- 04 Oct, 2021 13 commits
-
-
Oran Agra authored
-
sundb authored
Normally we execute the read event first and then the write event. When the barrier is set, we will do it reverse. However, under `kqueue`, if an `fd` has both read and write events, reading the event using `kevent` will generate two events, which will result in uncontrolled read and write timing. This also means that the guarantees of AOF `appendfsync` = `always` are not met on MacOS without this fix. The main change to this pr is to cache the events already obtained when reading them, so that if the same `fd` occurs again, only the mask in the cache is updated, rather than a new event is generated. This was exposed by the following test failure on MacOS: ``` *** [err]: AOF fsync always barrier issue in tests/integration/aof.tcl Expected 544 != 544 (context: type eval line 26 cmd {assert {$size1 != $size2}} proc ::test) ``` (cherry picked from commit 306a5ccd)
-
zhaozhao.zz authored
(cherry picked from commit da840e98)
-
Oran Agra authored
this code is in use only if the master is disk-based, and the replica is diskless. In this case we use a buffered reader, but we must avoid reading past the rdb file, into the command stream. which Luckly rdb.c doesn't really attempt to do (it knows how much it should read). When rioConnRead detects that the extra buffering attempt reaches beyond the read limit it should read less, but if the caller actually requested more, then it should return with an error rather than a short read. the bug would have resulted in short read. in order to fix it, the code must consider the real requested size, and not the extra buffering size. (cherry picked from commit 40d7fca3)
-
YiyuanGUO authored
-
Oran Agra authored
- fix possible heap corruption in ziplist and listpack resulting by trying to allocate more than the maximum size of 4GB. - prevent ziplist (hash and zset) from reaching size of above 1GB, will be converted to HT encoding, that's not a useful size. - prevent listpack (stream) from reaching size of above 1GB. - XADD will start a new listpack if the new record may cause the previous listpack to grow over 1GB. - XADD will respond with an error if a single stream record is over 1GB - List type (ziplist in quicklist) was truncating strings that were over 4GB, now it'll respond with an error.
-
meir@redislabs.com authored
When LUA call our C code, by default, the LUA stack has room for 20 elements. In most cases, this is more than enough but sometimes it's not and the caller must verify the LUA stack size before he pushes elements. On 3 places in the code, there was no verification of the LUA stack size. On specific inputs this missing verification could have lead to invalid memory write: 1. On 'luaReplyToRedisReply', one might return a nested reply that will explode the LUA stack. 2. On 'redisProtocolToLuaType', the Redis reply might be deep enough to explode the LUA stack (notice that currently there is no such command in Redis that returns such a nested reply, but modules might do it) 3. On 'ldbRedis', one might give a command with enough arguments to explode the LUA stack (all the arguments will be pushed to the LUA stack) This commit is solving all those 3 issues by calling 'lua_checkstack' and verify that there is enough room in the LUA stack to push elements. In case 'lua_checkstack' returns an error (there is not enough room in the LUA stack and it's not possible to increase the stack), we will do the following: 1. On 'luaReplyToRedisReply', we will return an error to the user. 2. On 'redisProtocolToLuaType' we will exit with panic (we assume this scenario is rare because it can only happen with a module). 3. On 'ldbRedis', we return an error.
-
meir@redislabs.com authored
The protocol parsing on 'ldbReplParseCommand' (LUA debugging) Assumed protocol correctness. This means that if the following is given: *1 $100 test The parser will try to read additional 94 unallocated bytes after the client buffer. This commit fixes this issue by validating that there are actually enough bytes to read. It also limits the amount of data that can be sent by the debugger client to 1M so the client will not be able to explode the memory.
-
Oran Agra authored
This change sets a low limit for multibulk and bulk length in the protocol for unauthenticated connections, so that they can't easily cause redis to allocate massive amounts of memory by sending just a few characters on the network. The new limits are 10 arguments of 16kb each (instead of 1m of 512mb)
-
Oran Agra authored
The redis-cli command line tool and redis-sentinel service may be vulnerable to integer overflow when parsing specially crafted large multi-bulk network replies. This is a result of a vulnerability in the underlying hiredis library which does not perform an overflow check before calling the calloc() heap allocation function. This issue only impacts systems with heap allocators that do not perform their own overflow checks. Most modern systems do and are therefore not likely to be affected. Furthermore, by default redis-sentinel uses the jemalloc allocator which is also not vulnerable.
