From 384914b2e5566dfce25f3f38d992708a9ef6f51b Mon Sep 17 00:00:00 2001 From: Ben Greear Date: Mon, 25 Aug 2014 08:37:32 +0300 Subject: [PATCH] ath10k: provide firmware crash info via debugfs Store the firmware registers and other relevant data to a firmware crash dump file and provide it to user-space via debugfs. Should help with figuring out why the firmware crashed. kvalo: remove dbglog support, rework and refactor the code to avoid ifdefs and otherwise simplify it as well Signed-off-by: Ben Greear Signed-off-by: Kalle Valo --- drivers/net/wireless/ath/ath10k/core.h | 13 ++ drivers/net/wireless/ath/ath10k/debug.c | 239 +++++++++++++++++++++++- drivers/net/wireless/ath/ath10k/debug.h | 15 ++ drivers/net/wireless/ath/ath10k/hw.h | 2 + drivers/net/wireless/ath/ath10k/pci.c | 43 ++++- drivers/net/wireless/ath/ath10k/pci.h | 3 - 6 files changed, 302 insertions(+), 13 deletions(-) diff --git a/drivers/net/wireless/ath/ath10k/core.h b/drivers/net/wireless/ath/ath10k/core.h index cca6060dbf30..8da77c706708 100644 --- a/drivers/net/wireless/ath/ath10k/core.h +++ b/drivers/net/wireless/ath/ath10k/core.h @@ -22,6 +22,8 @@ #include #include #include +#include +#include #include "htt.h" #include "htc.h" @@ -278,6 +280,15 @@ struct ath10k_vif_iter { struct ath10k_vif *arvif; }; +/* used for crash-dump storage, protected by data-lock */ +struct ath10k_fw_crash_data { + bool crashed_since_read; + + uuid_le uuid; + struct timespec timestamp; + __le32 registers[REG_DUMP_COUNT_QCA988X]; +}; + struct ath10k_debug { struct dentry *debugfs_phy; @@ -295,6 +306,8 @@ struct ath10k_debug { u8 htt_max_amsdu; u8 htt_max_ampdu; + + struct ath10k_fw_crash_data *fw_crash_data; }; enum ath10k_state { diff --git a/drivers/net/wireless/ath/ath10k/debug.c b/drivers/net/wireless/ath/ath10k/debug.c index df1abe7f1fef..2171744ba2fe 100644 --- a/drivers/net/wireless/ath/ath10k/debug.c +++ b/drivers/net/wireless/ath/ath10k/debug.c @@ -17,6 +17,9 @@ #include #include +#include +#include +#include #include "core.h" #include "debug.h" @@ -24,6 +27,85 @@ /* ms */ #define ATH10K_DEBUG_HTT_STATS_INTERVAL 1000 +#define ATH10K_FW_CRASH_DUMP_VERSION 1 + +/** + * enum ath10k_fw_crash_dump_type - types of data in the dump file + * @ATH10K_FW_CRASH_DUMP_REGDUMP: Register crash dump in binary format + */ +enum ath10k_fw_crash_dump_type { + ATH10K_FW_CRASH_DUMP_REGISTERS = 0, + + ATH10K_FW_CRASH_DUMP_MAX, +}; + +struct ath10k_tlv_dump_data { + /* see ath10k_fw_crash_dump_type above */ + __le32 type; + + /* in bytes */ + __le32 tlv_len; + + /* pad to 32-bit boundaries as needed */ + u8 tlv_data[]; +} __packed; + +struct ath10k_dump_file_data { + /* dump file information */ + + /* "ATH10K-FW-DUMP" */ + char df_magic[16]; + + __le32 len; + + /* file dump version */ + __le32 version; + + /* some info we can get from ath10k struct that might help */ + + u8 uuid[16]; + + __le32 chip_id; + + /* 0 for now, in place for later hardware */ + __le32 bus_type; + + __le32 target_version; + __le32 fw_version_major; + __le32 fw_version_minor; + __le32 fw_version_release; + __le32 fw_version_build; + __le32 phy_capability; + __le32 hw_min_tx_power; + __le32 hw_max_tx_power; + __le32 ht_cap_info; + __le32 vht_cap_info; + __le32 num_rf_chains; + + /* firmware version