From: Wei Huang <wei.huang2@amd.com>
To: <dmaengine@vger.kernel.org>
Cc: <vkoul@kernel.org>, <Frank.Li@kernel.org>, <shuah@kernel.org>,
<nathan.lynch@amd.com>, <wei.huang2@amd.com>,
<mario.limonciello@amd.com>, <Stephen.Bates@amd.com>,
<tycho@kernel.org>, <suravee.suthikulpanit@amd.com>,
<rientjes@google.com>, <John.Kariuki@amd.com>, <jic23@kernel.org>,
<weixugc@google.com>, <bhelgaas@google.com>,
<Shyam.Iyer@dell.com>, <linux-kernel@vger.kernel.org>,
<linux-kselftest@vger.kernel.org>, <linux-pci@vger.kernel.org>
Subject: [PATCH v1 10/44] dmaengine: sdxi: separate context and submission resources
Date: Thu, 19 Nov 2026 14:22:46 -0600 [thread overview]
Message-ID: <20261119202321.1734355-11-wei.huang2@amd.com> (raw)
In-Reply-To: <20261119202321.1734355-1-wei.huang2@amd.com>
Split common context allocation from kernel submission queue
allocation and make context table programming consume an explicit
control configuration. Kernel and admin contexts retain the existing
SQ/CQ model while later userspace contexts can provide PASID-backed
ring addresses.
Co-developed-by: Nathan Lynch <nathan.lynch@amd.com>
Signed-off-by: Nathan Lynch <nathan.lynch@amd.com>
Signed-off-by: Wei Huang <wei.huang2@amd.com>
---
drivers/dma/sdxi/context.c | 120 ++++++++++++++++++++++++++-----------
drivers/dma/sdxi/context.h | 3 +
drivers/dma/sdxi/device.c | 2 +
drivers/dma/sdxi/pci.c | 1 +
drivers/dma/sdxi/sdxi.h | 1 +
5 files changed, 91 insertions(+), 36 deletions(-)
diff --git a/drivers/dma/sdxi/context.c b/drivers/dma/sdxi/context.c
index a8d065b57bac..834223e7b003 100644
--- a/drivers/dma/sdxi/context.c
+++ b/drivers/dma/sdxi/context.c
@@ -17,6 +17,7 @@
#include <linux/errno.h>
#include <linux/idr.h>
#include <linux/iommu.h>
+#include <linux/overflow.h>
#include <linux/slab.h>
#include <linux/types.h>
#include <asm/barrier.h>
@@ -81,23 +82,14 @@ static struct sdxi_cxt *sdxi_alloc_cxt(struct sdxi_dev *sdxi)
cxt->sdxi = sdxi;
ida_init(&cxt->akey_ida);
-
- cxt->ring_state = kzalloc_obj(*cxt->ring_state, GFP_KERNEL);
- if (!cxt->ring_state)
- return NULL;
-
- cxt->sq = sdxi_sq_alloc(sdxi, DEFAULT_DESC_RING_ENTRIES);
- if (!cxt->sq)
- return NULL;
-
- cxt->cst_pool = sdxi_cst_pool_create(sdxi, DEFAULT_DESC_RING_ENTRIES);
- if (!cxt->cst_pool)
- return NULL;
+ cxt->pasid = IOMMU_NO_PASID;
+ cxt->opb_000_enb = sdxi->op_grp_cap;
cxt->akey_table = dma_alloc_coherent(dev, sizeof(*cxt->akey_table),
&cxt->akey_table_dma, GFP_KERNEL);
if (!cxt->akey_table)
return NULL;
+ memset(cxt->akey_table, 0, sizeof(*cxt->akey_table));
cxt->cxt_ctl = dma_pool_zalloc(sdxi->cxt_ctl_pool, GFP_KERNEL,
&cxt->cxt_ctl_dma);
@@ -107,6 +99,25 @@ static struct sdxi_cxt *sdxi_alloc_cxt(struct sdxi_dev *sdxi)
return_ptr(cxt);
}
+static int sdxi_alloc_kernel_submission(struct sdxi_cxt *cxt)
+{
+ cxt->ring_state = kzalloc_obj(*cxt->ring_state, GFP_KERNEL);
+ if (!cxt->ring_state)
+ return -ENOMEM;
+
+ cxt->sq = sdxi_sq_alloc(cxt->sdxi, DEFAULT_DESC_RING_ENTRIES);
+ if (!cxt->sq)
+ return -ENOMEM;
+
+ cxt->cst_pool = sdxi_cst_pool_create(cxt->sdxi,
+ DEFAULT_DESC_RING_ENTRIES);
+ if (!cxt->cst_pool)
+ return -ENOMEM;
+
+ sdxi_ring_state_init(cxt->ring_state, cxt->sq);
+ return 0;
+}
+
struct sdxi_cxt_ctl_cfg {
dma_addr_t ds_ring_ptr;
dma_addr_t cxt_sts_ptr;
@@ -253,9 +264,9 @@ sdxi_get_L1_table(struct sdxi_dev *sdxi, u16 l2_idx)
* implementation. L1 pages remain allocated until device teardown so a
* cached L2 pointer can never refer to freed memory.
