diff options
author | Jakub Kicinski <kuba@kernel.org> | 2025-03-03 17:16:36 -0800 |
---|---|---|
committer | Jakub Kicinski <kuba@kernel.org> | 2025-03-03 17:16:36 -0800 |
commit | cd170ca993164db9ebfd2ba332802619d737e0e3 (patch) | |
tree | bc7ebde7bfb68c09ac86dc6de1a44cb448afec90 /net | |
parent | b84c5239979f961a51c85441d6642f6256688dd8 (diff) | |
parent | 52f83c0b5f857dbe24f66fc9a7f035523e9ffbc9 (diff) |
Merge branch 'add-sock_kmemdup-helper'
Geliang Tang says:
====================
add sock_kmemdup helper
While developing MPTCP BPF path manager [1], I found it's useful to
add a new sock_kmemdup() helper.
My use case is this:
In mptcp_userspace_pm_append_new_local_addr() function (see patch 3
in this patchset), it uses sock_kmalloc() to allocate an address
entry "e", then immediately duplicate the input "entry" to it:
'''
e = sock_kmalloc(sk, sizeof(*e), GFP_ATOMIC);
if (!e) {
ret = -ENOMEM;
goto append_err;
}
*e = *entry;
'''
When I implemented MPTCP BPF path manager, I needed to implement a
code similar to this in BPF.
The kfunc sock_kmalloc() can be easily invoked in BPF to allocate
an entry "e", but the code "*e = *entry;" that assigns "entry" to
"e" is not easy to implemented.
I had to implement such a "copy entry" helper in BPF:
'''
static void mptcp_pm_copy_addr(struct mptcp_addr_info *dst,
struct mptcp_addr_info *src)
{
dst->id = src->id;
dst->family = src->family;
dst->port = src->port;
if (src->family == AF_INET) {
dst->addr.s_addr = src->addr.s_addr;
} else if (src->family == AF_INET6) {
dst->addr6.s6_addr32[0] = src->addr6.s6_addr32[0];
dst->addr6.s6_addr32[1] = src->addr6.s6_addr32[1];
dst->addr6.s6_addr32[2] = src->addr6.s6_addr32[2];
dst->addr6.s6_addr32[3] = src->addr6.s6_addr32[3];
}
}
static void mptcp_pm_copy_entry(struct mptcp_pm_addr_entry *dst,
struct mptcp_pm_addr_entry *src)
{
mptcp_pm_copy_addr(&dst->addr, &src->addr);
dst->flags = src->flags;
dst->ifindex = src->ifindex;
}
'''
And add "write permission" for BPF to each field of mptcp_pm_addr_entry:
'''
@@ static int bpf_mptcp_pm_btf_struct_access(struct bpf_verifier_log *log,
case offsetof(struct mptcp_pm_addr_entry, addr.port):
end = offsetofend(struct mptcp_pm_addr_entry, addr.port);
break;
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
case offsetof(struct mptcp_pm_addr_entry, addr.addr6.s6_addr32[0]):
end = offsetofend(struct mptcp_pm_addr_entry, addr.addr6.s6_addr32[0]);
break;
case offsetof(struct mptcp_pm_addr_entry, addr.addr6.s6_addr32[1]):
end = offsetofend(struct mptcp_pm_addr_entry, addr.addr6.s6_addr32[1]);
break;
case offsetof(struct mptcp_pm_addr_entry, addr.addr6.s6_addr32[2]):
end = offsetofend(struct mptcp_pm_addr_entry, addr.addr6.s6_addr32[2]);
break;
case offsetof(struct mptcp_pm_addr_entry, addr.addr6.s6_addr32[3]):
end = offsetofend(struct mptcp_pm_addr_entry, addr.addr6.s6_addr32[3]);
break;
#else
case offsetof(struct mptcp_pm_addr_entry, addr.addr.s_addr):
end = offsetofend(struct mptcp_pm_addr_entry, addr.addr.s_addr);
break;
#endif
'''
But if there's a sock_kmemdup() helper, it will become much simpler,
only need to call kfunc sock_kmemdup() instead in BPF.
So this patchset adds this new helper and uses it in several places.