string */ + char fw_ver[ETHTOOL_FWVERS_LEN]; + + /* Kernel related information */ + + /* time-of-day stamp */ + __le64 tv_sec; + + /* time-of-day stamp, nano-seconds */ + __le64 tv_nsec; + + /* LINUX_VERSION_CODE */ + __le32 kernel_ver_code; + + /* VERMAGIC_STRING */ + char kernel_ver[64]; + + /* room for growth w/out changing binary format */ + u8 unused[128]; + + /* struct ath10k_tlv_dump_data + more */ + u8 data[0]; +} __packed; + static int ath10k_printk(const char *level, const char *fmt, ...) { struct va_format vaf; @@ -588,6 +670,138 @@ static const struct file_operations fops_chip_id = { .llseek = default_llseek, }; +struct ath10k_fw_crash_data * +ath10k_debug_get_new_fw_crash_data(struct ath10k *ar) +{ + struct ath10k_fw_crash_data *crash_data = ar->debug.fw_crash_data; + + lockdep_assert_held(&ar->data_lock); + + crash_data->crashed_since_read = true; + uuid_le_gen(&crash_data->uuid); + getnstimeofday(&crash_data->timestamp); + + return crash_data; +} +EXPORT_SYMBOL(ath10k_debug_get_new_fw_crash_data); + +static struct ath10k_dump_file_data *ath10k_build_dump_file(struct ath10k *ar) +{ + struct ath10k_fw_crash_data *crash_data = ar->debug.fw_crash_data; + struct ath10k_dump_file_data *dump_data; + struct ath10k_tlv_dump_data *dump_tlv; + int hdr_len = sizeof(*dump_data); + unsigned int len, sofar = 0; + unsigned char *buf; + + len = hdr_len; + len += sizeof(*dump_tlv) + sizeof(crash_data->registers); + + sofar += hdr_len; + + /* This is going to get big when we start dumping FW RAM and such, + * so go ahead and use vmalloc. + */ + buf = vzalloc(len); + if (!buf) + return NULL; + + spin_lock_bh(&ar->data_lock); + + if (!crash_data->crashed_since_read) { + spin_unlock_bh(&ar->data_lock); + vfree(buf); + return NULL; + } + + dump_data = (struct ath10k_dump_file_data *)(buf); + strlcpy(dump_data->df_magic, "ATH10K-FW-DUMP", + sizeof(dump_data->df_magic)); + dump_data->len = cpu_to_le32(len); + + dump_data->version = cpu_to_le32(ATH10K_FW_CRASH_DUMP_VERSION); + + memcpy(dump_data->uuid, &crash_data->uuid, sizeof(dump_data->uuid)); + dump_data->chip_id = cpu_to_le32(ar->chip_id); + dump_data->bus_type = cpu_to_le32(0); + dump_data->target_version = cpu_to_le32(ar->target_version); + dump_data->fw_version_major = cpu_to_le32(ar->fw_version_major); + dump_data->fw_version_minor = cpu_to_le32(ar->fw_version_minor); + dump_data->fw_version_release = cpu_to_le32(ar->fw_version_release); + dump_data->fw_version_build = cpu_to_le32(ar->fw_version_build); + dump_data->phy_capability = cpu_to_le32(ar->phy_capability); + dump_data->hw_min_tx_power = cpu_to_le32(ar->hw_min_tx_power); + dump_data->hw_max_tx_power = cpu_to_le32(ar->hw_max_tx_power); + dump_data->ht_cap_info = cpu_to_le32(ar->ht_cap_info); + dump_data->vht_cap_info = cpu_to_le32(ar->vht_cap_info); + dump_data->num_rf_chains = cpu_to_le32(ar->num_rf_chains); + + strlcpy(dump_data->fw_ver, ar->hw->wiphy->fw_version, + sizeof(dump_data->fw_ver)); + + dump_data->kernel_ver_code = cpu_to_le32(LINUX_VERSION_CODE); + strlcpy(dump_data->kernel_ver, VERMAGIC_STRING, + sizeof(dump_data->kernel_ver)); + + dump_data->tv_sec = cpu_to_le64(crash_data->timestamp.tv_sec); + dump_data->tv_nsec = cpu_to_le64(crash_data->timestamp.tv_nsec); + + /* Gather