F: drivers/amba/
F: include/linux/amba/bus.h
+ARM PRIMECELL CLCD PL110 DRIVER
+M: Russell King <linux@armlinux.org.uk>
+S: Odd Fixes
+F: drivers/video/fbdev/amba-clcd.*
+
ARM PRIMECELL KMI PL050 DRIVER
M: Russell King <linux@armlinux.org.uk>
S: Odd Fixes
R: Martin KaFai Lau <kafai@fb.com>
R: Song Liu <songliubraving@fb.com>
R: Yonghong Song <yhs@fb.com>
- R: Andrii Nakryiko <andriin@fb.com>
+ R: Andrii Nakryiko <andrii@kernel.org>
R: John Fastabend <john.fastabend@gmail.com>
R: KP Singh <kpsingh@chromium.org>
L: netdev@vger.kernel.org
F: include/uapi/linux/can.h
F: include/uapi/linux/can/bcm.h
F: include/uapi/linux/can/gw.h
+F: include/uapi/linux/can/isotp.h
F: include/uapi/linux/can/raw.h
F: net/can/
F: Documentation/devicetree/bindings/net/qca,ar803x.yaml
F: Documentation/networking/phy.rst
F: drivers/net/mdio/
+F: drivers/net/mdio/of_mdio.c
F: drivers/net/pcs/
F: drivers/net/phy/
-F: drivers/of/of_mdio.c
F: drivers/of/of_net.c
F: include/dt-bindings/net/qca-ar803x.h
F: include/linux/*mdio*.h
F: include/uapi/drm/i915_drm.h
INTEL ETHERNET DRIVERS
-M: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
+M: Jesse Brandeburg <jesse.brandeburg@intel.com>
+M: Tony Nguyen <anthony.l.nguyen@intel.com>
L: intel-wired-lan@lists.osuosl.org (moderated for non-subscribers)
S: Supported
W: http://www.intel.com/support/feedback.htm
S: Maintained
F: drivers/hid/hid-mcp2221.c
-MCP25XXFD SPI-CAN NETWORK DRIVER
+MCP251XFD SPI-CAN NETWORK DRIVER
M: Marc Kleine-Budde <mkl@pengutronix.de>
M: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
R: Thomas Kopp <thomas.kopp@microchip.com>
L: linux-can@vger.kernel.org
S: Maintained
-F: Documentation/devicetree/bindings/net/can/microchip,mcp25xxfd.yaml
-F: drivers/net/can/spi/mcp25xxfd/
+F: Documentation/devicetree/bindings/net/can/microchip,mcp251xfd.yaml
+F: drivers/net/can/spi/mcp251xfd/
MCP4018 AND MCP4531 MICROCHIP DIGITAL POTENTIOMETER DRIVERS
M: Peter Rosin <peda@axentia.se>
M: Andrew Lunn <andrew@lunn.ch>
M: Vivien Didelot <vivien.didelot@gmail.com>
M: Florian Fainelli <f.fainelli@gmail.com>
+M: Vladimir Oltean <olteanv@gmail.com>
S: Maintained
F: Documentation/devicetree/bindings/net/dsa/
F: drivers/net/dsa/
F: net/ipv6/xfrm*
F: net/key/
F: net/xfrm/
+F: tools/testing/selftests/net/ipsec.c
NETWORKING [IPv4/IPv6]
M: "David S. Miller" <davem@davemloft.net>
F: drivers/net/ethernet/mscc/
F: include/soc/mscc/ocelot*
F: net/dsa/tag_ocelot.c
+F: tools/testing/selftests/drivers/net/ocelot/*
OCXL (Open Coherent Accelerator Processor Interface OpenCAPI) DRIVER
M: Frederic Barrat <fbarrat@linux.ibm.com>
PCI DRIVER FOR AARDVARK (Marvell Armada 3700)
M: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
+M: Pali Rohár <pali@kernel.org>
L: linux-pci@vger.kernel.org
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
L: linux-media@vger.kernel.org
S: Maintained
T: git git://linuxtv.org/media_tree.git
-F: Documentation/devicetree/bindings/media/i2c/imx274.txt
+F: Documentation/devicetree/bindings/media/i2c/sony,imx274.yaml
F: drivers/media/i2c/imx274.c
SONY IMX290 SENSOR DRIVER
F: include/linux/vga_switcheroo.h
VIA RHINE NETWORK DRIVER
-S: Orphan
+S: Maintained
+M: Kevin Brace <kevinbrace@bracecomputerlab.com>
F: drivers/net/ethernet/via/via-rhine.c
VIA SD/MMC CARD CONTROLLER DRIVER
F: arch/x86/mm/
X86 PLATFORM DRIVERS
-M: Darren Hart <dvhart@infradead.org>
-M: Andy Shevchenko <andy@infradead.org>
+M: Hans de Goede <hdegoede@redhat.com>
+M: Mark Gross <mgross@linux.intel.com>
L: platform-driver-x86@vger.kernel.org
-S: Odd Fixes
+S: Maintained
T: git git://git.infradead.org/linux-platform-drivers-x86.git
F: drivers/platform/olpc/
F: drivers/platform/x86/
unsigned char type;
#define NETDEV_HW_ADDR_T_LAN 1
#define NETDEV_HW_ADDR_T_SAN 2
-#define NETDEV_HW_ADDR_T_SLAVE 3
-#define NETDEV_HW_ADDR_T_UNICAST 4
-#define NETDEV_HW_ADDR_T_MULTICAST 5
+#define NETDEV_HW_ADDR_T_UNICAST 3
+#define NETDEV_HW_ADDR_T_MULTICAST 4
bool global_use;
int sync_cnt;
int refcount;
* int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm *p,
* int cmd);
* Add, change, delete or get information on an IPv4 tunnel.
+ * struct net_device *(*ndo_get_peer_dev)(struct net_device *dev);
+ * If a device is paired with a peer device, return the peer instance.
+ * The caller must be under RCU read context.
*/
struct net_device_ops {
int (*ndo_init)(struct net_device *dev);
struct devlink_port * (*ndo_get_devlink_port)(struct net_device *dev);
int (*ndo_tunnel_ctl)(struct net_device *dev,
struct ip_tunnel_parm *p, int cmd);
+ struct net_device * (*ndo_get_peer_dev)(struct net_device *dev);
};
/**
* @udp_tunnel_nic: UDP tunnel offload state
* @xdp_state: stores info on attached XDP BPF programs
*
+ * @nested_level: Used as as a parameter of spin_lock_nested() of
+ * dev->addr_list_lock.
+ * @unlink_list: As netif_addr_lock() can be called recursively,
+ * keep a list of interfaces to be deleted.
+ *
* FIXME: cleanup struct net_device such that network protocol info
* moves out.
