Re: [PATCH] drm/i915/pxp: limit drm-errors or warning on firmware API failures

"Ceraolo Spurio, Daniele" <daniele.ceraolospurio@xxxxxxxxx> · Fri, 3 Mar 2023 11:34:46 -0800

On 2/3/2023 9:48 PM, Alan Previn wrote:
MESA driver is creating protected context on every driver handle
creation to query caps bits for app. So when running CI tests,
they are observing hundreds of drm_errors when enabling PXP
in .config but using SOC fusing or BIOS configuration that cannot
support PXP sessions.

The fixes tag referenced below was to resolve a related issue
where we wanted to silence error messages, but that case was due
to outdated IFWI (firmware) that definitely needed an upgrade and
was, at that point, considered a one-off case as opposed to today's
realization that default CI was enabling PXP in kernel config for
all testing.

So with this patch, let's strike a balance between issues that is
critical but are root-caused from HW/platform gaps (louder drm-warn
but just ONCE) vs other cases where it could also come from session
state machine (which cannot be a WARN_ONCE since it can be triggered
due to runtime operation events).

Let's use helpers for these so as more functions are added in future
features / HW (or as FW designers continue to bless upstreaming of
the error codes and meanings), we only need to update the helpers.

NOTE: Don't completely remove FW errors (via drm_debug) or else cusomer
apps that really needs to know that content protection failed won't
be aware of it.

Fixes: b762787bf767 ("drm/i915/pxp: Use drm_dbg if arb session failed due to fw version")
Signed-off-by: Alan Previn <alan.previn.teres.alexis@xxxxxxxxx>
---
  .../i915/pxp/intel_pxp_cmd_interface_cmn.h    |  3 +
  drivers/gpu/drm/i915/pxp/intel_pxp_session.c  |  2 +-
  drivers/gpu/drm/i915/pxp/intel_pxp_tee.c      | 73 +++++++++++++++----
  3 files changed, 64 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_cmd_interface_cmn.h b/drivers/gpu/drm/i915/pxp/intel_pxp_cmd_interface_cmn.h
index ae9b151b7cb7..6f6541d5e49a 100644
--- a/drivers/gpu/drm/i915/pxp/intel_pxp_cmd_interface_cmn.h
+++ b/drivers/gpu/drm/i915/pxp/intel_pxp_cmd_interface_cmn.h
@@ -18,6 +18,9 @@
  enum pxp_status {
  	PXP_STATUS_SUCCESS = 0x0,
  	PXP_STATUS_ERROR_API_VERSION = 0x1002,
+	PXP_STATUS_NOT_READY = 0x100e,
+	PXP_STATUS_PLATFCONFIG_KF1_NOVERIF = 0x101a,
+	PXP_STATUS_PLATFCONFIG_KF1_BAD = 0x101f,
  	PXP_STATUS_OP_NOT_PERMITTED = 0x4013
  };
  
diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_session.c b/drivers/gpu/drm/i915/pxp/intel_pxp_session.c
index 448cacb0465d..7de849cb6c47 100644
--- a/drivers/gpu/drm/i915/pxp/intel_pxp_session.c
+++ b/drivers/gpu/drm/i915/pxp/intel_pxp_session.c
@@ -74,7 +74,7 @@ static int pxp_create_arb_session(struct intel_pxp *pxp)
  
  	ret = pxp_wait_for_session_state(pxp, ARB_SESSION, true);
  	if (ret) {
-		drm_err(&gt->i915->drm, "arb session failed to go in play\n");
+		drm_dbg(&gt->i915->drm, "arb session failed to go in play\n");
  		return ret;
  	}
  	drm_dbg(&gt->i915->drm, "PXP ARB session is alive\n");
diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_tee.c b/drivers/gpu/drm/i915/pxp/intel_pxp_tee.c
index d9d248b48093..2d3bcff93da3 100644
--- a/drivers/gpu/drm/i915/pxp/intel_pxp_tee.c
+++ b/drivers/gpu/drm/i915/pxp/intel_pxp_tee.c
@@ -19,6 +19,37 @@
  #include "intel_pxp_tee.h"
  #include "intel_pxp_types.h"
  
