[PATCH v1 13/44] dmaengine: sdxi: kill user contexts on fatal errors

From: Wei Huang

Date: Thu Nov 19 2026 - 15:26:20 EST


Use context references from current xarray to translate error-log
stop reactions into fatal userspace context cleanup. Kernel and
administrative contexts remain under their existing owners.

Co-developed-by: Nathan Lynch <nathan.lynch@xxxxxxx>
Signed-off-by: Nathan Lynch <nathan.lynch@xxxxxxx>
Signed-off-by: Wei Huang <wei.huang2@xxxxxxx>
---
drivers/dma/sdxi/context.c | 21 +++++++++++
drivers/dma/sdxi/context.h | 1 +
drivers/dma/sdxi/device.c | 5 +++
drivers/dma/sdxi/error.c | 71 ++++++++++++++++++++++++++++++++++++--
drivers/dma/sdxi/sdxi.h | 1 +
5 files changed, 96 insertions(+), 3 deletions(-)

diff --git a/drivers/dma/sdxi/context.c b/drivers/dma/sdxi/context.c
index f5e31f9f9131..2c3b6f5df4b5 100644
--- a/drivers/dma/sdxi/context.c
+++ b/drivers/dma/sdxi/context.c
@@ -1119,6 +1119,27 @@ void sdxi_cxt_kill(struct sdxi_cxt *cxt)
wake_up_poll(&cxt->poll_wq, EPOLLERR);
}

+void sdxi_cxt_kill_stopped(struct sdxi_cxt *cxt)
+{
+ bool newly_fatal;
+
+ if (!cxt)
+ return;
+
+ mutex_lock(&cxt->cleanup_lock);
+ newly_fatal = !cxt->fatal;
+ cxt->fatal = true;
+ cxt->started = false;
+ cxt->quiesced = true;
+ cxt->quiesce_cst_flags = 0;
+ if (sdxi_cxt_is_user(cxt))
+ sdxi_cxt_queue_cleanup_locked(cxt, 0);
+ mutex_unlock(&cxt->cleanup_lock);
+
+ if (newly_fatal)
+ wake_up_poll(&cxt->poll_wq, EPOLLERR);
+}
+
void sdxi_cxt_release_user_handle(struct sdxi_cxt *cxt)
{
if (!cxt)
diff --git a/drivers/dma/sdxi/context.h b/drivers/dma/sdxi/context.h
index b4a416509243..bbe83e54b827 100644
--- a/drivers/dma/sdxi/context.h
+++ b/drivers/dma/sdxi/context.h
@@ -108,6 +108,7 @@ int sdxi_cxt_quiesce(struct sdxi_cxt *cxt, unsigned int timeout_ms,
bool sdxi_cxt_is_user(const struct sdxi_cxt *cxt);
bool sdxi_cxt_is_fatal(const struct sdxi_cxt *cxt);
void sdxi_cxt_kill(struct sdxi_cxt *cxt);
+void sdxi_cxt_kill_stopped(struct sdxi_cxt *cxt);
void sdxi_cxt_release_user_handle(struct sdxi_cxt *cxt);
int sdxi_cxt_notify_mm_release(struct sdxi_cxt *cxt);
void sdxi_cxt_vma_open(struct sdxi_cxt *cxt);
diff --git a/drivers/dma/sdxi/device.c b/drivers/dma/sdxi/device.c
index e760c8a2603a..1587795c0a16 100644
--- a/drivers/dma/sdxi/device.c
+++ b/drivers/dma/sdxi/device.c
@@ -96,6 +96,11 @@ static enum sdxi_fn_gsv sdxi_dev_gsv(const struct sdxi_dev *sdxi)
return gsv;
}

+bool sdxi_dev_in_error(const struct sdxi_dev *sdxi)
+{
+ return sdxi_dev_gsv(sdxi) == SDXI_GSV_ERROR;
+}
+
static const unsigned long gsv_poll_interval_us = USEC_PER_MSEC * 100;
static const unsigned long gsv_transition_timeout_us = USEC_PER_SEC * 1;

diff --git a/drivers/dma/sdxi/error.c b/drivers/dma/sdxi/error.c
index 561e88d81f41..4d8607b3bbec 100644
--- a/drivers/dma/sdxi/error.c
+++ b/drivers/dma/sdxi/error.c
@@ -14,6 +14,7 @@
#include <linux/sizes.h>
#include <linux/string.h>

+#include "context.h"
#include "error.h"
#include "hw.h"
#include "mmio.h"
@@ -61,6 +62,11 @@ enum {
SDXI_PACKING_QUIRKS = QUIRK_LITTLE_ENDIAN | QUIRK_LSW32_IS_FIRST,
};

+enum sdxi_errlog_reaction {
+ SDXI_ERRLOG_REACTION_CXT_STOP = 1,
+ SDXI_ERRLOG_REACTION_FN_STOP = 2,
+};
+
static const char *const sdxi_err_steps[] = {
[1] = "internal",
[2] = "context L2",
@@ -124,6 +130,44 @@ static void sdxi_errlog_report(struct sdxi_dev *sdxi, u64 read_index,
dev_err(sdxi->dev, " buffer=%u\n", entry->buf);
}

