sata_mv: correct S/G table limits (baf14aa1) · Commits · 戴 / test

The recent mv_fill_sg() rewrite, to fix a data corruption problem related to IOMMU virtual merging, forgot to account for the potentially-increased size of the scatter/gather table after its run. Additionally, the DMA boundary is reduced from 0xffffffff to 0xffff to more closely match the needs of mv_fill_sg(). Signed-off-by:

Jeff Garzik <jgarzik@redhat.com> Signed-off-by:

Linus Torvalds <torvalds@linux-foundation.org>

drivers/ata/sata_mv.c

+6 −3

Original line number	Diff line number	Diff line
		@@ -313,7 +313,10 @@ enum {
		#define IS_GEN_IIE(hpriv) ((hpriv)->hp_flags & MV_HP_GEN_IIE)

		enum {
		MV_DMA_BOUNDARY = 0xffffffffU,
		/* DMA boundary 0xffff is required by the s/g splitting
		* we need on /length/ in mv_fill-sg().
		*/
		MV_DMA_BOUNDARY = 0xffffU,

		/* mask of register bits containing lower 32 bits
		* of EDMA request queue DMA address
		@@ -448,7 +451,7 @@ static struct scsi_host_template mv5_sht = {
		.queuecommand = ata_scsi_queuecmd,
		.can_queue = ATA_DEF_QUEUE,
		.this_id = ATA_SHT_THIS_ID,
		.sg_tablesize = MV_MAX_SG_CT,
		.sg_tablesize = MV_MAX_SG_CT / 2,
		.cmd_per_lun = ATA_SHT_CMD_PER_LUN,
		.emulated = ATA_SHT_EMULATED,
		.use_clustering = 1,
		@@ -466,7 +469,7 @@ static struct scsi_host_template mv6_sht = {
		.queuecommand = ata_scsi_queuecmd,
		.can_queue = ATA_DEF_QUEUE,
		.this_id = ATA_SHT_THIS_ID,
		.sg_tablesize = MV_MAX_SG_CT,
		.sg_tablesize = MV_MAX_SG_CT / 2,
		.cmd_per_lun = ATA_SHT_CMD_PER_LUN,
		.emulated = ATA_SHT_EMULATED,
		.use_clustering = 1,

Admin message