[libata] kill ata_sg_is_last()

Short term, this works around a bug introduced by early sg-chaining
work.

Long term, removing this function eliminates a branch from a hot
path loop in each scatter/gather table build.  Also, as this code
demonstrates, we don't need to _track_ the end of the s/g list, as
long as we mark it in some way.  And doing so programatically is nice.
So its a useful cleanup, regardless of its short term effects.

Based conceptually on a quick patch by Jens Axboe.

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

5 files changed, 27 insertions, 42 deletions

diff --git a/drivers/ata/pdc_adma.c b/drivers/ata/pdc_adma.c
index 8d1b03d5bcb1..199f7e150eb3 100644
--- a/drivers/ata/pdc_adma.c
+++ b/drivers/ata/pdc_adma.c
@@ -318,7 +318,7 @@ static int adma_fill_sg(struct ata_queued_cmd *qc)
         struct scatterlist *sg;
         struct ata_port *ap = qc->ap;
         struct adma_port_priv *pp = ap->private_data;
-        u8  *buf = pp->pkt;
+        u8  *buf = pp->pkt, *last_buf = NULL;
         int i = (2 + buf[3]) * 8;
         u8 pFLAGS = pORD | ((qc->tf.flags & ATA_TFLAG_WRITE) ? pDIRO : 0);
 
@@ -334,8 +334,7 @@ static int adma_fill_sg(struct ata_queued_cmd *qc)
                 *(__le32 *)(buf + i) = cpu_to_le32(len);
                 i += 4;
 
-                if (ata_sg_is_last(sg, qc))
-                        pFLAGS |= pEND;
+                last_buf = &buf[i];
                 buf[i++] = pFLAGS;
                 buf[i++] = qc->dev->dma_mode & 0xf;
                 buf[i++] = 0;   /* pPKLW */
@@ -348,6 +347,10 @@ static int adma_fill_sg(struct ata_queued_cmd *qc)
                 VPRINTK("PRD[%u] = (0x%lX, 0x%X)\n", i/4,
                                         (unsigned long)addr, len);
         }
+
+        if (likely(last_buf))
+                *last_buf |= pEND;
+
         return i;
 }
 
diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c
index 4df8311968e9..7f1b13e89cf7 100644
--- a/drivers/ata/sata_mv.c
+++ b/drivers/ata/sata_mv.c
@@ -421,7 +421,6 @@ static void mv_error_handler(struct ata_port *ap);
 static void mv_post_int_cmd(struct ata_queued_cmd *qc);
 static void mv_eh_freeze(struct ata_port *ap);
 static void mv_eh_thaw(struct ata_port *ap);
-static int mv_slave_config(struct scsi_device *sdev);
 static int mv_init_one(struct pci_dev *pdev, const struct pci_device_id *ent);
 
 static void mv5_phy_errata(struct mv_host_priv *hpriv, void __iomem *mmio,
@@ -459,7 +458,7 @@ static struct scsi_host_template mv5_sht = {
         .use_clustering         = 1,
         .proc_name              = DRV_NAME,
         .dma_boundary           = MV_DMA_BOUNDARY,
-        .slave_configure        = mv_slave_config,
+        .slave_configure        = ata_scsi_slave_config,
         .slave_destroy          = ata_scsi_slave_destroy,
         .bios_param             = ata_std_bios_param,
 };
@@ -477,7 +476,7 @@ static struct scsi_host_template mv6_sht = {
         .use_clustering         = 1,
         .proc_name              = DRV_NAME,
         .dma_boundary           = MV_DMA_BOUNDARY,
-        .slave_configure        = mv_slave_config,
+        .slave_configure        = ata_scsi_slave_config,
         .slave_destroy          = ata_scsi_slave_destroy,
         .bios_param             = ata_std_bios_param,
 };
@@ -756,17 +755,6 @@ static void mv_irq_clear(struct ata_port *ap)
 {
 }
 
