Re: [PATCH 1/2] s2io: add PCI error recovery support

[linas@austin.ibm.com (Linas Vepstas)]

I failed to cc some of the people on the cc list ... so am resending.
--linas

On Mon, May 14, 2007 at 06:37:30PM -0500, Linas Vepstas wrote:
> 
> This patch adds PCI error recovery support to the 
> s2io 10-Gigabit ethernet device driver. Third revision,
> blocks interrupts and the watchdog.
> 
> Tested, seems to work well.
> 
> Signed-off-by: Linas Vepstas <linas@austin.ibm.com>
> Acked-by: Ramkrishna Vepa <Ramkrishna.Vepa@neterion.com>
> Cc: Raghavendra Koushik <raghavendra.koushik@neterion.com>
> Cc: Wen Xiong <wenxiong@us.ibm.com>
> 
> ----
> 
> Jeff, please apply for 2.6.22
> 
> --linas
> 
> 
>  drivers/net/s2io.c |  116 ++++++++++++++++++++++++++++++++++++++++++++++++++---
>  drivers/net/s2io.h |    5 ++
>  2 files changed, 116 insertions(+), 5 deletions(-)
> 
> Index: linux-2.6.22-rc1/drivers/net/s2io.c
> ===================================================================
> --- linux-2.6.22-rc1.orig/drivers/net/s2io.c	2007-05-14 17:05:03.000000000 -0500
> +++ linux-2.6.22-rc1/drivers/net/s2io.c	2007-05-14 17:23:45.000000000 -0500
> @@ -480,11 +480,18 @@ static struct pci_device_id s2io_tbl[] _
>  
>  MODULE_DEVICE_TABLE(pci, s2io_tbl);
>  
> +static struct pci_error_handlers s2io_err_handler = {
> +	.error_detected = s2io_io_error_detected,
> +	.slot_reset = s2io_io_slot_reset,
> +	.resume = s2io_io_resume,
> +};
> +
>  static struct pci_driver s2io_driver = {
>        .name = "S2IO",
>        .id_table = s2io_tbl,
>        .probe = s2io_init_nic,
>        .remove = __devexit_p(s2io_rem_nic),
> +      .err_handler = &s2io_err_handler,
>  };
>  
>  /* A simplifier macro used both by init and free shared_mem Fns(). */
> @@ -2700,6 +2707,9 @@ static void s2io_netpoll(struct net_devi
>  	u64 val64 = 0xFFFFFFFFFFFFFFFFULL;
>  	int i;
>  
> +	if (pci_channel_offline(nic->pdev))
> +		return;
> +
>  	disable_irq(dev->irq);
>  
>  	atomic_inc(&nic->isr_cnt);
> @@ -3225,6 +3235,8 @@ static void alarm_intr_handler(struct s2
>  	int i;
>  	if (atomic_read(&nic->card_state) == CARD_DOWN)
>  		return;
> +	if (pci_channel_offline(nic->pdev))
> +		return;
>  	nic->mac_control.stats_info->sw_stat.ring_full_cnt = 0;
>  	/* Handling the XPAK counters update */
>  	if(nic->mac_control.stats_info->xpak_stat.xpak_timer_count < 72000) {
> @@ -4324,6 +4336,10 @@ static irqreturn_t s2io_isr(int irq, voi
>  	struct mac_info *mac_control;
>  	struct config_param *config;
>  
> +	/* Pretend we handled any irq's from a disconnected card */
> +	if (pci_channel_offline(sp->pdev))
> +		return IRQ_NONE;
> +
>  	atomic_inc(&sp->isr_cnt);
>  	mac_control = &sp->mac_control;
>  	config = &sp->config;
> @@ -6579,7 +6595,7 @@ static void s2io_rem_isr(struct s2io_nic
>  	} while(cnt < 5);
>  }
>  
> -static void s2io_card_down(struct s2io_nic * sp)
> +static void do_s2io_card_down(struct s2io_nic * sp, int do_io)
>  {
>  	int cnt = 0;
>  	struct XENA_dev_config __iomem *bar0 = sp->bar0;
> @@ -6594,7 +6610,8 @@ static void s2io_card_down(struct s2io_n
>  	atomic_set(&sp->card_state, CARD_DOWN);
>  
>  	/* disable Tx and Rx traffic on the NIC */
> -	stop_nic(sp);
> +	if (do_io)
> +		stop_nic(sp);
>  
>  	s2io_rem_isr(sp);
>  
> @@ -6602,7 +6619,7 @@ static void s2io_card_down(struct s2io_n
>  	tasklet_kill(&sp->task);
>  
>  	/* Check if the device is Quiescent and then Reset the NIC */
> -	do {
> +	while(do_io) {
>  		/* As per the HW requirement we need to replenish the
>  		 * receive buffer to avoid the ring bump. Since there is
>  		 * no intention of processing the Rx frame at this pointwe are
> @@ -6627,8 +6644,9 @@ static void s2io_card_down(struct s2io_n
>  				  (unsigned long long) val64);
>  			break;
>  		}
> -	} while (1);
> -	s2io_reset(sp);
> +	}
> +	if (do_io)
> +		s2io_reset(sp);
>  
>  	spin_lock_irqsave(&sp->tx_lock, flags);
