diff options
Diffstat (limited to 'include')
55 files changed, 1002 insertions, 648 deletions
diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h index e93375c710b9..cc7338f9e0d1 100644 --- a/include/asm-generic/io.h +++ b/include/asm-generic/io.h @@ -1023,16 +1023,7 @@ static inline void __iomem *ioport_map(unsigned long port, unsigned int nr) port &= IO_SPACE_LIMIT; return (port > MMIO_UPPER_LIMIT) ? NULL : PCI_IOBASE + port; } -#define __pci_ioport_unmap __pci_ioport_unmap -static inline void __pci_ioport_unmap(void __iomem *p) -{ - uintptr_t start = (uintptr_t) PCI_IOBASE; - uintptr_t addr = (uintptr_t) p; - - if (addr >= start && addr < start + IO_SPACE_LIMIT) - return; - iounmap(p); -} +#define ARCH_HAS_GENERIC_IOPORT_MAP #endif #ifndef ioport_unmap @@ -1048,21 +1039,10 @@ extern void ioport_unmap(void __iomem *p); #endif /* CONFIG_HAS_IOPORT_MAP */ #ifndef CONFIG_GENERIC_IOMAP -struct pci_dev; -extern void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max); - -#ifndef __pci_ioport_unmap -static inline void __pci_ioport_unmap(void __iomem *p) {} -#endif - #ifndef pci_iounmap -#define pci_iounmap pci_iounmap -static inline void pci_iounmap(struct pci_dev *dev, void __iomem *p) -{ - __pci_ioport_unmap(p); -} +#define ARCH_WANTS_GENERIC_PCI_IOUNMAP +#endif #endif -#endif /* CONFIG_GENERIC_IOMAP */ #ifndef xlate_dev_mem_ptr #define xlate_dev_mem_ptr xlate_dev_mem_ptr diff --git a/include/asm-generic/iomap.h b/include/asm-generic/iomap.h index 9b3eb6d86200..08237ae8b840 100644 --- a/include/asm-generic/iomap.h +++ b/include/asm-generic/iomap.h @@ -110,16 +110,6 @@ static inline void __iomem *ioremap_np(phys_addr_t offset, size_t size) } #endif -#ifdef CONFIG_PCI -/* Destroy a virtual mapping cookie for a PCI BAR (memory or IO) */ -struct pci_dev; -extern void pci_iounmap(struct pci_dev *dev, void __iomem *); -#elif defined(CONFIG_GENERIC_IOMAP) -struct pci_dev; -static inline void pci_iounmap(struct pci_dev *dev, void __iomem *addr) -{ } -#endif - #include <asm-generic/pci_iomap.h> #endif diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h index c1ab6a6e72b5..d3eae6cdbacb 100644 --- a/include/asm-generic/mshyperv.h +++ b/include/asm-generic/mshyperv.h @@ -197,10 +197,12 @@ static inline int hv_cpu_number_to_vp_number(int cpu_number) return hv_vp_index[cpu_number]; } -static inline int cpumask_to_vpset(struct hv_vpset *vpset, - const struct cpumask *cpus) +static inline int __cpumask_to_vpset(struct hv_vpset *vpset, + const struct cpumask *cpus, + bool exclude_self) { int cpu, vcpu, vcpu_bank, vcpu_offset, nr_bank = 1; + int this_cpu = smp_processor_id(); /* valid_bank_mask can represent up to 64 banks */ if (hv_max_vp_index / 64 >= 64) @@ -218,6 +220,8 @@ static inline int cpumask_to_vpset(struct hv_vpset *vpset, * Some banks may end up being empty but this is acceptable. */ for_each_cpu(cpu, cpus) { + if (exclude_self && cpu == this_cpu) + continue; vcpu = hv_cpu_number_to_vp_number(cpu); if (vcpu == VP_INVAL) return -1; @@ -232,6 +236,19 @@ static inline int cpumask_to_vpset(struct hv_vpset *vpset, return nr_bank; } +static inline int cpumask_to_vpset(struct hv_vpset *vpset, + const struct cpumask *cpus) +{ + return __cpumask_to_vpset(vpset, cpus, false); +} + +static inline int cpumask_to_vpset_noself(struct hv_vpset *vpset, + const struct cpumask *cpus) +{ + WARN_ON_ONCE(preemptible()); + return __cpumask_to_vpset(vpset, cpus, true); +} + void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die); bool hv_is_hyperv_initialized(void); bool hv_is_hibernation_supported(void); diff --git a/include/asm-generic/pci_iomap.h b/include/asm-generic/pci_iomap.h index df636c6d8e6c..5a2f9bf53384 100644 --- a/include/asm-generic/pci_iomap.h +++ b/include/asm-generic/pci_iomap.h @@ -18,6 +18,7 @@ extern void __iomem *pci_iomap_range(struct pci_dev *dev, int bar, extern void __iomem *pci_iomap_wc_range(struct pci_dev *dev, int bar, unsigned long offset, unsigned long maxlen); +extern void pci_iounmap(struct pci_dev *dev, void __iomem *); /* Create a virtual mapping cookie for a port on a given PCI device. * Do not call this directly, it exists to make it easier for architectures * to override */ @@ -50,6 +51,8 @@ static inline void __iomem *pci_iomap_wc_range(struct pci_dev *dev, int bar, { return NULL; } +static inline void pci_iounmap(struct pci_dev *dev, void __iomem *addr) +{ } #endif #endif /* __ASM_GENERIC_PCI_IOMAP_H */ diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index aa50bf2959fe..f2984af2b85b 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -116,11 +116,7 @@ * GCC 4.5 and later have a 32 bytes section alignment for structures. * Except GCC 4.9, that feels the need to align on 64 bytes. */ -#if __GNUC__ == 4 && __GNUC_MINOR__ == 9 -#define STRUCT_ALIGNMENT 64 -#else #define STRUCT_ALIGNMENT 32 -#endif #define STRUCT_ALIGN() . = ALIGN(STRUCT_ALIGNMENT) /* diff --git a/include/drm/amd_asic_type.h b/include/drm/amd_asic_type.h index 0f66a0d9f06d..90b69270f2fa 100644 --- a/include/drm/amd_asic_type.h +++ b/include/drm/amd_asic_type.h @@ -62,6 +62,7 @@ enum amd_asic_type { CHIP_DIMGREY_CAVEFISH, /* 33 */ CHIP_BEIGE_GOBY, /* 34 */ CHIP_YELLOW_CARP, /* 35 */ + CHIP_IP_DISCOVERY, /* 36 */ CHIP_LAST, }; diff --git a/include/drm/drm_bridge.h b/include/drm/drm_bridge.h index 46bdfa48c413..061d87313fac 100644 --- a/include/drm/drm_bridge.h +++ b/include/drm/drm_bridge.h @@ -790,11 +790,19 @@ drm_priv_to_bridge(struct drm_private_obj *priv) void drm_bridge_add(struct drm_bridge *bridge); void drm_bridge_remove(struct drm_bridge *bridge); -struct drm_bridge *of_drm_find_bridge(struct device_node *np); int drm_bridge_attach(struct drm_encoder *encoder, struct drm_bridge *bridge, struct drm_bridge *previous, enum drm_bridge_attach_flags flags); +#ifdef CONFIG_OF +struct drm_bridge *of_drm_find_bridge(struct device_node *np); +#else +static inline struct drm_bridge *of_drm_find_bridge(struct device_node *np) +{ + return NULL; +} +#endif + /** * drm_bridge_get_next_bridge() - Get the next bridge in the chain * @bridge: bridge object @@ -914,4 +922,17 @@ struct drm_bridge *devm_drm_panel_bridge_add_typed(struct device *dev, struct drm_connector *drm_panel_bridge_connector(struct drm_bridge *bridge); #endif +#if defined(CONFIG_OF) && defined(CONFIG_DRM_PANEL_BRIDGE) +struct drm_bridge *devm_drm_of_get_bridge(struct device *dev, struct device_node *node, + u32 port, u32 endpoint); +#else +static inline struct drm_bridge *devm_drm_of_get_bridge(struct device *dev, + struct device_node *node, + u32 port, + u32 endpoint) +{ + return ERR_PTR(-ENODEV); +} +#endif + #endif diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h index 1647960c9e50..379746d3266f 100644 --- a/include/drm/drm_connector.h +++ b/include/drm/drm_connector.h @@ -590,6 +590,18 @@ struct drm_display_info { * @monitor_range: Frequency range supported by monitor range descriptor */ struct drm_monitor_range_info monitor_range; + + /** + * @mso_stream_count: eDP Multi-SST Operation (MSO) stream count from + * the DisplayID VESA vendor block. 0 for conventional Single-Stream + * Transport (SST), or 2 or 4 MSO streams. + */ + u8 mso_stream_count; + + /** + * @mso_pixel_overlap: eDP MSO segment pixel overlap, 0-8 pixels. + */ + u8 mso_pixel_overlap; }; int drm_display_info_set_bus_formats(struct drm_display_info *info, @@ -1084,6 +1096,14 @@ struct drm_connector_funcs { */ void (*atomic_print_state)(struct drm_printer *p, const struct drm_connector_state *state); + + /** + * @oob_hotplug_event: + * + * This will get called when a hotplug-event for a drm-connector + * has been received from a source outside the display driver / device. + */ + void (*oob_hotplug_event)(struct drm_connector *connector); }; /** @@ -1228,6 +1248,14 @@ struct drm_connector { struct device *kdev; /** @attr: sysfs attributes */ struct device_attribute *attr; + /** + * @fwnode: associated fwnode supplied by platform firmware + * + * Drivers can set this to associate a fwnode with a connector, drivers + * are expected to get a reference on the fwnode when setting this. + * drm_connector_cleanup() will call fwnode_handle_put() on this. + */ + struct fwnode_handle *fwnode; /** * @head: @@ -1239,6 +1267,14 @@ struct drm_connector { */ struct list_head head; + /** + * @global_connector_list_entry: + * + * Connector entry in the global connector-list, used by + * drm_connector_find_by_fwnode(). + */ + struct list_head global_connector_list_entry; + /** @base: base KMS object */ struct drm_mode_object base; @@ -1650,6 +1686,7 @@ drm_connector_is_unregistered(struct drm_connector *connector) DRM_CONNECTOR_UNREGISTERED; } +void drm_connector_oob_hotplug_event(struct fwnode_handle *connector_fwnode); const char *drm_get_connector_type_name(unsigned int connector_type); const char *drm_get_connector_status_name(enum drm_connector_status status); const char *drm_get_subpixel_order_name(enum subpixel_order order); diff --git a/include/drm/drm_displayid.h b/include/drm/drm_displayid.h index ec64d141f578..7ffbd9f7bfc7 100644 --- a/include/drm/drm_displayid.h +++ b/include/drm/drm_displayid.h @@ -23,38 +23,71 @@ #define DRM_DISPLAYID_H #include <linux/types.h> +#include <linux/bits.h> struct edid; -#define DATA_BLOCK_PRODUCT_ID 0x00 -#define DATA_BLOCK_DISPLAY_PARAMETERS 0x01 -#define DATA_BLOCK_COLOR_CHARACTERISTICS 0x02 -#define DATA_BLOCK_TYPE_1_DETAILED_TIMING 0x03 -#define DATA_BLOCK_TYPE_2_DETAILED_TIMING 0x04 -#define DATA_BLOCK_TYPE_3_SHORT_TIMING 0x05 -#define DATA_BLOCK_TYPE_4_DMT_TIMING 0x06 -#define DATA_BLOCK_VESA_TIMING 0x07 -#define DATA_BLOCK_CEA_TIMING 0x08 -#define DATA_BLOCK_VIDEO_TIMING_RANGE 0x09 -#define DATA_BLOCK_PRODUCT_SERIAL_NUMBER 0x0a -#define DATA_BLOCK_GP_ASCII_STRING 0x0b -#define DATA_BLOCK_DISPLAY_DEVICE_DATA 0x0c -#define DATA_BLOCK_INTERFACE_POWER_SEQUENCING 0x0d -#define DATA_BLOCK_TRANSFER_CHARACTERISTICS 0x0e -#define DATA_BLOCK_DISPLAY_INTERFACE 0x0f -#define DATA_BLOCK_STEREO_DISPLAY_INTERFACE 0x10 -#define DATA_BLOCK_TILED_DISPLAY 0x12 -#define DATA_BLOCK_CTA 0x81 - -#define DATA_BLOCK_VENDOR_SPECIFIC 0x7f - -#define PRODUCT_TYPE_EXTENSION 0 -#define PRODUCT_TYPE_TEST 1 -#define PRODUCT_TYPE_PANEL 2 -#define PRODUCT_TYPE_MONITOR 3 -#define PRODUCT_TYPE_TV 4 -#define PRODUCT_TYPE_REPEATER 5 -#define PRODUCT_TYPE_DIRECT_DRIVE 6 +#define VESA_IEEE_OUI 0x3a0292 + +/* DisplayID Structure versions */ +#define DISPLAY_ID_STRUCTURE_VER_12 0x12 +#define DISPLAY_ID_STRUCTURE_VER_20 0x20 + +/* DisplayID Structure v1r2 Data Blocks */ +#define DATA_BLOCK_PRODUCT_ID 0x00 +#define DATA_BLOCK_DISPLAY_PARAMETERS 0x01 +#define DATA_BLOCK_COLOR_CHARACTERISTICS 0x02 +#define DATA_BLOCK_TYPE_1_DETAILED_TIMING 0x03 +#define DATA_BLOCK_TYPE_2_DETAILED_TIMING 0x04 +#define DATA_BLOCK_TYPE_3_SHORT_TIMING 0x05 +#define DATA_BLOCK_TYPE_4_DMT_TIMING 0x06 +#define DATA_BLOCK_VESA_TIMING 0x07 +#define DATA_BLOCK_CEA_TIMING 0x08 +#define DATA_BLOCK_VIDEO_TIMING_RANGE 0x09 +#define DATA_BLOCK_PRODUCT_SERIAL_NUMBER 0x0a +#define DATA_BLOCK_GP_ASCII_STRING 0x0b +#define DATA_BLOCK_DISPLAY_DEVICE_DATA 0x0c +#define DATA_BLOCK_INTERFACE_POWER_SEQUENCING 0x0d +#define DATA_BLOCK_TRANSFER_CHARACTERISTICS 0x0e +#define DATA_BLOCK_DISPLAY_INTERFACE 0x0f +#define DATA_BLOCK_STEREO_DISPLAY_INTERFACE 0x10 +#define DATA_BLOCK_TILED_DISPLAY 0x12 +#define DATA_BLOCK_VENDOR_SPECIFIC 0x7f +#define DATA_BLOCK_CTA 0x81 + +/* DisplayID Structure v2r0 Data Blocks */ +#define DATA_BLOCK_2_PRODUCT_ID 0x20 +#define DATA_BLOCK_2_DISPLAY_PARAMETERS 0x21 +#define DATA_BLOCK_2_TYPE_7_DETAILED_TIMING 0x22 +#define DATA_BLOCK_2_TYPE_8_ENUMERATED_TIMING 0x23 +#define DATA_BLOCK_2_TYPE_9_FORMULA_TIMING 0x24 +#define DATA_BLOCK_2_DYNAMIC_VIDEO_TIMING 0x25 +#define DATA_BLOCK_2_DISPLAY_INTERFACE_FEATURES 0x26 +#define DATA_BLOCK_2_STEREO_DISPLAY_INTERFACE 0x27 +#define DATA_BLOCK_2_TILED_DISPLAY_TOPOLOGY 0x28 +#define DATA_BLOCK_2_CONTAINER_ID 0x29 +#define DATA_BLOCK_2_VENDOR_SPECIFIC 0x7e +#define DATA_BLOCK_2_CTA_DISPLAY_ID 0x81 + +/* DisplayID Structure v1r2 Product Type */ +#define PRODUCT_TYPE_EXTENSION 0 +#define PRODUCT_TYPE_TEST 1 +#define PRODUCT_TYPE_PANEL 2 +#define PRODUCT_TYPE_MONITOR 3 +#define PRODUCT_TYPE_TV 4 +#define PRODUCT_TYPE_REPEATER 5 +#define PRODUCT_TYPE_DIRECT_DRIVE 6 + +/* DisplayID Structure v2r0 Display Product Primary Use Case (~Product Type) */ +#define PRIMARY_USE_EXTENSION 0 +#define PRIMARY_USE_TEST 1 +#define PRIMARY_USE_GENERIC 