From: Koichiro Den <den@valinux.co.jp>
To: "Manivannan Sadhasivam" <mani@kernel.org>,
"Krzysztof Wilczyński" <kwilczynski@kernel.org>,
"Kishon Vijay Abraham I" <kishon@kernel.org>,
"Frank Li" <Frank.Li@kernel.org>,
"Bjorn Helgaas" <bhelgaas@google.com>,
"Jingoo Han" <jingoohan1@gmail.com>,
"Niklas Cassel" <cassel@kernel.org>
Cc: Lorenzo Pieralisi <lpieralisi@kernel.org>,
Rob Herring <robh@kernel.org>, Aksh Garg <a-garg7@ti.com>,
Christoph Hellwig <hch@lst.de>, Sagi Grimberg <sagi@grimberg.me>,
Chaitanya Kulkarni <kch@nvidia.com>, Jon Mason <jdmason@kudzu.us>,
Dave Jiang <dave.jiang@intel.com>,
Allen Hubbe <allenbh@gmail.com>, Heiko Stuebner <heiko@sntech.de>,
Shawn Lin <shawn.lin@rock-chips.com>,
Manikanta Maddireddy <mmaddireddy@nvidia.com>,
Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>,
linux-pci@vger.kernel.org, linux-nvme@lists.infradead.org,
ntb@lists.linux.dev, linux-rockchip@lists.infradead.org,
linux-arm-kernel@lists.infradead.org,
linux-kernel@vger.kernel.org
Subject: [PATCH 3/3] PCI: endpoint: pci-epf-vntb: Honor MSI-X selection
Date: Fri, 28 Aug 2026 03:20:12 +0900 [thread overview]
Message-ID: <20260827182012.1984960-4-den@valinux.co.jp> (raw)
In-Reply-To: <20260827182012.1984960-1-den@valinux.co.jp>
ntb_hw_epf tries MSI-X first and falls back to MSI. It reports the
result in COMMAND_CONFIGURE_DOORBELL. pci-epf-vntb ignores MSIX_ENABLE,
configures only MSI, and always raises peer doorbells with PCI_IRQ_MSI.
When MSI-X is selected, the host does not program MSI, so raising it can
issue a write to an invalid address. This was observed with an IOMMU
enabled on the RC.
Configure MSI-X when supported and use the selected type for peer
doorbells. Use the hardware-owned layout when available. Otherwise
allocate an EPF-owned Table and PBA in the config BAR. Configure db_count
entries to cover the link event, the reserved slot, and the doorbell
slots.
Fixes: e35f56bb0330 ("PCI: endpoint: Support NTB transfer between RC and EP")
Signed-off-by: Koichiro Den <den@valinux.co.jp>
---
drivers/pci/endpoint/functions/pci-epf-vntb.c | 67 ++++++++++++++-----
1 file changed, 51 insertions(+), 16 deletions(-)
diff --git a/drivers/pci/endpoint/functions/pci-epf-vntb.c b/drivers/pci/endpoint/functions/pci-epf-vntb.c
index c3caec927d74..d9622a5d4710 100644
--- a/drivers/pci/endpoint/functions/pci-epf-vntb.c
+++ b/drivers/pci/endpoint/functions/pci-epf-vntb.c
@@ -148,6 +148,7 @@ struct epf_ntb {
u16 vntb_vid;
bool linkup;
+ bool peer_msix;
/*
* True when doorbells are interrupt-driven (MSI or embedded), false
@@ -155,6 +156,7 @@ struct epf_ntb {
*/
bool msi_doorbell;
u32 spad_size;
+ struct pci_epc_msix_layout msix_layout;
enum pci_barno epf_ntb_bar[VNTB_BAR_NUM];
@@ -303,6 +305,7 @@ static void epf_ntb_cmd_handler(struct work_struct *work)
switch (command) {
case COMMAND_CONFIGURE_DOORBELL:
+ WRITE_ONCE(ntb->peer_msix, argument & MSIX_ENABLE);
ctrl->command_status = COMMAND_STATUS_OK;
break;
case COMMAND_TEARDOWN_DOORBELL:
@@ -439,9 +442,9 @@ static void epf_ntb_config_spad_bar_free(struct epf_ntb *ntb)
* region
* @ntb: NTB device that facilitates communication between HOST and VHOST
*
- * Allocate the Local Memory mentioned in the above diagram. The size of
- * CONFIG REGION is sizeof(struct epf_ntb_ctrl) and size of SCRATCHPAD REGION
- * is obtained from "spad-count" configfs entry.
