From b86711c6d6e20eb945fe878de98ef7c9be2c2088 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Fri, 8 Nov 2024 16:42:38 +0100 Subject: drm/client: Move public client header to clients/ subdirectory Move the public header file drm_client_setup.h to the clients/ subdirectory and update all drivers. No functional changes. Signed-off-by: Thomas Zimmermann Reviewed-by: Jocelyn Falempe Link: https://patchwork.freedesktop.org/patch/msgid/20241108154600.126162-3-tzimmermann@suse.de --- include/drm/clients/drm_client_setup.h | 26 ++++++++++++++++++++++++++ include/drm/drm_client_setup.h | 26 -------------------------- 2 files changed, 26 insertions(+), 26 deletions(-) create mode 100644 include/drm/clients/drm_client_setup.h delete mode 100644 include/drm/drm_client_setup.h (limited to 'include') diff --git a/include/drm/clients/drm_client_setup.h b/include/drm/clients/drm_client_setup.h new file mode 100644 index 000000000000..46aab3fb46be --- /dev/null +++ b/include/drm/clients/drm_client_setup.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: MIT */ + +#ifndef DRM_CLIENT_SETUP_H +#define DRM_CLIENT_SETUP_H + +#include + +struct drm_device; +struct drm_format_info; + +#if defined(CONFIG_DRM_CLIENT_SETUP) +void drm_client_setup(struct drm_device *dev, const struct drm_format_info *format); +void drm_client_setup_with_fourcc(struct drm_device *dev, u32 fourcc); +void drm_client_setup_with_color_mode(struct drm_device *dev, unsigned int color_mode); +#else +static inline void drm_client_setup(struct drm_device *dev, + const struct drm_format_info *format) +{ } +static inline void drm_client_setup_with_fourcc(struct drm_device *dev, u32 fourcc) +{ } +static inline void drm_client_setup_with_color_mode(struct drm_device *dev, + unsigned int color_mode) +{ } +#endif + +#endif diff --git a/include/drm/drm_client_setup.h b/include/drm/drm_client_setup.h deleted file mode 100644 index 46aab3fb46be..000000000000 --- a/include/drm/drm_client_setup.h +++ /dev/null @@ -1,26 +0,0 @@ -/* SPDX-License-Identifier: MIT */ - -#ifndef DRM_CLIENT_SETUP_H -#define DRM_CLIENT_SETUP_H - -#include - -struct drm_device; -struct drm_format_info; - -#if defined(CONFIG_DRM_CLIENT_SETUP) -void drm_client_setup(struct drm_device *dev, const struct drm_format_info *format); -void drm_client_setup_with_fourcc(struct drm_device *dev, u32 fourcc); -void drm_client_setup_with_color_mode(struct drm_device *dev, unsigned int color_mode); -#else -static inline void drm_client_setup(struct drm_device *dev, - const struct drm_format_info *format) -{ } -static inline void drm_client_setup_with_fourcc(struct drm_device *dev, u32 fourcc) -{ } -static inline void drm_client_setup_with_color_mode(struct drm_device *dev, - unsigned int color_mode) -{ } -#endif - -#endif -- cgit v1.2.3 From 7d2faa8dbb7055a115fe0cd6068d7090094a573d Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Fri, 8 Nov 2024 16:42:39 +0100 Subject: drm/fbdev-client: Unexport drm_fbdev_client_setup() DRM drivers invoke drm_client_setup() to set up in-kernel clients. No driver should call drm_fbdev_client_setup() directly. Therefore, unexport the symbol and move the declaration to the internal header drm_client_internal.h. Signed-off-by: Thomas Zimmermann Reviewed-by: Jocelyn Falempe Link: https://patchwork.freedesktop.org/patch/msgid/20241108154600.126162-4-tzimmermann@suse.de --- drivers/gpu/drm/clients/drm_client_internal.h | 19 +++++++++++++++++++ drivers/gpu/drm/clients/drm_client_setup.c | 3 ++- drivers/gpu/drm/clients/drm_fbdev_client.c | 4 ++-- include/drm/drm_fbdev_client.h | 19 ------------------- 4 files changed, 23 insertions(+), 22 deletions(-) create mode 100644 drivers/gpu/drm/clients/drm_client_internal.h delete mode 100644 include/drm/drm_fbdev_client.h (limited to 'include') diff --git a/drivers/gpu/drm/clients/drm_client_internal.h b/drivers/gpu/drm/clients/drm_client_internal.h new file mode 100644 index 000000000000..23258934956a --- /dev/null +++ b/drivers/gpu/drm/clients/drm_client_internal.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: MIT */ + +#ifndef DRM_CLIENT_INTERNAL_H +#define DRM_CLIENT_INTERNAL_H + +struct drm_device; +struct drm_format_info; + +#ifdef CONFIG_DRM_FBDEV_EMULATION +int drm_fbdev_client_setup(struct drm_device *dev, const struct drm_format_info *format); +#else +static inline int drm_fbdev_client_setup(struct drm_device *dev, + const struct drm_format_info *format) +{ + return 0; +} +#endif + +#endif diff --git a/drivers/gpu/drm/clients/drm_client_setup.c b/drivers/gpu/drm/clients/drm_client_setup.c index c6a295d5de50..4b211a4812b5 100644 --- a/drivers/gpu/drm/clients/drm_client_setup.c +++ b/drivers/gpu/drm/clients/drm_client_setup.c @@ -2,10 +2,11 @@ #include #include -#include #include #include +#include "drm_client_internal.h" + /** * drm_client_setup() - Setup in-kernel DRM clients * @dev: DRM device diff --git a/drivers/gpu/drm/clients/drm_fbdev_client.c b/drivers/gpu/drm/clients/drm_fbdev_client.c index 246fb63ab250..f894ba52bdb5 100644 --- a/drivers/gpu/drm/clients/drm_fbdev_client.c +++ b/drivers/gpu/drm/clients/drm_fbdev_client.c @@ -3,11 +3,12 @@ #include #include #include -#include #include #include #include +#include "drm_client_internal.h" + /* * struct drm_client_funcs */ @@ -164,4 +165,3 @@ err_drm_client_init: kfree(fb_helper); return ret; } -EXPORT_SYMBOL(drm_fbdev_client_setup); diff --git a/include/drm/drm_fbdev_client.h b/include/drm/drm_fbdev_client.h deleted file mode 100644 index e11a5614f127..000000000000 --- a/include/drm/drm_fbdev_client.h +++ /dev/null @@ -1,19 +0,0 @@ -/* SPDX-License-Identifier: MIT */ - -#ifndef DRM_FBDEV_CLIENT_H -#define DRM_FBDEV_CLIENT_H - -struct drm_device; -struct drm_format_info; - -#ifdef CONFIG_DRM_FBDEV_EMULATION -int drm_fbdev_client_setup(struct drm_device *dev, const struct drm_format_info *format); -#else -static inline int drm_fbdev_client_setup(struct drm_device *dev, - const struct drm_format_info *format) -{ - return 0; -} -#endif - -#endif -- cgit v1.2.3 From 22e5c7ae12145af13785e3ff138395d5b1a22116 Mon Sep 17 00:00:00 2001 From: Thomas Weißschuh Date: Mon, 11 Nov 2024 19:09:35 +0100 Subject: drm: Add panel backlight quirks MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Panels using a PWM-controlled backlight source do not have a standard way to communicate their valid PWM ranges. On x86 the ranges are read from ACPI through driver-specific tables. The built-in ranges are not necessarily correct, or may grow stale if an older device can be retrofitted with newer panels. Add a quirk infrastructure with which the minimum valid backlight value can be maintained as part of the kernel. Signed-off-by: Thomas Weißschuh Tested-by: Dustin L. Howett Reviewed-by: Mario Limonciello Reviewed-by: Harry Wentland Signed-off-by: Mario Limonciello Link: https://patchwork.freedesktop.org/patch/msgid/20241111-amdgpu-min-backlight-quirk-v7-1-f662851fda69@weissschuh.net --- Documentation/gpu/drm-kms-helpers.rst | 3 ++ drivers/gpu/drm/Kconfig | 4 ++ drivers/gpu/drm/Makefile | 1 + drivers/gpu/drm/drm_panel_backlight_quirks.c | 70 ++++++++++++++++++++++++++++ include/drm/drm_utils.h | 4 ++ 5 files changed, 82 insertions(+) create mode 100644 drivers/gpu/drm/drm_panel_backlight_quirks.c (limited to 'include') diff --git a/Documentation/gpu/drm-kms-helpers.rst b/Documentation/gpu/drm-kms-helpers.rst index 8cf2f041af47..b4ee25af1702 100644 --- a/Documentation/gpu/drm-kms-helpers.rst +++ b/Documentation/gpu/drm-kms-helpers.rst @@ -221,6 +221,9 @@ Panel Helper Reference .. kernel-doc:: drivers/gpu/drm/drm_panel_orientation_quirks.c :export: +.. kernel-doc:: drivers/gpu/drm/drm_panel_backlight_quirks.c + :export: + Panel Self Refresh Helper Reference =================================== diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index fd294ccca6bb..698981a2ed51 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -456,6 +456,10 @@ config DRM_HYPERV config DRM_EXPORT_FOR_TESTS bool +# Separate option as not all DRM drivers use it +config DRM_PANEL_BACKLIGHT_QUIRKS + tristate + config DRM_LIB_RANDOM bool default n diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile index 4f6585be14cc..1677c1f335fb 100644 --- a/drivers/gpu/drm/Makefile +++ b/drivers/gpu/drm/Makefile @@ -95,6 +95,7 @@ drm-$(CONFIG_DRM_PANIC_SCREEN_QR_CODE) += drm_panic_qr.o obj-$(CONFIG_DRM) += drm.o obj-$(CONFIG_DRM_PANEL_ORIENTATION_QUIRKS) += drm_panel_orientation_quirks.o +obj-$(CONFIG_DRM_PANEL_BACKLIGHT_QUIRKS) += drm_panel_backlight_quirks.o # # Memory-management helpers diff --git a/drivers/gpu/drm/drm_panel_backlight_quirks.c b/drivers/gpu/drm/drm_panel_backlight_quirks.c new file mode 100644 index 000000000000..6b8bbed77c7f --- /dev/null +++ b/drivers/gpu/drm/drm_panel_backlight_quirks.c @@ -0,0 +1,70 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include +#include +#include +#include +#include + +struct drm_panel_min_backlight_quirk { + struct { + enum dmi_field field; + const char * const value; + } dmi_match; + struct drm_edid_ident ident; + u8 min_brightness; +}; + +static const struct drm_panel_min_backlight_quirk drm_panel_min_backlight_quirks[] = { +}; + +static bool drm_panel_min_backlight_quirk_matches(const struct drm_panel_min_backlight_quirk *quirk, + const struct drm_edid *edid) +{ + if (!dmi_match(quirk->dmi_match.field, quirk->dmi_match.value)) + return false; + + if (!drm_edid_match(edid, &quirk->ident)) + return false; + + return true; +} + +/** + * drm_get_panel_min_brightness_quirk - Get minimum supported brightness level for a panel. + * @edid: EDID of the panel to check + * + * This function checks for platform specific (e.g. DMI based) quirks + * providing info on the minimum backlight brightness for systems where this + * cannot be probed correctly from the hard-/firm-ware. + * + * Returns: + * A negative error value or + * an override value in the range [0, 255] representing 0-100% to be scaled to + * the drivers target range. + */ +int drm_get_panel_min_brightness_quirk(const struct drm_edid *edid) +{ + const struct drm_panel_min_backlight_quirk *quirk; + size_t i; + + if (!IS_ENABLED(CONFIG_DMI)) + return -ENODATA; + + if (!edid) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(drm_panel_min_backlight_quirks); i++) { + quirk = &drm_panel_min_backlight_quirks[i]; + + if (drm_panel_min_backlight_quirk_matches(quirk, edid)) + return quirk->min_brightness; + } + + return -ENODATA; +} +EXPORT_SYMBOL(drm_get_panel_min_brightness_quirk); + +MODULE_DESCRIPTION("Quirks for panel backlight overrides"); +MODULE_LICENSE("GPL"); diff --git a/include/drm/drm_utils.h b/include/drm/drm_utils.h index 70775748d243..15fa9b6865f4 100644 --- a/include/drm/drm_utils.h +++ b/include/drm/drm_utils.h @@ -12,8 +12,12 @@ #include +struct drm_edid; + int drm_get_panel_orientation_quirk(int width, int height); +int drm_get_panel_min_brightness_quirk(const struct drm_edid *edid); + signed long drm_timeout_abs_to_jiffies(int64_t timeout_nsec); #endif -- cgit v1.2.3 From 8c9ff1b181ba3d31d6b4a48606248b52180a7046 Mon Sep 17 00:00:00 2001 From: Lizhi Hou Date: Mon, 18 Nov 2024 09:29:34 -0800 Subject: accel/amdxdna: Add a new driver for AMD AI Engine AMD AI Engine forms the core of AMD NPU and can be used for accelerating machine learning applications. Add the driver to support AI Engine integrated to AMD CPU. Only very basic functionalities are added. - module and PCI device initialization - firmware load - power up - low level hardware initialization Co-developed-by: Narendra Gutta Signed-off-by: Narendra Gutta Co-developed-by: George Yang Signed-off-by: George Yang Co-developed-by: Min Ma Signed-off-by: Min Ma Reviewed-by: Jeffrey Hugo Signed-off-by: Lizhi Hou Signed-off-by: Jeffrey Hugo Link: https://patchwork.freedesktop.org/patch/msgid/20241118172942.2014541-3-lizhi.hou@amd.com --- MAINTAINERS | 10 ++ drivers/accel/Kconfig | 1 + drivers/accel/Makefile | 1 + drivers/accel/amdxdna/Kconfig | 18 ++++ drivers/accel/amdxdna/Makefile | 13 +++ drivers/accel/amdxdna/TODO | 5 + drivers/accel/amdxdna/aie2_pci.c | 181 ++++++++++++++++++++++++++++++++ drivers/accel/amdxdna/aie2_pci.h | 130 +++++++++++++++++++++++ drivers/accel/amdxdna/aie2_psp.c | 142 +++++++++++++++++++++++++ drivers/accel/amdxdna/aie2_smu.c | 117 +++++++++++++++++++++ drivers/accel/amdxdna/amdxdna_pci_drv.c | 129 +++++++++++++++++++++++ drivers/accel/amdxdna/amdxdna_pci_drv.h | 76 ++++++++++++++ drivers/accel/amdxdna/amdxdna_sysfs.c | 51 +++++++++ drivers/accel/amdxdna/npu1_regs.c | 99 +++++++++++++++++ drivers/accel/amdxdna/npu2_regs.c | 116 ++++++++++++++++++++ drivers/accel/amdxdna/npu4_regs.c | 116 ++++++++++++++++++++ drivers/accel/amdxdna/npu5_regs.c | 116 ++++++++++++++++++++ include/uapi/drm/amdxdna_accel.h | 24 +++++ 18 files changed, 1345 insertions(+) create mode 100644 drivers/accel/amdxdna/Kconfig create mode 100644 drivers/accel/amdxdna/Makefile create mode 100644 drivers/accel/amdxdna/TODO create mode 100644 drivers/accel/amdxdna/aie2_pci.c create mode 100644 drivers/accel/amdxdna/aie2_pci.h create mode 100644 drivers/accel/amdxdna/aie2_psp.c create mode 100644 drivers/accel/amdxdna/aie2_smu.c create mode 100644 drivers/accel/amdxdna/amdxdna_pci_drv.c create mode 100644 drivers/accel/amdxdna/amdxdna_pci_drv.h create mode 100644 drivers/accel/amdxdna/amdxdna_sysfs.c create mode 100644 drivers/accel/amdxdna/npu1_regs.c create mode 100644 drivers/accel/amdxdna/npu2_regs.c create mode 100644 drivers/accel/amdxdna/npu4_regs.c create mode 100644 drivers/accel/amdxdna/npu5_regs.c create mode 100644 include/uapi/drm/amdxdna_accel.h (limited to 'include') diff --git a/MAINTAINERS b/MAINTAINERS index 08e1f793ee45..cde77eb0bf1e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1178,6 +1178,16 @@ M: Sanjay R Mehta S: Maintained F: drivers/spi/spi-amd.c +AMD XDNA DRIVER +M: Min Ma +M: Lizhi Hou +L: dri-devel@lists.freedesktop.org +S: Supported +T: git https://gitlab.freedesktop.org/drm/misc/kernel.git +F: Documentation/accel/amdxdna/ +F: drivers/accel/amdxdna/ +F: include/uapi/drm/amdxdna_accel.h + AMD XGBE DRIVER M: "Shyam Sundar S K" L: netdev@vger.kernel.org diff --git a/drivers/accel/Kconfig b/drivers/accel/Kconfig index 64065fb8922b..5b9490367a39 100644 --- a/drivers/accel/Kconfig +++ b/drivers/accel/Kconfig @@ -24,6 +24,7 @@ menuconfig DRM_ACCEL different device files, called accel/accel* (in /dev, sysfs and debugfs). +source "drivers/accel/amdxdna/Kconfig" source "drivers/accel/habanalabs/Kconfig" source "drivers/accel/ivpu/Kconfig" source "drivers/accel/qaic/Kconfig" diff --git a/drivers/accel/Makefile b/drivers/accel/Makefile index ab3df932937f..a301fb6089d4 100644 --- a/drivers/accel/Makefile +++ b/drivers/accel/Makefile @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only +obj-$(CONFIG_DRM_ACCEL_AMDXDNA) += amdxdna/ obj-$(CONFIG_DRM_ACCEL_HABANALABS) += habanalabs/ obj-$(CONFIG_DRM_ACCEL_IVPU) += ivpu/ obj-$(CONFIG_DRM_ACCEL_QAIC) += qaic/ diff --git a/drivers/accel/amdxdna/Kconfig b/drivers/accel/amdxdna/Kconfig new file mode 100644 index 000000000000..f39d7a87296c --- /dev/null +++ b/drivers/accel/amdxdna/Kconfig @@ -0,0 +1,18 @@ +# SPDX-License-Identifier: GPL-2.0-only + +config DRM_ACCEL_AMDXDNA + tristate "AMD AI Engine" + depends on AMD_IOMMU + depends on DRM_ACCEL + depends on PCI && HAS_IOMEM + depends on X86_64 + select DRM_SCHED + select DRM_GEM_SHMEM_HELPER + select FW_LOADER + select HMM_MIRROR + help + Choose this option to enable support for NPU integrated into AMD + client CPUs like AMD Ryzen AI 300 Series. AMD NPU can be used to + accelerate machine learning applications. + + If "M" is selected, the driver module will be amdxdna. diff --git a/drivers/accel/amdxdna/Makefile b/drivers/accel/amdxdna/Makefile new file mode 100644 index 000000000000..1dee0cba8390 --- /dev/null +++ b/drivers/accel/amdxdna/Makefile @@ -0,0 +1,13 @@ +# SPDX-License-Identifier: GPL-2.0-only + +amdxdna-y := \ + aie2_pci.o \ + aie2_psp.o \ + aie2_smu.o \ + amdxdna_pci_drv.o \ + amdxdna_sysfs.o \ + npu1_regs.o \ + npu2_regs.o \ + npu4_regs.o \ + npu5_regs.o +obj-$(CONFIG_DRM_ACCEL_AMDXDNA) = amdxdna.o diff --git a/drivers/accel/amdxdna/TODO b/drivers/accel/amdxdna/TODO new file mode 100644 index 000000000000..a130259f5f70 --- /dev/null +++ b/drivers/accel/amdxdna/TODO @@ -0,0 +1,5 @@ +- Replace idr with xa +- Add import and export BO support +- Add debugfs support +- Add debug BO support +- Improve power management diff --git a/drivers/accel/amdxdna/aie2_pci.c b/drivers/accel/amdxdna/aie2_pci.c new file mode 100644 index 000000000000..770931674abb --- /dev/null +++ b/drivers/accel/amdxdna/aie2_pci.c @@ -0,0 +1,181 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2023-2024, Advanced Micro Devices, Inc. + */ + +#include +#include +#include +#include +#include +#include +#include + +#include "aie2_pci.h" +#include "amdxdna_pci_drv.h" + +static void aie2_hw_stop(struct amdxdna_dev *xdna) +{ + struct pci_dev *pdev = to_pci_dev(xdna->ddev.dev); + struct amdxdna_dev_hdl *ndev = xdna->dev_handle; + + aie2_psp_stop(ndev->psp_hdl); + aie2_smu_fini(ndev); + pci_disable_device(pdev); +} + +static int aie2_hw_start(struct amdxdna_dev *xdna) +{ + struct pci_dev *pdev = to_pci_dev(xdna->ddev.dev); + struct amdxdna_dev_hdl *ndev = xdna->dev_handle; + int ret; + + ret = pci_enable_device(pdev); + if (ret) { + XDNA_ERR(xdna, "failed to enable device, ret %d", ret); + return ret; + } + pci_set_master(pdev); + + ret = aie2_smu_init(ndev); + if (ret) { + XDNA_ERR(xdna, "failed to init smu, ret %d", ret); + goto disable_dev; + } + + ret = aie2_psp_start(ndev->psp_hdl); + if (ret) { + XDNA_ERR(xdna, "failed to start psp, ret %d", ret); + goto fini_smu; + } + + return 0; + +fini_smu: + aie2_smu_fini(ndev); +disable_dev: + pci_disable_device(pdev); + + return ret; +} + +static int aie2_init(struct amdxdna_dev *xdna) +{ + struct pci_dev *pdev = to_pci_dev(xdna->ddev.dev); + void __iomem *tbl[PCI_NUM_RESOURCES] = {0}; + struct amdxdna_dev_hdl *ndev; + struct psp_config psp_conf; + const struct firmware *fw; + unsigned long bars = 0; + int i, nvec, ret; + + ndev = drmm_kzalloc(&xdna->ddev, sizeof(*ndev), GFP_KERNEL); + if (!ndev) + return -ENOMEM; + + ndev->priv = xdna->dev_info->dev_priv; + ndev->xdna = xdna; + + ret = request_firmware(&fw, ndev->priv->fw_path, &pdev->dev); + if (ret) { + XDNA_ERR(xdna, "failed to request_firmware %s, ret %d", + ndev->priv->fw_path, ret); + return ret; + } + + ret = pcim_enable_device(pdev); + if (ret) { + XDNA_ERR(xdna, "pcim enable device failed, ret %d", ret); + goto release_fw; + } + + for (i = 0; i < PSP_MAX_REGS; i++) + set_bit(PSP_REG_BAR(ndev, i), &bars); + + set_bit(xdna->dev_info->sram_bar, &bars); + set_bit(xdna->dev_info->smu_bar, &bars); + set_bit(xdna->dev_info->mbox_bar, &bars); + + for (i = 0; i < PCI_NUM_RESOURCES; i++) { + if (!test_bit(i, &bars)) + continue; + tbl[i] = pcim_iomap(pdev, i, 0); + if (!tbl[i]) { + XDNA_ERR(xdna, "map bar %d failed", i); + ret = -ENOMEM; + goto release_fw; + } + } + + ndev->sram_base = tbl[xdna->dev_info->sram_bar]; + ndev->smu_base = tbl[xdna->dev_info->smu_bar]; + + ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + if (ret) { + XDNA_ERR(xdna, "Failed to set DMA mask: %d", ret); + goto release_fw; + } + + nvec = pci_msix_vec_count(pdev); + if (nvec <= 0) { + XDNA_ERR(xdna, "does not get number of interrupt vector"); + ret = -EINVAL; + goto release_fw; + } + + ret = pci_alloc_irq_vectors(pdev, nvec, nvec, PCI_IRQ_MSIX); + if (ret < 0) { + XDNA_ERR(xdna, "failed to alloc irq vectors, ret %d", ret); + goto release_fw; + } + + ret = iommu_dev_enable_feature(&pdev->dev, IOMMU_DEV_FEAT_SVA); + if (ret) { + XDNA_ERR(xdna, "Enable PASID failed, ret %d", ret); + goto free_irq; + } + + psp_conf.fw_size = fw->size; + psp_conf.fw_buf = fw->data; + for (i = 0; i < PSP_MAX_REGS; i++) + psp_conf.psp_regs[i] = tbl[PSP_REG_BAR(ndev, i)] + PSP_REG_OFF(ndev, i); + ndev->psp_hdl = aie2m_psp_create(&xdna->ddev, &psp_conf); + if (!ndev->psp_hdl) { + XDNA_ERR(xdna, "failed to create psp"); + ret = -ENOMEM; + goto disable_sva; + } + xdna->dev_handle = ndev; + + ret = aie2_hw_start(xdna); + if (ret) { + XDNA_ERR(xdna, "start npu failed, ret %d", ret); + goto disable_sva; + } + + release_firmware(fw); + return 0; + +disable_sva: + iommu_dev_disable_feature(&pdev->dev, IOMMU_DEV_FEAT_SVA); +free_irq: + pci_free_irq_vectors(pdev); +release_fw: + release_firmware(fw); + + return ret; +} + +static void aie2_fini(struct amdxdna_dev *xdna) +{ + struct pci_dev *pdev = to_pci_dev(xdna->ddev.dev); + + aie2_hw_stop(xdna); + iommu_dev_disable_feature(&pdev->dev, IOMMU_DEV_FEAT_SVA); + pci_free_irq_vectors(pdev); +} + +const struct amdxdna_dev_ops aie2_ops = { + .init = aie2_init, + .fini = aie2_fini, +}; diff --git a/drivers/accel/amdxdna/aie2_pci.h b/drivers/accel/amdxdna/aie2_pci.h new file mode 100644 index 000000000000..34f344b4b662 --- /dev/null +++ b/drivers/accel/amdxdna/aie2_pci.h @@ -0,0 +1,130 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2023-2024, Advanced Micro Devices, Inc. + */ + +#ifndef _AIE2_PCI_H_ +#define _AIE2_PCI_H_ + +#define AIE2_INTERVAL 20000 /* us */ +#define AIE2_TIMEOUT 1000000 /* us */ + +/* Firmware determines device memory base address and size */ +#define AIE2_DEVM_BASE 0x4000000 +#define AIE2_DEVM_SIZE SZ_64M + +#define NDEV2PDEV(ndev) (to_pci_dev((ndev)->xdna->ddev.dev)) + +#define AIE2_SRAM_OFF(ndev, addr) ((addr) - (ndev)->priv->sram_dev_addr) +#define AIE2_MBOX_OFF(ndev, addr) ((addr) - (ndev)->priv->mbox_dev_addr) + +#define PSP_REG_BAR(ndev, idx) ((ndev)->priv->psp_regs_off[(idx)].bar_idx) +#define PSP_REG_OFF(ndev, idx) ((ndev)->priv->psp_regs_off[(idx)].offset) +#define SRAM_REG_OFF(ndev, idx) ((ndev)->priv->sram_offs[(idx)].offset) + +#define SMU_REG(ndev, idx) \ +({ \ + typeof(ndev) _ndev = ndev; \ + ((_ndev)->smu_base + (_ndev)->priv->smu_regs_off[(idx)].offset); \ +}) +#define SRAM_GET_ADDR(ndev, idx) \ +({ \ + typeof(ndev) _ndev = ndev; \ + ((_ndev)->sram_base + SRAM_REG_OFF((_ndev), (idx))); \ +}) + +#define SMU_MPNPUCLK_FREQ_MAX(ndev) ((ndev)->priv->smu_mpnpuclk_freq_max) +#define SMU_HCLK_FREQ_MAX(ndev) ((ndev)->priv->smu_hclk_freq_max) + +enum aie2_smu_reg_idx { + SMU_CMD_REG = 0, + SMU_ARG_REG, + SMU_INTR_REG, + SMU_RESP_REG, + SMU_OUT_REG, + SMU_MAX_REGS /* Keep this at the end */ +}; + +enum aie2_sram_reg_idx { + MBOX_CHANN_OFF = 0, + FW_ALIVE_OFF, + SRAM_MAX_INDEX /* Keep this at the end */ +}; + +enum psp_reg_idx { + PSP_CMD_REG = 0, + PSP_ARG0_REG, + PSP_ARG1_REG, + PSP_ARG2_REG, + PSP_NUM_IN_REGS, /* number of input registers */ + PSP_INTR_REG = PSP_NUM_IN_REGS, + PSP_STATUS_REG, + PSP_RESP_REG, + PSP_MAX_REGS /* Keep this at the end */ +}; + +struct psp_config { + const void *fw_buf; + u32 fw_size; + void __iomem *psp_regs[PSP_MAX_REGS]; +}; + +struct clock_entry { + char name[16]; + u32 freq_mhz; +}; + +struct rt_config { + u32 type; + u32 value; +}; + +struct amdxdna_dev_hdl { + struct amdxdna_dev *xdna; + const struct amdxdna_dev_priv *priv; + void __iomem *sram_base; + void __iomem *smu_base; + struct psp_device *psp_hdl; + struct clock_entry mp_npu_clock; + struct clock_entry h_clock; +}; + +#define DEFINE_BAR_OFFSET(reg_name, bar, reg_addr) \ + [reg_name] = {bar##_BAR_INDEX, (reg_addr) - bar##_BAR_BASE} + +struct aie2_bar_off_pair { + int bar_idx; + u32 offset; +}; + +struct amdxdna_dev_priv { + const char *fw_path; + u64 protocol_major; + u64 protocol_minor; + struct rt_config rt_config; +#define COL_ALIGN_NONE 0 +#define COL_ALIGN_NATURE 1 + u32 col_align; + u32 mbox_dev_addr; + /* If mbox_size is 0, use BAR size. See MBOX_SIZE macro */ + u32 mbox_size; + u32 sram_dev_addr; + struct aie2_bar_off_pair sram_offs[SRAM_MAX_INDEX]; + struct aie2_bar_off_pair psp_regs_off[PSP_MAX_REGS]; + struct aie2_bar_off_pair smu_regs_off[SMU_MAX_REGS]; + u32 smu_mpnpuclk_freq_max; + u32 smu_hclk_freq_max; +}; + +extern const struct amdxdna_dev_ops aie2_ops; + +/* aie2_smu.c */ +int aie2_smu_init(struct amdxdna_dev_hdl *ndev); +void aie2_smu_fini(struct amdxdna_dev_hdl *ndev); + +/* aie2_psp.c */ +struct psp_device *aie2m_psp_create(struct drm_device *ddev, struct psp_config *conf); +int aie2_psp_start(struct psp_device *psp); +void aie2_psp_stop(struct psp_device *psp); + +#endif /* _AIE2_PCI_H_ */ diff --git a/drivers/accel/amdxdna/aie2_psp.c b/drivers/accel/amdxdna/aie2_psp.c new file mode 100644 index 000000000000..610ed8aa824a --- /dev/null +++ b/drivers/accel/amdxdna/aie2_psp.c @@ -0,0 +1,142 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022-2024, Advanced Micro Devices, Inc. + */ + +#include +#include +#include +#include +#include + +#include "aie2_pci.h" + +#define PSP_STATUS_READY BIT(31) + +/* PSP commands */ +#define PSP_VALIDATE 1 +#define PSP_START 2 +#define PSP_RELEASE_TMR 3 + +/* PSP special arguments */ +#define PSP_START_COPY_FW 1 + +/* PSP response error code */ +#define PSP_ERROR_CANCEL 0xFFFF0002 +#define PSP_ERROR_BAD_STATE 0xFFFF0007 + +#define PSP_FW_ALIGN 0x10000 +#define PSP_POLL_INTERVAL 20000 /* us */ +#define PSP_POLL_TIMEOUT 1000000 /* us */ + +#define PSP_REG(p, reg) ((p)->psp_regs[reg]) + +struct psp_device { + struct drm_device *ddev; + struct psp_config conf; + u32 fw_buf_sz; + u64 fw_paddr; + void *fw_buffer; + void __iomem *psp_regs[PSP_MAX_REGS]; +}; + +static int psp_exec(struct psp_device *psp, u32 *reg_vals) +{ + u32 resp_code; + int ret, i; + u32 ready; + + /* Write command and argument registers */ + for (i = 0; i < PSP_NUM_IN_REGS; i++) + writel(reg_vals[i], PSP_REG(psp, i)); + + /* clear and set PSP INTR register to kick off */ + writel(0, PSP_REG(psp, PSP_INTR_REG)); + writel(1, PSP_REG(psp, PSP_INTR_REG)); + + /* PSP should be busy. Wait for ready, so we know task is done. */ + ret = readx_poll_timeout(readl, PSP_REG(psp, PSP_STATUS_REG), ready, + FIELD_GET(PSP_STATUS_READY, ready), + PSP_POLL_INTERVAL, PSP_POLL_TIMEOUT); + if (ret) { + drm_err(psp->ddev, "PSP is not ready, ret 0x%x", ret); + return ret; + } + + resp_code = readl(PSP_REG(psp, PSP_RESP_REG)); + if (resp_code) { + drm_err(psp->ddev, "fw return error 0x%x", resp_code); + return -EIO; + } + + return 0; +} + +void aie2_psp_stop(struct psp_device *psp) +{ + u32 reg_vals[PSP_NUM_IN_REGS] = { PSP_RELEASE_TMR, }; + int ret; + + ret = psp_exec(psp, reg_vals); + if (ret) + drm_err(psp->ddev, "release tmr failed, ret %d", ret); +} + +int aie2_psp_start(struct psp_device *psp) +{ + u32 reg_vals[PSP_NUM_IN_REGS]; + int ret; + + reg_vals[0] = PSP_VALIDATE; + reg_vals[1] = lower_32_bits(psp->fw_paddr); + reg_vals[2] = upper_32_bits(psp->fw_paddr); + reg_vals[3] = psp->fw_buf_sz; + + ret = psp_exec(psp, reg_vals); + if (ret) { + drm_err(psp->ddev, "failed to validate fw, ret %d", ret); + return ret; + } + + memset(reg_vals, 0, sizeof(reg_vals)); + reg_vals[0] = PSP_START; + reg_vals[1] = PSP_START_COPY_FW; + ret = psp_exec(psp, reg_vals); + if (ret) { + drm_err(psp->ddev, "failed to start fw, ret %d", ret); + return ret; + } + + return 0; +} + +struct psp_device *aie2m_psp_create(struct drm_device *ddev, struct psp_config *conf) +{ + struct psp_device *psp; + u64 offset; + + psp = drmm_kzalloc(ddev, sizeof(*psp), GFP_KERNEL); + if (!psp) + return NULL; + + psp->ddev = ddev; + memcpy(psp->psp_regs, conf->psp_regs, sizeof(psp->psp_regs)); + + psp->fw_buf_sz = ALIGN(conf->fw_size, PSP_FW_ALIGN) + PSP_FW_ALIGN; + psp->fw_buffer = drmm_kmalloc(ddev, psp->fw_buf_sz, GFP_KERNEL); + if (!psp->fw_buffer) { + drm_err(ddev, "no memory for fw buffer"); + return NULL; + } + + /* + * AMD Platform Security Processor(PSP) requires host physical + * address to load NPU firmware. + */ + psp->fw_paddr = virt_to_phys(psp->fw_buffer); + offset = ALIGN(psp->fw_paddr, PSP_FW_ALIGN) - psp->fw_paddr; + psp->fw_paddr += offset; + memcpy(psp->fw_buffer + offset, conf->fw_buf, conf->fw_size); + + return psp; +} diff --git a/drivers/accel/amdxdna/aie2_smu.c b/drivers/accel/amdxdna/aie2_smu.c new file mode 100644 index 000000000000..3fa7064649aa --- /dev/null +++ b/drivers/accel/amdxdna/aie2_smu.c @@ -0,0 +1,117 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022-2024, Advanced Micro Devices, Inc. + */ + +#include +#include +#include + +#include "aie2_pci.h" +#include "amdxdna_pci_drv.h" + +#define SMU_RESULT_OK 1 + +/* SMU commands */ +#define AIE2_SMU_POWER_ON 0x3 +#define AIE2_SMU_POWER_OFF 0x4 +#define AIE2_SMU_SET_MPNPUCLK_FREQ 0x5 +#define AIE2_SMU_SET_HCLK_FREQ 0x6 + +static int aie2_smu_exec(struct amdxdna_dev_hdl *ndev, u32 reg_cmd, u32 reg_arg) +{ + u32 resp; + int ret; + + writel(0, SMU_REG(ndev, SMU_RESP_REG)); + writel(reg_arg, SMU_REG(ndev, SMU_ARG_REG)); + writel(reg_cmd, SMU_REG(ndev, SMU_CMD_REG)); + + /* Clear and set SMU_INTR_REG to kick off */ + writel(0, SMU_REG(ndev, SMU_INTR_REG)); + writel(1, SMU_REG(ndev, SMU_INTR_REG)); + + ret = readx_poll_timeout(readl, SMU_REG(ndev, SMU_RESP_REG), resp, + resp, AIE2_INTERVAL, AIE2_TIMEOUT); + if (ret) { + XDNA_ERR(ndev->xdna, "smu cmd %d timed out", reg_cmd); + return ret; + } + + if (resp != SMU_RESULT_OK) { + XDNA_ERR(ndev->xdna, "smu cmd %d failed, 0x%x", reg_cmd, resp); + return -EINVAL; + } + + return 0; +} + +static int aie2_smu_set_mpnpu_clock_freq(struct amdxdna_dev_hdl *ndev, u32 freq_mhz) +{ + int ret; + + if (!freq_mhz || freq_mhz > SMU_MPNPUCLK_FREQ_MAX(ndev)) { + XDNA_ERR(ndev->xdna, "invalid mpnpu clock freq %d", freq_mhz); + return -EINVAL; + } + + ndev->mp_npu_clock.freq_mhz = freq_mhz; + ret = aie2_smu_exec(ndev, AIE2_SMU_SET_MPNPUCLK_FREQ, freq_mhz); + if (!ret) + XDNA_INFO_ONCE(ndev->xdna, "set mpnpu_clock = %d mhz", freq_mhz); + + return ret; +} + +static int aie2_smu_set_hclock_freq(struct amdxdna_dev_hdl *ndev, u32 freq_mhz) +{ + int ret; + + if (!freq_mhz || freq_mhz > SMU_HCLK_FREQ_MAX(ndev)) { + XDNA_ERR(ndev->xdna, "invalid hclock freq %d", freq_mhz); + return -EINVAL; + } + + ndev->h_clock.freq_mhz = freq_mhz; + ret = aie2_smu_exec(ndev, AIE2_SMU_SET_HCLK_FREQ, freq_mhz); + if (!ret) + XDNA_INFO_ONCE(ndev->xdna, "set npu_hclock = %d mhz", freq_mhz); + + return ret; +} + +int aie2_smu_init(struct amdxdna_dev_hdl *ndev) +{ + int ret; + + ret = aie2_smu_exec(ndev, AIE2_SMU_POWER_ON, 0); + if (ret) { + XDNA_ERR(ndev->xdna, "Power on failed, ret %d", ret); + return ret; + } + + ret = aie2_smu_set_mpnpu_clock_freq(ndev, SMU_MPNPUCLK_FREQ_MAX(ndev)); + if (ret) { + XDNA_ERR(ndev->xdna, "Set mpnpu clk freq failed, ret %d", ret); + return ret; + } + snprintf(ndev->mp_npu_clock.name, sizeof(ndev->mp_npu_clock.name), "MP-NPU Clock"); + + ret = aie2_smu_set_hclock_freq(ndev, SMU_HCLK_FREQ_MAX(ndev)); + if (ret) { + XDNA_ERR(ndev->xdna, "Set hclk freq failed, ret %d", ret); + return ret; + } + snprintf(ndev->h_clock.name, sizeof(ndev->h_clock.name), "H Clock"); + + return 0; +} + +void aie2_smu_fini(struct amdxdna_dev_hdl *ndev) +{ + int ret; + + ret = aie2_smu_exec(ndev, AIE2_SMU_POWER_OFF, 0); + if (ret) + XDNA_ERR(ndev->xdna, "Power off failed, ret %d", ret); +} diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.c b/drivers/accel/amdxdna/amdxdna_pci_drv.c new file mode 100644 index 000000000000..b8caf323a0c6 --- /dev/null +++ b/drivers/accel/amdxdna/amdxdna_pci_drv.c @@ -0,0 +1,129 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022-2024, Advanced Micro Devices, Inc. + */ + +#include +#include +#include +#include +#include +#include + +#include "amdxdna_pci_drv.h" + +/* + * Bind the driver base on (vendor_id, device_id) pair and later use the + * (device_id, rev_id) pair as a key to select the devices. The devices with + * same device_id have very similar interface to host driver. + */ +static const struct pci_device_id pci_ids[] = { + { PCI_DEVICE(PCI_VENDOR_ID_AMD, 0x1502) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, 0x17f0) }, + {0} +}; + +MODULE_DEVICE_TABLE(pci, pci_ids); + +static const struct amdxdna_device_id amdxdna_ids[] = { + { 0x1502, 0x0, &dev_npu1_info }, + { 0x17f0, 0x0, &dev_npu2_info }, + { 0x17f0, 0x10, &dev_npu4_info }, + { 0x17f0, 0x11, &dev_npu5_info }, + {0} +}; + +DEFINE_DRM_ACCEL_FOPS(amdxdna_fops); + +const struct drm_driver amdxdna_drm_drv = { + .driver_features = DRIVER_GEM | DRIVER_COMPUTE_ACCEL | + DRIVER_SYNCOBJ | DRIVER_SYNCOBJ_TIMELINE, + .fops = &amdxdna_fops, + .name = "amdxdna_accel_driver", + .desc = "AMD XDNA DRM implementation", +}; + +static const struct amdxdna_dev_info * +amdxdna_get_dev_info(struct pci_dev *pdev) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(amdxdna_ids); i++) { + if (pdev->device == amdxdna_ids[i].device && + pdev->revision == amdxdna_ids[i].revision) + return amdxdna_ids[i].dev_info; + } + return NULL; +} + +static int amdxdna_probe(struct pci_dev *pdev, const struct pci_device_id *id) +{ + struct amdxdna_dev *xdna; + int ret; + + xdna = devm_drm_dev_alloc(&pdev->dev, &amdxdna_drm_drv, typeof(*xdna), ddev); + if (IS_ERR(xdna)) + return PTR_ERR(xdna); + + xdna->dev_info = amdxdna_get_dev_info(pdev); + if (!xdna->dev_info) + return -ENODEV; + + drmm_mutex_init(&xdna->ddev, &xdna->dev_lock); + pci_set_drvdata(pdev, xdna); + + mutex_lock(&xdna->dev_lock); + ret = xdna->dev_info->ops->init(xdna); + mutex_unlock(&xdna->dev_lock); + if (ret) { + XDNA_ERR(xdna, "Hardware init failed, ret %d", ret); + return ret; + } + + ret = amdxdna_sysfs_init(xdna); + if (ret) { + XDNA_ERR(xdna, "Create amdxdna attrs failed: %d", ret); + goto failed_dev_fini; + } + + ret = drm_dev_register(&xdna->ddev, 0); + if (ret) { + XDNA_ERR(xdna, "DRM register failed, ret %d", ret); + goto failed_sysfs_fini; + } + + return 0; + +failed_sysfs_fini: + amdxdna_sysfs_fini(xdna); +failed_dev_fini: + mutex_lock(&xdna->dev_lock); + xdna->dev_info->ops->fini(xdna); + mutex_unlock(&xdna->dev_lock); + return ret; +} + +static void amdxdna_remove(struct pci_dev *pdev) +{ + struct amdxdna_dev *xdna = pci_get_drvdata(pdev); + + drm_dev_unplug(&xdna->ddev); + amdxdna_sysfs_fini(xdna); + + mutex_lock(&xdna->dev_lock); + xdna->dev_info->ops->fini(xdna); + mutex_unlock(&xdna->dev_lock); +} + +static struct pci_driver amdxdna_pci_driver = { + .name = KBUILD_MODNAME, + .id_table = pci_ids, + .probe = amdxdna_probe, + .remove = amdxdna_remove, +}; + +module_pci_driver(amdxdna_pci_driver); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("XRT Team "); +MODULE_DESCRIPTION("amdxdna driver"); diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.h b/drivers/accel/amdxdna/amdxdna_pci_drv.h new file mode 100644 index 000000000000..2f1a1c2441f9 --- /dev/null +++ b/drivers/accel/amdxdna/amdxdna_pci_drv.h @@ -0,0 +1,76 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2022-2024, Advanced Micro Devices, Inc. + */ + +#ifndef _AMDXDNA_PCI_DRV_H_ +#define _AMDXDNA_PCI_DRV_H_ + +#define XDNA_INFO(xdna, fmt, args...) drm_info(&(xdna)->ddev, fmt, ##args) +#define XDNA_WARN(xdna, fmt, args...) drm_warn(&(xdna)->ddev, "%s: "fmt, __func__, ##args) +#define XDNA_ERR(xdna, fmt, args...) drm_err(&(xdna)->ddev, "%s: "fmt, __func__, ##args) +#define XDNA_DBG(xdna, fmt, args...) drm_dbg(&(xdna)->ddev, fmt, ##args) +#define XDNA_INFO_ONCE(xdna, fmt, args...) drm_info_once(&(xdna)->ddev, fmt, ##args) + +#define to_xdna_dev(drm_dev) \ + ((struct amdxdna_dev *)container_of(drm_dev, struct amdxdna_dev, ddev)) + +extern const struct drm_driver amdxdna_drm_drv; + +struct amdxdna_dev; + +/* + * struct amdxdna_dev_ops - Device hardware operation callbacks + */ +struct amdxdna_dev_ops { + int (*init)(struct amdxdna_dev *xdna); + void (*fini)(struct amdxdna_dev *xdna); +}; + +/* + * struct amdxdna_dev_info - Device hardware information + * Record device static information, like reg, mbox, PSP, SMU bar index + */ +struct amdxdna_dev_info { + int reg_bar; + int mbox_bar; + int sram_bar; + int psp_bar; + int smu_bar; + int device_type; + int first_col; + u32 dev_mem_buf_shift; + u64 dev_mem_base; + size_t dev_mem_size; + char *vbnv; + const struct amdxdna_dev_priv *dev_priv; + const struct amdxdna_dev_ops *ops; +}; + +struct amdxdna_dev { + struct drm_device ddev; + struct amdxdna_dev_hdl *dev_handle; + const struct amdxdna_dev_info *dev_info; + + struct mutex dev_lock; /* per device lock */ +}; + +/* + * struct amdxdna_device_id - PCI device info + */ +struct amdxdna_device_id { + unsigned short device; + u8 revision; + const struct amdxdna_dev_info *dev_info; +}; + +/* Add device info below */ +extern const struct amdxdna_dev_info dev_npu1_info; +extern const struct amdxdna_dev_info dev_npu2_info; +extern const struct amdxdna_dev_info dev_npu4_info; +extern const struct amdxdna_dev_info dev_npu5_info; + +int amdxdna_sysfs_init(struct amdxdna_dev *xdna); +void amdxdna_sysfs_fini(struct amdxdna_dev *xdna); + +#endif /* _AMDXDNA_PCI_DRV_H_ */ diff --git a/drivers/accel/amdxdna/amdxdna_sysfs.c b/drivers/accel/amdxdna/amdxdna_sysfs.c new file mode 100644 index 000000000000..5dd652fcf9d4 --- /dev/null +++ b/drivers/accel/amdxdna/amdxdna_sysfs.