[PATCH AUTOSEL 5.12 001/134] drm: Added orientation quirk for OneGX1 Pro

[PATCH AUTOSEL 5.12 001/134] drm: Added orientation quirk for OneGX1 Pro

[Sasha Levin]

From: Jared Baldridge <jrb@expunge.us>

[ Upstream commit 81ad7f9f78e4ff80e95be8282423f511b84f1166 ]

The OneGX1 Pro has a fairly unique combination of generic strings,
but we additionally match on the BIOS date just to be safe.

Signed-off-by: Jared Baldridge <jrb@expunge.us>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/41288ccb-1012-486b-81c1-a24c31850c91@www.fastmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/drm_panel_orientation_quirks.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c
index 58f5dc2f6dd5..f6bdec7fa925 100644
--- a/drivers/gpu/drm/drm_panel_orientation_quirks.c
+++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c
@@ -84,6 +84,13 @@ static const struct drm_dmi_panel_orientation_data itworks_tw891 = {
 	.orientation = DRM_MODE_PANEL_ORIENTATION_RIGHT_UP,
 };
 
+static const struct drm_dmi_panel_orientation_data onegx1_pro = {
+	.width = 1200,
+	.height = 1920,
+	.bios_dates = (const char * const []){ "12/17/2020", NULL },
+	.orientation = DRM_MODE_PANEL_ORIENTATION_RIGHT_UP,
+};
+
 static const struct drm_dmi_panel_orientation_data lcd720x1280_rightside_up = {
 	.width = 720,
 	.height = 1280,
@@ -211,6 +218,13 @@ static const struct dmi_system_id orientation_data[] = {
 		  DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "Lenovo ideapad D330-10IGM"),
 		},
 		.driver_data = (void *)&lcd1200x1920_rightside_up,
+	}, {	/* OneGX1 Pro */
+		.matches = {
+		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "SYSTEM_MANUFACTURER"),
+		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "SYSTEM_PRODUCT_NAME"),
+		  DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "Default string"),
+		},
+		.driver_data = (void *)&onegx1_pro,
 	}, {	/* VIOS LTH17 */
 		.matches = {
 		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "VIOS"),
-- 
2.30.2

[PATCH AUTOSEL 5.12 002/134] drm/qxl: do not run release if qxl failed to init

[Sasha Levin]

From: Tong Zhang <ztong0001@gmail.com>

[ Upstream commit b91907a6241193465ca92e357adf16822242296d ]

if qxl_device_init() fail, drm device will not be registered,
in this case, do not run qxl_drm_release()

[    5.258534] ==================================================================
[    5.258931] BUG: KASAN: user-memory-access in qxl_destroy_monitors_object+0x42/0xa0 [qxl]
[    5.259388] Write of size 8 at addr 00000000000014dc by task modprobe/95
[    5.259754]
[    5.259842] CPU: 0 PID: 95 Comm: modprobe Not tainted 5.11.0-rc6-00007-g88bb507a74ea #62
[    5.260309] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-48-gd9c812dda54
[    5.260917] Call Trace:
[    5.261056]  dump_stack+0x7d/0xa3
[    5.261245]  kasan_report.cold+0x10c/0x10e
[    5.261475]  ? qxl_destroy_monitors_object+0x42/0xa0 [qxl]
[    5.261789]  check_memory_region+0x17c/0x1e0
[    5.262029]  qxl_destroy_monitors_object+0x42/0xa0 [qxl]
[    5.262332]  qxl_modeset_fini+0x9/0x20 [qxl]
[    5.262595]  qxl_drm_release+0x22/0x30 [qxl]
[    5.262841]  drm_dev_release+0x32/0x50
[    5.263047]  release_nodes+0x39e/0x410
[    5.263253]  ? devres_release+0x40/0x40
[    5.263462]  really_probe+0x2ea/0x420
[    5.263664]  driver_probe_device+0x6d/0xd0
[    5.263888]  device_driver_attach+0x82/0x90
[    5.264116]  ? device_driver_attach+0x90/0x90
[    5.264353]  __driver_attach+0x60/0x100
[    5.264563]  ? device_driver_attach+0x90/0x90
[    5.264801]  bus_for_each_dev+0xe1/0x140
[    5.265014]  ? subsys_dev_iter_exit+0x10/0x10
[    5.265251]  ? klist_node_init+0x61/0x80
[    5.265464]  bus_add_driver+0x254/0x2a0
[    5.265673]  driver_register+0xd3/0x150
[    5.265882]  ? 0xffffffffc0048000
[    5.266064]  do_one_initcall+0x84/0x250
[    5.266274]  ? trace_event_raw_event_initcall_finish+0x150/0x150
[    5.266596]  ? unpoison_range+0xf/0x30
[    5.266801]  ? ____kasan_kmalloc.constprop.0+0x84/0xa0
[    5.267082]  ? unpoison_range+0xf/0x30
[    5.267287]  ? unpoison_range+0xf/0x30
[    5.267491]  do_init_module+0xf8/0x350
[    5.267697]  load_module+0x3fe6/0x4340
[    5.267902]  ? vm_unmap_ram+0x1d0/0x1d0
[    5.268115]  ? module_frob_arch_sections+0x20/0x20
[    5.268375]  ? __do_sys_finit_module+0x108/0x170
[    5.268624]  __do_sys_finit_module+0x108/0x170
[    5.268865]  ? __ia32_sys_init_module+0x40/0x40
[    5.269111]  ? file_open_root+0x200/0x200
[    5.269330]  ? do_sys_open+0x85/0xe0
[    5.269527]  ? filp_open+0x50/0x50
[    5.269714]  ? exit_to_user_mode_prepare+0xfc/0x130
[    5.269978]  do_syscall_64+0x33/0x40
[    5.270176]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
[    5.270450] RIP: 0033:0x7fa3f685bcf7
[    5.270646] Code: 48 89 57 30 48 8b 04 24 48 89 47 38 e9 1d a0 02 00 48 89 f8 48 89 f7 48 89 d1
[    5.271634] RSP: 002b:00007ffca83048d8 EFLAGS: 00000246 ORIG_RAX: 0000000000000139
[    5.272037] RAX: ffffffffffffffda RBX: 0000000001e94a70 RCX: 00007fa3f685bcf7
[    5.272416] RDX: 0000000000000000 RSI: 0000000001e939e0 RDI: 0000000000000003
[    5.272794] RBP: 0000000000000003 R08: 0000000000000000 R09: 0000000000000001
[    5.273171] R10: 00007fa3f68bf300 R11: 0000000000000246 R12: 0000000001e939e0
[    5.273550] R13: 0000000000000000 R14: 0000000001e93bd0 R15: 0000000000000001
[    5.273928] ==================================================================

Signed-off-by: Tong Zhang <ztong0001@gmail.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20210203040727.868921-1-ztong0001@gmail.com
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/qxl/qxl_drv.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/qxl/qxl_drv.c b/drivers/gpu/drm/qxl/qxl_drv.c
index 1864467f1063..1b09bbe98055 100644
--- a/drivers/gpu/drm/qxl/qxl_drv.c
+++ b/drivers/gpu/drm/qxl/qxl_drv.c
@@ -144,6 +144,8 @@ static void qxl_drm_release(struct drm_device *dev)
 	 * reordering qxl_modeset_fini() + qxl_device_fini() calls is
 	 * non-trivial though.
 	 */
+	if (!dev->registered)
+		return;
 	qxl_modeset_fini(qdev);
 	qxl_device_fini(qdev);
 }
-- 
2.30.2

[PATCH AUTOSEL 5.12 003/134] drm/qxl: release shadow on shutdown

[Sasha Levin]

From: Gerd Hoffmann <kraxel@redhat.com>

[ Upstream commit 4ca77c513537700d3fae69030879f781dde1904c ]

In case we have a shadow surface on shutdown release
it so it doesn't leak.

Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Acked-by: Thomas Zimmermann <tzimmermann@suse.de>
Link: http://patchwork.freedesktop.org/patch/msgid/20210204145712.1531203-6-kraxel@redhat.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/qxl/qxl_display.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c
index 10738e04c09b..56e0c6c625e9 100644
--- a/drivers/gpu/drm/qxl/qxl_display.c
+++ b/drivers/gpu/drm/qxl/qxl_display.c
@@ -1228,6 +1228,10 @@ int qxl_modeset_init(struct qxl_device *qdev)
 
 void qxl_modeset_fini(struct qxl_device *qdev)
 {
+	if (qdev->dumb_shadow_bo) {
+		drm_gem_object_put(&qdev->dumb_shadow_bo->tbo.base);
+		qdev->dumb_shadow_bo = NULL;
+	}
 	qxl_destroy_monitors_object(qdev);
 	drm_mode_config_cleanup(&qdev->ddev);
 }
-- 
2.30.2

[PATCH AUTOSEL 5.12 004/134] drm/ast: Fix invalid usage of AST_MAX_HWC_WIDTH in cursor atomic_check

[Sasha Levin]

From: Thomas Zimmermann <tzimmermann@suse.de>

[ Upstream commit ee4a92d690f30f3793df942939726bec0338e65b ]

Use AST_MAX_HWC_HEIGHT for setting offset_y in the cursor plane's
atomic_check. The code used AST_MAX_HWC_WIDTH instead. This worked
because both constants has the same value.

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Acked-by: Gerd Hoffmann <kraxel@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210209134632.12157-3-tzimmermann@suse.de
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/ast/ast_mode.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c
index 988b270fea5e..758c69aa7232 100644
--- a/drivers/gpu/drm/ast/ast_mode.c
+++ b/drivers/gpu/drm/ast/ast_mode.c
@@ -688,7 +688,7 @@ ast_cursor_plane_helper_atomic_update(struct drm_plane *plane,
 	unsigned int offset_x, offset_y;
 
 	offset_x = AST_MAX_HWC_WIDTH - fb->width;
-	offset_y = AST_MAX_HWC_WIDTH - fb->height;
+	offset_y = AST_MAX_HWC_HEIGHT - fb->height;
 
 	if (state->fb != old_state->fb) {
 		/* A new cursor image was installed. */
-- 
2.30.2

[PATCH AUTOSEL 5.12 005/134] drm/amd/display: changing sr exit latency

[Sasha Levin]

From: Martin Leung <martin.leung@amd.com>

[ Upstream commit efe213e5a57e0cd92fa4f328dc1963d330549982 ]

[Why]
Hardware team remeasured, need to update timings
to increase latency slightly and avoid intermittent
underflows.

[How]
sr exit latency update.

Signed-off-by: Martin Leung <martin.leung@amd.com>
Reviewed-by: Alvin Lee <Alvin.Lee2@amd.com>
Acked-by: Qingqing Zhuo <Qingqing.Zhuo@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
index fb7f1dea3c46..71e2d5e02571 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
@@ -181,7 +181,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_0_soc = {
 		},
 	.min_dcfclk = 500.0, /* TODO: set this to actual min DCFCLK */
 	.num_states = 1,
-	.sr_exit_time_us = 12,
+	.sr_exit_time_us = 15.5,
 	.sr_enter_plus_exit_time_us = 20,
 	.urgent_latency_us = 4.0,
 	.urgent_latency_pixel_data_only_us = 4.0,
-- 
2.30.2

[PATCH AUTOSEL 5.12 006/134] drm/amd/display: Fix MPC OGAM power on/off sequence

[Sasha Levin]

From: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>

[ Upstream commit 737b2b536a30a467c405d75f2287e17828838a13 ]

[Why]
Color corruption can occur on bootup into a login
manager that applies a non-linear gamma LUT because
the LUT may not actually be powered on before writing.

It's cleared on the next full pipe reprogramming as
we switch to LUTB from LUTA and the pipe accessing
the LUT has taken it out of light sleep mode.

[How]
The MPCC_OGAM_MEM_PWR_FORCE register does not force
the current power mode when set to 0. It only forces
when set light sleep, deep sleep or shutdown.

The register to actually force power on and ignore
sleep modes is MPCC_OGAM_MEM_PWR_DIS - a value of 0
will enable power requests and a value of 1 will
disable them.

When PWR_FORCE!=0 is combined with PWR_DIS=0 then
MPCC OGAM memory is forced into the state specified
by the force bits.

If PWR_FORCE is 0 then it respects the mode specified
by MPCC_OGAM_MEM_LOW_PWR_MODE if the RAM LUT is not
in use.

We set that bit to shutdown on low power, but otherwise
it inherits from bootup defaults.

So for the fix:

1. Update the sequence to "force" power on when needed

We can use MPCC_OGAM_MEM_PWR_DIS for this to turn on the
memory even when the block is in bypass and pending to be
enabled for the next frame.

We need this for both low power enabled or disabled.

If we don't set this then we can run into issues when we
first program the LUT from bootup.

2. Don't apply FORCE_SEL

Once we enable power requests with DIS=0 we run into the
issue of the RAM being forced into light sleep and being
unusable for display output. Leave this 0 like we used to
for DCN20.

3. Rely on MPCC OGAM init to determine light sleep/deep sleep

MPC low power debug mode isn't enabled on any ASIC currently
but we'll respect the setting determined during init if it
is.

Lightly tested as working with IGT tests and desktop color
adjustment.

4. Change the MPC resource default for DCN30

It was interleaving the dcn20 and dcn30 versions before
depending on the sequence.

5. REG_WAIT for it to be on whenever we're powering up the
memory

Otherwise we can write register values too early and we'll
get corruption.

Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Reviewed-by: Eric Yang <eric.yang2@amd.com>
Acked-by: Qingqing Zhuo <Qingqing.Zhuo@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../gpu/drm/amd/display/dc/dcn30/dcn30_mpc.c  | 24 ++++++++++---------
 1 file changed, 13 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.c
index 3e6f76096119..a7598356f37d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.c
@@ -143,16 +143,18 @@ static void mpc3_power_on_ogam_lut(
 {
 	struct dcn30_mpc *mpc30 = TO_DCN30_MPC(mpc);
 
-	if (mpc->ctx->dc->debug.enable_mem_low_power.bits.mpc) {
-		// Force power on
-		REG_UPDATE(MPCC_MEM_PWR_CTRL[mpcc_id], MPCC_OGAM_MEM_PWR_DIS, power_on == true ? 1:0);
-		// Wait for confirmation when powering on
-		if (power_on)
-			REG_WAIT(MPCC_MEM_PWR_CTRL[mpcc_id], MPCC_OGAM_MEM_PWR_STATE, 0, 10, 10);
-	} else {
-		REG_SET(MPCC_MEM_PWR_CTRL[mpcc_id], 0,
-				MPCC_OGAM_MEM_PWR_FORCE, power_on == true ? 0 : 1);
-	}
+	/*
+	 * Powering on: force memory active so the LUT can be updated.
+	 * Powering off: allow entering memory low power mode
+	 *
+	 * Memory low power mode is controlled during MPC OGAM LUT init.
+	 */
+	REG_UPDATE(MPCC_MEM_PWR_CTRL[mpcc_id],
+		   MPCC_OGAM_MEM_PWR_DIS, power_on != 0);
+
+	/* Wait for memory to be powered on - we won't be able to write to it otherwise. */
+	if (power_on)
+		REG_WAIT(MPCC_MEM_PWR_CTRL[mpcc_id], MPCC_OGAM_MEM_PWR_STATE, 0, 10, 10);
 }
 
 static void mpc3_configure_ogam_lut(
@@ -1427,7 +1429,7 @@ const struct mpc_funcs dcn30_mpc_funcs = {
 	.acquire_rmu = mpcc3_acquire_rmu,
 	.program_3dlut = mpc3_program_3dlut,
 	.release_rmu = mpcc3_release_rmu,
-	.power_on_mpc_mem_pwr = mpc20_power_on_ogam_lut,
+	.power_on_mpc_mem_pwr = mpc3_power_on_ogam_lut,
 	.get_mpc_out_mux = mpc1_get_mpc_out_mux,
 
 };
-- 
2.30.2

[PATCH AUTOSEL 5.12 007/134] drm/amd/pm: do not issue message while write "r" into pp_od_clk_voltage

[Sasha Levin]

From: Huang Rui <ray.huang@amd.com>

[ Upstream commit ca1203d7d7295c49e5707d7def457bdc524a8edb ]

We should commit the value after restore them back to default as well.

$ echo "r" > pp_od_clk_voltage
$ echo "c" > pp_od_clk_voltage

Signed-off-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c  | 14 -------
 .../gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c  | 38 -------------------
 .../gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c   | 18 ---------
 3 files changed, 70 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c
index ed05a30d1139..e2a56a7f3d7a 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c
@@ -1526,20 +1526,6 @@ static int smu10_set_fine_grain_clk_vol(struct pp_hwmgr *hwmgr,
 
 		smu10_data->gfx_actual_soft_min_freq = min_freq;
 		smu10_data->gfx_actual_soft_max_freq = max_freq;
-
-		ret = smum_send_msg_to_smc_with_parameter(hwmgr,
-					PPSMC_MSG_SetHardMinGfxClk,
-					min_freq,
-					NULL);
-		if (ret)
-			return ret;
-
-		ret = smum_send_msg_to_smc_with_parameter(hwmgr,
-					PPSMC_MSG_SetSoftMaxGfxClk,
-					max_freq,
-					NULL);
-		if (ret)
-			return ret;
 	} else if (type == PP_OD_COMMIT_DPM_TABLE) {
 		if (size != 0) {
 			pr_err("Input parameter number not correct\n");
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
index 101eaa20db9b..a80f551771b9 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
@@ -1462,7 +1462,6 @@ static int vangogh_od_edit_dpm_table(struct smu_context *smu, enum PP_OD_DPM_TAB
 					long input[], uint32_t size)
 {
 	int ret = 0;
-	int i;
 	struct smu_dpm_context *smu_dpm_ctx = &(smu->smu_dpm);
 
 	if (!(smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL)) {
@@ -1535,43 +1534,6 @@ static int vangogh_od_edit_dpm_table(struct smu_context *smu, enum PP_OD_DPM_TAB
 			smu->gfx_actual_soft_max_freq = smu->gfx_default_soft_max_freq;
 			smu->cpu_actual_soft_min_freq = smu->cpu_default_soft_min_freq;
 			smu->cpu_actual_soft_max_freq = smu->cpu_default_soft_max_freq;
-
-			ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetHardMinGfxClk,
-									smu->gfx_actual_hard_min_freq, NULL);
-			if (ret) {
-				dev_err(smu->adev->dev, "Restore the default hard min sclk failed!");
-				return ret;
-			}
-
-			ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetSoftMaxGfxClk,
-									smu->gfx_actual_soft_max_freq, NULL);
-			if (ret) {
-				dev_err(smu->adev->dev, "Restore the default soft max sclk failed!");
-				return ret;
-			}
-
-			if (smu->adev->pm.fw_version < 0x43f1b00) {
-				dev_warn(smu->adev->dev, "CPUSoftMax/CPUSoftMin are not supported, please update SBIOS!\n");
-				break;
-			}
-
-			for (i = 0; i < smu->cpu_core_num; i++) {
-				ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetSoftMinCclk,
-								      (i << 20) | smu->cpu_actual_soft_min_freq,
-								      NULL);
-				if (ret) {
-					dev_err(smu->adev->dev, "Set hard min cclk failed!");
-					return ret;
-				}
-
-				ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetSoftMaxCclk,
-								      (i << 20) | smu->cpu_actual_soft_max_freq,
-								      NULL);
-				if (ret) {
-					dev_err(smu->adev->dev, "Set soft max cclk failed!");
-					return ret;
-				}
-			}
 		}
 		break;
 	case PP_OD_COMMIT_DPM_TABLE:
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
index 5493388fcb10..dbe6d0caddb7 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
@@ -389,24 +389,6 @@ static int renoir_od_edit_dpm_table(struct smu_context *smu,
 		}
 		smu->gfx_actual_hard_min_freq = smu->gfx_default_hard_min_freq;
 		smu->gfx_actual_soft_max_freq = smu->gfx_default_soft_max_freq;
-
-		ret = smu_cmn_send_smc_msg_with_param(smu,
-								SMU_MSG_SetHardMinGfxClk,
-								smu->gfx_actual_hard_min_freq,
-								NULL);
-		if (ret) {
-			dev_err(smu->adev->dev, "Restore the default hard min sclk failed!");
-			return ret;
-		}
-
-		ret = smu_cmn_send_smc_msg_with_param(smu,
-								SMU_MSG_SetSoftMaxGfxClk,
-								smu->gfx_actual_soft_max_freq,
-								NULL);
-		if (ret) {
-			dev_err(smu->adev->dev, "Restore the default soft max sclk failed!");
-			return ret;
-		}
 		break;
 	case PP_OD_COMMIT_DPM_TABLE:
 		if (size != 0) {
-- 
2.30.2

[PATCH AUTOSEL 5.12 008/134] drm/ast: fix memory leak when unload the driver

[Sasha Levin]

From: Tong Zhang <ztong0001@gmail.com>

[ Upstream commit dc739820ff90acccd013f6bb420222978a982791 ]

a connector is leaked upon module unload, it seems that we should do
similar to sample driver as suggested in drm_drv.c.

Adding drm_atomic_helper_shutdown() in ast_pci_remove to prevent leaking.

[  153.822134] WARNING: CPU: 0 PID: 173 at drivers/gpu/drm/drm_mode_config.c:504 drm_mode_config_cle0
[  153.822698] Modules linked in: ast(-) drm_vram_helper drm_ttm_helper ttm [last unloaded: ttm]
[  153.823197] CPU: 0 PID: 173 Comm: modprobe Tainted: G        W         5.11.0-03615-g55f62bc873474
[  153.823708] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-48-gd9c812dda519-4
[  153.824333] RIP: 0010:drm_mode_config_cleanup+0x418/0x470
[  153.824637] Code: 0c 00 00 00 00 48 8b 84 24 a8 00 00 00 65 48 33 04 25 28 00 00 00 75 65 48 81 c0
[  153.825668] RSP: 0018:ffff888103c9fb70 EFLAGS: 00010212
[  153.825962] RAX: ffff888102b0d100 RBX: ffff888102b0c298 RCX: ffffffff818d8b2b
[  153.826356] RDX: dffffc0000000000 RSI: 000000007fffffff RDI: ffff888102b0c298
[  153.826748] RBP: ffff888103c9fba0 R08: 0000000000000001 R09: ffffed1020561857
[  153.827146] R10: ffff888102b0c2b7 R11: ffffed1020561856 R12: ffff888102b0c000
[  153.827538] R13: ffff888102b0c2d8 R14: ffff888102b0c2d8 R15: 1ffff11020793f70
[  153.827935] FS:  00007f24bff456a0(0000) GS:ffff88815b400000(0000) knlGS:0000000000000000
[  153.828380] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  153.828697] CR2: 0000000001c39018 CR3: 0000000103c90000 CR4: 00000000000006f0
[  153.829096] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  153.829486] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[  153.829883] Call Trace:
[  153.830024]  ? drmm_mode_config_init+0x930/0x930
[  153.830281]  ? cpumask_next+0x16/0x20
[  153.830488]  ? mnt_get_count+0x66/0x80
[  153.830699]  ? drm_mode_config_cleanup+0x470/0x470
[  153.830972]  drm_managed_release+0xed/0x1c0
[  153.831208]  drm_dev_release+0x3a/0x50
[  153.831420]  release_nodes+0x39e/0x410
[  153.831631]  ? devres_release+0x40/0x40
[  153.831852]  device_release_driver_internal+0x158/0x270
[  153.832143]  driver_detach+0x76/0xe0
[  153.832344]  bus_remove_driver+0x7e/0x100
[  153.832568]  pci_unregister_driver+0x28/0xf0
[  153.832821]  __x64_sys_delete_module+0x268/0x300
[  153.833086]  ? __ia32_sys_delete_module+0x300/0x300
[  153.833357]  ? call_rcu+0x372/0x4f0
[  153.833553]  ? fpregs_assert_state_consistent+0x4d/0x60
[  153.833840]  ? exit_to_user_mode_prepare+0x2f/0x130
[  153.834118]  do_syscall_64+0x33/0x40
[  153.834317]  entry_SYSCALL_64_after_hwframe+0x44/0xae
[  153.834597] RIP: 0033:0x7f24bfec7cf7
[  153.834797] Code: 48 89 57 30 48 8b 04 24 48 89 47 38 e9 1d a0 02 00 48 89 f8 48 89 f7 48 89 d6 41
[  153.835812] RSP: 002b:00007fff72e6cb58 EFLAGS: 00000202 ORIG_RAX: 00000000000000b0
[  153.836234] RAX: ffffffffffffffda RBX: 00007f24bff45690 RCX: 00007f24bfec7cf7
[  153.836623] RDX: 00000000ffffffff RSI: 0000000000000080 RDI: 0000000001c2fb10
[  153.837018] RBP: 0000000001c2fac0 R08: 2f2f2f2f2f2f2f2f R09: 0000000001c2fac0
[  153.837408] R10: fefefefefefefeff R11: 0000000000000202 R12: 0000000001c2fac0
[  153.837798] R13: 0000000001c2f9d0 R14: 0000000000000000 R15: 0000000000000001
[  153.838194] ---[ end trace b92031513bbe596c ]---
[  153.838441] [drm:drm_mode_config_cleanup] *ERROR* connector VGA-1 leaked!

Signed-off-by: Tong Zhang <ztong0001@gmail.com>
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Link: https://patchwork.freedesktop.org/patch/msgid/20210222023322.984885-1-ztong0001@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/ast/ast_drv.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/ast/ast_drv.c b/drivers/gpu/drm/ast/ast_drv.c
index ea8164e7a6dc..01837bea18c2 100644
--- a/drivers/gpu/drm/ast/ast_drv.c
+++ b/drivers/gpu/drm/ast/ast_drv.c
@@ -30,6 +30,7 @@
 #include <linux/module.h>
 #include <linux/pci.h>
 
+#include <drm/drm_atomic_helper.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_drv.h>
 #include <drm/drm_fb_helper.h>
@@ -138,6 +139,7 @@ static void ast_pci_remove(struct pci_dev *pdev)
 	struct drm_device *dev = pci_get_drvdata(pdev);
 
 	drm_dev_unregister(dev);
+	drm_atomic_helper_shutdown(dev);
 }
 
 static int ast_drm_freeze(struct drm_device *dev)
-- 
2.30.2

[PATCH AUTOSEL 5.12 009/134] drm/amd/display: Check for DSC support instead of ASIC revision

[Sasha Levin]

From: Eryk Brol <eryk.brol@amd.com>

[ Upstream commit 349a19b2f1b01e713268c7de9944ad669ccdf369 ]

[why]
This check for ASIC revision is no longer useful and causes
lightup issues after a topology change in MST DSC scenario.
In this case, DSC configs should be recalculated for the new
topology. This check prevented that from happening on certain
ASICs that do, in fact, support DSC.

[how]
Change the ASIC revision to instead check if DSC is supported.

Signed-off-by: Eryk Brol <eryk.brol@amd.com>
Acked-by: Bindu Ramamurthy <bindu.r@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index d699a5cf6c11..8ad83ccfcc6a 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -9383,7 +9383,7 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 	}
 
 #if defined(CONFIG_DRM_AMD_DC_DCN)
-	if (adev->asic_type >= CHIP_NAVI10) {
+	if (dc_resource_is_dsc_encoding_supported(dc)) {
 		for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
 			if (drm_atomic_crtc_needs_modeset(new_crtc_state)) {
 				ret = add_affected_mst_dsc_crtcs(state, crtc);
-- 
2.30.2

[PATCH AUTOSEL 5.12 010/134] drm/amd/display: Don't optimize bandwidth before disabling planes

[Sasha Levin]

From: Aric Cyr <aric.cyr@amd.com>

[ Upstream commit 6ad98e8aeb0106f453bb154933e8355849244990 ]

[Why]
There is a window of time where we optimize bandwidth due to no streams
enabled will enable PSTATE changing but HUBPs are not disabled yet.
This results in underflow counter increasing in some hotplug scenarios.

[How]
Set the optimize-bandwidth flag for later processing once all the HUBPs
are properly disabled.

Signed-off-by: Aric Cyr <aric.cyr@amd.com>
Acked-by: Bindu Ramamurthy <bindu.r@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/amd/display/dc/core/dc.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 8f8a13c7cf73..c0b827d16268 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -2398,7 +2398,8 @@ static void commit_planes_do_stream_update(struct dc *dc,
 					if (pipe_ctx->stream_res.audio && !dc->debug.az_endpoint_mute_only)
 						pipe_ctx->stream_res.audio->funcs->az_disable(pipe_ctx->stream_res.audio);
 
-					dc->hwss.optimize_bandwidth(dc, dc->current_state);
+					dc->optimized_required = true;
+
 				} else {
 					if (dc->optimize_seamless_boot_streams == 0)
 						dc->hwss.prepare_bandwidth(dc, dc->current_state);
-- 
2.30.2

[PATCH AUTOSEL 5.12 011/134] drm/amd/display: Return invalid state if GPINT times out

[Sasha Levin]

From: Wyatt Wood <wyatt.wood@amd.com>

[ Upstream commit 8039bc7130ef4206a58e4dc288621bc97eba08eb ]

[Why]
GPINT timeout is causing PSR_STATE_0 to be returned when it shouldn't.
We must guarantee that PSR is fully disabled before doing hw programming
on driver-side.

[How]
Return invalid state if GPINT command times out. Let existing retry
logic send the GPINT until successful.

Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Wyatt Wood <wyatt.wood@amd.com>
Reviewed-by: Anthony Koo <Anthony.Koo@amd.com>
Acked-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c
index 69e34bef274c..febccb35ddad 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c
@@ -81,13 +81,18 @@ static void dmub_psr_get_state(struct dmub_psr *dmub, enum dc_psr_state *state)
 {
 	struct dmub_srv *srv = dmub->ctx->dmub_srv->dmub;
 	uint32_t raw_state;
+	enum dmub_status status = DMUB_STATUS_INVALID;
 
 	// Send gpint command and wait for ack
-	dmub_srv_send_gpint_command(srv, DMUB_GPINT__GET_PSR_STATE, 0, 30);
-
-	dmub_srv_get_gpint_response(srv, &raw_state);
-
-	*state = convert_psr_state(raw_state);
+	status = dmub_srv_send_gpint_command(srv, DMUB_GPINT__GET_PSR_STATE, 0, 30);
+
+	if (status == DMUB_STATUS_OK) {
+		// GPINT was executed, get response
+		dmub_srv_get_gpint_response(srv, &raw_state);
+		*state = convert_psr_state(raw_state);
+	} else
+		// Return invalid state when GPINT times out
+		*state = 0xFF;
 }
 
 /*
-- 
2.30.2

[PATCH AUTOSEL 5.12 012/134] drm/amdgpu/display: buffer INTERRUPT_LOW_IRQ_CONTEXT interrupt work

[Sasha Levin]

From: Xiaogang Chen <xiaogang.chen@amd.com>

[ Upstream commit b6f91fc183f758461b9462cc93e673adbbf95c2d ]

amdgpu DM handles INTERRUPT_LOW_IRQ_CONTEXT interrupt(hpd, hpd_rx) by using work
queue and uses single work_struct. If new interrupt is recevied before the
previous handler finished, new interrupts(same type) will be discarded and
driver just sends "amdgpu_dm_irq_schedule_work FAILED" message out. If some
important hpd, hpd_rx related interrupts are missed by driver the hot (un)plug
devices may cause system hang or instability, such as issues with system
resume from S3 sleep with mst device connected.

This patch dynamically allocates new amdgpu_dm_irq_handler_data for new
interrupts if previous INTERRUPT_LOW_IRQ_CONTEXT interrupt work has not been
handled. So the new interrupt works can be queued to the same workqueue_struct,
instead of discard the new interrupts. All allocated amdgpu_dm_irq_handler_data
are put into a single linked list and will be reused after.

