[PATCH AUTOSEL 5.18 002/159] drm/selftests: fix a shift-out-of-bounds bug

[PATCH AUTOSEL 5.18 002/159] drm/selftests: fix a shift-out-of-bounds bug

[Sasha Levin]

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

[ Upstream commit fc3785fb56a27304c769af730d079f4337d4dc76 ]

pass the correct size value computed using the max_order.

<log snip>

[ 68.124177][ T1] UBSAN: shift-out-of-bounds in include/linux/log2.h:67:13
[ 68.125333][ T1] shift exponent 4294967295 is too large for 32-bit type 'long
unsigned int'
[ 68.126563][ T1] CPU: 0 PID: 1 Comm: swapper Not tainted
5.17.0-rc2-00311-g39ec47bbfd5d #2
[ 68.127758][ T1] Call Trace:
[ 68.128187][ T1] dump_stack_lvl (lib/dump_stack.c:108)
[ 68.128793][ T1] dump_stack (lib/dump_stack.c:114)
[ 68.129331][ T1] ubsan_epilogue (lib/ubsan.c:152)
[ 68.129958][ T1] __ubsan_handle_shift_out_of_bounds.cold (arch/x86/include/asm/smap.h:85)

[ 68.130791][ T1] ? drm_block_alloc+0x28/0x80
[ 68.131582][ T1] ? rcu_read_lock_sched_held (kernel/rcu/update.c:125)
[ 68.132215][ T1] ? kmem_cache_alloc (include/trace/events/kmem.h:54 mm/slab.c:3501)
[ 68.132878][ T1] ? mark_free+0x2e/0x80
[ 68.133524][ T1] drm_buddy_init.cold (include/linux/log2.h:67
drivers/gpu/drm/drm_buddy.c:131)
[ 68.134145][ T1] ? test_drm_cmdline_init (drivers/gpu/drm/selftests/test-drm_buddy.c:87)

[ 68.134770][ T1] igt_buddy_alloc_limit (drivers/gpu/drm/selftests/test-drm_buddy.c:30)
[ 68.135472][ T1] ? vprintk_default (kernel/printk/printk.c:2257)
[ 68.136057][ T1] ? test_drm_cmdline_init (drivers/gpu/drm/selftests/test-drm_buddy.c:87)

[ 68.136812][ T1] test_drm_buddy_init (drivers/gpu/drm/selftests/drm_selftest.c:77
drivers/gpu/drm/selftests/test-drm_buddy.c:95)
[ 68.137475][ T1] do_one_initcall (init/main.c:1300)
[ 68.138111][ T1] ? parse_args (kernel/params.c:609 kernel/params.c:146
kernel/params.c:188)
[ 68.138717][ T1] do_basic_setup (init/main.c:1372 init/main.c:1389 init/main.c:1408)
[ 68.139366][ T1] kernel_init_freeable (init/main.c:1617)
[ 68.140040][ T1] ? rest_init (init/main.c:1494)
[ 68.140634][ T1] kernel_init (init/main.c:1504)
[ 68.141155][ T1] ret_from_fork (arch/x86/entry/entry_32.S:772)
[ 68.141607][ T1]
================================================================================
[ 68.146730][ T1] ------------[ cut here ]------------
[ 68.147460][ T1] kernel BUG at drivers/gpu/drm/drm_buddy.c:140!
[ 68.148280][ T1] invalid opcode: 0000 [#1]
[ 68.148895][ T1] CPU: 0 PID: 1 Comm: swapper Not tainted
5.17.0-rc2-00311-g39ec47bbfd5d #2
[ 68.149896][ T1] EIP: drm_buddy_init (drivers/gpu/drm/drm_buddy.c:140 (discriminator 1))

For more details: https://lists.01.org/hyperkitty/list/lkp@lists.01.org/thread/FDIF3HCILZNN5UQAZMOR7E3MQSMHHKWU/

Signed-off-by: Arunpravin <Arunpravin.PaneerSelvam@amd.com>
Reported-by: kernel test robot <oliver.sang@intel.com>
Acked-by: Christian König <christian.koenig@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220303201602.2365-1-Arunpravin.PaneerSelvam@amd.com
Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/selftests/test-drm_buddy.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/selftests/test-drm_buddy.c b/drivers/gpu/drm/selftests/test-drm_buddy.c
index fa997f89522b..913cbd7eae04 100644
--- a/drivers/gpu/drm/selftests/test-drm_buddy.c
+++ b/drivers/gpu/drm/selftests/test-drm_buddy.c
@@ -902,14 +902,13 @@ static int igt_buddy_alloc_range(void *arg)
 
 static int igt_buddy_alloc_limit(void *arg)
 {
-	u64 end, size = U64_MAX, start = 0;
+	u64 size = U64_MAX, start = 0;
 	struct drm_buddy_block *block;
 	unsigned long flags = 0;
 	LIST_HEAD(allocated);
 	struct drm_buddy mm;
 	int err;
 
-	size = end = round_down(size, 4096);
 	err = drm_buddy_init(&mm, size, PAGE_SIZE);
 	if (err)
 		return err;
@@ -921,7 +920,8 @@ static int igt_buddy_alloc_limit(void *arg)
 		goto out_fini;
 	}
 
-	err = drm_buddy_alloc_blocks(&mm, start, end, size,
+	size = mm.chunk_size << mm.max_order;
+	err = drm_buddy_alloc_blocks(&mm, start, size, size,
 				     PAGE_SIZE, &allocated, flags);
 
 	if (unlikely(err))
-- 
2.35.1

[PATCH AUTOSEL 5.18 003/159] drm/vmwgfx: validate the screen formats

[Sasha Levin]

From: Zack Rusin <zackr@vmware.com>

[ Upstream commit 8bb75aeb58bd688d70827ae179bd3da57b6d975b ]

The kms code wasn't validating the modifiers and was letting through
unsupported formats. rgb8 was never properly supported and has no
matching svga screen target format so remove it.
This fixes format/modifier failures in kms_addfb_basic from IGT.

Signed-off-by: Zack Rusin <zackr@vmware.com>
Reviewed-by: Martin Krastev <krastevm@vmware.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220318174332.440068-4-zack@kde.org
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_kms.c | 30 +++++++++++++++--------------
 drivers/gpu/drm/vmwgfx/vmwgfx_kms.h |  1 -
 2 files changed, 16 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index 93431e8f6606..9410152f9d6f 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -914,6 +914,15 @@ static int vmw_kms_new_framebuffer_surface(struct vmw_private *dev_priv,
 	 * Sanity checks.
 	 */
 
+	if (!drm_any_plane_has_format(&dev_priv->drm,
+				      mode_cmd->pixel_format,
+				      mode_cmd->modifier[0])) {
+		drm_dbg(&dev_priv->drm,
+			"unsupported pixel format %p4cc / modifier 0x%llx\n",
+			&mode_cmd->pixel_format, mode_cmd->modifier[0]);
+		return -EINVAL;
+	}
+
 	/* Surface must be marked as a scanout. */
 	if (unlikely(!surface->metadata.scanout))
 		return -EINVAL;
@@ -1236,20 +1245,13 @@ static int vmw_kms_new_framebuffer_bo(struct vmw_private *dev_priv,
 		return -EINVAL;
 	}
 
-	/* Limited framebuffer color depth support for screen objects */
-	if (dev_priv->active_display_unit == vmw_du_screen_object) {
-		switch (mode_cmd->pixel_format) {
-		case DRM_FORMAT_XRGB8888:
-		case DRM_FORMAT_ARGB8888:
-			break;
-		case DRM_FORMAT_XRGB1555:
-		case DRM_FORMAT_RGB565:
-			break;
-		default:
-			DRM_ERROR("Invalid pixel format: %p4cc\n",
-				  &mode_cmd->pixel_format);
-			return -EINVAL;
-		}
+	if (!drm_any_plane_has_format(&dev_priv->drm,
+				      mode_cmd->pixel_format,
+				      mode_cmd->modifier[0])) {
+		drm_dbg(&dev_priv->drm,
+			"unsupported pixel format %p4cc / modifier 0x%llx\n",
+			&mode_cmd->pixel_format, mode_cmd->modifier[0]);
+		return -EINVAL;
 	}
 
 	vfbd = kzalloc(sizeof(*vfbd), GFP_KERNEL);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
index 4d36e8507380..d9ebd02099a6 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
@@ -247,7 +247,6 @@ struct vmw_framebuffer_bo {
 static const uint32_t __maybe_unused vmw_primary_plane_formats[] = {
 	DRM_FORMAT_XRGB1555,
 	DRM_FORMAT_RGB565,
-	DRM_FORMAT_RGB888,
 	DRM_FORMAT_XRGB8888,
 	DRM_FORMAT_ARGB8888,
 };
-- 
2.35.1

[PATCH AUTOSEL 5.18 005/159] drm/virtio: fix NULL pointer dereference in virtio_gpu_conn_get_modes

[Sasha Levin]

From: Liu Zixian <liuzixian4@huawei.com>

[ Upstream commit 194d250cdc4a40ccbd179afd522a9e9846957402 ]

drm_cvt_mode may return NULL and we should check it.