2 +#define PRIMARY_USE_TV 3 +#define PRIMARY_USE_DESKTOP_PRODUCTIVITY 4 +#define PRIMARY_USE_DESKTOP_GAMING 5 +#define PRIMARY_USE_PRESENTATION 6 +#define PRIMARY_USE_HEAD_MOUNTED_VR 7 +#define PRIMARY_USE_HEAD_MOUNTED_AR 8 struct displayid_header { u8 rev; @@ -96,6 +129,16 @@ struct displayid_detailed_timing_block { struct displayid_detailed_timings_1 timings[]; }; +#define DISPLAYID_VESA_MSO_OVERLAP GENMASK(3, 0) +#define DISPLAYID_VESA_MSO_MODE GENMASK(6, 5) + +struct displayid_vesa_vendor_specific_block { + struct displayid_block base; + u8 oui[3]; + u8 data_structure_type; + u8 mso; +} __packed; + /* DisplayID iteration */ struct displayid_iter { const struct edid *edid; diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h index 1d5b3dbb6e56..b52df4db3e8f 100644 --- a/include/drm/drm_dp_helper.h +++ b/include/drm/drm_dp_helper.h @@ -453,6 +453,7 @@ struct drm_panel; # define DP_FEC_UNCORR_BLK_ERROR_COUNT_CAP (1 << 1) # define DP_FEC_CORR_BLK_ERROR_COUNT_CAP (1 << 2) # define DP_FEC_BIT_ERROR_COUNT_CAP (1 << 3) +#define DP_FEC_CAPABILITY_1 0x091 /* 2.0 */ /* DP-HDMI2.1 PCON DSC ENCODER SUPPORT */ #define DP_PCON_DSC_ENCODER_CAP_SIZE 0xC /* 0x9E - 0x92 */ @@ -537,6 +538,9 @@ struct drm_panel; #define DP_DSC_BRANCH_OVERALL_THROUGHPUT_1 0x0a1 #define DP_DSC_BRANCH_MAX_LINE_WIDTH 0x0a2 +/* DFP Capability Extension */ +#define DP_DFP_CAPABILITY_EXTENSION_SUPPORT 0x0a3 /* 2.0 */ + /* Link Configuration */ #define DP_LINK_BW_SET 0x100 # define DP_LINK_RATE_TABLE 0x00 /* eDP 1.4 */ @@ -688,6 +692,7 @@ struct drm_panel; #define DP_DSC_ENABLE 0x160 /* DP 1.4 */ # define DP_DECOMPRESSION_EN (1 << 0) +#define DP_DSC_CONFIGURATION 0x161 /* DP 2.0 */ #define DP_PSR_EN_CFG 0x170 /* XXX 1.2? */ # define DP_PSR_ENABLE BIT(0) @@ -743,6 +748,7 @@ struct drm_panel; # define DP_RECEIVE_PORT_0_STATUS (1 << 0) # define DP_RECEIVE_PORT_1_STATUS (1 << 1) # define DP_STREAM_REGENERATION_STATUS (1 << 2) /* 2.0 */ +# define DP_INTRA_HOP_AUX_REPLY_INDICATION (1 << 3) /* 2.0 */ #define DP_ADJUST_REQUEST_LANE0_1 0x206 #define DP_ADJUST_REQUEST_LANE2_3 0x207 @@ -865,6 +871,8 @@ struct drm_panel; # define DP_PHY_TEST_PATTERN_80BIT_CUSTOM 0x4 # define DP_PHY_TEST_PATTERN_CP2520 0x5 +#define DP_PHY_SQUARE_PATTERN 0x249 + #define DP_TEST_HBR2_SCRAMBLER_RESET 0x24A #define DP_TEST_80BIT_CUSTOM_PATTERN_7_0 0x250 #define DP_TEST_80BIT_CUSTOM_PATTERN_15_8 0x251 @@ -1109,6 +1117,18 @@ struct drm_panel; #define DP_128B132B_TRAINING_AUX_RD_INTERVAL 0x2216 /* 2.0 */ # define DP_128B132B_TRAINING_AUX_RD_INTERVAL_MASK 0x7f +#define DP_TEST_264BIT_CUSTOM_PATTERN_7_0 0x2230 +#define DP_TEST_264BIT_CUSTOM_PATTERN_263_256 0x2250 + +/* DSC Extended Capability Branch Total DSC Resources */ +#define DP_DSC_SUPPORT_AND_DSC_DECODER_COUNT 0x2260 /* 2.0 */ +# define DP_DSC_DECODER_COUNT_MASK (0b111 << 5) +# define DP_DSC_DECODER_COUNT_SHIFT 5 +#define DP_DSC_MAX_SLICE_COUNT_AND_AGGREGATION_0 0x2270 /* 2.0 */ +# define DP_DSC_DECODER_0_MAXIMUM_SLICE_COUNT_MASK (1 << 0) +# define DP_DSC_DECODER_0_AGGREGATION_SUPPORT_MASK (0b111 << 1) +# define DP_DSC_DECODER_0_AGGREGATION_SUPPORT_SHIFT 1 + /* Protocol Converter Extension */ /* HDMI CEC tunneling over AUX DP 1.3 section 5.3.3.3.1 DPCD 1.4+ */ #define DP_CEC_TUNNELING_CAPABILITY 0x3000 @@ -1319,6 +1339,10 @@ struct drm_panel; #define DP_MAX_LANE_COUNT_PHY_REPEATER 0xf0004 /* 1.4a */ #define DP_Repeater_FEC_CAPABILITY 0xf0004 /* 1.4 */ #define DP_PHY_REPEATER_EXTENDED_WAIT_TIMEOUT 0xf0005 /* 1.4a */ +#define DP_MAIN_LINK_CHANNEL_CODING_PHY_REPEATER 0xf0006 /* 2.0 */ +# define DP_PHY_REPEATER_128B132B_SUPPORTED (1 << 0) +/* See DP_128B132B_SUPPORTED_LINK_RATES for values */ +#define DP_PHY_REPEATER_128B132B_RATES 0xf0007 /* 2.0 */ enum drm_dp_phy { DP_PHY_DPRX, @@ -1490,6 +1514,8 @@ u8 drm_dp_get_adjust_request_voltage(const u8 link_status[DP_LINK_STATUS_SIZE], int lane); u8 drm_dp_get_adjust_request_pre_emphasis(const u8 link_status[DP_LINK_STATUS_SIZE], int lane); +u8 drm_dp_get_adjust_tx_ffe_preset(const u8 link_status[DP_LINK_STATUS_SIZE], + int lane); u8 drm_dp_get_adjust_request_post_cursor(const u8 link_status[DP_LINK_STATUS_SIZE], unsigned int lane); diff --git a/include/drm/drm_edid.h b/include/drm/drm_edid.h index deccfd39e6db..18f6c700f6d0 100644 --- a/include/drm/drm_edid.h +++ b/include/drm/drm_edid.h @@ -508,6 +508,52 @@ static inline u8 drm_eld_get_conn_type(const uint8_t *eld) return eld[DRM_ELD_SAD_COUNT_CONN_TYPE] & DRM_ELD_CONN_TYPE_MASK; } +/** + * drm_edid_encode_panel_id - Encode an ID for matching against drm_edid_get_panel_id() + * @vend_chr_0: First character of the vendor string. + * @vend_chr_1: Second character of the vendor string. + * @vend_chr_2: Third character of the vendor string. + * @product_id: The 16-bit product ID. + * + * This is a macro so that it can be calculated at compile time and used + * as an initializer. + * + * For instance: + * drm_edid_encode_panel_id('B', 'O', 'E', 0x2d08) => 0x09e52d08 + * + * Return: a 32-bit ID per panel. + */ +#define drm_edid_encode_panel_id(vend_chr_0, vend_chr_1, vend_chr_2, product_id) \ + ((((u32)(vend_chr_0) - '@') & 0x1f) << 26 | \ + (((u32)(vend_chr_1) - '@') & 0x1f) << 21 | \ + (((u32)(vend_chr_2) - '@') & 0x1f) << 16 | \ + ((product_id) & 0xffff)) + +/** + * drm_edid_decode_panel_id - Decode a panel ID from drm_edid_encode_panel_id() + * @panel_id: The panel ID to decode. + * @vend: A 4-byte buffer to store the 3-letter vendor string plus a '\0' + * termination + * @product_id: The product ID will be returned here. + * + * For instance, after: + * drm_edid_decode_panel_id(0x09e52d08, vend, &product_id) + * These will be true: + * vend[0] = 'B' + * vend[1] = 'O' + * vend[2] = 'E' + * vend[3] = '\0' + * product_id = 0x2d08 + */ +static inline void drm_edid_decode_panel_id(u32 panel_id, char vend[4], u16 *product_id) +{ + *product_id = (u16)(panel_id & 0xffff); + vend[0] = '@' + ((panel_id >> 26) & 0x1f); + vend[1] = '@' + ((panel_id >> 21) & 0x1f); + vend[2] = '@' + ((panel_id >> 16) & 0x1f); + vend[3] = '\0'; +} + bool drm_probe_ddc(struct i2c_adapter *adapter); struct edid *drm_do_get_edid(struct drm_connector *connector, int (*get_edid_block)(void *data, u8 *buf, unsigned int block, @@ -515,6 +561,7 @@ struct edid *drm_do_get_edid(struct drm_connector *connector, void *data); struct edid *drm_get_edid(struct drm_connector *connector, struct i2c_adapter *adapter); +u32 drm_edid_get_panel_id(struct i2c_adapter *adapter); struct edid *drm_get_edid_switcheroo(struct drm_connector *connector, struct i2c_adapter *adapter); struct edid *drm_edid_duplicate(const struct edid *edid); diff --git a/include/drm/drm_format_helper.h b/include/drm/drm_format_helper.h index 4e0258a61311..e86925cf07b9 100644 --- a/include/drm/drm_format_helper.h +++ b/include/drm/drm_format_helper.h @@ -16,12 +16,16 @@ void drm_fb_memcpy_dstclip(void __iomem *dst, unsigned int dst_pitch, void *vadd struct drm_rect *clip); void drm_fb_swab(void *dst, void *src, struct drm_framebuffer *fb, struct drm_rect *clip, bool cached); +void drm_fb_xrgb8888_to_rgb332(void *dst, void *vaddr, struct drm_framebuffer *fb, + struct drm_rect *clip); void drm_fb_xrgb8888_to_rgb565(void *dst, void *vaddr, struct drm_framebuffer *fb, struct drm_rect *clip, bool swab); void drm_fb_xrgb8888_to_rgb565_dstclip(void __iomem *dst, unsigned int dst_pitch, void *vaddr, struct drm_framebuffer *fb, struct drm_rect *clip, bool swab); +void drm_fb_xrgb8888_to_rgb888(void *dst, void *src, struct drm_framebuffer *fb, + struct drm_rect *clip); void drm_fb_xrgb8888_to_rgb888_dstclip(void __iomem *dst, unsigned int dst_pitch, void *vaddr, struct drm_framebuffer *fb, struct drm_rect *clip); diff --git a/include/drm/drm_ioctl.h b/include/drm/drm_ioctl.h index afb27cb6a7bd..6ed61c371f6c 100644 --- a/include/drm/drm_ioctl.h +++ b/include/drm/drm_ioctl.h @@ -167,7 +167,6 @@ struct drm_ioctl_desc { .name = #ioctl \ } -int drm_ioctl_permit(u32 flags, struct drm_file *file_priv); long drm_ioctl(struct file *filp, unsigned int cmd, unsigned long arg); long drm_ioctl_kernel(struct file *, drm_ioctl_t, void *, u32); #ifdef CONFIG_COMPAT diff --git a/include/drm/drm_mipi_dsi.h b/include/drm/drm_mipi_dsi.h index af7ba8071eb0..147e51b6d241 100644 --- a/include/drm/drm_mipi_dsi.h +++ b/include/drm/drm_mipi_dsi.h @@ -227,9 +227,13 @@ struct mipi_dsi_device * mipi_dsi_device_register_full(struct mipi_dsi_host *host, const struct mipi_dsi_device_info *info); void mipi_dsi_device_unregister(struct mipi_dsi_device *dsi); +struct mipi_dsi_device * +devm_mipi_dsi_device_register_full(struct device *dev, struct mipi_dsi_host *host, + const struct mipi_dsi_device_info *info); struct mipi_dsi_device *of_find_mipi_dsi_device_by_node(struct device_node *np); int mipi_dsi_attach(struct mipi_dsi_device *dsi); int mipi_dsi_detach(struct mipi_dsi_device *dsi); +int devm_mipi_dsi_attach(struct device *dev, struct mipi_dsi_device *dsi); int mipi_dsi_shutdown_peripheral(struct mipi_dsi_device *dsi); int mipi_dsi_turn_on_peripheral(struct mipi_dsi_device *dsi); int mipi_dsi_set_maximum_return_packet_size(struct mipi_dsi_device *dsi, diff --git a/include/drm/drm_mode_config.h b/include/drm/drm_mode_config.h index 1ddf7783fdf7..48b7de80daf5 100644 --- a/include/drm/drm_mode_config.h +++ b/include/drm/drm_mode_config.h @@ -103,14 +103,13 @@ struct drm_mode_config_funcs { * Callback used by helpers to inform the driver of output configuration * changes. * - * Drivers implementing fbdev emulation with the helpers can call - * drm_fb_helper_hotplug_changed from this hook to inform the fbdev - * helper of output changes. + * Drivers implementing fbdev emulation use drm_kms_helper_hotplug_event() + * to call this hook to inform the fbdev helper of output changes. * - * FIXME: - * - * Except that there's no vtable for device-level helper callbacks - * there's no reason this is a core function. + * This hook is deprecated, drivers should instead use + * drm_fbdev_generic_setup() which takes care of any necessary + * hotplug event forwarding already without further involvement by + * the driver. */ void (*output_poll_changed)(struct drm_device *dev); diff --git a/include/drm/drm_plane.h b/include/drm/drm_plane.h index fed97e35626f..0c1102dc4d88 100644 --- a/include/drm/drm_plane.h +++ b/include/drm/drm_plane.h @@ -43,7 +43,7 @@ enum drm_scaling_filter { /** * struct drm_plane_state - mutable plane state * - * Please not that the destination coordinates @crtc_x, @crtc_y, @crtc_h and + * Please note that the destination coordinates @crtc_x, @crtc_y, @crtc_h and * @crtc_w and the source coordinates @src_x, @src_y, @src_h and @src_w are the * raw coordinates provided by userspace. Drivers should use * drm_atomic_helper_check_plane_state() and only use the derived rectangles in diff --git a/include/drm/drm_print.h b/include/drm/drm_print.h index 15a089a87c22..22fabdeed297 100644 --- a/include/drm/drm_print.h +++ b/include/drm/drm_print.h @@ -340,6 +340,8 @@ void drm_dev_dbg(const struct device *dev, enum drm_debug_category category, /** * DRM_DEV_ERROR() - Error output. * + * NOTE: this is deprecated in favor of drm_err() or dev_err(). + * * @dev: device pointer * @fmt: printf() like format string. */ @@ -349,6 +351,9 @@ void drm_dev_dbg(const struct device *dev, enum drm_debug_category category, /** * DRM_DEV_ERROR_RATELIMITED() - Rate limited error output. * + * NOTE: this is deprecated in favor of drm_err_ratelimited() or + * dev_err_ratelimited(). + * * @dev: device pointer * @fmt: printf() like format string. * @@ -364,9 +369,11 @@ void drm_dev_dbg(const struct device *dev, enum drm_debug_category category, DRM_DEV_ERROR(dev, fmt, ##__VA_ARGS__); \ }) +/* NOTE: this is deprecated in favor of drm_info() or dev_info(). */ #define DRM_DEV_INFO(dev, fmt, ...) \ drm_dev_printk(dev, KERN_INFO, fmt, ##__VA_ARGS__) +/* NOTE: this is deprecated in favor of drm_info_once() or dev_info_once(). */ #define DRM_DEV_INFO_ONCE(dev, fmt, ...) \ ({ \ static bool __print_once __read_mostly; \ @@ -379,6 +386,8 @@ void drm_dev_dbg(const struct device *dev, enum drm_debug_category category, /** * DRM_DEV_DEBUG() - Debug output for generic drm code * + * NOTE: this is deprecated in favor of drm_dbg_core(). + * * @dev: device pointer * @fmt: printf() like format string. */ @@ -387,6 +396,8 @@ void drm_dev_dbg(const struct device *dev, enum drm_debug_category category, /** * DRM_DEV_DEBUG_DRIVER() - Debug output for vendor specific part