#include <linux/bitfield.h>
#include <linux/devfreq.h>
+#include <linux/nvmem-consumer.h>
#include <linux/soc/qcom/llcc-qcom.h>
#define GPU_PAS_ID 13
* GPU registers so we need to add 0x1a800 to the register value on A630
* to get the right value from PM4.
*/
- get_stats_counter(ring, REG_A6XX_GMU_ALWAYS_ON_COUNTER_L + 0x1a800,
+ get_stats_counter(ring, REG_A6XX_CP_ALWAYS_ON_COUNTER_LO,
rbmemptr_stats(ring, index, alwayson_start));
/* Invalidate CCU depth and color */
get_stats_counter(ring, REG_A6XX_RBBM_PERFCTR_CP_0_LO,
rbmemptr_stats(ring, index, cpcycles_end));
- get_stats_counter(ring, REG_A6XX_GMU_ALWAYS_ON_COUNTER_L + 0x1a800,
+ get_stats_counter(ring, REG_A6XX_CP_ALWAYS_ON_COUNTER_LO,
rbmemptr_stats(ring, index, alwayson_end));
/* Write the fence to the scratch register */
OUT_RING(ring, submit->seqno);
trace_msm_gpu_submit_flush(submit,
- gmu_read64(&a6xx_gpu->gmu, REG_A6XX_GMU_ALWAYS_ON_COUNTER_L,
- REG_A6XX_GMU_ALWAYS_ON_COUNTER_H));
+ gpu_read64(gpu, REG_A6XX_CP_ALWAYS_ON_COUNTER_LO,
+ REG_A6XX_CP_ALWAYS_ON_COUNTER_HI));
a6xx_flush(gpu, ring);
}
gpu_write(gpu, REG_A6XX_RBBM_CLOCK_CNTL, state ? clock_cntl_on : 0);
}
+/* For a615, a616, a618, A619, a630, a640 and a680 */
+static const u32 a6xx_protect[] = {
+ A6XX_PROTECT_RDONLY(0x00000, 0x04ff),
+ A6XX_PROTECT_RDONLY(0x00501, 0x0005),
+ A6XX_PROTECT_RDONLY(0x0050b, 0x02f4),
+ A6XX_PROTECT_NORDWR(0x0050e, 0x0000),
+ A6XX_PROTECT_NORDWR(0x00510, 0x0000),
+ A6XX_PROTECT_NORDWR(0x00534, 0x0000),
+ A6XX_PROTECT_NORDWR(0x00800, 0x0082),
+ A6XX_PROTECT_NORDWR(0x008a0, 0x0008),
+ A6XX_PROTECT_NORDWR(0x008ab, 0x0024),
+ A6XX_PROTECT_RDONLY(0x008de, 0x00ae),
+ A6XX_PROTECT_NORDWR(0x00900, 0x004d),
+ A6XX_PROTECT_NORDWR(0x0098d, 0x0272),
+ A6XX_PROTECT_NORDWR(0x00e00, 0x0001),
+ A6XX_PROTECT_NORDWR(0x00e03, 0x000c),
+ A6XX_PROTECT_NORDWR(0x03c00, 0x00c3),
+ A6XX_PROTECT_RDONLY(0x03cc4, 0x1fff),
+ A6XX_PROTECT_NORDWR(0x08630, 0x01cf),
+ A6XX_PROTECT_NORDWR(0x08e00, 0x0000),
+ A6XX_PROTECT_NORDWR(0x08e08, 0x0000),
+ A6XX_PROTECT_NORDWR(0x08e50, 0x001f),
+ A6XX_PROTECT_NORDWR(0x09624, 0x01db),
+ A6XX_PROTECT_NORDWR(0x09e70, 0x0001),
+ A6XX_PROTECT_NORDWR(0x09e78, 0x0187),
+ A6XX_PROTECT_NORDWR(0x0a630, 0x01cf),
+ A6XX_PROTECT_NORDWR(0x0ae02, 0x0000),
+ A6XX_PROTECT_NORDWR(0x0ae50, 0x032f),
+ A6XX_PROTECT_NORDWR(0x0b604, 0x0000),
+ A6XX_PROTECT_NORDWR(0x0be02, 0x0001),
+ A6XX_PROTECT_NORDWR(0x0be20, 0x17df),
+ A6XX_PROTECT_NORDWR(0x0f000, 0x0bff),
+ A6XX_PROTECT_RDONLY(0x0fc00, 0x1fff),
+ A6XX_PROTECT_NORDWR(0x11c00, 0x0000), /* note: infinite range */
