diff options
Diffstat (limited to 'include')
75 files changed, 2457 insertions, 1119 deletions
diff --git a/include/acpi/processor.h b/include/acpi/processor.h index 7146a8e9e9c2..d0eccbd920e5 100644 --- a/include/acpi/processor.h +++ b/include/acpi/processor.h @@ -417,15 +417,32 @@ static inline void acpi_processor_throttling_init(void) {} #endif /* CONFIG_ACPI_CPU_FREQ_PSS */ /* in processor_idle.c */ +extern struct cpuidle_driver acpi_idle_driver; #ifdef CONFIG_ACPI_PROCESSOR_IDLE -void acpi_processor_power_init(struct acpi_processor *pr); -void acpi_processor_power_exit(struct acpi_processor *pr); +int acpi_processor_power_init(struct acpi_processor *pr); +int acpi_processor_power_exit(struct acpi_processor *pr); int acpi_processor_power_state_has_changed(struct acpi_processor *pr); int acpi_processor_hotplug(struct acpi_processor *pr); -void acpi_processor_register_idle_driver(void); -void acpi_processor_unregister_idle_driver(void); -int acpi_processor_ffh_lpi_probe(unsigned int cpu); -int acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi); +#else +static inline int acpi_processor_power_init(struct acpi_processor *pr) +{ + return -ENODEV; +} + +static inline int acpi_processor_power_exit(struct acpi_processor *pr) +{ + return -ENODEV; +} + +static inline int acpi_processor_power_state_has_changed(struct acpi_processor *pr) +{ + return -ENODEV; +} + +static inline int acpi_processor_hotplug(struct acpi_processor *pr) +{ + return -ENODEV; +} #endif /* CONFIG_ACPI_PROCESSOR_IDLE */ /* in processor_thermal.c */ @@ -448,6 +465,11 @@ static inline void acpi_thermal_cpufreq_exit(struct cpufreq_policy *policy) } #endif /* CONFIG_CPU_FREQ */ +#ifdef CONFIG_ACPI_PROCESSOR_IDLE +extern int acpi_processor_ffh_lpi_probe(unsigned int cpu); +extern int acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi); +#endif + void acpi_processor_init_invariance_cppc(void); #endif diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h index 387720933973..09e8eccee8ed 100644 --- a/include/asm-generic/bug.h +++ b/include/asm-generic/bug.h @@ -13,10 +13,19 @@ #define BUGFLAG_ONCE (1 << 1) #define BUGFLAG_DONE (1 << 2) #define BUGFLAG_NO_CUT_HERE (1 << 3) /* CUT_HERE already sent */ +#define BUGFLAG_ARGS (1 << 4) #define BUGFLAG_TAINT(taint) ((taint) << 8) #define BUG_GET_TAINT(bug) ((bug)->flags >> 8) #endif +#ifndef WARN_CONDITION_STR +#ifdef CONFIG_DEBUG_BUGVERBOSE_DETAILED +# define WARN_CONDITION_STR(cond_str) "[" cond_str "] " +#else +# define WARN_CONDITION_STR(cond_str) +#endif +#endif /* WARN_CONDITION_STR */ + #ifndef __ASSEMBLY__ #include <linux/panic.h> #include <linux/printk.h> @@ -29,19 +38,20 @@ void __warn(const char *file, int line, void *caller, unsigned taint, #ifdef CONFIG_BUG -#ifdef CONFIG_GENERIC_BUG -struct bug_entry { #ifndef CONFIG_GENERIC_BUG_RELATIVE_POINTERS - unsigned long bug_addr; +#define BUG_REL(type, name) type name #else - signed int bug_addr_disp; +#define BUG_REL(type, name) signed int name##_disp #endif -#ifdef CONFIG_DEBUG_BUGVERBOSE -#ifndef CONFIG_GENERIC_BUG_RELATIVE_POINTERS - const char *file; -#else - signed int file_disp; + +#ifdef CONFIG_GENERIC_BUG +struct bug_entry { + BUG_REL(unsigned long, bug_addr); +#ifdef HAVE_ARCH_BUG_FORMAT + BUG_REL(const char *, format); #endif +#ifdef CONFIG_DEBUG_BUGVERBOSE + BUG_REL(const char *, file); unsigned short line; #endif unsigned short flags; @@ -92,28 +102,50 @@ void warn_slowpath_fmt(const char *file, const int line, unsigned taint, const char *fmt, ...); extern __printf(1, 2) void __warn_printk(const char *fmt, ...); -#ifndef __WARN_FLAGS -#define __WARN() __WARN_printf(TAINT_WARN, NULL) +#ifdef __WARN_FLAGS +#define __WARN() __WARN_FLAGS("", BUGFLAG_TAINT(TAINT_WARN)) + +#ifndef WARN_ON +#define WARN_ON(condition) ({ \ + int __ret_warn_on = !!(condition); \ + if (unlikely(__ret_warn_on)) \ + __WARN_FLAGS(#condition, \ + BUGFLAG_TAINT(TAINT_WARN)); \ + unlikely(__ret_warn_on); \ +}) +#endif + +#ifndef WARN_ON_ONCE +#define WARN_ON_ONCE(condition) ({ \ + int __ret_warn_on = !!(condition); \ + if (unlikely(__ret_warn_on)) \ + __WARN_FLAGS(#condition, \ + BUGFLAG_ONCE | \ + BUGFLAG_TAINT(TAINT_WARN)); \ + unlikely(__ret_warn_on); \ +}) +#endif +#endif /* __WARN_FLAGS */ + +#if defined(__WARN_FLAGS) && !defined(__WARN_printf) #define __WARN_printf(taint, arg...) do { \ instrumentation_begin(); \ - warn_slowpath_fmt(__FILE__, __LINE__, taint, arg); \ + __warn_printk(arg); \ + __WARN_FLAGS("", BUGFLAG_NO_CUT_HERE | BUGFLAG_TAINT(taint));\ instrumentation_end(); \ } while (0) -#else -#define __WARN() __WARN_FLAGS(BUGFLAG_TAINT(TAINT_WARN)) +#endif + +#ifndef __WARN_printf #define __WARN_printf(taint, arg...) do { \ instrumentation_begin(); \ - __warn_printk(arg); \ - __WARN_FLAGS(BUGFLAG_NO_CUT_HERE | BUGFLAG_TAINT(taint));\ + warn_slowpath_fmt(__FILE__, __LINE__, taint, arg); \ instrumentation_end(); \ } while (0) -#define WARN_ON_ONCE(condition) ({ \ - int __ret_warn_on = !!(condition); \ - if (unlikely(__ret_warn_on)) \ - __WARN_FLAGS(BUGFLAG_ONCE | \ - BUGFLAG_TAINT(TAINT_WARN)); \ - unlikely(__ret_warn_on); \ -}) +#endif + +#ifndef __WARN +#define __WARN() __WARN_printf(TAINT_WARN, NULL) #endif /* used internally by panic.c */ @@ -148,8 +180,10 @@ extern __printf(1, 2) void __warn_printk(const char *fmt, ...); DO_ONCE_LITE_IF(condition, WARN_ON, 1) #endif +#ifndef WARN_ONCE #define WARN_ONCE(condition, format...) \ DO_ONCE_LITE_IF(condition, WARN, 1, format) +#endif #define WARN_TAINT_ONCE(condition, taint, format...) \ DO_ONCE_LITE_IF(condition, WARN_TAINT, 1, taint, format) diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index e04d56a5332e..a464ff6c1a61 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -87,39 +87,56 @@ #define ALIGN_FUNCTION() . = ALIGN(CONFIG_FUNCTION_ALIGNMENT) /* - * LD_DEAD_CODE_DATA_ELIMINATION option enables -fdata-sections, which - * generates .data.identifier sections, which need to be pulled in with - * .data. We don't want to pull in .data..other sections, which Linux - * has defined. Same for text and bss. + * Support -ffunction-sections by matching .text and .text.*, + * but exclude '.text..*', .text.startup[.*], and .text.exit[.*]. * - * With LTO_CLANG, the linker also splits sections by default, so we need - * these macros to combine the sections during the final link. + * .text.startup and .text.startup.* are matched later by INIT_TEXT, and + * .text.exit and .text.exit.* are matched later by EXIT_TEXT, so they must be + * explicitly excluded here. * - * With AUTOFDO_CLANG and PROPELLER_CLANG, by default, the linker splits - * text sections and regroups functions into subsections. + * Other .text.* sections that are typically grouped separately, such as + * .text.unlikely or .text.hot, must be matched explicitly before using + * TEXT_MAIN. * - * RODATA_MAIN is not used because existing code already defines .rodata.x - * sections to be brought in with rodata. + * NOTE: builds *with* and *without* -ffunction-sections are both supported by + * this single macro. Even with -ffunction-sections, there may be some objects + * NOT compiled with the flag due to the use of a specific Makefile override + * like cflags-y or AUTOFDO_PROFILE_foo.o. So this single catchall rule is + * needed to support mixed object builds. + * + * One implication is that functions named startup(), exit(), split(), + * unlikely(), hot(), and unknown() are not allowed in the kernel due to the + * ambiguity of their section names with -ffunction-sections. For example, + * .text.startup could be __attribute__((constructor)) code in a *non* + * ffunction-sections object, which should be placed in .init.text; or it could + * be an actual function named startup() in an ffunction-sections object, which + * should be placed in .text. The build will detect and complain about any such + * ambiguously named functions. + */ +#define TEXT_MAIN \ + .text \ + .text.[_0-9A-Za-df-rt-z]* \ + .text.s[_0-9A-Za-su-z]* .text.s .text.s.* \ + .text.st[_0-9A-Zb-z]* .text.st .text.st.* \ + .text.sta[_0-9A-Za-qs-z]* .text.sta .text.sta.* \ + .text.star[_0-9A-Za-su-z]* .text.star .text.star.* \ + .text.start[_0-9A-Za-tv-z]* .text.start .text.start.* \ + .text.startu[_0-9A-Za-oq-z]* .text.startu .text.startu.* \ + .text.startup[_0-9A-Za-z]* \ + .text.e[_0-9A-Za-wy-z]* .text.e .text.e.* \ + .text.ex[_0-9A-Za-hj-z]* .text.ex .text.ex.* \ + .text.exi[_0-9A-Za-su-z]* .text.exi .text.exi.* \ + .text.exit[_0-9A-Za-z]* + +/* + * Support -fdata-sections by matching .data, .data.*, and others, + * but exclude '.data..*'. */ -#if defined(CONFIG_LD_DEAD_CODE_DATA_ELIMINATION) || defined(CONFIG_LTO_CLANG) || \ -defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG) -#define TEXT_MAIN .text .text.[0-9a-zA-Z_]* -#else -#define TEXT_MAIN .text -#endif -#if defined(CONFIG_LD_DEAD_CODE_DATA_ELIMINATION) || defined(CONFIG_LTO_CLANG) #define DATA_MAIN .data .data.[0-9a-zA-Z_]* .data.rel.* .data..L* .data..compoundliteral* .data.$__unnamed_* .data.$L* #define SDATA_MAIN .sdata .sdata.[0-9a-zA-Z_]* #define RODATA_MAIN .rodata .rodata.[0-9a-zA-Z_]* .rodata..L* #define BSS_MAIN .bss .bss.[0-9a-zA-Z_]* .bss..L* .bss..compoundliteral* #define SBSS_MAIN .sbss .sbss.[0-9a-zA-Z_]* -#else -#define DATA_MAIN .data .data.rel .data.rel.local -#define SDATA_MAIN .sdata -#define RODATA_MAIN .rodata -#define BSS_MAIN .bss -#define SBSS_MAIN .sbss -#endif /* * GCC 4.5 and later have a 32 bytes section alignment for structures. @@ -581,9 +598,8 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG) * during second ld run in second ld pass when generating System.map * * TEXT_MAIN here will match symbols with a fixed pattern (for example, - * .text.hot or .text.unlikely) if dead code elimination or - * function-section is enabled. Match these symbols first before - * TEXT_MAIN to ensure they are grouped together. + * .text.hot or .text.unlikely). Match those before TEXT_MAIN to ensure + * they get grouped together. * * Also placing .text.hot section at the beginning of a page, this * would help the TLB performance. @@ -729,16 +745,16 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG) #define INIT_TEXT \ *(.init.text .init.text.*) \ - *(.text.startup) + *(.text.startup .text.startup.*) #define EXIT_DATA \ *(.exit.data .exit.data.*) \ *(.fini_array .fini_array.*) \ - *(.dtors .dtors.*) \ + *(.dtors .dtors.*) #define EXIT_TEXT \ *(.exit.text) \ - *(.text.exit) \ + *(.text.exit .text.exit.*) #define EXIT_CALL \ *(.exitcall.exit) @@ -955,7 +971,8 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG) #define RUNTIME_CONST_VARIABLES \ RUNTIME_CONST(shift, d_hash_shift) \ - RUNTIME_CONST(ptr, dentry_hashtable) + RUNTIME_CONST(ptr, dentry_hashtable) \ + RUNTIME_CONST(ptr, __dentry_cache) /* Alignment must be consistent with (kunit_suite *) in include/kunit/test.h */ #define KUNIT_TABLE() \ diff --git a/include/linux/annotate.h b/include/linux/annotate.h new file mode 100644 index 000000000000..7c10d34d198c --- /dev/null +++ b/include/linux/annotate.h @@ -0,0 +1,134 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_ANNOTATE_H +#define _LINUX_ANNOTATE_H + +#include <linux/objtool_types.h> + +#ifdef CONFIG_OBJTOOL + +#ifndef __ASSEMBLY__ + +#define __ASM_ANNOTATE(section, label, type) \ + ".pushsection " section ",\"M\", @progbits, 8\n\t" \ + ".long " __stringify(label) " - .\n\t" \ + ".long " __stringify(type) "\n\t" \ + ".popsection\n\t" + +#define ASM_ANNOTATE_LABEL(label, type) \ + __ASM_ANNOTATE(".discard.annotate_insn", label, type) + +#define ASM_ANNOTATE(type) \ + "911:\n\t" \ + ASM_ANNOTATE_LABEL(911b, type) + +#define ASM_ANNOTATE_DATA(type) \ + "912:\n\t" \ + __ASM_ANNOTATE(".discard.annotate_data", 912b, type) + +#else /* __ASSEMBLY__ */ + +.macro __ANNOTATE section, type +.Lhere_\@: + .pushsection \section, "M", @progbits, 8 + .long .Lhere_\@ - . + .long \type + .popsection +.endm + +.macro ANNOTATE type + __ANNOTATE ".discard.annotate_insn", \type +.endm + +.macro ANNOTATE_DATA type + __ANNOTATE ".discard.annotate_data", \type +.endm + +#endif /* __ASSEMBLY__ */ + +#else /* !CONFIG_OBJTOOL */ +#ifndef __ASSEMBLY__ +#define ASM_ANNOTATE_LABEL(label, type) "" +#define ASM_ANNOTATE(type) +#define ASM_ANNOTATE_DATA(type) +#else /* __ASSEMBLY__ */ +.macro ANNOTATE type +.endm +.macro ANNOTATE_DATA type +.endm +#endif /* __ASSEMBLY__ */ +#endif /* !CONFIG_OBJTOOL */ + +#ifndef __ASSEMBLY__ + +/* + * Annotate away the various 'relocation to !ENDBR` complaints; knowing that + * these relocations will never be used for indirect calls. + */ +#define ANNOTATE_NOENDBR ASM_ANNOTATE(ANNOTYPE_NOENDBR) +#define ANNOTATE_NOENDBR_SYM(sym) asm(ASM_ANNOTATE_LABEL(sym, ANNOTYPE_NOENDBR)) + +/* + * This should be used immediately before an indirect jump/call. It tells + * objtool the subsequent indirect jump/call is vouched safe for retpoline + * builds. + */ +#define ANNOTATE_RETPOLINE_SAFE ASM_ANNOTATE(ANNOTYPE_RETPOLINE_SAFE) +/* + * See linux/instrumentation.h + */ +#define ANNOTATE_INSTR_BEGIN(label) ASM_ANNOTATE_LABEL(label, ANNOTYPE_INSTR_BEGIN) +#define ANNOTATE_INSTR_END(label) ASM_ANNOTATE_LABEL(label, ANNOTYPE_INSTR_END) +/* + * objtool annotation to ignore the alternatives and only consider the original + * instruction(s). + */ +#define ANNOTATE_IGNORE_ALTERNATIVE ASM_ANNOTATE(ANNOTYPE_IGNORE_ALTS) +/* + * This macro indicates that the following intra-function call is valid. + * Any non-annotated intra-function call will cause objtool to issue a warning. + */ +#define ANNOTATE_INTRA_FUNCTION_CALL ASM_ANNOTATE(ANNOTYPE_INTRA_FUNCTION_CALL) +/* + * Use objtool to validate the entry requirement that all code paths do + * VALIDATE_UNRET_END before RET. + * + * NOTE: The macro must be used at the beginning of a global symbol, otherwise + * it will be ignored. + */ +#define ANNOTATE_UNRET_BEGIN ASM_ANNOTATE(ANNOTYPE_UNRET_BEGIN) +/* + * This should be used to refer to an instruction that is considered + * terminating, like a noreturn CALL or UD2 when we know they are not -- eg + * WARN using UD2. + */ +#define ANNOTATE_REACHABLE(label) ASM_ANNOTATE_LABEL(label, ANNOTYPE_REACHABLE) +/* + * This should not be used; it annotates away CFI violations. There are a few + * valid use cases like kexec handover to the next kernel image, and there is + * no security concern there. + * + * There are also a few real issues annotated away, like EFI because we can't + * control the EFI code. + */ +#define ANNOTATE_NOCFI_SYM(sym) asm(ASM_ANNOTATE_LABEL(sym, ANNOTYPE_NOCFI)) + +/* + * Annotate a special section entry. This emables livepatch module generation + * to find and extract individual special section entries as needed. + */ +#define ANNOTATE_DATA_SPECIAL ASM_ANNOTATE_DATA(ANNOTYPE_DATA_SPECIAL) + +#else /* __ASSEMBLY__ */ +#define ANNOTATE_NOENDBR ANNOTATE type=ANNOTYPE_NOENDBR +#define ANNOTATE_RETPOLINE_SAFE ANNOTATE type=ANNOTYPE_RETPOLINE_SAFE +/* ANNOTATE_INSTR_BEGIN ANNOTATE type=ANNOTYPE_INSTR_BEGIN */ +/* ANNOTATE_INSTR_END ANNOTATE type=ANNOTYPE_INSTR_END */ +#define ANNOTATE_IGNORE_ALTERNATIVE ANNOTATE type=ANNOTYPE_IGNORE_ALTS +#define ANNOTATE_INTRA_FUNCTION_CALL ANNOTATE type=ANNOTYPE_INTRA_FUNCTION_CALL +#define ANNOTATE_UNRET_BEGIN ANNOTATE type=ANNOTYPE_UNRET_BEGIN +#define ANNOTATE_REACHABLE ANNOTATE type=ANNOTYPE_REACHABLE +#define ANNOTATE_NOCFI_SYM ANNOTATE type=ANNOTYPE_NOCFI +#define ANNOTATE_DATA_SPECIAL ANNOTATE_DATA type=ANNOTYPE_DATA_SPECIAL +#endif /* __ASSEMBLY__ */ + +#endif /* _LINUX_ANNOTATE_H */ diff --git a/include/linux/atomic/atomic-instrumented.h b/include/linux/atomic/atomic-instrumented.h index 9409a6ddf3e0..37ab6314a9f7 100644 --- a/include/linux/atomic/atomic-instrumented.h +++ b/include/linux/atomic/atomic-instrumented.h @@ -1276,7 +1276,7 @@ atomic_try_cmpxchg(atomic_t *v, int *old, int new) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); - instrument_atomic_read_write(old, sizeof(*old)); + instrument_read_write(old, sizeof(*old)); return raw_atomic_try_cmpxchg(v, old, new); } @@ -1298,7 +1298,7 @@ static __always_inline bool atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) { instrument_atomic_read_write(v, sizeof(*v)); - instrument_atomic_read_write(old, sizeof(*old)); + instrument_read_write(old, sizeof(*old)); return raw_atomic_try_cmpxchg_acquire(v, old, new); } @@ -1321,7 +1321,7 @@ atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); - instrument_atomic_read_write(old, sizeof(*old)); + instrument_read_write(old, sizeof(*old)); return raw_atomic_try_cmpxchg_release(v, old, new); } @@ -1343,7 +1343,7 @@ static __always_inline bool atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) { instrument_atomic_read_write(v, sizeof(*v)); - instrument_atomic_read_write(old, sizeof(*old)); + instrument_read_write(old, sizeof(*old)); return raw_atomic_try_cmpxchg_relaxed(v, old, new); } @@ -2854,7 +2854,7 @@ atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); - instrument_atomic_read_write(old, sizeof(*old)); + instrument_read_write(old, sizeof(*old)); return raw_atomic64_try_cmpxchg(v, old, new); } @@ -2876,7 +2876,7 @@ static __always_inline bool atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) { instrument_atomic_read_write(v, sizeof(*v)); - instrument_atomic_read_write(old, sizeof(*old)); + instrument_read_write(old, sizeof(*old)); return raw_atomic64_try_cmpxchg_acquire(v, old, new); } @@ -2899,7 +2899,7 @@ atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); - instrument_atomic_read_write(old, sizeof(*old)); + instrument_read_write(old, sizeof(*old)); return raw_atomic64_try_cmpxchg_release(v, old, new); } @@ -2921,7 +2921,7 @@ static __always_inline bool atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) { instrument_atomic_read_write(v, sizeof(*v)); - instrument_atomic_read_write(old, sizeof(*old)); + instrument_read_write(old, sizeof(*old)); return raw_atomic64_try_cmpxchg_relaxed(v, old, new); } @@ -4432,7 +4432,7 @@ atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); - instrument_atomic_read_write(old, sizeof(*old)); + instrument_read_write(old, sizeof(*old)); return raw_atomic_long_try_cmpxchg(v, old, new); } @@ -4454,7 +4454,7 @@ static __always_inline bool atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new) { instrument_atomic_read_write(v, sizeof(*v)); - instrument_atomic_read_write(old, sizeof(*old)); + instrument_read_write(old, sizeof(*old)); return raw_atomic_long_try_cmpxchg_acquire(v, old, new); } @@ -4477,7 +4477,7 @@ atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); - instrument_atomic_read_write(old, sizeof(*old)); + instrument_read_write(old, sizeof(*old)); return raw_atomic_long_try_cmpxchg_release(v, old, new); } @@ -4499,7 +4499,7 @@ static __always_inline bool atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new) { instrument_atomic_read_write(v, sizeof(*v)); - instrument_atomic_read_write(old, sizeof(*old)); + instrument_read_write(old, sizeof(*old)); return raw_atomic_long_try_cmpxchg_relaxed(v, old, new); } @@ -5050,4 +5050,4 @@ atomic_long_dec_if_positive(atomic_long_t *v) #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */ -// 8829b337928e9508259079d32581775ececd415b +// f618ac667f868941a84ce0ab2242f1786e049ed4 diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index c5c9d89c73ed..610ef62b6a32 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -63,6 +63,8 @@ enum wb_reason { struct wb_completion { atomic_t cnt; wait_queue_head_t *waitq; + unsigned long progress_stamp; /* The jiffies when slow progress is detected */ + unsigned long wait_start; /* The jiffies when waiting for the writeback work to finish */ }; #define __WB_COMPLETION_INIT(_waitq) \ diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 3e64f14739dd..0c8342747cab 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -277,10 +277,11 @@ unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie) rcu_read_lock(); /* - * Paired with store_release in inode_switch_wbs_work_fn() and + * Paired with a release fence in inode_do_switch_wbs() and * ensures that we see the new wb if we see cleared I_WB_SWITCH. */ - cookie->locked = smp_load_acquire(&inode->i_state) & I_WB_SWITCH; + cookie->locked = inode_state_read_once(inode) & I_WB_SWITCH; + smp_rmb(); if (unlikely(cookie->locked)) xa_lock_irqsave(&inode->i_mapping->i_pages, cookie->flags); diff --git a/include/linux/bug.h b/include/linux/bug.h index a9948a9f1093..17a4933c611b 100644 --- a/include/linux/bug.h +++ b/include/linux/bug.h @@ -42,6 +42,7 @@ void bug_get_file_line(struct bug_entry *bug, const char **file, struct bug_entry *find_bug(unsigned long bugaddr); enum bug_trap_type report_bug(unsigned long bug_addr, struct pt_regs *regs); +enum bug_trap_type report_bug_entry(struct bug_entry *bug, struct pt_regs *regs); /* These are defined by the architecture */ int is_valid_bugaddr(unsigned long addr); @@ -62,6 +63,13 @@ static inline enum bug_trap_type report_bug(unsigned long bug_addr, } struct bug_entry; + +static inline enum bug_trap_type +report_bug_entry(struct bug_entry *bug, struct pt_regs *regs) +{ + return BUG_TRAP_TYPE_BUG; +} + static inline void bug_get_file_line(struct bug_entry *bug, const char **file, unsigned int *line) { diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 733e7f93db66..63e0e2aa1ce9 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -306,8 +306,7 @@ struct ceph_entity_addr *ceph_client_addr(struct ceph_client *client); u64 ceph_client_gid(struct ceph_client *client); extern void ceph_destroy_client(struct ceph_client *client); extern void ceph_reset_client_addr(struct ceph_client *client); -extern int __ceph_open_session(struct ceph_client *client, - unsigned long started); +extern int __ceph_open_session(struct ceph_client *client); extern int ceph_open_session(struct ceph_client *client); int ceph_wait_for_latest_osdmap(struct ceph_client *client, unsigned long timeout); diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h index 2573585b7f06..bacefa0f1512 100644 --- a/include/linux/cleanup.h +++ b/include/linux/cleanup.h @@ -261,6 +261,10 @@ const volatile void * __must_check_fn(const volatile void *val) * CLASS(name, var)(args...): * declare the variable @var as an instance of the named class * + * CLASS_INIT(name, var, init_expr): + * declare the variable @var as an instance of the named class with + * custom initialization expression. + * * Ex. * * DEFINE_CLASS(fdget, struct fd, fdput(_T), fdget(fd), int fd) @@ -290,15 +294,19 @@ static inline class_##_name##_t class_##_name##ext##_constructor(_init_args) \ class_##_name##_t var __cleanup(class_##_name##_destructor) = \ class_##_name##_constructor -#define scoped_class(_name, var, args) \ - for (CLASS(_name, var)(args); \ - __guard_ptr(_name)(&var) || !