From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753291AbaIXVCI (ORCPT ); Wed, 24 Sep 2014 17:02:08 -0400 Received: from mail-by2on0129.outbound.protection.outlook.com ([207.46.100.129]:52991 "EHLO na01-by2-obe.outbound.protection.outlook.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1750891AbaIXVCF (ORCPT ); Wed, 24 Sep 2014 17:02:05 -0400 X-WSS-ID: 0NCFB20-08-8F2-02 X-M-MSG: From: Oded Gabbay To: David Airlie , Alex Deucher , Jerome Glisse CC: , , "John Bridgman" , Andrew Lewycky , Joerg Roedel , Oded Gabbay , =?UTF-8?q?Christian=20K=C3=B6nig?= Subject: [PATCH v4 04/23] drm/radeon: adding synchronization for GRBM GFX Date: Wed, 24 Sep 2014 23:45:18 +0300 Message-ID: <1411591537-31636-5-git-send-email-oded.gabbay@amd.com> X-Mailer: git-send-email 1.9.1 In-Reply-To: <1411591537-31636-1-git-send-email-oded.gabbay@amd.com> References: <1411591537-31636-1-git-send-email-oded.gabbay@amd.com> MIME-Version: 1.0 Content-Type: text/plain X-Originating-IP: [10.20.0.84] X-EOPAttributedMessage: 0 X-Forefront-Antispam-Report: CIP:165.204.84.222;CTRY:US;IPV:NLI;EFV:NLI;SFV:NSPM;SFS:(10019020)(6009001)(428002)(199003)(189002)(77156001)(92726001)(104166001)(107046002)(64706001)(86362001)(77982003)(20776003)(47776003)(81342003)(92566001)(93916002)(33646002)(46102003)(74502003)(74662003)(99396003)(68736004)(90102001)(229853001)(81542003)(79102003)(80022003)(62966002)(97736003)(85852003)(77096002)(50466002)(88136002)(95666004)(83072002)(89996001)(76176999)(50986999)(85306004)(48376002)(31966008)(101416001)(4396001)(10300001)(102836001)(50226001)(84676001)(83322001)(19580395003)(19580405001)(87286001)(36756003)(87936001)(76482002)(106466001)(120916001)(44976005)(105586002)(21056001);DIR:OUT;SFP:1102;SCL:1;SRVR:BLUPR02MB195;H:atltwp02.amd.com;FPR:;MLV:sfv;PTR:InfoDomainNonexistent;A:1;MX:1;LANG:en; X-Microsoft-Antispam: UriScan:; X-Microsoft-Antispam: BCL:0;PCL:0;RULEID:;SRVR:BLUPR02MB195; X-Forefront-PRVS: 03449D5DD1 Authentication-Results: spf=none (sender IP is 165.204.84.222) smtp.mailfrom=Oded.Gabbay@amd.com; X-OriginatorOrg: amd4.onmicrosoft.com Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Implementing a lock for selecting and accessing shader engines and arrays. This lock will make sure that radeon and amdkfd are not colliding when accessing shader engines and arrays with GRBM_GFX_INDEX register. Signed-off-by: Oded Gabbay --- drivers/gpu/drm/radeon/cik.c | 26 ++++++++++++++++++++++++++ drivers/gpu/drm/radeon/radeon.h | 2 ++ drivers/gpu/drm/radeon/radeon_device.c | 1 + 3 files changed, 29 insertions(+) diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c index e789988..69b9027 100644 --- a/drivers/gpu/drm/radeon/cik.c +++ b/drivers/gpu/drm/radeon/cik.c @@ -1563,6 +1563,8 @@ static const u32 godavari_golden_registers[] = static void