summaryrefslogtreecommitdiffstats
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/Makefile2
-rw-r--r--net/core/dev.c80
-rw-r--r--net/core/dev_addr_lists.c85
-rw-r--r--net/core/filter.c775
-rw-r--r--net/core/neighbour.c4
-rw-r--r--net/core/net_namespace.c2
-rw-r--r--net/core/pktgen.c50
-rw-r--r--net/core/ptp_classifier.c2
-rw-r--r--net/core/rtnetlink.c71
-rw-r--r--net/core/secure_seq.c25
-rw-r--r--net/core/skbuff.c4
-rw-r--r--net/core/sock.c4
-rw-r--r--net/core/tso.c77
-rw-r--r--net/core/utils.c8
14 files changed, 670 insertions, 519 deletions
diff --git a/net/core/Makefile b/net/core/Makefile
index 826b925..71093d9 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -9,7 +9,7 @@ obj-$(CONFIG_SYSCTL) += sysctl_net_core.o
obj-y += dev.o ethtool.o dev_addr_lists.o dst.o netevent.o \
neighbour.o rtnetlink.o utils.o link_watch.o filter.o \
- sock_diag.o dev_ioctl.o
+ sock_diag.o dev_ioctl.o tso.o
obj-$(CONFIG_XFRM) += flow.o
obj-y += net-sysfs.o
diff --git a/net/core/dev.c b/net/core/dev.c
index 867adb2..0355ca5 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3957,6 +3957,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
}
NAPI_GRO_CB(skb)->count = 1;
NAPI_GRO_CB(skb)->age = jiffies;
+ NAPI_GRO_CB(skb)->last = skb;
skb_shinfo(skb)->gso_size = skb_gro_len(skb);
skb->next = napi->gro_list;
napi->gro_list = skb;
@@ -4547,6 +4548,32 @@ void *netdev_adjacent_get_private(struct list_head *adj_list)
EXPORT_SYMBOL(netdev_adjacent_get_private);
/**
+ * netdev_upper_get_next_dev_rcu - Get the next dev from upper list
+ * @dev: device
+ * @iter: list_head ** of the current position
+ *
+ * Gets the next device from the dev's upper list, starting from iter
+ * position. The caller must hold RCU read lock.
+ */
+struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev,
+ struct list_head **iter)
+{
+ struct netdev_adjacent *upper;
+
+ WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_rtnl_is_held());
+
+ upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list);
+
+ if (&upper->list == &dev->adj_list.upper)
+ return NULL;
+
+ *iter = &upper->list;
+
+ return upper->dev;
+}
+EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu);
+
+/**
* netdev_all_upper_get_next_dev_rcu - Get the next dev from upper list
* @dev: device
* @iter: list_head ** of the current position
@@ -4628,6 +4655,32 @@ void *netdev_lower_get_next_private_rcu(struct net_device *dev,
EXPORT_SYMBOL(netdev_lower_get_next_private_rcu);
/**
+ * netdev_lower_get_next - Get the next device from the lower neighbour
+ * list
+ * @dev: device
+ * @iter: list_head ** of the current position
+ *
+ * Gets the next netdev_adjacent from the dev's lower neighbour
+ * list, starting from iter position. The caller must hold RTNL lock or
+ * its own locking that guarantees that the neighbour lower
+ * list will remain unchainged.
+ */
+void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter)
+{
+ struct netdev_adjacent *lower;
+
+ lower = list_entry((*iter)->next, struct netdev_adjacent, list);
+
+ if (&lower->list == &dev->adj_list.lower)
+ return NULL;
+
+ *iter = &lower->list;
+
+ return lower->dev;
+}
+EXPORT_SYMBOL(netdev_lower_get_next);
+
+/**
* netdev_lower_get_first_private_rcu - Get the first ->private from the
* lower neighbour list, RCU
* variant
@@ -5077,6 +5130,30 @@ void *netdev_lower_dev_get_private(struct net_device *dev,
}
EXPORT_SYMBOL(netdev_lower_dev_get_private);
+
+int dev_get_nest_level(struct net_device *dev,
+ bool (*type_check)(struct net_device *dev))
+{
+ struct net_device *lower = NULL;
+ struct list_head *iter;
+ int max_nest = -1;
+ int nest;
+
+ ASSERT_RTNL();
+
+ netdev_for_each_lower_dev(dev, lower, iter) {
+ nest = dev_get_nest_level(lower, type_check);
+ if (max_nest < nest)
+ max_nest = nest;
+ }
+
+ if (type_check(dev))
+ max_nest++;
+
+ return max_nest;
+}
+EXPORT_SYMBOL(dev_get_nest_level);
+
static void dev_change_rx_flags(struct net_device *dev, int flags)
{
const struct net_device_ops *ops = dev->netdev_ops;
@@ -5242,7 +5319,6 @@ void __dev_set_rx_mode(struct net_device *dev)
if (ops->ndo_set_rx_mode)
ops->ndo_set_rx_mode(dev);
}
-EXPORT_SYMBOL(__dev_set_rx_mode);
void dev_set_rx_mode(struct net_device *dev)
{
@@ -5547,7 +5623,7 @@ static int dev_new_index(struct net *net)
/* Delayed registration/unregisteration */
static LIST_HEAD(net_todo_list);
-static DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq);
+DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq);
static void net_set_todo(struct net_device *dev)
{
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index 329d579..b6b2306 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -225,6 +225,91 @@ void __hw_addr_unsync(struct netdev_hw_addr_list *to_list,
}
EXPORT_SYMBOL(__hw_addr_unsync);
+/**
+ * __hw_addr_sync_dev - Synchonize device's multicast list
+ * @list: address list to syncronize
+ * @dev: device to sync
+ * @sync: function to call if address should be added
+ * @unsync: function to call if address should be removed
+ *
+ * This funciton is intended to be called from the ndo_set_rx_mode
+ * function of devices that require explicit address add/remove
+ * notifications. The unsync function may be NULL in which case
+ * the addresses requiring removal will simply be removed without
+ * any notification to the device.
+ **/
+int __hw_addr_sync_dev(struct netdev_hw_addr_list *list,
+ struct net_device *dev,
+ int (*sync)(struct net_device *, const unsigned char *),
+ int (*unsync)(struct net_device *,
+ const unsigned char *))
+{
+ struct netdev_hw_addr *ha, *tmp;
+ int err;
+
+ /* first go through and flush out any stale entries */
+ list_for_each_entry_safe(ha, tmp, &list->list, list) {
+ if (!ha->sync_cnt || ha->refcount != 1)
+ continue;
+
+ /* if unsync is defined and fails defer unsyncing address */
+ if (unsync && unsync(dev, ha->addr))
+ continue;
+
+ ha->sync_cnt--;
+ __hw_addr_del_entry(list, ha, false, false);
+ }
+
+ /* go through and sync new entries to the list */
+ list_for_each_entry_safe(ha, tmp, &list->list, list) {
+ if (ha->sync_cnt)
+ continue;
+
+ err = sync(dev, ha->addr);
+ if (err)
+ return err;
+
+ ha->sync_cnt++;
+ ha->refcount++;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL(__hw_addr_sync_dev);
+
+/**
+ * __hw_addr_unsync_dev - Remove synchonized addresses from device
+ * @list: address list to remove syncronized addresses from
+ * @dev: device to sync
+ * @unsync: function to call if address should be removed
+ *
+ * Remove all addresses that were added to the device by __hw_addr_sync_dev().
+ * This function is intended to be called from the ndo_stop or ndo_open
+ * functions on devices that require explicit address add/remove
+ * notifications. If the unsync function pointer is NULL then this function
+ * can be used to just reset the sync_cnt for the addresses in the list.
+ **/
+void __hw_addr_unsync_dev(struct netdev_hw_addr_list *list,
+ struct net_device *dev,
+ int (*unsync)(struct net_device *,
+ const unsigned char *))
+{
+ struct netdev_hw_addr *ha, *tmp;
+
+ list_for_each_entry_safe(ha, tmp, &list->list, list) {
+ if (!ha->sync_cnt)
+ continue;
+
+ /* if unsync is defined and fails defer unsyncing address */
+ if (unsync && unsync(dev, ha->addr))
+ continue;
+
+ ha->sync_cnt--;
+ __hw_addr_del_entry(list, ha, false, false);
+ }
+}
+EXPORT_SYMBOL(__hw_addr_unsync_dev);
+
static void __hw_addr_flush(struct netdev_hw_addr_list *list)
{
struct netdev_hw_addr *ha, *tmp;
diff --git a/net/core/filter.c b/net/core/filter.c
index c442a0d..842f839 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -153,102 +153,107 @@ noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
* keep, 0 for none. @ctx is the data we are operating on, @insn is the
* array of filter instructions.
