From 48527e5296edc7b952fb2c1c40fd8c388cc935ed Mon Sep 17 00:00:00 2001 From: Monk Liu Date: Mon, 15 Jan 2018 13:44:30 +0800 Subject: drm/amdgpu: refactoring mailbox to fix TDR handshake bugs(v2) this patch actually refactor mailbox implmentations, and all below changes are needed together to fix all those mailbox handshake issues exposured by heavey TDR test. 1)refactor all mailbox functions based on byte accessing for mb_control reason is to avoid touching non-related bits when writing trn/rcv part of mailbox_control, this way some incorrect INTR sent to hypervisor side could be avoided, and it fixes couple handshake bug. 2)trans_msg function re-impled: put a invalid logic before transmitting message to make sure the ACK bit is in a clear status, otherwise there is chance that ACK asserted already before transmitting message and lead to fake ACK polling. (hypervisor side have some tricks to workaround ACK bit being corrupted by VF FLR which hase an side effects that may make guest side ACK bit asserted wrongly), and clear TRANS_MSG words after message transferred. 3)for mailbox_flr_work, it is also re-worked: it takes the mutex lock first if invoked, to block gpu recover's participate too early while hypervisor side is doing VF FLR. (hypervisor sends FLR_NOTIFY to guest before doing VF FLR and sentds FLR_COMPLETE after VF FLR done, and the FLR_NOTIFY will trigger interrupt to guest which lead to mailbox_flr_work being invoked) This can avoid the issue that mailbox trans msg being cleared by its VF FLR. 4)for mailbox_rcv_irq IRQ routine, it should only peek msg and schedule mailbox_flr_work, instead of ACK to hypervisor itself, because FLR_NOTIFY msg sent from hypervisor side doesn't need VF's ACK (this is because VF's ACK would lead to hypervisor clear its trans_valid/msg, and this would cause handshake bug if trans_valid/msg is cleared not due to correct VF ACK but from a wrong VF ACK like this "FLR_NOTIFY" one) This fixed handshake bug that sometimes GUEST always couldn't receive "READY_TO_ACCESS_GPU" msg from hypervisor. 5)seperate polling time limite accordingly: POLL ACK cost no more than 500ms POLL MSG cost no more than 12000ms POLL FLR finish cost no more than 500ms 6) we still need to set adev into in_gpu_reset mode after we received FLR_NOTIFY from host side, this can prevent innocent app wrongly succesed to open amdgpu dri device. FLR_NOFITY is received due to an IDLE hang detected from hypervisor side which indicating GPU is already die in this VF. v2: use MACRO as the offset of mailbox_control register don't test if NOTIFY_CMPL event in rcv_msg since it won't recieve that message anymore Signed-off-by: Monk Liu Reviewed-by: Pixel Ding Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c | 196 ++++++++++++++++++---------------- 1 file changed, 103 insertions(+), 93 deletions(-) (limited to 'drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c') diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c index 271452d3999a..8b47484e169a 100644 --- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c +++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c @@ -33,56 +33,34 @@ static void xgpu_ai_mailbox_send_ack(struct amdgpu_device *adev) { - u32 reg; - int timeout = AI_MAILBOX_TIMEDOUT; - u32 mask = REG_FIELD_MASK(BIF_BX_PF0_MAILBOX_CONTROL, RCV_MSG_VALID); - - reg = RREG32_NO_KIQ(SOC15_REG_OFFSET(NBIO, 0, - mmBIF_BX_PF0_MAILBOX_CONTROL)); - reg = REG_SET_FIELD(reg, BIF_BX_PF0_MAILBOX_CONTROL, RCV_MSG_ACK, 1); - WREG32_NO_KIQ(SOC15_REG_OFFSET(NBIO, 0, - mmBIF_BX_PF0_MAILBOX_CONTROL), reg); - - /*Wait for RCV_MSG_VALID to be 0*/ - reg = RREG32_NO_KIQ(SOC15_REG_OFFSET(NBIO, 0, - mmBIF_BX_PF0_MAILBOX_CONTROL)); - while (reg & mask) { - if (timeout <= 0) { - pr_err("RCV_MSG_VALID is not cleared\n"); - break; - } - mdelay(1); - timeout -=1; - - reg = RREG32_NO_KIQ(SOC15_REG_OFFSET(NBIO, 0, - mmBIF_BX_PF0_MAILBOX_CONTROL)); - } + WREG8(AI_MAIBOX_CONTROL_RCV_OFFSET_BYTE, 2); } static void xgpu_ai_mailbox_set_valid(struct amdgpu_device *adev, bool val) { - u32 reg; + WREG8(AI_MAIBOX_CONTROL_TRN_OFFSET_BYTE, val ? 1 : 0); +} - reg = RREG32_NO_KIQ(SOC15_REG_OFFSET(NBIO, 0, - mmBIF_BX_PF0_MAILBOX_CONTROL)); - reg = REG_SET_FIELD(reg, BIF_BX_PF0_MAILBOX_CONTROL, - TRN_MSG_VALID, val ? 1 : 0); - WREG32_NO_KIQ(SOC15_REG_OFFSET(NBIO, 0, mmBIF_BX_PF0_MAILBOX_CONTROL), - reg); +/* + * this peek_msg could *only* be called in IRQ routine becuase in IRQ routine + * RCV_MSG_VALID filed of BIF_BX_PF0_MAILBOX_CONTROL must already be set to 1 + * by host. + * + * if called no in IRQ routine, this peek_msg cannot guaranteed to return the + * correct value since it doesn't return the RCV_DW0 under the case that + * RCV_MSG_VALID is set by host. + */ +static enum idh_event xgpu_ai_mailbox_peek_msg(struct amdgpu_device *adev) +{ + return RREG32_NO_KIQ(SOC15_REG_OFFSET(NBIO, 0, + mmBIF_BX_PF0_MAILBOX_MSGBUF_RCV_DW0)); } + static int xgpu_ai_mailbox_rcv_msg(struct amdgpu_device *adev, enum idh_event event) { u32 reg; - u32 mask = REG_FIELD_MASK(BIF_BX_PF0_MAILBOX_CONTROL, RCV_MSG_VALID); - - if (event != IDH_FLR_NOTIFICATION_CMPL) { - reg = RREG32_NO_KIQ(SOC15_REG_OFFSET(NBIO, 0, - mmBIF_BX_PF0_MAILBOX_CONTROL)); - if (!(reg & mask)) - return -ENOENT; - } reg = RREG32_NO_KIQ(SOC15_REG_OFFSET(NBIO, 0, mmBIF_BX_PF0_MAILBOX_MSGBUF_RCV_DW0)); @@ -94,54 +72,67 @@ static int xgpu_ai_mailbox_rcv_msg(struct amdgpu_device *adev, return 0; } +static uint8_t xgpu_ai_peek_ack(struct amdgpu_device *adev) { + return RREG8(AI_MAIBOX_CONTROL_TRN_OFFSET_BYTE) & 2; +} + static int xgpu_ai_poll_ack(struct amdgpu_device *adev) { - int r = 0, timeout = AI_MAILBOX_TIMEDOUT; - u32 mask = REG_FIELD_MASK(BIF_BX_PF0_MAILBOX_CONTROL, TRN_MSG_ACK); - u32 reg; + int timeout = AI_MAILBOX_POLL_ACK_TIMEDOUT; + u8 reg; + + do { + reg = RREG8(AI_MAIBOX_CONTROL_TRN_OFFSET_BYTE); + if (reg & 2) + return 0; - reg = RREG32_NO_KIQ(SOC15_REG_OFFSET(NBIO, 0, - mmBIF_BX_PF0_MAILBOX_CONTROL)); - while (!(reg & mask)) { - if (timeout <= 0) { - pr_err("Doesn't get ack from pf.\n"); - r = -ETIME; - break; - } mdelay(5); timeout -= 5; + } while (timeout > 1); - reg = RREG32_NO_KIQ(SOC15_REG_OFFSET(NBIO, 0, - mmBIF_BX_PF0_MAILBOX_CONTROL)); - } + pr_err("Doesn't get TRN_MSG_ACK from pf in %d msec\n", AI_MAILBOX_POLL_ACK_TIMEDOUT); - return r; + return -ETIME; } static int xgpu_ai_poll_msg(struct amdgpu_device *adev, enum idh_event event) { - int r = 0, timeout = AI_MAILBOX_TIMEDOUT; - - r = xgpu_ai_mailbox_rcv_msg(adev, event); - while (r) { - if (timeout <= 0) { - pr_err("Doesn't get msg:%d from pf.