Re: [RFC PATCH v4 08/38] NTB: epf: Provide db_vector_count/db_vector_mask callbacks

On Mon, Jan 19, 2026 at 03:03:07PM -0500, Frank Li wrote:
> On Sun, Jan 18, 2026 at 10:54:10PM +0900, Koichiro Den wrote:
> > Provide db_vector_count() and db_vector_mask() implementations for both
> > ntb_hw_epf and pci-epf-vntb so that ntb_transport can map MSI vectors to
> > doorbell bits. Without them, the upper layer cannot identify which
> > doorbell vector fired and ends up scheduling rxc_db_work() for all queue
> > pairs, resulting in a thundering-herd effect when multiple queue pairs
> > (QPs) are enabled.
> >
> > With this change, .peer_db_set() must honor the db_bits mask and raise
> > all requested doorbell interrupts, so update those implementations
> > accordingly.
> >
> > Signed-off-by: Koichiro Den <[email protected]>
> > ---
> 
> Patch 6/7/8 can be post seperatly. Basic look good.

Will do so. Thank you for the suggestion.

Koichiro

> 
> Frank
> 
> >  drivers/ntb/hw/epf/ntb_hw_epf.c               | 47 ++++++++++++-------
> >  drivers/pci/endpoint/functions/pci-epf-vntb.c | 41 +++++++++++++---
> >  2 files changed, 64 insertions(+), 24 deletions(-)
> >
> > diff --git a/drivers/ntb/hw/epf/ntb_hw_epf.c b/drivers/ntb/hw/epf/ntb_hw_epf.c
> > index dbb5bebe63a5..c37ede4063dc 100644
> > --- a/drivers/ntb/hw/epf/ntb_hw_epf.c
> > +++ b/drivers/ntb/hw/epf/ntb_hw_epf.c
> > @@ -381,7 +381,7 @@ static int ntb_epf_init_isr(struct ntb_epf_dev *ndev, int msi_min, int msi_max)
> >  		}
> >  	}
> >
> > -	ndev->db_count = irq;
> > +	ndev->db_count = irq - 1;
> >
> >  	ret = ntb_epf_send_command(ndev, CMD_CONFIGURE_DOORBELL,
> >  				   argument | irq);
> > @@ -415,6 +415,22 @@ static u64 ntb_epf_db_valid_mask(struct ntb_dev *ntb)
> >  	return ntb_ndev(ntb)->db_valid_mask;
> >  }
> >
> > +static int ntb_epf_db_vector_count(struct ntb_dev *ntb)
> > +{
> > +	return ntb_ndev(ntb)->db_count;
> > +}
> > +
> > +static u64 ntb_epf_db_vector_mask(struct ntb_dev *ntb, int db_vector)
> > +{
> > +	struct ntb_epf_dev *ndev = ntb_ndev(ntb);
> > +
> > +	db_vector--; /* vector 0 is reserved for link events */
> > +	if (db_vector < 0 || db_vector >= ndev->db_count)
> > +		return 0;
> > +
> > +	return ndev->db_valid_mask & BIT_ULL(db_vector);
> > +}
> > +
> >  static int ntb_epf_db_set_mask(struct ntb_dev *ntb, u64 db_bits)
> >  {
> >  	return 0;
> > @@ -507,26 +523,21 @@ static int ntb_epf_peer_mw_get_addr(struct ntb_dev *ntb, int idx,
> >  static int ntb_epf_peer_db_set(struct ntb_dev *ntb, u64 db_bits)
> >  {
> >  	struct ntb_epf_dev *ndev = ntb_ndev(ntb);
> > -	u32 interrupt_num = ffs(db_bits) + 1;
> > -	struct device *dev = ndev->dev;
> > +	u32 interrupt_num;
> >  	u32 db_entry_size;
> >  	u32 db_offset;
> >  	u32 db_data;
> > -
> > -	if (interrupt_num >= ndev->db_count) {
> > -		dev_err(dev, "DB interrupt %d greater than Max Supported %d\n",
> > -			interrupt_num, ndev->db_count);
> > -		return -EINVAL;
> > -	}
> > +	unsigned long i;
> >
> >  	db_entry_size = readl(ndev->ctrl_reg + NTB_EPF_DB_ENTRY_SIZE);
> >
> > -	db_data = readl(ndev->ctrl_reg + NTB_EPF_DB_DATA(interrupt_num));
> > -	db_offset = readl(ndev->ctrl_reg + NTB_EPF_DB_OFFSET(interrupt_num));
> > -
> > -	writel(db_data, ndev->db_reg + (db_entry_size * interrupt_num) +
> > -	       db_offset);
> > -
> > +	for_each_set_bit(i, (unsigned long *)&db_bits, ndev->db_count) {
> > +		interrupt_num = i + 1;
> > +		db_data = readl(ndev->ctrl_reg + NTB_EPF_DB_DATA(interrupt_num));
> > +		db_offset = readl(ndev->ctrl_reg + NTB_EPF_DB_OFFSET(interrupt_num));
> > +		writel(db_data, ndev->db_reg + (db_entry_size * interrupt_num) +