of the driver * + * NOTE: this is deprecated in favor of drm_dbg() or dev_dbg(). + * * @dev: device pointer * @fmt: printf() like format string. */ @@ -395,6 +406,8 @@ void drm_dev_dbg(const struct device *dev, enum drm_debug_category category, /** * DRM_DEV_DEBUG_KMS() - Debug output for modesetting code * + * NOTE: this is deprecated in favor of drm_dbg_kms(). + * * @dev: device pointer * @fmt: printf() like format string. */ @@ -480,47 +493,63 @@ void __drm_err(const char *format, ...); #define _DRM_PRINTK(once, level, fmt, ...) \ printk##once(KERN_##level "[" DRM_NAME "] " fmt, ##__VA_ARGS__) +/* NOTE: this is deprecated in favor of pr_info(). */ #define DRM_INFO(fmt, ...) \ _DRM_PRINTK(, INFO, fmt, ##__VA_ARGS__) +/* NOTE: this is deprecated in favor of pr_notice(). */ #define DRM_NOTE(fmt, ...) \ _DRM_PRINTK(, NOTICE, fmt, ##__VA_ARGS__) +/* NOTE: this is deprecated in favor of pr_warn(). */ #define DRM_WARN(fmt, ...) \ _DRM_PRINTK(, WARNING, fmt, ##__VA_ARGS__) +/* NOTE: this is deprecated in favor of pr_info_once(). */ #define DRM_INFO_ONCE(fmt, ...) \ _DRM_PRINTK(_once, INFO, fmt, ##__VA_ARGS__) +/* NOTE: this is deprecated in favor of pr_notice_once(). */ #define DRM_NOTE_ONCE(fmt, ...) \ _DRM_PRINTK(_once, NOTICE, fmt, ##__VA_ARGS__) +/* NOTE: this is deprecated in favor of pr_warn_once(). */ #define DRM_WARN_ONCE(fmt, ...) \ _DRM_PRINTK(_once, WARNING, fmt, ##__VA_ARGS__) +/* NOTE: this is deprecated in favor of pr_err(). */ #define DRM_ERROR(fmt, ...) \ __drm_err(fmt, ##__VA_ARGS__) +/* NOTE: this is deprecated in favor of pr_err_ratelimited(). */ #define DRM_ERROR_RATELIMITED(fmt, ...) \ DRM_DEV_ERROR_RATELIMITED(NULL, fmt, ##__VA_ARGS__) +/* NOTE: this is deprecated in favor of drm_dbg_core(NULL, ...). */ #define DRM_DEBUG(fmt, ...) \ __drm_dbg(DRM_UT_CORE, fmt, ##__VA_ARGS__) +/* NOTE: this is deprecated in favor of drm_dbg(NULL, ...). */ #define DRM_DEBUG_DRIVER(fmt, ...) \ __drm_dbg(DRM_UT_DRIVER, fmt, ##__VA_ARGS__) +/* NOTE: this is deprecated in favor of drm_dbg_kms(NULL, ...). */ #define DRM_DEBUG_KMS(fmt, ...) \ __drm_dbg(DRM_UT_KMS, fmt, ##__VA_ARGS__) +/* NOTE: this is deprecated in favor of drm_dbg_prime(NULL, ...). */ #define DRM_DEBUG_PRIME(fmt, ...) \ __drm_dbg(DRM_UT_PRIME, fmt, ##__VA_ARGS__) +/* NOTE: this is deprecated in favor of drm_dbg_atomic(NULL, ...). */ #define DRM_DEBUG_ATOMIC(fmt, ...) \ __drm_dbg(DRM_UT_ATOMIC, fmt, ##__VA_ARGS__) +/* NOTE: this is deprecated in favor of drm_dbg_vbl(NULL, ...). */ #define DRM_DEBUG_VBL(fmt, ...) \ __drm_dbg(DRM_UT_VBL, fmt, ##__VA_ARGS__) +/* NOTE: this is deprecated in favor of drm_dbg_lease(NULL, ...). */ #define DRM_DEBUG_LEASE(fmt, ...) \ __drm_dbg(DRM_UT_LEASE, fmt, ##__VA_ARGS__) +/* NOTE: this is deprecated in favor of drm_dbg_dp(NULL, ...). */ #define DRM_DEBUG_DP(fmt, ...) \ __drm_dbg(DRM_UT_DP, fmt, ## __VA_ARGS__) @@ -536,6 +565,7 @@ void __drm_err(const char *format, ...); #define drm_dbg_kms_ratelimited(drm, fmt, ...) \ __DRM_DEFINE_DBG_RATELIMITED(KMS, drm, fmt, ## __VA_ARGS__) +/* NOTE: this is deprecated in favor of drm_dbg_kms_ratelimited(NULL, ...). */ #define DRM_DEBUG_KMS_RATELIMITED(fmt, ...) drm_dbg_kms_ratelimited(NULL, fmt, ## __VA_ARGS__) /* diff --git a/include/drm/drm_probe_helper.h b/include/drm/drm_probe_helper.h index 8d3ed2834d34..04c57564c397 100644 --- a/include/drm/drm_probe_helper.h +++ b/include/drm/drm_probe_helper.h @@ -18,6 +18,7 @@ int drm_helper_probe_detect(struct drm_connector *connector, void drm_kms_helper_poll_init(struct drm_device *dev); void drm_kms_helper_poll_fini(struct drm_device *dev); bool drm_helper_hpd_irq_event(struct drm_device *dev); +bool drm_connector_helper_hpd_irq_event(struct drm_connector *connector); void drm_kms_helper_hotplug_event(struct drm_device *dev); void drm_kms_helper_poll_disable(struct drm_device *dev); diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index 88ae7f331bb1..f011e4c407f2 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -27,9 +27,12 @@ #include <drm/spsc_queue.h> #include <linux/dma-fence.h> #include <linux/completion.h> +#include <linux/xarray.h> #define MAX_WAIT_SCHED_ENTITY_Q_EMPTY msecs_to_jiffies(1000) +struct drm_gem_object; + struct drm_gpu_scheduler; struct drm_sched_rq; @@ -50,56 +53,147 @@ enum drm_sched_priority { * struct drm_sched_entity - A wrapper around a job queue (typically * attached to the DRM file_priv). * - * @list: used to append this struct to the list of entities in the - * runqueue. - * @rq: runqueue on which this entity is currently scheduled. - * @sched_list: A list of schedulers (drm_gpu_schedulers). - * Jobs from this entity can be scheduled on any scheduler - * on this list. - * @num_sched_list: number of drm_gpu_schedulers in the sched_list. - * @priority: priority of the entity - * @rq_lock: lock to modify the runqueue to which this entity belongs. - * @job_queue: the list of jobs of this entity. - * @fence_seq: a linearly increasing seqno incremented with each - * new &drm_sched_fence which is part of the entity. - * @fence_context: a unique context for all the fences which belong - * to this entity. - * The &drm_sched_fence.scheduled uses the - * fence_context but &drm_sched_fence.finished uses - * fence_context + 1. - * @dependency: the dependency fence of the job which is on the top - * of the job queue. - * @cb: callback for the dependency fence above. - * @guilty: points to ctx's guilty. - * @fini_status: contains the exit status in case the process was signalled. - * @last_scheduled: points to the finished fence of the last scheduled job. - * @last_user: last group leader pushing a job into the entity. - * @stopped: Marks the enity as removed from rq and destined for termination. - * @entity_idle: Signals when enityt is not in use - * * Entities will emit jobs in order to their corresponding hardware * ring, and the scheduler will alternate between entities based on * scheduling policy. */ struct drm_sched_entity { + /** + * @list: + * + * Used to append this struct to the list of entities in the runqueue + * @rq under &drm_sched_rq.entities. + * + * Protected by &drm_sched_rq.lock of @rq. + */ struct list_head list; + + /** + * @rq: + * + * Runqueue on which this entity is currently scheduled. + * + * FIXME: Locking is very unclear for this. Writers are protected by + * @rq_lock, but readers are generally lockless and seem to just race + * with not even a READ_ONCE. + */ struct drm_sched_rq *rq; + + /** + * @sched_list: + * + * A list of schedulers (struct drm_gpu_scheduler). Jobs from this entity can + * be scheduled on any scheduler on this list. + * + * This can be modified by calling drm_sched_entity_modify_sched(). + * Locking is entirely up to the driver, see the above function for more + * details. + * + * This will be set to NULL if &num_sched_list equals 1 and @rq has been + * set already. + * + * FIXME: This means priority changes through + * drm_sched_entity_set_priority() will be lost henceforth in this case. + */ struct drm_gpu_scheduler **sched_list; + + /** + * @num_sched_list: + * + * Number of drm_gpu_schedulers in the @sched_list. + */ unsigned int num_sched_list; + + /** + * @priority: + * + * Priority of the entity. This can be modified by calling + * drm_sched_entity_set_priority(). Protected by &rq_lock. + */ enum drm_sched_priority priority; + + /** + * @rq_lock: + * + * Lock to modify the runqueue to which this entity belongs. + */ spinlock_t rq_lock; + /** + * @job_queue: the list of jobs of this entity. + */ struct spsc_queue job_queue; + /** + * @fence_seq: + * + * A linearly increasing seqno incremented with each new + * &drm_sched_fence which is part of the entity. + * + * FIXME: Callers of drm_sched_job_arm() need to ensure correct locking, + * this doesn't need to be atomic. + */ atomic_t fence_seq; + + /** + * @fence_context: + * + * A unique context for all the fences which belong to this entity. The + * &drm_sched_fence.scheduled uses the fence_context but + * &drm_sched_fence.finished uses fence_context + 1. + */ uint64_t fence_context; + /** + * @dependency: + * + * The dependency fence of the job which is on the top of the job queue. + */ struct dma_fence *dependency; + + /** + * @cb: + * + * Callback for the dependency fence above. + */ struct dma_fence_cb cb; + + /** + * @guilty: + * + * Points to entities' guilty. + */ atomic_t *guilty; + + /** + * @last_scheduled: + * + * Points to the finished fence of the last scheduled job. Only written + * by the scheduler thread, can be accessed locklessly from + * drm_sched_job_arm() iff the queue is empty. + */ struct dma_fence *last_scheduled; + + /** + * @last_user: last group leader pushing a job into the entity. + */ struct task_struct *last_user; + + /** + * @stopped: + * + * Marks the enity as removed from rq and destined for + * termination. This is set by calling drm_sched_entity_flush() and by + * drm_sched_fini(). + */ bool stopped; + + /** + * @entity_idle: + * + * Signals when entity is not in use, used to sequence entity cleanup in + * drm_sched_entity_fini(). + */ struct completion entity_idle; }; @@ -198,6 +292,17 @@ struct drm_sched_job { enum drm_sched_priority s_priority; struct drm_sched_entity *entity; struct dma_fence_cb cb; + /** + * @dependencies: + * + * Contains the dependencies as struct dma_fence for this job, see + * drm_sched_job_add_dependency() and + * drm_sched_job_add_implicit_dependencies(). + */ + struct xarray dependencies; + + /** @last_dependency: tracks @dependencies as they signal */ + unsigned long last_dependency; }; static inline bool drm_sched_invalidate_job(struct drm_sched_job *s_job, @@ -220,9 +325,15 @@ enum drm_gpu_sched_stat { */ struct drm_sched_backend_ops { /** - * @dependency: Called when the scheduler is considering scheduling - * this job next, to get another struct dma_fence for this job to - * block on. Once it returns NULL, run_job() may be called. + * @dependency: + * + * Called when the scheduler is considering scheduling this job next, to + * get another struct dma_fence for this job to block on. Once it + * returns NULL, run_job() may be called. + * + * If a driver exclusively uses drm_sched_job_add_dependency() and + * drm_sched_job_add_implicit_dependencies() this can be ommitted and + * left as NULL. */ struct dma_fence *(*dependency)(struct drm_sched_job *sched_job, struct drm_sched_entity *s_entity); @@ -348,6 +459,14 @@ void drm_sched_fini(struct drm_gpu_scheduler *sched); int drm_sched_job_init(struct drm_sched_job *job, struct drm_sched_entity *entity, void *owner); +void drm_sched_job_arm(struct drm_sched_job *job); +int drm_sched_job_add_dependency(struct drm_sched_job *job, + struct dma_fence *fence); +int drm_sched_job_add_implicit_dependencies(struct drm_sched_job *job, + struct drm_gem_object *obj, + bool write); + + void drm_sched_entity_modify_sched(struct drm_sched_entity *entity, struct drm_gpu_scheduler **sched_list, unsigned int num_sched_list); @@ -381,14 +500,17 @@ void drm_sched_entity_fini(struct drm_sched_entity *entity); void drm_sched_entity_destroy(struct drm_sched_entity *entity); void drm_sched_entity_select_rq(struct drm_sched_entity *entity); struct drm_sched_job *drm_sched_entity_pop_job(struct drm_sched_entity *entity); -void drm_sched_entity_push_job(struct drm_sched_job *sched_job, - struct drm_sched_entity *entity); +void drm_sched_entity_push_job(struct drm_sched_job *sched_job); void drm_sched_entity_set_priority(struct drm_sched_entity *entity, enum drm_sched_priority priority); bool drm_sched_entity_is_ready(struct drm_sched_entity *entity); -struct drm_sched_fence *drm_sched_fence_create( +struct drm_sched_fence *drm_sched_fence_alloc( struct drm_sched_entity *s_entity, void *owner); +void drm_sched_fence_init(struct drm_sched_fence *fence, + struct drm_sched_entity *entity); +void drm_sched_fence_free(struct drm_sched_fence *fence); + void drm_sched_fence_scheduled(struct drm_sched_fence *fence); void drm_sched_fence_finished(struct drm_sched_fence *fence); diff --git a/include/drm/gud.h b/include/drm/gud.h index 0b46b54fe56e..c52a8ba4ae4e 100644 --- a/include/drm/gud.h +++ b/include/drm/gud.h @@ -246,10 +246,12 @@ struct gud_state_req { /* Get supported pixel formats as a byte array of GUD_PIXEL_FORMAT_* */ #define GUD_REQ_GET_FORMATS 0x40 #define GUD_FORMATS_MAX_NUM 32 - /* R1 is a 1-bit monochrome transfer format presented to userspace as XRGB8888 */ - #define GUD_PIXEL_FORMAT_R1 