diff mbox series

[net-next,v3,3/3] cxgb4: collect hardware dump in second kernel

Message ID 302fb326d8d15d64b5ef85471df40635f25cc890.1522483891.git.rahul.lakkireddy@chelsio.com
State Deferred, archived
Delegated to: David Miller
Headers show
Series kernel: add support to collect hardware logs in crash recovery kernel | expand

Commit Message

Rahul Lakkireddy March 31, 2018, 8:50 a.m. UTC 
Register callback to collect hardware/firmware dumps in second kernel
before hardware/firmware is initialized. The dumps for each device
will be available as elf notes in /proc/vmcore in second kernel.

Signed-off-by: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
---
v3:
- Replaced all crashdd* with vmcoredd*.
- Replaced crashdd_add_dump() with vmcore_add_device_dump().
- Updated comments and commit message.

v2:
- No Changes.

Changes since rfc v2:
- Update comments and commit message for sysfs change.

rfc v2:
- Updated dump registration to the new API in patch 1.

 drivers/net/ethernet/chelsio/cxgb4/cxgb4.h       |  4 ++++
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c | 25 ++++++++++++++++++++++++
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.h |  3 +++
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c  | 10 ++++++++++
 4 files changed, 42 insertions(+)

Comments

kernel test robot April 1, 2018, 12:15 a.m. UTC | #1 
Hi Rahul,

Thank you for the patch! Yet something to improve:

[auto build test ERROR on net-next/master]

url:    https://github.com/0day-ci/linux/commits/Rahul-Lakkireddy/kernel-add-support-to-collect-hardware-logs-in-crash-recovery-kernel/20180401-060904
config: sparc64-allyesconfig (attached as .config)
compiler: sparc64-linux-gnu-gcc (Debian 7.2.0-11) 7.2.0
reproduce:
        wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # save the attached .config to linux build tree
        make.cross ARCH=sparc64 

All errors (new ones prefixed by >>):

   `.exit.data' referenced in section `.exit.text' of drivers/tty/n_hdlc.o: defined in discarded section `.exit.data' of drivers/tty/n_hdlc.o
   `.exit.data' referenced in section `.exit.text' of drivers/tty/n_hdlc.o: defined in discarded section `.exit.data' of drivers/tty/n_hdlc.o
   `.exit.data' referenced in section `.exit.text' of drivers/tty/n_hdlc.o: defined in discarded section `.exit.data' of drivers/tty/n_hdlc.o
   `.exit.data' referenced in section `.exit.text' of drivers/tty/n_hdlc.o: defined in discarded section `.exit.data' of drivers/tty/n_hdlc.o
   drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.o: In function `cxgb4_cudbg_vmcore_add_dump':
>> cxgb4_cudbg.c:(.text+0x9ec): undefined reference to `vmcore_add_device_dump'

---
0-DAY kernel test infrastructure                Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all                   Intel Corporation
kernel test robot April 1, 2018, 12:19 a.m. UTC | #2 
Hi Rahul,

Thank you for the patch! Yet something to improve:

[auto build test ERROR on net-next/master]

url:    https://github.com/0day-ci/linux/commits/Rahul-Lakkireddy/kernel-add-support-to-collect-hardware-logs-in-crash-recovery-kernel/20180401-060904
config: tile-allyesconfig (attached as .config)
compiler: tilegx-linux-gcc (GCC) 7.2.0
reproduce:
        wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # save the attached .config to linux build tree
        make.cross ARCH=tile 

All errors (new ones prefixed by >>):

   `.exit.data' referenced in section `.exit.text' of drivers/tty/n_hdlc.o: defined in discarded section `.exit.data' of drivers/tty/n_hdlc.o
   `.exit.data' referenced in section `.exit.text' of drivers/tty/n_hdlc.o: defined in discarded section `.exit.data' of drivers/tty/n_hdlc.o
   `.exit.data' referenced in section `.exit.text' of drivers/tty/n_hdlc.o: defined in discarded section `.exit.data' of drivers/tty/n_hdlc.o
   `.exit.data' referenced in section `.exit.text' of drivers/tty/n_hdlc.o: defined in discarded section `.exit.data' of drivers/tty/n_hdlc.o
   `.exit.data' referenced in section `.exit.text' of drivers/tty/n_hdlc.o: defined in discarded section `.exit.data' of drivers/tty/n_hdlc.o
   `.exit.data' referenced in section `.exit.text' of drivers/tty/n_hdlc.o: defined in discarded section `.exit.data' of drivers/tty/n_hdlc.o
   drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.o: In function `cxgb4_cudbg_vmcore_add_dump':
>> (.text+0xed0): undefined reference to `vmcore_add_device_dump'
   drivers/net/wireless/mediatek/mt76/mac80211.o: In function `mt76_init_stream_cap.isra.1':
   mac80211.c:(.text+0x8a8): undefined reference to `__sw_hweight8'