__is_cond_ptr(_name); \ - ({ goto _label; })) \ - if (0) { \ -_label: \ - break; \ +#define CLASS_INIT(_name, _var, _init_expr) \ + class_##_name##_t _var __cleanup(class_##_name##_destructor) = (_init_expr) + +#define __scoped_class(_name, var, _label, args...) \ + for (CLASS(_name, var)(args); ; ({ goto _label; })) \ + if (0) { \ +_label: \ + break; \ } else +#define scoped_class(_name, var, args...) \ + __scoped_class(_name, var, __UNIQUE_ID(label), args) + /* * DEFINE_GUARD(name, type, lock, unlock): * trivial wrapper around DEFINE_CLASS() above specifically @@ -340,6 +348,11 @@ _label: \ #define __DEFINE_CLASS_IS_CONDITIONAL(_name, _is_cond) \ static __maybe_unused const bool class_##_name##_is_conditional = _is_cond +#define DEFINE_CLASS_IS_UNCONDITIONAL(_name) \ + __DEFINE_CLASS_IS_CONDITIONAL(_name, false); \ + static inline void * class_##_name##_lock_ptr(class_##_name##_t *_T) \ + { return (void *)1; } + #define __GUARD_IS_ERR(_ptr) \ ({ \ unsigned long _rc = (__force unsigned long)(_ptr); \ diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 5b45ea7dff3e..ab181d87d71d 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -163,7 +163,11 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, __asm__ ("" : "=r" (var) : "0" (var)) #endif -#define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__) +/* Format: __UNIQUE_ID_<name>_<__COUNTER__> */ +#define __UNIQUE_ID(name) \ + __PASTE(__UNIQUE_ID_, \ + __PASTE(name, \ + __PASTE(_, __COUNTER__))) /** * data_race - mark an expression as containing intentional data races @@ -283,7 +287,7 @@ static inline void *offset_to_ptr(const int *off) */ #define ___ADDRESSABLE(sym, __attrs) \ static void * __used __attrs \ - __UNIQUE_ID(__PASTE(__addressable_,sym)) = (void *)(uintptr_t)&sym; + __UNIQUE_ID(__PASTE(addressable_, sym)) = (void *)(uintptr_t)&sym; #define __ADDRESSABLE(sym) \ ___ADDRESSABLE(sym, __section(".discard.addressable")) diff --git a/include/linux/cred.h b/include/linux/cred.h index 89ae50ad2ace..343a140a6ba2 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -20,6 +20,8 @@ struct cred; struct inode; +extern struct task_struct init_task; + /* * COW Supplementary groups list */ @@ -156,6 +158,11 @@ extern struct cred *prepare_exec_creds(void); extern int commit_creds(struct cred *); extern void abort_creds(struct cred *); extern struct cred *prepare_kernel_cred(struct task_struct *); +static inline const struct cred *kernel_cred(void) +{ + /* shut up sparse */ + return rcu_dereference_raw(init_task.cred); +} extern int set_security_override(struct cred *, u32); extern int set_security_override_from_ctx(struct cred *, const char *); extern int set_create_files_as(struct cred *, struct inode *); @@ -180,6 +187,16 @@ static inline const struct cred *revert_creds(const struct cred *revert_cred) return rcu_replace_pointer(current->cred, revert_cred, 1); } +DEFINE_CLASS(override_creds, + const struct cred *, + revert_creds(_T), + override_creds(override_cred), const struct cred *override_cred) + +#define scoped_with_creds(cred) \ + scoped_class(override_creds, __UNIQUE_ID(label), cred) + +#define scoped_with_kernel_creds() scoped_with_creds(kernel_cred()) + /** * get_cred_many - Get references on a set of credentials * @cred: The credentials to reference @@ -263,6 +280,11 @@ static inline void put_cred(const struct cred *cred) put_cred_many(cred, 1); } +DEFINE_CLASS(prepare_creds, + struct cred *, + if (_T) put_cred(_T), + prepare_creds(), void) + DEFINE_FREE(put_cred, struct cred *, if (!IS_ERR_OR_NULL(_T)) put_cred(_T)) /** diff --git a/include/linux/elfnote.h b/include/linux/elfnote.h index 69b136e4dd2b..bb3dcded055f 100644 --- a/include/linux/elfnote.h +++ b/include/linux/elfnote.h @@ -60,23 +60,21 @@ #else /* !__ASSEMBLER__ */ #include <uapi/linux/elf.h> +#include <linux/compiler.h> /* * Use an anonymous structure which matches the shape of * Elf{32,64}_Nhdr, but includes the name and desc data. The size and * type of name and desc depend on the macro arguments. "name" must - * be a literal string, and "desc" must be passed by value. You may - * only define one note per line, since __LINE__ is used to generate - * unique symbols. + * be a literal string, and "desc" must be passed by value. */ -#define _ELFNOTE_PASTE(a,b) a##b -#define _ELFNOTE(size, name, unique, type, desc) \ +#define ELFNOTE(size, name, type, desc) \ static const struct { \ struct elf##size##_note _nhdr; \ unsigned char _name[sizeof(name)] \ __attribute__((aligned(sizeof(Elf##size##_Word)))); \ typeof(desc) _desc \ __attribute__((aligned(sizeof(Elf##size##_Word)))); \ - } _ELFNOTE_PASTE(_note_, unique) \ + } __UNIQUE_ID(note) \ __used \ __attribute__((section(".note." name), \ aligned(sizeof(Elf##size##_Word)), \ @@ -89,11 +87,10 @@ name, \ desc \ } -#define ELFNOTE(size, name, type, desc) \ - _ELFNOTE(size, name, __LINE__, type, desc) #define ELFNOTE32(name, type, desc) ELFNOTE(32, name, type, desc) #define ELFNOTE64(name, type, desc) ELFNOTE(64, name, type, desc) + #endif /* __ASSEMBLER__ */ #endif /* _LINUX_ELFNOTE_H */ diff --git a/include/linux/file.h b/include/linux/file.h index af1768d934a0..cf389fde9bc2 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -127,4 +127,130 @@ extern void __fput_sync(struct file *); extern unsigned int sysctl_nr_open_min, sysctl_nr_open_max; +/* + * fd_prepare: Combined fd + file allocation cleanup class. + * @err: Error code to indicate if allocation succeeded. + * @__fd: Allocated fd (may not be accessed directly) + * @__file: Allocated struct file pointer (may not be accessed directly) + * + * Allocates an fd and a file together. On error paths, automatically cleans + * up whichever resource was successfully allocated. Allows flexible file + * allocation with different functions per usage. + * + * Do not use directly. + */ +struct fd_prepare { + s32 err; + s32 __fd; /* do not access directly */ + struct file *__file; /* do not access directly */ +}; + +/* Typedef for fd_prepare cleanup guards. */ +typedef struct fd_prepare class_fd_prepare_t; + +/* + * Accessors for fd_prepare class members. + * _Generic() is used for zero-cost type safety. + */ +#define fd_prepare_fd(_fdf) \ + (_Generic((_fdf), struct fd_prepare: (_fdf).__fd)) + +#define fd_prepare_file(_fdf) \ + (_Generic((_fdf), struct fd_prepare: (_fdf).__file)) + +/* Do not use directly. */ +static inline void class_fd_prepare_destructor(const struct fd_prepare *fdf) +{ + if (unlikely(fdf->err)) { + if (likely(fdf->__fd >= 0)) + put_unused_fd(fdf->__fd); + if (unlikely(!IS_ERR_OR_NULL(fdf->__file))) + fput(fdf->__file); + } +} + +/* Do not use directly. */ +static inline int class_fd_prepare_lock_err(const struct fd_prepare *fdf) +{ + if (unlikely(fdf->err)) + return fdf->err; + if (unlikely(fdf->__fd < 0)) + return fdf->__fd; + if (unlikely(IS_ERR(fdf->__file))) + return PTR_ERR(fdf->__file); + if (unlikely(!fdf->__file)) + return -ENOMEM; + return 0; +} + +/* + * __FD_PREPARE_INIT - Helper to initialize fd_prepare class. + * @_fd_flags: flags for get_unused_fd_flags() + * @_file_owned: expression that returns struct file * + * + * Returns a struct fd_prepare with fd, file, and err set. + * If fd allocation fails, fd will be negative and err will be set. If + * fd succeeds but file_init_expr fails, file will be ERR_PTR and err + * will be set. The err field is the single source of truth for error + * checking. + */ +#define __FD_PREPARE_INIT(_fd_flags, _file_owned) \ + ({ \ + struct fd_prepare fdf = { \ + .__fd = get_unused_fd_flags((_fd_flags)), \ + }; \ + if (likely(fdf.__fd >= 0)) \ + fdf.__file = (_file_owned); \ + fdf.err = ACQUIRE_ERR(fd_prepare, &fdf); \ + fdf; \ + }) + +/* + * FD_PREPARE - Macro to declare and initialize an fd_prepare variable. + * + * Declares and initializes an fd_prepare variable with automatic + * cleanup. No separate scope required - cleanup happens when variable + * goes out of scope. + * + * @_fdf: name of struct fd_prepare variable to define + * @_fd_flags: flags for get_unused_fd_flags() + * @_file_owned: struct file to take ownership of (can be expression) + */ +#define FD_PREPARE(_fdf, _fd_flags, _file_owned) \ + CLASS_INIT(fd_prepare, _fdf, __FD_PREPARE_INIT(_fd_flags, _file_owned)) + +/* + * fd_publish - Publish prepared fd and file to the fd table. + * @_fdf: struct fd_prepare variable + */ +#define fd_publish(_fdf) \ + ({ \ + struct fd_prepare *fdp = &(_fdf); \ + VFS_WARN_ON_ONCE(fdp->err); \ + VFS_WARN_ON_ONCE(fdp->__fd < 0); \ + VFS_WARN_ON_ONCE(IS_ERR_OR_NULL(fdp->__file)); \ + fd_install(fdp->__fd, fdp->__file); \ + fdp->__fd; \ + }) + +/* Do not use directly. */ +#define __FD_ADD(_fdf, _fd_flags, _file_owned) \ + ({ \ + FD_PREPARE(_fdf, _fd_flags, _file_owned); \ + s32 ret = _fdf.err; \ + if (likely(!ret)) \ + ret = fd_publish(_fdf); \ + ret; \ + }) + +/* + * FD_ADD - Allocate and install an fd and file in one step. + * @_fd_flags: flags for get_unused_fd_flags() + * @_file_owned: struct file to take ownership of + * + * Returns the allocated fd number, or negative error code on failure. + */ +#define FD_ADD(_fd_flags, _file_owned) \ + __FD_ADD(__UNIQUE_ID(fd_prepare), _fd_flags, _file_owned) + #endif /* __LINUX_FILE_H */ diff --git a/include/linux/filelock.h b/include/linux/filelock.h index c2ce8ba05d06..54b824c05299 100644 --- a/include/linux/filelock.h +++ b/include/linux/filelock.h @@ -159,6 +159,8 @@ int fcntl_setlk64(unsigned int, struct file *, unsigned int, int fcntl_setlease(unsigned int fd, struct file *filp, int arg); int fcntl_getlease(struct file *filp); +int fcntl_setdeleg(unsigned int fd, struct file *filp, struct delegation *deleg); +int fcntl_getdeleg(struct file *filp, struct delegation *deleg); static inline bool lock_is_unlock(struct file_lock *fl) { @@ -212,7 +214,14 @@ int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl); void locks_init_lease(struct file_lease *); void locks_free_lease(struct file_lease *fl); struct file_lease *locks_alloc_lease(void); -int __break_lease(struct inode *inode, unsigned int flags, unsigned int type); + +#define LEASE_BREAK_LEASE BIT(0) // break leases and delegations +#define LEASE_BREAK_DELEG BIT(1) // break delegations only +#define LEASE_BREAK_LAYOUT BIT(2) // break layouts only +#define LEASE_BREAK_NONBLOCK BIT(3) // non-blocking break +#define LEASE_BREAK_OPEN_RDONLY BIT(4) // readonly open event + +int __break_lease(struct inode *inode, unsigned int flags); void lease_get_mtime(struct inode *, struct timespec64 *time); int generic_setlease(struct file *, int, struct file_lease **, void **priv); int kernel_setlease(struct file *, int, struct file_lease **, void **); @@ -271,6 +280,16 @@ static inline int fcntl_getlease(struct file *filp) return F_UNLCK; } +static inline int fcntl_setdeleg(unsigned int fd, struct file *filp, struct delegation *deleg) +{ + return -EINVAL; +} + +static inline int fcntl_getdeleg(struct file *filp, struct delegation *deleg) +{ + return -EINVAL; +} + static inline bool lock_is_unlock(struct file_lock *fl) { return false; @@ -367,7 +386,7 @@ static inline int locks_lock_inode_wait(struct inode *inode, struct file_lock *f return -ENOLCK; } -static inline int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) +static inline int __break_lease(struct inode *inode, unsigned int flags) { return 0; } @@ -428,6 +447,17 @@ static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl) } #ifdef CONFIG_FILE_LOCKING +static inline unsigned int openmode_to_lease_flags(unsigned int mode) +{ + unsigned int flags = 0; + + if ((mode & O_ACCMODE) == O_RDONLY) + flags |= LEASE_BREAK_OPEN_RDONLY; + if (mode & O_NONBLOCK) + flags |= LEASE_BREAK_NONBLOCK; + return flags; +} + static inline int break_lease(struct inode *inode, unsigned int mode) { struct file_lock_context *flctx; @@ -443,11 +473,11 @@ static inline int break_lease(struct inode *inode, unsigned int mode) return 0; smp_mb(); if (!list_empty_careful(&flctx->flc_lease)) - return __break_lease(inode, mode, FL_LEASE); + return __break_lease(inode, LEASE_BREAK_LEASE | openmode_to_lease_flags(mode)); return 0; } -static inline int break_deleg(struct inode *inode, unsigned int mode) +static inline int break_deleg(struct inode *inode, unsigned int flags) { struct file_lock_context *flctx; @@ -461,60 +491,84 @@ static inline int break_deleg(struct inode *inode, unsigned int mode) if (!flctx) return 0; smp_mb(); - if (!list_empty_careful(&flctx->flc_lease)) - return __break_lease(inode, mode, FL_DELEG); + if (!list_empty_careful(&flctx->flc_lease)) { + flags |= LEASE_BREAK_DELEG; + return __break_lease(inode, flags); + } return 0; } -static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode) +struct delegated_inode { + struct inode *di_inode; +}; + +static inline bool is_delegated(struct delegated_inode *di) +{ + return di->di_inode; +} + +static inline int try_break_deleg(struct inode *inode, + struct delegated_inode *di) { int ret; - ret = break_deleg(inode, O_WRONLY|O_NONBLOCK); - if (ret == -EWOULDBLOCK && delegated_inode) { - *delegated_inode = inode; + ret = break_deleg(inode, LEASE_BREAK_NONBLOCK); + if (ret == -EWOULDBLOCK && di) { + di->di_inode = inode; ihold(inode); } return ret; } -static inline int break_deleg_wait(struct inode **delegated_inode) +static inline int break_deleg_wait(struct delegated_inode *di) { int ret; - ret = break_deleg(*delegated_inode, O_WRONLY); - iput(*delegated_inode); - *delegated_inode = NULL; + ret = break_deleg(di->di_inode, 0); + iput(di->di_inode); + di->di_inode = NULL; return ret; } static inline int break_layout(struct inode *inode, bool wait) { smp_mb(); - if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) - return __break_lease(inode, - wait ? O_WRONLY : O_WRONLY | O_NONBLOCK, - FL_LAYOUT); + if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) { + unsigned int flags = LEASE_BREAK_LAYOUT; + + if (!wait) + flags |= LEASE_BREAK_NONBLOCK; + + return __break_lease(inode, flags); + } return 0; } #else /* !CONFIG_FILE_LOCKING */ -static inline int break_lease(struct inode *inode, unsigned int mode) +struct delegated_inode { }; + +static inline bool is_delegated(struct delegated_inode *di) +{ + return false; +} + +static inline int break_lease(struct inode *inode, bool wait) { return 0; } -static inline int break_deleg(struct inode *inode, unsigned int mode) +static inline int break_deleg(struct inode *inode, unsigned int flags) { return 0; } -static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode) +static inline int try_break_deleg(struct inode *inode, + struct delegated_inode *delegated_inode) { return 0; } -static inline int break_deleg_wait(struct inode **delegated_inode) +static inline int break_deleg_wait(struct delegated_inode *delegated_inode) { BUG(); return 0; diff --git a/include/linux/fs.h b/include/linux/fs.h index dd3b57cfadee..ce25feb06727 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2,6 +2,7 @@ #ifndef _LINUX_FS_H #define _LINUX_FS_H +#include <linux/fs/super.h> #include <linux/vfsdebug.h> #include <linux/linkage.h> #include <linux/wait_bit.h> @@ -11,7 +12,6 @@ #include <linux/stat.h> #include <linux/cache.h> #include <linux/list.h> -#include <linux/list_lru.h> #include <linux/llist.h> #include <linux/radix-tree.h> #include <linux/xarray.h> @@ -37,7 +37,6 @@ #include <linux/uuid.h> #include <linux/errseq.h> #include <linux/ioprio.h> -#include <linux/fs_types.h> #include <linux/build_bug.h> #include <linux/stddef.h> #include <linux/mount.h> @@ -52,11 +51,9 @@ #include <asm/byteorder.h> #include <uapi/linux/fs.h> -struct backing_dev_info; struct bdi_writeback; struct bio; struct io_comp_batch; -struct export_operations; struct fiemap_extent_info; struct hd_geometry; struct iovec; @@ -70,16 +67,13 @@ struct vfsmount; struct cred; struct swap_info_struct; struct seq_file; -struct workqueue_struct; struct iov_iter; -struct fscrypt_operations; -struct fsverity_operations; struct fsnotify_mark_connector; -struct fsnotify_sb_info; struct fs_context; struct fs_parameter_spec; struct file_kattr; struct iomap_ops; +struct delegated_inode; extern void __init inode_init(void); extern void __init inode_init_early(void); @@ -299,11 +293,6 @@ struct iattr { }; /* - * Includes for diskquotas. - */ -#include <linux/quota.h> - -/* * Maximum number of layers of fs stack. Needs to be limited to * prevent kernel stack overflow */ @@ -367,23 +356,9 @@ struct readahead_control; #define IOCB_NOIO (1 << 20) /* can use bio alloc cache */ #define IOCB_ALLOC_CACHE (1 << 21) -/* - * IOCB_DIO_CALLER_COMP can be set by the iocb owner, to indicate that the - * iocb completion can be passed back to the owner for execution from a safe - * context rather than needing to be punted through a workqueue. If this - * flag is set, the bio completion handling may set iocb->dio_complete to a - * handler function and iocb->private to context information for that handler. - * The issuer should call the handler with that context information from task - * context to complete the processing of the iocb. Note that while this - * provides a task context for the dio_complete() callback, it should only be - * used on the completion side for non-IO generating completions. It's fine to - * call blocking functions from this callback, but they should not wait for - * unrelated IO (like cache flushing, new IO generation, etc). - */ -#define IOCB_DIO_CALLER_COMP (1 << 22) /* kiocb is a read or write operation submitted by fs/aio.c. */ -#define IOCB_AIO_RW (1 << 23) -#define IOCB_HAS_METADATA (1 << 24) +#define IOCB_AIO_RW (1 << 22) +#define IOCB_HAS_METADATA (1 << 23) /* for use in trace events */ #define TRACE_IOCB_STRINGS \ @@ -400,7 +375,6 @@ struct readahead_control; { IOCB_WAITQ, "WAITQ" }, \ { IOCB_NOIO, "NOIO" }, \ { IOCB_ALLOC_CACHE, "ALLOC_CACHE" }, \ - { IOCB_DIO_CALLER_COMP, "CALLER_COMP" }, \ { IOCB_AIO_RW, "AIO_RW" }, \ { IOCB_HAS_METADATA, "AIO_HAS_METADATA" } @@ -412,23 +386,13 @@ struct kiocb { int ki_flags; u16 ki_ioprio; /* See linux/ioprio.h */ u8 ki_write_stream; - union { - /* - * Only used for async buffered reads, where it denotes the - * page waitqueue associated with completing the read. Valid - * IFF IOCB_WAITQ is set. - */ - struct wait_page_queue *ki_waitq; - /* - * Can be used for O_DIRECT IO, where the completion handling - * is punted back to the issuer of the IO. May only be set - * if IOCB_DIO_CALLER_COMP is set by the issuer, and the issuer - * must then check for presence of this handler when ki_complete - * is invoked. The data passed in to this handler must be - * assigned to ->private when dio_complete is assigned. - */ - ssize_t (*dio_complete)(void *data); - }; + + /* + * Only used for async buffered reads, where it denotes the page + * waitqueue associated with completing the read. + * Valid IFF IOCB_WAITQ is set. + */ + struct wait_page_queue *ki_waitq; }; static inline bool is_sync_kiocb(struct kiocb *kiocb) @@ -659,13 +623,14 @@ is_uncached_acl(struct posix_acl *acl) return (long)acl & 1; } -#define IOP_FASTPERM 0x0001 -#define IOP_LOOKUP 0x0002 -#define IOP_NOFOLLOW 0x0004 -#define IOP_XATTR 0x0008 +#define IOP_FASTPERM 0x0001 +#define IOP_LOOKUP 0x0002 +#define IOP_NOFOLLOW 0x0004 +#define IOP_XATTR 0x0008 #define IOP_DEFAULT_READLINK 0x0010 -#define IOP_MGTIME 0x0020 -#define IOP_CACHED_LINK 0x0040 +#define IOP_MGTIME 0x0020 +#define IOP_CACHED_LINK 0x0040 +#define IOP_FASTPERM_MAY_EXEC 0x0080 /* * Inode state bits. Protected by inode->i_lock @@ -759,7 +724,7 @@ enum inode_state_bits { /* reserved wait address bit 3 */ }; -enum inode_state_flags_t { +enum inode_state_flags_enum { I_NEW = (1U << __I_NEW), I_SYNC = (1U << __I_SYNC), I_LRU_ISOLATING = (1U << __I_LRU_ISOLATING), @@ -786,6 +751,13 @@ enum inode_state_flags_t { #define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME) /* + * Use inode_state_read() & friends to access. + */ +struct inode_state_flags { + enum inode_state_flags_enum __state; +}; + +/* * Keep mostly read-only and often accessed (especially for * the RCU path lookup and 'stat' data) fields at the beginning * of the 'struct inode' @@ -793,14 +765,13 @@ enum inode_state_flags_t { struct inode { umode_t i_mode; unsigned short i_opflags; - kuid_t i_uid; - kgid_t i_gid; unsigned int i_flags; - #ifdef CONFIG_FS_POSIX_ACL struct posix_acl *i_acl; struct posix_acl *i_default_acl; #endif + kuid_t i_uid; + kgid_t i_gid; const struct inode_operations *i_op; struct super_block *i_sb; @@ -843,7 +814,7 @@ struct inode { #endif /* Misc */ - enum inode_state_flags_t i_state; + struct inode_state_flags i_state; /* 32-bit hole */ struct rw_semaphore i_rwsem; @@ -902,6 +873,80 @@ struct inode { void *i_private; /* fs or device private pointer */ } __randomize_layout; +/* + * i_state handling + * + * We hide all of it behind helpers so that we can validate consumers. + */ +static inline enum inode_state_flags_enum inode_state_read_once(struct inode *inode) +{ + return READ_ONCE(inode->i_state.__state); +} + +static inline enum inode_state_flags_enum inode_state_read(struct inode *inode) +{ + lockdep_assert_held(&inode->i_lock); + return inode->i_state.__state; +} + +static inline void inode_state_set_raw(struct inode *inode, + enum inode_state_flags_enum flags) +{ + WRITE_ONCE(inode->i_state.__state, inode->i_state.__state | flags); +} + +static inline void inode_state_set(struct inode *inode, + enum inode_state_flags_enum flags) +{ + lockdep_assert_held(&inode->i_lock); + inode_state_set_raw(inode, flags); +} + +static inline void inode_state_clear_raw(struct inode *inode, + enum inode_state_flags_enum flags) +{ + WRITE_ONCE(inode->i_state.__state, inode->i_state.__state & ~flags); +} + +static inline void inode_state_clear(struct inode *inode, + enum inode_state_flags_enum flags) +{ + lockdep_assert_held(&inode->i_lock); + inode_state_clear_raw(inode, flags); +} + +static inline void inode_state_assign_raw(struct inode *inode, + enum inode_state_flags_enum flags) +{ + WRITE_ONCE(inode->i_state.__state, flags); +} + +static inline void inode_state_assign(struct inode *inode, + enum inode_state_flags_enum flags) +{ + lockdep_assert_held(&inode->i_lock); + inode_state_assign_raw(inode, flags); +} + +static inline void inode_state_replace_raw(struct inode *inode, + enum inode_state_flags_enum clearflags, + enum inode_state_flags_enum setflags) +{ + enum inode_state_flags_enum flags; + flags = inode->i_state.