*/
-unsigned int __sk_run_filter(void *ctx, const struct sock_filter_int *insn)
+static unsigned int __sk_run_filter(void *ctx, const struct sock_filter_int *insn)
{
u64 stack[MAX_BPF_STACK / sizeof(u64)];
u64 regs[MAX_BPF_REG], tmp;
static const void *jumptable[256] = {
[0 ... 255] = &&default_label,
/* Now overwrite non-defaults ... */
-#define DL(A, B, C) [BPF_##A|BPF_##B|BPF_##C] = &&A##_##B##_##C
- DL(ALU, ADD, X),
- DL(ALU, ADD, K),
- DL(ALU, SUB, X),
- DL(ALU, SUB, K),
- DL(ALU, AND, X),
- DL(ALU, AND, K),
- DL(ALU, OR, X),
- DL(ALU, OR, K),
- DL(ALU, LSH, X),
- DL(ALU, LSH, K),
- DL(ALU, RSH, X),
- DL(ALU, RSH, K),
- DL(ALU, XOR, X),
- DL(ALU, XOR, K),
- DL(ALU, MUL, X),
- DL(ALU, MUL, K),
- DL(ALU, MOV, X),
- DL(ALU, MOV, K),
- DL(ALU, DIV, X),
- DL(ALU, DIV, K),
- DL(ALU, MOD, X),
- DL(ALU, MOD, K),
- DL(ALU, NEG, 0),
- DL(ALU, END, TO_BE),
- DL(ALU, END, TO_LE),
- DL(ALU64, ADD, X),
- DL(ALU64, ADD, K),
- DL(ALU64, SUB, X),
- DL(ALU64, SUB, K),
- DL(ALU64, AND, X),
- DL(ALU64, AND, K),
- DL(ALU64, OR, X),
- DL(ALU64, OR, K),
- DL(ALU64, LSH, X),
- DL(ALU64, LSH, K),
- DL(ALU64, RSH, X),
- DL(ALU64, RSH, K),
- DL(ALU64, XOR, X),
- DL(ALU64, XOR, K),
- DL(ALU64, MUL, X),
- DL(ALU64, MUL, K),
- DL(ALU64, MOV, X),
- DL(ALU64, MOV, K),
- DL(ALU64, ARSH, X),
- DL(ALU64, ARSH, K),
- DL(ALU64, DIV, X),
- DL(ALU64, DIV, K),
- DL(ALU64, MOD, X),
- DL(ALU64, MOD, K),
- DL(ALU64, NEG, 0),
- DL(JMP, CALL, 0),
- DL(JMP, JA, 0),
- DL(JMP, JEQ, X),
- DL(JMP, JEQ, K),
- DL(JMP, JNE, X),
- DL(JMP, JNE, K),
- DL(JMP, JGT, X),
- DL(JMP, JGT, K),
- DL(JMP, JGE, X),
- DL(JMP, JGE, K),
- DL(JMP, JSGT, X),
- DL(JMP, JSGT, K),
- DL(JMP, JSGE, X),
- DL(JMP, JSGE, K),
- DL(JMP, JSET, X),
- DL(JMP, JSET, K),
- DL(JMP, EXIT, 0),
- DL(STX, MEM, B),
- DL(STX, MEM, H),
- DL(STX, MEM, W),
- DL(STX, MEM, DW),
- DL(STX, XADD, W),
- DL(STX, XADD, DW),
- DL(ST, MEM, B),
- DL(ST, MEM, H),
- DL(ST, MEM, W),
- DL(ST, MEM, DW),
- DL(LDX, MEM, B),
- DL(LDX, MEM, H),
- DL(LDX, MEM, W),
- DL(LDX, MEM, DW),
- DL(LD, ABS, W),
- DL(LD, ABS, H),
- DL(LD, ABS, B),
- DL(LD, IND, W),
- DL(LD, IND, H),
- DL(LD, IND, B),
-#undef DL
+ /* 32 bit ALU operations */
+ [BPF_ALU | BPF_ADD | BPF_X] = &&ALU_ADD_X,
+ [BPF_ALU | BPF_ADD | BPF_K] = &&ALU_ADD_K,
+ [BPF_ALU | BPF_SUB | BPF_X] = &&ALU_SUB_X,
+ [BPF_ALU | BPF_SUB | BPF_K] = &&ALU_SUB_K,
+ [BPF_ALU | BPF_AND | BPF_X] = &&ALU_AND_X,
+ [BPF_ALU | BPF_AND | BPF_K] = &&ALU_AND_K,
+ [BPF_ALU | BPF_OR | BPF_X] = &&ALU_OR_X,
+ [BPF_ALU | BPF_OR | BPF_K] = &&ALU_OR_K,
+ [BPF_ALU | BPF_LSH | BPF_X] = &&ALU_LSH_X,
+ [BPF_ALU | BPF_LSH | BPF_K] = &&ALU_LSH_K,
+ [BPF_ALU | BPF_RSH | BPF_X] = &&ALU_RSH_X,
+ [BPF_ALU | BPF_RSH | BPF_K] = &&ALU_RSH_K,
+ [BPF_ALU | BPF_XOR | BPF_X] = &&ALU_XOR_X,
+ [BPF_ALU | BPF_XOR | BPF_K] = &&ALU_XOR_K,
+ [BPF_ALU | BPF_MUL | BPF_X] = &&ALU_MUL_X,
+ [BPF_ALU | BPF_MUL | BPF_K] = &&ALU_MUL_K,
+ [BPF_ALU | BPF_MOV | BPF_X] = &&ALU_MOV_X,
+ [BPF_ALU | BPF_MOV | BPF_K] = &&ALU_MOV_K,
+ [BPF_ALU | BPF_DIV | BPF_X] = &&ALU_DIV_X,
+ [BPF_ALU | BPF_DIV | BPF_K] = &&ALU_DIV_K,
+ [BPF_ALU | BPF_MOD | BPF_X] = &&ALU_MOD_X,
+ [BPF_ALU | BPF_MOD | BPF_K] = &&ALU_MOD_K,
+ [BPF_ALU | BPF_NEG] = &&ALU_NEG,
+ [BPF_ALU | BPF_END | BPF_TO_BE] = &&ALU_END_TO_BE,
+ [BPF_ALU | BPF_END | BPF_TO_LE] = &&ALU_END_TO_LE,
+ /* 64 bit ALU operations */
+ [BPF_ALU64 | BPF_ADD | BPF_X] = &&ALU64_ADD_X,
+ [BPF_ALU64 | BPF_ADD | BPF_K] = &&ALU64_ADD_K,
+ [BPF_ALU64 | BPF_SUB | BPF_X] = &&ALU64_SUB_X,
+ [BPF_ALU64 | BPF_SUB | BPF_K] = &&ALU64_SUB_K,
+ [BPF_ALU64 | BPF_AND | BPF_X] = &&ALU64_AND_X,
+ [BPF_ALU64 | BPF_AND | BPF_K] = &&ALU64_AND_K,
+ [BPF_ALU64 | BPF_OR | BPF_X] = &&ALU64_OR_X,
+ [BPF_ALU64 | BPF_OR | BPF_K] = &&ALU64_OR_K,
+ [BPF_ALU64 | BPF_LSH | BPF_X] = &&ALU64_LSH_X,
+ [BPF_ALU64 | BPF_LSH | BPF_K] = &&ALU64_LSH_K,
+ [BPF_ALU64 | BPF_RSH | BPF_X] = &&ALU64_RSH_X,
+ [BPF_ALU64 | BPF_RSH | BPF_K] = &&ALU64_RSH_K,
+ [BPF_ALU64 | BPF_XOR | BPF_X] = &&ALU64_XOR_X,
+ [BPF_ALU64 | BPF_XOR | BPF_K] = &&ALU64_XOR_K,
+ [BPF_ALU64 | BPF_MUL | BPF_X] = &&ALU64_MUL_X,
+ [BPF_ALU64 | BPF_MUL | BPF_K] = &&ALU64_MUL_K,
+ [BPF_ALU64 | BPF_MOV | BPF_X] = &&ALU64_MOV_X,
+ [BPF_ALU64 | BPF_MOV | BPF_K] = &&ALU64_MOV_K,
+ [BPF_ALU64 | BPF_ARSH | BPF_X] = &&ALU64_ARSH_X,
+ [BPF_ALU64 | BPF_ARSH | BPF_K] = &&ALU64_ARSH_K,
+ [BPF_ALU64 | BPF_DIV | BPF_X] = &&ALU64_DIV_X,
+ [BPF_ALU64 | BPF_DIV | BPF_K] = &&ALU64_DIV_K,
+ [BPF_ALU64 | BPF_MOD | BPF_X] = &&ALU64_MOD_X,
+ [BPF_ALU64 | BPF_MOD | BPF_K] = &&ALU64_MOD_K,
+ [BPF_ALU64 | BPF_NEG] = &&ALU64_NEG,
+ /* Call instruction */
+ [BPF_JMP | BPF_CALL] = &&JMP_CALL,
+ /* Jumps */
+ [BPF_JMP | BPF_JA] = &&JMP_JA,
+ [BPF_JMP | BPF_JEQ | BPF_X] = &&JMP_JEQ_X,
+ [BPF_JMP | BPF_JEQ | BPF_K] = &&JMP_JEQ_K,
+ [BPF_JMP | BPF_JNE | BPF_X] = &&JMP_JNE_X,
+ [BPF_JMP | BPF_JNE | BPF_K] = &&JMP_JNE_K,
+ [BPF_JMP | BPF_JGT | BPF_X] = &&JMP_JGT_X,
+ [BPF_JMP | BPF_JGT | BPF_K] = &&JMP_JGT_K,
+ [BPF_JMP | BPF_JGE | BPF_X] = &&JMP_JGE_X,
+ [BPF_JMP | BPF_JGE | BPF_K] = &&JMP_JGE_K,
+ [BPF_JMP | BPF_JSGT | BPF_X] = &&JMP_JSGT_X,
+ [BPF_JMP | BPF_JSGT | BPF_K] = &&JMP_JSGT_K,
+ [BPF_JMP | BPF_JSGE | BPF_X] = &&JMP_JSGE_X,
+ [BPF_JMP | BPF_JSGE | BPF_K] = &&JMP_JSGE_K,
+ [BPF_JMP | BPF_JSET | BPF_X] = &&JMP_JSET_X,
+ [BPF_JMP | BPF_JSET | BPF_K] = &&JMP_JSET_K,
+ /* Program return */
+ [BPF_JMP | BPF_EXIT] = &&JMP_EXIT,
+ /* Store instructions */
+ [BPF_STX | BPF_MEM | BPF_B] = &&STX_MEM_B,
+ [BPF_STX | BPF_MEM | BPF_H] = &&STX_MEM_H,
+ [BPF_STX | BPF_MEM | BPF_W] = &&STX_MEM_W,
+ [BPF_STX | BPF_MEM | BPF_DW] = &&STX_MEM_DW,
+ [BPF_STX | BPF_XADD | BPF_W] = &&STX_XADD_W,
+ [BPF_STX | BPF_XADD | BPF_DW] = &&STX_XADD_DW,
+ [BPF_ST | BPF_MEM | BPF_B] = &&ST_MEM_B,
+ [BPF_ST | BPF_MEM | BPF_H] = &&ST_MEM_H,
+ [BPF_ST | BPF_MEM | BPF_W] = &&ST_MEM_W,
+ [BPF_ST | BPF_MEM | BPF_DW] = &&ST_MEM_DW,
+ /* Load instructions */
+ [BPF_LDX | BPF_MEM | BPF_B] = &&LDX_MEM_B,
+ [BPF_LDX | BPF_MEM | BPF_H] = &&LDX_MEM_H,
+ [BPF_LDX | BPF_MEM | BPF_W] = &&LDX_MEM_W,
+ [BPF_LDX | BPF_MEM | BPF_DW] = &&LDX_MEM_DW,
+ [BPF_LD | BPF_ABS | BPF_W] = &&LD_ABS_W,
+ [BPF_LD | BPF_ABS | BPF_H] = &&LD_ABS_H,
+ [BPF_LD | BPF_ABS | BPF_B] = &&LD_ABS_B,
+ [BPF_LD | BPF_IND | BPF_W] = &&LD_IND_W,
+ [BPF_LD | BPF_IND | BPF_H] = &&LD_IND_H,
+ [BPF_LD | BPF_IND | BPF_B] = &&LD_IND_B,
};
void *ptr;
int off;
@@ -290,10 +295,10 @@ select_insn:
ALU(XOR, ^)
ALU(MUL, *)
#undef ALU
- ALU_NEG_0:
+ ALU_NEG:
A = (u32) -A;
CONT;
- ALU64_NEG_0:
+ ALU64_NEG:
A = -A;
CONT;
ALU_MOV_X:
@@ -382,7 +387,7 @@ select_insn:
CONT;
/* CALL */
- JMP_CALL_0:
+ JMP_CALL:
/* Function call scratches BPF_R1-BPF_R5 registers,
* preserves BPF_R6-BPF_R9, and stores return value
* into BPF_R0.