cik_init_golden_registers(struct radeon_device *rdev) { + /* Some of the registers might be dependant on GRBM_GFX_INDEX */ + mutex_lock(&rdev->grbm_idx_mutex); switch (rdev->family) { case CHIP_BONAIRE: radeon_program_register_sequence(rdev, @@ -1637,6 +1639,7 @@ static void cik_init_golden_registers(struct radeon_device *rdev) default: break; } + mutex_unlock(&rdev->grbm_idx_mutex); } /** @@ -3419,6 +3422,7 @@ static void cik_setup_rb(struct radeon_device *rdev, u32 disabled_rbs = 0; u32 enabled_rbs = 0; + mutex_lock(&rdev->grbm_idx_mutex); for (i = 0; i < se_num; i++) { for (j = 0; j < sh_per_se; j++) { cik_select_se_sh(rdev, i, j); @@ -3430,6 +3434,7 @@ static void cik_setup_rb(struct radeon_device *rdev, } } cik_select_se_sh(rdev, 0xffffffff, 0xffffffff); + mutex_unlock(&rdev->grbm_idx_mutex); mask = 1; for (i = 0; i < max_rb_num_per_se * se_num; i++) { @@ -3440,6 +3445,7 @@ static void cik_setup_rb(struct radeon_device *rdev, rdev->config.cik.backend_enable_mask = enabled_rbs; + mutex_lock(&rdev->grbm_idx_mutex); for (i = 0; i < se_num; i++) { cik_select_se_sh(rdev, i, 0xffffffff); data = 0; @@ -3467,6 +3473,7 @@ static void cik_setup_rb(struct radeon_device *rdev, WREG32(PA_SC_RASTER_CONFIG, data); } cik_select_se_sh(rdev, 0xffffffff, 0xffffffff); + mutex_unlock(&rdev->grbm_idx_mutex); } /** @@ -3684,6 +3691,12 @@ static void cik_gpu_init(struct radeon_device *rdev) /* set HW defaults for 3D engine */ WREG32(CP_MEQ_THRESHOLDS, MEQ1_START(0x30) | MEQ2_START(0x60)); + mutex_lock(&rdev->grbm_idx_mutex); + /* + * making sure that the following register writes will be broadcasted + * to all the shaders + */ + cik_select_se_sh(rdev, 0xffffffff, 0xffffffff); WREG32(SX_DEBUG_1, 0x20); WREG32(TA_CNTL_AUX, 0x00010000); @@ -3739,6 +3752,7 @@ static void cik_gpu_init(struct radeon_device *rdev) WREG32(PA_CL_ENHANCE, CLIP_VTX_REORDER_ENA | NUM_CLIP_SEQ(3)); WREG32(PA_SC_ENHANCE, ENABLE_PA_SC_OUT_OF_ORDER); + mutex_unlock(&rdev->grbm_idx_mutex); udelay(50); } @@ -6062,6 +6076,7 @@ static void cik_wait_for_rlc_serdes(struct radeon_device *rdev) u32 i, j, k; u32 mask; + mutex_lock(&rdev->grbm_idx_mutex); for (i = 0; i < rdev->config.cik.max_shader_engines; i++) { for (j = 0; j < rdev->config.cik.max_sh_per_se; j++) { cik_select_se_sh(rdev, i, j); @@ -6073,6 +6088,7 @@ static void cik_wait_for_rlc_serdes(struct radeon_device *rdev) } } cik_select_se_sh(rdev, 0xffffffff, 0xffffffff); + mutex_unlock(&rdev->grbm_idx_mutex); mask = SE_MASTER_BUSY_MASK | GC_MASTER_BUSY | TC0_MASTER_BUSY | TC1_MASTER_BUSY; for (k = 0; k < rdev->usec_timeout; k++) { @@ -6207,10 +6223,12 @@ static int cik_rlc_resume(struct radeon_device *rdev) WREG32(RLC_LB_CNTR_INIT, 0); WREG32(RLC_LB_CNTR_MAX, 0x00008000); + mutex_lock(&rdev->grbm_idx_mutex); cik_select_se_sh(rdev, 0xffffffff, 0xffffffff); WREG32(RLC_LB_INIT_CU_MASK, 