From 8d55c25f158921b508bff0e7f25158991913f922 Mon Sep 17 00:00:00 2001 From: Pranith Kumar K Date: Wed, 11 Dec 2013 09:33:53 +0530 Subject: syncop: Change return value of syncop Problem: We found a day-1 bug when syncop_xxx() infra is used inside a synctask with compilation optimization (CFLAGS -O2). Detailed explanation of the Root cause: We found the bug in 'gf_defrag_migrate_data' in rebalance operation: Lets look at interesting parts of the function: int gf_defrag_migrate_data (xlator_t *this, gf_defrag_info_t *defrag, loc_t *loc, dict_t *migrate_data) { ..... code section - [ Loop ] while ((ret = syncop_readdirp (this, fd, 131072, offset, NULL, &entries)) != 0) { ..... code section - [ ERRNO-1 ] (errno of readdirp is stored in readdir_operrno by a thread) /* Need to keep track of ENOENT errno, that means, there is no need to send more readdirp() */ readdir_operrno = errno; ..... code section - [ SYNCOP-1 ] (syncop_getxattr is called by a thread) ret = syncop_getxattr (this, &entry_loc, &dict, GF_XATTR_LINKINFO_KEY); code section - [ ERRNO-2] (checking for failures of syncop_getxattr(). This may not always be executed in same thread which executed [SYNCOP-1]) if (ret < 0) { if (errno != ENODATA) { loglevel = GF_LOG_ERROR; defrag->total_failures += 1; ..... } the function above could be executed by thread(t1) till [SYNCOP-1] and code from [ERRNO-2] can be executed by a different thread(t2) because of the way syncop-infra schedules the tasks. when the code is compiled with -O2 optimization this is the assembly code that is generated: [ERRNO-1] 1165 readdir_operrno = errno; <<---- errno gets expanded as *(__errno_location()) 0x00007fd149d48b60 <+496>: callq 0x7fd149d410c0 0x00007fd149d48b72 <+514>: mov %rax,0x50(%rsp) <<------ Address returned by __errno_location() is stored in a special location in stack for later use. 0x00007fd149d48b77 <+519>: mov (%rax),%eax 0x00007fd149d48b79 <+521>: mov %eax,0x78(%rsp) .... [ERRNO-2] 1281 if (errno != ENODATA) { 0x00007fd149d492ae <+2366>: mov 0x50(%rsp),%rax <<----- Because it already stored the address returned by __errno_location(), it just dereferences the address to get the errno value. BUT THIS CODE NEED NOT BE EXECUTED BY SAME THREAD!!! 0x00007fd149d492b3 <+2371>: mov $0x9,%ebp 0x00007fd149d492b8 <+2376>: mov (%rax),%edi 0x00007fd149d492ba <+2378>: cmp $0x3d,%edi The problem is that __errno_location() value of t1 and t2 are different. So [ERRNO-2] ends up reading errno of t1 instead of errno of t2 even though t2 is executing [ERRNO-2] code section. When code is compiled without any optimization for [ERRNO-2]: 1281 if (errno != ENODATA) { 0x00007fd58e7a326f <+2237>: callq 0x7fd58e797300 <<--- As it is calling __errno_location() again it gets the location from t2 so it works as intended. 0x00007fd58e7a3274 <+2242>: mov (%rax),%eax 0x00007fd58e7a3276 <+2244>: cmp $0x3d,%eax 0x00007fd58e7a3279 <+2247>: je 0x7fd58e7a32a1 Fix: Make syncop_xxx() return (-errno) value as the return value in case of errors and all the functions which make syncop_xxx() will need to use (-ret) to figure out the reason for failure in case of syncop_xxx() failures. Change-Id: I314d20dabe55d3e62ff66f3b4adb1cac2eaebb57 BUG: 1040356 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.org/6475 Tested-by: Gluster Build System Reviewed-by: Anand Avati --- api/src/glfs-internal.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'api/src/glfs-internal.h') diff --git a/api/src/glfs-internal.h b/api/src/glfs-internal.h index ec1d5579d..f04557323 100644 --- a/api/src/glfs-internal.h +++ b/api/src/glfs-internal.h @@ -18,6 +18,26 @@ #define DEFAULT_REVAL_COUNT 1 +/* + * syncop_xxx() calls are executed in two ways, one is inside a synctask where + * the executing function will do 'swapcontext' and the other is without + * synctask where the executing thread is made to wait using pthread_cond_wait. + * Executing thread may change when syncop_xxx() is executed inside a synctask. + * This leads to errno_location change i.e. errno may give errno of + * non-executing thread. So errno is not touched inside a synctask execution. + * All gfapi calls are executed using the second way of executing syncop_xxx() + * where the executing thread waits using pthread_cond_wait so it is ok to set + * errno in these cases. The following macro makes syncop_xxx() behave just + * like a system call, where -1 is returned and errno is set when a failure + * occurs. + */ +#define DECODE_SYNCOP_ERR(ret) do { \ + if (ret < 0) { \ + errno = -ret; \ + ret = -1; \ + } \ + } while (0) + #define ESTALE_RETRY(ret,errno,reval,loc,label) do { \ if (ret == -1 && errno == ESTALE) { \ if (reval < DEFAULT_REVAL_COUNT) { \ -- cgit