sfc: fix channel allocation with brute force

It was possible for channel allocation logic to get confused between what
 it had and what it wanted, and end up trying to use the same channel for
 both PTP and regular TX.  This led to a kernel panic:
    BUG: unable to handle page fault for address: 0000000000047635
    #PF: supervisor write access in kernel mode
    #PF: error_code(0x0002) - not-present page
    PGD 0 P4D 0
    Oops: 0002 [#1] SMP PTI
    CPU: 0 PID: 0 Comm: swapper/0 Tainted: G        W         5.4.0-rc3-ehc14+ #900
    Hardware name: Dell Inc. PowerEdge R710/0M233H, BIOS 6.4.0 07/23/2013
    RIP: 0010:native_queued_spin_lock_slowpath+0x188/0x1e0
    Code: f3 90 48 8b 32 48 85 f6 74 f6 eb e8 c1 ee 12 83 e0 03 83 ee 01 48 c1 e0 05 48 63 f6 48 05 c0 98 02 00 48 03 04 f5 a0 c6 ed 81 <48> 89 10 8b 42 08 85 c0 75 09 f3 90 8b 42 08 85 c0 74 f7 48 8b 32
    RSP: 0018:ffffc90000003d28 EFLAGS: 00010006
    RAX: 0000000000047635 RBX: 0000000000000246 RCX: 0000000000040000
    RDX: ffff888627a298c0 RSI: 0000000000003ffe RDI: ffff88861f6b8dd4
    RBP: ffff8886225c6e00 R08: 0000000000040000 R09: 0000000000000000
    R10: 0000000616f080c6 R11: 00000000000000c0 R12: ffff88861f6b8dd4
    R13: ffffc90000003dc8 R14: ffff88861942bf00 R15: ffff8886150f2000
    FS:  0000000000000000(0000) GS:ffff888627a00000(0000) knlGS:0000000000000000
    CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
    CR2: 0000000000047635 CR3: 000000000200a000 CR4: 00000000000006f0
    Call Trace:
     <IRQ>
     _raw_spin_lock_irqsave+0x22/0x30
     skb_queue_tail+0x1b/0x50
     sock_queue_err_skb+0x9d/0xf0
     __skb_complete_tx_timestamp+0x9d/0xc0
     efx_dequeue_buffer+0x126/0x180 [sfc]
     efx_xmit_done+0x73/0x1c0 [sfc]
     efx_ef10_ev_process+0x56a/0xfe0 [sfc]
     ? tick_sched_do_timer+0x60/0x60
     ? timerqueue_add+0x5d/0x70
     ? enqueue_hrtimer+0x39/0x90
     efx_poll+0x111/0x380 [sfc]
     ? rcu_accelerate_cbs+0x50/0x160
     net_rx_action+0x14a/0x400
     __do_softirq+0xdd/0x2d0
     irq_exit+0xa0/0xb0
     do_IRQ+0x53/0xe0
     common_interrupt+0xf/0xf
     </IRQ>

In the long run we intend to rewrite the channel allocation code, but for
 'net' fix this by allocating extra_channels, and giving them TX queues,
 even if we do not in fact need them (e.g. on NICs without MAC TX
 timestamping), and thereby using simpler logic to assign the channels
 once they're allocated.

Fixes: 3990a8f ("sfc: allocate channels for XDP tx queues")
Signed-off-by: Edward Cree <[email protected]>
Signed-off-by: David S. Miller <[email protected]>

Author: ecree-solarflare

drivers/net/ethernet/sfc/efx.c

@@ -1472,6 +1472,12 @@ static int efx_allocate_msix_channels(struct efx_nic *efx,
 	n_xdp_tx = num_possible_cpus();
 	n_xdp_ev = DIV_ROUND_UP(n_xdp_tx, EFX_TXQ_TYPES);
 
+	vec_count = pci_msix_vec_count(efx->pci_dev);
+	if (vec_count < 0)
+		return vec_count;
+
+	max_channels = min_t(unsigned int, vec_count, max_channels);
+
 	/* Check resources.
 	 * We need a channel per event queue, plus a VI per tx queue.
 	 * This may be more pessimistic than it needs to be.
@@ -1493,11 +1499,6 @@ static int efx_allocate_msix_channels(struct efx_nic *efx,
 			  n_xdp_tx, n_xdp_ev);
 	}
 
