linux-kernel - [PATCH 5.4 77/80] drm/amdgpu/gfx10: re-init clear state buffer after gpu reset

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20191219183146.949139449@linuxfoundation.org>
Date:   Thu, 19 Dec 2019 19:35:09 +0100
From:   Greg Kroah-Hartman <gregkh@...uxfoundation.org>
To:     linux-kernel@...r.kernel.org
Cc:     Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
        stable@...r.kernel.org, Xiaojie Yuan <xiaojie.yuan@....com>,
        Hawking Zhang <Hawking.Zhang@....com>,
        Alex Deucher <alexander.deucher@....com>
Subject: [PATCH 5.4 77/80] drm/amdgpu/gfx10: re-init clear state buffer after gpu reset

From: Xiaojie Yuan <xiaojie.yuan@....com>

commit 210b3b3c7563df391bd81d49c51af303b928de4a upstream.

This patch fixes 2nd baco reset failure with gfxoff enabled on navi1x.

clear state buffer (resides in vram) is corrupted after 1st baco reset,
upon gfxoff exit, CPF gets garbage header in CSIB and hangs.

Signed-off-by: Xiaojie Yuan <xiaojie.yuan@....com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@....com>
Signed-off-by: Alex Deucher <alexander.deucher@....com>
Cc: stable@...r.kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@...uxfoundation.org>

---
 drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c |   43 ++++++++++++++++++++++++++++-----
 1 file changed, 37 insertions(+), 6 deletions(-)

--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -1785,27 +1785,52 @@ static void gfx_v10_0_enable_gui_idle_in
 	WREG32_SOC15(GC, 0, mmCP_INT_CNTL_RING0, tmp);
 }
 
-static void gfx_v10_0_init_csb(struct amdgpu_device *adev)
+static int gfx_v10_0_init_csb(struct amdgpu_device *adev)
 {
+	int r;
+
+	if (adev->in_gpu_reset) {
+		r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, false);
+		if (r)
+			return r;
+
+		r = amdgpu_bo_kmap(adev->gfx.rlc.clear_state_obj,
+				   (void **)&adev->gfx.rlc.cs_ptr);
+		if (!r) {
+			adev->gfx.rlc.funcs->get_csb_buffer(adev,
+					adev->gfx.rlc.cs_ptr);
+			amdgpu_bo_kunmap(adev->gfx.rlc.clear_state_obj);
+		}
+
+		amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj);
+		if (r)
+			return r;
+	}
+
 	/* csib */
 	WREG32_SOC15(GC, 0, mmRLC_CSIB_ADDR_HI,
 		     adev->gfx.rlc.clear_state_gpu_addr >> 32);
 	WREG32_SOC15(GC, 0, mmRLC_CSIB_ADDR_LO,
 		     adev->gfx.rlc.clear_state_gpu_addr & 0xfffffffc);
 	WREG32_SOC15(GC, 0, mmRLC_CSIB_LENGTH, adev->gfx.rlc.clear_state_size);
+
+	return 0;
 }
 
-static void gfx_v10_0_init_pg(struct amdgpu_device *adev)
+static int gfx_v10_0_init_pg(struct amdgpu_device *adev)
 {
 	int i;
+	int r;
 
-	gfx_v10_0_init_csb(adev);
+	r = gfx_v10_0_init_csb(adev);
+	if (r)
+		return r;
 
 	for (i = 0; i < adev->num_vmhubs; i++)
 		amdgpu_gmc_flush_gpu_tlb(adev, 0, i, 0);
 
 	/* TODO: init power gating */
-	return;
+	return 0;
 }
 
 void gfx_v10_0_rlc_stop(struct amdgpu_device *adev)
@@ -1907,7 +1932,10 @@ static int gfx_v10_0_rlc_resume(struct a
 		r = gfx_v10_0_wait_for_rlc_autoload_complete(adev);
 		if (r)
 			return r;
-		gfx_v10_0_init_pg(adev);
+
+		r = gfx_v10_0_init_pg(adev);
+		if (r)
+			return r;
 
 		/* enable RLC SRM */
 		gfx_v10_0_rlc_enable_srm(adev);
@@ -1933,7 +1961,10 @@ static int gfx_v10_0_rlc_resume(struct a
 				return r;
 		}
 
-		gfx_v10_0_init_pg(adev);
+		r = gfx_v10_0_init_pg(adev);
+		if (r)
+			return r;
+
 		adev->gfx.rlc.funcs->start(adev);
 
 		if (adev->firmware.load_type == AMDGPU_FW_LOAD_RLC_BACKDOOR_AUTO) {