-
Oran Agra authored
The vulnerability involves changing the default set-max-intset-entries configuration parameter to a very large value and constructing specially crafted commands to manipulate sets
-
- 21 Jul, 2021 21 commits
-
-
Oran Agra authored
-
Huang Zhw authored
On 32 bit platform, the bit position of GETBIT/SETBIT/BITFIELD/BITCOUNT,BITPOS may overflow (see CVE-2021-32761) (#9191) GETBIT, SETBIT may access wrong address because of wrap. BITCOUNT and BITPOS may return wrapped results. BITFIELD may access the wrong address but also allocate insufficient memory and segfault (see CVE-2021-32761). This commit uses `uint64_t` or `long long` instead of `size_t`. related https://github.com/redis/redis/pull/8096 At 32bit platform: > setbit bit 4294967295 1 (integer) 0 > config set proto-max-bulk-len 536870913 OK > append bit "\xFF" (integer) 536870913 > getbit bit 4294967296 (integer) 0 When the bit index is larger than 4294967295, size_t can't hold bit index. In the past, `proto-max-bulk-len` is limit to 536870912, so there is no problem. After this commit, bit position is stored in `uint64_t` or `long long`. So when `proto-max-bulk-len > 536870912`, 32bit platforms can still be correct. For 64bit platform, this problem still exists. The major reason is bit pos 8 times of byte pos. When proto-max-bulk-len is very larger, bit pos may overflow. But at 64bit platform, we don't have so long string. So this bug may never happen. Additionally this commit add a test cost `512MB` memory which is tag as `large-memory`. Make freebsd ci and valgrind ci ignore this test. * This test is disabled in this version since bitops doesn't rely on proto-max-bulk-len. some of the overflows can still occur so we do want the fixes. (cherry picked from commit 71d45287)
-
Huang Zhw authored
Fix module info genModulesInfoStringRenderModulesList lack separator when there's more than one module in the list. Co-authored-by:
Oran Agra <oran@redislabs.com> (cherry picked from commit 1895e134)
-
Wen Hui authored
Make it possible for redis-cli cluster import to work with source and target that require AUTH. Adding two different flags --cluster-from-user, --cluster-from-pass and --cluster-askpass for source node authentication. Also for target authentication, using existing --user and --pass flag. Example: ./redis-cli --cluster import 127.0.0.1:7000 --cluster-from 127.0.0.1:6379 --pass 1234 --user default --cluster-from-user default --cluster-from-pass 123456 ./redis-cli --cluster import 127.0.0.1:7000 --cluster-from 127.0.0.1:6379 --askpass --cluster-from-user default --cluster-from-askpass (cherry picked from commit 639b73cd)
-
Oran Agra authored
- promote the code in DEBUG PROTOCOL to addReplyBigNum - DEBUG PROTOCOL ATTRIB skips the attribute when client is RESP2 - networking.c addReply for push and attributes generate assertion when called on a RESP2 client, anything else would produce a broken protocol that clients can't handle. (cherry picked from commit 6a5bac30) (cherry picked from commit 7f38aa8bc719f709acdcefc35a45a7aa6faa76fa)
-
Huang Zhw authored
In clusterManagerCommandImport strcat was used to concat COPY and REPLACE, the space maybe not enough. If we use --cluster-replace but not --cluster-copy, the MIGRATE command contained COPY instead of REPLACE. (cherry picked from commit a049f629) (cherry picked from commit d4771a995e99e61e2e8feb92ede06431195b0300)
-
Binbin authored
SINTERSTORE would have deleted the dest key right away, even when later on it is bound to fail on an (WRONGTYPE) error. With this change it first picks up all the input keys, and only later delete the dest key if one is empty. Also add more tests for some commands. Mainly focus on - `wrong type error`: expand test case (base on sinter bug) in non-store variant add tests for store variant (although it exists in non-store variant, i think it would be better to have same tests) - the dstkey result when we meet `non-exist key (empty set)` in *store sdiff: - improve test case about wrong type error (the one we found in sinter, although it is safe in sdiff) - add test about using non-exist key (treat it like an empty set) sdiffstore: - according to sdiff test case, also add some tests about `wrong type error` and `non-exist key` - the different is that in sdiffstore, we will consider the `dstkey` result sunion/sunionstore add more tests (same as above) sinter/sinterstore also same as above ... (cherry picked from commit b8a5da80) (cherry picked from commit f4702b8b7a7da6cc661ddb6744cb322bc92e3267)
-
Jason Elbaum authored
When using RESP3, ZPOPMAX/ZPOPMIN should return nested arrays for consistency with other commands (e.g. ZRANGE). We do that only when COUNT argument is present (similarly to how LPOP behaves). for reasoning see https://github.com/redis/redis/issues/8824#issuecomment-855427955 This is a breaking change only when RESP3 is used, and COUNT argument is present! (cherry picked from commit 7f342020) (cherry picked from commit caaad2d686b2af0d13fbeda414e2b70e57635b5c)
-
Rob Snyder authored
Adds call to intrev16ifbe to ensure ZIPLIST_LENGTH is compared correctly (cherry picked from commit eaa52719) (cherry picked from commit 4c181230855bb3f92e93b32a48db52e69bd7e509)
-
perryitay authored
