diff options
Diffstat (limited to 'include')
245 files changed, 6922 insertions, 2550 deletions
diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h index 34fb3431a8f3..292a5c40bd0c 100644 --- a/include/acpi/ghes.h +++ b/include/acpi/ghes.h @@ -71,7 +71,7 @@ int ghes_register_vendor_record_notifier(struct notifier_block *nb); void ghes_unregister_vendor_record_notifier(struct notifier_block *nb); #endif -int ghes_estatus_pool_init(int num_ghes); +int ghes_estatus_pool_init(unsigned int num_ghes); /* From drivers/edac/ghes_edac.c */ diff --git a/include/asm-generic/cacheflush.h b/include/asm-generic/cacheflush.h index 4f07afacbc23..f46258d1a080 100644 --- a/include/asm-generic/cacheflush.h +++ b/include/asm-generic/cacheflush.h @@ -2,6 +2,8 @@ #ifndef _ASM_GENERIC_CACHEFLUSH_H #define _ASM_GENERIC_CACHEFLUSH_H +#include <linux/instrumented.h> + struct mm_struct; struct vm_area_struct; struct page; @@ -105,14 +107,22 @@ static inline void flush_cache_vunmap(unsigned long start, unsigned long end) #ifndef copy_to_user_page #define copy_to_user_page(vma, page, vaddr, dst, src, len) \ do { \ + instrument_copy_to_user((void __user *)dst, src, len); \ memcpy(dst, src, len); \ flush_icache_user_page(vma, page, vaddr, len); \ } while (0) #endif + #ifndef copy_from_user_page -#define copy_from_user_page(vma, page, vaddr, dst, src, len) \ - memcpy(dst, src, len) +#define copy_from_user_page(vma, page, vaddr, dst, src, len) \ + do { \ + instrument_copy_from_user_before(dst, (void __user *)src, \ + len); \ + memcpy(dst, src, len); \ + instrument_copy_from_user_after(dst, (void __user *)src, len, \ + 0); \ + } while (0) #endif #endif /* _ASM_GENERIC_CACHEFLUSH_H */ diff --git a/include/asm-generic/compat.h b/include/asm-generic/compat.h index aeb257ad3d1a..8392caea398f 100644 --- a/include/asm-generic/compat.h +++ b/include/asm-generic/compat.h @@ -15,7 +15,7 @@ #endif #ifndef compat_arg_u64 -#ifdef CONFIG_CPU_BIG_ENDIAN +#ifndef CONFIG_CPU_BIG_ENDIAN #define compat_arg_u64(name) u32 name##_lo, u32 name##_hi #define compat_arg_u64_dual(name) u32, name##_lo, u32, name##_hi #else diff --git a/include/asm-generic/hyperv-tlfs.h b/include/asm-generic/hyperv-tlfs.h index fdce7a4cfc6f..b17c6eeb9afa 100644 --- a/include/asm-generic/hyperv-tlfs.h +++ b/include/asm-generic/hyperv-tlfs.h @@ -102,6 +102,15 @@ struct ms_hyperv_tsc_page { volatile s64 tsc_offset; } __packed; +union hv_reference_tsc_msr { + u64 as_uint64; + struct { + u64 enable:1; + u64 reserved:11; + u64 pfn:52; + } __packed; +}; + /* * The guest OS needs to register the guest ID with the hypervisor. * The guest ID is a 64 bit entity and the structure of this ID is diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h index c05d2ce9b6cd..bfb9eb9d7215 100644 --- a/include/asm-generic/mshyperv.h +++ b/include/asm-generic/mshyperv.h @@ -105,15 +105,12 @@ static inline u64 hv_do_rep_hypercall(u16 code, u16 rep_count, u16 varhead_size, } /* Generate the guest OS identifier as described in the Hyper-V TLFS */ -static inline __u64 generate_guest_id(__u64 d_info1, __u64 kernel_version, - __u64 d_info2) +static inline u64 hv_generate_guest_id(u64 kernel_version) { - __u64 guest_id = 0; + u64 guest_id; - guest_id = (((__u64)HV_LINUX_VENDOR_ID) << 48); - guest_id |= (d_info1 << 48); + guest_id = (((u64)HV_LINUX_VENDOR_ID) << 48); guest_id |= (kernel_version << 16); - guest_id |= d_info2; return guest_id; } diff --git a/include/asm-generic/unaligned.h b/include/asm-generic/unaligned.h index df30f11b4a46..699650f81970 100644 --- a/include/asm-generic/unaligned.h +++ b/include/asm-generic/unaligned.h @@ -126,7 +126,7 @@ static inline void put_unaligned_le24(const u32 val, void *p) __put_unaligned_le24(val, p); } -static inline void __put_unaligned_be48(const u64 val, __u8 *p) +static inline void __put_unaligned_be48(const u64 val, u8 *p) { *p++ = val >> 40; *p++ = val >> 32; diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index c15de165ec8f..3dc5824141cd 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -162,6 +162,16 @@ #define PATCHABLE_DISCARDS *(__patchable_function_entries) #endif +#ifndef CONFIG_ARCH_SUPPORTS_CFI_CLANG +/* + * Simply points to ftrace_stub, but with the proper protocol. + * Defined by the linker script in linux/vmlinux.lds.h + */ +#define FTRACE_STUB_HACK ftrace_stub_graph = ftrace_stub; +#else +#define FTRACE_STUB_HACK +#endif + #ifdef CONFIG_FTRACE_MCOUNT_RECORD /* * The ftrace call sites are logged to a section whose name depends on the @@ -169,10 +179,6 @@ * FTRACE_CALLSITE_SECTION. We capture all of them here to avoid header * dependencies for FTRACE_CALLSITE_SECTION's definition. * - * Need to also make ftrace_stub_graph point to ftrace_stub - * so that the same stub location may have different protocols - * and not mess up with C verifiers. - * * ftrace_ops_list_func will be defined as arch_ftrace_ops_list_func * as some archs will have a different prototype for that function * but ftrace_ops_list_func() will have a single prototype. @@ -182,11 +188,11 @@ KEEP(*(__mcount_loc)) \ KEEP_PATCHABLE \ __stop_mcount_loc = .; \ - ftrace_stub_graph = ftrace_stub; \ + FTRACE_STUB_HACK \ ftrace_ops_list_func = arch_ftrace_ops_list_func; #else # ifdef CONFIG_FUNCTION_TRACER -# define MCOUNT_REC() ftrace_stub_graph = ftrace_stub; \ +# define MCOUNT_REC() FTRACE_STUB_HACK \ ftrace_ops_list_func = arch_ftrace_ops_list_func; # else # define MCOUNT_REC() @@ -341,6 +347,7 @@ #define DATA_DATA \ *(.xiptext) \ *(DATA_MAIN) \ + *(.data..decrypted) \ *(.ref.data) \ *(.data..shared_aligned) /* percpu related */ \ MEM_KEEP(init.data*) \ @@ -989,7 +996,6 @@ #ifdef CONFIG_AMD_MEM_ENCRYPT #define PERCPU_DECRYPTED_SECTION \ . = ALIGN(PAGE_SIZE); \ - *(.data..decrypted) \ *(.data..percpu..decrypted) \ . = ALIGN(PAGE_SIZE); #else diff --git a/include/clocksource/timer-ti-dm.h b/include/clocksource/timer-ti-dm.h index b0f80cfd2a26..77eceeae708c 100644 --- a/include/clocksource/timer-ti-dm.h +++ b/include/clocksource/timer-ti-dm.h @@ -52,10 +52,6 @@ #define OMAP_TIMER_TRIGGER_OVERFLOW 0x01 #define OMAP_TIMER_TRIGGER_OVERFLOW_AND_COMPARE 0x02 -/* posted mode types */ -#define OMAP_TIMER_NONPOSTED 0x00 -#define OMAP_TIMER_POSTED 0x01 - /* timer capabilities used in hwmod database */ #define OMAP_TIMER_SECURE 0x80000000 #define OMAP_TIMER_ALWON 0x40000000 @@ -63,73 +59,13 @@ #define OMAP_TIMER_NEEDS_RESET 0x10000000 #define OMAP_TIMER_HAS_DSP_IRQ 0x08000000 -/* - * timer errata flags - * - * Errata i103/i767 impacts all OMAP3/4/5 devices including AM33xx. This - * errata prevents us from using posted mode on these devices, unless the - * timer counter register is never read. For more details please refer to - * the OMAP3/4/5 errata documents. - */ -#define OMAP_TIMER_ERRATA_I103_I767 0x80000000 - -struct timer_regs { - u32 ocp_cfg; - u32 tidr; - u32 tier; - u32 twer; - u32 tclr; - u32 tcrr; - u32 tldr; - u32 ttrg; - u32 twps; - u32 tmar; - u32 tcar1; - u32 tsicr; - u32 tcar2; - u32 tpir; - u32 tnir; - u32 tcvr; - u32 tocr; - u32 towr; -}; - struct omap_dm_timer { - int id; - int irq; - struct clk *fclk; - - void __iomem *io_base; - void __iomem *irq_stat; /* TISR/IRQSTATUS interrupt status */ - void __iomem *irq_ena; /* irq enable */ - void __iomem *irq_dis; /* irq disable, only on v2 ip */ - void __iomem *pend; /* write pending */ - void __iomem *func_base; /* function register base */ - - atomic_t enabled; - unsigned long rate; - unsigned reserved:1; - unsigned posted:1; - struct timer_regs context; - int revision; - u32 capability; - u32 errata; - struct platform_device *pdev; - struct list_head node; - struct notifier_block nb; }; -int omap_dm_timer_reserve_systimer(int id); -struct omap_dm_timer *omap_dm_timer_request_by_cap(u32 cap); - int omap_dm_timer_get_irq(struct omap_dm_timer *timer); u32 omap_dm_timer_modify_idlect_mask(u32 inputmask); -int omap_dm_timer_trigger(struct omap_dm_timer *timer); - -int omap_dm_timers_active(void); - /* * Do not use the defines below, they are not needed. They should be only * used by dmtimer.c and sys_timer related code. @@ -199,52 +135,4 @@ int omap_dm_timers_active(void); #define _OMAP_TIMER_TICK_INT_MASK_SET_OFFSET 0x54 /* TOCR, 34xx only */ #define _OMAP_TIMER_TICK_INT_MASK_COUNT_OFFSET 0x58 /* TOWR, 34xx only */ -/* register offsets with the write pending bit encoded */ -#define WPSHIFT 16 - -#define OMAP_TIMER_WAKEUP_EN_REG (_OMAP_TIMER_WAKEUP_EN_OFFSET \ - | (WP_NONE << WPSHIFT)) - -#define OMAP_TIMER_CTRL_REG (_OMAP_TIMER_CTRL_OFFSET \ - | (WP_TCLR << WPSHIFT)) - -#define OMAP_TIMER_COUNTER_REG (_OMAP_TIMER_COUNTER_OFFSET \ - | (WP_TCRR << WPSHIFT)) - -#define OMAP_TIMER_LOAD_REG (_OMAP_TIMER_LOAD_OFFSET \ - | (WP_TLDR << WPSHIFT)) - -#define OMAP_TIMER_TRIGGER_REG (_OMAP_TIMER_TRIGGER_OFFSET \ - | (WP_TTGR << WPSHIFT)) - -#define OMAP_TIMER_WRITE_PEND_REG (_OMAP_TIMER_WRITE_PEND_OFFSET \ - | (WP_NONE << WPSHIFT)) - -#define OMAP_TIMER_MATCH_REG (_OMAP_TIMER_MATCH_OFFSET \ - | (WP_TMAR << WPSHIFT)) - -#define OMAP_TIMER_CAPTURE_REG (_OMAP_TIMER_CAPTURE_OFFSET \ - | (WP_NONE << WPSHIFT)) - -#define OMAP_TIMER_IF_CTRL_REG (_OMAP_TIMER_IF_CTRL_OFFSET \ - | (WP_NONE << WPSHIFT)) - -#define OMAP_TIMER_CAPTURE2_REG (_OMAP_TIMER_CAPTURE2_OFFSET \ - | (WP_NONE << WPSHIFT)) - -#define OMAP_TIMER_TICK_POS_REG (_OMAP_TIMER_TICK_POS_OFFSET \ - | (WP_TPIR << WPSHIFT)) - -#define OMAP_TIMER_TICK_NEG_REG (_OMAP_TIMER_TICK_NEG_OFFSET \ - | (WP_TNIR << WPSHIFT)) - -#define OMAP_TIMER_TICK_COUNT_REG (_OMAP_TIMER_TICK_COUNT_OFFSET \ - | (WP_TCVR << WPSHIFT)) - -#define OMAP_TIMER_TICK_INT_MASK_SET_REG \ - (_OMAP_TIMER_TICK_INT_MASK_SET_OFFSET | (WP_TOCR << WPSHIFT)) - -#define OMAP_TIMER_TICK_INT_MASK_COUNT_REG \ - (_OMAP_TIMER_TICK_INT_MASK_COUNT_OFFSET | (WP_TOWR << WPSHIFT)) - #endif /* __CLOCKSOURCE_DMTIMER_H */ diff --git a/include/crypto/aria.h b/include/crypto/aria.h index 4a86661788e8..254da46cc385 100644 --- a/include/crypto/aria.h +++ b/include/crypto/aria.h @@ -32,18 +32,10 @@ #define ARIA_RD_KEY_WORDS (ARIA_BLOCK_SIZE / sizeof(u32)) struct aria_ctx { - int key_length; - int rounds; u32 enc_key[ARIA_MAX_RD_KEYS][ARIA_RD_KEY_WORDS]; u32 dec_key[ARIA_MAX_RD_KEYS][ARIA_RD_KEY_WORDS]; -}; - -static const u32 key_rc[5][4] = { - { 0x517cc1b7, 0x27220a94, 0xfe13abe8, 0xfa9a6ee0 }, - { 0x6db14acc, 0x9e21c820, 0xff28b1d5, 0xef5de2b0 }, - { 0xdb92371d, 0x2126e970, 0x03249775, 0x04e8c90e }, - { 0x517cc1b7, 0x27220a94, 0xfe13abe8, 0xfa9a6ee0 }, - { 0x6db14acc, 0x9e21c820, 0xff28b1d5, 0xef5de2b0 } + int rounds; + int key_length; }; static const u32 s1[256] = { @@ -458,4 +450,9 @@ static inline void aria_gsrk(u32 *rk, u32 *x, u32 *y, u32 n) ((y[(q + 2) % 4]) << (32 - r)); } +void aria_encrypt(void *ctx, u8 *out, const u8 *in); +void aria_decrypt(void *ctx, u8 *out, const u8 *in); +int aria_set_key(struct crypto_tfm *tfm, const u8 *in_key, + unsigned int key_len); + #endif diff --git a/include/crypto/internal/aead.h b/include/crypto/internal/aead.h index 27b7b0224ea6..d482017f3e20 100644 --- a/include/crypto/internal/aead.h +++ b/include/crypto/internal/aead.h @@ -114,31 +114,6 @@ static inline void aead_init_queue(struct aead_queue *queue, crypto_init_queue(&queue->base, max_qlen); } -static inline int aead_enqueue_request(struct aead_queue *queue, - struct aead_request *request) -{ - return crypto_enqueue_request(&queue->base, &request->base); -} - -static inline struct aead_request *aead_dequeue_request( - struct aead_queue *queue) -{ - struct crypto_async_request *req; - - req = crypto_dequeue_request(&queue->base); - - return req ? container_of(req, struct aead_request, base) : NULL; -} - -static inline struct aead_request *aead_get_backlog(struct aead_queue *queue) -{ - struct crypto_async_request *req; - - req = crypto_get_backlog(&queue->base); - - return req ? container_of(req, struct aead_request, base) : NULL; -} - static inline unsigned int crypto_aead_alg_chunksize(struct aead_alg *alg) { return alg->chunksize; diff --git a/include/crypto/scatterwalk.h b/include/crypto/scatterwalk.h index 6407b4b61350..ccdb05f68a75 100644 --- a/include/crypto/scatterwalk.h +++ b/include/crypto/scatterwalk.h @@ -46,12 +46,6 @@ static inline void scatterwalk_advance(struct scatter_walk *walk, walk->offset += nbytes; } -static inline unsigned int scatterwalk_aligned(struct scatter_walk *walk, - unsigned int alignmask) -{ - return !(walk->offset & alignmask); -} - static inline struct page *scatterwalk_page(struct scatter_walk *walk) { return sg_page(walk->sg) + (walk->offset >> PAGE_SHIFT); diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index 599855c6a672..2ae4fd62e01c 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -32,6 +32,15 @@ #define MAX_WAIT_SCHED_ENTITY_Q_EMPTY msecs_to_jiffies(1000) +/** + * DRM_SCHED_FENCE_DONT_PIPELINE - Prefent dependency pipelining + * + * Setting this flag on a scheduler fence prevents pipelining of jobs depending + * on this fence. In other words we always insert a full CPU round trip before + * dependen jobs are pushed to the hw queue. + */ +#define DRM_SCHED_FENCE_DONT_PIPELINE DMA_FENCE_FLAG_USER_BITS + struct drm_gem_object; struct drm_gpu_scheduler; diff --git a/include/dt-bindings/clock/aspeed-clock.h b/include/dt-bindings/clock/aspeed-clock.h index 9ff4f6e4558c..06d568382c77 100644 --- a/include/dt-bindings/clock/aspeed-clock.h +++ b/include/dt-bindings/clock/aspeed-clock.h @@ -52,5 +52,6 @@ #define ASPEED_RESET_I2C 7 #define ASPEED_RESET_AHB 8 #define ASPEED_RESET_CRT1 9 +#define ASPEED_RESET_HACE 10 #endif diff --git a/include/dt-bindings/clock/ast2600-clock.h b/include/dt-bindings/clock/ast2600-clock.h index 62b9520a00fd..d8b0db2f7a7d 100644 --- a/include/dt-bindings/clock/ast2600-clock.h +++ b/include/dt-bindings/clock/ast2600-clock.h @@ -111,6 +111,7 @@ #define ASPEED_RESET_PCIE_RC_O 19 #define ASPEED_RESET_PCIE_RC_OEN 18 #define ASPEED_RESET_PCI_DP 5 +#define ASPEED_RESET_HACE 4 #define ASPEED_RESET_AHB 1 #define ASPEED_RESET_SDRAM 0 diff --git a/include/dt-bindings/leds/common.h b/include/dt-bindings/leds/common.h index 3be89a7c20a9..9a0d33d027ff 100644 --- a/include/dt-bindings/leds/common.h +++ b/include/dt-bindings/leds/common.h @@ -33,7 +33,12 @@ #define LED_COLOR_ID_MULTI 8 /* For multicolor LEDs */ #define LED_COLOR_ID_RGB 9 /* For multicolor LEDs that can do arbitrary color, so this would include RGBW and similar */ -#define LED_COLOR_ID_MAX 10 +#define LED_COLOR_ID_PURPLE 10 +#define LED_COLOR_ID_ORANGE 11 +#define LED_COLOR_ID_PINK 12 +#define LED_COLOR_ID_CYAN 13 +#define LED_COLOR_ID_LIME 14 +#define LED_COLOR_ID_MAX 15 /* Standard LED functions */ /* Keyboard LEDs, usually it would be input4::capslock etc. */ diff --git a/include/dt-bindings/memory/mt6795-larb-port.h b/include/dt-bindings/memory/mt6795-larb-port.h new file mode 100644 index 000000000000..58cf6a6b6372 --- /dev/null +++ b/include/dt-bindings/memory/mt6795-larb-port.h @@ -0,0 +1,95 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (c) 2022 Collabora Ltd. + * Author: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com> + */ + +#ifndef _DT_BINDINGS_MEMORY_MT6795_LARB_PORT_H_ +#define _DT_BINDINGS_MEMORY_MT6795_LARB_PORT_H_ + +#include <dt-bindings/memory/mtk-memory-port.h> + +#define M4U_LARB0_ID 0 +#define M4U_LARB1_ID 1 +#define M4U_LARB2_ID 2 +#define M4U_LARB3_ID 3 +#define M4U_LARB4_ID 4 + +/* larb0 */ +#define M4U_PORT_DISP_OVL0 MTK_M4U_ID(M4U_LARB0_ID, 0) +#define M4U_PORT_DISP_RDMA0 MTK_M4U_ID(M4U_LARB0_ID, 1) +#define M4U_PORT_DISP_RDMA1 MTK_M4U_ID(M4U_LARB0_ID, 2) +#define M4U_PORT_DISP_WDMA0 MTK_M4U_ID(M4U_LARB0_ID, 3) +#define M4U_PORT_DISP_OVL1 MTK_M4U_ID(M4U_LARB0_ID, 4) +#define M4U_PORT_DISP_RDMA2 MTK_M4U_ID(M4U_LARB0_ID, 5) +#define M4U_PORT_DISP_WDMA1 MTK_M4U_ID(M4U_LARB0_ID, 6) +#define M4U_PORT_DISP_OD_R MTK_M4U_ID(M4U_LARB0_ID, 7) +#define M4U_PORT_DISP_OD_W MTK_M4U_ID(M4U_LARB0_ID, 8) +#define M4U_PORT_MDP_RDMA0 MTK_M4U_ID(M4U_LARB0_ID, 9) +#define M4U_PORT_MDP_RDMA1 MTK_M4U_ID(M4U_LARB0_ID, 10) +#define M4U_PORT_MDP_WDMA MTK_M4U_ID(M4U_LARB0_ID, 11) +#define M4U_PORT_MDP_WROT0 MTK_M4U_ID(M4U_LARB0_ID, 12) +#define M4U_PORT_MDP_WROT1 MTK_M4U_ID(M4U_LARB0_ID, 13) + +/* larb1 */ +#define M4U_PORT_VDEC_MC MTK_M4U_ID(M4U_LARB1_ID, 0) +#define M4U_PORT_VDEC_PP MTK_M4U_ID(M4U_LARB1_ID, 1) +#define M4U_PORT_VDEC_UFO MTK_M4U_ID(M4U_LARB1_ID, 2) +#define M4U_PORT_VDEC_VLD MTK_M4U_ID(M4U_LARB1_ID, 3) +#define M4U_PORT_VDEC_VLD2 MTK_M4U_ID(M4U_LARB1_ID, 4) +#define M4U_PORT_VDEC_AVC_MV MTK_M4U_ID(M4U_LARB1_ID, 5) +#define M4U_PORT_VDEC_PRED_RD MTK_M4U_ID(M4U_LARB1_ID, 6) +#define M4U_PORT_VDEC_PRED_WR MTK_M4U_ID(M4U_LARB1_ID, 7) +#define M4U_PORT_VDEC_PPWRAP MTK_M4U_ID(M4U_LARB1_ID, 8) + +/* larb2 */ +#define M4U_PORT_CAM_IMGO MTK_M4U_ID(M4U_LARB2_ID, 0) +#define M4U_PORT_CAM_RRZO MTK_M4U_ID(M4U_LARB2_ID, 1) +#define M4U_PORT_CAM_AAO MTK_M4U_ID(M4U_LARB2_ID, 2) +#define M4U_PORT_CAM_LCSO MTK_M4U_ID(M4U_LARB2_ID, 3) +#define M4U_PORT_CAM_ESFKO MTK_M4U_ID(M4U_LARB2_ID, 4) +#define M4U_PORT_CAM_IMGO_S MTK_M4U_ID(M4U_LARB2_ID, 5) +#define M4U_PORT_CAM_LSCI MTK_M4U_ID(M4U_LARB2_ID, 6) +#define M4U_PORT_CAM_LSCI_D MTK_M4U_ID(M4U_LARB2_ID, 7) +#define M4U_PORT_CAM_BPCI MTK_M4U_ID(M4U_LARB2_ID, 8) +#define M4U_PORT_CAM_BPCI_D MTK_M4U_ID(M4U_LARB2_ID, 9) +#define M4U_PORT_CAM_UFDI MTK_M4U_ID(M4U_LARB2_ID, 10) +#define M4U_PORT_CAM_IMGI MTK_M4U_ID(M4U_LARB2_ID, 11) +#define M4U_PORT_CAM_IMG2O MTK_M4U_ID(M4U_LARB2_ID, 12) +#define M4U_PORT_CAM_IMG3O MTK_M4U_ID(M4U_LARB2_ID, 13) +#define M4U_PORT_CAM_VIPI MTK_M4U_ID(M4U_LARB2_ID, 14) +#define M4U_PORT_CAM_VIP2I MTK_M4U_ID(M4U_LARB2_ID, 15) +#define M4U_PORT_CAM_VIP3I MTK_M4U_ID(M4U_LARB2_ID, 16) +#define M4U_PORT_CAM_LCEI MTK_M4U_ID(M4U_LARB2_ID, 17) +#define M4U_PORT_CAM_RB MTK_M4U_ID(M4U_LARB2_ID, 18) +#define M4U_PORT_CAM_RP MTK_M4U_ID(M4U_LARB2_ID, 19) +#define M4U_PORT_CAM_WR MTK_M4U_ID(M4U_LARB2_ID, 20) + +/* larb3 */ +#define M4U_PORT_VENC_RCPU MTK_M4U_ID(M4U_LARB3_ID, 0) +#define M4U_PORT_VENC_REC MTK_M4U_ID(M4U_LARB3_ID, 1) +#define M4U_PORT_VENC_BSDMA MTK_M4U_ID(M4U_LARB3_ID, 2) +#define M4U_PORT_VENC_SV_COMV MTK_M4U_ID(M4U_LARB3_ID, 3) +#define M4U_PORT_VENC_RD_COMV MTK_M4U_ID(M4U_LARB3_ID, 4) +#define M4U_PORT_JPGENC_BSDMA MTK_M4U_ID(M4U_LARB3_ID, 5) +#define M4U_PORT_REMDC_SDMA MTK_M4U_ID(M4U_LARB3_ID, 6) +#define M4U_PORT_REMDC_BSDMA MTK_M4U_ID(M4U_LARB3_ID, 7) +#define M4U_PORT_JPGENC_RDMA MTK_M4U_ID(M4U_LARB3_ID, 8) +#define M4U_PORT_JPGENC_SDMA MTK_M4U_ID(M4U_LARB3_ID, 9) +#define M4U_PORT_JPGDEC_WDMA MTK_M4U_ID(M4U_LARB3_ID, 10) +#define M4U_PORT_JPGDEC_BSDMA MTK_M4U_ID(M4U_LARB3_ID, 11) +#define M4U_PORT_VENC_CUR_LUMA MTK_M4U_ID(M4U_LARB3_ID, 12) +#define M4U_PORT_VENC_CUR_CHROMA MTK_M4U_ID(M4U_LARB3_ID, 13) +#define M4U_PORT_VENC_REF_LUMA MTK_M4U_ID(M4U_LARB3_ID, 14) +#define M4U_PORT_VENC_REF_CHROMA MTK_M4U_ID(M4U_LARB3_ID, 15) +#define M4U_PORT_REMDC_WDMA MTK_M4U_ID(M4U_LARB3_ID, 16) +#define M4U_PORT_VENC_NBM_RDMA MTK_M4U_ID(M4U_LARB3_ID, 17) +#define M4U_PORT_VENC_NBM_WDMA MTK_M4U_ID(M4U_LARB3_ID, 18) + +/* larb4 */ +#define M4U_PORT_MJC_MV_RD MTK_M4U_ID(M4U_LARB4_ID, 0) +#define M4U_PORT_MJC_MV_WR MTK_M4U_ID(M4U_LARB4_ID, 1) +#define M4U_PORT_MJC_DMA_RD MTK_M4U_ID(M4U_LARB4_ID, 2) +#define M4U_PORT_MJC_DMA_WR MTK_M4U_ID(M4U_LARB4_ID, 3) + +#endif diff --git a/include/dt-bindings/pinctrl/mediatek,mt8188-pinfunc.h b/include/dt-bindings/pinctrl/mediatek,mt8188-pinfunc.h new file mode 100644 index 000000000000..2688da2f621f --- /dev/null +++ b/include/dt-bindings/pinctrl/mediatek,mt8188-pinfunc.h @@ -0,0 +1,1280 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (C) 2022 MediaTek Inc. + * Author: Hui Liu <hui.liu@mediatek.com> + */ + +#ifndef __MEDIATEK_MT8188_PINFUNC_H +#define __MEDIATEK_MT8188_PINFUNC_H + +#include "mt65xx.h" + +#define PINMUX_GPIO0__FUNC_B_GPIO0 (MTK_PIN_NO(0) | 0) +#define PINMUX_GPIO0__FUNC_B0_TP_GPIO0_AO (MTK_PIN_NO(0) | 1) +#define PINMUX_GPIO0__FUNC_O_SPIM5_CSB (MTK_PIN_NO(0) | 2) +#define PINMUX_GPIO0__FUNC_O_UTXD1 (MTK_PIN_NO(0) | 3) +#define PINMUX_GPIO0__FUNC_O_DMIC3_CLK (MTK_PIN_NO(0) | 4) +#define PINMUX_GPIO0__FUNC_B0_I2SIN_MCK (MTK_PIN_NO(0) | 5) +#define PINMUX_GPIO0__FUNC_O_I2SO2_MCK (MTK_PIN_NO(0) | 6) +#define PINMUX_GPIO0__FUNC_B0_DBG_MON_A0 (MTK_PIN_NO(0) | 7) + +#define PINMUX_GPIO1__FUNC_B_GPIO1 (MTK_PIN_NO(1) | 0) +#define PINMUX_GPIO1__FUNC_B0_TP_GPIO1_AO (MTK_PIN_NO(1) | 1) +#define PINMUX_GPIO1__FUNC_O_SPIM5_CLK (MTK_PIN_NO(1) | 2) +#define PINMUX_GPIO1__FUNC_I1_URXD1 (MTK_PIN_NO(1) | 3) +#define PINMUX_GPIO1__FUNC_I0_DMIC3_DAT (MTK_PIN_NO(1) | 4) +#define PINMUX_GPIO1__FUNC_B0_I2SIN_BCK (MTK_PIN_NO(1) | 5) +#define PINMUX_GPIO1__FUNC_B0_I2SO2_BCK (MTK_PIN_NO(1) | 6) +#define PINMUX_GPIO1__FUNC_B0_DBG_MON_A1 (MTK_PIN_NO(1) | 7) + +#define PINMUX_GPIO2__FUNC_B_GPIO2 (MTK_PIN_NO(2) | 0) +#define PINMUX_GPIO2__FUNC_B0_TP_GPIO2_AO (MTK_PIN_NO(2) | 1) +#define PINMUX_GPIO2__FUNC_B0_SPIM5_MOSI (MTK_PIN_NO(2) | 2) +#define PINMUX_GPIO2__FUNC_O_URTS1 (MTK_PIN_NO(2) | 3) +#define PINMUX_GPIO2__FUNC_I0_DMIC3_DAT_R (MTK_PIN_NO(2) | 4) +#define PINMUX_GPIO2__FUNC_B0_I2SIN_WS (MTK_PIN_NO(2) | 5) +#define PINMUX_GPIO2__FUNC_B0_I2SO2_WS (MTK_PIN_NO(2) | 6) +#define PINMUX_GPIO2__FUNC_B0_DBG_MON_A2 (MTK_PIN_NO(2) | 7) + +#define PINMUX_GPIO3__FUNC_B_GPIO3 (MTK_PIN_NO(3) | 0) +#define PINMUX_GPIO3__FUNC_B0_TP_GPIO3_AO (MTK_PIN_NO(3) | 1) +#define PINMUX_GPIO3__FUNC_B0_SPIM5_MISO (MTK_PIN_NO(3) | 2) +#define PINMUX_GPIO3__FUNC_I1_UCTS1 (MTK_PIN_NO(3) | 3) +#define PINMUX_GPIO3__FUNC_O_DMIC4_CLK (MTK_PIN_NO(3) | 4) +#define PINMUX_GPIO3__FUNC_I0_I2SIN_D0 (MTK_PIN_NO(3) | 5) +#define PINMUX_GPIO3__FUNC_O_I2SO2_D0 (MTK_PIN_NO(3) | 6) +#define PINMUX_GPIO3__FUNC_B0_DBG_MON_A3 (MTK_PIN_NO(3) | 7) + +#define PINMUX_GPIO4__FUNC_B_GPIO4 (MTK_PIN_NO(4) | 0) +#define PINMUX_GPIO4__FUNC_B0_TP_GPIO4_AO (MTK_PIN_NO(4) | 1) +#define PINMUX_GPIO4__FUNC_I0_SPDIF_IN2 (MTK_PIN_NO(4) | 2) +#define PINMUX_GPIO4__FUNC_O_I2SO1_MCK (MTK_PIN_NO(4) | 3) +#define PINMUX_GPIO4__FUNC_I0_DMIC4_DAT (MTK_PIN_NO(4) | 4) +#define PINMUX_GPIO4__FUNC_I0_I2SIN_D1 (MTK_PIN_NO(4) | 5) +#define PINMUX_GPIO4__FUNC_O_I2SO2_D1 (MTK_PIN_NO(4) | 6) +#define PINMUX_GPIO4__FUNC_B0_DBG_MON_A4 (MTK_PIN_NO(4) | 7) + +#define PINMUX_GPIO5__FUNC_B_GPIO5 (MTK_PIN_NO(5) | 0) +#define PINMUX_GPIO5__FUNC_B0_TP_GPIO5_AO (MTK_PIN_NO(5) | 1) +#define PINMUX_GPIO5__FUNC_I0_SPDIF_IN1 (MTK_PIN_NO(5) | 2) +#define PINMUX_GPIO5__FUNC_O_I2SO1_BCK (MTK_PIN_NO(5) | 3) +#define PINMUX_GPIO5__FUNC_I0_DMIC4_DAT_R (MTK_PIN_NO(5) | 4) +#define PINMUX_GPIO5__FUNC_I0_I2SIN_D2 (MTK_PIN_NO(5) | 5) +#define PINMUX_GPIO5__FUNC_O_I2SO2_D2 (MTK_PIN_NO(5) | 6) +#define PINMUX_GPIO5__FUNC_B0_DBG_MON_A5 (MTK_PIN_NO(5) | 7) + +#define PINMUX_GPIO6__FUNC_B_GPIO6 (MTK_PIN_NO(6) | 0) +#define PINMUX_GPIO6__FUNC_B0_TP_GPIO6_AO (MTK_PIN_NO(6) | 1) +#define PINMUX_GPIO6__FUNC_I0_SPDIF_IN0 (MTK_PIN_NO(6) | 2) +#define PINMUX_GPIO6__FUNC_O_I2SO1_WS (MTK_PIN_NO(6) | 3) +#define PINMUX_GPIO6__FUNC_O_DMIC1_CLK (MTK_PIN_NO(6) | 4) +#define PINMUX_GPIO6__FUNC_I0_I2SIN_D3 (MTK_PIN_NO(6) | 5) +#define PINMUX_GPIO6__FUNC_O_I2SO2_D3 (MTK_PIN_NO(6) | 6) +#define PINMUX_GPIO6__FUNC_B0_MD32_0_GPIO0 (MTK_PIN_NO(6) | 7) + +#define PINMUX_GPIO7__FUNC_B_GPIO7 (MTK_PIN_NO(7) | 0) +#define PINMUX_GPIO7__FUNC_B0_TP_GPIO7_AO (MTK_PIN_NO(7) | 1) +#define PINMUX_GPIO7__FUNC_O_SPIM3_CSB (MTK_PIN_NO(7) | 2) +#define PINMUX_GPIO7__FUNC_B0_TDMIN_MCK (MTK_PIN_NO(7) | 3) +#define PINMUX_GPIO7__FUNC_I0_DMIC1_DAT (MTK_PIN_NO(7) | 4) +#define PINMUX_GPIO7__FUNC_O_CMVREF0 (MTK_PIN_NO(7) | 5) +#define PINMUX_GPIO7__FUNC_O_CLKM0 (MTK_PIN_NO(7) | 6) +#define PINMUX_GPIO7__FUNC_B0_DBG_MON_A6 (MTK_PIN_NO(7) | 7) + +#define PINMUX_GPIO8__FUNC_B_GPIO8 (MTK_PIN_NO(8) | 0) +#define PINMUX_GPIO8__FUNC_B0_TP_GPIO0_AO (MTK_PIN_NO(8) | 1) +#define PINMUX_GPIO8__FUNC_O_SPIM3_CLK (MTK_PIN_NO(8) | 2) +#define PINMUX_GPIO8__FUNC_B0_TDMIN_BCK (MTK_PIN_NO(8) | 3) +#define PINMUX_GPIO8__FUNC_I0_DMIC1_DAT_R (MTK_PIN_NO(8) | 4) +#define PINMUX_GPIO8__FUNC_O_CMVREF1 (MTK_PIN_NO(8) | 5) +#define PINMUX_GPIO8__FUNC_O_CLKM1 (MTK_PIN_NO(8) | 6) +#define PINMUX_GPIO8__FUNC_B0_DBG_MON_A7 (MTK_PIN_NO(8) | 7) + +#define PINMUX_GPIO9__FUNC_B_GPIO9 (MTK_PIN_NO(9) | 0) +#define PINMUX_GPIO9__FUNC_B0_TP_GPIO1_AO (MTK_PIN_NO(9) | 1) +#define PINMUX_GPIO9__FUNC_B0_SPIM3_MOSI (MTK_PIN_NO(9) | 2) +#define PINMUX_GPIO9__FUNC_B0_TDMIN_LRCK (MTK_PIN_NO(9) | 3) +#define PINMUX_GPIO9__FUNC_O_DMIC2_CLK (MTK_PIN_NO(9) | 4) +#define PINMUX_GPIO9__FUNC_O_CMFLASH0 (MTK_PIN_NO(9) | 5) +#define PINMUX_GPIO9__FUNC_O_PWM_0 (MTK_PIN_NO(9) | 6) +#define PINMUX_GPIO9__FUNC_B0_DBG_MON_A8 (MTK_PIN_NO(9) | 7) + +#define PINMUX_GPIO10__FUNC_B_GPIO10 (MTK_PIN_NO(10) | 0) +#define PINMUX_GPIO10__FUNC_B0_TP_GPIO2_AO (MTK_PIN_NO(10) | 1) +#define PINMUX_GPIO10__FUNC_B0_SPIM3_MISO (MTK_PIN_NO(10) | 2) +#define PINMUX_GPIO10__FUNC_I0_TDMIN_DI (MTK_PIN_NO(10) | 3) +#define PINMUX_GPIO10__FUNC_I0_DMIC2_DAT (MTK_PIN_NO(10) | 4) +#define PINMUX_GPIO10__FUNC_O_CMFLASH1 (MTK_PIN_NO(10) | 5) +#define PINMUX_GPIO10__FUNC_O_PWM_1 (MTK_PIN_NO(10) | 6) +#define PINMUX_GPIO10__FUNC_B0_DBG_MON_A9 (MTK_PIN_NO(10) | 7) + +#define PINMUX_GPIO11__FUNC_B_GPIO11 (MTK_PIN_NO(11) | 0) +#define PINMUX_GPIO11__FUNC_B0_TP_GPIO3_AO (MTK_PIN_NO(11) | 1) +#define PINMUX_GPIO11__FUNC_O_SPDIF_OUT (MTK_PIN_NO(11) | 2) +#define PINMUX_GPIO11__FUNC_O_I2SO1_D0 (MTK_PIN_NO(11) | 3) +#define PINMUX_GPIO11__FUNC_I0_DMIC2_DAT_R (MTK_PIN_NO(11) | 4) +#define PINMUX_GPIO11__FUNC_I0_DVFSRC_EXT_REQ (MTK_PIN_NO(11) | 5) +#define PINMUX_GPIO11__FUNC_O_CMVREF6 (MTK_PIN_NO(11) | 6) +#define PINMUX_GPIO11__FUNC_B0_DBG_MON_A10 (MTK_PIN_NO(11) | 7) + +#define PINMUX_GPIO12__FUNC_B_GPIO12 (MTK_PIN_NO(12) | 0) +#define PINMUX_GPIO12__FUNC_B0_TP_GPIO4_AO (MTK_PIN_NO(12) | 1) +#define PINMUX_GPIO12__FUNC_O_SPIM4_CSB (MTK_PIN_NO(12) | 2) +#define PINMUX_GPIO12__FUNC_B1_JTMS_SEL3 (MTK_PIN_NO(12) | 3) +#define PINMUX_GPIO12__FUNC_B1_APU_JTAG_TMS (MTK_PIN_NO(12) | 4) +#define PINMUX_GPIO12__FUNC_I0_VPU_UDI_TMS (MTK_PIN_NO(12) | 5) +#define PINMUX_GPIO12__FUNC_I0_IPU_JTAG_TMS (MTK_PIN_NO(12) | 6) +#define PINMUX_GPIO12__FUNC_I0_HDMITX20_HTPLG (MTK_PIN_NO(12) | 7) + +#define PINMUX_GPIO13__FUNC_B_GPIO13 (MTK_PIN_NO(13) | 0) +#define PINMUX_GPIO13__FUNC_B0_TP_GPIO5_AO (MTK_PIN_NO(13) | 1) +#define PINMUX_GPIO13__FUNC_O_SPIM4_CLK (MTK_PIN_NO(13) | 2) +#define PINMUX_GPIO13__FUNC_I0_JTCK_SEL3 (MTK_PIN_NO(13) | 3) +#define PINMUX_GPIO13__FUNC_I0_APU_JTAG_TCK (MTK_PIN_NO(13) | 4) +#define PINMUX_GPIO13__FUNC_I0_VPU_UDI_TCK (MTK_PIN_NO(13) | 5) +#define PINMUX_GPIO13__FUNC_I0_IPU_JTAG_TCK (MTK_PIN_NO(13) | 6) +#define PINMUX_GPIO13__FUNC_B1_HDMITX20_CEC (MTK_PIN_NO(13) | 7) + +#define PINMUX_GPIO14__FUNC_B_GPIO14 (MTK_PIN_NO(14) | 0) +#define PINMUX_GPIO14__FUNC_B0_TP_GPIO6_AO (MTK_PIN_NO(14) | 1) +#define PINMUX_GPIO14__FUNC_B0_SPIM4_MOSI (MTK_PIN_NO(14) | 2) +#define PINMUX_GPIO14__FUNC_I1_JTDI_SEL3 (MTK_PIN_NO(14) | 3) +#define PINMUX_GPIO14__FUNC_I1_APU_JTAG_TDI (MTK_PIN_NO(14) | 4) +#define PINMUX_GPIO14__FUNC_I0_VPU_UDI_TDI (MTK_PIN_NO(14) | 5) +#define PINMUX_GPIO14__FUNC_I0_IPU_JTAG_TDI (MTK_PIN_NO(14) | 6) +#define PINMUX_GPIO14__FUNC_B1_HDMITX20_SCL (MTK_PIN_NO(14) | 7) + +#define PINMUX_GPIO15__FUNC_B_GPIO15 (MTK_PIN_NO(15) | 0) +#define PINMUX_GPIO15__FUNC_B0_TP_GPIO7_AO (MTK_PIN_NO(15) | 1) +#define PINMUX_GPIO15__FUNC_B0_SPIM4_MISO (MTK_PIN_NO(15) | 2) +#define PINMUX_GPIO15__FUNC_O_JTDO_SEL3 (MTK_PIN_NO(15) | 3) +#define PINMUX_GPIO15__FUNC_O_APU_JTAG_TDO (MTK_PIN_NO(15) | 4) +#define PINMUX_GPIO15__FUNC_O_VPU_UDI_TDO (MTK_PIN_NO(15) | 5) +#define PINMUX_GPIO15__FUNC_O_IPU_JTAG_TDO (MTK_PIN_NO(15) | 6) +#define PINMUX_GPIO15__FUNC_B1_HDMITX20_SDA (MTK_PIN_NO(15) | 7) + +#define PINMUX_GPIO16__FUNC_B_GPIO16 (MTK_PIN_NO(16) | 0) +#define PINMUX_GPIO16__FUNC_B0_TP_GPIO0_AO (MTK_PIN_NO(16) | 1) +#define PINMUX_GPIO16__FUNC_O_UTXD3 (MTK_PIN_NO(16) | 2) +#define PINMUX_GPIO16__FUNC_I1_JTRSTn_SEL3 (MTK_PIN_NO(16) | 3) +#define PINMUX_GPIO16__FUNC_I0_APU_JTAG_TRST (MTK_PIN_NO(16) | 4) +#define PINMUX_GPIO16__FUNC_I0_VPU_UDI_NTRST (MTK_PIN_NO(16) | 5) +#define PINMUX_GPIO16__FUNC_I0_IPU_JTAG_TRST (MTK_PIN_NO(16) | 6) +#define PINMUX_GPIO16__FUNC_O_HDMITX20_PWR5V (MTK_PIN_NO(16) | 7) + +#define PINMUX_GPIO17__FUNC_B_GPIO17 (MTK_PIN_NO(17) | 0) +#define PINMUX_GPIO17__FUNC_B0_TP_GPIO1_AO (MTK_PIN_NO(17) | 1) +#define PINMUX_GPIO17__FUNC_I1_URXD3 (MTK_PIN_NO(17) | 2) +#define PINMUX_GPIO17__FUNC_O_CMFLASH2 (MTK_PIN_NO(17) | 3) +#define PINMUX_GPIO17__FUNC_I0_EDP_TX_HPD (MTK_PIN_NO(17) | 4) +#define PINMUX_GPIO17__FUNC_I0_DVFSRC_EXT_REQ (MTK_PIN_NO(17) | 5) +#define PINMUX_GPIO17__FUNC_O_CMVREF7 (MTK_PIN_NO(17) | 6) +#define PINMUX_GPIO17__FUNC_B0_MD32_0_GPIO1 (MTK_PIN_NO(17) | 7) + +#define PINMUX_GPIO18__FUNC_B_GPIO18 (MTK_PIN_NO(18) | 0) +#define PINMUX_GPIO18__FUNC_B0_TP_GPIO2_AO (MTK_PIN_NO(18) | 1) +#define PINMUX_GPIO18__FUNC_O_CMFLASH0 (MTK_PIN_NO(18) | 2) +#define PINMUX_GPIO18__FUNC_O_CMVREF4 (MTK_PIN_NO(18) | 3) +#define PINMUX_GPIO18__FUNC_B0_TDMIN_MCK (MTK_PIN_NO(18) | 4) +#define PINMUX_GPIO18__FUNC_O_UTXD1 (MTK_PIN_NO(18) | 5) +#define PINMUX_GPIO18__FUNC_O_TP_UTXD1_AO (MTK_PIN_NO(18) | 6) +#define PINMUX_GPIO18__FUNC_B0_DBG_MON_A11 (MTK_PIN_NO(18) | 7) + +#define PINMUX_GPIO19__FUNC_B_GPIO19 (MTK_PIN_NO(19) | 0) +#define PINMUX_GPIO19__FUNC_B0_TP_GPIO3_AO (MTK_PIN_NO(19) | 1) +#define PINMUX_GPIO19__FUNC_O_CMFLASH1 (MTK_PIN_NO(19) | 2) +#define PINMUX_GPIO19__FUNC_O_CMVREF5 (MTK_PIN_NO(19) | 3) +#define PINMUX_GPIO19__FUNC_B0_TDMIN_BCK (MTK_PIN_NO(19) | 4) +#define PINMUX_GPIO19__FUNC_I1_URXD1 (MTK_PIN_NO(19) | 5) +#define PINMUX_GPIO19__FUNC_I1_TP_URXD1_AO (MTK_PIN_NO(19) | 6) +#define PINMUX_GPIO19__FUNC_B0_DBG_MON_A12 (MTK_PIN_NO(19) | 7) + +#define PINMUX_GPIO20__FUNC_B_GPIO20 (MTK_PIN_NO(20) | 0) +#define PINMUX_GPIO20__FUNC_B0_TP_GPIO4_AO (MTK_PIN_NO(20) | 1) +#define PINMUX_GPIO20__FUNC_O_CMFLASH2 (MTK_PIN_NO(20) | 2) +#define PINMUX_GPIO20__FUNC_O_CLKM2 (MTK_PIN_NO(20) | 3) +#define PINMUX_GPIO20__FUNC_B0_TDMIN_LRCK (MTK_PIN_NO(20) | 4) +#define PINMUX_GPIO20__FUNC_O_URTS1 (MTK_PIN_NO(20) | 5) +#define PINMUX_GPIO20__FUNC_O_TP_URTS1_AO (MTK_PIN_NO(20) | 6) +#define PINMUX_GPIO20__FUNC_B0_DBG_MON_A13 (MTK_PIN_NO(20) | 7) + +#define PINMUX_GPIO21__FUNC_B_GPIO21 (MTK_PIN_NO(21) | 0) +#define PINMUX_GPIO21__FUNC_B0_TP_GPIO5_AO (MTK_PIN_NO(21) | 1) +#define PINMUX_GPIO21__FUNC_O_CMFLASH3 (MTK_PIN_NO(21) | 2) +#define PINMUX_GPIO21__FUNC_O_CLKM3 (MTK_PIN_NO(21) | 3) +#define PINMUX_GPIO21__FUNC_I0_TDMIN_DI (MTK_PIN_NO(21) | 4) +#define PINMUX_GPIO21__FUNC_I1_UCTS1 (MTK_PIN_NO(21) | 5) +#define PINMUX_GPIO21__FUNC_I1_TP_UCTS1_AO (MTK_PIN_NO(21) | 6) +#define PINMUX_GPIO21__FUNC_B0_DBG_MON_A14 (MTK_PIN_NO(21) | 7) + +#define PINMUX_GPIO22__FUNC_B_GPIO22 (MTK_PIN_NO(22) | 0) +#define PINMUX_GPIO22__FUNC_O_CMMCLK0 (MTK_PIN_NO(22) | 1) +#define PINMUX_GPIO22__FUNC_B0_TP_GPIO6_AO (MTK_PIN_NO(22) | 5) +#define PINMUX_GPIO22__FUNC_B0_DBG_MON_A15 (MTK_PIN_NO(22) | 7) + +#define PINMUX_GPIO23__FUNC_B_GPIO23 (MTK_PIN_NO(23) | 0) +#define PINMUX_GPIO23__FUNC_O_CMMCLK1 (MTK_PIN_NO(23) | 1) +#define PINMUX_GPIO23__FUNC_O_PWM_2 (MTK_PIN_NO(23) | 3) +#define PINMUX_GPIO23__FUNC_B1_PCIE_PHY_I2C_SCL (MTK_PIN_NO(23) | 4) +#define PINMUX_GPIO23__FUNC_B0_TP_GPIO7_AO (MTK_PIN_NO(23) | 5) +#define PINMUX_GPIO23__FUNC_I0_DP_TX_HPD (MTK_PIN_NO(23) | 6) +#define PINMUX_GPIO23__FUNC_B0_DBG_MON_A16 (MTK_PIN_NO(23) | 7) + +#define PINMUX_GPIO24__FUNC_B_GPIO24 (MTK_PIN_NO(24) | 0) +#define PINMUX_GPIO24__FUNC_O_CMMCLK2 (MTK_PIN_NO(24) | 1) +#define PINMUX_GPIO24__FUNC_O_PWM_3 (MTK_PIN_NO(24) | 3) +#define PINMUX_GPIO24__FUNC_B1_PCIE_PHY_I2C_SDA (MTK_PIN_NO(24) | 4) +#define PINMUX_GPIO24__FUNC_I0_DVFSRC_EXT_REQ (MTK_PIN_NO(24) | 5) +#define PINMUX_GPIO24__FUNC_I0_EDP_TX_HPD (MTK_PIN_NO(24) | 6) +#define PINMUX_GPIO24__FUNC_B0_MD32_0_GPIO2 (MTK_PIN_NO(24) | 7) + +#define PINMUX_GPIO25__FUNC_B_GPIO25 (MTK_PIN_NO(25) | 0) +#define PINMUX_GPIO25__FUNC_O_LCM_RST (MTK_PIN_NO(25) | 1) +#define PINMUX_GPIO25__FUNC_O_LCM1_RST (MTK_PIN_NO(25) | 2) +#define PINMUX_GPIO25__FUNC_I0_DP_TX_HPD (MTK_PIN_NO(25) | 3) + +#define PINMUX_GPIO26__FUNC_B_GPIO26 (MTK_PIN_NO(26) | 0) +#define PINMUX_GPIO26__FUNC_I0_DSI_TE (MTK_PIN_NO(26) | 1) +#define PINMUX_GPIO26__FUNC_I0_DSI1_TE (MTK_PIN_NO(26) | 2) +#define PINMUX_GPIO26__FUNC_I0_EDP_TX_HPD (MTK_PIN_NO(26) | 3) + +#define PINMUX_GPIO27__FUNC_B_GPIO27 (MTK_PIN_NO(27) | 0) +#define PINMUX_GPIO27__FUNC_O_LCM1_RST (MTK_PIN_NO(27) | 1) +#define PINMUX_GPIO27__FUNC_O_LCM_RST (MTK_PIN_NO(27) | 2) +#define PINMUX_GPIO27__FUNC_I0_DP_TX_HPD (MTK_PIN_NO(27) | 3) +#define PINMUX_GPIO27__FUNC_O_CMVREF2 (MTK_PIN_NO(27) | 4) +#define PINMUX_GPIO27__FUNC_O_mbistwriteen_trigger (MTK_PIN_NO(27) | 5) +#define PINMUX_GPIO27__FUNC_O_PWM_2 (MTK_PIN_NO(27) | 6) +#define PINMUX_GPIO27__FUNC_B0_DBG_MON_A17 (MTK_PIN_NO(27) | 7) + +#define PINMUX_GPIO28__FUNC_B_GPIO28 (MTK_PIN_NO(28) | 0) +#define PINMUX_GPIO28__FUNC_I0_DSI1_TE (MTK_PIN_NO(28) | 1) +#define PINMUX_GPIO28__FUNC_I0_DSI_TE (MTK_PIN_NO(28) | 2) +#define PINMUX_GPIO28__FUNC_I0_EDP_TX_HPD (MTK_PIN_NO(28) | 3) +#define PINMUX_GPIO28__FUNC_O_CMVREF3 (MTK_PIN_NO(28) | 4) +#define PINMUX_GPIO28__FUNC_O_mbistreaden_trigger (MTK_PIN_NO(28) | 5) +#define PINMUX_GPIO28__FUNC_O_PWM_3 (MTK_PIN_NO(28) | 6) +#define PINMUX_GPIO28__FUNC_B0_DBG_MON_A18 (MTK_PIN_NO(28) | 7) + +#define PINMUX_GPIO29__FUNC_B_GPIO29 (MTK_PIN_NO(29) | 0) +#define PINMUX_GPIO29__FUNC_O_DISP_PWM0 (MTK_PIN_NO(29) | 1) +#define PINMUX_GPIO29__FUNC_O_DISP_PWM1 (MTK_PIN_NO(29) | 2) + +#define PINMUX_GPIO30__FUNC_B_GPIO30 (MTK_PIN_NO(30) | 0) +#define PINMUX_GPIO30__FUNC_O_DISP_PWM1 (MTK_PIN_NO(30) | 1) +#define PINMUX_GPIO30__FUNC_O_DISP_PWM0 (MTK_PIN_NO(30) | 2) +#define PINMUX_GPIO30__FUNC_O_CMFLASH3 (MTK_PIN_NO(30) | 3) +#define PINMUX_GPIO30__FUNC_O_PWM_1 (MTK_PIN_NO(30) | 4) +#define PINMUX_GPIO30__FUNC_B0_DBG_MON_A19 (MTK_PIN_NO(30) | 7) + +#define PINMUX_GPIO31__FUNC_B_GPIO31 (MTK_PIN_NO(31) | 0) +#define PINMUX_GPIO31__FUNC_O_UTXD0 (MTK_PIN_NO(31) | 1) +#define PINMUX_GPIO31__FUNC_O_TP_UTXD1_AO (MTK_PIN_NO(31) | 2) +#define PINMUX_GPIO31__FUNC_O_ADSP_UTXD0 (MTK_PIN_NO(31) | 3) +#define PINMUX_GPIO31__FUNC_O_TP_UTXD2_AO (MTK_PIN_NO(31) | 4) +#define PINMUX_GPIO31__FUNC_O_MD32_0_TXD (MTK_PIN_NO(31) | 5) +#define PINMUX_GPIO31__FUNC_O_MD32_1_TXD (MTK_PIN_NO(31) | 6) +#define PINMUX_GPIO31__FUNC_O_SSPM_UTXD_AO (MTK_PIN_NO(31) | 7) + +#define PINMUX_GPIO32__FUNC_B_GPIO32 (MTK_PIN_NO(32) | 0) +#define PINMUX_GPIO32__FUNC_I1_URXD0 (MTK_PIN_NO(32) | 1) +#define PINMUX_GPIO32__FUNC_I1_TP_URXD1_AO (MTK_PIN_NO(32) | 2) +#define PINMUX_GPIO32__FUNC_I1_ADSP_URXD0 (MTK_PIN_NO(32) | 3) +#define PINMUX_GPIO32__FUNC_I1_TP_URXD2_AO (MTK_PIN_NO(32) | 4) +#define PINMUX_GPIO32__FUNC_I1_MD32_0_RXD (MTK_PIN_NO(32) | 5) +#define PINMUX_GPIO32__FUNC_I1_MD32_1_RXD (MTK_PIN_NO(32) | 6) +#define PINMUX_GPIO32__FUNC_I1_SSPM_URXD_AO (MTK_PIN_NO(32) | 7) + +#define PINMUX_GPIO33__FUNC_B_GPIO33 (MTK_PIN_NO(33) | 0) +#define PINMUX_GPIO33__FUNC_O_UTXD1 (MTK_PIN_NO(33) | 1) +#define PINMUX_GPIO33__FUNC_O_URTS2 (MTK_PIN_NO(33) | 2) +#define PINMUX_GPIO33__FUNC_O_ADSP_UTXD0 (MTK_PIN_NO(33) | 3) +#define PINMUX_GPIO33__FUNC_O_TP_UTXD1_AO (MTK_PIN_NO(33) | 4) +#define PINMUX_GPIO33__FUNC_O_mbistwriteen_trigger (MTK_PIN_NO(33) | 5) +#define PINMUX_GPIO33__FUNC_O_MD32_0_TXD (MTK_PIN_NO(33) | 6) +#define PINMUX_GPIO33__FUNC_O_SSPM_UTXD_AO (MTK_PIN_NO(33) | 7) + +#define PINMUX_GPIO34__FUNC_B_GPIO34 (MTK_PIN_NO(34) | 0) +#define PINMUX_GPIO34__FUNC_I1_URXD1 (MTK_PIN_NO(34) | 1) +#define PINMUX_GPIO34__FUNC_I1_UCTS2 (MTK_PIN_NO(34) | 2) +#define PINMUX_GPIO34__FUNC_I1_ADSP_URXD0 (MTK_PIN_NO(34) | 3) +#define PINMUX_GPIO34__FUNC_I1_TP_URXD1_AO (MTK_PIN_NO(34) | 4) +#define PINMUX_GPIO34__FUNC_O_mbistreaden_trigger (MTK_PIN_NO(34) | 5) +#define PINMUX_GPIO34__FUNC_I1_MD32_0_RXD (MTK_PIN_NO(34) | 6) +#define PINMUX_GPIO34__FUNC_I1_SSPM_URXD_AO (MTK_PIN_NO(34) | 7) + +#define PINMUX_GPIO35__FUNC_B_GPIO35 (MTK_PIN_NO(35) | 0) +#define PINMUX_GPIO35__FUNC_O_UTXD2 (MTK_PIN_NO(35) | 1) +#define PINMUX_GPIO35__FUNC_O_URTS1 (MTK_PIN_NO(35) | 2) +#define PINMUX_GPIO35__FUNC_O_ADSP_UTXD0 (MTK_PIN_NO(35) | 3) +#define PINMUX_GPIO35__FUNC_O_TP_URTS1_AO (MTK_PIN_NO(35) | 4) +#define PINMUX_GPIO35__FUNC_O_TP_UTXD2_AO (MTK_PIN_NO(35) | 5) +#define PINMUX_GPIO35__FUNC_O_MD32_1_TXD (MTK_PIN_NO(35) | 6) +#define PINMUX_GPIO35__FUNC_B0_DBG_MON_A20 (MTK_PIN_NO(35) | 7) + +#define PINMUX_GPIO36__FUNC_B_GPIO36 (MTK_PIN_NO(36) | 0) +#define PINMUX_GPIO36__FUNC_I1_URXD2 (MTK_PIN_NO(36) | 1) +#define PINMUX_GPIO36__FUNC_I1_UCTS1 (MTK_PIN_NO(36) | 2) +#define PINMUX_GPIO36__FUNC_I1_ADSP_URXD0 (MTK_PIN_NO(36) | 3) +#define PINMUX_GPIO36__FUNC_I1_TP_UCTS1_AO (MTK_PIN_NO(36) | 4) +#define PINMUX_GPIO36__FUNC_I1_TP_URXD2_AO (MTK_PIN_NO(36) | 5) +#define PINMUX_GPIO36__FUNC_I1_MD32_1_RXD (MTK_PIN_NO(36) | 6) +#define PINMUX_GPIO36__FUNC_B0_DBG_MON_A21 (MTK_PIN_NO(36) | 7) + +#define PINMUX_GPIO37__FUNC_B_GPIO37 (MTK_PIN_NO(37) | 0) +#define PINMUX_GPIO37__FUNC_B1_JTMS_SEL1 (MTK_PIN_NO(37) | 1) +#define PINMUX_GPIO37__FUNC_I0_UDI_TMS (MTK_PIN_NO(37) | 2) +#define PINMUX_GPIO37__FUNC_I1_SPM_JTAG_TMS (MTK_PIN_NO(37) | 3) +#define PINMUX_GPIO37__FUNC_I1_ADSP_JTAG0_TMS (MTK_PIN_NO(37) | 4) +#define PINMUX_GPIO37__FUNC_I1_SCP_JTAG0_TMS (MTK_PIN_NO(37) | 5) +#define PINMUX_GPIO37__FUNC_I1_CCU0_JTAG_TMS (MTK_PIN_NO(37) | 6) +#define PINMUX_GPIO37__FUNC_I1_MCUPM_JTAG_TMS (MTK_PIN_NO(37) | 7) + +#define PINMUX_GPIO38__FUNC_B_GPIO38 (MTK_PIN_NO(38) | 0) +#define PINMUX_GPIO38__FUNC_I0_JTCK_SEL1 (MTK_PIN_NO(38) | 1) +#define PINMUX_GPIO38__FUNC_I0_UDI_TCK (MTK_PIN_NO(38) | 2) +#define PINMUX_GPIO38__FUNC_I1_SPM_JTAG_TCK (MTK_PIN_NO(38) | 3) +#define PINMUX_GPIO38__FUNC_I0_ADSP_JTAG0_TCK (MTK_PIN_NO(38) | 4) +#define PINMUX_GPIO38__FUNC_I1_SCP_JTAG0_TCK (MTK_PIN_NO(38) | 5) +#define PINMUX_GPIO38__FUNC_I1_CCU0_JTAG_TCK (MTK_PIN_NO(38) | 6) +#define PINMUX_GPIO38__FUNC_I1_MCUPM_JTAG_TCK (MTK_PIN_NO(38) | 7) + +#define PINMUX_GPIO39__FUNC_B_GPIO39 (MTK_PIN_NO(39) | 0) +#define PINMUX_GPIO39__FUNC_I1_JTDI_SEL1 (MTK_PIN_NO(39) | 1) +#define PINMUX_GPIO39__FUNC_I0_UDI_TDI (MTK_PIN_NO(39) | 2) +#define PINMUX_GPIO39__FUNC_I1_SPM_JTAG_TDI (MTK_PIN_NO(39) | 3) +#define PINMUX_GPIO39__FUNC_I1_ADSP_JTAG0_TDI (MTK_PIN_NO(39) | 4) +#define PINMUX_GPIO39__FUNC_I1_SCP_JTAG0_TDI (MTK_PIN_NO(39) | 5) +#define PINMUX_GPIO39__FUNC_I1_CCU0_JTAG_TDI (MTK_PIN_NO(39) | 6) +#define PINMUX_GPIO39__FUNC_I1_MCUPM_JTAG_TDI (MTK_PIN_NO(39) | 7) + +#define PINMUX_GPIO40__FUNC_B_GPIO40 (MTK_PIN_NO(40) | 0) +#define PINMUX_GPIO40__FUNC_O_JTDO_SEL1 (MTK_PIN_NO(40) | 1) +#define PINMUX_GPIO40__FUNC_O_UDI_TDO (MTK_PIN_NO(40) | 2) +#define PINMUX_GPIO40__FUNC_O_SPM_JTAG_TDO (MTK_PIN_NO(40) | 3) +#define PINMUX_GPIO40__FUNC_O_ADSP_JTAG0_TDO (MTK_PIN_NO(40) | 4) +#define PINMUX_GPIO40__FUNC_O_SCP_JTAG0_TDO (MTK_PIN_NO(40) | 5) +#define PINMUX_GPIO40__FUNC_O_CCU0_JTAG_TDO (MTK_PIN_NO(40) | 6) +#define PINMUX_GPIO40__FUNC_O_MCUPM_JTAG_TDO (MTK_PIN_NO(40) | 7) + +#define PINMUX_GPIO41__FUNC_B_GPIO41 (MTK_PIN_NO(41) | 0) +#define PINMUX_GPIO41__FUNC_I1_JTRSTn_SEL1 (MTK_PIN_NO(41) | 1) +#define PINMUX_GPIO41__FUNC_I0_UDI_NTRST (MTK_PIN_NO(41) | 2) +#define PINMUX_GPIO41__FUNC_I0_SPM_JTAG_TRSTN (MTK_PIN_NO(41) | 3) +#define PINMUX_GPIO41__FUNC_I1_ADSP_JTAG0_TRSTN (MTK_PIN_NO(41) | 4) +#define PINMUX_GPIO41__FUNC_I0_SCP_JTAG0_TRSTN (MTK_PIN_NO(41) | 5) +#define PINMUX_GPIO41__FUNC_I1_CCU0_JTAG_TRST (MTK_PIN_NO(41) | 6) +#define PINMUX_GPIO41__FUNC_I0_MCUPM_JTAG_TRSTN (MTK_PIN_NO(41) | 7) + +#define PINMUX_GPIO42__FUNC_B_GPIO42 (MTK_PIN_NO(42) | 0) +#define PINMUX_GPIO42__FUNC_B1_KPCOL0 (MTK_PIN_NO(42) | 1) + +#define PINMUX_GPIO43__FUNC_B_GPIO43 (MTK_PIN_NO(43) | 0) +#define PINMUX_GPIO43__FUNC_B1_KPCOL1 (MTK_PIN_NO(43) | 1) +#define PINMUX_GPIO43__FUNC_I0_DP_TX_HPD (MTK_PIN_NO(43) | 2) +#define PINMUX_GPIO43__FUNC_O_CMFLASH2 (MTK_PIN_NO(43) | 3) +#define PINMUX_GPIO43__FUNC_I0_DVFSRC_EXT_REQ (MTK_PIN_NO(43) | 4) +#define PINMUX_GPIO43__FUNC_O_mbistwriteen_trigger (MTK_PIN_NO(43) | 7) + +#define PINMUX_GPIO44__FUNC_B_GPIO44 (MTK_PIN_NO(44) | 0) +#define PINMUX_GPIO44__FUNC_B1_KPROW0 (MTK_PIN_NO(44) | 1) + +#define PINMUX_GPIO45__FUNC_B_GPIO45 (MTK_PIN_NO(45) | 0) +#define PINMUX_GPIO45__FUNC_B1_KPROW1 (MTK_PIN_NO(45) | 1) +#define PINMUX_GPIO45__FUNC_I0_EDP_TX_HPD (MTK_PIN_NO(45) | 2) +#define PINMUX_GPIO45__FUNC_O_CMFLASH3 (MTK_PIN_NO(45) | 3) +#define PINMUX_GPIO45__FUNC_B0_I2SIN_MCK (MTK_PIN_NO(45) | 4) +#define PINMUX_GPIO45__FUNC_O_mbistreaden_trigger (MTK_PIN_NO(45) | 7) + +#define PINMUX_GPIO46__FUNC_B_GPIO46 (MTK_PIN_NO(46) | 0) +#define PINMUX_GPIO46__FUNC_I0_DP_TX_HPD (MTK_PIN_NO(46) | 1) +#define PINMUX_GPIO46__FUNC_O_PWM_0 (MTK_PIN_NO(46) | 2) +#define PINMUX_GPIO46__FUNC_I0_VBUSVALID_2P (MTK_PIN_NO(46) | 3) +#define PINMUX_GPIO46__FUNC_B0_DBG_MON_A22 (MTK_PIN_NO(46) | 7) + +#define PINMUX_GPIO47__FUNC_B_GPIO47 (MTK_PIN_NO(47) | 0) +#define PINMUX_GPIO47__FUNC_I1_WAKEN (MTK_PIN_NO(47) | 1) +#define PINMUX_GPIO47__FUNC_O_GDU_TROOPS_DET0 (MTK_PIN_NO(47) | 6) + +#define PINMUX_GPIO48__FUNC_B_GPIO48 (MTK_PIN_NO(48) | 0) +#define PINMUX_GPIO48__FUNC_O_PERSTN (MTK_PIN_NO(48) | 1) +#define PINMUX_GPIO48__FUNC_O_GDU_TROOPS_DET1 (MTK_PIN_NO(48) | 6) + +#define PINMUX_GPIO49__FUNC_B_GPIO49 (MTK_PIN_NO(49) | 0) +#define PINMUX_GPIO49__FUNC_B1_CLKREQN (MTK_PIN_NO(49) | 1) +#define PINMUX_GPIO49__FUNC_O_GDU_TROOPS_DET2 (MTK_PIN_NO(49) | 6) + +#define PINMUX_GPIO50__FUNC_B_GPIO50 (MTK_PIN_NO(50) | 0) +#define PINMUX_GPIO50__FUNC_O_HDMITX20_PWR5V (MTK_PIN_NO(50) | 1) +#define PINMUX_GPIO50__FUNC_I1_IDDIG_1P (MTK_PIN_NO(50) | 3) +#define PINMUX_GPIO50__FUNC_I1_SCP_JTAG1_TMS (MTK_PIN_NO(50) | 4) +#define PINMUX_GPIO50__FUNC_I1_SSPM_JTAG_TMS (MTK_PIN_NO(50) | 5) +#define PINMUX_GPIO50__FUNC_I1_MD32_0_JTAG_TMS (MTK_PIN_NO(50) | 6) +#define PINMUX_GPIO50__FUNC_I1_MD32_1_JTAG_TMS (MTK_PIN_NO(50) | 7) + +#define PINMUX_GPIO51__FUNC_B_GPIO51 (MTK_PIN_NO(51) | 0) +#define PINMUX_GPIO51__FUNC_I0_HDMITX20_HTPLG (MTK_PIN_NO(51) | 1) +#define PINMUX_GPIO51__FUNC_I0_EDP_TX_HPD (MTK_PIN_NO(51) | 2) +#define PINMUX_GPIO51__FUNC_O_USB_DRVVBUS_1P (MTK_PIN_NO(51) | 3) +#define PINMUX_GPIO51__FUNC_I1_SCP_JTAG1_TCK (MTK_PIN_NO(51) | 4) +#define PINMUX_GPIO51__FUNC_I1_SSPM_JTAG_TCK (MTK_PIN_NO(51) | 5) +#define PINMUX_GPIO51__FUNC_I1_MD32_0_JTAG_TCK (MTK_PIN_NO(51) | 6) +#define PINMUX_GPIO51__FUNC_I1_MD32_1_JTAG_TCK (MTK_PIN_NO(51) | 7) + +#define PINMUX_GPIO52__FUNC_B_GPIO52 (MTK_PIN_NO(52) | 0) +#define PINMUX_GPIO52__FUNC_B1_HDMITX20_CEC (MTK_PIN_NO(52) | 1) +#define PINMUX_GPIO52__FUNC_I0_VBUSVALID_1P (MTK_PIN_NO(52) | 3) +#define PINMUX_GPIO52__FUNC_I1_SCP_JTAG1_TDI (MTK_PIN_NO(52) | 4) +#define PINMUX_GPIO52__FUNC_I1_SSPM_JTAG_TDI (MTK_PIN_NO(52) | 5) +#define PINMUX_GPIO52__FUNC_I1_MD32_0_JTAG_TDI (MTK_PIN_NO(52) | 6) +#define PINMUX_GPIO52__FUNC_I1_MD32_1_JTAG_TDI (MTK_PIN_NO(52) | 7) + +#define PINMUX_GPIO53__FUNC_B_GPIO53 (MTK_PIN_NO(53) | 0) +#define PINMUX_GPIO53__FUNC_B1_HDMITX20_SCL (MTK_PIN_NO(53) | 1) +#define PINMUX_GPIO53__FUNC_I1_IDDIG_2P (MTK_PIN_NO(53) | 3) +#define PINMUX_GPIO53__FUNC_O_SCP_JTAG1_TDO (MTK_PIN_NO(53) | 4) +#define PINMUX_GPIO53__FUNC_O_SSPM_JTAG_TDO (MTK_PIN_NO(53) | 5) +#define PINMUX_GPIO53__FUNC_O_MD32_0_JTAG_TDO (MTK_PIN_NO(53) | 6) +#define PINMUX_GPIO53__FUNC_O_MD32_1_JTAG_TDO (MTK_PIN_NO(53) | 7) + +#define PINMUX_GPIO54__FUNC_B_GPIO54 (MTK_PIN_NO(54) | 0) +#define PINMUX_GPIO54__FUNC_B1_HDMITX20_SDA (MTK_PIN_NO(54) | 1) +#define PINMUX_GPIO54__FUNC_O_USB_DRVVBUS_2P (MTK_PIN_NO(54) | 3) +#define PINMUX_GPIO54__FUNC_I0_SCP_JTAG1_TRSTN (MTK_PIN_NO(54) | 4) +#define PINMUX_GPIO54__FUNC_I0_SSPM_JTAG_TRSTN (MTK_PIN_NO(54) | 5) +#define PINMUX_GPIO54__FUNC_I1_MD32_0_JTAG_TRST (MTK_PIN_NO(54) | 6) +#define PINMUX_GPIO54__FUNC_I1_MD32_1_JTAG_TRST (MTK_PIN_NO(54) | 7) + +#define PINMUX_GPIO55__FUNC_B_GPIO55 (MTK_PIN_NO(55) | 0) +#define PINMUX_GPIO55__FUNC_B1_SCL0 (MTK_PIN_NO(55) | 1) +#define PINMUX_GPIO55__FUNC_B1_SCP_SCL0 (MTK_PIN_NO(55) | 2) +#define PINMUX_GPIO55__FUNC_B1_SCP_SCL1 (MTK_PIN_NO(55) | 3) +#define PINMUX_GPIO55__FUNC_B1_PCIE_PHY_I2C_SCL (MTK_PIN_NO(55) | 4) + +#define PINMUX_GPIO56__FUNC_B_GPIO56 (MTK_PIN_NO(56) | 0) +#define PINMUX_GPIO56__FUNC_B1_SDA0 (MTK_PIN_NO(56) | 1) +#define PINMUX_GPIO56__FUNC_B1_SCP_SDA0 (MTK_PIN_NO(56) | 2) +#define PINMUX_GPIO56__FUNC_B1_SCP_SDA1 (MTK_PIN_NO(56) | 3) +#define PINMUX_GPIO56__FUNC_B1_PCIE_PHY_I2C_SDA (MTK_PIN_NO(56) | 4) + +#define PINMUX_GPIO57__FUNC_B_GPIO57 (MTK_PIN_NO(57) | 0) +#define PINMUX_GPIO57__FUNC_B1_SCL1 (MTK_PIN_NO(57) | 1) + +#define PINMUX_GPIO58__FUNC_B_GPIO58 (MTK_PIN_NO(58) | 0) +#define PINMUX_GPIO58__FUNC_B1_SDA1 (MTK_PIN_NO(58) | 1) + +#define PINMUX_GPIO59__FUNC_B_GPIO59 (MTK_PIN_NO(59) | 0) +#define PINMUX_GPIO59__FUNC_B1_SCL2 (MTK_PIN_NO(59) | 1) +#define PINMUX_GPIO59__FUNC_B1_SCP_SCL0 (MTK_PIN_NO(59) | 2) +#define PINMUX_GPIO59__FUNC_B1_SCP_SCL1 (MTK_PIN_NO(59) | 3) + +#define PINMUX_GPIO60__FUNC_B_GPIO60 (MTK_PIN_NO(60) | 0) +#define PINMUX_GPIO60__FUNC_B1_SDA2 (MTK_PIN_NO(60) | 1) +#define PINMUX_GPIO60__FUNC_B1_SCP_SDA0 (MTK_PIN_NO(60) | 2) +#define PINMUX_GPIO60__FUNC_B1_SCP_SDA1 (MTK_PIN_NO(60) | 3) + +#define PINMUX_GPIO61__FUNC_B_GPIO61 (MTK_PIN_NO(61) | 0) +#define PINMUX_GPIO61__FUNC_B1_SCL3 (MTK_PIN_NO(61) | 1) +#define PINMUX_GPIO61__FUNC_B1_SCP_SCL0 (MTK_PIN_NO(61) | 2) +#define PINMUX_GPIO61__FUNC_B1_SCP_SCL1 (MTK_PIN_NO(61) | 3) +#define PINMUX_GPIO61__FUNC_B1_PCIE_PHY_I2C_SCL (MTK_PIN_NO(61) | 4) + +#define PINMUX_GPIO62__FUNC_B_GPIO62 (MTK_PIN_NO(62) | 0) +#define PINMUX_GPIO62__FUNC_B1_SDA3 (MTK_PIN_NO(62) | 1) +#define PINMUX_GPIO62__FUNC_B1_SCP_SDA0 (MTK_PIN_NO(62) | 2) +#define PINMUX_GPIO62__FUNC_B1_SCP_SDA1 (MTK_PIN_NO(62) | 3) +#define PINMUX_GPIO62__FUNC_B1_PCIE_PHY_I2C_SDA (MTK_PIN_NO(62) | 4) + +#define PINMUX_GPIO63__FUNC_B_GPIO63 (MTK_PIN_NO(63) | 0) +#define PINMUX_GPIO63__FUNC_B1_SCL4 (MTK_PIN_NO(63) | 1) + +#define PINMUX_GPIO64__FUNC_B_GPIO64 (MTK_PIN_NO(64) | 0) +#define PINMUX_GPIO64__FUNC_B1_SDA4 (MTK_PIN_NO(64) | 1) + +#define PINMUX_GPIO65__FUNC_B_GPIO65 (MTK_PIN_NO(65) | 0) +#define PINMUX_GPIO65__FUNC_B1_SCL5 (MTK_PIN_NO(65) | 1) +#define PINMUX_GPIO65__FUNC_B1_SCP_SCL0 (MTK_PIN_NO(65) | 2) +#define PINMUX_GPIO65__FUNC_B1_SCP_SCL1 (MTK_PIN_NO(65) | 3) + +#define PINMUX_GPIO66__FUNC_B_GPIO66 (MTK_PIN_NO(66) | 0) +#define PINMUX_GPIO66__FUNC_B1_SDA5 (MTK_PIN_NO(66) | 1) +#define PINMUX_GPIO66__FUNC_B1_SCP_SDA0 (MTK_PIN_NO(66) | 2) +#define PINMUX_GPIO66__FUNC_B1_SCP_SDA1 (MTK_PIN_NO(66) | 3) + +#define PINMUX_GPIO67__FUNC_B_GPIO67 (MTK_PIN_NO(67) | 0) +#define PINMUX_GPIO67__FUNC_B1_SCL6 (MTK_PIN_NO(67) | 1) +#define PINMUX_GPIO67__FUNC_B1_SCP_SCL0 (MTK_PIN_NO(67) | 2) +#define PINMUX_GPIO67__FUNC_B1_SCP_SCL1 (MTK_PIN_NO(67) | 3) +#define PINMUX_GPIO67__FUNC_B1_PCIE_PHY_I2C_SCL (MTK_PIN_NO(67) | 4) + +#define PINMUX_GPIO68__FUNC_B_GPIO68 (MTK_PIN_NO(68) | 0) +#define PINMUX_GPIO68__FUNC_B1_SDA6 (MTK_PIN_NO(68) | 1) +#define PINMUX_GPIO68__FUNC_B1_SCP_SDA0 (MTK_PIN_NO(68) | 2) +#define PINMUX_GPIO68__FUNC_B1_SCP_SDA1 (MTK_PIN_NO(68) | 3) +#define PINMUX_GPIO68__FUNC_B1_PCIE_PHY_I2C_SDA (MTK_PIN_NO(68) | 4) + +#define PINMUX_GPIO69__FUNC_B_GPIO69 (MTK_PIN_NO(69) | 0) +#define PINMUX_GPIO69__FUNC_O_SPIM0_CSB (MTK_PIN_NO(69) | 1) +#define PINMUX_GPIO69__FUNC_O_SCP_SPI0_CS (MTK_PIN_NO(69) | 2) +#define PINMUX_GPIO69__FUNC_O_DMIC3_CLK (MTK_PIN_NO(69) | 3) +#define PINMUX_GPIO69__FUNC_B0_MD32_1_GPIO0 (MTK_PIN_NO(69) | 4) +#define PINMUX_GPIO69__FUNC_O_CMVREF0 (MTK_PIN_NO(69) | 5) +#define PINMUX_GPIO69__FUNC_O_GDU_SUM_TROOP0_0 (MTK_PIN_NO(69) | 6) +#define PINMUX_GPIO69__FUNC_B0_DBG_MON_A23 (MTK_PIN_NO(69) | 7) + +#define PINMUX_GPIO70__FUNC_B_GPIO70 (MTK_PIN_NO(70) | 0) +#define PINMUX_GPIO70__FUNC_O_SPIM0_CLK (MTK_PIN_NO(70) | 1) +#define PINMUX_GPIO70__FUNC_O_SCP_SPI0_CK (MTK_PIN_NO(70) | 2) +#define PINMUX_GPIO70__FUNC_I0_DMIC3_DAT (MTK_PIN_NO(70) | 3) +#define PINMUX_GPIO70__FUNC_B0_MD32_1_GPIO1 (MTK_PIN_NO(70) | 4) +#define PINMUX_GPIO70__FUNC_O_CMVREF1 (MTK_PIN_NO(70) | 5) +#define PINMUX_GPIO70__FUNC_O_GDU_SUM_TROOP0_1 (MTK_PIN_NO(70) | 6) +#define PINMUX_GPIO70__FUNC_B0_DBG_MON_A24 (MTK_PIN_NO(70) | 7) + +#define PINMUX_GPIO71__FUNC_B_GPIO71 (MTK_PIN_NO(71) | 0) +#define PINMUX_GPIO71__FUNC_B0_SPIM0_MOSI (MTK_PIN_NO(71) | 1) +#define PINMUX_GPIO71__FUNC_O_SCP_SPI0_MO (MTK_PIN_NO(71) | 2) +#define PINMUX_GPIO71__FUNC_I0_DMIC3_DAT_R (MTK_PIN_NO(71) | 3) +#define PINMUX_GPIO71__FUNC_B0_MD32_1_GPIO2 (MTK_PIN_NO(71) | 4) +#define PINMUX_GPIO71__FUNC_O_CMVREF2 (MTK_PIN_NO(71) | 5) +#define PINMUX_GPIO71__FUNC_O_GDU_SUM_TROOP0_2 (MTK_PIN_NO(71) | 6) +#define PINMUX_GPIO71__FUNC_B0_DBG_MON_A25 (MTK_PIN_NO(71) | 7) + +#define PINMUX_GPIO72__FUNC_B_GPIO72 (MTK_PIN_NO(72) | 0) +#define PINMUX_GPIO72__FUNC_B0_SPIM0_MISO (MTK_PIN_NO(72) | 1) +#define PINMUX_GPIO72__FUNC_I0_SCP_SPI0_MI (MTK_PIN_NO(72) | 2) +#define PINMUX_GPIO72__FUNC_O_DMIC4_CLK (MTK_PIN_NO(72) | 3) +#define PINMUX_GPIO72__FUNC_O_CMVREF3 (MTK_PIN_NO(72) | 5) +#define PINMUX_GPIO72__FUNC_O_GDU_SUM_TROOP1_0 (MTK_PIN_NO(72) | 6) +#define PINMUX_GPIO72__FUNC_B0_DBG_MON_A26 (MTK_PIN_NO(72) | 7) + +#define PINMUX_GPIO73__FUNC_B_GPIO73 (MTK_PIN_NO(73) | 0) +#define PINMUX_GPIO73__FUNC_B0_SPIM0_MIO2 (MTK_PIN_NO(73) | 1) +#define PINMUX_GPIO73__FUNC_O_UTXD3 (MTK_PIN_NO(73) | 2) +#define PINMUX_GPIO73__FUNC_I0_DMIC4_DAT (MTK_PIN_NO(73) | 3) +#define PINMUX_GPIO73__FUNC_O_CLKM0 (MTK_PIN_NO(73) | 4) +#define PINMUX_GPIO73__FUNC_O_CMVREF4 (MTK_PIN_NO(73) | 5) +#define PINMUX_GPIO73__FUNC_O_GDU_SUM_TROOP1_1 (MTK_PIN_NO(73) | 6) +#define PINMUX_GPIO73__FUNC_B0_DBG_MON_A27 (MTK_PIN_NO(73) | 7) + +#define PINMUX_GPIO74__FUNC_B_GPIO74 (MTK_PIN_NO(74) | 0) +#define PINMUX_GPIO74__FUNC_B0_SPIM0_MIO3 (MTK_PIN_NO(74) | 1) +#define PINMUX_GPIO74__FUNC_I1_URXD3 (MTK_PIN_NO(74) | 2) +#define PINMUX_GPIO74__FUNC_I0_DMIC4_DAT_R (MTK_PIN_NO(74) | 3) +#define PINMUX_GPIO74__FUNC_O_CLKM1 (MTK_PIN_NO(74) | 4) +#define PINMUX_GPIO74__FUNC_O_CMVREF5 (MTK_PIN_NO(74) | 5) +#define PINMUX_GPIO74__FUNC_O_GDU_SUM_TROOP1_2 (MTK_PIN_NO(74) | 6) +#define PINMUX_GPIO74__FUNC_B0_DBG_MON_A28 (MTK_PIN_NO(74) | 7) + +#define PINMUX_GPIO75__FUNC_B_GPIO75 (MTK_PIN_NO(75) | 0) +#define PINMUX_GPIO75__FUNC_O_SPIM1_CSB (MTK_PIN_NO(75) | 1) +#define PINMUX_GPIO75__FUNC_O_SCP_SPI1_A_CS (MTK_PIN_NO(75) | 2) +#define PINMUX_GPIO75__FUNC_B0_TDMIN_MCK (MTK_PIN_NO(75) | 3) +#define PINMUX_GPIO75__FUNC_B1_SCP_SCL0 (MTK_PIN_NO(75) | 4) +#define PINMUX_GPIO75__FUNC_O_CMVREF6 (MTK_PIN_NO(75) | 5) +#define PINMUX_GPIO75__FUNC_O_GDU_SUM_TROOP2_0 (MTK_PIN_NO(75) | 6) +#define PINMUX_GPIO75__FUNC_B0_DBG_MON_A29 (MTK_PIN_NO(75) | 7) + +#define PINMUX_GPIO76__FUNC_B_GPIO76 (MTK_PIN_NO(76) | 0) +#define PINMUX_GPIO76__FUNC_O_SPIM1_CLK (MTK_PIN_NO(76) | 1) +#define PINMUX_GPIO76__FUNC_O_SCP_SPI1_A_CK (MTK_PIN_NO(76) | 2) +#define PINMUX_GPIO76__FUNC_B0_TDMIN_BCK (MTK_PIN_NO(76) | 3) +#define PINMUX_GPIO76__FUNC_B1_SCP_SDA0 (MTK_PIN_NO(76) | 4) +#define PINMUX_GPIO76__FUNC_O_CMVREF7 (MTK_PIN_NO(76) | 5) +#define PINMUX_GPIO76__FUNC_O_GDU_SUM_TROOP2_1 (MTK_PIN_NO(76) | 6) +#define PINMUX_GPIO76__FUNC_B0_DBG_MON_A30 (MTK_PIN_NO(76) | 7) + +#define PINMUX_GPIO77__FUNC_B_GPIO77 (MTK_PIN_NO(77) | 0) +#define PINMUX_GPIO77__FUNC_B0_SPIM1_MOSI (MTK_PIN_NO(77) | 1) +#define PINMUX_GPIO77__FUNC_O_SCP_SPI1_A_MO (MTK_PIN_NO(77) | 2) +#define PINMUX_GPIO77__FUNC_B0_TDMIN_LRCK (MTK_PIN_NO(77) | 3) +#define PINMUX_GPIO77__FUNC_B1_SCP_SCL1 (MTK_PIN_NO(77) | 4) +#define PINMUX_GPIO77__FUNC_O_GDU_SUM_TROOP2_2 (MTK_PIN_NO(77) | 6) +#define PINMUX_GPIO77__FUNC_B0_DBG_MON_A31 (MTK_PIN_NO(77) | 7) + +#define PINMUX_GPIO78__FUNC_B_GPIO78 (MTK_PIN_NO(78) | 0) +#define PINMUX_GPIO78__FUNC_B0_SPIM1_MISO (MTK_PIN_NO(78) | 1) +#define PINMUX_GPIO78__FUNC_I0_SCP_SPI1_A_MI (MTK_PIN_NO(78) | 2) +#define PINMUX_GPIO78__FUNC_I0_TDMIN_DI (MTK_PIN_NO(78) | 3) +#define PINMUX_GPIO78__FUNC_B1_SCP_SDA1 (MTK_PIN_NO(78) | 4) +#define PINMUX_GPIO78__FUNC_B0_DBG_MON_A32 (MTK_PIN_NO(78) | 7) + +#define PINMUX_GPIO79__FUNC_B_GPIO79 (MTK_PIN_NO(79) | 0) +#define PINMUX_GPIO79__FUNC_O_SPIM2_CSB (MTK_PIN_NO(79) | 1) +#define PINMUX_GPIO79__FUNC_O_SCP_SPI2_CS (MTK_PIN_NO(79) | 2) +#define PINMUX_GPIO79__FUNC_O_I2SO1_MCK (MTK_PIN_NO(79) | 3) +#define PINMUX_GPIO79__FUNC_O_UTXD2 (MTK_PIN_NO(79) | 4) +#define PINMUX_GPIO79__FUNC_O_TP_UTXD2_AO (MTK_PIN_NO(79) | 5) +#define PINMUX_GPIO79__FUNC_B0_PCM_SYNC (MTK_PIN_NO(79) | 6) +#define PINMUX_GPIO79__FUNC_B0_DBG_MON_B0 (MTK_PIN_NO(79) | 7) + +#define PINMUX_GPIO80__FUNC_B_GPIO80 (MTK_PIN_NO(80) | 0) +#define PINMUX_GPIO80__FUNC_O_SPIM2_CLK (MTK_PIN_NO(80) | 1) +#define PINMUX_GPIO80__FUNC_O_SCP_SPI2_CK (MTK_PIN_NO(80) | 2) +#define PINMUX_GPIO80__FUNC_O_I2SO1_BCK (MTK_PIN_NO(80) | 3) +#define PINMUX_GPIO80__FUNC_I1_URXD2 (MTK_PIN_NO(80) | 4) +#define PINMUX_GPIO80__FUNC_I1_TP_URXD2_AO (MTK_PIN_NO(80) | 5) +#define PINMUX_GPIO80__FUNC_B0_PCM_CLK (MTK_PIN_NO(80) | 6) +#define PINMUX_GPIO80__FUNC_B0_DBG_MON_B1 (MTK_PIN_NO(80) | 7) + +#define PINMUX_GPIO81__FUNC_B_GPIO81 (MTK_PIN_NO(81) | 0) +#define PINMUX_GPIO81__FUNC_B0_SPIM2_MOSI (MTK_PIN_NO(81) | 1) +#define PINMUX_GPIO81__FUNC_O_SCP_SPI2_MO (MTK_PIN_NO(81) | 2) +#define PINMUX_GPIO81__FUNC_O_I2SO1_WS (MTK_PIN_NO(81) | 3) +#define PINMUX_GPIO81__FUNC_O_URTS2 (MTK_PIN_NO(81) | 4) +#define PINMUX_GPIO81__FUNC_O_TP_URTS2_AO (MTK_PIN_NO(81) | 5) +#define PINMUX_GPIO81__FUNC_O_PCM_DO (MTK_PIN_NO(81) | 6) +#define PINMUX_GPIO81__FUNC_B0_DBG_MON_B2 (MTK_PIN_NO(81) | 7) + +#define PINMUX_GPIO82__FUNC_B_GPIO82 (MTK_PIN_NO(82) | 0) +#define PINMUX_GPIO82__FUNC_B0_SPIM2_MISO (MTK_PIN_NO(82) | 1) +#define PINMUX_GPIO82__FUNC_I0_SCP_SPI2_MI (MTK_PIN_NO(82) | 2) +#define PINMUX_GPIO82__FUNC_O_I2SO1_D0 (MTK_PIN_NO(82) | 3) +#define PINMUX_GPIO82__FUNC_I1_UCTS2 (MTK_PIN_NO(82) | 4) +#define PINMUX_GPIO82__FUNC_I1_TP_UCTS2_AO (MTK_PIN_NO(82) | 5) +#define PINMUX_GPIO82__FUNC_I0_PCM_DI (MTK_PIN_NO(82) | 6) +#define PINMUX_GPIO82__FUNC_B0_DBG_MON_B3 (MTK_PIN_NO(82) | 7) + +#define PINMUX_GPIO83__FUNC_B_GPIO83 (MTK_PIN_NO(83) | 0) +#define PINMUX_GPIO83__FUNC_I1_IDDIG (MTK_PIN_NO(83) | 1) + +#define PINMUX_GPIO84__FUNC_B_GPIO84 (MTK_PIN_NO(84) | 0) +#define PINMUX_GPIO84__FUNC_O_USB_DRVVBUS (MTK_PIN_NO(84) | 1) + +#define PINMUX_GPIO85__FUNC_B_GPIO85 (MTK_PIN_NO(85) | 0) +#define PINMUX_GPIO85__FUNC_I0_VBUSVALID (MTK_PIN_NO(85) | 1) + +#define PINMUX_GPIO86__FUNC_B_GPIO86 (MTK_PIN_NO(86) | 0) +#define PINMUX_GPIO86__FUNC_I1_IDDIG_1P (MTK_PIN_NO(86) | 1) +#define PINMUX_GPIO86__FUNC_O_UTXD1 (MTK_PIN_NO(86) | 2) +#define PINMUX_GPIO86__FUNC_O_URTS2 (MTK_PIN_NO(86) | 3) +#define PINMUX_GPIO86__FUNC_O_PWM_2 (MTK_PIN_NO(86) | 4) +#define PINMUX_GPIO86__FUNC_B0_TP_GPIO4_AO (MTK_PIN_NO(86) | 5) +#define PINMUX_GPIO86__FUNC_O_AUXIF_ST0 (MTK_PIN_NO(86) | 6) +#define PINMUX_GPIO86__FUNC_B0_DBG_MON_B4 (MTK_PIN_NO(86) | 7) + +#define PINMUX_GPIO87__FUNC_B_GPIO87 (MTK_PIN_NO(87) | 0) +#define PINMUX_GPIO87__FUNC_O_USB_DRVVBUS_1P (MTK_PIN_NO(87) | 1) +#define PINMUX_GPIO87__FUNC_I1_URXD1 (MTK_PIN_NO(87) | 2) +#define PINMUX_GPIO87__FUNC_I1_UCTS2 (MTK_PIN_NO(87) | 3) +#define PINMUX_GPIO87__FUNC_O_PWM_3 (MTK_PIN_NO(87) | 4) +#define PINMUX_GPIO87__FUNC_B0_TP_GPIO5_AO (MTK_PIN_NO(87) | 5) +#define PINMUX_GPIO87__FUNC_O_AUXIF_CLK0 (MTK_PIN_NO(87) | 6) +#define PINMUX_GPIO87__FUNC_B0_DBG_MON_B5 (MTK_PIN_NO(87) | 7) + +#define PINMUX_GPIO88__FUNC_B_GPIO88 (MTK_PIN_NO(88) | 0) +#define PINMUX_GPIO88__FUNC_I0_VBUSVALID_1P (MTK_PIN_NO(88) | 1) +#define PINMUX_GPIO88__FUNC_O_UTXD2 (MTK_PIN_NO(88) | 2) +#define PINMUX_GPIO88__FUNC_O_URTS1 (MTK_PIN_NO(88) | 3) +#define PINMUX_GPIO88__FUNC_O_CLKM2 (MTK_PIN_NO(88) | 4) +#define PINMUX_GPIO88__FUNC_B0_TP_GPIO6_AO (MTK_PIN_NO(88) | 5) +#define PINMUX_GPIO88__FUNC_O_AUXIF_ST1 (MTK_PIN_NO(88) | 6) +#define PINMUX_GPIO88__FUNC_B0_DBG_MON_B6 (MTK_PIN_NO(88) | 7) + +#define PINMUX_GPIO89__FUNC_B_GPIO89 (MTK_PIN_NO(89) | 0) +#define PINMUX_GPIO89__FUNC_I1_IDDIG_2P (MTK_PIN_NO(89) | 1) +#define PINMUX_GPIO89__FUNC_I1_URXD2 (MTK_PIN_NO(89) | 2) +#define PINMUX_GPIO89__FUNC_I1_UCTS1 (MTK_PIN_NO(89) | 3) +#define PINMUX_GPIO89__FUNC_O_CLKM3 (MTK_PIN_NO(89) | 4) +#define PINMUX_GPIO89__FUNC_B0_TP_GPIO7_AO (MTK_PIN_NO(89) | 5) +#define PINMUX_GPIO89__FUNC_O_AUXIF_CLK1 (MTK_PIN_NO(89) | 6) +#define PINMUX_GPIO89__FUNC_B0_DBG_MON_B7 (MTK_PIN_NO(89) | 7) + +#define PINMUX_GPIO90__FUNC_B_GPIO90 (MTK_PIN_NO(90) | 0) +#define PINMUX_GPIO90__FUNC_O_USB_DRVVBUS_2P (MTK_PIN_NO(90) | 1) +#define PINMUX_GPIO90__FUNC_O_UTXD3 (MTK_PIN_NO(90) | 2) +#define PINMUX_GPIO90__FUNC_O_ADSP_UTXD0 (MTK_PIN_NO(90) | 3) +#define PINMUX_GPIO90__FUNC_O_SSPM_UTXD_AO (MTK_PIN_NO(90) | 4) +#define PINMUX_GPIO90__FUNC_O_MD32_0_TXD (MTK_PIN_NO(90) | 5) +#define PINMUX_GPIO90__FUNC_O_MD32_1_TXD (MTK_PIN_NO(90) | 6) +#define PINMUX_GPIO90__FUNC_B0_DBG_MON_B8 (MTK_PIN_NO(90) | 7) + +#define PINMUX_GPIO91__FUNC_B_GPIO91 (MTK_PIN_NO(91) | 0) +#define PINMUX_GPIO91__FUNC_I0_VBUSVALID_2P (MTK_PIN_NO(91) | 1) +#define PINMUX_GPIO91__FUNC_I1_URXD3 (MTK_PIN_NO(91) | 2) +#define PINMUX_GPIO91__FUNC_I1_ADSP_URXD0 (MTK_PIN_NO(91) | 3) +#define PINMUX_GPIO91__FUNC_I1_SSPM_URXD_AO (MTK_PIN_NO(91) | 4) +#define PINMUX_GPIO91__FUNC_I1_MD32_0_RXD (MTK_PIN_NO(91) | 5) +#define PINMUX_GPIO91__FUNC_I1_MD32_1_RXD (MTK_PIN_NO(91) | 6) +#define PINMUX_GPIO91__FUNC_B0_DBG_MON_B9 (MTK_PIN_NO(91) | 7) + +#define PINMUX_GPIO92__FUNC_B_GPIO92 (MTK_PIN_NO(92) | 0) +#define PINMUX_GPIO92__FUNC_O_PWRAP_SPI0_CSN (MTK_PIN_NO(92) | 1) + +#define PINMUX_GPIO93__FUNC_B_GPIO93 (MTK_PIN_NO(93) | 0) +#define PINMUX_GPIO93__FUNC_O_PWRAP_SPI0_CK (MTK_PIN_NO(93) | 1) + +#define PINMUX_GPIO94__FUNC_B_GPIO94 (MTK_PIN_NO(94) | 0) +#define PINMUX_GPIO94__FUNC_B0_PWRAP_SPI0_MO (MTK_PIN_NO(94) | 1) +#define PINMUX_GPIO94__FUNC_B0_PWRAP_SPI0_MI (MTK_PIN_NO(94) | 2) + +#define PINMUX_GPIO95__FUNC_B_GPIO95 (MTK_PIN_NO(95) | 0) +#define PINMUX_GPIO95__FUNC_B0_PWRAP_SPI0_MI (MTK_PIN_NO(95) | 1) +#define PINMUX_GPIO95__FUNC_B0_PWRAP_SPI0_MO (MTK_PIN_NO(95) | 2) + +#define PINMUX_GPIO96__FUNC_B_GPIO96 (MTK_PIN_NO(96) | 0) +#define PINMUX_GPIO96__FUNC_O_SRCLKENA0 (MTK_PIN_NO(96) | 1) + +#define PINMUX_GPIO97__FUNC_B_GPIO97 (MTK_PIN_NO(97) | 0) +#define PINMUX_GPIO97__FUNC_O_SRCLKENA1 (MTK_PIN_NO(97) | 1) + +#define PINMUX_GPIO98__FUNC_B_GPIO98 (MTK_PIN_NO(98) | 0) +#define PINMUX_GPIO98__FUNC_O_SCP_VREQ_VAO (MTK_PIN_NO(98) | 1) +#define PINMUX_GPIO98__FUNC_I0_DVFSRC_EXT_REQ (MTK_PIN_NO(98) | 2) + +#define PINMUX_GPIO99__FUNC_B_GPIO99 (MTK_PIN_NO(99) | 0) +#define PINMUX_GPIO99__FUNC_I0_RTC32K_CK (MTK_PIN_NO(99) | 1) + +#define PINMUX_GPIO100__FUNC_B_GPIO100 (MTK_PIN_NO(100) | 0) +#define PINMUX_GPIO100__FUNC_O_WATCHDOG (MTK_PIN_NO(100) | 1) + +#define PINMUX_GPIO101__FUNC_B_GPIO101 (MTK_PIN_NO(101) | 0) +#define PINMUX_GPIO101__FUNC_O_AUD_CLK_MOSI (MTK_PIN_NO(101) | 1) +#define PINMUX_GPIO101__FUNC_O_I2SO1_MCK (MTK_PIN_NO(101) | 2) +#define PINMUX_GPIO101__FUNC_B0_I2SIN_BCK (MTK_PIN_NO(101) | 3) + +#define PINMUX_GPIO102__FUNC_B_GPIO102 (MTK_PIN_NO(102) | 0) +#define PINMUX_GPIO102__FUNC_O_AUD_SYNC_MOSI (MTK_PIN_NO(102) | 1) +#define PINMUX_GPIO102__FUNC_O_I2SO1_BCK (MTK_PIN_NO(102) | 2) +#define PINMUX_GPIO102__FUNC_B0_I2SIN_WS (MTK_PIN_NO(102) | 3) + +#define PINMUX_GPIO103__FUNC_B_GPIO103 (MTK_PIN_NO(103) | 0) +#define PINMUX_GPIO103__FUNC_O_AUD_DAT_MOSI0 (MTK_PIN_NO(103) | 1) +#define PINMUX_GPIO103__FUNC_O_I2SO1_WS (MTK_PIN_NO(103) | 2) +#define PINMUX_GPIO103__FUNC_I0_I2SIN_D0 (MTK_PIN_NO(103) | 3) + +#define PINMUX_GPIO104__FUNC_B_GPIO104 (MTK_PIN_NO(104) | 0) +#define PINMUX_GPIO104__FUNC_O_AUD_DAT_MOSI1 (MTK_PIN_NO(104) | 1) +#define PINMUX_GPIO104__FUNC_O_I2SO1_D0 (MTK_PIN_NO(104) | 2) +#define PINMUX_GPIO104__FUNC_I0_I2SIN_D1 (MTK_PIN_NO(104) | 3) + +#define PINMUX_GPIO105__FUNC_B_GPIO105 (MTK_PIN_NO(105) | 0) +#define PINMUX_GPIO105__FUNC_I0_AUD_DAT_MISO0 (MTK_PIN_NO(105) | 1) +#define PINMUX_GPIO105__FUNC_I0_VOW_DAT_MISO (MTK_PIN_NO(105) | 2) +#define PINMUX_GPIO105__FUNC_I0_I2SIN_D2 (MTK_PIN_NO(105) | 3) + +#define PINMUX_GPIO106__FUNC_B_GPIO106 (MTK_PIN_NO(106) | 0) +#define PINMUX_GPIO106__FUNC_I0_AUD_DAT_MISO1 (MTK_PIN_NO(106) | 1) +#define PINMUX_GPIO106__FUNC_I0_VOW_CLK_MISO (MTK_PIN_NO(106) | 2) +#define PINMUX_GPIO106__FUNC_I0_I2SIN_D3 (MTK_PIN_NO(106) | 3) + +#define PINMUX_GPIO107__FUNC_B_GPIO107 (MTK_PIN_NO(107) | 0) +#define PINMUX_GPIO107__FUNC_B0_I2SIN_MCK (MTK_PIN_NO(107) | 1) +#define PINMUX_GPIO107__FUNC_I0_SPLIN_MCK (MTK_PIN_NO(107) | 2) +#define PINMUX_GPIO107__FUNC_I0_SPDIF_IN0 (MTK_PIN_NO(107) | 3) +#define PINMUX_GPIO107__FUNC_O_CMVREF4 (MTK_PIN_NO(107) | 4) +#define PINMUX_GPIO107__FUNC_O_AUXIF_ST0 (MTK_PIN_NO(107) | 5) +#define PINMUX_GPIO107__FUNC_O_PGD_LV_LSC_PWR0 (MTK_PIN_NO(107) | 6) + +#define PINMUX_GPIO108__FUNC_B_GPIO108 (MTK_PIN_NO(108) | 0) +#define PINMUX_GPIO108__FUNC_B0_I2SIN_BCK (MTK_PIN_NO(108) | 1) +#define PINMUX_GPIO108__FUNC_I0_SPLIN_LRCK (MTK_PIN_NO(108) | 2) +#define PINMUX_GPIO108__FUNC_O_DMIC4_CLK (MTK_PIN_NO(108) | 3) +#define PINMUX_GPIO108__FUNC_O_CMVREF5 (MTK_PIN_NO(108) | 4) +#define PINMUX_GPIO108__FUNC_O_AUXIF_CLK0 (MTK_PIN_NO(108) | 5) +#define PINMUX_GPIO108__FUNC_O_PGD_LV_LSC_PWR1 (MTK_PIN_NO(108) | 6) +#define PINMUX_GPIO108__FUNC_B0_DBG_MON_B10 (MTK_PIN_NO(108) | 7) + +#define PINMUX_GPIO109__FUNC_B_GPIO109 (MTK_PIN_NO(109) | 0) +#define PINMUX_GPIO109__FUNC_B0_I2SIN_WS (MTK_PIN_NO(109) | 1) +#define PINMUX_GPIO109__FUNC_I0_SPLIN_BCK (MTK_PIN_NO(109) | 2) +#define PINMUX_GPIO109__FUNC_I0_DMIC4_DAT (MTK_PIN_NO(109) | 3) +#define PINMUX_GPIO109__FUNC_O_CMVREF6 (MTK_PIN_NO(109) | 4) +#define PINMUX_GPIO109__FUNC_O_AUXIF_ST1 (MTK_PIN_NO(109) | 5) +#define PINMUX_GPIO109__FUNC_O_PGD_LV_LSC_PWR2 (MTK_PIN_NO(109) | 6) +#define PINMUX_GPIO109__FUNC_B0_DBG_MON_B11 (MTK_PIN_NO(109) | 7) + +#define PINMUX_GPIO110__FUNC_B_GPIO110 (MTK_PIN_NO(110) | 0) +#define PINMUX_GPIO110__FUNC_I0_I2SIN_D0 (MTK_PIN_NO(110) | 1) +#define PINMUX_GPIO110__FUNC_I0_SPLIN_D0 (MTK_PIN_NO(110) | 2) +#define PINMUX_GPIO110__FUNC_I0_DMIC4_DAT_R (MTK_PIN_NO(110) | 3) +#define PINMUX_GPIO110__FUNC_O_CMVREF7 (MTK_PIN_NO(110) | 4) +#define PINMUX_GPIO110__FUNC_O_AUXIF_CLK1 (MTK_PIN_NO(110) | 5) +#define PINMUX_GPIO110__FUNC_O_PGD_LV_LSC_PWR3 (MTK_PIN_NO(110) | 6) +#define PINMUX_GPIO110__FUNC_B0_DBG_MON_B12 (MTK_PIN_NO(110) | 7) + +#define PINMUX_GPIO111__FUNC_B_GPIO111 (MTK_PIN_NO(111) | 0) +#define PINMUX_GPIO111__FUNC_I0_I2SIN_D1 (MTK_PIN_NO(111) | 1) +#define PINMUX_GPIO111__FUNC_I0_SPLIN_D1 (MTK_PIN_NO(111) | 2) +#define PINMUX_GPIO111__FUNC_O_DMIC3_CLK (MTK_PIN_NO(111) | 3) +#define PINMUX_GPIO111__FUNC_O_SPDIF_OUT (MTK_PIN_NO(111) | 4) +#define PINMUX_GPIO111__FUNC_O_PGD_LV_LSC_PWR4 (MTK_PIN_NO(111) | 6) +#define PINMUX_GPIO111__FUNC_B0_DBG_MON_B13 (MTK_PIN_NO(111) | 7) + +#define PINMUX_GPIO112__FUNC_B_GPIO112 (MTK_PIN_NO(112) | 0) +#define PINMUX_GPIO112__FUNC_I0_I2SIN_D2 (MTK_PIN_NO(112) | 1) +#define PINMUX_GPIO112__FUNC_I0_SPLIN_D2 (MTK_PIN_NO(112) | 2) +#define PINMUX_GPIO112__FUNC_I0_DMIC3_DAT (MTK_PIN_NO(112) | 3) +#define PINMUX_GPIO112__FUNC_B0_TDMIN_MCK (MTK_PIN_NO(112) | 4) +#define PINMUX_GPIO112__FUNC_O_I2SO1_WS (MTK_PIN_NO(112) | 5) +#define PINMUX_GPIO112__FUNC_O_PGD_LV_LSC_PWR5 (MTK_PIN_NO(112) | 6) +#define PINMUX_GPIO112__FUNC_B0_DBG_MON_B14 (MTK_PIN_NO(112) | 7) + +#define PINMUX_GPIO113__FUNC_B_GPIO113 (MTK_PIN_NO(113) | 0) +#define PINMUX_GPIO113__FUNC_I0_I2SIN_D3 (MTK_PIN_NO(113) | 1) +#define PINMUX_GPIO113__FUNC_I0_SPLIN_D3 (MTK_PIN_NO(113) | 2) +#define PINMUX_GPIO113__FUNC_I0_DMIC3_DAT_R (MTK_PIN_NO(113) | 3) +#define PINMUX_GPIO113__FUNC_B0_TDMIN_BCK (MTK_PIN_NO(113) | 4) +#define PINMUX_GPIO113__FUNC_O_I2SO1_D0 (MTK_PIN_NO(113) | 5) +#define PINMUX_GPIO113__FUNC_B0_DBG_MON_B15 (MTK_PIN_NO(113) | 7) + +#define PINMUX_GPIO114__FUNC_B_GPIO114 (MTK_PIN_NO(114) | 0) +#define PINMUX_GPIO114__FUNC_O_I2SO2_MCK (MTK_PIN_NO(114) | 1) +#define PINMUX_GPIO114__FUNC_B0_I2SIN_MCK (MTK_PIN_NO(114) | 2) +#define PINMUX_GPIO114__FUNC_I1_MCUPM_JTAG_TMS (MTK_PIN_NO(114) | 3) +#define PINMUX_GPIO114__FUNC_B1_APU_JTAG_TMS (MTK_PIN_NO(114) | 4) +#define PINMUX_GPIO114__FUNC_I1_SCP_JTAG1_TMS (MTK_PIN_NO(114) | 5) +#define PINMUX_GPIO114__FUNC_I1_SPM_JTAG_TMS (MTK_PIN_NO(114) | 6) +#define PINMUX_GPIO114__FUNC_B0_DBG_MON_B16 (MTK_PIN_NO(114) | 7) + +#define PINMUX_GPIO115__FUNC_B_GPIO115 (MTK_PIN_NO(115) | 0) +#define PINMUX_GPIO115__FUNC_B0_I2SO2_BCK (MTK_PIN_NO(115) | 1) +#define PINMUX_GPIO115__FUNC_B0_I2SIN_BCK (MTK_PIN_NO(115) | 2) +#define PINMUX_GPIO115__FUNC_I1_MCUPM_JTAG_TCK (MTK_PIN_NO(115) | 3) +#define PINMUX_GPIO115__FUNC_I0_APU_JTAG_TCK (MTK_PIN_NO(115) | 4) +#define PINMUX_GPIO115__FUNC_I1_SCP_JTAG1_TCK (MTK_PIN_NO(115) | 5) +#define PINMUX_GPIO115__FUNC_I1_SPM_JTAG_TCK (MTK_PIN_NO(115) | 6) +#define PINMUX_GPIO115__FUNC_B0_DBG_MON_B17 (MTK_PIN_NO(115) | 7) + +#define PINMUX_GPIO116__FUNC_B_GPIO116 (MTK_PIN_NO(116) | 0) +#define PINMUX_GPIO116__FUNC_B0_I2SO2_WS (MTK_PIN_NO(116) | 1) +#define PINMUX_GPIO116__FUNC_B0_I2SIN_WS (MTK_PIN_NO(116) | 2) +#define PINMUX_GPIO116__FUNC_I1_MCUPM_JTAG_TDI (MTK_PIN_NO(116) | 3) +#define PINMUX_GPIO116__FUNC_I1_APU_JTAG_TDI (MTK_PIN_NO(116) | 4) +#define PINMUX_GPIO116__FUNC_I1_SCP_JTAG1_TDI (MTK_PIN_NO(116) | 5) +#define PINMUX_GPIO116__FUNC_I1_SPM_JTAG_TDI (MTK_PIN_NO(116) | 6) +#define PINMUX_GPIO116__FUNC_B0_DBG_MON_B18 (MTK_PIN_NO(116) | 7) + +#define PINMUX_GPIO117__FUNC_B_GPIO117 (MTK_PIN_NO(117) | 0) +#define PINMUX_GPIO117__FUNC_O_I2SO2_D0 (MTK_PIN_NO(117) | 1) +#define PINMUX_GPIO117__FUNC_I0_I2SIN_D0 (MTK_PIN_NO(117) | 2) +#define PINMUX_GPIO117__FUNC_O_MCUPM_JTAG_TDO (MTK_PIN_NO(117) | 3) +#define PINMUX_GPIO117__FUNC_O_APU_JTAG_TDO (MTK_PIN_NO(117) | 4) +#define PINMUX_GPIO117__FUNC_O_SCP_JTAG1_TDO (MTK_PIN_NO(117) | 5) +#define PINMUX_GPIO117__FUNC_O_SPM_JTAG_TDO (MTK_PIN_NO(117) | 6) +#define PINMUX_GPIO117__FUNC_B0_DBG_MON_B19 (MTK_PIN_NO(117) | 7) + +#define PINMUX_GPIO118__FUNC_B_GPIO118 (MTK_PIN_NO(118) | 0) +#define PINMUX_GPIO118__FUNC_O_I2SO2_D1 (MTK_PIN_NO(118) | 1) +#define PINMUX_GPIO118__FUNC_I0_I2SIN_D1 (MTK_PIN_NO(118) | 2) +#define PINMUX_GPIO118__FUNC_I0_MCUPM_JTAG_TRSTN (MTK_PIN_NO(118) | 3) +#define PINMUX_GPIO118__FUNC_I0_APU_JTAG_TRST (MTK_PIN_NO(118) | 4) +#define PINMUX_GPIO118__FUNC_I0_SCP_JTAG1_TRSTN (MTK_PIN_NO(118) | 5) +#define PINMUX_GPIO118__FUNC_I0_SPM_JTAG_TRSTN (MTK_PIN_NO(118) | 6) +#define PINMUX_GPIO118__FUNC_B0_DBG_MON_B20 (MTK_PIN_NO(118) | 7) + +#define PINMUX_GPIO119__FUNC_B_GPIO119 (MTK_PIN_NO(119) | 0) +#define PINMUX_GPIO119__FUNC_O_I2SO2_D2 (MTK_PIN_NO(119) | 1) +#define PINMUX_GPIO119__FUNC_I0_I2SIN_D2 (MTK_PIN_NO(119) | 2) +#define PINMUX_GPIO119__FUNC_O_UTXD3 (MTK_PIN_NO(119) | 3) +#define PINMUX_GPIO119__FUNC_B0_TDMIN_LRCK (MTK_PIN_NO(119) | 4) +#define PINMUX_GPIO119__FUNC_O_I2SO1_MCK (MTK_PIN_NO(119) | 5) +#define PINMUX_GPIO119__FUNC_O_SSPM_UTXD_AO (MTK_PIN_NO(119) | 6) +#define PINMUX_GPIO119__FUNC_B0_DBG_MON_B21 (MTK_PIN_NO(119) | 7) + +#define PINMUX_GPIO120__FUNC_B_GPIO120 (MTK_PIN_NO(120) | 0) +#define PINMUX_GPIO120__FUNC_O_I2SO2_D3 (MTK_PIN_NO(120) | 1) +#define PINMUX_GPIO120__FUNC_I0_I2SIN_D3 (MTK_PIN_NO(120) | 2) +#define PINMUX_GPIO120__FUNC_I1_URXD3 (MTK_PIN_NO(120) | 3) +#define PINMUX_GPIO120__FUNC_I0_TDMIN_DI (MTK_PIN_NO(120) | 4) +#define PINMUX_GPIO120__FUNC_O_I2SO1_BCK (MTK_PIN_NO(120) | 5) +#define PINMUX_GPIO120__FUNC_I1_SSPM_URXD_AO (MTK_PIN_NO(120) | 6) +#define PINMUX_GPIO120__FUNC_B0_DBG_MON_B22 (MTK_PIN_NO(120) | 7) + +#define PINMUX_GPIO121__FUNC_B_GPIO121 (MTK_PIN_NO(121) | 0) +#define PINMUX_GPIO121__FUNC_B0_PCM_CLK (MTK_PIN_NO(121) | 1) +#define PINMUX_GPIO121__FUNC_O_SPIM4_CSB (MTK_PIN_NO(121) | 2) +#define PINMUX_GPIO121__FUNC_O_SCP_SPI1_B_CS (MTK_PIN_NO(121) | 3) +#define PINMUX_GPIO121__FUNC_O_TP_UTXD2_AO (MTK_PIN_NO(121) | 4) +#define PINMUX_GPIO121__FUNC_O_AUXIF_ST0 (MTK_PIN_NO(121) | 5) +#define PINMUX_GPIO121__FUNC_O_PGD_DA_EFUSE_RDY (MTK_PIN_NO(121) | 6) +#define PINMUX_GPIO121__FUNC_B0_DBG_MON_B23 (MTK_PIN_NO(121) | 7) + +#define PINMUX_GPIO122__FUNC_B_GPIO122 (MTK_PIN_NO(122) | 0) +#define PINMUX_GPIO122__FUNC_B0_PCM_SYNC (MTK_PIN_NO(122) | 1) +#define PINMUX_GPIO122__FUNC_O_SPIM4_CLK (MTK_PIN_NO(122) | 2) +#define PINMUX_GPIO122__FUNC_O_SCP_SPI1_B_CK (MTK_PIN_NO(122) | 3) +#define PINMUX_GPIO122__FUNC_I1_TP_URXD2_AO (MTK_PIN_NO(122) | 4) +#define PINMUX_GPIO122__FUNC_O_AUXIF_CLK0 (MTK_PIN_NO(122) | 5) +#define PINMUX_GPIO122__FUNC_O_PGD_DA_EFUSE_RDY_PRE (MTK_PIN_NO(122) | 6) +#define PINMUX_GPIO122__FUNC_B0_DBG_MON_B24 (MTK_PIN_NO(122) | 7) + +#define PINMUX_GPIO123__FUNC_B_GPIO123 (MTK_PIN_NO(123) | 0) +#define PINMUX_GPIO123__FUNC_O_PCM_DO (MTK_PIN_NO(123) | 1) +#define PINMUX_GPIO123__FUNC_B0_SPIM4_MOSI (MTK_PIN_NO(123) | 2) +#define PINMUX_GPIO123__FUNC_O_SCP_SPI1_B_MO (MTK_PIN_NO(123) | 3) +#define PINMUX_GPIO123__FUNC_O_TP_URTS2_AO (MTK_PIN_NO(123) | 4) +#define PINMUX_GPIO123__FUNC_O_AUXIF_ST1 (MTK_PIN_NO(123) | 5) +#define PINMUX_GPIO123__FUNC_O_PGD_DA_PWRGD_RESET (MTK_PIN_NO(123) | 6) +#define PINMUX_GPIO123__FUNC_B0_DBG_MON_B25 (MTK_PIN_NO(123) | 7) + +#define PINMUX_GPIO124__FUNC_B_GPIO124 (MTK_PIN_NO(124) | 0) +#define PINMUX_GPIO124__FUNC_I0_PCM_DI (MTK_PIN_NO(124) | 1) +#define PINMUX_GPIO124__FUNC_B0_SPIM4_MISO (MTK_PIN_NO(124) | 2) +#define PINMUX_GPIO124__FUNC_I0_SCP_SPI1_B_MI (MTK_PIN_NO(124) | 3) +#define PINMUX_GPIO124__FUNC_I1_TP_UCTS2_AO (MTK_PIN_NO(124) | 4) +#define PINMUX_GPIO124__FUNC_O_AUXIF_CLK1 (MTK_PIN_NO(124) | 5) +#define PINMUX_GPIO124__FUNC_O_PGD_DA_PWRGD_ENB (MTK_PIN_NO(124) | 6) +#define PINMUX_GPIO124__FUNC_B0_DBG_MON_B26 (MTK_PIN_NO(124) | 7) + +#define PINMUX_GPIO125__FUNC_B_GPIO125 (MTK_PIN_NO(125) | 0) +#define PINMUX_GPIO125__FUNC_O_DMIC1_CLK (MTK_PIN_NO(125) | 1) +#define PINMUX_GPIO125__FUNC_O_SPINOR_CK (MTK_PIN_NO(125) | 2) +#define PINMUX_GPIO125__FUNC_B0_TDMIN_MCK (MTK_PIN_NO(125) | 3) +#define PINMUX_GPIO125__FUNC_O_LVTS_FOUT (MTK_PIN_NO(125) | 6) +#define PINMUX_GPIO125__FUNC_B0_DBG_MON_B27 (MTK_PIN_NO(125) | 7) + +#define PINMUX_GPIO126__FUNC_B_GPIO126 (MTK_PIN_NO(126) | 0) +#define PINMUX_GPIO126__FUNC_I0_DMIC1_DAT (MTK_PIN_NO(126) | 1) +#define PINMUX_GPIO126__FUNC_O_SPINOR_CS (MTK_PIN_NO(126) | 2) +#define PINMUX_GPIO126__FUNC_B0_TDMIN_BCK (MTK_PIN_NO(126) | 3) +#define PINMUX_GPIO126__FUNC_O_LVTS_SDO (MTK_PIN_NO(126) | 6) +#define PINMUX_GPIO126__FUNC_B0_DBG_MON_B28 (MTK_PIN_NO(126) | 7) + +#define PINMUX_GPIO127__FUNC_B_GPIO127 (MTK_PIN_NO(127) | 0) +#define PINMUX_GPIO127__FUNC_I0_DMIC1_DAT_R (MTK_PIN_NO(127) | 1) +#define PINMUX_GPIO127__FUNC_B0_SPINOR_IO0 (MTK_PIN_NO(127) | 2) +#define PINMUX_GPIO127__FUNC_B0_TDMIN_LRCK (MTK_PIN_NO(127) | 3) +#define PINMUX_GPIO127__FUNC_I0_LVTS_26M (MTK_PIN_NO(127) | 6) +#define PINMUX_GPIO127__FUNC_B0_DBG_MON_B29 (MTK_PIN_NO(127) | 7) + +#define PINMUX_GPIO128__FUNC_B_GPIO128 (MTK_PIN_NO(128) | 0) +#define PINMUX_GPIO128__FUNC_O_DMIC2_CLK (MTK_PIN_NO(128) | 1) +#define PINMUX_GPIO128__FUNC_B0_SPINOR_IO1 (MTK_PIN_NO(128) | 2) +#define PINMUX_GPIO128__FUNC_I0_TDMIN_DI (MTK_PIN_NO(128) | 3) +#define PINMUX_GPIO128__FUNC_I0_LVTS_SCF (MTK_PIN_NO(128) | 6) +#define PINMUX_GPIO128__FUNC_B0_DBG_MON_B30 (MTK_PIN_NO(128) | 7) + +#define PINMUX_GPIO129__FUNC_B_GPIO129 (MTK_PIN_NO(129) | 0) +#define PINMUX_GPIO129__FUNC_I0_DMIC2_DAT (MTK_PIN_NO(129) | 1) +#define PINMUX_GPIO129__FUNC_B0_SPINOR_IO2 (MTK_PIN_NO(129) | 2) +#define PINMUX_GPIO129__FUNC_I0_SPDIF_IN1 (MTK_PIN_NO(129) | 3) +#define PINMUX_GPIO129__FUNC_I0_LVTS_SCK (MTK_PIN_NO(129) | 6) +#define PINMUX_GPIO129__FUNC_B0_DBG_MON_B31 (MTK_PIN_NO(129) | 7) + +#define PINMUX_GPIO130__FUNC_B_GPIO130 (MTK_PIN_NO(130) | 0) +#define PINMUX_GPIO130__FUNC_I0_DMIC2_DAT_R (MTK_PIN_NO(130) | 1) +#define PINMUX_GPIO130__FUNC_B0_SPINOR_IO3 (MTK_PIN_NO(130) | 2) +#define PINMUX_GPIO130__FUNC_I0_SPDIF_IN2 (MTK_PIN_NO(130) | 3) +#define PINMUX_GPIO130__FUNC_I0_LVTS_SDI (MTK_PIN_NO(130) | 6) +#define PINMUX_GPIO130__FUNC_B0_DBG_MON_B32 (MTK_PIN_NO(130) | 7) + +#define PINMUX_GPIO131__FUNC_B_GPIO131 (MTK_PIN_NO(131) | 0) +#define PINMUX_GPIO131__FUNC_O_DPI_D0 (MTK_PIN_NO(131) | 1) +#define PINMUX_GPIO131__FUNC_O_GBE_TXD3 (MTK_PIN_NO(131) | 2) +#define PINMUX_GPIO131__FUNC_O_DMIC1_CLK (MTK_PIN_NO(131) | 3) +#define PINMUX_GPIO131__FUNC_O_I2SO2_MCK (MTK_PIN_NO(131) | 4) +#define PINMUX_GPIO131__FUNC_B0_TP_GPIO0_AO (MTK_PIN_NO(131) | 5) +#define PINMUX_GPIO131__FUNC_O_SPIM5_CSB (MTK_PIN_NO(131) | 6) +#define PINMUX_GPIO131__FUNC_O_PGD_LV_HSC_PWR0 (MTK_PIN_NO(131) | 7) + +#define PINMUX_GPIO132__FUNC_B_GPIO132 (MTK_PIN_NO(132) | 0) +#define PINMUX_GPIO132__FUNC_O_DPI_D1 (MTK_PIN_NO(132) | 1) +#define PINMUX_GPIO132__FUNC_O_GBE_TXD2 (MTK_PIN_NO(132) | 2) +#define PINMUX_GPIO132__FUNC_I0_DMIC1_DAT (MTK_PIN_NO(132) | 3) +#define PINMUX_GPIO132__FUNC_B0_I2SO2_BCK (MTK_PIN_NO(132) | 4) +#define PINMUX_GPIO132__FUNC_B0_TP_GPIO1_AO (MTK_PIN_NO(132) | 5) +#define PINMUX_GPIO132__FUNC_O_SPIM5_CLK (MTK_PIN_NO(132) | 6) +#define PINMUX_GPIO132__FUNC_O_PGD_LV_HSC_PWR1 (MTK_PIN_NO(132) | 7) + +#define PINMUX_GPIO133__FUNC_B_GPIO133 (MTK_PIN_NO(133) | 0) +#define PINMUX_GPIO133__FUNC_O_DPI_D2 (MTK_PIN_NO(133) | 1) +#define PINMUX_GPIO133__FUNC_O_GBE_TXD1 (MTK_PIN_NO(133) | 2) +#define PINMUX_GPIO133__FUNC_I0_DMIC1_DAT_R (MTK_PIN_NO(133) | 3) +#define PINMUX_GPIO133__FUNC_B0_I2SO2_WS (MTK_PIN_NO(133) | 4) +#define PINMUX_GPIO133__FUNC_B0_TP_GPIO2_AO (MTK_PIN_NO(133) | 5) +#define PINMUX_GPIO133__FUNC_B0_SPIM5_MOSI (MTK_PIN_NO(133) | 6) +#define PINMUX_GPIO133__FUNC_O_PGD_LV_HSC_PWR2 (MTK_PIN_NO(133) | 7) + +#define PINMUX_GPIO134__FUNC_B_GPIO134 (MTK_PIN_NO(134) | 0) +#define PINMUX_GPIO134__FUNC_O_DPI_D3 (MTK_PIN_NO(134) | 1) +#define PINMUX_GPIO134__FUNC_O_GBE_TXD0 (MTK_PIN_NO(134) | 2) +#define PINMUX_GPIO134__FUNC_O_DMIC2_CLK (MTK_PIN_NO(134) | 3) +#define PINMUX_GPIO134__FUNC_O_I2SO2_D0 (MTK_PIN_NO(134) | 4) +#define PINMUX_GPIO134__FUNC_B0_TP_GPIO3_AO (MTK_PIN_NO(134) | 5) +#define PINMUX_GPIO134__FUNC_B0_SPIM5_MISO (MTK_PIN_NO(134) | 6) +#define PINMUX_GPIO134__FUNC_O_PGD_LV_HSC_PWR3 (MTK_PIN_NO(134) | 7) + +#define PINMUX_GPIO135__FUNC_B_GPIO135 (MTK_PIN_NO(135) | 0) +#define PINMUX_GPIO135__FUNC_O_DPI_D4 (MTK_PIN_NO(135) | 1) +#define PINMUX_GPIO135__FUNC_I0_GBE_RXD3 (MTK_PIN_NO(135) | 2) +#define PINMUX_GPIO135__FUNC_I0_DMIC2_DAT (MTK_PIN_NO(135) | 3) +#define PINMUX_GPIO135__FUNC_O_I2SO2_D1 (MTK_PIN_NO(135) | 4) +#define PINMUX_GPIO135__FUNC_B0_TP_GPIO4_AO (MTK_PIN_NO(135) | 5) +#define PINMUX_GPIO135__FUNC_I1_WAKEN (MTK_PIN_NO(135) | 6) +#define PINMUX_GPIO135__FUNC_O_PGD_LV_HSC_PWR4 (MTK_PIN_NO(135) | 7) + +#define PINMUX_GPIO136__FUNC_B_GPIO136 (MTK_PIN_NO(136) | 0) +#define PINMUX_GPIO136__FUNC_O_DPI_D5 (MTK_PIN_NO(136) | 1) +#define PINMUX_GPIO136__FUNC_I0_GBE_RXD2 (MTK_PIN_NO(136) | 2) +#define PINMUX_GPIO136__FUNC_I0_DMIC2_DAT_R (MTK_PIN_NO(136) | 3) +#define PINMUX_GPIO136__FUNC_O_I2SO2_D2 (MTK_PIN_NO(136) | 4) +#define PINMUX_GPIO136__FUNC_B0_TP_GPIO5_AO (MTK_PIN_NO(136) | 5) +#define PINMUX_GPIO136__FUNC_O_PERSTN (MTK_PIN_NO(136) | 6) +#define PINMUX_GPIO136__FUNC_O_PGD_LV_HSC_PWR5 (MTK_PIN_NO(136) | 7) + +#define PINMUX_GPIO137__FUNC_B_GPIO137 (MTK_PIN_NO(137) | 0) +#define PINMUX_GPIO137__FUNC_O_DPI_D6 (MTK_PIN_NO(137) | 1) +#define PINMUX_GPIO137__FUNC_I0_GBE_RXD1 (MTK_PIN_NO(137) | 2) +#define PINMUX_GPIO137__FUNC_O_DMIC3_CLK (MTK_PIN_NO(137) | 3) +#define PINMUX_GPIO137__FUNC_O_I2SO2_D3 (MTK_PIN_NO(137) | 4) +#define PINMUX_GPIO137__FUNC_B0_TP_GPIO6_AO (MTK_PIN_NO(137) | 5) +#define PINMUX_GPIO137__FUNC_B1_CLKREQN (MTK_PIN_NO(137) | 6) +#define PINMUX_GPIO137__FUNC_O_PWM_0 (MTK_PIN_NO(137) | 7) + +#define PINMUX_GPIO138__FUNC_B_GPIO138 (MTK_PIN_NO(138) | 0) +#define PINMUX_GPIO138__FUNC_O_DPI_D7 (MTK_PIN_NO(138) | 1) +#define PINMUX_GPIO138__FUNC_I0_GBE_RXD0 (MTK_PIN_NO(138) | 2) +#define PINMUX_GPIO138__FUNC_I0_DMIC3_DAT (MTK_PIN_NO(138) | 3) +#define PINMUX_GPIO138__FUNC_O_CLKM2 (MTK_PIN_NO(138) | 4) +#define PINMUX_GPIO138__FUNC_B0_TP_GPIO7_AO (MTK_PIN_NO(138) | 5) +#define PINMUX_GPIO138__FUNC_B0_MD32_0_GPIO0 (MTK_PIN_NO(138) | 7) + +#define PINMUX_GPIO139__FUNC_B_GPIO139 (MTK_PIN_NO(139) | 0) +#define PINMUX_GPIO139__FUNC_O_DPI_D8 (MTK_PIN_NO(139) | 1) +#define PINMUX_GPIO139__FUNC_B0_GBE_TXC (MTK_PIN_NO(139) | 2) +#define PINMUX_GPIO139__FUNC_I0_DMIC3_DAT_R (MTK_PIN_NO(139) | 3) +#define PINMUX_GPIO139__FUNC_O_CLKM3 (MTK_PIN_NO(139) | 4) +#define PINMUX_GPIO139__FUNC_O_TP_UTXD2_AO (MTK_PIN_NO(139) | 5) +#define PINMUX_GPIO139__FUNC_O_UTXD2 (MTK_PIN_NO(139) | 6) +#define PINMUX_GPIO139__FUNC_B0_MD32_0_GPIO1 (MTK_PIN_NO(139) | 7) + +#define PINMUX_GPIO140__FUNC_B_GPIO140 (MTK_PIN_NO(140) | 0) +#define PINMUX_GPIO140__FUNC_O_DPI_D9 (MTK_PIN_NO(140) | 1) +#define PINMUX_GPIO140__FUNC_I0_GBE_RXC (MTK_PIN_NO(140) | 2) +#define PINMUX_GPIO140__FUNC_O_DMIC4_CLK (MTK_PIN_NO(140) | 3) +#define PINMUX_GPIO140__FUNC_O_PWM_2 (MTK_PIN_NO(140) | 4) +#define PINMUX_GPIO140__FUNC_I1_TP_URXD2_AO (MTK_PIN_NO(140) | 5) +#define PINMUX_GPIO140__FUNC_I1_URXD2 (MTK_PIN_NO(140) | 6) +#define PINMUX_GPIO140__FUNC_B0_MD32_0_GPIO2 (MTK_PIN_NO(140) | 7) + +#define PINMUX_GPIO141__FUNC_B_GPIO141 (MTK_PIN_NO(141) | 0) +#define PINMUX_GPIO141__FUNC_O_DPI_D10 (MTK_PIN_NO(141) | 1) +#define PINMUX_GPIO141__FUNC_I0_GBE_RXDV (MTK_PIN_NO(141) | 2) +#define PINMUX_GPIO141__FUNC_I0_DMIC4_DAT (MTK_PIN_NO(141) | 3) +#define PINMUX_GPIO141__FUNC_O_PWM_3 (MTK_PIN_NO(141) | 4) +#define PINMUX_GPIO141__FUNC_O_TP_URTS2_AO (MTK_PIN_NO(141) | 5) +#define PINMUX_GPIO141__FUNC_O_URTS2 (MTK_PIN_NO(141) | 6) +#define PINMUX_GPIO141__FUNC_B0_MD32_1_GPIO0 (MTK_PIN_NO(141) | 7) + +#define PINMUX_GPIO142__FUNC_B_GPIO142 (MTK_PIN_NO(142) | 0) +#define PINMUX_GPIO142__FUNC_O_DPI_D11 (MTK_PIN_NO(142) | 1) +#define PINMUX_GPIO142__FUNC_O_GBE_TXEN (MTK_PIN_NO(142) | 2) +#define PINMUX_GPIO142__FUNC_I0_DMIC4_DAT_R (MTK_PIN_NO(142) | 3) +#define PINMUX_GPIO142__FUNC_O_PWM_1 (MTK_PIN_NO(142) | 4) +#define PINMUX_GPIO142__FUNC_I1_TP_UCTS2_AO (MTK_PIN_NO(142) | 5) +#define PINMUX_GPIO142__FUNC_I1_UCTS2 (MTK_PIN_NO(142) | 6) +#define PINMUX_GPIO142__FUNC_B0_MD32_1_GPIO1 (MTK_PIN_NO(142) | 7) + +#define PINMUX_GPIO143__FUNC_B_GPIO143 (MTK_PIN_NO(143) | 0) +#define PINMUX_GPIO143__FUNC_O_DPI_D12 (MTK_PIN_NO(143) | 1) +#define PINMUX_GPIO143__FUNC_O_GBE_MDC (MTK_PIN_NO(143) | 2) +#define PINMUX_GPIO143__FUNC_B0_MD32_0_GPIO0 (MTK_PIN_NO(143) | 3) +#define PINMUX_GPIO143__FUNC_O_CLKM0 (MTK_PIN_NO(143) | 4) +#define PINMUX_GPIO143__FUNC_O_SPIM3_CSB (MTK_PIN_NO(143) | 5) +#define PINMUX_GPIO143__FUNC_O_UTXD1 (MTK_PIN_NO(143) | 6) +#define PINMUX_GPIO143__FUNC_B0_MD32_1_GPIO2 (MTK_PIN_NO(143) | 7) + +#define PINMUX_GPIO144__FUNC_B_GPIO144 (MTK_PIN_NO(144) | 0) +#define PINMUX_GPIO144__FUNC_O_DPI_D13 (MTK_PIN_NO(144) | 1) +#define PINMUX_GPIO144__FUNC_B1_GBE_MDIO (MTK_PIN_NO(144) | 2) +#define PINMUX_GPIO144__FUNC_B0_MD32_0_GPIO1 (MTK_PIN_NO(144) | 3) +#define PINMUX_GPIO144__FUNC_O_CLKM1 (MTK_PIN_NO(144) | 4) +#define PINMUX_GPIO144__FUNC_O_SPIM3_CLK (MTK_PIN_NO(144) | 5) +#define PINMUX_GPIO144__FUNC_I1_URXD1 (MTK_PIN_NO(144) | 6) +#define PINMUX_GPIO144__FUNC_O_PGD_HV_HSC_PWR0 (MTK_PIN_NO(144) | 7) + +#define PINMUX_GPIO145__FUNC_B_GPIO145 (MTK_PIN_NO(145) | 0) +#define PINMUX_GPIO145__FUNC_O_DPI_D14 (MTK_PIN_NO(145) | 1) +#define PINMUX_GPIO145__FUNC_O_GBE_TXER (MTK_PIN_NO(145) | 2) +#define PINMUX_GPIO145__FUNC_B0_MD32_1_GPIO0 (MTK_PIN_NO(145) | 3) +#define PINMUX_GPIO145__FUNC_O_CMFLASH0 (MTK_PIN_NO(145) | 4) +#define PINMUX_GPIO145__FUNC_B0_SPIM3_MOSI (MTK_PIN_NO(145) | 5) +#define PINMUX_GPIO145__FUNC_B0_GBE_AUX_PPS2 (MTK_PIN_NO(145) | 6) +#define PINMUX_GPIO145__FUNC_O_PGD_HV_HSC_PWR1 (MTK_PIN_NO(145) | 7) + +#define PINMUX_GPIO146__FUNC_B_GPIO146 (MTK_PIN_NO(146) | 0) +#define PINMUX_GPIO146__FUNC_O_DPI_D15 (MTK_PIN_NO(146) | 1) +#define PINMUX_GPIO146__FUNC_I0_GBE_RXER (MTK_PIN_NO(146) | 2) +#define PINMUX_GPIO146__FUNC_B0_MD32_1_GPIO1 (MTK_PIN_NO(146) | 3) +#define PINMUX_GPIO146__FUNC_O_CMFLASH1 (MTK_PIN_NO(146) | 4) +#define PINMUX_GPIO146__FUNC_B0_SPIM3_MISO (MTK_PIN_NO(146) | 5) +#define PINMUX_GPIO146__FUNC_B0_GBE_AUX_PPS3 (MTK_PIN_NO(146) | 6) +#define PINMUX_GPIO146__FUNC_O_PGD_HV_HSC_PWR2 (MTK_PIN_NO(146) | 7) + +#define PINMUX_GPIO147__FUNC_B_GPIO147 (MTK_PIN_NO(147) | 0) +#define PINMUX_GPIO147__FUNC_O_DPI_HSYNC (MTK_PIN_NO(147) | 1) +#define PINMUX_GPIO147__FUNC_I0_GBE_COL (MTK_PIN_NO(147) | 2) +#define PINMUX_GPIO147__FUNC_O_I2SO1_MCK (MTK_PIN_NO(147) | 3) +#define PINMUX_GPIO147__FUNC_O_CMVREF0 (MTK_PIN_NO(147) | 4) +#define PINMUX_GPIO147__FUNC_O_SPDIF_OUT (MTK_PIN_NO(147) | 5) +#define PINMUX_GPIO147__FUNC_O_URTS1 (MTK_PIN_NO(147) | 6) +#define PINMUX_GPIO147__FUNC_O_PGD_HV_HSC_PWR3 (MTK_PIN_NO(147) | 7) + +#define PINMUX_GPIO148__FUNC_B_GPIO148 (MTK_PIN_NO(148) | 0) +#define PINMUX_GPIO148__FUNC_O_DPI_VSYNC (MTK_PIN_NO(148) | 1) +#define PINMUX_GPIO148__FUNC_I0_GBE_INTR (MTK_PIN_NO(148) | 2) +#define PINMUX_GPIO148__FUNC_O_I2SO1_BCK (MTK_PIN_NO(148) | 3) +#define PINMUX_GPIO148__FUNC_O_CMVREF1 (MTK_PIN_NO(148) | 4) +#define PINMUX_GPIO148__FUNC_I0_SPDIF_IN0 (MTK_PIN_NO(148) | 5) +#define PINMUX_GPIO148__FUNC_I1_UCTS1 (MTK_PIN_NO(148) | 6) +#define PINMUX_GPIO148__FUNC_O_PGD_HV_HSC_PWR4 (MTK_PIN_NO(148) | 7) + +#define PINMUX_GPIO149__FUNC_B_GPIO149 (MTK_PIN_NO(149) | 0) +#define PINMUX_GPIO149__FUNC_O_DPI_DE (MTK_PIN_NO(149) | 1) +#define PINMUX_GPIO149__FUNC_B0_GBE_AUX_PPS0 (MTK_PIN_NO(149) | 2) +#define PINMUX_GPIO149__FUNC_O_I2SO1_WS (MTK_PIN_NO(149) | 3) +#define PINMUX_GPIO149__FUNC_O_CMVREF2 (MTK_PIN_NO(149) | 4) +#define PINMUX_GPIO149__FUNC_I0_SPDIF_IN1 (MTK_PIN_NO(149) | 5) +#define PINMUX_GPIO149__FUNC_O_UTXD3 (MTK_PIN_NO(149) | 6) +#define PINMUX_GPIO149__FUNC_O_PGD_HV_HSC_PWR5 (MTK_PIN_NO(149) | 7) + +#define PINMUX_GPIO150__FUNC_B_GPIO150 (MTK_PIN_NO(150) | 0) +#define PINMUX_GPIO150__FUNC_O_DPI_CK (MTK_PIN_NO(150) | 1) +#define PINMUX_GPIO150__FUNC_B0_GBE_AUX_PPS1 (MTK_PIN_NO(150) | 2) +#define PINMUX_GPIO150__FUNC_O_I2SO1_D0 (MTK_PIN_NO(150) | 3) +#define PINMUX_GPIO150__FUNC_O_CMVREF3 (MTK_PIN_NO(150) | 4) +#define PINMUX_GPIO150__FUNC_I0_SPDIF_IN2 (MTK_PIN_NO(150) | 5) +#define PINMUX_GPIO150__FUNC_I1_URXD3 (MTK_PIN_NO(150) | 6) + +#define PINMUX_GPIO151__FUNC_B_GPIO151 (MTK_PIN_NO(151) | 0) +#define PINMUX_GPIO151__FUNC_B1_MSDC0_DAT7 (MTK_PIN_NO(151) | 1) + +#define PINMUX_GPIO152__FUNC_B_GPIO152 (MTK_PIN_NO(152) | 0) +#define PINMUX_GPIO152__FUNC_B1_MSDC0_DAT6 (MTK_PIN_NO(152) | 1) + +#define PINMUX_GPIO153__FUNC_B_GPIO153 (MTK_PIN_NO(153) | 0) +#define PINMUX_GPIO153__FUNC_B1_MSDC0_DAT5 (MTK_PIN_NO(153) | 1) + +#define PINMUX_GPIO154__FUNC_B_GPIO154 (MTK_PIN_NO(154) | 0) +#define PINMUX_GPIO154__FUNC_B1_MSDC0_DAT4 (MTK_PIN_NO(154) | 1) + +#define PINMUX_GPIO155__FUNC_B_GPIO155 (MTK_PIN_NO(155) | 0) +#define PINMUX_GPIO155__FUNC_O_MSDC0_RSTB (MTK_PIN_NO(155) | 1) + +#define PINMUX_GPIO156__FUNC_B_GPIO156 (MTK_PIN_NO(156) | 0) +#define PINMUX_GPIO156__FUNC_B1_MSDC0_CMD (MTK_PIN_NO(156) | 1) + +#define PINMUX_GPIO157__FUNC_B_GPIO157 (MTK_PIN_NO(157) | 0) +#define PINMUX_GPIO157__FUNC_B1_MSDC0_CLK (MTK_PIN_NO(157) | 1) + +#define PINMUX_GPIO158__FUNC_B_GPIO158 (MTK_PIN_NO(158) | 0) +#define PINMUX_GPIO158__FUNC_B1_MSDC0_DAT3 (MTK_PIN_NO(158) | 1) + +#define PINMUX_GPIO159__FUNC_B_GPIO159 (MTK_PIN_NO(159) | 0) +#define PINMUX_GPIO159__FUNC_B1_MSDC0_DAT2 (MTK_PIN_NO(159) | 1) + +#define PINMUX_GPIO160__FUNC_B_GPIO160 (MTK_PIN_NO(160) | 0) +#define PINMUX_GPIO160__FUNC_B1_MSDC0_DAT1 (MTK_PIN_NO(160) | 1) + +#define PINMUX_GPIO161__FUNC_B_GPIO161 (MTK_PIN_NO(161) | 0) +#define PINMUX_GPIO161__FUNC_B1_MSDC0_DAT0 (MTK_PIN_NO(161) | 1) + +#define PINMUX_GPIO162__FUNC_B_GPIO162 (MTK_PIN_NO(162) | 0) +#define PINMUX_GPIO162__FUNC_B0_MSDC0_DSL (MTK_PIN_NO(162) | 1) + +#define PINMUX_GPIO163__FUNC_B_GPIO163 (MTK_PIN_NO(163) | 0) +#define PINMUX_GPIO163__FUNC_B1_MSDC1_CMD (MTK_PIN_NO(163) | 1) +#define PINMUX_GPIO163__FUNC_O_SPDIF_OUT (MTK_PIN_NO(163) | 2) +#define PINMUX_GPIO163__FUNC_I1_MD32_0_JTAG_TMS (MTK_PIN_NO(163) | 3) +#define PINMUX_GPIO163__FUNC_I1_ADSP_JTAG0_TMS (MTK_PIN_NO(163) | 4) +#define PINMUX_GPIO163__FUNC_I1_SCP_JTAG0_TMS (MTK_PIN_NO(163) | 5) +#define PINMUX_GPIO163__FUNC_I1_CCU0_JTAG_TMS (MTK_PIN_NO(163) | 6) +#define PINMUX_GPIO163__FUNC_I0_IPU_JTAG_TMS (MTK_PIN_NO(163) | 7) + +#define PINMUX_GPIO164__FUNC_B_GPIO164 (MTK_PIN_NO(164) | 0) +#define PINMUX_GPIO164__FUNC_B1_MSDC1_CLK (MTK_PIN_NO(164) | 1) +#define PINMUX_GPIO164__FUNC_I0_SPDIF_IN0 (MTK_PIN_NO(164) | 2) +#define PINMUX_GPIO164__FUNC_I1_MD32_0_JTAG_TCK (MTK_PIN_NO(164) | 3) +#define PINMUX_GPIO164__FUNC_I0_ADSP_JTAG0_TCK (MTK_PIN_NO(164) | 4) +#define PINMUX_GPIO164__FUNC_I1_SCP_JTAG0_TCK (MTK_PIN_NO(164) | 5) +#define PINMUX_GPIO164__FUNC_I1_CCU0_JTAG_TCK (MTK_PIN_NO(164) | 6) +#define PINMUX_GPIO164__FUNC_I0_IPU_JTAG_TCK (MTK_PIN_NO(164) | 7) + +#define PINMUX_GPIO165__FUNC_B_GPIO165 (MTK_PIN_NO(165) | 0) +#define PINMUX_GPIO165__FUNC_B1_MSDC1_DAT0 (MTK_PIN_NO(165) | 1) +#define PINMUX_GPIO165__FUNC_I0_SPDIF_IN1 (MTK_PIN_NO(165) | 2) +#define PINMUX_GPIO165__FUNC_I1_MD32_0_JTAG_TDI (MTK_PIN_NO(165) | 3) +#define PINMUX_GPIO165__FUNC_I1_ADSP_JTAG0_TDI (MTK_PIN_NO(165) | 4) +#define PINMUX_GPIO165__FUNC_I1_SCP_JTAG0_TDI (MTK_PIN_NO(165) | 5) +#define PINMUX_GPIO165__FUNC_I1_CCU0_JTAG_TDI (MTK_PIN_NO(165) | 6) +#define PINMUX_GPIO165__FUNC_I0_IPU_JTAG_TDI (MTK_PIN_NO(165) | 7) + +#define PINMUX_GPIO166__FUNC_B_GPIO166 (MTK_PIN_NO(166) | 0) +#define PINMUX_GPIO166__FUNC_B1_MSDC1_DAT1 (MTK_PIN_NO(166) | 1) +#define PINMUX_GPIO166__FUNC_I0_SPDIF_IN2 (MTK_PIN_NO(166) | 2) +#define PINMUX_GPIO166__FUNC_O_MD32_0_JTAG_TDO (MTK_PIN_NO(166) | 3) +#define PINMUX_GPIO166__FUNC_O_ADSP_JTAG0_TDO (MTK_PIN_NO(166) | 4) +#define PINMUX_GPIO166__FUNC_O_SCP_JTAG0_TDO (MTK_PIN_NO(166) | 5) +#define PINMUX_GPIO166__FUNC_O_CCU0_JTAG_TDO (MTK_PIN_NO(166) | 6) +#define PINMUX_GPIO166__FUNC_O_IPU_JTAG_TDO (MTK_PIN_NO(166) | 7) + +#define PINMUX_GPIO167__FUNC_B_GPIO167 (MTK_PIN_NO(167) | 0) +#define PINMUX_GPIO167__FUNC_B1_MSDC1_DAT2 (MTK_PIN_NO(167) | 1) +#define PINMUX_GPIO167__FUNC_O_PWM_0 (MTK_PIN_NO(167) | 2) +#define PINMUX_GPIO167__FUNC_I1_MD32_0_JTAG_TRST (MTK_PIN_NO(167) | 3) +#define PINMUX_GPIO167__FUNC_I1_ADSP_JTAG0_TRSTN (MTK_PIN_NO(167) | 4) +#define PINMUX_GPIO167__FUNC_I0_SCP_JTAG0_TRSTN (MTK_PIN_NO(167) | 5) +#define PINMUX_GPIO167__FUNC_I1_CCU0_JTAG_TRST (MTK_PIN_NO(167) | 6) +#define PINMUX_GPIO167__FUNC_I0_IPU_JTAG_TRST (MTK_PIN_NO(167) | 7) + +#define PINMUX_GPIO168__FUNC_B_GPIO168 (MTK_PIN_NO(168) | 0) +#define PINMUX_GPIO168__FUNC_B1_MSDC1_DAT3 (MTK_PIN_NO(168) | 1) +#define PINMUX_GPIO168__FUNC_O_PWM_1 (MTK_PIN_NO(168) | 2) +#define PINMUX_GPIO168__FUNC_O_CLKM0 (MTK_PIN_NO(168) | 3) + +#define PINMUX_GPIO169__FUNC_B_GPIO169 (MTK_PIN_NO(169) | 0) +#define PINMUX_GPIO169__FUNC_B1_MSDC2_CMD (MTK_PIN_NO(169) | 1) +#define PINMUX_GPIO169__FUNC_O_LVTS_FOUT (MTK_PIN_NO(169) | 2) +#define PINMUX_GPIO169__FUNC_I1_MD32_1_JTAG_TMS (MTK_PIN_NO(169) | 3) +#define PINMUX_GPIO169__FUNC_I0_UDI_TMS (MTK_PIN_NO(169) | 4) +#define PINMUX_GPIO169__FUNC_I0_VPU_UDI_TMS (MTK_PIN_NO(169) | 5) +#define PINMUX_GPIO169__FUNC_B0_TDMIN_MCK (MTK_PIN_NO(169) | 6) +#define PINMUX_GPIO169__FUNC_I1_SSPM_JTAG_TMS (MTK_PIN_NO(169) | 7) + +#define PINMUX_GPIO170__FUNC_B_GPIO170 (MTK_PIN_NO(170) | 0) +#define PINMUX_GPIO170__FUNC_B1_MSDC2_CLK (MTK_PIN_NO(170) | 1) +#define PINMUX_GPIO170__FUNC_O_LVTS_SDO (MTK_PIN_NO(170) | 2) +#define PINMUX_GPIO170__FUNC_I1_MD32_1_JTAG_TCK (MTK_PIN_NO(170) | 3) +#define PINMUX_GPIO170__FUNC_I0_UDI_TCK (MTK_PIN_NO(170) | 4) +#define PINMUX_GPIO170__FUNC_I0_VPU_UDI_TCK (MTK_PIN_NO(170) | 5) +#define PINMUX_GPIO170__FUNC_B0_TDMIN_BCK (MTK_PIN_NO(170) | 6) +#define PINMUX_GPIO170__FUNC_I1_SSPM_JTAG_TCK (MTK_PIN_NO(170) | 7) + +#define PINMUX_GPIO171__FUNC_B_GPIO171 (MTK_PIN_NO(171) | 0) +#define PINMUX_GPIO171__FUNC_B1_MSDC2_DAT0 (MTK_PIN_NO(171) | 1) +#define PINMUX_GPIO171__FUNC_I0_LVTS_26M (MTK_PIN_NO(171) | 2) +#define PINMUX_GPIO171__FUNC_I1_MD32_1_JTAG_TDI (MTK_PIN_NO(171) | 3) +#define PINMUX_GPIO171__FUNC_I0_UDI_TDI (MTK_PIN_NO(171) | 4) +#define PINMUX_GPIO171__FUNC_I0_VPU_UDI_TDI (MTK_PIN_NO(171) | 5) +#define PINMUX_GPIO171__FUNC_B0_TDMIN_LRCK (MTK_PIN_NO(171) | 6) +#define PINMUX_GPIO171__FUNC_I1_SSPM_JTAG_TDI (MTK_PIN_NO(171) | 7) + +#define PINMUX_GPIO172__FUNC_B_GPIO172 (MTK_PIN_NO(172) | 0) +#define PINMUX_GPIO172__FUNC_B1_MSDC2_DAT1 (MTK_PIN_NO(172) | 1) +#define PINMUX_GPIO172__FUNC_I0_LVTS_SCF (MTK_PIN_NO(172) | 2) +#define PINMUX_GPIO172__FUNC_O_MD32_1_JTAG_TDO (MTK_PIN_NO(172) | 3) +#define PINMUX_GPIO172__FUNC_O_UDI_TDO (MTK_PIN_NO(172) | 4) +#define PINMUX_GPIO172__FUNC_O_VPU_UDI_TDO (MTK_PIN_NO(172) | 5) +#define PINMUX_GPIO172__FUNC_I0_TDMIN_DI (MTK_PIN_NO(172) | 6) +#define PINMUX_GPIO172__FUNC_O_SSPM_JTAG_TDO (MTK_PIN_NO(172) | 7) + +#define PINMUX_GPIO173__FUNC_B_GPIO173 (MTK_PIN_NO(173) | 0) +#define PINMUX_GPIO173__FUNC_B1_MSDC2_DAT2 (MTK_PIN_NO(173) | 1) +#define PINMUX_GPIO173__FUNC_I0_LVTS_SCK (MTK_PIN_NO(173) | 2) +#define PINMUX_GPIO173__FUNC_I1_MD32_1_JTAG_TRST (MTK_PIN_NO(173) | 3) +#define PINMUX_GPIO173__FUNC_I0_UDI_NTRST (MTK_PIN_NO(173) | 4) +#define PINMUX_GPIO173__FUNC_I0_VPU_UDI_NTRST (MTK_PIN_NO(173) | 5) +#define PINMUX_GPIO173__FUNC_I0_SSPM_JTAG_TRSTN (MTK_PIN_NO(173) | 7) + +#define PINMUX_GPIO174__FUNC_B_GPIO174 (MTK_PIN_NO(174) | 0) +#define PINMUX_GPIO174__FUNC_B1_MSDC2_DAT3 (MTK_PIN_NO(174) | 1) +#define PINMUX_GPIO174__FUNC_I0_LVTS_SDI (MTK_PIN_NO(174) | 2) + +#define PINMUX_GPIO175__FUNC_B_GPIO175 (MTK_PIN_NO(175) | 0) +#define PINMUX_GPIO175__FUNC_B0_SPMI_M_SCL (MTK_PIN_NO(175) | 1) + +#define PINMUX_GPIO176__FUNC_B_GPIO176 (MTK_PIN_NO(176) | 0) +#define PINMUX_GPIO176__FUNC_B0_SPMI_M_SDA (MTK_PIN_NO(176) | 1) + +#endif /* __MEDIATEK_MT8188-PINFUNC_H */ diff --git a/include/dt-bindings/pinctrl/pinctrl-starfive.h b/include/dt-bindings/pinctrl/pinctrl-starfive-jh7100.h index de4f75c2c9e8..a200f546d078 100644 --- a/include/dt-bindings/pinctrl/pinctrl-starfive.h +++ b/include/dt-bindings/pinctrl/pinctrl-starfive-jh7100.h @@ -3,8 +3,8 @@ * Copyright (C) 2021 Emil Renner Berthing <kernel@esmil.dk> */ -#ifndef __DT_BINDINGS_PINCTRL_STARFIVE_H__ -#define __DT_BINDINGS_PINCTRL_STARFIVE_H__ +#ifndef __DT_BINDINGS_PINCTRL_STARFIVE_JH7100_H__ +#define __DT_BINDINGS_PINCTRL_STARFIVE_JH7100_H__ #define PAD_GPIO_OFFSET 0 #define PAD_FUNC_SHARE_OFFSET 64 @@ -272,4 +272,4 @@ #define GPI_NONE 0xff -#endif /* __DT_BINDINGS_PINCTRL_STARFIVE_H__ */ +#endif /* __DT_BINDINGS_PINCTRL_STARFIVE_JH7100_H__ */ diff --git a/include/dt-bindings/pinctrl/samsung.h b/include/dt-bindings/pinctrl/samsung.h index 950970634dfe..d1da5ff68d0c 100644 --- a/include/dt-bindings/pinctrl/samsung.h +++ b/include/dt-bindings/pinctrl/samsung.h @@ -10,6 +10,13 @@ #ifndef __DT_BINDINGS_PINCTRL_SAMSUNG_H__ #define __DT_BINDINGS_PINCTRL_SAMSUNG_H__ +/* + * These bindings are deprecated, because they do not match the actual + * concept of bindings but rather contain pure register values. + * Instead include the header in the DTS source directory. + */ +#warning "These bindings are deprecated. Instead use the header in the DTS source directory." + #define EXYNOS_PIN_PULL_NONE 0 #define EXYNOS_PIN_PULL_DOWN 1 #define EXYNOS_PIN_PULL_UP 3 diff --git a/include/kunit/assert.h b/include/kunit/assert.h index 4b52e12c2ae8..ace3de8d1ee7 100644 --- a/include/kunit/assert.h +++ b/include/kunit/assert.h @@ -42,16 +42,15 @@ struct kunit_loc { /** * struct kunit_assert - Data for printing a failed assertion or expectation. - * @format: a function which formats the data in this kunit_assert to a string. * * Represents a failed expectation/assertion. Contains all the data necessary to * format a string to a user reporting the failure. */ -struct kunit_assert { - void (*format)(const struct kunit_assert *assert, - const struct va_format *message, - struct string_stream *stream); -}; +struct kunit_assert {}; + +typedef void (*assert_format_t)(const struct kunit_assert *assert, + const struct va_format *message, + struct string_stream *stream); void kunit_assert_prologue(const struct kunit_loc *loc, enum kunit_assert_type type, @@ -72,16 +71,6 @@ void kunit_fail_assert_format(const struct kunit_assert *assert, struct string_stream *stream); /** - * KUNIT_INIT_FAIL_ASSERT_STRUCT - Initializer for &struct kunit_fail_assert. - * - * Initializes a &struct kunit_fail_assert. Intended to be used in - * KUNIT_EXPECT_* and KUNIT_ASSERT_* macros. - */ -#define KUNIT_INIT_FAIL_ASSERT_STRUCT { \ - .assert = { .format = kunit_fail_assert_format }, \ -} - -/** * struct kunit_unary_assert - Represents a KUNIT_{EXPECT|ASSERT}_{TRUE|FALSE} * @assert: The parent of this type. * @condition: A string representation of a conditional expression. @@ -110,7 +99,6 @@ void kunit_unary_assert_format(const struct kunit_assert *assert, * KUNIT_EXPECT_* and KUNIT_ASSERT_* macros. */ #define KUNIT_INIT_UNARY_ASSERT_STRUCT(cond, expect_true) { \ - .assert = { .format = kunit_unary_assert_format }, \ .condition = cond, \ .expected_true = expect_true \ } @@ -145,7 +133,6 @@ void kunit_ptr_not_err_assert_format(const struct kunit_assert *assert, * KUNIT_EXPECT_* and KUNIT_ASSERT_* macros. */ #define KUNIT_INIT_PTR_NOT_ERR_STRUCT(txt, val) { \ - .assert = { .format = kunit_ptr_not_err_assert_format }, \ .text = txt, \ .value = val \ } @@ -190,7 +177,6 @@ void kunit_binary_assert_format(const struct kunit_assert *assert, * KUNIT_INIT_BINARY_ASSERT_STRUCT() - Initializes a binary assert like * kunit_binary_assert, kunit_binary_ptr_assert, etc. * - * @format_func: a function which formats the assert to a string. * @text_: Pointer to a kunit_binary_assert_text. * @left_val: The actual evaluated value of the expression in the left slot. * @right_val: The actual evaluated value of the expression in the right slot. @@ -200,11 +186,9 @@ void kunit_binary_assert_format(const struct kunit_assert *assert, * fields but with different types for left_val/right_val. * This is ultimately used by binary assertion macros like KUNIT_EXPECT_EQ, etc. */ -#define KUNIT_INIT_BINARY_ASSERT_STRUCT(format_func, \ - text_, \ +#define KUNIT_INIT_BINARY_ASSERT_STRUCT(text_, \ left_val, \ right_val) { \ - .assert = { .format = format_func }, \ .text = text_, \ .left_value = left_val, \ .right_value = right_val \ diff --git a/include/kunit/resource.h b/include/kunit/resource.h index 09c2b34d1c61..cf6fb8f2ac1b 100644 --- a/include/kunit/resource.h +++ b/include/kunit/resource.h @@ -301,22 +301,6 @@ typedef bool (*kunit_resource_match_t)(struct kunit *test, void *match_data); /** - * kunit_resource_instance_match() - Match a resource with the same instance. - * @test: Test case to which the resource belongs. - * @res: The resource. - * @match_data: The resource pointer to match against. - * - * An instance of kunit_resource_match_t that matches a resource whose - * allocation matches @match_data. - */ -static inline bool kunit_resource_instance_match(struct kunit *test, - struct kunit_resource *res, - void *match_data) -{ - return res->data == match_data; -} - -/** * kunit_resource_name_match() - Match a resource with the same name. * @test: Test case to which the resource belongs. * @res: The resource. diff --git a/include/kunit/test.h b/include/kunit/test.h index 20cc4770cb3f..b1ab6b32216d 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -473,30 +473,30 @@ void kunit_do_failed_assertion(struct kunit *test, const struct kunit_loc *loc, enum kunit_assert_type type, const struct kunit_assert *assert, + assert_format_t assert_format, const char *fmt, ...); -#define KUNIT_ASSERTION(test, assert_type, pass, assert_class, INITIALIZER, fmt, ...) do { \ - if (unlikely(!(pass))) { \ - static const struct kunit_loc __loc = KUNIT_CURRENT_LOC; \ - struct assert_class __assertion = INITIALIZER; \ - kunit_do_failed_assertion(test, \ - &__loc, \ - assert_type, \ - &__assertion.assert, \ - fmt, \ - ##__VA_ARGS__); \ - } \ +#define _KUNIT_FAILED(test, assert_type, assert_class, assert_format, INITIALIZER, fmt, ...) do { \ + static const struct kunit_loc __loc = KUNIT_CURRENT_LOC; \ + const struct assert_class __assertion = INITIALIZER; \ + kunit_do_failed_assertion(test, \ + &__loc, \ + assert_type, \ + &__assertion.assert, \ + assert_format, \ + fmt, \ + ##__VA_ARGS__); \ } while (0) #define KUNIT_FAIL_ASSERTION(test, assert_type, fmt, ...) \ - KUNIT_ASSERTION(test, \ - assert_type, \ - false, \ - kunit_fail_assert, \ - KUNIT_INIT_FAIL_ASSERT_STRUCT, \ - fmt, \ - ##__VA_ARGS__) + _KUNIT_FAILED(test, \ + assert_type, \ + kunit_fail_assert, \ + kunit_fail_assert_format, \ + {}, \ + fmt, \ + ##__VA_ARGS__) /** * KUNIT_FAIL() - Always causes a test to fail when evaluated. @@ -521,14 +521,19 @@ void kunit_do_failed_assertion(struct kunit *test, expected_true, \ fmt, \ ...) \ - KUNIT_ASSERTION(test, \ - assert_type, \ - !!(condition) == !!expected_true, \ - kunit_unary_assert, \ - KUNIT_INIT_UNARY_ASSERT_STRUCT(#condition, \ - expected_true), \ - fmt, \ - ##__VA_ARGS__) +do { \ + if (likely(!!(condition) == !!expected_true)) \ + break; \ + \ + _KUNIT_FAILED(test, \ + assert_type, \ + kunit_unary_assert, \ + kunit_unary_assert_format, \ + KUNIT_INIT_UNARY_ASSERT_STRUCT(#condition, \ + expected_true), \ + fmt, \ + ##__VA_ARGS__); \ +} while (0) #define KUNIT_TRUE_MSG_ASSERTION(test, assert_type, condition, fmt, ...) \ KUNIT_UNARY_ASSERTION(test, \ @@ -578,16 +583,18 @@ do { \ .right_text = #right, \ }; \ \ - KUNIT_ASSERTION(test, \ - assert_type, \ - __left op __right, \ - assert_class, \ - KUNIT_INIT_BINARY_ASSERT_STRUCT(format_func, \ - &__text, \ - __left, \ - __right), \ - fmt, \ - ##__VA_ARGS__); \ + if (likely(__left op __right)) \ + break; \ + \ + _KUNIT_FAILED(test, \ + assert_type, \ + assert_class, \ + format_func, \ + KUNIT_INIT_BINARY_ASSERT_STRUCT(&__text, \ + __left, \ + __right), \ + fmt, \ + ##__VA_ARGS__); \ } while (0) #define KUNIT_BINARY_INT_ASSERTION(test, \ @@ -636,16 +643,19 @@ do { \ .right_text = #right, \ }; \ \ - KUNIT_ASSERTION(test, \ - assert_type, \ - strcmp(__left, __right) op 0, \ - kunit_binary_str_assert, \ - KUNIT_INIT_BINARY_ASSERT_STRUCT(kunit_binary_str_assert_format,\ - &__text, \ - __left, \ - __right), \ - fmt, \ - ##__VA_ARGS__); \ + if (likely(strcmp(__left, __right) op 0)) \ + break; \ + \ + \ + _KUNIT_FAILED(test, \ + assert_type, \ + kunit_binary_str_assert, \ + kunit_binary_str_assert_format, \ + KUNIT_INIT_BINARY_ASSERT_STRUCT(&__text, \ + __left, \ + __right), \ + fmt, \ + ##__VA_ARGS__); \ } while (0) #define KUNIT_PTR_NOT_ERR_OR_NULL_MSG_ASSERTION(test, \ @@ -656,14 +666,16 @@ do { \ do { \ const typeof(ptr) __ptr = (ptr); \ \ - KUNIT_ASSERTION(test, \ - assert_type, \ - !IS_ERR_OR_NULL(__ptr), \ - kunit_ptr_not_err_assert, \ - KUNIT_INIT_PTR_NOT_ERR_STRUCT(#ptr, \ - __ptr), \ - fmt, \ - ##__VA_ARGS__); \ + if (!IS_ERR_OR_NULL(__ptr)) \ + break; \ + \ + _KUNIT_FAILED(test, \ + assert_type, \ + kunit_ptr_not_err_assert, \ + kunit_ptr_not_err_assert_format, \ + KUNIT_INIT_PTR_NOT_ERR_STRUCT(#ptr, __ptr), \ + fmt, \ + ##__VA_ARGS__); \ } while (0) /** diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 729cff1ee3f8..3015235d65e3 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -498,7 +498,7 @@ bool acpi_dev_resource_address_space(struct acpi_resource *ares, struct resource_win *win); bool acpi_dev_resource_ext_address_space(struct acpi_resource *ares, struct resource_win *win); -unsigned long acpi_dev_irq_flags(u8 triggering, u8 polarity, u8 shareable); +unsigned long acpi_dev_irq_flags(u8 triggering, u8 polarity, u8 shareable, u8 wake_capable); unsigned int acpi_dev_get_irq_type(int triggering, int polarity); bool acpi_dev_resource_interrupt(struct acpi_resource *ares, int index, struct resource *res); @@ -1211,7 +1211,8 @@ bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio); bool acpi_gpio_get_io_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio); -int acpi_dev_gpio_irq_get_by(struct acpi_device *adev, const char *name, int index); +int acpi_dev_gpio_irq_wake_get_by(struct acpi_device *adev, const char *name, int index, + bool *wake_capable); #else static inline bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio) @@ -1223,16 +1224,28 @@ static inline bool acpi_gpio_get_io_resource(struct acpi_resource *ares, { return false; } -static inline int acpi_dev_gpio_irq_get_by(struct acpi_device *adev, - const char *name, int index) +static inline int acpi_dev_gpio_irq_wake_get_by(struct acpi_device *adev, const char *name, + int index, bool *wake_capable) { return -ENXIO; } #endif +static inline int acpi_dev_gpio_irq_wake_get(struct acpi_device *adev, int index, + bool *wake_capable) +{ + return acpi_dev_gpio_irq_wake_get_by(adev, NULL, index, wake_capable); +} + +static inline int acpi_dev_gpio_irq_get_by(struct acpi_device *adev, const char *name, + int index) +{ + return acpi_dev_gpio_irq_wake_get_by(adev, name, index, NULL); +} + static inline int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index) { - return acpi_dev_gpio_irq_get_by(adev, NULL, index); + return acpi_dev_gpio_irq_wake_get_by(adev, NULL, index, NULL); } /* Device properties */ diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index f65410a49fda..7d6d73b78147 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -51,6 +51,7 @@ struct device; * bitmap_empty(src, nbits) Are all bits zero in *src? * bitmap_full(src, nbits) Are all bits set in *src? * bitmap_weight(src, nbits) Hamming Weight: number set bits + * bitmap_weight_and(src1, src2, nbits) Hamming Weight of and'ed bitmap * bitmap_set(dst, pos, nbits) Set specified bit area * bitmap_clear(dst, pos, nbits) Clear specified bit area * bitmap_find_next_zero_area(buf, len, pos, n, mask) Find bit free area @@ -164,6 +165,8 @@ bool __bitmap_intersects(const unsigned long *bitmap1, bool __bitmap_subset(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); unsigned int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits); +unsigned int __bitmap_weight_and(const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int nbits); void __bitmap_set(unsigned long *map, unsigned int start, int len); void __bitmap_clear(unsigned long *map, unsigned int start, int len); @@ -222,7 +225,6 @@ void bitmap_copy_le(unsigned long *dst, const unsigned long *src, unsigned int n #else #define bitmap_copy_le bitmap_copy #endif -unsigned int bitmap_ord_to_pos(const unsigned long *bitmap, unsigned int ord, unsigned int nbits); int bitmap_print_to_pagebuf(bool list, char *buf, const unsigned long *maskp, int nmaskbits); @@ -439,6 +441,15 @@ unsigned int bitmap_weight(const unsigned long *src, unsigned int nbits) return __bitmap_weight(src, nbits); } +static __always_inline +unsigned long bitmap_weight_and(const unsigned long *src1, + const unsigned long *src2, unsigned int nbits) +{ + if (small_const_nbits(nbits)) + return hweight_long(*src1 & *src2 & BITMAP_LAST_WORD_MASK(nbits)); + return __bitmap_weight_and(src1, src2, nbits); +} + static __always_inline void bitmap_set(unsigned long *map, unsigned int start, unsigned int nbits) { diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 3b89c64bcfd8..2ba557e067fe 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -248,6 +248,25 @@ static inline unsigned long __ffs64(u64 word) } /** + * fns - find N'th set bit in a word + * @word: The word to search + * @n: Bit to find + */ +static inline unsigned long fns(unsigned long word, unsigned int n) +{ + unsigned int bit; + + while (word) { + bit = __ffs(word); + if (n-- == 0) + return bit; + __clear_bit(bit, &word); + } + + return BITS_PER_LONG; +} + +/** * assign_bit - Assign value to a bit in memory * @nr: the bit to set * @addr: the address to start counting from @@ -328,10 +347,10 @@ static __always_inline void __assign_bit(long nr, volatile unsigned long *addr, const typeof(*(ptr)) mask__ = (mask), bits__ = (bits); \ typeof(*(ptr)) old__, new__; \ \ + old__ = READ_ONCE(*(ptr)); \ do { \ - old__ = READ_ONCE(*(ptr)); \ new__ = (old__ & ~mask__) | bits__; \ - } while (cmpxchg(ptr, old__, new__) != old__); \ + } while (!try_cmpxchg(ptr, &old__, new__)); \ \ old__; \ }) @@ -343,11 +362,12 @@ static __always_inline void __assign_bit(long nr, volatile unsigned long *addr, const typeof(*(ptr)) clear__ = (clear), test__ = (test);\ typeof(*(ptr)) old__, new__; \ \ + old__ = READ_ONCE(*(ptr)); \ do { \ - old__ = READ_ONCE(*(ptr)); \ + if (old__ & test__) \ + break; \ new__ = old__ & ~clear__; \ - } while (!(old__ & test__) && \ - cmpxchg(ptr, old__, new__) != old__); \ + } while (!try_cmpxchg(ptr, &old__, new__)); \ \ !(old__ & test__); \ }) diff --git a/include/linux/bma150.h b/include/linux/bma150.h index 31c9e323a391..4d4a62d49341 100644 --- a/include/linux/bma150.h +++ b/include/linux/bma150.h @@ -33,8 +33,8 @@ struct bma150_cfg { unsigned char lg_hyst; /* Low-G hysterisis */ unsigned char lg_dur; /* Low-G duration */ unsigned char lg_thres; /* Low-G threshold */ - unsigned char range; /* one of BMA0150_RANGE_xxx */ - unsigned char bandwidth; /* one of BMA0150_BW_xxx */ + unsigned char range; /* one of BMA150_RANGE_xxx */ + unsigned char bandwidth; /* one of BMA150_BW_xxx */ }; struct bma150_platform_data { diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 9e7d46d16032..c1bd1bd10506 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -27,6 +27,7 @@ #include <linux/bpfptr.h> #include <linux/btf.h> #include <linux/rcupdate_trace.h> +#include <linux/static_call.h> struct bpf_verifier_env; struct bpf_verifier_log; @@ -314,7 +315,7 @@ static inline void __copy_map_value(struct bpf_map *map, void *dst, void *src, b u32 next_off = map->off_arr->field_off[i]; memcpy(dst + curr_off, src + curr_off, next_off - curr_off); - curr_off += map->off_arr->field_sz[i]; + curr_off = next_off + map->off_arr->field_sz[i]; } memcpy(dst + curr_off, src + curr_off, map->value_size - curr_off); } @@ -343,7 +344,7 @@ static inline void zero_map_value(struct bpf_map *map, void *dst) u32 next_off = map->off_arr->field_off[i]; memset(dst + curr_off, 0, next_off - curr_off); - curr_off += map->off_arr->field_sz[i]; + curr_off = next_off + map->off_arr->field_sz[i]; } memset(dst + curr_off, 0, map->value_size - curr_off); } @@ -953,6 +954,10 @@ struct bpf_dispatcher { void *rw_image; u32 image_off; struct bpf_ksym ksym; +#ifdef CONFIG_HAVE_STATIC_CALL + struct static_call_key *sc_key; + void *sc_tramp; +#endif }; static __always_inline __nocfi unsigned int bpf_dispatcher_nop_func( @@ -970,6 +975,34 @@ struct bpf_trampoline *bpf_trampoline_get(u64 key, struct bpf_attach_target_info *tgt_info); void bpf_trampoline_put(struct bpf_trampoline *tr); int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_funcs); + +/* + * When the architecture supports STATIC_CALL replace the bpf_dispatcher_fn + * indirection with a direct call to the bpf program. If the architecture does + * not have STATIC_CALL, avoid a double-indirection. + */ +#ifdef CONFIG_HAVE_STATIC_CALL + +#define __BPF_DISPATCHER_SC_INIT(_name) \ + .sc_key = &STATIC_CALL_KEY(_name), \ + .sc_tramp = STATIC_CALL_TRAMP_ADDR(_name), + +#define __BPF_DISPATCHER_SC(name) \ + DEFINE_STATIC_CALL(bpf_dispatcher_##name##_call, bpf_dispatcher_nop_func) + +#define __BPF_DISPATCHER_CALL(name) \ + static_call(bpf_dispatcher_##name##_call)(ctx, insnsi, bpf_func) + +#define __BPF_DISPATCHER_UPDATE(_d, _new) \ + __static_call_update((_d)->sc_key, (_d)->sc_tramp, (_new)) + +#else +#define __BPF_DISPATCHER_SC_INIT(name) +#define __BPF_DISPATCHER_SC(name) +#define __BPF_DISPATCHER_CALL(name) bpf_func(ctx, insnsi) +#define __BPF_DISPATCHER_UPDATE(_d, _new) +#endif + #define BPF_DISPATCHER_INIT(_name) { \ .mutex = __MUTEX_INITIALIZER(_name.mutex), \ .func = &_name##_func, \ @@ -981,32 +1014,29 @@ int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_func .name = #_name, \ .lnode = LIST_HEAD_INIT(_name.ksym.lnode), \ }, \ + __BPF_DISPATCHER_SC_INIT(_name##_call) \ } -#ifdef CONFIG_X86_64 -#define BPF_DISPATCHER_ATTRIBUTES __attribute__((patchable_function_entry(5))) -#else -#define BPF_DISPATCHER_ATTRIBUTES -#endif - #define DEFINE_BPF_DISPATCHER(name) \ - notrace BPF_DISPATCHER_ATTRIBUTES \ + __BPF_DISPATCHER_SC(name); \ noinline __nocfi unsigned int bpf_dispatcher_##name##_func( \ const void *ctx, \ const struct bpf_insn *insnsi, \ bpf_func_t bpf_func) \ { \ - return bpf_func(ctx, insnsi); \ + return __BPF_DISPATCHER_CALL(name); \ } \ EXPORT_SYMBOL(bpf_dispatcher_##name##_func); \ struct bpf_dispatcher bpf_dispatcher_##name = \ BPF_DISPATCHER_INIT(bpf_dispatcher_##name); + #define DECLARE_BPF_DISPATCHER(name) \ unsigned int bpf_dispatcher_##name##_func( \ const void *ctx, \ const struct bpf_insn *insnsi, \ bpf_func_t bpf_func); \ extern struct bpf_dispatcher bpf_dispatcher_##name; + #define BPF_DISPATCHER_FUNC(name) bpf_dispatcher_##name##_func #define BPF_DISPATCHER_PTR(name) (&bpf_dispatcher_##name) void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 06089390d81d..33fa5e94aa80 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -225,8 +225,6 @@ struct buffer_head *__getblk_gfp(struct block_device *bdev, sector_t block, void __brelse(struct buffer_head *); void __bforget(struct buffer_head *); void __breadahead(struct block_device *, sector_t block, unsigned int size); -void __breadahead_gfp(struct block_device *, sector_t block, unsigned int size, - gfp_t gfp); struct buffer_head *__bread_gfp(struct block_device *, sector_t block, unsigned size, gfp_t gfp); void invalidate_bh_lrus(void); @@ -236,7 +234,6 @@ struct buffer_head *alloc_buffer_head(gfp_t gfp_flags); void free_buffer_head(struct buffer_head * bh); void unlock_buffer(struct buffer_head *bh); void __lock_buffer(struct buffer_head *bh); -void ll_rw_block(blk_opf_t, int, struct buffer_head * bh[]); int sync_dirty_buffer(struct buffer_head *bh); int __sync_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags); void write_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags); @@ -244,7 +241,9 @@ void submit_bh(blk_opf_t, struct buffer_head *); void write_boundary_block(struct block_device *bdev, sector_t bblock, unsigned blocksize); int bh_uptodate_or_lock(struct buffer_head *bh); -int bh_submit_read(struct buffer_head *bh); +int __bh_read(struct buffer_head *bh, blk_opf_t op_flags, bool wait); +void __bh_read_batch(int nr, struct buffer_head *bhs[], + blk_opf_t op_flags, bool force_lock); extern int buffer_heads_over_limit; @@ -351,12 +350,6 @@ sb_breadahead(struct super_block *sb, sector_t block) __breadahead(sb->s_bdev, block, sb->s_blocksize); } -static inline void -sb_breadahead_unmovable(struct super_block *sb, sector_t block) -{ - __breadahead_gfp(sb->s_bdev, block, sb->s_blocksize, 0); -} - static inline struct buffer_head * sb_getblk(struct super_block *sb, sector_t block) { @@ -418,6 +411,41 @@ static inline struct buffer_head *__getblk(struct block_device *bdev, return __getblk_gfp(bdev, block, size, __GFP_MOVABLE); } +static inline void bh_readahead(struct buffer_head *bh, blk_opf_t op_flags) +{ + if (!buffer_uptodate(bh) && trylock_buffer(bh)) { + if (!buffer_uptodate(bh)) + __bh_read(bh, op_flags, false); + else + unlock_buffer(bh); + } +} + +static inline void bh_read_nowait(struct buffer_head *bh, blk_opf_t op_flags) +{ + if (!bh_uptodate_or_lock(bh)) + __bh_read(bh, op_flags, false); +} + +/* Returns 1 if buffer uptodated, 0 on success, and -EIO on error. */ +static inline int bh_read(struct buffer_head *bh, blk_opf_t op_flags) +{ + if (bh_uptodate_or_lock(bh)) + return 1; + return __bh_read(bh, op_flags, true); +} + +static inline void bh_read_batch(int nr, struct buffer_head *bhs[]) +{ + __bh_read_batch(nr, bhs, 0, true); +} + +static inline void bh_readahead_batch(int nr, struct buffer_head *bhs[], + blk_opf_t op_flags) +{ + __bh_read_batch(nr, bhs, op_flags, false); +} + /** * __bread() - reads a specified block and returns the bh * @bdev: the block_device to read from diff --git a/include/linux/cache.h b/include/linux/cache.h index d742c57eaee5..5da1bbd96154 100644 --- a/include/linux/cache.h +++ b/include/linux/cache.h @@ -85,4 +85,17 @@ #define cache_line_size() L1_CACHE_BYTES #endif +/* + * Helper to add padding within a struct to ensure data fall into separate + * cachelines. + */ +#if defined(CONFIG_SMP) +struct cacheline_padding { + char x[0]; +} ____cacheline_internodealigned_in_smp; +#define CACHELINE_PADDING(name) struct cacheline_padding name +#else +#define CACHELINE_PADDING(name) +#endif + #endif /* __LINUX_CACHE_H */ diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 58f5431a5559..982ba245eb41 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -152,6 +152,22 @@ static inline bool can_is_canxl_dev_mtu(unsigned int mtu) return (mtu >= CANXL_MIN_MTU && mtu <= CANXL_MAX_MTU); } +/* drop skb if it does not contain a valid CAN frame for sending */ +static inline bool can_dev_dropped_skb(struct net_device *dev, struct sk_buff *skb) +{ + struct can_priv *priv = netdev_priv(dev); + + if (priv->ctrlmode & CAN_CTRLMODE_LISTENONLY) { + netdev_info_once(dev, + "interface in listen only mode, dropping skb\n"); + kfree_skb(skb); + dev->stats.tx_dropped++; + return true; + } + + return can_dropped_invalid_skb(dev, skb); +} + void can_setup(struct net_device *dev); struct net_device *alloc_candev_mqs(int sizeof_priv, unsigned int echo_skb_max, diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index e7f2fb2fc207..99c1726be6ee 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -207,7 +207,6 @@ struct ceph_msg_data_cursor { struct ceph_msg_data *data; /* current data item */ size_t resid; /* bytes not yet consumed */ - bool last_piece; /* current is last piece */ bool need_crc; /* crc update needed */ union { #ifdef CONFIG_BLOCK @@ -498,8 +497,7 @@ void ceph_con_discard_requeued(struct ceph_connection *con, u64 reconnect_seq); void ceph_msg_data_cursor_init(struct ceph_msg_data_cursor *cursor, struct ceph_msg *msg, size_t length); struct page *ceph_msg_data_next(struct ceph_msg_data_cursor *cursor, - size_t *page_offset, size_t *length, - bool *last_piece); + size_t *page_offset, size_t *length); void ceph_msg_data_advance(struct ceph_msg_data_cursor *cursor, size_t bytes); u32 ceph_crc32c_page(u32 crc, struct page *page, unsigned int page_offset, diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 4bcf56b3491c..6e01f10f0d88 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -126,11 +126,11 @@ enum { CFTYPE_NO_PREFIX = (1 << 3), /* (DON'T USE FOR NEW FILES) no subsys prefix */ CFTYPE_WORLD_WRITABLE = (1 << 4), /* (DON'T USE FOR NEW FILES) S_IWUGO */ CFTYPE_DEBUG = (1 << 5), /* create when cgroup_debug */ - CFTYPE_PRESSURE = (1 << 6), /* only if pressure feature is enabled */ /* internal flags, do not use outside cgroup core proper */ __CFTYPE_ONLY_ON_DFL = (1 << 16), /* only on default hierarchy */ __CFTYPE_NOT_ON_DFL = (1 << 17), /* not on default hierarchy */ + __CFTYPE_ADDED = (1 << 18), }; /* @@ -384,7 +384,7 @@ struct cgroup { /* * The depth this cgroup is at. The root is at depth zero and each * step down the hierarchy increments the level. This along with - * ancestor_ids[] can determine whether a given cgroup is a + * ancestors[] can determine whether a given cgroup is a * descendant of another without traversing the hierarchy. */ int level; @@ -428,6 +428,9 @@ struct cgroup { struct cgroup_file procs_file; /* handle for "cgroup.procs" */ struct cgroup_file events_file; /* handle for "cgroup.events" */ + /* handles for "{cpu,memory,io,irq}.pressure" */ + struct cgroup_file psi_files[NR_PSI_RESOURCES]; + /* * The bitmask of subsystems enabled on the child cgroups. * ->subtree_control is the one configured through @@ -504,8 +507,8 @@ struct cgroup { /* Used to store internal freezer state */ struct cgroup_freezer_state freezer; - /* ids of the ancestors at each level including self */ - u64 ancestor_ids[]; + /* All ancestors including self */ + struct cgroup *ancestors[]; }; /* @@ -522,11 +525,15 @@ struct cgroup_root { /* Unique id for this hierarchy. */ int hierarchy_id; - /* The root cgroup. Root is destroyed on its release. */ + /* + * The root cgroup. The containing cgroup_root will be destroyed on its + * release. cgrp->ancestors[0] will be used overflowing into the + * following field. cgrp_ancestor_storage must immediately follow. + */ struct cgroup cgrp; - /* for cgrp->ancestor_ids[0] */ - u64 cgrp_ancestor_id_storage; + /* must follow cgrp for cgrp->ancestors[0], see above */ + struct cgroup *cgrp_ancestor_storage; /* Number of cgroups in the hierarchy, used only for /proc/cgroups */ atomic_t nr_cgrps; diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index b0914aa26506..528bd44b59e2 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -106,6 +106,7 @@ struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, struct cgroup *cgroup_get_from_path(const char *path); struct cgroup *cgroup_get_from_fd(int fd); +struct cgroup *cgroup_v1v2_get_from_fd(int fd); int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); @@ -433,6 +434,18 @@ static inline void cgroup_put(struct cgroup *cgrp) css_put(&cgrp->self); } +extern struct mutex cgroup_mutex; + +static inline void cgroup_lock(void) +{ + mutex_lock(&cgroup_mutex); +} + +static inline void cgroup_unlock(void) +{ + mutex_unlock(&cgroup_mutex); +} + /** * task_css_set_check - obtain a task's css_set with extra access conditions * @task: the task to obtain css_set for @@ -447,7 +460,6 @@ static inline void cgroup_put(struct cgroup *cgrp) * as locks used during the cgroup_subsys::attach() methods. */ #ifdef CONFIG_PROVE_RCU -extern struct mutex cgroup_mutex; extern spinlock_t css_set_lock; #define task_css_set_check(task, __c) \ rcu_dereference_check((task)->cgroups, \ @@ -575,7 +587,7 @@ static inline bool cgroup_is_descendant(struct cgroup *cgrp, { if (cgrp->root != ancestor->root || cgrp->level < ancestor->level) return false; - return cgrp->ancestor_ids[ancestor->level] == cgroup_id(ancestor); + return cgrp->ancestors[ancestor->level] == ancestor; } /** @@ -592,11 +604,9 @@ static inline bool cgroup_is_descendant(struct cgroup *cgrp, static inline struct cgroup *cgroup_ancestor(struct cgroup *cgrp, int ancestor_level) { - if (cgrp->level < ancestor_level) + if (ancestor_level < 0 || ancestor_level > cgrp->level) return NULL; - while (cgrp && cgrp->level > ancestor_level) - cgrp = cgroup_parent(cgrp); - return cgrp; + return cgrp->ancestors[ancestor_level]; } /** @@ -673,11 +683,6 @@ static inline void pr_cont_cgroup_path(struct cgroup *cgrp) pr_cont_kernfs_path(cgrp->kn); } -static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) -{ - return cgrp->psi; -} - bool cgroup_psi_enabled(void); static inline void cgroup_init_kthreadd(void) @@ -709,6 +714,8 @@ struct cgroup; static inline u64 cgroup_id(const struct cgroup *cgrp) { return 1; } static inline void css_get(struct cgroup_subsys_state *css) {} static inline void css_put(struct cgroup_subsys_state *css) {} +static inline void cgroup_lock(void) {} +static inline void cgroup_unlock(void) {} static inline int cgroup_attach_task_all(struct task_struct *from, struct task_struct *t) { return 0; } static inline int cgroupstats_build(struct cgroupstats *stats, @@ -748,11 +755,6 @@ static inline bool task_under_cgroup_hierarchy(struct task_struct *task, static inline void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen) {} - -static inline struct cgroup *cgroup_get_from_id(u64 id) -{ - return NULL; -} #endif /* !CONFIG_CGROUPS */ #ifdef CONFIG_CGROUPS diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 2108b5695327..267cd06b54a0 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -42,6 +42,8 @@ struct dentry; * struct clk_rate_request - Structure encoding the clk constraints that * a clock user might require. * + * Should be initialized by calling clk_hw_init_rate_request(). + * * @rate: Requested clock rate. This field will be adjusted by * clock drivers according to hardware capabilities. * @min_rate: Minimum rate imposed by clk users. @@ -60,6 +62,15 @@ struct clk_rate_request { struct clk_hw *best_parent_hw; }; +void clk_hw_init_rate_request(const struct clk_hw *hw, + struct clk_rate_request *req, + unsigned long rate); +void clk_hw_forward_rate_request(const struct clk_hw *core, + const struct clk_rate_request *old_req, + const struct clk_hw *parent, + struct clk_rate_request *req, + unsigned long parent_rate); + /** * struct clk_duty - Struture encoding the duty cycle ratio of a clock * @@ -118,8 +129,9 @@ struct clk_duty { * * @recalc_rate Recalculate the rate of this clock, by querying hardware. The * parent rate is an input parameter. It is up to the caller to - * ensure that the prepare_mutex is held across this call. - * Returns the calculated rate. Optional, but recommended - if + * ensure that the prepare_mutex is held across this call. If the + * driver cannot figure out a rate for this clock, it must return + * 0. Returns the calculated rate. Optional, but recommended - if * this op is not set then clock rate will be initialized to 0. * * @round_rate: Given a target rate as input, returns the closest rate actually @@ -1303,6 +1315,8 @@ int clk_mux_determine_rate_flags(struct clk_hw *hw, struct clk_rate_request *req, unsigned long flags); void clk_hw_reparent(struct clk_hw *hw, struct clk_hw *new_parent); +void clk_hw_get_rate_range(struct clk_hw *hw, unsigned long *min_rate, + unsigned long *max_rate); void clk_hw_set_rate_range(struct clk_hw *hw, unsigned long min_rate, unsigned long max_rate); diff --git a/include/linux/clk.h b/include/linux/clk.h index c13061cabdfc..1ef013324237 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -799,7 +799,7 @@ int clk_set_rate_exclusive(struct clk *clk, unsigned long rate); * * Returns true if @parent is a possible parent for @clk, false otherwise. */ -bool clk_has_parent(struct clk *clk, struct clk *parent); +bool clk_has_parent(const struct clk *clk, const struct clk *parent); /** * clk_set_rate_range - set a rate range for a clock source diff --git a/include/linux/clk/at91_pmc.h b/include/linux/clk/at91_pmc.h index 3484309b59bf..7af499bdbecb 100644 --- a/include/linux/clk/at91_pmc.h +++ b/include/linux/clk/at91_pmc.h @@ -12,6 +12,8 @@ #ifndef AT91_PMC_H #define AT91_PMC_H +#include <linux/bits.h> + #define AT91_PMC_V1 (1) /* PMC version 1 */ #define AT91_PMC_V2 (2) /* PMC version 2 [SAM9X60] */ @@ -45,8 +47,8 @@ #define AT91_PMC_PCSR 0x18 /* Peripheral Clock Status Register */ #define AT91_PMC_PLL_ACR 0x18 /* PLL Analog Control Register [for SAM9X60] */ -#define AT91_PMC_PLL_ACR_DEFAULT_UPLL 0x12020010UL /* Default PLL ACR value for UPLL */ -#define AT91_PMC_PLL_ACR_DEFAULT_PLLA 0x00020010UL /* Default PLL ACR value for PLLA */ +#define AT91_PMC_PLL_ACR_DEFAULT_UPLL UL(0x12020010) /* Default PLL ACR value for UPLL */ +#define AT91_PMC_PLL_ACR_DEFAULT_PLLA UL(0x00020010) /* Default PLL ACR value for PLLA */ #define AT91_PMC_PLL_ACR_UTMIVR (1 << 12) /* UPLL Voltage regulator Control */ #define AT91_PMC_PLL_ACR_UTMIBG (1 << 13) /* UPLL Bandgap Control */ diff --git a/include/linux/clk/spear.h b/include/linux/clk/spear.h index a64d034ceddd..eaf95ca656f8 100644 --- a/include/linux/clk/spear.h +++ b/include/linux/clk/spear.h @@ -8,6 +8,20 @@ #ifndef __LINUX_CLK_SPEAR_H #define __LINUX_CLK_SPEAR_H +#ifdef CONFIG_ARCH_SPEAR3XX +void __init spear3xx_clk_init(void __iomem *misc_base, + void __iomem *soc_config_base); +#else +static inline void __init spear3xx_clk_init(void __iomem *misc_base, + void __iomem *soc_config_base) {} +#endif + +#ifdef CONFIG_ARCH_SPEAR6XX +void __init spear6xx_clk_init(void __iomem *misc_base); +#else +static inline void __init spear6xx_clk_init(void __iomem *misc_base) {} +#endif + #ifdef CONFIG_MACH_SPEAR1310 void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base); #else diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index 42e55579d649..6cfd6902bd5b 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -51,6 +51,29 @@ #define __no_sanitize_undefined #endif +#if __has_feature(memory_sanitizer) +#define __SANITIZE_MEMORY__ +/* + * Unlike other sanitizers, KMSAN still inserts code into functions marked with + * no_sanitize("kernel-memory"). Using disable_sanitizer_instrumentation + * provides the behavior consistent with other __no_sanitize_ attributes, + * guaranteeing that __no_sanitize_memory functions remain uninstrumented. + */ +#define __no_sanitize_memory __disable_sanitizer_instrumentation + +/* + * The __no_kmsan_checks attribute ensures that a function does not produce + * false positive reports by: + * - initializing all local variables and memory stores in this function; + * - skipping all shadow checks; + * - passing initialized arguments to this function's callees. + */ +#define __no_kmsan_checks __attribute__((no_sanitize("kernel-memory"))) +#else +#define __no_sanitize_memory +#define __no_kmsan_checks +#endif + /* * Support for __has_feature(coverage_sanitizer) was added in Clang 13 together * with no_sanitize("coverage"). Prior versions of Clang support coverage diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 9b157b71036f..f55a37efdb97 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -115,6 +115,12 @@ #endif /* + * GCC does not support KMSAN. + */ +#define __no_sanitize_memory +#define __no_kmsan_checks + +/* * Turn individual warnings and errors on and off locally, depending * on version. */ diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index fc93c9488c76..898b3458b24a 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -35,7 +35,8 @@ /* * Note: do not use this directly. Instead, use __alloc_size() since it is conditionally - * available and includes other attributes. + * available and includes other attributes. For GCC < 9.1, __alloc_size__ gets undefined + * in compiler-gcc.h, due to misbehaviors. * * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-alloc_005fsize-function-attribute * clang: https://clang.llvm.org/docs/AttributeReference.html#alloc-size diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index d9d98e8a9a3b..eb0466236661 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -233,7 +233,8 @@ struct ftrace_likely_data { /* Section for code which can't be instrumented at all */ #define noinstr \ noinline notrace __attribute((__section__(".noinstr.text"))) \ - __no_kcsan __no_sanitize_address __no_profile __no_sanitize_coverage + __no_kcsan __no_sanitize_address __no_profile __no_sanitize_coverage \ + __no_sanitize_memory #endif /* __KERNEL__ */ @@ -271,14 +272,16 @@ struct ftrace_likely_data { /* * Any place that could be marked with the "alloc_size" attribute is also - * a place to be marked with the "malloc" attribute. Do this as part of the - * __alloc_size macro to avoid redundant attributes and to avoid missing a - * __malloc marking. + * a place to be marked with the "malloc" attribute, except those that may + * be performing a _reallocation_, as that may alias the existing pointer. + * For these, use __realloc_size(). */ #ifdef __alloc_size__ # define __alloc_size(x, ...) __alloc_size__(x, ## __VA_ARGS__) __malloc +# define __realloc_size(x, ...) __alloc_size__(x, ## __VA_ARGS__) #else # define __alloc_size(x, ...) __malloc +# define __realloc_size(x, ...) #endif #ifndef asm_volatile_goto diff --git a/include/linux/completion.h b/include/linux/completion.h index 51d9ab079629..62b32b19e0a8 100644 --- a/include/linux/completion.h +++ b/include/linux/completion.h @@ -103,6 +103,7 @@ extern void wait_for_completion(struct completion *); extern void wait_for_completion_io(struct completion *); extern int wait_for_completion_interruptible(struct completion *x); extern int wait_for_completion_killable(struct completion *x); +extern int wait_for_completion_state(struct completion *x, unsigned int state); extern unsigned long wait_for_completion_timeout(struct completion *x, unsigned long timeout); extern unsigned long wait_for_completion_io_timeout(struct completion *x, diff --git a/include/linux/counter.h b/include/linux/counter.h index c41fa602ed28..b63746637de2 100644 --- a/include/linux/counter.h +++ b/include/linux/counter.h @@ -542,11 +542,10 @@ struct counter_array { #define DEFINE_COUNTER_ARRAY_CAPTURE(_name, _length) \ DEFINE_COUNTER_ARRAY_U64(_name, _length) -#define DEFINE_COUNTER_ARRAY_POLARITY(_name, _enums, _length) \ - DEFINE_COUNTER_AVAILABLE(_name##_available, _enums); \ +#define DEFINE_COUNTER_ARRAY_POLARITY(_name, _available, _length) \ struct counter_array _name = { \ .type = COUNTER_COMP_SIGNAL_POLARITY, \ - .avail = &(_name##_available), \ + .avail = &(_available), \ .length = (_length), \ } diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index e8ad12b5b9d2..c2aa0aa26b45 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -35,19 +35,23 @@ typedef struct cpumask { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t; */ #define cpumask_pr_args(maskp) nr_cpu_ids, cpumask_bits(maskp) -#if NR_CPUS == 1 -#define nr_cpu_ids 1U +#if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS) +#define nr_cpu_ids ((unsigned int)NR_CPUS) #else extern unsigned int nr_cpu_ids; #endif -#ifdef CONFIG_CPUMASK_OFFSTACK -/* Assuming NR_CPUS is huge, a runtime limit is more efficient. Also, - * not all bits may be allocated. */ -#define nr_cpumask_bits nr_cpu_ids +static inline void set_nr_cpu_ids(unsigned int nr) +{ +#if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS) + WARN_ON(nr != nr_cpu_ids); #else -#define nr_cpumask_bits ((unsigned int)NR_CPUS) + nr_cpu_ids = nr; #endif +} + +/* Deprecated. Always use nr_cpu_ids. */ +#define nr_cpumask_bits nr_cpu_ids /* * The following particular system cpumasks and operations manage @@ -67,10 +71,6 @@ extern unsigned int nr_cpu_ids; * cpu_online_mask is the dynamic subset of cpu_present_mask, * indicating those CPUs available for scheduling. * - * If HOTPLUG is enabled, then cpu_possible_mask is forced to have - * all NR_CPUS bits set, otherwise it is just the set of CPUs that - * ACPI reports present at boot. - * * If HOTPLUG is enabled, then cpu_present_mask varies dynamically, * depending on what ACPI reports as currently plugged in, otherwise * cpu_present_mask is just a copy of cpu_possible_mask. @@ -246,9 +246,7 @@ unsigned int cpumask_next_and(int n, const struct cpumask *src1p, * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu(cpu, mask) \ - for ((cpu) = -1; \ - (cpu) = cpumask_next((cpu), (mask)), \ - (cpu) < nr_cpu_ids;) + for_each_set_bit(cpu, cpumask_bits(mask), nr_cpumask_bits) /** * for_each_cpu_not - iterate over every cpu in a complemented mask @@ -258,9 +256,7 @@ unsigned int cpumask_next_and(int n, const struct cpumask *src1p, * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_not(cpu, mask) \ - for ((cpu) = -1; \ - (cpu) = cpumask_next_zero((cpu), (mask)), \ - (cpu) < nr_cpu_ids;) + for_each_clear_bit(cpu, cpumask_bits(mask), nr_cpumask_bits) #if NR_CPUS == 1 static inline @@ -293,10 +289,8 @@ unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int sta * * After the loop, cpu is >= nr_cpu_ids. */ -#define for_each_cpu_wrap(cpu, mask, start) \ - for ((cpu) = cpumask_next_wrap((start)-1, (mask), (start), false); \ - (cpu) < nr_cpumask_bits; \ - (cpu) = cpumask_next_wrap((cpu), (mask), (start), true)) +#define for_each_cpu_wrap(cpu, mask, start) \ + for_each_set_bit_wrap(cpu, cpumask_bits(mask), nr_cpumask_bits, start) /** * for_each_cpu_and - iterate over every cpu in both masks @@ -313,9 +307,25 @@ unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int sta * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_and(cpu, mask1, mask2) \ - for ((cpu) = -1; \ - (cpu) = cpumask_next_and((cpu), (mask1), (mask2)), \ - (cpu) < nr_cpu_ids;) + for_each_and_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), nr_cpumask_bits) + +/** + * for_each_cpu_andnot - iterate over every cpu present in one mask, excluding + * those present in another. + * @cpu: the (optionally unsigned) integer iterator + * @mask1: the first cpumask pointer + * @mask2: the second cpumask pointer + * + * This saves a temporary CPU mask in many places. It is equivalent to: + * struct cpumask tmp; + * cpumask_andnot(&tmp, &mask1, &mask2); + * for_each_cpu(cpu, &tmp) + * ... + * + * After the loop, cpu is >= nr_cpu_ids. + */ +#define for_each_cpu_andnot(cpu, mask1, mask2) \ + for_each_andnot_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), nr_cpumask_bits) /** * cpumask_any_but - return a "random" in a cpumask, but not this one. @@ -337,6 +347,50 @@ unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) return i; } +/** + * cpumask_nth - get the first cpu in a cpumask + * @srcp: the cpumask pointer + * @cpu: the N'th cpu to find, starting from 0 + * + * Returns >= nr_cpu_ids if such cpu doesn't exist. + */ +static inline unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *srcp) +{ + return find_nth_bit(cpumask_bits(srcp), nr_cpumask_bits, cpumask_check(cpu)); +} + +/** + * cpumask_nth_and - get the first cpu in 2 cpumasks + * @srcp1: the cpumask pointer + * @srcp2: the cpumask pointer + * @cpu: the N'th cpu to find, starting from 0 + * + * Returns >= nr_cpu_ids if such cpu doesn't exist. + */ +static inline +unsigned int cpumask_nth_and(unsigned int cpu, const struct cpumask *srcp1, + const struct cpumask *srcp2) +{ + return find_nth_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), + nr_cpumask_bits, cpumask_check(cpu)); +} + +/** + * cpumask_nth_andnot - get the first cpu set in 1st cpumask, and clear in 2nd. + * @srcp1: the cpumask pointer + * @srcp2: the cpumask pointer + * @cpu: the N'th cpu to find, starting from 0 + * + * Returns >= nr_cpu_ids if such cpu doesn't exist. + */ +static inline +unsigned int cpumask_nth_andnot(unsigned int cpu, const struct cpumask *srcp1, + const struct cpumask *srcp2) +{ + return find_nth_andnot_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), + nr_cpumask_bits, cpumask_check(cpu)); +} + #define CPU_BITS_NONE \ { \ [0 ... BITS_TO_LONGS(NR_CPUS)-1] = 0UL \ @@ -587,6 +641,17 @@ static inline unsigned int cpumask_weight(const struct cpumask *srcp) } /** + * cpumask_weight_and - Count of bits in (*srcp1 & *srcp2) + * @srcp1: the cpumask to count bits (< nr_cpu_ids) in. + * @srcp2: the cpumask to count bits (< nr_cpu_ids) in. + */ +static inline unsigned int cpumask_weight_and(const struct cpumask *srcp1, + const struct cpumask *srcp2) +{ + return bitmap_weight_and(cpumask_bits(srcp1), cpumask_bits(srcp2), nr_cpumask_bits); +} + +/** * cpumask_shift_right - *dstp = *srcp >> n * @dstp: the cpumask result * @srcp: the input to shift diff --git a/include/linux/damon.h b/include/linux/damon.h index 7b1f4a488230..620ada094c3b 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -216,13 +216,26 @@ struct damos_stat { }; /** - * struct damos - Represents a Data Access Monitoring-based Operation Scheme. + * struct damos_access_pattern - Target access pattern of the given scheme. * @min_sz_region: Minimum size of target regions. * @max_sz_region: Maximum size of target regions. * @min_nr_accesses: Minimum ``->nr_accesses`` of target regions. * @max_nr_accesses: Maximum ``->nr_accesses`` of target regions. * @min_age_region: Minimum age of target regions. * @max_age_region: Maximum age of target regions. + */ +struct damos_access_pattern { + unsigned long min_sz_region; + unsigned long max_sz_region; + unsigned int min_nr_accesses; + unsigned int max_nr_accesses; + unsigned int min_age_region; + unsigned int max_age_region; +}; + +/** + * struct damos - Represents a Data Access Monitoring-based Operation Scheme. + * @pattern: Access pattern of target regions. * @action: &damo_action to be applied to the target regions. * @quota: Control the aggressiveness of this scheme. * @wmarks: Watermarks for automated (in)activation of this scheme. @@ -230,10 +243,8 @@ struct damos_stat { * @list: List head for siblings. * * For each aggregation interval, DAMON finds regions which fit in the - * condition (&min_sz_region, &max_sz_region, &min_nr_accesses, - * &max_nr_accesses, &min_age_region, &max_age_region) and applies &action to - * those. To avoid consuming too much CPU time or IO resources for the - * &action, "a is used. + * &pattern and applies &action to those. To avoid consuming too much + * CPU time or IO resources for the &action, "a is used. * * To do the work only when needed, schemes can be activated for specific * system situations using &wmarks. If all