@@ -392,7 +397,7 @@ select_insn:
CONT;
/* JMP */
- JMP_JA_0:
+ JMP_JA:
insn += insn->off;
CONT;
JMP_JEQ_X:
@@ -479,7 +484,7 @@ select_insn:
CONT_JMP;
}
CONT;
- JMP_EXIT_0:
+ JMP_EXIT:
return BPF_R0;
/* STX and ST and LDX*/
@@ -531,11 +536,13 @@ load_word:
* Output:
* BPF_R0 - 8/16/32-bit skb data converted to cpu endianness
*/
+
ptr = load_pointer((struct sk_buff *) ctx, off, 4, &tmp);
if (likely(ptr != NULL)) {
BPF_R0 = get_unaligned_be32(ptr);
CONT;
}
+
return 0;
LD_ABS_H: /* BPF_R0 = ntohs(*(u16 *) (skb->data + K)) */
off = K;
@@ -545,6 +552,7 @@ load_half:
BPF_R0 = get_unaligned_be16(ptr);
CONT;
}
+
return 0;
LD_ABS_B: /* BPF_R0 = *(u8 *) (ctx + K) */
off = K;
@@ -554,6 +562,7 @@ load_byte:
BPF_R0 = *(u8 *)ptr;
CONT;
}
+
return 0;
LD_IND_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + X + K)) */
off = K + X;
@@ -571,15 +580,6 @@ load_byte:
return 0;
}
-u32 sk_run_filter_int_seccomp(const struct seccomp_data *ctx,
- const struct sock_filter_int *insni)
- __attribute__ ((alias ("__sk_run_filter")));
-
-u32 sk_run_filter_int_skb(const struct sk_buff *ctx,
- const struct sock_filter_int *insni)
- __attribute__ ((alias ("__sk_run_filter")));
-EXPORT_SYMBOL_GPL(sk_run_filter_int_skb);
-
/* Helper to find the offset of pkt_type in sk_buff structure. We want
* to make sure its still a 3bit field starting at a byte boundary;
* taken from arch/x86/net/bpf_jit_comp.c.
@@ -672,14 +672,10 @@ static bool convert_bpf_extensions(struct sock_filter *fp,
BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2);
/* A = *(u16 *) (ctx + offsetof(protocol)) */
- *insn = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX,
- offsetof(struct sk_buff, protocol));
- insn++;
-
+ *insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX,
+ offsetof(struct sk_buff, protocol));
/* A = ntohs(A) [emitting a nop or swap16] */
- insn->code = BPF_ALU | BPF_END | BPF_FROM_BE;
- insn->a_reg = BPF_REG_A;
- insn->imm = 16;
+ *insn = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, 16);
break;
case SKF_AD_OFF + SKF_AD_PKTTYPE:
@@ -688,37 +684,27 @@ static bool convert_bpf_extensions(struct sock_filter *fp,
if (insn->off < 0)
return false;
insn++;
-
*insn = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, PKT_TYPE_MAX);
break;
case SKF_AD_OFF + SKF_AD_IFINDEX:
case SKF_AD_OFF + SKF_AD_HATYPE:
- *insn = BPF_LDX_MEM(size_to_bpf(FIELD_SIZEOF(struct sk_buff, dev)),
- BPF_REG_TMP, BPF_REG_CTX,
- offsetof(struct sk_buff, dev));
- insn++;
-
- /* if (tmp != 0) goto pc+1 */
- *insn = BPF_JMP_IMM(BPF_JNE, BPF_REG_TMP, 0, 1);
- insn++;
-
- *insn = BPF_EXIT_INSN();
- insn++;
-
BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4);
BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, type) != 2);
-
- insn->a_reg = BPF_REG_A;
- insn->x_reg = BPF_REG_TMP;
-
- if (fp->k == SKF_AD_OFF + SKF_AD_IFINDEX) {
- insn->code = BPF_LDX | BPF_MEM | BPF_W;
- insn->off = offsetof(struct net_device, ifindex);
- } else {
- insn->code = BPF_LDX | BPF_MEM | BPF_H;
- insn->off = offsetof(struct net_device, type);
- }
+ BUILD_BUG_ON(bytes_to_bpf_size(FIELD_SIZEOF(struct sk_buff, dev)) < 0);
+
+ *insn++ = BPF_LDX_MEM(bytes_to_bpf_size(FIELD_SIZEOF(struct sk_buff, dev)),
+ BPF_REG_TMP, BPF_REG_CTX,
+ offsetof(struct sk_buff, dev));
+ /* if (tmp != 0) goto pc + 1 */
+ *insn++ = BPF_JMP_IMM(BPF_JNE, BPF_REG_TMP, 0, 1);
+ *insn++ = BPF_EXIT_INSN();
+ if (fp->k == SKF_AD_OFF + SKF_AD_IFINDEX)
+ *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_TMP,
+ offsetof(struct net_device, ifindex));
+ else
+ *insn = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_TMP,
+ offsetof(struct net_device, type));
break;
case SKF_AD_OFF + SKF_AD_MARK:
@@ -745,22 +731,17 @@ static bool convert_bpf_extensions(struct sock_filter *fp,
case SKF_AD_OFF + SKF_AD_VLAN_TAG:
case SKF_AD_OFF + SKF_AD_VLAN_TAG_PRESENT:
BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2);
-
- /* A = *(u16 *) (ctx + offsetof(vlan_tci)) */
- *insn = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX,
- offsetof(struct sk_buff, vlan_tci));
- insn++;
-
BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000);
+ /* A = *(u16 *) (ctx + offsetof(vlan_tci)) */
+ *insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX,
+ offsetof(struct sk_buff, vlan_tci));
if (fp->k == SKF_AD_OFF + SKF_AD_VLAN_TAG) {
*insn = BPF_ALU32_IMM(BPF_AND, BPF_REG_A,
~VLAN_TAG_PRESENT);
} else {
/* A >>= 12 */
- *insn = BPF_ALU32_IMM(BPF_RSH, BPF_REG_A, 12);
- insn++;
-
+ *insn++ = BPF_ALU32_IMM(BPF_RSH, BPF_REG_A, 12);
/* A &= 1 */
*insn = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, 1);
}
@@ -772,34 +753,27 @@ static bool convert_bpf_extensions(struct sock_filter *fp,
case SKF_AD_OFF + SKF_AD_CPU:
case SKF_AD_OFF + SKF_AD_RANDOM:
/* arg1 = ctx */
- *insn = BPF_ALU64_REG(BPF_MOV, BPF_REG_ARG1, BPF_REG_CTX);
- insn++;
-
+ *insn++ = BPF_MOV64_REG(BPF_REG_ARG1, BPF_REG_CTX);
/* arg2 = A */
- *insn = BPF_ALU64_REG(BPF_MOV, BPF_REG_ARG2, BPF_REG_A);
- insn++;
-
+ *insn++ = BPF_MOV64_REG(BPF_REG_ARG2, BPF_REG_A);
/* arg3 = X */
- *insn = BPF_ALU64_REG(BPF_MOV, BPF_REG_ARG3, BPF_REG_X);
- insn++;
-
+ *insn++ = BPF_MOV64_REG(BPF_REG_ARG3, BPF_REG_X);
/* Emit call(ctx, arg2=A, arg3=X) */
- insn->code = BPF_JMP | BPF_CALL;
switch (fp->k) {
case SKF_AD_OFF + SKF_AD_PAY_OFFSET:
- insn->imm = __skb_get_pay_offset - __bpf_call_base;
+ *insn = BPF_EMIT_CALL(__skb_get_pay_offset);
break;
case SKF_AD_OFF + SKF_AD_NLATTR:
- insn->imm = __skb_get_nlattr - __bpf_call_base;
+ *insn = BPF_EMIT_CALL(__skb_get_nlattr);
break;
case SKF_AD_OFF + SKF_AD_NLATTR_NEST:
- insn->imm = __skb_get_nlattr_nest - __bpf_call_base;
+ *insn = BPF_EMIT_CALL(__skb_get_nlattr_nest);
break;
case SKF_AD_OFF + SKF_AD_CPU:
- insn->imm = __get_raw_cpu_id - __bpf_call_base;
+ *insn = BPF_EMIT_CALL(__get_raw_cpu_id);
break;
case SKF_AD_OFF + SKF_AD_RANDOM:
- insn->imm = __get_random_u32 - __bpf_call_base;
+ *insn = BPF_EMIT_CALL(__get_random_u32);
break;
}
break;
@@ -871,9 +845,8 @@ do_pass:
new_insn = new_prog;
fp = prog;
- if (new_insn) {
- *new_insn = BPF_ALU64_REG(BPF_MOV, BPF_REG_CTX, BPF_REG_ARG1);
- }
+ if (new_insn)
+ *new_insn = BPF_MOV64_REG(BPF_REG_CTX, BPF_REG_ARG1);
new_insn++;
for (i = 0; i < len; fp++, i++) {
@@ -921,17 +894,16 @@ do_pass:
convert_bpf_extensions(fp, &insn))
break;
- insn->code = fp->code;
- insn->a_reg = BPF_REG_A;
- insn->x_reg = BPF_REG_X;
- insn->imm = fp->k;
+ *insn = BPF_RAW_INSN(fp->code, BPF_REG_A, BPF_REG_X, 0, fp->k);
break;
- /* Jump opcodes map as-is, but offsets need adjustment. */
- case BPF_JMP | BPF_JA:
- target = i + fp->k + 1;
- insn->code = fp->code;
-#define EMIT_JMP \
+ /* Jump transformation cannot use BPF block macros
+ * everywhere as offset calculation and target updates
+ * require a bit more work than the rest, i.e. jump
+ * opcodes map as-is, but offsets need adjustment.
+ */
+
+#define BPF_EMIT_JMP \
do { \
if (target >= len || target < 0) \
goto err; \
@@ -940,7 +912,10 @@ do_pass:
insn->off -= insn - tmp_insns; \
} while (0)
- EMIT_JMP;
+ case BPF_JMP | BPF_JA:
+ target = i + fp->k + 1;
+ insn->code = fp->code;
+ BPF_EMIT_JMP;
break;
case BPF_JMP | BPF_JEQ | BPF_K:
@@ -956,10 +931,7 @@ do_pass:
* immediate into tmp register and use it
* in compare insn.