+};
+
+/* These are for a620 and a650 */
+static const u32 a650_protect[] = {
+ A6XX_PROTECT_RDONLY(0x00000, 0x04ff),
+ A6XX_PROTECT_RDONLY(0x00501, 0x0005),
+ A6XX_PROTECT_RDONLY(0x0050b, 0x02f4),
+ A6XX_PROTECT_NORDWR(0x0050e, 0x0000),
+ A6XX_PROTECT_NORDWR(0x00510, 0x0000),
+ A6XX_PROTECT_NORDWR(0x00534, 0x0000),
+ A6XX_PROTECT_NORDWR(0x00800, 0x0082),
+ A6XX_PROTECT_NORDWR(0x008a0, 0x0008),
+ A6XX_PROTECT_NORDWR(0x008ab, 0x0024),
+ A6XX_PROTECT_RDONLY(0x008de, 0x00ae),
+ A6XX_PROTECT_NORDWR(0x00900, 0x004d),
+ A6XX_PROTECT_NORDWR(0x0098d, 0x0272),
+ A6XX_PROTECT_NORDWR(0x00e00, 0x0001),
+ A6XX_PROTECT_NORDWR(0x00e03, 0x000c),
+ A6XX_PROTECT_NORDWR(0x03c00, 0x00c3),
+ A6XX_PROTECT_RDONLY(0x03cc4, 0x1fff),
+ A6XX_PROTECT_NORDWR(0x08630, 0x01cf),
+ A6XX_PROTECT_NORDWR(0x08e00, 0x0000),
+ A6XX_PROTECT_NORDWR(0x08e08, 0x0000),
+ A6XX_PROTECT_NORDWR(0x08e50, 0x001f),
+ A6XX_PROTECT_NORDWR(0x08e80, 0x027f),
+ A6XX_PROTECT_NORDWR(0x09624, 0x01db),
+ A6XX_PROTECT_NORDWR(0x09e60, 0x0011),
+ A6XX_PROTECT_NORDWR(0x09e78, 0x0187),
+ A6XX_PROTECT_NORDWR(0x0a630, 0x01cf),
+ A6XX_PROTECT_NORDWR(0x0ae02, 0x0000),
+ A6XX_PROTECT_NORDWR(0x0ae50, 0x032f),
+ A6XX_PROTECT_NORDWR(0x0b604, 0x0000),
+ A6XX_PROTECT_NORDWR(0x0b608, 0x0007),
+ A6XX_PROTECT_NORDWR(0x0be02, 0x0001),
+ A6XX_PROTECT_NORDWR(0x0be20, 0x17df),
+ A6XX_PROTECT_NORDWR(0x0f000, 0x0bff),
+ A6XX_PROTECT_RDONLY(0x0fc00, 0x1fff),
+ A6XX_PROTECT_NORDWR(0x18400, 0x1fff),
+ A6XX_PROTECT_NORDWR(0x1a800, 0x1fff),
+ A6XX_PROTECT_NORDWR(0x1f400, 0x0443),
+ A6XX_PROTECT_RDONLY(0x1f844, 0x007b),
+ A6XX_PROTECT_NORDWR(0x1f887, 0x001b),
+ A6XX_PROTECT_NORDWR(0x1f8c0, 0x0000), /* note: infinite range */
+};
+
+static void a6xx_set_cp_protect(struct msm_gpu *gpu)
+{
+ struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+ const u32 *regs = a6xx_protect;
+ unsigned i, count = ARRAY_SIZE(a6xx_protect), count_max = 32;
+
+ BUILD_BUG_ON(ARRAY_SIZE(a6xx_protect) > 32);
+ BUILD_BUG_ON(ARRAY_SIZE(a650_protect) > 48);
+
+ if (adreno_is_a650(adreno_gpu)) {
+ regs = a650_protect;
+ count = ARRAY_SIZE(a650_protect);
+ count_max = 48;
+ }
+
+ /*
+ * Enable access protection to privileged registers, fault on an access
+ * protect violation and select the last span to protect from the start
+ * address all the way to the end of the register address space
+ */
+ gpu_write(gpu, REG_A6XX_CP_PROTECT_CNTL, BIT(0) | BIT(1) | BIT(3));
+
+ for (i = 0; i < count - 1; i++)
+ gpu_write(gpu, REG_A6XX_CP_PROTECT(i), regs[i]);