crash-dump */ + dump_tlv = (struct ath10k_tlv_dump_data *)(buf + sofar); + dump_tlv->type = cpu_to_le32(ATH10K_FW_CRASH_DUMP_REGISTERS); + dump_tlv->tlv_len = cpu_to_le32(sizeof(crash_data->registers)); + memcpy(dump_tlv->tlv_data, &crash_data->registers, + sizeof(crash_data->registers)); + sofar += sizeof(*dump_tlv) + sizeof(crash_data->registers); + + ar->debug.fw_crash_data->crashed_since_read = false; + + spin_unlock_bh(&ar->data_lock); + + return dump_data; +} + +static int ath10k_fw_crash_dump_open(struct inode *inode, struct file *file) +{ + struct ath10k *ar = inode->i_private; + struct ath10k_dump_file_data *dump; + + dump = ath10k_build_dump_file(ar); + if (!dump) + return -ENODATA; + + file->private_data = dump; + + return 0; +} + +static ssize_t ath10k_fw_crash_dump_read(struct file *file, + char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct ath10k_dump_file_data *dump_file = file->private_data; + + return simple_read_from_buffer(user_buf, count, ppos, + dump_file, + le32_to_cpu(dump_file->len)); +} + +static int ath10k_fw_crash_dump_release(struct inode *inode, + struct file *file) +{ + vfree(file->private_data); + + return 0; +} + +static const struct file_operations fops_fw_crash_dump = { + .open = ath10k_fw_crash_dump_open, + .read = ath10k_fw_crash_dump_read, + .release = ath10k_fw_crash_dump_release, + .owner = THIS_MODULE, + .llseek = default_llseek, +}; + static int ath10k_debug_htt_stats_req(struct ath10k *ar) { u64 cookie; @@ -921,11 +1135,20 @@ static const struct file_operations fops_dfs_stats = { int ath10k_debug_create(struct ath10k *ar) { + int ret; + + ar->debug.fw_crash_data = vzalloc(sizeof(*ar->debug.fw_crash_data)); + if (!ar->debug.fw_crash_data) { + ret = -ENOMEM; + goto err; + } + ar->debug.debugfs_phy = debugfs_create_dir("ath10k", ar->hw->wiphy->debugfsdir); - - if (!ar->debug.debugfs_phy) - return -ENOMEM; + if (!ar->debug.debugfs_phy) { + ret = -ENOMEM; + goto err_free_fw_crash_data; + } INIT_DELAYED_WORK(&ar->debug.htt_stats_dwork, ath10k_debug_htt_stats_dwork); @@ -941,6 +1164,9 @@ int ath10k_debug_create(struct ath10k *ar) debugfs_create_file("simulate_fw_crash", S_IRUSR, ar->debug.debugfs_phy, ar, &fops_simulate_fw_crash); + debugfs_create_file("fw_crash_dump", S_IRUSR, ar->debug.debugfs_phy, + ar, &fops_fw_crash_dump); + debugfs_create_file("chip_id", S_IRUSR, ar->debug.debugfs_phy, ar, &fops_chip_id); @@ -969,10 +1195,17 @@ int ath10k_debug_create(struct ath10k *ar) } return 0; + +err_free_fw_crash_data: + vfree(ar->debug.fw_crash_data); + +err: + return ret; } void ath10k_debug_destroy(struct ath10k *ar) { + vfree(ar->debug.fw_crash_data); cancel_delayed_work_sync(&ar->debug.htt_stats_dwork); } diff --git a/drivers/net/wireless/ath/ath10k/debug.h b/drivers/net/wireless/ath/ath10k/debug.h index a5824990bd2a..416c62bbbb26 100644 --- a/drivers/net/wireless/ath/ath10k/debug.h +++ b/drivers/net/wireless/ath/ath10k/debug.h @@ -53,6 +53,10 @@ void ath10k_debug_read_service_map(struct ath10k *ar, size_t map_size); void ath10k_debug_read_target_stats(struct ath10k *ar, struct wmi_stats_event *ev); +struct ath10k_fw_crash_data * +ath10k_debug_get_new_fw_crash_data(struct ath10k *ar); + +void ath10k_debug_dbglog_add(struct ath10k *ar, u8 *buffer, int