*/
- insn->code = BPF_ALU | BPF_MOV | BPF_K;
- insn->a_reg = BPF_REG_TMP;
- insn->imm = fp->k;
- insn++;
+ *insn++ = BPF_MOV32_IMM(BPF_REG_TMP, fp->k);
insn->a_reg = BPF_REG_A;
insn->x_reg = BPF_REG_TMP;
@@ -975,7 +947,7 @@ do_pass:
if (fp->jf == 0) {
insn->code = BPF_JMP | BPF_OP(fp->code) | bpf_src;
target = i + fp->jt + 1;
- EMIT_JMP;
+ BPF_EMIT_JMP;
break;
}
@@ -983,116 +955,94 @@ do_pass:
if (fp->jt == 0 && BPF_OP(fp->code) == BPF_JEQ) {
insn->code = BPF_JMP | BPF_JNE | bpf_src;
target = i + fp->jf + 1;
- EMIT_JMP;
+ BPF_EMIT_JMP;
break;
}
/* Other jumps are mapped into two insns: Jxx and JA. */
target = i + fp->jt + 1;
insn->code = BPF_JMP | BPF_OP(fp->code) | bpf_src;
- EMIT_JMP;
+ BPF_EMIT_JMP;
insn++;
insn->code = BPF_JMP | BPF_JA;
target = i + fp->jf + 1;
- EMIT_JMP;
+ BPF_EMIT_JMP;
break;
/* ldxb 4 * ([14] & 0xf) is remaped into 6 insns. */
case BPF_LDX | BPF_MSH | BPF_B:
/* tmp = A */
- *insn = BPF_ALU64_REG(BPF_MOV, BPF_REG_TMP, BPF_REG_A);
- insn++;
-
+ *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_A);
/* A = BPF_R0 = *(u8 *) (skb->data + K) */
- *insn = BPF_LD_ABS(BPF_B, fp->k);
- insn++;
-
+ *insn++ = BPF_LD_ABS(BPF_B, fp->k);
/* A &= 0xf */
- *insn = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, 0xf);
- insn++;
-
+ *insn++ = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, 0xf);
/* A <<= 2 */
- *insn = BPF_ALU32_IMM(BPF_LSH, BPF_REG_A, 2);
- insn++;
-
+ *insn++ = BPF_ALU32_IMM(BPF_LSH, BPF_REG_A, 2);
/* X = A */
- *insn = BPF_ALU64_REG(BPF_MOV, BPF_REG_X, BPF_REG_A);
- insn++;
-
+ *insn++ = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A);
/* A = tmp */
- *insn = BPF_ALU64_REG(BPF_MOV, BPF_REG_A, BPF_REG_TMP);
+ *insn = BPF_MOV64_REG(BPF_REG_A, BPF_REG_TMP);
break;
/* RET_K, RET_A are remaped into 2 insns. */
case BPF_RET | BPF_A:
case BPF_RET | BPF_K:
- insn->code = BPF_ALU | BPF_MOV |
- (BPF_RVAL(fp->code) == BPF_K ?
- BPF_K : BPF_X);
- insn->a_reg = 0;
- insn->x_reg = BPF_REG_A;
- insn->imm = fp->k;
- insn++;
-
+ *insn++ = BPF_MOV32_RAW(BPF_RVAL(fp->code) == BPF_K ?
+ BPF_K : BPF_X, BPF_REG_0,
+ BPF_REG_A, fp->k);
*insn = BPF_EXIT_INSN();
break;
/* Store to stack. */
case BPF_ST:
case BPF_STX:
- insn->code = BPF_STX | BPF_MEM | BPF_W;
- insn->a_reg = BPF_REG_FP;
- insn->x_reg = fp->code == BPF_ST ?
- BPF_REG_A : BPF_REG_X;
- insn->off = -(BPF_MEMWORDS - fp->k) * 4;
+ *insn = BPF_STX_MEM(BPF_W, BPF_REG_FP, BPF_CLASS(fp->code) ==
+ BPF_ST ? BPF_REG_A : BPF_REG_X,
+ -(BPF_MEMWORDS - fp->k) * 4);
break;
/* Load from stack. */
case BPF_LD | BPF_MEM:
case BPF_LDX | BPF_MEM:
- insn->code = BPF_LDX | BPF_MEM | BPF_W;
- insn->a_reg = BPF_CLASS(fp->code) == BPF_LD ?
- BPF_REG_A : BPF_REG_X;
- insn->x_reg = BPF_REG_FP;
- insn->off = -(BPF_MEMWORDS - fp->k) * 4;
+ *insn = BPF_LDX_MEM(BPF_W, BPF_CLASS(fp->code) == BPF_LD ?
+ BPF_REG_A : BPF_REG_X, BPF_REG_FP,
+ -(BPF_MEMWORDS - fp->k) * 4);
break;
/* A = K or X = K */
case BPF_LD | BPF_IMM:
case BPF_LDX | BPF_IMM:
- insn->code = BPF_ALU | BPF_MOV | BPF_K;
- insn->a_reg = BPF_CLASS(fp->code) == BPF_LD ?
- BPF_REG_A : BPF_REG_X;
- insn->imm = fp->k;
+ *insn = BPF_MOV32_IMM(BPF_CLASS(fp->code) == BPF_LD ?
+ BPF_REG_A : BPF_REG_X, fp->k);
break;
/* X = A */
case BPF_MISC | BPF_TAX:
- *insn = BPF_ALU64_REG(BPF_MOV, BPF_REG_X, BPF_REG_A);
+ *insn = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A);
break;
/* A = X */
case BPF_MISC | BPF_TXA:
- *insn = BPF_ALU64_REG(BPF_MOV, BPF_REG_A, BPF_REG_X);
+ *insn = BPF_MOV64_REG(BPF_REG_A, BPF_REG_X);
break;
/* A = skb->len or X = skb->len */
case BPF_LD | BPF_W | BPF_LEN:
case BPF_LDX | BPF_W | BPF_LEN:
- insn->code = BPF_LDX | BPF_MEM | BPF_W;
- insn->a_reg = BPF_CLASS(fp->code) == BPF_LD ?
- BPF_REG_A : BPF_REG_X;
- insn->x_reg = BPF_REG_CTX;
- insn->off = offsetof(struct sk_buff, len);
+ *insn = BPF_LDX_MEM(BPF_W, BPF_CLASS(fp->code) == BPF_LD ?
+ BPF_REG_A : BPF_REG_X, BPF_REG_CTX,
+ offsetof(struct sk_buff, len));
break;
- /* access seccomp_data fields */
+ /* Access seccomp_data fields. */
case BPF_LDX | BPF_ABS | BPF_W:
/* A = *(u32 *) (ctx + K) */
*insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX, fp->k);
break;
+ /* Unkown instruction. */
default:
goto err;
}
@@ -1101,7 +1051,6 @@ do_pass:
if (new_prog)
memcpy(new_insn, tmp_insns,
sizeof(*insn) * (insn - tmp_insns));
-
new_insn += insn - tmp_insns;
}
@@ -1116,7 +1065,6 @@ do_pass:
new_flen = new_insn - new_prog;
if (pass > 2)
goto err;
-
goto do_pass;
}
@@ -1140,44 +1088,46 @@ err:
*/
static int check_load_and_stores(struct sock_filter *filter, int flen)
{
- u16 *masks, memvalid = 0; /* one bit per cell, 16 cells */
+ u16 *masks, memvalid = 0; /* One bit per cell, 16 cells */
int pc, ret = 0;
BUILD_BUG_ON(BPF_MEMWORDS > 16);
+
masks = kmalloc(flen * sizeof(*masks), GFP_KERNEL);
if (!masks)
return -ENOMEM;
+
memset(masks, 0xff, flen * sizeof(*masks));
for (pc = 0; pc < flen; pc++) {
memvalid &= masks[pc];
switch (filter[pc].code) {
- case BPF_S_ST:
- case BPF_S_STX:
+ case BPF_ST:
+ case BPF_STX:
memvalid |= (1 << filter[pc].k);
break;
- case BPF_S_LD_MEM:
- case BPF_S_LDX_MEM:
+ case BPF_LD | BPF_MEM:
+ case BPF_LDX | BPF_MEM:
if (!(memvalid & (1 << filter[pc].k))) {
ret = -EINVAL;
goto error;
}
break;
- case BPF_S_JMP_JA:
- /* a jump must set masks on target */
+ case BPF_JMP | BPF_JA:
+ /* A jump must set masks on target */
masks[pc + 1 + filter[pc].k] &= memvalid;
memvalid = ~0;
break;
- case BPF_S_JMP_JEQ_K:
- case BPF_S_JMP_JEQ_X:
- case BPF_S_JMP_JGE_K:
- case BPF_S_JMP_JGE_X:
- case BPF_S_JMP_JGT_K:
- case BPF_S_JMP_JGT_X:
- case BPF_S_JMP_JSET_X:
- case BPF_S_JMP_JSET_K:
- /* a jump must set masks on targets */
+ case BPF_JMP | BPF_JEQ | BPF_K:
+ case BPF_JMP | BPF_JEQ | BPF_X:
+ case BPF_JMP | BPF_JGE | BPF_K:
+ case BPF_JMP | BPF_JGE | BPF_X:
+ case BPF_JMP | BPF_JGT | BPF_K:
+ case BPF_JMP | BPF_JGT | BPF_X:
+ case BPF_JMP | BPF_JSET | BPF_K:
