d/freebsd-skq
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
538779c1a0
freebsd-skq/sys/dev/mfi/mfi_debug.c

275 lines
6.6 KiB
C
Raw Normal View History

Add a command debugging module and a periodic watchdog timer. Sponsored by: IronPort
2006-09-25 11:35:34 +00:00
/*-
* Copyright (c) 2006 IronPort Systems
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
*
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*/
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
Fix a bad #include statment
2006-09-27 04:54:23 +00:00
#include "opt_mfi.h"
Add a command debugging module and a periodic watchdog timer. Sponsored by: IronPort
2006-09-25 11:35:34 +00:00
#ifdef MFI_DEBUG
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/kernel.h>
#include <sys/conf.h>
#include <sys/bus.h>
#include <sys/bio.h>
#include <sys/lock.h>
#include <sys/mutex.h>
#include <sys/malloc.h>
#include <sys/selinfo.h>
The sys/sysctl.h header is needed when MFI_DEBUG is defined. Nod from: jhb
2011-11-16 18:42:39 +00:00
#include <sys/sysctl.h>
Add a command debugging module and a periodic watchdog timer. Sponsored by: IronPort
2006-09-25 11:35:34 +00:00
#include <sys/taskqueue.h>
#include <sys/uio.h>
#include <machine/resource.h>
#include <machine/bus.h>
- Add a command validator for use in debugging. - Fix the locking protocol to eliminate races between normal I/O and AENs. - Various small improvements and usability tweaks. Sponsored by: IronPort Portions Submitted by: Doug Ambrisko
2006-10-16 04:18:38 +00:00
#include <vm/vm.h>
#include <vm/pmap.h>
Add a command debugging module and a periodic watchdog timer. Sponsored by: IronPort
2006-09-25 11:35:34 +00:00
#include <dev/mfi/mfireg.h>
#include <dev/mfi/mfi_ioctl.h>
#include <dev/mfi/mfivar.h>
static void
mfi_print_frame_flags(device_t dev, uint32_t flags)
{
Fixes queuing issues where mfi_release_command blindly sets the cm_flags = 0 without first removing the command from the relavent queue. This was causing panics in the queue functions which check to ensure a command is not on another queue. Fixed some cases where the error from mfi_mapcmd was lost and where the command was never released / dequeued in error cases. Ensure that all failures to mfi_mapcmd are logged. Fixed possible null pointer exception in mfi_aen_setup if mfi_get_log_state failed. Fixed mfi_parse_entries & mfi_aen_setup not returning possible errors. Corrected MFI_DUMP_CMDS calls with invalid vars SC vs sc. Commands which have timed out now set cm_error to ETIMEDOUT and call mfi_complete which prevents them getting stuck in the busy queue forever. Fixed possible use of NULL pointer in mfi_tbolt_get_cmd. Changed output formats to be more easily recognisable when debugging. Optimised mfi_cmd_pool_tbolt cleanup. Made information about driver limiting commands always display as for modern cards this can be severe. Fixed mfi_tbolt_alloc_cmd out of memory case which previously didnt return an error. Added malloc checks for request_desc_pool including free when subsiquent errors are detected. Fixed overflow error in SIMD reply descriptor check. Fixed tbolt_cmd leak in mfi_build_and_issue_cmd if there's an error during IO build. Elimintated double checks on sc->mfi_aen_cm & sc->mfi_map_sync_cm in mfi_shutdown. Move local hdr calculation after error check in mfi_aen_complete. Fixed wakeup on NULL in mfi_aen_complete. Fixed mfi_aen_cm cleanup in mfi_process_fw_state_chg_isr not checking if it was NULL. Changed mfi_alloc_commands to error if bus_dmamap_create fails. Previously we would try to continue with the number of allocated commands but lots of places in the driver assume sc->mfi_max_fw_cmds is whats available so its unsafe to do this without lots of changes. Removed mfi_total_cmds as its no longer used due the above change. Corrected mfi_tbolt_alloc_cmd to return ENOMEM where