+ /* last CP_PROTECT to have "infinite" length on the last entry */
+ gpu_write(gpu, REG_A6XX_CP_PROTECT(count_max - 1), regs[i]);
+}
+
static void a6xx_set_ubwc_config(struct msm_gpu *gpu)
{
struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
return a6xx_idle(gpu, ring) ? 0 : -EINVAL;
}
-static void a6xx_ucode_check_version(struct a6xx_gpu *a6xx_gpu,
+/*
+ * Check that the microcode version is new enough to include several key
+ * security fixes. Return true if the ucode is safe.
+ */
+static bool a6xx_ucode_check_version(struct a6xx_gpu *a6xx_gpu,
struct drm_gem_object *obj)
{
+ struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
+ struct msm_gpu *gpu = &adreno_gpu->base;
u32 *buf = msm_gem_get_vaddr(obj);
+ bool ret = false;
if (IS_ERR(buf))
- return;
+ return false;
/*
- * If the lowest nibble is 0xa that is an indication that this microcode
- * has been patched. The actual version is in dword [3] but we only care
- * about the patchlevel which is the lowest nibble of dword [3]
- *
- * Otherwise check that the firmware is greater than or equal to 1.90
- * which was the first version that had this fix built in
+ * Targets up to a640 (a618, a630 and a640) need to check for a
+ * microcode version that is patched to support the whereami opcode or
+ * one that is new enough to include it by default.
*/
- if (((buf[0] & 0xf) == 0xa) && (buf[2] & 0xf) >= 1)
- a6xx_gpu->has_whereami = true;
- else if ((buf[0] & 0xfff) > 0x190)
- a6xx_gpu->has_whereami = true;
+ if (adreno_is_a618(adreno_gpu) || adreno_is_a630(adreno_gpu) ||
+ adreno_is_a640(adreno_gpu)) {
+ /*
+ * If the lowest nibble is 0xa that is an indication that this
+ * microcode has been patched. The actual version is in dword
+ * [3] but we only care about the patchlevel which is the lowest
+ * nibble of dword [3]
+ *
+ * Otherwise check that the firmware is greater than or equal
+ * to 1.90 which was the first version that had this fix built
+ * in
+ */
+ if ((((buf[0] & 0xf) == 0xa) && (buf[2] & 0xf) >= 1) ||
+ (buf[0] & 0xfff) >= 0x190) {
+ a6xx_gpu->has_whereami = true;
+ ret = true;
+ goto out;
+ }
+ DRM_DEV_ERROR(&gpu->pdev->dev,
+ "a630 SQE ucode is too old. Have version %x need at least %x\n",
+ buf[0] & 0xfff, 0x190);
+ } else {
+ /*
+ * a650 tier targets don't need whereami but still need to be
+ * equal to or newer than 0.95 for other security fixes
+ */
+ if (adreno_is_a650(adreno_gpu)) {
+ if ((buf[0] & 0xfff) >= 0x095) {
+ ret = true;
+ goto out;
+ }
+
+ DRM_DEV_ERROR(&gpu->pdev->dev,
