linux-kernel - [PATCH 3/3] remoteproc: xlnx: add crash detection mechanism

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <20251028045730.1622685-4-tanmay.shah@amd.com>
Date: Mon, 27 Oct 2025 21:57:31 -0700
From: Tanmay Shah <tanmay.shah@....com>
To: <andersson@...nel.org>, <mathieu.poirier@...aro.org>
CC: <linux-remoteproc@...r.kernel.org>, <linux-kernel@...r.kernel.org>,
	"Tanmay Shah" <tanmay.shah@....com>
Subject: [PATCH 3/3] remoteproc: xlnx: add crash detection mechanism

Remote processor will report the crash reason via the resource table
and notify the host via kick. The host checks this crash reason on
every kick notification from the remote and report to the core
framework. Then the rproc core framework will start the recovery
process.

Signed-off-by: Tanmay Shah <tanmay.shah@....com>
---
 drivers/remoteproc/xlnx_r5_remoteproc.c | 58 ++++++++++++++++++++++++-
 1 file changed, 57 insertions(+), 1 deletion(-)

diff --git a/drivers/remoteproc/xlnx_r5_remoteproc.c b/drivers/remoteproc/xlnx_r5_remoteproc.c
index 8677b732ad14..9c6b5f751824 100644
--- a/drivers/remoteproc/xlnx_r5_remoteproc.c
+++ b/drivers/remoteproc/xlnx_r5_remoteproc.c
@@ -108,6 +108,10 @@ struct rsc_tbl_data {
 	const uintptr_t rsc_tbl;
 } __packed;
 
+enum fw_vendor_rsc {
+	FW_RSC_VENDOR_CRASH_REASON = RSC_VENDOR_START,
+};
+
 /*
  * Hardcoded TCM bank values. This will stay in driver to maintain backward
  * compatibility with device-tree that does not have TCM information.
@@ -127,9 +131,21 @@ static const struct mem_bank_data zynqmp_tcm_banks_lockstep[] = {
 	{0xffe30000UL, 0x30000, 0x10000UL, PD_R5_1_BTCM, "btcm1"},
 };
 
+/**
+ * struct xlnx_rproc_crash_report - resource to know crash status and reason
+ *
+ * @crash_state: if true, the rproc is notifying crash, time to recover
+ * @crash_reason: reason of crash
+ */
+struct xlnx_rproc_crash_report {
+	u32 crash_state;
+	u32 crash_reason;
+} __packed;
+
 /**
  * struct zynqmp_r5_core - remoteproc core's internal data
  *
+ * @crash_report: rproc crash state and reason
  * @rsc_tbl_va: resource table virtual address
  * @sram: Array of sram memories assigned to this core
  * @num_sram: number of sram for this core
@@ -143,6 +159,7 @@ static const struct mem_bank_data zynqmp_tcm_banks_lockstep[] = {
  * @ipi: pointer to mailbox information
  */
 struct zynqmp_r5_core {
+	struct xlnx_rproc_crash_report *crash_report;
 	void __iomem *rsc_tbl_va;
 	struct zynqmp_sram_bank *sram;
 	int num_sram;
@@ -227,10 +244,14 @@ static void handle_event_notified(struct work_struct *work)
 static void zynqmp_r5_mb_rx_cb(struct mbox_client *cl, void *msg)
 {
 	struct zynqmp_ipi_message *ipi_msg, *buf_msg;
+	struct zynqmp_r5_core *r5_core;
+	struct rproc *rproc;
 	struct mbox_info *ipi;
 	size_t len;
 
 	ipi = container_of(cl, struct mbox_info, mbox_cl);
+	r5_core = ipi->r5_core;
+	rproc = r5_core->rproc;
 
 	/* copy data from ipi buffer to r5_core */
 	ipi_msg = (struct zynqmp_ipi_message *)msg;
@@ -244,6 +265,13 @@ static void zynqmp_r5_mb_rx_cb(struct mbox_client *cl, void *msg)
 	buf_msg->len = len;
 	memcpy(buf_msg->data, ipi_msg->data, len);
 
+	/* Check for crash only if rproc crash is expected */
+	if (rproc->state == RPROC_ATTACHED || rproc->state == RPROC_RUNNING) {
+		if (r5_core->crash_report->crash_state)
+			rproc_report_crash(rproc,
+					   r5_core->crash_report->crash_reason);
+	}
+
 	/* received and processed interrupt ack */
 	if (mbox_send_message(ipi->rx_chan, NULL) < 0)
 		dev_err(cl->dev, "ack failed to mbox rx_chan\n");
@@ -394,9 +422,14 @@ static int zynqmp_r5_rproc_start(struct rproc *rproc)
 
 	ret = zynqmp_pm_request_wake(r5_core->pm_domain_id, 1,
 				     bootmem, ZYNQMP_PM_REQUEST_ACK_NO);
-	if (ret)
+	if (ret) {
 		dev_err(r5_core->dev,
 			"failed to start RPU = 0x%x\n", r5_core->pm_domain_id);
+		return ret;
+	}
+
+	clear_bit(RPROC_FEAT_ATTACH_ON_RECOVERY, rproc->features);
+
 	return ret;
 }
 
@@ -874,6 +907,8 @@ static int zynqmp_r5_get_rsc_table_va(struct zynqmp_r5_core *r5_core)
 
 static int zynqmp_r5_attach(struct rproc *rproc)
 {
+	rproc_set_feature(rproc, RPROC_FEAT_ATTACH_ON_RECOVERY);
+
 	dev_dbg(&rproc->dev, "rproc %d attached\n", rproc->index);
 
 	return 0;
@@ -896,6 +931,26 @@ static void zynqmp_r5_coredump(struct rproc *rproc)
 	(void)rproc;
 }
 
+static int zynqmp_r5_handle_crash_rsc(struct rproc *rproc, void *rsc,
+				      int offset, int avail)
+{
+	struct zynqmp_r5_core *r5_core = rproc->priv;
+
+	r5_core->crash_report =
+		(struct xlnx_rproc_crash_report *)(r5_core->rsc_tbl_va + offset);
+
+	return RSC_HANDLED;
+}
+
+static int zynqmp_r5_handle_rsc(struct rproc *rproc, u32 rsc_type, void *rsc,
+				int offset, int avail)
+{
+	if (rsc_type == FW_RSC_VENDOR_CRASH_REASON)
+		return zynqmp_r5_handle_crash_rsc(rproc, rsc, offset, avail);
+
+	return RSC_IGNORED;
+}
+
 static const struct rproc_ops zynqmp_r5_rproc_ops = {
 	.prepare	= zynqmp_r5_rproc_prepare,
 	.unprepare	= zynqmp_r5_rproc_unprepare,
@@ -911,6 +966,7 @@ static const struct rproc_ops zynqmp_r5_rproc_ops = {
 	.attach		= zynqmp_r5_attach,
 	.detach		= zynqmp_r5_detach,
 	.coredump	= zynqmp_r5_coredump,
+	.handle_rsc	= zynqmp_r5_handle_rsc,
 };
 
 /**
-- 
2.34.1