diff options
Diffstat (limited to 'include/linux')
178 files changed, 3328 insertions, 2132 deletions
diff --git a/include/linux/acpi_amd_wbrf.h b/include/linux/acpi_amd_wbrf.h new file mode 100644 index 000000000000..898f31d536d4 --- /dev/null +++ b/include/linux/acpi_amd_wbrf.h @@ -0,0 +1,91 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Wifi Band Exclusion Interface (AMD ACPI Implementation) + * Copyright (C) 2023 Advanced Micro Devices + */ + +#ifndef _ACPI_AMD_WBRF_H +#define _ACPI_AMD_WBRF_H + +#include <linux/device.h> +#include <linux/notifier.h> + +/* The maximum number of frequency band ranges */ +#define MAX_NUM_OF_WBRF_RANGES 11 + +/* Record actions */ +#define WBRF_RECORD_ADD 0x0 +#define WBRF_RECORD_REMOVE 0x1 + +/** + * struct freq_band_range - Wifi frequency band range definition + * @start: start frequency point (in Hz) + * @end: end frequency point (in Hz) + */ +struct freq_band_range { + u64 start; + u64 end; +}; + +/** + * struct wbrf_ranges_in_out - wbrf ranges info + * @num_of_ranges: total number of band ranges in this struct + * @band_list: array of Wifi band ranges + */ +struct wbrf_ranges_in_out { + u64 num_of_ranges; + struct freq_band_range band_list[MAX_NUM_OF_WBRF_RANGES]; +}; + +/** + * enum wbrf_notifier_actions - wbrf notifier actions index + * @WBRF_CHANGED: there was some frequency band updates. The consumers + * should retrieve the latest active frequency bands. + */ +enum wbrf_notifier_actions { + WBRF_CHANGED, +}; + +#if IS_ENABLED(CONFIG_AMD_WBRF) +bool acpi_amd_wbrf_supported_producer(struct device *dev); +int acpi_amd_wbrf_add_remove(struct device *dev, uint8_t action, struct wbrf_ranges_in_out *in); +bool acpi_amd_wbrf_supported_consumer(struct device *dev); +int amd_wbrf_retrieve_freq_band(struct device *dev, struct wbrf_ranges_in_out *out); +int amd_wbrf_register_notifier(struct notifier_block *nb); +int amd_wbrf_unregister_notifier(struct notifier_block *nb); +#else +static inline +bool acpi_amd_wbrf_supported_consumer(struct device *dev) +{ + return false; +} + +static inline +int acpi_amd_wbrf_add_remove(struct device *dev, uint8_t action, struct wbrf_ranges_in_out *in) +{ + return -ENODEV; +} + +static inline +bool acpi_amd_wbrf_supported_producer(struct device *dev) +{ + return false; +} +static inline +int amd_wbrf_retrieve_freq_band(struct device *dev, struct wbrf_ranges_in_out *out) +{ + return -ENODEV; +} +static inline +int amd_wbrf_register_notifier(struct notifier_block *nb) +{ + return -ENODEV; +} +static inline +int amd_wbrf_unregister_notifier(struct notifier_block *nb) +{ + return -ENODEV; +} +#endif /* CONFIG_AMD_WBRF */ + +#endif /* _ACPI_AMD_WBRF_H */ diff --git a/include/linux/amba/clcd-regs.h b/include/linux/amba/clcd-regs.h deleted file mode 100644 index 421b0fa90d6a..000000000000 --- a/include/linux/amba/clcd-regs.h +++ /dev/null @@ -1,87 +0,0 @@ -/* - * David A Rusling - * - * Copyright (C) 2001 ARM Limited - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file COPYING in the main directory of this archive - * for more details. - */ - -#ifndef AMBA_CLCD_REGS_H -#define AMBA_CLCD_REGS_H - -/* - * CLCD Controller Internal Register addresses - */ -#define CLCD_TIM0 0x00000000 -#define CLCD_TIM1 0x00000004 -#define CLCD_TIM2 0x00000008 -#define CLCD_TIM3 0x0000000c -#define CLCD_UBAS 0x00000010 -#define CLCD_LBAS 0x00000014 - -#define CLCD_PL110_IENB 0x00000018 -#define CLCD_PL110_CNTL 0x0000001c -#define CLCD_PL110_STAT 0x00000020 -#define CLCD_PL110_INTR 0x00000024 -#define CLCD_PL110_UCUR 0x00000028 -#define CLCD_PL110_LCUR 0x0000002C - -#define CLCD_PL111_CNTL 0x00000018 -#define CLCD_PL111_IENB 0x0000001c -#define CLCD_PL111_RIS 0x00000020 -#define CLCD_PL111_MIS 0x00000024 -#define CLCD_PL111_ICR 0x00000028 -#define CLCD_PL111_UCUR 0x0000002c -#define CLCD_PL111_LCUR 0x00000030 - -#define CLCD_PALL 0x00000200 -#define CLCD_PALETTE 0x00000200 - -#define TIM2_PCD_LO_MASK GENMASK(4, 0) -#define TIM2_PCD_LO_BITS 5 -#define TIM2_CLKSEL (1 << 5) -#define TIM2_ACB_MASK GENMASK(10, 6) -#define TIM2_IVS (1 << 11) -#define TIM2_IHS (1 << 12) -#define TIM2_IPC (1 << 13) -#define TIM2_IOE (1 << 14) -#define TIM2_BCD (1 << 26) -#define TIM2_PCD_HI_MASK GENMASK(31, 27) -#define TIM2_PCD_HI_BITS 5 -#define TIM2_PCD_HI_SHIFT 27 - -#define CNTL_LCDEN (1 << 0) -#define CNTL_LCDBPP1 (0 << 1) -#define CNTL_LCDBPP2 (1 << 1) -#define CNTL_LCDBPP4 (2 << 1) -#define CNTL_LCDBPP8 (3 << 1) -#define CNTL_LCDBPP16 (4 << 1) -#define CNTL_LCDBPP16_565 (6 << 1) -#define CNTL_LCDBPP16_444 (7 << 1) -#define CNTL_LCDBPP24 (5 << 1) -#define CNTL_LCDBW (1 << 4) -#define CNTL_LCDTFT (1 << 5) -#define CNTL_LCDMONO8 (1 << 6) -#define CNTL_LCDDUAL (1 << 7) -#define CNTL_BGR (1 << 8) -#define CNTL_BEBO (1 << 9) -#define CNTL_BEPO (1 << 10) -#define CNTL_LCDPWR (1 << 11) -#define CNTL_LCDVCOMP(x) ((x) << 12) -#define CNTL_LDMAFIFOTIME (1 << 15) -#define CNTL_WATERMARK (1 << 16) - -/* ST Microelectronics variant bits */ -#define CNTL_ST_1XBPP_444 0x0 -#define CNTL_ST_1XBPP_5551 (1 << 17) -#define CNTL_ST_1XBPP_565 (1 << 18) -#define CNTL_ST_CDWID_12 0x0 -#define CNTL_ST_CDWID_16 (1 << 19) -#define CNTL_ST_CDWID_18 (1 << 20) -#define CNTL_ST_CDWID_24 ((1 << 19)|(1 << 20)) -#define CNTL_ST_CEAEN (1 << 21) -#define CNTL_ST_LCDBPP24_PACKED (6 << 1) - -#endif /* AMBA_CLCD_REGS_H */ diff --git a/include/linux/amba/clcd.h b/include/linux/amba/clcd.h deleted file mode 100644 index b6e0cbeaf533..000000000000 --- a/include/linux/amba/clcd.h +++ /dev/null @@ -1,290 +0,0 @@ -/* - * linux/include/asm-arm/hardware/amba_clcd.h -- Integrator LCD panel. - * - * David A Rusling - * - * Copyright (C) 2001 ARM Limited - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file COPYING in the main directory of this archive - * for more details. - */ -#include <linux/fb.h> -#include <linux/amba/clcd-regs.h> - -enum { - /* individual formats */ - CLCD_CAP_RGB444 = (1 << 0), - CLCD_CAP_RGB5551 = (1 << 1), - CLCD_CAP_RGB565 = (1 << 2), - CLCD_CAP_RGB888 = (1 << 3), - CLCD_CAP_BGR444 = (1 << 4), - CLCD_CAP_BGR5551 = (1 << 5), - CLCD_CAP_BGR565 = (1 << 6), - CLCD_CAP_BGR888 = (1 << 7), - - /* connection layouts */ - CLCD_CAP_444 = CLCD_CAP_RGB444 | CLCD_CAP_BGR444, - CLCD_CAP_5551 = CLCD_CAP_RGB5551 | CLCD_CAP_BGR5551, - CLCD_CAP_565 = CLCD_CAP_RGB565 | CLCD_CAP_BGR565, - CLCD_CAP_888 = CLCD_CAP_RGB888 | CLCD_CAP_BGR888, - - /* red/blue ordering */ - CLCD_CAP_RGB = CLCD_CAP_RGB444 | CLCD_CAP_RGB5551 | - CLCD_CAP_RGB565 | CLCD_CAP_RGB888, - CLCD_CAP_BGR = CLCD_CAP_BGR444 | CLCD_CAP_BGR5551 | - CLCD_CAP_BGR565 | CLCD_CAP_BGR888, - - CLCD_CAP_ALL = CLCD_CAP_BGR | CLCD_CAP_RGB, -}; - -struct backlight_device; - -struct clcd_panel { - struct fb_videomode mode; - signed short width; /* width in mm */ - signed short height; /* height in mm */ - u32 tim2; - u32 tim3; - u32 cntl; - u32 caps; - unsigned int bpp:8, - fixedtimings:1, - grayscale:1; - unsigned int connector; - struct backlight_device *backlight; - /* - * If the B/R lines are switched between the CLCD - * and the panel we need to know this and not try to - * compensate with the BGR bit in the control register. - */ - bool bgr_connection; -}; - -struct clcd_regs { - u32 tim0; - u32 tim1; - u32 tim2; - u32 tim3; - u32 cntl; - unsigned long pixclock; -}; - -struct clcd_fb; - -/* - * the board-type specific routines - */ -struct clcd_board { - const char *name; - - /* - * Optional. Hardware capability flags. - */ - u32 caps; - - /* - * Optional. Check whether the var structure is acceptable - * for this display. - */ - int (*check)(struct clcd_fb *fb, struct fb_var_screeninfo *var); - - /* - * Compulsory. Decode fb->fb.var into regs->*. In the case of - * fixed timing, set regs->* to the register values required. - */ - void (*decode)(struct clcd_fb *fb, struct clcd_regs *regs); - - /* - * Optional. Disable any extra display hardware. - */ - void (*disable)(struct clcd_fb *); - - /* - * Optional. Enable any extra display hardware. - */ - void (*enable)(struct clcd_fb *); - - /* - * Setup platform specific parts of CLCD driver - */ - int (*setup)(struct clcd_fb *); - - /* - * mmap the framebuffer memory - */ - int (*mmap)(struct clcd_fb *, struct vm_area_struct *); - - /* - * Remove platform specific parts of CLCD driver - */ - void (*remove)(struct clcd_fb *); -}; - -struct amba_device; -struct clk; - -/* this data structure describes each frame buffer device we find */ -struct clcd_fb { - struct fb_info fb; - struct amba_device *dev; - struct clk *clk; - struct clcd_panel *panel; - struct clcd_board *board; - void *board_data; - void __iomem *regs; - u16 off_ienb; - u16 off_cntl; - u32 clcd_cntl; - u32 cmap[16]; - bool clk_enabled; -}; - -static inline void clcdfb_decode(struct clcd_fb *fb, struct clcd_regs *regs) -{ - struct fb_var_screeninfo *var = &fb->fb.var; - u32 val, cpl; - - /* - * Program the CLCD controller registers and start the CLCD - */ - val = ((var->xres / 16) - 1) << 2; - val |= (var->hsync_len - 1) << 8; - val |= (var->right_margin - 1) << 16; - val |= (var->left_margin - 1) << 24; - regs->tim0 = val; - - val = var->yres; - if (fb->panel->cntl & CNTL_LCDDUAL) - val /= 2; - val -= 1; - val |= (var->vsync_len - 1) << 10; - val |= var->lower_margin << 16; - val |= var->upper_margin << 24; - regs->tim1 = val; - - val = fb->panel->tim2; - val |= var->sync & FB_SYNC_HOR_HIGH_ACT ? 0 : TIM2_IHS; - val |= var->sync & FB_SYNC_VERT_HIGH_ACT ? 0 : TIM2_IVS; - - cpl = var->xres_virtual; - if (fb->panel->cntl & CNTL_LCDTFT) /* TFT */ - /* / 1 */; - else if (!var->grayscale) /* STN color */ - cpl = cpl * 8 / 3; - else if (fb->panel->cntl & CNTL_LCDMONO8) /* STN monochrome, 8bit */ - cpl /= 8; - else /* STN monochrome, 4bit */ - cpl /= 4; - - regs->tim2 = val | ((cpl - 1) << 16); - - regs->tim3 = fb->panel->tim3; - - val = fb->panel->cntl; - if (var->grayscale) - val |= CNTL_LCDBW; - - if (fb->panel->caps && fb->board->caps && var->bits_per_pixel >= 16) { - /* - * if board and panel supply capabilities, we can support - * changing BGR/RGB depending on supplied parameters. Here - * we switch to what the framebuffer is providing if need - * be, so if the framebuffer is BGR but the display connection - * is RGB (first case) we switch it around. Vice versa mutatis - * mutandis if the framebuffer is RGB but the display connection - * is BGR, we flip it around. - */ - if (var->red.offset == 0) - val &= ~CNTL_BGR; - else - val |= CNTL_BGR; - if (fb->panel->bgr_connection) - val ^= CNTL_BGR; - } - - switch (var->bits_per_pixel) { - case 1: - val |= CNTL_LCDBPP1; - break; - case 2: - val |= CNTL_LCDBPP2; - break; - case 4: - val |= CNTL_LCDBPP4; - break; - case 8: - val |= CNTL_LCDBPP8; - break; - case 16: - /* - * PL110 cannot choose between 5551 and 565 modes in its - * control register. It is possible to use 565 with - * custom external wiring. - */ - if (amba_part(fb->dev) == 0x110 || - var->green.length == 5) - val |= CNTL_LCDBPP16; - else if (var->green.length == 6) - val |= CNTL_LCDBPP16_565; - else - val |= CNTL_LCDBPP16_444; - break; - case 32: - val |= CNTL_LCDBPP24; - break; - } - - regs->cntl = val; - regs->pixclock = var->pixclock; -} - -static inline int clcdfb_check(struct clcd_fb *fb, struct fb_var_screeninfo *var) -{ - var->xres_virtual = var->xres = (var->xres + 15) & ~15; - var->yres_virtual = var->yres = (var->yres + 1) & ~1; - -#define CHECK(e,l,h) (var->e < l || var->e > h) - if (CHECK(right_margin, (5+1), 256) || /* back porch */ - CHECK(left_margin, (5+1), 256) || /* front porch */ - CHECK(hsync_len, (5+1), 256) || - var->xres > 4096 || - var->lower_margin > 255 || /* back porch */ - var->upper_margin > 255 || /* front porch */ - var->vsync_len > 32 || - var->yres > 1024) - return -EINVAL; -#undef CHECK - - /* single panel mode: PCD = max(PCD, 1) */ - /* dual panel mode: PCD = max(PCD, 5) */ - - /* - * You can't change the grayscale setting, and - * we can only do non-interlaced video. - */ - if (var->grayscale != fb->fb.var.grayscale || - (var->vmode & FB_VMODE_MASK) != FB_VMODE_NONINTERLACED) - return -EINVAL; - -#define CHECK(e) (var->e != fb->fb.var.e) - if (fb->panel->fixedtimings && - (CHECK(xres) || - CHECK(yres) || - CHECK(bits_per_pixel) || - CHECK(pixclock) || - CHECK(left_margin) || - CHECK(right_margin) || - CHECK(upper_margin) || - CHECK(lower_margin) || - CHECK(hsync_len) || - CHECK(vsync_len) || - CHECK(sync))) - return -EINVAL; -#undef CHECK - - var->nonstd = 0; - var->accel_flags = 0; - - return 0; -} diff --git a/include/linux/amd-pmf-io.h b/include/linux/amd-pmf-io.h new file mode 100644 index 000000000000..b4f818205216 --- /dev/null +++ b/include/linux/amd-pmf-io.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * AMD Platform Management Framework Interface + * + * Copyright (c) 2023, Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Authors: Shyam Sundar S K <Shyam-sundar.S-k@amd.com> + * Basavaraj Natikar <Basavaraj.Natikar@amd.com> + */ + +#ifndef AMD_PMF_IO_H +#define AMD_PMF_IO_H + +#include <linux/types.h> + +/** + * enum sfh_message_type - Query the SFH message type + * @MT_HPD: Message ID to know the Human presence info from MP2 FW + * @MT_ALS: Message ID to know the Ambient light info from MP2 FW + */ +enum sfh_message_type { + MT_HPD, + MT_ALS, +}; + +/** + * enum sfh_hpd_info - Query the Human presence information + * @SFH_NOT_DETECTED: Check the HPD connection information from MP2 FW + * @SFH_USER_PRESENT: Check if the user is present from HPD sensor + * @SFH_USER_AWAY: Check if the user is away from HPD sensor + */ +enum sfh_hpd_info { + SFH_NOT_DETECTED, + SFH_USER_PRESENT, + SFH_USER_AWAY, +}; + +/** + * struct amd_sfh_info - get HPD sensor info from MP2 FW + * @ambient_light: Populates the ambient light information + * @user_present: Populates the user presence information + */ +struct amd_sfh_info { + u32 ambient_light; + u8 user_present; +}; + +int amd_get_sfh_info(struct amd_sfh_info *sfh_info, enum sfh_message_type op); +#endif diff --git a/include/linux/anon_inodes.h b/include/linux/anon_inodes.h index 5deaddbd7927..93a5f16d03f3 100644 --- a/include/linux/anon_inodes.h +++ b/include/linux/anon_inodes.h @@ -15,13 +15,13 @@ struct inode; struct file *anon_inode_getfile(const char *name, const struct file_operations *fops, void *priv, int flags); -struct file *anon_inode_getfile_secure(const char *name, +struct file *anon_inode_create_getfile(const char *name, const struct file_operations *fops, void *priv, int flags, const struct inode *context_inode); int anon_inode_getfd(const char *name, const struct file_operations *fops, void *priv, int flags); -int anon_inode_getfd_secure(const char *name, +int anon_inode_create_getfd(const char *name, const struct file_operations *fops, void *priv, int flags, const struct inode *context_inode); diff --git a/include/linux/apple-mailbox.h b/include/linux/apple-mailbox.h deleted file mode 100644 index 720fbb70294a..000000000000 --- a/include/linux/apple-mailbox.h +++ /dev/null @@ -1,19 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only OR MIT */ -/* - * Apple mailbox message format - * - * Copyright (C) 2021 The Asahi Linux Contributors - */ - -#ifndef _LINUX_APPLE_MAILBOX_H_ -#define _LINUX_APPLE_MAILBOX_H_ - -#include <linux/types.h> - -/* encodes a single 96bit message sent over the single channel */ -struct apple_mbox_msg { - u64 msg0; - u32 msg1; -}; - -#endif diff --git a/include/linux/audit.h b/include/linux/audit.h index 51b1b7054a23..0050ef288ab3 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -36,6 +36,7 @@ struct mqstat; struct audit_watch; struct audit_tree; struct sk_buff; +struct kern_ipc_perm; struct audit_krule { u32 pflags; diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index 6b3acf15be5c..8e177b67e82f 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -5,6 +5,7 @@ #define _VIRTCHNL_H_ #include <linux/bitops.h> +#include <linux/bits.h> #include <linux/overflow.h> #include <uapi/linux/if_ether.h> @@ -118,6 +119,7 @@ enum virtchnl_ops { VIRTCHNL_OP_GET_STATS = 15, VIRTCHNL_OP_RSVD = 16, VIRTCHNL_OP_EVENT = 17, /* must ALWAYS be 17 */ + VIRTCHNL_OP_CONFIG_RSS_HFUNC = 18, /* opcode 19 is reserved */ VIRTCHNL_OP_IWARP = 20, /* advanced opcode */ VIRTCHNL_OP_RDMA = VIRTCHNL_OP_IWARP, @@ -911,6 +913,29 @@ struct virtchnl_rss_hena { VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_rss_hena); +/* Type of RSS algorithm */ +enum virtchnl_rss_algorithm { + VIRTCHNL_RSS_ALG_TOEPLITZ_ASYMMETRIC = 0, + VIRTCHNL_RSS_ALG_R_ASYMMETRIC = 1, + VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC = 2, + VIRTCHNL_RSS_ALG_XOR_SYMMETRIC = 3, +}; + +/* VIRTCHNL_OP_CONFIG_RSS_HFUNC + * VF sends this message to configure the RSS hash function. Only supported + * if both PF and VF drivers set the VIRTCHNL_VF_OFFLOAD_RSS_PF bit during + * configuration negotiation. + * The hash function is initialized to VIRTCHNL_RSS_ALG_TOEPLITZ_ASYMMETRIC + * by the PF. + */ +struct virtchnl_rss_hfunc { + u16 vsi_id; + u16 rss_algorithm; /* enum virtchnl_rss_algorithm */ + u32 reserved; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_rss_hfunc); + /* VIRTCHNL_OP_ENABLE_CHANNELS * VIRTCHNL_OP_DISABLE_CHANNELS * VF sends these messages to enable or disable channels based on @@ -1095,14 +1120,6 @@ enum virtchnl_vfr_states { VIRTCHNL_VFR_VFACTIVE, }; -/* Type of RSS algorithm */ -enum virtchnl_rss_algorithm { - VIRTCHNL_RSS_ALG_TOEPLITZ_ASYMMETRIC = 0, - VIRTCHNL_RSS_ALG_R_ASYMMETRIC = 1, - VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC = 2, - VIRTCHNL_RSS_ALG_XOR_SYMMETRIC = 3, -}; - #define VIRTCHNL_MAX_NUM_PROTO_HDRS 32 #define PROTO_HDR_SHIFT 5 #define PROTO_HDR_FIELD_START(proto_hdr_type) ((proto_hdr_type) << PROTO_HDR_SHIFT) @@ -1542,6 +1559,9 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode, vrl->lut_entries); } break; + case VIRTCHNL_OP_CONFIG_RSS_HFUNC: + valid_len = sizeof(struct virtchnl_rss_hfunc); + break; case VIRTCHNL_OP_GET_RSS_HENA_CAPS: break; case VIRTCHNL_OP_SET_RSS_HENA: diff --git a/include/linux/bio.h b/include/linux/bio.h index 41d417ee1349..ec4db73e5f4e 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -324,6 +324,8 @@ enum bip_flags { BIP_CTRL_NOCHECK = 1 << 2, /* disable HBA integrity checking */ BIP_DISK_NOCHECK = 1 << 3, /* disable disk integrity checking */ BIP_IP_CHECKSUM = 1 << 4, /* IP checksum */ + BIP_INTEGRITY_USER = 1 << 5, /* Integrity payload is user address */ + BIP_COPY_USER = 1 << 6, /* Kernel bounce buffer in use */ }; /* @@ -718,6 +720,7 @@ static inline bool bioset_initialized(struct bio_set *bs) for_each_bio(_bio) \ bip_for_each_vec(_bvl, _bio->bi_integrity, _iter) +int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t len, u32 seed); extern struct bio_integrity_payload *bio_integrity_alloc(struct bio *, gfp_t, unsigned int); extern int bio_integrity_add_page(struct bio *, struct page *, unsigned int, unsigned int); extern bool bio_integrity_prep(struct bio *); @@ -789,6 +792,12 @@ static inline int bio_integrity_add_page(struct bio *bio, struct page *page, return 0; } +static inline int bio_integrity_map_user(struct bio *bio, void __user *ubuf, + ssize_t len, u32 seed) +{ + return -EINVAL; +} + #endif /* CONFIG_BLK_DEV_INTEGRITY */ /* diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 1ab3081c82ed..a676e116085f 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -830,6 +830,12 @@ void blk_mq_end_request_batch(struct io_comp_batch *ib); */ static inline bool blk_mq_need_time_stamp(struct request *rq) { + /* + * passthrough io doesn't use iostat accounting, cgroup stats + * and io scheduler functionalities. + */ + if (blk_rq_is_passthrough(rq)) + return false; return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS | RQF_USE_SCHED)); } diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 7c2316c91cbd..f288c94374b3 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -378,6 +378,8 @@ enum req_op { REQ_OP_DISCARD = (__force blk_opf_t)3, /* securely erase sectors */ REQ_OP_SECURE_ERASE = (__force blk_opf_t)5, + /* write data at the current zone write pointer */ + REQ_OP_ZONE_APPEND = (__force blk_opf_t)7, /* write the zero filled sector many times */ REQ_OP_WRITE_ZEROES = (__force blk_opf_t)9, /* Open a zone */ @@ -386,12 +388,10 @@ enum req_op { REQ_OP_ZONE_CLOSE = (__force blk_opf_t)11, /* Transition a zone to full */ REQ_OP_ZONE_FINISH = (__force blk_opf_t)12, - /* write data at the current zone write pointer */ - REQ_OP_ZONE_APPEND = (__force blk_opf_t)13, /* reset a zone write pointer */ - REQ_OP_ZONE_RESET = (__force blk_opf_t)15, + REQ_OP_ZONE_RESET = (__force blk_opf_t)13, /* reset all the zone present on the device */ - REQ_OP_ZONE_RESET_ALL = (__force blk_opf_t)17, + REQ_OP_ZONE_RESET_ALL = (__force blk_opf_t)15, /* Driver private requests */ REQ_OP_DRV_IN = (__force blk_opf_t)34, diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c30a98e08423..99e4f5e72213 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -266,18 +266,6 @@ static inline bool blk_op_is_passthrough(blk_opf_t op) } /* - * Zoned block device models (zoned limit). - * - * Note: This needs to be ordered from the least to the most severe - * restrictions for the inheritance in blk_stack_limits() to work. - */ -enum blk_zoned_model { - BLK_ZONED_NONE = 0, /* Regular block device */ - BLK_ZONED_HA, /* Host-aware zoned block device */ - BLK_ZONED_HM, /* Host-managed zoned block device */ -}; - -/* * BLK_BOUNCE_NONE: never bounce (default) * BLK_BOUNCE_HIGH: bounce all highmem pages */ @@ -318,7 +306,7 @@ struct queue_limits { unsigned char misaligned; unsigned char discard_misaligned; unsigned char raid_partial_stripes_expensive; - enum blk_zoned_model zoned; + bool zoned; /* * Drivers that set dma_alignment to less than 511 must be prepared to @@ -331,24 +319,15 @@ struct queue_limits { typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx, void *data); -void disk_set_zoned(struct gendisk *disk, enum blk_zoned_model model); +void disk_set_zoned(struct gendisk *disk); -#ifdef CONFIG_BLK_DEV_ZONED #define BLK_ALL_ZONES ((unsigned int)-1) int blkdev_report_zones(struct block_device *bdev, sector_t sector, - unsigned int nr_zones, report_zones_cb cb, void *data); -unsigned int bdev_nr_zones(struct block_device *bdev); -extern int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op, - sector_t sectors, sector_t nr_sectors, - gfp_t gfp_mask); + unsigned int nr_zones, report_zones_cb cb, void *data); +int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op, + sector_t sectors, sector_t nr_sectors, gfp_t gfp_mask); int blk_revalidate_disk_zones(struct gendisk *disk, - void (*update_driver_data)(struct gendisk *disk)); -#else /* CONFIG_BLK_DEV_ZONED */ -static inline unsigned int bdev_nr_zones(struct block_device *bdev) -{ - return 0; -} -#endif /* CONFIG_BLK_DEV_ZONED */ + void (*update_driver_data)(struct gendisk *disk)); /* * Independent access ranges: struct blk_independent_access_range describes @@ -378,59 +357,51 @@ struct blk_independent_access_ranges { }; struct request_queue { - struct request *last_merge; - struct elevator_queue *elevator; - - struct percpu_ref q_usage_counter; + /* + * The queue owner gets to use this for whatever they like. + * ll_rw_blk doesn't touch it. + */ + void *queuedata; - struct blk_queue_stats *stats; - struct rq_qos *rq_qos; - struct mutex rq_qos_mutex; + struct elevator_queue *elevator; const struct blk_mq_ops *mq_ops; /* sw queues */ struct blk_mq_ctx __percpu *queue_ctx; + /* + * various queue flags, see QUEUE_* below + */ + unsigned long queue_flags; + + unsigned int rq_timeout; + unsigned int queue_depth; + refcount_t refs; + /* hw dispatch queues */ - struct xarray hctx_table; unsigned int nr_hw_queues; + struct xarray hctx_table; - /* - * The queue owner gets to use this for whatever they like. - * ll_rw_blk doesn't touch it. - */ - void *queuedata; - - /* - * various queue flags, see QUEUE_* below - */ - unsigned long queue_flags; - /* - * Number of contexts that have called blk_set_pm_only(). If this - * counter is above zero then only RQF_PM requests are processed. - */ - atomic_t pm_only; + struct percpu_ref q_usage_counter; - /* - * ida allocated id for this queue. Used to index queues from - * ioctx. - */ - int id; + struct request *last_merge; spinlock_t queue_lock; - struct gendisk *disk; + int quiesce_depth; - refcount_t refs; + struct gendisk *disk; /* * mq queue kobject */ struct kobject *mq_kobj; + struct queue_limits limits; + #ifdef CONFIG_BLK_DEV_INTEGRITY struct blk_integrity integrity; #endif /* CONFIG_BLK_DEV_INTEGRITY */ @@ -441,24 +412,40 @@ struct request_queue { #endif /* - * queue settings + * Number of contexts that have called blk_set_pm_only(). If this + * counter is above zero then only RQF_PM requests are processed. */ - unsigned long nr_requests; /* Max # of requests */ + atomic_t pm_only; + + struct blk_queue_stats *stats; + struct rq_qos *rq_qos; + struct mutex rq_qos_mutex; + + /* + * ida allocated id for this queue. Used to index queues from + * ioctx. + */ + int id; unsigned int dma_pad_mask; + /* + * queue settings + */ + unsigned long nr_requests; /* Max # of requests */ + #ifdef CONFIG_BLK_INLINE_ENCRYPTION struct blk_crypto_profile *crypto_profile; struct kobject *crypto_kobject; #endif - unsigned int rq_timeout; - struct timer_list timeout; struct work_struct timeout_work; atomic_t nr_active_requests_shared_tags; + unsigned int required_elevator_features; + struct blk_mq_tags *sched_shared_tags; struct list_head icq_list; @@ -469,11 +456,12 @@ struct request_queue { struct mutex blkcg_mutex; #endif - struct queue_limits limits; + int node; - unsigned int required_elevator_features; + spinlock_t requeue_lock; + struct list_head requeue_list; + struct delayed_work requeue_work; - int node; #ifdef CONFIG_BLK_DEV_IO_TRACE struct blk_trace __rcu *blk_trace; #endif @@ -483,10 +471,6 @@ struct request_queue { struct blk_flush_queue *fq; struct list_head flush_list; - struct list_head requeue_list; - spinlock_t requeue_lock; - struct delayed_work requeue_work; - struct mutex sysfs_lock; struct mutex sysfs_dir_lock; @@ -511,8 +495,6 @@ struct request_queue { */ struct mutex mq_freeze_lock; - int quiesce_depth; - struct blk_mq_tag_set *tag_set; struct list_head tag_set_list; @@ -625,26 +607,14 @@ static inline enum rpm_status queue_rpm_status(struct request_queue *q) } #endif -static inline enum blk_zoned_model -blk_queue_zoned_model(struct request_queue *q) -{ - if (IS_ENABLED(CONFIG_BLK_DEV_ZONED)) - return q->limits.zoned; - return BLK_ZONED_NONE; -} - static inline bool blk_queue_is_zoned(struct request_queue *q) { - switch (blk_queue_zoned_model(q)) { - case BLK_ZONED_HA: - case BLK_ZONED_HM: - return true; - default: - return false; - } + return IS_ENABLED(CONFIG_BLK_DEV_ZONED) && q->limits.zoned; } #ifdef CONFIG_BLK_DEV_ZONED +unsigned int bdev_nr_zones(struct block_device *bdev); + static inline unsigned int disk_nr_zones(struct gendisk *disk) { return blk_queue_is_zoned(disk->queue) ? disk->nr_zones : 0; @@ -689,6 +659,11 @@ static inline unsigned int bdev_max_active_zones(struct block_device *bdev) } #else /* CONFIG_BLK_DEV_ZONED */ +static inline unsigned int bdev_nr_zones(struct block_device *bdev) +{ + return 0; +} + static inline unsigned int disk_nr_zones(struct gendisk *disk) { return 0; @@ -1082,7 +1057,14 @@ enum blk_default_limits { BLK_SEG_BOUNDARY_MASK = 0xFFFFFFFFUL, }; -#define BLK_DEF_MAX_SECTORS 2560u +/* + * Default upper limit for the software max_sectors limit used for + * regular file system I/O. This can be increased through sysfs. + * + * Not to be confused with the max_hw_sector limit that is entirely + * controlled by the driver, usually based on hardware limits. + */ +#define BLK_DEF_MAX_SECTORS_CAP 2560u static inline unsigned long queue_segment_boundary(const struct request_queue *q) { @@ -1261,11 +1243,6 @@ static inline bool bdev_nowait(struct block_device *bdev) return test_bit(QUEUE_FLAG_NOWAIT, &bdev_get_queue(bdev)->queue_flags); } -static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev) -{ - return blk_queue_zoned_model(bdev_get_queue(bdev)); -} - static inline bool bdev_is_zoned(struct block_device *bdev) { return blk_queue_is_zoned(bdev_get_queue(bdev)); diff --git a/include/linux/bpf.h b/include/linux/bpf.h index cff5bb08820e..e30100597d0a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -29,6 +29,7 @@ #include <linux/rcupdate_trace.h> #include <linux/static_call.h> #include <linux/memcontrol.h> +#include <linux/cfi.h> struct bpf_verifier_env; struct bpf_verifier_log; @@ -106,7 +107,11 @@ struct bpf_map_ops { /* funcs called by prog_array and perf_event_array map */ void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file, int fd); - void (*map_fd_put_ptr)(void *ptr); + /* If need_defer is true, the implementation should guarantee that + * the to-be-put element is still alive before the bpf program, which + * may manipulate it, exists. + */ + void (*map_fd_put_ptr)(struct bpf_map *map, void *ptr, bool need_defer); int (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf); u32 (*map_fd_sys_lookup_elem)(void *ptr); void (*map_seq_show_elem)(struct bpf_map *map, void *key, @@ -186,8 +191,8 @@ enum btf_field_type { BPF_LIST_NODE = (1 << 6), BPF_RB_ROOT = (1 << 7), BPF_RB_NODE = (1 << 8), - BPF_GRAPH_NODE_OR_ROOT = BPF_LIST_NODE | BPF_LIST_HEAD | - BPF_RB_NODE | BPF_RB_ROOT, + BPF_GRAPH_NODE = BPF_RB_NODE | BPF_LIST_NODE, + BPF_GRAPH_ROOT = BPF_RB_ROOT | BPF_LIST_HEAD, BPF_REFCOUNT = (1 << 9), }; @@ -272,7 +277,11 @@ struct bpf_map { */ atomic64_t refcnt ____cacheline_aligned; atomic64_t usercnt; - struct work_struct work; + /* rcu is used before freeing and work is only used during freeing */ + union { + struct work_struct work; + struct rcu_head rcu; + }; struct mutex freeze_mutex; atomic64_t writecnt; /* 'Ownership' of program-containing map is claimed by the first program @@ -288,6 +297,9 @@ struct bpf_map { } owner; bool bypass_spec_v1; bool frozen; /* write-once; write-protected by freeze_mutex */ + bool free_after_mult_rcu_gp; + bool free_after_rcu_gp; + atomic64_t sleepable_refcnt; s64 __percpu *elem_count; }; @@ -1044,6 +1056,17 @@ struct btf_func_model { */ #define BPF_TRAMP_F_TAIL_CALL_CTX BIT(7) +/* + * Indicate the trampoline should be suitable to receive indirect calls; + * without this indirectly calling the generated code can result in #UD/#CP, + * depending on the CFI options. + * + * Used by bpf_struct_ops. + * + * Incompatible with FENTRY usage, overloads @func_addr argument. + */ +#define BPF_TRAMP_F_INDIRECT BIT(8) + /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50 * bytes on x86. */ @@ -1083,10 +1106,17 @@ struct bpf_tramp_run_ctx; * fexit = a set of program to run after original function */ struct bpf_tramp_image; -int arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *image_end, +int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end, const struct btf_func_model *m, u32 flags, struct bpf_tramp_links *tlinks, - void *orig_call); + void *func_addr); +void *arch_alloc_bpf_trampoline(unsigned int size); +void arch_free_bpf_trampoline(void *image, unsigned int size); +void arch_protect_bpf_trampoline(void *image, unsigned int size); +void arch_unprotect_bpf_trampoline(void *image, unsigned int size); +int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, + struct bpf_tramp_links *tlinks, void *func_addr); + u64 notrace __bpf_prog_enter_sleepable_recur(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx); void notrace __bpf_prog_exit_sleepable_recur(struct bpf_prog *prog, u64 start, @@ -1119,6 +1149,7 @@ enum bpf_tramp_prog_type { struct bpf_tramp_image { void *image; + int size; struct bpf_ksym ksym; struct percpu_ref pcref; void *ip_after_call; @@ -1188,7 +1219,11 @@ struct bpf_dispatcher { #endif }; -static __always_inline __nocfi unsigned int bpf_dispatcher_nop_func( +#ifndef __bpfcall +#define __bpfcall __nocfi +#endif + +static __always_inline __bpfcall unsigned int bpf_dispatcher_nop_func( const void *ctx, const struct bpf_insn *insnsi, bpf_func_t bpf_func) @@ -1226,6 +1261,8 @@ enum bpf_dynptr_type { int bpf_dynptr_check_size(u32 size); u32 __bpf_dynptr_size(const struct bpf_dynptr_kern *ptr); +const void *__bpf_dynptr_data(const struct bpf_dynptr_kern *ptr, u32 len); +void *__bpf_dynptr_data_rw(const struct bpf_dynptr_kern *ptr, u32 len); #ifdef CONFIG_BPF_JIT int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr); @@ -1278,7 +1315,7 @@ int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_func #define DEFINE_BPF_DISPATCHER(name) \ __BPF_DISPATCHER_SC(name); \ - noinline __nocfi unsigned int bpf_dispatcher_##name##_func( \ + noinline __bpfcall unsigned int bpf_dispatcher_##name##_func( \ const void *ctx, \ const struct bpf_insn *insnsi, \ bpf_func_t bpf_func) \ @@ -1301,7 +1338,7 @@ int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_func void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, struct bpf_prog *to); /* Called only from JIT-enabled code, so there's no need for stubs. */ -void bpf_image_ksym_add(void *data, struct bpf_ksym *ksym); +void bpf_image_ksym_add(void *data, unsigned int size, struct bpf_ksym *ksym); void bpf_image_ksym_del(struct bpf_ksym *ksym); void bpf_ksym_add(struct bpf_ksym *ksym); void bpf_ksym_del(struct bpf_ksym *ksym); @@ -1345,6 +1382,8 @@ static inline bool bpf_prog_has_trampoline(const struct bpf_prog *prog) struct bpf_func_info_aux { u16 linkage; bool unreliable; + bool called : 1; + bool verified : 1; }; enum bpf_jit_poke_reason { @@ -1410,6 +1449,7 @@ struct bpf_prog_aux { bool dev_bound; /* Program is bound to the netdev. */ bool offload_requested; /* Program is bound and offloaded to the netdev. */ bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */ + bool attach_tracing_prog; /* true if tracing another tracing program */ bool func_proto_unreliable; bool sleepable; bool tail_call_reachable; @@ -1426,6 +1466,9 @@ struct bpf_prog_aux { struct bpf_kfunc_desc_tab *kfunc_tab; struct bpf_kfunc_btf_tab *kfunc_btf_tab; u32 size_poke_tab; +#ifdef CONFIG_FINEIBT + struct bpf_ksym ksym_prefix; +#endif struct bpf_ksym ksym; const struct bpf_prog_ops *ops; struct bpf_map **used_maps; @@ -1438,7 +1481,7 @@ struct bpf_prog_aux { int cgroup_atype; /* enum cgroup_bpf_attach_type */ struct bpf_map *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]; char name[BPF_OBJ_NAME_LEN]; - unsigned int (*bpf_exception_cb)(u64 cookie, u64 sp, u64 bp); + u64 (*bpf_exception_cb)(u64 cookie, u64 sp, u64 bp, u64, u64); #ifdef CONFIG_SECURITY void *security; #endif @@ -1636,6 +1679,7 @@ struct bpf_struct_ops { struct btf_func_model func_models[BPF_STRUCT_OPS_MAX_NR_MEMBERS]; u32 type_id; u32 value_id; + void *cfi_stubs; }; #if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL) @@ -1649,6 +1693,7 @@ int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks, struct bpf_tramp_link *link, const struct btf_func_model *model, + void *stub_func, void *image, void *image_end); static inline bool bpf_try_module_get(const void *data, struct module *owner) { @@ -2422,12 +2467,7 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, struct btf_func_model *m); struct bpf_reg_state; -int btf_check_subprog_arg_match(struct bpf_verifier_env *env, int subprog, - struct bpf_reg_state *regs); -int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog, - struct bpf_reg_state *regs); -int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, - struct bpf_reg_state *reg, bool is_ex_cb); +int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog); int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog, struct btf *btf, const struct btf_type *t); const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type *pt, diff --git a/include/linux/bpf_mem_alloc.h b/include/linux/bpf_mem_alloc.h index bb1223b21308..aaf004d94322 100644 --- a/include/linux/bpf_mem_alloc.h +++ b/include/linux/bpf_mem_alloc.h @@ -11,6 +11,7 @@ struct bpf_mem_caches; struct bpf_mem_alloc { struct bpf_mem_caches __percpu *caches; struct bpf_mem_cache __percpu *cache; + struct obj_cgroup *objcg; bool percpu; struct work_struct work; }; @@ -21,8 +22,15 @@ struct bpf_mem_alloc { * 'size = 0' is for bpf_mem_alloc which manages many fixed-size objects. * Alloc and free are done with bpf_mem_{alloc,free}() and the size of * the returned object is given by the size argument of bpf_mem_alloc(). + * If percpu equals true, error will be returned in order to avoid + * large memory consumption and the below bpf_mem_alloc_percpu_unit_init() + * should be used to do on-demand per-cpu allocation for each size. */ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu); +/* Initialize a non-fix-size percpu memory allocator */ +int bpf_mem_alloc_percpu_init(struct bpf_mem_alloc *ma, struct obj_cgroup *objcg); +/* The percpu allocation with a specific unit size. */ +int bpf_mem_alloc_percpu_unit_init(struct bpf_mem_alloc *ma, int size); void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma); /* kmalloc/kfree equivalent: */ diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index aa4d19d0bc94..d07d857ca67f 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -275,6 +275,11 @@ struct bpf_reference_state { int callback_ref; }; +struct bpf_retval_range { + s32 minval; + s32 maxval; +}; + /* state of the program: * type of all registers and stack info */ @@ -297,8 +302,8 @@ struct bpf_func_state { * void foo(void) { bpf_timer_set_callback(,foo); } */ u32 async_entry_cnt; + struct bpf_retval_range callback_ret_range; bool in_callback_fn; - struct tnum callback_ret_range; bool in_async_callback_fn; bool in_exception_callback_fn; /* For callback calling functions that limit number of possible @@ -316,16 +321,48 @@ struct bpf_func_state { /* The following fields should be last. See copy_func_state() */ int acquired_refs; struct bpf_reference_state *refs; - int allocated_stack; + /* The state of the stack. Each element of the array describes BPF_REG_SIZE + * (i.e. 8) bytes worth of stack memory. + * stack[0] represents bytes [*(r10-8)..