*/
unsigned short type;
unsigned short hard_header_len;
unsigned char min_header_len;
+ unsigned char name_assign_type;
unsigned short needed_headroom;
unsigned short needed_tailroom;
unsigned char addr_len;
unsigned char upper_level;
unsigned char lower_level;
+
unsigned short neigh_priv_len;
unsigned short dev_id;
unsigned short dev_port;
spinlock_t addr_list_lock;
- unsigned char name_assign_type;
- bool uc_promisc;
+
struct netdev_hw_addr_list uc;
struct netdev_hw_addr_list mc;
struct netdev_hw_addr_list dev_addrs;
#ifdef CONFIG_SYSFS
struct kset *queues_kset;
+#endif
+#ifdef CONFIG_LOCKDEP
+ struct list_head unlink_list;
#endif
unsigned int promiscuity;
unsigned int allmulti;
+ bool uc_promisc;
+#ifdef CONFIG_LOCKDEP
+ unsigned char nested_level;
+#endif
/* Protocol-specific pointers */
void dev_lstats_read(struct net_device *dev, u64 *packets, u64 *bytes);
+static inline void dev_sw_netstats_rx_add(struct net_device *dev, unsigned int len)
+{
+ struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
+
+ u64_stats_update_begin(&tstats->syncp);
+ tstats->rx_bytes += len;
+ tstats->rx_packets++;
+ u64_stats_update_end(&tstats->syncp);
+}
+
static inline void dev_lstats_add(struct net_device *dev, unsigned int len)
{
struct pcpu_lstats *lstats = this_cpu_ptr(dev->lstats);
static inline void netif_addr_lock(struct net_device *dev)
{
- spin_lock(&dev->addr_list_lock);
-}
+ unsigned char nest_level = 0;
-static inline void netif_addr_lock_nested(struct net_device *dev)
-{
- spin_lock_nested(&dev->addr_list_lock, dev->lower_level);
+#ifdef CONFIG_LOCKDEP
+ nest_level = dev->nested_level;
+#endif
+ spin_lock_nested(&dev->addr_list_lock, nest_level);
}
static inline void netif_addr_lock_bh(struct net_device *dev)
{
- spin_lock_bh(&dev->addr_list_lock);
+ unsigned char nest_level = 0;
+
+#ifdef CONFIG_LOCKDEP
+ nest_level = dev->nested_level;
+#endif
+ local_bh_disable();
+ spin_lock_nested(&dev->addr_list_lock, nest_level);
}
static inline void netif_addr_unlock(struct net_device *dev)
extern int dev_tx_weight;
extern int gro_normal_batch;
+enum {
+ NESTED_SYNC_IMM_BIT,
+ NESTED_SYNC_TODO_BIT,
+};
+
+#define __NESTED_SYNC_BIT(bit) ((u32)1 << (bit))
+#define __NESTED_SYNC(name) __NESTED_SYNC_BIT(NESTED_SYNC_ ## name ## _BIT)
+
+#define NESTED_SYNC_IMM __NESTED_SYNC(IMM)
+#define NESTED_SYNC_TODO __NESTED_SYNC(TODO)
+
+struct netdev_nested_priv {
+ unsigned char flags;
+ void *data;
+};
+
bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev);
struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev,
struct list_head **iter);
struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev,
struct list_head **iter);
+#ifdef CONFIG_LOCKDEP
+static LIST_HEAD(net_unlink_list);
+
+static inline void net_unlink_todo(struct net_device *dev)
+{
+ if (list_empty(&dev->unlink_list))
+ list_add_tail(&dev->unlink_list, &net_unlink_list);
+}
+#endif
+
/* iterate through upper list, must be called under RCU read lock */
#define netdev_for_each_upper_dev_rcu(dev, updev, iter) \
for (iter = &(dev)->adj_list.upper, \
int netdev_walk_all_upper_dev_rcu(struct net_device *dev,
int (*fn)(struct net_device *upper_dev,
- void *data),
- void *data);
+ struct netdev_nested_priv *priv),
+ struct netdev_nested_priv *priv);
bool netdev_has_upper_dev_all_rcu(struct net_device *dev,
struct net_device *upper_dev);
struct list_head **iter);
int netdev_walk_all_lower_dev(struct net_device *dev,
int (*fn)(struct net_device *lower_dev,
- void *data),
- void *data);
+ struct netdev_nested_priv *priv),
+ struct netdev_nested_priv *priv);
int netdev_walk_all_lower_dev_rcu(struct net_device *dev,
int (*fn)(struct net_device *lower_dev,
- void *data),
- void *data);
+ struct netdev_nested_priv *priv),
+ struct netdev_nested_priv *priv);
void *netdev_adjacent_get_private(struct list_head *adj_list);
void *netdev_lower_get_first_private_rcu(struct net_device *dev);
u64 msize_max_value;
int ref_obj_id;
int func_id;
+ u32 btf_id;
+ u32 ret_btf_id;
};
struct btf *btf_vmlinux;
[PTR_TO_XDP_SOCK] = "xdp_sock",
[PTR_TO_BTF_ID] = "ptr_",
[PTR_TO_BTF_ID_OR_NULL] = "ptr_or_null_",
+ [PTR_TO_PERCPU_BTF_ID] = "percpu_ptr_",
[PTR_TO_MEM] = "mem",
[PTR_TO_MEM_OR_NULL] = "mem_or_null",
[PTR_TO_RDONLY_BUF] = "rdonly_buf",
/* reg->off should be 0 for SCALAR_VALUE */
verbose(env, "%lld", reg->var_off.value + reg->off);
} else {
- if (t == PTR_TO_BTF_ID || t == PTR_TO_BTF_ID_OR_NULL)
+ if (t == PTR_TO_BTF_ID ||
+ t == PTR_TO_BTF_ID_OR_NULL ||
+ t == PTR_TO_PERCPU_BTF_ID)
verbose(env, "%s", kernel_type_name(reg->btf_id));
verbose(env, "(id=%d", reg->id);
if (reg_type_may_be_refcounted_or_null(t))
case PTR_TO_RDONLY_BUF_OR_NULL:
case PTR_TO_RDWR_BUF:
case PTR_TO_RDWR_BUF_OR_NULL:
+ case PTR_TO_PERCPU_BTF_ID:
return true;
default:
return false;
return reg->type == SCALAR_VALUE && tnum_is_const(reg->var_off);
}
+ static bool __is_scalar_unbounded(struct bpf_reg_state *reg)
+ {
+ return tnum_is_unknown(reg->var_off) &&
+ reg->smin_value == S64_MIN && reg->smax_value == S64_MAX &&
+ reg->umin_value == 0 && reg->umax_value == U64_MAX &&
+ reg->s32_min_value == S32_MIN && reg->s32_max_value == S32_MAX &&
+ reg->u32_min_value == 0 && reg->u32_max_value == U32_MAX;
+ }
+
+ static bool register_is_bounded(struct bpf_reg_state *reg)
+ {
+ return reg->type == SCALAR_VALUE && !__is_scalar_unbounded(reg);
+ }
+
static bool __is_pointer_value(bool allow_ptr_leaks,
const struct bpf_reg_state *reg)
{
if (value_regno >= 0)
reg = &cur->regs[value_regno];
- if (reg && size == BPF_REG_SIZE && register_is_const(reg) &&
+ if (reg && size == BPF_REG_SIZE && register_is_bounded(reg) &&
!register_is_null(reg) && env->bpf_capable) {
if (dst_reg != BPF_REG_FP) {
/* The backtracking logic can only recognize explicit
case BPF_PROG_TYPE_CGROUP_SKB:
if (t == BPF_WRITE)
return false;
- /* fallthrough */
+ fallthrough;
/* Program types with direct read + write access go here! */
case BPF_PROG_TYPE_SCHED_CLS:
},
};
+ #ifdef CONFIG_NET
static const struct bpf_reg_types btf_id_sock_common_types = {
.types = {
PTR_TO_SOCK_COMMON,
},
.btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
};
+ #endif
static const struct bpf_reg_types mem_types = {
.types = {
static const struct bpf_reg_types const_map_ptr_types = { .types = { CONST_PTR_TO_MAP } };
static const struct bpf_reg_types btf_ptr_types = { .types = { PTR_TO_BTF_ID } };
static const struct bpf_reg_types spin_lock_types = { .types = { PTR_TO_MAP_VALUE } };
+ static const struct bpf_reg_types percpu_btf_ptr_types = { .types = { PTR_TO_PERCPU_BTF_ID } };
static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = {
[ARG_PTR_TO_MAP_KEY] = &map_key_value_types,
[ARG_PTR_TO_CTX] = &context_types,
[ARG_PTR_TO_CTX_OR_NULL] = &context_types,
[ARG_PTR_TO_SOCK_COMMON] = &sock_types,
+ #ifdef CONFIG_NET
[ARG_PTR_TO_BTF_ID_SOCK_COMMON] = &btf_id_sock_common_types,
+ #endif
[ARG_PTR_TO_SOCKET] = &fullsock_types,
[ARG_PTR_TO_SOCKET_OR_NULL] = &fullsock_types,
[ARG_PTR_TO_BTF_ID] = &btf_ptr_types,
[ARG_PTR_TO_ALLOC_MEM_OR_NULL] = &alloc_mem_types,
[ARG_PTR_TO_INT] = &int_ptr_types,
[ARG_PTR_TO_LONG] = &int_ptr_types,
+ [ARG_PTR_TO_PERCPU_BTF_ID] = &percpu_btf_ptr_types,
};
static int check_reg_type(struct bpf_verifier_env *env, u32 regno,
err = check_helper_mem_access(env, regno,
meta->map_ptr->value_size, false,
meta);
+ } else if (arg_type == ARG_PTR_TO_PERCPU_BTF_ID) {
+ if (!reg->btf_id) {
+ verbose(env, "Helper has invalid btf_id in R%d\n", regno);
+ return -EACCES;
+ }
+ meta->ret_btf_id = reg->btf_id;
} else if (arg_type == ARG_PTR_TO_SPIN_LOCK) {
if (meta->func_id == BPF_FUNC_spin_lock) {
if (process_spin_lock(env, regno, true))
regs[BPF_REG_0].type = PTR_TO_MEM_OR_NULL;
regs[BPF_REG_0].id = ++env->id_gen;
regs[BPF_REG_0].mem_size = meta.mem_size;
+ } else if (fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL ||
+ fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID) {
+ const struct btf_type *t;
+
+ mark_reg_known_zero(env, regs, BPF_REG_0);
+ t = btf_type_skip_modifiers(btf_vmlinux, meta.ret_btf_id, NULL);
+ if (!btf_type_is_struct(t)) {
+ u32 tsize;
+ const struct btf_type *ret;
+ const char *tname;
+
+ /* resolve the type size of ksym. */
+ ret = btf_resolve_size(btf_vmlinux, t, &tsize);
+ if (IS_ERR(ret)) {
+ tname = btf_name_by_offset(btf_vmlinux, t->name_off);
+ verbose(env, "unable to resolve the size of type '%s': %ld\n",
+ tname, PTR_ERR(ret));
+ return -EINVAL;
+ }
+ regs[BPF_REG_0].type =
+ fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID ?