+ * Allocate the control and scratchpad regions described in the above diagram.
+ * If the EPC does not provide a hardware-owned MSI-X table and PBA, allocate
+ * space for them between the control and scratchpad regions.
*
* Returns: Zero for success, or an error code in case of failure
*/
@@ -454,7 +457,7 @@ static int epf_ntb_config_spad_bar_alloc(struct epf_ntb *ntb)
struct device *dev = &epf->dev;
u32 spad_count;
void *base;
- int i;
+ int i, ret;
const struct pci_epc_features *epc_features = pci_epc_get_features(epf->epc,
epf->func_no,
epf->vfunc_no);
@@ -462,6 +465,29 @@ static int epf_ntb_config_spad_bar_alloc(struct epf_ntb *ntb)
spad_count = ntb->spad_count;
ctrl_size = ALIGN(sizeof(struct epf_ntb_ctrl), sizeof(u32));
+ if (epc_features->msix_capable) {
+ ret = pci_epc_get_hw_msix_layout(epc_features,
+ &ntb->msix_layout);
+ if (ret && ret != -ENOENT) {
+ dev_err(dev, "Invalid hardware-owned MSI-X layout\n");
+ return ret;
+ }
+
+ if (ret == -ENOENT) {
+ ntb->msix_layout.table_bar = barno;
+ ntb->msix_layout.table_offset = ALIGN(ctrl_size, 8);
+ ntb->msix_layout.table_size =
+ ntb->db_count * PCI_MSIX_ENTRY_SIZE;
+ ntb->msix_layout.pba_bar = barno;
+ ntb->msix_layout.pba_offset =
+ ntb->msix_layout.table_offset +
+ ntb->msix_layout.table_size;
+ ntb->msix_layout.pba_size =
+ BITS_TO_U64(ntb->db_count) * sizeof(u64);
+ ctrl_size = ntb->msix_layout.pba_offset +
+ ntb->msix_layout.pba_size;
+ }
+ }
spad_size = 2 * spad_count * sizeof(u32);
base = pci_epf_alloc_space(epf, ctrl_size + spad_size,
@@ -502,6 +528,7 @@ static int epf_ntb_config_spad_bar_alloc(struct epf_ntb *ntb)
static int epf_ntb_configure_interrupt(struct epf_ntb *ntb)
{
const struct pci_epc_features *epc_features;
+ struct pci_epf *epf = ntb->epf;
struct device *dev;
int ret;
@@ -521,16 +548,22 @@ static int epf_ntb_configure_interrupt(struct epf_ntb *ntb)
}
if (epc_features->msi_capable) {
- ret = pci_epc_set_msi(ntb->epf->epc,
- ntb->epf->func_no,
- ntb->epf->vfunc_no,
- 16);
+ ret = pci_epc_set_msi(epf->epc, epf->func_no, epf->vfunc_no, 16);
if (ret) {
dev_err(dev, "MSI configuration failed\n");
return ret;
}
}
+ if (epc_features->msix_capable) {
+ ret = pci_epc_set_msix(epf->epc, epf->func_no, epf->vfunc_no,
+ ntb->db_count, &ntb->msix_layout);
+ if (ret) {
+ dev_err(dev, "MSI-X configuration failed\n");
+ return ret;
+ }
+ }
+
return 0;
}
@@ -1512,6 +1545,7 @@ static void vntb_epf_peer_db_work(struct work_struct *work)
struct epf_ntb *ntb = container_of(work, struct epf_ntb, peer_db_work);
struct pci_epf *epf = ntb->epf;
unsigned int budget = VNTB_PEER_DB_WORK_BUDGET;
+ unsigned int irq_type;
u8 func_no, vfunc_no;
unsigned int db_bit;
u32 interrupt_num;
@@ -1523,6 +1557,7 @@ static void vntb_epf_peer_db_work(struct work_struct *work)
func_no = epf->func_no;
vfunc_no = epf->vfunc_no;
+ irq_type = READ_ONCE(ntb->peer_msix) ? PCI_IRQ_MSIX : PCI_IRQ_MSI;
/*
* Drain doorbells from peer_db_pending in snapshots (atomic64_xchg()).
