Implement suspend and resume callbacks for AIE4 Physical Function (PF), Virtual Function (VF), and Classic device types: - Implement aie4_hwctx_suspend_all() to destroy or drain contexts across all registered clients and wait for in-flight jobs. - Implement aie4_hwctx_resume_all() to recreate firmware contexts and kick doorbells via aie4_hwctx_resume_jobs() to resume hardware queue consumption. - Guard firmware destroy message in aie4_hwctx_destroy() when context ID is invalid. - Restore SR-IOV virtual functions on PF resume via aie4_restore_sriov(). - Link each VF to the PF with a stateless device link when SR-IOV is enabled, so system suspend handles VFs before the PF and resume handles the PF before VFs. The link survives VF driver rebind and is removed before SR-IOV is disabled.
Signed-off-by: David Zhang <[email protected]> --- drivers/accel/amdxdna/aie4_ctx.c | 18 +- drivers/accel/amdxdna/aie4_pci.c | 247 ++++++++++++++++++++++++ drivers/accel/amdxdna/aie4_pci.h | 11 ++ drivers/accel/amdxdna/aie4_sriov.c | 66 ++++++- drivers/accel/amdxdna/amdxdna_pci_drv.h | 3 + 5 files changed, 343 insertions(+), 2 deletions(-) diff --git a/drivers/accel/amdxdna/aie4_ctx.c b/drivers/accel/amdxdna/aie4_ctx.c index 31bf30b9dc86..be669c2804db 100644 --- a/drivers/accel/amdxdna/aie4_ctx.c +++ b/drivers/accel/amdxdna/aie4_ctx.c @@ -249,7 +249,7 @@ void aie4_hwctx_destroy(struct amdxdna_hwctx *hwctx, enum aie4_hwctx_flags flags if (has_error) wake_up_all(&priv->job_list_wq); - if (flags != AIE4_HWCTX_DISCONNECT) + if (flags != AIE4_HWCTX_DISCONNECT && priv->hw_ctx_id != CTX_INVALID_ID) aie4_msg_destroy_context(ndev, priv->hw_ctx_id); if (cert_comp) @@ -357,6 +357,7 @@ int aie4_hwctx_init(struct amdxdna_hwctx *hwctx) return -ENOMEM; hwctx->priv = priv; priv->hwctx = hwctx; + priv->hw_ctx_id = CTX_INVALID_ID; /* Initialize io_lock guarding cert_comp binding. */ mutex_init(&priv->io_lock); @@ -907,6 +908,21 @@ int aie4_hwctx_wait_for_running(struct amdxdna_hwctx *hwctx) return ret; } +void aie4_hwctx_resume_jobs(struct amdxdna_hwctx *hwctx) +{ + struct amdxdna_hwctx_priv *priv = hwctx->priv; + + mutex_lock(&priv->io_lock); + if (list_empty(&priv->running_job_list)) { + mutex_unlock(&priv->io_lock); + return; + } + aie4_doorbell_ring(hwctx); + mutex_unlock(&priv->io_lock); + + queue_work(priv->job_work_q, &priv->job_work); +} + static void put_cmd_bos(struct amdxdna_sched_job *job) { u32 i; diff --git a/drivers/accel/amdxdna/aie4_pci.c b/drivers/accel/amdxdna/aie4_pci.c index ae5b42287ef5..a368bd3c257f 100644 --- a/drivers/accel/amdxdna/aie4_pci.c +++ b/drivers/accel/amdxdna/aie4_pci.c @@ -1125,11 +1125,254 @@ static void aie4_debugfs_init(struct amdxdna_dev *xdna) &aie4_ctx_hysteresis_fops); } +void aie4_hwctx_suspend_all(struct amdxdna_dev_hdl *ndev, int clean_jobs) +{ + struct amdxdna_dev *xdna = ndev->aie.xdna; + struct amdxdna_client *client; + struct amdxdna_hwctx *hwctx; + unsigned long hwctx_id; + int idx; + + drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock)); + + amdxdna_for_each_client(xdna, client) { + idx = srcu_read_lock(&client->hwctx_srcu); + amdxdna_for_each_hwctx(client, hwctx_id, hwctx) { + /* clean up workers and drain running jobs */ + if (clean_jobs) { + int ret; + + aie4_hwctx_destroy(hwctx, AIE4_HWCTX_ERROR); + ret = aie4_hwctx_wait_for_running(hwctx); + if (ret) + XDNA_WARN(xdna, "hwctx %s wait for running failed %d", + hwctx->name, ret); + } else { + aie4_hwctx_destroy(hwctx, AIE4_HWCTX_NORMAL); + } + } + srcu_read_unlock(&client->hwctx_srcu, idx); + } + + XDNA_DBG(xdna, "Finished