| .. | .. |
|---|
| 20 | 20 | * OTHER DEALINGS IN THE SOFTWARE. |
|---|
| 21 | 21 | * |
|---|
| 22 | 22 | */ |
|---|
| 23 | | -#include <drm/drmP.h> |
|---|
| 23 | + |
|---|
| 24 | +#include <linux/pci.h> |
|---|
| 25 | + |
|---|
| 24 | 26 | #include "amdgpu.h" |
|---|
| 25 | 27 | #include "amdgpu_ih.h" |
|---|
| 26 | 28 | #include "soc15.h" |
|---|
| .. | .. |
|---|
| 31 | 33 | #include "soc15_common.h" |
|---|
| 32 | 34 | #include "vega10_ih.h" |
|---|
| 33 | 35 | |
|---|
| 34 | | - |
|---|
| 36 | +#define MAX_REARM_RETRY 10 |
|---|
| 35 | 37 | |
|---|
| 36 | 38 | static void vega10_ih_set_interrupt_funcs(struct amdgpu_device *adev); |
|---|
| 37 | 39 | |
|---|
| .. | .. |
|---|
| 48 | 50 | |
|---|
| 49 | 51 | ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, RB_ENABLE, 1); |
|---|
| 50 | 52 | ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, ENABLE_INTR, 1); |
|---|
| 51 | | - WREG32_SOC15(OSSSYS, 0, mmIH_RB_CNTL, ih_rb_cntl); |
|---|
| 53 | + if (amdgpu_sriov_vf(adev)) { |
|---|
| 54 | + if (psp_reg_program(&adev->psp, PSP_REG_IH_RB_CNTL, ih_rb_cntl)) { |
|---|
| 55 | + DRM_ERROR("PSP program IH_RB_CNTL failed!\n"); |
|---|
| 56 | + return; |
|---|
| 57 | + } |
|---|
| 58 | + } else { |
|---|
| 59 | + WREG32_SOC15(OSSSYS, 0, mmIH_RB_CNTL, ih_rb_cntl); |
|---|
| 60 | + } |
|---|
| 52 | 61 | adev->irq.ih.enabled = true; |
|---|
| 62 | + |
|---|
| 63 | + if (adev->irq.ih1.ring_size) { |
|---|
| 64 | + ih_rb_cntl = RREG32_SOC15(OSSSYS, 0, mmIH_RB_CNTL_RING1); |
|---|
| 65 | + ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL_RING1, |
|---|
| 66 | + RB_ENABLE, 1); |
|---|
| 67 | + if (amdgpu_sriov_vf(adev)) { |
|---|
| 68 | + if (psp_reg_program(&adev->psp, PSP_REG_IH_RB_CNTL_RING1, |
|---|
| 69 | + ih_rb_cntl)) { |
|---|
| 70 | + DRM_ERROR("program IH_RB_CNTL_RING1 failed!\n"); |
|---|
| 71 | + return; |
|---|
| 72 | + } |
|---|
| 73 | + } else { |
|---|
| 74 | + WREG32_SOC15(OSSSYS, 0, mmIH_RB_CNTL_RING1, ih_rb_cntl); |
|---|
| 75 | + } |
|---|
| 76 | + adev->irq.ih1.enabled = true; |
|---|
| 77 | + } |
|---|
| 78 | + |
|---|
| 79 | + if (adev->irq.ih2.ring_size) { |
|---|
| 80 | + ih_rb_cntl = RREG32_SOC15(OSSSYS, 0, mmIH_RB_CNTL_RING2); |
|---|
| 81 | + ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL_RING2, |
|---|
| 82 | + RB_ENABLE, 1); |
|---|
| 83 | + if (amdgpu_sriov_vf(adev)) { |
|---|
| 84 | + if (psp_reg_program(&adev->psp, PSP_REG_IH_RB_CNTL_RING2, |
|---|
| 85 | + ih_rb_cntl)) { |
|---|
| 86 | + DRM_ERROR("program IH_RB_CNTL_RING2 failed!\n"); |
|---|
| 87 | + return; |
|---|
| 88 | + } |
|---|
| 89 | + } else { |
|---|
| 90 | + WREG32_SOC15(OSSSYS, 0, mmIH_RB_CNTL_RING2, ih_rb_cntl); |
|---|
| 91 | + } |
|---|
| 92 | + adev->irq.ih2.enabled = true; |
|---|
| 93 | + } |
|---|
| 53 | 94 | } |
|---|
| 54 | 95 | |
|---|
| 55 | 96 | /** |
|---|
| .. | .. |
|---|
| 65 | 106 | |
|---|
| 66 | 107 | ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, RB_ENABLE, 0); |
|---|
| 67 | 108 | ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, ENABLE_INTR, 0); |
|---|
| 68 | | - WREG32_SOC15(OSSSYS, 0, mmIH_RB_CNTL, ih_rb_cntl); |
|---|
| 109 | + if (amdgpu_sriov_vf(adev)) { |
|---|
| 110 | + if (psp_reg_program(&adev->psp, PSP_REG_IH_RB_CNTL, ih_rb_cntl)) { |
|---|
| 111 | + DRM_ERROR("PSP program IH_RB_CNTL failed!\n"); |
|---|
| 112 | + return; |
|---|
| 113 | + } |
|---|
| 114 | + } else { |
|---|
| 115 | + WREG32_SOC15(OSSSYS, 0, mmIH_RB_CNTL, ih_rb_cntl); |
|---|
| 116 | + } |
|---|
| 117 | + |
|---|
| 69 | 118 | /* set rptr, wptr to 0 */ |
|---|
| 70 | 119 | WREG32_SOC15(OSSSYS, 0, mmIH_RB_RPTR, 0); |
|---|
| 71 | 120 | WREG32_SOC15(OSSSYS, 0, mmIH_RB_WPTR, 0); |
|---|
| 72 | 121 | adev->irq.ih.enabled = false; |
|---|
| 73 | 122 | adev->irq.ih.rptr = 0; |
|---|
| 123 | + |
|---|
| 124 | + if (adev->irq.ih1.ring_size) { |
|---|
| 125 | + ih_rb_cntl = RREG32_SOC15(OSSSYS, 0, mmIH_RB_CNTL_RING1); |
|---|
| 126 | + ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL_RING1, |
|---|
| 127 | + RB_ENABLE, 0); |
|---|
| 128 | + if (amdgpu_sriov_vf(adev)) { |
|---|
| 129 | + if (psp_reg_program(&adev->psp, PSP_REG_IH_RB_CNTL_RING1, |
|---|
| 130 | + ih_rb_cntl)) { |
|---|
| 131 | + DRM_ERROR("program IH_RB_CNTL_RING1 failed!\n"); |
|---|
| 132 | + return; |
|---|
| 133 | + } |
|---|
| 134 | + } else { |
|---|
| 135 | + WREG32_SOC15(OSSSYS, 0, mmIH_RB_CNTL_RING1, ih_rb_cntl); |
|---|
| 136 | + } |
|---|
| 137 | + /* set rptr, wptr to 0 */ |
|---|
| 138 | + WREG32_SOC15(OSSSYS, 0, mmIH_RB_RPTR_RING1, 0); |
|---|
| 139 | + WREG32_SOC15(OSSSYS, 0, mmIH_RB_WPTR_RING1, 0); |
|---|
| 140 | + adev->irq.ih1.enabled = false; |
