summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/core.c5
-rw-r--r--kernel/bpf/inode.c7
-rw-r--r--kernel/bpf/syscall.c24
-rw-r--r--kernel/bpf/verifier.c639
-rw-r--r--kernel/cgroup.c7
-rw-r--r--kernel/cpu.c33
-rw-r--r--kernel/cpuset.c4
-rw-r--r--kernel/events/core.c55
-rw-r--r--kernel/futex.c27
-rw-r--r--kernel/irq/ipi.c1
-rw-r--r--kernel/kcov.c3
-rw-r--r--kernel/kexec_core.c7
-rw-r--r--kernel/locking/lockdep.c37
-rw-r--r--kernel/locking/lockdep_proc.c2
-rw-r--r--kernel/locking/qspinlock_stat.h8
-rw-r--r--kernel/workqueue.c29
16 files changed, 736 insertions, 152 deletions
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index e4248fe79513..d781b077431f 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -794,6 +794,11 @@ void __weak bpf_int_jit_compile(struct bpf_prog *prog)
{
}
+bool __weak bpf_helper_changes_skb_data(void *func)
+{
+ return false;
+}
+
/* To execute LD_ABS/LD_IND instructions __bpf_prog_run() may call
* skb_copy_bits(), so provide a weak definition of it for NET-less config.
*/
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index f2ece3c174a5..8f94ca1860cf 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -31,10 +31,10 @@ static void *bpf_any_get(void *raw, enum bpf_type type)
{
switch (type) {
case BPF_TYPE_PROG:
- atomic_inc(&((struct bpf_prog *)raw)->aux->refcnt);
+ raw = bpf_prog_inc(raw);
break;
case BPF_TYPE_MAP:
- bpf_map_inc(raw, true);
+ raw = bpf_map_inc(raw, true);
break;
default:
WARN_ON_ONCE(1);
@@ -297,7 +297,8 @@ static void *bpf_obj_do_get(const struct filename *pathname,
goto out;
raw = bpf_any_get(inode->i_private, *type);
- touch_atime(&path);
+ if (!IS_ERR(raw))
+ touch_atime(&path);
path_put(&path);
return raw;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index adc5e4bd74f8..cf5e9f7ad13a 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -218,11 +218,18 @@ struct bpf_map *__bpf_map_get(struct fd f)
return f.file->private_data;
}
-void bpf_map_inc(struct bpf_map *map, bool uref)
+/* prog's and map's refcnt limit */
+#define BPF_MAX_REFCNT 32768
+
+struct bpf_map *bpf_map_inc(struct bpf_map *map, bool uref)
{
- atomic_inc(&map->refcnt);
+ if (atomic_inc_return(&map->refcnt) > BPF_MAX_REFCNT) {
+ atomic_dec(&map->refcnt);
+ return ERR_PTR(-EBUSY);
+ }
if (uref)
atomic_inc(&map->usercnt);
+ return map;
}
struct bpf_map *bpf_map_get_with_uref(u32 ufd)
@@ -234,7 +241,7 @@ struct bpf_map *bpf_map_get_with_uref(u32 ufd)
if (IS_ERR(map))
return map;
- bpf_map_inc(map, true);
+ map = bpf_map_inc(map, true);
fdput(f);
return map;
@@ -658,6 +665,15 @@ static struct bpf_prog *__bpf_prog_get(struct fd f)
return f.file->private_data;
}
+struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog)
+{
+ if (atomic_inc_return(&prog->aux->refcnt) > BPF_MAX_REFCNT) {
+ atomic_dec(&prog->aux->refcnt);
+ return ERR_PTR(-EBUSY);
+ }
+ return prog;
+}
+
/* called by sockets/tracing/seccomp before attaching program to an event
* pairs with bpf_prog_put()
*/
@@ -670,7 +686,7 @@ struct bpf_prog *bpf_prog_get(u32 ufd)
if (IS_ERR(prog))
return prog;
- atomic_inc(&prog->aux->refcnt);
+ prog = bpf_prog_inc(prog);
fdput(f);
return prog;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 6345623d6b02..84bff68cf80e 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1,4 +1,5 @@
/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
+ * Copyright (c) 2016 Facebook
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
@@ -136,13 +137,32 @@ enum bpf_reg_type {
FRAME_PTR, /* reg == frame_pointer */
PTR_TO_STACK, /* reg == frame_pointer + imm */
CONST_IMM, /* constant integer value */
+
+ /* PTR_TO_PACKET represents:
+ * skb->data
+ * skb->data + imm
+ * skb->data + (u16) var
+ * skb->data + (u16) var + imm
+ * if (range > 0) then [ptr, ptr + range - off) is safe to access
+ * if (id > 0) means that some 'var' was added
+ * if (off > 0) menas that 'imm' was added
+ */
+ PTR_TO_PACKET,
+ PTR_TO_PACKET_END, /* skb->data + headlen */
};
struct reg_state {
enum bpf_reg_type type;
union {
- /* valid when type == CONST_IMM | PTR_TO_STACK */
- long imm;
+ /* valid when type == CONST_IMM | PTR_TO_STACK | UNKNOWN_VALUE */
+ s64 imm;
+
+ /* valid when type == PTR_TO_PACKET* */
+ struct {
+ u32 id;
+ u16 off;
+ u16 range;
+ };
/* valid when type == CONST_PTR_TO_MAP | PTR_TO_MAP_VALUE |
* PTR_TO_MAP_VALUE_OR_NULL
@@ -247,40 +267,39 @@ static const char * const reg_type_str[] = {
[FRAME_PTR] = "fp",
[PTR_TO_STACK] = "fp",
[CONST_IMM] = "imm",
+ [PTR_TO_PACKET] = "pkt",
+ [PTR_TO_PACKET_END] = "pkt_end",
};
-static const struct {
- int map_type;
- int func_id;
-} func_limit[] = {
- {BPF_MAP_TYPE_PROG_ARRAY, BPF_FUNC_tail_call},
- {BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_FUNC_perf_event_read},
- {BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_FUNC_perf_event_output},
- {BPF_MAP_TYPE_STACK_TRACE, BPF_FUNC_get_stackid},
-};
-
-static void print_verifier_state(struct verifier_env *env)
+static void print_verifier_state(struct verifier_state *state)
{
+ struct reg_state *reg;
enum bpf_reg_type t;
int i;
for (i = 0; i < MAX_BPF_REG; i++) {
- t = env->cur_state.regs[i].type;
+ reg = &state->regs[i];
+ t = reg->type;
if (t == NOT_INIT)
continue;
verbose(" R%d=%s", i, reg_type_str[t]);
if (t == CONST_IMM || t == PTR_TO_STACK)
- verbose("%ld", env->cur_state.regs[i].imm);
+ verbose("%lld", reg->imm);
+ else if (t == PTR_TO_PACKET)
+ verbose("(id=%d,off=%d,r=%d)",
+ reg->id, reg->off, reg->range);
+ else if (t == UNKNOWN_VALUE && reg->imm)
+ verbose("%lld", reg->imm);
else if (t == CONST_PTR_TO_MAP || t == PTR_TO_MAP_VALUE ||
t == PTR_TO_MAP_VALUE_OR_NULL)
verbose("(ks=%d,vs=%d)",
- env->cur_state.regs[i].map_ptr->key_size,
- env->cur_state.regs[i].map_ptr->value_size);
+ reg->map_ptr->key_size,
+ reg->map_ptr->value_size);
}
for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
- if (env->cur_state.stack_slot_type[i] == STACK_SPILL)
+ if (state->stack_slot_type[i] == STACK_SPILL)
