mirror of
https://github.com/FEX-Emu/linux.git
synced 2024-12-15 05:11:32 +00:00
spidernet: Cure RX ram full bug
This patch fixes a rare deadlock that can occur when the kernel is not able to empty out the RX ring quickly enough. Below follows a detailed description of the bug and the fix. As long as the OS can empty out the RX buffers at a rate faster than the hardware can fill them, there is no problem. If, for some reason, the OS fails to empty the RX ring fast enough, the hardware GDACTDPA pointer will catch up to the head, notice the not-empty condition, ad stop. However, RX packets may still continue arriving on the wire. The spidernet chip can save some limited number of these in local RAM. When this local ram fills up, the spider chip will issue an interrupt indicating this (GHIINT0STS will show ERRINT, and the GRMFLLINT bit will be set in GHIINT1STS). When te RX ram full condition occurs, a certain bug/feature is triggered that has to be specially handled. This section describes the special handling for this condition. When the OS finally has a chance to run, it will empty out the RX ring. In particular, it will clear the descriptor on which the hardware had stopped. However, once the hardware has decided that a certain descriptor is invalid, it will not restart at that descriptor; instead it will restart at the next descr. This potentially will lead to a deadlock condition, as the tail pointer will be pointing at this descr, which, from the OS point of view, is empty; the OS will be waiting for this descr to be filled. However, the hardware has skipped this descr, and is filling the next descrs. Since the OS doesn't see this, there is a potential deadlock, with the OS waiting for one descr to fill, while the hardware is waiting for a differen set of descrs to become empty. A call to show_rx_chain() at this point indicates the nature of the problem. A typical print when the network is hung shows the following: net eth1: Spider RX RAM full, incoming packets might be discarded! net eth1: Total number of descrs=256 net eth1: Chain tail located at descr=255 net eth1: Chain head is at 255 net eth1: HW curr desc (GDACTDPA) is at 0 net eth1: Have 1 descrs with stat=xa0800000 net eth1: HW next desc (GDACNEXTDA) is at 1 net eth1: Have 127 descrs with stat=x40800101 net eth1: Have 1 descrs with stat=x40800001 net eth1: Have 126 descrs with stat=x40800101 net eth1: Last 1 descrs with stat=xa0800000 Both the tail and head pointers are pointing at descr 255, which is marked xa... which is "empty". Thus, from the OS point of view, there is nothing to be done. In particular, there is the implicit assumption that everything in front of the "empty" descr must surely also be empty, as explained in the last section. The OS is waiting for descr 255 to become non-empty, which, in this case, will never happen. The HW pointer is at descr 0. This descr is marked 0x4.. or "full". Since its already full, the hardware can do nothing more, and thus has halted processing. Notice that descrs 0 through 254 are all marked "full", while descr 254 and 255 are empty. (The "Last 1 descrs" is descr 254, since tail was at 255.) Thus, the system is deadlocked, and there can be no forward progress; the OS thinks there's nothing to do, and the hardware has nowhere to put incoming data. This bug/feature is worked around with the spider_net_resync_head_ptr() routine. When the driver receives RX interrupts, but an examination of the RX chain seems to show it is empty, then it is probable that the hardware has skipped a descr or two (sometimes dozens under heavy network conditions). The spider_net_resync_head_ptr() subroutine will search the ring for the next full descr, and the driver will resume operations there. Since this will leave "holes" in the ring, there is also a spider_net_resync_tail_ptr() that will skip over such holes. Signed-off-by: Linas Vepstas <linas@austin.ibm.com> Signed-off-by: Jeff Garzik <jeff@garzik.org>
This commit is contained in:
parent
83d35145c4
commit
4c4bd5a97a
@ -1050,6 +1050,66 @@ static void show_rx_chain(struct spider_net_card *card)
|
||||
}
|
||||
#endif
|
||||
|
||||
/**
|
||||
* spider_net_resync_head_ptr - Advance head ptr past empty descrs
|
||||
*
|
||||
* If the driver fails to keep up and empty the queue, then the
|
||||
* hardware wil run out of room to put incoming packets. This
|
||||
* will cause the hardware to skip descrs that are full (instead
|
||||
* of halting/retrying). Thus, once the driver runs, it wil need
|
||||
* to "catch up" to where the hardware chain pointer is at.