appropriate. Fixed timeouts actually firing at double what they should. Setting hw.mfi.max_cmds=-1 now configures to use the controller max. A few style (9) fixes e.g. braced single line conditions and double blank lines Cleaned up queuing macros Removed invalid queuing tests for multiple queues Trap and deal with errors when doing sends in mfi_data_cb Refactored frame sending into one method with error checking of the return code so we can ensure commands aren't left on the queue after error. This ensures that mfi_mapcmd & mfi_data_cb leave the queue in a valid state. Refactored how commands are cleaned up, mfi_release_command now ensures that all queues and command state is maintained in a consistent state. Prevent NULL pointer use in mfi_tbolt_complete_cmd Fixed use of NULL sc->mfi_map_sync_cm in wakeup Added defines to help with output of mfi_cmd and header flags. Fixed mfi_tbolt_init_MFI_queue invalidating cm_index of the acquired mfi_cmd. Reset now reinitialises sync map as well as AEN. Fixed possible use of NULL pointer in mfi_build_and_issue_cmd Fixed mfi_tbolt_init_MFI_queue call to mfi_process_fw_state_chg_isr causing panic on failure. Ensure that tbolt cards always initialise next_host_reply_index and free_host_reply_index (based off mfi_max_fw_cmds) on both startup and reset as per the linux driver. Fixed mfi_tbolt_complete_cmd not acknowledging unknown commands so it didn't clear the controller. Prevent locks from being dropped and re-acquired in the following functions which was allowing multiple threads to enter critical methods such as mfi_tbolt_complete_cmd & mfi_process_fw_state_chg_isr:- * mfi_tbolt_init_MFI_queue * mfi_aen_complete / mfi_aen_register * mfi_tbolt_sync_map_info * mfi_get_log_state * mfi_parse_entries The locking for these functions was promoting to higher level methods. This also fixed MFI_LINUX_SET_AEN_2 which was already acquiring the lock, so would have paniced for recursive lock. This also required changing malloc of ld_sync in mfi_tbolt_sync_map_info to M_NOWAIT which can hence now fail but this was already expected as its return was being tested. Removed the assignment of cm_index in mfi_tbolt_init_MFI_queue which breaks the world if the cmd returned by mfi_dequeue_free isn't the first cmd. Fixed locking in mfi_data_cb, this is an async callback from bus_dmamap_load which could hence be called after the caller has dropped the lock. If we don't have the lock we aquire it and ensure we unlock before returning. Fixed locking mfi_comms_init when mfi_dequeue_free fails. Fixed mfi_build_and_issue_cmd not returning tbolt cmds aquired to the pool on error. Fixed mfi_abort not dropping the io lock when mfi_dequeue_free fails. Added hw.mfi.polled_cmd_timeout sysctl that enables tuning of polled timeouts. This shouldn't be reduced below 50 seconds as its used for firmware patching which can take quite some time. Added hw.mfi.fw_reset_test sysctl which is avaliable when compiled with MFI_DEBUG and allows the testing of controller reset that was provoking a large number of the issues encountered here. Reviewed by: Doug Ambrisko Approved by: pjd (mentor) MFC after: 1 month
2013-02-27 02:21:10 +00:00
device_printf(dev, "flags=%b\n", flags, MFI_FRAME_FMT);
Add a command debugging module and a periodic watchdog timer. Sponsored by: IronPort
2006-09-25 11:35:34 +00:00
}
static void
mfi_print_sgl(struct mfi_frame_header *hdr, union mfi_sgl *sgl, int count)
{
int i, columns = 0;
printf("SG List:\n");
for (i = 0; i < count; i++) {