\n", event); - r = -ETIME; - break; - } - mdelay(5); - timeout -= 5; + int r, timeout = AI_MAILBOX_POLL_MSG_TIMEDOUT; + do { r = xgpu_ai_mailbox_rcv_msg(adev, event); - } + if (!r) + return 0; - return r; + msleep(10); + timeout -= 10; + } while (timeout > 1); + + pr_err("Doesn't get msg:%d from pf, error=%d\n", event, r); + + return -ETIME; } static void xgpu_ai_mailbox_trans_msg (struct amdgpu_device *adev, enum idh_request req, u32 data1, u32 data2, u32 data3) { u32 reg; int r; + uint8_t trn; + + /* IMPORTANT: + * clear TRN_MSG_VALID valid to clear host's RCV_MSG_ACK + * and with host's RCV_MSG_ACK cleared hw automatically clear host's RCV_MSG_ACK + * which lead to VF's TRN_MSG_ACK cleared, otherwise below xgpu_ai_poll_ack() + * will return immediatly + */ + do { + xgpu_ai_mailbox_set_valid(adev, false); + trn = xgpu_ai_peek_ack(adev); + if (trn) { + pr_err("trn=%x ACK should not asssert! wait again !\n", trn); + msleep(1); + } + } while(trn); reg = RREG32_NO_KIQ(SOC15_REG_OFFSET(NBIO, 0, mmBIF_BX_PF0_MAILBOX_MSGBUF_TRN_DW0)); @@ -245,15 +236,36 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work) { struct amdgpu_virt *virt = container_of(work, struct amdgpu_virt, flr_work); struct amdgpu_device *adev = container_of(virt, struct amdgpu_device, virt); - - /* wait until RCV_MSG become 3 */ - if (xgpu_ai_poll_msg(adev, IDH_FLR_NOTIFICATION_CMPL)) { - pr_err("failed to recieve FLR_CMPL\n"); - return; - } - - /* Trigger recovery due to world switch failure */ - amdgpu_device_gpu_recover(adev, NULL, false); + int timeout = AI_MAILBOX_POLL_FLR_TIMEDOUT; + int locked; + + /* block amdgpu_gpu_recover till msg FLR COMPLETE received, + * otherwise the mailbox msg will be ruined/reseted by + * the VF FLR. + * + * we can unlock the lock_reset to allow "amdgpu_job_timedout" + * to run gpu_recover() after FLR_NOTIFICATION_CMPL received + * which means host side had finished this VF's FLR. + */ + locked = mutex_trylock(&adev->lock_reset); + if (locked) + adev->in_gpu_reset = 1; + + do { + if (xgpu_ai_mailbox_peek_msg(adev) == IDH_FLR_NOTIFICATION_CMPL) + goto flr_done; + + msleep(10); + timeout -= 10; + } while (timeout > 1); + +flr_done: + if (locked) + mutex_unlock(&adev->lock_reset); + + /* Trigger recovery for world switch failure if no TDR */ + if (amdgpu_lockup_timeout == 0) + amdgpu_device_gpu_recover(adev, NULL, true); } static int xgpu_ai_set_mailbox_rcv_irq(struct amdgpu_device *adev, @@ -274,24 +286,22 @@ static int xgpu_ai_mailbox_rcv_irq(struct amdgpu_device *adev, struct amdgpu_irq_src *source, struct amdgpu_iv_entry *entry) { - int r; - - /* trigger gpu-reset by hypervisor only if TDR disbaled */ - if (!amdgpu_gpu_recovery) { - /* see what event we get */ - r = xgpu_ai_mailbox_rcv_msg(adev, IDH_FLR_NOTIFICATION); - - /* sometimes the interrupt is delayed to inject to VM, so under such case - * the IDH_FLR_NOTIFICATION is overwritten by VF FLR from GIM side, thus - * above recieve message could be failed, we should schedule the flr_work - * anyway + enum idh_event event = xgpu_ai_mailbox_peek_msg(adev); + + switch (event) { + case IDH_FLR_NOTIFICATION: + if (amdgpu_sriov_runtime(adev)) + schedule_work(&adev->virt.flr_work); + break; + /* READY_TO_ACCESS_GPU is fetched by kernel polling, IRQ can ignore + * it byfar since that polling thread will handle it, + * other msg like flr complete is not handled here. */ - if (r) { - DRM_ERROR("FLR_NOTIFICATION is