|---|
| 141 | + adev->irq.ih1.rptr = 0; |
|---|
| 142 | + } |
|---|
| 143 | + |
|---|
| 144 | + if (adev->irq.ih2.ring_size) { |
|---|
| 145 | + ih_rb_cntl = RREG32_SOC15(OSSSYS, 0, mmIH_RB_CNTL_RING2); |
|---|
| 146 | + ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL_RING2, |
|---|
| 147 | + RB_ENABLE, 0); |
|---|
| 148 | + if (amdgpu_sriov_vf(adev)) { |
|---|
| 149 | + if (psp_reg_program(&adev->psp, PSP_REG_IH_RB_CNTL_RING2, |
|---|
| 150 | + ih_rb_cntl)) { |
|---|
| 151 | + DRM_ERROR("program IH_RB_CNTL_RING2 failed!\n"); |
|---|
| 152 | + return; |
|---|
| 153 | + } |
|---|
| 154 | + } else { |
|---|
| 155 | + WREG32_SOC15(OSSSYS, 0, mmIH_RB_CNTL_RING2, ih_rb_cntl); |
|---|
| 156 | + } |
|---|
| 157 | + |
|---|
| 158 | + /* set rptr, wptr to 0 */ |
|---|
| 159 | + WREG32_SOC15(OSSSYS, 0, mmIH_RB_RPTR_RING2, 0); |
|---|
| 160 | + WREG32_SOC15(OSSSYS, 0, mmIH_RB_WPTR_RING2, 0); |
|---|
| 161 | + adev->irq.ih2.enabled = false; |
|---|
| 162 | + adev->irq.ih2.rptr = 0; |
|---|
| 163 | + } |
|---|
| 164 | +} |
|---|
| 165 | + |
|---|
| 166 | +static uint32_t vega10_ih_rb_cntl(struct amdgpu_ih_ring *ih, uint32_t ih_rb_cntl) |
|---|
| 167 | +{ |
|---|
| 168 | + int rb_bufsz = order_base_2(ih->ring_size / 4); |
|---|
| 169 | + |
|---|
| 170 | + ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, |
|---|
| 171 | + MC_SPACE, ih->use_bus_addr ? 1 : 4); |
|---|
| 172 | + ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, |
|---|
| 173 | + WPTR_OVERFLOW_CLEAR, 1); |
|---|
| 174 | + ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, |
|---|
| 175 | + WPTR_OVERFLOW_ENABLE, 1); |
|---|
| 176 | + ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, RB_SIZE, rb_bufsz); |
|---|
| 177 | + /* Ring Buffer write pointer writeback. If enabled, IH_RB_WPTR register |
|---|
| 178 | + * value is written to memory |
|---|
| 179 | + */ |
|---|
| 180 | + ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, |
|---|
| 181 | + WPTR_WRITEBACK_ENABLE, 1); |
|---|
| 182 | + ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, MC_SNOOP, 1); |
|---|
| 183 | + ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, MC_RO, 0); |
|---|
| 184 | + ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, MC_VMID, 0); |
|---|
| 185 | + |
|---|
| 186 | + return ih_rb_cntl; |
|---|
| 187 | +} |
|---|
| 188 | + |
|---|
| 189 | +static uint32_t vega10_ih_doorbell_rptr(struct amdgpu_ih_ring *ih) |
|---|
| 190 | +{ |
|---|
| 191 | + u32 ih_doorbell_rtpr = 0; |
|---|
| 192 | + |
|---|
| 193 | + if (ih->use_doorbell) { |
|---|
| 194 | + ih_doorbell_rtpr = REG_SET_FIELD(ih_doorbell_rtpr, |
|---|
| 195 | + IH_DOORBELL_RPTR, OFFSET, |
|---|
| 196 | + ih->doorbell_index); |
|---|
| 197 | + ih_doorbell_rtpr = REG_SET_FIELD(ih_doorbell_rtpr, |
|---|
| 198 | + IH_DOORBELL_RPTR, |
|---|
| 199 | + ENABLE, 1); |
|---|
| 200 | + } else { |
|---|
| 201 | + ih_doorbell_rtpr = REG_SET_FIELD(ih_doorbell_rtpr, |
|---|
| 202 | + IH_DOORBELL_RPTR, |
|---|
| 203 | + ENABLE, 0); |
|---|
| 204 | + } |
|---|
| 205 | + return ih_doorbell_rtpr; |
|---|
| 74 | 206 | } |
|---|
| 75 | 207 | |
|---|
| 76 | 208 | /** |
|---|
| .. | .. |
|---|
| 86 | 218 | */ |
|---|
| 87 | 219 | static int vega10_ih_irq_init(struct amdgpu_device *adev) |
|---|
| 88 | 220 | { |
|---|
| 221 | + struct amdgpu_ih_ring *ih; |
|---|
| 222 | + u32 ih_rb_cntl, ih_chicken; |
|---|
| 89 | 223 | int ret = 0; |
|---|
| 90 | | - int rb_bufsz; |
|---|
| 91 | | - u32 ih_rb_cntl, ih_doorbell_rtpr; |
|---|
| 92 | 224 | u32 tmp; |
|---|
| 93 | | - u64 wptr_off; |
|---|
| 94 | 225 | |
|---|
| 95 | 226 | /* disable irqs */ |
|---|
| 96 | 227 | vega10_ih_disable_interrupts(adev); |
|---|
| 97 | 228 | |
|---|
| 98 | | - adev->nbio_funcs->ih_control(adev); |
|---|
| 229 | + adev->nbio.funcs->ih_control(adev); |
|---|
| 230 | + |
|---|
| 231 | + ih = &adev->irq.ih; |
|---|
| 232 | + /* Ring Buffer base. [39:8] of 40-bit address of the beginning of the ring buffer*/ |
|---|
| 233 | + WREG32_SOC15(OSSSYS, 0, mmIH_RB_BASE, ih->gpu_addr >> 8); |
|---|
| 234 | + WREG32_SOC15(OSSSYS, 0, mmIH_RB_BASE_HI, (ih->gpu_addr >> 40) & 0xff); |
|---|
| 99 | 235 | |
|---|
| 100 | 236 | ih_rb_cntl = RREG32_SOC15(OSSSYS, 0, mmIH_RB_CNTL); |
|---|
| 101 | | - /* Ring Buffer base. [39:8] of 40-bit address of the beginning of the ring buffer*/ |
|---|
| 102 | | - if (adev->irq.ih.use_bus_addr) { |
|---|
| 103 | | - WREG32_SOC15(OSSSYS, 0, mmIH_RB_BASE, adev->irq.ih.rb_dma_addr >> 8); |
|---|
| 104 | | - WREG32_SOC15(OSSSYS, 0, mmIH_RB_BASE_HI, ((u64)adev->irq.ih.rb_dma_addr >> 40) & 0xff); |
|---|
| 105 | | - ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, MC_SPACE, 1); |
