This is a note to let you know that I've just added the patch titled
drm/msm/adreno: Simplify read64/write64 helpers
to the 6.1-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
drm-msm-adreno-simplify-read64-write64-helpers.patch
and it can be found in the queue-6.1 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit 966e633be4db8f49c40132061c985a3f7c2dfd10
Author: Rob Clark <robdclark@xxxxxxxxxxxx>
Date: Mon Nov 14 11:30:40 2022 -0800
drm/msm/adreno: Simplify read64/write64 helpers
[ Upstream commit cade05b2a88558847984287dd389fae0c7de31d6 ]
The _HI reg is always following the _LO reg, so no need to pass these
offsets seprately.
Signed-off-by: Rob Clark <robdclark@xxxxxxxxxxxx>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@xxxxxxxxxx>
Reviewed-by: Akhil P Oommen <quic_akhilpo@xxxxxxxxxxx>
Patchwork: https://patchwork.freedesktop.org/patch/511581/
Link: https://lore.kernel.org/r/20221114193049.1533391-2-robdclark@xxxxxxxxx
Stable-dep-of: ca090c837b43 ("drm/msm: fix missing wq allocation error handling")
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
index 7cb8d9849c073..a10feb8a4194a 100644
--- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
@@ -606,8 +606,7 @@ static int a4xx_pm_suspend(struct msm_gpu *gpu) {
static int a4xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value)
{
- *value = gpu_read64(gpu, REG_A4XX_RBBM_PERFCTR_CP_0_LO,
- REG_A4XX_RBBM_PERFCTR_CP_0_HI);
+ *value = gpu_read64(gpu, REG_A4XX_RBBM_PERFCTR_CP_0_LO);
return 0;
}
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index 02ff306f96f42..24feae285ccd6 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -605,11 +605,9 @@ static int a5xx_ucode_init(struct msm_gpu *gpu)
a5xx_ucode_check_version(a5xx_gpu, a5xx_gpu->pfp_bo);
}
- gpu_write64(gpu, REG_A5XX_CP_ME_INSTR_BASE_LO,
- REG_A5XX_CP_ME_INSTR_BASE_HI, a5xx_gpu->pm4_iova);
+ gpu_write64(gpu, REG_A5XX_CP_ME_INSTR_BASE_LO, a5xx_gpu->pm4_iova);
- gpu_write64(gpu, REG_A5XX_CP_PFP_INSTR_BASE_LO,
- REG_A5XX_CP_PFP_INSTR_BASE_HI, a5xx_gpu->pfp_iova);
+ gpu_write64(gpu, REG_A5XX_CP_PFP_INSTR_BASE_LO, a5xx_gpu->pfp_iova);
return 0;
}
@@ -868,8 +866,7 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
* memory rendering at this point in time and we don't want to block off
* part of the virtual memory space.