There are two issues fixed in this commit: 1. we want to fail the EXEC command in case there is a watched key that's logically expired but not yet deleted by active expire or lazy expire. 2. we saw that currently cache time is update in every `call()` (including nested calls), this time is being also being use for the isKeyExpired comparison, we want to update the cache time only in the first call (execCommand) Co-authored-by:
Oran Agra <oran@redislabs.com> (cherry picked from commit ac8b1df8)
-
Huang Zhw authored
Do not install a file event to send data to rewrite child when parent stop sending diff to child in aof rewrite. (#8767) In aof rewrite, when parent stop sending data to child, if there is new rewrite data, aofChildWriteDiffData write event will be installed. Then this event is issued and deletes the file event without do anyting. This will happen over and over again until aof rewrite finish. This bug used to waste a few system calls per excessive wake-up (epoll_ctl and epoll_wait) per cycle, each cycle triggered by receiving a write command from a client. (cherry picked from commit cb961d8c)
-
Omer Shadmi authored
Currently a replica is able to recover from a short read (when diskless loading is enabled) and avoid crashing/exiting, replying to the master and then the rdb could be sent again by the master for another load attempt by the replica. There were a few scenarios that were not behaving similarly, such as when there is no end-of-file marker, or when module aux data failed to load, which should be allowed to occur due to a short read. (cherry picked from commit f06d782f)
-
Oran Agra authored
The `Tracking gets notification of expired keys` test in tracking.tcl used to hung in valgrind CI quite a lot. It turns out the reason is that with valgrind and a busy machine, the server cron active expire cycle could easily run in the same event loop as the command that created `mykey`, so that when they key got expired, there were two change events to broadcast, one that set the key and one that expired it, but since we used raxTryInsert, the client that was associated with the "last" change was the one that created the key, so the NOLOOP filtered that event. This commit adds a test that reproduces the problem by using lazy expire in a multi-exec which makes sure the key expires in the same event loop as the one that added it. (cherry picked from commit 9b564b52)
-
Maxim Galushka authored
Fixes #6792. Added support of REDIS_REPLY_SET in raw and csv output of `./redis-cli` Test: run commands to test: ./redis-cli -3 --csv COMMAND ./redis-cli -3 --raw COMMAND Now they are returning resuts, were failing with: "Unknown reply type: 10" before the change. (cherry picked from commit 96bb0785)
-
YaacovHazan authored
In diskless replication, we create a read pipe for the RDB, between the child and the parent. When we close this pipe (fd), the read handler also needs to be removed from the event loop (if it still registered). Otherwise, next time we will use the same fd, the registration will be fail (panic), because we will use EPOLL_CTL_MOD (the fd still register in the event loop), on fd that already removed from epoll_ctl (cherry picked from commit 501d7755)
-
guybe7 authored
Starting redis 6.0 (part of the TLS feature), diskless master uses pipe from the fork child so that the parent is the one sending data to the replicas. This mechanism has an issue in which a hung replica will cause the master to wait for it to read the data sent to it forever, thus preventing the fork child from terminating and preventing the creations of any other forks. This PR adds a timeout mechanism, much like the ACK-based timeout, we disconnect replicas that aren't reading the RDB file fast enough. (cherry picked from commit d63d0260)
-
Oran Agra authored
Starting redis 6.0 and the changes we made to the diskless master to be suitable for TLS, I made the master avoid reaping (wait3) the pid of the child until we know all replicas are done reading their rdb. I did that in order to avoid a state where the rdb_child_pid is -1 but we don't yet want to start another fork (still busy serving that data to replicas). It turns out that the solution used so far was problematic in case the fork child was being killed (e.g. by the kernel OOM killer), in that case there's a chance that we currently disabled the read event on the rdb pipe, since we're waiting for a replica to become writable again. and in that scenario the master would have never realized the child exited, and the replica will remain hung too. Note that there's no mechanism to detect a hung replica while it's in rdb transfer state. The solution here is to add another pipe which is used by the parent to tell the child it is safe to exit. this mean that when the child exits, for whatever reason, it is safe to reap it. Besides that, i'm re-introducing an adjustment to REPLCONF ACK which was part of #6271 (Accelerate diskless master connections) but was dropped when that PR was rebased after the TLS fork/pipe changes (5a477946). Now that RdbPipeCleanup no longer calls checkChildrenDone, and the ACK has chance to detect that the child exited, it should be the one to call it so that we don't have to wait for cron (server.hz) to do that. (cherry picked from commit 573246f7)
-
- 01 Jun, 2021 5 commits
-
-
M Sazzadul Hoque authored
-
Oran Agra authored
-
patpatbear authored
this patch fixes sinterstore by add missing keyspace del event when any source set not exists. Co-authored-by:
srzhao <srzhao@sysnew.com> (cherry picked from commit 46d9f31e)
-
- 30 May, 2021 1 commit
-
-
ikeberlein authored
-