diff options
Diffstat (limited to 'drivers/gpu/drm/msm/adreno')
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/a3xx_gpu.c | 36 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/a3xx_gpu.h | 3 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/a4xx_gpu.c | 33 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/a4xx_gpu.h | 3 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/a5xx_debugfs.c | 4 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/a5xx_gpu.c | 90 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/a5xx_power.c | 7 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/a6xx.xml.h | 52 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/a6xx_gmu.c | 34 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/a6xx_gmu.h | 3 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 81 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/a6xx_gpu.h | 9 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c | 76 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h | 16 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/adreno_device.c | 27 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/adreno_gpu.c | 106 | ||||
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/adreno_gpu.h | 32 |
17 files changed, 488 insertions, 124 deletions
diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c index 5f7e98028eaf..b67f88872726 100644 --- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c @@ -6,10 +6,6 @@ * Copyright (c) 2014 The Linux Foundation. All rights reserved. */ -#ifdef CONFIG_MSM_OCMEM -# include <mach/ocmem.h> -#endif - #include "a3xx_gpu.h" #define A3XX_INT0_MASK \ @@ -195,9 +191,9 @@ static int a3xx_hw_init(struct msm_gpu *gpu) gpu_write(gpu, REG_A3XX_RBBM_GPR0_CTL, 0x00000000); /* Set the OCMEM base address for A330, etc */ - if (a3xx_gpu->ocmem_hdl) { + if (a3xx_gpu->ocmem.hdl) { gpu_write(gpu, REG_A3XX_RB_GMEM_BASE_ADDR, - (unsigned int)(a3xx_gpu->ocmem_base >> 14)); + (unsigned int)(a3xx_gpu->ocmem.base >> 14)); } /* Turn on performance counters: */ @@ -318,10 +314,7 @@ static void a3xx_destroy(struct msm_gpu *gpu) adreno_gpu_cleanup(adreno_gpu); -#ifdef CONFIG_MSM_OCMEM - if (a3xx_gpu->ocmem_base) - ocmem_free(OCMEM_GRAPHICS, a3xx_gpu->ocmem_hdl); -#endif + adreno_gpu_ocmem_cleanup(&a3xx_gpu->ocmem); kfree(a3xx_gpu); } @@ -494,17 +487,10 @@ struct msm_gpu *a3xx_gpu_init(struct drm_device *dev) /* if needed, allocate gmem: */ if (adreno_is_a330(adreno_gpu)) { -#ifdef CONFIG_MSM_OCMEM - /* TODO this is different/missing upstream: */ - struct ocmem_buf *ocmem_hdl = - ocmem_allocate(OCMEM_GRAPHICS, adreno_gpu->gmem); - - a3xx_gpu->ocmem_hdl = ocmem_hdl; - a3xx_gpu->ocmem_base = ocmem_hdl->addr; - adreno_gpu->gmem = ocmem_hdl->len; - DBG("using %dK of OCMEM at 0x%08x", adreno_gpu->gmem / 1024, - a3xx_gpu->ocmem_base); -#endif + ret = adreno_gpu_ocmem_init(&adreno_gpu->base.pdev->dev, + adreno_gpu, &a3xx_gpu->ocmem); + if (ret) + goto fail; } if (!gpu->aspace) { @@ -520,6 +506,14 @@ struct msm_gpu *a3xx_gpu_init(struct drm_device *dev) goto fail; } + /* + * Set the ICC path to maximum speed for now by multiplying the fastest + * frequency by the bus width (8). We'll want to scale this later on to + * improve battery life. + */ + icc_set_bw(gpu->icc_path, 0, Bps_to_icc(gpu->fast_rate) * 8); + icc_set_bw(gpu->ocmem_icc_path, 0, Bps_to_icc(gpu->fast_rate) * 8); + return gpu; fail: diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.h b/drivers/gpu/drm/msm/adreno/a3xx_gpu.h index 5dc33e5ea53b..c555fb13e0d7 100644 --- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.h +++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.h @@ -19,8 +19,7 @@ struct a3xx_gpu { struct adreno_gpu base; /* if OCMEM is used for GMEM: */ - uint32_t ocmem_base; - void *ocmem_hdl; + struct adreno_ocmem ocmem; }; #define to_a3xx_gpu(x) container_of(x, struct a3xx_gpu, base) diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c index ab2b752566d8..253d8d85daad 100644 --- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c @@ -2,9 +2,6 @@ /* Copyright (c) 2014 The Linux Foundation. All rights reserved. */ #include "a4xx_gpu.h" -#ifdef CONFIG_MSM_OCMEM -# include <soc/qcom/ocmem.h> -#endif #define A4XX_INT0_MASK \ (A4XX_INT0_RBBM_AHB_ERROR | \ @@ -188,7 +185,7 @@ static int a4xx_hw_init(struct msm_gpu *gpu) (1 << 30) | 0xFFFF); gpu_write(gpu, REG_A4XX_RB_GMEM_BASE_ADDR, - (unsigned int)(a4xx_gpu->ocmem_base >> 14)); + (unsigned int)(a4xx_gpu->ocmem.base >> 14)); /* Turn on performance counters: */ gpu_write(gpu, REG_A4XX_RBBM_PERFCTR_CTL, 0x01); @@ -318,10 +315,7 @@ static void a4xx_destroy(struct msm_gpu *gpu) adreno_gpu_cleanup(adreno_gpu); -#ifdef CONFIG_MSM_OCMEM - if (a4xx_gpu->ocmem_base) - ocmem_free(OCMEM_GRAPHICS, a4xx_gpu->ocmem_hdl); -#endif + adreno_gpu_ocmem_cleanup(&a4xx_gpu->ocmem); kfree(a4xx_gpu); } @@ -578,17 +572,10 @@ struct msm_gpu *a4xx_gpu_init(struct drm_device *dev) /* if needed, allocate gmem: */ if (adreno_is_a4xx(adreno_gpu)) { -#ifdef CONFIG_MSM_OCMEM - /* TODO this is different/missing upstream: */ - struct ocmem_buf *ocmem_hdl = - ocmem_allocate(OCMEM_GRAPHICS, adreno_gpu->gmem); - - a4xx_gpu->ocmem_hdl = ocmem_hdl; - a4xx_gpu->ocmem_base = ocmem_hdl->addr; - adreno_gpu->gmem = ocmem_hdl->len; - DBG("using %dK of OCMEM at 0x%08x", adreno_gpu->gmem / 1024, - a4xx_gpu->ocmem_base); -#endif + ret = adreno_gpu_ocmem_init(dev->dev, adreno_gpu, + &a4xx_gpu->ocmem); + if (ret) + goto fail; } if (!gpu->aspace) { @@ -604,6 +591,14 @@ struct msm_gpu *a4xx_gpu_init(struct drm_device *dev) goto fail; } + /* + * Set the ICC path to maximum speed for now by multiplying the fastest + * frequency by the bus width (8). We'll want to scale this later on to + * improve battery life. + */ + icc_set_bw(gpu->icc_path, 0, Bps_to_icc(gpu->fast_rate) * 8); + icc_set_bw(gpu->ocmem_icc_path, 0, Bps_to_icc(gpu->fast_rate) * 8); + return gpu; fail: diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.h b/drivers/gpu/drm/msm/adreno/a4xx_gpu.h index d506311ee240..a01448cba2ea 100644 --- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.h +++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.h @@ -16,8 +16,7 @@ struct a4xx_gpu { struct adreno_gpu base; /* if OCMEM is used for GMEM: */ - uint32_t ocmem_base; - void *ocmem_hdl; + struct adreno_ocmem ocmem; }; #define to_a4xx_gpu(x) container_of(x, struct a4xx_gpu, base) diff --git a/drivers/gpu/drm/msm/adreno/a5xx_debugfs.c b/drivers/gpu/drm/msm/adreno/a5xx_debugfs.c index 9f2dd76bd67a..075ecce4b5e0 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_debugfs.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_debugfs.c @@ -2,9 +2,11 @@ /* Copyright (c) 2016-2017 The Linux Foundation. All rights reserved. */ - #include <linux/types.h> #include <linux/debugfs.h> + +#include <drm/drm_debugfs.h> +#include <drm/drm_file.h> #include <drm/drm_print.h> #include "a5xx_gpu.h" diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index e9c55d1d6c04..7d9e63e20ded 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -353,6 +353,9 @@ static int a5xx_me_init(struct msm_gpu *gpu) * 2D mode 3 draw */ OUT_RING(ring, 0x0000000B); + } else if (adreno_is_a510(adreno_gpu)) { + /* Workaround for token and syncs */ + OUT_RING(ring, 0x00000001); } else { /* No workarounds enabled */ OUT_RING(ring, 0x00000000); @@ -568,15 +571,24 @@ static int a5xx_hw_init(struct msm_gpu *gpu) 0x00100000 + adreno_gpu->gmem - 1); gpu_write(gpu, REG_A5XX_UCHE_GMEM_RANGE_MAX_HI, 0x00000000); - gpu_write(gpu, REG_A5XX_CP_MEQ_THRESHOLDS, 0x40); - if (adreno_is_a530(adreno_gpu)) - gpu_write(gpu, REG_A5XX_CP_MERCIU_SIZE, 0x40); - if (adreno_is_a540(adreno_gpu)) - gpu_write(gpu, REG_A5XX_CP_MERCIU_SIZE, 0x400); - gpu_write(gpu, REG_A5XX_CP_ROQ_THRESHOLDS_2, 0x80000060); - gpu_write(gpu, REG_A5XX_CP_ROQ_THRESHOLDS_1, 0x40201B16); - - gpu_write(gpu, REG_A5XX_PC_DBG_ECO_CNTL, (0x400 << 11 | 0x300 << 22)); + if (adreno_is_a510(adreno_gpu)) { + gpu_write(gpu, REG_A5XX_CP_MEQ_THRESHOLDS, 0x20); + gpu_write(gpu, REG_A5XX_CP_MERCIU_SIZE, 0x20); + gpu_write(gpu, REG_A5XX_CP_ROQ_THRESHOLDS_2, 0x40000030); + gpu_write(gpu, REG_A5XX_CP_ROQ_THRESHOLDS_1, 0x20100D0A); + gpu_write(gpu, REG_A5XX_PC_DBG_ECO_CNTL, + (0x200 << 11 | 0x200 << 22)); + } else { + gpu_write(gpu, REG_A5XX_CP_MEQ_THRESHOLDS, 0x40); + if (adreno_is_a530(adreno_gpu)) + gpu_write(gpu, REG_A5XX_CP_MERCIU_SIZE, 0x40); + if (adreno_is_a540(adreno_gpu)) + gpu_write(gpu, REG_A5XX_CP_MERCIU_SIZE, 0x400); + gpu_write(gpu, REG_A5XX_CP_ROQ_THRESHOLDS_2, 0x80000060); + gpu_write(gpu, REG_A5XX_CP_ROQ_THRESHOLDS_1, 0x40201B16); + gpu_write(gpu, REG_A5XX_PC_DBG_ECO_CNTL, + (0x400 << 11 | 0x300 << 22)); + } if (adreno_gpu->info->quirks & ADRENO_QUIRK_TWO_PASS_USE_WFI) gpu_rmw(gpu, REG_A5XX_PC_DBG_ECO_CNTL, 0, (1 << 8)); @@ -589,6 +601,19 @@ static int a5xx_hw_init(struct msm_gpu *gpu) /* Enable ME/PFP split notification */ gpu_write(gpu, REG_A5XX_RBBM_AHB_CNTL1, 0xA6FFFFFF); + /* + * In A5x, CCU can send context_done event of a particular context to + * UCHE which ultimately reaches CP even when there is valid + * transaction of that context inside CCU. This can let CP to program + * config registers, which will make the "valid transaction" inside + * CCU to be interpreted differently. This can cause gpu fault. This + * bug is fixed in latest A510 revision. To enable this bug fix - + * bit[11] of RB_DBG_ECO_CNTL need to be set to 0, default is 1 + * (disable). For older A510 version this bit is unused. + */ + if (adreno_is_a510(adreno_gpu)) + gpu_rmw(gpu, REG_A5XX_RB_DBG_ECO_CNTL, (1 << 11), 0); + /* Enable HWCG */ a5xx_set_hwcg(gpu, true); @@ -635,7 +660,7 @@ static int a5xx_hw_init(struct msm_gpu *gpu) /* UCHE */ gpu_write(gpu, REG_A5XX_CP_PROTECT(16), ADRENO_PROTECT_RW(0xE80, 16)); - if (adreno_is_a530(adreno_gpu)) + if (adreno_is_a530(adreno_gpu) || adreno_is_a510(adreno_gpu)) gpu_write(gpu, REG_A5XX_CP_PROTECT(17), ADRENO_PROTECT_RW(0x10000, 0x8000)); @@ -679,7 +704,8 @@ static int a5xx_hw_init(struct msm_gpu *gpu) a5xx_preempt_hw_init(gpu); - a5xx_gpmu_ucode_init(gpu); + if (!adreno_is_a510(adreno_gpu)) + a5xx_gpmu_ucode_init(gpu); ret = a5xx_ucode_init(gpu); if (ret) @@ -712,7 +738,8 @@ static int a5xx_hw_init(struct msm_gpu *gpu) } /* - * Try to load a zap shader into the secure world. If successful + * If the chip that we are