+ "a650 SQE ucode is too old. Have version %x need at least %x\n",
+ buf[0] & 0xfff, 0x095);
+ }
+
+ /*
+ * When a660 is added those targets should return true here
+ * since those have all the critical security fixes built in
+ * from the start
+ */
+ }
+out:
msm_gem_put_vaddr(obj);
+ return ret;
}
static int a6xx_ucode_init(struct msm_gpu *gpu)
}
msm_gem_object_set_name(a6xx_gpu->sqe_bo, "sqefw");
- a6xx_ucode_check_version(a6xx_gpu, a6xx_gpu->sqe_bo);
+ if (!a6xx_ucode_check_version(a6xx_gpu, a6xx_gpu->sqe_bo)) {
+ msm_gem_unpin_iova(a6xx_gpu->sqe_bo, gpu->aspace);
+ drm_gem_object_put(a6xx_gpu->sqe_bo);
+
+ a6xx_gpu->sqe_bo = NULL;
+ return -EPERM;
+ }
}
gpu_write64(gpu, REG_A6XX_CP_SQE_INSTR_BASE_LO,
}
/* Protect registers from the CP */
- gpu_write(gpu, REG_A6XX_CP_PROTECT_CNTL, 0x00000003);
-
- gpu_write(gpu, REG_A6XX_CP_PROTECT(0),
- A6XX_PROTECT_RDONLY(0x600, 0x51));
- gpu_write(gpu, REG_A6XX_CP_PROTECT(1), A6XX_PROTECT_RW(0xae50, 0x2));
- gpu_write(gpu, REG_A6XX_CP_PROTECT(2), A6XX_PROTECT_RW(0x9624, 0x13));
- gpu_write(gpu, REG_A6XX_CP_PROTECT(3), A6XX_PROTECT_RW(0x8630, 0x8));
- gpu_write(gpu, REG_A6XX_CP_PROTECT(4), A6XX_PROTECT_RW(0x9e70, 0x1));
- gpu_write(gpu, REG_A6XX_CP_PROTECT(5), A6XX_PROTECT_RW(0x9e78, 0x187));
- gpu_write(gpu, REG_A6XX_CP_PROTECT(6), A6XX_PROTECT_RW(0xf000, 0x810));
- gpu_write(gpu, REG_A6XX_CP_PROTECT(7),
- A6XX_PROTECT_RDONLY(0xfc00, 0x3));
- gpu_write(gpu, REG_A6XX_CP_PROTECT(8), A6XX_PROTECT_RW(0x50e, 0x0));
- gpu_write(gpu, REG_A6XX_CP_PROTECT(9), A6XX_PROTECT_RDONLY(0x50f, 0x0));
- gpu_write(gpu, REG_A6XX_CP_PROTECT(10), A6XX_PROTECT_RW(0x510, 0x0));
- gpu_write(gpu, REG_A6XX_CP_PROTECT(11),
- A6XX_PROTECT_RDONLY(0x0, 0x4f9));
- gpu_write(gpu, REG_A6XX_CP_PROTECT(12),
- A6XX_PROTECT_RDONLY(0x501, 0xa));
- gpu_write(gpu, REG_A6XX_CP_PROTECT(13),
- A6XX_PROTECT_RDONLY(0x511, 0x44));
- gpu_write(gpu, REG_A6XX_CP_PROTECT(14), A6XX_PROTECT_RW(0xe00, 0xe));
- gpu_write(gpu, REG_A6XX_CP_PROTECT(15), A6XX_PROTECT_RW(0x8e00, 0x0));
- gpu_write(gpu, REG_A6XX_CP_PROTECT(16), A6XX_PROTECT_RW(0x8e50, 0xf));
- gpu_write(gpu, REG_A6XX_CP_PROTECT(17), A6XX_PROTECT_RW(0xbe02, 0x0));
- gpu_write(gpu, REG_A6XX_CP_PROTECT(18),
- A6XX_PROTECT_RW(0xbe20, 0x11f3));
- gpu_write(gpu, REG_A6XX_CP_PROTECT(19), A6XX_PROTECT_RW(0x800, 0x82));
- gpu_write(gpu, REG_A6XX_CP_PROTECT(20), A6XX_PROTECT_RW(0x8a0, 0x8));
- gpu_write(gpu, REG_A6XX_CP_PROTECT(21), A6XX_PROTECT_RW(0x8ab, 0x19));
- gpu_write(gpu, REG_A6XX_CP_PROTECT(22), A6XX_PROTECT_RW(0x900, 0x4d));
