8 @@ struct hfi1_devdata *hfi1_alloc_devdata(struct pci_dev *pdev, size_t extra)
 		return ERR_PTR(-ENOMEM);
 	dd->num_pports = nports;
 	dd->pport = (struct hfi1_pportdata *)(dd + 1);
+	dd->pcidev = pdev;
+	pci_set_drvdata(pdev, dd);
 
 	INIT_LIST_HEAD(&dd->list);
 	idr_preload(GFP_KERNEL);
@@ -1331,9 +1352,7 @@ struct hfi1_devdata *hfi1_alloc_devdata(struct pci_dev *pdev, size_t extra)
 	return dd;
 
 bail:
-	if (!list_empty(&dd->list))
-		list_del_init(&dd->list);
-	rvt_dealloc_device(&dd->verbs_dev.rdi);
+	hfi1_clean_devdata(dd);
 	return ERR_PTR(ret);
 }
 
diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c
index 83d66e862207..c1c982908b4b 100644
--- a/drivers/infiniband/hw/hfi1/pcie.c
+++ b/drivers/infiniband/hw/hfi1/pcie.c
@@ -163,9 +163,6 @@ int hfi1_pcie_ddinit(struct hfi1_devdata *dd, struct pci_dev *pdev)
 	resource_size_t addr;
 	int ret = 0;
 
-	dd->pcidev = pdev;
-	pci_set_drvdata(pdev, dd);
-
 	addr = pci_resource_start(pdev, 0);
 	len = pci_resource_len(pdev, 0);
 
diff --git a/drivers/infiniband/hw/hfi1/platform.c b/drivers/infiniband/hw/hfi1/platform.c
index d486355880cb..cbf7faa5038c 100644
--- a/drivers/infiniband/hw/hfi1/platform.c
+++ b/drivers/infiniband/hw/hfi1/platform.c
@@ -199,6 +199,7 @@ void free_platform_config(struct hfi1_devdata *dd)
 {
 	/* Release memory allocated for eprom or fallback file read. */
 	kfree(dd->platform_config.data);
+	dd->platform_config.data = NULL;
 }
 
 void get_port_type(struct hfi1_pportdata *ppd)
diff --git a/drivers/infiniband/hw/hfi1/qsfp.c b/drivers/infiniband/hw/hfi1/qsfp.c
index 1869f639c3ae..b5966991d647 100644
--- a/drivers/infiniband/hw/hfi1/qsfp.c
+++ b/drivers/infiniband/hw/hfi1/qsfp.c
@@ -204,6 +204,8 @@ static void clean_i2c_bus(struct hfi1_i2c_bus *bus)
 
 void clean_up_i2c(struct hfi1_devdata *dd, struct hfi1_asic_data *ad)
 {
+	if (!ad)
+		return;
 	clean_i2c_bus(ad->i2c_bus0);
 	ad->i2c_bus0 = NULL;
 	clean_i2c_bus(ad->i2c_bus1);
diff --git a/drivers/infiniband/hw/hfi1/ruc.c b/drivers/infiniband/hw/hfi1/ruc.c
index 3daa94bdae3a..c0071ca4147a 100644
--- a/drivers/infiniband/hw/hfi1/ruc.c
+++ b/drivers/infiniband/hw/hfi1/ruc.c
@@ -733,6 +733,20 @@ static inline void hfi1_make_ruc_bth(struct rvt_qp *qp,
 	ohdr->bth[2] = cpu_to_be32(bth2);
 }
 
+/**
+ * hfi1_make_ruc_header_16B - build a 16B header
+ * @qp: the queue pair
+ * @ohdr: a pointer to the destination header memory
+ * @bth0: bth0 passed in from the RC/UC builder
+ * @bth2: bth2 passed in from the RC/UC builder
+ * @middle: non zero implies indicates ahg "could" be used
+ * @ps: the current packet state
+ *
+ * This routine may disarm ahg under these situations:
+ * - packet needs a GRH
+ * - BECN needed
+ * - migration state not IB_MIG_MIGRATED
+ */
 static inline void hfi1_make_ruc_header_16B(struct rvt_qp *qp,
 					    struct ib_other_headers *ohdr,
 					    u32 bth0, u32 bth2, int middle,
@@ -777,6 +791,12 @@ static inline void hfi1_make_ruc_header_16B(struct rvt_qp *qp,
 	else
 		middle = 0;
 