*/
-static int sdxi_publish_cxt(const struct sdxi_cxt *cxt)
+static int sdxi_publish_cxt(const struct sdxi_cxt *cxt,
+ const struct sdxi_cxt_ctl_cfg *ctl_cfg)
{
- struct sdxi_cxt_ctl_cfg ctl_cfg;
struct sdxi_cxt_L1_cfg L1_cfg;
struct sdxi_cxt_L1_table *L1_table;
struct sdxi_cxt_L1_ent *ent;
@@ -268,16 +279,7 @@ static int sdxi_publish_cxt(const struct sdxi_cxt *cxt)
cxt->id, cxt->sdxi->max_cxtid))
return -EINVAL;
- ctl_cfg = (typeof(ctl_cfg)) {
- .se = 1,
- .csa = 1,
- .ds_ring_ptr = sdxi_sq_ring_dma(cxt->sq),
- .ds_ring_sz = cxt->sq->count,
- .cxt_sts_ptr = sdxi_sq_cxt_sts_dma(cxt->sq),
- .write_index_ptr = sdxi_sq_write_index_dma(cxt->sq),
- };
-
- err = configure_cxt_ctl(cxt->cxt_ctl, &ctl_cfg);
+ err = configure_cxt_ctl(cxt->cxt_ctl, ctl_cfg);
if (err)
return err;
@@ -294,13 +296,13 @@ static int sdxi_publish_cxt(const struct sdxi_cxt *cxt)
L1_cfg = (typeof(L1_cfg)) {
.ka = 1,
- .pv = 0,
+ .pv = cxt->pasid_valid,
.cxt_ctl_ptr = cxt->cxt_ctl_dma,
.akey_sz = akey_table_order(cxt->akey_table),
.akey_ptr = cxt->akey_table_dma,
- .cxt_pasid = IOMMU_NO_PASID,
+ .cxt_pasid = cxt->pasid,
.max_buffer = cxt->sdxi->max_buffer,
- .opb_000_enb = cxt->sdxi->op_grp_cap,
+ .opb_000_enb = cxt->opb_000_enb,
};
err = configure_L1_entry(ent, &L1_cfg);
@@ -321,23 +323,39 @@ static void free_admin_cxt(void *ptr)
sdxi_free_cxt(sdxi->admin_cxt);
}
+static int sdxi_cxt_set_doorbell(struct sdxi_cxt *cxt);
+
int sdxi_admin_cxt_init(struct sdxi_dev *sdxi)
{
- int err;
+ struct sdxi_cxt_ctl_cfg ctl_cfg;
struct sdxi_sq *sq;
+ int err;
struct sdxi_cxt *cxt __free(sdxi_cxt) = sdxi_alloc_cxt(sdxi);
if (!cxt)
return -ENOMEM;
+ err = sdxi_alloc_kernel_submission(cxt);
+ if (err)
+ return err;
+
sq = cxt->sq;
/* SDXI 1.0 4.1.8.4.b: Set CXT_STS.state to CXTV_RUN. */
sq->cxt_sts.state = FIELD_PREP(SDXI_CXT_STS_STATE, CXTV_RUN);
cxt->id = SDXI_ADMIN_CXT_ID;
- cxt->sq->doorbell = sdxi->dbs + cxt->id * sdxi->db_stride;
- sdxi_ring_state_init(cxt->ring_state, sq);
+ err = sdxi_cxt_set_doorbell(cxt);
+ if (err)
+ return err;
- err = sdxi_publish_cxt(cxt);
+ ctl_cfg = (typeof(ctl_cfg)) {
+ .se = 1,
+ .csa = 1,
+ .ds_ring_ptr = sdxi_sq_ring_dma(cxt->sq),
+ .ds_ring_sz = cxt->sq->count,
+ .cxt_sts_ptr = sdxi_sq_cxt_sts_dma(cxt->sq),
+ .write_index_ptr = sdxi_sq_write_index_dma(cxt->sq),
+ };
+ err = sdxi_publish_cxt(cxt, &ctl_cfg);
if (err)
return err;
@@ -382,6 +400,23 @@ static bool sdxi_cxt_id_valid(const struct sdxi_cxt_id *cxt_id)
return cxt_id->index > 0;
}
+static int sdxi_cxt_set_doorbell(struct sdxi_cxt *cxt)
+{
+ struct sdxi_dev *sdxi = cxt->sdxi;
+ size_t offset;
+
+ if (check_mul_overflow((size_t)cxt->id, (size_t)sdxi->db_stride,
+ &offset) ||
+ offset > sdxi->db_size ||
+ sdxi->db_stride > sdxi->db_size - offset)