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2023-2024, Advanced Micro Devices, Inc. + */ + +#include +#include + +#include "amdxdna_pci_drv.h" + +static ssize_t vbnv_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct amdxdna_dev *xdna = dev_get_drvdata(dev); + + return sprintf(buf, "%s\n", xdna->dev_info->vbnv); +} +static DEVICE_ATTR_RO(vbnv); + +static ssize_t device_type_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct amdxdna_dev *xdna = dev_get_drvdata(dev); + + return sprintf(buf, "%d\n", xdna->dev_info->device_type); +} +static DEVICE_ATTR_RO(device_type); + +static struct attribute *amdxdna_attrs[] = { + &dev_attr_device_type.attr, + &dev_attr_vbnv.attr, + NULL, +}; + +static struct attribute_group amdxdna_attr_group = { + .attrs = amdxdna_attrs, +}; + +int amdxdna_sysfs_init(struct amdxdna_dev *xdna) +{ + int ret; + + ret = sysfs_create_group(&xdna->ddev.dev->kobj, &amdxdna_attr_group); + if (ret) + XDNA_ERR(xdna, "Create attr group failed"); + + return ret; +} + +void amdxdna_sysfs_fini(struct amdxdna_dev *xdna) +{ + sysfs_remove_group(&xdna->ddev.dev->kobj, &amdxdna_attr_group); +} diff --git a/drivers/accel/amdxdna/npu1_regs.c b/drivers/accel/amdxdna/npu1_regs.c new file mode 100644 index 000000000000..858b31a82888 --- /dev/null +++ b/drivers/accel/amdxdna/npu1_regs.c @@ -0,0 +1,99 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2023-2024, Advanced Micro Devices, Inc. + */ + +#include +#include +#include + +#include "aie2_pci.h" +#include "amdxdna_pci_drv.h" + +/* Address definition from NPU1 docs */ +#define MPNPU_PUB_SEC_INTR 0x3010090 +#define MPNPU_PUB_PWRMGMT_INTR 0x3010094 +#define MPNPU_PUB_SCRATCH2 0x30100A0 +#define MPNPU_PUB_SCRATCH3 0x30100A4 +#define MPNPU_PUB_SCRATCH4 0x30100A8 +#define MPNPU_PUB_SCRATCH5 0x30100AC +#define MPNPU_PUB_SCRATCH6 0x30100B0 +#define MPNPU_PUB_SCRATCH7 0x30100B4 +#define MPNPU_PUB_SCRATCH9 0x30100BC + +#define MPNPU_SRAM_X2I_MAILBOX_0 0x30A0000 +#define MPNPU_SRAM_X2I_MAILBOX_1 0x30A2000 +#define MPNPU_SRAM_I2X_MAILBOX_15 0x30BF000 + +#define MPNPU_APERTURE0_BASE 0x3000000 +#define MPNPU_APERTURE1_BASE 0x3080000 +#define MPNPU_APERTURE2_BASE 0x30C0000 + +/* PCIe BAR Index for NPU1 */ +#define NPU1_REG_BAR_INDEX 0 +#define NPU1_MBOX_BAR_INDEX 4 +#define NPU1_PSP_BAR_INDEX 0 +#define NPU1_SMU_BAR_INDEX 0 +#define NPU1_SRAM_BAR_INDEX 2 +/* Associated BARs and Apertures */ +#define NPU1_REG_BAR_BASE MPNPU_APERTURE0_BASE +#define NPU1_MBOX_BAR_BASE MPNPU_APERTURE2_BASE +#define NPU1_PSP_BAR_BASE MPNPU_APERTURE0_BASE +#define NPU1_SMU_BAR_BASE MPNPU_APERTURE0_BASE +#define NPU1_SRAM_BAR_BASE MPNPU_APERTURE1_BASE + +#define NPU1_RT_CFG_TYPE_PDI_LOAD 2 +#define NPU1_RT_CFG_VAL_PDI_LOAD_MGMT 0 +#define NPU1_RT_CFG_VAL_PDI_LOAD_APP 1 + +#define NPU1_MPNPUCLK_FREQ_MAX 600 +#define NPU1_HCLK_FREQ_MAX 1024 + +const struct amdxdna_dev_priv npu1_dev_priv = { + .fw_path = "amdnpu/1502_00/npu.sbin", + .protocol_major = 0x5, + .protocol_minor = 0x1, + .rt_config = {NPU1_RT_CFG_TYPE_PDI_LOAD, NPU1_RT_CFG_VAL_PDI_LOAD_APP}, + .col_align = COL_ALIGN_NONE, + .mbox_dev_addr = NPU1_MBOX_BAR_BASE, + .mbox_size = 0, /* Use BAR size */ + .sram_dev_addr = NPU1_SRAM_BAR_BASE, + .sram_offs = { + DEFINE_BAR_OFFSET(MBOX_CHANN_OFF, NPU1_SRAM, MPNPU_SRAM_X2I_MAILBOX_0), + DEFINE_BAR_OFFSET(FW_ALIVE_OFF, NPU1_SRAM, MPNPU_SRAM_I2X_MAILBOX_15), + }, + .psp_regs_off = { + DEFINE_BAR_OFFSET(PSP_CMD_REG, NPU1_PSP, MPNPU_PUB_SCRATCH2), + DEFINE_BAR_OFFSET(PSP_ARG0_REG, NPU1_PSP, MPNPU_PUB_SCRATCH3), + DEFINE_BAR_OFFSET(PSP_ARG1_REG, NPU1_PSP, MPNPU_PUB_SCRATCH4), + DEFINE_BAR_OFFSET(PSP_ARG2_REG, NPU1_PSP, MPNPU_PUB_SCRATCH9), + DEFINE_BAR_OFFSET(PSP_INTR_REG, NPU1_PSP, MPNPU_PUB_SEC_INTR), + DEFINE_BAR_OFFSET(PSP_STATUS_REG, NPU1_PSP, MPNPU_PUB_SCRATCH2), + DEFINE_BAR_OFFSET(PSP_RESP_REG, NPU1_PSP, MPNPU_PUB_SCRATCH3), + }, + .smu_regs_off = { + DEFINE_BAR_OFFSET(SMU_CMD_REG, NPU1_SMU, MPNPU_PUB_SCRATCH5), + DEFINE_BAR_OFFSET(SMU_ARG_REG, NPU1_SMU, MPNPU_PUB_SCRATCH7), + DEFINE_BAR_OFFSET(SMU_INTR_REG, NPU1_SMU, MPNPU_PUB_PWRMGMT_INTR), + DEFINE_BAR_OFFSET(SMU_RESP_REG, NPU1_SMU, MPNPU_PUB_SCRATCH6), + DEFINE_BAR_OFFSET(SMU_OUT_REG, NPU1_SMU, MPNPU_PUB_SCRATCH7), + }, + .smu_mpnpuclk_freq_max = NPU1_MPNPUCLK_FREQ_MAX, + .smu_hclk_freq_max = NPU1_HCLK_FREQ_MAX, +}; + +const struct amdxdna_dev_info dev_npu1_info = { + .reg_bar = NPU1_REG_BAR_INDEX, + .mbox_bar = NPU1_MBOX_BAR_INDEX, + .sram_bar = NPU1_SRAM_BAR_INDEX, + .psp_bar = NPU1_PSP_BAR_INDEX, + .smu_bar = NPU1_SMU_BAR_INDEX, + .first_col = 1, + .dev_mem_buf_shift = 15, /* 32 KiB aligned */ + .dev_mem_base = AIE2_DEVM_BASE, + .dev_mem_size = AIE2_DEVM_SIZE, + .vbnv = "RyzenAI-npu1", + .device_type = AMDXDNA_DEV_TYPE_KMQ, + .dev_priv = &npu1_dev_priv, + .ops = &aie2_ops, +}; diff --git a/drivers/accel/amdxdna/npu2_regs.c b/drivers/accel/amdxdna/npu2_regs.c new file mode 100644 index 000000000000..02b0f22c9f14 --- /dev/null +++ b/drivers/accel/amdxdna/npu2_regs.c @@ -0,0 +1,116 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2023-2024, Advanced Micro Devices, Inc. + */ + +#include +#include +#include + +#include "aie2_pci.h" +#include "amdxdna_pci_drv.h" + +/* NPU Public Registers on MpNPUAxiXbar (refer to Diag npu_registers.h) */ +#define MPNPU_PUB_SEC_INTR 0x3010060 +#define MPNPU_PUB_PWRMGMT_INTR 0x3010064 +#define MPNPU_PUB_SCRATCH0 0x301006C +#define MPNPU_PUB_SCRATCH1 0x3010070 +#define MPNPU_PUB_SCRATCH2 0x3010074 +#define MPNPU_PUB_SCRATCH3 0x3010078 +#define MPNPU_PUB_SCRATCH4 0x301007C +#define MPNPU_PUB_SCRATCH5 0x3010080 +#define MPNPU_PUB_SCRATCH6 0x3010084 +#define MPNPU_PUB_SCRATCH7 0x3010088 +#define MPNPU_PUB_SCRATCH8 0x301008C +#define MPNPU_PUB_SCRATCH9 0x3010090 +#define MPNPU_PUB_SCRATCH10 0x3010094 +#define MPNPU_PUB_SCRATCH11 0x3010098 +#define MPNPU_PUB_SCRATCH12 0x301009C +#define MPNPU_PUB_SCRATCH13 0x30100A0 +#define MPNPU_PUB_SCRATCH14 0x30100A4 +#define MPNPU_PUB_SCRATCH15 0x30100A8 +#define MP0_C2PMSG_73 0x3810A24 +#define MP0_C2PMSG_123 0x3810AEC + +#define MP1_C2PMSG_0 0x3B10900 +#define MP1_C2PMSG_60 0x3B109F0 +#define MP1_C2PMSG_61 0x3B109F4 + +#define MPNPU_SRAM_X2I_MAILBOX_0 0x3600000 +#define MPNPU_SRAM_X2I_MAILBOX_15 0x361E000 +#define MPNPU_SRAM_X2I_MAILBOX_31 0x363E000 +#define MPNPU_SRAM_I2X_MAILBOX_31 0x363F000 + +#define MMNPU_APERTURE0_BASE 0x3000000 +#define MMNPU_APERTURE1_BASE 0x3600000 +#define MMNPU_APERTURE3_BASE 0x3810000 +#define MMNPU_APERTURE4_BASE 0x3B10000 + +/* PCIe BAR Index for NPU2 */ +#define NPU2_REG_BAR_INDEX 0 +#define NPU2_MBOX_BAR_INDEX 0 +#define NPU2_PSP_BAR_INDEX 4 +#define NPU2_SMU_BAR_INDEX 5 +#define NPU2_SRAM_BAR_INDEX 2 +/* Associated BARs and Apertures */ +#define NPU2_REG_BAR_BASE MMNPU_APERTURE0_BASE +#define NPU2_MBOX_BAR_BASE MMNPU_APERTURE0_BASE +#define NPU2_PSP_BAR_BASE MMNPU_APERTURE3_BASE +#define NPU2_SMU_BAR_BASE MMNPU_APERTURE4_BASE +#define NPU2_SRAM_BAR_BASE MMNPU_APERTURE1_BASE + +#define NPU2_RT_CFG_TYPE_PDI_LOAD 5 +#define NPU2_RT_CFG_VAL_PDI_LOAD_MGMT 0 +#define NPU2_RT_CFG_VAL_PDI_LOAD_APP 1 + +#define NPU2_MPNPUCLK_FREQ_MAX 1267 +#define NPU2_HCLK_FREQ_MAX 1800 + +const struct amdxdna_dev_priv npu2_dev_priv = { + .fw_path = "amdnpu/17f0_00/npu.sbin", + .protocol_major = 0x6, + .protocol_minor = 0x1, + .rt_config = {NPU2_RT_CFG_TYPE_PDI_LOAD, NPU2_RT_CFG_VAL_PDI_LOAD_APP}, + .col_align = COL_ALIGN_NATURE, + .mbox_dev_addr = NPU2_MBOX_BAR_BASE, + .mbox_size = 0, /* Use BAR size */ + .sram_dev_addr = NPU2_SRAM_BAR_BASE, + .sram_offs = { + DEFINE_BAR_OFFSET(MBOX_CHANN_OFF, NPU2_SRAM, MPNPU_SRAM_X2I_MAILBOX_0), + DEFINE_BAR_OFFSET(FW_ALIVE_OFF, NPU2_SRAM, MPNPU_SRAM_X2I_MAILBOX_15), + }, + .psp_regs_off = { + DEFINE_BAR_OFFSET(PSP_CMD_REG, NPU2_PSP, MP0_C2PMSG_123), + DEFINE_BAR_OFFSET(PSP_ARG0_REG, NPU2_REG, MPNPU_PUB_SCRATCH3), + DEFINE_BAR_OFFSET(PSP_ARG1_REG, NPU2_REG, MPNPU_PUB_SCRATCH4), + DEFINE_BAR_OFFSET(PSP_ARG2_REG, NPU2_REG, MPNPU_PUB_SCRATCH9), + DEFINE_BAR_OFFSET(PSP_INTR_REG, NPU2_PSP, MP0_C2PMSG_73), + DEFINE_BAR_OFFSET(PSP_STATUS_REG, NPU2_PSP, MP0_C2PMSG_123), + DEFINE_BAR_OFFSET(PSP_RESP_REG, NPU2_REG, MPNPU_PUB_SCRATCH3), + }, + .smu_regs_off = { + DEFINE_BAR_OFFSET(SMU_CMD_REG, NPU2_SMU, MP1_C2PMSG_0), + DEFINE_BAR_OFFSET(SMU_ARG_REG, NPU2_SMU, MP1_C2PMSG_60), + DEFINE_BAR_OFFSET(SMU_INTR_REG, NPU2_SMU, MMNPU_APERTURE4_BASE), + DEFINE_BAR_OFFSET(SMU_RESP_REG, NPU2_SMU, MP1_C2PMSG_61), + DEFINE_BAR_OFFSET(SMU_OUT_REG, NPU2_SMU, MP1_C2PMSG_60), + }, + .smu_mpnpuclk_freq_max = NPU2_MPNPUCLK_FREQ_MAX, + .smu_hclk_freq_max = NPU2_HCLK_FREQ_MAX, +}; + +const struct amdxdna_dev_info dev_npu2_info = { + .reg_bar = NPU2_REG_BAR_INDEX, + .mbox_bar = NPU2_MBOX_BAR_INDEX, + .sram_bar = NPU2_SRAM_BAR_INDEX, + .psp_bar = NPU2_PSP_BAR_INDEX, + .smu_bar = NPU2_SMU_BAR_INDEX, + .first_col = 0, + .dev_mem_buf_shift = 15, /* 32 KiB aligned */ + .dev_mem_base = AIE2_DEVM_BASE, + .dev_mem_size = AIE2_DEVM_SIZE, + .vbnv = "RyzenAI-npu2", + .device_type = AMDXDNA_DEV_TYPE_KMQ, + .dev_priv = &npu2_dev_priv, + .ops = &aie2_ops, /* NPU2 can share NPU1's callback */ +}; diff --git a/drivers/accel/amdxdna/npu4_regs.c b/drivers/accel/amdxdna/npu4_regs.c new file mode 100644 index 000000000000..ca5ca5a6c751 --- /dev/null +++ b/drivers/accel/amdxdna/npu4_regs.c @@ -0,0 +1,116 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2023-2024, Advanced Micro Devices, Inc. + */ + +#include +#include +#include + +#include "aie2_pci.h" +#include "amdxdna_pci_drv.h" + +/* NPU Public Registers on MpNPUAxiXbar (refer to Diag npu_registers.h) */ +#define MPNPU_PUB_SEC_INTR 0x3010060 +#define MPNPU_PUB_PWRMGMT_INTR 0x3010064 +#define MPNPU_PUB_SCRATCH0 0x301006C +#define MPNPU_PUB_SCRATCH1 0x3010070 +#define MPNPU_PUB_SCRATCH2 0x3010074 +#define MPNPU_PUB_SCRATCH3 0x3010078 +#define MPNPU_PUB_SCRATCH4 0x301007C +#define MPNPU_PUB_SCRATCH5 0x3010080 +#define MPNPU_PUB_SCRATCH6 0x3010084 +#define MPNPU_PUB_SCRATCH7 0x3010088 +#define MPNPU_PUB_SCRATCH8 0x301008C +#define MPNPU_PUB_SCRATCH9 0x3010090 +#define MPNPU_PUB_SCRATCH10 0x3010094 +#define MPNPU_PUB_SCRATCH11 0x3010098 +#define MPNPU_PUB_SCRATCH12 0x301009C +#define MPNPU_PUB_SCRATCH13 0x30100A0 +#define MPNPU_PUB_SCRATCH14 0x30100A4 +#define MPNPU_PUB_SCRATCH15 0x30100A8 +#define MP0_C2PMSG_73 0x3810A24 +#define MP0_C2PMSG_123 0x3810AEC + +#define MP1_C2PMSG_0 0x3B10900 +#define MP1_C2PMSG_60 0x3B109F0 +#define MP1_C2PMSG_61 0x3B109F4 + +#define MPNPU_SRAM_X2I_MAILBOX_0 0x3600000 +#define MPNPU_SRAM_X2I_MAILBOX_15 0x361E000 +#define MPNPU_SRAM_X2I_MAILBOX_31 0x363E000 +#define MPNPU_SRAM_I2X_MAILBOX_31 0x363F000 + +#define MMNPU_APERTURE0_BASE 0x3000000 +#define MMNPU_APERTURE1_BASE 0x3600000 +#define MMNPU_APERTURE3_BASE 0x3810000 +#define MMNPU_APERTURE4_BASE 0x3B10000 + +/* PCIe BAR Index for NPU4 */ +#define NPU4_REG_BAR_INDEX 0 +#define NPU4_MBOX_BAR_INDEX 0 +#define NPU4_PSP_BAR_INDEX 4 +#define NPU4_SMU_BAR_INDEX 5 +#define NPU4_SRAM_BAR_INDEX 2 +/* Associated BARs and Apertures */ +#define NPU4_REG_BAR_BASE MMNPU_APERTURE0_BASE +#define NPU4_MBOX_BAR_BASE MMNPU_APERTURE0_BASE +#define NPU4_PSP_BAR_BASE MMNPU_APERTURE3_BASE +#define NPU4_SMU_BAR_BASE MMNPU_APERTURE4_BASE +#define NPU4_SRAM_BAR_BASE MMNPU_APERTURE1_BASE + +#define NPU4_RT_CFG_TYPE_PDI_LOAD 5 +#define NPU4_RT_CFG_VAL_PDI_LOAD_MGMT 0 +#define NPU4_RT_CFG_VAL_PDI_LOAD_APP 1 + +#define NPU4_MPNPUCLK_FREQ_MAX 1267 +#define NPU4_HCLK_FREQ_MAX 1800 + +const struct amdxdna_dev_priv npu4_dev_priv = { + .fw_path = "amdnpu/17f0_10/npu.sbin", + .protocol_major = 0x6, + .protocol_minor = 0x1, + .rt_config = {NPU4_RT_CFG_TYPE_PDI_LOAD, NPU4_RT_CFG_VAL_PDI_LOAD_APP}, + .col_align = COL_ALIGN_NATURE, + .mbox_dev_addr = NPU4_MBOX_BAR_BASE, + .mbox_size = 0, /* Use BAR size */ + .sram_dev_addr = NPU4_SRAM_BAR_BASE, + .sram_offs = { + DEFINE_BAR_OFFSET(MBOX_CHANN_OFF, NPU4_SRAM, MPNPU_SRAM_X2I_MAILBOX_0), + DEFINE_BAR_OFFSET(FW_ALIVE_OFF, NPU4_SRAM, MPNPU_SRAM_X2I_MAILBOX_15), + }, + .psp_regs_off = { + DEFINE_BAR_OFFSET(PSP_CMD_REG, NPU4_PSP, MP0_C2PMSG_123), + DEFINE_BAR_OFFSET(PSP_ARG0_REG, NPU4_REG, MPNPU_PUB_SCRATCH3), + DEFINE_BAR_OFFSET(PSP_ARG1_REG, NPU4_REG, MPNPU_PUB_SCRATCH4), + DEFINE_BAR_OFFSET(PSP_ARG2_REG, NPU4_REG, MPNPU_PUB_SCRATCH9), + DEFINE_BAR_OFFSET(PSP_INTR_REG, NPU4_PSP, MP0_C2PMSG_73), + DEFINE_BAR_OFFSET(PSP_STATUS_REG, NPU4_PSP, MP0_C2PMSG_123), + DEFINE_BAR_OFFSET(PSP_RESP_REG, NPU4_REG, MPNPU_PUB_SCRATCH3), + }, + .smu_regs_off = { + DEFINE_BAR_OFFSET(SMU_CMD_REG, NPU4_SMU, MP1_C2PMSG_0), + DEFINE_BAR_OFFSET(SMU_ARG_REG, NPU4_SMU, MP1_C2PMSG_60), + DEFINE_BAR_OFFSET(SMU_INTR_REG, NPU4_SMU, MMNPU_APERTURE4_BASE), + DEFINE_BAR_OFFSET(SMU_RESP_REG, NPU4_SMU, MP1_C2PMSG_61), + DEFINE_BAR_OFFSET(SMU_OUT_REG, NPU4_SMU, MP1_C2PMSG_60), + }, + .smu_mpnpuclk_freq_max = NPU4_MPNPUCLK_FREQ_MAX, + .smu_hclk_freq_max = NPU4_HCLK_FREQ_MAX, +}; + +const struct amdxdna_dev_info dev_npu4_info = { + .reg_bar = NPU4_REG_BAR_INDEX, + .mbox_bar = NPU4_MBOX_BAR_INDEX, + .sram_bar = NPU4_SRAM_BAR_INDEX, + .psp_bar = NPU4_PSP_BAR_INDEX, + .smu_bar = NPU4_SMU_BAR_INDEX, + .first_col = 0, + .dev_mem_buf_shift = 15, /* 32 KiB aligned */ + .dev_mem_base = AIE2_DEVM_BASE, + .dev_mem_size = AIE2_DEVM_SIZE, + .vbnv = "RyzenAI-npu4", + .device_type = AMDXDNA_DEV_TYPE_KMQ, + .dev_priv = &npu4_dev_priv, + .ops = &aie2_ops, /* NPU4 can share NPU1's callback */ +}; diff --git a/drivers/accel/amdxdna/npu5_regs.c b/drivers/accel/amdxdna/npu5_regs.c new file mode 100644 index 000000000000..07fddcbb86ec --- /dev/null +++ b/drivers/accel/amdxdna/npu5_regs.c @@ -0,0 +1,116 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024, Advanced Micro Devices, Inc. + */ + +#include +#include +#include + +#include "aie2_pci.h" +#include "amdxdna_pci_drv.h" + +/* NPU Public Registers on MpNPUAxiXbar (refer to Diag npu_registers.h) */ +#define MPNPU_PUB_SEC_INTR 0x3010060 +#define MPNPU_PUB_PWRMGMT_INTR 0x3010064 +#define MPNPU_PUB_SCRATCH0 0x301006C +#define MPNPU_PUB_SCRATCH1 0x3010070 +#define MPNPU_PUB_SCRATCH2 0x3010074 +#define MPNPU_PUB_SCRATCH3 0x3010078 +#define MPNPU_PUB_SCRATCH4 0x301007C +#define MPNPU_PUB_SCRATCH5 0x3010080 +#define MPNPU_PUB_SCRATCH6 0x3010084 +#define MPNPU_PUB_SCRATCH7 0x3010088 +#define MPNPU_PUB_SCRATCH8 0x301008C +#define MPNPU_PUB_SCRATCH9 0x3010090 +#define MPNPU_PUB_SCRATCH10 0x3010094 +#define MPNPU_PUB_SCRATCH11 0x3010098 +#define MPNPU_PUB_SCRATCH12 0x301009C +#define MPNPU_PUB_SCRATCH13 0x30100A0 +#define MPNPU_PUB_SCRATCH14 0x30100A4 +#define MPNPU_PUB_SCRATCH15 0x30100A8 +#define MP0_C2PMSG_73 0x3810A24 +#define MP0_C2PMSG_123 0x3810AEC + +#define MP1_C2PMSG_0 0x3B10900 +#define MP1_C2PMSG_60 0x3B109F0 +#define MP1_C2PMSG_61 0x3B109F4 + +#define MPNPU_SRAM_X2I_MAILBOX_0 0x3600000 +#define MPNPU_SRAM_X2I_MAILBOX_15 0x361E000 +#define MPNPU_SRAM_X2I_MAILBOX_31 0x363E000 +#define MPNPU_SRAM_I2X_MAILBOX_31 0x363F000 + +#define MMNPU_APERTURE0_BASE 0x3000000 +#define MMNPU_APERTURE1_BASE 0x3600000 +#define MMNPU_APERTURE3_BASE 0x3810000 +#define MMNPU_APERTURE4_BASE 0x3B10000 + +/* PCIe BAR Index for NPU5 */ +#define NPU5_REG_BAR_INDEX 0 +#define NPU5_MBOX_BAR_INDEX 0 +#define NPU5_PSP_BAR_INDEX 4 +#define NPU5_SMU_BAR_INDEX 5 +#define NPU5_SRAM_BAR_INDEX 2 +/* Associated BARs and Apertures */ +#define NPU5_REG_BAR_BASE MMNPU_APERTURE0_BASE +#define NPU5_MBOX_BAR_BASE MMNPU_APERTURE0_BASE +#define NPU5_PSP_BAR_BASE MMNPU_APERTURE3_BASE +#define NPU5_SMU_BAR_BASE MMNPU_APERTURE4_BASE +#define NPU5_SRAM_BAR_BASE MMNPU_APERTURE1_BASE + +#define NPU5_RT_CFG_TYPE_PDI_LOAD 5 +#define NPU5_RT_CFG_VAL_PDI_LOAD_MGMT 0 +#define NPU5_RT_CFG_VAL_PDI_LOAD_APP 1 + +#define NPU5_MPNPUCLK_FREQ_MAX 1267 +#define NPU5_HCLK_FREQ_MAX 1800 + +const struct amdxdna_dev_priv npu5_dev_priv = { + .fw_path = "amdnpu/17f0_11/npu.sbin", + .protocol_major = 0x6, + .protocol_minor = 0x1, + .rt_config = {NPU5_RT_CFG_TYPE_PDI_LOAD, NPU5_RT_CFG_VAL_PDI_LOAD_APP}, + .col_align = COL_ALIGN_NATURE, + .mbox_dev_addr = NPU5_MBOX_BAR_BASE, + .mbox_size = 0, /* Use BAR size */ + .sram_dev_addr = NPU5_SRAM_BAR_BASE, + .sram_offs = { + DEFINE_BAR_OFFSET(MBOX_CHANN_OFF, NPU5_SRAM, MPNPU_SRAM_X2I_MAILBOX_0), + DEFINE_BAR_OFFSET(FW_ALIVE_OFF, NPU5_SRAM, MPNPU_SRAM_X2I_MAILBOX_15), + }, + .psp_regs_off = { + DEFINE_BAR_OFFSET(PSP_CMD_REG, NPU5_PSP, MP0_C2PMSG_123), + DEFINE_BAR_OFFSET(PSP_ARG0_REG, NPU5_REG, MPNPU_PUB_SCRATCH3), + DEFINE_BAR_OFFSET(PSP_ARG1_REG, NPU5_REG, MPNPU_PUB_SCRATCH4), + DEFINE_BAR_OFFSET(PSP_ARG2_REG, NPU5_REG, MPNPU_PUB_SCRATCH9), + DEFINE_BAR_OFFSET(PSP_INTR_REG, NPU5_PSP, MP0_C2PMSG_73), + DEFINE_BAR_OFFSET(PSP_STATUS_REG, NPU5_PSP, MP0_C2PMSG_123), + DEFINE_BAR_OFFSET(PSP_RESP_REG, NPU5_REG, MPNPU_PUB_SCRATCH3), + }, + .smu_regs_off = { + DEFINE_BAR_OFFSET(SMU_CMD_REG, NPU5_SMU, MP1_C2PMSG_0), + DEFINE_BAR_OFFSET(SMU_ARG_REG, NPU5_SMU, MP1_C2PMSG_60), + DEFINE_BAR_OFFSET(SMU_INTR_REG, NPU5_SMU, MMNPU_APERTURE4_BASE), + DEFINE_BAR_OFFSET(SMU_RESP_REG, NPU5_SMU, MP1_C2PMSG_61), + DEFINE_BAR_OFFSET(SMU_OUT_REG, NPU5_SMU, MP1_C2PMSG_60), + }, + .smu_mpnpuclk_freq_max = NPU5_MPNPUCLK_FREQ_MAX, + .smu_hclk_freq_max = NPU5_HCLK_FREQ_MAX, +}; + +const struct amdxdna_dev_info dev_npu5_info = { + .reg_bar = NPU5_REG_BAR_INDEX, + .mbox_bar = NPU5_MBOX_BAR_INDEX, + .sram_bar = NPU5_SRAM_BAR_INDEX, + .psp_bar = NPU5_PSP_BAR_INDEX, + .smu_bar = NPU5_SMU_BAR_INDEX, + .first_col = 0, + .dev_mem_buf_shift = 15, /* 32 KiB aligned */ + .dev_mem_base = AIE2_DEVM_BASE, + .dev_mem_size = AIE2_DEVM_SIZE, + .vbnv = "RyzenAI-npu5", + .device_type = AMDXDNA_DEV_TYPE_KMQ, + .dev_priv = &npu5_dev_priv, + .ops = &aie2_ops, +}; diff --git a/include/uapi/drm/amdxdna_accel.h b/include/uapi/drm/amdxdna_accel.h new file mode 100644 index 000000000000..6d97e8e90cf6 --- /dev/null +++ b/include/uapi/drm/amdxdna_accel.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Copyright (C) 2022-2024, Advanced Micro Devices, Inc. + */ + +#ifndef _UAPI_AMDXDNA_ACCEL_H_ +#define _UAPI_AMDXDNA_ACCEL_H_ + +#include "drm.h" + +#if defined(__cplusplus) +extern "C" { +#endif + +enum amdxdna_device_type { + AMDXDNA_DEV_TYPE_UNKNOWN = -1, + AMDXDNA_DEV_TYPE_KMQ, +}; + +#if defined(__cplusplus) +} /* extern c end */ +#endif + +#endif /* _UAPI_AMDXDNA_ACCEL_H_ */ -- cgit v1.2.3 From b87f920b934426a24d54613f12ed67c03ae05024 Mon Sep 17 00:00:00 2001 From: Lizhi Hou Date: Mon, 18 Nov 2024 09:29:35 -0800 Subject: accel/amdxdna: Support hardware mailbox The hardware mailboxes are used by the driver to submit requests to firmware and receive the completion notices from hardware. Initially, a management mailbox channel is up and running. The driver may request firmware to create/destroy more channels dynamically through management channel. Add driver internal mailbox interfaces. - create/destroy a mailbox channel instance - send a message to the firmware through a specific channel - wait for a notification from the specific channel Co-developed-by: George Yang Signed-off-by: George Yang Co-developed-by: Min Ma Signed-off-by: Min Ma Reviewed-by: Jeffrey Hugo Signed-off-by: Lizhi Hou Signed-off-by: Jeffrey Hugo Link: https://patchwork.freedesktop.org/patch/msgid/20241118172942.2014541-4-lizhi.hou@amd.com --- MAINTAINERS | 1 + drivers/accel/amdxdna/Makefile | 3 + drivers/accel/amdxdna/aie2_message.c | 194 +++++++++ drivers/accel/amdxdna/aie2_msg_priv.h | 370 ++++++++++++++++ drivers/accel/amdxdna/aie2_pci.c | 256 ++++++++++- drivers/accel/amdxdna/aie2_pci.h | 62 +++ drivers/accel/amdxdna/aie2_psp.c | 2 + drivers/accel/amdxdna/amdxdna_mailbox.c | 576 +++++++++++++++++++++++++ drivers/accel/amdxdna/amdxdna_mailbox.h | 124 ++++++ drivers/accel/amdxdna/amdxdna_mailbox_helper.c | 56 +++ drivers/accel/amdxdna/amdxdna_mailbox_helper.h | 42 ++ drivers/accel/amdxdna/amdxdna_pci_drv.h | 8 + drivers/accel/amdxdna/amdxdna_sysfs.c | 11 + drivers/accel/amdxdna/npu1_regs.c | 1 + drivers/accel/amdxdna/npu2_regs.c | 1 + drivers/accel/amdxdna/npu4_regs.c | 1 + drivers/accel/amdxdna/npu5_regs.c | 1 + include/trace/events/amdxdna.h | 60 +++ 18 files changed, 1768 insertions(+), 1 deletion(-) create mode 100644 drivers/accel/amdxdna/aie2_message.c create mode 100644 drivers/accel/amdxdna/aie2_msg_priv.h create mode 100644 drivers/accel/amdxdna/amdxdna_mailbox.c create mode 100644 drivers/accel/amdxdna/amdxdna_mailbox.h create mode 100644 drivers/accel/amdxdna/amdxdna_mailbox_helper.c create mode 100644 drivers/accel/amdxdna/amdxdna_mailbox_helper.h create mode 100644 include/trace/events/amdxdna.h (limited to 'include') diff --git a/MAINTAINERS b/MAINTAINERS index cde77eb0bf1e..0ddb471f8601 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1186,6 +1186,7 @@ S: Supported T: git https://gitlab.freedesktop.org/drm/misc/kernel.git F: Documentation/accel/amdxdna/ F: drivers/accel/amdxdna/ +F: include/trace/events/amdxdna.h F: include/uapi/drm/amdxdna_accel.h AMD XGBE DRIVER diff --git a/drivers/accel/amdxdna/Makefile b/drivers/accel/amdxdna/Makefile index 1dee0cba8390..1b4e78b43b44 100644 --- a/drivers/accel/amdxdna/Makefile +++ b/drivers/accel/amdxdna/Makefile @@ -1,9 +1,12 @@ # SPDX-License-Identifier: GPL-2.0-only amdxdna-y := \ + aie2_message.o \ aie2_pci.o \ aie2_psp.o \ aie2_smu.o \ + amdxdna_mailbox.o \ + amdxdna_mailbox_helper.o \ amdxdna_pci_drv.o \ amdxdna_sysfs.o \ npu1_regs.o \ diff --git a/drivers/accel/amdxdna/aie2_message.c b/drivers/accel/amdxdna/aie2_message.c new file mode 100644 index 000000000000..cbf8ee54c6c2 --- /dev/null +++ b/drivers/accel/amdxdna/aie2_message.c @@ -0,0 +1,194 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2023-2024, Advanced Micro Devices, Inc. + */ + +#include +#include +#include +#include + +#include "aie2_msg_priv.h" +#include "aie2_pci.h" +#include "amdxdna_mailbox.h" +#include "amdxdna_mailbox_helper.h" +#include "amdxdna_pci_drv.h" + +#define DECLARE_AIE2_MSG(name, op) \ + DECLARE_XDNA_MSG_COMMON(name, op, MAX_AIE2_STATUS_CODE) + +static int aie2_send_mgmt_msg_wait(struct amdxdna_dev_hdl *ndev, + struct xdna_mailbox_msg *msg) +{ + struct amdxdna_dev *xdna = ndev->xdna; + struct xdna_notify *hdl = msg->handle; + int ret; + + if (!ndev->mgmt_chann) + return -ENODEV; + + drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock)); + ret = xdna_send_msg_wait(xdna, ndev->mgmt_chann, msg); + if (ret == -ETIME) { + xdna_mailbox_stop_channel(ndev->mgmt_chann); + xdna_mailbox_destroy_channel(ndev->mgmt_chann); + ndev->mgmt_chann = NULL; + } + + if (!ret && *hdl->data != AIE2_STATUS_SUCCESS) { + XDNA_ERR(xdna, "command opcode 0x%x failed, status 0x%x", + msg->opcode, *hdl->data); + ret = -EINVAL; + } + + return ret; +} + +int aie2_suspend_fw(struct amdxdna_dev_hdl *ndev) +{ + DECLARE_AIE2_MSG(suspend, MSG_OP_SUSPEND); + + return aie2_send_mgmt_msg_wait(ndev, &msg); +} + +int aie2_resume_fw(struct amdxdna_dev_hdl *ndev) +{ + DECLARE_AIE2_MSG(suspend, MSG_OP_RESUME); + + return aie2_send_mgmt_msg_wait(ndev, &msg); +} + +int aie2_set_runtime_cfg(struct amdxdna_dev_hdl *ndev, u32 type, u64 value) +{ + DECLARE_AIE2_MSG(set_runtime_cfg, MSG_OP_SET_RUNTIME_CONFIG); + + req.type = type; + req.value = value; + + return aie2_send_mgmt_msg_wait(ndev, &msg); +} + +int aie2_get_runtime_cfg(struct amdxdna_dev_hdl *ndev, u32 type, u64 *value) +{ + DECLARE_AIE2_MSG(get_runtime_cfg, MSG_OP_GET_RUNTIME_CONFIG); + int ret; + + req.type = type; + ret = aie2_send_mgmt_msg_wait(ndev, &msg); + if (ret) { + XDNA_ERR(ndev->xdna, "Failed to get runtime config, ret %d", ret); + return ret; + } + + *value = resp.value; + return 0; +} + +int aie2_check_protocol_version(struct amdxdna_dev_hdl *ndev) +{ + DECLARE_AIE2_MSG(protocol_version, MSG_OP_GET_PROTOCOL_VERSION); + struct amdxdna_dev *xdna = ndev->xdna; + int ret; + + ret = aie2_send_mgmt_msg_wait(ndev, &msg); + if (ret) { + XDNA_ERR(xdna, "Failed to get protocol version, ret %d", ret); + return ret; + } + + if (resp.major != ndev->priv->protocol_major) { + XDNA_ERR(xdna, "Incompatible firmware protocol version major %d minor %d", + resp.major, resp.minor); + return -EINVAL; + } + + if (resp.minor < ndev->priv->protocol_minor) { + XDNA_ERR(xdna, "Firmware minor version smaller than supported"); + return -EINVAL; + } + + return 0; +} + +int aie2_assign_mgmt_pasid(struct amdxdna_dev_hdl *ndev, u16 pasid) +{ + DECLARE_AIE2_MSG(assign_mgmt_pasid, MSG_OP_ASSIGN_MGMT_PASID); + + req.pasid = pasid; + + return aie2_send_mgmt_msg_wait(ndev, &msg); +} + +int aie2_query_aie_version(struct amdxdna_dev_hdl *ndev, struct aie_version *version) +{ + DECLARE_AIE2_MSG(aie_version_info, MSG_OP_QUERY_AIE_VERSION); + struct amdxdna_dev *xdna = ndev->xdna; + int ret; + + ret = aie2_send_mgmt_msg_wait(ndev, &msg); + if (ret) + return ret; + + XDNA_DBG(xdna, "Query AIE version - major: %u minor: %u completed", + resp.major, resp.minor); + + version->major = resp.major; + version->minor = resp.minor; + + return 0; +} + +int aie2_query_aie_metadata(struct amdxdna_dev_hdl *ndev, struct aie_metadata *metadata) +{ + DECLARE_AIE2_MSG(aie_tile_info, MSG_OP_QUERY_AIE_TILE_INFO); + int ret; + + ret = aie2_send_mgmt_msg_wait(ndev, &msg); + if (ret) + return ret; + + metadata->size = resp.info.size; + metadata->cols = resp.info.cols; + metadata->rows = resp.info.rows; + + metadata->version.major = resp.info.major; + metadata->version.minor = resp.info.minor; + + metadata->core.row_count = resp.info.core_rows; + metadata->core.row_start = resp.info.core_row_start; + metadata->core.dma_channel_count = resp.info.core_dma_channels; + metadata->core.lock_count = resp.info.core_locks; + metadata->core.event_reg_count = resp.info.core_events; + + metadata->mem.row_count = resp.info.mem_rows; + metadata->mem.row_start = resp.info.mem_row_start; + metadata->mem.dma_channel_count = resp.info.mem_dma_channels; + metadata->mem.lock_count = resp.info.mem_locks; + metadata->mem.event_reg_count = resp.info.mem_events; + + metadata->shim.row_count = resp.info.shim_rows; + metadata->shim.row_start = resp.info.shim_row_start; + metadata->shim.dma_channel_count = resp.info.shim_dma_channels; + metadata->shim.lock_count = resp.info.shim_locks; + metadata->shim.event_reg_count = resp.info.shim_events; + + return 0; +} + +int aie2_query_firmware_version(struct amdxdna_dev_hdl *ndev, + struct amdxdna_fw_ver *fw_ver) +{ + DECLARE_AIE2_MSG(firmware_version, MSG_OP_GET_FIRMWARE_VERSION); + int ret; + + ret = aie2_send_mgmt_msg_wait(ndev, &msg); + if (ret) + return ret; + + fw_ver->major = resp.major; + fw_ver->minor = resp.minor; + fw_ver->sub = resp.sub; + fw_ver->build = resp.build; + + return 0; +} diff --git a/drivers/accel/amdxdna/aie2_msg_priv.h b/drivers/accel/amdxdna/aie2_msg_priv.h new file mode 100644 index 000000000000..4e02e744b470 --- /dev/null +++ b/drivers/accel/amdxdna/aie2_msg_priv.h @@ -0,0 +1,370 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2022-2024, Advanced Micro Devices, Inc. + */ + +#ifndef _AIE2_MSG_PRIV_H_ +#define _AIE2_MSG_PRIV_H_ + +enum aie2_msg_opcode { + MSG_OP_CREATE_CONTEXT = 0x2, + MSG_OP_DESTROY_CONTEXT = 0x3, + MSG_OP_SYNC_BO = 0x7, + MSG_OP_EXECUTE_BUFFER_CF = 0xC, + MSG_OP_QUERY_COL_STATUS = 0xD, + MSG_OP_QUERY_AIE_TILE_INFO = 0xE, + MSG_OP_QUERY_AIE_VERSION = 0xF, + MSG_OP_EXEC_DPU = 0x10, + MSG_OP_CONFIG_CU = 0x11, + MSG_OP_CHAIN_EXEC_BUFFER_CF = 0x12, + MSG_OP_CHAIN_EXEC_DPU = 0x13, + MSG_OP_MAX_XRT_OPCODE, + MSG_OP_SUSPEND = 0x101, + MSG_OP_RESUME = 0x102, + MSG_OP_ASSIGN_MGMT_PASID = 0x103, + MSG_OP_INVOKE_SELF_TEST = 0x104, + MSG_OP_MAP_HOST_BUFFER = 0x106, + MSG_OP_GET_FIRMWARE_VERSION = 0x108, + MSG_OP_SET_RUNTIME_CONFIG = 0x10A, + MSG_OP_GET_RUNTIME_CONFIG = 0x10B, + MSG_OP_REGISTER_ASYNC_EVENT_MSG = 0x10C, + MSG_OP_MAX_DRV_OPCODE, + MSG_OP_GET_PROTOCOL_VERSION = 0x301, + MSG_OP_MAX_OPCODE +}; + +enum aie2_msg_status { + AIE2_STATUS_SUCCESS = 0x0, + /* AIE Error codes */ + AIE2_STATUS_AIE_SATURATION_ERROR = 0x1000001, + AIE2_STATUS_AIE_FP_ERROR = 0x1000002, + AIE2_STATUS_AIE_STREAM_ERROR = 0x1000003, + AIE2_STATUS_AIE_ACCESS_ERROR = 0x1000004, + AIE2_STATUS_AIE_BUS_ERROR = 0x1000005, + AIE2_STATUS_AIE_INSTRUCTION_ERROR = 0x1000006, + AIE2_STATUS_AIE_ECC_ERROR = 0x1000007, + AIE2_STATUS_AIE_LOCK_ERROR = 0x1000008, + AIE2_STATUS_AIE_DMA_ERROR = 0x1000009, + AIE2_STATUS_AIE_MEM_PARITY_ERROR = 0x100000a, + AIE2_STATUS_AIE_PWR_CFG_ERROR = 0x100000b, + AIE2_STATUS_AIE_BACKTRACK_ERROR = 0x100000c, + AIE2_STATUS_MAX_AIE_STATUS_CODE, + /* MGMT ERT Error codes */ + AIE2_STATUS_MGMT_ERT_SELF_TEST_FAILURE = 0x2000001, + AIE2_STATUS_MGMT_ERT_HASH_MISMATCH, + AIE2_STATUS_MGMT_ERT_NOAVAIL, + AIE2_STATUS_MGMT_ERT_INVALID_PARAM, + AIE2_STATUS_MGMT_ERT_ENTER_SUSPEND_FAILURE, + AIE2_STATUS_MGMT_ERT_BUSY, + AIE2_STATUS_MGMT_ERT_APPLICATION_ACTIVE, + MAX_MGMT_ERT_STATUS_CODE, + /* APP ERT Error codes */ + AIE2_STATUS_APP_ERT_FIRST_ERROR = 0x3000001, + AIE2_STATUS_APP_INVALID_INSTR, + AIE2_STATUS_APP_LOAD_PDI_FAIL, + MAX_APP_ERT_STATUS_CODE, + /* NPU RTOS Error Codes */ + AIE2_STATUS_INVALID_INPUT_BUFFER = 0x4000001, + AIE2_STATUS_INVALID_COMMAND, + AIE2_STATUS_INVALID_PARAM, + AIE2_STATUS_INVALID_OPERATION = 0x4000006, + AIE2_STATUS_ASYNC_EVENT_MSGS_FULL, + AIE2_STATUS_MAX_RTOS_STATUS_CODE, + MAX_AIE2_STATUS_CODE +}; + +struct assign_mgmt_pasid_req { + __u16 pasid; + __u16 reserved; +} __packed; + +struct assign_mgmt_pasid_resp { + enum aie2_msg_status status; +} __packed; + +struct map_host_buffer_req { + __u32 context_id; + __u64 buf_addr; + __u64 buf_size; +} __packed; + +struct map_host_buffer_resp { + enum aie2_msg_status status; +} __packed; + +#define MAX_CQ_PAIRS 2 +struct cq_info { + __u32 head_addr; + __u32 tail_addr; + __u32 buf_addr; + __u32 buf_size; +}; + +struct cq_pair { + struct cq_info x2i_q; + struct cq_info i2x_q; +}; + +struct create_ctx_req { + __u32 aie_type; + __u8 start_col; + __u8 num_col; + __u16 reserved; + __u8 num_cq_pairs_requested; + __u8 reserved1; + __u16 pasid; + __u32 pad[2]; + __u32 sec_comm_target_type; + __u32 context_priority; +} __packed; + +struct create_ctx_resp { + enum aie2_msg_status status; + __u32 context_id; + __u16 msix_id; + __u8 num_cq_pairs_allocated; + __u8 reserved; + struct cq_pair cq_pair[MAX_CQ_PAIRS]; +} __packed; + +struct destroy_ctx_req { + __u32 context_id; +} __packed; + +struct destroy_ctx_resp { + enum aie2_msg_status status; +} __packed; + +struct execute_buffer_req { + __u32 cu_idx; + __u32 payload[19]; +} __packed; + +struct exec_dpu_req { + __u64 inst_buf_addr; + __u32 inst_size; + __u32 inst_prop_cnt; + __u32 cu_idx; + __u32 payload[35]; +} __packed; + +struct execute_buffer_resp { + enum aie2_msg_status status; +} __packed; + +struct aie_tile_info { + __u32 size; + __u16 major; + __u16 minor; + __u16 cols; + __u16 rows; + __u16 core_rows; + __u16 mem_rows; + __u16 shim_rows; + __u16 core_row_start; + __u16 mem_row_start; + __u16 shim_row_start; + __u16 core_dma_channels; + __u16 mem_dma_channels; + __u16 shim_dma_channels; + __u16 core_locks; + __u16 mem_locks; + __u16 shim_locks; + __u16 core_events; + __u16 mem_events; + __u16 shim_events; + __u16 reserved; +}; + +struct aie_tile_info_req { + __u32 reserved; +} __packed; + +struct aie_tile_info_resp { + enum aie2_msg_status status; + struct aie_tile_info info; +} __packed; + +struct aie_version_info_req { + __u32 reserved; +} __packed; + +struct aie_version_info_resp { + enum aie2_msg_status status; + __u16 major; + __u16 minor; +} __packed; + +struct aie_column_info_req { + __u64 dump_buff_addr; + __u32 dump_buff_size; + __u32 num_cols; + __u32 aie_bitmap; +} __packed; + +struct aie_column_info_resp { + enum aie2_msg_status status; + __u32 size; +} __packed; + +struct suspend_req { + __u32 place_holder; +} __packed; + +struct suspend_resp { + enum aie2_msg_status status; +} __packed; + +struct resume_req { + __u32 place_holder; +} __packed; + +struct resume_resp { + enum aie2_msg_status status; +} __packed; + +struct check_header_hash_req { + __u64 hash_high; + __u64 hash_low; +} __packed; + +struct check_header_hash_resp { + enum aie2_msg_status status; +} __packed; + +struct query_error_req { + __u64 buf_addr; + __u32 buf_size; + __u32 next_row; + __u32 next_column; + __u32 next_module; +} __packed; + +struct query_error_resp { + enum aie2_msg_status status; + __u32 num_err; + __u32 has_next_err; + __u32 next_row; + __u32 next_column; + __u32 next_module; +} __packed; + +struct protocol_version_req { + __u32 reserved; +} __packed; + +struct protocol_version_resp { + enum aie2_msg_status status; + __u32 major; + __u32 minor; +} __packed; + +struct firmware_version_req { + __u32 reserved; +} __packed; + +struct firmware_version_resp { + enum aie2_msg_status status; + __u32 major; + __u32 minor; + __u32 sub; + __u32 build; +} __packed; + +#define MAX_NUM_CUS 32 +#define AIE2_MSG_CFG_CU_PDI_ADDR GENMASK(16, 0) +#define AIE2_MSG_CFG_CU_FUNC GENMASK(24, 17) +struct config_cu_req { + __u32 num_cus; + __u32 cfgs[MAX_NUM_CUS]; +} __packed; + +struct config_cu_resp { + enum aie2_msg_status status; +} __packed; + +struct set_runtime_cfg_req { + __u32 type; + __u64 value; +} __packed; + +struct set_runtime_cfg_resp { + enum aie2_msg_status status; +} __packed; + +struct get_runtime_cfg_req { + __u32 type; +} __packed; + +struct get_runtime_cfg_resp { + enum aie2_msg_status status; + __u64 value; +} __packed; + +enum async_event_type { + ASYNC_EVENT_TYPE_AIE_ERROR, + ASYNC_EVENT_TYPE_EXCEPTION, + MAX_ASYNC_EVENT_TYPE +}; + +#define ASYNC_BUF_SIZE SZ_8K +struct async_event_msg_req { + __u64 buf_addr; + __u32 buf_size; +} __packed; + +struct async_event_msg_resp { + enum aie2_msg_status status; + enum async_event_type type; +} __packed; + +#define MAX_CHAIN_CMDBUF_SIZE SZ_4K +#define slot_cf_has_space(offset, payload_size) \ + (MAX_CHAIN_CMDBUF_SIZE - ((offset) + (payload_size)) > \ + offsetof(struct cmd_chain_slot_execbuf_cf, args[0])) +struct cmd_chain_slot_execbuf_cf { + __u32 cu_idx; + __u32 arg_cnt; + __u32 args[] __counted_by(arg_cnt); +}; + +#define slot_dpu_has_space(offset, payload_size) \ + (MAX_CHAIN_CMDBUF_SIZE - ((offset) + (payload_size)) > \ + offsetof(struct cmd_chain_slot_dpu, args[0])) +struct cmd_chain_slot_dpu { + __u64 inst_buf_addr; + __u32 inst_size; + __u32 inst_prop_cnt; + __u32 cu_idx; + __u32 arg_cnt; +#define MAX_DPU_ARGS_SIZE (34 * sizeof(__u32)) + __u32 args[] __counted_by(arg_cnt); +}; + +struct cmd_chain_req { + __u64 buf_addr; + __u32 buf_size; + __u32 count; +} __packed; + +struct cmd_chain_resp { + enum aie2_msg_status status; + __u32 fail_cmd_idx; + enum aie2_msg_status fail_cmd_status; +} __packed; + +#define AIE2_MSG_SYNC_BO_SRC_TYPE GENMASK(3, 0) +#define AIE2_MSG_SYNC_BO_DST_TYPE GENMASK(7, 4) +struct sync_bo_req { + __u64 src_addr; + __u64 dst_addr; + __u32 size; +#define SYNC_BO_DEV_MEM 0 +#define SYNC_BO_HOST_MEM 2 + __u32 type; +} __packed; + +struct sync_bo_resp { + enum aie2_msg_status status; +} __packed; +#endif /* _AIE2_MSG_PRIV_H_ */ diff --git a/drivers/accel/amdxdna/aie2_pci.c b/drivers/accel/amdxdna/aie2_pci.c index 770931674abb..d4acee1cee31 100644 --- a/drivers/accel/amdxdna/aie2_pci.c +++ b/drivers/accel/amdxdna/aie2_pci.c @@ -9,16 +9,210 @@ #include #include #include +#include #include +#include "aie2_msg_priv.h" #include "aie2_pci.h" +#include "amdxdna_mailbox.h" #include "amdxdna_pci_drv.h" +/* + * The management mailbox channel is allocated by firmware. + * The related register and ring buffer information is on SRAM BAR. + * This struct is the register layout. + */ +struct mgmt_mbox_chann_info { + u32 x2i_tail; + u32 x2i_head; + u32 x2i_buf; + u32 x2i_buf_sz; + u32 i2x_tail; + u32 i2x_head; + u32 i2x_buf; + u32 i2x_buf_sz; +}; + +static void aie2_dump_chann_info_debug(struct amdxdna_dev_hdl *ndev) +{ + struct amdxdna_dev *xdna = ndev->xdna; + + XDNA_DBG(xdna, "i2x tail 0x%x", ndev->mgmt_i2x.mb_tail_ptr_reg); + XDNA_DBG(xdna, "i2x head 0x%x", ndev->mgmt_i2x.mb_head_ptr_reg); + XDNA_DBG(xdna, "i2x ringbuf 0x%x", ndev->mgmt_i2x.rb_start_addr); + XDNA_DBG(xdna, "i2x rsize 0x%x", ndev->mgmt_i2x.rb_size); + XDNA_DBG(xdna, "x2i tail 0x%x", ndev->mgmt_x2i.mb_tail_ptr_reg); + XDNA_DBG(xdna, "x2i head 0x%x", ndev->mgmt_x2i.mb_head_ptr_reg); + XDNA_DBG(xdna, "x2i ringbuf 0x%x", ndev->mgmt_x2i.rb_start_addr); + XDNA_DBG(xdna, "x2i rsize 0x%x", ndev->mgmt_x2i.rb_size); + XDNA_DBG(xdna, "x2i chann index 0x%x", ndev->mgmt_chan_idx); +} + +static int aie2_get_mgmt_chann_info(struct amdxdna_dev_hdl *ndev) +{ + struct mgmt_mbox_chann_info info_regs; + struct xdna_mailbox_chann_res *i2x; + struct xdna_mailbox_chann_res *x2i; + u32 addr, off; + u32 *reg; + int ret; + int i; + + /* + * Once firmware is alive, it will write management channel + * information in SRAM BAR and write the address of that information + * at FW_ALIVE_OFF offset in SRMA BAR. + * + * Read a non-zero value from FW_ALIVE_OFF implies that firmware + * is alive. + */ + ret = readx_poll_timeout(readl, SRAM_GET_ADDR(ndev, FW_ALIVE_OFF), + addr, addr, AIE2_INTERVAL, AIE2_TIMEOUT); + if (ret || !addr) + return -ETIME; + + off = AIE2_SRAM_OFF(ndev, addr); + reg = (u32 *)&info_regs; + for (i = 0; i < sizeof(info_regs) / sizeof(u32); i++) + reg[i] = readl(ndev->sram_base + off + i * sizeof(u32)); + + i2x = &ndev->mgmt_i2x; + x2i = &ndev->mgmt_x2i; + + i2x->mb_head_ptr_reg = AIE2_MBOX_OFF(ndev, info_regs.i2x_head); + i2x->mb_tail_ptr_reg = AIE2_MBOX_OFF(ndev, info_regs.i2x_tail); + i2x->rb_start_addr = AIE2_SRAM_OFF(ndev, info_regs.i2x_buf); + i2x->rb_size = info_regs.i2x_buf_sz; + + x2i->mb_head_ptr_reg = AIE2_MBOX_OFF(ndev, info_regs.x2i_head); + x2i->mb_tail_ptr_reg = AIE2_MBOX_OFF(ndev, info_regs.x2i_tail); + x2i->rb_start_addr = AIE2_SRAM_OFF(ndev, info_regs.x2i_buf); + x2i->rb_size = info_regs.x2i_buf_sz; + ndev->mgmt_chan_idx = CHANN_INDEX(ndev, x2i->rb_start_addr); + + aie2_dump_chann_info_debug(ndev); + + /* Must clear address at FW_ALIVE_OFF */ + writel(0, SRAM_GET_ADDR(ndev, FW_ALIVE_OFF)); + + return 0; +} + +static int aie2_runtime_cfg(struct amdxdna_dev_hdl *ndev) +{ + const struct rt_config *cfg = &ndev->priv->rt_config; + u64 value; + int ret; + + ret = aie2_set_runtime_cfg(ndev, cfg->type, cfg->value); + if (ret) { + XDNA_ERR(ndev->xdna, "Set runtime type %d value %d failed", + cfg->type, cfg->value); + return ret; + } + + ret = aie2_get_runtime_cfg(ndev, cfg->type, &value); + if (ret) { + XDNA_ERR(ndev->xdna, "Get runtime cfg failed"); + return ret; + } + + if (value != cfg->value) + return -EINVAL; + + return 0; +} + +static int aie2_xdna_reset(struct amdxdna_dev_hdl *ndev) +{ + int ret; + + ret = aie2_suspend_fw(ndev); + if (ret) { + XDNA_ERR(ndev->xdna, "Suspend firmware failed"); + return ret; + } + + ret = aie2_resume_fw(ndev); + if (ret) { + XDNA_ERR(ndev->xdna, "Resume firmware failed"); + return ret; + } + + return 0; +} + +static int aie2_mgmt_fw_init(struct amdxdna_dev_hdl *ndev) +{ + int ret; + + ret = aie2_check_protocol_version(ndev); + if (ret) { + XDNA_ERR(ndev->xdna, "Check header hash failed"); + return ret; + } + + ret = aie2_runtime_cfg(ndev); + if (ret) { + XDNA_ERR(ndev->xdna, "Runtime config failed"); + return ret; + } + + ret = aie2_assign_mgmt_pasid(ndev, 0); + if (ret) { + XDNA_ERR(ndev->xdna, "Can not assign PASID"); + return ret; + } + + ret = aie2_xdna_reset(ndev); + if (ret) { + XDNA_ERR(ndev->xdna, "Reset firmware failed"); + return ret; + } + + return 0; +} + +static int aie2_mgmt_fw_query(struct amdxdna_dev_hdl *ndev) +{ + int ret; + + ret = aie2_query_firmware_version(ndev, &ndev->xdna->fw_ver); + if (ret) { + XDNA_ERR(ndev->xdna, "query firmware version failed"); + return ret; + } + + ret = aie2_query_aie_version(ndev, &ndev->version); + if (ret) { + XDNA_ERR(ndev->xdna, "Query AIE version failed"); + return ret; + } + + ret = aie2_query_aie_metadata(ndev, &ndev->metadata); + if (ret) { + XDNA_ERR(ndev->xdna, "Query AIE metadata failed"); + return ret; + } + + return 0; +} + +static void aie2_mgmt_fw_fini(struct amdxdna_dev_hdl *ndev) +{ + if (aie2_suspend_fw(ndev)) + XDNA_ERR(ndev->xdna, "Suspend_fw failed"); + XDNA_DBG(ndev->xdna, "Firmware suspended"); +} + static void aie2_hw_stop(struct amdxdna_dev *xdna) { struct pci_dev *pdev = to_pci_dev(xdna->ddev.dev); struct amdxdna_dev_hdl *ndev = xdna->dev_handle; + aie2_mgmt_fw_fini(ndev); + xdna_mailbox_stop_channel(ndev->mgmt_chann); + xdna_mailbox_destroy_channel(ndev->mgmt_chann); aie2_psp_stop(ndev->psp_hdl); aie2_smu_fini(ndev); pci_disable_device(pdev); @@ -28,7 +222,9 @@ static int aie2_hw_start(struct amdxdna_dev *xdna) { struct pci_dev *pdev = to_pci_dev(xdna->ddev.dev); struct amdxdna_dev_hdl *ndev = xdna->dev_handle; - int ret; + struct xdna_mailbox_res mbox_res; + u32 xdna_mailbox_intr_reg; + int mgmt_mb_irq, ret; ret = pci_enable_device(pdev); if (ret) { @@ -49,8 +245,56 @@ static int aie2_hw_start(struct amdxdna_dev *xdna) goto fini_smu; } + ret = aie2_get_mgmt_chann_info(ndev); + if (ret) { + XDNA_ERR(xdna, "firmware is not alive"); + goto stop_psp; + } + + mbox_res.ringbuf_base = (u64)ndev->sram_base; + mbox_res.ringbuf_size = pci_resource_len(pdev, xdna->dev_info->sram_bar); + mbox_res.mbox_base = (u64)ndev->mbox_base; + mbox_res.mbox_size = MBOX_SIZE(ndev); + mbox_res.name = "xdna_mailbox"; + ndev->mbox = xdnam_mailbox_create(&xdna->ddev, &mbox_res); + if (!ndev->mbox) { + XDNA_ERR(xdna, "failed to create mailbox device"); + ret = -ENODEV; + goto stop_psp; + } + + mgmt_mb_irq = pci_irq_vector(pdev, ndev->mgmt_chan_idx); + if (mgmt_mb_irq < 0) { + ret = mgmt_mb_irq; + XDNA_ERR(xdna, "failed to alloc irq vector, ret %d", ret); + goto stop_psp; + } + + xdna_mailbox_intr_reg = ndev->mgmt_i2x.mb_head_ptr_reg + 4; + ndev->mgmt_chann = xdna_mailbox_create_channel(ndev->mbox, + &ndev->mgmt_x2i, + &ndev->mgmt_i2x, + xdna_mailbox_intr_reg, + mgmt_mb_irq); + if (!ndev->mgmt_chann) { + XDNA_ERR(xdna, "failed to create management mailbox channel"); + ret = -EINVAL; + goto stop_psp; + } + + ret = aie2_mgmt_fw_init(ndev); + if (ret) { + XDNA_ERR(xdna, "initial mgmt firmware failed, ret %d", ret); + goto destroy_mgmt_chann; + } + return 0; +destroy_mgmt_chann: + xdna_mailbox_stop_channel(ndev->mgmt_chann); + xdna_mailbox_destroy_channel(ndev->mgmt_chann); +stop_psp: + aie2_psp_stop(ndev->psp_hdl); fini_smu: aie2_smu_fini(ndev); disable_dev: @@ -109,6 +353,7 @@ static int aie2_init(struct amdxdna_dev *xdna) ndev->sram_base = tbl[xdna->dev_info->sram_bar]; ndev->smu_base = tbl[xdna->dev_info->smu_bar]; + ndev->mbox_base = tbl[xdna->dev_info->mbox_bar]; ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); if (ret) { @@ -153,9 +398,18 @@ static int aie2_init(struct amdxdna_dev *xdna) goto disable_sva; } + ret = aie2_mgmt_fw_query(ndev); + if (ret) { + XDNA_ERR(xdna, "Query firmware failed, ret %d", ret); + goto stop_hw; + } + ndev->total_col = ndev->metadata.cols; + release_firmware(fw); return 0; +stop_hw: + aie2_hw_stop(xdna); disable_sva: iommu_dev_disable_feature(&pdev->dev, IOMMU_DEV_FEAT_SVA); free_irq: diff --git a/drivers/accel/amdxdna/aie2_pci.h b/drivers/accel/amdxdna/aie2_pci.h index 34f344b4b662..4c81d10a0998 100644 --- a/drivers/accel/amdxdna/aie2_pci.h +++ b/drivers/accel/amdxdna/aie2_pci.h @@ -6,6 +6,8 @@ #ifndef _AIE2_PCI_H_ #define _AIE2_PCI_H_ +#include "amdxdna_mailbox.h" + #define AIE2_INTERVAL 20000 /* us */ #define AIE2_TIMEOUT 1000000 /* us */ @@ -33,6 +35,17 @@ ((_ndev)->sram_base + SRAM_REG_OFF((_ndev), (idx))); \ }) +#define CHAN_SLOT_SZ SZ_8K +#define CHANN_INDEX(ndev, rbuf_off) \ + (((rbuf_off) - SRAM_REG_OFF((ndev), MBOX_CHANN_OFF)) / CHAN_SLOT_SZ) + +#define MBOX_SIZE(ndev) \ +({ \ + typeof(ndev) _ndev = (ndev); \ + ((_ndev)->priv->mbox_size) ? (_ndev)->priv->mbox_size : \ + pci_resource_len(NDEV2PDEV(_ndev), (_ndev)->xdna->dev_info->mbox_bar); \ +}) + #define SMU_MPNPUCLK_FREQ_MAX(ndev) ((ndev)->priv->smu_mpnpuclk_freq_max) #define SMU_HCLK_FREQ_MAX(ndev) ((ndev)->priv->smu_hclk_freq_max) @@ -63,12 +76,37 @@ enum psp_reg_idx { PSP_MAX_REGS /* Keep this at the end */ }; +struct amdxdna_fw_ver; + struct psp_config { const void *fw_buf; u32 fw_size; void __iomem *psp_regs[PSP_MAX_REGS]; }; +struct aie_version { + u16 major; + u16 minor; +}; + +struct aie_tile_metadata { + u16 row_count; + u16 row_start; + u16 dma_channel_count; + u16 lock_count; + u16 event_reg_count; +}; + +struct aie_metadata { + u32 size; + u16 cols; + u16 rows; + struct aie_version version; + struct aie_tile_metadata core; + struct aie_tile_metadata mem; + struct aie_tile_metadata shim; +}; + struct clock_entry { char name[16]; u32 freq_mhz; @@ -84,9 +122,22 @@ struct amdxdna_dev_hdl { const struct amdxdna_dev_priv *priv; void __iomem *sram_base; void __iomem *smu_base; + void __iomem *mbox_base; struct psp_device *psp_hdl; + + struct xdna_mailbox_chann_res mgmt_x2i; + struct xdna_mailbox_chann_res mgmt_i2x; + u32 mgmt_chan_idx; + + u32 total_col; + struct aie_version version; + struct aie_metadata metadata; struct clock_entry mp_npu_clock; struct clock_entry h_clock; + + /* Mailbox and the management channel */ + struct mailbox *mbox; + struct mailbox_channel *mgmt_chann; }; #define DEFINE_BAR_OFFSET(reg_name, bar, reg_addr) \ @@ -127,4 +178,15 @@ struct psp_device *aie2m_psp_create(struct drm_device *ddev, struct psp_config * int aie2_psp_start(struct psp_device *psp); void aie2_psp_stop(struct psp_device *psp); +/* aie2_message.c */ +int aie2_suspend_fw(struct amdxdna_dev_hdl *ndev); +int aie2_resume_fw(struct amdxdna_dev_hdl *ndev); +int aie2_set_runtime_cfg(struct amdxdna_dev_hdl *ndev, u32 type, u64 value); +int aie2_get_runtime_cfg(struct amdxdna_dev_hdl *ndev, u32 type, u64 *value); +int aie2_check_protocol_version(struct amdxdna_dev_hdl *ndev); +int aie2_assign_mgmt_pasid(struct amdxdna_dev_hdl *ndev, u16 pasid); +int aie2_query_aie_version(struct amdxdna_dev_hdl *ndev, struct aie_version *version); +int aie2_query_aie_metadata(struct amdxdna_dev_hdl *ndev, struct aie_metadata *metadata); +int aie2_query_firmware_version(struct amdxdna_dev_hdl *ndev, + struct amdxdna_fw_ver *fw_ver); #endif /* _AIE2_PCI_H_ */ diff --git a/drivers/accel/amdxdna/aie2_psp.c b/drivers/accel/amdxdna/aie2_psp.c index 610ed8aa824a..b03501e81065 100644 --- a/drivers/accel/amdxdna/aie2_psp.c +++ b/drivers/accel/amdxdna/aie2_psp.c @@ -10,6 +10,8 @@ #include #include "aie2_pci.h" +#include "amdxdna_mailbox.h" +#include "amdxdna_pci_drv.h" #define PSP_STATUS_READY BIT(31) diff --git a/drivers/accel/amdxdna/amdxdna_mailbox.c b/drivers/accel/amdxdna/amdxdna_mailbox.c new file mode 100644 index 000000000000..415d99abaaa3 --- /dev/null +++ b/drivers/accel/amdxdna/amdxdna_mailbox.c @@ -0,0 +1,576 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022-2024, Advanced Micro Devices, Inc. + */ + +#include +#include +#include +#include + +#define CREATE_TRACE_POINTS +#include + +#include "amdxdna_mailbox.h" + +#define MB_ERR(chann, fmt, args...) \ +({ \ + typeof(chann) _chann = chann; \ + dev_err((_chann)->mb->dev, "xdna_mailbox.