linux/net/xfrm/xfrm_ipcomp.c

387 lines
7.6 KiB
C
Raw Normal View History

/*
* IP Payload Compression Protocol (IPComp) - RFC3173.
*
* Copyright (c) 2003 James Morris <jmorris@intercode.com.au>
* Copyright (c) 2003-2008 Herbert Xu <herbert@gondor.apana.org.au>
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License as published by the Free
* Software Foundation; either version 2 of the License, or (at your option)
* any later version.
*
* Todo:
* - Tunable compression parameters.
* - Compression stats.
* - Adaptive compression.
*/
#include <linux/crypto.h>
#include <linux/err.h>
#include <linux/list.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/percpu.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 09:04:11 +01:00
#include <linux/slab.h>
#include <linux/smp.h>
#include <linux/vmalloc.h>
#include <net/ip.h>
#include <net/ipcomp.h>
#include <net/xfrm.h>
struct ipcomp_tfms {
struct list_head list;
struct crypto_comp * __percpu *tfms;
int users;
};
static DEFINE_MUTEX(ipcomp_resource_mutex);
static void * __percpu *ipcomp_scratches;
static int ipcomp_scratch_users;
static LIST_HEAD(ipcomp_tfms_list);
static int ipcomp_decompress(struct xfrm_state *x, struct sk_buff *skb)
{
struct ipcomp_data *ipcd = x->data;
const int plen = skb->len;
int dlen = IPCOMP_SCRATCH_SIZE;
const u8 *start = skb->data;
const int cpu = get_cpu();
u8 *scratch = *per_cpu_ptr(ipcomp_scratches, cpu);
struct crypto_comp *tfm = *per_cpu_ptr(ipcd->tfms, cpu);
int err = crypto_comp_decompress(tfm, start, plen, scratch, &dlen);
int len;
if (err)
goto out;
if (dlen < (plen + sizeof(struct ip_comp_hdr))) {
err = -EINVAL;
goto out;
}
len = dlen - plen;
if (len > skb_tailroom(skb))
len = skb_tailroom(skb);
__skb_put(skb, len);
len += plen;
skb_copy_to_linear_data(skb, scratch, len);
while ((scratch += len, dlen -= len) > 0) {
skb_frag_t *frag;
struct page *page;
err = -EMSGSIZE;
if (WARN_ON(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS))
goto out;
frag = skb_shinfo(skb)->frags + skb_shinfo(skb)->nr_frags;
page = alloc_page(GFP_ATOMIC);
err = -ENOMEM;
if (!page)
goto out;
__skb_frag_set_page(frag, page);
len = PAGE_SIZE;
if (dlen < len)
len = dlen;
frag->page_offset = 0;
skb_frag_size_set(frag, len);
memcpy(skb_frag_address(frag), scratch, len);
skb->truesize += len;
skb->data_len += len;
skb->len += len;
skb_shinfo(skb)->nr_frags++;
}
err = 0;
out:
put_cpu();
return err;
}
int ipcomp_input(struct xfrm_state *x, struct sk_buff *skb)
{
int nexthdr;
int err = -ENOMEM;
struct ip_comp_hdr *ipch;
if (skb_linearize_cow(skb))
goto out;
skb->ip_summed = CHECKSUM_NONE;
/* Remove ipcomp header and decompress original payload */
ipch = (void *)skb->data;
nexthdr = ipch->nexthdr;
skb->transport_header = skb->network_header + sizeof(*ipch);
__skb_pull(skb, sizeof(*ipch));
err = ipcomp_decompress(x, skb);
if (err)
goto out;
err = nexthdr;
out:
return err;
}
EXPORT_SYMBOL_GPL(ipcomp_input);
static int ipcomp_compress(struct xfrm_state *x, struct sk_buff *skb)
{
struct ipcomp_data *ipcd = x->data;
const int plen = skb->len;
int dlen = IPCOMP_SCRATCH_SIZE;
u8 *start = skb->data;
struct crypto_comp *tfm;
u8 *scratch;
int err;
local_bh_disable();
scratch = *this_cpu_ptr(ipcomp_scratches);
tfm = *this_cpu_ptr(ipcd->tfms);
err = crypto_comp_compress(tfm, start, plen, scratch, &dlen);
if (err)
goto out;
if ((dlen + sizeof(struct ip_comp_hdr)) >= plen) {
