// SPDX-License-Identifier: GPL-2.0-only/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com * Copyright (c) 2016,2017 Facebook */#include <linux/bpf.h>#include <linux/btf.h>#include <linux/err.h>#include <linux/slab.h>#include <linux/mm.h>#include <linux/filter.h>#include <linux/perf_event.h>#include <uapi/linux/btf.h>#include <linux/rcupdate_trace.h>#include <linux/btf_ids.h> #include "map_in_map.h" #define ARRAY_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_MMAPABLE | BPF_F_ACCESS_MASK | \ BPF_F_PRESERVE_ELEMS | BPF_F_INNER_MAP) static void bpf_array_free_percpu(struct bpf_array *array){ int i; for (i = 0; i < array->map.max_entries; i++) { free_percpu(array->pptrs[i]); cond_resched(); }} static int bpf_array_alloc_percpu(struct bpf_array *array){ void __percpu *ptr; int i; for (i = 0; i < array->map.max_entries; i++) { ptr = bpf_map_alloc_percpu(&array->map, array->elem_size, 8, GFP_USER | __GFP_NOWARN); if (!ptr) { bpf_array_free_percpu(array); return -ENOMEM; } array->pptrs[i] = ptr; cond_resched(); } return 0;} /* Called from syscall */int array_map_alloc_check(union bpf_attr *attr){ bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY; int numa_node = bpf_map_attr_numa_node(attr); /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || attr->value_size == 0 || attr->map_flags & ~ARRAY_CREATE_FLAG_MASK || !bpf_map_flags_access_ok(attr->map_flags) || (percpu && numa_node != NUMA_NO_NODE)) return -EINVAL; if (attr->map_type != BPF_MAP_TYPE_ARRAY && attr->map_flags & (BPF_F_MMAPABLE | BPF_F_INNER_MAP)) return -EINVAL; if (attr->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY && attr->map_flags & BPF_F_PRESERVE_ELEMS) return -EINVAL; /* avoid overflow on round_up(map->value_size) */ if (attr->value_size > INT_MAX) return -E2BIG; /* percpu map value size is bound by PCPU_MIN_UNIT_SIZE */ if (percpu && round_up(attr->value_size, 8) > PCPU_MIN_UNIT_SIZE) return -E2BIG; return 0;} static struct bpf_map *array_map_alloc(union bpf_attr *attr){ bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY; int numa_node = bpf_map_attr_numa_node(attr); u32 elem_size, index_mask, max_entries; bool bypass_spec_v1 = bpf_bypass_spec_v1(NULL); u64 array_size, mask64; struct bpf_array *array; elem_size = round_up(attr->value_size, 8); max_entries = attr->max_entries; /* On 32 bit archs roundup_pow_of_two() with max_entries that has * upper most bit set in u32 space is undefined behavior due to * resulting 1U << 32, so do it manually here in u64 space. */ mask64 = fls_long(max_entries - 1); mask64 = 1ULL << mask64; mask64 -= 1; index_mask = mask64; if (!bypass_spec_v1) { /* round up array size to nearest power of 2, * since cpu will speculate within index_mask limits */ max_entries = index_mask + 1; /* Check for overflows. */ if (max_entries < attr->max_entries) return ERR_PTR(-E2BIG); } array_size = sizeof(*array); if (percpu) { array_size += (u64) max_entries * sizeof(void *); } else { /* rely on vmalloc() to return page-aligned memory and * ensure array->value is exactly page-aligned */ if (attr->map_flags & BPF_F_MMAPABLE) { array_size = PAGE_ALIGN(array_size); array_size += PAGE_ALIGN((u64) max_entries * elem_size); } else { array_size += (u64) max_entries * elem_size; } } /* allocate all map elements and zero-initialize them */ if (attr->map_flags & BPF_F_MMAPABLE) { void *data; /* kmalloc'ed memory can't be mmap'ed, use explicit vmalloc */ data = bpf_map_area_mmapable_alloc(array_size, numa_node); if (!data) return ERR_PTR(-ENOMEM); array = data + PAGE_ALIGN(sizeof(struct bpf_array)) - offsetof(struct bpf_array, value); } else { array = bpf_map_area_alloc(array_size, numa_node); } if (!array) return ERR_PTR(-ENOMEM); array->index_mask = index_mask; array->map.bypass_spec_v1 = bypass_spec_v1; /* copy mandatory map attributes */ bpf_map_init_from_attr(&array->map, attr); array->elem_size = elem_size; if (percpu && bpf_array_alloc_percpu(array)) { bpf_map_area_free(array); return ERR_PTR(-ENOMEM); } return &array->map;} static void *array_map_elem_ptr(struct bpf_array* array, u32 index){ return array->value + (u64)array->elem_size * index;} /* Called from syscall or from eBPF program */static void *array_map_lookup_elem(struct bpf_map *map, void *key){ struct bpf_array *array = container_of(map, struct bpf_array, map); u32 index = *(u32 *)key; if (unlikely(index >= array->map.max_entries)) return NULL; return array->value + (u64)array->elem_size * (index & array->index_mask);} static int array_map_direct_value_addr(const struct bpf_map *map, u64 *imm, u32 off){ struct bpf_array *array = container_of(map, struct bpf_array, map); if (map->max_entries != 1) return -ENOTSUPP; if (off >= map->value_size) return -EINVAL; *imm = (unsigned long)array->value; return 0;} static int array_map_direct_value_meta(const struct bpf_map *map, u64 imm, u32 *off){ struct bpf_array *array = container_of(map, struct bpf_array, map); u64 base = (unsigned long)array->value; u64 range = array->elem_size; if (map->max_entries != 1) return -ENOTSUPP; if (imm < base || imm >= base + range) return -ENOENT; *off = imm - base; return 0;} /* emit BPF instructions equivalent to C code of array_map_lookup_elem() */static int array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf){ struct bpf_array *array = container_of(map, struct bpf_array, map); struct bpf_insn *insn = insn_buf; u32 elem_size = array->elem_size; const int ret = BPF_REG_0; const int map_ptr = BPF_REG_1; const int index = BPF_REG_2; if (map->map_flags & BPF_F_INNER_MAP) return -EOPNOTSUPP; *insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value)); *insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0); if (!map->bypass_spec_v1) { *insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 4); *insn++ = BPF_ALU32_IMM(BPF_AND, ret, array->index_mask); } else { *insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 3); } if (is_power_of_2(elem_size)) { *insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(elem_size)); } else { *insn++ = BPF_ALU64_IMM(BPF_MUL, ret, elem_size); } *insn++ = BPF_ALU64_REG(BPF_ADD, ret, map_ptr); *insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1); *insn++ = BPF_MOV64_IMM(ret, 0); return insn - insn_buf;} /* Called from eBPF program */static void *percpu_array_map_lookup_elem(struct bpf_map *map, void *key){ struct bpf_array *array = container_of(map, struct bpf_array, map); u32 index = *(u32 *)key; if (unlikely(index >= array->map.max_entries)) return NULL; return this_cpu_ptr(array->pptrs[index & array->index_mask]);} /* emit BPF instructions equivalent to C code of percpu_array_map_lookup_elem() */static int percpu_array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf){ struct bpf_array *array = container_of(map, struct bpf_array, map); struct bpf_insn *insn = insn_buf; if (!bpf_jit_supports_percpu_insn()) return -EOPNOTSUPP; if (map->map_flags & BPF_F_INNER_MAP) return -EOPNOTSUPP; BUILD_BUG_ON(offsetof(struct bpf_array, map) != 0); *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, offsetof(struct bpf_array, pptrs)); *insn++ = BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0); if (!map->bypass_spec_v1) { *insn++ = BPF_JMP_IMM(BPF_JGE, BPF_REG_0, map->max_entries, 6); *insn++ = BPF_ALU32_IMM(BPF_AND, BPF_REG_0, array->index_mask); } else { *insn++ = BPF_JMP_IMM(BPF_JGE, BPF_REG_0, map->max_entries, 5); } *insn++ = BPF_ALU64_IMM(BPF_LSH, BPF_REG_0, 3); *insn++ = BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1); *insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0); *insn++ = BPF_MOV64_PERCPU_REG(BPF_REG_0, BPF_REG_0); *insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1); *insn++ = BPF_MOV64_IMM(BPF_REG_0, 0); return insn - insn_buf;} static void *percpu_array_map_lookup_percpu_elem(struct bpf_map *map, void *key, u32 cpu){ struct bpf_array *array = container_of(map, struct bpf_array, map); u32 index = *(u32 *)key; if (cpu >= nr_cpu_ids) return NULL; if (unlikely(index >= array->map.max_entries)) return NULL; return per_cpu_ptr(array->pptrs[index & array->index_mask], cpu);} int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value){ struct bpf_array *array = container_of(map, struct bpf_array, map); u32 index = *(u32 *)key; void __percpu *pptr; int cpu, off = 0; u32 size; if (unlikely(index >= array->map.max_entries)) return -ENOENT; /* per_cpu areas are zero-filled and bpf programs can only * access 'value_size' of them, so copying rounded areas * will not leak any kernel data */ size = array->elem_size; rcu_read_lock(); pptr = array->pptrs[index & array->index_mask]; for_each_possible_cpu(cpu) { copy_map_value_long(map, value + off, per_cpu_ptr(pptr, cpu)); check_and_init_map_value(map, value + off); off += size; } rcu_read_unlock(); return 0;} /* Called from syscall */static int array_map_get_next_key(struct bpf_map *map, void *key, void *next_key){ struct bpf_array *array = container_of(map, struct bpf_array, map); u32 index = key ? *(u32 *)key : U32_MAX; u32 *next = (u32 *)next_key; if (index >= array->map.max_entries) { *next = 0; return 0; } if (index == array->map.max_entries - 1) return -ENOENT; *next = index + 1; return 0;} /* Called from syscall or from eBPF program */static long array_map_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags){ struct bpf_array *array = container_of(map, struct bpf_array, map); u32 index = *(u32 *)key; char *val; if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST)) /* unknown flags */ return -EINVAL; if (unlikely(index >= array->map.max_entries)) /* all elements were pre-allocated, cannot insert a new one */ return -E2BIG; if (unlikely(map_flags & BPF_NOEXIST)) /* all elements already exist */ return -EEXIST; if (unlikely((map_flags & BPF_F_LOCK) && !btf_record_has_field(map->record, BPF_SPIN_LOCK))) return -EINVAL; if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { val = this_cpu_ptr(array->pptrs[index & array->index_mask]); copy_map_value(map, val, value); bpf_obj_free_fields(array->map.record, val); } else { val = array->value + (u64)array->elem_size * (index & array->index_mask); if (map_flags & BPF_F_LOCK) copy_map_value_locked(map, val, value, false); else copy_map_value(map, val, value); bpf_obj_free_fields(array->map.record, val); } return 0;} int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value, u64 map_flags){ struct bpf_array *array = container_of(map, struct bpf_array, map); u32 index = *(u32 *)key; void __percpu *pptr; int cpu, off = 0; u32 size; if (unlikely(map_flags > BPF_EXIST)) /* unknown flags */ return -EINVAL; if (unlikely(index >= array->map.max_entries)) /* all elements were pre-allocated, cannot insert a new one */ return -E2BIG; if (unlikely(map_flags == BPF_NOEXIST)) /* all elements already exist */ return -EEXIST; /* the user space will provide round_up(value_size, 8) bytes that * will be copied into per-cpu area. bpf programs can only access * value_size of it. During lookup the same extra bytes will be * returned or zeros which were zero-filled by percpu_alloc, * so no kernel data leaks possible */ size = array->elem_size; rcu_read_lock(); pptr = array->pptrs[index & array->index_mask]; for_each_possible_cpu(cpu) { copy_map_value_long(map, per_cpu_ptr(pptr, cpu), value + off); bpf_obj_free_fields(array->map.record, per_cpu_ptr(pptr, cpu)); off += size; } rcu_read_unlock(); return 0;} /* Called from syscall or from eBPF program */static long array_map_delete_elem(struct bpf_map *map, void *key){ return -EINVAL;} static void *array_map_vmalloc_addr(struct bpf_array *array){ return (void *)round_down((unsigned long)array, PAGE_SIZE);} static void array_map_free_timers_wq(struct bpf_map *map){ struct bpf_array *array = container_of(map, struct bpf_array, map); int i; /* We don't reset or free fields other than timer and workqueue * on uref dropping to zero. */ if (btf_record_has_field(map->record, BPF_TIMER | BPF_WORKQUEUE)) { for (i = 0; i < array->map.max_entries; i++) { if (btf_record_has_field(map->record, BPF_TIMER)) bpf_obj_free_timer(map->record, array_map_elem_ptr(array, i)); if (btf_record_has_field(map->record, BPF_WORKQUEUE)) bpf_obj_free_workqueue(map->record, array_map_elem_ptr(array, i)); } }} /* Called when map->refcnt goes to zero, either from workqueue or from syscall */static void array_map_free(struct bpf_map *map){ struct bpf_array *array = container_of(map, struct bpf_array, map); int i; if (!IS_ERR_OR_NULL(map->record)) { if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { for (i = 0; i < array->map.max_entries; i++) { void __percpu *pptr = array->pptrs[i & array->index_mask]; int cpu; for_each_possible_cpu(cpu) { bpf_obj_free_fields(map->record, per_cpu_ptr(pptr, cpu)); cond_resched(); } } } else { for (i = 0; i < array->map.max_entries; i++) bpf_obj_free_fields(map->record, array_map_elem_ptr(array, i)); } } if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) bpf_array_free_percpu(array); if (array->map.map_flags & BPF_F_MMAPABLE) bpf_map_area_free(array_map_vmalloc_addr(array)); else bpf_map_area_free(array);} static void array_map_seq_show_elem(struct bpf_map *map, void *key, struct seq_file *m){ void *value; rcu_read_lock(); value = array_map_lookup_elem(map, key); if (!value) { rcu_read_unlock(); return; } if (map->btf_key_type_id) seq_printf(m, "%u: ", *(u32 *)key); btf_type_seq_show(map->btf, map->btf_value_type_id, value, m); seq_putc(m, '\n');Lines 1–500 of 1441. Load more
// SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com * Copyright (c) 2016,2017 Facebook */ #include <linux/bpf.h> #include <linux/btf.h> #include <linux/err.h> #include <linux/slab.h> #include <linux/mm.h> #include <linux/filter.h> #include <linux/perf_event.h> #include <uapi/linux/btf.h> #include <linux/rcupdate_trace.h> #include <linux/btf_ids.h> #include "map_in_map.h" #define ARRAY_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_MMAPABLE | BPF_F_ACCESS_MASK | \ BPF_F_PRESERVE_ELEMS | BPF_F_INNER_MAP) static void bpf_array_free_percpu(struct bpf_array *array) { int i; for (i = 0; i < array->map.max_entries; i++) { free_percpu(array->pptrs[i]); cond_resched(); } } static int bpf_array_alloc_percpu(struct bpf_array *array) { void __percpu *ptr; int i; for (i = 0; i < array->map.max_entries; i++) { ptr = bpf_map_alloc_percpu(&array->map, array->elem_size, 8, GFP_USER | __GFP_NOWARN); if (!ptr) { bpf_array_free_percpu(array); return -ENOMEM; } array->pptrs[i] = ptr; cond_resched(); } return 0; } /* Called from syscall */ int array_map_alloc_check(union bpf_attr *attr) { bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY; int numa_node = bpf_map_attr_numa_node(attr); /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || attr->value_size == 0 || attr->map_flags & ~ARRAY_CREATE_FLAG_MASK || !bpf_map_flags_access_ok(attr->map_flags) || (percpu && numa_node != NUMA_NO_NODE)) return -EINVAL; if (attr->map_type != BPF_MAP_TYPE_ARRAY && attr->map_flags & (BPF_F_MMAPABLE | BPF_F_INNER_MAP)) return -EINVAL; if (attr->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY && attr->map_flags & BPF_F_PRESERVE_ELEMS) return -EINVAL; /* avoid overflow on round_up(map->value_size) */ if (attr->value_size > INT_MAX) return -E2BIG; /* percpu map value size is bound by PCPU_MIN_UNIT_SIZE */ if (percpu && round_up(attr->value_size, 8) > PCPU_MIN_UNIT_SIZE) return -E2BIG; return 