__state; + flags &= ~clearflags; + flags |= setflags; + inode_state_assign_raw(inode, flags); +} + +static inline void inode_state_replace(struct inode *inode, + enum inode_state_flags_enum clearflags, + enum inode_state_flags_enum setflags) +{ + lockdep_assert_held(&inode->i_lock); + inode_state_replace_raw(inode, clearflags, setflags); +} + static inline void inode_set_cached_link(struct inode *inode, char *link, int linklen) { VFS_WARN_ON_INODE(strlen(link) != linklen, inode); @@ -949,6 +994,8 @@ static inline void inode_fake_hash(struct inode *inode) hlist_add_fake(&inode->i_hash); } +void wait_on_new_inode(struct inode *inode); + /* * inode->i_rwsem nesting subclasses for the lock validator: * @@ -1348,49 +1395,6 @@ extern pid_t f_getown(struct file *filp); extern int send_sigurg(struct file *file); /* - * sb->s_flags. Note that these mirror the equivalent MS_* flags where - * represented in both. - */ -#define SB_RDONLY BIT(0) /* Mount read-only */ -#define SB_NOSUID BIT(1) /* Ignore suid and sgid bits */ -#define SB_NODEV BIT(2) /* Disallow access to device special files */ -#define SB_NOEXEC BIT(3) /* Disallow program execution */ -#define SB_SYNCHRONOUS BIT(4) /* Writes are synced at once */ -#define SB_MANDLOCK BIT(6) /* Allow mandatory locks on an FS */ -#define SB_DIRSYNC BIT(7) /* Directory modifications are synchronous */ -#define SB_NOATIME BIT(10) /* Do not update access times. */ -#define SB_NODIRATIME BIT(11) /* Do not update directory access times */ -#define SB_SILENT BIT(15) -#define SB_POSIXACL BIT(16) /* Supports POSIX ACLs */ -#define SB_INLINECRYPT BIT(17) /* Use blk-crypto for encrypted files */ -#define SB_KERNMOUNT BIT(22) /* this is a kern_mount call */ -#define SB_I_VERSION BIT(23) /* Update inode I_version field */ -#define SB_LAZYTIME BIT(25) /* Update the on-disk [acm]times lazily */ - -/* These sb flags are internal to the kernel */ -#define SB_DEAD BIT(21) -#define SB_DYING BIT(24) -#define SB_FORCE BIT(27) -#define SB_NOSEC BIT(28) -#define SB_BORN BIT(29) -#define SB_ACTIVE BIT(30) -#define SB_NOUSER BIT(31) - -/* These flags relate to encoding and casefolding */ -#define SB_ENC_STRICT_MODE_FL (1 << 0) -#define SB_ENC_NO_COMPAT_FALLBACK_FL (1 << 1) - -#define sb_has_strict_encoding(sb) \ - (sb->s_encoding_flags & SB_ENC_STRICT_MODE_FL) - -#if IS_ENABLED(CONFIG_UNICODE) -#define sb_no_casefold_compat_fallback(sb) \ - (sb->s_encoding_flags & SB_ENC_NO_COMPAT_FALLBACK_FL) -#else -#define sb_no_casefold_compat_fallback(sb) (1) -#endif - -/* * Umount options */ @@ -1400,191 +1404,6 @@ extern int send_sigurg(struct file *file); #define UMOUNT_NOFOLLOW 0x00000008 /* Don't follow symlink on umount */ #define UMOUNT_UNUSED 0x80000000 /* Flag guaranteed to be unused */ -/* sb->s_iflags */ -#define SB_I_CGROUPWB 0x00000001 /* cgroup-aware writeback enabled */ -#define SB_I_NOEXEC 0x00000002 /* Ignore executables on this fs */ -#define SB_I_NODEV 0x00000004 /* Ignore devices on this fs */ -#define SB_I_STABLE_WRITES 0x00000008 /* don't modify blks until WB is done */ - -/* sb->s_iflags to limit user namespace mounts */ -#define SB_I_USERNS_VISIBLE 0x00000010 /* fstype already mounted */ -#define SB_I_IMA_UNVERIFIABLE_SIGNATURE 0x00000020 -#define SB_I_UNTRUSTED_MOUNTER 0x00000040 -#define SB_I_EVM_HMAC_UNSUPPORTED 0x00000080 - -#define SB_I_SKIP_SYNC 0x00000100 /* Skip superblock at global sync */ -#define SB_I_PERSB_BDI 0x00000200 /* has a per-sb bdi */ -#define SB_I_TS_EXPIRY_WARNED 0x00000400 /* warned about timestamp range expiry */ -#define SB_I_RETIRED 0x00000800 /* superblock shouldn't be reused */ -#define SB_I_NOUMASK 0x00001000 /* VFS does not apply umask */ -#define SB_I_NOIDMAP 0x00002000 /* No idmapped mounts on this superblock */ -#define SB_I_ALLOW_HSM 0x00004000 /* Allow HSM events on this superblock */ - -/* Possible states of 'frozen' field */ -enum { - SB_UNFROZEN = 0, /* FS is unfrozen */ - SB_FREEZE_WRITE = 1, /* Writes, dir ops, ioctls frozen */ - SB_FREEZE_PAGEFAULT = 2, /* Page faults stopped as well */ - SB_FREEZE_FS = 3, /* For internal FS use (e.g. to stop - * internal threads if needed) */ - SB_FREEZE_COMPLETE = 4, /* ->freeze_fs finished successfully */ -}; - -#define SB_FREEZE_LEVELS (SB_FREEZE_COMPLETE - 1) - -struct sb_writers { - unsigned short frozen; /* Is sb frozen? */ - int freeze_kcount; /* How many kernel freeze requests? */ - int freeze_ucount; /* How many userspace freeze requests? */ - const void *freeze_owner; /* Owner of the freeze */ - struct percpu_rw_semaphore rw_sem[SB_FREEZE_LEVELS]; -}; - -struct mount; - -struct super_block { - struct list_head s_list; /* Keep this first */ - dev_t s_dev; /* search index; _not_ kdev_t */ - unsigned char s_blocksize_bits; - unsigned long s_blocksize; - loff_t s_maxbytes; /* Max file size */ - struct file_system_type *s_type; - const struct super_operations *s_op; - const struct dquot_operations *dq_op; - const struct quotactl_ops *s_qcop; - const struct export_operations *s_export_op; - unsigned long s_flags; - unsigned long s_iflags; /* internal SB_I_* flags */ - unsigned long s_magic; - struct dentry *s_root; - struct rw_semaphore s_umount; - int s_count; - atomic_t s_active; -#ifdef CONFIG_SECURITY - void *s_security; -#endif - const struct xattr_handler * const *s_xattr; -#ifdef CONFIG_FS_ENCRYPTION - const struct fscrypt_operations *s_cop; - struct fscrypt_keyring *s_master_keys; /* master crypto keys in use */ -#endif -#ifdef CONFIG_FS_VERITY - const struct fsverity_operations *s_vop; -#endif -#if IS_ENABLED(CONFIG_UNICODE) - struct unicode_map *s_encoding; - __u16 s_encoding_flags; -#endif - struct hlist_bl_head s_roots; /* alternate root dentries for NFS */ - struct mount *s_mounts; /* list of mounts; _not_ for fs use */ - struct block_device *s_bdev; /* can go away once we use an accessor for @s_bdev_file */ - struct file *s_bdev_file; - struct backing_dev_info *s_bdi; - struct mtd_info *s_mtd; - struct hlist_node s_instances; - unsigned int s_quota_types; /* Bitmask of supported quota types */ - struct quota_info s_dquot; /* Diskquota specific options */ - - struct sb_writers s_writers; - - /* - * Keep s_fs_info, s_time_gran, s_fsnotify_mask, and - * s_fsnotify_info together for cache efficiency. They are frequently - * accessed and rarely modified. - */ - void *s_fs_info; /* Filesystem private info */ - - /* Granularity of c/m/atime in ns (cannot be worse than a second) */ - u32 s_time_gran; - /* Time limits for c/m/atime in seconds */ - time64_t s_time_min; - time64_t s_time_max; -#ifdef CONFIG_FSNOTIFY - u32 s_fsnotify_mask; - struct fsnotify_sb_info *s_fsnotify_info; -#endif - - /* - * q: why are s_id and s_sysfs_name not the same? both are human - * readable strings that identify the filesystem - * a: s_id is allowed to change at runtime; it's used in log messages, - * and we want to when a device starts out as single device (s_id is dev - * name) but then a device is hot added and we have to switch to - * identifying it by UUID - * but s_sysfs_name is a handle for programmatic access, and can't - * change at runtime - */ - char s_id[32]; /* Informational name */ - uuid_t s_uuid; /* UUID */ - u8 s_uuid_len; /* Default 16, possibly smaller for weird filesystems */ - - /* if set, fs shows up under sysfs at /sys/fs/$FSTYP/s_sysfs_name */ - char s_sysfs_name[UUID_STRING_LEN + 1]; - - unsigned int s_max_links; - unsigned int s_d_flags; /* default d_flags for dentries */ - - /* - * The next field is for VFS *only*. No filesystems have any business - * even looking at it. You had been warned. - */ - struct mutex s_vfs_rename_mutex; /* Kludge */ - - /* - * Filesystem subtype. If non-empty the filesystem type field - * in /proc/mounts will be "type.subtype" - */ - const char *s_subtype; - - const struct dentry_operations *__s_d_op; /* default d_op for dentries */ - - struct shrinker *s_shrink; /* per-sb shrinker handle */ - - /* Number of inodes with nlink == 0 but still referenced */ - atomic_long_t s_remove_count; - - /* Read-only state of the superblock is being changed */ - int s_readonly_remount; - - /* per-sb errseq_t for reporting writeback errors via syncfs */ - errseq_t s_wb_err; - - /* AIO completions deferred from interrupt context */ - struct workqueue_struct *s_dio_done_wq; - struct hlist_head s_pins; - - /* - * Owning user namespace and default context in which to - * interpret filesystem uids, gids, quotas, device nodes, - * xattrs and security labels. - */ - struct user_namespace *s_user_ns; - - /* - * The list_lru structure is essentially just a pointer to a table - * of per-node lru lists, each of which has its own spinlock. - * There is no need to put them into separate cachelines. - */ - struct list_lru s_dentry_lru; - struct list_lru s_inode_lru; - struct rcu_head rcu; - struct work_struct destroy_work; - - struct mutex s_sync_lock; /* sync serialisation lock */ - - /* - * Indicates how deep in a filesystem stack this SB is - */ - int s_stack_depth; - - /* s_inode_list_lock protects s_inodes */ - spinlock_t s_inode_list_lock ____cacheline_aligned_in_smp; - struct list_head s_inodes; /* all inodes */ - - spinlock_t s_inode_wblist_lock; - struct list_head s_inodes_wb; /* writeback inodes */ -} __randomize_layout; - static inline struct user_namespace *i_user_ns(const struct inode *inode) { return inode->i_sb->s_user_ns; @@ -1902,66 +1721,6 @@ struct timespec64 simple_inode_init_ts(struct inode *inode); * Snapshotting support. */ -/* - * These are internal functions, please use sb_start_{write,pagefault,intwrite} - * instead. - */ -static inline void __sb_end_write(struct super_block *sb, int level) -{ - percpu_up_read(sb->s_writers.rw_sem + level-1); -} - -static inline void __sb_start_write(struct super_block *sb, int level) -{ - percpu_down_read_freezable(sb->s_writers.rw_sem + level - 1, true); -} - -static inline bool __sb_start_write_trylock(struct super_block *sb, int level) -{ - return percpu_down_read_trylock(sb->s_writers.rw_sem + level - 1); -} - -#define __sb_writers_acquired(sb, lev) \ - percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_) -#define __sb_writers_release(sb, lev) \ - percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev)-1], _THIS_IP_) - -/** - * __sb_write_started - check if sb freeze level is held - * @sb: the super we write to - * @level: the freeze level - * - * * > 0 - sb freeze level is held - * * 0 - sb freeze level is not held - * * < 0 - !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN - */ -static inline int __sb_write_started(const struct super_block *sb, int level) -{ - return lockdep_is_held_type(sb->s_writers.rw_sem + level - 1, 1); -} - -/** - * sb_write_started - check if SB_FREEZE_WRITE is held - * @sb: the super we write to - * - * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. - */ -static inline bool sb_write_started(const struct super_block *sb) -{ - return __sb_write_started(sb, SB_FREEZE_WRITE); -} - -/** - * sb_write_not_started - check if SB_FREEZE_WRITE is not held - * @sb: the super we write to - * - * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. - */ -static inline bool sb_write_not_started(const struct super_block *sb) -{ - return __sb_write_started(sb, SB_FREEZE_WRITE) <= 0; -} - /** * file_write_started - check if SB_FREEZE_WRITE is held * @file: the file we write to @@ -1992,137 +1751,26 @@ static inline bool file_write_not_started(const struct file *file) return sb_write_not_started(file_inode(file)->i_sb); } -/** - * sb_end_write - drop write access to a superblock - * @sb: the super we wrote to - * - * Decrement number of writers to the filesystem. Wake up possible waiters - * wanting to freeze the filesystem. - */ -static inline void sb_end_write(struct super_block *sb) -{ - __sb_end_write(sb, SB_FREEZE_WRITE); -} - -/** - * sb_end_pagefault - drop write access to a superblock from a page fault - * @sb: the super we wrote to - * - * Decrement number of processes handling write page fault to the filesystem. - * Wake up possible waiters wanting to freeze the filesystem. - */ -static inline void sb_end_pagefault(struct super_block *sb) -{ - __sb_end_write(sb, SB_FREEZE_PAGEFAULT); -} - -/** - * sb_end_intwrite - drop write access to a superblock for internal fs purposes - * @sb: the super we wrote to - * - * Decrement fs-internal number of writers to the filesystem. Wake up possible - * waiters wanting to freeze the filesystem. - */ -static inline void sb_end_intwrite(struct super_block *sb) -{ - __sb_end_write(sb, SB_FREEZE_FS); -} - -/** - * sb_start_write - get write access to a superblock - * @sb: the super we write to - * - * When a process wants to write data or metadata to a file system (i.e. dirty - * a page or an inode), it should embed the operation in a sb_start_write() - - * sb_end_write() pair to get exclusion against file system freezing. This - * function increments number of writers preventing freezing. If the file - * system is already frozen, the function waits until the file system is - * thawed. - * - * Since freeze protection behaves as a lock, users have to preserve - * ordering of freeze protection and other filesystem locks. Generally, - * freeze protection should be the outermost lock. In particular, we have: - * - * sb_start_write - * -> i_rwsem (write path, truncate, directory ops, ...) - * -> s_umount (freeze_super, thaw_super) - */ -static inline void sb_start_write(struct super_block *sb) -{ - __sb_start_write(sb, SB_FREEZE_WRITE); -} - -static inline bool sb_start_write_trylock(struct super_block *sb) -{ - return __sb_start_write_trylock(sb, SB_FREEZE_WRITE); -} - -/** - * sb_start_pagefault - get write access to a superblock from a page fault - * @sb: the super we write to - * - * When a process starts handling write page fault, it should embed the - * operation into sb_start_pagefault() - sb_end_pagefault() pair to get - * exclusion against file system freezing. This is needed since the page fault - * is going to dirty a page. This function increments number of running page - * faults preventing freezing. If the file system is already frozen, the - * function waits until the file system is thawed. - * - * Since page fault freeze protection behaves as a lock, users have to preserve - * ordering of freeze protection and other filesystem locks. It is advised to - * put sb_start_pagefault() close to mmap_lock in lock ordering. Page fault - * handling code implies lock dependency: - * - * mmap_lock - * -> sb_start_pagefault - */ -static inline void sb_start_pagefault(struct super_block *sb) -{ - __sb_start_write(sb, SB_FREEZE_PAGEFAULT); -} - -/** - * sb_start_intwrite - get write access to a superblock for internal fs purposes - * @sb: the super we write to - * - * This is the third level of protection against filesystem freezing. It is - * free for use by a filesystem. The only requirement is that it must rank - * below sb_start_pagefault. - * - * For example filesystem can call sb_start_intwrite() when starting a - * transaction which somewhat eases handling of freezing for internal sources - * of filesystem changes (internal fs threads, discarding preallocation on file - * close, etc.). - */ -static inline void sb_start_intwrite(struct super_block *sb) -{ - __sb_start_write(sb, SB_FREEZE_FS); -} - -static inline bool sb_start_intwrite_trylock(struct super_block *sb) -{ - return __sb_start_write_trylock(sb, SB_FREEZE_FS); -} - bool inode_owner_or_capable(struct mnt_idmap *idmap, const struct inode *inode); /* * VFS helper functions.. */ -int vfs_create(struct mnt_idmap *, struct inode *, - struct dentry *, umode_t, bool); +int vfs_create(struct mnt_idmap *, struct dentry *, umode_t, + struct delegated_inode *); struct dentry *vfs_mkdir(struct mnt_idmap *, struct inode *, - struct dentry *, umode_t); + struct dentry *, umode_t, struct delegated_inode *); int vfs_mknod(struct mnt_idmap *, struct inode *, struct dentry *, - umode_t, dev_t); + umode_t, dev_t, struct delegated_inode *); int vfs_symlink(struct mnt_idmap *, struct inode *, - struct dentry *, const char *); + struct dentry *, const char *, struct delegated_inode *); int vfs_link(struct dentry *, struct mnt_idmap *, struct inode *, - struct dentry *, struct inode **); -int vfs_rmdir(struct mnt_idmap *, struct inode *, struct dentry *); + struct dentry *, struct delegated_inode *); +int vfs_rmdir(struct mnt_idmap *, struct inode *, struct dentry *, + struct delegated_inode *); int vfs_unlink(struct mnt_idmap *, struct inode *, struct dentry *, - struct inode **); + struct delegated_inode *); /** * struct renamedata - contains all information required for renaming @@ -2140,7 +1788,7 @@ struct renamedata { struct dentry *old_dentry; struct dentry *new_parent; struct dentry *new_dentry; - struct inode **delegated_inode; + struct delegated_inode *delegated_inode; unsigned int flags; } __randomize_layout; @@ -2150,7 +1798,7 @@ static inline int vfs_whiteout(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry) { return vfs_mknod(idmap, dir, dentry, S_IFCHR | WHITEOUT_MODE, - WHITEOUT_DEV); + WHITEOUT_DEV, NULL); } struct file *kernel_tmpfile_open(struct mnt_idmap *idmap, @@ -2431,72 +2079,6 @@ extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, struct file *dst_file, loff_t dst_pos, loff_t len, unsigned int remap_flags); -/** - * enum freeze_holder - holder of the freeze - * @FREEZE_HOLDER_KERNEL: kernel wants to freeze or thaw filesystem - * @FREEZE_HOLDER_USERSPACE: userspace wants to freeze or thaw filesystem - * @FREEZE_MAY_NEST: whether nesting freeze and thaw requests is allowed - * @FREEZE_EXCL: a freeze that can only be undone by the owner - * - * Indicate who the owner of the freeze or thaw request is and whether - * the freeze needs to be exclusive or can nest. - * Without @FREEZE_MAY_NEST, multiple freeze and thaw requests from the - * same holder aren't allowed. It is however allowed to hold a single - * @FREEZE_HOLDER_USERSPACE and a single @FREEZE_HOLDER_KERNEL freeze at - * the same time. This is relied upon by some filesystems during online - * repair or similar. - */ -enum freeze_holder { - FREEZE_HOLDER_KERNEL = (1U << 0), - FREEZE_HOLDER_USERSPACE = (1U << 1), - FREEZE_MAY_NEST = (1U << 2), - FREEZE_EXCL = (1U << 3), -}; - -struct super_operations { - struct inode *(*alloc_inode)(struct super_block *sb); - void (*destroy_inode)(struct inode *); - void (*free_inode)(struct inode *); - - void (*dirty_inode) (struct inode *, int flags); - int (*write_inode) (struct inode *, struct writeback_control *wbc); - int (*drop_inode) (struct inode *); - void (*evict_inode) (struct inode *); - void (*put_super) (struct super_block *); - int (*sync_fs)(struct super_block *sb, int wait); - int (*freeze_super) (struct super_block *, enum freeze_holder who, const void *owner); - int (*freeze_fs) (struct super_block *); - int (*thaw_super) (struct super_block *, enum freeze_holder who, const void *owner); - int (*unfreeze_fs) (struct super_block *); - int (*statfs) (struct dentry *, struct kstatfs *); - int (*remount_fs) (struct super_block *, int *, char *); - void (*umount_begin) (struct super_block *); - - int (*show_options)(struct seq_file *, struct dentry *); - int (*show_devname)(struct seq_file *, struct dentry *); - int (*show_path)(struct seq_file *, struct dentry *); - int (*show_stats)(struct seq_file *, struct dentry *); -#ifdef CONFIG_QUOTA - ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t); - ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t); - struct dquot __rcu **(*get_dquots)(struct inode *); -#endif - long (*nr_cached_objects)(struct super_block *, - struct shrink_control *); - long (*free_cached_objects)(struct super_block *, - struct shrink_control *); - /* - * If a filesystem can support graceful removal of a device and - * continue read-write operations, implement this callback. - * - * Return 0 if the filesystem can continue read-write. - * Non-zero return value or no such callback means the fs will be shutdown - * as usual. - */ - int (*remove_bdev)(struct super_block *sb, struct block_device *bdev); - void (*shutdown)(struct super_block *sb); -}; - /* * Inode flags - they have no relation to superblock flags now */ @@ -2539,7 +2121,6 @@ struct super_operations { */ #define __IS_FLG(inode, flg) ((inode)->i_sb->s_flags & (flg)) -static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags & SB_RDONLY; } #define IS_RDONLY(inode) sb_rdonly((inode)->i_sb) #define IS_SYNC(inode) (__IS_FLG(inode, SB_SYNCHRONOUS) || \ ((inode)->i_flags & S_SYNC)) @@ -2635,8 +2216,8 @@ static inline int icount_read(const struct inode *inode) */ static inline bool inode_is_dirtytime_only(struct inode *inode) { - return (inode->i_state & (I_DIRTY_TIME | I_NEW | - I_FREEING | I_WILL_FREE)) == I_DIRTY_TIME; + return (inode_state_read_once(inode) & + (I_DIRTY_TIME | I_NEW | I_FREEING | I_WILL_FREE)) == I_DIRTY_TIME; } extern void inc_nlink(struct inode *inode); @@ -2774,10 +2355,6 @@ extern int unregister_filesystem(struct file_system_type *); extern int vfs_statfs(const struct path *, struct kstatfs *); extern int user_statfs(const char __user *, struct kstatfs *); extern int fd_statfs(int, struct kstatfs *); -int freeze_super(struct super_block *super, enum freeze_holder who, - const void *freeze_owner); -int thaw_super(struct super_block *super, enum freeze_holder who, - const void *freeze_owner); extern __printf(2, 3) int super_setup_bdi_name(struct super_block *sb, char *fmt, ...); extern int super_setup_bdi(struct super_block *sb); @@ -2820,8 +2397,6 @@ static inline void super_set_sysfs_name_generic(struct super_block *sb, const ch va_end(args); } -extern int current_umask(void); - extern void ihold(struct inode * inode); extern void iput(struct inode *); void iput_not_last(struct inode *); @@ -2965,12 +2540,6 @@ extern struct kmem_cache *names_cachep; #define __getname() kmem_cache_alloc(names_cachep, GFP_KERNEL) #define __putname(name) kmem_cache_free(names_cachep, (void *)(name)) -extern struct super_block *blockdev_superblock; -static inline bool sb_is_blkdev_sb(struct super_block *sb) -{ - return IS_ENABLED(CONFIG_BLOCK) && sb == blockdev_superblock; -} - void emergency_thaw_all(void); extern int sync_filesystem(struct super_block *); extern const struct file_operations def_blk_fops; @@ -3016,7 +2585,7 @@ extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart, extern int __must_check file_check_and_advance_wb_err(struct file *file); extern int __must_check file_write_and_wait_range(struct file *file, loff_t start, loff_t end); -int filemap_fdatawrite_range_kick(struct address_space *mapping, loff_t start, +int filemap_flush_range(struct address_space *mapping, loff_t start, loff_t end); static inline int file_write_and_wait(struct file *file) @@ -3053,8 +2622,8 @@ static inline ssize_t generic_write_sync(struct kiocb *iocb, ssize_t count) } else if (iocb->ki_flags & IOCB_DONTCACHE) { struct address_space *mapping = iocb->ki_filp->f_mapping; - filemap_fdatawrite_range_kick(mapping, iocb->ki_pos - count, - iocb->ki_pos - 1); + filemap_flush_range(mapping, iocb->ki_pos - count, + iocb->ki_pos - 1); } return count; @@ -3073,7 +2642,7 @@ static inline int bmap(struct inode *inode, sector_t *block) #endif int notify_change(struct mnt_idmap *, struct dentry *, - struct iattr *, struct inode **); + struct iattr *, struct delegated_inode *); int inode_permission(struct mnt_idmap *, struct inode *, int); int generic_permission(struct mnt_idmap *, struct inode *, int); static inline int file_permission(struct file *file, int mask) @@ -3103,7 +2672,7 @@ static inline bool inode_wrong_type(const struct inode *inode, umode_t mode) * file_start_write - get write access to a superblock for regular file io * @file: the file we want to write to * - * This is a variant of sb_start_write() which is a noop on non-regualr file. + * This is a variant of sb_start_write() which is a noop on non-regular file. * Should be matched with a call to file_end_write(). */ static inline void file_start_write(struct file *file) @@ -3271,6 +2840,7 @@ extern struct file * open_exec(const char *); /* fs/dcache.c -- generic fs support functions */ extern bool is_subdir(struct