0x01 + #define GUD_PIXEL_FORMAT_R1 0x01 /* 1-bit monochrome */ + #define GUD_PIXEL_FORMAT_R8 0x08 /* 8-bit greyscale */ #define GUD_PIXEL_FORMAT_XRGB1111 0x20 + #define GUD_PIXEL_FORMAT_RGB332 0x30 #define GUD_PIXEL_FORMAT_RGB565 0x40 + #define GUD_PIXEL_FORMAT_RGB888 0x50 #define GUD_PIXEL_FORMAT_XRGB8888 0x80 #define GUD_PIXEL_FORMAT_ARGB8888 0x81 diff --git a/include/drm/i915_pciids.h b/include/drm/i915_pciids.h index eee18fa53b54..c00ac54692d7 100644 --- a/include/drm/i915_pciids.h +++ b/include/drm/i915_pciids.h @@ -632,18 +632,16 @@ INTEL_VGA_DEVICE(0x4905, info), \ INTEL_VGA_DEVICE(0x4906, info), \ INTEL_VGA_DEVICE(0x4907, info), \ - INTEL_VGA_DEVICE(0x4908, info) + INTEL_VGA_DEVICE(0x4908, info), \ + INTEL_VGA_DEVICE(0x4909, info) /* ADL-S */ #define INTEL_ADLS_IDS(info) \ INTEL_VGA_DEVICE(0x4680, info), \ - INTEL_VGA_DEVICE(0x4681, info), \ INTEL_VGA_DEVICE(0x4682, info), \ - INTEL_VGA_DEVICE(0x4683, info), \ INTEL_VGA_DEVICE(0x4688, info), \ - INTEL_VGA_DEVICE(0x4689, info), \ + INTEL_VGA_DEVICE(0x468A, info), \ INTEL_VGA_DEVICE(0x4690, info), \ - INTEL_VGA_DEVICE(0x4691, info), \ INTEL_VGA_DEVICE(0x4692, info), \ INTEL_VGA_DEVICE(0x4693, info) diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h index f681bbdbc698..76d7c33884da 100644 --- a/include/drm/ttm/ttm_bo_api.h +++ b/include/drm/ttm/ttm_bo_api.h @@ -265,18 +265,6 @@ static inline int ttm_bo_wait_ctx(struct ttm_buffer_object *bo, struct ttm_opera } /** - * ttm_bo_mem_compat - Check if proposed placement is compatible with a bo - * - * @placement: Return immediately if buffer is busy. - * @mem: The struct ttm_resource indicating the region where the bo resides - * @new_flags: Describes compatible placement found - * - * Returns true if the placement is compatible - */ -bool ttm_bo_mem_compat(struct ttm_placement *placement, struct ttm_resource *mem, - uint32_t *new_flags); - -/** * ttm_bo_validate * * @bo: The buffer object. diff --git a/include/drm/ttm/ttm_caching.h b/include/drm/ttm/ttm_caching.h index 3c9dd65f5aaf..235a743d90e1 100644 --- a/include/drm/ttm/ttm_caching.h +++ b/include/drm/ttm/ttm_caching.h @@ -27,9 +27,26 @@ #define TTM_NUM_CACHING_TYPES 3 +/** + * enum ttm_caching - CPU caching and BUS snooping behavior. + */ enum ttm_caching { + /** + * @ttm_uncached: Most defensive option for device mappings, + * don't even allow write combining. + */ ttm_uncached, + + /** + * @ttm_write_combined: Don't cache read accesses, but allow at least + * writes to be combined. + */ ttm_write_combined, + + /** + * @ttm_cached: Fully cached like normal system memory, requires that + * devices snoop the CPU cache on accesses. + */ ttm_cached }; diff --git a/include/drm/ttm/ttm_device.h b/include/drm/ttm/ttm_device.h index cd592f8e941b..0a4ddec78d8f 100644 --- a/include/drm/ttm/ttm_device.h +++ b/include/drm/ttm/ttm_device.h @@ -39,31 +39,23 @@ struct ttm_operation_ctx; /** * struct ttm_global - Buffer object driver global data. - * - * @dummy_read_page: Pointer to a dummy page used for mapping requests - * of unpopulated pages. - * @shrink: A shrink callback object used for buffer object swap. - * @device_list_mutex: Mutex protecting the device list. - * This mutex is held while traversing the device list for pm options. - * @lru_lock: Spinlock protecting the bo subsystem lru lists. - * @device_list: List of buffer object devices. - * @swap_lru: Lru list of buffer objects used for swapping. */ extern struct ttm_global { /** - * Constant after init. + * @dummy_read_page: Pointer to a dummy page used for mapping requests + * of unpopulated pages. Constant after init. */ - struct page *dummy_read_page; /** - * Protected by ttm_global_mutex. + * @device_list: List of buffer object devices. Protected by + * ttm_global_mutex. */ struct list_head device_list; /** - * Internal protection. + * @bo_count: Number of buffer objects allocated by devices. */ atomic_t bo_count; } ttm_glob; @@ -73,7 +65,7 @@ struct ttm_device_funcs { * ttm_tt_create * * @bo: The buffer object to create the ttm for. - * @page_flags: Page flags as identified by TTM_PAGE_FLAG_XX flags. + * @page_flags: Page flags as identified by TTM_TT_FLAG_XX flags. * * Create a struct ttm_tt to back data with system memory pages. * No pages are actually allocated. @@ -230,49 +222,64 @@ struct ttm_device_funcs { /** * struct ttm_device - Buffer object driver device-specific data. - * - * @device_list: Our entry in the global device list. - * @funcs: Function table for the device. - * @sysman: Resource manager for the system domain. - * @man_drv: An array of resource_managers. - * @vma_manager: Address space manager. - * @pool: page pool for the device. - * @dev_mapping: A pointer to the struct address_space representing the - * device address space. - * @wq: Work queue structure for the delayed delete workqueue. */ struct ttm_device { - /* + /** + * @device_list: Our entry in the global device list. * Constant after bo device init */ struct list_head device_list; + + /** + * @funcs: Function table for the device. + * Constant after bo device init + */ struct ttm_device_funcs *funcs; - /* + /** + * @sysman: Resource manager for the system domain. * Access via ttm_manager_type. */ struct ttm_resource_manager sysman; + + /** + * @man_drv: An array of resource_managers, one per resource type. + */ struct ttm_resource_manager *man_drv[TTM_NUM_MEM_TYPES]; - /* - * Protected by internal locks. + /** + * @vma_manager: Address space manager for finding BOs to mmap. */ struct drm_vma_offset_manager *vma_manager; + + /** + * @pool: page pool for the device. + */ struct ttm_pool pool; - /* - * Protection for the per manager LRU and ddestroy lists. + /** + * @lru_lock: Protection for the per manager LRU and ddestroy lists. */ spinlock_t lru_lock; + + /** + * @ddestroy: Destroyed but not yet cleaned up buffer objects. + */ struct list_head ddestroy; - /* - * Protected by load / firstopen / lastclose /unload sync. + /** + * @pinned: Buffer objects which are pinned and so not on any LRU list. + */ + struct list_head pinned; + + /** + * @dev_mapping: A pointer to the struct address_space for invalidating + * CPU mappings on buffer move. Protected by load/unload sync. */ struct address_space *dev_mapping; - /* - * Internal protection. + /** + * @wq: Work queue structure for the delayed delete workqueue. */ struct delayed_work wq; }; @@ -284,12 +291,15 @@ int ttm_device_swapout(struct ttm_device *bdev, struct ttm_operation_ctx *ctx, static inline struct ttm_resource_manager * ttm_manager_type(struct ttm_device *bdev, int mem_type) { + BUILD_BUG_ON(__builtin_constant_p(mem_type) + && mem_type >= TTM_NUM_MEM_TYPES); return bdev->man_drv[mem_type]; } static inline void ttm_set_driver_manager(struct ttm_device *bdev, int type, struct ttm_resource_manager *manager) { + BUILD_BUG_ON(__builtin_constant_p(type) && type >= TTM_NUM_MEM_TYPES); bdev->man_drv[type] = manager; } @@ -298,5 +308,6 @@ int ttm_device_init(struct ttm_device *bdev, struct ttm_device_funcs *funcs, struct drm_vma_offset_manager *vma_manager, bool use_dma_alloc, bool use_dma32); void ttm_device_fini(struct ttm_device *bdev); +void ttm_device_clear_dma_mappings(struct ttm_device *bdev); #endif diff --git a/include/drm/ttm/ttm_placement.h b/include/drm/ttm/ttm_placement.h index 8995c9e4ec1b..76d1b9119a2b 100644 --- a/include/drm/ttm/ttm_placement.h +++ b/include/drm/ttm/ttm_placement.h @@ -58,6 +58,7 @@ * * @fpfn: first valid page frame number to put the object * @lpfn: last valid page frame number to put the object + * @mem_type: One of TTM_PL_* where the resource should be allocated from. * @flags: memory domain and caching flags for the object * * Structure indicating a possible place to put an object. diff --git a/include/drm/ttm/ttm_pool.h b/include/drm/ttm/ttm_pool.h index 4321728bdd11..ef09b23d29e3 100644 --- a/include/drm/ttm/ttm_pool.h +++ b/include/drm/ttm/ttm_pool.h @@ -37,7 +37,7 @@ struct ttm_pool; struct ttm_operation_ctx; /** - * ttm_pool_type - Pool for a certain memory type + * struct ttm_pool_type - Pool for a certain memory type * * @pool: the pool we belong to, might be NULL for the global ones * @order: the allocation order our pages have @@ -58,8 +58,9 @@ struct ttm_pool_type { }; /** - * ttm_pool - Pool for all caching and orders + * struct ttm_pool - Pool for all caching and orders * + * @dev: the device we allocate pages for * @use_dma_alloc: if coherent DMA allocations should be used * @use_dma32: if GFP_DMA32 should be used * @caching: pools for each caching/order diff --git a/include/drm/ttm/ttm_range_manager.h b/include/drm/ttm/ttm_range_manager.h index 22b6fa42ac20..7963b957e9ef 100644 --- a/include/drm/ttm/ttm_range_manager.h +++ b/include/drm/ttm/ttm_range_manager.h @@ -4,6 +4,7 @@ #define _TTM_RANGE_MANAGER_H_ #include <drm/ttm/ttm_resource.h> +#include <drm/ttm/ttm_device.h> #include <drm/drm_mm.h> /** @@ -33,10 +34,23 @@ to_ttm_range_mgr_node(struct ttm_resource *res) return container_of(res, struct ttm_range_mgr_node, base); } -int ttm_range_man_init(struct ttm_device *bdev, +int ttm_range_man_init_nocheck(struct ttm_device *bdev, unsigned type, bool use_tt, unsigned long p_size); -int ttm_range_man_fini(struct ttm_device *bdev, +int ttm_range_man_fini_nocheck(struct ttm_device *bdev, unsigned type); +static __always_inline int ttm_range_man_init(struct ttm_device *bdev, + unsigned int type, bool use_tt, + unsigned long p_size) +{ + BUILD_BUG_ON(__builtin_constant_p(type) && type >= TTM_NUM_MEM_TYPES); + return ttm_range_man_init_nocheck(bdev, type, use_tt, p_size); +} +static __always_inline int ttm_range_man_fini(struct ttm_device *bdev, + unsigned int type) +{ + BUILD_BUG_ON(__builtin_constant_p(type) && type >= TTM_NUM_MEM_TYPES); + return ttm_range_man_fini_nocheck(bdev, type); +} #endif diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h index 140b6b9a8bbe..5952051091cd 100644 --- a/include/drm/ttm/ttm_resource.h +++ b/include/drm/ttm/ttm_resource.h @@ -40,6 +40,7 @@ struct ttm_resource_manager; struct ttm_resource; struct ttm_place; struct ttm_buffer_object; +struct ttm_placement; struct dma_buf_map; struct io_mapping; struct sg_table; @@ -102,10 +103,7 @@ struct ttm_resource_manager_func { * struct ttm_resource_manager * * @use_type: The memory type is enabled. - * @flags: TTM_MEMTYPE_XX flags identifying the traits of the memory - * managed by this memory type. - * @gpu_offset: If used, the GPU offset of the first managed page of - * fixed memory or the first managed location in an aperture. + * @use_tt: If a TT object should be used for the backing store. * @size: Size of the managed region. * @func: structure pointer implementing the range manager. See above * @move_lock: lock for move fence @@ -143,6 +141,7 @@ struct ttm_resource_manager { * @addr: mapped virtual address * @offset: physical addr * @is_iomem: is this io memory ? + * @caching: See enum ttm_caching * * Structure indicating the bus placement of an object. */ @@ -266,6 +265,8 @@ int ttm_resource_alloc(struct ttm_buffer_object *bo, const struct ttm_place *place, struct ttm_resource **res); void ttm_resource_free(struct ttm_buffer_object *bo, struct ttm_resource **res); +bool ttm_resource_compat(struct ttm_resource *res, + struct ttm_placement *placement); void ttm_resource_manager_init(struct ttm_resource_manager *man, unsigned long p_size); diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h index b20e89d321b0..f20832139815 100644 --- a/include/drm/ttm/ttm_tt.h +++ b/include/drm/ttm/ttm_tt.h @@ -38,36 +38,70 @@ struct ttm_resource; struct ttm_buffer_object; struct ttm_operation_ctx; -#define TTM_PAGE_FLAG_SWAPPED (1 << 4) -#define TTM_PAGE_FLAG_ZERO_ALLOC (1 << 6) -#define TTM_PAGE_FLAG_SG (1 << 8) -#define TTM_PAGE_FLAG_NO_RETRY (1 << 9) - -#define TTM_PAGE_FLAG_PRIV_POPULATED (1 << 31) - /** - * struct ttm_tt - * - * @pages: Array of pages backing the data. - * @page_flags: see TTM_PAGE_FLAG_* - * @num_pages: Number of pages in the page array. - * @sg: for SG objects via dma-buf - * @dma_address: The DMA (bus) addresses of the pages - * @swap_storage: Pointer to shmem struct file for swap storage. - * @pages_list: used by some page allocation backend - * @caching: The current caching state of the pages. - * - * This is a structure holding the pages, caching- and aperture binding - * status for a buffer object that isn't backed by fixed (VRAM / AGP) + * struct ttm_tt - This is a structure