From c3a6cf19e695c8b0a9bf8b5933f863e12d878b7c Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 18 Oct 2019 10:31:43 +0100 Subject: export: avoid code duplication in include/linux/export.h include/linux/export.h has lots of code duplication between EXPORT_SYMBOL and EXPORT_SYMBOL_NS. To improve the maintainability and readability, unify the implementation. When the symbol has no namespace, pass the empty string "" to the 'ns' parameter. The drawback of this change is, it grows the code size. When the symbol has no namespace, sym->namespace was previously NULL, but it is now an empty string "". So, it increases 1 byte for every no namespace EXPORT_SYMBOL. A typical kernel configuration has 10K exported symbols, so it increases 10KB in rough estimation. I did not come up with a good idea to refactor it without increasing the code size. I am not sure how big a deal it is, but at least include/linux/export.h looks nicer. Reviewed-by: Greg Kroah-Hartman Signed-off-by: Masahiro Yamada [maennich: rebase on top of 3 fixes for the namespace feature] Signed-off-by: Matthias Maennich Signed-off-by: Jessica Yu --- kernel/module.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/module.c b/kernel/module.c index ff2d7359a418..26c13173da3d 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1400,7 +1400,7 @@ static int verify_namespace_is_imported(const struct load_info *info, char *imported_namespace; namespace = kernel_symbol_namespace(sym); - if (namespace) { + if (namespace && namespace[0]) { imported_namespace = get_modinfo(info, "import_ns"); while (imported_namespace) { if (strcmp(namespace, imported_namespace) == 0) -- cgit v1.2.3 From 3f6ec871e1c2b360aaf022e90bb99dcc016b3874 Mon Sep 17 00:00:00 2001 From: Amit Kucheria Date: Mon, 21 Oct 2019 17:45:12 +0530 Subject: cpufreq: Initialize the governors in core_initcall Initialize the cpufreq governors earlier to allow for earlier performance control during the boot process. Signed-off-by: Amit Kucheria Acked-by: Viresh Kumar Reviewed-by: Rafael J. Wysocki Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/b98eae9b44eb2f034d7f5d12a161f5f831be1eb7.1571656015.git.amit.kucheria@linaro.org --- drivers/cpufreq/cpufreq_conservative.c | 2 +- drivers/cpufreq/cpufreq_ondemand.c | 2 +- drivers/cpufreq/cpufreq_performance.c | 2 +- drivers/cpufreq/cpufreq_powersave.c | 2 +- drivers/cpufreq/cpufreq_userspace.c | 2 +- kernel/sched/cpufreq_schedutil.c | 2 +- 6 files changed, 6 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c index b66e81c06a57..737ff3b9c2c0 100644 --- a/drivers/cpufreq/cpufreq_conservative.c +++ b/drivers/cpufreq/cpufreq_conservative.c @@ -346,7 +346,7 @@ struct cpufreq_governor *cpufreq_default_governor(void) return CPU_FREQ_GOV_CONSERVATIVE; } -fs_initcall(cpufreq_gov_dbs_init); +core_initcall(cpufreq_gov_dbs_init); #else module_init(cpufreq_gov_dbs_init); #endif diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c index dced033875bf..82a4d37ddecb 100644 --- a/drivers/cpufreq/cpufreq_ondemand.c +++ b/drivers/cpufreq/cpufreq_ondemand.c @@ -483,7 +483,7 @@ struct cpufreq_governor *cpufreq_default_governor(void) return CPU_FREQ_GOV_ONDEMAND; } -fs_initcall(cpufreq_gov_dbs_init); +core_initcall(cpufreq_gov_dbs_init); #else module_init(cpufreq_gov_dbs_init); #endif diff --git a/drivers/cpufreq/cpufreq_performance.c b/drivers/cpufreq/cpufreq_performance.c index aaa04dfcacd9..def9afe0f5b8 100644 --- a/drivers/cpufreq/cpufreq_performance.c +++ b/drivers/cpufreq/cpufreq_performance.c @@ -50,5 +50,5 @@ MODULE_AUTHOR("Dominik Brodowski "); MODULE_DESCRIPTION("CPUfreq policy governor 'performance'"); MODULE_LICENSE("GPL"); -fs_initcall(cpufreq_gov_performance_init); +core_initcall(cpufreq_gov_performance_init); module_exit(cpufreq_gov_performance_exit); diff --git a/drivers/cpufreq/cpufreq_powersave.c b/drivers/cpufreq/cpufreq_powersave.c index c143dc237d87..1ae66019eb83 100644 --- a/drivers/cpufreq/cpufreq_powersave.c +++ b/drivers/cpufreq/cpufreq_powersave.c @@ -43,7 +43,7 @@ struct cpufreq_governor *cpufreq_default_governor(void) return &cpufreq_gov_powersave; } -fs_initcall(cpufreq_gov_powersave_init); +core_initcall(cpufreq_gov_powersave_init); #else module_init(cpufreq_gov_powersave_init); #endif diff --git a/drivers/cpufreq/cpufreq_userspace.c b/drivers/cpufreq/cpufreq_userspace.c index cbd81c58cb8f..b43e7cd502c5 100644 --- a/drivers/cpufreq/cpufreq_userspace.c +++ b/drivers/cpufreq/cpufreq_userspace.c @@ -147,7 +147,7 @@ struct cpufreq_governor *cpufreq_default_governor(void) return &cpufreq_gov_userspace; } -fs_initcall(cpufreq_gov_userspace_init); +core_initcall(cpufreq_gov_userspace_init); #else module_init(cpufreq_gov_userspace_init); #endif diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 86800b4d5453..322ca8860f54 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -915,7 +915,7 @@ static int __init sugov_register(void) { return cpufreq_register_governor(&schedutil_gov); } -fs_initcall(sugov_register); +core_initcall(sugov_register); #ifdef CONFIG_ENERGY_MODEL extern bool sched_energy_update; -- cgit v1.2.3 From 5d603311615f612320bb77bd2a82553ef1ced5b7 Mon Sep 17 00:00:00 2001 From: Konstantin Khorenko Date: Wed, 13 Nov 2019 12:29:50 +0300 Subject: kernel/module.c: wakeup processes in module_wq on module unload Fix the race between load and unload a kernel module. sys_delete_module() try_stop_module() mod->state = _GOING add_unformed_module() old = find_module_all() (old->state == _GOING => wait_event_interruptible()) During pre-condition finished_loading() rets 0 schedule() (never gets waken up later) free_module() mod->state = _UNFORMED list_del_rcu(&mod->list) (dels mod from "modules" list) return The race above leads to modprobe hanging forever on loading a module. Error paths on loading module call wake_up_all(&module_wq) after freeing module, so let's do the same on straight module unload. Fixes: 6e6de3dee51a ("kernel/module.c: Only return -EEXIST for modules that have finished loading") Reviewed-by: Prarit Bhargava Signed-off-by: Konstantin Khorenko Signed-off-by: Jessica Yu --- kernel/module.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/module.c b/kernel/module.c index 26c13173da3d..bdbf95726cb7 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1033,6 +1033,8 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user, strlcpy(last_unloaded_module, mod->name, sizeof(last_unloaded_module)); free_module(mod); + /* someone could wait for the module in add_unformed_module() */ + wake_up_all(&module_wq); return 0; out: mutex_unlock(&module_mutex); -- cgit v1.2.3 From d0f010434124598988ba1c97fbb0e4e820ff5d8c Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 26 Nov 2019 15:01:06 -0800 Subject: bpf: Fix static checker warning kernel/bpf/btf.c:4023 btf_distill_func_proto() error: potentially dereferencing uninitialized 't'. kernel/bpf/btf.c 4012 nargs = btf_type_vlen(func); 4013 if (nargs >= MAX_BPF_FUNC_ARGS) { 4014 bpf_log(log, 4015 "The function %s has %d arguments. Too many.\n", 4016 tname, nargs); 4017 return -EINVAL; 4018 } 4019 ret = __get_type_size(btf, func->type, &t); ^^ t isn't initialized for the first -EINVAL return This is unlikely path, since BTF should have been validated at this point. Fix it by returning 'void' BTF. Reported-by: Dan Carpenter Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20191126230106.237179-1-ast@kernel.org --- kernel/bpf/btf.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 40efde5eedcb..bd5e11881ba3 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3976,8 +3976,10 @@ static int __get_type_size(struct btf *btf, u32 btf_id, t = btf_type_by_id(btf, btf_id); while (t && btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); - if (!t) + if (!t) { + *bad_type = btf->types[0]; return -EINVAL; + } if (btf_type_is_ptr(t)) /* kernel size of pointer. Not BPF's size of pointer*/ return sizeof(void *); -- cgit v1.2.3 From ce27709b8162e5c501bc54292b8bf6bdecc4bbd4 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 27 Nov 2019 20:35:08 -0800 Subject: bpf: Fix build in minimal configurations Some kconfigs can have BPF enabled without a single valid program type. In such configurations the build will fail with: ./kernel/bpf/btf.c:3466:1: error: empty enum is invalid Fix it by adding unused value to the enum. Reported-by: Randy Dunlap Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Randy Dunlap # build-tested Link: https://lore.kernel.org/bpf/20191128043508.2346723-1-ast@kernel.org --- kernel/bpf/btf.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index bd5e11881ba3..7d40da240891 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3463,6 +3463,7 @@ enum { __ctx_convert##_id, #include #undef BPF_PROG_TYPE + __ctx_convert_unused, /* to avoid empty enum in extreme .config */ }; static u8 bpf_ctx_convert_map[] = { #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ -- cgit v1.2.3 From 1a365e822372ba24c9da0822bc583894f6f3d821 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Wed, 20 Nov 2019 16:57:15 +0100 Subject: locking/spinlock/debug: Fix various data races This fixes various data races in spinlock_debug. By testing with KCSAN, it is observable that the console gets spammed with data races reports, suggesting these are extremely frequent. Example data race report: read to 0xffff8ab24f403c48 of 4 bytes by task 221 on cpu 2: debug_spin_lock_before kernel/locking/spinlock_debug.c:85 [inline] do_raw_spin_lock+0x9b/0x210 kernel/locking/spinlock_debug.c:112 __raw_spin_lock include/linux/spinlock_api_smp.h:143 [inline] _raw_spin_lock+0x39/0x40 kernel/locking/spinlock.c:151 spin_lock include/linux/spinlock.h:338 [inline] get_partial_node.isra.0.part.0+0x32/0x2f0 mm/slub.c:1873 get_partial_node mm/slub.c:1870 [inline] write to 0xffff8ab24f403c48 of 4 bytes by task 167 on cpu 3: debug_spin_unlock kernel/locking/spinlock_debug.c:103 [inline] do_raw_spin_unlock+0xc9/0x1a0 kernel/locking/spinlock_debug.c:138 __raw_spin_unlock_irqrestore include/linux/spinlock_api_smp.h:159 [inline] _raw_spin_unlock_irqrestore+0x2d/0x50 kernel/locking/spinlock.c:191 spin_unlock_irqrestore include/linux/spinlock.h:393 [inline] free_debug_processing+0x1b3/0x210 mm/slub.c:1214 __slab_free+0x292/0x400 mm/slub.c:2864 As a side-effect, with KCSAN, this eventually locks up the console, most likely due to deadlock, e.g. .. -> printk lock -> spinlock_debug -> KCSAN detects data race -> kcsan_print_report() -> printk lock -> deadlock. This fix will 1) avoid the data races, and 2) allow using lock debugging together with KCSAN. Reported-by: Qian Cai Signed-off-by: Marco Elver Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Will Deacon Link: https://lkml.kernel.org/r/20191120155715.28089-1-elver@google.com Signed-off-by: Ingo Molnar --- kernel/locking/spinlock_debug.c | 32 ++++++++++++++++---------------- 1 file changed, 16 insertions(+), 16 deletions(-) (limited to 'kernel') diff --git a/kernel/locking/spinlock_debug.c b/kernel/locking/spinlock_debug.c index 399669f7eba8..472dd462a40c 100644 --- a/kernel/locking/spinlock_debug.c +++ b/kernel/locking/spinlock_debug.c @@ -51,19 +51,19 @@ EXPORT_SYMBOL(__rwlock_init); static void spin_dump(raw_spinlock_t *lock, const char *msg) { - struct task_struct *owner = NULL; + struct task_struct *owner = READ_ONCE(lock->owner); - if (lock->owner && lock->owner != SPINLOCK_OWNER_INIT) - owner = lock->owner; + if (owner == SPINLOCK_OWNER_INIT) + owner = NULL; printk(KERN_EMERG "BUG: spinlock %s on CPU#%d, %s/%d\n", msg, raw_smp_processor_id(), current->comm, task_pid_nr(current)); printk(KERN_EMERG " lock: %pS, .magic: %08x, .owner: %s/%d, " ".owner_cpu: %d\n", - lock, lock->magic, + lock, READ_ONCE(lock->magic), owner ? owner->comm : "", owner ? task_pid_nr(owner) : -1, - lock->owner_cpu); + READ_ONCE(lock->owner_cpu)); dump_stack(); } @@ -80,16 +80,16 @@ static void spin_bug(raw_spinlock_t *lock, const char *msg) static inline void debug_spin_lock_before(raw_spinlock_t *lock) { - SPIN_BUG_ON(lock->magic != SPINLOCK_MAGIC, lock, "bad magic"); - SPIN_BUG_ON(lock->owner == current, lock, "recursion"); - SPIN_BUG_ON(lock->owner_cpu == raw_smp_processor_id(), + SPIN_BUG_ON(READ_ONCE(lock->magic) != SPINLOCK_MAGIC, lock, "bad magic"); + SPIN_BUG_ON(READ_ONCE(lock->owner) == current, lock, "recursion"); + SPIN_BUG_ON(READ_ONCE(lock->owner_cpu) == raw_smp_processor_id(), lock, "cpu recursion"); } static inline void debug_spin_lock_after(raw_spinlock_t *lock) { - lock->owner_cpu = raw_smp_processor_id(); - lock->owner = current; + WRITE_ONCE(lock->owner_cpu, raw_smp_processor_id()); + WRITE_ONCE(lock->owner, current); } static inline void debug_spin_unlock(raw_spinlock_t *lock) @@ -99,8 +99,8 @@ static inline void debug_spin_unlock(raw_spinlock_t *lock) SPIN_BUG_ON(lock->owner != current, lock, "wrong owner"); SPIN_BUG_ON(lock->owner_cpu != raw_smp_processor_id(), lock, "wrong CPU"); - lock->owner = SPINLOCK_OWNER_INIT; - lock->owner_cpu = -1; + WRITE_ONCE(lock->owner, SPINLOCK_OWNER_INIT); + WRITE_ONCE(lock->owner_cpu, -1); } /* @@ -187,8 +187,8 @@ static inline void debug_write_lock_before(rwlock_t *lock) static inline void debug_write_lock_after(rwlock_t *lock) { - lock->owner_cpu = raw_smp_processor_id(); - lock->owner = current; + WRITE_ONCE(lock->owner_cpu, raw_smp_processor_id()); + WRITE_ONCE(lock->owner, current); } static inline void debug_write_unlock(rwlock_t *lock) @@ -197,8 +197,8 @@ static inline void debug_write_unlock(rwlock_t *lock) RWLOCK_BUG_ON(lock->owner != current, lock, "wrong owner"); RWLOCK_BUG_ON(lock->owner_cpu != raw_smp_processor_id(), lock, "wrong CPU"); - lock->owner = SPINLOCK_OWNER_INIT; - lock->owner_cpu = -1; + WRITE_ONCE(lock->owner, SPINLOCK_OWNER_INIT); + WRITE_ONCE(lock->owner_cpu, -1); } void do_raw_write_lock(rwlock_t *lock) -- cgit v1.2.3 From 36a8015f89e40f7c9c91cc7e6d028fa288dad27b Mon Sep 17 00:00:00 2001 From: Leonard Crestez Date: Tue, 26 Nov 2019 17:17:13 +0200 Subject: PM / QoS: Restore DEV_PM_QOS_MIN/MAX_FREQUENCY Support for adding per-device frequency limits was removed in commit 2aac8bdf7a0f ("PM: QoS: Drop frequency QoS types from device PM QoS") after cpufreq switched to use a new "freq_constraints" construct. Restore support for per-device freq limits but base this upon freq_constraints. This is primarily meant to be used by the devfreq subsystem. This removes the "static" marking on freq_qos_apply but does not export it for modules. Signed-off-by: Leonard Crestez Reviewed-by: Matthias Kaehlcke Tested-by: Matthias Kaehlcke Signed-off-by: Rafael J. Wysocki --- drivers/base/power/qos.c | 73 ++++++++++++++++++++++++++++++++++++++++++++---- include/linux/pm_qos.h | 12 ++++++++ kernel/power/qos.c | 4 ++- 3 files changed, 82 insertions(+), 7 deletions(-) (limited to 'kernel') diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c index 350dcafd751f..8e93167f1783 100644 --- a/drivers/base/power/qos.c +++ b/drivers/base/power/qos.c @@ -115,10 +115,20 @@ s32 dev_pm_qos_read_value(struct device *dev, enum dev_pm_qos_req_type type) spin_lock_irqsave(&dev->power.lock, flags); - if (type == DEV_PM_QOS_RESUME_LATENCY) { + switch (type) { + case DEV_PM_QOS_RESUME_LATENCY: ret = IS_ERR_OR_NULL(qos) ? PM_QOS_RESUME_LATENCY_NO_CONSTRAINT : pm_qos_read_value(&qos->resume_latency); - } else { + break; + case DEV_PM_QOS_MIN_FREQUENCY: + ret = IS_ERR_OR_NULL(qos) ? PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE + : freq_qos_read_value(&qos->freq, FREQ_QOS_MIN); + break; + case DEV_PM_QOS_MAX_FREQUENCY: + ret = IS_ERR_OR_NULL(qos) ? PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE + : freq_qos_read_value(&qos->freq, FREQ_QOS_MAX); + break; + default: WARN_ON(1); ret = 0; } @@ -159,6 +169,10 @@ static int apply_constraint(struct dev_pm_qos_request *req, req->dev->power.set_latency_tolerance(req->dev, value); } break; + case DEV_PM_QOS_MIN_FREQUENCY: + case DEV_PM_QOS_MAX_FREQUENCY: + ret = freq_qos_apply(&req->data.freq, action, value); + break; case DEV_PM_QOS_FLAGS: ret = pm_qos_update_flags(&qos->flags, &req->data.flr, action, value); @@ -209,6 +223,8 @@ static int dev_pm_qos_constraints_allocate(struct device *dev) c->no_constraint_value = PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT; c->type = PM_QOS_MIN; + freq_constraints_init(&qos->freq); + INIT_LIST_HEAD(&qos->flags.list); spin_lock_irq(&dev->power.lock); @@ -269,6 +285,20 @@ void dev_pm_qos_constraints_destroy(struct device *dev) memset(req, 0, sizeof(*req)); } + c = &qos->freq.min_freq; + plist_for_each_entry_safe(req, tmp, &c->list, data.freq.pnode) { + apply_constraint(req, PM_QOS_REMOVE_REQ, + PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE); + memset(req, 0, sizeof(*req)); + } + + c = &qos->freq.max_freq; + plist_for_each_entry_safe(req, tmp, &c->list, data.freq.pnode) { + apply_constraint(req, PM_QOS_REMOVE_REQ, + PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE); + memset(req, 0, sizeof(*req)); + } + f = &qos->flags; list_for_each_entry_safe(req, tmp, &f->list, data.flr.node) { apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE); @@ -314,11 +344,22 @@ static int __dev_pm_qos_add_request(struct device *dev, ret = dev_pm_qos_constraints_allocate(dev); trace_dev_pm_qos_add_request(dev_name(dev), type, value); - if (!ret) { - req->dev = dev; - req->type = type; + if (ret) + return ret; + + req->dev = dev; + req->type = type; + if (req->type == DEV_PM_QOS_MIN_FREQUENCY) + ret = freq_qos_add_request(&dev->power.qos->freq, + &req->data.freq, + FREQ_QOS_MIN, value); + else if (req->type == DEV_PM_QOS_MAX_FREQUENCY) + ret = freq_qos_add_request(&dev->power.qos->freq, + &req->data.freq, + FREQ_QOS_MAX, value); + else ret = apply_constraint(req, PM_QOS_ADD_REQ, value); - } + return ret; } @@ -382,6 +423,10 @@ static int __dev_pm_qos_update_request(struct dev_pm_qos_request *req, case DEV_PM_QOS_LATENCY_TOLERANCE: curr_value = req->data.pnode.prio; break; + case DEV_PM_QOS_MIN_FREQUENCY: + case DEV_PM_QOS_MAX_FREQUENCY: + curr_value = req->data.freq.pnode.prio; + break; case DEV_PM_QOS_FLAGS: curr_value = req->data.flr.flags; break; @@ -507,6 +552,14 @@ int dev_pm_qos_add_notifier(struct device *dev, struct notifier_block *notifier, ret = blocking_notifier_chain_register(dev->power.qos->resume_latency.notifiers, notifier); break; + case DEV_PM_QOS_MIN_FREQUENCY: + ret = freq_qos_add_notifier(&dev->power.qos->freq, + FREQ_QOS_MIN, notifier); + break; + case DEV_PM_QOS_MAX_FREQUENCY: + ret = freq_qos_add_notifier(&dev->power.qos->freq, + FREQ_QOS_MAX, notifier); + break; default: WARN_ON(1); ret = -EINVAL; @@ -546,6 +599,14 @@ int dev_pm_qos_remove_notifier(struct device *dev, ret = blocking_notifier_chain_unregister(dev->power.qos->resume_latency.notifiers, notifier); break; + case DEV_PM_QOS_MIN_FREQUENCY: + ret = freq_qos_remove_notifier(&dev->power.qos->freq, + FREQ_QOS_MIN, notifier); + break; + case DEV_PM_QOS_MAX_FREQUENCY: + ret = freq_qos_remove_notifier(&dev->power.qos->freq, + FREQ_QOS_MAX, notifier); + break; default: WARN_ON(1); ret = -EINVAL; diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h index 678fec6da5b9..19eafca5680e 100644 --- a/include/linux/pm_qos.h +++ b/include/linux/pm_qos.h @@ -34,6 +34,8 @@ enum pm_qos_flags_status { #define PM_QOS_RESUME_LATENCY_NO_CONSTRAINT PM_QOS_LATENCY_ANY #define PM_QOS_RESUME_LATENCY_NO_CONSTRAINT_NS PM_QOS_LATENCY_ANY_NS #define PM_QOS_LATENCY_TOLERANCE_DEFAULT_VALUE 0 +#define PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE 0 +#define PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE FREQ_QOS_MAX_DEFAULT_VALUE #define PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT (-1) #define PM_QOS_FLAG_NO_POWER_OFF (1 << 0) @@ -101,6 +103,8 @@ struct freq_qos_request { enum dev_pm_qos_req_type { DEV_PM_QOS_RESUME_LATENCY = 1, DEV_PM_QOS_LATENCY_TOLERANCE, + DEV_PM_QOS_MIN_FREQUENCY, + DEV_PM_QOS_MAX_FREQUENCY, DEV_PM_QOS_FLAGS, }; @@ -109,6 +113,7 @@ struct dev_pm_qos_request { union { struct plist_node pnode; struct pm_qos_flags_request flr; + struct freq_qos_request freq; } data; struct device *dev; }; @@ -116,6 +121,7 @@ struct dev_pm_qos_request { struct dev_pm_qos { struct pm_qos_constraints resume_latency; struct pm_qos_constraints latency_tolerance; + struct freq_constraints freq; struct pm_qos_flags flags; struct dev_pm_qos_request *resume_latency_req; struct dev_pm_qos_request *latency_tolerance_req; @@ -214,6 +220,10 @@ static inline s32 dev_pm_qos_read_value(struct device *dev, switch (type) { case DEV_PM_QOS_RESUME_LATENCY: return PM_QOS_RESUME_LATENCY_NO_CONSTRAINT; + case DEV_PM_QOS_MIN_FREQUENCY: + return PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE; + case DEV_PM_QOS_MAX_FREQUENCY: + return PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE; default: WARN_ON(1); return 0; @@ -293,6 +303,8 @@ int freq_qos_add_request(struct freq_constraints *qos, enum freq_qos_req_type type, s32 value); int freq_qos_update_request(struct freq_qos_request *req, s32 new_value); int freq_qos_remove_request(struct freq_qos_request *req); +int freq_qos_apply(struct freq_qos_request *req, + enum pm_qos_req_action action, s32 value); int freq_qos_add_notifier(struct freq_constraints *qos, enum freq_qos_req_type type, diff --git a/kernel/power/qos.c b/kernel/power/qos.c index a45cba7df0ae..83edf8698118 100644 --- a/kernel/power/qos.c +++ b/kernel/power/qos.c @@ -714,8 +714,10 @@ s32 freq_qos_read_value(struct freq_constraints *qos, * @req: Constraint request to apply. * @action: Action to perform (add/update/remove). * @value: Value to assign to the QoS request. + * + * This is only meant to be called from inside pm_qos, not drivers. */ -static int freq_qos_apply(struct freq_qos_request *req, +int freq_qos_apply(struct freq_qos_request *req, enum pm_qos_req_action action, s32 value) { int ret; -- cgit v1.2.3 From 6c3edaf9fd6a3be7fb5bc6931897c24cd3848f84 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Fri, 29 Nov 2019 20:52:18 -0800 Subject: tracing: Introduce trace event injection We have been trying to use rasdaemon to monitor hardware errors like correctable memory errors. rasdaemon uses trace events to monitor various hardware errors. In order to test it, we have to inject some hardware errors, unfortunately not all of them provide error injections. MCE does provide a way to inject MCE errors, but errors like PCI error and devlink error don't, it is not easy to add error injection to each of them. Instead, it is relatively easier to just allow users to inject trace events in a generic way so that all trace events can be injected. This patch introduces trace event injection, where a new 'inject' is added to each tracepoint directory. Users could write into this file with key=value pairs to specify the value of each fields of the trace event, all unspecified fields are set to zero values by default. For example, for the net/net_dev_queue tracepoint, we can inject: INJECT=/sys/kernel/debug/tracing/events/net/net_dev_queue/inject echo "" > $INJECT echo "name='test'" > $INJECT echo "name='test' len=1024" > $INJECT cat /sys/kernel/debug/tracing/trace ... <...>-614 [000] .... 36.571483: net_dev_queue: dev= skbaddr=00000000fbf338c2 len=0 <...>-614 [001] .... 136.588252: net_dev_queue: dev=test skbaddr=00000000fbf338c2 len=0 <...>-614 [001] .N.. 208.431878: net_dev_queue: dev=test skbaddr=00000000fbf338c2 len=1024 Triggers could be triggered as usual too: echo "stacktrace if len == 1025" > /sys/kernel/debug/tracing/events/net/net_dev_queue/trigger echo "len=1025" > $INJECT cat /sys/kernel/debug/tracing/trace ... bash-614 [000] .... 36.571483: net_dev_queue: dev= skbaddr=00000000fbf338c2 len=0 bash-614 [001] .... 136.588252: net_dev_queue: dev=test skbaddr=00000000fbf338c2 len=0 bash-614 [001] .N.. 208.431878: net_dev_queue: dev=test skbaddr=00000000fbf338c2 len=1024 bash-614 [001] .N.1 284.236349: => event_inject_write => vfs_write => ksys_write => do_syscall_64 => entry_SYSCALL_64_after_hwframe The only thing that can't be injected is string pointers as they require constant string pointers, this can't be done at run time. Link: http://lkml.kernel.org/r/20191130045218.18979-1-xiyou.wangcong@gmail.com Cc: Ingo Molnar Signed-off-by: Cong Wang Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/Kconfig | 9 + kernel/trace/Makefile | 1 + kernel/trace/trace.h | 1 + kernel/trace/trace_events.c | 6 + kernel/trace/trace_events_inject.c | 331 +++++++++++++++++++++++++++++++++++++ 5 files changed, 348 insertions(+) create mode 100644 kernel/trace/trace_events_inject.c (limited to 'kernel') diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index f67620499faa..29a9c5058b62 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -672,6 +672,15 @@ config HIST_TRIGGERS See Documentation/trace/histogram.rst. If in doubt, say N. +config TRACE_EVENT_INJECT + bool "Trace event injection" + depends on TRACING + help + Allow user-space to inject a specific trace event into the ring + buffer. This is mainly used for testing purpose. + + If unsure, say N. + config MMIOTRACE_TEST tristate "Test module for mmiotrace" depends on MMIOTRACE && m diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index c2b2148bb1d2..0e63db62225f 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -69,6 +69,7 @@ obj-$(CONFIG_EVENT_TRACING) += trace_event_perf.o endif obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o obj-$(CONFIG_EVENT_TRACING) += trace_events_trigger.o +obj-$(CONFIG_TRACE_EVENT_INJECT) += trace_events_inject.o obj-$(CONFIG_HIST_TRIGGERS) += trace_events_hist.o obj-$(CONFIG_BPF_EVENTS) += bpf_trace.o obj-$(CONFIG_KPROBE_EVENTS) += trace_kprobe.o diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index ca7fccafbcbb..63bf60f79398 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1601,6 +1601,7 @@ extern struct list_head ftrace_events; extern const struct file_operations event_trigger_fops; extern const struct file_operations event_hist_fops; +extern const struct file_operations event_inject_fops; #ifdef CONFIG_HIST_TRIGGERS extern int register_trigger_hist_cmd(void); diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 6b3a69e9aa6a..c6de3cebc127 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -2044,6 +2044,12 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file) trace_create_file("format", 0444, file->dir, call, &ftrace_event_format_fops); +#ifdef CONFIG_TRACE_EVENT_INJECT + if (call->event.type && call->class->reg) + trace_create_file("inject", 0200, file->dir, file, + &event_inject_fops); +#endif + return 0; } diff --git a/kernel/trace/trace_events_inject.c b/kernel/trace/trace_events_inject.c new file mode 100644 index 000000000000..d43710718ee5 --- /dev/null +++ b/kernel/trace/trace_events_inject.c @@ -0,0 +1,331 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * trace_events_inject - trace event injection + * + * Copyright (C) 2019 Cong Wang + */ + +#include +#include +#include +#include +#include + +#include "trace.h" + +static int +trace_inject_entry(struct trace_event_file *file, void *rec, int len) +{ + struct trace_event_buffer fbuffer; + struct ring_buffer *buffer; + int written = 0; + void *entry; + + rcu_read_lock_sched(); + buffer = file->tr->trace_buffer.buffer; + entry = trace_event_buffer_reserve(&fbuffer, file, len); + if (entry) { + memcpy(entry, rec, len); + written = len; + trace_event_buffer_commit(&fbuffer); + } + rcu_read_unlock_sched(); + + return written; +} + +static int +parse_field(char *str, struct trace_event_call *call, + struct ftrace_event_field **pf, u64 *pv) +{ + struct ftrace_event_field *field; + char *field_name; + int s, i = 0; + int len; + u64 val; + + if (!str[i]) + return 0; + /* First find the field to associate to */ + while (isspace(str[i])) + i++; + s = i; + while (isalnum(str[i]) || str[i] == '_') + i++; + len = i - s; + if (!len) + return -EINVAL; + + field_name = kmemdup_nul(str + s, len, GFP_KERNEL); + if (!field_name) + return -ENOMEM; + field = trace_find_event_field(call, field_name); + kfree(field_name); + if (!field) + return -ENOENT; + + *pf = field; + while (isspace(str[i])) + i++; + if (str[i] != '=') + return -EINVAL; + i++; + while (isspace(str[i])) + i++; + s = i; + if (isdigit(str[i]) || str[i] == '-') { + char *num, c; + int ret; + + /* Make sure the field is not a string */ + if (is_string_field(field)) + return -EINVAL; + + if (str[i] == '-') + i++; + + /* We allow 0xDEADBEEF */ + while (isalnum(str[i])) + i++; + num = str + s; + c = str[i]; + if (c != '\0' && !isspace(c)) + return -EINVAL; + str[i] = '\0'; + /* Make sure it is a value */ + if (field->is_signed) + ret = kstrtoll(num, 0, &val); + else + ret = kstrtoull(num, 0, &val); + str[i] = c; + if (ret) + return ret; + + *pv = val; + return i; + } else if (str[i] == '\'' || str[i] == '"') { + char q = str[i]; + + /* Make sure the field is OK for strings */ + if (!is_string_field(field)) + return -EINVAL; + + for (i++; str[i]; i++) { + if (str[i] == '\\' && str[i + 1]) { + i++; + continue; + } + if (str[i] == q) + break; + } + if (!str[i]) + return -EINVAL; + + /* Skip quotes */ + s++; + len = i - s; + if (len >= MAX_FILTER_STR_VAL) + return -EINVAL; + + *pv = (unsigned long)(str + s); + str[i] = 0; + /* go past the last quote */ + i++; + return i; + } + + return -EINVAL; +} + +static int trace_get_entry_size(struct trace_event_call *call) +{ + struct ftrace_event_field *field; + struct list_head *head; + int size = 0; + + head = trace_get_fields(call); + list_for_each_entry(field, head, link) { + if (field->size + field->offset > size) + size = field->size + field->offset; + } + + return size; +} + +static void *trace_alloc_entry(struct trace_event_call *call, int *size) +{ + int entry_size = trace_get_entry_size(call); + struct ftrace_event_field *field; + struct list_head *head; + void *entry = NULL; + + /* We need an extra '\0' at the end. */ + entry = kzalloc(entry_size + 1, GFP_KERNEL); + if (!entry) + return NULL; + + head = trace_get_fields(call); + list_for_each_entry(field, head, link) { + if (!is_string_field(field)) + continue; + if (field->filter_type == FILTER_STATIC_STRING) + continue; + if (field->filter_type == FILTER_DYN_STRING) { + u32 *str_item; + int str_loc = entry_size & 0xffff; + + str_item = (u32 *)(entry + field->offset); + *str_item = str_loc; /* string length is 0. */ + } else { + char **paddr; + + paddr = (char **)(entry + field->offset); + *paddr = ""; + } + } + + *size = entry_size + 1; + return entry; +} + +#define INJECT_STRING "STATIC STRING CAN NOT BE INJECTED" + +/* Caller is responsible to free the *pentry. */ +static int parse_entry(char *str, struct trace_event_call *call, void **pentry) +{ + struct ftrace_event_field *field; + unsigned long irq_flags; + void *entry = NULL; + int entry_size; + u64 val; + int len; + + entry = trace_alloc_entry(call, &entry_size); + *pentry = entry; + if (!entry) + return -ENOMEM; + + local_save_flags(irq_flags); + tracing_generic_entry_update(entry, call->event.type, irq_flags, + preempt_count()); + + while ((len = parse_field(str, call, &field, &val)) > 0) { + if (is_function_field(field)) + return -EINVAL; + + if (is_string_field(field)) { + char *addr = (char *)(unsigned long) val; + + if (field->filter_type == FILTER_STATIC_STRING) { + strlcpy(entry + field->offset, addr, field->size); + } else if (field->filter_type == FILTER_DYN_STRING) { + int str_len = strlen(addr) + 1; + int str_loc = entry_size & 0xffff; + u32 *str_item; + + entry_size += str_len; + *pentry = krealloc(entry, entry_size, GFP_KERNEL); + if (!