+static bool
+is_fw_err_platform_config(u32 type)
+{
+	switch (type) {
+	case PXP_STATUS_ERROR_API_VERSION:
+	case PXP_STATUS_PLATFCONFIG_KF1_NOVERIF:
+	case PXP_STATUS_PLATFCONFIG_KF1_BAD:
+		return true;
+	default:
+		break;
+	}
+	return false;
+}
+
+static const char *
+fw_err_to_string(u32 type)
+{
+	switch (type) {
+	case PXP_STATUS_ERROR_API_VERSION:
+		return "ERR_API_VERSION";
+	case PXP_STATUS_NOT_READY:
+		return "ERR_NOT_READY";
+	case PXP_STATUS_PLATFCONFIG_KF1_NOVERIF:
+	case PXP_STATUS_PLATFCONFIG_KF1_BAD:
+		return "ERR_PLATFORM_CONFIG";
+	default:
+		break;
+	}
+	return NULL;
+}
+
  static int intel_pxp_tee_io_message(struct intel_pxp *pxp,
  				    void *msg_in, u32 msg_in_size,
  				    void *msg_out, u32 msg_out_max_size,
@@ -307,15 +338,21 @@ int intel_pxp_tee_cmd_create_arb_session(struct intel_pxp *pxp,
  				       &msg_out, sizeof(msg_out),
  				       NULL);
  
-	if (ret)
-		drm_err(&i915->drm, "Failed to send tee msg ret=[%d]\n", ret);
-	else if (msg_out.header.status == PXP_STATUS_ERROR_API_VERSION)
-		drm_dbg(&i915->drm, "PXP firmware version unsupported, requested: "
-			"CMD-ID-[0x%08x] on API-Ver-[0x%08x]\n",
-			msg_in.header.command_id, msg_in.header.api_version);
-	else if (msg_out.header.status != 0x0)
-		drm_warn(&i915->drm, "PXP firmware failed arb session init request ret=[0x%08x]\n",
-			 msg_out.header.status);
+	if (ret) {
+		drm_err(&i915->drm, "Failed to send tee msg init arb session, ret=[%d]\n", ret);
+	} else if (msg_out.header.status != 0) {
+		if (is_fw_err_platform_config(msg_out.header.status))
+			drm_WARN_ONCE(&i915->drm, true,
+				      "PXP init-arb-session-%d failed due to BIOS/SOC:0x%08x:%s\n",
+				      (int)arb_session_id, msg_out.header.status,
+				      fw_err_to_string(msg_out.header.status));
+		else
+			drm_dbg(&i915->drm, "PXP init-arb-session--%d failed 0x%08x:%st:\n"

I think we usually prefer to emit 2 separate drm_dbg instead of having a 
newline in the middle

+				"CMD-ID-[0x%08x]:API-Ver-[0x%08x]\n",
+				(int)arb_session_id, msg_out.header.status,

Isn't arb_session_id already an int? why the need to cast it?

+				fw_err_to_string(msg_out.header.status),
+				msg_in.header.command_id, msg_in.header.api_version);
+	}
  
  	return ret;
  }
@@ -347,10 +384,20 @@ void intel_pxp_tee_end_arb_fw_session(struct intel_pxp *pxp, u32 session_id)
  	if ((ret || msg_out.header.status != 0x0) && ++trials < 3)
  		goto try_again;
  
-	if (ret)
+	if (ret) {
  		drm_err(&i915->drm, "Failed to send tee msg for inv-stream-key-%d, ret=[%d]\n",
  			session_id, ret);
-	else if (msg_out.header.status != 0x0)
-		drm_warn(&i915->drm, "PXP firmware failed inv-stream-key-%d with status 0x%08x\n",
-			 session_id, msg_out.header.status);
+	} else if (msg_out.header.status != 0) {
+		if (is_fw_err_platform_config(msg_out.header.status))
+			drm_WARN_ONCE(&i915->drm, true,
+				      "PXP inv-stream-key-%d failed due to BIOS/SOC :0x%08x:%s\n",
+				      (int)session_id, msg_out.header.status,

This time this is a u32, so why not just use %u?

Patch LGTM apart from these nits.

Daniele

+				      fw_err_to_string(msg_out.header.status));
+		else
+			drm_dbg(&i915->drm, "PXP inv-stream-key-%d failed 0x%08x:%s:\n"
+				"CMD-ID-[0x%08x]:API-Ver-[0x%08x]\n",
+				(int)session_id, msg_out.header.status,
+				fw_err_to_string(msg_out.header.status),
+				msg_in.header.command_id, msg_in.header.api_version);
+	}
  }







