// SPDX-License-Identifier: GPL-2.0/* Copyright (c) 2011-2015 PLUMgrid, http://plumgrid.com * Copyright (c) 2016 Facebook */#include <linux/kernel.h>#include <linux/types.h>#include <linux/slab.h>#include <linux/bpf.h>#include <linux/bpf_verifier.h>#include <linux/bpf_perf_event.h>#include <linux/btf.h>#include <linux/filter.h>#include <linux/uaccess.h>#include <linux/ctype.h>#include <linux/kprobes.h>#include <linux/spinlock.h>#include <linux/syscalls.h>#include <linux/error-injection.h>#include <linux/btf_ids.h>#include <linux/bpf_lsm.h>#include <linux/fprobe.h>#include <linux/bsearch.h>#include <linux/sort.h>#include <linux/key.h>#include <linux/namei.h>#include <linux/file.h> #include <net/bpf_sk_storage.h> #include <uapi/linux/bpf.h>#include <uapi/linux/btf.h> #include <asm/tlb.h> #include "trace_probe.h"#include "trace.h" #define CREATE_TRACE_POINTS#include "bpf_trace.h" #define bpf_event_rcu_dereference(p) \ rcu_dereference_protected(p, lockdep_is_held(&bpf_event_mutex)) #define MAX_UPROBE_MULTI_CNT (1U << 20)#define MAX_KPROBE_MULTI_CNT (1U << 20)#define MAX_TRACING_MULTI_CNT (1U << 20) #ifdef CONFIG_MODULESstruct bpf_trace_module { struct module *module; struct list_head list;}; static LIST_HEAD(bpf_trace_modules);static DEFINE_MUTEX(bpf_module_mutex); static struct bpf_raw_event_map *bpf_get_raw_tracepoint_module(const char *name){ struct bpf_raw_event_map *btp, *ret = NULL; struct bpf_trace_module *btm; unsigned int i; mutex_lock(&bpf_module_mutex); list_for_each_entry(btm, &bpf_trace_modules, list) { for (i = 0; i < btm->module->num_bpf_raw_events; ++i) { btp = &btm->module->bpf_raw_events[i]; if (!strcmp(btp->tp->name, name)) { if (try_module_get(btm->module)) ret = btp; goto out; } } }out: mutex_unlock(&bpf_module_mutex); return ret;}#elsestatic struct bpf_raw_event_map *bpf_get_raw_tracepoint_module(const char *name){ return NULL;}#endif /* CONFIG_MODULES */ u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);u64 bpf_get_stack(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); static int bpf_btf_printf_prepare(struct btf_ptr *ptr, u32 btf_ptr_size, u64 flags, const struct btf **btf, s32 *btf_id);static u64 bpf_kprobe_multi_cookie(struct bpf_run_ctx *ctx);static u64 bpf_kprobe_multi_entry_ip(struct bpf_run_ctx *ctx); static u64 bpf_uprobe_multi_cookie(struct bpf_run_ctx *ctx);static u64 bpf_uprobe_multi_entry_ip(struct bpf_run_ctx *ctx); /** * trace_call_bpf - invoke BPF program * @call: tracepoint event * @ctx: opaque context pointer * * kprobe handlers execute BPF programs via this helper. * Can be used from static tracepoints in the future. * * Return: BPF programs always return an integer which is interpreted by * kprobe handler as: * 0 - return from kprobe (event is filtered out) * 1 - store kprobe event into ring buffer * Other values are reserved and currently alias to 1 */unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx){ unsigned int ret; cant_sleep(); if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) { /* * since some bpf program is already running on this cpu, * don't call into another bpf program (same or different) * and don't send kprobe event into ring-buffer, * so return zero here */ rcu_read_lock(); bpf_prog_inc_misses_counters(rcu_dereference(call->prog_array)); rcu_read_unlock(); ret = 0; goto out; } /* * Instead of moving rcu_read_lock/rcu_dereference/rcu_read_unlock * to all call sites, we did a bpf_prog_array_valid() there to check * whether call->prog_array is empty or not, which is * a heuristic to speed up execution. * * If bpf_prog_array_valid() fetched prog_array was * non-NULL, we go into trace_call_bpf() and do the actual * proper rcu_dereference() under RCU lock. * If it turns out that prog_array is NULL then, we bail out. * For the opposite, if the bpf_prog_array_valid() fetched pointer * was NULL, you'll skip the prog_array with the risk of missing * out of events when it was updated in between this and the * rcu_dereference() which is accepted risk. */ rcu_read_lock(); ret = bpf_prog_run_array(rcu_dereference(call->prog_array), ctx, bpf_prog_run); rcu_read_unlock(); out: __this_cpu_dec(bpf_prog_active); return ret;} /** * trace_call_bpf_faultable - invoke BPF program in faultable context * @call: tracepoint event * @ctx: opaque context pointer * * Variant of trace_call_bpf() for faultable tracepoints (syscall * tracepoints). Supports sleepable BPF programs by using rcu_tasks_trace * for lifetime protection and bpf_prog_run_array_sleepable() for per-program * RCU flavor selection, following the uprobe pattern. * * Per-program recursion protection is provided by * bpf_prog_run_array_sleepable(). Global bpf_prog_active is not * needed because syscall tracepoints cannot self-recurse. * * Must be called from a faultable/preemptible context. */unsigned int trace_call_bpf_faultable(struct trace_event_call *call, void *ctx){ struct bpf_prog_array *prog_array; might_fault(); guard(rcu_tasks_trace)(); prog_array = rcu_dereference_check(call->prog_array, rcu_read_lock_trace_held()); return bpf_prog_run_array_sleepable(prog_array, ctx, bpf_prog_run);} #ifdef CONFIG_BPF_KPROBE_OVERRIDEBPF_CALL_2(bpf_override_return, struct pt_regs *, regs, unsigned long, rc){ regs_set_return_value(regs, rc); override_function_with_return(regs); return 0;} static const struct bpf_func_proto bpf_override_return_proto = { .func = bpf_override_return, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING,};#endif static __always_inline intbpf_probe_read_user_common(void *dst, u32 size, const void __user *unsafe_ptr){ int ret; ret = copy_from_user_nofault(dst, unsafe_ptr, size); if (unlikely(ret < 0)) memset(dst, 0, size); return ret;} BPF_CALL_3(bpf_probe_read_user, void *, dst, u32, size, const void __user *, unsafe_ptr){ return bpf_probe_read_user_common(dst, size, unsafe_ptr);} const struct bpf_func_proto bpf_probe_read_user_proto = { .func = bpf_probe_read_user, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING,}; static __always_inline intbpf_probe_read_user_str_common(void *dst, u32 size, const void __user *unsafe_ptr){ int ret; /* * NB: We rely on strncpy_from_user() not copying junk past the NUL * terminator into `dst`. * * strncpy_from_user() does long-sized strides in the fast path. If the * strncpy does not mask out the bytes after the NUL in `unsafe_ptr`, * then there could be junk after the NUL in `dst`. If user takes `dst` * and keys a hash map with it, then semantically identical strings can * occupy multiple entries in the map. */ ret = strncpy_from_user_nofault(dst, unsafe_ptr, size); if (unlikely(ret < 0)) memset(dst, 0, size); return ret;} BPF_CALL_3(bpf_probe_read_user_str, void *, dst, u32, size, const void __user *, unsafe_ptr){ return bpf_probe_read_user_str_common(dst, size, unsafe_ptr);} const struct bpf_func_proto bpf_probe_read_user_str_proto = { .func = bpf_probe_read_user_str, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING,}; BPF_CALL_3(bpf_probe_read_kernel, void *, dst, u32, size, const void *, unsafe_ptr){ return bpf_probe_read_kernel_common(dst, size, unsafe_ptr);} const struct bpf_func_proto bpf_probe_read_kernel_proto = { .func = bpf_probe_read_kernel, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING,}; static __always_inline intbpf_probe_read_kernel_str_common(void *dst, u32 size, const void *unsafe_ptr){ int ret; /* * The strncpy_from_kernel_nofault() call will likely not fill the * entire buffer, but that's okay in this circumstance as we're probing * arbitrary memory anyway similar to bpf_probe_read_*() and might * as well probe the stack. Thus, memory is explicitly cleared * only in error case, so that improper users ignoring return * code altogether don't copy garbage; otherwise length of string * is returned that can be used for bpf_perf_event_output() et al. */ ret = strncpy_from_kernel_nofault(dst, unsafe_ptr, size); if (unlikely(ret < 0)) memset(dst, 0, size); return ret;} BPF_CALL_3(bpf_probe_read_kernel_str, void *, dst, u32, size, const void *, unsafe_ptr){ return bpf_probe_read_kernel_str_common(dst, size, unsafe_ptr);} const struct bpf_func_proto bpf_probe_read_kernel_str_proto = { .func = bpf_probe_read_kernel_str, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING,}; #ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACEBPF_CALL_3(bpf_probe_read_compat, void *, dst, u32, size, const void *, unsafe_ptr){ if ((unsigned long)unsafe_ptr < TASK_SIZE) { return bpf_probe_read_user_common(dst, size, (__force void __user *)unsafe_ptr); } return bpf_probe_read_kernel_common(dst, size, unsafe_ptr);} static const struct bpf_func_proto bpf_probe_read_compat_proto = { .func = bpf_probe_read_compat, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING,}; BPF_CALL_3(bpf_probe_read_compat_str, void *, dst, u32, size, const void *, unsafe_ptr){ if ((unsigned long)unsafe_ptr < TASK_SIZE) { return bpf_probe_read_user_str_common(dst, size, (__force void __user *)unsafe_ptr); } return bpf_probe_read_kernel_str_common(dst, size, unsafe_ptr);} static const struct bpf_func_proto bpf_probe_read_compat_str_proto = { .func = bpf_probe_read_compat_str, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING,};#endif /* CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE */ BPF_CALL_3(bpf_probe_write_user, void __user *, unsafe_ptr, const void *, src, u32, size){ /* * Ensure we're in user context which is safe for the helper to * run. This helper has no business in a kthread. * * access_ok() should prevent writing to non-user memory, but in * some situations (nommu, temporary switch, etc) access_ok() does * not provide enough validation, hence the check on KERNEL_DS. * * nmi_uaccess_okay() ensures the probe is not run in an interim * state, when the task or mm are switched. This is specifically * required to prevent the use of temporary mm. */ if (unlikely(in_interrupt() || current->flags & (PF_KTHREAD | PF_EXITING))) return -EPERM; if (unlikely(!nmi_uaccess_okay())) return -EPERM; return copy_to_user_nofault(unsafe_ptr, src, size);} static const struct bpf_func_proto bpf_probe_write_user_proto = { .func = bpf_probe_write_user, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE,}; #define MAX_TRACE_PRINTK_VARARGS 3#define BPF_TRACE_PRINTK_SIZE 1024 BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1, u64, arg2, u64, arg3){ u64 args[MAX_TRACE_PRINTK_VARARGS] = { arg1, arg2, arg3 }; struct bpf_bprintf_data data = { .get_bin_args = true, .get_buf = true, }; int ret; ret = bpf_bprintf_prepare(fmt, fmt_size, args, MAX_TRACE_PRINTK_VARARGS, &data); if (ret < 0) return ret; ret = bstr_printf(data.buf, MAX_BPRINTF_BUF, fmt, data.bin_args); trace_bpf_trace_printk(data.buf); bpf_bprintf_cleanup(&data); return ret;} static const struct bpf_func_proto bpf_trace_printk_proto = { .func = bpf_trace_printk, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE,}; static void __set_printk_clr_event(struct work_struct *work){ /* * This program might be calling