+ case BPF_JMP | BPF_JSET | BPF_X:
+ /* A jump must set masks on targets */
masks[pc + 1 + filter[pc].jt] &= memvalid;
masks[pc + 1 + filter[pc].jf] &= memvalid;
memvalid = ~0;
@@ -1189,6 +1139,72 @@ error:
return ret;
}
+static bool chk_code_allowed(u16 code_to_probe)
+{
+ static const bool codes[] = {
+ /* 32 bit ALU operations */
+ [BPF_ALU | BPF_ADD | BPF_K] = true,
+ [BPF_ALU | BPF_ADD | BPF_X] = true,
+ [BPF_ALU | BPF_SUB | BPF_K] = true,
+ [BPF_ALU | BPF_SUB | BPF_X] = true,
+ [BPF_ALU | BPF_MUL | BPF_K] = true,
+ [BPF_ALU | BPF_MUL | BPF_X] = true,
+ [BPF_ALU | BPF_DIV | BPF_K] = true,
+ [BPF_ALU | BPF_DIV | BPF_X] = true,
+ [BPF_ALU | BPF_MOD | BPF_K] = true,
+ [BPF_ALU | BPF_MOD | BPF_X] = true,
+ [BPF_ALU | BPF_AND | BPF_K] = true,
+ [BPF_ALU | BPF_AND | BPF_X] = true,
+ [BPF_ALU | BPF_OR | BPF_K] = true,
+ [BPF_ALU | BPF_OR | BPF_X] = true,
+ [BPF_ALU | BPF_XOR | BPF_K] = true,
+ [BPF_ALU | BPF_XOR | BPF_X] = true,
+ [BPF_ALU | BPF_LSH | BPF_K] = true,
+ [BPF_ALU | BPF_LSH | BPF_X] = true,
+ [BPF_ALU | BPF_RSH | BPF_K] = true,
+ [BPF_ALU | BPF_RSH | BPF_X] = true,
+ [BPF_ALU | BPF_NEG] = true,
+ /* Load instructions */
+ [BPF_LD | BPF_W | BPF_ABS] = true,
+ [BPF_LD | BPF_H | BPF_ABS] = true,
+ [BPF_LD | BPF_B | BPF_ABS] = true,
+ [BPF_LD | BPF_W | BPF_LEN] = true,
+ [BPF_LD | BPF_W | BPF_IND] = true,
+ [BPF_LD | BPF_H | BPF_IND] = true,
+ [BPF_LD | BPF_B | BPF_IND] = true,
+ [BPF_LD | BPF_IMM] = true,
+ [BPF_LD | BPF_MEM] = true,
+ [BPF_LDX | BPF_W | BPF_LEN] = true,
+ [BPF_LDX | BPF_B | BPF_MSH] = true,
+ [BPF_LDX | BPF_IMM] = true,
+ [BPF_LDX | BPF_MEM] = true,
+ /* Store instructions */
+ [BPF_ST] = true,
+ [BPF_STX] = true,
+ /* Misc instructions */
+ [BPF_MISC | BPF_TAX] = true,
+ [BPF_MISC | BPF_TXA] = true,
+ /* Return instructions */
+ [BPF_RET | BPF_K] = true,
+ [BPF_RET | BPF_A] = true,
+ /* Jump instructions */
+ [BPF_JMP | BPF_JA] = true,
+ [BPF_JMP | BPF_JEQ | BPF_K] = true,
+ [BPF_JMP | BPF_JEQ | BPF_X] = true,
+ [BPF_JMP | BPF_JGE | BPF_K] = true,
+ [BPF_JMP | BPF_JGE | BPF_X] = true,
+ [BPF_JMP | BPF_JGT | BPF_K] = true,
+ [BPF_JMP | BPF_JGT | BPF_X] = true,
+ [BPF_JMP | BPF_JSET | BPF_K] = true,
+ [BPF_JMP | BPF_JSET | BPF_X] = true,
+ };
+
+ if (code_to_probe >= ARRAY_SIZE(codes))
+ return false;
+
+ return codes[code_to_probe];
+}
+
/**
* sk_chk_filter - verify socket filter code
* @filter: filter to verify
@@ -1205,154 +1221,76 @@ error:
*/
int sk_chk_filter(struct sock_filter *filter, unsigned int flen)
{
- /*
- * Valid instructions are initialized to non-0.
- * Invalid instructions are initialized to 0.
- */
- static const u8 codes[] = {
- [BPF_ALU|BPF_ADD|BPF_K] = BPF_S_ALU_ADD_K,
- [BPF_ALU|BPF_ADD|BPF_X] = BPF_S_ALU_ADD_X,
- [BPF_ALU|BPF_SUB|BPF_K] = BPF_S_ALU_SUB_K,
- [BPF_ALU|BPF_SUB|BPF_X] = BPF_S_ALU_SUB_X,
- [BPF_ALU|BPF_MUL|BPF_K] = BPF_S_ALU_MUL_K,
- [BPF_ALU|BPF_MUL|BPF_X] = BPF_S_ALU_MUL_X,
- [BPF_ALU|BPF_DIV|BPF_X] = BPF_S_ALU_DIV_X,
- [BPF_ALU|BPF_MOD|BPF_K] = BPF_S_ALU_MOD_K,
- [BPF_ALU|BPF_MOD|BPF_X] = BPF_S_ALU_MOD_X,
- [BPF_ALU|BPF_AND|BPF_K] = BPF_S_ALU_AND_K,
- [BPF_ALU|BPF_AND|BPF_X] = BPF_S_ALU_AND_X,
- [BPF_ALU|BPF_OR|BPF_K] = BPF_S_ALU_OR_K,
- [BPF_ALU|BPF_OR|BPF_X] = BPF_S_ALU_OR_X,
- [BPF_ALU|BPF_XOR|BPF_K] = BPF_S_ALU_XOR_K,
- [BPF_ALU|BPF_XOR|BPF_X] = BPF_S_ALU_XOR_X,
- [BPF_ALU|BPF_LSH|BPF_K] = BPF_S_ALU_LSH_K,
- [BPF_ALU|BPF_LSH|BPF_X] = BPF_S_ALU_LSH_X,
- [BPF_ALU|BPF_RSH|BPF_K] = BPF_S_ALU_RSH_K,
- [BPF_ALU|BPF_RSH|BPF_X] = BPF_S_ALU_RSH_X,
- [BPF_ALU|BPF_NEG] = BPF_S_ALU_NEG,
- [BPF_LD|BPF_W|BPF_ABS] = BPF_S_LD_W_ABS,
- [BPF_LD|BPF_H|BPF_ABS] = BPF_S_LD_H_ABS,
- [BPF_LD|BPF_B|BPF_ABS] = BPF_S_LD_B_ABS,
- [BPF_LD|BPF_W|BPF_LEN] = BPF_S_LD_W_LEN,
- [BPF_LD|BPF_W|BPF_IND] = BPF_S_LD_W_IND,
- [BPF_LD|BPF_H|BPF_IND] = BPF_S_LD_H_IND,
- [BPF_LD|BPF_B|BPF_IND] = BPF_S_LD_B_IND,
- [BPF_LD|BPF_IMM] = BPF_S_LD_IMM,
- [BPF_LDX|BPF_W|BPF_LEN] = BPF_S_LDX_W_LEN,
- [BPF_LDX|BPF_B|BPF_MSH] = BPF_S_LDX_B_MSH,
- [BPF_LDX|BPF_IMM] = BPF_S_LDX_IMM,
- [BPF_MISC|BPF_TAX] = BPF_S_MISC_TAX,
- [BPF_MISC|BPF_TXA] = BPF_S_MISC_TXA,
- [BPF_RET|BPF_K] = BPF_S_RET_K,
- [BPF_RET|BPF_A] = BPF_S_RET_A,
- [BPF_ALU|BPF_DIV|BPF_K] = BPF_S_ALU_DIV_K,
- [BPF_LD|BPF_MEM] = BPF_S_LD_MEM,
- [BPF_LDX|BPF_MEM] = BPF_S_LDX_MEM,
- [BPF_ST] = BPF_S_ST,
- [BPF_STX] = BPF_S_STX,
- [BPF_JMP|BPF_JA] = BPF_S_JMP_JA,
- [BPF_JMP|BPF_JEQ|BPF_K] = BPF_S_JMP_JEQ_K,
- [BPF_JMP|BPF_JEQ|BPF_X] = BPF_S_JMP_JEQ_X,
- [BPF_JMP|BPF_JGE|BPF_K] = BPF_S_JMP_JGE_K,
- [BPF_JMP|BPF_JGE|BPF_X] = BPF_S_JMP_JGE_X,
- [BPF_JMP|BPF_JGT|BPF_K] = BPF_S_JMP_JGT_K,
- [BPF_JMP|BPF_JGT|BPF_X] = BPF_S_JMP_JGT_X,
- [BPF_JMP|BPF_JSET|BPF_K] = BPF_S_JMP_JSET_K,
- [BPF_JMP|BPF_JSET|BPF_X] = BPF_S_JMP_JSET_X,
- };
- int pc;
bool anc_found;
+ int pc;
if (flen == 0 || flen > BPF_MAXINSNS)
return -EINVAL;
- /* check the filter code now */
+ /* Check the filter code now */
for (pc = 0; pc < flen; pc++) {
struct sock_filter *ftest = &filter[pc];
- u16 code = ftest->code;
- if (code >= ARRAY_SIZE(codes))
- return -EINVAL;
- code = codes[code];
- if (!code)
+ /* May we actually operate on this code? */
+ if (!chk_code_allowed(ftest->code))
return -EINVAL;
+
/* Some instructions need special checks */
- switch (code) {
- case BPF_S_ALU_DIV_K:
- case BPF_S_ALU_MOD_K:
- /* check for division by zero */
+ switch (ftest->code) {
+ case BPF_ALU | BPF_DIV | BPF_K:
+ case BPF_ALU | BPF_MOD | BPF_K:
+ /* Check for division by zero */
if (ftest->k == 0)
return -EINVAL;
break;
- case BPF_S_LD_MEM:
- case BPF_S_LDX_MEM:
- case BPF_S_ST:
- case BPF_S_STX:
- /* check for invalid memory addresses */
+ case BPF_LD | BPF_MEM:
+ case BPF_LDX | BPF_MEM:
+ case BPF_ST:
+ case BPF_STX:
+ /* Check for invalid memory addresses */
if (ftest->k >= BPF_MEMWORDS)
return -EINVAL;
break;
- case BPF_S_JMP_JA:
- /*
- * Note, the large ftest->k might cause loops.
+ case BPF_JMP | BPF_JA:
+ /* Note, the large ftest->k might cause loops.