schemes that registered to the @@ -248,12 +259,7 @@ struct damos_stat { * &action is applied. */ struct damos { - unsigned long min_sz_region; - unsigned long max_sz_region; - unsigned int min_nr_accesses; - unsigned int max_nr_accesses; - unsigned int min_age_region; - unsigned int max_age_region; + struct damos_access_pattern pattern; enum damos_action action; struct damos_quota quota; struct damos_watermarks wmarks; @@ -340,7 +346,7 @@ struct damon_operations { unsigned long (*apply_scheme)(struct damon_ctx *context, struct damon_target *t, struct damon_region *r, struct damos *scheme); - bool (*target_valid)(void *target); + bool (*target_valid)(struct damon_target *t); void (*cleanup)(struct damon_ctx *context); }; @@ -383,13 +389,15 @@ struct damon_callback { }; /** - * struct damon_ctx - Represents a context for each monitoring. This is the - * main interface that allows users to set the attributes and get the results - * of the monitoring. + * struct damon_attrs - Monitoring attributes for accuracy/overhead control. * * @sample_interval: The time between access samplings. * @aggr_interval: The time between monitor results aggregations. * @ops_update_interval: The time between monitoring operations updates. + * @min_nr_regions: The minimum number of adaptive monitoring + * regions. + * @max_nr_regions: The maximum number of adaptive monitoring + * regions. * * For each @sample_interval, DAMON checks whether each region is accessed or * not. It aggregates and keeps the access information (number of accesses to @@ -399,7 +407,21 @@ struct damon_callback { * @ops_update_interval. All time intervals are in micro-seconds. * Please refer to &struct damon_operations and &struct damon_callback for more * detail. + */ +struct damon_attrs { + unsigned long sample_interval; + unsigned long aggr_interval; + unsigned long ops_update_interval; + unsigned long min_nr_regions; + unsigned long max_nr_regions; +}; + +/** + * struct damon_ctx - Represents a context for each monitoring. This is the + * main interface that allows users to set the attributes and get the results + * of the monitoring. * + * @attrs: Monitoring attributes for accuracy/overhead control. * @kdamond: Kernel thread who does the monitoring. * @kdamond_lock: Mutex for the synchronizations with @kdamond. * @@ -421,15 +443,11 @@ struct damon_callback { * @ops: Set of monitoring operations for given use cases. * @callback: Set of callbacks for monitoring events notifications. * - * @min_nr_regions: The minimum number of adaptive monitoring regions. - * @max_nr_regions: The maximum number of adaptive monitoring regions. * @adaptive_targets: Head of monitoring targets (&damon_target) list. * @schemes: Head of schemes (&damos) list. */ struct damon_ctx { - unsigned long sample_interval; - unsigned long aggr_interval; - unsigned long ops_update_interval; + struct damon_attrs attrs; /* private: internal use only */ struct timespec64 last_aggregation; @@ -442,8 +460,6 @@ struct damon_ctx { struct damon_operations ops; struct damon_callback callback; - unsigned long min_nr_regions; - unsigned long max_nr_regions; struct list_head adaptive_targets; struct list_head schemes; }; @@ -463,9 +479,23 @@ static inline struct damon_region *damon_last_region(struct damon_target *t) return list_last_entry(&t->regions_list, struct damon_region, list); } +static inline struct damon_region *damon_first_region(struct damon_target *t) +{ + return list_first_entry(&t->regions_list, struct damon_region, list); +} + +static inline unsigned long damon_sz_region(struct damon_region *r) +{ + return r->ar.end - r->ar.start; +} + + #define damon_for_each_region(r, t) \ list_for_each_entry(r, &t->regions_list, list) +#define damon_for_each_region_from(r, t) \ + list_for_each_entry_from(r, &t->regions_list, list) + #define damon_for_each_region_safe(r, next, t) \ list_for_each_entry_safe(r, next, &t->regions_list, list) @@ -501,12 +531,9 @@ void damon_destroy_region(struct damon_region *r, struct damon_target *t); int damon_set_regions(struct damon_target *t, struct damon_addr_range *ranges, unsigned int nr_ranges); -struct damos *damon_new_scheme( - unsigned long min_sz_region, unsigned long max_sz_region, - unsigned int min_nr_accesses, unsigned int max_nr_accesses, - unsigned int min_age_region, unsigned int max_age_region, - enum damos_action action, struct damos_quota *quota, - struct damos_watermarks *wmarks); +struct damos *damon_new_scheme(struct damos_access_pattern *pattern, + enum damos_action action, struct damos_quota *quota, + struct damos_watermarks *wmarks); void damon_add_scheme(struct damon_ctx *ctx, struct damos *s); void damon_destroy_scheme(struct damos *s); @@ -519,10 +546,8 @@ unsigned int damon_nr_regions(struct damon_target *t); struct damon_ctx *damon_new_ctx(void); void damon_destroy_ctx(struct damon_ctx *ctx); -int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int, - unsigned long aggr_int, unsigned long ops_upd_int, - unsigned long min_nr_reg, unsigned long max_nr_reg); -int damon_set_schemes(struct damon_ctx *ctx, +int damon_set_attrs(struct damon_ctx *ctx, struct damon_attrs *attrs); +void damon_set_schemes(struct damon_ctx *ctx, struct damos **schemes, ssize_t nr_schemes); int damon_nr_running_ctxs(void); bool damon_is_registered_ops(enum damon_ops_id id); @@ -538,6 +563,9 @@ static inline bool damon_target_has_pid(const struct damon_ctx *ctx) int damon_start(struct damon_ctx **ctxs, int nr_ctxs, bool exclusive); int damon_stop(struct damon_ctx **ctxs, int nr_ctxs); +int damon_set_region_biggest_system_ram_default(struct damon_target *t, + unsigned long *start, unsigned long *end); + #endif /* CONFIG_DAMON */ #endif /* _DAMON_H */ diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 54d46518c481..6b351e009f59 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -16,6 +16,7 @@ #include <linux/wait.h> struct path; +struct file; struct vfsmount; /* @@ -250,7 +251,7 @@ extern struct dentry * d_make_root(struct inode *); /* <clickety>-<click> the ramfs-type tree */ extern void d_genocide(struct dentry *); -extern void d_tmpfile(struct dentry *, struct inode *); +extern void d_tmpfile(struct file *, struct inode *); extern struct dentry *d_find_alias(struct inode *); extern void d_prune_aliases(struct inode *); diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index 58aea2d7385c..0da97dba9ef8 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -73,8 +73,8 @@ extern int delayacct_add_tsk(struct taskstats *, struct task_struct *); extern __u64 __delayacct_blkio_ticks(struct task_struct *); extern void __delayacct_freepages_start(void); extern void __delayacct_freepages_end(void); -extern void __delayacct_thrashing_start(void); -extern void __delayacct_thrashing_end(void); +extern void __delayacct_thrashing_start(bool *in_thrashing); +extern void __delayacct_thrashing_end(bool *in_thrashing); extern void __delayacct_swapin_start(void); extern void __delayacct_swapin_end(void); extern void __delayacct_compact_start(void); @@ -143,22 +143,22 @@ static inline void delayacct_freepages_end(void) __delayacct_freepages_end(); } -static inline void delayacct_thrashing_start(void) +static inline void delayacct_thrashing_start(bool *in_thrashing) { if (!static_branch_unlikely(&delayacct_key)) return; if (current->delays) - __delayacct_thrashing_start(); + __delayacct_thrashing_start(in_thrashing); } -static inline void delayacct_thrashing_end(void) +static inline void delayacct_thrashing_end(bool *in_thrashing) { if (!static_branch_unlikely(&delayacct_key)) return; if (current->delays) - __delayacct_thrashing_end(); + __delayacct_thrashing_end(in_thrashing); } static inline void delayacct_swapin_start(void) @@ -237,9 +237,9 @@ static inline void delayacct_freepages_start(void) {} static inline void delayacct_freepages_end(void) {} -static inline void delayacct_thrashing_start(void) +static inline void delayacct_thrashing_start(bool *in_thrashing) {} -static inline void delayacct_thrashing_end(void) +static inline void delayacct_thrashing_end(bool *in_thrashing) {} static inline void delayacct_swapin_start(void) {} diff --git a/include/linux/dma-iommu.h b/include/linux/dma-iommu.h deleted file mode 100644 index 24607dc3c2ac..000000000000 --- a/include/linux/dma-iommu.h +++ /dev/null @@ -1,93 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2014-2015 ARM Ltd. - */ -#ifndef __DMA_IOMMU_H -#define __DMA_IOMMU_H - -#include <linux/errno.h> -#include <linux/types.h> - -#ifdef CONFIG_IOMMU_DMA -#include <linux/dma-mapping.h> -#include <linux/iommu.h> -#include <linux/msi.h> - -/* Domain management interface for IOMMU drivers */ -int iommu_get_dma_cookie(struct iommu_domain *domain); -int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base); -void iommu_put_dma_cookie(struct iommu_domain *domain); - -/* Setup call for arch DMA mapping code */ -void iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 dma_limit); -int iommu_dma_init_fq(struct iommu_domain *domain); - -/* The DMA API isn't _quite_ the whole story, though... */ -/* - * iommu_dma_prepare_msi() - Map the MSI page in the IOMMU device - * - * The MSI page will be stored in @desc. - * - * Return: 0 on success otherwise an error describing the failure. - */ -int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr); - -/* Update the MSI message if required. */ -void iommu_dma_compose_msi_msg(struct msi_desc *desc, - struct msi_msg *msg); - -void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list); - -void iommu_dma_free_cpu_cached_iovas(unsigned int cpu, - struct iommu_domain *domain); - -extern bool iommu_dma_forcedac; - -#else /* CONFIG_IOMMU_DMA */ - -struct iommu_domain; -struct msi_desc; -struct msi_msg; -struct device; - -static inline void iommu_setup_dma_ops(struct device *dev, u64 dma_base, - u64 dma_limit) -{ -} - -static inline int iommu_dma_init_fq(struct iommu_domain *domain) -{ - return -EINVAL; -} - -static inline int iommu_get_dma_cookie(struct iommu_domain *domain) -{ - return -ENODEV; -} - -static inline int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base) -{ - return -ENODEV; -} - -static inline void iommu_put_dma_cookie(struct iommu_domain *domain) -{ -} - -static inline int iommu_dma_prepare_msi(struct msi_desc *desc, - phys_addr_t msi_addr) -{ - return 0; -} - -static inline void iommu_dma_compose_msi_msg(struct msi_desc *desc, - struct msi_msg *msg) -{ -} - -static inline void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list) -{ -} - -#endif /* CONFIG_IOMMU_DMA */ -#endif /* __DMA_IOMMU_H */ diff --git a/include/linux/dsa/tag_qca.h b/include/linux/dsa/tag_qca.h index 50be7cbd93a5..b1b5720d89a5 100644 --- a/include/linux/dsa/tag_qca.h +++ b/include/linux/dsa/tag_qca.h @@ -61,9 +61,9 @@ struct sk_buff; /* Special struct emulating a Ethernet header */ struct qca_mgmt_ethhdr { - u32 command; /* command bit 31:0 */ - u32 seq; /* seq 63:32 */ - u32 mdio_data; /* first 4byte mdio */ + __le32 command; /* command bit 31:0 */ + __le32 seq; /* seq 63:32 */ + __le32 mdio_data; /* first 4byte mdio */ __be16 hdr; /* qca hdr */ } __packed; @@ -73,7 +73,7 @@ enum mdio_cmd { }; struct mib_ethhdr { - u32 data[3]; /* first 3 mib counter */ + __le32 data[3]; /* first 3 mib counter */ __be16 hdr; /* qca hdr */ } __packed; diff --git a/include/linux/efi.h b/include/linux/efi.h index da3974bf05d3..7603fc58c47c 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -389,6 +389,7 @@ void efi_native_runtime_setup(void); #define EFI_LOAD_FILE2_PROTOCOL_GUID EFI_GUID(0x4006c0c1, 0xfcb3, 0x403e, 0x99, 0x6d, 0x4a, 0x6c, 0x87, 0x24, 0xe0, 0x6d) #define EFI_RT_PROPERTIES_TABLE_GUID EFI_GUID(0xeb66918a, 0x7eef, 0x402a, 0x84, 0x2e, 0x93, 0x1d, 0x21, 0xc3, 0x8a, 0xe9) #define EFI_DXE_SERVICES_TABLE_GUID EFI_GUID(0x05ad34ba, 0x6f02, 0x4214, 0x95, 0x2e, 0x4d, 0xa0, 0x39, 0x8e, 0x2b, 0xb9) +#define EFI_SMBIOS_PROTOCOL_GUID EFI_GUID(0x03583ff6, 0xcb36, 0x4940, 0x94, 0x7e, 0xb9, 0xb3, 0x9f, 0x4a, 0xfa, 0xf7) #define EFI_IMAGE_SECURITY_DATABASE_GUID EFI_GUID(0xd719b2cb, 0x3d3a, 0x4596, 0xa3, 0xbc, 0xda, 0xd0, 0x0e, 0x67, 0x65, 0x6f) #define EFI_SHIM_LOCK_GUID EFI_GUID(0x605dab50, 0xe046, 0x4300, 0xab, 0xb6, 0x3d, 0xd8, 0x10, 0xdd, 0x8b, 0x23) @@ -1085,9 +1086,6 @@ efi_status_t efivar_set_variable_locked(efi_char16_t *name, efi_guid_t *vendor, efi_status_t efivar_set_variable(efi_char16_t *name, efi_guid_t *vendor, u32 attr, unsigned long data_size, void *data); -efi_status_t check_var_size(u32 attributes, unsigned long size); -efi_status_t check_var_size_nonblocking(u32 attributes, unsigned long size); - #if IS_ENABLED(CONFIG_EFI_CAPSULE_LOADER) extern bool efi_capsule_pending(int *reset_type); @@ -1225,7 +1223,7 @@ efi_status_t efi_random_get_seed(void); arch_efi_call_virt_teardown(); \ }) -#define EFI_RANDOM_SEED_SIZE 64U +#define EFI_RANDOM_SEED_SIZE 32U // BLAKE2S_HASH_SIZE struct linux_efi_random_seed { u32 size; diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h index 84a466b176cf..d95ab85f96ba 100644 --- a/include/linux/entry-common.h +++ b/include/linux/entry-common.h @@ -253,7 +253,6 @@ static __always_inline void arch_exit_to_user_mode(void) { } /** * arch_do_signal_or_restart - Architecture specific signal delivery function * @regs: Pointer to currents pt_regs - * @has_signal: actual signal to handle * * Invoked from exit_to_user_mode_loop(). */ diff --git a/include/linux/export-internal.h b/include/linux/export-internal.h index c2b1d4fd5987..fe7e6ba918f1 100644 --- a/include/linux/export-internal.h +++ b/include/linux/export-internal.h @@ -10,8 +10,10 @@ #include <linux/compiler.h> #include <linux/types.h> -/* __used is needed to keep __crc_* for LTO */ #define SYMBOL_CRC(sym, crc, sec) \ - u32 __section("___kcrctab" sec "+" #sym) __used __crc_##sym = crc + asm(".section \"___kcrctab" sec "+" #sym "\",\"a\"" "\n" \ + "__crc_" #sym ":" "\n" \ + ".long " #crc "\n" \ + ".previous" "\n") #endif /* __LINUX_EXPORT_INTERNAL_H__ */ diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index d445150c5350..ee0d75d9a302 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -73,6 +73,42 @@ struct f2fs_device { __le32 total_segments; } __packed; +/* reason of stop_checkpoint */ +enum stop_cp_reason { + STOP_CP_REASON_SHUTDOWN, + STOP_CP_REASON_FAULT_INJECT, + STOP_CP_REASON_META_PAGE, + STOP_CP_REASON_WRITE_FAIL, + STOP_CP_REASON_CORRUPTED_SUMMARY, + STOP_CP_REASON_UPDATE_INODE, + STOP_CP_REASON_FLUSH_FAIL, + STOP_CP_REASON_MAX, +}; + +#define MAX_STOP_REASON 32 + +/* detail reason for EFSCORRUPTED */ +enum f2fs_error { + ERROR_CORRUPTED_CLUSTER, + ERROR_FAIL_DECOMPRESSION, + ERROR_INVALID_BLKADDR, + ERROR_CORRUPTED_DIRENT, + ERROR_CORRUPTED_INODE, + ERROR_INCONSISTENT_SUMMARY, + ERROR_INCONSISTENT_FOOTER, + ERROR_INCONSISTENT_SUM_TYPE, + ERROR_CORRUPTED_JOURNAL, + ERROR_INCONSISTENT_NODE_COUNT, + ERROR_INCONSISTENT_BLOCK_COUNT, + ERROR_INVALID_CURSEG, + ERROR_INCONSISTENT_SIT, + ERROR_CORRUPTED_VERITY_XATTR, + ERROR_CORRUPTED_XATTR, + ERROR_MAX, +}; + +#define MAX_F2FS_ERRORS 16 + struct f2fs_super_block { __le32 magic; /* Magic Number */ __le16 major_ver; /* Major Version */ @@ -116,7 +152,9 @@ struct f2fs_super_block { __u8 hot_ext_count; /* # of hot file extension */ __le16 s_encoding; /* Filename charset encoding */ __le16 s_encoding_flags; /* Filename charset encoding flags */ - __u8 reserved[306]; /* valid reserved region */ + __u8 s_stop_reason[MAX_STOP_REASON]; /* stop checkpoint reason */ + __u8 s_errors[MAX_F2FS_ERRORS]; /* reason of image corrupts */ + __u8 reserved[258]; /* valid reserved region */ __le32 crc; /* checksum of superblock */ } __packed; diff --git a/include/linux/fb.h b/include/linux/fb.h index 0aff76bcbb00..bcb8658f5b64 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -555,7 +555,7 @@ static inline struct apertures_struct *alloc_apertures(unsigned int max_num) { #elif defined(__i386__) || defined(__alpha__) || defined(__x86_64__) || \ defined(__hppa__) || defined(__sh__) || defined(__powerpc__) || \ - defined(__arm__) || defined(__aarch64__) + defined(__arm__) || defined(__aarch64__) || defined(__mips__) #define fb_readb __raw_readb #define fb_readw __raw_readw diff --git a/include/linux/find.h b/include/linux/find.h index 424ef67d4a42..ccaf61a0f5fd 100644 --- a/include/linux/find.h +++ b/include/linux/find.h @@ -8,15 +8,33 @@ #include <linux/bitops.h> -extern unsigned long _find_next_bit(const unsigned long *addr1, - const unsigned long *addr2, unsigned long nbits, - unsigned long start, unsigned long invert, unsigned long le); +unsigned long _find_next_bit(const unsigned long *addr1, unsigned long nbits, + unsigned long start); +unsigned long _find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long nbits, unsigned long start); +unsigned long _find_next_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long nbits, unsigned long start); +unsigned long _find_next_zero_bit(const unsigned long *addr, unsigned long nbits, + unsigned long start); extern unsigned long _find_first_bit(const unsigned long *addr, unsigned long size); +unsigned long __find_nth_bit(const unsigned long *addr, unsigned long size, unsigned long n); +unsigned long __find_nth_and_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long size, unsigned long n); +unsigned long __find_nth_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long size, unsigned long n); extern unsigned long _find_first_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size); extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size); extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long size); +#ifdef __BIG_ENDIAN +unsigned long _find_first_zero_bit_le(const unsigned long *addr, unsigned long size); +unsigned long _find_next_zero_bit_le(const unsigned long *addr, unsigned + long size, unsigned long offset); +unsigned long _find_next_bit_le(const unsigned long *addr, unsigned + long size, unsigned long offset); +#endif + #ifndef find_next_bit /** * find_next_bit - find the next set bit in a memory region @@ -41,7 +59,7 @@ unsigned long find_next_bit(const unsigned long *addr, unsigned long size, return val ? __ffs(val) : size; } - return _find_next_bit(addr, NULL, size, offset, 0UL, 0); + return _find_next_bit(addr, size, offset); } #endif @@ -71,7 +89,38 @@ unsigned long find_next_and_bit(const unsigned long *addr1, return val ? __ffs(val) : size; } - return _find_next_bit(addr1, addr2, size, offset, 0UL, 0); + return _find_next_and_bit(addr1, addr2, size, offset); +} +#endif + +#ifndef find_next_andnot_bit +/** + * find_next_andnot_bit - find the next set bit in *addr1 excluding all the bits + * in *addr2 + * @addr1: The first address to base the search on + * @addr2: The second address to base the search on + * @size: The bitmap size in bits + * @offset: The bitnumber to start searching at + * + * Returns the bit number for the next set bit + * If no bits are set, returns @size. + */ +static inline +unsigned long find_next_andnot_bit(const unsigned long *addr1, + const unsigned long *addr2, unsigned long size, + unsigned long offset) +{ + if (small_const_nbits(size)) { + unsigned long val; + + if (unlikely(offset >= size)) + return size; + + val = *addr1 & ~*addr2 & GENMASK(size - 1, offset); + return val ? __ffs(val) : size; + } + + return _find_next_andnot_bit(addr1, addr2, size, offset); } #endif @@ -99,7 +148,7 @@ unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, return val == ~0UL ? size : ffz(val); } - return _find_next_bit(addr, NULL, size, offset, ~0UL, 0); + return _find_next_zero_bit(addr, size, offset); } #endif @@ -125,6 +174,87 @@ unsigned long find_first_bit(const unsigned long *addr, unsigned long size) } #endif +/** + * find_nth_bit - find N'th set bit in a memory region + * @addr: The address to start the search at + * @size: The maximum number of bits to search + * @n: The number of set bit, which position is needed, counting from 0 + * + * The following is semantically equivalent: + * idx = find_nth_bit(addr, size, 0); + * idx = find_first_bit(addr, size); + * + * Returns the bit number of the N'th set bit. + * If no such, returns @size. + */ +static inline +unsigned long find_nth_bit(const unsigned long *addr, unsigned long size, unsigned long n) +{ + if (n >= size) + return size; + + if (small_const_nbits(size)) { + unsigned long val = *addr & GENMASK(size - 1, 0); + + return val ? fns(val, n) : size; + } + + return __find_nth_bit(addr, size, n); +} + +/** + * find_nth_and_bit - find N'th set bit in 2 memory regions + * @addr1: The 1st address to start the search at + * @addr2: The 2nd address to start the search at + * @size: The maximum number of bits to search + * @n: The number of set bit, which position is needed, counting from 0 + * + * Returns the bit number of the N'th set bit. + * If no such, returns @size. + */ +static inline +unsigned long find_nth_and_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long size, unsigned long n) +{ + if (n >= size) + return size; + + if (small_const_nbits(size)) { + unsigned long val = *addr1 & *addr2 & GENMASK(size - 1, 0); + + return val ? fns(val, n) : size; + } + + return __find_nth_and_bit(addr1, addr2, size, n); +} + +/** + * find_nth_andnot_bit - find N'th set bit in 2 memory regions, + * flipping bits in 2nd region + * @addr1: The 1st address to start the search at + * @addr2: The 2nd address to start the search at + * @size: The maximum number of bits to search + * @n: The number of set bit, which position is needed, counting from 0 + * + * Returns the bit number of the N'th set bit. + * If no such, returns @size. + */ +static inline +unsigned long find_nth_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long size, unsigned long n) +{ + if (n >= size) + return size; + + if (small_const_nbits(size)) { + unsigned long val = *addr1 & (~*addr2) & GENMASK(size - 1, 0); + + return val ? fns(val, n) : size; + } + + return __find_nth_andnot_bit(addr1, addr2, size, n); +} + #ifndef find_first_and_bit /** * find_first_and_bit - find the first set bit in both memory regions @@ -194,6 +324,78 @@ unsigned long find_last_bit(const unsigned long *addr, unsigned long size) #endif /** + * find_next_and_bit_wrap - find the next set bit in both memory regions + * @addr1: The first address to base the search on + * @addr2: The second address to base the search on + * @size: The bitmap size in bits + * @offset: The bitnumber to start searching at + * + * Returns the bit number for the next set bit, or first set bit up to @offset + * If no bits are set, returns @size. + */ +static inline +unsigned long find_next_and_bit_wrap(const unsigned long *addr1, + const unsigned long *addr2, + unsigned long size, unsigned long offset) +{ + unsigned long bit = find_next_and_bit(addr1, addr2, size, offset); + + if (bit < size) + return bit; + + bit = find_first_and_bit(addr1, addr2, offset); + return bit < offset ? bit : size; +} + +/** + * find_next_bit_wrap - find the next set bit in both memory regions + * @addr: The first address to base the search on + * @size: The bitmap size in bits + * @offset: The bitnumber to start searching at + * + * Returns the bit number for the next set bit, or first set bit up to @offset + * If no bits are set, returns @size. + */ +static inline +unsigned long find_next_bit_wrap(const unsigned long *addr, + unsigned long size, unsigned long offset) +{ + unsigned long bit = find_next_bit(addr, size, offset); + + if (bit < size) + return bit; + + bit = find_first_bit(addr, offset); + return bit < offset ? bit : size; +} + +/* + * Helper for for_each_set_bit_wrap(). Make sure you're doing right thing + * before using it alone. + */ +static inline +unsigned long __for_each_wrap(const unsigned long *bitmap, unsigned long size, + unsigned long start, unsigned long n) +{ + unsigned long bit; + + /* If not wrapped around */ + if (n > start) { + /* and have a bit, just return it. */ + bit = find_next_bit(bitmap, size, n); + if (bit < size) + return bit; + + /* Otherwise, wrap around and ... */ + n = 0; + } + + /* Search the other part. */ + bit = find_next_bit(bitmap, start, n); + return bit < start ? bit : size; +} + +/** * find_next_clump8 - find next 8-bit clump with set bits in a memory region * @clump: location to store copy of found clump * @addr: address to base the search on @@ -247,7 +449,21 @@ unsigned long find_next_zero_bit_le(const void *addr, unsigned return val == ~0UL ? size : ffz(val); } - return _find_next_bit(addr, NULL, size, offset, ~0UL, 1); + return _find_next_zero_bit_le(addr, size, offset); +} +#endif + +#ifndef find_first_zero_bit_le +static inline +unsigned long find_first_zero_bit_le(const void *addr, unsigned long size) +{ + if (small_const_nbits(size)) { + unsigned long val = swab(*(const unsigned long *)addr) | ~GENMASK(size - 1, 0); + + return val == ~0UL ? size : ffz(val); + } + + return _find_first_zero_bit_le(addr, size); } #endif @@ -266,40 +482,39 @@ unsigned long find_next_bit_le(const void *addr, unsigned return val ? __ffs(val) : size; } - return _find_next_bit(addr, NULL, size, offset, 0UL, 1); + return _find_next_bit_le(addr, size, offset); } #endif -#ifndef find_first_zero_bit_le -#define find_first_zero_bit_le(addr, size) \ - find_next_zero_bit_le((addr), (size), 0) -#endif - #else #error "Please fix <asm/byteorder.h>" #endif #define for_each_set_bit(bit, addr, size) \ - for ((bit) = find_next_bit((addr), (size), 0); \ - (bit) < (size); \ - (bit) = find_next_bit((addr), (size), (bit) + 1)) + for ((bit) = 0; (bit) = find_next_bit((addr), (size), (bit)), (bit) < (size); (bit)++) + +#define for_each_and_bit(bit, addr1, addr2, size) \ + for ((bit) = 0; \ + (bit) = find_next_and_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\ + (bit)++) + +#define for_each_andnot_bit(bit, addr1, addr2, size) \ + for ((bit) = 0; \ + (bit) = find_next_andnot_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\ + (bit)++) /* same as for_each_set_bit() but use bit as value to start with */ #define for_each_set_bit_from(bit, addr, size) \ - for ((bit) = find_next_bit((addr), (size), (bit)); \ - (bit) < (size); \ - (bit) = find_next_bit((addr), (size), (bit) + 1)) + for (; (bit) = find_next_bit((addr), (size), (bit)), (bit) < (size); (bit)++) #define for_each_clear_bit(bit, addr, size) \ - for ((bit) = find_next_zero_bit((addr), (size), 0); \ - (bit) < (size); \ - (bit) = find_next_zero_bit((addr), (size), (bit) + 1)) + for ((bit) = 0; \ + (bit) = find_next_zero_bit((addr), (size), (bit)), (bit) < (size); \ + (bit)++) /* same as for_each_clear_bit() but use bit as value to start with */ #define for_each_clear_bit_from(bit, addr, size) \ - for ((bit) = find_next_zero_bit((addr), (size), (bit)); \ - (bit) < (size); \ - (bit) = find_next_zero_bit((addr), (size), (bit) + 1)) + for (; (bit) = find_next_zero_bit((addr), (size), (bit)), (bit) < (size); (bit)++) /** * for_each_set_bitrange - iterate over all set bit ranges [b; e) @@ -309,11 +524,11 @@ unsigned long find_next_bit_le(const void *addr, unsigned * @size: bitmap size in number of bits */ #define for_each_set_bitrange(b, e, addr, size) \ - for ((b) = find_next_bit((addr), (size), 0), \ - (e) = find_next_zero_bit((addr), (size), (b) + 1); \ + for ((b) = 0; \ + (b) = find_next_bit((addr), (size), b), \ + (e) = find_next_zero_bit((addr), (size), (b) + 1), \ (b) < (size); \ - (b) = find_next_bit((addr), (size), (e) + 1), \ - (e) = find_next_zero_bit((addr), (size), (b) + 1)) + (b) = (e) + 1) /** * for_each_set_bitrange_from - iterate over all set bit ranges [b; e) @@ -323,11 +538,11 @@ unsigned long find_next_bit_le(const void *addr, unsigned * @size: bitmap size in number of bits */ #define for_each_set_bitrange_from(b, e, addr, size) \ - for ((b) = find_next_bit((addr), (size), (b)), \ - (e) = find_next_zero_bit((addr), (size), (b) + 1); \ + for (; \ + (b) = find_next_bit((addr), (size), (b)), \ + (e) = find_next_zero_bit((addr), (size), (b) + 1), \ (b) < (size); \ - (b) = find_next_bit((addr), (size), (e) + 1), \ - (e) = find_next_zero_bit((addr), (size), (b) + 1)) + (b) = (e) + 1) /** * for_each_clear_bitrange - iterate over all unset bit ranges [b; e) @@ -337,11 +552,11 @@ unsigned long find_next_bit_le(const void *addr, unsigned * @size: bitmap size in number of bits */ #define for_each_clear_bitrange(b, e, addr, size) \ - for ((b) = find_next_zero_bit((addr), (size), 0), \ - (e) = find_next_bit((addr), (size), (b) + 1); \ + for ((b) = 0; \ + (b) = find_next_zero_bit((addr), (size), (b)), \ + (e) = find_next_bit((addr), (size), (b) + 1), \ (b) < (size); \ - (b) = find_next_zero_bit((addr), (size), (e) + 1), \ - (e) = find_next_bit((addr), (size), (b) + 1)) + (b) = (e) + 1) /** * for_each_clear_bitrange_from - iterate over all unset bit ranges [b; e) @@ -351,11 +566,24 @@ unsigned long find_next_bit_le(const void *addr, unsigned * @size: bitmap size in number of bits */ #define for_each_clear_bitrange_from(b, e, addr, size) \ - for ((b) = find_next_zero_bit((addr), (size), (b)), \ - (e) = find_next_bit((addr), (size), (b) + 1); \ + for (; \ + (b) = find_next_zero_bit((addr), (size), (b)), \ + (e) = find_next_bit((addr), (size), (b) + 1), \ (b) < (size); \ - (b) = find_next_zero_bit((addr), (size), (e) + 1), \ - (e) = find_next_bit((addr), (size), (b) + 1)) + (b) = (e) + 1) + +/** + * for_each_set_bit_wrap - iterate over all set bits starting from @start, and + * wrapping around the end of bitmap. + * @bit: offset for current iteration + * @addr: bitmap address to base the search on + * @size: bitmap size in number of bits + * @start: Starting bit for bitmap traversing, wrapping around the bitmap end + */ +#define for_each_set_bit_wrap(bit, addr, size, start) \ + for ((bit) = find_next_bit_wrap((addr), (size), (start)); \ + (bit) < (size); \ + (bit) = __for_each_wrap((addr), (size), (start), (bit) + 1)) /** * for_each_set_clump8 - iterate over bitmap for each 8-bit clump with set bits diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index b62c90cfafaf..1067a8450826 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -43,11 +43,24 @@ extern __kernel_size_t __underlying_strlen(const char *p) __RENAME(strlen); extern char *__underlying_strncat(char *p, const char *q, __kernel_size_t count) __RENAME(strncat); extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) __RENAME(strncpy); #else -#define __underlying_memchr __builtin_memchr -#define __underlying_memcmp __builtin_memcmp + +#if defined(__SANITIZE_MEMORY__) +/* + * For KMSAN builds all memcpy/memset/memmove calls should be replaced by the + * corresponding __msan_XXX functions. + */ +#include <linux/kmsan_string.h> +#define __underlying_memcpy __msan_memcpy +#define __underlying_memmove __msan_memmove +#define __underlying_memset __msan_memset +#else #define __underlying_memcpy __builtin_memcpy #define __underlying_memmove __builtin_memmove #define __underlying_memset __builtin_memset +#endif + +#define __underlying_memchr __builtin_memchr +#define __underlying_memcmp __builtin_memcmp #define __underlying_strcat __builtin_strcat #define __underlying_strcpy __builtin_strcpy #define __underlying_strlen __builtin_strlen @@ -328,8 +341,10 @@ __FORTIFY_INLINE void fortify_memset_chk(__kernel_size_t size, * __struct_size() vs __member_size() must be captured here to avoid * evaluating argument side-effects further into the macro layers. */ +#ifndef CONFIG_KMSAN #define memset(p, c, s) __fortify_memset_chk(p, c, s, \ __struct_size(p), __member_size(p)) +#endif /* * To make sure the compiler can enforce protection against buffer overflows, @@ -439,13 +454,18 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size, #define __fortify_memcpy_chk(p, q, size, p_size, q_size, \ p_size_field, q_size_field, op) ({ \ - size_t __fortify_size = (size_t)(size); \ - WARN_ONCE(fortify_memcpy_chk(__fortify_size, p_size, q_size, \ - p_size_field, q_size_field, #op), \ + const size_t __fortify_size = (size_t)(size); \ + const size_t __p_size = (p_size); \ + const size_t __q_size = (q_size); \ + const size_t __p_size_field = (p_size_field); \ + const size_t __q_size_field = (q_size_field); \ + WARN_ONCE(fortify_memcpy_chk(__fortify_size, __p_size, \ + __q_size, __p_size_field, \ + __q_size_field, #op), \ #op ": detected field-spanning write (size %zu) of single %s (size %zu)\n", \ __fortify_size, \ "field \"" #p "\" at " __FILE__ ":" __stringify(__LINE__), \ - p_size_field); \ + __p_size_field); \ __underlying_##op(p, q, __fortify_size); \ }) diff --git a/include/linux/freezer.h b/include/linux/freezer.h index 0621c5f86c39..b303472255be 100644 --- a/include/linux/freezer.h +++ b/include/linux/freezer.h @@ -8,9 +8,11 @@ #include <linux/sched.h> #include <linux/wait.h> #include <linux/atomic.h> +#include <linux/jump_label.h> #ifdef CONFIG_FREEZER -extern atomic_t system_freezing_cnt; /* nr of freezing conds in effect */ +DECLARE_STATIC_KEY_FALSE(freezer_active); + extern bool pm_freezing; /* PM freezing in effect */ extern bool pm_nosig_freezing; /* PM nosig freezing in effect */ @@ -22,10 +24,7 @@ extern unsigned int freeze_timeout_msecs; /* * Check if a process has been frozen */ -static inline bool frozen(struct task_struct *p) -{ - return p->flags & PF_FROZEN; -} +extern bool frozen(struct task_struct *p); extern bool freezing_slow_path(struct task_struct *p); @@ -34,9 +33,10 @@ extern bool freezing_slow_path(struct task_struct *p); */ static inline bool freezing(struct task_struct *p) { - if (likely(!atomic_read(&system_freezing_cnt))) - return false; - return freezing_slow_path(p); + if (static_branch_unlikely(&freezer_active)) + return freezing_slow_path(p); + + return false; } /* Takes and releases task alloc lock using task_lock() */ @@ -48,23 +48,14 @@ extern int freeze_kernel_threads(void); extern void thaw_processes(void); extern void thaw_kernel_threads(void); -/* - * DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION - * If try_to_freeze causes a lockdep warning it means the caller may deadlock - */ -static inline bool try_to_freeze_unsafe(void) +static inline bool try_to_freeze(void) { might_sleep(); if (likely(!freezing(current))) return false; - return __refrigerator(false); -} - -static inline bool try_to_freeze(void) -{ if (!(current->flags & PF_NOFREEZE)) debug_check_no_locks_held(); - return try_to_freeze_unsafe(); + return __refrigerator(false); } extern bool freeze_task(struct task_struct *p); @@ -79,195 +70,6 @@ static inline bool cgroup_freezing(struct task_struct *task) } #endif /* !CONFIG_CGROUP_FREEZER */ -/* - * The PF_FREEZER_SKIP flag should be set by a vfork parent right before it - * calls wait_for_completion(&vfork) and reset right after it returns from this - * function. Next, the parent should call try_to_freeze() to freeze itself - * appropriately in case the child has exited before the freezing of tasks is - * complete. However, we don't want kernel threads to be frozen in unexpected - * places, so we allow them to block freeze_processes() instead or to set - * PF_NOFREEZE if needed. Fortunately, in the ____call_usermodehelper() case the - * parent won't really block freeze_processes(), since ____call_usermodehelper() - * (the child) does a little before exec/exit and it can't be frozen before - * waking up the parent. - */ - - -/** - * freezer_do_not_count - tell freezer to ignore %current - * - * Tell freezers to ignore the current task when determining whether the - * target frozen state is reached. IOW, the current task will be - * considered frozen enough by freezers. - * - * The caller shouldn't do anything which isn't allowed for a frozen task - * until freezer_cont() is called. Usually, freezer[_do_not]_count() pair - * wrap a scheduling operation and nothing much else. - */ -static inline void freezer_do_not_count(void) -{ - current->flags |= PF_FREEZER_SKIP; -} - -/** - * freezer_count - tell freezer to stop ignoring %current - * - * Undo freezer_do_not_count(). It tells freezers that %current should be - * considered again and tries to freeze if freezing condition is already in - * effect. - */ -static inline void freezer_count(void) -{ - current->flags &= ~PF_FREEZER_SKIP; - /* - * If freezing is in progress, the following paired with smp_mb() - * in freezer_should_skip() ensures that either we see %true - * freezing() or freezer_should_skip() sees !PF_FREEZER_SKIP. - */ - smp_mb(); - try_to_freeze(); -} - -/* DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION */ -static inline void freezer_count_unsafe(void) -{ - current->flags &= ~PF_FREEZER_SKIP; - smp_mb(); - try_to_freeze_unsafe(); -} - -/** - * freezer_should_skip - whether to skip a task when determining frozen - * state is reached - * @p: task in quesion - * - * This function is used by freezers after establishing %true freezing() to - * test whether a task should be skipped when determining the target frozen - * state is reached. IOW, if this function returns %true, @p is considered - * frozen enough. - */ -static inline bool freezer_should_skip(struct task_struct *p) -{ - /* - * The following smp_mb() paired with the one in freezer_count() - * ensures that either freezer_count() sees %true freezing() or we - * see cleared %PF_FREEZER_SKIP and return %false. This makes it - * impossible for a task to slip frozen state testing after - * clearing %PF_FREEZER_SKIP. - */ - smp_mb(); - return p->flags & PF_FREEZER_SKIP; -} - -/* - * These functions are intended to be used whenever you want allow a sleeping - * task to be frozen. Note that neither return any clear indication of - * whether a freeze event happened while in this function. - */ - -/* Like schedule(), but should not block the freezer. */ -static inline void freezable_schedule(void) -{ - freezer_do_not_count(); - schedule(); - freezer_count(); -} - -/* DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION */ -static inline void freezable_schedule_unsafe(void) -{ - freezer_do_not_count(); - schedule(); - freezer_count_unsafe(); -} - -/* - * Like schedule_timeout(), but should not block the freezer. Do not - * call this with locks held. - */ -static inline long freezable_schedule_timeout(long timeout) -{ - long __retval; - freezer_do_not_count(); - __retval = schedule_timeout(timeout); - freezer_count(); - return __retval; -} - -/* - * Like schedule_timeout_interruptible(), but should not block the freezer. Do not - * call this with locks held. - */ -static inline long freezable_schedule_timeout_interruptible(long timeout) -{ - long __retval; - freezer_do_not_count(); - __retval = schedule_timeout_interruptible(timeout); - freezer_count(); - return __retval; -} - -/* DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION */ -static inline long freezable_schedule_timeout_interruptible_unsafe(long timeout) -{ - long __retval; - - freezer_do_not_count(); - __retval = schedule_timeout_interruptible(timeout); - freezer_count_unsafe(); - return __retval; -} - -/* Like schedule_timeout_killable(), but should not block the freezer. */ -static inline long freezable_schedule_timeout_killable(long timeout) -{ - long __retval; - freezer_do_not_count(); - __retval = schedule_timeout_killable(timeout); - freezer_count(); - return __retval; -} - -/* DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION */ -static inline long freezable_schedule_timeout_killable_unsafe(long timeout) -{ - long __retval; - freezer_do_not_count(); - __retval = schedule_timeout_killable(timeout); - freezer_count_unsafe(); - return __retval; -} - -/* - * Like schedule_hrtimeout_range(), but should not block the freezer. Do not - * call this with locks held. - */ -static inline int freezable_schedule_hrtimeout_range(ktime_t *expires, - u64 delta, const enum hrtimer_mode mode) -{ - int __retval; - freezer_do_not_count(); - __retval = schedule_hrtimeout_range(expires, delta, mode); - freezer_count(); - return __retval; -} - -/* - * Freezer-friendly wrappers around wait_event_interruptible(), - * wait_event_killable() and wait_event_interruptible_timeout(), originally - * defined in <linux/wait.h> - */ - -/* DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION */ -#define wait_event_freezekillable_unsafe(wq, condition) \ -({ \ - int __retval; \ - freezer_do_not_count(); \ - __retval = wait_event_killable(wq, (condition)); \ - freezer_count_unsafe(); \ - __retval; \ -}) - #else /* !CONFIG_FREEZER */ static inline bool frozen(struct task_struct *p) { return false; } static inline bool freezing(struct task_struct *p) { return false; } @@ -281,35 +83,8 @@ static inline void thaw_kernel_threads(void) {} static inline bool try_to_freeze(void) { return false; } -static inline void freezer_do_not_count(void) {} -static inline void freezer_count(void) {} -static inline int freezer_should_skip(struct task_struct *p) { return 0; } static inline void set_freezable(void) {} -#define freezable_schedule() schedule() - -#define freezable_schedule_unsafe() schedule() - -#define freezable_schedule_timeout(timeout) schedule_timeout(timeout) - -#define freezable_schedule_timeout_interruptible(timeout) \ - schedule_timeout_interruptible(timeout) - -#define freezable_schedule_timeout_interruptible_unsafe(timeout) \ - schedule_timeout_interruptible(timeout) - -#define freezable_schedule_timeout_killable(timeout) \ - schedule_timeout_killable(timeout) - -#define freezable_schedule_timeout_killable_unsafe(timeout) \ - schedule_timeout_killable(timeout) - -#define freezable_schedule_hrtimeout_range(expires, delta, mode) \ - schedule_hrtimeout_range(expires, delta, mode) - -#define wait_event_freezekillable_unsafe(wq, condition) \ - wait_event_killable(wq, condition) - #endif /* !CONFIG_FREEZER */ #endif /* FREEZER_H_INCLUDED */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 619d683eb5fd..e654435f1651 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2004,8 +2004,9 @@ static inline int vfs_whiteout(struct user_namespace *mnt_userns, WHITEOUT_DEV); } -struct dentry *vfs_tmpfile(struct user_namespace *mnt_userns, - struct dentry *dentry, umode_t mode, int open_flag); +struct file *vfs_tmpfile_open(struct user_namespace *mnt_userns, + const struct path *parentpath, + umode_t mode, int open_flag, const struct cred *cred); int vfs_mkobj(struct dentry *, umode_t, int (*f)(struct dentry *, umode_t, void *), @@ -2170,7 +2171,7 @@ struct inode_operations { struct file *, unsigned open_flag, umode_t create_mode); int (*tmpfile) (struct user_namespace *, struct inode *, - struct dentry *, umode_t); + struct file *, umode_t); int (*set_acl)(struct user_namespace *, struct inode *, struct posix_acl *, int); int (*fileattr_set)(struct user_namespace *mnt_userns, @@ -2783,6 +2784,15 @@ extern int finish_open(struct file *file, struct dentry *dentry, int (*open)(struct inode *, struct file *)); extern int finish_no_open(struct file *file, struct dentry *dentry); +/* Helper for the simple case when original dentry is used */ +static inline int finish_open_simple(struct file *file, int error) +{ + if (error) + return error; + + return finish_open(file, file->f_path.dentry, NULL); +} + /* fs/dcache.c */ extern void __init vfs_caches_init_early(void); extern void __init vfs_caches_init(void); diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index cad78b569c7e..4f5f8a651213 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -307,7 +307,7 @@ fscrypt_free_dummy_policy(struct fscrypt_dummy_policy *dummy_policy) } /* keyring.c */ -void fscrypt_sb_delete(struct super_block *sb); +void fscrypt_destroy_keyring(struct super_block *sb); int fscrypt_ioctl_add_key(struct file *filp, void __user *arg); int fscrypt_add_test_dummy_key(struct super_block *sb, const struct fscrypt_dummy_policy *dummy_policy); @@ -521,7 +521,7 @@ fscrypt_free_dummy_policy(struct fscrypt_dummy_policy *dummy_policy) } /* keyring.c */ -static inline void fscrypt_sb_delete(struct super_block *sb) +static inline void fscrypt_destroy_keyring(struct super_block *sb) { } diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 0b61371e287b..62557d4bffc2 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -1122,47 +1122,6 @@ static inline void unpause_graph_tracing(void) { } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ #ifdef CONFIG_TRACING - -/* flags for current->trace */ -enum { - TSK_TRACE_FL_TRACE_BIT = 0, - TSK_TRACE_FL_GRAPH_BIT = 1, -}; -enum { - TSK_TRACE_FL_TRACE = 1 << TSK_TRACE_FL_TRACE_BIT, - TSK_TRACE_FL_GRAPH = 1 << TSK_TRACE_FL_GRAPH_BIT, -}; - -static inline void set_tsk_trace_trace(struct task_struct *tsk) -{ - set_bit(TSK_TRACE_FL_TRACE_BIT, &tsk->trace); -} - -static inline void clear_tsk_trace_trace(struct task_struct *tsk) -{ - clear_bit(TSK_TRACE_FL_TRACE_BIT, &tsk->trace); -} - -static inline int test_tsk_trace_trace(struct task_struct *tsk) -{ - return tsk->trace & TSK_TRACE_FL_TRACE; -} - -static inline void set_tsk_trace_graph(struct task_struct *tsk) -{ - set_bit(TSK_TRACE_FL_GRAPH_BIT, &tsk->trace); -} - -static inline void clear_tsk_trace_graph(struct task_struct *tsk) -{ - clear_bit(TSK_TRACE_FL_GRAPH_BIT, &tsk->trace); -} - -static inline int test_tsk_trace_graph(struct task_struct *tsk) -{ - return tsk->trace & TSK_TRACE_FL_GRAPH; -} - enum ftrace_dump_mode; extern enum ftrace_dump_mode ftrace_dump_on_oops; diff --git a/include/linux/gameport.h b/include/linux/gameport.h index 69081d899492..8c2f00018e89 100644 --- a/include/linux/gameport.h +++ b/include/linux/gameport.h @@ -110,7 +110,7 @@ static inline void gameport_free_port(struct gameport *gameport) static inline void gameport_set_name(struct gameport *gameport, const char *name) { - strlcpy(gameport->name, name, sizeof(gameport->name)); + strscpy(gameport->name, name, sizeof(gameport->name)); } /* diff --git a/include/linux/gfp.h b/include/linux/gfp.h index f314be58fa77..ef4aea3b356e 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -18,6 +18,9 @@ static inline int gfp_migratetype(const gfp_t gfp_flags) VM_WARN_ON((gfp_flags & GFP_MOVABLE_MASK) == GFP_MOVABLE_MASK); BUILD_BUG_ON((1UL << GFP_MOVABLE_SHIFT) != ___GFP_MOVABLE); BUILD_BUG_ON((___GFP_MOVABLE >> GFP_MOVABLE_SHIFT) != MIGRATE_MOVABLE); + BUILD_BUG_ON((___GFP_RECLAIMABLE >> GFP_MOVABLE_SHIFT) != MIGRATE_RECLAIMABLE); + BUILD_BUG_ON(((___GFP_MOVABLE | ___GFP_RECLAIMABLE) >> + GFP_MOVABLE_SHIFT) != MIGRATE_HIGHATOMIC); if (unlikely(page_group_by_mobility_disabled)) return MIGRATE_UNMOVABLE; @@ -33,29 +36,6 @@ static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags) return !!(gfp_flags & __GFP_DIRECT_RECLAIM); } -/** - * gfpflags_normal_context - is gfp_flags a normal sleepable context? - * @gfp_flags: gfp_flags to test - * - * Test whether @gfp_flags indicates that the allocation is from the - * %current context and allowed to sleep. - * - * An allocation being allowed to block doesn't mean it owns the %current - * context. When direct reclaim path tries to allocate memory, the - * allocation context is nested inside whatever %current was doing at the - * time of the original allocation. The nested allocation may be allowed - * to block but modifying anything %current owns can corrupt the outer - * context's expectations. - * - * %true result from this function indicates that the allocation context - * can sleep and use anything that's associated with %current. - */ -static inline bool gfpflags_normal_context(const gfp_t gfp_flags) -{ - return (gfp_flags & (__GFP_DIRECT_RECLAIM | __GFP_MEMALLOC)) == - __GFP_DIRECT_RECLAIM; -} - #ifdef CONFIG_HIGHMEM #define OPT_ZONE_HIGHMEM ZONE_HIGHMEM #else diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 25679035ca28..e9912da5441b 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -6,6 +6,7 @@ #include <linux/kernel.h> #include <linux/bug.h> #include <linux/cacheflush.h> +#include <linux/kmsan.h> #include <linux/mm.h> #include <linux/uaccess.h> #include <linux/hardirq.h> @@ -311,6 +312,7 @@ static inline void copy_user_highpage(struct page *to, struct page *from, vfrom = kmap_local_page(from); vto = kmap_local_page(to); copy_user_page(vto, vfrom, vaddr, to); + kmsan_unpoison_memory(page_address(to), PAGE_SIZE); kunmap_local(vto); kunmap_local(vfrom); } @@ -326,6 +328,7 @@ static inline void copy_highpage(struct page *to, struct page *from) vfrom = kmap_local_page(from); vto = kmap_local_page(to); copy_page(vto, vfrom); + kmsan_copy_page_meta(to, from); kunmap_local(vto); kunmap_local(vfrom); } diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h index 116e8bd68c99..e230c7c46110 100644 --- a/include/linux/hisi_acc_qm.h +++ b/include/linux/hisi_acc_qm.h @@ -87,29 +87,6 @@ #define PEH_AXUSER_CFG 0x401001 #define PEH_AXUSER_CFG_ENABLE 0xffffffff -#define QM_AXI_RRESP BIT(0) -#define QM_AXI_BRESP BIT(1) -#define QM_ECC_MBIT BIT(2) -#define QM_ECC_1BIT BIT(3) -#define QM_ACC_GET_TASK_TIMEOUT BIT(4) -#define QM_ACC_DO_TASK_TIMEOUT BIT(5) -#define QM_ACC_WB_NOT_READY_TIMEOUT BIT(6) -#define QM_SQ_CQ_VF_INVALID BIT(7) -#define QM_CQ_VF_INVALID BIT(8) -#define QM_SQ_VF_INVALID BIT(9) -#define QM_DB_TIMEOUT BIT(10) -#define QM_OF_FIFO_OF BIT(11) -#define QM_DB_RANDOM_INVALID BIT(12) -#define QM_MAILBOX_TIMEOUT BIT(13) -#define QM_FLR_TIMEOUT BIT(14) - -#define QM_BASE_NFE (QM_AXI_RRESP | QM_AXI_BRESP | QM_ECC_MBIT | \ - QM_ACC_GET_TASK_TIMEOUT | QM_DB_TIMEOUT | \ - QM_OF_FIFO_OF | QM_DB_RANDOM_INVALID | \ - QM_MAILBOX_TIMEOUT | QM_FLR_TIMEOUT) -#define QM_BASE_CE QM_ECC_1BIT - -#define QM_Q_DEPTH 1024 #define QM_MIN_QNUM 2 #define HISI_ACC_SGL_SGE_NR_MAX 255 #define QM_SHAPER_CFG 0x100164 @@ -168,6 +145,15 @@ enum qm_vf_state { QM_NOT_READY, }; +enum qm_cap_bits { + QM_SUPPORT_DB_ISOLATION = 0x0, + QM_SUPPORT_FUNC_QOS, + QM_SUPPORT_STOP_QP, + QM_SUPPORT_MB_COMMAND, + QM_SUPPORT_SVA_PREFETCH, + QM_SUPPORT_RPM, +}; + struct dfx_diff_registers { u32 *regs; u32 reg_offset; @@ -232,7 +218,10 @@ struct hisi_qm_err_info { char *acpi_rst; u32 msi_wr_port; u32 ecc_2bits_mask; - u32 dev_ce_mask; + u32 qm_shutdown_mask; + u32 dev_shutdown_mask; + u32 qm_reset_mask; + u32 dev_reset_mask; u32 ce; u32 nfe; u32 fe; @@ -258,6 +247,18 @@ struct hisi_qm_err_ini { void (*err_info_init)(struct hisi_qm *qm); }; +struct hisi_qm_cap_info { + u32 type; + /* Register offset */ + u32 offset; + /* Bit offset in register */ + u32 shift; + u32 mask; + u32 v1_val; + u32 v2_val; + u32 v3_val; +}; + struct hisi_qm_list { struct mutex lock; struct list_head list; @@ -278,6 +279,9 @@ struct hisi_qm { struct pci_dev *pdev; void __iomem *io_base; void __iomem *db_io_base; + + /* Capbility version, 0: not supports */ + u32 cap_ver; u32 sqe_size; u32 qp_base; u32 qp_num; @@ -286,6 +290,8 @@ struct hisi_qm { u32 max_qp_num; u32 vfs_num; u32 db_interval; + u16 eq_depth; + u16 aeq_depth; struct list_head list; struct hisi_qm_list *qm_list; @@ -304,6 +310,8 @@ struct hisi_qm { struct hisi_qm_err_info err_info; struct hisi_qm_err_status err_status; unsigned long misc_ctl; /* driver removing and reset sched */ + /* Device capability bit */ + unsigned long caps; struct rw_semaphore qps_lock; struct idr qp_idr; @@ -326,8 +334,6 @@ struct hisi_qm { bool use_sva; bool is_frozen; - /* doorbell isolation enable */ - bool use_db_isolation; resource_size_t phys_base; resource_size_t db_phys_base; struct uacce_device *uacce; @@ -351,6 +357,8 @@ struct hisi_qp_ops { struct hisi_qp { u32 qp_id; + u16 sq_depth; + u16 cq_depth; u8 alg_type; u8 req_type; @@ -501,6 +509,9 @@ void hisi_qm_pm_init(struct hisi_qm *qm); int hisi_qm_get_dfx_access(struct hisi_qm *qm); void hisi_qm_put_dfx_access(struct hisi_qm *qm); 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); /* Used by VFIO ACC live migration driver */ struct pci_driver *hisi_sec_get_pf_driver(void); diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 768e5261fdae..a1341fdcf666 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -168,9 +168,8 @@ static inline bool file_thp_enabled(struct vm_area_struct *vma) !inode_is_open_for_write(inode) && S_ISREG(inode->i_mode); } -bool hugepage_vma_check(struct vm_area_struct *vma, - unsigned long vm_flags, - bool smaps, bool in_pf); +bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags, + bool smaps, bool in_pf, bool enforce_sysfs); #define transparent_hugepage_use_zero_page() \ (transparent_hugepage_flags & \ @@ -219,6 +218,9 @@ void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud, int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice); +int madvise_collapse(struct vm_area_struct *vma, + struct vm_area_struct **prev, + unsigned long start, unsigned long end); void vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start, unsigned long end, long adjust_next); spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma); @@ -321,8 +323,8 @@ static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, } static inline bool hugepage_vma_check(struct vm_area_struct *vma, - unsigned long vm_flags, - bool smaps, bool in_pf) + unsigned long vm_flags, bool smaps, + bool in_pf, bool enforce_sysfs) { return false; } @@ -362,9 +364,16 @@ static inline void split_huge_pmd_address(struct vm_area_struct *vma, static inline int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice) { - BUG(); - return 0; + return -EINVAL; +} + +static inline int madvise_collapse(struct vm_area_struct *vma, + struct vm_area_struct **prev, + unsigned long start, unsigned long end) +{ + return -EINVAL; } + static inline void vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start, unsigned long end, @@ -435,6 +444,11 @@ static inline int split_folio_to_list(struct folio *folio, return split_huge_page_to_list(&folio->page, list); } +static inline int split_folio(struct folio *folio) +{ + return split_folio_to_list(folio, NULL); +} + /* * archs that select ARCH_WANTS_THP_SWAP but don't support THP_SWP due to * limitations in the implementation like arm64 MTE can override this to diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 1ec1535be04f..8b4f93e84868 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -16,6 +16,7 @@ struct ctl_table; struct user_struct; struct mmu_gather; +struct node; #ifndef CONFIG_ARCH_HAS_HUGEPD typedef struct { unsigned long pd; } hugepd_t; @@ -114,6 +115,12 @@ struct file_region { #endif }; +struct hugetlb_vma_lock { + struct kref refs; + struct rw_semaphore rw_sema; + struct vm_area_struct *vma; +}; + extern struct resv_map *resv_map_alloc(void); void resv_map_release(struct kref *ref); @@ -126,7 +133,7 @@ struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages, long min_hpages); void hugepage_put_subpool(struct hugepage_subpool *spool); -void reset_vma_resv_huge_pages(struct vm_area_struct *vma); +void hugetlb_dup_vma_private(struct vm_area_struct *vma); void clear_vma_resv_huge_pages(struct vm_area_struct *vma); int hugetlb_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int hugetlb_overcommit_handler(struct ctl_table *, int, void *, size_t *, @@ -207,13 +214,21 @@ struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, struct page *follow_huge_pd(struct vm_area_struct *vma, unsigned long address, hugepd_t hpd, int flags, int pdshift); -struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, - pmd_t *pmd, int flags); +struct page *follow_huge_pmd_pte(struct vm_area_struct *vma, unsigned long address, + int flags); struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address, pud_t *pud, int flags); struct page *follow_huge_pgd(struct mm_struct *mm, unsigned long address, pgd_t *pgd, int flags); +void hugetlb_vma_lock_read(struct vm_area_struct *vma); +void hugetlb_vma_unlock_read(struct vm_area_struct *vma); +void hugetlb_vma_lock_write(struct vm_area_struct *vma); +void hugetlb_vma_unlock_write(struct vm_area_struct *vma); +int hugetlb_vma_trylock_write(struct vm_area_struct *vma); +void hugetlb_vma_assert_locked(struct vm_area_struct *vma); +void hugetlb_vma_lock_release(struct kref *kref); + int pmd_huge(pmd_t pmd); int pud_huge(pud_t pud); unsigned long hugetlb_change_protection(struct vm_area_struct *vma, @@ -225,7 +240,7 @@ void hugetlb_unshare_all_pmds(struct vm_area_struct *vma); #else /* !CONFIG_HUGETLB_PAGE */ -static inline void reset_vma_resv_huge_pages(struct vm_area_struct *vma) +static inline void hugetlb_dup_vma_private(struct vm_area_struct *vma) { } @@ -312,8 +327,8 @@ static inline struct page *follow_huge_pd(struct vm_area_struct *vma, return NULL; } -static inline struct page *follow_huge_pmd(struct mm_struct *mm, - unsigned long address, pmd_t *pmd, int flags) +static inline struct page *follow_huge_pmd_pte(struct vm_area_struct *vma, + unsigned long address, int flags) { return NULL; } @@ -336,6 +351,31 @@ static inline int prepare_hugepage_range(struct file *file, return -EINVAL; } +static inline void hugetlb_vma_lock_read(struct vm_area_struct *vma) +{ +} + +static inline void hugetlb_vma_unlock_read(struct vm_area_struct *vma) +{ +} + +static inline void hugetlb_vma_lock_write(struct vm_area_struct *vma) +{ +} + +static inline void hugetlb_vma_unlock_write(struct vm_area_struct *vma) +{ +} + +static inline int hugetlb_vma_trylock_write(struct vm_area_struct *vma) +{ + return 1; +} + +static inline void hugetlb_vma_assert_locked(struct vm_area_struct *vma) +{ +} + static inline int pmd_huge(pmd_t pmd) { return 0; @@ -665,7 +705,7 @@ struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask); struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address); -int huge_add_to_page_cache(struct page *page, struct address_space *mapping, +int hugetlb_add_to_page_cache(struct page *page, struct address_space *mapping, pgoff_t idx); void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, unsigned long address, struct page *page); @@ -935,6 +975,11 @@ static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, } #endif +#ifdef CONFIG_NUMA +void hugetlb_register_node(struct node *node); +void hugetlb_unregister_node(struct node *node); +#endif + #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; @@ -1109,6 +1154,14 @@ static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { } + +static inline void hugetlb_register_node(struct node *node) +{ +} + +static inline void hugetlb_unregister_node(struct node *node) +{ +} #endif /* CONFIG_HUGETLB_PAGE */ static inline spinlock_t *huge_pte_lock(struct hstate *h, @@ -1123,14 +1176,10 @@ static inline spinlock_t *huge_pte_lock(struct hstate *h, #if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_CMA) extern void __init hugetlb_cma_reserve(int order); -extern void __init hugetlb_cma_check(void); #else static inline __init void hugetlb_cma_reserve(int order) { } -static inline __init void hugetlb_cma_check(void) -{ -} #endif bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr); diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h index 379344828e78..630cd255d0cf 100644 --- a/include/linux/hugetlb_cgroup.h +++ b/include/linux/hugetlb_cgroup.h @@ -90,32 +90,31 @@ hugetlb_cgroup_from_page_rsvd(struct page *page) return __hugetlb_cgroup_from_page(page, true); } -static inline int __set_hugetlb_cgroup(struct page *page, +static inline void __set_hugetlb_cgroup(struct page *page, struct hugetlb_cgroup *h_cg, bool rsvd) { VM_BUG_ON_PAGE(!PageHuge(page), page); if (compound_order(page) < HUGETLB_CGROUP_MIN_ORDER) - return -1; + return; if (rsvd) set_page_private(page + SUBPAGE_INDEX_CGROUP_RSVD, (unsigned long)h_cg); else set_page_private(page + SUBPAGE_INDEX_CGROUP, (unsigned long)h_cg); - return 0; } -static inline int set_hugetlb_cgroup(struct page *page, +static inline void set_hugetlb_cgroup(struct page *page, struct hugetlb_cgroup *h_cg) { - return __set_hugetlb_cgroup(page, h_cg, false); + __set_hugetlb_cgroup(page, h_cg, false); } -static inline int set_hugetlb_cgroup_rsvd(struct page *page, +static inline void set_hugetlb_cgroup_rsvd(struct page *page, struct hugetlb_cgroup *h_cg) { - return __set_hugetlb_cgroup(page, h_cg, true); + __set_hugetlb_cgroup(page, h_cg, true); } static inline bool hugetlb_cgroup_disabled(void) @@ -199,16 +198,14 @@ hugetlb_cgroup_from_page_rsvd(struct page *page) return NULL; } -static inline int set_hugetlb_cgroup(struct page *page, +static inline void set_hugetlb_cgroup(struct page *page, struct hugetlb_cgroup *h_cg) { - return 0; } -static inline int set_hugetlb_cgroup_rsvd(struct page *page, +static inline void set_hugetlb_cgroup_rsvd(struct page *page, struct hugetlb_cgroup *h_cg) { - return 0; } static inline bool hugetlb_cgroup_disabled(void) diff --git a/include/linux/hw_breakpoint.h b/include/linux/hw_breakpoint.h index 78dd7035d1e5..f319bd26b030 100644 --- a/include/linux/hw_breakpoint.h +++ b/include/linux/hw_breakpoint.h @@ -74,12 +74,12 @@ register_wide_hw_breakpoint(struct perf_event_attr *attr, extern int register_perf_hw_breakpoint(struct perf_event *bp); extern void unregister_hw_breakpoint(struct perf_event *bp); extern void unregister_wide_hw_breakpoint(struct perf_event * __percpu *cpu_events); +extern bool hw_breakpoint_is_used(void); extern int dbg_reserve_bp_slot(struct perf_event *bp); extern int dbg_release_bp_slot(struct perf_event *bp); extern int reserve_bp_slot(struct perf_event *bp); extern void release_bp_slot(struct perf_event *bp); -int hw_breakpoint_weight(struct perf_event *bp); int arch_reserve_bp_slot(struct perf_event *bp); void arch_release_bp_slot(struct perf_event *bp); void arch_unregister_hw_breakpoint(struct perf_event *bp); @@ -121,6 +121,8 @@ register_perf_hw_breakpoint(struct perf_event *bp) { return -ENOSYS; } static inline void unregister_hw_breakpoint(struct perf_event *bp) { } static inline void unregister_wide_hw_breakpoint(struct perf_event * __percpu *cpu_events) { } +static inline bool hw_breakpoint_is_used(void) { return false; } + static inline int reserve_bp_slot(struct perf_event *bp) {return -ENOSYS; } static inline void release_bp_slot(struct perf_event *bp) { } diff --git a/include/linux/hw_random.h b/include/linux/hw_random.h index aa1d4da03538..77c2885c4c13 100644 --- a/include/linux/hw_random.h +++ b/include/linux/hw_random.h @@ -50,6 +50,7 @@ struct hwrng { struct list_head list; struct kref ref; struct completion cleanup_done; + struct completion dying; }; struct device; @@ -61,4 +62,6 @@ extern int devm_hwrng_register(struct device *dev, struct hwrng *rng); extern void hwrng_unregister(struct hwrng *rng); extern void devm_hwrng_unregister(struct device *dve, struct hwrng *rng); +extern long hwrng_msleep(struct hwrng *rng, unsigned int msecs); + #endif /* LINUX_HWRANDOM_H_ */ diff --git a/include/linux/init.h b/include/linux/init.h index a0a90cd73ebe..077d7f93b402 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -134,7 +134,7 @@ static inline initcall_t initcall_from_entry(initcall_entry_t *entry) extern initcall_entry_t __con_initcall_start[], __con_initcall_end[]; -/* Used for contructor calls. */ +/* Used for constructor calls. */ typedef void (*ctor_fn_t)(void); struct file_system_type; diff --git a/include/linux/input/auo-pixcir-ts.h b/include/linux/input/auo-pixcir-ts.h deleted file mode 100644 index ed0776997a7a..000000000000 --- a/include/linux/input/auo-pixcir-ts.h +++ /dev/null @@ -1,44 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Driver for AUO in-cell touchscreens - * - * Copyright (c) 2011 Heiko Stuebner <heiko@sntech.de> - * - * based on auo_touch.h from Dell Streak kernel - * - * Copyright (c) 2008 QUALCOMM Incorporated. - * Copyright (c) 2008 QUALCOMM USA, INC. - */ - -#ifndef __AUO_PIXCIR_TS_H__ -#define __AUO_PIXCIR_TS_H__ - -/* - * Interrupt modes: - * periodical: interrupt is asserted periodicaly - * compare coordinates: interrupt is asserted when coordinates change - * indicate touch: interrupt is asserted during touch - */ -#define AUO_PIXCIR_INT_PERIODICAL 0x00 -#define AUO_PIXCIR_INT_COMP_COORD 0x01 -#define AUO_PIXCIR_INT_TOUCH_IND 0x02 - -/* - * @gpio_int interrupt gpio - * @int_setting one of AUO_PIXCIR_INT_* - * @init_hw hardwarespecific init - * @exit_hw hardwarespecific shutdown - * @x_max x-resolution - * @y_max y-resolution - */ -struct auo_pixcir_ts_platdata { - int gpio_int; - int gpio_rst; - - int int_setting; - - unsigned int x_max; - unsigned int y_max; -}; - -#endif diff --git a/include/linux/instrumented.h b/include/linux/instrumented.h index 42faebbaa202..501fa8486749 100644 --- a/include/linux/instrumented.h +++ b/include/linux/instrumented.h @@ -2,7 +2,7 @@ /* * This header provides generic wrappers for memory access instrumentation that - * the compiler cannot emit for: KASAN, KCSAN. + * the compiler cannot emit for: KASAN, KCSAN, KMSAN. */ #ifndef _LINUX_INSTRUMENTED_H #define _LINUX_INSTRUMENTED_H @@ -10,6 +10,7 @@ #include <linux/compiler.h> #include <linux/kasan-checks.h> #include <linux/kcsan-checks.h> +#include <linux/kmsan-checks.h> #include <linux/types.h> /** @@ -117,10 +118,11 @@ instrument_copy_to_user(void __user *to, const void *from, unsigned long n) { kasan_check_read(from, n); kcsan_check_read(from, n); + kmsan_copy_to_user(to, from, n, 0); } /** - * instrument_copy_from_user - instrument writes of copy_from_user + * instrument_copy_from_user_before - add instrumentation before copy_from_user * * Instrument writes to kernel memory, that are due to copy_from_user (and * variants). The instrumentation should be inserted before the accesses. @@ -130,10 +132,61 @@ instrument_copy_to_user(void __user *to, const void *from, unsigned long n) * @n number of bytes to copy */ static __always_inline void -instrument_copy_from_user(const void *to, const void __user *from, unsigned long n) +instrument_copy_from_user_before(const void *to, const void __user *from, unsigned long n) { kasan_check_write(to, n); kcsan_check_write(to, n); } +/** + * instrument_copy_from_user_after - add instrumentation after copy_from_user + * + * Instrument writes to kernel memory, that are due to copy_from_user (and + * variants). The instrumentation should be inserted after the accesses. + * + * @to destination address + * @from source address + * @n number of bytes to copy + * @left number of bytes not copied (as returned by copy_from_user) + */ +static __always_inline void +instrument_copy_from_user_after(const void *to, const void __user *from, + unsigned long n, unsigned long left) +{ + kmsan_unpoison_memory(to, n - left); +} + +/** + * instrument_get_user() - add instrumentation to get_user()-like macros + * + * get_user() and friends are fragile, so it may depend on the implementation + * whether the instrumentation happens before or after the data is copied from + * the userspace. + * + * @to destination variable, may not be address-taken + */ +#define instrument_get_user(to) \ +({ \ + u64 __tmp = (u64)(to); \ + kmsan_unpoison_memory(&__tmp, sizeof(__tmp)); \ + to = __tmp; \ +}) + + +/** + * instrument_put_user() - add instrumentation to put_user()-like macros + * + * put_user() and friends are fragile, so it may depend on the implementation + * whether the instrumentation happens before or after the data is copied from + * the userspace. + * + * @from source address + * @ptr userspace pointer to copy to + * @size number of bytes to copy + */ +#define instrument_put_user(from, ptr, size) \ +({ \ + kmsan_copy_to_user(ptr, &from, sizeof(from), 0); \ +}) + #endif /* _LINUX_INSTRUMENTED_H */ diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index ca98aeadcc80..1f068dfdb140 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -16,7 +16,9 @@ enum io_pgtable_fmt { ARM_V7S, ARM_MALI_LPAE, AMD_IOMMU_V1, + AMD_IOMMU_V2, APPLE_DART, + APPLE_DART2, IO_PGTABLE_NUM_FMTS, }; @@ -260,6 +262,7 @@ extern struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s2_init_fns; extern struct io_pgtable_init_fns io_pgtable_arm_v7s_init_fns; extern struct io_pgtable_init_fns io_pgtable_arm_mali_lpae_init_fns; extern struct io_pgtable_init_fns io_pgtable_amd_iommu_v1_init_fns; +extern struct io_pgtable_init_fns io_pgtable_amd_iommu_v2_init_fns; extern struct io_pgtable_init_fns io_pgtable_apple_dart_init_fns; #endif /* __IO_PGTABLE_H */ diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index aa4d90a53866..f5b687a787a3 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -34,9 +34,6 @@ struct io_file_table { unsigned int alloc_hint; }; -struct io_notif; -struct io_notif_slot; - struct io_hash_bucket { spinlock_t lock; struct hlist_head list; @@ -242,8 +239,6 @@ struct io_ring_ctx { unsigned nr_user_files; unsigned nr_user_bufs; struct io_mapped_ubuf **user_bufs; - struct io_notif_slot *notif_slots; - unsigned nr_notif_slots; struct io_submit_state submit_state; diff --git a/include/linux/iommu.h b/include/linux/iommu.h index ea30f00dc145..3c9da1f8979e 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -212,7 +212,7 @@ struct iommu_iotlb_gather { * @of_xlate: add OF master IDs to iommu grouping * @is_attach_deferred: Check if domain attach should be deferred from iommu * driver init to device driver init (default no) - * @dev_has/enable/disable_feat: per device entries to check/enable/disable + * @dev_enable/disable_feat: per device entries to enable/disable * iommu specific features. * @sva_bind: Bind process address space to device * @sva_unbind: Unbind process address space from device @@ -227,7 +227,7 @@ struct iommu_iotlb_gather { * @owner: Driver module providing these ops */ struct iommu_ops { - bool (*capable)(enum iommu_cap); + bool (*capable)(struct device *dev, enum iommu_cap); /* Domain allocation and freeing by the iommu driver */ struct iommu_domain *(*domain_alloc)(unsigned iommu_domain_type); @@ -416,11 +416,9 @@ static inline const struct iommu_ops *dev_iommu_ops(struct device *dev) return dev->iommu->iommu_dev->ops; } -extern int bus_set_iommu(struct bus_type *bus, const struct iommu_ops *ops); extern int bus_iommu_probe(struct bus_type *bus); extern bool iommu_present(struct bus_type *bus); extern bool device_iommu_capable(struct device *dev, enum iommu_cap cap); -extern bool iommu_capable(struct bus_type *bus, enum iommu_cap cap); extern struct iommu_domain *iommu_domain_alloc(struct bus_type *bus); extern struct iommu_group *iommu_group_get_by_id(int id); extern void iommu_domain_free(struct iommu_domain *domain); @@ -457,7 +455,7 @@ extern void iommu_set_default_translated(bool cmd_line); extern bool iommu_default_passthrough(void); extern struct iommu_resv_region * iommu_alloc_resv_region(phys_addr_t start, size_t length, int prot, - enum iommu_resv_type type); + enum iommu_resv_type type, gfp_t gfp); extern int iommu_get_group_resv_regions(struct iommu_group *group, struct list_head *head); @@ -697,11 +695,6 @@ static inline bool device_iommu_capable(struct device *dev, enum iommu_cap cap) return false; } -static inline bool iommu_capable(struct bus_type *bus, enum iommu_cap cap) -{ - return false; -} - static inline struct iommu_domain *iommu_domain_alloc(struct bus_type *bus) { return NULL; @@ -1070,4 +1063,40 @@ void iommu_debugfs_setup(void); static inline void iommu_debugfs_setup(void) {} #endif +#ifdef CONFIG_IOMMU_DMA +#include <linux/msi.h> + +/* Setup call for arch DMA mapping code */ +void iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 dma_limit); + +int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base); + +int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr); +void iommu_dma_compose_msi_msg(struct msi_desc *desc, struct msi_msg *msg); + +#else /* CONFIG_IOMMU_DMA */ + +struct msi_desc; +struct msi_msg; + +static inline void iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 dma_limit) +{ +} + +static inline int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base) +{ + return -ENODEV; +} + +static inline int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr) +{ + return 0; +} + +static inline void iommu_dma_compose_msi_msg(struct msi_desc *desc, struct msi_msg *msg) +{ +} + +#endif /* CONFIG_IOMMU_DMA */ + #endif /* __LINUX_IOMMU_H */ diff --git a/include/linux/ioport.h b/include/linux/ioport.h index 8a76dca9deee..27642ca15d93 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -79,7 +79,8 @@ struct resource { #define IORESOURCE_IRQ_HIGHLEVEL (1<<2) #define IORESOURCE_IRQ_LOWLEVEL (1<<3) #define IORESOURCE_IRQ_SHAREABLE (1<<4) -#define IORESOURCE_IRQ_OPTIONAL (1<<5) +#define IORESOURCE_IRQ_OPTIONAL (1<<5) +#define IORESOURCE_IRQ_WAKECAPABLE (1<<6) /* PnP DMA specific bits (IORESOURCE_BITS) */ #define IORESOURCE_DMA_TYPE_MASK (3<<0) diff --git a/include/linux/iova.h b/include/linux/iova.h index c6ba6d95d79c..83c00fac2acb 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -75,7 +75,7 @@ static inline unsigned long iova_pfn(struct iova_domain *iovad, dma_addr_t iova) return iova >> iova_shift(iovad); } -#if IS_ENABLED(CONFIG_IOMMU_IOVA) +#if IS_REACHABLE(CONFIG_IOMMU_IOVA) int iova_cache_get(void); void iova_cache_put(void); diff --git a/include/linux/iova_bitmap.h b/include/linux/iova_bitmap.h new file mode 100644 index 000000000000..c006cf0a25f3 --- /dev/null +++ b/include/linux/iova_bitmap.