libata: use FLUSH_EXT only when driver is larger than LBA28 limit
PATCH 1/1 libata: use FLUSH_EXT only when driver is larger than LBA28 limit
Many drives support LBA48 even when its capacity is smaller than 1<<28, as LBA48 is required for many functionalities. FLUSH_EXT is mandatory for drives w/ LBA48 support.
Interestingly, at least one of such drives (ST960812A) has problems dealing with FLUSH_EXT. It eventually completes the command but takes around 7 seconds to finish in many cases thus drastically slowing down IO transactions. This seems to be a firmware bug which sneaked into production probably because no other ATA driver including linux IDE issues FLUSH_EXT to drives which report support for LBA48 & FLUSH_EXT but is smaller than 1<<28 blocks.
This patch adds ATA_DFLAG_FLUSH_EXT which is set iff the drive supports LBA48 & FLUSH_EXT and is larger than LBA28 limit. Both cache flush paths are updated to issue FLUSH_EXT only when the flag is set. Note that the changed behavior is more inline with the rest of libata. libata prefers shorter commands whenever possible.
drivers/ata/libata-core.c +5 -1
@@ -1457,6 +1457,10 @@ int ata_dev_configure(struct ata_deviceif (ata_id_has_lba48 (id)) { dev->flags |=ATA_DFLAG_LBA48 ; lba_desc ="LBA48" ; + +if (ata_id_u64 (id,100 ) >= (1UL <<28 ) && +ata_id_has_flush_ext (id)) + dev->flags |=ATA_DFLAG_FLUSH_EXT ; }/* config NCQ */
@@ -5128,7 +5132,7 @@ int ata_flush_cache(struct ata_device *dif (!ata_try_flush_cache (dev))return 0 ; -if (ata_id_has_flush_ext (dev->id)) +if (dev->flags &ATA_DFLAG_FLUSH_EXT ) cmd =ATA_CMD_FLUSH_EXT ;else cmd =ATA_CMD_FLUSH ;
drivers/ata/libata-scsi.c +1 -2
@@ -1027,8 +1027,7 @@ static unsigned int ata_scsi_flush_xlat( tf->flags |=ATA_TFLAG_DEVICE ; tf->protocol =ATA_PROT_NODATA ; -if ((qc->dev->flags &ATA_DFLAG_LBA48 ) && - (ata_id_has_flush_ext (qc->dev->id))) +if (qc->dev->flags &ATA_DFLAG_FLUSH_EXT ) tf->command =ATA_CMD_FLUSH_EXT ;else tf->command =ATA_CMD_FLUSH ;
include/linux/libata.h +1 -0
@@ -140,6 +140,7 @@ enum {ATA_DFLAG_LBA48 = (1 <<1 ),/* device supports LBA48 */ ATA_DFLAG_CDB_INTR = (1 <<2 ),/* device asserts INTRQ when ready for CDB */ ATA_DFLAG_NCQ = (1 <<3 ),/* device supports NCQ */ +ATA_DFLAG_FLUSH_EXT = (1 <<4 ),/* do FLUSH_EXT instead of FLUSH */ ATA_DFLAG_CFG_MASK = (1 <<8 ) -1 , ATA_DFLAG_PIO = (1 << 8), /* device limited to PIO mode */
Quoted 12 lines · Tejun Heo
Many drives support LBA48 even when its capacity is smaller than 1<<28, as LBA48 is required for many functionalities.
FLUSH_EXTis mandatory for drives w/ LBA48 support.Interestingly, at least one of such drives (ST960812A) has problems dealing with
FLUSH_EXT. It eventually completes the command but takes around 7 seconds to finish in many cases thus drastically slowing down IO transactions. This seems to be a firmware bug which sneaked into production probably because no other ATA driver including linux IDE issuesFLUSH_EXTto drives which report support for LBA48 &FLUSH_EXTbut is smaller than 1<<28 blocks.
Quoted 5 lines
This patch adds
ATA_DFLAG_FLUSH_EXTwhich is set iff the drive supports LBA48 &FLUSH_EXTand is larger than LBA28 limit. Both cache flush paths are updated to issueFLUSH_EXTonly when the flag is set. Note that the changed behavior is more inline with the rest of libata. libata prefers shorter commands whenever possible.
Jeff, I think this should go into #uptream-fixes, too. We shouldn't have issued FLUSH_EXT to < 1<<28 devices in the first place.
Thanks.
Signature · 1 line
tejun
Quoted 7 lines · Tejun Heo
Interestingly, at least one of such drives (ST960812A) has problems dealing with
FLUSH_EXT. It eventually completes the command but takes around 7 seconds to finish in many cases thus drastically slowing down IO transactions. This seems to be a firmware bug which sneaked into production probably because no other ATA driver including linux IDE issuesFLUSH_EXTto drives which report support for LBA48 &FLUSH_EXTbut is smaller than 1<<28 blocks.