|
||||
*/
|
||||
static void spider_net_resync_head_ptr(struct spider_net_card *card)
|
||||
{
|
||||
unsigned long flags;
|
||||
struct spider_net_descr_chain *chain = &card->rx_chain;
|
||||
struct spider_net_descr *descr;
|
||||
int i, status;
|
||||
|
||||
/* Advance head pointer past any empty descrs */
|
||||
descr = chain->head;
|
||||
status = spider_net_get_descr_status(descr->hwdescr);
|
||||
|
||||
if (status == SPIDER_NET_DESCR_NOT_IN_USE)
|
||||
return;
|
||||
|
||||
spin_lock_irqsave(&chain->lock, flags);
|
||||
|
||||
descr = chain->head;
|
||||
status = spider_net_get_descr_status(descr->hwdescr);
|
||||
for (i=0; i<chain->num_desc; i++) {
|
||||
if (status != SPIDER_NET_DESCR_CARDOWNED) break;
|
||||
descr = descr->next;
|
||||
status = spider_net_get_descr_status(descr->hwdescr);
|
||||
}
|
||||
chain->head = descr;
|
||||
|
||||
spin_unlock_irqrestore(&chain->lock, flags);
|
||||
}
|
||||
|
||||
static int spider_net_resync_tail_ptr(struct spider_net_card *card)
|
||||
{
|
||||
struct spider_net_descr_chain *chain = &card->rx_chain;
|
||||
struct spider_net_descr *descr;
|
||||
int i, status;
|
||||
|
||||
/* Advance tail pointer past any empty and reaped descrs */
|
||||
descr = chain->tail;
|
||||
status = spider_net_get_descr_status(descr->hwdescr);
|
||||
|
||||
for (i=0; i<chain->num_desc; i++) {
|
||||
if ((status != SPIDER_NET_DESCR_CARDOWNED) &&
|
||||
(status != SPIDER_NET_DESCR_NOT_IN_USE)) break;
|
||||
descr = descr->next;
|
||||
status = spider_net_get_descr_status(descr->hwdescr);
|
||||
}
|
||||
chain->tail = descr;
|
||||
|
||||
if ((i == chain->num_desc) || (i == 0))
|
||||
return 1;
|
||||
return 0;
|
||||
}
|
||||
|
||||
/**
|
||||
* spider_net_decode_one_descr - processes an RX descriptor
|
||||
* @card: card structure
|
||||
@ -1175,6 +1235,12 @@ spider_net_poll(struct net_device *netdev, int *budget)
|
||||
}
|
||||
}
|
||||
|
||||
if ((packets_done == 0) && (card->num_rx_ints != 0)) {
|
||||
no_more_packets = spider_net_resync_tail_ptr(card);
|
||||
spider_net_resync_head_ptr(card);
|
||||
}
|
||||
card->num_rx_ints = 0;
|
||||
|
||||
netdev->quota -= packets_done;
|
||||
*budget -= packets_done;
|
||||
spider_net_refill_rx_chain(card);
|
||||
@ -1421,7 +1487,11 @@ spider_net_handle_error_irq(struct spider_net_card *card, u32 status_reg)
|
||||
if (netif_msg_intr(card) && net_ratelimit())
|
||||
pr_err("Spider RX RAM full, incoming packets "
|
||||
"might be discarded!\n");
|
||||
spider_net_rx_irq_off(card);
|
||||
/* Could happen when rx chain is full */
|
||||
spider_net_resync_head_ptr(card);
|
||||
spider_net_refill_rx_chain(card);
|
||||
spider_net_enable_rxdmac(card);
|
||||
card->num_rx_ints ++;
|
||||
netif_rx_schedule(card->netdev);
|
||||
show_error = 0;
|
||||
break;
|
||||
@ -1437,12 +1507,11 @@ spider_net_handle_error_irq(struct spider_net_card *card, u32 status_reg)
|
||||
case SPIDER_NET_GDCDCEINT: /* fallthrough */
|
||||
case SPIDER_NET_GDBDCEINT: /* fallthrough */
|
||||
case SPIDER_NET_GDADCEINT:
|
||||
if (netif_msg_intr(card) && net_ratelimit())
|
||||
pr_err("got descriptor chain end interrupt, "
|
||||
"restarting DMAC %c.\n",
|
||||
'D'-(i-SPIDER_NET_GDDDCEINT)/3);
|
||||
spider_net_resync_head_ptr(card);
|
||||
spider_net_refill_rx_chain(card);
|
||||
spider_net_enable_rxdmac(card);
|
||||
card->num_rx_ints ++;
|
||||
netif_rx_schedule(card->netdev);
|
||||
show_error = 0;
|
||||
break;
|
||||
|
||||
@ -1451,9 +1520,12 @@ spider_net_handle_error_irq(struct spider_net_card *card, u32 status_reg)
|
||||
case SPIDER_NET_GDCINVDINT: /* fallthrough */
|
||||
case SPIDER_NET_GDBINVDINT: /* fallthrough */
|
||||
case SPIDER_NET_GDAINVDINT:
|
||||
/* could happen when rx chain is full */
|
||||
/* Could happen when rx chain is full */
|
||||
spider_net_resync_head_ptr(card);
|
||||
spider_net_refill_rx_chain(card);
|
||||
spider_net_enable_rxdmac(card);
|
||||
card->num_rx_ints ++;
|
||||
netif_rx_schedule(card->netdev);
|
||||
show_error = 0;
|
||||
break;
|
||||
|
||||
@ -1546,6 +1618,7 @@ spider_net_interrupt(int irq, void *ptr)
|
||||
if (status_reg & SPIDER_NET_RXINT ) {
|
||||
spider_net_rx_irq_off(card);
|
||||
netif_rx_schedule(netdev);
|
||||
card->num_rx_ints ++;
|
||||
}
|
||||
if (status_reg & SPIDER_NET_TXINT)
|
||||
netif_rx_schedule(netdev);
|
||||
@ -2191,6 +2264,7 @@ spider_net_setup_netdev(struct spider_net_card *card)
|
||||
* NETIF_F_HW_VLAN_FILTER */
|
||||
|
||||
netdev->irq = card->pdev->irq;
|
||||
card->num_rx_ints = 0;
|
||||
|
||||
dn = pci_device_to_OF_node(card->pdev);
|
||||
if (!dn)
|
||||
|
@ -25,7 +25,7 @@
|
||||
#ifndef _SPIDER_NET_H
|
||||
#define _SPIDER_NET_H
|
||||
|
||||
#define VERSION "2.0 A"
|
||||
#define VERSION "2.0 B"
|
||||
|
||||
#include "sungem_phy.h"
|
||||
|
||||
@ -461,6 +461,7 @@ struct spider_net_card {
|
||||
struct work_struct tx_timeout_task;
|
||||
atomic_t tx_timeout_task_counter;
|
||||
wait_queue_head_t waitq;
|
||||
int num_rx_ints;
|
||||
|
||||
/* for ethtool */
|
||||
int msg_enable;
|
||||
|
Loading…
Reference in New Issue
Block a user