hwctx suspend"); +} + +int aie4_hwctx_resume_all(struct amdxdna_dev_hdl *ndev) +{ + struct amdxdna_dev *xdna = ndev->aie.xdna; + struct amdxdna_client *client; + struct amdxdna_hwctx *hwctx; + unsigned long hwctx_id; + int ret, idx; + + drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock)); + + amdxdna_for_each_client(xdna, client) { + idx = srcu_read_lock(&client->hwctx_srcu); + amdxdna_for_each_hwctx(client, hwctx_id, hwctx) { + ret = aie4_hwctx_create(hwctx); + if (ret) + goto error; + aie4_hwctx_resume_jobs(hwctx); + } + srcu_read_unlock(&client->hwctx_srcu, idx); + } + + XDNA_DBG(xdna, "Finished hwctx resume"); + return 0; +error: + srcu_read_unlock(&client->hwctx_srcu, idx); + XDNA_DBG(xdna, "Failed hwctx resume"); + return ret; +} + +static int aie4_restore_sriov(struct amdxdna_dev_hdl *ndev) +{ + struct amdxdna_dev *xdna = ndev->aie.xdna; + struct pci_dev *pdev = to_pci_dev(xdna->ddev.dev); + int ret; + + if (ndev->num_vfs) { + if (pci_num_vf(pdev) != ndev->num_vfs) { + XDNA_ERR(xdna, "inconsistent vf number"); + return -EINVAL; + } + ret = aie4_create_vfs(ndev, ndev->num_vfs); + if (ret) { + XDNA_ERR(xdna, "create vfs failed, %d", ret); + return ret; + } + XDNA_DBG(xdna, "restored num_vfs %d", ndev->num_vfs); + } + + return 0; +} + +static int aie4_pf_suspend(struct amdxdna_dev *xdna) +{ + struct amdxdna_dev_hdl *ndev = xdna->dev_handle; + struct pci_dev *pdev = to_pci_dev(xdna->ddev.dev); + + drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock)); + aie4_pf_hw_stop(ndev); + pci_disable_device(pdev); + + XDNA_DBG(xdna, "pf suspend done"); + return 0; +} + +static int aie4_pf_resume(struct amdxdna_dev *xdna) +{ + struct amdxdna_dev_hdl *ndev = xdna->dev_handle; + struct pci_dev *pdev = to_pci_dev(xdna->ddev.dev); + int ret; + + drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock)); + + ret = pci_enable_device(pdev); + if (ret) { + XDNA_ERR(xdna, "enable pci device failed %d", ret); + return ret; + } + pci_set_master(pdev); + + ret = aie4_pf_hw_start(ndev); + if (ret) { + XDNA_ERR(xdna, "hw_start failed %d", ret); + goto pci_disable; + } + + ret = aie4_restore_sriov(ndev); + if (ret) + goto hw_stop; + + XDNA_DBG(xdna, "pf resume done"); + return 0; +hw_stop: + aie4_pf_hw_stop(ndev); +pci_disable: + pci_disable_device(pdev); + return ret; +} + +static int aie4_vf_suspend(struct amdxdna_dev *xdna) +{ + struct amdxdna_dev_hdl *ndev = xdna->dev_handle; + struct pci_dev *pdev = to_pci_dev(xdna->ddev.dev); + + drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock)); + aie4_hwctx_suspend_all(ndev, false); + /* + * partition_fini and mailbox messages should not be called here + * because PF suspend will do the cleanup for all VFs. + */ + aie4_mailbox_fini(ndev); + pci_disable_device(pdev); + + XDNA_DBG(xdna, "vf suspend done"); + return 0; +} + +static int aie4_vf_resume(struct amdxdna_dev *xdna) +{ + struct amdxdna_dev_hdl *ndev = xdna->dev_handle; + struct pci_dev *pdev = to_pci_dev(xdna->ddev.dev); + int ret; + + drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock)); + + ret = pci_enable_device(pdev); + if (ret) { + XDNA_ERR(xdna, "enable pci device failed %d", ret); + return ret; + } + pci_set_master(pdev); + + ret = aie4_vf_hw_start(ndev); + if (ret) { + XDNA_ERR(xdna, "hw_start failed %d", ret); + /* Contexts cannot reconnect; fail waiters and abort running jobs. */ + aie4_hwctx_suspend_all(ndev, true); + goto pci_disable; + } + + ret = aie4_hwctx_resume_all(ndev); + if (ret) { + XDNA_ERR(xdna, "hwctx_resume failed %d", ret); + goto hw_clear; + } + + XDNA_DBG(xdna, "vf resume done"); + return 0; + +hw_clear: + aie4_hwctx_suspend_all(ndev, true); + aie4_vf_hw_stop(ndev); +pci_disable: + pci_disable_device(pdev); + return ret; +} + +static int aie4_classic_suspend(struct amdxdna_dev *xdna) +{ + struct amdxdna_dev_hdl *ndev = xdna->dev_handle; + struct pci_dev *pdev = to_pci_dev(xdna->ddev.dev); + + drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock)); + aie4_hwctx_suspend_all(ndev, false); + aie4_classic_hw_stop(ndev); + pci_disable_device(pdev); + + XDNA_DBG(xdna, "classic suspend done"); + return 0; +} + +static int aie4_classic_resume(struct amdxdna_dev *xdna) +{ + struct amdxdna_dev_hdl *ndev = xdna->dev_handle; + struct pci_dev *pdev = to_pci_dev(xdna->ddev.dev); + int ret; + + drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock)); + + ret = pci_enable_device(pdev); + if (ret) { + XDNA_ERR(xdna, "enable pci device failed %d", ret); + return ret; + } + pci_set_master(pdev); + + ret = aie4_classic_hw_start(ndev); + if (ret) { + XDNA_ERR(xdna, "hw_start failed %d", ret); + /* Contexts cannot reconnect; fail waiters and abort running jobs. */ + aie4_hwctx_suspend_all(ndev, true); + goto pci_disable; + } + + ret = aie4_hwctx_resume_all(ndev); + if (ret) { + XDNA_ERR(xdna, "hwctx_resume failed %d", ret); + goto hw_clear; + } + + XDNA_DBG(xdna, "classic resume done"); + return 0; +hw_clear: + aie4_hwctx_suspend_all(ndev, true); + aie4_classic_hw_stop(ndev); +pci_disable: + pci_disable_device(pdev); + return ret; +} + const struct amdxdna_dev_ops aie4_pf_ops = { .init = aie4_pf_init, .fini = aie4_pf_fini, .debugfs_init = aie4_debugfs_init, .sriov_configure = aie4_sriov_configure, + .resume = aie4_pf_resume, + .suspend = aie4_pf_suspend, }; const struct amdxdna_dev_ops aie4_vf_ops = { @@ -1143,6 +1386,8 @@ const struct amdxdna_dev_ops aie4_vf_ops = { .cmd_wait = aie4_cmd_wait, .get_aie_info = aie4_get_info, .set_aie_state = aie4_set_state, + .resume = aie4_vf_resume, + .suspend = aie4_vf_suspend, }; const struct amdxdna_dev_ops aie4_classic_ops = { @@ -1156,4 +1401,6 @@ const struct amdxdna_dev_ops aie4_classic_ops = { .cmd_wait = aie4_cmd_wait, .get_aie_info = aie4_get_info, .set_aie_state = aie4_set_state, + .resume = aie4_classic_resume, + .suspend = aie4_classic_suspend, }; diff --git a/drivers/accel/amdxdna/aie4_pci.h b/drivers/accel/amdxdna/aie4_pci.h index 4b7367af7cf1..fdc55e498246 100644 --- a/drivers/accel/amdxdna/aie4_pci.h +++ b/drivers/accel/amdxdna/aie4_pci.h @@ -95,6 +95,7 @@ struct amdxdna_dev_hdl { u32 total_col; u32 max_aieclk_level; u32 max_npuhclk_level; + u32 num_vfs; struct dpm_clk_freq dpm_clk_tbl[AIE4_MAX_DPM_LEVEL_COUNT]; @@ -159,8 +160,11 @@ int aie4_cmd_submit(struct amdxdna_hwctx *hwctx, struct amdxdna_sched_job *job, int aie4_hwctx_create(struct amdxdna_hwctx *hwctx); void aie4_hwctx_destroy(struct amdxdna_hwctx *hwctx, enum aie4_hwctx_flags); int aie4_hwctx_wait_for_running(struct amdxdna_hwctx *hwctx); +void aie4_hwctx_resume_jobs(struct amdxdna_hwctx *hwctx); /* aie4_pci.c */ +void aie4_hwctx_suspend_all(struct amdxdna_dev_hdl *ndev, int clean_jobs); +int aie4_hwctx_resume_all(struct amdxdna_dev_hdl *ndev); int aie4_restore_power_mode(struct amdxdna_dev_hdl *ndev); /* @@ -176,10 +180,17 @@ void aie4_free_notification(struct cert_comp *comp); /* aie4_sriov.c */ #if IS_ENABLED(CONFIG_PCI_IOV) +int aie4_create_vfs(struct amdxdna_dev_hdl *ndev, int num_vfs); int aie4_sriov_configure(struct amdxdna_dev *xdna, int num_vfs); int aie4_sriov_stop(struct amdxdna_dev_hdl *ndev); #else +static inline int aie4_create_vfs(struct amdxdna_dev_hdl *ndev, int num_vfs) +{ + return 0; +} + #define aie4_sriov_configure NULL + static inline int aie4_sriov_stop(struct amdxdna_dev_hdl *ndev) { return 0; diff --git a/drivers/accel/amdxdna/aie4_sriov.c b/drivers/accel/amdxdna/aie4_sriov.c index e1ce633768a5..d3df36644914 100644 --- a/drivers/accel/amdxdna/aie4_sriov.c +++ b/drivers/accel/amdxdna/aie4_sriov.c @@ -26,7 +26,7 @@ static int aie4_destroy_vfs(struct amdxdna_dev_hdl *ndev) return ret; } -static int aie4_create_vfs(struct amdxdna_dev_hdl *ndev, int num_vfs) +int aie4_create_vfs(struct amdxdna_dev_hdl *ndev, int num_vfs) { DECLARE_AIE_MSG(aie4_msg_create_vfs, AIE4_MSG_OP_CREATE_VFS); int ret; @@ -39,6 +39,59 @@ static int aie4_create_vfs(struct amdxdna_dev_hdl *ndev, int num_vfs) return ret; } +static int aie4_for_each_vfs(struct amdxdna_dev *xdna, + int (*cb)(struct amdxdna_dev *, struct pci_dev *)) +{ + struct pci_dev *pdev_pf = to_pci_dev(xdna->ddev.dev); + struct pci_dev *pdev_vf; + int pos, ret; + u16 vf_did; + + pos = pci_find_ext_capability(pdev_pf, PCI_EXT_CAP_ID_SRIOV); + if (!pos) + return 0; + ret = pci_read_config_word(pdev_pf, pos + PCI_SRIOV_VF_DID, &vf_did); + if (ret) { + XDNA_ERR(xdna, "read VF Device ID failed %d", ret); + return -ENODEV; + } + + for (pdev_vf = pci_get_device(pdev_pf->vendor, vf_did, NULL); + pdev_vf; + pdev_vf = pci_get_device(pdev_pf->vendor, vf_did, pdev_vf)) { + if (!pdev_vf->is_virtfn || pdev_vf->physfn != pdev_pf) + continue; + + ret = cb(xdna, pdev_vf); + if (ret) { + /* Release reference on early return. */ + pci_dev_put(pdev_vf); + return ret; + } + } + + return 0; +} + +static int aie4_link_vf(struct amdxdna_dev *xdna, struct pci_dev *pdev_vf) +{ + struct pci_dev *pdev_pf = to_pci_dev(xdna->ddev.dev); + + /* Stateless so the link survives VF driver rebind. */ + if (!device_link_add(&pdev_vf->dev, &pdev_pf->dev, DL_FLAG_STATELESS)) { + XDNA_ERR(xdna, "Failed to link VF %s", pci_name(pdev_vf)); + return -EINVAL; + } + + return 0; +} + +static int aie4_unlink_vf(struct amdxdna_dev *xdna, struct pci_dev *pdev_vf) +{ + device_link_remove(&pdev_vf->dev, xdna->ddev.dev); + return 0; +} + int aie4_sriov_stop(struct amdxdna_dev_hdl *ndev) { struct amdxdna_dev *xdna = ndev->aie.xdna; @@ -54,7 +107,9 @@ int aie4_sriov_stop(struct amdxdna_dev_hdl *ndev) return -EPERM; } + aie4_for_each_vfs(xdna, aie4_unlink_vf); pci_disable_sriov(pdev); + ndev->num_vfs = 0; return aie4_destroy_vfs(ndev); } @@ -75,6 +130,15 @@ static int aie4_sriov_start(struct amdxdna_dev_hdl *ndev, int num_vfs) return ret; } + ret = aie4_for_each_vfs(xdna, aie4_link_vf); + if (ret) { + aie4_for_each_vfs(xdna, aie4_unlink_vf); + pci_disable_sriov(pdev); + aie4_destroy_vfs(ndev); + return ret; + } + + ndev->num_vfs = num_vfs; return num_vfs; } diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.h b/drivers/accel/amdxdna/amdxdna_pci_drv.h index eccb461d32bc..505477b4a292 100644 --- a/drivers/accel/amdxdna/amdxdna_pci_drv.h +++ b/drivers/accel/amdxdna/amdxdna_pci_drv.h @@ -168,6 +168,9 @@ struct amdxdna_client { #define amdxdna_for_each_hwctx(client, hwctx_id, entry) \ xa_for_each(&(client)->hwctx_xa, hwctx_id, entry) +#define amdxdna_for_each_client(xdna, client) \ + list_for_each_entry(client, &(xdna)->client_list, node) + /* Add device info below */ extern const struct amdxdna_dev_info dev_npu1_info; extern const struct amdxdna_dev_info dev_npu3_classic_info; -- 2.34.1