MFhead_mfi r227068 First cut of new HW support from LSI and merge into FreeBSD. Supports Drake Skinny and ThunderBolt cards. MFhead_mfi r227574 Style MFhead_mfi r227579 Use bus_addr_t instead of uintXX_t. MFhead_mfi r227580 MSI support MFhead_mfi r227612 More bus_addr_t and remove "#ifdef __amd64__". MFhead_mfi r227905 Improved timeout support from Scott. MFhead_mfi r228108 Make file. MFhead_mfi r228208 Fixed botched merge of Skinny support and enhanced handling in call back routine. MFhead_mfi r228279 Remove superfluous !TAILQ_EMPTY() checks before TAILQ_FOREACH(). MFhead_mfi r228310 Move mfi_decode_evt() to taskqueue. MFhead_mfi r228320 Implement MFI_DEBUG for 64bit S/G lists. MFhead_mfi r231988 Restore structure layout by reverting the array header to use [0] instead of [1]. MFhead_mfi r232412 Put wildcard pattern later in the match table. MFhead_mfi r232413 Use lower case for hexadecimal numbers to match surrounding style. MFhead_mfi r232414 Add more Thunderbolt variants. MFhead_mfi r232888 Don't act on events prior to boot or when shutting down. Add hw.mfi.detect_jbod_change to enable or disable acting on JBOD type of disks being added on insert and removed on removing. Switch hw.mfi.msi to 1 by default since it works better on newer cards. MFhead_mfi r233016 Release driver lock before taking Giant when deleting children. Use TAILQ_FOREACH_SAFE when items can be deleted. Make code a little simplier to follow. Fix a couple more style issues. MFhead_mfi r233620 Update mfi_spare/mfi_array with the actual number of elements for array_ref and pd. Change these max. #define names to avoid name space collisions. This will require an update to mfiutil It avoids mfiutil having to do a magic calculation. Add a note and #define to state that a "SYSTEM" disk is really what the firmware calls a "JBOD" drive. Thanks to the many that helped, LSI for the initial code drop, mav, delphij, jhb, sbruno that all helped with code and testing.
2012-03-30 23:05:48 +00:00
if (hdr->flags & MFI_FRAME_IEEE_SGL) {
printf("0x%lx:%06d ", (u_long)sgl->sg_skinny[i].addr,
sgl->sg_skinny[i].len);
columns += 26;
if (columns > 77) {
printf("\n");
columns = 0;
}
} else if (hdr->flags & MFI_FRAME_SGL64) {
Add a command debugging module and a periodic watchdog timer. Sponsored by: IronPort
2006-09-25 11:35:34 +00:00
printf("0x%lx:%06d ", (u_long)sgl->sg64[i].addr,
sgl->sg64[i].len);
columns += 26;
if (columns > 77) {
printf("\n");
columns = 0;
}
} else {
printf("0x%x:%06d ", sgl->sg32[i].addr,
sgl->sg32[i].len);
columns += 18;
if (columns > 71) {
printf("\n");
columns = 0;
}
}
}
if (columns != 0)
printf("\n");
}
static void
mfi_print_ldio(struct mfi_softc *sc, device_t dev, struct mfi_command *cm)
{
struct mfi_io_frame *io;
struct mfi_frame_header *hdr;
io = &cm->cm_frame->io;
hdr = &io->header;
device_printf(dev, "cmd=%s target_id=%d sg_count=%d data_len=%d "
"lba=%d\n", (hdr->cmd == MFI_CMD_LD_READ) ? "LD_READ":"LD_WRITE",
hdr->target_id, hdr->sg_count, hdr->data_len, io->lba_lo);
mfi_print_frame_flags(dev, hdr->flags);
mfi_print_sgl(hdr, &io->sgl, hdr->sg_count);
}
static void
mfi_print_dcmd(struct mfi_softc *sc, device_t dev, struct mfi_command *cm)
{
struct mfi_dcmd_frame *dcmd;
struct mfi_frame_header *hdr;
const char *opcode;
dcmd = &cm->cm_frame->dcmd;
hdr = &dcmd->header;
switch (dcmd->opcode) {
case MFI_DCMD_CTRL_GETINFO:
opcode = "CTRL_GETINFO";
break;
case MFI_DCMD_CTRL_FLUSHCACHE:
opcode = "CTRL_FLUSHCACHE";
break;
case MFI_DCMD_CTRL_SHUTDOWN:
opcode = "CTRL_SHUTDOWN";
break;
case MFI_DCMD_CTRL_EVENT_GETINFO:
opcode = "EVENT_GETINFO";
break;
case MFI_DCMD_CTRL_EVENT_GET:
opcode = "EVENT_GET";
break;
case MFI_DCMD_CTRL_EVENT_WAIT:
opcode = "EVENT_WAIT";
break;
case MFI_DCMD_LD_GET_LIST:
opcode = "LD_GET_LIST";
break;
case MFI_DCMD_LD_GET_INFO:
opcode = "LD_GET_INFO";
break;
case MFI_DCMD_LD_GET_PROP:
opcode = "LD_GET_PROP";
break;
case MFI_DCMD_LD_SET_PROP:
opcode = "LD_SET_PROP";
break;
case MFI_DCMD_CLUSTER:
opcode = "CLUSTER";
break;
case MFI_DCMD_CLUSTER_RESET_ALL:
opcode = "CLUSTER_RESET_ALL";
break;
case MFI_DCMD_CLUSTER_RESET_LD:
opcode = "CLUSTER_RESET_LD";
break;