holding the pages, caching- and aperture + * binding status for a buffer object that isn't backed by fixed (VRAM / AGP) * memory. */ struct ttm_tt { + /** @pages: Array of pages backing the data. */ struct page **pages; + /** + * @page_flags: The page flags. + * + * Supported values: + * + * TTM_TT_FLAG_SWAPPED: Set by TTM when the pages have been unpopulated + * and swapped out by TTM. Calling ttm_tt_populate() will then swap the + * pages back in, and unset the flag. Drivers should in general never + * need to touch this. + * + * TTM_TT_FLAG_ZERO_ALLOC: Set if the pages will be zeroed on + * allocation. + * + * TTM_TT_FLAG_EXTERNAL: Set if the underlying pages were allocated + * externally, like with dma-buf or userptr. This effectively disables + * TTM swapping out such pages. Also important is to prevent TTM from + * ever directly mapping these pages. + * + * Note that enum ttm_bo_type.ttm_bo_type_sg objects will always enable + * this flag. + * + * TTM_TT_FLAG_EXTERNAL_MAPPABLE: Same behaviour as + * TTM_TT_FLAG_EXTERNAL, but with the reduced restriction that it is + * still valid to use TTM to map the pages directly. This is useful when + * implementing a ttm_tt backend which still allocates driver owned + * pages underneath(say with shmem). + * + * Note that since this also implies TTM_TT_FLAG_EXTERNAL, the usage + * here should always be: + * + * page_flags = TTM_TT_FLAG_EXTERNAL | + * TTM_TT_FLAG_EXTERNAL_MAPPABLE; + * + * TTM_TT_FLAG_PRIV_POPULATED: TTM internal only. DO NOT USE. This is + * set by TTM after ttm_tt_populate() has successfully returned, and is + * then unset when TTM calls ttm_tt_unpopulate(). + */ +#define TTM_TT_FLAG_SWAPPED (1 << 0) +#define TTM_TT_FLAG_ZERO_ALLOC (1 << 1) +#define TTM_TT_FLAG_EXTERNAL (1 << 2) +#define TTM_TT_FLAG_EXTERNAL_MAPPABLE (1 << 3) + +#define TTM_TT_FLAG_PRIV_POPULATED (1 << 31) uint32_t page_flags; + /** @num_pages: Number of pages in the page array. */ uint32_t num_pages; + /** @sg: for SG objects via dma-buf. */ struct sg_table *sg; + /** @dma_address: The DMA (bus) addresses of the pages. */ dma_addr_t *dma_address; + /** @swap_storage: Pointer to shmem struct file for swap storage. */ struct file *swap_storage; + /** + * @caching: The current caching state of the pages, see enum + * ttm_caching. + */ enum ttm_caching caching; }; @@ -85,7 +119,7 @@ struct ttm_kmap_iter_tt { static inline bool ttm_tt_is_populated(struct ttm_tt *tt) { - return tt->page_flags & TTM_PAGE_FLAG_PRIV_POPULATED; + return tt->page_flags & TTM_TT_FLAG_PRIV_POPULATED; } /** @@ -104,7 +138,7 @@ int ttm_tt_create(struct ttm_buffer_object *bo, bool zero_alloc); * * @ttm: The struct ttm_tt. * @bo: The buffer object we create the ttm for. - * @page_flags: Page flags as identified by TTM_PAGE_FLAG_XX flags. + * @page_flags: Page flags as identified by TTM_TT_FLAG_XX flags. * @caching: the desired caching state of the pages * * Create a struct ttm_tt to back data with system memory pages. @@ -127,8 +161,9 @@ int ttm_sg_tt_init(struct ttm_tt *ttm_dma, struct ttm_buffer_object *bo, void ttm_tt_fini(struct ttm_tt *ttm); /** - * ttm_ttm_destroy: + * ttm_tt_destroy: * + * @bdev: the ttm_device this object belongs to * @ttm: The struct ttm_tt. * * Unbind, unpopulate and destroy common struct ttm_tt. @@ -136,13 +171,6 @@ void ttm_tt_fini(struct ttm_tt *ttm); void ttm_tt_destroy(struct ttm_device *bdev, struct ttm_tt *ttm); /** - * ttm_tt_destroy_common: - * - * Called from driver to destroy common path. - */ -void ttm_tt_destroy_common(struct ttm_device *bdev, struct ttm_tt *ttm); - -/** * ttm_tt_swapin: * * @ttm: The struct ttm_tt. @@ -156,15 +184,19 @@ int ttm_tt_swapout(struct ttm_device *bdev, struct ttm_tt *ttm, /** * ttm_tt_populate - allocate pages for a ttm * + * @bdev: the ttm_device this object belongs to * @ttm: Pointer to the ttm_tt structure + * @ctx: operation context for populating the tt object. * * Calls the driver method to allocate pages for a ttm */ -int ttm_tt_populate(struct ttm_device *bdev, struct ttm_tt *ttm, struct ttm_operation_ctx *ctx); +int ttm_tt_populate(struct ttm_device *bdev, struct ttm_tt *ttm, + struct ttm_operation_ctx *ctx); /** * ttm_tt_unpopulate - free pages from a ttm * + * @bdev: the ttm_device this object belongs to * @ttm: Pointer to the ttm_tt structure * * Calls the driver method to free all pages from a ttm @@ -181,7 +213,7 @@ void ttm_tt_unpopulate(struct ttm_device *bdev, struct ttm_tt *ttm); */ static inline void ttm_tt_mark_for_clear(struct ttm_tt *ttm) { - ttm->page_flags |= TTM_PAGE_FLAG_ZERO_ALLOC; + ttm->page_flags |= TTM_TT_FLAG_ZERO_ALLOC; } void ttm_tt_mgr_init(unsigned long num_pages, unsigned long num_dma32_pages); @@ -197,7 +229,7 @@ struct ttm_kmap_iter *ttm_kmap_iter_tt_init(struct ttm_kmap_iter_tt *iter_tt, * * @bo: Buffer object we allocate the ttm for. * @bridge: The agp bridge this device is sitting on. - * @page_flags: Page flags as identified by TTM_PAGE_FLAG_XX flags. + * @page_flags: Page flags as identified by TTM_TT_FLAG_XX flags. * * * Create a TTM backend that uses the indicated AGP bridge as an aperture diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index e1c705fdfa7c..db2e147e069f 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -752,107 +752,54 @@ static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) {} * sock_cgroup_data is embedded at sock->sk_cgrp_data and contains * per-socket cgroup information except for memcg association. * - * On legacy hierarchies, net_prio and net_cls controllers directly set - * attributes on each sock which can then be tested by the network layer. - * On the default hierarchy, each sock is associated with the cgroup it was - * created in and the networking layer can match the cgroup directly. - * - * To avoid carrying all three cgroup related fields separately in sock, - * sock_cgroup_data overloads (prioidx, classid) and the cgroup pointer. - * On boot, sock_cgroup_data records the cgroup that the sock was created - * in so that cgroup2 matches can be made; however, once either net_prio or - * net_cls starts being used, the area is overridden to carry prioidx and/or - * classid. The two modes are distinguished by whether the lowest bit is - * set. Clear bit indicates cgroup pointer while set bit prioidx and - * classid. - * - * While userland may start using net_prio or net_cls at any time, once - * either is used, cgroup2 matching no longer works. There is no reason to - * mix the two and this is in line with how legacy and v2 compatibility is - * handled. On mode switch, cgroup references which are already being - * pointed to by socks may be leaked. While this can be remedied by adding - * synchronization around sock_cgroup_data, given that the number of leaked - * cgroups is bound and highly unlikely to be high, this seems to be the - * better trade-off. + * On legacy hierarchies, net_prio and net_cls controllers directly + * set attributes on each sock which can then be tested by the network + * layer. On the default hierarchy, each sock is associated with the + * cgroup it was created in and the networking layer can match the + * cgroup directly. */ struct sock_cgroup_data { - union { -#ifdef __LITTLE_ENDIAN - struct { - u8 is_data : 1; - u8 no_refcnt : 1; - u8 unused : 6; - u8 padding; - u16 prioidx; - u32 classid; - } __packed; -#else - struct { - u32 classid; - u16 prioidx; - u8 padding; - u8 unused : 6; - u8 no_refcnt : 1; - u8 is_data : 1; - } __packed; + struct cgroup *cgroup; /* v2 */ +#ifdef CONFIG_CGROUP_NET_CLASSID + u32 classid; /* v1 */ +#endif +#ifdef CONFIG_CGROUP_NET_PRIO + u16 prioidx; /* v1 */ #endif - u64 val; - }; }; -/* - * There's a theoretical window where the following accessors race with - * updaters and return part of the previous pointer as the prioidx or - * classid. Such races are short-lived and the result isn't critical. - */ static inline u16 sock_cgroup_prioidx(const struct sock_cgroup_data *skcd) { - /* fallback to 1 which is always the ID of the root cgroup */ - return (skcd->is_data & 1) ? skcd->prioidx : 1; +#ifdef CONFIG_CGROUP_NET_PRIO + return READ_ONCE(skcd->prioidx); +#else + return 1; +#endif } static inline u32 sock_cgroup_classid(const struct sock_cgroup_data *skcd) { - /* fallback to 0 which is the unconfigured default classid */ - return (skcd->is_data & 1) ? skcd->classid : 0; +#ifdef CONFIG_CGROUP_NET_CLASSID + return READ_ONCE(skcd->classid); +#else + return 0; +#endif } -/* - * If invoked concurrently, the updaters may clobber each other. The - * caller is responsible for synchronization. - */ static inline void sock_cgroup_set_prioidx(struct sock_cgroup_data *skcd, u16 prioidx) { - struct sock_cgroup_data skcd_buf = {{ .val = READ_ONCE(skcd->val) }}; - - if (sock_cgroup_prioidx(&skcd_buf) == prioidx) - return; - - if (!(skcd_buf.is_data & 1)) { - skcd_buf.val = 0; - skcd_buf.is_data = 1; - } - - skcd_buf.prioidx = prioidx; - WRITE_ONCE(skcd->val, skcd_buf.val); /* see sock_cgroup_ptr() */ +#ifdef CONFIG_CGROUP_NET_PRIO + WRITE_ONCE(skcd->prioidx, prioidx); +#endif } static inline void sock_cgroup_set_classid(struct sock_cgroup_data *skcd, u32 classid) { - struct sock_cgroup_data skcd_buf = {{ .val = READ_ONCE(skcd->val) }}; - - if (sock_cgroup_classid(&skcd_buf) == classid) - return; - - if (!(skcd_buf.is_data & 1)) { - skcd_buf.val = 0; - skcd_buf.is_data = 1; - } - - skcd_buf.classid = classid; - WRITE_ONCE(skcd->val, skcd_buf.val); /* see sock_cgroup_ptr() */ +#ifdef CONFIG_CGROUP_NET_CLASSID + WRITE_ONCE(skcd->classid, classid); +#endif } #else /* CONFIG_SOCK_CGROUP_DATA */ diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 7bf60454a313..75c151413fda 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -829,33 +829,13 @@ static inline void cgroup_account_cputime_field(struct task_struct *task, */ #ifdef CONFIG_SOCK_CGROUP_DATA -#if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID) -extern spinlock_t cgroup_sk_update_lock; -#endif - -void cgroup_sk_alloc_disable(void); void cgroup_sk_alloc(struct sock_cgroup_data *skcd); void cgroup_sk_clone(struct sock_cgroup_data *skcd); void cgroup_sk_free(struct sock_cgroup_data *skcd); static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd) { -#if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID) - unsigned long v; - - /* - * @skcd->val is 64bit but the following is safe on 32bit too as we - * just need the lower ulong to be written and read atomically. - */ - v = READ_ONCE(skcd->val); - - if (v & 3) - return &cgrp_dfl_root.cgrp; - - return (struct cgroup *)(unsigned long)v ?: &cgrp_dfl_root.cgrp; -#else - return (struct cgroup *)(unsigned long)skcd->val; -#endif + return skcd->cgroup; } #else /* CONFIG_CGROUP_DATA */ diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index 49b0ac8b6fd3..3c4de9b6c6e3 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -62,19 +62,6 @@ #define __no_sanitize_coverage #endif -/* - * Not all versions of clang implement the type-generic versions - * of the builtin overflow checkers. Fortunately, clang implements - * __has_builtin allowing us to avoid awkward version - * checks. Unfortunately, we don't know which version of gcc clang - * pretends to be, so the macro may or may not be defined. - */ -#if __has_builtin(__builtin_mul_overflow) && \ - __has_builtin(__builtin_add_overflow) && \ - __has_builtin(__builtin_sub_overflow) -#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 -#endif - #if __has_feature(shadow_call_stack) # define __noscs __attribute__((__no_sanitize__("shadow-call-stack"))) #endif diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 21c36b69eb06..bd2b881c6b63 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -95,10 +95,8 @@ #if GCC_VERSION >= 70000 #define KASAN_ABI_VERSION 5 -#elif GCC_VERSION >= 50000 +#else #define KASAN_ABI_VERSION 4 -#elif GCC_VERSION >= 40902 -#define KASAN_ABI_VERSION 3 #endif #if __has_attribute(__no_sanitize_address__) @@ -125,10 +123,6 @@ #define __no_sanitize_coverage #endif -#if GCC_VERSION >= 50100 -#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 -#endif - /* * Turn individual warnings and errors on and off locally, depending * on version. diff --git a/include/linux/compiler.h b/include/linux/compiler.h index b67261a1e3e9..3d5af56337bd 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -188,6 +188,8 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, (typeof(ptr)) (__ptr + (off)); }) #endif +#define