err = -EMSGSIZE;
goto out;
}
memcpy(start + sizeof(struct ip_comp_hdr), scratch, dlen);
local_bh_enable();
pskb_trim(skb, dlen + sizeof(struct ip_comp_hdr));
return 0;
out:
local_bh_enable();
return err;
}
int ipcomp_output(struct xfrm_state *x, struct sk_buff *skb)
{
int err;
struct ip_comp_hdr *ipch;
struct ipcomp_data *ipcd = x->data;
if (skb->len < ipcd->threshold) {
/* Don't bother compressing */
goto out_ok;
}
if (skb_linearize_cow(skb))
goto out_ok;
err = ipcomp_compress(x, skb);
if (err) {
goto out_ok;
}
/* Install ipcomp header, convert into ipcomp datagram. */
ipch = ip_comp_hdr(skb);
ipch->nexthdr = *skb_mac_header(skb);
ipch->flags = 0;
ipch->cpi = htons((u16 )ntohl(x->id.spi));
*skb_mac_header(skb) = IPPROTO_COMP;
out_ok:
skb_push(skb, -skb_network_offset(skb));
return 0;
}
EXPORT_SYMBOL_GPL(ipcomp_output);
static void ipcomp_free_scratches(void)
{
int i;
void * __percpu *scratches;
if (--ipcomp_scratch_users)
return;
scratches = ipcomp_scratches;
if (!scratches)
return;
for_each_possible_cpu(i)
vfree(*per_cpu_ptr(scratches, i));
free_percpu(scratches);
}
static void * __percpu *ipcomp_alloc_scratches(void)
{
void * __percpu *scratches;
int i;
if (ipcomp_scratch_users++)
return ipcomp_scratches;
scratches = alloc_percpu(void *);
if (!scratches)
return NULL;
ipcomp_scratches = scratches;
for_each_possible_cpu(i) {
void *scratch;
scratch = vmalloc_node(IPCOMP_SCRATCH_SIZE, cpu_to_node(i));
if (!scratch)
return NULL;
*per_cpu_ptr(scratches, i) = scratch;
}
return scratches;
}
static void ipcomp_free_tfms(struct crypto_comp * __percpu *tfms)
{
struct ipcomp_tfms *pos;
int cpu;
list_for_each_entry(pos, &ipcomp_tfms_list, list) {
if (pos->tfms == tfms)
break;
}
WARN_ON(!pos);
if (--pos->users)
return;
list_del(&pos->list);
kfree(pos);
if (!tfms)
return;
for_each_possible_cpu(cpu) {
struct crypto_comp *tfm = *per_cpu_ptr(tfms, cpu);
crypto_free_comp(tfm);
}
free_percpu(tfms);
}
static struct crypto_comp * __percpu *ipcomp_alloc_tfms(const char *alg_name)
{
struct ipcomp_tfms *pos;
struct crypto_comp * __percpu *tfms;
int cpu;
list_for_each_entry(pos, &ipcomp_tfms_list, list) {
struct crypto_comp *tfm;
/* This can be any valid CPU ID so we don't need locking. */
net: xfrm: use preempt-safe this_cpu_read() in ipcomp_alloc_tfms() f7c83bcbfaf5 ("net: xfrm: use __this_cpu_read per-cpu helper") added a __this_cpu_read() call inside ipcomp_alloc_tfms(). At the time, __this_cpu_read() required the caller to either not care about races or to handle preemption/interrupt issues. 3.15 tightened the rules around some per-cpu operations, and now __this_cpu_read() should never be used in a preemptible context. On 3.15 and later, we need to use this_cpu_read() instead. syzkaller reported this leading to the following kernel BUG while fuzzing sendmsg: BUG: using __this_cpu_read() in preemptible [00000000] code: repro/3101 caller is ipcomp_init_state+0x185/0x990 CPU: 3 PID: 3101 Comm: repro Not tainted 4.16.0-rc4-00123-g86f84779d8e9 #154 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014 Call Trace: dump_stack+0xb9/0x115 check_preemption_disabled+0x1cb/0x1f0 ipcomp_init_state+0x185/0x990 ? __xfrm_init_state+0x876/0xc20 ? lock_downgrade+0x5e0/0x5e0 ipcomp4_init_state+0xaa/0x7c0 __xfrm_init_state+0x3eb/0xc20 xfrm_init_state+0x19/0x60 pfkey_add+0x20df/0x36f0 ? pfkey_broadcast+0x3dd/0x600 ? pfkey_sock_destruct+0x340/0x340 ? pfkey_seq_stop+0x80/0x80 ? __skb_clone+0x236/0x750 ? kmem_cache_alloc+0x1f6/0x260 ? pfkey_sock_destruct+0x340/0x340 ? pfkey_process+0x62a/0x6f0 pfkey_process+0x62a/0x6f0 ? pfkey_send_new_mapping+0x11c0/0x11c0 ? mutex_lock_io_nested+0x1390/0x1390 pfkey_sendmsg+0x383/0x750 ? dump_sp+0x430/0x430 sock_sendmsg+0xc0/0x100 ___sys_sendmsg+0x6c8/0x8b0 ? copy_msghdr_from_user+0x3b0/0x3b0 ? pagevec_lru_move_fn+0x144/0x1f0 ? find_held_lock+0x32/0x1c0 ? do_huge_pmd_anonymous_page+0xc43/0x11e0 ? lock_downgrade+0x5e0/0x5e0 ? get_kernel_page+0xb0/0xb0 ? _raw_spin_unlock+0x29/0x40 ? do_huge_pmd_anonymous_page+0x400/0x11e0 ? __handle_mm_fault+0x553/0x2460 ? __fget_light+0x163/0x1f0 ? __sys_sendmsg+0xc7/0x170 __sys_sendmsg+0xc7/0x170 ? SyS_shutdown+0x1a0/0x1a0 ? __do_page_fault+0x5a0/0xca0 ? lock_downgrade+0x5e0/0x5e0 SyS_sendmsg+0x27/0x40 ? __sys_sendmsg+0x170/0x170 do_syscall_64+0x19f/0x640 entry_SYSCALL_64_after_hwframe+0x42/0xb7 RIP: 0033:0x7f0ee73dfb79 RSP: 002b:00007ffe14fc15a8 EFLAGS: 00000207 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f0ee73dfb79 RDX: 0000000000000000 RSI: 00000000208befc8 RDI: 0000000000000004 RBP: 00007ffe14fc15b0 R08: 00007ffe14fc15c0 R09: 00007ffe14fc15c0 R10: 0000000000000000 R11: 0000000000000207 R12: 0000000000400440 R13: 00007ffe14fc16b0 R14: 0000000000000000 R15: 0000000000000000 Signed-off-by: Greg Hackmann <ghackmann@google.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2018-03-07 23:42:53 +01:00
tfm = this_cpu_read(*pos->tfms);
if (!strcmp(crypto_comp_name(tfm), alg_name)) {
pos->users++;
return pos->tfms;
}
}
pos = kmalloc(sizeof(*pos), GFP_KERNEL);
if (!pos)
return NULL;
pos->users = 1;
INIT_LIST_HEAD(&pos->list);
list_add(&pos->list, &ipcomp_tfms_list);
pos->tfms = tfms = alloc_percpu(struct crypto_comp *);
if (!tfms)
goto error;
for_each_possible_cpu(cpu) {
struct crypto_comp *tfm = crypto_alloc_comp(alg_name, 0,
CRYPTO_ALG_ASYNC);
if (IS_ERR(tfm))
goto error;
*per_cpu_ptr(tfms, cpu) = tfm;
}
return tfms;
error:
ipcomp_free_tfms(tfms);
return NULL;
}
static void ipcomp_free_data(struct ipcomp_data *ipcd)
{
if (ipcd->tfms)
ipcomp_free_tfms(ipcd->tfms);
ipcomp_free_scratches();
}
void ipcomp_destroy(struct xfrm_state *x)
{
struct ipcomp_data *ipcd = x->data;
if (!ipcd)
return;
xfrm_state_delete_tunnel(x);
mutex_lock(&ipcomp_resource_mutex);
ipcomp_free_data(ipcd);
mutex_unlock(&ipcomp_resource_mutex);
kfree(ipcd);
}
EXPORT_SYMBOL_GPL(ipcomp_destroy);
int ipcomp_init_state(struct xfrm_state *x)
{
int err;
struct ipcomp_data *ipcd;
struct xfrm_algo_desc *calg_desc;
err = -EINVAL;
if (!x->calg)
goto out;
if (x->encap)
goto out;
err = -ENOMEM;
ipcd = kzalloc(sizeof(*ipcd), GFP_KERNEL);
if (!ipcd)
goto out;
mutex_lock(&ipcomp_resource_mutex);
if (!ipcomp_alloc_scratches())
goto error;
ipcd->tfms = ipcomp_alloc_tfms(x->calg->alg_name);
if (!ipcd->tfms)
goto error;
mutex_unlock(&ipcomp_resource_mutex);
calg_desc = xfrm_calg_get_byname(x->calg->alg_name, 0);
BUG_ON(!calg_desc);
ipcd->threshold = calg_desc->uinfo.comp.threshold;
x->data = ipcd;
err = 0;
out:
return err;
error:
ipcomp_free_data(ipcd);
mutex_unlock(&ipcomp_resource_mutex);
kfree(ipcd);
goto out;
}
EXPORT_SYMBOL_GPL(ipcomp_init_state);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("IP Payload Compression Protocol (IPComp) - RFC3173");
MODULE_AUTHOR("James Morris <jmorris@intercode.com.au>");