First fix pr 167226: ThunderBolt cannot read sector >= 2^32 or 2^21 with supplied patch. Second the bigger change, fix RAID operation on ThunderBolt base card such as physically removing a disk from a RAID and replacing it. The current situation is the RAID firmware effectively hangs waiting for an acknowledgement from the driver. This is due to the firmware support of the driver actually accessing the RAID from under the firmware. This is an interesting feature that the FreeBSD driver does not use. However, when the firmare detects the driver has attached it then expects the driver will synchronize LD's with the firmware. If the driver does not sync. then the management part of the firmware will hang waiting for it so a pulled driver will listed as still there. The fix for this problem isn't extremely difficult. However, figuring out why some of the code was the way it was and then redoing it was involved. Not have a spec. made it harder to try to figure out. The existing driver would send a MFI_DCMD_LD_MAP_GET_INFO command in write mode to acknowledge a LD state change. In read mode it gets the RAID map from the firmware. The FreeBSD driver doesn't do that currently. It could be added in the future with the appropriate structures. To simplify things, get the current LD state and then build the MFI_DCMD_LD_MAP_GET_INFO/write command so that it sends an acknowledgement for each LD. The map would probably state which LD's changed so then the driver could probably just acknowledge the LD's that changed versus all. This doesn't seem to be a problem. When a MFI_DCMD_LD_MAP_GET_INFO/write command is sent to the firmware, it will complete later when a change to the LD's happen. So it is very much like an AEN command returning when something happened. When the MFI_DCMD_LD_MAP_GET_INFO/write command completes, we refire the sync'ing of the LD state. This needs to be done in as an event so that MFI_DCMD_LD_GET_LIST can wait for that command to complete before issuing the MFI_DCMD_LD_MAP_GET_INFO/write. The prior code didn't use the call-back function and tried to intercept the MFI_DCMD_LD_MAP_GET_INFO/write command when processing an interrupt. This added a bunch of code complexity to the interrupt handler. Using the call-back that is done for other commands got rid of this need. So the interrupt handler is greatly simplified. It seems that even commands that shouldn't be acknowledged end up in the interrupt handler. To deal with this, code was added to check to see if a command is in the busy queue or not. This might have contributed to the interrupt storm happening without MSI enabled on these cards. Note that MFI_DCMD_LD_MAP_GET_INFO/read returns right away. It would be interesting to see what other complexity could be removed from the ThunderBolt driver that really isn't needed in our mode of operation. Letting the RAID firmware do all of the I/O to disks is a lot faster since it can use its caches. It greatly simplifies what the driver has to do and potential bugs if the driver and firmware are not in sync. Simplify the aen_abort/cm_map_abort and put it in the softc versus in the command structure. This should get merged to 9 before the driver is merged to 8. PR: 167226 Submitted by: Petr Lampa MFC after: 3 days
2012-05-04 16:00:39 +00:00
case MFI_DCMD_LD_MAP_GET_INFO:
opcode = "LD_MAP_GET_INFO";
break;
Add support for getting and setting BBU properties related to battery relearning. Specifically, add subcommands to mfiutil(8) which allow the user to set the BBU and autolearn modes when the firmware supports it, and add a subcommand which kicks off a battery relearn. Reviewed by: sbruno, rstone Tested by: sbruno Approved by: rstone (co-mentor) MFC after: 2 weeks Sponsored by: Sandvine Incorporated
2013-04-08 17:46:45 +00:00
case MFI_DCMD_BBU_START_LEARN:
opcode = "BBU_START_LEARN";
break;
case MFI_DCMD_BBU_GET_PROP:
opcode = "BBU_GET_PROP";