|---|
| 237 | + ih_rb_cntl = vega10_ih_rb_cntl(ih, ih_rb_cntl); |
|---|
| 238 | + ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, RPTR_REARM, |
|---|
| 239 | + !!adev->irq.msi_enabled); |
|---|
| 240 | + if (amdgpu_sriov_vf(adev)) { |
|---|
| 241 | + if (psp_reg_program(&adev->psp, PSP_REG_IH_RB_CNTL, ih_rb_cntl)) { |
|---|
| 242 | + DRM_ERROR("PSP program IH_RB_CNTL failed!\n"); |
|---|
| 243 | + return -ETIMEDOUT; |
|---|
| 244 | + } |
|---|
| 106 | 245 | } else { |
|---|
| 107 | | - WREG32_SOC15(OSSSYS, 0, mmIH_RB_BASE, adev->irq.ih.gpu_addr >> 8); |
|---|
| 108 | | - WREG32_SOC15(OSSSYS, 0, mmIH_RB_BASE_HI, (adev->irq.ih.gpu_addr >> 40) & 0xff); |
|---|
| 109 | | - ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, MC_SPACE, 4); |
|---|
| 246 | + WREG32_SOC15(OSSSYS, 0, mmIH_RB_CNTL, ih_rb_cntl); |
|---|
| 110 | 247 | } |
|---|
| 111 | | - rb_bufsz = order_base_2(adev->irq.ih.ring_size / 4); |
|---|
| 112 | | - ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1); |
|---|
| 113 | | - ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, WPTR_OVERFLOW_ENABLE, 1); |
|---|
| 114 | | - ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, RB_SIZE, rb_bufsz); |
|---|
| 115 | | - /* Ring Buffer write pointer writeback. If enabled, IH_RB_WPTR register value is written to memory */ |
|---|
| 116 | | - ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, WPTR_WRITEBACK_ENABLE, 1); |
|---|
| 117 | | - ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, MC_SNOOP, 1); |
|---|
| 118 | | - ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, MC_RO, 0); |
|---|
| 119 | | - ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, MC_VMID, 0); |
|---|
| 120 | 248 | |
|---|
| 121 | | - if (adev->irq.msi_enabled) |
|---|
| 122 | | - ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, RPTR_REARM, 1); |
|---|
| 123 | | - |
|---|
| 124 | | - WREG32_SOC15(OSSSYS, 0, mmIH_RB_CNTL, ih_rb_cntl); |
|---|
| 249 | + if ((adev->asic_type == CHIP_ARCTURUS && |
|---|
| 250 | + adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT) || |
|---|
| 251 | + adev->asic_type == CHIP_RENOIR) { |
|---|
| 252 | + ih_chicken = RREG32_SOC15(OSSSYS, 0, mmIH_CHICKEN); |
|---|
| 253 | + if (adev->irq.ih.use_bus_addr) { |
|---|
| 254 | + ih_chicken = REG_SET_FIELD(ih_chicken, IH_CHICKEN, |
|---|
| 255 | + MC_SPACE_GPA_ENABLE, 1); |
|---|
| 256 | + } else { |
|---|
| 257 | + ih_chicken = REG_SET_FIELD(ih_chicken, IH_CHICKEN, |
|---|
| 258 | + MC_SPACE_FBPA_ENABLE, 1); |
|---|
| 259 | + } |
|---|
| 260 | + WREG32_SOC15(OSSSYS, 0, mmIH_CHICKEN, ih_chicken); |
|---|
| 261 | + } |
|---|
| 125 | 262 | |
|---|
| 126 | 263 | /* set the writeback address whether it's enabled or not */ |
|---|
| 127 | | - if (adev->irq.ih.use_bus_addr) |
|---|
| 128 | | - wptr_off = adev->irq.ih.rb_dma_addr + (adev->irq.ih.wptr_offs * 4); |
|---|
| 129 | | - else |
|---|
| 130 | | - wptr_off = adev->wb.gpu_addr + (adev->irq.ih.wptr_offs * 4); |
|---|
| 131 | | - WREG32_SOC15(OSSSYS, 0, mmIH_RB_WPTR_ADDR_LO, lower_32_bits(wptr_off)); |
|---|
| 132 | | - WREG32_SOC15(OSSSYS, 0, mmIH_RB_WPTR_ADDR_HI, upper_32_bits(wptr_off) & 0xFFFF); |
|---|
| 264 | + WREG32_SOC15(OSSSYS, 0, mmIH_RB_WPTR_ADDR_LO, |
|---|
| 265 | + lower_32_bits(ih->wptr_addr)); |
|---|
| 266 | + WREG32_SOC15(OSSSYS, 0, mmIH_RB_WPTR_ADDR_HI, |
|---|
| 267 | + upper_32_bits(ih->wptr_addr) & 0xFFFF); |
|---|
| 133 | 268 | |
|---|
| 134 | 269 | /* set rptr, wptr to 0 */ |
|---|
| 135 | | - WREG32_SOC15(OSSSYS, 0, mmIH_RB_RPTR, 0); |
|---|
| 136 | 270 | WREG32_SOC15(OSSSYS, 0, mmIH_RB_WPTR, 0); |
|---|
| 271 | + WREG32_SOC15(OSSSYS, 0, mmIH_RB_RPTR, 0); |
|---|
| 137 | 272 | |
|---|
| 138 | | - ih_doorbell_rtpr = RREG32_SOC15(OSSSYS, 0, mmIH_DOORBELL_RPTR); |
|---|
| 139 | | - if (adev->irq.ih.use_doorbell) { |
|---|
| 140 | | - ih_doorbell_rtpr = REG_SET_FIELD(ih_doorbell_rtpr, IH_DOORBELL_RPTR, |
|---|
| 141 | | - OFFSET, adev->irq.ih.doorbell_index); |
|---|
| 142 | | - ih_doorbell_rtpr = REG_SET_FIELD(ih_doorbell_rtpr, IH_DOORBELL_RPTR, |
|---|
| 143 | | - ENABLE, 1); |
|---|
| 144 | | - } else { |
|---|
| 145 | | - ih_doorbell_rtpr = REG_SET_FIELD(ih_doorbell_rtpr, IH_DOORBELL_RPTR, |
|---|
| 146 | | - ENABLE, 0); |
|---|
| 273 | + WREG32_SOC15(OSSSYS, 0, mmIH_DOORBELL_RPTR, |
|---|
| 274 | + vega10_ih_doorbell_rptr(ih)); |
|---|
| 275 | + |
|---|
| 276 | + ih = &adev->irq.ih1; |
|---|
| 277 | + if (ih->ring_size) { |
|---|
| 278 | + WREG32_SOC15(OSSSYS, 0, mmIH_RB_BASE_RING1, ih->gpu_addr >> 8); |
|---|
| 279 | + WREG32_SOC15(OSSSYS, 0, mmIH_RB_BASE_HI_RING1, |
|---|