bpf_trace_printk, * so enable the associated bpf_trace/bpf_trace_printk event. * Repeat this each time as it is possible a user has * disabled bpf_trace_printk events. By loading a program * calling bpf_trace_printk() however the user has expressed * the intent to see such events. */ if (trace_set_clr_event("bpf_trace", "bpf_trace_printk", 1)) pr_warn_ratelimited("could not enable bpf_trace_printk events");}static DECLARE_WORK(set_printk_work, __set_printk_clr_event); const struct bpf_func_proto *bpf_get_trace_printk_proto(void){ schedule_work(&set_printk_work); return &bpf_trace_printk_proto;} BPF_CALL_4(bpf_trace_vprintk, char *, fmt, u32, fmt_size, const void *, args, u32, data_len){ struct bpf_bprintf_data data = { .get_bin_args = true, .get_buf = true, }; int ret, num_args; if (data_len & 7 || data_len > MAX_BPRINTF_VARARGS * 8 || (data_len && !args)) return -EINVAL; num_args = data_len / 8; ret = bpf_bprintf_prepare(fmt, fmt_size, args, num_args, &data); if (ret < 0) return ret; ret = bstr_printf(data.buf, MAX_BPRINTF_BUF, fmt, data.bin_args); trace_bpf_trace_printk(data.buf); bpf_bprintf_cleanup(&data); return ret;} static const struct bpf_func_proto bpf_trace_vprintk_proto = { .func = bpf_trace_vprintk, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, .arg3_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE_OR_ZERO,}; const struct bpf_func_proto *bpf_get_trace_vprintk_proto(void){ schedule_work(&set_printk_work); return &bpf_trace_vprintk_proto;} BPF_CALL_5(bpf_seq_printf, struct seq_file *, m, char *, fmt, u32, fmt_size, const void *, args, u32, data_len){ struct bpf_bprintf_data data = { .get_bin_args = true, }; int err, num_args; if (data_len & 7 || data_len > MAX_BPRINTF_VARARGS * 8 || (data_len && !args)) return -EINVAL; num_args = data_len / 8; Lines 1–500 of 3880. Load more
// SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2011-2015 PLUMgrid, http://plumgrid.com * Copyright (c) 2016 Facebook */ #include <linux/kernel.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/bpf.h> #include <linux/bpf_verifier.h> #include <linux/bpf_perf_event.h> #include <linux/btf.h> #include <linux/filter.h> #include <linux/uaccess.h> #include <linux/ctype.h> #include <linux/kprobes.h> #include <linux/spinlock.h> #include <linux/syscalls.h> #include <linux/error-injection.h> #include <linux/btf_ids.h> #include <linux/bpf_lsm.h> #include <linux/fprobe.h> #include <linux/bsearch.h> #include <linux/sort.h> #include <linux/key.h> #include <linux/namei.h> #include <linux/file.h> #include <net/bpf_sk_storage.h> #include <uapi/linux/bpf.h> #include <uapi/linux/btf.h> #include <asm/tlb.h> #include "trace_probe.h" #include "trace.h" #define CREATE_TRACE_POINTS #include "bpf_trace.h" #define bpf_event_rcu_dereference(p) \ rcu_dereference_protected(p, lockdep_is_held(&bpf_event_mutex)) #define MAX_UPROBE_MULTI_CNT (1U << 20) #define MAX_KPROBE_MULTI_CNT (1U << 20) #define MAX_TRACING_MULTI_CNT (1U << 20) #ifdef CONFIG_MODULES struct bpf_trace_module { struct module *module; struct list_head list; }; static LIST_HEAD(bpf_trace_modules); static DEFINE_MUTEX(bpf_module_mutex); static struct bpf_raw_event_map *bpf_get_raw_tracepoint_module(const char *name) { struct bpf_raw_event_map *btp, *ret = NULL; struct bpf_trace_module *btm; unsigned int i; mutex_lock(&bpf_module_mutex); list_for_each_entry(btm, &bpf_trace_modules, list) { for (i = 0; i < btm->module->num_bpf_raw_events; ++i) { btp = &btm->module->bpf_raw_events[i]; if (!strcmp(btp->tp->name, name)) { if (try_module_get(btm->module)) ret = btp; goto out; } } } out: mutex_unlock(&bpf_module_mutex); return ret; } #else static struct