0; } static struct bpf_map *array_map_alloc(union bpf_attr *attr) { bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY; int numa_node = bpf_map_attr_numa_node(attr); u32 elem_size, index_mask, max_entries; bool bypass_spec_v1 = bpf_bypass_spec_v1(NULL); u64 array_size, mask64; struct bpf_array *array; elem_size = round_up(attr->value_size, 8); max_entries = attr->max_entries; /* On 32 bit archs roundup_pow_of_two() with max_entries that has * upper most bit set in u32 space is undefined behavior due to * resulting 1U << 32, so do it manually here in u64 space. */ mask64 = fls_long(max_entries - 1); mask64 = 1ULL << mask64; mask64 -= 1; index_mask = mask64; if (!bypass_spec_v1) { /* round up array size to nearest power of 2, * since cpu will speculate within index_mask limits */ max_entries = index_mask + 1; /* Check for overflows. */ if (max_entries < attr->max_entries) return ERR_PTR(-E2BIG); } array_size = sizeof(*array); if (percpu) { array_size += (u64) max_entries * sizeof(void *); } else { /* rely on vmalloc() to return page-aligned memory and * ensure array->value is exactly page-aligned */ if (attr->map_flags & BPF_F_MMAPABLE) { array_size = PAGE_ALIGN(array_size); array_size += PAGE_ALIGN((u64) max_entries * elem_size); } else { array_size += (u64) max_entries * elem_size; } } /* allocate all map elements and zero-initialize them */ if (attr->map_flags & BPF_F_MMAPABLE) { void *data; /* kmalloc'ed memory can't be mmap'ed, use explicit vmalloc */ data = bpf_map_area_mmapable_alloc(array_size, numa_node); if (!data) return ERR_PTR(-ENOMEM); array = data + PAGE_ALIGN(sizeof(struct bpf_array)) - offsetof(struct bpf_array, value); } else { array = bpf_map_area_alloc(array_size, numa_node); } if (!array) return ERR_PTR(-ENOMEM); array->index_mask = index_mask; array->map.bypass_spec_v1 = bypass_spec_v1; /* copy mandatory map attributes */ bpf_map_init_from_attr(&array->map, attr); array->elem_size = elem_size; if (percpu && bpf_array_alloc_percpu(array)) { bpf_map_area_free(array); return ERR_PTR(-ENOMEM); } return &array->map; } static void *array_map_elem_ptr(struct bpf_array* array, u32 index) { return array->value + (u64)array->elem_size * index; } /* Called from syscall or from eBPF program */ static void *array_map_lookup_elem(struct bpf_map *map, void *key) { struct bpf_array *array = container_of(map, struct bpf_array, map); u32 index = *(u32 *)key; if (unlikely(index >= array->map.max_entries)) return NULL; return array->value + (u64)array->elem_size * (index & array->index_mask); } static int array_map_direct_value_addr(const struct bpf_map *map, u64 *imm, u32 off) { struct bpf_array *array = container_of(map, struct bpf_array, map); if (map->max_entries != 1) return -ENOTSUPP; if (off >= map->value_size) return -EINVAL; *imm = (unsigned long)array->value; return 0; } static int array_map_direct_value_meta(const struct bpf_map *map, u64 imm, u32 *off) { struct bpf_array *array = container_of(map, struct bpf_array, map); u64 base = (unsigned long)array->value; u64 range = array->elem_size; if (map->max_entries != 1) return -ENOTSUPP; if (imm < base || imm >= base + range) return -ENOENT; *off = imm - base; return 0; } /* emit BPF instructions equivalent to C code of array_map_lookup_elem() */ static int array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) { struct bpf_array *array = container_of(map, struct bpf_array, map); struct bpf_insn *insn = insn_buf; u32 elem_size = array->elem_size; const int ret = BPF_REG_0; const int map_ptr = BPF_REG_1; const int index = BPF_REG_2; if (map->map_flags & BPF_F_INNER_MAP) return -EOPNOTSUPP; *insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value)); *insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0); if (!map->bypass_spec_v1) { *insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 