+ PTR_TO_MEM : PTR_TO_MEM_OR_NULL;
+ regs[BPF_REG_0].mem_size = tsize;
+ } else {
+ regs[BPF_REG_0].type =
+ fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID ?
+ PTR_TO_BTF_ID : PTR_TO_BTF_ID_OR_NULL;
+ regs[BPF_REG_0].btf_id = meta.ret_btf_id;
+ }
} else if (fn->ret_type == RET_PTR_TO_BTF_ID_OR_NULL) {
int ret_btf_id;
/* smin_val represents the known value */
if (known && smin_val == 0 && opcode == BPF_ADD)
break;
- /* fall-through */
+ fallthrough;
case PTR_TO_PACKET_END:
case PTR_TO_SOCKET:
case PTR_TO_SOCKET_OR_NULL:
bool src_known = tnum_subreg_is_const(src_reg->var_off);
bool dst_known = tnum_subreg_is_const(dst_reg->var_off);
struct tnum var32_off = tnum_subreg(dst_reg->var_off);
- s32 smin_val = src_reg->smin_value;
- u32 umin_val = src_reg->umin_value;
+ s32 smin_val = src_reg->s32_min_value;
+ u32 umin_val = src_reg->u32_min_value;
/* Assuming scalar64_min_max_or will be called so it is safe
* to skip updating register for known case.
/* ORing two positives gives a positive, so safe to
* cast result into s64.
*/
- dst_reg->s32_min_value = dst_reg->umin_value;
- dst_reg->s32_max_value = dst_reg->umax_value;
+ dst_reg->s32_min_value = dst_reg->u32_min_value;
+ dst_reg->s32_max_value = dst_reg->u32_max_value;
}
}
src_reg = NULL;
if (dst_reg->type != SCALAR_VALUE)
ptr_reg = dst_reg;
+ else
+ /* Make sure ID is cleared otherwise dst_reg min/max could be
+ * incorrectly propagated into other registers by find_equal_scalars()
+ */
+ dst_reg->id = 0;
if (BPF_SRC(insn->code) == BPF_X) {
src_reg = ®s[insn->src_reg];
if (src_reg->type != SCALAR_VALUE) {
/* case: R1 = R2
* copy register state to dest reg
*/
+ if (src_reg->type == SCALAR_VALUE && !src_reg->id)
+ /* Assign src and dst registers the same ID
+ * that will be used by find_equal_scalars()
+ * to propagate min/max range.
+ */
+ src_reg->id = ++env->id_gen;
*dst_reg = *src_reg;
dst_reg->live |= REG_LIVE_WRITTEN;
dst_reg->subreg_def = DEF_NOT_SUBREG;
return -EACCES;
} else if (src_reg->type == SCALAR_VALUE) {
*dst_reg = *src_reg;
+ /* Make sure ID is cleared otherwise
+ * dst_reg min/max could be incorrectly
+ * propagated into src_reg by find_equal_scalars()
+ */
+ dst_reg->id = 0;
dst_reg->live |= REG_LIVE_WRITTEN;
dst_reg->subreg_def = env->insn_idx + 1;
} else {
return true;
}
+ static void find_equal_scalars(struct bpf_verifier_state *vstate,
+ struct bpf_reg_state *known_reg)
+ {
+ struct bpf_func_state *state;
+ struct bpf_reg_state *reg;
+ int i, j;
+
+ for (i = 0; i <= vstate->curframe; i++) {
+ state = vstate->frame[i];
+ for (j = 0; j < MAX_BPF_REG; j++) {
+ reg = &state->regs[j];
+ if (reg->type == SCALAR_VALUE && reg->id == known_reg->id)
+ *reg = *known_reg;
+ }
+
+ bpf_for_each_spilled_reg(j, state, reg) {
+ if (!reg)
+ continue;
+ if (reg->type == SCALAR_VALUE && reg->id == known_reg->id)
+ *reg = *known_reg;
+ }
+ }
+ }
+
static int check_cond_jmp_op(struct bpf_verifier_env *env,
struct bpf_insn *insn, int *insn_idx)
{
reg_combine_min_max(&other_branch_regs[insn->src_reg],
&other_branch_regs[insn->dst_reg],
src_reg, dst_reg, opcode);
+ if (src_reg->id) {
+ find_equal_scalars(this_branch, src_reg);
+ find_equal_scalars(other_branch, &other_branch_regs[insn->src_reg]);
+ }
+
}
} else if (dst_reg->type == SCALAR_VALUE) {
reg_set_min_max(&other_branch_regs[insn->dst_reg],
opcode, is_jmp32);
}
+ if (dst_reg->type == SCALAR_VALUE && dst_reg->id) {
+ find_equal_scalars(this_branch, dst_reg);
+ find_equal_scalars(other_branch, &other_branch_regs[insn->dst_reg]);
+ }
+
/* detect if R == 0 where R is returned from bpf_map_lookup_elem().
* NOTE: these optimizations below are related with pointer comparison
* which will never be JMP32.
{
struct bpf_insn_aux_data *aux = cur_aux(env);
struct bpf_reg_state *regs = cur_regs(env);
+ struct bpf_reg_state *dst_reg;
struct bpf_map *map;
int err;
if (err)
return err;
+ dst_reg = ®s[insn->dst_reg];
if (insn->src_reg == 0) {
u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm;
- regs[insn->dst_reg].type = SCALAR_VALUE;
+ dst_reg->type = SCALAR_VALUE;
__mark_reg_known(®s[insn->dst_reg], imm);
return 0;
}
+ if (insn->src_reg == BPF_PSEUDO_BTF_ID) {
+ mark_reg_known_zero(env, regs, insn->dst_reg);
+
+ dst_reg->type = aux->btf_var.reg_type;
+ switch (dst_reg->type) {
+ case PTR_TO_MEM:
+ dst_reg->mem_size = aux->btf_var.mem_size;
+ break;
+ case PTR_TO_BTF_ID:
+ case PTR_TO_PERCPU_BTF_ID:
+ dst_reg->btf_id = aux->btf_var.btf_id;
+ break;
+ default:
+ verbose(env, "bpf verifier is misconfigured\n");
+ return -EFAULT;
+ }
+ return 0;
+ }
+
map = env->used_maps[aux->map_index];
mark_reg_known_zero(env, regs, insn->dst_reg);
- regs[insn->dst_reg].map_ptr = map;
+ dst_reg->map_ptr = map;
if (insn->src_reg == BPF_PSEUDO_MAP_VALUE) {
- regs[insn->dst_reg].type = PTR_TO_MAP_VALUE;
- regs[insn->dst_reg].off = aux->map_off;
+ dst_reg->type = PTR_TO_MAP_VALUE;
+ dst_reg->off = aux->map_off;
if (map_value_has_spin_lock(map))
- regs[insn->dst_reg].id = ++env->id_gen;
+ dst_reg->id = ++env->id_gen;
} else if (insn->src_reg == BPF_PSEUDO_MAP_FD) {
- regs[insn->dst_reg].type = CONST_PTR_TO_MAP;
+ dst_reg->type = CONST_PTR_TO_MAP;
} else {
verbose(env, "bpf verifier is misconfigured\n");
return -EINVAL;
return 0;
}
+ /* replace pseudo btf_id with kernel symbol address */
+ static int check_pseudo_btf_id(struct bpf_verifier_env *env,
+ struct bpf_insn *insn,
+ struct bpf_insn_aux_data *aux)
+ {
+ u32 datasec_id, type, id = insn->imm;
+ const struct btf_var_secinfo *vsi;
+ const struct btf_type *datasec;
+ const struct btf_type *t;
+ const char *sym_name;
+ bool percpu = false;
+ u64 addr;
+ int i;
+
+ if (!btf_vmlinux) {
+ verbose(env, "kernel is missing BTF, make sure CONFIG_DEBUG_INFO_BTF=y is specified in Kconfig.\n");
+ return -EINVAL;
+ }
+
+ if (insn[1].imm != 0) {
+ verbose(env, "reserved field (insn[1].imm) is used in pseudo_btf_id ldimm64 insn.\n");
+ return -EINVAL;
+ }
+
+ t = btf_type_by_id(btf_vmlinux, id);
+ if (!t) {
+ verbose(env, "ldimm64 insn specifies invalid btf_id %d.\n", id);
+ return -ENOENT;
+ }
+
+ if (!btf_type_is_var(t)) {
+ verbose(env, "pseudo btf_id %d in ldimm64 isn't KIND_VAR.\n",
+ id);
+ return -EINVAL;
+ }
+
+ sym_name = btf_name_by_offset(btf_vmlinux, t->name_off);
+ addr = kallsyms_lookup_name(sym_name);
+ if (!addr) {
+ verbose(env, "ldimm64 failed to find the address for kernel symbol '%s'.\n",
+ sym_name);
+ return -ENOENT;
+ }
+
+ datasec_id = btf_find_by_name_kind(btf_vmlinux, ".data..percpu",
+ BTF_KIND_DATASEC);
+ if (datasec_id > 0) {
+ datasec = btf_type_by_id(btf_vmlinux, datasec_id);
+ for_each_vsi(i, datasec, vsi) {
+ if (vsi->type == id) {