dentry *, struct dentry *); extern bool path_is_under(const struct path *, const struct path *); +u64 vfsmount_to_propagation_flags(struct vfsmount *mnt); extern char *file_path(struct file *, char *, int); @@ -3328,7 +2898,7 @@ extern void d_mark_dontcache(struct inode *inode); extern struct inode *ilookup5_nowait(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), - void *data); + void *data, bool *isnew); extern struct inode *ilookup5(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data); extern struct inode *ilookup(struct super_block *sb, unsigned long ino); @@ -3380,11 +2950,9 @@ static inline bool is_zero_ino(ino_t ino) return (u32)ino == 0; } -/* - * inode->i_lock must be held - */ static inline void __iget(struct inode *inode) { + lockdep_assert_held(&inode->i_lock); atomic_inc(&inode->i_count); } @@ -3423,10 +2991,7 @@ static inline void remove_inode_hash(struct inode *inode) } extern void inode_sb_list_add(struct inode *inode); -extern void inode_add_lru(struct inode *inode); - -int sb_set_blocksize(struct super_block *sb, int size); -int __must_check sb_min_blocksize(struct super_block *sb, int size); +extern void inode_lru_list_add(struct inode *inode); int generic_file_mmap(struct file *, struct vm_area_struct *); int generic_file_mmap_prepare(struct vm_area_desc *desc); @@ -3611,6 +3176,8 @@ extern void iterate_supers_type(struct file_system_type *, void filesystems_freeze(bool freeze_all); void filesystems_thaw(void); +void end_dirop(struct dentry *de); + extern int dcache_dir_open(struct inode *, struct file *); extern int dcache_dir_close(struct inode *, struct file *); extern loff_t dcache_dir_lseek(struct file *, loff_t, int); @@ -3747,38 +3314,6 @@ static inline bool generic_ci_validate_strict_name(struct inode *dir, } #endif -static inline struct unicode_map *sb_encoding(const struct super_block *sb) -{ -#if IS_ENABLED(CONFIG_UNICODE) - return sb->s_encoding; -#else - return NULL; -#endif -} - -static inline bool sb_has_encoding(const struct super_block *sb) -{ - return !!sb_encoding(sb); -} - -/* - * Compare if two super blocks have the same encoding and flags - */ -static inline bool sb_same_encoding(const struct super_block *sb1, - const struct super_block *sb2) -{ -#if IS_ENABLED(CONFIG_UNICODE) - if (sb1->s_encoding == sb2->s_encoding) - return true; - - return (sb1->s_encoding && sb2->s_encoding && - (sb1->s_encoding->version == sb2->s_encoding->version) && - (sb1->s_encoding_flags == sb2->s_encoding_flags)); -#else - return true; -#endif -} - int may_setattr(struct mnt_idmap *idmap, struct inode *inode, unsigned int ia_valid); int setattr_prepare(struct mnt_idmap *, struct dentry *, struct iattr *); diff --git a/include/linux/fs/super.h b/include/linux/fs/super.h new file mode 100644 index 000000000000..f21ffbb6dea5 --- /dev/null +++ b/include/linux/fs/super.h @@ -0,0 +1,238 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_FS_SUPER_H +#define _LINUX_FS_SUPER_H + +#include <linux/fs/super_types.h> +#include <linux/unicode.h> + +/* + * These are internal functions, please use sb_start_{write,pagefault,intwrite} + * instead. + */ +static inline void __sb_end_write(struct super_block *sb, int level) +{ + percpu_up_read(sb->s_writers.rw_sem + level - 1); +} + +static inline void __sb_start_write(struct super_block *sb, int level) +{ + percpu_down_read_freezable(sb->s_writers.rw_sem + level - 1, true); +} + +static inline bool __sb_start_write_trylock(struct super_block *sb, int level) +{ + return percpu_down_read_trylock(sb->s_writers.rw_sem + level - 1); +} + +#define __sb_writers_acquired(sb, lev) \ + percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev) - 1], 1, _THIS_IP_) +#define __sb_writers_release(sb, lev) \ + percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev) - 1], _THIS_IP_) + +/** + * __sb_write_started - check if sb freeze level is held + * @sb: the super we write to + * @level: the freeze level + * + * * > 0 - sb freeze level is held + * * 0 - sb freeze level is not held + * * < 0 - !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN + */ +static inline int __sb_write_started(const struct super_block *sb, int level) +{ + return lockdep_is_held_type(sb->s_writers.rw_sem + level - 1, 1); +} + +/** + * sb_write_started - check if SB_FREEZE_WRITE is held + * @sb: the super we write to + * + * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. + */ +static inline bool sb_write_started(const struct super_block *sb) +{ + return __sb_write_started(sb, SB_FREEZE_WRITE); +} + +/** + * sb_write_not_started - check if SB_FREEZE_WRITE is not held + * @sb: the super we write to + * + * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. + */ +static inline bool sb_write_not_started(const struct super_block *sb) +{ + return __sb_write_started(sb, SB_FREEZE_WRITE) <= 0; +} + +/** + * sb_end_write - drop write access to a superblock + * @sb: the super we wrote to + * + * Decrement number of writers to the filesystem. Wake up possible waiters + * wanting to freeze the filesystem. + */ +static inline void sb_end_write(struct super_block *sb) +{ + __sb_end_write(sb, SB_FREEZE_WRITE); +} + +/** + * sb_end_pagefault - drop write access to a superblock from a page fault + * @sb: the super we wrote to + * + * Decrement number of processes handling write page fault to the filesystem. + * Wake up possible waiters wanting to freeze the filesystem. + */ +static inline void sb_end_pagefault(struct super_block *sb) +{ + __sb_end_write(sb, SB_FREEZE_PAGEFAULT); +} + +/** + * sb_end_intwrite - drop write access to a superblock for internal fs purposes + * @sb: the super we wrote to + * + * Decrement fs-internal number of writers to the filesystem. Wake up possible + * waiters wanting to freeze the filesystem. + */ +static inline void sb_end_intwrite(struct super_block *sb) +{ + __sb_end_write(sb, SB_FREEZE_FS); +} + +/** + * sb_start_write - get write access to a superblock + * @sb: the super we write to + * + * When a process wants to write data or metadata to a file system (i.e. dirty + * a page or an inode), it should embed the operation in a sb_start_write() - + * sb_end_write() pair to get exclusion against file system freezing. This + * function increments number of writers preventing freezing. If the file + * system is already frozen, the function waits until the file system is + * thawed. + * + * Since freeze protection behaves as a lock, users have to preserve + * ordering of freeze protection and other filesystem locks. Generally, + * freeze protection should be the outermost lock. In particular, we have: + * + * sb_start_write + * -> i_rwsem (write path, truncate, directory ops, ...) + * -> s_umount (freeze_super, thaw_super) + */ +static inline void sb_start_write(struct super_block *sb) +{ + __sb_start_write(sb, SB_FREEZE_WRITE); +} + +DEFINE_GUARD(super_write, + struct super_block *, + sb_start_write(_T), + sb_end_write(_T)) + +static inline bool sb_start_write_trylock(struct super_block *sb) +{ + return __sb_start_write_trylock(sb, SB_FREEZE_WRITE); +} + +/** + * sb_start_pagefault - get write access to a superblock from a page fault + * @sb: the super we write to + * + * When a process starts handling write page fault, it should embed the + * operation into sb_start_pagefault() - sb_end_pagefault() pair to get + * exclusion against file system freezing. This is needed since the page fault + * is going to dirty a page. This function increments number of running page + * faults preventing freezing. If the file system is already frozen, the + * function waits until the file system is thawed. + * + * Since page fault freeze protection behaves as a lock, users have to preserve + * ordering of freeze protection and other filesystem locks. It is advised to + * put sb_start_pagefault() close to mmap_lock in lock ordering. Page fault + * handling code implies lock dependency: + * + * mmap_lock + * -> sb_start_pagefault + */ +static inline void sb_start_pagefault(struct super_block *sb) +{ + __sb_start_write(sb, SB_FREEZE_PAGEFAULT); +} + +/** + * sb_start_intwrite - get write access to a superblock for internal fs purposes + * @sb: the super we write to + * + * This is the third level of protection against filesystem freezing. It is + * free for use by a filesystem. The only requirement is that it must rank + * below sb_start_pagefault. + * + * For example filesystem can call sb_start_intwrite() when starting a + * transaction which somewhat eases handling of freezing for internal sources + * of filesystem changes (internal fs threads, discarding preallocation on file + * close, etc.). + */ +static inline void sb_start_intwrite(struct super_block *sb) +{ + __sb_start_write(sb, SB_FREEZE_FS); +} + +static inline bool sb_start_intwrite_trylock(struct super_block *sb) +{ + return __sb_start_write_trylock(sb, SB_FREEZE_FS); +} + +static inline bool sb_rdonly(const struct super_block *sb) +{ + return sb->s_flags & SB_RDONLY; +} + +static inline bool sb_is_blkdev_sb(struct super_block *sb) +{ + return IS_ENABLED(CONFIG_BLOCK) && sb == blockdev_superblock; +} + +#if IS_ENABLED(CONFIG_UNICODE) +static inline struct unicode_map *sb_encoding(const struct super_block *sb) +{ + return sb->s_encoding; +} + +/* Compare if two super blocks have the same encoding and flags */ +static inline bool sb_same_encoding(const struct super_block *sb1, + const struct super_block *sb2) +{ + if (sb1->s_encoding == sb2->s_encoding) + return true; + + return (sb1->s_encoding && sb2->s_encoding && + (sb1->s_encoding->version == sb2->s_encoding->version) && + (sb1->s_encoding_flags == sb2->s_encoding_flags)); +} +#else +static inline struct unicode_map *sb_encoding(const struct super_block *sb) +{ + return NULL; +} + +static inline bool sb_same_encoding(const struct super_block *sb1, + const struct super_block *sb2) +{ + return true; +} +#endif + +static inline bool sb_has_encoding(const struct super_block *sb) +{ + return !!sb_encoding(sb); +} + +int sb_set_blocksize(struct super_block *sb, int size); +int __must_check sb_min_blocksize(struct super_block *sb, int size); + +int freeze_super(struct super_block *super, enum freeze_holder who, + const void *freeze_owner); +int thaw_super(struct super_block *super, enum freeze_holder who, + const void *freeze_owner); + +#endif /* _LINUX_FS_SUPER_H */ diff --git a/include/linux/fs/super_types.h b/include/linux/fs/super_types.h new file mode 100644 index 000000000000..6bd3009e09b3 --- /dev/null +++ b/include/linux/fs/super_types.h @@ -0,0 +1,336 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_FS_SUPER_TYPES_H +#define _LINUX_FS_SUPER_TYPES_H + +#include <linux/fs_dirent.h> +#include <linux/errseq.h> +#include <linux/list_lru.h> +#include <linux/list.h> +#include <linux/list_bl.h> +#include <linux/llist.h> +#include <linux/uidgid.h> +#include <linux/uuid.h> +#include <linux/percpu-rwsem.h> +#include <linux/workqueue_types.h> +#include <linux/quota.h> + +struct backing_dev_info; +struct block_device; +struct dentry; +struct dentry_operations; +struct dquot_operations; +struct export_operations; +struct file; +struct file_system_type; +struct fscrypt_operations; +struct fsnotify_sb_info; +struct fsverity_operations; +struct kstatfs; +struct mount; +struct mtd_info; +struct quotactl_ops; +struct shrinker; +struct unicode_map; +struct user_namespace; +struct workqueue_struct; +struct writeback_control; +struct xattr_handler; + +extern struct super_block *blockdev_superblock; + +/* Possible states of 'frozen' field */ +enum { + SB_UNFROZEN = 0, /* FS is unfrozen */ + SB_FREEZE_WRITE = 1, /* Writes, dir ops, ioctls frozen */ + SB_FREEZE_PAGEFAULT = 2, /* Page faults stopped as well */ + SB_FREEZE_FS = 3, /* For internal FS use (e.g. to stop internal threads if needed) */ + SB_FREEZE_COMPLETE = 4, /* ->freeze_fs finished successfully */ +}; + +#define SB_FREEZE_LEVELS (SB_FREEZE_COMPLETE - 1) + +struct sb_writers { + unsigned short frozen; /* Is sb frozen? */ + int freeze_kcount; /* How many kernel freeze requests? */ + int freeze_ucount; /* How many userspace freeze requests? */ + const void *freeze_owner; /* Owner of the freeze */ + struct percpu_rw_semaphore rw_sem[SB_FREEZE_LEVELS]; +}; + +/** + * enum freeze_holder - holder of the freeze + * @FREEZE_HOLDER_KERNEL: kernel wants to freeze or thaw filesystem + * @FREEZE_HOLDER_USERSPACE: userspace wants to freeze or thaw filesystem + * @FREEZE_MAY_NEST: whether nesting freeze and thaw requests is allowed + * @FREEZE_EXCL: a freeze that can only be undone by the owner + * + * Indicate who the owner of the freeze or thaw request is and whether + * the freeze needs to be exclusive or can nest. + * Without @FREEZE_MAY_NEST, multiple freeze and thaw requests from the + * same holder aren't allowed. It is however allowed to hold a single + * @FREEZE_HOLDER_USERSPACE and a single @FREEZE_HOLDER_KERNEL freeze at + * the same time. This is relied upon by some filesystems during online + * repair or similar. + */ +enum freeze_holder { + FREEZE_HOLDER_KERNEL = (1U << 0), + FREEZE_HOLDER_USERSPACE = (1U << 1), + FREEZE_MAY_NEST = (1U << 2), + FREEZE_EXCL = (1U << 3), +}; + +struct super_operations { + struct inode *(*alloc_inode)(struct super_block *sb); + void (*destroy_inode)(struct inode *inode); + void (*free_inode)(struct inode *inode); + void (*dirty_inode)(struct inode *inode, int flags); + int (*write_inode)(struct inode *inode, struct writeback_control *wbc); + int (*drop_inode)(struct inode *inode); + void (*evict_inode)(struct inode *inode); + void (*put_super)(struct super_block *sb); + int (*sync_fs)(struct super_block *sb, int wait); + int (*freeze_super)(struct super_block *sb, enum freeze_holder who, + const void *owner); + int (*freeze_fs)(struct super_block *sb); + int (*thaw_super)(struct super_block *sb, enum freeze_holder who, + const void *owner); + int (*unfreeze_fs)(struct super_block *sb); + int (*statfs)(struct dentry *dentry, struct kstatfs *kstatfs); + int (*remount_fs) (struct super_block *, int *, char *); + void (*umount_begin)(struct super_block *sb); + + int (*show_options)(struct seq_file *seq, struct dentry *dentry); + int (*show_devname)(struct seq_file *seq, struct dentry *dentry); + int (*show_path)(struct seq_file *seq, struct dentry *dentry); + int (*show_stats)(struct seq_file *seq, struct dentry *dentry); +#ifdef CONFIG_QUOTA + ssize_t (*quota_read)(struct super_block *sb, int type, char *data, + size_t len, loff_t off); + ssize_t (*quota_write)(struct super_block *sb, int type, + const char *data, size_t len, loff_t off); + struct dquot __rcu **(*get_dquots)(struct inode *inode); +#endif + long (*nr_cached_objects)(struct super_block *sb, + struct shrink_control *sc); + long (*free_cached_objects)(struct super_block *sb, + struct shrink_control *sc); + /* + * If a filesystem can support graceful removal of a device and + * continue read-write operations, implement this callback. + * + * Return 0 if the filesystem can continue read-write. + * Non-zero return value or no such callback means the fs will be shutdown + * as usual. + */ + int (*remove_bdev)(struct super_block *sb, struct block_device *bdev); + void (*shutdown)(struct super_block *sb); +}; + +struct super_block { + struct list_head s_list; /* Keep this first */ + dev_t s_dev; /* search index; _not_ kdev_t */ + unsigned char s_blocksize_bits; + unsigned long s_blocksize; + loff_t s_maxbytes; /* Max file size */ + struct file_system_type *s_type; + const struct super_operations *s_op; + const struct dquot_operations *dq_op; + const struct quotactl_ops *s_qcop; + const struct export_operations *s_export_op; + unsigned long s_flags; + unsigned long s_iflags; /* internal SB_I_* flags */ + unsigned long s_magic; + struct dentry *s_root; + struct rw_semaphore s_umount; + int s_count; + atomic_t s_active; +#ifdef CONFIG_SECURITY + void *s_security; +#endif + const struct xattr_handler *const *s_xattr; +#ifdef CONFIG_FS_ENCRYPTION + const struct fscrypt_operations *s_cop; + struct fscrypt_keyring *s_master_keys; /* master crypto keys in use */ +#endif +#ifdef CONFIG_FS_VERITY + const struct fsverity_operations *s_vop; +#endif +#if IS_ENABLED(CONFIG_UNICODE) + struct unicode_map *s_encoding; + __u16 s_encoding_flags; +#endif + struct hlist_bl_head s_roots; /* alternate root dentries for NFS */ + struct mount *s_mounts; /* list of mounts; _not_ for fs use */ + struct block_device *s_bdev; /* can go away once we use an accessor for @s_bdev_file */ + struct file *s_bdev_file; + struct backing_dev_info *s_bdi; + struct mtd_info *s_mtd; + struct hlist_node s_instances; + unsigned int s_quota_types; /* Bitmask of supported quota types */ + struct quota_info s_dquot; /* Diskquota specific options */ + + struct sb_writers s_writers; + + /* + * Keep s_fs_info, s_time_gran, s_fsnotify_mask, and + * s_fsnotify_info together for cache efficiency. They are frequently + * accessed and rarely modified. + */ + void *s_fs_info; /* Filesystem private info */ + + /* Granularity of c/m/atime in ns (cannot be worse than a second) */ + u32 s_time_gran; + /* Time limits for c/m/atime in seconds */ + time64_t s_time_min; + time64_t s_time_max; +#ifdef CONFIG_FSNOTIFY + u32 s_fsnotify_mask; + struct fsnotify_sb_info *s_fsnotify_info; +#endif + + /* + * q: why are s_id and s_sysfs_name not the same? both are human + * readable strings that identify the filesystem + * a: s_id is allowed to change at runtime; it's used in log messages, + * and we want to when a device starts out as single device (s_id is dev + * name) but then a device is hot added and we have to switch to + * identifying it by UUID + * but s_sysfs_name is a handle for programmatic access, and can't + * change at runtime + */ + char s_id[32]; /* Informational name */ + uuid_t s_uuid; /* UUID */ + u8 s_uuid_len; /* Default 16, possibly smaller for weird filesystems */ + + /* if set, fs shows up under sysfs at /sys/fs/$FSTYP/s_sysfs_name */ + char s_sysfs_name[UUID_STRING_LEN + 1]; + + unsigned int s_max_links; + unsigned int s_d_flags; /* default d_flags for dentries */ + + /* + * The next field is for VFS *only*. No filesystems have any business + * even looking at it. You had been warned. + */ + struct mutex s_vfs_rename_mutex; /* Kludge */ + + /* + * Filesystem subtype. If non-empty the filesystem type field + * in /proc/mounts will be "type.subtype" + */ + const char *s_subtype; + + const struct dentry_operations *__s_d_op; /* default d_op for dentries */ + + struct shrinker *s_shrink; /* per-sb shrinker handle */ + + /* Number of inodes with nlink == 0 but still referenced */ + atomic_long_t s_remove_count; + + /* Read-only state of the superblock is being changed */ + int s_readonly_remount; + + /* per-sb errseq_t for reporting writeback errors via syncfs */ + errseq_t s_wb_err; + + /* AIO completions deferred from interrupt context */ + struct workqueue_struct *s_dio_done_wq; + struct hlist_head s_pins; + + /* + * Owning user namespace and default context in which to + * interpret filesystem uids, gids, quotas, device nodes, + * xattrs and security labels. + */ + struct user_namespace *s_user_ns; + + /* + * The list_lru structure is essentially just a pointer to a table + * of per-node lru lists, each of which has its own spinlock. + * There is no need to put them into separate cachelines. + */ + struct list_lru s_dentry_lru; + struct list_lru s_inode_lru; + struct rcu_head rcu; + struct work_struct destroy_work; + + struct mutex s_sync_lock; /* sync serialisation lock */ + + /* + * Indicates how deep in a filesystem stack this SB is + */ + int s_stack_depth; + + /* s_inode_list_lock protects s_inodes */ + spinlock_t s_inode_list_lock ____cacheline_aligned_in_smp; + struct list_head s_inodes; /* all inodes */ + + spinlock_t s_inode_wblist_lock; + struct list_head s_inodes_wb; /* writeback inodes */ + long s_min_writeback_pages; +} __randomize_layout; + +/* + * sb->s_flags. Note that these mirror the equivalent MS_* flags where + * represented in both. + */ +#define SB_RDONLY BIT(0) /* Mount read-only */ +#define SB_NOSUID BIT(1) /* Ignore suid and sgid bits */ +#define SB_NODEV BIT(2) /* Disallow access to device special files */ +#define SB_NOEXEC BIT(3) /* Disallow program execution */ +#define SB_SYNCHRONOUS BIT(4) /* Writes are synced at once */ +#define SB_MANDLOCK BIT(6) /* Allow mandatory locks on an FS */ +#define SB_DIRSYNC BIT(7) /* Directory modifications are synchronous */ +#define SB_NOATIME BIT(10) /* Do not update access times. */ +#define SB_NODIRATIME BIT(11) /* Do not update directory access times */ +#define SB_SILENT BIT(15) +#define SB_POSIXACL BIT(16) /* Supports POSIX ACLs */ +#define SB_INLINECRYPT BIT(17) /* Use blk-crypto for encrypted files */ +#define SB_KERNMOUNT BIT(22) /* this is a kern_mount call */ +#define SB_I_VERSION BIT(23) /* Update inode I_version field */ +#define SB_LAZYTIME BIT(25) /* Update the on-disk [acm]times lazily */ + +/* These sb flags are internal to the kernel */ +#define SB_DEAD BIT(21) +#define SB_DYING BIT(24) +#define SB_FORCE BIT(27) +#define SB_NOSEC BIT(28) +#define SB_BORN BIT(29) +#define SB_ACTIVE BIT(30) +#define SB_NOUSER BIT(31) + +/* These flags relate to encoding and casefolding */ +#define SB_ENC_STRICT_MODE_FL (1 << 0) +#define SB_ENC_NO_COMPAT_FALLBACK_FL (1 << 1) + +#define sb_has_strict_encoding(sb) \ + (sb->s_encoding_flags & SB_ENC_STRICT_MODE_FL) + +#if IS_ENABLED(CONFIG_UNICODE) +#define sb_no_casefold_compat_fallback(sb) \ + (sb->s_encoding_flags & SB_ENC_NO_COMPAT_FALLBACK_FL) +#else +#define sb_no_casefold_compat_fallback(sb) (1) +#endif + +/* sb->s_iflags */ +#define SB_I_CGROUPWB 0x00000001 /* cgroup-aware writeback enabled */ +#define SB_I_NOEXEC 0x00000002 /* Ignore executables on this fs */ +#define SB_I_NODEV 0x00000004 /* Ignore devices on this fs */ +#define SB_I_STABLE_WRITES 0x00000008 /* don't modify blks until WB is done */ + +/* sb->s_iflags to limit user namespace mounts */ +#define SB_I_USERNS_VISIBLE 0x00000010 /* fstype already mounted */ +#define SB_I_IMA_UNVERIFIABLE_SIGNATURE 0x00000020 +#define SB_I_UNTRUSTED_MOUNTER 0x00000040 +#define SB_I_EVM_HMAC_UNSUPPORTED 0x00000080 + +#define SB_I_SKIP_SYNC 0x00000100 /* Skip superblock at global sync */ +#define SB_I_PERSB_BDI 0x00000200 /* has a per-sb bdi */ +#define SB_I_TS_EXPIRY_WARNED 0x00000400 /* warned about timestamp range expiry */ +#define SB_I_RETIRED 0x00000800 /* superblock shouldn't be reused */ +#define SB_I_NOUMASK 0x00001000 /* VFS does not apply umask */ +#define SB_I_NOIDMAP 0x00002000 /* No idmapped mounts on this superblock */ +#define SB_I_ALLOW_HSM 0x00004000 /* Allow HSM events on this superblock */ + +#endif /* _LINUX_FS_SUPER_TYPES_H */ diff --git a/include/linux/fs_types.h b/include/linux/fs_dirent.h index 54816791196f..92f75c5bac19 100644 --- a/include/linux/fs_types.h +++ b/include/linux/fs_dirent.h @@ -1,6 +1,9 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_FS_TYPES_H -#define _LINUX_FS_TYPES_H +#ifndef _LINUX_FS_DIRENT_H +#define _LINUX_FS_DIRENT_H + +#include <linux/stat.h> +#include <linux/types.h> /* * This is a header for the common implementation of dirent @@ -66,10 +69,10 @@ /* * declarations for helper functions, accompanying implementation - * is in fs/fs_types.c + * is in fs/fs_dirent.c */ extern unsigned char fs_ftype_to_dtype(unsigned int filetype); extern unsigned char fs_umode_to_ftype(umode_t mode); extern unsigned char fs_umode_to_dtype(umode_t mode); -#endif +#endif /* _LINUX_FS_DIRENT_H */ diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h index baf200ab5c77..0070764b790a 100644 --- a/include/linux/fs_struct.h +++ b/include/linux/fs_struct.h @@ -2,6 +2,7 @@ #ifndef _LINUX_FS_STRUCT_H #define _LINUX_FS_STRUCT_H +#include <linux/sched.h> #include <linux/path.h> #include <linux/spinlock.h> #include <linux/seqlock.h> @@ -41,4 +42,9 @@ static inline void get_fs_pwd(struct fs_struct *fs, struct path *pwd) extern bool current_chrooted(void); +static inline int current_umask(void) +{ + return current->fs->umask; +} + #endif /* _LINUX_FS_STRUCT_H */ diff --git a/include/linux/iio/buffer-dma.h b/include/linux/iio/buffer-dma.h index 5eb66a399002..4f33e6a39797 100644 --- a/include/linux/iio/buffer-dma.h +++ b/include/linux/iio/buffer-dma.h @@ -174,5 +174,6 @@ int iio_dma_buffer_enqueue_dmabuf(struct iio_buffer *buffer, size_t size, bool cyclic); void iio_dma_buffer_lock_queue(struct iio_buffer *buffer); void iio_dma_buffer_unlock_queue(struct iio_buffer *buffer); +struct device *iio_dma_buffer_get_dma_dev(struct iio_buffer *buffer); #endif diff --git a/include/linux/iio/buffer_impl.h b/include/linux/iio/buffer_impl.h index e72552e026f3..8d770ced66b2 100644 --- a/include/linux/iio/buffer_impl.h +++ b/include/linux/iio/buffer_impl.h @@ -50,6 +50,7 @@ struct sg_table; * @enqueue_dmabuf: called from userspace via ioctl to queue this DMABUF * object to this buffer. Requires a valid DMABUF fd, that * was previouly attached to this buffer. + * @get_dma_dev: called to get the DMA channel associated with this buffer. * @lock_queue: called when the core needs to lock the buffer queue; * it is used when enqueueing DMABUF objects. * @unlock_queue: used to unlock a previously locked buffer queue @@ -90,6 +91,7 @@ struct iio_buffer_access_funcs { struct iio_dma_buffer_block *block, struct dma_fence *fence, struct sg_table *sgt, size_t size, bool cyclic); + struct device * (*get_dma_dev)(struct iio_buffer *buffer); void (*lock_queue)(struct iio_buffer *buffer); void (*unlock_queue)(struct iio_buffer *buffer); diff --git a/include/linux/init.h b/include/linux/init.h index 17c1bc712e23..40331923b9f4 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -200,12 +200,13 @@ extern struct module __this_module; /* Format: <modname>__<counter>_<line>_<fn> */ #define __initcall_id(fn) \ + __PASTE(kmod_, \ __PASTE(__KBUILD_MODNAME, \ __PASTE(__, \ __PASTE(__COUNTER__, \ __PASTE(_, \ __PASTE(__LINE__, \ - __PASTE(_, fn)))))) + __PASTE(_, fn))))))) /* Format: __<prefix>__<iid><id> */ #define __initcall_name(prefix, __iid, id) \ diff --git a/include/linux/init_task.h b/include/linux/init_task.h index bccb3f1f6262..a6cb241ea00c 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -25,7 +25,6 @@ extern struct files_struct init_files; extern struct fs_struct init_fs; extern struct nsproxy init_nsproxy; -extern struct cred init_cred; #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE #define INIT_PREV_CPUTIME(x) .prev_cputime = { \ diff --git a/include/linux/interval_tree.h b/include/linux/interval_tree.h index 2b8026a39906..9d5791e9f737 100644 --- a/include/linux/interval_tree.h +++ b/include/linux/interval_tree.h @@ -20,6 +20,10 @@ interval_tree_remove(struct interval_tree_node *node, struct rb_root_cached *root); extern struct interval_tree_node * +interval_tree_subtree_search(struct interval_tree_node *node, + unsigned long start, unsigned long last); + +extern struct interval_tree_node * interval_tree_iter_first(struct rb_root_cached *root, unsigned long start, unsigned long last); diff --git a/include/linux/interval_tree_generic.h b/include/linux/interval_tree_generic.h index 1b400f26f63d..c5a2fed49eb0 100644 --- a/include/linux/interval_tree_generic.h +++ b/include/linux/interval_tree_generic.h @@ -77,7 +77,7 @@ ITSTATIC void ITPREFIX ## _remove(ITSTRUCT *node, \ * Cond2: start <= ITLAST(node) \ */ \ \ -static ITSTRUCT * \ +ITSTATIC ITSTRUCT * \ ITPREFIX ## _subtree_search(ITSTRUCT *node, ITTYPE start, ITTYPE last) \ { \ while (true) { \ diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 73dceabc21c8..520e967cb501 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -9,6 +9,7 @@ #include <linux/types.h> #include <linux/mm_types.h> #include <linux/blkdev.h> +#include <linux/pagevec.h> struct address_space; struct fiemap_extent_info; @@ -16,6 +17,7 @@ struct inode; struct iomap_iter; struct iomap_dio; struct iomap_writepage_ctx; +struct iomap_read_folio_ctx; struct iov_iter; struct kiocb; struct page; @@ -241,11 +243,12 @@ struct iomap_iter { unsigned flags; struct iomap iomap; struct iomap srcmap; + struct folio_batch *fbatch; void *private; }; int iomap_iter(struct iomap_iter *iter, const struct iomap_ops *ops); -int iomap_iter_advance(struct iomap_iter *iter, u64 *count); +int iomap_iter_advance(struct iomap_iter *iter, u64 count); /** * iomap_length_trim - trimmed length of the current iomap iteration @@ -282,9 +285,7 @@ static inline u64 iomap_length(const struct iomap_iter *iter) */ static inline int iomap_iter_advance_full(struct iomap_iter *iter) { - u64 length = iomap_length(iter); - - return iomap_iter_advance(iter, &length); + return iomap_iter_advance(iter, iomap_length(iter)); } /** @@ -339,8 +340,10 @@ static inline bool iomap_want_unshare_iter(const struct iomap_iter *iter) ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from, const struct iomap_ops *ops, const struct iomap_write_ops *write_ops, void *private); -int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops); -void iomap_readahead(struct readahead_control *, const struct iomap_ops *ops); +void iomap_read_folio(const struct iomap_ops *ops, + struct iomap_read_folio_ctx *ctx); +void iomap_readahead(const struct iomap_ops *ops, + struct iomap_read_folio_ctx *ctx); bool iomap_is_partially_uptodate(struct folio *, size_t from, size_t count); struct folio *iomap_get_folio(struct iomap_iter *iter, loff_t pos, size_t len); bool iomap_release_folio(struct folio *folio, gfp_t gfp_flags); @@ -349,6 +352,8 @@ bool iomap_dirty_folio(struct address_space *mapping, struct folio *folio); int iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len, const struct iomap_ops *ops, const struct iomap_write_ops *write_ops); +loff_t iomap_fill_dirty_folios(struct iomap_iter *iter, loff_t offset, + loff_t length); int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, const struct iomap_ops *ops, const struct iomap_write_ops *write_ops, void *private); @@ -430,6 +435,10 @@ struct iomap_writeback_ops { * An existing mapping from a previous call to this method can be reused * by the file system if it is still valid. * + * If this succeeds, iomap_finish_folio_write() must be called once + * writeback completes for the range, regardless of whether the + * writeback succeeded or failed. + * * Returns the number of bytes processed or a negative errno. */ ssize_t (*writeback_range)(struct iomap_writepage_ctx *wpc, @@ -467,14 +476,41 @@ ssize_t iomap_add_to_ioend(struct iomap_writepage_ctx *wpc, struct folio *folio, loff_t pos, loff_t end_pos, unsigned int dirty_len); int iomap_ioend_writeback_submit(struct iomap_writepage_ctx *wpc, int error); -void iomap_start_folio_write(struct inode *inode, struct folio *folio, - size_t len); +void iomap_finish_folio_read(struct folio *folio, size_t off, size_t len, + int error); void iomap_finish_folio_write(struct inode *inode, struct folio *folio, size_t len); int iomap_writeback_folio(struct iomap_writepage_ctx *wpc, struct folio *folio); int iomap_writepages(struct iomap_writepage_ctx *wpc); +struct iomap_read_folio_ctx { + const struct iomap_read_ops *ops; + struct folio *cur_folio; + struct readahead_control *rac; + void *read_ctx; +}; + +struct iomap_read_ops { + /* + * Read in a folio range. + * + * If this succeeds, iomap_finish_folio_read() must be called after the + * range is read in, regardless of whether the read succeeded or failed. + * + * Returns 0 on success or a negative error on failure. + */ + int (*read_folio_range)(const struct iomap_iter *iter, + struct iomap_read_folio_ctx *ctx, size_t len); + + /* + * Submit any pending read requests. + * + * This is optional. + */ + void (*submit_read)(struct iomap_read_folio_ctx *ctx); +}; + /* * Flags for direct I/O ->end_io: */ @@ -518,6 +554,14 @@ struct iomap_dio_ops { */ #define IOMAP_DIO_PARTIAL (1 << 2) +/* + * Ensure each bio is aligned to fs block size. + * + * For filesystems which need to calculate/verify the checksum of each fs + * block. Otherwise they may not be able to handle unaligned bios. + */ +#define IOMAP_DIO_FSBLOCK_ALIGNED (1 << 3) + ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, unsigned int dio_flags, void *private, size_t done_before); @@ -540,4 +584,30 @@ int iomap_swapfile_activate(struct swap_info_struct *sis, extern struct bio_set iomap_ioend_bioset; +#ifdef CONFIG_BLOCK +extern const struct iomap_read_ops iomap_bio_read_ops; + +static inline void iomap_bio_read_folio(struct folio *folio, + const struct iomap_ops *ops) +{ + struct iomap_read_folio_ctx ctx = { + .ops = &iomap_bio_read_ops, + .cur_folio = folio, + }; + + iomap_read_folio(ops, &ctx); +} + +static inline void iomap_bio_readahead(struct readahead_control *rac, + const struct iomap_ops *ops) +{ + struct iomap_read_folio_ctx ctx = { + .ops = &iomap_bio_read_ops, + .rac = rac, + }; + + iomap_readahead(ops, &ctx); +} +#endif /* CONFIG_BLOCK */ + #endif /* LINUX_IOMAP_H */ diff --git a/include/linux/irq-entry-common.h b/include/linux/irq-entry-common.h index d643c7c87822..ba1ed42f8a1c 100644 --- a/include/linux/irq-entry-common.h +++ b/include/linux/irq-entry-common.h @@ -253,11 +253,11 @@ static __always_inline void exit_to_user_mode_prepare(struct pt_regs *regs) static __always_inline void exit_to_user_mode(void) { instrumentation_begin(); + unwind_reset_info(); trace_hardirqs_on_prepare(); lockdep_hardirqs_on_prepare(); instrumentation_end(); - unwind_reset_info(); user_enter_irqoff(); arch_exit_to_user_mode(); lockdep_hardirqs_on(CALLER_ADDR0); diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h index 51a258c24ff5..772919e8096a 100644 --- a/include/linux/livepatch.h +++ b/include/linux/livepatch.h @@ -13,6 +13,7 @@ #include <linux/ftrace.h> #include <linux/completion.h> #include <linux/list.h> +#include <linux/livepatch_external.h> #include <linux/livepatch_sched.h> #if IS_ENABLED(CONFIG_LIVEPATCH) @@ -77,30 +78,6 @@ struct klp_func { bool transition; }; -struct klp_object; - -/** - * struct klp_callbacks - pre/post live-(un)patch callback structure - * @pre_patch: executed before code patching - * @post_patch: executed after code patching - * @pre_unpatch: executed before code unpatching - * @post_unpatch: executed after code unpatching - * @post_unpatch_enabled: flag indicating if post-unpatch callback - * should run - * - * All callbacks are optional. Only the pre-patch callback, if provided, - * will be unconditionally executed. If the parent klp_object fails to - * patch for any reason, including a non-zero error status returned from - * the pre-patch callback, no further callbacks will be executed. - */ -struct klp_callbacks { - int (*pre_patch)(struct klp_object *obj); - void (*post_patch)(struct klp_object *obj); - void (*pre_unpatch)(struct klp_object *obj); - void (*post_unpatch)(struct klp_object *obj); - bool post_unpatch_enabled; -}; - /** * struct klp_object - kernel object structure for live patching * @name: module name (or NULL for vmlinux) diff --git a/include/linux/livepatch_external.h b/include/linux/livepatch_external.h new file mode 100644 index 000000000000..138af19b0f5c --- /dev/null +++ b/include/linux/livepatch_external.h @@ -0,0 +1,76 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * External livepatch interfaces for patch creation tooling + */ + +#ifndef _LINUX_LIVEPATCH_EXTERNAL_H_ +#define _LINUX_LIVEPATCH_EXTERNAL_H_ + +#include <linux/types.h> + +#define KLP_RELOC_SEC_PREFIX ".klp.rela." +#define KLP_SYM_PREFIX ".klp.sym." + +#define __KLP_PRE_PATCH_PREFIX __klp_pre_patch_callback_ +#define __KLP_POST_PATCH_PREFIX __klp_post_patch_callback_ +#define __KLP_PRE_UNPATCH_PREFIX __klp_pre_unpatch_callback_ +#define __KLP_POST_UNPATCH_PREFIX __klp_post_unpatch_callback_ + +#define KLP_PRE_PATCH_PREFIX __stringify(__KLP_PRE_PATCH_PREFIX) +#define KLP_POST_PATCH_PREFIX __stringify(__KLP_POST_PATCH_PREFIX) +#define KLP_PRE_UNPATCH_PREFIX __stringify(__KLP_PRE_UNPATCH_PREFIX) +#define KLP_POST_UNPATCH_PREFIX __stringify(__KLP_POST_UNPATCH_PREFIX) + +struct klp_object; + +typedef int (*klp_pre_patch_t)(struct klp_object *obj); +typedef void (*klp_post_patch_t)(struct klp_object *obj); +typedef void (*klp_pre_unpatch_t)(struct klp_object *obj); +typedef void (*klp_post_unpatch_t)(struct klp_object *obj); + +/** + * struct klp_callbacks - pre/post live-(un)patch callback structure + * @pre_patch: executed before code patching + * @post_patch: executed after code patching + * @pre_unpatch: executed before code unpatching + * @post_unpatch: executed after code unpatching + * @post_unpatch_enabled: flag indicating if post-unpatch callback + * should run + * + * All callbacks are optional. Only the pre-patch callback, if provided, + * will be unconditionally executed. If the parent klp_object fails to + * patch for any reason, including a non-zero error status returned from + * the pre-patch callback, no further callbacks will be executed. + */ +struct klp_callbacks { + klp_pre_patch_t pre_patch; + klp_post_patch_t post_patch; + klp_pre_unpatch_t pre_unpatch; + klp_post_unpatch_t post_unpatch; + bool post_unpatch_enabled; +}; + +/* + * 'struct klp_{func,object}_ext' are compact "external" representations of + * 'struct klp_{func,object}'. They are used by objtool for livepatch + * generation. The structs are then read by the livepatch module and converted + * to the real structs before calling klp_enable_patch(). + * + * TODO make these the official API for klp_enable_patch(). That should + * simplify livepatch's interface as well as its data structure lifetime + * management. + */ +struct klp_func_ext { + const char *old_name; + void *new_func; + unsigned long sympos; +}; + +struct klp_object_ext { + const char *name; + struct klp_func_ext *funcs; + struct klp_callbacks callbacks; + unsigned int nr_funcs; +}; + +#endif /* _LINUX_LIVEPATCH_EXTERNAL_H_ */ diff --git a/include/linux/livepatch_helpers.h b/include/linux/livepatch_helpers.h new file mode 100644 index 000000000000..99d68d0773fa --- /dev/null +++ b/include/linux/livepatch_helpers.h @@ -0,0 +1,77 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_LIVEPATCH_HELPERS_H +#define _LINUX_LIVEPATCH_HELPERS_H + +/* + * Interfaces for use by livepatch patches + */ + +#include <linux/syscalls.h> +#include <linux/livepatch.h> + +#ifdef MODULE +#define KLP_OBJNAME __KBUILD_MODNAME +#else +#define KLP_OBJNAME vmlinux +#endif + +/* Livepatch callback registration */ + +#define KLP_CALLBACK_PTRS ".discard.klp_callback_ptrs" + +#define KLP_PRE_PATCH_CALLBACK(func) \ + klp_pre_patch_t __used __section(KLP_CALLBACK_PTRS) \ + __PASTE(__KLP_PRE_PATCH_PREFIX, KLP_OBJNAME) = func + +#define KLP_POST_PATCH_CALLBACK(func) \ + klp_post_patch_t __used __section(KLP_CALLBACK_PTRS) \ + __PASTE(__KLP_POST_PATCH_PREFIX, KLP_OBJNAME) = func + +#define KLP_PRE_UNPATCH_CALLBACK(func) \ + klp_pre_unpatch_t __used __section(KLP_CALLBACK_PTRS) \ + __PASTE(__KLP_PRE_UNPATCH_PREFIX, KLP_OBJNAME) = func + +#define KLP_POST_UNPATCH_CALLBACK(func) \ + klp_post_unpatch_t __used __section(KLP_CALLBACK_PTRS) \ + __PASTE(__KLP_POST_UNPATCH_PREFIX, KLP_OBJNAME) = func + +/* + * Replace static_call() usage with this macro when create-diff-object + * recommends it due to the original static call key living in a module. + * + * This converts the static call to a regular indirect call. + */ +#define KLP_STATIC_CALL(name) \ + ((typeof(STATIC_CALL_TRAMP(name))*)(STATIC_CALL_KEY(name).func)) + +/* Syscall patching */ + +#define KLP_SYSCALL_DEFINE1(name, ...) KLP_SYSCALL_DEFINEx(1, _##name, __VA_ARGS__) +#define KLP_SYSCALL_DEFINE2(name, ...) KLP_SYSCALL_DEFINEx(2, _##name, __VA_ARGS__) +#define KLP_SYSCALL_DEFINE3(name, ...) KLP_SYSCALL_DEFINEx(3, _##name, __VA_ARGS__) +#define KLP_SYSCALL_DEFINE4(name, ...) KLP_SYSCALL_DEFINEx(4, _##name, __VA_ARGS__) +#define KLP_SYSCALL_DEFINE5(name, ...) KLP_SYSCALL_DEFINEx(5, _##name, __VA_ARGS__) +#define KLP_SYSCALL_DEFINE6(name, ...) KLP_SYSCALL_DEFINEx(6, _##name, __VA_ARGS__) + +#define KLP_SYSCALL_DEFINEx(x, sname, ...) \ + __KLP_SYSCALL_DEFINEx(x, sname, __VA_ARGS__) + +#ifdef CONFIG_X86_64 +// TODO move this to arch/x86/include/asm/syscall_wrapper.h and share code +#define __KLP_SYSCALL_DEFINEx(x, name, ...) \ + static long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ + static inline long __klp_do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\ + __X64_SYS_STUBx(x, name, __VA_ARGS__) \ + __IA32_SYS_STUBx(x, name, __VA_ARGS__) \ + static long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \ + { \ + long ret = __klp_do_sys##name(__MAP(x,__SC_CAST,__VA_ARGS__));\ + __MAP(x,__SC_TEST,__VA_ARGS__); \ + __PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__)); \ + return ret; \ + } \ + static inline long __klp_do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) + +#endif + +#endif /* _LINUX_LIVEPATCH_HELPERS_H */ diff --git a/include/linux/local_lock.h b/include/linux/local_lock.h index 0d91d060e3e9..b0e6ab329b00 100644 --- a/include/linux/local_lock.h +++ b/include/linux/local_lock.h @@ -6,6 +6,7 @@ /** * local_lock_init - Runtime initialize a lock instance + * @lock: The lock variable */ #define local_lock_init(lock) __local_lock_init(lock) @@ -52,7 +53,8 @@ __local_unlock_irqrestore(this_cpu_ptr(lock), flags) /** - * local_lock_init - Runtime initialize a lock instance + * local_trylock_init - Runtime initialize a lock instance + * @lock: The lock variable */ #define local_trylock_init(lock) __local_trylock_init(lock) diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h index a4dc479157b5..8f82b4eb542f 100644 --- a/include/linux/local_lock_internal.h +++ b/include/linux/local_lock_internal.h @@ -99,18 +99,18 @@ do { \ #define __local_lock_acquire(lock) \ do { \ - local_trylock_t *tl; \ - local_lock_t *l; \ + local_trylock_t *__tl; \ + local_lock_t *__l; \ \ - l = (local_lock_t *)(lock); \ - tl = (local_trylock_t *)l; \ + __l = (local_lock_t *)(lock); \ + __tl = (local_trylock_t *)__l; \ _Generic((lock), \ local_trylock_t *: ({ \ - lockdep_assert(tl->acquired == 0); \ - WRITE_ONCE(tl->acquired, 1); \ + lockdep_assert(__tl->acquired == 0); \ + WRITE_ONCE(__tl->acquired, 1); \ }), \ local_lock_t *: (void)0); \ - local_lock_acquire(l); \ + local_lock_acquire(__l); \ } while (0) #define __local_lock(lock) \ @@ -133,36 +133,36 @@ do { \ #define __local_trylock(lock) \ ({ \ - local_trylock_t *tl; \ + local_trylock_t *__tl; \ \ preempt_disable(); \ - tl = (lock); \ - if (READ_ONCE(tl->acquired)) { \ + __tl = (lock); \ + if (READ_ONCE(__tl->acquired)) { \ preempt_enable(); \ - tl = NULL; \ + __tl = NULL; \ } else { \ - WRITE_ONCE(tl->acquired, 1); \ + WRITE_ONCE(__tl->acquired, 1); \ local_trylock_acquire( \ - (local_lock_t *)tl); \ + (local_lock_t *)__tl); \ } \ - !!tl; \ + !!__tl; \ }) #define __local_trylock_irqsave(lock, flags) \ ({ \ - local_trylock_t *tl; \ + local_trylock_t *__tl; \ \ local_irq_save(flags); \ - tl = (lock); \ - if (READ_ONCE(tl->acquired)) { \ + __tl = (lock); \ + if (READ_ONCE(__tl->acquired)) { \ local_irq_restore(flags); \ - tl = NULL; \ + __tl = NULL; \ } else { \ - WRITE_ONCE(tl->acquired, 1); \ + WRITE_ONCE(__tl->acquired, 1); \ local_trylock_acquire( \ - (local_lock_t *)tl); \ + (local_lock_t *)__tl); \ } \ - !!tl; \ + !!