using does support loading one, then + * try to load a zap shader into the secure world. If successful * we can use the CP to switch out of secure mode. If not then we * have no resource but to try to switch ourselves out manually. If we * guessed wrong then access to the RBBM_SECVID_TRUST_CNTL register will @@ -726,11 +753,18 @@ static int a5xx_hw_init(struct msm_gpu *gpu) gpu->funcs->flush(gpu, gpu->rb[0]); if (!a5xx_idle(gpu, gpu->rb[0])) return -EINVAL; - } else { - /* Print a warning so if we die, we know why */ + } else if (ret == -ENODEV) { + /* + * This device does not use zap shader (but print a warning + * just in case someone got their dt wrong.. hopefully they + * have a debug UART to realize the error of their ways... + * if you mess this up you are about to crash horribly) + */ dev_warn_once(gpu->dev->dev, "Zap shader not enabled - using SECVID_TRUST_CNTL instead\n"); gpu_write(gpu, REG_A5XX_RBBM_SECVID_TRUST_CNTL, 0x0); + } else { + return ret; } /* Last step - yield the ringbuffer */ @@ -1066,6 +1100,7 @@ static void a5xx_dump(struct msm_gpu *gpu) static int a5xx_pm_resume(struct msm_gpu *gpu) { + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); int ret; /* Turn on the core power */ @@ -1073,6 +1108,15 @@ static int a5xx_pm_resume(struct msm_gpu *gpu) if (ret) return ret; + if (adreno_is_a510(adreno_gpu)) { + /* Halt the sp_input_clk at HM level */ + gpu_write(gpu, REG_A5XX_RBBM_CLOCK_CNTL, 0x00000055); + a5xx_set_hwcg(gpu, true); + /* Turn on sp_input_clk at HM level */ + gpu_rmw(gpu, REG_A5XX_RBBM_CLOCK_CNTL, 0xff, 0); + return 0; + } + /* Turn the RBCCU domain first to limit the chances of voltage droop */ gpu_write(gpu, REG_A5XX_GPMU_RBCCU_POWER_CNTL, 0x778000); @@ -1101,9 +1145,17 @@ static int a5xx_pm_resume(struct msm_gpu *gpu) static int a5xx_pm_suspend(struct msm_gpu *gpu) { + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + u32 mask = 0xf; + + /* A510 has 3 XIN ports in VBIF */ + if (adreno_is_a510(adreno_gpu)) + mask = 0x7; + /* Clear the VBIF pipe before shutting down */ - gpu_write(gpu, REG_A5XX_VBIF_XIN_HALT_CTRL0, 0xF); - spin_until((gpu_read(gpu, REG_A5XX_VBIF_XIN_HALT_CTRL1) & 0xF) == 0xF); + gpu_write(gpu, REG_A5XX_VBIF_XIN_HALT_CTRL0, mask); + spin_until((gpu_read(gpu, REG_A5XX_VBIF_XIN_HALT_CTRL1) & + mask) == mask); gpu_write(gpu, REG_A5XX_VBIF_XIN_HALT_CTRL0, 0); @@ -1289,7 +1341,7 @@ static void a5xx_gpu_state_destroy(struct kref *kref) kfree(a5xx_state); } -int a5xx_gpu_state_put(struct msm_gpu_state *state) +static int a5xx_gpu_state_put(struct msm_gpu_state *state) { if (IS_ERR_OR_NULL(state)) return 1; @@ -1299,8 +1351,8 @@ int a5xx_gpu_state_put(struct msm_gpu_state *state) #if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP) -void a5xx_show(struct msm_gpu *gpu, struct msm_gpu_state *state, - struct drm_printer *p) +static void a5xx_show(struct msm_gpu *gpu, struct msm_gpu_state *state, + struct drm_printer *p) { int i, j; u32 pos = 0; diff --git a/drivers/gpu/drm/msm/adreno/a5xx_power.c b/drivers/gpu/drm/msm/adreno/a5xx_power.c index a3a06db675ba..321a8061fd32 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_power.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_power.c @@ -297,6 +297,10 @@ int a5xx_power_init(struct msm_gpu *gpu) struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); int ret; + /* Not all A5xx chips have a GPMU */ + if (adreno_is_a510(adreno_gpu)) + return 0; + /* Set up the limits management */ if (adreno_is_a530(adreno_gpu)) a530_lm_setup(gpu); @@ -326,6 +330,9 @@ void a5xx_gpmu_ucode_init(struct msm_gpu *gpu) unsigned int *data, *ptr, *cmds; unsigned int cmds_size; + if (adreno_is_a510(adreno_gpu)) + return; + if (a5xx_gpu->gpmu_bo) return; diff --git a/drivers/gpu/drm/msm/adreno/a6xx.xml.h b/drivers/gpu/drm/msm/adreno/a6xx.xml.h index f44553ec3193..ed78fee2a262 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx.xml.h +++ b/drivers/gpu/drm/msm/adreno/a6xx.xml.h @@ -16,11 +16,11 @@ The rules-ng-ng source files this header was generated from are: - /home/robclark/src/envytools/rnndb/adreno/a3xx.xml ( 83840 bytes, from 2018-07-03 19:37:13) - /home/robclark/src/envytools/rnndb/adreno/a4xx.xml ( 112086 bytes, from 2018-07-03 19:37:13) - /home/robclark/src/envytools/rnndb/adreno/a5xx.xml ( 147240 bytes, from 2018-12-02 17:29:54) -- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml ( 140790 bytes, from 2018-12-02 17:29:54) +- /home/smasetty/playarea/envytools/rnndb/adreno/a6xx.xml ( 161969 bytes, from 2019-11-29 07:18:16) - /home/robclark/src/envytools/rnndb/adreno/a6xx_gmu.xml ( 10431 bytes, from 2018-09-14 13:03:07) - /home/robclark/src/envytools/rnndb/adreno/ocmem.xml ( 1773 bytes, from 2018-07-03 19:37:13) -Copyright (C) 2013-2018 by the following authors: +Copyright (C) 2013-2019 by the following authors: - Rob Clark <robdclark@gmail.com> (robclark) - Ilia Mirkin <imirkin@alum.mit.edu> (imirkin) @@ -2519,6 +2519,54 @@ static inline uint32_t A6XX_VBIF_TEST_BUS2_CTRL1_DATA_SEL(uint32_t val) #define REG_A6XX_VBIF_PERF_PWR_CNT_HIGH2 0x0000311a +#define REG_A6XX_GBIF_SCACHE_CNTL1 0x00003c02 + +#define REG_A6XX_GBIF_QSB_SIDE0 0x00003c03 + +#define REG_A6XX_GBIF_QSB_SIDE1 