+ percpu = true;
+ break;
+ }
+ }
+ }
+
+ insn[0].imm = (u32)addr;
+ insn[1].imm = addr >> 32;
+
+ type = t->type;
+ t = btf_type_skip_modifiers(btf_vmlinux, type, NULL);
+ if (percpu) {
+ aux->btf_var.reg_type = PTR_TO_PERCPU_BTF_ID;
+ aux->btf_var.btf_id = type;
+ } else if (!btf_type_is_struct(t)) {
+ const struct btf_type *ret;
+ const char *tname;
+ u32 tsize;
+
+ /* resolve the type size of ksym. */
+ ret = btf_resolve_size(btf_vmlinux, t, &tsize);
+ if (IS_ERR(ret)) {
+ tname = btf_name_by_offset(btf_vmlinux, t->name_off);
+ verbose(env, "ldimm64 unable to resolve the size of type '%s': %ld\n",
+ tname, PTR_ERR(ret));
+ return -EINVAL;
+ }
+ aux->btf_var.reg_type = PTR_TO_MEM;
+ aux->btf_var.mem_size = tsize;
+ } else {
+ aux->btf_var.reg_type = PTR_TO_BTF_ID;
+ aux->btf_var.btf_id = type;
+ }
+ return 0;
+ }
+
static int check_map_prealloc(struct bpf_map *map)
{
return (map->map_type != BPF_MAP_TYPE_HASH &&
map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE);
}
- /* look for pseudo eBPF instructions that access map FDs and
- * replace them with actual map pointers
+ /* find and rewrite pseudo imm in ld_imm64 instructions:
+ *
+ * 1. if it accesses map FD, replace it with actual map pointer.
+ * 2. if it accesses btf_id of a VAR, replace it with pointer to the var.
+ *
+ * NOTE: btf_vmlinux is required for converting pseudo btf_id.
*/
- static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
+ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env)
{
struct bpf_insn *insn = env->prog->insnsi;
int insn_cnt = env->prog->len;
/* valid generic load 64-bit imm */
goto next_insn;
+ if (insn[0].src_reg == BPF_PSEUDO_BTF_ID) {
+ aux = &env->insn_aux_data[i];
+ err = check_pseudo_btf_id(env, insn, aux);
+ if (err)
+ return err;
+ goto next_insn;
+ }
+
/* In final convert_pseudo_ld_imm64() step, this is
* converted into regular 64-bit imm load insn.
*/
if (insn->imm == BPF_FUNC_map_lookup_elem &&
ops->map_gen_lookup) {
cnt = ops->map_gen_lookup(map_ptr, insn_buf);
- if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) {
+ if (cnt == -EOPNOTSUPP)
+ goto patch_map_ops_generic;
+ if (cnt <= 0 || cnt >= ARRAY_SIZE(insn_buf)) {
verbose(env, "bpf verifier is misconfigured\n");
return -EINVAL;
}
(int (*)(struct bpf_map *map, void *value))NULL));
BUILD_BUG_ON(!__same_type(ops->map_peek_elem,
(int (*)(struct bpf_map *map, void *value))NULL));
-
+ patch_map_ops_generic:
switch (insn->imm) {
case BPF_FUNC_map_lookup_elem:
insn->imm = BPF_CAST_CALL(ops->map_lookup_elem) -
if (is_priv)
env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ;
- ret = replace_map_fd_with_map_ptr(env);
- if (ret < 0)
- goto skip_full_check;
-
if (bpf_prog_is_dev_bound(env->prog->aux)) {
ret = bpf_prog_offload_verifier_prep(env->prog);
if (ret)
if (ret)
goto skip_full_check;
+ ret = resolve_pseudo_ldimm64(env);
+ if (ret < 0)
+ goto skip_full_check;
+
ret = check_cfg(env);
if (ret < 0)
goto skip_full_check;
static inline struct sk_buff *
sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
- struct net_device *orig_dev)
+ struct net_device *orig_dev, bool *another)
{
#ifdef CONFIG_NET_CLS_ACT
struct mini_Qdisc *miniq = rcu_dereference_bh(skb->dev->miniq_ingress);
* redirecting to another netdev
*/
__skb_push(skb, skb->mac_len);
- skb_do_redirect(skb);
+ if (skb_do_redirect(skb) == -EAGAIN) {
+ __skb_pull(skb, skb->mac_len);
+ *another = true;
+ break;
+ }
return NULL;
case TC_ACT_CONSUMED:
return NULL;
skip_taps:
#ifdef CONFIG_NET_INGRESS
if (static_branch_unlikely(&ingress_needed_key)) {
- skb = sch_handle_ingress(skb, &pt_prev, &ret, orig_dev);
+ bool another = false;
+
+ skb = sch_handle_ingress(skb, &pt_prev, &ret, orig_dev,
+ &another);
+ if (another)
+ goto another_round;
if (!skb)
goto out;
return NULL;
}
-static int ____netdev_has_upper_dev(struct net_device *upper_dev, void *data)
+static int ____netdev_has_upper_dev(struct net_device *upper_dev,
+ struct netdev_nested_priv *priv)
{
- struct net_device *dev = data;
+ struct net_device *dev = (struct net_device *)priv->data;
return upper_dev == dev;
}
bool netdev_has_upper_dev(struct net_device *dev,
struct net_device *upper_dev)
{
+ struct netdev_nested_priv priv = {
+ .data = (void *)upper_dev,
+ };
+
ASSERT_RTNL();
return netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev,
- upper_dev);
+ &priv);
}
EXPORT_SYMBOL(netdev_has_upper_dev);
bool netdev_has_upper_dev_all_rcu(struct net_device *dev,
struct net_device *upper_dev)
{
+ struct netdev_nested_priv priv = {
+ .data = (void *)upper_dev,
+ };
+
return !!netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev,
- upper_dev);
+ &priv);
}
EXPORT_SYMBOL(netdev_has_upper_dev_all_rcu);
static int __netdev_walk_all_upper_dev(struct net_device *dev,
int (*fn)(struct net_device *dev,
- void *data),
- void *data)
+ struct netdev_nested_priv *priv),
+ struct netdev_nested_priv *priv)
{
struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
while (1) {
if (now != dev) {
- ret = fn(now, data);
+ ret = fn(now, priv);
if (ret)
return ret;
}
int netdev_walk_all_upper_dev_rcu(struct net_device *dev,
int (*fn)(struct net_device *dev,
- void *data),
- void *data)
+ struct netdev_nested_priv *priv),
+ struct netdev_nested_priv *priv)
{
struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
while (1) {
if (now != dev) {
- ret = fn(now, data);
+ ret = fn(now, priv);
if (ret)
return ret;
}
static bool __netdev_has_upper_dev(struct net_device *dev,
struct net_device *upper_dev)
{
+ struct netdev_nested_priv priv = {
+ .flags = 0,
+ .data = (void *)upper_dev,
+ };
+
ASSERT_RTNL();
return __netdev_walk_all_upper_dev(dev, ____netdev_has_upper_dev,
- upper_dev);
+ &priv);
}
/**
int netdev_walk_all_lower_dev(struct net_device *dev,
int (*fn)(struct net_device *dev,
- void *data),
- void *data)
+ struct netdev_nested_priv *priv),
+ struct netdev_nested_priv *priv)
{
struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
while (1) {
if (now != dev) {
- ret = fn(now, data);
+ ret = fn(now, priv);
if (ret)
return ret;
}
static int __netdev_walk_all_lower_dev(struct net_device *dev,
int (*fn)(struct net_device *dev,
- void *data),
- void *data)
+ struct netdev_nested_priv *priv),
+ struct netdev_nested_priv *priv)
{
struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
while (1) {
if (now != dev) {
- ret = fn(now, data);
+ ret = fn(now, priv);
if (ret)
return ret;
}
return max_depth;
}
-static int __netdev_update_upper_level(struct net_device *dev, void *data)
+static int __netdev_update_upper_level(struct net_device *dev,
+ struct netdev_nested_priv *__unused)
{