This bug is found by syzkaller:

FAULT_INJECTION stacktrace:
[  168.567394] FAULT_INJECTION: forcing a failure.
name failslab, interval 1, probability 0, space 0, times 1
[  168.567403] CPU: 1 PID: 6425 Comm: syz Kdump: loaded Not tainted 4.19.90-vhulk2201.1.0.h1035.kasan.eulerosv2r10.aarch64 #1
[  168.567406] Hardware name: QEMU KVM Virtual Machine, BIOS 0.0.0 02/06/2015
[  168.567408] Call trace:
[  168.567414]  dump_backtrace+0x0/0x310
[  168.567418]  show_stack+0x28/0x38
[  168.567423]  dump_stack+0xec/0x15c
[  168.567427]  should_fail+0x3ac/0x3d0
[  168.567437]  __should_failslab+0xb8/0x120
[  168.567441]  should_failslab+0x28/0xc0
[  168.567445]  kmem_cache_alloc_trace+0x50/0x640
[  168.567454]  drm_mode_create+0x40/0x90
[  168.567458]  drm_cvt_mode+0x48/0xc78
[  168.567477]  virtio_gpu_conn_get_modes+0xa8/0x140 [virtio_gpu]
[  168.567485]  drm_helper_probe_single_connector_modes+0x3a4/0xd80
[  168.567492]  drm_mode_getconnector+0x2e0/0xa70
[  168.567496]  drm_ioctl_kernel+0x11c/0x1d8
[  168.567514]  drm_ioctl+0x558/0x6d0
[  168.567522]  do_vfs_ioctl+0x160/0xf30
[  168.567525]  ksys_ioctl+0x98/0xd8
[  168.567530]  __arm64_sys_ioctl+0x50/0xc8
[  168.567536]  el0_svc_common+0xc8/0x320
[  168.567540]  el0_svc_handler+0xf8/0x160
[  168.567544]  el0_svc+0x10/0x218

KASAN stacktrace:
[  168.567561] BUG: KASAN: null-ptr-deref in virtio_gpu_conn_get_modes+0xb4/0x140 [virtio_gpu]
[  168.567565] Read of size 4 at addr 0000000000000054 by task syz/6425
[  168.567566]
[  168.567571] CPU: 1 PID: 6425 Comm: syz Kdump: loaded Not tainted 4.19.90-vhulk2201.1.0.h1035.kasan.eulerosv2r10.aarch64 #1
[  168.567573] Hardware name: QEMU KVM Virtual Machine, BIOS 0.0.0 02/06/2015
[  168.567575] Call trace:
[  168.567578]  dump_backtrace+0x0/0x310
[  168.567582]  show_stack+0x28/0x38
[  168.567586]  dump_stack+0xec/0x15c
[  168.567591]  kasan_report+0x244/0x2f0
[  168.567594]  __asan_load4+0x58/0xb0
[  168.567607]  virtio_gpu_conn_get_modes+0xb4/0x140 [virtio_gpu]
[  168.567612]  drm_helper_probe_single_connector_modes+0x3a4/0xd80
[  168.567617]  drm_mode_getconnector+0x2e0/0xa70
[  168.567621]  drm_ioctl_kernel+0x11c/0x1d8
[  168.567624]  drm_ioctl+0x558/0x6d0
[  168.567628]  do_vfs_ioctl+0x160/0xf30
[  168.567632]  ksys_ioctl+0x98/0xd8
[  168.567636]  __arm64_sys_ioctl+0x50/0xc8
[  168.567641]  el0_svc_common+0xc8/0x320
[  168.567645]  el0_svc_handler+0xf8/0x160
[  168.567649]  el0_svc+0x10/0x218

Signed-off-by: Liu Zixian <liuzixian4@huawei.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20220322091730.1653-1-liuzixian4@huawei.com
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/virtio/virtgpu_display.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/virtio/virtgpu_display.c b/drivers/gpu/drm/virtio/virtgpu_display.c
index 5b00310ac4cd..f73352e7b832 100644
--- a/drivers/gpu/drm/virtio/virtgpu_display.c
+++ b/drivers/gpu/drm/virtio/virtgpu_display.c
@@ -179,6 +179,8 @@ static int virtio_gpu_conn_get_modes(struct drm_connector *connector)
 		DRM_DEBUG("add mode: %dx%d\n", width, height);
 		mode = drm_cvt_mode(connector->dev, width, height, 60,
 				    false, false, false);
+		if (!mode)
+			return count;
 		mode->type |= DRM_MODE_TYPE_PREFERRED;
 		drm_mode_probed_add(connector, mode);
 		count++;
-- 
2.35.1

[PATCH AUTOSEL 5.18 017/159] fbcon: Consistently protect deferred_takeover with console_lock()

[Sasha Levin]

From: Daniel Vetter <daniel.vetter@ffwll.ch>

[ Upstream commit 43553559121ca90965b572cf8a1d6d0fd618b449 ]

This shouldn't be a problem in practice since until we've actually
taken over the console there's nothing we've registered with the
console/vt subsystem, so the exit/unbind path that check this can't
do the wrong thing. But it's confusing, so fix it by moving it a tad
later.

Acked-by: Sam Ravnborg <sam@ravnborg.org>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Du Cheng <ducheng2@gmail.com>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Claudio Suarez <cssk@net-c.es>
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Link: https://patchwork.freedesktop.org/patch/msgid/20220405210335.3434130-14-daniel.vetter@ffwll.ch
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/video/fbdev/core/fbcon.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c
index 2fc1b80a26ad..9a8ae6fa6ecb 100644
--- a/drivers/video/fbdev/core/fbcon.c
+++ b/drivers/video/fbdev/core/fbcon.c
@@ -3265,6 +3265,9 @@ static void fbcon_register_existing_fbs(struct work_struct *work)
 
 	console_lock();
 
+	deferred_takeover = false;
+	logo_shown = FBCON_LOGO_DONTSHOW;
+
 	for_each_registered_fb(i)
 		fbcon_fb_registered(registered_fb[i]);
 
@@ -3282,8 +3285,6 @@ static int fbcon_output_notifier(struct notifier_block *nb,
 	pr_info("fbcon: Taking over console\n");
 
 	dummycon_unregister_output_notifier(&fbcon_output_nb);
-	deferred_takeover = false;
-	logo_shown = FBCON_LOGO_DONTSHOW;
 
 	/* We may get called in atomic context */
 	schedule_work(&fbcon_deferred_takeover_work);
-- 
2.35.1

[PATCH AUTOSEL 5.18 022/159] drm/komeda: return early if drm_universal_plane_init() fails.

[Sasha Levin]

From: Liviu Dudau <liviu.dudau@arm.com>

[ Upstream commit c8f76c37cc3668ee45e081e76a15f24a352ebbdd ]

If drm_universal_plane_init() fails early we jump to the common cleanup code
that calls komeda_plane_destroy() which in turn could access the uninitalised
drm_plane and crash. Return early if an error is detected without going through
the common code.

Reported-by: Steven Price <steven.price@arm.com>
Reviewed-by: Steven Price <steven.price@arm.com>
Signed-off-by: Liviu Dudau <liviu.dudau@arm.com>
Link: https://lore.kernel.org/dri-devel/20211203100946.2706922-1-liviu.dudau@arm.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/arm/display/komeda/komeda_plane.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_plane.c b/drivers/gpu/drm/arm/display/komeda/komeda_plane.c
index d63d83800a8a..d646e3ae1a23 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_plane.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_plane.c
@@ -275,8 +275,10 @@ static int komeda_plane_add(struct komeda_kms_dev *kms,
 
 	komeda_put_fourcc_list(formats);
 
-	if (err)
-		goto cleanup;
+	if (err) {
+		kfree(kplane);
+		return err;
+	}
 
 	drm_plane_helper_add(plane, &komeda_plane_helper_funcs);
 
-- 
2.35.1

[PATCH AUTOSEL 5.18 023/159] drm/amd/display: Disabling Z10 on DCN31

[Sasha Levin]

From: Saaem Rizvi <syerizvi@amd.com>

[ Upstream commit 5d5af34072c8b11f60960c3bea57ff9de5877791 ]

[WHY]
Z10 is should not be enabled by default on DCN31.

[HOW]
Using DC debug flags to disable Z10 by default on DCN31.