*pentry) { + kfree(entry); + return -ENOMEM; + } + entry = *pentry; + + strlcpy(entry + (entry_size - str_len), addr, str_len); + str_item = (u32 *)(entry + field->offset); + *str_item = (str_len << 16) | str_loc; + } else { + char **paddr; + + paddr = (char **)(entry + field->offset); + *paddr = INJECT_STRING; + } + } else { + switch (field->size) { + case 1: { + u8 tmp = (u8) val; + + memcpy(entry + field->offset, &tmp, 1); + break; + } + case 2: { + u16 tmp = (u16) val; + + memcpy(entry + field->offset, &tmp, 2); + break; + } + case 4: { + u32 tmp = (u32) val; + + memcpy(entry + field->offset, &tmp, 4); + break; + } + case 8: + memcpy(entry + field->offset, &val, 8); + break; + default: + return -EINVAL; + } + } + + str += len; + } + + if (len < 0) + return len; + + return entry_size; +} + +static ssize_t +event_inject_write(struct file *filp, const char __user *ubuf, size_t cnt, + loff_t *ppos) +{ + struct trace_event_call *call; + struct trace_event_file *file; + int err = -ENODEV, size; + void *entry = NULL; + char *buf; + + if (cnt >= PAGE_SIZE) + return -EINVAL; + + buf = memdup_user_nul(ubuf, cnt); + if (IS_ERR(buf)) + return PTR_ERR(buf); + strim(buf); + + mutex_lock(&event_mutex); + file = event_file_data(filp); + if (file) { + call = file->event_call; + size = parse_entry(buf, call, &entry); + if (size < 0) + err = size; + else + err = trace_inject_entry(file, entry, size); + } + mutex_unlock(&event_mutex); + + kfree(entry); + kfree(buf); + + if (err < 0) + return err; + + *ppos += err; + return cnt; +} + +static ssize_t +event_inject_read(struct file *file, char __user *buf, size_t size, + loff_t *ppos) +{ + return -EPERM; +} + +const struct file_operations event_inject_fops = { + .open = tracing_open_generic, + .read = event_inject_read, + .write = event_inject_write, +}; -- cgit v1.2.3 From a356646a56857c2e5ad875beec734d7145ecd49a Mon Sep 17 00:00:00 2001 From: Steven Rostedt (VMware) Date: Mon, 2 Dec 2019 16:25:27 -0500 Subject: tracing: Do not create directories if lockdown is in affect If lockdown is disabling tracing on boot up, it prevents the tracing files from even bering created. But when that happens, there's several places that will give a warning that the files were not created as that is usually a sign of a bug. Add in strategic locations where a check is made to see if tracing is disabled by lockdown, and if it is, do not go further, and fail silently (but print that tracing is disabled by lockdown, without doing a WARN_ON()). Cc: Matthew Garrett Fixes: 17911ff38aa5 ("tracing: Add locked_down checks to the open calls of files created for tracefs") Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ring_buffer.c | 6 ++++++ kernel/trace/trace.c | 17 +++++++++++++++++ 2 files changed, 23 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 66358d66c933..4bf050fcfe3b 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include /* for self test */ @@ -5068,6 +5069,11 @@ static __init int test_ringbuffer(void) int cpu; int ret = 0; + if (security_locked_down(LOCKDOWN_TRACEFS)) { + pr_warning("Lockdown is enabled, skipping ring buffer tests\n"); + return 0; + } + pr_info("Running ring buffer tests...\n"); buffer = ring_buffer_alloc(RB_TEST_BUFFER_SIZE, RB_FL_OVERWRITE); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 02a23a6e5e00..23459d53d576 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1888,6 +1888,12 @@ int __init register_tracer(struct tracer *type) return -1; } + if (security_locked_down(LOCKDOWN_TRACEFS)) { + pr_warning("Can not register tracer %s due to lockdown\n", + type->name); + return -EPERM; + } + mutex_lock(&trace_types_lock); tracing_selftest_running = true; @@ -8789,6 +8795,11 @@ struct dentry *tracing_init_dentry(void) { struct trace_array *tr = &global_trace; + if (security_locked_down(LOCKDOWN_TRACEFS)) { + pr_warning("Tracing disabled due to lockdown\n"); + return ERR_PTR(-EPERM); + } + /* The top level trace array uses NULL as parent */ if (tr->dir) return NULL; @@ -9231,6 +9242,12 @@ __init static int tracer_alloc_buffers(void) int ring_buf_size; int ret = -ENOMEM; + + if (security_locked_down(LOCKDOWN_TRACEFS)) { + pr_warning("Tracing disabled due to lockdown\n"); + return -EPERM; + } + /* * Make sure we don't accidently add more trace options * than we have bits for. -- cgit v1.2.3 From 1a50cb80f219c44adb6265f5071b81fc3c1deced Mon Sep 17 00:00:00 2001 From: Xiaoming Ni Date: Wed, 4 Dec 2019 16:50:39 -0800 Subject: kernel/notifier.c: intercept duplicate registrations to avoid infinite loops Registering the same notifier to a hook repeatedly can cause the hook list to form a ring or lose other members of the list. case1: An infinite loop in notifier_chain_register() can cause soft lockup atomic_notifier_chain_register(&test_notifier_list, &test1); atomic_notifier_chain_register(&test_notifier_list, &test1); atomic_notifier_chain_register(&test_notifier_list, &test2); case2: An infinite loop in notifier_chain_register() can cause soft lockup atomic_notifier_chain_register(&test_notifier_list, &test1); atomic_notifier_chain_register(&test_notifier_list, &test1); atomic_notifier_call_chain(&test_notifier_list, 0, NULL); case3: lose other hook test2 atomic_notifier_chain_register(&test_notifier_list, &test1); atomic_notifier_chain_register(&test_notifier_list, &test2); atomic_notifier_chain_register(&test_notifier_list, &test1); case4: Unregister returns 0, but the hook is still in the linked list, and it is not really registered. If you call notifier_call_chain after ko is unloaded, it will trigger oops. If the system is configured with softlockup_panic and the same hook is repeatedly registered on the panic_notifier_list, it will cause a loop panic. Add a check in notifier_chain_register(), intercepting duplicate registrations to avoid infinite loops Link: http://lkml.kernel.org/r/1568861888-34045-2-git-send-email-nixiaoming@huawei.com Signed-off-by: Xiaoming Ni Reviewed-by: Vasily Averin Reviewed-by: Andrew Morton Cc: Alexey Dobriyan Cc: Anna Schumaker Cc: Arjan van de Ven Cc: J. Bruce Fields Cc: Chuck Lever Cc: David S. Miller Cc: Jeff Layton Cc: Andy Lutomirski Cc: Ingo Molnar Cc: Nadia Derbey Cc: "Paul E. McKenney" Cc: Sam Protsenko Cc: Alan Stern Cc: Thomas Gleixner Cc: Trond Myklebust Cc: Viresh Kumar Cc: Xiaoming Ni Cc: YueHaibing Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/notifier.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/notifier.c b/kernel/notifier.c index d9f5081d578d..30bedb8be6dd 100644 --- a/kernel/notifier.c +++ b/kernel/notifier.c @@ -23,7 +23,10 @@ static int notifier_chain_register(struct notifier_block **nl, struct notifier_block *n) { while ((*nl) != NULL) { - WARN_ONCE(((*nl) == n), "double register detected"); + if (unlikely((*nl) == n)) { + WARN(1, "double register detected"); + return 0; + } if (n->priority > (*nl)->priority) break; nl = &((*nl)->next); -- cgit v1.2.3 From 5adaabb65a267d890b29193af2dbc38a3b85bbf2 Mon Sep 17 00:00:00 2001 From: Xiaoming Ni Date: Wed, 4 Dec 2019 16:50:43 -0800 Subject: kernel/notifier.c: remove notifier_chain_cond_register() The only difference between notifier_chain_cond_register() and notifier_chain_register() is the lack of warning hints for duplicate registrations. Use notifier_chain_register() instead of notifier_chain_cond_register() to avoid duplicate code Link: http://lkml.kernel.org/r/1568861888-34045-3-git-send-email-nixiaoming@huawei.com Signed-off-by: Xiaoming Ni Reviewed-by: Andrew Morton Cc: Alan Stern Cc: Alexey Dobriyan Cc: Andy Lutomirski Cc: Anna Schumaker Cc: Arjan van de Ven Cc: Chuck Lever Cc: David S. Miller Cc: Ingo Molnar Cc: J. Bruce Fields Cc: Jeff Layton Cc: Nadia Derbey Cc: "Paul E. McKenney" Cc: Sam Protsenko Cc: Thomas Gleixner Cc: Trond Myklebust Cc: Vasily Averin Cc: Viresh Kumar Cc: YueHaibing Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/notifier.c | 17 +---------------- 1 file changed, 1 insertion(+), 16 deletions(-) (limited to 'kernel') diff --git a/kernel/notifier.c b/kernel/notifier.c index 30bedb8be6dd..e3d221f092fe 100644 --- a/kernel/notifier.c +++ b/kernel/notifier.c @@ -36,21 +36,6 @@ static int notifier_chain_register(struct notifier_block **nl, return 0; } -static int notifier_chain_cond_register(struct notifier_block **nl, - struct notifier_block *n) -{ - while ((*nl) != NULL) { - if ((*nl) == n) - return 0; - if (n->priority > (*nl)->priority) - break; - nl = &((*nl)->next); - } - n->next = *nl; - rcu_assign_pointer(*nl, n); - return 0; -} - static int notifier_chain_unregister(struct notifier_block **nl, struct notifier_block *n) { @@ -252,7 +237,7 @@ int blocking_notifier_chain_cond_register(struct blocking_notifier_head *nh, int ret; down_write(&nh->rwsem); - ret = notifier_chain_cond_register(&nh->head, n); + ret = notifier_chain_register(&nh->head, n); up_write(&nh->rwsem); return ret; } -- cgit v1.2.3 From 260a2679e5cbfb3d8a4cf6cd1cb6f57e89c7e543 Mon Sep 17 00:00:00 2001 From: Xiaoming Ni Date: Wed, 4 Dec 2019 16:50:47 -0800 Subject: kernel/notifier.c: remove blocking_notifier_chain_cond_register() blocking_notifier_chain_cond_register() does not consider system_booting state, which is the only difference between this function and blocking_notifier_cain_register(). This can be a bug and is a piece of duplicate code. Delete blocking_notifier_chain_cond_register() Link: http://lkml.kernel.org/r/1568861888-34045-4-git-send-email-nixiaoming@huawei.com Signed-off-by: Xiaoming Ni Reviewed-by: Andrew Morton Cc: Alan Stern Cc: Alexey Dobriyan Cc: Andy Lutomirski Cc: Anna Schumaker Cc: Arjan van de Ven Cc: Chuck Lever Cc: David S. Miller Cc: Ingo Molnar Cc: J. Bruce Fields Cc: Jeff Layton Cc: Nadia Derbey Cc: "Paul E. McKenney" Cc: Sam Protsenko Cc: Thomas Gleixner Cc: Trond Myklebust Cc: Vasily Averin Cc: Viresh Kumar Cc: YueHaibing Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/notifier.h | 4 ---- kernel/notifier.c | 23 ----------------------- net/sunrpc/rpc_pipe.c | 2 +- 3 files changed, 1 insertion(+), 28 deletions(-) (limited to 'kernel') diff --git a/include/linux/notifier.h b/include/linux/notifier.h index 0096a05395e3..018947611483 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -150,10 +150,6 @@ extern int raw_notifier_chain_register(struct raw_notifier_head *nh, extern int srcu_notifier_chain_register(struct srcu_notifier_head *nh, struct notifier_block *nb); -extern int blocking_notifier_chain_cond_register( - struct blocking_notifier_head *nh, - struct notifier_block *nb); - extern int atomic_notifier_chain_unregister(struct atomic_notifier_head *nh, struct notifier_block *nb); extern int blocking_notifier_chain_unregister(struct blocking_notifier_head *nh, diff --git a/kernel/notifier.c b/kernel/notifier.c index e3d221f092fe..63d7501ac638 100644 --- a/kernel/notifier.c +++ b/kernel/notifier.c @@ -220,29 +220,6 @@ int blocking_notifier_chain_register(struct blocking_notifier_head *nh, } EXPORT_SYMBOL_GPL(blocking_notifier_chain_register); -/** - * blocking_notifier_chain_cond_register - Cond add notifier to a blocking notifier chain - * @nh: Pointer to head of the blocking notifier chain - * @n: New entry in notifier chain - * - * Adds a notifier to a blocking notifier chain, only if not already - * present in the chain. - * Must be called in process context. - * - * Currently always returns zero. - */ -int blocking_notifier_chain_cond_register(struct blocking_notifier_head *nh, - struct notifier_block *n) -{ - int ret; - - down_write(&nh->rwsem); - ret = notifier_chain_register(&nh->head, n); - up_write(&nh->rwsem); - return ret; -} -EXPORT_SYMBOL_GPL(blocking_notifier_chain_cond_register); - /** * blocking_notifier_chain_unregister - Remove notifier from a blocking notifier chain * @nh: Pointer to head of the blocking notifier chain diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index b71a39ded930..39e14d5edaf1 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -51,7 +51,7 @@ static BLOCKING_NOTIFIER_HEAD(rpc_pipefs_notifier_list); int rpc_pipefs_notifier_register(struct notifier_block *nb) { - return blocking_notifier_chain_cond_register(&rpc_pipefs_notifier_list, nb); + return blocking_notifier_chain_register(&rpc_pipefs_notifier_list, nb); } EXPORT_SYMBOL_GPL(rpc_pipefs_notifier_register); -- cgit v1.2.3 From ef70eff9dea66f38f8c2c2dcc7fe4b7a2bbb4921 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Wed, 4 Dec 2019 16:50:50 -0800 Subject: kernel/profile.c: use cpumask_available to check for NULL cpumask When building with clang + -Wtautological-pointer-compare, these instances pop up: kernel/profile.c:339:6: warning: comparison of array 'prof_cpu_mask' not equal to a null pointer is always true [-Wtautological-pointer-compare] if (prof_cpu_mask != NULL) ^~~~~~~~~~~~~ ~~~~ kernel/profile.c:376:6: warning: comparison of array 'prof_cpu_mask' not equal to a null pointer is always true [-Wtautological-pointer-compare] if (prof_cpu_mask != NULL) ^~~~~~~~~~~~~ ~~~~ kernel/profile.c:406:26: warning: comparison of array 'prof_cpu_mask' not equal to a null pointer is always true [-Wtautological-pointer-compare] if (!user_mode(regs) && prof_cpu_mask != NULL && ^~~~~~~~~~~~~ ~~~~ 3 warnings generated. This can be addressed with the cpumask_available helper, introduced in commit f7e30f01a9e2 ("cpumask: Add helper cpumask_available()") to fix warnings like this while keeping the code the same. Link: https://github.com/ClangBuiltLinux/linux/issues/747 Link: http://lkml.kernel.org/r/20191022191957.9554-1-natechancellor@gmail.com Signed-off-by: Nathan Chancellor Reviewed-by: Andrew Morton Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/profile.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/profile.c b/kernel/profile.c index af7c94bf5fa1..4b144b02ca5d 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -336,7 +336,7 @@ static int profile_dead_cpu(unsigned int cpu) struct page *page; int i; - if (prof_cpu_mask != NULL) + if (cpumask_available(prof_cpu_mask)) cpumask_clear_cpu(cpu, prof_cpu_mask); for (i = 0; i < 2; i++) { @@ -373,7 +373,7 @@ static int profile_prepare_cpu(unsigned int cpu) static int profile_online_cpu(unsigned int cpu) { - if (prof_cpu_mask != NULL) + if (cpumask_available(prof_cpu_mask)) cpumask_set_cpu(cpu, prof_cpu_mask); return 0; @@ -403,7 +403,7 @@ void profile_tick(int type) { struct pt_regs *regs = get_irq_regs(); - if (!user_mode(regs) && prof_cpu_mask != NULL && + if (!user_mode(regs) && cpumask_available(prof_cpu_mask) && cpumask_test_cpu(smp_processor_id(), prof_cpu_mask)) profile_hit(type, (void *)profile_pc(regs)); } -- cgit v1.2.3 From 5e1aada08cd19ea652b2d32a250501d09b02ff2e Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 4 Dec 2019 16:50:53 -0800 Subject: kernel/sys.c: avoid copying possible padding bytes in copy_to_user Initialization is not guaranteed to zero padding bytes so use an explicit memset instead to avoid leaking any kernel content in any possible padding bytes. Link: http://lkml.kernel.org/r/dfa331c00881d61c8ee51577a082d8bebd61805c.camel@perches.com Signed-off-by: Joe Perches Cc: Dan Carpenter Cc: Julia Lawall Cc: Thomas Gleixner Cc: Kees Cook Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sys.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sys.c b/kernel/sys.c index d3aef31e24dc..a9331f101883 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1279,11 +1279,13 @@ SYSCALL_DEFINE1(uname, struct old_utsname __user *, name) SYSCALL_DEFINE1(olduname, struct oldold_utsname __user *, name) { - struct oldold_utsname tmp = {}; + struct oldold_utsname tmp; if (!name) return -EFAULT; + memset(&tmp, 0, sizeof(tmp)); + down_read(&uts_sem); memcpy(&tmp.sysname, &utsname()->sysname, __OLD_UTS_LEN); memcpy(&tmp.nodename, &utsname()->nodename, __OLD_UTS_LEN); -- cgit v1.2.3 From 964975ac6677c97ae61ec9d6969dd5d03f18d1c3 Mon Sep 17 00:00:00 2001 From: Huang Shijie Date: Wed, 4 Dec 2019 16:52:03 -0800 Subject: lib/genalloc.c: rename addr_in_gen_pool to gen_pool_has_addr Follow the kernel conventions, rename addr_in_gen_pool to gen_pool_has_addr. [sjhuang@iluvatar.ai: fix Documentation/ too] Link: http://lkml.kernel.org/r/20181229015914.5573-1-sjhuang@iluvatar.ai Link: http://lkml.kernel.org/r/20181228083950.20398-1-sjhuang@iluvatar.ai Signed-off-by: Huang Shijie Reviewed-by: Andrew Morton Cc: Russell King Cc: Arnd Bergmann Cc: Greg Kroah-Hartman Cc: Christoph Hellwig Cc: Marek Szyprowski Cc: Robin Murphy Cc: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/core-api/genalloc.rst | 2 +- arch/arm/mm/dma-mapping.c | 2 +- drivers/misc/sram-exec.c | 2 +- include/linux/genalloc.h | 2 +- kernel/dma/remap.c | 2 +- lib/genalloc.c | 6 +++--- 6 files changed, 8 insertions(+), 8 deletions(-) (limited to 'kernel') diff --git a/Documentation/core-api/genalloc.rst b/Documentation/core-api/genalloc.rst index 098a46f55798..a5af2cbf58a5 100644 --- a/Documentation/core-api/genalloc.rst +++ b/Documentation/core-api/genalloc.rst @@ -129,7 +129,7 @@ writing of special-purpose memory allocators in the future. :functions: gen_pool_for_each_chunk .. kernel-doc:: lib/genalloc.c - :functions: addr_in_gen_pool + :functions: gen_pool_has_addr .. kernel-doc:: lib/genalloc.c :functions: gen_pool_avail diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 1df6eb42f22e..e822af0d9219 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -529,7 +529,7 @@ static void *__alloc_from_pool(size_t size, struct page **ret_page) static bool __in_atomic_pool(void *start, size_t size) { - return addr_in_gen_pool(atomic_pool, (unsigned long)start, size); + return gen_pool_has_addr(atomic_pool, (unsigned long)start, size); } static int __free_from_pool(void *start, size_t size) diff --git a/drivers/misc/sram-exec.c b/drivers/misc/sram-exec.c index 426ad912b441..d054e2842a5f 100644 --- a/drivers/misc/sram-exec.c +++ b/drivers/misc/sram-exec.c @@ -96,7 +96,7 @@ void *sram_exec_copy(struct gen_pool *pool, void *dst, void *src, if (!part) return NULL; - if (!addr_in_gen_pool(pool, (unsigned long)dst, size)) + if (!gen_pool_has_addr(pool, (unsigned long)dst, size)) return NULL; base = (unsigned long)part->base; diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h index 4bd583bd6934..5b14a0f38124 100644 --- a/include/linux/genalloc.h +++ b/include/linux/genalloc.h @@ -206,7 +206,7 @@ extern struct gen_pool *devm_gen_pool_create(struct device *dev, int min_alloc_order, int nid, const char *name); extern struct gen_pool *gen_pool_get(struct device *dev, const char *name); -bool addr_in_gen_pool(struct gen_pool *pool, unsigned long start, +extern bool gen_pool_has_addr(struct gen_pool *pool, unsigned long start, size_t size); #ifdef CONFIG_OF diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c index d47bd40fc0f5..d14cbc83986a 100644 --- a/kernel/dma/remap.c +++ b/kernel/dma/remap.c @@ -178,7 +178,7 @@ bool dma_in_atomic_pool(void *start, size_t size) if (unlikely(!atomic_pool)) return false; - return addr_in_gen_pool(atomic_pool, (unsigned long)start, size); + return gen_pool_has_addr(atomic_pool, (unsigned long)start, size); } void *dma_alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags) diff --git a/lib/genalloc.c b/lib/genalloc.c index af9a57422186..7f1244b5294a 100644 --- a/lib/genalloc.c +++ b/lib/genalloc.c @@ -540,7 +540,7 @@ void gen_pool_for_each_chunk(struct gen_pool *pool, EXPORT_SYMBOL(gen_pool_for_each_chunk); /** - * addr_in_gen_pool - checks if an address falls within the range of a pool + * gen_pool_has_addr - checks if an address falls within the range of a pool * @pool: the generic memory pool * @start: start address * @size: size of the region @@ -548,7 +548,7 @@ EXPORT_SYMBOL(gen_pool_for_each_chunk); * Check if the range of addresses falls within the specified pool. Returns * true if the entire range is contained in the pool and false otherwise. */ -bool addr_in_gen_pool(struct gen_pool *pool, unsigned long start, +bool gen_pool_has_addr(struct gen_pool *pool, unsigned long start, size_t size) { bool found = false; @@ -567,7 +567,7 @@ bool addr_in_gen_pool(struct gen_pool *pool, unsigned long start, rcu_read_unlock(); return found; } -EXPORT_SYMBOL(addr_in_gen_pool); +EXPORT_SYMBOL(gen_pool_has_addr); /** * gen_pool_avail - get available free space of the pool -- cgit v1.2.3 From eec028c9386ed1a692aa01a85b55952202b41619 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Wed, 4 Dec 2019 16:52:43 -0800 Subject: kcov: remote coverage support Patch series " kcov: collect coverage from usb and vhost", v3. This patchset extends kcov to allow collecting coverage from backgound kernel threads. This extension requires custom annotations for each of the places where coverage collection is desired. This patchset implements this for hub events in the USB subsystem and for vhost workers. See the first patch description for details about the kcov extension. The other two patches apply this kcov extension to USB and vhost. Examples of other subsystems that might potentially benefit from this when custom annotations are added (the list is based on process_one_work() callers for bugs recently reported by syzbot): 1. fs: writeback wb_workfn() worker, 2. net: addrconf_dad_work()/addrconf_verify_work() workers, 3. net: neigh_periodic_work() worker, 4. net/p9: p9_write_work()/p9_read_work() workers, 5. block: blk_mq_run_work_fn() worker. These patches have been used to enable coverage-guided USB fuzzing with syzkaller for the last few years, see the details here: https://github.com/google/syzkaller/blob/master/docs/linux/external_fuzzing_usb.md This patchset has been pushed to the public Linux kernel Gerrit instance: https://linux-review.googlesource.com/c/linux/kernel/git/torvalds/linux/+/1524 This patch (of 3): Add background thread coverage collection ability to kcov. With KCOV_ENABLE coverage is collected only for syscalls that are issued from the current process. With KCOV_REMOTE_ENABLE it's possible to collect coverage for arbitrary parts of the kernel code, provided that those parts are annotated with kcov_remote_start()/kcov_remote_stop(). This allows to collect coverage from two types of kernel background threads: the global ones, that are spawned during kernel boot in a limited number of instances (e.g. one USB hub_event() worker thread is spawned per USB HCD); and the local ones, that are spawned when a user interacts with some kernel interface (e.g. vhost workers). To enable collecting coverage from a global background thread, a unique global handle must be assigned and passed to the corresponding kcov_remote_start() call. Then a userspace process can pass a list of such handles to the KCOV_REMOTE_ENABLE ioctl in the handles array field of the kcov_remote_arg struct. This will attach the used kcov device to the code sections, that are referenced by those handles. Since there might be many local background threads spawned from different userspace processes, we can't use a single global handle per annotation. Instead, the userspace process passes a non-zero handle through the common_handle field of the kcov_remote_arg struct. This common handle gets saved to the kcov_handle field in the current task_struct and needs to be passed to the newly spawned threads via custom annotations. Those threads should in turn be annotated with kcov_remote_start()/kcov_remote_stop(). Internally kcov stores handles as u64 integers. The top byte of a handle is used to denote the id of a subsystem that this handle belongs to, and the lower 4 bytes are used to denote the id of a thread instance within that subsystem. A reserved value 0 is used as a subsystem id for common handles as they don't belong to a particular subsystem. The bytes 4-7 are currently reserved and must be zero. In the future the number of bytes used for the subsystem or handle ids might be increased. When a particular userspace process collects coverage by via a common handle, kcov will collect coverage for each code section that is annotated to use the common handle obtained as kcov_handle from the current task_struct. However non common handles allow to collect coverage selectively from different subsystems. Link: http://lkml.kernel.org/r/e90e315426a384207edbec1d6aa89e43008e4caf.1572366574.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Cc: Dmitry Vyukov Cc: Greg Kroah-Hartman Cc: Alan Stern Cc: "Michael S. Tsirkin" Cc: Jason Wang Cc: Arnd Bergmann Cc: Steven Rostedt Cc: David Windsor Cc: Elena Reshetova Cc: Anders Roxell Cc: Alexander Potapenko Cc: Marco Elver Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/dev-tools/kcov.rst | 129 +++++++++ include/linux/kcov.h | 23 ++ include/linux/sched.h | 8 + include/uapi/linux/kcov.h | 28 ++ kernel/kcov.c | 547 ++++++++++++++++++++++++++++++++++++--- 5 files changed, 700 insertions(+), 35 deletions(-) (limited to 'kernel') diff --git a/Documentation/dev-tools/kcov.rst b/Documentation/dev-tools/kcov.rst index 42b612677799..36890b026e77 100644 --- a/Documentation/dev-tools/kcov.rst +++ b/Documentation/dev-tools/kcov.rst @@ -34,6 +34,7 @@ Profiling data will only become accessible once debugfs has been mounted:: Coverage collection ------------------- + The following program demonstrates coverage collection from within a test program using kcov: @@ -128,6 +129,7 @@ only need to enable coverage (disable happens automatically on thread end). Comparison operands collection ------------------------------ + Comparison operands collection is similar to coverage collection: .. code-block:: c @@ -202,3 +204,130 @@ Comparison operands collection is similar to coverage collection: Note that the kcov modes (coverage collection or comparison operands) are mutually exclusive. + +Remote coverage collection +-------------------------- + +With KCOV_ENABLE coverage is collected only for syscalls that are issued +from the current process. With KCOV_REMOTE_ENABLE it's possible to collect +coverage for arbitrary parts of the kernel code, provided that those parts +are annotated with kcov_remote_start()/kcov_remote_stop(). + +This allows to collect coverage from two types of kernel background +threads: the global ones, that are spawned during kernel boot in a limited +number of instances (e.g. one USB hub_event() worker thread is spawned per +USB HCD); and the local ones, that are spawned when a user interacts with +some kernel interface (e.g. vhost workers). + +To enable collecting coverage from a global background thread, a unique +global handle must be assigned and passed to the corresponding +kcov_remote_start() call. Then a userspace process can pass a list of such +handles to the KCOV_REMOTE_ENABLE ioctl in the handles array field of the +kcov_remote_arg struct. This will attach the used kcov device to the code +sections, that are referenced by those handles. + +Since there might be many local background threads spawned from different +userspace processes, we can't use a single global handle per annotation. +Instead, the userspace process passes a non-zero handle through the +common_handle field of the kcov_remote_arg struct. This common handle gets +saved to the kcov_handle field in the current task_struct and needs to be +passed to the newly spawned threads via custom annotations. Those threads +should in turn be annotated with kcov_remote_start()/kcov_remote_stop(). + +Internally kcov stores handles as u64 integers. The top byte of a handle +is used to denote the id of a subsystem that this handle belongs to, and +the lower 4 bytes are used to denote the id of a thread instance within +that subsystem. A reserved value 0 is used as a subsystem id for common +handles as they don't belong to a particular subsystem. The bytes 4-7 are +currently reserved and must be zero. In the future the number of bytes +used for the subsystem or handle ids might be increased. + +When a particular userspace proccess collects coverage by via a common +handle, kcov will collect coverage for each code section that is annotated +to use the common handle obtained as kcov_handle from the current +task_struct. However non common handles allow to collect coverage +selectively from different subsystems. + +.. code-block:: c + + struct kcov_remote_arg { + unsigned trace_mode; + unsigned area_size; + unsigned num_handles; + uint64_t common_handle; + uint64_t handles[0]; + }; + + #define KCOV_INIT_TRACE _IOR('c', 1, unsigned long) + #define KCOV_DISABLE _IO('c', 101) + #define KCOV_REMOTE_ENABLE _IOW('c', 102, struct kcov_remote_arg) + + #define COVER_SIZE (64 << 10) + + #define KCOV_TRACE_PC 0 + + #define KCOV_SUBSYSTEM_COMMON (0x00ull << 56) + #define KCOV_SUBSYSTEM_USB (0x01ull << 56) + + #define KCOV_SUBSYSTEM_MASK (0xffull << 56) + #define KCOV_INSTANCE_MASK (0xffffffffull) + + static inline __u64 kcov_remote_handle(__u64 subsys, __u64 inst) + { + if (subsys & ~KCOV_SUBSYSTEM_MASK || inst & ~KCOV_INSTANCE_MASK) + return 0; + return subsys | inst; + } + + #define KCOV_COMMON_ID 0x42 + #define KCOV_USB_BUS_NUM 1 + + int main(int argc, char **argv) + { + int fd; + unsigned long *cover, n, i; + struct kcov_remote_arg *arg; + + fd = open("/sys/kernel/debug/kcov", O_RDWR); + if (fd == -1) + perror("open"), exit(1); + if (ioctl(fd, KCOV_INIT_TRACE, COVER_SIZE)) + perror("ioctl"), exit(1); + cover = (unsigned long*)mmap(NULL, COVER_SIZE * sizeof(unsigned long), + PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + if ((void*)cover == MAP_FAILED) + perror("mmap"), exit(1); + + /* Enable coverage collection via common handle and from USB bus #1. */ + arg = calloc(1, sizeof(*arg) + sizeof(uint64_t)); + if (!arg) + perror("calloc"), exit(1); + arg->trace_mode = KCOV_TRACE_PC; + arg->area_size = COVER_SIZE; + arg->num_handles = 1; + arg->common_handle = kcov_remote_handle(KCOV_SUBSYSTEM_COMMON, + KCOV_COMMON_ID); + arg->handles[0] = kcov_remote_handle(KCOV_SUBSYSTEM_USB, + KCOV_USB_BUS_NUM); + if (ioctl(fd, KCOV_REMOTE_ENABLE, arg)) + perror("ioctl"), free(arg), exit(1); + free(arg); + + /* + * Here the user needs to trigger execution of a kernel code section + * that is either annotated with the common handle, or to trigger some + * activity on USB bus #1. + */ + sleep(2); + + n = __atomic_load_n(&cover[0], __ATOMIC_RELAXED); + for (i = 0; i < n; i++) + printf("0x%lx\n", cover[i + 1]); + if (ioctl(fd, KCOV_DISABLE, 0)) + perror("ioctl"), exit(1); + if (munmap(cover, COVER_SIZE * sizeof(unsigned long))) + perror("munmap"), exit(1); + if (close(fd)) + perror("close"), exit(1); + return 0; + } diff --git a/include/linux/kcov.h b/include/linux/kcov.h index b76a1807028d..a10e84707d82 100644 --- a/include/linux/kcov.h +++ b/include/linux/kcov.h @@ -37,12 +37,35 @@ do { \ (t)->kcov_mode &= ~KCOV_IN_CTXSW; \ } while (0) +/* See Documentation/dev-tools/kcov.rst for usage details. */ +void kcov_remote_start(u64 handle); +void kcov_remote_stop(void); +u64 kcov_common_handle(void); + +static inline void kcov_remote_start_common(u64 id) +{ + kcov_remote_start(kcov_remote_handle(KCOV_SUBSYSTEM_COMMON, id)); +} + +static inline void kcov_remote_start_usb(u64 id) +{ + kcov_remote_start(kcov_remote_handle(KCOV_SUBSYSTEM_USB, id)); +} + #else static inline void kcov_task_init(struct task_struct *t) {} static inline void kcov_task_exit(struct task_struct *t) {} static inline void kcov_prepare_switch(struct task_struct *t) {} static inline void kcov_finish_switch(struct task_struct *t) {} +static inline void kcov_remote_start(u64 handle) {} +static inline void kcov_remote_stop(void) {} +static inline u64 kcov_common_handle(void) +{ + return 0; +} +static inline void kcov_remote_start_common(u64 id) {} +static inline void kcov_remote_start_usb(u64 id) {} #endif /* CONFIG_KCOV */ #endif /* _LINUX_KCOV_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 0cd97d9dd021..467d26046416 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1210,6 +1210,8 @@ struct task_struct { #endif /* CONFIG_TRACING */ #ifdef CONFIG_KCOV + /* See kernel/kcov.c for more details. */ + /* Coverage collection mode enabled for this task (0 if disabled): */ unsigned int kcov_mode; @@ -1221,6 +1223,12 @@ struct task_struct { /* KCOV descriptor wired with this task or