-	n_channels = min(n_channels, max_channels);
-
-	vec_count = pci_msix_vec_count(efx->pci_dev);
-	if (vec_count < 0)
-		return vec_count;
 	if (vec_count < n_channels) {
 		netif_err(efx, drv, efx->net_dev,
 			  "WARNING: Insufficient MSI-X vectors available (%d < %u).\n",
@@ -1507,11 +1508,9 @@ static int efx_allocate_msix_channels(struct efx_nic *efx,
 		n_channels = vec_count;
 	}
 
-	efx->n_channels = n_channels;
+	n_channels = min(n_channels, max_channels);
 
-	/* Do not create the PTP TX queue(s) if PTP uses the MC directly. */
-	if (extra_channels && !efx_ptp_use_mac_tx_timestamps(efx))
-		n_channels--;
+	efx->n_channels = n_channels;
 
 	/* Ignore XDP tx channels when creating rx channels. */
 	n_channels -= efx->n_xdp_channels;
@@ -1531,11 +1530,10 @@ static int efx_allocate_msix_channels(struct efx_nic *efx,
 		efx->n_rx_channels = n_channels;
 	}
 
-	if (efx->n_xdp_channels)
-		efx->xdp_channel_offset = efx->tx_channel_offset +
-					  efx->n_tx_channels;
-	else
-		efx->xdp_channel_offset = efx->n_channels;
+	efx->n_rx_channels = min(efx->n_rx_channels, parallelism);
+	efx->n_tx_channels = min(efx->n_tx_channels, parallelism);
+
+	efx->xdp_channel_offset = n_channels;
 
 	netif_dbg(efx, drv, efx->net_dev,
 		  "Allocating %u RX channels\n",
@@ -1550,6 +1548,7 @@ static int efx_allocate_msix_channels(struct efx_nic *efx,
 static int efx_probe_interrupts(struct efx_nic *efx)
 {
 	unsigned int extra_channels = 0;
+	unsigned int rss_spread;
 	unsigned int i, j;
 	int rc;
 
@@ -1631,8 +1630,7 @@ static int efx_probe_interrupts(struct efx_nic *efx)
 	for (i = 0; i < EFX_MAX_EXTRA_CHANNELS; i++) {
 		if (!efx->extra_channel_type[i])
 			continue;
-		if (efx->interrupt_mode != EFX_INT_MODE_MSIX ||
-		    efx->n_channels <= extra_channels) {
+		if (j <= efx->tx_channel_offset + efx->n_tx_channels) {
 			efx->extra_channel_type[i]->handle_no_channel(efx);
 		} else {
 			--j;
@@ -1643,16 +1641,17 @@ static int efx_probe_interrupts(struct efx_nic *efx)
 		}
 	}
 
+	rss_spread = efx->n_rx_channels;
 	/* RSS might be usable on VFs even if it is disabled on the PF */
 #ifdef CONFIG_SFC_SRIOV
 	if (efx->type->sriov_wanted) {
-		efx->rss_spread = ((efx->n_rx_channels > 1 ||
+		efx->rss_spread = ((rss_spread > 1 ||
 				    !efx->type->sriov_wanted(efx)) ?
-				   efx->n_rx_channels : efx_vf_size(efx));
+				   rss_spread : efx_vf_size(efx));
 		return 0;
 	}
 #endif
-	efx->rss_spread = efx->n_rx_channels;
+	efx->rss_spread = rss_spread;
 
 	return 0;
 }

drivers/net/ethernet/sfc/net_driver.h

@@ -1533,9 +1533,7 @@ static inline bool efx_channel_is_xdp_tx(struct efx_channel *channel)
 
 static inline bool efx_channel_has_tx_queues(struct efx_channel *channel)
 {
-	return efx_channel_is_xdp_tx(channel) ||
-	       (channel->type && channel->type->want_txqs &&
-		channel->type->want_txqs(channel));
+	return true;
 }
 
 static inline struct efx_tx_queue *