+	if (qp->s_flags & RVT_S_ECN) {
+		qp->s_flags &= ~RVT_S_ECN;
+		/* we recently received a FECN, so return a BECN */
+		becn = true;
+		middle = 0;
+	}
 	if (middle)
 		build_ahg(qp, bth2);
 	else
@@ -784,11 +804,6 @@ static inline void hfi1_make_ruc_header_16B(struct rvt_qp *qp,
 
 	bth0 |= pkey;
 	bth0 |= extra_bytes << 20;
-	if (qp->s_flags & RVT_S_ECN) {
-		qp->s_flags &= ~RVT_S_ECN;
-		/* we recently received a FECN, so return a BECN */
-		becn = true;
-	}
 	hfi1_make_ruc_bth(qp, ohdr, bth0, bth1, bth2);
 
 	if (!ppd->lid)
@@ -806,6 +821,20 @@ static inline void hfi1_make_ruc_header_16B(struct rvt_qp *qp,
 			  pkey, becn, 0, l4, priv->s_sc);
 }
 
+/**
+ * hfi1_make_ruc_header_9B - build a 9B header
+ * @qp: the queue pair
+ * @ohdr: a pointer to the destination header memory
+ * @bth0: bth0 passed in from the RC/UC builder
+ * @bth2: bth2 passed in from the RC/UC builder
+ * @middle: non zero implies indicates ahg "could" be used
+ * @ps: the current packet state
+ *
+ * This routine may disarm ahg under these situations:
+ * - packet needs a GRH
+ * - BECN needed
+ * - migration state not IB_MIG_MIGRATED
+ */
 static inline void hfi1_make_ruc_header_9B(struct rvt_qp *qp,
 					   struct ib_other_headers *ohdr,
 					   u32 bth0, u32 bth2, int middle,
@@ -839,6 +868,12 @@ static inline void hfi1_make_ruc_header_9B(struct rvt_qp *qp,
 	else
 		middle = 0;
 
+	if (qp->s_flags & RVT_S_ECN) {
+		qp->s_flags &= ~RVT_S_ECN;
+		/* we recently received a FECN, so return a BECN */
+		bth1 |= (IB_BECN_MASK << IB_BECN_SHIFT);
+		middle = 0;
+	}
 	if (middle)
 		build_ahg(qp, bth2);
 	else
@@ -846,11 +881,6 @@ static inline void hfi1_make_ruc_header_9B(struct rvt_qp *qp,
 
 	bth0 |= pkey;
 	bth0 |= extra_bytes << 20;
-	if (qp->s_flags & RVT_S_ECN) {
-		qp->s_flags &= ~RVT_S_ECN;
-		/* we recently received a FECN, so return a BECN */
-		bth1 |= (IB_BECN_MASK << IB_BECN_SHIFT);
-	}
 	hfi1_make_ruc_bth(qp, ohdr, bth0, bth1, bth2);
 	hfi1_make_ib_hdr(&ps->s_txreq->phdr.hdr.ibh,
 			 lrh0,
diff --git a/drivers/infiniband/hw/hfi1/ud.c b/drivers/infiniband/hw/hfi1/ud.c
index bcf3b0bebac8..69c17a5ef038 100644
--- a/drivers/infiniband/hw/hfi1/ud.c
+++ b/drivers/infiniband/hw/hfi1/ud.c
@@ -628,7 +628,7 @@ int hfi1_lookup_pkey_idx(struct hfi1_ibport *ibp, u16 pkey)
 }
 
 void return_cnp_16B(struct hfi1_ibport *ibp, struct rvt_qp *qp,
-		    u32 remote_qpn, u32 pkey, u32 slid, u32 dlid,
+		    u32 remote_qpn, u16 pkey, u32 slid, u32 dlid,
 		    u8 sc5, const struct ib_grh *old_grh)
 {
 	u64 pbc, pbc_flags = 0;
@@ -687,7 +687,7 @@ void return_cnp_16B(struct hfi1_ibport *ibp, struct rvt_qp *qp,
 }
 
 void return_cnp(struct hfi1_ibport *ibp, struct rvt_qp *qp, u32 remote_qpn,
-		u32 pkey, u32 slid, u32 dlid, u8 sc5,
+		u16 pkey, u32 slid, u32 dlid, u8 sc5,
 		const struct ib_grh *old_grh)
 {
 	u64 pbc, pbc_flags = 0;