+ return -ERANGE;
+
+ if (WARN_ON_ONCE(!cxt->sq))
+ return -EINVAL;
+ cxt->sq->doorbell = sdxi->dbs + offset;
+ return 0;
+}
+
/*
* Transfer the reserved ID to the context and store its pointer in client_cxts.
* sdxi_free_cxt() releases the ID.
@@ -401,6 +436,9 @@ static void sdxi_cxt_id_assign(struct sdxi_cxt *cxt, struct sdxi_cxt_id *cxt_id)
*/
struct sdxi_cxt *sdxi_cxt_new(struct sdxi_dev *sdxi)
{
+ struct sdxi_cxt_ctl_cfg ctl_cfg;
+ int err;
+
/*
* Ensure an ID is available before allocating memory for the
* context and its control structures.
@@ -413,13 +451,23 @@ struct sdxi_cxt *sdxi_cxt_new(struct sdxi_dev *sdxi)
if (!cxt)
return NULL;
- sdxi_cxt_id_assign(cxt, &id);
-
- cxt->sq->doorbell = sdxi->dbs + cxt->id * sdxi->db_stride;
+ err = sdxi_alloc_kernel_submission(cxt);
+ if (err)
+ return NULL;
- sdxi_ring_state_init(cxt->ring_state, cxt->sq);
+ sdxi_cxt_id_assign(cxt, &id);
+ if (sdxi_cxt_set_doorbell(cxt))
+ return NULL;
- if (sdxi_publish_cxt(cxt))
+ ctl_cfg = (typeof(ctl_cfg)) {
+ .se = 1,
+ .csa = 1,
+ .ds_ring_ptr = sdxi_sq_ring_dma(cxt->sq),
+ .ds_ring_sz = cxt->sq->count,
+ .cxt_sts_ptr = sdxi_sq_cxt_sts_dma(cxt->sq),
+ .write_index_ptr = sdxi_sq_write_index_dma(cxt->sq),
+ };
+ if (sdxi_publish_cxt(cxt, &ctl_cfg))
return NULL;
return_ptr(cxt);
diff --git a/drivers/dma/sdxi/context.h b/drivers/dma/sdxi/context.h
index 196207cbca94..8e57565c0707 100644
--- a/drivers/dma/sdxi/context.h
+++ b/drivers/dma/sdxi/context.h
@@ -36,6 +36,9 @@ static inline u8 akey_table_order(const struct sdxi_akey_table *tbl)
struct sdxi_cxt {
struct sdxi_dev *sdxi;
u16 id;
+ u32 pasid;
+ u32 opb_000_enb;
+ bool pasid_valid;
struct sdxi_cxt_ctl *cxt_ctl;
dma_addr_t cxt_ctl_dma;
diff --git a/drivers/dma/sdxi/device.c b/drivers/dma/sdxi/device.c
index fa9421a5410b..4b54b14fefc1 100644
--- a/drivers/dma/sdxi/device.c
+++ b/drivers/dma/sdxi/device.c
@@ -370,6 +370,8 @@ static int sdxi_fn_activate(struct sdxi_dev *sdxi)
cap0 = sdxi_read64(sdxi, SDXI_MMIO_CAP0);
sdxi->db_stride = SZ_4K;
sdxi->db_stride *= 1U << FIELD_GET(SDXI_MMIO_CAP0_DB_STRIDE, cap0);
+ if (sdxi->db_stride > sdxi->db_size)
+ return -ENODEV;
cap1 = sdxi_read64(sdxi, SDXI_MMIO_CAP1);
sdxi->op_grp_cap = FIELD_GET(SDXI_MMIO_CAP1_OPB_000_CAP, cap1);
diff --git a/drivers/dma/sdxi/pci.c b/drivers/dma/sdxi/pci.c
index f9f75ff5e179..7b477b7bec55 100644
--- a/drivers/dma/sdxi/pci.c
+++ b/drivers/dma/sdxi/pci.c
@@ -59,6 +59,7 @@ static int sdxi_pci_init(struct sdxi_dev *sdxi)
if (IS_ERR(sdxi->dbs))
return dev_err_probe(dev, PTR_ERR(sdxi->dbs),
"failed to map doorbell region\n");
+ sdxi->db_size = pci_resource_len(pdev, SDXI_PCI_BAR_DOORBELL);
/* Mailbox registers are reserved without SR-IOV support. */
sdxi->has_mailbox = pdev->is_virtfn ||