NULL: */ struct kcov *kcov; + + /* KCOV common handle for remote coverage collection: */ + u64 kcov_handle; + + /* KCOV sequence number: */ + int kcov_sequence; #endif #ifdef CONFIG_MEMCG diff --git a/include/uapi/linux/kcov.h b/include/uapi/linux/kcov.h index 9529867717a8..409d3ad1e6e2 100644 --- a/include/uapi/linux/kcov.h +++ b/include/uapi/linux/kcov.h @@ -4,9 +4,24 @@ #include +/* + * Argument for KCOV_REMOTE_ENABLE ioctl, see Documentation/dev-tools/kcov.rst + * and the comment before kcov_remote_start() for usage details. + */ +struct kcov_remote_arg { + unsigned int trace_mode; /* KCOV_TRACE_PC or KCOV_TRACE_CMP */ + unsigned int area_size; /* Length of coverage buffer in words */ + unsigned int num_handles; /* Size of handles array */ + __u64 common_handle; + __u64 handles[0]; +}; + +#define KCOV_REMOTE_MAX_HANDLES 0x100 + #define KCOV_INIT_TRACE _IOR('c', 1, unsigned long) #define KCOV_ENABLE _IO('c', 100) #define KCOV_DISABLE _IO('c', 101) +#define KCOV_REMOTE_ENABLE _IOW('c', 102, struct kcov_remote_arg) enum { /* @@ -32,4 +47,17 @@ enum { #define KCOV_CMP_SIZE(n) ((n) << 1) #define KCOV_CMP_MASK KCOV_CMP_SIZE(3) +#define KCOV_SUBSYSTEM_COMMON (0x00ull << 56) +#define KCOV_SUBSYSTEM_USB (0x01ull << 56) + +#define KCOV_SUBSYSTEM_MASK (0xffull << 56) +#define KCOV_INSTANCE_MASK (0xffffffffull) + +static inline __u64 kcov_remote_handle(__u64 subsys, __u64 inst) +{ + if (subsys & ~KCOV_SUBSYSTEM_MASK || inst & ~KCOV_INSTANCE_MASK) + return 0; + return subsys | inst; +} + #endif /* _LINUX_KCOV_IOCTLS_H */ diff --git a/kernel/kcov.c b/kernel/kcov.c index 2ee38727844a..f50354202dbe 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -21,8 +22,11 @@ #include #include #include +#include #include +#define kcov_debug(fmt, ...) pr_debug("%s: " fmt, __func__, ##__VA_ARGS__) + /* Number of 64-bit words written per one comparison: */ #define KCOV_WORDS_PER_CMP 4 @@ -44,19 +48,100 @@ struct kcov { * Reference counter. We keep one for: * - opened file descriptor * - task with enabled coverage (we can't unwire it from another task) + * - each code section for remote coverage collection */ refcount_t refcount; /* The lock protects mode, size, area and t. */ spinlock_t lock; enum kcov_mode mode; - /* Size of arena (in long's for KCOV_MODE_TRACE). */ - unsigned size; + /* Size of arena (in long's). */ + unsigned int size; /* Coverage buffer shared with user space. */ void *area; /* Task for which we collect coverage, or NULL. */ struct task_struct *t; + /* Collecting coverage from remote (background) threads. */ + bool remote; + /* Size of remote area (in long's). */ + unsigned int remote_size; + /* + * Sequence is incremented each time kcov is reenabled, used by + * kcov_remote_stop(), see the comment there. + */ + int sequence; }; +struct kcov_remote_area { + struct list_head list; + unsigned int size; +}; + +struct kcov_remote { + u64 handle; + struct kcov *kcov; + struct hlist_node hnode; +}; + +static DEFINE_SPINLOCK(kcov_remote_lock); +static DEFINE_HASHTABLE(kcov_remote_map, 4); +static struct list_head kcov_remote_areas = LIST_HEAD_INIT(kcov_remote_areas); + +/* Must be called with kcov_remote_lock locked. */ +static struct kcov_remote *kcov_remote_find(u64 handle) +{ + struct kcov_remote *remote; + + hash_for_each_possible(kcov_remote_map, remote, hnode, handle) { + if (remote->handle == handle) + return remote; + } + return NULL; +} + +static struct kcov_remote *kcov_remote_add(struct kcov *kcov, u64 handle) +{ + struct kcov_remote *remote; + + if (kcov_remote_find(handle)) + return ERR_PTR(-EEXIST); + remote = kmalloc(sizeof(*remote), GFP_ATOMIC); + if (!remote) + return ERR_PTR(-ENOMEM); + remote->handle = handle; + remote->kcov = kcov; + hash_add(kcov_remote_map, &remote->hnode, handle); + return remote; +} + +/* Must be called with kcov_remote_lock locked. */ +static struct kcov_remote_area *kcov_remote_area_get(unsigned int size) +{ + struct kcov_remote_area *area; + struct list_head *pos; + + kcov_debug("size = %u\n", size); + list_for_each(pos, &kcov_remote_areas) { + area = list_entry(pos, struct kcov_remote_area, list); + if (area->size == size) { + list_del(&area->list); + kcov_debug("rv = %px\n", area); + return area; + } + } + kcov_debug("rv = NULL\n"); + return NULL; +} + +/* Must be called with kcov_remote_lock locked. */ +static void kcov_remote_area_put(struct kcov_remote_area *area, + unsigned int size) +{ + kcov_debug("area = %px, size = %u\n", area, size); + INIT_LIST_HEAD(&area->list); + area->size = size; + list_add(&area->list, &kcov_remote_areas); +} + static notrace bool check_kcov_mode(enum kcov_mode needed_mode, struct task_struct *t) { unsigned int mode; @@ -73,7 +158,7 @@ static notrace bool check_kcov_mode(enum kcov_mode needed_mode, struct task_stru * in_interrupt() returns false (e.g. preempt_schedule_irq()). * READ_ONCE()/barrier() effectively provides load-acquire wrt * interrupts, there are paired barrier()/WRITE_ONCE() in - * kcov_ioctl_locked(). + * kcov_start(). */ barrier(); return mode == needed_mode; @@ -227,6 +312,78 @@ void notrace __sanitizer_cov_trace_switch(u64 val, u64 *cases) EXPORT_SYMBOL(__sanitizer_cov_trace_switch); #endif /* ifdef CONFIG_KCOV_ENABLE_COMPARISONS */ +static void kcov_start(struct task_struct *t, unsigned int size, + void *area, enum kcov_mode mode, int sequence) +{ + kcov_debug("t = %px, size = %u, area = %px\n", t, size, area); + /* Cache in task struct for performance. */ + t->kcov_size = size; + t->kcov_area = area; + /* See comment in check_kcov_mode(). */ + barrier(); + WRITE_ONCE(t->kcov_mode, mode); + t->kcov_sequence = sequence; +} + +static void kcov_stop(struct task_struct *t) +{ + WRITE_ONCE(t->kcov_mode, KCOV_MODE_DISABLED); + barrier(); + t->kcov_size = 0; + t->kcov_area = NULL; +} + +static void kcov_task_reset(struct task_struct *t) +{ + kcov_stop(t); + t->kcov = NULL; + t->kcov_sequence = 0; + t->kcov_handle = 0; +} + +void kcov_task_init(struct task_struct *t) +{ + kcov_task_reset(t); + t->kcov_handle = current->kcov_handle; +} + +static void kcov_reset(struct kcov *kcov) +{ + kcov->t = NULL; + kcov->mode = KCOV_MODE_INIT; + kcov->remote = false; + kcov->remote_size = 0; + kcov->sequence++; +} + +static void kcov_remote_reset(struct kcov *kcov) +{ + int bkt; + struct kcov_remote *remote; + struct hlist_node *tmp; + + spin_lock(&kcov_remote_lock); + hash_for_each_safe(kcov_remote_map, bkt, tmp, remote, hnode) { + if (remote->kcov != kcov) + continue; + kcov_debug("removing handle %llx\n", remote->handle); + hash_del(&remote->hnode); + kfree(remote); + } + /* Do reset before unlock to prevent races with kcov_remote_start(). */ + kcov_reset(kcov); + spin_unlock(&kcov_remote_lock); +} + +static void kcov_disable(struct task_struct *t, struct kcov *kcov) +{ + kcov_task_reset(t); + if (kcov->remote) + kcov_remote_reset(kcov); + else + kcov_reset(kcov); +} + static void kcov_get(struct kcov *kcov) { refcount_inc(&kcov->refcount); @@ -235,20 +392,12 @@ static void kcov_get(struct kcov *kcov) static void kcov_put(struct kcov *kcov) { if (refcount_dec_and_test(&kcov->refcount)) { + kcov_remote_reset(kcov); vfree(kcov->area); kfree(kcov); } } -void kcov_task_init(struct task_struct *t) -{ - WRITE_ONCE(t->kcov_mode, KCOV_MODE_DISABLED); - barrier(); - t->kcov_size = 0; - t->kcov_area = NULL; - t->kcov = NULL; -} - void kcov_task_exit(struct task_struct *t) { struct kcov *kcov; @@ -256,15 +405,36 @@ void kcov_task_exit(struct task_struct *t) kcov = t->kcov; if (kcov == NULL) return; + spin_lock(&kcov->lock); + kcov_debug("t = %px, kcov->t = %px\n", t, kcov->t); + /* + * For KCOV_ENABLE devices we want to make sure that t->kcov->t == t, + * which comes down to: + * WARN_ON(!kcov->remote && kcov->t != t); + * + * For KCOV_REMOTE_ENABLE devices, the exiting task is either: + * 2. A remote task between kcov_remote_start() and kcov_remote_stop(). + * In this case we should print a warning right away, since a task + * shouldn't be exiting when it's in a kcov coverage collection + * section. Here t points to the task that is collecting remote + * coverage, and t->kcov->t points to the thread that created the + * kcov device. Which means that to detect this case we need to + * check that t != t->kcov->t, and this gives us the following: + * WARN_ON(kcov->remote && kcov->t != t); + * + * 2. The task that created kcov exiting without calling KCOV_DISABLE, + * and then again we can make sure that t->kcov->t == t: + * WARN_ON(kcov->remote && kcov->t != t); + * + * By combining all three checks into one we get: + */ if (WARN_ON(kcov->t != t)) { spin_unlock(&kcov->lock); return; } /* Just to not leave dangling references behind. */ - kcov_task_init(t); - kcov->t = NULL; - kcov->mode = KCOV_MODE_INIT; + kcov_disable(t, kcov); spin_unlock(&kcov->lock); kcov_put(kcov); } @@ -313,6 +483,7 @@ static int kcov_open(struct inode *inode, struct file *filep) if (!kcov) return -ENOMEM; kcov->mode = KCOV_MODE_DISABLED; + kcov->sequence = 1; refcount_set(&kcov->refcount, 1); spin_lock_init(&kcov->lock); filep->private_data = kcov; @@ -325,6 +496,20 @@ static int kcov_close(struct inode *inode, struct file *filep) return 0; } +static int kcov_get_mode(unsigned long arg) +{ + if (arg == KCOV_TRACE_PC) + return KCOV_MODE_TRACE_PC; + else if (arg == KCOV_TRACE_CMP) +#ifdef CONFIG_KCOV_ENABLE_COMPARISONS + return KCOV_MODE_TRACE_CMP; +#else + return -ENOTSUPP; +#endif + else + return -EINVAL; +} + /* * Fault in a lazily-faulted vmalloc area before it can be used by * __santizer_cov_trace_pc(), to avoid recursion issues if any code on the @@ -340,14 +525,35 @@ static void kcov_fault_in_area(struct kcov *kcov) READ_ONCE(area[offset]); } +static inline bool kcov_check_handle(u64 handle, bool common_valid, + bool uncommon_valid, bool zero_valid) +{ + if (handle & ~(KCOV_SUBSYSTEM_MASK | KCOV_INSTANCE_MASK)) + return false; + switch (handle & KCOV_SUBSYSTEM_MASK) { + case KCOV_SUBSYSTEM_COMMON: + return (handle & KCOV_INSTANCE_MASK) ? + common_valid : zero_valid; + case KCOV_SUBSYSTEM_USB: + return uncommon_valid; + default: + return false; + } + return false; +} + static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd, unsigned long arg) { struct task_struct *t; unsigned long size, unused; + int mode, i; + struct kcov_remote_arg *remote_arg; + struct kcov_remote *remote; switch (cmd) { case KCOV_INIT_TRACE: + kcov_debug("KCOV_INIT_TRACE\n"); /* * Enable kcov in trace mode and setup buffer size. * Must happen before anything else. @@ -366,6 +572,7 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd, kcov->mode = KCOV_MODE_INIT; return 0; case KCOV_ENABLE: + kcov_debug("KCOV_ENABLE\n"); /* * Enable coverage for the current task. * At this point user must have been enabled trace mode, @@ -378,29 +585,20 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd, t = current; if (kcov->t != NULL || t->kcov != NULL) return -EBUSY; - if (arg == KCOV_TRACE_PC) - kcov->mode = KCOV_MODE_TRACE_PC; - else if (arg == KCOV_TRACE_CMP) -#ifdef CONFIG_KCOV_ENABLE_COMPARISONS - kcov->mode = KCOV_MODE_TRACE_CMP; -#else - return -ENOTSUPP; -#endif - else - return -EINVAL; + mode = kcov_get_mode(arg); + if (mode < 0) + return mode; kcov_fault_in_area(kcov); - /* Cache in task struct for performance. */ - t->kcov_size = kcov->size; - t->kcov_area = kcov->area; - /* See comment in check_kcov_mode(). */ - barrier(); - WRITE_ONCE(t->kcov_mode, kcov->mode); + kcov->mode = mode; + kcov_start(t, kcov->size, kcov->area, kcov->mode, + kcov->sequence); t->kcov = kcov; kcov->t = t; - /* This is put either in kcov_task_exit() or in KCOV_DISABLE. */ + /* Put either in kcov_task_exit() or in KCOV_DISABLE. */ kcov_get(kcov); return 0; case KCOV_DISABLE: + kcov_debug("KCOV_DISABLE\n"); /* Disable coverage for the current task. */ unused = arg; if (unused != 0 || current->kcov != kcov) @@ -408,11 +606,65 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd, t = current; if (WARN_ON(kcov->t != t)) return -EINVAL; - kcov_task_init(t); - kcov->t = NULL; - kcov->mode = KCOV_MODE_INIT; + kcov_disable(t, kcov); kcov_put(kcov); return 0; + case KCOV_REMOTE_ENABLE: + kcov_debug("KCOV_REMOTE_ENABLE\n"); + if (kcov->mode != KCOV_MODE_INIT || !kcov->area) + return -EINVAL; + t = current; + if (kcov->t != NULL || t->kcov != NULL) + return -EBUSY; + remote_arg = (struct kcov_remote_arg *)arg; + mode = kcov_get_mode(remote_arg->trace_mode); + if (mode < 0) + return mode; + if (remote_arg->area_size > LONG_MAX / sizeof(unsigned long)) + return -EINVAL; + kcov->mode = mode; + t->kcov = kcov; + kcov->t = t; + kcov->remote = true; + kcov->remote_size = remote_arg->area_size; + spin_lock(&kcov_remote_lock); + for (i = 0; i < remote_arg->num_handles; i++) { + kcov_debug("handle %llx\n", remote_arg->handles[i]); + if (!kcov_check_handle(remote_arg->handles[i], + false, true, false)) { + spin_unlock(&kcov_remote_lock); + kcov_disable(t, kcov); + return -EINVAL; + } + remote = kcov_remote_add(kcov, remote_arg->handles[i]); + if (IS_ERR(remote)) { + spin_unlock(&kcov_remote_lock); + kcov_disable(t, kcov); + return PTR_ERR(remote); + } + } + if (remote_arg->common_handle) { + kcov_debug("common handle %llx\n", + remote_arg->common_handle); + if (!kcov_check_handle(remote_arg->common_handle, + true, false, false)) { + spin_unlock(&kcov_remote_lock); + kcov_disable(t, kcov); + return -EINVAL; + } + remote = kcov_remote_add(kcov, + remote_arg->common_handle); + if (IS_ERR(remote)) { + spin_unlock(&kcov_remote_lock); + kcov_disable(t, kcov); + return PTR_ERR(remote); + } + t->kcov_handle = remote_arg->common_handle; + } + spin_unlock(&kcov_remote_lock); + /* Put either in kcov_task_exit() or in KCOV_DISABLE. */ + kcov_get(kcov); + return 0; default: return -ENOTTY; } @@ -422,11 +674,35 @@ static long kcov_ioctl(struct file *filep, unsigned int cmd, unsigned long arg) { struct kcov *kcov; int res; + struct kcov_remote_arg *remote_arg = NULL; + unsigned int remote_num_handles; + unsigned long remote_arg_size; + + if (cmd == KCOV_REMOTE_ENABLE) { + if (get_user(remote_num_handles, (unsigned __user *)(arg + + offsetof(struct kcov_remote_arg, num_handles)))) + return -EFAULT; + if (remote_num_handles > KCOV_REMOTE_MAX_HANDLES) + return -EINVAL; + remote_arg_size = struct_size(remote_arg, handles, + remote_num_handles); + remote_arg = memdup_user((void __user *)arg, remote_arg_size); + if (IS_ERR(remote_arg)) + return PTR_ERR(remote_arg); + if (remote_arg->num_handles != remote_num_handles) { + kfree(remote_arg); + return -EINVAL; + } + arg = (unsigned long)remote_arg; + } kcov = filep->private_data; spin_lock(&kcov->lock); res = kcov_ioctl_locked(kcov, cmd, arg); spin_unlock(&kcov->lock); + + kfree(remote_arg); + return res; } @@ -438,6 +714,207 @@ static const struct file_operations kcov_fops = { .release = kcov_close, }; +/* + * kcov_remote_start() and kcov_remote_stop() can be used to annotate a section + * of code in a kernel background thread to allow kcov to be used to collect + * coverage from that part of code. + * + * The handle argument of kcov_remote_start() identifies a code section that is + * used for coverage collection. A userspace process passes this handle to + * KCOV_REMOTE_ENABLE ioctl to make the used kcov device start collecting + * coverage for the code section identified by this handle. + * + * The usage of these annotations in the kernel code is different depending on + * the type of the kernel thread whose code is being annotated. + * + * For global kernel threads that are spawned in a limited number of instances + * (e.g. one USB hub_event() worker thread is spawned per USB HCD), each + * instance must be assigned a unique 4-byte instance id. The instance id is + * then combined with a 1-byte subsystem id to get a handle via + * kcov_remote_handle(subsystem_id, instance_id). + * + * For local kernel threads that are spawned from system calls handler when a + * user interacts with some kernel interface (e.g. vhost workers), a handle is + * passed from a userspace process as the common_handle field of the + * kcov_remote_arg struct (note, that the user must generate a handle by using + * kcov_remote_handle() with KCOV_SUBSYSTEM_COMMON as the subsystem id and an + * arbitrary 4-byte non-zero number as the instance id). This common handle + * then gets saved into the task_struct of the process that issued the + * KCOV_REMOTE_ENABLE ioctl. When this proccess issues system calls that spawn + * kernel threads, the common handle must be retrived via kcov_common_handle() + * and passed to the spawned threads via custom annotations. Those kernel + * threads must in turn be annotated with kcov_remote_start(common_handle) and + * kcov_remote_stop(). All of the threads that are spawned by the same process + * obtain the same handle, hence the name "common". + * + * See Documentation/dev-tools/kcov.rst for more details. + * + * Internally, this function looks up the kcov device associated with the + * provided handle, allocates an area for coverage collection, and saves the + * pointers to kcov and area into the current task_struct to allow coverage to + * be collected via __sanitizer_cov_trace_pc() + * In turns kcov_remote_stop() clears those pointers from task_struct to stop + * collecting coverage and copies all collected coverage into the kcov area. + */ +void kcov_remote_start(u64 handle) +{ + struct kcov_remote *remote; + void *area; + struct task_struct *t; + unsigned int size; + enum kcov_mode mode; + int sequence; + + if (WARN_ON(!kcov_check_handle(handle, true, true, true))) + return; + if (WARN_ON(!in_task())) + return; + t = current; + /* + * Check that kcov_remote_start is not called twice + * nor called by user tasks (with enabled kcov). + */ + if (WARN_ON(t->kcov)) + return; + + kcov_debug("handle = %llx\n", handle); + + spin_lock(&kcov_remote_lock); + remote = kcov_remote_find(handle); + if (!remote) { + kcov_debug("no remote found"); + spin_unlock(&kcov_remote_lock); + return; + } + /* Put in kcov_remote_stop(). */ + kcov_get(remote->kcov); + t->kcov = remote->kcov; + /* + * Read kcov fields before unlock to prevent races with + * KCOV_DISABLE / kcov_remote_reset(). + */ + size = remote->kcov->remote_size; + mode = remote->kcov->mode; + sequence = remote->kcov->sequence; + area = kcov_remote_area_get(size); + spin_unlock(&kcov_remote_lock); + + if (!area) { + area = vmalloc(size * sizeof(unsigned long)); + if (!area) { + t->kcov = NULL; + kcov_put(remote->kcov); + return; + } + } + /* Reset coverage size. */ + *(u64 *)area = 0; + + kcov_debug("area = %px, size = %u", area, size); + + kcov_start(t, size, area, mode, sequence); + +} +EXPORT_SYMBOL(kcov_remote_start); + +static void kcov_move_area(enum kcov_mode mode, void *dst_area, + unsigned int dst_area_size, void *src_area) +{ + u64 word_size = sizeof(unsigned long); + u64 count_size, entry_size_log; + u64 dst_len, src_len; + void *dst_entries, *src_entries; + u64 dst_occupied, dst_free, bytes_to_move, entries_moved; + + kcov_debug("%px %u <= %px %lu\n", + dst_area, dst_area_size, src_area, *(unsigned long *)src_area); + + switch (mode) { + case KCOV_MODE_TRACE_PC: + dst_len = READ_ONCE(*(unsigned long *)dst_area); + src_len = *(unsigned long *)src_area; + count_size = sizeof(unsigned long); + entry_size_log = __ilog2_u64(sizeof(unsigned long)); + break; + case KCOV_MODE_TRACE_CMP: + dst_len = READ_ONCE(*(u64 *)dst_area); + src_len = *(u64 *)src_area; + count_size = sizeof(u64); + BUILD_BUG_ON(!is_power_of_2(KCOV_WORDS_PER_CMP)); + entry_size_log = __ilog2_u64(sizeof(u64) * KCOV_WORDS_PER_CMP); + break; + default: + WARN_ON(1); + return; + } + + /* As arm can't divide u64 integers use log of entry size. */ + if (dst_len > ((dst_area_size * word_size - count_size) >> + entry_size_log)) + return; + dst_occupied = count_size + (dst_len << entry_size_log); + dst_free = dst_area_size * word_size - dst_occupied; + bytes_to_move = min(dst_free, src_len << entry_size_log); + dst_entries = dst_area + dst_occupied; + src_entries = src_area + count_size; + memcpy(dst_entries, src_entries, bytes_to_move); + entries_moved = bytes_to_move >> entry_size_log; + + switch (mode) { + case KCOV_MODE_TRACE_PC: + WRITE_ONCE(*(unsigned long *)dst_area, dst_len + entries_moved); + break; + case KCOV_MODE_TRACE_CMP: + WRITE_ONCE(*(u64 *)dst_area, dst_len + entries_moved); + break; + default: + break; + } +} + +/* See the comment before kcov_remote_start() for usage details. */ +void kcov_remote_stop(void) +{ + struct task_struct *t = current; + struct kcov *kcov = t->kcov; + void *area = t->kcov_area; + unsigned int size = t->kcov_size; + int sequence = t->kcov_sequence; + + if (!kcov) { + kcov_debug("no kcov found\n"); + return; + } + + kcov_stop(t); + t->kcov = NULL; + + spin_lock(&kcov->lock); + /* + * KCOV_DISABLE could have been called between kcov_remote_start() + * and kcov_remote_stop(), hence the check. + */ + kcov_debug("move if: %d == %d && %d\n", + sequence, kcov->sequence, (int)kcov->remote); + if (sequence == kcov->sequence && kcov->remote) + kcov_move_area(kcov->mode, kcov->area, kcov->size, area); + spin_unlock(&kcov->lock); + + spin_lock(&kcov_remote_lock); + kcov_remote_area_put(area, size); + spin_unlock(&kcov_remote_lock); + + kcov_put(kcov); +} +EXPORT_SYMBOL(kcov_remote_stop); + +/* See the comment before kcov_remote_start() for usage details. */ +u64 kcov_common_handle(void) +{ + return current->kcov_handle; +} +EXPORT_SYMBOL(kcov_common_handle); + static int __init kcov_init(void) { /* -- cgit v1.2.3 From e9eeec58c992c47b394e4f829e4f81b923b0a322 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Wed, 4 Dec 2019 17:06:06 -0800 Subject: bpf: Fix a bug when getting subprog 0 jited image in check_attach_btf_id For jited bpf program, if the subprogram count is 1, i.e., there is no callees in the program, prog->aux->func will be NULL and prog->bpf_func points to image address of the program. If there is more than one subprogram, prog->aux->func is populated, and subprogram 0 can be accessed through either prog->bpf_func or prog->aux->func[0]. Other subprograms should be accessed through prog->aux->func[subprog_id]. This patch fixed a bug in check_attach_btf_id(), where prog->aux->func[subprog_id] is used to access any subprogram which caused a segfault like below: [79162.619208] BUG: kernel NULL pointer dereference, address: 0000000000000000 ...... [79162.634255] Call Trace: [79162.634974] ? _cond_resched+0x15/0x30 [79162.635686] ? kmem_cache_alloc_trace+0x162/0x220 [79162.636398] ? selinux_bpf_prog_alloc+0x1f/0x60 [79162.637111] bpf_prog_load+0x3de/0x690 [79162.637809] __do_sys_bpf+0x105/0x1740 [79162.638488] do_syscall_64+0x5b/0x180 [79162.639147] entry_SYSCALL_64_after_hwframe+0x44/0xa9 ...... Fixes: 5b92a28aae4d ("bpf: Support attaching tracing BPF program to other BPF programs") Reported-by: Eelco Chaudron Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20191205010606.177774-1-yhs@fb.com --- kernel/bpf/verifier.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index a0482e1c4a77..034ef81f935b 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -9636,7 +9636,10 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) ret = -EINVAL; goto out; } - addr = (long) tgt_prog->aux->func[subprog]->bpf_func; + if (subprog == 0) + addr = (long) tgt_prog->bpf_func; + else + addr = (long) tgt_prog->aux->func[subprog]->bpf_func; } else { addr = kallsyms_lookup_name(tname); if (!addr) { -- cgit v1.2.3 From 1d9a6159bd04b676cb7d9b13245888fa450cec10 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Thu, 28 Nov 2019 08:47:49 +0800 Subject: workqueue: Use pr_warn instead of pr_warning Use pr_warn() instead of the remaining pr_warning() calls. Link: http://lkml.kernel.org/r/20191128004752.35268-2-wangkefeng.wang@huawei.com To: joe@perches.com To: linux-kernel@vger.kernel.org Cc: gregkh@linuxfoundation.org Cc: tj@kernel.org Cc: arnd@arndb.de Cc: sergey.senozhatsky@gmail.com Cc: rostedt@goodmis.org Signed-off-by: Kefeng Wang Acked-by: Tejun Heo Signed-off-by: Petr Mladek --- kernel/workqueue.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/workqueue.c b/kernel/workqueue.c index bc88fd939f4e..cfc923558e04 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -4374,8 +4374,8 @@ void destroy_workqueue(struct workqueue_struct *wq) for_each_pwq(pwq, wq) { spin_lock_irq(&pwq->pool->lock); if (WARN_ON(pwq_busy(pwq))) { - pr_warning("%s: %s has the following busy pwq\n", - __func__, wq->name); + pr_warn("%s: %s has the following busy pwq\n", + __func__, wq->name); show_pwq(pwq); spin_unlock_irq(&pwq->pool->lock); mutex_unlock(&wq->mutex); -- cgit v1.2.3 From ee19545220a8663f0ca58c3427bc08fd6a104a42 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Fri, 6 Dec 2019 09:25:03 +1100 Subject: Fix up for "printk: Drop pr_warning definition" Link: http://lkml.kernel.org/r/20191206092503.303d6a57@canb.auug.org.au Cc: Linux Next Mailing List Cc: Linux Kernel Mailing List Cc: "Steven Rostedt (VMware)" Cc: Kefeng Wang Cc: Linus Torvalds Signed-off-by: Stephen Rothwell Signed-off-by: Petr Mladek --- kernel/trace/ring_buffer.c | 2 +- kernel/trace/trace.c | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 4bf050fcfe3b..3f655371eaf6 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -5070,7 +5070,7 @@ static __init int test_ringbuffer(void) int ret = 0; if (security_locked_down(LOCKDOWN_TRACEFS)) { - pr_warning("Lockdown is enabled, skipping ring buffer tests\n"); + pr_warn("Lockdown is enabled, skipping ring buffer tests\n"); return 0; } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 23459d53d576..6c75410f9698 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1889,7 +1889,7 @@ int __init register_tracer(struct tracer *type) } if (security_locked_down(LOCKDOWN_TRACEFS)) { - pr_warning("Can not register tracer %s due to lockdown\n", + pr_warn("Can not register tracer %s due to lockdown\n", type->name); return -EPERM; } @@ -8796,7 +8796,7 @@ struct dentry *tracing_init_dentry(void) struct trace_array *tr = &global_trace; if (security_locked_down(LOCKDOWN_TRACEFS)) { - pr_warning("Tracing disabled due to lockdown\n"); + pr_warn("Tracing disabled due to lockdown\n"); return ERR_PTR(-EPERM); } @@ -9244,7 +9244,7 @@ __init static int tracer_alloc_buffers(void) if (security_locked_down(LOCKDOWN_TRACEFS)) { - pr_warning("Tracing disabled due to lockdown\n"); + pr_warn("Tracing disabled due to lockdown\n"); return -EPERM; } -- cgit v1.2.3 From c593642c8be046915ca3a4a300243a68077cd207 Mon Sep 17 00:00:00 2001 From: Pankaj Bharadiya Date: Mon, 9 Dec 2019 10:31:43 -0800 Subject: treewide: Use sizeof_field() macro Replace all the occurrences of FIELD_SIZEOF() with sizeof_field() except at places where these are defined. Later patches will remove the unused definition of FIELD_SIZEOF(). This patch is generated using following script: EXCLUDE_FILES="include/linux/stddef.h|include/linux/kernel.h" git grep -l -e "\bFIELD_SIZEOF\b" | while read file; do if [[ "$file" =~ $EXCLUDE_FILES ]]; then continue fi sed -i -e 's/\bFIELD_SIZEOF\b/sizeof_field/g' $file; done Signed-off-by: Pankaj Bharadiya Link: https://lore.kernel.org/r/20190924105839.110713-3-pankaj.laxminarayan.bharadiya@intel.com Co-developed-by: Kees Cook Signed-off-by: Kees Cook Acked-by: David Miller # for net --- Documentation/process/coding-style.rst | 2 +- .../translations/it_IT/process/coding-style.rst | 2 +- .../translations/zh_CN/process/coding-style.rst | 2 +- arch/arc/kernel/unwind.c | 6 +- arch/powerpc/net/bpf_jit32.h | 4 +- arch/powerpc/net/bpf_jit_comp.c | 16 +-- arch/sparc/net/bpf_jit_comp_32.c | 8 +- arch/x86/kernel/fpu/xstate.c | 2 +- block/blk-core.c | 4 +- crypto/adiantum.c | 4 +- crypto/essiv.c | 2 +- drivers/firmware/efi/efi.c | 2 +- drivers/infiniband/hw/efa/efa_verbs.c | 2 +- drivers/infiniband/hw/hfi1/sdma.c | 2 +- drivers/infiniband/hw/hfi1/verbs.h | 4 +- drivers/infiniband/ulp/opa_vnic/opa_vnic_ethtool.c | 2 +- drivers/md/raid5-ppl.c | 2 +- drivers/media/platform/omap3isp/isppreview.c | 24 ++-- drivers/media/v4l2-core/v4l2-ioctl.c | 2 +- drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c | 4 +- .../net/ethernet/cavium/liquidio/octeon_console.c | 16 +-- drivers/net/ethernet/emulex/benet/be_ethtool.c | 2 +- .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 2 +- .../net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c | 2 +- drivers/net/ethernet/huawei/hinic/hinic_ethtool.c | 8 +- drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c | 2 +- drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 2 +- drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c | 2 +- drivers/net/ethernet/intel/iavf/iavf_ethtool.c | 2 +- drivers/net/ethernet/intel/ice/ice_ethtool.c | 10 +- drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h | 2 +- drivers/net/ethernet/intel/igb/igb_ethtool.c | 4 +- drivers/net/ethernet/intel/igc/igc_ethtool.c | 4 +- drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c | 4 +- drivers/net/ethernet/intel/ixgbevf/ethtool.c | 4 +- drivers/net/ethernet/marvell/mv643xx_eth.c | 4 +- drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 2 +- .../net/ethernet/mellanox/mlx5/core/fpga/ipsec.c | 6 +- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 4 +- drivers/net/ethernet/netronome/nfp/bpf/jit.c | 10 +- drivers/net/ethernet/netronome/nfp/bpf/main.c | 2 +- drivers/net/ethernet/netronome/nfp/bpf/offload.c | 2 +- drivers/net/ethernet/netronome/nfp/flower/main.h | 2 +- .../ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c | 2 +- drivers/net/ethernet/qlogic/qede/qede.h | 2 +- .../net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c | 2 +- drivers/net/ethernet/realtek/r8169_firmware.c | 2 +- drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c | 2 +- .../net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 4 +- drivers/net/ethernet/ti/cpsw_ethtool.c | 6 +- drivers/net/ethernet/ti/netcp_ethss.c | 32 ++--- drivers/net/fjes/fjes_ethtool.c | 2 +- drivers/net/geneve.c | 2 +- drivers/net/hyperv/netvsc_drv.c | 2 +- drivers/net/usb/sierra_net.c | 2 +- drivers/net/usb/usbnet.c | 2 +- drivers/net/vxlan.c | 4 +- drivers/net/wireless/marvell/libertas/debugfs.c | 2 +- drivers/net/wireless/marvell/mwifiex/util.h | 4 +- drivers/s390/net/qeth_core_main.c | 2 +- drivers/s390/net/qeth_core_mpc.h | 10 +- drivers/scsi/aacraid/aachba.c | 4 +- drivers/scsi/be2iscsi/be_cmds.h | 2 +- drivers/scsi/cxgbi/libcxgbi.c | 2 +- drivers/scsi/smartpqi/smartpqi_init.c | 6 +- drivers/staging/qlge/qlge_ethtool.c | 2 +- drivers/staging/wfx/data_tx.c | 2 +- drivers/target/iscsi/cxgbit/cxgbit_main.c | 2 +- drivers/usb/atm/usbatm.c | 2 +- drivers/usb/gadget/function/f_fs.c | 2 +- fs/crypto/keyring.c | 2 +- fs/verity/enable.c | 2 +- include/linux/filter.h | 12 +- include/linux/kvm_host.h | 2 +- include/linux/phy_led_triggers.h | 2 +- include/net/garp.h | 2 +- include/net/ip_tunnels.h | 6 +- include/net/mrp.h | 2 +- include/net/netfilter/nf_conntrack_helper.h | 2 +- include/net/netfilter/nf_tables_core.h | 2 +- include/net/sock.h | 2 +- ipc/util.c | 2 +- kernel/bpf/cgroup.c | 2 +- kernel/bpf/local_storage.c | 4 +- net/802/mrp.c | 6 +- net/batman-adv/main.c | 2 +- net/bpf/test_run.c | 8 +- net/bridge/br.c | 2 +- net/core/dev.c | 2 +- net/core/filter.c | 140 ++++++++++----------- net/core/flow_dissector.c | 10 +- net/core/xdp.c | 4 +- net/dccp/proto.c | 2 +- net/ipv4/ip_gre.c | 4 +- net/ipv4/ip_vti.c | 4 +- net/ipv4/tcp.c | 2 +- net/ipv6/ip6_gre.c | 4 +- net/iucv/af_iucv.c | 2 +- net/netfilter/nf_tables_api.c | 4 +- net/netfilter/nfnetlink_cthelper.c | 2 +- net/netfilter/nft_ct.c | 12 +- net/netfilter/nft_masq.c | 2 +- net/netfilter/nft_nat.c | 6 +- net/netfilter/nft_redir.c | 2 +- net/netfilter/nft_tproxy.c | 4 +- net/netfilter/xt_RATEEST.c | 2 +- net/netlink/af_netlink.c | 2 +- net/openvswitch/datapath.c | 2 +- net/openvswitch/flow.h | 4 +- net/rxrpc/af_rxrpc.c | 2 +- net/sched/act_ct.c | 4 +- net/sched/cls_flower.c | 2 +- net/unix/af_unix.c | 2 +- security/integrity/ima/ima_policy.c | 4 +- sound/soc/codecs/hdmi-codec.c | 2 +- 115 files changed, 298 insertions(+), 298 deletions(-) (limited to 'kernel') diff --git a/Documentation/process/coding-style.rst b/Documentation/process/coding-style.rst index ada573b7d703..edb296c52f61 100644 --- a/Documentation/process/coding-style.rst +++ b/Documentation/process/coding-style.rst @@ -988,7 +988,7 @@ Similarly, if you need to calculate the size of some structure member, use .. code-block:: c - #define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f)) + #define sizeof_field(t, f) (sizeof(((t*)0)->f)) There are also min() and max() macros that do strict type checking if you need them. Feel free to peruse that header file to see what else is already diff --git a/Documentation/translations/it_IT/process/coding-style.rst b/Documentation/translations/it_IT/process/coding-style.rst index 8995d2d19f20..8725f2b9e960 100644 --- a/Documentation/translations/it_IT/process/coding-style.rst +++ b/Documentation/translations/it_IT/process/coding-style.rst @@ -1005,7 +1005,7 @@ struttura, usate .. code-block:: c - #define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f)) + #define sizeof_field(t, f) (sizeof(((t*)0)->f)) Ci sono anche le macro min() e max() che, se vi serve, effettuano un controllo rigido sui tipi. Sentitevi liberi di leggere attentamente questo file diff --git a/Documentation/translations/zh_CN/process/coding-style.rst b/Documentation/translations/zh_CN/process/coding-style.rst index 4f6237392e65..eae10bc7f86f 100644 --- a/Documentation/translations/zh_CN/process/coding-style.rst +++ b/Documentation/translations/zh_CN/process/coding-style.rst @@ -826,7 +826,7 @@ inline gcc 也可以自动使其内联。