Signed-off-by: Xiaogang Chen <xiaogang.chen@amd.com>
Reviewed-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h |  14 +--
 .../drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c | 115 ++++++++++++------
 2 files changed, 80 insertions(+), 49 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index 8bfe901cf237..52cc81705280 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -68,18 +68,6 @@ struct common_irq_params {
 	enum dc_irq_source irq_src;
 };
 
-/**
- * struct irq_list_head - Linked-list for low context IRQ handlers.
- *
- * @head: The list_head within &struct handler_data
- * @work: A work_struct containing the deferred handler work
- */
-struct irq_list_head {
-	struct list_head head;
-	/* In case this interrupt needs post-processing, 'work' will be queued*/
-	struct work_struct work;
-};
-
 /**
  * struct dm_compressor_info - Buffer info used by frame buffer compression
  * @cpu_addr: MMIO cpu addr
@@ -293,7 +281,7 @@ struct amdgpu_display_manager {
 	 * Note that handlers are called in the same order as they were
 	 * registered (FIFO).
 	 */
-	struct irq_list_head irq_handler_list_low_tab[DAL_IRQ_SOURCES_NUMBER];
+	struct list_head irq_handler_list_low_tab[DAL_IRQ_SOURCES_NUMBER];
 
 	/**
 	 * @irq_handler_list_high_tab:
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
index e0000c180ed1..8ce10d0973c5 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
@@ -82,6 +82,7 @@ struct amdgpu_dm_irq_handler_data {
 	struct amdgpu_display_manager *dm;
 	/* DAL irq source which registered for this interrupt. */
 	enum dc_irq_source irq_source;
+	struct work_struct work;
 };
 
 #define DM_IRQ_TABLE_LOCK(adev, flags) \
@@ -111,20 +112,10 @@ static void init_handler_common_data(struct amdgpu_dm_irq_handler_data *hcd,
  */
 static void dm_irq_work_func(struct work_struct *work)
 {
-	struct irq_list_head *irq_list_head =
-		container_of(work, struct irq_list_head, work);
-	struct list_head *handler_list = &irq_list_head->head;
-	struct amdgpu_dm_irq_handler_data *handler_data;
-
-	list_for_each_entry(handler_data, handler_list, list) {
-		DRM_DEBUG_KMS("DM_IRQ: work_func: for dal_src=%d\n",
-				handler_data->irq_source);
+	struct amdgpu_dm_irq_handler_data *handler_data =
+		container_of(work, struct amdgpu_dm_irq_handler_data, work);
 
-		DRM_DEBUG_KMS("DM_IRQ: schedule_work: for dal_src=%d\n",
-			handler_data->irq_source);
-
-		handler_data->handler(handler_data->handler_arg);
-	}
+	handler_data->handler(handler_data->handler_arg);
 
 	/* Call a DAL subcomponent which registered for interrupt notification
 	 * at INTERRUPT_LOW_IRQ_CONTEXT.
@@ -156,7 +147,7 @@ static struct list_head *remove_irq_handler(struct amdgpu_device *adev,
 		break;
 	case INTERRUPT_LOW_IRQ_CONTEXT:
 	default:
-		hnd_list = &adev->dm.irq_handler_list_low_tab[irq_source].head;
+		hnd_list = &adev->dm.irq_handler_list_low_tab[irq_source];
 		break;
 	}
 
@@ -290,7 +281,8 @@ void *amdgpu_dm_irq_register_interrupt(struct amdgpu_device *adev,
 		break;
 	case INTERRUPT_LOW_IRQ_CONTEXT:
 	default:
-		hnd_list = &adev->dm.irq_handler_list_low_tab[irq_source].head;
+		hnd_list = &adev->dm.irq_handler_list_low_tab[irq_source];
+		INIT_WORK(&handler_data->work, dm_irq_work_func);
 		break;
 	}
 
@@ -372,7 +364,7 @@ void amdgpu_dm_irq_unregister_interrupt(struct amdgpu_device *adev,
 int amdgpu_dm_irq_init(struct amdgpu_device *adev)
 {
 	int src;
-	struct irq_list_head *lh;
+	struct list_head *lh;
 
 	DRM_DEBUG_KMS("DM_IRQ\n");
 
@@ -381,9 +373,7 @@ int amdgpu_dm_irq_init(struct amdgpu_device *adev)
 	for (src = 0; src < DAL_IRQ_SOURCES_NUMBER; src++) {
 		/* low context handler list init */
 		lh = &adev->dm.irq_handler_list_low_tab[src];
-		INIT_LIST_HEAD(&lh->head);
-		INIT_WORK(&lh->work, dm_irq_work_func);
-
+		INIT_LIST_HEAD(lh);
 		/* high context handler init */
 		INIT_LIST_HEAD(&adev->dm.irq_handler_list_high_tab[src]);
 	}
@@ -400,8 +390,11 @@ int amdgpu_dm_irq_init(struct amdgpu_device *adev)
 void amdgpu_dm_irq_fini(struct amdgpu_device *adev)
 {
 	int src;
-	struct irq_list_head *lh;
+	struct list_head *lh;
+	struct list_head *entry, *tmp;
+	struct amdgpu_dm_irq_handler_data *handler;
 	unsigned long irq_table_flags;
+
 	DRM_DEBUG_KMS("DM_IRQ: releasing resources.\n");
 	for (src = 0; src < DAL_IRQ_SOURCES_NUMBER; src++) {
 		DM_IRQ_TABLE_LOCK(adev, irq_table_flags);
@@ -410,7 +403,16 @@ void amdgpu_dm_irq_fini(struct amdgpu_device *adev)
 		 * (because no code can schedule a new one). */
 		lh = &adev->dm.irq_handler_list_low_tab[src];
 		DM_IRQ_TABLE_UNLOCK(adev, irq_table_flags);
-		flush_work(&lh->work);
+
+		if (!list_empty(lh)) {
+			list_for_each_safe(entry, tmp, lh) {
+				handler = list_entry(
+					entry,
+					struct amdgpu_dm_irq_handler_data,
+					list);
+				flush_work(&handler->work);
+			}
+		}
 	}
 }
 
@@ -420,6 +422,8 @@ int amdgpu_dm_irq_suspend(struct amdgpu_device *adev)
 	struct list_head *hnd_list_h;
 	struct list_head *hnd_list_l;
 	unsigned long irq_table_flags;
+	struct list_head *entry, *tmp;
+	struct amdgpu_dm_irq_handler_data *handler;
 
 	DM_IRQ_TABLE_LOCK(adev, irq_table_flags);
 
@@ -430,14 +434,22 @@ int amdgpu_dm_irq_suspend(struct amdgpu_device *adev)
 	 * will be disabled from manage_dm_interrupts on disable CRTC.
 	 */
 	for (src = DC_IRQ_SOURCE_HPD1; src <= DC_IRQ_SOURCE_HPD6RX; src++) {
-		hnd_list_l = &adev->dm.irq_handler_list_low_tab[src].head;
+		hnd_list_l = &adev->dm.irq_handler_list_low_tab[src];
 		hnd_list_h = &adev->dm.irq_handler_list_high_tab[src];
 		if (!list_empty(hnd_list_l) || !list_empty(hnd_list_h))
 			dc_interrupt_set(adev->dm.dc, src, false);
 
 		DM_IRQ_TABLE_UNLOCK(adev, irq_table_flags);
-		flush_work(&adev->dm.irq_handler_list_low_tab[src].work);
 
+		if (!list_empty(hnd_list_l)) {
+			list_for_each_safe (entry, tmp, hnd_list_l) {
+				handler = list_entry(
+					entry,
+					struct amdgpu_dm_irq_handler_data,
+					list);
+				flush_work(&handler->work);
+			}
+		}
 		DM_IRQ_TABLE_LOCK(adev, irq_table_flags);
 	}
 
@@ -457,7 +469,7 @@ int amdgpu_dm_irq_resume_early(struct amdgpu_device *adev)
 
 	/* re-enable short pulse interrupts HW interrupt */
 	for (src = DC_IRQ_SOURCE_HPD1RX; src <= DC_IRQ_SOURCE_HPD6RX; src++) {
-		hnd_list_l = &adev->dm.irq_handler_list_low_tab[src].head;
+		hnd_list_l = &adev->dm.irq_handler_list_low_tab[src];
 		hnd_list_h = &adev->dm.irq_handler_list_high_tab[src];
 		if (!list_empty(hnd_list_l) || !list_empty(hnd_list_h))
 			dc_interrupt_set(adev->dm.dc, src, true);
@@ -483,7 +495,7 @@ int amdgpu_dm_irq_resume_late(struct amdgpu_device *adev)
 	 * will be enabled from manage_dm_interrupts on enable CRTC.
 	 */
 	for (src = DC_IRQ_SOURCE_HPD1; src <= DC_IRQ_SOURCE_HPD6; src++) {
-		hnd_list_l = &adev->dm.irq_handler_list_low_tab[src].head;
+		hnd_list_l = &adev->dm.irq_handler_list_low_tab[src];
 		hnd_list_h = &adev->dm.irq_handler_list_high_tab[src];
 		if (!list_empty(hnd_list_l) || !list_empty(hnd_list_h))
 			dc_interrupt_set(adev->dm.dc, src, true);
@@ -500,22 +512,53 @@ int amdgpu_dm_irq_resume_late(struct amdgpu_device *adev)
 static void amdgpu_dm_irq_schedule_work(struct amdgpu_device *adev,
 					enum dc_irq_source irq_source)
 {
-	unsigned long irq_table_flags;
-	struct work_struct *work = NULL;
+	struct  list_head *handler_list = &adev->dm.irq_handler_list_low_tab[irq_source];
+	struct  amdgpu_dm_irq_handler_data *handler_data;
+	bool    work_queued = false;
 
-	DM_IRQ_TABLE_LOCK(adev, irq_table_flags);
+	if (list_empty(handler_list))
+		return;
+
+	list_for_each_entry (handler_data, handler_list, list) {
+		if (!queue_work(system_highpri_wq, &handler_data->work)) {
+			continue;
+		} else {
+			work_queued = true;
+			break;
+		}
+	}
 
-	if (!list_empty(&adev->dm.irq_handler_list_low_tab[irq_source].head))
-		work = &adev->dm.irq_handler_list_low_tab[irq_source].work;
+	if (!work_queued) {
+		struct  amdgpu_dm_irq_handler_data *handler_data_add;
+		/*get the amdgpu_dm_irq_handler_data of first item pointed by handler_list*/
+		handler_data = container_of(handler_list->next, struct amdgpu_dm_irq_handler_data, list);
 
-	DM_IRQ_TABLE_UNLOCK(adev, irq_table_flags);
+		/*allocate a new amdgpu_dm_irq_handler_data*/
+		handler_data_add = kzalloc(sizeof(*handler_data), GFP_KERNEL);
+		if (!handler_data_add) {
+			DRM_ERROR("DM_IRQ: failed to allocate irq handler!\n");
+			return;
+		}
 
-	if (work) {
-		if (!schedule_work(work))
-			DRM_INFO("amdgpu_dm_irq_schedule_work FAILED src %d\n",
-						irq_source);
-	}
+		/*copy new amdgpu_dm_irq_handler_data members from handler_data*/
+		handler_data_add->handler       = handler_data->handler;
+		handler_data_add->handler_arg   = handler_data->handler_arg;
+		handler_data_add->dm            = handler_data->dm;
+		handler_data_add->irq_source    = irq_source;
 
+		list_add_tail(&handler_data_add->list, handler_list);
+
+		INIT_WORK(&handler_data_add->work, dm_irq_work_func);
+
+		if (queue_work(system_highpri_wq, &handler_data_add->work))
+			DRM_DEBUG("Queued work for handling interrupt from "
+				  "display for IRQ source %d\n",
+				  irq_source);
+		else
+			DRM_ERROR("Failed to queue work for handling interrupt "
+				  "from display for IRQ source %d\n",
+				  irq_source);
+	}
 }
 
 /*
-- 
2.30.2

[PATCH AUTOSEL 5.12 013/134] drm/amd/display/dc/dce/dce_aux: Remove duplicate line causing 'field overwritten' issue

[Sasha Levin]

From: Lee Jones <lee.jones@linaro.org>

[ Upstream commit 3e3527f5b765c6f479ba55e5a570ee9538589a74 ]

Fixes the following W=1 kernel build warning(s):

 In file included from drivers/gpu/drm/amd/amdgpu/../display/dc/dce112/dce112_resource.c:59:
 drivers/gpu/drm/amd/amdgpu/../include/asic_reg/dce/dce_11_2_sh_mask.h:10014:58: warning: initialized field overwritten [-Woverride-init]
 drivers/gpu/drm/amd/amdgpu/../display/dc/dce/dce_aux.h:214:16: note: in expansion of macro ‘AUX_SW_DATA__AUX_SW_AUTOINCREMENT_DISABLE__SHIFT’
 drivers/gpu/drm/amd/amdgpu/../display/dc/dce/dce_aux.h:127:2: note: in expansion of macro ‘AUX_SF’
 drivers/gpu/drm/amd/amdgpu/../display/dc/dce112/dce112_resource.c:177:2: note: in expansion of macro ‘DCE_AUX_MASK_SH_LIST’
 drivers/gpu/drm/amd/amdgpu/../include/asic_reg/dce/dce_11_2_sh_mask.h:10014:58: note: (near initialization for ‘aux_shift.AUX_SW_AUTOINCREMENT_DISABLE’)
 drivers/gpu/drm/amd/amdgpu/../display/dc/dce/dce_aux.h:214:16: note: in expansion of macro ‘AUX_SW_DATA__AUX_SW_AUTOINCREMENT_DISABLE__SHIFT’
 drivers/gpu/drm/amd/amdgpu/../display/dc/dce/dce_aux.h:127:2: note: in expansion of macro ‘AUX_SF’
 drivers/gpu/drm/amd/amdgpu/../display/dc/dce112/dce112_resource.c:177:2: note: in expansion of macro ‘DCE_AUX_MASK_SH_LIST’
 drivers/gpu/drm/amd/amdgpu/../include/asic_reg/dce/dce_11_2_sh_mask.h:10013:56: warning: initialized field overwritten [-Woverride-init]
 drivers/gpu/drm/amd/amdgpu/../display/dc/dce/dce_aux.h:214:16: note: in expansion of macro ‘AUX_SW_DATA__AUX_SW_AUTOINCREMENT_DISABLE_MASK’
 drivers/gpu/drm/amd/amdgpu/../display/dc/dce/dce_aux.h:127:2: note: in expansion of macro ‘AUX_SF’
 drivers/gpu/drm/amd/amdgpu/../display/dc/dce112/dce112_resource.c:181:2: note: in expansion of macro ‘DCE_AUX_MASK_SH_LIST’
 drivers/gpu/drm/amd/amdgpu/../include/asic_reg/dce/dce_11_2_sh_mask.h:10013:56: note: (near initialization for ‘aux_mask.AUX_SW_AUTOINCREMENT_DISABLE’)
 drivers/gpu/drm/amd/amdgpu/../display/dc/dce/dce_aux.h:214:16: note: in expansion of macro ‘AUX_SW_DATA__AUX_SW_AUTOINCREMENT_DISABLE_MASK’
 drivers/gpu/drm/amd/amdgpu/../display/dc/dce/dce_aux.h:127:2: note: in expansion of macro ‘AUX_SF’

Cc: Harry Wentland <harry.wentland@amd.com>
Cc: Leo Li <sunpeng.li@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: "Christian König" <christian.koenig@amd.com>
Cc: David Airlie <airlied@linux.ie>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: amd-gfx@lists.freedesktop.org
Cc: dri-devel@lists.freedesktop.org
Signed-off-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/amd/display/dc/dce/dce_aux.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h
index 277484cf853e..d4be5954d7aa 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h
@@ -99,7 +99,6 @@ struct dce110_aux_registers {
 	AUX_SF(AUX_SW_CONTROL, AUX_SW_GO, mask_sh),\
 	AUX_SF(AUX_SW_DATA, AUX_SW_AUTOINCREMENT_DISABLE, mask_sh),\
 	AUX_SF(AUX_SW_DATA, AUX_SW_DATA_RW, mask_sh),\
-	AUX_SF(AUX_SW_DATA, AUX_SW_AUTOINCREMENT_DISABLE, mask_sh),\
 	AUX_SF(AUX_SW_DATA, AUX_SW_INDEX, mask_sh),\
 	AUX_SF(AUX_SW_DATA, AUX_SW_DATA, mask_sh),\
 	AUX_SF(AUX_SW_STATUS, AUX_SW_REPLY_BYTE_COUNT, mask_sh),\
-- 
2.30.2

[PATCH AUTOSEL 5.12 014/134] scsi: lpfc: Fix incorrect dbde assignment when building target abts wqe

[Sasha Levin]

From: James Smart <jsmart2021@gmail.com>

[ Upstream commit 9302154c07bff4e7f7f43c506a1ac84540303d06 ]

The wqe_dbde field indicates whether a Data BDE is present in Words 0:2 and
should therefore should be clear in the abts request wqe. By setting the
bit we can be misleading fw into error cases.

Clear the wqe_dbde field.

Link: https://lore.kernel.org/r/20210301171821.3427-2-jsmart2021@gmail.com
Co-developed-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/lpfc/lpfc_nvmet.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c
index bb2a4a0d1295..a3fd959f7431 100644
--- a/drivers/scsi/lpfc/lpfc_nvmet.c
+++ b/drivers/scsi/lpfc/lpfc_nvmet.c
@@ -3304,7 +3304,6 @@ lpfc_nvmet_unsol_issue_abort(struct lpfc_hba *phba,
 	bf_set(wqe_rcvoxid, &wqe_abts->xmit_sequence.wqe_com, xri);
 
 	/* Word 10 */
-	bf_set(wqe_dbde, &wqe_abts->xmit_sequence.wqe_com, 1);
 	bf_set(wqe_iod, &wqe_abts->xmit_sequence.wqe_com, LPFC_WQE_IOD_WRITE);
 	bf_set(wqe_lenloc, &wqe_abts->xmit_sequence.wqe_com,
 	       LPFC_WQE_LENLOC_WORD12);
-- 
2.30.2

[PATCH AUTOSEL 5.12 015/134] scsi: lpfc: Fix pt2pt connection does not recover after LOGO

[Sasha Levin]

From: James Smart <jsmart2021@gmail.com>

[ Upstream commit bd4f5100424d17d4e560d6653902ef8e49b2fc1f ]

On a pt2pt setup, between 2 initiators, if one side issues a a LOGO, there
is no relogin attempt. The FC specs are grey in this area on which port
(higher wwn or not) is to re-login.

As there is no spec guidance, unconditionally re-PLOGI after the logout to
ensure a login is re-established.

Link: https://lore.kernel.org/r/20210301171821.3427-8-jsmart2021@gmail.com
Co-developed-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/lpfc/lpfc_nportdisc.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c
index 135d8e8a42ba..4918423960d6 100644
--- a/drivers/scsi/lpfc/lpfc_nportdisc.c
+++ b/drivers/scsi/lpfc/lpfc_nportdisc.c
@@ -913,9 +913,14 @@ lpfc_rcv_logo(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		}
 	} else if ((!(ndlp->nlp_type & NLP_FABRIC) &&
 		((ndlp->nlp_type & NLP_FCP_TARGET) ||
-		!(ndlp->nlp_type & NLP_FCP_INITIATOR))) ||
+		(ndlp->nlp_type & NLP_NVME_TARGET) ||
+		(vport->fc_flag & FC_PT2PT))) ||
 		(ndlp->nlp_state == NLP_STE_ADISC_ISSUE)) {
-		/* Only try to re-login if this is NOT a Fabric Node */
+		/* Only try to re-login if this is NOT a Fabric Node
+		 * AND the remote NPORT is a FCP/NVME Target or we
+		 * are in pt2pt mode. NLP_STE_ADISC_ISSUE is a special
+		 * case for LOGO as a response to ADISC behavior.
+		 */
 		mod_timer(&ndlp->nlp_delayfunc,
 			  jiffies + msecs_to_jiffies(1000 * 1));
 		spin_lock_irq(&ndlp->lock);
-- 
2.30.2

[PATCH AUTOSEL 5.12 016/134] scsi: lpfc: Fix status returned in lpfc_els_retry() error exit path

[Sasha Levin]

From: James Smart <jsmart2021@gmail.com>

[ Upstream commit 148bc64d38fe314475a074c4f757ec9d84537d1c ]

An unlikely error exit path from lpfc_els_retry() returns incorrect status
to a caller, erroneously indicating that a retry has been successfully
issued or scheduled.

Change error exit path to indicate no retry.

Link: https://lore.kernel.org/r/20210301171821.3427-12-jsmart2021@gmail.com
Co-developed-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/lpfc/lpfc_els.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index f0a758138ae8..beb2fcd2d8e7 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -3829,7 +3829,7 @@ lpfc_els_retry(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		did = irsp->un.elsreq64.remoteID;
 		ndlp = lpfc_findnode_did(vport, did);
 		if (!ndlp && (cmd != ELS_CMD_PLOGI))
-			return 1;
+			return 0;
 	}
 
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_CMD,
-- 
2.30.2

[PATCH AUTOSEL 5.12 017/134] scsi: lpfc: Fix PLOGI ACC to be transmit after REG_LOGIN

[Sasha Levin]

From: James Smart <jsmart2021@gmail.com>

[ Upstream commit 143753059b8b957f1cf4355338a3e3a32f3a85bf ]

The driver is seeing a scenario where PLOGI response was issued and traffic
is arriving while the adapter is still setting up the login context. This
is resulting in errors handling the traffic.

Change the driver so that PLOGI response is sent after the login context
has been setup to avoid the situation.

Link: https://lore.kernel.org/r/20210301171821.3427-14-jsmart2021@gmail.com
Co-developed-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/lpfc/lpfc_nportdisc.c | 239 +++++++++--------------------
 1 file changed, 70 insertions(+), 169 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c
index 4918423960d6..f32e5743e30c 100644
--- a/drivers/scsi/lpfc/lpfc_nportdisc.c
+++ b/drivers/scsi/lpfc/lpfc_nportdisc.c
@@ -279,106 +279,43 @@ lpfc_els_abort(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp)
 	lpfc_cancel_retry_delay_tmo(phba->pport, ndlp);
 }
 
-/* lpfc_defer_pt2pt_acc - Complete SLI3 pt2pt processing on link up
+/* lpfc_defer_plogi_acc - Issue PLOGI ACC after reg_login completes
  * @phba: pointer to lpfc hba data structure.
- * @link_mbox: pointer to CONFIG_LINK mailbox object
+ * @login_mbox: pointer to REG_RPI mailbox object
  *
- * This routine is only called if we are SLI3, direct connect pt2pt
- * mode and the remote NPort issues the PLOGI after link up.
+ * The ACC for a rcv'ed PLOGI is deferred until AFTER the REG_RPI completes
  */
 static void
-lpfc_defer_pt2pt_acc(struct lpfc_hba *phba, LPFC_MBOXQ_t *link_mbox)
+lpfc_defer_plogi_acc(struct lpfc_hba *phba, LPFC_MBOXQ_t *login_mbox)
 {
-	LPFC_MBOXQ_t *login_mbox;
-	MAILBOX_t *mb = &link_mbox->u.mb;
 	struct lpfc_iocbq *save_iocb;
 	struct lpfc_nodelist *ndlp;
+	MAILBOX_t *mb = &login_mbox->u.mb;
+
 	int rc;
 
-	ndlp = link_mbox->ctx_ndlp;
-	login_mbox = link_mbox->context3;
+	ndlp = login_mbox->ctx_ndlp;
 	save_iocb = login_mbox->context3;
-	link_mbox->context3 = NULL;
-	login_mbox->context3 = NULL;
-
-	/* Check for CONFIG_LINK error */
-	if (mb->mbxStatus) {
-		lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT,
-				"4575 CONFIG_LINK fails pt2pt discovery: %x\n",
-				mb->mbxStatus);
-		mempool_free(login_mbox, phba->mbox_mem_pool);
-		mempool_free(link_mbox, phba->mbox_mem_pool);
-		kfree(save_iocb);
-		return;
-	}
 
-	/* Now that CONFIG_LINK completed, and our SID is configured,
-	 * we can now proceed with sending the PLOGI ACC.
-	 */
-	rc = lpfc_els_rsp_acc(link_mbox->vport, ELS_CMD_PLOGI,
-			      save_iocb, ndlp, login_mbox);
-	if (rc) {
-		lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT,
-				"4576 PLOGI ACC fails pt2pt discovery: %x\n",
-				rc);
-		mempool_free(login_mbox, phba->mbox_mem_pool);
+	if (mb->mbxStatus == MBX_SUCCESS) {
+		/* Now that REG_RPI completed successfully,
+		 * we can now proceed with sending the PLOGI ACC.
+		 */
+		rc = lpfc_els_rsp_acc(login_mbox->vport, ELS_CMD_PLOGI,
+				      save_iocb, ndlp, NULL);
+		if (rc) {
+			lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT,
+					"4576 PLOGI ACC fails pt2pt discovery: "
+					"DID %x Data: %x\n", ndlp->nlp_DID, rc);
+		}
 	}
 
-	mempool_free(link_mbox, phba->mbox_mem_pool);
+	/* Now process the REG_RPI cmpl */
+	lpfc_mbx_cmpl_reg_login(phba, login_mbox);
+	ndlp->nlp_flag &= ~NLP_ACC_REGLOGIN;
 	kfree(save_iocb);
 }
 
-/**
- * lpfc_defer_tgt_acc - Progress SLI4 target rcv PLOGI handler
- * @phba: Pointer to HBA context object.
- * @pmb: Pointer to mailbox object.
- *
- * This function provides the unreg rpi mailbox completion handler for a tgt.
- * The routine frees the memory resources associated with the completed
- * mailbox command and transmits the ELS ACC.
- *
- * This routine is only called if we are SLI4, acting in target
- * mode and the remote NPort issues the PLOGI after link up.
- **/
-static void
-lpfc_defer_acc_rsp(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
-{
-	struct lpfc_vport *vport = pmb->vport;
-	struct lpfc_nodelist *ndlp = pmb->ctx_ndlp;
-	LPFC_MBOXQ_t *mbox = pmb->context3;
-	struct lpfc_iocbq *piocb = NULL;
-	int rc;
-
-	if (mbox) {
-		pmb->context3 = NULL;
-		piocb = mbox->context3;
-		mbox->context3 = NULL;
-	}
-
-	/*
-	 * Complete the unreg rpi mbx request, and update flags.
-	 * This will also restart any deferred events.
-	 */
-	lpfc_sli4_unreg_rpi_cmpl_clr(phba, pmb);
-
-	if (!piocb) {
-		lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT,
-				 "4578 PLOGI ACC fail\n");
-		if (mbox)
-			mempool_free(mbox, phba->mbox_mem_pool);
-		return;
-	}
-
-	rc = lpfc_els_rsp_acc(vport, ELS_CMD_PLOGI, piocb, ndlp, mbox);
-	if (rc) {
-		lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT,
-				 "4579 PLOGI ACC fail %x\n", rc);
-		if (mbox)
-			mempool_free(mbox, phba->mbox_mem_pool);
-	}
-	kfree(piocb);
-}
-
 static int
 lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	       struct lpfc_iocbq *cmdiocb)
@@ -395,8 +332,7 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	struct lpfc_iocbq *save_iocb;
 	struct ls_rjt stat;
 	uint32_t vid, flag;
-	u16 rpi;
-	int rc, defer_acc;
+	int rc;
 
 	memset(&stat, 0, sizeof (struct ls_rjt));
 	pcmd = (struct lpfc_dmabuf *) cmdiocb->context2;
@@ -445,7 +381,6 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	else
 		ndlp->nlp_fcp_info |= CLASS3;
 
-	defer_acc = 0;
 	ndlp->nlp_class_sup = 0;
 	if (sp->cls1.classValid)
 		ndlp->nlp_class_sup |= FC_COS_CLASS1;
@@ -539,27 +474,26 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 
 		memcpy(&phba->fc_fabparam, sp, sizeof(struct serv_parm));
 
-		/* Issue config_link / reg_vfi to account for updated TOV's */
-
+		/* Issue CONFIG_LINK for SLI3 or REG_VFI for SLI4,
+		 * to account for updated TOV's / parameters
+		 */
 		if (phba->sli_rev == LPFC_SLI_REV4)
 			lpfc_issue_reg_vfi(vport);
 		else {
-			defer_acc = 1;
 			link_mbox = mempool_alloc(phba->mbox_mem_pool,
 						  GFP_KERNEL);
 			if (!link_mbox)
 				goto out;
 			lpfc_config_link(phba, link_mbox);
-			link_mbox->mbox_cmpl = lpfc_defer_pt2pt_acc;
+			link_mbox->mbox_cmpl = lpfc_sli_def_mbox_cmpl;
 			link_mbox->vport = vport;
 			link_mbox->ctx_ndlp = ndlp;
 
-			save_iocb = kzalloc(sizeof(*save_iocb), GFP_KERNEL);
-			if (!save_iocb)
+			rc = lpfc_sli_issue_mbox(phba, link_mbox, MBX_NOWAIT);
+			if (rc == MBX_NOT_FINISHED) {
+				mempool_free(link_mbox, phba->mbox_mem_pool);
 				goto out;
-			/* Save info from cmd IOCB used in rsp */
-			memcpy((uint8_t *)save_iocb, (uint8_t *)cmdiocb,
-			       sizeof(struct lpfc_iocbq));
+			}
 		}
 
 		lpfc_can_disctmo(vport);
@@ -578,59 +512,28 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	if (!login_mbox)
 		goto out;
 
-	/* Registering an existing RPI behaves differently for SLI3 vs SLI4 */
-	if (phba->nvmet_support && !defer_acc) {
-		link_mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
-		if (!link_mbox)
-			goto out;
-
-		/* As unique identifiers such as iotag would be overwritten
-		 * with those from the cmdiocb, allocate separate temporary
-		 * storage for the copy.
-		 */
-		save_iocb = kzalloc(sizeof(*save_iocb), GFP_KERNEL);
-		if (!save_iocb)
-			goto out;
-
-		/* Unreg RPI is required for SLI4. */
-		rpi = phba->sli4_hba.rpi_ids[ndlp->nlp_rpi];
-		lpfc_unreg_login(phba, vport->vpi, rpi, link_mbox);
-		link_mbox->vport = vport;
-		link_mbox->ctx_ndlp = lpfc_nlp_get(ndlp);
-		if (!link_mbox->ctx_ndlp)
-			goto out;
-
-		link_mbox->mbox_cmpl = lpfc_defer_acc_rsp;
-
-		if (((ndlp->nlp_DID & Fabric_DID_MASK) != Fabric_DID_MASK) &&
-		    (!(vport->fc_flag & FC_OFFLINE_MODE)))
-			ndlp->nlp_flag |= NLP_UNREG_INP;
+	save_iocb = kzalloc(sizeof(*save_iocb), GFP_KERNEL);
+	if (!save_iocb)
+		goto out;
 
-		/* Save info from cmd IOCB used in rsp */
-		memcpy(save_iocb, cmdiocb, sizeof(*save_iocb));
+	/* Save info from cmd IOCB to be used in rsp after all mbox completes */
+	memcpy((uint8_t *)save_iocb, (uint8_t *)cmdiocb,
+	       sizeof(struct lpfc_iocbq));
 