* Compare this with conditional jumps below,
* where offsets are limited. --ANK (981016)
*/
- if (ftest->k >= (unsigned int)(flen-pc-1))
+ if (ftest->k >= (unsigned int)(flen - pc - 1))
return -EINVAL;
break;
- case BPF_S_JMP_JEQ_K:
- case BPF_S_JMP_JEQ_X:
- case BPF_S_JMP_JGE_K:
- case BPF_S_JMP_JGE_X:
- case BPF_S_JMP_JGT_K:
- case BPF_S_JMP_JGT_X:
- case BPF_S_JMP_JSET_X:
- case BPF_S_JMP_JSET_K:
- /* for conditionals both must be safe */
+ case BPF_JMP | BPF_JEQ | BPF_K:
+ case BPF_JMP | BPF_JEQ | BPF_X:
+ case BPF_JMP | BPF_JGE | BPF_K:
+ case BPF_JMP | BPF_JGE | BPF_X:
+ case BPF_JMP | BPF_JGT | BPF_K:
+ case BPF_JMP | BPF_JGT | BPF_X:
+ case BPF_JMP | BPF_JSET | BPF_K:
+ case BPF_JMP | BPF_JSET | BPF_X:
+ /* Both conditionals must be safe */
if (pc + ftest->jt + 1 >= flen ||
pc + ftest->jf + 1 >= flen)
return -EINVAL;
break;
- case BPF_S_LD_W_ABS:
- case BPF_S_LD_H_ABS:
- case BPF_S_LD_B_ABS:
+ case BPF_LD | BPF_W | BPF_ABS:
+ case BPF_LD | BPF_H | BPF_ABS:
+ case BPF_LD | BPF_B | BPF_ABS:
anc_found = false;
-#define ANCILLARY(CODE) case SKF_AD_OFF + SKF_AD_##CODE: \
- code = BPF_S_ANC_##CODE; \
- anc_found = true; \
- break
- switch (ftest->k) {
- ANCILLARY(PROTOCOL);
- ANCILLARY(PKTTYPE);
- ANCILLARY(IFINDEX);
- ANCILLARY(NLATTR);
- ANCILLARY(NLATTR_NEST);
- ANCILLARY(MARK);
- ANCILLARY(QUEUE);
- ANCILLARY(HATYPE);
- ANCILLARY(RXHASH);
- ANCILLARY(CPU);
- ANCILLARY(ALU_XOR_X);
- ANCILLARY(VLAN_TAG);
- ANCILLARY(VLAN_TAG_PRESENT);
- ANCILLARY(PAY_OFFSET);
- ANCILLARY(RANDOM);
- }
-
- /* ancillary operation unknown or unsupported */
+ if (bpf_anc_helper(ftest) & BPF_ANC)
+ anc_found = true;
+ /* Ancillary operation unknown or unsupported */
if (anc_found == false && ftest->k >= SKF_AD_OFF)
return -EINVAL;
}
- ftest->code = code;
}
- /* last instruction must be a RET code */
+ /* Last instruction must be a RET code */
switch (filter[flen - 1].code) {
- case BPF_S_RET_K:
- case BPF_S_RET_A:
+ case BPF_RET | BPF_K:
+ case BPF_RET | BPF_A:
return check_load_and_stores(filter, flen);
}
+
return -EINVAL;
}
EXPORT_SYMBOL(sk_chk_filter);
@@ -1397,7 +1335,7 @@ static void sk_filter_release_rcu(struct rcu_head *rcu)
struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu);
sk_release_orig_filter(fp);
- bpf_jit_free(fp);
+ sk_filter_free(fp);
}
/**
@@ -1452,7 +1390,7 @@ static struct sk_filter *__sk_migrate_filter(struct sk_filter *fp,
{
struct sock_filter *old_prog;
struct sk_filter *old_fp;
- int i, err, new_len, old_len = fp->len;
+ int err, new_len, old_len = fp->len;
/* We are free to overwrite insns et al right here as it
* won't be used at this point in time anymore internally
@@ -1462,13 +1400,6 @@ static struct sk_filter *__sk_migrate_filter(struct sk_filter *fp,
BUILD_BUG_ON(sizeof(struct sock_filter) !=
sizeof(struct sock_filter_int));
- /* For now, we need to unfiddle BPF_S_* identifiers in place.
- * This can sooner or later on be subject to removal, e.g. when
- * JITs have been converted.
- */
- for (i = 0; i < fp->len; i++)
- sk_decode_filter(&fp->insns[i], &fp->insns[i]);
-
/* Conversion cannot happen on overlapping memory areas,
* so we need to keep the user BPF around until the 2nd
* pass. At this time, the user BPF is stored in fp->insns.
@@ -1497,7 +1428,6 @@ static struct sk_filter *__sk_migrate_filter(struct sk_filter *fp,
goto out_err_free;
}
- fp->bpf_func = sk_run_filter_int_skb;
fp->len = new_len;
/* 2nd pass: remap sock_filter insns into sock_filter_int insns. */
@@ -1510,6 +1440,8 @@ static struct sk_filter *__sk_migrate_filter(struct sk_filter *fp,
*/
goto out_err_free;
+ sk_filter_select_runtime(fp);
+
kfree(old_prog);
return fp;
@@ -1524,6 +1456,33 @@ out_err:
return ERR_PTR(err);
}
+void __weak bpf_int_jit_compile(struct sk_filter *prog)
+{
+}
+
+/**
+ * sk_filter_select_runtime - select execution runtime for BPF program
+ * @fp: sk_filter populated with internal BPF program
+ *
+ * try to JIT internal BPF program, if JIT is not available select interpreter
+ * BPF program will be executed via SK_RUN_FILTER() macro
+ */
+void sk_filter_select_runtime(struct sk_filter *fp)
+{
+ fp->bpf_func = (void *) __sk_run_filter;
+
+ /* Probe if internal BPF can be JITed */
+ bpf_int_jit_compile(fp);
+}
+EXPORT_SYMBOL_GPL(sk_filter_select_runtime);
+
+/* free internal BPF program */
+void sk_filter_free(struct sk_filter *fp)
+{
+ bpf_jit_free(fp);
+}
+EXPORT_SYMBOL_GPL(sk_filter_free);
+
static struct sk_filter *__sk_prepare_filter(struct sk_filter *fp,
struct sock *sk)
{
@@ -1561,7 +1520,7 @@ static struct sk_filter *__sk_prepare_filter(struct sk_filter *fp,
* a negative errno code is returned. On success the return is zero.
*/
int sk_unattached_filter_create(struct sk_filter **pfp,
- struct sock_fprog *fprog)
+ struct sock_fprog_kern *fprog)
{
unsigned int fsize = sk_filter_proglen(fprog);
struct sk_filter *fp;
@@ -1682,84 +1641,6 @@ int sk_detach_filter(struct sock *sk)
}
EXPORT_SYMBOL_GPL(sk_detach_filter);
-void sk_decode_filter(struct sock_filter *filt, struct sock_filter *to)
-{
- static const u16 decodes[] = {
- [BPF_S_ALU_ADD_K] = BPF_ALU|BPF_ADD|BPF_K,
- [BPF_S_ALU_ADD_X] = BPF_ALU|BPF_ADD|BPF_X,
- [BPF_S_ALU_SUB_K] = BPF_ALU|BPF_SUB|BPF_K,
- [BPF_S_ALU_SUB_X] = BPF_ALU|BPF_SUB|BPF_X,
- [BPF_S_ALU_MUL_K] = BPF_ALU|BPF_MUL|BPF_K,
- [BPF_S_ALU_MUL_X] = BPF_ALU|BPF_MUL|BPF_X,
- [BPF_S_ALU_DIV_X] = BPF_ALU|BPF_DIV|BPF_X,
- [BPF_S_ALU_MOD_K] = BPF_ALU|BPF_MOD|BPF_K,
- [BPF_S_ALU_MOD_X] = BPF_ALU|BPF_MOD|BPF_X,
- [BPF_S_ALU_AND_K] = BPF_ALU|BPF_AND|BPF_K,
- [BPF_S_ALU_AND_X] = BPF_ALU|BPF_AND|BPF_X,
- [BPF_S_ALU_OR_K] = BPF_ALU|BPF_OR|BPF_K,
- [BPF_S_ALU_OR_X] = BPF_ALU|BPF_OR|BPF_X,
- [BPF_S_ALU_XOR_K] = BPF_ALU|BPF_XOR|BPF_K,
- [BPF_S_ALU_XOR_X] = BPF_ALU|BPF_XOR|BPF_X,
- [BPF_S_ALU_LSH_K] = BPF_ALU|BPF_LSH|BPF_K,
- [BPF_S_ALU_LSH_X] = BPF_ALU|BPF_LSH|BPF_X,
- [BPF_S_ALU_RSH_K] = BPF_ALU|BPF_RSH|BPF_K,
- [BPF_S_ALU_RSH_X] = BPF_ALU|BPF_RSH|BPF_X,
- [BPF_S_ALU_NEG] = BPF_ALU|BPF_NEG,
- [BPF_S_LD_W_ABS] = BPF_LD|BPF_W|BPF_ABS,
- [BPF_S_LD_H_ABS] = BPF_LD|BPF_H|BPF_ABS,
- [BPF_S_LD_B_ABS] = BPF_LD|BPF_B|BPF_ABS,
- [BPF_S_ANC_PROTOCOL] = BPF_LD|BPF_B|BPF_ABS,
- [BPF_S_ANC_PKTTYPE] = BPF_LD|BPF_B|BPF_ABS,
- [BPF_S_ANC_IFINDEX] = BPF_LD|BPF_B|BPF_ABS,
- [BPF_S_ANC_NLATTR] = BPF_LD|BPF_B|BPF_ABS,
- [BPF_S_ANC_NLATTR_NEST] = BPF_LD|BPF_B|BPF_ABS,
- [BPF_S_ANC_MARK] = BPF_LD|BPF_B|BPF_ABS,
- [BPF_S_ANC_QUEUE] = BPF_LD|BPF_B|BPF_ABS,
- [BPF_S_ANC_HATYPE] = BPF_LD|BPF_B|BPF_ABS,
- [BPF_S_ANC_RXHASH] = BPF_LD|BPF_B|BPF_ABS,
- [BPF_S_ANC_CPU] = BPF_LD|BPF_B|BPF_ABS,
- [BPF_S_ANC_ALU_XOR_X] = BPF_LD|BPF_B|BPF_ABS,
- [BPF_S_ANC_VLAN_TAG] = BPF_LD|BPF_B|BPF_ABS,
- [BPF_S_ANC_VLAN_TAG_PRESENT] = BPF_LD|BPF_B|BPF_ABS,
- [BPF_S_ANC_PAY_OFFSET] = BPF_LD|BPF_B|BPF_ABS,
- [BPF_S_ANC_RANDOM] = BPF_LD|BPF_B|BPF_ABS,
- [BPF_S_LD_W_LEN] = BPF_LD|BPF_W|BPF_LEN,
- [BPF_S_LD_W_IND] = BPF_LD|BPF_W|BPF_IND,
- [BPF_S_LD_H_IND] = BPF_LD|BPF_H|BPF_IND,
- [BPF_S_LD_B_IND] = BPF_LD|BPF_B|BPF_IND,
- [BPF_S_LD_IMM] = BPF_LD|BPF_IMM,
- [BPF_S_LDX_W_LEN] = BPF_LDX|BPF_W|BPF_LEN,
- [BPF_S_LDX_B_MSH] = BPF_LDX|BPF_B|BPF_MSH,
- [BPF_S_LDX_IMM] = BPF_LDX|BPF_IMM,
- [BPF_S_MISC_TAX] = BPF_MISC|BPF_TAX,
- [BPF_S_MISC_TXA] = BPF_MISC|BPF_TXA,
- [BPF_S_RET_K] = BPF_RET|BPF_K,
- [BPF_S_RET_A] = BPF_RET|BPF_A,
- [BPF_S_ALU_DIV_K] = BPF_ALU|BPF_DIV|BPF_K,
- [BPF_S_LD_MEM] = BPF_LD|BPF_MEM,
- [BPF_S_LDX_MEM] = BPF_LDX|BPF_MEM,
- [BPF_S_ST] = BPF_ST,
- [BPF_S_STX] = BPF_STX,
- [BPF_S_JMP_JA] = BPF_JMP|BPF_JA,
- [BPF_S_JMP_JEQ_K] = BPF_JMP|BPF_JEQ|BPF_K,
- [BPF_S_JMP_JEQ_X] = BPF_JMP|BPF_JEQ|BPF_X,
- [BPF_S_JMP_JGE_K] = BPF_JMP|BPF_JGE|BPF_K,
- [BPF_S_JMP_JGE_X] = BPF_JMP|BPF_JGE|BPF_X,
- [BPF_S_JMP_JGT_K] = BPF_JMP|BPF_JGT|BPF_K,
- [BPF_S_JMP_JGT_X] = BPF_JMP|BPF_JGT|BPF_X,
- [BPF_S_JMP_JSET_K] = BPF_JMP|BPF_JSET|BPF_K,
- [BPF_S_JMP_JSET_X] = BPF_JMP|BPF_JSET|BPF_X,
- };
- u16 code;
-
- code = filt->code;
-
- to->code = decodes[code];
- to->jt = filt->jt;
- to->jf = filt->jf;
- to->k = filt->k;
-}
-
int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf,
unsigned int len)
{
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 8f8a96e..32d872e 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1248,8 +1248,8 @@ void __neigh_set_probe_once(struct neighbour *neigh)
neigh->updated = jiffies;
if (!(neigh->nud_state & NUD_FAILED))
return;
- neigh->nud_state = NUD_PROBE;
- atomic_set(&neigh->probes, NEIGH_VAR(neigh->parms, UCAST_PROBES));
+ neigh->nud_state = NUD_INCOMPLETE;
+ atomic_set(&neigh->probes, neigh_max_probes(neigh));
neigh_add_timer(neigh,
jiffies + NEIGH_VAR(neigh->parms, RETRANS_TIME));
}
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 05e949d..85b6269 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -24,7 +24,7 @@
static LIST_HEAD(pernet_list);
static struct list_head *first_device = &pernet_list;
-static DEFINE_MUTEX(net_mutex);
+DEFINE_MUTEX(net_mutex);
LIST_HEAD(net_namespace_list);
EXPORT_SYMBOL_GPL(net_namespace_list);
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 0304f98..fc17a9d 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -573,7 +573,7 @@ static int pktgen_if_show(struct seq_file *seq, void *v)
is_zero_ether_addr(pkt_dev->src_mac) ?