@@ -1536,16 +1571,16 @@ static void vntb_epf_peer_db_work(struct work_struct *work)
while (db_bits) {
/*
- * pci_epc_raise_irq() for MSI expects a 1-based
- * interrupt number. The first usable doorbell starts
- * at EPF_IRQ_DB_START in the legacy slot layout.
+ * pci_epc_raise_irq() expects a 1-based interrupt
+ * number for MSI and MSI-X. The first usable doorbell
+ * starts at EPF_IRQ_DB_START in the legacy slot layout.
*
* Legacy mapping (kept for compatibility):
*
- * MSI #1 : link event (reserved)
- * MSI #2 : unused (historical offset)
- * MSI #3 : doorbell bit 0 (DB#0)
- * MSI #4 : doorbell bit 1 (DB#1)
+ * IRQ #1 : link event (reserved)
+ * IRQ #2 : unused (historical offset)
+ * IRQ #3 : doorbell bit 0 (DB#0)
+ * IRQ #4 : doorbell bit 1 (DB#1)
* ...
*
* Do not change this mapping to avoid breaking
@@ -1556,7 +1591,7 @@ static void vntb_epf_peer_db_work(struct work_struct *work)
db_bits &= ~BIT_ULL(db_bit);
ret = pci_epc_raise_irq(epf->epc, func_no, vfunc_no,
- PCI_IRQ_MSI, interrupt_num);
+ irq_type, interrupt_num);
if (ret)
dev_err(&ntb->ntb.dev,
"Failed to raise IRQ for interrupt_num %u: %d\n",
--
2.51.0
_______________________________________________
Linux-rockchip mailing list
Linux-rockchip@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-rockchip
next prev parent reply other threads:[~2026-08-27 18:20 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-08-27 18:20 [PATCH 0/3] PCI: endpoint: Support hardware-owned MSI-X table and PBA Koichiro Den
2026-08-27 18:20 ` [PATCH 1/3] " Koichiro Den
2026-08-27 18:20 ` [PATCH 2/3] PCI: dw-rockchip: Support fixed MSI-X table and PBA on RK3588 Koichiro Den
2026-08-27 18:20 ` Koichiro Den [this message]
2026-08-27 19:23 ` [PATCH 3/3] PCI: endpoint: pci-epf-vntb: Honor MSI-X selection Frank Li
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20260827182012.1984960-4-den@valinux.co.jp \
--to=den@valinux.co.jp \
--cc=Frank.Li@kernel.org \
--cc=a-garg7@ti.com \
--cc=allenbh@gmail.com \
--cc=bhelgaas@google.com \
--cc=cassel@kernel.org \
--cc=dave.jiang@intel.com \
--cc=hch@lst.de \
--cc=heiko@sntech.de \
--cc=jdmason@kudzu.us \
--cc=jingoohan1@gmail.com \
--cc=kch@nvidia.com \
--cc=kishon@kernel.org \
--cc=kwilczynski@kernel.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-nvme@lists.infradead.org \
--cc=linux-pci@vger.kernel.org \
--cc=linux-rockchip@lists.infradead.org \
--cc=lpieralisi@kernel.org \
--cc=mani@kernel.org \
--cc=mmaddireddy@nvidia.com \
--cc=ntb@lists.linux.dev \
--cc=robh@kernel.org \
--cc=sagi@grimberg.me \
--cc=shawn.lin@rock-chips.com \
--cc=shinichiro.kawasaki@wdc.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox