fsi and hwmon (occ): Prevent occasional checksum failures
Subsystems (2)
Eddie James
maintainercover fsi and hwmon (occ): Prevent occasional checksum failures
Due to the OCC communication design with a shared SRAM area, checkum errors are expected due to corrupted buffer from OCC communications with other system components. Therefore, use a unique errno for checksum failures and retry the command twice in that case.
Eddie James (2):
fsi: occ: Fix checksum failure mode
hwmon (occ): Retry for checksum failure
drivers/fsi/fsi-occ.c | 7 +++++-- drivers/hwmon/occ/p9_sbe.c | 28 ++++++++++++++++++---------- 2 files changed, 23 insertions(+), 12 deletions(-)
Signature · 1 line
2.27.0
Eddie James
maintainerPATCH 1/2 fsi: occ: Fix checksum failure mode
Change the checksum errno to something different than the errno used for a bad SBE message. In addition, don't set the user's response length to the data length in this case, since it's not SBE FFDC.
--- drivers/fsi/fsi-occ.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)
drivers/fsi/fsi-occ.c +5 -2
@@ -246,7 +246,7 @@ static int occ_verify_checksum(struct occ *occ, struct occ_response *resp,if (checksum != checksum_resp) {dev_err (occ->dev,"Bad checksum: %04x!=%04x\n" , checksum, checksum_resp); -return -EBADMSG ; +return -EBADE ; }return 0 ;
@@ -575,8 +575,11 @@ int fsi_occ_submit(struct device *dev, const void *request, size_t req_len,dev_dbg (dev,"resp_status=%02x resp_data_len=%d\n" , resp->return_status, resp_data_length); - occ->client_response_size = resp_data_length +7 ; rc =occ_verify_checksum (occ, resp, resp_data_length); +if (rc) + goto done; + + occ->client_response_size = resp_data_length +7 ; done: *resp_len = occ->client_response_size;
Signature · 1 line
2.27.0
Eddie James
maintainerPATCH 2/2 hwmon (occ): Retry for checksum failure
In reply to Eddie JamesDue to the OCC communication design with a shared SRAM area, checkum errors are expected due to corrupted buffer from OCC communications with other system components. Therefore, retry the command twice in the event of a checksum failure.
--- drivers/hwmon/occ/p9_sbe.c | 28 ++++++++++++++++++---------- 1 file changed, 18 insertions(+), 10 deletions(-)
drivers/hwmon/occ/p9_sbe.c +18 -10
@@ -84,17 +84,25 @@ static int p9_sbe_occ_send_cmd(struct occ *occ, u8 *cmd, size_t len)struct p9_sbe_occ *ctx =to_p9_sbe_occ (occ);size_t resp_len =sizeof (*resp);int rc; - - rc =fsi_occ_submit (ctx->sbe, cmd, len, resp, &resp_len); -if (rc <0 ) { -if (resp_len) { -if (p9_sbe_occ_save_ffdc (ctx, resp, resp_len)) -sysfs_notify (&occ->bus_dev->kobj,NULL , - bin_attr_ffdc.attr.name); +int tries =0 ; + +do { + rc =fsi_occ_submit (ctx->sbe, cmd, len, resp, &resp_len); +if (rc <0 ) { +if (resp_len) { +if (p9_sbe_occ_save_ffdc (ctx, resp, resp_len)) +sysfs_notify (&occ->bus_dev->kobj,NULL , + bin_attr_ffdc.attr.name); + +return rc; + }else if (rc != -EBADE ) { +return rc; + } +/* retry twice for checksum failures */ + }else { +break ; } - -return rc; - } + }while (++tries <3 );switch (resp->return_status) {case OCC_RESP_CMD_IN_PRG :
Signature · 1 line
2.27.0
Re: [PATCH 2/2] hwmon (occ): Retry for checksum failure
Quoted 6 lines · Eddie James
Due to the OCC communication design with a shared SRAM area, checkum errors are expected due to corrupted buffer from OCC communications with other system components. Therefore, retry the command twice in the event of a checksum failure.
Signed-off-by Eddie James <[email protected]>
I assume this will be applied together with patch 1 of the series.
Guenter
Quoted 44 lines
--- drivers/hwmon/occ/p9_sbe.c | 28 ++++++++++++++++++---------- 1 file changed, 18 insertions(+), 10 deletions(-)drivers/hwmon/occ/p9_sbe.c +18
-10@@ -84,17 +84,25 @@ static int p9_sbe_occ_send_cmd(struct occ *occ, u8 *cmd, size_t len)struct p9_sbe_occ *ctx =to_p9_sbe_occ (occ);size_t resp_len =sizeof (*resp);int rc; - - rc =fsi_occ_submit (ctx->sbe, cmd, len, resp, &resp_len); -if (rc <0 ) { -if (resp_len) { -if (p9_sbe_occ_save_ffdc (ctx, resp, resp_len)) -sysfs_notify (&occ->bus_dev->kobj,NULL , - bin_attr_ffdc.attr.name); +int tries =0 ; + +do { + rc =fsi_occ_submit (ctx->sbe, cmd, len, resp, &resp_len); +if (rc <0 ) { +if (resp_len) { +if (p9_sbe_occ_save_ffdc (ctx, resp, resp_len)) +sysfs_notify (&occ->bus_dev->kobj,NULL , + bin_attr_ffdc.attr.name); + +return rc; + }else if (rc != -EBADE ) { +return rc; + } +/* retry twice for checksum failures */ + }else { +break ; } - -return rc; - } + }while (++tries <3 );switch (resp->return_status) {case OCC_RESP_CMD_IN_PRG :
RE: [PATCH 2/2] hwmon (occ): Retry for checksum failure
From: Guenter Roeck
Quoted 30 lines
Sent: 24 April 2022 18:18
Quoted 6 lines · Eddie James
Due to the OCC communication design with a shared SRAM area, checkum errors are expected due to corrupted buffer from OCC communications with other system components. Therefore, retry the command twice in the event of a checksum failure.
Signed-off-by Eddie James <[email protected]>I assume this will be applied together with patch 1 of the series.
Acked-by Guenter Roeck <[email protected]>Guenter
Quoted 14 lines
--- drivers/hwmon/occ/p9_sbe.c | 28 ++++++++++++++++++---------- 1 file changed, 18 insertions(+), 10 deletions(-)drivers/hwmon/occ/p9_sbe.c +0
-2@@ -84,17 +84,25 @@ static int p9_sbe_occ_send_cmd(struct occ *occ, u8 *cmd, size_t len)struct p9_sbe_occ *ctx =to_p9_sbe_occ (occ);size_t resp_len =sizeof (*resp);int rc; - - rc =fsi_occ_submit (ctx->sbe, cmd, len, resp, &resp_len);
Quoted 8 lines
drivers/hwmon/occ/p9_sbe.c static int p9_sbe_occ_send_cmd(struct occ *occ, u8 *cmd, size_t len) · line 89
Quoted 8 lines
drivers/hwmon/occ/p9_sbe.c +3
-5-if (rc <0 ) { -if (resp_len) { -if (p9_sbe_occ_save_ffdc (ctx, resp, resp_len)) -sysfs_notify (&occ->bus_dev->kobj,NULL , - bin_attr_ffdc.attr.name); +int tries =0 ; + + do {
Why not use a for() loop?
Quoted 11 lines
drivers/hwmon/occ/p9_sbe.c static int p9_sbe_occ_send_cmd(struct occ *occ, u8 *cmd, size_t len) · line 100
Quoted 11 lines
drivers/hwmon/occ/p9_sbe.c +11
-0+ rc =fsi_occ_submit (ctx->sbe, cmd, len, resp, &resp_len); +if (rc <0 ) { +if (resp_len) { +if (p9_sbe_occ_save_ffdc (ctx, resp, resp_len)) +sysfs_notify (&occ->bus_dev->kobj,NULL , + bin_attr_ffdc.attr.name); + +return rc; + }else if (rc != -EBADE ) { +return rc; + }
No need for else after return.
Quoted 3 lines
drivers/hwmon/occ/p9_sbe.c static int p9_sbe_occ_send_cmd(struct occ *occ, u8 *cmd, size_t len) · line 103
Quoted 3 lines
drivers/hwmon/occ/p9_sbe.c +3
-0+/* retry twice for checksum failures */ + }else { +break ;
I'd break on the success path after testing (rc >= 0). Saves a level of indent.