*/
- gpu_write64(gpu, REG_A5XX_RBBM_SECVID_TSB_TRUSTED_BASE_LO,
- REG_A5XX_RBBM_SECVID_TSB_TRUSTED_BASE_HI, 0x00000000);
+ gpu_write64(gpu, REG_A5XX_RBBM_SECVID_TSB_TRUSTED_BASE_LO, 0x00000000);
gpu_write(gpu, REG_A5XX_RBBM_SECVID_TSB_TRUSTED_SIZE, 0x00000000);
/* Put the GPU into 64 bit by default */
@@ -908,8 +905,7 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
return ret;
/* Set the ringbuffer address */
- gpu_write64(gpu, REG_A5XX_CP_RB_BASE, REG_A5XX_CP_RB_BASE_HI,
- gpu->rb[0]->iova);
+ gpu_write64(gpu, REG_A5XX_CP_RB_BASE, gpu->rb[0]->iova);
/*
* If the microcode supports the WHERE_AM_I opcode then we can use that
@@ -936,7 +932,7 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
}
gpu_write64(gpu, REG_A5XX_CP_RB_RPTR_ADDR,
- REG_A5XX_CP_RB_RPTR_ADDR_HI, shadowptr(a5xx_gpu, gpu->rb[0]));
+ shadowptr(a5xx_gpu, gpu->rb[0]));
} else if (gpu->nr_rings > 1) {
/* Disable preemption if WHERE_AM_I isn't available */
a5xx_preempt_fini(gpu);
@@ -1239,9 +1235,9 @@ static void a5xx_fault_detect_irq(struct msm_gpu *gpu)
gpu_read(gpu, REG_A5XX_RBBM_STATUS),
gpu_read(gpu, REG_A5XX_CP_RB_RPTR),
gpu_read(gpu, REG_A5XX_CP_RB_WPTR),
- gpu_read64(gpu, REG_A5XX_CP_IB1_BASE, REG_A5XX_CP_IB1_BASE_HI),
+ gpu_read64(gpu, REG_A5XX_CP_IB1_BASE),
gpu_read(gpu, REG_A5XX_CP_IB1_BUFSZ),
- gpu_read64(gpu, REG_A5XX_CP_IB2_BASE, REG_A5XX_CP_IB2_BASE_HI),
+ gpu_read64(gpu, REG_A5XX_CP_IB2_BASE),
gpu_read(gpu, REG_A5XX_CP_IB2_BUFSZ));
/* Turn off the hangcheck timer to keep it from bothering us */
@@ -1427,8 +1423,7 @@ static int a5xx_pm_suspend(struct msm_gpu *gpu)
static int a5xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value)
{
- *value = gpu_read64(gpu, REG_A5XX_RBBM_ALWAYSON_COUNTER_LO,
- REG_A5XX_RBBM_ALWAYSON_COUNTER_HI);
+ *value = gpu_read64(gpu, REG_A5XX_RBBM_ALWAYSON_COUNTER_LO);
return 0;
}
@@ -1465,8 +1460,7 @@ static int a5xx_crashdumper_run(struct msm_gpu *gpu,
if (IS_ERR_OR_NULL(dumper->ptr))
return -EINVAL;
- gpu_write64(gpu, REG_A5XX_CP_CRASH_SCRIPT_BASE_LO,
- REG_A5XX_CP_CRASH_SCRIPT_BASE_HI, dumper->iova);
+ gpu_write64(gpu, REG_A5XX_CP_CRASH_SCRIPT_BASE_LO, dumper->iova);
gpu_write(gpu, REG_A5XX_CP_CRASH_DUMP_CNTL, 1);
@@ -1666,8 +1660,7 @@ static u64 a5xx_gpu_busy(struct msm_gpu *gpu, unsigned long *out_sample_rate)
{
u64 busy_cycles;
- busy_cycles = gpu_read64(gpu, REG_A5XX_RBBM_PERFCTR_RBBM_0_LO,
- REG_A5XX_RBBM_PERFCTR_RBBM_0_HI);
+ busy_cycles = gpu_read64(gpu, REG_A5XX_RBBM_PERFCTR_RBBM_0_LO);
*out_sample_rate = clk_get_rate(gpu->core_clk);
return busy_cycles;
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c
index e0eef47dae632..f58dd564d122b 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c
@@ -137,7 +137,6 @@ void a5xx_preempt_trigger(struct msm_gpu *gpu)
/* Set the address of the incoming preemption record */