Reviewed-by: Eric Yang <Eric.Yang2@amd.com>
Acked-by: Pavle Kotarac <Pavle.Kotarac@amd.com>
Signed-off-by: Saaem Rizvi <syerizvi@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/dcn31/dcn31_resource.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
index 63934ecf6be8..d71e625cc476 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
@@ -1030,6 +1030,7 @@ static const struct dc_debug_options debug_defaults_drv = {
 			.afmt = true,
 		}
 	},
+	.disable_z10 = true,
 	.optimize_edp_link_rate = true,
 	.enable_sw_cntl_psr = true,
 	.apply_vendor_specific_lttpr_wa = true,
-- 
2.35.1

[PATCH AUTOSEL 5.18 042/159] drm/amdgpu/pm: fix the null pointer while the smu is disabled

[Sasha Levin]

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

[ Upstream commit eea5c7b3390c6e006ba4cbd906447dd8cea8cfbf ]

It needs to check if the pp_funcs is initialized while release the
context, otherwise it will trigger null pointer panic while the software
smu is not enabled.

[ 1109.404555] BUG: kernel NULL pointer dereference, address: 0000000000000078
[ 1109.404609] #PF: supervisor read access in kernel mode
[ 1109.404638] #PF: error_code(0x0000) - not-present page
[ 1109.404657] PGD 0 P4D 0
[ 1109.404672] Oops: 0000 [#1] PREEMPT SMP NOPTI
[ 1109.404701] CPU: 7 PID: 9150 Comm: amdgpu_test Tainted: G           OEL    5.16.0-custom #1
[ 1109.404732] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[ 1109.404765] RIP: 0010:amdgpu_dpm_force_performance_level+0x1d/0x170 [amdgpu]
[ 1109.405109] Code: 5d c3 44 8b a3 f0 80 00 00 eb e5 66 90 0f 1f 44 00 00 55 48 89 e5 41 57 41 56 41 55 41 54 53 48 83 ec 08 4c 8b b7 f0 7d 00 00 <49> 83 7e 78 00 0f 84 f2 00 00 00 80 bf 87 80 00 00 00 48 89 fb 0f
[ 1109.405176] RSP: 0018:ffffaf3083ad7c20 EFLAGS: 00010282
[ 1109.405203] RAX: 0000000000000000 RBX: ffff9796b1c14600 RCX: 0000000002862007
[ 1109.405229] RDX: ffff97968591c8c0 RSI: 0000000000000001 RDI: ffff9796a3700000
[ 1109.405260] RBP: ffffaf3083ad7c50 R08: ffffffff9897de00 R09: ffff979688d9db60
[ 1109.405286] R10: 0000000000000000 R11: ffff979688d9db90 R12: 0000000000000001
[ 1109.405316] R13: ffff9796a3700000 R14: 0000000000000000 R15: ffff9796a3708fc0
[ 1109.405345] FS:  00007ff055cff180(0000) GS:ffff9796bfdc0000(0000) knlGS:0000000000000000
[ 1109.405378] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 1109.405400] CR2: 0000000000000078 CR3: 000000000a394000 CR4: 00000000000506e0
[ 1109.405434] Call Trace:
[ 1109.405445]  <TASK>
[ 1109.405456]  ? delete_object_full+0x1d/0x20
[ 1109.405480]  amdgpu_ctx_set_stable_pstate+0x7c/0xa0 [amdgpu]
[ 1109.405698]  amdgpu_ctx_fini.part.0+0xcb/0x100 [amdgpu]
[ 1109.405911]  amdgpu_ctx_do_release+0x71/0x80 [amdgpu]
[ 1109.406121]  amdgpu_ctx_ioctl+0x52d/0x550 [amdgpu]
[ 1109.406327]  ? _raw_spin_unlock+0x1a/0x30
[ 1109.406354]  ? drm_gem_handle_delete+0x81/0xb0 [drm]
[ 1109.406400]  ? amdgpu_ctx_get_entity+0x2c0/0x2c0 [amdgpu]
[ 1109.406609]  drm_ioctl_kernel+0xb6/0x140 [drm]

Signed-off-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Aaron Liu <aaron.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/amd/pm/amdgpu_dpm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
index 72e7b5d40af6..5472f9936feb 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
@@ -790,7 +790,7 @@ int amdgpu_dpm_force_performance_level(struct amdgpu_device *adev,
 					AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK |
 					AMD_DPM_FORCED_LEVEL_PROFILE_PEAK;
 
-	if (!pp_funcs->force_performance_level)
+	if (!pp_funcs || !pp_funcs->force_performance_level)
 		return 0;
 
 	if (adev->pm.dpm.thermal_active)
-- 
2.35.1

[PATCH AUTOSEL 5.18 043/159] drm/amd/pm: fix double free in si_parse_power_table()

[Sasha Levin]

From: Keita Suzuki <keitasuzuki.park@sslab.ics.keio.ac.jp>

[ Upstream commit f3fa2becf2fc25b6ac7cf8d8b1a2e4a86b3b72bd ]

In function si_parse_power_table(), array adev->pm.dpm.ps and its member
is allocated. If the allocation of each member fails, the array itself
is freed and returned with an error code. However, the array is later
freed again in si_dpm_fini() function which is called when the function
returns an error.

This leads to potential double free of the array adev->pm.dpm.ps, as
well as leak of its array members, since the members are not freed in
the allocation function and the array is not nulled when freed.
In addition adev->pm.dpm.num_ps, which keeps track of the allocated
array member, is not updated until the member allocation is
successfully finished, this could also lead to either use after free,
or uninitialized variable access in si_dpm_fini().

Fix this by postponing the free of the array until si_dpm_fini() and
increment adev->pm.dpm.num_ps everytime the array member is allocated.

Signed-off-by: Keita Suzuki <keitasuzuki.park@sslab.ics.keio.ac.jp>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
index 633dab14f51c..49c398ec0aaf 100644
--- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
+++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
@@ -7297,17 +7297,15 @@ static int si_parse_power_table(struct amdgpu_device *adev)
 	if (!adev->pm.dpm.ps)
 		return -ENOMEM;
 	power_state_offset = (u8 *)state_array->states;
-	for (i = 0; i < state_array->ucNumEntries; i++) {
+	for (adev->pm.dpm.num_ps = 0, i = 0; i < state_array->ucNumEntries; i++) {
 		u8 *idx;
 		power_state = (union pplib_power_state *)power_state_offset;
 		non_clock_array_index = power_state->v2.nonClockInfoIndex;
 		non_clock_info = (struct _ATOM_PPLIB_NONCLOCK_INFO *)
 			&non_clock_info_array->nonClockInfo[non_clock_array_index];
 		ps = kzalloc(sizeof(struct  si_ps), GFP_KERNEL);
-		if (ps == NULL) {
-			kfree(adev->pm.dpm.ps);
+		if (ps == NULL)
 			return -ENOMEM;
-		}
 		adev->pm.dpm.ps[i].ps_priv = ps;
 		si_parse_pplib_non_clock_info(adev, &adev->pm.dpm.ps[i],
 					      non_clock_info,
@@ -7329,8 +7327,8 @@ static int si_parse_power_table(struct amdgpu_device *adev)
 			k++;
 		}
 		power_state_offset += 2 + power_state->v2.ucNumDPMLevels;
+		adev->pm.dpm.num_ps++;
 	}
-	adev->pm.dpm.num_ps = state_array->ucNumEntries;
 
 	/* fill in the vce power states */
 	for (i = 0; i < adev->pm.dpm.num_of_vce_states; i++) {
-- 
2.35.1

[PATCH AUTOSEL 5.18 057/159] drm/sun4i: Add support for D1 TCONs

[Sasha Levin]

From: Samuel Holland <samuel@sholland.org>

[ Upstream commit b9b52d2f4aafa2bd637ace0f24615bdad8e49f01 ]

D1 has a TCON TOP, so its quirks are similar to those for the R40 TCONs.
While there are some register changes, the part of the TCON TV supported
by the driver matches the R40 quirks, so that quirks structure can be
reused. D1 has the first supported TCON LCD with a TCON TOP, so the TCON
LCD needs a new quirks structure.

D1's TCON LCD hardware supports LVDS; in fact it provides dual-link LVDS
from a single TCON. However, it comes with a brand new LVDS PHY. Since
this PHY has not been tested, leave out LVDS driver support for now.