pkt_dev->odev->dev_addr : pkt_dev->src_mac);
- seq_printf(seq, "dst_mac: ");
+ seq_puts(seq, "dst_mac: ");
seq_printf(seq, "%pM\n", pkt_dev->dst_mac);
seq_printf(seq,
@@ -588,7 +588,7 @@ static int pktgen_if_show(struct seq_file *seq, void *v)
if (pkt_dev->nr_labels) {
unsigned int i;
- seq_printf(seq, " mpls: ");
+ seq_puts(seq, " mpls: ");
for (i = 0; i < pkt_dev->nr_labels; i++)
seq_printf(seq, "%08x%s", ntohl(pkt_dev->labels[i]),
i == pkt_dev->nr_labels-1 ? "\n" : ", ");
@@ -613,67 +613,67 @@ static int pktgen_if_show(struct seq_file *seq, void *v)
if (pkt_dev->node >= 0)
seq_printf(seq, " node: %d\n", pkt_dev->node);
- seq_printf(seq, " Flags: ");
+ seq_puts(seq, " Flags: ");
if (pkt_dev->flags & F_IPV6)
- seq_printf(seq, "IPV6 ");
+ seq_puts(seq, "IPV6 ");
if (pkt_dev->flags & F_IPSRC_RND)
- seq_printf(seq, "IPSRC_RND ");
+ seq_puts(seq, "IPSRC_RND ");
if (pkt_dev->flags & F_IPDST_RND)
- seq_printf(seq, "IPDST_RND ");
+ seq_puts(seq, "IPDST_RND ");
if (pkt_dev->flags & F_TXSIZE_RND)
- seq_printf(seq, "TXSIZE_RND ");
+ seq_puts(seq, "TXSIZE_RND ");
if (pkt_dev->flags & F_UDPSRC_RND)
- seq_printf(seq, "UDPSRC_RND ");
+ seq_puts(seq, "UDPSRC_RND ");
if (pkt_dev->flags & F_UDPDST_RND)
- seq_printf(seq, "UDPDST_RND ");
+ seq_puts(seq, "UDPDST_RND ");
if (pkt_dev->flags & F_UDPCSUM)
- seq_printf(seq, "UDPCSUM ");
+ seq_puts(seq, "UDPCSUM ");
if (pkt_dev->flags & F_MPLS_RND)
- seq_printf(seq, "MPLS_RND ");
+ seq_puts(seq, "MPLS_RND ");
if (pkt_dev->flags & F_QUEUE_MAP_RND)
- seq_printf(seq, "QUEUE_MAP_RND ");
+ seq_puts(seq, "QUEUE_MAP_RND ");
if (pkt_dev->flags & F_QUEUE_MAP_CPU)
- seq_printf(seq, "QUEUE_MAP_CPU ");
+ seq_puts(seq, "QUEUE_MAP_CPU ");
if (pkt_dev->cflows) {
if (pkt_dev->flags & F_FLOW_SEQ)
- seq_printf(seq, "FLOW_SEQ "); /*in sequence flows*/
+ seq_puts(seq, "FLOW_SEQ "); /*in sequence flows*/
else
- seq_printf(seq, "FLOW_RND ");
+ seq_puts(seq, "FLOW_RND ");
}
#ifdef CONFIG_XFRM
if (pkt_dev->flags & F_IPSEC_ON) {
- seq_printf(seq, "IPSEC ");
+ seq_puts(seq, "IPSEC ");
if (pkt_dev->spi)
seq_printf(seq, "spi:%u", pkt_dev->spi);
}
#endif
if (pkt_dev->flags & F_MACSRC_RND)
- seq_printf(seq, "MACSRC_RND ");
+ seq_puts(seq, "MACSRC_RND ");
if (pkt_dev->flags & F_MACDST_RND)
- seq_printf(seq, "MACDST_RND ");
+ seq_puts(seq, "MACDST_RND ");
if (pkt_dev->flags & F_VID_RND)
- seq_printf(seq, "VID_RND ");
+ seq_puts(seq, "VID_RND ");
if (pkt_dev->flags & F_SVID_RND)
- seq_printf(seq, "SVID_RND ");
+ seq_puts(seq, "SVID_RND ");
if (pkt_dev->flags & F_NODE)
- seq_printf(seq, "NODE_ALLOC ");
+ seq_puts(seq, "NODE_ALLOC ");
seq_puts(seq, "\n");
@@ -716,7 +716,7 @@ static int pktgen_if_show(struct seq_file *seq, void *v)
if (pkt_dev->result[0])
seq_printf(seq, "Result: %s\n", pkt_dev->result);
else
- seq_printf(seq, "Result: Idle\n");
+ seq_puts(seq, "Result: Idle\n");
return 0;
}
@@ -1735,14 +1735,14 @@ static int pktgen_thread_show(struct seq_file *seq, void *v)
BUG_ON(!t);
- seq_printf(seq, "Running: ");
+ seq_puts(seq, "Running: ");
if_lock(t);
list_for_each_entry(pkt_dev, &t->if_list, list)
if (pkt_dev->running)
seq_printf(seq, "%s ", pkt_dev->odevname);
- seq_printf(seq, "\nStopped: ");
+ seq_puts(seq, "\nStopped: ");
list_for_each_entry(pkt_dev, &t->if_list, list)
if (!pkt_dev->running)
@@ -1751,7 +1751,7 @@ static int pktgen_thread_show(struct seq_file *seq, void *v)
if (t->result[0])
seq_printf(seq, "\nResult: %s\n", t->result);
else
- seq_printf(seq, "\nResult: NA\n");
+ seq_puts(seq, "\nResult: NA\n");
if_unlock(t);
diff --git a/net/core/ptp_classifier.c b/net/core/ptp_classifier.c
index 37d8615..d3027a7 100644
--- a/net/core/ptp_classifier.c
+++ b/net/core/ptp_classifier.c
@@ -133,7 +133,7 @@ void __init ptp_classifier_init(void)
{ 0x16, 0, 0, 0x00000000 },
{ 0x06, 0, 0, 0x00000000 },
};
- struct sock_fprog ptp_prog = {
+ struct sock_fprog_kern ptp_prog = {
.len = ARRAY_SIZE(ptp_filter), .filter = ptp_filter,
};
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 9837beb..f31268d 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -353,15 +353,46 @@ void __rtnl_link_unregister(struct rtnl_link_ops *ops)
}
EXPORT_SYMBOL_GPL(__rtnl_link_unregister);
+/* Return with the rtnl_lock held when there are no network
+ * devices unregistering in any network namespace.
+ */
+static void rtnl_lock_unregistering_all(void)
+{
+ struct net *net;
+ bool unregistering;
+ DEFINE_WAIT(wait);
+
+ for (;;) {
+ prepare_to_wait(&netdev_unregistering_wq, &wait,
+ TASK_UNINTERRUPTIBLE);
+ unregistering = false;
+ rtnl_lock();
+ for_each_net(net) {
+ if (net->dev_unreg_count > 0) {
+ unregistering = true;
+ break;
+ }
+ }
+ if (!unregistering)
+ break;
+ __rtnl_unlock();
+ schedule();
+ }
+ finish_wait(&netdev_unregistering_wq, &wait);
+}
+
/**
* rtnl_link_unregister - Unregister rtnl_link_ops from rtnetlink.