0xffffffff); WREG32(RLC_LB_PARAMS, 0x00600408); WREG32(RLC_LB_CNTL, 0x80000004); + mutex_unlock(&rdev->grbm_idx_mutex); WREG32(RLC_MC_CNTL, 0); WREG32(RLC_UCODE_CNTL, 0); @@ -6277,11 +6295,13 @@ static void cik_enable_cgcg(struct radeon_device *rdev, bool enable) tmp = cik_halt_rlc(rdev); + mutex_lock(&rdev->grbm_idx_mutex); cik_select_se_sh(rdev, 0xffffffff, 0xffffffff); WREG32(RLC_SERDES_WR_CU_MASTER_MASK, 0xffffffff); WREG32(RLC_SERDES_WR_NONCU_MASTER_MASK, 0xffffffff); tmp2 = BPM_ADDR_MASK | CGCG_OVERRIDE_0 | CGLS_ENABLE; WREG32(RLC_SERDES_WR_CTRL, tmp2); + mutex_unlock(&rdev->grbm_idx_mutex); cik_update_rlc(rdev, tmp); @@ -6323,11 +6343,13 @@ static void cik_enable_mgcg(struct radeon_device *rdev, bool enable) tmp = cik_halt_rlc(rdev); + mutex_lock(&rdev->grbm_idx_mutex); cik_select_se_sh(rdev, 0xffffffff, 0xffffffff); WREG32(RLC_SERDES_WR_CU_MASTER_MASK, 0xffffffff); WREG32(RLC_SERDES_WR_NONCU_MASTER_MASK, 0xffffffff); data = BPM_ADDR_MASK | MGCG_OVERRIDE_0; WREG32(RLC_SERDES_WR_CTRL, data); + mutex_unlock(&rdev->grbm_idx_mutex); cik_update_rlc(rdev, tmp); @@ -6371,11 +6393,13 @@ static void cik_enable_mgcg(struct radeon_device *rdev, bool enable) tmp = cik_halt_rlc(rdev); + mutex_lock(&rdev->grbm_idx_mutex); cik_select_se_sh(rdev, 0xffffffff, 0xffffffff); WREG32(RLC_SERDES_WR_CU_MASTER_MASK, 0xffffffff); WREG32(RLC_SERDES_WR_NONCU_MASTER_MASK, 0xffffffff); data = BPM_ADDR_MASK | MGCG_OVERRIDE_1; WREG32(RLC_SERDES_WR_CTRL, data); + mutex_unlock(&rdev->grbm_idx_mutex); cik_update_rlc(rdev, tmp); } @@ -6804,10 +6828,12 @@ static u32 cik_get_cu_active_bitmap(struct radeon_device *rdev, u32 se, u32 sh) u32 mask = 0, tmp, tmp1; int i; + mutex_lock(&rdev->grbm_idx_mutex); cik_select_se_sh(rdev, se, sh); tmp = RREG32(CC_GC_SHADER_ARRAY_CONFIG); tmp1 = RREG32(GC_USER_SHADER_ARRAY_CONFIG); cik_select_se_sh(rdev, 0xffffffff, 0xffffffff); + mutex_unlock(&rdev->grbm_idx_mutex); tmp &= 0xffff0000; diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index 67d249a..c30f1fd 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -2386,6 +2386,8 @@ struct radeon_device { struct radeon_atcs atcs; /* srbm instance registers */ struct mutex srbm_mutex; + /* GRBM index mutex. Protects concurrents access to GRBM index */ + struct mutex grbm_idx_mutex; /* clock, powergating flags */ u32 cg_flags; u32 pg_flags; diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index da3035f..eca614e 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -1299,6 +1299,7 @@ int radeon_device_init(struct radeon_device *rdev, mutex_init(&rdev->pm.mutex); mutex_init(&rdev->gpu_clock_mutex); mutex_init(&rdev->srbm_mutex); + mutex_init(&rdev->grbm_idx_mutex); init_rwsem(&rdev->pm.mclk_lock); init_rwsem(&rdev->exclusive_lock); init_waitqueue_head(&rdev->irq.vblank_queue); -- 1.9.1