verbose(" fp%d=%s", -MAX_BPF_STACK + i,
- reg_type_str[env->cur_state.spilled_regs[i / BPF_REG_SIZE].type]);
+ reg_type_str[state->spilled_regs[i / BPF_REG_SIZE].type]);
}
verbose("\n");
}
@@ -556,6 +575,8 @@ static bool is_spillable_regtype(enum bpf_reg_type type)
case PTR_TO_MAP_VALUE_OR_NULL:
case PTR_TO_STACK:
case PTR_TO_CTX:
+ case PTR_TO_PACKET:
+ case PTR_TO_PACKET_END:
case FRAME_PTR:
case CONST_PTR_TO_MAP:
return true;
@@ -655,6 +676,27 @@ static int check_map_access(struct verifier_env *env, u32 regno, int off,
return 0;
}
+#define MAX_PACKET_OFF 0xffff
+
+static int check_packet_access(struct verifier_env *env, u32 regno, int off,
+ int size)
+{
+ struct reg_state *regs = env->cur_state.regs;
+ struct reg_state *reg = &regs[regno];
+ int linear_size = (int) reg->range - (int) reg->off;
+
+ if (linear_size < 0 || linear_size >= MAX_PACKET_OFF) {
+ verbose("verifier bug\n");
+ return -EFAULT;
+ }
+ if (off < 0 || off + size > linear_size) {
+ verbose("invalid access to packet, off=%d size=%d, allowed=%d\n",
+ off, size, linear_size);
+ return -EACCES;
+ }
+ return 0;
+}
+
/* check access to 'struct bpf_context' fields */
static int check_ctx_access(struct verifier_env *env, int off, int size,
enum bpf_access_type t)
@@ -685,6 +727,45 @@ static bool is_pointer_value(struct verifier_env *env, int regno)
}
}
+static int check_ptr_alignment(struct verifier_env *env, struct reg_state *reg,
+ int off, int size)
+{
+ if (reg->type != PTR_TO_PACKET) {
+ if (off % size != 0) {
+ verbose("misaligned access off %d size %d\n", off, size);
+ return -EACCES;
+ } else {
+ return 0;
+ }
+ }
+
+ switch (env->prog->type) {
+ case BPF_PROG_TYPE_SCHED_CLS:
+ case BPF_PROG_TYPE_SCHED_ACT:
+ break;
+ default:
+ verbose("verifier is misconfigured\n");
+ return -EACCES;
+ }
+
+ if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
+ /* misaligned access to packet is ok on x86,arm,arm64 */
+ return 0;
+
+ if (reg->id && size != 1) {
+ verbose("Unknown packet alignment. Only byte-sized access allowed\n");
+ return -EACCES;
+ }
+
+ /* skb->data is NET_IP_ALIGN-ed */
+ if ((NET_IP_ALIGN + reg->off + off) % size != 0) {
+ verbose("misaligned packet access off %d+%d+%d size %d\n",
+ NET_IP_ALIGN, reg->off, off, size);
+ return -EACCES;
+ }
+ return 0;
+}
+
/* check whether memory at (regno + off) is accessible for t = (read | write)
* if t==write, value_regno is a register which value is stored into memory
* if t==read, value_regno is a register which will receive the value from memory
@@ -696,21 +777,21 @@ static int check_mem_access(struct verifier_env *env, u32 regno, int off,
int value_regno)
{
struct verifier_state *state = &env->cur_state;
+ struct reg_state *reg = &state->regs[regno];
int size, err = 0;
- if (state->regs[regno].type == PTR_TO_STACK)
- off += state->regs[regno].imm;
+ if (reg->type == PTR_TO_STACK)
+ off += reg->imm;
size = bpf_size_to_bytes(bpf_size);
if (size < 0)
return size;
- if (off % size != 0) {
- verbose("misaligned access off %d size %d\n", off, size);
- return -EACCES;
- }
+ err = check_ptr_alignment(env, reg, off, size);
+ if (err)
+ return err;
- if (state->regs[regno].type == PTR_TO_MAP_VALUE) {
+ if (reg->type == PTR_TO_MAP_VALUE) {
if (t == BPF_WRITE && value_regno >= 0 &&
is_pointer_value(env, value_regno)) {
verbose("R%d leaks addr into map\n", value_regno);
@@ -720,18 +801,25 @@ static int check_mem_access(struct verifier_env *env, u32 regno, int off,
if (!err && t == BPF_READ && value_regno >= 0)
mark_reg_unknown_value(state->regs, value_regno);
- } else if (state->regs[regno].type == PTR_TO_CTX) {
+ } else if (reg->type == PTR_TO_CTX) {
if (t == BPF_WRITE && value_regno >= 0 &&
is_pointer_value(env, value_regno)) {
verbose("R%d leaks addr into ctx\n", value_regno);
return -EACCES;
}
err = check_ctx_access(env, off, size, t);
- if (!err && t == BPF_READ && value_regno >= 0)
+ if (!err && t == BPF_READ && value_regno >= 0) {
mark_reg_unknown_value(state->regs, value_regno);
+ if (off == offsetof(struct __sk_buff, data) &&
+ env->allow_ptr_leaks)
+ /* note that reg.[id|off|range] == 0 */
+ state->regs[value_regno].type = PTR_TO_PACKET;
+ else if (off == offsetof(struct __sk_buff, data_end) &&
+ env->allow_ptr_leaks)
+ state->regs[value_regno].type = PTR_TO_PACKET_END;
+ }
- } else if (state->regs[regno].type == FRAME_PTR ||
- state->regs[regno].type == PTR_TO_STACK) {
+ } else if (reg->type == FRAME_PTR || reg->type == PTR_TO_STACK) {
if (off >= 0 || off < -MAX_BPF_STACK) {
verbose("invalid stack off=%d size=%d\n", off, size);
return -EACCES;
@@ -747,11 +835,28 @@ static int check_mem_access(struct verifier_env *env, u32 regno, int off,
} else {
err = check_stack_read(state, off, size, value_regno);
}
+ } else if (state->regs[regno].type == PTR_TO_PACKET) {
+ if (t == BPF_WRITE) {
+ verbose("cannot write into packet\n");
+ return -EACCES;
+ }
+ err = check_packet_access(env, regno, off, size);
+ if (!err && t == BPF_READ && value_regno >= 0)
+ mark_reg_unknown_value(state->regs, value_regno);
} else {
verbose("R%d invalid mem access '%s'\n",
- regno, reg_type_str[state->regs[regno].type]);
+ regno, reg_type_str[reg->type]);
return -EACCES;
}
+
+ if (!err && size <= 2 && value_regno >= 0 && env->allow_ptr_leaks &&
+ state->regs[value_regno].type == UNKNOWN_VALUE) {
+ /* 1 or 2 byte load zero-extends, determine the number of
+ * zero upper bits. Not doing it fo 4 byte load, since
+ * such values cannot be added to ptr_to_packet anyway.
+ */
+ state->regs[value_regno].imm = 64 - size * 8;
+ }
return err;
}
@@ -943,27 +1048,52 @@ static int check_func_arg(struct verifier_env *env, u32 regno,
static int check_map_func_compatibility(struct bpf_map *map, int func_id)
{
- bool bool_map, bool_func;
- int i;
-
if (!map)
return 0;
- for (i = 0; i < ARRAY_SIZE(func_limit); i++) {
- bool_map = (map->map_type == func_limit[i].map_type);
- bool_func = (func_id == func_limit[i].func_id);
- /* only when map & func pair match it can continue.