| 280 | + (ih->gpu_addr >> 40) & 0xff); |
|---|
| 281 | + |
|---|
| 282 | + ih_rb_cntl = RREG32_SOC15(OSSSYS, 0, mmIH_RB_CNTL_RING1); |
|---|
| 283 | + ih_rb_cntl = vega10_ih_rb_cntl(ih, ih_rb_cntl); |
|---|
| 284 | + ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, |
|---|
| 285 | + WPTR_OVERFLOW_ENABLE, 0); |
|---|
| 286 | + ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, |
|---|
| 287 | + RB_FULL_DRAIN_ENABLE, 1); |
|---|
| 288 | + if (amdgpu_sriov_vf(adev)) { |
|---|
| 289 | + if (psp_reg_program(&adev->psp, PSP_REG_IH_RB_CNTL_RING1, |
|---|
| 290 | + ih_rb_cntl)) { |
|---|
| 291 | + DRM_ERROR("program IH_RB_CNTL_RING1 failed!\n"); |
|---|
| 292 | + return -ETIMEDOUT; |
|---|
| 293 | + } |
|---|
| 294 | + } else { |
|---|
| 295 | + WREG32_SOC15(OSSSYS, 0, mmIH_RB_CNTL_RING1, ih_rb_cntl); |
|---|
| 296 | + } |
|---|
| 297 | + |
|---|
| 298 | + /* set rptr, wptr to 0 */ |
|---|
| 299 | + WREG32_SOC15(OSSSYS, 0, mmIH_RB_WPTR_RING1, 0); |
|---|
| 300 | + WREG32_SOC15(OSSSYS, 0, mmIH_RB_RPTR_RING1, 0); |
|---|
| 301 | + |
|---|
| 302 | + WREG32_SOC15(OSSSYS, 0, mmIH_DOORBELL_RPTR_RING1, |
|---|
| 303 | + vega10_ih_doorbell_rptr(ih)); |
|---|
| 147 | 304 | } |
|---|
| 148 | | - WREG32_SOC15(OSSSYS, 0, mmIH_DOORBELL_RPTR, ih_doorbell_rtpr); |
|---|
| 149 | | - adev->nbio_funcs->ih_doorbell_range(adev, adev->irq.ih.use_doorbell, |
|---|
| 150 | | - adev->irq.ih.doorbell_index); |
|---|
| 305 | + |
|---|
| 306 | + ih = &adev->irq.ih2; |
|---|
| 307 | + if (ih->ring_size) { |
|---|
| 308 | + WREG32_SOC15(OSSSYS, 0, mmIH_RB_BASE_RING2, ih->gpu_addr >> 8); |
|---|
| 309 | + WREG32_SOC15(OSSSYS, 0, mmIH_RB_BASE_HI_RING2, |
|---|
| 310 | + (ih->gpu_addr >> 40) & 0xff); |
|---|
| 311 | + |
|---|
| 312 | + ih_rb_cntl = RREG32_SOC15(OSSSYS, 0, mmIH_RB_CNTL_RING2); |
|---|
| 313 | + ih_rb_cntl = vega10_ih_rb_cntl(ih, ih_rb_cntl); |
|---|
| 314 | + |
|---|
| 315 | + if (amdgpu_sriov_vf(adev)) { |
|---|
| 316 | + if (psp_reg_program(&adev->psp, PSP_REG_IH_RB_CNTL_RING2, |
|---|
| 317 | + ih_rb_cntl)) { |
|---|
| 318 | + DRM_ERROR("program IH_RB_CNTL_RING2 failed!\n"); |
|---|
| 319 | + return -ETIMEDOUT; |
|---|
| 320 | + } |
|---|
| 321 | + } else { |
|---|
| 322 | + WREG32_SOC15(OSSSYS, 0, mmIH_RB_CNTL_RING2, ih_rb_cntl); |
|---|
| 323 | + } |
|---|
| 324 | + |
|---|
| 325 | + /* set rptr, wptr to 0 */ |
|---|
| 326 | + WREG32_SOC15(OSSSYS, 0, mmIH_RB_WPTR_RING2, 0); |
|---|
| 327 | + WREG32_SOC15(OSSSYS, 0, mmIH_RB_RPTR_RING2, 0); |
|---|
| 328 | + |
|---|
| 329 | + WREG32_SOC15(OSSSYS, 0, mmIH_DOORBELL_RPTR_RING2, |
|---|
| 330 | + vega10_ih_doorbell_rptr(ih)); |
|---|
| 331 | + } |
|---|
| 151 | 332 | |
|---|
| 152 | 333 | tmp = RREG32_SOC15(OSSSYS, 0, mmIH_STORM_CLIENT_LIST_CNTL); |
|---|
| 153 | 334 | tmp = REG_SET_FIELD(tmp, IH_STORM_CLIENT_LIST_CNTL, |
|---|
| .. | .. |
|---|
| 191 | 372 | * ring buffer overflow and deal with it. |
|---|
| 192 | 373 | * Returns the value of the wptr. |
|---|
| 193 | 374 | */ |
|---|
| 194 | | -static u32 vega10_ih_get_wptr(struct amdgpu_device *adev) |
|---|
| 375 | +static u32 vega10_ih_get_wptr(struct amdgpu_device *adev, |
|---|
| 376 | + struct amdgpu_ih_ring *ih) |
|---|
| 195 | 377 | { |
|---|
| 196 | | - u32 wptr, tmp; |
|---|
| 378 | + u32 wptr, reg, tmp; |
|---|
| 197 | 379 | |
|---|
| 198 | | - if (adev->irq.ih.use_bus_addr) |
|---|
| 199 | | - wptr = le32_to_cpu(adev->irq.ih.ring[adev->irq.ih.wptr_offs]); |
|---|
| 380 | + wptr = le32_to_cpu(*ih->wptr_cpu); |
|---|
| 381 | + |
|---|
| 382 | + if (!REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW)) |
|---|
| 383 | + goto out; |
|---|
| 384 | + |
|---|
| 385 | + /* Double check that the overflow wasn't already cleared. */ |
|---|
| 386 | + |
|---|
| 387 | + if (ih == &adev->irq.ih) |
|---|
| 388 | + reg = SOC15_REG_OFFSET(OSSSYS, 0, mmIH_RB_WPTR); |
|---|
| 389 | + else if (ih == &adev->irq.ih1) |
|---|
| 390 | + reg = SOC15_REG_OFFSET(OSSSYS, 0, mmIH_RB_WPTR_RING1); |
|---|
| 391 | + else if (ih == &adev->irq.ih2) |
|---|
| 392 | + reg = SOC15_REG_OFFSET(OSSSYS, 0, mmIH_RB_WPTR_RING2); |
|---|
| 200 | 393 | else |
|---|
| 201 | | - wptr = le32_to_cpu(adev->wb.wb[adev->irq.ih.wptr_offs]); |
|---|
| 394 | + BUG(); |
|---|
| 202 | 395 | |
|---|
| 203 | | - if (REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW)) { |
|---|
| 204 | | - wptr = REG_SET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW, 0); |
|---|
| 396 | + wptr = RREG32_NO_KIQ(reg); |
|---|
| 397 | + if (!REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW)) |
|---|
| 398 | + goto out; |
|---|
| 205 | 399 | |
|---|
| 206 | | - /* When a ring buffer overflow happen start parsing interrupt |
