void __iomem *ctl_block;
void __iomem *gen_block;
void __iomem *notifier_clear_block;
+ u64 adma_dma_mask;
u8 flags;
int last_issue_ncq;
};
{
struct ata_port *ap = ata_shost_to_port(sdev->host);
struct nv_adma_port_priv *pp = ap->private_data;
+ struct nv_adma_port_priv *port0, *port1;
+ struct scsi_device *sdev0, *sdev1;
struct pci_dev *pdev = to_pci_dev(ap->host->dev);
- u64 bounce_limit;
- unsigned long segment_boundary;
+ unsigned long segment_boundary, flags;
unsigned short sg_tablesize;
int rc;
int adma_enable;
/* Not a proper libata device, ignore */
return rc;
+ spin_lock_irqsave(ap->lock, flags);
+
if (ap->link.device[sdev->id].class == ATA_DEV_ATAPI) {
/*
* NVIDIA reports that ADMA mode does not support ATAPI commands.
* Restrict DMA parameters as required by the legacy interface
* when an ATAPI device is connected.
*/
- bounce_limit = ATA_DMA_MASK;
segment_boundary = ATA_DMA_BOUNDARY;
/* Subtract 1 since an extra entry may be needed for padding, see
libata-scsi.c */
adma_enable = 0;
nv_adma_register_mode(ap);
} else {
- bounce_limit = *ap->dev->dma_mask;
segment_boundary = NV_ADMA_DMA_BOUNDARY;
sg_tablesize = NV_ADMA_SGTBL_TOTAL_LEN;
adma_enable = 1;
if (current_reg != new_reg)
pci_write_config_dword(pdev, NV_MCP_SATA_CFG_20, new_reg);
- blk_queue_bounce_limit(sdev->request_queue, bounce_limit);
+ port0 = ap->host->ports[0]->private_data;
+ port1 = ap->host->ports[1]->private_data;
+ sdev0 = ap->host->ports[0]->link.device[0].sdev;
+ sdev1 = ap->host->ports[1]->link.device[0].sdev;
+ if ((port0->flags & NV_ADMA_ATAPI_SETUP_COMPLETE) ||
+ (port1->flags & NV_ADMA_ATAPI_SETUP_COMPLETE)) {
+ /** We have to set the DMA mask to 32-bit if either port is in
+ ATAPI mode, since they are on the same PCI device which is
+ used for DMA mapping. If we set the mask we also need to set
+ the bounce limit on both ports to ensure that the block
+ layer doesn't feed addresses that cause DMA mapping to
+ choke. If either SCSI device is not allocated yet, it's OK
+ since that port will discover its correct setting when it
+ does get allocated.
+ Note: Setting 32-bit mask should not fail. */
+ if (sdev0)
+ blk_queue_bounce_limit(sdev0->request_queue,
+ ATA_DMA_MASK);
+ if (sdev1)
+ blk_queue_bounce_limit(sdev1->request_queue,
+ ATA_DMA_MASK);
+
+ pci_set_dma_mask(pdev, ATA_DMA_MASK);
+ } else {
+ /** This shouldn't fail as it was set to this value before */
+ pci_set_dma_mask(pdev, pp->adma_dma_mask);
+ if (sdev0)
+ blk_queue_bounce_limit(sdev0->request_queue,
+ pp->adma_dma_mask);
+ if (sdev1)
+ blk_queue_bounce_limit(sdev1->request_queue,
+ pp->adma_dma_mask);
+ }
+
blk_queue_segment_boundary(sdev->request_queue, segment_boundary);
blk_queue_max_hw_segments(sdev->request_queue, sg_tablesize);
ata_port_printk(ap, KERN_INFO,
- "bounce limit 0x%llX, segment boundary 0x%lX, hw segs %hu\n",
- (unsigned long long)bounce_limit, segment_boundary, sg_tablesize);
+ "DMA mask 0x%llX, segment boundary 0x%lX, hw segs %hu\n",