break;
case MFI_DCMD_BBU_SET_PROP:
opcode = "BBU_SET_PROP";
break;
Add a command debugging module and a periodic watchdog timer. Sponsored by: IronPort
2006-09-25 11:35:34 +00:00
default:
opcode = "UNKNOWN";
break;
}
device_printf(dev, "cmd=MFI_CMD_DCMD opcode=%s data_len=%d\n",
opcode, hdr->data_len);
mfi_print_frame_flags(dev, hdr->flags);
mfi_print_sgl(hdr, &dcmd->sgl, hdr->sg_count);
}
static void
mfi_print_generic_frame(struct mfi_softc *sc, struct mfi_command *cm)
{
hexdump(cm->cm_frame, cm->cm_total_frame_size, NULL, HD_OMIT_CHARS);
}
void
mfi_print_cmd(struct mfi_command *cm)
{
device_t dev;
struct mfi_softc *sc;
sc = cm->cm_sc;
dev = sc->mfi_dev;
device_printf(dev, "cm=%p index=%d total_frame_size=%d "
"extra_frames=%d\n", cm, cm->cm_index, cm->cm_total_frame_size,
cm->cm_extra_frames);
Fixes queuing issues where mfi_release_command blindly sets the cm_flags = 0 without first removing the command from the relavent queue. This was causing panics in the queue functions which check to ensure a command is not on another queue. Fixed some cases where the error from mfi_mapcmd was lost and where the command was never released / dequeued in error cases. Ensure that all failures to mfi_mapcmd are logged. Fixed possible null pointer exception in mfi_aen_setup if mfi_get_log_state failed. Fixed mfi_parse_entries & mfi_aen_setup not returning possible errors. Corrected MFI_DUMP_CMDS calls with invalid vars SC vs sc. Commands which have timed out now set cm_error to ETIMEDOUT and call mfi_complete which prevents them getting stuck in the busy queue forever. Fixed possible use of NULL pointer in mfi_tbolt_get_cmd. Changed output formats to be more easily recognisable when debugging. Optimised mfi_cmd_pool_tbolt cleanup. Made information about driver limiting commands always display as for modern cards this can be severe. Fixed mfi_tbolt_alloc_cmd out of memory case which previously didnt return an error. Added malloc checks for request_desc_pool including free when subsiquent errors are detected. Fixed overflow error in SIMD reply descriptor check. Fixed tbolt_cmd leak in mfi_build_and_issue_cmd if there's an error during IO build. Elimintated double checks on sc->mfi_aen_cm & sc->mfi_map_sync_cm in mfi_shutdown. Move local hdr calculation after error check in mfi_aen_complete. Fixed wakeup on NULL in mfi_aen_complete. Fixed mfi_aen_cm cleanup in mfi_process_fw_state_chg_isr not checking if it was NULL. Changed mfi_alloc_commands to error if bus_dmamap_create fails. Previously we would try to continue with the number of allocated commands but lots of places in the driver assume sc->mfi_max_fw_cmds is whats available so its unsafe to do this without lots of changes. Removed mfi_total_cmds as its no longer used due the above change. Corrected mfi_tbolt_alloc_cmd to return ENOMEM where appropriate. Fixed timeouts actually firing at double what they should. Setting hw.mfi.max_cmds=-1 now configures to use the controller max. A few style (9) fixes e.g. braced single line conditions and double blank lines Cleaned up queuing macros Removed invalid queuing tests for multiple queues Trap and deal with errors when doing sends in mfi_data_cb Refactored frame sending into one method with error checking of the return code so we can ensure commands aren't left on the queue after error. This ensures that mfi_mapcmd & mfi_data_cb leave the queue in a valid state. Refactored how commands are cleaned up, mfi_release_command now ensures that all queues and command state is maintained in a consistent state. Prevent NULL pointer use in mfi_tbolt_complete_cmd Fixed use of NULL sc->mfi_map_sync_cm in wakeup Added defines to help with output of mfi_cmd and header flags. Fixed mfi_tbolt_init_MFI_queue invalidating cm_index of the acquired mfi_cmd. Reset now reinitialises sync map as well as