gpu_write64(gpu, REG_A5XX_CP_CONTEXT_SWITCH_RESTORE_ADDR_LO,
- REG_A5XX_CP_CONTEXT_SWITCH_RESTORE_ADDR_HI,
a5xx_gpu->preempt_iova[ring->id]);
a5xx_gpu->next_ring = ring;
@@ -212,8 +211,7 @@ void a5xx_preempt_hw_init(struct msm_gpu *gpu)
}
/* Write a 0 to signal that we aren't switching pagetables */
- gpu_write64(gpu, REG_A5XX_CP_CONTEXT_SWITCH_SMMU_INFO_LO,
- REG_A5XX_CP_CONTEXT_SWITCH_SMMU_INFO_HI, 0);
+ gpu_write64(gpu, REG_A5XX_CP_CONTEXT_SWITCH_SMMU_INFO_LO, 0);
/* Reset the preemption state */
set_preempt_state(a5xx_gpu, PREEMPT_NONE);
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index 9d7fc44c1e2a9..dc53466864b05 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -247,8 +247,7 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
OUT_RING(ring, submit->seqno);
trace_msm_gpu_submit_flush(submit,
- gpu_read64(gpu, REG_A6XX_CP_ALWAYS_ON_COUNTER_LO,
- REG_A6XX_CP_ALWAYS_ON_COUNTER_HI));
+ gpu_read64(gpu, REG_A6XX_CP_ALWAYS_ON_COUNTER_LO));
a6xx_flush(gpu, ring);
}
@@ -947,8 +946,7 @@ static int a6xx_ucode_init(struct msm_gpu *gpu)
}
}
- gpu_write64(gpu, REG_A6XX_CP_SQE_INSTR_BASE,
- REG_A6XX_CP_SQE_INSTR_BASE+1, a6xx_gpu->sqe_iova);
+ gpu_write64(gpu, REG_A6XX_CP_SQE_INSTR_BASE, a6xx_gpu->sqe_iova);
return 0;
}
@@ -999,8 +997,7 @@ static int hw_init(struct msm_gpu *gpu)
* memory rendering at this point in time and we don't want to block off
* part of the virtual memory space.
*/
- gpu_write64(gpu, REG_A6XX_RBBM_SECVID_TSB_TRUSTED_BASE_LO,
- REG_A6XX_RBBM_SECVID_TSB_TRUSTED_BASE_HI, 0x00000000);
+ gpu_write64(gpu, REG_A6XX_RBBM_SECVID_TSB_TRUSTED_BASE_LO, 0x00000000);
gpu_write(gpu, REG_A6XX_RBBM_SECVID_TSB_TRUSTED_SIZE, 0x00000000);
/* Turn on 64 bit addressing for all blocks */
@@ -1049,11 +1046,9 @@ static int hw_init(struct msm_gpu *gpu)
if (!adreno_is_a650_family(adreno_gpu)) {
/* Set the GMEM VA range [0x100000:0x100000 + gpu->gmem - 1] */
- gpu_write64(gpu, REG_A6XX_UCHE_GMEM_RANGE_MIN_LO,
- REG_A6XX_UCHE_GMEM_RANGE_MIN_HI, 0x00100000);
+ gpu_write64(gpu, REG_A6XX_UCHE_GMEM_RANGE_MIN_LO, 0x00100000);
gpu_write64(gpu, REG_A6XX_UCHE_GMEM_RANGE_MAX_LO,
- REG_A6XX_UCHE_GMEM_RANGE_MAX_HI,
0x00100000 + adreno_gpu->gmem - 1);
}
@@ -1145,8 +1140,7 @@ static int hw_init(struct msm_gpu *gpu)
goto out;
/* Set the ringbuffer address */
- gpu_write64(gpu, REG_A6XX_CP_RB_BASE, REG_A6XX_CP_RB_BASE_HI,
- gpu->rb[0]->iova);
+ gpu_write64(gpu, REG_A6XX_CP_RB_BASE, gpu->rb[0]->iova);
/* Targets that support extended APRIV can use the RPTR shadow from
* hardware but all the other ones need to disable the feature. Targets
@@ -1178,7 +1172,6 @@ static int hw_init(struct msm_gpu *gpu)
}
gpu_write64(gpu, REG_A6XX_CP_RB_RPTR_ADDR_LO,
- REG_A6XX_CP_RB_RPTR_ADDR_HI,
shadowptr(a6xx_gpu, gpu->rb[0]));
}