*(r10-1)] + * stack[1] represents bytes [*(r10-16)..*(r10-9)] + * ... + * stack[allocated_stack/8 - 1] represents [*(r10-allocated_stack)..*(r10-allocated_stack+7)] + */ struct bpf_stack_state *stack; + /* Size of the current stack, in bytes. The stack state is tracked below, in + * `stack`. allocated_stack is always a multiple of BPF_REG_SIZE. + */ + int allocated_stack; +}; + +#define MAX_CALL_FRAMES 8 + +/* instruction history flags, used in bpf_jmp_history_entry.flags field */ +enum { + /* instruction references stack slot through PTR_TO_STACK register; + * we also store stack's frame number in lower 3 bits (MAX_CALL_FRAMES is 8) + * and accessed stack slot's index in next 6 bits (MAX_BPF_STACK is 512, + * 8 bytes per slot, so slot index (spi) is [0, 63]) + */ + INSN_F_FRAMENO_MASK = 0x7, /* 3 bits */ + + INSN_F_SPI_MASK = 0x3f, /* 6 bits */ + INSN_F_SPI_SHIFT = 3, /* shifted 3 bits to the left */ + + INSN_F_STACK_ACCESS = BIT(9), /* we need 10 bits total */ }; -struct bpf_idx_pair { - u32 prev_idx; +static_assert(INSN_F_FRAMENO_MASK + 1 >= MAX_CALL_FRAMES); +static_assert(INSN_F_SPI_MASK + 1 >= MAX_BPF_STACK / 8); + +struct bpf_jmp_history_entry { u32 idx; + /* insn idx can't be bigger than 1 million */ + u32 prev_idx : 22; + /* special flags, e.g., whether insn is doing register stack spill/load */ + u32 flags : 10; }; -#define MAX_CALL_FRAMES 8 /* Maximum number of register states that can exist at once */ #define BPF_ID_MAP_SIZE ((MAX_BPF_REG + MAX_BPF_STACK / BPF_REG_SIZE) * MAX_CALL_FRAMES) struct bpf_verifier_state { @@ -408,7 +445,7 @@ struct bpf_verifier_state { * For most states jmp_history_cnt is [0-3]. * For loops can go up to ~40. */ - struct bpf_idx_pair *jmp_history; + struct bpf_jmp_history_entry *jmp_history; u32 jmp_history_cnt; u32 dfs_depth; u32 callback_unroll_depth; @@ -569,17 +606,28 @@ static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log) #define BPF_MAX_SUBPROGS 256 +struct bpf_subprog_arg_info { + enum bpf_arg_type arg_type; + union { + u32 mem_size; + }; +}; + struct bpf_subprog_info { /* 'start' has to be the first field otherwise find_subprog() won't work */ u32 start; /* insn idx of function entry point */ u32 linfo_idx; /* The idx to the main_prog->aux->linfo */ u16 stack_depth; /* max. stack depth used by this function */ - bool has_tail_call; - bool tail_call_reachable; - bool has_ld_abs; - bool is_cb; - bool is_async_cb; - bool is_exception_cb; + bool has_tail_call: 1; + bool tail_call_reachable: 1; + bool has_ld_abs: 1; + bool is_cb: 1; + bool is_async_cb: 1; + bool is_exception_cb: 1; + bool args_cached: 1; + + u8 arg_cnt; + struct bpf_subprog_arg_info args[MAX_BPF_FUNC_REG_ARGS]; }; struct bpf_verifier_env; @@ -618,6 +666,7 @@ struct bpf_verifier_env { int stack_size; /* number of states to be processed */ bool strict_alignment; /* perform strict pointer alignment checks */ bool test_state_freq; /* test verifier with different pruning frequency */ + bool test_reg_invariants; /* fail verification on register invariants violations */ struct bpf_verifier_state *cur_state; /* current verifier state */ struct bpf_verifier_state_list **explored_states; /* search pruning optimization */ struct bpf_verifier_state_list *free_list; @@ -630,6 +679,10 @@ struct bpf_verifier_env { int exception_callback_subprog; bool explore_alu_limits; bool allow_ptr_leaks; + /* Allow access to uninitialized stack memory. Writes with fixed offset are + * always allowed, so this refers to reads (with fixed or variable offset), + * to writes with variable offset and to indirect (helper) accesses. + */ bool allow_uninit_stack; bool bpf_capable; bool bypass_spec_v1; @@ -650,6 +703,7 @@ struct bpf_verifier_env { int cur_stack; } cfg; struct backtrack_state bt; + struct bpf_jmp_history_entry *cur_hist_ent; u32 pass_cnt; /* number of times do_check() was called */ u32 subprog_cnt; /* number of instructions analyzed by the verifier */ @@ -684,6 +738,16 @@ struct bpf_verifier_env { char tmp_str_buf[TMP_STR_BUF_LEN]; }; +static inline struct bpf_func_info_aux *subprog_aux(struct bpf_verifier_env *env, int subprog) +{ + return &env->prog->aux->func_info_aux[subprog]; +} + +static inline struct bpf_subprog_info *subprog_info(struct bpf_verifier_env *env, int subprog) +{ + return &env->subprog_info[subprog]; +} + __printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt, va_list args); __printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env, @@ -695,6 +759,10 @@ int bpf_vlog_init(struct bpf_verifier_log *log, u32 log_level, void bpf_vlog_reset(struct bpf_verifier_log *log, u64 new_pos); int bpf_vlog_finalize(struct bpf_verifier_log *log, u32 *log_size_actual); +__printf(3, 4) void verbose_linfo(struct bpf_verifier_env *env, + u32 insn_off, + const char *prefix_fmt, ...); + static inline struct bpf_func_state *cur_func(struct bpf_verifier_env *env) { struct bpf_verifier_state *cur = env->cur_state; @@ -717,14 +785,6 @@ bpf_prog_offload_replace_insn(struct bpf_verifier_env *env, u32 off, void bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt); -int check_ptr_off_reg(struct bpf_verifier_env *env, - const struct bpf_reg_state *reg, int regno); -int check_func_arg_reg_off(struct bpf_verifier_env *env, - const struct bpf_reg_state *reg, int regno, - enum bpf_arg_type arg_type); -int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, - u32 regno, u32 mem_size); - /* this lives here instead of in bpf.h because it needs to dereference tgt_prog */ static inline u64 bpf_trampoline_compute_key(const struct bpf_prog *tgt_prog, struct btf *btf, u32 btf_id) @@ -794,4 +854,76 @@ static inline bool bpf_type_has_unsafe_modifiers(u32 type) return type_flag(type) & ~BPF_REG_TRUSTED_MODIFIERS; } +static inline bool type_is_ptr_alloc_obj(u32 type) +{ + return base_type(type) == PTR_TO_BTF_ID && type_flag(type) & MEM_ALLOC; +} + +static inline bool type_is_non_owning_ref(u32 type) +{ + return type_is_ptr_alloc_obj(type) && type_flag(type) & NON_OWN_REF; +} + +static inline bool type_is_pkt_pointer(enum bpf_reg_type type) +{ + type = base_type(type); + return type == PTR_TO_PACKET || + type == PTR_TO_PACKET_META; +} + +static inline bool type_is_sk_pointer(enum bpf_reg_type type) +{ + return type == PTR_TO_SOCKET || + type == PTR_TO_SOCK_COMMON || + type == PTR_TO_TCP_SOCK || + type == PTR_TO_XDP_SOCK; +} + +static inline void mark_reg_scratched(struct bpf_verifier_env *env, u32 regno) +{ + env->scratched_regs |= 1U << regno; +} + +static inline void mark_stack_slot_scratched(struct bpf_verifier_env *env, u32 spi) +{ + env->scratched_stack_slots |= 1ULL << spi; +} + +static inline bool reg_scratched(const struct bpf_verifier_env *env, u32 regno) +{ + return (env->scratched_regs >> regno) & 1; +} + +static inline bool stack_slot_scratched(const struct bpf_verifier_env *env, u64 regno) +{ + return (env->scratched_stack_slots >> regno) & 1; +} + +static inline bool verifier_state_scratched(const struct bpf_verifier_env *env) +{ + return env->scratched_regs || env->scratched_stack_slots; +} + +static inline void mark_verifier_state_clean(struct bpf_verifier_env *env) +{ + env->scratched_regs = 0U; + env->scratched_stack_slots = 0ULL; +} + +/* Used for printing the entire verifier state. */ +static inline void mark_verifier_state_scratched(struct bpf_verifier_env *env) +{ + env->scratched_regs = ~0U; + env->scratched_stack_slots = ~0ULL; +} + +const char *reg_type_str(struct bpf_verifier_env *env, enum bpf_reg_type type); +const char *dynptr_type_str(enum bpf_dynptr_type type); +const char *iter_type_str(const struct btf *btf, u32 btf_id); +const char *iter_state_str(enum bpf_iter_state state); + +void print_verifier_state(struct bpf_verifier_env *env, + const struct bpf_func_state *state, bool print_all); +void print_insn_state(struct bpf_verifier_env *env, const struct bpf_func_state *state); + #endif /* _LINUX_BPF_VERIFIER_H */ diff --git a/include/linux/bpfilter.h b/include/linux/bpfilter.h deleted file mode 100644 index 736ded4905e0..000000000000 --- a/include/linux/bpfilter.h +++ /dev/null @@ -1,24 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_BPFILTER_H -#define _LINUX_BPFILTER_H - -#include <uapi/linux/bpfilter.h> -#include <linux/usermode_driver.h> -#include <linux/sockptr.h> - -struct sock; -int bpfilter_ip_set_sockopt(struct sock *sk, int optname, sockptr_t optval, - unsigned int optlen); -int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char __user *optval, - int __user *optlen); - -struct bpfilter_umh_ops { - struct umd_info info; - /* since ip_getsockopt() can run in parallel, serialize access to umh */ - struct mutex lock; - int (*sockopt)(struct sock *sk, int optname, sockptr_t optval, - unsigned int optlen, bool is_set); - int (*start)(void); -}; -extern struct bpfilter_umh_ops bpfilter_ops; -#endif diff --git a/include/linux/cache.h b/include/linux/cache.h index 9900d20b76c2..0ecb17bb6883 100644 --- a/include/linux/cache.h +++ b/include/linux/cache.h @@ -85,6 +85,31 @@ #define cache_line_size() L1_CACHE_BYTES #endif +#ifndef __cacheline_group_begin +#define __cacheline_group_begin(GROUP) \ + __u8 __cacheline_group_begin__##GROUP[0] +#endif + +#ifndef __cacheline_group_end +#define __cacheline_group_end(GROUP) \ + __u8 __cacheline_group_end__##GROUP[0] +#endif + +#ifndef CACHELINE_ASSERT_GROUP_MEMBER +#define CACHELINE_ASSERT_GROUP_MEMBER(TYPE, GROUP, MEMBER) \ + BUILD_BUG_ON(!(offsetof(TYPE, MEMBER) >= \ + offsetofend(TYPE, __cacheline_group_begin__##GROUP) && \ + offsetofend(TYPE, MEMBER) <= \ + offsetof(TYPE, __cacheline_group_end__##GROUP))) +#endif + +#ifndef CACHELINE_ASSERT_GROUP_SIZE +#define CACHELINE_ASSERT_GROUP_SIZE(TYPE, GROUP, SIZE) \ + BUILD_BUG_ON(offsetof(TYPE, __cacheline_group_end__##GROUP) - \ + offsetofend(TYPE, __cacheline_group_begin__##GROUP) > \ + SIZE) +#endif + /* * Helper to add padding within a struct to ensure data fall into separate * cachelines. diff --git a/include/linux/cfi.h b/include/linux/cfi.h index 3552ec82b725..f0df518e11dd 100644 --- a/include/linux/cfi.h +++ b/include/linux/cfi.h @@ -9,6 +9,14 @@ #include <linux/bug.h> #include <linux/module.h> +#include <asm/cfi.h> + +#ifndef cfi_get_offset +static inline int cfi_get_offset(void) +{ + return 0; +} +#endif #ifdef CONFIG_CFI_CLANG enum bug_trap_type report_cfi_failure(struct pt_regs *regs, unsigned long addr, @@ -38,4 +46,8 @@ static inline void module_cfi_finalize(const Elf_Ehdr *hdr, #endif /* CONFIG_ARCH_USES_CFI_TRAPS */ #endif /* CONFIG_MODULES */ +#ifndef CFI_NOSEAL +#define CFI_NOSEAL(x) +#endif + #endif /* _LINUX_CFI_H */ diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index ace3a4ce2fc9..1293c38ddb7f 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -448,8 +448,8 @@ struct clk *clk_register_fixed_rate(struct device *dev, const char *name, */ #define clk_hw_register_fixed_rate_with_accuracy_parent_hw(dev, name, \ parent_hw, flags, fixed_rate, fixed_accuracy) \ - __clk_hw_register_fixed_rate((dev), NULL, (name), NULL, (parent_hw) \ - NULL, NULL, (flags), (fixed_rate), \ + __clk_hw_register_fixed_rate((dev), NULL, (name), NULL, (parent_hw), \ + NULL, (flags), (fixed_rate), \ (fixed_accuracy), 0, false) /** * clk_hw_register_fixed_rate_with_accuracy_parent_data - register fixed-rate diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 2ceba3fe4ec1..aebb65bf95a7 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -136,7 +136,7 @@ #endif #define __diag_ignore_all(option, comment) \ - __diag_GCC(8, ignore, option) + __diag(__diag_GCC_ignore option) /* * Prior to 9.1, -Wno-alloc-size-larger-than (and therefore the "alloc_size" diff --git a/include/linux/connector.h b/include/linux/connector.h index cec2d99ae902..70bc1160f3d8 100644 --- a/include/linux/connector.h +++ b/include/linux/connector.h @@ -100,8 +100,7 @@ void cn_del_callback(const struct cb_id *id); */ int cn_netlink_send_mult(struct cn_msg *msg, u16 len, u32 portid, u32 group, gfp_t gfp_mask, - int (*filter)(struct sock *dsk, struct sk_buff *skb, - void *data), + netlink_filter_fn filter, void *filter_data); /** diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 3da2f0545d5d..1666c387861f 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -68,12 +68,12 @@ extern const struct qstr dotdot_name; * large memory footprint increase). */ #ifdef CONFIG_64BIT -# define DNAME_INLINE_LEN 32 /* 192 bytes */ +# define DNAME_INLINE_LEN 40 /* 192 bytes */ #else # ifdef CONFIG_SMP -# define DNAME_INLINE_LEN 36 /* 128 bytes */ -# else # define DNAME_INLINE_LEN 40 /* 128 bytes */ +# else +# define DNAME_INLINE_LEN 44 /* 128 bytes */ # endif #endif @@ -101,8 +101,8 @@ struct dentry { struct list_head d_lru; /* LRU list */ wait_queue_head_t *d_wait; /* in-lookup ones only */ }; - struct list_head d_child; /* child of parent list */ - struct list_head d_subdirs; /* our children */ + struct hlist_node d_sib; /* child of parent list */ + struct hlist_head d_children; /* our children */ /* * d_alias and d_rcu can share memory */ @@ -111,7 +111,7 @@ struct dentry { struct hlist_bl_node d_in_lookup_hash; /* only for in-lookup ones */ struct rcu_head d_rcu; } d_u; -} __randomize_layout; +}; /* * dentry->d_lock spinlock nesting subclasses: @@ -151,13 +151,13 @@ struct dentry_operations { */ /* d_flags entries */ -#define DCACHE_OP_HASH 0x00000001 -#define DCACHE_OP_COMPARE 0x00000002 -#define DCACHE_OP_REVALIDATE 0x00000004 -#define DCACHE_OP_DELETE 0x00000008 -#define DCACHE_OP_PRUNE 0x00000010 +#define DCACHE_OP_HASH BIT(0) +#define DCACHE_OP_COMPARE BIT(1) +#define DCACHE_OP_REVALIDATE BIT(2) +#define DCACHE_OP_DELETE BIT(3) +#define DCACHE_OP_PRUNE BIT(4) -#define DCACHE_DISCONNECTED 0x00000020 +#define DCACHE_DISCONNECTED BIT(5) /* This dentry is possibly not currently connected to the dcache tree, in * which case its parent will either be itself, or will have this flag as * well. nfsd will not use a dentry with this bit set, but will first @@ -168,50 +168,46 @@ struct dentry_operations { * dentry into place and return that dentry rather than the passed one, * typically using d_splice_alias. */ -#define DCACHE_REFERENCED 0x00000040 /* Recently used, don't discard. */ +#define DCACHE_REFERENCED BIT(6) /* Recently used, don't discard. */ -#define DCACHE_DONTCACHE 0x00000080 /* Purge from memory on final dput() */ +#define DCACHE_DONTCACHE BIT(7) /* Purge from memory on final dput() */ -#define DCACHE_CANT_MOUNT 0x00000100 -#define DCACHE_GENOCIDE 0x00000200 -#define DCACHE_SHRINK_LIST 0x00000400 +#define DCACHE_CANT_MOUNT BIT(8) +#define DCACHE_SHRINK_LIST BIT(10) -#define DCACHE_OP_WEAK_REVALIDATE 0x00000800 +#define DCACHE_OP_WEAK_REVALIDATE BIT(11) -#define DCACHE_NFSFS_RENAMED 0x00001000 +#define DCACHE_NFSFS_RENAMED BIT(12) /* this dentry has been "silly renamed" and has to be deleted on the last * dput() */ -#define DCACHE_COOKIE 0x00002000 /* For use by dcookie subsystem */ -#define DCACHE_FSNOTIFY_PARENT_WATCHED 0x00004000 +#define DCACHE_FSNOTIFY_PARENT_WATCHED BIT(14) /* Parent inode is watched by some fsnotify listener */ -#define DCACHE_DENTRY_KILLED 0x00008000 +#define DCACHE_DENTRY_KILLED BIT(15) -#define DCACHE_MOUNTED 0x00010000 /* is a mountpoint */ -#define DCACHE_NEED_AUTOMOUNT 0x00020000 /* handle automount on this dir */ -#define DCACHE_MANAGE_TRANSIT 0x00040000 /* manage transit from this dirent */ +#define DCACHE_MOUNTED BIT(16) /* is a mountpoint */ +#define DCACHE_NEED_AUTOMOUNT BIT(17) /* handle automount on this dir */ +#define DCACHE_MANAGE_TRANSIT BIT(18) /* manage transit from this dirent */ #define DCACHE_MANAGED_DENTRY \ (DCACHE_MOUNTED|DCACHE_NEED_AUTOMOUNT|DCACHE_MANAGE_TRANSIT) -#define DCACHE_LRU_LIST 0x00080000 +#define DCACHE_LRU_LIST BIT(19) -#define DCACHE_ENTRY_TYPE 0x00700000 -#define DCACHE_MISS_TYPE 0x00000000 /* Negative dentry (maybe fallthru to nowhere) */ -#define DCACHE_WHITEOUT_TYPE 0x00100000 /* Whiteout dentry (stop pathwalk) */ -#define DCACHE_DIRECTORY_TYPE 0x00200000 /* Normal directory */ -#define DCACHE_AUTODIR_TYPE 0x00300000 /* Lookupless directory (presumed automount) */ -#define DCACHE_REGULAR_TYPE 0x00400000 /* Regular file type (or fallthru to such) */ -#define DCACHE_SPECIAL_TYPE 0x00500000 /* Other file type (or fallthru to such) */ -#define DCACHE_SYMLINK_TYPE 0x00600000 /* Symlink (or fallthru to such) */ +#define DCACHE_ENTRY_TYPE (7 << 20) /* bits 20..22 are for storing type: */ +#define DCACHE_MISS_TYPE (0 << 20) /* Negative dentry */ +#define DCACHE_WHITEOUT_TYPE (1 << 20) /* Whiteout dentry (stop pathwalk) */ +#define DCACHE_DIRECTORY_TYPE (2 << 20) /* Normal directory */ +#define DCACHE_AUTODIR_TYPE (3 << 20) /* Lookupless directory (presumed automount) */ +#define DCACHE_REGULAR_TYPE (4 << 20) /* Regular file type */ +#define DCACHE_SPECIAL_TYPE (5 << 20) /* Other file type */ +#define DCACHE_SYMLINK_TYPE (6 << 20) /* Symlink */ -#define DCACHE_MAY_FREE 0x00800000 -#define DCACHE_FALLTHRU 0x01000000 /* Fall through to lower layer */ -#define DCACHE_NOKEY_NAME 0x02000000 /* Encrypted name encoded without key */ -#define DCACHE_OP_REAL 0x04000000 +#define DCACHE_NOKEY_NAME BIT(25) /* Encrypted name encoded without key */ +#define DCACHE_OP_REAL BIT(26) -#define DCACHE_PAR_LOOKUP 0x10000000 /* being looked up (with parent locked shared) */ -#define DCACHE_DENTRY_CURSOR 0x20000000 -#define DCACHE_NORCU 0x40000000 /* No RCU delay for freeing */ +#define DCACHE_PAR_LOOKUP BIT(28) /* being looked up (with parent locked shared) */ +#define DCACHE_DENTRY_CURSOR BIT(29) +#define DCACHE_NORCU BIT(30) /* No RCU delay for freeing */ extern seqlock_t rename_lock; @@ -220,8 +216,6 @@ extern seqlock_t rename_lock; */ extern void d_instantiate(struct dentry *, struct inode *); extern void d_instantiate_new(struct dentry *, struct inode *); -extern struct dentry * d_instantiate_unique(struct dentry *, struct inode *); -extern struct dentry * d_instantiate_anon(struct dentry *, struct inode *); extern void __d_drop(struct dentry *dentry); extern void d_drop(struct dentry *dentry); extern void d_delete(struct dentry *); @@ -242,15 +236,11 @@ extern struct dentry * d_obtain_alias(struct inode *); extern struct dentry * d_obtain_root(struct inode *); extern void shrink_dcache_sb(struct super_block *); extern void shrink_dcache_parent(struct dentry *); -extern void shrink_dcache_for_umount(struct super_block *); extern void d_invalidate(struct dentry *); /* only used at mount-time */ extern struct dentry * d_make_root(struct inode *); -/* <clickety>-<click> the ramfs-type tree */ -extern void d_genocide(struct dentry *); - extern void d_mark_tmpfile(struct file *, struct inode *); extern void d_tmpfile(struct file *, struct inode *); @@ -274,12 +264,8 @@ extern void d_move(struct dentry *, struct dentry *); extern void d_exchange(struct dentry *, struct dentry *); extern struct dentry *d_ancestor(struct dentry *, struct dentry *); -/* appendix may either be NULL or be used for transname suffixes */ extern struct dentry *d_lookup(const struct dentry *, const struct qstr *); extern struct dentry *d_hash_and_lookup(struct dentry *, struct qstr *); -extern struct dentry *__d_lookup(const struct dentry *, const struct qstr *); -extern struct dentry *__d_lookup_rcu(const struct dentry *parent, - const struct qstr *name, unsigned *seq); static inline unsigned d_count(const struct dentry *dentry) { @@ -301,20 +287,40 @@ extern char *dentry_path(const struct dentry *, char *, int); /* Allocation counts.. */ /** - * dget, dget_dlock - get a reference to a dentry - * @dentry: dentry to get a reference to + * dget_dlock - get a reference to a dentry + * @dentry: dentry to get a reference to * - * Given a dentry or %NULL pointer increment the reference count - * if appropriate and return the dentry. A dentry will not be - * destroyed when it has references. + * Given a live dentry, increment the reference count and return the dentry. + * Caller must hold @dentry->d_lock. Making sure that dentry is alive is + * caller's resonsibility. There are many conditions sufficient to guarantee + * that; e.g. anything with non-negative refcount is alive, so's anything + * hashed, anything positive, anyone's parent, etc. */ static inline struct dentry *dget_dlock(struct dentry *dentry) { - if (dentry) - dentry->d_lockref.count++; + dentry->d_lockref.count++; return dentry; } + +/** + * dget - get a reference to a dentry + * @dentry: dentry to get a reference to + * + * Given a dentry or %NULL pointer increment the reference count + * if appropriate and return the dentry. A dentry will not be + * destroyed when it has references. Conversely, a dentry with + * no references can disappear for any number of reasons, starting + * with memory pressure. In other words, that primitive is + * used to clone an existing reference; using it on something with + * zero refcount is a bug. + * + * NOTE: it will spin if @dentry->d_lock is held. From the deadlock + * avoidance point of view it is equivalent to spin_lock()/increment + * refcount/spin_unlock(), so calling it under @dentry->d_lock is + * always a bug; so's calling it under ->d_lock on any of its descendents. + * + */ static inline struct dentry *dget(struct dentry *dentry) { if (dentry) @@ -325,12 +331,11 @@ static inline struct dentry *dget(struct dentry *dentry) extern struct dentry *dget_parent(struct dentry *dentry); /** - * d_unhashed - is dentry hashed - * @dentry: entry to check + * d_unhashed - is dentry hashed + * @dentry: entry to check * - * Returns true if the dentry passed is not currently hashed. + * Returns true if the dentry passed is not currently hashed. */ - static inline int d_unhashed(const struct dentry *dentry) { return hlist_bl_unhashed(&dentry->d_hash); @@ -490,14 +495,6 @@ static inline int simple_positive(const struct dentry *dentry) return d_really_is_positive(dentry) && !d_unhashed(dentry); } -extern void d_set_fallthru(struct dentry *dentry); - -static inline bool d_is_fallthru(const struct dentry *dentry) -{ - return dentry->d_flags & DCACHE_FALLTHRU; -} - - extern int sysctl_vfs_cache_pressure; static inline unsigned long vfs_pressure_ratio(unsigned long val) @@ -547,21 +544,6 @@ static inline struct inode *d_backing_inode(const struct dentry *upper) } /** - * d_backing_dentry - Get upper or lower dentry we should be using - * @upper: The upper layer - * - * This is the helper that should be used to get the dentry of the inode that - * will be used if this dentry were opened as a file. It may be the upper - * dentry or it may be a lower dentry pinned by the upper. - * - * Normal filesystems should not use this to access their own dentries. - */ -static inline struct dentry *d_backing_dentry(struct dentry *upper) -{ - return upper; -} - -/** * d_real - Return the real dentry * @dentry: the dentry to query * @inode: inode to select the dentry from multiple layers (can be NULL) @@ -600,4 +582,14 @@ struct name_snapshot { void take_dentry_name_snapshot(struct name_snapshot *, struct dentry *); void release_dentry_name_snapshot(struct name_snapshot *); +static inline struct dentry *d_first_child(const struct dentry *dentry) +{ + return hlist_entry_safe(dentry->d_children.first, struct dentry, d_sib); +} + +static inline struct dentry *d_next_sibling(const struct dentry *dentry) +{ + return hlist_entry_safe(dentry->d_sib.next, struct dentry, d_sib); +} + #endif /* __LINUX_DCACHE_H */ diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 3f31baa3293f..8ff4add71f88 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -343,16 +343,19 @@ struct dma_buf { /** * @exp_name: * - * Name of the exporter; useful for debugging. See the - * DMA_BUF_SET_NAME IOCTL. + * Name of the exporter; useful for debugging. Must not be NULL */ const char *exp_name; /** * @name: * - * Userspace-provided name; useful for accounting and debugging, - * protected by dma_resv_lock() on @resv and @name_lock for read access. + * Userspace-provided name. Default value is NULL. If not NULL, + * length cannot be longer than DMA_BUF_NAME_LEN, including NIL + * char. Useful for accounting and debugging. Read/Write accesses + * are protected by @name_lock + * + * See the IOCTLs DMA_BUF_SET_NAME or DMA_BUF_SET_NAME_A/B */ const char *name; diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 18aade195884..3eb3589ff43e 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -21,7 +21,6 @@ struct bus_dma_region { phys_addr_t cpu_start; dma_addr_t dma_start; u64 size; - u64 offset; }; static inline dma_addr_t translate_phys_to_dma(struct device *dev, @@ -29,9 +28,12 @@ static inline dma_addr_t translate_phys_to_dma(struct device *dev, { const struct bus_dma_region *m; - for (m = dev->dma_range_map; m->size; m++) - if (paddr >= m->cpu_start && paddr - m->cpu_start < m->size) - return (dma_addr_t)paddr - m->offset; + for (m = dev->dma_range_map; m->size; m++) { + u64 offset = paddr - m->cpu_start; + + if (paddr >= m->cpu_start && offset < m->size) + return m->dma_start + offset; + } /* make sure dma_capable fails when no translation is available */ return DMA_MAPPING_ERROR; @@ -42,9 +44,12 @@ static inline phys_addr_t translate_dma_to_phys(struct device *dev, { const struct bus_dma_region *m; - for (m = dev->dma_range_map; m->size; m++) - if (dma_addr >= m->dma_start && dma_addr - m->dma_start < m->size) - return (phys_addr_t)dma_addr + m->offset; + for (m = dev->dma_range_map; m->size; m++) { + u64 offset = dma_addr - m->dma_start; + + if (dma_addr >= m->dma_start && offset < m->size) + return m->cpu_start + offset; + } return (phys_addr_t)-1; } diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index b3772edca2e6..e06bad467f55 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -21,6 +21,7 @@ #include <linux/sched.h> #include <linux/printk.h> #include <linux/rcupdate.h> +#include <linux/timekeeping.h> struct dma_fence; struct dma_fence_ops; diff --git a/include/linux/dpll.h b/include/linux/dpll.h index 578fc5fa3750..9cf896ea1d41 100644 --- a/include/linux/dpll.h +++ b/include/linux/dpll.h @@ -17,9 +17,6 @@ struct dpll_pin; struct dpll_device_ops { int (*mode_get)(const struct dpll_device *dpll, void *dpll_priv, enum dpll_mode *mode, struct netlink_ext_ack *extack); - bool (*mode_supported)(const struct dpll_device *dpll, void *dpll_priv, - const enum dpll_mode mode, - struct netlink_ext_ack *extack); int (*lock_status_get)(const struct dpll_device *dpll, void *dpll_priv, enum dpll_lock_status *status, struct netlink_ext_ack *extack); @@ -80,6 +77,9 @@ struct dpll_pin_ops { const struct dpll_device *dpll, void *dpll_priv, const s32 phase_adjust, struct netlink_ext_ack *extack); + int (*ffo_get)(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + s64 *ffo, struct netlink_ext_ack *extack); }; struct dpll_pin_frequency { diff --git a/include/linux/efi.h b/include/linux/efi.h index 9cc5bf32f6f2..c74f47711f0b 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -40,6 +40,7 @@ struct screen_info; #define EFI_WRITE_PROTECTED ( 8 | (1UL << (BITS_PER_LONG-1))) #define EFI_OUT_OF_RESOURCES ( 9 | (1UL << (BITS_PER_LONG-1))) #define EFI_NOT_FOUND (14 | (1UL << (BITS_PER_LONG-1))) +#define EFI_ACCESS_DENIED (15 | (1UL << (BITS_PER_LONG-1))) #define EFI_TIMEOUT (18 | (1UL << (BITS_PER_LONG-1))) #define EFI_ABORTED (21 | (1UL << (BITS_PER_LONG-1))) #define EFI_SECURITY_VIOLATION (26 | (1UL << (BITS_PER_LONG-1))) @@ -1348,4 +1349,15 @@ bool efi_config_table_is_usable(const efi_guid_t *guid, unsigned long table) umode_t efi_attr_is_visible(struct kobject *kobj, struct attribute *attr, int n); +/* + * efivar ops event type + */ +#define EFIVAR_OPS_RDONLY 0 +#define EFIVAR_OPS_RDWR 1 + +extern struct blocking_notifier_head efivar_ops_nh; + +void efivars_generic_ops_register(void); +void efivars_generic_ops_unregister(void); + #endif /* _LINUX_EFI_H */ diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 689028257fcc..325e0778e937 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -95,6 +95,7 @@ struct kernel_ethtool_ringparam { * @ETHTOOL_RING_USE_TX_PUSH: capture for setting tx_push * @ETHTOOL_RING_USE_RX_PUSH: capture for setting rx_push * @ETHTOOL_RING_USE_TX_PUSH_BUF_LEN: capture for setting tx_push_buf_len + * @ETHTOOL_RING_USE_TCP_DATA_SPLIT: capture for setting tcp_data_split */ enum ethtool_supported_ring_param { ETHTOOL_RING_USE_RX_BUF_LEN = BIT(0), @@ -102,6 +103,7 @@ enum ethtool_supported_ring_param { ETHTOOL_RING_USE_TX_PUSH = BIT(2), ETHTOOL_RING_USE_RX_PUSH = BIT(3), ETHTOOL_RING_USE_TX_PUSH_BUF_LEN = BIT(4), + ETHTOOL_RING_USE_TCP_DATA_SPLIT = BIT(5), }; #define __ETH_RSS_HASH_BIT(bit) ((u32)1 << (bit)) @@ -409,8 +411,10 @@ struct ethtool_pause_stats { * not entire FEC data blocks. This is a non-standard statistic. * Reported to user space as %ETHTOOL_A_FEC_STAT_CORR_BITS. * - * @lane: per-lane/PCS-instance counts as defined by the standard - * @total: error counts for the entire port, for drivers incapable of reporting + * For each of the above fields, the two substructure members are: + * + * - @lanes: per-lane/PCS-instance counts as defined by the standard + * - @total: error counts for the entire port, for drivers incapable of reporting * per-lane stats * * Drivers should fill in either only total or per-lane statistics, core @@ -595,9 +599,46 @@ struct ethtool_mm_stats { }; /** + * struct ethtool_rxfh_param - RXFH (RSS) parameters + * @hfunc: Defines the current RSS hash function used by HW (or to be set to). + * Valid values are one of the %ETH_RSS_HASH_*. + * @indir_size: On SET, the array size of the user buffer for the + * indirection table, which may be zero, or + * %ETH_RXFH_INDIR_NO_CHANGE. On GET (read from the driver), + * the array size of the hardware indirection table. + * @indir: The indirection table of size @indir_size entries. + * @key_size: On SET, the array size of the user buffer for the hash key, + * which may be zero. On GET (read from the driver), the size of the + * hardware hash key. + * @key: The hash key of size @key_size bytes. + * @rss_context: RSS context identifier. Context 0 is the default for normal + * traffic; other contexts can be referenced as the destination for RX flow + * classification rules. On SET, %ETH_RXFH_CONTEXT_ALLOC is used + * to allocate a new RSS context; on return this field will + * contain the ID of the newly allocated context. + * @rss_delete: Set to non-ZERO to remove the @rss_context context. + * @input_xfrm: Defines how the input data is transformed. Valid values are one + * of %RXH_XFRM_*. + */ +struct ethtool_rxfh_param { + u8 hfunc; + u32 indir_size; + u32 *indir; + u32 key_size; + u8 *key; + u32 rss_context; + u8 rss_delete; + u8 input_xfrm; +}; + +/** * struct ethtool_ops - optional netdev operations * @cap_link_lanes_supported: indicates if the driver supports lanes * parameter. + * @cap_rss_ctx_supported: indicates if the driver supports RSS + * contexts. + * @cap_rss_sym_xor_supported: indicates if the driver supports symmetric-xor + * RSS. * @supported_coalesce_params: supported types of interrupt coalescing. * @supported_ring_params: supported ring params. * @get_drvinfo: Report driver/device information. Modern drivers no @@ -694,15 +735,6 @@ struct ethtool_mm_stats { * will remain unchanged. * Returns a negative error code or zero. An error code must be returned * if at least one unsupported change was requested. - * @get_rxfh_context: Get the contents of the RX flow hash indirection table, - * hash key, and/or hash function assiciated to the given rss context. - * Returns a negative error code or zero. - * @set_rxfh_context: Create, remove and configure RSS contexts. Allows setting - * the contents of the RX flow hash indirection table, hash key, and/or - * hash function associated to the given context. Arguments which are set - * to %NULL or zero will remain unchanged. - * Returns a negative error code or zero. An error code must be returned - * if at least one unsupported change was requested. * @get_channels: Get number of channels. * @set_channels: Set number of channels. Returns a negative error code or * zero. @@ -785,6 +817,8 @@ struct ethtool_mm_stats { */ struct ethtool_ops { u32 cap_link_lanes_supported:1; + u32 cap_rss_ctx_supported:1; + u32 cap_rss_sym_xor_supported:1; u32 supported_coalesce_params; u32 supported_ring_params; void (*get_drvinfo)(struct net_device *, struct ethtool_drvinfo *); @@ -844,15 +878,9 @@ struct ethtool_ops { int (*reset)(struct net_device *, u32 *); u32 (*get_rxfh_key_size)(struct net_device *); u32 (*get_rxfh_indir_size)(struct net_device *); - int (*get_rxfh)(struct net_device *, u32 *indir, u8 *key, - u8 *hfunc); - int (*set_rxfh)(struct net_device *, const u32 *indir, - const u8 *key, const u8 hfunc); - int (*get_rxfh_context)(struct net_device *, u32 *indir, u8 *key, - u8 *hfunc, u32 rss_context); - int (*set_rxfh_context)(struct net_device *, const u32 *indir, - const u8 *key, const u8 hfunc, - u32 *rss_context, bool delete); + int (*get_rxfh)(struct net_device *, struct ethtool_rxfh_param *); + int (*set_rxfh)(struct net_device *, struct ethtool_rxfh_param *, + struct netlink_ext_ack *extack); void (*get_channels)(struct net_device *, struct ethtool_channels *); int (*set_channels)(struct net_device *, struct ethtool_channels *); int (*get_dump_flag)(struct net_device *, struct ethtool_dump *); @@ -1044,6 +1072,14 @@ static inline int ethtool_mm_frag_size_min_to_add(u32 val_min, u32 *val_add, } /** + * ethtool_get_ts_info_by_layer - Obtains time stamping capabilities from the MAC or PHY layer. + * @dev: pointer to net_device structure + * @info: buffer to hold the result + * Returns zero on success, non-zero otherwise. + */ +int ethtool_get_ts_info_by_layer(struct net_device *dev, struct ethtool_ts_info *info); + +/** * ethtool_sprintf - Write formatted string to ethtool string data * @data: Pointer to a pointer to the start of string to update * @fmt: Format of string to write @@ -1053,6 +1089,19 @@ static inline int ethtool_mm_frag_size_min_to_add(u32 val_min, u32 *val_add, */ extern __printf(2, 3) void ethtool_sprintf(u8 **data, const char *fmt, ...); +/** + * ethtool_puts - Write string to ethtool string data + * @data: Pointer to a pointer to the start of string to update + * @str: String to write + * + * Write string to *data without a trailing newline. Update *data + * to point at start of next string. + * + * Prefer this function to ethtool_sprintf() when given only + * two arguments or if @fmt is just "%s". + */ +extern void ethtool_puts(u8 **data, const char *str); + /* Link mode to forced speed capabilities maps */ struct ethtool_forced_speed_map { u32 speed; diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 039fe0ce8d83..053137a0fe45 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -441,7 +441,7 @@ struct f2fs_sit_block { * ex) data_blkaddr = (block_t)(nodepage_start_address + ofs_in_node) */ #define ENTRIES_IN_SUM (F2FS_BLKSIZE / 8) -#define SUMMARY_SIZE (7) /* sizeof(struct summary) */ +#define SUMMARY_SIZE (7) /* sizeof(struct f2fs_summary) */ #define SUM_FOOTER_SIZE (5) /* sizeof(struct summary_footer) */ #define SUM_ENTRY_SIZE (SUMMARY_SIZE * ENTRIES_IN_SUM) diff --git a/include/linux/fb.h b/include/linux/fb.h index 94e2c44c6569..05dc9624897d 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -536,6 +536,7 @@ extern ssize_t fb_io_read(struct fb_info *info, char __user *buf, size_t count, loff_t *ppos); extern ssize_t fb_io_write(struct fb_info *info, const char __user *buf, size_t count, loff_t *ppos); +int fb_io_mmap(struct fb_info *info, struct vm_area_struct *vma); #define __FB_DEFAULT_IOMEM_OPS_RDWR \ .fb_read = fb_io_read, \ @@ -547,7 +548,7 @@ extern ssize_t fb_io_write(struct fb_info *info, const char __user *buf, .fb_imageblit = cfb_imageblit #define __FB_DEFAULT_IOMEM_OPS_MMAP \ - .fb_mmap = NULL /* default implementation */ + .fb_mmap = fb_io_mmap #define FB_DEFAULT_IOMEM_OPS \ __FB_DEFAULT_IOMEM_OPS_RDWR, \ @@ -848,7 +849,10 @@ static inline bool fb_modesetting_disabled(const char *drvname) } #endif -/* Convenience logging macros */ +/* + * Convenience logging macros + */ + #define fb_err(fb_info, fmt, ...) \ pr_err("fb%d: " fmt, (fb_info)->node, ##__VA_ARGS__) #define fb_notice(info, fmt, ...) \ @@ -860,4 +864,12 @@ static inline bool fb_modesetting_disabled(const char *drvname) #define fb_dbg(fb_info, fmt, ...) \ pr_debug("fb%d: " fmt, (fb_info)->node, ##__VA_ARGS__) +#define fb_warn_once(fb_info, fmt, ...) \ + pr_warn_once("fb%d: " fmt, (fb_info)->node, ##__VA_ARGS__) + +#define fb_WARN_ONCE(fb_info, condition, fmt, ...) \ + WARN_ONCE(condition, "fb%d: " fmt, (fb_info)->node, ##__VA_ARGS__) +#define fb_WARN_ON_ONCE(fb_info, x) \ + fb_WARN_ONCE(fb_info, (x), "%s", "fb_WARN_ON_ONCE(" __stringify(x) ")") + #endif /* _LINUX_FB_H */ diff --git a/include/linux/filter.h b/include/linux/filter.h index a4953fafc8cb..68fb6c8142fe 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1067,7 +1067,7 @@ struct bpf_binary_header * bpf_jit_binary_pack_hdr(const struct bpf_prog *fp); void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns); -void bpf_prog_pack_free(struct bpf_binary_header *hdr); +void bpf_prog_pack_free(void *ptr, u32 size); static inline bool bpf_prog_kallsyms_verify_off(const struct bpf_prog *fp) { diff --git a/include/linux/firewire.h b/include/linux/firewire.h index bd3fc75d4f14..dd9f2d765e68 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -75,7 +75,7 @@ void fw_csr_iterator_init(struct fw_csr_iterator *ci, const u32 *p); int fw_csr_iterator_next(struct fw_csr_iterator *ci, int *key, int *value); int fw_csr_string(const u32 *directory, int key, char *buf, size_t size); -extern struct bus_type fw_bus_type; +extern const struct bus_type fw_bus_type; struct fw_card_driver; struct fw_node; diff --git a/include/linux/firmware.h b/include/linux/firmware.h index de7fea3bca51..0311858b46ce 100644 --- a/include/linux/firmware.h +++ b/include/linux/firmware.h @@ -27,6 +27,7 @@ struct firmware { * @FW_UPLOAD_ERR_INVALID_SIZE: invalid firmware image size * @FW_UPLOAD_ERR_RW_ERROR: read or write to HW failed, see kernel log * @FW_UPLOAD_ERR_WEAROUT: FLASH device is approaching wear-out, wait & retry + * @FW_UPLOAD_ERR_FW_INVALID: invalid firmware file * @FW_UPLOAD_ERR_MAX: Maximum error code marker */ enum fw_upload_err { @@ -38,6 +39,7 @@ enum fw_upload_err { FW_UPLOAD_ERR_INVALID_SIZE, FW_UPLOAD_ERR_RW_ERROR, FW_UPLOAD_ERR_WEAROUT, + FW_UPLOAD_ERR_FW_INVALID, FW_UPLOAD_ERR_MAX }; diff --git a/include/linux/framer/framer-provider.h b/include/linux/framer/framer-provider.h new file mode 100644 index 000000000000..782cd5fc83d5 --- /dev/null +++ b/include/linux/framer/framer-provider.h @@ -0,0 +1,194 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Generic framer profider header file + * + * Copyright 2023 CS GROUP France + * + * Author: Herve Codina <herve.codina@bootlin.com> + */ + +#ifndef __DRIVERS_PROVIDER_FRAMER_H +#define __DRIVERS_PROVIDER_FRAMER_H + +#include <linux/export.h> +#include <linux/framer/framer.h> +#include <linux/types.h> + +#define FRAMER_FLAG_POLL_STATUS BIT(0) + +/** + * struct framer_ops - set of function pointers for performing framer operations + * @init: operation to be performed for initializing the framer + * @exit: operation to be performed while exiting + * @power_on: powering on the framer + * @power_off: powering off the framer + * @flags: OR-ed flags (FRAMER_FLAG_*) to ask for core functionality + * - @FRAMER_FLAG_POLL_STATUS: + * Ask the core to perform a polling to get the framer status and + * notify consumers on change. + * The framer should call @framer_notify_status_change() when it + * detects a status change. This is usually done using interrupts. + * If the framer cannot detect this change, it can ask the core for + * a status polling. The core will call @get_status() periodically + * and, on change detected, it will notify the consumer. + * the @get_status() + * @owner: the module owner containing the ops + */ +struct framer_ops { + int (*init)(struct framer *framer); + void (*exit)(struct framer *framer); + int (*power_on)(struct framer *framer); + int (*power_off)(struct framer *framer); + + /** + * @get_status: + * + * Optional. + * + * Used to get the framer status. framer_init() must have + * been called on the framer. + * + * Returns: 0 if successful, an negative error code otherwise + */ + int (*get_status)(struct framer *framer, struct framer_status *status); + + /** + * @set_config: + * + * Optional. + * + * Used to set the framer configuration. framer_init() must have + * been called on the framer. + * + * Returns: 0 if successful, an negative error code otherwise + */ + int (*set_config)(struct framer *framer, const struct framer_config *config); + + /** + * @get_config: + * + * Optional. + * + * Used to get the framer configuration. framer_init() must have + * been called on the framer. + * + * Returns: 0 if successful, an negative error code otherwise + */ + int (*get_config)(struct framer *framer, struct framer_config *config); + + u32 flags; + struct module *owner; +}; + +/** + * struct framer_provider - represents the framer provider + * @dev: framer provider device + * @children: can be used to override the default (dev->of_node) child node + * @owner: the module owner having of_xlate + * @list: to maintain a linked list of framer providers + * @of_xlate: function pointer to obtain framer instance from framer pointer + */ +struct framer_provider { + struct device *dev; + struct module *owner; + struct list_head list; + struct framer * (*of_xlate)(struct device *dev, + struct of_phandle_args *args); +}; + +static inline void framer_set_drvdata(struct framer *framer, void *data) +{ + dev_set_drvdata(&framer->dev, data); +} + +static inline void *framer_get_drvdata(struct framer *framer) +{ + return dev_get_drvdata(&framer->dev); +} + +#if IS_ENABLED(CONFIG_GENERIC_FRAMER) + +/* Create and destroy a framer */ +struct framer *framer_create(struct device *dev, struct device_node *node, + const struct framer_ops *ops); +void framer_destroy(struct framer *framer); + +/* devm version */ +struct framer *devm_framer_create(struct device *dev, struct device_node *node, + const struct framer_ops *ops); + +struct framer *framer_provider_simple_of_xlate(struct device *dev, + struct of_phandle_args *args); + +struct framer_provider * +__framer_provider_of_register(struct device *dev, struct module *owner, + struct framer *(*of_xlate)(struct device *dev, + struct of_phandle_args *args)); + +void framer_provider_of_unregister(struct framer_provider *framer_provider); + +struct framer_provider * +__devm_framer_provider_of_register(struct device *dev, struct module *owner, + struct framer *(*of_xlate)(struct device *dev, + struct of_phandle_args *args)); + +void framer_notify_status_change(struct framer *framer); + +#else /* IS_ENABLED(CONFIG_GENERIC_FRAMER) */ + +static inline struct framer *framer_create(struct device *dev, struct device_node *node, + const struct framer_ops *ops) +{ + return ERR_PTR(-ENOSYS); +} + +static inline void framer_destroy(struct framer *framer) +{ +} + +/* devm version */ +static inline struct framer *devm_framer_create(struct device *dev, struct device_node *node, + const struct framer_ops *ops) +{ + return ERR_PTR(-ENOSYS); +} + +static inline struct framer *framer_provider_simple_of_xlate(struct device *dev, + struct of_phandle_args *args) +{ + return ERR_PTR(-ENOSYS); +} + +static inline struct framer_provider * +__framer_provider_of_register(struct device *dev, struct module *owner, + struct framer *(*of_xlate)(struct device *dev, + struct of_phandle_args *args)) +{ + return ERR_PTR(-ENOSYS); +} + +void framer_provider_of_unregister(struct framer_provider *framer_provider) +{ +} + +static inline struct framer_provider * +__devm_framer_provider_of_register(struct device *dev, struct module *owner, + struct framer *(*of_xlate)(struct device *dev, + struct of_phandle_args *args)) +{ + return ERR_PTR(-ENOSYS); +} + +void framer_notify_status_change(struct framer *framer) +{ +} + +#endif /* IS_ENABLED(CONFIG_GENERIC_FRAMER) */ + +#define framer_provider_of_register(dev, xlate) \ + __framer_provider_of_register((dev), THIS_MODULE, (xlate)) + +#define devm_framer_provider_of_register(dev, xlate) \ + __devm_framer_provider_of_register((dev), THIS_MODULE, (xlate)) + +#endif /* __DRIVERS_PROVIDER_FRAMER_H */ diff --git a/include/linux/framer/framer.h b/include/linux/framer/framer.h new file mode 100644 index 000000000000..9a9b88962c29 --- /dev/null +++ b/include/linux/framer/framer.h @@ -0,0 +1,205 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Generic framer header file + * + * Copyright 2023 CS GROUP France + * + * Author: Herve Codina <herve.codina@bootlin.com> + */ + +#ifndef __DRIVERS_FRAMER_H +#define __DRIVERS_FRAMER_H + +#include <linux/err.h> +#include <linux/mutex.h> +#include <linux/notifier.h> +#include <linux/of.h> +#include <linux/device.h> +#include <linux/workqueue.h> + +/** + * enum framer_iface - Framer interface + * @FRAMER_IFACE_E1: E1 interface + * @FRAMER_IFACE_T1: T1 interface + */ +enum framer_iface { + FRAMER_IFACE_E1, + FRAMER_IFACE_T1, +}; + +/** + * enum framer_clock_type - Framer clock type + * @FRAMER_CLOCK_EXT: External clock + * @FRAMER_CLOCK_INT: Internal clock + */ +enum framer_clock_type { + FRAMER_CLOCK_EXT, + FRAMER_CLOCK_INT, +}; + +/** + * struct framer_config - Framer configuration + * @iface: Framer line interface + * @clock_type: Framer clock type + * @line_clock_rate: Framer line clock rate + */ +struct framer_config { + enum framer_iface iface; + enum framer_clock_type clock_type; + unsigned long line_clock_rate; +}; + +/** + * struct framer_status - Framer status + * @link_is_on: Framer link state. true, the link is on, false, the link is off. + */ +struct framer_status { + bool link_is_on; +}; + +/** + * enum framer_event - Event available for notification + * @FRAMER_EVENT_STATUS: Event notified on framer_status changes + */ +enum framer_event { + FRAMER_EVENT_STATUS, +}; + +/** + * struct framer - represents the framer device + * @dev: framer device + * @id: id of the framer device + * @ops: function pointers for performing framer operations + * @mutex: mutex to protect framer_ops + * @init_count: used to protect when the framer is used by multiple consumers + * @power_count: used to protect when the framer is used by multiple consumers + * @pwr: power regulator associated with the framer + * @notify_status_work: work structure used for status notifications + * @notifier_list: notifier list used for notifications + * @polling_work: delayed work structure used for the polling task + * @prev_status: previous read status used by the polling task to detect changes + */ +struct framer { + struct device dev; + int id; + const struct framer_ops *ops; + struct mutex mutex; /* Protect framer */ + int init_count; + int power_count; + struct regulator *pwr; + struct work_struct notify_status_work; + struct blocking_notifier_head notifier_list; + struct delayed_work polling_work; + struct framer_status prev_status; +}; + +#if IS_ENABLED(CONFIG_GENERIC_FRAMER) +int framer_pm_runtime_get(struct framer *framer); +int framer_pm_runtime_get_sync(struct framer *framer); +int framer_pm_runtime_put(struct framer *framer); +int framer_pm_runtime_put_sync(struct framer *framer); +int framer_init(struct framer *framer); +int framer_exit(struct framer *framer); +int framer_power_on(struct framer *framer); +int framer_power_off(struct framer *framer); +int framer_get_status(struct framer *framer, struct framer_status *status); +int framer_get_config(struct framer *framer, struct framer_config *config); +int framer_set_config(struct framer *framer, const struct framer_config *config); +int framer_notifier_register(struct framer *framer, struct notifier_block *nb); +int framer_notifier_unregister(struct framer *framer, struct notifier_block *nb); + +struct framer *framer_get(struct device *dev, const char *con_id); +void framer_put(struct device *dev, struct framer *framer); + +struct framer *devm_framer_get(struct device *dev, const char *con_id); +struct framer *devm_framer_optional_get(struct device *dev, const char *con_id); +#else +static inline int framer_pm_runtime_get(struct framer *framer) +{ + return -ENOSYS; +} + +static inline int framer_pm_runtime_get_sync(struct framer *framer) +{ + return -ENOSYS; +} + +static inline int framer_pm_runtime_put(struct framer *framer) +{ + return -ENOSYS; +} + +static inline int framer_pm_runtime_put_sync(struct framer *framer) +{ + return -ENOSYS; +} + +static inline int framer_init(struct framer *framer) +{ + return -ENOSYS; +} + +static inline int framer_exit(struct framer *framer) +{ + return -ENOSYS; +} + +static inline int framer_power_on(struct framer *framer) +{ + return -ENOSYS; +} + +static inline int framer_power_off(struct framer *framer) +{ + return -ENOSYS; +} + +static inline int framer_get_status(struct framer *framer, struct framer_status *status) +{ + return -ENOSYS; +} + +static inline int framer_get_config(struct framer *framer, struct framer_config *config) +{ + return -ENOSYS; +} + +static inline int framer_set_config(struct framer *framer, const struct framer_config *config) +{ + return -ENOSYS; +} + +static inline int framer_notifier_register(struct framer *framer, + struct notifier_block *nb) +{ + return -ENOSYS; +} + +static inline int framer_notifier_unregister(struct framer *framer, + struct notifier_block *nb) +{ + return -ENOSYS; +} + +struct framer *framer_get(struct device *dev, const char *con_id) +{ + return ERR_PTR(-ENOSYS); +} + +void framer_put(struct device *dev, struct framer *framer) +{ +} + +static inline struct framer *devm_framer_get(struct device *dev, const char *con_id) +{ + return ERR_PTR(-ENOSYS); +} + +static inline struct framer *devm_framer_optional_get(struct device *dev, const char *con_id) +{ + return NULL; +} + +#endif + +#endif /* __DRIVERS_FRAMER_H */ diff --git a/include/linux/framer/pef2256.h b/include/linux/framer/pef2256.h new file mode 100644 index 000000000000..71d80af58c40 --- /dev/null +++ b/include/linux/framer/pef2256.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * PEF2256 consumer API + * + * Copyright 2023 CS GROUP France + * + * Author: Herve Codina <herve.codina@bootlin.com> + */ +#ifndef __PEF2256_H__ +#define __PEF2256_H__ + +#include <linux/types.h> + +struct pef2256; +struct regmap; + +/* Retrieve the PEF2256 regmap */ +struct regmap *pef2256_get_regmap(struct pef2256 *pef2256); + +/* PEF2256 hardware versions */ +enum pef2256_version { + PEF2256_VERSION_UNKNOWN, + PEF2256_VERSION_1_2, + PEF2256_VERSION_2_1, + PEF2256_VERSION_2_2, +}; + +/* Get the PEF2256 hardware version */ +enum pef2256_version pef2256_get_version(struct pef2256 *pef2256); + +#endif /* __PEF2256_H__ */ diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 11e6434b8e71..8300a5286988 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -100,6 +100,7 @@ static inline int fsnotify_file(struct file *file, __u32 mask) return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH); } +#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS /* * fsnotify_file_area_perm - permission hook before access to file range */ @@ -145,6 +146,24 @@ static inline int fsnotify_open_perm(struct file *file) return fsnotify_file(file, FS_OPEN_PERM); } +#else +static inline int fsnotify_file_area_perm(struct file *file, int perm_mask, + const loff_t *ppos, size_t count) +{ + return 0; +} + +static inline int fsnotify_file_perm(struct file *file, int perm_mask) +{ + return 0; +} + +static inline int fsnotify_open_perm(struct file *file) +{ + return 0; +} +#endif + /* * fsnotify_link_count - inode's link count changed */ diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index c0892d75ce33..7f63be5ca0f1 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -472,10 +472,8 @@ typedef struct fsnotify_mark_connector __rcu *fsnotify_connp_t; struct fsnotify_mark_connector { spinlock_t lock; unsigned short type; /* Type of object [lock] */ -#define FSNOTIFY_CONN_FLAG_HAS_FSID 0x01 #define FSNOTIFY_CONN_FLAG_HAS_IREF 0x02 unsigned short flags; /* flags [lock] */ - __kernel_fsid_t fsid; /* fsid of filesystem containing object */ union { /* Object pointer [lock] */ fsnotify_connp_t *obj; @@ -530,6 +528,8 @@ struct fsnotify_mark { #define FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY 0x0100 #define FSNOTIFY_MARK_FLAG_NO_IREF 0x0200 #define FSNOTIFY_MARK_FLAG_HAS_IGNORE_FLAGS 0x0400 +#define FSNOTIFY_MARK_FLAG_HAS_FSID 0x0800 +#define FSNOTIFY_MARK_FLAG_WEAK_FSID 0x1000 unsigned int flags; /* flags [mark->lock] */ }; @@ -763,11 +763,10 @@ extern struct fsnotify_mark *fsnotify_find_mark(fsnotify_connp_t *connp, /* attach the mark to the object */ extern int fsnotify_add_mark(struct fsnotify_mark *mark, fsnotify_connp_t *connp, unsigned int obj_type, - int add_flags, __kernel_fsid_t *fsid); + int add_flags); extern int fsnotify_add_mark_locked(struct fsnotify_mark *mark, fsnotify_connp_t *connp, - unsigned int obj_type, int add_flags, - __kernel_fsid_t *fsid); + unsigned int obj_type, int add_flags); /* attach the mark to the inode */ static inline int fsnotify_add_inode_mark(struct fsnotify_mark *mark, @@ -775,15 +774,14 @@ static inline int fsnotify_add_inode_mark(struct fsnotify_mark *mark, int add_flags) { return fsnotify_add_mark(mark, &inode->i_fsnotify_marks, - FSNOTIFY_OBJ_TYPE_INODE, add_flags, NULL); + FSNOTIFY_OBJ_TYPE_INODE, add_flags); } static inline int fsnotify_add_inode_mark_locked(struct fsnotify_mark *mark, struct inode *inode, int add_flags) { return fsnotify_add_mark_locked(mark, &inode->i_fsnotify_marks, - FSNOTIFY_OBJ_TYPE_INODE, add_flags, - NULL); + FSNOTIFY_OBJ_TYPE_INODE, add_flags); } /* given a group and a mark, flag mark to be freed when all references are dropped */ diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 0aed62f0c633..e846bd4e7559 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -531,19 +531,40 @@ struct gpio_chip { #endif /* CONFIG_OF_GPIO */ }; -const char *gpiochip_is_requested(struct gpio_chip *gc, unsigned int offset); +char *gpiochip_dup_line_label(struct gpio_chip *gc, unsigned int offset); + + +struct _gpiochip_for_each_data { + const char **label; + unsigned int *i; +}; + +DEFINE_CLASS(_gpiochip_for_each_data, + struct _gpiochip_for_each_data, + if (*_T.label) kfree(*_T.label), + ({ + struct _gpiochip_for_each_data _data = { label, i }; + *_data.i = 0; + _data; + }), + const char **label, int *i) /** * for_each_requested_gpio_in_range - iterates over requested GPIOs in a given range - * @chip: the chip to query - * @i: loop variable - * @base: first GPIO in the range - * @size: amount of GPIOs to check starting from @base - * @label: label of current GPIO + * @_chip: the chip to query + * @_i: loop variable + * @_base: first GPIO in the range + * @_size: amount of GPIOs to check starting from @base + * @_label: label of current GPIO */ -#define for_each_requested_gpio_in_range(chip, i, base, size, label) \ - for (i = 0; i < size; i++) \ - if ((label = gpiochip_is_requested(chip, base + i)) == NULL) {} else +#define for_each_requested_gpio_in_range(_chip, _i, _base, _size, _label) \ + for (CLASS(_gpiochip_for_each_data, _data)(&_label, &_i); \ + *_data.i < _size; \ + (*_data.i)++, kfree(*(_data.label)), *_data.label = NULL) \ + if ((*_data.label = \ + gpiochip_dup_line_label(_chip, _base + *_data.i)) == NULL) {} \ + else if (IS_ERR(*_data.label)) {} \ + else /* Iterates over all requested GPIO of the given @chip */ #define for_each_requested_gpio(chip, i, label) \ @@ -701,7 +722,6 @@ int gpiochip_irqchip_add_domain(struct gpio_chip *gc, #else #include <asm/bug.h> -#include <asm/errno.h> static inline int gpiochip_irqchip_add_domain(struct gpio_chip *gc, struct irq_domain *domain) @@ -786,11 +806,10 @@ struct gpio_device *gpiod_to_gpio_device(struct gpio_desc *desc); /* struct gpio_device getters */ int gpio_device_get_base(struct gpio_device *gdev); +const char *gpio_device_get_label(struct gpio_device *gdev); #else /* CONFIG_GPIOLIB */ -#include <linux/err.h> - #include <asm/bug.h> static inline struct gpio_chip *gpiod_to_chip(const struct gpio_desc *desc) diff --git a/include/linux/habanalabs/cpucp_if.h b/include/linux/habanalabs/cpucp_if.h index 86ea7c63a0d2..f316c8d0f3fc 100644 --- a/include/linux/habanalabs/cpucp_if.h +++ b/include/linux/habanalabs/cpucp_if.h @@ -659,6 +659,12 @@ enum pq_init_status { * number (nonce) provided by the host to prevent replay attacks. * public key and certificate also provided as part of the FW response. * + * CPUCP_PACKET_INFO_SIGNED_GET - + * Get the device information signed by the Trusted Platform device. + * device info data is also hashed with some unique number (nonce) provided + * by the host to prevent replay attacks. public key and certificate also + * provided as part of the FW response. + * * CPUCP_PACKET_MONITOR_DUMP_GET - * Get monitors registers dump from the CpuCP kernel. * The CPU will put the registers dump in the a buffer allocated by the driver @@ -733,7 +739,7 @@ enum cpucp_packet_id { CPUCP_PACKET_ENGINE_CORE_ASID_SET, /* internal */ CPUCP_PACKET_RESERVED2, /* not used */ CPUCP_PACKET_SEC_ATTEST_GET, /* internal */ - CPUCP_PACKET_RESERVED3, /* not used */ + CPUCP_PACKET_INFO_SIGNED_GET, /* internal */ CPUCP_PACKET_RESERVED4, /* not used */ CPUCP_PACKET_MONITOR_DUMP_GET, /* debugfs */ CPUCP_PACKET_RESERVED5, /* not used */ diff --git a/include/linux/hid.h b/include/linux/hid.h index bf43f3ff6664..7c26db874ff0 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -912,7 +912,7 @@ extern bool hid_ignore(struct hid_device *); extern int hid_add_device(struct hid_device *); extern void hid_destroy_device(struct hid_device *); -extern struct bus_type hid_bus_type; +extern const struct bus_type hid_bus_type; extern int __must_check __hid_register_driver(struct hid_driver *, struct module *, const char *mod_name); diff --git a/include/linux/hid_bpf.h b/include/linux/hid_bpf.h index e9afb61e6ee0..840cd254172d 100644 --- a/include/linux/hid_bpf.h +++ b/include/linux/hid_bpf.h @@ -115,7 +115,7 @@ struct hid_bpf_ops { size_t len, enum hid_report_type rtype, enum hid_class_request reqtype); struct module *owner; - struct bus_type *bus_type; + const struct bus_type *bus_type; }; extern struct hid_bpf_ops *hid_bpf_ops; diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h index ddc7ebb70523..5f4c74facf6a 100644 --- a/include/linux/hisi_acc_qm.h +++ b/include/linux/hisi_acc_qm.h @@ -108,17 +108,13 @@ enum qm_stop_reason { }; enum qm_state { - QM_INIT = 0, - QM_START, - QM_CLOSE, + QM_WORK = 0, QM_STOP, }; enum qp_state { - QP_INIT = 1, - QP_START, + QP_START = 1, QP_STOP, - QP_CLOSE, }; enum qm_hw_ver { @@ -160,6 +156,11 @@ enum qm_cap_bits { QM_SUPPORT_RPM, }; +struct qm_dev_alg { + u64 alg_msk; + const char *alg; +}; + struct dfx_diff_registers { u32 *regs; u32 reg_offset; @@ -265,6 +266,16 @@ struct hisi_qm_cap_info { u32 v3_val; }; +struct hisi_qm_cap_record { + u32 type; + u32 cap_val; +}; + +struct hisi_qm_cap_tables { + struct hisi_qm_cap_record *qm_cap_table; + struct hisi_qm_cap_record *dev_cap_table; +}; + struct hisi_qm_list { struct mutex lock; struct list_head list; @@ -365,7 +376,6 @@ struct hisi_qm { struct work_struct rst_work; struct work_struct cmd_process; - const char *algs; bool use_sva; resource_size_t phys_base; @@ -376,6 +386,8 @@ struct hisi_qm { u32 mb_qos; u32 type_rate; struct qm_err_isolate isolate_data; + + struct hisi_qm_cap_tables cap_tables; }; struct hisi_qp_status { @@ -563,6 +575,8 @@ void hisi_qm_regs_dump(struct seq_file *s, struct debugfs_regset32 *regset); u32 hisi_qm_get_hw_info(struct hisi_qm *qm, const struct hisi_qm_cap_info *info_table, u32 index, bool is_read); +int hisi_qm_set_algs(struct hisi_qm *qm, u64 alg_msk, const struct qm_dev_alg *dev_algs, + u32 dev_algs_size); /* Used by VFIO ACC live migration driver */ struct pci_driver *hisi_sec_get_pf_driver(void); diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index f2044d5a652b..87e3bedf8eb0 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -13,13 +13,13 @@ #define _LINUX_HRTIMER_H #include <linux/hrtimer_defs.h> -#include <linux/rbtree.h> +#include <linux/hrtimer_types.h> #include <linux/init.h> #include <linux/list.h> -#include <linux/percpu.h> +#include <linux/percpu-defs.h> +#include <linux/rbtree.h> #include <linux/seqlock.h> #include <linux/timer.h> -#include <linux/timerqueue.h> struct hrtimer_clock_base; struct hrtimer_cpu_base; @@ -60,14 +60,6 @@ enum hrtimer_mode { }; /* - * Return values for the callback function - */ -enum hrtimer_restart { - HRTIMER_NORESTART, /* Timer is not restarted */ - HRTIMER_RESTART, /* Timer must be restarted */ -}; - -/* * Values to track state of the timer * * Possible states: @@ -95,38 +87,6 @@ enum hrtimer_restart { #define HRTIMER_STATE_ENQUEUED 0x01 /** - * struct hrtimer - the basic hrtimer structure - * @node: timerqueue node, which also manages node.expires, - * the absolute expiry time in the hrtimers internal - * representation. The time is related to the clock on - * which the timer is based. Is setup by adding - * slack to the _softexpires value. For non range timers - * identical to _softexpires. - * @_softexpires: the absolute earliest expiry time of the hrtimer. - * The time which was given as expiry time when the timer - * was armed. - * @function: timer expiry callback function - * @base: pointer to the timer base (per cpu and per clock) - * @state: state information (See bit values above) - * @is_rel: Set if the timer was armed relative - * @is_soft: Set if hrtimer will be expired in soft interrupt context. - * @is_hard: Set if hrtimer will be expired in hard interrupt context - * even on RT. - * - * The hrtimer structure must be initialized by hrtimer_init() - */ -struct hrtimer { - struct timerqueue_node node; - ktime_t _softexpires; - enum hrtimer_restart (*function)(struct hrtimer *); - struct hrtimer_clock_base *base; - u8 state; - u8 is_rel; - u8 is_soft; - u8 is_hard; -}; - -/** * struct hrtimer_sleeper - simple sleeper structure * @timer: embedded timer structure * @task: task to wake up diff --git a/include/linux/hrtimer_types.h b/include/linux/hrtimer_types.h new file mode 100644 index 000000000000..ad66a3081735 --- /dev/null +++ b/include/linux/hrtimer_types.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_HRTIMER_TYPES_H +#define _LINUX_HRTIMER_TYPES_H + +#include <linux/types.h> +#include <linux/timerqueue_types.h> + +struct hrtimer_clock_base; + +/* + * Return values for the callback function + */ +enum hrtimer_restart { + HRTIMER_NORESTART, /* Timer is not restarted */ + HRTIMER_RESTART, /* Timer must be restarted */ +}; + +/** + * struct hrtimer - the basic hrtimer structure + * @node: timerqueue node, which also manages node.expires, + * the absolute expiry time in the hrtimers internal + * representation. The time is related to the clock on + * which the timer is based. Is setup by adding + * slack to the _softexpires value. For non range timers + * identical to _softexpires. + * @_softexpires: the absolute earliest expiry time of the hrtimer. + * The time which was given as expiry time when the timer + * was armed. + * @function: timer expiry callback function + * @base: pointer to the timer base (per cpu and per clock) + * @state: state information (See bit values above) + * @is_rel: Set if the timer was armed relative + * @is_soft: Set if hrtimer will be expired in soft interrupt context. + * @is_hard: Set if hrtimer will be expired in hard interrupt context + * even on RT. + * + * The hrtimer structure must be initialized by hrtimer_init() + */ +struct hrtimer { + struct timerqueue_node node; + ktime_t _softexpires; + enum hrtimer_restart (*function)(struct hrtimer *); + struct hrtimer_clock_base *base; + u8 state; + u8 is_rel; + u8 is_soft; + u8 is_hard; +}; + +#endif /* _LINUX_HRTIMER_TYPES_H */ diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 2b5e500bf093..83c4d060a559 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -172,11 +172,11 @@ #define IEEE80211_SN_MODULO (IEEE80211_MAX_SN + 1) -/* PV1 Layout 11ah 9.8.3.1 */ +/* PV1 Layout IEEE 802.11-2020 9.8.3.1 */ #define IEEE80211_PV1_FCTL_VERS 0x0003 #define IEEE80211_PV1_FCTL_FTYPE 0x001c #define IEEE80211_PV1_FCTL_STYPE 0x00e0 -#define IEEE80211_PV1_FCTL_TODS 0x0100 +#define IEEE80211_PV1_FCTL_FROMDS 0x0100 #define IEEE80211_PV1_FCTL_MOREFRAGS 0x0200 #define IEEE80211_PV1_FCTL_PM 0x0400 #define IEEE80211_PV1_FCTL_MOREDATA 0x0800 @@ -2720,6 +2720,7 @@ static inline bool ieee80211_he_capa_size_ok(const u8 *data, u8 len) #define IEEE80211_6GHZ_CTRL_REG_LPI_AP 0 #define IEEE80211_6GHZ_CTRL_REG_SP_AP 1 +#define IEEE80211_6GHZ_CTRL_REG_VLP_AP 2 /** * struct ieee80211_he_6ghz_oper - HE 6 GHz operation Information field diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 3028af87716e..c1645c86eed9 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -540,7 +540,7 @@ static inline int __vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci) struct vlan_ethhdr *veth = skb_vlan_eth_hdr(skb); if (!eth_type_vlan(veth->h_vlan_proto)) - return -EINVAL; + return -ENODATA; *vlan_tci = ntohs(veth->h_vlan_TCI); return 0; @@ -561,7 +561,7 @@ static inline int __vlan_hwaccel_get_tag(const struct sk_buff *skb, return 0; } else { *vlan_tci = 0; - return -EINVAL; + return -ENODATA; } } diff --git a/include/linux/indirect_call_wrapper.h b/include/linux/indirect_call_wrapper.h index c1c76a70a6ce..adb83a42a6b9 100644 --- a/include/linux/indirect_call_wrapper.h +++ b/include/linux/indirect_call_wrapper.h @@ -11,7 +11,7 @@ * @__VA_ARGS__: arguments for @f * * Avoid retpoline overhead for known builtin, checking @f vs each of them and - * eventually invoking directly the builtin function. The functions are check + * eventually invoking directly the builtin function. The functions are checked * in the given order. Fallback to the indirect call. */ #define INDIRECT_CALL_1(f, f1, ...) \ diff --git a/include/linux/intel-ish-client-if.h b/include/linux/intel-ish-client-if.h index f45f13304add..771622650247 100644 --- a/include/linux/intel-ish-client-if.h +++ b/include/linux/intel-ish-client-if.h @@ -94,6 +94,9 @@ int ishtp_cl_link(struct ishtp_cl *cl); void ishtp_cl_unlink(struct ishtp_cl *cl); int ishtp_cl_disconnect(struct ishtp_cl *cl); int ishtp_cl_connect(struct ishtp_cl *cl); +int ishtp_cl_establish_connection(struct ishtp_cl *cl, const guid_t *uuid, + int tx_size, int rx_size, bool reset); +void ishtp_cl_destroy_connection(struct ishtp_cl *cl, bool reset); int ishtp_cl_send(struct ishtp_cl *cl, uint8_t *buf, size_t length); int ishtp_cl_flush_queues(struct ishtp_cl *cl); int ishtp_cl_io_rb_recycle(struct ishtp_cl_rb *rb); diff --git a/include/linux/intel_tpmi.h b/include/linux/intel_tpmi.h index ee07393445f9..a3529b962be6 100644 --- a/include/linux/intel_tpmi.h +++ b/include/linux/intel_tpmi.h @@ -12,6 +12,19 @@ #define TPMI_MINOR_VERSION(val) FIELD_GET(GENMASK(4, 0), val) #define TPMI_MAJOR_VERSION(val) FIELD_GET(GENMASK(7, 5), val) +/* + * List of supported TMPI IDs. + * Some TMPI IDs are not used by Linux, so the numbers are not consecutive. + */ +enum intel_tpmi_id { + TPMI_ID_RAPL = 0, /* Running Average Power Limit */ + TPMI_ID_PEM = 1, /* Power and Perf excursion Monitor */ + TPMI_ID_UNCORE = 2, /* Uncore Frequency Scaling */ + TPMI_ID_SST = 5, /* Speed Select Technology */ + TPMI_CONTROL_ID = 0x80, /* Special ID for getting feature status */ + TPMI_INFO_ID = 0x81, /* Special ID for PCI BDF and Package ID information */ +}; + /** * struct intel_tpmi_plat_info - Platform information for a TPMI device instance * @package_id: CPU Package id @@ -32,7 +45,6 @@ struct intel_tpmi_plat_info { struct intel_tpmi_plat_info *tpmi_get_platform_data(struct auxiliary_device *auxdev); struct resource *tpmi_get_resource_at_index(struct auxiliary_device *auxdev, int index); int tpmi_get_resource_count(struct auxiliary_device *auxdev); - -int tpmi_get_feature_status(struct auxiliary_device *auxdev, int feature_id, int *locked, - int *disabled); +int tpmi_get_feature_status(struct auxiliary_device *auxdev, int feature_id, bool *read_blocked, + bool *write_blocked); #endif diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index aefb73eeeebf..68ed6697fece 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -6,71 +6,13 @@ #include <linux/xarray.h> #include <uapi/linux/io_uring.h> -enum io_uring_cmd_flags { - IO_URING_F_COMPLETE_DEFER = 1, - IO_URING_F_UNLOCKED = 2, - /* the request is executed from poll, it should not be freed */ - IO_URING_F_MULTISHOT = 4, - /* executed by io-wq */ - IO_URING_F_IOWQ = 8, - /* int's last bit, sign checks are usually faster than a bit test */ - IO_URING_F_NONBLOCK = INT_MIN, - - /* ctx state flags, for URING_CMD */ - IO_URING_F_SQE128 = (1 << 8), - IO_URING_F_CQE32 = (1 << 9), - IO_URING_F_IOPOLL = (1 << 10), - - /* set when uring wants to cancel a previously issued command */ - IO_URING_F_CANCEL = (1 << 11), - IO_URING_F_COMPAT = (1 << 12), -}; - -/* only top 8 bits of sqe->uring_cmd_flags for kernel internal use */ -#define IORING_URING_CMD_CANCELABLE (1U << 30) -#define IORING_URING_CMD_POLLED (1U << 31) - -struct io_uring_cmd { - struct file *file; - const struct io_uring_sqe *sqe; - union { - /* callback to defer completions to task context */ - void (*task_work_cb)(struct io_uring_cmd *cmd, unsigned); - /* used for polled completion */ - void *cookie; - }; - u32 cmd_op; - u32 flags; - u8 pdu[32]; /* available inline for free use */ -}; - -static inline const void *io_uring_sqe_cmd(const struct io_uring_sqe *sqe) -{ - return sqe->cmd; -} - #if defined(CONFIG_IO_URING) -int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, - struct iov_iter *iter, void *ioucmd); -void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, ssize_t res2, - unsigned issue_flags); -struct sock *io_uring_get_socket(struct file *file); void __io_uring_cancel(bool cancel_all); void __io_uring_free(struct task_struct *tsk); void io_uring_unreg_ringfd(void); const char *io_uring_get_opcode(u8 opcode); -void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd, - void (*task_work_cb)(struct io_uring_cmd *, unsigned), - unsigned flags); -/* users should follow semantics of IOU_F_TWQ_LAZY_WAKE */ -void io_uring_cmd_do_in_task_lazy(struct io_uring_cmd *ioucmd, - void (*task_work_cb)(struct io_uring_cmd *, unsigned)); - -static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, - void (*task_work_cb)(struct io_uring_cmd *, unsigned)) -{ - __io_uring_cmd_do_in_task(ioucmd, task_work_cb, 0); -} +int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags); +bool io_is_uring_fops(struct file *file); static inline void io_uring_files_cancel(void) { @@ -89,32 +31,7 @@ static inline void io_uring_free(struct task_struct *tsk) if (tsk->io_uring) __io_uring_free(tsk); } -int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags); -void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd, - unsigned int issue_flags); -struct task_struct *io_uring_cmd_get_task(struct io_uring_cmd *cmd); #else -static inline int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, - struct iov_iter *iter, void *ioucmd) -{ - return -EOPNOTSUPP; -} -static inline void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, - ssize_t ret2, unsigned issue_flags) -{ -} -static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, - void (*task_work_cb)(struct io_uring_cmd *, unsigned)) -{ -} -static inline void io_uring_cmd_do_in_task_lazy(struct io_uring_cmd *ioucmd, - void (*task_work_cb)(struct io_uring_cmd *, unsigned)) -{ -} -static inline struct sock *io_uring_get_socket(struct file *file) -{ - return NULL; -} static inline void io_uring_task_cancel(void) { } @@ -133,13 +50,9 @@ static inline int io_uring_cmd_sock(struct io_uring_cmd *cmd, { return -EOPNOTSUPP; } -static inline void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd, - unsigned int issue_flags) -{ -} -static inline struct task_struct *io_uring_cmd_get_task(struct io_uring_cmd *cmd) +static inline bool io_is_uring_fops(struct file *file) { - return NULL; + return false; } #endif diff --git a/include/linux/io_uring/cmd.h b/include/linux/io_uring/cmd.h new file mode 100644 index 000000000000..e453a997c060 --- /dev/null +++ b/include/linux/io_uring/cmd.h @@ -0,0 +1,77 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _LINUX_IO_URING_CMD_H +#define _LINUX_IO_URING_CMD_H + +#include <uapi/linux/io_uring.h> +#include <linux/io_uring_types.h> + +/* only top 8 bits of sqe->uring_cmd_flags for kernel internal use */ +#define IORING_URING_CMD_CANCELABLE (1U << 30) + +struct io_uring_cmd { + struct file *file; + const struct io_uring_sqe *sqe; + /* callback to defer completions to task context */ + void (*task_work_cb)(struct io_uring_cmd *cmd, unsigned); + u32 cmd_op; + u32 flags; + u8 pdu[32]; /* available inline for free use */ +}; + +static inline const void *io_uring_sqe_cmd(const struct io_uring_sqe *sqe) +{ + return sqe->cmd; +} + +#if defined(CONFIG_IO_URING) +int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, + struct iov_iter *iter, void *ioucmd); +void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, ssize_t res2, + unsigned issue_flags); +void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd, + void (*task_work_cb)(struct io_uring_cmd *, unsigned), + unsigned flags); + +void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd, + unsigned int issue_flags); + +#else +static inline int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, + struct iov_iter *iter, void *ioucmd) +{ + return -EOPNOTSUPP; +} +static inline void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, + ssize_t ret2, unsigned issue_flags) +{ +} +static inline void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd, + void (*task_work_cb)(struct io_uring_cmd *, unsigned), + unsigned flags) +{ +} +static inline void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd, + unsigned int issue_flags) +{ +} +#endif + +/* users must follow the IOU_F_TWQ_LAZY_WAKE semantics */ +static inline void io_uring_cmd_do_in_task_lazy(struct io_uring_cmd *ioucmd, + void (*task_work_cb)(struct io_uring_cmd *, unsigned)) +{ + __io_uring_cmd_do_in_task(ioucmd, task_work_cb, IOU_F_TWQ_LAZY_WAKE); +} + +static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, + void (*task_work_cb)(struct io_uring_cmd *, unsigned)) +{ + __io_uring_cmd_do_in_task(ioucmd, task_work_cb, 0); +} + +static inline struct task_struct *io_uring_cmd_get_task(struct io_uring_cmd *cmd) +{ + return cmd_to_io_kiocb(cmd)->task; +} + +#endif /* _LINUX_IO_URING_CMD_H */ diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 239a4f68801b..854ad67a5f70 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -7,6 +7,37 @@ #include <linux/llist.h> #include <uapi/linux/io_uring.h> +enum { + /* + * A hint to not wake right away but delay until there are enough of + * tw's queued to match the number of CQEs the task is waiting for. + * + * Must not be used wirh requests generating more than one CQE. + * It's also ignored unless IORING_SETUP_DEFER_TASKRUN is set. + */ + IOU_F_TWQ_LAZY_WAKE = 1, +}; + +enum io_uring_cmd_flags { + IO_URING_F_COMPLETE_DEFER = 1, + IO_URING_F_UNLOCKED = 2, + /* the request is executed from poll, it should not be freed */ + IO_URING_F_MULTISHOT = 4, + /* executed by io-wq */ + IO_URING_F_IOWQ = 8, + /* int's last bit, sign checks are usually faster than a bit test */ + IO_URING_F_NONBLOCK = INT_MIN, + + /* ctx state flags, for URING_CMD */ + IO_URING_F_SQE128 = (1 << 8), + IO_URING_F_CQE32 = (1 << 9), + IO_URING_F_IOPOLL = (1 << 10), + + /* set when uring wants to cancel a previously issued command */ + IO_URING_F_CANCEL = (1 << 11), + IO_URING_F_COMPAT = (1 << 12), +}; + struct io_wq_work_node { struct io_wq_work_node *next; }; @@ -358,9 +389,6 @@ struct io_ring_ctx { struct wait_queue_head rsrc_quiesce_wq; unsigned rsrc_quiesce; - #if defined(CONFIG_UNIX) - struct socket *ring_sock; - #endif /* hashed buffered write serialization */ struct io_wq_hash *hash_map; diff --git a/include/linux/iosys-map.h b/include/linux/iosys-map.h index 1b06d074ade0..e3649a6563dd 100644 --- a/include/linux/iosys-map.h +++ b/include/linux/iosys-map.h @@ -168,9 +168,9 @@ struct iosys_map { * about the use of uninitialized variable. */ #define IOSYS_MAP_INIT_OFFSET(map_, offset_) ({ \ - struct iosys_map copy = *map_; \ - iosys_map_incr(©, offset_); \ - copy; \ + struct iosys_map copy_ = *map_; \ + iosys_map_incr(©_, offset_); \ + copy_; \ }) /** @@ -391,14 +391,14 @@ static inline void iosys_map_memset(struct iosys_map *dst, size_t offset, * Returns: * The value read from the mapping. */ -#define iosys_map_rd(map__, offset__, type__) ({ \ - type__ val; \ - if ((map__)->is_iomem) { \ - __iosys_map_rd_io(val, (map__)->vaddr_iomem + (offset__), type__);\ - } else { \ - __iosys_map_rd_sys(val, (map__)->vaddr + (offset__), type__); \ - } \ - val; \ +#define iosys_map_rd(map__, offset__, type__) ({ \ + type__ val_; \ + if ((map__)->is_iomem) { \ + __iosys_map_rd_io(val_, (map__)->vaddr_iomem + (offset__), type__); \ + } else { \ + __iosys_map_rd_sys(val_, (map__)->vaddr + (offset__), type__); \ + } \ + val_; \ }) /** @@ -413,13 +413,13 @@ static inline void iosys_map_memset(struct iosys_map *dst, size_t offset, * or if pointer may be unaligned (and problematic for the architecture * supported), use iosys_map_memcpy_to() */ -#define iosys_map_wr(map__, offset__, type__, val__) ({ \ - type__ val = (val__); \ - if ((map__)->is_iomem) { \ - __iosys_map_wr_io(val, (map__)->vaddr_iomem + (offset__), type__);\ - } else { \ - __iosys_map_wr_sys(val, (map__)->vaddr + (offset__), type__); \ - } \ +#define iosys_map_wr(map__, offset__, type__, val__) ({ \ + type__ val_ = (val__); \ + if ((map__)->is_iomem) { \ + __iosys_map_wr_io(val_, (map__)->vaddr_iomem + (offset__), type__); \ + } else { \ + __iosys_map_wr_sys(val_, (map__)->vaddr + (offset__), type__); \ + } \ }) /** @@ -485,9 +485,9 @@ static inline void iosys_map_memset(struct iosys_map *dst, size_t offset, * The value read from the mapping. */ #define iosys_map_rd_field(map__, struct_offset__, struct_type__, field__) ({ \ - struct_type__ *s; \ + struct_type__ *s_; \ iosys_map_rd(map__, struct_offset__ + offsetof(struct_type__, field__), \ - typeof(s->field__)); \ + typeof(s_->field__)); \ }) /** @@ -508,9 +508,9 @@ static inline void iosys_map_memset(struct iosys_map *dst, size_t offset, * usage and memory layout. */ #define iosys_map_wr_field(map__, struct_offset__, struct_type__, field__, val__) ({ \ - struct_type__ *s; \ + struct_type__ *s_; \ iosys_map_wr(map__, struct_offset__ + offsetof(struct_type__, field__), \ - typeof(s->field__), val__); \ + typeof(s_->field__), val__); \ }) #endif /* __IOSYS_MAP_H__ */ diff --git a/include/linux/ipc.h b/include/linux/ipc.h index e1c9eea6015b..9b1434247aab 100644 --- a/include/linux/ipc.h +++ b/include/linux/ipc.h @@ -2,7 +2,7 @@ #ifndef _LINUX_IPC_H #define _LINUX_IPC_H -#include <linux/spinlock.h> +#include <linux/spinlock_types.h> #include <linux/uidgid.h> #include <linux/rhashtable-types.h> #include <uapi/linux/ipc.h> diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h index 8cd11a223260..136f2980cba3 100644 --- a/include/linux/irq_work.h +++ b/include/linux/irq_work.h @@ -66,6 +66,9 @@ void irq_work_sync(struct irq_work *work); void irq_work_run(void); bool irq_work_needs_cpu(void); void irq_work_single(void *arg); + +void arch_irq_work_raise(void); + #else static inline bool irq_work_needs_cpu(void) { return false; } static inline void irq_work_run(void) { } diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 2b665c32f5fe..147feebd508c 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -12,6 +12,7 @@ #ifndef _LINUX_TRACE_IRQFLAGS_H #define _LINUX_TRACE_IRQFLAGS_H +#include <linux/irqflags_types.h> #include <linux/typecheck.h> #include <linux/cleanup.h> #include <asm/irqflags.h> @@ -34,19 +35,6 @@ #ifdef CONFIG_TRACE_IRQFLAGS -/* Per-task IRQ trace events information. */ -struct irqtrace_events { - unsigned int irq_events; - unsigned long hardirq_enable_ip; - unsigned long hardirq_disable_ip; - unsigned int hardirq_enable_event; - unsigned int hardirq_disable_event; - unsigned long softirq_disable_ip; - unsigned long softirq_enable_ip; - unsigned int softirq_disable_event; - unsigned int softirq_enable_event; -}; - DECLARE_PER_CPU(int, hardirqs_enabled); DECLARE_PER_CPU(int, hardirq_context); diff --git a/include/linux/irqflags_types.h b/include/linux/irqflags_types.h new file mode 100644 index 000000000000..c13f0d915097 --- /dev/null +++ b/include/linux/irqflags_types.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_IRQFLAGS_TYPES_H +#define _LINUX_IRQFLAGS_TYPES_H + +#ifdef CONFIG_TRACE_IRQFLAGS + +/* Per-task IRQ trace events information. */ +struct irqtrace_events { + unsigned int irq_events; + unsigned long hardirq_enable_ip; + unsigned long hardirq_disable_ip; + unsigned int hardirq_enable_event; + unsigned int hardirq_disable_event; + unsigned long softirq_disable_ip; + unsigned long softirq_enable_ip; + unsigned int softirq_disable_event; + unsigned int softirq_enable_event; +}; + +#endif + +#endif /* _LINUX_IRQFLAGS_TYPES_H */ diff --git a/include/linux/ism.h b/include/linux/ism.h index 9a4c204df3da..5428edd90982 100644 --- a/include/linux/ism.h +++ b/include/linux/ism.h @@ -86,7 +86,6 @@ int ism_register_dmb(struct ism_dev *dev, struct ism_dmb *dmb, int ism_unregister_dmb(struct ism_dev *dev, struct ism_dmb *dmb); int ism_move(struct ism_dev *dev, u64 dmb_tok, unsigned int idx, bool sf, unsigned int offset, void *data, unsigned int size); -u8 *ism_get_seid(void); const struct smcd_ops *ism_get_smcd_ops(void); diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index beb30719ee16..971f3e826e15 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -756,11 +756,6 @@ struct journal_s unsigned long j_flags; /** - * @j_atomic_flags: Atomic journaling state flags. - */ - unsigned long j_atomic_flags; - - /** * @j_errno: * * Is there an outstanding uncleared error on the journal (from a prior @@ -999,6 +994,13 @@ struct journal_s struct block_device *j_fs_dev; /** + * @j_fs_dev_wb_err: + * + * Records the errseq of the client fs's backing block device. + */ + errseq_t j_fs_dev_wb_err; + + /** * @j_total_len: Total maximum capacity of the journal region on disk. */ unsigned int j_total_len; @@ -1400,12 +1402,6 @@ JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit, FAST_COMMIT) JBD2_JOURNAL_FLUSH_ZEROOUT) /* - * Journal atomic flag definitions - */ -#define JBD2_CHECKPOINT_IO_ERROR 0x001 /* Detect io error while writing - * buffer back to disk */ - -/* * Function declarations for the journaling transaction and buffer * management */ @@ -1698,6 +1694,25 @@ static inline void jbd2_journal_abort_handle(handle_t *handle) handle->h_aborted = 1; } +static inline void jbd2_init_fs_dev_write_error(journal_t *journal) +{ + struct address_space *mapping = journal->j_fs_dev->bd_inode->i_mapping; + + /* + * Save the original wb_err value of client fs's bdev mapping which + * could be used to detect the client fs's metadata async write error. + */ + errseq_check_and_advance(&mapping->wb_err, &journal->j_fs_dev_wb_err); +} + +static inline int jbd2_check_fs_dev_write_error(journal_t *journal) +{ + struct address_space *mapping = journal->j_fs_dev->bd_inode->i_mapping; + + return errseq_check(&mapping->wb_err, + READ_ONCE(journal->j_fs_dev_wb_err)); +} + #endif /* __KERNEL__ */ /* Comparison functions for transaction IDs: perform comparisons using diff --git a/include/linux/kfence.h b/include/linux/kfence.h index 401af4757514..88100cc9caba 100644 --- a/include/linux/kfence.h +++ b/include/linux/kfence.h @@ -223,6 +223,8 @@ bool __kfence_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *sla #else /* CONFIG_KFENCE */ +#define kfence_sample_interval (0) + static inline bool is_kfence_address(const void *addr) { return false; } static inline void kfence_alloc_pool_and_metadata(void) { } static inline void kfence_init(void) { } diff --git a/include/linux/kmsan_types.h b/include/linux/kmsan_types.h index 8bfa6c98176d..929287981afe 100644 --- a/include/linux/kmsan_types.h +++ b/include/linux/kmsan_types.h @@ -9,6 +9,8 @@ #ifndef _LINUX_KMSAN_TYPES_H #define _LINUX_KMSAN_TYPES_H +#include <linux/types.h> + /* These constants are defined in the MSan LLVM instrumentation pass. */ #define KMSAN_RETVAL_SIZE 800 #define KMSAN_PARAM_SIZE 800 diff --git a/include/linux/ktime.h b/include/linux/ktime.h index 73f20deb497d..3a4e723eae0f 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -21,12 +21,10 @@ #ifndef _LINUX_KTIME_H #define _LINUX_KTIME_H -#include <linux/time.h> -#include <linux/jiffies.h> #include <asm/bug.h> - -/* Nanosecond scalar representation for kernel time values */ -typedef s64 ktime_t; +#include <linux/jiffies.h> +#include <linux/time.h> +#include <linux/types.h> /** * ktime_set - Set a ktime_t variable from a seconds/nanoseconds value diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 4944136efaa2..7e7fd25b09b3 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -80,8 +80,8 @@ /* Two fragments for cross MMIO pages. */ #define KVM_MAX_MMIO_FRAGMENTS 2 -#ifndef KVM_ADDRESS_SPACE_NUM -#define KVM_ADDRESS_SPACE_NUM 1 +#ifndef KVM_MAX_NR_ADDRESS_SPACES +#define KVM_MAX_NR_ADDRESS_SPACES 1 #endif /* @@ -253,9 +253,10 @@ bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu); #endif -#ifdef KVM_ARCH_WANT_MMU_NOTIFIER +#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER union kvm_mmu_notifier_arg { pte_t pte; + unsigned long attributes; }; struct kvm_gfn_range { @@ -588,8 +589,20 @@ struct kvm_memory_slot { u32 flags; short id; u16 as_id; + +#ifdef CONFIG_KVM_PRIVATE_MEM + struct { + struct file __rcu *file; + pgoff_t pgoff; + } gmem; +#endif }; +static inline bool kvm_slot_can_be_private(const struct kvm_memory_slot *slot) +{ + return slot && (slot->flags & KVM_MEM_GUEST_MEMFD); +} + static inline bool kvm_slot_dirty_track_enabled(const struct kvm_memory_slot *slot) { return slot->flags & KVM_MEM_LOG_DIRTY_PAGES; @@ -677,13 +690,29 @@ bool kvm_arch_irqchip_in_kernel(struct kvm *kvm); #define KVM_MEM_SLOTS_NUM SHRT_MAX #define KVM_USER_MEM_SLOTS (KVM_MEM_SLOTS_NUM - KVM_INTERNAL_MEM_SLOTS) -#ifndef __KVM_VCPU_MULTIPLE_ADDRESS_SPACE +#if KVM_MAX_NR_ADDRESS_SPACES == 1 +static inline int kvm_arch_nr_memslot_as_ids(struct kvm *kvm) +{ + return KVM_MAX_NR_ADDRESS_SPACES; +} + static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu) { return 0; } #endif +/* + * Arch code must define kvm_arch_has_private_mem if support for private memory + * is enabled. + */ +#if !defined(kvm_arch_has_private_mem) && !IS_ENABLED(CONFIG_KVM_PRIVATE_MEM) +static inline bool kvm_arch_has_private_mem(struct kvm *kvm) +{ + return false; +} +#endif + struct kvm_memslots { u64 generation; atomic_long_t last_used_slot; @@ -721,9 +750,9 @@ struct kvm { struct mm_struct *mm; /* userspace tied to this vm */ unsigned long nr_memslot_pages; /* The two memslot sets - active and inactive (per address space) */ - struct kvm_memslots __memslots[KVM_ADDRESS_SPACE_NUM][2]; + struct kvm_memslots __memslots[KVM_MAX_NR_ADDRESS_SPACES][2]; /* The current active memslot set for each address space */ - struct kvm_memslots __rcu *memslots[KVM_ADDRESS_SPACE_NUM]; + struct kvm_memslots __rcu *memslots[KVM_MAX_NR_ADDRESS_SPACES]; struct xarray vcpu_array; /* * Protected by slots_lock, but can be read outside if an @@ -753,7 +782,7 @@ struct kvm { struct list_head vm_list; struct mutex lock; struct kvm_io_bus __rcu *buses[KVM_NR_BUSES]; -#ifdef CONFIG_HAVE_KVM_EVENTFD +#ifdef CONFIG_HAVE_KVM_IRQCHIP struct { spinlock_t lock; struct list_head items; @@ -761,8 +790,8 @@ struct kvm { struct list_head resampler_list; struct mutex resampler_lock; } irqfds; - struct list_head ioeventfds; #endif + struct list_head ioeventfds; struct kvm_vm_stat stat; struct kvm_arch arch; refcount_t users_count; @@ -778,17 +807,16 @@ struct kvm { * Update side is protected by irq_lock. */ struct kvm_irq_routing_table __rcu *irq_routing; -#endif -#ifdef CONFIG_HAVE_KVM_IRQFD + struct hlist_head irq_ack_notifier_list; #endif -#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) +#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER struct mmu_notifier mmu_notifier; unsigned long mmu_invalidate_seq; long mmu_invalidate_in_progress; - unsigned long mmu_invalidate_range_start; - unsigned long mmu_invalidate_range_end; + gfn_t mmu_invalidate_range_start; + gfn_t mmu_invalidate_range_end; #endif struct list_head devices; u64 manual_dirty_log_protect; @@ -807,6 +835,10 @@ struct kvm { #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER struct notifier_block pm_notifier; #endif +#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES + /* Protected by slots_locks (for writes) and RCU (for reads) */ + struct xarray mem_attr_array; +#endif char stats_id[KVM_STATS_NAME_SIZE]; }; @@ -965,7 +997,7 @@ static inline void kvm_arch_post_irq_routing_update(struct kvm *kvm) } #endif -#ifdef CONFIG_HAVE_KVM_IRQFD +#ifdef CONFIG_HAVE_KVM_IRQCHIP int kvm_irqfd_init(void); void kvm_irqfd_exit(void); #else @@ -989,7 +1021,7 @@ void kvm_put_kvm_no_destroy(struct kvm *kvm); static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id) { - as_id = array_index_nospec(as_id, KVM_ADDRESS_SPACE_NUM); + as_id = array_index_nospec(as_id, KVM_MAX_NR_ADDRESS_SPACES); return srcu_dereference_check(kvm->memslots[as_id], &kvm->srcu, lockdep_is_held(&kvm->slots_lock) || !refcount_read(&kvm->users_count)); @@ -1146,9 +1178,9 @@ enum kvm_mr_change { }; int kvm_set_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem); + const struct kvm_userspace_memory_region2 *mem); int __kvm_set_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem); + const struct kvm_userspace_memory_region2 *mem); void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot); void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen); int kvm_arch_prepare_memory_region(struct kvm *kvm, @@ -1392,10 +1424,10 @@ void kvm_mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc); void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc); #endif -void kvm_mmu_invalidate_begin(struct kvm *kvm, unsigned long start, - unsigned long end); -void kvm_mmu_invalidate_end(struct kvm *kvm, unsigned long start, - unsigned long end); +void kvm_mmu_invalidate_begin(struct kvm *kvm); +void kvm_mmu_invalidate_range_add(struct kvm *kvm, gfn_t start, gfn_t end); +void kvm_mmu_invalidate_end(struct kvm *kvm); +bool kvm_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range); long kvm_arch_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); @@ -1947,7 +1979,7 @@ extern const struct _kvm_stats_desc kvm_vm_stats_desc[]; extern const struct kvm_stats_header kvm_vcpu_stats_header; extern const struct _kvm_stats_desc kvm_vcpu_stats_desc[]; -#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) +#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq) { if (unlikely(kvm->mmu_invalidate_in_progress)) @@ -1970,9 +2002,9 @@ static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq) return 0; } -static inline int mmu_invalidate_retry_hva(struct kvm *kvm, +static inline int mmu_invalidate_retry_gfn(struct kvm *kvm, unsigned long mmu_seq, - unsigned long hva) + gfn_t gfn) { lockdep_assert_held(&kvm->mmu_lock); /* @@ -1981,10 +2013,20 @@ static inline int mmu_invalidate_retry_hva(struct kvm *kvm, * that might be being invalidated. Note that it may include some false * positives, due to shortcuts when handing concurrent invalidations. */ - if (unlikely(kvm->mmu_invalidate_in_progress) && - hva >= kvm->mmu_invalidate_range_start && - hva < kvm->mmu_invalidate_range_end) - return 1; + if (unlikely(kvm->mmu_invalidate_in_progress)) { + /* + * Dropping mmu_lock after bumping mmu_invalidate_in_progress + * but before updating the range is a KVM bug. + */ + if (WARN_ON_ONCE(kvm->mmu_invalidate_range_start == INVALID_GPA || + kvm->mmu_invalidate_range_end == INVALID_GPA)) + return 1; + + if (gfn >= kvm->mmu_invalidate_range_start && + gfn < kvm->mmu_invalidate_range_end) + return 1; + } + if (kvm->mmu_invalidate_seq != mmu_seq) return 1; return 0; @@ -2013,12 +2055,10 @@ static inline void kvm_free_irq_routing(struct kvm *kvm) {} int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi); -#ifdef CONFIG_HAVE_KVM_EVENTFD - void kvm_eventfd_init(struct kvm *kvm); int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args); -#ifdef CONFIG_HAVE_KVM_IRQFD +#ifdef CONFIG_HAVE_KVM_IRQCHIP int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args); void kvm_irqfd_release(struct kvm *kvm); bool kvm_notify_irqfd_resampler(struct kvm *kvm, @@ -2039,31 +2079,7 @@ static inline bool kvm_notify_irqfd_resampler(struct kvm *kvm, { return false; } -#endif - -#else - -static inline void kvm_eventfd_init(struct kvm *kvm) {} - -static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args) -{ - return -EINVAL; -} - -static inline void kvm_irqfd_release(struct kvm *kvm) {} - -#ifdef CONFIG_HAVE_KVM_IRQCHIP -static inline void kvm_irq_routing_update(struct kvm *kvm) -{ -} -#endif - -static inline int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) -{ - return -ENOSYS; -} - -#endif /* CONFIG_HAVE_KVM_EVENTFD */ +#endif /* CONFIG_HAVE_KVM_IRQCHIP */ void kvm_arch_irq_routing_update(struct kvm *kvm); @@ -2318,4 +2334,57 @@ static inline void kvm_account_pgtable_pages(void *virt, int nr) /* Max number of entries allowed for each kvm dirty ring */ #define KVM_DIRTY_RING_MAX_ENTRIES 65536 +static inline void kvm_prepare_memory_fault_exit(struct kvm_vcpu *vcpu, + gpa_t gpa, gpa_t size, + bool is_write, bool is_exec, + bool is_private) +{ + vcpu->run->exit_reason = KVM_EXIT_MEMORY_FAULT; + vcpu->run->memory_fault.gpa = gpa; + vcpu->run->memory_fault.size = size; + + /* RWX flags are not (yet) defined or communicated to userspace. */ + vcpu->run->memory_fault.flags = 0; + if (is_private) + vcpu->run->memory_fault.flags |= KVM_MEMORY_EXIT_FLAG_PRIVATE; +} + +#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES +static inline unsigned long kvm_get_memory_attributes(struct kvm *kvm, gfn_t gfn) +{ + return xa_to_value(xa_load(&kvm->mem_attr_array, gfn)); +} + +bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end, + unsigned long attrs); +bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm, + struct kvm_gfn_range *range); +bool kvm_arch_post_set_memory_attributes(struct kvm *kvm, + struct kvm_gfn_range *range); + +static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn) +{ + return IS_ENABLED(CONFIG_KVM_PRIVATE_MEM) && + kvm_get_memory_attributes(kvm, gfn) & KVM_MEMORY_ATTRIBUTE_PRIVATE; +} +#else +static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn) +{ + return false; +} +#endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */ + +#ifdef CONFIG_KVM_PRIVATE_MEM +int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot, + gfn_t gfn, kvm_pfn_t *pfn, int *max_order); +#else +static inline int kvm_gmem_get_pfn(struct kvm *kvm, + struct kvm_memory_slot *slot, gfn_t gfn, + kvm_pfn_t *pfn, int *max_order) +{ + KVM_BUG_ON(1, kvm); + return -EIO; +} +#endif /* CONFIG_KVM_PRIVATE_MEM */ + #endif diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index 6f4737d5046a..9d1f7835d8c1 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -6,6 +6,7 @@ struct kvm; struct kvm_async_pf; struct kvm_device_ops; +struct kvm_gfn_range; struct kvm_interrupt; struct kvm_irq_routing_table; struct kvm_memory_slot; diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h index 7303b4bc2ce0..287f590ed56b 100644 --- a/include/linux/linkmode.h +++ b/include/linux/linkmode.h @@ -10,6 +10,11 @@ static inline void linkmode_zero(unsigned long *dst) bitmap_zero(dst, __ETHTOOL_LINK_MODE_MASK_NBITS); } +static inline void linkmode_fill(unsigned long *dst) +{ + bitmap_fill(dst, __ETHTOOL_LINK_MODE_MASK_NBITS); +} + static inline void linkmode_copy(unsigned long *dst, const unsigned long *src) { bitmap_copy(dst, src, __ETHTOOL_LINK_MODE_MASK_NBITS); diff --git a/include/linux/list.h b/include/linux/list.h index 1837caedf723..059aa1fff41e 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -1119,6 +1119,26 @@ static inline void hlist_move_list(struct hlist_head *old, old->first = NULL; } +/** + * hlist_splice_init() - move all entries from one list to another + * @from: hlist_head from which entries will be moved + * @last: last entry on the @from list + * @to: hlist_head to which entries will be moved + * + * @to can be empty, @from must contain at least @last. + */ +static inline void hlist_splice_init(struct hlist_head *from, + struct hlist_node *last, + struct hlist_head *to) +{ + if (to->first) + to->first->pprev = &last->next; + last->next = to->first; + to->first = from->first; + from->first->pprev = &to->first; + from->first = NULL; +} + #define hlist_entry(ptr, type, member) container_of(ptr,type,member) #define hlist_for_each(pos, head) \ diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index dc2844b071c2..08b0d1d9d78b 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -82,63 +82,6 @@ struct lock_chain { u64 chain_key; }; -#define MAX_LOCKDEP_KEYS_BITS 13 -#define MAX_LOCKDEP_KEYS (1UL << MAX_LOCKDEP_KEYS_BITS) -#define INITIAL_CHAIN_KEY -1 - -struct held_lock { - /* - * One-way hash of the dependency chain up to this point. We - * hash the hashes step by step as the dependency chain grows. - * - * We use it for dependency-caching and we skip detection - * passes and dependency-updates if there is a cache-hit, so - * it is absolutely critical for 100% coverage of the validator - * to have a unique key value for every unique dependency path - * that can occur in the system, to make a unique hash value - * as likely as possible - hence the 64-bit width. - * - * The task struct holds the current hash value (initialized - * with zero), here we store the previous hash value: - */ - u64 prev_chain_key; - unsigned long acquire_ip; - struct lockdep_map *instance; - struct lockdep_map *nest_lock; -#ifdef CONFIG_LOCK_STAT - u64 waittime_stamp; - u64 holdtime_stamp; -#endif - /* - * class_idx is zero-indexed; it points to the element in - * lock_classes this held lock instance belongs to. class_idx is in - * the range from 0 to (MAX_LOCKDEP_KEYS-1) inclusive. - */ - unsigned int class_idx:MAX_LOCKDEP_KEYS_BITS; - /* - * The lock-stack is unified in that the lock chains of interrupt - * contexts nest ontop of process context chains, but we 'separate' - * the hashes by starting with 0 if we cross into an interrupt - * context, and we also keep do not add cross-context lock - * dependencies - the lock usage graph walking covers that area - * anyway, and we'd just unnecessarily increase the number of - * dependencies otherwise. [Note: hardirq and softirq contexts - * are separated from each other too.] - * - * The following field is used to detect when we cross into an - * interrupt context: - */ - unsigned int irq_context:2; /* bit 0 - soft, bit 1 - hard */ - unsigned int trylock:1; /* 16 bits */ - - unsigned int read:2; /* see lock_acquire() comment */ - unsigned int check:1; /* see lock_acquire() comment */ - unsigned int hardirqs_off:1; - unsigned int sync:1; - unsigned int references:11; /* 32 bits */ - unsigned int pin_count; -}; - /* * Initialization, self-test and debugging-output methods: */ diff --git a/include/linux/lockdep_types.h b/include/linux/lockdep_types.h index 857d785e89e6..70d30d40ea4a 100644 --- a/include/linux/lockdep_types.h +++ b/include/linux/lockdep_types.h @@ -198,6 +198,63 @@ struct lockdep_map { struct pin_cookie { unsigned int val; }; +#define MAX_LOCKDEP_KEYS_BITS 13 +#define MAX_LOCKDEP_KEYS (1UL << MAX_LOCKDEP_KEYS_BITS) +#define INITIAL_CHAIN_KEY -1 + +struct held_lock { + /* + * One-way hash of the dependency chain up to this point. We + * hash the hashes step by step as the dependency chain grows. + * + * We use it for dependency-caching and we skip detection + * passes and dependency-updates if there is a cache-hit, so + * it is absolutely critical for 100% coverage of the validator + * to have a unique key value for every unique dependency path + * that can occur in the system, to make a unique hash value + * as likely as possible - hence the 64-bit width. + * + * The task struct holds the current hash value (initialized + * with zero), here we store the previous hash value: + */ + u64 prev_chain_key; + unsigned long acquire_ip; + struct lockdep_map *instance; + struct lockdep_map *nest_lock; +#ifdef CONFIG_LOCK_STAT + u64 waittime_stamp; + u64 holdtime_stamp; +#endif + /* + * class_idx is zero-indexed; it points to the element in + * lock_classes this held lock instance belongs to. class_idx is in + * the range from 0 to (MAX_LOCKDEP_KEYS-1) inclusive. + */ + unsigned int class_idx:MAX_LOCKDEP_KEYS_BITS; + /* + * The lock-stack is unified in that the lock chains of interrupt + * contexts nest ontop of process context chains, but we 'separate' + * the hashes by starting with 0 if we cross into an interrupt + * context, and we also keep do not add cross-context lock + * dependencies - the lock usage graph walking covers that area + * anyway, and we'd just unnecessarily increase the number of + * dependencies otherwise. [Note: hardirq and softirq contexts + * are separated from each other too.] + * + * The following field is used to detect when we cross into an + * interrupt context: + */ + unsigned int irq_context:2; /* bit 0 - soft, bit 1 - hard */ + unsigned int trylock:1; /* 16 bits */ + + unsigned int read:2; /* see lock_acquire() comment */ + unsigned int check:1; /* see lock_acquire() comment */ + unsigned int hardirqs_off:1; + unsigned int sync:1; + unsigned int references:11; /* 32 bits */ + unsigned int pin_count; +}; + #else /* !CONFIG_LOCKDEP */ /* diff --git a/include/linux/mdio.h b/include/linux/mdio.h index 007fd9c3e4b6..79ceee3c8673 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -38,6 +38,7 @@ struct mdio_device { /* Bus address of the MDIO device (0-31) */ int addr; int flags; + int reset_state; struct gpio_desc *reset_gpio; struct reset_control *reset_ctrl; unsigned int reset_assert_delay; diff --git a/include/linux/mii_timestamper.h b/include/linux/mii_timestamper.h index fa940bbaf8ae..26b04f73f214 100644 --- a/include/linux/mii_timestamper.h +++ b/include/linux/mii_timestamper.h @@ -9,6 +9,7 @@ #include <linux/device.h> #include <linux/ethtool.h> #include <linux/skbuff.h> +#include <linux/net_tstamp.h> struct phy_device; @@ -51,7 +52,8 @@ struct mii_timestamper { struct sk_buff *skb, int type); int (*hwtstamp)(struct mii_timestamper *mii_ts, - struct ifreq *ifreq); + struct kernel_hwtstamp_config *kernel_config, + struct netlink_ext_ack *extack); void (*link_state)(struct mii_timestamper *mii_ts, struct phy_device *phydev); diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 820bca965fb6..01275c6e8468 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -918,7 +918,7 @@ static inline u8 get_cqe_tls_offload(struct mlx5_cqe64 *cqe) return (cqe->tls_outer_l3_tunneled >> 3) & 0x3; } -static inline bool cqe_has_vlan(struct mlx5_cqe64 *cqe) +static inline bool cqe_has_vlan(const struct mlx5_cqe64 *cqe) { return cqe->l4_l3_hdr_type & 0x1; } diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index d2b8d4a74a30..8c55ff351e5f 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -150,6 +150,7 @@ enum { MLX5_REG_MTPPSE = 0x9054, MLX5_REG_MTUTC = 0x9055, MLX5_REG_MPEGC = 0x9056, + MLX5_REG_MPIR = 0x9059, MLX5_REG_MCQS = 0x9060, MLX5_REG_MCQI = 0x9061, MLX5_REG_MCC = 0x9062, @@ -678,6 +679,8 @@ struct mlx5e_resources { struct mlx5_td td; u32 mkey; struct mlx5_sq_bfreg bfreg; +#define MLX5_MAX_NUM_TC 8 + u32 tisn[MLX5_MAX_PORTS][MLX5_MAX_NUM_TC]; } hw_objs; struct net_device *uplink_netdev; struct mutex uplink_netdev_lock; @@ -688,6 +691,7 @@ enum mlx5_sw_icm_type { MLX5_SW_ICM_TYPE_STEERING, MLX5_SW_ICM_TYPE_HEADER_MODIFY, MLX5_SW_ICM_TYPE_HEADER_MODIFY_PATTERN, + MLX5_SW_ICM_TYPE_SW_ENCAP, }; #define MLX5_MAX_RESERVED_GIDS 8 diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index 950d2431a53c..df73a2ccc9af 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -7,6 +7,7 @@ #define _MLX5_ESWITCH_ #include <linux/mlx5/driver.h> +#include <linux/mlx5/vport.h> #include <net/devlink.h> #define MLX5_ESWITCH_MANAGER(mdev) MLX5_CAP_GEN(mdev, eswitch_manager) @@ -210,4 +211,11 @@ static inline bool is_mdev_switchdev_mode(struct mlx5_core_dev *dev) return mlx5_eswitch_mode(dev) == MLX5_ESWITCH_OFFLOADS; } +/* The returned number is valid only when the dev is eswitch manager. */ +static inline u16 mlx5_eswitch_manager_vport(struct mlx5_core_dev *dev) +{ + return mlx5_core_is_ecpf_esw_manager(dev) ? + MLX5_VPORT_ECPF : MLX5_VPORT_PF; +} + #endif diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 3f7b664d625b..7235f3eaed8b 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -435,7 +435,7 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 flow_table_modify[0x1]; u8 reformat[0x1]; u8 decap[0x1]; - u8 reserved_at_9[0x1]; + u8 reset_root_to_default[0x1]; u8 pop_vlan[0x1]; u8 push_vlan[0x1]; u8 reserved_at_c[0x1]; @@ -1193,7 +1193,8 @@ struct mlx5_ifc_device_mem_cap_bits { u8 log_sw_icm_alloc_granularity[0x6]; u8 log_steering_sw_icm_size[0x8]; - u8 reserved_at_120[0x18]; + u8 log_indirect_encap_sw_icm_size[0x8]; + u8 reserved_at_128[0x10]; u8 log_header_modify_pattern_sw_icm_size[0x8]; u8 header_modify_sw_icm_start_address[0x40]; @@ -1204,7 +1205,11 @@ struct mlx5_ifc_device_mem_cap_bits { u8 memic_operations[0x20]; - u8 reserved_at_220[0x5e0]; + u8 reserved_at_220[0x20]; + + u8 indirect_encap_sw_icm_start_address[0x40]; + + u8 reserved_at_280[0x580]; }; struct mlx5_ifc_device_event_cap_bits { @@ -1801,7 +1806,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 disable_local_lb_uc[0x1]; u8 disable_local_lb_mc[0x1]; u8 log_min_hairpin_wq_data_sz[0x5]; - u8 reserved_at_3e8[0x2]; + u8 reserved_at_3e8[0x1]; + u8 silent_mode[0x1]; u8 vhca_state[0x1]; u8 log_max_vlan_list[0x5]; u8 reserved_at_3f0[0x3]; @@ -1818,7 +1824,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_460[0x1]; u8 ats[0x1]; - u8 reserved_at_462[0x1]; + u8 cross_vhca_rqt[0x1]; u8 log_max_uctx[0x5]; u8 reserved_at_468[0x1]; u8 crypto[0x1]; @@ -1943,6 +1949,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { enum { MLX5_CROSS_VHCA_OBJ_TO_OBJ_SUPPORTED_LOCAL_FLOW_TABLE_TO_REMOTE_FLOW_TABLE_MISS = 0x80000, + MLX5_CROSS_VHCA_OBJ_TO_OBJ_SUPPORTED_LOCAL_FLOW_TABLE_ROOT_TO_REMOTE_FLOW_TABLE = (1ULL << 20), }; enum { @@ -1992,7 +1999,11 @@ struct mlx5_ifc_cmd_hca_cap_2_bits { u8 reserved_at_260[0x120]; u8 reserved_at_380[0x10]; u8 ec_vf_vport_base[0x10]; - u8 reserved_at_3a0[0x460]; + + u8 reserved_at_3a0[0x10]; + u8 max_rqt_vhca_id[0x10]; + + u8 reserved_at_3c0[0x440]; }; enum mlx5_ifc_flow_destination_type { @@ -2151,6 +2162,13 @@ struct mlx5_ifc_rq_num_bits { u8 rq_num[0x18]; }; +struct mlx5_ifc_rq_vhca_bits { + u8 reserved_at_0[0x8]; + u8 rq_num[0x18]; + u8 reserved_at_20[0x10]; + u8 rq_vhca_id[0x10]; +}; + struct mlx5_ifc_mac_address_layout_bits { u8 reserved_at_0[0x10]; u8 mac_addr_47_32[0x10]; @@ -3901,7 +3919,10 @@ struct mlx5_ifc_rqtc_bits { u8 reserved_at_e0[0x6a0]; - struct mlx5_ifc_rq_num_bits rq_num[]; + union { + DECLARE_FLEX_ARRAY(struct mlx5_ifc_rq_num_bits, rq_num); + DECLARE_FLEX_ARRAY(struct mlx5_ifc_rq_vhca_bits, rq_vhca); + }; }; enum { @@ -4744,7 +4765,10 @@ struct mlx5_ifc_set_l2_table_entry_in_bits { u8 reserved_at_c0[0x20]; - u8 reserved_at_e0[0x13]; + u8 reserved_at_e0[0x10]; + u8 silent_mode_valid[0x1]; + u8 silent_mode[0x1]; + u8 reserved_at_f2[0x1]; u8 vlan_valid[0x1]; u8 vlan[0xc]; @@ -10089,6 +10113,20 @@ struct mlx5_ifc_mpegc_reg_bits { u8 reserved_at_60[0x100]; }; +struct mlx5_ifc_mpir_reg_bits { + u8 sdm[0x1]; + u8 reserved_at_1[0x1b]; + u8 host_buses[0x4]; + + u8 reserved_at_20[0x20]; + + u8 local_port[0x8]; + u8 reserved_at_28[0x15]; + u8 sd_group[0x3]; + + u8 reserved_at_60[0x20]; +}; + enum { MLX5_MTUTC_FREQ_ADJ_UNITS_PPB = 0x0, MLX5_MTUTC_FREQ_ADJ_UNITS_SCALED_PPM = 0x1, @@ -10103,7 +10141,10 @@ enum { struct mlx5_ifc_mtutc_reg_bits { u8 reserved_at_0[0x5]; u8 freq_adj_units[0x3]; - u8 reserved_at_8[0x14]; + u8 reserved_at_8[0x3]; + u8 log_max_freq_adjustment[0x5]; + + u8 reserved_at_10[0xc]; u8 operation[0x4]; u8 freq_adjustment[0x20]; diff --git a/include/linux/mm.h b/include/linux/mm.h index 896c0079f64f..f5a97dec5169 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3942,6 +3942,7 @@ enum mf_flags { MF_UNPOISON = 1 << 4, MF_SW_SIMULATED = 1 << 5, MF_NO_RETRY = 1 << 6, + MF_MEM_PRE_REMOVE = 1 << 7, }; int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index, unsigned long count, int mf_flags); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 4dd996ad0bd3..b2d3a88a34d1 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -125,7 +125,7 @@ struct page { struct page_pool *pp; unsigned long _pp_mapping_pad; unsigned long dma_addr; - atomic_long_t pp_frag_count; + atomic_long_t pp_ref_count; }; struct { /* Tail pages of compound page */ unsigned long compound_head; /* Bit zero is set */ diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h index aa44fff8bb9d..a2f6179b672b 100644 --- a/include/linux/mm_types_task.h +++ b/include/linux/mm_types_task.h @@ -9,9 +9,6 @@ */ #include <linux/types.h> -#include <linux/threads.h> -#include <linux/atomic.h> -#include <linux/cpumask.h> #include <asm/page.h> @@ -36,6 +33,8 @@ enum { NR_MM_COUNTERS }; +struct