dev->upper_level = __netdev_upper_depth(dev) + 1;
return 0;
}
-static int __netdev_update_lower_level(struct net_device *dev, void *data)
+static int __netdev_update_lower_level(struct net_device *dev,
+ struct netdev_nested_priv *priv)
{
dev->lower_level = __netdev_lower_depth(dev) + 1;
+
+#ifdef CONFIG_LOCKDEP
+ if (!priv)
+ return 0;
+
+ if (priv->flags & NESTED_SYNC_IMM)
+ dev->nested_level = dev->lower_level - 1;
+ if (priv->flags & NESTED_SYNC_TODO)
+ net_unlink_todo(dev);
+#endif
return 0;
}
int netdev_walk_all_lower_dev_rcu(struct net_device *dev,
int (*fn)(struct net_device *dev,
- void *data),
- void *data)
+ struct netdev_nested_priv *priv),
+ struct netdev_nested_priv *priv)
{
struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
while (1) {
if (now != dev) {
- ret = fn(now, data);
+ ret = fn(now, priv);
if (ret)
return ret;
}
static int __netdev_upper_dev_link(struct net_device *dev,
struct net_device *upper_dev, bool master,
void *upper_priv, void *upper_info,
+ struct netdev_nested_priv *priv,
struct netlink_ext_ack *extack)
{
struct netdev_notifier_changeupper_info changeupper_info = {
__netdev_update_upper_level(dev, NULL);
__netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL);
- __netdev_update_lower_level(upper_dev, NULL);
+ __netdev_update_lower_level(upper_dev, priv);
__netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level,
- NULL);
+ priv);
return 0;
struct net_device *upper_dev,
struct netlink_ext_ack *extack)
{
+ struct netdev_nested_priv priv = {
+ .flags = NESTED_SYNC_IMM | NESTED_SYNC_TODO,
+ .data = NULL,
+ };
+
return __netdev_upper_dev_link(dev, upper_dev, false,
- NULL, NULL, extack);
+ NULL, NULL, &priv, extack);
}
EXPORT_SYMBOL(netdev_upper_dev_link);
void *upper_priv, void *upper_info,
struct netlink_ext_ack *extack)
{
+ struct netdev_nested_priv priv = {
+ .flags = NESTED_SYNC_IMM | NESTED_SYNC_TODO,
+ .data = NULL,
+ };
+
return __netdev_upper_dev_link(dev, upper_dev, true,
- upper_priv, upper_info, extack);
+ upper_priv, upper_info, &priv, extack);
}
EXPORT_SYMBOL(netdev_master_upper_dev_link);
-/**
- * netdev_upper_dev_unlink - Removes a link to upper device
- * @dev: device
- * @upper_dev: new upper device
- *
- * Removes a link to device which is upper to this one. The caller must hold
- * the RTNL lock.
- */
-void netdev_upper_dev_unlink(struct net_device *dev,
- struct net_device *upper_dev)
+static void __netdev_upper_dev_unlink(struct net_device *dev,
+ struct net_device *upper_dev,
+ struct netdev_nested_priv *priv)
{
struct netdev_notifier_changeupper_info changeupper_info = {
.info = {
__netdev_update_upper_level(dev, NULL);
__netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL);
- __netdev_update_lower_level(upper_dev, NULL);
+ __netdev_update_lower_level(upper_dev, priv);
__netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level,
- NULL);
+ priv);
+}
+
+/**
+ * netdev_upper_dev_unlink - Removes a link to upper device
+ * @dev: device
+ * @upper_dev: new upper device
+ *
+ * Removes a link to device which is upper to this one. The caller must hold
+ * the RTNL lock.
+ */
+void netdev_upper_dev_unlink(struct net_device *dev,
+ struct net_device *upper_dev)
+{
+ struct netdev_nested_priv priv = {
+ .flags = NESTED_SYNC_TODO,
+ .data = NULL,
+ };
+
+ __netdev_upper_dev_unlink(dev, upper_dev, &priv);
}
EXPORT_SYMBOL(netdev_upper_dev_unlink);
struct net_device *dev,
struct netlink_ext_ack *extack)
{
+ struct netdev_nested_priv priv = {
+ .flags = 0,
+ .data = NULL,
+ };
int err;
if (!new_dev)
if (old_dev && new_dev != old_dev)
netdev_adjacent_dev_disable(dev, old_dev);
-
- err = netdev_upper_dev_link(new_dev, dev, extack);
+ err = __netdev_upper_dev_link(new_dev, dev, false, NULL, NULL, &priv,
+ extack);
if (err) {
if (old_dev && new_dev != old_dev)
netdev_adjacent_dev_enable(dev, old_dev);
struct net_device *new_dev,
struct net_device *dev)
{
+ struct netdev_nested_priv priv = {
+ .flags = NESTED_SYNC_IMM | NESTED_SYNC_TODO,
+ .data = NULL,
+ };
+
if (!new_dev || !old_dev)
return;
return;
netdev_adjacent_dev_enable(dev, old_dev);
- netdev_upper_dev_unlink(old_dev, dev);
+ __netdev_upper_dev_unlink(old_dev, dev, &priv);
}
EXPORT_SYMBOL(netdev_adjacent_change_commit);
struct net_device *new_dev,
struct net_device *dev)
{
+ struct netdev_nested_priv priv = {
+ .flags = 0,
+ .data = NULL,
+ };
+
if (!new_dev)
return;
if (old_dev && new_dev != old_dev)
netdev_adjacent_dev_enable(dev, old_dev);
- netdev_upper_dev_unlink(new_dev, dev);
+ __netdev_upper_dev_unlink(new_dev, dev, &priv);
}
EXPORT_SYMBOL(netdev_adjacent_change_abort);
void netdev_run_todo(void)
{
struct list_head list;
+#ifdef CONFIG_LOCKDEP
+ struct list_head unlink_list;
+
+ list_replace_init(&net_unlink_list, &unlink_list);
+
+ while (!list_empty(&unlink_list)) {
+ struct net_device *dev = list_first_entry(&unlink_list,
+ struct net_device,
+ unlink_list);
+ list_del(&dev->unlink_list);
+ dev->nested_level = dev->lower_level - 1;
+ }
+#endif
/* Snapshot list, allow later requests */
list_replace_init(&net_todo_list, &list);
dev->gso_max_segs = GSO_MAX_SEGS;
dev->upper_level = 1;
dev->lower_level = 1;
+#ifdef CONFIG_LOCKDEP
+ dev->nested_level = 0;
+ INIT_LIST_HEAD(&dev->unlink_list);
+#endif
INIT_LIST_HEAD(&dev->napi_list);
INIT_LIST_HEAD(&dev->unreg_list);
#include <net/bpf_sk_storage.h>
#include <net/transp_v6.h>
#include <linux/btf_ids.h>
+ #include <net/tls.h>
static const struct bpf_func_proto *
bpf_sk_base_func_proto(enum bpf_func_id func_id);
/* Internal, non-exposed redirect flags. */
enum {
- BPF_F_NEIGH = (1ULL << 1),
- #define BPF_F_REDIRECT_INTERNAL (BPF_F_NEIGH)
+ BPF_F_NEIGH = (1ULL << 1),
+ BPF_F_PEER = (1ULL << 2),
+ #define BPF_F_REDIRECT_INTERNAL (BPF_F_NEIGH | BPF_F_PEER)
};
BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags)
int skb_do_redirect(struct sk_buff *skb)
{
struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+ struct net *net = dev_net(skb->dev);
struct net_device *dev;
u32 flags = ri->flags;
- dev = dev_get_by_index_rcu(dev_net(skb->dev), ri->tgt_index);
+ dev = dev_get_by_index_rcu(net, ri->tgt_index);
ri->tgt_index = 0;
- if (unlikely(!dev)) {
- kfree_skb(skb);
- return -EINVAL;
+ ri->flags = 0;
+ if (unlikely(!dev))
+ goto out_drop;
+ if (flags & BPF_F_PEER) {
+ const struct net_device_ops *ops = dev->netdev_ops;
+
+ if (unlikely(!ops->ndo_get_peer_dev ||
+ !skb_at_tc_ingress(skb)))
+ goto out_drop;
+ dev = ops->ndo_get_peer_dev(dev);
+ if (unlikely(!dev ||
+ !is_skb_forwardable(dev, skb) ||
+ net_eq(net, dev_net(dev))))
+ goto out_drop;
+ skb->dev = dev;
+ return -EAGAIN;
}
-
return flags & BPF_F_NEIGH ?