%d: "fmt, \ + (_chann)->msix_irq, ##args); \ +}) +#define MB_DBG(chann, fmt, args...) \ +({ \ + typeof(chann) _chann = chann; \ + dev_dbg((_chann)->mb->dev, "xdna_mailbox.%d: "fmt, \ + (_chann)->msix_irq, ##args); \ +}) +#define MB_WARN_ONCE(chann, fmt, args...) \ +({ \ + typeof(chann) _chann = chann; \ + dev_warn_once((_chann)->mb->dev, "xdna_mailbox.%d: "fmt, \ + (_chann)->msix_irq, ##args); \ +}) + +#define MAGIC_VAL 0x1D000000U +#define MAGIC_VAL_MASK 0xFF000000 +#define MAX_MSG_ID_ENTRIES 256 +#define MSG_RX_TIMER 200 /* milliseconds */ +#define MAILBOX_NAME "xdna_mailbox" + +enum channel_res_type { + CHAN_RES_X2I, + CHAN_RES_I2X, + CHAN_RES_NUM +}; + +struct mailbox { + struct device *dev; + struct xdna_mailbox_res res; +}; + +struct mailbox_channel { + struct mailbox *mb; + struct xdna_mailbox_chann_res res[CHAN_RES_NUM]; + int msix_irq; + u32 iohub_int_addr; + struct idr chan_idr; + spinlock_t chan_idr_lock; /* protect chan_idr */ + u32 x2i_tail; + + /* Received msg related fields */ + struct workqueue_struct *work_q; + struct work_struct rx_work; + u32 i2x_head; + bool bad_state; +}; + +#define MSG_BODY_SZ GENMASK(10, 0) +#define MSG_PROTO_VER GENMASK(23, 16) +struct xdna_msg_header { + __u32 total_size; + __u32 sz_ver; + __u32 id; + __u32 opcode; +} __packed; + +static_assert(sizeof(struct xdna_msg_header) == 16); + +struct mailbox_pkg { + struct xdna_msg_header header; + __u32 payload[]; +}; + +/* The protocol version. */ +#define MSG_PROTOCOL_VERSION 0x1 +/* The tombstone value. */ +#define TOMBSTONE 0xDEADFACE + +struct mailbox_msg { + void *handle; + int (*notify_cb)(void *handle, const u32 *data, size_t size); + size_t pkg_size; /* package size in bytes */ + struct mailbox_pkg pkg; +}; + +static void mailbox_reg_write(struct mailbox_channel *mb_chann, u32 mbox_reg, u32 data) +{ + struct xdna_mailbox_res *mb_res = &mb_chann->mb->res; + u64 ringbuf_addr = mb_res->mbox_base + mbox_reg; + + writel(data, (void *)ringbuf_addr); +} + +static u32 mailbox_reg_read(struct mailbox_channel *mb_chann, u32 mbox_reg) +{ + struct xdna_mailbox_res *mb_res = &mb_chann->mb->res; + u64 ringbuf_addr = mb_res->mbox_base + mbox_reg; + + return readl((void *)ringbuf_addr); +} + +static int mailbox_reg_read_non_zero(struct mailbox_channel *mb_chann, u32 mbox_reg, u32 *val) +{ + struct xdna_mailbox_res *mb_res = &mb_chann->mb->res; + u64 ringbuf_addr = mb_res->mbox_base + mbox_reg; + int ret, value; + + /* Poll till value is not zero */ + ret = readx_poll_timeout(readl, (void *)ringbuf_addr, value, + value, 1 /* us */, 100); + if (ret < 0) + return ret; + + *val = value; + return 0; +} + +static inline void +mailbox_set_headptr(struct mailbox_channel *mb_chann, u32 headptr_val) +{ + mailbox_reg_write(mb_chann, mb_chann->res[CHAN_RES_I2X].mb_head_ptr_reg, headptr_val); + mb_chann->i2x_head = headptr_val; +} + +static inline void +mailbox_set_tailptr(struct mailbox_channel *mb_chann, u32 tailptr_val) +{ + mailbox_reg_write(mb_chann, mb_chann->res[CHAN_RES_X2I].mb_tail_ptr_reg, tailptr_val); + mb_chann->x2i_tail = tailptr_val; +} + +static inline u32 +mailbox_get_headptr(struct mailbox_channel *mb_chann, enum channel_res_type type) +{ + return mailbox_reg_read(mb_chann, mb_chann->res[type].mb_head_ptr_reg); +} + +static inline u32 +mailbox_get_tailptr(struct mailbox_channel *mb_chann, enum channel_res_type type) +{ + return mailbox_reg_read(mb_chann, mb_chann->res[type].mb_tail_ptr_reg); +} + +static inline u32 +mailbox_get_ringbuf_size(struct mailbox_channel *mb_chann, enum channel_res_type type) +{ + return mb_chann->res[type].rb_size; +} + +static inline int mailbox_validate_msgid(int msg_id) +{ + return (msg_id & MAGIC_VAL_MASK) == MAGIC_VAL; +} + +static int mailbox_acquire_msgid(struct mailbox_channel *mb_chann, struct mailbox_msg *mb_msg) +{ + unsigned long flags; + int msg_id; + + spin_lock_irqsave(&mb_chann->chan_idr_lock, flags); + msg_id = idr_alloc_cyclic(&mb_chann->chan_idr, mb_msg, 0, + MAX_MSG_ID_ENTRIES, GFP_NOWAIT); + spin_unlock_irqrestore(&mb_chann->chan_idr_lock, flags); + if (msg_id < 0) + return msg_id; + + /* + * The IDR becomes less efficient when dealing with larger IDs. + * Thus, add MAGIC_VAL to the higher bits. + */ + msg_id |= MAGIC_VAL; + return msg_id; +} + +static void mailbox_release_msgid(struct mailbox_channel *mb_chann, int msg_id) +{ + unsigned long flags; + + msg_id &= ~MAGIC_VAL_MASK; + spin_lock_irqsave(&mb_chann->chan_idr_lock, flags); + idr_remove(&mb_chann->chan_idr, msg_id); + spin_unlock_irqrestore(&mb_chann->chan_idr_lock, flags); +} + +static int mailbox_release_msg(int id, void *p, void *data) +{ + struct mailbox_channel *mb_chann = data; + struct mailbox_msg *mb_msg = p; + + MB_DBG(mb_chann, "msg_id 0x%x msg opcode 0x%x", + mb_msg->pkg.header.id, mb_msg->pkg.header.opcode); + mb_msg->notify_cb(mb_msg->handle, NULL, 0); + kfree(mb_msg); + + return 0; +} + +static int +mailbox_send_msg(struct mailbox_channel *mb_chann, struct mailbox_msg *mb_msg) +{ + u32 ringbuf_size; + u32 head, tail; + u32 start_addr; + u64 write_addr; + u32 tmp_tail; + + head = mailbox_get_headptr(mb_chann, CHAN_RES_X2I); + tail = mb_chann->x2i_tail; + ringbuf_size = mailbox_get_ringbuf_size(mb_chann, CHAN_RES_X2I); + start_addr = mb_chann->res[CHAN_RES_X2I].rb_start_addr; + tmp_tail = tail + mb_msg->pkg_size; + + if (tail < head && tmp_tail >= head) + goto no_space; + + if (tail >= head && (tmp_tail > ringbuf_size - sizeof(u32) && + mb_msg->pkg_size >= head)) + goto no_space; + + if (tail >= head && tmp_tail > ringbuf_size - sizeof(u32)) { + write_addr = mb_chann->mb->res.ringbuf_base + start_addr + tail; + writel(TOMBSTONE, (void *)write_addr); + + /* tombstone is set. Write from the start of the ringbuf */ + tail = 0; + } + + write_addr = mb_chann->mb->res.ringbuf_base + start_addr + tail; + memcpy_toio((void *)write_addr, &mb_msg->pkg, mb_msg->pkg_size); + mailbox_set_tailptr(mb_chann, tail + mb_msg->pkg_size); + + trace_mbox_set_tail(MAILBOX_NAME, mb_chann->msix_irq, + mb_msg->pkg.header.opcode, + mb_msg->pkg.header.id); + + return 0; + +no_space: + return -ENOSPC; +} + +static int +mailbox_get_resp(struct mailbox_channel *mb_chann, struct xdna_msg_header *header, + void *data) +{ + struct mailbox_msg *mb_msg; + unsigned long flags; + int msg_id; + int ret; + + msg_id = header->id; + if (!mailbox_validate_msgid(msg_id)) { + MB_ERR(mb_chann, "Bad message ID 0x%x", msg_id); + return -EINVAL; + } + + msg_id &= ~MAGIC_VAL_MASK; + spin_lock_irqsave(&mb_chann->chan_idr_lock, flags); + mb_msg = idr_find(&mb_chann->chan_idr, msg_id); + if (!mb_msg) { + MB_ERR(mb_chann, "Cannot find msg 0x%x", msg_id); + spin_unlock_irqrestore(&mb_chann->chan_idr_lock, flags); + return -EINVAL; + } + idr_remove(&mb_chann->chan_idr, msg_id); + spin_unlock_irqrestore(&mb_chann->chan_idr_lock, flags); + + MB_DBG(mb_chann, "opcode 0x%x size %d id 0x%x", + header->opcode, header->total_size, header->id); + ret = mb_msg->notify_cb(mb_msg->handle, data, header->total_size); + if (unlikely(ret)) + MB_ERR(mb_chann, "Message callback ret %d", ret); + + kfree(mb_msg); + return ret; +} + +static int mailbox_get_msg(struct mailbox_channel *mb_chann) +{ + struct xdna_msg_header header; + u32 msg_size, rest; + u32 ringbuf_size; + u32 head, tail; + u32 start_addr; + u64 read_addr; + int ret; + + if (mailbox_reg_read_non_zero(mb_chann, mb_chann->res[CHAN_RES_I2X].mb_tail_ptr_reg, &tail)) + return -EINVAL; + head = mb_chann->i2x_head; + ringbuf_size = mailbox_get_ringbuf_size(mb_chann, CHAN_RES_I2X); + start_addr = mb_chann->res[CHAN_RES_I2X].rb_start_addr; + + if (unlikely(tail > ringbuf_size || !IS_ALIGNED(tail, 4))) { + MB_WARN_ONCE(mb_chann, "Invalid tail 0x%x", tail); + return -EINVAL; + } + + /* ringbuf empty */ + if (head == tail) + return -ENOENT; + + if (head == ringbuf_size) + head = 0; + + /* Peek size of the message or TOMBSTONE */ + read_addr = mb_chann->mb->res.ringbuf_base + start_addr + head; + header.total_size = readl((void *)read_addr); + /* size is TOMBSTONE, set next read from 0 */ + if (header.total_size == TOMBSTONE) { + if (head < tail) { + MB_WARN_ONCE(mb_chann, "Tombstone, head 0x%x tail 0x%x", + head, tail); + return -EINVAL; + } + mailbox_set_headptr(mb_chann, 0); + return 0; + } + + if (unlikely(!header.total_size || !IS_ALIGNED(header.total_size, 4))) { + MB_WARN_ONCE(mb_chann, "Invalid total size 0x%x", header.total_size); + return -EINVAL; + } + msg_size = sizeof(header) + header.total_size; + + if (msg_size > ringbuf_size - head || msg_size > tail - head) { + MB_WARN_ONCE(mb_chann, "Invalid message size %d, tail %d, head %d", + msg_size, tail, head); + return -EINVAL; + } + + rest = sizeof(header) - sizeof(u32); + read_addr += sizeof(u32); + memcpy_fromio((u32 *)&header + 1, (void *)read_addr, rest); + read_addr += rest; + + ret = mailbox_get_resp(mb_chann, &header, (u32 *)read_addr); + + mailbox_set_headptr(mb_chann, head + msg_size); + /* After update head, it can equal to ringbuf_size. This is expected. */ + trace_mbox_set_head(MAILBOX_NAME, mb_chann->msix_irq, + header.opcode, header.id); + + return ret; +} + +static irqreturn_t mailbox_irq_handler(int irq, void *p) +{ + struct mailbox_channel *mb_chann = p; + + trace_mbox_irq_handle(MAILBOX_NAME, irq); + /* Schedule a rx_work to call the callback functions */ + queue_work(mb_chann->work_q, &mb_chann->rx_work); + /* Clear IOHUB register */ + mailbox_reg_write(mb_chann, mb_chann->iohub_int_addr, 0); + + return IRQ_HANDLED; +} + +static void mailbox_rx_worker(struct work_struct *rx_work) +{ + struct mailbox_channel *mb_chann; + int ret; + + mb_chann = container_of(rx_work, struct mailbox_channel, rx_work); + + if (READ_ONCE(mb_chann->bad_state)) { + MB_ERR(mb_chann, "Channel in bad state, work aborted"); + return; + } + + while (1) { + /* + * If return is 0, keep consuming next message, until there is + * no messages or an error happened. + */ + ret = mailbox_get_msg(mb_chann); + if (ret == -ENOENT) + break; + + /* Other error means device doesn't look good, disable irq. */ + if (unlikely(ret)) { + MB_ERR(mb_chann, "Unexpected ret %d, disable irq", ret); + WRITE_ONCE(mb_chann->bad_state, true); + disable_irq(mb_chann->msix_irq); + break; + } + } +} + +int xdna_mailbox_send_msg(struct mailbox_channel *mb_chann, + const struct xdna_mailbox_msg *msg, u64 tx_timeout) +{ + struct xdna_msg_header *header; + struct mailbox_msg *mb_msg; + size_t pkg_size; + int ret; + + pkg_size = sizeof(*header) + msg->send_size; + if (pkg_size > mailbox_get_ringbuf_size(mb_chann, CHAN_RES_X2I)) { + MB_ERR(mb_chann, "Message size larger than ringbuf size"); + return -EINVAL; + } + + if (unlikely(!IS_ALIGNED(msg->send_size, 4))) { + MB_ERR(mb_chann, "Message must be 4 bytes align"); + return -EINVAL; + } + + /* The fist word in payload can NOT be TOMBSTONE */ + if (unlikely(((u32 *)msg->send_data)[0] == TOMBSTONE)) { + MB_ERR(mb_chann, "Tomb stone in data"); + return -EINVAL; + } + + if (READ_ONCE(mb_chann->bad_state)) { + MB_ERR(mb_chann, "Channel in bad state"); + return -EPIPE; + } + + mb_msg = kzalloc(sizeof(*mb_msg) + pkg_size, GFP_KERNEL); + if (!mb_msg) + return -ENOMEM; + + mb_msg->handle = msg->handle; + mb_msg->notify_cb = msg->notify_cb; + mb_msg->pkg_size = pkg_size; + + header = &mb_msg->pkg.header; + /* + * Hardware use total_size and size to split huge message. + * We do not support it here. Thus the values are the same. + */ + header->total_size = msg->send_size; + header->sz_ver = FIELD_PREP(MSG_BODY_SZ, msg->send_size) | + FIELD_PREP(MSG_PROTO_VER, MSG_PROTOCOL_VERSION); + header->opcode = msg->opcode; + memcpy(mb_msg->pkg.payload, msg->send_data, msg->send_size); + + ret = mailbox_acquire_msgid(mb_chann, mb_msg); + if (unlikely(ret < 0)) { + MB_ERR(mb_chann, "mailbox_acquire_msgid failed"); + goto msg_id_failed; + } + header->id = ret; + + MB_DBG(mb_chann, "opcode 0x%x size %d id 0x%x", + header->opcode, header->total_size, header->id); + + ret = mailbox_send_msg(mb_chann, mb_msg); + if (ret) { + MB_DBG(mb_chann, "Error in mailbox send msg, ret %d", ret); + goto release_id; + } + + return 0; + +release_id: + mailbox_release_msgid(mb_chann, header->id); +msg_id_failed: + kfree(mb_msg); + return ret; +} + +struct mailbox_channel * +xdna_mailbox_create_channel(struct mailbox *mb, + const struct xdna_mailbox_chann_res *x2i, + const struct xdna_mailbox_chann_res *i2x, + u32 iohub_int_addr, + int mb_irq) +{ + struct mailbox_channel *mb_chann; + int ret; + + if (!is_power_of_2(x2i->rb_size) || !is_power_of_2(i2x->rb_size)) { + pr_err("Ring buf size must be power of 2"); + return NULL; + } + + mb_chann = kzalloc(sizeof(*mb_chann), GFP_KERNEL); + if (!mb_chann) + return NULL; + + mb_chann->mb = mb; + mb_chann->msix_irq = mb_irq; + mb_chann->iohub_int_addr = iohub_int_addr; + memcpy(&mb_chann->res[CHAN_RES_X2I], x2i, sizeof(*x2i)); + memcpy(&mb_chann->res[CHAN_RES_I2X], i2x, sizeof(*i2x)); + + spin_lock_init(&mb_chann->chan_idr_lock); + idr_init(&mb_chann->chan_idr); + mb_chann->x2i_tail = mailbox_get_tailptr(mb_chann, CHAN_RES_X2I); + mb_chann->i2x_head = mailbox_get_headptr(mb_chann, CHAN_RES_I2X); + + INIT_WORK(&mb_chann->rx_work, mailbox_rx_worker); + mb_chann->work_q = create_singlethread_workqueue(MAILBOX_NAME); + if (!mb_chann->work_q) { + MB_ERR(mb_chann, "Create workqueue failed"); + goto free_and_out; + } + + /* Everything look good. Time to enable irq handler */ + ret = request_irq(mb_irq, mailbox_irq_handler, 0, MAILBOX_NAME, mb_chann); + if (ret) { + MB_ERR(mb_chann, "Failed to request irq %d ret %d", mb_irq, ret); + goto destroy_wq; + } + + mb_chann->bad_state = false; + + MB_DBG(mb_chann, "Mailbox channel created (irq: %d)", mb_chann->msix_irq); + return mb_chann; + +destroy_wq: + destroy_workqueue(mb_chann->work_q); +free_and_out: + kfree(mb_chann); + return NULL; +} + +int xdna_mailbox_destroy_channel(struct mailbox_channel *mb_chann) +{ + if (!mb_chann) + return 0; + + MB_DBG(mb_chann, "IRQ disabled and RX work cancelled"); + free_irq(mb_chann->msix_irq, mb_chann); + destroy_workqueue(mb_chann->work_q); + /* We can clean up and release resources */ + + idr_for_each(&mb_chann->chan_idr, mailbox_release_msg, mb_chann); + idr_destroy(&mb_chann->chan_idr); + + MB_DBG(mb_chann, "Mailbox channel destroyed, irq: %d", mb_chann->msix_irq); + kfree(mb_chann); + return 0; +} + +void xdna_mailbox_stop_channel(struct mailbox_channel *mb_chann) +{ + if (!mb_chann) + return; + + /* Disable an irq and wait. This might sleep. */ + disable_irq(mb_chann->msix_irq); + + /* Cancel RX work and wait for it to finish */ + cancel_work_sync(&mb_chann->rx_work); + MB_DBG(mb_chann, "IRQ disabled and RX work cancelled"); +} + +struct mailbox *xdnam_mailbox_create(struct drm_device *ddev, + const struct xdna_mailbox_res *res) +{ + struct mailbox *mb; + + mb = drmm_kzalloc(ddev, sizeof(*mb), GFP_KERNEL); + if (!mb) + return NULL; + mb->dev = ddev->dev; + + /* mailbox and ring buf base and size information */ + memcpy(&mb->res, res, sizeof(*res)); + + return mb; +} diff --git a/drivers/accel/amdxdna/amdxdna_mailbox.h b/drivers/accel/amdxdna/amdxdna_mailbox.h new file mode 100644 index 000000000000..6ab7f5424633 --- /dev/null +++ b/drivers/accel/amdxdna/amdxdna_mailbox.h @@ -0,0 +1,124 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2022-2024, Advanced Micro Devices, Inc. + */ + +#ifndef _AIE2_MAILBOX_H_ +#define _AIE2_MAILBOX_H_ + +struct mailbox; +struct mailbox_channel; + +/* + * xdna_mailbox_msg - message struct + * + * @opcode: opcode for firmware + * @handle: handle used for the notify callback + * @notify_cb: callback function to notify the sender when there is response + * @send_data: pointing to sending data + * @send_size: size of the sending data + * + * The mailbox will split the sending data in to multiple firmware message if + * the size of the data is too big. This is transparent to the sender. The + * sender will receive one notification. + */ +struct xdna_mailbox_msg { + u32 opcode; + void *handle; + int (*notify_cb)(void *handle, const u32 *data, size_t size); + u8 *send_data; + size_t send_size; +}; + +/* + * xdna_mailbox_res - mailbox hardware resource + * + * @ringbuf_base: ring buffer base address + * @ringbuf_size: ring buffer size + * @mbox_base: mailbox base address + * @mbox_size: mailbox size + */ +struct xdna_mailbox_res { + u64 ringbuf_base; + size_t ringbuf_size; + u64 mbox_base; + size_t mbox_size; + const char *name; +}; + +/* + * xdna_mailbox_chann_res - resources + * + * @rb_start_addr: ring buffer start address + * @rb_size: ring buffer size + * @mb_head_ptr_reg: mailbox head pointer register + * @mb_tail_ptr_reg: mailbox tail pointer register + */ +struct xdna_mailbox_chann_res { + u32 rb_start_addr; + u32 rb_size; + u32 mb_head_ptr_reg; + u32 mb_tail_ptr_reg; +}; + +/* + * xdna_mailbox_create() -- create mailbox subsystem and initialize + * + * @ddev: device pointer + * @res: SRAM and mailbox resources + * + * Return: If success, return a handle of mailbox subsystem. + * Otherwise, return NULL pointer. + */ +struct mailbox *xdnam_mailbox_create(struct drm_device *ddev, + const struct xdna_mailbox_res *res); + +/* + * xdna_mailbox_create_channel() -- Create a mailbox channel instance + * + * @mailbox: the handle return from xdna_mailbox_create() + * @x2i: host to firmware mailbox resources + * @i2x: firmware to host mailbox resources + * @xdna_mailbox_intr_reg: register addr of MSI-X interrupt + * @mb_irq: Linux IRQ number associated with mailbox MSI-X interrupt vector index + * + * Return: If success, return a handle of mailbox channel. Otherwise, return NULL. + */ +struct mailbox_channel * +xdna_mailbox_create_channel(struct mailbox *mailbox, + const struct xdna_mailbox_chann_res *x2i, + const struct xdna_mailbox_chann_res *i2x, + u32 xdna_mailbox_intr_reg, + int mb_irq); + +/* + * xdna_mailbox_destroy_channel() -- destroy mailbox channel + * + * @mailbox_chann: the handle return from xdna_mailbox_create_channel() + * + * Return: if success, return 0. otherwise return error code + */ +int xdna_mailbox_destroy_channel(struct mailbox_channel *mailbox_chann); + +/* + * xdna_mailbox_stop_channel() -- stop mailbox channel + * + * @mailbox_chann: the handle return from xdna_mailbox_create_channel() + * + * Return: if success, return 0. otherwise return error code + */ +void xdna_mailbox_stop_channel(struct mailbox_channel *mailbox_chann); + +/* + * xdna_mailbox_send_msg() -- Send a message + * + * @mailbox_chann: Mailbox channel handle + * @msg: message struct for message information + * @tx_timeout: the timeout value for sending the message in ms. + * + * Return: If success return 0, otherwise, return error code + */ +int xdna_mailbox_send_msg(struct mailbox_channel *mailbox_chann, + const struct xdna_mailbox_msg *msg, u64 tx_timeout); + +#endif /* _AIE2_MAILBOX_ */ diff --git a/drivers/accel/amdxdna/amdxdna_mailbox_helper.c b/drivers/accel/amdxdna/amdxdna_mailbox_helper.c new file mode 100644 index 000000000000..42b615394605 --- /dev/null +++ b/drivers/accel/amdxdna/amdxdna_mailbox_helper.c @@ -0,0 +1,56 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024, Advanced Micro Devices, Inc. + */ + +#include +#include +#include + +#include "amdxdna_mailbox.h" +#include "amdxdna_mailbox_helper.h" +#include "amdxdna_pci_drv.h" + +int xdna_msg_cb(void *handle, const u32 *data, size_t size) +{ + struct xdna_notify *cb_arg = handle; + int ret; + + if (unlikely(!data)) + goto out; + + if (unlikely(cb_arg->size != size)) { + cb_arg->error = -EINVAL; + goto out; + } + + print_hex_dump_debug("resp data: ", DUMP_PREFIX_OFFSET, + 16, 4, data, cb_arg->size, true); + memcpy(cb_arg->data, data, cb_arg->size); +out: + ret = cb_arg->error; + complete(&cb_arg->comp); + return ret; +} + +int xdna_send_msg_wait(struct amdxdna_dev *xdna, struct mailbox_channel *chann, + struct xdna_mailbox_msg *msg) +{ + struct xdna_notify *hdl = msg->handle; + int ret; + + ret = xdna_mailbox_send_msg(chann, msg, TX_TIMEOUT); + if (ret) { + XDNA_ERR(xdna, "Send message failed, ret %d", ret); + return ret; + } + + ret = wait_for_completion_timeout(&hdl->comp, + msecs_to_jiffies(RX_TIMEOUT)); + if (!ret) { + XDNA_ERR(xdna, "Wait for completion timeout"); + return -ETIME; + } + + return hdl->error; +} diff --git a/drivers/accel/amdxdna/amdxdna_mailbox_helper.h b/drivers/accel/amdxdna/amdxdna_mailbox_helper.h new file mode 100644 index 000000000000..23e1317b79fe --- /dev/null +++ b/drivers/accel/amdxdna/amdxdna_mailbox_helper.h @@ -0,0 +1,42 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2023-2024, Advanced Micro Devices, Inc. + */ + +#ifndef _AMDXDNA_MAILBOX_HELPER_H +#define _AMDXDNA_MAILBOX_HELPER_H + +#define TX_TIMEOUT 2000 /* milliseconds */ +#define RX_TIMEOUT 5000 /* milliseconds */ + +struct amdxdna_dev; + +struct xdna_notify { + struct completion comp; + u32 *data; + size_t size; + int error; +}; + +#define DECLARE_XDNA_MSG_COMMON(name, op, status) \ + struct name##_req req = { 0 }; \ + struct name##_resp resp = { status }; \ + struct xdna_notify hdl = { \ + .error = 0, \ + .data = (u32 *)&resp, \ + .size = sizeof(resp), \ + .comp = COMPLETION_INITIALIZER_ONSTACK(hdl.comp), \ + }; \ + struct xdna_mailbox_msg msg = { \ + .send_data = (u8 *)&req, \ + .send_size = sizeof(req), \ + .handle = &hdl, \ + .opcode = op, \ + .notify_cb = xdna_msg_cb, \ + } + +int xdna_msg_cb(void *handle, const u32 *data, size_t size); +int xdna_send_msg_wait(struct amdxdna_dev *xdna, struct mailbox_channel *chann, + struct xdna_mailbox_msg *msg); + +#endif /* _AMDXDNA_MAILBOX_HELPER_H */ diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.h b/drivers/accel/amdxdna/amdxdna_pci_drv.h index 2f1a1c2441f9..64bce970514b 100644 --- a/drivers/accel/amdxdna/amdxdna_pci_drv.h +++ b/drivers/accel/amdxdna/amdxdna_pci_drv.h @@ -47,12 +47,20 @@ struct amdxdna_dev_info { const struct amdxdna_dev_ops *ops; }; +struct amdxdna_fw_ver { + u32 major; + u32 minor; + u32 sub; + u32 build; +}; + struct amdxdna_dev { struct drm_device ddev; struct amdxdna_dev_hdl *dev_handle; const struct amdxdna_dev_info *dev_info; struct mutex dev_lock; /* per device lock */ + struct amdxdna_fw_ver fw_ver; }; /* diff --git a/drivers/accel/amdxdna/amdxdna_sysfs.c b/drivers/accel/amdxdna/amdxdna_sysfs.c index 5dd652fcf9d4..668b94b92714 100644 --- a/drivers/accel/amdxdna/amdxdna_sysfs.c +++ b/drivers/accel/amdxdna/amdxdna_sysfs.c @@ -24,9 +24,20 @@ static ssize_t device_type_show(struct device *dev, struct device_attribute *att } static DEVICE_ATTR_RO(device_type); +static ssize_t fw_version_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct amdxdna_dev *xdna = dev_get_drvdata(dev); + + return sprintf(buf, "%d.%d.%d.%d\n", xdna->fw_ver.major, + xdna->fw_ver.minor, xdna->fw_ver.sub, + xdna->fw_ver.build); +} +static DEVICE_ATTR_RO(fw_version); + static struct attribute *amdxdna_attrs[] = { &dev_attr_device_type.attr, &dev_attr_vbnv.attr, + &dev_attr_fw_version.attr, NULL, }; diff --git a/drivers/accel/amdxdna/npu1_regs.c b/drivers/accel/amdxdna/npu1_regs.c index 858b31a82888..720aab0ed7c4 100644 --- a/drivers/accel/amdxdna/npu1_regs.c +++ b/drivers/accel/amdxdna/npu1_regs.c @@ -8,6 +8,7 @@ #include #include "aie2_pci.h" +#include "amdxdna_mailbox.h" #include "amdxdna_pci_drv.h" /* Address definition from NPU1 docs */ diff --git a/drivers/accel/amdxdna/npu2_regs.c b/drivers/accel/amdxdna/npu2_regs.c index 02b0f22c9f14..f3ea18bcf294 100644 --- a/drivers/accel/amdxdna/npu2_regs.c +++ b/drivers/accel/amdxdna/npu2_regs.c @@ -8,6 +8,7 @@ #include #include "aie2_pci.h" +#include "amdxdna_mailbox.h" #include "amdxdna_pci_drv.h" /* NPU Public Registers on MpNPUAxiXbar (refer to Diag npu_registers.h) */ diff --git a/drivers/accel/amdxdna/npu4_regs.c b/drivers/accel/amdxdna/npu4_regs.c index ca5ca5a6c751..db61142f0d4e 100644 --- a/drivers/accel/amdxdna/npu4_regs.c +++ b/drivers/accel/amdxdna/npu4_regs.c @@ -8,6 +8,7 @@ #include #include "aie2_pci.h" +#include "amdxdna_mailbox.h" #include "amdxdna_pci_drv.h" /* NPU Public Registers on MpNPUAxiXbar (refer to Diag npu_registers.h) */ diff --git a/drivers/accel/amdxdna/npu5_regs.c b/drivers/accel/amdxdna/npu5_regs.c index 07fddcbb86ec..debf4e95b9bb 100644 --- a/drivers/accel/amdxdna/npu5_regs.c +++ b/drivers/accel/amdxdna/npu5_regs.c @@ -8,6 +8,7 @@ #include #include "aie2_pci.h" +#include "amdxdna_mailbox.h" #include "amdxdna_pci_drv.h" /* NPU Public Registers on MpNPUAxiXbar (refer to Diag npu_registers.h) */ diff --git a/include/trace/events/amdxdna.h b/include/trace/events/amdxdna.h new file mode 100644 index 000000000000..33343d8f0622 --- /dev/null +++ b/include/trace/events/amdxdna.h @@ -0,0 +1,60 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2023-2024, Advanced Micro Devices, Inc. + */ + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM amdxdna + +#if !defined(_TRACE_AMDXDNA_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_AMDXDNA_H + +#include + +DECLARE_EVENT_CLASS(xdna_mbox_msg, + TP_PROTO(char *name, u8 chann_id, u32 opcode, u32 msg_id), + + TP_ARGS(name, chann_id, opcode, msg_id), + + TP_STRUCT__entry(__string(name, name) + __field(u32, chann_id) + __field(u32, opcode) + __field(u32, msg_id)), + + TP_fast_assign(__assign_str(name); + __entry->chann_id = chann_id; + __entry->opcode = opcode; + __entry->msg_id = msg_id;), + + TP_printk("%s.%d id 0x%x opcode 0x%x", __get_str(name), + __entry->chann_id, __entry->msg_id, __entry->opcode) +); + +DEFINE_EVENT(xdna_mbox_msg, mbox_set_tail, + TP_PROTO(char *name, u8 chann_id, u32 opcode, u32 id), + TP_ARGS(name, chann_id, opcode, id) +); + +DEFINE_EVENT(xdna_mbox_msg, mbox_set_head, + TP_PROTO(char *name, u8 chann_id, u32 opcode, u32 id), + TP_ARGS(name, chann_id, opcode, id) +); + +TRACE_EVENT(mbox_irq_handle, + TP_PROTO(char *name, int irq), + + TP_ARGS(name, irq), + + TP_STRUCT__entry(__string(name, name) + __field(int, irq)), + + TP_fast_assign(__assign_str(name); + __entry->irq = irq;), + + TP_printk("%s.%d", __get_str(name), __entry->irq) +); + +#endif /* !defined(_TRACE_AMDXDNA_H) || defined(TRACE_HEADER_MULTI_READ) */ + +/* This part must be outside protection */ +#include -- cgit v1.2.3 From be462c97b7dfd24999babe39cce3de224ebe1f80 Mon Sep 17 00:00:00 2001 From: Lizhi Hou Date: Mon, 18 Nov 2024 09:29:37 -0800 Subject: accel/amdxdna: Add hardware context The hardware can be shared among multiple user applications. The hardware resources are allocated/freed based on the request from user application via driver IOCTLs. DRM_IOCTL_AMDXDNA_CREATE_HWCTX Allocate tile columns and create a hardware context structure to track the usage and status of the resources. A hardware context ID is returned for XDNA command execution. DRM_IOCTL_AMDXDNA_DESTROY_HWCTX Release hardware context based on its ID. The tile columns belong to this hardware context will be reclaimed. DRM_IOCTL_AMDXDNA_CONFIG_HWCTX Config hardware context. Bind the hardware context to the required resources. Co-developed-by: Min Ma Signed-off-by: Min Ma Reviewed-by: Jeffrey Hugo Signed-off-by: Lizhi Hou Signed-off-by: Jeffrey Hugo Link: https://patchwork.freedesktop.org/patch/msgid/20241118172942.2014541-6-lizhi.hou@amd.com --- drivers/accel/amdxdna/Makefile | 2 + drivers/accel/amdxdna/aie2_ctx.c | 186 +++++++++++++++++++++++++++ drivers/accel/amdxdna/aie2_message.c | 90 +++++++++++++ drivers/accel/amdxdna/aie2_pci.c | 43 +++++++ drivers/accel/amdxdna/aie2_pci.h | 13 ++ drivers/accel/amdxdna/amdxdna_ctx.c | 219 ++++++++++++++++++++++++++++++++ drivers/accel/amdxdna/amdxdna_ctx.h | 39 ++++++ drivers/accel/amdxdna/amdxdna_pci_drv.c | 125 +++++++++++++++++- drivers/accel/amdxdna/amdxdna_pci_drv.h | 20 +++ include/uapi/drm/amdxdna_accel.h | 131 +++++++++++++++++++ 10 files changed, 867 insertions(+), 1 deletion(-) create mode 100644 drivers/accel/amdxdna/aie2_ctx.c create mode 100644 drivers/accel/amdxdna/amdxdna_ctx.c create mode 100644 drivers/accel/amdxdna/amdxdna_ctx.h (limited to 'include') diff --git a/drivers/accel/amdxdna/Makefile b/drivers/accel/amdxdna/Makefile index 39d3404fbc8f..c86c90dfd303 100644 --- a/drivers/accel/amdxdna/Makefile +++ b/drivers/accel/amdxdna/Makefile @@ -1,11 +1,13 @@ # SPDX-License-Identifier: GPL-2.0-only amdxdna-y := \ + aie2_ctx.o \ aie2_message.o \ aie2_pci.o \ aie2_psp.o \ aie2_smu.o \ aie2_solver.o \ + amdxdna_ctx.o \ amdxdna_mailbox.o \ amdxdna_mailbox_helper.o \ amdxdna_pci_drv.o \ diff --git a/drivers/accel/amdxdna/aie2_ctx.c b/drivers/accel/amdxdna/aie2_ctx.c new file mode 100644 index 000000000000..022b2b0b015d --- /dev/null +++ b/drivers/accel/amdxdna/aie2_ctx.c @@ -0,0 +1,186 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024, Advanced Micro Devices, Inc. + */ + +#include +#include +#include +#include + +#include "aie2_pci.h" +#include "aie2_solver.h" +#include "amdxdna_ctx.h" +#include "amdxdna_mailbox.h" +#include "amdxdna_pci_drv.h" + +static int aie2_hwctx_col_list(struct amdxdna_hwctx *hwctx) +{ + struct amdxdna_dev *xdna = hwctx->client->xdna; + struct amdxdna_dev_hdl *ndev; + int start, end, first, last; + u32 width = 1, entries = 0; + int i; + + if (!hwctx->num_tiles) { + XDNA_ERR(xdna, "Number of tiles is zero"); + return -EINVAL; + } + + ndev = xdna->dev_handle; + if (unlikely(!ndev->metadata.core.row_count)) { + XDNA_WARN(xdna, "Core tile row count is zero"); + return -EINVAL; + } + + hwctx->num_col = hwctx->num_tiles / ndev->metadata.core.row_count; + if (!hwctx->num_col || hwctx->num_col > ndev->total_col) { + XDNA_ERR(xdna, "Invalid num_col %d", hwctx->num_col); + return -EINVAL; + } + + if (ndev->priv->col_align == COL_ALIGN_NATURE) + width = hwctx->num_col; + + /* + * In range [start, end], find out columns that is multiple of width. + * 'first' is the first column, + * 'last' is the last column, + * 'entries' is the total number of columns. + */ + start = xdna->dev_info->first_col; + end = ndev->total_col - hwctx->num_col; + if (start > 0 && end == 0) { + XDNA_DBG(xdna, "Force start from col 0"); + start = 0; + } + first = start + (width - start % width) % width; + last = end - end % width; + if (last >= first) + entries = (last - first) / width + 1; + XDNA_DBG(xdna, "start %d end %d first %d last %d", + start, end, first, last); + + if (unlikely(!entries)) { + XDNA_ERR(xdna, "Start %d end %d width %d", + start, end, width); + return -EINVAL; + } + + hwctx->col_list = kmalloc_array(entries, sizeof(*hwctx->col_list), GFP_KERNEL); + if (!hwctx->col_list) + return -ENOMEM; + + hwctx->col_list_len = entries; + hwctx->col_list[0] = first; + for (i = 1; i < entries; i++) + hwctx->col_list[i] = hwctx->col_list[i - 1] + width; + + print_hex_dump_debug("col_list: ", DUMP_PREFIX_OFFSET, 16, 4, hwctx->col_list, + entries * sizeof(*hwctx->col_list), false); + return 0; +} + +static int aie2_alloc_resource(struct amdxdna_hwctx *hwctx) +{ + struct amdxdna_dev *xdna = hwctx->client->xdna; + struct alloc_requests *xrs_req; + int ret; + + xrs_req = kzalloc(sizeof(*xrs_req), GFP_KERNEL); + if (!xrs_req) + return -ENOMEM; + + xrs_req->cdo.start_cols = hwctx->col_list; + xrs_req->cdo.cols_len = hwctx->col_list_len; + xrs_req->cdo.ncols = hwctx->num_col; + xrs_req->cdo.qos_cap.opc = hwctx->max_opc; + + xrs_req->rqos.gops = hwctx->qos.gops; + xrs_req->rqos.fps = hwctx->qos.fps; + xrs_req->rqos.dma_bw = hwctx->qos.dma_bandwidth; + xrs_req->rqos.latency = hwctx->qos.latency; + xrs_req->rqos.exec_time = hwctx->qos.frame_exec_time; + xrs_req->rqos.priority = hwctx->qos.priority; + + xrs_req->rid = (uintptr_t)hwctx; + + ret = xrs_allocate_resource(xdna->xrs_hdl, xrs_req, hwctx); + if (ret) + XDNA_ERR(xdna, "Allocate AIE resource failed, ret %d", ret); + + kfree(xrs_req); + return ret; +} + +static void aie2_release_resource(struct amdxdna_hwctx *hwctx) +{ + struct amdxdna_dev *xdna = hwctx->client->xdna; + int ret; + + ret = xrs_release_resource(xdna->xrs_hdl, (uintptr_t)hwctx); + if (ret) + XDNA_ERR(xdna, "Release AIE resource failed, ret %d", ret); +} + +int aie2_hwctx_init(struct amdxdna_hwctx *hwctx) +{ + struct amdxdna_client *client = hwctx->client; + struct amdxdna_dev *xdna = client->xdna; + struct amdxdna_hwctx_priv *priv; + int ret; + + priv = kzalloc(sizeof(*hwctx->priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + hwctx->priv = priv; + + ret = aie2_hwctx_col_list(hwctx); + if (ret) { + XDNA_ERR(xdna, "Create col list failed, ret %d", ret); + goto free_priv; + } + + ret = aie2_alloc_resource(hwctx); + if (ret) { + XDNA_ERR(xdna, "Alloc hw resource failed, ret %d", ret); + goto free_col_list; + } + + hwctx->status = HWCTX_STAT_INIT; + + XDNA_DBG(xdna, "hwctx %s init completed", hwctx->name); + + return 0; + +free_col_list: + kfree(hwctx->col_list); +free_priv: + kfree(priv); + return ret; +} + +void aie2_hwctx_fini(struct amdxdna_hwctx *hwctx) +{ + aie2_release_resource(hwctx); + + kfree(hwctx->col_list); + kfree(hwctx->priv); + kfree(hwctx->cus); +} + +int aie2_hwctx_config(struct amdxdna_hwctx *hwctx, u32 type, u64 value, void *buf, u32 size) +{ + struct amdxdna_dev *xdna = hwctx->client->xdna; + + drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock)); + switch (type) { + case DRM_AMDXDNA_HWCTX_CONFIG_CU: + case DRM_AMDXDNA_HWCTX_ASSIGN_DBG_BUF: + case DRM_AMDXDNA_HWCTX_REMOVE_DBG_BUF: + return -EOPNOTSUPP; + default: + XDNA_DBG(xdna, "Not supported type %d", type); + return -EOPNOTSUPP; + } +} diff --git a/drivers/accel/amdxdna/aie2_message.c b/drivers/accel/amdxdna/aie2_message.c index cbf8ee54c6c2..4b8a71bf4fae 100644 --- a/drivers/accel/amdxdna/aie2_message.c +++ b/drivers/accel/amdxdna/aie2_message.c @@ -3,13 +3,16 @@ * Copyright (C) 2023-2024, Advanced Micro Devices, Inc. */ +#include #include #include #include +#include #include #include "aie2_msg_priv.h" #include "aie2_pci.h" +#include "amdxdna_ctx.h" #include "amdxdna_mailbox.h" #include "amdxdna_mailbox_helper.h" #include "amdxdna_pci_drv.h" @@ -192,3 +195,90 @@ int aie2_query_firmware_version(struct amdxdna_dev_hdl *ndev, return 0; } + +int aie2_create_context(struct amdxdna_dev_hdl *ndev, struct amdxdna_hwctx *hwctx) +{ + DECLARE_AIE2_MSG(create_ctx, MSG_OP_CREATE_CONTEXT); + struct amdxdna_dev *xdna = ndev->xdna; + struct xdna_mailbox_chann_res x2i; + struct xdna_mailbox_chann_res i2x; + struct cq_pair *cq_pair; + u32 intr_reg; + int ret; + + req.aie_type = 1; + req.start_col = hwctx->start_col; + req.num_col = hwctx->num_col; + req.num_cq_pairs_requested = 1; + req.pasid = hwctx->client->pasid; + req.context_priority = 2; + + ret = aie2_send_mgmt_msg_wait(ndev, &msg); + if (ret) + return ret; + + hwctx->fw_ctx_id = resp.context_id; + WARN_ONCE(hwctx->fw_ctx_id == -1, "Unexpected context id"); + + cq_pair = &resp.cq_pair[0]; + x2i.mb_head_ptr_reg = AIE2_MBOX_OFF(ndev, cq_pair->x2i_q.head_addr); + x2i.mb_tail_ptr_reg = AIE2_MBOX_OFF(ndev, cq_pair->x2i_q.tail_addr); + x2i.rb_start_addr = AIE2_SRAM_OFF(ndev, cq_pair->x2i_q.buf_addr); + x2i.rb_size = cq_pair->x2i_q.buf_size; + + i2x.mb_head_ptr_reg = AIE2_MBOX_OFF(ndev, cq_pair->i2x_q.head_addr); + i2x.mb_tail_ptr_reg = AIE2_MBOX_OFF(ndev, cq_pair->i2x_q.tail_addr); + i2x.rb_start_addr = AIE2_SRAM_OFF(ndev, cq_pair->i2x_q.buf_addr); + i2x.rb_size = cq_pair->i2x_q.buf_size; + + ret = pci_irq_vector(to_pci_dev(xdna->ddev.dev), resp.msix_id); + if (ret == -EINVAL) { + XDNA_ERR(xdna, "not able to create channel"); + goto out_destroy_context; + } + + intr_reg = i2x.mb_head_ptr_reg + 4; + hwctx->priv->mbox_chann = xdna_mailbox_create_channel(ndev->mbox, &x2i, &i2x, + intr_reg, ret); + if (!hwctx->priv->mbox_chann) { + XDNA_ERR(xdna, "not able to create channel"); + ret = -EINVAL; + goto out_destroy_context; + } + + XDNA_DBG(xdna, "%s mailbox channel irq: %d, msix_id: %d", + hwctx->name, ret, resp.msix_id); + XDNA_DBG(xdna, "%s created fw ctx %d pasid %d", hwctx->name, + hwctx->fw_ctx_id, hwctx->client->pasid); + + return 0; + +out_destroy_context: + aie2_destroy_context(ndev, hwctx); + return ret; +} + +int aie2_destroy_context(struct amdxdna_dev_hdl *ndev, struct amdxdna_hwctx *hwctx) +{ + DECLARE_AIE2_MSG(destroy_ctx, MSG_OP_DESTROY_CONTEXT); + struct amdxdna_dev *xdna = ndev->xdna; + int ret; + + if (hwctx->fw_ctx_id == -1) + return 0; + + xdna_mailbox_stop_channel(hwctx->priv->mbox_chann); + + req.context_id = hwctx->fw_ctx_id; + ret = aie2_send_mgmt_msg_wait(ndev, &msg); + if (ret) + XDNA_WARN(xdna, "%s destroy context failed, ret %d", hwctx->name, ret); + + xdna_mailbox_destroy_channel(hwctx->priv->mbox_chann); + XDNA_DBG(xdna, "%s destroyed fw ctx %d", hwctx->name, + hwctx->fw_ctx_id); + hwctx->priv->mbox_chann = NULL; + hwctx->fw_ctx_id = -1; + + return ret; +} diff --git a/drivers/accel/amdxdna/aie2_pci.c b/drivers/accel/amdxdna/aie2_pci.c index ce0822238b11..6181854c799c 100644 --- a/drivers/accel/amdxdna/aie2_pci.c +++ b/drivers/accel/amdxdna/aie2_pci.c @@ -3,6 +3,7 @@ * Copyright (C) 2023-2024, Advanced Micro Devices, Inc. */ +#include #include #include #include @@ -15,6 +16,7 @@ #include "aie2_msg_priv.h" #include "aie2_pci.h" #include "aie2_solver.h" +#include "amdxdna_ctx.h" #include "amdxdna_mailbox.h" #include "amdxdna_pci_drv.h" @@ -210,6 +212,43 @@ static void aie2_mgmt_fw_fini(struct amdxdna_dev_hdl *ndev) XDNA_DBG(ndev->xdna, "Firmware suspended"); } +static int aie2_xrs_load(void *cb_arg, struct xrs_action_load *action) +{ + struct amdxdna_hwctx *hwctx = cb_arg; + struct amdxdna_dev *xdna; + int ret; + + xdna = hwctx->client->xdna; + + hwctx->start_col = action->part.start_col; + hwctx->num_col = action->part.ncols; + ret = aie2_create_context(xdna->dev_handle, hwctx); + if (ret) + XDNA_ERR(xdna, "create context failed, ret %d", ret); + + return ret; +} + +static int aie2_xrs_unload(void *cb_arg) +{ + struct amdxdna_hwctx *hwctx = cb_arg; + struct amdxdna_dev *xdna; + int ret; + + xdna = hwctx->client->xdna; + + ret = aie2_destroy_context(xdna->dev_handle, hwctx); + if (ret) + XDNA_ERR(xdna, "destroy context failed, ret %d", ret); + + return ret; +} + +static struct xrs_action_ops aie2_xrs_actions = { + .load = aie2_xrs_load, + .unload = aie2_xrs_unload, +}; + static void aie2_hw_stop(struct amdxdna_dev *xdna) { struct pci_dev *pdev = to_pci_dev(xdna->ddev.dev); @@ -417,6 +456,7 @@ static int aie2_init(struct amdxdna_dev *xdna) xrs_cfg.clk_list.cu_clk_list[2] = 1000; xrs_cfg.sys_eff_factor = 1; xrs_cfg.ddev = &xdna->ddev; + xrs_cfg.actions = &aie2_xrs_actions; xrs_cfg.total_col = ndev->total_col; xdna->xrs_hdl = xrsm_init(&xrs_cfg); @@ -453,4 +493,7 @@ static void aie2_fini(struct amdxdna_dev *xdna) const struct amdxdna_dev_ops aie2_ops = { .init = aie2_init, .fini = aie2_fini, + .hwctx_init = aie2_hwctx_init, + .hwctx_fini = aie2_hwctx_fini, + .hwctx_config = aie2_hwctx_config, }; diff --git a/drivers/accel/amdxdna/aie2_pci.h b/drivers/accel/amdxdna/aie2_pci.h index 4c81d10a0998..b789286bc9d4 100644 --- a/drivers/accel/amdxdna/aie2_pci.h +++ b/drivers/accel/amdxdna/aie2_pci.h @@ -77,6 +77,7 @@ enum psp_reg_idx { }; struct amdxdna_fw_ver; +struct amdxdna_hwctx; struct psp_config { const void *fw_buf; @@ -117,6 +118,10 @@ struct rt_config { u32 value; }; +struct amdxdna_hwctx_priv { + void *mbox_chann; +}; + struct amdxdna_dev_hdl { struct amdxdna_dev *xdna; const struct amdxdna_dev_priv *priv; @@ -189,4 +194,12 @@ int aie2_query_aie_version(struct amdxdna_dev_hdl *ndev, struct aie_version *ver int aie2_query_aie_metadata(struct amdxdna_dev_hdl *ndev, struct aie_metadata *metadata); int aie2_query_firmware_version(struct amdxdna_dev_hdl *ndev, struct amdxdna_fw_ver *fw_ver); +int aie2_create_context(struct amdxdna_dev_hdl *ndev, struct amdxdna_hwctx *hwctx); +int aie2_destroy_context(struct amdxdna_dev_hdl *ndev, struct amdxdna_hwctx *hwctx); + +/* aie2_hwctx.c */ +int aie2_hwctx_init(struct amdxdna_hwctx *hwctx); +void aie2_hwctx_fini(struct amdxdna_hwctx *hwctx); +int aie2_hwctx_config(struct amdxdna_hwctx *hwctx, u32 type, u64 value, void *buf, u32 size); + #endif /* _AIE2_PCI_H_ */ diff --git a/drivers/accel/amdxdna/amdxdna_ctx.c b/drivers/accel/amdxdna/amdxdna_ctx.c new file mode 100644 index 000000000000..9489399adea1 --- /dev/null +++ b/drivers/accel/amdxdna/amdxdna_ctx.c @@ -0,0 +1,219 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022-2024, Advanced Micro Devices, Inc. + */ + +#include +#include +#include +#include +#include + +#include "amdxdna_ctx.h" +#include "amdxdna_pci_drv.h" + +#define MAX_HWCTX_ID 255 + +static void amdxdna_hwctx_destroy(struct amdxdna_hwctx *hwctx) +{ + struct amdxdna_dev *xdna = hwctx->client->xdna; + + /* At this point, user is not able to submit new commands */ + mutex_lock(&xdna->dev_lock); + xdna->dev_info->ops->hwctx_fini(hwctx); + mutex_unlock(&xdna->dev_lock); + + kfree(hwctx->name); + kfree(hwctx); +} + +/* + * This should be called in close() and remove(). DO NOT call in other syscalls. + * This guarantee that when hwctx and resources will be released, if user + * doesn't call amdxdna_drm_destroy_hwctx_ioctl. + */ +void amdxdna_hwctx_remove_all(struct amdxdna_client *client) +{ + struct amdxdna_hwctx *hwctx; + int next = 0; + + mutex_lock(&client->hwctx_lock); + idr_for_each_entry_continue(&client->hwctx_idr, hwctx, next) { + XDNA_DBG(client->xdna, "PID %d close HW context %d", + client->pid, hwctx->id); + idr_remove(&client->hwctx_idr, hwctx->id); + mutex_unlock(&client->hwctx_lock); + amdxdna_hwctx_destroy(hwctx); + mutex_lock(&client->hwctx_lock); + } + mutex_unlock(&client->hwctx_lock); +} + +int amdxdna_drm_create_hwctx_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) +{ + struct amdxdna_client *client = filp->driver_priv; + struct amdxdna_drm_create_hwctx *args = data; + struct amdxdna_dev *xdna = to_xdna_dev(dev); + struct amdxdna_hwctx *hwctx; + int ret, idx; + + if (args->ext || args->ext_flags) + return -EINVAL; + + if (!drm_dev_enter(dev, &idx)) + return -ENODEV; + + hwctx = kzalloc(sizeof(*hwctx), GFP_KERNEL); + if (!hwctx) { + ret = -ENOMEM; + goto exit; + } + + if (copy_from_user(&hwctx->qos, u64_to_user_ptr(args->qos_p), sizeof(hwctx->qos))) { + XDNA_ERR(xdna, "Access QoS info failed"); + ret = -EFAULT; + goto free_hwctx; + } + + hwctx->client = client; + hwctx->fw_ctx_id = -1; + hwctx->num_tiles = args->num_tiles; + hwctx->mem_size = args->mem_size; + hwctx->max_opc = args->max_opc; + mutex_lock(&client->hwctx_lock); + ret = idr_alloc_cyclic(&client->hwctx_idr, hwctx, 0, MAX_HWCTX_ID, GFP_KERNEL); + if (ret < 0) { + mutex_unlock(&client->hwctx_lock); + XDNA_ERR(xdna, "Allocate hwctx ID failed, ret %d", ret); + goto free_hwctx; + } + hwctx->id = ret; + mutex_unlock(&client->hwctx_lock); + + hwctx->name = kasprintf(GFP_KERNEL, "hwctx.