0x00003c04 + +#define REG_A6XX_GBIF_QSB_SIDE2 0x00003c05 + +#define REG_A6XX_GBIF_QSB_SIDE3 0x00003c06 + +#define REG_A6XX_GBIF_HALT 0x00003c45 + +#define REG_A6XX_GBIF_HALT_ACK 0x00003c46 + +#define REG_A6XX_GBIF_PERF_PWR_CNT_EN 0x00003cc0 + +#define REG_A6XX_GBIF_PERF_CNT_SEL 0x00003cc2 + +#define REG_A6XX_GBIF_PERF_PWR_CNT_SEL 0x00003cc3 + +#define REG_A6XX_GBIF_PERF_CNT_LOW0 0x00003cc4 + +#define REG_A6XX_GBIF_PERF_CNT_LOW1 0x00003cc5 + +#define REG_A6XX_GBIF_PERF_CNT_LOW2 0x00003cc6 + +#define REG_A6XX_GBIF_PERF_CNT_LOW3 0x00003cc7 + +#define REG_A6XX_GBIF_PERF_CNT_HIGH0 0x00003cc8 + +#define REG_A6XX_GBIF_PERF_CNT_HIGH1 0x00003cc9 + +#define REG_A6XX_GBIF_PERF_CNT_HIGH2 0x00003cca + +#define REG_A6XX_GBIF_PERF_CNT_HIGH3 0x00003ccb + +#define REG_A6XX_GBIF_PWR_CNT_LOW0 0x00003ccc + +#define REG_A6XX_GBIF_PWR_CNT_LOW1 0x00003ccd + +#define REG_A6XX_GBIF_PWR_CNT_LOW2 0x00003cce + +#define REG_A6XX_GBIF_PWR_CNT_HIGH0 0x00003ccf + +#define REG_A6XX_GBIF_PWR_CNT_HIGH1 0x00003cd0 + +#define REG_A6XX_GBIF_PWR_CNT_HIGH2 0x00003cd1 + #define REG_A6XX_RB_WINDOW_OFFSET2 0x000088d4 #define A6XX_RB_WINDOW_OFFSET2_WINDOW_OFFSET_DISABLE 0x80000000 #define A6XX_RB_WINDOW_OFFSET2_X__MASK 0x00007fff diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c index 2ca470eb5cb8..983afeaee737 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (c) 2017-2018 The Linux Foundation. All rights reserved. */ +/* Copyright (c) 2017-2019 The Linux Foundation. All rights reserved. */ #include <linux/clk.h> #include <linux/interconnect.h> @@ -149,6 +149,8 @@ void a6xx_gmu_set_freq(struct msm_gpu *gpu, unsigned long freq) if (freq == gmu->gpu_freqs[perf_index]) break; + gmu->current_perf_index = perf_index; + __a6xx_gmu_set_freq(gmu, perf_index); } @@ -433,6 +435,8 @@ static void __iomem *a6xx_gmu_get_mmio(struct platform_device *pdev, static void a6xx_gmu_rpmh_init(struct a6xx_gmu *gmu) { + struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu); + struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; struct platform_device *pdev = to_platform_device(gmu->dev); void __iomem *pdcptr = a6xx_gmu_get_mmio(pdev, "gmu_pdc"); void __iomem *seqptr = a6xx_gmu_get_mmio(pdev, "gmu_pdc_seq"); @@ -480,20 +484,34 @@ static void a6xx_gmu_rpmh_init(struct a6xx_gmu *gmu) pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_MSGID + 4, 0x10108); pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_ADDR + 4, 0x30000); pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_DATA + 4, 0x0); + pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_MSGID + 8, 0x10108); - pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_ADDR + 8, 0x30080); + if (adreno_is_a618(adreno_gpu)) + pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_ADDR + 8, 0x30090); + else + pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_ADDR + 8, 0x30080); pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_DATA + 8, 0x0); + pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD_ENABLE_BANK, 7); pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD_WAIT_FOR_CMPL_BANK, 0); pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CONTROL, 0); pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_MSGID, 0x10108); pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_ADDR, 0x30010); pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_DATA, 2); + pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_MSGID + 4, 0x10108); pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_ADDR + 4, 0x30000); - pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_DATA + 4, 0x3); + if (adreno_is_a618(adreno_gpu)) + pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_DATA + 4, 0x2); + else + pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_DATA + 4, 0x3); + + pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_MSGID + 8, 0x10108); - pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_ADDR + 8, 0x30080); + if (adreno_is_a618(adreno_gpu)) + pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_ADDR + 8, 0x30090); + else + pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_ADDR + 8, 0x30080); pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_DATA + 8, 0x3); /* Setup GPU PDC */ @@ -741,8 +759,8 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu) gmu_write(gmu, REG_A6XX_GMU_GMU2HOST_INTR_MASK, ~A6XX_HFI_IRQ_MASK); enable_irq(gmu->hfi_irq); - /* Set the GPU to the highest power frequency */ - __a6xx_gmu_set_freq(gmu, gmu->nr_gpu_freqs - 1); + /* Set the GPU to the current freq */ + __a6xx_gmu_set_freq(gmu, gmu->current_perf_index); /* * "enable" the GX power domain which won't actually do anything but it @@ -1166,13 +1184,15 @@ static int a6xx_gmu_pwrlevels_probe(struct a6xx_gmu *gmu) gmu->nr_gpu_freqs = a6xx_gmu_build_freq_table(&gpu->pdev->dev, gmu->gpu_freqs, ARRAY_SIZE(gmu->gpu_freqs)); + gmu->current_perf_index = gmu->nr_gpu_freqs - 1; + /* Build the list of RPMh votes that we'll send to the GMU */ return a6xx_gmu_rpmh_votes_init(gmu); } static int a6xx_gmu_clocks_probe(struct a6xx_gmu *gmu) { - int ret = msm_clk_bulk_get(gmu->dev, &gmu->clocks); + int ret = devm_clk_bulk_get_all(gmu->dev, &gmu->clocks); if (ret < 1) return ret; diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h index 39a26dd63674..2af91ed7ed0c 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h @@ -63,6 +63,9 @@ struct a6xx_gmu { struct clk_bulk_data *clocks; struct clk *core_clk; + /* current performance index set externally */ + int current_perf_index; + int nr_gpu_freqs; unsigned long gpu_freqs[16]; u32 gx_arc_votes[16]; diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index dc8ec2c94301..daf07800cde0 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (c) 2017-2018 The Linux Foundation. All rights reserved. */ +/* Copyright (c) 2017-2019 The Linux Foundation. All rights reserved. */ #include "msm_gem.h" @@ -378,6 +378,18 @@ static int a6xx_hw_init(struct msm_gpu *gpu) struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); int ret; + /* + * During a previous slumber, GBIF halt is asserted to ensure + * no further transaction can go through GPU before GPU + * headswitch is turned off. + * + * This halt is deasserted once headswitch goes off but + * incase headswitch doesn't goes off clear GBIF halt + * here to ensure GPU wake-up doesn't fail because of + * halted GPU transactions. + */ + gpu_write(gpu, REG_A6XX_GBIF_HALT, 0x0); + /* Make sure the GMU keeps the GPU on while we set it up */ a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET); @@ -406,12 +418,17 @@ static int a6xx_hw_init(struct msm_gpu *gpu) gpu_write(gpu, REG_A6XX_TPL1_ADDR_MODE_CNTL, 0x1); gpu_write(gpu, REG_A6XX_RBBM_SECVID_TSB_ADDR_MODE_CNTL, 0x1); - /* enable hardware clockgating */ - a6xx_set_hwcg(gpu, true); + /* + * enable hardware clockgating + * For now enable clock gating only for a630 + */ + if (adreno_is_a630(adreno_gpu)) + a6xx_set_hwcg(gpu, true); - /* VBIF start */ - gpu_write(gpu, REG_A6XX_VBIF_GATE_OFF_WRREQ_EN, 0x00000009); + /* VBIF/GBIF start*/ gpu_write(gpu, REG_A6XX_RBBM_VBIF_CLIENT_QOS_CNTL, 0x3); + if (adreno_is_a630(adreno_gpu)) + gpu_write(gpu, REG_A6XX_VBIF_GATE_OFF_WRREQ_EN, 0x00000009); /* Make all blocks contribute to the GPU BUSY perf counter */ gpu_write(gpu, REG_A6XX_RBBM_PERFCTR_GPU_BUSY_MASKED, 0xffffffff); @@ -537,12 +554,19 @@ static int a6xx_hw_init(struct msm_gpu *gpu) a6xx_flush(gpu, gpu->rb[0]); if (!a6xx_idle(gpu, gpu->rb[0])) return -EINVAL; - } else { - /* Print a warning so if we die, we know why */ + } else if (ret == -ENODEV) { + /* + * This device does not use zap shader (but print a warning + * just in case someone got their dt wrong.. hopefully they + * have a debug UART to realize the error of their ways... + * if you mess this up you are about to crash horribly) + */ dev_warn_once(gpu->dev->dev, "Zap shader not enabled - using SECVID_TRUST_CNTL instead\n"); gpu_write(gpu, REG_A6XX_RBBM_SECVID_TRUST_CNTL, 0x0); ret = 0; + } else { + return ret; } out: @@ -724,6 +748,39 @@ static const u32 a6xx_register_offsets[REG_ADRENO_REGISTER_MAX] = { REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_CNTL, REG_A6XX_CP_RB_CNTL), }; +#define GBIF_CLIENT_HALT_MASK BIT(0) +#define GBIF_ARB_HALT_MASK BIT(1) + +static void a6xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu) +{ + struct msm_gpu *gpu = &adreno_gpu->base; + + if(!a6xx_has_gbif(adreno_gpu)){ + gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0xf); + spin_until((gpu_read(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL1) & + 0xf) == 0xf); + gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0); + + return; + } + + /* Halt new client requests on GBIF */ + gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_CLIENT_HALT_MASK); + spin_until((gpu_read(gpu, REG_A6XX_GBIF_HALT_ACK) & + (GBIF_CLIENT_HALT_MASK)) == GBIF_CLIENT_HALT_MASK); + + /* Halt all AXI requests on GBIF */ + gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_ARB_HALT_MASK); + spin_until((gpu_read(gpu, REG_A6XX_GBIF_HALT_ACK) & + (GBIF_ARB_HALT_MASK)) == GBIF_ARB_HALT_MASK); + + /* + * GMU needs DDR access in slumber path. Deassert GBIF halt now + * to allow for GMU to access system memory. + */ + gpu_write(gpu, REG_A6XX_GBIF_HALT, 0x0); +} + static int a6xx_pm_resume(struct msm_gpu *gpu) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); @@ -748,6 +805,16 @@ static int a6xx_pm_suspend(struct msm_gpu *gpu) devfreq_suspend_device(gpu->devfreq.devfreq); + /* + * Make sure the GMU is idle before continuing (because some transitions + * may use VBIF + */ + a6xx_gmu_wait_for_idle(&a6xx_gpu->gmu); + + /* Clear the VBIF pipe before shutting down */ + /* FIXME: This accesses the GPU - do we need to make sure it is on? */ + a6xx_bus_clear_pending_transactions(adreno_gpu); + return a6xx_gmu_stop(a6xx_gpu); } diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h index 64399554f2dd..7239b8b60939 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (c) 2017 The Linux Foundation. All rights reserved. */ +/* Copyright (c) 2017, 2019 The Linux Foundation. All rights reserved. */ #ifndef __A6XX_GPU_H__ #define __A6XX_GPU_H__ @@ -42,6 +42,13 @@ struct a6xx_gpu { #define A6XX_PROTECT_RDONLY(_reg, _len) \ ((((_len) & 0x3FFF) << 18) | ((_reg) & 0x3FFFF)) +static inline bool a6xx_has_gbif(struct adreno_gpu *gpu) +{ + if(adreno_is_a630(gpu)) + return false; + + return true; +} int a6xx_gmu_resume(struct a6xx_gpu *gpu); int a6xx_gmu_stop(struct a6xx_gpu *gpu); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c index e686331fa089..d6023ba8033c 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (c) 2018 The Linux Foundation. All rights reserved. */ +/* Copyright (c) 2018-2019 The Linux Foundation. All rights reserved. */ #include <linux/ascii85.h> #include "msm_gem.h" @@ -320,6 +320,7 @@ static void a6xx_get_debugbus(struct msm_gpu *gpu, { struct resource *res; void __iomem *cxdbg = NULL; + int nr_debugbus_blocks; /* Set up the GX debug bus */ @@ -352,31 +353,33 @@ static void a6xx_get_debugbus(struct msm_gpu *gpu, cxdbg = ioremap(res->start, resource_size(res)); if (cxdbg) { - cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_CNTLT, + cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_CNTLT, A6XX_DBGC_CFG_DBGBUS_CNTLT_SEGT(0xf)); - cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_CNTLM, + cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_CNTLM, A6XX_DBGC_CFG_DBGBUS_CNTLM_ENABLE(0xf)); - cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_IVTL_0, 0); - cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_IVTL_1, 0); - cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_IVTL_2, 0); - cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_IVTL_3, 0); + cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_IVTL_0, 0); + cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_IVTL_1, 0); + cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_IVTL_2, 0); + cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_IVTL_3, 0); - cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_BYTEL_0, + cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_BYTEL_0, 0x76543210); - cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_BYTEL_1, + cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_BYTEL_1, 0xFEDCBA98); - cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_MASKL_0, 0); - cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_MASKL_1, 0); - cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_MASKL_2, 0); - cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_MASKL_3, 0); + cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_MASKL_0, 0); + cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_MASKL_1, 0); + cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_MASKL_2, 0); + cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_MASKL_3, 0); } - a6xx_state->debugbus = state_kcalloc(a6xx_state, - ARRAY_SIZE(a6xx_debugbus_blocks), - sizeof(*a6xx_state->debugbus)); + nr_debugbus_blocks = ARRAY_SIZE(a6xx_debugbus_blocks) + + (a6xx_has_gbif(to_adreno_gpu(gpu)) ? 1 : 0); + + a6xx_state->debugbus = state_kcalloc(a6xx_state, nr_debugbus_blocks, + sizeof(*a6xx_state->debugbus)); if (a6xx_state->debugbus) { int i; @@ -388,15 +391,31 @@ static void a6xx_get_debugbus(struct msm_gpu *gpu, &a6xx_state->debugbus[i]); a6xx_state->nr_debugbus = ARRAY_SIZE(a6xx_debugbus_blocks); + + /* + * GBIF has same debugbus as of other GPU blocks, fall back to + * default path if GPU uses GBIF, also GBIF uses exactly same + * ID as of VBIF. + */ + if (a6xx_has_gbif(to_adreno_gpu(gpu))) { + a6xx_get_debugbus_block(gpu, a6xx_state, + &a6xx_gbif_debugbus_block, + &a6xx_state->debugbus[i]); + + a6xx_state->nr_debugbus += 1; + } } - a6xx_state->vbif_debugbus = - state_kcalloc(a6xx_state, 1, - sizeof(*a6xx_state->vbif_debugbus)); + /* Dump the VBIF debugbus on applicable targets */ + if (!a6xx_has_gbif(to_adreno_gpu(gpu))) { + a6xx_state->vbif_debugbus = + state_kcalloc(a6xx_state, 1, + sizeof(*a6xx_state->vbif_debugbus)); - if (a6xx_state->vbif_debugbus) - a6xx_get_vbif_debugbus_block(gpu, a6xx_state, - a6xx_state->vbif_debugbus); + if (a6xx_state->vbif_debugbus) + a6xx_get_vbif_debugbus_block(gpu, a6xx_state, + a6xx_state->vbif_debugbus); + } if (cxdbg) { a6xx_state->cx_debugbus = @@ -770,14 +789,16 @@ static void a6xx_get_gmu_registers(struct msm_gpu *gpu, &a6xx_state->gmu_registers[1]); } +#define A6XX_GBIF_REGLIST_SIZE 1 static void a6xx_get_registers(struct msm_gpu *gpu, struct a6xx_gpu_state *a6xx_state, struct a6xx_crashdumper *dumper) { int i, count = ARRAY_SIZE(a6xx_ahb_reglist) + ARRAY_SIZE(a6xx_reglist) + - ARRAY_SIZE(a6xx_hlsq_reglist); + ARRAY_SIZE(a6xx_hlsq_reglist) + A6XX_GBIF_REGLIST_SIZE; int index = 0; + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); a6xx_state->registers = state_kcalloc(a6xx_state, count, sizeof(*a6xx_state->registers)); @@ -792,6 +813,15 @@ static void a6xx_get_registers(struct msm_gpu *gpu, a6xx_state, &a6xx_ahb_reglist[i], &a6xx_state->registers[index++]); + if (a6xx_has_gbif(adreno_gpu)) + a6xx_get_ahb_gpu_registers(gpu, + a6xx_state, &a6xx_gbif_reglist, + &a6xx_state->registers[index++]); + else + a6xx_get_ahb_gpu_registers(gpu, + a6xx_state, &a6xx_vbif_reglist, + &a6xx_state->registers[index++]); + for (i = 0; i < ARRAY_SIZE(a6xx_reglist); i++) a6xx_get_crashdumper_registers(gpu, a6xx_state, &a6xx_reglist[i], diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h index 68cccfa2870a..e67c20c415af 