On Mon, Jan 19, 2026 at 03:26:11PM -0500, Frank Li wrote:
> On Sun, Jan 18, 2026 at 10:54:15PM +0900, Koichiro Den wrote:
> > pci-epf-vntb can pack multiple memory windows into a single BAR using
> > mwN_offset. With the NTB core gaining support for programming multiple
> > translation ranges for a window, the EPF needs to provide the per-BAR
> > subrange layout to the endpoint controller (EPC).
> >
> > Implement .mw_set_trans_ranges() for pci-epf-vntb. Track subranges for
> > each BAR and pass them to pci_epc_set_bar() so EPC drivers can select an
> > appropriate inbound mapping mode (e.g. Address Match mode on DesignWare
> > controllers) when subrange mappings are required.
> >
> > Signed-off-by: Koichiro Den <den@valinux.co.jp>
> > ---
> > drivers/pci/endpoint/functions/pci-epf-vntb.c | 183 +++++++++++++++++-
> > 1 file changed, 175 insertions(+), 8 deletions(-)
> >
> > diff --git a/drivers/pci/endpoint/functions/pci-epf-vntb.c b/drivers/pci/endpoint/functions/pci-epf-vntb.c
> > index 39e784e21236..98128c2c5079 100644
> > --- a/drivers/pci/endpoint/functions/pci-epf-vntb.c
> > +++ b/drivers/pci/endpoint/functions/pci-epf-vntb.c
> > @@ -42,6 +42,7 @@
> > #include <linux/log2.h>
> > #include <linux/module.h>
> > #include <linux/slab.h>
> > +#include <linux/sort.h>
> >
> > #include <linux/pci-ep-msi.h>
> > #include <linux/pci-epc.h>
> > @@ -144,6 +145,10 @@ struct epf_ntb {
> >
> > enum pci_barno epf_ntb_bar[VNTB_BAR_NUM];
> >
> > + /* Cache for subrange mapping */
> > + struct ntb_mw_subrange *mw_subrange[MAX_MW];
> > + unsigned int num_subrange[MAX_MW];
> > +
> > struct epf_ntb_ctrl *reg;
> >
> > u32 *epf_db;
> > @@ -736,6 +741,7 @@ static int epf_ntb_mw_bar_init(struct epf_ntb *ntb)
> > ntb->epf->bar[barno].flags |= upper_32_bits(size) ?
> > PCI_BASE_ADDRESS_MEM_TYPE_64 :
> > PCI_BASE_ADDRESS_MEM_TYPE_32;
> > + ntb->epf->bar[barno].num_submap = 0;
> >
> > ret = pci_epc_set_bar(ntb->epf->epc,
> > ntb->epf->func_no,
> > @@ -1405,28 +1411,188 @@ static int vntb_epf_db_set_mask(struct ntb_dev *ntb, u64 db_bits)
> > return 0;
> > }
> >
> > -static int vntb_epf_mw_set_trans(struct ntb_dev *ndev, int pidx, int idx,
> > - dma_addr_t addr, resource_size_t size)
> > +struct vntb_mw_order {
> > + u64 off;
> > + unsigned int mw;
> > +};
> > +
> > +static int vntb_cmp_mw_order(const void *a, const void *b)
> > +{
> > + const struct vntb_mw_order *ma = a;
> > + const struct vntb_mw_order *mb = b;
> > +
> > + if (ma->off < mb->off)
> > + return -1;
> > + if (ma->off > mb->off)
> > + return 1;
> > + return 0;
> > +}
> > +
> > +static int vntb_epf_mw_set_trans_ranges(struct ntb_dev *ndev, int pidx, int idx,
> > + unsigned int num_ranges,
> > + const struct ntb_mw_subrange *ranges)
> > {
> > struct epf_ntb *ntb = ntb_ndev(ndev);
> > + struct pci_epf_bar_submap *submap;
> > + struct vntb_mw_order mws[MAX_MW];
> > struct pci_epf_bar *epf_bar;
> > + struct ntb_mw_subrange *r;
> > enum pci_barno barno;
> > + struct device *dev, *epf_dev;
> > + unsigned int total_ranges = 0;
> > + unsigned int mw_cnt = 0;
> > + unsigned int cur = 0;
> > + u64 expected_off = 0;
> > + unsigned int i, j;
> > int ret;
> > +
> > + dev = &ntb->ntb->dev;
> > + epf_dev = &ntb->epf->dev;
> > + barno = ntb->epf_ntb_bar[BAR_MW1 + idx];
> > + epf_bar = &ntb->epf->bar[barno];
> > + epf_bar->barno = barno;
> > +
> > + r = devm_kmemdup(epf_dev, ranges, num_ranges * sizeof(*ranges), GFP_KERNEL);
>
> size_mul(sizeof(*ranges), num_ranges)
Will update.