missed\n"); - xgpu_ai_mailbox_send_ack(adev); - } - - schedule_work(&adev->virt.flr_work); + case IDH_CLR_MSG_BUF: + case IDH_FLR_NOTIFICATION_CMPL: + case IDH_READY_TO_ACCESS_GPU: + default: + break; } return 0; -- cgit v1.2.3-59-g8ed1b From 3760f76cbebb455deaaa3e64ad5feb25222e65a9 Mon Sep 17 00:00:00 2001 From: Oak Zeng Date: Thu, 8 Mar 2018 16:44:47 -0500 Subject: drm/amdgpu: Move IH clientid defs to separate file This is preparation for sharing client ID definitions between amdgpu and amdkfd Signed-off-by: Oak Zeng Reviewed-by: Chunming Zhou Acked-by: Alex Deucher Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h | 43 +------------ drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 8 +-- drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 4 +- drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c | 4 +- drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c | 8 +-- drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c | 4 +- drivers/gpu/drm/amd/amdgpu/vce_v4_0.c | 2 +- drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c | 4 +- drivers/gpu/drm/amd/amdgpu/vega10_ih.c | 4 +- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 8 +-- drivers/gpu/drm/amd/include/soc15_ih_clientid.h | 70 ++++++++++++++++++++++ drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c | 6 +- 12 files changed, 98 insertions(+), 67 deletions(-) create mode 100644 drivers/gpu/drm/amd/include/soc15_ih_clientid.h (limited to 'drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h index b8a7dba69595..0e01f115bbe5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h @@ -25,51 +25,12 @@ #define __AMDGPU_IH_H__ #include +#include "soc15_ih_clientid.h" struct amdgpu_device; - /* - * vega10+ IH clients - */ -enum amdgpu_ih_clientid -{ - AMDGPU_IH_CLIENTID_IH = 0x00, - AMDGPU_IH_CLIENTID_ACP = 0x01, - AMDGPU_IH_CLIENTID_ATHUB = 0x02, - AMDGPU_IH_CLIENTID_BIF = 0x03, - AMDGPU_IH_CLIENTID_DCE = 0x04, - AMDGPU_IH_CLIENTID_ISP = 0x05, - AMDGPU_IH_CLIENTID_PCIE0 = 0x06, - AMDGPU_IH_CLIENTID_RLC = 0x07, - AMDGPU_IH_CLIENTID_SDMA0 = 0x08, - AMDGPU_IH_CLIENTID_SDMA1 = 0x09, - AMDGPU_IH_CLIENTID_SE0SH = 0x0a, - AMDGPU_IH_CLIENTID_SE1SH = 0x0b, - AMDGPU_IH_CLIENTID_SE2SH = 0x0c, - AMDGPU_IH_CLIENTID_SE3SH = 0x0d, - AMDGPU_IH_CLIENTID_SYSHUB = 0x0e, - AMDGPU_IH_CLIENTID_THM = 0x0f, - AMDGPU_IH_CLIENTID_UVD = 0x10, - AMDGPU_IH_CLIENTID_VCE0 = 0x11, - AMDGPU_IH_CLIENTID_VMC = 0x12, - AMDGPU_IH_CLIENTID_XDMA = 0x13, - AMDGPU_IH_CLIENTID_GRBM_CP = 0x14, - AMDGPU_IH_CLIENTID_ATS = 0x15, - AMDGPU_IH_CLIENTID_ROM_SMUIO = 0x16, - AMDGPU_IH_CLIENTID_DF = 0x17, - AMDGPU_IH_CLIENTID_VCE1 = 0x18, - AMDGPU_IH_CLIENTID_PWR = 0x19, - AMDGPU_IH_CLIENTID_UTCL2 = 0x1b, - AMDGPU_IH_CLIENTID_EA = 0x1c, - AMDGPU_IH_CLIENTID_UTCL2LOG = 0x1d, - AMDGPU_IH_CLIENTID_MP0 = 0x1e, - AMDGPU_IH_CLIENTID_MP1 = 0x1f, - - AMDGPU_IH_CLIENTID_MAX, - - AMDGPU_IH_CLIENTID_VCN = AMDGPU_IH_CLIENTID_UVD -}; #define AMDGPU_IH_CLIENTID_LEGACY 0 +#define AMDGPU_IH_CLIENTID_MAX SOC15_IH_CLIENTID_MAX #define AMDGPU_PAGEFAULT_HASH_BITS 8 struct amdgpu_retryfault_hashtable { diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index d73bbb092202..d1d2c27156b2 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -1261,23 +1261,23 @@ static int gfx_v9_0_sw_init(void *handle) adev->gfx.mec.num_queue_per_pipe = 8; /* KIQ event */ - r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_GRBM_CP, 