AEN. Fixed possible use of NULL pointer in mfi_build_and_issue_cmd Fixed mfi_tbolt_init_MFI_queue call to mfi_process_fw_state_chg_isr causing panic on failure. Ensure that tbolt cards always initialise next_host_reply_index and free_host_reply_index (based off mfi_max_fw_cmds) on both startup and reset as per the linux driver. Fixed mfi_tbolt_complete_cmd not acknowledging unknown commands so it didn't clear the controller. Prevent locks from being dropped and re-acquired in the following functions which was allowing multiple threads to enter critical methods such as mfi_tbolt_complete_cmd & mfi_process_fw_state_chg_isr:- * mfi_tbolt_init_MFI_queue * mfi_aen_complete / mfi_aen_register * mfi_tbolt_sync_map_info * mfi_get_log_state * mfi_parse_entries The locking for these functions was promoting to higher level methods. This also fixed MFI_LINUX_SET_AEN_2 which was already acquiring the lock, so would have paniced for recursive lock. This also required changing malloc of ld_sync in mfi_tbolt_sync_map_info to M_NOWAIT which can hence now fail but this was already expected as its return was being tested. Removed the assignment of cm_index in mfi_tbolt_init_MFI_queue which breaks the world if the cmd returned by mfi_dequeue_free isn't the first cmd. Fixed locking in mfi_data_cb, this is an async callback from bus_dmamap_load which could hence be called after the caller has dropped the lock. If we don't have the lock we aquire it and ensure we unlock before returning. Fixed locking mfi_comms_init when mfi_dequeue_free fails. Fixed mfi_build_and_issue_cmd not returning tbolt cmds aquired to the pool on error. Fixed mfi_abort not dropping the io lock when mfi_dequeue_free fails. Added hw.mfi.polled_cmd_timeout sysctl that enables tuning of polled timeouts. This shouldn't be reduced below 50 seconds as its used for firmware patching which can take quite some time. Added hw.mfi.fw_reset_test sysctl which is avaliable when compiled with MFI_DEBUG and allows the testing of controller reset that was provoking a large number of the issues encountered here. Reviewed by: Doug Ambrisko Approved by: pjd (mentor) MFC after: 1 month
2013-02-27 02:21:10 +00:00
device_printf(dev, "flags=%b\n", cm->cm_flags, MFI_CMD_FLAGS_FMT);
Add a command debugging module and a periodic watchdog timer. Sponsored by: IronPort
2006-09-25 11:35:34 +00:00
switch (cm->cm_frame->header.cmd) {
case MFI_CMD_DCMD:
mfi_print_dcmd(sc, dev, cm);
break;
case MFI_CMD_LD_READ:
case MFI_CMD_LD_WRITE:
mfi_print_ldio(sc, dev, cm);
break;
default:
mfi_print_generic_frame(sc, cm);
break;
}
return;
}
void
mfi_dump_cmds(struct mfi_softc *sc)
{
int i;
Fixes queuing issues where mfi_release_command blindly sets the cm_flags = 0 without first removing the command from the relavent queue. This was causing panics in the queue functions which check to ensure a command is not on another queue. Fixed some cases where the error from mfi_mapcmd was lost and where the command was never released / dequeued in error cases. Ensure that all failures to mfi_mapcmd are logged. Fixed possible null pointer exception in mfi_aen_setup if mfi_get_log_state failed. Fixed mfi_parse_entries & mfi_aen_setup not returning possible errors. Corrected MFI_DUMP_CMDS calls with invalid vars SC vs sc. Commands which have timed out now set cm_error to ETIMEDOUT and call mfi_complete which prevents them getting stuck in the busy queue forever. Fixed possible use of NULL pointer in mfi_tbolt_get_cmd. Changed output formats to be more easily recognisable when debugging. Optimised mfi_cmd_pool_tbolt cleanup. Made information about driver limiting commands always display as for modern cards this can be severe. Fixed mfi_tbolt_alloc_cmd out of memory case which previously didnt return an error. Added malloc checks for request_desc_pool including free when subsiquent