x86: syscalls: sys_setrlimit64/sys_getrlimit64 calls to provide FSIZE limits > 2^32-1
PATCH 1/1 x86: syscalls: sys_setrlimit64/sys_getrlimit64 calls to provide FSIZE limits > 2^32-1
x86: syscalls: sys_setrlimit64/sys_getrlimit64 calls to provide FSIZE limits > 2^32-1 Problem Description:
The following issue affects the setrlimit() and getrlimit() system calls on Linux 2.6.13 (and earlier) on x86. The Problem is filed at kernel.org bug 5042
(http://bugzilla.kernel.org/show_bug.cgi?id=5042)
With setrlimit()/getrlimit(), resource limits can not be set > 2^32-1 on x86 as internally, resource limits are represented in the 'rlimit' structure (defined in include/linux/resource.h) as unsigned longs, meaning 32 bits on x86. The most pertinent limit here is RLIMIT_FSIZE, which specifies the maximum size to which a file can grow: to be useful, this limit must be represented using a type that is as wide as the type used to represent file offsets, i.e., as wide as a 64-bit off_t.
Current versions of glibc (e.g., 2.3.5) deal with this situation somewhat
strangely: if a program compiled with FILE_OFFSET_BITS set to 64 (i.e., off_t is thus 'long long' -- 64 bits) tries to set a resource limit to a value larger than can be represented in a 32-bit unsigned long,then the glibc wrapper for setrlimit() silently converts the limit value to RLIM_INFINITY. In other words, the requested resource limit setting is silently ignored. One could argue that perhaps the glibc wrapper should give an error, rather than silently turning a very large limit into infinity; however, the glibc developers instead seem to have decided on the current behaviour as a means of dealing with what is fundamentally a kernel problem.)
(NOTE: This problem is not merely a theoretical one facing programmers developing new applications. Since many x86 distributions compile all file utilities with -D_FILE_OFFSET_BITS=64, this issue can bite end-users as well, if they expect to be able to set resource limits greater than 2^32-1.)
The solution to this problem would require new setrlimit64() and getrlimit64() system calls on x86, and the existing 32-bit system calls would need to be retained so that existing binaries would still run.
Design Approach:
Add two system calls sys_setrlimit64()/sys_getrlimit64(). And a type 'struct rlimit64' to accomodate more no. of limits <= 2^64-1
Implementation Details:
Inclusions: struct rlimit64, struct rlimit64 rlim64[RLIM64_NRLIMITS] to
task_struct
Test Results:
Test results are posted as Comment#6 to
http://bugzilla.kernel.org/show_bug.cgi?id=5042 System Info (uname -a): Linux infinity 2.6.29-rc2rlim64 #2 SMP Sat Jan 17 16:57:07 IST 2009 i686 GNU/Linux CPU: Intel Centrino Duo
getrlimit64: Limits in the Kernel ....
retval : 0
rlim | max64 = ffffffffffffffff
rlim | cur64 = ffffffffffffffff
setrlimit64: setting the following limits ...
retval : 0
rlim | max64 = 1122334455667788
rlim | cur64 = 1122334455667788
getrlimit64: Limits in the Kernel set ....
retval : 0
rlim | max64 = 1122334455667788
rlim | cur64 = 1122334455667788
arch/x86/kernel/syscall_table_32.S +2 -0
@@ -332,3 +332,5 @@ ENTRY(sys_call_table) .long sys_dup3 /* 330 */ .long sys_pipe2 .long sys_inotify_init1 + .long sys_setrlimit64 + .long sys_getrlimit64
include/asm-generic/resource.h +10 -0
@@ -46,6 +46,7 @@#define RLIMIT_RTPRIO 14/* maximum realtime priority */ #define RLIMIT_RTTIME 15/* timeout for RT tasks in us */ #define RLIM_NLIMITS 16 +#define RLIM64_NLIMITS 2/* * SuS says limits have to be unsigned.
@@ -56,6 +57,9 @@#ifndef RLIM_INFINITY # define RLIM_INFINITY (~0UL)#endif +#ifndef RLIM64_INFINITY +# define RLIM64_INFINITY (~0ULL) +#endif /* * RLIMIT_STACK default maximum - some architectures override it:
@@ -89,6 +93,12 @@ [RLIMIT_RTTIME] = { RLIM_INFINITY, RLIM_INFINITY }, \ } +#define INIT_RLIMITS64 \ +{ \ + [0] = { RLIM64_INFINITY, RLIM64_INFINITY }, \ + [RLIMIT_FSIZE] = { RLIM64_INFINITY, RLIM64_INFINITY }, \ +} +#endif /* __KERNEL__ */ #endif
include/linux/init_task.h +1 -0
@@ -48,6 +48,7 @@ extern struct fs_struct init_fs; .posix_timers = LIST_HEAD_INIT(sig.posix_timers), \ .cpu_timers = INIT_CPU_TIMERS(sig.cpu_timers), \ .rlim = INIT_RLIMITS, \ + .rlim64 = INIT_RLIMITS64, \ }extern struct nsproxy init_nsproxy;
include/linux/resource.h +5 -0
@@ -45,6 +45,11 @@ struct rlimit {unsigned long rlim_max; }; +struct rlimit64 { +u64 rlim64_cur; +u64 rlim64_max; +}; +#define PRIO_MIN (-20)#define PRIO_MAX 20
include/linux/sched.h +1 -0
@@ -572,6 +572,7 @@ struct signal_struct {* have no need to disable irqs. */ struct rlimit rlim[RLIM_NLIMITS ]; +struct rlimit64 rlim64[RLIM64_NLIMITS ];#ifdef CONFIG_BSD_PROCESS_ACCT struct pacct_struct pacct;/* per-process accounting information */
kernel/ChangeLog +10 -0
@@ -0,0 +1,10 @@ +2008-01-17 Narendra Prasad <[email protected]> + Problem Description: + The following issue affects the setrlimit() and getrlimit() system calls on Linux 2.6.13 (and earlier) on x86. + The Problem is filed at kernel.org bug 5042 (http://bugzilla.kernel.org/show_bug.cgi?id=5042) + Design Approach: + Add two system calls sys_setrlimit64()/sys_getrlimit64(). + And a type 'struct rlimit64' to accomodate more no. of limits <= 2^64-1 + Implementation Details: + Inclusions: struct rlimit64, struct rlimit64 + rlim64[RLIM64_NRLIMITS] to task_struct
kernel/fork.c +1 -0
@@ -862,6 +862,7 @@ static int copy_signal(unsigned long clotask_lock (current->group_leader);memcpy (sig->rlim, current->signal->rlim,sizeof sig->rlim); +memcpy (sig->rlim64, current->signal->rlim64,sizeof sig->rlim64);task_unlock (current->group_leader);posix_cpu_timers_init_group (sig);
kernel/sys.c +126 -0
132 lines not on this page · raw message