|---|
| 207 | | - * from the last not overwritten vector (wptr + 32). Hopefully |
|---|
| 208 | | - * this should allow us to catchup. |
|---|
| 209 | | - */ |
|---|
| 210 | | - tmp = (wptr + 32) & adev->irq.ih.ptr_mask; |
|---|
| 211 | | - dev_warn(adev->dev, "IH ring buffer overflow (0x%08X, 0x%08X, 0x%08X)\n", |
|---|
| 212 | | - wptr, adev->irq.ih.rptr, tmp); |
|---|
| 213 | | - adev->irq.ih.rptr = tmp; |
|---|
| 400 | + wptr = REG_SET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW, 0); |
|---|
| 214 | 401 | |
|---|
| 215 | | - tmp = RREG32_NO_KIQ(SOC15_REG_OFFSET(OSSSYS, 0, mmIH_RB_CNTL)); |
|---|
| 216 | | - tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1); |
|---|
| 217 | | - WREG32_NO_KIQ(SOC15_REG_OFFSET(OSSSYS, 0, mmIH_RB_CNTL), tmp); |
|---|
| 218 | | - } |
|---|
| 219 | | - return (wptr & adev->irq.ih.ptr_mask); |
|---|
| 220 | | -} |
|---|
| 221 | | - |
|---|
| 222 | | -/** |
|---|
| 223 | | - * vega10_ih_prescreen_iv - prescreen an interrupt vector |
|---|
| 224 | | - * |
|---|
| 225 | | - * @adev: amdgpu_device pointer |
|---|
| 226 | | - * |
|---|
| 227 | | - * Returns true if the interrupt vector should be further processed. |
|---|
| 228 | | - */ |
|---|
| 229 | | -static bool vega10_ih_prescreen_iv(struct amdgpu_device *adev) |
|---|
| 230 | | -{ |
|---|
| 231 | | - u32 ring_index = adev->irq.ih.rptr >> 2; |
|---|
| 232 | | - u32 dw0, dw3, dw4, dw5; |
|---|
| 233 | | - u16 pasid; |
|---|
| 234 | | - u64 addr, key; |
|---|
| 235 | | - struct amdgpu_vm *vm; |
|---|
| 236 | | - int r; |
|---|
| 237 | | - |
|---|
| 238 | | - dw0 = le32_to_cpu(adev->irq.ih.ring[ring_index + 0]); |
|---|
| 239 | | - dw3 = le32_to_cpu(adev->irq.ih.ring[ring_index + 3]); |
|---|
| 240 | | - dw4 = le32_to_cpu(adev->irq.ih.ring[ring_index + 4]); |
|---|
| 241 | | - dw5 = le32_to_cpu(adev->irq.ih.ring[ring_index + 5]); |
|---|
| 242 | | - |
|---|
| 243 | | - /* Filter retry page faults, let only the first one pass. If |
|---|
| 244 | | - * there are too many outstanding faults, ignore them until |
|---|
| 245 | | - * some faults get cleared. |
|---|
| 402 | + /* When a ring buffer overflow happen start parsing interrupt |
|---|
| 403 | + * from the last not overwritten vector (wptr + 32). Hopefully |
|---|
| 404 | + * this should allow us to catchup. |
|---|
| 246 | 405 | */ |
|---|
| 247 | | - switch (dw0 & 0xff) { |
|---|
| 248 | | - case SOC15_IH_CLIENTID_VMC: |
|---|
| 249 | | - case SOC15_IH_CLIENTID_UTCL2: |
|---|
| 250 | | - break; |
|---|
| 251 | | - default: |
|---|
| 252 | | - /* Not a VM fault */ |
|---|
| 253 | | - return true; |
|---|
| 254 | | - } |
|---|
| 406 | + tmp = (wptr + 32) & ih->ptr_mask; |
|---|
| 407 | + dev_warn(adev->dev, "IH ring buffer overflow " |
|---|
| 408 | + "(0x%08X, 0x%08X, 0x%08X)\n", |
|---|
| 409 | + wptr, ih->rptr, tmp); |
|---|
| 410 | + ih->rptr = tmp; |
|---|
| 255 | 411 | |
|---|
| 256 | | - pasid = dw3 & 0xffff; |
|---|
| 257 | | - /* No PASID, can't identify faulting process */ |
|---|
| 258 | | - if (!pasid) |
|---|
| 259 | | - return true; |
|---|
| 412 | + if (ih == &adev->irq.ih) |
|---|
| 413 | + reg = SOC15_REG_OFFSET(OSSSYS, 0, mmIH_RB_CNTL); |
|---|
| 414 | + else if (ih == &adev->irq.ih1) |
|---|
| 415 | + reg = SOC15_REG_OFFSET(OSSSYS, 0, mmIH_RB_CNTL_RING1); |
|---|
| 416 | + else if (ih == &adev->irq.ih2) |
|---|
| 417 | + reg = SOC15_REG_OFFSET(OSSSYS, 0, mmIH_RB_CNTL_RING2); |
|---|
| 418 | + else |
|---|
| 419 | + BUG(); |
|---|
| 260 | 420 | |
|---|
| 261 | | - /* Not a retry fault, check fault credit */ |
|---|
| 262 | | - if (!(dw5 & 0x80)) { |
|---|
| 263 | | - if (!amdgpu_vm_pasid_fault_credit(adev, pasid)) |
|---|
| 264 | | - goto ignore_iv; |
|---|
| 265 | | - return true; |
|---|
| 266 | | - } |
|---|
| 421 | + tmp = RREG32_NO_KIQ(reg); |
|---|
| 422 | + tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1); |
|---|
| 423 | + WREG32_NO_KIQ(reg, tmp); |
|---|
| 267 | 424 | |
|---|
| 268 | | - addr = ((u64)(dw5 & 0xf) << 44) | ((u64)dw4 << 12); |
|---|
| 269 | | - key = AMDGPU_VM_FAULT(pasid, addr); |
|---|
| 270 | | - r = amdgpu_ih_add_fault(adev, key); |
|---|
| 271 | | - |
|---|
| 272 | | - /* Hash table is full or the fault is already being processed, |
|---|
| 273 | | - * ignore further page faults |
|---|
| 274 | | - */ |
|---|
| 275 | | - if (r != 0) |
|---|
| 276 | | - goto ignore_iv; |
|---|
| 277 | | - |
|---|
| 278 | | - /* Track retry faults in per-VM fault FIFO. */ |
|---|
| 279 | | - spin_lock(&adev->vm_manager.pasid_lock); |
|---|
| 280 | | - vm = idr_find(&adev->vm_manager.pasid_idr, pasid); |
|---|
| 281 | | - if (!vm) { |