__tl; \ }) /* preemption or migration must be disabled before calling __local_lock_is_locked */ @@ -170,16 +170,16 @@ do { \ #define __local_lock_release(lock) \ do { \ - local_trylock_t *tl; \ - local_lock_t *l; \ + local_trylock_t *__tl; \ + local_lock_t *__l; \ \ - l = (local_lock_t *)(lock); \ - tl = (local_trylock_t *)l; \ - local_lock_release(l); \ + __l = (local_lock_t *)(lock); \ + __tl = (local_trylock_t *)__l; \ + local_lock_release(__l); \ _Generic((lock), \ local_trylock_t *: ({ \ - lockdep_assert(tl->acquired == 1); \ - WRITE_ONCE(tl->acquired, 0); \ + lockdep_assert(__tl->acquired == 1); \ + WRITE_ONCE(__tl->acquired, 0); \ }), \ local_lock_t *: (void)0); \ } while (0) @@ -223,12 +223,12 @@ typedef spinlock_t local_trylock_t; #define INIT_LOCAL_LOCK(lockname) __LOCAL_SPIN_LOCK_UNLOCKED((lockname)) #define INIT_LOCAL_TRYLOCK(lockname) __LOCAL_SPIN_LOCK_UNLOCKED((lockname)) -#define __local_lock_init(l) \ +#define __local_lock_init(__l) \ do { \ - local_spin_lock_init((l)); \ + local_spin_lock_init((__l)); \ } while (0) -#define __local_trylock_init(l) __local_lock_init(l) +#define __local_trylock_init(__l) __local_lock_init(__l) #define __local_lock(__lock) \ do { \ diff --git a/include/linux/mailbox/mtk-cmdq-mailbox.h b/include/linux/mailbox/mtk-cmdq-mailbox.h index 4c1a91b07de3..e1555e06e7e5 100644 --- a/include/linux/mailbox/mtk-cmdq-mailbox.h +++ b/include/linux/mailbox/mtk-cmdq-mailbox.h @@ -77,6 +77,16 @@ struct cmdq_pkt { size_t buf_size; /* real buffer size */ }; +/** + * cmdq_get_shift_pa() - get the shift bits of physical address + * @chan: mailbox channel + * + * GCE can only fetch the command buffer address from a 32-bit register. + * Some SOCs support more than 32-bit command buffer address for GCE, which + * requires some shift bits to make the address fit into the 32-bit register. + * + * Return: the shift bits of physical address + */ u8 cmdq_get_shift_pa(struct mbox_chan *chan); #endif /* __MTK_CMDQ_MAILBOX_H__ */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 7c79b3369b82..170594b5cb6b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3376,6 +3376,8 @@ void vma_interval_tree_insert_after(struct vm_area_struct *node, struct rb_root_cached *root); void vma_interval_tree_remove(struct vm_area_struct *node, struct rb_root_cached *root); +struct vm_area_struct *vma_interval_tree_subtree_search(struct vm_area_struct *node, + unsigned long start, unsigned long last); struct vm_area_struct *vma_interval_tree_iter_first(struct rb_root_cached *root, unsigned long start, unsigned long last); struct vm_area_struct *vma_interval_tree_iter_next(struct vm_area_struct *node, @@ -3502,10 +3504,10 @@ struct vm_unmapped_area_info { extern unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info); /* truncate.c */ -extern void truncate_inode_pages(struct address_space *, loff_t); -extern void truncate_inode_pages_range(struct address_space *, - loff_t lstart, loff_t lend); -extern void truncate_inode_pages_final(struct address_space *); +void truncate_inode_pages(struct address_space *mapping, loff_t lstart); +void truncate_inode_pages_range(struct address_space *mapping, loff_t lstart, + uoff_t lend); +void truncate_inode_pages_final(struct address_space *mapping); /* generic vm_area_ops exported for stackable file systems */ extern vm_fault_t filemap_fault(struct vm_fault *vmf); diff --git a/include/linux/module.h b/include/linux/module.h index e135cc79acee..d80c3ea57472 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -251,10 +251,11 @@ struct module_kobject *lookup_or_create_module_kobject(const char *name); */ #define __mod_device_table(type, name) \ __PASTE(__mod_device_table__, \ + __PASTE(kmod_, \ __PASTE(__KBUILD_MODNAME, \ __PASTE(__, \ __PASTE(type, \ - __PASTE(__, name))))) + __PASTE(__, name)))))) /* Creates an alias so file2alias.c can find device table. */ #define MODULE_DEVICE_TABLE(type, name) \ diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 847b81ca6436..bf535f0118bb 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -86,8 +86,23 @@ do { \ #define DEFINE_MUTEX(mutexname) \ struct mutex mutexname = __MUTEX_INITIALIZER(mutexname) -extern void __mutex_init(struct mutex *lock, const char *name, - struct lock_class_key *key); +#ifdef CONFIG_DEBUG_LOCK_ALLOC +void mutex_init_lockep(struct mutex *lock, const char *name, struct lock_class_key *key); + +static inline void __mutex_init(struct mutex *lock, const char *name, + struct lock_class_key *key) +{ + mutex_init_lockep(lock, name, key); +} +#else +extern void mutex_init_generic(struct mutex *lock); + +static inline void __mutex_init(struct mutex *lock, const char *name, + struct lock_class_key *key) +{ + mutex_init_generic(lock); +} +#endif /* !CONFIG_DEBUG_LOCK_ALLOC */ /** * mutex_is_locked - is the mutex locked @@ -111,17 +126,27 @@ extern bool mutex_is_locked(struct mutex *lock); #define DEFINE_MUTEX(mutexname) \ struct mutex mutexname = __MUTEX_INITIALIZER(mutexname) -extern void __mutex_rt_init(struct mutex *lock, const char *name, - struct lock_class_key *key); - #define mutex_is_locked(l) rt_mutex_base_is_locked(&(l)->rtmutex) -#define __mutex_init(mutex, name, key) \ -do { \ - rt_mutex_base_init(&(mutex)->rtmutex); \ - __mutex_rt_init((mutex), name, key); \ -} while (0) +#ifdef CONFIG_DEBUG_LOCK_ALLOC +extern void mutex_rt_init_lockdep(struct mutex *mutex, const char *name, + struct lock_class_key *key); + +static inline void __mutex_init(struct mutex *lock, const char *name, + struct lock_class_key *key) +{ + mutex_rt_init_lockdep(lock, name, key); +} +#else +extern void mutex_rt_init_generic(struct mutex *mutex); + +static inline void __mutex_init(struct mutex *lock, const char *name, + struct lock_class_key *key) +{ + mutex_rt_init_generic(lock); +} +#endif /* !CONFIG_LOCKDEP */ #endif /* CONFIG_PREEMPT_RT */ #ifdef CONFIG_DEBUG_MUTEXES diff --git a/include/linux/namei.h b/include/linux/namei.h index fed86221c69c..58600cf234bc 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -7,6 +7,7 @@ #include <linux/path.h> #include <linux/fcntl.h> #include <linux/errno.h> +#include <linux/fs_struct.h> enum { MAX_NESTED_LINKS = 8 }; @@ -88,6 +89,81 @@ struct dentry *lookup_one_positive_killable(struct mnt_idmap *idmap, struct qstr *name, struct dentry *base); +struct dentry *start_creating(struct mnt_idmap *idmap, struct dentry *parent, + struct qstr *name); +struct dentry *start_removing(struct mnt_idmap *idmap, struct dentry *parent, + struct qstr *name); +struct dentry *start_creating_killable(struct mnt_idmap *idmap, + struct dentry *parent, + struct qstr *name); +struct dentry *start_removing_killable(struct mnt_idmap *idmap, + struct dentry *parent, + struct qstr *name); +struct dentry *start_creating_noperm(struct dentry *parent, struct qstr *name); +struct dentry *start_removing_noperm(struct dentry *parent, struct qstr *name); +struct dentry *start_creating_dentry(struct dentry *parent, + struct dentry *child); +struct dentry *start_removing_dentry(struct dentry *parent, + struct dentry *child); + +/* end_creating - finish action started with start_creating + * @child: dentry returned by start_creating() or vfs_mkdir() + * + * Unlock and release the child. This can be called after + * start_creating() whether that function succeeded or not, + * but it is not needed on failure. + * + * If vfs_mkdir() was called then the value returned from that function + * should be given for @child rather than the original dentry, as vfs_mkdir() + * may have provided a new dentry. + * + * + * If vfs_mkdir() was not called, then @child will be a valid dentry and + * @parent will be ignored. + */ +static inline void end_creating(struct dentry *child) +{ + end_dirop(child); +} + +/* end_creating_keep - finish action started with start_creating() and return result + * @child: dentry returned by start_creating() or vfs_mkdir() + * + * Unlock and return the child. This can be called after + * start_creating() whether that function succeeded or not, + * but it is not needed on failure. + * + * If vfs_mkdir() was called then the value returned from that function + * should be given for @child rather than the original dentry, as vfs_mkdir() + * may have provided a new dentry. + * + * Returns: @child, which may be a dentry or an error. + * + */ +static inline struct dentry *end_creating_keep(struct dentry *child) +{ + if (!IS_ERR(child)) + dget(child); + end_dirop(child); + return child; +} + +/** + * end_removing - finish action started with start_removing + * @child: dentry returned by start_removing() + * @parent: dentry given to start_removing() + * + * Unlock and release the child. + * + * This is identical to end_dirop(). It can be passed the result of + * start_removing() whether that was successful or not, but it not needed + * if start_removing() failed. + */ +static inline void end_removing(struct dentry *child) +{ + end_dirop(child); +} + extern int follow_down_one(struct path *); extern int follow_down(struct path *path, unsigned int flags); extern int follow_up(struct path *); @@ -95,6 +171,13 @@ extern int follow_up(struct path *); extern struct dentry *lock_rename(struct dentry *, struct dentry *); extern struct dentry *lock_rename_child(struct dentry *, struct dentry *); extern void unlock_rename(struct dentry *, struct dentry *); +int start_renaming(struct renamedata *rd, int lookup_flags, + struct qstr *old_last, struct qstr *new_last); +int start_renaming_dentry(struct renamedata *rd, int lookup_flags, + struct dentry *old_dentry, struct qstr *new_last); +int start_renaming_two_dentries(struct renamedata *rd, + struct dentry *old_dentry, struct dentry *new_dentry); +void end_renaming(struct renamedata *rd); /** * mode_strip_umask - handle vfs umask stripping diff --git a/include/linux/ns/ns_common_types.h b/include/linux/ns/ns_common_types.h new file mode 100644 index 000000000000..b332b019b29c --- /dev/null +++ b/include/linux/ns/ns_common_types.h @@ -0,0 +1,196 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_NS_COMMON_TYPES_H +#define _LINUX_NS_COMMON_TYPES_H + +#include <linux/atomic.h> +#include <linux/ns/nstree_types.h> +#include <linux/rbtree.h> +#include <linux/refcount.h> +#include <linux/types.h> + +struct cgroup_namespace; +struct dentry; +struct ipc_namespace; +struct mnt_namespace; +struct net; +struct pid_namespace; +struct proc_ns_operations; +struct time_namespace; +struct user_namespace; +struct uts_namespace; + +extern struct cgroup_namespace init_cgroup_ns; +extern struct ipc_namespace init_ipc_ns; +extern struct mnt_namespace init_mnt_ns; +extern struct net init_net; +extern struct pid_namespace init_pid_ns; +extern struct time_namespace init_time_ns; +extern struct user_namespace init_user_ns; +extern struct uts_namespace init_uts_ns; + +extern const struct proc_ns_operations cgroupns_operations; +extern const struct proc_ns_operations ipcns_operations; +extern const struct proc_ns_operations mntns_operations; +extern const struct proc_ns_operations netns_operations; +extern const struct proc_ns_operations pidns_operations; +extern const struct proc_ns_operations pidns_for_children_operations; +extern const struct proc_ns_operations timens_operations; +extern const struct proc_ns_operations timens_for_children_operations; +extern const struct proc_ns_operations userns_operations; +extern const struct proc_ns_operations utsns_operations; + +/* + * Namespace lifetimes are managed via a two-tier reference counting model: + * + * (1) __ns_ref (refcount_t): Main reference count tracking memory + * lifetime. Controls when the namespace structure itself is freed. + * It also pins the namespace on the namespace trees whereas (2) + * only regulates their visibility to userspace. + * + * (2) __ns_ref_active (atomic_t): Reference count tracking active users. + * Controls visibility of the namespace in the namespace trees. + * Any live task that uses the namespace (via nsproxy or cred) holds + * an active reference. Any open file descriptor or bind-mount of + * the namespace holds an active reference. Once all tasks have + * called exited their namespaces and all file descriptors and + * bind-mounts have been released the active reference count drops + * to zero and the namespace becomes inactive. IOW, the namespace + * cannot be listed or opened via file handles anymore. + * + * Note that it is valid to transition from active to inactive and + * back from inactive to active e.g., when resurrecting an inactive + * namespace tree via the SIOCGSKNS ioctl(). + * + * Relationship and lifecycle states: + * + * - Active (__ns_ref_active > 0): + * Namespace is actively used and visible to userspace. The namespace + * can be reopened via /proc/<pid>/ns/<ns_type>, via namespace file + * handles, or discovered via listns(). + * + * - Inactive (__ns_ref_active == 0, __ns_ref > 0): + * No tasks are actively using the namespace and it isn't pinned by + * any bind-mounts or open file descriptors anymore. But the namespace + * is still kept alive by internal references. For example, the user + * namespace could be pinned by an open file through file->f_cred + * references when one of the now defunct tasks had opened a file and + * handed the file descriptor off to another process via a UNIX + * sockets. Such references keep the namespace structure alive through + * __ns_ref but will not hold an active reference. + * + * - Destroyed (__ns_ref == 0): + * No references remain. The namespace is removed from the tree and freed. + * + * State transitions: + * + * Active -> Inactive: + * When the last task using the namespace exits it drops its active + * references to all namespaces. However, user and pid namespaces + * remain accessible until the task has been reaped. + * + * Inactive -> Active: + * An inactive namespace tree might be resurrected due to e.g., the + * SIOCGSKNS ioctl() on a socket. + * + * Inactive -> Destroyed: + * When __ns_ref drops to zero the namespace is removed from the + * namespaces trees and the memory is freed (after RCU grace period). + * + * Initial namespaces: + * Boot-time namespaces (init_net, init_pid_ns, etc.) start with + * __ns_ref_active = 1 and remain active forever. + * + * @ns_type: type of namespace (e.g., CLONE_NEWNET) + * @stashed: cached dentry to be used by the vfs + * @ops: namespace operations + * @inum: namespace inode number (quickly recycled for non-initial namespaces) + * @__ns_ref: main reference count (do not use directly) + * @ns_tree: namespace tree nodes and active reference count + */ +struct ns_common { + u32 ns_type; + struct dentry *stashed; + const struct proc_ns_operations *ops; + unsigned int inum; + refcount_t __ns_ref; /* do not use directly */ + union { + struct ns_tree; + struct rcu_head ns_rcu; + }; +}; + +#define to_ns_common(__ns) \ + _Generic((__ns), \ + struct cgroup_namespace *: &(__ns)->ns, \ + const struct cgroup_namespace *: &(__ns)->ns, \ + struct ipc_namespace *: &(__ns)->ns, \ + const struct ipc_namespace *: &(__ns)->ns, \ + struct mnt_namespace *: &(__ns)->ns, \ + const struct mnt_namespace *: &(__ns)->ns, \ + struct net *: &(__ns)->ns, \ + const struct net *: &(__ns)->ns, \ + struct pid_namespace *: &(__ns)->ns, \ + const struct pid_namespace *: &(__ns)->ns, \ + struct time_namespace *: &(__ns)->ns, \ + const struct time_namespace *: &(__ns)->ns, \ + struct user_namespace *: &(__ns)->ns, \ + const struct user_namespace *: &(__ns)->ns, \ + struct uts_namespace *: &(__ns)->ns, \ + const struct uts_namespace *: &(__ns)->ns) + +#define ns_init_inum(__ns) \ + _Generic((__ns), \ + struct cgroup_namespace *: CGROUP_NS_INIT_INO, \ + struct ipc_namespace *: IPC_NS_INIT_INO, \ + struct mnt_namespace *: MNT_NS_INIT_INO, \ + struct net *: NET_NS_INIT_INO, \ + struct pid_namespace *: PID_NS_INIT_INO, \ + struct time_namespace *: TIME_NS_INIT_INO, \ + struct user_namespace *: USER_NS_INIT_INO, \ + struct uts_namespace *: UTS_NS_INIT_INO) + +#define ns_init_ns(__ns) \ + _Generic((__ns), \ + struct cgroup_namespace *: &init_cgroup_ns, \ + struct ipc_namespace *: &init_ipc_ns, \ + struct mnt_namespace *: &init_mnt_ns, \ + struct net *: &init_net, \ + struct pid_namespace *: &init_pid_ns, \ + struct time_namespace *: &init_time_ns, \ + struct user_namespace *: &init_user_ns, \ + struct uts_namespace *: &init_uts_ns) + +#define ns_init_id(__ns) \ + _Generic((__ns), \ + struct cgroup_namespace *: CGROUP_NS_INIT_ID, \ + struct ipc_namespace *: IPC_NS_INIT_ID, \ + struct mnt_namespace *: MNT_NS_INIT_ID, \ + struct net *: NET_NS_INIT_ID, \ + struct pid_namespace *: PID_NS_INIT_ID, \ + struct time_namespace *: TIME_NS_INIT_ID, \ + struct user_namespace *: USER_NS_INIT_ID, \ + struct uts_namespace *: UTS_NS_INIT_ID) + +#define to_ns_operations(__ns) \ + _Generic((__ns), \ + struct cgroup_namespace *: (IS_ENABLED(CONFIG_CGROUPS) ? &cgroupns_operations : NULL), \ + struct ipc_namespace *: (IS_ENABLED(CONFIG_IPC_NS) ? &ipcns_operations : NULL), \ + struct mnt_namespace *: &mntns_operations, \ + struct net *: (IS_ENABLED(CONFIG_NET_NS) ? &netns_operations : NULL), \ + struct pid_namespace *: (IS_ENABLED(CONFIG_PID_NS) ? &pidns_operations : NULL), \ + struct time_namespace *: (IS_ENABLED(CONFIG_TIME_NS) ? &timens_operations : NULL), \ + struct user_namespace *: (IS_ENABLED(CONFIG_USER_NS) ? &userns_operations : NULL), \ + struct uts_namespace *: (IS_ENABLED(CONFIG_UTS_NS) ? &utsns_operations : NULL)) + +#define ns_common_type(__ns) \ + _Generic((__ns), \ + struct cgroup_namespace *: CLONE_NEWCGROUP, \ + struct ipc_namespace *: CLONE_NEWIPC, \ + struct mnt_namespace *: CLONE_NEWNS, \ + struct net *: CLONE_NEWNET, \ + struct pid_namespace *: CLONE_NEWPID, \ + struct time_namespace *: CLONE_NEWTIME, \ + struct user_namespace *: CLONE_NEWUSER, \ + struct uts_namespace *: CLONE_NEWUTS) + +#endif /* _LINUX_NS_COMMON_TYPES_H */ diff --git a/include/linux/ns/nstree_types.h b/include/linux/ns/nstree_types.h new file mode 100644 index 000000000000..2fb28ee31efb --- /dev/null +++ b/include/linux/ns/nstree_types.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2025 Christian Brauner <brauner@kernel.org> */ +#ifndef _LINUX_NSTREE_TYPES_H +#define _LINUX_NSTREE_TYPES_H + +#include <linux/rbtree.h> +#include <linux/list.h> + +/** + * struct ns_tree_root - Root of a namespace tree + * @ns_rb: Red-black tree root for efficient lookups + * @ns_list_head: List head for sequential iteration + * + * Each namespace tree maintains both an rbtree (for O(log n) lookups) + * and a list (for efficient sequential iteration). The list is kept in + * the same sorted order as the rbtree. + */ +struct ns_tree_root { + struct rb_root ns_rb; + struct list_head ns_list_head; +}; + +/** + * struct ns_tree_node - Node in a namespace tree + * @ns_node: Red-black tree node + * @ns_list_entry: List entry for sequential iteration + * + * Represents a namespace's position in a tree. Each namespace has + * multiple tree nodes for different trees (unified, per-type, owner). + */ +struct ns_tree_node { + struct rb_node ns_node; + struct list_head ns_list_entry; +}; + +/** + * struct ns_tree - Namespace tree nodes and active reference count + * @ns_id: Unique namespace identifier + * @__ns_ref_active: Active reference count (do not use directly) + * @ns_unified_node: Node in the global namespace tree + * @ns_tree_node: Node in the per-type namespace tree + * @ns_owner_node: Node in the owner namespace's tree of owned namespaces + * @ns_owner_root: Root of the tree of namespaces owned by this namespace + * (only used when this namespace is an owner) + */ +struct ns_tree { + u64 ns_id; + atomic_t __ns_ref_active; + struct ns_tree_node ns_unified_node; + struct ns_tree_node ns_tree_node; + struct ns_tree_node ns_owner_node; + struct ns_tree_root ns_owner_root; +}; + +#endif /* _LINUX_NSTREE_TYPES_H */ diff --git a/include/linux/ns_common.h b/include/linux/ns_common.h index f5b68b8abb54..825f5865bfc5 100644 --- a/include/linux/ns_common.h +++ b/include/linux/ns_common.h @@ -2,122 +2,44 @@ #ifndef _LINUX_NS_COMMON_H #define _LINUX_NS_COMMON_H +#include <linux/ns/ns_common_types.h> #include <linux/refcount.h> -#include <linux/rbtree.h> +#include <linux/vfsdebug.h> #include <uapi/linux/sched.h> +#include <uapi/linux/nsfs.h> -struct proc_ns_operations; - -struct cgroup_namespace; -struct ipc_namespace; -struct mnt_namespace; -struct net; -struct pid_namespace; -struct time_namespace; -struct user_namespace; -struct uts_namespace; - -extern struct cgroup_namespace init_cgroup_ns; -extern struct ipc_namespace init_ipc_ns; -extern struct mnt_namespace init_mnt_ns; -extern struct net init_net; -extern struct pid_namespace init_pid_ns; -extern struct time_namespace init_time_ns; -extern struct user_namespace init_user_ns; -extern struct uts_namespace init_uts_ns; - -extern const struct proc_ns_operations netns_operations; -extern const struct proc_ns_operations utsns_operations; -extern const struct proc_ns_operations ipcns_operations; -extern const struct proc_ns_operations pidns_operations; -extern const struct proc_ns_operations pidns_for_children_operations; -extern const struct proc_ns_operations userns_operations; -extern const struct proc_ns_operations mntns_operations; -extern const struct proc_ns_operations cgroupns_operations; -extern const struct proc_ns_operations timens_operations; -extern const struct proc_ns_operations timens_for_children_operations; - -struct ns_common { - u32 ns_type; - struct dentry *stashed; - const struct proc_ns_operations *ops; - unsigned int inum; - refcount_t __ns_ref; /* do not use directly */ - union { - struct { - u64 ns_id; - struct rb_node ns_tree_node; - struct list_head ns_list_node; - }; - struct rcu_head ns_rcu; - }; -}; - +bool is_current_namespace(struct ns_common *ns); int __ns_common_init(struct ns_common *ns, u32 ns_type, const struct proc_ns_operations *ops, int inum); void __ns_common_free(struct ns_common *ns); +struct ns_common *__must_check ns_owner(struct ns_common *ns); + +static __always_inline bool is_ns_init_inum(const struct ns_common *ns) +{ + VFS_WARN_ON_ONCE(ns->inum == 0); + return unlikely(in_range(ns->inum, MNT_NS_INIT_INO, + IPC_NS_INIT_INO - MNT_NS_INIT_INO + 1)); +} + +static __always_inline bool is_ns_init_id(const struct ns_common *ns) +{ + VFS_WARN_ON_ONCE(ns->ns_id == 0); + return ns->ns_id <= NS_LAST_INIT_ID; +} -#define to_ns_common(__ns) \ - _Generic((__ns), \ - struct cgroup_namespace *: &(__ns)->ns, \ - const struct cgroup_namespace *: &(__ns)->ns, \ - struct ipc_namespace *: &(__ns)->ns, \ - const struct ipc_namespace *: &(__ns)->ns, \ - struct mnt_namespace *: &(__ns)->ns, \ - const struct mnt_namespace *: &(__ns)->ns, \ - struct net *: &(__ns)->ns, \ - const struct net *: &(__ns)->ns, \ - struct pid_namespace *: &(__ns)->ns, \ - const struct pid_namespace *: &(__ns)->ns, \ - struct time_namespace *: &(__ns)->ns, \ - const struct time_namespace *: &(__ns)->ns, \ - struct user_namespace *: &(__ns)->ns, \ - const struct user_namespace *: &(__ns)->ns, \ - struct uts_namespace *: &(__ns)->ns, \ - const struct uts_namespace *: &(__ns)->ns) - -#define ns_init_inum(__ns) \ - _Generic((__ns), \ - struct cgroup_namespace *: CGROUP_NS_INIT_INO, \ - struct ipc_namespace *: IPC_NS_INIT_INO, \ - struct mnt_namespace *: MNT_NS_INIT_INO, \ - struct net *: NET_NS_INIT_INO, \ - struct pid_namespace *: PID_NS_INIT_INO, \ - struct time_namespace *: TIME_NS_INIT_INO, \ - struct user_namespace *: USER_NS_INIT_INO, \ - struct uts_namespace *: UTS_NS_INIT_INO) - -#define ns_init_ns(__ns) \ - _Generic((__ns), \ - struct cgroup_namespace *: &init_cgroup_ns, \ - struct ipc_namespace *: &init_ipc_ns, \ - struct mnt_namespace *: &init_mnt_ns, \ - struct net *: &init_net, \ - struct pid_namespace *: &init_pid_ns, \ - struct time_namespace *: &init_time_ns, \ - struct user_namespace *: &init_user_ns, \ - struct uts_namespace *: &init_uts_ns) - -#define to_ns_operations(__ns) \ - _Generic((__ns), \ - struct cgroup_namespace *: (IS_ENABLED(CONFIG_CGROUPS) ? &cgroupns_operations : NULL), \ - struct ipc_namespace *: (IS_ENABLED(CONFIG_IPC_NS) ? &ipcns_operations : NULL), \ - struct mnt_namespace *: &mntns_operations, \ - struct net *: (IS_ENABLED(CONFIG_NET_NS) ? &netns_operations : NULL), \ - struct pid_namespace *: (IS_ENABLED(CONFIG_PID_NS) ? &pidns_operations : NULL), \ - struct time_namespace *: (IS_ENABLED(CONFIG_TIME_NS) ? &timens_operations : NULL), \ - struct user_namespace *: (IS_ENABLED(CONFIG_USER_NS) ? &userns_operations : NULL), \ - struct uts_namespace *: (IS_ENABLED(CONFIG_UTS_NS) ? &utsns_operations : NULL)) - -#define ns_common_type(__ns) \ - _Generic((__ns), \ - struct cgroup_namespace *: CLONE_NEWCGROUP, \ - struct ipc_namespace *: CLONE_NEWIPC, \ - struct mnt_namespace *: CLONE_NEWNS, \ - struct net *: CLONE_NEWNET, \ - struct pid_namespace *: CLONE_NEWPID, \ - struct time_namespace *: CLONE_NEWTIME, \ - struct user_namespace *: CLONE_NEWUSER, \ - struct uts_namespace *: CLONE_NEWUTS) +#define NS_COMMON_INIT(nsname) \ +{ \ + .ns_type = ns_common_type(&nsname), \ + .ns_id = ns_init_id(&nsname), \ + .inum = ns_init_inum(&nsname), \ + .ops = to_ns_operations(&nsname), \ + .stashed = NULL, \ + .__ns_ref = REFCOUNT_INIT(1), \ + .