而且其他用户可能会要求移除 .. code-block:: c - #define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f)) + #define sizeof_field(t, f) (sizeof(((t*)0)->f)) 还有可以做严格的类型检查的 min() 和 max() 宏，如果你需要可以使用它们。你可以 自己看看那个头文件里还定义了什么你可以拿来用的东西，如果有定义的话，你就不应 diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c index dc05a63516f5..27ea64b1fa33 100644 --- a/arch/arc/kernel/unwind.c +++ b/arch/arc/kernel/unwind.c @@ -42,10 +42,10 @@ do { \ #define EXTRA_INFO(f) { \ BUILD_BUG_ON_ZERO(offsetof(struct unwind_frame_info, f) \ - % FIELD_SIZEOF(struct unwind_frame_info, f)) \ + % sizeof_field(struct unwind_frame_info, f)) \ + offsetof(struct unwind_frame_info, f) \ - / FIELD_SIZEOF(struct unwind_frame_info, f), \ - FIELD_SIZEOF(struct unwind_frame_info, f) \ + / sizeof_field(struct unwind_frame_info, f), \ + sizeof_field(struct unwind_frame_info, f) \ } #define PTREGS_INFO(f) EXTRA_INFO(regs.f) diff --git a/arch/powerpc/net/bpf_jit32.h b/arch/powerpc/net/bpf_jit32.h index 6e5a2a4faeab..4ec2a9f14f84 100644 --- a/arch/powerpc/net/bpf_jit32.h +++ b/arch/powerpc/net/bpf_jit32.h @@ -97,12 +97,12 @@ DECLARE_LOAD_FUNC(sk_load_byte_msh); #ifdef CONFIG_SMP #ifdef CONFIG_PPC64 #define PPC_BPF_LOAD_CPU(r) \ - do { BUILD_BUG_ON(FIELD_SIZEOF(struct paca_struct, paca_index) != 2); \ + do { BUILD_BUG_ON(sizeof_field(struct paca_struct, paca_index) != 2); \ PPC_LHZ_OFFS(r, 13, offsetof(struct paca_struct, paca_index)); \ } while (0) #else #define PPC_BPF_LOAD_CPU(r) \ - do { BUILD_BUG_ON(FIELD_SIZEOF(struct task_struct, cpu) != 4); \ + do { BUILD_BUG_ON(sizeof_field(struct task_struct, cpu) != 4); \ PPC_LHZ_OFFS(r, 2, offsetof(struct task_struct, cpu)); \ } while(0) #endif diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index d57b46e0dd60..0acc9d5fb19e 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -321,7 +321,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, ctx->seen |= SEEN_XREG | SEEN_MEM | (1<<(K & 0xf)); break; case BPF_LD | BPF_W | BPF_LEN: /* A = skb->len; */ - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4); + BUILD_BUG_ON(sizeof_field(struct sk_buff, len) != 4); PPC_LWZ_OFFS(r_A, r_skb, offsetof(struct sk_buff, len)); break; case BPF_LDX | BPF_W | BPF_ABS: /* A = *((u32 *)(seccomp_data + K)); */ @@ -333,16 +333,16 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, /*** Ancillary info loads ***/ case BPF_ANC | SKF_AD_PROTOCOL: /* A = ntohs(skb->protocol); */ - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, + BUILD_BUG_ON(sizeof_field(struct sk_buff, protocol) != 2); PPC_NTOHS_OFFS(r_A, r_skb, offsetof(struct sk_buff, protocol)); break; case BPF_ANC | SKF_AD_IFINDEX: case BPF_ANC | SKF_AD_HATYPE: - BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, + BUILD_BUG_ON(sizeof_field(struct net_device, ifindex) != 4); - BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, + BUILD_BUG_ON(sizeof_field(struct net_device, type) != 2); PPC_LL_OFFS(r_scratch1, r_skb, offsetof(struct sk_buff, dev)); @@ -365,17 +365,17 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, break; case BPF_ANC | SKF_AD_MARK: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4); + BUILD_BUG_ON(sizeof_field(struct sk_buff, mark) != 4); PPC_LWZ_OFFS(r_A, r_skb, offsetof(struct sk_buff, mark)); break; case BPF_ANC | SKF_AD_RXHASH: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4); + BUILD_BUG_ON(sizeof_field(struct sk_buff, hash) != 4); PPC_LWZ_OFFS(r_A, r_skb, offsetof(struct sk_buff, hash)); break; case BPF_ANC | SKF_AD_VLAN_TAG: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2); + BUILD_BUG_ON(sizeof_field(struct sk_buff, vlan_tci) != 2); PPC_LHZ_OFFS(r_A, r_skb, offsetof(struct sk_buff, vlan_tci)); @@ -388,7 +388,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, PPC_ANDI(r_A, r_A, 1); break; case BPF_ANC | SKF_AD_QUEUE: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, + BUILD_BUG_ON(sizeof_field(struct sk_buff, queue_mapping) != 2); PPC_LHZ_OFFS(r_A, r_skb, offsetof(struct sk_buff, queue_mapping)); diff --git a/arch/sparc/net/bpf_jit_comp_32.c b/arch/sparc/net/bpf_jit_comp_32.c index 84cc8f7f83e9..c8eabb973b86 100644 --- a/arch/sparc/net/bpf_jit_comp_32.c +++ b/arch/sparc/net/bpf_jit_comp_32.c @@ -180,19 +180,19 @@ do { \ #define emit_loadptr(BASE, STRUCT, FIELD, DEST) \ do { unsigned int _off = offsetof(STRUCT, FIELD); \ - BUILD_BUG_ON(FIELD_SIZEOF(STRUCT, FIELD) != sizeof(void *)); \ + BUILD_BUG_ON(sizeof_field(STRUCT, FIELD) != sizeof(void *)); \ *prog++ = LDPTRI | RS1(BASE) | S13(_off) | RD(DEST); \ } while (0) #define emit_load32(BASE, STRUCT, FIELD, DEST) \ do { unsigned int _off = offsetof(STRUCT, FIELD); \ - BUILD_BUG_ON(FIELD_SIZEOF(STRUCT, FIELD) != sizeof(u32)); \ + BUILD_BUG_ON(sizeof_field(STRUCT, FIELD) != sizeof(u32)); \ *prog++ = LD32I | RS1(BASE) | S13(_off) | RD(DEST); \ } while (0) #define emit_load16(BASE, STRUCT, FIELD, DEST) \ do { unsigned int _off = offsetof(STRUCT, FIELD); \ - BUILD_BUG_ON(FIELD_SIZEOF(STRUCT, FIELD) != sizeof(u16)); \ + BUILD_BUG_ON(sizeof_field(STRUCT, FIELD) != sizeof(u16)); \ *prog++ = LD16I | RS1(BASE) | S13(_off) | RD(DEST); \ } while (0) @@ -202,7 +202,7 @@ do { unsigned int _off = offsetof(STRUCT, FIELD); \ } while (0) #define emit_load8(BASE, STRUCT, FIELD, DEST) \ -do { BUILD_BUG_ON(FIELD_SIZEOF(STRUCT, FIELD) != sizeof(u8)); \ +do { BUILD_BUG_ON(sizeof_field(STRUCT, FIELD) != sizeof(u8)); \ __emit_load8(BASE, STRUCT, FIELD, DEST); \ } while (0) diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 319be936c348..fa31470bbf24 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -259,7 +259,7 @@ static void __init setup_xstate_features(void) xmm_space); xstate_offsets[XFEATURE_SSE] = xstate_sizes[XFEATURE_FP]; - xstate_sizes[XFEATURE_SSE] = FIELD_SIZEOF(struct fxregs_state, + xstate_sizes[XFEATURE_SSE] = sizeof_field(struct fxregs_state, xmm_space); for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) { diff --git a/block/blk-core.c b/block/blk-core.c index a1e228752083..e4b27f7e9f51 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1792,9 +1792,9 @@ int __init blk_dev_init(void) { BUILD_BUG_ON(REQ_OP_LAST >= (1 << REQ_OP_BITS)); BUILD_BUG_ON(REQ_OP_BITS + REQ_FLAG_BITS > 8 * - FIELD_SIZEOF(struct request, cmd_flags)); + sizeof_field(struct request, cmd_flags)); BUILD_BUG_ON(REQ_OP_BITS + REQ_FLAG_BITS > 8 * - FIELD_SIZEOF(struct bio, bi_opf)); + sizeof_field(struct bio, bi_opf)); /* used for unplugging and affects IO latency/throughput - HIGHPRI */ kblockd_workqueue = alloc_workqueue("kblockd", diff --git a/crypto/adiantum.c b/crypto/adiantum.c index aded26092268..9dc53cf9b1f1 100644 --- a/crypto/adiantum.c +++ b/crypto/adiantum.c @@ -436,10 +436,10 @@ static int adiantum_init_tfm(struct crypto_skcipher *tfm) BUILD_BUG_ON(offsetofend(struct adiantum_request_ctx, u) != sizeof(struct adiantum_request_ctx)); - subreq_size = max(FIELD_SIZEOF(struct adiantum_request_ctx, + subreq_size = max(sizeof_field(struct adiantum_request_ctx, u.hash_desc) + crypto_shash_descsize(hash), - FIELD_SIZEOF(struct adiantum_request_ctx, + sizeof_field(struct adiantum_request_ctx, u.streamcipher_req) + crypto_skcipher_reqsize(streamcipher)); diff --git a/crypto/essiv.c b/crypto/essiv.c index 808f2b362106..495a2d1e1460 100644 --- a/crypto/essiv.c +++ b/crypto/essiv.c @@ -347,7 +347,7 @@ static int essiv_aead_init_tfm(struct crypto_aead *tfm) if (IS_ERR(aead)) return PTR_ERR(aead); - subreq_size = FIELD_SIZEOF(struct essiv_aead_request_ctx, aead_req) + + subreq_size = sizeof_field(struct essiv_aead_request_ctx, aead_req) + crypto_aead_reqsize(aead); tctx->ivoffset = offsetof(struct essiv_aead_request_ctx, aead_req) + diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index d101f072c8f8..407816da9fcb 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -681,7 +681,7 @@ device_initcall(efi_load_efivars); { name }, \ { prop }, \ offsetof(struct efi_fdt_params, field), \ - FIELD_SIZEOF(struct efi_fdt_params, field) \ + sizeof_field(struct efi_fdt_params, field) \ } struct params { diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c index c9d294caa27a..50c22575aed6 100644 --- a/drivers/infiniband/hw/efa/efa_verbs.c +++ b/drivers/infiniband/hw/efa/efa_verbs.c @@ -145,7 +145,7 @@ static inline bool is_rdma_read_cap(struct efa_dev *dev) } #define field_avail(x, fld, sz) (offsetof(typeof(x), fld) + \ - FIELD_SIZEOF(typeof(x), fld) <= (sz)) + sizeof_field(typeof(x), fld) <= (sz)) #define is_reserved_cleared(reserved) \ !memchr_inv(reserved, 0, sizeof(reserved)) diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c index 5774dfc22e18..a51525647ac8 100644 --- a/drivers/infiniband/hw/hfi1/sdma.c +++ b/drivers/infiniband/hw/hfi1/sdma.c @@ -848,7 +848,7 @@ static const struct rhashtable_params sdma_rht_params = { .nelem_hint = NR_CPUS_HINT, .head_offset = offsetof(struct sdma_rht_node, node), .key_offset = offsetof(struct sdma_rht_node, cpu_id), - .key_len = FIELD_SIZEOF(struct sdma_rht_node, cpu_id), + .key_len = sizeof_field(struct sdma_rht_node, cpu_id), .max_size = NR_CPUS, .min_size = 8, .automatic_shrinking = true, diff --git a/drivers/infiniband/hw/hfi1/verbs.h b/drivers/infiniband/hw/hfi1/verbs.h index b0e9bf7cd150..d36e3e14896d 100644 --- a/drivers/infiniband/hw/hfi1/verbs.h +++ b/drivers/infiniband/hw/hfi1/verbs.h @@ -107,9 +107,9 @@ enum { HFI1_HAS_GRH = (1 << 0), }; -#define LRH_16B_BYTES (FIELD_SIZEOF(struct hfi1_16b_header, lrh)) +#define LRH_16B_BYTES (sizeof_field(struct hfi1_16b_header, lrh)) #define LRH_16B_DWORDS (LRH_16B_BYTES / sizeof(u32)) -#define LRH_9B_BYTES (FIELD_SIZEOF(struct ib_header, lrh)) +#define LRH_9B_BYTES (sizeof_field(struct ib_header, lrh)) #define LRH_9B_DWORDS (LRH_9B_BYTES / sizeof(u32)) /* 24Bits for qpn, upper 8Bits reserved */ diff --git a/drivers/infiniband/ulp/opa_vnic/opa_vnic_ethtool.c b/drivers/infiniband/ulp/opa_vnic/opa_vnic_ethtool.c index 62390e9e0023..8ad7da989a0e 100644 --- a/drivers/infiniband/ulp/opa_vnic/opa_vnic_ethtool.c +++ b/drivers/infiniband/ulp/opa_vnic/opa_vnic_ethtool.c @@ -63,7 +63,7 @@ struct vnic_stats { }; }; -#define VNIC_STAT(m) { FIELD_SIZEOF(struct opa_vnic_stats, m), \ +#define VNIC_STAT(m) { sizeof_field(struct opa_vnic_stats, m), \ offsetof(struct opa_vnic_stats, m) } static struct vnic_stats vnic_gstrings_stats[] = { diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c index cab5b1352892..d50238d0a85d 100644 --- a/drivers/md/raid5-ppl.c +++ b/drivers/md/raid5-ppl.c @@ -1360,7 +1360,7 @@ int ppl_init_log(struct r5conf *conf) return -EINVAL; } - max_disks = FIELD_SIZEOF(struct ppl_log, disk_flush_bitmap) * + max_disks = sizeof_field(struct ppl_log, disk_flush_bitmap) * BITS_PER_BYTE; if (conf->raid_disks > max_disks) { pr_warn("md/raid:%s PPL doesn't support over %d disks in the array\n", diff --git a/drivers/media/platform/omap3isp/isppreview.c b/drivers/media/platform/omap3isp/isppreview.c index 97d660606d98..4dbdf3180d10 100644 --- a/drivers/media/platform/omap3isp/isppreview.c +++ b/drivers/media/platform/omap3isp/isppreview.c @@ -753,7 +753,7 @@ static const struct preview_update update_attrs[] = { preview_config_luma_enhancement, preview_enable_luma_enhancement, offsetof(struct prev_params, luma), - FIELD_SIZEOF(struct prev_params, luma), + sizeof_field(struct prev_params, luma), offsetof(struct omap3isp_prev_update_config, luma), }, /* OMAP3ISP_PREV_INVALAW */ { NULL, @@ -762,55 +762,55 @@ static const struct preview_update update_attrs[] = { preview_config_hmed, preview_enable_hmed, offsetof(struct prev_params, hmed), - FIELD_SIZEOF(struct prev_params, hmed), + sizeof_field(struct prev_params, hmed), offsetof(struct omap3isp_prev_update_config, hmed), }, /* OMAP3ISP_PREV_CFA */ { preview_config_cfa, NULL, offsetof(struct prev_params, cfa), - FIELD_SIZEOF(struct prev_params, cfa), + sizeof_field(struct prev_params, cfa), offsetof(struct omap3isp_prev_update_config, cfa), }, /* OMAP3ISP_PREV_CHROMA_SUPP */ { preview_config_chroma_suppression, preview_enable_chroma_suppression, offsetof(struct prev_params, csup), - FIELD_SIZEOF(struct prev_params, csup), + sizeof_field(struct prev_params, csup), offsetof(struct omap3isp_prev_update_config, csup), }, /* OMAP3ISP_PREV_WB */ { preview_config_whitebalance, NULL, offsetof(struct prev_params, wbal), - FIELD_SIZEOF(struct prev_params, wbal), + sizeof_field(struct prev_params, wbal), offsetof(struct omap3isp_prev_update_config, wbal), }, /* OMAP3ISP_PREV_BLKADJ */ { preview_config_blkadj, NULL, offsetof(struct prev_params, blkadj), - FIELD_SIZEOF(struct prev_params, blkadj), + sizeof_field(struct prev_params, blkadj), offsetof(struct omap3isp_prev_update_config, blkadj), }, /* OMAP3ISP_PREV_RGB2RGB */ { preview_config_rgb_blending, NULL, offsetof(struct prev_params, rgb2rgb), - FIELD_SIZEOF(struct prev_params, rgb2rgb), + sizeof_field(struct prev_params, rgb2rgb), offsetof(struct omap3isp_prev_update_config, rgb2rgb), }, /* OMAP3ISP_PREV_COLOR_CONV */ { preview_config_csc, NULL, offsetof(struct prev_params, csc), - FIELD_SIZEOF(struct prev_params, csc), + sizeof_field(struct prev_params, csc), offsetof(struct omap3isp_prev_update_config, csc), }, /* OMAP3ISP_PREV_YC_LIMIT */ { preview_config_yc_range, NULL, offsetof(struct prev_params, yclimit), - FIELD_SIZEOF(struct prev_params, yclimit), + sizeof_field(struct prev_params, yclimit), offsetof(struct omap3isp_prev_update_config, yclimit), }, /* OMAP3ISP_PREV_DEFECT_COR */ { preview_config_dcor, preview_enable_dcor, offsetof(struct prev_params, dcor), - FIELD_SIZEOF(struct prev_params, dcor), + sizeof_field(struct prev_params, dcor), offsetof(struct omap3isp_prev_update_config, dcor), }, /* Previously OMAP3ISP_PREV_GAMMABYPASS, not used anymore */ { NULL, @@ -828,13 +828,13 @@ static const struct preview_update update_attrs[] = { preview_config_noisefilter, preview_enable_noisefilter, offsetof(struct prev_params, nf), - FIELD_SIZEOF(struct prev_params, nf), + sizeof_field(struct prev_params, nf), offsetof(struct omap3isp_prev_update_config, nf), }, /* OMAP3ISP_PREV_GAMMA */ { preview_config_gammacorrn, preview_enable_gammacorrn, offsetof(struct prev_params, gamma), - FIELD_SIZEOF(struct prev_params, gamma), + sizeof_field(struct prev_params, gamma), offsetof(struct omap3isp_prev_update_config, gamma), }, /* OMAP3ISP_PREV_CONTRAST */ { preview_config_contrast, diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 4e700583659b..003b7422aeef 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -2652,7 +2652,7 @@ struct v4l2_ioctl_info { /* Zero struct from after the field to the end */ #define INFO_FL_CLEAR(v4l2_struct, field) \ ((offsetof(struct v4l2_struct, field) + \ - FIELD_SIZEOF(struct v4l2_struct, field)) << 16) + sizeof_field(struct v4l2_struct, field)) << 16) #define INFO_FL_CLEAR_MASK (_IOC_SIZEMASK << 16) #define DEFINE_V4L_STUB_FUNC(_vidioc) \ diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c index a880f10e3e70..8083173f1a8f 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c @@ -129,13 +129,13 @@ struct xgbe_stats { #define XGMAC_MMC_STAT(_string, _var) \ { _string, \ - FIELD_SIZEOF(struct xgbe_mmc_stats, _var), \ + sizeof_field(struct xgbe_mmc_stats, _var), \ offsetof(struct xgbe_prv_data, mmc_stats._var), \ } #define XGMAC_EXT_STAT(_string, _var) \ { _string, \ - FIELD_SIZEOF(struct xgbe_ext_stats, _var), \ + sizeof_field(struct xgbe_ext_stats, _var), \ offsetof(struct xgbe_prv_data, ext_stats._var), \ } diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_console.c b/drivers/net/ethernet/cavium/liquidio/octeon_console.c index 0cc2338d8d2a..dfc77507b159 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_console.c +++ b/drivers/net/ethernet/cavium/liquidio/octeon_console.c @@ -205,11 +205,11 @@ static int __cvmx_bootmem_check_version(struct octeon_device *oct, major_version = (u32)__cvmx_bootmem_desc_get( oct, oct->bootmem_desc_addr, offsetof(struct cvmx_bootmem_desc, major_version), - FIELD_SIZEOF(struct cvmx_bootmem_desc, major_version)); + sizeof_field(struct cvmx_bootmem_desc, major_version)); minor_version = (u32)__cvmx_bootmem_desc_get( oct, oct->bootmem_desc_addr, offsetof(struct cvmx_bootmem_desc, minor_version), - FIELD_SIZEOF(struct cvmx_bootmem_desc, minor_version)); + sizeof_field(struct cvmx_bootmem_desc, minor_version)); dev_dbg(&oct->pci_dev->dev, "%s: major_version=%d\n", __func__, major_version); @@ -237,13 +237,13 @@ static const struct cvmx_bootmem_named_block_desc oct, named_addr, offsetof(struct cvmx_bootmem_named_block_desc, base_addr), - FIELD_SIZEOF( + sizeof_field( struct cvmx_bootmem_named_block_desc, base_addr)); desc->size = __cvmx_bootmem_desc_get(oct, named_addr, offsetof(struct cvmx_bootmem_named_block_desc, size), - FIELD_SIZEOF( + sizeof_field( struct cvmx_bootmem_named_block_desc, size)); @@ -268,20 +268,20 @@ static u64 cvmx_bootmem_phy_named_block_find(struct octeon_device *oct, oct, oct->bootmem_desc_addr, offsetof(struct cvmx_bootmem_desc, named_block_array_addr), - FIELD_SIZEOF(struct cvmx_bootmem_desc, + sizeof_field(struct cvmx_bootmem_desc, named_block_array_addr)); u32 num_blocks = (u32)__cvmx_bootmem_desc_get( oct, oct->bootmem_desc_addr, offsetof(struct cvmx_bootmem_desc, nb_num_blocks), - FIELD_SIZEOF(struct cvmx_bootmem_desc, + sizeof_field(struct cvmx_bootmem_desc, nb_num_blocks)); u32 name_length = (u32)__cvmx_bootmem_desc_get( oct, oct->bootmem_desc_addr, offsetof(struct cvmx_bootmem_desc, named_block_name_len), - FIELD_SIZEOF(struct cvmx_bootmem_desc, + sizeof_field(struct cvmx_bootmem_desc, named_block_name_len)); u64 named_addr = named_block_array_addr; @@ -292,7 +292,7 @@ static u64 cvmx_bootmem_phy_named_block_find(struct octeon_device *oct, offsetof( struct cvmx_bootmem_named_block_desc, size), - FIELD_SIZEOF( + sizeof_field( struct cvmx_bootmem_named_block_desc, size)); diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c index 5bb5abf99588..022a54a1805b 100644 --- a/drivers/net/ethernet/emulex/benet/be_ethtool.c +++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c @@ -23,7 +23,7 @@ struct be_ethtool_stat { }; enum {DRVSTAT_TX, DRVSTAT_RX, DRVSTAT}; -#define FIELDINFO(_struct, field) FIELD_SIZEOF(_struct, field), \ +#define FIELDINFO(_struct, field) sizeof_field(_struct, field), \ offsetof(_struct, field) #define DRVSTAT_TX_INFO(field) #field, DRVSTAT_TX,\ FIELDINFO(struct be_tx_stats, field) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index d862e9ba27e1..13dbd249f35f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -10240,7 +10240,7 @@ static int hclge_get_dfx_reg_len(struct hclge_dev *hdev, int *len) return ret; } - data_len_per_desc = FIELD_SIZEOF(struct hclge_desc, data); + data_len_per_desc = sizeof_field(struct hclge_desc, data); *len = 0; for (i = 0; i < dfx_reg_type_num; i++) { bd_num = bd_num_list[i]; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index fbc39a2480d0..180224eab1ca 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -614,7 +614,7 @@ static void hclge_tm_vport_tc_info_update(struct hclge_vport *vport) } memcpy(kinfo->prio_tc, hdev->tm_info.prio_tc, - FIELD_SIZEOF(struct hnae3_knic_private_info, prio_tc)); + sizeof_field(struct hnae3_knic_private_info, prio_tc)); } static void hclge_tm_vport_info_update(struct hclge_dev *hdev) diff --git a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c index 60ec48fe4144..966aea949c0b 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c @@ -450,7 +450,7 @@ static u32 hinic_get_rxfh_indir_size(struct net_device *netdev) #define HINIC_FUNC_STAT(_stat_item) { \ .name = #_stat_item, \ - .size = FIELD_SIZEOF(struct hinic_vport_stats, _stat_item), \ + .size = sizeof_field(struct hinic_vport_stats, _stat_item), \ .offset = offsetof(struct hinic_vport_stats, _stat_item) \ } @@ -477,7 +477,7 @@ static struct hinic_stats hinic_function_stats[] = { #define HINIC_PORT_STAT(_stat_item) { \ .name = #_stat_item, \ - .size = FIELD_SIZEOF(struct hinic_phy_port_stats, _stat_item), \ + .size = sizeof_field(struct hinic_phy_port_stats, _stat_item), \ .offset = offsetof(struct hinic_phy_port_stats, _stat_item) \ } @@ -571,7 +571,7 @@ static struct hinic_stats hinic_port_stats[] = { #define HINIC_TXQ_STAT(_stat_item) { \ .name = "txq%d_"#_stat_item, \ - .size = FIELD_SIZEOF(struct hinic_txq_stats, _stat_item), \ + .size = sizeof_field(struct hinic_txq_stats, _stat_item), \ .offset = offsetof(struct hinic_txq_stats, _stat_item) \ } @@ -586,7 +586,7 @@ static struct hinic_stats hinic_tx_queue_stats[] = { #define HINIC_RXQ_STAT(_stat_item) { \ .name = "rxq%d_"#_stat_item, \ - .size = FIELD_SIZEOF(struct hinic_rxq_stats, _stat_item), \ + .size = sizeof_field(struct hinic_rxq_stats, _stat_item), \ .offset = offsetof(struct hinic_rxq_stats, _stat_item) \ } diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c index c681d2d28107..68edf55ac906 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c @@ -18,7 +18,7 @@ struct fm10k_stats { #define FM10K_STAT_FIELDS(_type, _name, _stat) { \ .stat_string = _name, \ - .sizeof_stat = FIELD_SIZEOF(_type, _stat), \ + .sizeof_stat = sizeof_field(_type, _stat), \ .stat_offset = offsetof(_type, _stat) \ } diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index d24d8731bef0..317f3f1458db 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -43,7 +43,7 @@ struct i40e_stats { */ #define I40E_STAT(_type, _name, _stat) { \ .stat_string = _name, \ - .sizeof_stat = FIELD_SIZEOF(_type, _stat), \ + .sizeof_stat = sizeof_field(_type, _stat), \ .stat_offset = offsetof(_type, _stat) \ } diff --git a/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c index be24d42280d8..a3da422ab05b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c +++ b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c @@ -659,7 +659,7 @@ i40e_status i40e_shutdown_lan_hmc(struct i40e_hw *hw) #define I40E_HMC_STORE(_struct, _ele) \ offsetof(struct _struct, _ele), \ - FIELD_SIZEOF(struct _struct, _ele) + sizeof_field(struct _struct, _ele) struct i40e_context_ele { u16 offset; diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index dad3eec8ccd8..84c3d8d97ef6 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -42,7 +42,7 @@ struct iavf_stats { */ #define IAVF_STAT(_type, _name, _stat) { \ .stat_string = _name, \ - .sizeof_stat = FIELD_SIZEOF(_type, _stat), \ + .sizeof_stat = sizeof_field(_type, _stat), \ .stat_offset = offsetof(_type, _stat) \ } diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index aec3c6c379df..9ebd93e79aeb 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -15,7 +15,7 @@ struct ice_stats { #define ICE_STAT(_type, _name, _stat) { \ .stat_string = _name, \ - .sizeof_stat = FIELD_SIZEOF(_type, _stat), \ + .sizeof_stat = sizeof_field(_type, _stat), \ .stat_offset = offsetof(_type, _stat) \ } @@ -36,10 +36,10 @@ static int ice_q_stats_len(struct net_device *netdev) #define ICE_VSI_STATS_LEN ARRAY_SIZE(ice_gstrings_vsi_stats) #define ICE_PFC_STATS_LEN ( \ - (FIELD_SIZEOF(struct ice_pf, stats.priority_xoff_rx) + \ - FIELD_SIZEOF(struct ice_pf, stats.priority_xon_rx) + \ - FIELD_SIZEOF(struct ice_pf, stats.priority_xoff_tx) + \ - FIELD_SIZEOF(struct ice_pf, stats.priority_xon_tx)) \ + (sizeof_field(struct ice_pf, stats.priority_xoff_rx) + \ + sizeof_field(struct ice_pf, stats.priority_xon_rx) + \ + sizeof_field(struct ice_pf, stats.priority_xoff_tx) + \ + sizeof_field(struct ice_pf, stats.priority_xon_tx)) \ / sizeof(u64)) #define ICE_ALL_STATS_LEN(n) (ICE_PF_STATS_LEN + ICE_PFC_STATS_LEN + \ ICE_VSI_STATS_LEN + ice_q_stats_len(n)) diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h index ad34f22d44ef..0997d352709b 100644 --- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h +++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h @@ -302,7 +302,7 @@ struct ice_ctx_ele { #define ICE_CTX_STORE(_struct, _ele, _width, _lsb) { \ .offset = offsetof(struct _struct, _ele), \ - .size_of = FIELD_SIZEOF(struct _struct, _ele), \ + .size_of = sizeof_field(struct _struct, _ele), \ .width = _width, \ .lsb = _lsb, \ } diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index 3182b059bf55..4690d6c87f39 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -26,7 +26,7 @@ struct igb_stats { #define IGB_STAT(_name, _stat) { \ .stat_string = _name, \ - .sizeof_stat = FIELD_SIZEOF(struct igb_adapter, _stat), \ + .sizeof_stat = sizeof_field(struct igb_adapter, _stat), \ .stat_offset = offsetof(struct igb_adapter, _stat) \ } static const struct igb_stats igb_gstrings_stats[] = { @@ -76,7 +76,7 @@ static const struct igb_stats igb_gstrings_stats[] = { #define IGB_NETDEV_STAT(_net_stat) { \ .stat_string = __stringify(_net_stat), \ - .sizeof_stat = FIELD_SIZEOF(struct rtnl_link_stats64, _net_stat), \ + .sizeof_stat = sizeof_field(struct rtnl_link_stats64, _net_stat), \ .stat_offset = offsetof(struct rtnl_link_stats64, _net_stat) \ } static const struct igb_stats igb_gstrings_net_stats[] = { diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index ac98f1d96892..455c1cdceb6e 100644 --- a/drivers/net/ethernet/intel/igc/igc_ethtool.c +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -16,7 +16,7 @@ struct igc_stats { #define IGC_STAT(_name, _stat) { \ .stat_string = _name, \ - .sizeof_stat = FIELD_SIZEOF(struct igc_adapter, _stat), \ + .sizeof_stat = sizeof_field(struct igc_adapter, _stat), \ .stat_offset = offsetof(struct igc_adapter, _stat) \ } @@ -67,7 +67,7 @@ static const struct igc_stats igc_gstrings_stats[] = { #define IGC_NETDEV_STAT(_net_stat) { \ .stat_string = __stringify(_net_stat), \ - .sizeof_stat = FIELD_SIZEOF(struct rtnl_link_stats64, _net_stat), \ + .sizeof_stat = sizeof_field(struct rtnl_link_stats64, _net_stat), \ .stat_offset = offsetof(struct rtnl_link_stats64, _net_stat) \ } diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c b/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c index c8c93ac436d4..c65eb1afc8fb 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c @@ -19,10 +19,10 @@ struct ixgb_stats { }; #define IXGB_STAT(m) IXGB_STATS, \ - FIELD_SIZEOF(struct ixgb_adapter, m), \ + sizeof_field(struct ixgb_adapter, m), \ offsetof(struct ixgb_adapter, m) #define IXGB_NETDEV_STAT(m) NETDEV_STATS, \ - FIELD_SIZEOF(struct net_device, m), \ + sizeof_field(struct net_device, m), \ offsetof(struct net_device, m) static struct ixgb_stats ixgb_gstrings_stats[] = { diff --git a/drivers/net/ethernet/intel/ixgbevf/ethtool.c b/drivers/net/ethernet/intel/ixgbevf/ethtool.c index 54459b69c948..f7f309c96fa8 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ethtool.c +++ b/drivers/net/ethernet/intel/ixgbevf/ethtool.c @@ -31,14 +31,14 @@ struct ixgbe_stats { #define IXGBEVF_STAT(_name, _stat) { \ .stat_string = _name, \ .type = IXGBEVF_STATS, \ - .sizeof_stat = FIELD_SIZEOF(struct ixgbevf_adapter, _stat), \ + .sizeof_stat = sizeof_field(struct ixgbevf_adapter, _stat), \ .stat_offset = offsetof(struct ixgbevf_adapter, _stat) \ } #define IXGBEVF_NETDEV_STAT(_net_stat) { \ .stat_string = #_net_stat, \ .type = NETDEV_STATS, \ - .sizeof_stat = FIELD_SIZEOF(struct net_device_stats, _net_stat), \ + .sizeof_stat = sizeof_field(struct net_device_stats, _net_stat), \ .stat_offset = offsetof(struct net_device_stats, _net_stat) \ } diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index d5b644131cff..65a093216dac 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -1432,11 +1432,11 @@ struct mv643xx_eth_stats { }; #define SSTAT(m) \ - { #m, FIELD_SIZEOF(struct net_device_stats, m), \ + { #m, sizeof_field(struct net_device_stats, m), \ offsetof(struct net_device, stats.m), -1 } #define MIBSTAT(m) \ - { #m, FIELD_SIZEOF(struct mib_counters, m), \ + { #m, sizeof_field(struct mib_counters, m), \ -1, offsetof(struct mv643xx_eth_private, mib_counters.m) } static const struct mv643xx_eth_stats mv643xx_eth_stats[] = { diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index a1202e53710c..8bf1f08fdee2 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -611,7 +611,7 @@ static u32 ptys_get_active_port(struct mlx4_ptys_reg *ptys_reg) } #define MLX4_LINK_MODES_SZ \ - (FIELD_SIZEOF(struct mlx4_ptys_reg, eth_proto_cap) * 8) + (sizeof_field(struct mlx4_ptys_reg, eth_proto_cap) * 8) enum ethtool_report { SUPPORTED = 0, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c index c76da309506b..e4ec0e03c289 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c @@ -87,10 +87,10 @@ static const struct rhashtable_params rhash_sa = { * value is not constant during the lifetime * of the key object. */ - .key_len = FIELD_SIZEOF(struct mlx5_fpga_ipsec_sa_ctx, hw_sa) - - FIELD_SIZEOF(struct mlx5_ifc_fpga_ipsec_sa_v1, cmd), + .key_len = sizeof_field(struct mlx5_fpga_ipsec_sa_ctx, hw_sa) - + sizeof_field(struct mlx5_ifc_fpga_ipsec_sa_v1, cmd), .key_offset = offsetof(struct mlx5_fpga_ipsec_sa_ctx, hw_sa) + - FIELD_SIZEOF(struct mlx5_ifc_fpga_ipsec_sa_v1, cmd), + sizeof_field(struct mlx5_ifc_fpga_ipsec_sa_v1, cmd), .head_offset = offsetof(struct mlx5_fpga_ipsec_sa_ctx, hash), .automatic_shrinking = true, .min_size = 1, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index d60577484567..9a48c4310887 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -209,7 +209,7 @@ enum fs_i_lock_class { }; static const struct rhashtable_params rhash_fte = { - .key_len = FIELD_SIZEOF(struct fs_fte, val), + .key_len = sizeof_field(struct fs_fte, val), .key_offset = offsetof(struct fs_fte, val), .head_offset = offsetof(struct fs_fte, hash), .automatic_shrinking = true, @@ -217,7 +217,7 @@ static const struct rhashtable_params rhash_fte = { }; static const struct rhashtable_params rhash_fg = { - .key_len = FIELD_SIZEOF(struct mlx5_flow_group, mask), + .key_len = sizeof_field(struct mlx5_flow_group, mask), .key_offset = offsetof(struct mlx5_flow_group, mask), .head_offset = offsetof(struct mlx5_flow_group, hash), .automatic_shrinking = true, diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c index c80bb83c8ac9..0a721f6e8676 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c @@ -2652,17 +2652,17 @@ static int mem_ldx_skb(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, switch (meta->insn.off) { case offsetof(struct __sk_buff, len): - if (size != FIELD_SIZEOF(struct __sk_buff, len)) + if (size != sizeof_field(struct __sk_buff, len)) return -EOPNOTSUPP; wrp_mov(nfp_prog, dst, plen_reg(nfp_prog)); break; case offsetof(struct __sk_buff, data): - if (size != FIELD_SIZEOF(struct __sk_buff, data)) + if (size != sizeof_field(struct __sk_buff, data)) return -EOPNOTSUPP; wrp_mov(nfp_prog, dst, pptr_reg(nfp_prog)); break; case offsetof(struct __sk_buff, data_end): - if (size != FIELD_SIZEOF(struct __sk_buff, data_end)) + if (size != sizeof_field(struct __sk_buff, data_end)) return -EOPNOTSUPP; emit_alu(nfp_prog, dst, plen_reg(nfp_prog), ALU_OP_ADD, pptr_reg(nfp_prog)); @@ -2683,12 +2683,12 @@ static int mem_ldx_xdp(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, switch (meta->insn.off) { case offsetof(struct xdp_md, data): - if (size != FIELD_SIZEOF(struct xdp_md, data)) + if (size != sizeof_field(struct xdp_md, data)) return -EOPNOTSUPP; wrp_mov(nfp_prog, dst, pptr_reg(nfp_prog)); break; case offsetof(struct xdp_md, data_end): - if (size != FIELD_SIZEOF(struct xdp_md, data_end)) + if (size != sizeof_field(struct xdp_md, data_end)) return -EOPNOTSUPP; emit_alu(nfp_prog, dst, plen_reg(nfp_prog), ALU_OP_ADD, pptr_reg(nfp_prog)); diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c index 8f732771d3fa..11c83a99b014 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c @@ -15,7 +15,7 @@ const struct rhashtable_params nfp_bpf_maps_neutral_params = { .nelem_hint = 4, - .key_len = FIELD_SIZEOF(struct bpf_map, id), + .key_len = sizeof_field(struct bpf_map, id), .key_offset = offsetof(struct nfp_bpf_neutral_map, map_id), .head_offset = offsetof(struct nfp_bpf_neutral_map, l), .automatic_shrinking = true, diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c index 95a0d3910e31..ac02369174a9 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c @@ -374,7 +374,7 @@ nfp_bpf_map_alloc(struct nfp_app_bpf *bpf, struct bpf_offloaded_map *offmap) } use_map_size = DIV_ROUND_UP(offmap->map.value_size, 4) * - FIELD_SIZEOF(struct nfp_bpf_map, use_map[0]); + sizeof_field(struct nfp_bpf_map, use_map[0]); nfp_map = kzalloc(sizeof(*nfp_map) + use_map_size, GFP_USER); if (!nfp_map) diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h index 31d94592a7c0..e0c985fcaec1 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.h +++ b/drivers/net/ethernet/netronome/nfp/flower/main.h @@ -24,7 +24,7 @@ struct nfp_app; #define NFP_FL_STAT_ID_MU_NUM GENMASK(31, 22) #define NFP_FL_STAT_ID_STAT GENMASK(21, 0) -#define NFP_FL_STATS_ELEM_RS FIELD_SIZEOF(struct nfp_fl_stats_id, \ +#define NFP_FL_STATS_ELEM_RS sizeof_field(struct nfp_fl_stats_id, \ init_unalloc) #define NFP_FLOWER_MASK_ENTRY_RS 256 #define NFP_FLOWER_MASK_ELEMENT_RS 1 diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c index 1a3008e33182..b36aa5bf3c5f 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c +++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c @@ -20,7 +20,7 @@ struct pch_gbe_stats { #define PCH_GBE_STAT(m) \ { \ .string = #m, \ - .size = FIELD_SIZEOF(struct pch_gbe_hw_stats, m), \ + .size = sizeof_field(struct pch_gbe_hw_stats, m), \ .offset = offsetof(struct pch_gbe_hw_stats, m), \ } diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h index c303a92d5b06..e8a1b27db84d 100644 --- a/drivers/net/ethernet/qlogic/qede/qede.h +++ b/drivers/net/ethernet/qlogic/qede/qede.h @@ -464,7 +464,7 @@ struct qede_fastpath { struct qede_tx_queue *txq; struct qede_tx_queue *xdp_tx; -#define VEC_NAME_SIZE (FIELD_SIZEOF(struct net_device, name) + 8) +#define VEC_NAME_SIZE (sizeof_field(struct net_device, name) + 8) char name[VEC_NAME_SIZE]; }; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c index a4cd6f2cfb86..75d83c3cbf27 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c @@ -20,7 +20,7 @@ struct qlcnic_stats { int stat_offset; }; -#define QLC_SIZEOF(m) FIELD_SIZEOF(struct qlcnic_adapter, m) +#define QLC_SIZEOF(m) sizeof_field(struct qlcnic_adapter, m) #define QLC_OFF(m) offsetof(struct qlcnic_adapter, m) static const u32 qlcnic_fw_dump_level[] = { 0x3, 0x7, 0xf, 0x1f, 0x3f, 0x7f, 0xff diff --git a/drivers/net/ethernet/realtek/r8169_firmware.c b/drivers/net/ethernet/realtek/r8169_firmware.c index 355cc810e322..cbc6b846ded5 100644 --- a/drivers/net/ethernet/realtek/r8169_firmware.c +++ b/drivers/net/ethernet/realtek/r8169_firmware.c @@ -37,7 +37,7 @@ struct fw_info { u8 chksum; } __packed; -#define FW_OPCODE_SIZE FIELD_SIZEOF(struct rtl_fw_phy_action, code[0]) +#define FW_OPCODE_SIZE sizeof_field(struct rtl_fw_phy_action, code[0]) static bool rtl_fw_format_ok(struct rtl_fw *rtl_fw) { diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c index 0775b9464b4e..466483c4ac67 100644 --- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c +++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c @@ -30,7 +30,7 @@ struct sxgbe_stats { #define SXGBE_STAT(m) \ { \ #m, \ - FIELD_SIZEOF(struct sxgbe_extra_stats, m), \ + sizeof_field(struct sxgbe_extra_stats, m), \ offsetof(struct sxgbe_priv_data, xstats.m) \ } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index 1a768837ca72..b29603ec744c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -34,7 +34,7 @@ struct stmmac_stats { }; #define STMMAC_STAT(m) \ - { #m, FIELD_SIZEOF(struct stmmac_extra_stats, m), \ + { #m, sizeof_field(struct stmmac_extra_stats, m), \ offsetof(struct stmmac_priv, xstats.m)} static const struct stmmac_stats stmmac_gstrings_stats[] = { @@ -163,7 +163,7 @@ static const struct stmmac_stats stmmac_gstrings_stats[] = { /* HW MAC Management counters (if supported) */ #define STMMAC_MMC_STAT(m) \ - { #m, FIELD_SIZEOF(struct stmmac_counters, m), \ + { #m, sizeof_field(struct stmmac_counters, m), \ offsetof(struct stmmac_priv, mmc.m)} static const struct stmmac_stats stmmac_mmc[] = { diff --git a/drivers/net/ethernet/ti/cpsw_ethtool.c b/drivers/net/ethernet/ti/cpsw_ethtool.c index 31248a6cc642..fa54efe3be63 100644 --- a/drivers/net/ethernet/ti/cpsw_ethtool.c +++ b/drivers/net/ethernet/ti/cpsw_ethtool.c @@ -73,13 +73,13 @@ enum { }; #define CPSW_STAT(m) CPSW_STATS, \ - FIELD_SIZEOF(struct cpsw_hw_stats, m), \ + sizeof_field(struct cpsw_hw_stats, m), \ offsetof(struct cpsw_hw_stats, m) #define CPDMA_RX_STAT(m) CPDMA_RX_STATS, \ - FIELD_SIZEOF(struct cpdma_chan_stats, m), \ + sizeof_field(struct cpdma_chan_stats, m), \ offsetof(struct cpdma_chan_stats, m) #define CPDMA_TX_STAT(m) CPDMA_TX_STATS, \ - FIELD_SIZEOF(struct cpdma_chan_stats, m), \ + sizeof_field(struct cpdma_chan_stats, m), \ offsetof(struct cpdma_chan_stats, m) static const struct cpsw_stats cpsw_gstrings_stats[] = { diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c index 86a3f42a3dcc..d6a192c1f337 100644 --- a/drivers/net/ethernet/ti/netcp_ethss.c +++ b/drivers/net/ethernet/ti/netcp_ethss.c @@ -783,28 +783,28 @@ struct netcp_ethtool_stat { #define GBE_STATSA_INFO(field) \ { \ "GBE_A:"#field, GBE_STATSA_MODULE, \ - FIELD_SIZEOF(struct gbe_hw_stats, field), \ + sizeof_field(struct gbe_hw_stats, field), \ offsetof(struct gbe_hw_stats, field) \ } #define GBE_STATSB_INFO(field) \ { \ "GBE_B:"#field, GBE_STATSB_MODULE, \ - FIELD_SIZEOF(struct gbe_hw_stats, field), \ + sizeof_field(struct gbe_hw_stats, field), \ offsetof(struct gbe_hw_stats, field) \ } #define GBE_STATSC_INFO(field) \ { \ "GBE_C:"#field, GBE_STATSC_MODULE, \ - FIELD_SIZEOF(struct gbe_hw_stats, field), \ + sizeof_field(struct gbe_hw_stats, field), \ offsetof(struct gbe_hw_stats, field) \ } #define GBE_STATSD_INFO(field) \ { \ "GBE_D:"#field, GBE_STATSD_MODULE, \ - FIELD_SIZEOF(struct gbe_hw_stats, field), \ + sizeof_field(struct gbe_hw_stats, field), \ offsetof(struct gbe_hw_stats, field) \ } @@ -957,7 +957,7 @@ static const struct netcp_ethtool_stat gbe13_et_stats[] = { #define GBENU_STATS_HOST(field) \ { \ "GBE_HOST:"#field, GBENU_STATS0_MODULE, \ - FIELD_SIZEOF(struct gbenu_hw_stats, field), \ + sizeof_field(struct gbenu_hw_stats, field), \ offsetof(struct gbenu_hw_stats, field) \ } @@ -967,56 +967,56 @@ static const struct netcp_ethtool_stat gbe13_et_stats[] = { #define GBENU_STATS_P1(field) \ { \ "GBE_P1:"#field, GBENU_STATS1_MODULE, \ - FIELD_SIZEOF(struct gbenu_hw_stats, field), \ + sizeof_field(struct gbenu_hw_stats, field), \ offsetof(struct gbenu_hw_stats, field) \ } #define GBENU_STATS_P2(field) \ { \ "GBE_P2:"#field, GBENU_STATS2_MODULE, \ - FIELD_SIZEOF(struct gbenu_hw_stats, field), \ + sizeof_field(struct gbenu_hw_stats, field), \ offsetof(struct gbenu_hw_stats, field) \ } #define GBENU_STATS_P3(field) \ { \ "GBE_P3:"#field, GBENU_STATS3_MODULE, \ - FIELD_SIZEOF(struct gbenu_hw_stats, field), \ + sizeof_field(struct gbenu_hw_stats, field), \ offsetof(struct gbenu_hw_stats, field) \ } #define GBENU_STATS_P4(field) \ { \ "GBE_P4:"#field, GBENU_STATS4_MODULE, \ - FIELD_SIZEOF(struct gbenu_hw_stats, field), \ + sizeof_field(struct gbenu_hw_stats, field), \ offsetof(struct gbenu_hw_stats, field) \ } #define GBENU_STATS_P5(field) \ { \ "GBE_P5:"#field, GBENU_STATS5_MODULE, \ - FIELD_SIZEOF(struct gbenu_hw_stats, field), \ + sizeof_field(struct gbenu_hw_stats, field), \ offsetof(struct gbenu_hw_stats, field) \ } #define GBENU_STATS_P6(field) \ { \ "GBE_P6:"#field, GBENU_STATS6_MODULE, \ - FIELD_SIZEOF(struct gbenu_hw_stats, field), \ + sizeof_field(struct gbenu_hw_stats, field), \ offsetof(struct gbenu_hw_stats, field) \ } #define GBENU_STATS_P7(field) \ { \ "GBE_P7:"#field, GBENU_STATS7_MODULE, \ - FIELD_SIZEOF(struct gbenu_hw_stats, field), \ + sizeof_field(struct gbenu_hw_stats, field), \ offsetof(struct gbenu_hw_stats, field) \ } #define GBENU_STATS_P8(field) \ { \ "GBE_P8:"#field, GBENU_STATS8_MODULE, \ - FIELD_SIZEOF(struct gbenu_hw_stats, field), \ + sizeof_field(struct gbenu_hw_stats, field), \ offsetof(struct gbenu_hw_stats, field) \ } @@ -1607,21 +1607,21 @@ static const struct netcp_ethtool_stat gbenu_et_stats[] = { #define XGBE_STATS0_INFO(field) \ { \ "GBE_0:"#field, XGBE_STATS0_MODULE, \ - FIELD_SIZEOF(struct xgbe_hw_stats, field), \ + sizeof_field(struct xgbe_hw_stats, field), \ offsetof(struct xgbe_hw_stats, field) \ } #define XGBE_STATS1_INFO(field) \ { \ "GBE_1:"#field, XGBE_STATS1_MODULE, \ - FIELD_SIZEOF(struct xgbe_hw_stats, field), \ + sizeof_field(struct xgbe_hw_stats, field), \ offsetof(struct xgbe_hw_stats, field) \ } #define XGBE_STATS2_INFO(field) \ { \ "GBE_2:"#field, XGBE_STATS2_MODULE, \ - FIELD_SIZEOF(struct xgbe_hw_stats, field), \ + sizeof_field(struct xgbe_hw_stats, field), \ offsetof(struct xgbe_hw_stats, field) \ } diff --git a/drivers/net/fjes/fjes_ethtool.c b/drivers/net/fjes/fjes_ethtool.c index 09f3604cfbf8..746736c83873 100644 --- a/drivers/net/fjes/fjes_ethtool.c +++ b/drivers/net/fjes/fjes_ethtool.c @@ -21,7 +21,7 @@ struct fjes_stats { #define FJES_STAT(name, stat) { \ .stat_string = name, \ - .sizeof_stat = FIELD_SIZEOF(struct fjes_adapter, stat), \ + .sizeof_stat = sizeof_field(struct fjes_adapter, stat), \ .stat_offset = offsetof(struct fjes_adapter, stat) \ } diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 5c6b7fc04ea6..75757e9954ba 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -1156,7 +1156,7 @@ static void geneve_setup(struct net_device *dev) static const struct nla_policy geneve_policy[IFLA_GENEVE_MAX + 1] = { [IFLA_GENEVE_ID] = { .type = NLA_U32 }, - [IFLA_GENEVE_REMOTE] = { .len = FIELD_SIZEOF(struct iphdr, daddr) }, + [IFLA_GENEVE_REMOTE] = { .len = sizeof_field(struct iphdr, daddr) }, [IFLA_GENEVE_REMOTE6] = { .len = sizeof(struct in6_addr) }, [IFLA_GENEVE_TTL] = { .type = NLA_U8 }, [IFLA_GENEVE_TOS] = { .type = NLA_U8 }, diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index eff8fef4f775..02e66473f2ed 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -571,7 +571,7 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net) /* Use the skb control buffer for building up the packet */ BUILD_BUG_ON(sizeof(struct hv_netvsc_packet) > - FIELD_SIZEOF(struct sk_buff, cb)); + sizeof_field(struct sk_buff, cb)); packet = (struct hv_netvsc_packet *)skb->cb; packet->q_idx = skb_get_queue_mapping(skb); diff --git a/drivers/net/usb/sierra_net.c b/drivers/net/usb/sierra_net.c index 34c1eaba536c..389d19dd7909 100644 --- a/drivers/net/usb/sierra_net.c +++ b/drivers/net/usb/sierra_net.c @@ -865,7 +865,7 @@ static struct sk_buff *sierra_net_tx_fixup(struct usbnet *dev, u16 len; bool need_tail; - BUILD_BUG_ON(FIELD_SIZEOF(struct usbnet, data) + BUILD_BUG_ON(sizeof_field(struct usbnet, data) < sizeof(struct cdc_state)); dev_dbg(&dev->udev->dev, "%s", __func__); diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 30e511c2c8d0..9ce6d30576dd 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -2184,7 +2184,7 @@ static int __init usbnet_init(void) { /* Compiler should optimize this out. */ BUILD_BUG_ON( - FIELD_SIZEOF(struct sk_buff, cb) < sizeof(struct skb_data)); + sizeof_field(struct sk_buff, cb) < sizeof(struct skb_data)); eth_random_addr(node_id); return 0; diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 4c34375c2e22..3ec6b506033d 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -3069,10 +3069,10 @@ static void vxlan_raw_setup(struct net_device *dev) static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = { [IFLA_VXLAN_ID] = { .type = NLA_U32 }, - [IFLA_VXLAN_GROUP] = { .len = FIELD_SIZEOF(struct iphdr, daddr) }, + [IFLA_VXLAN_GROUP] = { .len = sizeof_field(struct iphdr, daddr) }, [IFLA_VXLAN_GROUP6] = { .len = sizeof(struct in6_addr) }, [IFLA_VXLAN_LINK] = { .type = NLA_U32 }, - [IFLA_VXLAN_LOCAL] = { .len = FIELD_SIZEOF(struct iphdr, saddr) }, + [IFLA_VXLAN_LOCAL] = { .len = sizeof_field(struct iphdr, saddr) }, [IFLA_VXLAN_LOCAL6] = { .len = sizeof(struct in6_addr) }, [IFLA_VXLAN_TOS] = { .type = NLA_U8 }, [IFLA_VXLAN_TTL] = { .type = NLA_U8 }, diff --git a/drivers/net/wireless/marvell/libertas/debugfs.c b/drivers/net/wireless/marvell/libertas/debugfs.c index fe14814af300..c604613ab506 100644 --- a/drivers/net/wireless/marvell/libertas/debugfs.c +++ b/drivers/net/wireless/marvell/libertas/debugfs.c @@ -774,7 +774,7 @@ void lbs_debugfs_remove_one(struct lbs_private *priv) #ifdef PROC_DEBUG -#define item_size(n) (FIELD_SIZEOF(struct lbs_private, n)) +#define item_size(n) (sizeof_field(struct lbs_private, n)) #define item_addr(n) (offsetof(struct lbs_private, n)) diff --git a/drivers/net/wireless/marvell/mwifiex/util.h b/drivers/net/wireless/marvell/mwifiex/util.h index c386992abcdb..7cafcecd7b85 100644 --- a/drivers/net/wireless/marvell/mwifiex/util.h +++ b/drivers/net/wireless/marvell/mwifiex/util.h @@ -36,11 +36,11 @@ struct mwifiex_cb { }; /* size/addr for mwifiex_debug_info */ -#define item_size(n) (FIELD_SIZEOF(struct mwifiex_debug_info, n)) +#define item_size(n) (sizeof_field(struct mwifiex_debug_info, n)) #define item_addr(n) (offsetof(struct mwifiex_debug_info, n)) /* size/addr for struct mwifiex_adapter */ -#define adapter_item_size(n) (FIELD_SIZEOF(struct mwifiex_adapter, n)) +#define adapter_item_size(n) (sizeof_field(struct mwifiex_adapter, n)) #define adapter_item_addr(n) (offsetof(struct mwifiex_adapter, n)) struct mwifiex_debug_data { diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index b9a2349e4b90..33a62a6692c0 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -4779,7 +4779,7 @@ static int qeth_qdio_establish(struct qeth_card *card) QETH_CARD_TEXT(card, 2, "qdioest"); - qib_param_field = kzalloc(FIELD_SIZEOF(struct qib, parm), GFP_KERNEL); + qib_param_field = kzalloc(sizeof_field(struct qib, parm), GFP_KERNEL); if (!qib_param_field) { rc = -ENOMEM; goto out_free_nothing; diff --git a/drivers/s390/net/qeth_core_mpc.h b/drivers/s390/net/qeth_core_mpc.h index 88f4dc140751..c1ecce95094d 100644 --- a/drivers/s390/net/qeth_core_mpc.h +++ b/drivers/s390/net/qeth_core_mpc.h @@ -421,7 +421,7 @@ struct qeth_ipacmd_setassparms { } data; } __attribute__ ((packed)); -#define SETASS_DATA_SIZEOF(field) FIELD_SIZEOF(struct qeth_ipacmd_setassparms,\ +#define SETASS_DATA_SIZEOF(field) sizeof_field(struct qeth_ipacmd_setassparms,\ data.field) /* SETRTG IPA Command: ****************************************************/ @@ -535,7 +535,7 @@ struct qeth_ipacmd_setadpparms { } data; } __attribute__ ((packed)); -#define SETADP_DATA_SIZEOF(field) FIELD_SIZEOF(struct qeth_ipacmd_setadpparms,\ +#define SETADP_DATA_SIZEOF(field) sizeof_field(struct qeth_ipacmd_setadpparms,\ data.field) /* CREATE_ADDR IPA Command: ***********************************************/ @@ -648,7 +648,7 @@ struct qeth_ipacmd_vnicc { } data; }; -#define VNICC_DATA_SIZEOF(field) FIELD_SIZEOF(struct qeth_ipacmd_vnicc,\ +#define VNICC_DATA_SIZEOF(field) sizeof_field(struct qeth_ipacmd_vnicc,\ data.field) /* SETBRIDGEPORT IPA Command: *********************************************/ @@ -729,7 +729,7 @@ struct qeth_ipacmd_setbridgeport { } data; } __packed; -#define SBP_DATA_SIZEOF(field) FIELD_SIZEOF(struct qeth_ipacmd_setbridgeport,\ +#define SBP_DATA_SIZEOF(field) sizeof_field(struct qeth_ipacmd_setbridgeport,\ data.field) /* ADDRESS_CHANGE_NOTIFICATION adapter-initiated "command" *******************/ @@ -790,7 +790,7 @@ struct qeth_ipa_cmd { } data; } __attribute__ ((packed)); -#define IPA_DATA_SIZEOF(field) FIELD_SIZEOF(struct qeth_ipa_cmd, data.field) +#define IPA_DATA_SIZEOF(field) sizeof_field(struct qeth_ipa_cmd, data.field) /* * special command for ARP processing. diff --git a/drivers/scsi/aacraid/aachba.c b/drivers/scsi/aacraid/aachba.c index e36608ce937a..33dbc051bff9 100644 --- a/drivers/scsi/aacraid/aachba.c +++ b/drivers/scsi/aacraid/aachba.c @@ -535,7 +535,7 @@ static void get_container_name_callback(void *context, struct fib * fibptr) if ((le32_to_cpu(get_name_reply->status) == CT_OK) && (get_name_reply->data[0] != '\0')) { char *sp = get_name_reply->data; - int data_size = FIELD_SIZEOF(struct aac_get_name_resp, data); + int data_size = sizeof_field(struct aac_get_name_resp, data); sp[data_size - 1] = '\0'; while (*sp == ' ') @@ -574,7 +574,7 @@ static int aac_get_container_name(struct scsi_cmnd * scsicmd) dev = (struct aac_dev *)scsicmd->device->host->hostdata; - data_size = FIELD_SIZEOF(struct aac_get_name_resp, data); + data_size = sizeof_field(struct aac_get_name_resp, data); cmd_fibcontext = aac_fib_alloc_tag(dev, scsicmd); diff --git a/drivers/scsi/be2iscsi/be_cmds.h b/drivers/scsi/be2iscsi/be_cmds.h index 063dccc18f70..5f9f0b18ddf3 100644 --- a/drivers/scsi/be2iscsi/be_cmds.h +++ b/drivers/scsi/be2iscsi/be_cmds.h @@ -1300,7 +1300,7 @@ struct be_cmd_get_port_name { /* Returns the number of items in the field array. */ #define BE_NUMBER_OF_FIELD(_type_, _field_) \ - (FIELD_SIZEOF(_type_, _field_)/sizeof((((_type_ *)0)->_field_[0])))\ + (sizeof_field(_type_, _field_)/sizeof((((_type_ *)0)->_field_[0])))\ /** * Different types of iSCSI completions to host driver for both initiator diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c index 0d044c165960..c4e4b0136f86 100644 --- a/drivers/scsi/cxgbi/libcxgbi.c +++ b/drivers/scsi/cxgbi/libcxgbi.c @@ -2746,7 +2746,7 @@ static int __init libcxgbi_init_module(void) { pr_info("%s", version); - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, cb) < + BUILD_BUG_ON(sizeof_field(struct sk_buff, cb) < sizeof(struct cxgbi_skb_cb)); return 0; } diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c index 7b7ef3acb504..412ac56ecd60 100644 --- a/drivers/scsi/smartpqi/smartpqi_init.c +++ b/drivers/scsi/smartpqi/smartpqi_init.c @@ -8689,11 +8689,11 @@ static void __attribute__((unused)) verify_structures(void) BUILD_BUG_ON(offsetof(struct pqi_general_admin_request, data.delete_operational_queue.queue_id) != 12); BUILD_BUG_ON(sizeof(struct pqi_general_admin_request) != 64); - BUILD_BUG_ON(FIELD_SIZEOF(struct pqi_general_admin_request, + BUILD_BUG_ON(sizeof_field(struct pqi_general_admin_request, data.create_operational_iq) != 64 - 11); - BUILD_BUG_ON(FIELD_SIZEOF(struct pqi_general_admin_request, + BUILD_BUG_ON(sizeof_field(struct pqi_general_admin_request, data.create_operational_oq) != 64 - 11); - BUILD_BUG_ON(FIELD_SIZEOF(struct pqi_general_admin_request, + BUILD_BUG_ON(sizeof_field(struct pqi_general_admin_request, data.delete_operational_queue) != 64 - 11); BUILD_BUG_ON(offsetof(struct pqi_general_admin_response, diff --git a/drivers/staging/qlge/qlge_ethtool.c b/drivers/staging/qlge/qlge_ethtool.c index a6886cc5654c..56d116d79e56 100644 --- a/drivers/staging/qlge/qlge_ethtool.c +++ b/drivers/staging/qlge/qlge_ethtool.c @@ -41,7 +41,7 @@ struct ql_stats { int stat_offset; }; -#define QL_SIZEOF(m) FIELD_SIZEOF(struct ql_adapter, m) +#define QL_SIZEOF(m) sizeof_field(struct ql_adapter, m) #define QL_OFF(m) offsetof(struct ql_adapter, m) static const struct ql_stats ql_gstrings_stats[] = { diff --git a/drivers/staging/wfx/data_tx.c b/drivers/staging/wfx/data_tx.c index b722e9773232..df2640a79f02 100644 --- a/drivers/staging/wfx/data_tx.c +++ b/drivers/staging/wfx/data_tx.c @@ -679,7 +679,7 @@ void wfx_tx(struct ieee80211_hw *hw, struct ieee80211_tx_control *control, struct ieee80211_sta *sta = control ? control->sta : NULL; struct ieee80211_tx_info *tx_info = IEEE80211_SKB_CB(skb); struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; - size_t driver_data_room = FIELD_SIZEOF(struct ieee80211_tx_info, + size_t driver_data_room = sizeof_field(struct ieee80211_tx_info, rate_driver_data); compiletime_assert(sizeof(struct wfx_tx_priv) <= driver_data_room, diff --git a/drivers/target/iscsi/cxgbit/cxgbit_main.c b/drivers/target/iscsi/cxgbit/cxgbit_main.c index e877b917c15f..30ea37e1a3f5 100644 --- a/drivers/target/iscsi/cxgbit/cxgbit_main.c +++ b/drivers/target/iscsi/cxgbit/cxgbit_main.c @@ -708,7 +708,7 @@ static int __init cxgbit_init(void) pr_info("%s dcb enabled.\n", DRV_NAME); register_dcbevent_notifier(&cxgbit_dcbevent_nb); #endif - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, cb) < + BUILD_BUG_ON(sizeof_field(struct sk_buff, cb) < sizeof(union cxgbit_skb_cb)); return 0; } diff --git a/drivers/usb/atm/usbatm.c b/drivers/usb/atm/usbatm.c index dbea28495e1d..4e12a32ca392 100644 --- a/drivers/usb/atm/usbatm.c +++ b/drivers/usb/atm/usbatm.c @@ -1275,7 +1275,7 @@ EXPORT_SYMBOL_GPL(usbatm_usb_disconnect); static int __init usbatm_usb_init(void) { - if (sizeof(struct usbatm_control) > FIELD_SIZEOF(struct sk_buff, cb)) { + if (sizeof(struct usbatm_control) > sizeof_field(struct sk_buff, cb)) { printk(KERN_ERR "%s unusable with this kernel!\n", usbatm_driver_name); return -EIO; } diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index ce1d0235969c..0bbccac94d6c 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -3509,7 +3509,7 @@ static void ffs_free_inst(struct usb_function_instance *f) static int ffs_set_inst_name(struct usb_function_instance *fi, const char *name) { - if (strlen(name) >= FIELD_SIZEOF(struct ffs_dev, name)) + if (strlen(name) >= sizeof_field(struct ffs_dev, name)) return -ENAMETOOLONG; return ffs_name_dev(to_f_fs_opts(fi)->dev, name); } diff --git a/fs/crypto/keyring.c b/fs/crypto/keyring.c index 040df1f5e1c8..40cca351273f 100644 --- a/fs/crypto/keyring.c +++ b/fs/crypto/keyring.c @@ -151,7 +151,7 @@ static struct key *search_fscrypt_keyring(struct key *keyring, } #define FSCRYPT_FS_KEYRING_DESCRIPTION_SIZE \ - (CONST_STRLEN("fscrypt-") + FIELD_SIZEOF(struct super_block, s_id)) + (CONST_STRLEN("fscrypt-") + sizeof_field(struct super_block, s_id)) #define FSCRYPT_MK_DESCRIPTION_SIZE (2 * FSCRYPT_KEY_IDENTIFIER_SIZE + 1) diff --git a/fs/verity/enable.c b/fs/verity/enable.c index eabc6ac19906..b79e3fd19d11 100644 --- a/fs/verity/enable.c +++ b/fs/verity/enable.c @@ -315,7 +315,7 @@ int fsverity_ioctl_enable(struct file *filp, const void __user *uarg) if (arg.block_size != PAGE_SIZE) return -EINVAL; - if (arg.salt_size > FIELD_SIZEOF(struct fsverity_descriptor, salt)) + if (arg.salt_size > sizeof_field(struct fsverity_descriptor, salt)) return -EMSGSIZE; if (arg.sig_size > FS_VERITY_MAX_SIGNATURE_SIZE) diff --git a/include/linux/filter.h b/include/linux/filter.h index a141cb07e76a..345f3748e0fb 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -420,7 +420,7 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) #define BPF_FIELD_SIZEOF(type, field) \ ({ \ - const int __size = bytes_to_bpf_size(FIELD_SIZEOF(type, field)); \ + const int __size = bytes_to_bpf_size(sizeof_field(type, field)); \ BUILD_BUG_ON(__size < 0); \ __size; \ }) @@ -497,7 +497,7 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) #define bpf_target_off(TYPE, MEMBER, SIZE, PTR_SIZE) \ ({ \ - BUILD_BUG_ON(FIELD_SIZEOF(TYPE, MEMBER) != (SIZE)); \ + BUILD_BUG_ON(sizeof_field(TYPE, MEMBER) != (SIZE)); \ *(PTR_SIZE) = (SIZE); \ offsetof(TYPE, MEMBER); \ }) @@ -608,7 +608,7 @@ static inline void bpf_compute_data_pointers(struct sk_buff *skb) { struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb; - BUILD_BUG_ON(sizeof(*cb) > FIELD_SIZEOF(struct sk_buff, cb)); + BUILD_BUG_ON(sizeof(*cb) > sizeof_field(struct sk_buff, cb)); cb->data_meta = skb->data - skb_metadata_len(skb); cb->data_end = skb->data + skb_headlen(skb); } @@ -646,9 +646,9 @@ static inline u8 *bpf_skb_cb(struct sk_buff *skb) * attached to sockets, we need to clear the bpf_skb_cb() area * to not leak previous contents to user space. */ - BUILD_BUG_ON(FIELD_SIZEOF(struct __sk_buff, cb) != BPF_SKB_CB_LEN); - BUILD_BUG_ON(FIELD_SIZEOF(struct __sk_buff, cb) != - FIELD_SIZEOF(struct qdisc_skb_cb, data)); + BUILD_BUG_ON(sizeof_field(struct __sk_buff, cb) != BPF_SKB_CB_LEN); + BUILD_BUG_ON(sizeof_field(struct __sk_buff, cb) != + sizeof_field(struct qdisc_skb_cb, data)); return qdisc_skb_cb(skb)->data; } diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 7ed1e2f8641e..538c25e778c0 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -149,7 +149,7 @@ static inline bool is_error_page(struct page *page) #define KVM_REQUEST_ARCH_BASE 8 #define KVM_ARCH_REQ_FLAGS(nr, flags) ({ \ - BUILD_BUG_ON((unsigned)(nr) >= (FIELD_SIZEOF(struct kvm_vcpu, requests) * 8) - KVM_REQUEST_ARCH_BASE); \ + BUILD_BUG_ON((unsigned)(nr) >= (sizeof_field(struct kvm_vcpu, requests) * 8) - KVM_REQUEST_ARCH_BASE); \ (unsigned)(((nr) + KVM_REQUEST_ARCH_BASE) | (flags)); \ }) #define KVM_ARCH_REQ(nr) KVM_ARCH_REQ_FLAGS(nr, 0) diff --git a/include/linux/phy_led_triggers.h b/include/linux/phy_led_triggers.h index 3d507a8a6989..5c4d7a755101 100644 --- a/include/linux/phy_led_triggers.h +++ b/include/linux/phy_led_triggers.h @@ -14,7 +14,7 @@ struct phy_device; #define PHY_LED_TRIGGER_SPEED_SUFFIX_SIZE 11 #define PHY_LINK_LED_TRIGGER_NAME_SIZE (MII_BUS_ID_SIZE + \ - FIELD_SIZEOF(struct mdio_device, addr)+\ + sizeof_field(struct mdio_device, addr)+\ PHY_LED_TRIGGER_SPEED_SUFFIX_SIZE) struct phy_led_trigger { diff --git a/include/net/garp.h b/include/net/garp.h index c41833bd4590..4d9a0c6a2e5f 100644 --- a/include/net/garp.h +++ b/include/net/garp.h @@ -37,7 +37,7 @@ struct garp_skb_cb { static inline struct garp_skb_cb *garp_cb(struct sk_buff *skb) { BUILD_BUG_ON(sizeof(struct garp_skb_cb) > - FIELD_SIZEOF(struct sk_buff, cb)); + sizeof_field(struct sk_buff, cb)); return (struct garp_skb_cb *)skb->cb; } diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index af645604f328..236503a50759 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -33,8 +33,8 @@ /* Used to memset ipv4 address padding. */ #define IP_TUNNEL_KEY_IPV4_PAD offsetofend(struct ip_tunnel_key, u.ipv4.dst) #define IP_TUNNEL_KEY_IPV4_PAD_LEN \ - (FIELD_SIZEOF(struct ip_tunnel_key, u) - \ - FIELD_SIZEOF(struct ip_tunnel_key, u.ipv4)) + (sizeof_field(struct ip_tunnel_key, u) - \ + sizeof_field(struct ip_tunnel_key, u.ipv4)) struct ip_tunnel_key { __be64 tun_id; @@ -63,7 +63,7 @@ struct ip_tunnel_key { /* Maximum tunnel options length. */ #define IP_TUNNEL_OPTS_MAX \ - GENMASK((FIELD_SIZEOF(struct ip_tunnel_info, \ + GENMASK((sizeof_field(struct ip_tunnel_info, \ options_len) * BITS_PER_BYTE) - 1, 0) struct ip_tunnel_info { diff --git a/include/net/mrp.h b/include/net/mrp.h index ef58b4a07190..1c308c034e1a 100644 --- a/include/net/mrp.h +++ b/include/net/mrp.h @@ -39,7 +39,7 @@ struct mrp_skb_cb { static inline struct mrp_skb_cb *mrp_cb(struct sk_buff *skb) { BUILD_BUG_ON(sizeof(struct mrp_skb_cb) > - FIELD_SIZEOF(struct sk_buff, cb)); + sizeof_field(struct sk_buff, cb)); return (struct mrp_skb_cb *)skb->cb; } diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h index 44b5a00a9c64..37f0fbefb060 100644 --- a/include/net/netfilter/nf_conntrack_helper.h +++ b/include/net/netfilter/nf_conntrack_helper.h @@ -81,7 +81,7 @@ struct nf_conn_help { }; #define NF_CT_HELPER_BUILD_BUG_ON(structsize) \ - BUILD_BUG_ON((structsize) > FIELD_SIZEOF(struct nf_conn_help, data)) + BUILD_BUG_ON((structsize) > sizeof_field(struct nf_conn_help, data)) struct nf_conntrack_helper *__nf_conntrack_helper_find(const char *name, u16 l3num, u8 protonum); diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index 7281895fa6d9..2656155b4069 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -41,7 +41,7 @@ struct nft_immediate_expr { */ static inline u32 nft_cmp_fast_mask(unsigned int len) { - return cpu_to_le32(~0U >> (FIELD_SIZEOF(struct nft_cmp_fast_expr, + return cpu_to_le32(~0U >> (sizeof_field(struct nft_cmp_fast_expr, data) * BITS_PER_BYTE - len)); } diff --git a/include/net/sock.h b/include/net/sock.h index 87d54ef57f00..80f996406bba 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2305,7 +2305,7 @@ struct sock_skb_cb { * using skb->cb[] would keep using it directly and utilize its * alignement guarantee. */ -#define SOCK_SKB_CB_OFFSET ((FIELD_SIZEOF(struct sk_buff, cb) - \ +#define SOCK_SKB_CB_OFFSET ((sizeof_field(struct sk_buff, cb) - \ sizeof(struct sock_skb_cb))) #define SOCK_SKB_CB(__skb) ((struct sock_skb_cb *)((__skb)->cb + \ diff --git a/ipc/util.c b/ipc/util.c index d126d156efc6..915eacb9c059 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -100,7 +100,7 @@ device_initcall(ipc_init); static const struct rhashtable_params ipc_kht_params = { .head_offset = offsetof(struct kern_ipc_perm, khtnode), .key_offset = offsetof(struct kern_ipc_perm, key), - .key_len = FIELD_SIZEOF(struct kern_ipc_perm, key), + .key_len = sizeof_field(struct kern_ipc_perm, key), .automatic_shrinking = true, }; diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 9f90d3c92bda..4fb20ab179fe 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1341,7 +1341,7 @@ static u32 sysctl_convert_ctx_access(enum bpf_access_type type, *insn++ = BPF_LDX_MEM( BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sysctl_kern, write, - FIELD_SIZEOF(struct bpf_sysctl_kern, + sizeof_field(struct bpf_sysctl_kern, write), target_size)); break; diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index 2ba750725cb2..6bd22f6d9f41 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -357,7 +357,7 @@ static int cgroup_storage_check_btf(const struct bpf_map *map, * The first field must be a 64 bit integer at 0 offset. */ m = (struct btf_member *)(key_type + 1); - size = FIELD_SIZEOF(struct bpf_cgroup_storage_key, cgroup_inode_id); + size = sizeof_field(struct bpf_cgroup_storage_key, cgroup_inode_id); if (!btf_member_is_reg_int(btf, key_type, m, 0, size)) return -EINVAL; @@ -366,7 +366,7 @@ static int cgroup_storage_check_btf(const struct bpf_map *map, */ m++; offset = offsetof(struct bpf_cgroup_storage_key, attach_type); - size = FIELD_SIZEOF(struct bpf_cgroup_storage_key, attach_type); + size = sizeof_field(struct bpf_cgroup_storage_key, attach_type); if (!btf_member_is_reg_int(btf, key_type, m, offset, size)) return -EINVAL; diff --git a/net/802/mrp.c b/net/802/mrp.c index 2cfdfbfbb2ed..bea6e43d45a0 100644 --- a/net/802/mrp.c +++ b/net/802/mrp.c @@ -523,7 +523,7 @@ int mrp_request_join(const struct net_device *dev, struct mrp_attr *attr; if (sizeof(struct mrp_skb_cb) + len > - FIELD_SIZEOF(struct