page; + struct page_frag { struct page *page; #if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536) diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 7b12eebc5586..f34407cc2788 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -32,6 +32,7 @@ struct mmc_csd { unsigned int r2w_factor; unsigned int max_dtr; unsigned int erase_size; /* In sectors */ + unsigned int wp_grp_size; unsigned int read_blkbits; unsigned int write_blkbits; unsigned int capacity; @@ -52,9 +53,6 @@ struct mmc_ext_csd { u8 part_config; u8 cache_ctrl; u8 rst_n_function; - u8 max_packed_writes; - u8 max_packed_reads; - u8 packed_event_en; unsigned int part_time; /* Units: ms */ unsigned int sa_timeout; /* Units: 100ns */ unsigned int generic_cmd6_time; /* Units: 10ms */ @@ -306,6 +304,7 @@ struct mmc_card { unsigned int eg_boundary; /* don't cross erase-group boundaries */ unsigned int erase_arg; /* erase / trim / discard */ u8 erased_byte; /* value of erased bytes */ + unsigned int wp_grp_size; /* write group size in sectors */ u32 raw_cid[4]; /* raw card CID */ u32 raw_csd[4]; /* raw card CSD */ diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index 6efec0b9820c..2c7928a50907 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -27,7 +27,6 @@ struct mmc_command { u32 opcode; u32 arg; #define MMC_CMD23_ARG_REL_WR (1 << 31) -#define MMC_CMD23_ARG_PACKED ((0 << 31) | (1 << 30)) #define MMC_CMD23_ARG_TAG_REQ (1 << 29) u32 resp[4]; unsigned int flags; /* expected response type */ diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h index 6f7993803ee7..cf2bcb5da30d 100644 --- a/include/linux/mmc/mmc.h +++ b/include/linux/mmc/mmc.h @@ -257,8 +257,6 @@ static inline bool mmc_ready_for_data(u32 status) #define EXT_CSD_FLUSH_CACHE 32 /* W */ #define EXT_CSD_CACHE_CTRL 33 /* R/W */ #define EXT_CSD_POWER_OFF_NOTIFICATION 34 /* R/W */ -#define EXT_CSD_PACKED_FAILURE_INDEX 35 /* RO */ -#define EXT_CSD_PACKED_CMD_STATUS 36 /* RO */ #define EXT_CSD_EXP_EVENTS_STATUS 54 /* RO, 2 bytes */ #define EXT_CSD_EXP_EVENTS_CTRL 56 /* R/W, 2 bytes */ #define EXT_CSD_DATA_SECTOR_SIZE 61 /* R */ @@ -321,8 +319,6 @@ static inline bool mmc_ready_for_data(u32 status) #define EXT_CSD_SUPPORTED_MODE 493 /* RO */ #define EXT_CSD_TAG_UNIT_SIZE 498 /* RO */ #define EXT_CSD_DATA_TAG_SUPPORT 499 /* RO */ -#define EXT_CSD_MAX_PACKED_WRITES 500 /* RO */ -#define EXT_CSD_MAX_PACKED_READS 501 /* RO */ #define EXT_CSD_BKOPS_SUPPORT 502 /* RO */ #define EXT_CSD_HPI_FEATURES 503 /* RO */ @@ -402,18 +398,12 @@ static inline bool mmc_ready_for_data(u32 status) #define EXT_CSD_PWR_CL_8BIT_SHIFT 4 #define EXT_CSD_PWR_CL_4BIT_SHIFT 0 -#define EXT_CSD_PACKED_EVENT_EN BIT(3) - /* * EXCEPTION_EVENT_STATUS field */ #define EXT_CSD_URGENT_BKOPS BIT(0) #define EXT_CSD_DYNCAP_NEEDED BIT(1) #define EXT_CSD_SYSPOOL_EXHAUSTED BIT(2) -#define EXT_CSD_PACKED_FAILURE BIT(3) - -#define EXT_CSD_PACKED_GENERIC_ERROR BIT(0) -#define EXT_CSD_PACKED_INDEXED_ERROR BIT(1) /* * BKOPS status level diff --git a/include/linux/module.h b/include/linux/module.h index a98e188cf37b..96bc462872c0 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -540,6 +540,8 @@ struct module { struct static_call_site *static_call_sites; #endif #if IS_ENABLED(CONFIG_KUNIT) + int num_kunit_init_suites; + struct kunit_suite **kunit_init_suites; int num_kunit_suites; struct kunit_suite **kunit_suites; #endif @@ -668,7 +670,7 @@ extern void __module_get(struct module *module); * @module: the module we should check for * * Only try to get a module reference count if the module is not being removed. - * This call will fail if the module is already being removed. + * This call will fail if the module is in the process of being removed. * * Care must also be taken to ensure the module exists and is alive prior to * usage of this call. This can be gauranteed through two means: diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h index 4fa9726bc328..bfb85fd13e1f 100644 --- a/include/linux/moduleparam.h +++ b/include/linux/moduleparam.h @@ -385,6 +385,8 @@ extern bool parameq(const char *name1, const char *name2); */ extern bool parameqn(const char *name1, const char *name2, size_t n); +typedef int (*parse_unknown_fn)(char *param, char *val, const char *doing, void *arg); + /* Called on module insert or kernel boot */ extern char *parse_args(const char *name, char *args, @@ -392,9 +394,7 @@ extern char *parse_args(const char *name, unsigned num, s16 level_min, s16 level_max, - void *arg, - int (*unknown)(char *param, char *val, - const char *doing, void *arg)); + void *arg, parse_unknown_fn unknown); /* Called by module remove. */ #ifdef CONFIG_SYSFS diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 95d11308f995..7e208d46ba5b 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -20,6 +20,7 @@ #include <linux/osq_lock.h> #include <linux/debug_locks.h> #include <linux/cleanup.h> +#include <linux/mutex_types.h> #ifdef CONFIG_DEBUG_LOCK_ALLOC # define __DEP_MAP_MUTEX_INITIALIZER(lockname) \ @@ -33,49 +34,6 @@ #ifndef CONFIG_PREEMPT_RT -/* - * Simple, straightforward mutexes with strict semantics: - * - * - only one task can hold the mutex at a time - * - only the owner can unlock the mutex - * - multiple unlocks are not permitted - * - recursive locking is not permitted - * - a mutex object must be initialized via the API - * - a mutex object must not be initialized via memset or copying - * - task may not exit with mutex held - * - memory areas where held locks reside must not be freed - * - held mutexes must not be reinitialized - * - mutexes may not be used in hardware or software interrupt - * contexts such as tasklets and timers - * - * These semantics are fully enforced when DEBUG_MUTEXES is - * enabled. Furthermore, besides enforcing the above rules, the mutex - * debugging code also implements a number of additional features - * that make lock debugging easier and faster: - * - * - uses symbolic names of mutexes, whenever they are printed in debug output - * - point-of-acquire tracking, symbolic lookup of function names - * - list of all locks held in the system, printout of them - * - owner tracking - * - detects self-recursing locks and prints out all relevant info - * - detects multi-task circular deadlocks and prints out all affected - * locks and tasks (and only those tasks) - */ -struct mutex { - atomic_long_t owner; - raw_spinlock_t wait_lock; -#ifdef CONFIG_MUTEX_SPIN_ON_OWNER - struct optimistic_spin_queue osq; /* Spinner MCS lock */ -#endif - struct list_head wait_list; -#ifdef CONFIG_DEBUG_MUTEXES - void *magic; -#endif -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lockdep_map dep_map; -#endif -}; - #ifdef CONFIG_DEBUG_MUTEXES #define __DEBUG_MUTEX_INITIALIZER(lockname) \ @@ -131,14 +89,6 @@ extern bool mutex_is_locked(struct mutex *lock); /* * Preempt-RT variant based on rtmutexes. */ -#include <linux/rtmutex.h> - -struct mutex { - struct rt_mutex_base rtmutex; -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lockdep_map dep_map; -#endif -}; #define __MUTEX_INITIALIZER(mutexname) \ { \ diff --git a/include/linux/mutex_types.h b/include/linux/mutex_types.h new file mode 100644 index 000000000000..fdf7f515fde8 --- /dev/null +++ b/include/linux/mutex_types.h @@ -0,0 +1,71 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_MUTEX_TYPES_H +#define __LINUX_MUTEX_TYPES_H + +#include <linux/atomic.h> +#include <linux/lockdep_types.h> +#include <linux/osq_lock.h> +#include <linux/spinlock_types.h> +#include <linux/types.h> + +#ifndef CONFIG_PREEMPT_RT + +/* + * Simple, straightforward mutexes with strict semantics: + * + * - only one task can hold the mutex at a time + * - only the owner can unlock the mutex + * - multiple unlocks are not permitted + * - recursive locking is not permitted + * - a mutex object must be initialized via the API + * - a mutex object must not be initialized via memset or copying + * - task may not exit with mutex held + * - memory areas where held locks reside must not be freed + * - held mutexes must not be reinitialized + * - mutexes may not be used in hardware or software interrupt + * contexts such as tasklets and timers + * + * These semantics are fully enforced when DEBUG_MUTEXES is + * enabled. Furthermore, besides enforcing the above rules, the mutex + * debugging code also implements a number of additional features + * that make lock debugging easier and faster: + * + * - uses symbolic names of mutexes, whenever they are printed in debug output + * - point-of-acquire tracking, symbolic lookup of function names + * - list of all locks held in the system, printout of them + * - owner tracking + * - detects self-recursing locks and prints out all relevant info + * - detects multi-task circular deadlocks and prints out all affected + * locks and tasks (and only those tasks) + */ +struct mutex { + atomic_long_t owner; + raw_spinlock_t wait_lock; +#ifdef CONFIG_MUTEX_SPIN_ON_OWNER + struct optimistic_spin_queue osq; /* Spinner MCS lock */ +#endif + struct list_head wait_list; +#ifdef CONFIG_DEBUG_MUTEXES + void *magic; +#endif +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif +}; + +#else /* !CONFIG_PREEMPT_RT */ +/* + * Preempt-RT variant based on rtmutexes. + */ +#include <linux/rtmutex.h> + +struct mutex { + struct rt_mutex_base rtmutex; +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif +}; + +#endif /* CONFIG_PREEMPT_RT */ + +#endif /* __LINUX_MUTEX_TYPES_H */ diff --git a/include/linux/namei.h b/include/linux/namei.h index 3100371b5e32..74e0cc14ebf8 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -66,6 +66,7 @@ extern struct dentry *kern_path_create(int, const char *, struct path *, unsigne extern struct dentry *user_path_create(int, const char __user *, struct path *, unsigned int); extern void done_path_create(struct path *, struct dentry *); extern struct dentry *kern_path_locked(const char *, struct path *); +extern struct dentry *user_path_locked_at(int , const char __user *, struct path *); int vfs_path_parent_lookup(struct filename *filename, unsigned int flags, struct path *parent, struct qstr *last, int *type, const struct path *root); diff --git a/include/linux/net/intel/i40e_client.h b/include/linux/net/intel/i40e_client.h index ed42bd5f639f..0aa4411528fc 100644 --- a/include/linux/net/intel/i40e_client.h +++ b/include/linux/net/intel/i40e_client.h @@ -45,7 +45,7 @@ struct i40e_qv_info { struct i40e_qvlist_info { u32 num_vectors; - struct i40e_qv_info qv_info[]; + struct i40e_qv_info qv_info[] __counted_by(num_vectors); }; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2564e209465e..118c40258d07 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -382,6 +382,7 @@ struct napi_struct { /* control-path-only fields follow */ struct list_head dev_list; struct hlist_node napi_hash_node; + int irq; }; enum { @@ -665,6 +666,10 @@ struct netdev_queue { #ifdef CONFIG_XDP_SOCKETS struct xsk_buff_pool *pool; #endif + /* NAPI instance for the queue + * Readers and writers must hold RTNL + */ + struct napi_struct *napi; /* * write-mostly part */ @@ -1324,6 +1329,9 @@ struct netdev_net_notifier { * int (*ndo_mdb_del)(struct net_device *dev, struct nlattr *tb[], * struct netlink_ext_ack *extack); * Deletes the MDB entry from dev. + * int (*ndo_mdb_del_bulk)(struct net_device *dev, struct nlattr *tb[], + * struct netlink_ext_ack *extack); + * Bulk deletes MDB entries from dev. * int (*ndo_mdb_dump)(struct net_device *dev, struct sk_buff *skb, * struct netlink_callback *cb); * Dumps MDB entries from dev. The first argument (marker) in the netlink @@ -1606,6 +1614,9 @@ struct net_device_ops { int (*ndo_mdb_del)(struct net_device *dev, struct nlattr *tb[], struct netlink_ext_ack *extack); + int (*ndo_mdb_del_bulk)(struct net_device *dev, + struct nlattr *tb[], + struct netlink_ext_ack *extack); int (*ndo_mdb_dump)(struct net_device *dev, struct sk_buff *skb, struct netlink_callback *cb); @@ -1865,6 +1876,7 @@ enum netdev_stat_type { * @netdev_ops: Includes several pointers to callbacks, * if one wants to override the ndo_*() functions * @xdp_metadata_ops: Includes pointers to XDP metadata callbacks. + * @xsk_tx_metadata_ops: Includes pointers to AF_XDP TX metadata callbacks. * @ethtool_ops: Management operations * @l3mdev_ops: Layer 3 master device operations * @ndisc_ops: Includes callbacks for different IPv6 neighbour @@ -2091,6 +2103,72 @@ enum netdev_stat_type { */ struct net_device { + /* Cacheline organization can be found documented in + * Documentation/networking/net_cachelines/net_device.rst. + * Please update the document when adding new fields. + */ + + /* TX read-mostly hotpath */ + __cacheline_group_begin(net_device_read_tx); + unsigned long long priv_flags; + const struct net_device_ops *netdev_ops; + const struct header_ops *header_ops; + struct netdev_queue *_tx; + netdev_features_t gso_partial_features; + unsigned int real_num_tx_queues; + unsigned int gso_max_size; + unsigned int gso_ipv4_max_size; + u16 gso_max_segs; + s16 num_tc; + /* Note : dev->mtu is often read without holding a lock. + * Writers usually hold RTNL. + * It is recommended to use READ_ONCE() to annotate the reads, + * and to use WRITE_ONCE() to annotate the writes. + */ + unsigned int mtu; + unsigned short needed_headroom; + struct netdev_tc_txq tc_to_txq[TC_MAX_QUEUE]; +#ifdef CONFIG_XPS + struct xps_dev_maps __rcu *xps_maps[XPS_MAPS_MAX]; +#endif +#ifdef CONFIG_NETFILTER_EGRESS + struct nf_hook_entries __rcu *nf_hooks_egress; +#endif +#ifdef CONFIG_NET_XGRESS + struct bpf_mprog_entry __rcu *tcx_egress; +#endif + __cacheline_group_end(net_device_read_tx); + + /* TXRX read-mostly hotpath */ + __cacheline_group_begin(net_device_read_txrx); + unsigned int flags; + unsigned short hard_header_len; + netdev_features_t features; + struct inet6_dev __rcu *ip6_ptr; + __cacheline_group_end(net_device_read_txrx); + + /* RX read-mostly hotpath */ + __cacheline_group_begin(net_device_read_rx); + struct bpf_prog __rcu *xdp_prog; + struct list_head ptype_specific; + int ifindex; + unsigned int real_num_rx_queues; + struct netdev_rx_queue *_rx; + unsigned long gro_flush_timeout; + int napi_defer_hard_irqs; + unsigned int gro_max_size; + unsigned int gro_ipv4_max_size; + rx_handler_func_t __rcu *rx_handler; + void __rcu *rx_handler_data; + possible_net_t nd_net; +#ifdef CONFIG_NETPOLL + struct netpoll_info __rcu *npinfo; +#endif +#ifdef CONFIG_NET_XGRESS + struct bpf_mprog_entry __rcu *tcx_ingress; +#endif + __cacheline_group_end(net_device_read_rx); + char name[IFNAMSIZ]; struct netdev_name_node *name_node; struct dev_ifalias __rcu *ifalias; @@ -2115,7 +2193,6 @@ struct net_device { struct list_head unreg_list; struct list_head close_list; struct list_head ptype_all; - struct list_head ptype_specific; struct { struct list_head upper; @@ -2123,31 +2200,18 @@ struct net_device { } adj_list; /* Read-mostly cache-line for fast-path access */ - unsigned int flags; xdp_features_t xdp_features; - unsigned long long priv_flags; - const struct net_device_ops *netdev_ops; const struct xdp_metadata_ops *xdp_metadata_ops; - int ifindex; + const struct xsk_tx_metadata_ops *xsk_tx_metadata_ops; unsigned short gflags; - unsigned short hard_header_len; - /* Note : dev->mtu is often read without holding a lock. - * Writers usually hold RTNL. - * It is recommended to use READ_ONCE() to annotate the reads, - * and to use WRITE_ONCE() to annotate the writes. - */ - unsigned int mtu; - unsigned short needed_headroom; unsigned short needed_tailroom; - netdev_features_t features; netdev_features_t hw_features; netdev_features_t wanted_features; netdev_features_t vlan_features; netdev_features_t hw_enc_features; netdev_features_t mpls_features; - netdev_features_t gso_partial_features; unsigned int min_mtu; unsigned int max_mtu; @@ -2185,8 +2249,6 @@ struct net_device { const struct tlsdev_ops *tlsdev_ops; #endif - const struct header_ops *header_ops; - unsigned char operstate; unsigned char link_mode; @@ -2227,9 +2289,7 @@ struct net_device { /* Protocol-specific pointers */ - struct in_device __rcu *ip_ptr; - struct inet6_dev __rcu *ip6_ptr; #if IS_ENABLED(CONFIG_VLAN_8021Q) struct vlan_info __rcu *vlan_info; #endif @@ -2264,26 +2324,13 @@ struct net_device { /* Interface address info used in eth_type_trans() */ const unsigned char *dev_addr; - struct netdev_rx_queue *_rx; unsigned int num_rx_queues; - unsigned int real_num_rx_queues; - - struct bpf_prog __rcu *xdp_prog; - unsigned long gro_flush_timeout; - int napi_defer_hard_irqs; #define GRO_LEGACY_MAX_SIZE 65536u /* TCP minimal MSS is 8 (TCP_MIN_GSO_SIZE), * and shinfo->gso_segs is a 16bit field. */ #define GRO_MAX_SIZE (8 * 65535u) - unsigned int gro_max_size; - unsigned int gro_ipv4_max_size; unsigned int xdp_zc_max_segs; - rx_handler_func_t __rcu *rx_handler; - void __rcu *rx_handler_data; -#ifdef CONFIG_NET_XGRESS - struct bpf_mprog_entry __rcu *tcx_ingress; -#endif struct netdev_queue __rcu *ingress_queue; #ifdef CONFIG_NETFILTER_INGRESS struct nf_hook_entries __rcu *nf_hooks_ingress; @@ -2298,25 +2345,13 @@ struct net_device { /* * Cache lines mostly used on transmit path */ - struct netdev_queue *_tx ____cacheline_aligned_in_smp; unsigned int num_tx_queues; - unsigned int real_num_tx_queues; struct Qdisc __rcu *qdisc; unsigned int tx_queue_len; spinlock_t tx_global_lock; struct xdp_dev_bulk_queue __percpu *xdp_bulkq; -#ifdef CONFIG_XPS - struct xps_dev_maps __rcu *xps_maps[XPS_MAPS_MAX]; -#endif -#ifdef CONFIG_NET_XGRESS - struct bpf_mprog_entry __rcu *tcx_egress; -#endif -#ifdef CONFIG_NETFILTER_EGRESS - struct nf_hook_entries __rcu *nf_hooks_egress; -#endif - #ifdef CONFIG_NET_SCHED DECLARE_HASHTABLE (qdisc_hash, 4); #endif @@ -2355,12 +2390,6 @@ struct net_device { bool needs_free_netdev; void (*priv_destructor)(struct net_device *dev); -#ifdef CONFIG_NETPOLL - struct netpoll_info __rcu *npinfo; -#endif - - possible_net_t nd_net; - /* mid-layer private */ void *ml_priv; enum netdev_ml_priv_type ml_priv_type; @@ -2395,20 +2424,15 @@ struct net_device { */ #define GSO_MAX_SIZE (8 * GSO_MAX_SEGS) - unsigned int gso_max_size; #define TSO_LEGACY_MAX_SIZE 65536 #define TSO_MAX_SIZE UINT_MAX unsigned int tso_max_size; - u16 gso_max_segs; #define TSO_MAX_SEGS U16_MAX u16 tso_max_segs; - unsigned int gso_ipv4_max_size; #ifdef CONFIG_DCB const struct dcbnl_rtnl_ops *dcbnl_ops; #endif - s16 num_tc; - struct netdev_tc_txq tc_to_txq[TC_MAX_QUEUE]; u8 prio_tc_map[TC_BITMASK + 1]; #if IS_ENABLED(CONFIG_FCOE) @@ -2447,6 +2471,10 @@ struct net_device { #if IS_ENABLED(CONFIG_DPLL) struct dpll_pin *dpll_pin; #endif +#if IS_ENABLED(CONFIG_PAGE_POOL) + /** @page_pools: page pools created for this netdevice */ + struct hlist_head page_pools; +#endif }; #define to_net_dev(d) container_of(d, struct net_device, dev) @@ -2651,6 +2679,15 @@ static inline void *netdev_priv(const struct net_device *dev) */ #define SET_NETDEV_DEVTYPE(net, devtype) ((net)->dev.type = (devtype)) +void netif_queue_set_napi(struct net_device *dev, unsigned int queue_index, + enum netdev_queue_type type, + struct napi_struct *napi); + +static inline void netif_napi_set_irq(struct napi_struct *napi, int irq) +{ + napi->irq = irq; +} + /* Default NAPI poll() weight * Device drivers are strongly advised to not use bigger value */ @@ -3964,6 +4001,9 @@ int generic_hwtstamp_get_lower(struct net_device *dev, int generic_hwtstamp_set_lower(struct net_device *dev, struct kernel_hwtstamp_config *kernel_cfg, struct netlink_ext_ack *extack); +int dev_set_hwtstamp_phylib(struct net_device *dev, + struct kernel_hwtstamp_config *cfg, + struct netlink_ext_ack *extack); int dev_ethtool(struct net *net, struct ifreq *ifr, void __user *userdata); unsigned int dev_get_flags(const struct net_device *); int __dev_change_flags(struct net_device *dev, unsigned int flags, @@ -4196,6 +4236,15 @@ static inline void netdev_ref_replace(struct net_device *odev, void linkwatch_fire_event(struct net_device *dev); /** + * linkwatch_sync_dev - sync linkwatch for the given device + * @dev: network device to sync linkwatch for + * + * Sync linkwatch for the given device, removing it from the + * pending work list (if queued). + */ +void linkwatch_sync_dev(struct net_device *dev); + +/** * netif_carrier_ok - test if carrier present * @dev: network device * diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index 7834c0be2831..61aa48f46dd7 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -51,7 +51,7 @@ struct nf_ipv6_ops { u32 (*cookie_init_sequence)(const struct ipv6hdr *iph, const struct tcphdr *th, u16 *mssp); int (*cookie_v6_check)(const struct ipv6hdr *iph, - const struct tcphdr *th, __u32 cookie); + const struct tcphdr *th); #endif void (*route_input)(struct sk_buff *skb); int (*fragment)(struct net *net, struct sock *sk, struct sk_buff *skb, @@ -179,16 +179,16 @@ static inline u32 nf_ipv6_cookie_init_sequence(const struct ipv6hdr *iph, } static inline int nf_cookie_v6_check(const struct ipv6hdr *iph, - const struct tcphdr *th, __u32 cookie) + const struct tcphdr *th) { #if IS_ENABLED(CONFIG_SYN_COOKIES) #if IS_MODULE(CONFIG_IPV6) const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops(); if (v6_ops) - return v6_ops->cookie_v6_check(iph, th, cookie); + return v6_ops->cookie_v6_check(iph, th); #elif IS_BUILTIN(CONFIG_IPV6) - return __cookie_v6_check(iph, th, cookie); + return __cookie_v6_check(iph, th); #endif #endif return 0; diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 75d7de34c908..1a4445bf2ab9 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -228,10 +228,12 @@ bool netlink_strict_get_check(struct sk_buff *skb); int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 portid, int nonblock); int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 portid, __u32 group, gfp_t allocation); + +typedef int (*netlink_filter_fn)(struct sock *dsk, struct sk_buff *skb, void *data); + int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb, __u32 portid, __u32 group, gfp_t allocation, - int (*filter)(struct sock *dsk, - struct sk_buff *skb, void *data), + netlink_filter_fn filter, void *filter_data); int netlink_set_err(struct sock *ssk, __u32 portid, __u32 group, int code); int netlink_register_notifier(struct notifier_block *nb); @@ -351,5 +353,6 @@ bool netlink_ns_capable(const struct sk_buff *skb, struct user_namespace *ns, int cap); bool netlink_capable(const struct sk_buff *skb, int cap); bool netlink_net_capable(const struct sk_buff *skb, int cap); +struct sk_buff *netlink_alloc_large_skb(unsigned int size, int broadcast); #endif /* __LINUX_NETLINK_H */ diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index c11c4db34639..ef8d2d618d5b 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -869,4 +869,26 @@ enum { RCA4_TYPE_MASK_OTHER_LAYOUT_MAX = 15, }; +enum nfs_cb_opnum4 { + OP_CB_GETATTR = 3, + OP_CB_RECALL = 4, + + /* Callback operations new to NFSv4.1 */ + OP_CB_LAYOUTRECALL = 5, + OP_CB_NOTIFY = 6, + OP_CB_PUSH_DELEG = 7, + OP_CB_RECALL_ANY = 8, + OP_CB_RECALLABLE_OBJ_AVAIL = 9, + OP_CB_RECALL_SLOT = 10, + OP_CB_SEQUENCE = 11, + OP_CB_WANTS_CANCELLED = 12, + OP_CB_NOTIFY_LOCK = 13, + OP_CB_NOTIFY_DEVICEID = 14, + + /* Callback operations new to NFSv4.2 */ + OP_CB_OFFLOAD = 15, + + OP_CB_ILLEGAL = 10044, +}; + #endif diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 279262057a92..f5ce7b101146 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -595,7 +595,6 @@ extern void nfs_complete_unlink(struct dentry *dentry, struct inode *); * linux/fs/nfs/write.c */ extern int nfs_congestion_kb; -extern int nfs_writepage(struct page *page, struct writeback_control *wbc); extern int nfs_writepages(struct address_space *, struct writeback_control *); extern int nfs_flush_incompatible(struct file *file, struct folio *folio); extern int nfs_update_folio(struct file *file, struct folio *folio, diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 8d07116caaf1..b61438313a73 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -93,10 +93,10 @@ #include <linux/threads.h> #include <linux/bitmap.h> #include <linux/minmax.h> +#include <linux/nodemask_types.h> #include <linux/numa.h> #include <linux/random.h> -typedef struct { DECLARE_BITMAP(bits, MAX_NUMNODES); } nodemask_t; extern nodemask_t _unused_nodemask_arg_; /** diff --git a/include/linux/nodemask_types.h b/include/linux/nodemask_types.h new file mode 100644 index 000000000000..6b28d97ea6ed --- /dev/null +++ b/include/linux/nodemask_types.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_NODEMASK_TYPES_H +#define __LINUX_NODEMASK_TYPES_H + +#include <linux/bitops.h> +#include <linux/numa.h> + +typedef struct { DECLARE_BITMAP(bits, MAX_NUMNODES); } nodemask_t; + +#endif /* __LINUX_NODEMASK_TYPES_H */ diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h index 771cb0285872..5601d14e2886 100644 --- a/include/linux/nsproxy.h +++ b/include/linux/nsproxy.h @@ -2,6 +2,7 @@ #ifndef _LINUX_NSPROXY_H #define _LINUX_NSPROXY_H +#include <linux/refcount.h> #include <linux/spinlock.h> #include <linux/sched.h> diff --git a/include/linux/numa.h b/include/linux/numa.h index a904861de800..915033a75731 100644 --- a/include/linux/numa.h +++ b/include/linux/numa.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_NUMA_H #define _LINUX_NUMA_H +#include <linux/init.h> #include <linux/types.h> #ifdef CONFIG_NODES_SHIFT @@ -22,34 +23,26 @@ #endif #ifdef CONFIG_NUMA -#include <linux/printk.h> #include <asm/sparsemem.h> /* Generic implementation available */ int numa_nearest_node(int node, unsigned int state); #ifndef memory_add_physaddr_to_nid -static inline int memory_add_physaddr_to_nid(u64 start) -{ - pr_info_once("Unknown online node for memory at 0x%llx, assuming node 0\n", - start); - return 0; -} +int memory_add_physaddr_to_nid(u64 start); #endif + #ifndef phys_to_target_node -static inline int phys_to_target_node(u64 start) -{ - pr_info_once("Unknown target node for memory at 0x%llx, assuming node 0\n", - start); - return 0; -} +int phys_to_target_node(u64 start); #endif + #ifndef numa_fill_memblks static inline int __init numa_fill_memblks(u64 start, u64 end) { return NUMA_NO_MEMBLK; } #endif + #else /* !CONFIG_NUMA */ static inline int numa_nearest_node(int node, unsigned int state) { diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 06142ff7f9ce..2df35e65557d 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -206,6 +206,7 @@ enum mapping_flags { AS_RELEASE_ALWAYS, /* Call ->release_folio(), even if no private data */ AS_STABLE_WRITES, /* must wait for writeback before modifying folio contents */ + AS_UNMOVABLE, /* The mapping cannot be moved, ever */ }; /** @@ -306,6 +307,22 @@ static inline void mapping_clear_stable_writes(struct address_space *mapping) clear_bit(AS_STABLE_WRITES, &mapping->flags); } +static inline void mapping_set_unmovable(struct address_space *mapping) +{ + /* + * It's expected unmovable mappings are also unevictable. Compaction + * migrate scanner (isolate_migratepages_block()) relies on this to + * reduce page locking. + */ + set_bit(AS_UNEVICTABLE, &mapping->flags); + set_bit(AS_UNMOVABLE, &mapping->flags); +} + +static inline bool mapping_unmovable(struct address_space *mapping) +{ + return test_bit(AS_UNMOVABLE, &mapping->flags); +} + static inline gfp_t mapping_gfp_mask(struct address_space * mapping) { return mapping->gfp_mask; diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 844ffdac8d7d..a0c75e467df3 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -3067,6 +3067,7 @@ #define PCI_DEVICE_ID_INTEL_82443GX_0 0x71a0 #define PCI_DEVICE_ID_INTEL_82443GX_2 0x71a2 #define PCI_DEVICE_ID_INTEL_82372FB_1 0x7601 +#define PCI_DEVICE_ID_INTEL_HDA_ARL 0x7728 #define PCI_DEVICE_ID_INTEL_HDA_RPL_S 0x7a50 #define PCI_DEVICE_ID_INTEL_HDA_ADL_S 0x7ad0 #define PCI_DEVICE_ID_INTEL_HDA_MTL 0x7e28 diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 466cf477551a..f6d0e3513948 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -299,6 +299,27 @@ static inline pmd_t pmdp_get(pmd_t *pmdp) } #endif +#ifndef pudp_get +static inline pud_t pudp_get(pud_t *pudp) +{ + return READ_ONCE(*pudp); +} +#endif + +#ifndef p4dp_get +static inline p4d_t p4dp_get(p4d_t *p4dp) +{ + return READ_ONCE(*p4dp); +} +#endif + +#ifndef pgdp_get +static inline pgd_t pgdp_get(pgd_t *pgdp) +{ + return READ_ONCE(*pgdp); +} +#endif + #ifndef __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, diff --git a/include/linux/phy.h b/include/linux/phy.h index bd285950972c..684efaeca07c 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -327,7 +327,8 @@ struct mdio_bus_stats { /** * struct phy_package_shared - Shared information in PHY packages - * @addr: Common PHY address used to combine PHYs in one package + * @base_addr: Base PHY address of PHY package used to combine PHYs + * in one package and for offset calculation of phy_package_read/write * @refcnt: Number of PHYs connected to this shared data * @flags: Initialization of PHY package * @priv_size: Size of the shared private data @priv @@ -338,7 +339,7 @@ struct mdio_bus_stats { * phy_package_leave(). */ struct phy_package_shared { - int addr; + u8 base_addr; refcount_t refcnt; unsigned long flags; size_t priv_size; @@ -604,6 +605,8 @@ struct macsec_ops; * @irq_rerun: Flag indicating interrupts occurred while PHY was suspended, * requiring a rerun of the interrupt handler after resume * @interface: enum phy_interface_t value + * @possible_interfaces: bitmap if interface modes that the attached PHY + * will switch between depending on media speed. * @skb: Netlink message for cable diagnostics * @nest: Netlink nest used for cable diagnostics * @ehdr: nNtlink header for cable diagnostics @@ -673,6 +676,7 @@ struct phy_device { u32 dev_flags; phy_interface_t interface; + DECLARE_PHY_INTERFACE_MASK(possible_interfaces); /* * forced speed & duplex (no autoneg) @@ -1559,9 +1563,11 @@ static inline bool phy_has_txtstamp(struct phy_device *phydev) return phydev && phydev->mii_ts && phydev->mii_ts->txtstamp; } -static inline int phy_hwtstamp(struct phy_device *phydev, struct ifreq *ifr) +static inline int phy_hwtstamp(struct phy_device *phydev, + struct kernel_hwtstamp_config *cfg, + struct netlink_ext_ack *extack) { - return phydev->mii_ts->hwtstamp(phydev->mii_ts, ifr); + return phydev->mii_ts->hwtstamp(phydev->mii_ts, cfg, extack); } static inline bool phy_rxtstamp(struct phy_device *phydev, struct sk_buff *skb, @@ -1860,6 +1866,7 @@ int genphy_c45_an_config_aneg(struct phy_device *phydev); int genphy_c45_an_disable_aneg(struct phy_device *phydev); int genphy_c45_read_mdix(struct phy_device *phydev); int genphy_c45_pma_read_abilities(struct phy_device *phydev); +int genphy_c45_pma_read_ext_abilities(struct phy_device *phydev); int genphy_c45_pma_baset1_read_abilities(struct phy_device *phydev); int genphy_c45_read_eee_abilities(struct phy_device *phydev); int genphy_c45_pma_baset1_read_master_slave(struct phy_device *phydev); @@ -1969,10 +1976,10 @@ int phy_ethtool_get_link_ksettings(struct net_device *ndev, int phy_ethtool_set_link_ksettings(struct net_device *ndev, const struct ethtool_link_ksettings *cmd); int phy_ethtool_nway_reset(struct net_device *ndev); -int phy_package_join(struct phy_device *phydev, int addr, size_t priv_size); +int phy_package_join(struct phy_device *phydev, int base_addr, size_t priv_size); void phy_package_leave(struct phy_device *phydev); int devm_phy_package_join(struct device *dev, struct phy_device *phydev, - int addr, size_t priv_size); + int base_addr, size_t priv_size); int __init mdio_bus_init(void); void mdio_bus_exit(void); @@ -1995,48 +2002,83 @@ int __phy_hwtstamp_set(struct phy_device *phydev, struct kernel_hwtstamp_config *config, struct netlink_ext_ack *extack); -static inline int phy_package_read(struct phy_device *phydev, u32 regnum) +static inline int phy_package_address(struct phy_device *phydev, + unsigned int addr_offset) { struct phy_package_shared *shared = phydev->shared; + u8 base_addr = shared->base_addr; - if (!shared) + if (addr_offset >= PHY_MAX_ADDR - base_addr) return -EIO; - return mdiobus_read(phydev->mdio.bus, shared->addr, regnum); + /* we know that addr will be in the range 0..31 and thus the + * implicit cast to a signed int is not a problem. + */ + return base_addr + addr_offset; } -static inline int __phy_package_read(struct phy_device *phydev, u32 regnum) +static inline int phy_package_read(struct phy_device *phydev, + unsigned int addr_offset, u32 regnum) { - struct phy_package_shared *shared = phydev->shared; + int addr = phy_package_address(phydev, addr_offset); - if (!shared) - return -EIO; + if (addr < 0) + return addr; + + return mdiobus_read(phydev->mdio.bus, addr, regnum); +} + +static inline int __phy_package_read(struct phy_device *phydev, + unsigned int addr_offset, u32 regnum) +{ + int addr = phy_package_address(phydev, addr_offset); + + if (addr < 0) + return addr; - return __mdiobus_read(phydev->mdio.bus, shared->addr, regnum); + return __mdiobus_read(phydev->mdio.bus, addr, regnum); } static inline int phy_package_write(struct phy_device *phydev, - u32 regnum, u16 val) + unsigned int addr_offset, u32 regnum, + u16 val) { - struct phy_package_shared *shared = phydev->shared; + int addr = phy_package_address(phydev, addr_offset); - if (!shared) - return -EIO; + if (addr < 0) + return addr; - return mdiobus_write(phydev->mdio.bus, shared->addr, regnum, val); + return mdiobus_write(phydev->mdio.bus, addr, regnum, val); } static inline int __phy_package_write(struct phy_device *phydev, - u32 regnum, u16 val) + unsigned int addr_offset, u32 regnum, + u16 val) { - struct phy_package_shared *shared = phydev->shared; + int addr = phy_package_address(phydev, addr_offset); - if (!shared) - return -EIO; + if (addr < 0) + return addr; - return __mdiobus_write(phydev->mdio.bus, shared->addr, regnum, val); + return __mdiobus_write(phydev->mdio.bus, addr, regnum, val); } +int __phy_package_read_mmd(struct phy_device *phydev, + unsigned int addr_offset, int devad, + u32 regnum); + +int phy_package_read_mmd(struct phy_device *phydev, + unsigned int addr_offset, int devad, + u32 regnum); + +int __phy_package_write_mmd(struct phy_device *phydev, + unsigned int addr_offset, int devad, + u32 regnum, u16 val); + +int phy_package_write_mmd(struct phy_device *phydev, + unsigned int addr_offset, int devad, + u32 regnum, u16 val); + static inline bool __phy_package_set_once(struct phy_device *phydev, unsigned int b) { diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 875439ab45de..d589f89c612c 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -99,72 +99,6 @@ static inline bool phylink_autoneg_inband(unsigned int mode) } /** - * phylink_pcs_neg_mode() - helper to determine PCS inband mode - * @mode: one of %MLO_AN_FIXED, %MLO_AN_PHY, %MLO_AN_INBAND. - * @interface: interface mode to be used - * @advertising: adertisement ethtool link mode mask - * - * Determines the negotiation mode to be used by the PCS, and returns - * one of: - * - * - %PHYLINK_PCS_NEG_NONE: interface mode does not support inband - * - %PHYLINK_PCS_NEG_OUTBAND: an out of band mode (e.g. reading the PHY) - * will be used. - * - %PHYLINK_PCS_NEG_INBAND_DISABLED: inband mode selected but autoneg - * disabled - * - %PHYLINK_PCS_NEG_INBAND_ENABLED: inband mode selected and autoneg enabled - * - * Note: this is for cases where the PCS itself is involved in negotiation - * (e.g. Clause 37, SGMII and similar) not Clause 73. - */ -static inline unsigned int phylink_pcs_neg_mode(unsigned int mode, - phy_interface_t interface, - const unsigned long *advertising) -{ - unsigned int neg_mode; - - switch (interface) { - case PHY_INTERFACE_MODE_SGMII: - case PHY_INTERFACE_MODE_QSGMII: - case PHY_INTERFACE_MODE_QUSGMII: - case PHY_INTERFACE_MODE_USXGMII: - /* These protocols are designed for use with a PHY which - * communicates its negotiation result back to the MAC via - * inband communication. Note: there exist PHYs that run - * with SGMII but do not send the inband data. - */ - if (!phylink_autoneg_inband(mode)) - neg_mode = PHYLINK_PCS_NEG_OUTBAND; - else - neg_mode = PHYLINK_PCS_NEG_INBAND_ENABLED; - break; - - case PHY_INTERFACE_MODE_1000BASEX: - case PHY_INTERFACE_MODE_2500BASEX: - /* 1000base-X is designed for use media-side for Fibre - * connections, and thus the Autoneg bit needs to be - * taken into account. We also do this for 2500base-X - * as well, but drivers may not support this, so may - * need to override this. - */ - if (!phylink_autoneg_inband(mode)) - neg_mode = PHYLINK_PCS_NEG_OUTBAND; - else if (linkmode_test_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, - advertising)) - neg_mode = PHYLINK_PCS_NEG_INBAND_ENABLED; - else - neg_mode = PHYLINK_PCS_NEG_INBAND_DISABLED; - break; - - default: - neg_mode = PHYLINK_PCS_NEG_NONE; - break; - } - - return neg_mode; -} - -/** * struct phylink_link_state - link state structure * @advertising: ethtool bitmask containing advertised link modes * @lp_advertising: ethtool bitmask containing link partner advertised link diff --git a/include/linux/pid.h b/include/linux/pid.h index 653a527574c4..395cacce1179 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -2,18 +2,12 @@ #ifndef _LINUX_PID_H #define _LINUX_PID_H +#include <linux/pid_types.h> #include <linux/rculist.h> -#include <linux/wait.h> +#include <linux/rcupdate.h> #include <linux/refcount.h> - -enum pid_type -{ - PIDTYPE_PID, - PIDTYPE_TGID, - PIDTYPE_PGID, - PIDTYPE_SID, - PIDTYPE_MAX, -}; +#include <linux/sched.h> +#include <linux/wait.h> /* * What is struct pid? @@ -110,9 +104,6 @@ extern void exchange_tids(struct task_struct *task, struct task_struct *old); extern void transfer_pid(struct task_struct *old, struct task_struct *new, enum pid_type); -struct pid_namespace; -extern struct pid_namespace init_pid_ns; - extern int pid_max; extern int pid_max_min, pid_max_max; @@ -215,4 +206,127 @@ pid_t pid_vnr(struct pid *pid); } \ task = tg___; \ } while_each_pid_task(pid, type, task) + +static inline struct pid *task_pid(struct task_struct *task) +{ + return task->thread_pid; +} + +/* + * the helpers to get the task's different pids as they are seen + * from various namespaces + * + * task_xid_nr() : global id, i.e. the id seen from the init namespace; + * task_xid_vnr() : virtual id, i.e. the id seen from the pid namespace of + * current. + * task_xid_nr_ns() : id seen from the ns specified; + * + * see also pid_nr() etc in include/linux/pid.h + */ +pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, struct pid_namespace *ns); + +static inline pid_t task_pid_nr(struct task_struct *tsk) +{ + return tsk->pid; +} + +static inline pid_t task_pid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) +{ + return __task_pid_nr_ns(tsk, PIDTYPE_PID, ns); +} + +static inline pid_t task_pid_vnr(struct task_struct *tsk) +{ + return __task_pid_nr_ns(tsk, PIDTYPE_PID, NULL); +} + + +static inline pid_t task_tgid_nr(struct task_struct *tsk) +{ + return tsk->tgid; +} + +/** + * pid_alive - check that a task structure is not stale + * @p: Task structure to be checked. + * + * Test if a process is not yet dead (at most zombie state) + * If pid_alive fails, then pointers within the task structure + * can be stale and must not be dereferenced. + * + * Return: 1 if the process is alive. 