__bpf_redirect_neigh(skb, dev) :
__bpf_redirect(skb, dev, flags);
+ out_drop:
+ kfree_skb(skb);
+ return -EINVAL;
}
BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags)
.arg2_type = ARG_ANYTHING,
};
+ BPF_CALL_2(bpf_redirect_peer, u32, ifindex, u64, flags)
+ {
+ struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+
+ if (unlikely(flags))
+ return TC_ACT_SHOT;
+
+ ri->flags = BPF_F_PEER;
+ ri->tgt_index = ifindex;
+
+ return TC_ACT_REDIRECT;
+ }
+
+ static const struct bpf_func_proto bpf_redirect_peer_proto = {
+ .func = bpf_redirect_peer,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_ANYTHING,
+ .arg2_type = ARG_ANYTHING,
+ };
+
BPF_CALL_2(bpf_redirect_neigh, u32, ifindex, u64, flags)
{
struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
SKB_MAX_ALLOC;
}
+ BPF_CALL_4(sk_skb_adjust_room, struct sk_buff *, skb, s32, len_diff,
+ u32, mode, u64, flags)
+ {
+ u32 len_diff_abs = abs(len_diff);
+ bool shrink = len_diff < 0;
+ int ret = 0;
+
+ if (unlikely(flags || mode))
+ return -EINVAL;
+ if (unlikely(len_diff_abs > 0xfffU))
+ return -EFAULT;
+
+ if (!shrink) {
+ ret = skb_cow(skb, len_diff);
+ if (unlikely(ret < 0))
+ return ret;
+ __skb_push(skb, len_diff_abs);
+ memset(skb->data, 0, len_diff_abs);
+ } else {
+ if (unlikely(!pskb_may_pull(skb, len_diff_abs)))
+ return -ENOMEM;
+ __skb_pull(skb, len_diff_abs);
+ }
+ bpf_compute_data_end_sk_skb(skb);
+ if (tls_sw_has_ctx_rx(skb->sk)) {
+ struct strp_msg *rxm = strp_msg(skb);
+
+ rxm->full_len += len_diff;
+ }
+ return ret;
+ }
+
+ static const struct bpf_func_proto sk_skb_adjust_room_proto = {
+ .func = sk_skb_adjust_room,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+ .arg3_type = ARG_ANYTHING,
+ .arg4_type = ARG_ANYTHING,
+ };
+
BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff,
u32, mode, u64, flags)
{
else
icsk->icsk_user_timeout = val;
break;
+ case TCP_NOTSENT_LOWAT:
+ tp->notsent_lowat = val;
+ sk->sk_write_space(sk);
+ break;
default:
ret = -EINVAL;
}
memcpy(params->smac, dev->dev_addr, ETH_ALEN);
params->h_vlan_TCI = 0;
params->h_vlan_proto = 0;
- params->ifindex = dev->ifindex;
return 0;
}
dev = nhc->nhc_dev;
params->rt_metric = res.fi->fib_priority;
+ params->ifindex = dev->ifindex;
/* xdp and cls_bpf programs are run in RCU-bh so
* rcu_read_lock_bh is not needed here
dev = res.nh->fib_nh_dev;
params->rt_metric = res.f6i->fib6_metric;
+ params->ifindex = dev->ifindex;
/* xdp and cls_bpf programs are run in RCU-bh so rcu_read_lock_bh is
* not needed here.
func == bpf_skb_change_tail ||
func == sk_skb_change_tail ||
func == bpf_skb_adjust_room ||
+ func == sk_skb_adjust_room ||
func == bpf_skb_pull_data ||
func == sk_skb_pull_data ||
func == bpf_clone_redirect ||
return &bpf_redirect_proto;
case BPF_FUNC_redirect_neigh:
return &bpf_redirect_neigh_proto;
+ case BPF_FUNC_redirect_peer:
+ return &bpf_redirect_peer_proto;
case BPF_FUNC_get_route_realm:
return &bpf_get_route_realm_proto;
case BPF_FUNC_get_hash_recalc:
return &sk_skb_change_tail_proto;
case BPF_FUNC_skb_change_head:
return &sk_skb_change_head_proto;
+ case BPF_FUNC_skb_adjust_room:
+ return &sk_skb_adjust_room_proto;
case BPF_FUNC_get_socket_cookie:
return &bpf_get_socket_cookie_proto;
case BPF_FUNC_get_socket_uid:
BPF_CALL_1(bpf_skc_to_tcp_timewait_sock, struct sock *, sk)
{
+ /* BTF types for tcp_timewait_sock and inet_timewait_sock are not
+ * generated if CONFIG_INET=n. Trigger an explicit generation here.
+ */
+ BTF_TYPE_EMIT(struct inet_timewait_sock);
+ BTF_TYPE_EMIT(struct tcp_timewait_sock);
+
#ifdef CONFIG_INET
if (sk && sk->sk_prot == &tcp_prot && sk->sk_state == TCP_TIME_WAIT)
return (unsigned long)sk;
} kcfg;
struct {
unsigned long long addr;
+
+ /* target btf_id of the corresponding kernel var. */
+ int vmlinux_btf_id;
+
+ /* local btf_id of the ksym extern's type. */
+ __u32 type_id;
} ksym;
};
};
{
bool need_vmlinux_btf = false;
struct bpf_program *prog;
- int err;
+ int i, err;
/* CO-RE relocations need kernel BTF */
if (obj->btf_ext && obj->btf_ext->core_relo_info.len)
need_vmlinux_btf = true;
+ /* Support for typed ksyms needs kernel BTF */
+ for (i = 0; i < obj->nr_extern; i++) {
+ const struct extern_desc *ext;
+
+ ext = &obj->externs[i];
+ if (ext->type == EXT_KSYM && ext->ksym.type_id) {
+ need_vmlinux_btf = true;
+ break;
+ }
+ }
+
bpf_object__for_each_program(prog, obj) {
if (!prog->load)
continue;
return -ENOTSUP;
}
} else if (strcmp(sec_name, KSYMS_SEC) == 0) {
- const struct btf_type *vt;
-
ksym_sec = sec;
ext->type = EXT_KSYM;
-
- vt = skip_mods_and_typedefs(obj->btf, t->type, NULL);
- if (!btf_is_void(vt)) {
- pr_warn("extern (ksym) '%s' is not typeless (void)\n", ext_name);
- return -ENOTSUP;
- }
+ skip_mods_and_typedefs(obj->btf, t->type,
+ &ext->ksym.type_id);
} else {
pr_warn("unrecognized extern section '%s'\n", sec_name);
return -ENOTSUP;
return 0;
}
+ static int init_map_slots(struct bpf_map *map)
+ {
+ const struct bpf_map *targ_map;
+ unsigned int i;
+ int fd, err;
+
+ for (i = 0; i < map->init_slots_sz; i++) {
+ if (!map->init_slots[i])
+ continue;
+
+ targ_map = map->init_slots[i];
+ fd = bpf_map__fd(targ_map);
+ err = bpf_map_update_elem(map->fd, &i, &fd, 0);
+ if (err) {
+ err = -errno;
+ pr_warn("map '%s': failed to initialize slot [%d] to map '%s' fd=%d: %d\n",
+ map->name, i, targ_map->name,
+ fd, err);
+ return err;
+ }
+ pr_debug("map '%s': slot [%d] set to map '%s' fd=%d\n",
+ map->name, i, targ_map->name, fd);
+ }
+
+ zfree(&map->init_slots);
+ map->init_slots_sz = 0;
+
+ return 0;
+ }
+
static int
bpf_object__create_maps(struct bpf_object *obj)
{
if (map->fd >= 0) {
pr_debug("map '%s': skipping creation (preset fd=%d)\n",
map->name, map->fd);
- continue;
- }
-
- err = bpf_object__create_map(obj, map);
- if (err)
- goto err_out;
-
- pr_debug("map '%s': created successfully, fd=%d\n", map->name,
- map->fd);
-
- if (bpf_map__is_internal(map)) {
- err = bpf_object__populate_internal_map(obj, map);
- if (err < 0) {
- zclose(map->fd);
+ } else {
+ err = bpf_object__create_map(obj, map);
+ if (err)
goto err_out;
- }
- }
- if (map->init_slots_sz) {
- for (j = 0; j < map->init_slots_sz; j++) {
- const struct bpf_map *targ_map;
- int fd;
+ pr_debug("map '%s': created successfully, fd=%d\n",
+ map->name, map->fd);
- if (!map->init_slots[j])
- continue;
+ if (bpf_map__is_internal(map)) {
+ err = bpf_object__populate_internal_map(obj, map);
+ if (err < 0) {
