From f66ee0410b1c3481ee75e5db9b34547b4d582465 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Tue, 11 Feb 2020 23:20:43 +0100 Subject: netfilter: ipset: Fix "INFO: rcu detected stall in hash_xxx" reports In the case of huge hash:* types of sets, due to the single spinlock of a set the processing of the whole set under spinlock protection could take too long. There were four places where the whole hash table of the set was processed from bucket to bucket under holding the spinlock: - During resizing a set, the original set was locked to exclude kernel side add/del element operations (userspace add/del is excluded by the nfnetlink mutex). The original set is actually just read during the resize, so the spinlocking is replaced with rcu locking of regions. However, thus there can be parallel kernel side add/del of entries. In order not to loose those operations a backlog is added and replayed after the successful resize. - Garbage collection of timed out entries was also protected by the spinlock. In order not to lock too long, region locking is introduced and a single region is processed in one gc go. Also, the simple timer based gc running is replaced with a workqueue based solution. The internal book-keeping (number of elements, size of extensions) is moved to region level due to the region locking. - Adding elements: when the max number of the elements is reached, the gc was called to evict the timed out entries. The new approach is that the gc is called just for the matching region, assuming that if the region (proportionally) seems to be full, then the whole set does. We could scan the other regions to check every entry under rcu locking, but for huge sets it'd mean a slowdown at adding elements. - Listing the set header data: when the set was defined with timeout support, the garbage collector was called to clean up timed out entries to get the correct element numbers and set size values. Now the set is scanned to check non-timed out entries, without actually calling the gc for the whole set. Thanks to Florian Westphal for helping me to solve the SOFTIRQ-safe -> SOFTIRQ-unsafe lock order issues during working on the patch. Reported-by: syzbot+4b0e9d4ff3cf117837e5@syzkaller.appspotmail.com Reported-by: syzbot+c27b8d5010f45c666ed1@syzkaller.appspotmail.com Reported-by: syzbot+68a806795ac89df3aa1c@syzkaller.appspotmail.com Fixes: 23c42a403a9c ("netfilter: ipset: Introduction of new commands and protocol version 7") Signed-off-by: Jozsef Kadlecsik --- include/linux/netfilter/ipset/ip_set.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux/netfilter') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 908d38dbcb91..5448c8b443db 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -121,6 +121,7 @@ struct ip_set_ext { u32 timeout; u8 packets_op; u8 bytes_op; + bool target; }; struct ip_set; @@ -187,6 +188,14 @@ struct ip_set_type_variant { /* Return true if "b" set is the same as "a" * according to the create set parameters */ bool (*same_set)(const struct ip_set *a, const struct ip_set *b); + /* Region-locking is used */ + bool region_lock; +}; + +struct ip_set_region { + spinlock_t lock; /* Region lock */ + size_t ext_size; /* Size of the dynamic extensions */ + u32 elements; /* Number of elements vs timeout */ }; /* The core set type structure */ @@ -501,7 +510,7 @@ ip_set_init_skbinfo(struct ip_set_skbinfo *skbinfo, } #define IP_SET_INIT_KEXT(skb, opt, set) \ - { .bytes = (skb)->len, .packets = 1, \ + { .bytes = (skb)->len, .packets = 1, .target = true,\ .timeout = ip_set_adt_opt_timeout(opt, set) } #define IP_SET_INIT_UEXT(set) \ -- cgit v1.2.3 From 6daf14140129d30207ed6a0a69851fa6a3636bda Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 20 Feb 2020 07:59:14 -0600 Subject: netfilter: Replace zero-length array with flexible-array member The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] Lastly, fix checkpatch.pl warning WARNING: __aligned(size) is preferred over __attribute__((aligned(size))) in net/bridge/netfilter/ebtables.c This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set.h | 2 +- include/linux/netfilter/x_tables.h | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux/netfilter') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 5448c8b443db..ab192720e2d6 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -98,7 +98,7 @@ struct ip_set_counter { struct ip_set_comment_rcu { struct rcu_head rcu; - char str[0]; + char str[]; }; struct ip_set_comment { diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 1b261c51b3a3..5da88451853b 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -264,7 +264,7 @@ struct xt_table_info { unsigned int stacksize; void ***jumpstack; - unsigned char entries[0] __aligned(8); + unsigned char entries[] __aligned(8); }; int xt_register_target(struct xt_target *target); @@ -464,7 +464,7 @@ struct compat_xt_entry_match { } kernel; u_int16_t match_size; } u; - unsigned char data[0]; + unsigned char data[]; }; struct compat_xt_entry_target { @@ -480,7 +480,7 @@ struct compat_xt_entry_target { } kernel; u_int16_t target_size; } u; - unsigned char data[0]; + unsigned char data[]; }; /* FIXME: this works only on 32 bit tasks @@ -494,7 +494,7 @@ struct compat_xt_counters { struct compat_xt_counters_info { char name[XT_TABLE_MAXNAMELEN]; compat_uint_t num_counters; - struct compat_xt_counters counters[0]; + struct compat_xt_counters counters[]; }; struct _compat_xt_align { -- cgit v1.2.3