0 otherwise. + */ +static inline int pid_alive(const struct task_struct *p) +{ + return p->thread_pid != NULL; +} + +static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) +{ + return __task_pid_nr_ns(tsk, PIDTYPE_PGID, ns); +} + +static inline pid_t task_pgrp_vnr(struct task_struct *tsk) +{ + return __task_pid_nr_ns(tsk, PIDTYPE_PGID, NULL); +} + + +static inline pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) +{ + return __task_pid_nr_ns(tsk, PIDTYPE_SID, ns); +} + +static inline pid_t task_session_vnr(struct task_struct *tsk) +{ + return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL); +} + +static inline pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) +{ + return __task_pid_nr_ns(tsk, PIDTYPE_TGID, ns); +} + +static inline pid_t task_tgid_vnr(struct task_struct *tsk) +{ + return __task_pid_nr_ns(tsk, PIDTYPE_TGID, NULL); +} + +static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns) +{ + pid_t pid = 0; + + rcu_read_lock(); + if (pid_alive(tsk)) + pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns); + rcu_read_unlock(); + + return pid; +} + +static inline pid_t task_ppid_nr(const struct task_struct *tsk) +{ + return task_ppid_nr_ns(tsk, &init_pid_ns); +} + +/* Obsolete, do not use: */ +static inline pid_t task_pgrp_nr(struct task_struct *tsk) +{ + return task_pgrp_nr_ns(tsk, &init_pid_ns); +} + +/** + * is_global_init - check if a task structure is init. Since init + * is free to have sub-threads we need to check tgid. + * @tsk: Task structure to be checked. + * + * Check if a task structure is the first user space task the kernel created. + * + * Return: 1 if the task structure is init. 0 otherwise. + */ +static inline int is_global_init(struct task_struct *tsk) +{ + return task_tgid_nr(tsk) == 1; +} + #endif /* _LINUX_PID_H */ diff --git a/include/linux/pid_types.h b/include/linux/pid_types.h new file mode 100644 index 000000000000..c2aee1d91dcf --- /dev/null +++ b/include/linux/pid_types.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_PID_TYPES_H +#define _LINUX_PID_TYPES_H + +enum pid_type { + PIDTYPE_PID, + PIDTYPE_TGID, + PIDTYPE_PGID, + PIDTYPE_SID, + PIDTYPE_MAX, +}; + +struct pid_namespace; +extern struct pid_namespace init_pid_ns; + +#endif /* _LINUX_PID_TYPES_H */ diff --git a/include/linux/platform_data/microchip-ksz.h b/include/linux/platform_data/microchip-ksz.h index ea1cc6d829e9..f177416635a2 100644 --- a/include/linux/platform_data/microchip-ksz.h +++ b/include/linux/platform_data/microchip-ksz.h @@ -20,10 +20,31 @@ #define __MICROCHIP_KSZ_H #include <linux/types.h> +#include <linux/platform_data/dsa.h> + +enum ksz_chip_id { + KSZ8563_CHIP_ID = 0x8563, + KSZ8795_CHIP_ID = 0x8795, + KSZ8794_CHIP_ID = 0x8794, + KSZ8765_CHIP_ID = 0x8765, + KSZ8830_CHIP_ID = 0x8830, + KSZ9477_CHIP_ID = 0x00947700, + KSZ9896_CHIP_ID = 0x00989600, + KSZ9897_CHIP_ID = 0x00989700, + KSZ9893_CHIP_ID = 0x00989300, + KSZ9563_CHIP_ID = 0x00956300, + KSZ9567_CHIP_ID = 0x00956700, + LAN9370_CHIP_ID = 0x00937000, + LAN9371_CHIP_ID = 0x00937100, + LAN9372_CHIP_ID = 0x00937200, + LAN9373_CHIP_ID = 0x00937300, + LAN9374_CHIP_ID = 0x00937400, +}; struct ksz_platform_data { + /* Must be first such that dsa_register_switch() can access it */ + struct dsa_chip_data cd; u32 chip_id; - u16 enabled_ports; }; #endif diff --git a/include/linux/platform_data/si5351.h b/include/linux/platform_data/si5351.h index c71a2dd66143..5f412a615532 100644 --- a/include/linux/platform_data/si5351.h +++ b/include/linux/platform_data/si5351.h @@ -105,10 +105,12 @@ struct si5351_clkout_config { * @clk_xtal: xtal input clock * @clk_clkin: clkin input clock * @pll_src: array of pll source clock setting + * @pll_reset: array indicating if plls should be reset after setting the rate * @clkout: array of clkout configuration */ struct si5351_platform_data { enum si5351_pll_src pll_src[2]; + bool pll_reset[2]; struct si5351_clkout_config clkout[8]; }; diff --git a/include/linux/platform_data/x86/clk-lpss.h b/include/linux/platform_data/x86/clk-lpss.h index 41df326583f9..7f132029316a 100644 --- a/include/linux/platform_data/x86/clk-lpss.h +++ b/include/linux/platform_data/x86/clk-lpss.h @@ -15,6 +15,6 @@ struct lpss_clk_data { struct clk *clk; }; -extern int lpss_atom_clk_init(void); +int lpss_atom_clk_init(void); #endif /* __CLK_LPSS_H */ diff --git a/include/linux/plist.h b/include/linux/plist.h index 0f352c1d3c80..8c1c8adf7fe9 100644 --- a/include/linux/plist.h +++ b/include/linux/plist.h @@ -75,20 +75,10 @@ #include <linux/container_of.h> #include <linux/list.h> -#include <linux/types.h> +#include <linux/plist_types.h> #include <asm/bug.h> -struct plist_head { - struct list_head node_list; -}; - -struct plist_node { - int prio; - struct list_head prio_list; - struct list_head node_list; -}; - /** * PLIST_HEAD_INIT - static struct plist_head initializer * @head: struct plist_head variable name diff --git a/include/linux/plist_types.h b/include/linux/plist_types.h new file mode 100644 index 000000000000..c37e784330af --- /dev/null +++ b/include/linux/plist_types.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _LINUX_PLIST_TYPES_H +#define _LINUX_PLIST_TYPES_H + +#include <linux/types.h> + +struct plist_head { + struct list_head node_list; +}; + +struct plist_node { + int prio; + struct list_head prio_list; + struct list_head node_list; +}; + +#endif /* _LINUX_PLIST_TYPES_H */ diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 34663d0d5c55..b97c5e9820f9 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -118,7 +118,6 @@ struct genpd_power_state { }; struct genpd_lock_ops; -struct dev_pm_opp; struct opp_table; struct generic_pm_domain { @@ -146,8 +145,6 @@ struct generic_pm_domain { int (*power_on)(struct generic_pm_domain *domain); struct raw_notifier_head power_notifiers; /* Power on/off notifiers */ struct opp_table *opp_table; /* OPP table of the genpd */ - unsigned int (*opp_to_performance_state)(struct generic_pm_domain *genpd, - struct dev_pm_opp *opp); int (*set_performance_state)(struct generic_pm_domain *genpd, unsigned int state); struct gpd_dev_ops dev_ops; @@ -348,8 +345,6 @@ int of_genpd_remove_subdomain(struct of_phandle_args *parent_spec, struct generic_pm_domain *of_genpd_remove_last(struct device_node *np); int of_genpd_parse_idle_states(struct device_node *dn, struct genpd_power_state **states, int *n); -unsigned int pm_genpd_opp_to_performance_state(struct device *genpd_dev, - struct dev_pm_opp *opp); int genpd_dev_pm_attach(struct device *dev); struct device *genpd_dev_pm_attach_by_id(struct device *dev, @@ -395,13 +390,6 @@ static inline int of_genpd_parse_idle_states(struct device_node *dn, return -ENODEV; } -static inline unsigned int -pm_genpd_opp_to_performance_state(struct device *genpd_dev, - struct dev_pm_opp *opp) -{ - return 0; -} - static inline int genpd_dev_pm_attach(struct device *dev) { return 0; diff --git a/include/linux/poison.h b/include/linux/poison.h index 851a855d3868..27a7dad17eef 100644 --- a/include/linux/poison.h +++ b/include/linux/poison.h @@ -83,6 +83,8 @@ /********** net/core/skbuff.c **********/ #define SKB_LIST_POISON_NEXT ((void *)(0x800 + POISON_POINTER_DELTA)) +/********** net/ **********/ +#define NET_PTR_POISON ((void *)(0x801 + POISON_POINTER_DELTA)) /********** kernel/bpf/ **********/ #define BPF_PTR_POISON ((void *)(0xeB9FUL + POISON_POINTER_DELTA)) diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index d607f51404fc..dc7b738de299 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -2,40 +2,16 @@ #ifndef _linux_POSIX_TIMERS_H #define _linux_POSIX_TIMERS_H -#include <linux/spinlock.h> +#include <linux/alarmtimer.h> #include <linux/list.h> #include <linux/mutex.h> -#include <linux/alarmtimer.h> +#include <linux/posix-timers_types.h> +#include <linux/spinlock.h> #include <linux/timerqueue.h> struct kernel_siginfo; struct task_struct; -/* - * Bit fields within a clockid: - * - * The most significant 29 bits hold either a pid or a file descriptor. - * - * Bit 2 indicates whether a cpu clock refers to a thread or a process. - * - * Bits 1 and 0 give the type: PROF=0, VIRT=1, SCHED=2, or FD=3. - * - * A clockid is invalid if bits 2, 1, and 0 are all set. - */ -#define CPUCLOCK_PID(clock) ((pid_t) ~((clock) >> 3)) -#define CPUCLOCK_PERTHREAD(clock) \ - (((clock) & (clockid_t) CPUCLOCK_PERTHREAD_MASK) != 0) - -#define CPUCLOCK_PERTHREAD_MASK 4 -#define CPUCLOCK_WHICH(clock) ((clock) & (clockid_t) CPUCLOCK_CLOCK_MASK) -#define CPUCLOCK_CLOCK_MASK 3 -#define CPUCLOCK_PROF 0 -#define CPUCLOCK_VIRT 1 -#define CPUCLOCK_SCHED 2 -#define CPUCLOCK_MAX 3 -#define CLOCKFD CPUCLOCK_MAX -#define CLOCKFD_MASK (CPUCLOCK_PERTHREAD_MASK|CPUCLOCK_CLOCK_MASK) - static inline clockid_t make_process_cpuclock(const unsigned int pid, const clockid_t clock) { @@ -109,44 +85,6 @@ static inline void cpu_timer_setexpires(struct cpu_timer *ctmr, u64 exp) ctmr->node.expires = exp; } -/** - * posix_cputimer_base - Container per posix CPU clock - * @nextevt: Earliest-expiration cache - * @tqhead: timerqueue head for cpu_timers - */ -struct posix_cputimer_base { - u64 nextevt; - struct timerqueue_head tqhead; -}; - -/** - * posix_cputimers - Container for posix CPU timer related data - * @bases: Base container for posix CPU clocks - * @timers_active: Timers are queued. - * @expiry_active: Timer expiry is active. Used for - * process wide timers to avoid multiple - * task trying to handle expiry concurrently - * - * Used in task_struct and signal_struct - */ -struct posix_cputimers { - struct posix_cputimer_base bases[CPUCLOCK_MAX]; - unsigned int timers_active; - unsigned int expiry_active; -}; - -/** - * posix_cputimers_work - Container for task work based posix CPU timer expiry - * @work: The task work to be scheduled - * @mutex: Mutex held around expiry in context of this task work - * @scheduled: @work has been scheduled already, no further processing - */ -struct posix_cputimers_work { - struct callback_head work; - struct mutex mutex; - unsigned int scheduled; -}; - static inline void posix_cputimers_init(struct posix_cputimers *pct) { memset(pct, 0, sizeof(*pct)); @@ -179,7 +117,6 @@ static inline void posix_cputimers_rt_watchdog(struct posix_cputimers *pct, .bases = INIT_CPU_TIMERBASES(s.posix_cputimers.bases), \ }, #else -struct posix_cputimers { }; struct cpu_timer { }; #define INIT_CPU_TIMERS(s) static inline void posix_cputimers_init(struct posix_cputimers *pct) { } diff --git a/include/linux/posix-timers_types.h b/include/linux/posix-timers_types.h new file mode 100644 index 000000000000..a4712c1008c9 --- /dev/null +++ b/include/linux/posix-timers_types.h @@ -0,0 +1,80 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _linux_POSIX_TIMERS_TYPES_H +#define _linux_POSIX_TIMERS_TYPES_H + +#include <linux/mutex_types.h> +#include <linux/timerqueue_types.h> +#include <linux/types.h> + +/* + * Bit fields within a clockid: + * + * The most significant 29 bits hold either a pid or a file descriptor. + * + * Bit 2 indicates whether a cpu clock refers to a thread or a process. + * + * Bits 1 and 0 give the type: PROF=0, VIRT=1, SCHED=2, or FD=3. + * + * A clockid is invalid if bits 2, 1, and 0 are all set. + */ +#define CPUCLOCK_PID(clock) ((pid_t) ~((clock) >> 3)) +#define CPUCLOCK_PERTHREAD(clock) \ + (((clock) & (clockid_t) CPUCLOCK_PERTHREAD_MASK) != 0) + +#define CPUCLOCK_PERTHREAD_MASK 4 +#define CPUCLOCK_WHICH(clock) ((clock) & (clockid_t) CPUCLOCK_CLOCK_MASK) +#define CPUCLOCK_CLOCK_MASK 3 +#define CPUCLOCK_PROF 0 +#define CPUCLOCK_VIRT 1 +#define CPUCLOCK_SCHED 2 +#define CPUCLOCK_MAX 3 +#define CLOCKFD CPUCLOCK_MAX +#define CLOCKFD_MASK (CPUCLOCK_PERTHREAD_MASK|CPUCLOCK_CLOCK_MASK) + +#ifdef CONFIG_POSIX_TIMERS + +/** + * posix_cputimer_base - Container per posix CPU clock + * @nextevt: Earliest-expiration cache + * @tqhead: timerqueue head for cpu_timers + */ +struct posix_cputimer_base { + u64 nextevt; + struct timerqueue_head tqhead; +}; + +/** + * posix_cputimers - Container for posix CPU timer related data + * @bases: Base container for posix CPU clocks + * @timers_active: Timers are queued. + * @expiry_active: Timer expiry is active. Used for + * process wide timers to avoid multiple + * task trying to handle expiry concurrently + * + * Used in task_struct and signal_struct + */ +struct posix_cputimers { + struct posix_cputimer_base bases[CPUCLOCK_MAX]; + unsigned int timers_active; + unsigned int expiry_active; +}; + +/** + * posix_cputimers_work - Container for task work based posix CPU timer expiry + * @work: The task work to be scheduled + * @mutex: Mutex held around expiry in context of this task work + * @scheduled: @work has been scheduled already, no further processing + */ +struct posix_cputimers_work { + struct callback_head work; + struct mutex mutex; + unsigned int scheduled; +}; + +#else /* CONFIG_POSIX_TIMERS */ + +struct posix_cputimers { }; + +#endif /* CONFIG_POSIX_TIMERS */ + +#endif /* _linux_POSIX_TIMERS_TYPES_H */ diff --git a/include/linux/prandom.h b/include/linux/prandom.h index f2ed5b72b3d6..f7f1e5251c67 100644 --- a/include/linux/prandom.h +++ b/include/linux/prandom.h @@ -10,7 +10,6 @@ #include <linux/types.h> #include <linux/once.h> -#include <linux/percpu.h> #include <linux/random.h> struct rnd_state { diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 9aa6358a1a16..7233e9cf1bab 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -9,7 +9,7 @@ #include <linux/linkage.h> #include <linux/cleanup.h> -#include <linux/list.h> +#include <linux/types.h> /* * We put the hardirq and softirq counter into the preemption @@ -360,7 +360,9 @@ void preempt_notifier_unregister(struct preempt_notifier *notifier); static inline void preempt_notifier_init(struct preempt_notifier *notifier, struct preempt_ops *ops) { - INIT_HLIST_NODE(¬ifier->link); + /* INIT_HLIST_NODE() open coded, to avoid dependency on list.h */ + notifier->link.next = NULL; + notifier->link.pprev = NULL; notifier->ops = ops; } diff --git a/include/linux/property.h b/include/linux/property.h index 97f901c0914e..60e35bd97398 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -80,6 +80,16 @@ int fwnode_property_match_string(const struct fwnode_handle *fwnode, bool fwnode_device_is_available(const struct fwnode_handle *fwnode); +static inline bool fwnode_device_is_big_endian(const struct fwnode_handle *fwnode) +{ + if (fwnode_property_present(fwnode, "big-endian")) + return true; + if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN) && + fwnode_property_present(fwnode, "native-endian")) + return true; + return false; +} + static inline bool fwnode_device_is_compatible(const struct fwnode_handle *fwnode, const char *compat) { @@ -87,6 +97,22 @@ bool fwnode_device_is_compatible(const struct fwnode_handle *fwnode, const char } /** + * device_is_big_endian - check if a device has BE registers + * @dev: Pointer to the struct device + * + * Returns: true if the device has a "big-endian" property, or if the kernel + * was compiled for BE *and* the device has a "native-endian" property. + * Returns false otherwise. + * + * Callers would nominally use ioread32be/iowrite32be if + * device_is_big_endian() == true, or readl/writel otherwise. + */ +static inline bool device_is_big_endian(const struct device *dev) +{ + return fwnode_device_is_big_endian(dev_fwnode(dev)); +} + +/** * device_is_compatible - match 'compatible' property of the device with a given string * @dev: Pointer to the struct device * @compat: The string to match 'compatible' property with @@ -109,6 +135,7 @@ struct fwnode_handle *fwnode_find_reference(const struct fwnode_handle *fwnode, const char *fwnode_get_name(const struct fwnode_handle *fwnode); const char *fwnode_get_name_prefix(const struct fwnode_handle *fwnode); +bool fwnode_name_eq(const struct fwnode_handle *fwnode, const char *name); struct fwnode_handle *fwnode_get_parent(const struct fwnode_handle *fwnode); struct fwnode_handle *fwnode_get_next_parent(struct fwnode_handle *fwnode); diff --git a/include/linux/pwm.h b/include/linux/pwm.h index cda3597b84f2..fcc2c4496f73 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -69,7 +69,6 @@ struct pwm_state { * @label: name of the PWM device * @flags: flags associated with the PWM device * @hwpwm: per-chip relative index of the PWM device - * @pwm: global index of the PWM device * @chip: PWM chip providing this PWM device * @args: PWM arguments * @state: last applied state @@ -79,7 +78,6 @@ struct pwm_device { const char *label; unsigned long flags; unsigned int hwpwm; - unsigned int pwm; struct pwm_chip *chip; struct pwm_args args; @@ -93,8 +91,8 @@ struct pwm_device { * @state: state to fill with the current PWM state * * The returned PWM state represents the state that was applied by a previous call to - * pwm_apply_state(). Drivers may have to slightly tweak that state before programming it to - * hardware. If pwm_apply_state() was never called, this returns either the current hardware + * pwm_apply_might_sleep(). Drivers may have to slightly tweak that state before programming it to + * hardware. If pwm_apply_might_sleep() was never called, this returns either the current hardware * state (if supported) or the default settings. */ static inline void pwm_get_state(const struct pwm_device *pwm, @@ -112,12 +110,6 @@ static inline bool pwm_is_enabled(const struct pwm_device *pwm) return state.enabled; } -static inline void pwm_set_period(struct pwm_device *pwm, u64 period) -{ - if (pwm) - pwm->state.period = period; -} - static inline u64 pwm_get_period(const struct pwm_device *pwm) { struct pwm_state state; @@ -127,12 +119,6 @@ static inline u64 pwm_get_period(const struct pwm_device *pwm) return state.period; } -static inline void pwm_set_duty_cycle(struct pwm_device *pwm, unsigned int duty) -{ - if (pwm) - pwm->state.duty_cycle = duty; -} - static inline u64 pwm_get_duty_cycle(const struct pwm_device *pwm) { struct pwm_state state; @@ -158,20 +144,20 @@ static inline void pwm_get_args(const struct pwm_device *pwm, } /** - * pwm_init_state() - prepare a new state to be applied with pwm_apply_state() + * pwm_init_state() - prepare a new state to be applied with pwm_apply_might_sleep() * @pwm: PWM device * @state: state to fill with the prepared PWM state * * This functions prepares a state that can later be tweaked and applied - * to the PWM device with pwm_apply_state(). This is a convenient function + * to the PWM device with pwm_apply_might_sleep(). This is a convenient function * that first retrieves the current PWM state and the replaces the period * and polarity fields with the reference values defined in pwm->args. * Once the function returns, you can adjust the ->enabled and ->duty_cycle - * fields according to your needs before calling pwm_apply_state(). + * fields according to your needs before calling pwm_apply_might_sleep(). * * ->duty_cycle is initially set to zero to avoid cases where the current * ->duty_cycle value exceed the pwm_args->period one, which would trigger - * an error if the user calls pwm_apply_state() without adjusting ->duty_cycle + * an error if the user calls pwm_apply_might_sleep() without adjusting ->duty_cycle * first. */ static inline void pwm_init_state(const struct pwm_device *pwm, @@ -227,7 +213,7 @@ pwm_get_relative_duty_cycle(const struct pwm_state *state, unsigned int scale) * * pwm_init_state(pwm, &state); * pwm_set_relative_duty_cycle(&state, 50, 100); - * pwm_apply_state(pwm, &state); + * pwm_apply_might_sleep(pwm, &state); * * This functions returns -EINVAL if @duty_cycle and/or @scale are * inconsistent (@scale == 0 or @duty_cycle > @scale). @@ -282,32 +268,33 @@ struct pwm_ops { * @dev: device providing the PWMs * @ops: callbacks for this PWM controller * @owner: module providing this chip - * @base: number of first PWM controlled by this chip + * @id: unique number of this PWM chip * @npwm: number of PWMs controlled by this chip * @of_xlate: request a PWM device given a device tree PWM specifier * @of_pwm_n_cells: number of cells expected in the device tree PWM specifier - * @list: list node for internal use + * @atomic: can the driver's ->apply() be called in atomic context * @pwms: array of PWM devices allocated by the framework */ struct pwm_chip { struct device *dev; const struct pwm_ops *ops; struct module *owner; - int base; + unsigned int id; unsigned int npwm; struct pwm_device * (*of_xlate)(struct pwm_chip *chip, const struct of_phandle_args *args); unsigned int of_pwm_n_cells; + bool atomic; /* only used internally by the PWM framework */ - struct list_head list; struct pwm_device *pwms; }; #if IS_ENABLED(CONFIG_PWM) /* PWM user APIs */ -int pwm_apply_state(struct pwm_device *pwm, const struct pwm_state *state); +int pwm_apply_might_sleep(struct pwm_device *pwm, const struct pwm_state *state); +int pwm_apply_atomic(struct pwm_device *pwm, const struct pwm_state *state); int pwm_adjust_config(struct pwm_device *pwm); /** @@ -335,7 +322,7 @@ static inline int pwm_config(struct pwm_device *pwm, int duty_ns, state.duty_cycle = duty_ns; state.period = period_ns; - return pwm_apply_state(pwm, &state); + return pwm_apply_might_sleep(pwm, &state); } /** @@ -356,7 +343,7 @@ static inline int pwm_enable(struct pwm_device *pwm) return 0; state.enabled = true; - return pwm_apply_state(pwm, &state); + return pwm_apply_might_sleep(pwm, &state); } /** @@ -375,7 +362,18 @@ static inline void pwm_disable(struct pwm_device *pwm) return; state.enabled = false; - pwm_apply_state(pwm, &state); + pwm_apply_might_sleep(pwm, &state); +} + +/** + * pwm_might_sleep() - is pwm_apply_atomic() supported? + * @pwm: PWM device + * + * Returns: false if pwm_apply_atomic() can be called from atomic context. + */ +static inline bool pwm_might_sleep(struct pwm_device *pwm) +{ + return !pwm->chip->atomic; } /* PWM provider APIs */ @@ -406,16 +404,27 @@ struct pwm_device *devm_fwnode_pwm_get(struct device *dev, struct fwnode_handle *fwnode, const char *con_id); #else -static inline int pwm_apply_state(struct pwm_device *pwm, - const struct pwm_state *state) +static inline bool pwm_might_sleep(struct pwm_device *pwm) +{ + return true; +} + +static inline int pwm_apply_might_sleep(struct pwm_device *pwm, + const struct pwm_state *state) { might_sleep(); - return -ENOTSUPP; + return -EOPNOTSUPP; +} + +static inline int pwm_apply_atomic(struct pwm_device *pwm, + const struct pwm_state *state) +{ + return -EOPNOTSUPP; } static inline int pwm_adjust_config(struct pwm_device *pwm) { - return -ENOTSUPP; + return -EOPNOTSUPP; } static inline int pwm_config(struct pwm_device *pwm, int duty_ns, @@ -524,7 +533,14 @@ static inline void pwm_apply_args(struct pwm_device *pwm) state.period = pwm->args.period; state.usage_power = false; - pwm_apply_state(pwm, &state); + pwm_apply_might_sleep(pwm, &state); +} + +/* only for backwards-compatibility, new code should not use this */ +static inline int pwm_apply_state(struct pwm_device *pwm, + const struct pwm_state *state) +{ + return pwm_apply_might_sleep(pwm, state); } struct pwm_lookup { diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 4fa4ef0a173a..06cc8888199e 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -74,7 +74,7 @@ void __dquot_free_space(struct inode *inode, qsize_t number, int flags); int dquot_alloc_inode(struct inode *inode); -int dquot_claim_space_nodirty(struct inode *inode, qsize_t number); +void dquot_claim_space_nodirty(struct inode *inode, qsize_t number); void dquot_free_inode(struct inode *inode); void dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number); @@ -257,10 +257,9 @@ static inline void __dquot_free_space(struct inode *inode, qsize_t number, inode_sub_bytes(inode, number); } -static inline int dquot_claim_space_nodirty(struct inode *inode, qsize_t number) +static inline void dquot_claim_space_nodirty(struct inode *inode, qsize_t number) { inode_add_bytes(inode, number); - return 0; } static inline int dquot_reclaim_space_nodirty(struct inode *inode, @@ -358,14 +357,10 @@ static inline int dquot_reserve_block(struct inode *inode, qsize_t nr) DQUOT_SPACE_WARN|DQUOT_SPACE_RESERVE); } -static inline int dquot_claim_block(struct inode *inode, qsize_t nr) +static inline void dquot_claim_block(struct inode *inode, qsize_t nr) { - int ret; - - ret = dquot_claim_space_nodirty(inode, nr << inode->i_blkbits); - if (!ret) - mark_inode_dirty_sync(inode); - return ret; + dquot_claim_space_nodirty(inode, nr << inode->i_blkbits); + mark_inode_dirty_sync(inode); } static inline void dquot_reclaim_block(struct inode *inode, qsize_t nr) diff --git a/include/linux/rcu_notifier.h b/include/linux/rcu_notifier.h index ebf371364581..5640f024773b 100644 --- a/include/linux/rcu_notifier.h +++ b/include/linux/rcu_notifier.h @@ -13,7 +13,7 @@ #define RCU_STALL_NOTIFY_NORM 1 #define RCU_STALL_NOTIFY_EXP 2 -#ifdef CONFIG_RCU_STALL_COMMON +#if defined(CONFIG_RCU_STALL_COMMON) && defined(CONFIG_RCU_CPU_STALL_NOTIFIER) #include <linux/notifier.h> #include <linux/types.h> @@ -21,12 +21,12 @@ int rcu_stall_chain_notifier_register(struct notifier_block *n); int rcu_stall_chain_notifier_unregister(struct notifier_block *n); -#else // #ifdef CONFIG_RCU_STALL_COMMON +#else // #if defined(CONFIG_RCU_STALL_COMMON) && defined(CONFIG_RCU_CPU_STALL_NOTIFIER) // No RCU CPU stall warnings in Tiny RCU. static inline int rcu_stall_chain_notifier_register(struct notifier_block *n) { return -EEXIST; } static inline int rcu_stall_chain_notifier_unregister(struct notifier_block *n) { return -ENOENT; } -#endif // #else // #ifdef CONFIG_RCU_STALL_COMMON +#endif // #else // #if defined(CONFIG_RCU_STALL_COMMON) && defined(CONFIG_RCU_CPU_STALL_NOTIFIER) #endif /* __LINUX_RCU_NOTIFIER_H */ diff --git a/include/linux/rculist.h b/include/linux/rculist.h index d29740be4833..3dc1e58865f7 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -355,7 +355,7 @@ static inline void list_splice_tail_init_rcu(struct list_head *list, }) /** - * list_next_or_null_rcu - get the first element from a list + * list_next_or_null_rcu - get the next element from a list * @head: the head for the list. * @ptr: the list head to take the next element from. * @type: the type of the struct this is embedded in. diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index f7206b2623c9..0746b1b0b663 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -34,9 +34,6 @@ #define ULONG_CMP_GE(a, b) (ULONG_MAX / 2 >= (a) - (b)) #define ULONG_CMP_LT(a, b) (ULONG_MAX / 2 < (a) - (b)) -#define ulong2long(a) (*(long *)(&(a))) -#define USHORT_CMP_GE(a, b) (USHRT_MAX / 2 >= (unsigned short)((a) - (b))) -#define USHORT_CMP_LT(a, b) (USHRT_MAX / 2 < (unsigned short)((a) - (b))) /* Exported common interfaces */ void call_rcu(struct rcu_head *head, rcu_callback_t func); @@ -301,6 +298,11 @@ static inline void rcu_lock_acquire(struct lockdep_map *map) lock_acquire(map, 0, 0, 2, 0, NULL, _THIS_IP_); } +static inline void rcu_try_lock_acquire(struct lockdep_map *map) +{ + lock_acquire(map, 0, 1, 2, 0, NULL, _THIS_IP_); +} + static inline void rcu_lock_release(struct lockdep_map *map) { lock_release(map, _THIS_IP_); @@ -315,6 +317,7 @@ int rcu_read_lock_any_held(void); #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ # define rcu_lock_acquire(a) do { } while (0) +# define rcu_try_lock_acquire(a) do { } while (0) # define rcu_lock_release(a) do { } while (0) static inline int rcu_read_lock_held(void) diff --git a/include/linux/rcupdate_wait.h b/include/linux/rcupdate_wait.h index 5e0f74f2f8ca..d07f0848802e 100644 --- a/include/linux/rcupdate_wait.h +++ b/include/linux/rcupdate_wait.h @@ -8,6 +8,7 @@ #include <linux/rcupdate.h> #include <linux/completion.h> +#include <linux/sched.h> /* * Structure allowing asynchronous waiting on RCU. @@ -55,4 +56,13 @@ do { \ #define synchronize_rcu_mult(...) \ _wait_rcu_gp(IS_ENABLED(CONFIG_TINY_RCU), __VA_ARGS__) +static inline void cond_resched_rcu(void) +{ +#if defined(CONFIG_DEBUG_ATOMIC_SLEEP) || !defined(CONFIG_PREEMPT_RCU) + rcu_read_unlock(); + cond_resched(); + rcu_read_lock(); +#endif +} + #endif /* _LINUX_SCHED_RCUPDATE_WAIT_H */ diff --git a/include/linux/refcount.h b/include/linux/refcount.h index a62fcca97486..85c6df0d1bef 100644 --- a/include/linux/refcount.h +++ b/include/linux/refcount.h @@ -96,22 +96,11 @@ #include <linux/bug.h> #include <linux/compiler.h> #include <linux/limits.h> +#include <linux/refcount_types.h> #include <linux/spinlock_types.h> struct mutex; -/** - * typedef refcount_t - variant of atomic_t specialized for reference counts - * @refs: atomic_t counter field - * - * The counter saturates at REFCOUNT_SATURATED and will not move once - * there. This avoids wrapping the counter and causing 'spurious' - * use-after-free bugs. - */ -typedef struct refcount_struct { - atomic_t refs; -} refcount_t; - #define REFCOUNT_INIT(n) { .refs = ATOMIC_INIT(n), } #define REFCOUNT_MAX INT_MAX #define REFCOUNT_SATURATED (INT_MIN / 2) diff --git a/include/linux/refcount_types.h b/include/linux/refcount_types.h new file mode 100644 index 000000000000..162004f06edf --- /dev/null +++ b/include/linux/refcount_types.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_REFCOUNT_TYPES_H +#define _LINUX_REFCOUNT_TYPES_H + +#include <linux/types.h> + +/** + * typedef refcount_t - variant of atomic_t specialized for reference counts + * @refs: atomic_t counter field + * + * The counter saturates at REFCOUNT_SATURATED and will not move once + * there. This avoids wrapping the counter and causing 'spurious' + * use-after-free bugs. + */ +typedef struct refcount_struct { + atomic_t refs; +} refcount_t; + +#endif /* _LINUX_REFCOUNT_TYPES_H */ diff --git a/include/linux/restart_block.h b/include/linux/restart_block.h index 980a65594412..13f17676c5f4 100644 --- a/include/linux/restart_block.h +++ b/include/linux/restart_block.h @@ -7,8 +7,8 @@ #include <linux/compiler.h> #include <linux/types.h> -#include <linux/time64.h> +struct __kernel_timespec; struct timespec; struct old_timespec32; struct pollfd; diff --git a/include/linux/resume_user_mode.h b/include/linux/resume_user_mode.h index f8f3e958e9cf..e0135e0adae0 100644 --- a/include/linux/resume_user_mode.h +++ b/include/linux/resume_user_mode.h @@ -6,6 +6,7 @@ #include <linux/sched.h> #include <linux/task_work.h> #include <linux/memcontrol.h> +#include <linux/rseq.h> #include <linux/blk-cgroup.h> /** diff --git a/include/linux/rhashtable-types.h b/include/linux/rhashtable-types.h index 57467cbf4c5b..b6f3797277ff 100644 --- a/include/linux/rhashtable-types.h +++ b/include/linux/rhashtable-types.h @@ -12,7 +12,7 @@ #include <linux/atomic.h> #include <linux/compiler.h> #include <linux/mutex.h> -#include <linux/workqueue.h> +#include <linux/workqueue_types.h> struct rhash_head { struct rhash_head __rcu *next; diff --git a/include/linux/rseq.h b/include/linux/rseq.h new file mode 100644 index 000000000000..bc8af3eb5598 --- /dev/null +++ b/include/linux/rseq.h @@ -0,0 +1,131 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +#ifndef _LINUX_RSEQ_H +#define _LINUX_RSEQ_H + +#ifdef CONFIG_RSEQ + +#include <linux/preempt.h> +#include <linux/sched.h> + +/* + * Map the event mask on the user-space ABI enum rseq_cs_flags + * for direct mask checks. + */ +enum rseq_event_mask_bits { + RSEQ_EVENT_PREEMPT_BIT = RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT, + RSEQ_EVENT_SIGNAL_BIT = RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT, + RSEQ_EVENT_MIGRATE_BIT = RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT, +}; + +enum rseq_event_mask { + RSEQ_EVENT_PREEMPT = (1U << RSEQ_EVENT_PREEMPT_BIT), + RSEQ_EVENT_SIGNAL = (1U << RSEQ_EVENT_SIGNAL_BIT), + RSEQ_EVENT_MIGRATE = (1U << RSEQ_EVENT_MIGRATE_BIT), +}; + +static inline void rseq_set_notify_resume(struct task_struct *t) +{ + if (t->rseq) + set_tsk_thread_flag(t, TIF_NOTIFY_RESUME); +} + +void __rseq_handle_notify_resume(struct ksignal *sig, struct pt_regs *regs); + +static inline void rseq_handle_notify_resume(struct ksignal *ksig, + struct pt_regs *regs) +{ + if (current->rseq) + __rseq_handle_notify_resume(ksig, regs); +} + +static inline void rseq_signal_deliver(struct ksignal *ksig, + struct pt_regs *regs) +{ + preempt_disable(); + __set_bit(RSEQ_EVENT_SIGNAL_BIT, ¤t->rseq_event_mask); + preempt_enable(); + rseq_handle_notify_resume(ksig, regs); +} + +/* rseq_preempt() requires preemption to be disabled. */ +static inline void rseq_preempt(struct task_struct *t) +{ + __set_bit(RSEQ_EVENT_PREEMPT_BIT, &t->rseq_event_mask); + rseq_set_notify_resume(t); +} + +/* rseq_migrate() requires preemption to be disabled. */ +static inline void rseq_migrate(struct task_struct *t) +{ + __set_bit(RSEQ_EVENT_MIGRATE_BIT, &t->rseq_event_mask); + rseq_set_notify_resume(t); +} + +/* + * If parent process has a registered restartable sequences area, the + * child inherits. Unregister rseq for a clone with CLONE_VM set. + */ +static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) +{ + if (clone_flags & CLONE_VM) { + t->rseq = NULL; + t->rseq_len = 0; + t->rseq_sig = 0; + t->rseq_event_mask = 0; + } else { + t->rseq = current->rseq; + t->rseq_len = current->rseq_len; + t->rseq_sig = current->rseq_sig; + t->rseq_event_mask = current->rseq_event_mask; + } +} + +static inline void rseq_execve(struct task_struct *t) +{ + t->rseq = NULL; + t->rseq_len = 0; + t->rseq_sig = 0; + t->rseq_event_mask = 0; +} + +#else + +static inline void rseq_set_notify_resume(struct task_struct *t) +{ +} +static inline void rseq_handle_notify_resume(struct ksignal *ksig, + struct pt_regs *regs) +{ +} +static inline void rseq_signal_deliver(struct ksignal *ksig, + struct pt_regs *regs) +{ +} +static inline void rseq_preempt(struct task_struct *t) +{ +} +static inline void rseq_migrate(struct task_struct *t) +{ +} +static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) +{ +} +static inline void rseq_execve(struct task_struct *t) +{ +} + +#endif + +#ifdef CONFIG_DEBUG_RSEQ + +void rseq_syscall(struct pt_regs *regs); + +#else + +static inline void rseq_syscall(struct pt_regs *regs) +{ +} + +#endif + +#endif /* _LINUX_RSEQ_H */ diff --git a/include/linux/rslib.h b/include/linux/rslib.h index 238bb85243d3..a04dacbdc8ae 100644 --- a/include/linux/rslib.h +++ b/include/linux/rslib.h @@ -10,7 +10,6 @@ #ifndef _RSLIB_H_ #define _RSLIB_H_ -#include <linux/list.h> #include <linux/types.h> /* for gfp_t */ #include <linux/gfp.h> /* for GFP_KERNEL */ diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 3d6cf306cd55..410529fca18b 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -10,6 +10,13 @@ #include <uapi/linux/rtnetlink.h> extern int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, u32 group, int echo); + +static inline int rtnetlink_maybe_send(struct sk_buff *skb, struct net *net, + u32 pid, u32 group, int echo) +{ + return !skb ? 