- gpu_write(gpu, REG_A6XX_CP_PROTECT(23), A6XX_PROTECT_RW(0x98d, 0x76));
- gpu_write(gpu, REG_A6XX_CP_PROTECT(24),
- A6XX_PROTECT_RDONLY(0x980, 0x4));
- gpu_write(gpu, REG_A6XX_CP_PROTECT(25), A6XX_PROTECT_RW(0xa630, 0x0));
+ a6xx_set_cp_protect(gpu);
/* Enable expanded apriv for targets that support it */
if (gpu->hw_apriv) {
{
struct device_node *phandle;
- a6xx_gpu->llc_mmio = msm_ioremap(pdev, "cx_mem", "gpu_cx");
- if (IS_ERR(a6xx_gpu->llc_mmio))
- return;
-
/*
* There is a different programming path for targets with an mmu500
* attached, so detect if that is the case
of_device_is_compatible(phandle, "arm,mmu-500"));
of_node_put(phandle);
+ if (a6xx_gpu->have_mmu500)
+ a6xx_gpu->llc_mmio = NULL;
+ else
+ a6xx_gpu->llc_mmio = msm_ioremap(pdev, "cx_mem", "gpu_cx");
+
a6xx_gpu->llc_slice = llcc_slice_getd(LLCC_GPU);
a6xx_gpu->htw_llc_slice = llcc_slice_getd(LLCC_GPUHTW);
- if (IS_ERR(a6xx_gpu->llc_slice) && IS_ERR(a6xx_gpu->htw_llc_slice))
+ if (IS_ERR_OR_NULL(a6xx_gpu->llc_slice) && IS_ERR_OR_NULL(a6xx_gpu->htw_llc_slice))
a6xx_gpu->llc_mmio = ERR_PTR(-EINVAL);
}
{
struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
+ static DEFINE_MUTEX(perfcounter_oob);
+
+ mutex_lock(&perfcounter_oob);
/* Force the GPU power on so we can read this register */
- a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET);
+ a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_PERFCOUNTER_SET);
- *value = gpu_read64(gpu, REG_A6XX_RBBM_PERFCTR_CP_0_LO,
- REG_A6XX_RBBM_PERFCTR_CP_0_HI);
+ *value = gpu_read64(gpu, REG_A6XX_CP_ALWAYS_ON_COUNTER_LO,
+ REG_A6XX_CP_ALWAYS_ON_COUNTER_HI);
- a6xx_gmu_clear_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET);
+ a6xx_gmu_clear_oob(&a6xx_gpu->gmu, GMU_OOB_PERFCOUNTER_SET);
+ mutex_unlock(&perfcounter_oob);
return 0;
}
a6xx_gmu_remove(a6xx_gpu);
adreno_gpu_cleanup(adreno_gpu);
+
+ if (a6xx_gpu->opp_table)
+ dev_pm_opp_put_supported_hw(a6xx_gpu->opp_table);
+
kfree(a6xx_gpu);
}
return (unsigned long)busy_time;
}
+static struct msm_gem_address_space *
+a6xx_create_address_space(struct msm_gpu *gpu, struct platform_device *pdev)
+{
+ struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+ struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
+ struct iommu_domain *iommu;
+ struct msm_mmu *mmu;
+ struct msm_gem_address_space *aspace;
+ u64 start, size;
+
+ iommu = iommu_domain_alloc(&platform_bus_type);
+ if (!iommu)
+ return NULL;
+
+ /*
+ * This allows GPU to set the bus attributes required to use system
+ * cache on behalf of the iommu page table walker.