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (c) 2018 The Linux Foundation. All rights reserved. */ +/* Copyright (c) 2018-2019 The Linux Foundation. All rights reserved. */ #ifndef _A6XX_CRASH_DUMP_H_ #define _A6XX_CRASH_DUMP_H_ @@ -307,11 +307,20 @@ static const u32 a6xx_vbif_registers[] = { 0x3410, 0x3410, 0x3800, 0x3801, }; +static const u32 a6xx_gbif_registers[] = { + 0x3C00, 0X3C0B, 0X3C40, 0X3C47, 0X3CC0, 0X3CD1, 0xE3A, 0xE3A, +}; + static const struct a6xx_registers a6xx_ahb_reglist[] = { REGS(a6xx_ahb_registers, 0, 0), - REGS(a6xx_vbif_registers, 0, 0), }; +static const struct a6xx_registers a6xx_vbif_reglist = + REGS(a6xx_vbif_registers, 0, 0); + +static const struct a6xx_registers a6xx_gbif_reglist = + REGS(a6xx_gbif_registers, 0, 0); + static const u32 a6xx_gmu_gx_registers[] = { /* GMU GX */ 0x0000, 0x0000, 0x0010, 0x0013, 0x0016, 0x0016, 0x0018, 0x001b, @@ -422,6 +431,9 @@ static const struct a6xx_debugbus_block { DEBUGBUS(A6XX_DBGBUS_TPL1_3, 0x100), }; +static const struct a6xx_debugbus_block a6xx_gbif_debugbus_block = + DEBUGBUS(A6XX_DBGBUS_VBIF, 0x100); + static const struct a6xx_debugbus_block a6xx_cx_debugbus_blocks[] = { DEBUGBUS(A6XX_DBGBUS_GMU_CX, 0x100), DEBUGBUS(A6XX_DBGBUS_CX, 0x100), diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c index 40133a43960c..cb3a6e597d76 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_device.c +++ b/drivers/gpu/drm/msm/adreno/adreno_device.c @@ -115,6 +115,21 @@ static const struct adreno_info gpulist[] = { .inactive_period = DRM_MSM_INACTIVE_PERIOD, .init = a4xx_gpu_init, }, { + .rev = ADRENO_REV(5, 1, 0, ANY_ID), + .revn = 510, + .name = "A510", + .fw = { + [ADRENO_FW_PM4] = "a530_pm4.fw", + [ADRENO_FW_PFP] = "a530_pfp.fw", + }, + .gmem = SZ_256K, + /* + * Increase inactive period to 250 to avoid bouncing + * the GDSC which appears to make it grumpy + */ + .inactive_period = 250, + .init = a5xx_gpu_init, + }, { .rev = ADRENO_REV(5, 3, 0, 2), .revn = 530, .name = "A530", @@ -152,6 +167,17 @@ static const struct adreno_info gpulist[] = { .init = a5xx_gpu_init, .zapfw = "a540_zap.mdt", }, { + .rev = ADRENO_REV(6, 1, 8, ANY_ID), + .revn = 618, + .name = "A618", + .fw = { + [ADRENO_FW_SQE] = "a630_sqe.fw", + [ADRENO_FW_GMU] = "a630_gmu.bin", + }, + .gmem = SZ_512K, + .inactive_period = DRM_MSM_INACTIVE_PERIOD, + .init = a6xx_gpu_init, + }, { .rev = ADRENO_REV(6, 3, 0, ANY_ID), .revn = 630, .name = "A630", @@ -181,6 +207,7 @@ MODULE_FIRMWARE("qcom/a530_zap.b01"); MODULE_FIRMWARE("qcom/a530_zap.b02"); MODULE_FIRMWARE("qcom/a630_sqe.fw"); MODULE_FIRMWARE("qcom/a630_gmu.bin"); +MODULE_FIRMWARE("qcom/a630_zap.mbn"); static inline bool _rev_match(uint8_t entry, uint8_t id) { diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index 048c8be426f3..7fd29829b2fa 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -14,6 +14,7 @@ #include <linux/pm_opp.h> #include <linux/slab.h> #include <linux/soc/qcom/mdt_loader.h> +#include <soc/qcom/ocmem.h> #include "adreno_gpu.h" #include "msm_gem.h" #include "msm_mmu.h" @@ -25,6 +26,7 @@ static int zap_shader_load_mdt(struct msm_gpu *gpu, const char *fwname, { struct device *dev = &gpu->pdev->dev; const struct firmware *fw; + const char *signed_fwname = NULL; struct device_node *np, *mem_np; struct resource r; phys_addr_t mem_phys; @@ -57,8 +59,43 @@ static int zap_shader_load_mdt(struct msm_gpu *gpu, const char *fwname, mem_phys = r.start; - /* Request the MDT file for the firmware */ - fw = adreno_request_fw(to_adreno_gpu(gpu), fwname); + /* + * Check for a firmware-name property. This is the new scheme + * to handle firmware that may be signed with device specific + * keys, allowing us to have a different zap fw path for different + * devices. + * + * If the firmware-name property is found, we bypass the + * adreno_request_fw() mechanism, because we don't need to handle + * the /lib/firmware/qcom/... vs /lib/firmware/... case. + * + * If the firmware-name property is not found, for backwards + * compatibility we fall back to the fwname from the gpulist + * table. + */ + of_property_read_string_index(np, "firmware-name", 0, &signed_fwname); + if (signed_fwname) { + fwname = signed_fwname; + ret = request_firmware_direct(&fw, fwname, gpu->dev->dev); + if (ret) + fw = ERR_PTR(ret); + } else if (fwname) { + /* Request the MDT file from the default location: */ + fw = adreno_request_fw(to_adreno_gpu(gpu), fwname); + } else { + /* + * For new targets, we require the firmware-name property, + * if a zap-shader is required, rather than falling back + * to a firmware name specified in gpulist. + * + * Because the firmware is signed with a (potentially) + * device specific key, having the name come from gpulist + * was a bad idea, and is only provided for backwards + * compatibility for older targets. + */ + return -ENODEV; + } + if (IS_ERR(fw)) { DRM_DEV_ERROR(dev, "Unable to load %s\n", fwname); return PTR_ERR(fw); @@ -94,7 +131,7 @@ static int zap_shader_load_mdt(struct msm_gpu *gpu, const char *fwname, * not. But since we've already gotten through adreno_request_fw() * we know which of the two cases it is: */ - if (to_adreno_gpu(gpu)->fwloc == FW_LOCATION_LEGACY) { + if (signed_fwname || (to_adreno_gpu(gpu)->fwloc == FW_LOCATION_LEGACY)) { ret = qcom_mdt_load(dev, fw, fwname, pasid, mem_region, mem_phys, mem_size, NULL); } else { @@ -145,14 +182,6 @@ int adreno_zap_shader_load(struct msm_gpu *gpu, u32 pasid) return -EPROBE_DEFER; } - /* Each GPU has a target specific zap shader firmware name to use */ - if (!adreno_gpu->info->zapfw) { - zap_available = false; - DRM_DEV_ERROR(&pdev->dev, - "Zap shader firmware file not specified for this target\n"); - return -ENODEV; - } - return zap_shader_load_mdt(gpu, adreno_gpu->info->zapfw, pasid); } @@ -825,7 +854,7 @@ static int adreno_get_legacy_pwrlevels(struct device *dev) node = of_get_compatible_child(dev->of_node, "qcom,gpu-pwrlevels"); if (!node) { - DRM_DEV_ERROR(dev, "Could not find the GPU powerlevels\n"); + DRM_DEV_DEBUG(dev, "Could not find the GPU powerlevels\n"); return -ENXIO; } @@ -886,13 +915,63 @@ static int adreno_get_pwrlevels(struct device *dev, DBG("fast_rate=%u, slow_rate=27000000", gpu->fast_rate); /* Check for an interconnect path for the bus */ - gpu->icc_path = of_icc_get(dev, NULL); + gpu->icc_path = of_icc_get(dev, "gfx-mem"); + if (!gpu->icc_path) { + /* + * Keep compatbility with device trees that don't have an + * interconnect-names property. + */ + gpu->icc_path = of_icc_get(dev, NULL); + } if (IS_ERR(gpu->icc_path)) gpu->icc_path = NULL; + gpu->ocmem_icc_path = of_icc_get(dev, "ocmem"); + if (IS_ERR(gpu->ocmem_icc_path)) + gpu->ocmem_icc_path = NULL; + + return 0; +} + +int adreno_gpu_ocmem_init(struct device *dev, struct adreno_gpu *adreno_gpu, + struct adreno_ocmem *adreno_ocmem) +{ + struct ocmem_buf *ocmem_hdl; + struct ocmem *ocmem; + + ocmem = of_get_ocmem(dev); + if (IS_ERR(ocmem)) { + if (PTR_ERR(ocmem) == -ENODEV) { + /* + * Return success since either the ocmem property was + * not specified in device tree, or ocmem support is + * not compiled into the kernel. + */ + return 0; + } + + return PTR_ERR(ocmem); + } + + ocmem_hdl = ocmem_allocate(ocmem, OCMEM_GRAPHICS, adreno_gpu->gmem); + if (IS_ERR(ocmem_hdl)) + return PTR_ERR(ocmem_hdl); + + adreno_ocmem->ocmem = ocmem; + adreno_ocmem->base = ocmem_hdl->addr; + adreno_ocmem->hdl = ocmem_hdl; + adreno_gpu->gmem = ocmem_hdl->len; + return 0; } +void adreno_gpu_ocmem_cleanup(struct adreno_ocmem *adreno_ocmem) +{ + if (adreno_ocmem && adreno_ocmem->base) + ocmem_free(adreno_ocmem->ocmem, OCMEM_GRAPHICS, + adreno_ocmem->hdl); +} + int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev, struct adreno_gpu *adreno_gpu, const struct adreno_gpu_funcs *funcs, int nr_rings) @@ -937,6 +1016,7 @@ void adreno_gpu_cleanup(struct adreno_gpu *adreno_gpu) release_firmware(adreno_gpu->fw[i]); icc_put(gpu->icc_path); + icc_put(gpu->ocmem_icc_path); msm_gpu_cleanup(&adreno_gpu->base); } diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h index c7441fb8313e..9ff4e550e7bd 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h @@ -3,7 +3,7 @@ * Copyright (C) 2013 Red Hat * Author: Rob Clark <robdclark@gmail.com> * - * Copyright (c) 2014,2017 The Linux Foundation. All rights reserved. + * Copyright (c) 2014,2017, 2019 The Linux Foundation. All rights reserved. */ #ifndef __ADRENO_GPU_H__ @@ -126,6 +126,12 @@ struct adreno_gpu { }; #define to_adreno_gpu(x) container_of(x, struct adreno_gpu, base) +struct adreno_ocmem { + struct ocmem *ocmem; + unsigned long base; + void *hdl; +}; + /* platform config data (ie. from DT, or pdata) */ struct adreno_platform_config { struct adreno_rev rev; @@ -206,6 +212,11 @@ static inline int adreno_is_a430(struct adreno_gpu *gpu) return gpu->revn == 430; } +static inline int adreno_is_a510(struct adreno_gpu *gpu) +{ + return gpu->revn == 510; +} + static inline int adreno_is_a530(struct adreno_gpu *gpu) { return gpu->revn == 530; @@ -216,6 +227,16 @@ static inline int adreno_is_a540(struct adreno_gpu *gpu) return gpu->revn == 540; } +static inline int adreno_is_a618(struct adreno_gpu *gpu) +{ + return gpu->revn == 618; +} + +static inline int adreno_is_a630(struct adreno_gpu *gpu) +{ + return gpu->revn == 630; +} + int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value); const struct firmware *adreno_request_fw(struct adreno_gpu *adreno_gpu, const char *fwname); @@ -236,6 +257,10 @@ void adreno_dump(struct msm_gpu *gpu); void adreno_wait_ring(struct msm_ringbuffer *ring, uint32_t ndwords); struct msm_ringbuffer *adreno_active_ring(struct msm_gpu *gpu); +int adreno_gpu_ocmem_init(struct device *dev, struct adreno_gpu *adreno_gpu, + struct adreno_ocmem *ocmem); +void adreno_gpu_ocmem_cleanup(struct adreno_ocmem *ocmem); + int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev, struct adreno_gpu *gpu, const struct adreno_gpu_funcs *funcs, int nr_rings); @@ -315,10 +340,7 @@ OUT_PKT7(struct msm_ringbuffer *ring, uint8_t opcode, uint16_t cnt) static inline bool adreno_reg_check(struct adreno_gpu *gpu, enum adreno_regs offset_name) { - if (offset_name >= REG_ADRENO_REGISTER_MAX || - !gpu->reg_offsets[offset_name]) { - BUG(); - } + BUG_ON(offset_name >= REG_ADRENO_REGISTER_MAX || !gpu->reg_offsets[offset_name]); /* * REG_SKIP is a special value that tell us that the register in |