diff --git a/drivers/dma/sdxi/sdxi.h b/drivers/dma/sdxi/sdxi.h
index 65e0191391db..fa6c3ef1c58f 100644
--- a/drivers/dma/sdxi/sdxi.h
+++ b/drivers/dma/sdxi/sdxi.h
@@ -74,6 +74,7 @@ struct sdxi_dev {
struct device *dev;
void __iomem *ctrl_regs; /* virt addr of ctrl registers */
void __iomem *dbs; /* virt addr of doorbells */
+ size_t db_size; /* mapped doorbell region size */
struct sdxi_version sdxi_version;
--
2.56.1
next prev parent reply other threads:[~2026-11-19 20:25 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-11-19 20:22 [PATCH v1 00/44] dmaengine: sdxi: add userspace control and management support Wei Huang
2026-11-19 20:22 ` [PATCH v1 01/44] dmaengine: sdxi: cache hardware version for feature gating Wei Huang
2026-11-19 20:22 ` [PATCH v1 02/44] dmaengine: sdxi: define key and error MMIO registers Wei Huang
2026-11-19 20:22 ` [PATCH v1 03/44] dmaengine: sdxi: define SDXI hardware layouts Wei Huang
2026-11-19 20:22 ` [PATCH v1 04/44] dmaengine: sdxi: encode admin descriptors Wei Huang
2026-11-19 20:22 ` [PATCH v1 05/44] dmaengine: sdxi: support timeout-aware completion waits Wei Huang
2026-11-19 20:22 ` [PATCH v1 06/44] dmaengine: sdxi: support the full context table hierarchy Wei Huang
2026-11-19 20:22 ` [PATCH v1 07/44] dmaengine: sdxi: implement synchronous admin operations Wei Huang
2026-11-19 20:22 ` [PATCH v1 08/44] dmaengine: sdxi: add core RKey table management Wei Huang
2026-11-19 20:22 ` [PATCH v1 09/44] dmaengine: sdxi: handle hardware error logs Wei Huang
2026-11-19 20:22 ` Wei Huang [this message]
2026-11-19 20:22 ` [PATCH v1 11/44] dmaengine: sdxi: support userspace context lifetimes Wei Huang
2026-11-19 20:22 ` [PATCH v1 12/44] dmaengine: sdxi: route context interrupts to eventfd Wei Huang
2026-11-19 20:22 ` [PATCH v1 13/44] dmaengine: sdxi: kill user contexts on fatal errors Wei Huang
2026-11-19 20:22 ` [PATCH v1 14/44] dmaengine: sdxi: define the ioctl UAPI surface Wei Huang
2026-11-19 20:22 ` [PATCH v1 15/44] dmaengine: sdxi: add internal ioctl definitions Wei Huang
2026-11-19 20:22 ` [PATCH v1 16/44] dmaengine: sdxi: register core character devices Wei Huang
2026-11-19 20:22 ` [PATCH v1 17/44] dmaengine: sdxi: implement fixed-size ioctl dispatch Wei Huang
2026-11-19 20:22 ` [PATCH v1 18/44] dmaengine: sdxi: implement userspace context file operations Wei Huang
2026-11-19 20:22 ` [PATCH v1 19/44] dmaengine: sdxi: validate and copy key ioctl payloads Wei Huang
2026-11-19 20:22 ` [PATCH v1 20/44] dmaengine: sdxi: implement RKey management ioctls Wei Huang
2026-11-19 20:22 ` [PATCH v1 21/44] dmaengine: sdxi: implement AKey " Wei Huang
2026-11-19 20:22 ` [PATCH v1 22/44] dmaengine: sdxi: expose operation-group discovery Wei Huang