Signed-off-by: Samuel Holland <samuel@sholland.org>
Reviewed-by: Jernej Skrabec <jernej.skrabec@gmail.com>
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Link: https://patchwork.freedesktop.org/patch/msgid/20220424162633.12369-14-samuel@sholland.org
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/sun4i/sun4i_tcon.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c
index 88db2d2a9336..2ee158aaeb9e 100644
--- a/drivers/gpu/drm/sun4i/sun4i_tcon.c
+++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c
@@ -1542,6 +1542,12 @@ static const struct sun4i_tcon_quirks sun9i_a80_tcon_tv_quirks = {
 	.needs_edp_reset = true,
 };
 
+static const struct sun4i_tcon_quirks sun20i_d1_lcd_quirks = {
+	.has_channel_0		= true,
+	.dclk_min_div		= 1,
+	.set_mux		= sun8i_r40_tcon_tv_set_mux,
+};
+
 /* sun4i_drv uses this list to check if a device node is a TCON */
 const struct of_device_id sun4i_tcon_of_table[] = {
 	{ .compatible = "allwinner,sun4i-a10-tcon", .data = &sun4i_a10_quirks },
@@ -1559,6 +1565,8 @@ const struct of_device_id sun4i_tcon_of_table[] = {
 	{ .compatible = "allwinner,sun8i-v3s-tcon", .data = &sun8i_v3s_quirks },
 	{ .compatible = "allwinner,sun9i-a80-tcon-lcd", .data = &sun9i_a80_tcon_lcd_quirks },
 	{ .compatible = "allwinner,sun9i-a80-tcon-tv", .data = &sun9i_a80_tcon_tv_quirks },
+	{ .compatible = "allwinner,sun20i-d1-tcon-lcd", .data = &sun20i_d1_lcd_quirks },
+	{ .compatible = "allwinner,sun20i-d1-tcon-tv", .data = &sun8i_r40_tv_quirks },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, sun4i_tcon_of_table);
-- 
2.35.1

[PATCH AUTOSEL 5.18 059/159] drm/amdgpu/sdma: Fix incorrect calculations of the wptr of the doorbells

[Sasha Levin]

From: Haohui Mai <ricetons@gmail.com>

[ Upstream commit 7dba6e838e741caadcf27ef717b6dcb561e77f89 ]

This patch fixes the issue where the driver miscomputes the 64-bit
values of the wptr of the SDMA doorbell when initializing the
hardware. SDMA engines v4 and later on have full 64-bit registers for
wptr thus they should be set properly.

Older generation hardwares like CIK / SI have only 16 / 20 / 24bits
for the WPTR, where the calls of lower_32_bits() will be removed in a
following patch.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Haohui Mai <ricetons@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c | 4 ++--
 drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c | 8 ++++----
 drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c | 8 ++++----
 3 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index d7e8f7232364..ff86c43b63d1 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -772,8 +772,8 @@ static void sdma_v4_0_ring_set_wptr(struct amdgpu_ring *ring)
 
 		DRM_DEBUG("Using doorbell -- "
 				"wptr_offs == 0x%08x "
-				"lower_32_bits(ring->wptr) << 2 == 0x%08x "
-				"upper_32_bits(ring->wptr) << 2 == 0x%08x\n",
+				"lower_32_bits(ring->wptr << 2) == 0x%08x "
+				"upper_32_bits(ring->wptr << 2) == 0x%08x\n",
 				ring->wptr_offs,
 				lower_32_bits(ring->wptr << 2),
 				upper_32_bits(ring->wptr << 2));
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
index a8d49c005f73..627eb1f147c2 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
@@ -394,8 +394,8 @@ static void sdma_v5_0_ring_set_wptr(struct amdgpu_ring *ring)
 	if (ring->use_doorbell) {
 		DRM_DEBUG("Using doorbell -- "
 				"wptr_offs == 0x%08x "
-				"lower_32_bits(ring->wptr) << 2 == 0x%08x "
-				"upper_32_bits(ring->wptr) << 2 == 0x%08x\n",
+				"lower_32_bits(ring->wptr << 2) == 0x%08x "
+				"upper_32_bits(ring->wptr << 2) == 0x%08x\n",
 				ring->wptr_offs,
 				lower_32_bits(ring->wptr << 2),
 				upper_32_bits(ring->wptr << 2));
@@ -774,9 +774,9 @@ static int sdma_v5_0_gfx_resume(struct amdgpu_device *adev)
 
 		if (!amdgpu_sriov_vf(adev)) { /* only bare-metal use register write for wptr */
 			WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR),
-			       lower_32_bits(ring->wptr) << 2);
+			       lower_32_bits(ring->wptr << 2));
 			WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_HI),
-			       upper_32_bits(ring->wptr) << 2);
+			       upper_32_bits(ring->wptr << 2));
 		}
 
 		doorbell = RREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_DOORBELL));
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
index 824eace69884..a5eb82bfeaa8 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
@@ -295,8 +295,8 @@ static void sdma_v5_2_ring_set_wptr(struct amdgpu_ring *ring)
 	if (ring->use_doorbell) {
 		DRM_DEBUG("Using doorbell -- "
 				"wptr_offs == 0x%08x "
-				"lower_32_bits(ring->wptr) << 2 == 0x%08x "
-				"upper_32_bits(ring->wptr) << 2 == 0x%08x\n",
+				"lower_32_bits(ring->wptr << 2) == 0x%08x "
+				"upper_32_bits(ring->wptr << 2) == 0x%08x\n",
 				ring->wptr_offs,
 				lower_32_bits(ring->wptr << 2),
 				upper_32_bits(ring->wptr << 2));
@@ -672,8 +672,8 @@ static int sdma_v5_2_gfx_resume(struct amdgpu_device *adev)
 		WREG32_SOC15_IP(GC, sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_GFX_MINOR_PTR_UPDATE), 1);
 
 		if (!amdgpu_sriov_vf(adev)) { /* only bare-metal use register write for wptr */
-			WREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR), lower_32_bits(ring->wptr) << 2);
-			WREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_HI), upper_32_bits(ring->wptr) << 2);
+			WREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR), lower_32_bits(ring->wptr << 2));
+			WREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_HI), upper_32_bits(ring->wptr << 2));
 		}
 
 		doorbell = RREG32_SOC15_IP(GC, sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_GFX_DOORBELL));
-- 
2.35.1

[PATCH AUTOSEL 5.18 065/159] drm/plane: Move range check for format_count earlier

[Sasha Levin]

From: Steven Price <steven.price@arm.com>

[ Upstream commit 4b674dd69701c2e22e8e7770c1706a69f3b17269 ]

While the check for format_count > 64 in __drm_universal_plane_init()
shouldn't be hit (it's a WARN_ON), in its current position it will then
leak the plane->format_types array and fail to call
drm_mode_object_unregister() leaking the modeset identifier. Move it to
the start of the function to avoid allocating those resources in the
first place.

Signed-off-by: Steven Price <steven.price@arm.com>
Signed-off-by: Liviu Dudau <liviu.dudau@arm.com>
Link: https://lore.kernel.org/dri-devel/20211203102815.38624-1-steven.price@arm.com/
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/drm_plane.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/drm_plane.c b/drivers/gpu/drm/drm_plane.c
index bf0daa8d9bbd..726f2f163c26 100644
--- a/drivers/gpu/drm/drm_plane.c
+++ b/drivers/gpu/drm/drm_plane.c
@@ -247,6 +247,13 @@ static int __drm_universal_plane_init(struct drm_device *dev,
 	if (WARN_ON(config->num_total_plane >= 32))
 		return -EINVAL;
 
+	/*
+	 * First driver to need more than 64 formats needs to fix this. Each
+	 * format is encoded as a bit and the current code only supports a u64.
+	 */
+	if (WARN_ON(format_count > 64))
+		return -EINVAL;
+
 	WARN_ON(drm_drv_uses_atomic_modeset(dev) &&
 		(!funcs->atomic_destroy_state ||
 		 !funcs->atomic_duplicate_state));
@@ -268,13 +275,6 @@ static int __drm_universal_plane_init(struct drm_device *dev,
 		return -ENOMEM;
 	}
 
-	/*
-	 * First driver to need more than 64 formats needs to fix this. Each
-	 * format is encoded as a bit and the current code only supports a u64.
-	 */
-	if (WARN_ON(format_count > 64))
-		return -EINVAL;
-
 	if (format_modifiers) {
 		const uint64_t *temp_modifiers = format_modifiers;
 
-- 
2.35.1

[PATCH AUTOSEL 5.18 066/159] drm/amdkfd: Fix circular lock dependency warning

[Sasha Levin]

From: Mukul Joshi <mukul.joshi@amd.com>

[ Upstream commit b179fc28d521379ba7e0a38eec1a4c722e7ea634 ]

[  168.544078] ======================================================
[  168.550309] WARNING: possible circular locking dependency detected
[  168.556523] 5.16.0-kfd-fkuehlin #148 Tainted: G            E
[  168.562558] ------------------------------------------------------
[  168.568764] kfdtest/3479 is trying to acquire lock:
[  168.573672] ffffffffc0927a70 (&topology_lock){++++}-{3:3}, at:
		kfd_topology_device_by_id+0x16/0x60 [amdgpu] [  168.583663]
                but task is already holding lock:
[  168.589529] ffff97d303dee668 (&mm->mmap_lock#2){++++}-{3:3}, at:
		vm_mmap_pgoff+0xa9/0x180 [  168.597755]
                which lock already depends on the new lock.

