[PATCH for-rc 3/4] IB/hfi1: Fix probe time panic when AIP is enabled with a buggy BIOS

[dennis.dalessandro@cornelisnetworks.com]

From: Mike Marciniszyn <mike.marciniszyn@cornelisnetworks.com>

A panic can result when AIP is enabled:

[ 8.644728] BUG: unable to handle kernel NULL pointer dereference at 000000000000000
[ 8.657708] PGD 0 P4D 0
[ 8.664488] Oops: 0000 1 SMP PTI
[ 8.672190] CPU: 70 PID: 981 Comm: systemd-udevd Tainted: G OE --------- - - 4.18.0-240.el8.x86_64 #1
[ 8.687916] Hardware name: Intel Corporation S2600KP/S2600KP, BIOS SE5C610.86B.01.01.0005.101720141054 10/17/2014
[ 8.703340] RIP: 0010:__bitmap_and+0x1b/0x70
[ 8.741702] RSP: 0018:ffff99aa0845f9f0 EFLAGS: 00010246
[ 8.751757] RAX: 0000000000000000 RBX: ffff8d5a6fc18000 RCX: 0000000000000048
[ 8.764203] RDX: 0000000000000000 RSI: ffffffffc06336f0 RDI: ffff8d5a8fa67750
[ 8.776990] RBP: 0000000000000079 R08: 0000000fffffffff R09: 0000000000000000
[ 8.789768] R10: 0000000000000000 R11: 0000000000000001 R12: ffffffffc06336f0
[ 8.802007] R13: 00000000000000a0 R14: ffff8d5a6fc18000 R15: 0000000000000003
[ 8.814317] FS: 00007fec137a5980(0000) GS:ffff8d5a9fa80000(0000) knlGS:0000000000000000
[ 8.827629] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 8.838309] CR2: 0000000000000000 CR3: 0000000a04b48002 CR4: 00000000001606e0
[ 8.850502] Call Trace:
[ 8.857950] hfi1_num_netdev_contexts+0x7c/0x110 [hfi1]
[ 8.868295] hfi1_init_dd+0xd7f/0x1a90 [hfi1]
[ 8.877681] ? pci_bus_read_config_dword+0x49/0x70
[ 8.887567] ? pci_mmcfg_read+0x3e/0xe0
[ 8.896797] do_init_one.isra.18+0x336/0x640 [hfi1]
[ 8.906958] local_pci_probe+0x41/0x90
[ 8.915784] pci_device_probe+0x105/0x1c0
[ 8.925002] really_probe+0x212/0x440
[ 8.933687] driver_probe_device+0x49/0xc0
[ 8.942918] device_driver_attach+0x50/0x60
[ 8.952553] __driver_attach+0x61/0x130
[ 8.961553] ? device_driver_attach+0x60/0x60
[ 8.971122] bus_for_each_dev+0x77/0xc0
[ 8.979912] ? klist_add_tail+0x3b/0x70
[ 8.988886] bus_add_driver+0x14d/0x1e0
[ 8.998175] ? dev_init+0x10b/0x10b [hfi1]
[ 9.007531] driver_register+0x6b/0xb0
[ 9.016757] ? dev_init+0x10b/0x10b [hfi1]
[ 9.026220] hfi1_mod_init+0x1e6/0x20a [hfi1]
[ 9.035601] do_one_initcall+0x46/0x1c3
[ 9.043958] ? free_unref_page_commit+0x91/0x100
[ 9.053460] ? _cond_resched+0x15/0x30
[ 9.062426] ? kmem_cache_alloc_trace+0x140/0x1c0
[ 9.071982] do_init_module+0x5a/0x220
[ 9.080574] load_module+0x14b4/0x17e0
[ 9.088911] ? __do_sys_finit_module+0xa8/0x110
[ 9.098231] __do_sys_finit_module+0xa8/0x110
[ 9.107307] do_syscall_64+0x5b/0x1a0

The issue happens when pcibus_to_node() returns NO_NUMA_NODE.

Fix this issue by moving the initialization of dd->node to hfi1_devdata
allocation and remove the other pcibus_to_node() calls in the probe
path and use dd->node instead.

Affinity logic is adjusted to use a new field dd->affinity_entry
as a guard instead of dd->node.

Fixes: 4730f4a6c6b2 ("IB/hfi1: Activate the dummy netdev")
Cc: stable@vger.kernel.org
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@cornelisnetworks.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com>
---
 drivers/infiniband/hw/hfi1/affinity.c  | 21 +++++----------------
 drivers/infiniband/hw/hfi1/hfi.h       |  1 +
 drivers/infiniband/hw/hfi1/init.c      | 10 +++++++++-
 drivers/infiniband/hw/hfi1/netdev_rx.c |  3 +--
 4 files changed, 16 insertions(+), 19 deletions(-)

diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c
index 2a91b8d..04b1e8f 100644
--- a/drivers/infiniband/hw/hfi1/affinity.c
+++ b/drivers/infiniband/hw/hfi1/affinity.c
@@ -632,22 +632,11 @@ static void _dev_comp_vect_cpu_mask_clean_up(struct hfi1_devdata *dd,
  */
 int hfi1_dev_affinity_init(struct hfi1_devdata *dd)
 {
-	int node = pcibus_to_node(dd->pcidev->bus);
 	struct hfi1_affinity_node *entry;
 	const struct cpumask *local_mask;
 	int curr_cpu, possible, i, ret;
 	bool new_entry = false;
 