%d.%d", client->pid, hwctx->id); + if (!hwctx->name) { + ret = -ENOMEM; + goto rm_id; + } + + mutex_lock(&xdna->dev_lock); + ret = xdna->dev_info->ops->hwctx_init(hwctx); + if (ret) { + mutex_unlock(&xdna->dev_lock); + XDNA_ERR(xdna, "Init hwctx failed, ret %d", ret); + goto free_name; + } + args->handle = hwctx->id; + args->syncobj_handle = hwctx->syncobj_hdl; + mutex_unlock(&xdna->dev_lock); + + XDNA_DBG(xdna, "PID %d create HW context %d, ret %d", client->pid, args->handle, ret); + drm_dev_exit(idx); + return 0; + +free_name: + kfree(hwctx->name); +rm_id: + mutex_lock(&client->hwctx_lock); + idr_remove(&client->hwctx_idr, hwctx->id); + mutex_unlock(&client->hwctx_lock); +free_hwctx: + kfree(hwctx); +exit: + drm_dev_exit(idx); + return ret; +} + +int amdxdna_drm_destroy_hwctx_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) +{ + struct amdxdna_client *client = filp->driver_priv; + struct amdxdna_drm_destroy_hwctx *args = data; + struct amdxdna_dev *xdna = to_xdna_dev(dev); + struct amdxdna_hwctx *hwctx; + int ret = 0, idx; + + if (!drm_dev_enter(dev, &idx)) + return -ENODEV; + + mutex_lock(&client->hwctx_lock); + hwctx = idr_find(&client->hwctx_idr, args->handle); + if (!hwctx) { + mutex_unlock(&client->hwctx_lock); + ret = -EINVAL; + XDNA_DBG(xdna, "PID %d HW context %d not exist", + client->pid, args->handle); + goto out; + } + idr_remove(&client->hwctx_idr, hwctx->id); + mutex_unlock(&client->hwctx_lock); + + amdxdna_hwctx_destroy(hwctx); + + XDNA_DBG(xdna, "PID %d destroyed HW context %d", client->pid, args->handle); +out: + drm_dev_exit(idx); + return ret; +} + +int amdxdna_drm_config_hwctx_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) +{ + struct amdxdna_client *client = filp->driver_priv; + struct amdxdna_drm_config_hwctx *args = data; + struct amdxdna_dev *xdna = to_xdna_dev(dev); + struct amdxdna_hwctx *hwctx; + u32 buf_size; + void *buf; + u64 val; + int ret; + + if (!xdna->dev_info->ops->hwctx_config) + return -EOPNOTSUPP; + + val = args->param_val; + buf_size = args->param_val_size; + + switch (args->param_type) { + case DRM_AMDXDNA_HWCTX_CONFIG_CU: + /* For those types that param_val is pointer */ + if (buf_size > PAGE_SIZE) { + XDNA_ERR(xdna, "Config CU param buffer too large"); + return -E2BIG; + } + + /* Hwctx needs to keep buf */ + buf = kzalloc(PAGE_SIZE, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + if (copy_from_user(buf, u64_to_user_ptr(val), buf_size)) { + kfree(buf); + return -EFAULT; + } + + break; + case DRM_AMDXDNA_HWCTX_ASSIGN_DBG_BUF: + case DRM_AMDXDNA_HWCTX_REMOVE_DBG_BUF: + /* For those types that param_val is a value */ + buf = NULL; + buf_size = 0; + break; + default: + XDNA_DBG(xdna, "Unknown HW context config type %d", args->param_type); + return -EINVAL; + } + + mutex_lock(&xdna->dev_lock); + hwctx = idr_find(&client->hwctx_idr, args->handle); + if (!hwctx) { + XDNA_DBG(xdna, "PID %d failed to get hwctx %d", client->pid, args->handle); + ret = -EINVAL; + goto unlock; + } + + ret = xdna->dev_info->ops->hwctx_config(hwctx, args->param_type, val, buf, buf_size); + +unlock: + mutex_unlock(&xdna->dev_lock); + kfree(buf); + return ret; +} diff --git a/drivers/accel/amdxdna/amdxdna_ctx.h b/drivers/accel/amdxdna/amdxdna_ctx.h new file mode 100644 index 000000000000..00b96cf2e9a7 --- /dev/null +++ b/drivers/accel/amdxdna/amdxdna_ctx.h @@ -0,0 +1,39 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2022-2024, Advanced Micro Devices, Inc. + */ + +#ifndef _AMDXDNA_CTX_H_ +#define _AMDXDNA_CTX_H_ + +struct amdxdna_hwctx { + struct amdxdna_client *client; + struct amdxdna_hwctx_priv *priv; + char *name; + + u32 id; + u32 max_opc; + u32 num_tiles; + u32 mem_size; + u32 fw_ctx_id; + u32 col_list_len; + u32 *col_list; + u32 start_col; + u32 num_col; +#define HWCTX_STAT_INIT 0 +#define HWCTX_STAT_READY 1 +#define HWCTX_STAT_STOP 2 + u32 status; + u32 old_status; + + struct amdxdna_qos_info qos; + struct amdxdna_hwctx_param_config_cu *cus; + u32 syncobj_hdl; +}; + +void amdxdna_hwctx_remove_all(struct amdxdna_client *client); +int amdxdna_drm_create_hwctx_ioctl(struct drm_device *dev, void *data, struct drm_file *filp); +int amdxdna_drm_config_hwctx_ioctl(struct drm_device *dev, void *data, struct drm_file *filp); +int amdxdna_drm_destroy_hwctx_ioctl(struct drm_device *dev, void *data, struct drm_file *filp); + +#endif /* _AMDXDNA_CTX_H_ */ diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.c b/drivers/accel/amdxdna/amdxdna_pci_drv.c index b8caf323a0c6..dfe682df5640 100644 --- a/drivers/accel/amdxdna/amdxdna_pci_drv.c +++ b/drivers/accel/amdxdna/amdxdna_pci_drv.c @@ -3,13 +3,16 @@ * Copyright (C) 2022-2024, Advanced Micro Devices, Inc. */ +#include #include #include #include #include #include +#include #include +#include "amdxdna_ctx.h" #include "amdxdna_pci_drv.h" /* @@ -33,7 +36,108 @@ static const struct amdxdna_device_id amdxdna_ids[] = { {0} }; -DEFINE_DRM_ACCEL_FOPS(amdxdna_fops); +static int amdxdna_drm_open(struct drm_device *ddev, struct drm_file *filp) +{ + struct amdxdna_dev *xdna = to_xdna_dev(ddev); + struct amdxdna_client *client; + int ret; + + client = kzalloc(sizeof(*client), GFP_KERNEL); + if (!client) + return -ENOMEM; + + client->pid = pid_nr(filp->pid); + client->xdna = xdna; + + client->sva = iommu_sva_bind_device(xdna->ddev.dev, current->mm); + if (IS_ERR(client->sva)) { + ret = PTR_ERR(client->sva); + XDNA_ERR(xdna, "SVA bind device failed, ret %d", ret); + goto failed; + } + client->pasid = iommu_sva_get_pasid(client->sva); + if (client->pasid == IOMMU_PASID_INVALID) { + XDNA_ERR(xdna, "SVA get pasid failed"); + ret = -ENODEV; + goto unbind_sva; + } + mutex_init(&client->hwctx_lock); + idr_init_base(&client->hwctx_idr, AMDXDNA_INVALID_CTX_HANDLE + 1); + + mutex_lock(&xdna->dev_lock); + list_add_tail(&client->node, &xdna->client_list); + mutex_unlock(&xdna->dev_lock); + + filp->driver_priv = client; + client->filp = filp; + + XDNA_DBG(xdna, "pid %d opened", client->pid); + return 0; + +unbind_sva: + iommu_sva_unbind_device(client->sva); +failed: + kfree(client); + + return ret; +} + +static void amdxdna_drm_close(struct drm_device *ddev, struct drm_file *filp) +{ + struct amdxdna_client *client = filp->driver_priv; + struct amdxdna_dev *xdna = to_xdna_dev(ddev); + + XDNA_DBG(xdna, "closing pid %d", client->pid); + + idr_destroy(&client->hwctx_idr); + mutex_destroy(&client->hwctx_lock); + + iommu_sva_unbind_device(client->sva); + + XDNA_DBG(xdna, "pid %d closed", client->pid); + kfree(client); +} + +static int amdxdna_flush(struct file *f, fl_owner_t id) +{ + struct drm_file *filp = f->private_data; + struct amdxdna_client *client = filp->driver_priv; + struct amdxdna_dev *xdna = client->xdna; + int idx; + + XDNA_DBG(xdna, "PID %d flushing...", client->pid); + if (!drm_dev_enter(&xdna->ddev, &idx)) + return 0; + + mutex_lock(&xdna->dev_lock); + list_del_init(&client->node); + mutex_unlock(&xdna->dev_lock); + amdxdna_hwctx_remove_all(client); + + drm_dev_exit(idx); + return 0; +} + +static const struct drm_ioctl_desc amdxdna_drm_ioctls[] = { + /* Context */ + DRM_IOCTL_DEF_DRV(AMDXDNA_CREATE_HWCTX, amdxdna_drm_create_hwctx_ioctl, 0), + DRM_IOCTL_DEF_DRV(AMDXDNA_DESTROY_HWCTX, amdxdna_drm_destroy_hwctx_ioctl, 0), + DRM_IOCTL_DEF_DRV(AMDXDNA_CONFIG_HWCTX, amdxdna_drm_config_hwctx_ioctl, 0), +}; + +static const struct file_operations amdxdna_fops = { + .owner = THIS_MODULE, + .open = accel_open, + .release = drm_release, + .flush = amdxdna_flush, + .unlocked_ioctl = drm_ioctl, + .compat_ioctl = drm_compat_ioctl, + .poll = drm_poll, + .read = drm_read, + .llseek = noop_llseek, + .mmap = drm_gem_mmap, + .fop_flags = FOP_UNSIGNED_OFFSET, +}; const struct drm_driver amdxdna_drm_drv = { .driver_features = DRIVER_GEM | DRIVER_COMPUTE_ACCEL | @@ -41,6 +145,10 @@ const struct drm_driver amdxdna_drm_drv = { .fops = &amdxdna_fops, .name = "amdxdna_accel_driver", .desc = "AMD XDNA DRM implementation", + .open = amdxdna_drm_open, + .postclose = amdxdna_drm_close, + .ioctls = amdxdna_drm_ioctls, + .num_ioctls = ARRAY_SIZE(amdxdna_drm_ioctls), }; static const struct amdxdna_dev_info * @@ -70,6 +178,7 @@ static int amdxdna_probe(struct pci_dev *pdev, const struct pci_device_id *id) return -ENODEV; drmm_mutex_init(&xdna->ddev, &xdna->dev_lock); + INIT_LIST_HEAD(&xdna->client_list); pci_set_drvdata(pdev, xdna); mutex_lock(&xdna->dev_lock); @@ -106,11 +215,25 @@ failed_dev_fini: static void amdxdna_remove(struct pci_dev *pdev) { struct amdxdna_dev *xdna = pci_get_drvdata(pdev); + struct amdxdna_client *client; drm_dev_unplug(&xdna->ddev); amdxdna_sysfs_fini(xdna); mutex_lock(&xdna->dev_lock); + client = list_first_entry_or_null(&xdna->client_list, + struct amdxdna_client, node); + while (client) { + list_del_init(&client->node); + mutex_unlock(&xdna->dev_lock); + + amdxdna_hwctx_remove_all(client); + + mutex_lock(&xdna->dev_lock); + client = list_first_entry_or_null(&xdna->client_list, + struct amdxdna_client, node); + } + xdna->dev_info->ops->fini(xdna); mutex_unlock(&xdna->dev_lock); } diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.h b/drivers/accel/amdxdna/amdxdna_pci_drv.h index c0710d3130fd..5ec7fe168406 100644 --- a/drivers/accel/amdxdna/amdxdna_pci_drv.h +++ b/drivers/accel/amdxdna/amdxdna_pci_drv.h @@ -18,6 +18,7 @@ extern const struct drm_driver amdxdna_drm_drv; struct amdxdna_dev; +struct amdxdna_hwctx; /* * struct amdxdna_dev_ops - Device hardware operation callbacks @@ -25,6 +26,9 @@ struct amdxdna_dev; struct amdxdna_dev_ops { int (*init)(struct amdxdna_dev *xdna); void (*fini)(struct amdxdna_dev *xdna); + int (*hwctx_init)(struct amdxdna_hwctx *hwctx); + void (*hwctx_fini)(struct amdxdna_hwctx *hwctx); + int (*hwctx_config)(struct amdxdna_hwctx *hwctx, u32 type, u64 value, void *buf, u32 size); }; /* @@ -61,6 +65,7 @@ struct amdxdna_dev { void *xrs_hdl; struct mutex dev_lock; /* per device lock */ + struct list_head client_list; struct amdxdna_fw_ver fw_ver; }; @@ -73,6 +78,21 @@ struct amdxdna_device_id { const struct amdxdna_dev_info *dev_info; }; +/* + * struct amdxdna_client - amdxdna client + * A per fd data structure for managing context and other user process stuffs. + */ +struct amdxdna_client { + struct list_head node; + pid_t pid; + struct mutex hwctx_lock; /* protect hwctx */ + struct idr hwctx_idr; + struct amdxdna_dev *xdna; + struct drm_file *filp; + struct iommu_sva *sva; + int pasid; +}; + /* Add device info below */ extern const struct amdxdna_dev_info dev_npu1_info; extern const struct amdxdna_dev_info dev_npu2_info; diff --git a/include/uapi/drm/amdxdna_accel.h b/include/uapi/drm/amdxdna_accel.h index 6d97e8e90cf6..a0dc821c1363 100644 --- a/include/uapi/drm/amdxdna_accel.h +++ b/include/uapi/drm/amdxdna_accel.h @@ -6,17 +6,148 @@ #ifndef _UAPI_AMDXDNA_ACCEL_H_ #define _UAPI_AMDXDNA_ACCEL_H_ +#include #include "drm.h" #if defined(__cplusplus) extern "C" { #endif +#define AMDXDNA_INVALID_CTX_HANDLE 0 + enum amdxdna_device_type { AMDXDNA_DEV_TYPE_UNKNOWN = -1, AMDXDNA_DEV_TYPE_KMQ, }; +enum amdxdna_drm_ioctl_id { + DRM_AMDXDNA_CREATE_HWCTX, + DRM_AMDXDNA_DESTROY_HWCTX, + DRM_AMDXDNA_CONFIG_HWCTX, +}; + +/** + * struct qos_info - QoS information for driver. + * @gops: Giga operations per second. + * @fps: Frames per second. + * @dma_bandwidth: DMA bandwidtha. + * @latency: Frame response latency. + * @frame_exec_time: Frame execution time. + * @priority: Request priority. + * + * User program can provide QoS hints to driver. + */ +struct amdxdna_qos_info { + __u32 gops; + __u32 fps; + __u32 dma_bandwidth; + __u32 latency; + __u32 frame_exec_time; + __u32 priority; +}; + +/** + * struct amdxdna_drm_create_hwctx - Create hardware context. + * @ext: MBZ. + * @ext_flags: MBZ. + * @qos_p: Address of QoS info. + * @umq_bo: BO handle for user mode queue(UMQ). + * @log_buf_bo: BO handle for log buffer. + * @max_opc: Maximum operations per cycle. + * @num_tiles: Number of AIE tiles. + * @mem_size: Size of AIE tile memory. + * @umq_doorbell: Returned offset of doorbell associated with UMQ. + * @handle: Returned hardware context handle. + * @syncobj_handle: Returned syncobj handle for command completion. + */ +struct amdxdna_drm_create_hwctx { + __u64 ext; + __u64 ext_flags; + __u64 qos_p; + __u32 umq_bo; + __u32 log_buf_bo; + __u32 max_opc; + __u32 num_tiles; + __u32 mem_size; + __u32 umq_doorbell; + __u32 handle; + __u32 syncobj_handle; +}; + +/** + * struct amdxdna_drm_destroy_hwctx - Destroy hardware context. + * @handle: Hardware context handle. + * @pad: Structure padding. + */ +struct amdxdna_drm_destroy_hwctx { + __u32 handle; + __u32 pad; +}; + +/** + * struct amdxdna_cu_config - configuration for one CU + * @cu_bo: CU configuration buffer bo handle. + * @cu_func: Function of a CU. + * @pad: Structure padding. + */ +struct amdxdna_cu_config { + __u32 cu_bo; + __u8 cu_func; + __u8 pad[3]; +}; + +/** + * struct amdxdna_hwctx_param_config_cu - configuration for CUs in hardware context + * @num_cus: Number of CUs to configure. + * @pad: Structure padding. + * @cu_configs: Array of CU configurations of struct amdxdna_cu_config. + */ +struct amdxdna_hwctx_param_config_cu { + __u16 num_cus; + __u16 pad[3]; + struct amdxdna_cu_config cu_configs[] __counted_by(num_cus); +}; + +enum amdxdna_drm_config_hwctx_param { + DRM_AMDXDNA_HWCTX_CONFIG_CU, + DRM_AMDXDNA_HWCTX_ASSIGN_DBG_BUF, + DRM_AMDXDNA_HWCTX_REMOVE_DBG_BUF, + DRM_AMDXDNA_HWCTX_CONFIG_NUM +}; + +/** + * struct amdxdna_drm_config_hwctx - Configure hardware context. + * @handle: hardware context handle. + * @param_type: Value in enum amdxdna_drm_config_hwctx_param. Specifies the + * structure passed in via param_val. + * @param_val: A structure specified by the param_type struct member. + * @param_val_size: Size of the parameter buffer pointed to by the param_val. + * If param_val is not a pointer, driver can ignore this. + * @pad: Structure padding. + * + * Note: if the param_val is a pointer pointing to a buffer, the maximum size + * of the buffer is 4KiB(PAGE_SIZE). + */ +struct amdxdna_drm_config_hwctx { + __u32 handle; + __u32 param_type; + __u64 param_val; + __u32 param_val_size; + __u32 pad; +}; + +#define DRM_IOCTL_AMDXDNA_CREATE_HWCTX \ + DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDXDNA_CREATE_HWCTX, \ + struct amdxdna_drm_create_hwctx) + +#define DRM_IOCTL_AMDXDNA_DESTROY_HWCTX \ + DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDXDNA_DESTROY_HWCTX, \ + struct amdxdna_drm_destroy_hwctx) + +#define DRM_IOCTL_AMDXDNA_CONFIG_HWCTX \ + DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDXDNA_CONFIG_HWCTX, \ + struct amdxdna_drm_config_hwctx) + #if defined(__cplusplus) } /* extern c end */ #endif -- cgit v1.2.3 From ac49797c1815d4f8f04b7053b2998c546283c89e Mon Sep 17 00:00:00 2001 From: Lizhi Hou Date: Mon, 18 Nov 2024 09:29:38 -0800 Subject: accel/amdxdna: Add GEM buffer object management There different types of BOs are supported: - shmem A user application uses shmem BOs as input/output for its workload running on NPU. - device memory heap The fixed size buffer dedicated to the device. - device buffer The buffer object allocated from device memory heap. - command buffer The buffer object created for delivering commands. The command buffer object is small and pinned on creation. New IOCTLs are added: CREATE_BO, GET_BO_INFO, SYNC_BO. SYNC_BO is used to explicitly flush CPU cache for BO memory. Co-developed-by: Min Ma Signed-off-by: Min Ma Reviewed-by: Jeffrey Hugo Signed-off-by: Lizhi Hou Signed-off-by: Jeffrey Hugo Link: https://patchwork.freedesktop.org/patch/msgid/20241118172942.2014541-7-lizhi.hou@amd.com --- drivers/accel/amdxdna/Makefile | 1 + drivers/accel/amdxdna/aie2_ctx.c | 85 ++++- drivers/accel/amdxdna/aie2_message.c | 80 ++++ drivers/accel/amdxdna/aie2_pci.h | 3 + drivers/accel/amdxdna/amdxdna_ctx.h | 10 + drivers/accel/amdxdna/amdxdna_gem.c | 621 ++++++++++++++++++++++++++++++++ drivers/accel/amdxdna/amdxdna_gem.h | 65 ++++ drivers/accel/amdxdna/amdxdna_pci_drv.c | 12 + drivers/accel/amdxdna/amdxdna_pci_drv.h | 6 + include/uapi/drm/amdxdna_accel.h | 77 ++++ 10 files changed, 959 insertions(+), 1 deletion(-) create mode 100644 drivers/accel/amdxdna/amdxdna_gem.c create mode 100644 drivers/accel/amdxdna/amdxdna_gem.h (limited to 'include') diff --git a/drivers/accel/amdxdna/Makefile b/drivers/accel/amdxdna/Makefile index c86c90dfd303..a688c378761f 100644 --- a/drivers/accel/amdxdna/Makefile +++ b/drivers/accel/amdxdna/Makefile @@ -8,6 +8,7 @@ amdxdna-y := \ aie2_smu.o \ aie2_solver.o \ amdxdna_ctx.o \ + amdxdna_gem.o \ amdxdna_mailbox.o \ amdxdna_mailbox_helper.o \ amdxdna_pci_drv.o \ diff --git a/drivers/accel/amdxdna/aie2_ctx.c b/drivers/accel/amdxdna/aie2_ctx.c index 022b2b0b015d..ae8a91dad042 100644 --- a/drivers/accel/amdxdna/aie2_ctx.c +++ b/drivers/accel/amdxdna/aie2_ctx.c @@ -5,12 +5,15 @@ #include #include +#include +#include #include #include #include "aie2_pci.h" #include "aie2_solver.h" #include "amdxdna_ctx.h" +#include "amdxdna_gem.h" #include "amdxdna_mailbox.h" #include "amdxdna_pci_drv.h" @@ -128,6 +131,7 @@ int aie2_hwctx_init(struct amdxdna_hwctx *hwctx) struct amdxdna_client *client = hwctx->client; struct amdxdna_dev *xdna = client->xdna; struct amdxdna_hwctx_priv *priv; + struct amdxdna_gem_obj *heap; int ret; priv = kzalloc(sizeof(*hwctx->priv), GFP_KERNEL); @@ -135,10 +139,28 @@ int aie2_hwctx_init(struct amdxdna_hwctx *hwctx) return -ENOMEM; hwctx->priv = priv; + mutex_lock(&client->mm_lock); + heap = client->dev_heap; + if (!heap) { + XDNA_ERR(xdna, "The client dev heap object not exist"); + mutex_unlock(&client->mm_lock); + ret = -ENOENT; + goto free_priv; + } + drm_gem_object_get(to_gobj(heap)); + mutex_unlock(&client->mm_lock); + priv->heap = heap; + + ret = amdxdna_gem_pin(heap); + if (ret) { + XDNA_ERR(xdna, "Dev heap pin failed, ret %d", ret); + goto put_heap; + } + ret = aie2_hwctx_col_list(hwctx); if (ret) { XDNA_ERR(xdna, "Create col list failed, ret %d", ret); - goto free_priv; + goto unpin; } ret = aie2_alloc_resource(hwctx); @@ -147,14 +169,26 @@ int aie2_hwctx_init(struct amdxdna_hwctx *hwctx) goto free_col_list; } + ret = aie2_map_host_buf(xdna->dev_handle, hwctx->fw_ctx_id, + heap->mem.userptr, heap->mem.size); + if (ret) { + XDNA_ERR(xdna, "Map host buffer failed, ret %d", ret); + goto release_resource; + } hwctx->status = HWCTX_STAT_INIT; XDNA_DBG(xdna, "hwctx %s init completed", hwctx->name); return 0; +release_resource: + aie2_release_resource(hwctx); free_col_list: kfree(hwctx->col_list); +unpin: + amdxdna_gem_unpin(heap); +put_heap: + drm_gem_object_put(to_gobj(heap)); free_priv: kfree(priv); return ret; @@ -164,11 +198,59 @@ void aie2_hwctx_fini(struct amdxdna_hwctx *hwctx) { aie2_release_resource(hwctx); + amdxdna_gem_unpin(hwctx->priv->heap); + drm_gem_object_put(to_gobj(hwctx->priv->heap)); + kfree(hwctx->col_list); kfree(hwctx->priv); kfree(hwctx->cus); } +static int aie2_hwctx_cu_config(struct amdxdna_hwctx *hwctx, void *buf, u32 size) +{ + struct amdxdna_hwctx_param_config_cu *config = buf; + struct amdxdna_dev *xdna = hwctx->client->xdna; + u32 total_size; + int ret; + + XDNA_DBG(xdna, "Config %d CU to %s", config->num_cus, hwctx->name); + if (hwctx->status != HWCTX_STAT_INIT) { + XDNA_ERR(xdna, "Not support re-config CU"); + return -EINVAL; + } + + if (!config->num_cus) { + XDNA_ERR(xdna, "Number of CU is zero"); + return -EINVAL; + } + + total_size = struct_size(config, cu_configs, config->num_cus); + if (total_size > size) { + XDNA_ERR(xdna, "CU config larger than size"); + return -EINVAL; + } + + hwctx->cus = kmemdup(config, total_size, GFP_KERNEL); + if (!hwctx->cus) + return -ENOMEM; + + ret = aie2_config_cu(hwctx); + if (ret) { + XDNA_ERR(xdna, "Config CU to firmware failed, ret %d", ret); + goto free_cus; + } + + wmb(); /* To avoid locking in command submit when check status */ + hwctx->status = HWCTX_STAT_READY; + + return 0; + +free_cus: + kfree(hwctx->cus); + hwctx->cus = NULL; + return ret; +} + int aie2_hwctx_config(struct amdxdna_hwctx *hwctx, u32 type, u64 value, void *buf, u32 size) { struct amdxdna_dev *xdna = hwctx->client->xdna; @@ -176,6 +258,7 @@ int aie2_hwctx_config(struct amdxdna_hwctx *hwctx, u32 type, u64 value, void *bu drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock)); switch (type) { case DRM_AMDXDNA_HWCTX_CONFIG_CU: + return aie2_hwctx_cu_config(hwctx, buf, size); case DRM_AMDXDNA_HWCTX_ASSIGN_DBG_BUF: case DRM_AMDXDNA_HWCTX_REMOVE_DBG_BUF: return -EOPNOTSUPP; diff --git a/drivers/accel/amdxdna/aie2_message.c b/drivers/accel/amdxdna/aie2_message.c index 4b8a71bf4fae..40d9e4261e8b 100644 --- a/drivers/accel/amdxdna/aie2_message.c +++ b/drivers/accel/amdxdna/aie2_message.c @@ -5,7 +5,10 @@ #include #include +#include +#include #include +#include #include #include #include @@ -13,6 +16,7 @@ #include "aie2_msg_priv.h" #include "aie2_pci.h" #include "amdxdna_ctx.h" +#include "amdxdna_gem.h" #include "amdxdna_mailbox.h" #include "amdxdna_mailbox_helper.h" #include "amdxdna_pci_drv.h" @@ -282,3 +286,79 @@ int aie2_destroy_context(struct amdxdna_dev_hdl *ndev, struct amdxdna_hwctx *hwc return ret; } + +int aie2_map_host_buf(struct amdxdna_dev_hdl *ndev, u32 context_id, u64 addr, u64 size) +{ + DECLARE_AIE2_MSG(map_host_buffer, MSG_OP_MAP_HOST_BUFFER); + struct amdxdna_dev *xdna = ndev->xdna; + int ret; + + req.context_id = context_id; + req.buf_addr = addr; + req.buf_size = size; + ret = aie2_send_mgmt_msg_wait(ndev, &msg); + if (ret) + return ret; + + XDNA_DBG(xdna, "fw ctx %d map host buf addr 0x%llx size 0x%llx", + context_id, addr, size); + + return 0; +} + +int aie2_config_cu(struct amdxdna_hwctx *hwctx) +{ + struct mailbox_channel *chann = hwctx->priv->mbox_chann; + struct amdxdna_dev *xdna = hwctx->client->xdna; + u32 shift = xdna->dev_info->dev_mem_buf_shift; + DECLARE_AIE2_MSG(config_cu, MSG_OP_CONFIG_CU); + struct drm_gem_object *gobj; + struct amdxdna_gem_obj *abo; + int ret, i; + + if (!chann) + return -ENODEV; + + if (hwctx->cus->num_cus > MAX_NUM_CUS) { + XDNA_DBG(xdna, "Exceed maximum CU %d", MAX_NUM_CUS); + return -EINVAL; + } + + for (i = 0; i < hwctx->cus->num_cus; i++) { + struct amdxdna_cu_config *cu = &hwctx->cus->cu_configs[i]; + + gobj = drm_gem_object_lookup(hwctx->client->filp, cu->cu_bo); + if (!gobj) { + XDNA_ERR(xdna, "Lookup GEM object failed"); + return -EINVAL; + } + abo = to_xdna_obj(gobj); + + if (abo->type != AMDXDNA_BO_DEV) { + drm_gem_object_put(gobj); + XDNA_ERR(xdna, "Invalid BO type"); + return -EINVAL; + } + + req.cfgs[i] = FIELD_PREP(AIE2_MSG_CFG_CU_PDI_ADDR, + abo->mem.dev_addr >> shift); + req.cfgs[i] |= FIELD_PREP(AIE2_MSG_CFG_CU_FUNC, cu->cu_func); + XDNA_DBG(xdna, "CU %d full addr 0x%llx, cfg 0x%x", i, + abo->mem.dev_addr, req.cfgs[i]); + drm_gem_object_put(gobj); + } + req.num_cus = hwctx->cus->num_cus; + + ret = xdna_send_msg_wait(xdna, chann, &msg); + if (ret == -ETIME) + aie2_destroy_context(xdna->dev_handle, hwctx); + + if (resp.status == AIE2_STATUS_SUCCESS) { + XDNA_DBG(xdna, "Configure %d CUs, ret %d", req.num_cus, ret); + return 0; + } + + XDNA_ERR(xdna, "Command opcode 0x%x failed, status 0x%x ret %d", + msg.opcode, resp.status, ret); + return ret; +} diff --git a/drivers/accel/amdxdna/aie2_pci.h b/drivers/accel/amdxdna/aie2_pci.h index b789286bc9d4..3ac936e2c9d1 100644 --- a/drivers/accel/amdxdna/aie2_pci.h +++ b/drivers/accel/amdxdna/aie2_pci.h @@ -119,6 +119,7 @@ struct rt_config { }; struct amdxdna_hwctx_priv { + struct amdxdna_gem_obj *heap; void *mbox_chann; }; @@ -196,6 +197,8 @@ int aie2_query_firmware_version(struct amdxdna_dev_hdl *ndev, struct amdxdna_fw_ver *fw_ver); int aie2_create_context(struct amdxdna_dev_hdl *ndev, struct amdxdna_hwctx *hwctx); int aie2_destroy_context(struct amdxdna_dev_hdl *ndev, struct amdxdna_hwctx *hwctx); +int aie2_map_host_buf(struct amdxdna_dev_hdl *ndev, u32 context_id, u64 addr, u64 size); +int aie2_config_cu(struct amdxdna_hwctx *hwctx); /* aie2_hwctx.c */ int aie2_hwctx_init(struct amdxdna_hwctx *hwctx); diff --git a/drivers/accel/amdxdna/amdxdna_ctx.h b/drivers/accel/amdxdna/amdxdna_ctx.h index 00b96cf2e9a7..b409d0731ab8 100644 --- a/drivers/accel/amdxdna/amdxdna_ctx.h +++ b/drivers/accel/amdxdna/amdxdna_ctx.h @@ -6,6 +6,16 @@ #ifndef _AMDXDNA_CTX_H_ #define _AMDXDNA_CTX_H_ +/* Exec buffer command header format */ +#define AMDXDNA_CMD_STATE GENMASK(3, 0) +#define AMDXDNA_CMD_EXTRA_CU_MASK GENMASK(11, 10) +#define AMDXDNA_CMD_COUNT GENMASK(22, 12) +#define AMDXDNA_CMD_OPCODE GENMASK(27, 23) +struct amdxdna_cmd { + u32 header; + u32 data[]; +}; + struct amdxdna_hwctx { struct amdxdna_client *client; struct amdxdna_hwctx_priv *priv; diff --git a/drivers/accel/amdxdna/amdxdna_gem.c b/drivers/accel/amdxdna/amdxdna_gem.c new file mode 100644 index 000000000000..f2ba86ae9e1a --- /dev/null +++ b/drivers/accel/amdxdna/amdxdna_gem.c @@ -0,0 +1,621 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024, Advanced Micro Devices, Inc. + */ + +#include +#include +#include +#include +#include +#include +#include + +#include "amdxdna_ctx.h" +#include "amdxdna_gem.h" +#include "amdxdna_pci_drv.h" + +#define XDNA_MAX_CMD_BO_SIZE SZ_32K + +static int +amdxdna_gem_insert_node_locked(struct amdxdna_gem_obj *abo, bool use_vmap) +{ + struct amdxdna_client *client = abo->client; + struct amdxdna_dev *xdna = client->xdna; + struct amdxdna_mem *mem = &abo->mem; + u64 offset; + u32 align; + int ret; + + align = 1 << max(PAGE_SHIFT, xdna->dev_info->dev_mem_buf_shift); + ret = drm_mm_insert_node_generic(&abo->dev_heap->mm, &abo->mm_node, + mem->size, align, + 0, DRM_MM_INSERT_BEST); + if (ret) { + XDNA_ERR(xdna, "Failed to alloc dev bo memory, ret %d", ret); + return ret; + } + + mem->dev_addr = abo->mm_node.start; + offset = mem->dev_addr - abo->dev_heap->mem.dev_addr; + mem->userptr = abo->dev_heap->mem.userptr + offset; + mem->pages = &abo->dev_heap->base.pages[offset >> PAGE_SHIFT]; + mem->nr_pages = mem->size >> PAGE_SHIFT; + + if (use_vmap) { + mem->kva = vmap(mem->pages, mem->nr_pages, VM_MAP, PAGE_KERNEL); + if (!mem->kva) { + XDNA_ERR(xdna, "Failed to vmap"); + drm_mm_remove_node(&abo->mm_node); + return -EFAULT; + } + } + + return 0; +} + +static void amdxdna_gem_obj_free(struct drm_gem_object *gobj) +{ + struct amdxdna_dev *xdna = to_xdna_dev(gobj->dev); + struct amdxdna_gem_obj *abo = to_xdna_obj(gobj); + struct iosys_map map = IOSYS_MAP_INIT_VADDR(abo->mem.kva); + + XDNA_DBG(xdna, "BO type %d xdna_addr 0x%llx", abo->type, abo->mem.dev_addr); + if (abo->pinned) + amdxdna_gem_unpin(abo); + + if (abo->type == AMDXDNA_BO_DEV) { + mutex_lock(&abo->client->mm_lock); + drm_mm_remove_node(&abo->mm_node); + mutex_unlock(&abo->client->mm_lock); + + vunmap(abo->mem.kva); + drm_gem_object_put(to_gobj(abo->dev_heap)); + drm_gem_object_release(gobj); + mutex_destroy(&abo->lock); + kfree(abo); + return; + } + + if (abo->type == AMDXDNA_BO_DEV_HEAP) + drm_mm_takedown(&abo->mm); + + drm_gem_vunmap_unlocked(gobj, &map); + mutex_destroy(&abo->lock); + drm_gem_shmem_free(&abo->base); +} + +static const struct drm_gem_object_funcs amdxdna_gem_dev_obj_funcs = { + .free = amdxdna_gem_obj_free, +}; + +static bool amdxdna_hmm_invalidate(struct mmu_interval_notifier *mni, + const struct mmu_notifier_range *range, + unsigned long cur_seq) +{ + struct amdxdna_gem_obj *abo = container_of(mni, struct amdxdna_gem_obj, + mem.notifier); + struct amdxdna_dev *xdna = to_xdna_dev(to_gobj(abo)->dev); + + XDNA_DBG(xdna, "Invalid range 0x%llx, 0x%lx, type %d", + abo->mem.userptr, abo->mem.size, abo->type); + + if (!mmu_notifier_range_blockable(range)) + return false; + + xdna->dev_info->ops->hmm_invalidate(abo, cur_seq); + + return true; +} + +static const struct mmu_interval_notifier_ops amdxdna_hmm_ops = { + .invalidate = amdxdna_hmm_invalidate, +}; + +static void amdxdna_hmm_unregister(struct amdxdna_gem_obj *abo) +{ + struct amdxdna_dev *xdna = to_xdna_dev(to_gobj(abo)->dev); + + if (!xdna->dev_info->ops->hmm_invalidate) + return; + + mmu_interval_notifier_remove(&abo->mem.notifier); + kvfree(abo->mem.pfns); + abo->mem.pfns = NULL; +} + +static int amdxdna_hmm_register(struct amdxdna_gem_obj *abo, unsigned long addr, + size_t len) +{ + struct amdxdna_dev *xdna = to_xdna_dev(to_gobj(abo)->dev); + u32 nr_pages; + int ret; + + if (!xdna->dev_info->ops->hmm_invalidate) + return 0; + + if (abo->mem.pfns) + return -EEXIST; + + nr_pages = (PAGE_ALIGN(addr + len) - (addr & PAGE_MASK)) >> PAGE_SHIFT; + abo->mem.pfns = kvcalloc(nr_pages, sizeof(*abo->mem.pfns), + GFP_KERNEL); + if (!abo->mem.pfns) + return -ENOMEM; + + ret = mmu_interval_notifier_insert_locked(&abo->mem.notifier, + current->mm, + addr, + len, + &amdxdna_hmm_ops); + if (ret) { + XDNA_ERR(xdna, "Insert mmu notifier failed, ret %d", ret); + kvfree(abo->mem.pfns); + } + abo->mem.userptr = addr; + + return ret; +} + +static int amdxdna_gem_obj_mmap(struct drm_gem_object *gobj, + struct vm_area_struct *vma) +{ + struct amdxdna_gem_obj *abo = to_xdna_obj(gobj); + unsigned long num_pages; + int ret; + + ret = amdxdna_hmm_register(abo, vma->vm_start, gobj->size); + if (ret) + return ret; + + ret = drm_gem_shmem_mmap(&abo->base, vma); + if (ret) + goto hmm_unreg; + + num_pages = gobj->size >> PAGE_SHIFT; + /* Try to insert the pages */ + vm_flags_mod(vma, VM_MIXEDMAP, VM_PFNMAP); + ret = vm_insert_pages(vma, vma->vm_start, abo->base.pages, &num_pages); + if (ret) + XDNA_ERR(abo->client->xdna, "Failed insert pages, ret %d", ret); + + return 0; + +hmm_unreg: + amdxdna_hmm_unregister(abo); + return ret; +} + +static vm_fault_t amdxdna_gem_vm_fault(struct vm_fault *vmf) +{ + return drm_gem_shmem_vm_ops.fault(vmf); +} + +static void amdxdna_gem_vm_open(struct vm_area_struct *vma) +{ + drm_gem_shmem_vm_ops.open(vma); +} + +static void amdxdna_gem_vm_close(struct vm_area_struct *vma) +{ + struct drm_gem_object *gobj = vma->vm_private_data; + + amdxdna_hmm_unregister(to_xdna_obj(gobj)); + drm_gem_shmem_vm_ops.close(vma); +} + +static const struct vm_operations_struct amdxdna_gem_vm_ops = { + .fault = amdxdna_gem_vm_fault, + .open = amdxdna_gem_vm_open, + .close = amdxdna_gem_vm_close, +}; + +static const struct drm_gem_object_funcs amdxdna_gem_shmem_funcs = { + .free = amdxdna_gem_obj_free, + .print_info = drm_gem_shmem_object_print_info, + .pin = drm_gem_shmem_object_pin, + .unpin = drm_gem_shmem_object_unpin, + .get_sg_table = drm_gem_shmem_object_get_sg_table, + .vmap = drm_gem_shmem_object_vmap, + .vunmap = drm_gem_shmem_object_vunmap, + .mmap = amdxdna_gem_obj_mmap, + .vm_ops = &amdxdna_gem_vm_ops, +}; + +static struct amdxdna_gem_obj * +amdxdna_gem_create_obj(struct drm_device *dev, size_t size) +{ + struct amdxdna_gem_obj *abo; + + abo = kzalloc(sizeof(*abo), GFP_KERNEL); + if (!abo) + return ERR_PTR(-ENOMEM); + + abo->pinned = false; + abo->assigned_hwctx = AMDXDNA_INVALID_CTX_HANDLE; + mutex_init(&abo->lock); + + abo->mem.userptr = AMDXDNA_INVALID_ADDR; + abo->mem.dev_addr = AMDXDNA_INVALID_ADDR; + abo->mem.size = size; + + return abo; +} + +/* For drm_driver->gem_create_object callback */ +struct drm_gem_object * +amdxdna_gem_create_object_cb(struct drm_device *dev, size_t size) +{ + struct amdxdna_gem_obj *abo; + + abo = amdxdna_gem_create_obj(dev, size); + if (IS_ERR(abo)) + return ERR_CAST(abo); + + to_gobj(abo)->funcs = &amdxdna_gem_shmem_funcs; + + return to_gobj(abo); +} + +static struct amdxdna_gem_obj * +amdxdna_drm_alloc_shmem(struct drm_device *dev, + struct amdxdna_drm_create_bo *args, + struct drm_file *filp) +{ + struct amdxdna_client *client = filp->driver_priv; + struct drm_gem_shmem_object *shmem; + struct amdxdna_gem_obj *abo; + + shmem = drm_gem_shmem_create(dev, args->size); + if (IS_ERR(shmem)) + return ERR_CAST(shmem); + + shmem->map_wc = false; + + abo = to_xdna_obj(&shmem->base); + abo->client = client; + abo->type = AMDXDNA_BO_SHMEM; + + return abo; +} + +static struct amdxdna_gem_obj * +amdxdna_drm_create_dev_heap(struct drm_device *dev, + struct amdxdna_drm_create_bo *args, + struct drm_file *filp) +{ + struct amdxdna_client *client = filp->driver_priv; + struct amdxdna_dev *xdna = to_xdna_dev(dev); + struct drm_gem_shmem_object *shmem; + struct amdxdna_gem_obj *abo; + int ret; + + if (args->size > xdna->dev_info->dev_mem_size) { + XDNA_DBG(xdna, "Invalid dev heap size 0x%llx, limit 0x%lx", + args->size, xdna->dev_info->dev_mem_size); + return ERR_PTR(-EINVAL); + } + + mutex_lock(&client->mm_lock); + if (client->dev_heap) { + XDNA_DBG(client->xdna, "dev heap is already created"); + ret = -EBUSY; + goto mm_unlock; + } + + shmem = drm_gem_shmem_create(dev, args->size); + if (IS_ERR(shmem)) { + ret = PTR_ERR(shmem); + goto mm_unlock; + } + + shmem->map_wc = false; + abo = to_xdna_obj(&shmem->base); + + abo->type = AMDXDNA_BO_DEV_HEAP; + abo->client = client; + abo->mem.dev_addr = client->xdna->dev_info->dev_mem_base; + drm_mm_init(&abo->mm, abo->mem.dev_addr, abo->mem.size); + + client->dev_heap = abo; + drm_gem_object_get(to_gobj(abo)); + mutex_unlock(&client->mm_lock); + + return abo; + +mm_unlock: + mutex_unlock(&client->mm_lock); + return ERR_PTR(ret); +} + +struct amdxdna_gem_obj * +amdxdna_drm_alloc_dev_bo(struct drm_device *dev, + struct amdxdna_drm_create_bo *args, + struct drm_file *filp, bool use_vmap) +{ + struct amdxdna_client *client = filp->driver_priv; + struct amdxdna_dev *xdna = to_xdna_dev(dev); + size_t aligned_sz = PAGE_ALIGN(args->size); + struct amdxdna_gem_obj *abo, *heap; + int ret; + + mutex_lock(&client->mm_lock); + heap = client->dev_heap; + if (!heap) { + ret = -EINVAL; + goto mm_unlock; + } + + if (heap->mem.userptr == AMDXDNA_INVALID_ADDR) { + XDNA_ERR(xdna, "Invalid dev heap userptr"); + ret = -EINVAL; + goto mm_unlock; + } + + if (args->size > heap->mem.size) { + XDNA_ERR(xdna, "Invalid dev bo size 0x%llx, limit 0x%lx", + args->size, heap->mem.size); + ret = -EINVAL; + goto mm_unlock; + } + + abo = amdxdna_gem_create_obj(&xdna->ddev, aligned_sz); + if (IS_ERR(abo)) { + ret = PTR_ERR(abo); + goto mm_unlock; + } + to_gobj(abo)->funcs = &amdxdna_gem_dev_obj_funcs; + abo->type = AMDXDNA_BO_DEV; + abo->client = client; + abo->dev_heap = heap; + ret = amdxdna_gem_insert_node_locked(abo, use_vmap); + if (ret) { + XDNA_ERR(xdna, "Failed to alloc dev bo memory, ret %d", ret); + goto mm_unlock; + } + + drm_gem_object_get(to_gobj(heap)); + drm_gem_private_object_init(&xdna->ddev, to_gobj(abo), aligned_sz); + + mutex_unlock(&client->mm_lock); + return