|---|
| 282 | | - /* VM not found, process it normally */ |
|---|
| 283 | | - spin_unlock(&adev->vm_manager.pasid_lock); |
|---|
| 284 | | - amdgpu_ih_clear_fault(adev, key); |
|---|
| 285 | | - return true; |
|---|
| 286 | | - } |
|---|
| 287 | | - /* No locking required with single writer and single reader */ |
|---|
| 288 | | - r = kfifo_put(&vm->faults, key); |
|---|
| 289 | | - if (!r) { |
|---|
| 290 | | - /* FIFO is full. Ignore it until there is space */ |
|---|
| 291 | | - spin_unlock(&adev->vm_manager.pasid_lock); |
|---|
| 292 | | - amdgpu_ih_clear_fault(adev, key); |
|---|
| 293 | | - goto ignore_iv; |
|---|
| 294 | | - } |
|---|
| 295 | | - spin_unlock(&adev->vm_manager.pasid_lock); |
|---|
| 296 | | - |
|---|
| 297 | | - /* It's the first fault for this address, process it normally */ |
|---|
| 298 | | - return true; |
|---|
| 299 | | - |
|---|
| 300 | | -ignore_iv: |
|---|
| 301 | | - adev->irq.ih.rptr += 32; |
|---|
| 302 | | - return false; |
|---|
| 425 | +out: |
|---|
| 426 | + return (wptr & ih->ptr_mask); |
|---|
| 303 | 427 | } |
|---|
| 304 | 428 | |
|---|
| 305 | 429 | /** |
|---|
| .. | .. |
|---|
| 311 | 435 | * position and also advance the position. |
|---|
| 312 | 436 | */ |
|---|
| 313 | 437 | static void vega10_ih_decode_iv(struct amdgpu_device *adev, |
|---|
| 314 | | - struct amdgpu_iv_entry *entry) |
|---|
| 438 | + struct amdgpu_ih_ring *ih, |
|---|
| 439 | + struct amdgpu_iv_entry *entry) |
|---|
| 315 | 440 | { |
|---|
| 316 | 441 | /* wptr/rptr are in bytes! */ |
|---|
| 317 | | - u32 ring_index = adev->irq.ih.rptr >> 2; |
|---|
| 442 | + u32 ring_index = ih->rptr >> 2; |
|---|
| 318 | 443 | uint32_t dw[8]; |
|---|
| 319 | 444 | |
|---|
| 320 | | - dw[0] = le32_to_cpu(adev->irq.ih.ring[ring_index + 0]); |
|---|
| 321 | | - dw[1] = le32_to_cpu(adev->irq.ih.ring[ring_index + 1]); |
|---|
| 322 | | - dw[2] = le32_to_cpu(adev->irq.ih.ring[ring_index + 2]); |
|---|
| 323 | | - dw[3] = le32_to_cpu(adev->irq.ih.ring[ring_index + 3]); |
|---|
| 324 | | - dw[4] = le32_to_cpu(adev->irq.ih.ring[ring_index + 4]); |
|---|
| 325 | | - dw[5] = le32_to_cpu(adev->irq.ih.ring[ring_index + 5]); |
|---|
| 326 | | - dw[6] = le32_to_cpu(adev->irq.ih.ring[ring_index + 6]); |
|---|
| 327 | | - dw[7] = le32_to_cpu(adev->irq.ih.ring[ring_index + 7]); |
|---|
| 445 | + dw[0] = le32_to_cpu(ih->ring[ring_index + 0]); |
|---|
| 446 | + dw[1] = le32_to_cpu(ih->ring[ring_index + 1]); |
|---|
| 447 | + dw[2] = le32_to_cpu(ih->ring[ring_index + 2]); |
|---|
| 448 | + dw[3] = le32_to_cpu(ih->ring[ring_index + 3]); |
|---|
| 449 | + dw[4] = le32_to_cpu(ih->ring[ring_index + 4]); |
|---|
| 450 | + dw[5] = le32_to_cpu(ih->ring[ring_index + 5]); |
|---|
| 451 | + dw[6] = le32_to_cpu(ih->ring[ring_index + 6]); |
|---|
| 452 | + dw[7] = le32_to_cpu(ih->ring[ring_index + 7]); |
|---|
| 328 | 453 | |
|---|
| 329 | 454 | entry->client_id = dw[0] & 0xff; |
|---|
| 330 | 455 | entry->src_id = (dw[0] >> 8) & 0xff; |
|---|
| .. | .. |
|---|
| 340 | 465 | entry->src_data[2] = dw[6]; |
|---|
| 341 | 466 | entry->src_data[3] = dw[7]; |
|---|
| 342 | 467 | |
|---|
| 343 | | - |
|---|
| 344 | 468 | /* wptr/rptr are in bytes! */ |
|---|
| 345 | | - adev->irq.ih.rptr += 32; |
|---|
| 469 | + ih->rptr += 32; |
|---|
| 470 | +} |
|---|
| 471 | + |
|---|
| 472 | +/** |
|---|
| 473 | + * vega10_ih_irq_rearm - rearm IRQ if lost |
|---|
| 474 | + * |
|---|
| 475 | + * @adev: amdgpu_device pointer |
|---|
| 476 | + * |
|---|
| 477 | + */ |
|---|
| 478 | +static void vega10_ih_irq_rearm(struct amdgpu_device *adev, |
|---|
| 479 | + struct amdgpu_ih_ring *ih) |
|---|
| 480 | +{ |
|---|
| 481 | + uint32_t reg_rptr = 0; |
|---|
| 482 | + uint32_t v = 0; |
|---|
| 483 | + uint32_t i = 0; |
|---|
| 484 | + |
|---|
| 485 | + if (ih == &adev->irq.ih) |
|---|
| 486 | + reg_rptr = SOC15_REG_OFFSET(OSSSYS, 0, mmIH_RB_RPTR); |
|---|
| 487 | + else if (ih == &adev->irq.ih1) |
|---|
| 488 | + reg_rptr = SOC15_REG_OFFSET(OSSSYS, 0, mmIH_RB_RPTR_RING1); |
|---|
| 489 | + else if (ih == &adev->irq.ih2) |
|---|
| 490 | + reg_rptr = SOC15_REG_OFFSET(OSSSYS, 0, mmIH_RB_RPTR_RING2); |
|---|
| 491 | + else |
|---|
| 492 | + return; |
|---|
| 493 | + |
|---|
| 494 | + /* Rearm IRQ / re-wwrite doorbell if doorbell write is lost */ |
|---|
| 495 | + for (i = 0; i < MAX_REARM_RETRY; i++) { |
|---|
| 496 | + v = RREG32_NO_KIQ(reg_rptr); |
|---|
| 497 | + if ((v < ih->ring_size) && (v != ih->rptr)) |
|---|
| 498 | + WDOORBELL32(ih->doorbell_index, ih->rptr); |
|---|
| 499 | + else |
|---|
| 500 | + break; |
|---|
| 501 | + } |
|---|
| 346 | 502 | } |
|---|
| 347 | 503 | |
|---|