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2022, Oracle and/or its affiliates. + * Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved + */ +#ifndef _IOVA_BITMAP_H_ +#define _IOVA_BITMAP_H_ + +#include <linux/types.h> + +struct iova_bitmap; + +typedef int (*iova_bitmap_fn_t)(struct iova_bitmap *bitmap, + unsigned long iova, size_t length, + void *opaque); + +struct iova_bitmap *iova_bitmap_alloc(unsigned long iova, size_t length, + unsigned long page_size, + u64 __user *data); +void iova_bitmap_free(struct iova_bitmap *bitmap); +int iova_bitmap_for_each(struct iova_bitmap *bitmap, void *opaque, + iova_bitmap_fn_t fn); +void iova_bitmap_set(struct iova_bitmap *bitmap, + unsigned long iova, size_t length); + +#endif diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index e3e8c8662b49..e8240cf2611a 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -11,6 +11,7 @@ #include <linux/refcount.h> #include <linux/rhashtable-types.h> #include <linux/sysctl.h> +#include <linux/percpu_counter.h> struct user_namespace; @@ -36,8 +37,8 @@ struct ipc_namespace { unsigned int msg_ctlmax; unsigned int msg_ctlmnb; unsigned int msg_ctlmni; - atomic_t msg_bytes; - atomic_t msg_hdrs; + struct percpu_counter percpu_msg_bytes; + struct percpu_counter percpu_msg_hdrs; size_t shm_ctlmax; size_t shm_ctlall; diff --git a/include/linux/irqchip.h b/include/linux/irqchip.h index 3a091d0710ae..d5e6024cb2a8 100644 --- a/include/linux/irqchip.h +++ b/include/linux/irqchip.h @@ -44,7 +44,8 @@ static const struct of_device_id drv_name##_irqchip_match_table[] = { #define IRQCHIP_MATCH(compat, fn) { .compatible = compat, \ .data = typecheck_irq_init_cb(fn), }, -#define IRQCHIP_PLATFORM_DRIVER_END(drv_name) \ + +#define IRQCHIP_PLATFORM_DRIVER_END(drv_name, ...) \ {}, \ }; \ MODULE_DEVICE_TABLE(of, drv_name##_irqchip_match_table); \ @@ -56,6 +57,7 @@ static struct platform_driver drv_name##_driver = { \ .owner = THIS_MODULE, \ .of_match_table = drv_name##_irqchip_match_table, \ .suppress_bind_attrs = true, \ + __VA_ARGS__ \ }, \ }; \ builtin_platform_driver(drv_name##_driver) diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 1cd4e36890fb..844a8e30e6de 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -169,6 +169,7 @@ int generic_handle_irq_safe(unsigned int irq); * conversion failed. */ int generic_handle_domain_irq(struct irq_domain *domain, unsigned int hwirq); +int generic_handle_domain_irq_safe(struct irq_domain *domain, unsigned int hwirq); int generic_handle_domain_nmi(struct irq_domain *domain, unsigned int hwirq); #endif diff --git a/include/linux/iversion.h b/include/linux/iversion.h index 3bfebde5a1a6..e27bd4f55d84 100644 --- a/include/linux/iversion.h +++ b/include/linux/iversion.h @@ -123,17 +123,12 @@ inode_peek_iversion_raw(const struct inode *inode) static inline void inode_set_max_iversion_raw(struct inode *inode, u64 val) { - u64 cur, old; + u64 cur = inode_peek_iversion_raw(inode); - cur = inode_peek_iversion_raw(inode); - for (;;) { + do { if (cur > val) break; - old = atomic64_cmpxchg(&inode->i_version, cur, val); - if (likely(old == cur)) - break; - cur = old; - } + } while (!atomic64_try_cmpxchg(&inode->i_version, &cur, val)); } /** @@ -177,56 +172,7 @@ inode_set_iversion_queried(struct inode *inode, u64 val) I_VERSION_QUERIED); } -/** - * inode_maybe_inc_iversion - increments i_version - * @inode: inode with the i_version that should be updated - * @force: increment the counter even if it's not necessary? - * - * Every time the inode is modified, the i_version field must be seen to have - * changed by any observer. - * - * If "force" is set or the QUERIED flag is set, then ensure that we increment - * the value, and clear the queried flag. - * - * In the common case where neither is set, then we can return "false" without - * updating i_version. - * - * If this function returns false, and no other metadata has changed, then we - * can avoid logging the metadata. - */ -static inline bool -inode_maybe_inc_iversion(struct inode *inode, bool force) -{ - u64 cur, old, new; - - /* - * The i_version field is not strictly ordered with any other inode - * information, but the legacy inode_inc_iversion code used a spinlock - * to serialize increments. - * - * Here, we add full memory barriers to ensure that any de-facto - * ordering with other info is preserved. - * - * This barrier pairs with the barrier in inode_query_iversion() - */ - smp_mb(); - cur = inode_peek_iversion_raw(inode); - for (;;) { - /* If flag is clear then we needn't do anything */ - if (!force && !(cur & I_VERSION_QUERIED)) - return false; - - /* Since lowest bit is flag, add 2 to avoid it */ - new = (cur & ~I_VERSION_QUERIED) + I_VERSION_INCREMENT; - - old = atomic64_cmpxchg(&inode->i_version, cur, new); - if (likely(old == cur)) - break; - cur = old; - } - return true; -} - +bool inode_maybe_inc_iversion(struct inode *inode, bool force); /** * inode_inc_iversion - forcibly increment i_version @@ -304,10 +250,10 @@ inode_peek_iversion(const struct inode *inode) static inline u64 inode_query_iversion(struct inode *inode) { - u64 cur, old, new; + u64 cur, new; cur = inode_peek_iversion_raw(inode); - for (;;) { + do { /* If flag is already set, then no need to swap */ if (cur & I_VERSION_QUERIED) { /* @@ -320,11 +266,7 @@ inode_query_iversion(struct inode *inode) } new = cur | I_VERSION_QUERIED; - old = atomic64_cmpxchg(&inode->i_version, cur, new); - if (likely(old == cur)) - break; - cur = old; - } + } while (!atomic64_try_cmpxchg(&inode->i_version, &cur, new)); return cur >> I_VERSION_QUERIED_SHIFT; } diff --git a/include/linux/kasan.h b/include/linux/kasan.h index b092277bf48d..d811b3d7d2a1 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -98,19 +98,13 @@ static inline bool kasan_has_integrated_init(void) #ifdef CONFIG_KASAN struct kasan_cache { +#ifdef CONFIG_KASAN_GENERIC int alloc_meta_offset; int free_meta_offset; +#endif bool is_kmalloc; }; -slab_flags_t __kasan_never_merge(void); -static __always_inline slab_flags_t kasan_never_merge(void) -{ - if (kasan_enabled()) - return __kasan_never_merge(); - return 0; -} - void __kasan_unpoison_range(const void *addr, size_t size); static __always_inline void kasan_unpoison_range(const void *addr, size_t size) { @@ -134,15 +128,6 @@ static __always_inline void kasan_unpoison_pages(struct page *page, __kasan_unpoison_pages(page, order, init); } -void __kasan_cache_create(struct kmem_cache *cache, unsigned int *size, - slab_flags_t *flags); -static __always_inline void kasan_cache_create(struct kmem_cache *cache, - unsigned int *size, slab_flags_t *flags) -{ - if (kasan_enabled()) - __kasan_cache_create(cache, size, flags); -} - void __kasan_cache_create_kmalloc(struct kmem_cache *cache); static __always_inline void kasan_cache_create_kmalloc(struct kmem_cache *cache) { @@ -150,14 +135,6 @@ static __always_inline void kasan_cache_create_kmalloc(struct kmem_cache *cache) __kasan_cache_create_kmalloc(cache); } -size_t __kasan_metadata_size(struct kmem_cache *cache); -static __always_inline size_t kasan_metadata_size(struct kmem_cache *cache) -{ - if (kasan_enabled()) - return __kasan_metadata_size(cache); - return 0; -} - void __kasan_poison_slab(struct slab *slab); static __always_inline void kasan_poison_slab(struct slab *slab) { @@ -269,20 +246,12 @@ static __always_inline bool kasan_check_byte(const void *addr) #else /* CONFIG_KASAN */ -static inline slab_flags_t kasan_never_merge(void) -{ - return 0; -} static inline void kasan_unpoison_range(const void *address, size_t size) {} static inline void kasan_poison_pages(struct page *page, unsigned int order, bool init) {} static inline void kasan_unpoison_pages(struct page *page, unsigned int order, bool init) {} -static inline void kasan_cache_create(struct kmem_cache *cache, - unsigned int *size, - slab_flags_t *flags) {} static inline void kasan_cache_create_kmalloc(struct kmem_cache *cache) {} -static inline size_t kasan_metadata_size(struct kmem_cache *cache) { return 0; } static inline void kasan_poison_slab(struct slab *slab) {} static inline void kasan_unpoison_object_data(struct kmem_cache *cache, void *object) {} @@ -333,6 +302,11 @@ static inline void kasan_unpoison_task_stack(struct task_struct *task) {} #ifdef CONFIG_KASAN_GENERIC +size_t kasan_metadata_size(struct kmem_cache *cache); +slab_flags_t kasan_never_merge(void); +void kasan_cache_create(struct kmem_cache *cache, unsigned int *size, + slab_flags_t *flags); + void kasan_cache_shrink(struct kmem_cache *cache); void kasan_cache_shutdown(struct kmem_cache *cache); void kasan_record_aux_stack(void *ptr); @@ -340,6 +314,21 @@ void kasan_record_aux_stack_noalloc(void *ptr); #else /* CONFIG_KASAN_GENERIC */ +/* Tag-based KASAN modes do not use per-object metadata. */ +static inline size_t kasan_metadata_size(struct kmem_cache *cache) +{ + return 0; +} +/* And thus nothing prevents cache merging. */ +static inline slab_flags_t kasan_never_merge(void) +{ + return 0; +} +/* And no cache-related metadata initialization is required. */ +static inline void kasan_cache_create(struct kmem_cache *cache, + unsigned int *size, + slab_flags_t *flags) {} + static inline void kasan_cache_shrink(struct kmem_cache *cache) {} static inline void kasan_cache_shutdown(struct kmem_cache *cache) {} static inline void kasan_record_aux_stack(void *ptr) {} diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 13e6c4b58f07..41a686996aaa 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -427,7 +427,7 @@ extern int kexec_load_disabled; extern bool kexec_in_progress; int crash_shrink_memory(unsigned long new_size); -size_t crash_get_memory_size(void); +ssize_t crash_get_memory_size(void); #ifndef arch_kexec_protect_crashkres /* diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h index 384f034ae947..70162d707caf 100644 --- a/include/linux/khugepaged.h +++ b/include/linux/khugepaged.h @@ -16,11 +16,13 @@ extern void khugepaged_enter_vma(struct vm_area_struct *vma, unsigned long vm_flags); extern void khugepaged_min_free_kbytes_update(void); #ifdef CONFIG_SHMEM -extern void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr); +extern int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, + bool install_pmd); #else -static inline void collapse_pte_mapped_thp(struct mm_struct *mm, - unsigned long addr) +static inline int collapse_pte_mapped_thp(struct mm_struct *mm, + unsigned long addr, bool install_pmd) { + return 0; } #endif @@ -46,9 +48,10 @@ static inline void khugepaged_enter_vma(struct vm_area_struct *vma, unsigned long vm_flags) { } -static inline void collapse_pte_mapped_thp(struct mm_struct *mm, - unsigned long addr) +static inline int collapse_pte_mapped_thp(struct mm_struct *mm, + unsigned long addr, bool install_pmd) { + return 0; } static inline void khugepaged_min_free_kbytes_update(void) diff --git a/include/linux/kmsan-checks.h b/include/linux/kmsan-checks.h new file mode 100644 index 000000000000..c4cae333deec --- /dev/null +++ b/include/linux/kmsan-checks.h @@ -0,0 +1,83 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * KMSAN checks to be used for one-off annotations in subsystems. + * + * Copyright (C) 2017-2022 Google LLC + * Author: Alexander Potapenko <glider@google.com> + * + */ + +#ifndef _LINUX_KMSAN_CHECKS_H +#define _LINUX_KMSAN_CHECKS_H + +#include <linux/types.h> + +#ifdef CONFIG_KMSAN + +/** + * kmsan_poison_memory() - Mark the memory range as uninitialized. + * @address: address to start with. + * @size: size of buffer to poison. + * @flags: GFP flags for allocations done by this function. + * + * Until other data is written to this range, KMSAN will treat it as + * uninitialized. Error reports for this memory will reference the call site of + * kmsan_poison_memory() as origin. + */ +void kmsan_poison_memory(const void *address, size_t size, gfp_t flags); + +/** + * kmsan_unpoison_memory() - Mark the memory range as initialized. + * @address: address to start with. + * @size: size of buffer to unpoison. + * + * Until other data is written to this range, KMSAN will treat it as + * initialized. + */ +void kmsan_unpoison_memory(const void *address, size_t size); + +/** + * kmsan_check_memory() - Check the memory range for being initialized. + * @address: address to start with. + * @size: size of buffer to check. + * + * If any piece of the given range is marked as uninitialized, KMSAN will report + * an error. + */ +void kmsan_check_memory(const void *address, size_t size); + +/** + * kmsan_copy_to_user() - Notify KMSAN about a data transfer to userspace. + * @to: destination address in the userspace. + * @from: source address in the kernel. + * @to_copy: number of bytes to copy. + * @left: number of bytes not copied. + * + * If this is a real userspace data transfer, KMSAN checks the bytes that were + * actually copied to ensure there was no information leak. If @to belongs to + * the kernel space (which is possible for compat syscalls), KMSAN just copies + * the metadata. + */ +void kmsan_copy_to_user(void __user *to, const void *from, size_t to_copy, + size_t left); + +#else + +static inline void kmsan_poison_memory(const void *address, size_t size, + gfp_t flags) +{ +} +static inline void kmsan_unpoison_memory(const void *address, size_t size) +{ +} +static inline void kmsan_check_memory(const void *address, size_t size) +{ +} +static inline void kmsan_copy_to_user(void __user *to, const void *from, + size_t to_copy, size_t left) +{ +} + +#endif + +#endif /* _LINUX_KMSAN_CHECKS_H */ diff --git a/include/linux/kmsan.h b/include/linux/kmsan.h new file mode 100644 index 000000000000..e38ae3c34618 --- /dev/null +++ b/include/linux/kmsan.h @@ -0,0 +1,330 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * KMSAN API for subsystems. + * + * Copyright (C) 2017-2022 Google LLC + * Author: Alexander Potapenko <glider@google.com> + * + */ +#ifndef _LINUX_KMSAN_H +#define _LINUX_KMSAN_H + +#include <linux/dma-direction.h> +#include <linux/gfp.h> +#include <linux/kmsan-checks.h> +#include <linux/types.h> + +struct page; +struct kmem_cache; +struct task_struct; +struct scatterlist; +struct urb; + +#ifdef CONFIG_KMSAN + +/** + * kmsan_task_create() - Initialize KMSAN state for the task. + * @task: task to initialize. + */ +void kmsan_task_create(struct task_struct *task); + +/** + * kmsan_task_exit() - Notify KMSAN that a task has exited. + * @task: task about to finish. + */ +void kmsan_task_exit(struct task_struct *task); + +/** + * kmsan_init_shadow() - Initialize KMSAN shadow at boot time. + * + * Allocate and initialize KMSAN metadata for early allocations. + */ +void __init kmsan_init_shadow(void); + +/** + * kmsan_init_runtime() - Initialize KMSAN state and enable KMSAN. + */ +void __init kmsan_init_runtime(void); + +/** + * kmsan_memblock_free_pages() - handle freeing of memblock pages. + * @page: struct page to free. + * @order: order of @page. + * + * Freed pages are either returned to buddy allocator or held back to be used + * as metadata pages. + */ +bool __init kmsan_memblock_free_pages(struct page *page, unsigned int order); + +/** + * kmsan_alloc_page() - Notify KMSAN about an alloc_pages() call. + * @page: struct page pointer returned by alloc_pages(). + * @order: order of allocated struct page. + * @flags: GFP flags used by alloc_pages() + * + * KMSAN marks 1<<@order pages starting at @page as uninitialized, unless + * @flags contain __GFP_ZERO. + */ +void kmsan_alloc_page(struct page *page, unsigned int order, gfp_t flags); + +/** + * kmsan_free_page() - Notify KMSAN about a free_pages() call. + * @page: struct page pointer passed to free_pages(). + * @order: order of deallocated struct page. + * + * KMSAN marks freed memory as uninitialized. + */ +void kmsan_free_page(struct page *page, unsigned int order); + +/** + * kmsan_copy_page_meta() - Copy KMSAN metadata between two pages. + * @dst: destination page. + * @src: source page. + * + * KMSAN copies the contents of metadata pages for @src into the metadata pages + * for @dst. If @dst has no associated metadata pages, nothing happens. + * If @src has no associated metadata pages, @dst metadata pages are unpoisoned. + */ +void kmsan_copy_page_meta(struct page *dst, struct page *src); + +/** + * kmsan_slab_alloc() - Notify KMSAN about a slab allocation. + * @s: slab cache the object belongs to. + * @object: object pointer. + * @flags: GFP flags passed to the allocator. + * + * Depending on cache flags and GFP flags, KMSAN sets up the metadata of the + * newly created object, marking it as initialized or uninitialized. + */ +void kmsan_slab_alloc(struct kmem_cache *s, void *object, gfp_t flags); + +/** + * kmsan_slab_free() - Notify KMSAN about a slab deallocation. + * @s: slab cache the object belongs to. + * @object: object pointer. + * + * KMSAN marks the freed object as uninitialized. + */ +void kmsan_slab_free(struct kmem_cache *s, void *object); + +/** + * kmsan_kmalloc_large() - Notify KMSAN about a large slab allocation. + * @ptr: object pointer. + * @size: object size. + * @flags: GFP flags passed to the allocator. + * + * Similar to kmsan_slab_alloc(), but for large allocations. + */ +void kmsan_kmalloc_large(const void *ptr, size_t size, gfp_t flags); + +/** + * kmsan_kfree_large() - Notify KMSAN about a large slab deallocation. + * @ptr: object pointer. + * + * Similar to kmsan_slab_free(), but for large allocations. + */ +void kmsan_kfree_large(const void *ptr); + +/** + * kmsan_map_kernel_range_noflush() - Notify KMSAN about a vmap. + * @start: start of vmapped range. + * @end: end of vmapped range. + * @prot: page protection flags used for vmap. + * @pages: array of pages. + * @page_shift: page_shift passed to vmap_range_noflush(). + * + * KMSAN maps shadow and origin pages of @pages into contiguous ranges in + * vmalloc metadata address range. + */ +void kmsan_vmap_pages_range_noflush(unsigned long start, unsigned long end, + pgprot_t prot, struct page **pages, + unsigned int page_shift); + +/** + * kmsan_vunmap_kernel_range_noflush() - Notify KMSAN about a vunmap. + * @start: start of vunmapped range. + * @end: end of vunmapped range. + * + * KMSAN unmaps the contiguous metadata ranges created by + * kmsan_map_kernel_range_noflush(). + */ +void kmsan_vunmap_range_noflush(unsigned long start, unsigned long end); + +/** + * kmsan_ioremap_page_range() - Notify KMSAN about a ioremap_page_range() call. + * @addr: range start. + * @end: range end. + * @phys_addr: physical range start. + * @prot: page protection flags used for ioremap_page_range(). + * @page_shift: page_shift argument passed to vmap_range_noflush(). + * + * KMSAN creates new metadata pages for the physical pages mapped into the + * virtual memory. + */ +void kmsan_ioremap_page_range(unsigned long addr, unsigned long end, + phys_addr_t phys_addr, pgprot_t prot, + unsigned int page_shift); + +/** + * kmsan_iounmap_page_range() - Notify KMSAN about a iounmap_page_range() call. + * @start: range start. + * @end: range end. + * + * KMSAN unmaps the metadata pages for the given range and, unlike for + * vunmap_page_range(), also deallocates them. + */ +void kmsan_iounmap_page_range(unsigned long start, unsigned long end); + +/** + * kmsan_handle_dma() - Handle a DMA data transfer. + * @page: first page of the buffer. + * @offset: offset of the buffer within the first page. + * @size: buffer size. + * @dir: one of possible dma_data_direction values. + * + * Depending on @direction, KMSAN: + * * checks the buffer, if it is copied to device; + * * initializes the buffer, if it is copied from device; + * * does both, if this is a DMA_BIDIRECTIONAL transfer. + */ +void kmsan_handle_dma(struct page *page, size_t offset, size_t size, + enum dma_data_direction dir); + +/** + * kmsan_handle_dma_sg() - Handle a DMA transfer using scatterlist. + * @sg: scatterlist holding DMA buffers. + * @nents: number of scatterlist entries. + * @dir: one of possible dma_data_direction values. + * + * Depending on @direction, KMSAN: + * * checks the buffers in the scatterlist, if they are copied to device; + * * initializes the buffers, if they are copied from device; + * * does both, if this is a DMA_BIDIRECTIONAL transfer. + */ +void kmsan_handle_dma_sg(struct scatterlist *sg, int nents, + enum dma_data_direction dir); + +/** + * kmsan_handle_urb() - Handle a USB data transfer. + * @urb: struct urb pointer. + * @is_out: data transfer direction (true means output to hardware). + * + * If @is_out is true, KMSAN checks the transfer buffer of @urb. Otherwise, + * KMSAN initializes the transfer buffer. + */ +void kmsan_handle_urb(const struct urb *urb, bool is_out); + +/** + * kmsan_unpoison_entry_regs() - Handle pt_regs in low-level entry code. + * @regs: struct pt_regs pointer received from assembly code. + * + * KMSAN unpoisons the contents of the passed pt_regs, preventing potential + * false positive reports. Unlike kmsan_unpoison_memory(), + * kmsan_unpoison_entry_regs() can be called from the regions where + * kmsan_in_runtime() returns true, which is the case in early entry code. + */ +void kmsan_unpoison_entry_regs(const struct pt_regs *regs); + +#else + +static inline void kmsan_init_shadow(void) +{ +} + +static inline void kmsan_init_runtime(void) +{ +} + +static inline bool kmsan_memblock_free_pages(struct page *page, + unsigned int order) +{ + return true; +} + +static inline void kmsan_task_create(struct task_struct *task) +{ +} + +static inline void kmsan_task_exit(struct task_struct *task) +{ +} + +static inline int kmsan_alloc_page(struct page *page, unsigned int order, + gfp_t flags) +{ + return 0; +} + +static inline void kmsan_free_page(struct page *page, unsigned int order) +{ +} + +static inline void kmsan_copy_page_meta(struct page *dst, struct page *src) +{ +} + +static inline void kmsan_slab_alloc(struct kmem_cache *s, void *object, + gfp_t flags) +{ +} + +static inline void kmsan_slab_free(struct kmem_cache *s, void *object) +{ +} + +static inline void kmsan_kmalloc_large(const void *ptr, size_t size, + gfp_t flags) +{ +} + +static inline void kmsan_kfree_large(const void *ptr) +{ +} + +static inline void kmsan_vmap_pages_range_noflush(unsigned long start, + unsigned long end, + pgprot_t prot, + struct page **pages, + unsigned int page_shift) +{ +} + +static inline void kmsan_vunmap_range_noflush(unsigned long start, + unsigned long end) +{ +} + +static inline void kmsan_ioremap_page_range(unsigned long start, + unsigned long end, + phys_addr_t phys_addr, + pgprot_t prot, + unsigned int page_shift) +{ +} + +static inline void kmsan_iounmap_page_range(unsigned long start, + unsigned long end) +{ +} + +static inline void kmsan_handle_dma(struct page *page, size_t offset, + size_t size, enum dma_data_direction dir) +{ +} + +static inline void kmsan_handle_dma_sg(struct scatterlist *sg, int nents, + enum dma_data_direction dir) +{ +} + +static inline void kmsan_handle_urb(const struct urb *urb, bool is_out) +{ +} + +static inline void kmsan_unpoison_entry_regs(const struct pt_regs *regs) +{ +} + +#endif + +#endif /* _LINUX_KMSAN_H */ diff --git a/include/linux/kmsan_string.h b/include/linux/kmsan_string.h new file mode 100644 index 000000000000..7287da6f52ef --- /dev/null +++ b/include/linux/kmsan_string.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * KMSAN string functions API used in other headers. + * + * Copyright (C) 2022 Google LLC + * Author: Alexander Potapenko <glider@google.com> + * + */ +#ifndef _LINUX_KMSAN_STRING_H +#define _LINUX_KMSAN_STRING_H + +/* + * KMSAN overrides the default memcpy/memset/memmove implementations in the + * kernel, which requires having __msan_XXX function prototypes in several other + * headers. Keep them in one place instead of open-coding. + */ +void *__msan_memcpy(void *dst, const void *src, size_t size); +void *__msan_memset(void *s, int c, size_t n); +void *__msan_memmove(void *dest, const void *src, size_t len); + +#endif /* _LINUX_KMSAN_STRING_H */ diff --git a/include/linux/kmsan_types.h b/include/linux/kmsan_types.h new file mode 100644 index 000000000000..8bfa6c98176d --- /dev/null +++ b/include/linux/kmsan_types.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * A minimal header declaring types added by KMSAN to existing kernel structs. + * + * Copyright (C) 2017-2022 Google LLC + * Author: Alexander Potapenko <glider@google.com> + * + */ +#ifndef _LINUX_KMSAN_TYPES_H +#define _LINUX_KMSAN_TYPES_H + +/* These constants are defined in the MSan LLVM instrumentation pass. */ +#define KMSAN_RETVAL_SIZE 800 +#define KMSAN_PARAM_SIZE 800 + +struct kmsan_context_state { + char param_tls[KMSAN_PARAM_SIZE]; + char retval_tls[KMSAN_RETVAL_SIZE]; + char va_arg_tls[KMSAN_PARAM_SIZE]; + char va_arg_origin_tls[KMSAN_PARAM_SIZE]; + u64 va_arg_overflow_size_tls; + char param_origin_tls[KMSAN_PARAM_SIZE]; + u32 retval_origin_tls; +}; + +#undef KMSAN_PARAM_SIZE +#undef KMSAN_RETVAL_SIZE + +struct kmsan_ctx { + struct kmsan_context_state cstate; + int kmsan_in_runtime; + bool allow_reporting; +}; + +#endif /* _LINUX_KMSAN_TYPES_H */ diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 0b4f17418f64..7e232ba59b86 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -15,9 +15,6 @@ #include <linux/sched.h> #include <linux/sched/coredump.h> -struct stable_node; -struct mem_cgroup; - #ifdef CONFIG_KSM int ksm_madvise(struct vm_area_struct *vma, unsigned long start, unsigned long end, int advice, unsigned long *vm_flags); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 32f259fa5801..18592bdf4c1b 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1240,8 +1240,18 @@ int kvm_vcpu_write_guest(struct kvm_vcpu *vcpu, gpa_t gpa, const void *data, void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn); /** - * kvm_gfn_to_pfn_cache_init - prepare a cached kernel mapping and HPA for a - * given guest physical address. + * kvm_gpc_init - initialize gfn_to_pfn_cache. + * + * @gpc: struct gfn_to_pfn_cache object. + * + * This sets up a gfn_to_pfn_cache by initializing locks. Note, the cache must + * be zero-allocated (or zeroed by the caller before init). + */ +void kvm_gpc_init(struct gfn_to_pfn_cache *gpc); + +/** + * kvm_gpc_activate - prepare a cached kernel mapping and HPA for a given guest + * physical address. * * @kvm: pointer to kvm instance. * @gpc: struct gfn_to_pfn_cache object. @@ -1265,9 +1275,9 @@ void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn); * kvm_gfn_to_pfn_cache_check() to ensure that the cache is valid before * accessing the target page. */ -int kvm_gfn_to_pfn_cache_init(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, - struct kvm_vcpu *vcpu, enum pfn_cache_usage usage, - gpa_t gpa, unsigned long len); +int kvm_gpc_activate(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, + struct kvm_vcpu *vcpu, enum pfn_cache_usage usage, + gpa_t gpa, unsigned long len); /** * kvm_gfn_to_pfn_cache_check - check validity of a gfn_to_pfn_cache. @@ -1324,7 +1334,7 @@ int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, void kvm_gfn_to_pfn_cache_unmap(struct kvm *kvm, struct gfn_to_pfn_cache *gpc); /** - * kvm_gfn_to_pfn_cache_destroy - destroy and unlink a gfn_to_pfn_cache. + * kvm_gpc_deactivate - deactivate and unlink a gfn_to_pfn_cache. * * @kvm: pointer to kvm instance. * @gpc: struct gfn_to_pfn_cache object. @@ -1332,7 +1342,7 @@ void kvm_gfn_to_pfn_cache_unmap(struct kvm *kvm, struct gfn_to_pfn_cache *gpc); * This removes a cache from the @kvm's list to be processed on MMU notifier * invocation. */ -void kvm_gfn_to_pfn_cache_destroy(struct kvm *kvm, struct gfn_to_pfn_cache *gpc); +void kvm_gpc_deactivate(struct kvm *kvm, struct gfn_to_pfn_cache *gpc); void kvm_sigset_activate(struct kvm_vcpu *vcpu); void kvm_sigset_deactivate(struct kvm_vcpu *vcpu); @@ -1390,6 +1400,8 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap); long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); +long kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl, + unsigned long arg); int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu); int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu); diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h new file mode 100644 index 000000000000..e594db58a0f1 --- /dev/null +++ b/include/linux/maple_tree.h @@ -0,0 +1,692 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +#ifndef _LINUX_MAPLE_TREE_H +#define _LINUX_MAPLE_TREE_H +/* + * Maple Tree - An RCU-safe adaptive tree for storing ranges + * Copyright (c) 2018-2022 Oracle + * Authors: Liam R. Howlett <Liam.Howlett@Oracle.com> + * Matthew Wilcox <willy@infradead.org> + */ + +#include <linux/kernel.h> +#include <linux/rcupdate.h> +#include <linux/spinlock.h> +/* #define CONFIG_MAPLE_RCU_DISABLED */ +/* #define CONFIG_DEBUG_MAPLE_TREE_VERBOSE */ + +/* + * Allocated nodes are mutable until they have been inserted into the tree, + * at which time they cannot change their type until they have been removed + * from the tree and an RCU grace period has passed. + * + * Removed nodes have their ->parent set to point to themselves. RCU readers + * check ->parent before relying on the value that they loaded from the + * slots array. This lets us reuse the slots array for the RCU head. + * + * Nodes in the tree point to their parent unless bit 0 is set. + */ +#if defined(CONFIG_64BIT) || defined(BUILD_VDSO32_64) +/* 64bit sizes */ +#define MAPLE_NODE_SLOTS 31 /* 256 bytes including ->parent */ +#define MAPLE_RANGE64_SLOTS 16 /* 256 bytes */ +#define MAPLE_ARANGE64_SLOTS 10 /* 240 bytes */ +#define MAPLE_ARANGE64_META_MAX 15 /* Out of range for metadata */ +#define MAPLE_ALLOC_SLOTS (MAPLE_NODE_SLOTS - 1) +#else +/* 32bit sizes */ +#define MAPLE_NODE_SLOTS 63 /* 256 bytes including ->parent */ +#define MAPLE_RANGE64_SLOTS 32 /* 256 bytes */ +#define MAPLE_ARANGE64_SLOTS 21 /* 240 bytes */ +#define MAPLE_ARANGE64_META_MAX 31 /* Out of range for metadata */ +#define MAPLE_ALLOC_SLOTS (MAPLE_NODE_SLOTS - 2) +#endif /* defined(CONFIG_64BIT) || defined(BUILD_VDSO32_64) */ + +#define MAPLE_NODE_MASK 255UL + +/* + * The node->parent of the root node has bit 0 set and the rest of the pointer + * is a pointer to the tree itself. No more bits are available in this pointer + * (on m68k, the data structure may only be 2-byte aligned). + * + * Internal non-root nodes can only have maple_range_* nodes as parents. The + * parent pointer is 256B aligned like all other tree nodes. When storing a 32 + * or 64 bit values, the offset can fit into 4 bits. The 16 bit values need an + * extra bit to store the offset. This extra bit comes from a reuse of the last + * bit in the node type. This is possible by using bit 1 to indicate if bit 2 + * is part of the type or the slot. + * + * Once the type is decided, the decision of an allocation range type or a range + * type is done by examining the immutable tree flag for the MAPLE_ALLOC_RANGE + * flag. + * + * Node types: + * 0x??1 = Root + * 0x?00 = 16 bit nodes + * 0x010 = 32 bit nodes + * 0x110 = 64 bit nodes + * + * Slot size and location in the parent pointer: + * type : slot location + * 0x??1 : Root + * 0x?00 : 16 bit values, type in 0-1, slot in 2-6 + * 0x010 : 32 bit values, type in 0-2, slot in 3-6 + * 0x110 : 64 bit values, type in 0-2, slot in 3-6 + */ + +/* + * This metadata is used to optimize the gap updating code and in reverse + * searching for gaps or any other code that needs to find the end of the data. + */ +struct maple_metadata { + unsigned char end; + unsigned char gap; +}; + +/* + * Leaf nodes do not store pointers to nodes, they store user data. Users may + * store almost any bit pattern. As noted above, the optimisation of storing an + * entry at 0 in the root pointer cannot be done for data which have the bottom + * two bits set to '10'. We also reserve values with the bottom two bits set to + * '10' which are below 4096 (ie 2, 6, 10 .. 4094) for internal use. Some APIs + * return errnos as a negative errno shifted right by two bits and the bottom + * two bits set to '10', and while choosing to store these values in the array + * is not an error, it may lead to confusion if you're testing for an error with + * mas_is_err(). + * + * Non-leaf nodes store the type of the node pointed to (enum maple_type in bits + * 3-6), bit 2 is reserved. That leaves bits 0-1 unused for now. + * + * In regular B-Tree terms, pivots are called keys. The term pivot is used to + * indicate that the tree is specifying ranges, Pivots may appear in the + * subtree with an entry attached to the value whereas keys are unique to a + * specific position of a B-tree. Pivot values are inclusive of the slot with + * the same index. + */ + +struct maple_range_64 { + struct maple_pnode *parent; + unsigned long pivot[MAPLE_RANGE64_SLOTS - 1]; + union { + void __rcu *slot[MAPLE_RANGE64_SLOTS]; + struct { + void __rcu *pad[MAPLE_RANGE64_SLOTS - 1]; + struct maple_metadata meta; + }; + }; +}; + +/* + * At tree creation time, the user can specify that they're willing to trade off + * storing fewer entries in a tree in return for storing more information in + * each node. + * + * The maple tree supports recording the largest range of NULL entries available + * in this node, also called gaps. This optimises the tree for allocating a + * range. + */ +struct maple_arange_64 { + struct maple_pnode *parent; + unsigned long pivot[MAPLE_ARANGE64_SLOTS - 1]; + void __rcu *slot[MAPLE_ARANGE64_SLOTS]; + unsigned long gap[MAPLE_ARANGE64_SLOTS]; + struct maple_metadata meta; +}; + +struct maple_alloc { + unsigned long total; + unsigned char node_count; + unsigned int request_count; + struct maple_alloc *slot[MAPLE_ALLOC_SLOTS]; +}; + +struct maple_topiary { + struct maple_pnode *parent; + struct maple_enode *next; /* Overlaps the pivot */ +}; + +enum maple_type { + maple_dense, + maple_leaf_64, + maple_range_64, + maple_arange_64, +}; + + +/** + * DOC: Maple tree flags + * + * * MT_FLAGS_ALLOC_RANGE - Track gaps in this tree + * * MT_FLAGS_USE_RCU - Operate in RCU mode + * * MT_FLAGS_HEIGHT_OFFSET - The position of the tree height in the flags + * * MT_FLAGS_HEIGHT_MASK - The mask for the maple tree height value + * * MT_FLAGS_LOCK_MASK - How the mt_lock is used + * * MT_FLAGS_LOCK_IRQ - Acquired irq-safe + * * MT_FLAGS_LOCK_BH - Acquired bh-safe + * * MT_FLAGS_LOCK_EXTERN - mt_lock is not used + * + * MAPLE_HEIGHT_MAX The largest height that can be stored + */ +#define MT_FLAGS_ALLOC_RANGE 0x01 +#define MT_FLAGS_USE_RCU 0x02 +#define MT_FLAGS_HEIGHT_OFFSET 0x02 +#define MT_FLAGS_HEIGHT_MASK 0x7C +#define MT_FLAGS_LOCK_MASK 0x300 +#define MT_FLAGS_LOCK_IRQ 0x100 +#define MT_FLAGS_LOCK_BH 0x200 +#define MT_FLAGS_LOCK_EXTERN 0x300 + +#define MAPLE_HEIGHT_MAX 31 + + +#define MAPLE_NODE_TYPE_MASK 0x0F +#define MAPLE_NODE_TYPE_SHIFT 0x03 + +#define MAPLE_RESERVED_RANGE 4096 + +#ifdef CONFIG_LOCKDEP +typedef struct lockdep_map *lockdep_map_p; +#define mt_lock_is_held(mt) lock_is_held(mt->ma_external_lock) +#define mt_set_external_lock(mt, lock) \ + (mt)->ma_external_lock = &(lock)->dep_map +#else +typedef struct { /* nothing */ } lockdep_map_p; +#define mt_lock_is_held(mt) 1 +#define mt_set_external_lock(mt, lock) do { } while (0) +#endif + +/* + * If the tree contains a single entry at index 0, it is usually stored in + * tree->ma_root. To optimise for the page cache, an entry which ends in '00', + * '01' or '11' is stored in the root, but an entry which ends in '10' will be + * stored in a node. Bits 3-6 are used to store enum maple_type. + * + * The flags are used both to store some immutable information about this tree + * (set at tree creation time) and dynamic information set under the spinlock. + * + * Another use of flags are to indicate global states of the tree. This is the + * case with the MAPLE_USE_RCU flag, which indicates the tree is currently in + * RCU mode. This mode was added to allow the tree to reuse nodes instead of + * re-allocating and RCU freeing nodes when there is a single user. + */ +struct maple_tree { + union { + spinlock_t ma_lock; + lockdep_map_p ma_external_lock; + }; + void __rcu *ma_root; + unsigned int ma_flags; +}; + +/** + * MTREE_INIT() - Initialize a maple tree + * @name: The maple tree name + * @__flags: The maple tree flags + * + */ +#define MTREE_INIT(name, __flags) { \ + .ma_lock = __SPIN_LOCK_UNLOCKED((name).ma_lock), \ + .ma_flags = __flags, \ + .ma_root = NULL, \ +} + +/** + * MTREE_INIT_EXT() - Initialize a maple tree with an external lock. + * @name: The tree name + * @__flags: The maple tree flags + * @__lock: The external lock + */ +#ifdef CONFIG_LOCKDEP +#define MTREE_INIT_EXT(name, __flags, __lock) { \ + .ma_external_lock = &(__lock).dep_map, \ + .ma_flags = (__flags), \ + .ma_root = NULL, \ +} +#else +#define MTREE_INIT_EXT(name, __flags, __lock) MTREE_INIT(name, __flags) +#endif + +#define DEFINE_MTREE(name) \ + struct maple_tree name = MTREE_INIT(name, 0) + +#define mtree_lock(mt) spin_lock((&(mt)->ma_lock)) +#define mtree_unlock(mt) spin_unlock((&(mt)->ma_lock)) + +/* + * The Maple Tree squeezes various bits in at various points which aren't + * necessarily obvious. Usually, this is done by observing that pointers are + * N-byte aligned and thus the bottom log_2(N) bits are available for use. We + * don't use the high bits of pointers to store additional information because + * we don't know what bits are unused on any given architecture. + * + * Nodes are 256 bytes in size and are also aligned to 256 bytes, giving us 8 + * low bits for our own purposes. Nodes are currently of 4 types: + * 1. Single pointer (Range is 0-0) + * 2. Non-leaf Allocation Range nodes + * 3. Non-leaf Range nodes + * 4. Leaf Range nodes All nodes consist of a number of node slots, + * pivots, and a parent pointer. + */ + +struct maple_node { + union { + struct { + struct maple_pnode *parent; + void __rcu *slot[MAPLE_NODE_SLOTS]; + }; + struct { + void *pad; + struct rcu_head rcu; + struct maple_enode *piv_parent; + unsigned char parent_slot; + enum maple_type type; + unsigned char slot_len; + unsigned int ma_flags; + }; + struct maple_range_64 mr64; + struct maple_arange_64 ma64; + struct maple_alloc alloc; + }; +}; + +/* + * More complicated stores can cause two nodes to become one or three and + * potentially alter the height of the tree. Either half of the tree may need + * to be rebalanced against the other. The ma_topiary struct is used to track + * which nodes have been 'cut' from the tree so that the change can be done + * safely at a later date. This is done to support RCU. + */ +struct ma_topiary { + struct maple_enode *head; + struct maple_enode *tail; + struct maple_tree *mtree; +}; + +void *mtree_load(struct maple_tree *mt, unsigned long index); + +int mtree_insert(struct maple_tree *mt, unsigned long index, + void *entry, gfp_t gfp); +int mtree_insert_range(struct maple_tree *mt, unsigned long first, + unsigned long last, void *entry, gfp_t gfp); +int mtree_alloc_range(struct maple_tree *mt, unsigned long *startp, + void *entry, unsigned long size, unsigned long min, + unsigned long max, gfp_t gfp); +int mtree_alloc_rrange(struct maple_tree *mt, unsigned long *startp, + void *entry, unsigned long size, unsigned long min, + unsigned long max, gfp_t gfp); + +int mtree_store_range(struct maple_tree *mt, unsigned long first, + unsigned long last, void *entry, gfp_t gfp); +int mtree_store(struct maple_tree *mt, unsigned long index, + void *entry, gfp_t gfp); +void *mtree_erase(struct maple_tree *mt, unsigned long index); + +void mtree_destroy(struct maple_tree *mt); +void __mt_destroy(struct maple_tree *mt); + +/** + * mtree_empty() - Determine if a tree has any present entries. + * @mt: Maple Tree. + * + * Context: Any context. + * Return: %true if the tree contains only NULL pointers. + */ +static inline bool mtree_empty(const struct maple_tree *mt) +{ + return mt->ma_root == NULL; +} + +/* Advanced API */ + +/* + * The maple state is defined in the struct ma_state and is used to keep track + * of information during operations, and even between operations when using the + * advanced API. + * + * If state->node has bit 0 set then it references a tree location which is not + * a node (eg the root). If bit 1 is set, the rest of the bits are a negative + * errno. Bit 2 (the 'unallocated slots' bit) is clear. Bits 3-6 indicate the + * node type. + * + * state->alloc either has a request number of nodes or an allocated node. If + * stat->alloc has a requested number of nodes, the first bit will be set (0x1) + * and the remaining bits are the value. If state->alloc is a node, then the + * node will be of type maple_alloc. maple_alloc has MAPLE_NODE_SLOTS - 1 for + * storing more allocated nodes, a total number of nodes allocated, and the + * node_count in this node. node_count is the number of allocated nodes in this + * node. The scaling beyond MAPLE_NODE_SLOTS - 1 is handled by storing further + * nodes into state->alloc->slot[0]'s node. Nodes are taken from state->alloc + * by removing a node from the state->alloc node until state->alloc->node_count + * is 1, when state->alloc is returned and the state->alloc->slot[0] is promoted + * to state->alloc. Nodes are pushed onto state->alloc by putting the current + * state->alloc into the pushed node's slot[0]. + * + * The state also contains the implied min/max of the state->node, the depth of + * this search, and the offset. The implied min/max are either from the parent + * node or are 0-oo for the root node. The depth is incremented or decremented + * every time a node is walked down or up. The offset is the slot/pivot of + * interest in the node - either for reading or writing. + * + * When returning a value the maple state index and last respectively contain + * the start and end of the range for the entry. Ranges are inclusive in the + * Maple Tree. + */ +struct ma_state { + struct maple_tree *tree; /* The tree we're operating in */ + unsigned long index; /* The index we're operating on - range start */ + unsigned long last; /* The last index we're operating on - range end */ + struct maple_enode *node; /* The node containing this entry */ + unsigned long min; /* The minimum index of this node - implied pivot min */ + unsigned long max; /* The maximum index of this node - implied pivot max */ + struct maple_alloc *alloc; /* Allocated nodes for this operation */ + unsigned char depth; /* depth of tree descent during write */ + unsigned char offset; + unsigned char mas_flags; +}; + +struct ma_wr_state { + struct ma_state *mas; + struct maple_node *node; /* Decoded mas->node */ + unsigned long r_min; /* range min */ + unsigned long r_max; /* range max */ + enum maple_type type; /* mas->node type */ + unsigned char offset_end; /* The offset where the write ends */ + unsigned char node_end; /* mas->node end */ + unsigned long *pivots; /* mas->node->pivots pointer */ + unsigned long end_piv; /* The pivot at the offset end */ + void __rcu **slots; /* mas->node->slots pointer */ + void *entry; /* The entry to write */ + void *content; /* The existing entry that is being overwritten */ +}; + +#define mas_lock(mas) spin_lock(&((mas)->tree->ma_lock)) +#define mas_unlock(mas) spin_unlock(&((mas)->tree->ma_lock)) + + +/* + * Special values for ma_state.node. + * MAS_START means we have not searched the tree. + * MAS_ROOT means we have searched the tree and the entry we found lives in + * the root of the tree (ie it has index 0, length 1 and is the only entry in + * the tree). + * MAS_NONE means we have searched the tree and there is no node in the + * tree for this entry. For example, we searched for index 1 in an empty + * tree. Or we have a tree which points to a full leaf node and we + * searched for an entry which is larger than can be contained in that + * leaf node. + * MA_ERROR represents an errno. After dropping the lock and attempting + * to resolve the error, the walk would have to be restarted from the + * top of the tree as the tree may have been modified. + */ +#define MAS_START ((struct maple_enode *)1UL) +#define MAS_ROOT ((struct maple_enode *)5UL) +#define MAS_NONE ((struct maple_enode *)9UL) +#define MAS_PAUSE ((struct maple_enode *)17UL) +#define MA_ERROR(err) \ + ((struct maple_enode *)(((unsigned long)err << 2) | 2UL)) + +#define MA_STATE(name, mt, first, end) \ + struct ma_state name = { \ + .tree = mt, \ + .index = first, \ + .last = end, \ + .node = MAS_START, \ + .min = 0, \ + .max = ULONG_MAX, \ + .alloc = NULL, \ + } + +#define MA_WR_STATE(name, ma_state, wr_entry) \ + struct ma_wr_state name = { \ + .mas = ma_state, \ + .content = NULL, \ + .entry = wr_entry, \ + } + +#define MA_TOPIARY(name, tree) \ + struct ma_topiary name = { \ + .head = NULL, \ + .tail = NULL, \ + .mtree = tree, \ + } + +void *mas_walk(struct ma_state *mas); +void *mas_store(struct ma_state *mas, void *entry); +void *mas_erase(struct ma_state *mas); +int mas_store_gfp(struct ma_state *mas, void *entry, gfp_t gfp); +void mas_store_prealloc(struct ma_state *mas, void *entry); +void *mas_find(struct ma_state *mas, unsigned long max); +void *mas_find_rev(struct ma_state *mas, unsigned long min); +int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp); +bool mas_is_err(struct ma_state *mas); + +bool mas_nomem(struct ma_state *mas, gfp_t gfp); +void mas_pause(struct ma_state *mas); +void maple_tree_init(void); +void mas_destroy(struct ma_state *mas); +int mas_expected_entries(struct ma_state *mas, unsigned long nr_entries); + +void *mas_prev(struct ma_state *mas, unsigned long min); +void *mas_next(struct ma_state *mas, unsigned long max); + +int mas_empty_area(struct ma_state *mas, unsigned long min, unsigned long max, + unsigned long size); + +/* Checks if a mas has not found anything */ +static inline bool mas_is_none(struct ma_state *mas) +{ + return mas->node == MAS_NONE; +} + +/* Checks if a mas has been paused */ +static inline bool mas_is_paused(struct ma_state *mas) +{ + return mas->node == MAS_PAUSE; +} + +void mas_dup_tree(struct ma_state *oldmas, struct ma_state *mas); +void mas_dup_store(struct ma_state *mas, void *entry); + +/* + * This finds an empty area from the highest address to the lowest. + * AKA "Topdown" version, + */ +int mas_empty_area_rev(struct ma_state *mas, unsigned long min, + unsigned long max, unsigned long size); +/** + * mas_reset() - Reset a Maple Tree operation state. + * @mas: Maple Tree operation state. + * + * Resets the error or walk state of the @mas so future walks of the + * array will start from the root. Use this if you have dropped the + * lock and want to reuse the ma_state. + * + * Context: Any context. + */ +static inline void mas_reset(struct ma_state *mas) +{ + mas->node = MAS_START; +} + +/** + * mas_for_each() - Iterate over a range of the maple tree. + * @__mas: Maple Tree operation state (maple_state) + * @__entry: Entry retrieved from the tree + * @__max: maximum index to retrieve from the tree + * + * When returned, mas->index and mas->last will hold the entire range for the + * entry. + * + * Note: may return the zero entry. + * + */ +#define mas_for_each(__mas, __entry, __max) \ + while (((__entry) = mas_find((__mas), (__max))) != NULL) + + +/** + * mas_set_range() - Set up Maple Tree operation state for a different index. + * @mas: Maple Tree operation state. + * @start: New start of range in the Maple Tree. + * @last: New end of range in the Maple Tree. + * + * Move the operation state to refer to a different range. This will + * have the effect of starting a walk from the top; see mas_next() + * to move to an adjacent index. + */ +static inline +void mas_set_range(struct ma_state *mas, unsigned long start, unsigned long last) +{ + mas->index = start; + mas->last = last; + mas->node = MAS_START; +} + +/** + * mas_set() - Set up Maple Tree operation state for a different index. + * @mas: Maple Tree operation state. + * @index: New index into the Maple Tree. + * + * Move the operation state to refer to a different index. This will + * have the effect of starting a walk from the top; see mas_next() + * to move to an adjacent index. + */ +static inline void mas_set(struct ma_state *mas, unsigned long index) +{ + + mas_set_range(mas, index, index); +} + +static inline bool mt_external_lock(const struct maple_tree *mt) +{ + return (mt->ma_flags & MT_FLAGS_LOCK_MASK) == MT_FLAGS_LOCK_EXTERN; +} + +/** + * mt_init_flags() - Initialise an empty maple tree with flags. + * @mt: Maple Tree + * @flags: maple tree flags. + * + * If you need to initialise a Maple Tree with special flags (eg, an + * allocation tree), use this function. + * + * Context: Any context. + */ +static inline void mt_init_flags(struct maple_tree *mt, unsigned int flags) +{ + mt->ma_flags = flags; + if (!mt_external_lock(mt)) + spin_lock_init(&mt->ma_lock); + rcu_assign_pointer(mt->ma_root, NULL); +} + +/** + * mt_init() - Initialise an empty maple tree. + * @mt: Maple Tree + * + * An empty Maple Tree. + * + * Context: Any context. + */ +static inline void mt_init(struct maple_tree *mt) +{ + mt_init_flags(mt, 0); +} + +static inline bool mt_in_rcu(struct maple_tree *mt) +{ +#ifdef CONFIG_MAPLE_RCU_DISABLED + return false; +#endif + return mt->ma_flags & MT_FLAGS_USE_RCU; +} + +/** + * mt_clear_in_rcu() - Switch the tree to non-RCU mode. + * @mt: The Maple Tree + */ +static inline void mt_clear_in_rcu(struct maple_tree *mt) +{ + if (!mt_in_rcu(mt)) + return; + + if (mt_external_lock(mt)) { + BUG_ON(!mt_lock_is_held(mt)); + mt->ma_flags &= ~MT_FLAGS_USE_RCU; + } else { + mtree_lock(mt); + mt->ma_flags &= ~MT_FLAGS_USE_RCU; + mtree_unlock(mt); + } +} + +/** + * mt_set_in_rcu() - Switch the tree to RCU safe mode. + * @mt: The Maple Tree + */ +static inline void mt_set_in_rcu(struct maple_tree *mt) +{ + if (mt_in_rcu(mt)) + return; + + if (mt_external_lock(mt)) { + BUG_ON(!mt_lock_is_held(mt)); + mt->ma_flags |= MT_FLAGS_USE_RCU; + } else { + mtree_lock(mt); + mt->ma_flags |= MT_FLAGS_USE_RCU; + mtree_unlock(mt); + } +} + +static inline unsigned int mt_height(const struct maple_tree *mt) + +{ + return (mt->ma_flags & MT_FLAGS_HEIGHT_MASK) >> MT_FLAGS_HEIGHT_OFFSET; +} + +void *mt_find(struct maple_tree *mt, unsigned long *index, unsigned long max); +void *mt_find_after(struct maple_tree *mt, unsigned long *index, + unsigned long max); +void *mt_prev(struct maple_tree *mt, unsigned long index, unsigned long min); +void *mt_next(struct maple_tree *mt, unsigned long index, unsigned long max); + +/** + * mt_for_each - Iterate over each entry starting at index until max. + * @__tree: The Maple Tree + * @__entry: The current entry + * @__index: The index to update to track the location in the tree + * @__max: The maximum limit for @index + * + * Note: Will not return the zero entry. + */ +#define mt_for_each(__tree, __entry, __index, __max) \ + for (__entry = mt_find(__tree, &(__index), __max); \ + __entry; __entry = mt_find_after(__tree, &(__index), __max)) + + +#ifdef CONFIG_DEBUG_MAPLE_TREE +extern atomic_t maple_tree_tests_run; +extern atomic_t maple_tree_tests_passed; + +void mt_dump(const struct maple_tree *mt); +void mt_validate(struct maple_tree *mt); +void mt_cache_shrink(void); +#define MT_BUG_ON(__tree, __x) do { \ + atomic_inc(&maple_tree_tests_run); \ + if (__x) { \ + pr_info("BUG at %s:%d (%u)\n", \ + __func__, __LINE__, __x); \ + mt_dump(__tree); \ + pr_info("Pass: %u Run:%u\n", \ + atomic_read(&maple_tree_tests_passed), \ + atomic_read(&maple_tree_tests_run)); \ + dump_stack(); \ + } else { \ + atomic_inc(&maple_tree_tests_passed); \ + } \ +} while (0) +#else +#define MT_BUG_ON(__tree, __x) BUG_ON(__x) +#endif /* CONFIG_DEBUG_MAPLE_TREE */ + +#endif /*_LINUX_MAPLE_TREE_H */ diff --git a/include/linux/mdev.h b/include/linux/mdev.h index 47ad3b104d9e..139d05b26f82 100644 --- a/include/linux/mdev.h +++ b/include/linux/mdev.h @@ -10,6 +10,9 @@ #ifndef MDEV_H #define MDEV_H +#include <linux/device.h> +#include <linux/uuid.h> + struct mdev_type; struct mdev_device { @@ -20,67 +23,67 @@ struct mdev_device { bool active; }; -static inline struct mdev_device *to_mdev_device(struct device *dev) -{ - return container_of(dev, struct mdev_device, dev); -} +struct mdev_type { + /* set by the driver before calling mdev_register parent: */ + const char *sysfs_name; + const char *pretty_name; -unsigned int mdev_get_type_group_id(struct mdev_device *mdev); -unsigned int mtype_get_type_group_id(struct mdev_type *mtype); -struct device *mtype_get_parent_dev(struct mdev_type *mtype); + /* set by the core, can be used drivers */ + struct mdev_parent *parent; -/* interface for exporting mdev supported type attributes */ -struct mdev_type_attribute { - struct attribute attr; - ssize_t (*show)(struct mdev_type *mtype, - struct mdev_type_attribute *attr, char *buf); - ssize_t (*store)(struct mdev_type *mtype, - struct mdev_type_attribute *attr, const char *buf, - size_t count); + /* internal only */ + struct kobject kobj; + struct kobject *devices_kobj; }; -#define MDEV_TYPE_ATTR(_name, _mode, _show, _store) \ -struct mdev_type_attribute mdev_type_attr_##_name = \ - __ATTR(_name, _mode, _show, _store) -#define MDEV_TYPE_ATTR_RW(_name) \ - struct mdev_type_attribute mdev_type_attr_##_name = __ATTR_RW(_name) -#define MDEV_TYPE_ATTR_RO(_name) \ - struct mdev_type_attribute mdev_type_attr_##_name = __ATTR_RO(_name) -#define MDEV_TYPE_ATTR_WO(_name) \ - struct mdev_type_attribute mdev_type_attr_##_name = __ATTR_WO(_name) +/* embedded into the struct device that the mdev devices hang off */ +struct mdev_parent { + struct device *dev; + struct mdev_driver *mdev_driver; + struct kset *mdev_types_kset; + /* Synchronize device creation/removal with parent unregistration */ + struct rw_semaphore unreg_sem; + struct mdev_type **types; + unsigned int nr_types; + atomic_t available_instances; +}; + +static inline struct mdev_device *to_mdev_device(struct device *dev) +{ + return container_of(dev, struct mdev_device, dev); +} /** * struct mdev_driver - Mediated device driver + * @device_api: string to return for the device_api sysfs + * @max_instances: maximum number of instances supported (optional) * @probe: called when new device created * @remove: called when device removed - * @supported_type_groups: Attributes to define supported types. It is mandatory - * to provide supported types. + * @get_available: Return the max number of instances that can be created + * @show_description: Print a description of the mtype * @driver: device driver structure - * **/ struct mdev_driver { + const char *device_api; + unsigned int max_instances; int (*probe)(struct mdev_device *dev); void (*remove)(struct mdev_device *dev); - struct attribute_group **supported_type_groups; + unsigned int (*get_available)(struct mdev_type *mtype); + ssize_t (*show_description)(struct mdev_type *mtype, char *buf); struct device_driver driver; }; -extern struct bus_type mdev_bus_type; - -int mdev_register_device(struct device *dev, struct mdev_driver *mdev_driver); -void mdev_unregister_device(struct device *dev); +int mdev_register_parent(struct mdev_parent *parent, struct device *dev, + struct mdev_driver *mdev_driver, struct mdev_type **types, + unsigned int nr_types); +void mdev_unregister_parent(struct mdev_parent *parent); int mdev_register_driver(struct mdev_driver *drv); void mdev_unregister_driver(struct mdev_driver *drv); -struct device *mdev_parent_dev(struct mdev_device *mdev); static inline struct device *mdev_dev(struct mdev_device *mdev) { return &mdev->dev; } -static inline struct mdev_device *mdev_from_dev(struct device *dev) -{ - return dev->bus == &mdev_bus_type ? to_mdev_device(dev) : NULL; -} #endif /* MDEV_H */ diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 567f12323f55..e1644a24009c 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -80,29 +80,8 @@ enum mem_cgroup_events_target { MEM_CGROUP_NTARGETS, }; -struct memcg_vmstats_percpu { - /* Local (CPU and cgroup) page state & events */ - long state[MEMCG_NR_STAT]; - unsigned long events[NR_VM_EVENT_ITEMS]; - - /* Delta calculation for lockless upward propagation */ - long state_prev[MEMCG_NR_STAT]; - unsigned long events_prev[NR_VM_EVENT_ITEMS]; - - /* Cgroup1: threshold notifications & softlimit tree updates */ - unsigned long nr_page_events; - unsigned long targets[MEM_CGROUP_NTARGETS]; -}; - -struct memcg_vmstats { - /* Aggregated (CPU and subtree) page state & events */ - long state[MEMCG_NR_STAT]; - unsigned long events[NR_VM_EVENT_ITEMS]; - - /* Pending child counts during tree propagation */ - long state_pending[MEMCG_NR_STAT]; - unsigned long events_pending[NR_VM_EVENT_ITEMS]; -}; +struct memcg_vmstats_percpu; +struct memcg_vmstats; struct mem_cgroup_reclaim_iter { struct mem_cgroup *position; @@ -185,15 +164,6 @@ struct mem_cgroup_thresholds { struct mem_cgroup_threshold_ary *spare; }; -#if defined(CONFIG_SMP) -struct memcg_padding { - char x[0]; -} ____cacheline_internodealigned_in_smp; -#define MEMCG_PADDING(name) struct memcg_padding name -#else -#define MEMCG_PADDING(name) -#endif - /* * Remember four most recent foreign writebacks with dirty pages in this * cgroup. Inode sharing is expected to be uncommon and, even if we miss @@ -304,10 +274,10 @@ struct mem_cgroup { spinlock_t move_lock; unsigned long move_lock_flags; - MEMCG_PADDING(_pad1_); + CACHELINE_PADDING(_pad1_); /* memory.stat */ - struct memcg_vmstats vmstats; + struct memcg_vmstats *vmstats; /* memory.events */ atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS]; @@ -326,7 +296,7 @@ struct mem_cgroup { struct list_head objcg_list; #endif - MEMCG_PADDING(_pad2_); + CACHELINE_PADDING(_pad2_); /* * set > 0 if pages under this cgroup are moving to other cgroup. @@ -350,14 +320,20 @@ struct mem_cgroup { struct deferred_split deferred_split_queue; #endif +#ifdef CONFIG_LRU_GEN + /* per-memcg mm_struct list */ + struct lru_gen_mm_list mm_list; +#endif + struct mem_cgroup_per_node *nodeinfo[]; }; /* - * size of first charge trial. "32" comes from vmscan.c's magic value. - * TODO: maybe necessary to use big numbers in big irons. + * size of first charge trial. + * TODO: maybe necessary to use big numbers in big irons or dynamic based of the + * workload. */ -#define MEMCG_CHARGE_BATCH 32U +#define MEMCG_CHARGE_BATCH 64U extern struct mem_cgroup *root_mem_cgroup; @@ -444,6 +420,7 @@ static inline struct obj_cgroup *__folio_objcg(struct folio *folio) * - LRU isolation * - lock_page_memcg() * - exclusive reference + * - mem_cgroup_trylock_pages() * * For a kmem folio a caller should hold an rcu read lock to protect memcg * associated with a kmem folio from being released. @@ -505,6 +482,7 @@ static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio) * - LRU isolation * - lock_page_memcg() * - exclusive reference + * - mem_cgroup_trylock_pages() * * For a kmem page a caller should hold an rcu read lock to protect memcg * associated with a kmem page from being released. @@ -689,7 +667,7 @@ static inline int mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, return __mem_cgroup_charge(folio, mm, gfp); } -int mem_cgroup_swapin_charge_page(struct page *page, struct mm_struct *mm, +int mem_cgroup_swapin_charge_folio(struct folio *folio, struct mm_struct *mm, gfp_t gfp, swp_entry_t entry); void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry); @@ -959,6 +937,23 @@ void unlock_page_memcg(struct page *page); void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val); +/* try to stablize folio_memcg() for all the pages in a memcg */ +static inline bool mem_cgroup_trylock_pages(struct mem_cgroup *memcg) +{ + rcu_read_lock(); + + if (mem_cgroup_disabled() || !atomic_read(&memcg->moving_account)) + return true; + + rcu_read_unlock(); + return false; +} + +static inline void mem_cgroup_unlock_pages(void) +{ + rcu_read_unlock(); +} + /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void mod_memcg_state(struct mem_cgroup *memcg, int idx, int val) @@ -985,15 +980,7 @@ static inline void mod_memcg_page_state(struct page *page, rcu_read_unlock(); } -static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) -{ - long x = READ_ONCE(memcg->vmstats.state[idx]); -#ifdef CONFIG_SMP - if (x < 0) - x = 0; -#endif - return x; -} +unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx); static inline unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx) @@ -1238,7 +1225,7 @@ static inline int mem_cgroup_charge(struct folio *folio, return 0; } -static inline int mem_cgroup_swapin_charge_page(struct page *page, +static inline int mem_cgroup_swapin_charge_folio(struct folio *folio, struct mm_struct *mm, gfp_t gfp, swp_entry_t entry) { return 0; @@ -1433,6 +1420,18 @@ static inline void folio_memcg_unlock(struct folio *folio) { } +static inline bool mem_cgroup_trylock_pages(struct mem_cgroup *memcg) +{ + /* to match folio_memcg_rcu() */ + rcu_read_lock(); + return true; +} + +static inline void mem_cgroup_unlock_pages(void) +{ + rcu_read_unlock(); +} + static inline void mem_cgroup_handle_over_high(void) { } @@ -1779,7 +1778,7 @@ static inline void count_objcg_event(struct obj_cgroup *objcg, { struct mem_cgroup *memcg; - if (mem_cgroup_kmem_disabled()) + if (!memcg_kmem_enabled()) return; rcu_read_lock(); diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h new file mode 100644 index 000000000000..965009aa01d7 --- /dev/null +++ b/include/linux/memory-tiers.h @@ -0,0 +1,102 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_MEMORY_TIERS_H +#define _LINUX_MEMORY_TIERS_H + +#include <linux/types.h> +#include <linux/nodemask.h> +#include <linux/kref.h> +#include <linux/mmzone.h> +/* + * Each tier cover a abstrace distance chunk size of 128 + */ +#define MEMTIER_CHUNK_BITS 7 +#define MEMTIER_CHUNK_SIZE (1 << MEMTIER_CHUNK_BITS) +/* + * Smaller abstract distance values imply faster (higher) memory tiers. Offset + * the DRAM adistance so that we can accommodate devices with a slightly lower + * adistance value (slightly faster) than default DRAM adistance to be part of + * the same memory tier. + */ +#define MEMTIER_ADISTANCE_DRAM ((4 * MEMTIER_CHUNK_SIZE) + (MEMTIER_CHUNK_SIZE >> 1)) +#define MEMTIER_HOTPLUG_PRIO 100 + +struct memory_tier; +struct memory_dev_type { + /* list of memory types that are part of same tier as this type */ + struct list_head tier_sibiling; + /* abstract distance for this specific memory type */ + int adistance; + /* Nodes of same abstract distance */ + nodemask_t nodes; + struct kref kref; +}; + +#ifdef CONFIG_NUMA +extern bool numa_demotion_enabled; +struct memory_dev_type *alloc_memory_type(int adistance); +void destroy_memory_type(struct memory_dev_type *memtype); +void init_node_memory_type(int node, struct memory_dev_type *default_type); +void clear_node_memory_type(int node, struct memory_dev_type *memtype); +#ifdef CONFIG_MIGRATION +int next_demotion_node(int node); +void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets); +bool node_is_toptier(int node); +#else +static inline int next_demotion_node(int node) +{ + return NUMA_NO_NODE; +} + +static inline void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets) +{ + *targets = NODE_MASK_NONE; +} + +static inline bool node_is_toptier(int node) +{ + return true; +} +#endif + +#else + +#define numa_demotion_enabled false +/* + * CONFIG_NUMA implementation returns non NULL error. + */ +static inline struct memory_dev_type *alloc_memory_type(int adistance) +{ + return