178, &adev->gfx.kiq.irq); + r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_GRBM_CP, 178, &adev->gfx.kiq.irq); if (r) return r; /* EOP Event */ - r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_GRBM_CP, 181, &adev->gfx.eop_irq); + r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_GRBM_CP, 181, &adev->gfx.eop_irq); if (r) return r; /* Privileged reg */ - r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_GRBM_CP, 184, + r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_GRBM_CP, 184, &adev->gfx.priv_reg_irq); if (r) return r; /* Privileged inst */ - r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_GRBM_CP, 185, + r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_GRBM_CP, 185, &adev->gfx.priv_inst_irq); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index ceab14f16795..a70cbc45c4c1 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -861,9 +861,9 @@ static int gmc_v9_0_sw_init(void *handle) } /* This interrupt is VMC page fault.*/ - r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_VMC, 0, + r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VMC, 0, &adev->gmc.vm_fault); - r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_UTCL2, 0, + r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_UTCL2, 0, &adev->gmc.vm_fault); if (r) diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c index 8b47484e169a..8fb933c62cf5 100644 --- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c +++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c @@ -329,11 +329,11 @@ int xgpu_ai_mailbox_add_irq_id(struct amdgpu_device *adev) { int r; - r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_BIF, 135, &adev->virt.rcv_irq); + r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_BIF, 135, &adev->virt.rcv_irq); if (r) return r; - r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_BIF, 138, &adev->virt.ack_irq); + r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_BIF, 138, &adev->virt.ack_irq); if (r) { amdgpu_irq_put(adev, &adev->virt.rcv_irq, 0); return r; diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index 215743df0957..939f92b295a2 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -1172,13 +1172,13 @@ static int sdma_v4_0_sw_init(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; /* SDMA trap event */ - r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_SDMA0, 224, + r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_SDMA0, 224, &adev->sdma.trap_irq); if (r) return r; /* SDMA trap event */ - r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_SDMA1, 224, + r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_SDMA1, 224, &adev->sdma.trap_irq); if (r) return r; @@ -1333,7 +1333,7 @@ static int sdma_v4_0_process_trap_irq(struct amdgpu_device *adev, { DRM_DEBUG("IH: SDMA trap\n"); switch (entry->client_id) { - case AMDGPU_IH_CLIENTID_SDMA0: + case SOC15_IH_CLIENTID_SDMA0: switch (entry->ring_id) { case 0: amdgpu_fence_process(&adev->sdma.instance[0].ring); @@ -1349,7 +1349,7 @@ static int sdma_v4_0_process_trap_irq(struct amdgpu_device *adev, break; } break; - case AMDGPU_IH_CLIENTID_SDMA1: + case SOC15_IH_CLIENTID_SDMA1: switch (entry->ring_id) { case 0: amdgpu_fence_process(&adev->sdma.instance[1].ring); diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c index