4); *insn++ = BPF_ALU32_IMM(BPF_AND, ret, array->index_mask); } else { *insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 3); } if (is_power_of_2(elem_size)) { *insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(elem_size)); } else { *insn++ = BPF_ALU64_IMM(BPF_MUL, ret, elem_size); } *insn++ = BPF_ALU64_REG(BPF_ADD, ret, map_ptr); *insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1); *insn++ = BPF_MOV64_IMM(ret, 0); return insn - insn_buf; } /* Called from eBPF program */ static void *percpu_array_map_lookup_elem(struct bpf_map *map, void *key) { struct bpf_array *array = container_of(map, struct bpf_array, map); u32 index = *(u32 *)key; if (unlikely(index >= array->map.max_entries)) return NULL; return this_cpu_ptr(array->pptrs[index & array->index_mask]); } /* emit BPF instructions equivalent to C code of percpu_array_map_lookup_elem() */ static int percpu_array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) { struct bpf_array *array = container_of(map, struct bpf_array, map); struct bpf_insn *insn = insn_buf; if (!bpf_jit_supports_percpu_insn()) return -EOPNOTSUPP; if (map->map_flags & BPF_F_INNER_MAP) return -EOPNOTSUPP; BUILD_BUG_ON(offsetof(struct bpf_array, map) != 0); *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, offsetof(struct bpf_array, pptrs)); *insn++ = BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0); if (!map->bypass_spec_v1) { *insn++ = BPF_JMP_IMM(BPF_JGE, BPF_REG_0, map->max_entries, 6); *insn++ = BPF_ALU32_IMM(BPF_AND, BPF_REG_0, array->index_mask); } else { *insn++ = BPF_JMP_IMM(BPF_JGE, BPF_REG_0, map->max_entries, 5); } *insn++ = BPF_ALU64_IMM(BPF_LSH, BPF_REG_0, 3); *insn++ = BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1); *insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0); *insn++ = BPF_MOV64_PERCPU_REG(BPF_REG_0, BPF_REG_0); *insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1); *insn++ = BPF_MOV64_IMM(BPF_REG_0, 0); return insn - insn_buf; } static void *percpu_array_map_lookup_percpu_elem(struct bpf_map *map, void *key, u32 cpu) { struct bpf_array *array = container_of(map, struct bpf_array, map); u32 index = *(u32 *)key; if (cpu >= nr_cpu_ids) return NULL; if (unlikely(index >= array->map.max_entries)) return NULL; return per_cpu_ptr(array->pptrs[index & array->index_mask], cpu); } int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value) { struct bpf_array *array = container_of(map, struct bpf_array, map); u32 index = *(u32 *)key; void __percpu *pptr; int cpu, off = 0; u32 size; if (unlikely(index >= array->map.max_entries)) return -ENOENT; /* per_cpu areas are zero-filled and bpf programs can only * access 'value_size' of them, so copying rounded areas * will not leak any kernel data */ size = array->elem_size; rcu_read_lock(); pptr = array->pptrs[index & array->index_mask]; for_each_possible_cpu(cpu) { copy_map_value_long(map, value + off, per_cpu_ptr(pptr, cpu)); check_and_init_map_value(map, value + off); off += size; } rcu_read_unlock(); return 0; } /* Called from syscall */ static int array_map_get_next_key(struct bpf_map *map, void *key, void *next_key) { struct bpf_array *array = container_of(map, struct bpf_array, map); u32 index = key ? *(u32 *)key : U32_MAX; u32 *next = (u32 *)next_key; if (index >= array->map.max_entries) { *next = 0; return 0; } if (index == array->map.max_entries - 1) return -ENOENT; *next = index + 1; return 0; } /* Called from syscall or from eBPF program */ static long array_map_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { struct bpf_array *array = container_of(map, struct bpf_array, map); u32 index = *(u32 *)key; char *val; if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST)) /* unknown flags */ return -EINVAL; if (unlikely(index >= array->map.max_entries)) /* all elements were pre-allocated, cannot