absolute_pointer(val) RELOC_HIDE((void *)(val), 0) + #ifndef OPTIMIZER_HIDE_VAR /* Make the optimizer believe the variable can be manipulated arbitrarily. */ #define OPTIMIZER_HIDE_VAR(var) \ diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index 8f2106e9e5c1..e6ec63403965 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -21,29 +21,6 @@ */ /* - * __has_attribute is supported on gcc >= 5, clang >= 2.9 and icc >= 17. - * In the meantime, to support gcc < 5, we implement __has_attribute - * by hand. - */ -#ifndef __has_attribute -# define __has_attribute(x) __GCC4_has_attribute_##x -# define __GCC4_has_attribute___assume_aligned__ 1 -# define __GCC4_has_attribute___copy__ 0 -# define __GCC4_has_attribute___designated_init__ 0 -# define __GCC4_has_attribute___error__ 1 -# define __GCC4_has_attribute___externally_visible__ 1 -# define __GCC4_has_attribute___no_caller_saved_registers__ 0 -# define __GCC4_has_attribute___noclone__ 1 -# define __GCC4_has_attribute___no_profile_instrument_function__ 0 -# define __GCC4_has_attribute___nonstring__ 0 -# define __GCC4_has_attribute___no_sanitize_address__ 1 -# define __GCC4_has_attribute___no_sanitize_undefined__ 1 -# define __GCC4_has_attribute___no_sanitize_coverage__ 0 -# define __GCC4_has_attribute___fallthrough__ 0 -# define __GCC4_has_attribute___warning__ 1 -#endif - -/* * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-alias-function-attribute */ #define __alias(symbol) __attribute__((__alias__(#symbol))) @@ -77,7 +54,6 @@ * compiler should see some alignment anyway, when the return value is * massaged by 'flags = ptr & 3; ptr &= ~3;'). * - * Optional: only supported since gcc >= 4.9 * Optional: not supported by icc * * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-assume_005faligned-function-attribute diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 8b32b4bdd590..02c2eb874da6 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -420,6 +420,13 @@ struct dma_buf { * - Dynamic importers should set fences for any access that they can't * disable immediately from their &dma_buf_attach_ops.move_notify * callback. + * + * IMPORTANT: + * + * All drivers must obey the struct dma_resv rules, specifically the + * rules for updating fences, see &dma_resv.fence_excl and + * &dma_resv.fence. If these dependency rules are broken access tracking + * can be lost resulting in use after free issues. */ struct dma_resv *resv; @@ -433,7 +440,7 @@ struct dma_buf { wait_queue_head_t *poll; __poll_t active; - } cb_excl, cb_shared; + } cb_in, cb_out; #ifdef CONFIG_DMABUF_SYSFS_STATS /** * @sysfs_entry: diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index 6ffb4b2c6371..a706b7bf51d7 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -214,19 +214,15 @@ struct dma_fence_ops { * Custom wait implementation, defaults to dma_fence_default_wait() if * not set. * - * The dma_fence_default_wait implementation should work for any fence, as long - * as @enable_signaling works correctly. This hook allows drivers to - * have an optimized version for the case where a process context is - * already available, e.g. if @enable_signaling for the general case - * needs to set up a worker thread. + * Deprecated and should not be used by new implementations. Only used + * by existing implementations which need special handling for their + * hardware reset procedure. * * Must return -ERESTARTSYS if the wait is intr = true and the wait was * interrupted, and remaining jiffies if fence has signaled, or 0 if wait * timed out. Can also return other error values on custom implementations, * which should be treated as if the fence is signaled. For example a hardware * lockup could be reported like that. - * - * This callback is optional. */ signed long (*wait)(struct dma_fence *fence, bool intr, signed long timeout); @@ -590,26 +586,4 @@ struct dma_fence *dma_fence_get_stub(void); struct dma_fence *dma_fence_allocate_private_stub(void); u64 dma_fence_context_alloc(unsigned num); -#define DMA_FENCE_TRACE(f, fmt, args...) \ - do { \ - struct dma_fence *__ff = (f); \ - if (IS_ENABLED(CONFIG_DMA_FENCE_TRACE)) \ - pr_info("f %llu#%llu: " fmt, \ - __ff->context, __ff->seqno, ##args); \ - } while (0) - -#define DMA_FENCE_WARN(f, fmt, args...) \ - do { \ - struct dma_fence *__ff = (f); \ - pr_warn("f %llu#%llu: " fmt, __ff->context, __ff->seqno,\ - ##args); \ - } while (0) - -#define DMA_FENCE_ERR(f, fmt, args...) \ - do { \ - struct dma_fence *__ff = (f); \ - pr_err("f %llu#%llu: " fmt, __ff->context, __ff->seqno, \ - ##args); \ - } while (0) - #endif /* __LINUX_DMA_FENCE_H */ diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index 39fefb86780b..8b6c20636a79 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -62,19 +62,188 @@ struct dma_resv_list { /** * struct dma_resv - a reservation object manages fences for a buffer - * @lock: update side lock - * @seq: sequence count for managing RCU read-side synchronization - * @fence_excl: the exclusive fence, if there is one currently - * @fence: list of current shared fences + * + * There are multiple uses for this, with sometimes slightly different rules in + * how the fence slots are used. + * + * One use is to synchronize cross-driver access to a struct dma_buf, either for + * dynamic buffer management or just to handle implicit synchronization between + * different users of the buffer in userspace. See &dma_buf.resv for a more + * in-depth discussion. + * + * The other major use is to manage access and locking within a driver in a + * buffer based memory manager. struct ttm_buffer_object is the canonical + * example here, since this is where reservation objects originated from. But + * use in drivers is spreading and some drivers also manage struct + * drm_gem_object with the same scheme. */ struct dma_resv { + /** + * @lock: + * + * Update side lock. Don't use directly, instead use the wrapper + * functions like dma_resv_lock() and dma_resv_unlock(). + * + * Drivers which use the reservation object to manage memory dynamically + * also use this lock to protect buffer object state like placement, + * allocation policies or throughout command submission. + */ struct ww_mutex lock; + + /** + * @seq: + * + * Sequence count for managing RCU read-side synchronization, allows + * read-only access to @fence_excl and @fence while ensuring we take a + * consistent snapshot. + */ seqcount_ww_mutex_t seq; + /** + * @fence_excl: + * + * The exclusive fence, if there is one currently. + * + * There are two ways to update this fence: + * + * - First by calling dma_resv_add_excl_fence(), which replaces all + * fences attached to the reservation object. To guarantee that no + * fences are lost, this new fence must signal only after all previous + * fences, both shared and exclusive, have signalled. In some cases it + * is convenient to achieve that by attaching a struct dma_fence_array + * with all the new and old fences. + * + * - Alternatively the fence can be set directly, which leaves the + * shared fences unchanged. To guarantee that no fences are lost, this + * new fence must signal only after the previous exclusive fence has + * signalled. Since the shared fences are staying intact, it is not + * necessary to maintain any ordering against those. If semantically + * only a new access is added without actually treating the previous + * one as a dependency the exclusive fences can be strung together + * using struct dma_fence_chain. + * + * Note that actual semantics of what an exclusive or shared fence mean + * is defined by the user, for reservation objects shared across drivers + * see &dma_buf.resv. + */ struct dma_fence __rcu *fence_excl; + + /** + * @fence: + * + * List of current shared fences. + * + * There are no ordering constraints of shared fences against the + * exclusive fence slot. If a waiter needs to wait for all access, it + * has to wait for both sets of fences to signal. + * + * A new fence is added by calling dma_resv_add_shared_fence(). Since + * this often needs to be done past the point of no return in command + * submission it cannot fail, and therefore sufficient slots need to be + * reserved by calling dma_resv_reserve_shared(). + * + * Note that actual semantics of what an exclusive or shared fence mean + * is defined by the user, for reservation objects shared across drivers + * see &dma_buf.resv. + */ struct dma_resv_list __rcu *fence; }; +/** + * struct dma_resv_iter - current position into the dma_resv fences + * + * Don't touch this directly in the driver, use the accessor function instead. + */ +struct dma_resv_iter { + /** @obj: The dma_resv object we iterate over */ + struct dma_resv *obj; + + /** @all_fences: If all fences should be returned */ + bool all_fences; + + /** @fence: the currently handled fence */ + struct dma_fence *fence; + + /** @seq: sequence number to check for modifications */ + unsigned int seq; + + /** @index: index into the shared fences */ + unsigned int index; + + /** @fences: the shared fences */ + struct dma_resv_list *fences; + + /** @is_restarted: true if this is the first returned fence */ + bool is_restarted; +}; + +struct dma_fence *dma_resv_iter_first_unlocked(struct dma_resv_iter *cursor); +struct dma_fence *dma_resv_iter_next_unlocked(struct dma_resv_iter *cursor); + +/** + * dma_resv_iter_begin - initialize a dma_resv_iter object + * @cursor: The dma_resv_iter object to initialize + * @obj: The dma_resv object which we want to iterate over + * @all_fences: If all fences should be returned or just the exclusive one + */ +static inline void dma_resv_iter_begin(struct dma_resv_iter *cursor, + struct dma_resv *obj, + bool all_fences) +{ + cursor->obj = obj; + cursor->all_fences = all_fences; + cursor->fence = NULL; +} + +/** + * dma_resv_iter_end - cleanup a dma_resv_iter object + * @cursor: the dma_resv_iter object which should be cleaned up + * + * Make sure that the reference to the fence in the cursor is properly + * dropped. + */ +static inline void dma_resv_iter_end(struct dma_resv_iter *cursor) +{ + dma_fence_put(cursor->fence); +} + +/** + * dma_resv_iter_is_exclusive - test if the current fence is the exclusive one + * @cursor: the cursor of the current position + * + * Returns true if the currently returned fence is the exclusive one. + */ +static inline bool dma_resv_iter_is_exclusive(struct dma_resv_iter *cursor) +{ + return cursor->index == 0; +} + +/** + * dma_resv_iter_is_restarted - test if this is the first fence after a restart + * @cursor: the cursor with the current position + * + * Return true if this is the first fence in an iteration after a restart. + */ +static inline bool dma_resv_iter_is_restarted(struct dma_resv_iter *cursor) +{ + return cursor->is_restarted; +} + +/** + * dma_resv_for_each_fence_unlocked - unlocked fence iterator + * @cursor: a struct dma_resv_iter pointer + * @fence: the current fence + * + * Iterate over the fences in a struct dma_resv object without holding the + * &dma_resv.lock and using RCU instead. The cursor needs to be initialized + * with dma_resv_iter_begin() and cleaned up with dma_resv_iter_end(). Inside + * the iterator a reference to the dma_fence is held and the RCU lock dropped. + * When the dma_resv is modified the iteration starts over again. + */ +#define dma_resv_for_each_fence_unlocked(cursor, fence) \ + for (fence = dma_resv_iter_first_unlocked(cursor); \ + fence; fence = dma_resv_iter_next_unlocked(cursor)) + #define dma_resv_held(obj) lockdep_is_held(&(obj)->lock.base) #define dma_resv_assert_held(obj) lockdep_assert_held(&(obj)->lock.base) @@ -98,6 +267,13 @@ static inline void dma_resv_reset_shared_max(struct dma_resv *obj) {} * undefined order, a #ww_acquire_ctx is passed to unwind if a cycle * is detected. See ww_mutex_lock() and ww_acquire_init(). A reservation * object may be locked by itself by passing NULL as @ctx. + * + * When a die situation is indicated by returning -EDEADLK all locks held by + * @ctx must be unlocked and then dma_resv_lock_slow() called on @obj. + * + * Unlocked by calling dma_resv_unlock(). + * + * See also dma_resv_lock_interruptible() for the interruptible variant. */ static inline int dma_resv_lock(struct dma_resv *obj, struct ww_acquire_ctx *ctx) @@ -119,6 +295,12 @@ static inline int dma_resv_lock(struct dma_resv *obj, * undefined order, a #ww_acquire_ctx is passed to unwind if a cycle * is detected. See ww_mutex_lock() and ww_acquire_init(). A