>
> > + if (!r)
> > + return -ENOMEM;
> > +
> > + if (ntb->mw_subrange[idx])
> > + devm_kfree(epf_dev, ntb->mw_subrange[idx]);
> > +
> > + ntb->mw_subrange[idx] = r;
> > + ntb->num_subrange[idx] = num_ranges;
> > +
> > + /* Defer pci_epc_set_bar() until all MWs in this BAR have range info. */
> > + for (i = 0; i < MAX_MW; i++) {
> > + enum pci_barno bar = ntb->epf_ntb_bar[BAR_MW1 + i];
> > +
> > + if (bar != barno)
> > + continue;
> > + if (!ntb->num_subrange[i])
> > + return 0;
> > +
> > + mws[mw_cnt].mw = i;
> > + mws[mw_cnt].off = ntb->mws_offset[i];
> > + mw_cnt++;
> > + }
> > +
> > + sort(mws, mw_cnt, sizeof(mws[0]), vntb_cmp_mw_order, NULL);
>
> Can we require mws_offset is ordered? So needn't sort here.
Yes, by adding an ordering validation at epf_ntb_bind() time, and
documenting the constraint in
Documentation/PCI/endpoint/pci-vntb-howto.rst.
The sorting was only added for convenience, and there should be no strong
technical reason to support arbitrary MW ordering.
Thanks for the review.
Koichiro
>
> > +
> > + /* BAR submap must cover the whole BAR with no holes. */
> > + for (i = 0; i < mw_cnt; i++) {
> > + unsigned int mw = mws[i].mw;
> > + u64 sum = 0;
> > +
> > + if (mws[i].off != expected_off) {
>
> can we all use size instead 'off' to keep align with submap?
Yes, will rename it.
Thanks for the review,
Koichiro
>
> Frank
> > + dev_err(dev,
> > + "BAR%d: hole/overlap at %#llx (MW%d@%#llx)\n",
> > + barno, expected_off, mw + 1, mws[i].off);
> > + return -EINVAL;
> > + }
> > +
> > + total_ranges += ntb->num_subrange[mw];
> > + for (j = 0; j < ntb->num_subrange[mw]; j++)
> > + sum += ntb->mw_subrange[mw][j].size;
> > +
> > + if (sum != ntb->mws_size[mw]) {
> > + dev_err(dev,
> > + "MW%d: ranges size %#llx != window size %#llx\n",
> > + mw + 1, sum, ntb->mws_size[mw]);
> > + return -EINVAL;
> > + }
> > + expected_off += ntb->mws_size[mw];
> > + }
> > +
> > + submap = devm_krealloc_array(epf_dev, epf_bar->submap, total_ranges,
> > + sizeof(*submap), GFP_KERNEL);
> > + if (!submap)
> > + return -ENOMEM;
> > +
> > + epf_bar->submap = submap;
> > + epf_bar->num_submap = total_ranges;
> > + dev_dbg(dev, "Requesting BAR%d layout (#. of subranges is %u):\n",
> > + barno, total_ranges);
> > +
> > + for (i = 0; i < mw_cnt; i++) {
> > + unsigned int mw = mws[i].mw;
> > +
> > + dev_dbg(dev, "- MW%d\n", 1 + mw);
> > + for (j = 0; j < ntb->num_subrange[mw]; j++) {
> > + dev_dbg(dev, " - addr/size = %#llx/%#llx\n",
> > + ntb->mw_subrange[mw][j].addr,
> > + ntb->mw_subrange[mw][j].size);
> > + submap[cur].phys_addr = ntb->mw_subrange[mw][j].addr;
> > + submap[cur].size = ntb->mw_subrange[mw][j].size;
> > + cur++;
> > + }
> > + }
> > +