abo; + +mm_unlock: + mutex_unlock(&client->mm_lock); + return ERR_PTR(ret); +} + +static struct amdxdna_gem_obj * +amdxdna_drm_create_cmd_bo(struct drm_device *dev, + struct amdxdna_drm_create_bo *args, + struct drm_file *filp) +{ + struct amdxdna_dev *xdna = to_xdna_dev(dev); + struct drm_gem_shmem_object *shmem; + struct amdxdna_gem_obj *abo; + struct iosys_map map; + int ret; + + if (args->size > XDNA_MAX_CMD_BO_SIZE) { + XDNA_ERR(xdna, "Command bo size 0x%llx too large", args->size); + return ERR_PTR(-EINVAL); + } + + if (args->size < sizeof(struct amdxdna_cmd)) { + XDNA_DBG(xdna, "Command BO size 0x%llx too small", args->size); + return ERR_PTR(-EINVAL); + } + + shmem = drm_gem_shmem_create(dev, args->size); + if (IS_ERR(shmem)) + return ERR_CAST(shmem); + + shmem->map_wc = false; + abo = to_xdna_obj(&shmem->base); + + abo->type = AMDXDNA_BO_CMD; + abo->client = filp->driver_priv; + + ret = drm_gem_vmap_unlocked(to_gobj(abo), &map); + if (ret) { + XDNA_ERR(xdna, "Vmap cmd bo failed, ret %d", ret); + goto release_obj; + } + abo->mem.kva = map.vaddr; + + return abo; + +release_obj: + drm_gem_shmem_free(shmem); + return ERR_PTR(ret); +} + +int amdxdna_drm_create_bo_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) +{ + struct amdxdna_dev *xdna = to_xdna_dev(dev); + struct amdxdna_drm_create_bo *args = data; + struct amdxdna_gem_obj *abo; + int ret; + + if (args->flags || args->vaddr || !args->size) + return -EINVAL; + + XDNA_DBG(xdna, "BO arg type %d vaddr 0x%llx size 0x%llx flags 0x%llx", + args->type, args->vaddr, args->size, args->flags); + switch (args->type) { + case AMDXDNA_BO_SHMEM: + abo = amdxdna_drm_alloc_shmem(dev, args, filp); + break; + case AMDXDNA_BO_DEV_HEAP: + abo = amdxdna_drm_create_dev_heap(dev, args, filp); + break; + case AMDXDNA_BO_DEV: + abo = amdxdna_drm_alloc_dev_bo(dev, args, filp, false); + break; + case AMDXDNA_BO_CMD: + abo = amdxdna_drm_create_cmd_bo(dev, args, filp); + break; + default: + return -EINVAL; + } + if (IS_ERR(abo)) + return PTR_ERR(abo); + + /* ready to publish object to userspace */ + ret = drm_gem_handle_create(filp, to_gobj(abo), &args->handle); + if (ret) { + XDNA_ERR(xdna, "Create handle failed"); + goto put_obj; + } + + XDNA_DBG(xdna, "BO hdl %d type %d userptr 0x%llx xdna_addr 0x%llx size 0x%lx", + args->handle, args->type, abo->mem.userptr, + abo->mem.dev_addr, abo->mem.size); +put_obj: + /* Dereference object reference. Handle holds it now. */ + drm_gem_object_put(to_gobj(abo)); + return ret; +} + +int amdxdna_gem_pin_nolock(struct amdxdna_gem_obj *abo) +{ + struct amdxdna_dev *xdna = to_xdna_dev(to_gobj(abo)->dev); + int ret; + + switch (abo->type) { + case AMDXDNA_BO_SHMEM: + case AMDXDNA_BO_DEV_HEAP: + ret = drm_gem_shmem_pin(&abo->base); + break; + case AMDXDNA_BO_DEV: + ret = drm_gem_shmem_pin(&abo->dev_heap->base); + break; + default: + ret = -EOPNOTSUPP; + } + + XDNA_DBG(xdna, "BO type %d ret %d", abo->type, ret); + return ret; +} + +int amdxdna_gem_pin(struct amdxdna_gem_obj *abo) +{ + int ret; + + if (abo->type == AMDXDNA_BO_DEV) + abo = abo->dev_heap; + + mutex_lock(&abo->lock); + ret = amdxdna_gem_pin_nolock(abo); + mutex_unlock(&abo->lock); + + return ret; +} + +void amdxdna_gem_unpin(struct amdxdna_gem_obj *abo) +{ + if (abo->type == AMDXDNA_BO_DEV) + abo = abo->dev_heap; + + mutex_lock(&abo->lock); + drm_gem_shmem_unpin(&abo->base); + mutex_unlock(&abo->lock); +} + +struct amdxdna_gem_obj *amdxdna_gem_get_obj(struct amdxdna_client *client, + u32 bo_hdl, u8 bo_type) +{ + struct amdxdna_dev *xdna = client->xdna; + struct amdxdna_gem_obj *abo; + struct drm_gem_object *gobj; + + gobj = drm_gem_object_lookup(client->filp, bo_hdl); + if (!gobj) { + XDNA_DBG(xdna, "Can not find bo %d", bo_hdl); + return NULL; + } + + abo = to_xdna_obj(gobj); + if (bo_type == AMDXDNA_BO_INVALID || abo->type == bo_type) + return abo; + + drm_gem_object_put(gobj); + return NULL; +} + +int amdxdna_drm_get_bo_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) +{ + struct amdxdna_drm_get_bo_info *args = data; + struct amdxdna_dev *xdna = to_xdna_dev(dev); + struct amdxdna_gem_obj *abo; + struct drm_gem_object *gobj; + int ret = 0; + + if (args->ext || args->ext_flags) + return -EINVAL; + + gobj = drm_gem_object_lookup(filp, args->handle); + if (!gobj) { + XDNA_DBG(xdna, "Lookup GEM object %d failed", args->handle); + return -ENOENT; + } + + abo = to_xdna_obj(gobj); + args->vaddr = abo->mem.userptr; + args->xdna_addr = abo->mem.dev_addr; + + if (abo->type != AMDXDNA_BO_DEV) + args->map_offset = drm_vma_node_offset_addr(&gobj->vma_node); + else + args->map_offset = AMDXDNA_INVALID_ADDR; + + XDNA_DBG(xdna, "BO hdl %d map_offset 0x%llx vaddr 0x%llx xdna_addr 0x%llx", + args->handle, args->map_offset, args->vaddr, args->xdna_addr); + + drm_gem_object_put(gobj); + return ret; +} + +/* + * The sync bo ioctl is to make sure the CPU cache is in sync with memory. + * This is required because NPU is not cache coherent device. CPU cache + * flushing/invalidation is expensive so it is best to handle this outside + * of the command submission path. This ioctl allows explicit cache + * flushing/invalidation outside of the critical path. + */ +int amdxdna_drm_sync_bo_ioctl(struct drm_device *dev, + void *data, struct drm_file *filp) +{ + struct amdxdna_dev *xdna = to_xdna_dev(dev); + struct amdxdna_drm_sync_bo *args = data; + struct amdxdna_gem_obj *abo; + struct drm_gem_object *gobj; + int ret; + + gobj = drm_gem_object_lookup(filp, args->handle); + if (!gobj) { + XDNA_ERR(xdna, "Lookup GEM object failed"); + return -ENOENT; + } + abo = to_xdna_obj(gobj); + + ret = amdxdna_gem_pin(abo); + if (ret) { + XDNA_ERR(xdna, "Pin BO %d failed, ret %d", args->handle, ret); + goto put_obj; + } + + if (abo->type == AMDXDNA_BO_DEV) + drm_clflush_pages(abo->mem.pages, abo->mem.nr_pages); + else + drm_clflush_pages(abo->base.pages, gobj->size >> PAGE_SHIFT); + + amdxdna_gem_unpin(abo); + + XDNA_DBG(xdna, "Sync bo %d offset 0x%llx, size 0x%llx\n", + args->handle, args->offset, args->size); + +put_obj: + drm_gem_object_put(gobj); + return ret; +} diff --git a/drivers/accel/amdxdna/amdxdna_gem.h b/drivers/accel/amdxdna/amdxdna_gem.h new file mode 100644 index 000000000000..8ccc0375dd9d --- /dev/null +++ b/drivers/accel/amdxdna/amdxdna_gem.h @@ -0,0 +1,65 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2024, Advanced Micro Devices, Inc. + */ + +#ifndef _AMDXDNA_GEM_H_ +#define _AMDXDNA_GEM_H_ + +struct amdxdna_mem { + u64 userptr; + void *kva; + u64 dev_addr; + size_t size; + struct page **pages; + u32 nr_pages; + struct mmu_interval_notifier notifier; + unsigned long *pfns; + bool map_invalid; +}; + +struct amdxdna_gem_obj { + struct drm_gem_shmem_object base; + struct amdxdna_client *client; + u8 type; + bool pinned; + struct mutex lock; /* Protects: pinned */ + struct amdxdna_mem mem; + + /* Below members is uninitialized when needed */ + struct drm_mm mm; /* For AMDXDNA_BO_DEV_HEAP */ + struct amdxdna_gem_obj *dev_heap; /* For AMDXDNA_BO_DEV */ + struct drm_mm_node mm_node; /* For AMDXDNA_BO_DEV */ + u32 assigned_hwctx; +}; + +#define to_gobj(obj) (&(obj)->base.base) + +static inline struct amdxdna_gem_obj *to_xdna_obj(struct drm_gem_object *gobj) +{ + return container_of(gobj, struct amdxdna_gem_obj, base.base); +} + +struct amdxdna_gem_obj *amdxdna_gem_get_obj(struct amdxdna_client *client, + u32 bo_hdl, u8 bo_type); +static inline void amdxdna_gem_put_obj(struct amdxdna_gem_obj *abo) +{ + drm_gem_object_put(to_gobj(abo)); +} + +struct drm_gem_object * +amdxdna_gem_create_object_cb(struct drm_device *dev, size_t size); +struct amdxdna_gem_obj * +amdxdna_drm_alloc_dev_bo(struct drm_device *dev, + struct amdxdna_drm_create_bo *args, + struct drm_file *filp, bool use_vmap); + +int amdxdna_gem_pin_nolock(struct amdxdna_gem_obj *abo); +int amdxdna_gem_pin(struct amdxdna_gem_obj *abo); +void amdxdna_gem_unpin(struct amdxdna_gem_obj *abo); + +int amdxdna_drm_create_bo_ioctl(struct drm_device *dev, void *data, struct drm_file *filp); +int amdxdna_drm_get_bo_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp); +int amdxdna_drm_sync_bo_ioctl(struct drm_device *dev, void *data, struct drm_file *filp); + +#endif /* _AMDXDNA_GEM_H_ */ diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.c b/drivers/accel/amdxdna/amdxdna_pci_drv.c index dfe682df5640..172109cc9617 100644 --- a/drivers/accel/amdxdna/amdxdna_pci_drv.c +++ b/drivers/accel/amdxdna/amdxdna_pci_drv.c @@ -7,12 +7,14 @@ #include #include #include +#include #include #include #include #include #include "amdxdna_ctx.h" +#include "amdxdna_gem.h" #include "amdxdna_pci_drv.h" /* @@ -63,6 +65,7 @@ static int amdxdna_drm_open(struct drm_device *ddev, struct drm_file *filp) } mutex_init(&client->hwctx_lock); idr_init_base(&client->hwctx_idr, AMDXDNA_INVALID_CTX_HANDLE + 1); + mutex_init(&client->mm_lock); mutex_lock(&xdna->dev_lock); list_add_tail(&client->node, &xdna->client_list); @@ -91,6 +94,9 @@ static void amdxdna_drm_close(struct drm_device *ddev, struct drm_file *filp) idr_destroy(&client->hwctx_idr); mutex_destroy(&client->hwctx_lock); + mutex_destroy(&client->mm_lock); + if (client->dev_heap) + drm_gem_object_put(to_gobj(client->dev_heap)); iommu_sva_unbind_device(client->sva); @@ -123,6 +129,10 @@ static const struct drm_ioctl_desc amdxdna_drm_ioctls[] = { DRM_IOCTL_DEF_DRV(AMDXDNA_CREATE_HWCTX, amdxdna_drm_create_hwctx_ioctl, 0), DRM_IOCTL_DEF_DRV(AMDXDNA_DESTROY_HWCTX, amdxdna_drm_destroy_hwctx_ioctl, 0), DRM_IOCTL_DEF_DRV(AMDXDNA_CONFIG_HWCTX, amdxdna_drm_config_hwctx_ioctl, 0), + /* BO */ + DRM_IOCTL_DEF_DRV(AMDXDNA_CREATE_BO, amdxdna_drm_create_bo_ioctl, 0), + DRM_IOCTL_DEF_DRV(AMDXDNA_GET_BO_INFO, amdxdna_drm_get_bo_info_ioctl, 0), + DRM_IOCTL_DEF_DRV(AMDXDNA_SYNC_BO, amdxdna_drm_sync_bo_ioctl, 0), }; static const struct file_operations amdxdna_fops = { @@ -149,6 +159,8 @@ const struct drm_driver amdxdna_drm_drv = { .postclose = amdxdna_drm_close, .ioctls = amdxdna_drm_ioctls, .num_ioctls = ARRAY_SIZE(amdxdna_drm_ioctls), + + .gem_create_object = amdxdna_gem_create_object_cb, }; static const struct amdxdna_dev_info * diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.h b/drivers/accel/amdxdna/amdxdna_pci_drv.h index 5ec7fe168406..3dddde4ac12a 100644 --- a/drivers/accel/amdxdna/amdxdna_pci_drv.h +++ b/drivers/accel/amdxdna/amdxdna_pci_drv.h @@ -18,6 +18,7 @@ extern const struct drm_driver amdxdna_drm_drv; struct amdxdna_dev; +struct amdxdna_gem_obj; struct amdxdna_hwctx; /* @@ -29,6 +30,7 @@ struct amdxdna_dev_ops { int (*hwctx_init)(struct amdxdna_hwctx *hwctx); void (*hwctx_fini)(struct amdxdna_hwctx *hwctx); int (*hwctx_config)(struct amdxdna_hwctx *hwctx, u32 type, u64 value, void *buf, u32 size); + void (*hmm_invalidate)(struct amdxdna_gem_obj *abo, unsigned long cur_seq); }; /* @@ -89,6 +91,10 @@ struct amdxdna_client { struct idr hwctx_idr; struct amdxdna_dev *xdna; struct drm_file *filp; + + struct mutex mm_lock; /* protect memory related */ + struct amdxdna_gem_obj *dev_heap; + struct iommu_sva *sva; int pasid; }; diff --git a/include/uapi/drm/amdxdna_accel.h b/include/uapi/drm/amdxdna_accel.h index a0dc821c1363..e3e78b79a8e7 100644 --- a/include/uapi/drm/amdxdna_accel.h +++ b/include/uapi/drm/amdxdna_accel.h @@ -13,7 +13,9 @@ extern "C" { #endif +#define AMDXDNA_INVALID_ADDR (~0UL) #define AMDXDNA_INVALID_CTX_HANDLE 0 +#define AMDXDNA_INVALID_BO_HANDLE 0 enum amdxdna_device_type { AMDXDNA_DEV_TYPE_UNKNOWN = -1, @@ -24,6 +26,9 @@ enum amdxdna_drm_ioctl_id { DRM_AMDXDNA_CREATE_HWCTX, DRM_AMDXDNA_DESTROY_HWCTX, DRM_AMDXDNA_CONFIG_HWCTX, + DRM_AMDXDNA_CREATE_BO, + DRM_AMDXDNA_GET_BO_INFO, + DRM_AMDXDNA_SYNC_BO, }; /** @@ -136,6 +141,66 @@ struct amdxdna_drm_config_hwctx { __u32 pad; }; +enum amdxdna_bo_type { + AMDXDNA_BO_INVALID = 0, + AMDXDNA_BO_SHMEM, + AMDXDNA_BO_DEV_HEAP, + AMDXDNA_BO_DEV, + AMDXDNA_BO_CMD, +}; + +/** + * struct amdxdna_drm_create_bo - Create a buffer object. + * @flags: Buffer flags. MBZ. + * @vaddr: User VA of buffer if applied. MBZ. + * @size: Size in bytes. + * @type: Buffer type. + * @handle: Returned DRM buffer object handle. + */ +struct amdxdna_drm_create_bo { + __u64 flags; + __u64 vaddr; + __u64 size; + __u32 type; + __u32 handle; +}; + +/** + * struct amdxdna_drm_get_bo_info - Get buffer object information. + * @ext: MBZ. + * @ext_flags: MBZ. + * @handle: DRM buffer object handle. + * @pad: Structure padding. + * @map_offset: Returned DRM fake offset for mmap(). + * @vaddr: Returned user VA of buffer. 0 in case user needs mmap(). + * @xdna_addr: Returned XDNA device virtual address. + */ +struct amdxdna_drm_get_bo_info { + __u64 ext; + __u64 ext_flags; + __u32 handle; + __u32 pad; + __u64 map_offset; + __u64 vaddr; + __u64 xdna_addr; +}; + +/** + * struct amdxdna_drm_sync_bo - Sync buffer object. + * @handle: Buffer object handle. + * @direction: Direction of sync, can be from device or to device. + * @offset: Offset in the buffer to sync. + * @size: Size in bytes. + */ +struct amdxdna_drm_sync_bo { + __u32 handle; +#define SYNC_DIRECT_TO_DEVICE 0U +#define SYNC_DIRECT_FROM_DEVICE 1U + __u32 direction; + __u64 offset; + __u64 size; +}; + #define DRM_IOCTL_AMDXDNA_CREATE_HWCTX \ DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDXDNA_CREATE_HWCTX, \ struct amdxdna_drm_create_hwctx) @@ -148,6 +213,18 @@ struct amdxdna_drm_config_hwctx { DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDXDNA_CONFIG_HWCTX, \ struct amdxdna_drm_config_hwctx) +#define DRM_IOCTL_AMDXDNA_CREATE_BO \ + DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDXDNA_CREATE_BO, \ + struct amdxdna_drm_create_bo) + +#define DRM_IOCTL_AMDXDNA_GET_BO_INFO \ + DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDXDNA_GET_BO_INFO, \ + struct amdxdna_drm_get_bo_info) + +#define DRM_IOCTL_AMDXDNA_SYNC_BO \ + DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDXDNA_SYNC_BO, \ + struct amdxdna_drm_sync_bo) + #if defined(__cplusplus) } /* extern c end */ #endif -- cgit v1.2.3 From aac243092b707bb3018e951d470cc1a9bcbaba6c Mon Sep 17 00:00:00 2001 From: Lizhi Hou Date: Mon, 18 Nov 2024 09:29:39 -0800 Subject: accel/amdxdna: Add command execution Add interfaces for user application to submit command and wait for its completion. Co-developed-by: Min Ma Signed-off-by: Min Ma Reviewed-by: Jeffrey Hugo Signed-off-by: Lizhi Hou Signed-off-by: Jeffrey Hugo Link: https://patchwork.freedesktop.org/patch/msgid/20241118172942.2014541-8-lizhi.hou@amd.com --- drivers/accel/amdxdna/aie2_ctx.c | 607 ++++++++++++++++++++++++- drivers/accel/amdxdna/aie2_message.c | 343 ++++++++++++++ drivers/accel/amdxdna/aie2_pci.c | 5 + drivers/accel/amdxdna/aie2_pci.h | 39 ++ drivers/accel/amdxdna/aie2_psp.c | 2 + drivers/accel/amdxdna/aie2_smu.c | 2 + drivers/accel/amdxdna/amdxdna_ctx.c | 320 ++++++++++++- drivers/accel/amdxdna/amdxdna_ctx.h | 111 +++++ drivers/accel/amdxdna/amdxdna_gem.c | 1 + drivers/accel/amdxdna/amdxdna_mailbox_helper.c | 5 + drivers/accel/amdxdna/amdxdna_pci_drv.c | 12 + drivers/accel/amdxdna/amdxdna_pci_drv.h | 5 + drivers/accel/amdxdna/amdxdna_sysfs.c | 5 + drivers/accel/amdxdna/npu1_regs.c | 1 + drivers/accel/amdxdna/npu2_regs.c | 1 + drivers/accel/amdxdna/npu4_regs.c | 1 + drivers/accel/amdxdna/npu5_regs.c | 1 + include/trace/events/amdxdna.h | 41 ++ include/uapi/drm/amdxdna_accel.h | 38 ++ 19 files changed, 1531 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/drivers/accel/amdxdna/aie2_ctx.c b/drivers/accel/amdxdna/aie2_ctx.c index ae8a91dad042..2040a01256eb 100644 --- a/drivers/accel/amdxdna/aie2_ctx.c +++ b/drivers/accel/amdxdna/aie2_ctx.c @@ -8,8 +8,12 @@ #include #include #include +#include +#include #include +#include +#include "aie2_msg_priv.h" #include "aie2_pci.h" #include "aie2_solver.h" #include "amdxdna_ctx.h" @@ -17,6 +21,321 @@ #include "amdxdna_mailbox.h" #include "amdxdna_pci_drv.h" +bool force_cmdlist; +module_param(force_cmdlist, bool, 0600); +MODULE_PARM_DESC(force_cmdlist, "Force use command list (Default false)"); + +#define HWCTX_MAX_TIMEOUT 60000 /* milliseconds */ + +static void aie2_job_release(struct kref *ref) +{ + struct amdxdna_sched_job *job; + + job = container_of(ref, struct amdxdna_sched_job, refcnt); + amdxdna_sched_job_cleanup(job); + if (job->out_fence) + dma_fence_put(job->out_fence); + kfree(job); +} + +static void aie2_job_put(struct amdxdna_sched_job *job) +{ + kref_put(&job->refcnt, aie2_job_release); +} + +/* The bad_job is used in aie2_sched_job_timedout, otherwise, set it to NULL */ +static void aie2_hwctx_stop(struct amdxdna_dev *xdna, struct amdxdna_hwctx *hwctx, + struct drm_sched_job *bad_job) +{ + drm_sched_stop(&hwctx->priv->sched, bad_job); + aie2_destroy_context(xdna->dev_handle, hwctx); +} + +static int aie2_hwctx_restart(struct amdxdna_dev *xdna, struct amdxdna_hwctx *hwctx) +{ + struct amdxdna_gem_obj *heap = hwctx->priv->heap; + int ret; + + ret = aie2_create_context(xdna->dev_handle, hwctx); + if (ret) { + XDNA_ERR(xdna, "Create hwctx failed, ret %d", ret); + goto out; + } + + ret = aie2_map_host_buf(xdna->dev_handle, hwctx->fw_ctx_id, + heap->mem.userptr, heap->mem.size); + if (ret) { + XDNA_ERR(xdna, "Map host buf failed, ret %d", ret); + goto out; + } + + if (hwctx->status != HWCTX_STAT_READY) { + XDNA_DBG(xdna, "hwctx is not ready, status %d", hwctx->status); + goto out; + } + + ret = aie2_config_cu(hwctx); + if (ret) { + XDNA_ERR(xdna, "Config cu failed, ret %d", ret); + goto out; + } + +out: + drm_sched_start(&hwctx->priv->sched, 0); + XDNA_DBG(xdna, "%s restarted, ret %d", hwctx->name, ret); + return ret; +} + +void aie2_restart_ctx(struct amdxdna_client *client) +{ + struct amdxdna_dev *xdna = client->xdna; + struct amdxdna_hwctx *hwctx; + int next = 0; + + drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock)); + mutex_lock(&client->hwctx_lock); + idr_for_each_entry_continue(&client->hwctx_idr, hwctx, next) { + if (hwctx->status != HWCTX_STAT_STOP) + continue; + + hwctx->status = hwctx->old_status; + XDNA_DBG(xdna, "Resetting %s", hwctx->name); + aie2_hwctx_restart(xdna, hwctx); + } + mutex_unlock(&client->hwctx_lock); +} + +static struct dma_fence *aie2_cmd_get_out_fence(struct amdxdna_hwctx *hwctx, u64 seq) +{ + struct dma_fence *fence, *out_fence = NULL; + int ret; + + fence = drm_syncobj_fence_get(hwctx->priv->syncobj); + if (!fence) + return NULL; + + ret = dma_fence_chain_find_seqno(&fence, seq); + if (ret) + goto out; + + out_fence = dma_fence_get(dma_fence_chain_contained(fence)); + +out: + dma_fence_put(fence); + return out_fence; +} + +static void aie2_hwctx_wait_for_idle(struct amdxdna_hwctx *hwctx) +{ + struct dma_fence *fence; + + fence = aie2_cmd_get_out_fence(hwctx, hwctx->priv->seq - 1); + if (!fence) + return; + + dma_fence_wait(fence, false); + dma_fence_put(fence); +} + +static void +aie2_sched_notify(struct amdxdna_sched_job *job) +{ + struct dma_fence *fence = job->fence; + + trace_xdna_job(&job->base, job->hwctx->name, "signaled fence", job->seq); + job->hwctx->priv->completed++; + dma_fence_signal(fence); + + up(&job->hwctx->priv->job_sem); + job->job_done = true; + dma_fence_put(fence); + mmput(job->mm); + aie2_job_put(job); +} + +static int +aie2_sched_resp_handler(void *handle, const u32 *data, size_t size) +{ + struct amdxdna_sched_job *job = handle; + struct amdxdna_gem_obj *cmd_abo; + u32 ret = 0; + u32 status; + + cmd_abo = job->cmd_bo; + + if (unlikely(!data)) + goto out; + + if (unlikely(size != sizeof(u32))) { + amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_ABORT); + ret = -EINVAL; + goto out; + } + + status = *data; + XDNA_DBG(job->hwctx->client->xdna, "Resp status 0x%x", status); + if (status == AIE2_STATUS_SUCCESS) + amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_COMPLETED); + else + amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_ERROR); + +out: + aie2_sched_notify(job); + return ret; +} + +static int +aie2_sched_nocmd_resp_handler(void *handle, const u32 *data, size_t size) +{ + struct amdxdna_sched_job *job = handle; + u32 ret = 0; + u32 status; + + if (unlikely(!data)) + goto out; + + if (unlikely(size != sizeof(u32))) { + ret = -EINVAL; + goto out; + } + + status = *data; + XDNA_DBG(job->hwctx->client->xdna, "Resp status 0x%x", status); + +out: + aie2_sched_notify(job); + return ret; +} + +static int +aie2_sched_cmdlist_resp_handler(void *handle, const u32 *data, size_t size) +{ + struct amdxdna_sched_job *job = handle; + struct amdxdna_gem_obj *cmd_abo; + struct cmd_chain_resp *resp; + struct amdxdna_dev *xdna; + u32 fail_cmd_status; + u32 fail_cmd_idx; + u32 ret = 0; + + cmd_abo = job->cmd_bo; + if (unlikely(!data) || unlikely(size != sizeof(u32) * 3)) { + amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_ABORT); + ret = -EINVAL; + goto out; + } + + resp = (struct cmd_chain_resp *)data; + xdna = job->hwctx->client->xdna; + XDNA_DBG(xdna, "Status 0x%x", resp->status); + if (resp->status == AIE2_STATUS_SUCCESS) { + amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_COMPLETED); + goto out; + } + + /* Slow path to handle error, read from ringbuf on BAR */ + fail_cmd_idx = resp->fail_cmd_idx; + fail_cmd_status = resp->fail_cmd_status; + XDNA_DBG(xdna, "Failed cmd idx %d, status 0x%x", + fail_cmd_idx, fail_cmd_status); + + if (fail_cmd_status == AIE2_STATUS_SUCCESS) { + amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_ABORT); + ret = -EINVAL; + goto out; + } + amdxdna_cmd_set_state(cmd_abo, fail_cmd_status); + + if (amdxdna_cmd_get_op(cmd_abo) == ERT_CMD_CHAIN) { + struct amdxdna_cmd_chain *cc = amdxdna_cmd_get_payload(cmd_abo, NULL); + + cc->error_index = fail_cmd_idx; + if (cc->error_index >= cc->command_count) + cc->error_index = 0; + } +out: + aie2_sched_notify(job); + return ret; +} + +static struct dma_fence * +aie2_sched_job_run(struct drm_sched_job *sched_job) +{ + struct amdxdna_sched_job *job = drm_job_to_xdna_job(sched_job); + struct amdxdna_gem_obj *cmd_abo = job->cmd_bo; + struct amdxdna_hwctx *hwctx = job->hwctx; + struct dma_fence *fence; + int ret; + + if (!mmget_not_zero(job->mm)) + return ERR_PTR(-ESRCH); + + kref_get(&job->refcnt); + fence = dma_fence_get(job->fence); + + if (unlikely(!cmd_abo)) { + ret = aie2_sync_bo(hwctx, job, aie2_sched_nocmd_resp_handler); + goto out; + } + + amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_NEW); + + if (amdxdna_cmd_get_op(cmd_abo) == ERT_CMD_CHAIN) + ret = aie2_cmdlist_multi_execbuf(hwctx, job, aie2_sched_cmdlist_resp_handler); + else if (force_cmdlist) + ret = aie2_cmdlist_single_execbuf(hwctx, job, aie2_sched_cmdlist_resp_handler); + else + ret = aie2_execbuf(hwctx, job, aie2_sched_resp_handler); + +out: + if (ret) { + dma_fence_put(job->fence); + aie2_job_put(job); + mmput(job->mm); + fence = ERR_PTR(ret); + } + trace_xdna_job(sched_job, hwctx->name, "sent to device", job->seq); + + return fence; +} + +static void aie2_sched_job_free(struct drm_sched_job *sched_job) +{ + struct amdxdna_sched_job *job = drm_job_to_xdna_job(sched_job); + struct amdxdna_hwctx *hwctx = job->hwctx; + + trace_xdna_job(sched_job, hwctx->name, "job free", job->seq); + if (!job->job_done) + up(&hwctx->priv->job_sem); + + drm_sched_job_cleanup(sched_job); + aie2_job_put(job); +} + +static enum drm_gpu_sched_stat +aie2_sched_job_timedout(struct drm_sched_job *sched_job) +{ + struct amdxdna_sched_job *job = drm_job_to_xdna_job(sched_job); + struct amdxdna_hwctx *hwctx = job->hwctx; + struct amdxdna_dev *xdna; + + xdna = hwctx->client->xdna; + trace_xdna_job(sched_job, hwctx->name, "job timedout", job->seq); + mutex_lock(&xdna->dev_lock); + aie2_hwctx_stop(xdna, hwctx, sched_job); + + aie2_hwctx_restart(xdna, hwctx); + mutex_unlock(&xdna->dev_lock); + + return DRM_GPU_SCHED_STAT_NOMINAL; +} + +const struct drm_sched_backend_ops sched_ops = { + .run_job = aie2_sched_job_run, + .free_job = aie2_sched_job_free, + .timedout_job = aie2_sched_job_timedout, +}; + static int aie2_hwctx_col_list(struct amdxdna_hwctx *hwctx) { struct amdxdna_dev *xdna = hwctx->client->xdna; @@ -126,13 +445,50 @@ static void aie2_release_resource(struct amdxdna_hwctx *hwctx) XDNA_ERR(xdna, "Release AIE resource failed, ret %d", ret); } +static int aie2_ctx_syncobj_create(struct amdxdna_hwctx *hwctx) +{ + struct amdxdna_dev *xdna = hwctx->client->xdna; + struct drm_file *filp = hwctx->client->filp; + struct drm_syncobj *syncobj; + u32 hdl; + int ret; + + hwctx->syncobj_hdl = AMDXDNA_INVALID_FENCE_HANDLE; + + ret = drm_syncobj_create(&syncobj, 0, NULL); + if (ret) { + XDNA_ERR(xdna, "Create ctx syncobj failed, ret %d", ret); + return ret; + } + ret = drm_syncobj_get_handle(filp, syncobj, &hdl); + if (ret) { + drm_syncobj_put(syncobj); + XDNA_ERR(xdna, "Create ctx syncobj handle failed, ret %d", ret); + return ret; + } + hwctx->priv->syncobj = syncobj; + hwctx->syncobj_hdl = hdl; + + return 0; +} + +static void aie2_ctx_syncobj_destroy(struct amdxdna_hwctx *hwctx) +{ + /* + * The syncobj_hdl is owned by user space and will be cleaned up + * separately. + */ + drm_syncobj_put(hwctx->priv->syncobj); +} + int aie2_hwctx_init(struct amdxdna_hwctx *hwctx) { struct amdxdna_client *client = hwctx->client; struct amdxdna_dev *xdna = client->xdna; + struct drm_gpu_scheduler *sched; struct amdxdna_hwctx_priv *priv; struct amdxdna_gem_obj *heap; - int ret; + int i, ret; priv = kzalloc(sizeof(*hwctx->priv), GFP_KERNEL); if (!priv) @@ -150,6 +506,7 @@ int aie2_hwctx_init(struct amdxdna_hwctx *hwctx) drm_gem_object_get(to_gobj(heap)); mutex_unlock(&client->mm_lock); priv->heap = heap; + sema_init(&priv->job_sem, HWCTX_MAX_CMDS); ret = amdxdna_gem_pin(heap); if (ret) { @@ -157,10 +514,52 @@ int aie2_hwctx_init(struct amdxdna_hwctx *hwctx) goto put_heap; } + for (i = 0; i < ARRAY_SIZE(priv->cmd_buf); i++) { + struct amdxdna_gem_obj *abo; + struct amdxdna_drm_create_bo args = { + .flags = 0, + .type = AMDXDNA_BO_DEV, + .vaddr = 0, + .size = MAX_CHAIN_CMDBUF_SIZE, + }; + + abo = amdxdna_drm_alloc_dev_bo(&xdna->ddev, &args, client->filp, true); + if (IS_ERR(abo)) { + ret = PTR_ERR(abo); + goto free_cmd_bufs; + } + + XDNA_DBG(xdna, "Command buf %d addr 0x%llx size 0x%lx", + i, abo->mem.dev_addr, abo->mem.size); + priv->cmd_buf[i] = abo; + } + + sched = &priv->sched; + mutex_init(&priv->io_lock); + + fs_reclaim_acquire(GFP_KERNEL); + might_lock(&priv->io_lock); + fs_reclaim_release(GFP_KERNEL); + + ret = drm_sched_init(sched, &sched_ops, NULL, DRM_SCHED_PRIORITY_COUNT, + HWCTX_MAX_CMDS, 0, msecs_to_jiffies(HWCTX_MAX_TIMEOUT), + NULL, NULL, hwctx->name, xdna->ddev.dev); + if (ret) { + XDNA_ERR(xdna, "Failed to init DRM scheduler. ret %d", ret); + goto free_cmd_bufs; + } + + ret = drm_sched_entity_init(&priv->entity, DRM_SCHED_PRIORITY_NORMAL, + &sched, 1, NULL); + if (ret) { + XDNA_ERR(xdna, "Failed to initial sched entiry. ret %d", ret); + goto free_sched; + } + ret = aie2_hwctx_col_list(hwctx); if (ret) { XDNA_ERR(xdna, "Create col list failed, ret %d", ret); - goto unpin; + goto free_entity; } ret = aie2_alloc_resource(hwctx); @@ -175,6 +574,13 @@ int aie2_hwctx_init(struct amdxdna_hwctx *hwctx) XDNA_ERR(xdna, "Map host buffer failed, ret %d", ret); goto release_resource; } + + ret = aie2_ctx_syncobj_create(hwctx); + if (ret) { + XDNA_ERR(xdna, "Create syncobj failed, ret %d", ret); + goto release_resource; + } + hwctx->status = HWCTX_STAT_INIT; XDNA_DBG(xdna, "hwctx %s init completed", hwctx->name); @@ -185,7 +591,16 @@ release_resource: aie2_release_resource(hwctx); free_col_list: kfree(hwctx->col_list); -unpin: +free_entity: + drm_sched_entity_destroy(&priv->entity); +free_sched: + drm_sched_fini(&priv->sched); +free_cmd_bufs: + for (i = 0; i < ARRAY_SIZE(priv->cmd_buf); i++) { + if (!priv->cmd_buf[i]) + continue; + drm_gem_object_put(to_gobj(priv->cmd_buf[i])); + } amdxdna_gem_unpin(heap); put_heap: drm_gem_object_put(to_gobj(heap)); @@ -196,11 +611,35 @@ free_priv: void aie2_hwctx_fini(struct amdxdna_hwctx *hwctx) { + struct amdxdna_dev *xdna; + int idx; + + xdna = hwctx->client->xdna; + drm_sched_wqueue_stop(&hwctx->priv->sched); + + /* Now, scheduler will not send command to device. */ aie2_release_resource(hwctx); + /* + * All submitted commands are aborted. + * Restart scheduler queues to cleanup jobs. The amdxdna_sched_job_run() + * will return NODEV if it is called. + */ + drm_sched_wqueue_start(&hwctx->priv->sched); + + aie2_hwctx_wait_for_idle(hwctx); + drm_sched_entity_destroy(&hwctx->priv->entity); + drm_sched_fini(&hwctx->priv->sched); + aie2_ctx_syncobj_destroy(hwctx); + + XDNA_DBG(xdna, "%s sequence number %lld", hwctx->name, hwctx->priv->seq); + + for (idx = 0; idx < ARRAY_SIZE(hwctx->priv->cmd_buf); idx++) + drm_gem_object_put(to_gobj(hwctx->priv->cmd_buf[idx])); amdxdna_gem_unpin(hwctx->priv->heap); drm_gem_object_put(to_gobj(hwctx->priv->heap)); + mutex_destroy(&hwctx->priv->io_lock); kfree(hwctx->col_list); kfree(hwctx->priv); kfree(hwctx->cus); @@ -267,3 +706,165 @@ int aie2_hwctx_config(struct amdxdna_hwctx *hwctx, u32 type, u64 value, void *bu return -EOPNOTSUPP; } } + +static int aie2_populate_range(struct amdxdna_gem_obj *abo) +{ + struct amdxdna_dev *xdna = to_xdna_dev(to_gobj(abo)->dev); + struct mm_struct *mm = abo->mem.notifier.mm; + struct hmm_range range = { 0 }; + unsigned long timeout; + int ret; + + XDNA_INFO_ONCE(xdna, "populate memory range %llx size %lx", + abo->mem.userptr, abo->mem.size); + range.notifier = &abo->mem.notifier; + range.start = abo->mem.userptr; + range.end = abo->mem.userptr + abo->mem.size; + range.hmm_pfns = abo->mem.pfns; + range.default_flags = HMM_PFN_REQ_FAULT; + + if (!mmget_not_zero(mm)) + return -EFAULT; + + timeout = jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT); +again: + range.notifier_seq = mmu_interval_read_begin(&abo->mem.notifier); + mmap_read_lock(mm); + ret = hmm_range_fault(&range); + mmap_read_unlock(mm); + if (ret) { + if (time_after(jiffies, timeout)) { + ret = -ETIME; + goto put_mm; + } + + if (ret == -EBUSY) + goto again; + + goto put_mm; + } + + down_read(&xdna->notifier_lock); + if (mmu_interval_read_retry(&abo->mem.notifier, range.notifier_seq)) { + up_read(&xdna->notifier_lock); + goto again; + } + abo->mem.map_invalid = false; + up_read(&xdna->notifier_lock); + +put_mm: + mmput(mm); + return ret; +} + +int aie2_cmd_submit(struct amdxdna_hwctx *hwctx, struct amdxdna_sched_job *job, u64 *seq) +{ + struct amdxdna_dev *xdna = hwctx->client->xdna; + struct ww_acquire_ctx acquire_ctx; + struct dma_fence_chain *chain; + struct amdxdna_gem_obj *abo; + unsigned long timeout = 0; + int ret, i; + + ret = down_interruptible(&hwctx->priv->job_sem); + if (ret) { + XDNA_ERR(xdna, "Grab job sem failed, ret %d", ret); + return ret; + } + + chain = dma_fence_chain_alloc(); + if (!chain) { + XDNA_ERR(xdna, "Alloc fence chain failed"); + ret = -ENOMEM; + goto up_sem; + } + + ret = drm_sched_job_init(&job->base, &hwctx->priv->entity, 1, hwctx); + if (ret) { + XDNA_ERR(xdna, "DRM job init failed, ret %d", ret); + goto free_chain; + } + +retry: + ret = drm_gem_lock_reservations(job->bos, job->bo_cnt, &acquire_ctx); + if (ret) { + XDNA_WARN(xdna, "Failed to lock BOs, ret %d", ret); + goto cleanup_job; + } + + for (i = 0; i < job->bo_cnt; i++) { + ret = dma_resv_reserve_fences(job->bos[i]->resv, 1); + if (ret) { + XDNA_WARN(xdna, "Failed to reserve fences %d", ret); + drm_gem_unlock_reservations(job->bos, job->bo_cnt, &acquire_ctx); + goto cleanup_job; + } + } + + down_read(&xdna->notifier_lock); + for (i = 0; i < job->bo_cnt; i++) { + abo = to_xdna_obj(job->bos[i]); + if (abo->mem.map_invalid) { + up_read(&xdna->notifier_lock); + drm_gem_unlock_reservations(job->bos, job->bo_cnt, &acquire_ctx); + if (!timeout) { + timeout = jiffies + + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT); + } else if (time_after(jiffies, timeout)) { + ret = -ETIME; + goto cleanup_job; + } + + ret = aie2_populate_range(abo); + if (ret) + goto cleanup_job; + goto retry; + } + } + + mutex_lock(&hwctx->priv->io_lock); + drm_sched_job_arm(&job->base); + job->out_fence = dma_fence_get(&job->base.s_fence->finished); + for (i = 0; i < job->bo_cnt; i++) + dma_resv_add_fence(job->bos[i]->resv, job->out_fence, DMA_RESV_USAGE_WRITE); + job->seq = hwctx->priv->seq++; + kref_get(&job->refcnt); + drm_sched_entity_push_job(&job->base); + + *seq = job->seq; + drm_syncobj_add_point(hwctx->priv->syncobj, chain, job->out_fence, *seq); + mutex_unlock(&hwctx->priv->io_lock); + + up_read(&xdna->notifier_lock); + drm_gem_unlock_reservations(job->bos, job->bo_cnt, &acquire_ctx); + + aie2_job_put(job); + + return 0; + +cleanup_job: + drm_sched_job_cleanup(&job->base); +free_chain: + dma_fence_chain_free(chain); +up_sem: + up(&hwctx->priv->job_sem); + job->job_done = true; + return ret; +} + +void aie2_hmm_invalidate(struct amdxdna_gem_obj *abo, + unsigned long cur_seq) +{ + struct amdxdna_dev *xdna = to_xdna_dev(to_gobj(abo)->dev); + struct drm_gem_object *gobj = to_gobj(abo); + long ret; + + down_write(&xdna->notifier_lock); + abo->mem.map_invalid = true; + mmu_interval_set_seq(&abo->mem.notifier, cur_seq); + up_write(&xdna->notifier_lock); + ret = dma_resv_wait_timeout(gobj->resv, DMA_RESV_USAGE_BOOKKEEP, + true, MAX_SCHEDULE_TIMEOUT); + if (!ret || ret == -ERESTARTSYS) + XDNA_ERR(xdna, "Failed to wait for bo, ret %ld", ret); +} diff --git a/drivers/accel/amdxdna/aie2_message.c b/drivers/accel/amdxdna/aie2_message.c index 40d9e4261e8b..db62954eb378 100644 --- a/drivers/accel/amdxdna/aie2_message.c +++ b/drivers/accel/amdxdna/aie2_message.c @@ -4,10 +4,12 @@ */ #include +#include #include #include #include #include +#include #include #include #include @@ -362,3 +364,344 @@ int aie2_config_cu(struct amdxdna_hwctx *hwctx) msg.opcode, resp.status, ret); return ret; } + +int aie2_execbuf(struct amdxdna_hwctx *hwctx, struct amdxdna_sched_job *job, + int (*notify_cb)(void *, const u32 *, size_t)) +{ + struct mailbox_channel *chann = hwctx->priv->mbox_chann; + struct amdxdna_dev *xdna = hwctx->client->xdna; + struct amdxdna_gem_obj *cmd_abo = job->cmd_bo; + union { + struct execute_buffer_req ebuf; + struct exec_dpu_req dpu; + } req; + struct xdna_mailbox_msg msg; + u32 payload_len; + void *payload; + int cu_idx; + int ret; + u32 op; + + if (!chann) + return -ENODEV; + + payload = amdxdna_cmd_get_payload(cmd_abo, &payload_len); + if (!payload) { + XDNA_ERR(xdna, "Invalid command, cannot get payload"); + return -EINVAL; + } + + cu_idx = amdxdna_cmd_get_cu_idx(cmd_abo); + if (cu_idx < 0) { + XDNA_DBG(xdna, "Invalid cu idx"); + return -EINVAL; + } + + op = amdxdna_cmd_get_op(cmd_abo); + switch (op) { + case ERT_START_CU: + if (unlikely(payload_len > sizeof(req.ebuf.payload))) + XDNA_DBG(xdna, "Invalid ebuf payload len: %d", payload_len); + req.ebuf.cu_idx = cu_idx; + memcpy(req.ebuf.payload, payload, sizeof(req.ebuf.payload)); + msg.send_size = sizeof(req.ebuf); + msg.opcode = MSG_OP_EXECUTE_BUFFER_CF; + break; + case ERT_START_NPU: { + struct amdxdna_cmd_start_npu *sn = payload; + + if (unlikely(payload_len - sizeof(*sn) > sizeof(req.dpu.payload))) + XDNA_DBG(xdna, "Invalid dpu payload len: %d", payload_len); + req.dpu.inst_buf_addr = sn->buffer; + req.dpu.inst_size = sn->buffer_size; + req.dpu.inst_prop_cnt = sn->prop_count; + req.dpu.cu_idx = cu_idx; + memcpy(req.dpu.payload, sn->prop_args, sizeof(req.dpu.payload)); + msg.send_size = sizeof(req.dpu); + msg.opcode = MSG_OP_EXEC_DPU; + break; + } + default: + XDNA_DBG(xdna, "Invalid ERT cmd op code: %d", op); + return -EINVAL; + } + msg.handle = job; + msg.notify_cb = notify_cb; + msg.send_data = (u8 *)&req; + print_hex_dump_debug("cmd: ", DUMP_PREFIX_OFFSET, 16, 4, &req, + 0x40, false); + + ret = xdna_mailbox_send_msg(chann, &msg, TX_TIMEOUT); + if (ret) { + XDNA_ERR(xdna, "Send message failed"); + return ret; + } + + return 0; +} + +static int +aie2_cmdlist_fill_one_slot_cf(void *cmd_buf, u32 offset, + struct amdxdna_gem_obj *abo, u32 *size) +{ + struct cmd_chain_slot_execbuf_cf *buf = cmd_buf + offset; + int cu_idx = amdxdna_cmd_get_cu_idx(abo); + u32 payload_len; + void *payload; + + if (cu_idx < 0) + return -EINVAL; + + payload = amdxdna_cmd_get_payload(abo, &payload_len); + if (!payload) + return -EINVAL; + + if (!slot_cf_has_space(offset, payload_len)) + return -ENOSPC; + + buf->cu_idx = cu_idx; + buf->arg_cnt = payload_len / sizeof(u32); + memcpy(buf->args, payload, payload_len); + /* Accurate buf size to hint firmware to do necessary copy */ + *size = sizeof(*buf) + payload_len; + return 0; +} + +static int +aie2_cmdlist_fill_one_slot_dpu(void *cmd_buf, u32 offset, + struct amdxdna_gem_obj *abo, u32 *size) +{ + struct cmd_chain_slot_dpu *buf = cmd_buf + offset; + int cu_idx = amdxdna_cmd_get_cu_idx(abo); + struct amdxdna_cmd_start_npu *sn; + u32 payload_len; + void *payload; + u32 arg_sz; + + if (cu_idx < 0) + return -EINVAL; + + payload = amdxdna_cmd_get_payload(abo, &payload_len); + if (!payload) + return -EINVAL; + sn = payload; + arg_sz = payload_len - sizeof(*sn); + if (payload_len < sizeof(*sn) || arg_sz > MAX_DPU_ARGS_SIZE) + return -EINVAL; + + if (!slot_dpu_has_space(offset, arg_sz)) + return -ENOSPC; + + buf->inst_buf_addr = sn->buffer; + buf->inst_size = sn->buffer_size; + buf->inst_prop_cnt = sn->prop_count; + buf->cu_idx = cu_idx; + buf->arg_cnt = arg_sz / sizeof(u32); + memcpy(buf->args, sn->prop_args, arg_sz); + + /* Accurate buf size to hint firmware to do necessary copy */ + *size += sizeof(*buf) + arg_sz; + return 0; +} + +static int +aie2_cmdlist_fill_one_slot(u32 op, struct amdxdna_gem_obj *cmdbuf_abo, u32 offset, + struct amdxdna_gem_obj *abo, u32 *size) +{ + u32 this_op = amdxdna_cmd_get_op(abo); + void *cmd_buf = cmdbuf_abo->mem.kva; + int ret; + + if (this_op != op) { + ret = -EINVAL; + goto done; + } + + switch (op) { + case ERT_START_CU: + ret = aie2_cmdlist_fill_one_slot_cf(cmd_buf, offset, abo, size); + break; + case ERT_START_NPU: + ret = aie2_cmdlist_fill_one_slot_dpu(cmd_buf, offset, abo, size); + break; + default: + ret = -EOPNOTSUPP; + } + +done: + if (ret) { + XDNA_ERR(abo->client->xdna, "Can't fill slot for cmd op %d ret %d", + op, ret); + } + return ret; +} + +static inline struct amdxdna_gem_obj * +aie2_cmdlist_get_cmd_buf(struct amdxdna_sched_job *job) +{ + int idx = get_job_idx(job->seq); + + return job->hwctx->priv->cmd_buf[idx]; +} + +static void +aie2_cmdlist_prepare_request(struct cmd_chain_req *req, + struct amdxdna_gem_obj *cmdbuf_abo, u32 size, u32 cnt) +{ + req->buf_addr = cmdbuf_abo->mem.dev_addr; + req->buf_size = size; + req->count = cnt; + drm_clflush_virt_range(cmdbuf_abo->mem.kva, size); + XDNA_DBG(cmdbuf_abo->client->xdna, "Command buf addr 0x%llx size 0x%x count %d", + req->buf_addr, size, cnt); +} + +static inline u32 +aie2_cmd_op_to_msg_op(u32 op) +{ + switch (op) { + case ERT_START_CU: + return MSG_OP_CHAIN_EXEC_BUFFER_CF; + case ERT_START_NPU: + return MSG_OP_CHAIN_EXEC_DPU; + default: + return MSG_OP_MAX_OPCODE; + } +} + +int aie2_cmdlist_multi_execbuf(struct amdxdna_hwctx *hwctx, + struct amdxdna_sched_job *job, + int (*notify_cb)(void *, const u32 *, size_t)) +{ + struct amdxdna_gem_obj *cmdbuf_abo = aie2_cmdlist_get_cmd_buf(job); + struct mailbox_channel *chann = hwctx->priv->mbox_chann; + struct amdxdna_client *client = hwctx->client; + struct amdxdna_gem_obj *cmd_abo = job->cmd_bo; + struct amdxdna_cmd_chain *payload; + struct xdna_mailbox_msg msg; + struct cmd_chain_req req; + u32 payload_len; + u32 offset = 0; + u32 size; + int ret; + u32 op; + u32 i; + + op = amdxdna_cmd_get_op(cmd_abo); + payload = amdxdna_cmd_get_payload(cmd_abo, &payload_len); + if (op != ERT_CMD_CHAIN || !payload || + payload_len < struct_size(payload, data, payload->command_count)) + return -EINVAL; + + for (i = 0; i < payload->command_count; i++) { + u32 boh = (u32)(payload->data[i]); + struct amdxdna_gem_obj *abo; + + abo = amdxdna_gem_get_obj(client, boh, AMDXDNA_BO_CMD); + if (!abo) { + XDNA_ERR(client->xdna, "Failed to find cmd BO %d", boh); + return -ENOENT; + } + + /* All sub-cmd should have same op, use the first one. */ + if (i == 0) + op = amdxdna_cmd_get_op(abo); + + ret = aie2_cmdlist_fill_one_slot(op, cmdbuf_abo, offset, abo, &size); + amdxdna_gem_put_obj(abo); + if (ret) + return -EINVAL; + + offset += size; + } + + /* The offset is the accumulated total size of the cmd buffer */ + aie2_cmdlist_prepare_request(&req, cmdbuf_abo, offset, payload->command_count); + + msg.opcode = aie2_cmd_op_to_msg_op(op); + if (msg.opcode == MSG_OP_MAX_OPCODE) + return -EOPNOTSUPP; + msg.handle = job; + msg.notify_cb = notify_cb; + msg.send_data = (u8 *)&req; + msg.send_size = sizeof(req); + ret = xdna_mailbox_send_msg(chann, &msg, TX_TIMEOUT); + if (ret) { + XDNA_ERR(hwctx->client->xdna, "Send message failed"); + return ret; + } + + return 0; +} + +int aie2_cmdlist_single_execbuf(struct amdxdna_hwctx *hwctx, + struct amdxdna_sched_job *job, + int (*notify_cb)(void *, const u32 *, size_t)) +{ + struct amdxdna_gem_obj *cmdbuf_abo = aie2_cmdlist_get_cmd_buf(job); + struct mailbox_channel *chann = hwctx->priv->mbox_chann; + struct amdxdna_gem_obj *cmd_abo = job->cmd_bo; + struct xdna_mailbox_msg msg; + struct cmd_chain_req req; + u32 size; + int ret; + u32 op; + + op = amdxdna_cmd_get_op(cmd_abo); + ret = aie2_cmdlist_fill_one_slot(op, cmdbuf_abo, 0, cmd_abo, &size); + if (ret) + return ret; + + aie2_cmdlist_prepare_request(&req, cmdbuf_abo, size, 1); + + msg.opcode = aie2_cmd_op_to_msg_op(op); + if (msg.opcode == MSG_OP_MAX_OPCODE) + return -EOPNOTSUPP; + msg.handle = job; + msg.notify_cb = notify_cb; + msg.send_data = (u8 *)&req; + msg.send_size = sizeof(req); + ret = xdna_mailbox_send_msg(chann, &msg, TX_TIMEOUT); + if (ret) { + XDNA_ERR(hwctx->client->xdna, "Send message failed"); + return ret; + } + + return 0; +} + +int aie2_sync_bo(struct amdxdna_hwctx *hwctx, struct amdxdna_sched_job *job, + int (*notify_cb)(void *, const u32 *, size_t)) +{ + struct mailbox_channel *chann = hwctx->priv->mbox_chann; + struct amdxdna_gem_obj *abo = to_xdna_obj(job->bos[0]); + struct amdxdna_dev *xdna = hwctx->client->xdna; + struct xdna_mailbox_msg msg; + struct sync_bo_req req; + int ret = 0; + + req.src_addr = 0; + req.dst_addr = abo->mem.dev_addr - hwctx->client->dev_heap->mem.dev_addr; + req.size = abo->mem.size; + + /* Device to Host */ + req.type = FIELD_PREP(AIE2_MSG_SYNC_BO_SRC_TYPE, SYNC_BO_DEV_MEM) | + FIELD_PREP(AIE2_MSG_SYNC_BO_DST_TYPE, SYNC_BO_HOST_MEM); + + XDNA_DBG(xdna, "sync %d bytes src(0x%llx) to dst(0x%llx) completed", + req.size, req.src_addr, req.dst_addr); + + msg.handle = job; + msg.notify_cb = notify_cb; + msg.send_data = (u8 *)&req; + msg.send_size = sizeof(req); + msg.opcode = MSG_OP_SYNC_BO; + + ret = xdna_mailbox_send_msg(chann, &msg, TX_TIMEOUT); + if (ret) { + XDNA_ERR(xdna, "Send message failed"); + return ret; + } + + return 0; +} diff --git a/drivers/accel/amdxdna/aie2_pci.c b/drivers/accel/amdxdna/aie2_pci.c index 6181854c799c..465764712040 100644 --- a/drivers/accel/amdxdna/aie2_pci.c +++ b/drivers/accel/amdxdna/aie2_pci.c @@ -5,8 +5,10 @@ #include #include +#include #include #include +#include #include #include #include @@ -17,6 +19,7 @@ #include "aie2_pci.h" #include "aie2_solver.h" #include "amdxdna_ctx.h" +#include "amdxdna_gem.h" #include "amdxdna_mailbox.h" #include "amdxdna_pci_drv.h" @@ -496,4 +499,6 @@ const struct amdxdna_dev_ops aie2_ops = { .hwctx_init = aie2_hwctx_init, .hwctx_fini = aie2_hwctx_fini, .hwctx_config = aie2_hwctx_config, + .cmd_submit = aie2_cmd_submit, + .hmm_invalidate = aie2_hmm_invalidate, }; diff --git a/drivers/accel/amdxdna/aie2_pci.h b/drivers/accel/amdxdna/aie2_pci.h index 3ac936e2c9d1..9836f721fc9a 100644 --- a/drivers/accel/amdxdna/aie2_pci.h +++ b/drivers/accel/amdxdna/aie2_pci.h @@ -6,6 +6,8 @@ #ifndef _AIE2_PCI_H_ #define _AIE2_PCI_H_ +#include + #include "amdxdna_mailbox.h" #define AIE2_INTERVAL 20000 /* us */ @@ -76,8 +78,10 @@ enum psp_reg_idx { PSP_MAX_REGS /* Keep this at the end */ }; +struct amdxdna_client; struct amdxdna_fw_ver; struct amdxdna_hwctx; +struct amdxdna_sched_job; struct psp_config { const void *fw_buf; @@ -118,9 +122,31 @@ struct rt_config { u32 value; }; +/* + * Define the maximum number of pending commands in a hardware context. + * Must be power of 2! + */ +#define HWCTX_MAX_CMDS 4 +#define get_job_idx(seq) ((seq) & (HWCTX_MAX_CMDS - 1)) struct amdxdna_hwctx_priv { struct amdxdna_gem_obj *heap; void *mbox_chann; + + struct drm_gpu_scheduler sched; + struct drm_sched_entity entity; + + struct mutex io_lock; /* protect seq and cmd order */ + struct wait_queue_head job_free_wq; + u32 num_pending; + u64 seq; + struct semaphore job_sem; + bool job_done; + + /* Completed job counter */ + u64 completed; + + struct amdxdna_gem_obj *cmd_buf[HWCTX_MAX_CMDS]; + struct drm_syncobj *syncobj; }; struct amdxdna_dev_hdl { @@ -199,10 +225,23 @@ int aie2_create_context(struct amdxdna_dev_hdl *ndev, struct amdxdna_hwctx *hwct int aie2_destroy_context(struct amdxdna_dev_hdl *ndev, struct amdxdna_hwctx *hwctx); int aie2_map_host_buf(struct amdxdna_dev_hdl *ndev, u32 context_id, u64 addr, u64 size); int aie2_config_cu(struct amdxdna_hwctx *hwctx); +int aie2_execbuf(struct amdxdna_hwctx *hwctx, struct amdxdna_sched_job *job, + int (*notify_cb)(void *, const u32 *, size_t)); +int aie2_cmdlist_single_execbuf(struct amdxdna_hwctx *hwctx, + struct amdxdna_sched_job *job, + int (*notify_cb)(void *, const u32 *, size_t)); +int aie2_cmdlist_multi_execbuf(struct amdxdna_hwctx *hwctx, + struct amdxdna_sched_job *job, + int (*notify_cb)(void *, const u32 *, size_t)); +int aie2_sync_bo(struct amdxdna_hwctx *hwctx, struct amdxdna_sched_job *job, + int (*notify_cb)(void *, const u32 *, size_t)); /* aie2_hwctx.c */ int aie2_hwctx_init(struct amdxdna_hwctx *hwctx); void aie2_hwctx_fini(struct amdxdna_hwctx *hwctx); int aie2_hwctx_config(struct amdxdna_hwctx *hwctx, u32 type, u64 value, void *buf, u32 size); +int aie2_cmd_submit(struct amdxdna_hwctx *hwctx, struct amdxdna_sched_job *job, u64 *seq); +void aie2_hmm_invalidate(struct amdxdna_gem_obj *abo, unsigned long cur_seq); +void aie2_restart_ctx(struct amdxdna_client *client); #endif /* _AIE2_PCI_H_ */ diff --git a/drivers/accel/amdxdna/aie2_psp.c b/drivers/accel/amdxdna/aie2_psp.c index b03501e81065..dc3a072ce3b6 100644 --- a/drivers/accel/amdxdna/aie2_psp.c +++ b/drivers/accel/amdxdna/aie2_psp.c @@ -4,8 +4,10 @@ */ #include +#include #include #include +#include #include #include diff --git a/drivers/accel/amdxdna/aie2_smu.c b/drivers/accel/amdxdna/aie2_smu.c index 3fa7064649aa..91893d438da7 100644 --- a/drivers/accel/amdxdna/aie2_smu.c +++ b/drivers/accel/amdxdna/aie2_smu.c @@ -4,7 +4,9 @@ */ #include +#include #include +#include #include #include "aie2_pci.h" diff --git a/drivers/accel/amdxdna/amdxdna_ctx.c b/drivers/accel/amdxdna/amdxdna_ctx.c index 9489399adea1..13cfbab9caa0 100644 --- a/drivers/accel/amdxdna/amdxdna_ctx.c +++ b/drivers/accel/amdxdna/amdxdna_ctx.c @@ -7,17 +7,65 @@ #include #include #include +#include +#include #include +#include +#include #include "amdxdna_ctx.h" +#include "amdxdna_gem.h" #include "amdxdna_pci_drv.h" #define MAX_HWCTX_ID 255 +#define MAX_ARG_COUNT 4095 -static void amdxdna_hwctx_destroy(struct amdxdna_hwctx *hwctx) +struct amdxdna_fence { + struct dma_fence base; + spinlock_t lock; /* for base */ + struct amdxdna_hwctx *hwctx; +}; + +static const char *amdxdna_fence_get_driver_name(struct dma_fence *fence) +{ + return KBUILD_MODNAME; +} + +static const char *amdxdna_fence_get_timeline_name(struct dma_fence *fence) +{ + struct amdxdna_fence *xdna_fence; + + xdna_fence = container_of(fence, struct amdxdna_fence, base); + + return xdna_fence->hwctx->name; +} + +static const struct dma_fence_ops fence_ops = { + .get_driver_name = amdxdna_fence_get_driver_name, + .get_timeline_name = amdxdna_fence_get_timeline_name, +}; + +static struct dma_fence *amdxdna_fence_create(struct amdxdna_hwctx *hwctx) +{ + struct amdxdna_fence *fence; + + fence = kzalloc(sizeof(*fence), GFP_KERNEL); + if (!fence) + return NULL; + + fence->hwctx = hwctx; + spin_lock_init(&fence->lock); + dma_fence_init(&fence->base, &fence_ops, &fence->lock, hwctx->id, 0); + return &fence->base; +} + +static void amdxdna_hwctx_destroy_rcu(struct amdxdna_hwctx *hwctx, + struct srcu_struct *ss) { struct amdxdna_dev *xdna = hwctx->client->xdna; + synchronize_srcu(ss); + /* At this point, user is not able to submit new commands */ mutex_lock(&xdna->dev_lock); xdna->dev_info->ops->hwctx_fini(hwctx); @@ -27,6 +75,46 @@ static void amdxdna_hwctx_destroy(struct amdxdna_hwctx *hwctx) kfree(hwctx); } +void *amdxdna_cmd_get_payload(struct amdxdna_gem_obj *abo, u32 *size) +{ + struct amdxdna_cmd *cmd = abo->mem.kva; + u32 num_masks, count; + + if (amdxdna_cmd_get_op(abo) == ERT_CMD_CHAIN) + num_masks = 0; + else + num_masks = 1 + FIELD_GET(AMDXDNA_CMD_EXTRA_CU_MASK, cmd->header); + + if (size) { + count = FIELD_GET(AMDXDNA_CMD_COUNT, cmd->header); + if (unlikely(count <= num_masks)) { + *size = 0; + return NULL; + } + *size = (count - num_masks) * sizeof(u32); + } + return &cmd->data[num_masks]; +} + +int amdxdna_cmd_get_cu_idx(struct amdxdna_gem_obj *abo) +{ + struct amdxdna_cmd *cmd = abo->mem.kva; + u32 num_masks, i; + u32 *cu_mask; + + if (amdxdna_cmd_get_op(abo) == ERT_CMD_CHAIN) + return -1; + + num_masks = 1 + FIELD_GET(AMDXDNA_CMD_EXTRA_CU_MASK, cmd->header); + cu_mask = cmd->data; + for (i = 0; i < num_masks; i++) { + if (cu_mask[i]) + return ffs(cu_mask[i]) - 1; + } + + return -1; +} + /* * This should be called in close() and remove(). DO NOT call in other syscalls. * This guarantee that when hwctx and resources will be released, if user @@ -43,7 +131,7 @@ void amdxdna_hwctx_remove_all(struct amdxdna_client *client) client->pid, hwctx->id); idr_remove(&client->hwctx_idr, hwctx->id); mutex_unlock(&client->hwctx_lock); - amdxdna_hwctx_destroy(hwctx); + amdxdna_hwctx_destroy_rcu(hwctx, &client->hwctx_srcu); mutex_lock(&client->hwctx_lock); } mutex_unlock(&client->hwctx_lock); @@ -135,6 +223,12 @@ int amdxdna_drm_destroy_hwctx_ioctl(struct drm_device *dev, void *data, struct d if (!drm_dev_enter(dev, &idx)) return -ENODEV; + /* + * Use hwctx_lock to achieve exclusion with other hwctx writers, + * SRCU to synchronize with exec/wait command ioctls. + * + * The pushed jobs are handled by DRM scheduler during destroy. + */ mutex_lock(&client->hwctx_lock); hwctx = idr_find(&client->hwctx_idr, args->handle); if (!hwctx) { @@ -147,7 +241,7 @@ int amdxdna_drm_destroy_hwctx_ioctl(struct drm_device *dev, void *data, struct d idr_remove(&client->hwctx_idr, hwctx->id); mutex_unlock(&client->hwctx_lock); - amdxdna_hwctx_destroy(hwctx); + amdxdna_hwctx_destroy_rcu(hwctx, &client->hwctx_srcu); XDNA_DBG(xdna, "PID %d destroyed HW context %d", client->pid, args->handle); out: @@ -161,10 +255,10 @@ int amdxdna_drm_config_hwctx_ioctl(struct drm_device *dev, void *data, struct dr struct amdxdna_drm_config_hwctx *args = data; struct amdxdna_dev *xdna = to_xdna_dev(dev); struct amdxdna_hwctx *hwctx; + int ret, idx; u32 buf_size; void *buf; u64 val; - int ret; if (!xdna->dev_info->ops->hwctx_config) return -EOPNOTSUPP; @@ -203,17 +297,231 @@ int amdxdna_drm_config_hwctx_ioctl(struct drm_device *dev, void *data, struct dr } mutex_lock(&xdna->dev_lock); + idx = srcu_read_lock(&client->hwctx_srcu); hwctx = idr_find(&client->hwctx_idr, args->handle); if (!hwctx) { XDNA_DBG(xdna, "PID %d failed to get hwctx %d", client->pid, args->handle); ret = -EINVAL; - goto unlock; + goto unlock_srcu; } ret = xdna->dev_info->ops->hwctx_config(hwctx, args->param_type, val, buf, buf_size); -unlock: +unlock_srcu: + srcu_read_unlock(&client->hwctx_srcu, idx); mutex_unlock(&xdna->dev_lock); kfree(buf); return ret; } + +static void +amdxdna_arg_bos_put(struct amdxdna_sched_job *job) +{ + int i; + + for (i = 0; i < job->bo_cnt; i++) { + if (!job->bos[i]) + break; + drm_gem_object_put(job->bos[i]); + } +} + +static int +amdxdna_arg_bos_lookup(struct amdxdna_client *client, + struct amdxdna_sched_job *job, + u32 *bo_hdls, u32 bo_cnt) +{ + struct drm_gem_object *gobj; + int i, ret; + + job->bo_cnt = bo_cnt; + for (i = 0; i < job->bo_cnt; i++) { + struct amdxdna_gem_obj *abo; + + gobj = drm_gem_object_lookup(client->filp, bo_hdls[i]); + if (!gobj) { + ret = -ENOENT; + goto put_shmem_bo; + } + abo = to_xdna_obj(gobj); + + mutex_lock(&abo->lock); + if (abo->pinned) { + mutex_unlock(&abo->lock); + job->bos[i] = gobj; + continue; + } + + ret = amdxdna_gem_pin_nolock(abo); + if (ret) { + mutex_unlock(&abo->lock); + drm_gem_object_put(gobj); + goto put_shmem_bo; + } + abo->pinned = true; + mutex_unlock(&abo->lock); + + job->bos[i] = gobj; + } + + return 0; + +put_shmem_bo: + amdxdna_arg_bos_put(job); + return ret; +} + +void amdxdna_sched_job_cleanup(struct amdxdna_sched_job *job) +{ + trace_amdxdna_debug_point(job->hwctx->name, job->seq, "job release"); + amdxdna_arg_bos_put(job); + amdxdna_gem_put_obj(job->cmd_bo); +} + +int amdxdna_cmd_submit(struct amdxdna_client *client, + u32 cmd_bo_hdl, u32 *arg_bo_hdls, u32 arg_bo_cnt, + u32 hwctx_hdl, u64 *seq) +{ + struct amdxdna_dev *xdna = client->xdna; + struct amdxdna_sched_job *job; + struct amdxdna_hwctx *hwctx; + int ret, idx; + + XDNA_DBG(xdna, "Command BO hdl %d, Arg BO count %d", cmd_bo_hdl, arg_bo_cnt); + job = kzalloc(struct_size(job, bos, arg_bo_cnt), GFP_KERNEL); + if (!job) + return -ENOMEM; + + if (cmd_bo_hdl != AMDXDNA_INVALID_BO_HANDLE) { + job->cmd_bo = amdxdna_gem_get_obj(client, cmd_bo_hdl, AMDXDNA_BO_CMD); + if (!job->cmd_bo) { + XDNA_ERR(xdna, "Failed to get cmd bo from %d", cmd_bo_hdl); + ret = -EINVAL; + goto free_job; + } + } else { + job->cmd_bo = NULL; + } + + ret = amdxdna_arg_bos_lookup(client, job, arg_bo_hdls, arg_bo_cnt); + if (ret) { + XDNA_ERR(xdna, "Argument BOs lookup failed, ret %d", ret); + goto cmd_put; + } + + idx = srcu_read_lock(&client->hwctx_srcu); + hwctx = idr_find(&client->hwctx_idr, hwctx_hdl); + if (!hwctx) { + XDNA_DBG(xdna, "PID %d failed to get hwctx %d", + client->pid, hwctx_hdl); + ret = -EINVAL; + goto unlock_srcu; + } + + if (hwctx->status != HWCTX_STAT_READY) { + XDNA_ERR(xdna, "HW Context is not ready"); + ret = -EINVAL; + goto unlock_srcu; + } + + job->hwctx = hwctx; + job->mm = current->mm; + + job->fence = amdxdna_fence_create(hwctx); + if (!job->fence) { + XDNA_ERR(xdna, "Failed to create fence"); + ret = -ENOMEM; + goto unlock_srcu; + } + kref_init(&job->refcnt); + + ret = xdna->dev_info->ops->cmd_submit(hwctx, job, seq); + if (ret) + goto put_fence; + + /* + * The amdxdna_hwctx_destroy_rcu() will release hwctx and associated + * resource after synchronize_srcu(). The submitted jobs should be + * handled by the queue, for example DRM scheduler, in device layer. + * For here we can unlock SRCU. + */ + srcu_read_unlock(&client->hwctx_srcu, idx); + trace_amdxdna_debug_point(hwctx->name, *seq, "job pushed"); + + return 0; + +put_fence: + dma_fence_put(job->fence); +unlock_srcu: + srcu_read_unlock(&client->hwctx_srcu, idx); + amdxdna_arg_bos_put(job); +cmd_put: + amdxdna_gem_put_obj(job->cmd_bo); +free_job: + kfree(job); + return ret; +} + +/* + * The submit command ioctl submits a command to firmware. One firmware command + * may contain multiple command BOs for processing as a whole. + * The command sequence number is returned which can be used for wait command ioctl. + */ +static int amdxdna_drm_submit_execbuf(struct amdxdna_client *client, + struct amdxdna_drm_exec_cmd *args) +{ + struct amdxdna_dev *xdna = client->xdna; + u32 *arg_bo_hdls; + u32 cmd_bo_hdl; + int ret; + + if (!args->arg_count || args->arg_count > MAX_ARG_COUNT) { + XDNA_ERR(xdna, "Invalid arg bo count %d", args->arg_count); + return -EINVAL; + } + + /* Only support single command for now. */ + if (args->cmd_count != 1) { + XDNA_ERR(xdna, "Invalid cmd bo count %d", args->cmd_count); + return -EINVAL; + } + + cmd_bo_hdl = (u32)args->cmd_handles; + arg_bo_hdls = kcalloc(args->arg_count, sizeof(u32), GFP_KERNEL); + if (!arg_bo_hdls) + return -ENOMEM; + ret = copy_from_user(arg_bo_hdls, u64_to_user_ptr(args->args), + args->arg_count * sizeof(u32)); + if (ret) { + ret = -EFAULT; + goto free_cmd_bo_hdls; + } + + ret = amdxdna_cmd_submit(client, cmd_bo_hdl, arg_bo_hdls, + args->arg_count, args->hwctx, &args->seq); + if (ret) + XDNA_DBG(xdna, "Submit cmds failed, ret %d", ret); + +free_cmd_bo_hdls: + kfree(arg_bo_hdls); + if (!ret) + XDNA_DBG(xdna, "Pushed cmd %lld to scheduler", args->seq); + return ret; +} + +int amdxdna_drm_submit_cmd_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) +{ + struct amdxdna_client *client = filp->driver_priv; + struct amdxdna_drm_exec_cmd *args = data; + + if (args->ext || args->ext_flags) + return -EINVAL; + + switch (args->type) { + case AMDXDNA_CMD_SUBMIT_EXEC_BUF: + return amdxdna_drm_submit_execbuf(client, args); + } + + XDNA_ERR(client->xdna, "Invalid command type %d", args->type); + return -EINVAL; +} diff --git a/drivers/accel/amdxdna/amdxdna_ctx.h b/drivers/accel/amdxdna/amdxdna_ctx.h index b409d0731ab8..18ed9bdbd6d8 100644 --- a/drivers/accel/amdxdna/amdxdna_ctx.h +++ b/drivers/accel/amdxdna/amdxdna_ctx.h @@ -6,6 +6,54 @@ #ifndef _AMDXDNA_CTX_H_ #define _AMDXDNA_CTX_H_ +#include + +#include "amdxdna_gem.h" + +struct amdxdna_hwctx_priv; + +enum ert_cmd_opcode { + ERT_START_CU = 0, + ERT_CMD_CHAIN = 19, + ERT_START_NPU = 20, +}; + +enum ert_cmd_state { + ERT_CMD_STATE_INVALID, + ERT_CMD_STATE_NEW, + ERT_CMD_STATE_QUEUED, + ERT_CMD_STATE_RUNNING, + ERT_CMD_STATE_COMPLETED, + ERT_CMD_STATE_ERROR, + ERT_CMD_STATE_ABORT, + ERT_CMD_STATE_SUBMITTED, + ERT_CMD_STATE_TIMEOUT, + ERT_CMD_STATE_NORESPONSE, +}; + +/* + * Interpretation of the beginning of data payload for ERT_START_NPU in + * amdxdna_cmd. The rest of the payload in amdxdna_cmd is regular kernel args. + */ +struct amdxdna_cmd_start_npu { + u64 buffer; /* instruction buffer address */ + u32 buffer_size; /* size of buffer in bytes */ + u32 prop_count; /* properties count */ + u32 prop_args[]; /* properties and regular kernel arguments */ +}; + +/* + * Interpretation of the beginning of data payload for ERT_CMD_CHAIN in + * amdxdna_cmd. The rest of the payload in amdxdna_cmd is cmd BO handles. + */ +struct amdxdna_cmd_chain { + u32 command_count; + u32 submit_index; + u32 error_index; + u32 reserved[3]; + u64 data[] __counted_by(command_count); +}; + /* Exec buffer command header format */ #define AMDXDNA_CMD_STATE GENMASK(3, 0) #define AMDXDNA_CMD_EXTRA_CU_MASK GENMASK(11, 10) @@ -41,9 +89,72 @@ struct amdxdna_hwctx { u32 syncobj_hdl; }; +#define drm_job_to_xdna_job(j) \ + container_of(j, struct amdxdna_sched_job, base) + +struct amdxdna_sched_job { + struct drm_sched_job base; + struct kref refcnt; + struct amdxdna_hwctx *hwctx; + struct mm_struct *mm; + /* The fence to notice DRM scheduler that job is done by hardware */ + struct dma_fence *fence; + /* user can wait on this fence */ + struct dma_fence *out_fence; + bool job_done; + u64 seq; + struct amdxdna_gem_obj *cmd_bo; + size_t bo_cnt; + struct drm_gem_object *bos[] __counted_by(bo_cnt); +}; + +static inline u32 +amdxdna_cmd_get_op(struct amdxdna_gem_obj *abo) +{ + struct amdxdna_cmd *cmd = abo->mem.kva; + + return FIELD_GET(AMDXDNA_CMD_OPCODE, cmd->header); +} + +static inline void +amdxdna_cmd_set_state(struct amdxdna_gem_obj *abo, enum ert_cmd_state s) +{ + struct amdxdna_cmd *cmd = abo->mem.kva; + + cmd->header &= ~AMDXDNA_CMD_STATE; + cmd->header |= FIELD_PREP(AMDXDNA_CMD_STATE, s); +} + +static inline enum ert_cmd_state +amdxdna_cmd_get_state(struct amdxdna_gem_obj *abo) +{ + struct amdxdna_cmd *cmd = abo->mem.kva; + + return FIELD_GET(AMDXDNA_CMD_STATE, cmd->header); +} + +void *amdxdna_cmd_get_payload(struct amdxdna_gem_obj *abo, u32 *size); +int amdxdna_cmd_get_cu_idx(struct amdxdna_gem_obj *abo); + +static inline u32 amdxdna_hwctx_col_map(struct amdxdna_hwctx *hwctx) +{ + return GENMASK(hwctx->start_col + hwctx->num_col - 1, + hwctx->start_col); +} + +void amdxdna_sched_job_cleanup(struct amdxdna_sched_job *job); void amdxdna_hwctx_remove_all(struct amdxdna_client *client); + +int amdxdna_cmd_submit(struct amdxdna_client *client, + u32 cmd_bo_hdls, u32 *arg_bo_hdls, u32 arg_bo_cnt, + u32 hwctx_hdl, u64 *seq); + +int amdxdna_cmd_wait(struct amdxdna_client *client, u32 hwctx_hdl, + u64 seq, u32 timeout); + int amdxdna_drm_create_hwctx_ioctl(struct drm_device *dev, void *data, struct drm_file *filp); int amdxdna_drm_config_hwctx_ioctl(struct drm_device *dev, void *data, struct drm_file *filp); int amdxdna_drm_destroy_hwctx_ioctl(struct drm_device *dev, void *data, struct drm_file *filp); +int amdxdna_drm_submit_cmd_ioctl(struct drm_device *dev, void *data, struct drm_file *filp); #endif /* _AMDXDNA_CTX_H_ */ diff --git a/drivers/accel/amdxdna/amdxdna_gem.c b/drivers/accel/amdxdna/amdxdna_gem.c index f2ba86ae9e1a..4dfeca306d98 100644 --- a/drivers/accel/amdxdna/amdxdna_gem.c +++ b/drivers/accel/amdxdna/amdxdna_gem.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include diff --git a/drivers/accel/amdxdna/amdxdna_mailbox_helper.c b/drivers/accel/amdxdna/amdxdna_mailbox_helper.c index 42b615394605..5139a9c96a91 100644 --- a/drivers/accel/amdxdna/amdxdna_mailbox_helper.c +++ b/drivers/accel/amdxdna/amdxdna_mailbox_helper.c @@ -3,10 +3,15 @@ * Copyright (C) 2024, Advanced Micro Devices, Inc. */ +#include #include #include +#include +#include +#include #include +#include "amdxdna_gem.h" #include "amdxdna_mailbox.h" #include "amdxdna_mailbox_helper.h" #include "amdxdna_pci_drv.h" diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.c b/drivers/accel/amdxdna/amdxdna_pci_drv.c index 172109cc9617..2262157b26a6 100644 --- a/drivers/accel/amdxdna/amdxdna_pci_drv.c +++ b/drivers/accel/amdxdna/amdxdna_pci_drv.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include @@ -64,6 +65,7 @@ static int amdxdna_drm_open(struct drm_device *ddev, struct drm_file *filp) goto unbind_sva; } mutex_init(&client->hwctx_lock); + init_srcu_struct(&client->hwctx_srcu); idr_init_base(&client->hwctx_idr, AMDXDNA_INVALID_CTX_HANDLE + 1); mutex_init(&client->mm_lock); @@ -93,6 +95,7 @@ static void amdxdna_drm_close(struct drm_device *ddev, struct drm_file *filp) XDNA_DBG(xdna, "closing pid %d", client->pid); idr_destroy(&client->hwctx_idr); + cleanup_srcu_struct(&client->hwctx_srcu); mutex_destroy(&client->hwctx_lock); mutex_destroy(&client->mm_lock); if (client->dev_heap) @@ -133,6 +136,8 @@ static const struct drm_ioctl_desc amdxdna_drm_ioctls[] = { DRM_IOCTL_DEF_DRV(AMDXDNA_CREATE_BO, amdxdna_drm_create_bo_ioctl, 0), DRM_IOCTL_DEF_DRV(AMDXDNA_GET_BO_INFO, amdxdna_drm_get_bo_info_ioctl, 0), DRM_IOCTL_DEF_DRV(AMDXDNA_SYNC_BO, amdxdna_drm_sync_bo_ioctl, 0), + /* Execution */ + DRM_IOCTL_DEF_DRV(AMDXDNA_EXEC_CMD, amdxdna_drm_submit_cmd_ioctl, 0), }; static const struct file_operations amdxdna_fops = { @@ -190,9 +195,16 @@ static int amdxdna_probe(struct pci_dev *pdev, const struct pci_device_id *id) return -ENODEV; drmm_mutex_init(&xdna->ddev, &xdna->dev_lock); + init_rwsem(&xdna->notifier_lock); INIT_LIST_HEAD(&xdna->client_list); pci_set_drvdata(pdev, xdna); + if (IS_ENABLED(CONFIG_LOCKDEP)) { + fs_reclaim_acquire(GFP_KERNEL); + might_lock(&xdna->notifier_lock); + fs_reclaim_release(GFP_KERNEL); + } + mutex_lock(&xdna->dev_lock); ret = xdna->dev_info->ops->init(xdna); mutex_unlock(&xdna->dev_lock); diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.h b/drivers/accel/amdxdna/amdxdna_pci_drv.h index 3dddde4ac12a..30ea8da55d69 100644 --- a/drivers/accel/amdxdna/amdxdna_pci_drv.h +++ b/drivers/accel/amdxdna/amdxdna_pci_drv.h @@ -20,6 +20,7 @@ extern const struct drm_driver amdxdna_drm_drv; struct amdxdna_dev; struct amdxdna_gem_obj; struct amdxdna_hwctx; +struct amdxdna_sched_job; /* * struct amdxdna_dev_ops - Device hardware operation callbacks @@ -31,6 +32,7 @@ struct amdxdna_dev_ops { void (*hwctx_fini)(struct amdxdna_hwctx *hwctx); int (*hwctx_config)(struct amdxdna_hwctx *hwctx, u32 type, u64 value, void *buf, u32 size); void (*hmm_invalidate)(struct amdxdna_gem_obj *abo, unsigned long cur_seq); + int (*cmd_submit)(struct amdxdna_hwctx *hwctx, struct amdxdna_sched_job *job, u64 *seq); }; /* @@ -69,6 +71,7 @@ struct amdxdna_dev { struct mutex dev_lock; /* per device lock */ struct list_head client_list; struct amdxdna_fw_ver fw_ver; + struct rw_semaphore notifier_lock; /* for mmu notifier*/ }; /* @@ -88,6 +91,8 @@ struct amdxdna_client { struct list_head node; pid_t pid; struct mutex hwctx_lock; /* protect hwctx */ + /* do NOT wait this srcu when hwctx_lock is held */ + struct srcu_struct hwctx_srcu; struct idr hwctx_idr; struct amdxdna_dev *xdna; struct drm_file *filp; diff --git a/drivers/accel/amdxdna/amdxdna_sysfs.c b/drivers/accel/amdxdna/amdxdna_sysfs.c index 668b94b92714..f27e4ee960a0 100644 --- a/drivers/accel/amdxdna/amdxdna_sysfs.c +++ b/drivers/accel/amdxdna/amdxdna_sysfs.c @@ -3,9 +3,14 @@ * Copyright (C) 2023-2024, Advanced Micro Devices, Inc. */ +#include #include +#include #include +#include +#include +#include "amdxdna_gem.h" #include "amdxdna_pci_drv.h" static ssize_t vbnv_show(struct device *dev, struct device_attribute *attr, char *buf) diff --git a/drivers/accel/amdxdna/npu1_regs.c b/drivers/accel/amdxdna/npu1_regs.c index 720aab0ed7c4..f00c50461b09 100644 --- a/drivers/accel/amdxdna/npu1_regs.c +++ b/drivers/accel/amdxdna/npu1_regs.c @@ -5,6 +5,7 @@ #include #include +#include #include #include "aie2_pci.h" diff --git a/drivers/accel/amdxdna/npu2_regs.c b/drivers/accel/amdxdna/npu2_regs.c index f3ea18bcf294..00cb381031d2 100644 --- a/drivers/accel/amdxdna/npu2_regs.c +++ b/drivers/accel/amdxdna/npu2_regs.c @@ -5,6 +5,7 @@ #include #include +#include #include #include "aie2_pci.h" diff --git a/drivers/accel/amdxdna/npu4_regs.c b/drivers/accel/amdxdna/npu4_regs.c index db61142f0d4e..b6dae9667cca 100644 --- a/drivers/accel/amdxdna/npu4_regs.c +++ b/drivers/accel/amdxdna/npu4_regs.c @@ -5,6 +5,7 @@ #include #include +#include #include #include "aie2_pci.h" diff --git a/drivers/accel/amdxdna/npu5_regs.c b/drivers/accel/amdxdna/npu5_regs.c index debf4e95b9bb..bed1baf8e160 100644 --- a/drivers/accel/amdxdna/npu5_regs.c +++ b/drivers/accel/amdxdna/npu5_regs.c @@ -5,6 +5,7 @@ #include #include +#include #include #include "aie2_pci.h" diff --git a/include/trace/events/amdxdna.h b/include/trace/events/amdxdna.h index 33343d8f0622..c6cb2da7b706 100644 --- a/include/trace/events/amdxdna.h +++ b/include/trace/events/amdxdna.h @@ -9,8 +9,49 @@ #if !defined(_TRACE_AMDXDNA_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_AMDXDNA_H +#include #include +TRACE_EVENT(amdxdna_debug_point, + TP_PROTO(const char *name, u64 number, const char *str), + + TP_ARGS(name, number, str), + + TP_STRUCT__entry(__string(name, name) + __field(u64, number) + __string(str, str)), + + TP_fast_assign(__assign_str(name); + __entry->number = number; + __assign_str(str);), + + TP_printk("%s:%llu %s", __get_str(name), __entry->number, + __get_str(str)) +); + +TRACE_EVENT(xdna_job, + TP_PROTO(struct drm_sched_job *sched_job, const char *name, const char *str, u64 seq), + + TP_ARGS(sched_job, name, str, seq), + + TP_STRUCT__entry(__string(name, name) + __string(str, str) + __field(u64, fence_context) + __field(u64, fence_seqno) + __field(u64, seq)), + + TP_fast_assign(__assign_str(name); + __assign_str(str); + __entry->fence_context = sched_job->s_fence->finished.context; + __entry->fence_seqno = sched_job->s_fence->finished.seqno; + __entry->seq = seq;), + + TP_printk("fence=(context:%llu, seqno:%lld), %s seq#:%lld %s", + __entry->fence_context, __entry->fence_seqno, + __get_str(name), __entry->seq, + __get_str(str)) +); + DECLARE_EVENT_CLASS(xdna_mbox_msg, TP_PROTO(char *name, u8 chann_id, u32 opcode, u32 msg_id), diff --git a/include/uapi/drm/amdxdna_accel.h b/include/uapi/drm/amdxdna_accel.h index e3e78b79a8e7..3e88ed386fac 100644 --- a/include/uapi/drm/amdxdna_accel.h +++ b/include/uapi/drm/amdxdna_accel.h @@ -13,9 +13,11 @@ extern "C" { #endif +#define AMDXDNA_INVALID_CMD_HANDLE (~0UL) #define AMDXDNA_INVALID_ADDR (~0UL) #define AMDXDNA_INVALID_CTX_HANDLE 0 #define AMDXDNA_INVALID_BO_HANDLE 0 +#define AMDXDNA_INVALID_FENCE_HANDLE 0 enum amdxdna_device_type { AMDXDNA_DEV_TYPE_UNKNOWN = -1, @@ -29,6 +31,7 @@ enum amdxdna_drm_ioctl_id { DRM_AMDXDNA_CREATE_BO, DRM_AMDXDNA_GET_BO_INFO, DRM_AMDXDNA_SYNC_BO, + DRM_AMDXDNA_EXEC_CMD, }; /** @@ -201,6 +204,37 @@ struct amdxdna_drm_sync_bo { __u64 size; }; +enum amdxdna_cmd_type { + AMDXDNA_CMD_SUBMIT_EXEC_BUF = 0, + AMDXDNA_CMD_SUBMIT_DEPENDENCY, + AMDXDNA_CMD_SUBMIT_SIGNAL, +}; + +/** + * struct amdxdna_drm_exec_cmd - Execute command. + * @ext: MBZ. + * @ext_flags: MBZ. + * @hwctx: Hardware context handle. + * @type: One of command type in enum amdxdna_cmd_type. + * @cmd_handles: Array of command handles or the command handle itself + * in case of just one. + * @args: Array of arguments for all command handles. + * @cmd_count: Number of command handles in the cmd_handles array. + * @arg_count: Number of arguments in the args array. + * @seq: Returned sequence number for this command. + */ +struct amdxdna_drm_exec_cmd { + __u64 ext; + __u64 ext_flags; + __u32 hwctx; + __u32 type; + __u64 cmd_handles; + __u64 args; + __u32 cmd_count; + __u32 arg_count; + __u64 seq; +}; + #define DRM_IOCTL_AMDXDNA_CREATE_HWCTX \ DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDXDNA_CREATE_HWCTX, \ struct amdxdna_drm_create_hwctx) @@ -225,6 +259,10 @@ struct amdxdna_drm_sync_bo { DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDXDNA_SYNC_BO, \ struct amdxdna_drm_sync_bo) +#define DRM_IOCTL_AMDXDNA_EXEC_CMD \ + DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDXDNA_EXEC_CMD, \ + struct amdxdna_drm_exec_cmd) + #if defined(__cplusplus) } /* extern c end */ #endif -- cgit v1.2.3 From 850d71f6bf4c2010efae845f9ff841cce902f22c Mon Sep 17 00:00:00 2001 From: Lizhi Hou Date: Mon, 18 Nov 2024 09:29:42 -0800 Subject: accel/amdxdna: Add query functions Add GET_INFO ioctl to retrieve hardware information, including AIE, clock, hardware context etc. Co-developed-by: Min Ma Signed-off-by: Min Ma Reviewed-by: Jeffrey Hugo Signed-off-by: Lizhi Hou Signed-off-by: Jeffrey Hugo Link: https://patchwork.freedesktop.org/patch/msgid/20241118172942.2014541-11-lizhi.hou@amd.com --- drivers/accel/amdxdna/aie2_message.c | 65 ++++++++++ drivers/accel/amdxdna/aie2_pci.c | 222 ++++++++++++++++++++++++++++++++ drivers/accel/amdxdna/aie2_pci.h | 1 + drivers/accel/amdxdna/amdxdna_pci_drv.c | 19 +++ drivers/accel/amdxdna/amdxdna_pci_drv.h | 3 + include/uapi/drm/amdxdna_accel.h | 166 ++++++++++++++++++++++++ 6 files changed, 476 insertions(+) (limited to 'include') diff --git a/drivers/accel/amdxdna/aie2_message.c b/drivers/accel/amdxdna/aie2_message.c index eb7e27045213..c01a1d957b56 100644 --- a/drivers/accel/amdxdna/aie2_message.c +++ b/drivers/accel/amdxdna/aie2_message.c @@ -308,6 +308,71 @@ int aie2_map_host_buf(struct amdxdna_dev_hdl *ndev, u32 context_id, u64 addr, u6 return 0; } +int aie2_query_status(struct amdxdna_dev_hdl *ndev, char __user *buf, + u32 size, u32 *cols_filled) +{ + DECLARE_AIE2_MSG(aie_column_info, MSG_OP_QUERY_COL_STATUS); + struct amdxdna_dev *xdna = ndev->xdna; + struct amdxdna_client *client; + struct amdxdna_hwctx *hwctx; + dma_addr_t dma_addr; + u32 aie_bitmap = 0; + u8 *buff_addr; + int next = 0; + int ret, idx; + + buff_addr = dma_alloc_noncoherent(xdna->ddev.dev, size, &dma_addr, + DMA_FROM_DEVICE, GFP_KERNEL); + if (!buff_addr) + return -ENOMEM; + + /* Go through each hardware context and mark the AIE columns that are active */ + list_for_each_entry(client, &xdna->client_list, node) { + idx = srcu_read_lock(&client->hwctx_srcu); + idr_for_each_entry_continue(&client->hwctx_idr, hwctx, next) + aie_bitmap |= amdxdna_hwctx_col_map(hwctx); + srcu_read_unlock(&client->hwctx_srcu, idx); + } + + *cols_filled = 0; + req.dump_buff_addr = dma_addr; + req.dump_buff_size = size; + req.num_cols = hweight32(aie_bitmap); + req.aie_bitmap = aie_bitmap; + + drm_clflush_virt_range(buff_addr, size); /* device can access */ + ret = aie2_send_mgmt_msg_wait(ndev, &msg); + if (ret) { + XDNA_ERR(xdna, "Error during NPU query, status %d", ret); + goto fail; + } + + if (resp.status != AIE2_STATUS_SUCCESS) { + XDNA_ERR(xdna, "Query NPU status failed, status 0x%x", resp.status); + ret = -EINVAL; + goto fail; + } + XDNA_DBG(xdna, "Query NPU status completed"); + + if (size < resp.size) { + ret = -EINVAL; + XDNA_ERR(xdna, "Bad buffer size. Available: %u. Needs: %u", size, resp.size); + goto fail; + } + + if (copy_to_user(buf, buff_addr, resp.size)) { + ret = -EFAULT; + XDNA_ERR(xdna, "Failed to copy NPU status to user space"); + goto fail; + } + + *cols_filled = aie_bitmap; + +fail: + dma_free_noncoherent(xdna->ddev.dev, size, buff_addr, dma_addr, DMA_FROM_DEVICE); + return ret; +} + int aie2_register_asyn_event_msg(struct amdxdna_dev_hdl *ndev, dma_addr_t addr, u32 size, void *handle, int (*cb)(void*, const u32 *, size_t)) { diff --git a/drivers/accel/amdxdna/aie2_pci.c b/drivers/accel/amdxdna/aie2_pci.c index 5467aabe7308..349ada697e48 100644 --- a/drivers/accel/amdxdna/aie2_pci.c +++ b/drivers/accel/amdxdna/aie2_pci.c @@ -5,6 +5,7 @@ #include #include +#include #include #include #include @@ -525,11 +526,232 @@ static void aie2_fini(struct amdxdna_dev *xdna) pci_free_irq_vectors(pdev); } +static int aie2_get_aie_status(struct amdxdna_client *client, + struct amdxdna_drm_get_info *args) +{ + struct amdxdna_drm_query_aie_status status; + struct amdxdna_dev *xdna = client->xdna; + struct amdxdna_dev_hdl *ndev; + int ret; + + ndev = xdna->dev_handle; + if (copy_from_user(&status, u64_to_user_ptr(args->buffer), sizeof(status))) { + XDNA_ERR(xdna, "Failed to copy AIE request into kernel"); + return -EFAULT; + } + + if (ndev->metadata.cols * ndev->metadata.size < status.buffer_size) { + XDNA_ERR(xdna, "Invalid buffer size. Given Size: %u. Need Size: %u.", + status.buffer_size, ndev->metadata.cols * ndev->metadata.size); + return -EINVAL; + } + + ret = aie2_query_status(ndev, u64_to_user_ptr(status.buffer), + status.buffer_size, &status.cols_filled); + if (ret) { + XDNA_ERR(xdna, "Failed to get AIE status info. Ret: %d", ret); + return ret; + } + + if (copy_to_user(u64_to_user_ptr(args->buffer), &status, sizeof(status))) { + XDNA_ERR(xdna, "Failed to copy AIE request info to user space"); + return -EFAULT; + } + + return 0; +} + +static int aie2_get_aie_metadata(struct amdxdna_client *client, + struct amdxdna_drm_get_info *args) +{ + struct amdxdna_drm_query_aie_metadata *meta; + struct amdxdna_dev *xdna = client->xdna; + struct amdxdna_dev_hdl *ndev; + int ret = 0; + + ndev = xdna->dev_handle; + meta = kzalloc(sizeof(*meta), GFP_KERNEL); + if (!meta) + return -ENOMEM; + + meta->col_size = ndev->metadata.size; + meta->cols = ndev->metadata.cols; + meta->rows = ndev->metadata.rows; + + meta->version.major = ndev->metadata.version.major; + meta->version.minor = ndev->metadata.version.minor; + + meta->core.row_count = ndev->metadata.core.row_count; + meta->core.row_start = ndev->metadata.core.row_start; + meta->core.dma_channel_count = ndev->metadata.core.dma_channel_count; + meta->core.lock_count = ndev->metadata.core.lock_count; + meta->core.event_reg_count = ndev->metadata.core.event_reg_count; + + meta->mem.row_count = ndev->metadata.mem.row_count; + meta->mem.row_start = ndev->metadata.mem.row_start; + meta->mem.dma_channel_count = ndev->metadata.mem.dma_channel_count; + meta->mem.lock_count = ndev->metadata.mem.lock_count; + meta->mem.event_reg_count = ndev->metadata.mem.event_reg_count; + + meta->shim.row_count = ndev->metadata.shim.row_count; + meta->shim.row_start = ndev->metadata.shim.row_start; + meta->shim.dma_channel_count = ndev->metadata.shim.dma_channel_count; + meta->shim.lock_count = ndev->metadata.shim.lock_count; + meta->shim.event_reg_count = ndev->metadata.shim.event_reg_count; + + if (copy_to_user(u64_to_user_ptr(args->buffer), meta, sizeof(*meta))) + ret = -EFAULT; + + kfree(meta); + return ret; +} + +static int aie2_get_aie_version(struct amdxdna_client *client, + struct amdxdna_drm_get_info *args) +{ + struct amdxdna_drm_query_aie_version version; + struct amdxdna_dev *xdna = client->xdna; + struct amdxdna_dev_hdl *ndev; + + ndev = xdna->dev_handle; + version.major = ndev->version.major; + version.minor = ndev->version.minor; + + if (copy_to_user(u64_to_user_ptr(args->buffer), &version, sizeof(version))) + return -EFAULT; + + return 0; +} + +static int aie2_get_clock_metadata(struct amdxdna_client *client, + struct amdxdna_drm_get_info *args) +{ + struct amdxdna_drm_query_clock_metadata *clock; + struct amdxdna_dev *xdna = client->xdna; + struct amdxdna_dev_hdl *ndev; + int ret = 0; + + ndev = xdna->dev_handle; + clock = kzalloc(sizeof(*clock), GFP_KERNEL); + if (!clock) + return -ENOMEM; + + memcpy(clock->mp_npu_clock.name, ndev->mp_npu_clock.name, + sizeof(clock->mp_npu_clock.name)); + clock->mp_npu_clock.freq_mhz = ndev->mp_npu_clock.freq_mhz; + memcpy(clock->h_clock.name, ndev->h_clock.name, sizeof(clock->h_clock.name)); + clock->h_clock.freq_mhz = ndev->h_clock.freq_mhz; + + if (copy_to_user(u64_to_user_ptr(args->buffer), clock, sizeof(*clock))) + ret = -EFAULT; + + kfree(clock); + return ret; +} + +static int aie2_get_hwctx_status(struct amdxdna_client *client, + struct amdxdna_drm_get_info *args) +{ + struct amdxdna_drm_query_hwctx __user *buf; + struct amdxdna_dev *xdna = client->xdna; + struct amdxdna_drm_query_hwctx *tmp; + struct amdxdna_client *tmp_client; + struct amdxdna_hwctx *hwctx; + bool overflow = false; + u32 req_bytes = 0; + u32 hw_i = 0; + int ret = 0; + int next; + int idx; + + drm_WARN_ON(&xdna->ddev, !mutex_is_locked(&xdna->dev_lock)); + + tmp = kzalloc(sizeof(*tmp), GFP_KERNEL); + if (!tmp) + return -ENOMEM; + + buf = u64_to_user_ptr(args->buffer); + list_for_each_entry(tmp_client, &xdna->client_list, node) { + idx = srcu_read_lock(&tmp_client->hwctx_srcu); + next = 0; + idr_for_each_entry_continue(&tmp_client->hwctx_idr, hwctx, next) { + req_bytes += sizeof(*tmp); + if (args->buffer_size < req_bytes) { + /* Continue iterating to get the required size */ + overflow = true; + continue; + } + + memset(tmp, 0, sizeof(*tmp)); + tmp->pid = tmp_client->pid; + tmp->context_id = hwctx->id; + tmp->start_col = hwctx->start_col; + tmp->num_col = hwctx->num_col; + tmp->command_submissions = hwctx->priv->seq; + tmp->command_completions = hwctx->priv->completed; + + if (copy_to_user(&buf[hw_i], tmp, sizeof(*tmp))) { + ret = -EFAULT; + srcu_read_unlock(&tmp_client->hwctx_srcu, idx); + goto out; + } + hw_i++; + } + srcu_read_unlock(&tmp_client->hwctx_srcu, idx); + } + + if (overflow) { + XDNA_ERR(xdna, "Invalid buffer size. Given: %u Need: %u.", + args->buffer_size, req_bytes); + ret = -EINVAL; + } + +out: + kfree(tmp); + args->buffer_size = req_bytes; + return ret; +} + +static int aie2_get_info(struct amdxdna_client *client, struct amdxdna_drm_get_info *args) +{ + struct amdxdna_dev *xdna = client->xdna; + int ret, idx; + + if (!drm_dev_enter(&xdna->ddev, &idx)) + return -ENODEV; + + switch (args->param) { + case DRM_AMDXDNA_QUERY_AIE_STATUS: + ret = aie2_get_aie_status(client, args); + break; + case DRM_AMDXDNA_QUERY_AIE_METADATA: + ret = aie2_get_aie_metadata(client, args); + break; + case DRM_AMDXDNA_QUERY_AIE_VERSION: + ret = aie2_get_aie_version(client, args); + break; + case DRM_AMDXDNA_QUERY_CLOCK_METADATA: + ret = aie2_get_clock_metadata(client, args); + break; + case DRM_AMDXDNA_QUERY_HW_CONTEXTS: + ret = aie2_get_hwctx_status(client, args); + break; + default: + XDNA_ERR(xdna, "Not supported request parameter %u", args->param); + ret = -EOPNOTSUPP; + } + XDNA_DBG(xdna, "Got param %d", args->param); + + drm_dev_exit(idx); + return ret; +} + const struct amdxdna_dev_ops aie2_ops = { .init = aie2_init, .fini = aie2_fini, .resume = aie2_hw_start, .suspend = aie2_hw_stop, + .get_aie_info = aie2_get_info, .hwctx_init = aie2_hwctx_init, .hwctx_fini = aie2_hwctx_fini, .hwctx_config = aie2_hwctx_config, diff --git a/drivers/accel/amdxdna/aie2_pci.h b/drivers/accel/amdxdna/aie2_pci.h index 4422dd6c985e..6a2686255c9c 100644 --- a/drivers/accel/amdxdna/aie2_pci.h +++ b/drivers/accel/amdxdna/aie2_pci.h @@ -231,6 +231,7 @@ int aie2_query_firmware_version(struct amdxdna_dev_hdl *ndev, int