-		/* Delay sending ACC till unreg RPI completes. */
-		defer_acc = 1;
-	} else if (phba->sli_rev == LPFC_SLI_REV4)
+	/* Registering an existing RPI behaves differently for SLI3 vs SLI4 */
+	if (phba->sli_rev == LPFC_SLI_REV4)
 		lpfc_unreg_rpi(vport, ndlp);
 
+	/* Issue REG_LOGIN first, before ACCing the PLOGI, thus we will
+	 * always be deferring the ACC.
+	 */
 	rc = lpfc_reg_rpi(phba, vport->vpi, icmd->un.rcvels.remoteID,
 			    (uint8_t *)sp, login_mbox, ndlp->nlp_rpi);
 	if (rc)
 		goto out;
 
-	/* ACC PLOGI rsp command needs to execute first,
-	 * queue this login_mbox command to be processed later.
-	 */
 	login_mbox->mbox_cmpl = lpfc_mbx_cmpl_reg_login;
-	/*
-	 * login_mbox->ctx_ndlp = lpfc_nlp_get(ndlp) deferred until mailbox
-	 * command issued in lpfc_cmpl_els_acc().
-	 */
 	login_mbox->vport = vport;
-	spin_lock_irq(&ndlp->lock);
-	ndlp->nlp_flag |= (NLP_ACC_REGLOGIN | NLP_RCV_PLOGI);
-	spin_unlock_irq(&ndlp->lock);
 
 	/*
 	 * If there is an outstanding PLOGI issued, abort it before
@@ -660,7 +563,8 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		 * to register, then unregister the RPI.
 		 */
 		spin_lock_irq(&ndlp->lock);
-		ndlp->nlp_flag |= NLP_RM_DFLT_RPI;
+		ndlp->nlp_flag |= (NLP_RM_DFLT_RPI | NLP_ACC_REGLOGIN |
+				   NLP_RCV_PLOGI);
 		spin_unlock_irq(&ndlp->lock);
 		stat.un.b.lsRjtRsnCode = LSRJT_INVALID_CMD;
 		stat.un.b.lsRjtRsnCodeExp = LSEXP_NOTHING_MORE;
@@ -670,42 +574,39 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 			mempool_free(login_mbox, phba->mbox_mem_pool);
 		return 1;
 	}
-	if (defer_acc) {
-		/* So the order here should be:
-		 * SLI3 pt2pt
-		 *   Issue CONFIG_LINK mbox
-		 *   CONFIG_LINK cmpl
-		 * SLI4 tgt
-		 *   Issue UNREG RPI mbx
-		 *   UNREG RPI cmpl
-		 * Issue PLOGI ACC
-		 * PLOGI ACC cmpl
-		 * Issue REG_LOGIN mbox
-		 */
 
-		/* Save the REG_LOGIN mbox for and rcv IOCB copy later */
-		link_mbox->context3 = login_mbox;
-		login_mbox->context3 = save_iocb;
+	/* So the order here should be:
+	 * SLI3 pt2pt
+	 *   Issue CONFIG_LINK mbox
+	 *   CONFIG_LINK cmpl
+	 * SLI4 pt2pt
+	 *   Issue REG_VFI mbox
+	 *   REG_VFI cmpl
+	 * SLI4
+	 *   Issue UNREG RPI mbx
+	 *   UNREG RPI cmpl
+	 * Issue REG_RPI mbox
+	 * REG RPI cmpl
+	 * Issue PLOGI ACC
+	 * PLOGI ACC cmpl
+	 */
+	login_mbox->mbox_cmpl = lpfc_defer_plogi_acc;
+	login_mbox->ctx_ndlp = lpfc_nlp_get(ndlp);
+	login_mbox->context3 = save_iocb; /* For PLOGI ACC */
 
-		/* Start the ball rolling by issuing CONFIG_LINK here */
-		rc = lpfc_sli_issue_mbox(phba, link_mbox, MBX_NOWAIT);
-		if (rc == MBX_NOT_FINISHED)
-			goto out;
-		return 1;
-	}
+	spin_lock_irq(&ndlp->lock);
+	ndlp->nlp_flag |= (NLP_ACC_REGLOGIN | NLP_RCV_PLOGI);
+	spin_unlock_irq(&ndlp->lock);
+
+	/* Start the ball rolling by issuing REG_LOGIN here */
+	rc = lpfc_sli_issue_mbox(phba, login_mbox, MBX_NOWAIT);
+	if (rc == MBX_NOT_FINISHED)
+		goto out;
+	lpfc_nlp_set_state(vport, ndlp, NLP_STE_REG_LOGIN_ISSUE);
 
-	rc = lpfc_els_rsp_acc(vport, ELS_CMD_PLOGI, cmdiocb, ndlp, login_mbox);
-	if (rc)
-		mempool_free(login_mbox, phba->mbox_mem_pool);
 	return 1;
 out:
-	if (defer_acc)
-		lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT,
-				"4577 discovery failure: %p %p %p\n",
-				save_iocb, link_mbox, login_mbox);
 	kfree(save_iocb);
-	if (link_mbox)
-		mempool_free(link_mbox, phba->mbox_mem_pool);
 	if (login_mbox)
 		mempool_free(login_mbox, phba->mbox_mem_pool);
 
-- 
2.30.2

[PATCH AUTOSEL 5.12 018/134] scsi: lpfc: Fix ADISC handling that never frees nodes

[Sasha Levin]

From: James Smart <jsmart2021@gmail.com>

[ Upstream commit 309b477462df7542355ac984674a6e89c01c89aa ]

While testing target port swap test with ADISC enabled, several nodes
remain in UNUSED state. These nodes are never freed and rmmod hangs for
long time before finising with "0233 Nodelist not empty" error.

During PLOGI completion lpfc_plogi_confirm_nport() looks for existing nodes
with same WWPN. If found, the existing node is used to continue discovery.
The node on which plogi was performed is freed.  When ADISC is enabled, an
ADISC els request is triggered in response to an RSCN.  It's possible that
the ADISC may be rejected by the remote port causing the ADISC completion
handler to clear the port and node name in the node.  If this occurs, if a
PLOGI is received it causes a node lookup based on wwpn to now fail,
causing the port swap logic to kick in which allocates a new node and swaps
to it. This effectively orphans the original node structure.

Fix the situation by detecting when the lookup fails and forgo the node
swap and node allocation by using the node on which the PLOGI was issued.

Link: https://lore.kernel.org/r/20210301171821.3427-15-jsmart2021@gmail.com
Co-developed-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/lpfc/lpfc_els.c | 33 +++++++--------------------------
 1 file changed, 7 insertions(+), 26 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index beb2fcd2d8e7..04c002eea446 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -1600,7 +1600,7 @@ lpfc_plogi_confirm_nport(struct lpfc_hba *phba, uint32_t *prsp,
 	struct lpfc_nodelist *new_ndlp;
 	struct serv_parm *sp;
 	uint8_t  name[sizeof(struct lpfc_name)];
-	uint32_t rc, keepDID = 0, keep_nlp_flag = 0;
+	uint32_t keepDID = 0, keep_nlp_flag = 0;
 	uint32_t keep_new_nlp_flag = 0;
 	uint16_t keep_nlp_state;
 	u32 keep_nlp_fc4_type = 0;
@@ -1622,7 +1622,7 @@ lpfc_plogi_confirm_nport(struct lpfc_hba *phba, uint32_t *prsp,
 	new_ndlp = lpfc_findnode_wwpn(vport, &sp->portName);
 
 	/* return immediately if the WWPN matches ndlp */
-	if (new_ndlp == ndlp)
+	if (!new_ndlp || (new_ndlp == ndlp))
 		return ndlp;
 
 	if (phba->sli_rev == LPFC_SLI_REV4) {
@@ -1641,30 +1641,11 @@ lpfc_plogi_confirm_nport(struct lpfc_hba *phba, uint32_t *prsp,
 			 (new_ndlp ? new_ndlp->nlp_flag : 0),
 			 (new_ndlp ? new_ndlp->nlp_fc4_type : 0));
 
-	if (!new_ndlp) {
-		rc = memcmp(&ndlp->nlp_portname, name,
-			    sizeof(struct lpfc_name));
-		if (!rc) {
-			if (active_rrqs_xri_bitmap)
-				mempool_free(active_rrqs_xri_bitmap,
-					     phba->active_rrq_pool);
-			return ndlp;
-		}
-		new_ndlp = lpfc_nlp_init(vport, ndlp->nlp_DID);
-		if (!new_ndlp) {
-			if (active_rrqs_xri_bitmap)
-				mempool_free(active_rrqs_xri_bitmap,
-					     phba->active_rrq_pool);
-			return ndlp;
-		}
-	} else {
-		keepDID = new_ndlp->nlp_DID;
-		if (phba->sli_rev == LPFC_SLI_REV4 &&
-		    active_rrqs_xri_bitmap)
-			memcpy(active_rrqs_xri_bitmap,
-			       new_ndlp->active_rrqs_xri_bitmap,
-			       phba->cfg_rrq_xri_bitmap_sz);
-	}
+	keepDID = new_ndlp->nlp_DID;
+
+	if (phba->sli_rev == LPFC_SLI_REV4 && active_rrqs_xri_bitmap)
+		memcpy(active_rrqs_xri_bitmap, new_ndlp->active_rrqs_xri_bitmap,
+		       phba->cfg_rrq_xri_bitmap_sz);
 
 	/* At this point in this routine, we know new_ndlp will be
 	 * returned. however, any previous GID_FTs that were done
-- 
2.30.2

[PATCH AUTOSEL 5.12 019/134] drm/amd/pm/swsmu: clean up user profile function

[Sasha Levin]

From: Arunpravin <Arunpravin.PaneerSelvam@amd.com>

[ Upstream commit d8cce9306801cfbf709055677f7896905094ff95 ]

Remove unnecessary comments, enable restore mode using
'|=' operator, fixes the alignment to improve the code
readability.

v2: Move all restoration flag check to bitwise '&' operator

Signed-off-by: Arunpravin <Arunpravin.PaneerSelvam@amd.com>
Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c | 34 ++++++++---------------
 1 file changed, 12 insertions(+), 22 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index cd905e41080e..42c4dbe3e362 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -279,35 +279,25 @@ static void smu_set_user_clk_dependencies(struct smu_context *smu, enum smu_clk_
 	if (smu->adev->in_suspend)
 		return;
 
-	/*
-	 * mclk, fclk and socclk are interdependent
-	 * on each other
-	 */
 	if (clk == SMU_MCLK) {
-		/* reset clock dependency */
 		smu->user_dpm_profile.clk_dependency = 0;
-		/* set mclk dependent clocks(fclk and socclk) */
 		smu->user_dpm_profile.clk_dependency = BIT(SMU_FCLK) | BIT(SMU_SOCCLK);
 	} else if (clk == SMU_FCLK) {
-		/* give priority to mclk, if mclk dependent clocks are set */
+		/* MCLK takes precedence over FCLK */
 		if (smu->user_dpm_profile.clk_dependency == (BIT(SMU_FCLK) | BIT(SMU_SOCCLK)))
 			return;
 
-		/* reset clock dependency */
 		smu->user_dpm_profile.clk_dependency = 0;
-		/* set fclk dependent clocks(mclk and socclk) */
 		smu->user_dpm_profile.clk_dependency = BIT(SMU_MCLK) | BIT(SMU_SOCCLK);
 	} else if (clk == SMU_SOCCLK) {
-		/* give priority to mclk, if mclk dependent clocks are set */
+		/* MCLK takes precedence over SOCCLK */
 		if (smu->user_dpm_profile.clk_dependency == (BIT(SMU_FCLK) | BIT(SMU_SOCCLK)))
 			return;
 
-		/* reset clock dependency */
 		smu->user_dpm_profile.clk_dependency = 0;
-		/* set socclk dependent clocks(mclk and fclk) */
 		smu->user_dpm_profile.clk_dependency = BIT(SMU_MCLK) | BIT(SMU_FCLK);
 	} else
-		/* add clk dependencies here, if any */
+		/* Add clk dependencies here, if any */
 		return;
 }
 
@@ -331,7 +321,7 @@ static void smu_restore_dpm_user_profile(struct smu_context *smu)
 		return;
 
 	/* Enable restore flag */
-	smu->user_dpm_profile.flags = SMU_DPM_USER_PROFILE_RESTORE;
+	smu->user_dpm_profile.flags |= SMU_DPM_USER_PROFILE_RESTORE;
 
 	/* set the user dpm power limit */
 	if (smu->user_dpm_profile.power_limit) {
@@ -354,8 +344,8 @@ static void smu_restore_dpm_user_profile(struct smu_context *smu)
 				ret = smu_force_clk_levels(smu, clk_type,
 						smu->user_dpm_profile.clk_mask[clk_type]);
 				if (ret)
-					dev_err(smu->adev->dev, "Failed to set clock type = %d\n",
-							clk_type);
+					dev_err(smu->adev->dev,
+						"Failed to set clock type = %d\n", clk_type);
 			}
 		}
 	}
@@ -1777,7 +1767,7 @@ int smu_force_clk_levels(struct smu_context *smu,
 
 	if (smu->ppt_funcs && smu->ppt_funcs->force_clk_levels) {
 		ret = smu->ppt_funcs->force_clk_levels(smu, clk_type, mask);
-		if (!ret && smu->user_dpm_profile.flags != SMU_DPM_USER_PROFILE_RESTORE) {
+		if (!ret && !(smu->user_dpm_profile.flags & SMU_DPM_USER_PROFILE_RESTORE)) {
 			smu->user_dpm_profile.clk_mask[clk_type] = mask;
 			smu_set_user_clk_dependencies(smu, clk_type);
 		}
@@ -2034,7 +2024,7 @@ int smu_set_fan_speed_rpm(struct smu_context *smu, uint32_t speed)
 	if (smu->ppt_funcs->set_fan_speed_percent) {
 		percent = speed * 100 / smu->fan_max_rpm;
 		ret = smu->ppt_funcs->set_fan_speed_percent(smu, percent);
-		if (!ret && smu->user_dpm_profile.flags != SMU_DPM_USER_PROFILE_RESTORE)
+		if (!ret && !(smu->user_dpm_profile.flags & SMU_DPM_USER_PROFILE_RESTORE))
 			smu->user_dpm_profile.fan_speed_percent = percent;
 	}
 
@@ -2104,7 +2094,7 @@ int smu_set_power_limit(struct smu_context *smu, uint32_t limit)
 
 	if (smu->ppt_funcs->set_power_limit) {
 		ret = smu->ppt_funcs->set_power_limit(smu, limit);
-		if (!ret && smu->user_dpm_profile.flags != SMU_DPM_USER_PROFILE_RESTORE)
+		if (!ret && !(smu->user_dpm_profile.flags & SMU_DPM_USER_PROFILE_RESTORE))
 			smu->user_dpm_profile.power_limit = limit;
 	}
 
@@ -2285,7 +2275,7 @@ int smu_set_fan_control_mode(struct smu_context *smu, int value)
 
 	if (smu->ppt_funcs->set_fan_control_mode) {
 		ret = smu->ppt_funcs->set_fan_control_mode(smu, value);
-		if (!ret && smu->user_dpm_profile.flags != SMU_DPM_USER_PROFILE_RESTORE)
+		if (!ret && !(smu->user_dpm_profile.flags & SMU_DPM_USER_PROFILE_RESTORE))
 			smu->user_dpm_profile.fan_mode = value;
 	}
 
@@ -2293,7 +2283,7 @@ int smu_set_fan_control_mode(struct smu_context *smu, int value)
 
 	/* reset user dpm fan speed */
 	if (!ret && value != AMD_FAN_CTRL_MANUAL &&
-			smu->user_dpm_profile.flags != SMU_DPM_USER_PROFILE_RESTORE)
+			!(smu->user_dpm_profile.flags & SMU_DPM_USER_PROFILE_RESTORE))
 		smu->user_dpm_profile.fan_speed_percent = 0;
 
 	return ret;
@@ -2335,7 +2325,7 @@ int smu_set_fan_speed_percent(struct smu_context *smu, uint32_t speed)
 		if (speed > 100)
 			speed = 100;
 		ret = smu->ppt_funcs->set_fan_speed_percent(smu, speed);
-		if (!ret && smu->user_dpm_profile.flags != SMU_DPM_USER_PROFILE_RESTORE)
+		if (!ret && !(smu->user_dpm_profile.flags & SMU_DPM_USER_PROFILE_RESTORE))
 			smu->user_dpm_profile.fan_speed_percent = speed;
 	}
 
-- 
2.30.2

[PATCH AUTOSEL 5.12 020/134] drm/amdgpu: Fix some unload driver issues

[Sasha Levin]

From: Emily Deng <Emily.Deng@amd.com>

[ Upstream commit bb0cd09be45ea457f25fdcbcb3d6cf2230f26c46 ]

When unloading driver after killing some applications, it will hit sdma
flush tlb job timeout which is called by ttm_bo_delay_delete. So
to avoid the job submit after fence driver fini, call ttm_bo_lock_delayed_workqueue
before fence driver fini. And also put drm_sched_fini before waiting fence.

Signed-off-by: Emily Deng <Emily.Deng@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 1 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c  | 5 +++--
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 8a5a8ff5d362..5eee251e3335 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3613,6 +3613,7 @@ void amdgpu_device_fini(struct amdgpu_device *adev)
 {
 	dev_info(adev->dev, "amdgpu: finishing device.\n");
 	flush_delayed_work(&adev->delayed_init_work);
+	ttm_bo_lock_delayed_workqueue(&adev->mman.bdev);
 	adev->shutdown = true;
 
 	kfree(adev->pci_state);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index d56f4023ebb3..7e8e46c39dbd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -533,6 +533,8 @@ void amdgpu_fence_driver_fini(struct amdgpu_device *adev)
 
 		if (!ring || !ring->fence_drv.initialized)
 			continue;
+		if (!ring->no_scheduler)
+			drm_sched_fini(&ring->sched);
 		r = amdgpu_fence_wait_empty(ring);
 		if (r) {
 			/* no need to trigger GPU reset as we are unloading */
@@ -541,8 +543,7 @@ void amdgpu_fence_driver_fini(struct amdgpu_device *adev)
 		if (ring->fence_drv.irq_src)
 			amdgpu_irq_put(adev, ring->fence_drv.irq_src,
 				       ring->fence_drv.irq_type);
-		if (!ring->no_scheduler)
-			drm_sched_fini(&ring->sched);
+
 		del_timer_sync(&ring->fence_drv.fallback_timer);
 		for (j = 0; j <= ring->fence_drv.num_fences_mask; ++j)
 			dma_fence_put(ring->fence_drv.fences[j]);
-- 
2.30.2

[PATCH AUTOSEL 5.12 021/134] sched/fair: Fix task utilization accountability in compute_energy()

[Sasha Levin]

From: Vincent Donnefort <vincent.donnefort@arm.com>

[ Upstream commit 0372e1cf70c28de6babcba38ef97b6ae3400b101 ]

find_energy_efficient_cpu() (feec()) computes for each perf_domain (pd) an
energy delta as follows:

  feec(task)
    for_each_pd
      base_energy = compute_energy(task, -1, pd)
        -> for_each_cpu(pd)
           -> cpu_util_next(cpu, task, -1)

      energy_delta = compute_energy(task, dst_cpu, pd)
        -> for_each_cpu(pd)
           -> cpu_util_next(cpu, task, dst_cpu)
      energy_delta -= base_energy

Then it picks the best CPU as being the one that minimizes energy_delta.

cpu_util_next() estimates the CPU utilization that would happen if the
task was placed on dst_cpu as follows:

  max(cpu_util + task_util, cpu_util_est + _task_util_est)

The task contribution to the energy delta can then be either:

  (1) _task_util_est, on a mostly idle CPU, where cpu_util is close to 0
      and _task_util_est > cpu_util.
  (2) task_util, on a mostly busy CPU, where cpu_util > _task_util_est.

  (cpu_util_est doesn't appear here. It is 0 when a CPU is idle and
   otherwise must be small enough so that feec() takes the CPU as a
   potential target for the task placement)

This is problematic for feec(), as cpu_util_next() might give an unfair
advantage to a CPU which is mostly busy (2) compared to one which is
mostly idle (1). _task_util_est being always bigger than task_util in
feec() (as the task is waking up), the task contribution to the energy
might look smaller on certain CPUs (2) and this breaks the energy
comparison.

This issue is, moreover, not sporadic. By starving idle CPUs, it keeps
their cpu_util < _task_util_est (1) while others will maintain cpu_util >
_task_util_est (2).

Fix this problem by always using max(task_util, _task_util_est) as a task
contribution to the energy (ENERGY_UTIL). The new estimated CPU
utilization for the energy would then be:

  max(cpu_util, cpu_util_est) + max(task_util, _task_util_est)

compute_energy() still needs to know which OPP would be selected if the
task would be migrated in the perf_domain (FREQUENCY_UTIL). Hence,
cpu_util_next() is still used to estimate the maximum util within the pd.

Signed-off-by: Vincent Donnefort <vincent.donnefort@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Quentin Perret <qperret@google.com>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Link: https://lkml.kernel.org/r/20210225083612.1113823-2-vincent.donnefort@arm.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/sched/fair.c | 24 ++++++++++++++++++++----
 1 file changed, 20 insertions(+), 4 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 794c2cb945f8..e3c2dcb1b015 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6518,8 +6518,24 @@ compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd)
 	 * its pd list and will not be accounted by compute_energy().
 	 */
 	for_each_cpu_and(cpu, pd_mask, cpu_online_mask) {
-		unsigned long cpu_util, util_cfs = cpu_util_next(cpu, p, dst_cpu);
-		struct task_struct *tsk = cpu == dst_cpu ? p : NULL;
+		unsigned long util_freq = cpu_util_next(cpu, p, dst_cpu);
+		unsigned long cpu_util, util_running = util_freq;
+		struct task_struct *tsk = NULL;
+
+		/*
+		 * When @p is placed on @cpu:
+		 *
+		 * util_running = max(cpu_util, cpu_util_est) +
+		 *		  max(task_util, _task_util_est)
+		 *
+		 * while cpu_util_next is: max(cpu_util + task_util,
+		 *			       cpu_util_est + _task_util_est)
+		 */
+		if (cpu == dst_cpu) {
+			tsk = p;
+			util_running =
+				cpu_util_next(cpu, p, -1) + task_util_est(p);
+		}
 
 		/*
 		 * Busy time computation: utilization clamping is not
@@ -6527,7 +6543,7 @@ compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd)
 		 * is already enough to scale the EM reported power
 		 * consumption at the (eventually clamped) cpu_capacity.
 		 */
-		sum_util += effective_cpu_util(cpu, util_cfs, cpu_cap,
+		sum_util += effective_cpu_util(cpu, util_running, cpu_cap,
 					       ENERGY_UTIL, NULL);
 
 		/*
@@ -6537,7 +6553,7 @@ compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd)
 		 * NOTE: in case RT tasks are running, by default the
 		 * FREQUENCY_UTIL's utilization can be max OPP.
 		 */
-		cpu_util = effective_cpu_util(cpu, util_cfs, cpu_cap,
+		cpu_util = effective_cpu_util(cpu, util_freq, cpu_cap,
 					      FREQUENCY_UTIL, tsk);
 		max_util = max(max_util, cpu_util);
 	}
-- 
2.30.2

[PATCH AUTOSEL 5.12 022/134] sched/pelt: Fix task util_est update filtering

[Sasha Levin]

From: Vincent Donnefort <vincent.donnefort@arm.com>

[ Upstream commit b89997aa88f0b07d8a6414c908af75062103b8c9 ]

Being called for each dequeue, util_est reduces the number of its updates
by filtering out when the EWMA signal is different from the task util_avg
by less than 1%. It is a problem for a sudden util_avg ramp-up. Due to the
decay from a previous high util_avg, EWMA might now be close enough to
the new util_avg. No update would then happen while it would leave
ue.enqueued with an out-of-date value.

Taking into consideration the two util_est members, EWMA and enqueued for
the filtering, ensures, for both, an up-to-date value.

This is for now an issue only for the trace probe that might return the
stale value. Functional-wise, it isn't a problem, as the value is always
accessed through max(enqueued, ewma).

This problem has been observed using LISA's UtilConvergence:test_means on
the sd845c board.

No regression observed with Hackbench on sd845c and Perf-bench sched pipe
on hikey/hikey960.

Signed-off-by: Vincent Donnefort <vincent.donnefort@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20210225165820.1377125-1-vincent.donnefort@arm.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/sched/fair.c | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e3c2dcb1b015..2a4041e3178f 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3941,6 +3941,8 @@ static inline void util_est_dequeue(struct cfs_rq *cfs_rq,
 	trace_sched_util_est_cfs_tp(cfs_rq);
 }
 
+#define UTIL_EST_MARGIN (SCHED_CAPACITY_SCALE / 100)
+
 /*
  * Check if a (signed) value is within a specified (unsigned) margin,
  * based on the observation that:
@@ -3958,7 +3960,7 @@ static inline void util_est_update(struct cfs_rq *cfs_rq,
 				   struct task_struct *p,
 				   bool task_sleep)
 {
-	long last_ewma_diff;
+	long last_ewma_diff, last_enqueued_diff;
 	struct util_est ue;
 
 	if (!sched_feat(UTIL_EST))
@@ -3979,6 +3981,8 @@ static inline void util_est_update(struct cfs_rq *cfs_rq,
 	if (ue.enqueued & UTIL_AVG_UNCHANGED)
 		return;
 
+	last_enqueued_diff = ue.enqueued;
+
 	/*
 	 * Reset EWMA on utilization increases, the moving average is used only
 	 * to smooth utilization decreases.
@@ -3992,12 +3996,17 @@ static inline void util_est_update(struct cfs_rq *cfs_rq,
 	}
 
 	/*
-	 * Skip update of task's estimated utilization when its EWMA is
+	 * Skip update of task's estimated utilization when its members are
 	 * already ~1% close to its last activation value.
 	 */
 	last_ewma_diff = ue.enqueued - ue.ewma;
-	if (within_margin(last_ewma_diff, (SCHED_CAPACITY_SCALE / 100)))
+	last_enqueued_diff -= ue.enqueued;
+	if (within_margin(last_ewma_diff, UTIL_EST_MARGIN)) {
+		if (!within_margin(last_enqueued_diff, UTIL_EST_MARGIN))
+			goto done;
+
 		return;
+	}
 
 	/*
 	 * To avoid overestimation of actual task utilization, skip updates if
-- 
2.30.2

[PATCH AUTOSEL 5.12 023/134] sched/topology: fix the issue groups don't span domain->span for NUMA diameter > 2

[Sasha Levin]

From: Barry Song <song.bao.hua@hisilicon.com>

[ Upstream commit 585b6d2723dc927ebc4ad884c4e879e4da8bc21f ]

As long as NUMA diameter > 2, building sched_domain by sibling's child
domain will definitely create a sched_domain with sched_group which will
span out of the sched_domain:

               +------+         +------+        +-------+       +------+
               | node |  12     |node  | 20     | node  |  12   |node  |
               |  0   +---------+1     +--------+ 2     +-------+3     |
               +------+         +------+        +-------+       +------+

domain0        node0            node1            node2          node3

domain1        node0+1          node0+1          node2+3        node2+3
                                                 +
domain2        node0+1+2                         |
             group: node0+1                      |
               group:node2+3 <-------------------+

when node2 is added into the domain2 of node0, kernel is using the child
domain of node2's domain2, which is domain1(node2+3). Node 3 is outside
the span of the domain including node0+1+2.

This will make load_balance() run based on screwed avg_load and group_type
in the sched_group spanning out of the sched_domain, and it also makes
select_task_rq_fair() pick an idle CPU outside the sched_domain.

Real servers which suffer from this problem include Kunpeng920 and 8-node
Sun Fire X4600-M2, at least.

Here we move to use the *child* domain of the *child* domain of node2's
domain2 as the new added sched_group. At the same, we re-use the lower
level sgc directly.
               +------+         +------+        +-------+       +------+
               | node |  12     |node  | 20     | node  |  12   |node  |
               |  0   +---------+1     +--------+ 2     +-------+3     |
               +------+         +------+        +-------+       +------+

domain0        node0            node1          +- node2          node3
                                               |
domain1        node0+1          node0+1        | node2+3        node2+3
                                               |
domain2        node0+1+2                       |
             group: node0+1                    |
               group:node2 <-------------------+

While the lower level sgc is re-used, this patch only changes the remote
sched_groups for those sched_domains playing grandchild trick, therefore,
sgc->next_update is still safe since it's only touched by CPUs that have
the group span as local group. And sgc->imbalance is also safe because
sd_parent remains the same in load_balance and LB only tries other CPUs
from the local group.
Moreover, since local groups are not touched, they are still getting
roughly equal size in a TL. And should_we_balance() only matters with
local groups, so the pull probability of those groups are still roughly
equal.