+ zclose(map->fd);
+ goto err_out;
+ }
+ }
- targ_map = map->init_slots[j];
- fd = bpf_map__fd(targ_map);
- err = bpf_map_update_elem(map->fd, &j, &fd, 0);
- if (err) {
- err = -errno;
- pr_warn("map '%s': failed to initialize slot [%d] to map '%s' fd=%d: %d\n",
- map->name, j, targ_map->name,
- fd, err);
+ if (map->init_slots_sz) {
+ err = init_map_slots(map);
+ if (err < 0) {
+ zclose(map->fd);
goto err_out;
}
- pr_debug("map '%s': slot [%d] set to map '%s' fd=%d\n",
- map->name, j, targ_map->name, fd);
}
- zfree(&map->init_slots);
- map->init_slots_sz = 0;
}
if (map->pin_path && !map->pinned) {
static int bpf_core_calc_field_relo(const struct bpf_program *prog,
const struct bpf_core_relo *relo,
const struct bpf_core_spec *spec,
- __u32 *val, bool *validate)
+ __u32 *val, __u32 *field_sz, __u32 *type_id,
+ bool *validate)
{
const struct bpf_core_accessor *acc;
const struct btf_type *t;
- __u32 byte_off, byte_sz, bit_off, bit_sz;
+ __u32 byte_off, byte_sz, bit_off, bit_sz, field_type_id;
const struct btf_member *m;
const struct btf_type *mt;
bool bitfield;
__s64 sz;
+ *field_sz = 0;
+
if (relo->kind == BPF_FIELD_EXISTS) {
*val = spec ? 1 : 0;
return 0;
if (!acc->name) {
if (relo->kind == BPF_FIELD_BYTE_OFFSET) {
*val = spec->bit_offset / 8;
+ /* remember field size for load/store mem size */
+ sz = btf__resolve_size(spec->btf, acc->type_id);
+ if (sz < 0)
+ return -EINVAL;
+ *field_sz = sz;
+ *type_id = acc->type_id;
} else if (relo->kind == BPF_FIELD_BYTE_SIZE) {
sz = btf__resolve_size(spec->btf, acc->type_id);
if (sz < 0)
}
m = btf_members(t) + acc->idx;
- mt = skip_mods_and_typedefs(spec->btf, m->type, NULL);
+ mt = skip_mods_and_typedefs(spec->btf, m->type, &field_type_id);
bit_off = spec->bit_offset;
bit_sz = btf_member_bitfield_size(t, acc->idx);
byte_off = bit_off / 8 / byte_sz * byte_sz;
}
} else {
- sz = btf__resolve_size(spec->btf, m->type);
+ sz = btf__resolve_size(spec->btf, field_type_id);
if (sz < 0)
return -EINVAL;
byte_sz = sz;
switch (relo->kind) {
case BPF_FIELD_BYTE_OFFSET:
*val = byte_off;
+ if (!bitfield) {
+ *field_sz = byte_sz;
+ *type_id = field_type_id;
+ }
break;
case BPF_FIELD_BYTE_SIZE:
*val = byte_sz;
bool poison;
/* some relocations can't be validated against orig_val */
bool validate;
+ /* for field byte offset relocations or the forms:
+ * *(T *)(rX + <off>) = rY
+ * rX = *(T *)(rY + <off>),
+ * we remember original and resolved field size to adjust direct
+ * memory loads of pointers and integers; this is necessary for 32-bit
+ * host kernel architectures, but also allows to automatically
+ * relocate fields that were resized from, e.g., u32 to u64, etc.
+ */
+ bool fail_memsz_adjust;
+ __u32 orig_sz;
+ __u32 orig_type_id;
+ __u32 new_sz;
+ __u32 new_type_id;
};
/* Calculate original and target relocation values, given local and target
res->new_val = 0;
res->poison = false;
res->validate = true;
+ res->fail_memsz_adjust = false;
+ res->orig_sz = res->new_sz = 0;
+ res->orig_type_id = res->new_type_id = 0;
if (core_relo_is_field_based(relo->kind)) {
- err = bpf_core_calc_field_relo(prog, relo, local_spec, &res->orig_val, &res->validate);
- err = err ?: bpf_core_calc_field_relo(prog, relo, targ_spec, &res->new_val, NULL);
+ err = bpf_core_calc_field_relo(prog, relo, local_spec,
+ &res->orig_val, &res->orig_sz,
+ &res->orig_type_id, &res->validate);
+ err = err ?: bpf_core_calc_field_relo(prog, relo, targ_spec,
+ &res->new_val, &res->new_sz,
+ &res->new_type_id, NULL);
+ if (err)
+ goto done;
+ /* Validate if it's safe to adjust load/store memory size.
+ * Adjustments are performed only if original and new memory
+ * sizes differ.
+ */
+ res->fail_memsz_adjust = false;
+ if (res->orig_sz != res->new_sz) {
+ const struct btf_type *orig_t, *new_t;
+
+ orig_t = btf__type_by_id(local_spec->btf, res->orig_type_id);
+ new_t = btf__type_by_id(targ_spec->btf, res->new_type_id);
+
+ /* There are two use cases in which it's safe to
+ * adjust load/store's mem size:
+ * - reading a 32-bit kernel pointer, while on BPF
+ * size pointers are always 64-bit; in this case
+ * it's safe to "downsize" instruction size due to
+ * pointer being treated as unsigned integer with
+ * zero-extended upper 32-bits;
+ * - reading unsigned integers, again due to
+ * zero-extension is preserving the value correctly.
+ *
+ * In all other cases it's incorrect to attempt to
+ * load/store field because read value will be
+ * incorrect, so we poison relocated instruction.
+ */
+ if (btf_is_ptr(orig_t) && btf_is_ptr(new_t))
+ goto done;
+ if (btf_is_int(orig_t) && btf_is_int(new_t) &&
+ btf_int_encoding(orig_t) != BTF_INT_SIGNED &&
+ btf_int_encoding(new_t) != BTF_INT_SIGNED)
+ goto done;
+
+ /* mark as invalid mem size adjustment, but this will
+ * only be checked for LDX/STX/ST insns
+ */
+ res->fail_memsz_adjust = true;
+ }
} else if (core_relo_is_type_based(relo->kind)) {
err = bpf_core_calc_type_relo(relo, local_spec, &res->orig_val);
err = err ?: bpf_core_calc_type_relo(relo, targ_spec, &res->new_val);
err = err ?: bpf_core_calc_enumval_relo(relo, targ_spec, &res->new_val);
}
+ done:
if (err == -EUCLEAN) {
/* EUCLEAN is used to signal instruction poisoning request */
res->poison = true;
return insn->code == (BPF_LD | BPF_IMM | BPF_DW);
}
+ static int insn_bpf_size_to_bytes(struct bpf_insn *insn)
+ {
+ switch (BPF_SIZE(insn->code)) {
+ case BPF_DW: return 8;
+ case BPF_W: return 4;
+ case BPF_H: return 2;
+ case BPF_B: return 1;
+ default: return -1;
+ }
+ }
+
+ static int insn_bytes_to_bpf_size(__u32 sz)
+ {
+ switch (sz) {
+ case 8: return BPF_DW;
+ case 4: return BPF_W;
+ case 2: return BPF_H;
+ case 1: return BPF_B;
+ default: return -1;
+ }
+ }
+
/*
* Patch relocatable BPF instruction.
*
* spec, and is checked before patching instruction. If actual insn->imm value
* is wrong, bail out with error.
*
- * Currently three kinds of BPF instructions are supported:
+ * Currently supported classes of BPF instruction are:
* 1. rX = <imm> (assignment with immediate operand);
* 2. rX += <imm> (arithmetic operations with immediate operand);
- * 3. rX = <imm64> (load with 64-bit immediate value).
+ * 3. rX = <imm64> (load with 64-bit immediate value);
+ * 4. rX = *(T *)(rY + <off>), where T is one of {u8, u16, u32, u64};
+ * 5. *(T *)(rX + <off>) = rY, where T is one of {u8, u16, u32, u64};
+ * 6. *(T *)(rX + <off>) = <imm>, where T is one of {u8, u16, u32, u64}.