+ (unsigned long long)*ap->host->dev->dma_mask,
+ segment_boundary, sg_tablesize);
+
+ spin_unlock_irqrestore(ap->lock, flags);
+
return rc;
}
static void nv_adma_tf_read(struct ata_port *ap, struct ata_taskfile *tf)
{
- /* Since commands where a result TF is requested are not
- executed in ADMA mode, the only time this function will be called
- in ADMA mode will be if a command fails. In this case we
- don't care about going into register mode with ADMA commands
- pending, as the commands will all shortly be aborted anyway. */
+ /* Other than when internal or pass-through commands are executed,
+ the only time this function will be called in ADMA mode will be
+ if a command fails. In the failure case we don't care about going
+ into register mode with ADMA commands pending, as the commands will
+ all shortly be aborted anyway. We assume that NCQ commands are not
+ issued via passthrough, which is the only way that switching into
+ ADMA mode could abort outstanding commands. */
nv_adma_register_mode(ap);
ata_tf_read(ap, tf);
}
if (status & (NV_ADMA_STAT_DONE |
- NV_ADMA_STAT_CPBERR)) {
- u32 check_commands;
+ NV_ADMA_STAT_CPBERR |
+ NV_ADMA_STAT_CMD_COMPLETE)) {
+ u32 check_commands = notifier_clears[i];
int pos, error = 0;
- if (ata_tag_valid(ap->link.active_tag))
- check_commands = 1 << ap->link.active_tag;
- else
- check_commands = ap->link.sactive;
+ if (status & NV_ADMA_STAT_CPBERR) {
+ /* Check all active commands */
+ if (ata_tag_valid(ap->link.active_tag))
+ check_commands = 1 <<
+ ap->link.active_tag;
+ else
+ check_commands = ap->
+ link.sactive;
+ }
/** Check CPBs for completed commands */
while ((pos = ffs(check_commands)) && !error) {
void *mem;
dma_addr_t mem_dma;
void __iomem *mmio;
+ struct pci_dev *pdev = to_pci_dev(dev);
u16 tmp;
VPRINTK("ENTER\n");
+ /* Ensure DMA mask is set to 32-bit before allocating legacy PRD and
+ pad buffers */
+ rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
+ if (rc)
+ return rc;
+ rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
+ if (rc)
+ return rc;
+
rc = ata_port_start(ap);
if (rc)
return rc;
pp->notifier_clear_block = pp->gen_block +
NV_ADMA_NOTIFIER_CLEAR + (4 * ap->port_no);
+ /* Now that the legacy PRD and padding buffer are allocated we can
+ safely raise the DMA mask to allocate the CPB/APRD table.
+ These are allowed to fail since we store the value that ends up
+ being used to set as the bounce limit in slave_config later if
+ needed. */
+ pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
+ pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
+ pp->adma_dma_mask = *dev->dma_mask;
+
mem = dmam_alloc_coherent(dev, NV_ADMA_PORT_PRIV_DMA_SZ,
&mem_dma, GFP_KERNEL);
if (!mem)
static void nv_adma_fill_sg(struct ata_queued_cmd *qc, struct nv_adma_cpb *cpb)
{
struct nv_adma_port_priv *pp = qc->ap->private_data;
- unsigned int idx;
struct nv_adma_prd *aprd;
struct scatterlist *sg;
+ unsigned int si;
VPRINTK("ENTER\n");
- idx = 0;
-
- ata_for_each_sg(sg, qc) {
