ehea: Fixed error recovery

Error recovery for QP errors: Reset QPs and dump error information

Signed-off-by: Jan-Bernd Themann <themann@de.ibm.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>

diff --git a/drivers/net/ehea/ehea.h b/drivers/net/ehea/ehea.h
index 272e1ec51aa2b4202c5ea93980d9026039ef6a05..42295d61ecd847791f6a8c04513940c471732790 100644 (file)
--- a/drivers/net/ehea/ehea.h
+++ b/drivers/net/ehea/ehea.h
@@ -39,7 +39,7 @@
 #include <asm/io.h>
 
 #define DRV_NAME       "ehea"
-#define DRV_VERSION    "EHEA_0045"
+#define DRV_VERSION    "EHEA_0046"
 
 #define EHEA_MSG_DEFAULT (NETIF_MSG_LINK | NETIF_MSG_TIMER \
        | NETIF_MSG_RX_ERR | NETIF_MSG_TX_ERR)

diff --git a/drivers/net/ehea/ehea_main.c b/drivers/net/ehea/ehea_main.c
index 9de2d38a5321f6d40194a0a2eb061685b9773331..1ef3846a5ea0c50982b1f0303e49e865f6c756bf 100644 (file)
--- a/drivers/net/ehea/ehea_main.c
+++ b/drivers/net/ehea/ehea_main.c
@@ -76,7 +76,7 @@ void ehea_dump(void *adr, int len, char *msg) {
        int x;
        unsigned char *deb = adr;
        for (x = 0; x < len; x += 16) {
-               printk(DRV_NAME "%s adr=%p ofs=%04x %016lx %016lx\n", msg,
+               printk(DRV_NAME " %s adr=%p ofs=%04x %016lx %016lx\n", msg,
                          deb, x, *((u64*)&deb[0]), *((u64*)&deb[8]));
                deb += 16;
        }
@@ -555,6 +555,7 @@ static irqreturn_t ehea_qp_aff_irq_handler(int irq, void *param)
 {
        struct ehea_port *port = param;
        struct ehea_eqe *eqe;
+       struct ehea_qp *qp;
        u32 qp_token;
 
        eqe = ehea_poll_eq(port->qp_eq);
@@ -563,9 +564,14 @@ static irqreturn_t ehea_qp_aff_irq_handler(int irq, void *param)
                qp_token = EHEA_BMASK_GET(EHEA_EQE_QP_TOKEN, eqe->entry);
                ehea_error("QP aff_err: entry=0x%lx, token=0x%x",
                           eqe->entry, qp_token);
+
+               qp = port->port_res[qp_token].qp;
+               ehea_error_data(port->adapter, qp->fw_handle);
                eqe = ehea_poll_eq(port->qp_eq);
        }
 
+       queue_work(port->adapter->ehea_wq, &port->reset_task);
+
        return IRQ_HANDLED;
 }
 

diff --git a/drivers/net/ehea/ehea_phyp.c b/drivers/net/ehea/ehea_phyp.c
index 37716e05e808fe50e777da3490331bf60ea9a64e..bc3c005472642af53f72627c666911cf380c60f0 100644 (file)
--- a/drivers/net/ehea/ehea_phyp.c
+++ b/drivers/net/ehea/ehea_phyp.c
@@ -612,3 +612,13 @@ u64 ehea_h_reset_events(const u64 adapter_handle, const u64 neq_handle,
                                       event_mask,              /* R6 */
                                       0, 0, 0, 0);             /* R7-R12 */
 }
+
+u64 ehea_h_error_data(const u64 adapter_handle, const u64 ressource_handle,
+                     void *rblock)
+{
+       return ehea_plpar_hcall_norets(H_ERROR_DATA,
+                                      adapter_handle,          /* R4 */
+                                      ressource_handle,        /* R5 */
+                                      virt_to_abs(rblock),     /* R6 */
+                                      0, 0, 0, 0);             /* R7-R12 */
+}

diff --git a/drivers/net/ehea/ehea_phyp.h b/drivers/net/ehea/ehea_phyp.h
index 919f94b759336e95cd25afe54b1217ae22bde9bf..90acddb068a1ab819938631675c4db83ab01bda3 100644 (file)
--- a/drivers/net/ehea/ehea_phyp.h
+++ b/drivers/net/ehea/ehea_phyp.h
@@ -454,4 +454,7 @@ u64 ehea_h_reg_dereg_bcmc(const u64 adapter_handle, const u16 port_num,
 u64 ehea_h_reset_events(const u64 adapter_handle, const u64 neq_handle,
                        const u64 event_mask);
 