bpf_raw_event_map *bpf_get_raw_tracepoint_module(const char *name) { return NULL; } #endif /* CONFIG_MODULES */ u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); u64 bpf_get_stack(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); static int bpf_btf_printf_prepare(struct btf_ptr *ptr, u32 btf_ptr_size, u64 flags, const struct btf **btf, s32 *btf_id); static u64 bpf_kprobe_multi_cookie(struct bpf_run_ctx *ctx); static u64 bpf_kprobe_multi_entry_ip(struct bpf_run_ctx *ctx); static u64 bpf_uprobe_multi_cookie(struct bpf_run_ctx *ctx); static u64 bpf_uprobe_multi_entry_ip(struct bpf_run_ctx *ctx); /** * trace_call_bpf - invoke BPF program * @call: tracepoint event * @ctx: opaque context pointer * * kprobe handlers execute BPF programs via this helper. * Can be used from static tracepoints in the future. * * Return: BPF programs always return an integer which is interpreted by * kprobe handler as: * 0 - return from kprobe (event is filtered out) * 1 - store kprobe event into ring buffer * Other values are reserved and currently alias to 1 */ unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx) { unsigned int ret; cant_sleep(); if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) { /* * since some bpf program is already running on this cpu, * don't call into another bpf program (same or different) * and don't send kprobe event into ring-buffer, * so return zero here */ rcu_read_lock(); bpf_prog_inc_misses_counters(rcu_dereference(call->prog_array)); rcu_read_unlock(); ret = 0; goto out; } /* * Instead of moving rcu_read_lock/rcu_dereference/rcu_read_unlock * to all call sites, we did a bpf_prog_array_valid() there to check * whether call->prog_array is empty or not, which is * a heuristic to speed up execution. * * If bpf_prog_array_valid() fetched prog_array was * non-NULL, we go into trace_call_bpf() and do the actual * proper rcu_dereference() under RCU lock. * If it turns out that prog_array is NULL then, we bail out. * For the opposite, if the bpf_prog_array_valid() fetched pointer * was NULL, you'll skip the prog_array with the risk of missing * out of events when it was updated in between this and the * rcu_dereference() which is accepted risk. */ rcu_read_lock(); ret = bpf_prog_run_array(rcu_dereference(call->prog_array), ctx, bpf_prog_run); rcu_read_unlock(); out: __this_cpu_dec(bpf_prog_active); return ret; } /** * trace_call_bpf_faultable - invoke BPF program in faultable context * @call: tracepoint event * @ctx: opaque context pointer * * Variant of trace_call_bpf() for faultable tracepoints (syscall * tracepoints). Supports sleepable BPF programs by using rcu_tasks_trace * for lifetime protection and bpf_prog_run_array_sleepable() for per-program * RCU flavor selection, following the uprobe pattern. * * Per-program recursion protection is provided by * bpf_prog_run_array_sleepable(). Global bpf_prog_active is not * needed because syscall tracepoints cannot self-recurse. * * Must be called from a faultable/preemptible context. */ unsigned int trace_call_bpf_faultable(struct trace_event_call *call, void *ctx) { struct bpf_prog_array *prog_array; might_fault(); guard(rcu_tasks_trace)(); prog_array = rcu_dereference_check(call->prog_array, rcu_read_lock_trace_held()); return bpf_prog_run_array_sleepable(prog_array, ctx, bpf_prog_run); } #ifdef CONFIG_BPF_KPROBE_OVERRIDE BPF_CALL_2(bpf_override_return, struct pt_regs *, regs, unsigned long, rc) { regs_set_return_value(regs, rc); override_function_with_return(regs); return 0; } static const struct bpf_func_proto bpf_override_return_proto = { .func = bpf_override_return, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; #endif