reservation * object may be locked by itself by passing NULL as @ctx. + * + * When a die situation is indicated by returning -EDEADLK all locks held by + * @ctx must be unlocked and then dma_resv_lock_slow_interruptible() called on + * @obj. + * + * Unlocked by calling dma_resv_unlock(). */ static inline int dma_resv_lock_interruptible(struct dma_resv *obj, struct ww_acquire_ctx *ctx) @@ -134,6 +316,8 @@ static inline int dma_resv_lock_interruptible(struct dma_resv *obj, * Acquires the reservation object after a die case. This function * will sleep until the lock becomes available. See dma_resv_lock() as * well. + * + * See also dma_resv_lock_slow_interruptible() for the interruptible variant. */ static inline void dma_resv_lock_slow(struct dma_resv *obj, struct ww_acquire_ctx *ctx) @@ -167,7 +351,7 @@ static inline int dma_resv_lock_slow_interruptible(struct dma_resv *obj, * if they overlap with a writer. * * Also note that since no context is provided, no deadlock protection is - * possible. + * possible, which is also not needed for a trylock. * * Returns true if the lock was acquired, false otherwise. */ @@ -193,6 +377,11 @@ static inline bool dma_resv_is_locked(struct dma_resv *obj) * * Returns the context used to lock a reservation object or NULL if no context * was used or the object is not locked at all. + * + * WARNING: This interface is pretty horrible, but TTM needs it because it + * doesn't pass the struct ww_acquire_ctx around in some very long callchains. + * Everyone else just uses it to check whether they're holding a reservation or + * not. */ static inline struct ww_acquire_ctx *dma_resv_locking_ctx(struct dma_resv *obj) { diff --git a/include/linux/io.h b/include/linux/io.h index 9595151d800d..5fc800390fe4 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -132,6 +132,8 @@ static inline int arch_phys_wc_index(int handle) #endif #endif +int devm_arch_phys_wc_add(struct device *dev, unsigned long base, unsigned long size); + enum { /* See memremap() kernel-doc for usage description... */ MEMREMAP_WB = 1 << 0, @@ -166,4 +168,7 @@ static inline void arch_io_free_memtype_wc(resource_size_t base, } #endif +int devm_arch_io_reserve_memtype_wc(struct device *dev, resource_size_t start, + resource_size_t size); + #endif /* _LINUX_IO_H */ diff --git a/include/linux/memblock.h b/include/linux/memblock.h index b066024c62e3..34de69b3b8ba 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -118,6 +118,7 @@ int memblock_mark_nomap(phys_addr_t base, phys_addr_t size); int memblock_clear_nomap(phys_addr_t base, phys_addr_t size); void memblock_free_all(void); +void memblock_free_ptr(void *ptr, size_t size); void reset_node_managed_pages(pg_data_t *pgdat); void reset_all_zones_managed_pages(void); diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index b179f1e3541a..96e113e23d04 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -144,15 +144,6 @@ static inline void mmap_read_unlock(struct mm_struct *mm) up_read(&mm->mmap_lock); } -static inline bool mmap_read_trylock_non_owner(struct mm_struct *mm) -{ - if (mmap_read_trylock(mm)) { - rwsem_release(&mm->mmap_lock.dep_map, _RET_IP_); - return true; - } - return false; -} - static inline void mmap_read_unlock_non_owner(struct mm_struct *mm) { __mmap_lock_trace_released(mm, false); diff --git a/include/linux/overflow.h b/include/linux/overflow.h index 0f12345c21fb..4669632bd72b 100644 --- a/include/linux/overflow.h +++ b/include/linux/overflow.h @@ -6,12 +6,9 @@ #include <linux/limits.h> /* - * In the fallback code below, we need to compute the minimum and - * maximum values representable in a given type. These macros may also - * be useful elsewhere, so we provide them outside the - * COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW block. - * - * It would seem more obvious to do something like + * We need to compute the minimum and maximum values representable in a given + * type. These macros may also be useful elsewhere. It would seem more obvious + * to do something like: * * #define type_min(T) (T)(is_signed_type(T) ? (T)1 << (8*sizeof(T)-1) : 0) * #define type_max(T) (T)(is_signed_type(T) ? ((T)1 << (8*sizeof(T)-1)) - 1 : ~(T)0) @@ -54,7 +51,6 @@ static inline bool __must_check __must_check_overflow(bool overflow) return unlikely(overflow); } -#ifdef COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW /* * For simplicity and code hygiene, the fallback code below insists on * a, b and *d having the same type (similar to the min() and max() @@ -90,134 +86,6 @@ static inline bool __must_check __must_check_overflow(bool overflow) __builtin_mul_overflow(__a, __b, __d); \ })) -#else - - -/* Checking for unsigned overflow is relatively easy without causing UB. */ -#define __unsigned_add_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = __a + __b; \ - *__d < __a; \ -}) -#define __unsigned_sub_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = __a - __b; \ - __a < __b; \ -}) -/* - * If one of a or b is a compile-time constant, this avoids a division. - */ -#define __unsigned_mul_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = __a * __b; \ - __builtin_constant_p(__b) ? \ - __b > 0 && __a > type_max(typeof(__a)) / __b : \ - __a > 0 && __b > type_max(typeof(__b)) / __a; \ -}) - -/* - * For signed types, detecting overflow is much harder, especially if - * we want to avoid UB. But the interface of these macros is such that - * we must provide a result in *d, and in fact we must produce the - * result promised by gcc's builtins, which is simply the possibly - * wrapped-around value. Fortunately, we can just formally do the - * operations in the widest relevant unsigned type (u64) and then - * truncate the result - gcc is smart enough to generate the same code - * with and without the (u64) casts. - */ - -/* - * Adding two signed integers can overflow only if they have the same - * sign, and overflow has happened iff the result has the opposite - * sign. - */ -#define __signed_add_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = (u64)__a + (u64)__b; \ - (((~(__a ^ __b)) & (*__d ^ __a)) \ - & type_min(typeof(__a))) != 0; \ -}) - -/* - * Subtraction is similar, except that overflow can now happen only - * when the signs are opposite. In this case, overflow has happened if - * the result has the opposite sign of a. - */ -#define __signed_sub_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = (u64)__a - (u64)__b; \ - ((((__a ^ __b)) & (*__d ^ __a)) \ - & type_min(typeof(__a))) != 0; \ -}) - -/* - * Signed multiplication is rather hard. gcc always follows C99, so - * division is truncated towards 0. This means that we can write the - * overflow check like this: - * - * (a > 0 && (b > MAX/a || b < MIN/a)) || - * (a < -1 && (b > MIN/a || b < MAX/a) || - * (a == -1 && b == MIN) - * - * The redundant casts of -1 are to silence an annoying -Wtype-limits - * (included in -Wextra) warning: When the type is u8 or u16, the - * __b_c_e in check_mul_overflow obviously selects - * __unsigned_mul_overflow, but unfortunately gcc still parses this - * code and warns about the limited range of __b. - */ - -#define __signed_mul_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - typeof(a) __tmax = type_max(typeof(a)); \ - typeof(a) __tmin = type_min(typeof(a)); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = (u64)__a * (u64)__b; \ - (__b > 0 && (__a > __tmax/__b || __a < __tmin/__b)) || \ - (__b < (typeof(__b))-1 && (__a > __tmin/__b || __a < __tmax/__b)) || \ - (__b == (typeof(__b))-1 && __a == __tmin); \ -}) - - -#define check_add_overflow(a, b, d) __must_check_overflow( \ - __builtin_choose_expr(is_signed_type(typeof(a)), \ - __signed_add_overflow(a, b, d), \ - __unsigned_add_overflow(a, b, d))) - -#define check_sub_overflow(a, b, d) __must_check_overflow( \ - __builtin_choose_expr(is_signed_type(typeof(a)), \ - __signed_sub_overflow(a, b, d), \ - __unsigned_sub_overflow(a, b, d))) - -#define check_mul_overflow(a, b, d) __must_check_overflow( \ - __builtin_choose_expr(is_signed_type(typeof(a)), \ - __signed_mul_overflow(a, b, d), \ - __unsigned_mul_overflow(a, b, d))) - -#endif /* COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW */ - /** check_shl_overflow() - Calculate a left-shifted value and check overflow * * @a: Value to be shifted diff --git a/include/linux/sched.h b/include/linux/sched.h index e12b524426b0..39039ce8ac4c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1471,6 +1471,7 @@ struct task_struct { mce_whole_page : 1, __mce_reserved : 62; struct callback_head mce_kill_me; + int mce_count; #endif #ifdef CONFIG_KRETPROBES diff --git a/include/linux/seqno-fence.h b/include/linux/seqno-fence.h deleted file mode 100644 index 3cca2b8fac43..000000000000 --- a/include/linux/seqno-fence.h +++ /dev/null @@ -1,109 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * seqno-fence, using a dma-buf to synchronize fencing - * - * Copyright (C) 2012 Texas Instruments - * Copyright (C) 2012 Canonical Ltd - * Authors: - * Rob Clark <[email protected]> - * Maarten Lankhorst <[email protected]> - */ - -#ifndef __LINUX_SEQNO_FENCE_H -#define __LINUX_SEQNO_FENCE_H - -#include <linux/dma-fence.h> -#include <linux/dma-buf.h> - -enum seqno_fence_condition { - SEQNO_FENCE_WAIT_GEQUAL, - SEQNO_FENCE_WAIT_NONZERO -}; - -struct seqno_fence { - struct dma_fence base; - - const struct dma_fence_ops *ops; - struct dma_buf *sync_buf; - uint32_t seqno_ofs; - enum seqno_fence_condition condition; -}; - -extern const struct dma_fence_ops seqno_fence_ops; - -/** - * to_seqno_fence - cast a fence to a seqno_fence - * @fence: fence to cast to a seqno_fence - * - * Returns NULL if the fence is not a seqno_fence, - * or the seqno_fence otherwise. - */ -static inline struct seqno_fence * -to_seqno_fence(struct dma_fence *fence) -{ - if (fence->ops != &seqno_fence_ops) - return NULL; - return container_of(fence, struct seqno_fence, base); -} - -/** - * seqno_fence_init - initialize a seqno fence - * @fence: seqno_fence to initialize - * @lock: pointer to spinlock to use for fence - * @sync_buf: buffer containing the memory location to signal on - * @context: the execution context this fence is a part of - * @seqno_ofs: the offset within @sync_buf - * @seqno: the sequence # to signal on - * @cond: fence wait condition - * @ops: the fence_ops for operations on this seqno fence - * - * This function initializes a struct seqno_fence with passed parameters, - * and takes a reference on sync_buf which is released on fence destruction. - * - * A seqno_fence is a dma_fence which can complete in software when - * enable_signaling is called, but it also completes when - * (s32)((sync_buf)[seqno_ofs] - seqno) >= 0 is true - * - * The seqno_fence will take a refcount on the sync_buf until it's - * destroyed, but actual lifetime of sync_buf may be longer if one of the - * callers take a reference to it. - * - * Certain hardware have instructions to insert this type of wait condition - * in the command stream, so no intervention from software would be needed. - * This type of fence can be destroyed before completed, however a reference - * on the sync_buf dma-buf can be taken. It is encouraged to re-use the same - * dma-buf for sync_buf, since mapping or unmapping the sync_buf to the - * device's vm can be expensive. - * - * It is recommended for creators of seqno_fence to call dma_fence_signal() - * before destruction. This will prevent possible issues from wraparound at - * time of issue vs time of check, since users can check dma_fence_is_signaled() - * before submitting instructions for the hardware to wait on the fence. - * However, when ops.enable_signaling is not called, it doesn't have to be - * done as soon as possible, just before there's any real danger of seqno - * wraparound. - */ -static inline void -seqno_fence_init(struct seqno_fence *fence, spinlock_t *lock, - struct dma_buf *sync_buf, uint32_t context, - uint32_t seqno_ofs, uint32_t seqno, - enum seqno_fence_condition cond, - const struct dma_fence_ops *ops) -{ - BUG_ON(!fence || !sync_buf || !ops); - BUG_ON(!ops->wait || !ops->enable_signaling || - !ops->get_driver_name || !ops->get_timeline_name); - - /* - * ops is used in dma_fence_init for get_driver_name, so needs to be - * initialized first - */ - fence->ops = ops; - dma_fence_init(&fence->base, &seqno_fence_ops, lock, context, seqno); - get_dma_buf(sync_buf); - fence->sync_buf = sync_buf; - fence->seqno_ofs = seqno_ofs; - fence->condition = cond; -} - -#endif /* __LINUX_SEQNO_FENCE_H */ diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index 9814fff58a69..76fbf92b04d9 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -93,4 +93,5 @@ extern void register_shrinker_prepared(struct shrinker *shrinker); extern int register_shrinker(struct shrinker *shrinker); extern void unregister_shrinker(struct shrinker *shrinker); extern void free_prealloced_shrinker(struct shrinker *shrinker); +extern void synchronize_shrinkers(void); #endif diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 6bdb0db3e825..841e2f0f5240 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1940,7 +1940,7 @@ static inline void __skb_insert(struct sk_buff *newsk, WRITE_ONCE(newsk->prev, prev); WRITE_ONCE(next->prev, newsk); WRITE_ONCE(prev->next, newsk); - list->qlen++; + WRITE_ONCE(list->qlen, list->qlen + 1); } static inline void __skb_queue_splice(const struct sk_buff_head *list, diff --git a/include/linux/uio.h b/include/linux/uio.h index 5265024e8b90..207101a9c5c3 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -27,6 +27,12 @@ enum iter_type { ITER_DISCARD, }; +struct iov_iter_state { + size_t iov_offset; + size_t count; + unsigned long nr_segs; +}; + struct iov_iter { u8 iter_type; bool data_source; @@ -47,7 +53,6 @@ struct iov_iter { }; loff_t xarray_start; }; - size_t truncated; }; static inline enum iter_type iov_iter_type(const struct iov_iter *i) @@ -55,6 +60,14 @@ static inline enum iter_type iov_iter_type(const struct iov_iter *i) return i->iter_type; } +static inline void iov_iter_save_state(struct iov_iter *iter, + struct iov_iter_state *state) +{ + state->iov_offset = iter->iov_offset; + state->count = iter->count; + state->nr_segs = iter->nr_segs; +} + static inline bool iter_is_iovec(const struct iov_iter *i) { return iov_iter_type(i) == ITER_IOVEC; @@ -233,6 +246,7 @@ ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages, ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages, size_t maxsize, size_t *start); int iov_iter_npages(const struct iov_iter *i, int maxpages); +void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state); const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags); @@ -255,10 +269,8 @@ static inline void iov_iter_truncate(struct iov_iter *i, u64 count) * conversion in assignement is by definition greater than all * values of size_t, including old i->count. */ - if (i->count > count) { - i->truncated += i->count - count; + if (i->count > count) i->count = count; - } } /* @@ -267,7 +279,6 @@ static inline void iov_iter_truncate(struct iov_iter *i, u64 count) */ static inline void iov_iter_reexpand(struct iov_iter *i, size_t count) { - i->truncated -= count - i->count; i->count = count; } diff --git a/include/net/dsa.h b/include/net/dsa.h index f9a17145255a..258867eff230 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -447,6 +447,11 @@ static inline bool dsa_port_is_user(struct dsa_port *dp) return dp->type == DSA_PORT_TYPE_USER; } +static inline bool dsa_port_is_unused(struct dsa_port *dp) +{ + return dp->type == DSA_PORT_TYPE_UNUSED; +} + static inline bool dsa_is_unused_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_UNUSED; diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h index 9f4bb4a6f358..45a914850be0 100644 --- a/include/uapi/drm/drm_fourcc.h +++ b/include/uapi/drm/drm_fourcc.h @@ -373,6 +373,12 @@ extern "C" { #define DRM_FORMAT_RESERVED ((1ULL << 56) - 1) +#define fourcc_mod_get_vendor(modifier) \ + (((modifier) >> 56) & 0xff) + +#define fourcc_mod_is_vendor(modifier, vendor) \ + (fourcc_mod_get_vendor(modifier) == DRM_FORMAT_MOD_VENDOR_## vendor) + #define fourcc_mod_code(vendor, val) \ ((((__u64)DRM_FORMAT_MOD_VENDOR_## vendor) << 56) | ((val) & 0x00ffffffffffffffULL)) diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h index 90c55383f1ee..e1e351682872 100644 --- a/include/uapi/drm/drm_mode.h +++ b/include/uapi/drm/drm_mode.h @@ -1110,6 +1110,10 @@ struct drm_mode_destroy_blob { * struct drm_mode_create_lease - Create lease * * Lease mode resources, creating another drm_master. + * + * The @object_ids array must reference at least one CRTC, one connector and + * one plane if &DRM_CLIENT_CAP_UNIVERSAL_PLANES is enabled. Alternatively, + * the lease can be completely empty. */ struct drm_mode_create_lease { /** @object_ids: Pointer to array of object ids (__u32) */ diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index c2a63e1584cb..914ebd9290e5 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -1522,6 +1522,12 @@ struct drm_i915_gem_caching { #define I915_TILING_NONE 0 #define I915_TILING_X 1 #define I915_TILING_Y 2 +/* + * Do not add new tiling types here. The I915_TILING_* values are for + * de-tiling fence registers that no longer exist on modern platforms. Although + * the hardware may support new types of tiling in general (e.g., Tile4), we + * do not need to add them to the uapi that is specific to now-defunct ioctls. + */ #define I915_TILING_LAST I915_TILING_Y #define I915_BIT_6_SWIZZLE_NONE 0 diff --git a/include/uapi/drm/v3d_drm.h b/include/uapi/drm/v3d_drm.h index 4104f22fb3d3..3dfc0af8756a 100644 --- a/include/uapi/drm/v3d_drm.h +++ b/include/uapi/drm/v3d_drm.h @@ -58,6 +58,67 @@ extern "C" { struct drm_v3d_perfmon_get_values) #define DRM_V3D_SUBMIT_CL_FLUSH_CACHE 0x01 +#define DRM_V3D_SUBMIT_EXTENSION 0x02 + +/* struct drm_v3d_extension - ioctl extensions + * + * Linked-list of generic extensions where the id identify which struct is + * pointed by ext_data. Therefore, DRM_V3D_EXT_ID_* is used on id to identify + * the extension type. + */ +struct drm_v3d_extension { + __u64 next; + __u32 id; +#define DRM_V3D_EXT_ID_MULTI_SYNC 0x01 + __u32 flags; /* mbz */ +}; + +/* struct drm_v3d_sem - wait/signal semaphore + * + * If binary semaphore, it only takes syncobj handle and ignores flags and + * point fields. Point is defined for timeline syncobj feature. + */ +struct drm_v3d_sem { + __u32 handle; /* syncobj */ + /* rsv below, for future uses */ + __u32 flags; + __u64 point; /* for timeline sem support */ + __u64 mbz[2]; /* must be zero, rsv */ +}; + +/* Enum for each of the V3D queues. */ +enum v3d_queue { + V3D_BIN, + V3D_RENDER, + V3D_TFU, + V3D_CSD, + V3D_CACHE_CLEAN, +}; + +/** + * struct drm_v3d_multi_sync - ioctl extension to add support multiples + * syncobjs for commands submission. + * + * When an extension of DRM_V3D_EXT_ID_MULTI_SYNC id is defined, it points to + * this extension to define wait and signal dependencies, instead of single + * in/out sync entries on submitting commands. The field flags is used to + * determine the stage to set wait dependencies. + */ +struct drm_v3d_multi_sync { + struct drm_v3d_extension base; + /* Array of wait and signal semaphores */ + __u64 in_syncs; + __u64 out_syncs; + + /* Number of entries */ + __u32 in_sync_count; + __u32 out_sync_count; + + /* set the stage (v3d_queue) to sync */ + __u32 wait_stage; + + __u32 pad; /* mbz */ +}; /** * struct drm_v3d_submit_cl - ioctl argument for submitting commands to the 3D @@ -135,12 +196,16 @@ struct drm_v3d_submit_cl { /* Number of BO handles passed in (size is that times 4). */ __u32 bo_handle_count; + /* DRM_V3D_SUBMIT_* properties */ __u32 flags; /* ID of the perfmon to attach to this job. 0 means no perfmon. */ __u32 perfmon_id; __u32 pad; + + /* Pointer to an array of ioctl extensions*/ + __u64 extensions; }; /** @@ -210,6 +275,7 @@ enum drm_v3d_param { DRM_V3D_PARAM_SUPPORTS_CSD, DRM_V3D_PARAM_SUPPORTS_CACHE_FLUSH, DRM_V3D_PARAM_SUPPORTS_PERFMON, + DRM_V3D_PARAM_SUPPORTS_MULTISYNC_EXT, }; struct drm_v3d_get_param { @@ -248,6 +314,11 @@ struct drm_v3d_submit_tfu { __u32 in_sync; /* Sync object to signal when the TFU job is done. */ __u32 out_sync; + + __u32 flags; + + /* Pointer to an array of ioctl extensions*/ + __u64 extensions; }; /* Submits a compute shader for dispatch. This job will block on any @@ -276,6 +347,13 @@ struct drm_v3d_submit_csd { /* ID of the perfmon to attach to this job. 0 means no perfmon. */ __u32 perfmon_id; + + /* Pointer to an array of ioctl extensions*/ + __u64 extensions; + + __u32 flags; + + __u32 pad; }; enum { diff --git a/include/uapi/drm/virtgpu_drm.h b/include/uapi/drm/virtgpu_drm.h index b9ec26e9c646..a13e20cc66b4 100644 --- a/include/uapi/drm/virtgpu_drm.h +++ b/include/uapi/drm/virtgpu_drm.h @@ -47,12 +47,15 @@ extern "C" { #define DRM_VIRTGPU_WAIT 0x08 #define DRM_VIRTGPU_GET_CAPS 0x09 #define DRM_VIRTGPU_RESOURCE_CREATE_BLOB 0x0a +#define DRM_VIRTGPU_CONTEXT_INIT 0x0b #define VIRTGPU_EXECBUF_FENCE_FD_IN 0x01 #define VIRTGPU_EXECBUF_FENCE_FD_OUT 0x02 +#define VIRTGPU_EXECBUF_RING_IDX 0x04 #define VIRTGPU_EXECBUF_FLAGS (\ VIRTGPU_EXECBUF_FENCE_FD_IN |\ VIRTGPU_EXECBUF_FENCE_FD_OUT |\ + VIRTGPU_EXECBUF_RING_IDX |\ 0) struct drm_virtgpu_map { @@ -68,6 +71,8 @@ struct drm_virtgpu_execbuffer { __u64 bo_handles; __u32 num_bo_handles; __s32 fence_fd; /* in/out fence fd (see VIRTGPU_EXECBUF_FENCE_FD_IN/OUT) */ + __u32 ring_idx; /* command ring index (see VIRTGPU_EXECBUF_RING_IDX) */ + __u32 pad; }; #define VIRTGPU_PARAM_3D_FEATURES 1 /* do we have 3D features in the hw */ @@ -75,6 +80,8 @@ struct drm_virtgpu_execbuffer { #define VIRTGPU_PARAM_RESOURCE_BLOB 3 /* DRM_VIRTGPU_RESOURCE_CREATE_BLOB */ #define VIRTGPU_PARAM_HOST_VISIBLE 4 /* Host blob resources are mappable */ #define VIRTGPU_PARAM_CROSS_DEVICE 5 /* Cross virtio-device resource sharing */ +#define VIRTGPU_PARAM_CONTEXT_INIT 6 /* DRM_VIRTGPU_CONTEXT_INIT */ +#define VIRTGPU_PARAM_SUPPORTED_CAPSET_IDs 7 /* Bitmask of supported capability set ids */ struct drm_virtgpu_getparam { __u64 param; @@ -173,6 +180,22 @@ struct drm_virtgpu_resource_create_blob { __u64 blob_id; }; +#define VIRTGPU_CONTEXT_PARAM_CAPSET_ID 0x0001 +#define VIRTGPU_CONTEXT_PARAM_NUM_RINGS 0x0002 +#define VIRTGPU_CONTEXT_PARAM_POLL_RINGS_MASK 0x0003 +struct drm_virtgpu_context_set_param { + __u64 param; + __u64 value; +}; + +struct drm_virtgpu_context_init { + __u32 num_params; + __u32 pad; + + /* pointer to drm_virtgpu_context_set_param array */ + __u64 ctx_set_params; +}; + #define DRM_IOCTL_VIRTGPU_MAP \ DRM_IOWR(DRM_COMMAND_BASE + DRM_VIRTGPU_MAP, struct drm_virtgpu_map) @@ -212,6 +235,10 @@ struct drm_virtgpu_resource_create_blob { DRM_IOWR(DRM_COMMAND_BASE + DRM_VIRTGPU_RESOURCE_CREATE_BLOB, \ struct drm_virtgpu_resource_create_blob) +#define DRM_IOCTL_VIRTGPU_CONTEXT_INIT \ + DRM_IOWR(DRM_COMMAND_BASE + DRM_VIRTGPU_CONTEXT_INIT, \ + struct drm_virtgpu_context_init) + #if defined(__cplusplus) } #endif diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 59ef35154e3d..b270a07b285e 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -317,13 +317,19 @@ enum { IORING_REGISTER_IOWQ_AFF = 17, IORING_UNREGISTER_IOWQ_AFF = 18, - /* set/get max number of workers */ + /* set/get max number of io-wq workers */ IORING_REGISTER_IOWQ_MAX_WORKERS = 19, /* this goes last */ IORING_REGISTER_LAST }; +/* io-wq worker categories */ +enum { + IO_WQ_BOUND, + IO_WQ_UNBOUND, +}; + /* deprecated, see struct io_uring_rsrc_update */ struct io_uring_files_update { __u32 offset; diff --git a/include/uapi/linux/virtio_gpu.h b/include/uapi/linux/virtio_gpu.h index 97523a95781d..f556fde07b76 100644 --- a/include/uapi/linux/virtio_gpu.h +++ b/include/uapi/linux/virtio_gpu.h @@ -59,6 +59,11 @@ * VIRTIO_GPU_CMD_RESOURCE_CREATE_BLOB */ #define VIRTIO_GPU_F_RESOURCE_BLOB 3 +/* + * VIRTIO_GPU_CMD_CREATE_CONTEXT with + * context_init and multiple timelines + */ +#define VIRTIO_GPU_F_CONTEXT_INIT 4 enum virtio_gpu_ctrl_type { VIRTIO_GPU_UNDEFINED = 0, @@ -122,14 +127,20 @@ enum virtio_gpu_shm_id { VIRTIO_GPU_SHM_ID_HOST_VISIBLE = 1 }; -#define VIRTIO_GPU_FLAG_FENCE (1 << 0) +#define VIRTIO_GPU_FLAG_FENCE (1 << 0) +/* + * If the following flag is set, then ring_idx contains the index + * of the command ring that needs to used when creating the fence + */ +#define VIRTIO_GPU_FLAG_INFO_RING_IDX (1 << 1) struct virtio_gpu_ctrl_hdr { __le32 type; __le32 flags; __le64 fence_id; __le32 ctx_id; - __le32 padding; + __u8 ring_idx; + __u8 padding[3]; }; /* data passed in the cursor vq */ @@ -269,10 +280,11 @@ struct virtio_gpu_resource_create_3d { }; /* VIRTIO_GPU_CMD_CTX_CREATE */ +#define VIRTIO_GPU_CONTEXT_INIT_CAPSET_ID_MASK 0x000000ff struct virtio_gpu_ctx_create { struct virtio_gpu_ctrl_hdr hdr; __le32 nlen; - __le32 padding; + __le32 context_init; char debug_name[64]; }; |