Note that i'm quite sure that i have seen this on more than this single drive. It might be that those were all seagates, though.
Signature · 3 lines
Stefan Seyfried QA / R&D Team Mobile Devices | "Any ideas, John?" SUSE LINUX Products GmbH, Nürnberg | "Well, surrounding them's out."
PATCH 1/1 libata: use FLUSH_EXT only when driver is larger than LBA28 limit
In reply to Tejun HeoMany drives support LBA48 even when its capacity is smaller than 1<<28, as LBA48 is required for many functionalities. FLUSH_EXT is mandatory for drives w/ LBA48 support.
Interestingly, at least one of such drives (ST960812A) has problems dealing with FLUSH_EXT. It eventually completes the command but takes around 7 seconds to finish in many cases thus drastically slowing down IO transactions. This seems to be a firmware bug which sneaked into production probably because no other ATA driver including linux IDE issues FLUSH_EXT to drives which report support for LBA48 & FLUSH_EXT but is smaller than 1<<28 blocks.
This patch adds ATA_DFLAG_FLUSH_EXT which is set iff the drive supports LBA48 & FLUSH_EXT and is larger than LBA28 limit. Both cache flush paths are updated to issue FLUSH_EXT only when the flag is set. Note that the changed behavior is more inline with the rest of libata. libata prefers shorter commands whenever possible.
---
* In ata_dev_configure(), use dev->n_sectors instead of reading it directly from id.
drivers/ata/libata-core.c +5 -1
@@ -1457,6 +1457,10 @@ int ata_dev_configure(struct ata_deviceif (ata_id_has_lba48 (id)) { dev->flags |=ATA_DFLAG_LBA48 ; lba_desc ="LBA48" ; + +if (dev->n_sectors >= (1UL <<28 ) && +ata_id_has_flush_ext (id)) + dev->flags |=ATA_DFLAG_FLUSH_EXT ; }/* config NCQ */
@@ -5128,7 +5132,7 @@ int ata_flush_cache(struct ata_device *dif (!ata_try_flush_cache (dev))return 0 ; -if (ata_id_has_flush_ext (dev->id)) +if (dev->flags &ATA_DFLAG_FLUSH_EXT ) cmd =ATA_CMD_FLUSH_EXT ;else cmd =ATA_CMD_FLUSH ;
drivers/ata/libata-scsi.c +1 -2
@@ -1027,8 +1027,7 @@ static unsigned int ata_scsi_flush_xlat( tf->flags |=ATA_TFLAG_DEVICE ; tf->protocol =ATA_PROT_NODATA ; -if ((qc->dev->flags &ATA_DFLAG_LBA48 ) && - (ata_id_has_flush_ext (qc->dev->id))) +if (qc->dev->flags &ATA_DFLAG_FLUSH_EXT ) tf->command =ATA_CMD_FLUSH_EXT ;else tf->command =ATA_CMD_FLUSH ;
include/linux/libata.h +1 -0
@@ -140,6 +140,7 @@ enum {ATA_DFLAG_LBA48 = (1 <<1 ),/* device supports LBA48 */ ATA_DFLAG_CDB_INTR = (1 <<2 ),/* device asserts INTRQ when ready for CDB */ ATA_DFLAG_NCQ = (1 <<3 ),/* device supports NCQ */ +ATA_DFLAG_FLUSH_EXT = (1 <<4 ),/* do FLUSH_EXT instead of FLUSH */ ATA_DFLAG_CFG_MASK = (1 <<8 ) -1 , ATA_DFLAG_PIO = (1 << 8), /* device limited to PIO mode */
Quoted 18 lines · Tejun Heo
Many drives support LBA48 even when its capacity is smaller than 1<<28, as LBA48 is required for many functionalities.
FLUSH_EXTis mandatory for drives w/ LBA48 support.Interestingly, at least one of such drives (ST960812A) has problems dealing with
FLUSH_EXT. It eventually completes the command but takes around 7 seconds to finish in many cases thus drastically slowing down IO transactions. This seems to be a firmware bug which sneaked into production probably because no other ATA driver including linux IDE issuesFLUSH_EXTto drives which report support for LBA48 &FLUSH_EXTbut is smaller than 1<<28 blocks.This patch adds
ATA_DFLAG_FLUSH_EXTwhich is set iff the drive supports LBA48 &FLUSH_EXTand is larger than LBA28 limit. Both cache flush paths are updated to issueFLUSH_EXTonly when the flag is set. Note that the changed behavior is more inline with the rest of libata. libata prefers shorter commands whenever possible.
Quoted 7 lines
Signed-off-by Tejun Heo <[email protected]>Cc Danny Kukawka <[email protected]>Cc Stefan Seyfried <[email protected]>---
* In
ata_dev_configure(), usedev->n_sectorsinstead of reading it directly from id.
applied to #upstream -- I think this wants more testing than 2.6.19-rc5 will allow