static __always_inline int bpf_probe_read_user_common(void *dst, u32 size, const void __user *unsafe_ptr) { int ret; ret = copy_from_user_nofault(dst, unsafe_ptr, size); if (unlikely(ret < 0)) memset(dst, 0, size); return ret; } BPF_CALL_3(bpf_probe_read_user, void *, dst, u32, size, const void __user *, unsafe_ptr) { return bpf_probe_read_user_common(dst, size, unsafe_ptr); } const struct bpf_func_proto bpf_probe_read_user_proto = { .func = bpf_probe_read_user, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, }; static __always_inline int bpf_probe_read_user_str_common(void *dst, u32 size, const void __user *unsafe_ptr) { int ret; /* * NB: We rely on strncpy_from_user() not copying junk past the NUL * terminator into `dst`. * * strncpy_from_user() does long-sized strides in the fast path. If the * strncpy does not mask out the bytes after the NUL in `unsafe_ptr`, * then there could be junk after the NUL in `dst`. If user takes `dst` * and keys a hash map with it, then semantically identical strings can * occupy multiple entries in the map. */ ret = strncpy_from_user_nofault(dst, unsafe_ptr, size); if (unlikely(ret < 0)) memset(dst, 0, size); return ret; } BPF_CALL_3(bpf_probe_read_user_str, void *, dst, u32, size, const void __user *, unsafe_ptr) { return bpf_probe_read_user_str_common(dst, size, unsafe_ptr); } const struct bpf_func_proto bpf_probe_read_user_str_proto = { .func = bpf_probe_read_user_str, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_probe_read_kernel, void *, dst, u32, size, const void *, unsafe_ptr) { return bpf_probe_read_kernel_common(dst, size, unsafe_ptr); } const struct bpf_func_proto bpf_probe_read_kernel_proto = { .func = bpf_probe_read_kernel, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, }; static __always_inline int bpf_probe_read_kernel_str_common(void *dst, u32 size, const void *unsafe_ptr) { int ret; /* * The strncpy_from_kernel_nofault() call will likely not fill the * entire buffer, but that's okay in this circumstance as we're probing * arbitrary memory anyway similar to bpf_probe_read_*() and might * as well probe the stack. Thus, memory is explicitly cleared * only in error case, so that improper users ignoring return * code altogether don't copy garbage; otherwise length of string * is returned that can be used for bpf_perf_event_output() et al. */ ret = strncpy_from_kernel_nofault(dst, unsafe_ptr, size); if (unlikely(ret < 0)) memset(dst, 0, size); return ret; } BPF_CALL_3(bpf_probe_read_kernel_str, void *, dst, u32, size, const void *, unsafe_ptr) { return bpf_probe_read_kernel_str_common(dst, size, unsafe_ptr); } const struct bpf_func_proto bpf_probe_read_kernel_str_proto = { .func = bpf_probe_read_kernel_str, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, }; #ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE BPF_CALL_3(bpf_probe_read_compat, void *, dst, u32, size, const void *, unsafe_ptr) { if ((unsigned long)unsafe_ptr < TASK_SIZE) { return bpf_probe_read_user_common(dst, size, (__force void __user *)unsafe_ptr); } return bpf_probe_read_kernel_common(dst, size, unsafe_ptr); } static const struct bpf_func_proto bpf_probe_read_compat_proto = { .func = bpf_probe_read_compat, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_probe_read_compat_str, void *, dst, u32, size, const void *, unsafe_ptr) { if ((unsigned long)unsafe_ptr < TASK_SIZE) { return bpf_probe_read_user_str_common(dst, size, (__force void __user *)unsafe_ptr); } return bpf_probe_read_kernel_str_common(dst, size, unsafe_ptr); } static const struct bpf_func_proto bpf_probe_read_compat_str_proto = { .func = bpf_probe_read_compat_str, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, }; #endif /* CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE */ BPF_CALL_3(bpf_probe_write_user, void __user *, unsafe_ptr, const void *, src, u32, size) { /* * Ensure we're in user context which is safe for the helper to * run. This helper has no business in a kthread. * * access_ok() should prevent writing to non-user memory, but in * some situations (nommu, temporary switch, etc) access_ok() does * not provide enough validation, hence the check on KERNEL_DS. * * nmi_uaccess_okay() ensures the probe is not run in an interim * state, when the task or mm are switched. This is specifically * required to prevent the use of temporary mm. */ if (unlikely(in_interrupt() || current->flags & (PF_KTHREAD | PF_EXITING))) return -EPERM; if (unlikely(!nmi_uaccess_okay())) return -EPERM; return copy_to_user_nofault(unsafe_ptr, src, size); } static const struct bpf_func_proto bpf_probe_write_user_proto = { .func = bpf_probe_write_user, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, }; #define MAX_TRACE_PRINTK_VARARGS 3 #define BPF_TRACE_PRINTK_SIZE 1024 BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1, u64, arg2, u64, arg3) { u64 args[MAX_TRACE_PRINTK_VARARGS] = { arg1, arg2, arg3 }; struct bpf_bprintf_data data = { .get_bin_args = true, .get_buf = true, }; int ret; ret = bpf_bprintf_prepare(fmt, fmt_size, args, MAX_TRACE_PRINTK_VARARGS, &data); if (ret < 0) return ret; ret = bstr_printf(data.buf, MAX_BPRINTF_BUF, fmt, data.bin_args); trace_bpf_trace_printk(data.buf); bpf_bprintf_cleanup(&data); return ret; } static const struct bpf_func_proto bpf_trace_printk_proto = { .func = bpf_trace_printk, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, }; static void __set_printk_clr_event(struct work_struct *work) { /* * This program might be calling bpf_trace_printk, * so enable the associated bpf_trace/bpf_trace_printk event. * Repeat this each time as it is possible a user has * disabled bpf_trace_printk events. By loading a program * calling bpf_trace_printk() however the user has expressed * the intent to see such events. */ if (trace_set_clr_event("bpf_trace", "bpf_trace_printk", 1)) pr_warn_ratelimited("could not enable bpf_trace_printk events"); } static DECLARE_WORK(set_printk_work, __set_printk_clr_event); const struct bpf_func_proto *bpf_get_trace_printk_proto(void) { schedule_work(&set_printk_work); return &bpf_trace_printk_proto; } BPF_CALL_4(bpf_trace_vprintk, char *, fmt, u32, fmt_size, const void *, args, u32, data_len) { struct bpf_bprintf_data data = { .get_bin_args = true, .get_buf = true, }; int ret, num_args; if (data_len & 7 || data_len > MAX_BPRINTF_VARARGS * 8 || (data_len && !args)) return -EINVAL; num_args = data_len / 8; ret = bpf_bprintf_prepare(fmt, fmt_size, args, num_args, &data); if (ret < 0) return ret; ret = bstr_printf(data.buf, MAX_BPRINTF_BUF, fmt, data.bin_args); trace_bpf_trace_printk(data.buf); bpf_bprintf_cleanup(&data); return ret; } static const struct bpf_func_proto bpf_trace_vprintk_proto = { .func = bpf_trace_vprintk, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, .arg3_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE_OR_ZERO, }; const struct bpf_func_proto *bpf_get_trace_vprintk_proto(void) { schedule_work(&set_printk_work); return &bpf_trace_vprintk_proto; } BPF_CALL_5(bpf_seq_printf, struct seq_file *, m, char *, fmt, u32, fmt_size, const void *, args, u32, data_len) { struct bpf_bprintf_data data = { .get_bin_args = true, }; int err, num_args; if (data_len & 7 || data_len > MAX_BPRINTF_VARARGS * 8 || (data_len && !args)) return -EINVAL; num_args = data_len / 8;