[  168.605970]
                the existing dependency chain (in reverse order) is:
[  168.613487]
                -> #3 (&mm->mmap_lock#2){++++}-{3:3}:
[  168.619700]        lock_acquire+0xca/0x2e0
[  168.623814]        down_read+0x3e/0x140
[  168.627676]        do_user_addr_fault+0x40d/0x690
[  168.632399]        exc_page_fault+0x6f/0x270
[  168.636692]        asm_exc_page_fault+0x1e/0x30
[  168.641249]        filldir64+0xc8/0x1e0
[  168.645115]        call_filldir+0x7c/0x110
[  168.649238]        ext4_readdir+0x58e/0x940
[  168.653442]        iterate_dir+0x16a/0x1b0
[  168.657558]        __x64_sys_getdents64+0x83/0x140
[  168.662375]        do_syscall_64+0x35/0x80
[  168.666492]        entry_SYSCALL_64_after_hwframe+0x44/0xae
[  168.672095]
                -> #2 (&type->i_mutex_dir_key#6){++++}-{3:3}:
[  168.679008]        lock_acquire+0xca/0x2e0
[  168.683122]        down_read+0x3e/0x140
[  168.686982]        path_openat+0x5b2/0xa50
[  168.691095]        do_file_open_root+0xfc/0x190
[  168.695652]        file_open_root+0xd8/0x1b0
[  168.702010]        kernel_read_file_from_path_initns+0xc4/0x140
[  168.709542]        _request_firmware+0x2e9/0x5e0
[  168.715741]        request_firmware+0x32/0x50
[  168.721667]        amdgpu_cgs_get_firmware_info+0x370/0xdd0 [amdgpu]
[  168.730060]        smu7_upload_smu_firmware_image+0x53/0x190 [amdgpu]
[  168.738414]        fiji_start_smu+0xcf/0x4e0 [amdgpu]
[  168.745539]        pp_dpm_load_fw+0x21/0x30 [amdgpu]
[  168.752503]        amdgpu_pm_load_smu_firmware+0x4b/0x80 [amdgpu]
[  168.760698]        amdgpu_device_fw_loading+0xb8/0x140 [amdgpu]
[  168.768412]        amdgpu_device_init.cold+0xdf6/0x1716 [amdgpu]
[  168.776285]        amdgpu_driver_load_kms+0x15/0x120 [amdgpu]
[  168.784034]        amdgpu_pci_probe+0x19b/0x3a0 [amdgpu]
[  168.791161]        local_pci_probe+0x40/0x80
[  168.797027]        work_for_cpu_fn+0x10/0x20
[  168.802839]        process_one_work+0x273/0x5b0
[  168.808903]        worker_thread+0x20f/0x3d0
[  168.814700]        kthread+0x176/0x1a0
[  168.819968]        ret_from_fork+0x1f/0x30
[  168.825563]
                -> #1 (&adev->pm.mutex){+.+.}-{3:3}:
[  168.834721]        lock_acquire+0xca/0x2e0
[  168.840364]        __mutex_lock+0xa2/0x930
[  168.846020]        amdgpu_dpm_get_mclk+0x37/0x60 [amdgpu]
[  168.853257]        amdgpu_amdkfd_get_local_mem_info+0xba/0xe0 [amdgpu]
[  168.861547]        kfd_create_vcrat_image_gpu+0x1b1/0xbb0 [amdgpu]
[  168.869478]        kfd_create_crat_image_virtual+0x447/0x510 [amdgpu]
[  168.877884]        kfd_topology_add_device+0x5c8/0x6f0 [amdgpu]
[  168.885556]        kgd2kfd_device_init.cold+0x385/0x4c5 [amdgpu]
[  168.893347]        amdgpu_amdkfd_device_init+0x138/0x180 [amdgpu]
[  168.901177]        amdgpu_device_init.cold+0x141b/0x1716 [amdgpu]
[  168.909025]        amdgpu_driver_load_kms+0x15/0x120 [amdgpu]
[  168.916458]        amdgpu_pci_probe+0x19b/0x3a0 [amdgpu]
[  168.923442]        local_pci_probe+0x40/0x80
[  168.929249]        work_for_cpu_fn+0x10/0x20
[  168.935008]        process_one_work+0x273/0x5b0
[  168.940944]        worker_thread+0x20f/0x3d0
[  168.946623]        kthread+0x176/0x1a0
[  168.951765]        ret_from_fork+0x1f/0x30
[  168.957277]
                -> #0 (&topology_lock){++++}-{3:3}:
[  168.965993]        check_prev_add+0x8f/0xbf0
[  168.971613]        __lock_acquire+0x1299/0x1ca0
[  168.977485]        lock_acquire+0xca/0x2e0
[  168.982877]        down_read+0x3e/0x140
[  168.987975]        kfd_topology_device_by_id+0x16/0x60 [amdgpu]
[  168.995583]        kfd_device_by_id+0xa/0x20 [amdgpu]
[  169.002180]        kfd_mmap+0x95/0x200 [amdgpu]
[  169.008293]        mmap_region+0x337/0x5a0
[  169.013679]        do_mmap+0x3aa/0x540
[  169.018678]        vm_mmap_pgoff+0xdc/0x180
[  169.024095]        ksys_mmap_pgoff+0x186/0x1f0
[  169.029734]        do_syscall_64+0x35/0x80
[  169.035005]        entry_SYSCALL_64_after_hwframe+0x44/0xae
[  169.041754]
                other info that might help us debug this:

[  169.053276] Chain exists of:
                  &topology_lock --> &type->i_mutex_dir_key#6 --> &mm->mmap_lock#2

[  169.068389]  Possible unsafe locking scenario:

[  169.076661]        CPU0                    CPU1
[  169.082383]        ----                    ----
[  169.088087]   lock(&mm->mmap_lock#2);
[  169.092922]                                lock(&type->i_mutex_dir_key#6);
[  169.100975]                                lock(&mm->mmap_lock#2);
[  169.108320]   lock(&topology_lock);
[  169.112957]
                 *** DEADLOCK ***

This commit fixes the deadlock warning by ensuring pm.mutex is not
held while holding the topology lock. For this, kfd_local_mem_info
is moved into the KFD dev struct and filled during device init.
This cached value can then be used instead of querying the value
again and again.

Signed-off-by: Mukul Joshi <mukul.joshi@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/amdkfd/kfd_chardev.c  | 7 ++-----
 drivers/gpu/drm/amd/amdkfd/kfd_crat.c     | 2 +-
 drivers/gpu/drm/amd/amdkfd/kfd_device.c   | 2 ++
 drivers/gpu/drm/amd/amdkfd/kfd_priv.h     | 1 +
 drivers/gpu/drm/amd/amdkfd/kfd_topology.c | 7 ++-----
 5 files changed, 8 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 607f65ab39ac..10cc834a5ac3 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -944,8 +944,6 @@ static int kfd_ioctl_acquire_vm(struct file *filep, struct kfd_process *p,
 
 bool kfd_dev_is_large_bar(struct kfd_dev *dev)
 {
-	struct kfd_local_mem_info mem_info;
-
 	if (debug_largebar) {
 		pr_debug("Simulate large-bar allocation on non large-bar machine\n");
 		return true;
@@ -954,9 +952,8 @@ bool kfd_dev_is_large_bar(struct kfd_dev *dev)
 	if (dev->use_iommu_v2)
 		return false;
 
-	amdgpu_amdkfd_get_local_mem_info(dev->adev, &mem_info);
-	if (mem_info.local_mem_size_private == 0 &&
-			mem_info.local_mem_size_public > 0)
+	if (dev->local_mem_info.local_mem_size_private == 0 &&
+			dev->local_mem_info.local_mem_size_public > 0)
 		return true;
 	return false;
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
index 1eaabd2cb41b..59b349a4c04a 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
@@ -2152,7 +2152,7 @@ static int kfd_create_vcrat_image_gpu(void *pcrat_image,
 	 * report the total FB size (public+private) as a single
 	 * private heap.
 	 */
-	amdgpu_amdkfd_get_local_mem_info(kdev->adev, &local_mem_info);
+	local_mem_info = kdev->local_mem_info;
 	sub_type_hdr = (typeof(sub_type_hdr))((char *)sub_type_hdr +
 			sub_type_hdr->length);
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 62aa6c9d5123..c96d521447fc 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -575,6 +575,8 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
 	if (kfd_resume(kfd))
 		goto kfd_resume_error;
 