sk_buff, cb)) + sizeof_field(struct sk_buff, cb)) return -ENOMEM; spin_lock_bh(&app->lock); @@ -548,7 +548,7 @@ void mrp_request_leave(const struct net_device *dev, struct mrp_attr *attr; if (sizeof(struct mrp_skb_cb) + len > - FIELD_SIZEOF(struct sk_buff, cb)) + sizeof_field(struct sk_buff, cb)) return; spin_lock_bh(&app->lock); @@ -692,7 +692,7 @@ static int mrp_pdu_parse_vecattr(struct mrp_applicant *app, * advance to the next event in its Vector. */ if (sizeof(struct mrp_skb_cb) + mrp_cb(skb)->mh->attrlen > - FIELD_SIZEOF(struct sk_buff, cb)) + sizeof_field(struct sk_buff, cb)) return -1; if (skb_copy_bits(skb, *offset, mrp_cb(skb)->attrvalue, mrp_cb(skb)->mh->attrlen) < 0) diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index 4a89177def64..4811ec65bc43 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -548,7 +548,7 @@ static void batadv_recv_handler_init(void) BUILD_BUG_ON(sizeof(struct batadv_tvlv_tt_change) != 12); BUILD_BUG_ON(sizeof(struct batadv_tvlv_roam_adv) != 8); - i = FIELD_SIZEOF(struct sk_buff, cb); + i = sizeof_field(struct sk_buff, cb); BUILD_BUG_ON(sizeof(struct batadv_skb_cb) > i); /* broadcast packet */ diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 915c2d6f7fb9..f79205d4444f 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -253,21 +253,21 @@ static int convert___skb_to_skb(struct sk_buff *skb, struct __sk_buff *__skb) /* priority is allowed */ if (!range_is_zero(__skb, offsetof(struct __sk_buff, priority) + - FIELD_SIZEOF(struct __sk_buff, priority), + sizeof_field(struct __sk_buff, priority), offsetof(struct __sk_buff, cb))) return -EINVAL; /* cb is allowed */ if (!range_is_zero(__skb, offsetof(struct __sk_buff, cb) + - FIELD_SIZEOF(struct __sk_buff, cb), + sizeof_field(struct __sk_buff, cb), offsetof(struct __sk_buff, tstamp))) return -EINVAL; /* tstamp is allowed */ if (!range_is_zero(__skb, offsetof(struct __sk_buff, tstamp) + - FIELD_SIZEOF(struct __sk_buff, tstamp), + sizeof_field(struct __sk_buff, tstamp), sizeof(struct __sk_buff))) return -EINVAL; @@ -438,7 +438,7 @@ static int verify_user_bpf_flow_keys(struct bpf_flow_keys *ctx) /* flags is allowed */ if (!range_is_zero(ctx, offsetof(struct bpf_flow_keys, flags) + - FIELD_SIZEOF(struct bpf_flow_keys, flags), + sizeof_field(struct bpf_flow_keys, flags), sizeof(struct bpf_flow_keys))) return -EINVAL; diff --git a/net/bridge/br.c b/net/bridge/br.c index 8a8f9e5f264f..b6fe30e3768f 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -312,7 +312,7 @@ static int __init br_init(void) { int err; - BUILD_BUG_ON(sizeof(struct br_input_skb_cb) > FIELD_SIZEOF(struct sk_buff, cb)); + BUILD_BUG_ON(sizeof(struct br_input_skb_cb) > sizeof_field(struct sk_buff, cb)); err = stp_proto_register(&br_stp_proto); if (err < 0) { diff --git a/net/core/dev.c b/net/core/dev.c index 2c277b8aba38..0ad39c87b7fd 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -10165,7 +10165,7 @@ static struct hlist_head * __net_init netdev_create_hash(void) static int __net_init netdev_init(struct net *net) { BUILD_BUG_ON(GRO_HASH_BUCKETS > - 8 * FIELD_SIZEOF(struct napi_struct, gro_bitmask)); + 8 * sizeof_field(struct napi_struct, gro_bitmask)); if (net != &init_net) INIT_LIST_HEAD(&net->dev_base_head); diff --git a/net/core/filter.c b/net/core/filter.c index f1e703eed3d2..c19dd0973e0c 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -274,7 +274,7 @@ static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg, switch (skb_field) { case SKF_AD_MARK: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4); + BUILD_BUG_ON(sizeof_field(struct sk_buff, mark) != 4); *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, offsetof(struct sk_buff, mark)); @@ -289,14 +289,14 @@ static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg, break; case SKF_AD_QUEUE: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, queue_mapping) != 2); + BUILD_BUG_ON(sizeof_field(struct sk_buff, queue_mapping) != 2); *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg, offsetof(struct sk_buff, queue_mapping)); break; case SKF_AD_VLAN_TAG: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2); + BUILD_BUG_ON(sizeof_field(struct sk_buff, vlan_tci) != 2); /* dst_reg = *(u16 *) (src_reg + offsetof(vlan_tci)) */ *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg, @@ -322,7 +322,7 @@ static bool convert_bpf_extensions(struct sock_filter *fp, switch (fp->k) { case SKF_AD_OFF + SKF_AD_PROTOCOL: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2); + BUILD_BUG_ON(sizeof_field(struct sk_buff, protocol) != 2); /* A = *(u16 *) (CTX + offsetof(protocol)) */ *insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, @@ -338,8 +338,8 @@ static bool convert_bpf_extensions(struct sock_filter *fp, case SKF_AD_OFF + SKF_AD_IFINDEX: case SKF_AD_OFF + SKF_AD_HATYPE: - BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4); - BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, type) != 2); + BUILD_BUG_ON(sizeof_field(struct net_device, ifindex) != 4); + BUILD_BUG_ON(sizeof_field(struct net_device, type) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, dev), BPF_REG_TMP, BPF_REG_CTX, @@ -361,7 +361,7 @@ static bool convert_bpf_extensions(struct sock_filter *fp, break; case SKF_AD_OFF + SKF_AD_RXHASH: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4); + BUILD_BUG_ON(sizeof_field(struct sk_buff, hash) != 4); *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX, offsetof(struct sk_buff, hash)); @@ -385,7 +385,7 @@ static bool convert_bpf_extensions(struct sock_filter *fp, break; case SKF_AD_OFF + SKF_AD_VLAN_TPID: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_proto) != 2); + BUILD_BUG_ON(sizeof_field(struct sk_buff, vlan_proto) != 2); /* A = *(u16 *) (CTX + offsetof(vlan_proto)) */ *insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, @@ -5589,8 +5589,8 @@ u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, #define BPF_TCP_SOCK_GET_COMMON(FIELD) \ do { \ - BUILD_BUG_ON(FIELD_SIZEOF(struct tcp_sock, FIELD) > \ - FIELD_SIZEOF(struct bpf_tcp_sock, FIELD)); \ + BUILD_BUG_ON(sizeof_field(struct tcp_sock, FIELD) > \ + sizeof_field(struct bpf_tcp_sock, FIELD)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct tcp_sock, FIELD),\ si->dst_reg, si->src_reg, \ offsetof(struct tcp_sock, FIELD)); \ @@ -5598,9 +5598,9 @@ u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, #define BPF_INET_SOCK_GET_COMMON(FIELD) \ do { \ - BUILD_BUG_ON(FIELD_SIZEOF(struct inet_connection_sock, \ + BUILD_BUG_ON(sizeof_field(struct inet_connection_sock, \ FIELD) > \ - FIELD_SIZEOF(struct bpf_tcp_sock, FIELD)); \ + sizeof_field(struct bpf_tcp_sock, FIELD)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct inet_connection_sock, \ FIELD), \ @@ -5615,7 +5615,7 @@ u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, switch (si->off) { case offsetof(struct bpf_tcp_sock, rtt_min): - BUILD_BUG_ON(FIELD_SIZEOF(struct tcp_sock, rtt_min) != + BUILD_BUG_ON(sizeof_field(struct tcp_sock, rtt_min) != sizeof(struct minmax)); BUILD_BUG_ON(sizeof(struct minmax) < sizeof(struct minmax_sample)); @@ -5780,8 +5780,8 @@ u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type, #define BPF_XDP_SOCK_GET(FIELD) \ do { \ - BUILD_BUG_ON(FIELD_SIZEOF(struct xdp_sock, FIELD) > \ - FIELD_SIZEOF(struct bpf_xdp_sock, FIELD)); \ + BUILD_BUG_ON(sizeof_field(struct xdp_sock, FIELD) > \ + sizeof_field(struct bpf_xdp_sock, FIELD)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_sock, FIELD),\ si->dst_reg, si->src_reg, \ offsetof(struct xdp_sock, FIELD)); \ @@ -7344,7 +7344,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, case offsetof(struct __sk_buff, cb[0]) ... offsetofend(struct __sk_buff, cb[4]) - 1: - BUILD_BUG_ON(FIELD_SIZEOF(struct qdisc_skb_cb, data) < 20); + BUILD_BUG_ON(sizeof_field(struct qdisc_skb_cb, data) < 20); BUILD_BUG_ON((offsetof(struct sk_buff, cb) + offsetof(struct qdisc_skb_cb, data)) % sizeof(__u64)); @@ -7363,7 +7363,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct __sk_buff, tc_classid): - BUILD_BUG_ON(FIELD_SIZEOF(struct qdisc_skb_cb, tc_classid) != 2); + BUILD_BUG_ON(sizeof_field(struct qdisc_skb_cb, tc_classid) != 2); off = si->off; off -= offsetof(struct __sk_buff, tc_classid); @@ -7434,7 +7434,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, #endif break; case offsetof(struct __sk_buff, family): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_family) != 2); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_family) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, @@ -7445,7 +7445,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, 2, target_size)); break; case offsetof(struct __sk_buff, remote_ip4): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_daddr) != 4); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_daddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, @@ -7456,7 +7456,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, 4, target_size)); break; case offsetof(struct __sk_buff, local_ip4): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_rcv_saddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), @@ -7470,7 +7470,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, case offsetof(struct __sk_buff, remote_ip6[0]) ... offsetof(struct __sk_buff, remote_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_daddr.s6_addr32[0]) != 4); off = si->off; @@ -7490,7 +7490,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, case offsetof(struct __sk_buff, local_ip6[0]) ... offsetof(struct __sk_buff, local_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) != 4); off = si->off; @@ -7509,7 +7509,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct __sk_buff, remote_port): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_dport) != 2); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_dport) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, @@ -7524,7 +7524,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct __sk_buff, local_port): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_num) != 2); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_num) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, @@ -7535,7 +7535,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct __sk_buff, tstamp): - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, tstamp) != 8); + BUILD_BUG_ON(sizeof_field(struct sk_buff, tstamp) != 8); if (type == BPF_WRITE) *insn++ = BPF_STX_MEM(BPF_DW, @@ -7573,7 +7573,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, target_size)); break; case offsetof(struct __sk_buff, wire_len): - BUILD_BUG_ON(FIELD_SIZEOF(struct qdisc_skb_cb, pkt_len) != 4); + BUILD_BUG_ON(sizeof_field(struct qdisc_skb_cb, pkt_len) != 4); off = si->off; off -= offsetof(struct __sk_buff, wire_len); @@ -7603,7 +7603,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, switch (si->off) { case offsetof(struct bpf_sock, bound_dev_if): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock, sk_bound_dev_if) != 4); + BUILD_BUG_ON(sizeof_field(struct sock, sk_bound_dev_if) != 4); if (type == BPF_WRITE) *insn++ = BPF_STX_MEM(BPF_W, si->dst_reg, si->src_reg, @@ -7614,7 +7614,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock, mark): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock, sk_mark) != 4); + BUILD_BUG_ON(sizeof_field(struct sock, sk_mark) != 4); if (type == BPF_WRITE) *insn++ = BPF_STX_MEM(BPF_W, si->dst_reg, si->src_reg, @@ -7625,7 +7625,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock, priority): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock, sk_priority) != 4); + BUILD_BUG_ON(sizeof_field(struct sock, sk_priority) != 4); if (type == BPF_WRITE) *insn++ = BPF_STX_MEM(BPF_W, si->dst_reg, si->src_reg, @@ -7641,7 +7641,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_family, - FIELD_SIZEOF(struct sock_common, + sizeof_field(struct sock_common, skc_family), target_size)); break; @@ -7668,7 +7668,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, *insn++ = BPF_LDX_MEM( BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_rcv_saddr, - FIELD_SIZEOF(struct sock_common, + sizeof_field(struct sock_common, skc_rcv_saddr), target_size)); break; @@ -7677,7 +7677,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, *insn++ = BPF_LDX_MEM( BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_daddr, - FIELD_SIZEOF(struct sock_common, + sizeof_field(struct sock_common, skc_daddr), target_size)); break; @@ -7691,7 +7691,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, bpf_target_off( struct sock_common, skc_v6_rcv_saddr.s6_addr32[0], - FIELD_SIZEOF(struct sock_common, + sizeof_field(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]), target_size) + off); #else @@ -7708,7 +7708,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_v6_daddr.s6_addr32[0], - FIELD_SIZEOF(struct sock_common, + sizeof_field(struct sock_common, skc_v6_daddr.s6_addr32[0]), target_size) + off); #else @@ -7722,7 +7722,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, BPF_FIELD_SIZEOF(struct sock_common, skc_num), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_num, - FIELD_SIZEOF(struct sock_common, + sizeof_field(struct sock_common, skc_num), target_size)); break; @@ -7732,7 +7732,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, BPF_FIELD_SIZEOF(struct sock_common, skc_dport), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_dport, - FIELD_SIZEOF(struct sock_common, + sizeof_field(struct sock_common, skc_dport), target_size)); break; @@ -7742,7 +7742,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, BPF_FIELD_SIZEOF(struct sock_common, skc_state), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_state, - FIELD_SIZEOF(struct sock_common, + sizeof_field(struct sock_common, skc_state), target_size)); break; @@ -7837,7 +7837,7 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type, si->src_reg, offsetof(S, F)); \ *insn++ = BPF_LDX_MEM( \ SIZE, si->dst_reg, si->dst_reg, \ - bpf_target_off(NS, NF, FIELD_SIZEOF(NS, NF), \ + bpf_target_off(NS, NF, sizeof_field(NS, NF), \ target_size) \ + OFF); \ } while (0) @@ -7868,7 +7868,7 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type, *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(S, F), tmp_reg, \ si->dst_reg, offsetof(S, F)); \ *insn++ = BPF_STX_MEM(SIZE, tmp_reg, si->src_reg, \ - bpf_target_off(NS, NF, FIELD_SIZEOF(NS, NF), \ + bpf_target_off(NS, NF, sizeof_field(NS, NF), \ target_size) \ + OFF); \ *insn++ = BPF_LDX_MEM(BPF_DW, tmp_reg, si->dst_reg, \ @@ -7930,8 +7930,8 @@ static u32 sock_addr_convert_ctx_access(enum bpf_access_type type, */ BUILD_BUG_ON(offsetof(struct sockaddr_in, sin_port) != offsetof(struct sockaddr_in6, sin6_port)); - BUILD_BUG_ON(FIELD_SIZEOF(struct sockaddr_in, sin_port) != - FIELD_SIZEOF(struct sockaddr_in6, sin6_port)); + BUILD_BUG_ON(sizeof_field(struct sockaddr_in, sin_port) != + sizeof_field(struct sockaddr_in6, sin6_port)); SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD(struct bpf_sock_addr_kern, struct sockaddr_in6, uaddr, sin6_port, tmp_reg); @@ -7997,8 +7997,8 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, /* Helper macro for adding read access to tcp_sock or sock fields. */ #define SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ) \ do { \ - BUILD_BUG_ON(FIELD_SIZEOF(OBJ, OBJ_FIELD) > \ - FIELD_SIZEOF(struct bpf_sock_ops, BPF_FIELD)); \ + BUILD_BUG_ON(sizeof_field(OBJ, OBJ_FIELD) > \ + sizeof_field(struct bpf_sock_ops, BPF_FIELD)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, \ is_fullsock), \ @@ -8031,8 +8031,8 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, #define SOCK_OPS_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ) \ do { \ int reg = BPF_REG_9; \ - BUILD_BUG_ON(FIELD_SIZEOF(OBJ, OBJ_FIELD) > \ - FIELD_SIZEOF(struct bpf_sock_ops, BPF_FIELD)); \ + BUILD_BUG_ON(sizeof_field(OBJ, OBJ_FIELD) > \ + sizeof_field(struct bpf_sock_ops, BPF_FIELD)); \ if (si->dst_reg == reg || si->src_reg == reg) \ reg--; \ if (si->dst_reg == reg || si->src_reg == reg) \ @@ -8073,12 +8073,12 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, switch (si->off) { case offsetof(struct bpf_sock_ops, op) ... offsetof(struct bpf_sock_ops, replylong[3]): - BUILD_BUG_ON(FIELD_SIZEOF(struct bpf_sock_ops, op) != - FIELD_SIZEOF(struct bpf_sock_ops_kern, op)); - BUILD_BUG_ON(FIELD_SIZEOF(struct bpf_sock_ops, reply) != - FIELD_SIZEOF(struct bpf_sock_ops_kern, reply)); - BUILD_BUG_ON(FIELD_SIZEOF(struct bpf_sock_ops, replylong) != - FIELD_SIZEOF(struct bpf_sock_ops_kern, replylong)); + BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, op) != + sizeof_field(struct bpf_sock_ops_kern, op)); + BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, reply) != + sizeof_field(struct bpf_sock_ops_kern, reply)); + BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, replylong) != + sizeof_field(struct bpf_sock_ops_kern, replylong)); off = si->off; off -= offsetof(struct bpf_sock_ops, op); off += offsetof(struct bpf_sock_ops_kern, op); @@ -8091,7 +8091,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock_ops, family): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_family) != 2); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_family) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), @@ -8102,7 +8102,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock_ops, remote_ip4): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_daddr) != 4); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_daddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), @@ -8113,7 +8113,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock_ops, local_ip4): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_rcv_saddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( @@ -8128,7 +8128,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, case offsetof(struct bpf_sock_ops, remote_ip6[0]) ... offsetof(struct bpf_sock_ops, remote_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_daddr.s6_addr32[0]) != 4); off = si->off; @@ -8149,7 +8149,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, case offsetof(struct bpf_sock_ops, local_ip6[0]) ... offsetof(struct bpf_sock_ops, local_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) != 4); off = si->off; @@ -8168,7 +8168,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock_ops, remote_port): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_dport) != 2); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_dport) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), @@ -8182,7 +8182,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock_ops, local_port): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_num) != 2); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_num) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), @@ -8202,7 +8202,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock_ops, state): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_state) != 1); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_state) != 1); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), @@ -8213,7 +8213,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock_ops, rtt_min): - BUILD_BUG_ON(FIELD_SIZEOF(struct tcp_sock, rtt_min) != + BUILD_BUG_ON(sizeof_field(struct tcp_sock, rtt_min) != sizeof(struct minmax)); BUILD_BUG_ON(sizeof(struct minmax) < sizeof(struct minmax_sample)); @@ -8224,7 +8224,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct tcp_sock, rtt_min) + - FIELD_SIZEOF(struct minmax_sample, t)); + sizeof_field(struct minmax_sample, t)); break; case offsetof(struct bpf_sock_ops, bpf_sock_ops_cb_flags): @@ -8366,7 +8366,7 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, offsetof(struct sk_msg, data_end)); break; case offsetof(struct sk_msg_md, family): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_family) != 2); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_family) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), @@ -8377,7 +8377,7 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct sk_msg_md, remote_ip4): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_daddr) != 4); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_daddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), @@ -8388,7 +8388,7 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct sk_msg_md, local_ip4): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_rcv_saddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( @@ -8403,7 +8403,7 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, case offsetof(struct sk_msg_md, remote_ip6[0]) ... offsetof(struct sk_msg_md, remote_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_daddr.s6_addr32[0]) != 4); off = si->off; @@ -8424,7 +8424,7 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, case offsetof(struct sk_msg_md, local_ip6[0]) ... offsetof(struct sk_msg_md, local_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) != 4); off = si->off; @@ -8443,7 +8443,7 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct sk_msg_md, remote_port): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_dport) != 2); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_dport) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), @@ -8457,7 +8457,7 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct sk_msg_md, local_port): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_num) != 2); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_num) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), @@ -8847,7 +8847,7 @@ sk_reuseport_is_valid_access(int off, int size, /* Fields that allow narrowing */ case bpf_ctx_range(struct sk_reuseport_md, eth_protocol): - if (size < FIELD_SIZEOF(struct sk_buff, protocol)) + if (size < sizeof_field(struct sk_buff, protocol)) return false; /* fall through */ case bpf_ctx_range(struct sk_reuseport_md, ip_protocol): @@ -8865,7 +8865,7 @@ sk_reuseport_is_valid_access(int off, int size, *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_reuseport_kern, F), \ si->dst_reg, si->src_reg, \ bpf_target_off(struct sk_reuseport_kern, F, \ - FIELD_SIZEOF(struct sk_reuseport_kern, F), \ + sizeof_field(struct sk_reuseport_kern, F), \ target_size)); \ }) diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index d524a693e00f..2dbbb030fbed 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -599,8 +599,8 @@ __skb_flow_dissect_gre(const struct sk_buff *skb, offset += sizeof(struct gre_base_hdr); if (hdr->flags & GRE_CSUM) - offset += FIELD_SIZEOF(struct gre_full_hdr, csum) + - FIELD_SIZEOF(struct gre_full_hdr, reserved1); + offset += sizeof_field(struct gre_full_hdr, csum) + + sizeof_field(struct gre_full_hdr, reserved1); if (hdr->flags & GRE_KEY) { const __be32 *keyid; @@ -622,11 +622,11 @@ __skb_flow_dissect_gre(const struct sk_buff *skb, else key_keyid->keyid = *keyid & GRE_PPTP_KEY_MASK; } - offset += FIELD_SIZEOF(struct gre_full_hdr, key); + offset += sizeof_field(struct gre_full_hdr, key); } if (hdr->flags & GRE_SEQ) - offset += FIELD_SIZEOF(struct pptp_gre_header, seq); + offset += sizeof_field(struct pptp_gre_header, seq); if (gre_ver == 0) { if (*p_proto == htons(ETH_P_TEB)) { @@ -653,7 +653,7 @@ __skb_flow_dissect_gre(const struct sk_buff *skb, u8 *ppp_hdr; if (hdr->flags & GRE_ACK) - offset += FIELD_SIZEOF(struct pptp_gre_header, ack); + offset += sizeof_field(struct pptp_gre_header, ack); ppp_hdr = __skb_header_pointer(skb, *p_nhoff + offset, sizeof(_ppp_hdr), diff --git a/net/core/xdp.c b/net/core/xdp.c index 7c8390ad4dc6..8310714c47fd 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -36,7 +36,7 @@ static u32 xdp_mem_id_hashfn(const void *data, u32 len, u32 seed) const u32 *k = data; const u32 key = *k; - BUILD_BUG_ON(FIELD_SIZEOF(struct xdp_mem_allocator, mem.id) + BUILD_BUG_ON(sizeof_field(struct xdp_mem_allocator, mem.id) != sizeof(u32)); /* Use cyclic increasing ID as direct hash key */ @@ -56,7 +56,7 @@ static const struct rhashtable_params mem_id_rht_params = { .nelem_hint = 64, .head_offset = offsetof(struct xdp_mem_allocator, node), .key_offset = offsetof(struct xdp_mem_allocator, mem.id), - .key_len = FIELD_SIZEOF(struct xdp_mem_allocator, mem.id), + .key_len = sizeof_field(struct xdp_mem_allocator, mem.id), .max_size = MEM_ID_MAX, .min_size = 8, .automatic_shrinking = true, diff --git a/net/dccp/proto.c b/net/dccp/proto.c index a52e8ba1ced0..4af8a98fe784 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -1132,7 +1132,7 @@ static int __init dccp_init(void) int rc; BUILD_BUG_ON(sizeof(struct dccp_skb_cb) > - FIELD_SIZEOF(struct sk_buff, cb)); + sizeof_field(struct sk_buff, cb)); rc = percpu_counter_init(&dccp_orphan_count, 0, GFP_KERNEL); if (rc) goto out_fail; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 572b6307a2df..8274f98c511c 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1464,8 +1464,8 @@ static const struct nla_policy ipgre_policy[IFLA_GRE_MAX + 1] = { [IFLA_GRE_OFLAGS] = { .type = NLA_U16 }, [IFLA_GRE_IKEY] = { .type = NLA_U32 }, [IFLA_GRE_OKEY] = { .type = NLA_U32 }, - [IFLA_GRE_LOCAL] = { .len = FIELD_SIZEOF(struct iphdr, saddr) }, - [IFLA_GRE_REMOTE] = { .len = FIELD_SIZEOF(struct iphdr, daddr) }, + [IFLA_GRE_LOCAL] = { .len = sizeof_field(struct iphdr, saddr) }, + [IFLA_GRE_REMOTE] = { .len = sizeof_field(struct iphdr, daddr) }, [IFLA_GRE_TTL] = { .type = NLA_U8 }, [IFLA_GRE_TOS] = { .type = NLA_U8 }, [IFLA_GRE_PMTUDISC] = { .type = NLA_U8 }, diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index cfb025606793..9b153c7fcbb4 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -580,8 +580,8 @@ static const struct nla_policy vti_policy[IFLA_VTI_MAX + 1] = { [IFLA_VTI_LINK] = { .type = NLA_U32 }, [IFLA_VTI_IKEY] = { .type = NLA_U32 }, [IFLA_VTI_OKEY] = { .type = NLA_U32 }, - [IFLA_VTI_LOCAL] = { .len = FIELD_SIZEOF(struct iphdr, saddr) }, - [IFLA_VTI_REMOTE] = { .len = FIELD_SIZEOF(struct iphdr, daddr) }, + [IFLA_VTI_LOCAL] = { .len = sizeof_field(struct iphdr, saddr) }, + [IFLA_VTI_REMOTE] = { .len = sizeof_field(struct iphdr, daddr) }, [IFLA_VTI_FWMARK] = { .type = NLA_U32 }, }; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 8a39ee794891..3e50ac24fe41 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3949,7 +3949,7 @@ void __init tcp_init(void) BUILD_BUG_ON(TCP_MIN_SND_MSS <= MAX_TCP_OPTION_SPACE); BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > - FIELD_SIZEOF(struct sk_buff, cb)); + sizeof_field(struct sk_buff, cb)); percpu_counter_init(&tcp_sockets_allocated, 0, GFP_KERNEL); percpu_counter_init(&tcp_orphan_count, 0, GFP_KERNEL); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 923034c52ce4..9d0965252ddf 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -2170,8 +2170,8 @@ static const struct nla_policy ip6gre_policy[IFLA_GRE_MAX + 1] = { [IFLA_GRE_OFLAGS] = { .type = NLA_U16 }, [IFLA_GRE_IKEY] = { .type = NLA_U32 }, [IFLA_GRE_OKEY] = { .type = NLA_U32 }, - [IFLA_GRE_LOCAL] = { .len = FIELD_SIZEOF(struct ipv6hdr, saddr) }, - [IFLA_GRE_REMOTE] = { .len = FIELD_SIZEOF(struct ipv6hdr, daddr) }, + [IFLA_GRE_LOCAL] = { .len = sizeof_field(struct ipv6hdr, saddr) }, + [IFLA_GRE_REMOTE] = { .len = sizeof_field(struct ipv6hdr, daddr) }, [IFLA_GRE_TTL] = { .type = NLA_U8 }, [IFLA_GRE_ENCAP_LIMIT] = { .type = NLA_U8 }, [IFLA_GRE_FLOWINFO] = { .type = NLA_U32 }, diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index ebb62a4ebe30..c4bdcbc84b07 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -50,7 +50,7 @@ static struct iucv_interface *pr_iucv; static const u8 iprm_shutdown[8] = {0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01}; -#define TRGCLS_SIZE FIELD_SIZEOF(struct iucv_message, class) +#define TRGCLS_SIZE sizeof_field(struct iucv_message, class) #define __iucv_sock_wait(sk, condition, timeo, ret) \ do { \ diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 062b73a83af0..c26a5663795e 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -7595,7 +7595,7 @@ int nft_validate_register_load(enum nft_registers reg, unsigned int len) return -EINVAL; if (len == 0) return -EINVAL; - if (reg * NFT_REG32_SIZE + len > FIELD_SIZEOF(struct nft_regs, data)) + if (reg * NFT_REG32_SIZE + len > sizeof_field(struct nft_regs, data)) return -ERANGE; return 0; @@ -7643,7 +7643,7 @@ int nft_validate_register_store(const struct nft_ctx *ctx, if (len == 0) return -EINVAL; if (reg * NFT_REG32_SIZE + len > - FIELD_SIZEOF(struct nft_regs, data)) + sizeof_field(struct nft_regs, data)) return -ERANGE; if (data != NULL && type != NFT_DATA_VALUE) diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index 7525063c25f5..de3a9596b7f1 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -236,7 +236,7 @@ nfnl_cthelper_create(const struct nlattr * const tb[], nla_strlcpy(helper->name, tb[NFCTH_NAME], NF_CT_HELPER_NAME_LEN); size = ntohl(nla_get_be32(tb[NFCTH_PRIV_DATA_LEN])); - if (size > FIELD_SIZEOF(struct nf_conn_help, data)) { + if (size > sizeof_field(struct nf_conn_help, data)) { ret = -ENOMEM; goto err2; } diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 46ca8bcca1bd..faea72c2df32 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -440,12 +440,12 @@ static int nft_ct_get_init(const struct nft_ctx *ctx, switch (ctx->family) { case NFPROTO_IPV4: - len = FIELD_SIZEOF(struct nf_conntrack_tuple, + len = sizeof_field(struct nf_conntrack_tuple, src.u3.ip); break; case NFPROTO_IPV6: case NFPROTO_INET: - len = FIELD_SIZEOF(struct nf_conntrack_tuple, + len = sizeof_field(struct nf_conntrack_tuple, src.u3.ip6); break; default: @@ -457,20 +457,20 @@ static int nft_ct_get_init(const struct nft_ctx *ctx, if (tb[NFTA_CT_DIRECTION] == NULL) return -EINVAL; - len = FIELD_SIZEOF(struct nf_conntrack_tuple, src.u3.ip); + len = sizeof_field(struct nf_conntrack_tuple, src.u3.ip); break; case NFT_CT_SRC_IP6: case NFT_CT_DST_IP6: if (tb[NFTA_CT_DIRECTION] == NULL) return -EINVAL; - len = FIELD_SIZEOF(struct nf_conntrack_tuple, src.u3.ip6); + len = sizeof_field(struct nf_conntrack_tuple, src.u3.ip6); break; case NFT_CT_PROTO_SRC: case NFT_CT_PROTO_DST: if (tb[NFTA_CT_DIRECTION] == NULL) return -EINVAL; - len = FIELD_SIZEOF(struct nf_conntrack_tuple, src.u.all); + len = sizeof_field(struct nf_conntrack_tuple, src.u.all); break; case NFT_CT_BYTES: case NFT_CT_PKTS: @@ -551,7 +551,7 @@ static int nft_ct_set_init(const struct nft_ctx *ctx, case NFT_CT_MARK: if (tb[NFTA_CT_DIRECTION]) return -EINVAL; - len = FIELD_SIZEOF(struct nf_conn, mark); + len = sizeof_field(struct nf_conn, mark); break; #endif #ifdef CONFIG_NF_CONNTRACK_LABELS diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c index 39dc94f2491e..bc9fd98c5d6d 100644 --- a/net/netfilter/nft_masq.c +++ b/net/netfilter/nft_masq.c @@ -43,7 +43,7 @@ static int nft_masq_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { - u32 plen = FIELD_SIZEOF(struct nf_nat_range, min_addr.all); + u32 plen = sizeof_field(struct nf_nat_range, min_addr.all); struct nft_masq *priv = nft_expr_priv(expr); int err; diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index c3c93e95b46e..8b44a4de5329 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -141,10 +141,10 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, switch (family) { case NFPROTO_IPV4: - alen = FIELD_SIZEOF(struct nf_nat_range, min_addr.ip); + alen = sizeof_field(struct nf_nat_range, min_addr.ip); break; case NFPROTO_IPV6: - alen = FIELD_SIZEOF(struct nf_nat_range, min_addr.ip6); + alen = sizeof_field(struct nf_nat_range, min_addr.ip6); break; default: return -EAFNOSUPPORT; @@ -171,7 +171,7 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, } } - plen = FIELD_SIZEOF(struct nf_nat_range, min_addr.all); + plen = sizeof_field(struct nf_nat_range, min_addr.all); if (tb[NFTA_NAT_REG_PROTO_MIN]) { priv->sreg_proto_min = nft_parse_register(tb[NFTA_NAT_REG_PROTO_MIN]); diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c index 43eeb1f609f1..5b779171565c 