errors are detected. Fixed overflow error in SIMD reply descriptor check. Fixed tbolt_cmd leak in mfi_build_and_issue_cmd if there's an error during IO build. Elimintated double checks on sc->mfi_aen_cm & sc->mfi_map_sync_cm in mfi_shutdown. Move local hdr calculation after error check in mfi_aen_complete. Fixed wakeup on NULL in mfi_aen_complete. Fixed mfi_aen_cm cleanup in mfi_process_fw_state_chg_isr not checking if it was NULL. Changed mfi_alloc_commands to error if bus_dmamap_create fails. Previously we would try to continue with the number of allocated commands but lots of places in the driver assume sc->mfi_max_fw_cmds is whats available so its unsafe to do this without lots of changes. Removed mfi_total_cmds as its no longer used due the above change. Corrected mfi_tbolt_alloc_cmd to return ENOMEM where appropriate. Fixed timeouts actually firing at double what they should. Setting hw.mfi.max_cmds=-1 now configures to use the controller max. A few style (9) fixes e.g. braced single line conditions and double blank lines Cleaned up queuing macros Removed invalid queuing tests for multiple queues Trap and deal with errors when doing sends in mfi_data_cb Refactored frame sending into one method with error checking of the return code so we can ensure commands aren't left on the queue after error. This ensures that mfi_mapcmd & mfi_data_cb leave the queue in a valid state. Refactored how commands are cleaned up, mfi_release_command now ensures that all queues and command state is maintained in a consistent state. Prevent NULL pointer use in mfi_tbolt_complete_cmd Fixed use of NULL sc->mfi_map_sync_cm in wakeup Added defines to help with output of mfi_cmd and header flags. Fixed mfi_tbolt_init_MFI_queue invalidating cm_index of the acquired mfi_cmd. Reset now reinitialises sync map as well as AEN. Fixed possible use of NULL pointer in mfi_build_and_issue_cmd Fixed mfi_tbolt_init_MFI_queue call to mfi_process_fw_state_chg_isr causing panic on failure. Ensure that tbolt cards always initialise next_host_reply_index and free_host_reply_index (based off mfi_max_fw_cmds) on both startup and reset as per the linux driver. Fixed mfi_tbolt_complete_cmd not acknowledging unknown commands so it didn't clear the controller. Prevent locks from being dropped and re-acquired in the following functions which was allowing multiple threads to enter critical methods such as mfi_tbolt_complete_cmd & mfi_process_fw_state_chg_isr:- * mfi_tbolt_init_MFI_queue * mfi_aen_complete / mfi_aen_register * mfi_tbolt_sync_map_info * mfi_get_log_state * mfi_parse_entries The locking for these functions was promoting to higher level methods. This also fixed MFI_LINUX_SET_AEN_2 which was already acquiring the lock, so would have paniced for recursive lock. This also required changing malloc of ld_sync in mfi_tbolt_sync_map_info to M_NOWAIT which can hence now fail but this was already expected as its return was being tested. Removed the assignment of cm_index in mfi_tbolt_init_MFI_queue which breaks the world if the cmd returned by mfi_dequeue_free isn't the first cmd. Fixed locking in mfi_data_cb, this is an async callback from bus_dmamap_load which could hence be called after the caller has dropped the lock. If we don't have the lock we aquire it and ensure we unlock before returning. Fixed locking mfi_comms_init when mfi_dequeue_free fails. Fixed mfi_build_and_issue_cmd not returning tbolt cmds aquired to the pool on error. Fixed mfi_abort not dropping the io lock when mfi_dequeue_free fails. Added hw.mfi.polled_cmd_timeout sysctl that enables tuning of polled timeouts. This shouldn't be reduced below 50 seconds as its used for firmware patching which can take quite some time. Added hw.mfi.fw_reset_test sysctl which is avaliable when compiled with MFI_DEBUG and allows the testing of controller reset that was provoking a large number of the issues encountered here. Reviewed by: Doug Ambrisko Approved by: pjd (mentor) MFC after: 1 month