Tested by the below topology:
qemu-system-aarch64  -M virt -nographic \
 -smp cpus=8 \
 -numa node,cpus=0-1,nodeid=0 \
 -numa node,cpus=2-3,nodeid=1 \
 -numa node,cpus=4-5,nodeid=2 \
 -numa node,cpus=6-7,nodeid=3 \
 -numa dist,src=0,dst=1,val=12 \
 -numa dist,src=0,dst=2,val=20 \
 -numa dist,src=0,dst=3,val=22 \
 -numa dist,src=1,dst=2,val=22 \
 -numa dist,src=2,dst=3,val=12 \
 -numa dist,src=1,dst=3,val=24 \
 -m 4G -cpu cortex-a57 -kernel arch/arm64/boot/Image

w/o patch, we get lots of "groups don't span domain->span":
[    0.802139] CPU0 attaching sched-domain(s):
[    0.802193]  domain-0: span=0-1 level=MC
[    0.802443]   groups: 0:{ span=0 cap=1013 }, 1:{ span=1 cap=979 }
[    0.802693]   domain-1: span=0-3 level=NUMA
[    0.802731]    groups: 0:{ span=0-1 cap=1992 }, 2:{ span=2-3 cap=1943 }
[    0.802811]    domain-2: span=0-5 level=NUMA
[    0.802829]     groups: 0:{ span=0-3 cap=3935 }, 4:{ span=4-7 cap=3937 }
[    0.802881] ERROR: groups don't span domain->span
[    0.803058]     domain-3: span=0-7 level=NUMA
[    0.803080]      groups: 0:{ span=0-5 mask=0-1 cap=5843 }, 6:{ span=4-7 mask=6-7 cap=4077 }
[    0.804055] CPU1 attaching sched-domain(s):
[    0.804072]  domain-0: span=0-1 level=MC
[    0.804096]   groups: 1:{ span=1 cap=979 }, 0:{ span=0 cap=1013 }
[    0.804152]   domain-1: span=0-3 level=NUMA
[    0.804170]    groups: 0:{ span=0-1 cap=1992 }, 2:{ span=2-3 cap=1943 }
[    0.804219]    domain-2: span=0-5 level=NUMA
[    0.804236]     groups: 0:{ span=0-3 cap=3935 }, 4:{ span=4-7 cap=3937 }
[    0.804302] ERROR: groups don't span domain->span
[    0.804520]     domain-3: span=0-7 level=NUMA
[    0.804546]      groups: 0:{ span=0-5 mask=0-1 cap=5843 }, 6:{ span=4-7 mask=6-7 cap=4077 }
[    0.804677] CPU2 attaching sched-domain(s):
[    0.804687]  domain-0: span=2-3 level=MC
[    0.804705]   groups: 2:{ span=2 cap=934 }, 3:{ span=3 cap=1009 }
[    0.804754]   domain-1: span=0-3 level=NUMA
[    0.804772]    groups: 2:{ span=2-3 cap=1943 }, 0:{ span=0-1 cap=1992 }
[    0.804820]    domain-2: span=0-5 level=NUMA
[    0.804836]     groups: 2:{ span=0-3 mask=2-3 cap=3991 }, 4:{ span=0-1,4-7 mask=4-5 cap=5985 }
[    0.804944] ERROR: groups don't span domain->span
[    0.805108]     domain-3: span=0-7 level=NUMA
[    0.805134]      groups: 2:{ span=0-5 mask=2-3 cap=5899 }, 6:{ span=0-1,4-7 mask=6-7 cap=6125 }
[    0.805223] CPU3 attaching sched-domain(s):
[    0.805232]  domain-0: span=2-3 level=MC
[    0.805249]   groups: 3:{ span=3 cap=1009 }, 2:{ span=2 cap=934 }
[    0.805319]   domain-1: span=0-3 level=NUMA
[    0.805336]    groups: 2:{ span=2-3 cap=1943 }, 0:{ span=0-1 cap=1992 }
[    0.805383]    domain-2: span=0-5 level=NUMA
[    0.805399]     groups: 2:{ span=0-3 mask=2-3 cap=3991 }, 4:{ span=0-1,4-7 mask=4-5 cap=5985 }
[    0.805458] ERROR: groups don't span domain->span
[    0.805605]     domain-3: span=0-7 level=NUMA
[    0.805626]      groups: 2:{ span=0-5 mask=2-3 cap=5899 }, 6:{ span=0-1,4-7 mask=6-7 cap=6125 }
[    0.805712] CPU4 attaching sched-domain(s):
[    0.805721]  domain-0: span=4-5 level=MC
[    0.805738]   groups: 4:{ span=4 cap=984 }, 5:{ span=5 cap=924 }
[    0.805787]   domain-1: span=4-7 level=NUMA
[    0.805803]    groups: 4:{ span=4-5 cap=1908 }, 6:{ span=6-7 cap=2029 }
[    0.805851]    domain-2: span=0-1,4-7 level=NUMA
[    0.805867]     groups: 4:{ span=4-7 cap=3937 }, 0:{ span=0-3 cap=3935 }
[    0.805915] ERROR: groups don't span domain->span
[    0.806108]     domain-3: span=0-7 level=NUMA
[    0.806130]      groups: 4:{ span=0-1,4-7 mask=4-5 cap=5985 }, 2:{ span=0-3 mask=2-3 cap=3991 }
[    0.806214] CPU5 attaching sched-domain(s):
[    0.806222]  domain-0: span=4-5 level=MC
[    0.806240]   groups: 5:{ span=5 cap=924 }, 4:{ span=4 cap=984 }
[    0.806841]   domain-1: span=4-7 level=NUMA
[    0.806866]    groups: 4:{ span=4-5 cap=1908 }, 6:{ span=6-7 cap=2029 }
[    0.806934]    domain-2: span=0-1,4-7 level=NUMA
[    0.806953]     groups: 4:{ span=4-7 cap=3937 }, 0:{ span=0-3 cap=3935 }
[    0.807004] ERROR: groups don't span domain->span
[    0.807312]     domain-3: span=0-7 level=NUMA
[    0.807386]      groups: 4:{ span=0-1,4-7 mask=4-5 cap=5985 }, 2:{ span=0-3 mask=2-3 cap=3991 }
[    0.807686] CPU6 attaching sched-domain(s):
[    0.807710]  domain-0: span=6-7 level=MC
[    0.807750]   groups: 6:{ span=6 cap=1017 }, 7:{ span=7 cap=1012 }
[    0.807840]   domain-1: span=4-7 level=NUMA
[    0.807870]    groups: 6:{ span=6-7 cap=2029 }, 4:{ span=4-5 cap=1908 }
[    0.807952]    domain-2: span=0-1,4-7 level=NUMA
[    0.807985]     groups: 6:{ span=4-7 mask=6-7 cap=4077 }, 0:{ span=0-5 mask=0-1 cap=5843 }
[    0.808045] ERROR: groups don't span domain->span
[    0.808257]     domain-3: span=0-7 level=NUMA
[    0.808571]      groups: 6:{ span=0-1,4-7 mask=6-7 cap=6125 }, 2:{ span=0-5 mask=2-3 cap=5899 }
[    0.808848] CPU7 attaching sched-domain(s):
[    0.808860]  domain-0: span=6-7 level=MC
[    0.808880]   groups: 7:{ span=7 cap=1012 }, 6:{ span=6 cap=1017 }
[    0.808953]   domain-1: span=4-7 level=NUMA
[    0.808974]    groups: 6:{ span=6-7 cap=2029 }, 4:{ span=4-5 cap=1908 }
[    0.809034]    domain-2: span=0-1,4-7 level=NUMA
[    0.809055]     groups: 6:{ span=4-7 mask=6-7 cap=4077 }, 0:{ span=0-5 mask=0-1 cap=5843 }
[    0.809128] ERROR: groups don't span domain->span
[    0.810361]     domain-3: span=0-7 level=NUMA
[    0.810400]      groups: 6:{ span=0-1,4-7 mask=6-7 cap=5961 }, 2:{ span=0-5 mask=2-3 cap=5903 }

w/ patch, we don't get "groups don't span domain->span" any more:
[    1.486271] CPU0 attaching sched-domain(s):
[    1.486820]  domain-0: span=0-1 level=MC
[    1.500924]   groups: 0:{ span=0 cap=980 }, 1:{ span=1 cap=994 }
[    1.515717]   domain-1: span=0-3 level=NUMA
[    1.515903]    groups: 0:{ span=0-1 cap=1974 }, 2:{ span=2-3 cap=1989 }
[    1.516989]    domain-2: span=0-5 level=NUMA
[    1.517124]     groups: 0:{ span=0-3 cap=3963 }, 4:{ span=4-5 cap=1949 }
[    1.517369]     domain-3: span=0-7 level=NUMA
[    1.517423]      groups: 0:{ span=0-5 mask=0-1 cap=5912 }, 6:{ span=4-7 mask=6-7 cap=4054 }
[    1.520027] CPU1 attaching sched-domain(s):
[    1.520097]  domain-0: span=0-1 level=MC
[    1.520184]   groups: 1:{ span=1 cap=994 }, 0:{ span=0 cap=980 }
[    1.520429]   domain-1: span=0-3 level=NUMA
[    1.520487]    groups: 0:{ span=0-1 cap=1974 }, 2:{ span=2-3 cap=1989 }
[    1.520687]    domain-2: span=0-5 level=NUMA
[    1.520744]     groups: 0:{ span=0-3 cap=3963 }, 4:{ span=4-5 cap=1949 }
[    1.520948]     domain-3: span=0-7 level=NUMA
[    1.521038]      groups: 0:{ span=0-5 mask=0-1 cap=5912 }, 6:{ span=4-7 mask=6-7 cap=4054 }
[    1.522068] CPU2 attaching sched-domain(s):
[    1.522348]  domain-0: span=2-3 level=MC
[    1.522606]   groups: 2:{ span=2 cap=1003 }, 3:{ span=3 cap=986 }
[    1.522832]   domain-1: span=0-3 level=NUMA
[    1.522885]    groups: 2:{ span=2-3 cap=1989 }, 0:{ span=0-1 cap=1974 }
[    1.523043]    domain-2: span=0-5 level=NUMA
[    1.523092]     groups: 2:{ span=0-3 mask=2-3 cap=4037 }, 4:{ span=4-5 cap=1949 }
[    1.523302]     domain-3: span=0-7 level=NUMA
[    1.523352]      groups: 2:{ span=0-5 mask=2-3 cap=5986 }, 6:{ span=0-1,4-7 mask=6-7 cap=6102 }
[    1.523748] CPU3 attaching sched-domain(s):
[    1.523774]  domain-0: span=2-3 level=MC
[    1.523825]   groups: 3:{ span=3 cap=986 }, 2:{ span=2 cap=1003 }
[    1.524009]   domain-1: span=0-3 level=NUMA
[    1.524086]    groups: 2:{ span=2-3 cap=1989 }, 0:{ span=0-1 cap=1974 }
[    1.524281]    domain-2: span=0-5 level=NUMA
[    1.524331]     groups: 2:{ span=0-3 mask=2-3 cap=4037 }, 4:{ span=4-5 cap=1949 }
[    1.524534]     domain-3: span=0-7 level=NUMA
[    1.524586]      groups: 2:{ span=0-5 mask=2-3 cap=5986 }, 6:{ span=0-1,4-7 mask=6-7 cap=6102 }
[    1.524847] CPU4 attaching sched-domain(s):
[    1.524873]  domain-0: span=4-5 level=MC
[    1.524954]   groups: 4:{ span=4 cap=958 }, 5:{ span=5 cap=991 }
[    1.525105]   domain-1: span=4-7 level=NUMA
[    1.525153]    groups: 4:{ span=4-5 cap=1949 }, 6:{ span=6-7 cap=2006 }
[    1.525368]    domain-2: span=0-1,4-7 level=NUMA
[    1.525428]     groups: 4:{ span=4-7 cap=3955 }, 0:{ span=0-1 cap=1974 }
[    1.532726]     domain-3: span=0-7 level=NUMA
[    1.532811]      groups: 4:{ span=0-1,4-7 mask=4-5 cap=6003 }, 2:{ span=0-3 mask=2-3 cap=4037 }
[    1.534125] CPU5 attaching sched-domain(s):
[    1.534159]  domain-0: span=4-5 level=MC
[    1.534303]   groups: 5:{ span=5 cap=991 }, 4:{ span=4 cap=958 }
[    1.534490]   domain-1: span=4-7 level=NUMA
[    1.534572]    groups: 4:{ span=4-5 cap=1949 }, 6:{ span=6-7 cap=2006 }
[    1.534734]    domain-2: span=0-1,4-7 level=NUMA
[    1.534783]     groups: 4:{ span=4-7 cap=3955 }, 0:{ span=0-1 cap=1974 }
[    1.536057]     domain-3: span=0-7 level=NUMA
[    1.536430]      groups: 4:{ span=0-1,4-7 mask=4-5 cap=6003 }, 2:{ span=0-3 mask=2-3 cap=3896 }
[    1.536815] CPU6 attaching sched-domain(s):
[    1.536846]  domain-0: span=6-7 level=MC
[    1.536934]   groups: 6:{ span=6 cap=1005 }, 7:{ span=7 cap=1001 }
[    1.537144]   domain-1: span=4-7 level=NUMA
[    1.537262]    groups: 6:{ span=6-7 cap=2006 }, 4:{ span=4-5 cap=1949 }
[    1.537553]    domain-2: span=0-1,4-7 level=NUMA
[    1.537613]     groups: 6:{ span=4-7 mask=6-7 cap=4054 }, 0:{ span=0-1 cap=1805 }
[    1.537872]     domain-3: span=0-7 level=NUMA
[    1.537998]      groups: 6:{ span=0-1,4-7 mask=6-7 cap=6102 }, 2:{ span=0-5 mask=2-3 cap=5845 }
[    1.538448] CPU7 attaching sched-domain(s):
[    1.538505]  domain-0: span=6-7 level=MC
[    1.538586]   groups: 7:{ span=7 cap=1001 }, 6:{ span=6 cap=1005 }
[    1.538746]   domain-1: span=4-7 level=NUMA
[    1.538798]    groups: 6:{ span=6-7 cap=2006 }, 4:{ span=4-5 cap=1949 }
[    1.539048]    domain-2: span=0-1,4-7 level=NUMA
[    1.539111]     groups: 6:{ span=4-7 mask=6-7 cap=4054 }, 0:{ span=0-1 cap=1805 }
[    1.539571]     domain-3: span=0-7 level=NUMA
[    1.539610]      groups: 6:{ span=0-1,4-7 mask=6-7 cap=6102 }, 2:{ span=0-5 mask=2-3 cap=5845 }

Signed-off-by: Barry Song <song.bao.hua@hisilicon.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Tested-by: Meelis Roos <mroos@linux.ee>
Link: https://lkml.kernel.org/r/20210224030944.15232-1-song.bao.hua@hisilicon.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/sched/topology.c | 91 +++++++++++++++++++++++++++--------------
 1 file changed, 61 insertions(+), 30 deletions(-)

diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 09d35044bd88..12f80587e127 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -723,35 +723,6 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
 	for (tmp = sd; tmp; tmp = tmp->parent)
 		numa_distance += !!(tmp->flags & SD_NUMA);
 
-	/*
-	 * FIXME: Diameter >=3 is misrepresented.
-	 *
-	 * Smallest diameter=3 topology is:
-	 *
-	 *   node   0   1   2   3
-	 *     0:  10  20  30  40
-	 *     1:  20  10  20  30
-	 *     2:  30  20  10  20
-	 *     3:  40  30  20  10
-	 *
-	 *   0 --- 1 --- 2 --- 3
-	 *
-	 * NUMA-3	0-3		N/A		N/A		0-3
-	 *  groups:	{0-2},{1-3}					{1-3},{0-2}
-	 *
-	 * NUMA-2	0-2		0-3		0-3		1-3
-	 *  groups:	{0-1},{1-3}	{0-2},{2-3}	{1-3},{0-1}	{2-3},{0-2}
-	 *
-	 * NUMA-1	0-1		0-2		1-3		2-3
-	 *  groups:	{0},{1}		{1},{2},{0}	{2},{3},{1}	{3},{2}
-	 *
-	 * NUMA-0	0		1		2		3
-	 *
-	 * The NUMA-2 groups for nodes 0 and 3 are obviously buggered, as the
-	 * group span isn't a subset of the domain span.
-	 */
-	WARN_ONCE(numa_distance > 2, "Shortest NUMA path spans too many nodes\n");
-
 	sched_domain_debug(sd, cpu);
 
 	rq_attach_root(rq, rd);
@@ -982,6 +953,31 @@ static void init_overlap_sched_group(struct sched_domain *sd,
 	sg->sgc->max_capacity = SCHED_CAPACITY_SCALE;
 }
 
+static struct sched_domain *
+find_descended_sibling(struct sched_domain *sd, struct sched_domain *sibling)
+{
+	/*
+	 * The proper descendant would be the one whose child won't span out
+	 * of sd
+	 */
+	while (sibling->child &&
+	       !cpumask_subset(sched_domain_span(sibling->child),
+			       sched_domain_span(sd)))
+		sibling = sibling->child;
+
+	/*
+	 * As we are referencing sgc across different topology level, we need
+	 * to go down to skip those sched_domains which don't contribute to
+	 * scheduling because they will be degenerated in cpu_attach_domain
+	 */
+	while (sibling->child &&
+	       cpumask_equal(sched_domain_span(sibling->child),
+			     sched_domain_span(sibling)))
+		sibling = sibling->child;
+
+	return sibling;
+}
+
 static int
 build_overlap_sched_groups(struct sched_domain *sd, int cpu)
 {
@@ -1015,6 +1011,41 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
 		if (!cpumask_test_cpu(i, sched_domain_span(sibling)))
 			continue;
 
+		/*
+		 * Usually we build sched_group by sibling's child sched_domain
+		 * But for machines whose NUMA diameter are 3 or above, we move
+		 * to build sched_group by sibling's proper descendant's child
+		 * domain because sibling's child sched_domain will span out of
+		 * the sched_domain being built as below.
+		 *
+		 * Smallest diameter=3 topology is:
+		 *
+		 *   node   0   1   2   3
+		 *     0:  10  20  30  40
+		 *     1:  20  10  20  30
+		 *     2:  30  20  10  20
+		 *     3:  40  30  20  10
+		 *
+		 *   0 --- 1 --- 2 --- 3
+		 *
+		 * NUMA-3       0-3             N/A             N/A             0-3
+		 *  groups:     {0-2},{1-3}                                     {1-3},{0-2}
+		 *
+		 * NUMA-2       0-2             0-3             0-3             1-3
+		 *  groups:     {0-1},{1-3}     {0-2},{2-3}     {1-3},{0-1}     {2-3},{0-2}
+		 *
+		 * NUMA-1       0-1             0-2             1-3             2-3
+		 *  groups:     {0},{1}         {1},{2},{0}     {2},{3},{1}     {3},{2}
+		 *
+		 * NUMA-0       0               1               2               3
+		 *
+		 * The NUMA-2 groups for nodes 0 and 3 are obviously buggered, as the
+		 * group span isn't a subset of the domain span.
+		 */
+		if (sibling->child &&
+		    !cpumask_subset(sched_domain_span(sibling->child), span))
+			sibling = find_descended_sibling(sd, sibling);
+
 		sg = build_group_from_child_sched_domain(sibling, cpu);
 		if (!sg)
 			goto fail;
@@ -1022,7 +1053,7 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
 		sg_span = sched_group_span(sg);
 		cpumask_or(covered, covered, sg_span);
 
-		init_overlap_sched_group(sd, sg);
+		init_overlap_sched_group(sibling, sg);
 
 		if (!first)
 			first = sg;
-- 
2.30.2

[PATCH AUTOSEL 5.12 024/134] kvfree_rcu: Use same set of GFP flags as does single-argument

[Sasha Levin]

From: "Uladzislau Rezki (Sony)" <urezki@gmail.com>

[ Upstream commit ee6ddf58475cce8a3d3697614679cd8cb4a6f583 ]

Running an rcuscale stress-suite can lead to "Out of memory" of a
system. This can happen under high memory pressure with a small amount
of physical memory.

For example, a KVM test configuration with 64 CPUs and 512 megabytes
can result in OOM when running rcuscale with below parameters:

../kvm.sh --torture rcuscale --allcpus --duration 10 --kconfig CONFIG_NR_CPUS=64 \
--bootargs "rcuscale.kfree_rcu_test=1 rcuscale.kfree_nthreads=16 rcuscale.holdoff=20 \
  rcuscale.kfree_loops=10000 torture.disable_onoff_at_boot" --trust-make

<snip>
[   12.054448] kworker/1:1H invoked oom-killer: gfp_mask=0x2cc0(GFP_KERNEL|__GFP_NOWARN), order=0, oom_score_adj=0
[   12.055303] CPU: 1 PID: 377 Comm: kworker/1:1H Not tainted 5.11.0-rc3+ #510
[   12.055416] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.12.0-1 04/01/2014
[   12.056485] Workqueue: events_highpri fill_page_cache_func
[   12.056485] Call Trace:
[   12.056485]  dump_stack+0x57/0x6a
[   12.056485]  dump_header+0x4c/0x30a
[   12.056485]  ? del_timer_sync+0x20/0x30
[   12.056485]  out_of_memory.cold.47+0xa/0x7e
[   12.056485]  __alloc_pages_slowpath.constprop.123+0x82f/0xc00
[   12.056485]  __alloc_pages_nodemask+0x289/0x2c0
[   12.056485]  __get_free_pages+0x8/0x30
[   12.056485]  fill_page_cache_func+0x39/0xb0
[   12.056485]  process_one_work+0x1ed/0x3b0
[   12.056485]  ? process_one_work+0x3b0/0x3b0
[   12.060485]  worker_thread+0x28/0x3c0
[   12.060485]  ? process_one_work+0x3b0/0x3b0
[   12.060485]  kthread+0x138/0x160
[   12.060485]  ? kthread_park+0x80/0x80
[   12.060485]  ret_from_fork+0x22/0x30
[   12.062156] Mem-Info:
[   12.062350] active_anon:0 inactive_anon:0 isolated_anon:0
[   12.062350]  active_file:0 inactive_file:0 isolated_file:0
[   12.062350]  unevictable:0 dirty:0 writeback:0
[   12.062350]  slab_reclaimable:2797 slab_unreclaimable:80920
[   12.062350]  mapped:1 shmem:2 pagetables:8 bounce:0
[   12.062350]  free:10488 free_pcp:1227 free_cma:0
...
[   12.101610] Out of memory and no killable processes...
[   12.102042] Kernel panic - not syncing: System is deadlocked on memory
[   12.102583] CPU: 1 PID: 377 Comm: kworker/1:1H Not tainted 5.11.0-rc3+ #510
[   12.102600] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.12.0-1 04/01/2014
<snip>

Because kvfree_rcu() has a fallback path, memory allocation failure is
not the end of the world.  Furthermore, the added overhead of aggressive
GFP settings must be balanced against the overhead of the fallback path,
which is a cache miss for double-argument kvfree_rcu() and a call to
synchronize_rcu() for single-argument kvfree_rcu().  The current choice
of GFP_KERNEL|__GFP_NOWARN can result in longer latencies than a call
to synchronize_rcu(), so less-tenacious GFP flags would be helpful.

Here is the tradeoff that must be balanced:
    a) Minimize use of the fallback path,
    b) Avoid pushing the system into OOM,
    c) Bound allocation latency to that of synchronize_rcu(), and
    d) Leave the emergency reserves to use cases lacking fallbacks.

This commit therefore changes GFP flags from GFP_KERNEL|__GFP_NOWARN to
GFP_KERNEL|__GFP_NORETRY|__GFP_NOMEMALLOC|__GFP_NOWARN.  This combination
leaves the emergency reserves alone and can initiate reclaim, but will
not invoke the OOM killer.

Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/rcu/tree.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index da6f5213fb74..2a739c5fcca5 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3464,7 +3464,7 @@ static void fill_page_cache_func(struct work_struct *work)
 
 	for (i = 0; i < rcu_min_cached_objs; i++) {
 		bnode = (struct kvfree_rcu_bulk_data *)
-			__get_free_page(GFP_KERNEL | __GFP_NOWARN);
+			__get_free_page(GFP_KERNEL | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN);
 
 		if (bnode) {
 			raw_spin_lock_irqsave(&krcp->lock, flags);
-- 
2.30.2

[PATCH AUTOSEL 5.12 025/134] drm/virtio: fix possible leak/unlock virtio_gpu_object_array

[Sasha Levin]

From: xndcn <xndchn@gmail.com>

[ Upstream commit 377f8331d0565e6f71ba081c894029a92d0c7e77 ]

virtio_gpu_object array is not freed or unlocked in some
failed cases.

Signed-off-by: xndcn <xndchn@gmail.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20210305151819.14330-1-xndchn@gmail.com
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/virtio/virtgpu_ioctl.c  | 2 +-
 drivers/gpu/drm/virtio/virtgpu_object.c | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c
index 23eb6d772e40..669f2ee39515 100644
--- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c
+++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c
@@ -174,7 +174,7 @@ static int virtio_gpu_execbuffer_ioctl(struct drm_device *dev, void *data,
 		if (!sync_file) {
 			dma_fence_put(&out_fence->f);
 			ret = -ENOMEM;
-			goto out_memdup;
+			goto out_unresv;
 		}
 
 		exbuf->fence_fd = out_fence_fd;
diff --git a/drivers/gpu/drm/virtio/virtgpu_object.c b/drivers/gpu/drm/virtio/virtgpu_object.c
index d69a5b6da553..4ff1ec28e630 100644
--- a/drivers/gpu/drm/virtio/virtgpu_object.c
+++ b/drivers/gpu/drm/virtio/virtgpu_object.c
@@ -248,6 +248,7 @@ int virtio_gpu_object_create(struct virtio_gpu_device *vgdev,
 
 	ret = virtio_gpu_object_shmem_init(vgdev, bo, &ents, &nents);
 	if (ret != 0) {
+		virtio_gpu_array_put_free(objs);
 		virtio_gpu_free_object(&shmem_obj->base);
 		return ret;
 	}
-- 
2.30.2

[PATCH AUTOSEL 5.12 026/134] scsi: target: pscsi: Fix warning in pscsi_complete_cmd()

[Sasha Levin]

From: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>

[ Upstream commit fd48c056a32ed6e7754c7c475490f3bed54ed378 ]

This fixes a compilation warning in pscsi_complete_cmd():

     drivers/target/target_core_pscsi.c: In function ‘pscsi_complete_cmd’:
     drivers/target/target_core_pscsi.c:624:5: warning: suggest braces around empty body in an ‘if’ statement [-Wempty-body]
     ; /* XXX: TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE */

Link: https://lore.kernel.org/r/20210228055645.22253-5-chaitanya.kulkarni@wdc.com
Reviewed-by: Mike Christie <michael.christie@oracle.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/target/target_core_pscsi.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index 9ee797b8cb7e..508b49b0eaf5 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -620,8 +620,9 @@ static void pscsi_complete_cmd(struct se_cmd *cmd, u8 scsi_status,
 			unsigned char *buf;
 
 			buf = transport_kmap_data_sg(cmd);
-			if (!buf)
+			if (!buf) {
 				; /* XXX: TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE */
+			}
 
 			if (cdb[0] == MODE_SENSE_10) {
 				if (!(buf[3] & 0x80))
-- 
2.30.2

[PATCH AUTOSEL 5.12 027/134] media: ite-cir: check for receive overflow

[Sasha Levin]

From: Sean Young <sean@mess.org>

[ Upstream commit 28c7afb07ccfc0a939bb06ac1e7afe669901c65a ]

It's best if this condition is reported.

Signed-off-by: Sean Young <sean@mess.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/media/rc/ite-cir.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/media/rc/ite-cir.c b/drivers/media/rc/ite-cir.c
index 0c6229592e13..e5c4a6941d26 100644
--- a/drivers/media/rc/ite-cir.c
+++ b/drivers/media/rc/ite-cir.c
@@ -276,8 +276,14 @@ static irqreturn_t ite_cir_isr(int irq, void *data)
 	/* read the interrupt flags */
 	iflags = dev->params.get_irq_causes(dev);
 
+	/* Check for RX overflow */
+	if (iflags & ITE_IRQ_RX_FIFO_OVERRUN) {
+		dev_warn(&dev->rdev->dev, "receive overflow\n");
+		ir_raw_event_reset(dev->rdev);
+	}
+
 	/* check for the receive interrupt */
-	if (iflags & (ITE_IRQ_RX_FIFO | ITE_IRQ_RX_FIFO_OVERRUN)) {
+	if (iflags & ITE_IRQ_RX_FIFO) {
 		/* read the FIFO bytes */
 		rx_bytes =
 			dev->params.get_rx_bytes(dev, rx_buf,
-- 
2.30.2

[PATCH AUTOSEL 5.12 028/134] media: drivers: media: pci: sta2x11: fix Kconfig dependency on GPIOLIB

[Sasha Levin]

From: Julian Braha <julianbraha@gmail.com>

[ Upstream commit 24df8b74c8b2fb42c49ffe8585562da0c96446ff ]

When STA2X11_VIP is enabled, and GPIOLIB is disabled,
Kbuild gives the following warning:

WARNING: unmet direct dependencies detected for VIDEO_ADV7180
  Depends on [n]: MEDIA_SUPPORT [=y] && GPIOLIB [=n] && VIDEO_V4L2 [=y] && I2C [=y]
  Selected by [y]:
  - STA2X11_VIP [=y] && MEDIA_SUPPORT [=y] && MEDIA_PCI_SUPPORT [=y] && MEDIA_CAMERA_SUPPORT [=y] && PCI [=y] && VIDEO_V4L2 [=y] && VIRT_TO_BUS [=y] && I2C [=y] && (STA2X11 [=n] || COMPILE_TEST [=y]) && MEDIA_SUBDRV_AUTOSELECT [=y]

This is because STA2X11_VIP selects VIDEO_ADV7180
without selecting or depending on GPIOLIB,
despite VIDEO_ADV7180 depending on GPIOLIB.

Signed-off-by: Julian Braha <julianbraha@gmail.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/media/pci/sta2x11/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/media/pci/sta2x11/Kconfig b/drivers/media/pci/sta2x11/Kconfig
index 4dd98f94a91e..27bb78513631 100644
--- a/drivers/media/pci/sta2x11/Kconfig
+++ b/drivers/media/pci/sta2x11/Kconfig
@@ -3,6 +3,7 @@ config STA2X11_VIP
 	tristate "STA2X11 VIP Video For Linux"
 	depends on PCI && VIDEO_V4L2 && VIRT_TO_BUS && I2C
 	depends on STA2X11 || COMPILE_TEST
+	select GPIOLIB if MEDIA_SUBDRV_AUTOSELECT
 	select VIDEO_ADV7180 if MEDIA_SUBDRV_AUTOSELECT
 	select VIDEOBUF2_DMA_CONTIG
 	select MEDIA_CONTROLLER
-- 
2.30.2

[PATCH AUTOSEL 5.12 029/134] media: drivers/media/usb: fix memory leak in zr364xx_probe

[Sasha Levin]

From: Pavel Skripkin <paskripkin@gmail.com>

[ Upstream commit 9c39be40c0155c43343f53e3a439290c0fec5542 ]

syzbot reported memory leak in zr364xx_probe()[1].
The problem was in invalid error handling order.
All error conditions rigth after v4l2_ctrl_handler_init()
must call v4l2_ctrl_handler_free().

Reported-by: syzbot+efe9aefc31ae1e6f7675@syzkaller.appspotmail.com
Signed-off-by: Pavel Skripkin <paskripkin@gmail.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/media/usb/zr364xx/zr364xx.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/drivers/media/usb/zr364xx/zr364xx.c b/drivers/media/usb/zr364xx/zr364xx.c
index d29b861367ea..1ef611e08323 100644
--- a/drivers/media/usb/zr364xx/zr364xx.c
+++ b/drivers/media/usb/zr364xx/zr364xx.c
@@ -1430,7 +1430,7 @@ static int zr364xx_probe(struct usb_interface *intf,
 	if (hdl->error) {
 		err = hdl->error;
 		dev_err(&udev->dev, "couldn't register control\n");
-		goto unregister;
+		goto free_hdlr_and_unreg_dev;
 	}
 	/* save the init method used by this camera */
 	cam->method = id->driver_info;
@@ -1503,7 +1503,7 @@ static int zr364xx_probe(struct usb_interface *intf,
 	if (!cam->read_endpoint) {
 		err = -ENOMEM;
 		dev_err(&intf->dev, "Could not find bulk-in endpoint\n");
-		goto unregister;
+		goto free_hdlr_and_unreg_dev;
 	}
 
 	/* v4l */
@@ -1515,7 +1515,7 @@ static int zr364xx_probe(struct usb_interface *intf,
 	/* load zr364xx board specific */
 	err = zr364xx_board_init(cam);
 	if (err)
-		goto unregister;
+		goto free_hdlr_and_unreg_dev;
 	err = v4l2_ctrl_handler_setup(hdl);
 	if (err)
 		goto board_uninit;
@@ -1533,7 +1533,7 @@ static int zr364xx_probe(struct usb_interface *intf,
 	err = video_register_device(&cam->vdev, VFL_TYPE_VIDEO, -1);
 	if (err) {
 		dev_err(&udev->dev, "video_register_device failed\n");
-		goto free_handler;
+		goto board_uninit;
 	}
 	cam->v4l2_dev.release = zr364xx_release;
 
@@ -1541,11 +1541,10 @@ static int zr364xx_probe(struct usb_interface *intf,
 		 video_device_node_name(&cam->vdev));
 	return 0;
 
-free_handler:
-	v4l2_ctrl_handler_free(hdl);
 board_uninit:
 	zr364xx_board_uninit(cam);
-unregister:
+free_hdlr_and_unreg_dev:
+	v4l2_ctrl_handler_free(hdl);
 	v4l2_device_unregister(&cam->v4l2_dev);
 free_cam:
 	kfree(cam);
-- 
2.30.2

[PATCH AUTOSEL 5.12 030/134] media: cx23885: add more quirks for reset DMA on some AMD IOMMU

[Sasha Levin]

From: Brad Love <brad@nextdimension.cc>

[ Upstream commit 5f864cfbf59bfed2057bd214ce7fbf6ad420d54b ]

The folowing AMD IOMMU are affected by the RiSC engine stall, requiring a
reset to maintain continual operation. After being added to the
broken_dev_id list the systems are functional long term.