-	/*
-	 * If the BIOS does not have the NUMA node information set, select
-	 * NUMA 0 so we get consistent performance.
-	 */
-	if (node < 0) {
-		dd_dev_err(dd, "Invalid PCI NUMA node. Performance may be affected\n");
-		node = 0;
-	}
-	dd->node = node;
-
 	local_mask = cpumask_of_node(dd->node);
 	if (cpumask_first(local_mask) >= nr_cpu_ids)
 		local_mask = topology_core_cpumask(0);
@@ -660,7 +649,7 @@ int hfi1_dev_affinity_init(struct hfi1_devdata *dd)
 	 * create an entry in the global affinity structure and initialize it.
 	 */
 	if (!entry) {
-		entry = node_affinity_allocate(node);
+		entry = node_affinity_allocate(dd->node);
 		if (!entry) {
 			dd_dev_err(dd,
 				   "Unable to allocate global affinity node\n");
@@ -751,6 +740,7 @@ int hfi1_dev_affinity_init(struct hfi1_devdata *dd)
 	if (new_entry)
 		node_affinity_add_tail(entry);
 
+	dd->affinity_entry = entry;
 	mutex_unlock(&node_affinity.lock);
 
 	return 0;
@@ -766,10 +756,9 @@ void hfi1_dev_affinity_clean_up(struct hfi1_devdata *dd)
 {
 	struct hfi1_affinity_node *entry;
 
-	if (dd->node < 0)
-		return;
-
 	mutex_lock(&node_affinity.lock);
+	if (!dd->affinity_entry)
+		goto unlock;
 	entry = node_affinity_lookup(dd->node);
 	if (!entry)
 		goto unlock;
@@ -780,8 +769,8 @@ void hfi1_dev_affinity_clean_up(struct hfi1_devdata *dd)
 	 */
 	_dev_comp_vect_cpu_mask_clean_up(dd, entry);
 unlock:
+	dd->affinity_entry = NULL;
 	mutex_unlock(&node_affinity.lock);
-	dd->node = NUMA_NO_NODE;
 }
 
 /*
diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index 024ef6e..d341b8a 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -1403,6 +1403,7 @@ struct hfi1_devdata {
 	spinlock_t irq_src_lock;
 	int vnic_num_vports;
 	struct net_device *dummy_netdev;
+	struct hfi1_affinity_node *affinity_entry;
 
 	/* Keeps track of IPoIB RSM rule users */
 	atomic_t ipoib_rsm_usr_num;
diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c
index e4f8db4..6d03aa0 100644
--- a/drivers/infiniband/hw/hfi1/init.c
+++ b/drivers/infiniband/hw/hfi1/init.c
@@ -1277,7 +1277,6 @@ static struct hfi1_devdata *hfi1_alloc_devdata(struct pci_dev *pdev,
 	dd->pport = (struct hfi1_pportdata *)(dd + 1);
 	dd->pcidev = pdev;
 	pci_set_drvdata(pdev, dd);
-	dd->node = NUMA_NO_NODE;
 
 	ret = xa_alloc_irq(&hfi1_dev_table, &dd->unit, dd, xa_limit_32b,
 			GFP_KERNEL);
@@ -1287,6 +1286,15 @@ static struct hfi1_devdata *hfi1_alloc_devdata(struct pci_dev *pdev,
 		goto bail;
 	}
 	rvt_set_ibdev_name(&dd->verbs_dev.rdi, "%s_%d", class_name(), dd->unit);
+	/*
+	 * If the BIOS does not have the NUMA node information set, select
+	 * NUMA 0 so we get consistent performance.
+	 */
+	dd->node = pcibus_to_node(pdev->bus);
+	if (dd->node == NUMA_NO_NODE) {
+		dd_dev_err(dd, "Invalid PCI NUMA node. Performance may be affected\n");
+		dd->node = 0;
+	}
 
 	/*
 	 * Initialize all locks for the device. This needs to be as early as
diff --git a/drivers/infiniband/hw/hfi1/netdev_rx.c b/drivers/infiniband/hw/hfi1/netdev_rx.c
index cec02e8..c1fa53d 100644
--- a/drivers/infiniband/hw/hfi1/netdev_rx.c
+++ b/drivers/infiniband/hw/hfi1/netdev_rx.c
@@ -173,8 +173,7 @@ u32 hfi1_num_netdev_contexts(struct hfi1_devdata *dd, u32 available_contexts,
 		return 0;
 	}
 
-	cpumask_and(node_cpu_mask, cpu_mask,
-		    cpumask_of_node(pcibus_to_node(dd->pcidev->bus)));
+	cpumask_and(node_cpu_mask, cpu_mask, cpumask_of_node(dd->node));
 
 	available_cpus = cpumask_weight(node_cpu_mask);
 
-- 
1.8.3.1