e54cc3ca2303..eddc57f3b72a 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c @@ -390,13 +390,13 @@ static int uvd_v7_0_sw_init(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; /* UVD TRAP */ - r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_UVD, 124, &adev->uvd.irq); + r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_UVD, 124, &adev->uvd.irq); if (r) return r; /* UVD ENC TRAP */ for (i = 0; i < adev->uvd.num_enc_rings; ++i) { - r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_UVD, i + 119, &adev->uvd.irq); + r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_UVD, i + 119, &adev->uvd.irq); if (r) return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c index 2329b310ccf2..73fd48d6c756 100755 --- a/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c @@ -420,7 +420,7 @@ static int vce_v4_0_sw_init(void *handle) unsigned size; int r, i; - r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_VCE0, 167, &adev->vce.irq); + r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCE0, 167, &adev->vce.irq); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c index fdf4ac9313cf..8c132673bc79 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c @@ -75,13 +75,13 @@ static int vcn_v1_0_sw_init(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; /* VCN DEC TRAP */ - r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_VCN, 124, &adev->vcn.irq); + r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN, 124, &adev->vcn.irq); if (r) return r; /* VCN ENC TRAP */ for (i = 0; i < adev->vcn.num_enc_rings; ++i) { - r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_VCN, i + 119, + r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN, i + 119, &adev->vcn.irq); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c index cc8ce7e352a8..5ae5ed2e62d6 100644 --- a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c @@ -245,8 +245,8 @@ static bool vega10_ih_prescreen_iv(struct amdgpu_device *adev) * some faults get cleared. */ switch (dw0 & 0xff) { - case AMDGPU_IH_CLIENTID_VMC: - case AMDGPU_IH_CLIENTID_UTCL2: + case SOC15_IH_CLIENTID_VMC: + case SOC15_IH_CLIENTID_UTCL2: break; default: /* Not a VM fault */ diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index f523b2476c1e..9e2f673cb6e1 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1131,7 +1131,7 @@ static int dce110_register_irq_handlers(struct amdgpu_device *adev) if (adev->asic_type == CHIP_VEGA10 || adev->asic_type == CHIP_RAVEN) - client_id = AMDGPU_IH_CLIENTID_DCE; + client_id = SOC15_IH_CLIENTID_DCE; int_params.requested_polarity = INTERRUPT_POLARITY_DEFAULT; int_params.current_polarity = INTERRUPT_POLARITY_DEFAULT; @@ -1231,7 +1231,7 @@ static int dcn10_register_irq_handlers(struct amdgpu_device *adev) for (i = DCN_1_0__SRCID__DC_D1_OTG_VSTARTUP; i <= DCN_1_0__SRCID__DC_D1_OTG_VSTARTUP + adev->mode_info.num_crtc - 1; i++) { - r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_DCE, i, &adev->crtc_irq); + r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_DCE, i, &adev->crtc_irq); if (r) { DRM_ERROR("Failed to add crtc irq id!\n"); @@ -1255,7 +1255,7 @@ static int dcn10_register_irq_handlers(struct amdgpu_device *adev) for (i = DCN_1_0__SRCID__HUBP0_FLIP_INTERRUPT; i <= DCN_1_0__SRCID__HUBP0_FLIP_INTERRUPT + adev->mode_info.num_crtc - 1; i++) { - r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_DCE, i, &adev->pageflip_irq); + r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_DCE, i, &adev->pageflip_irq); if (r) { DRM_ERROR("Failed to add page flip irq id!