[PATCH 19/33] drm/amd/display: Apply w/a for hard hang on HPD

From: Mikita Lipski <mikita.lipski@amd.com>
To: <amd-gfx@lists.freedesktop.org>
Cc: <Harry.Wentland@amd.com>, <Sunpeng.Li@amd.com>,
	<Bhawanpreet.Lakha@amd.com>, <Rodrigo.Siqueira@amd.com>,
	<Aurabindo.Pillai@amd.com>, <qingqing.zhuo@amd.com>,
	<mikita.lipski@amd.com>,  <roman.li@amd.com>,
	<Anson.Jacob@amd.com>, <wayne.lin@amd.com>, <stylon.wang@amd.com>,
	<solomon.chiu@amd.com>, Hersen Wu <hersenwu@amd.com>
Subject: [PATCH 19/33] drm/amd/display: Apply w/a for hard hang on HPD
Date: Wed, 8 Sep 2021 10:54:10 -0400	[thread overview]
Message-ID: <20210908145424.3311-20-mikita.lipski@amd.com> (raw)
In-Reply-To: <20210908145424.3311-1-mikita.lipski@amd.com>

From: Qingqing Zhuo <qingqing.zhuo@amd.com>

[Why]
HPD disable and enable sequences are not mutually exclusive
on Linux. For HPDs that spans under 1s (i.e. HPD low = 1s),
part of the disable sequence (specifically, a request to SMU
to lower refclk) could come right before the call to PHY
enablement, causing DMUB to access an irresponsive PHY
and thus a hard hang on the system.

[How]
Disable 48mhz refclk off when there is any HPD status in
connected state.

Reviewed-by: Hersen Wu <hersenwu@amd.com>
Acked-by: Mikita Lipski <mikita.lipski@amd.com>
Signed-off-by: Qingqing Zhuo <qingqing.zhuo@amd.com>
---
 .../amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c | 12 ++++++++-
 .../display/dc/irq/dcn21/irq_service_dcn21.c  | 25 +++++++++++++++++++
 .../display/dc/irq/dcn21/irq_service_dcn21.h  |  2 ++
 .../gpu/drm/amd/display/dc/irq/irq_service.c  |  2 +-
 .../gpu/drm/amd/display/dc/irq/irq_service.h  |  4 +++
 5 files changed, 43 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
index c6f494f0dcea..3fabf32a0558 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
@@ -42,6 +42,7 @@
 #include "clk/clk_10_0_2_sh_mask.h"
 #include "renoir_ip_offset.h"
 
+#include "irq/dcn21/irq_service_dcn21.h"
 
 /* Constants */
 
@@ -129,9 +130,11 @@ void rn_update_clocks(struct clk_mgr *clk_mgr_base,
 	struct dc_clocks *new_clocks = &context->bw_ctx.bw.dcn.clk;
 	struct dc *dc = clk_mgr_base->ctx->dc;
 	int display_count;
+	int irq_src;
 	bool update_dppclk = false;
 	bool update_dispclk = false;
 	bool dpp_clock_lowered = false;
+	uint32_t hpd_state;
 
 	struct dmcu *dmcu = clk_mgr_base->ctx->dc->res_pool->dmcu;
 
@@ -147,8 +150,15 @@ void rn_update_clocks(struct clk_mgr *clk_mgr_base,
 		if (clk_mgr_base->clks.pwr_state != DCN_PWR_STATE_LOW_POWER) {
 
 			display_count = rn_get_active_display_cnt_wa(dc, context);
+
+			for (irq_src = DC_IRQ_SOURCE_HPD1; irq_src <= DC_IRQ_SOURCE_HPD5; irq_src++) {
+				hpd_state = dal_get_hpd_state_dcn21(dc->res_pool->irqs, irq_src);
+				if (hpd_state)
+					break;
+			}
+
 			/* if we can go lower, go lower */
-			if (display_count == 0) {
+			if (display_count == 0 && !hpd_state) {
 				rn_vbios_smu_set_dcn_low_power_state(clk_mgr, DCN_PWR_STATE_LOW_POWER);
 				/* update power state */
 				clk_mgr_base->clks.pwr_state = DCN_PWR_STATE_LOW_POWER;
diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.c b/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.c
index ed54e1c819be..685528734575 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.c
+++ b/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.c
@@ -135,6 +135,31 @@ enum dc_irq_source to_dal_irq_source_dcn21(
 	return DC_IRQ_SOURCE_INVALID;
 }
 
+uint32_t dal_get_hpd_state_dcn21(struct irq_service *irq_service, enum dc_irq_source source)
+{
+	const struct irq_source_info *info;
+	uint32_t addr;
+	uint32_t value;
+	uint32_t current_status;
+
+	info = find_irq_source_info(irq_service, source);
+	if (!info)
+		return 0;
+
+	addr = info->status_reg;
+	if (!addr)
+		return 0;
+
+	value = dm_read_reg(irq_service->ctx, addr);
+	current_status =
+		get_reg_field_value(
+			value,
+			HPD0_DC_HPD_INT_STATUS,
+			DC_HPD_SENSE);
+
+	return current_status;
+}
+
 static bool hpd_ack(
 	struct irq_service *irq_service,
 	const struct irq_source_info *info)
diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.h b/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.h
index da2bd0e93d7a..3df2ceeb2b70 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.h
+++ b/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.h
@@ -31,4 +31,6 @@
 struct irq_service *dal_irq_service_dcn21_create(
 	struct irq_service_init_data *init_data);
 
+uint32_t dal_get_hpd_state_dcn21(struct irq_service *irq_service, enum dc_irq_source source);
+
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/irq/irq_service.c b/drivers/gpu/drm/amd/display/dc/irq/irq_service.c
index a2a4fbeb83f8..4db1133e4466 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/irq_service.c
+++ b/drivers/gpu/drm/amd/display/dc/irq/irq_service.c
@@ -79,7 +79,7 @@ void dal_irq_service_destroy(struct irq_service **irq_service)
 	*irq_service = NULL;
 }
 
-static const struct irq_source_info *find_irq_source_info(
+const struct irq_source_info *find_irq_source_info(
 	struct irq_service *irq_service,
 	enum dc_irq_source source)
 {
diff --git a/drivers/gpu/drm/amd/display/dc/irq/irq_service.h b/drivers/gpu/drm/amd/display/dc/irq/irq_service.h
index dbfcb096eedd..e60b82480093 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/irq_service.h
+++ b/drivers/gpu/drm/amd/display/dc/irq/irq_service.h
@@ -69,6 +69,10 @@ struct irq_service {
 	const struct irq_service_funcs *funcs;
 };
 
+const struct irq_source_info *find_irq_source_info(
+	struct irq_service *irq_service,
+	enum dc_irq_source source);
+
 void dal_irq_service_construct(
 	struct irq_service *irq_service,
 	struct irq_service_init_data *init_data);
-- 
2.25.1