- * don't allow any other map type to be passed into
- * the special func;
- */
- if (bool_func && bool_map != bool_func) {
- verbose("cannot pass map_type %d into func %d\n",
- map->map_type, func_id);
- return -EINVAL;
- }
+ /* We need a two way check, first is from map perspective ... */
+ switch (map->map_type) {
+ case BPF_MAP_TYPE_PROG_ARRAY:
+ if (func_id != BPF_FUNC_tail_call)
+ goto error;
+ break;
+ case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
+ if (func_id != BPF_FUNC_perf_event_read &&
+ func_id != BPF_FUNC_perf_event_output)
+ goto error;
+ break;
+ case BPF_MAP_TYPE_STACK_TRACE:
+ if (func_id != BPF_FUNC_get_stackid)
+ goto error;
+ break;
+ default:
+ break;
+ }
+
+ /* ... and second from the function itself. */
+ switch (func_id) {
+ case BPF_FUNC_tail_call:
+ if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY)
+ goto error;
+ break;
+ case BPF_FUNC_perf_event_read:
+ case BPF_FUNC_perf_event_output:
+ if (map->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY)
+ goto error;
+ break;
+ case BPF_FUNC_get_stackid:
+ if (map->map_type != BPF_MAP_TYPE_STACK_TRACE)
+ goto error;
+ break;
+ default:
+ break;
}
return 0;
+error:
+ verbose("cannot pass map_type %d into func %d\n",
+ map->map_type, func_id);
+ return -EINVAL;
}
static int check_raw_mode(const struct bpf_func_proto *fn)
@@ -984,6 +1114,29 @@ static int check_raw_mode(const struct bpf_func_proto *fn)
return count > 1 ? -EINVAL : 0;
}
+static void clear_all_pkt_pointers(struct verifier_env *env)
+{
+ struct verifier_state *state = &env->cur_state;
+ struct reg_state *regs = state->regs, *reg;
+ int i;
+
+ for (i = 0; i < MAX_BPF_REG; i++)
+ if (regs[i].type == PTR_TO_PACKET ||
+ regs[i].type == PTR_TO_PACKET_END)
+ mark_reg_unknown_value(regs, i);
+
+ for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
+ if (state->stack_slot_type[i] != STACK_SPILL)
+ continue;
+ reg = &state->spilled_regs[i / BPF_REG_SIZE];
+ if (reg->type != PTR_TO_PACKET &&
+ reg->type != PTR_TO_PACKET_END)
+ continue;
+ reg->type = UNKNOWN_VALUE;
+ reg->imm = 0;
+ }
+}
+
static int check_call(struct verifier_env *env, int func_id)
{
struct verifier_state *state = &env->cur_state;
@@ -991,6 +1144,7 @@ static int check_call(struct verifier_env *env, int func_id)
struct reg_state *regs = state->regs;
struct reg_state *reg;
struct bpf_call_arg_meta meta;
+ bool changes_data;
int i, err;
/* find function prototype */
@@ -1013,6 +1167,8 @@ static int check_call(struct verifier_env *env, int func_id)
return -EINVAL;
}
+ changes_data = bpf_helper_changes_skb_data(fn->func);
+
memset(&meta, 0, sizeof(meta));
/* We only support one arg being in raw mode at the moment, which
@@ -1083,13 +1239,196 @@ static int check_call(struct verifier_env *env, int func_id)
if (err)
return err;
+ if (changes_data)
+ clear_all_pkt_pointers(env);
+ return 0;
+}
+
+static int check_packet_ptr_add(struct verifier_env *env, struct bpf_insn *insn)
+{
+ struct reg_state *regs = env->cur_state.regs;
+ struct reg_state *dst_reg = &regs[insn->dst_reg];
+ struct reg_state *src_reg = &regs[insn->src_reg];
+ s32 imm;
+
+ if (BPF_SRC(insn->code) == BPF_K) {
+ /* pkt_ptr += imm */
+ imm = insn->imm;
+
+add_imm:
+ if (imm <= 0) {
+ verbose("addition of negative constant to packet pointer is not allowed\n");
+ return -EACCES;
+ }
+ if (imm >= MAX_PACKET_OFF ||
+ imm + dst_reg->off >= MAX_PACKET_OFF) {
+ verbose("constant %d is too large to add to packet pointer\n",
+ imm);
+ return -EACCES;
+ }
+ /* a constant was added to pkt_ptr.
+ * Remember it while keeping the same 'id'
+ */
+ dst_reg->off += imm;
+ } else {
+ if (src_reg->type == CONST_IMM) {
+ /* pkt_ptr += reg where reg is known constant */
+ imm = src_reg->imm;
+ goto add_imm;
+ }
+ /* disallow pkt_ptr += reg
+ * if reg is not uknown_value with guaranteed zero upper bits
+ * otherwise pkt_ptr may overflow and addition will become
+ * subtraction which is not allowed
+ */
+ if (src_reg->type != UNKNOWN_VALUE) {
+ verbose("cannot add '%s' to ptr_to_packet\n",
+ reg_type_str[src_reg->type]);
+ return -EACCES;
+ }
+ if (src_reg->imm < 48) {
+ verbose("cannot add integer value with %lld upper zero bits to ptr_to_packet\n",
+ src_reg->imm);
+ return -EACCES;
+ }
+ /* dst_reg stays as pkt_ptr type and since some positive
+ * integer value was added to the pointer, increment its 'id'
+ */
+ dst_reg->id++;
+
+ /* something was added to pkt_ptr, set range and off to zero */
+ dst_reg->off = 0;
+ dst_reg->range = 0;
+ }
+ return 0;
+}
+
+static int evaluate_reg_alu(struct verifier_env *env, struct bpf_insn *insn)
+{
+ struct reg_state *regs = env->cur_state.regs;
+ struct reg_state *dst_reg = &regs[insn->dst_reg];
+ u8 opcode = BPF_OP(insn->code);
+ s64 imm_log2;
+
+ /* for type == UNKNOWN_VALUE:
+ * imm > 0 -> number of zero upper bits
+ * imm == 0 -> don't track which is the same as all bits can be non-zero
+ */
+
+ if (BPF_SRC(insn->code) == BPF_X) {
+ struct reg_state *src_reg = &regs[insn->src_reg];
+
+ if (src_reg->type == UNKNOWN_VALUE && src_reg->imm > 0 &&
+ dst_reg->imm && opcode == BPF_ADD) {
+ /* dreg += sreg
+ * where both have zero upper bits. Adding them
+ * can only result making one more bit non-zero
+ * in the larger value.
+ * Ex. 0xffff (imm=48) + 1 (imm=63) = 0x10000 (imm=47)
+ * 0xffff (imm=48) + 0xffff = 0x1fffe (imm=47)
+ */
+ dst_reg->imm = min(dst_reg->imm, src_reg->imm);
+ dst_reg->imm--;
+ return 0;
+ }
+ if (src_reg->type == CONST_IMM && src_reg->imm > 0 &&
+ dst_reg->imm && opcode == BPF_ADD) {
+ /* dreg += sreg
+ * where dreg has zero upper bits and sreg is const.