* @ops: struct rtnl_link_ops * to unregister
*/
void rtnl_link_unregister(struct rtnl_link_ops *ops)
{
- rtnl_lock();
+ /* Close the race with cleanup_net() */
+ mutex_lock(&net_mutex);
+ rtnl_lock_unregistering_all();
__rtnl_link_unregister(ops);
rtnl_unlock();
+ mutex_unlock(&net_mutex);
}
EXPORT_SYMBOL_GPL(rtnl_link_unregister);
@@ -767,8 +798,8 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev,
size += num_vfs *
(nla_total_size(sizeof(struct ifla_vf_mac)) +
nla_total_size(sizeof(struct ifla_vf_vlan)) +
- nla_total_size(sizeof(struct ifla_vf_tx_rate)) +
- nla_total_size(sizeof(struct ifla_vf_spoofchk)));
+ nla_total_size(sizeof(struct ifla_vf_spoofchk)) +
+ nla_total_size(sizeof(struct ifla_vf_rate)));
return size;
} else
return 0;
@@ -1034,6 +1065,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
struct ifla_vf_info ivi;
struct ifla_vf_mac vf_mac;
struct ifla_vf_vlan vf_vlan;
+ struct ifla_vf_rate vf_rate;
struct ifla_vf_tx_rate vf_tx_rate;
struct ifla_vf_spoofchk vf_spoofchk;
struct ifla_vf_link_state vf_linkstate;
@@ -1054,6 +1086,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
break;
vf_mac.vf =
vf_vlan.vf =
+ vf_rate.vf =
vf_tx_rate.vf =
vf_spoofchk.vf =
vf_linkstate.vf = ivi.vf;
@@ -1061,7 +1094,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
memcpy(vf_mac.mac, ivi.mac, sizeof(ivi.mac));
vf_vlan.vlan = ivi.vlan;
vf_vlan.qos = ivi.qos;
- vf_tx_rate.rate = ivi.tx_rate;
+ vf_tx_rate.rate = ivi.max_tx_rate;
+ vf_rate.min_tx_rate = ivi.min_tx_rate;
+ vf_rate.max_tx_rate = ivi.max_tx_rate;
vf_spoofchk.setting = ivi.spoofchk;
vf_linkstate.link_state = ivi.linkstate;
vf = nla_nest_start(skb, IFLA_VF_INFO);
@@ -1071,6 +1106,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
}
if (nla_put(skb, IFLA_VF_MAC, sizeof(vf_mac), &vf_mac) ||
nla_put(skb, IFLA_VF_VLAN, sizeof(vf_vlan), &vf_vlan) ||
+ nla_put(skb, IFLA_VF_RATE, sizeof(vf_rate),
+ &vf_rate) ||
nla_put(skb, IFLA_VF_TX_RATE, sizeof(vf_tx_rate),
&vf_tx_rate) ||
nla_put(skb, IFLA_VF_SPOOFCHK, sizeof(vf_spoofchk),
@@ -1177,6 +1214,8 @@ static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = {
.len = sizeof(struct ifla_vf_tx_rate) },
[IFLA_VF_SPOOFCHK] = { .type = NLA_BINARY,
.len = sizeof(struct ifla_vf_spoofchk) },
+ [IFLA_VF_RATE] = { .type = NLA_BINARY,
+ .len = sizeof(struct ifla_vf_rate) },
};
static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = {
@@ -1336,11 +1375,29 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr *attr)
}
case IFLA_VF_TX_RATE: {
struct ifla_vf_tx_rate *ivt;
+ struct ifla_vf_info ivf;
+ ivt = nla_data(vf);
+ err = -EOPNOTSUPP;
+ if (ops->ndo_get_vf_config)
+ err = ops->ndo_get_vf_config(dev, ivt->vf,
+ &ivf);
+ if (err)
+ break;
+ err = -EOPNOTSUPP;
+ if (ops->ndo_set_vf_rate)
+ err = ops->ndo_set_vf_rate(dev, ivt->vf,
+ ivf.min_tx_rate,
+ ivt->rate);
+ break;
+ }
+ case IFLA_VF_RATE: {
+ struct ifla_vf_rate *ivt;
ivt = nla_data(vf);
err = -EOPNOTSUPP;
- if (ops->ndo_set_vf_tx_rate)
- err = ops->ndo_set_vf_tx_rate(dev, ivt->vf,
- ivt->rate);
+ if (ops->ndo_set_vf_rate)
+ err = ops->ndo_set_vf_rate(dev, ivt->vf,
+ ivt->min_tx_rate,
+ ivt->max_tx_rate);
break;
}
case IFLA_VF_SPOOFCHK: {
diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c
index 897da56..ba71212 100644
--- a/net/core/secure_seq.c
+++ b/net/core/secure_seq.c
@@ -85,31 +85,6 @@ EXPORT_SYMBOL(secure_ipv6_port_ephemeral);
#endif
#ifdef CONFIG_INET
-__u32 secure_ip_id(__be32 daddr)
-{
- u32 hash[MD5_DIGEST_WORDS];
-
- net_secret_init();
- hash[0] = (__force __u32) daddr;
- hash[1] = net_secret[13];
- hash[2] = net_secret[14];
- hash[3] = net_secret[15];
-
- md5_transform(hash, net_secret);
-
- return hash[0];
-}
-
-__u32 secure_ipv6_id(const __be32 daddr[4])
-{
- __u32 hash[4];
-
- net_secret_init();
- memcpy(hash, daddr, 16);
- md5_transform(hash, net_secret);
-
- return hash[0];
-}
__u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr,
__be16 sport, __be16 dport)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 3d74530..3f6c7e8 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3076,7 +3076,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
if (unlikely(p->len + len >= 65536))
return -E2BIG;
- lp = NAPI_GRO_CB(p)->last ?: p;
+ lp = NAPI_GRO_CB(p)->last;
pinfo = skb_shinfo(lp);
if (headlen <= offset) {
@@ -3192,7 +3192,7 @@ merge:
__skb_pull(skb, offset);
- if (!NAPI_GRO_CB(p)->last)
+ if (NAPI_GRO_CB(p)->last == p)
skb_shinfo(p)->frag_list = skb;
else
NAPI_GRO_CB(p)->last->next = skb;
diff --git a/net/core/sock.c b/net/core/sock.c
index 664ee42..026e01f 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -784,7 +784,7 @@ set_rcvbuf:
break;
case SO_NO_CHECK:
- sk->sk_no_check = valbool;
+ sk->sk_no_check_tx = valbool;
break;
case SO_PRIORITY:
@@ -1064,7 +1064,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
break;
case SO_NO_CHECK:
- v.val = sk->sk_no_check;
+ v.val = sk->sk_no_check_tx;
break;
case SO_PRIORITY:
diff --git a/net/core/tso.c b/net/core/tso.c
new file mode 100644
index 0000000..8c3203c
--- /dev/null
+++ b/net/core/tso.c
@@ -0,0 +1,77 @@
+#include <linux/export.h>
+#include <net/ip.h>
+#include <net/tso.h>
+
+/* Calculate expected number of TX descriptors */
+int tso_count_descs(struct sk_buff *skb)
+{
+ /* The Marvell Way */
+ return skb_shinfo(skb)->gso_segs * 2 + skb_shinfo(skb)->nr_frags;
+}
+EXPORT_SYMBOL(tso_count_descs);
+
+void tso_build_hdr(struct sk_buff *skb, char *hdr, struct tso_t *tso,
+ int size, bool is_last)
+{
+ struct iphdr *iph;
+ struct tcphdr *tcph;
+ int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
+ int mac_hdr_len = skb_network_offset(skb);
+
+ memcpy(hdr, skb->data, hdr_len);
+ iph = (struct iphdr *)(hdr + mac_hdr_len);
+ iph->id = htons(tso->ip_id);
+ iph->tot_len = htons(size + hdr_len - mac_hdr_len);
+ tcph = (struct tcphdr *)(hdr + skb_transport_offset(skb));
+ tcph->seq = htonl(tso->tcp_seq);
+ tso->ip_id++;
+
+ if (!is_last) {
+ /* Clear all special flags for not last packet */
+ tcph->psh = 0;
+ tcph->fin = 0;
+ tcph->rst = 0;
+ }
+}
+EXPORT_SYMBOL(tso_build_hdr);
+
+void tso_build_data(struct sk_buff *skb, struct tso_t *tso, int size)
+{
+ tso->tcp_seq += size;
+ tso->size -= size;
+ tso->data += size;
+
+ if ((tso->size == 0) &&
+ (tso->next_frag_idx < skb_shinfo(skb)->nr_frags)) {
+ skb_frag_t *frag = &skb_shinfo(skb)->frags[tso->next_frag_idx];
+
+ /* Move to next segment */
+ tso->size = frag->size;
+ tso->data = page_address(frag->page.p) + frag->page_offset;
+ tso->next_frag_idx++;
+ }
+}
+EXPORT_SYMBOL(tso_build_data);
+
+void tso_start(struct sk_buff *skb, struct tso_t *tso)
+{
+ int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
+
+ tso->ip_id = ntohs(ip_hdr(skb)->id);
+ tso->tcp_seq = ntohl(tcp_hdr(skb)->seq);
+ tso->next_frag_idx = 0;
+
+ /* Build first data */
+ tso->size = skb_headlen(skb) - hdr_len;
+ tso->data = skb->data + hdr_len;
+ if ((tso->size == 0) &&
+ (tso->next_frag_idx < skb_shinfo(skb)->nr_frags)) {
+ skb_frag_t *frag = &skb_shinfo(skb)->frags[tso->next_frag_idx];
+
+ /* Move to next segment */
+ tso->size = frag->size;
+ tso->data = page_address(frag->page.p) + frag->page_offset;
+ tso->next_frag_idx++;
+ }
+}
+EXPORT_SYMBOL(tso_start);
diff --git a/net/core/utils.c b/net/core/utils.c
index 2f737bf..eed3433 100644
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -348,8 +348,8 @@ static void __net_random_once_deferred(struct work_struct *w)
{
struct __net_random_once_work *work =
container_of(w, struct __net_random_once_work, work);
- if (!static_key_enabled(work->key))
- static_key_slow_inc(work->key);
+ BUG_ON(!static_key_enabled(work->key));
+ static_key_slow_dec(work->key);
kfree(work);
}
@@ -367,7 +367,7 @@ static void __net_random_once_disable_jump(struct static_key *key)
}
bool __net_get_random_once(void *buf, int nbytes, bool *done,
- struct static_key *done_key)
+ struct static_key *once_key)
{
static DEFINE_SPINLOCK(lock);
unsigned long flags;
@@ -382,7 +382,7 @@ bool __net_get_random_once(void *buf, int nbytes, bool *done,
*done = true;
spin_unlock_irqrestore(&lock, flags);
- __net_random_once_disable_jump(done_key);
+ __net_random_once_disable_jump(once_key);
return true;
}
OpenPOWER on IntegriCloud