100644 --- a/net/netfilter/nft_redir.c +++ b/net/netfilter/nft_redir.c @@ -48,7 +48,7 @@ static int nft_redir_init(const struct nft_ctx *ctx, unsigned int plen; int err; - plen = FIELD_SIZEOF(struct nf_nat_range, min_addr.all); + plen = sizeof_field(struct nf_nat_range, min_addr.all); if (tb[NFTA_REDIR_REG_PROTO_MIN]) { priv->sreg_proto_min = nft_parse_register(tb[NFTA_REDIR_REG_PROTO_MIN]); diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c index f92a82c73880..4c33dfc9dab5 100644 --- a/net/netfilter/nft_tproxy.c +++ b/net/netfilter/nft_tproxy.c @@ -218,14 +218,14 @@ static int nft_tproxy_init(const struct nft_ctx *ctx, switch (priv->family) { case NFPROTO_IPV4: - alen = FIELD_SIZEOF(union nf_inet_addr, in); + alen = sizeof_field(union nf_inet_addr, in); err = nf_defrag_ipv4_enable(ctx->net); if (err) return err; break; #if IS_ENABLED(CONFIG_NF_TABLES_IPV6) case NFPROTO_IPV6: - alen = FIELD_SIZEOF(union nf_inet_addr, in6); + alen = sizeof_field(union nf_inet_addr, in6); err = nf_defrag_ipv6_enable(ctx->net); if (err) return err; diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c index 2236455b10a3..37253d399c6b 100644 --- a/net/netfilter/xt_RATEEST.c +++ b/net/netfilter/xt_RATEEST.c @@ -30,7 +30,7 @@ static unsigned int jhash_rnd __read_mostly; static unsigned int xt_rateest_hash(const char *name) { - return jhash(name, FIELD_SIZEOF(struct xt_rateest, name), jhash_rnd) & + return jhash(name, sizeof_field(struct xt_rateest, name), jhash_rnd) & (RATEEST_HSIZE - 1); } diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 90b2ab9dd449..4e31721e7293 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2755,7 +2755,7 @@ static int __init netlink_proto_init(void) if (err != 0) goto out; - BUILD_BUG_ON(sizeof(struct netlink_skb_parms) > FIELD_SIZEOF(struct sk_buff, cb)); + BUILD_BUG_ON(sizeof(struct netlink_skb_parms) > sizeof_field(struct sk_buff, cb)); nl_table = kcalloc(MAX_LINKS, sizeof(*nl_table), GFP_KERNEL); if (!nl_table) diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 1047e8043084..e3a37d22539c 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -2497,7 +2497,7 @@ static int __init dp_init(void) { int err; - BUILD_BUG_ON(sizeof(struct ovs_skb_cb) > FIELD_SIZEOF(struct sk_buff, cb)); + BUILD_BUG_ON(sizeof(struct ovs_skb_cb) > sizeof_field(struct sk_buff, cb)); pr_info("Open vSwitch switching datapath\n"); diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h index fd8ed766bdd1..758a8c77f736 100644 --- a/net/openvswitch/flow.h +++ b/net/openvswitch/flow.h @@ -37,7 +37,7 @@ enum sw_flow_mac_proto { * matching for small options. */ #define TUN_METADATA_OFFSET(opt_len) \ - (FIELD_SIZEOF(struct sw_flow_key, tun_opts) - opt_len) + (sizeof_field(struct sw_flow_key, tun_opts) - opt_len) #define TUN_METADATA_OPTS(flow_key, opt_len) \ ((void *)((flow_key)->tun_opts + TUN_METADATA_OFFSET(opt_len))) @@ -52,7 +52,7 @@ struct vlan_head { #define OVS_SW_FLOW_KEY_METADATA_SIZE \ (offsetof(struct sw_flow_key, recirc_id) + \ - FIELD_SIZEOF(struct sw_flow_key, recirc_id)) + sizeof_field(struct sw_flow_key, recirc_id)) struct ovs_key_nsh { struct ovs_nsh_key_base base; diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index d72ddb67bb74..9d3c4d2d893a 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -972,7 +972,7 @@ static int __init af_rxrpc_init(void) int ret = -1; unsigned int tmp; - BUILD_BUG_ON(sizeof(struct rxrpc_skb_priv) > FIELD_SIZEOF(struct sk_buff, cb)); + BUILD_BUG_ON(sizeof(struct rxrpc_skb_priv) > sizeof_field(struct sk_buff, cb)); get_random_bytes(&tmp, sizeof(tmp)); tmp &= 0x3fffffff; diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index bf2d69335d4b..f685c0d73708 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -312,7 +312,7 @@ static void tcf_ct_act_set_labels(struct nf_conn *ct, u32 *labels_m) { #if IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) - size_t labels_sz = FIELD_SIZEOF(struct tcf_ct_params, labels); + size_t labels_sz = sizeof_field(struct tcf_ct_params, labels); if (!memchr_inv(labels_m, 0, labels_sz)) return; @@ -936,7 +936,7 @@ static struct tc_action_ops act_ct_ops = { static __net_init int ct_init_net(struct net *net) { - unsigned int n_bits = FIELD_SIZEOF(struct tcf_ct_params, labels) * 8; + unsigned int n_bits = sizeof_field(struct tcf_ct_params, labels) * 8; struct tc_ct_action_net *tn = net_generic(net, ct_net_id); if (nf_connlabels_get(net, n_bits - 1)) { diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 6c68971d99df..0d125de54285 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1481,7 +1481,7 @@ static int fl_init_mask_hashtable(struct fl_flow_mask *mask) } #define FL_KEY_MEMBER_OFFSET(member) offsetof(struct fl_flow_key, member) -#define FL_KEY_MEMBER_SIZE(member) FIELD_SIZEOF(struct fl_flow_key, member) +#define FL_KEY_MEMBER_SIZE(member) sizeof_field(struct fl_flow_key, member) #define FL_KEY_IS_MASKED(mask, member) \ memchr_inv(((char *)mask) + FL_KEY_MEMBER_OFFSET(member), \ diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 7cfdce10de36..774babbee045 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2865,7 +2865,7 @@ static int __init af_unix_init(void) { int rc = -1; - BUILD_BUG_ON(sizeof(struct unix_skb_parms) > FIELD_SIZEOF(struct sk_buff, cb)); + BUILD_BUG_ON(sizeof(struct unix_skb_parms) > sizeof_field(struct sk_buff, cb)); rc = proto_register(&unix_proto, 1); if (rc != 0) { diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c index f19a895ad7cd..ef8dfd47c7e3 100644 --- a/security/integrity/ima/ima_policy.c +++ b/security/integrity/ima/ima_policy.c @@ -45,7 +45,7 @@ #define DONT_HASH 0x0200 #define INVALID_PCR(a) (((a) < 0) || \ - (a) >= (FIELD_SIZEOF(struct integrity_iint_cache, measured_pcrs) * 8)) + (a) >= (sizeof_field(struct integrity_iint_cache, measured_pcrs) * 8)) int ima_policy_flag; static int temp_ima_appraise; @@ -274,7 +274,7 @@ static struct ima_rule_entry *ima_lsm_copy_rule(struct ima_rule_entry *entry) * lsm rules can change */ memcpy(nentry, entry, sizeof(*nentry)); - memset(nentry->lsm, 0, FIELD_SIZEOF(struct ima_rule_entry, lsm)); + memset(nentry->lsm, 0, sizeof_field(struct ima_rule_entry, lsm)); for (i = 0; i < MAX_LSM_RULES; i++) { if (!entry->lsm[i].rule) diff --git a/sound/soc/codecs/hdmi-codec.c b/sound/soc/codecs/hdmi-codec.c index f8b5b960e597..4eaa2b5b20a5 100644 --- a/sound/soc/codecs/hdmi-codec.c +++ b/sound/soc/codecs/hdmi-codec.c @@ -292,7 +292,7 @@ static int hdmi_eld_ctl_info(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_info *uinfo) { uinfo->type = SNDRV_CTL_ELEM_TYPE_BYTES; - uinfo->count = FIELD_SIZEOF(struct hdmi_codec_priv, eld); + uinfo->count = sizeof_field(struct hdmi_codec_priv, eld); return 0; } -- cgit v1.2.3 From af74262337faa65d5ac2944553437d3f5fb29123 Mon Sep 17 00:00:00 2001 From: Steven Rostedt (VMware) Date: Mon, 9 Dec 2019 10:33:30 -0500 Subject: module: Remove accidental change of module_enable_x() When pulling in Divya Indi's patch, I made a minor fix to remove unneeded braces. I commited my fix up via "git commit -a --amend". Unfortunately, I didn't realize I had some changes I was testing in the module code, and those changes were applied to Divya's patch as well. This reverts the accidental updates to the module code. Cc: Jessica Yu Cc: Divya Indi Reported-by: Peter Zijlstra Fixes: e585e6469d6f ("tracing: Verify if trace array exists before destroying it.") Signed-off-by: Steven Rostedt (VMware) --- kernel/module.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/module.c b/kernel/module.c index 6e2fd40a6ed9..ff2d7359a418 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -3728,6 +3728,7 @@ static int complete_formation(struct module *mod, struct load_info *info) module_enable_ro(mod, false); module_enable_nx(mod); + module_enable_x(mod); /* Mark state as coming so strong_try_module_get() ignores us, * but kallsyms etc. can see us. */ @@ -3750,11 +3751,6 @@ static int prepare_coming_module(struct module *mod) if (err) return err; - /* Make module executable after ftrace is enabled */ - mutex_lock(&module_mutex); - module_enable_x(mod); - mutex_unlock(&module_mutex); - blocking_notifier_call_chain(&module_notify_list, MODULE_STATE_COMING, mod); return 0; -- cgit v1.2.3 From a61f810567be0ef101d8bbb65b89ffeac7d62103 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Sat, 7 Dec 2019 11:44:09 +0800 Subject: tracing: remove set but not used variable 'buffer' kernel/trace/trace_events_inject.c: In function trace_inject_entry: kernel/trace/trace_events_inject.c:20:22: warning: variable buffer set but not used [-Wunused-but-set-variable] It is never used, so remove it. Link: http://lkml.kernel.org/r/20191207034409.25668-1-yuehaibing@huawei.com Reported-by: Hulk Robot Acked-by: Cong Wang Signed-off-by: YueHaibing Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_events_inject.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_events_inject.c b/kernel/trace/trace_events_inject.c index d43710718ee5..d45079ee62f8 100644 --- a/kernel/trace/trace_events_inject.c +++ b/kernel/trace/trace_events_inject.c @@ -17,12 +17,10 @@ static int trace_inject_entry(struct trace_event_file *file, void *rec, int len) { struct trace_event_buffer fbuffer; - struct ring_buffer *buffer; int written = 0; void *entry; rcu_read_lock_sched(); - buffer = file->tr->trace_buffer.buffer; entry = trace_event_buffer_reserve(&fbuffer, file, len); if (entry) { memcpy(entry, rec, len); -- cgit v1.2.3 From ff205766dbbee024a4a716638868d98ffb17748a Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Sun, 8 Dec 2019 16:01:12 -0800 Subject: ftrace: Fix function_graph tracer interaction with BPF trampoline Depending on type of BPF programs served by BPF trampoline it can call original function. In such case the trampoline will skip one stack frame while returning. That will confuse function_graph tracer and will cause crashes with bad RIP. Teach graph tracer to skip functions that have BPF trampoline attached. Signed-off-by: Alexei Starovoitov Signed-off-by: Steven Rostedt (VMware) --- arch/x86/kernel/ftrace.c | 14 -------------- include/linux/ftrace.h | 5 +++++ kernel/trace/fgraph.c | 9 +++++++++ kernel/trace/ftrace.c | 19 +++++++------------ 4 files changed, 21 insertions(+), 26 deletions(-) (limited to 'kernel') diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 060a361d9d11..024c3053dbba 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -1042,20 +1042,6 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, if (unlikely(atomic_read(¤t->tracing_graph_pause))) return; - /* - * If the return location is actually pointing directly to - * the start of a direct trampoline (if we trace the trampoline - * it will still be offset by MCOUNT_INSN_SIZE), then the - * return address is actually off by one word, and we - * need to adjust for that. - */ - if (ftrace_direct_func_count) { - if (ftrace_find_direct_func(self_addr + MCOUNT_INSN_SIZE)) { - self_addr = *parent; - parent++; - } - } - /* * Protect against fault, even if it shouldn't * happen. This tool is too much intrusive to diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 232806d5689d..987c2dc55bde 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -264,6 +264,7 @@ int ftrace_modify_direct_caller(struct ftrace_func_entry *entry, struct dyn_ftrace *rec, unsigned long old_addr, unsigned long new_addr); +unsigned long ftrace_find_rec_direct(unsigned long ip); #else # define ftrace_direct_func_count 0 static inline int register_ftrace_direct(unsigned long ip, unsigned long addr) @@ -290,6 +291,10 @@ static inline int ftrace_modify_direct_caller(struct ftrace_func_entry *entry, { return -ENODEV; } +static inline unsigned long ftrace_find_rec_direct(unsigned long ip) +{ + return 0; +} #endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ #ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index 67e0c462b059..a2659735db73 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -101,6 +101,15 @@ int function_graph_enter(unsigned long ret, unsigned long func, { struct ftrace_graph_ent trace; + /* + * Skip graph tracing if the return location is served by direct trampoline, + * since call sequence and return addresses is unpredicatable anymore. + * Ex: BPF trampoline may call original function and may skip frame + * depending on type of BPF programs attached. + */ + if (ftrace_direct_func_count && + ftrace_find_rec_direct(ret - MCOUNT_INSN_SIZE)) + return -EBUSY; trace.func = func; trace.depth = ++current->curr_ret_depth; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index caae523f4ef3..57477dc683db 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -2364,7 +2364,7 @@ int ftrace_direct_func_count; * Search the direct_functions hash to see if the given instruction pointer * has a direct caller attached to it. */ -static unsigned long find_rec_direct(unsigned long ip) +unsigned long ftrace_find_rec_direct(unsigned long ip) { struct ftrace_func_entry *entry; @@ -2380,7 +2380,7 @@ static void call_direct_funcs(unsigned long ip, unsigned long pip, { unsigned long addr; - addr = find_rec_direct(ip); + addr = ftrace_find_rec_direct(ip); if (!addr) return; @@ -2393,11 +2393,6 @@ struct ftrace_ops direct_ops = { | FTRACE_OPS_FL_DIRECT | FTRACE_OPS_FL_SAVE_REGS | FTRACE_OPS_FL_PERMANENT, }; -#else -static inline unsigned long find_rec_direct(unsigned long ip) -{ - return 0; -} #endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ /** @@ -2417,7 +2412,7 @@ unsigned long ftrace_get_addr_new(struct dyn_ftrace *rec) if ((rec->flags & FTRACE_FL_DIRECT) && (ftrace_rec_count(rec) == 1)) { - addr = find_rec_direct(rec->ip); + addr = ftrace_find_rec_direct(rec->ip); if (addr) return addr; WARN_ON_ONCE(1); @@ -2458,7 +2453,7 @@ unsigned long ftrace_get_addr_curr(struct dyn_ftrace *rec) /* Direct calls take precedence over trampolines */ if (rec->flags & FTRACE_FL_DIRECT_EN) { - addr = find_rec_direct(rec->ip); + addr = ftrace_find_rec_direct(rec->ip); if (addr) return addr; WARN_ON_ONCE(1); @@ -3604,7 +3599,7 @@ static int t_show(struct seq_file *m, void *v) if (rec->flags & FTRACE_FL_DIRECT) { unsigned long direct; - direct = find_rec_direct(rec->ip); + direct = ftrace_find_rec_direct(rec->ip); if (direct) seq_printf(m, "\n\tdirect-->%pS", (void *)direct); } @@ -5008,7 +5003,7 @@ int register_ftrace_direct(unsigned long ip, unsigned long addr) mutex_lock(&direct_mutex); /* See if there's a direct function at @ip already */ - if (find_rec_direct(ip)) + if (ftrace_find_rec_direct(ip)) goto out_unlock; ret = -ENODEV; @@ -5027,7 +5022,7 @@ int register_ftrace_direct(unsigned long ip, unsigned long addr) if (ip != rec->ip) { ip = rec->ip; /* Need to check this ip for a direct. */ - if (find_rec_direct(ip)) + if (ftrace_find_rec_direct(ip)) goto out_unlock; } -- cgit v1.2.3 From c571b72e2b845ca0519670cb7c4b5fe5f56498a5 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Tue, 10 Dec 2019 14:05:23 -0800 Subject: Revert "locking/mutex: Complain upon mutex API misuse in IRQ contexts" This ended up causing some noise in places such as rxrpc running in softirq. The warning is misleading in this case as the mutex trylock and unlock operations are done within the same context; and therefore we need not worry about the PI-boosting issues that comes along with no single-owner lock guarantees. While we don't want to support this in mutexes, there is no way out of this yet; so lets get rid of the WARNs for now, as it is only fair to code that has historically relied on non-preemptible softirq guarantees. In addition, changing the lock type is also unviable: exclusive rwsems have the same issue (just not the WARN_ON) and counting semaphores would introduce a performance hit as mutexes are a lot more optimized. This reverts: a0855d24fc22: ("locking/mutex: Complain upon mutex API misuse in IRQ contexts") Fixes: a0855d24fc22: ("locking/mutex: Complain upon mutex API misuse in IRQ contexts") Signed-off-by: Davidlohr Bueso Tested-by: David Howells Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-afs@lists.infradead.org Cc: linux-fsdevel@vger.kernel.org Cc: will@kernel.org Link: https://lkml.kernel.org/r/20191210220523.28540-1-dave@stgolabs.net Signed-off-by: Ingo Molnar --- kernel/locking/mutex.c | 4 ---- 1 file changed, 4 deletions(-) (limited to 'kernel') diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index 54cc5f9286e9..5352ce50a97e 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -733,9 +733,6 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne */ void __sched mutex_unlock(struct mutex *lock) { -#ifdef CONFIG_DEBUG_MUTEXES - WARN_ON(in_interrupt()); -#endif #ifndef CONFIG_DEBUG_LOCK_ALLOC if (__mutex_unlock_fast(lock)) return; @@ -1416,7 +1413,6 @@ int __sched mutex_trylock(struct mutex *lock) #ifdef CONFIG_DEBUG_MUTEXES DEBUG_LOCKS_WARN_ON(lock->magic != lock); - WARN_ON(in_interrupt()); #endif locked = __mutex_trylock(lock); -- cgit v1.2.3 From 4c80c7bc583a87ded5f61906f81256b57c795806 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 10 Dec 2019 21:35:46 +0100 Subject: bpf: Fix build in minimal configurations, again Building with -Werror showed another failure: kernel/bpf/btf.c: In function 'btf_get_prog_ctx_type.isra.31': kernel/bpf/btf.c:3508:63: error: array subscript 0 is above array bounds of 'u8[0]' {aka 'unsigned char[0]'} [-Werror=array-bounds] ctx_type = btf_type_member(conv_struct) + bpf_ctx_convert_map[prog_type] * 2; I don't actually understand why the array is empty, but a similar fix has addressed a related problem, so I suppose we can do the same thing here. Fixes: ce27709b8162 ("bpf: Fix build in minimal configurations") Signed-off-by: Arnd Bergmann Signed-off-by: Daniel Borkmann Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20191210203553.2941035-1-arnd@arndb.de --- kernel/bpf/btf.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 7d40da240891..ed2075884724 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3470,6 +3470,7 @@ static u8 bpf_ctx_convert_map[] = { [_id] = __ctx_convert##_id, #include #undef BPF_PROG_TYPE + 0, /* avoid empty array */ }; #undef BPF_MAP_TYPE -- cgit v1.2.3 From b91e014f078e2e4f24778680e28dbbdecc7f0eb9 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Sun, 8 Dec 2019 16:01:13 -0800 Subject: bpf: Make BPF trampoline use register_ftrace_direct() API Make BPF trampoline attach its generated assembly code to kernel functions via register_ftrace_direct() API. It helps ftrace-based tracers co-exist with BPF trampoline on the same kernel function. It also switches attaching logic from arch specific text_poke to generic ftrace that is available on many architectures. text_poke is still necessary for bpf-to-bpf attach and for bpf_tail_call optimization. Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20191209000114.1876138-3-ast@kernel.org --- include/linux/bpf.h | 1 + kernel/bpf/trampoline.c | 64 ++++++++++++++++++++++++++++++++++++++++++++----- 2 files changed, 59 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 35903f148be5..ac7de5291509 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -461,6 +461,7 @@ struct bpf_trampoline { struct { struct btf_func_model model; void *addr; + bool ftrace_managed; } func; /* list of BPF programs using this trampoline */ struct hlist_head progs_hlist[BPF_TRAMP_MAX]; diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index 7e89f1f49d77..23b0d5cfd47e 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -3,6 +3,7 @@ #include #include #include +#include /* btf_vmlinux has ~22k attachable functions. 1k htab is enough. */ #define TRAMPOLINE_HASH_BITS 10 @@ -59,6 +60,60 @@ out: return tr; } +static int is_ftrace_location(void *ip) +{ + long addr; + + addr = ftrace_location((long)ip); + if (!addr) + return 0; + if (WARN_ON_ONCE(addr != (long)ip)) + return -EFAULT; + return 1; +} + +static int unregister_fentry(struct bpf_trampoline *tr, void *old_addr) +{ + void *ip = tr->func.addr; + int ret; + + if (tr->func.ftrace_managed) + ret = unregister_ftrace_direct((long)ip, (long)old_addr); + else + ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, old_addr, NULL); + return ret; +} + +static int modify_fentry(struct bpf_trampoline *tr, void *old_addr, void *new_addr) +{ + void *ip = tr->func.addr; + int ret; + + if (tr->func.ftrace_managed) + ret = modify_ftrace_direct((long)ip, (long)old_addr, (long)new_addr); + else + ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, old_addr, new_addr); + return ret; +} + +/* first time registering */ +static int register_fentry(struct bpf_trampoline *tr, void *new_addr) +{ + void *ip = tr->func.addr; + int ret; + + ret = is_ftrace_location(ip); + if (ret < 0) + return ret; + tr->func.ftrace_managed = ret; + + if (tr->func.ftrace_managed) + ret = register_ftrace_direct((long)ip, (long)new_addr); + else + ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, NULL, new_addr); + return ret; +} + /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50 * bytes on x86. Pick a number to fit into PAGE_SIZE / 2 */ @@ -77,8 +132,7 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr) int err; if (fentry_cnt + fexit_cnt == 0) { - err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_CALL, - old_image, NULL); + err = unregister_fentry(tr, old_image); tr->selector = 0; goto out; } @@ -105,12 +159,10 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr) if (tr->selector) /* progs already running at this address */ - err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_CALL, - old_image, new_image); + err = modify_fentry(tr, old_image, new_image); else /* first time registering */ - err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_CALL, NULL, - new_image); + err = register_fentry(tr, new_image); if (err) goto out; tr->selector++; -- cgit v1.2.3 From 85572c2c4a45a541e880e087b5b17a48198b2416 Mon Sep 17 00:00:00 2001 From: Rafael J. Wysocki Date: Wed, 11 Dec 2019 11:28:41 +0100 Subject: cpufreq: Avoid leaving stale IRQ work items during CPU offline The scheduler code calling cpufreq_update_util() may run during CPU offline on the target CPU after the IRQ work lists have been flushed for it, so the target CPU should be prevented from running code that may queue up an IRQ work item on it at that point. Unfortunately, that may not be the case if dvfs_possible_from_any_cpu is set for at least one cpufreq policy in the system, because that allows the CPU going offline to run the utilization update callback of the cpufreq governor on behalf of another (online) CPU in some cases. If that happens, the cpufreq governor callback may queue up an IRQ work on the CPU running it, which is going offline, and the IRQ work may not be flushed after that point. Moreover, that IRQ work cannot be flushed until the "offlining" CPU goes back online, so if any other CPU calls irq_work_sync() to wait for the completion of that IRQ work, it will have to wait until the "offlining" CPU is back online and that may not happen forever. In particular, a system-wide deadlock may occur during CPU online as a result of that. The failing scenario is as follows. CPU0 is the boot CPU, so it creates a cpufreq policy and becomes the "leader" of it (policy->cpu). It cannot go offline, because it is the boot CPU. Next, other CPUs join the cpufreq policy as they go online and they leave it when they go offline. The last CPU to go offline, say CPU3, may queue up an IRQ work while running the governor callback on behalf of CPU0 after leaving the cpufreq policy because of the dvfs_possible_from_any_cpu effect described above. Then, CPU0 is the only online CPU in the system and the stale IRQ work is still queued on CPU3. When, say, CPU1 goes back online, it will run irq_work_sync() to wait for that IRQ work to complete and so it will wait for CPU3 to go back online (which may never happen even in principle), but (worse yet) CPU0 is waiting for CPU1 at that point too and a system-wide deadlock occurs. To address this problem notice that CPUs which cannot run cpufreq utilization update code for themselves (for example, because they have left the cpufreq policies that they belonged to), should also be prevented from running that code on behalf of the other CPUs that belong to a cpufreq policy with dvfs_possible_from_any_cpu set and so in that case the cpufreq_update_util_data pointer of the CPU running the code must not be NULL as well as for the CPU which is the target of the cpufreq utilization update in progress. Accordingly, change cpufreq_this_cpu_can_update() into a regular function in kernel/sched/cpufreq.c (instead of a static inline in a header file) and make it check the cpufreq_update_util_data pointer of the local CPU if dvfs_possible_from_any_cpu is set for the target cpufreq policy. Also update the schedutil governor to do the cpufreq_this_cpu_can_update() check in the non-fast-switch case too to avoid the stale IRQ work issues. Fixes: 99d14d0e16fa ("cpufreq: Process remote callbacks from any CPU if the platform permits") Link: https://lore.kernel.org/linux-pm/20191121093557.bycvdo4xyinbc5cb@vireshk-i7/ Reported-by: Anson Huang Tested-by: Anson Huang Cc: 4.14+ # 4.14+ Signed-off-by: Rafael J. Wysocki Acked-by: Viresh Kumar Tested-by: Peng Fan (i.MX8QXP-MEK) Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 11 ----------- include/linux/sched/cpufreq.h | 3 +++ kernel/sched/cpufreq.c | 18 ++++++++++++++++++ kernel/sched/cpufreq_schedutil.c | 8 +++----- 4 files changed, 24 insertions(+), 16 deletions(-) (limited to 'kernel') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 92d5fdc8154e..31b1b0e03df8 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -595,17 +595,6 @@ struct governor_attr { size_t count); }; -static inline bool cpufreq_this_cpu_can_update(struct cpufreq_policy *policy) -{ - /* - * Allow remote callbacks if: - * - dvfs_possible_from_any_cpu flag is set - * - the local and remote CPUs share cpufreq policy - */ - return policy->dvfs_possible_from_any_cpu || - cpumask_test_cpu(smp_processor_id(), policy->cpus); -} - /********************************************************************* * FREQUENCY TABLE HELPERS * *********************************************************************/ diff --git a/include/linux/sched/cpufreq.h b/include/linux/sched/cpufreq.h index afa940cd50dc..cc6bcc1e96bc 100644 --- a/include/linux/sched/cpufreq.h +++ b/include/linux/sched/cpufreq.h @@ -12,6 +12,8 @@ #define SCHED_CPUFREQ_MIGRATION (1U << 1) #ifdef CONFIG_CPU_FREQ +struct cpufreq_policy; + struct update_util_data { void (*func)(struct update_util_data *data, u64 time, unsigned int flags); }; @@ -20,6 +22,7 @@ void cpufreq_add_update_util_hook(int cpu, struct update_util_data *data, void (*func)(struct update_util_data *data, u64 time, unsigned int flags)); void cpufreq_remove_update_util_hook(int cpu); +bool cpufreq_this_cpu_can_update(struct cpufreq_policy *policy); static inline unsigned long map_util_freq(unsigned long util, unsigned long freq, unsigned long cap) diff --git a/kernel/sched/cpufreq.c b/kernel/sched/cpufreq.c index b5dcd1d83c7f..7c2fe50fd76d 100644 --- a/kernel/sched/cpufreq.c +++ b/kernel/sched/cpufreq.c @@ -5,6 +5,8 @@ * Copyright (C) 2016, Intel Corporation * Author: Rafael J. Wysocki */ +#include + #include "sched.h" DEFINE_PER_CPU(struct update_util_data __rcu *, cpufreq_update_util_data); @@ -57,3 +59,19 @@ void cpufreq_remove_update_util_hook(int cpu) rcu_assign_pointer(per_cpu(cpufreq_update_util_data, cpu), NULL); } EXPORT_SYMBOL_GPL(cpufreq_remove_update_util_hook); + +/** + * cpufreq_this_cpu_can_update - Check if cpufreq policy can be updated. + * @policy: cpufreq policy to check. + * + * Return 'true' if: + * - the local and remote CPUs share @policy, + * - dvfs_possible_from_any_cpu is set in @policy and the local CPU is not going + * offline (in which case it is not expected to run cpufreq updates any more). + */ +bool cpufreq_this_cpu_can_update(struct cpufreq_policy *policy) +{ + return cpumask_test_cpu(smp_processor_id(), policy->cpus) || + (policy->dvfs_possible_from_any_cpu && + rcu_dereference_sched(*this_cpu_ptr(&cpufreq_update_util_data))); +} diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 322ca8860f54..9b8916fd00a2 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -82,12 +82,10 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time) * by the hardware, as calculating the frequency is pointless if * we cannot in fact act on it. * - * For the slow switching platforms, the kthread is always scheduled on - * the right set of CPUs and any CPU can find the next frequency and - * schedule the kthread. + * This is needed on the slow switching platforms too to prevent CPUs + * going offline from leaving stale IRQ work items behind. */ - if (sg_policy->policy->fast_switch_enabled && - !cpufreq_this_cpu_can_update(sg_policy->policy)) + if (!cpufreq_this_cpu_can_update(sg_policy->policy)) return false; if (unlikely(sg_policy->limits_changed)) { -- cgit v1.2.3 From a2ea07465c8d7984cc6b8b1f0b3324f9b138094a Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 16 Dec 2019 17:49:00 +0100 Subject: bpf: Fix missing prog untrack in release_maps Commit da765a2f5993 ("bpf: Add poke dependency tracking for prog array maps") wrongly assumed that in case of prog load errors, we're cleaning up all program tracking via bpf_free_used_maps(). However, it can happen that we're still at the point where we didn't copy map pointers into the prog's aux section such that env->prog->aux->used_maps is still zero, running into a UAF. In such case, the verifier has similar release_maps() helper that drops references to used maps from its env. Consolidate the release code into __bpf_free_used_maps() and call it from all sides to fix it. Fixes: da765a2f5993 ("bpf: Add poke dependency tracking for prog array maps") Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/1c2909484ca524ae9f55109b06f22b6213e76376.1576514756.git.daniel@iogearbox.net --- include/linux/bpf.h | 2 ++ kernel/bpf/core.c | 14 ++++++++++---- kernel/bpf/verifier.c | 14 ++------------ 3 files changed, 14 insertions(+), 16 deletions(-) (limited to 'kernel') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index ac7de5291509..085a59afba85 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -818,6 +818,8 @@ struct bpf_prog * __must_check bpf_prog_inc_not_zero(struct bpf_prog *prog); void bpf_prog_put(struct bpf_prog *prog); int __bpf_prog_charge(struct user_struct *user, u32 pages); void __bpf_prog_uncharge(struct user_struct *user, u32 pages); +void __bpf_free_used_maps(struct bpf_prog_aux *aux, + struct bpf_map **used_maps, u32 len); void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock); void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 49e32acad7d8..6231858df723 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2048,18 +2048,24 @@ static void bpf_free_cgroup_storage(struct bpf_prog_aux *aux) } } -static void bpf_free_used_maps(struct bpf_prog_aux *aux) +void __bpf_free_used_maps(struct bpf_prog_aux *aux, + struct bpf_map **used_maps, u32 len) { struct bpf_map *map; - int i; + u32 i; bpf_free_cgroup_storage(aux); - for (i = 0; i < aux->used_map_cnt; i++) { - map = aux->used_maps[i]; + for (i = 0; i < len; i++) { + map = used_maps[i]; if (map->ops->map_poke_untrack) map->ops->map_poke_untrack(map, aux); bpf_map_put(map); } +} + +static void bpf_free_used_maps(struct bpf_prog_aux *aux) +{ + __bpf_free_used_maps(aux, aux->used_maps, aux->used_map_cnt); kfree(aux->used_maps); } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 034ef81f935b..a1acdce77070 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -8298,18 +8298,8 @@ next_insn: /* drop refcnt of maps used by the rejected program */ static void release_maps(struct bpf_verifier_env *env) { - enum bpf_cgroup_storage_type stype; - int i; - - for_each_cgroup_storage_type(stype) { - if (!env->prog->aux->cgroup_storage[stype]) - continue; - bpf_cgroup_storage_release(env->prog, - env->prog->aux->cgroup_storage[stype]); - } - - for (i = 0; i < env->used_map_cnt; i++) - bpf_map_put(env->used_maps[i]); + __bpf_free_used_maps(env->prog->aux, env->used_maps, + env->used_map_cnt); } /* convert pseudo BPF_LD_IMM64 into generic BPF_LD_IMM64 */ -- cgit v1.2.3 From 9f0bff1180efc9ea988fed3fd93da7647151ac8b Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Tue, 19 Nov 2019 13:14:29 +0100 Subject: perf/core: Add SRCU annotation for pmus list walk Since commit 28875945ba98d ("rcu: Add support for consolidated-RCU reader checking") there is an additional check to ensure that a RCU related lock is held while the RCU list is iterated. This section holds the SRCU reader lock instead. Add annotation to list_for_each_entry_rcu() that pmus_srcu must be acquired during the list traversal. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Joel Fernandes (Google) Link: https://lkml.kernel.org/r/20191119121429.zhcubzdhm672zasg@linutronix.de --- kernel/events/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/events/core.c b/kernel/events/core.c index 4ff86d57f9e5..a1f8bde19b56 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -10523,7 +10523,7 @@ again: goto unlock; } - list_for_each_entry_rcu(pmu, &pmus, entry) { + list_for_each_entry_rcu(pmu, &pmus, entry, lockdep_is_held(&pmus_srcu)) { ret = perf_try_init_event(pmu, event); if (!ret) goto unlock; -- cgit v1.2.3 From 3dfbe25c27eab7c90c8a7e97b4c354a9d24dd985 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Tue, 3 Dec 2019 13:35:23 -0500 Subject: sched/psi: Fix sampling error and rare div0 crashes with cgroups and high uptime Jingfeng reports rare div0 crashes in psi on systems with some uptime: [58914.066423] divide error: 0000 [#1] SMP [58914.070416] Modules linked in: ipmi_poweroff ipmi_watchdog toa overlay fuse tcp_diag inet_diag binfmt_misc aisqos(O) aisqos_hotfixes(O) [58914.083158] CPU: 94 PID: 140364 Comm: kworker/94:2 Tainted: G W OE K 4.9.151-015.ali3000.alios7.x86_64 #1 [58914.093722] Hardware name: Alibaba Alibaba Cloud ECS/Alibaba Cloud ECS, BIOS 3.23.34 02/14/2019 [58914.102728] Workqueue: events psi_update_work [58914.107258] task: ffff8879da83c280 task.stack: ffffc90059dcc000 [58914.113336] RIP: 0010:[] [] psi_update_stats+0x1c1/0x330 [58914.122183] RSP: 0018:ffffc90059dcfd60 EFLAGS: 00010246 [58914.127650] RAX: 0000000000000000 RBX: ffff8858fe98be50 RCX: 000000007744d640 [58914.134947] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 00003594f700648e [58914.142243] RBP: ffffc90059dcfdf8 R08: 0000359500000000 R09: 0000000000000000 [58914.149538] R10: 0000000000000000 R11: 0000000000000000 R12: 0000359500000000 [58914.156837] R13: 0000000000000000 R14: 0000000000000000 R15: ffff8858fe98bd78 [58914.164136] FS: 0000000000000000(0000) GS:ffff887f7f380000(0000) knlGS:0000000000000000 [58914.172529] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [58914.178467] CR2: 00007f2240452090 CR3: 0000005d5d258000 CR4: 00000000007606f0 [58914.185765] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [58914.193061] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [58914.200360] PKRU: 55555554 [58914.203221] Stack: [58914.205383] ffff8858fe98bd48 00000000000002f0 0000002e81036d09 ffffc90059dcfde8 [58914.213168] ffff8858fe98bec8 0000000000000000 0000000000000000 0000000000000000 [58914.220951] 0000000000000000 0000000000000000 0000000000000000 0000000000000000 [58914.228734] Call Trace: [58914.231337] [] psi_update_work+0x22/0x60 [58914.237067] [] process_one_work+0x189/0x420 [58914.243063] [] worker_thread+0x4e/0x4b0 [58914.248701] [] ? process_one_work+0x420/0x420 [58914.254869] [] kthread+0xe6/0x100 [58914.259994] [] ? kthread_park+0x60/0x60 [58914.265640] [] ret_from_fork+0x39/0x50 [58914.271193] Code: 41 29 c3 4d 39 dc 4d 0f 42 dc <49> f7 f1 48 8b 13 48 89 c7 48 c1 [58914.279691] RIP [] psi_update_stats+0x1c1/0x330 The crashing instruction is trying to divide the observed stall time by the sampling period. The period, stored in R8, is not 0, but we are dividing by the lower 32 bits only, which are all 0 in this instance. We could switch to a 64-bit division, but the period shouldn't be that big in the first place. It's the time between the last update and the next scheduled one, and so should always be around 2s and comfortably fit into 32 bits. The bug is in the initialization of new cgroups: we schedule the first sampling event in a cgroup as an offset of sched_clock(), but fail to initialize the last_update timestamp, and it defaults to 0. That results in a bogusly large sampling period the first time we run the sampling code, and consequently we underreport pressure for the first 2s of a cgroup's life. But worse, if sched_clock() is sufficiently advanced on the system, and the user gets unlucky, the period's lower 32 bits can all be 0 and the sampling division will crash. Fix this by initializing the last update timestamp to the creation time of the cgroup, thus correctly marking the start of the first pressure sampling period in a new cgroup. Reported-by: Jingfeng Xie Signed-off-by: Johannes Weiner Signed-off-by: Peter Zijlstra (Intel) Cc: Suren Baghdasaryan Link: https://lkml.kernel.org/r/20191203183524.41378-2-hannes@cmpxchg.org --- kernel/sched/psi.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 517e3719027e..970db4686dd4 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -185,7 +185,8 @@ static void group_init(struct psi_group *group) for_each_possible_cpu(cpu) seqcount_init(&per_cpu_ptr(group->pcpu, cpu)->seq); - group->avg_next_update = sched_clock() + psi_period; + group->avg_last_update = sched_clock(); + group->avg_next_update = group->avg_last_update + psi_period; INIT_DELAYED_WORK(&group->avgs_work, psi_avgs_work); mutex_init(&group->avgs_lock); /* Init trigger-related members */ -- cgit v1.2.3 From c3466952ca1514158d7c16c9cfc48c27d5c5dc0f Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Tue, 3 Dec 2019 13:35:24 -0500 Subject: psi: Fix a division error in psi poll() The psi window size is a u64 an can be up to 10 seconds right now, which exceeds the lower 32 bits of the variable. We currently use div_u64 for it, which is meant only for 32-bit divisors. The result is garbage pressure sampling values and even potential div0 crashes. Use div64_u64. Signed-off-by: Johannes Weiner Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Suren Baghdasaryan Cc: Jingfeng Xie Link: https://lkml.kernel.org/r/20191203183524.41378-3-hannes@cmpxchg.org --- kernel/sched/psi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 970db4686dd4..ce8f6748678a 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -482,7 +482,7 @@ static u64 window_update(struct psi_window *win, u64 now, u64 value) u32 remaining; remaining = win->size - elapsed; - growth += div_u64(win->prev_growth * remaining, win->size); + growth += div64_u64(win->prev_growth * remaining, win->size); } return growth; -- cgit v1.2.3 From 7ed735c33104f3c6194fbc67e3a8b6e64ae84ad1 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Wed, 4 Dec 2019 19:21:40 +0100 Subject: sched/fair: Fix find_idlest_group() to handle CPU affinity Because of CPU affinity, the local group can be skipped which breaks the assumption that statistics are always collected for local group. With uninitialized local_sgs, the comparison is meaningless and the behavior unpredictable. This can even end up to use local pointer which is to NULL in this case. If the local group has been skipped because of CPU affinity, we return the idlest group. Fixes: 57abff067a08 ("sched/fair: Rework find_idlest_group()") Reported-by: John Stultz Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Valentin Schneider Tested-by: John Stultz Cc: rostedt@goodmis.org Cc: valentin.schneider@arm.com Cc: mingo@redhat.com Cc: mgorman@suse.de Cc: juri.lelli@redhat.com Cc: dietmar.eggemann@arm.com Cc: bsegall@google.com Cc: qais.yousef@arm.com Link: https://lkml.kernel.org/r/1575483700-22153-1-git-send-email-vincent.guittot@linaro.org --- kernel/sched/fair.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'kernel') diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 08a233e97a01..146b6c83633f 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -8417,6 +8417,10 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, if (!idlest) return NULL; + /* The local group has been skipped because of CPU affinity */ + if (!local) + return idlest; + /* * If the local group is idler than the selected idlest group * don't try and push the task. -- cgit v1.2.3 From 6cf82d559e1a1d89f06ff4d428aca479c1dd0be6 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Fri, 29 Nov 2019 15:04:47 +0100 Subject: sched/cfs: fix spurious active migration The load balance can fail to find a suitable task during the periodic check because the imbalance is smaller than half of the load of the waiting tasks. This results in the increase of the number of failed load balance, which can end up to start an active migration. This active migration is useless because the current running task is not a better choice than the waiting ones. In fact, the current task was probably not running but waiting for the CPU during one of the previous attempts and it had already not been selected. When load balance fails too many times to migrate a task, we should relax the contraint on the maximum load of the tasks that can be migrated similarly to what is done with cache hotness. Before the rework, load balance used to set the imbalance to the average load_per_task in order to mitigate such situation. This increased the likelihood of migrating a task but also of selecting a larger task than needed while more appropriate ones were in the list. Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/1575036287-6052-1-git-send-email-vincent.guittot@linaro.org --- kernel/sched/fair.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 146b6c83633f..ba749f579714 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -7328,7 +7328,14 @@ static int detach_tasks(struct lb_env *env) load < 16 && !env->sd->nr_balance_failed) goto next; - if (load/2 > env->imbalance) + /* + * Make sure that we don't migrate too much load. + * Nevertheless, let relax the constraint if + * scheduler fails to find a good waiting task to + * migrate. + */ + if (load/2 > env->imbalance && + env->sd->nr_balance_failed <= env->sd->cache_nice_tries) goto next; env->imbalance -= load; -- cgit v1.2.3 From e47304232b373362228bf233f17bd12b11c9aafc Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 17 Dec 2019 13:28:16 +0100 Subject: bpf: Fix cgroup local storage prog tracking Recently noticed that we're tracking programs related to local storage maps through their prog pointer. This is a wrong assumption since the prog pointer can still change throughout the verification process, for example, whenever bpf_patch_insn_single() is called. Therefore, the prog pointer that was assigned via bpf_cgroup_storage_assign() is not guaranteed to be the same as we pass in bpf_cgroup_storage_release() and the map would therefore remain in busy state forever. Fix this by using the prog's aux pointer which is stable throughout verification and beyond. Fixes: de9cbbaadba5 ("bpf: introduce cgroup storage maps") Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Cc: Roman Gushchin Cc: Martin KaFai Lau Link: https://lore.kernel.org/bpf/1471c69eca3022218666f909bc927a92388fd09e.1576580332.git.daniel@iogearbox.net --- include/linux/bpf-cgroup.h | 8 ++++---- kernel/bpf/core.c | 3 +-- kernel/bpf/local_storage.c | 24 ++++++++++++------------ kernel/bpf/verifier.c | 2 +- 4 files changed, 18 insertions(+), 19 deletions(-) (limited to 'kernel') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 169fd25f6bc2..9be71c195d74 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -157,8 +157,8 @@ void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage, struct cgroup *cgroup, enum bpf_attach_type type); void bpf_cgroup_storage_unlink(struct bpf_cgroup_storage *storage); -int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *map); -void bpf_cgroup_storage_release(struct bpf_prog *prog, struct bpf_map *map); +int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *map); +void bpf_cgroup_storage_release(struct bpf_prog_aux *aux, struct bpf_map *map); int bpf_percpu_cgroup_storage_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, @@ -360,9 +360,9 @@ static inline int cgroup_bpf_prog_query(const union bpf_attr *attr, static inline void bpf_cgroup_storage_set( struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]) {} -static inline int bpf_cgroup_storage_assign(struct bpf_prog *prog, +static inline int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *map) { return 0; } -static inline void bpf_cgroup_storage_release(struct bpf_prog *prog, +static inline void bpf_cgroup_storage_release(struct bpf_prog_aux *aux, struct bpf_map *map) {} static inline struct bpf_cgroup_storage *bpf_cgroup_storage_alloc( struct bpf_prog *prog, enum bpf_cgroup_storage_type stype) { return NULL; } diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 6231858df723..af6b738cf435 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2043,8 +2043,7 @@ static void bpf_free_cgroup_storage(struct bpf_prog_aux *aux) for_each_cgroup_storage_type(stype) { if (!aux->cgroup_storage[stype]) continue; - bpf_cgroup_storage_release(aux->prog, - aux->cgroup_storage[stype]); + bpf_cgroup_storage_release(aux, aux->cgroup_storage[stype]); } } diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index 2ba750725cb2..6bf605dd4b94 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -20,7 +20,7 @@ struct bpf_cgroup_storage_map { struct bpf_map map; spinlock_t lock; - struct bpf_prog *prog; + struct bpf_prog_aux *aux; struct rb_root root; struct list_head list; }; @@ -420,7 +420,7 @@ const struct bpf_map_ops cgroup_storage_map_ops = { .map_seq_show_elem = cgroup_storage_seq_show_elem, }; -int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *_map) +int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *_map) { enum bpf_cgroup_storage_type stype = cgroup_storage_type(_map); struct bpf_cgroup_storage_map *map = map_to_storage(_map); @@ -428,14 +428,14 @@ int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *_map) spin_lock_bh(&map->lock); - if (map->prog && map->prog != prog) + if (map->aux && map->aux != aux) goto unlock; - if (prog->aux->cgroup_storage[stype] && - prog->aux->cgroup_storage[stype] != _map) + if (aux->cgroup_storage[stype] && + aux->cgroup_storage[stype] != _map) goto unlock; - map->prog = prog; - prog->aux->cgroup_storage[stype] = _map; + map->aux = aux; + aux->cgroup_storage[stype] = _map; ret = 0; unlock: spin_unlock_bh(&map->lock); @@ -443,16 +443,16 @@ unlock: return ret; } -void bpf_cgroup_storage_release(struct bpf_prog *prog, struct bpf_map *_map) +void bpf_cgroup_storage_release(struct bpf_prog_aux *aux, struct bpf_map *_map) { enum bpf_cgroup_storage_type stype = cgroup_storage_type(_map); struct bpf_cgroup_storage_map *map = map_to_storage(_map); spin_lock_bh(&map->lock); - if (map->prog == prog) { - WARN_ON(prog->aux->cgroup_storage[stype] != _map); - map->prog = NULL; - prog->aux->cgroup_storage[stype] = NULL; + if (map->aux == aux) { + WARN_ON(aux->cgroup_storage[stype] != _map); + map->aux = NULL; + aux->cgroup_storage[stype] = NULL; } spin_unlock_bh(&map->lock); } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index a1acdce77070..6ef71429d997 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -8268,7 +8268,7 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) env->used_maps[env->used_map_cnt++] = map; if (bpf_map_is_cgroup_storage(map) && - bpf_cgroup_storage_assign(env->prog, map)) { + bpf_cgroup_storage_assign(env->prog->aux, map)) { verbose(env, "only one cgroup storage of each type is allowed\n"); fdput(f); return -EBUSY; -- cgit v1.2.3 From cc52d9140aa920d8d61c7f6de3fff5fea6692ea9 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 19 Dec 2019 22:19:50 +0100 Subject: bpf: Fix record_func_key to perform backtracking on r3 While testing Cilium with /unreleased/ Linus' tree under BPF-based NodePort implementation, I noticed a strange BPF SNAT engine behavior from time to time. In some cases it would do the correct SNAT/DNAT service translation, but at a random point in time it would just stop and perform an unexpected translation after SYN, SYN/ACK and stack would send a RST back. While initially assuming that there is some sort of a race condition in BPF code, adding trace_printk()s for debugging purposes at some point seemed to have resolved the issue auto-magically. Digging deeper on this Heisenbug and reducing the trace_printk() calls to an absolute minimum, it turns out that a single call would suffice to trigger / not trigger the seen RST issue, even though the logic of the program itself remains unchanged. Turns out the single call changed verifier pruning behavior to get everything to work. Reconstructing a minimal test case, the incorrect JIT dump looked as follows: # bpftool p d j i 11346 0xffffffffc0cba96c: [...] 21: movzbq 0x30(%rdi),%rax 26: cmp $0xd,%rax 2a: je 0x000000000000003a 2c: xor %edx,%edx 2e: movabs $0xffff89cc74e85800,%rsi 38: jmp 0x0000000000000049 3a: mov $0x2,%edx 3f: movabs $0xffff89cc74e85800,%rsi 49: mov -0x224(%rbp),%eax 4f: cmp $0x20,%eax 52: ja 0x0000000000000062 54: add $0x1,%eax 57: mov %eax,-0x224(%rbp) 5d: jmpq 0xffffffffffff6911 62: mov $0x1,%eax [...] Hence, unexpectedly, JIT emitted a direct jump even though retpoline based one would have been needed since in line 2c and 3a we have different slot keys in BPF reg r3. Verifier log of the test case reveals what happened: 0: (b7) r0 = 14 1: (73) *(u8 *)(r1 +48) = r0 2: (71) r0 = *(u8 *)(r1 +48) 3: (15) if r0 == 0xd goto pc+4 R0_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff)) R1=ctx(id=0,off=0,imm=0) R10=fp0 4: (b7) r3 = 0 5: (18) r2 = 0xffff89cc74d54a00 7: (05) goto pc+3 11: (85) call bpf_tail_call#12 12: (b7) r0 = 1 13: (95) exit from 3 to 8: R0_w=inv13 R1=ctx(id=0,off=0,imm=0) R10=fp0 8: (b7) r3 = 2 9: (18) r2 = 0xffff89cc74d54a00 11: safe processed 13 insns (limit 1000000) [...] Second branch is pruned by verifier since considered safe, but issue is that record_func_key() couldn't have seen the index in line 3a and therefore decided that emitting a direct jump at this location was okay. Fix this by reusing our backtracking logic for precise scalar verification in order to prevent pruning on the slot key. This means verifier will track content of r3 all the way backwards and only prune if both scalars were unknown in state equivalence check and therefore poisoned in the first place in record_func_key(). The range is [x,x] in record_func_key() case since the slot always would have to be constant immediate. Correct verification after fix: 0: (b7) r0 = 14 1: (73) *(u8 *)(r1 +48) = r0 2: (71) r0 = *(u8 *)(r1 +48) 3: (15) if r0 == 0xd goto pc+4 R0_w=invP(id=0,umax_value=255,var_off=(0x0; 0xff)) R1=ctx(id=0,off=0,imm=0) R10=fp0 4: (b7) r3 = 0 5: (18) r2 = 0x0 7: (05) goto pc+3 11: (85) call bpf_tail_call#12 12: (b7) r0 = 1 13: (95) exit from 3 to 8: R0_w=invP13 R1=ctx(id=0,off=0,imm=0) R10=fp0 8: (b7) r3 = 2 9: (18) r2 = 0x0 11: (85) call bpf_tail_call#12 12: (b7) r0 = 1 13: (95) exit processed 15 insns (limit 1000000) [...] And correct corresponding JIT dump: # bpftool p d j i 11 0xffffffffc0dc34c4: [...] 21: movzbq 0x30(%rdi),%rax 26: cmp $0xd,%rax 2a: je 0x000000000000003a 2c: xor %edx,%edx 2e: movabs $0xffff9928b4c02200,%rsi 38: jmp 0x0000000000000049 3a: mov $0x2,%edx 3f: movabs $0xffff9928b4c02200,%rsi 49: cmp $0x4,%rdx 4d: jae 0x0000000000000093 4f: and $0x3,%edx 52: mov %edx,%edx 54: cmp %edx,0x24(%rsi) 57: jbe 0x0000000000000093 59: mov -0x224(%rbp),%eax 5f: cmp $0x20,%eax 62: ja 0x0000000000000093 64: add $0x1,%eax 67: mov %eax,-0x224(%rbp) 6d: mov 0x110(%rsi,%rdx,8),%rax 75: test %rax,%rax 78: je 0x0000000000000093 7a: mov 0x30(%rax),%rax 7e: add $0x19,%rax 82: callq 0x000000000000008e 87: pause 89: lfence 8c: jmp 0x0000000000000087 8e: mov %rax,(%rsp) 92: retq 93: mov $0x1,%eax [...] Also explicitly adding explicit env->allow_ptr_leaks to fixup_bpf_calls() since backtracking is enabled under former (direct jumps as well, but use different test). In case of only tracking different map pointers as in c93552c443eb ("bpf: properly enforce index mask to prevent out-of-bounds speculation"), pruning cannot make such short-cuts, neither if there are paths with scalar and non-scalar types as r3. mark_chain_precision() is only needed after we know that register_is_const(). If it was not the case, we already poison the key on first path and non-const key in later paths are not matching the scalar range in regsafe() either. Cilium NodePort testing passes fine as well now. Note, released kernels not affected. Fixes: d2e4c1e6c294 ("bpf: Constant map key tracking for prog array pokes") Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/ac43ffdeb7386c5bd688761ed266f3722bb39823.1576789878.git.daniel@iogearbox.net --- kernel/bpf/verifier.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 6ef71429d997..4983940cbdca 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4134,6 +4134,7 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, struct bpf_map *map = meta->map_ptr; struct tnum range; u64 val; + int err; if (func_id != BPF_FUNC_tail_call) return 0; @@ -4150,6 +4151,10 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, return 0; } + err = mark_chain_precision(env, BPF_REG_3); + if (err) + return err; + val = reg->var_off.value; if (bpf_map_key_unseen(aux)) bpf_map_key_store(aux, val); @@ -9272,7 +9277,8 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) insn->code = BPF_JMP | BPF_TAIL_CALL; aux = &env->insn_aux_data[i + delta]; - if (prog->jit_requested && !expect_blinding && + if (env->allow_ptr_leaks && !expect_blinding && + prog->jit_requested && !bpf_map_key_poisoned(aux) && !bpf_map_ptr_poisoned(aux) && !bpf_map_ptr_unpriv(aux)) { -- cgit v1.2.3 From 79e65c27f09683fbb50c33acab395d0ddf5302d2 Mon Sep 17 00:00:00 2001 From: Keita Suzuki Date: Wed, 11 Dec 2019 09:12:58 +0000 Subject: tracing: Avoid memory leak in process_system_preds() When failing in the allocation of filter_item, process_system_preds() goes to fail_mem, where the allocated filter is freed. However, this leads to memory leak of filter->filter_string and filter->prog, which is allocated before and in process_preds(). This bug has been detected by kmemleak as well. Fix this by changing kfree to __free_fiter. unreferenced object 0xffff8880658007c0 (size 32): comm "bash", pid 579, jiffies 4295096372 (age 17.752s) hex dump (first 32 bytes): 63 6f 6d 6d 6f 6e 5f 70 69 64 20 20 3e 20 31 30 common_pid > 10 00 00 00 00 00 00 00 00 65 73 00 00 00 00 00 00 ........es...... backtrace: [<0000000067441602>] kstrdup+0x2d/0x60 [<00000000141cf7b7>] apply_subsystem_event_filter+0x378/0x932 [<000000009ca32334>] subsystem_filter_write+0x5a/0x90 [<0000000072da2bee>] vfs_write+0xe1/0x240 [<000000004f14f473>] ksys_write+0xb4/0x150 [<00000000a968b4a0>] do_syscall_64+0x6d/0x1e0 [<000000001a189f40>] entry_SYSCALL_64_after_hwframe+0x44/0xa9 unreferenced object 0xffff888060c22d00 (size 64): comm "bash", pid 579, jiffies 4295096372 (age 17.752s) hex dump (first 32 bytes): 01 00 00 00 00 00 00 00 00 e8 d7 41 80 88 ff ff ...........A.... 01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<00000000b8c1b109>] process_preds+0x243/0x1820 [<000000003972c7f0>] apply_subsystem_event_filter+0x3be/0x932 [<000000009ca32334>] subsystem_filter_write+0x5a/0x90 [<0000000072da2bee>] vfs_write+0xe1/0x240 [<000000004f14f473>] ksys_write+0xb4/0x150 [<00000000a968b4a0>] do_syscall_64+0x6d/0x1e0 [<000000001a189f40>] entry_SYSCALL_64_after_hwframe+0x44/0xa9 unreferenced object 0xffff888041d7e800 (size 512): comm "bash", pid 579, jiffies 4295096372 (age 17.752s) hex dump (first 32 bytes): 70 bc 85 97 ff ff ff ff 0a 00 00 00 00 00 00 00 p............... 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<000000001e04af34>] process_preds+0x71a/0x1820 [<000000003972c7f0>] apply_subsystem_event_filter+0x3be/0x932 [<000000009ca32334>] subsystem_filter_write+0x5a/0x90 [<0000000072da2bee>] vfs_write+0xe1/0x240 [<000000004f14f473>] ksys_write+0xb4/0x150 [<00000000a968b4a0>] do_syscall_64+0x6d/0x1e0 [<000000001a189f40>] entry_SYSCALL_64_after_hwframe+0x44/0xa9 Link: http://lkml.kernel.org/r/20191211091258.11310-1-keitasuzuki.park@sslab.ics.keio.ac.jp Cc: Ingo Molnar Cc: stable@vger.kernel.org Fixes: 404a3add43c9c ("tracing: Only add filter list when needed") Signed-off-by: Keita Suzuki Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_events_filter.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index c9a74f82b14a..bf44f6bbd0c3 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -1662,7 +1662,7 @@ static int process_system_preds(struct trace_subsystem_dir *dir, parse_error(pe, FILT_ERR_BAD_SUBSYS_FILTER, 0); return -EINVAL; fail_mem: - kfree(filter); + __free_filter(filter); /* If any call succeeded, we still need to sync */ if (!fail) tracepoint_synchronize_unregister(); -- cgit v1.2.3 From 106f41f5a302cb1f36c7543fae6a05de12e96fa4 Mon Sep 17 00:00:00 2001 From: Steven Rostedt (VMware) Date: Wed, 11 Dec 2019 15:44:22 -0500 Subject: tracing: Have the histogram compare functions convert to u64 first The compare functions of the histogram code would be specific for the size of the value being compared (byte, short, int, long long). It would reference the value from the array via the type of the compare, but the value was stored in a 64 bit number. This is fine for little endian machines, but for big endian machines, it would end up comparing zeros or all ones (depending on the sign) for anything but 64 bit numbers. To fix this, first derference the value as a u64 then convert it to the type being compared. Link: http://lkml.kernel.org/r/20191211103557.7bed6928@gandalf.local.home Cc: stable@vger.kernel.org Fixes: 08d43a5fa063e ("tracing: Add lock-free tracing_map") Acked-by: Tom Zanussi Reported-by: Sven Schnelle Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/tracing_map.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c index 9a1c22310323..9e31bfc818ff 100644 --- a/kernel/trace/tracing_map.c +++ b/kernel/trace/tracing_map.c @@ -148,8 +148,8 @@ static int tracing_map_cmp_atomic64(void *val_a, void *val_b) #define DEFINE_TRACING_MAP_CMP_FN(type) \ static int tracing_map_cmp_##type(void *val_a, void *val_b) \ { \ - type a = *(type *)val_a; \ - type b = *(type *)val_b; \ + type a = (type)(*(u64 *)val_a); \ + type b = (type)(*(u64 *)val_b); \ \ return (a > b) ? 1 : ((a < b) ? -1 : 0); \ } -- cgit v1.2.3 From 3a53acf1d9bea11b57c1f6205e3fe73f9d8a3688 Mon Sep 17 00:00:00 2001 From: Prateek Sood Date: Tue, 10 Dec 2019 09:15:16 +0000 Subject: tracing: Fix lock inversion in trace_event_enable_tgid_record() Task T2 Task T3 trace_options_core_write() subsystem_open() mutex_lock(trace_types_lock) mutex_lock(event_mutex) set_tracer_flag() trace_event_enable_tgid_record() mutex_lock(trace_types_lock) mutex_lock(event_mutex) This gives a circular dependency deadlock between trace_types_lock and event_mutex. To fix this invert the usage of trace_types_lock and event_mutex in trace_options_core_write(). This keeps the sequence of lock usage consistent. Link: http://lkml.kernel.org/r/0101016eef175e38-8ca71caf-a4eb-480d-a1e6-6f0bbc015495-000000@us-west-2.amazonses.com Cc: stable@vger.kernel.org Fixes: d914ba37d7145 ("tracing: Add support for recording tgid of tasks") Signed-off-by: Prateek Sood Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace.c | 8 ++++++++ kernel/trace/trace_events.c | 8 ++++---- 2 files changed, 12 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 6c75410f9698..ddb7e7f5fe8d 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4685,6 +4685,10 @@ int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set) int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled) { + if ((mask == TRACE_ITER_RECORD_TGID) || + (mask == TRACE_ITER_RECORD_CMD)) + lockdep_assert_held(&event_mutex); + /* do nothing if flag is already set */ if (!!(tr->trace_flags & mask) == !!enabled) return 0; @@ -4752,6 +4756,7 @@ static int trace_set_options(struct trace_array *tr, char *option) cmp += len; + mutex_lock(&event_mutex); mutex_lock(&trace_types_lock); ret = match_string(trace_options, -1, cmp); @@ -4762,6 +4767,7 @@ static int trace_set_options(struct trace_array *tr, char *option) ret = set_tracer_flag(tr, 1 << ret, !neg); mutex_unlock(&trace_types_lock); + mutex_unlock(&event_mutex); /* * If the first trailing whitespace is replaced with '\0' by strstrip, @@ -8076,9 +8082,11 @@ trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt, if (val != 0 && val != 1) return -EINVAL; + mutex_lock(&event_mutex); mutex_lock(&trace_types_lock); ret = set_tracer_flag(tr, 1 << index, val); mutex_unlock(&trace_types_lock); + mutex_unlock(&event_mutex); if (ret < 0) return ret; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index c6de3cebc127..a5b614cc3887 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -320,7 +320,8 @@ void trace_event_enable_cmd_record(bool enable) struct trace_event_file *file; struct trace_array *tr; - mutex_lock(&event_mutex); + lockdep_assert_held(&event_mutex); + do_for_each_event_file(tr, file) { if (!(file->flags & EVENT_FILE_FL_ENABLED)) @@ -334,7 +335,6 @@ void trace_event_enable_cmd_record(bool enable) clear_bit(EVENT_FILE_FL_RECORDED_CMD_BIT, &file->flags); } } while_for_each_event_file(); - mutex_unlock(&event_mutex); } void trace_event_enable_tgid_record(bool enable) @@ -342,7 +342,8 @@ void trace_event_enable_tgid_record(bool enable) struct trace_event_file *file; struct trace_array *tr; - mutex_lock(&event_mutex); + lockdep_assert_held(&event_mutex); + do_for_each_event_file(tr, file) { if (!(file->flags & EVENT_FILE_FL_ENABLED)) continue; @@ -356,7 +357,6 @@ void trace_event_enable_tgid_record(bool enable) &file->flags); } } while_for_each_event_file(); - mutex_unlock(&event_mutex); } static int __ftrace_event_enable_disable(struct trace_event_file *file, -- cgit v1.2.3 From fe6e096a5bbf73a142f09c72e7aa2835026eb1a3 Mon Sep 17 00:00:00 2001 From: Sven Schnelle Date: Wed, 18 Dec 2019 08:44:27 +0100 Subject: tracing: Fix endianness bug in histogram trigger At least on PA-RISC and s390 synthetic histogram triggers are failing selftests because trace_event_raw_event_synth() always writes a 64 bit values, but the reader expects a field->size sized value. On little endian machines this doesn't hurt, but on big endian this makes the reader always read zero values. Link: http://lore.kernel.org/linux-trace-devel/20191218074427.96184-4-svens@linux.ibm.com Cc: stable@vger.kernel.org Fixes: 4b147936fa509 ("tracing: Add support for 'synthetic' events") Acked-by: Tom Zanussi Signed-off-by: Sven Schnelle Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_events_hist.c | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index f49d1a36d3ae..f62de5f43e79 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -911,7 +911,26 @@ static notrace void trace_event_raw_event_synth(void *__data, strscpy(str_field, str_val, STR_VAR_LEN_MAX); n_u64 += STR_VAR_LEN_MAX / sizeof(u64); } else { - entry->fields[n_u64] = var_ref_vals[var_ref_idx + i]; + struct synth_field *field = event->fields[i]; + u64 val = var_ref_vals[var_ref_idx + i]; + + switch (field->size) { + case 1: + *(u8 *)&entry->fields[n_u64] = (u8)val; + break; + + case 2: + *(u16 *)&entry->fields[n_u64] = (u16)val; + break; + + case 4: + *(u32 *)&entry->fields[n_u64] = (u32)val; + break; + + default: + entry->fields[n_u64] = val; + break; + } n_u64++; } } -- cgit v1.2.3