0x1481 is the PCI ID for the IOMMU found on Starship/Matisse

0x1419 is the PCI ID for the IOMMU found on 15h (Models 10h-1fh) family

0x5a23 is the PCI ID for the IOMMU found on RD890S/RD990

Signed-off-by: Brad Love <brad@nextdimension.cc>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/media/pci/cx23885/cx23885-core.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/media/pci/cx23885/cx23885-core.c b/drivers/media/pci/cx23885/cx23885-core.c
index 22f55a7840a6..d0ca260ecf70 100644
--- a/drivers/media/pci/cx23885/cx23885-core.c
+++ b/drivers/media/pci/cx23885/cx23885-core.c
@@ -2077,6 +2077,15 @@ static struct {
 	 * 0x1423 is the PCI ID for the IOMMU found on Kaveri
 	 */
 	{ PCI_VENDOR_ID_AMD, 0x1423 },
+	/* 0x1481 is the PCI ID for the IOMMU found on Starship/Matisse
+	 */
+	{ PCI_VENDOR_ID_AMD, 0x1481 },
+	/* 0x1419 is the PCI ID for the IOMMU found on 15h (Models 10h-1fh) family
+	 */
+	{ PCI_VENDOR_ID_AMD, 0x1419 },
+	/* 0x5a23 is the PCI ID for the IOMMU found on RD890S/RD990
+	 */
+	{ PCI_VENDOR_ID_ATI, 0x5a23 },
 };
 
 static bool cx23885_does_need_dma_reset(void)
-- 
2.30.2

[PATCH AUTOSEL 5.12 031/134] media: imx: capture: Return -EPIPE from __capture_legacy_try_fmt()

[Sasha Levin]

From: Laurent Pinchart <laurent.pinchart@ideasonboard.com>

[ Upstream commit cc271b6754691af74d710b761eaf027e3743e243 ]

The correct return code to report an invalid pipeline configuration is
-EPIPE. Return it instead of -EINVAL from __capture_legacy_try_fmt()
when the capture format doesn't match the media bus format of the
connected subdev.

Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Reviewed-by: Rui Miguel Silva <rmfrfs@gmail.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/staging/media/imx/imx-media-capture.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/staging/media/imx/imx-media-capture.c b/drivers/staging/media/imx/imx-media-capture.c
index e10ce103a5b4..94a0467d673b 100644
--- a/drivers/staging/media/imx/imx-media-capture.c
+++ b/drivers/staging/media/imx/imx-media-capture.c
@@ -557,7 +557,7 @@ static int capture_validate_fmt(struct capture_priv *priv)
 		priv->vdev.fmt.fmt.pix.height != f.fmt.pix.height ||
 		priv->vdev.cc->cs != cc->cs ||
 		priv->vdev.compose.width != compose.width ||
-		priv->vdev.compose.height != compose.height) ? -EINVAL : 0;
+		priv->vdev.compose.height != compose.height) ? -EPIPE : 0;
 }
 
 static int capture_start_streaming(struct vb2_queue *vq, unsigned int count)
-- 
2.30.2

[PATCH AUTOSEL 5.12 032/134] atomisp: don't let it go past pipes array

[Sasha Levin]

From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>

[ Upstream commit 1f6c45ac5fd70ab59136ab5babc7def269f3f509 ]

In practice, IA_CSS_PIPE_ID_NUM should never be used when
calling atomisp_q_video_buffers_to_css(), as the driver should
discover the right pipe before calling it.

Yet, if some pipe parsing issue happens, it could end using
it.

So, add a WARN_ON() to prevent such case.

Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/staging/media/atomisp/pci/atomisp_fops.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/staging/media/atomisp/pci/atomisp_fops.c b/drivers/staging/media/atomisp/pci/atomisp_fops.c
index 453bb6913550..f1e6b2597853 100644
--- a/drivers/staging/media/atomisp/pci/atomisp_fops.c
+++ b/drivers/staging/media/atomisp/pci/atomisp_fops.c
@@ -221,6 +221,9 @@ int atomisp_q_video_buffers_to_css(struct atomisp_sub_device *asd,
 	unsigned long irqflags;
 	int err = 0;
 
+	if (WARN_ON(css_pipe_id >= IA_CSS_PIPE_ID_NUM))
+		return -EINVAL;
+
 	while (pipe->buffers_in_css < ATOMISP_CSS_Q_DEPTH) {
 		struct videobuf_buffer *vb;
 
-- 
2.30.2

[PATCH AUTOSEL 5.12 033/134] power: supply: bq27xxx: fix power_avg for newer ICs

[Sasha Levin]

From: Matthias Schiffer <matthias.schiffer@ew.tq-group.com>

[ Upstream commit c4d57c22ac65bd503716062a06fad55a01569cac ]

On all newer bq27xxx ICs, the AveragePower register contains a signed
value; in addition to handling the raw value as unsigned, the driver
code also didn't convert it to µW as expected.

At least for the BQ28Z610, the reference manual incorrectly states that
the value is in units of 1mW and not 10mW. I have no way of knowing
whether the manuals of other supported ICs contain the same error, or if
there are models that actually use 1mW. At least, the new code shouldn't
be *less* correct than the old version for any device.

power_avg is removed from the cache structure, se we don't have to
extend it to store both a signed value and an error code. Always getting
an up-to-date value may be desirable anyways, as it avoids inconsistent
current and power readings when switching between charging and
discharging.

Signed-off-by: Matthias Schiffer <matthias.schiffer@ew.tq-group.com>
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/power/supply/bq27xxx_battery.c | 51 ++++++++++++++------------
 include/linux/power/bq27xxx_battery.h  |  1 -
 2 files changed, 27 insertions(+), 25 deletions(-)

diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c
index 4c4a7b1c64c5..0262109ac285 100644
--- a/drivers/power/supply/bq27xxx_battery.c
+++ b/drivers/power/supply/bq27xxx_battery.c
@@ -1661,27 +1661,6 @@ static int bq27xxx_battery_read_time(struct bq27xxx_device_info *di, u8 reg)
 	return tval * 60;
 }
 
-/*
- * Read an average power register.
- * Return < 0 if something fails.
- */
-static int bq27xxx_battery_read_pwr_avg(struct bq27xxx_device_info *di)
-{
-	int tval;
-
-	tval = bq27xxx_read(di, BQ27XXX_REG_AP, false);
-	if (tval < 0) {
-		dev_err(di->dev, "error reading average power register  %02x: %d\n",
-			BQ27XXX_REG_AP, tval);
-		return tval;
-	}
-
-	if (di->opts & BQ27XXX_O_ZERO)
-		return (tval * BQ27XXX_POWER_CONSTANT) / BQ27XXX_RS;
-	else
-		return tval;
-}
-
 /*
  * Returns true if a battery over temperature condition is detected
  */
@@ -1769,8 +1748,6 @@ void bq27xxx_battery_update(struct bq27xxx_device_info *di)
 		}
 		if (di->regs[BQ27XXX_REG_CYCT] != INVALID_REG_ADDR)
 			cache.cycle_count = bq27xxx_battery_read_cyct(di);
-		if (di->regs[BQ27XXX_REG_AP] != INVALID_REG_ADDR)
-			cache.power_avg = bq27xxx_battery_read_pwr_avg(di);
 
 		/* We only have to read charge design full once */
 		if (di->charge_design_full <= 0)
@@ -1833,6 +1810,32 @@ static int bq27xxx_battery_current(struct bq27xxx_device_info *di,
 	return 0;
 }
 
+/*
+ * Get the average power in µW
+ * Return < 0 if something fails.
+ */
+static int bq27xxx_battery_pwr_avg(struct bq27xxx_device_info *di,
+				   union power_supply_propval *val)
+{
+	int power;
+
+	power = bq27xxx_read(di, BQ27XXX_REG_AP, false);
+	if (power < 0) {
+		dev_err(di->dev,
+			"error reading average power register %02x: %d\n",
+			BQ27XXX_REG_AP, power);
+		return power;
+	}
+
+	if (di->opts & BQ27XXX_O_ZERO)
+		val->intval = (power * BQ27XXX_POWER_CONSTANT) / BQ27XXX_RS;
+	else
+		/* Other gauges return a signed value in units of 10mW */
+		val->intval = (int)((s16)power) * 10000;
+
+	return 0;
+}
+
 static int bq27xxx_battery_status(struct bq27xxx_device_info *di,
 				  union power_supply_propval *val)
 {
@@ -2020,7 +2023,7 @@ static int bq27xxx_battery_get_property(struct power_supply *psy,
 		ret = bq27xxx_simple_value(di->cache.energy, val);
 		break;
 	case POWER_SUPPLY_PROP_POWER_AVG:
-		ret = bq27xxx_simple_value(di->cache.power_avg, val);
+		ret = bq27xxx_battery_pwr_avg(di, val);
 		break;
 	case POWER_SUPPLY_PROP_HEALTH:
 		ret = bq27xxx_simple_value(di->cache.health, val);
diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h
index 111a40d0d3d5..8d5f4f40fb41 100644
--- a/include/linux/power/bq27xxx_battery.h
+++ b/include/linux/power/bq27xxx_battery.h
@@ -53,7 +53,6 @@ struct bq27xxx_reg_cache {
 	int capacity;
 	int energy;
 	int flags;
-	int power_avg;
 	int health;
 };
 
-- 
2.30.2

[PATCH AUTOSEL 5.12 034/134] extcon: arizona: Fix some issues when HPDET IRQ fires after the jack has been unplugged

[Sasha Levin]

From: Hans de Goede <hdegoede@redhat.com>

[ Upstream commit c309a3e8793f7e01c4a4ec7960658380572cb576 ]

When the jack is partially inserted and then removed again it may be
removed while the hpdet code is running. In this case the following
may happen:

1. The "JACKDET rise" or ""JACKDET fall" IRQ triggers
2. arizona_jackdet runs and takes info->lock
3. The "HPDET" IRQ triggers
4. arizona_hpdet_irq runs, blocks on info->lock
5. arizona_jackdet calls arizona_stop_mic() and clears info->hpdet_done
6. arizona_jackdet releases info->lock
7. arizona_hpdet_irq now can continue running and:
7.1 Calls arizona_start_mic() (if a mic was detected)
7.2 sets info->hpdet_done

Step 7 is undesirable / a bug:
7.1 causes the device to stay in a high power-state (with MICVDD enabled)
7.2 causes hpdet to not run on the next jack insertion, which in turn
    causes the EXTCON_JACK_HEADPHONE state to never get set

This fixes both issues by skipping these 2 steps when arizona_hpdet_irq
runs after the jack has been unplugged.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Acked-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Tested-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Acked-by: Chanwoo Choi <cw00.choi@samsung.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/extcon/extcon-arizona.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/drivers/extcon/extcon-arizona.c b/drivers/extcon/extcon-arizona.c
index aae82db542a5..f7ef247de46a 100644
--- a/drivers/extcon/extcon-arizona.c
+++ b/drivers/extcon/extcon-arizona.c
@@ -601,7 +601,7 @@ static irqreturn_t arizona_hpdet_irq(int irq, void *data)
 	struct arizona *arizona = info->arizona;
 	int id_gpio = arizona->pdata.hpdet_id_gpio;
 	unsigned int report = EXTCON_JACK_HEADPHONE;
-	int ret, reading;
+	int ret, reading, state;
 	bool mic = false;
 
 	mutex_lock(&info->lock);
@@ -614,12 +614,11 @@ static irqreturn_t arizona_hpdet_irq(int irq, void *data)
 	}
 
 	/* If the cable was removed while measuring ignore the result */
-	ret = extcon_get_state(info->edev, EXTCON_MECHANICAL);
-	if (ret < 0) {
-		dev_err(arizona->dev, "Failed to check cable state: %d\n",
-			ret);
+	state = extcon_get_state(info->edev, EXTCON_MECHANICAL);
+	if (state < 0) {
+		dev_err(arizona->dev, "Failed to check cable state: %d\n", state);
 		goto out;
-	} else if (!ret) {
+	} else if (!state) {
 		dev_dbg(arizona->dev, "Ignoring HPDET for removed cable\n");
 		goto done;
 	}
@@ -667,7 +666,7 @@ static irqreturn_t arizona_hpdet_irq(int irq, void *data)
 		gpio_set_value_cansleep(id_gpio, 0);
 
 	/* If we have a mic then reenable MICDET */
-	if (mic || info->mic)
+	if (state && (mic || info->mic))
 		arizona_start_mic(info);
 
 	if (info->hpdet_active) {
@@ -675,7 +674,9 @@ static irqreturn_t arizona_hpdet_irq(int irq, void *data)
 		info->hpdet_active = false;
 	}
 
-	info->hpdet_done = true;
+	/* Do not set hp_det done when the cable has been unplugged */
+	if (state)
+		info->hpdet_done = true;
 
 out:
 	mutex_unlock(&info->lock);
-- 
2.30.2

[PATCH AUTOSEL 5.12 035/134] extcon: arizona: Fix various races on driver unbind

[Sasha Levin]

From: Hans de Goede <hdegoede@redhat.com>

[ Upstream commit e5b499f6fb17bc95a813e85d0796522280203806 ]

We must free/disable all interrupts and cancel all pending works
before doing further cleanup.

Before this commit arizona_extcon_remove() was doing several
register writes to shut things down before disabling the IRQs
and it was cancelling only 1 of the 3 different works used.

Move all the register-writes shutting things down to after
the disabling of the IRQs and add the 2 missing
cancel_delayed_work_sync() calls.

This fixes various possible races on driver unbind. One of which
would always trigger on devices using the mic-clamp feature for
jack detection. The ARIZONA_MICD_CLAMP_MODE_MASK update was
done before disabling the IRQs, causing:
1. arizona_jackdet() to run
2. detect a jack being inserted (clamp disabled means jack inserted)
3. call arizona_start_mic() which:
3.1 Enables the MICVDD regulator
3.2 takes a pm_runtime_reference

And this was all happening after the ARIZONA_MICD_ENA bit clearing,
which would undo 3.1 and 3.2 because the ARIZONA_MICD_CLAMP_MODE_MASK
update was being done after the ARIZONA_MICD_ENA bit clearing.

So this means that arizona_extcon_remove() would exit with
1. MICVDD enabled and 2. The pm_runtime_reference being unbalanced.

MICVDD still being enabled caused the following oops when the
regulator is released by the devm framework:

[ 2850.745757] ------------[ cut here ]------------
[ 2850.745827] WARNING: CPU: 2 PID: 2098 at drivers/regulator/core.c:2123 _regulator_put.part.0+0x19f/0x1b0
[ 2850.745835] Modules linked in: extcon_arizona ...
...
[ 2850.746909] Call Trace:
[ 2850.746932]  regulator_put+0x2d/0x40
[ 2850.746946]  release_nodes+0x22a/0x260
[ 2850.746984]  __device_release_driver+0x190/0x240
[ 2850.747002]  driver_detach+0xd4/0x120
...
[ 2850.747337] ---[ end trace f455dfd7abd9781f ]---

Note this oops is just one of various theoretically possible races caused
by the wrong ordering inside arizona_extcon_remove(), this fixes the
ordering fixing all possible races, including the reported oops.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Acked-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Tested-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Acked-by: Chanwoo Choi <cw00.choi@samsung.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/extcon/extcon-arizona.c | 40 +++++++++++++++++----------------
 1 file changed, 21 insertions(+), 19 deletions(-)

diff --git a/drivers/extcon/extcon-arizona.c b/drivers/extcon/extcon-arizona.c
index f7ef247de46a..76aacbac5869 100644
--- a/drivers/extcon/extcon-arizona.c
+++ b/drivers/extcon/extcon-arizona.c
@@ -1760,25 +1760,6 @@ static int arizona_extcon_remove(struct platform_device *pdev)
 	bool change;
 	int ret;
 
-	ret = regmap_update_bits_check(arizona->regmap, ARIZONA_MIC_DETECT_1,
-				       ARIZONA_MICD_ENA, 0,
-				       &change);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "Failed to disable micd on remove: %d\n",
-			ret);
-	} else if (change) {
-		regulator_disable(info->micvdd);
-		pm_runtime_put(info->dev);
-	}
-
-	gpiod_put(info->micd_pol_gpio);
-
-	pm_runtime_disable(&pdev->dev);
-
-	regmap_update_bits(arizona->regmap,
-			   ARIZONA_MICD_CLAMP_CONTROL,
-			   ARIZONA_MICD_CLAMP_MODE_MASK, 0);
-
 	if (info->micd_clamp) {
 		jack_irq_rise = ARIZONA_IRQ_MICD_CLAMP_RISE;
 		jack_irq_fall = ARIZONA_IRQ_MICD_CLAMP_FALL;
@@ -1794,10 +1775,31 @@ static int arizona_extcon_remove(struct platform_device *pdev)
 	arizona_free_irq(arizona, jack_irq_rise, info);
 	arizona_free_irq(arizona, jack_irq_fall, info);
 	cancel_delayed_work_sync(&info->hpdet_work);
+	cancel_delayed_work_sync(&info->micd_detect_work);
+	cancel_delayed_work_sync(&info->micd_timeout_work);
+
+	ret = regmap_update_bits_check(arizona->regmap, ARIZONA_MIC_DETECT_1,
+				       ARIZONA_MICD_ENA, 0,
+				       &change);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Failed to disable micd on remove: %d\n",
+			ret);
+	} else if (change) {
+		regulator_disable(info->micvdd);
+		pm_runtime_put(info->dev);
+	}
+
+	regmap_update_bits(arizona->regmap,
+			   ARIZONA_MICD_CLAMP_CONTROL,
+			   ARIZONA_MICD_CLAMP_MODE_MASK, 0);
 	regmap_update_bits(arizona->regmap, ARIZONA_JACK_DETECT_ANALOGUE,
 			   ARIZONA_JD1_ENA, 0);
 	arizona_clk32k_disable(arizona);
 
+	gpiod_put(info->micd_pol_gpio);
+
+	pm_runtime_disable(&pdev->dev);
+
 	return 0;
 }
 
-- 
2.30.2

[PATCH AUTOSEL 5.12 036/134] media: venus: core, venc, vdec: Fix probe dependency error

[Sasha Levin]

From: Bryan O'Donoghue <bryan.odonoghue@linaro.org>

[ Upstream commit 08b1cf474b7f72750adebe0f0a35f8e9a3eb75f6 ]

Commit aaaa93eda64b ("media] media: venus: venc: add video encoder files")
is the last in a series of three commits to add core.c vdec.c and venc.c
adding core, encoder and decoder.

The encoder and decoder check for core drvdata as set and return -EPROBE_DEFER
if it has not been set, however both the encoder and decoder rely on
core.v4l2_dev as valid.

core.v4l2_dev will not be valid until v4l2_device_register() has completed
in core.c's probe().

Normally this is never seen however, Dmitry reported the following
backtrace when compiling drivers and firmware directly into a kernel image.

[    5.259968] Hardware name: Qualcomm Technologies, Inc. Robotics RB5 (DT)
[    5.269850] sd 0:0:0:3: [sdd] Optimal transfer size 524288 bytes
[    5.275505] Workqueue: events deferred_probe_work_func
[    5.275513] pstate: 60400005 (nZCv daif +PAN -UAO -TCO BTYPE=--)
[    5.441211] usb 2-1: new SuperSpeedPlus Gen 2 USB device number 2 using xhci-hcd
[    5.442486] pc : refcount_warn_saturate+0x140/0x148
[    5.493756] hub 2-1:1.0: USB hub found
[    5.496266] lr : refcount_warn_saturate+0x140/0x148
[    5.500982] hub 2-1:1.0: 4 ports detected
[    5.503440] sp : ffff80001067b730
[    5.503442] x29: ffff80001067b730
[    5.592660] usb 1-1: new high-speed USB device number 2 using xhci-hcd
[    5.598478] x28: ffff6c6bc1c379b8
[    5.598480] x27: ffffa5c673852960 x26: ffffa5c673852000
[    5.598484] x25: ffff6c6bc1c37800 x24: 0000000000000001
[    5.810652] x23: 0000000000000000 x22: ffffa5c673bc7118
[    5.813777] hub 1-1:1.0: USB hub found
[    5.816108] x21: ffffa5c674440000 x20: 0000000000000001
[    5.820846] hub 1-1:1.0: 4 ports detected
[    5.825415] x19: ffffa5c6744f4000 x18: ffffffffffffffff
[    5.825418] x17: 0000000000000000 x16: 0000000000000000
[    5.825421] x15: 00000a4810c193ba x14: 0000000000000000
[    5.825424] x13: 00000000000002b8 x12: 000000000000f20a
[    5.825427] x11: 000000000000f20a x10: 0000000000000038
[    5.845447] usb 2-1.1: new SuperSpeed Gen 1 USB device number 3 using xhci-hcd
[    5.845904]
[    5.845905] x9 : 0000000000000000 x8 : ffff6c6d36fae780
[    5.871208] x7 : ffff6c6d36faf240 x6 : 0000000000000000
[    5.876664] x5 : 0000000000000004 x4 : 0000000000000085
[    5.882121] x3 : 0000000000000119 x2 : ffffa5c6741ef478
[    5.887578] x1 : 3acbb3926faf5f00 x0 : 0000000000000000
[    5.893036] Call trace:
[    5.895551]  refcount_warn_saturate+0x140/0x148
[    5.900202]  __video_register_device+0x64c/0xd10
[    5.904944]  venc_probe+0xc4/0x148
[    5.908444]  platform_probe+0x68/0xe0
[    5.912210]  really_probe+0x118/0x3e0
[    5.915977]  driver_probe_device+0x5c/0xc0
[    5.920187]  __device_attach_driver+0x98/0xb8
[    5.924661]  bus_for_each_drv+0x68/0xd0
[    5.928604]  __device_attach+0xec/0x148
[    5.932547]  device_initial_probe+0x14/0x20
[    5.936845]  bus_probe_device+0x9c/0xa8
[    5.940788]  device_add+0x3e8/0x7c8
[    5.944376]  of_device_add+0x4c/0x60
[    5.948056]  of_platform_device_create_pdata+0xbc/0x140
[    5.953425]  of_platform_bus_create+0x17c/0x3c0
[    5.958078]  of_platform_populate+0x80/0x110
[    5.962463]  venus_probe+0x2ec/0x4d8
[    5.966143]  platform_probe+0x68/0xe0
[    5.969907]  really_probe+0x118/0x3e0
[    5.973674]  driver_probe_device+0x5c/0xc0
[    5.977882]  __device_attach_driver+0x98/0xb8
[    5.982356]  bus_for_each_drv+0x68/0xd0
[    5.986298]  __device_attach+0xec/0x148
[    5.990242]  device_initial_probe+0x14/0x20
[    5.994539]  bus_probe_device+0x9c/0xa8
[    5.998481]  deferred_probe_work_func+0x74/0xb0
[    6.003132]  process_one_work+0x1e8/0x360
[    6.007254]  worker_thread+0x208/0x478
[    6.011106]  kthread+0x150/0x158
[    6.014431]  ret_from_fork+0x10/0x30
[    6.018111] ---[ end trace f074246b1ecdb466 ]---

This patch fixes by

- Only setting drvdata after v4l2_device_register() completes
- Moving v4l2_device_register() so that suspend/reume in core::probe()
  stays as-is
- Changes pm_ops->core_function() to take struct venus_core not struct
  device
- Minimal rework of v4l2_device_*register in probe/remove

Reported-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Signed-off-by: Bryan O'Donoghue <bryan.odonoghue@linaro.org>
Signed-off-by: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/media/platform/qcom/venus/core.c      | 30 +++++++++++--------
 .../media/platform/qcom/venus/pm_helpers.c    | 30 ++++++++-----------
 .../media/platform/qcom/venus/pm_helpers.h    |  7 +++--
 3 files changed, 34 insertions(+), 33 deletions(-)

diff --git a/drivers/media/platform/qcom/venus/core.c b/drivers/media/platform/qcom/venus/core.c
index f9896c121fd8..d2842f496b47 100644
--- a/drivers/media/platform/qcom/venus/core.c
+++ b/drivers/media/platform/qcom/venus/core.c
@@ -218,7 +218,6 @@ static int venus_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	core->dev = dev;
-	platform_set_drvdata(pdev, core);
 
 	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	core->base = devm_ioremap_resource(dev, r);
@@ -248,7 +247,7 @@ static int venus_probe(struct platform_device *pdev)
 		return -ENODEV;
 
 	if (core->pm_ops->core_get) {
-		ret = core->pm_ops->core_get(dev);
+		ret = core->pm_ops->core_get(core);
 		if (ret)
 			return ret;
 	}
@@ -273,6 +272,12 @@ static int venus_probe(struct platform_device *pdev)
 	if (ret)
 		goto err_core_put;
 
+	ret = v4l2_device_register(dev, &core->v4l2_dev);
+	if (ret)
+		goto err_core_deinit;
+
+	platform_set_drvdata(pdev, core);
+
 	pm_runtime_enable(dev);
 
 	ret = pm_runtime_get_sync(dev);
@@ -307,10 +312,6 @@ static int venus_probe(struct platform_device *pdev)
 	if (ret)
 		goto err_venus_shutdown;
 
-	ret = v4l2_device_register(dev, &core->v4l2_dev);
-	if (ret)
-		goto err_core_deinit;
-
 	ret = pm_runtime_put_sync(dev);
 	if (ret) {
 		pm_runtime_get_noresume(dev);
@@ -323,8 +324,6 @@ static int venus_probe(struct platform_device *pdev)
 
 err_dev_unregister:
 	v4l2_device_unregister(&core->v4l2_dev);
-err_core_deinit:
-	hfi_core_deinit(core, false);
 err_venus_shutdown:
 	venus_shutdown(core);
 err_runtime_disable:
@@ -332,9 +331,11 @@ static int venus_probe(struct platform_device *pdev)
 	pm_runtime_set_suspended(dev);
 	pm_runtime_disable(dev);
 	hfi_destroy(core);
+err_core_deinit:
+	hfi_core_deinit(core, false);
 err_core_put:
 	if (core->pm_ops->core_put)
-		core->pm_ops->core_put(dev);
+		core->pm_ops->core_put(core);
 	return ret;
 }
 
@@ -360,7 +361,9 @@ static int venus_remove(struct platform_device *pdev)
 	pm_runtime_disable(dev);
 
 	if (pm_ops->core_put)
-		pm_ops->core_put(dev);
+		pm_ops->core_put(core);
+
+	v4l2_device_unregister(&core->v4l2_dev);
 
 	hfi_destroy(core);
 
@@ -368,6 +371,7 @@ static int venus_remove(struct platform_device *pdev)
 	icc_put(core->cpucfg_path);
 
 	v4l2_device_unregister(&core->v4l2_dev);
+
 	mutex_destroy(&core->pm_lock);
 	mutex_destroy(&core->lock);
 	venus_dbgfs_deinit(core);
@@ -396,7 +400,7 @@ static __maybe_unused int venus_runtime_suspend(struct device *dev)
 		return ret;
 
 	if (pm_ops->core_power) {
-		ret = pm_ops->core_power(dev, POWER_OFF);
+		ret = pm_ops->core_power(core, POWER_OFF);
 		if (ret)
 			return ret;
 	}
@@ -414,7 +418,7 @@ static __maybe_unused int venus_runtime_suspend(struct device *dev)
 err_video_path:
 	icc_set_bw(core->cpucfg_path, kbps_to_icc(1000), 0);
 err_cpucfg_path:
-	pm_ops->core_power(dev, POWER_ON);
+	pm_ops->core_power(core, POWER_ON);
 
 	return ret;
 }
@@ -434,7 +438,7 @@ static __maybe_unused int venus_runtime_resume(struct device *dev)
 		return ret;
 
 	if (pm_ops->core_power) {
-		ret = pm_ops->core_power(dev, POWER_ON);
+		ret = pm_ops->core_power(core, POWER_ON);
 		if (ret)
 			return ret;
 	}
diff --git a/drivers/media/platform/qcom/venus/pm_helpers.c b/drivers/media/platform/qcom/venus/pm_helpers.c
index 43c4e3d9e281..e349d01422c5 100644
--- a/drivers/media/platform/qcom/venus/pm_helpers.c
+++ b/drivers/media/platform/qcom/venus/pm_helpers.c
@@ -277,16 +277,13 @@ static int load_scale_v1(struct venus_inst *inst)
 	return 0;
 }
 
-static int core_get_v1(struct device *dev)
+static int core_get_v1(struct venus_core *core)
 {
-	struct venus_core *core = dev_get_drvdata(dev);
-
 	return core_clks_get(core);
 }
 
-static int core_power_v1(struct device *dev, int on)
+static int core_power_v1(struct venus_core *core, int on)
 {
-	struct venus_core *core = dev_get_drvdata(dev);
 	int ret = 0;
 
 	if (on == POWER_ON)
@@ -753,12 +750,12 @@ static int venc_power_v4(struct device *dev, int on)
 	return ret;
 }
 
-static int vcodec_domains_get(struct device *dev)
+static int vcodec_domains_get(struct venus_core *core)
 {
 	int ret;
 	struct opp_table *opp_table;
 	struct device **opp_virt_dev;
-	struct venus_core *core = dev_get_drvdata(dev);
+	struct device *dev = core->dev;
 	const struct venus_resources *res = core->res;
 	struct device *pd;
 	unsigned int i;
@@ -809,9 +806,8 @@ static int vcodec_domains_get(struct device *dev)
 	return ret;
 }
 
-static void vcodec_domains_put(struct device *dev)
+static void vcodec_domains_put(struct venus_core *core)
 {
-	struct venus_core *core = dev_get_drvdata(dev);
 	const struct venus_resources *res = core->res;
 	unsigned int i;
 
@@ -834,9 +830,9 @@ static void vcodec_domains_put(struct device *dev)
 	dev_pm_opp_detach_genpd(core->opp_table);
 }
 
-static int core_get_v4(struct device *dev)
+static int core_get_v4(struct venus_core *core)
 {
-	struct venus_core *core = dev_get_drvdata(dev);
+	struct device *dev = core->dev;
 	const struct venus_resources *res = core->res;
 	int ret;
 
@@ -875,7 +871,7 @@ static int core_get_v4(struct device *dev)
 		}
 	}
 
-	ret = vcodec_domains_get(dev);
+	ret = vcodec_domains_get(core);
 	if (ret) {
 		if (core->has_opp_table)
 			dev_pm_opp_of_remove_table(dev);
@@ -886,14 +882,14 @@ static int core_get_v4(struct device *dev)
 	return 0;
 }
 
-static void core_put_v4(struct device *dev)
+static void core_put_v4(struct venus_core *core)
 {
-	struct venus_core *core = dev_get_drvdata(dev);
+	struct device *dev = core->dev;
 
 	if (legacy_binding)
 		return;
 
-	vcodec_domains_put(dev);
+	vcodec_domains_put(core);
 
 	if (core->has_opp_table)
 		dev_pm_opp_of_remove_table(dev);
@@ -901,9 +897,9 @@ static void core_put_v4(struct device *dev)
 
 }
 
-static int core_power_v4(struct device *dev, int on)
+static int core_power_v4(struct venus_core *core, int on)
 {
-	struct venus_core *core = dev_get_drvdata(dev);
+	struct device *dev = core->dev;
 	struct device *pmctrl = core->pmdomains[0];
 	int ret = 0;
 
diff --git a/drivers/media/platform/qcom/venus/pm_helpers.h b/drivers/media/platform/qcom/venus/pm_helpers.h
index aa2f6afa2354..a492c50c5543 100644
--- a/drivers/media/platform/qcom/venus/pm_helpers.h
+++ b/drivers/media/platform/qcom/venus/pm_helpers.h
@@ -4,14 +4,15 @@
 #define __VENUS_PM_HELPERS_H__
 
 struct device;
+struct venus_core;
 
 #define POWER_ON	1
 #define POWER_OFF	0
 
 struct venus_pm_ops {
-	int (*core_get)(struct device *dev);
-	void (*core_put)(struct device *dev);
-	int (*core_power)(struct device *dev, int on);
+	int (*core_get)(struct venus_core *core);
+	void (*core_put)(struct venus_core *core);
+	int (*core_power)(struct venus_core *core, int on);
 
 	int (*vdec_get)(struct device *dev);
 	void (*vdec_put)(struct device *dev);
-- 
2.30.2

[PATCH AUTOSEL 5.12 037/134] s390/qdio: let driver manage the QAOB

[Sasha Levin]

From: Julian Wiedmann <jwi@linux.ibm.com>

[ Upstream commit 396c100472dd63bb1a5389d9dfb25a94943c41c9 ]

We are spending way too much effort on qdio-internal bookkeeping for
QAOB management & caching, and it's still not robust. Once qdio's
TX path has detached the QAOB from a PENDING buffer, we lost all
track of it until it shows up in a CQ notification again. So if the
device is torn down before that notification arrives, we leak the QAOB.