Quoted 8 lines
drivers/hwmon/occ/p9_sbe.c static int p9_sbe_occ_send_cmd(struct occ *occ, u8 *cmd, size_t len) · line 108
Quoted 8 lines
drivers/hwmon/occ/p9_sbe.c +1
-3} - -return rc; - } + }while (++tries <3 );switch (resp->return_status) {case OCC_RESP_CMD_IN_PRG :
Probably end up with something like:
for (tries = 0; tries < 3; tries++) {
rc = ...;
if (rc >= 0)
break;
if (resp_len) {
...
return rc;
}
if (rc != -EBADE)
return rc;
}
David-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK Registration No: 1397386 (Wales)
Eddie James
maintainerRe: [PATCH 2/2] hwmon (occ): Retry for checksum failure
Quoted 68 lines · David Laight
From: Guenter Roeck
Quoted 29 lines
Sent: 24 April 2022 18:18
Quoted 6 lines · Eddie James
Due to the OCC communication design with a shared SRAM area, checkum errors are expected due to corrupted buffer from OCC communications with other system components. Therefore, retry the command twice in the event of a checksum failure.
Signed-off-by Eddie James <[email protected]>I assume this will be applied together with patch 1 of the series.
Acked-by Guenter Roeck <[email protected]>Guenter
Quoted 14 lines
--- drivers/hwmon/occ/p9_sbe.c | 28 ++++++++++++++++++---------- 1 file changed, 18 insertions(+), 10 deletions(-)drivers/hwmon/occ/p9_sbe.c +0
-2@@ -84,17 +84,25 @@ static int p9_sbe_occ_send_cmd(struct occ *occ, u8 *cmd, size_t len)struct p9_sbe_occ *ctx =to_p9_sbe_occ (occ);size_t resp_len =sizeof (*resp);int rc; - - rc =fsi_occ_submit (ctx->sbe, cmd, len, resp, &resp_len);Quoted 8 lines
drivers/hwmon/occ/p9_sbe.c static int p9_sbe_occ_send_cmd(struct occ *occ, u8 *cmd, size_t len) · line 89
Quoted 8 lines
drivers/hwmon/occ/p9_sbe.c +3
-5-if (rc <0 ) { -if (resp_len) { -if (p9_sbe_occ_save_ffdc (ctx, resp, resp_len)) -sysfs_notify (&occ->bus_dev->kobj,NULL , - bin_attr_ffdc.attr.name); +int tries =0 ; + + do {Why not use a
for()loop?Quoted 11 lines
drivers/hwmon/occ/p9_sbe.c static int p9_sbe_occ_send_cmd(struct occ *occ, u8 *cmd, size_t len) · line 100
Quoted 11 lines
drivers/hwmon/occ/p9_sbe.c +11
-0+ rc =fsi_occ_submit (ctx->sbe, cmd, len, resp, &resp_len); +if (rc <0 ) { +if (resp_len) { +if (p9_sbe_occ_save_ffdc (ctx, resp, resp_len)) +sysfs_notify (&occ->bus_dev->kobj,NULL , + bin_attr_ffdc.attr.name); + +return rc; + }else if (rc != -EBADE ) { +return rc; + }No need for else after return.
Quoted 3 lines
drivers/hwmon/occ/p9_sbe.c static int p9_sbe_occ_send_cmd(struct occ *occ, u8 *cmd, size_t len) · line 103
Quoted 3 lines
drivers/hwmon/occ/p9_sbe.c +3
-0+/* retry twice for checksum failures */ + }else { +break ;I'd break on the success path after testing (rc >= 0). Saves a level of indent.
Quoted 8 lines
drivers/hwmon/occ/p9_sbe.c static int p9_sbe_occ_send_cmd(struct occ *occ, u8 *cmd, size_t len) · line 108
Quoted 8 lines
drivers/hwmon/occ/p9_sbe.c +1
-3} - -return rc; - } + }while (++tries <3 );switch (resp->return_status) {case OCC_RESP_CMD_IN_PRG :Probably end up with something like:
Quoted 13 lines
for (tries = 0; tries < 3; tries++) {
rc = ...;
if (rc >= 0)
break;
if (resp_len) {
...
return rc;
}
if (rc != -EBADE)
return rc;
}
DavidThanks David, Ack.
Quoted 5 lines
-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK Registration No: 1397386 (Wales)