@@ -686,6 +686,7 @@ struct qib_devdata {
void __iomem *piobase;
/* mem-mapped pointer to base of user chip regs (if using WC PAT) */
u64 __iomem *userbase;
+ void __iomem *piovl15base; /* base of VL15 buffers, if not WC */
/*
* points to area where PIOavail registers will be DMA'ed.
* Has to be on a page of it's own, because the page will be
@@ -233,6 +233,7 @@ static u32 __iomem *qib_remap_ioaddr32(struct qib_devdata *dd, u32 offset,
u32 __iomem *krb32 = (u32 __iomem *)dd->kregbase;
u32 __iomem *map = NULL;
u32 cnt = 0;
+ u32 tot4k, offs4k;
/* First, simplest case, offset is within the first map. */
kreglen = (dd->kregend - dd->kregbase) * sizeof(u64);
@@ -250,7 +251,8 @@ static u32 __iomem *qib_remap_ioaddr32(struct qib_devdata *dd, u32 offset,
if (dd->userbase) {
/* If user regs mapped, they are after send, so set limit. */
u32 ulim = (dd->cfgctxts * dd->ureg_align) + dd->uregbase;
- snd_lim = dd->uregbase;
+ if (!dd->piovl15base)
+ snd_lim = dd->uregbase;
krb32 = (u32 __iomem *)dd->userbase;
if (offset >= dd->uregbase && offset < ulim) {
map = krb32 + (offset - dd->uregbase) / sizeof(u32);
@@ -277,14 +279,14 @@ static u32 __iomem *qib_remap_ioaddr32(struct qib_devdata *dd, u32 offset,
/* If 4k buffers exist, account for them by bumping
* appropriate limit.
*/
+ tot4k = dd->piobcnt4k * dd->align4k;
+ offs4k = dd->piobufbase >> 32;
if (dd->piobcnt4k) {
- u32 tot4k = dd->piobcnt4k * dd->align4k;
- u32 offs4k = dd->piobufbase >> 32;
if (snd_bottom > offs4k)
snd_bottom = offs4k;
else {
/* 4k above 2k. Bump snd_lim, if needed*/
- if (!dd->userbase)
+ if (!dd->userbase || dd->piovl15base)
snd_lim = offs4k + tot4k;
}
}
@@ -298,6 +300,15 @@ static u32 __iomem *qib_remap_ioaddr32(struct qib_devdata *dd, u32 offset,
cnt = snd_lim - offset;
}
+ if (!map && offs4k && dd->piovl15base) {
+ snd_lim = offs4k + tot4k + 2 * dd->align4k;
+ if (offset >= (offs4k + tot4k) && offset < snd_lim) {
+ map = (u32 __iomem *)dd->piovl15base +
+ ((offset - (offs4k + tot4k)) / sizeof(u32));
+ cnt = snd_lim - offset;
+ }
+ }
+
mapped:
if (cntp)
*cntp = cnt;
@@ -6119,9 +6119,25 @@ static int qib_init_7322_variables(struct qib_devdata *dd)
qib_set_ctxtcnt(dd);
if (qib_wc_pat) {
- ret = init_chip_wc_pat(dd, NUM_VL15_BUFS * dd->align4k);
+ resource_size_t vl15off;
+ /*
+ * We do not set WC on the VL15 buffers to avoid
+ * a rare problem with unaligned writes from
+ * interrupt-flushed store buffers, so we need
+ * to map those separately here. We can't solve
+ * this for the rarely used mtrr case.
+ */
+ ret = init_chip_wc_pat(dd, 0);
if (ret)
goto bail;
+
+ /* vl15 buffers start just after the 4k buffers */
+ vl15off = dd->physaddr + (dd->piobufbase >> 32) +
+ dd->piobcnt4k * dd->align4k;
+ dd->piovl15base = ioremap_nocache(vl15off,
+ NUM_VL15_BUFS * dd->align4k);
+ if (!dd->piovl15base)
+ goto bail;
}
qib_7322_set_baseaddrs(dd); /* set chip access pointers now */
@@ -1499,6 +1499,12 @@ bail:
return -ENOMEM;
}
+/*
+ * Note: Changes to this routine should be mirrored
+ * for the diagnostics routine qib_remap_ioaddr32().
+ * There is also related code for VL15 buffers in qib_init_7322_variables().
+ * The teardown code that unmaps is in qib_pcie_ddcleanup()
+ */
int init_chip_wc_pat(struct qib_devdata *dd, u32 vl15buflen)
{
u64 __iomem *qib_kregbase = NULL;
@@ -179,6 +179,8 @@ void qib_pcie_ddcleanup(struct qib_devdata *dd)
iounmap(dd->piobase);
if (dd->userbase)
iounmap(dd->userbase);
+ if (dd->piovl15base)
+ iounmap(dd->piovl15base);
pci_disable_device(dd->pcidev);
pci_release_regions(dd->pcidev);
@@ -340,9 +340,13 @@ rescan:
if (i < dd->piobcnt2k)
buf = (u32 __iomem *)(dd->pio2kbase +
i * dd->palign);
- else
+ else if (i < dd->piobcnt2k + dd->piobcnt4k || !dd->piovl15base)
buf = (u32 __iomem *)(dd->pio4kbase +
(i - dd->piobcnt2k) * dd->align4k);
+ else
+ buf = (u32 __iomem *)(dd->piovl15base +
+ (i - (dd->piobcnt2k + dd->piobcnt4k)) *
+ dd->align4k);
if (pbufnum)
*pbufnum = i;
dd->upd_pio_shadow = 0;