| 348 | 504 | /** |
|---|
| .. | .. |
|---|
| 352 | 508 | * |
|---|
| 353 | 509 | * Set the IH ring buffer rptr. |
|---|
| 354 | 510 | */ |
|---|
| 355 | | -static void vega10_ih_set_rptr(struct amdgpu_device *adev) |
|---|
| 511 | +static void vega10_ih_set_rptr(struct amdgpu_device *adev, |
|---|
| 512 | + struct amdgpu_ih_ring *ih) |
|---|
| 356 | 513 | { |
|---|
| 357 | | - if (adev->irq.ih.use_doorbell) { |
|---|
| 514 | + if (ih->use_doorbell) { |
|---|
| 358 | 515 | /* XXX check if swapping is necessary on BE */ |
|---|
| 359 | | - if (adev->irq.ih.use_bus_addr) |
|---|
| 360 | | - adev->irq.ih.ring[adev->irq.ih.rptr_offs] = adev->irq.ih.rptr; |
|---|
| 361 | | - else |
|---|
| 362 | | - adev->wb.wb[adev->irq.ih.rptr_offs] = adev->irq.ih.rptr; |
|---|
| 363 | | - WDOORBELL32(adev->irq.ih.doorbell_index, adev->irq.ih.rptr); |
|---|
| 364 | | - } else { |
|---|
| 365 | | - WREG32_SOC15(OSSSYS, 0, mmIH_RB_RPTR, adev->irq.ih.rptr); |
|---|
| 516 | + *ih->rptr_cpu = ih->rptr; |
|---|
| 517 | + WDOORBELL32(ih->doorbell_index, ih->rptr); |
|---|
| 518 | + |
|---|
| 519 | + if (amdgpu_sriov_vf(adev)) |
|---|
| 520 | + vega10_ih_irq_rearm(adev, ih); |
|---|
| 521 | + } else if (ih == &adev->irq.ih) { |
|---|
| 522 | + WREG32_SOC15(OSSSYS, 0, mmIH_RB_RPTR, ih->rptr); |
|---|
| 523 | + } else if (ih == &adev->irq.ih1) { |
|---|
| 524 | + WREG32_SOC15(OSSSYS, 0, mmIH_RB_RPTR_RING1, ih->rptr); |
|---|
| 525 | + } else if (ih == &adev->irq.ih2) { |
|---|
| 526 | + WREG32_SOC15(OSSSYS, 0, mmIH_RB_RPTR_RING2, ih->rptr); |
|---|
| 366 | 527 | } |
|---|
| 528 | +} |
|---|
| 529 | + |
|---|
| 530 | +/** |
|---|
| 531 | + * vega10_ih_self_irq - dispatch work for ring 1 and 2 |
|---|
| 532 | + * |
|---|
| 533 | + * @adev: amdgpu_device pointer |
|---|
| 534 | + * @source: irq source |
|---|
| 535 | + * @entry: IV with WPTR update |
|---|
| 536 | + * |
|---|
| 537 | + * Update the WPTR from the IV and schedule work to handle the entries. |
|---|
| 538 | + */ |
|---|
| 539 | +static int vega10_ih_self_irq(struct amdgpu_device *adev, |
|---|
| 540 | + struct amdgpu_irq_src *source, |
|---|
| 541 | + struct amdgpu_iv_entry *entry) |
|---|
| 542 | +{ |
|---|
| 543 | + uint32_t wptr = cpu_to_le32(entry->src_data[0]); |
|---|
| 544 | + |
|---|
| 545 | + switch (entry->ring_id) { |
|---|
| 546 | + case 1: |
|---|
| 547 | + *adev->irq.ih1.wptr_cpu = wptr; |
|---|
| 548 | + schedule_work(&adev->irq.ih1_work); |
|---|
| 549 | + break; |
|---|
| 550 | + case 2: |
|---|
| 551 | + *adev->irq.ih2.wptr_cpu = wptr; |
|---|
| 552 | + schedule_work(&adev->irq.ih2_work); |
|---|
| 553 | + break; |
|---|
| 554 | + default: break; |
|---|
| 555 | + } |
|---|
| 556 | + return 0; |
|---|
| 557 | +} |
|---|
| 558 | + |
|---|
| 559 | +static const struct amdgpu_irq_src_funcs vega10_ih_self_irq_funcs = { |
|---|
| 560 | + .process = vega10_ih_self_irq, |
|---|
| 561 | +}; |
|---|
| 562 | + |
|---|
| 563 | +static void vega10_ih_set_self_irq_funcs(struct amdgpu_device *adev) |
|---|
| 564 | +{ |
|---|
| 565 | + adev->irq.self_irq.num_types = 0; |
|---|
| 566 | + adev->irq.self_irq.funcs = &vega10_ih_self_irq_funcs; |
|---|
| 367 | 567 | } |
|---|
| 368 | 568 | |
|---|
| 369 | 569 | static int vega10_ih_early_init(void *handle) |
|---|
| .. | .. |
|---|
| 371 | 571 | struct amdgpu_device *adev = (struct amdgpu_device *)handle; |
|---|
| 372 | 572 | |
|---|
| 373 | 573 | vega10_ih_set_interrupt_funcs(adev); |
|---|
| 574 | + vega10_ih_set_self_irq_funcs(adev); |
|---|
| 374 | 575 | return 0; |
|---|
| 375 | 576 | } |
|---|
| 376 | 577 | |
|---|
| 377 | 578 | static int vega10_ih_sw_init(void *handle) |
|---|
| 378 | 579 | { |
|---|
| 379 | | - int r; |
|---|
| 380 | 580 | struct amdgpu_device *adev = (struct amdgpu_device *)handle; |
|---|
| 581 | + int r; |
|---|
| 381 | 582 | |
|---|
| 382 | | - r = amdgpu_ih_ring_init(adev, 256 * 1024, true); |
|---|
| 583 | + r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_IH, 0, |
|---|
| 584 | + &adev->irq.self_irq); |
|---|
| 585 | + if (r) |
|---|
| 586 | + return r; |
|---|
| 587 | + |
|---|
| 588 | + r = amdgpu_ih_ring_init(adev, &adev->irq.ih, 256 * 1024, true); |
|---|
| 383 | 589 | if (r) |
|---|
| 384 | 590 | return r; |
|---|
| 385 | 591 | |
|---|
| 386 | 592 | adev->irq.ih.use_doorbell = true; |
|---|
| 387 | | - adev->irq.ih.doorbell_index = AMDGPU_DOORBELL64_IH << 1; |
|---|
| 593 | + adev->irq.ih.doorbell_index = adev->doorbell_index.ih << 1; |
|---|
| 388 | 594 | |
|---|
| 389 | | - adev->irq.ih.faults = kmalloc(sizeof(*adev->irq.ih.faults), GFP_KERNEL); |
|---|
| 390 | | - if (!adev->irq.ih.faults) |
|---|