insert a new one */ return -E2BIG; if (unlikely(map_flags & BPF_NOEXIST)) /* all elements already exist */ return -EEXIST; if (unlikely((map_flags & BPF_F_LOCK) && !btf_record_has_field(map->record, BPF_SPIN_LOCK))) return -EINVAL; if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { val = this_cpu_ptr(array->pptrs[index & array->index_mask]); copy_map_value(map, val, value); bpf_obj_free_fields(array->map.record, val); } else { val = array->value + (u64)array->elem_size * (index & array->index_mask); if (map_flags & BPF_F_LOCK) copy_map_value_locked(map, val, value, false); else copy_map_value(map, val, value); bpf_obj_free_fields(array->map.record, val); } return 0; } int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value, u64 map_flags) { struct bpf_array *array = container_of(map, struct bpf_array, map); u32 index = *(u32 *)key; void __percpu *pptr; int cpu, off = 0; u32 size; if (unlikely(map_flags > BPF_EXIST)) /* unknown flags */ return -EINVAL; if (unlikely(index >= array->map.max_entries)) /* all elements were pre-allocated, cannot insert a new one */ return -E2BIG; if (unlikely(map_flags == BPF_NOEXIST)) /* all elements already exist */ return -EEXIST; /* the user space will provide round_up(value_size, 8) bytes that * will be copied into per-cpu area. bpf programs can only access * value_size of it. During lookup the same extra bytes will be * returned or zeros which were zero-filled by percpu_alloc, * so no kernel data leaks possible */ size = array->elem_size; rcu_read_lock(); pptr = array->pptrs[index & array->index_mask]; for_each_possible_cpu(cpu) { copy_map_value_long(map, per_cpu_ptr(pptr, cpu), value + off); bpf_obj_free_fields(array->map.record, per_cpu_ptr(pptr, cpu)); off += size; } rcu_read_unlock(); return 0; } /* Called from syscall or from eBPF program */ static long array_map_delete_elem(struct bpf_map *map, void *key) { return -EINVAL; } static void *array_map_vmalloc_addr(struct bpf_array *array) { return (void *)round_down((unsigned long)array, PAGE_SIZE); } static void array_map_free_timers_wq(struct bpf_map *map) { struct bpf_array *array = container_of(map, struct bpf_array, map); int i; /* We don't reset or free fields other than timer and workqueue * on uref dropping to zero. */ if (btf_record_has_field(map->record, BPF_TIMER | BPF_WORKQUEUE)) { for (i = 0; i < array->map.max_entries; i++) { if (btf_record_has_field(map->record, BPF_TIMER)) bpf_obj_free_timer(map->record, array_map_elem_ptr(array, i)); if (btf_record_has_field(map->record, BPF_WORKQUEUE)) bpf_obj_free_workqueue(map->record, array_map_elem_ptr(array, i)); } } } /* Called when map->refcnt goes to zero, either from workqueue or from syscall */ static void array_map_free(struct bpf_map *map) { struct bpf_array *array = container_of(map, struct bpf_array, map); int i; if (!IS_ERR_OR_NULL(map->record)) { if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { for (i = 0; i < array->map.max_entries; i++) { void __percpu *pptr = array->pptrs[i & array->index_mask]; int cpu; for_each_possible_cpu(cpu) { bpf_obj_free_fields(map->record, per_cpu_ptr(pptr, cpu)); cond_resched(); } } } else { for (i = 0; i < array->map.max_entries; i++) bpf_obj_free_fields(map->record, array_map_elem_ptr(array, i)); } } if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) bpf_array_free_percpu(array); if (array->map.map_flags & BPF_F_MMAPABLE) bpf_map_area_free(array_map_vmalloc_addr(array)); else bpf_map_area_free(array); } static void array_map_seq_show_elem(struct bpf_map *map, void *key, struct seq_file *m) { void *value; rcu_read_lock(); value = array_map_lookup_elem(map, key); if (!value) { rcu_read_unlock(); return; } if (map->btf_key_type_id) seq_printf(m, "%u: ", *(u32 *)key); btf_type_seq_show(map->btf, map->btf_value_type_id, value, m); seq_putc(m, '\n');