aie2_create_context(struct amdxdna_dev_hdl *ndev, struct amdxdna_hwctx *hwctx); int aie2_destroy_context(struct amdxdna_dev_hdl *ndev, struct amdxdna_hwctx *hwctx); int aie2_map_host_buf(struct amdxdna_dev_hdl *ndev, u32 context_id, u64 addr, u64 size); +int aie2_query_status(struct amdxdna_dev_hdl *ndev, char *buf, u32 size, u32 *cols_filled); int aie2_register_asyn_event_msg(struct amdxdna_dev_hdl *ndev, dma_addr_t addr, u32 size, void *handle, int (*cb)(void*, const u32 *, size_t)); int aie2_config_cu(struct amdxdna_hwctx *hwctx); diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.c b/drivers/accel/amdxdna/amdxdna_pci_drv.c index c4df674fdf50..02533732d4ca 100644 --- a/drivers/accel/amdxdna/amdxdna_pci_drv.c +++ b/drivers/accel/amdxdna/amdxdna_pci_drv.c @@ -143,6 +143,23 @@ static int amdxdna_flush(struct file *f, fl_owner_t id) return 0; } +static int amdxdna_drm_get_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) +{ + struct amdxdna_client *client = filp->driver_priv; + struct amdxdna_dev *xdna = to_xdna_dev(dev); + struct amdxdna_drm_get_info *args = data; + int ret; + + if (!xdna->dev_info->ops->get_aie_info) + return -EOPNOTSUPP; + + XDNA_DBG(xdna, "Request parameter %u", args->param); + mutex_lock(&xdna->dev_lock); + ret = xdna->dev_info->ops->get_aie_info(client, args); + mutex_unlock(&xdna->dev_lock); + return ret; +} + static const struct drm_ioctl_desc amdxdna_drm_ioctls[] = { /* Context */ DRM_IOCTL_DEF_DRV(AMDXDNA_CREATE_HWCTX, amdxdna_drm_create_hwctx_ioctl, 0), @@ -154,6 +171,8 @@ static const struct drm_ioctl_desc amdxdna_drm_ioctls[] = { DRM_IOCTL_DEF_DRV(AMDXDNA_SYNC_BO, amdxdna_drm_sync_bo_ioctl, 0), /* Execution */ DRM_IOCTL_DEF_DRV(AMDXDNA_EXEC_CMD, amdxdna_drm_submit_cmd_ioctl, 0), + /* AIE hardware */ + DRM_IOCTL_DEF_DRV(AMDXDNA_GET_INFO, amdxdna_drm_get_info_ioctl, 0), }; static const struct file_operations amdxdna_fops = { diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.h b/drivers/accel/amdxdna/amdxdna_pci_drv.h index 52c59249c8a0..c50d65a050ad 100644 --- a/drivers/accel/amdxdna/amdxdna_pci_drv.h +++ b/drivers/accel/amdxdna/amdxdna_pci_drv.h @@ -17,7 +17,9 @@ extern const struct drm_driver amdxdna_drm_drv; +struct amdxdna_client; struct amdxdna_dev; +struct amdxdna_drm_get_info; struct amdxdna_gem_obj; struct amdxdna_hwctx; struct amdxdna_sched_job; @@ -37,6 +39,7 @@ struct amdxdna_dev_ops { void (*hwctx_suspend)(struct amdxdna_hwctx *hwctx); void (*hwctx_resume)(struct amdxdna_hwctx *hwctx); int (*cmd_submit)(struct amdxdna_hwctx *hwctx, struct amdxdna_sched_job *job, u64 *seq); + int (*get_aie_info)(struct amdxdna_client *client, struct amdxdna_drm_get_info *args); }; /* diff --git a/include/uapi/drm/amdxdna_accel.h b/include/uapi/drm/amdxdna_accel.h index 3e88ed386fac..af12af8bd699 100644 --- a/include/uapi/drm/amdxdna_accel.h +++ b/include/uapi/drm/amdxdna_accel.h @@ -32,6 +32,7 @@ enum amdxdna_drm_ioctl_id { DRM_AMDXDNA_GET_BO_INFO, DRM_AMDXDNA_SYNC_BO, DRM_AMDXDNA_EXEC_CMD, + DRM_AMDXDNA_GET_INFO, }; /** @@ -235,6 +236,167 @@ struct amdxdna_drm_exec_cmd { __u64 seq; }; +/** + * struct amdxdna_drm_query_aie_status - Query the status of the AIE hardware + * @buffer: The user space buffer that will return the AIE status. + * @buffer_size: The size of the user space buffer. + * @cols_filled: A bitmap of AIE columns whose data has been returned in the buffer. + */ +struct amdxdna_drm_query_aie_status { + __u64 buffer; /* out */ + __u32 buffer_size; /* in */ + __u32 cols_filled; /* out */ +}; + +/** + * struct amdxdna_drm_query_aie_version - Query the version of the AIE hardware + * @major: The major version number. + * @minor: The minor version number. + */ +struct amdxdna_drm_query_aie_version { + __u32 major; /* out */ + __u32 minor; /* out */ +}; + +/** + * struct amdxdna_drm_query_aie_tile_metadata - Query the metadata of AIE tile (core, mem, shim) + * @row_count: The number of rows. + * @row_start: The starting row number. + * @dma_channel_count: The number of dma channels. + * @lock_count: The number of locks. + * @event_reg_count: The number of events. + * @pad: Structure padding. + */ +struct amdxdna_drm_query_aie_tile_metadata { + __u16 row_count; + __u16 row_start; + __u16 dma_channel_count; + __u16 lock_count; + __u16 event_reg_count; + __u16 pad[3]; +}; + +/** + * struct amdxdna_drm_query_aie_metadata - Query the metadata of the AIE hardware + * @col_size: The size of a column in bytes. + * @cols: The total number of columns. + * @rows: The total number of rows. + * @version: The version of the AIE hardware. + * @core: The metadata for all core tiles. + * @mem: The metadata for all mem tiles. + * @shim: The metadata for all shim tiles. + */ +struct amdxdna_drm_query_aie_metadata { + __u32 col_size; + __u16 cols; + __u16 rows; + struct amdxdna_drm_query_aie_version version; + struct amdxdna_drm_query_aie_tile_metadata core; + struct amdxdna_drm_query_aie_tile_metadata mem; + struct amdxdna_drm_query_aie_tile_metadata shim; +}; + +/** + * struct amdxdna_drm_query_clock - Metadata for a clock + * @name: The clock name. + * @freq_mhz: The clock frequency. + * @pad: Structure padding. + */ +struct amdxdna_drm_query_clock { + __u8 name[16]; + __u32 freq_mhz; + __u32 pad; +}; + +/** + * struct amdxdna_drm_query_clock_metadata - Query metadata for clocks + * @mp_npu_clock: The metadata for MP-NPU clock. + * @h_clock: The metadata for H clock. + */ +struct amdxdna_drm_query_clock_metadata { + struct amdxdna_drm_query_clock mp_npu_clock; + struct amdxdna_drm_query_clock h_clock; +}; + +enum amdxdna_sensor_type { + AMDXDNA_SENSOR_TYPE_POWER +}; + +/** + * struct amdxdna_drm_query_sensor - The data for single sensor. + * @label: The name for a sensor. + * @input: The current value of the sensor. + * @max: The maximum value possible for the sensor. + * @average: The average value of the sensor. + * @highest: The highest recorded sensor value for this driver load for the sensor. + * @status: The sensor status. + * @units: The sensor units. + * @unitm: Translates value member variables into the correct unit via (pow(10, unitm) * value). + * @type: The sensor type from enum amdxdna_sensor_type. + * @pad: Structure padding. + */ +struct amdxdna_drm_query_sensor { + __u8 label[64]; + __u32 input; + __u32 max; + __u32 average; + __u32 highest; + __u8 status[64]; + __u8 units[16]; + __s8 unitm; + __u8 type; + __u8 pad[6]; +}; + +/** + * struct amdxdna_drm_query_hwctx - The data for single context. + * @context_id: The ID for this context. + * @start_col: The starting column for the partition assigned to this context. + * @num_col: The number of columns in the partition assigned to this context. + * @pad: Structure padding. + * @pid: The Process ID of the process that created this context. + * @command_submissions: The number of commands submitted to this context. + * @command_completions: The number of commands completed by this context. + * @migrations: The number of times this context has been moved to a different partition. + * @preemptions: The number of times this context has been preempted by another context in the + * same partition. + * @errors: The errors for this context. + */ +struct amdxdna_drm_query_hwctx { + __u32 context_id; + __u32 start_col; + __u32 num_col; + __u32 pad; + __s64 pid; + __u64 command_submissions; + __u64 command_completions; + __u64 migrations; + __u64 preemptions; + __u64 errors; +}; + +enum amdxdna_drm_get_param { + DRM_AMDXDNA_QUERY_AIE_STATUS, + DRM_AMDXDNA_QUERY_AIE_METADATA, + DRM_AMDXDNA_QUERY_AIE_VERSION, + DRM_AMDXDNA_QUERY_CLOCK_METADATA, + DRM_AMDXDNA_QUERY_SENSORS, + DRM_AMDXDNA_QUERY_HW_CONTEXTS, + DRM_AMDXDNA_NUM_GET_PARAM, +}; + +/** + * struct amdxdna_drm_get_info - Get some information from the AIE hardware. + * @param: Value in enum amdxdna_drm_get_param. Specifies the structure passed in the buffer. + * @buffer_size: Size of the input buffer. Size needed/written by the kernel. + * @buffer: A structure specified by the param struct member. + */ +struct amdxdna_drm_get_info { + __u32 param; /* in */ + __u32 buffer_size; /* in/out */ + __u64 buffer; /* in/out */ +}; + #define DRM_IOCTL_AMDXDNA_CREATE_HWCTX \ DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDXDNA_CREATE_HWCTX, \ struct amdxdna_drm_create_hwctx) @@ -263,6 +425,10 @@ struct amdxdna_drm_exec_cmd { DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDXDNA_EXEC_CMD, \ struct amdxdna_drm_exec_cmd) +#define DRM_IOCTL_AMDXDNA_GET_INFO \ + DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDXDNA_GET_INFO, \ + struct amdxdna_drm_get_info) + #if defined(__cplusplus) } /* extern c end */ #endif -- cgit v1.2.3 From f2663f704d8428a7f1bacf084de460d006259f6e Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Tue, 3 Dec 2024 17:17:08 +0200 Subject: drm/dp: extract drm_dp_dpcd_poll_act_handled() SST with 128b/132b channel coding needs this too. Extract to a separate helper, independent of MST. Pass timeout in as a parameter, anticipating that we can reduce the timeout for SST. v2: Clean up kernel-doc a bit Cc: Lyude Paul Reviewed-by: Imre Deak Reviewed-by: Lyude Paul Link: https://patchwork.freedesktop.org/patch/msgid/459fd3e96a55a8ea8ada8d27d93eaa24c235f9c1.1733238941.git.jani.nikula@intel.com Signed-off-by: Jani Nikula --- drivers/gpu/drm/display/drm_dp_helper.c | 54 ++++++++++++++++++++++++++- drivers/gpu/drm/display/drm_dp_mst_topology.c | 36 +----------------- include/drm/display/drm_dp_helper.h | 2 + 3 files changed, 57 insertions(+), 35 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/display/drm_dp_helper.c b/drivers/gpu/drm/display/drm_dp_helper.c index 6ee51003de3c..fdb55c462d64 100644 --- a/drivers/gpu/drm/display/drm_dp_helper.c +++ b/drivers/gpu/drm/display/drm_dp_helper.c @@ -22,15 +22,16 @@ #include #include +#include #include #include #include +#include #include #include #include #include #include -#include #include #include @@ -779,6 +780,57 @@ int drm_dp_dpcd_read_phy_link_status(struct drm_dp_aux *aux, } EXPORT_SYMBOL(drm_dp_dpcd_read_phy_link_status); +static int read_payload_update_status(struct drm_dp_aux *aux) +{ + int ret; + u8 status; + + ret = drm_dp_dpcd_readb(aux, DP_PAYLOAD_TABLE_UPDATE_STATUS, &status); + if (ret < 0) + return ret; + + return status; +} + +/** + * drm_dp_dpcd_poll_act_handled() - Poll for ACT handled status + * @aux: DisplayPort AUX channel + * @timeout_ms: Timeout in ms + * + * Try waiting for the sink to finish updating its payload table by polling for + * the ACT handled bit of DP_PAYLOAD_TABLE_UPDATE_STATUS for up to @timeout_ms + * milliseconds, defaulting to 3000 ms if 0. + * + * Returns: + * 0 if the ACT was handled in time, negative error code on failure. + */ +int drm_dp_dpcd_poll_act_handled(struct drm_dp_aux *aux, int timeout_ms) +{ + int ret, status; + + /* default to 3 seconds, this is arbitrary */ + timeout_ms = timeout_ms ?: 3000; + + ret = readx_poll_timeout(read_payload_update_status, aux, status, + status & DP_PAYLOAD_ACT_HANDLED || status < 0, + 200, timeout_ms * USEC_PER_MSEC); + if (ret < 0 && status >= 0) { + drm_err(aux->drm_dev, "Failed to get ACT after %d ms, last status: %02x\n", + timeout_ms, status); + return -EINVAL; + } else if (status < 0) { + /* + * Failure here isn't unexpected - the hub may have + * just been unplugged + */ + drm_dbg_kms(aux->drm_dev, "Failed to read payload table status: %d\n", status); + return status; + } + + return 0; +} +EXPORT_SYMBOL(drm_dp_dpcd_poll_act_handled); + static bool is_edid_digital_input_dp(const struct drm_edid *drm_edid) { /* FIXME: get rid of drm_edid_raw() */ diff --git a/drivers/gpu/drm/display/drm_dp_mst_topology.c b/drivers/gpu/drm/display/drm_dp_mst_topology.c index ac90118b9e7a..2bdbc1eb282b 100644 --- a/drivers/gpu/drm/display/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/display/drm_dp_mst_topology.c @@ -29,7 +29,6 @@ #include #include #include -#include #if IS_ENABLED(CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS) #include @@ -4723,18 +4722,6 @@ fail: return ret; } -static int do_get_act_status(struct drm_dp_aux *aux) -{ - int ret; - u8 status; - - ret = drm_dp_dpcd_readb(aux, DP_PAYLOAD_TABLE_UPDATE_STATUS, &status); - if (ret < 0) - return ret; - - return status; -} - /** * drm_dp_check_act_status() - Polls for ACT handled status. * @mgr: manager to use @@ -4752,28 +4739,9 @@ int drm_dp_check_act_status(struct drm_dp_mst_topology_mgr *mgr) * There doesn't seem to be any recommended retry count or timeout in * the MST specification. Since some hubs have been observed to take * over 1 second to update their payload allocations under certain - * conditions, we use a rather large timeout value. + * conditions, we use a rather large timeout value of 3 seconds. */ - const int timeout_ms = 3000; - int ret, status; - - ret = readx_poll_timeout(do_get_act_status, mgr->aux, status, - status & DP_PAYLOAD_ACT_HANDLED || status < 0, - 200, timeout_ms * USEC_PER_MSEC); - if (ret < 0 && status >= 0) { - drm_err(mgr->dev, "Failed to get ACT after %dms, last status: %02x\n", - timeout_ms, status); - return -EINVAL; - } else if (status < 0) { - /* - * Failure here isn't unexpected - the hub may have - * just been unplugged - */ - drm_dbg_kms(mgr->dev, "Failed to read payload table status: %d\n", status); - return status; - } - - return 0; + return drm_dp_dpcd_poll_act_handled(mgr->aux, 3000); } EXPORT_SYMBOL(drm_dp_check_act_status); diff --git a/include/drm/display/drm_dp_helper.h b/include/drm/display/drm_dp_helper.h index 279624833ea9..38eea21d1082 100644 --- a/include/drm/display/drm_dp_helper.h +++ b/include/drm/display/drm_dp_helper.h @@ -567,6 +567,8 @@ int drm_dp_dpcd_read_phy_link_status(struct drm_dp_aux *aux, enum drm_dp_phy dp_phy, u8 link_status[DP_LINK_STATUS_SIZE]); +int drm_dp_dpcd_poll_act_handled(struct drm_dp_aux *aux, int timeout_ms); + bool drm_dp_send_real_edid_checksum(struct drm_dp_aux *aux, u8 real_edid_checksum); -- cgit v1.2.3 From 3b00b53afe6047983b14de269cd0a93c612e646d Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Tue, 3 Dec 2024 17:17:09 +0200 Subject: drm/dp: extract drm_dp_dpcd_write_payload() SST with 128b/132b channel coding needs this too. Extract to a separate helper, independent of MST. v2: Clean up kernel-doc a bit Cc: Lyude Paul Reviewed-by: Imre Deak Reviewed-by: Lyude Paul Link: https://patchwork.freedesktop.org/patch/msgid/f626715ba4e348546770750aa3e10fac73a5cbd7.1733238941.git.jani.nikula@intel.com Signed-off-by: Jani Nikula --- drivers/gpu/drm/display/drm_dp_helper.c | 57 +++++++++++++++++++++++++++ drivers/gpu/drm/display/drm_dp_mst_topology.c | 52 ++---------------------- include/drm/display/drm_dp_helper.h | 2 + 3 files changed, 62 insertions(+), 49 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/display/drm_dp_helper.c b/drivers/gpu/drm/display/drm_dp_helper.c index fdb55c462d64..55eca899ce18 100644 --- a/drivers/gpu/drm/display/drm_dp_helper.c +++ b/drivers/gpu/drm/display/drm_dp_helper.c @@ -792,6 +792,63 @@ static int read_payload_update_status(struct drm_dp_aux *aux) return status; } +/** + * drm_dp_dpcd_write_payload() - Write Virtual Channel information to payload table + * @aux: DisplayPort AUX channel + * @vcpid: Virtual Channel Payload ID + * @start_time_slot: Starting time slot + * @time_slot_count: Time slot count + * + * Write the Virtual Channel payload allocation table, checking the payload + * update status and retrying as necessary. + * + * Returns: + * 0 on success, negative error otherwise + */ +int drm_dp_dpcd_write_payload(struct drm_dp_aux *aux, + int vcpid, u8 start_time_slot, u8 time_slot_count) +{ + u8 payload_alloc[3], status; + int ret; + int retries = 0; + + drm_dp_dpcd_writeb(aux, DP_PAYLOAD_TABLE_UPDATE_STATUS, + DP_PAYLOAD_TABLE_UPDATED); + + payload_alloc[0] = vcpid; + payload_alloc[1] = start_time_slot; + payload_alloc[2] = time_slot_count; + + ret = drm_dp_dpcd_write(aux, DP_PAYLOAD_ALLOCATE_SET, payload_alloc, 3); + if (ret != 3) { + drm_dbg_kms(aux->drm_dev, "failed to write payload allocation %d\n", ret); + goto fail; + } + +retry: + ret = drm_dp_dpcd_readb(aux, DP_PAYLOAD_TABLE_UPDATE_STATUS, &status); + if (ret < 0) { + drm_dbg_kms(aux->drm_dev, "failed to read payload table status %d\n", ret); + goto fail; + } + + if (!(status & DP_PAYLOAD_TABLE_UPDATED)) { + retries++; + if (retries < 20) { + usleep_range(10000, 20000); + goto retry; + } + drm_dbg_kms(aux->drm_dev, "status not set after read payload table status %d\n", + status); + ret = -EINVAL; + goto fail; + } + ret = 0; +fail: + return ret; +} +EXPORT_SYMBOL(drm_dp_dpcd_write_payload); + /** * drm_dp_dpcd_poll_act_handled() - Poll for ACT handled status * @aux: DisplayPort AUX channel diff --git a/drivers/gpu/drm/display/drm_dp_mst_topology.c b/drivers/gpu/drm/display/drm_dp_mst_topology.c index 2bdbc1eb282b..a426d13a7a36 100644 --- a/drivers/gpu/drm/display/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/display/drm_dp_mst_topology.c @@ -67,9 +67,6 @@ static bool dump_dp_payload_table(struct drm_dp_mst_topology_mgr *mgr, static void drm_dp_mst_topology_put_port(struct drm_dp_mst_port *port); -static int drm_dp_dpcd_write_payload(struct drm_dp_mst_topology_mgr *mgr, - int id, u8 start_slot, u8 num_slots); - static int drm_dp_send_dpcd_read(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port, int offset, int size, u8 *bytes); @@ -3263,7 +3260,7 @@ EXPORT_SYMBOL(drm_dp_send_query_stream_enc_status); static int drm_dp_create_payload_at_dfp(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_atomic_payload *payload) { - return drm_dp_dpcd_write_payload(mgr, payload->vcpi, payload->vc_start_slot, + return drm_dp_dpcd_write_payload(mgr->aux, payload->vcpi, payload->vc_start_slot, payload->time_slots); } @@ -3294,7 +3291,7 @@ static void drm_dp_destroy_payload_at_remote_and_dfp(struct drm_dp_mst_topology_ } if (payload->payload_allocation_status == DRM_DP_MST_PAYLOAD_ALLOCATION_DFP) - drm_dp_dpcd_write_payload(mgr, payload->vcpi, payload->vc_start_slot, 0); + drm_dp_dpcd_write_payload(mgr->aux, payload->vcpi, payload->vc_start_slot, 0); } /** @@ -3682,7 +3679,7 @@ int drm_dp_mst_topology_mgr_set_mst(struct drm_dp_mst_topology_mgr *mgr, bool ms goto out_unlock; /* Write reset payload */ - drm_dp_dpcd_write_payload(mgr, 0, 0, 0x3f); + drm_dp_dpcd_write_payload(mgr->aux, 0, 0, 0x3f); drm_dp_mst_queue_probe_work(mgr); @@ -4679,49 +4676,6 @@ void drm_dp_mst_update_slots(struct drm_dp_mst_topology_state *mst_state, uint8_ } EXPORT_SYMBOL(drm_dp_mst_update_slots); -static int drm_dp_dpcd_write_payload(struct drm_dp_mst_topology_mgr *mgr, - int id, u8 start_slot, u8 num_slots) -{ - u8 payload_alloc[3], status; - int ret; - int retries = 0; - - drm_dp_dpcd_writeb(mgr->aux, DP_PAYLOAD_TABLE_UPDATE_STATUS, - DP_PAYLOAD_TABLE_UPDATED); - - payload_alloc[0] = id; - payload_alloc[1] = start_slot; - payload_alloc[2] = num_slots; - - ret = drm_dp_dpcd_write(mgr->aux, DP_PAYLOAD_ALLOCATE_SET, payload_alloc, 3); - if (ret != 3) { - drm_dbg_kms(mgr->dev, "failed to write payload allocation %d\n", ret); - goto fail; - } - -retry: - ret = drm_dp_dpcd_readb(mgr->aux, DP_PAYLOAD_TABLE_UPDATE_STATUS, &status); - if (ret < 0) { - drm_dbg_kms(mgr->dev, "failed to read payload table status %d\n", ret); - goto fail; - } - - if (!(status & DP_PAYLOAD_TABLE_UPDATED)) { - retries++; - if (retries < 20) { - usleep_range(10000, 20000); - goto retry; - } - drm_dbg_kms(mgr->dev, "status not set after read payload table status %d\n", - status); - ret = -EINVAL; - goto fail; - } - ret = 0; -fail: - return ret; -} - /** * drm_dp_check_act_status() - Polls for ACT handled status. * @mgr: manager to use diff --git a/include/drm/display/drm_dp_helper.h b/include/drm/display/drm_dp_helper.h index 38eea21d1082..69793815aa82 100644 --- a/include/drm/display/drm_dp_helper.h +++ b/include/drm/display/drm_dp_helper.h @@ -567,6 +567,8 @@ int drm_dp_dpcd_read_phy_link_status(struct drm_dp_aux *aux, enum drm_dp_phy dp_phy, u8 link_status[DP_LINK_STATUS_SIZE]); +int drm_dp_dpcd_write_payload(struct drm_dp_aux *aux, + int vcpid, u8 start_time_slot, u8 time_slot_count); int drm_dp_dpcd_poll_act_handled(struct drm_dp_aux *aux, int timeout_ms); bool drm_dp_send_real_edid_checksum(struct drm_dp_aux *aux, -- cgit v1.2.3 From f3c03be182efccce3f6c2d8ceb35ba43e77ac128 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Tue, 3 Dec 2024 17:17:10 +0200 Subject: drm/dp: extract drm_dp_dpcd_clear_payload() SST with 128b/132b channel coding needs this too. Extract to a separate helper, independent of MST. Cc: Lyude Paul Reviewed-by: Imre Deak Reviewed-by: Lyude Paul Link: https://patchwork.freedesktop.org/patch/msgid/904fa73ea9ea976185062eeb493a08ffc43ed27e.1733238941.git.jani.nikula@intel.com Signed-off-by: Jani Nikula --- drivers/gpu/drm/display/drm_dp_helper.c | 14 ++++++++++++++ drivers/gpu/drm/display/drm_dp_mst_topology.c | 2 +- include/drm/display/drm_dp_helper.h | 1 + 3 files changed, 16 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/gpu/drm/display/drm_dp_helper.c b/drivers/gpu/drm/display/drm_dp_helper.c index 55eca899ce18..da3c8521a7fa 100644 --- a/drivers/gpu/drm/display/drm_dp_helper.c +++ b/drivers/gpu/drm/display/drm_dp_helper.c @@ -849,6 +849,20 @@ fail: } EXPORT_SYMBOL(drm_dp_dpcd_write_payload); +/** + * drm_dp_dpcd_clear_payload() - Clear the entire VC Payload ID table + * @aux: DisplayPort AUX channel + * + * Clear the entire VC Payload ID table. + * + * Returns: 0 on success, negative error code on errors. + */ +int drm_dp_dpcd_clear_payload(struct drm_dp_aux *aux) +{ + return drm_dp_dpcd_write_payload(aux, 0, 0, 0x3f); +} +EXPORT_SYMBOL(drm_dp_dpcd_clear_payload); + /** * drm_dp_dpcd_poll_act_handled() - Poll for ACT handled status * @aux: DisplayPort AUX channel diff --git a/drivers/gpu/drm/display/drm_dp_mst_topology.c b/drivers/gpu/drm/display/drm_dp_mst_topology.c index a426d13a7a36..307ce0981e2c 100644 --- a/drivers/gpu/drm/display/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/display/drm_dp_mst_topology.c @@ -3679,7 +3679,7 @@ int drm_dp_mst_topology_mgr_set_mst(struct drm_dp_mst_topology_mgr *mgr, bool ms goto out_unlock; /* Write reset payload */ - drm_dp_dpcd_write_payload(mgr->aux, 0, 0, 0x3f); + drm_dp_dpcd_clear_payload(mgr->aux); drm_dp_mst_queue_probe_work(mgr); diff --git a/include/drm/display/drm_dp_helper.h b/include/drm/display/drm_dp_helper.h index 69793815aa82..8f4054a56039 100644 --- a/include/drm/display/drm_dp_helper.h +++ b/include/drm/display/drm_dp_helper.h @@ -569,6 +569,7 @@ int drm_dp_dpcd_read_phy_link_status(struct drm_dp_aux *aux, int drm_dp_dpcd_write_payload(struct drm_dp_aux *aux, int vcpid, u8 start_time_slot, u8 time_slot_count); +int drm_dp_dpcd_clear_payload(struct drm_dp_aux *aux); int drm_dp_dpcd_poll_act_handled(struct drm_dp_aux *aux, int timeout_ms); bool drm_dp_send_real_edid_checksum(struct drm_dp_aux *aux, -- cgit v1.2.3 From c6eabbab359c156669e10d5dec3e71e80ff09bd2 Mon Sep 17 00:00:00 2001 From: Christian Gmeiner Date: Mon, 2 Dec 2024 15:06:13 +0100 Subject: drm/v3d: Add DRM_IOCTL_V3D_PERFMON_SET_GLOBAL MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a new ioctl, DRM_IOCTL_V3D_PERFMON_SET_GLOBAL, to allow configuration of a global performance monitor (perfmon). Use the global perfmon for all jobs to ensure consistent performance tracking across submissions. This feature is needed to implement a Perfetto datasources in user-space. Signed-off-by: Christian Gmeiner Reviewed-by: Maíra Canal Signed-off-by: Maíra Canal Link: https://patchwork.freedesktop.org/patch/msgid/20241202140615.74802-1-christian.gmeiner@gmail.com --- drivers/gpu/drm/v3d/v3d_drv.c | 1 + drivers/gpu/drm/v3d/v3d_drv.h | 8 ++++++++ drivers/gpu/drm/v3d/v3d_perfmon.c | 37 +++++++++++++++++++++++++++++++++++++ drivers/gpu/drm/v3d/v3d_sched.c | 14 +++++++++++--- drivers/gpu/drm/v3d/v3d_submit.c | 10 ++++++++++ include/uapi/drm/v3d_drm.h | 18 ++++++++++++++++++ 6 files changed, 85 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/v3d/v3d_drv.c b/drivers/gpu/drm/v3d/v3d_drv.c index fb35c5c3f1a7..8e5cacfa38d3 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.c +++ b/drivers/gpu/drm/v3d/v3d_drv.c @@ -224,6 +224,7 @@ static const struct drm_ioctl_desc v3d_drm_ioctls[] = { DRM_IOCTL_DEF_DRV(V3D_PERFMON_GET_VALUES, v3d_perfmon_get_values_ioctl, DRM_RENDER_ALLOW), DRM_IOCTL_DEF_DRV(V3D_SUBMIT_CPU, v3d_submit_cpu_ioctl, DRM_RENDER_ALLOW | DRM_AUTH), DRM_IOCTL_DEF_DRV(V3D_PERFMON_GET_COUNTER, v3d_perfmon_get_counter_ioctl, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(V3D_PERFMON_SET_GLOBAL, v3d_perfmon_set_global_ioctl, DRM_RENDER_ALLOW), }; static const struct drm_driver v3d_drm_driver = { diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h index de73eefff9ac..dc1cfe2e14be 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.h +++ b/drivers/gpu/drm/v3d/v3d_drv.h @@ -183,6 +183,12 @@ struct v3d_dev { u32 num_allocated; u32 pages_allocated; } bo_stats; + + /* To support a performance analysis tool in user space, we require + * a single, globally configured performance monitor (perfmon) for + * all jobs. + */ + struct v3d_perfmon *global_perfmon; }; static inline struct v3d_dev * @@ -594,6 +600,8 @@ int v3d_perfmon_get_values_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv); int v3d_perfmon_get_counter_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv); +int v3d_perfmon_set_global_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_priv); /* v3d_sysfs.c */ int v3d_sysfs_init(struct device *dev); diff --git a/drivers/gpu/drm/v3d/v3d_perfmon.c b/drivers/gpu/drm/v3d/v3d_perfmon.c index b4c3708ea781..a1429b9684e0 100644 --- a/drivers/gpu/drm/v3d/v3d_perfmon.c +++ b/drivers/gpu/drm/v3d/v3d_perfmon.c @@ -313,6 +313,9 @@ static int v3d_perfmon_idr_del(int id, void *elem, void *data) if (perfmon == v3d->active_perfmon) v3d_perfmon_stop(v3d, perfmon, false); + /* If the global perfmon is being destroyed, set it to NULL */ + cmpxchg(&v3d->global_perfmon, perfmon, NULL); + v3d_perfmon_put(perfmon); return 0; @@ -398,6 +401,9 @@ int v3d_perfmon_destroy_ioctl(struct drm_device *dev, void *data, if (perfmon == v3d->active_perfmon) v3d_perfmon_stop(v3d, perfmon, false); + /* If the global perfmon is being destroyed, set it to NULL */ + cmpxchg(&v3d->global_perfmon, perfmon, NULL); + v3d_perfmon_put(perfmon); return 0; @@ -457,3 +463,34 @@ int v3d_perfmon_get_counter_ioctl(struct drm_device *dev, void *data, return 0; } + +int v3d_perfmon_set_global_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_priv) +{ + struct v3d_file_priv *v3d_priv = file_priv->driver_priv; + struct drm_v3d_perfmon_set_global *req = data; + struct v3d_dev *v3d = to_v3d_dev(dev); + struct v3d_perfmon *perfmon; + + if (req->flags & ~DRM_V3D_PERFMON_CLEAR_GLOBAL) + return -EINVAL; + + perfmon = v3d_perfmon_find(v3d_priv, req->id); + if (!perfmon) + return -EINVAL; + + /* If the request is to clear the global performance monitor */ + if (req->flags & DRM_V3D_PERFMON_CLEAR_GLOBAL) { + if (!v3d->global_perfmon) + return -EINVAL; + + xchg(&v3d->global_perfmon, NULL); + + return 0; + } + + if (cmpxchg(&v3d->global_perfmon, NULL, perfmon)) + return -EBUSY; + + return 0; +} diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c index 99ac4995b5a1..a6c3760da6ed 100644 --- a/drivers/gpu/drm/v3d/v3d_sched.c +++ b/drivers/gpu/drm/v3d/v3d_sched.c @@ -120,11 +120,19 @@ v3d_cpu_job_free(struct drm_sched_job *sched_job) static void v3d_switch_perfmon(struct v3d_dev *v3d, struct v3d_job *job) { - if (job->perfmon != v3d->active_perfmon) + struct v3d_perfmon *perfmon = v3d->global_perfmon; + + if (!perfmon) + perfmon = job->perfmon; + + if (perfmon == v3d->active_perfmon) + return; + + if (perfmon != v3d->active_perfmon) v3d_perfmon_stop(v3d, v3d->active_perfmon, true); - if (job->perfmon && v3d->active_perfmon != job->perfmon) - v3d_perfmon_start(v3d, job->perfmon); + if (perfmon && v3d->active_perfmon != perfmon) + v3d_perfmon_start(v3d, perfmon); } static void diff --git a/drivers/gpu/drm/v3d/v3d_submit.c b/drivers/gpu/drm/v3d/v3d_submit.c index d607aa9c4ec2..9e439c9f0a93 100644 --- a/drivers/gpu/drm/v3d/v3d_submit.c +++ b/drivers/gpu/drm/v3d/v3d_submit.c @@ -981,6 +981,11 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data, goto fail; if (args->perfmon_id) { + if (v3d->global_perfmon) { + ret = -EAGAIN; + goto fail_perfmon; + } + render->base.perfmon = v3d_perfmon_find(v3d_priv, args->perfmon_id); @@ -1196,6 +1201,11 @@ v3d_submit_csd_ioctl(struct drm_device *dev, void *data, goto fail; if (args->perfmon_id) { + if (v3d->global_perfmon) { + ret = -EAGAIN; + goto fail_perfmon; + } + job->base.perfmon = v3d_perfmon_find(v3d_priv, args->perfmon_id); if (!job->base.perfmon) { diff --git a/include/uapi/drm/v3d_drm.h b/include/uapi/drm/v3d_drm.h index 2376c73abca1..dbbc404d2b3d 100644 --- a/include/uapi/drm/v3d_drm.h +++ b/include/uapi/drm/v3d_drm.h @@ -43,6 +43,7 @@ extern "C" { #define DRM_V3D_PERFMON_GET_VALUES 0x0a #define DRM_V3D_SUBMIT_CPU 0x0b #define DRM_V3D_PERFMON_GET_COUNTER 0x0c +#define DRM_V3D_PERFMON_SET_GLOBAL 0x0d #define DRM_IOCTL_V3D_SUBMIT_CL DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_SUBMIT_CL, struct drm_v3d_submit_cl) #define DRM_IOCTL_V3D_WAIT_BO DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_WAIT_BO, struct drm_v3d_wait_bo) @@ -61,6 +62,8 @@ extern "C" { #define DRM_IOCTL_V3D_SUBMIT_CPU DRM_IOW(DRM_COMMAND_BASE + DRM_V3D_SUBMIT_CPU, struct drm_v3d_submit_cpu) #define DRM_IOCTL_V3D_PERFMON_GET_COUNTER DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_PERFMON_GET_COUNTER, \ struct drm_v3d_perfmon_get_counter) +#define DRM_IOCTL_V3D_PERFMON_SET_GLOBAL DRM_IOW(DRM_COMMAND_BASE + DRM_V3D_PERFMON_SET_GLOBAL, \ + struct drm_v3d_perfmon_set_global) #define DRM_V3D_SUBMIT_CL_FLUSH_CACHE 0x01 #define DRM_V3D_SUBMIT_EXTENSION 0x02 @@ -766,6 +769,21 @@ struct drm_v3d_perfmon_get_counter { __u8 reserved[7]; }; +#define DRM_V3D_PERFMON_CLEAR_GLOBAL 0x0001 + +/** + * struct drm_v3d_perfmon_set_global - ioctl to define a global performance + * monitor + * + * The global performance monitor will be used for all jobs. If a global + * performance monitor is defined, jobs with a self-defined performance + * monitor won't be allowed. + */ +struct drm_v3d_perfmon_set_global { + __u32 flags; + __u32 id; +}; + #if defined(__cplusplus) } #endif -- cgit v1.2.3 From cb2e1c2136f71618142557ceca3a8802e87a44cd Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Wed, 4 Dec 2024 16:31:12 +0200 Subject: drm: remove driver date from struct drm_driver and all drivers We stopped using the driver initialized date in commit 7fb8af6798e8 ("drm: deprecate driver date") and (eventually) started returning "0" for drm_version ioctl instead. Finish the job, and remove the unused date member from struct drm_driver, its initialization from drivers, along with the common DRIVER_DATE macros. v2: Also update drivers/accel (kernel test robot) Reviewed-by: Javier Martinez Canillas Acked-by: Alex Deucher Acked-by: Simon Ser Acked-by: Jeffrey Hugo Acked-by: Lucas De Marchi Acked-by: Dmitry Baryshkov # msm Reviewed-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/1f2bf2543aed270a06f6c707fd6ed1b78bf16712.1733322525.git.jani.nikula@intel.com Signed-off-by: Jani Nikula --- drivers/accel/habanalabs/common/habanalabs_drv.c | 1 - drivers/accel/ivpu/ivpu_drv.c | 1 - drivers/accel/qaic/qaic_drv.c | 1 - drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 2 -- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.h | 1 - drivers/gpu/drm/arm/display/komeda/komeda_kms.c | 1 - drivers/gpu/drm/arm/hdlcd_drv.c | 1 - drivers/gpu/drm/arm/malidp_drv.c | 1 - drivers/gpu/drm/armada/armada_drv.c | 1 - drivers/gpu/drm/aspeed/aspeed_gfx_drv.c | 1 - drivers/gpu/drm/ast/ast_drv.c | 1 - drivers/gpu/drm/ast/ast_drv.h | 1 - drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c | 1 - drivers/gpu/drm/etnaviv/etnaviv_drv.c | 1 - drivers/gpu/drm/exynos/exynos_drm_drv.c | 2 -- drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c | 1 - drivers/gpu/drm/gma500/psb_drv.c | 1 - drivers/gpu/drm/gma500/psb_drv.h | 1 - drivers/gpu/drm/gud/gud_drv.c | 1 - drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c | 1 - drivers/gpu/drm/hisilicon/kirin/kirin_drm_ade.c | 1 - drivers/gpu/drm/hyperv/hyperv_drm_drv.c | 2 -- drivers/gpu/drm/i915/i915_driver.c | 1 - drivers/gpu/drm/i915/i915_driver.h | 1 - drivers/gpu/drm/i915/i915_gpu_error.c | 1 - drivers/gpu/drm/imagination/pvr_drv.c | 1 - drivers/gpu/drm/imagination/pvr_drv.h | 1 - drivers/gpu/drm/imx/dcss/dcss-kms.c | 1 - drivers/gpu/drm/imx/ipuv3/imx-drm-core.c | 1 - drivers/gpu/drm/imx/lcdc/imx-lcdc.c | 1 - drivers/gpu/drm/ingenic/ingenic-drm-drv.c | 1 - drivers/gpu/drm/kmb/kmb_drv.c | 1 - drivers/gpu/drm/kmb/kmb_drv.h | 1 - drivers/gpu/drm/lima/lima_drv.c | 1 - drivers/gpu/drm/logicvc/logicvc_drm.c | 1 - drivers/gpu/drm/loongson/lsdc_drv.c | 2 -- drivers/gpu/drm/mcde/mcde_drv.c | 1 - drivers/gpu/drm/mediatek/mtk_drm_drv.c | 2 -- drivers/gpu/drm/meson/meson_drv.c | 1 - drivers/gpu/drm/mgag200/mgag200_drv.c | 1 - drivers/gpu/drm/mgag200/mgag200_drv.h | 1 - drivers/gpu/drm/msm/msm_drv.c | 1 - drivers/gpu/drm/mxsfb/lcdif_drv.c | 1 - drivers/gpu/drm/mxsfb/mxsfb_drv.c | 1 - drivers/gpu/drm/nouveau/nouveau_drm.c | 5 ----- drivers/gpu/drm/nouveau/nouveau_drv.h | 1 - drivers/gpu/drm/omapdrm/omap_drv.c | 2 -- drivers/gpu/drm/panfrost/panfrost_drv.c | 1 - drivers/gpu/drm/panthor/panthor_drv.c | 1 - drivers/gpu/drm/pl111/pl111_drv.c | 1 - drivers/gpu/drm/qxl/qxl_drv.c | 1 - drivers/gpu/drm/qxl/qxl_drv.h | 1 - drivers/gpu/drm/radeon/radeon_drv.c | 1 - drivers/gpu/drm/radeon/radeon_drv.h | 1 - drivers/gpu/drm/renesas/rcar-du/rcar_du_drv.c | 1 - drivers/gpu/drm/renesas/rz-du/rzg2l_du_drv.c | 1 - drivers/gpu/drm/renesas/shmobile/shmob_drm_drv.c | 1 - drivers/gpu/drm/rockchip/rockchip_drm_drv.c | 2 -- drivers/gpu/drm/solomon/ssd130x.c | 2 -- drivers/gpu/drm/sprd/sprd_drm.c | 2 -- drivers/gpu/drm/sti/sti_drv.c | 2 -- drivers/gpu/drm/stm/drv.c | 1 - drivers/gpu/drm/sun4i/sun4i_drv.c | 1 - drivers/gpu/drm/tegra/drm.c | 2 -- drivers/gpu/drm/tidss/tidss_drv.c | 1 - drivers/gpu/drm/tilcdc/tilcdc_drv.c | 1 - drivers/gpu/drm/tiny/arcpgu.c | 1 - drivers/gpu/drm/tiny/bochs.c | 1 - drivers/gpu/drm/tiny/cirrus-qemu.c | 2 -- drivers/gpu/drm/tiny/gm12u320.c | 2 -- drivers/gpu/drm/tiny/hx8357d.c | 1 - drivers/gpu/drm/tiny/ili9163.c | 1 - drivers/gpu/drm/tiny/ili9225.c | 1 - drivers/gpu/drm/tiny/ili9341.c | 1 - drivers/gpu/drm/tiny/ili9486.c | 1 - drivers/gpu/drm/tiny/mi0283qt.c | 1 - drivers/gpu/drm/tiny/ofdrm.c | 2 -- drivers/gpu/drm/tiny/panel-mipi-dbi.c | 1 - drivers/gpu/drm/tiny/repaper.c | 1 - drivers/gpu/drm/tiny/sharp-memory.c | 1 - drivers/gpu/drm/tiny/simpledrm.c | 2 -- drivers/gpu/drm/tiny/st7586.c | 1 - drivers/gpu/drm/tiny/st7735r.c | 1 - drivers/gpu/drm/tve200/tve200_drv.c | 1 - drivers/gpu/drm/udl/udl_drv.c | 1 - drivers/gpu/drm/udl/udl_drv.h | 1 - drivers/gpu/drm/v3d/v3d_drv.c | 2 -- drivers/gpu/drm/vboxvideo/vbox_drv.c | 1 - drivers/gpu/drm/vboxvideo/vbox_drv.h | 1 - drivers/gpu/drm/vc4/vc4_drv.c | 3 --- drivers/gpu/drm/vgem/vgem_drv.c | 2 -- drivers/gpu/drm/virtio/virtgpu_drv.c | 1 - drivers/gpu/drm/virtio/virtgpu_drv.h | 1 - drivers/gpu/drm/vkms/vkms_drv.c | 2 -- drivers/gpu/drm/vmwgfx/vmwgfx_drv.c | 1 - drivers/gpu/drm/vmwgfx/vmwgfx_drv.h | 1 - drivers/gpu/drm/xe/xe_device.c | 1 - drivers/gpu/drm/xe/xe_drv.h | 1 - drivers/gpu/drm/xen/xen_drm_front.c | 1 - drivers/gpu/drm/xlnx/zynqmp_kms.c | 1 - include/drm/drm_drv.h | 2 -- 101 files changed, 126 deletions(-) (limited to 'include') diff --git a/drivers/accel/habanalabs/common/habanalabs_drv.c b/drivers/accel/habanalabs/common/habanalabs_drv.c index 708dfd10f39c..5409b2c656c8 100644 --- a/drivers/accel/habanalabs/common/habanalabs_drv.c +++ b/drivers/accel/habanalabs/common/habanalabs_drv.c @@ -101,7 +101,6 @@ static const struct drm_driver hl_driver = { .major = LINUX_VERSION_MAJOR, .minor = LINUX_VERSION_PATCHLEVEL, .patchlevel = LINUX_VERSION_SUBLEVEL, - .date = "20190505", .fops = &hl_fops, .open = hl_device_open, diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c index 1f359dbe5150..1e8ffbe25eee 100644 --- a/drivers/accel/ivpu/ivpu_drv.c +++ b/drivers/accel/ivpu/ivpu_drv.c @@ -458,7 +458,6 @@ static const struct drm_driver driver = { .name = DRIVER_NAME, .desc = DRIVER_DESC, - .date = UTS_RELEASE, .major = 1, }; diff --git a/drivers/accel/qaic/qaic_drv.c b/drivers/accel/qaic/qaic_drv.c index 3575e0c984d6..542c5d24e499 100644 --- a/drivers/accel/qaic/qaic_drv.c +++ b/drivers/accel/qaic/qaic_drv.c @@ -208,7 +208,6 @@ static const struct drm_driver qaic_accel_driver = { .name = QAIC_NAME, .desc = QAIC_DESC, - .date = "20190618", .fops = &qaic_accel_fops, .open = qaic_open, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 346746d6c233..eaeaaddb32cd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -2916,7 +2916,6 @@ static const struct drm_driver amdgpu_kms_driver = { .name = DRIVER_NAME, .desc = DRIVER_DESC, - .date = DRIVER_DATE, .major = KMS_DRIVER_MAJOR, .minor = KMS_DRIVER_MINOR, .patchlevel = KMS_DRIVER_PATCHLEVEL, @@ -2940,7 +2939,6 @@ const struct drm_driver amdgpu_partition_driver = { .name = DRIVER_NAME, .desc = DRIVER_DESC, - .date = DRIVER_DATE, .major = KMS_DRIVER_MAJOR, .minor = KMS_DRIVER_MINOR, .patchlevel = KMS_DRIVER_PATCHLEVEL, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.h index 5bc2cb661af7..2d86cc6f7f4d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.h @@ -40,7 +40,6 @@ #define DRIVER_NAME "amdgpu" #define DRIVER_DESC "AMD GPU" -#define DRIVER_DATE "20150101" extern const struct drm_driver amdgpu_partition_driver; diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_kms.c b/drivers/gpu/drm/arm/display/komeda/komeda_kms.c index 1e7b1fcb2848..6ed504099188 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_kms.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_kms.c @@ -63,7 +63,6 @@ static const struct drm_driver komeda_kms_driver = { .fops = &komeda_cma_fops, .name = "komeda", .desc = "Arm Komeda Display Processor driver", - .date = "20181101", .major = 0, .minor = 1, }; diff --git a/drivers/gpu/drm/arm/hdlcd_drv.c b/drivers/gpu/drm/arm/hdlcd_drv.c index 4af8fce7dab7..8617d10940d8 100644 --- a/drivers/gpu/drm/arm/hdlcd_drv.c +++ b/drivers/gpu/drm/arm/hdlcd_drv.c @@ -233,7 +233,6 @@ static const struct drm_driver hdlcd_driver = { .fops = &fops, .name = "hdlcd", .desc = "ARM HDLCD Controller DRM", - .date = "20151021", .major = 1, .minor = 0, }; diff --git a/drivers/gpu/drm/arm/malidp_drv.c b/drivers/gpu/drm/arm/malidp_drv.c index 38b1b5b6bf69..3abc9339464b 100644 --- a/drivers/gpu/drm/arm/malidp_drv.c +++ b/drivers/gpu/drm/arm/malidp_drv.c @@ -570,7 +570,6 @@ static const struct drm_driver malidp_driver = { .fops = &fops, .name = "mali-dp", .desc = "ARM Mali Display Processor driver", - .date = "20160106", .major = 1, .minor = 0, }; diff --git a/drivers/gpu/drm/armada/armada_drv.c b/drivers/gpu/drm/armada/armada_drv.c index ddf0eaf546a6..5d5b7435970a 100644 --- a/drivers/gpu/drm/armada/armada_drv.c +++ b/drivers/gpu/drm/armada/armada_drv.c @@ -45,7 +45,6 @@ static const struct drm_driver armada_drm_driver = { .minor = 0, .name = "armada-drm", .desc = "Armada SoC DRM", - .date = "20120730", .driver_features = DRIVER_GEM | DRIVER_MODESET | DRIVER_ATOMIC, .ioctls = armada_ioctls, .num_ioctls = ARRAY_SIZE(armada_ioctls), diff --git a/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c b/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c index 55e90ab9b231..90189a3cf886 100644 --- a/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c +++ b/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c @@ -252,7 +252,6 @@ static const struct drm_driver aspeed_gfx_driver = { .fops = &fops, .name = "aspeed-gfx-drm", .desc = "ASPEED GFX DRM", - .date = "20180319", .major = 1, .minor = 0, }; diff --git a/drivers/gpu/drm/ast/ast_drv.c b/drivers/gpu/drm/ast/ast_drv.c index 8e9c9cb89a50..ff3bcdd1cff2 100644 --- a/drivers/gpu/drm/ast/ast_drv.c +++ b/drivers/gpu/drm/ast/ast_drv.c @@ -60,7 +60,6 @@ static const struct drm_driver ast_driver = { .fops = &ast_fops, .name = DRIVER_NAME, .desc = DRIVER_DESC, - .date = DRIVER_DATE, .major = DRIVER_MAJOR, .minor = DRIVER_MINOR, .patchlevel = DRIVER_PATCHLEVEL, diff --git a/drivers/gpu/drm/ast/ast_drv.h b/drivers/gpu/drm/ast/ast_drv.h index 21ce3769bf0d..6b4305ac07d4 100644 --- a/drivers/gpu/drm/ast/ast_drv.h +++ b/drivers/gpu/drm/ast/ast_drv.h @@ -43,7 +43,6 @@ #define DRIVER_NAME "ast" #define DRIVER_DESC "AST" -#define DRIVER_DATE "20120228" #define DRIVER_MAJOR 0 #define DRIVER_MINOR 1 diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c index 506289a937e2..b51528b2166c 100644 --- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c +++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c @@ -846,7 +846,6 @@ static const struct drm_driver atmel_hlcdc_dc_driver = { .fops = &fops, .name = "atmel-hlcdc", .desc = "Atmel HLCD Controller DRM", - .date = "20141504", .major = 1, .minor = 0, }; diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.c b/drivers/gpu/drm/etnaviv/etnaviv_drv.c index 9b4e2f4b1bc7..c4ddabe3cabd 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_drv.