+	amdgpu_amdkfd_get_local_mem_info(kfd->adev, &kfd->local_mem_info);
+
 	if (kfd_topology_add_device(kfd)) {
 		dev_err(kfd_device, "Error adding device to topology\n");
 		goto kfd_topology_add_device_error;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 8f58fc491b28..49a29a60b71e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -272,6 +272,7 @@ struct kfd_dev {
 
 	struct kgd2kfd_shared_resources shared_resources;
 	struct kfd_vmid_info vm_info;
+	struct kfd_local_mem_info local_mem_info;
 
 	const struct kfd2kgd_calls *kfd2kgd;
 	struct mutex doorbell_mutex;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index 3bdcae239bc0..9fc24f6823df 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -1102,15 +1102,12 @@ static uint32_t kfd_generate_gpu_id(struct kfd_dev *gpu)
 	uint32_t buf[7];
 	uint64_t local_mem_size;
 	int i;
-	struct kfd_local_mem_info local_mem_info;
 
 	if (!gpu)
 		return 0;
 
-	amdgpu_amdkfd_get_local_mem_info(gpu->adev, &local_mem_info);
-
-	local_mem_size = local_mem_info.local_mem_size_private +
-			local_mem_info.local_mem_size_public;
+	local_mem_size = gpu->local_mem_info.local_mem_size_private +
+			gpu->local_mem_info.local_mem_size_public;
 
 	buf[0] = gpu->pdev->devfn;
 	buf[1] = gpu->pdev->subsystem_vendor |
-- 
2.35.1

[PATCH AUTOSEL 5.18 067/159] drm/amd/pm: fix the compile warning

[Sasha Levin]

From: Evan Quan <evan.quan@amd.com>

[ Upstream commit 555238d92ac32dbad2d77ad2bafc48d17391990c ]

Fix the compile warning below:
drivers/gpu/drm/amd/amdgpu/../pm/legacy-dpm/kv_dpm.c:1641
kv_get_acp_boot_level() warn: always true condition '(table->entries[i]->clk >= 0) => (0-u32max >= 0)'

Reported-by: kernel test robot <lkp@intel.com>
CC: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Evan Quan <evan.quan@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>
---
 drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c | 14 +-------------
 1 file changed, 1 insertion(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c
index 8b23cc9f098a..8fd0782a2b20 100644
--- a/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c
+++ b/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c
@@ -1623,19 +1623,7 @@ static int kv_update_samu_dpm(struct amdgpu_device *adev, bool gate)
 
 static u8 kv_get_acp_boot_level(struct amdgpu_device *adev)
 {
-	u8 i;
-	struct amdgpu_clock_voltage_dependency_table *table =
-		&adev->pm.dpm.dyn_state.acp_clock_voltage_dependency_table;
-
-	for (i = 0; i < table->count; i++) {
-		if (table->entries[i].clk >= 0) /* XXX */
-			break;
-	}
-
-	if (i >= table->count)
-		i = table->count - 1;
-
-	return i;
+	return 0;
 }
 
 static void kv_update_acp_boot_level(struct amdgpu_device *adev)
-- 
2.35.1

[PATCH AUTOSEL 5.18 070/159] drm: msm: fix error check return value of irq_of_parse_and_map()

[Sasha Levin]

From: Lv Ruyi <lv.ruyi@zte.com.cn>

[ Upstream commit b9e4f1d2b505df8e2439b63e67afaa287c1c43e2 ]

The irq_of_parse_and_map() function returns 0 on failure, and does not
return an negative value.

Reported-by: Zeal Robot <zealci@zte.com.cn>
Signed-off-by: Lv Ruyi <lv.ruyi@zte.com.cn>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Patchwork: https://patchwork.freedesktop.org/patch/483175/
Link: https://lore.kernel.org/r/20220424031959.3172406-1-lv.ruyi@zte.com.cn
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
index 3b92372e7bdf..1d4bbde29320 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
@@ -570,9 +570,9 @@ struct msm_kms *mdp5_kms_init(struct drm_device *dev)
 	}
 
 	irq = irq_of_parse_and_map(pdev->dev.of_node, 0);
-	if (irq < 0) {
-		ret = irq;
-		DRM_DEV_ERROR(&pdev->dev, "failed to get irq: %d\n", ret);
+	if (!irq) {
+		ret = -EINVAL;
+		DRM_DEV_ERROR(&pdev->dev, "failed to get irq\n");
 		goto fail;
 	}
 
-- 
2.35.1

[PATCH AUTOSEL 5.18 082/159] drm/amdgpu/psp: move PSP memory alloc from hw_init to sw_init

[Sasha Levin]

From: Alex Deucher <alexander.deucher@amd.com>

[ Upstream commit b95b5391684b39695887afb4a13cccee7820f5d6 ]

Memory allocations should be done in sw_init.  hw_init should
just be hardware programming needed to initialize the IP block.
This is how most other IP blocks work.  Move the GPU memory
allocations from psp hw_init to psp sw_init and move the memory
free to sw_fini.  This also fixes a potential GPU memory leak
if psp hw_init fails.

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_psp.c | 95 ++++++++++++-------------
 1 file changed, 47 insertions(+), 48 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index a6acec1a6155..21aa556a6bef 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -357,7 +357,39 @@ static int psp_sw_init(void *handle)
 		}
 	}
 
+	ret = amdgpu_bo_create_kernel(adev, PSP_1_MEG, PSP_1_MEG,
+				      amdgpu_sriov_vf(adev) ?
+				      AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT,
+				      &psp->fw_pri_bo,
+				      &psp->fw_pri_mc_addr,
+				      &psp->fw_pri_buf);
+	if (ret)
+		return ret;
+
+	ret = amdgpu_bo_create_kernel(adev, PSP_FENCE_BUFFER_SIZE, PAGE_SIZE,
+				      AMDGPU_GEM_DOMAIN_VRAM,
+				      &psp->fence_buf_bo,
+				      &psp->fence_buf_mc_addr,
+				      &psp->fence_buf);
+	if (ret)
+		goto failed1;
+
+	ret = amdgpu_bo_create_kernel(adev, PSP_CMD_BUFFER_SIZE, PAGE_SIZE,
+				      AMDGPU_GEM_DOMAIN_VRAM,
+				      &psp->cmd_buf_bo, &psp->cmd_buf_mc_addr,
+				      (void **)&psp->cmd_buf_mem);
+	if (ret)
+		goto failed2;
+
 	return 0;
+
+failed2:
+	amdgpu_bo_free_kernel(&psp->fw_pri_bo,
+			      &psp->fw_pri_mc_addr, &psp->fw_pri_buf);
+failed1:
+	amdgpu_bo_free_kernel(&psp->fence_buf_bo,
+			      &psp->fence_buf_mc_addr, &psp->fence_buf);
+	return ret;
 }
 
 static int psp_sw_fini(void *handle)
@@ -391,6 +423,13 @@ static int psp_sw_fini(void *handle)
 	kfree(cmd);
 	cmd = NULL;
 
+	amdgpu_bo_free_kernel(&psp->fw_pri_bo,
+			      &psp->fw_pri_mc_addr, &psp->fw_pri_buf);
+	amdgpu_bo_free_kernel(&psp->fence_buf_bo,
+			      &psp->fence_buf_mc_addr, &psp->fence_buf);
+	amdgpu_bo_free_kernel(&psp->cmd_buf_bo, &psp->cmd_buf_mc_addr,
+			      (void **)&psp->cmd_buf_mem);
+
 	return 0;
 }
 
@@ -2430,51 +2469,18 @@ static int psp_load_fw(struct amdgpu_device *adev)
 	struct psp_context *psp = &adev->psp;
 
 	if (amdgpu_sriov_vf(adev) && amdgpu_in_reset(adev)) {
-		psp_ring_stop(psp, PSP_RING_TYPE__KM); /* should not destroy ring, only stop */
-		goto skip_memalloc;
-	}
-
-	if (amdgpu_sriov_vf(adev)) {
-		ret = amdgpu_bo_create_kernel(adev, PSP_1_MEG, PSP_1_MEG,
-						AMDGPU_GEM_DOMAIN_VRAM,
-						&psp->fw_pri_bo,
-						&psp->fw_pri_mc_addr,
-						&psp->fw_pri_buf);
+		/* should not destroy ring, only stop */
+		psp_ring_stop(psp, PSP_RING_TYPE__KM);
 	} else {
-		ret = amdgpu_bo_create_kernel(adev, PSP_1_MEG, PSP_1_MEG,
-						AMDGPU_GEM_DOMAIN_GTT,
-						&psp->fw_pri_bo,
-						&psp->fw_pri_mc_addr,
-						&psp->fw_pri_buf);
-	}
-
-	if (ret)
-		goto failed;
-
-	ret = amdgpu_bo_create_kernel(adev, PSP_FENCE_BUFFER_SIZE, PAGE_SIZE,
-					AMDGPU_GEM_DOMAIN_VRAM,
-					&psp->fence_buf_bo,
-					&psp->fence_buf_mc_addr,
-					&psp->fence_buf);
-	if (ret)
-		goto failed;
-
-	ret = amdgpu_bo_create_kernel(adev, PSP_CMD_BUFFER_SIZE, PAGE_SIZE,
-				      AMDGPU_GEM_DOMAIN_VRAM,
-				      &psp->cmd_buf_bo, &psp->cmd_buf_mc_addr,
-				      (void **)&psp->cmd_buf_mem);
-	if (ret)
-		goto failed;
+		memset(psp->fence_buf, 0, PSP_FENCE_BUFFER_SIZE);
 
