diff options
author | Oliver O'Halloran <oohall@gmail.com> | 2019-02-15 11:48:17 +1100 |
---|---|---|
committer | Michael Ellerman <mpe@ellerman.id.au> | 2019-02-22 00:10:15 +1100 |
commit | 954bd99435b8ba99e86665d6a2ec1baa1d128325 (patch) | |
tree | 27e3156fee9ccaa8162b462c198ec20ad425aae1 /arch/powerpc/kernel/eeh.c | |
parent | 6b493f6079a430fd41f66933b68d1bb1ad37ca8c (diff) | |
download | linux-954bd99435b8ba99e86665d6a2ec1baa1d128325.tar.bz2 |
powerpc/eeh: Add eeh_force_recover to debugfs
This patch adds a debugfs interface to force scheduling a recovery event.
This can be used to recover a specific PE or schedule a "special" recovery
even that checks for errors at the PHB level.
To force a recovery of a normal PE, use:
echo '<#pe>:<#phb>' > /sys/kernel/debug/powerpc/eeh_force_recover
To force a scan for broken PHBs:
echo 'hwcheck' > /sys/kernel/debug/powerpc/eeh_force_recover
Signed-off-by: Oliver O'Halloran <oohall@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Diffstat (limited to 'arch/powerpc/kernel/eeh.c')
-rw-r--r-- | arch/powerpc/kernel/eeh.c | 59 |
1 files changed, 59 insertions, 0 deletions
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 0996f22b2612..289c0b37d845 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -1838,6 +1838,62 @@ static int eeh_enable_dbgfs_get(void *data, u64 *val) DEFINE_DEBUGFS_ATTRIBUTE(eeh_enable_dbgfs_ops, eeh_enable_dbgfs_get, eeh_enable_dbgfs_set, "0x%llx\n"); + +static ssize_t eeh_force_recover_write(struct file *filp, + const char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct pci_controller *hose; + uint32_t phbid, pe_no; + struct eeh_pe *pe; + char buf[20]; + int ret; + + ret = simple_write_to_buffer(buf, sizeof(buf), ppos, user_buf, count); + if (!ret) + return -EFAULT; + + /* + * When PE is NULL the event is a "special" event. Rather than + * recovering a specific PE it forces the EEH core to scan for failed + * PHBs and recovers each. This needs to be done before any device + * recoveries can occur. + */ + if (!strncmp(buf, "hwcheck", 7)) { + __eeh_send_failure_event(NULL); + return count; + } + + ret = sscanf(buf, "%x:%x", &phbid, &pe_no); + if (ret != 2) + return -EINVAL; + + hose = pci_find_controller_for_domain(phbid); + if (!hose) + return -ENODEV; + + /* Retrieve PE */ + pe = eeh_pe_get(hose, pe_no, 0); + if (!pe) + return -ENODEV; + + /* + * We don't do any state checking here since the detection + * process is async to the recovery process. The recovery + * thread *should* not break even if we schedule a recovery + * from an odd state (e.g. PE removed, or recovery of a + * non-isolated PE) + */ + __eeh_send_failure_event(pe); + + return ret < 0 ? ret : count; +} + +static const struct file_operations eeh_force_recover_fops = { + .open = simple_open, + .llseek = no_llseek, + .write = eeh_force_recover_write, +}; #endif static int __init eeh_init_proc(void) @@ -1853,6 +1909,9 @@ static int __init eeh_init_proc(void) debugfs_create_bool("eeh_disable_recovery", 0600, powerpc_debugfs_root, &eeh_debugfs_no_recover); + debugfs_create_file_unsafe("eeh_force_recover", 0600, + powerpc_debugfs_root, NULL, + &eeh_force_recover_fops); eeh_cache_debugfs_init(); #endif } |