> > + ret = pci_epc_set_bar(ntb->epf->epc, ntb->epf->func_no,
> > + ntb->epf->vfunc_no, epf_bar);
> > + if (ret)
> > + dev_err(dev, "BAR%d: failed to program mappings for MW%d: %d\n",
> > + barno, idx + 1, ret);
> > +
> > + return ret;
> > +}
> > +
> > +static int vntb_epf_mw_set_trans(struct ntb_dev *ndev, int pidx, int idx,
> > + dma_addr_t addr, resource_size_t size)
> > +{
> > + struct epf_ntb *ntb = ntb_ndev(ndev);
> > + struct pci_epf_bar *epf_bar;
> > + resource_size_t bar_size;
> > + enum pci_barno barno;
> > struct device *dev;
> > + unsigned int i;
> > + int ret;
> >
> > dev = &ntb->ntb->dev;
> > barno = ntb->epf_ntb_bar[BAR_MW1 + idx];
> > epf_bar = &ntb->epf->bar[barno];
> > epf_bar->phys_addr = addr;
> > epf_bar->barno = barno;
> > - epf_bar->size = size;
> >
> > - ret = pci_epc_set_bar(ntb->epf->epc, 0, 0, epf_bar);
> > - if (ret) {
> > - dev_err(dev, "failure set mw trans\n");
> > - return ret;
> > + bar_size = epf_bar->size;
> > + if (!bar_size || !size)
> > + return -EINVAL;
> > +
> > + if (size != ntb->mws_size[idx])
> > + return -EINVAL;
> > +
> > + /*
> > + * Even if the caller intends to map the entire MW, the MW might
> > + * actually be just a part of the BAR. In that case, redirect the
> > + * handling to vntb_epf_mw_set_trans_ranges().
> > + */
> > + if (size < bar_size) {
> > + struct ntb_mw_subrange r = {
> > + .addr = addr,
> > + .size = size,
> > + };
> > + return vntb_epf_mw_set_trans_ranges(ndev, pidx, idx, 1, &r);
> > }
> > - return 0;
> > +
> > + /* Drop any stale cache for the BAR. */
> > + for (i = 0; i < MAX_MW; i++) {
> > + if (ntb->epf_ntb_bar[BAR_MW1 + i] != barno)
> > + continue;
> > + devm_kfree(&ntb->epf->dev, ntb->mw_subrange[i]);
> > + ntb->mw_subrange[i] = NULL;
> > + ntb->num_subrange[i] = 0;
> > + }
> > +
> > + /* Not use subrange mapping. If it's used in the past, clear it off. */
> > + devm_kfree(&ntb->epf->dev, epf_bar->submap);
> > + epf_bar->submap = NULL;
> > + epf_bar->num_submap = 0;
> > +
> > + ret = pci_epc_set_bar(ntb->epf->epc, ntb->epf->func_no,
> > + ntb->epf->vfunc_no, epf_bar);
> > + if (ret)
> > + dev_err(dev, "failure set mw trans\n");
> > +
> > + return ret;
> > }
> >
> > static int vntb_epf_mw_clear_trans(struct ntb_dev *ntb, int pidx, int idx)
> > @@ -1590,6 +1756,7 @@ static const struct ntb_dev_ops vntb_epf_ops = {
> > .db_vector_mask = vntb_epf_db_vector_mask,
> > .db_set_mask = vntb_epf_db_set_mask,
> > .mw_set_trans = vntb_epf_mw_set_trans,
> > + .mw_set_trans_ranges = vntb_epf_mw_set_trans_ranges,
> > .mw_clear_trans = vntb_epf_mw_clear_trans,
> > .peer_mw_get_addr = vntb_epf_peer_mw_get_addr,
> > .link_enable = vntb_epf_link_enable,
> > --
> > 2.51.0
> >