2026-11-19 20:22 ` [PATCH v1 23/44] dmaengine: sdxi: implement typed vendor admin transport Wei Huang
2026-11-19 20:23 ` [PATCH v1 24/44] dmaengine: sdxi: expose character device attributes Wei Huang
2026-11-19 20:23 ` [PATCH v1 25/44] dmaengine: sdxi: add PF and VF device naming Wei Huang
2026-11-19 20:23 ` [PATCH v1 26/44] dmaengine: sdxi: add SDXI trace events Wei Huang
2026-11-19 20:23 ` [PATCH v1 27/44] dmaengine: sdxi: support suspend and resume Wei Huang
2026-11-19 20:23 ` [PATCH v1 28/44] dmaengine: sdxi: amd: define QoS request formats Wei Huang
2026-11-19 20:23 ` [PATCH v1 29/44] dmaengine: sdxi: amd: add QoS validation scaffolding Wei Huang
2026-11-19 20:23 ` [PATCH v1 30/44] dmaengine: sdxi: amd: build QoS admin descriptors Wei Huang
2026-11-19 20:23 ` [PATCH v1 31/44] dmaengine: sdxi: amd: prevalidate QoS operations Wei Huang
2026-11-19 20:23 ` [PATCH v1 32/44] dmaengine: sdxi: amd: execute QoS vendor operations Wei Huang
2026-11-19 20:23 ` [PATCH v1 33/44] dmaengine: sdxi: amd: register QoS vendor handler Wei Huang
2026-11-19 20:23 ` [PATCH v1 34/44] dmaengine: sdxi: amd: test QoS validation with KUnit Wei Huang
2026-11-19 20:23 ` [PATCH v1 35/44] selftests: sdxi: add build scaffold Wei Huang
2026-11-19 20:23 ` [PATCH v1 36/44] selftests: sdxi: add shared descriptor and context helpers Wei Huang
2026-11-19 20:23 ` [PATCH v1 37/44] selftests: sdxi: test context creation Wei Huang
2026-11-19 20:23 ` [PATCH v1 38/44] selftests: sdxi: test NOP descriptor submission Wei Huang
2026-11-19 20:23 ` [PATCH v1 39/44] selftests: sdxi: test copy submission and ring wrap Wei Huang
2026-11-19 20:23 ` [PATCH v1 40/44] selftests: sdxi: exercise dataplane error paths Wei Huang
2026-11-19 20:23 ` [PATCH v1 41/44] selftests: sdxi: test device ioctls Wei Huang
2026-11-19 20:23 ` [PATCH v1 42/44] selftests: sdxi: test vendor admin ioctls Wei Huang
2026-11-19 20:23 ` [PATCH v1 43/44] selftests: sdxi: test RKey ioctls Wei Huang
2026-11-19 20:23 ` [PATCH v1 44/44] MAINTAINERS: cover SDXI UAPI, vendor files, and selftests Wei Huang
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=20261119202321.1734355-11-wei.huang2@amd.com \
--to=wei.huang2@amd.com \
--cc=Frank.Li@kernel.org \
--cc=John.Kariuki@amd.com \
--cc=Shyam.Iyer@dell.com \
--cc=Stephen.Bates@amd.com \
--cc=bhelgaas@google.com \
--cc=dmaengine@vger.kernel.org \
--cc=jic23@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-kselftest@vger.kernel.org \
--cc=linux-pci@vger.kernel.org \
--cc=mario.limonciello@amd.com \
--cc=nathan.lynch@amd.com \
--cc=rientjes@google.com \
--cc=shuah@kernel.org \
--cc=suravee.suthikulpanit@amd.com \
--cc=tycho@kernel.org \
--cc=vkoul@kernel.org \
--cc=weixugc@google.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
all inboxes | Powered by JetHome®