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.c @@ -503,7 +503,6 @@ static const struct drm_driver etnaviv_drm_driver = { .fops = &fops, .name = "etnaviv", .desc = "etnaviv DRM", - .date = "20151214", .major = 1, .minor = 4, }; diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c index 7e517a2ec681..91ab42b56716 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_drv.c +++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c @@ -35,7 +35,6 @@ #define DRIVER_NAME "exynos" #define DRIVER_DESC "Samsung SoC DRM" -#define DRIVER_DATE "20180330" /* * Interface history: @@ -118,7 +117,6 @@ static const struct drm_driver exynos_drm_driver = { .fops = &exynos_drm_driver_fops, .name = DRIVER_NAME, .desc = DRIVER_DESC, - .date = DRIVER_DATE, .major = DRIVER_MAJOR, .minor = DRIVER_MINOR, }; diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c index 12b2096b6c9d..e1183644ec39 100644 --- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c +++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c @@ -174,7 +174,6 @@ static const struct drm_driver fsl_dcu_drm_driver = { .fops = &fsl_dcu_drm_fops, .name = "fsl-dcu-drm", .desc = "Freescale DCU DRM", - .date = "20160425", .major = 1, .minor = 1, }; diff --git a/drivers/gpu/drm/gma500/psb_drv.c b/drivers/gpu/drm/gma500/psb_drv.c index 2c56ece17d71..85d3557c2eb9 100644 --- a/drivers/gpu/drm/gma500/psb_drv.c +++ b/drivers/gpu/drm/gma500/psb_drv.c @@ -513,7 +513,6 @@ static const struct drm_driver driver = { .fops = &psb_gem_fops, .name = DRIVER_NAME, .desc = DRIVER_DESC, - .date = DRIVER_DATE, .major = DRIVER_MAJOR, .minor = DRIVER_MINOR, .patchlevel = DRIVER_PATCHLEVEL diff --git a/drivers/gpu/drm/gma500/psb_drv.h b/drivers/gpu/drm/gma500/psb_drv.h index de62cbfcdc72..7f77cb2b2751 100644 --- a/drivers/gpu/drm/gma500/psb_drv.h +++ b/drivers/gpu/drm/gma500/psb_drv.h @@ -26,7 +26,6 @@ #define DRIVER_NAME "gma500" #define DRIVER_DESC "DRM driver for the Intel GMA500, GMA600, GMA3600, GMA3650" -#define DRIVER_DATE "20140314" #define DRIVER_MAJOR 1 #define DRIVER_MINOR 0 diff --git a/drivers/gpu/drm/gud/gud_drv.c b/drivers/gpu/drm/gud/gud_drv.c index 65a16f009ea6..cb405771d6e2 100644 --- a/drivers/gpu/drm/gud/gud_drv.c +++ b/drivers/gpu/drm/gud/gud_drv.c @@ -381,7 +381,6 @@ static const struct drm_driver gud_drm_driver = { .name = "gud", .desc = "Generic USB Display", - .date = "20200422", .major = 1, .minor = 0, }; diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c index 69bdae604982..7f814c32ed34 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c @@ -57,7 +57,6 @@ static const struct drm_driver hibmc_driver = { .driver_features = DRIVER_GEM | DRIVER_MODESET | DRIVER_ATOMIC, .fops = &hibmc_fops, .name = "hibmc", - .date = "20160828", .desc = "hibmc drm driver", .major = 1, .minor = 0, diff --git a/drivers/gpu/drm/hisilicon/kirin/kirin_drm_ade.c b/drivers/gpu/drm/hisilicon/kirin/kirin_drm_ade.c index 5616c3917c03..2eb49177ac42 100644 --- a/drivers/gpu/drm/hisilicon/kirin/kirin_drm_ade.c +++ b/drivers/gpu/drm/hisilicon/kirin/kirin_drm_ade.c @@ -929,7 +929,6 @@ static const struct drm_driver ade_driver = { DRM_FBDEV_DMA_DRIVER_OPS, .name = "kirin", .desc = "Hisilicon Kirin620 SoC DRM Driver", - .date = "20150718", .major = 1, .minor = 0, }; diff --git a/drivers/gpu/drm/hyperv/hyperv_drm_drv.c b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c index c5ac240f7a7a..f59abfa7622a 100644 --- a/drivers/gpu/drm/hyperv/hyperv_drm_drv.c +++ b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c @@ -20,7 +20,6 @@ #define DRIVER_NAME "hyperv_drm" #define DRIVER_DESC "DRM driver for Hyper-V synthetic video device" -#define DRIVER_DATE "2020" #define DRIVER_MAJOR 1 #define DRIVER_MINOR 0 @@ -31,7 +30,6 @@ static struct drm_driver hyperv_driver = { .name = DRIVER_NAME, .desc = DRIVER_DESC, - .date = DRIVER_DATE, .major = DRIVER_MAJOR, .minor = DRIVER_MINOR, diff --git a/drivers/gpu/drm/i915/i915_driver.c b/drivers/gpu/drm/i915/i915_driver.c index 365329ff8a07..1bafefb726f5 100644 --- a/drivers/gpu/drm/i915/i915_driver.c +++ b/drivers/gpu/drm/i915/i915_driver.c @@ -1785,7 +1785,6 @@ static const struct drm_driver i915_drm_driver = { .fops = &i915_driver_fops, .name = DRIVER_NAME, .desc = DRIVER_DESC, - .date = DRIVER_DATE, .major = DRIVER_MAJOR, .minor = DRIVER_MINOR, .patchlevel = DRIVER_PATCHLEVEL, diff --git a/drivers/gpu/drm/i915/i915_driver.h b/drivers/gpu/drm/i915/i915_driver.h index 94a70d8ec5d5..4b67ad9a61cd 100644 --- a/drivers/gpu/drm/i915/i915_driver.h +++ b/drivers/gpu/drm/i915/i915_driver.h @@ -15,7 +15,6 @@ struct drm_printer; #define DRIVER_NAME "i915" #define DRIVER_DESC "Intel Graphics" -#define DRIVER_DATE "20230929" #define DRIVER_TIMESTAMP 1695980603 extern const struct dev_pm_ops i915_pm_ops; diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 4eb58887819a..eb975b3815df 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -841,7 +841,6 @@ static void __err_print_to_sgl(struct drm_i915_error_state_buf *m, err_printf(m, "Kernel: %s %s\n", init_utsname()->release, init_utsname()->machine); - err_printf(m, "Driver: %s\n", DRIVER_DATE); ts = ktime_to_timespec64(error->time); err_printf(m, "Time: %lld s %ld us\n", (s64)ts.tv_sec, ts.tv_nsec / NSEC_PER_USEC); diff --git a/drivers/gpu/drm/imagination/pvr_drv.c b/drivers/gpu/drm/imagination/pvr_drv.c index 36c0e768698e..6ab023593476 100644 --- a/drivers/gpu/drm/imagination/pvr_drv.c +++ b/drivers/gpu/drm/imagination/pvr_drv.c @@ -1387,7 +1387,6 @@ static struct drm_driver pvr_drm_driver = { .name = PVR_DRIVER_NAME, .desc = PVR_DRIVER_DESC, - .date = PVR_DRIVER_DATE, .major = PVR_DRIVER_MAJOR, .minor = PVR_DRIVER_MINOR, .patchlevel = PVR_DRIVER_PATCHLEVEL, diff --git a/drivers/gpu/drm/imagination/pvr_drv.h b/drivers/gpu/drm/imagination/pvr_drv.h index 378fe477b759..7fa147312dd1 100644 --- a/drivers/gpu/drm/imagination/pvr_drv.h +++ b/drivers/gpu/drm/imagination/pvr_drv.h @@ -9,7 +9,6 @@ #define PVR_DRIVER_NAME "powervr" #define PVR_DRIVER_DESC "Imagination PowerVR (Series 6 and later) & IMG Graphics" -#define PVR_DRIVER_DATE "20230904" /* * Driver interface version: diff --git a/drivers/gpu/drm/imx/dcss/dcss-kms.c b/drivers/gpu/drm/imx/dcss/dcss-kms.c index 490b5c269f39..3633e8f3aff6 100644 --- a/drivers/gpu/drm/imx/dcss/dcss-kms.c +++ b/drivers/gpu/drm/imx/dcss/dcss-kms.c @@ -34,7 +34,6 @@ static const struct drm_driver dcss_kms_driver = { .fops = &dcss_cma_fops, .name = "imx-dcss", .desc = "i.MX8MQ Display Subsystem", - .date = "20190917", .major = 1, .minor = 0, .patchlevel = 0, diff --git a/drivers/gpu/drm/imx/ipuv3/imx-drm-core.c b/drivers/gpu/drm/imx/ipuv3/imx-drm-core.c index 6b84429735d6..bcb35ba670fc 100644 --- a/drivers/gpu/drm/imx/ipuv3/imx-drm-core.c +++ b/drivers/gpu/drm/imx/ipuv3/imx-drm-core.c @@ -163,7 +163,6 @@ static const struct drm_driver imx_drm_driver = { .fops = &imx_drm_driver_fops, .name = "imx-drm", .desc = "i.MX DRM graphics", - .date = "20120507", .major = 1, .minor = 0, .patchlevel = 0, diff --git a/drivers/gpu/drm/imx/lcdc/imx-lcdc.c b/drivers/gpu/drm/imx/lcdc/imx-lcdc.c index c5121fed80fd..d70981295f88 100644 --- a/drivers/gpu/drm/imx/lcdc/imx-lcdc.c +++ b/drivers/gpu/drm/imx/lcdc/imx-lcdc.c @@ -352,7 +352,6 @@ static struct drm_driver imx_lcdc_drm_driver = { DRM_FBDEV_DMA_DRIVER_OPS, .name = "imx-lcdc", .desc = "i.MX LCDC driver", - .date = "20200716", }; static const struct of_device_id imx_lcdc_of_dev_id[] = { diff --git a/drivers/gpu/drm/ingenic/ingenic-drm-drv.c b/drivers/gpu/drm/ingenic/ingenic-drm-drv.c index 0a4eb3994cd6..6546d9ec410a 100644 --- a/drivers/gpu/drm/ingenic/ingenic-drm-drv.c +++ b/drivers/gpu/drm/ingenic/ingenic-drm-drv.c @@ -953,7 +953,6 @@ static const struct drm_driver ingenic_drm_driver_data = { .driver_features = DRIVER_MODESET | DRIVER_GEM | DRIVER_ATOMIC, .name = "ingenic-drm", .desc = "DRM module for Ingenic SoCs", - .date = "20200716", .major = 1, .minor = 1, .patchlevel = 0, diff --git a/drivers/gpu/drm/kmb/kmb_drv.c b/drivers/gpu/drm/kmb/kmb_drv.c index 4173344ba32c..c340b4c6a74b 100644 --- a/drivers/gpu/drm/kmb/kmb_drv.c +++ b/drivers/gpu/drm/kmb/kmb_drv.c @@ -445,7 +445,6 @@ static const struct drm_driver kmb_driver = { DRM_FBDEV_DMA_DRIVER_OPS, .name = "kmb-drm", .desc = "KEEMBAY DISPLAY DRIVER", - .date = DRIVER_DATE, .major = DRIVER_MAJOR, .minor = DRIVER_MINOR, }; diff --git a/drivers/gpu/drm/kmb/kmb_drv.h b/drivers/gpu/drm/kmb/kmb_drv.h index bf085e95b28f..1f0c10d317fe 100644 --- a/drivers/gpu/drm/kmb/kmb_drv.h +++ b/drivers/gpu/drm/kmb/kmb_drv.h @@ -16,7 +16,6 @@ #define KMB_MIN_WIDTH 1920 /*Max width in pixels */ #define KMB_MIN_HEIGHT 1080 /*Max height in pixels */ -#define DRIVER_DATE "20210223" #define DRIVER_MAJOR 1 #define DRIVER_MINOR 1 diff --git a/drivers/gpu/drm/lima/lima_drv.c b/drivers/gpu/drm/lima/lima_drv.c index 10bce18b7c31..4b70c5189f7c 100644 --- a/drivers/gpu/drm/lima/lima_drv.c +++ b/drivers/gpu/drm/lima/lima_drv.c @@ -271,7 +271,6 @@ static const struct drm_driver lima_drm_driver = { .fops = &lima_drm_driver_fops, .name = "lima", .desc = "lima DRM", - .date = "20191231", .major = 1, .minor = 1, .patchlevel = 0, diff --git a/drivers/gpu/drm/logicvc/logicvc_drm.c b/drivers/gpu/drm/logicvc/logicvc_drm.c index 9152034e54a3..bda2a689d928 100644 --- a/drivers/gpu/drm/logicvc/logicvc_drm.c +++ b/drivers/gpu/drm/logicvc/logicvc_drm.c @@ -52,7 +52,6 @@ static struct drm_driver logicvc_drm_driver = { .fops = &logicvc_drm_fops, .name = "logicvc-drm", .desc = "Xylon LogiCVC DRM driver", - .date = "20200403", .major = 1, .minor = 0, diff --git a/drivers/gpu/drm/loongson/lsdc_drv.c b/drivers/gpu/drm/loongson/lsdc_drv.c index a55aa1fe2c21..12193d2a301a 100644 --- a/drivers/gpu/drm/loongson/lsdc_drv.c +++ b/drivers/gpu/drm/loongson/lsdc_drv.c @@ -26,7 +26,6 @@ #define DRIVER_AUTHOR "Sui Jingfeng " #define DRIVER_NAME "loongson" #define DRIVER_DESC "drm driver for loongson graphics" -#define DRIVER_DATE "20220701" #define DRIVER_MAJOR 1 #define DRIVER_MINOR 0 #define DRIVER_PATCHLEVEL 0 @@ -39,7 +38,6 @@ static const struct drm_driver lsdc_drm_driver = { .name = DRIVER_NAME, .desc = DRIVER_DESC, - .date = DRIVER_DATE, .major = DRIVER_MAJOR, .minor = DRIVER_MINOR, .patchlevel = DRIVER_PATCHLEVEL, diff --git a/drivers/gpu/drm/mcde/mcde_drv.c b/drivers/gpu/drm/mcde/mcde_drv.c index f8c7aa9d7f33..324a95d7f15b 100644 --- a/drivers/gpu/drm/mcde/mcde_drv.c +++ b/drivers/gpu/drm/mcde/mcde_drv.c @@ -208,7 +208,6 @@ static const struct drm_driver mcde_drm_driver = { .fops = &drm_fops, .name = "mcde", .desc = DRIVER_DESC, - .date = "20180529", .major = 1, .minor = 0, .patchlevel = 0, diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index 38297d705df6..723782e75c55 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -33,7 +33,6 @@ #define DRIVER_NAME "mediatek" #define DRIVER_DESC "Mediatek SoC DRM" -#define DRIVER_DATE "20150513" #define DRIVER_MAJOR 1 #define DRIVER_MINOR 0 @@ -615,7 +614,6 @@ static const struct drm_driver mtk_drm_driver = { .name = DRIVER_NAME, .desc = DRIVER_DESC, - .date = DRIVER_DATE, .major = DRIVER_MAJOR, .minor = DRIVER_MINOR, }; diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c index 83ee18024682..64c8c4bb60f1 100644 --- a/drivers/gpu/drm/meson/meson_drv.c +++ b/drivers/gpu/drm/meson/meson_drv.c @@ -105,7 +105,6 @@ static const struct drm_driver meson_driver = { .fops = &fops, .name = DRIVER_NAME, .desc = DRIVER_DESC, - .date = "20161109", .major = 1, .minor = 0, }; diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.c b/drivers/gpu/drm/mgag200/mgag200_drv.c index b7ed763addfa..069fdd2dc8f6 100644 --- a/drivers/gpu/drm/mgag200/mgag200_drv.c +++ b/drivers/gpu/drm/mgag200/mgag200_drv.c @@ -97,7 +97,6 @@ static const struct drm_driver mgag200_driver = { .fops = &mgag200_driver_fops, .name = DRIVER_NAME, .desc = DRIVER_DESC, - .date = DRIVER_DATE, .major = DRIVER_MAJOR, .minor = DRIVER_MINOR, .patchlevel = DRIVER_PATCHLEVEL, diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.h b/drivers/gpu/drm/mgag200/mgag200_drv.h index 988967eafbf2..0608fc63e588 100644 --- a/drivers/gpu/drm/mgag200/mgag200_drv.h +++ b/drivers/gpu/drm/mgag200/mgag200_drv.h @@ -25,7 +25,6 @@ #define DRIVER_NAME "mgag200" #define DRIVER_DESC "MGA G200 SE" -#define DRIVER_DATE "20110418" #define DRIVER_MAJOR 1 #define DRIVER_MINOR 0 diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index b5fa715cbfb0..73e72aee6ec5 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -910,7 +910,6 @@ static const struct drm_driver msm_driver = { .fops = &fops, .name = "msm", .desc = "MSM Snapdragon DRM", - .date = "20130625", .major = MSM_VERSION_MAJOR, .minor = MSM_VERSION_MINOR, .patchlevel = MSM_VERSION_PATCHLEVEL, diff --git a/drivers/gpu/drm/mxsfb/lcdif_drv.c b/drivers/gpu/drm/mxsfb/lcdif_drv.c index 81ec91cef66c..02fe6b89f3aa 100644 --- a/drivers/gpu/drm/mxsfb/lcdif_drv.c +++ b/drivers/gpu/drm/mxsfb/lcdif_drv.c @@ -248,7 +248,6 @@ static const struct drm_driver lcdif_driver = { .fops = &fops, .name = "imx-lcdif", .desc = "i.MX LCDIF Controller DRM", - .date = "20220417", .major = 1, .minor = 0, }; diff --git a/drivers/gpu/drm/mxsfb/mxsfb_drv.c b/drivers/gpu/drm/mxsfb/mxsfb_drv.c index 1c27a97dce03..129cc3fb4448 100644 --- a/drivers/gpu/drm/mxsfb/mxsfb_drv.c +++ b/drivers/gpu/drm/mxsfb/mxsfb_drv.c @@ -336,7 +336,6 @@ static const struct drm_driver mxsfb_driver = { .fops = &fops, .name = "mxsfb-drm", .desc = "MXSFB Controller DRM", - .date = "20160824", .major = 1, .minor = 0, }; diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index 7eee22657a1c..21d2d9ca5e85 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -1342,11 +1342,6 @@ driver_stub = { .name = DRIVER_NAME, .desc = DRIVER_DESC, -#ifdef GIT_REVISION - .date = GIT_REVISION, -#else - .date = DRIVER_DATE, -#endif .major = DRIVER_MAJOR, .minor = DRIVER_MINOR, .patchlevel = DRIVER_PATCHLEVEL, diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h index 685d6ca3d8aa..55abc510067b 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drv.h +++ b/drivers/gpu/drm/nouveau/nouveau_drv.h @@ -7,7 +7,6 @@ #define DRIVER_NAME "nouveau" #define DRIVER_DESC "nVidia Riva/TNT/GeForce/Quadro/Tesla/Tegra K1+" -#define DRIVER_DATE "20120801" #define DRIVER_MAJOR 1 #define DRIVER_MINOR 4 diff --git a/drivers/gpu/drm/omapdrm/omap_drv.c b/drivers/gpu/drm/omapdrm/omap_drv.c index 1796cd20a877..a80e0f375a0e 100644 --- a/drivers/gpu/drm/omapdrm/omap_drv.c +++ b/drivers/gpu/drm/omapdrm/omap_drv.c @@ -28,7 +28,6 @@ #define DRIVER_NAME MODULE_NAME #define DRIVER_DESC "OMAP DRM" -#define DRIVER_DATE "20110917" #define DRIVER_MAJOR 1 #define DRIVER_MINOR 0 #define DRIVER_PATCHLEVEL 0 @@ -653,7 +652,6 @@ static const struct drm_driver omap_drm_driver = { .fops = &omapdriver_fops, .name = DRIVER_NAME, .desc = DRIVER_DESC, - .date = DRIVER_DATE, .major = DRIVER_MAJOR, .minor = DRIVER_MINOR, .patchlevel = DRIVER_PATCHLEVEL, diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c index 04d615df5259..fbaef3afcd66 100644 --- a/drivers/gpu/drm/panfrost/panfrost_drv.c +++ b/drivers/gpu/drm/panfrost/panfrost_drv.c @@ -636,7 +636,6 @@ static const struct drm_driver panfrost_drm_driver = { .fops = &panfrost_drm_driver_fops, .name = "panfrost", .desc = "panfrost DRM", - .date = "20180908", .major = 1, .minor = 3, diff --git a/drivers/gpu/drm/panthor/panthor_drv.c b/drivers/gpu/drm/panthor/panthor_drv.c index ac7e53f6e3f0..ad46a40ed9e1 100644 --- a/drivers/gpu/drm/panthor/panthor_drv.c +++ b/drivers/gpu/drm/panthor/panthor_drv.c @@ -1505,7 +1505,6 @@ static const struct drm_driver panthor_drm_driver = { .fops = &panthor_drm_driver_fops, .name = "panthor", .desc = "Panthor DRM driver", - .date = "20230801", .major = 1, .minor = 2, diff --git a/drivers/gpu/drm/pl111/pl111_drv.c b/drivers/gpu/drm/pl111/pl111_drv.c index 4b96f48cf630..56ff6a3fb483 100644 --- a/drivers/gpu/drm/pl111/pl111_drv.c +++ b/drivers/gpu/drm/pl111/pl111_drv.c @@ -220,7 +220,6 @@ static const struct drm_driver pl111_drm_driver = { .fops = &drm_fops, .name = "pl111", .desc = DRIVER_DESC, - .date = "20170317", .major = 1, .minor = 0, .patchlevel = 0, diff --git a/drivers/gpu/drm/qxl/qxl_drv.c b/drivers/gpu/drm/qxl/qxl_drv.c index f15e9583b098..417061ae59eb 100644 --- a/drivers/gpu/drm/qxl/qxl_drv.c +++ b/drivers/gpu/drm/qxl/qxl_drv.c @@ -300,7 +300,6 @@ static struct drm_driver qxl_driver = { .num_ioctls = ARRAY_SIZE(qxl_ioctls), .name = DRIVER_NAME, .desc = DRIVER_DESC, - .date = DRIVER_DATE, .major = 0, .minor = 1, .patchlevel = 0, diff --git a/drivers/gpu/drm/qxl/qxl_drv.h b/drivers/gpu/drm/qxl/qxl_drv.h index b5fc14c9525d..cc02b5f10ad9 100644 --- a/drivers/gpu/drm/qxl/qxl_drv.h +++ b/drivers/gpu/drm/qxl/qxl_drv.h @@ -54,7 +54,6 @@ struct iosys_map; #define DRIVER_NAME "qxl" #define DRIVER_DESC "RH QXL" -#define DRIVER_DATE "20120117" #define DRIVER_MAJOR 0 #define DRIVER_MINOR 1 diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c index 5ce7e91bedad..267f082bc430 100644 --- a/drivers/gpu/drm/radeon/radeon_drv.c +++ b/drivers/gpu/drm/radeon/radeon_drv.c @@ -603,7 +603,6 @@ static const struct drm_driver kms_driver = { .name = DRIVER_NAME, .desc = DRIVER_DESC, - .date = DRIVER_DATE, .major = KMS_DRIVER_MAJOR, .minor = KMS_DRIVER_MINOR, .patchlevel = KMS_DRIVER_PATCHLEVEL, diff --git a/drivers/gpu/drm/radeon/radeon_drv.h b/drivers/gpu/drm/radeon/radeon_drv.h index 02a65971d140..0f3dbffc492d 100644 --- a/drivers/gpu/drm/radeon/radeon_drv.h +++ b/drivers/gpu/drm/radeon/radeon_drv.h @@ -43,7 +43,6 @@ #define DRIVER_NAME "radeon" #define DRIVER_DESC "ATI Radeon" -#define DRIVER_DATE "20080528" /* Interface history: * diff --git a/drivers/gpu/drm/renesas/rcar-du/rcar_du_drv.c b/drivers/gpu/drm/renesas/rcar-du/rcar_du_drv.c index 0f5204ef996e..be39b107b98c 100644 --- a/drivers/gpu/drm/renesas/rcar-du/rcar_du_drv.c +++ b/drivers/gpu/drm/renesas/rcar-du/rcar_du_drv.c @@ -611,7 +611,6 @@ static const struct drm_driver rcar_du_driver = { .fops = &rcar_du_fops, .name = "rcar-du", .desc = "Renesas R-Car Display Unit", - .date = "20130110", .major = 1, .minor = 0, }; diff --git a/drivers/gpu/drm/renesas/rz-du/rzg2l_du_drv.c b/drivers/gpu/drm/renesas/rz-du/rzg2l_du_drv.c index 0a03a20f663b..9bbdc4d63d88 100644 --- a/drivers/gpu/drm/renesas/rz-du/rzg2l_du_drv.c +++ b/drivers/gpu/drm/renesas/rz-du/rzg2l_du_drv.c @@ -84,7 +84,6 @@ static const struct drm_driver rzg2l_du_driver = { .fops = &rzg2l_du_fops, .name = "rzg2l-du", .desc = "Renesas RZ/G2L Display Unit", - .date = "20230410", .major = 1, .minor = 0, }; diff --git a/drivers/gpu/drm/renesas/shmobile/shmob_drm_drv.c b/drivers/gpu/drm/renesas/shmobile/shmob_drm_drv.c index 40b582ee178e..387eb602dadf 100644 --- a/drivers/gpu/drm/renesas/shmobile/shmob_drm_drv.c +++ b/drivers/gpu/drm/renesas/shmobile/shmob_drm_drv.c @@ -107,7 +107,6 @@ static const struct drm_driver shmob_drm_driver = { .fops = &shmob_drm_fops, .name = "shmob-drm", .desc = "Renesas SH Mobile DRM", - .date = "20120424", .major = 1, .minor = 0, }; diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c index 0393b48ad65b..1fe4399d6901 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c @@ -39,7 +39,6 @@ #define DRIVER_NAME "rockchip" #define DRIVER_DESC "RockChip Soc DRM" -#define DRIVER_DATE "20140818" #define DRIVER_MAJOR 1 #define DRIVER_MINOR 0 @@ -235,7 +234,6 @@ static const struct drm_driver rockchip_drm_driver = { .fops = &rockchip_drm_driver_fops, .name = DRIVER_NAME, .desc = DRIVER_DESC, - .date = DRIVER_DATE, .major = DRIVER_MAJOR, .minor = DRIVER_MINOR, }; diff --git a/drivers/gpu/drm/solomon/ssd130x.c b/drivers/gpu/drm/solomon/ssd130x.c index a737f650c2bc..7b9f8fc193ac 100644 --- a/drivers/gpu/drm/solomon/ssd130x.c +++ b/drivers/gpu/drm/solomon/ssd130x.c @@ -39,7 +39,6 @@ #define DRIVER_NAME "ssd130x" #define DRIVER_DESC "DRM driver for Solomon SSD13xx OLED displays" -#define DRIVER_DATE "20220131" #define DRIVER_MAJOR 1 #define DRIVER_MINOR 0 @@ -1784,7 +1783,6 @@ static const struct drm_driver ssd130x_drm_driver = { DRM_FBDEV_SHMEM_DRIVER_OPS, .name = DRIVER_NAME, .desc = DRIVER_DESC, - .date = DRIVER_DATE, .major = DRIVER_MAJOR, .minor = DRIVER_MINOR, .driver_features = DRIVER_ATOMIC | DRIVER_GEM | DRIVER_MODESET, diff --git a/drivers/gpu/drm/sprd/sprd_drm.c b/drivers/gpu/drm/sprd/sprd_drm.c index a74cd0caf645..867ee2d8997f 100644 --- a/drivers/gpu/drm/sprd/sprd_drm.c +++ b/drivers/gpu/drm/sprd/sprd_drm.c @@ -23,7 +23,6 @@ #define DRIVER_NAME "sprd" #define DRIVER_DESC "Spreadtrum SoCs' DRM Driver" -#define DRIVER_DATE "20200201" #define DRIVER_MAJOR 1 #define DRIVER_MINOR 0 @@ -59,7 +58,6 @@ static struct drm_driver sprd_drm_drv = { .name = DRIVER_NAME, .desc = DRIVER_DESC, - .date = DRIVER_DATE, .major = DRIVER_MAJOR, .minor = DRIVER_MINOR, }; diff --git a/drivers/gpu/drm/sti/sti_drv.c b/drivers/gpu/drm/sti/sti_drv.c index a6c13318aa0b..46e6b674fa54 100644 --- a/drivers/gpu/drm/sti/sti_drv.c +++ b/drivers/gpu/drm/sti/sti_drv.c @@ -29,7 +29,6 @@ #define DRIVER_NAME "sti" #define DRIVER_DESC "STMicroelectronics SoC DRM" -#define DRIVER_DATE "20140601" #define DRIVER_MAJOR 1 #define DRIVER_MINOR 0 @@ -143,7 +142,6 @@ static const struct drm_driver sti_driver = { .name = DRIVER_NAME, .desc = DRIVER_DESC, - .date = DRIVER_DATE, .major = DRIVER_MAJOR, .minor = DRIVER_MINOR, }; diff --git a/drivers/gpu/drm/stm/drv.c b/drivers/gpu/drm/stm/drv.c index d181d11b277b..40a62c57e04c 100644 --- a/drivers/gpu/drm/stm/drv.c +++ b/drivers/gpu/drm/stm/drv.c @@ -62,7 +62,6 @@ static const struct drm_driver drv_driver = { .driver_features = DRIVER_MODESET | DRIVER_GEM | DRIVER_ATOMIC, .name = "stm", .desc = "STMicroelectronics SoC DRM", - .date = "20170330", .major = 1, .minor = 0, .patchlevel = 0, diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c index a7c11b795e98..025b0bdcbfd9 100644 --- a/drivers/gpu/drm/sun4i/sun4i_drv.c +++ b/drivers/gpu/drm/sun4i/sun4i_drv.c @@ -50,7 +50,6 @@ static const struct drm_driver sun4i_drv_driver = { .fops = &sun4i_drv_fops, .name = "sun4i-drm", .desc = "Allwinner sun4i Display Engine", - .date = "20150629", .major = 1, .minor = 0, diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c index 34878f5d2918..4596073fe28f 100644 --- a/drivers/gpu/drm/tegra/drm.c +++ b/drivers/gpu/drm/tegra/drm.c @@ -35,7 +35,6 @@ #define DRIVER_NAME "tegra" #define DRIVER_DESC "NVIDIA Tegra graphics" -#define DRIVER_DATE "20120330" #define DRIVER_MAJOR 1 #define DRIVER_MINOR 0 #define DRIVER_PATCHLEVEL 0 @@ -901,7 +900,6 @@ static const struct drm_driver tegra_drm_driver = { .name = DRIVER_NAME, .desc = DRIVER_DESC, - .date = DRIVER_DATE, .major = DRIVER_MAJOR, .minor = DRIVER_MINOR, .patchlevel = DRIVER_PATCHLEVEL, diff --git a/drivers/gpu/drm/tidss/tidss_drv.c b/drivers/gpu/drm/tidss/tidss_drv.c index 53bc219c097f..ee1132d581f5 100644 --- a/drivers/gpu/drm/tidss/tidss_drv.c +++ b/drivers/gpu/drm/tidss/tidss_drv.c @@ -113,7 +113,6 @@ static const struct drm_driver tidss_driver = { DRM_FBDEV_DMA_DRIVER_OPS, .name = "tidss", .desc = "TI Keystone DSS", - .date = "20180215", .major = 1, .minor = 0, }; diff --git a/drivers/gpu/drm/tilcdc/tilcdc_drv.c b/drivers/gpu/drm/tilcdc/tilcdc_drv.c index 821d0ba26287..8013f01dbdf0 100644 --- a/drivers/gpu/drm/tilcdc/tilcdc_drv.c +++ b/drivers/gpu/drm/tilcdc/tilcdc_drv.c @@ -481,7 +481,6 @@ static const struct drm_driver tilcdc_driver = { .fops = &fops, .name = "tilcdc", .desc = "TI LCD Controller DRM", - .date = "20121205", .major = 1, .minor = 0, }; diff --git a/drivers/gpu/drm/tiny/arcpgu.c b/drivers/gpu/drm/tiny/arcpgu.c index 5a0c8a874421..1e570f6f639f 100644 --- a/drivers/gpu/drm/tiny/arcpgu.c +++ b/drivers/gpu/drm/tiny/arcpgu.c @@ -367,7 +367,6 @@ static const struct drm_driver arcpgu_drm_driver = { .driver_features = DRIVER_MODESET | DRIVER_GEM | DRIVER_ATOMIC, .name = "arcpgu", .desc = "ARC PGU Controller", - .date = "20160219", .major = 1, .minor = 0, .patchlevel = 0, diff --git a/drivers/gpu/drm/tiny/bochs.c b/drivers/gpu/drm/tiny/bochs.c index 71a1f15d6ac9..89a699370a59 100644 --- a/drivers/gpu/drm/tiny/bochs.c +++ b/drivers/gpu/drm/tiny/bochs.c @@ -680,7 +680,6 @@ static const struct drm_driver bochs_driver = { .fops = &bochs_fops, .name = "bochs-drm", .desc = "bochs dispi vga interface (qemu stdvga)", - .date = "20130925", .major = 1, .minor = 0, DRM_GEM_SHMEM_DRIVER_OPS, diff --git a/drivers/gpu/drm/tiny/cirrus-qemu.c b/drivers/gpu/drm/tiny/cirrus-qemu.c index c0ae316888e2..52ec1e4ea9e5 100644 --- a/drivers/gpu/drm/tiny/cirrus-qemu.c +++ b/drivers/gpu/drm/tiny/cirrus-qemu.c @@ -48,7 +48,6 @@ #define DRIVER_NAME "cirrus-qemu" #define DRIVER_DESC "qemu cirrus vga" -#define DRIVER_DATE "2019" #define DRIVER_MAJOR 2 #define DRIVER_MINOR 0 @@ -659,7 +658,6 @@ static const struct drm_driver cirrus_driver = { .name = DRIVER_NAME, .desc = DRIVER_DESC, - .date = DRIVER_DATE, .major = DRIVER_MAJOR, .minor = DRIVER_MINOR, diff --git a/drivers/gpu/drm/tiny/gm12u320.c b/drivers/gpu/drm/tiny/gm12u320.c index 47dbee84d58b..41e9bfb2e2ff 100644 --- a/drivers/gpu/drm/tiny/gm12u320.c +++ b/drivers/gpu/drm/tiny/gm12u320.c @@ -34,7 +34,6 @@ MODULE_PARM_DESC(eco_mode, "Turn on Eco mode (less bright, more silent)"); #define DRIVER_NAME "gm12u320" #define DRIVER_DESC "Grain Media GM12U320 USB projector display" -#define DRIVER_DATE "2019" #define DRIVER_MAJOR 1 #define DRIVER_MINOR 0 @@ -626,7 +625,6 @@ static const struct drm_driver gm12u320_drm_driver = { .name = DRIVER_NAME, .desc = DRIVER_DESC, - .date = DRIVER_DATE, .major = DRIVER_MAJOR, .minor = DRIVER_MINOR, diff --git a/drivers/gpu/drm/tiny/hx8357d.c b/drivers/gpu/drm/tiny/hx8357d.c index 910279ebbbaa..df263818f45f 100644 --- a/drivers/gpu/drm/tiny/hx8357d.c +++ b/drivers/gpu/drm/tiny/hx8357d.c @@ -199,7 +199,6 @@ static const struct drm_driver hx8357d_driver = { .debugfs_init = mipi_dbi_debugfs_init, .name = "hx8357d", .desc = "HX8357D", - .date = "20181023", .major = 1, .minor = 0, }; diff --git a/drivers/gpu/drm/tiny/ili9163.c b/drivers/gpu/drm/tiny/ili9163.c index e54ce120692f..62cadf5e033d 100644 --- a/drivers/gpu/drm/tiny/ili9163.c +++ b/drivers/gpu/drm/tiny/ili9163.c @@ -118,7 +118,6 @@ static struct drm_driver ili9163_driver = { .debugfs_init = mipi_dbi_debugfs_init, .name = "ili9163", .desc = "Ilitek ILI9163", - .date = "20210208", .major = 1, .minor = 0, }; diff --git a/drivers/gpu/drm/tiny/ili9225.c b/drivers/gpu/drm/tiny/ili9225.c index f322e67f473a..6de44ff69b51 100644 --- a/drivers/gpu/drm/tiny/ili9225.c +++ b/drivers/gpu/drm/tiny/ili9225.c @@ -364,7 +364,6 @@ static const struct drm_driver ili9225_driver = { DRM_FBDEV_DMA_DRIVER_OPS, .name = "ili9225", .desc = "Ilitek ILI9225", - .date = "20171106", .major = 1, .minor = 0, }; diff --git a/drivers/gpu/drm/tiny/ili9341.c b/drivers/gpu/drm/tiny/ili9341.c index 356c7f107c3e..e55029433509 100644 --- a/drivers/gpu/drm/tiny/ili9341.c +++ b/drivers/gpu/drm/tiny/ili9341.c @@ -155,7 +155,6 @@ static const struct drm_driver ili9341_driver = { .debugfs_init = mipi_dbi_debugfs_init, .name = "ili9341", .desc = "Ilitek ILI9341", - .date = "20180514", .major = 1, .minor = 0, }; diff --git a/drivers/gpu/drm/tiny/ili9486.c b/drivers/gpu/drm/tiny/ili9486.c index f5b1d21f7109..093661c771a0 100644 --- a/drivers/gpu/drm/tiny/ili9486.c +++ b/drivers/gpu/drm/tiny/ili9486.c @@ -177,7 +177,6 @@ static const struct drm_driver ili9486_driver = { .debugfs_init = mipi_dbi_debugfs_init, .name = "ili9486", .desc = "Ilitek ILI9486", - .date = "20200118", .major = 1, .minor = 0, }; diff --git a/drivers/gpu/drm/tiny/mi0283qt.c b/drivers/gpu/drm/tiny/mi0283qt.c index 61e33376fbc9..b6b4664908ae 100644 --- a/drivers/gpu/drm/tiny/mi0283qt.c +++ b/drivers/gpu/drm/tiny/mi0283qt.c @@ -159,7 +159,6 @@ static const struct drm_driver mi0283qt_driver = { .debugfs_init = mipi_dbi_debugfs_init, .name = "mi0283qt", .desc = "Multi-Inno MI0283QT", - .date = "20160614", .major = 1, .minor = 0, }; diff --git a/drivers/gpu/drm/tiny/ofdrm.c b/drivers/gpu/drm/tiny/ofdrm.c index b27ed3677bfd..cd5916752507 100644 --- a/drivers/gpu/drm/tiny/ofdrm.c +++ b/drivers/gpu/drm/tiny/ofdrm.c @@ -25,7 +25,6 @@ #define DRIVER_NAME "ofdrm" #define DRIVER_DESC "DRM driver for OF platform devices" -#define DRIVER_DATE "20220501" #define DRIVER_MAJOR 1 #define DRIVER_MINOR 0 @@ -1348,7 +1347,6 @@ static struct drm_driver ofdrm_driver = { DRM_FBDEV_SHMEM_DRIVER_OPS, .name = DRIVER_NAME, .desc = DRIVER_DESC, - .date = DRIVER_DATE, .major = DRIVER_MAJOR, .minor = DRIVER_MINOR, .driver_features = DRIVER_ATOMIC | DRIVER_GEM | DRIVER_MODESET, diff --git a/drivers/gpu/drm/tiny/panel-mipi-dbi.c b/drivers/gpu/drm/tiny/panel-mipi-dbi.c index 79d5818cbbe6..4786b8144a9f 100644 --- a/drivers/gpu/drm/tiny/panel-mipi-dbi.c +++ b/drivers/gpu/drm/tiny/panel-mipi-dbi.c @@ -269,7 +269,6 @@ static const struct drm_driver panel_mipi_dbi_driver = { .debugfs_init = mipi_dbi_debugfs_init, .name = "panel-mipi-dbi", .desc = "MIPI DBI compatible display panel", - .date = "20220103", .major = 1, .minor = 0, }; diff --git a/drivers/gpu/drm/tiny/repaper.c b/drivers/gpu/drm/tiny/repaper.c index 9373063a13fc..52ba6c699bc8 100644 --- a/drivers/gpu/drm/tiny/repaper.c +++ b/drivers/gpu/drm/tiny/repaper.c @@ -917,7 +917,6 @@ static const struct drm_driver repaper_driver = { DRM_FBDEV_DMA_DRIVER_OPS, .name = "repaper", .desc = "Pervasive Displays RePaper e-ink panels", - .date = "20170405", .major = 1, .minor = 0, }; diff --git a/drivers/gpu/drm/tiny/sharp-memory.c b/drivers/gpu/drm/tiny/sharp-memory.c index d87068126f9b..03d2850310c4 100644 --- a/drivers/gpu/drm/tiny/sharp-memory.c +++ b/drivers/gpu/drm/tiny/sharp-memory.c @@ -107,7 +107,6 @@ static const struct drm_driver sharp_memory_drm_driver = { DRM_FBDEV_DMA_DRIVER_OPS, .name = "sharp_memory_display", .desc = "Sharp Display Memory LCD", - .date = "20231129", .major = 1, .minor = 0, }; diff --git a/drivers/gpu/drm/tiny/simpledrm.c b/drivers/gpu/drm/tiny/simpledrm.c index b3a2fc11dcf0..b47ca2d902d9 100644 --- a/drivers/gpu/drm/tiny/simpledrm.c +++ b/drivers/gpu/drm/tiny/simpledrm.c @@ -31,7 +31,6 @@ #define DRIVER_NAME "simpledrm" #define DRIVER_DESC "DRM driver for simple-framebuffer platform devices" -#define DRIVER_DATE "20200625" #define DRIVER_MAJOR 1 #define DRIVER_MINOR 0 @@ -1015,7 +1014,6 @@ static struct drm_driver simpledrm_driver = { DRM_FBDEV_SHMEM_DRIVER_OPS, .name = DRIVER_NAME, .desc = DRIVER_DESC, - .date = DRIVER_DATE, .major = DRIVER_MAJOR, .minor = DRIVER_MINOR, .driver_features = DRIVER_ATOMIC | DRIVER_GEM | DRIVER_MODESET, diff --git a/drivers/gpu/drm/tiny/st7586.c b/drivers/gpu/drm/tiny/st7586.c index 7bfd4296c1c9..a29672d84ede 100644 --- a/drivers/gpu/drm/tiny/st7586.c +++ b/drivers/gpu/drm/tiny/st7586.c @@ -295,7 +295,6 @@ static const struct drm_driver st7586_driver = { .debugfs_init = mipi_dbi_debugfs_init, .name = "st7586", .desc = "Sitronix ST7586", - .date = "20170801", .major = 1, .minor = 0, }; diff --git a/drivers/gpu/drm/tiny/st7735r.c b/drivers/gpu/drm/tiny/st7735r.c index 6832ca590127..1d60f6e5b3bc 100644 --- a/drivers/gpu/drm/tiny/st7735r.c +++ b/drivers/gpu/drm/tiny/st7735r.c @@ -160,7 +160,6 @@ static const struct drm_driver st7735r_driver = { .debugfs_init = mipi_dbi_debugfs_init, .name = "st7735r", .desc = "Sitronix ST7735R", - .date = "20171128", .major = 1, .minor = 0, }; diff --git a/drivers/gpu/drm/tve200/tve200_drv.c b/drivers/gpu/drm/tve200/tve200_drv.c index cb66dbbe2801..65a0d4301160 100644 --- a/drivers/gpu/drm/tve200/tve200_drv.c +++ b/drivers/gpu/drm/tve200/tve200_drv.c @@ -146,7 +146,6 @@ static const struct drm_driver tve200_drm_driver = { .fops = &drm_fops, .name = "tve200", .desc = DRIVER_DESC, - .date = "20170703", .major = 1, .minor = 0, .patchlevel = 0, diff --git a/drivers/gpu/drm/udl/udl_drv.c b/drivers/gpu/drm/udl/udl_drv.c index 6c182b21028e..05b3a152cc33 100644 --- a/drivers/gpu/drm/udl/udl_drv.c +++ b/drivers/gpu/drm/udl/udl_drv.c @@ -78,7 +78,6 @@ static const struct drm_driver driver = { .name = DRIVER_NAME, .desc = DRIVER_DESC, - .date = DRIVER_DATE, .major = DRIVER_MAJOR, .minor = DRIVER_MINOR, .patchlevel = DRIVER_PATCHLEVEL, diff --git a/drivers/gpu/drm/udl/udl_drv.h b/drivers/gpu/drm/udl/udl_drv.h index 1eb716d9dad5..be00dc1d87a1 100644 --- a/drivers/gpu/drm/udl/udl_drv.h +++ b/drivers/gpu/drm/udl/udl_drv.h @@ -26,7 +26,6 @@ struct drm_mode_create_dumb; #define DRIVER_NAME "udl" #define DRIVER_DESC "DisplayLink" -#define DRIVER_DATE "20120220" #define DRIVER_MAJOR 0 #define DRIVER_MINOR 0 diff --git a/drivers/gpu/drm/v3d/v3d_drv.c b/drivers/gpu/drm/v3d/v3d_drv.c index 8e5cacfa38d3..d91c9a38219f 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.c +++ b/drivers/gpu/drm/v3d/v3d_drv.c @@ -31,7 +31,6 @@ #define DRIVER_NAME "v3d" #define DRIVER_DESC "Broadcom V3D graphics" -#define DRIVER_DATE "20180419" #define DRIVER_MAJOR 1 #define DRIVER_MINOR 0 #define DRIVER_PATCHLEVEL 0 @@ -249,7 +248,6 @@ static const struct drm_driver v3d_drm_driver = { .name = DRIVER_NAME, .desc = DRIVER_DESC, - .date = DRIVER_DATE, .major = DRIVER_MAJOR, .minor = DRIVER_MINOR, .patchlevel = DRIVER_PATCHLEVEL, diff --git a/drivers/gpu/drm/vboxvideo/vbox_drv.c b/drivers/gpu/drm/vboxvideo/vbox_drv.c index d9d884aad97f..bb861f0a0a31 100644 --- a/drivers/gpu/drm/vboxvideo/vbox_drv.c +++ b/drivers/gpu/drm/vboxvideo/vbox_drv.c @@ -189,7 +189,6 @@ static const struct drm_driver driver = { .fops = &vbox_fops, .name = DRIVER_NAME, .desc = DRIVER_DESC, - .date = DRIVER_DATE, .major = DRIVER_MAJOR, .minor = DRIVER_MINOR, .patchlevel = DRIVER_PATCHLEVEL, diff --git a/drivers/gpu/drm/vboxvideo/vbox_drv.h b/drivers/gpu/drm/vboxvideo/vbox_drv.h index e77bd6512eb1..dfa935f381a6 100644 --- a/drivers/gpu/drm/vboxvideo/vbox_drv.h +++ b/drivers/gpu/drm/vboxvideo/vbox_drv.h @@ -25,7 +25,6 @@ #define DRIVER_NAME "vboxvideo" #define DRIVER_DESC "Oracle VM VirtualBox Graphics Card" -#define DRIVER_DATE "20130823" #define DRIVER_MAJOR 1 #define DRIVER_MINOR 0 diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c index ee5df153c2a6..e88a7ee486c6 100644 --- a/drivers/gpu/drm/vc4/vc4_drv.c +++ b/drivers/gpu/drm/vc4/vc4_drv.c @@ -47,7 +47,6 @@ #define DRIVER_NAME "vc4" #define DRIVER_DESC "Broadcom VC4 graphics" -#define DRIVER_DATE "20140616" #define DRIVER_MAJOR 0 #define DRIVER_MINOR 0 #define DRIVER_PATCHLEVEL 0 @@ -222,7 +221,6 @@ const struct drm_driver vc4_drm_driver = { .name = DRIVER_NAME, .desc = DRIVER_DESC, - .date = DRIVER_DATE, .major = DRIVER_MAJOR, .minor = DRIVER_MINOR, .patchlevel = DRIVER_PATCHLEVEL, @@ -244,7 +242,6 @@ const struct drm_driver vc5_drm_driver = { .name = DRIVER_NAME, .desc = DRIVER_DESC, - .date = DRIVER_DATE, .major = DRIVER_MAJOR, .minor = DRIVER_MINOR, .patchlevel = DRIVER_PATCHLEVEL, diff --git a/drivers/gpu/drm/vgem/vgem_drv.c b/drivers/gpu/drm/vgem/vgem_drv.c index c5e3e5457737..2752ab4f1c97 100644 --- a/drivers/gpu/drm/vgem/vgem_drv.c +++ b/drivers/gpu/drm/vgem/vgem_drv.c @@ -47,7 +47,6 @@ #define DRIVER_NAME "vgem" #define DRIVER_DESC "Virtual GEM provider" -#define DRIVER_DATE "20120112" #define DRIVER_MAJOR 1 #define DRIVER_MINOR 0 @@ -121,7 +120,6 @@ static const struct drm_driver vgem_driver = { .name = DRIVER_NAME, .desc = DRIVER_DESC, - .date = DRIVER_DATE, .major = DRIVER_MAJOR, .minor = DRIVER_MINOR, }; diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.c b/drivers/gpu/drm/virtio/virtgpu_drv.c index e216123ce6a5..6a67c6297d58 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.c +++ b/drivers/gpu/drm/virtio/virtgpu_drv.c @@ -201,7 +201,6 @@ static const struct drm_driver driver = { .name = DRIVER_NAME, .desc = DRIVER_DESC, - .date = DRIVER_DATE, .major = DRIVER_MAJOR, .minor = DRIVER_MINOR, .patchlevel = DRIVER_PATCHLEVEL, diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h index 8328107edf78..f42ca9d8ed10 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.h +++ b/drivers/gpu/drm/virtio/virtgpu_drv.h @@ -45,7 +45,6 @@ #define DRIVER_NAME "virtio_gpu" #define DRIVER_DESC "virtio GPU" -#define DRIVER_DATE "0" #define DRIVER_MAJOR 0 #define DRIVER_MINOR 1 diff --git a/drivers/gpu/drm/vkms/vkms_drv.c b/drivers/gpu/drm/vkms/vkms_drv.c index fa3331f612e3..e0409aba9349 100644 --- a/drivers/gpu/drm/vkms/vkms_drv.c +++ b/drivers/gpu/drm/vkms/vkms_drv.c @@ -34,7 +34,6 @@ #define DRIVER_NAME "vkms" #define DRIVER_DESC "Virtual Kernel Mode Setting" -#define DRIVER_DATE "20180514" #define DRIVER_MAJOR 1 #define DRIVER_MINOR 0 @@ -116,7 +115,6 @@ static const struct drm_driver vkms_driver = { .name = DRIVER_NAME, .desc = DRIVER_DESC, - .date = DRIVER_DATE, .major = DRIVER_MAJOR, .minor = DRIVER_MINOR, }; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index ded48554568a..1699236fca5a 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -1634,7 +1634,6 @@ static const struct drm_driver driver = { .fops = &vmwgfx_driver_fops, .name = VMWGFX_DRIVER_NAME, .desc = VMWGFX_DRIVER_DESC, - .date = VMWGFX_DRIVER_DATE, .major = VMWGFX_DRIVER_MAJOR, .minor = VMWGFX_DRIVER_MINOR, .patchlevel = VMWGFX_DRIVER_PATCHLEVEL diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index b21831ef214a..5275ef632d4b 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -57,7 +57,6 @@ #define VMWGFX_DRIVER_NAME "vmwgfx" -#define VMWGFX_DRIVER_DATE "20211206" #define VMWGFX_DRIVER_MAJOR 2 #define VMWGFX_DRIVER_MINOR 20 #define VMWGFX_DRIVER_PATCHLEVEL 0 diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c index 06d6db8b50f9..d8b6bc8fc8cf 100644 --- a/drivers/gpu/drm/xe/xe_device.c +++ b/drivers/gpu/drm/xe/xe_device.c @@ -269,7 +269,6 @@ static struct drm_driver driver = { .fops = &xe_driver_fops, .name = DRIVER_NAME, .desc = DRIVER_DESC, - .date = DRIVER_DATE, .major = DRIVER_MAJOR, .minor = DRIVER_MINOR, .patchlevel = DRIVER_PATCHLEVEL, diff --git a/drivers/gpu/drm/xe/xe_drv.h b/drivers/gpu/drm/xe/xe_drv.h index d45b71426cc8..d61650d4aa0b 100644 --- a/drivers/gpu/drm/xe/xe_drv.h +++ b/drivers/gpu/drm/xe/xe_drv.h @@ -10,7 +10,6 @@ #define DRIVER_NAME "xe" #define DRIVER_DESC "Intel Xe Graphics" -#define DRIVER_DATE "20201103" /* Interface history: * diff --git a/drivers/gpu/drm/xen/xen_drm_front.c b/drivers/gpu/drm/xen/xen_drm_front.c index 931d855bfbe8..1bda7ef606cc 100644 --- a/drivers/gpu/drm/xen/xen_drm_front.c +++ b/drivers/gpu/drm/xen/xen_drm_front.c @@ -478,7 +478,6 @@ static const struct drm_driver xen_drm_driver = { .fops = &xen_drm_dev_fops, .name = "xendrm-du", .desc = "Xen PV DRM Display Unit", - .date = "20180221", .major = 1, .minor = 0, diff --git a/drivers/gpu/drm/xlnx/zynqmp_kms.c b/drivers/gpu/drm/xlnx/zynqmp_kms.c index e272ecbce78d..b47463473472 100644 --- a/drivers/gpu/drm/xlnx/zynqmp_kms.c +++ b/drivers/gpu/drm/xlnx/zynqmp_kms.c @@ -409,7 +409,6 @@ static const struct drm_driver zynqmp_dpsub_drm_driver = { .name = "zynqmp-dpsub", .desc = "Xilinx DisplayPort Subsystem Driver", - .date = "20130509", .major = 1, .minor = 0, }; diff --git a/include/drm/drm_drv.h b/include/drm/drm_drv.h index 1bbbcb8e2d23..1b6e59139e6c 100644 --- a/include/drm/drm_drv.h +++ b/include/drm/drm_drv.h @@ -401,8 +401,6 @@ struct drm_driver { char *name; /** @desc: driver description */ char *desc; - /** @date: driver date, unused, to be removed */ - char *date; /** * @driver_features: -- cgit v1.2.3