+static bool sdxi_errlog_handle_reaction(struct sdxi_dev *sdxi,
+ const struct sdxi_errlog_entry *entry)
+{
+ struct sdxi_cxt *cxt;
+
+ if (entry->reaction == SDXI_ERRLOG_REACTION_FN_STOP)
+ return true;
+ if (entry->reaction != SDXI_ERRLOG_REACTION_CXT_STOP ||
+ !entry->cv || !entry->cxt_num)
+ return false;
+
+ cxt = sdxi_cxt_get_by_id(sdxi, entry->cxt_num);
+ if (!cxt)
+ return false;
+
+ if (sdxi_cxt_is_user(cxt))
+ sdxi_cxt_kill_stopped(cxt);
+ sdxi_cxt_put(cxt);
+ return false;
+}
+
+static void sdxi_error_handle_function(struct sdxi_dev *sdxi)
+{
+ struct sdxi_cxt *cxt;
+ u32 cxt_id;
+
+ dev_err(sdxi->dev, "function stopped after hardware error\n");
+ sdxi_dev_fail(sdxi);
+
+ for (cxt_id = 1; cxt_id <= sdxi->max_cxtid; cxt_id++) {
+ cxt = sdxi_cxt_get_by_id(sdxi, cxt_id);
+ if (!cxt)
+ continue;
+ sdxi_cxt_kill_stopped(cxt);
+ sdxi_cxt_put(cxt);
+ }
+}
+
static irqreturn_t sdxi_error_irq_thread(int irq, void *data)
{
struct sdxi_dev *sdxi = data;
@@ -134,10 +178,16 @@ static irqreturn_t sdxi_error_irq_thread(int irq, void *data)
u64 read_index;
u64 status;
u64 count;
+ bool function_stopped;

status = sdxi_read64(sdxi, SDXI_MMIO_ERR_STS);
- if (!(status & ack_mask))
- return IRQ_NONE;
+ function_stopped = sdxi_dev_in_error(sdxi);
+ if (!(status & ack_mask)) {
+ if (!function_stopped)
+ return IRQ_NONE;
+ sdxi_error_handle_function(sdxi);
+ return IRQ_HANDLED;
+ }

if (status & SDXI_MMIO_ERR_STS_ERR_BIT)
dev_err(sdxi->dev, "hardware could not write the error log\n");
@@ -145,6 +195,8 @@ static irqreturn_t sdxi_error_irq_thread(int irq, void *data)
dev_err(sdxi->dev, "error log overflowed\n");
if (!(status & SDXI_MMIO_ERR_STS_STS_BIT)) {
sdxi_write64(sdxi, SDXI_MMIO_ERR_STS, status & ack_mask);
+ if (function_stopped)
+ sdxi_error_handle_function(sdxi);
return IRQ_HANDLED;
}

@@ -170,12 +222,17 @@ static irqreturn_t sdxi_error_irq_thread(int irq, void *data)
size_t index = read_index % SDXI_ERRLOG_ENTRIES;

memcpy(&raw, &sdxi->err_log[index], sizeof(raw));
- if (sdxi_errlog_decode(sdxi, &raw, &entry))
+ if (sdxi_errlog_decode(sdxi, &raw, &entry)) {
sdxi_errlog_report(sdxi, read_index, &entry);
+ function_stopped |=
+ sdxi_errlog_handle_reaction(sdxi, &entry);
+ }
read_index++;
}

sdxi_write64(sdxi, SDXI_MMIO_ERR_RD, read_index);
+ if (function_stopped)
+ sdxi_error_handle_function(sdxi);
return IRQ_HANDLED;
}

@@ -214,6 +271,10 @@ int sdxi_error_init(struct sdxi_dev *sdxi)
FIELD_MODIFY(SDXI_MMIO_ERR_CTL_EN, &reg, 1);
sdxi_write64(sdxi, SDXI_MMIO_ERR_CTL, reg);

+ reg = sdxi_read64(sdxi, SDXI_MMIO_CTL0);
+ FIELD_MODIFY(SDXI_MMIO_CTL0_FN_ERR_INTR_EN, &reg, 1);
+ sdxi_write64(sdxi, SDXI_MMIO_CTL0, reg);
+
size_order = ilog2(SDXI_ERRLOG_SIZE) - ilog2(SZ_4K);
reg = FIELD_PREP(SDXI_MMIO_ERR_CFG_PTR,
sdxi->err_log_dma >> ilog2(SZ_4K)) |
@@ -237,6 +298,10 @@ void sdxi_error_exit(struct sdxi_dev *sdxi)
FIELD_MODIFY(SDXI_MMIO_ERR_CTL_EN, &reg, 0);
sdxi_write64(sdxi, SDXI_MMIO_ERR_CTL, reg);

+ reg = sdxi_read64(sdxi, SDXI_MMIO_CTL0);
+ FIELD_MODIFY(SDXI_MMIO_CTL0_FN_ERR_INTR_EN, &reg, 0);
+ sdxi_write64(sdxi, SDXI_MMIO_CTL0, reg);
+
if (sdxi->error_irq >= 0)
devm_free_irq(sdxi->dev, sdxi->error_irq, sdxi);

diff --git a/drivers/dma/sdxi/sdxi.h b/drivers/dma/sdxi/sdxi.h
index c000542b5ce9..fa34aaa36c16 100644
--- a/drivers/dma/sdxi/sdxi.h
+++ b/drivers/dma/sdxi/sdxi.h
@@ -160,6 +160,7 @@ static inline int sdxi_vector_to_irq(struct sdxi_dev *sdxi, unsigned int nr)

int sdxi_register(struct device *dev, const struct sdxi_bus_ops *ops);
void sdxi_unregister(struct device *dev);
+bool sdxi_dev_in_error(const struct sdxi_dev *sdxi);
void sdxi_dev_force_quiesce(struct sdxi_dev *sdxi);
void sdxi_dev_fail(struct sdxi_dev *sdxi);

--
2.56.1