0 : rtnetlink_send(skb, net, pid, group, echo); +} + extern int rtnl_unicast(struct sk_buff *skb, struct net *net, u32 pid); extern void rtnl_notify(struct sk_buff *skb, struct net *net, u32 pid, u32 group, const struct nlmsghdr *nlh, gfp_t flags); @@ -72,6 +79,18 @@ static inline bool lockdep_rtnl_is_held(void) #define rtnl_dereference(p) \ rcu_dereference_protected(p, lockdep_rtnl_is_held()) +/** + * rcu_replace_pointer_rtnl - replace an RCU pointer under rtnl_lock, returning + * its old value + * @rp: RCU pointer, whose value is returned + * @p: regular pointer + * + * Perform a replacement under rtnl_lock, where @rp is an RCU-annotated + * pointer. The old value of @rp is returned, and @rp is set to @p + */ +#define rcu_replace_pointer_rtnl(rp, p) \ + rcu_replace_pointer(rp, p, lockdep_rtnl_is_held()) + static inline struct netdev_queue *dev_ingress_queue(struct net_device *dev) { return rtnl_dereference(dev->ingress_queue); @@ -130,4 +149,26 @@ extern int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, extern void rtnl_offload_xstats_notify(struct net_device *dev); +static inline int rtnl_has_listeners(const struct net *net, u32 group) +{ + struct sock *rtnl = net->rtnl; + + return netlink_has_listeners(rtnl, group); +} + +/** + * rtnl_notify_needed - check if notification is needed + * @net: Pointer to the net namespace + * @nlflags: netlink ingress message flags + * @group: rtnl group + * + * Based on the ingress message flags and rtnl group, returns true + * if a notification is needed, false otherwise. + */ +static inline bool +rtnl_notify_needed(const struct net *net, u16 nlflags, u32 group) +{ + return (nlflags & NLM_F_ECHO) || rtnl_has_listeners(net, group); +} + #endif /* __LINUX_RTNETLINK_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index d3097f0682d7..9a66147915b2 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -10,33 +10,41 @@ #include <uapi/linux/sched.h> #include <asm/current.h> - -#include <linux/pid.h> -#include <linux/sem.h> +#include <asm/processor.h> +#include <linux/thread_info.h> +#include <linux/preempt.h> +#include <linux/cpumask.h> + +#include <linux/cache.h> +#include <linux/irqflags_types.h> +#include <linux/smp_types.h> +#include <linux/pid_types.h> +#include <linux/sem_types.h> #include <linux/shm.h> #include <linux/kmsan_types.h> -#include <linux/mutex.h> -#include <linux/plist.h> -#include <linux/hrtimer.h> -#include <linux/irqflags.h> -#include <linux/seccomp.h> -#include <linux/nodemask.h> -#include <linux/rcupdate.h> -#include <linux/refcount.h> +#include <linux/mutex_types.h> +#include <linux/plist_types.h> +#include <linux/hrtimer_types.h> +#include <linux/timer_types.h> +#include <linux/seccomp_types.h> +#include <linux/nodemask_types.h> +#include <linux/refcount_types.h> #include <linux/resource.h> #include <linux/latencytop.h> #include <linux/sched/prio.h> #include <linux/sched/types.h> #include <linux/signal_types.h> -#include <linux/syscall_user_dispatch.h> +#include <linux/syscall_user_dispatch_types.h> #include <linux/mm_types_task.h> #include <linux/task_io_accounting.h> -#include <linux/posix-timers.h> -#include <linux/rseq.h> -#include <linux/seqlock.h> +#include <linux/posix-timers_types.h> +#include <linux/restart_block.h> +#include <uapi/linux/rseq.h> +#include <linux/seqlock_types.h> #include <linux/kcsan.h> #include <linux/rv.h> #include <linux/livepatch_sched.h> +#include <linux/uidgid_types.h> #include <asm/kmap_size.h> /* task_struct member predeclarations (sorted alphabetically): */ @@ -1556,114 +1564,6 @@ struct task_struct { */ }; -static inline struct pid *task_pid(struct task_struct *task) -{ - return task->thread_pid; -} - -/* - * the helpers to get the task's different pids as they are seen - * from various namespaces - * - * task_xid_nr() : global id, i.e. the id seen from the init namespace; - * task_xid_vnr() : virtual id, i.e. the id seen from the pid namespace of - * current. - * task_xid_nr_ns() : id seen from the ns specified; - * - * see also pid_nr() etc in include/linux/pid.h - */ -pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, struct pid_namespace *ns); - -static inline pid_t task_pid_nr(struct task_struct *tsk) -{ - return tsk->pid; -} - -static inline pid_t task_pid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) -{ - return __task_pid_nr_ns(tsk, PIDTYPE_PID, ns); -} - -static inline pid_t task_pid_vnr(struct task_struct *tsk) -{ - return __task_pid_nr_ns(tsk, PIDTYPE_PID, NULL); -} - - -static inline pid_t task_tgid_nr(struct task_struct *tsk) -{ - return tsk->tgid; -} - -/** - * pid_alive - check that a task structure is not stale - * @p: Task structure to be checked. - * - * Test if a process is not yet dead (at most zombie state) - * If pid_alive fails, then pointers within the task structure - * can be stale and must not be dereferenced. - * - * Return: 1 if the process is alive. 0 otherwise. - */ -static inline int pid_alive(const struct task_struct *p) -{ - return p->thread_pid != NULL; -} - -static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) -{ - return __task_pid_nr_ns(tsk, PIDTYPE_PGID, ns); -} - -static inline pid_t task_pgrp_vnr(struct task_struct *tsk) -{ - return __task_pid_nr_ns(tsk, PIDTYPE_PGID, NULL); -} - - -static inline pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) -{ - return __task_pid_nr_ns(tsk, PIDTYPE_SID, ns); -} - -static inline pid_t task_session_vnr(struct task_struct *tsk) -{ - return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL); -} - -static inline pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) -{ - return __task_pid_nr_ns(tsk, PIDTYPE_TGID, ns); -} - -static inline pid_t task_tgid_vnr(struct task_struct *tsk) -{ - return __task_pid_nr_ns(tsk, PIDTYPE_TGID, NULL); -} - -static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns) -{ - pid_t pid = 0; - - rcu_read_lock(); - if (pid_alive(tsk)) - pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns); - rcu_read_unlock(); - - return pid; -} - -static inline pid_t task_ppid_nr(const struct task_struct *tsk) -{ - return task_ppid_nr_ns(tsk, &init_pid_ns); -} - -/* Obsolete, do not use: */ -static inline pid_t task_pgrp_nr(struct task_struct *tsk) -{ - return task_pgrp_nr_ns(tsk, &init_pid_ns); -} - #define TASK_REPORT_IDLE (TASK_REPORT + 1) #define TASK_REPORT_MAX (TASK_REPORT_IDLE << 1) @@ -1707,20 +1607,6 @@ static inline char task_state_to_char(struct task_struct *tsk) return task_index_to_char(task_state_index(tsk)); } -/** - * is_global_init - check if a task structure is init. Since init - * is free to have sub-threads we need to check tgid. - * @tsk: Task structure to be checked. - * - * Check if a task structure is the first user space task the kernel created. - * - * Return: 1 if the task structure is init. 0 otherwise. - */ -static inline int is_global_init(struct task_struct *tsk) -{ - return task_tgid_nr(tsk) == 1; -} - extern struct pid *cad_pid; /* @@ -2170,15 +2056,6 @@ extern int __cond_resched_rwlock_write(rwlock_t *lock); __cond_resched_rwlock_write(lock); \ }) -static inline void cond_resched_rcu(void) -{ -#if defined(CONFIG_DEBUG_ATOMIC_SLEEP) || !defined(CONFIG_PREEMPT_RCU) - rcu_read_unlock(); - cond_resched(); - rcu_read_lock(); -#endif -} - #ifdef CONFIG_PREEMPT_DYNAMIC extern bool preempt_model_none(void); @@ -2220,37 +2097,6 @@ static inline bool preempt_model_preemptible(void) return preempt_model_full() || preempt_model_rt(); } -/* - * Does a critical section need to be broken due to another - * task waiting?: (technically does not depend on CONFIG_PREEMPTION, - * but a general need for low latency) - */ -static inline int spin_needbreak(spinlock_t *lock) -{ -#ifdef CONFIG_PREEMPTION - return spin_is_contended(lock); -#else - return 0; -#endif -} - -/* - * Check if a rwlock is contended. - * Returns non-zero if there is another task waiting on the rwlock. - * Returns zero if the lock is not contended or the system / underlying - * rwlock implementation does not support contention detection. - * Technically does not depend on CONFIG_PREEMPTION, but a general need - * for low latency. - */ -static inline int rwlock_needbreak(rwlock_t *lock) -{ -#ifdef CONFIG_PREEMPTION - return rwlock_is_contended(lock); -#else - return 0; -#endif -} - static __always_inline bool need_resched(void) { return unlikely(tif_need_resched()); @@ -2285,6 +2131,8 @@ extern bool sched_task_on_rq(struct task_struct *p); extern unsigned long get_wchan(struct task_struct *p); extern struct task_struct *cpu_curr_snapshot(int cpu); +#include <linux/spinlock.h> + /* * In order to reduce various lock holder preemption latencies provide an * interface to see if a vCPU is currently running or not. @@ -2321,129 +2169,6 @@ static inline bool owner_on_cpu(struct task_struct *owner) unsigned long sched_cpu_util(int cpu); #endif /* CONFIG_SMP */ -#ifdef CONFIG_RSEQ - -/* - * Map the event mask on the user-space ABI enum rseq_cs_flags - * for direct mask checks. - */ -enum rseq_event_mask_bits { - RSEQ_EVENT_PREEMPT_BIT = RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT, - RSEQ_EVENT_SIGNAL_BIT = RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT, - RSEQ_EVENT_MIGRATE_BIT = RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT, -}; - -enum rseq_event_mask { - RSEQ_EVENT_PREEMPT = (1U << RSEQ_EVENT_PREEMPT_BIT), - RSEQ_EVENT_SIGNAL = (1U << RSEQ_EVENT_SIGNAL_BIT), - RSEQ_EVENT_MIGRATE = (1U << RSEQ_EVENT_MIGRATE_BIT), -}; - -static inline void rseq_set_notify_resume(struct task_struct *t) -{ - if (t->rseq) - set_tsk_thread_flag(t, TIF_NOTIFY_RESUME); -} - -void __rseq_handle_notify_resume(struct ksignal *sig, struct pt_regs *regs); - -static inline void rseq_handle_notify_resume(struct ksignal *ksig, - struct pt_regs *regs) -{ - if (current->rseq) - __rseq_handle_notify_resume(ksig, regs); -} - -static inline void rseq_signal_deliver(struct ksignal *ksig, - struct pt_regs *regs) -{ - preempt_disable(); - __set_bit(RSEQ_EVENT_SIGNAL_BIT, ¤t->rseq_event_mask); - preempt_enable(); - rseq_handle_notify_resume(ksig, regs); -} - -/* rseq_preempt() requires preemption to be disabled. */ -static inline void rseq_preempt(struct task_struct *t) -{ - __set_bit(RSEQ_EVENT_PREEMPT_BIT, &t->rseq_event_mask); - rseq_set_notify_resume(t); -} - -/* rseq_migrate() requires preemption to be disabled. */ -static inline void rseq_migrate(struct task_struct *t) -{ - __set_bit(RSEQ_EVENT_MIGRATE_BIT, &t->rseq_event_mask); - rseq_set_notify_resume(t); -} - -/* - * If parent process has a registered restartable sequences area, the - * child inherits. Unregister rseq for a clone with CLONE_VM set. - */ -static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) -{ - if (clone_flags & CLONE_VM) { - t->rseq = NULL; - t->rseq_len = 0; - t->rseq_sig = 0; - t->rseq_event_mask = 0; - } else { - t->rseq = current->rseq; - t->rseq_len = current->rseq_len; - t->rseq_sig = current->rseq_sig; - t->rseq_event_mask = current->rseq_event_mask; - } -} - -static inline void rseq_execve(struct task_struct *t) -{ - t->rseq = NULL; - t->rseq_len = 0; - t->rseq_sig = 0; - t->rseq_event_mask = 0; -} - -#else - -static inline void rseq_set_notify_resume(struct task_struct *t) -{ -} -static inline void rseq_handle_notify_resume(struct ksignal *ksig, - struct pt_regs *regs) -{ -} -static inline void rseq_signal_deliver(struct ksignal *ksig, - struct pt_regs *regs) -{ -} -static inline void rseq_preempt(struct task_struct *t) -{ -} -static inline void rseq_migrate(struct task_struct *t) -{ -} -static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) -{ -} -static inline void rseq_execve(struct task_struct *t) -{ -} - -#endif - -#ifdef CONFIG_DEBUG_RSEQ - -void rseq_syscall(struct pt_regs *regs); - -#else - -static inline void rseq_syscall(struct pt_regs *regs) -{ -} - -#endif - #ifdef CONFIG_SCHED_CORE extern void sched_core_free(struct task_struct *tsk); extern void sched_core_fork(struct task_struct *p); diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 015c0e3a3e1d..4b7664c56208 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -9,6 +9,7 @@ #include <linux/sched/task.h> #include <linux/cred.h> #include <linux/refcount.h> +#include <linux/pid.h> #include <linux/posix-timers.h> #include <linux/mm_types.h> #include <asm/ptrace.h> diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 4f3dca353556..d362aacf9f89 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -7,6 +7,8 @@ * functionality: */ +#include <linux/rcupdate.h> +#include <linux/refcount.h> #include <linux/sched.h> #include <linux/uaccess.h> diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h index f158b025c175..ccd72b978e1f 100644 --- a/include/linux/sched/task_stack.h +++ b/include/linux/sched/task_stack.h @@ -8,6 +8,7 @@ #include <linux/sched.h> #include <linux/magic.h> +#include <linux/refcount.h> #ifdef CONFIG_THREAD_INFO_IN_TASK diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index 175079552f68..709ad84809e1 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -3,6 +3,7 @@ #define _LINUX_SECCOMP_H #include <uapi/linux/seccomp.h> +#include <linux/seccomp_types.h> #define SECCOMP_FILTER_FLAG_MASK (SECCOMP_FILTER_FLAG_TSYNC | \ SECCOMP_FILTER_FLAG_LOG | \ @@ -21,25 +22,6 @@ #include <linux/atomic.h> #include <asm/seccomp.h> -struct seccomp_filter; -/** - * struct seccomp - the state of a seccomp'ed process - * - * @mode: indicates one of the valid values above for controlled - * system calls available to a process. - * @filter_count: number of seccomp filters - * @filter: must always point to a valid seccomp-filter or NULL as it is - * accessed without locking during system call entry. - * - * @filter must only be accessed from the context of current as there - * is no read locking. - */ -struct seccomp { - int mode; - atomic_t filter_count; - struct seccomp_filter *filter; -}; - #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER extern int __secure_computing(const struct seccomp_data *sd); static inline int secure_computing(void) @@ -64,8 +46,6 @@ static inline int seccomp_mode(struct seccomp *s) #include <linux/errno.h> -struct seccomp { }; -struct seccomp_filter { }; struct seccomp_data; #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER @@ -126,6 +106,8 @@ static inline long seccomp_get_metadata(struct task_struct *task, #ifdef CONFIG_SECCOMP_CACHE_DEBUG struct seq_file; +struct pid_namespace; +struct pid; int proc_pid_seccomp_cache(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task); diff --git a/include/linux/seccomp_types.h b/include/linux/seccomp_types.h new file mode 100644 index 000000000000..cf0a0355024f --- /dev/null +++ b/include/linux/seccomp_types.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_SECCOMP_TYPES_H +#define _LINUX_SECCOMP_TYPES_H + +#include <linux/types.h> + +#ifdef CONFIG_SECCOMP + +struct seccomp_filter; +/** + * struct seccomp - the state of a seccomp'ed process + * + * @mode: indicates one of the valid values above for controlled + * system calls available to a process. + * @filter_count: number of seccomp filters + * @filter: must always point to a valid seccomp-filter or NULL as it is + * accessed without locking during system call entry. + * + * @filter must only be accessed from the context of current as there + * is no read locking. + */ +struct seccomp { + int mode; + atomic_t filter_count; + struct seccomp_filter *filter; +}; + +#else + +struct seccomp { }; +struct seccomp_filter { }; + +#endif + +#endif /* _LINUX_SECCOMP_TYPES_H */ diff --git a/include/linux/sem.h b/include/linux/sem.h index 5608a500c43e..c4deefe42aeb 100644 --- a/include/linux/sem.h +++ b/include/linux/sem.h @@ -3,25 +3,17 @@ #define _LINUX_SEM_H #include <uapi/linux/sem.h> +#include <linux/sem_types.h> struct task_struct; -struct sem_undo_list; #ifdef CONFIG_SYSVIPC -struct sysv_sem { - struct sem_undo_list *undo_list; -}; - extern int copy_semundo(unsigned long clone_flags, struct task_struct *tsk); extern void exit_sem(struct task_struct *tsk); #else -struct sysv_sem { - /* empty */ -}; - static inline int copy_semundo(unsigned long clone_flags, struct task_struct *tsk) { return 0; diff --git a/include/linux/sem_types.h b/include/linux/sem_types.h new file mode 100644 index 000000000000..73df1971a7ae --- /dev/null +++ b/include/linux/sem_types.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_SEM_TYPES_H +#define _LINUX_SEM_TYPES_H + +struct sem_undo_list; + +struct sysv_sem { +#ifdef CONFIG_SYSVIPC + struct sem_undo_list *undo_list; +#endif +}; + +#endif /* _LINUX_SEM_TYPES_H */ diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index e92f9d5577ba..d90d8ee29d81 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -18,6 +18,7 @@ #include <linux/lockdep.h> #include <linux/mutex.h> #include <linux/preempt.h> +#include <linux/seqlock_types.h> #include <linux/spinlock.h> #include <asm/processor.h> @@ -37,37 +38,6 @@ */ #define KCSAN_SEQLOCK_REGION_MAX 1000 -/* - * Sequence counters (seqcount_t) - * - * This is the raw counting mechanism, without any writer protection. - * - * Write side critical sections must be serialized and non-preemptible. - * - * If readers can be invoked from hardirq or softirq contexts, - * interrupts or bottom halves must also be respectively disabled before - * entering the write section. - * - * This mechanism can't be used if the protected data contains pointers, - * as the writer can invalidate a pointer that a reader is following. - * - * If the write serialization mechanism is one of the common kernel - * locking primitives, use a sequence counter with associated lock - * (seqcount_LOCKNAME_t) instead. - * - * If it's desired to automatically handle the sequence counter writer - * serialization and non-preemptibility requirements, use a sequential - * lock (seqlock_t) instead. - * - * See Documentation/locking/seqlock.rst - */ -typedef struct seqcount { - unsigned sequence; -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lockdep_map dep_map; -#endif -} seqcount_t; - static inline void __seqcount_init(seqcount_t *s, const char *name, struct lock_class_key *key) { @@ -132,28 +102,6 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s) */ /* - * For PREEMPT_RT, seqcount_LOCKNAME_t write side critical sections cannot - * disable preemption. It can lead to higher latencies, and the write side - * sections will not be able to acquire locks which become sleeping locks - * (e.g. spinlock_t). - * - * To remain preemptible while avoiding a possible livelock caused by the - * reader preempting the writer, use a different technique: let the reader - * detect if a seqcount_LOCKNAME_t writer is in progress. If that is the - * case, acquire then release the associated LOCKNAME writer serialization - * lock. This will allow any possibly-preempted writer to make progress - * until the end of its writer serialization lock critical section. - * - * This lock-unlock technique must be implemented for all of PREEMPT_RT - * sleeping locks. See Documentation/locking/locktypes.rst - */ -#if defined(CONFIG_LOCKDEP) || defined(CONFIG_PREEMPT_RT) -#define __SEQ_LOCK(expr) expr -#else -#define __SEQ_LOCK(expr) -#endif - -/* * typedef seqcount_LOCKNAME_t - sequence counter with LOCKNAME associated * @seqcount: The real sequence counter * @lock: Pointer to the associated lock @@ -194,11 +142,6 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s) * @lockbase: prefix for associated lock/unlock */ #define SEQCOUNT_LOCKNAME(lockname, locktype, preemptible, lockbase) \ -typedef struct seqcount_##lockname { \ - seqcount_t seqcount; \ - __SEQ_LOCK(locktype *lock); \ -} seqcount_##lockname##_t; \ - \ static __always_inline seqcount_t * \ __seqprop_##lockname##_ptr(seqcount_##lockname##_t *s) \ { \ @@ -284,6 +227,7 @@ SEQCOUNT_LOCKNAME(raw_spinlock, raw_spinlock_t, false, raw_spin) SEQCOUNT_LOCKNAME(spinlock, spinlock_t, __SEQ_RT, spin) SEQCOUNT_LOCKNAME(rwlock, rwlock_t, __SEQ_RT, read) SEQCOUNT_LOCKNAME(mutex, struct mutex, true, mutex) +#undef SEQCOUNT_LOCKNAME /* * SEQCNT_LOCKNAME_ZERO - static initializer for seqcount_LOCKNAME_t @@ -794,25 +738,6 @@ static inline void raw_write_seqcount_latch(seqcount_latch_t *s) smp_wmb(); /* increment "sequence" before following stores */ } -/* - * Sequential locks (seqlock_t) - * - * Sequence counters with an embedded spinlock for writer serialization - * and non-preemptibility. - * - * For more info, see: - * - Comments on top of seqcount_t - * - Documentation/locking/seqlock.rst - */ -typedef struct { - /* - * Make sure that readers don't starve writers on PREEMPT_RT: use - * seqcount_spinlock_t instead of seqcount_t. Check __SEQ_LOCK(). - */ - seqcount_spinlock_t seqcount; - spinlock_t lock; -} seqlock_t; - #define __SEQLOCK_UNLOCKED(lockname) \ { \ .seqcount = SEQCNT_SPINLOCK_ZERO(lockname, &(lockname).lock), \ diff --git a/include/linux/seqlock_types.h b/include/linux/seqlock_types.h new file mode 100644 index 000000000000..dfdf43e3fa3d --- /dev/null +++ b/include/linux/seqlock_types.h @@ -0,0 +1,93 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_SEQLOCK_TYPES_H +#define __LINUX_SEQLOCK_TYPES_H + +#include <linux/lockdep_types.h> +#include <linux/mutex_types.h> +#include <linux/spinlock_types.h> + +/* + * Sequence counters (seqcount_t) + * + * This is the raw counting mechanism, without any writer protection. + * + * Write side critical sections must be serialized and non-preemptible. + * + * If readers can be invoked from hardirq or softirq contexts, + * interrupts or bottom halves must also be respectively disabled before + * entering the write section. + * + * This mechanism can't be used if the protected data contains pointers, + * as the writer can invalidate a pointer that a reader is following. + * + * If the write serialization mechanism is one of the common kernel + * locking primitives, use a sequence counter with associated lock + * (seqcount_LOCKNAME_t) instead. + * + * If it's desired to automatically handle the sequence counter writer + * serialization and non-preemptibility requirements, use a sequential + * lock (seqlock_t) instead. + * + * See Documentation/locking/seqlock.rst + */ +typedef struct seqcount { + unsigned sequence; +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif +} seqcount_t; + +/* + * For PREEMPT_RT, seqcount_LOCKNAME_t write side critical sections cannot + * disable preemption. It can lead to higher latencies, and the write side + * sections will not be able to acquire locks which become sleeping locks + * (e.g. spinlock_t). + * + * To remain preemptible while avoiding a possible livelock caused by the + * reader preempting the writer, use a different technique: let the reader + * detect if a seqcount_LOCKNAME_t writer is in progress. If that is the + * case, acquire then release the associated LOCKNAME writer serialization + * lock. This will allow any possibly-preempted writer to make progress + * until the end of its writer serialization lock critical section. + * + * This lock-unlock technique must be implemented for all of PREEMPT_RT + * sleeping locks. See Documentation/locking/locktypes.rst + */ +#if defined(CONFIG_LOCKDEP) || defined(CONFIG_PREEMPT_RT) +#define __SEQ_LOCK(expr) expr +#else +#define __SEQ_LOCK(expr) +#endif + +#define SEQCOUNT_LOCKNAME(lockname, locktype, preemptible, lockbase) \ +typedef struct seqcount_##lockname { \ + seqcount_t seqcount; \ + __SEQ_LOCK(locktype *lock); \ +} seqcount_##lockname##_t; + +SEQCOUNT_LOCKNAME(raw_spinlock, raw_spinlock_t, false, raw_spin) +SEQCOUNT_LOCKNAME(spinlock, spinlock_t, __SEQ_RT, spin) +SEQCOUNT_LOCKNAME(rwlock, rwlock_t, __SEQ_RT, read) +SEQCOUNT_LOCKNAME(mutex, struct mutex, true, mutex) +#undef SEQCOUNT_LOCKNAME + +/* + * Sequential locks (seqlock_t) + * + * Sequence counters with an embedded spinlock for writer serialization + * and non-preemptibility. + * + * For more info, see: + * - Comments on top of seqcount_t + * - Documentation/locking/seqlock.rst + */ +typedef struct { + /* + * Make sure that readers don't starve writers on PREEMPT_RT: use + * seqcount_spinlock_t instead of seqcount_t. Check __SEQ_LOCK(). + */ + seqcount_spinlock_t seqcount; + spinlock_t lock; +} seqlock_t; + +#endif /* __LINUX_SEQLOCK_TYPES_H */ diff --git a/include/linux/shm.h b/include/linux/shm.h index d8e69aed3d32..c55bef0538e5 100644 --- a/include/linux/shm.h +++ b/include/linux/shm.h @@ -2,12 +2,12 @@ #ifndef _LINUX_SHM_H_ #define _LINUX_SHM_H_ -#include <linux/list.h> +#include <linux/types.h> #include <asm/page.h> -#include <uapi/linux/shm.h> #include <asm/shmparam.h> struct file; +struct task_struct; #ifdef CONFIG_SYSVIPC struct sysv_shm { diff --git a/include/linux/signal.h b/include/linux/signal.h index 3b98e7a28538..f19816832f05 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -3,6 +3,7 @@ #define _LINUX_SIGNAL_H #include <linux/bug.h> +#include <linux/list.h> #include <linux/signal_types.h> #include <linux/string.h> diff --git a/include/linux/signal_types.h b/include/linux/signal_types.h index a70b2bdbf4d9..caf4f7a59ab9 100644 --- a/include/linux/signal_types.h +++ b/include/linux/signal_types.h @@ -6,7 +6,7 @@ * Basic signal handling related data type definitions: */ -#include <linux/list.h> +#include <linux/types.h> #include <uapi/linux/signal.h> typedef struct kernel_siginfo { diff --git a/include/linux/sizes.h b/include/linux/sizes.h index 84aa448d8bb3..c3a00b967d18 100644 --- a/include/linux/sizes.h +++ b/include/linux/sizes.h @@ -47,8 +47,17 @@ #define SZ_8G _AC(0x200000000, ULL) #define SZ_16G _AC(0x400000000, ULL) #define SZ_32G _AC(0x800000000, ULL) +#define SZ_64G _AC(0x1000000000, ULL) +#define SZ_128G _AC(0x2000000000, ULL) +#define SZ_256G _AC(0x4000000000, ULL) +#define SZ_512G _AC(0x8000000000, ULL) #define SZ_1T _AC(0x10000000000, ULL) +#define SZ_2T _AC(0x20000000000, ULL) +#define SZ_4T _AC(0x40000000000, ULL) +#define SZ_8T _AC(0x80000000000, ULL) +#define SZ_16T _AC(0x100000000000, ULL) +#define SZ_32T _AC(0x200000000000, ULL) #define SZ_64T _AC(0x400000000000, ULL) #endif /* __LINUX_SIZES_H__ */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 27998f73183e..a5ae952454c8 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -566,6 +566,15 @@ struct ubuf_info_msgzc { int mm_account_pinned_pages(struct mmpin *mmp, size_t size); void mm_unaccount_pinned_pages(struct mmpin *mmp); +/* Preserve some data across TX submission and completion. + * + * Note, this state is stored in the driver. Extending the layout + * might need some special care. + */ +struct xsk_tx_metadata_compl { + __u64 *tx_timestamp; +}; + /* This data is invariant across clones and lives at * the end of the header data, ie. at skb->end. */ @@ -578,7 +587,10 @@ struct skb_shared_info { /* Warning: this field is not always filled in (UFO)! */ unsigned short gso_segs; struct sk_buff *frag_list; - struct skb_shared_hwtstamps hwtstamps; + union { + struct skb_shared_hwtstamps hwtstamps; + struct xsk_tx_metadata_compl xsk_meta; + }; unsigned int gso_type; u32 tskey; @@ -742,7 +754,6 @@ typedef unsigned char *sk_buff_data_t; * @dev_scratch: (aka @dev) alternate use of @dev when @dev would be %NULL * @cb: Control buffer. Free for use by every layer. Put private vars here * @_skb_refdst: destination entry (with norefcount bit) - * @sp: the security path, used for xfrm * @len: Length of actual data * @data_len: Data length * @mac_len: Length of link layer header @@ -776,7 +787,6 @@ typedef unsigned char *sk_buff_data_t; * @tcp_tsorted_anchor: list structure for TCP (tp->tsorted_sent_queue) * @_sk_redir: socket redirection information for skmsg * @_nfct: Associated connection, if any (with nfctinfo bits) - * @nf_bridge: Saved data about a bridged frame - see br_netfilter.c * @skb_iif: ifindex of device we arrived on * @tc_index: Traffic control index * @hash: the packet hash @@ -1057,7 +1067,7 @@ struct sk_buff { refcount_t users; #ifdef CONFIG_SKB_EXTENSIONS - /* only useable after checking ->active_extensions != 0 */ + /* only usable after checking ->active_extensions != 0 */ struct skb_ext *extensions; #endif }; @@ -3299,7 +3309,7 @@ static inline struct page *__dev_alloc_pages(gfp_t gfp_mask, unsigned int order) { /* This piece of code contains several assumptions. - * 1. This is for device Rx, therefor a cold page is preferred. + * 1. This is for device Rx, therefore a cold page is preferred. * 2. The expectation is the user wants a compound page. * 3. If requesting a order 0 page it will not be compound * due to the check to see if order has a value in prep_new_page @@ -3997,6 +4007,7 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, netdev_features_t features unsigned int offset); struct sk_buff *skb_vlan_untag(struct sk_buff *skb); int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len); +int skb_ensure_writable_head_tail(struct sk_buff *skb, struct net_device *dev); int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci); int skb_vlan_pop(struct sk_buff *skb); int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci); @@ -4235,10 +4246,13 @@ static inline bool __skb_metadata_differs(const struct sk_buff *skb_a, { const void *a = skb_metadata_end(skb_a); const void *b = skb_metadata_end(skb_b); - /* Using more efficient varaiant than plain call to memcmp(). */ -#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 u64 diffs = 0; + if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) || + BITS_PER_LONG != 64) + goto slow; + + /* Using more efficient variant than plain call to memcmp(). */ switch (meta_len) { #define __it(x, op) (x -= sizeof(u##op)) #define __it_diff(a, b, op) (*(u##op *)__it(a, op)) ^ (*(u##op *)__it(b, op)) @@ -4258,11 +4272,11 @@ static inline bool __skb_metadata_differs(const struct sk_buff *skb_a, fallthrough; case 4: diffs |= __it_diff(a, b, 32); break; + default: +slow: + return memcmp(a - meta_len, b - meta_len, meta_len); } return diffs; -#else - return memcmp(a - meta_len, b - meta_len, meta_len); -#endif } static inline bool skb_metadata_differs(const struct sk_buff *skb_a, diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index c953b8c0d2f4..888a4b217829 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -100,6 +100,11 @@ struct sk_psock { void (*saved_close)(struct sock *sk, long timeout); void (*saved_write_space)(struct sock *sk); void (*saved_data_ready)(struct sock *sk); + /* psock_update_sk_prot may be called with restore=false many times + * so the handler must be safe for this case. It will be called + * exactly once with restore=true when the psock is being destroyed + * and psock refcnt is zero, but before an RCU grace period. + */ int (*psock_update_sk_prot)(struct sock *sk, struct sk_psock *psock, bool restore); struct proto *sk_proto; diff --git a/include/linux/soc/apple/rtkit.h b/include/linux/soc/apple/rtkit.h index fc456f75c131..8c9ca857ccf6 100644 --- a/include/linux/soc/apple/rtkit.h +++ b/include/linux/soc/apple/rtkit.h @@ -161,24 +161,6 @@ int apple_rtkit_send_message(struct apple_rtkit *rtk, u8 ep, u64 message, struct completion *completion, bool atomic); /* - * Send a message to the given endpoint and wait until it has been submitted - * to the hardware FIFO. - * Will return zero on success and a negative error code on failure - * (e.g. -ETIME when the message couldn't be written within the given - * timeout) - * - * @rtk: RTKit reference - * @ep: target endpoint - * @message: message to be sent - * @timeout: timeout in milliseconds to allow the message transmission - * to be completed - * @atomic: if set to true this function can be called from atomic - * context. - */ -int apple_rtkit_send_message_wait(struct apple_rtkit *rtk, u8 ep, u64 message, - unsigned long timeout, bool atomic); - -/* * Process incoming messages in atomic context. * This only guarantees that messages arrive as far as the recv_message_early * callback; drivers expecting to handle incoming messages synchronously diff --git a/include/linux/soc/mediatek/mtk-mmsys.h b/include/linux/soc/mediatek/mtk-mmsys.h index 2475ef914746..4885b065b849 100644 --- a/include/linux/soc/mediatek/mtk-mmsys.h +++ b/include/linux/soc/mediatek/mtk-mmsys.h @@ -62,6 +62,14 @@ enum mtk_ddp_comp_id { DDP_COMPONENT_OVL_2L1, DDP_COMPONENT_OVL_2L2, DDP_COMPONENT_OVL1, + DDP_COMPONENT_PADDING0, + DDP_COMPONENT_PADDING1, + DDP_COMPONENT_PADDING2, + DDP_COMPONENT_PADDING3, + DDP_COMPONENT_PADDING4, + DDP_COMPONENT_PADDING5, + DDP_COMPONENT_PADDING6, + DDP_COMPONENT_PADDING7, DDP_COMPONENT_POSTMASK0, DDP_COMPONENT_PWM0, DDP_COMPONENT_PWM1, diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 90bc853cafb6..eaac8b0da25b 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -449,6 +449,37 @@ static __always_inline int spin_is_contended(spinlock_t *lock) return raw_spin_is_contended(&lock->rlock); } +/* + * Does a critical section need to be broken due to another + * task waiting?: (technically does not depend on CONFIG_PREEMPTION, + * but a general need for low latency) + */ +static inline int spin_needbreak(spinlock_t *lock) +{ +#ifdef CONFIG_PREEMPTION + return spin_is_contended(lock); +#else + return 0; +#endif +} + +/* + * Check if a rwlock is contended. + * Returns non-zero if there is another task waiting on the rwlock. + * Returns zero if the lock is not contended or the system / underlying + * rwlock implementation does not support contention detection. + * Technically does not depend on CONFIG_PREEMPTION, but a general need + * for low latency. + */ +static inline int rwlock_needbreak(rwlock_t *lock) +{ +#ifdef CONFIG_PREEMPTION + return rwlock_is_contended(lock); +#else + return 0; +#endif +} + #define assert_spin_locked(lock) assert_raw_spin_locked(&(lock)->rlock) #else /* !CONFIG_PREEMPT_RT */ diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 127ef3b2e607..236610e4a8fa 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -229,7 +229,7 @@ static inline int srcu_read_lock_nmisafe(struct srcu_struct *ssp) __acquires(ssp srcu_check_nmi_safety(ssp, true); retval = __srcu_read_lock_nmisafe(ssp); - rcu_lock_acquire(&ssp->dep_map); + rcu_try_lock_acquire(&ssp->dep_map); return retval; } diff --git a/include/linux/sunrpc/bc_xprt.h b/include/linux/sunrpc/bc_xprt.h index db30a159f9d5..f22bf915dcf6 100644 --- a/include/linux/sunrpc/bc_xprt.h +++ b/include/linux/sunrpc/bc_xprt.h @@ -20,7 +20,8 @@ #ifdef CONFIG_SUNRPC_BACKCHANNEL struct rpc_rqst *xprt_lookup_bc_request(struct rpc_xprt *xprt, __be32 xid); void xprt_complete_bc_request(struct rpc_rqst *req, uint32_t copied); -void xprt_init_bc_request(struct rpc_rqst *req, struct rpc_task *task); +void xprt_init_bc_request(struct rpc_rqst *req, struct rpc_task *task, + const struct rpc_timeout *to); void xprt_free_bc_request(struct rpc_rqst *req); int xprt_setup_backchannel(struct rpc_xprt *, unsigned int min_reqs); void xprt_destroy_backchannel(struct rpc_xprt *, unsigned int max_reqs); diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index e9d4377d03c6..5e9d1469c6fa 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -252,7 +252,6 @@ void rpc_clnt_probe_trunked_xprts(struct rpc_clnt *, const char *rpc_proc_name(const struct rpc_task *task); -void rpc_clnt_xprt_switch_put(struct rpc_clnt *); void rpc_clnt_xprt_switch_add_xprt(struct rpc_clnt *, struct rpc_xprt *); void rpc_clnt_xprt_switch_remove_xprt(struct rpc_clnt *, struct rpc_xprt *); bool rpc_clnt_xprt_switch_has_addr(struct rpc_clnt *clnt, diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 8ada7dc802d3..2d61987b3545 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -38,6 +38,17 @@ struct rpc_wait { }; /* + * This describes a timeout strategy + */ +struct rpc_timeout { + unsigned long to_initval, /* initial timeout */ + to_maxval, /* max timeout */ + to_increment; /* if !exponential */ + unsigned int to_retries; /* max # of retries */ + unsigned char to_exponential; +}; + +/* * This is the RPC task struct */ struct rpc_task { @@ -205,7 +216,8 @@ struct rpc_wait_queue { */ struct rpc_task *rpc_new_task(const struct rpc_task_setup *); struct rpc_task *rpc_run_task(const struct rpc_task_setup *); -struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req); +struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req, + struct rpc_timeout *timeout); void rpc_put_task(struct rpc_task *); void rpc_put_task_async(struct rpc_task *); bool rpc_task_set_rpc_status(struct rpc_task *task, int rpc_status); diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index b10f987509cc..67cf1c9efd80 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -69,7 +69,6 @@ struct svc_serv { struct svc_program * sv_program; /* RPC program */ struct svc_stat * sv_stats; /* RPC statistics */ spinlock_t sv_lock; - struct kref sv_refcnt; unsigned int sv_nrthreads; /* # of server threads */ unsigned int sv_maxconn; /* max connections allowed or * '0' causing max to be based @@ -97,31 +96,13 @@ struct svc_serv { #endif /* CONFIG_SUNRPC_BACKCHANNEL */ }; -/** - * svc_get() - increment reference count on a SUNRPC serv - * @serv: the svc_serv to have count incremented - * - * Returns: the svc_serv that was passed in. - */ -static inline struct svc_serv *svc_get(struct svc_serv *serv) -{ - kref_get(&serv->sv_refcnt); - return serv; -} - -void svc_destroy(struct kref *); +/* This is used by pool_stats to find and lock an svc */ +struct svc_info { + struct svc_serv *serv; + struct mutex *mutex; +}; -/** - * svc_put - decrement reference count on a SUNRPC serv - * @serv: the svc_serv to have count decremented - * - * When the reference count reaches zero, svc_destroy() - * is called to clean up and free the serv. - */ -static inline void svc_put(struct svc_serv *serv) -{ - kref_put(&serv->sv_refcnt, svc_destroy); -} +void svc_destroy(struct svc_serv **svcp); /* * Maximum payload size supported by a kernel RPC server. @@ -250,6 +231,8 @@ struct svc_rqst { struct net *rq_bc_net; /* pointer to backchannel's * net namespace */ + unsigned long bc_to_initval; + unsigned int bc_to_retries; void ** rq_lease_breaker; /* The v4 client breaking a lease */ unsigned int rq_status_counter; /* RPC processing counter */ }; @@ -260,8 +243,6 @@ enum { RQ_LOCAL, /* local request */ RQ_USEDEFERRAL, /* use deferral */ RQ_DROPME, /* drop current reply */ - RQ_SPLICE_OK, /* turned off in gss privacy to prevent - * encrypting page cache pages */ RQ_VICTIM, /* Have agreed to shut down */ RQ_DATA, /* request has data */ }; @@ -433,7 +414,7 @@ void svc_exit_thread(struct svc_rqst *); struct svc_serv * svc_create_pooled(struct svc_program *, unsigned int, int (*threadfn)(void *data)); int svc_set_num_threads(struct svc_serv *, struct svc_pool *, int); -int svc_pool_stats_open(struct svc_serv *serv, struct file *file); +int svc_pool_stats_open(struct svc_info *si, struct file *file); void svc_process(struct svc_rqst *rqstp); void svc_process_bc(struct rpc_rqst *req, struct svc_rqst *rqstp); int svc_register(const struct svc_serv *, struct net *, const int, diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index a5ee0af2a310..e7595ae62fe2 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -65,6 +65,7 @@ extern unsigned int svcrdma_ord; extern unsigned int svcrdma_max_requests; extern unsigned int svcrdma_max_bc_requests; extern unsigned int svcrdma_max_req_size; +extern struct workqueue_struct *svcrdma_wq; extern struct percpu_counter svcrdma_stat_read; extern struct percpu_counter svcrdma_stat_recv; @@ -97,6 +98,7 @@ struct svcxprt_rdma { u32 sc_pending_recvs; u32 sc_recv_batch; struct list_head sc_rq_dto_q; + struct list_head sc_read_complete_q; spinlock_t sc_rq_dto_lock; struct ib_qp *sc_qp; struct ib_cq *sc_rq_cq; @@ -115,6 +117,13 @@ struct svcxprt_rdma { /* sc_flags */ #define RDMAXPRT_CONN_PENDING 3 +static inline struct svcxprt_rdma *svc_rdma_rqst_rdma(struct svc_rqst *rqstp) +{ + struct svc_xprt *xprt = rqstp->rq_xprt; + + return container_of(xprt, struct svcxprt_rdma, sc_xprt); +} + /* * Default connection parameters */ @@ -126,6 +135,43 @@ enum { #define RPCSVC_MAXPAYLOAD_RDMA RPCSVC_MAXPAYLOAD +/** + * svc_rdma_send_cid_init - Initialize a Receive Queue completion ID + * @rdma: controlling transport + * @cid: completion ID to initialize + */ +static inline void svc_rdma_recv_cid_init(struct svcxprt_rdma *rdma, + struct rpc_rdma_cid *cid) +{ + cid->ci_queue_id = rdma->sc_rq_cq->res.id; + cid->ci_completion_id = atomic_inc_return(&rdma->sc_completion_ids); +} + +/** + * svc_rdma_send_cid_init - Initialize a Send Queue completion ID + * @rdma: controlling transport + * @cid: completion ID to initialize + */ +static inline void svc_rdma_send_cid_init(struct svcxprt_rdma *rdma, + struct rpc_rdma_cid *cid) +{ + cid->ci_queue_id = rdma->sc_sq_cq->res.id; + cid->ci_completion_id = atomic_inc_return(&rdma->sc_completion_ids); +} + +/* + * A chunk context tracks all I/O for moving one Read or Write + * chunk. This is a set of rdma_rw's that handle data movement + * for all segments of one chunk. + */ +struct svc_rdma_chunk_ctxt { + struct rpc_rdma_cid cc_cid; + struct ib_cqe cc_cqe; + struct list_head cc_rwctxts; + ktime_t cc_posttime; + int cc_sqecount; +}; + struct svc_rdma_recv_ctxt { struct llist_node rc_node; struct list_head rc_list; @@ -136,22 +182,33 @@ struct svc_rdma_recv_ctxt { void *rc_recv_buf; struct xdr_stream rc_stream; u32 rc_byte_len; - unsigned int rc_page_count; u32 rc_inv_rkey; __be32 rc_msgtype; + /* State for pulling a Read chunk */ + unsigned int rc_pageoff; + unsigned int rc_curpage; + unsigned int rc_readbytes; + struct xdr_buf rc_saved_arg; + struct svc_rdma_chunk_ctxt rc_cc; + struct svc_rdma_pcl rc_call_pcl; struct svc_rdma_pcl rc_read_pcl; struct svc_rdma_chunk *rc_cur_result_payload; struct svc_rdma_pcl rc_write_pcl; struct svc_rdma_pcl rc_reply_pcl; + + unsigned int rc_page_count; + struct page *rc_pages[RPCSVC_MAXPAGES]; }; struct svc_rdma_send_ctxt { struct llist_node sc_node; struct rpc_rdma_cid sc_cid; + struct work_struct sc_work; + struct svcxprt_rdma *sc_rdma; struct ib_send_wr sc_send_wr; struct ib_cqe sc_cqe; struct xdr_buf sc_hdrbuf; @@ -180,6 +237,11 @@ extern int svc_rdma_recvfrom(struct svc_rqst *); /* svc_rdma_rw.c */ extern void svc_rdma_destroy_rw_ctxts(struct svcxprt_rdma *rdma); +extern void svc_rdma_cc_init(struct svcxprt_rdma *rdma, + struct svc_rdma_chunk_ctxt *cc); +extern void svc_rdma_cc_release(struct svcxprt_rdma *rdma, + struct svc_rdma_chunk_ctxt *cc, + enum dma_data_direction dir); extern int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma, const struct svc_rdma_chunk *chunk, const struct xdr_buf *xdr); @@ -200,7 +262,8 @@ extern int svc_rdma_send(struct svcxprt_rdma *rdma, struct svc_rdma_send_ctxt *ctxt); extern int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma, struct svc_rdma_send_ctxt *sctxt, - const struct svc_rdma_recv_ctxt *rctxt, + const struct svc_rdma_pcl *write_pcl, + const struct svc_rdma_pcl *reply_pcl, const struct xdr_buf *xdr); extern void svc_rdma_send_error_msg(struct svcxprt_rdma *rdma, struct svc_rdma_send_ctxt *sctxt, diff --git a/include/linux/sunrpc/svcauth.h b/include/linux/sunrpc/svcauth.h index 6f90203edbf8..61c455f1e1f5 100644 --- a/include/linux/sunrpc/svcauth.h +++ b/include/linux/sunrpc/svcauth.h @@ -131,8 +131,11 @@ enum svc_auth_status { * This call releases a domain. * * set_client() - * Givens a pending request (struct svc_rqst), finds and assigns + * Given a pending request (struct svc_rqst), finds and assigns * an appropriate 'auth_domain' as the client. + * + * pseudoflavor() + * Returns RPC_AUTH pseudoflavor in use by @rqstp. */ struct auth_ops { char * name; @@ -143,11 +146,13 @@ struct auth_ops { int (*release)(struct svc_rqst *rqstp); void (*domain_release)(struct auth_domain *dom); enum svc_auth_status (*set_client)(struct svc_rqst *rqstp); + rpc_authflavor_t (*pseudoflavor)(struct svc_rqst *rqstp); }; struct svc_xprt; extern enum svc_auth_status svc_authenticate(struct svc_rqst *rqstp); +extern rpc_authflavor_t svc_auth_flavor(struct svc_rqst *rqstp); extern int svc_authorise(struct svc_rqst *rqstp); extern enum svc_auth_status svc_set_client(struct svc_rqst *rqstp); extern int svc_auth_register(rpc_authflavor_t flavor, struct auth_ops *aops); diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index f85d3a0daca2..464f6a9492ab 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -30,17 +30,6 @@ #define RPC_MAXCWND(xprt) ((xprt)->max_reqs << RPC_CWNDSHIFT) #define RPCXPRT_CONGESTED(xprt) ((xprt)->cong >= (xprt)->cwnd) -/* - * This describes a timeout strategy - */ -struct rpc_timeout { - unsigned long to_initval, /* initial timeout */ - to_maxval, /* max timeout */ - to_increment; /* if !exponential */ - unsigned int to_retries; /* max # of retries */ - unsigned char to_exponential; -}; - enum rpc_display_format_t { RPC_DISPLAY_ADDR = 0, RPC_DISPLAY_PORT, diff --git a/include/linux/syscall_user_dispatch.h b/include/linux/syscall_user_dispatch.h index 641ca8880995..3858a6ffdd5c 100644 --- a/include/linux/syscall_user_dispatch.h +++ b/include/linux/syscall_user_dispatch.h @@ -6,16 +6,10 @@ #define _SYSCALL_USER_DISPATCH_H #include <linux/thread_info.h> +#include <linux/syscall_user_dispatch_types.h> #ifdef CONFIG_GENERIC_ENTRY -struct syscall_user_dispatch { - char __user *selector; - unsigned long offset; - unsigned long len; - bool on_dispatch; -}; - int set_syscall_user_dispatch(unsigned long mode, unsigned long offset, unsigned long len, char __user *selector); @@ -29,7 +23,6 @@ int syscall_user_dispatch_set_config(struct task_struct *task, unsigned long siz void __user *data); #else -struct syscall_user_dispatch {}; static inline int set_syscall_user_dispatch(unsigned long mode, unsigned long offset, unsigned long len, char __user *selector) diff --git a/include/linux/syscall_user_dispatch_types.h b/include/linux/syscall_user_dispatch_types.h new file mode 100644 index 000000000000..3be36b06c7d7 --- /dev/null +++ b/include/linux/syscall_user_dispatch_types.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _SYSCALL_USER_DISPATCH_TYPES_H +#define _SYSCALL_USER_DISPATCH_TYPES_H + +#include <linux/types.h> + +#ifdef CONFIG_GENERIC_ENTRY + +struct syscall_user_dispatch { + char __user *selector; + unsigned long offset; + unsigned long len; + bool on_dispatch; +}; + +#else + +struct syscall_user_dispatch {}; + +#endif + +#endif /* _SYSCALL_USER_DISPATCH_TYPES_H */ diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 5c0dbef55792..cdba4d0c6d4a 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -414,7 +414,7 @@ asmlinkage long sys_statmount(const struct mnt_id_req __user *req, struct statmount __user *buf, size_t bufsize, unsigned int flags); asmlinkage long sys_listmount(const struct mnt_id_req __user *req, - u64 __user *buf, size_t bufsize, + u64 __user *mnt_ids, size_t nr_mnt_ids, unsigned int flags); asmlinkage long sys_truncate(const char __user *path, long length); asmlinkage long sys_ftruncate(unsigned int fd, unsigned long length); diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 61b40ea81f4d..ee7d33b89e9e 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -210,11 +210,6 @@ struct ctl_table_root { int (*permissions)(struct ctl_table_header *head, struct ctl_table *table); }; -/* struct ctl_path describes where in the hierarchy a table is added */ -struct ctl_path { - const char *procname; -}; - #define register_sysctl(path, table) \ register_sysctl_sz(path, table, ARRAY_SIZE(table)) @@ -255,8 +250,6 @@ extern int unaligned_enabled; extern int unaligned_dump_stack; extern int no_unaligned_warning; -#define SYSCTL_PERM_EMPTY_DIR (1 << 0) - #else /* CONFIG_SYSCTL */ static inline void register_sysctl_init(const char *path, struct ctl_table *table) diff --git a/include/linux/tcp.h b/include/linux/tcp.h index b646b574b060..89b290d8c8dc 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -190,23 +190,121 @@ static inline bool tcp_rsk_used_ao(const struct request_sock *req) #define TCP_RMEM_TO_WIN_SCALE 8 struct tcp_sock { + /* Cacheline organization can be found documented in + * Documentation/networking/net_cachelines/tcp_sock.rst. + * Please update the document when adding new fields. + */ + /* inet_connection_sock has to be the first member of tcp_sock */ struct inet_connection_sock inet_conn; - u16 tcp_header_len; /* Bytes of tcp header to send */ + + /* TX read-mostly hotpath cache lines */ + __cacheline_group_begin(tcp_sock_read_tx); + /* timestamp of last sent data packet (for restart window) */ + u32 max_window; /* Maximal window ever seen from peer */ + u32 rcv_ssthresh; /* Current window clamp */ + u32 reordering; /* Packet reordering metric. */ + u32 notsent_lowat; /* TCP_NOTSENT_LOWAT */ u16 gso_segs; /* Max number of segs per GSO packet */ + /* from STCP, retrans queue hinting */ + struct sk_buff *lost_skb_hint; + struct sk_buff *retransmit_skb_hint; + __cacheline_group_end(tcp_sock_read_tx); + + /* TXRX read-mostly hotpath cache lines */ + __cacheline_group_begin(tcp_sock_read_txrx); + u32 tsoffset; /* timestamp offset */ + u32 snd_wnd; /* The window we expect to receive */ + u32 mss_cache; /* Cached effective mss, not including SACKS */ + u32 snd_cwnd; /* Sending congestion window */ + u32 prr_out; /* Total number of pkts sent during Recovery. */ + u32 lost_out; /* Lost packets */ + u32 sacked_out; /* SACK'd packets */ + u16 tcp_header_len; /* Bytes of tcp header to send */ + u8 chrono_type : 2, /* current chronograph type */ + repair : 1, + is_sack_reneg:1, /* in recovery from loss with SACK reneg? */ + is_cwnd_limited:1;/* forward progress limited by snd_cwnd? */ + __cacheline_group_end(tcp_sock_read_txrx); + + /* RX read-mostly hotpath cache lines */ + __cacheline_group_begin(tcp_sock_read_rx); + u32 copied_seq; /* Head of yet unread data */ + u32 rcv_tstamp; /* timestamp of last received ACK (for keepalives) */ + u32 snd_wl1; /* Sequence for window update */ + u32 tlp_high_seq; /* snd_nxt at the time of TLP */ + u32 rttvar_us; /* smoothed mdev_max */ + u32 retrans_out; /* Retransmitted packets out */ + u16 advmss; /* Advertised MSS */ + u16 urg_data; /* Saved octet of OOB data and control flags */ + u32 lost; /* Total data packets lost incl. rexmits */ + struct minmax rtt_min; + /* OOO segments go in this rbtree. Socket lock must be held. */ + struct rb_root out_of_order_queue; + u32 snd_ssthresh; /* Slow start size threshold */ + __cacheline_group_end(tcp_sock_read_rx); + /* TX read-write hotpath cache lines */ + __cacheline_group_begin(tcp_sock_write_tx) ____cacheline_aligned; + u32 segs_out; /* RFC4898 tcpEStatsPerfSegsOut + * The total number of segments sent. + */ + u32 data_segs_out; /* RFC4898 tcpEStatsPerfDataSegsOut + * total number of data segments sent. + */ + u64 bytes_sent; /* RFC4898 tcpEStatsPerfHCDataOctetsOut + * total number of data bytes sent. + */ + u32 snd_sml; /* Last byte of the most recently transmitted small packet */ + u32 chrono_start; /* Start time in jiffies of a TCP chrono */ + u32 chrono_stat[3]; /* Time in jiffies for chrono_stat stats */ + u32 write_seq; /* Tail(+1) of data held in tcp send buffer */ + u32 pushed_seq; /* Last pushed seq, required to talk to windows */ + u32 lsndtime; + u32 mdev_us; /* medium deviation */ + u64 tcp_wstamp_ns; /* departure time for next sent data packet */ + u64 tcp_clock_cache; /* cache last tcp_clock_ns() (see tcp_mstamp_refresh()) */ + u64 tcp_mstamp; /* most recent packet received/sent */ + u32 rtt_seq; /* sequence number to update rttvar */ + struct list_head tsorted_sent_queue; /* time-sorted sent but un-SACKed skbs */ + struct sk_buff *highest_sack; /* skb just after the highest + * skb with SACKed bit set + * (validity guaranteed only if + * sacked_out > 0) + */ + u8 ecn_flags; /* ECN status bits. */ + __cacheline_group_end(tcp_sock_write_tx); + + /* TXRX read-write hotpath cache lines */ + __cacheline_group_begin(tcp_sock_write_txrx); /* * Header prediction flags * 0x5?10 << 16 + snd_wnd in net byte order */ __be32 pred_flags; - + u32 rcv_nxt; /* What we want to receive next */ + u32 snd_nxt; /* Next sequence we send */ + u32 snd_una; /* First byte we want an ack for */ + u32 window_clamp; /* Maximal window to advertise */ + u32 srtt_us; /* smoothed round trip time << 3 in usecs */ + u32 packets_out; /* Packets which are "in flight" */ + u32 snd_up; /* Urgent pointer */ + u32 delivered; /* Total data packets delivered incl. rexmits */ + u32 delivered_ce; /* Like the above but only ECE marked packets */ + u32 app_limited; /* limited until "delivered" reaches this val */ + u32 rcv_wnd; /* Current receiver window */ /* - * RFC793 variables by their proper names. This means you can - * read the code and the spec side by side (and laugh ...) - * See RFC793 and RFC1122. The RFC writes these in capitals. + * Options received (usually on last packet, some only on SYN packets). */ - u64 bytes_received; /* RFC4898 tcpEStatsAppHCThruOctetsReceived + struct tcp_options_received rx_opt; + u8 nonagle : 4,/* Disable Nagle algorithm? */ + rate_app_limited:1; /* rate_{delivered,interval_us} limited? */ + __cacheline_group_end(tcp_sock_write_txrx); + + /* RX read-write hotpath cache lines */ + __cacheline_group_begin(tcp_sock_write_rx); + u64 bytes_received; + /* RFC4898 tcpEStatsAppHCThruOctetsReceived * sum(delta(rcv_nxt)), or how many bytes * were acked. */ @@ -216,45 +314,44 @@ struct tcp_sock { u32 data_segs_in; /* RFC4898 tcpEStatsPerfDataSegsIn * total number of data segments in. */ - u32 rcv_nxt; /* What we want to receive next */ - u32 copied_seq; /* Head of yet unread data */ u32 rcv_wup; /* rcv_nxt on last window update sent */ - u32 snd_nxt; /* Next sequence we send */ - u32 segs_out; /* RFC4898 tcpEStatsPerfSegsOut - * The total number of segments sent. - */ - u32 data_segs_out; /* RFC4898 tcpEStatsPerfDataSegsOut - * total number of data segments sent. - */ - u64 bytes_sent; /* RFC4898 tcpEStatsPerfHCDataOctetsOut - * total number of data bytes sent. - */ + u32 max_packets_out; /* max packets_out in last window */ + u32 cwnd_usage_seq; /* right edge of cwnd usage tracking flight */ + u32 rate_delivered; /* saved rate sample: packets delivered */ + u32 rate_interval_us; /* saved rate sample: time elapsed */ + u32 rcv_rtt_last_tsecr; + u64 first_tx_mstamp; /* start of window send phase */ + u64 delivered_mstamp; /* time we reached "delivered" */ u64 bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked * sum(delta(snd_una)), or how many bytes * were acked. */ + struct { + u32 rtt_us; + u32 seq; + u64 time; + } rcv_rtt_est; +/* Receiver queue space */ + struct { + u32 space; + u32 seq; + u64 time; + } rcvq_space; + __cacheline_group_end(tcp_sock_write_rx); + /* End of Hot Path */ + +/* + * RFC793 variables by their proper names. This means you can + * read the code and the spec side by side (and laugh ...) + * See RFC793 and RFC1122. The RFC writes these in capitals. + */ u32 dsack_dups; /* RFC4898 tcpEStatsStackDSACKDups * total number of DSACK blocks received */ - u32 snd_una; /* First byte we want an ack for */ - u32 snd_sml; /* Last byte of the most recently transmitted small packet */ - u32 rcv_tstamp; /* timestamp of last received ACK (for keepalives) */ - u32 lsndtime; /* timestamp of last sent data packet (for restart window) */ u32 last_oow_ack_time; /* timestamp of last out-of-window ACK */ u32 compressed_ack_rcv_nxt; - - u32 tsoffset; /* timestamp offset */ - struct list_head tsq_node; /* anchor in tsq_tasklet.head list */ - struct list_head tsorted_sent_queue; /* time-sorted sent but un-SACKed skbs */ - - u32 snd_wl1; /* Sequence for window update */ - u32 snd_wnd; /* The window we expect to receive */ - u32 max_window; /* Maximal window ever seen from peer */ - u32 mss_cache; /* Cached effective mss, not including SACKS */ - u32 window_clamp; /* Maximal window to advertise */ - u32 rcv_ssthresh; /* Current window clamp */ u8 scaling_ratio; /* see tcp_win_from_space() */ /* Information of the most recently (s)acked skb */ struct tcp_rack { @@ -268,24 +365,16 @@ struct tcp_sock { dsack_seen:1, /* Whether DSACK seen after last adj */ advanced:1; /* mstamp advanced since last lost marking */ } rack; - u16 advmss; /* Advertised MSS */ u8 compressed_ack; u8 dup_ack_counter:2, tlp_retrans:1, /* TLP is a retransmission */ tcp_usec_ts:1, /* TSval values in usec */ unused:4; - u32 chrono_start; /* Start time in jiffies of a TCP chrono */ - u32 chrono_stat[3]; /* Time in jiffies for chrono_stat stats */ - u8 chrono_type:2, /* current chronograph type */ - rate_app_limited:1, /* rate_{delivered,interval_us} limited? */ + u8 thin_lto : 1,/* Use linear timeouts for thin streams */ + recvmsg_inq : 1,/* Indicate # of bytes in queue upon recvmsg */ fastopen_connect:1, /* FASTOPEN_CONNECT sockopt */ fastopen_no_cookie:1, /* Allow send/recv SYN+data without a cookie */ - is_sack_reneg:1, /* in recovery from loss with SACK reneg? */ - fastopen_client_fail:2; /* reason why fastopen failed */ - u8 nonagle : 4,/* Disable Nagle algorithm? */ - thin_lto : 1,/* Use linear timeouts for thin streams */ - recvmsg_inq : 1,/* Indicate # of bytes in queue upon recvmsg */ - repair : 1, + fastopen_client_fail:2, /* reason why fastopen failed */ frto : 1;/* F-RTO (RFC5682) activated in CA_Loss */ u8 repair_queue; u8 save_syn:2, /* Save headers of SYN packet */ @@ -293,45 +382,19 @@ struct tcp_sock { syn_fastopen:1, /* SYN includes Fast Open option */ syn_fastopen_exp:1,/* SYN includes Fast Open exp. option */ syn_fastopen_ch:1, /* Active TFO re-enabling probe */ - syn_data_acked:1,/* data in SYN is acked by SYN-ACK */ - is_cwnd_limited:1;/* forward progress limited by snd_cwnd? */ - u32 tlp_high_seq; /* snd_nxt at the time of TLP */ + syn_data_acked:1;/* data in SYN is acked by SYN-ACK */ u32 tcp_tx_delay; /* delay (in usec) added to TX packets */ - u64 tcp_wstamp_ns; /* departure time for next sent data packet */ - u64 tcp_clock_cache; /* cache last tcp_clock_ns() (see tcp_mstamp_refresh()) */ /* RTT measurement */ - u64 tcp_mstamp; /* most recent packet received/sent */ - u32 srtt_us; /* smoothed round trip time << 3 in usecs */ - u32 mdev_us; /* medium deviation */ u32 mdev_max_us; /* maximal mdev for the last rtt period */ - u32 rttvar_us; /* smoothed mdev_max */ - u32 rtt_seq; /* sequence number to update rttvar */ - struct minmax rtt_min; - u32 packets_out; /* Packets which are "in flight" */ - u32 retrans_out; /* Retransmitted packets out */ - u32 max_packets_out; /* max packets_out in last window */ - u32 cwnd_usage_seq; /* right edge of cwnd usage tracking flight */ - - u16 urg_data; /* Saved octet of OOB data and control flags */ - u8 ecn_flags; /* ECN status bits. */ u8 keepalive_probes; /* num of allowed keep alive probes */ - u32 reordering; /* Packet reordering metric. */ u32 reord_seen; /* number of data packet reordering events */ - u32 snd_up; /* Urgent pointer */ - -/* - * Options received (usually on last packet, some only on SYN packets). - */ - struct tcp_options_received rx_opt; /* * Slow start and congestion control (see also Nagle, and Karn & Partridge) */ - u32 snd_ssthresh; /* Slow start size threshold */ - u32 snd_cwnd; /* Sending congestion window */ u32 snd_cwnd_cnt; /* Linear increase counter */ u32 snd_cwnd_clamp; /* Do not allow snd_cwnd to grow above this */ u32 snd_cwnd_used; @@ -339,32 +402,10 @@ struct tcp_sock { u32 prior_cwnd; /* cwnd right before starting loss recovery */ u32 prr_delivered; /* Number of newly delivered packets to * receiver in Recovery. */ - u32 prr_out; /* Total number of pkts sent during Recovery. */ - u32 delivered; /* Total data packets delivered incl. rexmits */ - u32 delivered_ce; /* Like the above but only ECE marked packets */ - u32 lost; /* Total data packets lost incl. rexmits */ - u32 app_limited; /* limited until "delivered" reaches this val */ - u64 first_tx_mstamp; /* start of window send phase */ - u64 delivered_mstamp; /* time we reached "delivered" */ - u32 rate_delivered; /* saved rate sample: packets delivered */ - u32 rate_interval_us; /* saved rate sample: time elapsed */ - - u32 rcv_wnd; /* Current receiver window */ - u32 write_seq; /* Tail(+1) of data held in tcp send buffer */ - u32 notsent_lowat; /* TCP_NOTSENT_LOWAT */ - u32 pushed_seq; /* Last pushed seq, required to talk to windows */ - u32 lost_out; /* Lost packets */ - u32 sacked_out; /* SACK'd packets */ struct hrtimer pacing_timer; struct hrtimer compressed_ack_timer; - /* from STCP, retrans queue hinting */ - struct sk_buff* lost_skb_hint; - struct sk_buff *retransmit_skb_hint; - - /* OOO segments go in this rbtree. Socket lock must be held. */ - struct rb_root out_of_order_queue; struct sk_buff *ooo_last_skb; /* cache rb_last(out_of_order_queue) */ /* SACKs data, these 2 need to be together (see tcp_options_write) */ @@ -373,12 +414,6 @@ struct tcp_sock { struct tcp_sack_block recv_sack_cache[4]; - struct sk_buff *highest_sack; /* skb just after the highest - * skb with SACKed bit set - * (validity guaranteed only if - * sacked_out > 0) - */ - int lost_cnt_hint; u32 prior_ssthresh; /* ssthresh saved at recovery start */ @@ -429,21 +464,6 @@ struct tcp_sock { u32 rcv_ooopack; /* Received out-of-order packets, for tcpinfo */ -/* Receiver side RTT estimation */ - u32 rcv_rtt_last_tsecr; - struct { - u32 rtt_us; - u32 seq; - u64 time; - } rcv_rtt_est; - -/* Receiver queue space */ - struct { - u32 space; - u32 seq; - u64 time; - } rcvq_space; - /* TCP-specific MTU probe information. */ struct { u32 probe_seq_start; diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index 17eb1c5205d3..911ddf92dcee 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -84,6 +84,7 @@ struct tee_param { * @release: release this open file * @open_session: open a new session * @close_session: close a session + * @system_session: declare session as a system session * @invoke_func: invoke a trusted function * @cancel_req: request cancel of an ongoing invoke or open * @supp_recv: called for supplicant to get a command @@ -100,6 +101,7 @@ struct tee_driver_ops { struct tee_ioctl_open_session_arg *arg, struct tee_param *param); int (*close_session)(struct tee_context *ctx, u32 session); + int (*system_session)(struct tee_context *ctx, u32 session); int (*invoke_func)(struct tee_context *ctx, struct tee_ioctl_invoke_arg *arg, struct tee_param *param); @@ -430,6 +432,20 @@ int tee_client_open_session(struct tee_context *ctx, int tee_client_close_session(struct tee_context *ctx, u32 session); /** + * tee_client_system_session() - Declare session as a system session + * @ctx: TEE Context + * @session: Session id + * + * This function requests TEE to provision an entry context ready to use for + * that session only. The provisioned entry context is used for command + * invocation and session closure, not for command cancelling requests. + * TEE releases the provisioned context upon session closure. + * + * Return < 0 on error else 0 if an entry context has been provisioned. + */ +int tee_client_system_session(struct tee_context *ctx, u32 session); + +/** * tee_client_invoke_func() - Invoke a function in a Trusted Application * @ctx: TEE Context * @arg: Invoke arguments, see description of diff --git a/include/linux/time_namespace.h b/include/linux/time_namespace.h index 03d9c5ac01d1..876e31b4461d 100644 --- a/include/linux/time_namespace.h +++ b/include/linux/time_namespace.h @@ -7,10 +7,13 @@ #include <linux/nsproxy.h> #include <linux/ns_common.h> #include <linux/err.h> +#include <linux/time64.h> struct user_namespace; extern struct user_namespace init_user_ns; +struct vm_area_struct; + struct timens_offsets { struct timespec64 monotonic; struct timespec64 boottime; diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index fe1e467ba046..7c43e98cf211 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -4,6 +4,7 @@ #include <linux/errno.h> #include <linux/clocksource_ids.h> +#include <linux/ktime.h> /* Included from linux/ktime.h */ diff --git a/include/linux/timer.h b/include/linux/timer.h index 26a545bb0153..f18a2f1eb79e 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -7,21 +7,7 @@ #include <linux/stddef.h> #include <linux/debugobjects.h> #include <linux/stringify.h> - -struct timer_list { - /* - * All fields that change during normal runtime grouped to the - * same cacheline - */ - struct hlist_node entry; - unsigned long expires; - void (*function)(struct timer_list *); - u32 flags; - -#ifdef CONFIG_LOCKDEP - struct lockdep_map lockdep_map; -#endif -}; +#include <linux/timer_types.h> #ifdef CONFIG_LOCKDEP /* diff --git a/include/linux/timer_types.h b/include/linux/timer_types.h new file mode 100644 index 000000000000..fae5a388f914 --- /dev/null +++ b/include/linux/timer_types.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_TIMER_TYPES_H +#define _LINUX_TIMER_TYPES_H + +#include <linux/lockdep_types.h> +#include <linux/types.h> + +struct timer_list { + /* + * All fields that change during normal runtime grouped to the + * same cacheline + */ + struct hlist_node entry; + unsigned long expires; + void (*function)(struct timer_list *); + u32 flags; + +#ifdef CONFIG_LOCKDEP + struct lockdep_map lockdep_map; +#endif +}; + +#endif /* _LINUX_TIMER_TYPES_H */ diff --git a/include/linux/timerqueue.h b/include/linux/timerqueue.h index adc80e29168e..62973f7d4610 100644 --- a/include/linux/timerqueue.h +++ b/include/linux/timerqueue.h @@ -3,18 +3,7 @@ #define _LINUX_TIMERQUEUE_H #include <linux/rbtree.h> -#include <linux/ktime.h> - - -struct timerqueue_node { - struct rb_node node; - ktime_t expires; -}; - -struct timerqueue_head { - struct rb_root_cached rb_root; -}; - +#include <linux/timerqueue_types.h> extern bool timerqueue_add(struct timerqueue_head *head, struct timerqueue_node *node); diff --git a/include/linux/timerqueue_types.h b/include/linux/timerqueue_types.h new file mode 100644 index 000000000000..dc298d0923e3 --- /dev/null +++ b/include/linux/timerqueue_types.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_TIMERQUEUE_TYPES_H +#define _LINUX_TIMERQUEUE_TYPES_H + +#include <linux/rbtree_types.h> +#include <linux/types.h> + +struct timerqueue_node { + struct rb_node node; + ktime_t expires; +}; + +struct timerqueue_head { + struct rb_root_cached rb_root; +}; + +#endif /* _LINUX_TIMERQUEUE_TYPES_H */ diff --git a/include/linux/tnum.h b/include/linux/tnum.h index 1c3948a1d6ad..3c13240077b8 100644 --- a/include/linux/tnum.h +++ b/include/linux/tnum.h @@ -106,6 +106,10 @@ int tnum_sbin(char *str, size_t size, struct tnum a); struct tnum tnum_subreg(struct tnum a); /* Returns the tnum with the lower 32-bit subreg cleared */ struct tnum tnum_clear_subreg(struct tnum a); +/* Returns the tnum with the lower 32-bit subreg in *reg* set to the lower + * 32-bit subreg in *subreg* + */ +struct tnum tnum_with_subreg(struct tnum reg, struct tnum subreg); /* Returns the tnum with the lower 32-bit subreg set to value */ struct tnum tnum_const_subreg(struct tnum a, u32 value); /* Returns true if 32-bit subreg @a is a known constant*/ diff --git a/include/linux/torture.h b/include/linux/torture.h index c98d0c83d117..1541454da03e 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -21,6 +21,7 @@ #include <linux/debugobjects.h> #include <linux/bug.h> #include <linux/compiler.h> +#include <linux/hrtimer.h> /* Definitions for a non-string torture-test module parameter. */ #define torture_param(type, name, init, msg) \ diff --git a/include/linux/types.h b/include/linux/types.h index 253168bb3fe1..2bc8766ba20c 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -120,6 +120,9 @@ typedef s64 int64_t; #define aligned_be64 __aligned_be64 #define aligned_le64 __aligned_le64 +/* Nanosecond scalar representation for kernel time values */ +typedef s64 ktime_t; + /** * The type used for indexing onto a disc or disc partition. * diff --git a/include/linux/uidgid.h b/include/linux/uidgid.h index 415a7ca2b882..f85ec5613721 100644 --- a/include/linux/uidgid.h +++ b/include/linux/uidgid.h @@ -12,22 +12,13 @@ * to detect when we overlook these differences. * */ -#include <linux/types.h> +#include <linux/uidgid_types.h> #include <linux/highuid.h> struct user_namespace; extern struct user_namespace init_user_ns; struct uid_gid_map; -typedef struct { - uid_t val; -} kuid_t; - - -typedef struct { - gid_t val; -} kgid_t; - #define KUIDT_INIT(value) (kuid_t){ value } #define KGIDT_INIT(value) (kgid_t){ value } diff --git a/include/linux/uidgid_types.h b/include/linux/uidgid_types.h new file mode 100644 index 000000000000..b35ac4955a33 --- /dev/null +++ b/include/linux/uidgid_types.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_UIDGID_TYPES_H +#define _LINUX_UIDGID_TYPES_H + +#include <linux/types.h> + +typedef struct { + uid_t val; +} kuid_t; + +typedef struct { + gid_t val; +} kgid_t; + +#endif /* _LINUX_UIDGID_TYPES_H */ diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index ebb3ce63d64d..c82089dee0c8 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -256,4 +256,5 @@ void virtio_transport_put_credit(struct virtio_vsock_sock *vvs, u32 credit); void virtio_transport_deliver_tap_pkt(struct sk_buff *skb); int virtio_transport_purge_skbs(void *vsk, struct sk_buff_head *list); int virtio_transport_read_skb(struct vsock_sock *vsk, skb_read_actor_t read_actor); +int virtio_transport_notify_set_rcvlowat(struct vsock_sock *vsk, int val); #endif /* _LINUX_VIRTIO_VSOCK_H */ diff --git a/include/linux/wait.h b/include/linux/wait.h index 3473b663176f..8aa3372f21a0 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -9,7 +9,6 @@ #include <linux/spinlock.h> #include <asm/current.h> -#include <uapi/linux/wait.h> typedef struct wait_queue_entry wait_queue_entry_t; diff --git a/include/linux/wmi.h b/include/linux/wmi.h index 763bd382cf2d..686291b87852 100644 --- a/include/linux/wmi.h +++ b/include/linux/wmi.h @@ -11,7 +11,6 @@ #include <linux/device.h> #include <linux/acpi.h> #include <linux/mod_devicetable.h> -#include <uapi/linux/wmi.h> /** * struct wmi_device - WMI device structure @@ -22,11 +21,17 @@ */ struct wmi_device { struct device dev; - - /* private: used by the WMI driver core */ bool setable; }; +/** + * to_wmi_device() - Helper macro to cast a device to a wmi_device + * @device: device struct + * + * Cast a struct device to a struct wmi_device. + */ +#define to_wmi_device(device) container_of(device, struct wmi_device, dev) + extern acpi_status wmidev_evaluate_method(struct wmi_device *wdev, u8 instance, u32 method_id, const struct acpi_buffer *in, @@ -35,9 +40,9 @@ extern acpi_status wmidev_evaluate_method(struct wmi_device *wdev, extern union acpi_object *wmidev_block_query(struct wmi_device *wdev, u8 instance); -u8 wmidev_instance_count(struct wmi_device *wdev); +acpi_status wmidev_block_set(struct wmi_device *wdev, u8 instance, const struct acpi_buffer *in); -extern int set_required_buffer_size(struct wmi_device *wdev, u64 length); +u8 wmidev_instance_count(struct wmi_device *wdev); /** * struct wmi_driver - WMI driver structure @@ -47,11 +52,8 @@ extern int set_required_buffer_size(struct wmi_device *wdev, u64 length); * @probe: Callback for device binding * @remove: Callback for device unbinding * @notify: Callback for receiving WMI events - * @filter_callback: Callback for filtering device IOCTLs * * This represents WMI drivers which handle WMI devices. - * @filter_callback is only necessary for drivers which - * want to set up a WMI IOCTL interface. */ struct wmi_driver { struct device_driver driver; @@ -61,8 +63,6 @@ struct wmi_driver { int (*probe)(struct wmi_device *wdev, const void *context); void (*remove)(struct wmi_device *wdev); void (*notify)(struct wmi_device *device, union acpi_object *data); - long (*filter_callback)(struct wmi_device *wdev, unsigned int cmd, - struct wmi_ioctl_buffer *arg); }; extern int __must_check __wmi_driver_register(struct wmi_driver *driver, diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index b0b9604b76b8..2cc0a9606175 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -14,12 +14,7 @@ #include <linux/atomic.h> #include <linux/cpumask.h> #include <linux/rcupdate.h> - -struct workqueue_struct; - -struct work_struct; -typedef void (*work_func_t)(struct work_struct *work); -void delayed_work_timer_fn(struct timer_list *t); +#include <linux/workqueue_types.h> /* * The first word is the work queue pointer and the flags rolled into @@ -95,15 +90,6 @@ enum { #define WORK_STRUCT_FLAG_MASK ((1ul << WORK_STRUCT_FLAG_BITS) - 1) #define WORK_STRUCT_WQ_DATA_MASK (~WORK_STRUCT_FLAG_MASK) -struct work_struct { - atomic_long_t data; - struct list_head entry; - work_func_t func; -#ifdef CONFIG_LOCKDEP - struct lockdep_map lockdep_map; -#endif -}; - #define WORK_DATA_INIT() ATOMIC_LONG_INIT((unsigned long)WORK_STRUCT_NO_POOL) #define WORK_DATA_STATIC_INIT() \ ATOMIC_LONG_INIT((unsigned long)(WORK_STRUCT_NO_POOL | WORK_STRUCT_STATIC)) diff --git a/include/linux/workqueue_types.h b/include/linux/workqueue_types.h new file mode 100644 index 000000000000..4c38824f3ab4 --- /dev/null +++ b/include/linux/workqueue_types.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_WORKQUEUE_TYPES_H +#define _LINUX_WORKQUEUE_TYPES_H + +#include <linux/atomic.h> +#include <linux/lockdep_types.h> +#include <linux/timer_types.h> +#include <linux/types.h> + +struct workqueue_struct; + +struct work_struct; +typedef void (*work_func_t)(struct work_struct *work); +void delayed_work_timer_fn(struct timer_list *t); + +struct work_struct { + atomic_long_t data; + struct list_head entry; + work_func_t func; +#ifdef CONFIG_LOCKDEP + struct lockdep_map lockdep_map; +#endif +}; + +#endif /* _LINUX_WORKQUEUE_TYPES_H */ |