-	memset(psp->fence_buf, 0, PSP_FENCE_BUFFER_SIZE);
-
-	ret = psp_ring_init(psp, PSP_RING_TYPE__KM);
-	if (ret) {
-		DRM_ERROR("PSP ring init failed!\n");
-		goto failed;
+		ret = psp_ring_init(psp, PSP_RING_TYPE__KM);
+		if (ret) {
+			DRM_ERROR("PSP ring init failed!\n");
+			goto failed;
+		}
 	}
 
-skip_memalloc:
 	ret = psp_hw_start(psp);
 	if (ret)
 		goto failed;
@@ -2592,13 +2598,6 @@ static int psp_hw_fini(void *handle)
 	psp_tmr_terminate(psp);
 	psp_ring_destroy(psp, PSP_RING_TYPE__KM);
 
-	amdgpu_bo_free_kernel(&psp->fw_pri_bo,
-			      &psp->fw_pri_mc_addr, &psp->fw_pri_buf);
-	amdgpu_bo_free_kernel(&psp->fence_buf_bo,
-			      &psp->fence_buf_mc_addr, &psp->fence_buf);
-	amdgpu_bo_free_kernel(&psp->cmd_buf_bo, &psp->cmd_buf_mc_addr,
-			      (void **)&psp->cmd_buf_mem);
-
 	return 0;
 }
 
-- 
2.35.1

[PATCH AUTOSEL 5.18 083/159] drm/amdgpu/ucode: Remove firmware load type check in amdgpu_ucode_free_bo

[Sasha Levin]

From: Alice Wong <shiwei.wong@amd.com>

[ Upstream commit ab0cd4a9ae5b4679b714d8dbfedc0901fecdce9f ]

When psp_hw_init failed, it will set the load_type to AMDGPU_FW_LOAD_DIRECT.
During amdgpu_device_ip_fini, amdgpu_ucode_free_bo checks that load_type is
AMDGPU_FW_LOAD_DIRECT and skips deallocating fw_buf causing memory leak.
Remove load_type check in amdgpu_ucode_free_bo.

Signed-off-by: Alice Wong <shiwei.wong@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>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
index ca3350502618..aebafbc327fb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
@@ -714,8 +714,7 @@ int amdgpu_ucode_create_bo(struct amdgpu_device *adev)
 
 void amdgpu_ucode_free_bo(struct amdgpu_device *adev)
 {
-	if (adev->firmware.load_type != AMDGPU_FW_LOAD_DIRECT)
-		amdgpu_bo_free_kernel(&adev->firmware.fw_buf,
+	amdgpu_bo_free_kernel(&adev->firmware.fw_buf,
 		&adev->firmware.fw_buf_mc,
 		&adev->firmware.fw_buf_ptr);
 }
-- 
2.35.1

[PATCH AUTOSEL 5.18 087/159] drm/tegra: gem: Do not try to dereference ERR_PTR()

[Sasha Levin]

From: Thierry Reding <treding@nvidia.com>

[ Upstream commit cb7e1abc2c73633e1eefa168ab2dad6e838899c9 ]

When mapping the DMA-BUF attachment fails, map->sgt will be an ERR_PTR-
encoded error code and the cleanup code would try to free that memory,
which obviously would fail.

Zero out that pointer after extracting the error code when this happens
so that kfree() can do the right thing.

Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/tegra/gem.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c
index 0063403ab5e1..7c7dd84e6db8 100644
--- a/drivers/gpu/drm/tegra/gem.c
+++ b/drivers/gpu/drm/tegra/gem.c
@@ -88,6 +88,7 @@ static struct host1x_bo_mapping *tegra_bo_pin(struct device *dev, struct host1x_
 		if (IS_ERR(map->sgt)) {
 			dma_buf_detach(buf, map->attach);
 			err = PTR_ERR(map->sgt);
+			map->sgt = NULL;
 			goto free;
 		}
 
-- 
2.35.1

[PATCH AUTOSEL 5.18 129/159] drm/amd/pm: update smartshift powerboost calc for smu12

[Sasha Levin]

From: Sathishkumar S <sathishkumar.sundararaju@amd.com>

[ Upstream commit 138292f1dc00e7e0724f44769f9da39cf2f3bf0b ]

smartshift apu and dgpu power boost are reported as percentage with
respect to their power limits. This value[0-100] reflects the boost
for the respective device.

Signed-off-by: Sathishkumar S <sathishkumar.sundararaju@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c   | 60 ++++++++++++++-----
 1 file changed, 44 insertions(+), 16 deletions(-)

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 fd6c44ece168..012e3bd99cc2 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
@@ -1119,6 +1119,39 @@ static int renoir_get_power_profile_mode(struct smu_context *smu,
 	return size;
 }
 
+static void renoir_get_ss_power_percent(SmuMetrics_t *metrics,
+					uint32_t *apu_percent, uint32_t *dgpu_percent)
+{
+	uint32_t apu_boost = 0;
+	uint32_t dgpu_boost = 0;
+	uint16_t apu_limit = 0;
+	uint16_t dgpu_limit = 0;
+	uint16_t apu_power = 0;
+	uint16_t dgpu_power = 0;
+
+	apu_power = metrics->ApuPower;
+	apu_limit = metrics->StapmOriginalLimit;
+	if (apu_power > apu_limit && apu_limit != 0)
+		apu_boost =  ((apu_power - apu_limit) * 100) / apu_limit;
+	apu_boost = (apu_boost > 100) ? 100 : apu_boost;
+
+	dgpu_power = metrics->dGpuPower;
+	if (metrics->StapmCurrentLimit > metrics->StapmOriginalLimit)
+		dgpu_limit = metrics->StapmCurrentLimit - metrics->StapmOriginalLimit;
+	if (dgpu_power > dgpu_limit && dgpu_limit != 0)
+		dgpu_boost = ((dgpu_power - dgpu_limit) * 100) / dgpu_limit;
+	dgpu_boost = (dgpu_boost > 100) ? 100 : dgpu_boost;
+
+	if (dgpu_boost >= apu_boost)
+		apu_boost = 0;
+	else
+		dgpu_boost = 0;
+
+	*apu_percent = apu_boost;
+	*dgpu_percent = dgpu_boost;
+}
+
+
 static int renoir_get_smu_metrics_data(struct smu_context *smu,
 				       MetricsMember_t member,
 				       uint32_t *value)
@@ -1127,6 +1160,9 @@ static int renoir_get_smu_metrics_data(struct smu_context *smu,
 
 	SmuMetrics_t *metrics = (SmuMetrics_t *)smu_table->metrics_table;
 	int ret = 0;
+	uint32_t apu_percent = 0;
+	uint32_t dgpu_percent = 0;
+
 
 	ret = smu_cmn_get_metrics_table(smu,
 					NULL,
@@ -1171,26 +1207,18 @@ static int renoir_get_smu_metrics_data(struct smu_context *smu,
 		*value = metrics->Voltage[1];
 		break;
 	case METRICS_SS_APU_SHARE:
-		/* return the percentage of APU power with respect to APU's power limit.
-		 * percentage is reported, this isn't boost value. Smartshift power
-		 * boost/shift is only when the percentage is more than 100.
+		/* return the percentage of APU power boost
+		 * with respect to APU's power limit.
 		 */
-		if (metrics->StapmOriginalLimit > 0)
-			*value =  (metrics->ApuPower * 100) / metrics->StapmOriginalLimit;
-		else
-			*value = 0;
+		renoir_get_ss_power_percent(metrics, &apu_percent, &dgpu_percent);
+		*value = apu_percent;
 		break;
 	case METRICS_SS_DGPU_SHARE:
-		/* return the percentage of dGPU power with respect to dGPU's power limit.
-		 * percentage is reported, this isn't boost value. Smartshift power
-		 * boost/shift is only when the percentage is more than 100.
+		/* return the percentage of dGPU power boost
+		 * with respect to dGPU's power limit.
 		 */
-		if ((metrics->dGpuPower > 0) &&
-		    (metrics->StapmCurrentLimit > metrics->StapmOriginalLimit))
-			*value = (metrics->dGpuPower * 100) /
-				  (metrics->StapmCurrentLimit - metrics->StapmOriginalLimit);
-		else
-			*value = 0;
+		renoir_get_ss_power_percent(metrics, &apu_percent, &dgpu_percent);
+		*value = dgpu_percent;
 		break;
 	default:
 		*value = UINT_MAX;
-- 
2.35.1

[PATCH AUTOSEL 5.18 131/159] drm/amdgpu: Move mutex_init(&smu->message_lock) to smu_early_init()

[Sasha Levin]

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

[ Upstream commit 4b9caaa0281972ca5ea4e1cdac2e12b9df1ae00b ]

Lockdep complains about the smu->message_lock mutex being used before
it is initialized through the following call path:

amdgpu_device_init()
 amdgpu_dpm_mode2_reset()
  smu_mode2_reset()
   smu_v12_0_mode2_reset()
    smu_cmn_send_smc_msg_with_param()

Move the mutex_init() call to smu_early_init() to fix the mutex being
used before it is initialized.