NULL; +} + +static inline void destroy_memory_type(struct memory_dev_type *memtype) +{ + +} + +static inline void init_node_memory_type(int node, struct memory_dev_type *default_type) +{ + +} + +static inline void clear_node_memory_type(int node, struct memory_dev_type *memtype) +{ + +} + +static inline int next_demotion_node(int node) +{ + return NUMA_NO_NODE; +} + +static inline void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets) +{ + *targets = NODE_MASK_NONE; +} + +static inline bool node_is_toptier(int node) +{ + return true; +} +#endif /* CONFIG_NUMA */ +#endif /* _LINUX_MEMORY_TIERS_H */ diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index e0b2209ab71c..9fcbf5706595 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -11,7 +11,6 @@ struct page; struct zone; struct pglist_data; struct mem_section; -struct memory_block; struct memory_group; struct resource; struct vmem_altmap; @@ -44,11 +43,6 @@ extern void arch_refresh_nodedata(int nid, pg_data_t *pgdat); ({ \ memblock_alloc(sizeof(*pgdat), SMP_CACHE_BYTES); \ }) -/* - * This definition is just for error path in node hotadd. - * For node hotremove, we have to replace this. - */ -#define generic_free_nodedata(pgdat) kfree(pgdat) extern pg_data_t *node_data[]; static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat) @@ -64,9 +58,6 @@ static inline pg_data_t *generic_alloc_nodedata(int nid) BUG(); return NULL; } -static inline void generic_free_nodedata(pg_data_t *pgdat) -{ -} static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat) { } @@ -216,6 +207,22 @@ void put_online_mems(void); void mem_hotplug_begin(void); void mem_hotplug_done(void); +/* See kswapd_is_running() */ +static inline void pgdat_kswapd_lock(pg_data_t *pgdat) +{ + mutex_lock(&pgdat->kswapd_lock); +} + +static inline void pgdat_kswapd_unlock(pg_data_t *pgdat) +{ + mutex_unlock(&pgdat->kswapd_lock); +} + +static inline void pgdat_kswapd_lock_init(pg_data_t *pgdat) +{ + mutex_init(&pgdat->kswapd_lock); +} + #else /* ! CONFIG_MEMORY_HOTPLUG */ #define pfn_to_online_page(pfn) \ ({ \ @@ -252,6 +259,10 @@ static inline bool movable_node_is_enabled(void) { return false; } + +static inline void pgdat_kswapd_lock(pg_data_t *pgdat) {} +static inline void pgdat_kswapd_unlock(pg_data_t *pgdat) {} +static inline void pgdat_kswapd_lock_init(pg_data_t *pgdat) {} #endif /* ! CONFIG_MEMORY_HOTPLUG */ /* @@ -333,7 +344,6 @@ extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn, extern void remove_pfn_range_from_zone(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages); -extern bool is_memblock_offlined(struct memory_block *mem); extern int sparse_add_section(int nid, unsigned long pfn, unsigned long nr_pages, struct vmem_altmap *altmap, struct dev_pagemap *pgmap); diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 668389b4b53d..d232de7cdc56 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -151,13 +151,6 @@ extern bool mempolicy_in_oom_domain(struct task_struct *tsk, const nodemask_t *mask); extern nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy); -static inline nodemask_t *policy_nodemask_current(gfp_t gfp) -{ - struct mempolicy *mpol = get_task_policy(current); - - return policy_nodemask(gfp, mpol); -} - extern unsigned int mempolicy_slab_node(void); extern enum zone_type policy_zone; @@ -189,6 +182,7 @@ static inline bool mpol_is_preferred_many(struct mempolicy *pol) return (pol->mode == MPOL_PREFERRED_MANY); } +extern bool apply_policy_zone(struct mempolicy *policy, enum zone_type zone); #else @@ -294,11 +288,6 @@ static inline void mpol_put_task_policy(struct task_struct *task) { } -static inline nodemask_t *policy_nodemask_current(gfp_t gfp) -{ - return NULL; -} - static inline bool mpol_is_preferred_many(struct mempolicy *pol) { return false; diff --git a/include/linux/memremap.h b/include/linux/memremap.h index c3b4cc84877b..7fcaf3180a5b 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -187,6 +187,7 @@ static inline bool folio_is_device_coherent(const struct folio *folio) } #ifdef CONFIG_ZONE_DEVICE +void zone_device_page_init(struct page *page); void *memremap_pages(struct dev_pagemap *pgmap, int nid); void memunmap_pages(struct dev_pagemap *pgmap); void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap); diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 22c0a0cf5e0c..3ef77f52a4f0 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -62,6 +62,8 @@ extern const char *migrate_reason_names[MR_TYPES]; #ifdef CONFIG_MIGRATION extern void putback_movable_pages(struct list_head *l); +int migrate_folio_extra(struct address_space *mapping, struct folio *dst, + struct folio *src, enum migrate_mode mode, int extra_count); int migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode); extern int migrate_pages(struct list_head *l, new_page_t new, free_page_t free, @@ -100,21 +102,6 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping, #endif /* CONFIG_MIGRATION */ -#if defined(CONFIG_MIGRATION) && defined(CONFIG_NUMA) -extern void set_migration_target_nodes(void); -extern void migrate_on_reclaim_init(void); -extern bool numa_demotion_enabled; -extern int next_demotion_node(int node); -#else -static inline void set_migration_target_nodes(void) {} -static inline void migrate_on_reclaim_init(void) {} -static inline int next_demotion_node(int node) -{ - return NUMA_NO_NODE; -} -#define numa_demotion_enabled false -#endif - #ifdef CONFIG_COMPACTION bool PageMovable(struct page *page); void __SetPageMovable(struct page *page, const struct movable_operations *ops); @@ -212,11 +199,24 @@ struct migrate_vma { */ void *pgmap_owner; unsigned long flags; + + /* + * Set to vmf->page if this is being called to migrate a page as part of + * a migrate_to_ram() callback. + */ + struct page *fault_page; }; int migrate_vma_setup(struct migrate_vma *args); void migrate_vma_pages(struct migrate_vma *migrate); void migrate_vma_finalize(struct migrate_vma *migrate); +int migrate_device_range(unsigned long *src_pfns, unsigned long start, + unsigned long npages); +void migrate_device_pages(unsigned long *src_pfns, unsigned long *dst_pfns, + unsigned long npages); +void migrate_device_finalize(unsigned long *src_pfns, + unsigned long *dst_pfns, unsigned long npages); + #endif /* CONFIG_MIGRATION */ #endif /* _LINUX_MIGRATE_H */ diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index a12929bc31b2..af2ceb4160bc 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -970,7 +970,7 @@ void mlx5_cmd_allowed_opcode(struct mlx5_core_dev *dev, u16 opcode); struct mlx5_async_ctx { struct mlx5_core_dev *dev; atomic_t num_inflight; - struct wait_queue_head wait; + struct completion inflight_done; }; struct mlx5_async_work; diff --git a/include/linux/mm.h b/include/linux/mm.h index 21f8b27bd9fd..8bbcccbc5565 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -661,6 +661,38 @@ static inline bool vma_is_accessible(struct vm_area_struct *vma) return vma->vm_flags & VM_ACCESS_FLAGS; } +static inline +struct vm_area_struct *vma_find(struct vma_iterator *vmi, unsigned long max) +{ + return mas_find(&vmi->mas, max); +} + +static inline struct vm_area_struct *vma_next(struct vma_iterator *vmi) +{ + /* + * Uses vma_find() to get the first VMA when the iterator starts. + * Calling mas_next() could skip the first entry. + */ + return vma_find(vmi, ULONG_MAX); +} + +static inline struct vm_area_struct *vma_prev(struct vma_iterator *vmi) +{ + return mas_prev(&vmi->mas, 0); +} + +static inline unsigned long vma_iter_addr(struct vma_iterator *vmi) +{ + return vmi->mas.index; +} + +#define for_each_vma(__vmi, __vma) \ + while (((__vma) = vma_next(&(__vmi))) != NULL) + +/* The MM code likes to work with exclusive end addresses */ +#define for_each_vma_range(__vmi, __vma, __end) \ + while (((__vma) = vma_find(&(__vmi), (__end) - 1)) != NULL) + #ifdef CONFIG_SHMEM /* * The vma_is_shmem is not inline because it is used only by slow @@ -697,7 +729,9 @@ static inline unsigned int compound_order(struct page *page) */ static inline unsigned int folio_order(struct folio *folio) { - return compound_order(&folio->page); + if (!folio_test_large(folio)) + return 0; + return folio->_folio_order; } #include <linux/huge_mm.h> @@ -1255,6 +1289,18 @@ static inline int folio_nid(const struct folio *folio) } #ifdef CONFIG_NUMA_BALANCING +/* page access time bits needs to hold at least 4 seconds */ +#define PAGE_ACCESS_TIME_MIN_BITS 12 +#if LAST_CPUPID_SHIFT < PAGE_ACCESS_TIME_MIN_BITS +#define PAGE_ACCESS_TIME_BUCKETS \ + (PAGE_ACCESS_TIME_MIN_BITS - LAST_CPUPID_SHIFT) +#else +#define PAGE_ACCESS_TIME_BUCKETS 0 +#endif + +#define PAGE_ACCESS_TIME_MASK \ + (LAST_CPUPID_MASK << PAGE_ACCESS_TIME_BUCKETS) + static inline int cpu_pid_to_cpupid(int cpu, int pid) { return ((cpu & LAST__CPU_MASK) << LAST__PID_SHIFT) | (pid & LAST__PID_MASK); @@ -1318,12 +1364,25 @@ static inline void page_cpupid_reset_last(struct page *page) page->flags |= LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT; } #endif /* LAST_CPUPID_NOT_IN_PAGE_FLAGS */ + +static inline int xchg_page_access_time(struct page *page, int time) +{ + int last_time; + + last_time = page_cpupid_xchg_last(page, time >> PAGE_ACCESS_TIME_BUCKETS); + return last_time << PAGE_ACCESS_TIME_BUCKETS; +} #else /* !CONFIG_NUMA_BALANCING */ static inline int page_cpupid_xchg_last(struct page *page, int cpupid) { return page_to_nid(page); /* XXX */ } +static inline int xchg_page_access_time(struct page *page, int time) +{ + return 0; +} + static inline int page_cpupid_last(struct page *page) { return page_to_nid(page); /* XXX */ @@ -1465,6 +1524,11 @@ static inline unsigned long folio_pfn(struct folio *folio) return page_to_pfn(&folio->page); } +static inline struct folio *pfn_folio(unsigned long pfn) +{ + return page_folio(pfn_to_page(pfn)); +} + static inline atomic_t *folio_pincount_ptr(struct folio *folio) { return &folio_page(folio, 1)->compound_pincount; @@ -1597,7 +1661,13 @@ static inline void set_page_links(struct page *page, enum zone_type zone, */ static inline long folio_nr_pages(struct folio *folio) { - return compound_nr(&folio->page); + if (!folio_test_large(folio)) + return 1; +#ifdef CONFIG_64BIT + return folio->_folio_nr_pages; +#else + return 1L << folio->_folio_order; +#endif } /** @@ -1776,7 +1846,11 @@ extern void pagefault_out_of_memory(void); */ #define SHOW_MEM_FILTER_NODES (0x0001u) /* disallowed nodes */ -extern void show_free_areas(unsigned int flags, nodemask_t *nodemask); +extern void __show_free_areas(unsigned int flags, nodemask_t *nodemask, int max_zone_idx); +static void __maybe_unused show_free_areas(unsigned int flags, nodemask_t *nodemask) +{ + __show_free_areas(flags, nodemask, MAX_NR_ZONES - 1); +} #ifdef CONFIG_MMU extern bool can_do_mlock(void); @@ -1795,8 +1869,9 @@ void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, unsigned long size); void zap_page_range(struct vm_area_struct *vma, unsigned long address, unsigned long size); -void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma, - unsigned long start, unsigned long end); +void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt, + struct vm_area_struct *start_vma, unsigned long start, + unsigned long end); struct mmu_notifier_range; @@ -2495,7 +2570,6 @@ extern unsigned long absent_pages_in_range(unsigned long start_pfn, unsigned long end_pfn); extern void get_pfn_range_for_nid(unsigned int nid, unsigned long *start_pfn, unsigned long *end_pfn); -extern unsigned long find_min_pfn_with_active_regions(void); #ifndef CONFIG_NUMA static inline int early_pfn_to_nid(unsigned long pfn) @@ -2516,7 +2590,12 @@ extern void calculate_min_free_kbytes(void); extern int __meminit init_per_zone_wmark_min(void); extern void mem_init(void); extern void __init mmap_init(void); -extern void show_mem(unsigned int flags, nodemask_t *nodemask); + +extern void __show_mem(unsigned int flags, nodemask_t *nodemask, int max_zone_idx); +static inline void show_mem(unsigned int flags, nodemask_t *nodemask) +{ + __show_mem(flags, nodemask, MAX_NR_ZONES - 1); +} extern long si_mem_available(void); extern void si_meminfo(struct sysinfo * val); extern void si_meminfo_node(struct sysinfo *val, int nid); @@ -2593,14 +2672,15 @@ extern int __split_vma(struct mm_struct *, struct vm_area_struct *, extern int split_vma(struct mm_struct *, struct vm_area_struct *, unsigned long addr, int new_below); extern int insert_vm_struct(struct mm_struct *, struct vm_area_struct *); -extern void __vma_link_rb(struct mm_struct *, struct vm_area_struct *, - struct rb_node **, struct rb_node *); extern void unlink_file_vma(struct vm_area_struct *); extern struct vm_area_struct *copy_vma(struct vm_area_struct **, unsigned long addr, unsigned long len, pgoff_t pgoff, bool *need_rmap_locks); extern void exit_mmap(struct mm_struct *); +void vma_mas_store(struct vm_area_struct *vma, struct ma_state *mas); +void vma_mas_remove(struct vm_area_struct *vma, struct ma_state *mas); + static inline int check_data_rlimit(unsigned long rlim, unsigned long new, unsigned long start, @@ -2648,8 +2728,9 @@ extern unsigned long mmap_region(struct file *file, unsigned long addr, extern unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, unsigned long pgoff, unsigned long *populate, struct list_head *uf); -extern int __do_munmap(struct mm_struct *, unsigned long, size_t, - struct list_head *uf, bool downgrade); +extern int do_mas_munmap(struct ma_state *mas, struct mm_struct *mm, + unsigned long start, size_t len, struct list_head *uf, + bool downgrade); extern int do_munmap(struct mm_struct *, unsigned long, size_t, struct list_head *uf); extern int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int behavior); @@ -2716,26 +2797,12 @@ extern struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long add extern struct vm_area_struct * find_vma_prev(struct mm_struct * mm, unsigned long addr, struct vm_area_struct **pprev); -/** - * find_vma_intersection() - Look up the first VMA which intersects the interval - * @mm: The process address space. - * @start_addr: The inclusive start user address. - * @end_addr: The exclusive end user address. - * - * Returns: The first VMA within the provided range, %NULL otherwise. Assumes - * start_addr < end_addr. +/* + * Look up the first VMA which intersects the interval [start_addr, end_addr) + * NULL if none. Assume start_addr < end_addr. */ -static inline struct vm_area_struct *find_vma_intersection(struct mm_struct *mm, - unsigned long start_addr, - unsigned long end_addr) -{ - struct vm_area_struct *vma = find_vma(mm, start_addr); - - if (vma && end_addr <= vma->vm_start) - vma = NULL; - return vma; -} + unsigned long start_addr, unsigned long end_addr); /** * vma_lookup() - Find a VMA at a specific address @@ -2747,12 +2814,7 @@ struct vm_area_struct *find_vma_intersection(struct mm_struct *mm, static inline struct vm_area_struct *vma_lookup(struct mm_struct *mm, unsigned long addr) { - struct vm_area_struct *vma = find_vma(mm, addr); - - if (vma && addr < vma->vm_start) - vma = NULL; - - return vma; + return mtree_load(&mm->mm_mt, addr); } static inline unsigned long vm_start_gap(struct vm_area_struct *vma) @@ -2788,7 +2850,7 @@ static inline unsigned long vma_pages(struct vm_area_struct *vma) static inline struct vm_area_struct *find_exact_vma(struct mm_struct *mm, unsigned long vm_start, unsigned long vm_end) { - struct vm_area_struct *vma = find_vma(mm, vm_start); + struct vm_area_struct *vma = vma_lookup(mm, vm_start); if (vma && (vma->vm_start != vm_start || vma->vm_end != vm_end)) vma = NULL; @@ -2888,7 +2950,6 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, * and return without waiting upon it */ #define FOLL_NOFAULT 0x80 /* do not fault in pages */ #define FOLL_HWPOISON 0x100 /* check page is hwpoisoned */ -#define FOLL_NUMA 0x200 /* force NUMA hinting page fault */ #define FOLL_MIGRATION 0x400 /* wait for page to replace migration entry */ #define FOLL_TRIED 0x800 /* a retry, previous pass started an IO */ #define FOLL_REMOTE 0x2000 /* we are working on non-current tsk/mm */ @@ -2975,8 +3036,8 @@ static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) * PageAnonExclusive() has to protect against concurrent GUP: * * Ordinary GUP: Using the PT lock * * GUP-fast and fork(): mm->write_protect_seq - * * GUP-fast and KSM or temporary unmapping (swap, migration): - * clear/invalidate+flush of the page table entry + * * GUP-fast and KSM or temporary unmapping (swap, migration): see + * page_try_share_anon_rmap() * * Must be called with the (sub)page that's actually referenced via the * page table entry, which might not necessarily be the head page for a @@ -2997,6 +3058,11 @@ static inline bool gup_must_unshare(unsigned int flags, struct page *page) */ if (!PageAnon(page)) return false; + + /* Paired with a memory barrier in page_try_share_anon_rmap(). */ + if (IS_ENABLED(CONFIG_HAVE_FAST_GUP)) + smp_rmb(); + /* * Note that PageKsm() pages cannot be exclusive, and consequently, * cannot get pinned. @@ -3004,6 +3070,21 @@ static inline bool gup_must_unshare(unsigned int flags, struct page *page) return !PageAnonExclusive(page); } +/* + * Indicates whether GUP can follow a PROT_NONE mapped page, or whether + * a (NUMA hinting) fault is required. + */ +static inline bool gup_can_follow_protnone(unsigned int flags) +{ + /* + * FOLL_FORCE has to be able to make progress even if the VMA is + * inaccessible. Further, FOLL_FORCE access usually does not represent + * application behaviour and we should avoid triggering NUMA hinting + * faults. + */ + return flags & FOLL_FORCE; +} + typedef int (*pte_fn_t)(pte_t *pte, unsigned long addr, void *data); extern int apply_to_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); @@ -3011,7 +3092,7 @@ extern int apply_to_existing_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); -extern void init_mem_debugging_and_hardening(void); +extern void __init init_mem_debugging_and_hardening(void); #ifdef CONFIG_PAGE_POISONING extern void __kernel_poison_pages(struct page *page, int numpages); extern void __kernel_unpoison_pages(struct page *page, int numpages); diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 7b25b53c474a..e8ed225d8f7c 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -34,15 +34,25 @@ static inline int page_is_file_lru(struct page *page) return folio_is_file_lru(page_folio(page)); } -static __always_inline void update_lru_size(struct lruvec *lruvec, +static __always_inline void __update_lru_size(struct lruvec *lruvec, enum lru_list lru, enum zone_type zid, long nr_pages) { struct pglist_data *pgdat = lruvec_pgdat(lruvec); + lockdep_assert_held(&lruvec->lru_lock); + WARN_ON_ONCE(nr_pages != (int)nr_pages); + __mod_lruvec_state(lruvec, NR_LRU_BASE + lru, nr_pages); __mod_zone_page_state(&pgdat->node_zones[zid], NR_ZONE_LRU_BASE + lru, nr_pages); +} + +static __always_inline void update_lru_size(struct lruvec *lruvec, + enum lru_list lru, enum zone_type zid, + long nr_pages) +{ + __update_lru_size(lruvec, lru, zid, nr_pages); #ifdef CONFIG_MEMCG mem_cgroup_update_lru_size(lruvec, lru, zid, nr_pages); #endif @@ -66,11 +76,6 @@ static __always_inline void __folio_clear_lru_flags(struct folio *folio) __folio_clear_unevictable(folio); } -static __always_inline void __clear_page_lru_flags(struct page *page) -{ - __folio_clear_lru_flags(page_folio(page)); -} - /** * folio_lru_list - Which LRU list should a folio be on? * @folio: The folio to test. @@ -94,11 +99,224 @@ static __always_inline enum lru_list folio_lru_list(struct folio *folio) return lru; } +#ifdef CONFIG_LRU_GEN + +#ifdef CONFIG_LRU_GEN_ENABLED +static inline bool lru_gen_enabled(void) +{ + DECLARE_STATIC_KEY_TRUE(lru_gen_caps[NR_LRU_GEN_CAPS]); + + return static_branch_likely(&lru_gen_caps[LRU_GEN_CORE]); +} +#else +static inline bool lru_gen_enabled(void) +{ + DECLARE_STATIC_KEY_FALSE(lru_gen_caps[NR_LRU_GEN_CAPS]); + + return static_branch_unlikely(&lru_gen_caps[LRU_GEN_CORE]); +} +#endif + +static inline bool lru_gen_in_fault(void) +{ + return current->in_lru_fault; +} + +static inline int lru_gen_from_seq(unsigned long seq) +{ + return seq % MAX_NR_GENS; +} + +static inline int lru_hist_from_seq(unsigned long seq) +{ + return seq % NR_HIST_GENS; +} + +static inline int lru_tier_from_refs(int refs) +{ + VM_WARN_ON_ONCE(refs > BIT(LRU_REFS_WIDTH)); + + /* see the comment in folio_lru_refs() */ + return order_base_2(refs + 1); +} + +static inline int folio_lru_refs(struct folio *folio) +{ + unsigned long flags = READ_ONCE(folio->flags); + bool workingset = flags & BIT(PG_workingset); + + /* + * Return the number of accesses beyond PG_referenced, i.e., N-1 if the + * total number of accesses is N>1, since N=0,1 both map to the first + * tier. lru_tier_from_refs() will account for this off-by-one. Also see + * the comment on MAX_NR_TIERS. + */ + return ((flags & LRU_REFS_MASK) >> LRU_REFS_PGOFF) + workingset; +} + +static inline int folio_lru_gen(struct folio *folio) +{ + unsigned long flags = READ_ONCE(folio->flags); + + return ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; +} + +static inline bool lru_gen_is_active(struct lruvec *lruvec, int gen) +{ + unsigned long max_seq = lruvec->lrugen.max_seq; + + VM_WARN_ON_ONCE(gen >= MAX_NR_GENS); + + /* see the comment on MIN_NR_GENS */ + return gen == lru_gen_from_seq(max_seq) || gen == lru_gen_from_seq(max_seq - 1); +} + +static inline void lru_gen_update_size(struct lruvec *lruvec, struct folio *folio, + int old_gen, int new_gen) +{ + int type = folio_is_file_lru(folio); + int zone = folio_zonenum(folio); + int delta = folio_nr_pages(folio); + enum lru_list lru = type * LRU_INACTIVE_FILE; + struct lru_gen_struct *lrugen = &lruvec->lrugen; + + VM_WARN_ON_ONCE(old_gen != -1 && old_gen >= MAX_NR_GENS); + VM_WARN_ON_ONCE(new_gen != -1 && new_gen >= MAX_NR_GENS); + VM_WARN_ON_ONCE(old_gen == -1 && new_gen == -1); + + if (old_gen >= 0) + WRITE_ONCE(lrugen->nr_pages[old_gen][type][zone], + lrugen->nr_pages[old_gen][type][zone] - delta); + if (new_gen >= 0) + WRITE_ONCE(lrugen->nr_pages[new_gen][type][zone], + lrugen->nr_pages[new_gen][type][zone] + delta); + + /* addition */ + if (old_gen < 0) { + if (lru_gen_is_active(lruvec, new_gen)) + lru += LRU_ACTIVE; + __update_lru_size(lruvec, lru, zone, delta); + return; + } + + /* deletion */ + if (new_gen < 0) { + if (lru_gen_is_active(lruvec, old_gen)) + lru += LRU_ACTIVE; + __update_lru_size(lruvec, lru, zone, -delta); + return; + } + + /* promotion */ + if (!lru_gen_is_active(lruvec, old_gen) && lru_gen_is_active(lruvec, new_gen)) { + __update_lru_size(lruvec, lru, zone, -delta); + __update_lru_size(lruvec, lru + LRU_ACTIVE, zone, delta); + } + + /* demotion requires isolation, e.g., lru_deactivate_fn() */ + VM_WARN_ON_ONCE(lru_gen_is_active(lruvec, old_gen) && !lru_gen_is_active(lruvec, new_gen)); +} + +static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) +{ + unsigned long seq; + unsigned long flags; + int gen = folio_lru_gen(folio); + int type = folio_is_file_lru(folio); + int zone = folio_zonenum(folio); + struct lru_gen_struct *lrugen = &lruvec->lrugen; + + VM_WARN_ON_ONCE_FOLIO(gen != -1, folio); + + if (folio_test_unevictable(folio) || !lrugen->enabled) + return false; + /* + * There are three common cases for this page: + * 1. If it's hot, e.g., freshly faulted in or previously hot and + * migrated, add it to the youngest generation. + * 2. If it's cold but can't be evicted immediately, i.e., an anon page + * not in swapcache or a dirty page pending writeback, add it to the + * second oldest generation. + * 3. Everything else (clean, cold) is added to the oldest generation. + */ + if (folio_test_active(folio)) + seq = lrugen->max_seq; + else if ((type == LRU_GEN_ANON && !folio_test_swapcache(folio)) || + (folio_test_reclaim(folio) && + (folio_test_dirty(folio) || folio_test_writeback(folio)))) + seq = lrugen->min_seq[type] + 1; + else + seq = lrugen->min_seq[type]; + + gen = lru_gen_from_seq(seq); + flags = (gen + 1UL) << LRU_GEN_PGOFF; + /* see the comment on MIN_NR_GENS about PG_active */ + set_mask_bits(&folio->flags, LRU_GEN_MASK | BIT(PG_active), flags); + + lru_gen_update_size(lruvec, folio, -1, gen); + /* for folio_rotate_reclaimable() */ + if (reclaiming) + list_add_tail(&folio->lru, &lrugen->lists[gen][type][zone]); + else + list_add(&folio->lru, &lrugen->lists[gen][type][zone]); + + return true; +} + +static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) +{ + unsigned long flags; + int gen = folio_lru_gen(folio); + + if (gen < 0) + return false; + + VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio); + VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); + + /* for folio_migrate_flags() */ + flags = !reclaiming && lru_gen_is_active(lruvec, gen) ? BIT(PG_active) : 0; + flags = set_mask_bits(&folio->flags, LRU_GEN_MASK, flags); + gen = ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; + + lru_gen_update_size(lruvec, folio, gen, -1); + list_del(&folio->lru); + + return true; +} + +#else /* !CONFIG_LRU_GEN */ + +static inline bool lru_gen_enabled(void) +{ + return false; +} + +static inline bool lru_gen_in_fault(void) +{ + return false; +} + +static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) +{ + return false; +} + +static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) +{ + return false; +} + +#endif /* CONFIG_LRU_GEN */ + static __always_inline void lruvec_add_folio(struct lruvec *lruvec, struct folio *folio) { enum lru_list lru = folio_lru_list(folio); + if (lru_gen_add_folio(lruvec, folio, false)) + return; + update_lru_size(lruvec, lru, folio_zonenum(folio), folio_nr_pages(folio)); if (lru != LRU_UNEVICTABLE) @@ -116,23 +334,23 @@ void lruvec_add_folio_tail(struct lruvec *lruvec, struct folio *folio) { enum lru_list lru = folio_lru_list(folio); + if (lru_gen_add_folio(lruvec, folio, true)) + return; + update_lru_size(lruvec, lru, folio_zonenum(folio), folio_nr_pages(folio)); /* This is not expected to be used on LRU_UNEVICTABLE */ list_add_tail(&folio->lru, &lruvec->lists[lru]); } -static __always_inline void add_page_to_lru_list_tail(struct page *page, - struct lruvec *lruvec) -{ - lruvec_add_folio_tail(lruvec, page_folio(page)); -} - static __always_inline void lruvec_del_folio(struct lruvec *lruvec, struct folio *folio) { enum lru_list lru = folio_lru_list(folio); + if (lru_gen_del_folio(lruvec, folio, false)) + return; + if (lru != LRU_UNEVICTABLE) list_del(&folio->lru); update_lru_size(lruvec, lru, folio_zonenum(folio), diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index cf97f3884fda..500e536796ca 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -9,6 +9,7 @@ #include <linux/list.h> #include <linux/spinlock.h> #include <linux/rbtree.h> +#include <linux/maple_tree.h> #include <linux/rwsem.h> #include <linux/completion.h> #include <linux/cpumask.h> @@ -223,6 +224,18 @@ struct page { not kmapped, ie. highmem) */ #endif /* WANT_PAGE_VIRTUAL */ +#ifdef CONFIG_KMSAN + /* + * KMSAN metadata for this page: + * - shadow page: every bit indicates whether the corresponding + * bit of the original page is initialized (0) or not (1); + * - origin page: every 4 bytes contain an id of the stack trace + * where the uninitialized value was created. + */ + struct page *kmsan_shadow; + struct page *kmsan_origin; +#endif + #ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS int _last_cpupid; #endif @@ -244,6 +257,13 @@ struct page { * @_refcount: Do not access this member directly. Use folio_ref_count() * to find how many references there are to this folio. * @memcg_data: Memory Control Group data. + * @_flags_1: For large folios, additional page flags. + * @__head: Points to the folio. Do not use. + * @_folio_dtor: Which destructor to use for this folio. + * @_folio_order: Do not use directly, call folio_order(). + * @_total_mapcount: Do not use directly, call folio_entire_mapcount(). + * @_pincount: Do not use directly, call folio_maybe_dma_pinned(). + * @_folio_nr_pages: Do not use directly, call folio_nr_pages(). * * A folio is a physically, virtually and logically contiguous set * of bytes. It is a power-of-two in size, and it is aligned to that @@ -282,9 +302,17 @@ struct folio { }; struct page page; }; + unsigned long _flags_1; + unsigned long __head; + unsigned char _folio_dtor; + unsigned char _folio_order; + atomic_t _total_mapcount; + atomic_t _pincount; +#ifdef CONFIG_64BIT + unsigned int _folio_nr_pages; +#endif }; -static_assert(sizeof(struct page) == sizeof(struct folio)); #define FOLIO_MATCH(pg, fl) \ static_assert(offsetof(struct page, pg) == offsetof(struct folio, fl)) FOLIO_MATCH(flags, flags); @@ -299,6 +327,19 @@ FOLIO_MATCH(_refcount, _refcount); FOLIO_MATCH(memcg_data, memcg_data); #endif #undef FOLIO_MATCH +#define FOLIO_MATCH(pg, fl) \ + static_assert(offsetof(struct folio, fl) == \ + offsetof(struct page, pg) + sizeof(struct page)) +FOLIO_MATCH(flags, _flags_1); +FOLIO_MATCH(compound_head, __head); +FOLIO_MATCH(compound_dtor, _folio_dtor); +FOLIO_MATCH(compound_order, _folio_order); +FOLIO_MATCH(compound_mapcount, _total_mapcount); +FOLIO_MATCH(compound_pincount, _pincount); +#ifdef CONFIG_64BIT +FOLIO_MATCH(compound_nr, _folio_nr_pages); +#endif +#undef FOLIO_MATCH static inline atomic_t *folio_mapcount_ptr(struct folio *folio) { @@ -407,21 +448,6 @@ struct vm_area_struct { unsigned long vm_end; /* The first byte after our end address within vm_mm. */ - /* linked list of VM areas per task, sorted by address */ - struct vm_area_struct *vm_next, *vm_prev; - - struct rb_node vm_rb; - - /* - * Largest free memory gap in bytes to the left of this VMA. - * Either between this VMA and vma->vm_prev, or between one of the - * VMAs below us in the VMA rbtree and its ->vm_prev. This helps - * get_unmapped_area find a free area of the right size. - */ - unsigned long rb_subtree_gap; - - /* Second cache line starts here. */ - struct mm_struct *vm_mm; /* The address space we belong to. */ /* @@ -485,9 +511,7 @@ struct vm_area_struct { struct kioctx_table; struct mm_struct { struct { - struct vm_area_struct *mmap; /* list of VMAs */ - struct rb_root mm_rb; - u64 vmacache_seqnum; /* per-thread vmacache */ + struct maple_tree mm_mt; #ifdef CONFIG_MMU unsigned long (*get_unmapped_area) (struct file *filp, unsigned long addr, unsigned long len, @@ -501,7 +525,6 @@ struct mm_struct { unsigned long mmap_compat_legacy_base; #endif unsigned long task_size; /* size of task vm space */ - unsigned long highest_vm_end; /* highest vma end address */ pgd_t * pgd; #ifdef CONFIG_MEMBARRIER @@ -631,22 +654,22 @@ struct mm_struct { #endif #ifdef CONFIG_NUMA_BALANCING /* - * numa_next_scan is the next time that the PTEs will be marked - * pte_numa. NUMA hinting faults will gather statistics and - * migrate pages to new nodes if necessary. + * numa_next_scan is the next time that PTEs will be remapped + * PROT_NONE to trigger NUMA hinting faults; such faults gather + * statistics and migrate pages to new nodes if necessary. */ unsigned long numa_next_scan; - /* Restart point for scanning and setting pte_numa */ + /* Restart point for scanning and remapping PTEs. */ unsigned long numa_scan_offset; - /* numa_scan_seq prevents two threads setting pte_numa */ + /* numa_scan_seq prevents two threads remapping PTEs. */ int numa_scan_seq; #endif /* * An operation with batched TLB flushing is going on. Anything * that can move process memory needs to flush the TLB when - * moving a PROT_NONE or PROT_NUMA mapped page. + * moving a PROT_NONE mapped page. */ atomic_t tlb_flush_pending; #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH @@ -671,7 +694,28 @@ struct mm_struct { * merging. */ unsigned long ksm_merging_pages; + /* + * Represent how many pages are checked for ksm merging + * including merged and not merged. + */ + unsigned long ksm_rmap_items; +#endif +#ifdef CONFIG_LRU_GEN + struct { + /* this mm_struct is on lru_gen_mm_list */ + struct list_head list; + /* + * Set when switching to this mm_struct, as a hint of + * whether it has been used since the last time per-node + * page table walkers cleared the corresponding bits. + */ + unsigned long bitmap; +#ifdef CONFIG_MEMCG + /* points to the memcg of "owner" above */ + struct mem_cgroup *memcg; #endif + } lru_gen; +#endif /* CONFIG_LRU_GEN */ } __randomize_layout; /* @@ -681,6 +725,7 @@ struct mm_struct { unsigned long cpu_bitmap[]; }; +#define MM_MT_FLAGS (MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN) extern struct mm_struct init_mm; /* Pointer magic because the dynamic array size confuses some compilers. */ @@ -698,6 +743,87 @@ static inline cpumask_t *mm_cpumask(struct mm_struct *mm) return (struct cpumask *)&mm->cpu_bitmap; } +#ifdef CONFIG_LRU_GEN + +struct lru_gen_mm_list { + /* mm_struct list for page table walkers */ + struct list_head fifo; + /* protects the list above */ + spinlock_t lock; +}; + +void lru_gen_add_mm(struct mm_struct *mm); +void lru_gen_del_mm(struct mm_struct *mm); +#ifdef CONFIG_MEMCG +void lru_gen_migrate_mm(struct mm_struct *mm); +#endif + +static inline void lru_gen_init_mm(struct mm_struct *mm) +{ + INIT_LIST_HEAD(&mm->lru_gen.list); + mm->lru_gen.bitmap = 0; +#ifdef CONFIG_MEMCG + mm->lru_gen.memcg = NULL; +#endif +} + +static inline void lru_gen_use_mm(struct mm_struct *mm) +{ + /* + * When the bitmap is set, page reclaim knows this mm_struct has been + * used since the last time it cleared the bitmap. So it might be worth + * walking the page tables of this mm_struct to clear the accessed bit. + */ + WRITE_ONCE(mm->lru_gen.bitmap, -1); +} + +#else /* !CONFIG_LRU_GEN */ + +static inline void lru_gen_add_mm(struct mm_struct *mm) +{ +} + +static inline void lru_gen_del_mm(struct mm_struct *mm) +{ +} + +#ifdef CONFIG_MEMCG +static inline void lru_gen_migrate_mm(struct mm_struct *mm) +{ +} +#endif + +static inline void lru_gen_init_mm(struct mm_struct *mm) +{ +} + +static inline void lru_gen_use_mm(struct mm_struct *mm) +{ +} + +#endif /* CONFIG_LRU_GEN */ + +struct vma_iterator { + struct ma_state mas; +}; + +#define VMA_ITERATOR(name, __mm, __addr) \ + struct vma_iterator name = { \ + .mas = { \ + .tree = &(__mm)->mm_mt, \ + .index = __addr, \ + .node = MAS_START, \ + }, \ + } + +static inline void vma_iter_init(struct vma_iterator *vmi, + struct mm_struct *mm, unsigned long addr) +{ + vmi->mas.tree = &mm->mm_mt; + vmi->mas.index = addr; + vmi->mas.node = MAS_START; +} + struct mmu_gather; extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm); extern void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm); diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h index c1bc6731125c..0bb4b6da9993 100644 --- a/include/linux/mm_types_task.h +++ b/include/linux/mm_types_task.h @@ -25,18 +25,6 @@ #define ALLOC_SPLIT_PTLOCKS (SPINLOCK_SIZE > BITS_PER_LONG/8) /* - * The per task VMA cache array: - */ -#define VMACACHE_BITS 2 -#define VMACACHE_SIZE (1U << VMACACHE_BITS) -#define VMACACHE_MASK (VMACACHE_SIZE - 1) - -struct vmacache { - u64 seqnum; - struct vm_area_struct *vmas[VMACACHE_SIZE]; -}; - -/* * When updating this, please also update struct resident_page_types[] in * kernel/fork.c */ diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 8a30de08e913..c726ea781255 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -293,6 +293,7 @@ struct mmc_card { #define MMC_QUIRK_BROKEN_IRQ_POLLING (1<<11) /* Polling SDIO_CCCR_INTx could create a fake interrupt */ #define MMC_QUIRK_TRIM_BROKEN (1<<12) /* Skip trim */ #define MMC_QUIRK_BROKEN_HPI (1<<13) /* Disable broken HPI support */ +#define MMC_QUIRK_BROKEN_SD_DISCARD (1<<14) /* Disable broken SD discard support */ bool reenable_cmdq; /* Re-enable Command Queue */ diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h index 15ae78cd2853..b8728d11c949 100644 --- a/include/linux/mmdebug.h +++ b/include/linux/mmdebug.h @@ -94,6 +94,12 @@ void dump_mm(const struct mm_struct *mm); #define VM_WARN(cond, format...) BUILD_BUG_ON_INVALID(cond) #endif +#ifdef CONFIG_DEBUG_VM_IRQSOFF +#define VM_WARN_ON_IRQS_ENABLED() WARN_ON_ONCE(!irqs_disabled()) +#else +#define VM_WARN_ON_IRQS_ENABLED() do { } while (0) +#endif + #ifdef CONFIG_DEBUG_VIRTUAL #define VIRTUAL_BUG_ON(cond) BUG_ON(cond) #else diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 355d842d2731..5f74891556f3 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -24,10 +24,10 @@ #include <asm/page.h> /* Free memory management - zoned buddy allocator. */ -#ifndef CONFIG_FORCE_MAX_ZONEORDER +#ifndef CONFIG_ARCH_FORCE_MAX_ORDER #define MAX_ORDER 11 #else -#define MAX_ORDER CONFIG_FORCE_MAX_ZONEORDER +#define MAX_ORDER CONFIG_ARCH_FORCE_MAX_ORDER #endif #define MAX_ORDER_NR_PAGES (1 << (MAX_ORDER - 1)) @@ -121,20 +121,6 @@ static inline bool free_area_empty(struct free_area *area, int migratetype) struct pglist_data; -/* - * Add a wild amount of padding here to ensure data fall into separate - * cachelines. There are very few zone structures in the machine, so space - * consumption is not a concern here. - */ -#if defined(CONFIG_SMP) -struct zone_padding { - char x[0]; -} ____cacheline_internodealigned_in_smp; -#define ZONE_PADDING(name) struct zone_padding name; -#else -#define ZONE_PADDING(name) -#endif - #ifdef CONFIG_NUMA enum numa_stat_item { NUMA_HIT, /* allocated in intended node */ @@ -222,6 +208,7 @@ enum node_stat_item { #endif #ifdef CONFIG_NUMA_BALANCING PGPROMOTE_SUCCESS, /* promote successfully */ + PGPROMOTE_CANDIDATE, /* candidate pages to promote */ #endif NR_VM_NODE_STAT_ITEMS }; @@ -307,6 +294,8 @@ static inline bool is_active_lru(enum lru_list lru) return (lru == LRU_ACTIVE_ANON || lru == LRU_ACTIVE_FILE); } +#define WORKINGSET_ANON 0 +#define WORKINGSET_FILE 1 #define ANON_AND_FILE 2 enum lruvec_flags { @@ -315,6 +304,207 @@ enum lruvec_flags { */ }; +#endif /* !__GENERATING_BOUNDS_H */ + +/* + * Evictable pages are divided into multiple generations. The youngest and the + * oldest generation numbers, max_seq and min_seq, are monotonically increasing. + * They form a sliding window of a variable size [MIN_NR_GENS, MAX_NR_GENS]. An + * offset within MAX_NR_GENS, i.e., gen, indexes the LRU list of the + * corresponding generation. The gen counter in folio->flags stores gen+1 while + * a page is on one of lrugen->lists[]. Otherwise it stores 0. + * + * A page is added to the youngest generation on faulting. The aging needs to + * check the accessed bit at least twice before handing this page over to the + * eviction. The first check takes care of the accessed bit set on the initial + * fault; the second check makes sure this page hasn't been used since then. + * This process, AKA second chance, requires a minimum of two generations, + * hence MIN_NR_GENS. And to maintain ABI compatibility with the active/inactive + * LRU, e.g., /proc/vmstat, these two generations are considered active; the + * rest of generations, if they exist, are considered inactive. See + * lru_gen_is_active(). + * + * PG_active is always cleared while a page is on one of lrugen->lists[] so that + * the aging needs not to worry about it. And it's set again when a page + * considered active is isolated for non-reclaiming purposes, e.g., migration. + * See lru_gen_add_folio() and lru_gen_del_folio(). + * + * MAX_NR_GENS is set to 4 so that the multi-gen LRU can support twice the + * number of categories of the active/inactive LRU when keeping track of + * accesses through page tables. This requires order_base_2(MAX_NR_GENS+1) bits + * in folio->flags. + */ +#define MIN_NR_GENS 2U +#define MAX_NR_GENS 4U + +/* + * Each generation is divided into multiple tiers. A page accessed N times + * through file descriptors is in tier order_base_2(N). A page in the first tier + * (N=0,1) is marked by PG_referenced unless it was faulted in through page + * tables or read ahead. A page in any other tier (N>1) is marked by + * PG_referenced and PG_workingset. This implies a minimum of two tiers is + * supported without using additional bits in folio->flags. + * + * In contrast to moving across generations which requires the LRU lock, moving + * across tiers only involves atomic operations on folio->flags and therefore + * has a negligible cost in the buffered access path. In the eviction path, + * comparisons of refaulted/(evicted+protected) from the first tier and the + * rest infer whether pages accessed multiple times through file descriptors + * are statistically hot and thus worth protecting. + * + * MAX_NR_TIERS is set to 4 so that the multi-gen LRU can support twice the + * number of categories of the active/inactive LRU when keeping track of + * accesses through file descriptors. This uses MAX_NR_TIERS-2 spare bits in + * folio->flags. + */ +#define MAX_NR_TIERS 4U + +#ifndef __GENERATING_BOUNDS_H + +struct lruvec; +struct page_vma_mapped_walk; + +#define LRU_GEN_MASK ((BIT(LRU_GEN_WIDTH) - 1) << LRU_GEN_PGOFF) +#define LRU_REFS_MASK ((BIT(LRU_REFS_WIDTH) - 1) << LRU_REFS_PGOFF) + +#ifdef CONFIG_LRU_GEN + +enum { + LRU_GEN_ANON, + LRU_GEN_FILE, +}; + +enum { + LRU_GEN_CORE, + LRU_GEN_MM_WALK, + LRU_GEN_NONLEAF_YOUNG, + NR_LRU_GEN_CAPS +}; + +#define MIN_LRU_BATCH BITS_PER_LONG +#define MAX_LRU_BATCH (MIN_LRU_BATCH * 64) + +/* whether to keep historical stats from evicted generations */ +#ifdef CONFIG_LRU_GEN_STATS +#define NR_HIST_GENS MAX_NR_GENS +#else +#define NR_HIST_GENS 1U +#endif + +/* + * The youngest generation number is stored in max_seq for both anon and file + * types as they are aged on an equal footing. The oldest generation numbers are + * stored in min_seq[] separately for anon and file types as clean file pages + * can be evicted regardless of swap constraints. + * + * Normally anon and file min_seq are in sync. But if swapping is constrained, + * e.g., out of swap space, file min_seq is allowed to advance and leave anon + * min_seq behind. + * + * The number of pages in each generation is eventually consistent and therefore + * can be transiently negative when reset_batch_size() is pending. + */ +struct lru_gen_struct { + /* the aging increments the youngest generation number */ + unsigned long max_seq; + /* the eviction increments the oldest generation numbers */ + unsigned long min_seq[ANON_AND_FILE]; + /* the birth time of each generation in jiffies */ + unsigned long timestamps[MAX_NR_GENS]; + /* the multi-gen LRU lists, lazily sorted on eviction */ + struct list_head lists[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; + /* the multi-gen LRU sizes, eventually consistent */ + long nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; + /* the exponential moving average of refaulted */ + unsigned long avg_refaulted[ANON_AND_FILE][MAX_NR_TIERS]; + /* the exponential moving average of evicted+protected */ + unsigned long avg_total[ANON_AND_FILE][MAX_NR_TIERS]; + /* the first tier doesn't need protection, hence the minus one */ + unsigned long protected[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS - 1]; + /* can be modified without holding the LRU lock */ + atomic_long_t evicted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; + atomic_long_t refaulted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; + /* whether the multi-gen LRU is enabled */ + bool enabled; +}; + +enum { + MM_LEAF_TOTAL, /* total leaf entries */ + MM_LEAF_OLD, /* old leaf entries */ + MM_LEAF_YOUNG, /* young leaf entries */ + MM_NONLEAF_TOTAL, /* total non-leaf entries */ + MM_NONLEAF_FOUND, /* non-leaf entries found in Bloom filters */ + MM_NONLEAF_ADDED, /* non-leaf entries added to Bloom filters */ + NR_MM_STATS +}; + +/* double-buffering Bloom filters */ +#define NR_BLOOM_FILTERS 2 + +struct lru_gen_mm_state { + /* set to max_seq after each iteration */ + unsigned long seq; + /* where the current iteration continues (inclusive) */ + struct list_head *head; + /* where the last iteration ended (exclusive) */ + struct list_head *tail; + /* to wait for the last page table walker to finish */ + struct wait_queue_head wait; + /* Bloom filters flip after each iteration */ + unsigned long *filters[NR_BLOOM_FILTERS]; + /* the mm stats for debugging */ + unsigned long stats[NR_HIST_GENS][NR_MM_STATS]; + /* the number of concurrent page table walkers */ + int nr_walkers; +}; + +struct lru_gen_mm_walk { + /* the lruvec under reclaim */ + struct lruvec *lruvec; + /* unstable max_seq from lru_gen_struct */ + unsigned long max_seq; + /* the next address within an mm to scan */ + unsigned long next_addr; + /* to batch promoted pages */ + int nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; + /* to batch the mm stats */ + int mm_stats[NR_MM_STATS]; + /* total batched items */ + int batched; + bool can_swap; + bool force_scan; +}; + +void lru_gen_init_lruvec(struct lruvec *lruvec); +void lru_gen_look_around(struct page_vma_mapped_walk *pvmw); + +#ifdef CONFIG_MEMCG +void lru_gen_init_memcg(struct mem_cgroup *memcg); +void lru_gen_exit_memcg(struct mem_cgroup *memcg); +#endif + +#else /* !CONFIG_LRU_GEN */ + +static inline void lru_gen_init_lruvec(struct lruvec *lruvec) +{ +} + +static inline void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) +{ +} + +#ifdef CONFIG_MEMCG +static inline void lru_gen_init_memcg(struct mem_cgroup *memcg) +{ +} + +static inline void lru_gen_exit_memcg(struct mem_cgroup *memcg) +{ +} +#endif + +#endif /* CONFIG_LRU_GEN */ + struct lruvec { struct list_head lists[NR_LRU_LISTS]; /* per lruvec lru_lock for memcg */ @@ -332,6 +522,12 @@ struct lruvec { unsigned long refaults[ANON_AND_FILE]; /* Various lruvec state flags (enum lruvec_flags) */ unsigned long flags; +#ifdef CONFIG_LRU_GEN + /* evictable pages divided into generations */ + struct lru_gen_struct lrugen; + /* to concurrently iterate lru_gen_mm_list */ + struct lru_gen_mm_state mm_state; +#endif #ifdef CONFIG_MEMCG struct pglist_data *pgdat; #endif @@ -369,13 +565,6 @@ enum zone_watermarks { #define NR_LOWORDER_PCP_LISTS (MIGRATE_PCPTYPES * (PAGE_ALLOC_COSTLY_ORDER + 1)) #define NR_PCP_LISTS (NR_LOWORDER_PCP_LISTS + NR_PCP_THP) -/* - * Shift to encode migratetype and order in the same integer, with order - * in the least significant bits. - */ -#define NR_PCP_ORDER_WIDTH 8 -#define NR_PCP_ORDER_MASK ((1<<NR_PCP_ORDER_WIDTH) - 1) - #define min_wmark_pages(z) (z->_watermark[WMARK_MIN] + z->watermark_boost) #define low_wmark_pages(z) (z->_watermark[WMARK_LOW] + z->watermark_boost) #define high_wmark_pages(z) (z->_watermark[WMARK_HIGH] + z->watermark_boost) @@ -628,7 +817,7 @@ struct zone { int initialized; /* Write-intensive fields used from the page allocator */ - ZONE_PADDING(_pad1_) + CACHELINE_PADDING(_pad1_); /* free areas of different sizes */ struct free_area free_area[MAX_ORDER]; @@ -640,7 +829,7 @@ struct zone { spinlock_t lock; /* Write-intensive fields used by compaction and vmstats. */ - ZONE_PADDING(_pad2_) + CACHELINE_PADDING(_pad2_); /* * When free pages are below this point, additional steps are taken @@ -677,7 +866,7 @@ struct zone { bool contiguous; - ZONE_PADDING(_pad3_) + CACHELINE_PADDING(_pad3_); /* Zone statistics */ atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS]; atomic_long_t vm_numa_event[NR_VM_NUMA_EVENT_ITEMS]; @@ -747,6 +936,8 @@ static inline bool zone_is_empty(struct zone *zone) #define ZONES_PGOFF (NODES_PGOFF - ZONES_WIDTH) #define LAST_CPUPID_PGOFF (ZONES_PGOFF - LAST_CPUPID_WIDTH) #define KASAN_TAG_PGOFF (LAST_CPUPID_PGOFF - KASAN_TAG_WIDTH) +#define LRU_GEN_PGOFF (KASAN_TAG_PGOFF - LRU_GEN_WIDTH) +#define LRU_REFS_PGOFF (LRU_GEN_PGOFF - LRU_REFS_WIDTH) /* * Define the bit shifts to access each section. For non-existent @@ -954,8 +1145,10 @@ typedef struct pglist_data { atomic_t nr_writeback_throttled;/* nr of writeback-throttled tasks */ unsigned long nr_reclaim_start; /* nr pages written while throttled * when throttling started. */ - struct task_struct *kswapd; /* Protected by - mem_hotplug_begin/done() */ +#ifdef CONFIG_MEMORY_HOTPLUG + struct mutex kswapd_lock; +#endif + struct task_struct *kswapd; /* Protected by kswapd_lock */ int kswapd_order; enum zone_type kswapd_highest_zoneidx; @@ -983,7 +1176,7 @@ typedef struct pglist_data { #endif /* CONFIG_NUMA */ /* Write-intensive fields used by page reclaim */ - ZONE_PADDING(_pad1_) + CACHELINE_PADDING(_pad1_); #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /* @@ -997,6 +1190,21 @@ typedef struct pglist_data { struct deferred_split deferred_split_queue; #endif +#ifdef CONFIG_NUMA_BALANCING + /* start time in ms of current promote rate limit period */ + unsigned int nbp_rl_start; + /* number of promote candidate pages at start time of current rate limit period */ + unsigned long nbp_rl_nr_cand; + /* promote threshold in ms */ + unsigned int nbp_threshold; + /* start time in ms of current promote threshold adjustment period */ + unsigned int nbp_th_start; + /* + * number of promote candidate pages at stat time of current promote + * threshold adjustment period + */ + unsigned long nbp_th_nr_cand; +#endif /* Fields commonly accessed by the page reclaim scanner */ /* @@ -1008,11 +1216,19 @@ typedef struct pglist_data { unsigned long flags; - ZONE_PADDING(_pad2_) +#ifdef CONFIG_LRU_GEN + /* kswap mm walk data */ + struct lru_gen_mm_walk mm_walk; +#endif + + CACHELINE_PADDING(_pad2_); /* Per-node vmstats */ struct per_cpu_nodestat __percpu *per_cpu_nodestats; atomic_long_t vm_stat[NR_VM_NODE_STAT_ITEMS]; +#ifdef CONFIG_NUMA + struct memory_tier __rcu *memtier; +#endif } pg_data_t; #define node_present_pages(nid) (NODE_DATA(nid)->node_present_pages) @@ -1026,11 +1242,6 @@ static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat) return pgdat->node_start_pfn + pgdat->node_spanned_pages; } -static inline bool pgdat_is_empty(pg_data_t *pgdat) -{ - return !pgdat->node_start_pfn && !pgdat->node_spanned_pages; -} - #include <linux/memory_hotplug.h> void build_all_zonelists(pg_data_t *pgdat); diff --git a/include/linux/net.h b/include/linux/net.h index 711c3593c3b8..18d942bbdf6e 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -41,6 +41,7 @@ struct net; #define SOCK_NOSPACE 2 #define SOCK_PASSCRED 3 #define SOCK_PASSSEC 4 +#define SOCK_SUPPORT_ZC 5 #ifndef ARCH_HAS_SOCKET_TYPES /** diff --git a/include/linux/node.h b/include/linux/node.h index 40d641a8bfb0..427a5975cf40 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -2,15 +2,15 @@ /* * include/linux/node.h - generic node definition * - * This is mainly for topological representation. We define the - * basic 'struct node' here, which can be embedded in per-arch + * This is mainly for topological representation. We define the + * basic 'struct node' here, which can be embedded in per-arch * definitions of processors. * * Basic handling of the devices is done in drivers/base/node.c - * and system devices are handled in drivers/base/sys.c. + * and system devices are handled in drivers/base/sys.c. * * Nodes are exported via driverfs in the class/node/devices/ - * directory. + * directory. */ #ifndef _LINUX_NODE_H_ #define _LINUX_NODE_H_ @@ -18,7 +18,6 @@ #include <linux/device.h> #include <linux/cpumask.h> #include <linux/list.h> -#include <linux/workqueue.h> /** * struct node_hmem_attrs - heterogeneous memory performance attributes @@ -84,10 +83,6 @@ static inline void node_set_perf_attrs(unsigned int nid, struct node { struct device dev; struct list_head access_list; - -#if defined(CONFIG_MEMORY_HOTPLUG) && defined(CONFIG_HUGETLBFS) - struct work_struct node_work; -#endif #ifdef CONFIG_HMEM_REPORTING struct list_head cache_attrs; struct device *cache_dev; @@ -96,7 +91,6 @@ struct node { struct memory_block; extern struct node *node_devices[]; -typedef void (*node_registration_func_t)(struct node *); #if defined(CONFIG_MEMORY_HOTPLUG) && defined(CONFIG_NUMA) void register_memory_blocks_under_node(int nid, unsigned long start_pfn, @@ -144,11 +138,6 @@ extern void unregister_memory_block_under_nodes(struct memory_block *mem_blk); extern int register_memory_node_under_compute_node(unsigned int mem_nid, unsigned int cpu_nid, unsigned access); - -#ifdef CONFIG_HUGETLBFS -extern void register_hugetlbfs_with_node(node_registration_func_t doregister, - node_registration_func_t unregister); -#endif #else static inline void node_dev_init(void) { @@ -176,18 +165,8 @@ static inline int unregister_cpu_under_node(unsigned int cpu, unsigned int nid) static inline void unregister_memory_block_under_nodes(struct memory_block *mem_blk) { } - -static inline void register_hugetlbfs_with_node(node_registration_func_t reg, - node_registration_func_t unreg) -{ -} #endif #define to_node(device) container_of(device, struct node, dev) -static inline bool node_is_toptier(int node) -{ - return node_state(node, N_CPU); -} - #endif /* _LINUX_NODE_H_ */ diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 4b71a96190a8..efef68c9352a 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -493,6 +493,7 @@ static inline int num_node_state(enum node_states state) #define first_online_node 0 #define first_memory_node 0 #define next_online_node(nid) (MAX_NUMNODES) +#define next_memory_node(nid) (MAX_NUMNODES) #define nr_node_ids 1U #define nr_online_nodes 1U @@ -504,12 +505,20 @@ static inline int num_node_state(enum node_states state) static inline int node_random(const nodemask_t *maskp) { #if defined(CONFIG_NUMA) && (MAX_NUMNODES > 1) - int w, bit = NUMA_NO_NODE; + int w, bit; w = nodes_weight(*maskp); - if (w) - bit = bitmap_ord_to_pos(maskp->bits, - get_random_int() % w, MAX_NUMNODES); + switch (w) { + case 0: + bit = NUMA_NO_NODE; + break; + case 1: + bit = first_node(*maskp); + break; + default: + bit = find_nth_bit(maskp->bits, MAX_NUMNODES, prandom_u32_max(w)); + break; + } return bit; #else return 0; diff --git a/include/linux/of.h b/include/linux/of.h index 766d002bddb9..6b79ef9a6541 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -342,7 +342,7 @@ extern int of_property_read_string_helper(const struct device_node *np, const char **out_strs, size_t sz, int index); extern int of_device_is_compatible(const struct device_node *device, const char *); -extern int of_device_compatible_match(struct device_node *device, +extern int of_device_compatible_match(const struct device_node *device, const char *const *compat); extern bool of_device_is_available(const struct device_node *device); extern bool of_device_is_big_endian(const struct device_node *device); @@ -562,7 +562,7 @@ static inline int of_device_is_compatible(const struct device_node *device, return 0; } -static inline int of_device_compatible_match(struct device_node *device, +static inline int of_device_compatible_match(const struct device_node *device, const char *const *compat) { return 0; diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h index 83fccd0c9bba..d6d3eae2f145 100644 --- a/include/linux/of_irq.h +++ b/include/linux/of_irq.h @@ -37,9 +37,8 @@ extern unsigned int irq_create_of_mapping(struct of_phandle_args *irq_data); extern int of_irq_to_resource(struct device_node *dev, int index, struct resource *r); -extern void of_irq_init(const struct of_device_id *matches); - #ifdef CONFIG_OF_IRQ +extern void of_irq_init(const struct of_device_id *matches); extern int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_args *out_irq); extern int of_irq_count(struct device_node *dev); @@ -57,6 +56,9 @@ extern struct irq_domain *of_msi_map_get_device_domain(struct device *dev, extern void of_msi_configure(struct device *dev, struct device_node *np); u32 of_msi_map_id(struct device *dev, struct device_node *msi_np, u32 id_in); #else +static inline void of_irq_init(const struct of_device_id *matches) +{ +} static inline int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_args *out_irq) { diff --git a/include/linux/oom.h b/include/linux/oom.h index 02d1e7bbd8cd..7d0c9c48a0c5 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -78,15 +78,6 @@ static inline bool tsk_is_oom_victim(struct task_struct * tsk) } /* - * Use this helper if tsk->mm != mm and the victim mm needs a special - * handling. This is guaranteed to stay true after once set. - */ -static inline bool mm_is_oom_victim(struct mm_struct *mm) -{ - return test_bit(MMF_OOM_VICTIM, &mm->flags); -} - -/* * Checks whether a page fault on the given mm is still reliable. * This is no longer true if the oom reaper started to reap the * address space which is reflected by MMF_UNSTABLE flag set in @@ -106,8 +97,6 @@ static inline vm_fault_t check_stable_address_space(struct mm_struct *mm) return 0; } -bool __oom_reap_task_mm(struct mm_struct *mm); - long oom_badness(struct task_struct *p, unsigned long totalpages); diff --git a/include/linux/overflow.h b/include/linux/overflow.h index 19dfdd74835e..1d3be1a2204c 100644 --- a/include/linux/overflow.h +++ b/include/linux/overflow.h @@ -51,8 +51,8 @@ static inline bool __must_check __must_check_overflow(bool overflow) return unlikely(overflow); } -/** check_add_overflow() - Calculate addition with overflow checking - * +/** + * check_add_overflow() - Calculate addition with overflow checking * @a: first addend * @b: second addend * @d: pointer to store sum @@ -66,8 +66,8 @@ static inline bool __must_check __must_check_overflow(bool overflow) #define check_add_overflow(a, b, d) \ __must_check_overflow(__builtin_add_overflow(a, b, d)) -/** check_sub_overflow() - Calculate subtraction with overflow checking - * +/** + * check_sub_overflow() - Calculate subtraction with overflow checking * @a: minuend; value to subtract from * @b: subtrahend; value to subtract from @a * @d: pointer to store difference @@ -81,8 +81,8 @@ static inline bool __must_check __must_check_overflow(bool overflow) #define check_sub_overflow(a, b, d) \ __must_check_overflow(__builtin_sub_overflow(a, b, d)) -/** check_mul_overflow() - Calculate multiplication with overflow checking - * +/** + * check_mul_overflow() - Calculate multiplication with overflow checking * @a: first factor * @b: second factor * @d: pointer to store product @@ -96,23 +96,24 @@ static inline bool __must_check __must_check_overflow(bool overflow) #define check_mul_overflow(a, b, d) \ __must_check_overflow(__builtin_mul_overflow(a, b, d)) -/** check_shl_overflow() - Calculate a left-shifted value and check overflow - * +/** + * check_shl_overflow() - Calculate a left-shifted value and check overflow * @a: Value to be shifted * @s: How many bits left to shift * @d: Pointer to where to store the result * * Computes *@d = (@a << @s) * - * Returns true if '*d' cannot hold the result or when 'a << s' doesn't + * Returns true if '*@d' cannot hold the result or when '@a << @s' doesn't * make sense. Example conditions: - * - 'a << s' causes bits to be lost when stored in *d. - * - 's' is garbage (e.g. negative) or so large that the result of - * 'a << s' is guaranteed to be 0. - * - 'a' is negative. - * - 'a << s' sets the sign bit, if any, in '*d'. * - * '*d' will hold the results of the attempted shift, but is not + * - '@a << @s' causes bits to be lost when stored in *@d. + * - '@s' is garbage (e.g. negative) or so large that the result of + * '@a << @s' is guaranteed to be 0. + * - '@a' is negative. + * - '@a << @s' sets the sign bit, if any, in '*@d'. + * + * '*@d' will hold the results of the attempted shift, but is not * considered "safe for use" if true is returned. */ #define check_shl_overflow(a, s, d) __must_check_overflow(({ \ @@ -129,7 +130,6 @@ static inline bool __must_check __must_check_overflow(bool overflow) /** * size_mul() - Calculate size_t multiplication with saturation at SIZE_MAX - * * @factor1: first factor * @factor2: second factor * @@ -149,7 +149,6 @@ static inline size_t __must_check size_mul(size_t factor1, size_t factor2) /** * size_add() - Calculate size_t addition with saturation at SIZE_MAX - * * @addend1: first addend * @addend2: second addend * @@ -169,7 +168,6 @@ static inline size_t __must_check size_add(size_t addend1, size_t addend2) /** * size_sub() - Calculate size_t subtraction with saturation at SIZE_MAX - * * @minuend: value to subtract from * @subtrahend: value to subtract from @minuend * @@ -192,7 +190,6 @@ static inline size_t __must_check size_sub(size_t minuend, size_t subtrahend) /** * array_size() - Calculate size of 2-dimensional array. - * * @a: dimension one * @b: dimension two * @@ -205,7 +202,6 @@ static inline size_t __must_check size_sub(size_t minuend, size_t subtrahend) /** * array3_size() - Calculate size of 3-dimensional array. - * * @a: dimension one * @b: dimension two * @c: dimension three @@ -220,7 +216,6 @@ static inline size_t __must_check size_sub(size_t minuend, size_t subtrahend) /** * flex_array_size() - Calculate size of a flexible array member * within an enclosing structure. - * * @p: Pointer to the structure. * @member: Name of the flexible array member. * @count: Number of elements in the array. @@ -237,7 +232,6 @@ static inline size_t __must_check size_sub(size_t minuend, size_t subtrahend) /** * struct_size() - Calculate size of structure with trailing flexible array. - * * @p: Pointer to the structure. * @member: Name of the array member. * @count: Number of elements in the array. diff --git a/include/linux/page-flags-layout.h b/include/linux/page-flags-layout.h index ef1e3e736e14..7d79818dc065 100644 --- a/include/linux/page-flags-layout.h +++ b/include/linux/page-flags-layout.h @@ -55,7 +55,8 @@ #define SECTIONS_WIDTH 0 #endif -#if ZONES_WIDTH + SECTIONS_WIDTH + NODES_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS +#if ZONES_WIDTH + LRU_GEN_WIDTH + SECTIONS_WIDTH + NODES_SHIFT \ + <= BITS_PER_LONG - NR_PAGEFLAGS #define NODES_WIDTH NODES_SHIFT #elif defined(CONFIG_SPARSEMEM_VMEMMAP) #error "Vmemmap: No space for nodes field in page flags" @@ -89,8 +90,8 @@ #define LAST_CPUPID_SHIFT 0 #endif -#if ZONES_WIDTH + SECTIONS_WIDTH + NODES_WIDTH + KASAN_TAG_WIDTH + LAST_CPUPID_SHIFT \ - <= BITS_PER_LONG - NR_PAGEFLAGS +#if ZONES_WIDTH + LRU_GEN_WIDTH + SECTIONS_WIDTH + NODES_WIDTH + \ + KASAN_TAG_WIDTH + LAST_CPUPID_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS #define LAST_CPUPID_WIDTH LAST_CPUPID_SHIFT #else #define LAST_CPUPID_WIDTH 0 @@ -100,10 +101,15 @@ #define LAST_CPUPID_NOT_IN_PAGE_FLAGS #endif -#if ZONES_WIDTH + SECTIONS_WIDTH + NODES_WIDTH + KASAN_TAG_WIDTH + LAST_CPUPID_WIDTH \ - > BITS_PER_LONG - NR_PAGEFLAGS +#if ZONES_WIDTH + LRU_GEN_WIDTH + SECTIONS_WIDTH + NODES_WIDTH + \ + KASAN_TAG_WIDTH + LAST_CPUPID_WIDTH > BITS_PER_LONG - NR_PAGEFLAGS #error "Not enough bits in page flags" #endif +/* see the comment on MAX_NR_TIERS */ +#define LRU_REFS_WIDTH min(__LRU_REFS_WIDTH, BITS_PER_LONG - NR_PAGEFLAGS - \ + ZONES_WIDTH - LRU_GEN_WIDTH - SECTIONS_WIDTH - \ + NODES_WIDTH - KASAN_TAG_WIDTH - LAST_CPUPID_WIDTH) + #endif #endif /* _LINUX_PAGE_FLAGS_LAYOUT */ diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 465ff35a8c00..0b0ae5084e60 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -1058,7 +1058,7 @@ static __always_inline void __ClearPageAnonExclusive(struct page *page) 1UL << PG_private | 1UL << PG_private_2 | \ 1UL << PG_writeback | 1UL << PG_reserved | \ 1UL << PG_slab | 1UL << PG_active | \ - 1UL << PG_unevictable | __PG_MLOCKED) + 1UL << PG_unevictable | __PG_MLOCKED | LRU_GEN_MASK) /* * Flags checked when a page is prepped for return by the page allocator. @@ -1069,7 +1069,7 @@ static __always_inline void __ClearPageAnonExclusive(struct page *page) * alloc-free cycle to prevent from reusing the page. */ #define PAGE_FLAGS_CHECK_AT_PREP \ - (PAGEFLAGS_MASK & ~__PG_HWPOISON) + ((PAGEFLAGS_MASK & ~__PG_HWPOISON) | LRU_GEN_MASK | LRU_REFS_MASK) #define PAGE_FLAGS_PRIVATE \ (1UL << PG_private | 1UL << PG_private_2) diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h index 679591301994..c141ea9a95ef 100644 --- a/include/linux/page_counter.h +++ b/include/linux/page_counter.h @@ -3,15 +3,17 @@ #define _LINUX_PAGE_COUNTER_H #include <linux/atomic.h> +#include <linux/cache.h> #include <linux/kernel.h> #include <asm/page.h> struct page_counter { + /* + * Make sure 'usage' does not share cacheline with any other field. The + * memcg->memory.usage is a hot member of struct mem_cgroup. + */ atomic_long_t usage; - unsigned long min; - unsigned long low; - unsigned long high; - unsigned long max; + CACHELINE_PADDING(_pad1_); /* effective memory.min and memory.min usage tracking */ unsigned long emin; @@ -23,18 +25,18 @@ struct page_counter { atomic_long_t low_usage; atomic_long_t children_low_usage; - /* legacy */ unsigned long watermark; unsigned long failcnt; - /* - * 'parent' is placed here to be far from 'usage' to reduce - * cache false sharing, as 'usage' is written mostly while - * parent is frequently read for cgroup's hierarchical - * counting nature. - */ + /* Keep all the read most fields in a separete cacheline. */ + CACHELINE_PADDING(_pad2_); + + unsigned long min; + unsigned long low; + unsigned long high; + unsigned long max; struct page_counter *parent; -}; +} ____cacheline_internodealigned_in_smp; #if BITS_PER_LONG == 32 #define PAGE_COUNTER_MAX LONG_MAX diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index fabb2e1e087f..22be4582faae 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -36,9 +36,15 @@ struct page_ext { unsigned long flags; }; +extern bool early_page_ext; extern unsigned long page_ext_size; extern void pgdat_page_ext_init(struct pglist_data *pgdat); +static inline bool early_page_ext_enabled(void) +{ + return early_page_ext; +} + #ifdef CONFIG_SPARSEMEM static inline void page_ext_init_flatmem(void) { @@ -55,7 +61,8 @@ static inline void page_ext_init(void) } #endif -struct page_ext *lookup_page_ext(const struct page *page); +extern struct page_ext *page_ext_get(struct page *page); +extern void page_ext_put(struct page_ext *page_ext); static inline struct page_ext *page_ext_next(struct page_ext *curr) { @@ -67,13 +74,13 @@ static inline struct page_ext *page_ext_next(struct page_ext *curr) #else /* !CONFIG_PAGE_EXTENSION */ struct page_ext; -static inline void pgdat_page_ext_init(struct pglist_data *pgdat) +static inline bool early_page_ext_enabled(void) { + return false; } -static inline struct page_ext *lookup_page_ext(const struct page *page) +static inline void pgdat_page_ext_init(struct pglist_data *pgdat) { - return NULL; } static inline void page_ext_init(void) @@ -87,5 +94,14 @@ static inline void page_ext_init_flatmem_late(void) static inline void page_ext_init_flatmem(void) { } + +static inline struct page_ext *page_ext_get(struct page *page) +{ + return NULL; +} + +static inline void page_ext_put(struct page_ext *page_ext) +{ +} #endif /* CONFIG_PAGE_EXTENSION */ #endif /* __LINUX_PAGE_EXT_H */ diff --git a/include/linux/page_idle.h b/include/linux/page_idle.h index 4663dfed1293..5cb7bd2078ec 100644 --- a/include/linux/page_idle.h +++ b/include/linux/page_idle.h @@ -13,65 +13,79 @@ * If there is not enough space to store Idle and Young bits in page flags, use * page ext flags instead. */ - static inline bool folio_test_young(struct folio *folio) { - struct page_ext *page_ext = lookup_page_ext(&folio->page); + struct page_ext *page_ext = page_ext_get(&folio->page); + bool page_young; if (unlikely(!page_ext)) return false; - return test_bit(PAGE_EXT_YOUNG, &page_ext->flags); + page_young = test_bit(PAGE_EXT_YOUNG, &page_ext->flags); + page_ext_put(page_ext); + + return page_young; } static inline void folio_set_young(struct folio *folio) { - struct page_ext *page_ext = lookup_page_ext(&folio->page); + struct page_ext *page_ext = page_ext_get(&folio->page); if (unlikely(!page_ext)) return; set_bit(PAGE_EXT_YOUNG, &page_ext->flags); + page_ext_put(page_ext); } static inline bool folio_test_clear_young(struct folio *folio) { - struct page_ext *page_ext = lookup_page_ext(&folio->page); + struct page_ext *page_ext = page_ext_get(&folio->page); + bool page_young; if (unlikely(!page_ext)) return false; - return test_and_clear_bit(PAGE_EXT_YOUNG, &page_ext->flags); + page_young = test_and_clear_bit(PAGE_EXT_YOUNG, &page_ext->flags); + page_ext_put(page_ext); + + return page_young; } static inline bool folio_test_idle(struct folio *folio) { - struct page_ext *page_ext = lookup_page_ext(&folio->page); + struct page_ext *page_ext = page_ext_get(&folio->page); + bool page_idle; if (unlikely(!page_ext)) return false; - return test_bit(PAGE_EXT_IDLE, &page_ext->flags); + page_idle = test_bit(PAGE_EXT_IDLE, &page_ext->flags); + page_ext_put(page_ext); + + return page_idle; } static inline void folio_set_idle(struct folio *folio) { - struct page_ext *page_ext = lookup_page_ext(&folio->page); + struct page_ext *page_ext = page_ext_get(&folio->page); if (unlikely(!page_ext)) return; set_bit(PAGE_EXT_IDLE, &page_ext->flags); + page_ext_put(page_ext); } static inline void folio_clear_idle(struct folio *folio) { - struct page_ext *page_ext = lookup_page_ext(&folio->page); + struct page_ext *page_ext = page_ext_get(&folio->page); if (unlikely(!page_ext)) return; clear_bit(PAGE_EXT_IDLE, &page_ext->flags); + page_ext_put(page_ext); } #endif /* !CONFIG_64BIT */ diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h index 83c7248053a1..5f1ae07d724b 100644 --- a/include/linux/pageblock-flags.h +++ b/include/linux/pageblock-flags.h @@ -53,6 +53,10 @@ extern unsigned int pageblock_order; #endif /* CONFIG_HUGETLB_PAGE */ #define pageblock_nr_pages (1UL << pageblock_order) +#define pageblock_align(pfn) ALIGN((pfn), pageblock_nr_pages) +#define pageblock_aligned(pfn) IS_ALIGNED((pfn), pageblock_nr_pages) +#define pageblock_start_pfn(pfn) ALIGN_DOWN((pfn), pageblock_nr_pages) +#define pageblock_end_pfn(pfn) ALIGN((pfn) + 1, pageblock_nr_pages) /* Forward declaration */ struct page; diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 201dc7281640..bbccb4044222 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -718,8 +718,8 @@ static inline struct page *find_subpage(struct page *head, pgoff_t index) unsigned filemap_get_folios(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch); -unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start, - unsigned int nr_pages, struct page **pages); +unsigned filemap_get_folios_contig(struct address_space *mapping, + pgoff_t *start, pgoff_t end, struct folio_batch *fbatch); unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index, pgoff_t end, xa_mark_t tag, unsigned int nr_pages, struct page **pages); @@ -989,19 +989,16 @@ static inline int lock_page_killable(struct page *page) } /* - * lock_page_or_retry - Lock the page, unless this would block and the + * folio_lock_or_retry - Lock the folio, unless this would block and the * caller indicated that it can handle a retry. * * Return value and mmap_lock implications depend on flags; see * __folio_lock_or_retry(). */ -static inline bool lock_page_or_retry(struct page *page, struct mm_struct *mm, - unsigned int flags) +static inline bool folio_lock_or_retry(struct folio *folio, + struct mm_struct *mm, unsigned int flags) { - struct folio *folio; might_sleep(); - - folio = page_folio(page); return folio_trylock(folio) || __folio_lock_or_retry(folio, mm, flags); } @@ -1042,7 +1039,6 @@ static inline int wait_on_page_locked_killable(struct page *page) return folio_wait_locked_killable(page_folio(page)); } -int folio_put_wait_locked(struct folio *folio, int state); void wait_on_page_writeback(struct page *page); void folio_wait_writeback(struct folio *folio); int folio_wait_writeback_killable(struct folio *folio); diff --git a/include/linux/pagewalk.h b/include/linux/pagewalk.h index ac7b38ad5903..f3fafb731ffd 100644 --- a/include/linux/pagewalk.h +++ b/include/linux/pagewalk.h @@ -15,12 +15,12 @@ struct mm_walk; * this handler is required to be able to handle * pmd_trans_huge() pmds. They may simply choose to * split_huge_page() instead of handling it explicitly. - * @pte_entry: if set, called for each non-empty PTE (lowest-level) - * entry + * @pte_entry: if set, called for each PTE (lowest-level) entry, + * including empty ones * @pte_hole: if set, called for each hole at all levels, - * depth is -1 if not known, 0:PGD, 1:P4D, 2:PUD, 3:PMD - * 4:PTE. Any folded depths (where PTRS_PER_P?D is equal - * to 1) are skipped. + * depth is -1 if not known, 0:PGD, 1:P4D, 2:PUD, 3:PMD. + * Any folded depths (where PTRS_PER_P?D is equal to 1) + * are skipped. * @hugetlb_entry: if set, called for each hugetlb entry * @test_walk: caller specific callback function to determine whether * we walk over the current vma or not. Returning 0 means diff --git a/include/linux/pci.h b/include/linux/pci.h index 5da0846aa3c1..2bda4a4e47e8 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -475,6 +475,7 @@ struct pci_dev { unsigned int broken_cmd_compl:1; /* No compl for some cmds */ #endif #ifdef CONFIG_PCIE_PTM + u16 ptm_cap; /* PTM Capability */ unsigned int ptm_root:1; unsigned int ptm_enabled:1; u8 ptm_granularity; @@ -1677,10 +1678,12 @@ bool pci_ats_disabled(void); #ifdef CONFIG_PCIE_PTM int pci_enable_ptm(struct pci_dev *dev, u8 *granularity); +void pci_disable_ptm(struct pci_dev *dev); bool pcie_ptm_enabled(struct pci_dev *dev); #else static inline int pci_enable_ptm(struct pci_dev *dev, u8 *granularity) { return -EINVAL; } +static inline void pci_disable_ptm(struct pci_dev *dev) { } static inline bool pcie_ptm_enabled(struct pci_dev *dev) { return false; } #endif diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h index 5fda40f97fe9..36b942b67b7d 100644 --- a/include/linux/percpu-rwsem.h +++ b/include/linux/percpu-rwsem.h @@ -121,9 +121,15 @@ static inline void percpu_up_read(struct percpu_rw_semaphore *sem) preempt_enable(); } +extern bool percpu_is_read_locked(struct percpu_rw_semaphore *); extern void percpu_down_write(struct percpu_rw_semaphore *); extern void percpu_up_write(struct percpu_rw_semaphore *); +static inline bool percpu_is_write_locked(struct percpu_rw_semaphore *sem) +{ + return atomic_read(&sem->block); +} + extern int __percpu_init_rwsem(struct percpu_rw_semaphore *, const char *, struct lock_class_key *); diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h index 01861eebed79..8ed5fba6d156 100644 --- a/include/linux/percpu_counter.h +++ b/include/linux/percpu_counter.h @@ -15,6 +15,9 @@ #include <linux/types.h> #include <linux/gfp.h> +/* percpu_counter batch for local add or sub */ +#define PERCPU_COUNTER_LOCAL_BATCH INT_MAX + #ifdef CONFIG_SMP struct percpu_counter { @@ -56,6 +59,22 @@ static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) percpu_counter_add_batch(fbc, amount, percpu_counter_batch); } +/* + * With percpu_counter_add_local() and percpu_counter_sub_local(), counts + * are accumulated in local per cpu counter and not in fbc->count until + * local count overflows PERCPU_COUNTER_LOCAL_BATCH. This makes counter + * write efficient. + * But percpu_counter_sum(), instead of percpu_counter_read(), needs to be + * used to add up the counts from each CPU to account for all the local + * counts. So percpu_counter_add_local() and percpu_counter_sub_local() + * should be used when a counter is updated frequently and read rarely. + */ +static inline void +percpu_counter_add_local(struct percpu_counter *fbc, s64 amount) +{ + percpu_counter_add_batch(fbc, amount, PERCPU_COUNTER_LOCAL_BATCH); +} + static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc) { s64 ret = __percpu_counter_sum(fbc); @@ -138,6 +157,13 @@ percpu_counter_add(struct percpu_counter *fbc, s64 amount) preempt_enable(); } +/* non-SMP percpu_counter_add_local is the same with percpu_counter_add */ +static inline void +percpu_counter_add_local(struct percpu_counter *fbc, s64 amount) +{ + percpu_counter_add(fbc, amount); +} + static inline void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) { @@ -193,4 +219,10 @@ static inline void percpu_counter_sub(struct percpu_counter *fbc, s64 amount) percpu_counter_add(fbc, -amount); } +static inline void +percpu_counter_sub_local(struct percpu_counter *fbc, s64 amount) +{ + percpu_counter_add_local(fbc, -amount); +} + #endif /* _LINUX_PERCPU_COUNTER_H */ diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index 0407a38b470a..0356cb6a215d 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -24,10 +24,11 @@ /* * ARM PMU hw_event flags */ -/* Event uses a 64bit counter */ -#define ARMPMU_EVT_64BIT 1 -/* Event uses a 47bit counter */ -#define ARMPMU_EVT_47BIT 2 +#define ARMPMU_EVT_64BIT 0x00001 /* Event uses a 64bit counter */ +#define ARMPMU_EVT_47BIT 0x00002 /* Event uses a 47bit counter */ + +static_assert((PERF_EVENT_FLAG_ARCH & ARMPMU_EVT_64BIT) == ARMPMU_EVT_64BIT); +static_assert((PERF_EVENT_FLAG_ARCH & ARMPMU_EVT_47BIT) == ARMPMU_EVT_47BIT); #define HW_OP_UNSUPPORTED 0xFFFF #define C(_x) PERF_COUNT_HW_CACHE_##_x diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index ee8b9ecdc03b..0031f7b4d9ab 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -36,6 +36,7 @@ struct perf_guest_info_callbacks { }; #ifdef CONFIG_HAVE_HW_BREAKPOINT +#include <linux/rhashtable-types.h> #include <asm/hw_breakpoint.h> #endif @@ -60,6 +61,7 @@ struct perf_guest_info_callbacks { #include <linux/refcount.h> #include <linux/security.h> #include <linux/static_call.h> +#include <linux/lockdep.h> #include <asm/local.h> struct perf_callchain_entry { @@ -137,9 +139,11 @@ struct hw_perf_event_extra { * PERF_EVENT_FLAG_ARCH bits are reserved for architecture-specific * usage. */ -#define PERF_EVENT_FLAG_ARCH 0x0000ffff +#define PERF_EVENT_FLAG_ARCH 0x000fffff #define PERF_EVENT_FLAG_USER_READ_CNT 0x80000000 +static_assert((PERF_EVENT_FLAG_USER_READ_CNT & PERF_EVENT_FLAG_ARCH) == 0); + /** * struct hw_perf_event - performance event hardware details: */ @@ -178,7 +182,7 @@ struct hw_perf_event { * creation and event initalization. */ struct arch_hw_breakpoint info; - struct list_head bp_list; + struct rhlist_head bp_list; }; #endif struct { /* amd_iommu */ @@ -631,7 +635,23 @@ struct pmu_event_list { struct list_head list; }; +/* + * event->sibling_list is modified whole holding both ctx->lock and ctx->mutex + * as such iteration must hold either lock. However, since ctx->lock is an IRQ + * safe lock, and is only held by the CPU doing the modification, having IRQs + * disabled is sufficient since it will hold-off the IPIs. + */ +#ifdef CONFIG_PROVE_LOCKING +#define lockdep_assert_event_ctx(event) \ + WARN_ON_ONCE(__lockdep_enabled && \ + (this_cpu_read(hardirqs_enabled) && \ + lockdep_is_held(&(event)->ctx->mutex) != LOCK_STATE_HELD)) +#else +#define lockdep_assert_event_ctx(event) +#endif + #define for_each_sibling_event(sibling, event) \ + lockdep_assert_event_ctx(event); \ if ((event)->group_leader == (event)) \ list_for_each_entry((sibling), &(event)->sibling_list, sibling_list) @@ -736,11 +756,14 @@ struct perf_event { struct fasync_struct *fasync; /* delayed work for NMIs and such */ - int pending_wakeup; - int pending_kill; - int pending_disable; + unsigned int pending_wakeup; + unsigned int pending_kill; + unsigned int pending_disable; + unsigned int pending_sigtrap; unsigned long pending_addr; /* SIGTRAP */ - struct irq_work pending; + struct irq_work pending_irq; + struct callback_head pending_task; + unsigned int pending_work; atomic_t event_limit; @@ -857,6 +880,14 @@ struct perf_event_context { #endif void *task_ctx_data; /* pmu specific data */ struct rcu_head rcu_head; + + /* + * Sum (event->pending_sigtrap + event->pending_work) + * + * The SIGTRAP is targeted at ctx->task, as such it won't do changing + * that until the signal is delivered. + */ + local_t nr_pending; }; /* @@ -1007,18 +1038,20 @@ struct perf_sample_data { * Fields set by perf_sample_data_init(), group so as to * minimize the cachelines touched. */ - u64 addr; - struct perf_raw_record *raw; - struct perf_branch_stack *br_stack; + u64 sample_flags; u64 period; - union perf_sample_weight weight; - u64 txn; - union perf_mem_data_src data_src; /* * The other fields, optionally {set,used} by * perf_{prepare,output}_sample(). */ + struct perf_branch_stack *br_stack; + union perf_sample_weight weight; + union perf_mem_data_src data_src; + u64 txn; + u64 addr; + struct perf_raw_record *raw; + u64 type; u64 ip; struct { @@ -1056,13 +1089,13 @@ static inline void perf_sample_data_init(struct perf_sample_data *data, u64 addr, u64 period) { /* remaining struct members initialized in perf_prepare_sample() */ - data->addr = addr; - data->raw = NULL; - data->br_stack = NULL; + data->sample_flags = PERF_SAMPLE_PERIOD; data->period = period; - data->weight.full = 0; - data->data_src.val = PERF_MEM_NA; - data->txn = 0; + + if (addr) { + data->addr = addr; + data->sample_flags |= PERF_SAMPLE_ADDR; + } } /* @@ -1078,6 +1111,7 @@ static inline void perf_clear_branch_entry_bitfields(struct perf_branch_entry *b br->abort = 0; br->cycles = 0; br->type = 0; + br->spec = PERF_BR_SPEC_NA; br->reserved = 0; } @@ -1684,4 +1718,30 @@ static inline void perf_lopwr_cb(bool mode) } #endif +#ifdef CONFIG_PERF_EVENTS +static inline bool branch_sample_no_flags(const struct perf_event *event) +{ + return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_NO_FLAGS; +} + +static inline bool branch_sample_no_cycles(const struct perf_event *event) +{ + return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_NO_CYCLES; +} + +static inline bool branch_sample_type(const struct perf_event *event) +{ + return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_TYPE_SAVE; +} + +static inline bool branch_sample_hw_index(const struct perf_event *event) +{ + return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX; +} + +static inline bool branch_sample_priv(const struct perf_event *event) +{ + return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_PRIV_SAVE; +} +#endif /* CONFIG_PERF_EVENTS */ #endif /* _LINUX_PERF_EVENT_H */ diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 014ee8f0fbaa..a108b60a6962 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -213,7 +213,7 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, #endif #ifndef __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG -#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) @@ -234,7 +234,7 @@ static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, BUILD_BUG(); return 0; } -#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG */ #endif #ifndef __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH @@ -260,6 +260,19 @@ static inline int pmdp_clear_flush_young(struct vm_area_struct *vma, #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif +#ifndef arch_has_hw_pte_young +/* + * Return whether the accessed bit is supported on the local CPU. + * + * This stub assumes accessing through an old PTE triggers a page fault. + * Architectures that automatically set the access bit should overwrite it. + */ +static inline bool arch_has_hw_pte_young(void) +{ + return false; +} +#endif + #ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long address, @@ -1276,8 +1289,7 @@ static inline int pgd_devmap(pgd_t pgd) #endif #if !defined(CONFIG_TRANSPARENT_HUGEPAGE) || \ - (defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ - !defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)) + !defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) static inline int pud_trans_huge(pud_t pud) { return 0; @@ -1598,11 +1610,7 @@ typedef unsigned int pgtbl_mod_mask; #endif #ifndef has_transparent_hugepage -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -#define has_transparent_hugepage() 1 -#else -#define has_transparent_hugepage() 0 -#endif +#define has_transparent_hugepage() IS_BUILTIN(CONFIG_TRANSPARENT_HUGEPAGE) #endif /* diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 664dd409feb9..3f01ac8017e0 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -122,6 +122,7 @@ enum phylink_op_type { * (See commit 7cceb599d15d ("net: phylink: avoid mac_config calls") * @poll_fixed_state: if true, starts link_poll, * if MAC link is at %MLO_AN_FIXED mode. + * @mac_managed_pm: if true, indicate the MAC driver is responsible for PHY PM. * @ovr_an_inband: if true, override PCS to MLO_AN_INBAND * @get_fixed_state: callback to execute to determine the fixed link state, * if MAC link is at %MLO_AN_FIXED mode. @@ -134,6 +135,7 @@ struct phylink_config { enum phylink_op_type type; bool legacy_pre_march2020; bool poll_fixed_state; + bool mac_managed_pm; bool ovr_an_inband; void (*get_fixed_state)(struct phylink_config *config, struct phylink_link_state *state); diff --git a/include/linux/platform_data/adp5588.h b/include/linux/platform_data/adp5588.h deleted file mode 100644 index 6d3f7d911a92..000000000000 --- a/include/linux/platform_data/adp5588.h +++ /dev/null @@ -1,171 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Analog Devices ADP5588 I/O Expander and QWERTY Keypad Controller - * - * Copyright 2009-2010 Analog Devices Inc. - */ - -#ifndef _ADP5588_H -#define _ADP5588_H - -#define DEV_ID 0x00 /* Device ID */ -#define CFG 0x01 /* Configuration Register1 */ -#define INT_STAT 0x02 /* Interrupt Status Register */ -#define KEY_LCK_EC_STAT 0x03 /* Key Lock and Event Counter Register */ -#define Key_EVENTA 0x04 /* Key Event Register A */ -#define Key_EVENTB 0x05 /* Key Event Register B */ -#define Key_EVENTC 0x06 /* Key Event Register C */ -#define Key_EVENTD 0x07 /* Key Event Register D */ -#define Key_EVENTE 0x08 /* Key Event Register E */ -#define Key_EVENTF 0x09 /* Key Event Register F */ -#define Key_EVENTG 0x0A /* Key Event Register G */ -#define Key_EVENTH 0x0B /* Key Event Register H */ -#define Key_EVENTI 0x0C /* Key Event Register I */ -#define Key_EVENTJ 0x0D /* Key Event Register J */ -#define KP_LCK_TMR 0x0E /* Keypad Lock1 to Lock2 Timer */ -#define UNLOCK1 0x0F /* Unlock Key1 */ -#define UNLOCK2 0x10 /* Unlock Key2 */ -#define GPIO_INT_STAT1 0x11 /* GPIO Interrupt Status */ -#define GPIO_INT_STAT2 0x12 /* GPIO Interrupt Status */ -#define GPIO_INT_STAT3 0x13 /* GPIO Interrupt Status */ -#define GPIO_DAT_STAT1 0x14 /* GPIO Data Status, Read twice to clear */ -#define GPIO_DAT_STAT2 0x15 /* GPIO Data Status, Read twice to clear */ -#define GPIO_DAT_STAT3 0x16 /* GPIO Data Status, Read twice to clear */ -#define GPIO_DAT_OUT1 0x17 /* GPIO DATA OUT */ -#define GPIO_DAT_OUT2 0x18 /* GPIO DATA OUT */ -#define GPIO_DAT_OUT3 0x19 /* GPIO DATA OUT */ -#define GPIO_INT_EN1 0x1A /* GPIO Interrupt Enable */ -#define GPIO_INT_EN2 0x1B /* GPIO Interrupt Enable */ -#define GPIO_INT_EN3 0x1C /* GPIO Interrupt Enable */ -#define KP_GPIO1 0x1D /* Keypad or GPIO Selection */ -#define KP_GPIO2 0x1E /* Keypad or GPIO Selection */ -#define KP_GPIO3 0x1F /* Keypad or GPIO Selection */ -#define GPI_EM1 0x20 /* GPI Event Mode 1 */ -#define GPI_EM2 0x21 /* GPI Event Mode 2 */ -#define GPI_EM3 0x22 /* GPI Event Mode 3 */ -#define GPIO_DIR1 0x23 /* GPIO Data Direction */ -#define GPIO_DIR2 0x24 /* GPIO Data Direction */ -#define GPIO_DIR3 0x25 /* GPIO Data Direction */ -#define GPIO_INT_LVL1 0x26 /* GPIO Edge/Level Detect */ -#define GPIO_INT_LVL2 0x27 /* GPIO Edge/Level Detect */ -#define GPIO_INT_LVL3 0x28 /* GPIO Edge/Level Detect */ -#define Debounce_DIS1 0x29 /* Debounce Disable */ -#define Debounce_DIS2 0x2A /* Debounce Disable */ -#define Debounce_DIS3 0x2B /* Debounce Disable */ -#define GPIO_PULL1 0x2C /* GPIO Pull Disable */ -#define GPIO_PULL2 0x2D /* GPIO Pull Disable */ -#define GPIO_PULL3 0x2E /* GPIO Pull Disable */ -#define CMP_CFG_STAT 0x30 /* Comparator Configuration and Status Register */ -#define CMP_CONFG_SENS1 0x31 /* Sensor1 Comparator Configuration Register */ -#define CMP_CONFG_SENS2 0x32 /* L2 Light Sensor Reference Level, Output Falling for Sensor 1 */ -#define CMP1_LVL2_TRIP 0x33 /* L2 Light Sensor Hysteresis (Active when Output Rising) for Sensor 1 */ -#define CMP1_LVL2_HYS 0x34 /* L3 Light Sensor Reference Level, Output Falling For Sensor 1 */ -#define CMP1_LVL3_TRIP 0x35 /* L3 Light Sensor Hysteresis (Active when Output Rising) For Sensor 1 */ -#define CMP1_LVL3_HYS 0x36 /* Sensor 2 Comparator Configuration Register */ -#define CMP2_LVL2_TRIP 0x37 /* L2 Light Sensor Reference Level, Output Falling for Sensor 2 */ -#define CMP2_LVL2_HYS 0x38 /* L2 Light Sensor Hysteresis (Active when Output Rising) for Sensor 2 */ -#define CMP2_LVL3_TRIP 0x39 /* L3 Light Sensor Reference Level, Output Falling For Sensor 2 */ -#define CMP2_LVL3_HYS 0x3A /* L3 Light Sensor Hysteresis (Active when Output Rising) For Sensor 2 */ -#define CMP1_ADC_DAT_R1 0x3B /* Comparator 1 ADC data Register1 */ -#define CMP1_ADC_DAT_R2 0x3C /* Comparator 1 ADC data Register2 */ -#define CMP2_ADC_DAT_R1 0x3D /* Comparator 2 ADC data Register1 */ -#define CMP2_ADC_DAT_R2 0x3E /* Comparator 2 ADC data Register2 */ - -#define ADP5588_DEVICE_ID_MASK 0xF - - /* Configuration Register1 */ -#define ADP5588_AUTO_INC (1 << 7) -#define ADP5588_GPIEM_CFG (1 << 6) -#define ADP5588_OVR_FLOW_M (1 << 5) -#define ADP5588_INT_CFG (1 << 4) -#define ADP5588_OVR_FLOW_IEN (1 << 3) -#define ADP5588_K_LCK_IM (1 << 2) -#define ADP5588_GPI_IEN (1 << 1) -#define ADP5588_KE_IEN (1 << 0) - -/* Interrupt Status Register */ -#define ADP5588_CMP2_INT (1 << 5) -#define ADP5588_CMP1_INT (1 << 4) -#define ADP5588_OVR_FLOW_INT (1 << 3) -#define ADP5588_K_LCK_INT (1 << 2) -#define ADP5588_GPI_INT (1 << 1) -#define ADP5588_KE_INT (1 << 0) - -/* Key Lock and Event Counter Register */ -#define ADP5588_K_LCK_EN (1 << 6) -#define ADP5588_LCK21 0x30 -#define ADP5588_KEC 0xF - -#define ADP5588_MAXGPIO 18 -#define ADP5588_BANK(offs) ((offs) >> 3) -#define ADP5588_BIT(offs) (1u << ((offs) & 0x7)) - -/* Put one of these structures in i2c_board_info platform_data */ - -#define ADP5588_KEYMAPSIZE 80 - -#define GPI_PIN_ROW0 97 -#define GPI_PIN_ROW1 98 -#define GPI_PIN_ROW2 99 -#define GPI_PIN_ROW3 100 -#define GPI_PIN_ROW4 101 -#define GPI_PIN_ROW5 102 -#define GPI_PIN_ROW6 103 -#define GPI_PIN_ROW7 104 -#define GPI_PIN_COL0 105 -#define GPI_PIN_COL1 106 -#define GPI_PIN_COL2 107 -#define GPI_PIN_COL3 108 -#define GPI_PIN_COL4 109 -#define GPI_PIN_COL5 110 -#define GPI_PIN_COL6 111 -#define GPI_PIN_COL7 112 -#define GPI_PIN_COL8 113 -#define GPI_PIN_COL9 114 - -#define GPI_PIN_ROW_BASE GPI_PIN_ROW0 -#define GPI_PIN_ROW_END GPI_PIN_ROW7 -#define GPI_PIN_COL_BASE GPI_PIN_COL0 -#define GPI_PIN_COL_END GPI_PIN_COL9 - -#define GPI_PIN_BASE GPI_PIN_ROW_BASE -#define GPI_PIN_END GPI_PIN_COL_END - -#define ADP5588_GPIMAPSIZE_MAX (GPI_PIN_END - GPI_PIN_BASE + 1) - -struct adp5588_gpi_map { - unsigned short pin; - unsigned short sw_evt; -}; - -struct adp5588_kpad_platform_data { - int rows; /* Number of rows */ - int cols; /* Number of columns */ - const unsigned short *keymap; /* Pointer to keymap */ - unsigned short keymapsize; /* Keymap size */ - unsigned repeat:1; /* Enable key repeat */ - unsigned en_keylock:1; /* Enable Key Lock feature */ - unsigned short unlock_key1; /* Unlock Key 1 */ - unsigned short unlock_key2; /* Unlock Key 2 */ - const struct adp5588_gpi_map *gpimap; - unsigned short gpimapsize; - const struct adp5588_gpio_platform_data *gpio_data; -}; - -struct i2c_client; /* forward declaration */ - -struct adp5588_gpio_platform_data { - int gpio_start; /* GPIO Chip base # */ - const char *const *names; - unsigned irq_base; /* interrupt base # */ - unsigned pullup_dis_mask; /* Pull-Up Disable Mask */ - int (*setup)(struct i2c_client *client, - unsigned gpio, unsigned ngpio, - void *context); - int (*teardown)(struct i2c_client *client, - unsigned gpio, unsigned ngpio, - void *context); - void *context; -}; - -#endif diff --git a/include/linux/pm.h b/include/linux/pm.h index 871c9c49ec9d..93cd34f00822 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -375,19 +375,20 @@ const struct dev_pm_ops name = { \ } #ifdef CONFIG_PM -#define _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, runtime_suspend_fn, \ - runtime_resume_fn, idle_fn, sec, ns) \ - _DEFINE_DEV_PM_OPS(name, suspend_fn, resume_fn, runtime_suspend_fn, \ - runtime_resume_fn, idle_fn); \ - __EXPORT_SYMBOL(name, sec, ns) +#define _EXPORT_DEV_PM_OPS(name, sec, ns) \ + const struct dev_pm_ops name; \ + __EXPORT_SYMBOL(name, sec, ns); \ + const struct dev_pm_ops name #else -#define _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, runtime_suspend_fn, \ - runtime_resume_fn, idle_fn, sec, ns) \ -static __maybe_unused _DEFINE_DEV_PM_OPS(__static_##name, suspend_fn, \ - resume_fn, runtime_suspend_fn, \ - runtime_resume_fn, idle_fn) +#define _EXPORT_DEV_PM_OPS(name, sec, ns) \ + static __maybe_unused const struct dev_pm_ops __static_##name #endif +#define EXPORT_DEV_PM_OPS(name) _EXPORT_DEV_PM_OPS(name, "", "") +#define EXPORT_GPL_DEV_PM_OPS(name) _EXPORT_DEV_PM_OPS(name, "_gpl", "") +#define EXPORT_NS_DEV_PM_OPS(name, ns) _EXPORT_DEV_PM_OPS(name, "", #ns) +#define EXPORT_NS_GPL_DEV_PM_OPS(name, ns) _EXPORT_DEV_PM_OPS(name, "_gpl", #ns) + /* * Use this if you want to use the same suspend and resume callbacks for suspend * to RAM and hibernation. @@ -399,13 +400,21 @@ static __maybe_unused _DEFINE_DEV_PM_OPS(__static_##name, suspend_fn, \ _DEFINE_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL) #define EXPORT_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ - _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "", "") + EXPORT_DEV_PM_OPS(name) = { \ + SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ + } #define EXPORT_GPL_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ - _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "_gpl", "") + EXPORT_GPL_DEV_PM_OPS(name) = { \ + SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ + } #define EXPORT_NS_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn, ns) \ - _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "", #ns) + EXPORT_NS_DEV_PM_OPS(name, ns) = { \ + SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ + } #define EXPORT_NS_GPL_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn, ns) \ - _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "_gpl", #ns) + EXPORT_NS_GPL_DEV_PM_OPS(name, ns) = { \ + SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ + } /* Deprecated. Use DEFINE_SIMPLE_DEV_PM_OPS() instead. */ #define SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 0a41b2dcccad..9a8151a2bdea 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -40,17 +40,21 @@ resume_fn, idle_fn) #define EXPORT_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ - _EXPORT_DEV_PM_OPS(name, pm_runtime_force_suspend, pm_runtime_force_resume, \ - suspend_fn, resume_fn, idle_fn, "", "") + EXPORT_DEV_PM_OPS(name) = { \ + RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ + } #define EXPORT_GPL_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ - _EXPORT_DEV_PM_OPS(name, pm_runtime_force_suspend, pm_runtime_force_resume, \ - suspend_fn, resume_fn, idle_fn, "_gpl", "") + EXPORT_GPL_DEV_PM_OPS(name) = { \ + RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ + } #define EXPORT_NS_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn, ns) \ - _EXPORT_DEV_PM_OPS(name, pm_runtime_force_suspend, pm_runtime_force_resume, \ - suspend_fn, resume_fn, idle_fn, "", #ns) + EXPORT_NS_DEV_PM_OPS(name, ns) = { \ + RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ + } #define EXPORT_NS_GPL_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn, ns) \ - _EXPORT_DEV_PM_OPS(name, pm_runtime_force_suspend, pm_runtime_force_resume, \ - suspend_fn, resume_fn, idle_fn, "_gpl", #ns) + EXPORT_NS_GPL_DEV_PM_OPS(name, ns) = { \ + RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ + } #ifdef CONFIG_PM extern struct workqueue_struct *pm_wq; diff --git a/include/linux/prandom.h b/include/linux/prandom.h index deace5fb4e62..e0a0759dd09c 100644 --- a/include/linux/prandom.h +++ b/include/linux/prandom.h @@ -12,16 +12,6 @@ #include <linux/percpu.h> #include <linux/random.h> -static inline u32 prandom_u32(void) -{ - return get_random_u32(); -} - -static inline void prandom_bytes(void *buf, size_t nbytes) -{ - return get_random_bytes(buf, nbytes); -} - struct rnd_state { __u32 s1, s2, s3, s4; }; @@ -37,17 +27,20 @@ void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state); * prandom_u32_max - returns a pseudo-random number in interval [0, ep_ro) * @ep_ro: right open interval endpoint * - * Returns a pseudo-random number that is in interval [0, ep_ro). Note - * that the result depends on PRNG being well distributed in [0, ~0U] - * u32 space. Here we use maximally equidistributed combined Tausworthe - * generator, that is, prandom_u32(). This is useful when requesting a - * random index of an array containing ep_ro elements, for example. + * Returns a pseudo-random number that is in interval [0, ep_ro). This is + * useful when requesting a random index of an array containing ep_ro elements, + * for example. The result is somewhat biased when ep_ro is not a power of 2, + * so do not use this for cryptographic purposes. * * Returns: pseudo-random number in interval [0, ep_ro) */ static inline u32 prandom_u32_max(u32 ep_ro) { - return (u32)(((u64) prandom_u32() * ep_ro) >> 32); + if (__builtin_constant_p(ep_ro <= 1U << 8) && ep_ro <= 1U << 8) + return (get_random_u8() * ep_ro) >> 8; + if (__builtin_constant_p(ep_ro <= 1U << 16) && ep_ro <= 1U << 16) + return (get_random_u16() * ep_ro) >> 16; + return ((u64)get_random_u32() * ep_ro) >> 32; } /* diff --git a/include/linux/preempt.h b/include/linux/preempt.h index b4381f255a5c..0df425bf9bd7 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -421,4 +421,46 @@ static inline void migrate_enable(void) { } #endif /* CONFIG_SMP */ +/** + * preempt_disable_nested - Disable preemption inside a normally preempt disabled section + * + * Use for code which requires preemption protection inside a critical + * section which has preemption disabled implicitly on non-PREEMPT_RT + * enabled kernels, by e.g.: + * - holding a spinlock/rwlock + * - soft interrupt context + * - regular interrupt handlers + * + * On PREEMPT_RT enabled kernels spinlock/rwlock held sections, soft + * interrupt context and regular interrupt handlers are preemptible and + * only prevent migration. preempt_disable_nested() ensures that preemption + * is disabled for cases which require CPU local serialization even on + * PREEMPT_RT. For non-PREEMPT_RT kernels this is a NOP. + * + * The use cases are code sequences which are not serialized by a + * particular lock instance, e.g.: + * - seqcount write side critical sections where the seqcount is not + * associated to a particular lock and therefore the automatic + * protection mechanism does not work. This prevents a live lock + * against a preempting high priority reader. + * - RMW per CPU variable updates like vmstat. + */ +/* Macro to avoid header recursion hell vs. lockdep */ +#define preempt_disable_nested() \ +do { \ + if (IS_ENABLED(CONFIG_PREEMPT_RT)) \ + preempt_disable(); \ + else \ + lockdep_assert_preemption_disabled(); \ +} while (0) + +/** + * preempt_enable_nested - Undo the effect of preempt_disable_nested() + */ +static __always_inline void preempt_enable_nested(void) +{ + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_enable(); +} + #endif /* __LINUX_PREEMPT_H */ diff --git a/include/linux/printk.h b/include/linux/printk.h index cf7d666ab1f8..8c81806c2e99 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -169,8 +169,6 @@ extern void __printk_safe_exit(void); #define printk_deferred_enter __printk_safe_enter #define printk_deferred_exit __printk_safe_exit -extern bool pr_flush(int timeout_ms, bool reset_on_progress); - /* * Please don't use printk_ratelimit(), because it shares ratelimiting state * with all other unrelated printk_ratelimit() callsites. Instead use @@ -221,11 +219,6 @@ static inline void printk_deferred_exit(void) { } -static inline bool pr_flush(int timeout_ms, bool reset_on_progress) -{ - return true; -} - static inline int printk_ratelimit(void) { return 0; diff --git a/include/linux/psi.h b/include/linux/psi.h index dd74411ac21d..b029a847def1 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -7,6 +7,7 @@ #include <linux/sched.h> #include <linux/poll.h> #include <linux/cgroup-defs.h> +#include <linux/cgroup.h> struct seq_file; struct css_set; @@ -18,10 +19,6 @@ extern struct psi_group psi_system; void psi_init(void); -void psi_task_change(struct task_struct *task, int clear, int set); -void psi_task_switch(struct task_struct *prev, struct task_struct *next, - bool sleep); - void psi_memstall_enter(unsigned long *flags); void psi_memstall_leave(unsigned long *flags); @@ -34,9 +31,15 @@ __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file, poll_table *wait); #ifdef CONFIG_CGROUPS +static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) +{ + return cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi; +} + int psi_cgroup_alloc(struct cgroup *cgrp); void psi_cgroup_free(struct cgroup *cgrp); void cgroup_move_task(struct task_struct *p, struct css_set *to); +void psi_cgroup_restart(struct psi_group *group); #endif #else /* CONFIG_PSI */ @@ -58,6 +61,7 @@ static inline void cgroup_move_task(struct task_struct *p, struct css_set *to) { rcu_assign_pointer(p->cgroups, to); } +static inline void psi_cgroup_restart(struct psi_group *group) {} #endif #endif /* CONFIG_PSI */ diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index c7fe7c089718..6e4372735068 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -16,13 +16,6 @@ enum psi_task_count { NR_MEMSTALL, NR_RUNNING, /* - * This can't have values other than 0 or 1 and could be - * implemented as a bit flag. But for now we still have room - * in the first cacheline of psi_group_cpu, and this way we - * don't have to special case any state tracking for it. - */ - NR_ONCPU, - /* * For IO and CPU stalls the presence of running/oncpu tasks * in the domain means a partial rather than a full stall. * For memory it's not so simple because of page reclaimers: @@ -32,22 +25,27 @@ enum psi_task_count { * threads and memstall ones. */ NR_MEMSTALL_RUNNING, - NR_PSI_TASK_COUNTS = 5, + NR_PSI_TASK_COUNTS = 4, }; /* Task state bitmasks */ #define TSK_IOWAIT (1 << NR_IOWAIT) #define TSK_MEMSTALL (1 << NR_MEMSTALL) #define TSK_RUNNING (1 << NR_RUNNING) -#define TSK_ONCPU (1 << NR_ONCPU) #define TSK_MEMSTALL_RUNNING (1 << NR_MEMSTALL_RUNNING) +/* Only one task can be scheduled, no corresponding task count */ +#define TSK_ONCPU (1 << NR_PSI_TASK_COUNTS) + /* Resources that workloads could be stalled on */ enum psi_res { PSI_IO, PSI_MEM, PSI_CPU, - NR_PSI_RESOURCES = 3, +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + PSI_IRQ, +#endif + NR_PSI_RESOURCES, }; /* @@ -63,11 +61,17 @@ enum psi_states { PSI_MEM_FULL, PSI_CPU_SOME, PSI_CPU_FULL, +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + PSI_IRQ_FULL, +#endif /* Only per-CPU, to weigh the CPU in the global average: */ PSI_NONIDLE, - NR_PSI_STATES = 7, + NR_PSI_STATES, }; +/* Use one bit in the state mask to track TSK_ONCPU */ +#define PSI_ONCPU (1 << NR_PSI_STATES) + enum psi_aggregators { PSI_AVGS = 0, PSI_POLL, @@ -147,6 +151,9 @@ struct psi_trigger { }; struct psi_group { + struct psi_group *parent; + bool enabled; + /* Protects data used by the aggregator */ struct mutex avgs_lock; @@ -188,6 +195,8 @@ struct psi_group { #else /* CONFIG_PSI */ +#define NR_PSI_RESOURCES 0 + struct psi_group { }; #endif /* CONFIG_PSI */ diff --git a/include/linux/random.h b/include/linux/random.h index 3fec206487f6..147a5e0d0b8e 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -38,12 +38,10 @@ static inline int unregister_random_vmfork_notifier(struct notifier_block *nb) { #endif void get_random_bytes(void *buf, size_t len); +u8 get_random_u8(void); +u16 get_random_u16(void); u32 get_random_u32(void); u64 get_random_u64(void); -static inline unsigned int get_random_int(void) -{ - return get_random_u32(); -} static inline unsigned long get_random_long(void) { #if BITS_PER_LONG == 64 @@ -72,7 +70,8 @@ static inline unsigned long get_random_canary(void) return get_random_long() & CANARY_MASK; } -int __init random_init(const char *command_line); +void __init random_init_early(const char *command_line); +void __init random_init(void); bool rng_is_initialized(void); int wait_for_random_bytes(void); @@ -93,9 +92,10 @@ static inline int get_random_bytes_wait(void *buf, size_t nbytes) *out = get_random_ ## name(); \ return 0; \ } +declare_get_random_var_wait(u8, u8) +declare_get_random_var_wait(u16, u16) declare_get_random_var_wait(u32, u32) declare_get_random_var_wait(u64, u32) -declare_get_random_var_wait(int, unsigned int) declare_get_random_var_wait(long, unsigned long) #undef declare_get_random_var diff --git a/include/linux/reboot.h b/include/linux/reboot.h index e5d9ef886179..2b6bb593be5b 100644 --- a/include/linux/reboot.h +++ b/include/linux/reboot.h @@ -106,6 +106,14 @@ enum sys_off_mode { SYS_OFF_MODE_POWER_OFF, /** + * @SYS_OFF_MODE_RESTART_PREPARE: + * + * Handlers prepare system to be restarted. Handlers are + * allowed to sleep. + */ + SYS_OFF_MODE_RESTART_PREPARE, + + /** * @SYS_OFF_MODE_RESTART: * * Handlers restart system. Handlers are disallowed to sleep. diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index dac53fd3afea..2504df9a0453 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -101,7 +101,7 @@ __ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *k int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full); __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, struct file *filp, poll_table *poll_table); - +void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu); #define RING_BUFFER_ALL_CPUS -1 diff --git a/include/linux/rmap.h b/include/linux/rmap.h index b89b4b86951f..bd3504d11b15 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -166,7 +166,7 @@ static inline void anon_vma_merge(struct vm_area_struct *vma, unlink_anon_vmas(next); } -struct anon_vma *page_get_anon_vma(struct page *page); +struct anon_vma *folio_get_anon_vma(struct folio *folio); /* RMAP flags, currently only relevant for some anon rmap operations. */ typedef int __bitwise rmap_t; @@ -270,7 +270,7 @@ dup: * @page: the exclusive anonymous page to try marking possibly shared * * The caller needs to hold the PT lock and has to have the page table entry - * cleared/invalidated+flushed, to properly sync against GUP-fast. + * cleared/invalidated. * * This is similar to page_try_dup_anon_rmap(), however, not used during fork() * to duplicate a mapping, but instead to prepare for KSM or temporarily @@ -286,12 +286,68 @@ static inline int page_try_share_anon_rmap(struct page *page) { VM_BUG_ON_PAGE(!PageAnon(page) || !PageAnonExclusive(page), page); - /* See page_try_dup_anon_rmap(). */ - if (likely(!is_device_private_page(page) && - unlikely(page_maybe_dma_pinned(page)))) - return -EBUSY; + /* device private pages cannot get pinned via GUP. */ + if (unlikely(is_device_private_page(page))) { + ClearPageAnonExclusive(page); + return 0; + } + + /* + * We have to make sure that when we clear PageAnonExclusive, that + * the page is not pinned and that concurrent GUP-fast won't succeed in + * concurrently pinning the page. + * + * Conceptually, PageAnonExclusive clearing consists of: + * (A1) Clear PTE + * (A2) Check if the page is pinned; back off if so. + * (A3) Clear PageAnonExclusive + * (A4) Restore PTE (optional, but certainly not writable) + * + * When clearing PageAnonExclusive, we cannot possibly map the page + * writable again, because anon pages that may be shared must never + * be writable. So in any case, if the PTE was writable it cannot + * be writable anymore afterwards and there would be a PTE change. Only + * if the PTE wasn't writable, there might not be a PTE change. + * + * Conceptually, GUP-fast pinning of an anon page consists of: + * (B1) Read the PTE + * (B2) FOLL_WRITE: check if the PTE is not writable; back off if so. + * (B3) Pin the mapped page + * (B4) Check if the PTE changed by re-reading it; back off if so. + * (B5) If the original PTE is not writable, check if + * PageAnonExclusive is not set; back off if so. + * + * If the PTE was writable, we only have to make sure that GUP-fast + * observes a PTE change and properly backs off. + * + * If the PTE was not writable, we have to make sure that GUP-fast either + * detects a (temporary) PTE change or that PageAnonExclusive is cleared + * and properly backs off. + * + * Consequently, when clearing PageAnonExclusive(), we have to make + * sure that (A1), (A2)/(A3) and (A4) happen in the right memory + * order. In GUP-fast pinning code, we have to make sure that (B3),(B4) + * and (B5) happen in the right memory order. + * + * We assume that there might not be a memory barrier after + * clearing/invalidating the PTE (A1) and before restoring the PTE (A4), + * so we use explicit ones here. + */ + /* Paired with the memory barrier in try_grab_folio(). */ + if (IS_ENABLED(CONFIG_HAVE_FAST_GUP)) + smp_mb(); + + if (unlikely(page_maybe_dma_pinned(page))) + return -EBUSY; ClearPageAnonExclusive(page); + + /* + * This is conceptually a smp_wmb() paired with the smp_rmb() in + * gup_must_unshare(). + */ + if (IS_ENABLED(CONFIG_HAVE_FAST_GUP)) + smp_mb__after_atomic(); return 0; } @@ -405,13 +461,8 @@ struct rmap_walk_control { void rmap_walk(struct folio *folio, struct rmap_walk_control *rwc); void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc); - -/* - * Called by memory-failure.c to kill processes. - */ struct anon_vma *folio_lock_anon_vma_read(struct folio *folio, struct rmap_walk_control *rwc); -void page_unlock_anon_vma_read(struct anon_vma *anon_vma); #else /* !CONFIG_MMU */ diff --git a/include/linux/rwlock.h b/include/linux/rwlock.h index 8f416c5e929e..c0ef596f340b 100644 --- a/include/linux/rwlock.h +++ b/include/linux/rwlock.h @@ -1,7 +1,7 @@ #ifndef __LINUX_RWLOCK_H #define __LINUX_RWLOCK_H -#ifndef __LINUX_SPINLOCK_H +#ifndef __LINUX_INSIDE_SPINLOCK_H # error "please don't include this file directly" #endif diff --git a/include/linux/sched.h b/include/linux/sched.h index 8d82d6d32670..ffb6eb55cd13 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -14,6 +14,7 @@ #include <linux/pid.h> #include <linux/sem.h> #include <linux/shm.h> +#include <linux/kmsan_types.h> #include <linux/mutex.h> #include <linux/plist.h> #include <linux/hrtimer.h> @@ -81,25 +82,34 @@ struct task_group; */ /* Used in tsk->state: */ -#define TASK_RUNNING 0x0000 -#define TASK_INTERRUPTIBLE 0x0001 -#define TASK_UNINTERRUPTIBLE 0x0002 -#define __TASK_STOPPED 0x0004 -#define __TASK_TRACED 0x0008 +#define TASK_RUNNING 0x00000000 +#define TASK_INTERRUPTIBLE 0x00000001 +#define TASK_UNINTERRUPTIBLE 0x00000002 +#define __TASK_STOPPED 0x00000004 +#define __TASK_TRACED 0x00000008 /* Used in tsk->exit_state: */ -#define EXIT_DEAD 0x0010 -#define EXIT_ZOMBIE 0x0020 +#define EXIT_DEAD 0x00000010 +#define EXIT_ZOMBIE 0x00000020 #define EXIT_TRACE (EXIT_ZOMBIE | EXIT_DEAD) /* Used in tsk->state again: */ -#define TASK_PARKED 0x0040 -#define TASK_DEAD 0x0080 -#define TASK_WAKEKILL 0x0100 -#define TASK_WAKING 0x0200 -#define TASK_NOLOAD 0x0400 -#define TASK_NEW 0x0800 -/* RT specific auxilliary flag to mark RT lock waiters */ -#define TASK_RTLOCK_WAIT 0x1000 -#define TASK_STATE_MAX 0x2000 +#define TASK_PARKED 0x00000040 +#define TASK_DEAD 0x00000080 +#define TASK_WAKEKILL 0x00000100 +#define TASK_WAKING 0x00000200 +#define TASK_NOLOAD 0x00000400 +#define TASK_NEW 0x00000800 +#define TASK_RTLOCK_WAIT 0x00001000 +#define TASK_FREEZABLE 0x00002000 +#define __TASK_FREEZABLE_UNSAFE (0x00004000 * IS_ENABLED(CONFIG_LOCKDEP)) +#define TASK_FROZEN 0x00008000 +#define TASK_STATE_MAX 0x00010000 + +#define TASK_ANY (TASK_STATE_MAX-1) + +/* + * DO NOT ADD ANY NEW USERS ! + */ +#define TASK_FREEZABLE_UNSAFE (TASK_FREEZABLE | __TASK_FREEZABLE_UNSAFE) /* Convenience macros for the sake of set_current_state: */ #define TASK_KILLABLE (TASK_WAKEKILL | TASK_UNINTERRUPTIBLE) @@ -860,9 +870,6 @@ struct task_struct { struct mm_struct *mm; struct mm_struct *active_mm; - /* Per-thread vma caching: */ - struct vmacache vmacache; - #ifdef SPLIT_RSS_COUNTING struct task_rss_stat rss_stat; #endif @@ -914,6 +921,10 @@ struct task_struct { #ifdef CONFIG_MEMCG unsigned in_user_fault:1; #endif +#ifdef CONFIG_LRU_GEN + /* whether the LRU algorithm may apply to this access */ + unsigned in_lru_fault:1; +#endif #ifdef CONFIG_COMPAT_BRK unsigned brk_randomized:1; #endif @@ -944,6 +955,10 @@ struct task_struct { #ifdef CONFIG_CPU_SUP_INTEL unsigned reported_split_lock:1; #endif +#ifdef CONFIG_TASK_DELAY_ACCT + /* delay due to memory thrashing */ + unsigned in_thrashing:1; +#endif unsigned long atomic_flags; /* Flags requiring atomic access. */ @@ -1355,6 +1370,10 @@ struct task_struct { #endif #endif +#ifdef CONFIG_KMSAN + struct kmsan_ctx kmsan_ctx; +#endif + #if IS_ENABLED(CONFIG_KUNIT) struct kunit *kunit_test; #endif @@ -1381,9 +1400,6 @@ struct task_struct { #endif #ifdef CONFIG_TRACING - /* State flags for use by tracers: */ - unsigned long trace; - /* Bitmask and counter of trace recursion: */ unsigned long trace_recursion; #endif /* CONFIG_TRACING */ @@ -1713,8 +1729,9 @@ extern struct pid *cad_pid; #define PF_MEMALLOC 0x00000800 /* Allocating memory */ #define PF_NPROC_EXCEEDED 0x00001000 /* set_user() noticed that RLIMIT_NPROC was exceeded */ #define PF_USED_MATH 0x00002000 /* If unset the fpu must be initialized before use */ +#define PF__HOLE__00004000 0x00004000 #define PF_NOFREEZE 0x00008000 /* This thread should not be frozen */ -#define PF_FROZEN 0x00010000 /* Frozen for system suspend */ +#define PF__HOLE__00010000 0x00010000 #define PF_KSWAPD 0x00020000 /* I am kswapd */ #define PF_MEMALLOC_NOFS 0x00040000 /* All allocation requests will inherit GFP_NOFS */ #define PF_MEMALLOC_NOIO 0x00080000 /* All allocation requests will inherit GFP_NOIO */ @@ -1722,10 +1739,14 @@ extern struct pid *cad_pid; * I am cleaning dirty pages from some other bdi. */ #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* Randomize virtual address space */ +#define PF__HOLE__00800000 0x00800000 +#define PF__HOLE__01000000 0x01000000 +#define PF__HOLE__02000000 0x02000000 #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_mask */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MEMALLOC_PIN 0x10000000 /* Allocation context constrained to zones which allow long term pinning. */ -#define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezable */ +#define PF__HOLE__20000000 0x20000000 +#define PF__HOLE__40000000 0x40000000 #define PF_SUSPEND_TASK 0x80000000 /* This thread called freeze_processes() and should not be frozen */ /* diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index 4d0a5be28b70..8270ad7ae14c 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -71,9 +71,8 @@ static inline int get_dumpable(struct mm_struct *mm) #define MMF_UNSTABLE 22 /* mm is unstable for copy_from_user */ #define MMF_HUGE_ZERO_PAGE 23 /* mm has ever used the global huge zero page */ #define MMF_DISABLE_THP 24 /* disable THP for all VMAs */ -#define MMF_OOM_VICTIM 25 /* mm is the oom victim */ -#define MMF_OOM_REAP_QUEUED 26 /* mm was queued for oom_reaper */ -#define MMF_MULTIPROCESS 27 /* mm is shared between processes */ +#define MMF_OOM_REAP_QUEUED 25 /* mm was queued for oom_reaper */ +#define MMF_MULTIPROCESS 26 /* mm is shared between processes */ /* * MMF_HAS_PINNED: Whether this mm has pinned any pages. This can be either * replaced in the future by mm.pinned_vm when it becomes stable, or grow into @@ -81,7 +80,7 @@ static inline int get_dumpable(struct mm_struct *mm) * pinned pages were unpinned later on, we'll still keep this bit set for the * lifecycle of this mm, just for simplicity. */ -#define MMF_HAS_PINNED 28 /* FOLL_PIN has run, never cleared */ +#define MMF_HAS_PINNED 27 /* FOLL_PIN has run, never cleared */ #define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP) #define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index e650946816d0..303ee7dd0c7e 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -27,6 +27,7 @@ enum sched_tunable_scaling { #ifdef CONFIG_NUMA_BALANCING extern int sysctl_numa_balancing_mode; +extern unsigned int sysctl_numa_balancing_promote_rate_limit; #else #define sysctl_numa_balancing_mode 0 #endif diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 81cab4b01edc..d6c48163c6de 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -127,6 +127,9 @@ static inline void put_task_struct_many(struct task_struct *t, int nr) void put_task_struct_rcu_user(struct task_struct *task); +/* Free all architecture-specific resources held by a thread. */ +void release_thread(struct task_struct *dead_task); + #ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT extern int arch_task_struct_size __read_mostly; #else diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index ff0b990de83d..d500ea967dc7 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -92,17 +92,19 @@ extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, extern void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end); int shmem_unuse(unsigned int type); -extern bool shmem_is_huge(struct vm_area_struct *vma, - struct inode *inode, pgoff_t index); -static inline bool shmem_huge_enabled(struct vm_area_struct *vma) +extern bool shmem_is_huge(struct vm_area_struct *vma, struct inode *inode, + pgoff_t index, bool shmem_huge_force); +static inline bool shmem_huge_enabled(struct vm_area_struct *vma, + bool shmem_huge_force) { - return shmem_is_huge(vma, file_inode(vma->vm_file), vma->vm_pgoff); + return shmem_is_huge(vma, file_inode(vma->vm_file), vma->vm_pgoff, + shmem_huge_force); } extern unsigned long shmem_swap_usage(struct vm_area_struct *vma); extern unsigned long shmem_partial_swap_usage(struct address_space *mapping, pgoff_t start, pgoff_t end); -/* Flag allocation requirements to shmem_getpage */ +/* Flag allocation requirements to shmem_get_folio */ enum sgp_type { SGP_READ, /* don't exceed i_size, don't allocate page */ SGP_NOALLOC, /* similar, but fail on hole or use fallocated page */ @@ -111,8 +113,8 @@ enum sgp_type { SGP_FALLOC, /* like SGP_WRITE, but make existing page Uptodate */ }; -extern int shmem_getpage(struct inode *inode, pgoff_t index, - struct page **pagep, enum sgp_type sgp); +int shmem_get_folio(struct inode *inode, pgoff_t index, struct folio **foliop, + enum sgp_type sgp); static inline struct page *shmem_read_mapping_page( struct address_space *mapping, pgoff_t index) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9fcf534f2d92..7be5bb4c94b6 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -803,6 +803,7 @@ typedef unsigned char *sk_buff_data_t; * @csum_level: indicates the number of consecutive checksums found in * the packet minus one that have been verified as * CHECKSUM_UNNECESSARY (max 3) + * @scm_io_uring: SKB holds io_uring registered files * @dst_pending_confirm: need to confirm neighbour * @decrypted: Decrypted SKB * @slow_gro: state present at GRO time, slower prepare step required @@ -982,6 +983,7 @@ struct sk_buff { #endif __u8 slow_gro:1; __u8 csum_not_inet:1; + __u8 scm_io_uring:1; #ifdef CONFIG_NET_SCHED __u16 tc_index; /* traffic control index */ diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 48f4b645193b..70d6cb94e580 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -376,7 +376,7 @@ static inline void sk_psock_report_error(struct sk_psock *psock, int err) } struct sk_psock *sk_psock_init(struct sock *sk, int node); -void sk_psock_stop(struct sk_psock *psock, bool wait); +void sk_psock_stop(struct sk_psock *psock); #if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock); diff --git a/include/linux/slab.h b/include/linux/slab.h index 0fefdf528e0d..45efc6c553b8 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -29,6 +29,8 @@ #define SLAB_RED_ZONE ((slab_flags_t __force)0x00000400U) /* DEBUG: Poison objects */ #define SLAB_POISON ((slab_flags_t __force)0x00000800U) +/* Indicate a kmalloc slab */ +#define SLAB_KMALLOC ((slab_flags_t __force)0x00001000U) /* Align objs on cache lines */ #define SLAB_HWCACHE_ALIGN ((slab_flags_t __force)0x00002000U) /* Use GFP_DMA memory */ @@ -106,7 +108,7 @@ # define SLAB_ACCOUNT 0 #endif -#ifdef CONFIG_KASAN +#ifdef CONFIG_KASAN_GENERIC #define SLAB_KASAN ((slab_flags_t __force)0x08000000U) #else #define SLAB_KASAN 0 @@ -119,6 +121,12 @@ */ #define SLAB_NO_USER_FLAGS ((slab_flags_t __force)0x10000000U) +#ifdef CONFIG_KFENCE +#define SLAB_SKIP_KFENCE ((slab_flags_t __force)0x20000000U) +#else +#define SLAB_SKIP_KFENCE 0 +#endif + /* The following flags affect the page allocator grouping pages by mobility */ /* Objects are reclaimable */ #define SLAB_RECLAIM_ACCOUNT ((slab_flags_t __force)0x00020000U) @@ -184,11 +192,25 @@ int kmem_cache_shrink(struct kmem_cache *s); /* * Common kmalloc functions provided by all allocators */ -void * __must_check krealloc(const void *objp, size_t new_size, gfp_t flags) __alloc_size(2); +void * __must_check krealloc(const void *objp, size_t new_size, gfp_t flags) __realloc_size(2); void kfree(const void *objp); void kfree_sensitive(const void *objp); size_t __ksize(const void *objp); + +/** + * ksize - Report actual allocation size of associated object + * + * @objp: Pointer returned from a prior kmalloc()-family allocation. + * + * This should not be used for writing beyond the originally requested + * allocation size. Either use krealloc() or round up the allocation size + * with kmalloc_size_roundup() prior to allocation. If this is used to + * access beyond the originally requested allocation size, UBSAN_BOUNDS + * and/or FORTIFY_SOURCE may trip, since they only know about the + * originally allocated size via the __alloc_size attribute. + */ size_t ksize(const void *objp); + #ifdef CONFIG_PRINTK bool kmem_valid_obj(void *object); void kmem_dump_obj(void *object); @@ -243,27 +265,17 @@ static inline unsigned int arch_slab_minalign(void) #ifdef CONFIG_SLAB /* - * The largest kmalloc size supported by the SLAB allocators is - * 32 megabyte (2^25) or the maximum allocatable page order if that is - * less than 32 MB. - * - * WARNING: Its not easy to increase this value since the allocators have - * to do various tricks to work around compiler limitations in order to - * ensure proper constant folding. + * SLAB and SLUB directly allocates requests fitting in to an order-1 page + * (PAGE_SIZE*2). Larger requests are passed to the page allocator. */ -#define KMALLOC_SHIFT_HIGH ((MAX_ORDER + PAGE_SHIFT - 1) <= 25 ? \ - (MAX_ORDER + PAGE_SHIFT - 1) : 25) -#define KMALLOC_SHIFT_MAX KMALLOC_SHIFT_HIGH +#define KMALLOC_SHIFT_HIGH (PAGE_SHIFT + 1) +#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT - 1) #ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 5 #endif #endif #ifdef CONFIG_SLUB -/* - * SLUB directly allocates requests fitting in to an order-1 page - * (PAGE_SIZE*2). Larger requests are passed to the page allocator. - */ #define KMALLOC_SHIFT_HIGH (PAGE_SHIFT + 1) #define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT - 1) #ifndef KMALLOC_SHIFT_LOW @@ -415,10 +427,6 @@ static __always_inline unsigned int __kmalloc_index(size_t size, if (size <= 512 * 1024) return 19; if (size <= 1024 * 1024) return 20; if (size <= 2 * 1024 * 1024) return 21; - if (size <= 4 * 1024 * 1024) return 22; - if (size <= 8 * 1024 * 1024) return 23; - if (size <= 16 * 1024 * 1024) return 24; - if (size <= 32 * 1024 * 1024) return 25; if (!IS_ENABLED(CONFIG_PROFILE_ALL_BRANCHES) && size_is_constant) BUILD_BUG_ON_MSG(1, "unexpected size in kmalloc_index()"); @@ -428,6 +436,7 @@ static __always_inline unsigned int __kmalloc_index(size_t size, /* Will never be reached. Needed because the compiler may complain */ return -1; } +static_assert(PAGE_SHIFT <= 20); #define kmalloc_index(s) __kmalloc_index(s, true) #endif /* !CONFIG_SLOB */ @@ -456,78 +465,22 @@ static __always_inline void kfree_bulk(size_t size, void **p) kmem_cache_free_bulk(NULL, size, p); } -#ifdef CONFIG_NUMA void *__kmalloc_node(size_t size, gfp_t flags, int node) __assume_kmalloc_alignment __alloc_size(1); void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t flags, int node) __assume_slab_alignment __malloc; -#else -static __always_inline __alloc_size(1) void *__kmalloc_node(size_t size, gfp_t flags, int node) -{ - return __kmalloc(size, flags); -} -static __always_inline void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t flags, int node) -{ - return kmem_cache_alloc(s, flags); -} -#endif - -#ifdef CONFIG_TRACING -extern void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t flags, size_t size) - __assume_slab_alignment __alloc_size(3); - -#ifdef CONFIG_NUMA -extern void *kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, - int node, size_t size) __assume_slab_alignment - __alloc_size(4); -#else -static __always_inline __alloc_size(4) void *kmem_cache_alloc_node_trace(struct kmem_cache *s, - gfp_t gfpflags, int node, size_t size) -{ - return kmem_cache_alloc_trace(s, gfpflags, size); -} -#endif /* CONFIG_NUMA */ - -#else /* CONFIG_TRACING */ -static __always_inline __alloc_size(3) void *kmem_cache_alloc_trace(struct kmem_cache *s, - gfp_t flags, size_t size) -{ - void *ret = kmem_cache_alloc(s, flags); +void *kmalloc_trace(struct kmem_cache *s, gfp_t flags, size_t size) + __assume_kmalloc_alignment __alloc_size(3); - ret = kasan_kmalloc(s, ret, size, flags); - return ret; -} - -static __always_inline void *kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, - int node, size_t size) -{ - void *ret = kmem_cache_alloc_node(s, gfpflags, node); - - ret = kasan_kmalloc(s, ret, size, gfpflags); - return ret; -} -#endif /* CONFIG_TRACING */ +void *kmalloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, + int node, size_t size) __assume_kmalloc_alignment + __alloc_size(4); +void *kmalloc_large(size_t size, gfp_t flags) __assume_page_alignment + __alloc_size(1); -extern void *kmalloc_order(size_t size, gfp_t flags, unsigned int order) __assume_page_alignment - __alloc_size(1); - -#ifdef CONFIG_TRACING -extern void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) - __assume_page_alignment __alloc_size(1); -#else -static __always_inline __alloc_size(1) void *kmalloc_order_trace(size_t size, gfp_t flags, - unsigned int order) -{ - return kmalloc_order(size, flags, order); -} -#endif - -static __always_inline __alloc_size(1) void *kmalloc_large(size_t size, gfp_t flags) -{ - unsigned int order = get_order(size); - return kmalloc_order_trace(size, flags, order); -} +void *kmalloc_large_node(size_t size, gfp_t flags, int node) __assume_page_alignment + __alloc_size(1); /** * kmalloc - allocate memory @@ -597,7 +550,7 @@ static __always_inline __alloc_size(1) void *kmalloc(size_t size, gfp_t flags) if (!index) return ZERO_SIZE_PTR; - return kmem_cache_alloc_trace( + return kmalloc_trace( kmalloc_caches[kmalloc_type(flags)][index], flags, size); #endif @@ -605,23 +558,35 @@ static __always_inline __alloc_size(1) void *kmalloc(size_t size, gfp_t flags) return __kmalloc(size, flags); } +#ifndef CONFIG_SLOB static __always_inline __alloc_size(1) void *kmalloc_node(size_t size, gfp_t flags, int node) { -#ifndef CONFIG_SLOB - if (__builtin_constant_p(size) && - size <= KMALLOC_MAX_CACHE_SIZE) { - unsigned int i = kmalloc_index(size); + if (__builtin_constant_p(size)) { + unsigned int index; + + if (size > KMALLOC_MAX_CACHE_SIZE) + return kmalloc_large_node(size, flags, node); + + index = kmalloc_index(size); - if (!i) + if (!index) return ZERO_SIZE_PTR; - return kmem_cache_alloc_node_trace( - kmalloc_caches[kmalloc_type(flags)][i], - flags, node, size); + return kmalloc_node_trace( + kmalloc_caches[kmalloc_type(flags)][index], + flags, node, size); } -#endif return __kmalloc_node(size, flags, node); } +#else +static __always_inline __alloc_size(1) void *kmalloc_node(size_t size, gfp_t flags, int node) +{ + if (__builtin_constant_p(size) && size > KMALLOC_MAX_CACHE_SIZE) + return kmalloc_large_node(size, flags, node); + + return __kmalloc_node(size, flags, node); +} +#endif /** * kmalloc_array - allocate memory for an array. @@ -647,10 +612,10 @@ static inline __alloc_size(1, 2) void *kmalloc_array(size_t n, size_t size, gfp_ * @new_size: new size of a single member of the array * @flags: the type of memory to allocate (see kmalloc) */ -static inline __alloc_size(2, 3) void * __must_check krealloc_array(void *p, - size_t new_n, - size_t new_size, - gfp_t flags) +static inline __realloc_size(2, 3) void * __must_check krealloc_array(void *p, + size_t new_n, + size_t new_size, + gfp_t flags) { size_t bytes; @@ -671,6 +636,12 @@ static inline __alloc_size(1, 2) void *kcalloc(size_t n, size_t size, gfp_t flag return kmalloc_array(n, size, flags | __GFP_ZERO); } +void *__kmalloc_node_track_caller(size_t size, gfp_t flags, int node, + unsigned long caller) __alloc_size(1); +#define kmalloc_node_track_caller(size, flags, node) \ + __kmalloc_node_track_caller(size, flags, node, \ + _RET_IP_) + /* * kmalloc_track_caller is a special version of kmalloc that records the * calling function of the routine calling it for slab leak tracking instead @@ -679,9 +650,9 @@ static inline __alloc_size(1, 2) void *kcalloc(size_t n, size_t size, gfp_t flag * allocator where we care about the real place the memory allocation * request comes from. */ -extern void *__kmalloc_track_caller(size_t size, gfp_t flags, unsigned long caller); #define kmalloc_track_caller(size, flags) \ - __kmalloc_track_caller(size, flags, _RET_IP_) + __kmalloc_node_track_caller(size, flags, \ + NUMA_NO_NODE, _RET_IP_) static inline __alloc_size(1, 2) void *kmalloc_array_node(size_t n, size_t size, gfp_t flags, int node) @@ -700,21 +671,6 @@ static inline __alloc_size(1, 2) void *kcalloc_node(size_t n, size_t size, gfp_t return kmalloc_array_node(n, size, flags | __GFP_ZERO, node); } - -#ifdef CONFIG_NUMA -extern void *__kmalloc_node_track_caller(size_t size, gfp_t flags, int node, - unsigned long caller) __alloc_size(1); -#define kmalloc_node_track_caller(size, flags, node) \ - __kmalloc_node_track_caller(size, flags, node, \ - _RET_IP_) - -#else /* CONFIG_NUMA */ - -#define kmalloc_node_track_caller(size, flags, node) \ - kmalloc_track_caller(size, flags) - -#endif /* CONFIG_NUMA */ - /* * Shortcuts */ @@ -774,11 +730,28 @@ static inline __alloc_size(1, 2) void *kvcalloc(size_t n, size_t size, gfp_t fla } extern void *kvrealloc(const void *p, size_t oldsize, size_t newsize, gfp_t flags) - __alloc_size(3); + __realloc_size(3); extern void kvfree(const void *addr); extern void kvfree_sensitive(const void *addr, size_t len); unsigned int kmem_cache_size(struct kmem_cache *s); + +/** + * kmalloc_size_roundup - Report allocation bucket size for the given size + * + * @size: Number of bytes to round up from. + * + * This returns the number of bytes that would be available in a kmalloc() + * allocation of @size bytes. For example, a 126 byte request would be + * rounded up to the next sized kmalloc bucket, 128 bytes. (This is strictly + * for the general-purpose kmalloc()-based allocations, and is not for the + * pre-sized kmem_cache_alloc()-based allocations.) + * + * Use this to kmalloc() the full bucket size ahead of time instead of using + * ksize() to query the size after an allocation. + */ +size_t kmalloc_size_roundup(size_t size); + void __init kmem_cache_init_late(void); #if defined(CONFIG_SMP) && defined(CONFIG_SLAB) diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index e24c9aff6fed..f0ffad6a3365 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -33,7 +33,6 @@ struct kmem_cache { size_t colour; /* cache colouring range */ unsigned int colour_off; /* colour offset */ - struct kmem_cache *freelist_cache; unsigned int freelist_size; /* constructor func */ diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h index 2ba044d0d5e5..8e984d75f5b6 100644 --- a/include/linux/spi/spi-mem.h +++ b/include/linux/spi/spi-mem.h @@ -225,7 +225,7 @@ static inline void *spi_mem_get_drvdata(struct spi_mem *mem) /** * struct spi_controller_mem_ops - SPI memory operations * @adjust_op_size: shrink the data xfer of an operation to match controller's - * limitations (can be alignment of max RX/TX size + * limitations (can be alignment or max RX/TX size * limitations) * @supports_op: check if an operation is supported by the controller * @exec_op: execute a SPI memory operation diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 5c0c5174155d..1341f7d62da4 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_SPINLOCK_H #define __LINUX_SPINLOCK_H +#define __LINUX_INSIDE_SPINLOCK_H /* * include/linux/spinlock.h - generic spinlock/rwlock declarations @@ -492,4 +493,5 @@ int __alloc_bucket_spinlocks(spinlock_t **locks, unsigned int *lock_mask, void free_bucket_spinlocks(spinlock_t *locks); +#undef __LINUX_INSIDE_SPINLOCK_H #endif /* __LINUX_SPINLOCK_H */ diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h index 51fa0dab68c4..89eb6f4c659c 100644 --- a/include/linux/spinlock_api_smp.h +++ b/include/linux/spinlock_api_smp.h @@ -1,7 +1,7 @@ #ifndef __LINUX_SPINLOCK_API_SMP_H #define __LINUX_SPINLOCK_API_SMP_H -#ifndef __LINUX_SPINLOCK_H +#ifndef __LINUX_INSIDE_SPINLOCK_H # error "please don't include this file directly" #endif diff --git a/include/linux/spinlock_api_up.h b/include/linux/spinlock_api_up.h index b8ba00ccccde..819aeba1c87e 100644 --- a/include/linux/spinlock_api_up.h +++ b/include/linux/spinlock_api_up.h @@ -1,7 +1,7 @@ #ifndef __LINUX_SPINLOCK_API_UP_H #define __LINUX_SPINLOCK_API_UP_H -#ifndef __LINUX_SPINLOCK_H +#ifndef __LINUX_INSIDE_SPINLOCK_H # error "please don't include this file directly" #endif diff --git a/include/linux/spinlock_rt.h b/include/linux/spinlock_rt.h index 835aedaf68ac..61c49b16f69a 100644 --- a/include/linux/spinlock_rt.h +++ b/include/linux/spinlock_rt.h @@ -2,7 +2,7 @@ #ifndef __LINUX_SPINLOCK_RT_H #define __LINUX_SPINLOCK_RT_H -#ifndef __LINUX_SPINLOCK_H +#ifndef __LINUX_INSIDE_SPINLOCK_H #error Do not include directly. Use spinlock.h #endif diff --git a/include/linux/spinlock_up.h b/include/linux/spinlock_up.h index 16521074b6f7..c87204247592 100644 --- a/include/linux/spinlock_up.h +++ b/include/linux/spinlock_up.h @@ -1,7 +1,7 @@ #ifndef __LINUX_SPINLOCK_UP_H #define __LINUX_SPINLOCK_UP_H -#ifndef __LINUX_SPINLOCK_H +#ifndef __LINUX_INSIDE_SPINLOCK_H # error "please don't include this file directly" #endif diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index bc2797955de9..9ca7798d7a31 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -14,9 +14,15 @@ #include <linux/gfp.h> typedef u32 depot_stack_handle_t; +/* + * Number of bits in the handle that stack depot doesn't use. Users may store + * information in them. + */ +#define STACK_DEPOT_EXTRA_BITS 5 depot_stack_handle_t __stack_depot_save(unsigned long *entries, unsigned int nr_entries, + unsigned int extra_bits, gfp_t gfp_flags, bool can_alloc); /* @@ -59,6 +65,8 @@ depot_stack_handle_t stack_depot_save(unsigned long *entries, unsigned int stack_depot_fetch(depot_stack_handle_t handle, unsigned long **entries); +unsigned int stack_depot_get_extra_bits(depot_stack_handle_t handle); + int stack_depot_snprint(depot_stack_handle_t handle, char *buf, size_t size, int spaces); diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 75eea5ebb179..770ef2cb5775 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -246,6 +246,7 @@ void rpc_clnt_xprt_switch_remove_xprt(struct rpc_clnt *, struct rpc_xprt *); bool rpc_clnt_xprt_switch_has_addr(struct rpc_clnt *clnt, const struct sockaddr *sap); void rpc_clnt_xprt_set_online(struct rpc_clnt *clnt, struct rpc_xprt *xprt); +void rpc_clnt_disconnect(struct rpc_clnt *clnt); void rpc_cleanup_clids(void); static inline int rpc_reply_expected(struct rpc_task *task) diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index acc62647317c..b8ca3ecaf8d7 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -209,11 +209,17 @@ struct rpc_task *rpc_run_task(const struct rpc_task_setup *); struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req); 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); +void rpc_task_try_cancel(struct rpc_task *task, int error); void rpc_signal_task(struct rpc_task *); void rpc_exit_task(struct rpc_task *); void rpc_exit(struct rpc_task *, int); void rpc_release_calldata(const struct rpc_call_ops *, void *); void rpc_killall_tasks(struct rpc_clnt *); +unsigned long rpc_cancel_tasks(struct rpc_clnt *clnt, int error, + bool (*fnmatch)(const struct rpc_task *, + const void *), + const void *data); void rpc_execute(struct rpc_task *); void rpc_init_priority_wait_queue(struct rpc_wait_queue *, const char *); void rpc_init_wait_queue(struct rpc_wait_queue *, const char *); @@ -252,7 +258,7 @@ int rpc_malloc(struct rpc_task *); void rpc_free(struct rpc_task *); int rpciod_up(void); void rpciod_down(void); -int __rpc_wait_for_completion_task(struct rpc_task *task, wait_bit_action_f *); +int rpc_wait_for_completion_task(struct rpc_task *task); #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) struct net; void rpc_show_tasks(struct net *); @@ -264,11 +270,6 @@ extern struct workqueue_struct *xprtiod_workqueue; void rpc_prepare_task(struct rpc_task *task); gfp_t rpc_task_gfp_mask(void); -static inline int rpc_wait_for_completion_task(struct rpc_task *task) -{ - return __rpc_wait_for_completion_task(task, NULL); -} - #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) || IS_ENABLED(CONFIG_TRACEPOINTS) static inline const char * rpc_qname(const struct rpc_wait_queue *q) { diff --git a/include/linux/suspend.h b/include/linux/suspend.h index be7737262d8f..cfe19a028918 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -511,8 +511,8 @@ extern bool pm_save_wakeup_count(unsigned int count); extern void pm_wakep_autosleep_enabled(bool set); extern void pm_print_active_wakeup_sources(void); -extern void lock_system_sleep(void); -extern void unlock_system_sleep(void); +extern unsigned int lock_system_sleep(void); +extern void unlock_system_sleep(unsigned int); #else /* !CONFIG_PM_SLEEP */ @@ -535,8 +535,8 @@ static inline void pm_system_wakeup(void) {} static inline void pm_wakeup_clear(bool reset) {} static inline void pm_system_irq_wakeup(unsigned int irq_number) {} -static inline void lock_system_sleep(void) {} -static inline void unlock_system_sleep(void) {} +static inline unsigned int lock_system_sleep(void) { return 0; } +static inline void unlock_system_sleep(unsigned int flags) {} #endif /* !CONFIG_PM_SLEEP */ diff --git a/include/linux/swap.h b/include/linux/swap.h index 43150b9bbc5c..a18cf4b7c724 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -162,6 +162,10 @@ union swap_header { */ struct reclaim_state { unsigned long reclaimed_slab; +#ifdef CONFIG_LRU_GEN + /* per-thread mm walk data */ + struct lru_gen_mm_walk *mm_walk; +#endif }; #ifdef __KERNEL__ @@ -351,6 +355,11 @@ static inline swp_entry_t folio_swap_entry(struct folio *folio) return entry; } +static inline void folio_set_swap_entry(struct folio *folio, swp_entry_t entry) +{ + folio->private = (void *)entry.val; +} + /* linux/mm/workingset.c */ void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages); void *workingset_eviction(struct folio *folio, struct mem_cgroup *target_memcg); @@ -375,11 +384,11 @@ extern unsigned long totalreserve_pages; /* linux/mm/swap.c */ -extern void lru_note_cost(struct lruvec *lruvec, bool file, - unsigned int nr_pages); -extern void lru_note_cost_folio(struct folio *); -extern void folio_add_lru(struct folio *); -extern void lru_cache_add(struct page *); +void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages); +void lru_note_cost_folio(struct folio *); +void folio_add_lru(struct folio *); +void folio_add_lru_vma(struct folio *, struct vm_area_struct *); +void lru_cache_add(struct page *); void mark_page_accessed(struct page *); void folio_mark_accessed(struct folio *); @@ -481,7 +490,8 @@ static inline long get_nr_swap_pages(void) extern void si_swapinfo(struct sysinfo *); swp_entry_t folio_alloc_swap(struct folio *folio); -extern void put_swap_page(struct page *page, swp_entry_t entry); +bool folio_free_swap(struct folio *folio); +void put_swap_folio(struct folio *folio, swp_entry_t entry); extern swp_entry_t get_swap_page_of_type(int); extern int get_swap_pages(int n, swp_entry_t swp_entries[], int entry_size); extern int add_swap_count_continuation(swp_entry_t, gfp_t); @@ -500,7 +510,6 @@ extern int __swp_swapcount(swp_entry_t entry); extern int swp_swapcount(swp_entry_t entry); extern struct swap_info_struct *page_swap_info(struct page *); extern struct swap_info_struct *swp_swap_info(swp_entry_t entry); -extern int try_to_free_swap(struct page *); struct backing_dev_info; extern int init_swap_address_space(unsigned int type, unsigned long nr_pages); extern void exit_swap_address_space(unsigned int type); @@ -566,7 +575,7 @@ static inline void swap_free(swp_entry_t swp) { } -static inline void put_swap_page(struct page *page, swp_entry_t swp) +static inline void put_swap_folio(struct folio *folio, swp_entry_t swp) { } @@ -585,11 +594,6 @@ static inline int swp_swapcount(swp_entry_t entry) return 0; } -static inline int try_to_free_swap(struct page *page) -{ - return 0; -} - static inline swp_entry_t folio_alloc_swap(struct folio *folio) { swp_entry_t entry; @@ -597,6 +601,11 @@ static inline swp_entry_t folio_alloc_swap(struct folio *folio) return entry; } +static inline bool folio_free_swap(struct folio *folio) +{ + return false; +} + static inline int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block) @@ -657,7 +666,7 @@ static inline void folio_throttle_swaprate(struct folio *folio, gfp_t gfp) cgroup_throttle_swaprate(&folio->page, gfp); } -#ifdef CONFIG_MEMCG_SWAP +#if defined(CONFIG_MEMCG) && defined(CONFIG_SWAP) void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry); int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry); static inline int mem_cgroup_try_charge_swap(struct folio *folio, @@ -677,7 +686,7 @@ static inline void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_p } extern long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg); -extern bool mem_cgroup_swap_full(struct page *page); +extern bool mem_cgroup_swap_full(struct folio *folio); #else static inline void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry) { @@ -699,7 +708,7 @@ static inline long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg) return get_nr_swap_pages(); } -static inline bool mem_cgroup_swap_full(struct page *page) +static inline bool mem_cgroup_swap_full(struct folio *folio) { return vm_swap_full(); } diff --git a/include/linux/swap_cgroup.h b/include/linux/swap_cgroup.h index a12dd1c3966c..ae73a87775b3 100644 --- a/include/linux/swap_cgroup.h +++ b/include/linux/swap_cgroup.h @@ -4,7 +4,7 @@ #include <linux/swap.h> -#ifdef CONFIG_MEMCG_SWAP +#if defined(CONFIG_MEMCG) && defined(CONFIG_SWAP) extern unsigned short swap_cgroup_cmpxchg(swp_entry_t ent, unsigned short old, unsigned short new); @@ -40,6 +40,6 @@ static inline void swap_cgroup_swapoff(int type) return; } -#endif /* CONFIG_MEMCG_SWAP */ +#endif #endif /* __LINUX_SWAP_CGROUP_H */ diff --git a/include/linux/swapfile.h b/include/linux/swapfile.h index 54078542134c..7ed529a77c5b 100644 --- a/include/linux/swapfile.h +++ b/include/linux/swapfile.h @@ -8,6 +8,11 @@ */ extern struct swap_info_struct *swap_info[]; extern unsigned long generic_max_swapfile_size(void); -extern unsigned long max_swapfile_size(void); +unsigned long arch_max_swapfile_size(void); + +/* Maximum swapfile size supported for the arch (not inclusive). */ +extern unsigned long swapfile_maximum_size; +/* Whether swap migration entry supports storing A/D bits for the arch */ +extern bool swap_migration_ad_supported; #endif /* _LINUX_SWAPFILE_H */ diff --git a/include/linux/swapops.h b/include/linux/swapops.h index a3d435bf9f97..86b95ccb81bb 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -8,6 +8,10 @@ #ifdef CONFIG_MMU +#ifdef CONFIG_SWAP +#include <linux/swapfile.h> +#endif /* CONFIG_SWAP */ + /* * swapcache pages are stored in the swapper_space radix tree. We want to * get good packing density in that tree, so the index should be dense in @@ -23,6 +27,45 @@ #define SWP_TYPE_SHIFT (BITS_PER_XA_VALUE - MAX_SWAPFILES_SHIFT) #define SWP_OFFSET_MASK ((1UL << SWP_TYPE_SHIFT) - 1) +/* + * Definitions only for PFN swap entries (see is_pfn_swap_entry()). To + * store PFN, we only need SWP_PFN_BITS bits. Each of the pfn swap entries + * can use the extra bits to store other information besides PFN. + */ +#ifdef MAX_PHYSMEM_BITS +#define SWP_PFN_BITS (MAX_PHYSMEM_BITS - PAGE_SHIFT) +#else /* MAX_PHYSMEM_BITS */ +#define SWP_PFN_BITS (BITS_PER_LONG - PAGE_SHIFT) +#endif /* MAX_PHYSMEM_BITS */ +#define SWP_PFN_MASK (BIT(SWP_PFN_BITS) - 1) + +/** + * Migration swap entry specific bitfield definitions. Layout: + * + * |----------+--------------------| + * | swp_type | swp_offset | + * |----------+--------+-+-+-------| + * | | resv |D|A| PFN | + * |----------+--------+-+-+-------| + * + * @SWP_MIG_YOUNG_BIT: Whether the page used to have young bit set (bit A) + * @SWP_MIG_DIRTY_BIT: Whether the page used to have dirty bit set (bit D) + * + * Note: A/D bits will be stored in migration entries iff there're enough + * free bits in arch specific swp offset. By default we'll ignore A/D bits + * when migrating a page. Please refer to migration_entry_supports_ad() + * for more information. If there're more bits besides PFN and A/D bits, + * they should be reserved and always be zeros. + */ +#define SWP_MIG_YOUNG_BIT (SWP_PFN_BITS) +#define SWP_MIG_DIRTY_BIT (SWP_PFN_BITS + 1) +#define SWP_MIG_TOTAL_BITS (SWP_PFN_BITS + 2) + +#define SWP_MIG_YOUNG BIT(SWP_MIG_YOUNG_BIT) +#define SWP_MIG_DIRTY BIT(SWP_MIG_DIRTY_BIT) + +static inline bool is_pfn_swap_entry(swp_entry_t entry); + /* Clear all flags but only keep swp_entry_t related information */ static inline pte_t pte_swp_clear_flags(pte_t pte) { @@ -64,6 +107,17 @@ static inline pgoff_t swp_offset(swp_entry_t entry) return entry.val & SWP_OFFSET_MASK; } +/* + * This should only be called upon a pfn swap entry to get the PFN stored + * in the swap entry. Please refers to is_pfn_swap_entry() for definition + * of pfn swap entry. + */ +static inline unsigned long swp_offset_pfn(swp_entry_t entry) +{ + VM_BUG_ON(!is_pfn_swap_entry(entry)); + return swp_offset(entry) & SWP_PFN_MASK; +} + /* check whether a pte points to a swap entry */ static inline int is_swap_pte(pte_t pte) { @@ -240,6 +294,52 @@ static inline swp_entry_t make_writable_migration_entry(pgoff_t offset) return swp_entry(SWP_MIGRATION_WRITE, offset); } +/* + * Returns whether the host has large enough swap offset field to support + * carrying over pgtable A/D bits for page migrations. The result is + * pretty much arch specific. + */ +static inline bool migration_entry_supports_ad(void) +{ +#ifdef CONFIG_SWAP + return swap_migration_ad_supported; +#else /* CONFIG_SWAP */ + return false; +#endif /* CONFIG_SWAP */ +} + +static inline swp_entry_t make_migration_entry_young(swp_entry_t entry) +{ + if (migration_entry_supports_ad()) + return swp_entry(swp_type(entry), + swp_offset(entry) | SWP_MIG_YOUNG); + return entry; +} + +static inline bool is_migration_entry_young(swp_entry_t entry) +{ + if (migration_entry_supports_ad()) + return swp_offset(entry) & SWP_MIG_YOUNG; + /* Keep the old behavior of aging page after migration */ + return false; +} + +static inline swp_entry_t make_migration_entry_dirty(swp_entry_t entry) +{ + if (migration_entry_supports_ad()) + return swp_entry(swp_type(entry), + swp_offset(entry) | SWP_MIG_DIRTY); + return entry; +} + +static inline bool is_migration_entry_dirty(swp_entry_t entry) +{ + if (migration_entry_supports_ad()) + return swp_offset(entry) & SWP_MIG_DIRTY; + /* Keep the old behavior of clean page after migration */ + return false; +} + extern void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, spinlock_t *ptl); extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, @@ -247,8 +347,8 @@ extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, #ifdef CONFIG_HUGETLB_PAGE extern void __migration_entry_wait_huge(pte_t *ptep, spinlock_t *ptl); extern void migration_entry_wait_huge(struct vm_area_struct *vma, pte_t *pte); -#endif -#else +#endif /* CONFIG_HUGETLB_PAGE */ +#else /* CONFIG_MIGRATION */ static inline swp_entry_t make_readable_migration_entry(pgoff_t offset) { return swp_entry(0, 0); @@ -276,7 +376,7 @@ static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, #ifdef CONFIG_HUGETLB_PAGE static inline void __migration_entry_wait_huge(pte_t *ptep, spinlock_t *ptl) { } static inline void migration_entry_wait_huge(struct vm_area_struct *vma, pte_t *pte) { } -#endif +#endif /* CONFIG_HUGETLB_PAGE */ static inline int is_writable_migration_entry(swp_entry_t entry) { return 0; @@ -286,7 +386,26 @@ static inline int is_readable_migration_entry(swp_entry_t entry) return 0; } -#endif +static inline swp_entry_t make_migration_entry_young(swp_entry_t entry) +{ + return entry; +} + +static inline bool is_migration_entry_young(swp_entry_t entry) +{ + return false; +} + +static inline swp_entry_t make_migration_entry_dirty(swp_entry_t entry) +{ + return entry; +} + +static inline bool is_migration_entry_dirty(swp_entry_t entry) +{ + return false; +} +#endif /* CONFIG_MIGRATION */ typedef unsigned long pte_marker; @@ -369,7 +488,7 @@ static inline int pte_none_mostly(pte_t pte) static inline struct page *pfn_swap_entry_to_page(swp_entry_t entry) { - struct page *p = pfn_to_page(swp_offset(entry)); + struct page *p = pfn_to_page(swp_offset_pfn(entry)); /* * Any use of migration entries may only occur while the @@ -387,6 +506,9 @@ static inline struct page *pfn_swap_entry_to_page(swp_entry_t entry) */ static inline bool is_pfn_swap_entry(swp_entry_t entry) { + /* Make sure the swp offset can always store the needed fields */ + BUILD_BUG_ON(SWP_TYPE_SHIFT < SWP_PFN_BITS); + return is_migration_entry(entry) || is_device_private_entry(entry) || is_device_exclusive_entry(entry); } @@ -426,7 +548,7 @@ static inline int is_pmd_migration_entry(pmd_t pmd) { return is_swap_pmd(pmd) && is_migration_entry(pmd_to_swp_entry(pmd)); } -#else +#else /* CONFIG_ARCH_ENABLE_THP_MIGRATION */ static inline int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, struct page *page) { @@ -455,7 +577,7 @@ static inline int is_pmd_migration_entry(pmd_t pmd) { return 0; } -#endif +#endif /* CONFIG_ARCH_ENABLE_THP_MIGRATION */ #ifdef CONFIG_MEMORY_FAILURE @@ -475,27 +597,17 @@ static inline int is_hwpoison_entry(swp_entry_t entry) return swp_type(entry) == SWP_HWPOISON; } -static inline unsigned long hwpoison_entry_to_pfn(swp_entry_t entry) -{ - return swp_offset(entry); -} - static inline void num_poisoned_pages_inc(void) { atomic_long_inc(&num_poisoned_pages); } -static inline void num_poisoned_pages_dec(void) -{ - atomic_long_dec(&num_poisoned_pages); -} - static inline void num_poisoned_pages_sub(long i) { atomic_long_sub(i, &num_poisoned_pages); } -#else +#else /* CONFIG_MEMORY_FAILURE */ static inline swp_entry_t make_hwpoison_entry(struct page *page) { @@ -514,7 +626,7 @@ static inline void num_poisoned_pages_inc(void) static inline void num_poisoned_pages_sub(long i) { } -#endif +#endif /* CONFIG_MEMORY_FAILURE */ static inline int non_swap_entry(swp_entry_t entry) { diff --git a/include/linux/syslog.h b/include/linux/syslog.h index 86af908e2663..955f80e34d4f 100644 --- a/include/linux/syslog.h +++ b/include/linux/syslog.h @@ -8,6 +8,8 @@ #ifndef _LINUX_SYSLOG_H #define _LINUX_SYSLOG_H +#include <linux/wait.h> + /* Close the log. Currently a NOP. */ #define SYSLOG_ACTION_CLOSE 0 /* Open the log. Currently a NOP. */ @@ -35,5 +37,6 @@ #define SYSLOG_FROM_PROC 1 int do_syslog(int type, char __user *buf, int count, int source); +extern wait_queue_head_t log_wait; #endif /* _LINUX_SYSLOG_H */ diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 6f1ec4fb7ef8..9ecc128944a1 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -308,9 +308,6 @@ void devm_thermal_of_zone_unregister(struct device *dev, struct thermal_zone_dev void thermal_of_zone_unregister(struct thermal_zone_device *tz); -int thermal_zone_of_get_sensor_id(struct device_node *tz_np, - struct device_node *sensor_np, - u32 *id); #else static inline struct thermal_zone_device *thermal_of_zone_register(struct device_node *sensor, int id, void *data, @@ -334,13 +331,6 @@ static inline void devm_thermal_of_zone_unregister(struct device *dev, struct thermal_zone_device *tz) { } - -static inline int thermal_zone_of_get_sensor_id(struct device_node *tz_np, - struct device_node *sensor_np, - u32 *id) -{ - return -ENOENT; -} #endif #ifdef CONFIG_THERMAL diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 8401dec93c15..20749bd9db71 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -92,6 +92,7 @@ struct trace_iterator { unsigned int temp_size; char *fmt; /* modified format holder */ unsigned int fmt_size; + long wait_index; /* trace_seq for __print_flags() and __print_symbolic() etc. */ struct trace_seq tmp_seq; diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h index 6ad4e9032d53..46040d66334a 100644 --- a/include/linux/u64_stats_sync.h +++ b/include/linux/u64_stats_sync.h @@ -8,7 +8,7 @@ * * Key points : * - * - Use a seqcount on 32-bit SMP, only disable preemption for 32-bit UP. + * - Use a seqcount on 32-bit * - The whole thing is a no-op on 64-bit architectures. * * Usage constraints: @@ -20,7 +20,8 @@ * writer and also spin forever. * * 3) Write side must use the _irqsave() variant if other writers, or a reader, - * can be invoked from an IRQ context. + * can be invoked from an IRQ context. On 64bit systems this variant does not + * disable interrupts. * * 4) If reader fetches several counters, there is no guarantee the whole values * are consistent w.r.t. each other (remember point #2: seqcounts are not @@ -29,11 +30,6 @@ * 5) Readers are allowed to sleep or be preempted/interrupted: they perform * pure reads. * - * 6) Readers must use both u64_stats_fetch_{begin,retry}_irq() if the stats - * might be updated from a hardirq or softirq context (remember point #1: - * seqcounts are not used for UP kernels). 32-bit UP stat readers could read - * corrupted 64-bit values otherwise. - * * Usage : * * Stats producer (writer) should use following template granted it already got @@ -66,7 +62,7 @@ #include <linux/seqlock.h> struct u64_stats_sync { -#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) +#if BITS_PER_LONG == 32 seqcount_t seq; #endif }; @@ -98,7 +94,22 @@ static inline void u64_stats_inc(u64_stats_t *p) local64_inc(&p->v); } -#else +static inline void u64_stats_init(struct u64_stats_sync *syncp) { } +static inline void __u64_stats_update_begin(struct u64_stats_sync *syncp) { } +static inline void __u64_stats_update_end(struct u64_stats_sync *syncp) { } +static inline unsigned long __u64_stats_irqsave(void) { return 0; } +static inline void __u64_stats_irqrestore(unsigned long flags) { } +static inline unsigned int __u64_stats_fetch_begin(const struct u64_stats_sync *syncp) +{ + return 0; +} +static inline bool __u64_stats_fetch_retry(const struct u64_stats_sync *syncp, + unsigned int start) +{ + return false; +} + +#else /* 64 bit */ typedef struct { u64 v; @@ -123,123 +134,95 @@ static inline void u64_stats_inc(u64_stats_t *p) { p->v++; } -#endif -#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) -#define u64_stats_init(syncp) seqcount_init(&(syncp)->seq) -#else static inline void u64_stats_init(struct u64_stats_sync *syncp) { + seqcount_init(&syncp->seq); } -#endif -static inline void u64_stats_update_begin(struct u64_stats_sync *syncp) +static inline void __u64_stats_update_begin(struct u64_stats_sync *syncp) { -#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) - if (IS_ENABLED(CONFIG_PREEMPT_RT)) - preempt_disable(); + preempt_disable_nested(); write_seqcount_begin(&syncp->seq); -#endif } -static inline void u64_stats_update_end(struct u64_stats_sync *syncp) +static inline void __u64_stats_update_end(struct u64_stats_sync *syncp) { -#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) write_seqcount_end(&syncp->seq); - if (IS_ENABLED(CONFIG_PREEMPT_RT)) - preempt_enable(); -#endif + preempt_enable_nested(); } -static inline unsigned long -u64_stats_update_begin_irqsave(struct u64_stats_sync *syncp) +static inline unsigned long __u64_stats_irqsave(void) { - unsigned long flags = 0; + unsigned long flags; -#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) - if (IS_ENABLED(CONFIG_PREEMPT_RT)) - preempt_disable(); - else - local_irq_save(flags); - write_seqcount_begin(&syncp->seq); -#endif + local_irq_save(flags); return flags; } -static inline void -u64_stats_update_end_irqrestore(struct u64_stats_sync *syncp, - unsigned long flags) +static inline void __u64_stats_irqrestore(unsigned long flags) { -#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) - write_seqcount_end(&syncp->seq); - if (IS_ENABLED(CONFIG_PREEMPT_RT)) - preempt_enable(); - else - local_irq_restore(flags); -#endif + local_irq_restore(flags); } static inline unsigned int __u64_stats_fetch_begin(const struct u64_stats_sync *syncp) { -#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) return read_seqcount_begin(&syncp->seq); -#else - return 0; -#endif } -static inline unsigned int u64_stats_fetch_begin(const struct u64_stats_sync *syncp) +static inline bool __u64_stats_fetch_retry(const struct u64_stats_sync *syncp, + unsigned int start) { -#if BITS_PER_LONG == 32 && (!defined(CONFIG_SMP) && !defined(CONFIG_PREEMPT_RT)) - preempt_disable(); -#endif - return __u64_stats_fetch_begin(syncp); + return read_seqcount_retry(&syncp->seq, start); } +#endif /* !64 bit */ -static inline bool __u64_stats_fetch_retry(const struct u64_stats_sync *syncp, - unsigned int start) +static inline void u64_stats_update_begin(struct u64_stats_sync *syncp) { -#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) - return read_seqcount_retry(&syncp->seq, start); -#else - return false; -#endif + __u64_stats_update_begin(syncp); +} + +static inline void u64_stats_update_end(struct u64_stats_sync *syncp) +{ + __u64_stats_update_end(syncp); +} + +static inline unsigned long u64_stats_update_begin_irqsave(struct u64_stats_sync *syncp) +{ + unsigned long flags = __u64_stats_irqsave(); + + __u64_stats_update_begin(syncp); + return flags; +} + +static inline void u64_stats_update_end_irqrestore(struct u64_stats_sync *syncp, + unsigned long flags) +{ + __u64_stats_update_end(syncp); + __u64_stats_irqrestore(flags); +} + +static inline unsigned int u64_stats_fetch_begin(const struct u64_stats_sync *syncp) +{ + return __u64_stats_fetch_begin(syncp); } static inline bool u64_stats_fetch_retry(const struct u64_stats_sync *syncp, unsigned int start) { -#if BITS_PER_LONG == 32 && (!defined(CONFIG_SMP) && !defined(CONFIG_PREEMPT_RT)) - preempt_enable(); -#endif return __u64_stats_fetch_retry(syncp, start); } -/* - * In case irq handlers can update u64 counters, readers can use following helpers - * - SMP 32bit arches use seqcount protection, irq safe. - * - UP 32bit must disable irqs. - * - 64bit have no problem atomically reading u64 values, irq safe. - */ +/* Obsolete interfaces */ static inline unsigned int u64_stats_fetch_begin_irq(const struct u64_stats_sync *syncp) { -#if BITS_PER_LONG == 32 && defined(CONFIG_PREEMPT_RT) - preempt_disable(); -#elif BITS_PER_LONG == 32 && !defined(CONFIG_SMP) - local_irq_disable(); -#endif - return __u64_stats_fetch_begin(syncp); + return u64_stats_fetch_begin(syncp); } static inline bool u64_stats_fetch_retry_irq(const struct u64_stats_sync *syncp, unsigned int start) { -#if BITS_PER_LONG == 32 && defined(CONFIG_PREEMPT_RT) - preempt_enable(); -#elif BITS_PER_LONG == 32 && !defined(CONFIG_SMP) - local_irq_enable(); -#endif - return __u64_stats_fetch_retry(syncp, start); + return u64_stats_fetch_retry(syncp, start); } #endif /* _LINUX_U64_STATS_SYNC_H */ diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 47e5d374c7eb..afb18f198843 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -58,20 +58,28 @@ static __always_inline __must_check unsigned long __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n) { - instrument_copy_from_user(to, from, n); + unsigned long res; + + instrument_copy_from_user_before(to, from, n); check_object_size(to, n, false); - return raw_copy_from_user(to, from, n); + res = raw_copy_from_user(to, from, n); + instrument_copy_from_user_after(to, from, n, res); + return res; } static __always_inline __must_check unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n) { + unsigned long res; + might_fault(); + instrument_copy_from_user_before(to, from, n); if (should_fail_usercopy()) return n; - instrument_copy_from_user(to, from, n); check_object_size(to, n, false); - return raw_copy_from_user(to, from, n); + res = raw_copy_from_user(to, from, n); + instrument_copy_from_user_after(to, from, n, res); + return res; } /** @@ -115,8 +123,9 @@ _copy_from_user(void *to, const void __user *from, unsigned long n) unsigned long res = n; might_fault(); if (!should_fail_usercopy() && likely(access_ok(from, n))) { - instrument_copy_from_user(to, from, n); + instrument_copy_from_user_before(to, from, n); res = raw_copy_from_user(to, from, n); + instrument_copy_from_user_after(to, from, n, res); } if (unlikely(res)) memset(to + (n - res), 0, res); diff --git a/include/linux/umh.h b/include/linux/umh.h index 244aff638220..5d1f6129b847 100644 --- a/include/linux/umh.h +++ b/include/linux/umh.h @@ -11,10 +11,11 @@ struct cred; struct file; -#define UMH_NO_WAIT 0 /* don't wait at all */ -#define UMH_WAIT_EXEC 1 /* wait for the exec, but not the process */ -#define UMH_WAIT_PROC 2 /* wait for the process to complete */ -#define UMH_KILLABLE 4 /* wait for EXEC/PROC killable */ +#define UMH_NO_WAIT 0x00 /* don't wait at all */ +#define UMH_WAIT_EXEC 0x01 /* wait for the exec, but not the process */ +#define UMH_WAIT_PROC 0x02 /* wait for the process to complete */ +#define UMH_KILLABLE 0x04 /* wait for EXEC/PROC killable */ +#define UMH_FREEZABLE 0x08 /* wait for EXEC/PROC freezable */ struct subprocess_info { struct work_struct work; diff --git a/include/linux/user_events.h b/include/linux/user_events.h index 736e05603463..592a3fbed98e 100644 --- a/include/linux/user_events.h +++ b/include/linux/user_events.h @@ -20,15 +20,6 @@ #define USER_EVENTS_SYSTEM "user_events" #define USER_EVENTS_PREFIX "u:" -/* Bits 0-6 are for known probe types, Bit 7 is for unknown probes */ -#define EVENT_BIT_FTRACE 0 -#define EVENT_BIT_PERF 1 -#define EVENT_BIT_OTHER 7 - -#define EVENT_STATUS_FTRACE (1 << EVENT_BIT_FTRACE) -#define EVENT_STATUS_PERF (1 << EVENT_BIT_PERF) -#define EVENT_STATUS_OTHER (1 << EVENT_BIT_OTHER) - /* Create dynamic location entry within a 32-bit value */ #define DYN_LOC(offset, size) ((size) << 16 | (offset)) @@ -45,12 +36,12 @@ struct user_reg { /* Input: Pointer to string with event name, description and flags */ __u64 name_args; - /* Output: Byte index of the event within the status page */ - __u32 status_index; + /* Output: Bitwise index of the event within the status page */ + __u32 status_bit; /* Output: Index of the event to use when writing data */ __u32 write_index; -}; +} __attribute__((__packed__)); #define DIAG_IOC_MAGIC '*' diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index e1b8a915e9e9..9df0b9a762cc 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -146,9 +146,9 @@ static inline bool userfaultfd_armed(struct vm_area_struct *vma) static inline bool vma_can_userfault(struct vm_area_struct *vma, unsigned long vm_flags) { - if (vm_flags & VM_UFFD_MINOR) - return is_vm_hugetlb_page(vma) || vma_is_shmem(vma); - + if ((vm_flags & VM_UFFD_MINOR) && + (!is_vm_hugetlb_page(vma) && !vma_is_shmem(vma))) + return false; #ifndef CONFIG_PTE_MARKER_UFFD_WP /* * If user requested uffd-wp but not enabled pte markers for @@ -175,9 +175,8 @@ extern bool userfaultfd_remove(struct vm_area_struct *vma, unsigned long start, unsigned long end); -extern int userfaultfd_unmap_prep(struct vm_area_struct *vma, - unsigned long start, unsigned long end, - struct list_head *uf); +extern int userfaultfd_unmap_prep(struct mm_struct *mm, unsigned long start, + unsigned long end, struct list_head *uf); extern void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf); @@ -258,7 +257,7 @@ static inline bool userfaultfd_remove(struct vm_area_struct *vma, return true; } -static inline int userfaultfd_unmap_prep(struct vm_area_struct *vma, +static inline int userfaultfd_unmap_prep(struct mm_struct *mm, unsigned long start, unsigned long end, struct list_head *uf) { diff --git a/include/linux/utsname.h b/include/linux/utsname.h index 2b1737c9b244..bf7613ba412b 100644 --- a/include/linux/utsname.h +++ b/include/linux/utsname.h @@ -10,6 +10,7 @@ #include <uapi/linux/utsname.h> enum uts_proc { + UTS_PROC_ARCH, UTS_PROC_OSTYPE, UTS_PROC_OSRELEASE, UTS_PROC_VERSION, diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index d282f464d2f1..6d0f5e4e82c2 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -104,6 +104,7 @@ struct vdpa_iova_range { }; struct vdpa_dev_set_config { + u64 device_features; struct { u8 mac[ETH_ALEN]; u16 mtu; diff --git a/include/linux/vfio.h b/include/linux/vfio.h index e05ddc6fe6a5..fdd393f70b19 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -14,6 +14,7 @@ #include <linux/workqueue.h> #include <linux/poll.h> #include <uapi/linux/vfio.h> +#include <linux/iova_bitmap.h> struct kvm; @@ -33,10 +34,11 @@ struct vfio_device { struct device *dev; const struct vfio_device_ops *ops; /* - * mig_ops is a static property of the vfio_device which must be set - * prior to registering the vfio_device. + * mig_ops/log_ops is a static property of the vfio_device which must + * be set prior to registering the vfio_device. */ const struct vfio_migration_ops *mig_ops; + const struct vfio_log_ops *log_ops; struct vfio_group *group; struct vfio_device_set *dev_set; struct list_head dev_set_list; @@ -45,7 +47,9 @@ struct vfio_device { struct kvm *kvm; /* Members below here are private, not for driver use */ - refcount_t refcount; + unsigned int index; + struct device device; /* device.kref covers object life circle */ + refcount_t refcount; /* user count on registered device*/ unsigned int open_count; struct completion comp; struct list_head group_next; @@ -55,6 +59,8 @@ struct vfio_device { /** * struct vfio_device_ops - VFIO bus driver device callbacks * + * @init: initialize private fields in device structure + * @release: Reclaim private fields in device structure * @open_device: Called when the first file descriptor is opened for this device * @close_device: Opposite of open_device * @read: Perform read(2) on device file descriptor @@ -72,6 +78,8 @@ struct vfio_device { */ struct vfio_device_ops { char *name; + int (*init)(struct vfio_device *vdev); + void (*release)(struct vfio_device *vdev); int (*open_device)(struct vfio_device *vdev); void (*close_device)(struct vfio_device *vdev); ssize_t (*read)(struct vfio_device *vdev, char __user *buf, @@ -109,6 +117,28 @@ struct vfio_migration_ops { }; /** + * @log_start: Optional callback to ask the device start DMA logging. + * @log_stop: Optional callback to ask the device stop DMA logging. + * @log_read_and_clear: Optional callback to ask the device read + * and clear the dirty DMAs in some given range. + * + * The vfio core implementation of the DEVICE_FEATURE_DMA_LOGGING_ set + * of features does not track logging state relative to the device, + * therefore the device implementation of vfio_log_ops must handle + * arbitrary user requests. This includes rejecting subsequent calls + * to log_start without an intervening log_stop, as well as graceful + * handling of log_stop and log_read_and_clear from invalid states. + */ +struct vfio_log_ops { + int (*log_start)(struct vfio_device *device, + struct rb_root_cached *ranges, u32 nnodes, u64 *page_size); + int (*log_stop)(struct vfio_device *device); + int (*log_read_and_clear)(struct vfio_device *device, + unsigned long iova, unsigned long length, + struct iova_bitmap *dirty); +}; + +/** * vfio_check_feature - Validate user input for the VFIO_DEVICE_FEATURE ioctl * @flags: Arg from the device_feature op * @argsz: Arg from the device_feature op @@ -137,14 +167,29 @@ static inline int vfio_check_feature(u32 flags, size_t argsz, u32 supported_ops, return 1; } -void vfio_init_group_dev(struct vfio_device *device, struct device *dev, - const struct vfio_device_ops *ops); -void vfio_uninit_group_dev(struct vfio_device *device); +struct vfio_device *_vfio_alloc_device(size_t size, struct device *dev, + const struct vfio_device_ops *ops); +#define vfio_alloc_device(dev_struct, member, dev, ops) \ + container_of(_vfio_alloc_device(sizeof(struct dev_struct) + \ + BUILD_BUG_ON_ZERO(offsetof( \ + struct dev_struct, member)), \ + dev, ops), \ + struct dev_struct, member) + +int vfio_init_device(struct vfio_device *device, struct device *dev, + const struct vfio_device_ops *ops); +void vfio_free_device(struct vfio_device *device); +static inline void vfio_put_device(struct vfio_device *device) +{ + put_device(&device->device); +} + int vfio_register_group_dev(struct vfio_device *device); int vfio_register_emulated_iommu_dev(struct vfio_device *device); void vfio_unregister_group_dev(struct vfio_device *device); int vfio_assign_device_set(struct vfio_device *device, void *set_id); +unsigned int vfio_device_set_open_count(struct vfio_device_set *dev_set); int vfio_mig_get_next_state(struct vfio_device *device, enum vfio_device_mig_state cur_fsm, @@ -155,6 +200,7 @@ int vfio_mig_get_next_state(struct vfio_device *device, * External user API */ struct iommu_group *vfio_file_iommu_group(struct file *file); +bool vfio_file_is_group(struct file *file); bool vfio_file_enforced_coherent(struct file *file); void vfio_file_set_kvm(struct file *file, struct kvm *kvm); bool vfio_file_has_dev(struct file *file, struct vfio_device *device); diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index 5579ece4347b..367fd79226a3 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -20,39 +20,10 @@ #define VFIO_PCI_CORE_H #define VFIO_PCI_OFFSET_SHIFT 40 - #define VFIO_PCI_OFFSET_TO_INDEX(off) (off >> VFIO_PCI_OFFSET_SHIFT) #define VFIO_PCI_INDEX_TO_OFFSET(index) ((u64)(index) << VFIO_PCI_OFFSET_SHIFT) #define VFIO_PCI_OFFSET_MASK (((u64)(1) << VFIO_PCI_OFFSET_SHIFT) - 1) -/* Special capability IDs predefined access */ -#define PCI_CAP_ID_INVALID 0xFF /* default raw access */ -#define PCI_CAP_ID_INVALID_VIRT 0xFE /* default virt access */ - -/* Cap maximum number of ioeventfds per device (arbitrary) */ -#define VFIO_PCI_IOEVENTFD_MAX 1000 - -struct vfio_pci_ioeventfd { - struct list_head next; - struct vfio_pci_core_device *vdev; - struct virqfd *virqfd; - void __iomem *addr; - uint64_t data; - loff_t pos; - int bar; - int count; - bool test_mem; -}; - -struct vfio_pci_irq_ctx { - struct eventfd_ctx *trigger; - struct virqfd *unmask; - struct virqfd *mask; - char *name; - bool masked; - struct irq_bypass_producer producer; -}; - struct vfio_pci_core_device; struct vfio_pci_region; @@ -78,23 +49,6 @@ struct vfio_pci_region { u32 flags; }; -struct vfio_pci_dummy_resource { - struct resource resource; - int index; - struct list_head res_next; -}; - -struct vfio_pci_vf_token { - struct mutex lock; - uuid_t uuid; - int users; -}; - -struct vfio_pci_mmap_vma { - struct vm_area_struct *vma; - struct list_head vma_next; -}; - struct vfio_pci_core_device { struct vfio_device vdev; struct pci_dev *pdev; @@ -124,11 +78,14 @@ struct vfio_pci_core_device { bool needs_reset; bool nointx; bool needs_pm_restore; + bool pm_intx_masked; + bool pm_runtime_engaged; struct pci_saved_state *pci_saved_state; struct pci_saved_state *pm_save; int ioeventfds_nr; struct eventfd_ctx *err_trigger; struct eventfd_ctx *req_trigger; + struct eventfd_ctx *pm_wake_eventfd_ctx; struct list_head dummy_resources_list; struct mutex ioeventfds_lock; struct list_head ioeventfds_list; @@ -141,100 +98,17 @@ struct vfio_pci_core_device { struct rw_semaphore memory_lock; }; -#define is_intx(vdev) (vdev->irq_type == VFIO_PCI_INTX_IRQ_INDEX) -#define is_msi(vdev) (vdev->irq_type == VFIO_PCI_MSI_IRQ_INDEX) -#define is_msix(vdev) (vdev->irq_type == VFIO_PCI_MSIX_IRQ_INDEX) -#define is_irq_none(vdev) (!(is_intx(vdev) || is_msi(vdev) || is_msix(vdev))) -#define irq_is(vdev, type) (vdev->irq_type == type) - -void vfio_pci_intx_mask(struct vfio_pci_core_device *vdev); -void vfio_pci_intx_unmask(struct vfio_pci_core_device *vdev); - -int vfio_pci_set_irqs_ioctl(struct vfio_pci_core_device *vdev, - uint32_t flags, unsigned index, - unsigned start, unsigned count, void *data); - -ssize_t vfio_pci_config_rw(struct vfio_pci_core_device *vdev, - char __user *buf, size_t count, - loff_t *ppos, bool iswrite); - -ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf, - size_t count, loff_t *ppos, bool iswrite); - -#ifdef CONFIG_VFIO_PCI_VGA -ssize_t vfio_pci_vga_rw(struct vfio_pci_core_device *vdev, char __user *buf, - size_t count, loff_t *ppos, bool iswrite); -#else -static inline ssize_t vfio_pci_vga_rw(struct vfio_pci_core_device *vdev, - char __user *buf, size_t count, - loff_t *ppos, bool iswrite) -{ - return -EINVAL; -} -#endif - -long vfio_pci_ioeventfd(struct vfio_pci_core_device *vdev, loff_t offset, - uint64_t data, int count, int fd); - -int vfio_pci_init_perm_bits(void); -void vfio_pci_uninit_perm_bits(void); - -int vfio_config_init(struct vfio_pci_core_device *vdev); -void vfio_config_free(struct vfio_pci_core_device *vdev); - -int vfio_pci_register_dev_region(struct vfio_pci_core_device *vdev, - unsigned int type, unsigned int subtype, - const struct vfio_pci_regops *ops, - size_t size, u32 flags, void *data); - -int vfio_pci_set_power_state(struct vfio_pci_core_device *vdev, - pci_power_t state); - -bool __vfio_pci_memory_enabled(struct vfio_pci_core_device *vdev); -void vfio_pci_zap_and_down_write_memory_lock(struct vfio_pci_core_device *vdev); -u16 vfio_pci_memory_lock_and_enable(struct vfio_pci_core_device *vdev); -void vfio_pci_memory_unlock_and_restore(struct vfio_pci_core_device *vdev, - u16 cmd); - -#ifdef CONFIG_VFIO_PCI_IGD -int vfio_pci_igd_init(struct vfio_pci_core_device *vdev); -#else -static inline int vfio_pci_igd_init(struct vfio_pci_core_device *vdev) -{ - return -ENODEV; -} -#endif - -#ifdef CONFIG_VFIO_PCI_ZDEV_KVM -int vfio_pci_info_zdev_add_caps(struct vfio_pci_core_device *vdev, - struct vfio_info_cap *caps); -int vfio_pci_zdev_open_device(struct vfio_pci_core_device *vdev); -void vfio_pci_zdev_close_device(struct vfio_pci_core_device *vdev); -#else -static inline int vfio_pci_info_zdev_add_caps(struct vfio_pci_core_device *vdev, - struct vfio_info_cap *caps) -{ - return -ENODEV; -} - -static inline int vfio_pci_zdev_open_device(struct vfio_pci_core_device *vdev) -{ - return 0; -} - -static inline void vfio_pci_zdev_close_device(struct vfio_pci_core_device *vdev) -{} -#endif - /* Will be exported for vfio pci drivers usage */ +int vfio_pci_core_register_dev_region(struct vfio_pci_core_device *vdev, + unsigned int type, unsigned int subtype, + const struct vfio_pci_regops *ops, + size_t size, u32 flags, void *data); void vfio_pci_core_set_params(bool nointxmask, bool is_disable_vga, bool is_disable_idle_d3); void vfio_pci_core_close_device(struct vfio_device *core_vdev); -void vfio_pci_core_init_device(struct vfio_pci_core_device *vdev, - struct pci_dev *pdev, - const struct vfio_device_ops *vfio_pci_ops); +int vfio_pci_core_init_dev(struct vfio_device *core_vdev); +void vfio_pci_core_release_dev(struct vfio_device *core_vdev); int vfio_pci_core_register_device(struct vfio_pci_core_device *vdev); -void vfio_pci_core_uninit_device(struct vfio_pci_core_device *vdev); void vfio_pci_core_unregister_device(struct vfio_pci_core_device *vdev); extern const struct pci_error_handlers vfio_pci_core_err_handlers; int vfio_pci_core_sriov_configure(struct vfio_pci_core_device *vdev, @@ -256,9 +130,4 @@ void vfio_pci_core_finish_enable(struct vfio_pci_core_device *vdev); pci_ers_result_t vfio_pci_core_aer_err_detected(struct pci_dev *pdev, pci_channel_state_t state); -static inline bool vfio_pci_is_vga(struct pci_dev *pdev) -{ - return (pdev->class >> 8) == PCI_CLASS_DISPLAY_VGA; -} - #endif /* VFIO_PCI_CORE_H */ diff --git a/include/linux/virtio_pci_legacy.h b/include/linux/virtio_pci_legacy.h index e5d665faf00e..a8dc757d0367 100644 --- a/include/linux/virtio_pci_legacy.h +++ b/include/linux/virtio_pci_legacy.h @@ -32,8 +32,6 @@ void vp_legacy_set_queue_address(struct virtio_pci_legacy_device *ldev, u16 index, u32 queue_pfn); bool vp_legacy_get_queue_enable(struct virtio_pci_legacy_device *ldev, u16 idx); -void vp_legacy_set_queue_size(struct virtio_pci_legacy_device *ldev, - u16 idx, u16 size); u16 vp_legacy_get_queue_size(struct virtio_pci_legacy_device *ldev, u16 idx); int vp_legacy_probe(struct virtio_pci_legacy_device *ldev); diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index f3fc36cd2276..3518dba1e02f 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -129,10 +129,6 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, NR_TLB_LOCAL_FLUSH_ALL, NR_TLB_LOCAL_FLUSH_ONE, #endif /* CONFIG_DEBUG_TLBFLUSH */ -#ifdef CONFIG_DEBUG_VM_VMACACHE - VMACACHE_FIND_CALLS, - VMACACHE_FIND_HITS, -#endif #ifdef CONFIG_SWAP SWAP_RA, SWAP_RA_HIT, diff --git a/include/linux/vmacache.h b/include/linux/vmacache.h deleted file mode 100644 index 6fce268a4588..000000000000 --- a/include/linux/vmacache.h +++ /dev/null @@ -1,28 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __LINUX_VMACACHE_H -#define __LINUX_VMACACHE_H - -#include <linux/sched.h> -#include <linux/mm.h> - -static inline void vmacache_flush(struct task_struct *tsk) -{ - memset(tsk->vmacache.vmas, 0, sizeof(tsk->vmacache.vmas)); -} - -extern void vmacache_update(unsigned long addr, struct vm_area_struct *newvma); -extern struct vm_area_struct *vmacache_find(struct mm_struct *mm, - unsigned long addr); - -#ifndef CONFIG_MMU -extern struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm, - unsigned long start, - unsigned long end); -#endif - -static inline void vmacache_invalidate(struct mm_struct *mm) -{ - mm->vmacache_seqnum++; -} - -#endif /* __LINUX_VMACACHE_H */ diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index bfe38869498d..19cf5b6892ce 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -125,12 +125,6 @@ static inline void vm_events_fold_cpu(int cpu) #define count_vm_tlb_events(x, y) do { (void)(y); } while (0) #endif -#ifdef CONFIG_DEBUG_VM_VMACACHE -#define count_vm_vmacache_event(x) count_vm_event(x) -#else -#define count_vm_vmacache_event(x) do {} while (0) -#endif - #define __count_zid_vm_events(item, zid, delta) \ __count_vm_events(item##_NORMAL - ZONE_NORMAL + zid, delta) diff --git a/include/linux/wait.h b/include/linux/wait.h index 58cfbf81447c..7f5a51aae0a7 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -281,7 +281,7 @@ static inline void wake_up_pollfree(struct wait_queue_head *wq_head) #define ___wait_is_interruptible(state) \ (!__builtin_constant_p(state) || \ - state == TASK_INTERRUPTIBLE || state == TASK_KILLABLE) \ + (state & (TASK_INTERRUPTIBLE | TASK_WAKEKILL))) extern void init_wait_entry(struct wait_queue_entry *wq_entry, int flags); @@ -361,8 +361,8 @@ do { \ } while (0) #define __wait_event_freezable(wq_head, condition) \ - ___wait_event(wq_head, condition, TASK_INTERRUPTIBLE, 0, 0, \ - freezable_schedule()) + ___wait_event(wq_head, condition, (TASK_INTERRUPTIBLE|TASK_FREEZABLE), \ + 0, 0, schedule()) /** * wait_event_freezable - sleep (or freeze) until a condition gets true @@ -420,8 +420,8 @@ do { \ #define __wait_event_freezable_timeout(wq_head, condition, timeout) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ - TASK_INTERRUPTIBLE, 0, timeout, \ - __ret = freezable_schedule_timeout(__ret)) + (TASK_INTERRUPTIBLE|TASK_FREEZABLE), 0, timeout, \ + __ret = schedule_timeout(__ret)) /* * like wait_event_timeout() -- except it uses TASK_INTERRUPTIBLE to avoid @@ -642,8 +642,8 @@ do { \ #define __wait_event_freezable_exclusive(wq, condition) \ - ___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, 0, \ - freezable_schedule()) + ___wait_event(wq, condition, (TASK_INTERRUPTIBLE|TASK_FREEZABLE), 1, 0,\ + schedule()) #define wait_event_freezable_exclusive(wq, condition) \ ({ \ @@ -932,6 +932,34 @@ extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_entry_t *); __ret; \ }) +#define __wait_event_state(wq, condition, state) \ + ___wait_event(wq, condition, state, 0, 0, schedule()) + +/** + * wait_event_state - sleep until a condition gets true + * @wq_head: the waitqueue to wait on + * @condition: a C expression for the event to wait for + * @state: state to sleep in + * + * The process is put to sleep (@state) until the @condition evaluates to true + * or a signal is received (when allowed by @state). The @condition is checked + * each time the waitqueue @wq_head is woken up. + * + * wake_up() has to be called after changing any variable that could + * change the result of the wait condition. + * + * The function will return -ERESTARTSYS if it was interrupted by a signal + * (when allowed by @state) and 0 if @condition evaluated to true. + */ +#define wait_event_state(wq_head, condition, state) \ +({ \ + int __ret = 0; \ + might_sleep(); \ + if (!(condition)) \ + __ret = __wait_event_state(wq_head, condition, state); \ + __ret; \ +}) + #define __wait_event_killable_timeout(wq_head, condition, timeout) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ TASK_KILLABLE, 0, timeout, \ diff --git a/include/linux/wireless.h b/include/linux/wireless.h index 2d1b54556eff..e6e34d74dda0 100644 --- a/include/linux/wireless.h +++ b/include/linux/wireless.h @@ -26,7 +26,15 @@ struct compat_iw_point { struct __compat_iw_event { __u16 len; /* Real length of this stuff */ __u16 cmd; /* Wireless IOCTL */ - compat_caddr_t pointer; + + union { + compat_caddr_t pointer; + + /* we need ptr_bytes to make memcpy() run-time destination + * buffer bounds checking happy, nothing special + */ + DECLARE_FLEX_ARRAY(__u8, ptr_bytes); + }; }; #define IW_EV_COMPAT_LCP_LEN offsetof(struct __compat_iw_event, pointer) #define IW_EV_COMPAT_POINT_OFF offsetof(struct compat_iw_point, length) diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 3f045f6d6c4f..06f9291b6fd5 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -17,20 +17,12 @@ struct bio; DECLARE_PER_CPU(int, dirty_throttle_leaks); /* - * The 1/4 region under the global dirty thresh is for smooth dirty throttling: - * - * (thresh - thresh/DIRTY_FULL_SCOPE, thresh) - * - * Further beyond, all dirtier tasks will enter a loop waiting (possibly long - * time) for the dirty pages to drop, unless written enough pages. - * * The global dirty threshold is normally equal to the global dirty limit, * except when the system suddenly allocates a lot of anonymous memory and * knocks down the global dirty threshold quickly, in which case the global * dirty limit will follow down slowly to prevent livelocking all dirtier tasks. */ #define DIRTY_SCOPE 8 -#define DIRTY_FULL_SCOPE (DIRTY_SCOPE / 2) struct backing_dev_info; diff --git a/include/media/i2c/ir-kbd-i2c.h b/include/media/i2c/ir-kbd-i2c.h index 9f47d6a48cff..0b58f8b9e7a4 100644 --- a/include/media/i2c/ir-kbd-i2c.h +++ b/include/media/i2c/ir-kbd-i2c.h @@ -35,6 +35,7 @@ enum ir_kbd_get_key_fn { IR_KBD_GET_KEY_PIXELVIEW, IR_KBD_GET_KEY_HAUP, IR_KBD_GET_KEY_KNC1, + IR_KBD_GET_KEY_GENIATECH, IR_KBD_GET_KEY_FUSIONHDTV, IR_KBD_GET_KEY_HAUP_XVR, IR_KBD_GET_KEY_AVERMEDIA_CARDBUS, diff --git a/include/media/media-device.h b/include/media/media-device.h index a10b30507524..86716ee7cc6c 100644 --- a/include/media/media-device.h +++ b/include/media/media-device.h @@ -192,21 +192,6 @@ struct usb_device; #define MEDIA_DEV_NOTIFY_POST_LINK_CH 1 /** - * media_entity_enum_init - Initialise an entity enumeration - * - * @ent_enum: Entity enumeration to be initialised - * @mdev: The related media device - * - * Return: zero on success or a negative error code. - */ -static inline __must_check int media_entity_enum_init( - struct media_entity_enum *ent_enum, struct media_device *mdev) -{ - return __media_entity_enum_init(ent_enum, - mdev->entity_internal_idx_max + 1); -} - -/** * media_device_init() - Initializes a media device element * * @mdev: pointer to struct &media_device diff --git a/include/media/media-entity.h b/include/media/media-entity.h index f16ffe70f7a6..28c9de8a1f34 100644 --- a/include/media/media-entity.h +++ b/include/media/media-entity.h @@ -17,6 +17,7 @@ #include <linux/fwnode.h> #include <linux/list.h> #include <linux/media.h> +#include <linux/minmax.h> #include <linux/types.h> /* Enums used internally at the media controller to represent graphs */ @@ -99,12 +100,34 @@ struct media_graph { /** * struct media_pipeline - Media pipeline related information * - * @streaming_count: Streaming start count - streaming stop count - * @graph: Media graph walk during pipeline start / stop + * @allocated: Media pipeline allocated and freed by the framework + * @mdev: The media device the pipeline is part of + * @pads: List of media_pipeline_pad + * @start_count: Media pipeline start - stop count */ struct media_pipeline { - int streaming_count; - struct media_graph graph; + bool allocated; + struct media_device *mdev; + struct list_head pads; + int start_count; +}; + +/** + * struct media_pipeline_pad - A pad part of a media pipeline + * + * @list: Entry in the media_pad pads list + * @pipe: The media_pipeline that the pad is part of + * @pad: The media pad + * + * This structure associate a pad with a media pipeline. Instances of + * media_pipeline_pad are created by media_pipeline_start() when it builds the + * pipeline, and stored in the &media_pad.pads list. media_pipeline_stop() + * removes the entries from the list and deletes them. + */ +struct media_pipeline_pad { + struct list_head list; + struct media_pipeline *pipe; + struct media_pad *pad; }; /** @@ -186,6 +209,8 @@ enum media_pad_signal_type { * @flags: Pad flags, as defined in * :ref:`include/uapi/linux/media.h <media_header>` * (seek for ``MEDIA_PAD_FL_*``) + * @pipe: Pipeline this pad belongs to. Use media_entity_pipeline() to + * access this field. */ struct media_pad { struct media_gobj graph_obj; /* must be first field in struct */ @@ -193,6 +218,12 @@ struct media_pad { u16 index; enum media_pad_signal_type sig_type; unsigned long flags; + + /* + * The fields below are private, and should only be accessed via + * appropriate functions. + */ + struct media_pipeline *pipe; }; /** @@ -206,6 +237,14 @@ struct media_pad { * @link_validate: Return whether a link is valid from the entity point of * view. The media_pipeline_start() function * validates all links by calling this operation. Optional. + * @has_pad_interdep: Return whether a two pads inside the entity are + * interdependent. If two pads are interdependent they are + * part of the same pipeline and enabling one of the pads + * means that the other pad will become "locked" and + * doesn't allow configuration changes. pad0 and pad1 are + * guaranteed to not both be sinks or sources. + * Optional: If the operation isn't implemented all pads + * will be considered as interdependent. * * .. note:: * @@ -219,6 +258,8 @@ struct media_entity_operations { const struct media_pad *local, const struct media_pad *remote, u32 flags); int (*link_validate)(struct media_link *link); + bool (*has_pad_interdep)(struct media_entity *entity, unsigned int pad0, + unsigned int pad1); }; /** @@ -269,7 +310,6 @@ enum media_entity_type { * @links: List of data links. * @ops: Entity operations. * @use_count: Use count for the entity. - * @pipe: Pipeline this entity belongs to. * @info: Union with devnode information. Kept just for backward * compatibility. * @info.dev: Contains device major and minor info. @@ -305,8 +345,6 @@ struct media_entity { int use_count; - struct media_pipeline *pipe; - union { struct { u32 major; @@ -316,6 +354,18 @@ struct media_entity { }; /** + * media_entity_for_each_pad - Iterate on all pads in an entity + * @entity: The entity the pads belong to + * @iter: The iterator pad + * + * Iterate on all pads in a media entity. + */ +#define media_entity_for_each_pad(entity, iter) \ + for (iter = (entity)->pads; \ + iter < &(entity)->pads[(entity)->num_pads]; \ + ++iter) + +/** * struct media_interface - A media interface graph object. * * @graph_obj: embedded graph object @@ -426,15 +476,15 @@ static inline bool is_media_entity_v4l2_subdev(struct media_entity *entity) } /** - * __media_entity_enum_init - Initialise an entity enumeration + * media_entity_enum_init - Initialise an entity enumeration * * @ent_enum: Entity enumeration to be initialised - * @idx_max: Maximum number of entities in the enumeration + * @mdev: The related media device * - * Return: Returns zero on success or a negative error code. + * Return: zero on success or a negative error code. */ -__must_check int __media_entity_enum_init(struct media_entity_enum *ent_enum, - int idx_max); +__must_check int media_entity_enum_init(struct media_entity_enum *ent_enum, + struct media_device *mdev); /** * media_entity_enum_cleanup - Release resources of an entity enumeration @@ -924,6 +974,18 @@ media_entity_remote_source_pad_unique(const struct media_entity *entity) } /** + * media_pad_is_streaming - Test if a pad is part of a streaming pipeline + * @pad: The pad + * + * Return: True if the pad is part of a pipeline started with the + * media_pipeline_start() function, false otherwise. + */ +static inline bool media_pad_is_streaming(const struct media_pad *pad) +{ + return pad->pipe; +} + +/** * media_entity_is_streaming - Test if an entity is part of a streaming pipeline * @entity: The entity * @@ -932,10 +994,50 @@ media_entity_remote_source_pad_unique(const struct media_entity *entity) */ static inline bool media_entity_is_streaming(const struct media_entity *entity) { - return entity->pipe; + struct media_pad *pad; + + media_entity_for_each_pad(entity, pad) { + if (media_pad_is_streaming(pad)) + return true; + } + + return false; } /** + * media_entity_pipeline - Get the media pipeline an entity is part of + * @entity: The entity + * + * DEPRECATED: use media_pad_pipeline() instead. + * + * This function returns the media pipeline that an entity has been associated + * with when constructing the pipeline with media_pipeline_start(). The pointer + * remains valid until media_pipeline_stop() is called. + * + * In general, entities can be part of multiple pipelines, when carrying + * multiple streams (either on different pads, or on the same pad using + * multiplexed streams). This function is to be used only for entities that + * do not support multiple pipelines. + * + * Return: The media_pipeline the entity is part of, or NULL if the entity is + * not part of any pipeline. + */ +struct media_pipeline *media_entity_pipeline(struct media_entity *entity); + +/** + * media_pad_pipeline - Get the media pipeline a pad is part of + * @pad: The pad + * + * This function returns the media pipeline that a pad has been associated + * with when constructing the pipeline with media_pipeline_start(). The pointer + * remains valid until media_pipeline_stop() is called. + * + * Return: The media_pipeline the pad is part of, or NULL if the pad is + * not part of any pipeline. + */ +struct media_pipeline *media_pad_pipeline(struct media_pad *pad); + +/** * media_entity_get_fwnode_pad - Get pad number from fwnode * * @entity: The entity @@ -1013,53 +1115,66 @@ struct media_entity *media_graph_walk_next(struct media_graph *graph); /** * media_pipeline_start - Mark a pipeline as streaming - * @entity: Starting entity - * @pipe: Media pipeline to be assigned to all entities in the pipeline. + * @pad: Starting pad + * @pipe: Media pipeline to be assigned to all pads in the pipeline. * - * Mark all entities connected to a given entity through enabled links, either + * Mark all pads connected to a given pad through enabled links, either * directly or indirectly, as streaming. The given pipeline object is assigned - * to every entity in the pipeline and stored in the media_entity pipe field. + * to every pad in the pipeline and stored in the media_pad pipe field. * * Calls to this function can be nested, in which case the same number of * media_pipeline_stop() calls will be required to stop streaming. The * pipeline pointer must be identical for all nested calls to * media_pipeline_start(). */ -__must_check int media_pipeline_start(struct media_entity *entity, +__must_check int media_pipeline_start(struct media_pad *pad, struct media_pipeline *pipe); /** * __media_pipeline_start - Mark a pipeline as streaming * - * @entity: Starting entity - * @pipe: Media pipeline to be assigned to all entities in the pipeline. + * @pad: Starting pad + * @pipe: Media pipeline to be assigned to all pads in the pipeline. * * ..note:: This is the non-locking version of media_pipeline_start() */ -__must_check int __media_pipeline_start(struct media_entity *entity, +__must_check int __media_pipeline_start(struct media_pad *pad, struct media_pipeline *pipe); /** * media_pipeline_stop - Mark a pipeline as not streaming - * @entity: Starting entity + * @pad: Starting pad * - * Mark all entities connected to a given entity through enabled links, either - * directly or indirectly, as not streaming. The media_entity pipe field is + * Mark all pads connected to a given pads through enabled links, either + * directly or indirectly, as not streaming. The media_pad pipe field is * reset to %NULL. * * If multiple calls to media_pipeline_start() have been made, the same * number of calls to this function are required to mark the pipeline as not * streaming. */ -void media_pipeline_stop(struct media_entity *entity); +void media_pipeline_stop(struct media_pad *pad); /** * __media_pipeline_stop - Mark a pipeline as not streaming * - * @entity: Starting entity + * @pad: Starting pad * * .. note:: This is the non-locking version of media_pipeline_stop() */ -void __media_pipeline_stop(struct media_entity *entity); +void __media_pipeline_stop(struct media_pad *pad); + +/** + * media_pipeline_alloc_start - Mark a pipeline as streaming + * @pad: Starting pad + * + * media_pipeline_alloc_start() is similar to media_pipeline_start() but instead + * of working on a given pipeline the function will use an existing pipeline if + * the pad is already part of a pipeline, or allocate a new pipeline. + * + * Calls to media_pipeline_alloc_start() must be matched with + * media_pipeline_stop(). + */ +__must_check int media_pipeline_alloc_start(struct media_pad *pad); /** * media_devnode_create() - creates and initializes a device node interface diff --git a/include/media/v4l2-common.h b/include/media/v4l2-common.h index 725ff91b26e0..1bdaea248089 100644 --- a/include/media/v4l2-common.h +++ b/include/media/v4l2-common.h @@ -175,7 +175,8 @@ struct v4l2_subdev *v4l2_i2c_new_subdev_board(struct v4l2_device *v4l2_dev, * * @sd: pointer to &struct v4l2_subdev * @client: pointer to struct i2c_client - * @devname: the name of the device; if NULL, the I²C device's name will be used + * @devname: the name of the device; if NULL, the I²C device drivers's name + * will be used * @postfix: sub-device specific string to put right after the I²C device name; * may be NULL */ diff --git a/include/media/v4l2-ctrls.h b/include/media/v4l2-ctrls.h index b76a0714d425..e59d9a234631 100644 --- a/include/media/v4l2-ctrls.h +++ b/include/media/v4l2-ctrls.h @@ -121,21 +121,19 @@ struct v4l2_ctrl_ops { * struct v4l2_ctrl_type_ops - The control type operations that the driver * has to provide. * - * @equal: return true if both values are equal. - * @init: initialize the value. + * @equal: return true if all ctrl->elems array elements are equal. + * @init: initialize the value for array elements from from_idx to ctrl->elems. * @log: log the value. - * @validate: validate the value. Return 0 on success and a negative value - * otherwise. + * @validate: validate the value for ctrl->new_elems array elements. + * Return 0 on success and a negative value otherwise. */ struct v4l2_ctrl_type_ops { - bool (*equal)(const struct v4l2_ctrl *ctrl, u32 elems, - union v4l2_ctrl_ptr ptr1, - union v4l2_ctrl_ptr ptr2); - void (*init)(const struct v4l2_ctrl *ctrl, u32 from_idx, u32 tot_elems, + bool (*equal)(const struct v4l2_ctrl *ctrl, + union v4l2_ctrl_ptr ptr1, union v4l2_ctrl_ptr ptr2); + void (*init)(const struct v4l2_ctrl *ctrl, u32 from_idx, union v4l2_ctrl_ptr ptr); void (*log)(const struct v4l2_ctrl *ctrl); - int (*validate)(const struct v4l2_ctrl *ctrl, u32 elems, - union v4l2_ctrl_ptr ptr); + int (*validate)(const struct v4l2_ctrl *ctrl, union v4l2_ctrl_ptr ptr); }; /** @@ -1543,13 +1541,12 @@ int v4l2_ctrl_new_fwnode_properties(struct v4l2_ctrl_handler *hdl, * v4l2_ctrl_type_op_equal - Default v4l2_ctrl_type_ops equal callback. * * @ctrl: The v4l2_ctrl pointer. - * @elems: The number of elements to compare. * @ptr1: A v4l2 control value. * @ptr2: A v4l2 control value. * * Return: true if values are equal, otherwise false. */ -bool v4l2_ctrl_type_op_equal(const struct v4l2_ctrl *ctrl, u32 elems, +bool v4l2_ctrl_type_op_equal(const struct v4l2_ctrl *ctrl, union v4l2_ctrl_ptr ptr1, union v4l2_ctrl_ptr ptr2); /** @@ -1557,13 +1554,12 @@ bool v4l2_ctrl_type_op_equal(const struct v4l2_ctrl *ctrl, u32 elems, * * @ctrl: The v4l2_ctrl pointer. * @from_idx: Starting element index. - * @elems: The number of elements to initialize. * @ptr: The v4l2 control value. * * Return: void */ void v4l2_ctrl_type_op_init(const struct v4l2_ctrl *ctrl, u32 from_idx, - u32 elems, union v4l2_ctrl_ptr ptr); + union v4l2_ctrl_ptr ptr); /** * v4l2_ctrl_type_op_log - Default v4l2_ctrl_type_ops log callback. @@ -1578,12 +1574,10 @@ void v4l2_ctrl_type_op_log(const struct v4l2_ctrl *ctrl); * v4l2_ctrl_type_op_validate - Default v4l2_ctrl_type_ops validate callback. * * @ctrl: The v4l2_ctrl pointer. - * @elems: The number of elements in the control. * @ptr: The v4l2 control value. * * Return: 0 on success, a negative error code on failure. */ -int v4l2_ctrl_type_op_validate(const struct v4l2_ctrl *ctrl, u32 elems, - union v4l2_ctrl_ptr ptr); +int v4l2_ctrl_type_op_validate(const struct v4l2_ctrl *ctrl, union v4l2_ctrl_ptr ptr); #endif diff --git a/include/media/v4l2-dev.h b/include/media/v4l2-dev.h index 5cf1edefb822..e0a13505f88d 100644 --- a/include/media/v4l2-dev.h +++ b/include/media/v4l2-dev.h @@ -539,4 +539,106 @@ static inline int video_is_registered(struct video_device *vdev) return test_bit(V4L2_FL_REGISTERED, &vdev->flags); } +#if defined(CONFIG_MEDIA_CONTROLLER) + +/** + * video_device_pipeline_start - Mark a pipeline as streaming + * @vdev: Starting video device + * @pipe: Media pipeline to be assigned to all entities in the pipeline. + * + * Mark all entities connected to a given video device through enabled links, + * either directly or indirectly, as streaming. The given pipeline object is + * assigned to every pad in the pipeline and stored in the media_pad pipe + * field. + * + * Calls to this function can be nested, in which case the same number of + * video_device_pipeline_stop() calls will be required to stop streaming. The + * pipeline pointer must be identical for all nested calls to + * video_device_pipeline_start(). + * + * The video device must contain a single pad. + * + * This is a convenience wrapper around media_pipeline_start(). + */ +__must_check int video_device_pipeline_start(struct video_device *vdev, + struct media_pipeline *pipe); + +/** + * __video_device_pipeline_start - Mark a pipeline as streaming + * @vdev: Starting video device + * @pipe: Media pipeline to be assigned to all entities in the pipeline. + * + * ..note:: This is the non-locking version of video_device_pipeline_start() + * + * The video device must contain a single pad. + * + * This is a convenience wrapper around __media_pipeline_start(). + */ +__must_check int __video_device_pipeline_start(struct video_device *vdev, + struct media_pipeline *pipe); + +/** + * video_device_pipeline_stop - Mark a pipeline as not streaming + * @vdev: Starting video device + * + * Mark all entities connected to a given video device through enabled links, + * either directly or indirectly, as not streaming. The media_pad pipe field + * is reset to %NULL. + * + * If multiple calls to media_pipeline_start() have been made, the same + * number of calls to this function are required to mark the pipeline as not + * streaming. + * + * The video device must contain a single pad. + * + * This is a convenience wrapper around media_pipeline_stop(). + */ +void video_device_pipeline_stop(struct video_device *vdev); + +/** + * __video_device_pipeline_stop - Mark a pipeline as not streaming + * @vdev: Starting video device + * + * .. note:: This is the non-locking version of media_pipeline_stop() + * + * The video device must contain a single pad. + * + * This is a convenience wrapper around __media_pipeline_stop(). + */ +void __video_device_pipeline_stop(struct video_device *vdev); + +/** + * video_device_pipeline_alloc_start - Mark a pipeline as streaming + * @vdev: Starting video device + * + * video_device_pipeline_alloc_start() is similar to video_device_pipeline_start() + * but instead of working on a given pipeline the function will use an + * existing pipeline if the video device is already part of a pipeline, or + * allocate a new pipeline. + * + * Calls to video_device_pipeline_alloc_start() must be matched with + * video_device_pipeline_stop(). + */ +__must_check int video_device_pipeline_alloc_start(struct video_device *vdev); + +/** + * video_device_pipeline - Get the media pipeline a video device is part of + * @vdev: The video device + * + * This function returns the media pipeline that a video device has been + * associated with when constructing the pipeline with + * video_device_pipeline_start(). The pointer remains valid until + * video_device_pipeline_stop() is called. + * + * Return: The media_pipeline the video device is part of, or NULL if the video + * device is not part of any pipeline. + * + * The video device must contain a single pad. + * + * This is a convenience wrapper around media_entity_pipeline(). + */ +struct media_pipeline *video_device_pipeline(struct video_device *vdev); + +#endif /* CONFIG_MEDIA_CONTROLLER */ + #endif /* _V4L2_DEV_H */ diff --git a/include/media/v4l2-fwnode.h b/include/media/v4l2-fwnode.h index 15e4ab672223..394d798f3dfa 100644 --- a/include/media/v4l2-fwnode.h +++ b/include/media/v4l2-fwnode.h @@ -45,10 +45,6 @@ struct v4l2_async_subdev; */ struct v4l2_fwnode_endpoint { struct fwnode_endpoint base; - /* - * Fields below this line will be zeroed by - * v4l2_fwnode_endpoint_parse() - */ enum v4l2_mbus_type bus_type; struct { struct v4l2_mbus_config_parallel parallel; diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h index 9689f38a0af1..2f80c9c818ed 100644 --- a/include/media/v4l2-subdev.h +++ b/include/media/v4l2-subdev.h @@ -358,7 +358,11 @@ struct v4l2_mbus_frame_desc_entry { } bus; }; -#define V4L2_FRAME_DESC_ENTRY_MAX 4 + /* + * If this number is too small, it should be dropped altogether and the + * API switched to a dynamic number of frame descriptor entries. + */ +#define V4L2_FRAME_DESC_ENTRY_MAX 8 /** * enum v4l2_mbus_frame_desc_type - media bus frame description type @@ -1046,6 +1050,8 @@ v4l2_subdev_get_pad_format(struct v4l2_subdev *sd, struct v4l2_subdev_state *state, unsigned int pad) { + if (WARN_ON(!state)) + return NULL; if (WARN_ON(pad >= sd->entity.num_pads)) pad = 0; return &state->pads[pad].try_fmt; @@ -1064,6 +1070,8 @@ v4l2_subdev_get_pad_crop(struct v4l2_subdev *sd, struct v4l2_subdev_state *state, unsigned int pad) { + if (WARN_ON(!state)) + return NULL; if (WARN_ON(pad >= sd->entity.num_pads)) pad = 0; return &state->pads[pad].try_crop; @@ -1082,6 +1090,8 @@ v4l2_subdev_get_pad_compose(struct v4l2_subdev *sd, struct v4l2_subdev_state *state, unsigned int pad) { + if (WARN_ON(!state)) + return NULL; if (WARN_ON(pad >= sd->entity.num_pads)) pad = 0; return &state->pads[pad].try_compose; diff --git a/include/net/9p/9p.h b/include/net/9p/9p.h index 24a509f559ee..13abe013af21 100644 --- a/include/net/9p/9p.h +++ b/include/net/9p/9p.h @@ -331,6 +331,9 @@ enum p9_qid_t { /* size of header for zero copy read/write */ #define P9_ZC_HDR_SZ 4096 +/* maximum length of an error string */ +#define P9_ERRMAX 128 + /** * struct p9_qid - file system entity information * @type: 8-bit type &p9_qid_t diff --git a/include/net/9p/transport.h b/include/net/9p/transport.h index ff842f963071..766ec07c9599 100644 --- a/include/net/9p/transport.h +++ b/include/net/9p/transport.h @@ -19,6 +19,10 @@ * @list: used to maintain a list of currently available transports * @name: the human-readable name of the transport * @maxsize: transport provided maximum packet size + * @pooled_rbuffers: currently only set for RDMA transport which pulls the + * response buffers from a shared pool, and accordingly + * we're less flexible when choosing the response message + * size in this case * @def: set if this transport should be considered the default * @create: member function to create a new connection on this transport * @close: member function to discard a connection on this transport @@ -38,6 +42,7 @@ struct p9_trans_module { struct list_head list; char *name; /* name of transport */ int maxsize; /* max message size of transport */ + bool pooled_rbuffers; int def; /* this transport should be default */ struct module *owner; int (*create)(struct p9_client *client, diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 8f780170e2f8..9f97f73615b6 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -37,16 +37,25 @@ struct genl_info; * do additional, common, filtering and return an error * @post_doit: called after an operation's doit callback, it may * undo operations done by pre_doit, for example release locks + * @module: pointer to the owning module (set to THIS_MODULE) * @mcgrps: multicast groups used by this family * @n_mcgrps: number of multicast groups * @resv_start_op: first operation for which reserved fields of the header - * can be validated, new families should leave this field at zero + * can be validated and policies are required (see below); + * new families should leave this field at zero * @mcgrp_offset: starting number of multicast group IDs in this family * (private) * @ops: the operations supported by this family * @n_ops: number of operations supported by this family * @small_ops: the small-struct operations supported by this family * @n_small_ops: number of small-struct operations supported by this family + * + * Attribute policies (the combination of @policy and @maxattr fields) + * can be attached at the family level or at the operation level. + * If both are present the per-operation policy takes precedence. + * For operations before @resv_start_op lack of policy means that the core + * will perform no attribute parsing or validation. For newer operations + * if policy is not provided core will reject all TLV attributes. */ struct genl_family { int id; /* private */ @@ -173,9 +182,9 @@ struct genl_ops { }; /** - * struct genl_info - info that is available during dumpit op call + * struct genl_dumpit_info - info that is available during dumpit op call * @family: generic netlink family - for internal genl code usage - * @ops: generic netlink ops - for internal genl code usage + * @op: generic netlink ops - for internal genl code usage * @attrs: netlink attributes */ struct genl_dumpit_info { @@ -354,6 +363,7 @@ int genlmsg_multicast_allns(const struct genl_family *family, /** * genlmsg_unicast - unicast a netlink message + * @net: network namespace to look up @portid in * @skb: netlink message as socket buffer * @portid: netlink portid of the destination socket */ @@ -373,7 +383,7 @@ static inline int genlmsg_reply(struct sk_buff *skb, struct genl_info *info) } /** - * gennlmsg_data - head of message payload + * genlmsg_data - head of message payload * @gnlh: genetlink message header */ static inline void *genlmsg_data(const struct genlmsghdr *gnlh) diff --git a/include/net/ieee802154_netdev.h b/include/net/ieee802154_netdev.h index a8994f307fc3..03b64bf876a4 100644 --- a/include/net/ieee802154_netdev.h +++ b/include/net/ieee802154_netdev.h @@ -185,21 +185,27 @@ static inline int ieee802154_sockaddr_check_size(struct sockaddr_ieee802154 *daddr, int len) { struct ieee802154_addr_sa *sa; + int ret = 0; sa = &daddr->addr; if (len < IEEE802154_MIN_NAMELEN) return -EINVAL; switch (sa->addr_type) { + case IEEE802154_ADDR_NONE: + break; case IEEE802154_ADDR_SHORT: if (len < IEEE802154_NAMELEN_SHORT) - return -EINVAL; + ret = -EINVAL; break; case IEEE802154_ADDR_LONG: if (len < IEEE802154_NAMELEN_LONG) - return -EINVAL; + ret = -EINVAL; + break; + default: + ret = -EINVAL; break; } - return 0; + return ret; } static inline void ieee802154_addr_from_sa(struct ieee802154_addr *a, diff --git a/include/net/ip.h b/include/net/ip.h index 038097c2a152..144bdfbb25af 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -563,7 +563,7 @@ static inline void iph_to_flow_copy_v4addrs(struct flow_keys *flow, BUILD_BUG_ON(offsetof(typeof(flow->addrs), v4addrs.dst) != offsetof(typeof(flow->addrs), v4addrs.src) + sizeof(flow->addrs.v4addrs.src)); - memcpy(&flow->addrs.v4addrs, &iph->saddr, sizeof(flow->addrs.v4addrs)); + memcpy(&flow->addrs.v4addrs, &iph->addrs, sizeof(flow->addrs.v4addrs)); flow->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; } diff --git a/include/net/ipv6.h b/include/net/ipv6.h index d664ba5812d8..d383c895592a 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -897,7 +897,7 @@ static inline void iph_to_flow_copy_v6addrs(struct flow_keys *flow, BUILD_BUG_ON(offsetof(typeof(flow->addrs), v6addrs.dst) != offsetof(typeof(flow->addrs), v6addrs.src) + sizeof(flow->addrs.v6addrs.src)); - memcpy(&flow->addrs.v6addrs, &iph->saddr, sizeof(flow->addrs.v6addrs)); + memcpy(&flow->addrs.v6addrs, &iph->addrs, sizeof(flow->addrs.v6addrs)); flow->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; } @@ -1182,6 +1182,8 @@ void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port, void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info); void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu); +void inet6_cleanup_sock(struct sock *sk); +void inet6_sock_destruct(struct sock *sk); int inet6_release(struct socket *sock); int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len); int inet6_getname(struct socket *sock, struct sockaddr *uaddr, diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h index 980daa6e1e3a..c81021ab07aa 100644 --- a/include/net/netfilter/nf_queue.h +++ b/include/net/netfilter/nf_queue.h @@ -43,7 +43,7 @@ void nf_queue_entry_free(struct nf_queue_entry *entry); static inline void init_hashrandom(u32 *jhash_initval) { while (*jhash_initval == 0) - *jhash_initval = prandom_u32(); + *jhash_initval = get_random_u32(); } static inline u32 hash_v4(const struct iphdr *iph, u32 initval) diff --git a/include/net/netlink.h b/include/net/netlink.h index 4418b1981e31..6bfa972f2fbf 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -181,6 +181,8 @@ enum { NLA_S64, NLA_BITFIELD32, NLA_REJECT, + NLA_BE16, + NLA_BE32, __NLA_TYPE_MAX, }; @@ -231,6 +233,7 @@ enum nla_policy_validation { * NLA_U32, NLA_U64, * NLA_S8, NLA_S16, * NLA_S32, NLA_S64, + * NLA_BE16, NLA_BE32, * NLA_MSECS Leaving the length field zero will verify the * given type fits, using it verifies minimum length * just like "All other" @@ -261,6 +264,8 @@ enum nla_policy_validation { * NLA_U16, * NLA_U32, * NLA_U64, + * NLA_BE16, + * NLA_BE32, * NLA_S8, * NLA_S16, * NLA_S32, @@ -317,19 +322,10 @@ struct nla_policy { u8 validation_type; u16 len; union { - const u32 bitfield32_valid; - const u32 mask; - const char *reject_message; - const struct nla_policy *nested_policy; - struct netlink_range_validation *range; - struct netlink_range_validation_signed *range_signed; - struct { - s16 min, max; - u8 network_byte_order:1; - }; - int (*validate)(const struct nlattr *attr, - struct netlink_ext_ack *extack); - /* This entry is special, and used for the attribute at index 0 + /** + * @strict_start_type: first attribute to validate strictly + * + * This entry is special, and used for the attribute at index 0 * only, and specifies special data about the policy, namely it * specifies the "boundary type" where strict length validation * starts for any attribute types >= this value, also, strict @@ -348,6 +344,19 @@ struct nla_policy { * was added to enforce strict validation from thereon. */ u16 strict_start_type; + + /* private: use NLA_POLICY_*() to set */ + const u32 bitfield32_valid; + const u32 mask; + const char *reject_message; + const struct nla_policy *nested_policy; + struct netlink_range_validation *range; + struct netlink_range_validation_signed *range_signed; + struct { + s16 min, max; + }; + int (*validate)(const struct nlattr *attr, + struct netlink_ext_ack *extack); }; }; @@ -369,6 +378,8 @@ struct nla_policy { (tp == NLA_U8 || tp == NLA_U16 || tp == NLA_U32 || tp == NLA_U64) #define __NLA_IS_SINT_TYPE(tp) \ (tp == NLA_S8 || tp == NLA_S16 || tp == NLA_S32 || tp == NLA_S64) +#define __NLA_IS_BEINT_TYPE(tp) \ + (tp == NLA_BE16 || tp == NLA_BE32) #define __NLA_ENSURE(condition) BUILD_BUG_ON_ZERO(!