+ */
+ if (!IS_ERR_OR_NULL(a6xx_gpu->htw_llc_slice))
+ adreno_set_llc_attributes(iommu);
+
+ mmu = msm_iommu_new(&pdev->dev, iommu);
+ if (IS_ERR(mmu)) {
+ iommu_domain_free(iommu);
+ return ERR_CAST(mmu);
+ }
+
+ /*
+ * Use the aperture start or SZ_16M, whichever is greater. This will
+ * ensure that we align with the allocated pagetable range while still
+ * allowing room in the lower 32 bits for GMEM and whatnot
+ */
+ start = max_t(u64, SZ_16M, iommu->geometry.aperture_start);
+ size = iommu->geometry.aperture_end - start + 1;
+
+ aspace = msm_gem_address_space_create(mmu, "gpu",
+ start & GENMASK_ULL(48, 0), size);
+
+ if (IS_ERR(aspace) && !IS_ERR(mmu))
+ mmu->funcs->destroy(mmu);
+
+ return aspace;
+}
+
static struct msm_gem_address_space *
a6xx_create_private_address_space(struct msm_gpu *gpu)
{
return ring->memptrs->rptr = gpu_read(gpu, REG_A6XX_CP_RB_RPTR);
}
+static u32 a618_get_speed_bin(u32 fuse)
+{
+ if (fuse == 0)
+ return 0;
+ else if (fuse == 169)
+ return 1;
+ else if (fuse == 174)
+ return 2;
+
+ return UINT_MAX;
+}
+
+static u32 fuse_to_supp_hw(struct device *dev, u32 revn, u32 fuse)
+{
+ u32 val = UINT_MAX;
+
+ if (revn == 618)
+ val = a618_get_speed_bin(fuse);
+
+ if (val == UINT_MAX) {
+ DRM_DEV_ERROR(dev,
+ "missing support for speed-bin: %u. Some OPPs may not be supported by hardware",
+ fuse);
+ return UINT_MAX;
+ }
+
+ return (1 << val);
+}
+
+static int a6xx_set_supported_hw(struct device *dev, struct a6xx_gpu *a6xx_gpu,
+ u32 revn)
+{
+ struct opp_table *opp_table;
+ u32 supp_hw = UINT_MAX;
+ u16 speedbin;
+ int ret;
+
+ ret = nvmem_cell_read_u16(dev, "speed_bin", &speedbin);
+ /*
+ * -ENOENT means that the platform doesn't support speedbin which is
+ * fine
+ */
+ if (ret == -ENOENT) {
+ return 0;
+ } else if (ret) {
+ DRM_DEV_ERROR(dev,
+ "failed to read speed-bin (%d). Some OPPs may not be supported by hardware",
+ ret);
+ goto done;
+ }
+ speedbin = le16_to_cpu(speedbin);
+
+ supp_hw = fuse_to_supp_hw(dev, revn, speedbin);
+
+done:
+ opp_table = dev_pm_opp_set_supported_hw(dev, &supp_hw, 1);
+ if (IS_ERR(opp_table))
+ return PTR_ERR(opp_table);
+
+ a6xx_gpu->opp_table = opp_table;
+ return 0;
+}
+
static const struct adreno_gpu_funcs funcs = {
.base = {
.get_param = adreno_get_param,
.gpu_state_get = a6xx_gpu_state_get,
.gpu_state_put = a6xx_gpu_state_put,
#endif
- .create_address_space = adreno_iommu_create_address_space,
+ .create_address_space = a6xx_create_address_space,
.create_private_address_space = a6xx_create_private_address_space,
.get_rptr = a6xx_get_rptr,
},
a6xx_llc_slices_init(pdev, a6xx_gpu);
+ ret = a6xx_set_supported_hw(&pdev->dev, a6xx_gpu, info->revn);
+ if (ret) {
+ a6xx_destroy(&(a6xx_gpu->base.base));
+ return ERR_PTR(ret);
+ }
+
ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1);
if (ret) {
a6xx_destroy(&(a6xx_gpu->base.base));