---
0-DAY kernel test infrastructure                Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all                   Intel Corporation
diff mbox series

Patch

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index 688f95440af2..01e7aad4ce5b 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -50,6 +50,7 @@ 
 #include <linux/net_tstamp.h>
 #include <linux/ptp_clock_kernel.h>
 #include <linux/ptp_classify.h>
+#include <linux/crash_dump.h>
 #include <asm/io.h>
 #include "t4_chip_type.h"
 #include "cxgb4_uld.h"
@@ -964,6 +965,9 @@  struct adapter {
 	struct hma_data hma;
 
 	struct srq_data *srq;
+
+	/* Dump buffer for collecting logs in kdump kernel */
+	struct vmcoredd_data vmcoredd;
 };
 
 /* Support for "sched-class" command to allow a TX Scheduling Class to be
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c
index 143686c60234..76433d4fe483 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c
@@ -488,3 +488,28 @@  void cxgb4_init_ethtool_dump(struct adapter *adapter)
 	adapter->eth_dump.version = adapter->params.fw_vers;
 	adapter->eth_dump.len = 0;
 }
+
+static int cxgb4_cudbg_vmcoredd_collect(struct vmcoredd_data *data, void *buf)
+{
+	struct adapter *adap = container_of(data, struct adapter, vmcoredd);
+	u32 len = data->size;
+
+	return cxgb4_cudbg_collect(adap, buf, &len, CXGB4_ETH_DUMP_ALL);
+}
+
+int cxgb4_cudbg_vmcore_add_dump(struct adapter *adap)
+{
+	struct vmcoredd_data *data = &adap->vmcoredd;
+	u32 len;
+
+	len = sizeof(struct cudbg_hdr) +
+	      sizeof(struct cudbg_entity_hdr) * CUDBG_MAX_ENTITY;
+	len += CUDBG_DUMP_BUFF_SIZE;
+
+	data->size = len;
+	snprintf(data->name, sizeof(data->name), "%s_%s", cxgb4_driver_name,
+		 adap->name);
+	data->vmcoredd_callback = cxgb4_cudbg_vmcoredd_collect;
+
+	return vmcore_add_device_dump(data);
+}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.h
index ce1ac9a1c878..ef59ba1ed968 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.h
@@ -41,8 +41,11 @@  enum CXGB4_ETHTOOL_DUMP_FLAGS {
 	CXGB4_ETH_DUMP_HW = (1 << 1), /* various FW and HW dumps */
 };
 
+#define CXGB4_ETH_DUMP_ALL (CXGB4_ETH_DUMP_MEM | CXGB4_ETH_DUMP_HW)
+
 u32 cxgb4_get_dump_length(struct adapter *adap, u32 flag);
 int cxgb4_cudbg_collect(struct adapter *adap, void *buf, u32 *buf_size,
 			u32 flag);
 void cxgb4_init_ethtool_dump(struct adapter *adapter);
+int cxgb4_cudbg_vmcore_add_dump(struct adapter *adap);
 #endif /* __CXGB4_CUDBG_H__ */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 0072580e2c25..040004db4a35 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -5530,6 +5530,16 @@  static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (err)
 		goto out_free_adapter;
 
+	if (is_kdump_kernel()) {
+		/* Collect hardware state and append to /proc/vmcore */
+		err = cxgb4_cudbg_vmcore_add_dump(adapter);
+		if (err) {
+			dev_warn(adapter->pdev_dev,
+				 "Fail collecting vmcore device dump, err: %d. Continuing\n",
+				 err);
+			err = 0;
+		}
+	}
 
 	if (!is_t4(adapter->params.chip)) {
 		s_qpp = (QUEUESPERPAGEPF0_S +