+ * Adding them can only result making one more bit
+ * non-zero in the larger value.
+ */
+ imm_log2 = __ilog2_u64((long long)src_reg->imm);
+ dst_reg->imm = min(dst_reg->imm, 63 - imm_log2);
+ dst_reg->imm--;
+ return 0;
+ }
+ /* all other cases non supported yet, just mark dst_reg */
+ dst_reg->imm = 0;
+ return 0;
+ }
+
+ /* sign extend 32-bit imm into 64-bit to make sure that
+ * negative values occupy bit 63. Note ilog2() would have
+ * been incorrect, since sizeof(insn->imm) == 4
+ */
+ imm_log2 = __ilog2_u64((long long)insn->imm);
+
+ if (dst_reg->imm && opcode == BPF_LSH) {
+ /* reg <<= imm
+ * if reg was a result of 2 byte load, then its imm == 48
+ * which means that upper 48 bits are zero and shifting this reg
+ * left by 4 would mean that upper 44 bits are still zero
+ */
+ dst_reg->imm -= insn->imm;
+ } else if (dst_reg->imm && opcode == BPF_MUL) {
+ /* reg *= imm
+ * if multiplying by 14 subtract 4
+ * This is conservative calculation of upper zero bits.
+ * It's not trying to special case insn->imm == 1 or 0 cases
+ */
+ dst_reg->imm -= imm_log2 + 1;
+ } else if (opcode == BPF_AND) {
+ /* reg &= imm */
+ dst_reg->imm = 63 - imm_log2;
+ } else if (dst_reg->imm && opcode == BPF_ADD) {
+ /* reg += imm */
+ dst_reg->imm = min(dst_reg->imm, 63 - imm_log2);
+ dst_reg->imm--;
+ } else if (opcode == BPF_RSH) {
+ /* reg >>= imm
+ * which means that after right shift, upper bits will be zero
+ * note that verifier already checked that
+ * 0 <= imm < 64 for shift insn
+ */
+ dst_reg->imm += insn->imm;
+ if (unlikely(dst_reg->imm > 64))
+ /* some dumb code did:
+ * r2 = *(u32 *)mem;
+ * r2 >>= 32;
+ * and all bits are zero now */
+ dst_reg->imm = 64;
+ } else {
+ /* all other alu ops, means that we don't know what will
+ * happen to the value, mark it with unknown number of zero bits
+ */
+ dst_reg->imm = 0;
+ }
+
+ if (dst_reg->imm < 0) {
+ /* all 64 bits of the register can contain non-zero bits
+ * and such value cannot be added to ptr_to_packet, since it
+ * may overflow, mark it as unknown to avoid further eval
+ */
+ dst_reg->imm = 0;
+ }
+ return 0;
+}
+
+static int evaluate_reg_imm_alu(struct verifier_env *env, struct bpf_insn *insn)
+{
+ struct reg_state *regs = env->cur_state.regs;
+ struct reg_state *dst_reg = &regs[insn->dst_reg];
+ struct reg_state *src_reg = &regs[insn->src_reg];
+ u8 opcode = BPF_OP(insn->code);
+
+ /* dst_reg->type == CONST_IMM here, simulate execution of 'add' insn.
+ * Don't care about overflow or negative values, just add them
+ */
+ if (opcode == BPF_ADD && BPF_SRC(insn->code) == BPF_K)
+ dst_reg->imm += insn->imm;
+ else if (opcode == BPF_ADD && BPF_SRC(insn->code) == BPF_X &&
+ src_reg->type == CONST_IMM)
+ dst_reg->imm += src_reg->imm;
+ else
+ mark_reg_unknown_value(regs, insn->dst_reg);
return 0;
}
/* check validity of 32-bit and 64-bit arithmetic operations */
static int check_alu_op(struct verifier_env *env, struct bpf_insn *insn)
{
- struct reg_state *regs = env->cur_state.regs;
+ struct reg_state *regs = env->cur_state.regs, *dst_reg;
u8 opcode = BPF_OP(insn->code);
int err;
@@ -1178,8 +1517,6 @@ static int check_alu_op(struct verifier_env *env, struct bpf_insn *insn)
} else { /* all other ALU ops: and, sub, xor, add, ... */
- bool stack_relative = false;
-
if (BPF_SRC(insn->code) == BPF_X) {
if (insn->imm != 0 || insn->off != 0) {
verbose("BPF_ALU uses reserved fields\n");
@@ -1217,11 +1554,34 @@ static int check_alu_op(struct verifier_env *env, struct bpf_insn *insn)
}
}
+ /* check dest operand */
+ err = check_reg_arg(regs, insn->dst_reg, DST_OP_NO_MARK);
+ if (err)
+ return err;
+
+ dst_reg = &regs[insn->dst_reg];
+
/* pattern match 'bpf_add Rx, imm' instruction */
if (opcode == BPF_ADD && BPF_CLASS(insn->code) == BPF_ALU64 &&
- regs[insn->dst_reg].type == FRAME_PTR &&
- BPF_SRC(insn->code) == BPF_K) {
- stack_relative = true;
+ dst_reg->type == FRAME_PTR && BPF_SRC(insn->code) == BPF_K) {
+ dst_reg->type = PTR_TO_STACK;
+ dst_reg->imm = insn->imm;
+ return 0;
+ } else if (opcode == BPF_ADD &&
+ BPF_CLASS(insn->code) == BPF_ALU64 &&
+ dst_reg->type == PTR_TO_PACKET) {
+ /* ptr_to_packet += K|X */
+ return check_packet_ptr_add(env, insn);
+ } else if (BPF_CLASS(insn->code) == BPF_ALU64 &&
+ dst_reg->type == UNKNOWN_VALUE &&
+ env->allow_ptr_leaks) {
+ /* unknown += K|X */
+ return evaluate_reg_alu(env, insn);
+ } else if (BPF_CLASS(insn->code) == BPF_ALU64 &&
+ dst_reg->type == CONST_IMM &&
+ env->allow_ptr_leaks) {
+ /* reg_imm += K|X */
+ return evaluate_reg_imm_alu(env, insn);
} else if (is_pointer_value(env, insn->dst_reg)) {
verbose("R%d pointer arithmetic prohibited\n",
insn->dst_reg);
@@ -1233,24 +1593,45 @@ static int check_alu_op(struct verifier_env *env, struct bpf_insn *insn)
return -EACCES;
}
- /* check dest operand */
- err = check_reg_arg(regs, insn->dst_reg, DST_OP);
- if (err)
- return err;
-
- if (stack_relative) {
- regs[insn->dst_reg].type = PTR_TO_STACK;
- regs[insn->dst_reg].imm = insn->imm;
- }
+ /* mark dest operand */
+ mark_reg_unknown_value(regs, insn->dst_reg);
}
return 0;
}
+static void find_good_pkt_pointers(struct verifier_env *env,
+ struct reg_state *dst_reg)
+{
+ struct verifier_state *state = &env->cur_state;
+ struct reg_state *regs = state->regs, *reg;
+ int i;
+ /* r2 = r3;
+ * r2 += 8
+ * if (r2 > pkt_end) goto somewhere
+ * r2 == dst_reg, pkt_end == src_reg,
+ * r2=pkt(id=n,off=8,r=0)
+ * r3=pkt(id=n,off=0,r=0)
+ * find register r3 and mark its range as r3=pkt(id=n,off=0,r=8)
+ * so that range of bytes [r3, r3 + 8) is safe to access
+ */
+ for (i = 0; i < MAX_BPF_REG; i++)
+ if (regs[i].type == PTR_TO_PACKET && regs[i].id == dst_reg->id)