-static int mv_slave_config(struct scsi_device *sdev)
-{
-        int rc = ata_scsi_slave_config(sdev);
-        if (rc)
-                return rc;
-
-        blk_queue_max_phys_segments(sdev->request_queue, MV_MAX_SG_CT / 2);
-
-        return 0;       /* scsi layer doesn't check return value, sigh */
-}
-
 static void mv_set_edma_ptrs(void __iomem *port_mmio,
                              struct mv_host_priv *hpriv,
                              struct mv_port_priv *pp)
@@ -1138,7 +1126,7 @@ static void mv_fill_sg(struct ata_queued_cmd *qc)
 {
         struct mv_port_priv *pp = qc->ap->private_data;
         struct scatterlist *sg;
-        struct mv_sg *mv_sg;
+        struct mv_sg *mv_sg, *last_sg = NULL;
 
         mv_sg = pp->sg_tbl;
         ata_for_each_sg(sg, qc) {
@@ -1159,13 +1147,13 @@ static void mv_fill_sg(struct ata_queued_cmd *qc)
                         sg_len -= len;
                         addr += len;
 
-                        if (!sg_len && ata_sg_is_last(sg, qc))
-                                mv_sg->flags_size |= cpu_to_le32(EPRD_FLAG_END_OF_TBL);
-
+                        last_sg = mv_sg;
                         mv_sg++;
                 }
-
         }
+
+        if (likely(last_sg))
+                last_sg->flags_size |= cpu_to_le32(EPRD_FLAG_END_OF_TBL);
 }
 
 static inline void mv_crqb_pack_cmd(__le16 *cmdw, u8 data, u8 addr, unsigned last)
diff --git a/drivers/ata/sata_sil24.c b/drivers/ata/sata_sil24.c
index b0619278454a..26ebffc10f3e 100644
--- a/drivers/ata/sata_sil24.c
+++ b/drivers/ata/sata_sil24.c
@@ -796,16 +796,19 @@ static inline void sil24_fill_sg(struct ata_queued_cmd *qc,
                                  struct sil24_sge *sge)
 {
         struct scatterlist *sg;
+        struct sil24_sge *last_sge = NULL;
 
         ata_for_each_sg(sg, qc) {
                 sge->addr = cpu_to_le64(sg_dma_address(sg));
                 sge->cnt = cpu_to_le32(sg_dma_len(sg));
-                if (ata_sg_is_last(sg, qc))
-                        sge->flags = cpu_to_le32(SGE_TRM);
-                else
-                        sge->flags = 0;
+                sge->flags = 0;
+
+                last_sge = sge;
                 sge++;
         }
+
+        if (likely(last_sge))
+                last_sge->flags = cpu_to_le32(SGE_TRM);
 }
 
 static int sil24_qc_defer(struct ata_queued_cmd *qc)
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index b41dfb539021..c316a0bcae6c 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -5134,6 +5134,7 @@ static void ipr_build_ata_ioadl(struct ipr_cmnd *ipr_cmd,
         u32 ioadl_flags = 0;
         struct ipr_ioarcb *ioarcb = &ipr_cmd->ioarcb;
         struct ipr_ioadl_desc *ioadl = ipr_cmd->ioadl;
+        struct ipr_ioadl_desc *last_ioadl = NULL;
         int len = qc->nbytes + qc->pad_len;
         struct scatterlist *sg;
 
@@ -5156,11 +5157,13 @@ static void ipr_build_ata_ioadl(struct ipr_cmnd *ipr_cmd,
         ata_for_each_sg(sg, qc) {
                 ioadl->flags_and_data_len = cpu_to_be32(ioadl_flags | sg_dma_len(sg));
                 ioadl->address = cpu_to_be32(sg_dma_address(sg));
-                if (ata_sg_is_last(sg, qc))
-                        ioadl->flags_and_data_len |= cpu_to_be32(IPR_IOADL_FLAGS_LAST);
-                else
-                        ioadl++;
+
+                last_ioadl = ioadl;
+                ioadl++;
         }
+
+        if (likely(last_ioadl))
+                last_ioadl->flags_and_data_len |= cpu_to_be32(IPR_IOADL_FLAGS_LAST);
 }
 
 /**
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 377e6d4d9be3..bc3b6fc7b98d 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -1037,18 +1037,6 @@ extern void ata_port_pbar_desc(struct ata_port *ap, int bar, ssize_t offset,
 /*
  * qc helpers
  */
-static inline int
-ata_sg_is_last(struct scatterlist *sg, struct ata_queued_cmd *qc)
-{
-        if (sg == &qc->pad_sgent)
-                return 1;
-        if (qc->pad_len)
-                return 0;
-        if (qc->n_iter == qc->n_elem)
-                return 1;
-        return 0;
-}
-
 static inline struct scatterlist *
 ata_qc_first_sg(struct ata_queued_cmd *qc)
 {