+u64 ehea_h_error_data(const u64 adapter_handle, const u64 ressource_handle,
+                     void *rblock);
+
 #endif /* __EHEA_PHYP_H__ */

diff --git a/drivers/net/ehea/ehea_qmr.c b/drivers/net/ehea/ehea_qmr.c
index f143e13b229dda570b10f84142398aad43ee8699..96ff3b6799969d50c2cd9f13e6899c1f3f1e8993 100644 (file)
--- a/drivers/net/ehea/ehea_qmr.c
+++ b/drivers/net/ehea/ehea_qmr.c
@@ -486,6 +486,7 @@ int ehea_destroy_qp(struct ehea_qp *qp)
        if (!qp)
                return 0;
 
+       ehea_h_disable_and_get_hea(qp->adapter->handle, qp->fw_handle);
        hret = ehea_h_free_resource(qp->adapter->handle, qp->fw_handle);
        if (hret != H_SUCCESS) {
                ehea_error("destroy_qp failed");
@@ -581,4 +582,45 @@ out:
        return ret;
 }
 
+void print_error_data(u64 *data)
+{
+       int length;
+       u64 type = EHEA_BMASK_GET(ERROR_DATA_TYPE, data[2]);
+       u64 resource = data[1];
+
+       length = EHEA_BMASK_GET(ERROR_DATA_LENGTH, data[0]);
+
+       if (length > EHEA_PAGESIZE)
+               length = EHEA_PAGESIZE;
+
+       if (type == 0x8) /* Queue Pair */
+               ehea_error("QP (resource=%lX) state: AER=0x%lX, AERR=0x%lX, "
+                          "port=%lX", resource, data[6], data[12], data[22]);
+
+       ehea_dump(data, length, "error data");
+}
+
+void ehea_error_data(struct ehea_adapter *adapter, u64 res_handle)
+{
+       unsigned long ret;
+       u64 *rblock;
+
+       rblock = kzalloc(PAGE_SIZE, GFP_KERNEL);
+       if (!rblock) {
+               ehea_error("Cannot allocate rblock memory.");
+               return;
+       }
 
+       ret = ehea_h_error_data(adapter->handle,
+                               res_handle,
+                               rblock);
+
+       if (ret == H_R_STATE)
+               ehea_error("No error data is available: %lX.", res_handle);
+       else if (ret == H_SUCCESS)
+               print_error_data(rblock);
+       else
+               ehea_error("Error data could not be fetched: %lX", res_handle);
+
+       kfree(rblock);
+}

diff --git a/drivers/net/ehea/ehea_qmr.h b/drivers/net/ehea/ehea_qmr.h
index 7efdc96919ca606a5920ff8aca7a95b909265484..1ff60983504d07385bed88e72dc3c7c65a3dd018 100644 (file)
--- a/drivers/net/ehea/ehea_qmr.h
+++ b/drivers/net/ehea/ehea_qmr.h
@@ -180,6 +180,9 @@ struct ehea_eqe {
        u64 entry;
 };
 
+#define ERROR_DATA_LENGTH  EHEA_BMASK_IBM(52,63)
+#define ERROR_DATA_TYPE    EHEA_BMASK_IBM(0,7)
+
 static inline void *hw_qeit_calc(struct hw_queue *queue, u64 q_offset)
 {
        struct ehea_page *current_page;
@@ -355,4 +358,6 @@ int ehea_destroy_qp(struct ehea_qp *qp);
 
 int ehea_reg_mr_adapter(struct ehea_adapter *adapter);
 
+void ehea_error_data(struct ehea_adapter *adapter, u64 res_handle);
+
 #endif /* __EHEA_QMR_H__ */