+ regs[i].range = dst_reg->off;
+
+ for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
+ if (state->stack_slot_type[i] != STACK_SPILL)
+ continue;
+ reg = &state->spilled_regs[i / BPF_REG_SIZE];
+ if (reg->type == PTR_TO_PACKET && reg->id == dst_reg->id)
+ reg->range = dst_reg->off;
+ }
+}
+
static int check_cond_jmp_op(struct verifier_env *env,
struct bpf_insn *insn, int *insn_idx)
{
- struct reg_state *regs = env->cur_state.regs;
+ struct reg_state *regs = env->cur_state.regs, *dst_reg;
struct verifier_state *other_branch;
u8 opcode = BPF_OP(insn->code);
int err;
@@ -1288,11 +1669,12 @@ static int check_cond_jmp_op(struct verifier_env *env,
if (err)
return err;
+ dst_reg = &regs[insn->dst_reg];
+
/* detect if R == 0 where R was initialized to zero earlier */
if (BPF_SRC(insn->code) == BPF_K &&
(opcode == BPF_JEQ || opcode == BPF_JNE) &&
- regs[insn->dst_reg].type == CONST_IMM &&
- regs[insn->dst_reg].imm == insn->imm) {
+ dst_reg->type == CONST_IMM && dst_reg->imm == insn->imm) {
if (opcode == BPF_JEQ) {
/* if (imm == imm) goto pc+off;
* only follow the goto, ignore fall-through
@@ -1314,44 +1696,30 @@ static int check_cond_jmp_op(struct verifier_env *env,
/* detect if R == 0 where R is returned value from bpf_map_lookup_elem() */
if (BPF_SRC(insn->code) == BPF_K &&
- insn->imm == 0 && (opcode == BPF_JEQ ||
- opcode == BPF_JNE) &&
- regs[insn->dst_reg].type == PTR_TO_MAP_VALUE_OR_NULL) {
+ insn->imm == 0 && (opcode == BPF_JEQ || opcode == BPF_JNE) &&
+ dst_reg->type == PTR_TO_MAP_VALUE_OR_NULL) {
if (opcode == BPF_JEQ) {
/* next fallthrough insn can access memory via
* this register
*/
regs[insn->dst_reg].type = PTR_TO_MAP_VALUE;
/* branch targer cannot access it, since reg == 0 */
- other_branch->regs[insn->dst_reg].type = CONST_IMM;
- other_branch->regs[insn->dst_reg].imm = 0;
+ mark_reg_unknown_value(other_branch->regs,
+ insn->dst_reg);
} else {
other_branch->regs[insn->dst_reg].type = PTR_TO_MAP_VALUE;
- regs[insn->dst_reg].type = CONST_IMM;
- regs[insn->dst_reg].imm = 0;
+ mark_reg_unknown_value(regs, insn->dst_reg);
}
+ } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGT &&
+ dst_reg->type == PTR_TO_PACKET &&
+ regs[insn->src_reg].type == PTR_TO_PACKET_END) {
+ find_good_pkt_pointers(env, dst_reg);
} else if (is_pointer_value(env, insn->dst_reg)) {
verbose("R%d pointer comparison prohibited\n", insn->dst_reg);
return -EACCES;
- } else if (BPF_SRC(insn->code) == BPF_K &&
- (opcode == BPF_JEQ || opcode == BPF_JNE)) {
-
- if (opcode == BPF_JEQ) {
- /* detect if (R == imm) goto
- * and in the target state recognize that R = imm
- */
- other_branch->regs[insn->dst_reg].type = CONST_IMM;
- other_branch->regs[insn->dst_reg].imm = insn->imm;
- } else {
- /* detect if (R != imm) goto
- * and in the fall-through state recognize that R = imm
- */
- regs[insn->dst_reg].type = CONST_IMM;
- regs[insn->dst_reg].imm = insn->imm;
- }
}
if (log_level)
- print_verifier_state(env);
+ print_verifier_state(&env->cur_state);
return 0;
}
@@ -1429,14 +1797,14 @@ static int check_ld_abs(struct verifier_env *env, struct bpf_insn *insn)
int i, err;
if (!may_access_skb(env->prog->type)) {
- verbose("BPF_LD_ABS|IND instructions not allowed for this program type\n");
+ verbose("BPF_LD_[ABS|IND] instructions not allowed for this program type\n");
return -EINVAL;
}
if (insn->dst_reg != BPF_REG_0 || insn->off != 0 ||
BPF_SIZE(insn->code) == BPF_DW ||
(mode == BPF_ABS && insn->src_reg != BPF_REG_0)) {
- verbose("BPF_LD_ABS uses reserved fields\n");
+ verbose("BPF_LD_[ABS|IND] uses reserved fields\n");
return -EINVAL;
}
@@ -1669,6 +2037,58 @@ err_free:
return ret;
}
+/* the following conditions reduce the number of explored insns
+ * from ~140k to ~80k for ultra large programs that use a lot of ptr_to_packet
+ */
+static bool compare_ptrs_to_packet(struct reg_state *old, struct reg_state *cur)
+{
+ if (old->id != cur->id)
+ return false;
+
+ /* old ptr_to_packet is more conservative, since it allows smaller
+ * range. Ex:
+ * old(off=0,r=10) is equal to cur(off=0,r=20), because
+ * old(off=0,r=10) means that with range=10 the verifier proceeded
+ * further and found no issues with the program. Now we're in the same
+ * spot with cur(off=0,r=20), so we're safe too, since anything further
+ * will only be looking at most 10 bytes after this pointer.
+ */
+ if (old->off == cur->off && old->range < cur->range)
+ return true;
+
+ /* old(off=20,r=10) is equal to cur(off=22,re=22 or 5 or 0)
+ * since both cannot be used for packet access and safe(old)
+ * pointer has smaller off that could be used for further
+ * 'if (ptr > data_end)' check
+ * Ex:
+ * old(off=20,r=10) and cur(off=22,r=22) and cur(off=22,r=0) mean
+ * that we cannot access the packet.
+ * The safe range is:
+ * [ptr, ptr + range - off)
+ * so whenever off >=range, it means no safe bytes from this pointer.
+ * When comparing old->off <= cur->off, it means that older code
+ * went with smaller offset and that offset was later
+ * used to figure out the safe range after 'if (ptr > data_end)' check
+ * Say, 'old' state was explored like:
+ * ... R3(off=0, r=0)
+ * R4 = R3 + 20
+ * ... now R4(off=20,r=0) <-- here
+ * if (R4 > data_end)
+ * ... R4(off=20,r=20), R3(off=0,r=20) and R3 can be used to access.
+ * ... the code further went all the way to bpf_exit.
+ * Now the 'cur' state at the mark 'here' has R4(off=30,r=0).
+ * old_R4(off=20,r=0) equal to cur_R4(off=30,r=0), since if the verifier
+ * goes further, such cur_R4 will give larger safe packet range after
+ * 'if (R4 > data_end)' and all further insn were already good with r=20,
+ * so they will be good with r=30 and we can prune the search.