2013-02-27 02:21:10 +00:00
for (i = 0; i < sc->mfi_max_fw_cmds; i++)
Add a command debugging module and a periodic watchdog timer. Sponsored by: IronPort
2006-09-25 11:35:34 +00:00
mfi_print_generic_frame(sc, &sc->mfi_commands[i]);
}
- Add a command validator for use in debugging. - Fix the locking protocol to eliminate races between normal I/O and AENs. - Various small improvements and usability tweaks. Sponsored by: IronPort Portions Submitted by: Doug Ambrisko
2006-10-16 04:18:38 +00:00
void
mfi_validate_sg(struct mfi_softc *sc, struct mfi_command *cm,
const char *function, int line)
{
struct mfi_frame_header *hdr;
int i;
uint32_t count = 0, data_len;
hdr = &cm->cm_frame->header;
count = 0;
for (i = 0; i < hdr->sg_count; i++) {
MFhead_mfi r227068 First cut of new HW support from LSI and merge into FreeBSD. Supports Drake Skinny and ThunderBolt cards. MFhead_mfi r227574 Style MFhead_mfi r227579 Use bus_addr_t instead of uintXX_t. MFhead_mfi r227580 MSI support MFhead_mfi r227612 More bus_addr_t and remove "#ifdef __amd64__". MFhead_mfi r227905 Improved timeout support from Scott. MFhead_mfi r228108 Make file. MFhead_mfi r228208 Fixed botched merge of Skinny support and enhanced handling in call back routine. MFhead_mfi r228279 Remove superfluous !TAILQ_EMPTY() checks before TAILQ_FOREACH(). MFhead_mfi r228310 Move mfi_decode_evt() to taskqueue. MFhead_mfi r228320 Implement MFI_DEBUG for 64bit S/G lists. MFhead_mfi r231988 Restore structure layout by reverting the array header to use [0] instead of [1]. MFhead_mfi r232412 Put wildcard pattern later in the match table. MFhead_mfi r232413 Use lower case for hexadecimal numbers to match surrounding style. MFhead_mfi r232414 Add more Thunderbolt variants. MFhead_mfi r232888 Don't act on events prior to boot or when shutting down. Add hw.mfi.detect_jbod_change to enable or disable acting on JBOD type of disks being added on insert and removed on removing. Switch hw.mfi.msi to 1 by default since it works better on newer cards. MFhead_mfi r233016 Release driver lock before taking Giant when deleting children. Use TAILQ_FOREACH_SAFE when items can be deleted. Make code a little simplier to follow. Fix a couple more style issues. MFhead_mfi r233620 Update mfi_spare/mfi_array with the actual number of elements for array_ref and pd. Change these max. #define names to avoid name space collisions. This will require an update to mfiutil It avoids mfiutil having to do a magic calculation. Add a note and #define to state that a "SYSTEM" disk is really what the firmware calls a "JBOD" drive. Thanks to the many that helped, LSI for the initial code drop, mav, delphij, jhb, sbruno that all helped with code and testing.
2012-03-30 23:05:48 +00:00
if (hdr->flags & MFI_FRAME_IEEE_SGL)
count += cm->cm_sg->sg_skinny[i].len;
else if (hdr->flags & MFI_FRAME_SGL64)
count += cm->cm_sg->sg64[i].len;
else
count += cm->cm_sg->sg32[i].len;
- Add a command validator for use in debugging. - Fix the locking protocol to eliminate races between normal I/O and AENs. - Various small improvements and usability tweaks. Sponsored by: IronPort Portions Submitted by: Doug Ambrisko
2006-10-16 04:18:38 +00:00
}
/*
count++;
*/
data_len = hdr->data_len;
switch (hdr->cmd) {
case MFI_CMD_LD_READ:
case MFI_CMD_LD_WRITE:
data_len = data_len * 512;
case MFI_CMD_DCMD:
if (count != data_len) {
device_printf(sc->mfi_dev,
"%s %d COMMAND %p S/G count bad %d %d %d 0x%jx\n",
function, line, cm, count, data_len, cm->cm_len,
(intmax_t)pmap_kextract((vm_offset_t)cm->cm_data));
MFI_PRINT_CMD(cm);
}
}
}
Add a command debugging module and a periodic watchdog timer. Sponsored by: IronPort
2006-09-25 11:35:34 +00:00
#endif
Reference in New Issue Copy Permalink