> > +		       db_offset);
> > +	}
> >  	return 0;
> >  }
> >
> > @@ -556,6 +567,8 @@ static const struct ntb_dev_ops ntb_epf_ops = {
> >  	.spad_count		= ntb_epf_spad_count,
> >  	.peer_mw_count		= ntb_epf_peer_mw_count,
> >  	.db_valid_mask		= ntb_epf_db_valid_mask,
> > +	.db_vector_count	= ntb_epf_db_vector_count,
> > +	.db_vector_mask		= ntb_epf_db_vector_mask,
> >  	.db_set_mask		= ntb_epf_db_set_mask,
> >  	.mw_set_trans		= ntb_epf_mw_set_trans,
> >  	.mw_clear_trans		= ntb_epf_mw_clear_trans,
> > @@ -607,8 +620,8 @@ static int ntb_epf_init_dev(struct ntb_epf_dev *ndev)
> >  	int ret;
> >
> >  	/* One Link interrupt and rest doorbell interrupt */
> > -	ret = ntb_epf_init_isr(ndev, NTB_EPF_MIN_DB_COUNT + NTB_EPF_IRQ_RESERVE,
> > -			       NTB_EPF_MAX_DB_COUNT + NTB_EPF_IRQ_RESERVE);
> > +	ret = ntb_epf_init_isr(ndev, NTB_EPF_MIN_DB_COUNT + 1 + NTB_EPF_IRQ_RESERVE,
> > +			       NTB_EPF_MAX_DB_COUNT + 1 + NTB_EPF_IRQ_RESERVE);
> >  	if (ret) {
> >  		dev_err(dev, "Failed to init ISR\n");
> >  		return ret;
> > diff --git a/drivers/pci/endpoint/functions/pci-epf-vntb.c b/drivers/pci/endpoint/functions/pci-epf-vntb.c
> > index 4927faa28255..39e784e21236 100644
> > --- a/drivers/pci/endpoint/functions/pci-epf-vntb.c
> > +++ b/drivers/pci/endpoint/functions/pci-epf-vntb.c
> > @@ -1384,6 +1384,22 @@ static u64 vntb_epf_db_valid_mask(struct ntb_dev *ntb)
> >  	return BIT_ULL(ntb_ndev(ntb)->db_count) - 1;
> >  }
> >
> > +static int vntb_epf_db_vector_count(struct ntb_dev *ntb)
> > +{
> > +	return ntb_ndev(ntb)->db_count;
> > +}
> > +
> > +static u64 vntb_epf_db_vector_mask(struct ntb_dev *ntb, int db_vector)
> > +{
> > +	struct epf_ntb *ndev = ntb_ndev(ntb);
> > +
> > +	db_vector--; /* vector 0 is reserved for link events */
> > +	if (db_vector < 0 || db_vector >= ndev->db_count)
> > +		return 0;
> > +
> > +	return BIT_ULL(db_vector);
> > +}
> > +
> >  static int vntb_epf_db_set_mask(struct ntb_dev *ntb, u64 db_bits)
> >  {
> >  	return 0;
> > @@ -1487,20 +1503,29 @@ static int vntb_epf_peer_spad_write(struct ntb_dev *ndev, int pidx, int idx, u32
> >
> >  static int vntb_epf_peer_db_set(struct ntb_dev *ndev, u64 db_bits)
> >  {
> > -	u32 interrupt_num = ffs(db_bits) + 1;
> >  	struct epf_ntb *ntb = ntb_ndev(ndev);
> >  	u8 func_no, vfunc_no;
> > -	int ret;
> > +	u64 failed = 0;
> > +	unsigned long i;
> >
> >  	func_no = ntb->epf->func_no;
> >  	vfunc_no = ntb->epf->vfunc_no;
> >
> > -	ret = pci_epc_raise_irq(ntb->epf->epc, func_no, vfunc_no,
> > -				PCI_IRQ_MSI, interrupt_num + 1);
> > -	if (ret)
> > -		dev_err(&ntb->ntb->dev, "Failed to raise IRQ\n");
> > +	for_each_set_bit(i, (unsigned long *)&db_bits, ntb->db_count) {
> > +		/*
> > +		 * DB bit i is MSI interrupt (i + 2).
> > +		 * Vector 0 is used for link events and MSI vectors are
> > +		 * 1-based for pci_epc_raise_irq().
> > +		 */
> > +		if (pci_epc_raise_irq(ntb->epf->epc, func_no, vfunc_no,
> > +				      PCI_IRQ_MSI, i + 2))
> > +			failed |= BIT_ULL(i);
> > +	}
> > +	if (failed)
> > +		dev_err(&ntb->ntb->dev, "Failed to raise IRQ (%#llx)\n",
> > +			failed);
> >
> > -	return ret;
> > +	return failed ? -EIO : 0;
> >  }
> >
> >  static u64 vntb_epf_db_read(struct ntb_dev *ndev)
> > @@ -1561,6 +1586,8 @@ static const struct ntb_dev_ops vntb_epf_ops = {
> >  	.spad_count		= vntb_epf_spad_count,
> >  	.peer_mw_count		= vntb_epf_peer_mw_count,
> >  	.db_valid_mask		= vntb_epf_db_valid_mask,
> > +	.db_vector_count	= vntb_epf_db_vector_count,
> > +	.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_clear_trans		= vntb_epf_mw_clear_trans,
> > --
> > 2.51.0
> >