Just have the driver take care of it, and simply pass down a QAOB if
they want a TX with async-completion capability. For a buffer in PENDING
state that requires the QAOB for final completion, qeth can now also try
to recycle the buffer's QAOB rather than unconditionally freeing it.

This also eliminates the qdio_outbuf_state array, which was only needed
to transfer the aob->user1 tag from the driver to the qdio layer.

Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Acked-by: Benjamin Block <bblock@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/s390/include/asm/qdio.h      |  22 ++-----
 drivers/s390/cio/qdio.h           |  10 ---
 drivers/s390/cio/qdio_main.c      |  63 +++---------------
 drivers/s390/cio/qdio_setup.c     |  49 +-------------
 drivers/s390/net/qeth_core.h      |   3 +-
 drivers/s390/net/qeth_core_main.c | 102 ++++++++++++++----------------
 drivers/s390/scsi/zfcp_qdio.c     |   7 +-
 7 files changed, 66 insertions(+), 190 deletions(-)

diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h
index d9215c7106f0..8fc52679543d 100644
--- a/arch/s390/include/asm/qdio.h
+++ b/arch/s390/include/asm/qdio.h
@@ -246,21 +246,8 @@ struct slsb {
 	u8 val[QDIO_MAX_BUFFERS_PER_Q];
 } __attribute__ ((packed, aligned(256)));
 
-/**
- * struct qdio_outbuf_state - SBAL related asynchronous operation information
- *   (for communication with upper layer programs)
- *   (only required for use with completion queues)
- * @user: pointer to upper layer program's state information related to SBAL
- *        (stored in user1 data of QAOB)
- */
-struct qdio_outbuf_state {
-	void *user;
-};
-
-#define CHSC_AC1_INITIATE_INPUTQ	0x80
-
-
 /* qdio adapter-characteristics-1 flag */
+#define CHSC_AC1_INITIATE_INPUTQ	0x80
 #define AC1_SIGA_INPUT_NEEDED		0x40	/* process input queues */
 #define AC1_SIGA_OUTPUT_NEEDED		0x20	/* process output queues */
 #define AC1_SIGA_SYNC_NEEDED		0x10	/* ask hypervisor to sync */
@@ -338,7 +325,6 @@ typedef void qdio_handler_t(struct ccw_device *, unsigned int, int,
  * @int_parm: interruption parameter
  * @input_sbal_addr_array:  per-queue array, each element points to 128 SBALs
  * @output_sbal_addr_array: per-queue array, each element points to 128 SBALs
- * @output_sbal_state_array: no_output_qs * 128 state info (for CQ or NULL)
  */
 struct qdio_initialize {
 	unsigned char q_format;
@@ -357,7 +343,6 @@ struct qdio_initialize {
 	unsigned long int_parm;
 	struct qdio_buffer ***input_sbal_addr_array;
 	struct qdio_buffer ***output_sbal_addr_array;
-	struct qdio_outbuf_state *output_sbal_state_array;
 };
 
 #define QDIO_STATE_INACTIVE		0x00000002 /* after qdio_cleanup */
@@ -378,9 +363,10 @@ extern int qdio_allocate(struct ccw_device *cdev, unsigned int no_input_qs,
 extern int qdio_establish(struct ccw_device *cdev,
 			  struct qdio_initialize *init_data);
 extern int qdio_activate(struct ccw_device *);
+extern struct qaob *qdio_allocate_aob(void);
 extern void qdio_release_aob(struct qaob *);
-extern int do_QDIO(struct ccw_device *, unsigned int, int, unsigned int,
-		   unsigned int);
+extern int do_QDIO(struct ccw_device *cdev, unsigned int callflags, int q_nr,
+		   unsigned int bufnr, unsigned int count, struct qaob *aob);
 extern int qdio_start_irq(struct ccw_device *cdev);
 extern int qdio_stop_irq(struct ccw_device *cdev);
 extern int qdio_get_next_buffers(struct ccw_device *, int, int *, int *);
diff --git a/drivers/s390/cio/qdio.h b/drivers/s390/cio/qdio.h
index 34bf2f197c71..0e0044d70844 100644
--- a/drivers/s390/cio/qdio.h
+++ b/drivers/s390/cio/qdio.h
@@ -181,12 +181,6 @@ struct qdio_input_q {
 struct qdio_output_q {
 	/* PCIs are enabled for the queue */
 	int pci_out_enabled;
-	/* cq: use asynchronous output buffers */
-	int use_cq;
-	/* cq: aobs used for particual SBAL */
-	struct qaob **aobs;
-	/* cq: sbal state related to asynchronous operation */
-	struct qdio_outbuf_state *sbal_state;
 	/* timer to check for more outbound work */
 	struct timer_list timer;
 	/* tasklet to check for completions */
@@ -379,12 +373,8 @@ int qdio_setup_irq(struct qdio_irq *irq_ptr, struct qdio_initialize *init_data);
 void qdio_shutdown_irq(struct qdio_irq *irq);
 void qdio_print_subchannel_info(struct qdio_irq *irq_ptr);
 void qdio_free_queues(struct qdio_irq *irq_ptr);
-void qdio_free_async_data(struct qdio_irq *irq_ptr);
 int qdio_setup_init(void);
 void qdio_setup_exit(void);
-int qdio_enable_async_operation(struct qdio_output_q *q);
-void qdio_disable_async_operation(struct qdio_output_q *q);
-struct qaob *qdio_allocate_aob(void);
 
 int debug_get_buf_state(struct qdio_q *q, unsigned int bufnr,
 			unsigned char *state);
diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c
index 03a011619908..307ce7ff5ca4 100644
--- a/drivers/s390/cio/qdio_main.c
+++ b/drivers/s390/cio/qdio_main.c
@@ -517,24 +517,6 @@ static inline int qdio_inbound_q_done(struct qdio_q *q, unsigned int start)
 	return 1;
 }
 
-static inline unsigned long qdio_aob_for_buffer(struct qdio_output_q *q,
-					int bufnr)
-{
-	unsigned long phys_aob = 0;
-
-	if (!q->aobs[bufnr]) {
-		struct qaob *aob = qdio_allocate_aob();
-		q->aobs[bufnr] = aob;
-	}
-	if (q->aobs[bufnr]) {
-		q->aobs[bufnr]->user1 = (u64) q->sbal_state[bufnr].user;
-		phys_aob = virt_to_phys(q->aobs[bufnr]);
-		WARN_ON_ONCE(phys_aob & 0xFF);
-	}
-
-	return phys_aob;
-}
-
 static inline int qdio_tasklet_schedule(struct qdio_q *q)
 {
 	if (likely(q->irq_ptr->state == QDIO_IRQ_STATE_ACTIVE)) {
@@ -548,7 +530,6 @@ static int get_outbound_buffer_frontier(struct qdio_q *q, unsigned int start,
 					unsigned int *error)
 {
 	unsigned char state = 0;
-	unsigned int i;
 	int count;
 
 	q->timestamp = get_tod_clock_fast();
@@ -570,10 +551,6 @@ static int get_outbound_buffer_frontier(struct qdio_q *q, unsigned int start,
 
 	switch (state) {
 	case SLSB_P_OUTPUT_PENDING:
-		/* detach the utilized QAOBs: */
-		for (i = 0; i < count; i++)
-			q->u.out.aobs[QDIO_BUFNR(start + i)] = NULL;
-
 		*error = QDIO_ERROR_SLSB_PENDING;
 		fallthrough;
 	case SLSB_P_OUTPUT_EMPTY:
@@ -999,7 +976,6 @@ int qdio_free(struct ccw_device *cdev)
 	cdev->private->qdio_data = NULL;
 	mutex_unlock(&irq_ptr->setup_mutex);
 
-	qdio_free_async_data(irq_ptr);
 	qdio_free_queues(irq_ptr);
 	free_page((unsigned long) irq_ptr->qdr);
 	free_page(irq_ptr->chsc_page);
@@ -1075,28 +1051,6 @@ int qdio_allocate(struct ccw_device *cdev, unsigned int no_input_qs,
 }
 EXPORT_SYMBOL_GPL(qdio_allocate);
 
-static void qdio_detect_hsicq(struct qdio_irq *irq_ptr)
-{
-	struct qdio_q *q = irq_ptr->input_qs[0];
-	int i, use_cq = 0;
-
-	if (irq_ptr->nr_input_qs > 1 && queue_type(q) == QDIO_IQDIO_QFMT)
-		use_cq = 1;
-
-	for_each_output_queue(irq_ptr, q, i) {
-		if (use_cq) {
-			if (multicast_outbound(q))
-				continue;
-			if (qdio_enable_async_operation(&q->u.out) < 0) {
-				use_cq = 0;
-				continue;
-			}
-		} else
-			qdio_disable_async_operation(&q->u.out);
-	}
-	DBF_EVENT("use_cq:%d", use_cq);
-}
-
 static void qdio_trace_init_data(struct qdio_irq *irq,
 				 struct qdio_initialize *data)
 {
@@ -1191,8 +1145,6 @@ int qdio_establish(struct ccw_device *cdev,
 
 	qdio_setup_ssqd_info(irq_ptr);
 
-	qdio_detect_hsicq(irq_ptr);
-
 	/* qebsm is now setup if available, initialize buffer states */
 	qdio_init_buf_states(irq_ptr);
 
@@ -1297,9 +1249,11 @@ static int handle_inbound(struct qdio_q *q, unsigned int callflags,
  * @callflags: flags
  * @bufnr: first buffer to process
  * @count: how many buffers are filled
+ * @aob: asynchronous operation block
  */
 static int handle_outbound(struct qdio_q *q, unsigned int callflags,
-			   unsigned int bufnr, unsigned int count)
+			   unsigned int bufnr, unsigned int count,
+			   struct qaob *aob)
 {
 	const unsigned int scan_threshold = q->irq_ptr->scan_threshold;
 	unsigned char state = 0;
@@ -1320,11 +1274,9 @@ static int handle_outbound(struct qdio_q *q, unsigned int callflags,
 		q->u.out.pci_out_enabled = 0;
 
 	if (queue_type(q) == QDIO_IQDIO_QFMT) {
-		unsigned long phys_aob = 0;
-
-		if (q->u.out.use_cq && count == 1)
-			phys_aob = qdio_aob_for_buffer(&q->u.out, bufnr);
+		unsigned long phys_aob = aob ? virt_to_phys(aob) : 0;
 
+		WARN_ON_ONCE(!IS_ALIGNED(phys_aob, 256));
 		rc = qdio_kick_outbound_q(q, count, phys_aob);
 	} else if (need_siga_sync(q)) {
 		rc = qdio_siga_sync_q(q);
@@ -1359,9 +1311,10 @@ static int handle_outbound(struct qdio_q *q, unsigned int callflags,
  * @q_nr: queue number
  * @bufnr: buffer number
  * @count: how many buffers to process
+ * @aob: asynchronous operation block (outbound only)
  */
 int do_QDIO(struct ccw_device *cdev, unsigned int callflags,
-	    int q_nr, unsigned int bufnr, unsigned int count)
+	    int q_nr, unsigned int bufnr, unsigned int count, struct qaob *aob)
 {
 	struct qdio_irq *irq_ptr = cdev->private->qdio_data;
 
@@ -1383,7 +1336,7 @@ int do_QDIO(struct ccw_device *cdev, unsigned int callflags,
 				      callflags, bufnr, count);
 	else if (callflags & QDIO_FLAG_SYNC_OUTPUT)
 		return handle_outbound(irq_ptr->output_qs[q_nr],
-				       callflags, bufnr, count);
+				       callflags, bufnr, count, aob);
 	return -EINVAL;
 }
 EXPORT_SYMBOL_GPL(do_QDIO);
diff --git a/drivers/s390/cio/qdio_setup.c b/drivers/s390/cio/qdio_setup.c
index c8b9620bc688..da67e4979402 100644
--- a/drivers/s390/cio/qdio_setup.c
+++ b/drivers/s390/cio/qdio_setup.c
@@ -30,6 +30,7 @@ struct qaob *qdio_allocate_aob(void)
 {
 	return kmem_cache_zalloc(qdio_aob_cache, GFP_ATOMIC);
 }
+EXPORT_SYMBOL_GPL(qdio_allocate_aob);
 
 void qdio_release_aob(struct qaob *aob)
 {
@@ -247,8 +248,6 @@ static void setup_queues(struct qdio_irq *irq_ptr,
 			 struct qdio_initialize *qdio_init)
 {
 	struct qdio_q *q;
-	struct qdio_outbuf_state *output_sbal_state_array =
-				  qdio_init->output_sbal_state_array;
 	int i;
 
 	for_each_input_queue(irq_ptr, q, i) {
@@ -265,9 +264,6 @@ static void setup_queues(struct qdio_irq *irq_ptr,
 		DBF_EVENT("outq:%1d", i);
 		setup_queues_misc(q, irq_ptr, qdio_init->output_handler, i);
 
-		q->u.out.sbal_state = output_sbal_state_array;
-		output_sbal_state_array += QDIO_MAX_BUFFERS_PER_Q;
-
 		q->is_input_q = 0;
 		setup_storage_lists(q, irq_ptr,
 				    qdio_init->output_sbal_addr_array[i], i);
@@ -372,30 +368,6 @@ void qdio_setup_ssqd_info(struct qdio_irq *irq_ptr)
 	DBF_EVENT("3:%4x qib:%4x", irq_ptr->ssqd_desc.qdioac3, irq_ptr->qib.ac);
 }
 
-void qdio_free_async_data(struct qdio_irq *irq_ptr)
-{
-	struct qdio_q *q;
-	int i;
-
-	for (i = 0; i < irq_ptr->max_output_qs; i++) {
-		q = irq_ptr->output_qs[i];
-		if (q->u.out.use_cq) {
-			unsigned int n;
-
-			for (n = 0; n < QDIO_MAX_BUFFERS_PER_Q; n++) {
-				struct qaob *aob = q->u.out.aobs[n];
-
-				if (aob) {
-					qdio_release_aob(aob);
-					q->u.out.aobs[n] = NULL;
-				}
-			}
-
-			qdio_disable_async_operation(&q->u.out);
-		}
-	}
-}
-
 static void qdio_fill_qdr_desc(struct qdesfmt0 *desc, struct qdio_q *queue)
 {
 	desc->sliba = virt_to_phys(queue->slib);
@@ -545,25 +517,6 @@ void qdio_print_subchannel_info(struct qdio_irq *irq_ptr)
 	printk(KERN_INFO "%s", s);
 }
 
-int qdio_enable_async_operation(struct qdio_output_q *outq)
-{
-	outq->aobs = kcalloc(QDIO_MAX_BUFFERS_PER_Q, sizeof(struct qaob *),
-			     GFP_KERNEL);
-	if (!outq->aobs) {
-		outq->use_cq = 0;
-		return -ENOMEM;
-	}
-	outq->use_cq = 1;
-	return 0;
-}
-
-void qdio_disable_async_operation(struct qdio_output_q *q)
-{
-	kfree(q->aobs);
-	q->aobs = NULL;
-	q->use_cq = 0;
-}
-
 int __init qdio_setup_init(void)
 {
 	int rc;
diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 91acff493612..fd9b869d278e 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -437,6 +437,7 @@ struct qeth_qdio_out_buffer {
 
 	struct qeth_qdio_out_q *q;
 	struct list_head list_entry;
+	struct qaob *aob;
 };
 
 struct qeth_card;
@@ -499,7 +500,6 @@ struct qeth_out_q_stats {
 struct qeth_qdio_out_q {
 	struct qdio_buffer *qdio_bufs[QDIO_MAX_BUFFERS_PER_Q];
 	struct qeth_qdio_out_buffer *bufs[QDIO_MAX_BUFFERS_PER_Q];
-	struct qdio_outbuf_state *bufstates; /* convenience pointer */
 	struct list_head pending_bufs;
 	struct qeth_out_q_stats stats;
 	spinlock_t lock;
@@ -563,7 +563,6 @@ struct qeth_qdio_info {
 	/* output */
 	unsigned int no_out_queues;
 	struct qeth_qdio_out_q *out_qs[QETH_MAX_OUT_QUEUES];
-	struct qdio_outbuf_state *out_bufstates;
 
 	/* priority queueing */
 	int do_prio_queueing;
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index a814698387bc..175b82b98f36 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -369,8 +369,7 @@ static int qeth_cq_init(struct qeth_card *card)
 				   QDIO_MAX_BUFFERS_PER_Q);
 		card->qdio.c_q->next_buf_to_init = 127;
 		rc = do_QDIO(CARD_DDEV(card), QDIO_FLAG_SYNC_INPUT,
-			     card->qdio.no_in_queues - 1, 0,
-			     127);
+			     card->qdio.no_in_queues - 1, 0, 127, NULL);
 		if (rc) {
 			QETH_CARD_TEXT_(card, 2, "1err%d", rc);
 			goto out;
@@ -383,48 +382,22 @@ static int qeth_cq_init(struct qeth_card *card)
 
 static int qeth_alloc_cq(struct qeth_card *card)
 {
-	int rc;
-
 	if (card->options.cq == QETH_CQ_ENABLED) {
-		int i;
-		struct qdio_outbuf_state *outbuf_states;
-
 		QETH_CARD_TEXT(card, 2, "cqon");
 		card->qdio.c_q = qeth_alloc_qdio_queue();
 		if (!card->qdio.c_q) {
-			rc = -1;
-			goto kmsg_out;
+			dev_err(&card->gdev->dev, "Failed to create completion queue\n");
+			return -ENOMEM;
 		}
+
 		card->qdio.no_in_queues = 2;
-		card->qdio.out_bufstates =
-			kcalloc(card->qdio.no_out_queues *
-					QDIO_MAX_BUFFERS_PER_Q,
-				sizeof(struct qdio_outbuf_state),
-				GFP_KERNEL);
-		outbuf_states = card->qdio.out_bufstates;
-		if (outbuf_states == NULL) {
-			rc = -1;
-			goto free_cq_out;
-		}
-		for (i = 0; i < card->qdio.no_out_queues; ++i) {
-			card->qdio.out_qs[i]->bufstates = outbuf_states;
-			outbuf_states += QDIO_MAX_BUFFERS_PER_Q;
-		}
 	} else {
 		QETH_CARD_TEXT(card, 2, "nocq");
 		card->qdio.c_q = NULL;
 		card->qdio.no_in_queues = 1;
 	}
 	QETH_CARD_TEXT_(card, 2, "iqc%d", card->qdio.no_in_queues);
-	rc = 0;
-out:
-	return rc;
-free_cq_out:
-	qeth_free_qdio_queue(card->qdio.c_q);
-	card->qdio.c_q = NULL;
-kmsg_out:
-	dev_err(&card->gdev->dev, "Failed to create completion queue\n");
-	goto out;
+	return 0;
 }
 
 static void qeth_free_cq(struct qeth_card *card)
@@ -434,8 +407,6 @@ static void qeth_free_cq(struct qeth_card *card)
 		qeth_free_qdio_queue(card->qdio.c_q);
 		card->qdio.c_q = NULL;
 	}
-	kfree(card->qdio.out_bufstates);
-	card->qdio.out_bufstates = NULL;
 }
 
 static enum iucv_tx_notify qeth_compute_cq_notification(int sbalf15,
@@ -487,12 +458,12 @@ static void qeth_qdio_handle_aob(struct qeth_card *card,
 	switch (atomic_xchg(&buffer->state, new_state)) {
 	case QETH_QDIO_BUF_PRIMED:
 		/* Faster than TX completion code, let it handle the async
-		 * completion for us.
+		 * completion for us. It will also recycle the QAOB.
 		 */
 		break;
 	case QETH_QDIO_BUF_PENDING:
 		/* TX completion code is active and will handle the async
-		 * completion for us.
+		 * completion for us. It will also recycle the QAOB.
 		 */
 		break;
 	case QETH_QDIO_BUF_NEED_QAOB:
@@ -501,7 +472,7 @@ static void qeth_qdio_handle_aob(struct qeth_card *card,
 		qeth_notify_skbs(buffer->q, buffer, notification);
 
 		/* Free dangling allocations. The attached skbs are handled by
-		 * qeth_tx_complete_pending_bufs().
+		 * qeth_tx_complete_pending_bufs(), and so is the QAOB.
 		 */
 		for (i = 0;
 		     i < aob->sb_count && i < QETH_MAX_BUFFER_ELEMENTS(card);
@@ -520,8 +491,6 @@ static void qeth_qdio_handle_aob(struct qeth_card *card,
 	default:
 		WARN_ON_ONCE(1);
 	}
-
-	qdio_release_aob(aob);
 }
 
 static void qeth_setup_ccw(struct ccw1 *ccw, u8 cmd_code, u8 flags, u32 len,
@@ -1451,6 +1420,13 @@ static void qeth_clear_output_buffer(struct qeth_qdio_out_q *queue,
 	atomic_set(&buf->state, QETH_QDIO_BUF_EMPTY);
 }
 
+static void qeth_free_out_buf(struct qeth_qdio_out_buffer *buf)
+{
+	if (buf->aob)
+		qdio_release_aob(buf->aob);
+	kmem_cache_free(qeth_qdio_outbuf_cache, buf);
+}
+
 static void qeth_tx_complete_pending_bufs(struct qeth_card *card,
 					  struct qeth_qdio_out_q *queue,
 					  bool drain)
@@ -1468,7 +1444,7 @@ static void qeth_tx_complete_pending_bufs(struct qeth_card *card,
 			qeth_tx_complete_buf(buf, drain, 0);
 
 			list_del(&buf->list_entry);
-			kmem_cache_free(qeth_qdio_outbuf_cache, buf);
+			qeth_free_out_buf(buf);
 		}
 	}
 }
@@ -1485,7 +1461,7 @@ static void qeth_drain_output_queue(struct qeth_qdio_out_q *q, bool free)
 
 		qeth_clear_output_buffer(q, q->bufs[j], true, 0);
 		if (free) {
-			kmem_cache_free(qeth_qdio_outbuf_cache, q->bufs[j]);
+			qeth_free_out_buf(q->bufs[j]);
 			q->bufs[j] = NULL;
 		}
 	}
@@ -2637,7 +2613,7 @@ static struct qeth_qdio_out_q *qeth_alloc_output_queue(void)
 
 err_out_bufs:
 	while (i > 0)
-		kmem_cache_free(qeth_qdio_outbuf_cache, q->bufs[--i]);
+		qeth_free_out_buf(q->bufs[--i]);
 	qdio_free_buffers(q->qdio_bufs, QDIO_MAX_BUFFERS_PER_Q);
 err_qdio_bufs:
 	kfree(q);
@@ -3024,7 +3000,8 @@ static int qeth_init_qdio_queues(struct qeth_card *card)
 	}
 
 	card->qdio.in_q->next_buf_to_init = QDIO_BUFNR(rx_bufs);
-	rc = do_QDIO(CARD_DDEV(card), QDIO_FLAG_SYNC_INPUT, 0, 0, rx_bufs);
+	rc = do_QDIO(CARD_DDEV(card), QDIO_FLAG_SYNC_INPUT, 0, 0, rx_bufs,
+		     NULL);
 	if (rc) {
 		QETH_CARD_TEXT_(card, 2, "1err%d", rc);
 		return rc;
@@ -3516,7 +3493,7 @@ static unsigned int qeth_rx_refill_queue(struct qeth_card *card,
 		}
 
 		rc = do_QDIO(CARD_DDEV(card), QDIO_FLAG_SYNC_INPUT, 0,
-			     queue->next_buf_to_init, count);
+			     queue->next_buf_to_init, count, NULL);
 		if (rc) {
 			QETH_CARD_TEXT(card, 2, "qinberr");
 		}
@@ -3625,6 +3602,7 @@ static void qeth_flush_buffers(struct qeth_qdio_out_q *queue, int index,
 	struct qeth_qdio_out_buffer *buf = queue->bufs[index];
 	unsigned int qdio_flags = QDIO_FLAG_SYNC_OUTPUT;
 	struct qeth_card *card = queue->card;
+	struct qaob *aob = NULL;
 	int rc;
 	int i;
 
@@ -3637,16 +3615,24 @@ static void qeth_flush_buffers(struct qeth_qdio_out_q *queue, int index,
 				SBAL_EFLAGS_LAST_ENTRY;
 		queue->coalesced_frames += buf->frames;
 
-		if (queue->bufstates)
-			queue->bufstates[bidx].user = buf;
-
 		if (IS_IQD(card)) {
 			skb_queue_walk(&buf->skb_list, skb)
 				skb_tx_timestamp(skb);
 		}
 	}
 
-	if (!IS_IQD(card)) {
+	if (IS_IQD(card)) {
+		if (card->options.cq == QETH_CQ_ENABLED &&
+		    !qeth_iqd_is_mcast_queue(card, queue) &&
+		    count == 1) {
+			if (!buf->aob)
+				buf->aob = qdio_allocate_aob();
+			if (buf->aob) {
+				aob = buf->aob;
+				aob->user1 = (u64) buf;
+			}
+		}
+	} else {
 		if (!queue->do_pack) {
 			if ((atomic_read(&queue->used_buffers) >=
 				(QETH_HIGH_WATERMARK_PACK -
@@ -3677,8 +3663,8 @@ static void qeth_flush_buffers(struct qeth_qdio_out_q *queue, int index,
 	}
 
 	QETH_TXQ_STAT_INC(queue, doorbell);
-	rc = do_QDIO(CARD_DDEV(queue->card), qdio_flags,
-		     queue->queue_no, index, count);
+	rc = do_QDIO(CARD_DDEV(card), qdio_flags, queue->queue_no, index, count,
+		     aob);
 
 	switch (rc) {
 	case 0:
@@ -3814,8 +3800,7 @@ static void qeth_qdio_cq_handler(struct qeth_card *card, unsigned int qdio_err,
 		qeth_scrub_qdio_buffer(buffer, QDIO_MAX_ELEMENTS_PER_BUFFER);
 	}
 	rc = do_QDIO(CARD_DDEV(card), QDIO_FLAG_SYNC_INPUT, queue,
-		    card->qdio.c_q->next_buf_to_init,
-		    count);
+		     cq->next_buf_to_init, count, NULL);
 	if (rc) {
 		dev_warn(&card->gdev->dev,
 			"QDIO reported an error, rc=%i\n", rc);
@@ -5270,7 +5255,6 @@ static int qeth_qdio_establish(struct qeth_card *card)
 	init_data.int_parm               = (unsigned long) card;
 	init_data.input_sbal_addr_array  = in_sbal_ptrs;
 	init_data.output_sbal_addr_array = out_sbal_ptrs;
-	init_data.output_sbal_state_array = card->qdio.out_bufstates;
 	init_data.scan_threshold	 = IS_IQD(card) ? 0 : 32;
 
 	if (atomic_cmpxchg(&card->qdio.state, QETH_QDIO_ALLOCATED,
@@ -6069,7 +6053,15 @@ static void qeth_iqd_tx_complete(struct qeth_qdio_out_q *queue,
 	bool error = !!qdio_error;
 
 	if (qdio_error == QDIO_ERROR_SLSB_PENDING) {
-		WARN_ON_ONCE(card->options.cq != QETH_CQ_ENABLED);
+		struct qaob *aob = buffer->aob;
+
+		if (!aob) {
+			netdev_WARN_ONCE(card->dev,
+					 "Pending TX buffer %#x without QAOB on TX queue %u\n",
+					 bidx, queue->queue_no);
+			qeth_schedule_recovery(card);
+			return;
+		}
 
 		QETH_CARD_TEXT_(card, 5, "pel%u", bidx);
 
@@ -6125,6 +6117,8 @@ static void qeth_iqd_tx_complete(struct qeth_qdio_out_q *queue,
 		default:
 			WARN_ON_ONCE(1);
 		}
+
+		memset(aob, 0, sizeof(*aob));
 	} else if (card->options.cq == QETH_CQ_ENABLED) {
 		qeth_notify_skbs(queue, buffer,
 				 qeth_compute_cq_notification(sflags, 0));
diff --git a/drivers/s390/scsi/zfcp_qdio.c b/drivers/s390/scsi/zfcp_qdio.c
index 23ab16d65f2a..049596cbfb5d 100644
--- a/drivers/s390/scsi/zfcp_qdio.c
+++ b/drivers/s390/scsi/zfcp_qdio.c
@@ -128,7 +128,7 @@ static void zfcp_qdio_int_resp(struct ccw_device *cdev, unsigned int qdio_err,
 	/*
 	 * put SBALs back to response queue
 	 */
-	if (do_QDIO(cdev, QDIO_FLAG_SYNC_INPUT, 0, idx, count))
+	if (do_QDIO(cdev, QDIO_FLAG_SYNC_INPUT, 0, idx, count, NULL))
 		zfcp_erp_adapter_reopen(qdio->adapter, 0, "qdires2");
 }
 
@@ -298,7 +298,7 @@ int zfcp_qdio_send(struct zfcp_qdio *qdio, struct zfcp_qdio_req *q_req)
 	atomic_sub(sbal_number, &qdio->req_q_free);
 
 	retval = do_QDIO(qdio->adapter->ccw_device, QDIO_FLAG_SYNC_OUTPUT, 0,
-			 q_req->sbal_first, sbal_number);
+			 q_req->sbal_first, sbal_number, NULL);
 
 	if (unlikely(retval)) {
 		/* Failed to submit the IO, roll back our modifications. */
@@ -463,7 +463,8 @@ int zfcp_qdio_open(struct zfcp_qdio *qdio)
 		sbale->addr = 0;
 	}
 
-	if (do_QDIO(cdev, QDIO_FLAG_SYNC_INPUT, 0, 0, QDIO_MAX_BUFFERS_PER_Q))
+	if (do_QDIO(cdev, QDIO_FLAG_SYNC_INPUT, 0, 0, QDIO_MAX_BUFFERS_PER_Q,
+		    NULL))
 		goto failed_qdio;
 
 	/* set index of first available SBALS / number of available SBALS */
-- 
2.30.2

[PATCH AUTOSEL 5.12 038/134] media: media/saa7164: fix saa7164_encoder_register() memory leak bugs

[Sasha Levin]

From: Daniel Niv <danielniv3@gmail.com>

[ Upstream commit c759b2970c561e3b56aa030deb13db104262adfe ]

Add a fix for the memory leak bugs that can occur when the
saa7164_encoder_register() function fails.
The function allocates memory without explicitly freeing
it when errors occur.
Add a better error handling that deallocate the unused buffers before the
function exits during a fail.