\n"); return r; @@ -1276,7 +1276,7 @@ static int dcn10_register_irq_handlers(struct amdgpu_device *adev) } /* HPD */ - r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_DCE, DCN_1_0__SRCID__DC_HPD1_INT, + r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_DCE, DCN_1_0__SRCID__DC_HPD1_INT, &adev->hpd_irq); if (r) { DRM_ERROR("Failed to add hpd irq id!\n"); diff --git a/drivers/gpu/drm/amd/include/soc15_ih_clientid.h b/drivers/gpu/drm/amd/include/soc15_ih_clientid.h new file mode 100644 index 000000000000..a12d4f27cfa4 --- /dev/null +++ b/drivers/gpu/drm/amd/include/soc15_ih_clientid.h @@ -0,0 +1,70 @@ +/* + * Copyright 2018 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + */ + +#ifndef __SOC15_IH_CLIENTID_H__ +#define __SOC15_IH_CLIENTID_H__ + + /* + * vega10+ IH clients + */ +enum soc15_ih_clientid { + SOC15_IH_CLIENTID_IH = 0x00, + SOC15_IH_CLIENTID_ACP = 0x01, + SOC15_IH_CLIENTID_ATHUB = 0x02, + SOC15_IH_CLIENTID_BIF = 0x03, + SOC15_IH_CLIENTID_DCE = 0x04, + SOC15_IH_CLIENTID_ISP = 0x05, + SOC15_IH_CLIENTID_PCIE0 = 0x06, + SOC15_IH_CLIENTID_RLC = 0x07, + SOC15_IH_CLIENTID_SDMA0 = 0x08, + SOC15_IH_CLIENTID_SDMA1 = 0x09, + SOC15_IH_CLIENTID_SE0SH = 0x0a, + SOC15_IH_CLIENTID_SE1SH = 0x0b, + SOC15_IH_CLIENTID_SE2SH = 0x0c, + SOC15_IH_CLIENTID_SE3SH = 0x0d, + SOC15_IH_CLIENTID_SYSHUB = 0x0e, + SOC15_IH_CLIENTID_THM = 0x0f, + SOC15_IH_CLIENTID_UVD = 0x10, + SOC15_IH_CLIENTID_VCE0 = 0x11, + SOC15_IH_CLIENTID_VMC = 0x12, + SOC15_IH_CLIENTID_XDMA = 0x13, + SOC15_IH_CLIENTID_GRBM_CP = 0x14, + SOC15_IH_CLIENTID_ATS = 0x15, + SOC15_IH_CLIENTID_ROM_SMUIO = 0x16, + SOC15_IH_CLIENTID_DF = 0x17, + SOC15_IH_CLIENTID_VCE1 = 0x18, + SOC15_IH_CLIENTID_PWR = 0x19, + SOC15_IH_CLIENTID_UTCL2 = 0x1b, + SOC15_IH_CLIENTID_EA = 0x1c, + SOC15_IH_CLIENTID_UTCL2LOG = 0x1d, + SOC15_IH_CLIENTID_MP0 = 0x1e, + SOC15_IH_CLIENTID_MP1 = 0x1f, + + SOC15_IH_CLIENTID_MAX, + + SOC15_IH_CLIENTID_VCN = SOC15_IH_CLIENTID_UVD +}; + +#endif + + diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c index f23861f2c685..2fcbb17b794d 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c @@ -4874,12 +4874,12 @@ static int vega10_register_thermal_interrupt(struct pp_hwmgr *hwmgr, hwmgr->thermal_controller.ucType == ATOM_VEGA10_PP_THERMALCONTROLLER_EMC2103_WITH_INTERNAL) { PP_ASSERT_WITH_CODE(!cgs_add_irq_source(hwmgr->device, - 0xf, /* AMDGPU_IH_CLIENTID_THM */ + SOC15_IH_CLIENTID_THM, 0, 0, irq_src[0].set, irq_src[0].handler, hwmgr), "Failed to register high thermal interrupt!", return -EINVAL); PP_ASSERT_WITH_CODE(!cgs_add_irq_source(hwmgr->device, - 0xf, /* AMDGPU_IH_CLIENTID_THM */ + SOC15_IH_CLIENTID_THM, 1, 0, irq_src[1].set, irq_src[1].handler, hwmgr), "Failed to register low thermal interrupt!", return -EINVAL); @@ -4887,7 +4887,7 @@ static int vega10_register_thermal_interrupt(struct pp_hwmgr *hwmgr, /* Register CTF(GPIO_19) interrupt */ PP_ASSERT_WITH_CODE(!cgs_add_irq_source(hwmgr->device, - 0x16, /* AMDGPU_IH_CLIENTID_ROM_SMUIO, */ + SOC15_IH_CLIENTID_ROM_SMUIO, 83, 0, irq_src[2].set, irq_src[2].handler, hwmgr), "Failed to register CTF thermal interrupt!", return -EINVAL); -- cgit v1.2.3-59-g8ed1b