(condition)) #define NLA_ENSURE_UINT_TYPE(tp) \ @@ -382,6 +393,7 @@ struct nla_policy { #define NLA_ENSURE_INT_OR_BINARY_TYPE(tp) \ (__NLA_ENSURE(__NLA_IS_UINT_TYPE(tp) || \ __NLA_IS_SINT_TYPE(tp) || \ + __NLA_IS_BEINT_TYPE(tp) || \ tp == NLA_MSECS || \ tp == NLA_BINARY) + tp) #define NLA_ENSURE_NO_VALIDATION_PTR(tp) \ @@ -389,6 +401,8 @@ struct nla_policy { tp != NLA_REJECT && \ tp != NLA_NESTED && \ tp != NLA_NESTED_ARRAY) + tp) +#define NLA_ENSURE_BEINT_TYPE(tp) \ + (__NLA_ENSURE(__NLA_IS_BEINT_TYPE(tp)) + tp) #define NLA_POLICY_RANGE(tp, _min, _max) { \ .type = NLA_ENSURE_INT_OR_BINARY_TYPE(tp), \ @@ -419,14 +433,6 @@ struct nla_policy { .type = NLA_ENSURE_INT_OR_BINARY_TYPE(tp), \ .validation_type = NLA_VALIDATE_MAX, \ .max = _max, \ - .network_byte_order = 0, \ -} - -#define NLA_POLICY_MAX_BE(tp, _max) { \ - .type = NLA_ENSURE_UINT_TYPE(tp), \ - .validation_type = NLA_VALIDATE_MAX, \ - .max = _max, \ - .network_byte_order = 1, \ } #define NLA_POLICY_MASK(tp, _mask) { \ diff --git a/include/net/red.h b/include/net/red.h index 454ac2b65d8c..425364de0df7 100644 --- a/include/net/red.h +++ b/include/net/red.h @@ -363,7 +363,7 @@ static inline unsigned long red_calc_qavg(const struct red_parms *p, static inline u32 red_random(const struct red_parms *p) { - return reciprocal_divide(prandom_u32(), p->max_P_reciprocal); + return reciprocal_divide(get_random_u32(), p->max_P_reciprocal); } static inline int red_mark_probability(const struct red_parms *p, diff --git a/include/net/sock.h b/include/net/sock.h index 08038a385ef2..e0517ecc6531 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -323,7 +323,7 @@ struct sk_filter; * @sk_tskey: counter to disambiguate concurrent tstamp requests * @sk_zckey: counter to order MSG_ZEROCOPY notifications * @sk_socket: Identd and reporting IO signals - * @sk_user_data: RPC layer private data + * @sk_user_data: RPC layer private data. Write-protected by @sk_callback_lock. * @sk_frag: cached page frag * @sk_peek_off: current peek_offset value * @sk_send_head: front of stuff to transmit @@ -1889,6 +1889,13 @@ void sock_kfree_s(struct sock *sk, void *mem, int size); void sock_kzfree_s(struct sock *sk, void *mem, int size); void sk_send_sigurg(struct sock *sk); +static inline void sock_replace_proto(struct sock *sk, struct proto *proto) +{ + if (sk->sk_socket) + clear_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); + WRITE_ONCE(sk->sk_prot, proto); +} + struct sockcm_cookie { u64 transmit_time; u32 mark; @@ -2109,7 +2116,7 @@ static inline kuid_t sock_net_uid(const struct net *net, const struct sock *sk) static inline u32 net_tx_rndhash(void) { - u32 v = prandom_u32(); + u32 v = get_random_u32(); return v ?: 1; } @@ -2585,7 +2592,7 @@ static inline gfp_t gfp_any(void) static inline gfp_t gfp_memcg_charge(void) { - return in_softirq() ? GFP_NOWAIT : GFP_KERNEL; + return in_softirq() ? GFP_ATOMIC : GFP_KERNEL; } static inline long sock_rcvtimeo(const struct sock *sk, bool noblock) diff --git a/include/net/sock_reuseport.h b/include/net/sock_reuseport.h index 473b0b0fa4ab..efc9085c6892 100644 --- a/include/net/sock_reuseport.h +++ b/include/net/sock_reuseport.h @@ -43,21 +43,20 @@ struct sock *reuseport_migrate_sock(struct sock *sk, extern int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog); extern int reuseport_detach_prog(struct sock *sk); -static inline bool reuseport_has_conns(struct sock *sk, bool set) +static inline bool reuseport_has_conns(struct sock *sk) { struct sock_reuseport *reuse; bool ret = false; rcu_read_lock(); reuse = rcu_dereference(sk->sk_reuseport_cb); - if (reuse) { - if (set) - reuse->has_conns = 1; - ret = reuse->has_conns; - } + if (reuse && reuse->has_conns) + ret = true; rcu_read_unlock(); return ret; } +void reuseport_has_conns_set(struct sock *sk); + #endif /* _SOCK_REUSEPORT_H */ diff --git a/include/net/udp.h b/include/net/udp.h index 5ee88ddf79c3..fee053bcd17c 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -247,7 +247,7 @@ static inline bool udp_sk_bound_dev_eq(struct net *net, int bound_dev_if, } /* net/ipv4/udp.c */ -void udp_destruct_sock(struct sock *sk); +void udp_destruct_common(struct sock *sk); void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len); int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb); void udp_skb_destructor(struct sock *sk, struct sk_buff *skb); diff --git a/include/net/udplite.h b/include/net/udplite.h index 0143b373602e..299c14ce2bb9 100644 --- a/include/net/udplite.h +++ b/include/net/udplite.h @@ -25,14 +25,6 @@ static __inline__ int udplite_getfrag(void *from, char *to, int offset, return copy_from_iter_full(to, len, &msg->msg_iter) ? 0 : -EFAULT; } -/* Designate sk as UDP-Lite socket */ -static inline int udplite_sk_init(struct sock *sk) -{ - udp_init_sock(sk); - udp_sk(sk)->pcflag = UDPLITE_BIT; - return 0; -} - /* * Checksumming routines */ diff --git a/include/soc/at91/pm.h b/include/soc/at91/pm.h deleted file mode 100644 index 7a41e53a3ffa..000000000000 --- a/include/soc/at91/pm.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Atmel Power Management - * - * Copyright (C) 2020 Atmel - * - * Author: Lee Jones <lee.jones@linaro.org> - */ - -#ifndef __SOC_ATMEL_PM_H -#define __SOC_ATMEL_PM_H - -void at91_pinctrl_gpio_suspend(void); -void at91_pinctrl_gpio_resume(void); - -#endif /* __SOC_ATMEL_PM_H */ diff --git a/include/soc/at91/sama7-ddr.h b/include/soc/at91/sama7-ddr.h index 6ce3bd22f6c6..5ad7ac2e3a7c 100644 --- a/include/soc/at91/sama7-ddr.h +++ b/include/soc/at91/sama7-ddr.h @@ -26,7 +26,10 @@ #define DDR3PHY_PGSR (0x0C) /* DDR3PHY PHY General Status Register */ #define DDR3PHY_PGSR_IDONE (1 << 0) /* Initialization Done */ -#define DDR3PHY_ACIOCR (0x24) /* DDR3PHY AC I/O Configuration Register */ +#define DDR3PHY_ACDLLCR (0x14) /* DDR3PHY AC DLL Control Register */ +#define DDR3PHY_ACDLLCR_DLLSRST (1 << 30) /* DLL Soft Reset */ + +#define DDR3PHY_ACIOCR (0x24) /* DDR3PHY AC I/O Configuration Register */ #define DDR3PHY_ACIOCR_CSPDD_CS0 (1 << 18) /* CS#[0] Power Down Driver */ #define DDR3PHY_ACIOCR_CKPDD_CK0 (1 << 8) /* CK[0] Power Down Driver */ #define DDR3PHY_ACIORC_ACPDD (1 << 3) /* AC Power Down Driver */ diff --git a/include/soc/sifive/sifive_ccache.h b/include/soc/sifive/sifive_ccache.h new file mode 100644 index 000000000000..4d4ed49388a0 --- /dev/null +++ b/include/soc/sifive/sifive_ccache.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * SiFive Composable Cache Controller header file + * + */ + +#ifndef __SOC_SIFIVE_CCACHE_H +#define __SOC_SIFIVE_CCACHE_H + +extern int register_sifive_ccache_error_notifier(struct notifier_block *nb); +extern int unregister_sifive_ccache_error_notifier(struct notifier_block *nb); + +#define SIFIVE_CCACHE_ERR_TYPE_CE 0 +#define SIFIVE_CCACHE_ERR_TYPE_UE 1 + +#endif /* __SOC_SIFIVE_CCACHE_H */ diff --git a/include/soc/sifive/sifive_l2_cache.h b/include/soc/sifive/sifive_l2_cache.h deleted file mode 100644 index 92ade10ed67e..000000000000 --- a/include/soc/sifive/sifive_l2_cache.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * SiFive L2 Cache Controller header file - * - */ - -#ifndef __SOC_SIFIVE_L2_CACHE_H -#define __SOC_SIFIVE_L2_CACHE_H - -extern int register_sifive_l2_error_notifier(struct notifier_block *nb); -extern int unregister_sifive_l2_error_notifier(struct notifier_block *nb); - -#define SIFIVE_L2_ERR_TYPE_CE 0 -#define SIFIVE_L2_ERR_TYPE_UE 1 - -#endif /* __SOC_SIFIVE_L2_CACHE_H */ diff --git a/include/sound/control.h b/include/sound/control.h index eae443ba79ba..cc3dcc6cfb0f 100644 --- a/include/sound/control.h +++ b/include/sound/control.h @@ -138,6 +138,7 @@ int snd_ctl_remove(struct snd_card * card, struct snd_kcontrol * kcontrol); int snd_ctl_replace(struct snd_card *card, struct snd_kcontrol *kcontrol, bool add_on_replace); int snd_ctl_remove_id(struct snd_card * card, struct snd_ctl_elem_id *id); int snd_ctl_rename_id(struct snd_card * card, struct snd_ctl_elem_id *src_id, struct snd_ctl_elem_id *dst_id); +void snd_ctl_rename(struct snd_card *card, struct snd_kcontrol *kctl, const char *name); int snd_ctl_activate_id(struct snd_card *card, struct snd_ctl_elem_id *id, int active); struct snd_kcontrol *snd_ctl_find_numid(struct snd_card * card, unsigned int numid); struct snd_kcontrol *snd_ctl_find_id(struct snd_card * card, struct snd_ctl_elem_id *id); diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h index ddff03e546e9..35778f953a3f 100644 --- a/include/sound/hdaudio.h +++ b/include/sound/hdaudio.h @@ -592,11 +592,11 @@ int snd_hdac_get_stream_stripe_ctl(struct hdac_bus *bus, #define snd_hdac_stream_readb(dev, reg) \ snd_hdac_reg_readb((dev)->bus, (dev)->sd_addr + AZX_REG_ ## reg) #define snd_hdac_stream_readb_poll(dev, reg, val, cond, delay_us, timeout_us) \ - readb_poll_timeout((dev)->sd_addr + AZX_REG_ ## reg, val, cond, \ - delay_us, timeout_us) + read_poll_timeout_atomic(snd_hdac_reg_readb, val, cond, delay_us, timeout_us, \ + false, (dev)->bus, (dev)->sd_addr + AZX_REG_ ## reg) #define snd_hdac_stream_readl_poll(dev, reg, val, cond, delay_us, timeout_us) \ - readl_poll_timeout((dev)->sd_addr + AZX_REG_ ## reg, val, cond, \ - delay_us, timeout_us) + read_poll_timeout_atomic(snd_hdac_reg_readl, val, cond, delay_us, timeout_us, \ + false, (dev)->bus, (dev)->sd_addr + AZX_REG_ ## reg) /* update a register, pass without AZX_REG_ prefix */ #define snd_hdac_stream_updatel(dev, reg, mask, val) \ diff --git a/include/sound/simple_card_utils.h b/include/sound/simple_card_utils.h index a0b827f0c2f6..25e049f44178 100644 --- a/include/sound/simple_card_utils.h +++ b/include/sound/simple_card_utils.h @@ -177,6 +177,7 @@ void asoc_simple_convert_fixup(struct asoc_simple_data *data, struct snd_pcm_hw_params *params); void asoc_simple_parse_convert(struct device_node *np, char *prefix, struct asoc_simple_data *data); +bool asoc_simple_is_convert_required(const struct asoc_simple_data *data); int asoc_simple_parse_routing(struct snd_soc_card *card, char *prefix); diff --git a/include/sound/sof/info.h b/include/sound/sof/info.h index 65e86e4e9fd8..75193850ead0 100644 --- a/include/sound/sof/info.h +++ b/include/sound/sof/info.h @@ -36,6 +36,10 @@ enum sof_ipc_ext_data { SOF_IPC_EXT_USER_ABI_INFO = 4, }; +/* Build u32 number in format MMmmmppp */ +#define SOF_FW_VER(MAJOR, MINOR, PATCH) ((uint32_t)( \ + ((MAJOR) << 24) | ((MINOR) << 12) | (PATCH))) + /* FW version - SOF_IPC_GLB_VERSION */ struct sof_ipc_fw_version { struct sof_ipc_hdr hdr; diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index f1e922237736..c6b372401c27 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -1578,9 +1578,10 @@ TRACE_EVENT_CONDITION(f2fs_lookup_extent_tree_end, TRACE_EVENT(f2fs_update_extent_tree_range, TP_PROTO(struct inode *inode, unsigned int pgofs, block_t blkaddr, - unsigned int len), + unsigned int len, + unsigned int c_len), - TP_ARGS(inode, pgofs, blkaddr, len), + TP_ARGS(inode, pgofs, blkaddr, len, c_len), TP_STRUCT__entry( __field(dev_t, dev) @@ -1588,6 +1589,7 @@ TRACE_EVENT(f2fs_update_extent_tree_range, __field(unsigned int, pgofs) __field(u32, blk) __field(unsigned int, len) + __field(unsigned int, c_len) ), TP_fast_assign( @@ -1596,14 +1598,17 @@ TRACE_EVENT(f2fs_update_extent_tree_range, __entry->pgofs = pgofs; __entry->blk = blkaddr; __entry->len = len; + __entry->c_len = c_len; ), TP_printk("dev = (%d,%d), ino = %lu, pgofs = %u, " - "blkaddr = %u, len = %u", + "blkaddr = %u, len = %u, " + "c_len = %u", show_dev_ino(__entry), __entry->pgofs, __entry->blk, - __entry->len) + __entry->len, + __entry->c_len) ); TRACE_EVENT(f2fs_shrink_extent_tree, @@ -1823,7 +1828,10 @@ TRACE_EVENT(f2fs_iostat, __field(unsigned long long, app_bio) __field(unsigned long long, app_wio) __field(unsigned long long, app_mio) + __field(unsigned long long, app_bcdio) + __field(unsigned long long, app_mcdio) __field(unsigned long long, fs_dio) + __field(unsigned long long, fs_cdio) __field(unsigned long long, fs_nio) __field(unsigned long long, fs_mio) __field(unsigned long long, fs_gc_dio) @@ -1835,6 +1843,8 @@ TRACE_EVENT(f2fs_iostat, __field(unsigned long long, app_brio) __field(unsigned long long, app_rio) __field(unsigned long long, app_mrio) + __field(unsigned long long, app_bcrio) + __field(unsigned long long, app_mcrio) __field(unsigned long long, fs_drio) __field(unsigned long long, fs_gdrio) __field(unsigned long long, fs_cdrio) @@ -1849,7 +1859,10 @@ TRACE_EVENT(f2fs_iostat, __entry->app_bio = iostat[APP_BUFFERED_IO]; __entry->app_wio = iostat[APP_WRITE_IO]; __entry->app_mio = iostat[APP_MAPPED_IO]; + __entry->app_bcdio = iostat[APP_BUFFERED_CDATA_IO]; + __entry->app_mcdio = iostat[APP_MAPPED_CDATA_IO]; __entry->fs_dio = iostat[FS_DATA_IO]; + __entry->fs_cdio = iostat[FS_CDATA_IO]; __entry->fs_nio = iostat[FS_NODE_IO]; __entry->fs_mio = iostat[FS_META_IO]; __entry->fs_gc_dio = iostat[FS_GC_DATA_IO]; @@ -1861,6 +1874,8 @@ TRACE_EVENT(f2fs_iostat, __entry->app_brio = iostat[APP_BUFFERED_READ_IO]; __entry->app_rio = iostat[APP_READ_IO]; __entry->app_mrio = iostat[APP_MAPPED_READ_IO]; + __entry->app_bcrio = iostat[APP_BUFFERED_CDATA_READ_IO]; + __entry->app_mcrio = iostat[APP_MAPPED_CDATA_READ_IO]; __entry->fs_drio = iostat[FS_DATA_READ_IO]; __entry->fs_gdrio = iostat[FS_GDATA_READ_IO]; __entry->fs_cdrio = iostat[FS_CDATA_READ_IO]; @@ -1870,20 +1885,24 @@ TRACE_EVENT(f2fs_iostat, ), TP_printk("dev = (%d,%d), " - "app [write=%llu (direct=%llu, buffered=%llu), mapped=%llu], " - "fs [data=%llu, node=%llu, meta=%llu, discard=%llu], " + "app [write=%llu (direct=%llu, buffered=%llu), mapped=%llu, " + "compr(buffered=%llu, mapped=%llu)], " + "fs [data=%llu, cdata=%llu, node=%llu, meta=%llu, discard=%llu], " "gc [data=%llu, node=%llu], " "cp [data=%llu, node=%llu, meta=%llu], " "app [read=%llu (direct=%llu, buffered=%llu), mapped=%llu], " - "fs [data=%llu, (gc_data=%llu, compr_data=%llu), " + "compr(buffered=%llu, mapped=%llu)], " + "fs [data=%llu, (gc_data=%llu, cdata=%llu), " "node=%llu, meta=%llu]", show_dev(__entry->dev), __entry->app_wio, __entry->app_dio, - __entry->app_bio, __entry->app_mio, __entry->fs_dio, + __entry->app_bio, __entry->app_mio, __entry->app_bcdio, + __entry->app_mcdio, __entry->fs_dio, __entry->fs_cdio, __entry->fs_nio, __entry->fs_mio, __entry->fs_discard, __entry->fs_gc_dio, __entry->fs_gc_nio, __entry->fs_cp_dio, __entry->fs_cp_nio, __entry->fs_cp_mio, __entry->app_rio, __entry->app_drio, __entry->app_brio, - __entry->app_mrio, __entry->fs_drio, __entry->fs_gdrio, + __entry->app_mrio, __entry->app_bcrio, __entry->app_mcrio, + __entry->fs_drio, __entry->fs_gdrio, __entry->fs_cdrio, __entry->fs_nrio, __entry->fs_mrio) ); diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h index d651f3437367..935af4947917 100644 --- a/include/trace/events/huge_memory.h +++ b/include/trace/events/huge_memory.h @@ -11,11 +11,14 @@ EM( SCAN_FAIL, "failed") \ EM( SCAN_SUCCEED, "succeeded") \ EM( SCAN_PMD_NULL, "pmd_null") \ + EM( SCAN_PMD_NONE, "pmd_none") \ + EM( SCAN_PMD_MAPPED, "page_pmd_mapped") \ EM( SCAN_EXCEED_NONE_PTE, "exceed_none_pte") \ EM( SCAN_EXCEED_SWAP_PTE, "exceed_swap_pte") \ EM( SCAN_EXCEED_SHARED_PTE, "exceed_shared_pte") \ EM( SCAN_PTE_NON_PRESENT, "pte_non_present") \ EM( SCAN_PTE_UFFD_WP, "pte_uffd_wp") \ + EM( SCAN_PTE_MAPPED_HUGEPAGE, "pte_mapped_hugepage") \ EM( SCAN_PAGE_RO, "no_writable_page") \ EM( SCAN_LACK_REFERENCED_PAGE, "lack_referenced_page") \ EM( SCAN_PAGE_NULL, "page_null") \ @@ -166,5 +169,39 @@ TRACE_EVENT(mm_collapse_huge_page_swapin, __entry->ret) ); +TRACE_EVENT(mm_khugepaged_scan_file, + + TP_PROTO(struct mm_struct *mm, struct page *page, const char *filename, + int present, int swap, int result), + + TP_ARGS(mm, page, filename, present, swap, result), + + TP_STRUCT__entry( + __field(struct mm_struct *, mm) + __field(unsigned long, pfn) + __string(filename, filename) + __field(int, present) + __field(int, swap) + __field(int, result) + ), + + TP_fast_assign( + __entry->mm = mm; + __entry->pfn = page ? page_to_pfn(page) : -1; + __assign_str(filename, filename); + __entry->present = present; + __entry->swap = swap; + __entry->result = result; + ), + + TP_printk("mm=%p, scan_pfn=0x%lx, filename=%s, present=%d, swap=%d, result=%s", + __entry->mm, + __entry->pfn, + __get_str(filename), + __entry->present, + __entry->swap, + __print_symbolic(__entry->result, SCAN_STATUS)) +); + #endif /* __HUGE_MEMORY_H */ #include <trace/define_trace.h> diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h index 4cb51ace600d..243073cfc29d 100644 --- a/include/trace/events/kmem.h +++ b/include/trace/events/kmem.h @@ -9,16 +9,15 @@ #include <linux/tracepoint.h> #include <trace/events/mmflags.h> -DECLARE_EVENT_CLASS(kmem_alloc, +TRACE_EVENT(kmem_cache_alloc, TP_PROTO(unsigned long call_site, const void *ptr, struct kmem_cache *s, - size_t bytes_req, - size_t bytes_alloc, - gfp_t gfp_flags), + gfp_t gfp_flags, + int node), - TP_ARGS(call_site, ptr, s, bytes_req, bytes_alloc, gfp_flags), + TP_ARGS(call_site, ptr, s, gfp_flags, node), TP_STRUCT__entry( __field( unsigned long, call_site ) @@ -26,56 +25,42 @@ DECLARE_EVENT_CLASS(kmem_alloc, __field( size_t, bytes_req ) __field( size_t, bytes_alloc ) __field( unsigned long, gfp_flags ) + __field( int, node ) __field( bool, accounted ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; - __entry->bytes_req = bytes_req; - __entry->bytes_alloc = bytes_alloc; + __entry->bytes_req = s->object_size; + __entry->bytes_alloc = s->size; __entry->gfp_flags = (__force unsigned long)gfp_flags; + __entry->node = node; __entry->accounted = IS_ENABLED(CONFIG_MEMCG_KMEM) ? ((gfp_flags & __GFP_ACCOUNT) || - (s && s->flags & SLAB_ACCOUNT)) : false; + (s->flags & SLAB_ACCOUNT)) : false; ), - TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s accounted=%s", + TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d accounted=%s", (void *)__entry->call_site, __entry->ptr, __entry->bytes_req, __entry->bytes_alloc, show_gfp_flags(__entry->gfp_flags), + __entry->node, __entry->accounted ? "true" : "false") ); -DEFINE_EVENT(kmem_alloc, kmalloc, - - TP_PROTO(unsigned long call_site, const void *ptr, struct kmem_cache *s, - size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags), - - TP_ARGS(call_site, ptr, s, bytes_req, bytes_alloc, gfp_flags) -); - -DEFINE_EVENT(kmem_alloc, kmem_cache_alloc, - - TP_PROTO(unsigned long call_site, const void *ptr, struct kmem_cache *s, - size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags), - - TP_ARGS(call_site, ptr, s, bytes_req, bytes_alloc, gfp_flags) -); - -DECLARE_EVENT_CLASS(kmem_alloc_node, +TRACE_EVENT(kmalloc, TP_PROTO(unsigned long call_site, const void *ptr, - struct kmem_cache *s, size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags, int node), - TP_ARGS(call_site, ptr, s, bytes_req, bytes_alloc, gfp_flags, node), + TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node), TP_STRUCT__entry( __field( unsigned long, call_site ) @@ -84,7 +69,6 @@ DECLARE_EVENT_CLASS(kmem_alloc_node, __field( size_t, bytes_alloc ) __field( unsigned long, gfp_flags ) __field( int, node ) - __field( bool, accounted ) ), TP_fast_assign( @@ -94,9 +78,6 @@ DECLARE_EVENT_CLASS(kmem_alloc_node, __entry->bytes_alloc = bytes_alloc; __entry->gfp_flags = (__force unsigned long)gfp_flags; __entry->node = node; - __entry->accounted = IS_ENABLED(CONFIG_MEMCG_KMEM) ? - ((gfp_flags & __GFP_ACCOUNT) || - (s && s->flags & SLAB_ACCOUNT)) : false; ), TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d accounted=%s", @@ -106,25 +87,8 @@ DECLARE_EVENT_CLASS(kmem_alloc_node, __entry->bytes_alloc, show_gfp_flags(__entry->gfp_flags), __entry->node, - __entry->accounted ? "true" : "false") -); - -DEFINE_EVENT(kmem_alloc_node, kmalloc_node, - - TP_PROTO(unsigned long call_site, const void *ptr, - struct kmem_cache *s, size_t bytes_req, size_t bytes_alloc, - gfp_t gfp_flags, int node), - - TP_ARGS(call_site, ptr, s, bytes_req, bytes_alloc, gfp_flags, node) -); - -DEFINE_EVENT(kmem_alloc_node, kmem_cache_alloc_node, - - TP_PROTO(unsigned long call_site, const void *ptr, - struct kmem_cache *s, size_t bytes_req, size_t bytes_alloc, - gfp_t gfp_flags, int node), - - TP_ARGS(call_site, ptr, s, bytes_req, bytes_alloc, gfp_flags, node) + (IS_ENABLED(CONFIG_MEMCG_KMEM) && + (__entry->gfp_flags & (__force unsigned long)__GFP_ACCOUNT)) ? "true" : "false") ); TRACE_EVENT(kfree, @@ -149,20 +113,20 @@ TRACE_EVENT(kfree, TRACE_EVENT(kmem_cache_free, - TP_PROTO(unsigned long call_site, const void *ptr, const char *name), + TP_PROTO(unsigned long call_site, const void *ptr, const struct kmem_cache *s), - TP_ARGS(call_site, ptr, name), + TP_ARGS(call_site, ptr, s), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) - __string( name, name ) + __string( name, s->name ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; - __assign_str(name, name); + __assign_str(name, s->name); ), TP_printk("call_site=%pS ptr=%p name=%s", diff --git a/include/trace/events/maple_tree.h b/include/trace/events/maple_tree.h new file mode 100644 index 000000000000..2be403bdc2bd --- /dev/null +++ b/include/trace/events/maple_tree.h @@ -0,0 +1,123 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM maple_tree + +#if !defined(_TRACE_MM_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_MM_H + + +#include <linux/tracepoint.h> + +struct ma_state; + +TRACE_EVENT(ma_op, + + TP_PROTO(const char *fn, struct ma_state *mas), + + TP_ARGS(fn, mas), + + TP_STRUCT__entry( + __field(const char *, fn) + __field(unsigned long, min) + __field(unsigned long, max) + __field(unsigned long, index) + __field(unsigned long, last) + __field(void *, node) + ), + + TP_fast_assign( + __entry->fn = fn; + __entry->min = mas->min; + __entry->max = mas->max; + __entry->index = mas->index; + __entry->last = mas->last; + __entry->node = mas->node; + ), + + TP_printk("%s\tNode: %p (%lu %lu) range: %lu-%lu", + __entry->fn, + (void *) __entry->node, + (unsigned long) __entry->min, + (unsigned long) __entry->max, + (unsigned long) __entry->index, + (unsigned long) __entry->last + ) +) +TRACE_EVENT(ma_read, + + TP_PROTO(const char *fn, struct ma_state *mas), + + TP_ARGS(fn, mas), + + TP_STRUCT__entry( + __field(const char *, fn) + __field(unsigned long, min) + __field(unsigned long, max) + __field(unsigned long, index) + __field(unsigned long, last) + __field(void *, node) + ), + + TP_fast_assign( + __entry->fn = fn; + __entry->min = mas->min; + __entry->max = mas->max; + __entry->index = mas->index; + __entry->last = mas->last; + __entry->node = mas->node; + ), + + TP_printk("%s\tNode: %p (%lu %lu) range: %lu-%lu", + __entry->fn, + (void *) __entry->node, + (unsigned long) __entry->min, + (unsigned long) __entry->max, + (unsigned long) __entry->index, + (unsigned long) __entry->last + ) +) + +TRACE_EVENT(ma_write, + + TP_PROTO(const char *fn, struct ma_state *mas, unsigned long piv, + void *val), + + TP_ARGS(fn, mas, piv, val), + + TP_STRUCT__entry( + __field(const char *, fn) + __field(unsigned long, min) + __field(unsigned long, max) + __field(unsigned long, index) + __field(unsigned long, last) + __field(unsigned long, piv) + __field(void *, val) + __field(void *, node) + ), + + TP_fast_assign( + __entry->fn = fn; + __entry->min = mas->min; + __entry->max = mas->max; + __entry->index = mas->index; + __entry->last = mas->last; + __entry->piv = piv; + __entry->val = val; + __entry->node = mas->node; + ), + + TP_printk("%s\tNode %p (%lu %lu) range:%lu-%lu piv (%lu) val %p", + __entry->fn, + (void *) __entry->node, + (unsigned long) __entry->min, + (unsigned long) __entry->max, + (unsigned long) __entry->index, + (unsigned long) __entry->last, + (unsigned long) __entry->piv, + (void *) __entry->val + ) +) +#endif /* _TRACE_MM_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/include/trace/events/mmap.h b/include/trace/events/mmap.h index 4661f7ba07c0..216de5f03621 100644 --- a/include/trace/events/mmap.h +++ b/include/trace/events/mmap.h @@ -42,6 +42,79 @@ TRACE_EVENT(vm_unmapped_area, __entry->low_limit, __entry->high_limit, __entry->align_mask, __entry->align_offset) ); + +TRACE_EVENT(vma_mas_szero, + TP_PROTO(struct maple_tree *mt, unsigned long start, + unsigned long end), + + TP_ARGS(mt, start, end), + + TP_STRUCT__entry( + __field(struct maple_tree *, mt) + __field(unsigned long, start) + __field(unsigned long, end) + ), + + TP_fast_assign( + __entry->mt = mt; + __entry->start = start; + __entry->end = end; + ), + + TP_printk("mt_mod %p, (NULL), SNULL, %lu, %lu,", + __entry->mt, + (unsigned long) __entry->start, + (unsigned long) __entry->end + ) +); + +TRACE_EVENT(vma_store, + TP_PROTO(struct maple_tree *mt, struct vm_area_struct *vma), + + TP_ARGS(mt, vma), + + TP_STRUCT__entry( + __field(struct maple_tree *, mt) + __field(struct vm_area_struct *, vma) + __field(unsigned long, vm_start) + __field(unsigned long, vm_end) + ), + + TP_fast_assign( + __entry->mt = mt; + __entry->vma = vma; + __entry->vm_start = vma->vm_start; + __entry->vm_end = vma->vm_end - 1; + ), + + TP_printk("mt_mod %p, (%p), STORE, %lu, %lu,", + __entry->mt, __entry->vma, + (unsigned long) __entry->vm_start, + (unsigned long) __entry->vm_end + ) +); + + +TRACE_EVENT(exit_mmap, + TP_PROTO(struct mm_struct *mm), + + TP_ARGS(mm), + + TP_STRUCT__entry( + __field(struct mm_struct *, mm) + __field(struct maple_tree *, mt) + ), + + TP_fast_assign( + __entry->mm = mm; + __entry->mt = &mm->mm_mt; + ), + + TP_printk("mt_mod %p, DESTROY\n", + __entry->mt + ) +); + #endif /* This part must be outside protection */ diff --git a/include/trace/events/watchdog.h b/include/trace/events/watchdog.h new file mode 100644 index 000000000000..beb9bb3424c8 --- /dev/null +++ b/include/trace/events/watchdog.h @@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM watchdog + +#if !defined(_TRACE_WATCHDOG_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_WATCHDOG_H + +#include <linux/watchdog.h> +#include <linux/tracepoint.h> + +DECLARE_EVENT_CLASS(watchdog_template, + + TP_PROTO(struct watchdog_device *wdd, int err), + + TP_ARGS(wdd, err), + + TP_STRUCT__entry( + __field(int, id) + __field(int, err) + ), + + TP_fast_assign( + __entry->id = wdd->id; + __entry->err = err; + ), + + TP_printk("watchdog%d err=%d", __entry->id, __entry->err) +); + +DEFINE_EVENT(watchdog_template, watchdog_start, + TP_PROTO(struct watchdog_device *wdd, int err), + TP_ARGS(wdd, err)); + +DEFINE_EVENT(watchdog_template, watchdog_ping, + TP_PROTO(struct watchdog_device *wdd, int err), + TP_ARGS(wdd, err)); + +DEFINE_EVENT(watchdog_template, watchdog_stop, + TP_PROTO(struct watchdog_device *wdd, int err), + TP_ARGS(wdd, err)); + +TRACE_EVENT(watchdog_set_timeout, + + TP_PROTO(struct watchdog_device *wdd, unsigned int timeout, int err), + + TP_ARGS(wdd, timeout, err), + + TP_STRUCT__entry( + __field(int, id) + __field(unsigned int, timeout) + __field(int, err) + ), + + TP_fast_assign( + __entry->id = wdd->id; + __entry->timeout = timeout; + __entry->err = err; + ), + + TP_printk("watchdog%d timeout=%u err=%d", __entry->id, __entry->timeout, __entry->err) +); + +#endif /* !defined(_TRACE_WATCHDOG_H) || defined(TRACE_HEADER_MULTI_READ) */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/include/uapi/asm-generic/hugetlb_encode.h b/include/uapi/asm-generic/hugetlb_encode.h index 4f3d5aaa11f5..de687009bfe5 100644 --- a/include/uapi/asm-generic/hugetlb_encode.h +++ b/include/uapi/asm-generic/hugetlb_encode.h @@ -20,18 +20,18 @@ #define HUGETLB_FLAG_ENCODE_SHIFT 26 #define HUGETLB_FLAG_ENCODE_MASK 0x3f -#define HUGETLB_FLAG_ENCODE_16KB (14 << HUGETLB_FLAG_ENCODE_SHIFT) -#define HUGETLB_FLAG_ENCODE_64KB (16 << HUGETLB_FLAG_ENCODE_SHIFT) -#define HUGETLB_FLAG_ENCODE_512KB (19 << HUGETLB_FLAG_ENCODE_SHIFT) -#define HUGETLB_FLAG_ENCODE_1MB (20 << HUGETLB_FLAG_ENCODE_SHIFT) -#define HUGETLB_FLAG_ENCODE_2MB (21 << HUGETLB_FLAG_ENCODE_SHIFT) -#define HUGETLB_FLAG_ENCODE_8MB (23 << HUGETLB_FLAG_ENCODE_SHIFT) -#define HUGETLB_FLAG_ENCODE_16MB (24 << HUGETLB_FLAG_ENCODE_SHIFT) -#define HUGETLB_FLAG_ENCODE_32MB (25 << HUGETLB_FLAG_ENCODE_SHIFT) -#define HUGETLB_FLAG_ENCODE_256MB (28 << HUGETLB_FLAG_ENCODE_SHIFT) -#define HUGETLB_FLAG_ENCODE_512MB (29 << HUGETLB_FLAG_ENCODE_SHIFT) -#define HUGETLB_FLAG_ENCODE_1GB (30 << HUGETLB_FLAG_ENCODE_SHIFT) -#define HUGETLB_FLAG_ENCODE_2GB (31 << HUGETLB_FLAG_ENCODE_SHIFT) -#define HUGETLB_FLAG_ENCODE_16GB (34 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_16KB (14U << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_64KB (16U << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_512KB (19U << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_1MB (20U << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_2MB (21U << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_8MB (23U << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_16MB (24U << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_32MB (25U << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_256MB (28U << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_512MB (29U << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_1GB (30U << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_2GB (31U << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_16GB (34U << HUGETLB_FLAG_ENCODE_SHIFT) #endif /* _ASM_GENERIC_HUGETLB_ENCODE_H_ */ diff --git a/include/uapi/asm-generic/mman-common.h b/include/uapi/asm-generic/mman-common.h index 6c1aa92a92e4..6ce1f1ceb432 100644 --- a/include/uapi/asm-generic/mman-common.h +++ b/include/uapi/asm-generic/mman-common.h @@ -77,6 +77,8 @@ #define MADV_DONTNEED_LOCKED 24 /* like DONTNEED, but drop locked pages too */ +#define MADV_COLLAPSE 25 /* Synchronous hugepage collapse */ + /* compatibility flags */ #define MAP_FILE 0 diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index 7ee65c0b4f70..0d93ec132ebb 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -763,6 +763,8 @@ struct drm_amdgpu_cs_chunk_data { #define AMDGPU_INFO_FW_MES_KIQ 0x19 /* Subquery id: Query MES firmware version */ #define AMDGPU_INFO_FW_MES 0x1a + /* Subquery id: Query IMU firmware version */ + #define AMDGPU_INFO_FW_IMU 0x1b /* number of bytes moved for TTM migration */ #define AMDGPU_INFO_NUM_BYTES_MOVED 0x0f diff --git a/include/uapi/drm/panfrost_drm.h b/include/uapi/drm/panfrost_drm.h index eac87310b348..9f231d40a146 100644 --- a/include/uapi/drm/panfrost_drm.h +++ b/include/uapi/drm/panfrost_drm.h @@ -235,25 +235,29 @@ struct drm_panfrost_madvise { #define PANFROSTDUMP_BUF_BO (PANFROSTDUMP_BUF_BOMAP + 1) #define PANFROSTDUMP_BUF_TRAILER (PANFROSTDUMP_BUF_BO + 1) +/* + * This structure is the native endianness of the dumping machine, tools can + * detect the endianness by looking at the value in 'magic'. + */ struct panfrost_dump_object_header { - __le32 magic; - __le32 type; - __le32 file_size; - __le32 file_offset; + __u32 magic; + __u32 type; + __u32 file_size; + __u32 file_offset; union { - struct pan_reg_hdr { - __le64 jc; - __le32 gpu_id; - __le32 major; - __le32 minor; - __le64 nbos; + struct { + __u64 jc; + __u32 gpu_id; + __u32 major; + __u32 minor; + __u64 nbos; } reghdr; - struct pan_bomap_hdr { - __le32 valid; - __le64 iova; - __le32 data[2]; + struct { + __u32 valid; + __u64 iova; + __u32 data[2]; } bomap; /* @@ -261,14 +265,14 @@ struct panfrost_dump_object_header { * with new fields and also keep it 512-byte aligned */ - __le32 sizer[496]; + __u32 sizer[496]; }; }; /* Registers object, an array of these */ struct panfrost_dump_registers { - __le32 reg; - __le32 value; + __u32 reg; + __u32 value; }; #if defined(__cplusplus) diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index 7c1dc818b1d5..d676ed2b246e 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -187,7 +187,7 @@ #define AUDIT_MAX_KEY_LEN 256 #define AUDIT_BITMASK_SIZE 64 #define AUDIT_WORD(nr) ((__u32)((nr)/32)) -#define AUDIT_BIT(nr) (1 << ((nr) - AUDIT_WORD(nr)*32)) +#define AUDIT_BIT(nr) (1U << ((nr) - AUDIT_WORD(nr)*32)) #define AUDIT_SYSCALL_CLASSES 16 #define AUDIT_CLASS_DIR_WRITE 0 diff --git a/include/uapi/linux/capability.h b/include/uapi/linux/capability.h index 463d1ba2232a..3d61a0ae055d 100644 --- a/include/uapi/linux/capability.h +++ b/include/uapi/linux/capability.h @@ -426,7 +426,7 @@ struct vfs_ns_cap_data { */ #define CAP_TO_INDEX(x) ((x) >> 5) /* 1 << 5 == bits in __u32 */ -#define CAP_TO_MASK(x) (1 << ((x) & 31)) /* mask for indexed __u32 */ +#define CAP_TO_MASK(x) (1U << ((x) & 31)) /* mask for indexed __u32 */ #endif /* _UAPI_LINUX_CAPABILITY_H */ diff --git a/include/uapi/linux/cec-funcs.h b/include/uapi/linux/cec-funcs.h index c3baaea0b8ef..d58fa1cdcb08 100644 --- a/include/uapi/linux/cec-funcs.h +++ b/include/uapi/linux/cec-funcs.h @@ -1568,6 +1568,20 @@ static inline void cec_ops_request_short_audio_descriptor(const struct cec_msg * } } +static inline void cec_msg_set_audio_volume_level(struct cec_msg *msg, + __u8 audio_volume_level) +{ + msg->len = 3; + msg->msg[1] = CEC_MSG_SET_AUDIO_VOLUME_LEVEL; + msg->msg[2] = audio_volume_level; +} + +static inline void cec_ops_set_audio_volume_level(const struct cec_msg *msg, + __u8 *audio_volume_level) +{ + *audio_volume_level = msg->msg[2]; +} + /* Audio Rate Control Feature */ static inline void cec_msg_set_audio_rate(struct cec_msg *msg, diff --git a/include/uapi/linux/cec.h b/include/uapi/linux/cec.h index 1d48da926216..b8e071abaea5 100644 --- a/include/uapi/linux/cec.h +++ b/include/uapi/linux/cec.h @@ -768,6 +768,7 @@ struct cec_event { #define CEC_OP_FEAT_DEV_HAS_SET_AUDIO_RATE 0x08 #define CEC_OP_FEAT_DEV_SINK_HAS_ARC_TX 0x04 #define CEC_OP_FEAT_DEV_SOURCE_HAS_ARC_RX 0x02 +#define CEC_OP_FEAT_DEV_HAS_SET_AUDIO_VOLUME_LEVEL 0x01 #define CEC_MSG_GIVE_FEATURES 0xa5 /* HDMI 2.0 */ @@ -1059,6 +1060,7 @@ struct cec_event { #define CEC_OP_AUD_FMT_ID_CEA861 0 #define CEC_OP_AUD_FMT_ID_CEA861_CXT 1 +#define CEC_MSG_SET_AUDIO_VOLUME_LEVEL 0x73 /* Audio Rate Control Feature */ #define CEC_MSG_SET_AUDIO_RATE 0x9a diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index d6ccee961891..76ee8f9e024a 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -194,6 +194,9 @@ * - add FUSE_SECURITY_CTX init flag * - add security context to create, mkdir, symlink, and mknod requests * - add FUSE_HAS_INODE_DAX, FUSE_ATTR_DAX + * + * 7.37 + * - add FUSE_TMPFILE */ #ifndef _LINUX_FUSE_H @@ -229,7 +232,7 @@ #define FUSE_KERNEL_VERSION 7 /** Minor version number of this interface */ -#define FUSE_KERNEL_MINOR_VERSION 36 +#define FUSE_KERNEL_MINOR_VERSION 37 /** The node ID of the root inode */ #define FUSE_ROOT_ID 1 @@ -537,6 +540,7 @@ enum fuse_opcode { FUSE_SETUPMAPPING = 48, FUSE_REMOVEMAPPING = 49, FUSE_SYNCFS = 50, + FUSE_TMPFILE = 51, /* CUSE specific operations */ CUSE_INIT = 4096, diff --git a/include/uapi/linux/idxd.h b/include/uapi/linux/idxd.h index 095299c75828..2b9e7feba3f3 100644 --- a/include/uapi/linux/idxd.h +++ b/include/uapi/linux/idxd.h @@ -29,6 +29,7 @@ enum idxd_scmd_stat { IDXD_SCMD_WQ_NO_SIZE = 0x800e0000, IDXD_SCMD_WQ_NO_PRIV = 0x800f0000, IDXD_SCMD_WQ_IRQ_ERR = 0x80100000, + IDXD_SCMD_WQ_USER_NO_IOMMU = 0x80110000, }; #define IDXD_SCMD_SOFTERR_MASK 0x80000000 diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index f243ce665f74..07a4cb149305 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -20,6 +20,7 @@ #define _UAPI_LINUX_IN_H #include <linux/types.h> +#include <linux/stddef.h> #include <linux/libc-compat.h> #include <linux/socket.h> diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index dff8e7f17074..7ad931a32970 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -862,6 +862,7 @@ #define ABS_TOOL_WIDTH 0x1c #define ABS_VOLUME 0x20 +#define ABS_PROFILE 0x21 #define ABS_MISC 0x28 diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index ab7458033ee3..2df3225b562f 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -222,7 +222,7 @@ enum io_uring_op { /* * sqe->uring_cmd_flags - * IORING_URING_CMD_FIXED use registered buffer; pass thig flag + * IORING_URING_CMD_FIXED use registered buffer; pass this flag * along with setting sqe->buf_index. */ #define IORING_URING_CMD_FIXED (1U << 0) diff --git a/include/uapi/linux/ip.h b/include/uapi/linux/ip.h index 961ec16a26b8..874a92349bf5 100644 --- a/include/uapi/linux/ip.h +++ b/include/uapi/linux/ip.h @@ -100,8 +100,10 @@ struct iphdr { __u8 ttl; __u8 protocol; __sum16 check; - __be32 saddr; - __be32 daddr; + __struct_group(/* no tag */, addrs, /* no attrs */, + __be32 saddr; + __be32 daddr; + ); /*The options start here. */ }; diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 03cdbe798fe3..81f4243bebb1 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -130,8 +130,10 @@ struct ipv6hdr { __u8 nexthdr; __u8 hop_limit; - struct in6_addr saddr; - struct in6_addr daddr; + __struct_group(/* no tag */, addrs, /* no attrs */, + struct in6_addr saddr; + struct in6_addr daddr; + ); }; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index eed0315a77a6..0d5d4419139a 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1177,6 +1177,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_VM_DISABLE_NX_HUGE_PAGES 220 #define KVM_CAP_S390_ZPCI_OP 221 #define KVM_CAP_S390_CPU_TOPOLOGY 222 +#define KVM_CAP_DIRTY_LOG_RING_ACQ_REL 223 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 03b370062741..ccb7f5dad59b 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -164,8 +164,6 @@ enum perf_event_sample_format { PERF_SAMPLE_WEIGHT_STRUCT = 1U << 24, PERF_SAMPLE_MAX = 1U << 25, /* non-ABI */ - - __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63, /* non-ABI; internal use */ }; #define PERF_SAMPLE_WEIGHT_TYPE (PERF_SAMPLE_WEIGHT | PERF_SAMPLE_WEIGHT_STRUCT) @@ -204,6 +202,8 @@ enum perf_branch_sample_type_shift { PERF_SAMPLE_BRANCH_HW_INDEX_SHIFT = 17, /* save low level index of raw branch records */ + PERF_SAMPLE_BRANCH_PRIV_SAVE_SHIFT = 18, /* save privilege mode */ + PERF_SAMPLE_BRANCH_MAX_SHIFT /* non-ABI */ }; @@ -233,6 +233,8 @@ enum perf_branch_sample_type { PERF_SAMPLE_BRANCH_HW_INDEX = 1U << PERF_SAMPLE_BRANCH_HW_INDEX_SHIFT, + PERF_SAMPLE_BRANCH_PRIV_SAVE = 1U << PERF_SAMPLE_BRANCH_PRIV_SAVE_SHIFT, + PERF_SAMPLE_BRANCH_MAX = 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT, }; @@ -253,9 +255,48 @@ enum { PERF_BR_COND_RET = 10, /* conditional function return */ PERF_BR_ERET = 11, /* exception return */ PERF_BR_IRQ = 12, /* irq */ + PERF_BR_SERROR = 13, /* system error */ + PERF_BR_NO_TX = 14, /* not in transaction */ + PERF_BR_EXTEND_ABI = 15, /* extend ABI */ PERF_BR_MAX, }; +/* + * Common branch speculation outcome classification + */ +enum { + PERF_BR_SPEC_NA = 0, /* Not available */ + PERF_BR_SPEC_WRONG_PATH = 1, /* Speculative but on wrong path */ + PERF_BR_NON_SPEC_CORRECT_PATH = 2, /* Non-speculative but on correct path */ + PERF_BR_SPEC_CORRECT_PATH = 3, /* Speculative and on correct path */ + PERF_BR_SPEC_MAX, +}; + +enum { + PERF_BR_NEW_FAULT_ALGN = 0, /* Alignment fault */ + PERF_BR_NEW_FAULT_DATA = 1, /* Data fault */ + PERF_BR_NEW_FAULT_INST = 2, /* Inst fault */ + PERF_BR_NEW_ARCH_1 = 3, /* Architecture specific */ + PERF_BR_NEW_ARCH_2 = 4, /* Architecture specific */ + PERF_BR_NEW_ARCH_3 = 5, /* Architecture specific */ + PERF_BR_NEW_ARCH_4 = 6, /* Architecture specific */ + PERF_BR_NEW_ARCH_5 = 7, /* Architecture specific */ + PERF_BR_NEW_MAX, +}; + +enum { + PERF_BR_PRIV_UNKNOWN = 0, + PERF_BR_PRIV_USER = 1, + PERF_BR_PRIV_KERNEL = 2, + PERF_BR_PRIV_HV = 3, +}; + +#define PERF_BR_ARM64_FIQ PERF_BR_NEW_ARCH_1 +#define PERF_BR_ARM64_DEBUG_HALT PERF_BR_NEW_ARCH_2 +#define PERF_BR_ARM64_DEBUG_EXIT PERF_BR_NEW_ARCH_3 +#define PERF_BR_ARM64_DEBUG_INST PERF_BR_NEW_ARCH_4 +#define PERF_BR_ARM64_DEBUG_DATA PERF_BR_NEW_ARCH_5 + #define PERF_SAMPLE_BRANCH_PLM_ALL \ (PERF_SAMPLE_BRANCH_USER|\ PERF_SAMPLE_BRANCH_KERNEL|\ @@ -1295,7 +1336,9 @@ union perf_mem_data_src { #define PERF_MEM_LVLNUM_L2 0x02 /* L2 */ #define PERF_MEM_LVLNUM_L3 0x03 /* L3 */ #define PERF_MEM_LVLNUM_L4 0x04 /* L4 */ -/* 5-0xa available */ +/* 5-0x8 available */ +#define PERF_MEM_LVLNUM_CXL 0x09 /* CXL */ +#define PERF_MEM_LVLNUM_IO 0x0a /* I/O */ #define PERF_MEM_LVLNUM_ANY_CACHE 0x0b /* Any cache */ #define PERF_MEM_LVLNUM_LFB 0x0c /* LFB */ #define PERF_MEM_LVLNUM_RAM 0x0d /* RAM */ @@ -1313,7 +1356,7 @@ union perf_mem_data_src { #define PERF_MEM_SNOOP_SHIFT 19 #define PERF_MEM_SNOOPX_FWD 0x01 /* forward */ -/* 1 free */ +#define PERF_MEM_SNOOPX_PEER 0x02 /* xfer from peer */ #define PERF_MEM_SNOOPX_SHIFT 38 /* locked instruction */ @@ -1363,6 +1406,7 @@ union perf_mem_data_src { * abort: aborting a hardware transaction * cycles: cycles from last branch (or 0 if not supported) * type: branch type + * spec: branch speculation info (or 0 if not supported) */ struct perf_branch_entry { __u64 from; @@ -1373,7 +1417,10 @@ struct perf_branch_entry { abort:1, /* transaction abort */ cycles:16, /* cycle count to last branch */ type:4, /* branch type */ - reserved:40; + spec:2, /* branch speculation info */ + new_type:4, /* additional branch type */ + priv:3, /* privilege level */ + reserved:31; }; union perf_sample_weight { diff --git a/include/uapi/linux/rkisp1-config.h b/include/uapi/linux/rkisp1-config.h index 583ca0d9a79d..730673ecc63d 100644 --- a/include/uapi/linux/rkisp1-config.h +++ b/include/uapi/linux/rkisp1-config.h @@ -117,7 +117,46 @@ /* * Defect Pixel Cluster Correction */ -#define RKISP1_CIF_ISP_DPCC_METHODS_MAX 3 +#define RKISP1_CIF_ISP_DPCC_METHODS_MAX 3 + +#define RKISP1_CIF_ISP_DPCC_MODE_STAGE1_ENABLE (1U << 2) + +#define RKISP1_CIF_ISP_DPCC_OUTPUT_MODE_STAGE1_INCL_G_CENTER (1U << 0) +#define RKISP1_CIF_ISP_DPCC_OUTPUT_MODE_STAGE1_INCL_RB_CENTER (1U << 1) +#define RKISP1_CIF_ISP_DPCC_OUTPUT_MODE_STAGE1_G_3X3 (1U << 2) +#define RKISP1_CIF_ISP_DPCC_OUTPUT_MODE_STAGE1_RB_3X3 (1U << 3) + +/* 0-2 for sets 1-3 */ +#define RKISP1_CIF_ISP_DPCC_SET_USE_STAGE1_USE_SET(n) ((n) << 0) +#define RKISP1_CIF_ISP_DPCC_SET_USE_STAGE1_USE_FIX_SET (1U << 3) + +#define RKISP1_CIF_ISP_DPCC_METHODS_SET_PG_GREEN_ENABLE (1U << 0) +#define RKISP1_CIF_ISP_DPCC_METHODS_SET_LC_GREEN_ENABLE (1U << 1) +#define RKISP1_CIF_ISP_DPCC_METHODS_SET_RO_GREEN_ENABLE (1U << 2) +#define RKISP1_CIF_ISP_DPCC_METHODS_SET_RND_GREEN_ENABLE (1U << 3) +#define RKISP1_CIF_ISP_DPCC_METHODS_SET_RG_GREEN_ENABLE (1U << 4) +#define RKISP1_CIF_ISP_DPCC_METHODS_SET_PG_RED_BLUE_ENABLE (1U << 8) +#define RKISP1_CIF_ISP_DPCC_METHODS_SET_LC_RED_BLUE_ENABLE (1U << 9) +#define RKISP1_CIF_ISP_DPCC_METHODS_SET_RO_RED_BLUE_ENABLE (1U << 10) +#define RKISP1_CIF_ISP_DPCC_METHODS_SET_RND_RED_BLUE_ENABLE (1U << 11) +#define RKISP1_CIF_ISP_DPCC_METHODS_SET_RG_RED_BLUE_ENABLE (1U << 12) + +#define RKISP1_CIF_ISP_DPCC_LINE_THRESH_G(v) ((v) << 0) +#define RKISP1_CIF_ISP_DPCC_LINE_THRESH_RB(v) ((v) << 8) +#define RKISP1_CIF_ISP_DPCC_LINE_MAD_FAC_G(v) ((v) << 0) +#define RKISP1_CIF_ISP_DPCC_LINE_MAD_FAC_RB(v) ((v) << 8) +#define RKISP1_CIF_ISP_DPCC_PG_FAC_G(v) ((v) << 0) +#define RKISP1_CIF_ISP_DPCC_PG_FAC_RB(v) ((v) << 8) +#define RKISP1_CIF_ISP_DPCC_RND_THRESH_G(v) ((v) << 0) +#define RKISP1_CIF_ISP_DPCC_RND_THRESH_RB(v) ((v) << 8) +#define RKISP1_CIF_ISP_DPCC_RG_FAC_G(v) ((v) << 0) +#define RKISP1_CIF_ISP_DPCC_RG_FAC_RB(v) ((v) << 8) + +#define RKISP1_CIF_ISP_DPCC_RO_LIMITS_n_G(n, v) ((v) << ((n) * 4)) +#define RKISP1_CIF_ISP_DPCC_RO_LIMITS_n_RB(n, v) ((v) << ((n) * 4 + 2)) + +#define RKISP1_CIF_ISP_DPCC_RND_OFFS_n_G(n, v) ((v) << ((n) * 4)) +#define RKISP1_CIF_ISP_DPCC_RND_OFFS_n_RB(n, v) ((v) << ((n) * 4 + 2)) /* * Denoising pre filter @@ -249,16 +288,20 @@ struct rkisp1_cif_isp_bls_config { }; /** - * struct rkisp1_cif_isp_dpcc_methods_config - Methods Configuration used by DPCC + * struct rkisp1_cif_isp_dpcc_methods_config - DPCC methods set configuration * - * Methods Configuration used by Defect Pixel Cluster Correction + * This structure stores the configuration of one set of methods for the DPCC + * algorithm. Multiple methods can be selected in each set (independently for + * the Green and Red/Blue components) through the @method field, the result is + * the logical AND of all enabled methods. The remaining fields set thresholds + * and factors for each method. * - * @method: Method enable bits - * @line_thresh: Line threshold - * @line_mad_fac: Line MAD factor - * @pg_fac: Peak gradient factor - * @rnd_thresh: Rank Neighbor Difference threshold - * @rg_fac: Rank gradient factor + * @method: Method enable bits (RKISP1_CIF_ISP_DPCC_METHODS_SET_*) + * @line_thresh: Line threshold (RKISP1_CIF_ISP_DPCC_LINE_THRESH_*) + * @line_mad_fac: Line Mean Absolute Difference factor (RKISP1_CIF_ISP_DPCC_LINE_MAD_FAC_*) + * @pg_fac: Peak gradient factor (RKISP1_CIF_ISP_DPCC_PG_FAC_*) + * @rnd_thresh: Rank Neighbor Difference threshold (RKISP1_CIF_ISP_DPCC_RND_THRESH_*) + * @rg_fac: Rank gradient factor (RKISP1_CIF_ISP_DPCC_RG_FAC_*) */ struct rkisp1_cif_isp_dpcc_methods_config { __u32 method; @@ -272,14 +315,16 @@ struct rkisp1_cif_isp_dpcc_methods_config { /** * struct rkisp1_cif_isp_dpcc_config - Configuration used by DPCC * - * Configuration used by Defect Pixel Cluster Correction + * Configuration used by Defect Pixel Cluster Correction. Three sets of methods + * can be configured and selected through the @set_use field. The result is the + * logical OR of all enabled sets. * - * @mode: dpcc output mode - * @output_mode: whether use hard coded methods - * @set_use: stage1 methods set - * @methods: methods config - * @ro_limits: rank order limits - * @rnd_offs: differential rank offsets for rank neighbor difference + * @mode: DPCC mode (RKISP1_CIF_ISP_DPCC_MODE_*) + * @output_mode: Interpolation output mode (RKISP1_CIF_ISP_DPCC_OUTPUT_MODE_*) + * @set_use: Methods sets selection (RKISP1_CIF_ISP_DPCC_SET_USE_*) + * @methods: Methods sets configuration + * @ro_limits: Rank order limits (RKISP1_CIF_ISP_DPCC_RO_LIMITS_*) + * @rnd_offs: Differential rank offsets for rank neighbor difference (RKISP1_CIF_ISP_DPCC_RND_OFFS_*) */ struct rkisp1_cif_isp_dpcc_config { __u32 mode; diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h index 7d32b1e797fb..005e5e306266 100644 --- a/include/uapi/linux/userfaultfd.h +++ b/include/uapi/linux/userfaultfd.h @@ -12,6 +12,10 @@ #include <linux/types.h> +/* ioctls for /dev/userfaultfd */ +#define USERFAULTFD_IOC 0xAA +#define USERFAULTFD_IOC_NEW _IO(USERFAULTFD_IOC, 0x00) + /* * If the UFFDIO_API is upgraded someday, the UFFDIO_UNREGISTER and * UFFDIO_WAKE ioctls should be defined as _IOW and not as _IOR. In diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index 25c55cab3d7c..9bd79235c875 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -46,12 +46,18 @@ enum vdpa_attr { VDPA_ATTR_DEV_NEGOTIATED_FEATURES, /* u64 */ VDPA_ATTR_DEV_MGMTDEV_MAX_VQS, /* u32 */ + /* virtio features that are supported by the vDPA management device */ VDPA_ATTR_DEV_SUPPORTED_FEATURES, /* u64 */ VDPA_ATTR_DEV_QUEUE_INDEX, /* u32 */ VDPA_ATTR_DEV_VENDOR_ATTR_NAME, /* string */ VDPA_ATTR_DEV_VENDOR_ATTR_VALUE, /* u64 */ + VDPA_ATTR_DEV_FEATURES, /* u64 */ + + /* virtio features that are supported by the vDPA device */ + VDPA_ATTR_VDPA_DEV_SUPPORTED_FEATURES, /* u64 */ + /* new attributes must be added above here */ VDPA_ATTR_MAX, }; diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 733a1cddde30..d7d8e0922376 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -986,6 +986,148 @@ enum vfio_device_mig_state { VFIO_DEVICE_STATE_RUNNING_P2P = 5, }; +/* + * Upon VFIO_DEVICE_FEATURE_SET, allow the device to be moved into a low power + * state with the platform-based power management. Device use of lower power + * states depends on factors managed by the runtime power management core, + * including system level support and coordinating support among dependent + * devices. Enabling device low power entry does not guarantee lower power + * usage by the device, nor is a mechanism provided through this feature to + * know the current power state of the device. If any device access happens + * (either from the host or through the vfio uAPI) when the device is in the + * low power state, then the host will move the device out of the low power + * state as necessary prior to the access. Once the access is completed, the + * device may re-enter the low power state. For single shot low power support + * with wake-up notification, see + * VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY_WITH_WAKEUP below. Access to mmap'd + * device regions is disabled on LOW_POWER_ENTRY and may only be resumed after + * calling LOW_POWER_EXIT. + */ +#define VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY 3 + +/* + * This device feature has the same behavior as + * VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY with the exception that the user + * provides an eventfd for wake-up notification. When the device moves out of + * the low power state for the wake-up, the host will not allow the device to + * re-enter a low power state without a subsequent user call to one of the low + * power entry device feature IOCTLs. Access to mmap'd device regions is + * disabled on LOW_POWER_ENTRY_WITH_WAKEUP and may only be resumed after the + * low power exit. The low power exit can happen either through LOW_POWER_EXIT + * or through any other access (where the wake-up notification has been + * generated). The access to mmap'd device regions will not trigger low power + * exit. + * + * The notification through the provided eventfd will be generated only when + * the device has entered and is resumed from a low power state after + * calling this device feature IOCTL. A device that has not entered low power + * state, as managed through the runtime power management core, will not + * generate a notification through the provided eventfd on access. Calling the + * LOW_POWER_EXIT feature is optional in the case where notification has been + * signaled on the provided eventfd that a resume from low power has occurred. + */ +struct vfio_device_low_power_entry_with_wakeup { + __s32 wakeup_eventfd; + __u32 reserved; +}; + +#define VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY_WITH_WAKEUP 4 + +/* + * Upon VFIO_DEVICE_FEATURE_SET, disallow use of device low power states as + * previously enabled via VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY or + * VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY_WITH_WAKEUP device features. + * This device feature IOCTL may itself generate a wakeup eventfd notification + * in the latter case if the device had previously entered a low power state. + */ +#define VFIO_DEVICE_FEATURE_LOW_POWER_EXIT 5 + +/* + * Upon VFIO_DEVICE_FEATURE_SET start/stop device DMA logging. + * VFIO_DEVICE_FEATURE_PROBE can be used to detect if the device supports + * DMA logging. + * + * DMA logging allows a device to internally record what DMAs the device is + * initiating and report them back to userspace. It is part of the VFIO + * migration infrastructure that allows implementing dirty page tracking + * during the pre copy phase of live migration. Only DMA WRITEs are logged, + * and this API is not connected to VFIO_DEVICE_FEATURE_MIG_DEVICE_STATE. + * + * When DMA logging is started a range of IOVAs to monitor is provided and the + * device can optimize its logging to cover only the IOVA range given. Each + * DMA that the device initiates inside the range will be logged by the device + * for later retrieval. + * + * page_size is an input that hints what tracking granularity the device + * should try to achieve. If the device cannot do the hinted page size then + * it's the driver choice which page size to pick based on its support. + * On output the device will return the page size it selected. + * + * ranges is a pointer to an array of + * struct vfio_device_feature_dma_logging_range. + * + * The core kernel code guarantees to support by minimum num_ranges that fit + * into a single kernel page. User space can try higher values but should give + * up if the above can't be achieved as of some driver limitations. + * + * A single call to start device DMA logging can be issued and a matching stop + * should follow at the end. Another start is not allowed in the meantime. + */ +struct vfio_device_feature_dma_logging_control { + __aligned_u64 page_size; + __u32 num_ranges; + __u32 __reserved; + __aligned_u64 ranges; +}; + +struct vfio_device_feature_dma_logging_range { + __aligned_u64 iova; + __aligned_u64 length; +}; + +#define VFIO_DEVICE_FEATURE_DMA_LOGGING_START 6 + +/* + * Upon VFIO_DEVICE_FEATURE_SET stop device DMA logging that was started + * by VFIO_DEVICE_FEATURE_DMA_LOGGING_START + */ +#define VFIO_DEVICE_FEATURE_DMA_LOGGING_STOP 7 + +/* + * Upon VFIO_DEVICE_FEATURE_GET read back and clear the device DMA log + * + * Query the device's DMA log for written pages within the given IOVA range. + * During querying the log is cleared for the IOVA range. + * + * bitmap is a pointer to an array of u64s that will hold the output bitmap + * with 1 bit reporting a page_size unit of IOVA. The mapping of IOVA to bits + * is given by: + * bitmap[(addr - iova)/page_size] & (1ULL << (addr % 64)) + * + * The input page_size can be any power of two value and does not have to + * match the value given to VFIO_DEVICE_FEATURE_DMA_LOGGING_START. The driver + * will format its internal logging to match the reporting page size, possibly + * by replicating bits if the internal page size is lower than requested. + * + * The LOGGING_REPORT will only set bits in the bitmap and never clear or + * perform any initialization of the user provided bitmap. + * + * If any error is returned userspace should assume that the dirty log is + * corrupted. Error recovery is to consider all memory dirty and try to + * restart the dirty tracking, or to abort/restart the whole migration. + * + * If DMA logging is not enabled, an error will be returned. + * + */ +struct vfio_device_feature_dma_logging_report { + __aligned_u64 iova; + __aligned_u64 length; + __aligned_u64 page_size; + __aligned_u64 bitmap; +}; + +#define VFIO_DEVICE_FEATURE_DMA_LOGGING_REPORT 8 + /* -------- API for Type1 VFIO IOMMU -------- */ /** diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 86cae23cc446..29da1f4b4578 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -1601,7 +1601,8 @@ struct v4l2_bt_timings { ((bt)->width + V4L2_DV_BT_BLANKING_WIDTH(bt)) #define V4L2_DV_BT_BLANKING_HEIGHT(bt) \ ((bt)->vfrontporch + (bt)->vsync + (bt)->vbackporch + \ - (bt)->il_vfrontporch + (bt)->il_vsync + (bt)->il_vbackporch) + ((bt)->interlaced ? \ + ((bt)->il_vfrontporch + (bt)->il_vsync + (bt)->il_vbackporch) : 0)) #define V4L2_DV_BT_FRAME_HEIGHT(bt) \ ((bt)->height + V4L2_DV_BT_BLANKING_HEIGHT(bt)) diff --git a/include/uapi/linux/virtio_blk.h b/include/uapi/linux/virtio_blk.h index d888f013d9ff..58e70b24b504 100644 --- a/include/uapi/linux/virtio_blk.h +++ b/include/uapi/linux/virtio_blk.h @@ -40,6 +40,7 @@ #define VIRTIO_BLK_F_MQ 12 /* support more than one vq */ #define VIRTIO_BLK_F_DISCARD 13 /* DISCARD is supported */ #define VIRTIO_BLK_F_WRITE_ZEROES 14 /* WRITE ZEROES is supported */ +#define VIRTIO_BLK_F_SECURE_ERASE 16 /* Secure Erase is supported */ /* Legacy feature bits */ #ifndef VIRTIO_BLK_NO_LEGACY @@ -121,6 +122,21 @@ struct virtio_blk_config { __u8 write_zeroes_may_unmap; __u8 unused1[3]; + + /* the next 3 entries are guarded by VIRTIO_BLK_F_SECURE_ERASE */ + /* + * The maximum secure erase sectors (in 512-byte sectors) for + * one segment. + */ + __virtio32 max_secure_erase_sectors; + /* + * The maximum number of secure erase segments in a + * secure erase command. + */ + __virtio32 max_secure_erase_seg; + /* Secure erase commands must be aligned to this number of sectors. */ + __virtio32 secure_erase_sector_alignment; + } __attribute__((packed)); /* @@ -155,6 +171,9 @@ struct virtio_blk_config { /* Write zeroes command */ #define VIRTIO_BLK_T_WRITE_ZEROES 13 +/* Secure erase command */ +#define VIRTIO_BLK_T_SECURE_ERASE 14 + #ifndef VIRTIO_BLK_NO_LEGACY /* Barrier before this op. */ #define VIRTIO_BLK_T_BARRIER 0x80000000 diff --git a/include/uapi/misc/uacce/hisi_qm.h b/include/uapi/misc/uacce/hisi_qm.h index 1faef5ff87ef..3e66dbc2f323 100644 --- a/include/uapi/misc/uacce/hisi_qm.h +++ b/include/uapi/misc/uacce/hisi_qm.h @@ -14,11 +14,26 @@ struct hisi_qp_ctx { __u16 qc_type; }; +/** + * struct hisi_qp_info - User data for hisi qp. + * @sqe_size: Submission queue element size + * @sq_depth: The number of sqe + * @cq_depth: The number of cqe + * @reserved: Reserved data + */ +struct hisi_qp_info { + __u32 sqe_size; + __u16 sq_depth; + __u16 cq_depth; + __u64 reserved; +}; + #define HISI_QM_API_VER_BASE "hisi_qm_v1" #define HISI_QM_API_VER2_BASE "hisi_qm_v2" #define HISI_QM_API_VER3_BASE "hisi_qm_v3" /* UACCE_CMD_QM_SET_QP_CTX: Set qp algorithm type */ #define UACCE_CMD_QM_SET_QP_CTX _IOWR('H', 10, struct hisi_qp_ctx) - +/* UACCE_CMD_QM_SET_QP_INFO: Set qp depth and BD size */ +#define UACCE_CMD_QM_SET_QP_INFO _IOWR('H', 11, struct hisi_qp_info) #endif diff --git a/include/uapi/mtd/ubi-user.h b/include/uapi/mtd/ubi-user.h index b69e9ba6742b..dcb179de4358 100644 --- a/include/uapi/mtd/ubi-user.h +++ b/include/uapi/mtd/ubi-user.h @@ -247,6 +247,7 @@ enum { * @vid_hdr_offset: VID header offset (use defaults if %0) * @max_beb_per1024: maximum expected number of bad PEB per 1024 PEBs * @padding: reserved for future, not used, has to be zeroed + * @disable_fm: whether disable fastmap * * This data structure is used to specify MTD device UBI has to attach and the * parameters it has to use. The number which should be assigned to the new UBI @@ -281,13 +282,18 @@ enum { * eraseblocks for new bad eraseblocks, but attempts to use available * eraseblocks (if any). The accepted range is 0-768. If 0 is given, the * default kernel value of %CONFIG_MTD_UBI_BEB_LIMIT will be used. + * + * If @disable_fm is not zero, ubi doesn't create new fastmap even the module + * param 'fm_autoconvert' is set, and existed old fastmap will be destroyed + * after doing full scanning. */ struct ubi_attach_req { __s32 ubi_num; __s32 mtd_num; __s32 vid_hdr_offset; __s16 max_beb_per1024; - __s8 padding[10]; + __s8 disable_fm; + __s8 padding[9]; }; /* diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h index dae0f350c678..a34f4271a2e9 100644 --- a/include/xen/xen-ops.h +++ b/include/xen/xen-ops.h @@ -219,6 +219,7 @@ static inline void xen_preemptible_hcall_end(void) { } void xen_grant_setup_dma_ops(struct device *dev); bool xen_is_grant_dma_device(struct device *dev); bool xen_virtio_mem_acc(struct virtio_device *dev); +bool xen_virtio_restricted_mem_acc(struct virtio_device *dev); #else static inline void xen_grant_setup_dma_ops(struct device *dev) { @@ -234,6 +235,11 @@ static inline bool xen_virtio_mem_acc(struct virtio_device *dev) { return false; } + +static inline bool xen_virtio_restricted_mem_acc(struct virtio_device *dev) +{ + return false; +} #endif /* CONFIG_XEN_GRANT_DMA_OPS */ #endif /* INCLUDE_XEN_OPS_H */ |