+ */
+ if (old->off <= cur->off &&
+ old->off >= old->range && cur->off >= cur->range)
+ return true;
+
+ return false;
+}
+
/* compare two verifier states
*
* all states stored in state_list are known to be valid, since
@@ -1697,17 +2117,25 @@ err_free:
*/
static bool states_equal(struct verifier_state *old, struct verifier_state *cur)
{
+ struct reg_state *rold, *rcur;
int i;
for (i = 0; i < MAX_BPF_REG; i++) {
- if (memcmp(&old->regs[i], &cur->regs[i],
- sizeof(old->regs[0])) != 0) {
- if (old->regs[i].type == NOT_INIT ||
- (old->regs[i].type == UNKNOWN_VALUE &&
- cur->regs[i].type != NOT_INIT))
- continue;
- return false;
- }
+ rold = &old->regs[i];
+ rcur = &cur->regs[i];
+
+ if (memcmp(rold, rcur, sizeof(*rold)) == 0)
+ continue;
+
+ if (rold->type == NOT_INIT ||
+ (rold->type == UNKNOWN_VALUE && rcur->type != NOT_INIT))
+ continue;
+
+ if (rold->type == PTR_TO_PACKET && rcur->type == PTR_TO_PACKET &&
+ compare_ptrs_to_packet(rold, rcur))
+ continue;
+
+ return false;
}
for (i = 0; i < MAX_BPF_STACK; i++) {
@@ -1829,7 +2257,7 @@ static int do_check(struct verifier_env *env)
if (log_level && do_print_state) {
verbose("\nfrom %d to %d:", prev_insn_idx, insn_idx);
- print_verifier_state(env);
+ print_verifier_state(&env->cur_state);
do_print_state = false;
}
@@ -2041,6 +2469,7 @@ process_bpf_exit:
insn_idx++;
}
+ verbose("processed %d insns\n", insn_processed);
return 0;
}
@@ -2092,7 +2521,6 @@ static int replace_map_fd_with_map_ptr(struct verifier_env *env)
if (IS_ERR(map)) {
verbose("fd %d is not pointing to valid bpf_map\n",
insn->imm);
- fdput(f);
return PTR_ERR(map);
}
@@ -2112,15 +2540,18 @@ static int replace_map_fd_with_map_ptr(struct verifier_env *env)
return -E2BIG;
}
- /* remember this map */
- env->used_maps[env->used_map_cnt++] = map;
-
/* hold the map. If the program is rejected by verifier,
* the map will be released by release_maps() or it
* will be used by the valid program until it's unloaded
* and all maps are released in free_bpf_prog_info()
*/
- bpf_map_inc(map, false);
+ map = bpf_map_inc(map, false);
+ if (IS_ERR(map)) {
+ fdput(f);
+ return PTR_ERR(map);
+ }
+ env->used_maps[env->used_map_cnt++] = map;
+
fdput(f);
next_insn:
insn++;
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 671dc05c0b0f..909a7d31ffd3 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2825,9 +2825,10 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
size_t nbytes, loff_t off, bool threadgroup)
{
struct task_struct *tsk;
+ struct cgroup_subsys *ss;
struct cgroup *cgrp;
pid_t pid;
- int ret;
+ int ssid, ret;
if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0)
return -EINVAL;
@@ -2875,8 +2876,10 @@ out_unlock_rcu:
rcu_read_unlock();
out_unlock_threadgroup:
percpu_up_write(&cgroup_threadgroup_rwsem);
+ for_each_subsys(ss, ssid)
+ if (ss->post_attach)
+ ss->post_attach();
cgroup_kn_unlock(of->kn);
- cpuset_post_attach_flush();
return ret ?: nbytes;
}
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 6ea42e8da861..3e3f6e49eabb 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -36,6 +36,7 @@
* @target: The target state
* @thread: Pointer to the hotplug thread
* @should_run: Thread should execute
+ * @rollback: Perform a rollback
* @cb_stat: The state for a single callback (install/uninstall)
* @cb: Single callback function (install/uninstall)
* @result: Result of the operation
@@ -47,6 +48,7 @@ struct cpuhp_cpu_state {
#ifdef CONFIG_SMP
struct task_struct *thread;
bool should_run;
+ bool rollback;
enum cpuhp_state cb_state;
int (*cb)(unsigned int cpu);
int result;
@@ -301,6 +303,11 @@ static int cpu_notify(unsigned long val, unsigned int cpu)
return __cpu_notify(val, cpu, -1, NULL);
}
+static void cpu_notify_nofail(unsigned long val, unsigned int cpu)
+{
+ BUG_ON(cpu_notify(val, cpu));
+}
+
/* Notifier wrappers for transitioning to state machine */
static int notify_prepare(unsigned int cpu)
{
@@ -477,6 +484,16 @@ static void cpuhp_thread_fun(unsigned int cpu)
} else {
ret = cpuhp_invoke_callback(cpu, st->cb_state, st->cb);
}
+ } else if (st->rollback) {
+ BUG_ON(st->state < CPUHP_AP_ONLINE_IDLE);
+
+ undo_cpu_down(cpu, st, cpuhp_ap_states);
+ /*
+ * This is a momentary workaround to keep the notifier users
+ * happy. Will go away once we got rid of the notifiers.
+ */
+ cpu_notify_nofail(CPU_DOWN_FAILED, cpu);
+ st->rollback = false;
} else {
/* Cannot happen .... */
BUG_ON(st->state < CPUHP_AP_ONLINE_IDLE);
@@ -636,11 +653,6 @@ static inline void check_for_tasks(int dead_cpu)
read_unlock(&tasklist_lock);
}
-static void cpu_notify_nofail(unsigned long val, unsigned int cpu)
-{
- BUG_ON(cpu_notify(val, cpu));
-}
-
static int notify_down_prepare(unsigned int cpu)
{
int err, nr_calls = 0;
@@ -721,9 +733,10 @@ static int takedown_cpu(unsigned int cpu)
*/
err = stop_machine(take_cpu_down, NULL, cpumask_of(cpu));
if (err) {
- /* CPU didn't die: tell everyone. Can't complain. */
- cpu_notify_nofail(CPU_DOWN_FAILED, cpu);
+ /* CPU refused to die */
irq_unlock_sparse();
+ /* Unpark the hotplug thread so we can rollback there */
+ kthread_unpark(per_cpu_ptr(&cpuhp_state, cpu)->thread);
return err;
}
BUG_ON(cpu_online(cpu));
@@ -832,6 +845,11 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen,
* to do the further cleanups.
*/
ret = cpuhp_down_callbacks(cpu, st, cpuhp_bp_states, target);
+ if (ret && st->state > CPUHP_TEARDOWN_CPU && st->state < prev_state) {
+ st->target = prev_state;
+ st->rollback = true;
+ cpuhp_kick_ap_work(cpu);
+ }
hasdied = prev_state != st->state && st->state == CPUHP_OFFLINE;
out:
@@ -1249,6 +1267,7 @@ static struct cpuhp_step cpuhp_ap_states[] = {
.name = "notify:online",
.startup = notify_online,
.teardown = notify_down_prepare,
+ .skip_onerr = true,
},
#endif
/*
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 00ab5c2b7c5b..1902956baba1 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -58,7 +58,6 @@
#include <asm/uaccess.h>
#include <linux/atomic.h>
#include <linux/mutex.h>
-#include <linux/workqueue.h>
#include <linux/cgroup.h>
#include <linux/wait.h>
@@ -1016,7 +1015,7 @@ static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from,
}
}
-void cpuset_post_attach_flush(void)
+static void cpuset_post_attach(void)
{
flush_workqueue(cpuset_migrate_mm_wq);
}
@@ -2087,6 +2086,7 @@ struct cgroup_subsys cpuset_cgrp_subsys = {
.can_attach = cpuset_can_attach,
.cancel_attach = cpuset_cancel_attach,
.attach = cpuset_attach,
+ .post_attach = cpuset_post_attach,
.bind = cpuset_bind,
.legacy_cftypes = files,
.early_init = true,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 9eb23dc27462..0bdc6e7d4908 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -412,7 +412,8 @@ int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write,
if (ret || !write)
return ret;
- if (sysctl_perf_cpu_time_max_percent == 100) {
+ if (sysctl_perf_cpu_time_max_percent == 100 ||
+ sysctl_perf_cpu_time_max_percent == 0) {
printk(KERN_WARNING
"perf: Dynamic interrupt throttling disabled, can hang your system!\n");
WRITE_ONCE(perf_sample_allowed_ns, 0);
@@ -1105,6 +1106,7 @@ static void put_ctx(struct perf_event_context *ctx)
* function.