This fixes the following lockdep splat:

[    3.867331] ------------[ cut here ]------------
[    3.867335] fbcon: Taking over console
[    3.867338] DEBUG_LOCKS_WARN_ON(lock->magic != lock)
[    3.867340] WARNING: CPU: 14 PID: 491 at kernel/locking/mutex.c:579 __mutex_lock+0x44c/0x830
[    3.867349] Modules linked in: amdgpu(+) crct10dif_pclmul drm_ttm_helper crc32_pclmul ttm crc32c_intel ghash_clmulni_intel hid_lg_g15 iommu_v2 sp5100_tco nvme gpu_sched drm_dp_helper nvme_core ccp wmi video hid_logitech_dj ip6_tables ip_tables ipmi_devintf ipmi_msghandler fuse i2c_dev
[    3.867363] CPU: 14 PID: 491 Comm: systemd-udevd Tainted: G          I       5.18.0-rc5+ #33
[    3.867366] Hardware name: Micro-Star International Co., Ltd. MS-7C95/B550M PRO-VDH WIFI (MS-7C95), BIOS 2.90 12/23/2021
[    3.867369] RIP: 0010:__mutex_lock+0x44c/0x830
[    3.867372] Code: ff 85 c0 0f 84 33 fc ff ff 8b 0d b7 50 25 01 85 c9 0f 85 25 fc ff ff 48 c7 c6 fb 41 82 99 48 c7 c7 6b 63 80 99 e8 88 2a f8 ff <0f> 0b e9 0b fc ff ff f6 83 b9 0c 00 00 01 0f 85 64 ff ff ff 4c 89
[    3.867377] RSP: 0018:ffffaef8c0fc79f0 EFLAGS: 00010286
[    3.867380] RAX: 0000000000000028 RBX: 0000000000000000 RCX: 0000000000000027
[    3.867382] RDX: ffff9ccc0dda0928 RSI: 0000000000000001 RDI: ffff9ccc0dda0920
[    3.867384] RBP: ffffaef8c0fc7a80 R08: 0000000000000000 R09: ffffaef8c0fc7820
[    3.867386] R10: 0000000000000003 R11: ffff9ccc2a2fffe8 R12: 0000000000000002
[    3.867388] R13: ffff9cc990808058 R14: 0000000000000000 R15: ffff9cc98bfc0000
[    3.867390] FS:  00007fc4d830f580(0000) GS:ffff9ccc0dd80000(0000) knlGS:0000000000000000
[    3.867394] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[    3.867396] CR2: 0000560a77031410 CR3: 000000010f522000 CR4: 0000000000750ee0
[    3.867398] PKRU: 55555554
[    3.867399] Call Trace:
[    3.867401]  <TASK>
[    3.867403]  ? smu_cmn_send_smc_msg_with_param+0x98/0x240 [amdgpu]
[    3.867533]  ? __mutex_lock+0x90/0x830
[    3.867535]  ? amdgpu_dpm_mode2_reset+0x37/0x60 [amdgpu]
[    3.867653]  ? smu_cmn_send_smc_msg_with_param+0x98/0x240 [amdgpu]
[    3.867758]  smu_cmn_send_smc_msg_with_param+0x98/0x240 [amdgpu]
[    3.867857]  smu_mode2_reset+0x2b/0x50 [amdgpu]
[    3.867953]  amdgpu_dpm_mode2_reset+0x46/0x60 [amdgpu]
[    3.868096]  amdgpu_device_init.cold+0x1069/0x1e78 [amdgpu]
[    3.868219]  ? _raw_spin_unlock_irqrestore+0x30/0x50
[    3.868222]  ? pci_conf1_read+0x9b/0xf0
[    3.868226]  amdgpu_driver_load_kms+0x15/0x110 [amdgpu]
[    3.868314]  amdgpu_pci_probe+0x1a9/0x3c0 [amdgpu]
[    3.868398]  local_pci_probe+0x41/0x80
[    3.868401]  pci_device_probe+0xab/0x200
[    3.868404]  really_probe+0x1a1/0x370
[    3.868407]  __driver_probe_device+0xfc/0x170
[    3.868410]  driver_probe_device+0x1f/0x90
[    3.868412]  __driver_attach+0xbf/0x1a0
[    3.868414]  ? __device_attach_driver+0xe0/0xe0
[    3.868416]  bus_for_each_dev+0x65/0x90
[    3.868419]  bus_add_driver+0x151/0x1f0
[    3.868421]  driver_register+0x89/0xd0
[    3.868423]  ? 0xffffffffc0bd4000
[    3.868425]  do_one_initcall+0x5d/0x300
[    3.868428]  ? do_init_module+0x22/0x240
[    3.868431]  ? rcu_read_lock_sched_held+0x3c/0x70
[    3.868434]  ? trace_kmalloc+0x30/0xe0
[    3.868437]  ? kmem_cache_alloc_trace+0x1e6/0x3a0
[    3.868440]  do_init_module+0x4a/0x240
[    3.868442]  __do_sys_finit_module+0x93/0xf0
[    3.868446]  do_syscall_64+0x5b/0x80
[    3.868449]  ? rcu_read_lock_sched_held+0x3c/0x70
[    3.868451]  ? lockdep_hardirqs_on_prepare+0xd9/0x180
[    3.868454]  ? do_syscall_64+0x67/0x80
[    3.868456]  ? do_syscall_64+0x67/0x80
[    3.868458]  ? do_syscall_64+0x67/0x80
[    3.868460]  ? do_syscall_64+0x67/0x80
[    3.868462]  entry_SYSCALL_64_after_hwframe+0x44/0xae
[    3.868465] RIP: 0033:0x7fc4d8ec1ced
[    3.868467] Code: 5d c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d fb 70 0e 00 f7 d8 64 89 01 48
[    3.868472] RSP: 002b:00007fff687ae6b8 EFLAGS: 00000246 ORIG_RAX: 0000000000000139
[    3.868475] RAX: ffffffffffffffda RBX: 0000560a76fbca60 RCX: 00007fc4d8ec1ced
[    3.868477] RDX: 0000000000000000 RSI: 00007fc4d902343c RDI: 0000000000000011
[    3.868479] RBP: 00007fc4d902343c R08: 0000000000000000 R09: 0000560a76fb59c0
[    3.868481] R10: 0000000000000011 R11: 0000000000000246 R12: 0000000000020000
[    3.868484] R13: 0000560a76f8bfd0 R14: 0000000000000000 R15: 0000560a76fc2d10
[    3.868487]  </TASK>
[    3.868489] irq event stamp: 120617
[    3.868490] hardirqs last  enabled at (120617): [<ffffffff9817169e>] __up_console_sem+0x5e/0x70
[    3.868494] hardirqs last disabled at (120616): [<ffffffff98171683>] __up_console_sem+0x43/0x70
[    3.868497] softirqs last  enabled at (119684): [<ffffffff980ee83a>] __irq_exit_rcu+0xca/0x100
[    3.868501] softirqs last disabled at (119679): [<ffffffff980ee83a>] __irq_exit_rcu+0xca/0x100
[    3.868504] ---[ end trace 0000000000000000 ]---

Signed-off-by: Hans de Goede <hdegoede@redhat.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 | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index f10a0256413e..32cff21f261c 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -576,6 +576,8 @@ static int smu_early_init(void *handle)
 	smu->smu_baco.platform_support = false;
 	smu->user_dpm_profile.fan_mode = -1;
 
+	mutex_init(&smu->message_lock);
+
 	adev->powerplay.pp_handle = smu;
 	adev->powerplay.pp_funcs = &swsmu_pm_funcs;
 
@@ -975,8 +977,6 @@ static int smu_sw_init(void *handle)
 	bitmap_zero(smu->smu_feature.supported, SMU_FEATURE_MAX);
 	bitmap_zero(smu->smu_feature.allowed, SMU_FEATURE_MAX);
 
-	mutex_init(&smu->message_lock);
-
 	INIT_WORK(&smu->throttling_logging_work, smu_throttling_logging_work_fn);
 	INIT_WORK(&smu->interrupt_work, smu_interrupt_work_fn);
 	atomic64_set(&smu->throttle_int_counter, 0);
-- 
2.35.1