>  	/* Free all Tx buffers */
> @@ -6643,6 +6661,11 @@ static void s2io_card_down(struct s2io_n
>  	clear_bit(0, &(sp->link_state));
>  }
>  
> +static void s2io_card_down(struct s2io_nic * sp)
> +{
> +	do_s2io_card_down(sp, 1);
> +}
> +
>  static int s2io_card_up(struct s2io_nic * sp)
>  {
>  	int i, ret = 0;
> @@ -8020,3 +8043,86 @@ static void lro_append_pkt(struct s2io_n
>  	sp->mac_control.stats_info->sw_stat.clubbed_frms_cnt++;
>  	return;
>  }
> +
> +/**
> + * s2io_io_error_detected - called when PCI error is detected
> + * @pdev: Pointer to PCI device
> + * @state: The current pci conneection state
> + *
> + * This function is called after a PCI bus error affecting
> + * this device has been detected.
> + */
> +static pci_ers_result_t s2io_io_error_detected(struct pci_dev *pdev,
> +                                               pci_channel_state_t state)
> +{
> +	struct net_device *netdev = pci_get_drvdata(pdev);
> +	struct s2io_nic *sp = netdev->priv;
> +
> +	netif_device_detach(netdev);
> +
> +	if (netif_running(netdev)) {
> +		/* Bring down the card, while avoiding PCI I/O */
> +		do_s2io_card_down(sp, 0);
> +		sp->device_close_flag = TRUE;	/* Device is shut down. */
> +	}
> +	pci_disable_device(pdev);
> +
> +	return PCI_ERS_RESULT_NEED_RESET;
> +}
> +
> +/**
> + * s2io_io_slot_reset - called after the pci bus has been reset.
> + * @pdev: Pointer to PCI device
> + *
> + * Restart the card from scratch, as if from a cold-boot.
> + * At this point, the card has exprienced a hard reset,
> + * followed by fixups by BIOS, and has its config space
> + * set up identically to what it was at cold boot.
> + */
> +static pci_ers_result_t s2io_io_slot_reset(struct pci_dev *pdev)
> +{
> +	struct net_device *netdev = pci_get_drvdata(pdev);
> +	struct s2io_nic *sp = netdev->priv;
> +
> +	if (pci_enable_device(pdev)) {
> +		printk(KERN_ERR "s2io: "
> +		       "Cannot re-enable PCI device after reset.\n");
> +		return PCI_ERS_RESULT_DISCONNECT;
> +	}
> +
> +	pci_set_master(pdev);
> +	s2io_reset(sp);
> +
> +	return PCI_ERS_RESULT_RECOVERED;
> +}
> +
> +/**
> + * s2io_io_resume - called when traffic can start flowing again.
> + * @pdev: Pointer to PCI device
> + *
> + * This callback is called when the error recovery driver tells
> + * us that its OK to resume normal operation.
> + */
> +static void s2io_io_resume(struct pci_dev *pdev)
> +{
> +	struct net_device *netdev = pci_get_drvdata(pdev);
> +	struct s2io_nic *sp = netdev->priv;
> +
> +	if (netif_running(netdev)) {
> +		if (s2io_card_up(sp)) {
> +			printk(KERN_ERR "s2io: "
> +			       "Can't bring device back up after reset.\n");
> +			return;
> +		}
> +
> +		if (s2io_set_mac_addr(netdev, netdev->dev_addr) == FAILURE) {
> +			s2io_card_down(sp);
> +			printk(KERN_ERR "s2io: "
> +			       "Can't resetore mac addr after reset.\n");
> +			return;
> +		}
> +	}
> +
> +	netif_device_attach(netdev);
> +	netif_wake_queue(netdev);
> +}
> Index: linux-2.6.22-rc1/drivers/net/s2io.h
> ===================================================================
> --- linux-2.6.22-rc1.orig/drivers/net/s2io.h	2007-05-14 17:05:03.000000000 -0500
> +++ linux-2.6.22-rc1/drivers/net/s2io.h	2007-05-14 17:23:45.000000000 -0500
> @@ -1052,6 +1052,11 @@ static void lro_append_pkt(struct s2io_n
>  			   struct sk_buff *skb, u32 tcp_len);
>  static int rts_ds_steer(struct s2io_nic *nic, u8 ds_codepoint, u8 ring);
>  
> +static pci_ers_result_t s2io_io_error_detected(struct pci_dev *pdev,
> +			                      pci_channel_state_t state);
> +static pci_ers_result_t s2io_io_slot_reset(struct pci_dev *pdev);
> +static void s2io_io_resume(struct pci_dev *pdev);
> +
>  #define s2io_tcp_mss(skb) skb_shinfo(skb)->gso_size
>  #define s2io_udp_mss(skb) skb_shinfo(skb)->gso_size
>  #define s2io_offload_type(skb) skb_shinfo(skb)->gso_type
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/