__ns_ref_active = ATOMIC_INIT(1), \ + .ns_unified_node.ns_list_entry = LIST_HEAD_INIT(nsname.ns.ns_unified_node.ns_list_entry), \ + .ns_tree_node.ns_list_entry = LIST_HEAD_INIT(nsname.ns.ns_tree_node.ns_list_entry), \ + .ns_owner_node.ns_list_entry = LIST_HEAD_INIT(nsname.ns.ns_owner_node.ns_list_entry), \ + .ns_owner_root.ns_list_head = LIST_HEAD_INIT(nsname.ns.ns_owner_root.ns_list_head), \ +} #define ns_common_init(__ns) \ __ns_common_init(to_ns_common(__ns), \ @@ -133,21 +55,96 @@ void __ns_common_free(struct ns_common *ns); #define ns_common_free(__ns) __ns_common_free(to_ns_common((__ns))) +static __always_inline __must_check int __ns_ref_active_read(const struct ns_common *ns) +{ + return atomic_read(&ns->__ns_ref_active); +} + +static __always_inline __must_check int __ns_ref_read(const struct ns_common *ns) +{ + return refcount_read(&ns->__ns_ref); +} + static __always_inline __must_check bool __ns_ref_put(struct ns_common *ns) { - return refcount_dec_and_test(&ns->__ns_ref); + if (is_ns_init_id(ns)) { + VFS_WARN_ON_ONCE(__ns_ref_read(ns) != 1); + VFS_WARN_ON_ONCE(__ns_ref_active_read(ns) != 1); + return false; + } + if (refcount_dec_and_test(&ns->__ns_ref)) { + VFS_WARN_ON_ONCE(__ns_ref_active_read(ns)); + return true; + } + return false; } static __always_inline __must_check bool __ns_ref_get(struct ns_common *ns) { - return refcount_inc_not_zero(&ns->__ns_ref); + if (is_ns_init_id(ns)) { + VFS_WARN_ON_ONCE(__ns_ref_read(ns) != 1); + VFS_WARN_ON_ONCE(__ns_ref_active_read(ns) != 1); + return true; + } + if (refcount_inc_not_zero(&ns->__ns_ref)) + return true; + VFS_WARN_ON_ONCE(__ns_ref_active_read(ns)); + return false; } -#define ns_ref_read(__ns) refcount_read(&to_ns_common((__ns))->__ns_ref) -#define ns_ref_inc(__ns) refcount_inc(&to_ns_common((__ns))->__ns_ref) -#define ns_ref_get(__ns) __ns_ref_get(to_ns_common((__ns))) -#define ns_ref_put(__ns) __ns_ref_put(to_ns_common((__ns))) -#define ns_ref_put_and_lock(__ns, __lock) \ - refcount_dec_and_lock(&to_ns_common((__ns))->__ns_ref, (__lock)) +static __always_inline void __ns_ref_inc(struct ns_common *ns) +{ + if (is_ns_init_id(ns)) { + VFS_WARN_ON_ONCE(__ns_ref_read(ns) != 1); + VFS_WARN_ON_ONCE(__ns_ref_active_read(ns) != 1); + return; + } + refcount_inc(&ns->__ns_ref); +} + +static __always_inline __must_check bool __ns_ref_dec_and_lock(struct ns_common *ns, + spinlock_t *ns_lock) +{ + if (is_ns_init_id(ns)) { + VFS_WARN_ON_ONCE(__ns_ref_read(ns) != 1); + VFS_WARN_ON_ONCE(__ns_ref_active_read(ns) != 1); + return false; + } + return refcount_dec_and_lock(&ns->__ns_ref, ns_lock); +} + +#define ns_ref_read(__ns) __ns_ref_read(to_ns_common((__ns))) +#define ns_ref_inc(__ns) \ + do { if (__ns) __ns_ref_inc(to_ns_common((__ns))); } while (0) +#define ns_ref_get(__ns) \ + ((__ns) ? __ns_ref_get(to_ns_common((__ns))) : false) +#define ns_ref_put(__ns) \ + ((__ns) ? __ns_ref_put(to_ns_common((__ns))) : false) +#define ns_ref_put_and_lock(__ns, __ns_lock) \ + ((__ns) ? __ns_ref_dec_and_lock(to_ns_common((__ns)), __ns_lock) : false) + +#define ns_ref_active_read(__ns) \ + ((__ns) ? __ns_ref_active_read(to_ns_common(__ns)) : 0) + +void __ns_ref_active_put(struct ns_common *ns); + +#define ns_ref_active_put(__ns) \ + do { if (__ns) __ns_ref_active_put(to_ns_common(__ns)); } while (0) + +static __always_inline struct ns_common *__must_check ns_get_unless_inactive(struct ns_common *ns) +{ + if (!__ns_ref_active_read(ns)) { + VFS_WARN_ON_ONCE(is_ns_init_id(ns)); + return NULL; + } + if (!__ns_ref_get(ns)) + return NULL; + return ns; +} + +void __ns_ref_active_get(struct ns_common *ns); + +#define ns_ref_active_get(__ns) \ + do { if (__ns) __ns_ref_active_get(to_ns_common(__ns)); } while (0) #endif diff --git a/include/linux/nsfs.h b/include/linux/nsfs.h index e5a5fa83d36b..731b67fc2fec 100644 --- a/include/linux/nsfs.h +++ b/include/linux/nsfs.h @@ -37,4 +37,7 @@ void nsfs_init(void); #define current_in_namespace(__ns) (__current_namespace_from_type(__ns) == __ns) +void nsproxy_ns_active_get(struct nsproxy *ns); +void nsproxy_ns_active_put(struct nsproxy *ns); + #endif /* _LINUX_NSFS_H */ diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h index bd118a187dec..5a67648721c7 100644 --- a/include/linux/nsproxy.h +++ b/include/linux/nsproxy.h @@ -93,10 +93,13 @@ static inline struct cred *nsset_cred(struct nsset *set) */ int copy_namespaces(u64 flags, struct task_struct *tsk); -void exit_task_namespaces(struct task_struct *tsk); +void switch_cred_namespaces(const struct cred *old, const struct cred *new); +void exit_nsproxy_namespaces(struct task_struct *tsk); +void get_cred_namespaces(struct task_struct *tsk); +void exit_cred_namespaces(struct task_struct *tsk); void switch_task_namespaces(struct task_struct *tsk, struct nsproxy *new); int exec_task_namespaces(void); -void free_nsproxy(struct nsproxy *ns); +void deactivate_nsproxy(struct nsproxy *ns); int unshare_nsproxy_namespaces(unsigned long, struct nsproxy **, struct cred *, struct fs_struct *); int __init nsproxy_cache_init(void); @@ -104,7 +107,7 @@ int __init nsproxy_cache_init(void); static inline void put_nsproxy(struct nsproxy *ns) { if (refcount_dec_and_test(&ns->count)) - free_nsproxy(ns); + deactivate_nsproxy(ns); } static inline void get_nsproxy(struct nsproxy *ns) diff --git a/include/linux/nstree.h b/include/linux/nstree.h index 8b8636690473..175e4625bfa6 100644 --- a/include/linux/nstree.h +++ b/include/linux/nstree.h @@ -1,22 +1,34 @@ /* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2025 Christian Brauner <brauner@kernel.org> */ #ifndef _LINUX_NSTREE_H #define _LINUX_NSTREE_H -#include <linux/ns_common.h> +#include <linux/ns/nstree_types.h> #include <linux/nsproxy.h> #include <linux/rbtree.h> #include <linux/seqlock.h> #include <linux/rculist.h> #include <linux/cookie.h> +#include <uapi/linux/nsfs.h> -extern struct ns_tree cgroup_ns_tree; -extern struct ns_tree ipc_ns_tree; -extern struct ns_tree mnt_ns_tree; -extern struct ns_tree net_ns_tree; -extern struct ns_tree pid_ns_tree; -extern struct ns_tree time_ns_tree; -extern struct ns_tree user_ns_tree; -extern struct ns_tree uts_ns_tree; +struct ns_common; + +extern struct ns_tree_root cgroup_ns_tree; +extern struct ns_tree_root ipc_ns_tree; +extern struct ns_tree_root mnt_ns_tree; +extern struct ns_tree_root net_ns_tree; +extern struct ns_tree_root pid_ns_tree; +extern struct ns_tree_root time_ns_tree; +extern struct ns_tree_root user_ns_tree; +extern struct ns_tree_root uts_ns_tree; + +void ns_tree_node_init(struct ns_tree_node *node); +void ns_tree_root_init(struct ns_tree_root *root); +bool ns_tree_node_empty(const struct ns_tree_node *node); +struct rb_node *ns_tree_node_add(struct ns_tree_node *node, + struct ns_tree_root *root, + int (*cmp)(struct rb_node *, const struct rb_node *)); +void ns_tree_node_del(struct ns_tree_node *node, struct ns_tree_root *root); #define to_ns_tree(__ns) \ _Generic((__ns), \ @@ -29,17 +41,21 @@ extern struct ns_tree uts_ns_tree; struct user_namespace *: &(user_ns_tree), \ struct uts_namespace *: &(uts_ns_tree)) -u64 ns_tree_gen_id(struct ns_common *ns); -void __ns_tree_add_raw(struct ns_common *ns, struct ns_tree *ns_tree); -void __ns_tree_remove(struct ns_common *ns, struct ns_tree *ns_tree); +#define ns_tree_gen_id(__ns) \ + __ns_tree_gen_id(to_ns_common(__ns), \ + (((__ns) == ns_init_ns(__ns)) ? ns_init_id(__ns) : 0)) + +u64 __ns_tree_gen_id(struct ns_common *ns, u64 id); +void __ns_tree_add_raw(struct ns_common *ns, struct ns_tree_root *ns_tree); +void __ns_tree_remove(struct ns_common *ns, struct ns_tree_root *ns_tree); struct ns_common *ns_tree_lookup_rcu(u64 ns_id, int ns_type); struct ns_common *__ns_tree_adjoined_rcu(struct ns_common *ns, - struct ns_tree *ns_tree, + struct ns_tree_root *ns_tree, bool previous); -static inline void __ns_tree_add(struct ns_common *ns, struct ns_tree *ns_tree) +static inline void __ns_tree_add(struct ns_common *ns, struct ns_tree_root *ns_tree, u64 id) { - ns_tree_gen_id(ns); + __ns_tree_gen_id(ns, id); __ns_tree_add_raw(ns, ns_tree); } @@ -59,7 +75,9 @@ static inline void __ns_tree_add(struct ns_common *ns, struct ns_tree *ns_tree) * This function assigns a new id to the namespace and adds it to the * appropriate namespace tree and list. */ -#define ns_tree_add(__ns) __ns_tree_add(to_ns_common(__ns), to_ns_tree(__ns)) +#define ns_tree_add(__ns) \ + __ns_tree_add(to_ns_common(__ns), to_ns_tree(__ns), \ + (((__ns) == ns_init_ns(__ns)) ? ns_init_id(__ns) : 0)) /** * ns_tree_remove - Remove a namespace from a namespace tree @@ -73,6 +91,6 @@ static inline void __ns_tree_add(struct ns_common *ns, struct ns_tree *ns_tree) #define ns_tree_adjoined_rcu(__ns, __previous) \ __ns_tree_adjoined_rcu(to_ns_common(__ns), to_ns_tree(__ns), __previous) -#define ns_tree_active(__ns) (!RB_EMPTY_NODE(&to_ns_common(__ns)->ns_tree_node)) +#define ns_tree_active(__ns) (!RB_EMPTY_NODE(&to_ns_common(__ns)->ns_tree_node.ns_node)) #endif /* _LINUX_NSTREE_H */ diff --git a/include/linux/objtool.h b/include/linux/objtool.h index 46ebaa46e6c5..b18ab53561c9 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -3,16 +3,16 @@ #define _LINUX_OBJTOOL_H #include <linux/objtool_types.h> +#include <linux/annotate.h> #ifdef CONFIG_OBJTOOL -#include <asm/asm.h> - #ifndef __ASSEMBLY__ -#define UNWIND_HINT(type, sp_reg, sp_offset, signal) \ +#define UNWIND_HINT(type, sp_reg, sp_offset, signal) \ "987: \n\t" \ ".pushsection .discard.unwind_hints\n\t" \ + ANNOTATE_DATA_SPECIAL \ /* struct unwind_hint */ \ ".long 987b - .\n\t" \ ".short " __stringify(sp_offset) "\n\t" \ @@ -53,16 +53,6 @@ #define __ASM_BREF(label) label ## b -#define __ASM_ANNOTATE(label, type) \ - ".pushsection .discard.annotate_insn,\"M\",@progbits,8\n\t" \ - ".long " __stringify(label) " - .\n\t" \ - ".long " __stringify(type) "\n\t" \ - ".popsection\n\t" - -#define ASM_ANNOTATE(type) \ - "911:\n\t" \ - __ASM_ANNOTATE(911b, type) - #else /* __ASSEMBLY__ */ /* @@ -89,6 +79,7 @@ .macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0 .Lhere_\@: .pushsection .discard.unwind_hints + ANNOTATE_DATA_SPECIAL /* struct unwind_hint */ .long .Lhere_\@ - . .short \sp_offset @@ -101,7 +92,7 @@ .macro STACK_FRAME_NON_STANDARD func:req .pushsection .discard.func_stack_frame_non_standard, "aw" - .long \func - . + .quad \func .popsection .endm @@ -111,14 +102,6 @@ #endif .endm -.macro ANNOTATE type:req -.Lhere_\@: - .pushsection .discard.annotate_insn,"M",@progbits,8 - .long .Lhere_\@ - . - .long \type - .popsection -.endm - #endif /* __ASSEMBLY__ */ #else /* !CONFIG_OBJTOOL */ @@ -128,84 +111,15 @@ #define UNWIND_HINT(type, sp_reg, sp_offset, signal) "\n\t" #define STACK_FRAME_NON_STANDARD(func) #define STACK_FRAME_NON_STANDARD_FP(func) -#define __ASM_ANNOTATE(label, type) "" -#define ASM_ANNOTATE(type) #else .macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0 .endm .macro STACK_FRAME_NON_STANDARD func:req .endm -.macro ANNOTATE type:req -.endm #endif #endif /* CONFIG_OBJTOOL */ -#ifndef __ASSEMBLY__ -/* - * Annotate away the various 'relocation to !ENDBR` complaints; knowing that - * these relocations will never be used for indirect calls. - */ -#define ANNOTATE_NOENDBR ASM_ANNOTATE(ANNOTYPE_NOENDBR) -#define ANNOTATE_NOENDBR_SYM(sym) asm(__ASM_ANNOTATE(sym, ANNOTYPE_NOENDBR)) - -/* - * This should be used immediately before an indirect jump/call. It tells - * objtool the subsequent indirect jump/call is vouched safe for retpoline - * builds. - */ -#define ANNOTATE_RETPOLINE_SAFE ASM_ANNOTATE(ANNOTYPE_RETPOLINE_SAFE) -/* - * See linux/instrumentation.h - */ -#define ANNOTATE_INSTR_BEGIN(label) __ASM_ANNOTATE(label, ANNOTYPE_INSTR_BEGIN) -#define ANNOTATE_INSTR_END(label) __ASM_ANNOTATE(label, ANNOTYPE_INSTR_END) -/* - * objtool annotation to ignore the alternatives and only consider the original - * instruction(s). - */ -#define ANNOTATE_IGNORE_ALTERNATIVE ASM_ANNOTATE(ANNOTYPE_IGNORE_ALTS) -/* - * This macro indicates that the following intra-function call is valid. - * Any non-annotated intra-function call will cause objtool to issue a warning. - */ -#define ANNOTATE_INTRA_FUNCTION_CALL ASM_ANNOTATE(ANNOTYPE_INTRA_FUNCTION_CALL) -/* - * Use objtool to validate the entry requirement that all code paths do - * VALIDATE_UNRET_END before RET. - * - * NOTE: The macro must be used at the beginning of a global symbol, otherwise - * it will be ignored. - */ -#define ANNOTATE_UNRET_BEGIN ASM_ANNOTATE(ANNOTYPE_UNRET_BEGIN) -/* - * This should be used to refer to an instruction that is considered - * terminating, like a noreturn CALL or UD2 when we know they are not -- eg - * WARN using UD2. - */ -#define ANNOTATE_REACHABLE(label) __ASM_ANNOTATE(label, ANNOTYPE_REACHABLE) -/* - * This should not be used; it annotates away CFI violations. There are a few - * valid use cases like kexec handover to the next kernel image, and there is - * no security concern there. - * - * There are also a few real issues annotated away, like EFI because we can't - * control the EFI code. - */ -#define ANNOTATE_NOCFI_SYM(sym) asm(__ASM_ANNOTATE(sym, ANNOTYPE_NOCFI)) - -#else -#define ANNOTATE_NOENDBR ANNOTATE type=ANNOTYPE_NOENDBR -#define ANNOTATE_RETPOLINE_SAFE ANNOTATE type=ANNOTYPE_RETPOLINE_SAFE -/* ANNOTATE_INSTR_BEGIN ANNOTATE type=ANNOTYPE_INSTR_BEGIN */ -/* ANNOTATE_INSTR_END ANNOTATE type=ANNOTYPE_INSTR_END */ -#define ANNOTATE_IGNORE_ALTERNATIVE ANNOTATE type=ANNOTYPE_IGNORE_ALTS -#define ANNOTATE_INTRA_FUNCTION_CALL ANNOTATE type=ANNOTYPE_INTRA_FUNCTION_CALL -#define ANNOTATE_UNRET_BEGIN ANNOTATE type=ANNOTYPE_UNRET_BEGIN -#define ANNOTATE_REACHABLE ANNOTATE type=ANNOTYPE_REACHABLE -#define ANNOTATE_NOCFI_SYM ANNOTATE type=ANNOTYPE_NOCFI -#endif - #if defined(CONFIG_NOINSTR_VALIDATION) && \ (defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO)) #define VALIDATE_UNRET_BEGIN ANNOTATE_UNRET_BEGIN diff --git a/include/linux/objtool_types.h b/include/linux/objtool_types.h index aceac94632c8..c6def4049b1a 100644 --- a/include/linux/objtool_types.h +++ b/include/linux/objtool_types.h @@ -67,4 +67,6 @@ struct unwind_hint { #define ANNOTYPE_REACHABLE 8 #define ANNOTYPE_NOCFI 9 +#define ANNOTYPE_DATA_SPECIAL 1 + #endif /* _LINUX_OBJTOOL_TYPES_H */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 09b581c1d878..e601a3144f28 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -38,6 +38,7 @@ int filemap_invalidate_pages(struct address_space *mapping, int write_inode_now(struct inode *, int sync); int filemap_fdatawrite(struct address_space *); int filemap_flush(struct address_space *); +int filemap_flush_nr(struct address_space *mapping, long *nr_to_write); int filemap_fdatawait_keep_errors(struct address_space *mapping); int filemap_fdatawait_range(struct address_space *, loff_t lstart, loff_t lend); int filemap_fdatawait_range_keep_errors(struct address_space *mapping, @@ -53,14 +54,10 @@ static inline int filemap_fdatawait(struct address_space *mapping) bool filemap_range_has_page(struct address_space *, loff_t lstart, loff_t lend); int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend); -int __filemap_fdatawrite_range(struct address_space *mapping, - loff_t start, loff_t end, int sync_mode); int filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end); int filemap_check_errors(struct address_space *mapping); void __filemap_set_wb_err(struct address_space *mapping, int err); -int filemap_fdatawrite_wbc(struct address_space *mapping, - struct writeback_control *wbc); int kiocb_write_and_wait(struct kiocb *iocb, size_t count); static inline int filemap_write_and_wait(struct address_space *mapping) @@ -942,6 +939,17 @@ static inline pgoff_t folio_next_index(const struct folio *folio) } /** + * folio_next_pos - Get the file position of the next folio. + * @folio: The current folio. + * + * Return: The position of the folio which follows this folio in the file. + */ +static inline loff_t folio_next_pos(const struct folio *folio) +{ + return (loff_t)folio_next_index(folio) << PAGE_SHIFT; +} + +/** * folio_file_page - The page for a particular index. * @folio: The folio which contains this index. * @index: The index we want to look up. @@ -977,6 +985,8 @@ unsigned filemap_get_folios_contig(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch); unsigned filemap_get_folios_tag(struct address_space *mapping, pgoff_t *start, pgoff_t end, xa_mark_t tag, struct folio_batch *fbatch); +unsigned filemap_get_folios_dirty(struct address_space *mapping, + pgoff_t *start, pgoff_t end, struct folio_batch *fbatch); struct folio *read_cache_folio(struct address_space *, pgoff_t index, filler_t *filler, struct file *file); diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index fd1d91017b99..9870d768db4c 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1720,7 +1720,7 @@ extern void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct p extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs); extern struct perf_callchain_entry * get_perf_callchain(struct pt_regs *regs, bool kernel, bool user, - u32 max_stack, bool crosstask, bool add_mark); + u32 max_stack, bool crosstask, bool add_mark, u64 defer_cookie); extern int get_callchain_buffers(int max_stack); extern void put_callchain_buffers(void); extern struct perf_callchain_entry *get_callchain_entry(int *rctx); diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index 445517a72ad0..0e7ae12c96d2 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -61,8 +61,7 @@ static inline struct pid_namespace *to_pid_ns(struct ns_common *ns) static inline struct pid_namespace *get_pid_ns(struct pid_namespace *ns) { - if (ns != &init_pid_ns) - ns_ref_inc(ns); + ns_ref_inc(ns); return ns; } diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 9d42d473d201..7f6a92ac9704 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -44,11 +44,11 @@ typedef unsigned int pipe_index_t; typedef unsigned short pipe_index_t; #endif -/* - * We have to declare this outside 'struct pipe_inode_info', - * but then we can't use 'union pipe_index' for an anonymous - * union, so we end up having to duplicate this declaration - * below. Annoying. +/** + * struct pipe_index - pipe indeces + * @head: The point of buffer production + * @tail: The point of buffer consumption + * @head_tail: unsigned long union of @head and @tail */ union pipe_index { unsigned long head_tail; @@ -63,9 +63,7 @@ union pipe_index { * @mutex: mutex protecting the whole thing * @rd_wait: reader wait point in case of empty pipe * @wr_wait: writer wait point in case of full pipe - * @head: The point of buffer production - * @tail: The point of buffer consumption - * @head_tail: unsigned long union of @head and @tail + * @pipe_index: the pipe indeces * @note_loss: The next read() should insert a data-lost message * @max_usage: The maximum number of slots that may be used in the ring * @ring_size: total number of buffers (should be a power of 2) @@ -87,14 +85,7 @@ struct pipe_inode_info { struct mutex mutex; wait_queue_head_t rd_wait, wr_wait; - /* This has to match the 'union pipe_index' above */ - union { - unsigned long head_tail; - struct { - pipe_index_t head; - pipe_index_t tail; - }; - }; + union pipe_index; unsigned int max_usage; unsigned int ring_size; diff --git a/include/linux/pseudo_fs.h b/include/linux/pseudo_fs.h index 2503f7625d65..a651e60d9410 100644 --- a/include/linux/pseudo_fs.h +++ b/include/linux/pseudo_fs.h @@ -9,6 +9,7 @@ struct pseudo_fs_context { const struct xattr_handler * const *xattr; const struct dentry_operations *dops; unsigned long magic; + unsigned int s_d_flags; }; struct pseudo_fs_context *init_pseudo(struct fs_context *fc, diff --git a/include/linux/sched.h b/include/linux/sched.h index b469878de25c..e84bc5bce816 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -637,8 +637,8 @@ struct sched_rt_entity { #endif } __randomize_layout; -typedef bool (*dl_server_has_tasks_f)(struct sched_dl_entity *); -typedef struct task_struct *(*dl_server_pick_f)(struct sched_dl_entity *); +struct rq_flags; +typedef struct task_struct *(*dl_server_pick_f)(struct sched_dl_entity *, struct rq_flags *rf); struct sched_dl_entity { struct rb_node rb_node; @@ -685,20 +685,22 @@ struct sched_dl_entity { * * @dl_server tells if this is a server entity. * - * @dl_defer tells if this is a deferred or regular server. For - * now only defer server exists. - * - * @dl_defer_armed tells if the deferrable server is waiting - * for the replenishment timer to activate it. - * * @dl_server_active tells if the dlserver is active(started). * dlserver is started on first cfs enqueue on an idle runqueue * and is stopped when a dequeue results in 0 cfs tasks on the * runqueue. In other words, dlserver is active only when cpu's * runqueue has atleast one cfs task. * + * @dl_defer tells if this is a deferred or regular server. For + * now only defer server exists. + * + * @dl_defer_armed tells if the deferrable server is waiting + * for the replenishment timer to activate it. + * * @dl_defer_running tells if the deferrable server is actually * running, skipping the defer phase. + * + * @dl_defer_idle tracks idle state */ unsigned int dl_throttled : 1; unsigned int dl_yielded : 1; @@ -709,6 +711,7 @@ struct sched_dl_entity { unsigned int dl_defer : 1; unsigned int dl_defer_armed : 1; unsigned int dl_defer_running : 1; + unsigned int dl_defer_idle : 1; /* * Bandwidth enforcement timer. Each -deadline task has its @@ -730,9 +733,6 @@ struct sched_dl_entity { * dl_server_update(). * * @rq the runqueue this server is for - * - * @server_has_tasks() returns true if @server_pick return a - * runnable task. */ struct rq *rq; dl_server_pick_f server_pick_task; @@ -1861,8 +1861,8 @@ extern int task_can_attach(struct task_struct *p); extern int dl_bw_alloc(int cpu, u64 dl_bw); extern void dl_bw_free(int cpu, u64 dl_bw); -/* do_set_cpus_allowed() - consider using set_cpus_allowed_ptr() instead */ -extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask); +/* set_cpus_allowed_force() - consider using set_cpus_allowed_ptr() instead */ +extern void set_cpus_allowed_force(struct task_struct *p, const struct cpumask *new_mask); /** * set_cpus_allowed_ptr - set CPU affinity mask of a task @@ -2058,6 +2058,13 @@ static inline int test_tsk_need_resched(struct task_struct *tsk) return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED)); } +static inline void set_need_resched_current(void) +{ + lockdep_assert_irqs_disabled(); + set_tsk_need_resched(current); + set_preempt_need_resched(); +} + /* * cond_resched() and cond_resched_lock(): latency reduction via * explicit rescheduling in places that are safe. The return diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index b7fafe999073..624fda17a785 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -8,7 +8,7 @@ #define SUID_DUMP_USER 1 /* Dump as user of process */ #define SUID_DUMP_ROOT 2 /* Dump as root */ -static inline unsigned long __mm_flags_get_dumpable(struct mm_struct *mm) +static inline unsigned long __mm_flags_get_dumpable(const struct mm_struct *mm) { /* * By convention, dumpable bits are contained in first 32 bits of the diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index bbcfdf12aa6e..45c0022b91ce 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -92,6 +92,9 @@ struct sched_domain { unsigned int nr_balance_failed; /* initialise to 0 */ /* idle_balance() stats */ + unsigned int newidle_call; + unsigned int newidle_success; + unsigned int newidle_ratio; u64 max_newidle_lb_cost; unsigned long last_decay_max_lb_cost; diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 5ce48eab7a2a..a8a8661839b6 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -1209,4 +1209,118 @@ done_seqretry_irqrestore(seqlock_t *lock, int seq, unsigned long flags) if (seq & 1) read_sequnlock_excl_irqrestore(lock, flags); } + +enum ss_state { + ss_done = 0, + ss_lock, + ss_lock_irqsave, + ss_lockless, +}; + +struct