len); #define ATH10K_DFS_STAT_INC(ar, c) (ar->debug.dfs_stats.c++) @@ -86,6 +90,17 @@ static inline void ath10k_debug_read_target_stats(struct ath10k *ar, { } +static inline void ath10k_debug_dbglog_add(struct ath10k *ar, u8 *buffer, + int len) +{ +} + +static inline struct ath10k_fw_crash_data * +ath10k_debug_get_new_fw_crash_data(struct ath10k *ar) +{ + return NULL; +} + #define ATH10K_DFS_STAT_INC(ar, c) do { } while (0) #endif /* CONFIG_ATH10K_DEBUGFS */ diff --git a/drivers/net/wireless/ath/ath10k/hw.h b/drivers/net/wireless/ath/ath10k/hw.h index ffd04890407e..13568b01de9f 100644 --- a/drivers/net/wireless/ath/ath10k/hw.h +++ b/drivers/net/wireless/ath/ath10k/hw.h @@ -39,6 +39,8 @@ /* includes also the null byte */ #define ATH10K_FIRMWARE_MAGIC "QCA-ATH10K" +#define REG_DUMP_COUNT_QCA988X 60 + struct ath10k_fw_ie { __le32 id; __le32 len; diff --git a/drivers/net/wireless/ath/ath10k/pci.c b/drivers/net/wireless/ath/ath10k/pci.c index b4ae4bb3fc09..36c4f4130027 100644 --- a/drivers/net/wireless/ath/ath10k/pci.c +++ b/drivers/net/wireless/ath/ath10k/pci.c @@ -832,16 +832,13 @@ static u16 ath10k_pci_hif_get_free_queue_number(struct ath10k *ar, u8 pipe) return ath10k_ce_num_free_src_entries(ar_pci->pipe_info[pipe].ce_hdl); } -static void ath10k_pci_hif_dump_area(struct ath10k *ar) +static void ath10k_pci_dump_registers(struct ath10k *ar, + struct ath10k_fw_crash_data *crash_data) { - u32 reg_dump_values[REG_DUMP_COUNT_QCA988X] = {}; + u32 i, reg_dump_values[REG_DUMP_COUNT_QCA988X] = {}; int ret; - u32 i; - ath10k_err("firmware crashed!\n"); - ath10k_err("hardware name %s version 0x%x\n", - ar->hw_params.name, ar->target_version); - ath10k_err("firmware version: %s\n", ar->hw->wiphy->fw_version); + lockdep_assert_held(&ar->data_lock); ret = ath10k_pci_diag_read_hi(ar, ®_dump_values[0], hi_failure_state, @@ -862,6 +859,38 @@ static void ath10k_pci_hif_dump_area(struct ath10k *ar) reg_dump_values[i + 2], reg_dump_values[i + 3]); + /* crash_data is in little endian */ + for (i = 0; i < REG_DUMP_COUNT_QCA988X; i++) + crash_data->registers[i] = cpu_to_le32(reg_dump_values[i]); +} + +static void ath10k_pci_hif_dump_area(struct ath10k *ar) +{ + struct ath10k_fw_crash_data *crash_data; + char uuid[50]; + + spin_lock_bh(&ar->data_lock); + + crash_data = ath10k_debug_get_new_fw_crash_data(ar); + + if (crash_data) + scnprintf(uuid, sizeof(uuid), "%pUl", &crash_data->uuid); + else + scnprintf(uuid, sizeof(uuid), "n/a"); + + ath10k_err("firmware crashed! (uuid %s)\n", uuid); + ath10k_err("hardware name %s version 0x%x\n", + ar->hw_params.name, ar->target_version); + ath10k_err("firmware version: %s\n", ar->hw->wiphy->fw_version); + + if (!crash_data) + goto exit; + + ath10k_pci_dump_registers(ar, crash_data); + +exit: + spin_unlock_bh(&ar->data_lock); + queue_work(ar->workqueue, &ar->restart_work); } diff --git a/drivers/net/wireless/ath/ath10k/pci.h b/drivers/net/wireless/ath/ath10k/pci.h index 662bca3922ef..294a72e01909 100644 --- a/drivers/net/wireless/ath/ath10k/pci.h +++ b/drivers/net/wireless/ath/ath10k/pci.h @@ -23,9 +23,6 @@ #include "hw.h" #include "ce.h" -/* FW dump area */ -#define REG_DUMP_COUNT_QCA988X 60 - /* * maximum number of bytes that can be handled atomically by DiagRead/DiagWrite */ -- 2.20.1