| 391 | | - return -ENOMEM; |
|---|
| 392 | | - INIT_CHASH_TABLE(adev->irq.ih.faults->hash, |
|---|
| 393 | | - AMDGPU_PAGEFAULT_HASH_BITS, 8, 0); |
|---|
| 394 | | - spin_lock_init(&adev->irq.ih.faults->lock); |
|---|
| 395 | | - adev->irq.ih.faults->count = 0; |
|---|
| 595 | + r = amdgpu_ih_ring_init(adev, &adev->irq.ih1, PAGE_SIZE, true); |
|---|
| 596 | + if (r) |
|---|
| 597 | + return r; |
|---|
| 598 | + |
|---|
| 599 | + adev->irq.ih1.use_doorbell = true; |
|---|
| 600 | + adev->irq.ih1.doorbell_index = (adev->doorbell_index.ih + 1) << 1; |
|---|
| 601 | + |
|---|
| 602 | + r = amdgpu_ih_ring_init(adev, &adev->irq.ih2, PAGE_SIZE, true); |
|---|
| 603 | + if (r) |
|---|
| 604 | + return r; |
|---|
| 605 | + |
|---|
| 606 | + adev->irq.ih2.use_doorbell = true; |
|---|
| 607 | + adev->irq.ih2.doorbell_index = (adev->doorbell_index.ih + 2) << 1; |
|---|
| 396 | 608 | |
|---|
| 397 | 609 | r = amdgpu_irq_init(adev); |
|---|
| 398 | 610 | |
|---|
| .. | .. |
|---|
| 404 | 616 | struct amdgpu_device *adev = (struct amdgpu_device *)handle; |
|---|
| 405 | 617 | |
|---|
| 406 | 618 | amdgpu_irq_fini(adev); |
|---|
| 407 | | - amdgpu_ih_ring_fini(adev); |
|---|
| 408 | | - |
|---|
| 409 | | - kfree(adev->irq.ih.faults); |
|---|
| 410 | | - adev->irq.ih.faults = NULL; |
|---|
| 619 | + amdgpu_ih_ring_fini(adev, &adev->irq.ih2); |
|---|
| 620 | + amdgpu_ih_ring_fini(adev, &adev->irq.ih1); |
|---|
| 621 | + amdgpu_ih_ring_fini(adev, &adev->irq.ih); |
|---|
| 411 | 622 | |
|---|
| 412 | 623 | return 0; |
|---|
| 413 | 624 | } |
|---|
| .. | .. |
|---|
| 466 | 677 | return 0; |
|---|
| 467 | 678 | } |
|---|
| 468 | 679 | |
|---|
| 680 | +static void vega10_ih_update_clockgating_state(struct amdgpu_device *adev, |
|---|
| 681 | + bool enable) |
|---|
| 682 | +{ |
|---|
| 683 | + uint32_t data, def, field_val; |
|---|
| 684 | + |
|---|
| 685 | + if (adev->cg_flags & AMD_CG_SUPPORT_IH_CG) { |
|---|
| 686 | + def = data = RREG32_SOC15(OSSSYS, 0, mmIH_CLK_CTRL); |
|---|
| 687 | + field_val = enable ? 0 : 1; |
|---|
| 688 | + /** |
|---|
| 689 | + * Vega10 does not have IH_RETRY_INT_CAM_MEM_CLK_SOFT_OVERRIDE |
|---|
| 690 | + * and IH_BUFFER_MEM_CLK_SOFT_OVERRIDE field. |
|---|
| 691 | + */ |
|---|
| 692 | + if (adev->asic_type > CHIP_VEGA10) { |
|---|
| 693 | + data = REG_SET_FIELD(data, IH_CLK_CTRL, |
|---|
| 694 | + IH_RETRY_INT_CAM_MEM_CLK_SOFT_OVERRIDE, field_val); |
|---|
| 695 | + data = REG_SET_FIELD(data, IH_CLK_CTRL, |
|---|
| 696 | + IH_BUFFER_MEM_CLK_SOFT_OVERRIDE, field_val); |
|---|
| 697 | + } |
|---|
| 698 | + |
|---|
| 699 | + data = REG_SET_FIELD(data, IH_CLK_CTRL, |
|---|
| 700 | + DBUS_MUX_CLK_SOFT_OVERRIDE, field_val); |
|---|
| 701 | + data = REG_SET_FIELD(data, IH_CLK_CTRL, |
|---|
| 702 | + OSSSYS_SHARE_CLK_SOFT_OVERRIDE, field_val); |
|---|
| 703 | + data = REG_SET_FIELD(data, IH_CLK_CTRL, |
|---|
| 704 | + LIMIT_SMN_CLK_SOFT_OVERRIDE, field_val); |
|---|
| 705 | + data = REG_SET_FIELD(data, IH_CLK_CTRL, |
|---|
| 706 | + DYN_CLK_SOFT_OVERRIDE, field_val); |
|---|
| 707 | + data = REG_SET_FIELD(data, IH_CLK_CTRL, |
|---|
| 708 | + REG_CLK_SOFT_OVERRIDE, field_val); |
|---|
| 709 | + if (def != data) |
|---|
| 710 | + WREG32_SOC15(OSSSYS, 0, mmIH_CLK_CTRL, data); |
|---|
| 711 | + } |
|---|
| 712 | +} |
|---|
| 713 | + |
|---|
| 469 | 714 | static int vega10_ih_set_clockgating_state(void *handle, |
|---|
| 470 | 715 | enum amd_clockgating_state state) |
|---|
| 471 | 716 | { |
|---|
| 717 | + struct amdgpu_device *adev = (struct amdgpu_device *)handle; |
|---|
| 718 | + |
|---|
| 719 | + vega10_ih_update_clockgating_state(adev, |
|---|
| 720 | + state == AMD_CG_STATE_GATE); |
|---|
| 472 | 721 | return 0; |
|---|
| 722 | + |
|---|
| 473 | 723 | } |
|---|
| 474 | 724 | |
|---|
| 475 | 725 | static int vega10_ih_set_powergating_state(void *handle, |
|---|
| .. | .. |
|---|
| 497 | 747 | |
|---|
| 498 | 748 | static const struct amdgpu_ih_funcs vega10_ih_funcs = { |
|---|
| 499 | 749 | .get_wptr = vega10_ih_get_wptr, |
|---|
| 500 | | - .prescreen_iv = vega10_ih_prescreen_iv, |
|---|
| 501 | 750 | .decode_iv = vega10_ih_decode_iv, |
|---|
| 502 | 751 | .set_rptr = vega10_ih_set_rptr |
|---|
| 503 | 752 | }; |
|---|
| 504 | 753 | |
|---|
| 505 | 754 | static void vega10_ih_set_interrupt_funcs(struct amdgpu_device *adev) |
|---|
| 506 | 755 | { |
|---|
| 507 | | - if (adev->irq.ih_funcs == NULL) |
|---|
| 508 | | - adev->irq.ih_funcs = &vega10_ih_funcs; |
|---|
| 756 | + adev->irq.ih_funcs = &vega10_ih_funcs; |
|---|
| 509 | 757 | } |
|---|
| 510 | 758 | |
|---|
| 511 | 759 | const struct amdgpu_ip_block_version vega10_ih_ip_block = |
|---|