@@ -1506,9 +1499,9 @@ static void a6xx_fault_detect_irq(struct msm_gpu *gpu)
gpu_read(gpu, REG_A6XX_RBBM_STATUS),
gpu_read(gpu, REG_A6XX_CP_RB_RPTR),
gpu_read(gpu, REG_A6XX_CP_RB_WPTR),
- gpu_read64(gpu, REG_A6XX_CP_IB1_BASE, REG_A6XX_CP_IB1_BASE_HI),
+ gpu_read64(gpu, REG_A6XX_CP_IB1_BASE),
gpu_read(gpu, REG_A6XX_CP_IB1_REM_SIZE),
- gpu_read64(gpu, REG_A6XX_CP_IB2_BASE, REG_A6XX_CP_IB2_BASE_HI),
+ gpu_read64(gpu, REG_A6XX_CP_IB2_BASE),
gpu_read(gpu, REG_A6XX_CP_IB2_REM_SIZE));
/* Turn off the hangcheck timer to keep it from bothering us */
@@ -1719,8 +1712,7 @@ static int a6xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value)
/* Force the GPU power on so we can read this register */
a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_PERFCOUNTER_SET);
- *value = gpu_read64(gpu, REG_A6XX_CP_ALWAYS_ON_COUNTER_LO,
- REG_A6XX_CP_ALWAYS_ON_COUNTER_HI);
+ *value = gpu_read64(gpu, REG_A6XX_CP_ALWAYS_ON_COUNTER_LO);
a6xx_gmu_clear_oob(&a6xx_gpu->gmu, GMU_OOB_PERFCOUNTER_SET);
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
index a5c3d1ed255a6..a023d5f962dce 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
@@ -147,8 +147,7 @@ static int a6xx_crashdumper_run(struct msm_gpu *gpu,
/* Make sure all pending memory writes are posted */
wmb();
- gpu_write64(gpu, REG_A6XX_CP_CRASH_SCRIPT_BASE_LO,
- REG_A6XX_CP_CRASH_SCRIPT_BASE_HI, dumper->iova);
+ gpu_write64(gpu, REG_A6XX_CP_CRASH_SCRIPT_BASE_LO, dumper->iova);
gpu_write(gpu, REG_A6XX_CP_CRASH_DUMP_CNTL, 1);
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index a89bfdc3d7f90..7a36e0784f067 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -548,7 +548,7 @@ static inline void gpu_rmw(struct msm_gpu *gpu, u32 reg, u32 mask, u32 or)
msm_rmw(gpu->mmio + (reg << 2), mask, or);
}
-static inline u64 gpu_read64(struct msm_gpu *gpu, u32 lo, u32 hi)
+static inline u64 gpu_read64(struct msm_gpu *gpu, u32 reg)
{
u64 val;
@@ -566,17 +566,17 @@ static inline u64 gpu_read64(struct msm_gpu *gpu, u32 lo, u32 hi)
* when the lo is read, so make sure to read the lo first to trigger
* that
*/
- val = (u64) msm_readl(gpu->mmio + (lo << 2));
- val |= ((u64) msm_readl(gpu->mmio + (hi << 2)) << 32);
+ val = (u64) msm_readl(gpu->mmio + (reg << 2));
+ val |= ((u64) msm_readl(gpu->mmio + ((reg + 1) << 2)) << 32);
return val;
}
-static inline void gpu_write64(struct msm_gpu *gpu, u32 lo, u32 hi, u64 val)
+static inline void gpu_write64(struct msm_gpu *gpu, u32 reg, u64 val)
{
/* Why not a writeq here? Read the screed above */
- msm_writel(lower_32_bits(val), gpu->mmio + (lo << 2));
- msm_writel(upper_32_bits(val), gpu->mmio + (hi << 2));
+ msm_writel(lower_32_bits(val), gpu->mmio + (reg << 2));
+ msm_writel(upper_32_bits(val), gpu->mmio + ((reg + 1) << 2));
}
int msm_gpu_pm_suspend(struct msm_gpu *gpu);