Signed-off-by: Daniel Niv <danielniv3@gmail.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/media/pci/saa7164/saa7164-encoder.c | 20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

diff --git a/drivers/media/pci/saa7164/saa7164-encoder.c b/drivers/media/pci/saa7164/saa7164-encoder.c
index 11e1eb6a6809..1d1d32e043f1 100644
--- a/drivers/media/pci/saa7164/saa7164-encoder.c
+++ b/drivers/media/pci/saa7164/saa7164-encoder.c
@@ -1008,7 +1008,7 @@ int saa7164_encoder_register(struct saa7164_port *port)
 		printk(KERN_ERR "%s() failed (errno = %d), NO PCI configuration\n",
 			__func__, result);
 		result = -ENOMEM;
-		goto failed;
+		goto fail_pci;
 	}
 
 	/* Establish encoder defaults here */
@@ -1062,7 +1062,7 @@ int saa7164_encoder_register(struct saa7164_port *port)
 			  100000, ENCODER_DEF_BITRATE);
 	if (hdl->error) {
 		result = hdl->error;
-		goto failed;
+		goto fail_hdl;
 	}
 
 	port->std = V4L2_STD_NTSC_M;
@@ -1080,7 +1080,7 @@ int saa7164_encoder_register(struct saa7164_port *port)
 		printk(KERN_INFO "%s: can't allocate mpeg device\n",
 			dev->name);
 		result = -ENOMEM;
-		goto failed;
+		goto fail_hdl;
 	}
 
 	port->v4l_device->ctrl_handler = hdl;
@@ -1091,10 +1091,7 @@ int saa7164_encoder_register(struct saa7164_port *port)
 	if (result < 0) {
 		printk(KERN_INFO "%s: can't register mpeg device\n",
 			dev->name);
-		/* TODO: We're going to leak here if we don't dealloc
-		 The buffers above. The unreg function can't deal wit it.
-		*/
-		goto failed;
+		goto fail_reg;
 	}
 
 	printk(KERN_INFO "%s: registered device video%d [mpeg]\n",
@@ -1116,9 +1113,14 @@ int saa7164_encoder_register(struct saa7164_port *port)
 
 	saa7164_api_set_encoder(port);
 	saa7164_api_get_encoder(port);
+	return 0;
 
-	result = 0;
-failed:
+fail_reg:
+	video_device_release(port->v4l_device);
+	port->v4l_device = NULL;
+fail_hdl:
+	v4l2_ctrl_handler_free(hdl);
+fail_pci:
 	return result;
 }
 
-- 
2.30.2

[PATCH AUTOSEL 5.12 039/134] media: gspca/sq905.c: fix uninitialized variable

[Sasha Levin]

From: Hans Verkuil <hverkuil-cisco@xs4all.nl>

[ Upstream commit eaaea4681984c79d2b2b160387b297477f0c1aab ]

act_len can be uninitialized if usb_bulk_msg() returns an error.
Set it to 0 to avoid a KMSAN error.

Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Reported-by: syzbot+a4e309017a5f3a24c7b3@syzkaller.appspotmail.com
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/media/usb/gspca/sq905.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/usb/gspca/sq905.c b/drivers/media/usb/gspca/sq905.c
index 97799cfb832e..949111070971 100644
--- a/drivers/media/usb/gspca/sq905.c
+++ b/drivers/media/usb/gspca/sq905.c
@@ -158,7 +158,7 @@ static int
 sq905_read_data(struct gspca_dev *gspca_dev, u8 *data, int size, int need_lock)
 {
 	int ret;
-	int act_len;
+	int act_len = 0;
 
 	gspca_dev->usb_buf[0] = '\0';
 	if (need_lock)
-- 
2.30.2

[PATCH AUTOSEL 5.12 040/134] media: v4l2-ctrls.c: initialize flags field of p_fwht_params

[Sasha Levin]

From: Hans Verkuil <hverkuil-cisco@xs4all.nl>

[ Upstream commit ea1611ba3a544b34f89ffa3d1e833caab30a3f09 ]

The V4L2_CID_STATELESS_FWHT_PARAMS compound control was missing a
proper initialization of the flags field, so after loading the vicodec
module for the first time, running v4l2-compliance for the stateless
decoder would fail on this control because the initial control value
was considered invalid by the vicodec driver.

Initializing the flags field to sane values fixes this.

Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/media/v4l2-core/v4l2-ctrls.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c
index 016cf6204cbb..77f63773096e 100644
--- a/drivers/media/v4l2-core/v4l2-ctrls.c
+++ b/drivers/media/v4l2-core/v4l2-ctrls.c
@@ -1675,6 +1675,8 @@ static void std_init_compound(const struct v4l2_ctrl *ctrl, u32 idx,
 		p_fwht_params->version = V4L2_FWHT_VERSION;
 		p_fwht_params->width = 1280;
 		p_fwht_params->height = 720;
+		p_fwht_params->flags = V4L2_FWHT_FL_PIXENC_YUV |
+			(2 << V4L2_FWHT_FL_COMPONENTS_NUM_OFFSET);
 		break;
 	}
 }
-- 
2.30.2

[PATCH AUTOSEL 5.12 041/134] media: pci: saa7164: Rudimentary spelling fixes in the file saa7164-types.h

[Sasha Levin]

From: Bhaskar Chowdhury <unixbhaskar@gmail.com>

[ Upstream commit 4b19f9716ad89af51f07f9b611aabfd5fd80c625 ]

s/structues/structures/
s/decies/decides/

Signed-off-by: Bhaskar Chowdhury <unixbhaskar@gmail.com>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/media/pci/saa7164/saa7164-types.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/media/pci/saa7164/saa7164-types.h b/drivers/media/pci/saa7164/saa7164-types.h
index 34dd2be6fce4..00f163b38d40 100644
--- a/drivers/media/pci/saa7164/saa7164-types.h
+++ b/drivers/media/pci/saa7164/saa7164-types.h
@@ -7,7 +7,7 @@
 
 /* TODO: Cleanup and shorten the namespace */
 
-/* Some structues are passed directly to/from the firmware and
+/* Some structures are passed directly to/from the firmware and
  * have strict alignment requirements. This is one of them.
  */
 struct tmComResHWDescr {
@@ -28,7 +28,7 @@ struct tmComResHWDescr {
 /* This is DWORD aligned on windows but I can't find the right
  * gcc syntax to match the binary data from the device.
  * I've manually padded with Reserved[3] bytes to match the hardware,
- * but this could break if GCC decies to pack in a different way.
+ * but this could break if GCC decides to pack in a different way.
  */
 struct tmComResInterfaceDescr {
 	u8	bLength;
-- 
2.30.2

[PATCH AUTOSEL 5.12 042/134] power: supply: Use IRQF_ONESHOT

[Sasha Levin]

From: dongjian <dongjian@yulong.com>

[ Upstream commit 2469b836fa835c67648acad17d62bc805236a6ea ]

Fixes coccicheck error:

drivers/power/supply/pm2301_charger.c:1089:7-27: ERROR:
drivers/power/supply/lp8788-charger.c:502:8-28: ERROR:
drivers/power/supply/tps65217_charger.c:239:8-33: ERROR:
drivers/power/supply/tps65090-charger.c:303:8-33: ERROR:

Threaded IRQ with no primary handler requested without IRQF_ONESHOT

Signed-off-by: dongjian <dongjian@yulong.com>
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/power/supply/lp8788-charger.c   | 2 +-
 drivers/power/supply/pm2301_charger.c   | 2 +-
 drivers/power/supply/tps65090-charger.c | 2 +-
 drivers/power/supply/tps65217_charger.c | 2 +-
 4 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/power/supply/lp8788-charger.c b/drivers/power/supply/lp8788-charger.c
index e7931ffb7151..397e5a03b7d9 100644
--- a/drivers/power/supply/lp8788-charger.c
+++ b/drivers/power/supply/lp8788-charger.c
@@ -501,7 +501,7 @@ static int lp8788_set_irqs(struct platform_device *pdev,
 
 		ret = request_threaded_irq(virq, NULL,
 					lp8788_charger_irq_thread,
-					0, name, pchg);
+					IRQF_ONESHOT, name, pchg);
 		if (ret)
 			break;
 	}
diff --git a/drivers/power/supply/pm2301_charger.c b/drivers/power/supply/pm2301_charger.c
index ac06ecf7fc9c..a3bfb9612b17 100644
--- a/drivers/power/supply/pm2301_charger.c
+++ b/drivers/power/supply/pm2301_charger.c
@@ -1089,7 +1089,7 @@ static int pm2xxx_wall_charger_probe(struct i2c_client *i2c_client,
 	ret = request_threaded_irq(gpio_to_irq(pm2->pdata->gpio_irq_number),
 				NULL,
 				pm2xxx_charger_irq[0].isr,
-				pm2->pdata->irq_type,
+				pm2->pdata->irq_type | IRQF_ONESHOT,
 				pm2xxx_charger_irq[0].name, pm2);
 
 	if (ret != 0) {
diff --git a/drivers/power/supply/tps65090-charger.c b/drivers/power/supply/tps65090-charger.c
index 6b0098e5a88b..0990b2fa6cd8 100644
--- a/drivers/power/supply/tps65090-charger.c
+++ b/drivers/power/supply/tps65090-charger.c
@@ -301,7 +301,7 @@ static int tps65090_charger_probe(struct platform_device *pdev)
 
 	if (irq != -ENXIO) {
 		ret = devm_request_threaded_irq(&pdev->dev, irq, NULL,
-			tps65090_charger_isr, 0, "tps65090-charger", cdata);
+			tps65090_charger_isr, IRQF_ONESHOT, "tps65090-charger", cdata);
 		if (ret) {
 			dev_err(cdata->dev,
 				"Unable to register irq %d err %d\n", irq,
diff --git a/drivers/power/supply/tps65217_charger.c b/drivers/power/supply/tps65217_charger.c
index 814c2b81fdfe..ba33d1617e0b 100644
--- a/drivers/power/supply/tps65217_charger.c
+++ b/drivers/power/supply/tps65217_charger.c
@@ -238,7 +238,7 @@ static int tps65217_charger_probe(struct platform_device *pdev)
 	for (i = 0; i < NUM_CHARGER_IRQS; i++) {
 		ret = devm_request_threaded_irq(&pdev->dev, irq[i], NULL,
 						tps65217_charger_irq,
-						0, "tps65217-charger",
+						IRQF_ONESHOT, "tps65217-charger",
 						charger);
 		if (ret) {
 			dev_err(charger->dev,
-- 
2.30.2

[PATCH AUTOSEL 5.12 043/134] backlight: qcom-wled: Use sink_addr for sync toggle

[Sasha Levin]

From: Obeida Shamoun <oshmoun100@googlemail.com>

[ Upstream commit cdfd4c689e2a52c313b35ddfc1852ff274f91acb ]

WLED3_SINK_REG_SYNC is, as the name implies, a sink register offset.
Therefore, use the sink address as base instead of the ctrl address.

This fixes the sync toggle on wled4, which can be observed by the fact
that adjusting brightness now works.

It has no effect on wled3 because sink and ctrl base addresses are the
same.  This allows adjusting the brightness without having to disable
then reenable the module.

Signed-off-by: Obeida Shamoun <oshmoun100@googlemail.com>
Signed-off-by: Konrad Dybcio <konrad.dybcio@somainline.org>
Signed-off-by: Marijn Suijten <marijn.suijten@somainline.org>
Reviewed-by: Daniel Thompson <daniel.thompson@linaro.org>
Acked-by: Kiran Gunda <kgunda@codeaurora.org>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/video/backlight/qcom-wled.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/video/backlight/qcom-wled.c b/drivers/video/backlight/qcom-wled.c
index 091f07e7c145..fc8b443d10fd 100644
--- a/drivers/video/backlight/qcom-wled.c
+++ b/drivers/video/backlight/qcom-wled.c
@@ -336,13 +336,13 @@ static int wled3_sync_toggle(struct wled *wled)
 	unsigned int mask = GENMASK(wled->max_string_count - 1, 0);
 
 	rc = regmap_update_bits(wled->regmap,
-				wled->ctrl_addr + WLED3_SINK_REG_SYNC,
+				wled->sink_addr + WLED3_SINK_REG_SYNC,
 				mask, mask);
 	if (rc < 0)
 		return rc;
 
 	rc = regmap_update_bits(wled->regmap,
-				wled->ctrl_addr + WLED3_SINK_REG_SYNC,
+				wled->sink_addr + WLED3_SINK_REG_SYNC,
 				mask, WLED3_SINK_REG_SYNC_CLEAR);
 
 	return rc;
-- 
2.30.2

[PATCH AUTOSEL 5.12 044/134] backlight: qcom-wled: Fix FSC update issue for WLED5

[Sasha Levin]

From: Kiran Gunda <kgunda@codeaurora.org>

[ Upstream commit 4d6e9cdff7fbb6bef3e5559596fab3eeffaf95ca ]

Currently, for WLED5, the FSC (Full scale current) setting is not
updated properly due to driver toggling the wrong register after
an FSC update.

On WLED5 we should only toggle the MOD_SYNC bit after a brightness
update. For an FSC update we need to toggle the SYNC bits instead.

Fix it by adopting the common wled3_sync_toggle() for WLED5 and
introducing new code to the brightness update path to compensate.

Signed-off-by: Kiran Gunda <kgunda@codeaurora.org>
Reviewed-by: Daniel Thompson <daniel.thompson@linaro.org>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/video/backlight/qcom-wled.c | 25 +++++++++++++++++++------
 1 file changed, 19 insertions(+), 6 deletions(-)

diff --git a/drivers/video/backlight/qcom-wled.c b/drivers/video/backlight/qcom-wled.c
index fc8b443d10fd..e9fbe2483844 100644
--- a/drivers/video/backlight/qcom-wled.c
+++ b/drivers/video/backlight/qcom-wled.c
@@ -348,7 +348,7 @@ static int wled3_sync_toggle(struct wled *wled)
 	return rc;
 }
 
-static int wled5_sync_toggle(struct wled *wled)
+static int wled5_mod_sync_toggle(struct wled *wled)
 {
 	int rc;
 	u8 val;
@@ -445,10 +445,23 @@ static int wled_update_status(struct backlight_device *bl)
 			goto unlock_mutex;
 		}
 
-		rc = wled->wled_sync_toggle(wled);
-		if (rc < 0) {
-			dev_err(wled->dev, "wled sync failed rc:%d\n", rc);
-			goto unlock_mutex;
+		if (wled->version < 5) {
+			rc = wled->wled_sync_toggle(wled);
+			if (rc < 0) {
+				dev_err(wled->dev, "wled sync failed rc:%d\n", rc);
+				goto unlock_mutex;
+			}
+		} else {
+			/*
+			 * For WLED5 toggling the MOD_SYNC_BIT updates the
+			 * brightness
+			 */
+			rc = wled5_mod_sync_toggle(wled);
+			if (rc < 0) {
+				dev_err(wled->dev, "wled mod sync failed rc:%d\n",
+					rc);
+				goto unlock_mutex;
+			}
 		}
 	}
 
@@ -1459,7 +1472,7 @@ static int wled_configure(struct wled *wled)
 		size = ARRAY_SIZE(wled5_opts);
 		*cfg = wled5_config_defaults;
 		wled->wled_set_brightness = wled5_set_brightness;
-		wled->wled_sync_toggle = wled5_sync_toggle;
+		wled->wled_sync_toggle = wled3_sync_toggle;
 		wled->wled_cabc_config = wled5_cabc_config;
 		wled->wled_ovp_delay = wled5_ovp_delay;
 		wled->wled_auto_detection_required =
-- 
2.30.2

[PATCH AUTOSEL 5.12 045/134] drm/bridge/analogix/anx78xx: Setup encoder before registering connector

[Sasha Levin]

From: Lyude Paul <lyude@redhat.com>

[ Upstream commit 9962849d0871f5e53d0e3b3d84561f8f2847fbf4 ]

Since encoder mappings for connectors are exposed to userspace, we should
be attaching the encoder before exposing the connector to userspace. Just a
drive-by fix for an issue I noticed while fixing up usages of
drm_dp_aux_init()/drm_dp_aux_register() across the tree.

Signed-off-by: Lyude Paul <lyude@redhat.com>
Reviewed-by: Robert Foss <robert.foss@linaro.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20210219215326.2227596-9-lyude@redhat.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/bridge/analogix/analogix-anx78xx.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/bridge/analogix/analogix-anx78xx.c b/drivers/gpu/drm/bridge/analogix/analogix-anx78xx.c
index 81debd02c169..fbfe0cc89ba4 100644
--- a/drivers/gpu/drm/bridge/analogix/analogix-anx78xx.c
+++ b/drivers/gpu/drm/bridge/analogix/analogix-anx78xx.c
@@ -924,12 +924,6 @@ static int anx78xx_bridge_attach(struct drm_bridge *bridge,
 	drm_connector_helper_add(&anx78xx->connector,
 				 &anx78xx_connector_helper_funcs);
 
-	err = drm_connector_register(&anx78xx->connector);
-	if (err) {
-		DRM_ERROR("Failed to register connector: %d\n", err);
-		return err;
-	}
-
 	anx78xx->connector.polled = DRM_CONNECTOR_POLL_HPD;
 
 	err = drm_connector_attach_encoder(&anx78xx->connector,
@@ -939,6 +933,12 @@ static int anx78xx_bridge_attach(struct drm_bridge *bridge,
 		return err;
 	}
 
+	err = drm_connector_register(&anx78xx->connector);
+	if (err) {
+		DRM_ERROR("Failed to register connector: %d\n", err);
+		return err;
+	}
+
 	return 0;
 }
 
-- 
2.30.2

[PATCH AUTOSEL 5.12 046/134] drm/bridge/analogix/anx78xx: Cleanup on error in anx78xx_bridge_attach()

[Sasha Levin]

From: Lyude Paul <lyude@redhat.com>

[ Upstream commit 212ee8db84600f7b279b8645c62a112bff310995 ]

Just another issue I noticed while correcting usages of
drm_dp_aux_init()/drm_dp_aux_register() around the tree. If any of the
steps in anx78xx_bridge_attach() fail, we end up leaking resources. So,
let's fix that (and fix leaking a DP AUX adapter in the process) by
unrolling on errors.

Signed-off-by: Lyude Paul <lyude@redhat.com>
Reviewed-by: Robert Foss <robert.foss@linaro.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20210219215326.2227596-10-lyude@redhat.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/bridge/analogix/analogix-anx78xx.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/bridge/analogix/analogix-anx78xx.c b/drivers/gpu/drm/bridge/analogix/analogix-anx78xx.c
index fbfe0cc89ba4..bcc778f680a8 100644
--- a/drivers/gpu/drm/bridge/analogix/analogix-anx78xx.c
+++ b/drivers/gpu/drm/bridge/analogix/analogix-anx78xx.c
@@ -918,7 +918,7 @@ static int anx78xx_bridge_attach(struct drm_bridge *bridge,
 				 DRM_MODE_CONNECTOR_DisplayPort);
 	if (err) {
 		DRM_ERROR("Failed to initialize connector: %d\n", err);
-		return err;
+		goto aux_unregister;
 	}
 
 	drm_connector_helper_add(&anx78xx->connector,
@@ -930,16 +930,21 @@ static int anx78xx_bridge_attach(struct drm_bridge *bridge,
 					   bridge->encoder);
 	if (err) {
 		DRM_ERROR("Failed to link up connector to encoder: %d\n", err);
-		return err;
+		goto connector_cleanup;
 	}
 
 	err = drm_connector_register(&anx78xx->connector);
 	if (err) {
 		DRM_ERROR("Failed to register connector: %d\n", err);
-		return err;
+		goto connector_cleanup;
 	}
 
 	return 0;
+connector_cleanup:
+	drm_connector_cleanup(&anx78xx->connector);
+aux_unregister:
+	drm_dp_aux_unregister(&anx78xx->aux);
+	return err;
 }
 
 static enum drm_mode_status
-- 
2.30.2

[PATCH AUTOSEL 5.12 047/134] drm/amdgpu: enable retry fault wptr overflow

[Sasha Levin]

From: Philip Yang <Philip.Yang@amd.com>

[ Upstream commit b672cb1eee59efe6ca5bb2a2ce90060a22860558 ]

If xnack is on, VM retry fault interrupt send to IH ring1, and ring1
will be full quickly. IH cannot receive other interrupts, this causes
deadlock if migrating buffer using sdma and waiting for sdma done while
handling retry fault.

Remove VMC from IH storm client, enable ring1 write pointer overflow,
then IH will drop retry fault interrupts and be able to receive other
interrupts while driver is handling retry fault.

IH ring1 write pointer doesn't writeback to memory by IH, and ring1
write pointer recorded by self-irq is not updated, so always read
the latest ring1 write pointer from register.

Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/amd/amdgpu/vega10_ih.c | 32 +++++++++-----------------
 drivers/gpu/drm/amd/amdgpu/vega20_ih.c | 32 +++++++++-----------------
 2 files changed, 22 insertions(+), 42 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
index 88626d83e07b..ca8efa5c6978 100644
--- a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
@@ -220,10 +220,8 @@ static int vega10_ih_enable_ring(struct amdgpu_device *adev,
 	tmp = vega10_ih_rb_cntl(ih, tmp);
 	if (ih == &adev->irq.ih)
 		tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, RPTR_REARM, !!adev->irq.msi_enabled);
-	if (ih == &adev->irq.ih1) {
-		tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_ENABLE, 0);
+	if (ih == &adev->irq.ih1)
 		tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, RB_FULL_DRAIN_ENABLE, 1);
-	}
 	if (amdgpu_sriov_vf(adev)) {
 		if (psp_reg_program(&adev->psp, ih_regs->psp_reg_id, tmp)) {
 			dev_err(adev->dev, "PSP program IH_RB_CNTL failed!\n");
@@ -265,7 +263,6 @@ static int vega10_ih_irq_init(struct amdgpu_device *adev)
 	u32 ih_chicken;
 	int ret;
 	int i;
-	u32 tmp;
 
 	/* disable irqs */
 	ret = vega10_ih_toggle_interrupts(adev, false);
@@ -291,15 +288,6 @@ static int vega10_ih_irq_init(struct amdgpu_device *adev)
 		}
 	}
 
-	tmp = RREG32_SOC15(OSSSYS, 0, mmIH_STORM_CLIENT_LIST_CNTL);
-	tmp = REG_SET_FIELD(tmp, IH_STORM_CLIENT_LIST_CNTL,
-			    CLIENT18_IS_STORM_CLIENT, 1);
-	WREG32_SOC15(OSSSYS, 0, mmIH_STORM_CLIENT_LIST_CNTL, tmp);
-
-	tmp = RREG32_SOC15(OSSSYS, 0, mmIH_INT_FLOOD_CNTL);
-	tmp = REG_SET_FIELD(tmp, IH_INT_FLOOD_CNTL, FLOOD_CNTL_ENABLE, 1);
-	WREG32_SOC15(OSSSYS, 0, mmIH_INT_FLOOD_CNTL, tmp);
-
 	pci_set_master(adev->pdev);
 
 	/* enable interrupts */
@@ -345,11 +333,17 @@ static u32 vega10_ih_get_wptr(struct amdgpu_device *adev,
 	u32 wptr, tmp;
 	struct amdgpu_ih_regs *ih_regs;
 
-	wptr = le32_to_cpu(*ih->wptr_cpu);
-	ih_regs = &ih->ih_regs;
+	if (ih == &adev->irq.ih) {
+		/* Only ring0 supports writeback. On other rings fall back
+		 * to register-based code with overflow checking below.
+		 */
+		wptr = le32_to_cpu(*ih->wptr_cpu);
 
-	if (!REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW))
-		goto out;
+		if (!REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW))
+			goto out;
+	}
+
+	ih_regs = &ih->ih_regs;
 
 	/* Double check that the overflow wasn't already cleared. */
 	wptr = RREG32_NO_KIQ(ih_regs->ih_rb_wptr);
@@ -440,15 +434,11 @@ static int vega10_ih_self_irq(struct amdgpu_device *adev,
 			      struct amdgpu_irq_src *source,
 			      struct amdgpu_iv_entry *entry)
 {
-	uint32_t wptr = cpu_to_le32(entry->src_data[0]);
-
 	switch (entry->ring_id) {
 	case 1:
-		*adev->irq.ih1.wptr_cpu = wptr;
 		schedule_work(&adev->irq.ih1_work);
 		break;
 	case 2:
-		*adev->irq.ih2.wptr_cpu = wptr;
 		schedule_work(&adev->irq.ih2_work);
 		break;
 	default: break;
diff --git a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
index 5a3c867d5881..75b06e1964ab 100644
--- a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
@@ -220,10 +220,8 @@ static int vega20_ih_enable_ring(struct amdgpu_device *adev,
 	tmp = vega20_ih_rb_cntl(ih, tmp);
 	if (ih == &adev->irq.ih)
 		tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, RPTR_REARM, !!adev->irq.msi_enabled);
-	if (ih == &adev->irq.ih1) {
-		tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_ENABLE, 0);
+	if (ih == &adev->irq.ih1)
 		tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, RB_FULL_DRAIN_ENABLE, 1);
-	}
 	if (amdgpu_sriov_vf(adev)) {
 		if (psp_reg_program(&adev->psp, ih_regs->psp_reg_id, tmp)) {
 			dev_err(adev->dev, "PSP program IH_RB_CNTL failed!\n");
@@ -297,7 +295,6 @@ static int vega20_ih_irq_init(struct amdgpu_device *adev)
 	u32 ih_chicken;
 	int ret;
 	int i;
-	u32 tmp;
 
 	/* disable irqs */
 	ret = vega20_ih_toggle_interrupts(adev, false);
@@ -326,15 +323,6 @@ static int vega20_ih_irq_init(struct amdgpu_device *adev)
 		}
 	}
 
-	tmp = RREG32_SOC15(OSSSYS, 0, mmIH_STORM_CLIENT_LIST_CNTL);
-	tmp = REG_SET_FIELD(tmp, IH_STORM_CLIENT_LIST_CNTL,
-			    CLIENT18_IS_STORM_CLIENT, 1);
-	WREG32_SOC15(OSSSYS, 0, mmIH_STORM_CLIENT_LIST_CNTL, tmp);
-
-	tmp = RREG32_SOC15(OSSSYS, 0, mmIH_INT_FLOOD_CNTL);
-	tmp = REG_SET_FIELD(tmp, IH_INT_FLOOD_CNTL, FLOOD_CNTL_ENABLE, 1);
-	WREG32_SOC15(OSSSYS, 0, mmIH_INT_FLOOD_CNTL, tmp);
-
 	pci_set_master(adev->pdev);
 
 	/* enable interrupts */
@@ -380,11 +368,17 @@ static u32 vega20_ih_get_wptr(struct amdgpu_device *adev,
 	u32 wptr, tmp;
 	struct amdgpu_ih_regs *ih_regs;
 
-	wptr = le32_to_cpu(*ih->wptr_cpu);
-	ih_regs = &ih->ih_regs;
+	if (ih == &adev->irq.ih) {
+		/* Only ring0 supports writeback. On other rings fall back
+		 * to register-based code with overflow checking below.
+		 */
+		wptr = le32_to_cpu(*ih->wptr_cpu);
 
-	if (!REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW))
-		goto out;
+		if (!REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW))
+			goto out;
+	}
+
+	ih_regs = &ih->ih_regs;
 
 	/* Double check that the overflow wasn't already cleared. */
 	wptr = RREG32_NO_KIQ(ih_regs->ih_rb_wptr);
@@ -476,15 +470,11 @@ static int vega20_ih_self_irq(struct amdgpu_device *adev,
 			      struct amdgpu_irq_src *source,
 			      struct amdgpu_iv_entry *entry)
 {
-	uint32_t wptr = cpu_to_le32(entry->src_data[0]);
-
 	switch (entry->ring_id) {
 	case 1:
-		*adev->irq.ih1.wptr_cpu = wptr;
 		schedule_work(&adev->irq.ih1_work);
 		break;
 	case 2:
-		*adev->irq.ih2.wptr_cpu = wptr;
 		schedule_work(&adev->irq.ih2_work);
 		break;
 	default: break;
-- 
2.30.2

[PATCH AUTOSEL 5.12 048/134] drm/amdgpu: enable 48-bit IH timestamp counter

[Sasha Levin]

From: Alex Sierra <alex.sierra@amd.com>

[ Upstream commit 9a9c59a8f4f4478d5951eb0bded1d17b936aad6e ]

By default this timestamp is 32 bit counter. It gets
overflowed in around 10 minutes.

Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/amd/amdgpu/vega20_ih.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
index 75b06e1964ab..86dcf448e0c2 100644
--- a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
@@ -104,6 +104,8 @@ static int vega20_ih_toggle_ring_interrupts(struct amdgpu_device *adev,
 
 	tmp = RREG32(ih_regs->ih_rb_cntl);
 	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, RB_ENABLE, (enable ? 1 : 0));
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, RB_GPU_TS_ENABLE, 1);
+
 	/* enable_intr field is only valid in ring0 */
 	if (ih == &adev->irq.ih)
 		tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, ENABLE_INTR, (enable ? 1 : 0));
-- 
2.30.2

[PATCH AUTOSEL 5.12 049/134] drm/amdgpu: mask the xgmi number of hops reported from psp to kfd

[Sasha Levin]

From: Jonathan Kim <jonathan.kim@amd.com>

[ Upstream commit 4ac5617c4b7d0f0a8f879997f8ceaa14636d7554 ]

The psp supplies the link type in the upper 2 bits of the psp xgmi node
information num_hops field.  With a new link type, Aldebaran has these
bits set to a non-zero value (1 = xGMI3) so the KFD topology will report
the incorrect IO link weights without proper masking.
The actual number of hops is located in the 3 least significant bits of
this field so mask if off accordingly before passing it to the KFD.

Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Amber Lin <amber.lin@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index 659b385b27b5..4d3a24fdeb9c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -468,15 +468,22 @@ int amdgpu_xgmi_update_topology(struct amdgpu_hive_info *hive, struct amdgpu_dev
 }
 
 
+/*
+ * NOTE psp_xgmi_node_info.num_hops layout is as follows:
+ * num_hops[7:6] = link type (0 = xGMI2, 1 = xGMI3, 2/3 = reserved)
+ * num_hops[5:3] = reserved
+ * num_hops[2:0] = number of hops
+ */
 int amdgpu_xgmi_get_hops_count(struct amdgpu_device *adev,
 		struct amdgpu_device *peer_adev)
 {
 	struct psp_xgmi_topology_info *top = &adev->psp.xgmi_context.top_info;
+	uint8_t num_hops_mask = 0x7;
 	int i;
 
 	for (i = 0 ; i < top->num_nodes; ++i)
 		if (top->nodes[i].node_id == peer_adev->gmc.xgmi.node_id)
-			return top->nodes[i].num_hops;
+			return top->nodes[i].num_hops & num_hops_mask;
 	return	-EINVAL;
 }
 
-- 
2.30.2

[PATCH AUTOSEL 5.12 050/134] drm/amdkfd: Fix UBSAN shift-out-of-bounds warning

[Sasha Levin]

From: Anson Jacob <Anson.Jacob@amd.com>

[ Upstream commit 50e2fc36e72d4ad672032ebf646cecb48656efe0 ]

If get_num_sdma_queues or get_num_xgmi_sdma_queues is 0, we end up
doing a shift operation where the number of bits shifted equals
number of bits in the operand. This behaviour is undefined.

Set num_sdma_queues or num_xgmi_sdma_queues to ULLONG_MAX, if the
count is >= number of bits in the operand.

Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1472

Reported-by: Lyude Paul <lyude@redhat.com>
Signed-off-by: Anson Jacob <Anson.Jacob@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Tested-by: Lyude Paul <lyude@redhat.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../drm/amd/amdkfd/kfd_device_queue_manager.c   | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 4598a9a58125..a4266c4bca13 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -1128,6 +1128,9 @@ static int set_sched_resources(struct device_queue_manager *dqm)
 
 static int initialize_cpsch(struct device_queue_manager *dqm)
 {
+	uint64_t num_sdma_queues;
+	uint64_t num_xgmi_sdma_queues;
+
 	pr_debug("num of pipes: %d\n", get_pipes_per_mec(dqm));
 
 	mutex_init(&dqm->lock_hidden);
@@ -1136,8 +1139,18 @@ static int initialize_cpsch(struct device_queue_manager *dqm)
 	dqm->active_cp_queue_count = 0;
 	dqm->gws_queue_count = 0;
 	dqm->active_runlist = false;
-	dqm->sdma_bitmap = ~0ULL >> (64 - get_num_sdma_queues(dqm));
-	dqm->xgmi_sdma_bitmap = ~0ULL >> (64 - get_num_xgmi_sdma_queues(dqm));
+
+	num_sdma_queues = get_num_sdma_queues(dqm);
+	if (num_sdma_queues >= BITS_PER_TYPE(dqm->sdma_bitmap))
+		dqm->sdma_bitmap = ULLONG_MAX;
+	else
+		dqm->sdma_bitmap = (BIT_ULL(num_sdma_queues) - 1);
+
+	num_xgmi_sdma_queues = get_num_xgmi_sdma_queues(dqm);
+	if (num_xgmi_sdma_queues >= BITS_PER_TYPE(dqm->xgmi_sdma_bitmap))
+		dqm->xgmi_sdma_bitmap = ULLONG_MAX;
+	else
+		dqm->xgmi_sdma_bitmap = (BIT_ULL(num_xgmi_sdma_queues) - 1);
 
 	INIT_WORK(&dqm->hw_exception_work, kfd_process_hw_exception);
 
-- 
2.30.2

[PATCH AUTOSEL 5.12 051/134] drm/amd/display: Align cursor cache address to 2KB

[Sasha Levin]

From: Joshua Aberback <joshua.aberback@amd.com>

[ Upstream commit 554ba183b135ef09250b61a202d88512b5bbd03a ]

[Why]
The registers for the address of the cursor are aligned to 2KB, so all
cursor surfaces also need to be aligned to 2KB. Currently, the
provided cursor cache surface is not aligned, so we need a workaround
until alignment is enforced by the surface provider.

[How]
 - round up surface address to nearest multiple of 2048
 - current policy is to provide a much bigger cache size than
   necessary,so this operation is safe

Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Joshua Aberback <joshua.aberback@amd.com>
Reviewed-by: Jun Lei <Jun.Lei@amd.com>
Acked-by: Eryk Brol <eryk.brol@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
index 06dc1e2e8383..07c8d2e2c09c 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
@@ -848,7 +848,7 @@ bool dcn30_apply_idle_power_optimizations(struct dc *dc, bool enable)
 
 					cmd.mall.cursor_copy_src.quad_part = cursor_attr.address.quad_part;
 					cmd.mall.cursor_copy_dst.quad_part =
-							plane->address.grph.cursor_cache_addr.quad_part;
+							(plane->address.grph.cursor_cache_addr.quad_part + 2047) & ~2047;
 					cmd.mall.cursor_width = cursor_attr.width;
 					cmd.mall.cursor_height = cursor_attr.height;
 					cmd.mall.cursor_pitch = cursor_attr.pitch;
@@ -858,8 +858,7 @@ bool dcn30_apply_idle_power_optimizations(struct dc *dc, bool enable)
 					dc_dmub_srv_wait_idle(dc->ctx->dmub_srv);
 
 					/* Use copied cursor, and it's okay to not switch back */
-					cursor_attr.address.quad_part =
-							plane->address.grph.cursor_cache_addr.quad_part;
+					cursor_attr.address.quad_part = cmd.mall.cursor_copy_dst.quad_part;
 					dc_stream_set_cursor_attributes(stream, &cursor_attr);
 				}
 
-- 
2.30.2

[PATCH AUTOSEL 5.12 052/134] drm/amdgpu : Fix asic reset regression issue introduce by 8f211fe8ac7c4f

[Sasha Levin]

From: shaoyunl <shaoyun.liu@amd.com>

[ Upstream commit c8941550aa66b2a90f4b32c45d59e8571e33336e ]

This recent change introduce SDMA interrupt info printing with irq->process function.
These functions do not require a set function to enable/disable the irq

Signed-off-by: shaoyunl <shaoyun.liu@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
index afbbec82a289..9be945d8e72f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
@@ -535,7 +535,7 @@ void amdgpu_irq_gpu_reset_resume_helper(struct amdgpu_device *adev)
 		for (j = 0; j < AMDGPU_MAX_IRQ_SRC_ID; ++j) {
 			struct amdgpu_irq_src *src = adev->irq.client[i].sources[j];
 
-			if (!src)
+			if (!src || !src->funcs || !src->funcs->set)
 				continue;
 			for (k = 0; k < src->num_types; k++)
 				amdgpu_irq_update(adev, src, k);
-- 
2.30.2

[PATCH AUTOSEL 5.12 053/134] drm/amd/pm: fix workload mismatch on vega10

[Sasha Levin]

From: Kenneth Feng <kenneth.feng@amd.com>

[ Upstream commit 0979d43259e13846d86ba17e451e17fec185d240 ]

Workload number mapped to the correct one.
This issue is only on vega10.

Signed-off-by: Kenneth Feng <kenneth.feng@amd.com>
Reviewed-by: Kevin Wang <kevin1.wang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
index 599ec9726601..959143eff651 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
@@ -5160,7 +5160,7 @@ static int vega10_set_power_profile_mode(struct pp_hwmgr *hwmgr, long *input, ui
 
 out:
 	smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetWorkloadMask,
-						1 << power_profile_mode,
+						(!power_profile_mode) ? 0 : 1 << (power_profile_mode - 1),
 						NULL);
 	hwmgr->power_profile_mode = power_profile_mode;
 
-- 
2.30.2

[PATCH AUTOSEL 5.12 054/134] drm/amd/display: Fix UBSAN warning for not a valid value for type '_Bool'

[Sasha Levin]

From: Anson Jacob <Anson.Jacob@amd.com>

[ Upstream commit 6a30a92997eee49554f72b462dce90abe54a496f ]

[Why]
dc_cursor_position do not initialise position.translate_by_source when
crtc or plane->state->fb is NULL. UBSAN caught this error in
dce110_set_cursor_position, as the value was garbage.

[How]
Initialise dc_cursor_position structure elements to 0 in handle_cursor_update
before calling get_cursor_position.

Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1471
Reported-by: Lyude Paul <lyude@redhat.com>
Signed-off-by: Anson Jacob <Anson.Jacob@amd.com>
Reviewed-by: Aurabindo Jayamohanan Pillai <Aurabindo.Pillai@amd.com>
Acked-by: Solomon Chiu <solomon.chiu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 8ad83ccfcc6a..167e04ab9d5b 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -7417,10 +7417,6 @@ static int get_cursor_position(struct drm_plane *plane, struct drm_crtc *crtc,
 	int x, y;
 	int xorigin = 0, yorigin = 0;
 
-	position->enable = false;
-	position->x = 0;
-	position->y = 0;
-
 	if (!crtc || !plane->state->fb)
 		return 0;
 
@@ -7467,7 +7463,7 @@ static void handle_cursor_update(struct drm_plane *plane,
 	struct dm_crtc_state *crtc_state = crtc ? to_dm_crtc_state(crtc->state) : NULL;
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	uint64_t address = afb ? afb->address : 0;
-	struct dc_cursor_position position;
+	struct dc_cursor_position position = {0};
 	struct dc_cursor_attributes attributes;
 	int ret;
 
-- 
2.30.2

[PATCH AUTOSEL 5.12 055/134] drm/amd/display: DCHUB underflow counter increasing in some scenarios

[Sasha Levin]

From: Aric Cyr <aric.cyr@amd.com>

[ Upstream commit 4710430a779e6077d81218ac768787545bff8c49 ]

[Why]
When unplugging a display, the underflow counter can be seen to
increase because PSTATE switch is allowed even when some planes are not
blanked.

[How]
Check that all planes are not active instead of all streams before
allowing PSTATE change.

Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Aric Cyr <aric.cyr@amd.com>
Acked-by: Solomon Chiu <solomon.chiu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c
index c7e5a64e06af..81ea5d3a1947 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c
@@ -252,6 +252,7 @@ static void dcn3_update_clocks(struct clk_mgr *clk_mgr_base,
 	bool force_reset = false;
 	bool update_uclk = false;
 	bool p_state_change_support;
+	int total_plane_count;
 
 	if (dc->work_arounds.skip_clock_update || !clk_mgr->smu_present)
 		return;
@@ -292,7 +293,8 @@ static void dcn3_update_clocks(struct clk_mgr *clk_mgr_base,
 		clk_mgr_base->clks.socclk_khz = new_clocks->socclk_khz;
 
 	clk_mgr_base->clks.prev_p_state_change_support = clk_mgr_base->clks.p_state_change_support;
-	p_state_change_support = new_clocks->p_state_change_support || (display_count == 0);
+	total_plane_count = clk_mgr_helper_get_active_plane_cnt(dc, context);
+	p_state_change_support = new_clocks->p_state_change_support || (total_plane_count == 0);
 	if (should_update_pstate_support(safe_to_lower, p_state_change_support, clk_mgr_base->clks.p_state_change_support)) {
 		clk_mgr_base->clks.p_state_change_support = p_state_change_support;
 
-- 
2.30.2

[PATCH AUTOSEL 5.12 056/134] drm/amd/display: fix dml prefetch validation

[Sasha Levin]

From: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>

[ Upstream commit 8ee0fea4baf90e43efe2275de208a7809f9985bc ]

Incorrect variable used, missing initialization during validation.

Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Eric Bernstein <Eric.Bernstein@amd.com>
Acked-by: Solomon Chiu <solomon.chiu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c   | 1 +
 drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c
index 0f3f510fd83b..9729cf292e84 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c
@@ -3437,6 +3437,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 			mode_lib->vba.DCCEnabledInAnyPlane = true;
 		}
 	}
+	mode_lib->vba.UrgentLatency = mode_lib->vba.UrgentLatencyPixelDataOnly;
 	for (i = 0; i <= mode_lib->vba.soc.num_states; i++) {
 		locals->FabricAndDRAMBandwidthPerState[i] = dml_min(
 				mode_lib->vba.DRAMSpeedPerState[i] * mode_lib->vba.NumberOfChannels
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c
index 210c96cd5b03..51098c2c9854 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c
@@ -3544,6 +3544,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 			mode_lib->vba.DCCEnabledInAnyPlane = true;
 		}
 	}
+	mode_lib->vba.UrgentLatency = mode_lib->vba.UrgentLatencyPixelDataOnly;
 	for (i = 0; i <= mode_lib->vba.soc.num_states; i++) {
 		locals->FabricAndDRAMBandwidthPerState[i] = dml_min(
 				mode_lib->vba.DRAMSpeedPerState[i] * mode_lib->vba.NumberOfChannels
-- 
2.30.2

[PATCH AUTOSEL 5.12 057/134] drm/amd/display: Fix potential memory leak

[Sasha Levin]

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

[ Upstream commit 51ba691206e35464fd7ec33dd519d141c80b5dff ]

[Why]
vblank_workqueue is never released.

[How]
Free it upon dm finish.

Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Qingqing Zhuo <qingqing.zhuo@amd.com>
Reviewed-by: Nicholas Kazlauskas <Nicholas.Kazlauskas@amd.com>
Acked-by: Solomon Chiu <solomon.chiu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 167e04ab9d5b..9c243f66867a 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -1191,6 +1191,15 @@ static void amdgpu_dm_fini(struct amdgpu_device *adev)
 	if (adev->dm.dc)
 		dc_deinit_callbacks(adev->dm.dc);
 #endif
+
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+	if (adev->dm.vblank_workqueue) {
+		adev->dm.vblank_workqueue->dm = NULL;
+		kfree(adev->dm.vblank_workqueue);
+		adev->dm.vblank_workqueue = NULL;
+	}
+#endif
+
 	if (adev->dm.dc->ctx->dmub_srv) {
 		dc_dmub_srv_destroy(&adev->dm.dc->ctx->dmub_srv);
 		adev->dm.dc->ctx->dmub_srv = NULL;
-- 
2.30.2

[PATCH AUTOSEL 5.12 058/134] drm/amdgpu: Fix memory leak

[Sasha Levin]

From: xinhui pan <xinhui.pan@amd.com>

[ Upstream commit 79fcd446e7e182c52c2c808c76f8de3eb6714349 ]

drm_gem_object_put() should be paired with drm_gem_object_lookup().

All gem objs are saved in fb->base.obj[]. Need put the old first before
assign a new obj.

Trigger VRAM leak by running command below
$ service gdm restart

Signed-off-by: xinhui pan <xinhui.pan@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_display.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index f753e04fee99..cbe050436c7b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -910,8 +910,9 @@ int amdgpu_display_framebuffer_init(struct drm_device *dev,
 	}
 
 	for (i = 1; i < rfb->base.format->num_planes; ++i) {
+		drm_gem_object_get(rfb->base.obj[0]);
+		drm_gem_object_put(rfb->base.obj[i]);
 		rfb->base.obj[i] = rfb->base.obj[0];
-		drm_gem_object_get(rfb->base.obj[i]);
 	}
 
 	return 0;
@@ -960,6 +961,7 @@ amdgpu_display_user_framebuffer_create(struct drm_device *dev,
 		return ERR_PTR(ret);
 	}
 
+	drm_gem_object_put(obj);
 	return &amdgpu_fb->base;
 }
 
-- 
2.30.2

[PATCH AUTOSEL 5.12 059/134] scsi: qla2xxx: Always check the return value of qla24xx_get_isp_stats()

[Sasha Levin]

From: Bart Van Assche <bvanassche@acm.org>

[ Upstream commit a2b2cc660822cae08c351c7f6b452bfd1330a4f7 ]

This patch fixes the following Coverity warning:

    CID 361199 (#1 of 1): Unchecked return value (CHECKED_RETURN)
    3. check_return: Calling qla24xx_get_isp_stats without checking return
    value (as is done elsewhere 4 out of 5 times).

Link: https://lore.kernel.org/r/20210320232359.941-7-bvanassche@acm.org
Cc: Quinn Tran <qutran@marvell.com>
Cc: Mike Christie <michael.christie@oracle.com>
Cc: Himanshu Madhani <himanshu.madhani@oracle.com>
Cc: Daniel Wagner <dwagner@suse.de>
Cc: Lee Duncan <lduncan@suse.com>
Reviewed-by: Daniel Wagner <dwagner@suse.de>
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/qla2xxx/qla_attr.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c
index 63391c9be05d..3aa9869f6fae 100644
--- a/drivers/scsi/qla2xxx/qla_attr.c
+++ b/drivers/scsi/qla2xxx/qla_attr.c
@@ -2864,6 +2864,8 @@ qla2x00_reset_host_stats(struct Scsi_Host *shost)
 	vha->qla_stats.jiffies_at_last_reset = get_jiffies_64();
 
 	if (IS_FWI2_CAPABLE(ha)) {
+		int rval;
+
 		stats = dma_alloc_coherent(&ha->pdev->dev,
 		    sizeof(*stats), &stats_dma, GFP_KERNEL);
 		if (!stats) {
@@ -2873,7 +2875,11 @@ qla2x00_reset_host_stats(struct Scsi_Host *shost)
 		}
 
 		/* reset firmware statistics */
-		qla24xx_get_isp_stats(base_vha, stats, stats_dma, BIT_0);
+		rval = qla24xx_get_isp_stats(base_vha, stats, stats_dma, BIT_0);
+		if (rval != QLA_SUCCESS)
+			ql_log(ql_log_warn, vha, 0x70de,
+			       "Resetting ISP statistics failed: rval = %d\n",
+			       rval);
 
 		dma_free_coherent(&ha->pdev->dev, sizeof(*stats),
 		    stats, stats_dma);
-- 
2.30.2

[PATCH AUTOSEL 5.12 060/134] drm/vkms: fix misuse of WARN_ON

[Sasha Levin]

From: Dmitry Vyukov <dvyukov@google.com>

[ Upstream commit b4142fc4d52d051d4d8df1fb6c569e5b445d369e ]

vkms_vblank_simulate() uses WARN_ON for timing-dependent condition
(timer overrun). This is a mis-use of WARN_ON, WARN_ON must be used
to denote kernel bugs. Use pr_warn() instead.

Signed-off-by: Dmitry Vyukov <dvyukov@google.com>
Reported-by: syzbot+4fc21a003c8332eb0bdd@syzkaller.appspotmail.com
Cc: Rodrigo Siqueira <rodrigosiqueiramelo@gmail.com>
Cc: Melissa Wen <melissa.srw@gmail.com>
Cc: Haneen Mohammed <hamohammed.sa@gmail.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: David Airlie <airlied@linux.ie>
Cc: dri-devel@lists.freedesktop.org
Cc: linux-kernel@vger.kernel.org
Acked-by: Melissa Wen <melissa.srw@gmail.com>
Signed-off-by: Melissa Wen <melissa.srw@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210320132840.1315853-1-dvyukov@google.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/vkms/vkms_crtc.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/vkms/vkms_crtc.c b/drivers/gpu/drm/vkms/vkms_crtc.c
index 0443b7deeaef..758d8a98d96b 100644
--- a/drivers/gpu/drm/vkms/vkms_crtc.c
+++ b/drivers/gpu/drm/vkms/vkms_crtc.c
@@ -18,7 +18,8 @@ static enum hrtimer_restart vkms_vblank_simulate(struct hrtimer *timer)
 
 	ret_overrun = hrtimer_forward_now(&output->vblank_hrtimer,
 					  output->period_ns);
-	WARN_ON(ret_overrun != 1);
+	if (ret_overrun != 1)
+		pr_warn("%s: vblank timer overrun\n", __func__);
 
 	spin_lock(&output->lock);
 	ret = drm_crtc_handle_vblank(crtc);
-- 
2.30.2

[PATCH AUTOSEL 5.12 061/134] block, bfq: fix weight-raising resume with !low_latency

[Sasha Levin]

From: Paolo Valente <paolo.valente@linaro.org>

[ Upstream commit 8c544770092a3d7532d01903b75721e537d87001 ]

When the io_latency heuristic is off, bfq_queues must not start to be
weight-raised. Unfortunately, by mistake, this may happen when the
state of a previously weight-raised bfq_queue is resumed after a queue
split. This commit fixes this error.

Tested-by: Jan Kara <jack@suse.cz>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Link: https://lore.kernel.org/r/20210304174627.161-5-paolo.valente@linaro.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 block/bfq-iosched.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 95586137194e..20ba5db0f61c 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -1012,7 +1012,7 @@ static void
 bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_data *bfqd,
 		      struct bfq_io_cq *bic, bool bfq_already_existing)
 {
-	unsigned int old_wr_coeff = bfqq->wr_coeff;
+	unsigned int old_wr_coeff = 1;
 	bool busy = bfq_already_existing && bfq_bfqq_busy(bfqq);
 
 	if (bic->saved_has_short_ttime)
@@ -1033,7 +1033,13 @@ bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_data *bfqd,
 	bfqq->ttime = bic->saved_ttime;
 	bfqq->io_start_time = bic->saved_io_start_time;
 	bfqq->tot_idle_time = bic->saved_tot_idle_time;
-	bfqq->wr_coeff = bic->saved_wr_coeff;
+	/*
+	 * Restore weight coefficient only if low_latency is on
+	 */
+	if (bfqd->low_latency) {
+		old_wr_coeff = bfqq->wr_coeff;
+		bfqq->wr_coeff = bic->saved_wr_coeff;
+	}
 	bfqq->service_from_wr = bic->saved_service_from_wr;
 	bfqq->wr_start_at_switch_to_srt = bic->saved_wr_start_at_switch_to_srt;
 	bfqq->last_wr_start_finish = bic->saved_last_wr_start_finish;
-- 
2.30.2

[PATCH AUTOSEL 5.12 062/134] scsi: qla2xxx: Fix use after free in bsg

[Sasha Levin]

From: Quinn Tran <qutran@marvell.com>

[ Upstream commit 2ce35c0821afc2acd5ee1c3f60d149f8b2520ce8 ]

On bsg command completion, bsg_job_done() was called while qla driver
continued to access the bsg_job buffer. bsg_job_done() would free up
resources that ended up being reused by other task while the driver
continued to access the buffers. As a result, driver was reading garbage
data.

localhost kernel: BUG: KASAN: use-after-free in sg_next+0x64/0x80
localhost kernel: Read of size 8 at addr ffff8883228a3330 by task swapper/26/0
localhost kernel:
localhost kernel: CPU: 26 PID: 0 Comm: swapper/26 Kdump:
loaded Tainted: G          OE    --------- -  - 4.18.0-193.el8.x86_64+debug #1
localhost kernel: Hardware name: HP ProLiant DL360
Gen9/ProLiant DL360 Gen9, BIOS P89 08/12/2016
localhost kernel: Call Trace:
localhost kernel: <IRQ>
localhost kernel: dump_stack+0x9a/0xf0
localhost kernel: print_address_description.cold.3+0x9/0x23b
localhost kernel: kasan_report.cold.4+0x65/0x95
localhost kernel: debug_dma_unmap_sg.part.12+0x10d/0x2d0
localhost kernel: qla2x00_bsg_sp_free+0xaf6/0x1010 [qla2xxx]

Link: https://lore.kernel.org/r/20210329085229.4367-6-njavali@marvell.com
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Quinn Tran <qutran@marvell.com>
Signed-off-by: Saurav Kashyap <skashyap@marvell.com>
Signed-off-by: Nilesh Javali <njavali@marvell.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/qla2xxx/qla_bsg.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/qla2xxx/qla_bsg.c b/drivers/scsi/qla2xxx/qla_bsg.c
index bee8cf9f8123..d021e51344f5 100644
--- a/drivers/scsi/qla2xxx/qla_bsg.c
+++ b/drivers/scsi/qla2xxx/qla_bsg.c
@@ -25,10 +25,11 @@ void qla2x00_bsg_job_done(srb_t *sp, int res)
 	struct bsg_job *bsg_job = sp->u.bsg_job;
 	struct fc_bsg_reply *bsg_reply = bsg_job->reply;
 
+	sp->free(sp);
+
 	bsg_reply->result = res;
 	bsg_job_done(bsg_job, bsg_reply->result,
 		       bsg_reply->reply_payload_rcv_len);
-	sp->free(sp);
 }
 
 void qla2x00_bsg_sp_free(srb_t *sp)
-- 
2.30.2

[PATCH AUTOSEL 5.12 063/134] mmc: sdhci-esdhc-imx: validate pinctrl before use it

[Sasha Levin]

From: Peng Fan <peng.fan@nxp.com>

[ Upstream commit f410ee0aa2df050a9505f5c261953e9b18e21206 ]

When imx_data->pinctrl is not a valid pointer, pinctrl_lookup_state
will trigger kernel panic.

When we boot Dual OS on Jailhouse hypervisor, we let the 1st Linux to
configure pinmux ready for the 2nd OS, so the 2nd OS not have pinctrl
settings.

Similar to this commit b62eee9f804e ("mmc: sdhci-esdhc-imx: no fail when no pinctrl available").

Reviewed-by: Bough Chen <haobo.chen@nxp.com>
Reviewed-by: Alice Guo <alice.guo@nxp.com>
Signed-off-by: Peng Fan <peng.fan@nxp.com>
Link: https://lore.kernel.org/r/1614222604-27066-6-git-send-email-peng.fan@oss.nxp.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/mmc/host/sdhci-esdhc-imx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c
index a20459744d21..94327988da91 100644
--- a/drivers/mmc/host/sdhci-esdhc-imx.c
+++ b/drivers/mmc/host/sdhci-esdhc-imx.c
@@ -1488,7 +1488,7 @@ sdhci_esdhc_imx_probe_dt(struct platform_device *pdev,
 
 	mmc_of_parse_voltage(np, &host->ocr_mask);
 
-	if (esdhc_is_usdhc(imx_data)) {
+	if (esdhc_is_usdhc(imx_data) && !IS_ERR(imx_data->pinctrl)) {
 		imx_data->pins_100mhz = pinctrl_lookup_state(imx_data->pinctrl,
 						ESDHC_PINCTRL_STATE_100MHZ);
 		imx_data->pins_200mhz = pinctrl_lookup_state(imx_data->pinctrl,
-- 
2.30.2

[PATCH AUTOSEL 5.12 064/134] mmc: sdhci-pci: Add PCI IDs for Intel LKF

[Sasha Levin]

From: Adrian Hunter <adrian.hunter@intel.com>

[ Upstream commit ee629112be8b4eff71d4d3d108a28bc7dc877e13 ]

Add PCI IDs for Intel LKF eMMC and SD card host controllers.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Link: https://lore.kernel.org/r/20210322055356.24923-1-adrian.hunter@intel.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/mmc/host/sdhci-pci-core.c | 2 ++
 drivers/mmc/host/sdhci-pci.h      | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c
index 9552708846ca..393e6251b3c3 100644
--- a/drivers/mmc/host/sdhci-pci-core.c
+++ b/drivers/mmc/host/sdhci-pci-core.c
@@ -1903,6 +1903,8 @@ static const struct pci_device_id pci_ids[] = {
 	SDHCI_PCI_DEVICE(INTEL, CMLH_SD,   intel_byt_sd),
 	SDHCI_PCI_DEVICE(INTEL, JSL_EMMC,  intel_glk_emmc),
 	SDHCI_PCI_DEVICE(INTEL, JSL_SD,    intel_byt_sd),
+	SDHCI_PCI_DEVICE(INTEL, LKF_EMMC,  intel_glk_emmc),
+	SDHCI_PCI_DEVICE(INTEL, LKF_SD,    intel_byt_sd),
 	SDHCI_PCI_DEVICE(O2, 8120,     o2),
 	SDHCI_PCI_DEVICE(O2, 8220,     o2),
 	SDHCI_PCI_DEVICE(O2, 8221,     o2),
diff --git a/drivers/mmc/host/sdhci-pci.h b/drivers/mmc/host/sdhci-pci.h
index d0ed232af0eb..8f90c4163bb5 100644
--- a/drivers/mmc/host/sdhci-pci.h
+++ b/drivers/mmc/host/sdhci-pci.h
@@ -57,6 +57,8 @@
 #define PCI_DEVICE_ID_INTEL_CMLH_SD	0x06f5
 #define PCI_DEVICE_ID_INTEL_JSL_EMMC	0x4dc4
 #define PCI_DEVICE_ID_INTEL_JSL_SD	0x4df8
+#define PCI_DEVICE_ID_INTEL_LKF_EMMC	0x98c4
+#define PCI_DEVICE_ID_INTEL_LKF_SD	0x98f8
 
 #define PCI_DEVICE_ID_SYSKONNECT_8000	0x8000
 #define PCI_DEVICE_ID_VIA_95D0		0x95d0
-- 
2.30.2

[PATCH AUTOSEL 5.12 065/134] mmc: sdhci-brcmstb: Remove CQE quirk

[Sasha Levin]

From: Al Cooper <alcooperx@gmail.com>

[ Upstream commit f0bdf98fab058efe7bf49732f70a0f26d1143154 ]

Remove the CQHCI_QUIRK_SHORT_TXFR_DESC_SZ quirk because the
latest chips have this fixed and earlier chips have other
CQE problems that prevent the feature from being enabled.

Signed-off-by: Al Cooper <alcooperx@gmail.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Link: https://lore.kernel.org/r/20210325192834.42955-1-alcooperx@gmail.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/mmc/host/sdhci-brcmstb.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/mmc/host/sdhci-brcmstb.c b/drivers/mmc/host/sdhci-brcmstb.c
index f9780c65ebe9..f24623aac2db 100644
--- a/drivers/mmc/host/sdhci-brcmstb.c
+++ b/drivers/mmc/host/sdhci-brcmstb.c
@@ -199,7 +199,6 @@ static int sdhci_brcmstb_add_host(struct sdhci_host *host,
 	if (dma64) {
 		dev_dbg(mmc_dev(host->mmc), "Using 64 bit DMA\n");
 		cq_host->caps |= CQHCI_TASK_DESC_SZ_128;
-		cq_host->quirks |= CQHCI_QUIRK_SHORT_TXFR_DESC_SZ;
 	}
 
 	ret = cqhci_init(cq_host, host->mmc, dma64);
-- 
2.30.2

[PATCH AUTOSEL 5.12 066/134] ata: ahci: Disable SXS for Hisilicon Kunpeng920

[Sasha Levin]

From: Xingui Yang <yangxingui@huawei.com>

[ Upstream commit 234e6d2c18f5b080cde874483c4c361f3ae7cffe ]

On Hisilicon Kunpeng920, ESP is set to 1 by default for all ports of
SATA controller. In some scenarios, some ports are not external SATA ports,
and it cause disks connected to these ports to be identified as removable
disks. So disable the SXS capability on the software side to prevent users
from mistakenly considering non-removable disks as removable disks and
performing related operations.

Signed-off-by: Xingui Yang <yangxingui@huawei.com>
Signed-off-by: Luo Jiaxing <luojiaxing@huawei.com>
Reviewed-by: John Garry <john.garry@huawei.com>
Link: https://lore.kernel.org/r/1615544676-61926-1-git-send-email-luojiaxing@huawei.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/ata/ahci.c    | 5 +++++
 drivers/ata/ahci.h    | 1 +
 drivers/ata/libahci.c | 5 +++++
 3 files changed, 11 insertions(+)

diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 00ba8e5a1ccc..33192a8f687d 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -1772,6 +1772,11 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		hpriv->flags |= AHCI_HFLAG_NO_DEVSLP;
 
 #ifdef CONFIG_ARM64
+	if (pdev->vendor == PCI_VENDOR_ID_HUAWEI &&
+	    pdev->device == 0xa235 &&
+	    pdev->revision < 0x30)
+		hpriv->flags |= AHCI_HFLAG_NO_SXS;
+
 	if (pdev->vendor == 0x177d && pdev->device == 0xa01c)
 		hpriv->irq_handler = ahci_thunderx_irq_handler;
 #endif
diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h
index 98b8baa47dc5..d1f284f0c83d 100644
--- a/drivers/ata/ahci.h
+++ b/drivers/ata/ahci.h
@@ -242,6 +242,7 @@ enum {
 							suspend/resume */
 	AHCI_HFLAG_IGN_NOTSUPP_POWER_ON	= (1 << 27), /* ignore -EOPNOTSUPP
 							from phy_power_on() */
+	AHCI_HFLAG_NO_SXS		= (1 << 28), /* SXS not supported */
 
 	/* ap->flags bits */
 
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index ea5bf5f4cbed..fec2e9754aed 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -493,6 +493,11 @@ void ahci_save_initial_config(struct device *dev, struct ahci_host_priv *hpriv)
 		cap |= HOST_CAP_ALPM;
 	}
 
+	if ((cap & HOST_CAP_SXS) && (hpriv->flags & AHCI_HFLAG_NO_SXS)) {
+		dev_info(dev, "controller does not support SXS, disabling CAP_SXS\n");
+		cap &= ~HOST_CAP_SXS;
+	}
+
 	if (hpriv->force_port_map && port_map != hpriv->force_port_map) {
 		dev_info(dev, "forcing port_map 0x%x -> 0x%x\n",
 			 port_map, hpriv->force_port_map);
-- 
2.30.2