- aprd = (idx < 5) ? &cpb->aprd[idx] :
- &pp->aprd[NV_ADMA_SGTBL_LEN * qc->tag + (idx-5)];
- nv_adma_fill_aprd(qc, sg, idx, aprd);
- idx++;
+ for_each_sg(qc->sg, sg, qc->n_elem, si) {
+ aprd = (si < 5) ? &cpb->aprd[si] :
+ &pp->aprd[NV_ADMA_SGTBL_LEN * qc->tag + (si-5)];
+ nv_adma_fill_aprd(qc, sg, si, aprd);
}
- if (idx > 5)
+ if (si > 5)
cpb->next_aprd = cpu_to_le64(((u64)(pp->aprd_dma + NV_ADMA_SGTBL_SZ * qc->tag)));
else
cpb->next_aprd = cpu_to_le64(0);
struct nv_adma_port_priv *pp = qc->ap->private_data;
/* ADMA engine can only be used for non-ATAPI DMA commands,
- or interrupt-driven no-data commands, where a result taskfile
- is not required. */
+ or interrupt-driven no-data commands. */
if ((pp->flags & NV_ADMA_ATAPI_SETUP_COMPLETE) ||
- (qc->tf.flags & ATA_TFLAG_POLLING) ||
- (qc->flags & ATA_QCFLAG_RESULT_TF))
+ (qc->tf.flags & ATA_TFLAG_POLLING))
return 1;
if ((qc->flags & ATA_QCFLAG_DMAMAP) ||
NV_CPB_CTL_IEN;
if (nv_adma_use_reg_mode(qc)) {
+ BUG_ON(!(pp->flags & NV_ADMA_ATAPI_SETUP_COMPLETE) &&
+ (qc->flags & ATA_QCFLAG_DMAMAP));
nv_adma_register_mode(qc->ap);
ata_qc_prep(qc);
return;
VPRINTK("ENTER\n");
+ /* We can't handle result taskfile with NCQ commands, since
+ retrieving the taskfile switches us out of ADMA mode and would abort
+ existing commands. */
+ if (unlikely(qc->tf.protocol == ATA_PROT_NCQ &&
+ (qc->flags & ATA_QCFLAG_RESULT_TF))) {
+ ata_dev_printk(qc->dev, KERN_ERR,
+ "NCQ w/ RESULT_TF not allowed\n");
+ return AC_ERR_SYSTEM;
+ }
+
if (nv_adma_use_reg_mode(qc)) {
/* use ATA register mode */
VPRINTK("using ATA register mode: 0x%lx\n", qc->flags);
+ BUG_ON(!(pp->flags & NV_ADMA_ATAPI_SETUP_COMPLETE) &&
+ (qc->flags & ATA_QCFLAG_DMAMAP));
nv_adma_register_mode(qc->ap);
return ata_qc_issue_prot(qc);
} else
/* SATA hardreset fails to retrieve proper device signature on
* some controllers. Don't classify on hardreset. For more
- * info, see http://bugme.osdl.org/show_bug.cgi?id=3352
+ * info, see http://bugzilla.kernel.org/show_bug.cgi?id=3352
*/
return sata_std_hardreset(link, &dummy, deadline);
}
{
struct ata_port *ap = qc->ap;
struct scatterlist *sg;
- unsigned int idx;
struct nv_swncq_port_priv *pp = ap->private_data;
struct ata_prd *prd;
-
- WARN_ON(qc->__sg == NULL);
- WARN_ON(qc->n_elem == 0 && qc->pad_len == 0);
+ unsigned int si, idx;
prd = pp->prd + ATA_MAX_PRD * qc->tag;
idx = 0;
- ata_for_each_sg(sg, qc) {
+ for_each_sg(qc->sg, sg, qc->n_elem, si) {
u32 addr, offset;
u32 sg_len, len;
}
}
- if (idx)
- prd[idx - 1].flags_len |= cpu_to_le32(ATA_PRD_EOT);
+ prd[idx - 1].flags_len |= cpu_to_le32(ATA_PRD_EOT);
}
static unsigned int nv_swncq_issue_atacmd(struct ata_port *ap,
hpriv->type = type;
host->private_data = hpriv;
- /* set 64bit dma masks, may fail */
- if (type == ADMA) {
- if (pci_set_dma_mask(pdev, DMA_64BIT_MASK) == 0)
- pci_set_consistent_dma_mask(pdev, DMA_64BIT_MASK);
- }
-
/* request and iomap NV_MMIO_BAR */
rc = pcim_iomap_regions(pdev, 1 << NV_MMIO_BAR, DRV_NAME);
if (rc)