*/
static int bpf_core_patch_insn(struct bpf_program *prog,
const struct bpf_core_relo *relo,
class = BPF_CLASS(insn->code);
if (res->poison) {
+ poison:
/* poison second part of ldimm64 to avoid confusing error from
* verifier about "unknown opcode 00"
*/
prog->name, relo_idx, insn_idx, new_val);
return -ERANGE;
}
+ if (res->fail_memsz_adjust) {
+ pr_warn("prog '%s': relo #%d: insn #%d (LDX/ST/STX) accesses field incorrectly. "
+ "Make sure you are accessing pointers, unsigned integers, or fields of matching type and size.\n",
+ prog->name, relo_idx, insn_idx);
+ goto poison;
+ }
+
orig_val = insn->off;
insn->off = new_val;
pr_debug("prog '%s': relo #%d: patched insn #%d (LDX/ST/STX) off %u -> %u\n",
prog->name, relo_idx, insn_idx, orig_val, new_val);
+
+ if (res->new_sz != res->orig_sz) {
+ int insn_bytes_sz, insn_bpf_sz;
+
+ insn_bytes_sz = insn_bpf_size_to_bytes(insn);
+ if (insn_bytes_sz != res->orig_sz) {
+ pr_warn("prog '%s': relo #%d: insn #%d (LDX/ST/STX) unexpected mem size: got %d, exp %u\n",
+ prog->name, relo_idx, insn_idx, insn_bytes_sz, res->orig_sz);
+ return -EINVAL;
+ }
+
+ insn_bpf_sz = insn_bytes_to_bpf_size(res->new_sz);
+ if (insn_bpf_sz < 0) {
+ pr_warn("prog '%s': relo #%d: insn #%d (LDX/ST/STX) invalid new mem size: %u\n",
+ prog->name, relo_idx, insn_idx, res->new_sz);
+ return -EINVAL;
+ }
+
+ insn->code = BPF_MODE(insn->code) | insn_bpf_sz | BPF_CLASS(insn->code);
+ pr_debug("prog '%s': relo #%d: patched insn #%d (LDX/ST/STX) mem_sz %u -> %u\n",
+ prog->name, relo_idx, insn_idx, res->orig_sz, res->new_sz);
+ }
break;
case BPF_LD: {
__u64 imm;
return 0;
if (targ_btf_path)
- targ_btf = btf__parse_elf(targ_btf_path, NULL);
+ targ_btf = btf__parse(targ_btf_path, NULL);
else
targ_btf = obj->btf_vmlinux;
if (IS_ERR_OR_NULL(targ_btf)) {
err = -EINVAL;
goto out;
}
+ /* no need to apply CO-RE relocation if the program is
+ * not going to be loaded
+ */
+ if (!prog->load)
+ continue;
err = bpf_core_apply_relo(prog, rec, i, obj->btf,
targ_btf, cand_cache);
insn[0].imm = obj->maps[obj->kconfig_map_idx].fd;
insn[1].imm = ext->kcfg.data_off;
} else /* EXT_KSYM */ {
- insn[0].imm = (__u32)ext->ksym.addr;
- insn[1].imm = ext->ksym.addr >> 32;
+ if (ext->ksym.type_id) { /* typed ksyms */
+ insn[0].src_reg = BPF_PSEUDO_BTF_ID;
+ insn[0].imm = ext->ksym.vmlinux_btf_id;
+ } else { /* typeless ksyms */
+ insn[0].imm = (__u32)ext->ksym.addr;
+ insn[1].imm = ext->ksym.addr >> 32;
+ }
}
relo->processed = true;
break;
return err;
}
+ static int bpf_object__resolve_ksyms_btf_id(struct bpf_object *obj)
+ {
+ struct extern_desc *ext;
+ int i, id;
+
+ for (i = 0; i < obj->nr_extern; i++) {
+ const struct btf_type *targ_var, *targ_type;
+ __u32 targ_type_id, local_type_id;
+ const char *targ_var_name;
+ int ret;
+
+ ext = &obj->externs[i];
+ if (ext->type != EXT_KSYM || !ext->ksym.type_id)
+ continue;
+
+ id = btf__find_by_name_kind(obj->btf_vmlinux, ext->name,
+ BTF_KIND_VAR);
+ if (id <= 0) {
+ pr_warn("extern (ksym) '%s': failed to find BTF ID in vmlinux BTF.\n",
+ ext->name);
+ return -ESRCH;
+ }
+
+ /* find local type_id */
+ local_type_id = ext->ksym.type_id;
+
+ /* find target type_id */
+ targ_var = btf__type_by_id(obj->btf_vmlinux, id);
+ targ_var_name = btf__name_by_offset(obj->btf_vmlinux,
+ targ_var->name_off);
+ targ_type = skip_mods_and_typedefs(obj->btf_vmlinux,
+ targ_var->type,
+ &targ_type_id);
+
+ ret = bpf_core_types_are_compat(obj->btf, local_type_id,
+ obj->btf_vmlinux, targ_type_id);
+ if (ret <= 0) {
+ const struct btf_type *local_type;
+ const char *targ_name, *local_name;
+
+ local_type = btf__type_by_id(obj->btf, local_type_id);
+ local_name = btf__name_by_offset(obj->btf,
+ local_type->name_off);
+ targ_name = btf__name_by_offset(obj->btf_vmlinux,
+ targ_type->name_off);
+
+ pr_warn("extern (ksym) '%s': incompatible types, expected [%d] %s %s, but kernel has [%d] %s %s\n",
+ ext->name, local_type_id,
+ btf_kind_str(local_type), local_name, targ_type_id,
+ btf_kind_str(targ_type), targ_name);
+ return -EINVAL;
+ }
+
+ ext->is_set = true;
+ ext->ksym.vmlinux_btf_id = id;
+ pr_debug("extern (ksym) '%s': resolved to [%d] %s %s\n",
+ ext->name, id, btf_kind_str(targ_var), targ_var_name);
+ }
+ return 0;
+ }
+
static int bpf_object__resolve_externs(struct bpf_object *obj,
const char *extra_kconfig)
{
bool need_config = false, need_kallsyms = false;
+ bool need_vmlinux_btf = false;
struct extern_desc *ext;
void *kcfg_data = NULL;
int err, i;
strncmp(ext->name, "CONFIG_", 7) == 0) {
need_config = true;
} else if (ext->type == EXT_KSYM) {
- need_kallsyms = true;
+ if (ext->ksym.type_id)
+ need_vmlinux_btf = true;
+ else
+ need_kallsyms = true;
} else {
pr_warn("unrecognized extern '%s'\n", ext->name);
return -EINVAL;
if (err)
return -EINVAL;
}
+ if (need_vmlinux_btf) {
+ err = bpf_object__resolve_ksyms_btf_id(obj);
+ if (err)
+ return -EINVAL;
+ }
for (i = 0; i < obj->nr_extern; i++) {
ext = &obj->externs[i];
}
err = bpf_object__probe_loading(obj);
+ err = err ? : bpf_object__load_vmlinux_btf(obj);
err = err ? : bpf_object__resolve_externs(obj, obj->kconfig);
err = err ? : bpf_object__sanitize_and_load_btf(obj);
err = err ? : bpf_object__sanitize_maps(obj);
- err = err ? : bpf_object__load_vmlinux_btf(obj);
err = err ? : bpf_object__init_kern_struct_ops_maps(obj);
err = err ? : bpf_object__create_maps(obj);
err = err ? : bpf_object__relocate(obj, attr->target_btf_path);
BPF_XDP_DEVMAP),
BPF_EAPROG_SEC("xdp_cpumap/", BPF_PROG_TYPE_XDP,
BPF_XDP_CPUMAP),
- BPF_EAPROG_SEC("xdp", BPF_PROG_TYPE_XDP,
+ BPF_APROG_SEC("xdp", BPF_PROG_TYPE_XDP,
BPF_XDP),
BPF_PROG_SEC("perf_event", BPF_PROG_TYPE_PERF_EVENT),
BPF_PROG_SEC("lwt_in", BPF_PROG_TYPE_LWT_IN),
btf_id = libbpf_find_prog_btf_id(attach_func_name,
attach_prog_fd);
else
- btf_id = __find_vmlinux_btf_id(prog->obj->btf_vmlinux,
- attach_func_name,
- prog->expected_attach_type);
+ btf_id = libbpf_find_vmlinux_btf_id(attach_func_name,
+ prog->expected_attach_type);
if (btf_id < 0)
return btf_id;