nvme-pci: adjust irq max_vector using num_possible_cpus()

If the "irq_queues" are greater than num_possible_cpus(),
nvme_calc_irq_sets() can have irq set_size for HCTX_TYPE_DEFAULT greater
than it can be afforded.
2039         affd->set_size[HCTX_TYPE_DEFAULT] = nrirqs - nr_read_queues;

It might cause a WARN() from the irq_build_affinity_masks() like [1]:
220         if (nr_present < numvecs)
221                 WARN_ON(nr_present + nr_others < numvecs);

This patch prevents it from the WARN() by adjusting the max_vector value
from the nvme_setup_irqs().

[1] WARN messages when modprobe nvme write_queues=32 poll_queues=0:
root@target:~/nvme# nproc
8
root@target:~/nvme# modprobe nvme write_queues=32 poll_queues=0
[   17.925326] nvme nvme0: pci function 0000:00:04.0
[   17.940601] WARNING: CPU: 3 PID: 1030 at kernel/irq/affinity.c:221 irq_create_affinity_masks+0x222/0x330
[   17.940602] Modules linked in: nvme nvme_core [last unloaded: nvme]
[   17.940605] CPU: 3 PID: 1030 Comm: kworker/u17:4 Tainted: G        W         5.1.0+ #156
[   17.940605] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.org 04/01/2014
[   17.940608] Workqueue: nvme-reset-wq nvme_reset_work [nvme]
[   17.940609] RIP: 0010:irq_create_affinity_masks+0x222/0x330
[   17.940611] Code: 4c 8d 4c 24 28 4c 8d 44 24 30 e8 c9 fa ff ff 89 44 24 18 e8 c0 38 fa ff 8b 44 24 18 44 8b 54 24 1c 5a 44 01 d0 41 39 c4 76 02 <0f> 0b 48 89 df 44 01 e5 e8 f1 ce 10 00 48 8b 34 24 44 89 f0 44 01
[   17.940611] RSP: 0018:ffffc90002277c50 EFLAGS: 00010216
[   17.940612] RAX: 0000000000000008 RBX: ffff88807ca48860 RCX: 0000000000000000
[   17.940612] RDX: ffff88807bc03800 RSI: 0000000000000020 RDI: 0000000000000000
[   17.940613] RBP: 0000000000000001 R08: ffffc90002277c78 R09: ffffc90002277c70
[   17.940613] R10: 0000000000000008 R11: 0000000000000001 R12: 0000000000000020
[   17.940614] R13: 0000000000025d08 R14: 0000000000000001 R15: ffff88807bc03800
[   17.940614] FS:  0000000000000000(0000) GS:ffff88807db80000(0000) knlGS:0000000000000000
[   17.940616] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   17.940617] CR2: 00005635e583f790 CR3: 000000000240a000 CR4: 00000000000006e0
[   17.940617] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[   17.940618] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[   17.940618] Call Trace:
[   17.940622]  __pci_enable_msix_range+0x215/0x540
[   17.940623]  ? kernfs_put+0x117/0x160
[   17.940625]  pci_alloc_irq_vectors_affinity+0x74/0x110
[   17.940626]  nvme_reset_work+0xc30/0x1397 [nvme]
[   17.940628]  ? __switch_to_asm+0x34/0x70
[   17.940628]  ? __switch_to_asm+0x40/0x70
[   17.940629]  ? __switch_to_asm+0x34/0x70
[   17.940630]  ? __switch_to_asm+0x40/0x70
[   17.940630]  ? __switch_to_asm+0x34/0x70
[   17.940631]  ? __switch_to_asm+0x40/0x70
[   17.940632]  ? nvme_irq_check+0x30/0x30 [nvme]
[   17.940633]  process_one_work+0x20b/0x3e0
[   17.940634]  worker_thread+0x1f9/0x3d0
[   17.940635]  ? cancel_delayed_work+0xa0/0xa0
[   17.940636]  kthread+0x117/0x120
[   17.940637]  ? kthread_stop+0xf0/0xf0
[   17.940638]  ret_from_fork+0x3a/0x50
[   17.940639] ---[ end trace aca8a131361cd42a ]---
[   17.942124] nvme nvme0: 7/1/0 default/read/poll queues

Signed-off-by: Minwoo Im <minwoo.im.dev@gmail.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 007f8becde4aeceb4a9a4eefbac24c7c5df291fe..c98b73da38e20864c93ba1b91eabeff2ce2d16a3 100644 (file)
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2051,6 +2051,7 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues)
                .priv           = dev,
        };
        unsigned int irq_queues, this_p_queues;
+       unsigned int nr_cpus = num_possible_cpus();
 
        /*
         * Poll queues don't need interrupts, but we need at least one IO
@@ -2061,7 +2062,10 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues)
                this_p_queues = nr_io_queues - 1;
                irq_queues = 1;
        } else {
-               irq_queues = nr_io_queues - this_p_queues + 1;
+               if (nr_cpus < nr_io_queues - this_p_queues)
+                       irq_queues = nr_cpus + 1;
+               else
+                       irq_queues = nr_io_queues - this_p_queues + 1;
        }
        dev->io_queues[HCTX_TYPE_POLL] = this_p_queues;