*
* Lock order:
+ * cred_guard_mutex
* task_struct::perf_event_mutex
* perf_event_context::mutex
* perf_event::child_mutex;
@@ -3420,7 +3422,6 @@ static struct task_struct *
find_lively_task_by_vpid(pid_t vpid)
{
struct task_struct *task;
- int err;
rcu_read_lock();
if (!vpid)
@@ -3434,16 +3435,7 @@ find_lively_task_by_vpid(pid_t vpid)
if (!task)
return ERR_PTR(-ESRCH);
- /* Reuse ptrace permission checks for now. */
- err = -EACCES;
- if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS))
- goto errout;
-
return task;
-errout:
- put_task_struct(task);
- return ERR_PTR(err);
-
}
/*
@@ -8446,6 +8438,24 @@ SYSCALL_DEFINE5(perf_event_open,
get_online_cpus();
+ if (task) {
+ err = mutex_lock_interruptible(&task->signal->cred_guard_mutex);
+ if (err)
+ goto err_cpus;
+
+ /*
+ * Reuse ptrace permission checks for now.
+ *
+ * We must hold cred_guard_mutex across this and any potential
+ * perf_install_in_context() call for this new event to
+ * serialize against exec() altering our credentials (and the
+ * perf_event_exit_task() that could imply).
+ */
+ err = -EACCES;
+ if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS))
+ goto err_cred;
+ }
+
if (flags & PERF_FLAG_PID_CGROUP)
cgroup_fd = pid;
@@ -8453,7 +8463,7 @@ SYSCALL_DEFINE5(perf_event_open,
NULL, NULL, cgroup_fd);
if (IS_ERR(event)) {
err = PTR_ERR(event);
- goto err_cpus;
+ goto err_cred;
}
if (is_sampling_event(event)) {
@@ -8512,11 +8522,6 @@ SYSCALL_DEFINE5(perf_event_open,
goto err_context;
}
- if (task) {
- put_task_struct(task);
- task = NULL;
- }
-
/*
* Look up the group leader (we will attach this event to it):
*/
@@ -8614,6 +8619,11 @@ SYSCALL_DEFINE5(perf_event_open,
WARN_ON_ONCE(ctx->parent_ctx);
+ /*
+ * This is the point on no return; we cannot fail hereafter. This is
+ * where we start modifying current state.
+ */
+
if (move_group) {
/*
* See perf_event_ctx_lock() for comments on the details
@@ -8685,6 +8695,11 @@ SYSCALL_DEFINE5(perf_event_open,
mutex_unlock(&gctx->mutex);
mutex_unlock(&ctx->mutex);
+ if (task) {
+ mutex_unlock(&task->signal->cred_guard_mutex);
+ put_task_struct(task);
+ }
+
put_online_cpus();
mutex_lock(&current->perf_event_mutex);
@@ -8717,6 +8732,9 @@ err_alloc:
*/
if (!event_file)
free_event(event);
+err_cred:
+ if (task)
+ mutex_unlock(&task->signal->cred_guard_mutex);
err_cpus:
put_online_cpus();
err_task:
@@ -9001,6 +9019,9 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
/*
* When a child task exits, feed back event values to parent events.
+ *
+ * Can be called with cred_guard_mutex held when called from
+ * install_exec_creds().
*/
void perf_event_exit_task(struct task_struct *child)
{
diff --git a/kernel/futex.c b/kernel/futex.c
index a5d2e74c89e0..c20f06f38ef3 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1295,10 +1295,20 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this,
if (unlikely(should_fail_futex(true)))
ret = -EFAULT;
- if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))
+ if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)) {
ret = -EFAULT;
- else if (curval != uval)
- ret = -EINVAL;
+ } else if (curval != uval) {
+ /*
+ * If a unconditional UNLOCK_PI operation (user space did not
+ * try the TID->0 transition) raced with a waiter setting the
+ * FUTEX_WAITERS flag between get_user() and locking the hash
+ * bucket lock, retry the operation.
+ */
+ if ((FUTEX_TID_MASK & curval) == uval)
+ ret = -EAGAIN;
+ else
+ ret = -EINVAL;
+ }
if (ret) {
raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
return ret;
@@ -1525,8 +1535,8 @@ void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1,
if (likely(&hb1->chain != &hb2->chain)) {
plist_del(&q->list, &hb1->chain);
hb_waiters_dec(hb1);
- plist_add(&q->list, &hb2->chain);
hb_waiters_inc(hb2);
+ plist_add(&q->list, &hb2->chain);
q->lock_ptr = &hb2->lock;
}
get_futex_key_refs(key2);
@@ -2623,6 +2633,15 @@ retry:
if (ret == -EFAULT)
goto pi_faulted;
/*
+ * A unconditional UNLOCK_PI op raced against a waiter
+ * setting the FUTEX_WAITERS bit. Try again.
+ */
+ if (ret == -EAGAIN) {
+ spin_unlock(&hb->lock);
+ put_futex_key(&key);
+ goto retry;
+ }
+ /*
* wake_futex_pi has detected invalid state. Tell user
* space.
*/
diff --git a/kernel/irq/ipi.c b/kernel/irq/ipi.c
index c37f34b00a11..14777af8e097 100644
--- a/kernel/irq/ipi.c
+++ b/kernel/irq/ipi.c
@@ -94,6 +94,7 @@ unsigned int irq_reserve_ipi(struct irq_domain *domain,
data = irq_get_irq_data(virq + i);
cpumask_copy(data->common->affinity, dest);
data->common->ipi_offset = offset;
+ irq_set_status_flags(virq + i, IRQ_NO_BALANCING);
}
return virq;
diff --git a/kernel/kcov.c b/kernel/kcov.c
index 3efbee0834a8..a02f2dddd1d7 100644
--- a/kernel/kcov.c
+++ b/kernel/kcov.c
@@ -1,5 +1,6 @@
#define pr_fmt(fmt) "kcov: " fmt
+#define DISABLE_BRANCH_PROFILING
#include <linux/compiler.h>
#include <linux/types.h>
#include <linux/file.h>
@@ -43,7 +44,7 @@ struct kcov {
* Entry point from instrumented code.
* This is called once per basic-block/edge.