ss_tmp { + enum ss_state state; + unsigned long data; + spinlock_t *lock; + spinlock_t *lock_irqsave; +}; + +static inline void __scoped_seqlock_cleanup(struct ss_tmp *sst) +{ + if (sst->lock) + spin_unlock(sst->lock); + if (sst->lock_irqsave) + spin_unlock_irqrestore(sst->lock_irqsave, sst->data); +} + +extern void __scoped_seqlock_invalid_target(void); + +#if (defined(CONFIG_CC_IS_GCC) && CONFIG_GCC_VERSION < 90000) || defined(CONFIG_KASAN) +/* + * For some reason some GCC-8 architectures (nios2, alpha) have trouble + * determining that the ss_done state is impossible in __scoped_seqlock_next() + * below. + * + * Similarly KASAN is known to confuse compilers enough to break this. But we + * don't care about code quality for KASAN builds anyway. + */ +static inline void __scoped_seqlock_bug(void) { } +#else +/* + * Canary for compiler optimization -- if the compiler doesn't realize this is + * an impossible state, it very likely generates sub-optimal code here. + */ +extern void __scoped_seqlock_bug(void); +#endif + +static inline void +__scoped_seqlock_next(struct ss_tmp *sst, seqlock_t *lock, enum ss_state target) +{ + switch (sst->state) { + case ss_done: + __scoped_seqlock_bug(); + return; + + case ss_lock: + case ss_lock_irqsave: + sst->state = ss_done; + return; + + case ss_lockless: + if (!read_seqretry(lock, sst->data)) { + sst->state = ss_done; + return; + } + break; + } + + switch (target) { + case ss_done: + __scoped_seqlock_invalid_target(); + return; + + case ss_lock: + sst->lock = &lock->lock; + spin_lock(sst->lock); + sst->state = ss_lock; + return; + + case ss_lock_irqsave: + sst->lock_irqsave = &lock->lock; + spin_lock_irqsave(sst->lock_irqsave, sst->data); + sst->state = ss_lock_irqsave; + return; + + case ss_lockless: + sst->data = read_seqbegin(lock); + return; + } +} + +#define __scoped_seqlock_read(_seqlock, _target, _s) \ + for (struct ss_tmp _s __cleanup(__scoped_seqlock_cleanup) = \ + { .state = ss_lockless, .data = read_seqbegin(_seqlock) }; \ + _s.state != ss_done; \ + __scoped_seqlock_next(&_s, _seqlock, _target)) + +/** + * scoped_seqlock_read (lock, ss_state) - execute the read side critical + * section without manual sequence + * counter handling or calls to other + * helpers + * @lock: pointer to seqlock_t protecting the data + * @ss_state: one of {ss_lock, ss_lock_irqsave, ss_lockless} indicating + * the type of critical read section + * + * Example: + * + * scoped_seqlock_read (&lock, ss_lock) { + * // read-side critical section + * } + * + * Starts with a lockess pass first. If it fails, restarts the critical + * section with the lock held. + */ +#define scoped_seqlock_read(_seqlock, _target) \ + __scoped_seqlock_read(_seqlock, _target, __UNIQUE_ID(seqlock)) + #endif /* __LINUX_SEQLOCK_H */ diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 0e47465ef0fd..774efe592a9a 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -111,7 +111,7 @@ struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); int shmem_writeout(struct folio *folio, struct swap_iocb **plug, struct list_head *folio_list); -void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end); +void shmem_truncate_range(struct inode *inode, loff_t start, uoff_t end); int shmem_unuse(unsigned int type); #ifdef CONFIG_TRANSPARENT_HUGEPAGE diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 66c06fcdfe19..cf84d98964b2 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -77,6 +77,7 @@ struct cachestat_range; struct cachestat; struct statmount; struct mnt_id_req; +struct ns_id_req; struct xattr_args; struct file_attr; @@ -437,6 +438,9 @@ asmlinkage long sys_statmount(const struct mnt_id_req __user *req, asmlinkage long sys_listmount(const struct mnt_id_req __user *req, u64 __user *mnt_ids, size_t nr_mnt_ids, unsigned int flags); +asmlinkage long sys_listns(const struct ns_id_req __user *req, + u64 __user *ns_ids, size_t nr_ns_ids, + unsigned int flags); asmlinkage long sys_truncate(const char __user *path, long length); asmlinkage long sys_ftruncate(unsigned int fd, off_t length); #if BITS_PER_LONG == 32 diff --git a/include/linux/types.h b/include/linux/types.h index 6dfdb8e8e4c3..d4437e9c452c 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -50,6 +50,7 @@ typedef __kernel_old_gid_t old_gid_t; #if defined(__GNUC__) typedef __kernel_loff_t loff_t; +typedef __kernel_uoff_t uoff_t; #endif /* diff --git a/include/linux/unwind_deferred.h b/include/linux/unwind_deferred.h index 26122d00708a..bc7ae7d21900 100644 --- a/include/linux/unwind_deferred.h +++ b/include/linux/unwind_deferred.h @@ -6,16 +6,6 @@ #include <linux/unwind_user.h> #include <linux/unwind_deferred_types.h> -struct unwind_work; - -typedef void (*unwind_callback_t)(struct unwind_work *work, struct unwind_stacktrace *trace, u64 cookie); - -struct unwind_work { - struct list_head list; - unwind_callback_t func; - int bit; -}; - #ifdef CONFIG_UNWIND_USER enum { @@ -44,22 +34,22 @@ void unwind_deferred_task_exit(struct task_struct *task); static __always_inline void unwind_reset_info(void) { struct unwind_task_info *info = ¤t->unwind_info; - unsigned long bits; + unsigned long bits = atomic_long_read(&info->unwind_mask); /* Was there any unwinding? */ - if (unlikely(info->unwind_mask)) { - bits = info->unwind_mask; - do { - /* Is a task_work going to run again before going back */ - if (bits & UNWIND_PENDING) - return; - } while (!try_cmpxchg(&info->unwind_mask, &bits, 0UL)); - current->unwind_info.id.id = 0; - - if (unlikely(info->cache)) { - info->cache->nr_entries = 0; - info->cache->unwind_completed = 0; - } + if (likely(!bits)) + return; + + do { + /* Is a task_work going to run again before going back */ + if (bits & UNWIND_PENDING) + return; + } while (!atomic_long_try_cmpxchg(&info->unwind_mask, &bits, 0UL)); + current->unwind_info.id.id = 0; + + if (unlikely(info->cache)) { + info->cache->nr_entries = 0; + info->cache->unwind_completed = 0; } } @@ -68,9 +58,17 @@ static __always_inline void unwind_reset_info(void) static inline void unwind_task_init(struct task_struct *task) {} static inline void unwind_task_free(struct task_struct *task) {} -static inline int unwind_user_faultable(struct unwind_stacktrace *trace) { return -ENOSYS; } -static inline int unwind_deferred_init(struct unwind_work *work, unwind_callback_t func) { return -ENOSYS; } -static inline int unwind_deferred_request(struct unwind_work *work, u64 *timestamp) { return -ENOSYS; } +static inline int unwind_user_faultable(struct unwind_stacktrace *trace) +{ return -ENOSYS; } + +static inline int +unwind_deferred_init(struct unwind_work *work, unwind_callback_t func) +{ return -ENOSYS; } + +static inline int +unwind_deferred_request(struct unwind_work *work, u64 *timestamp) +{ return -ENOSYS; } + static inline void unwind_deferred_cancel(struct unwind_work *work) {} static inline void unwind_deferred_task_exit(struct task_struct *task) {} diff --git a/include/linux/unwind_deferred_types.h b/include/linux/unwind_deferred_types.h index 33b62ac25c86..18fa3932f61c 100644 --- a/include/linux/unwind_deferred_types.h +++ b/include/linux/unwind_deferred_types.h @@ -2,6 +2,9 @@ #ifndef _LINUX_UNWIND_USER_DEFERRED_TYPES_H #define _LINUX_UNWIND_USER_DEFERRED_TYPES_H +#include <linux/types.h> +#include <linux/atomic.h> + struct unwind_cache { unsigned long unwind_completed; unsigned int nr_entries; @@ -30,10 +33,23 @@ union unwind_task_id { }; struct unwind_task_info { - unsigned long unwind_mask; + atomic_long_t unwind_mask; struct unwind_cache *cache; struct callback_head work; union unwind_task_id id; }; +struct unwind_work; +struct unwind_stacktrace; + +typedef void (*unwind_callback_t)(struct unwind_work *work, + struct unwind_stacktrace *trace, + u64 cookie); + +struct unwind_work { + struct list_head list; + unwind_callback_t func; + int bit; +}; + #endif /* _LINUX_UNWIND_USER_DEFERRED_TYPES_H */ diff --git a/include/linux/unwind_user_types.h b/include/linux/unwind_user_types.h index a449f15be890..412729a269bc 100644 --- a/include/linux/unwind_user_types.h +++ b/include/linux/unwind_user_types.h @@ -36,8 +36,10 @@ struct unwind_user_state { unsigned long ip; unsigned long sp; unsigned long fp; + unsigned int ws; enum unwind_user_type current_type; unsigned int available_types; + bool topmost; bool done; }; diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 3aaf19e77558..8285b19a25e0 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -376,6 +376,9 @@ struct usb_gadget_ops { * can handle. The UDC must support this and all slower speeds and lower * number of lanes. * @state: the state we are now (attached, suspended, configured, etc) + * @state_lock: Spinlock protecting the `state` and `teardown` members. + * @teardown: True if the device is undergoing teardown, used to prevent + * new work from being scheduled during cleanup. * @name: Identifies the controller hardware type. Used in diagnostics * and sometimes configuration. * @dev: Driver model state for this abstract device. @@ -451,6 +454,8 @@ struct usb_gadget { enum usb_ssp_rate max_ssp_rate; enum usb_device_state state; + spinlock_t state_lock; + bool teardown; const char *name; struct device dev; unsigned isoch_delay; diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 9a9aebbf96b9..9c3be157397e 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -166,13 +166,13 @@ static inline void set_userns_rlimit_max(struct user_namespace *ns, ns->rlimit_max[type] = max <= LONG_MAX ? max : LONG_MAX; } -#ifdef CONFIG_USER_NS - static inline struct user_namespace *to_user_ns(struct ns_common *ns) { return container_of(ns, struct user_namespace, ns); } +#ifdef CONFIG_USER_NS + static inline struct user_namespace *get_user_ns(struct user_namespace *ns) { if (ns) diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index b673c31569f3..75dabb763c65 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -384,7 +384,8 @@ virtio_net_hdr_tnl_from_skb(const struct sk_buff *skb, struct virtio_net_hdr_v1_hash_tunnel *vhdr, bool tnl_hdr_negotiated, bool little_endian, - int vlan_hlen) + int vlan_hlen, + bool has_data_valid) { struct virtio_net_hdr *hdr = (struct virtio_net_hdr *)vhdr; unsigned int inner_nh, outer_th; @@ -394,8 +395,8 @@ virtio_net_hdr_tnl_from_skb(const struct sk_buff *skb, tnl_gso_type = skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL | SKB_GSO_UDP_TUNNEL_CSUM); if (!tnl_gso_type) - return virtio_net_hdr_from_skb(skb, hdr, little_endian, false, - vlan_hlen); + return virtio_net_hdr_from_skb(skb, hdr, little_endian, + has_data_valid, vlan_hlen); /* Tunnel support not negotiated but skb ask for it. */ if (!tnl_hdr_negotiated) diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 22dd4adc5667..f48e8ccffe81 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -189,11 +189,11 @@ void wakeup_flusher_threads_bdi(struct backing_dev_info *bdi, void inode_wait_for_writeback(struct inode *inode); void inode_io_list_del(struct inode *inode); -/* writeback.h requires fs.h; it, too, is not included from here. */ -static inline void wait_on_inode(struct inode *inode) +static inline xa_mark_t wbc_to_tag(struct writeback_control *wbc) { - wait_var_event(inode_state_wait_address(inode, __I_NEW), - !(READ_ONCE(inode->i_state) & I_NEW)); + if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) + return PAGECACHE_TAG_TOWRITE; + return PAGECACHE_TAG_DIRTY; } #ifdef CONFIG_CGROUP_WRITEBACK @@ -234,7 +234,7 @@ static inline void inode_attach_wb(struct inode *inode, struct folio *folio) static inline void inode_detach_wb(struct inode *inode) { if (inode->i_wb) { - WARN_ON_ONCE(!(inode->i_state & I_CLEAR)); + WARN_ON_ONCE(!(inode_state_read_once(inode) & I_CLEAR)); wb_put(inode->i_wb); inode->i_wb = NULL; } @@ -374,4 +374,9 @@ bool redirty_page_for_writepage(struct writeback_control *, struct page *); void sb_mark_inode_writeback(struct inode *inode); void sb_clear_inode_writeback(struct inode *inode); +/* + * 4MB minimal write chunk size + */ +#define MIN_WRITEBACK_PAGES (4096UL >> (PAGE_SHIFT - 10)) + #endif /* WRITEBACK_H */ diff --git a/include/linux/xattr.h b/include/linux/xattr.h index 86b0d47984a1..64e9afe7d647 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -85,12 +85,12 @@ int __vfs_setxattr_noperm(struct mnt_idmap *, struct dentry *, const char *, const void *, size_t, int); int __vfs_setxattr_locked(struct mnt_idmap *, struct dentry *, const char *, const void *, size_t, int, - struct inode **); + struct delegated_inode *); int vfs_setxattr(struct mnt_idmap *, struct dentry *, const char *, const void *, size_t, int); int __vfs_removexattr(struct mnt_idmap *, struct dentry *, const char *); int __vfs_removexattr_locked(struct mnt_idmap *, struct dentry *, - const char *, struct inode **); + const char *, struct delegated_inode *); int vfs_removexattr(struct mnt_idmap *, struct dentry *, const char *); ssize_t generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size); diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index b8100dbfe5d7..0cb87687837f 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -749,7 +749,6 @@ struct hci_conn { __u8 remote_cap; __u8 remote_auth; - __u8 remote_id; unsigned int sent; @@ -857,11 +856,12 @@ extern struct mutex hci_cb_list_lock; /* ----- HCI interface to upper protocols ----- */ int l2cap_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr); int l2cap_disconn_ind(struct hci_conn *hcon); -void l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags); +int l2cap_recv_acldata(struct hci_dev *hdev, u16 handle, struct sk_buff *skb, + u16 flags); #if IS_ENABLED(CONFIG_BT_BREDR) int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags); -void sco_recv_scodata(struct hci_conn *hcon, struct sk_buff *skb); +int sco_recv_scodata(struct hci_dev *hdev, u16 handle, struct sk_buff *skb); #else static inline int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) @@ -869,23 +869,30 @@ static inline int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, return 0; } -static inline void sco_recv_scodata(struct hci_conn *hcon, struct sk_buff *skb) +static inline int sco_recv_scodata(struct hci_dev *hdev, u16 handle, + struct sk_buff *skb) { + kfree_skb(skb); + return -ENOENT; } #endif #if IS_ENABLED(CONFIG_BT_LE) int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags); -void iso_recv(struct hci_conn *hcon, struct sk_buff *skb, u16 flags); +int iso_recv(struct hci_dev *hdev, u16 handle, struct sk_buff *skb, + u16 flags); #else static inline int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) { return 0; } -static inline void iso_recv(struct hci_conn *hcon, struct sk_buff *skb, - u16 flags) + +static inline int iso_recv(struct hci_dev *hdev, u16 handle, + struct sk_buff *skb, u16 flags) { + kfree_skb(skb); + return -ENOENT; } #endif diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index c64fd896b1f9..99ac747b7906 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -536,6 +536,8 @@ static inline unsigned char * tcf_get_base_ptr(struct sk_buff *skb, int layer) case TCF_LAYER_NETWORK: return skb_network_header(skb); case TCF_LAYER_TRANSPORT: + if (!skb_transport_header_was_set(skb)) + break; return skb_transport_header(skb); } diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index c08aff044e80..311a341e6fe4 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -120,7 +120,7 @@ DECLARE_EVENT_CLASS(writeback_dirty_inode_template, /* may be called for files on pseudo FSes w/ unregistered bdi */ strscpy_pad(__entry->name, bdi_dev_name(bdi), 32); __entry->ino = inode->i_ino; - __entry->state = inode->i_state; + __entry->state = inode_state_read_once(inode); __entry->flags = flags; ), @@ -748,7 +748,7 @@ TRACE_EVENT(writeback_sb_inodes_requeue, strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; - __entry->state = inode->i_state; + __entry->state = inode_state_read_once(inode); __entry->dirtied_when = inode->dirtied_when; __entry->cgroup_ino = __trace_wb_assign_cgroup(inode_to_wb(inode)); ), @@ -787,7 +787,7 @@ DECLARE_EVENT_CLASS(writeback_single_inode_template, strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; - __entry->state = inode->i_state; + __entry->state = inode_state_read_once(inode); __entry->dirtied_when = inode->dirtied_when; __entry->writeback_index = inode->i_mapping->writeback_index; __entry->nr_to_write = nr_to_write; @@ -839,7 +839,7 @@ DECLARE_EVENT_CLASS(writeback_inode_template, TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; - __entry->state = inode->i_state; + __entry->state = inode_state_read_once(inode); __entry->mode = inode->i_mode; __entry->dirtied_when = inode->dirtied_when; ), diff --git a/include/uapi/asm-generic/posix_types.h b/include/uapi/asm-generic/posix_types.h index b5f7594eee7a..0a90ad92dbf3 100644 --- a/include/uapi/asm-generic/posix_types.h +++ b/include/uapi/asm-generic/posix_types.h @@ -86,6 +86,7 @@ typedef struct { */ typedef __kernel_long_t __kernel_off_t; typedef long long __kernel_loff_t; +typedef unsigned long long __kernel_uoff_t; typedef __kernel_long_t __kernel_old_time_t; #ifndef __KERNEL__ typedef __kernel_long_t __kernel_time_t; diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 04e0077fb4c9..942370b3f5d2 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -857,9 +857,11 @@ __SYSCALL(__NR_open_tree_attr, sys_open_tree_attr) __SYSCALL(__NR_file_getattr, sys_file_getattr) #define __NR_file_setattr 469 __SYSCALL(__NR_file_setattr, sys_file_setattr) +#define __NR_listns 470 +__SYSCALL(__NR_listns, sys_listns) #undef __NR_syscalls -#define __NR_syscalls 470 +#define __NR_syscalls 471 /* * 32 bit systems traditionally used different diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h index 3741ea1b73d8..5e277fd955aa 100644 --- a/include/uapi/linux/fcntl.h +++ b/include/uapi/linux/fcntl.h @@ -4,6 +4,11 @@ #include <asm/fcntl.h> #include <linux/openat2.h> +#ifdef __KERNEL__ +#include <linux/types.h> +#else +#include <stdint.h> +#endif #define F_SETLEASE (F_LINUX_SPECIFIC_BASE + 0) #define F_GETLEASE (F_LINUX_SPECIFIC_BASE + 1) @@ -79,6 +84,17 @@ */ #define RWF_WRITE_LIFE_NOT_SET RWH_WRITE_LIFE_NOT_SET +/* Set/Get delegations */ +#define F_GETDELEG (F_LINUX_SPECIFIC_BASE + 15) +#define F_SETDELEG (F_LINUX_SPECIFIC_BASE + 16) + +/* Argument structure for F_GETDELEG and F_SETDELEG */ +struct delegation { + uint32_t d_flags; /* Must be 0 */ + uint16_t d_type; /* F_RDLCK, F_WRLCK, F_UNLCK */ + uint16_t __pad; /* Must be 0 */ +}; + /* * Types of directory notifications that may be requested. */ diff --git a/include/uapi/linux/nsfs.h b/include/uapi/linux/nsfs.h index e098759ec917..a25e38d1c874 100644 --- a/include/uapi/linux/nsfs.h +++ b/include/uapi/linux/nsfs.h @@ -67,4 +67,62 @@ struct nsfs_file_handle { #define NSFS_FILE_HANDLE_SIZE_VER0 16 /* sizeof first published struct */ #define NSFS_FILE_HANDLE_SIZE_LATEST sizeof(struct nsfs_file_handle) /* sizeof latest published struct */ +enum init_ns_id { + IPC_NS_INIT_ID = 1ULL, + UTS_NS_INIT_ID = 2ULL, + USER_NS_INIT_ID = 3ULL, + PID_NS_INIT_ID = 4ULL, + CGROUP_NS_INIT_ID = 5ULL, + TIME_NS_INIT_ID = 6ULL, + NET_NS_INIT_ID = 7ULL, + MNT_NS_INIT_ID = 8ULL, +#ifdef __KERNEL__ + NS_LAST_INIT_ID = MNT_NS_INIT_ID, +#endif +}; + +enum ns_type { + TIME_NS = (1ULL << 7), /* CLONE_NEWTIME */ + MNT_NS = (1ULL << 17), /* CLONE_NEWNS */ + CGROUP_NS = (1ULL << 25), /* CLONE_NEWCGROUP */ + UTS_NS = (1ULL << 26), /* CLONE_NEWUTS */ + IPC_NS = (1ULL << 27), /* CLONE_NEWIPC */ + USER_NS = (1ULL << 28), /* CLONE_NEWUSER */ + PID_NS = (1ULL << 29), /* CLONE_NEWPID */ + NET_NS = (1ULL << 30), /* CLONE_NEWNET */ +}; + +/** + * struct ns_id_req - namespace ID request structure + * @size: size of this structure + * @spare: reserved for future use + * @filter: filter mask + * @ns_id: last namespace id + * @user_ns_id: owning user namespace ID + * + * Structure for passing namespace ID and miscellaneous parameters to + * statns(2) and listns(2). + * + * For statns(2) @param represents the request mask. + * For listns(2) @param represents the last listed mount id (or zero). + */ +struct ns_id_req { + __u32 size; + __u32 spare; + __u64 ns_id; + struct /* listns */ { + __u32 ns_type; + __u32 spare2; + __u64 user_ns_id; + }; +}; + +/* + * Special @user_ns_id value that can be passed to listns() + */ +#define LISTNS_CURRENT_USER 0xffffffffffffffff /* Caller's userns */ + +/* List of all ns_id_req versions. */ +#define NS_ID_REQ_SIZE_VER0 32 /* sizeof first published struct */ + #endif /* __LINUX_NSFS_H */ diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 78a362b80027..d292f96bc06f 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -463,7 +463,9 @@ struct perf_event_attr { inherit_thread : 1, /* children only inherit if cloned with CLONE_THREAD */ remove_on_exec : 1, /* event is removed from task on exec */ sigtrap : 1, /* send synchronous SIGTRAP on event */ - __reserved_1 : 26; + defer_callchain: 1, /* request PERF_RECORD_CALLCHAIN_DEFERRED records */ + defer_output : 1, /* output PERF_RECORD_CALLCHAIN_DEFERRED records */ + __reserved_1 : 24; union { __u32 wakeup_events; /* wake up every n events */ @@ -1239,6 +1241,22 @@ enum perf_event_type { */ PERF_RECORD_AUX_OUTPUT_HW_ID = 21, + /* + * This user callchain capture was deferred until shortly before + * returning to user space. Previous samples would have kernel + * callchains only and they need to be stitched with this to make full + * callchains. + * + * struct { + * struct perf_event_header header; + * u64 cookie; + * u64 nr; + * u64 ips[nr]; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_CALLCHAIN_DEFERRED = 22, + PERF_RECORD_MAX, /* non-ABI */ }; @@ -1269,6 +1287,7 @@ enum perf_callchain_context { PERF_CONTEXT_HV = (__u64)-32, PERF_CONTEXT_KERNEL = (__u64)-128, PERF_CONTEXT_USER = (__u64)-512, + PERF_CONTEXT_USER_DEFERRED = (__u64)-640, PERF_CONTEXT_GUEST = (__u64)-2048, PERF_CONTEXT_GUEST_KERNEL = (__u64)-2176, diff --git a/include/uapi/linux/pidfd.h b/include/uapi/linux/pidfd.h index 957db425d459..ea9a6811fc76 100644 --- a/include/uapi/linux/pidfd.h +++ b/include/uapi/linux/pidfd.h @@ -26,8 +26,12 @@ #define PIDFD_INFO_CGROUPID (1UL << 2) /* Always returned if available, even if not requested */ #define PIDFD_INFO_EXIT (1UL << 3) /* Only returned if requested. */ #define PIDFD_INFO_COREDUMP (1UL << 4) /* Only returned if requested. */ +#define PIDFD_INFO_SUPPORTED_MASK (1UL << 5) /* Want/got supported mask flags */ +#define PIDFD_INFO_COREDUMP_SIGNAL (1UL << 6) /* Always returned if PIDFD_INFO_COREDUMP is requested. */ #define PIDFD_INFO_SIZE_VER0 64 /* sizeof first published struct */ +#define PIDFD_INFO_SIZE_VER1 72 /* sizeof second published struct */ +#define PIDFD_INFO_SIZE_VER2 80 /* sizeof third published struct */ /* * Values for @coredump_mask in pidfd_info. @@ -91,8 +95,11 @@ struct pidfd_info { __u32 fsuid; __u32 fsgid; __s32 exit_code; - __u32 coredump_mask; - __u32 __spare1; + struct /* coredump info */ { + __u32 coredump_mask; + __u32 coredump_signal; + }; + __u64 supported_mask; /* Mask flags that this kernel supports */ }; #define PIDFS_IOCTL_MAGIC 0xFF |