[1]
https://lore.kernel.org/mptcp/cover.1738924875.git.tanggeliang@kylinos.cn/
====================
Link: https://patch.msgid.link/cover.1740735165.git.tanggeliang@kylinos.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'net')
-rw-r--r-- | net/core/sock.c | 16 | ||||
-rw-r--r-- | net/ipv6/exthdrs.c | 3 | ||||
-rw-r--r-- | net/mptcp/pm_userspace.c | 3 | ||||
-rw-r--r-- | net/mptcp/protocol.c | 7 | ||||
-rw-r--r-- | net/sctp/protocol.c | 7 |
5 files changed, 22 insertions, 14 deletions
diff --git a/net/core/sock.c b/net/core/sock.c index 23bce41f7f1f..a0598518ce89 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2836,6 +2836,22 @@ void *sock_kmalloc(struct sock *sk, int size, gfp_t priority) } EXPORT_SYMBOL(sock_kmalloc); +/* + * Duplicate the input "src" memory block using the socket's + * option memory buffer. + */ +void *sock_kmemdup(struct sock *sk, const void *src, + int size, gfp_t priority) +{ + void *mem; + + mem = sock_kmalloc(sk, size, priority); + if (mem) + memcpy(mem, src, size); + return mem; +} +EXPORT_SYMBOL(sock_kmemdup); + /* Free an option memory block. Note, we actually want the inline * here as this allows gcc to detect the nullify and fold away the * condition entirely. diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 6789623b2b0d..457de0745a33 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -1204,10 +1204,9 @@ ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *opt) { struct ipv6_txoptions *opt2; - opt2 = sock_kmalloc(sk, opt->tot_len, GFP_ATOMIC); + opt2 = sock_kmemdup(sk, opt, opt->tot_len, GFP_ATOMIC); if (opt2) { long dif = (char *)opt2 - (char *)opt; - memcpy(opt2, opt, opt->tot_len); if (opt2->hopopt) *((char **)&opt2->hopopt) += dif; if (opt2->dst0opt) diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index 6bf6a20ef7f3..7e7d01bef5d4 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -71,13 +71,12 @@ static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, /* Memory for the entry is allocated from the * sock option buffer. */ - e = sock_kmalloc(sk, sizeof(*e), GFP_ATOMIC); + e = sock_kmemdup(sk, entry, sizeof(*entry), GFP_ATOMIC); if (!e) { ret = -ENOMEM; goto append_err; } - *e = *entry; if (!e->addr.id && needs_id) e->addr.id = find_next_zero_bit(id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1, diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 6b61b7dee33b..ec23e65ef0f1 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -3178,12 +3178,9 @@ static void mptcp_copy_ip_options(struct sock *newsk, const struct sock *sk) rcu_read_lock(); inet_opt = rcu_dereference(inet->inet_opt); if (inet_opt) { - newopt = sock_kmalloc(newsk, sizeof(*inet_opt) + + newopt = sock_kmemdup(newsk, inet_opt, sizeof(*inet_opt) + inet_opt->opt.optlen, GFP_ATOMIC); - if (newopt) - memcpy(newopt, inet_opt, sizeof(*inet_opt) + - inet_opt->opt.optlen); - else + if (!newopt) net_warn_ratelimited("%s: Failed to copy ip options\n", __func__); } RCU_INIT_POINTER(newinet->inet_opt, newopt); diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 29727ed1008e..5407a3922101 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -185,12 +185,9 @@ static void sctp_v4_copy_ip_options(struct sock *sk, struct sock *newsk) rcu_read_lock(); inet_opt = rcu_dereference(inet->inet_opt); if (inet_opt) { - newopt = sock_kmalloc(newsk, sizeof(*inet_opt) + + newopt = sock_kmemdup(newsk, inet_opt, sizeof(*inet_opt) + inet_opt->opt.optlen, GFP_ATOMIC); - if (newopt) - memcpy(newopt, inet_opt, sizeof(*inet_opt) + - inet_opt->opt.optlen); - else + if (!newopt) pr_err("%s: Failed to copy ip options\n", __func__); } RCU_INIT_POINTER(newinet->inet_opt, newopt); |