*/
-void __sanitizer_cov_trace_pc(void)
+void notrace __sanitizer_cov_trace_pc(void)
{
struct task_struct *t;
enum kcov_mode mode;
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index 8d34308ea449..1391d3ee3b86 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -1415,6 +1415,9 @@ static int __init crash_save_vmcoreinfo_init(void)
VMCOREINFO_OFFSET(page, lru);
VMCOREINFO_OFFSET(page, _mapcount);
VMCOREINFO_OFFSET(page, private);
+ VMCOREINFO_OFFSET(page, compound_dtor);
+ VMCOREINFO_OFFSET(page, compound_order);
+ VMCOREINFO_OFFSET(page, compound_head);
VMCOREINFO_OFFSET(pglist_data, node_zones);
VMCOREINFO_OFFSET(pglist_data, nr_zones);
#ifdef CONFIG_FLAT_NODE_MEM_MAP
@@ -1447,8 +1450,8 @@ static int __init crash_save_vmcoreinfo_init(void)
#ifdef CONFIG_X86
VMCOREINFO_NUMBER(KERNEL_IMAGE_SIZE);
#endif
-#ifdef CONFIG_HUGETLBFS
- VMCOREINFO_SYMBOL(free_huge_page);
+#ifdef CONFIG_HUGETLB_PAGE
+ VMCOREINFO_NUMBER(HUGETLB_PAGE_DTOR);
#endif
arch_crash_save_vmcoreinfo();
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index ed9410936a22..78c1c0ee6dc1 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -2176,15 +2176,37 @@ cache_hit:
chain->irq_context = hlock->irq_context;
i = get_first_held_lock(curr, hlock);
chain->depth = curr->lockdep_depth + 1 - i;
+
+ BUILD_BUG_ON((1UL << 24) <= ARRAY_SIZE(chain_hlocks));
+ BUILD_BUG_ON((1UL << 6) <= ARRAY_SIZE(curr->held_locks));
+ BUILD_BUG_ON((1UL << 8*sizeof(chain_hlocks[0])) <= ARRAY_SIZE(lock_classes));
+
if (likely(nr_chain_hlocks + chain->depth <= MAX_LOCKDEP_CHAIN_HLOCKS)) {
chain->base = nr_chain_hlocks;
- nr_chain_hlocks += chain->depth;
for (j = 0; j < chain->depth - 1; j++, i++) {
int lock_id = curr->held_locks[i].class_idx - 1;
chain_hlocks[chain->base + j] = lock_id;
}
chain_hlocks[chain->base + j] = class - lock_classes;
}
+
+ if (nr_chain_hlocks < MAX_LOCKDEP_CHAIN_HLOCKS)
+ nr_chain_hlocks += chain->depth;
+
+#ifdef CONFIG_DEBUG_LOCKDEP
+ /*
+ * Important for check_no_collision().
+ */
+ if (unlikely(nr_chain_hlocks > MAX_LOCKDEP_CHAIN_HLOCKS)) {
+ if (debug_locks_off_graph_unlock())
+ return 0;
+
+ print_lockdep_off("BUG: MAX_LOCKDEP_CHAIN_HLOCKS too low!");
+ dump_stack();
+ return 0;
+ }
+#endif
+
hlist_add_head_rcu(&chain->entry, hash_head);
debug_atomic_inc(chain_lookup_misses);
inc_chains();
@@ -2932,6 +2954,11 @@ static int mark_irqflags(struct task_struct *curr, struct held_lock *hlock)
return 1;
}
+static inline unsigned int task_irq_context(struct task_struct *task)
+{
+ return 2 * !!task->hardirq_context + !!task->softirq_context;
+}
+
static int separate_irq_context(struct task_struct *curr,
struct held_lock *hlock)
{
@@ -2940,8 +2967,6 @@ static int separate_irq_context(struct task_struct *curr,
/*
* Keep track of points where we cross into an interrupt context:
*/
- hlock->irq_context = 2*(curr->hardirq_context ? 1 : 0) +
- curr->softirq_context;
if (depth) {
struct held_lock *prev_hlock;
@@ -2973,6 +2998,11 @@ static inline int mark_irqflags(struct task_struct *curr,
return 1;
}
+static inline unsigned int task_irq_context(struct task_struct *task)
+{
+ return 0;
+}
+
static inline int separate_irq_context(struct task_struct *curr,
struct held_lock *hlock)
{
@@ -3241,6 +3271,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
hlock->acquire_ip = ip;
hlock->instance = lock;
hlock->nest_lock = nest_lock;
+ hlock->irq_context = task_irq_context(curr);
hlock->trylock = trylock;
hlock->read = read;
hlock->check = check;
diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c
index dbb61a302548..a0f61effad25 100644
--- a/kernel/locking/lockdep_proc.c
+++ b/kernel/locking/lockdep_proc.c
@@ -141,6 +141,8 @@ static int lc_show(struct seq_file *m, void *v)
int i;
if (v == SEQ_START_TOKEN) {
+ if (nr_chain_hlocks > MAX_LOCKDEP_CHAIN_HLOCKS)
+ seq_printf(m, "(buggered) ");
seq_printf(m, "all lock chains:\n");
return 0;
}
diff --git a/kernel/locking/qspinlock_stat.h b/kernel/locking/qspinlock_stat.h
index eb2a2c9bc3fc..d734b7502001 100644
--- a/kernel/locking/qspinlock_stat.h
+++ b/kernel/locking/qspinlock_stat.h
@@ -136,10 +136,12 @@ static ssize_t qstat_read(struct file *file, char __user *user_buf,
}
if (counter == qstat_pv_hash_hops) {
- u64 frac;
+ u64 frac = 0;
- frac = 100ULL * do_div(stat, kicks);
- frac = DIV_ROUND_CLOSEST_ULL(frac, kicks);
+ if (kicks) {
+ frac = 100ULL * do_div(stat, kicks);
+ frac = DIV_ROUND_CLOSEST_ULL(frac, kicks);
+ }
/*
* Return a X.XX decimal number
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 2232ae3e3ad6..3bfdff06eea7 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -666,6 +666,35 @@ static void set_work_pool_and_clear_pending(struct work_struct *work,
*/
smp_wmb();
set_work_data(work, (unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT, 0);
+ /*
+ * The following mb guarantees that previous clear of a PENDING bit
+ * will not be reordered with any speculative LOADS or STORES from
+ * work->current_func, which is executed afterwards. This possible
+ * reordering can lead to a missed execution on attempt to qeueue
+ * the same @work. E.g. consider this case:
+ *
+ * CPU#0 CPU#1
+ * ---------------------------- --------------------------------
+ *
+ * 1 STORE event_indicated
+ * 2 queue_work_on() {
+ * 3 test_and_set_bit(PENDING)
+ * 4 } set_..._and_clear_pending() {
+ * 5 set_work_data() # clear bit
+ * 6 smp_mb()
+ * 7 work->current_func() {
+ * 8 LOAD event_indicated
+ * }
+ *
+ * Without an explicit full barrier speculative LOAD on line 8 can
+ * be executed before CPU#0 does STORE on line 1. If that happens,
+ * CPU#0 observes the PENDING bit is still set and new execution of
+ * a @work is not queued in a hope, that CPU#1 will eventually
+ * finish the queued @work. Meanwhile CPU#1 does not see
+ * event_indicated is set, because speculative LOAD was executed
+ * before actual STORE.
+ */
+ smp_mb();
}
static void clear_work_data(struct work_struct *work)
generated by cgit v1.2.3 (git 2.39.1) at 2025-12-13 01:13:24 +0000