From 1070204c9a492fd6ec16cd1d19b2dfe3af5c70e3 Mon Sep 17 00:00:00 2001 From: "Sergey Semyonov (Serge)" Date: Fri, 1 Mar 2013 06:44:14 +0000 Subject: [PATCH] drivers: udpate ddk git-svn-id: svn://kolibrios.org@3297 a494cfbc-eb01-0410-851d-a64ba20cac60 --- drivers/ddk/linux/time.c | 16 + drivers/ddk/malloc/malloc.c | 2240 ++++++++++++++++++----- drivers/include/drm/drmP.h | 2 +- drivers/include/linux/asm/scatterlist.h | 2 + drivers/include/linux/list.h | 2 +- drivers/include/linux/scatterlist.h | 2 +- drivers/include/linux/wait.h | 10 +- 7 files changed, 1837 insertions(+), 437 deletions(-) diff --git a/drivers/ddk/linux/time.c b/drivers/ddk/linux/time.c index 254331825a..74b57c069c 100644 --- a/drivers/ddk/linux/time.c +++ b/drivers/ddk/linux/time.c @@ -146,3 +146,19 @@ unsigned long usecs_to_jiffies(const unsigned int u) #endif } +unsigned long +timespec_to_jiffies(const struct timespec *value) +{ + unsigned long sec = value->tv_sec; + long nsec = value->tv_nsec + TICK_NSEC - 1; + + if (sec >= MAX_SEC_IN_JIFFIES){ + sec = MAX_SEC_IN_JIFFIES; + nsec = 0; + } + return (((u64)sec * SEC_CONVERSION) + + (((u64)nsec * NSEC_CONVERSION) >> + (NSEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC; + +} + diff --git a/drivers/ddk/malloc/malloc.c b/drivers/ddk/malloc/malloc.c index 3ef406a2e3..d980bb27f9 100644 --- a/drivers/ddk/malloc/malloc.c +++ b/drivers/ddk/malloc/malloc.c @@ -1,11 +1,10 @@ /* This is a version (aka dlmalloc) of malloc/free/realloc written by Doug Lea and released to the public domain, as explained at - http://creativecommons.org/licenses/publicdomain. Send questions, + http://creativecommons.org/publicdomain/zero/1.0/ Send questions, comments, complaints, performance data, etc to dl@cs.oswego.edu -* Version 2.8.4 Wed May 27 09:56:23 2009 Doug Lea (dl at gee) - +* Version 2.8.6 Wed Aug 29 06:57:58 2012 Doug Lea Note: There may be an updated version of this malloc obtainable at ftp://gee.cs.oswego.edu/pub/misc/malloc.c Check before installing! @@ -19,7 +18,7 @@ compile-time and dynamic tuning options. For convenience, an include file for code using this malloc is at: - ftp://gee.cs.oswego.edu/pub/misc/malloc-2.8.4.h + ftp://gee.cs.oswego.edu/pub/misc/malloc-2.8.6.h You don't really need this .h file unless you call functions not defined in your system include files. The .h file contains only the excerpts from this file needed for using this malloc on ANSI C/C++ @@ -32,33 +31,592 @@ in this file to customize settings or to avoid overheads associated with library versions. +* Vital statistics: + + Supported pointer/size_t representation: 4 or 8 bytes + size_t MUST be an unsigned type of the same width as + pointers. (If you are using an ancient system that declares + size_t as a signed type, or need it to be a different width + than pointers, you can use a previous release of this malloc + (e.g. 2.7.2) supporting these.) + + Alignment: 8 bytes (minimum) + This suffices for nearly all current machines and C compilers. + However, you can define MALLOC_ALIGNMENT to be wider than this + if necessary (up to 128bytes), at the expense of using more space. + + Minimum overhead per allocated chunk: 4 or 8 bytes (if 4byte sizes) + 8 or 16 bytes (if 8byte sizes) + Each malloced chunk has a hidden word of overhead holding size + and status information, and additional cross-check word + if FOOTERS is defined. + + Minimum allocated size: 4-byte ptrs: 16 bytes (including overhead) + 8-byte ptrs: 32 bytes (including overhead) + + Even a request for zero bytes (i.e., malloc(0)) returns a + pointer to something of the minimum allocatable size. + The maximum overhead wastage (i.e., number of extra bytes + allocated than were requested in malloc) is less than or equal + to the minimum size, except for requests >= mmap_threshold that + are serviced via mmap(), where the worst case wastage is about + 32 bytes plus the remainder from a system page (the minimal + mmap unit); typically 4096 or 8192 bytes. + + Security: static-safe; optionally more or less + The "security" of malloc refers to the ability of malicious + code to accentuate the effects of errors (for example, freeing + space that is not currently malloc'ed or overwriting past the + ends of chunks) in code that calls malloc. This malloc + guarantees not to modify any memory locations below the base of + heap, i.e., static variables, even in the presence of usage + errors. The routines additionally detect most improper frees + and reallocs. All this holds as long as the static bookkeeping + for malloc itself is not corrupted by some other means. This + is only one aspect of security -- these checks do not, and + cannot, detect all possible programming errors. + + If FOOTERS is defined nonzero, then each allocated chunk + carries an additional check word to verify that it was malloced + from its space. These check words are the same within each + execution of a program using malloc, but differ across + executions, so externally crafted fake chunks cannot be + freed. This improves security by rejecting frees/reallocs that + could corrupt heap memory, in addition to the checks preventing + writes to statics that are always on. This may further improve + security at the expense of time and space overhead. (Note that + FOOTERS may also be worth using with MSPACES.) + + By default detected errors cause the program to abort (calling + "abort()"). You can override this to instead proceed past + errors by defining PROCEED_ON_ERROR. In this case, a bad free + has no effect, and a malloc that encounters a bad address + caused by user overwrites will ignore the bad address by + dropping pointers and indices to all known memory. This may + be appropriate for programs that should continue if at all + possible in the face of programming errors, although they may + run out of memory because dropped memory is never reclaimed. + + If you don't like either of these options, you can define + CORRUPTION_ERROR_ACTION and USAGE_ERROR_ACTION to do anything + else. And if if you are sure that your program using malloc has + no errors or vulnerabilities, you can define INSECURE to 1, + which might (or might not) provide a small performance improvement. + + It is also possible to limit the maximum total allocatable + space, using malloc_set_footprint_limit. This is not + designed as a security feature in itself (calls to set limits + are not screened or privileged), but may be useful as one + aspect of a secure implementation. + + Thread-safety: NOT thread-safe unless USE_LOCKS defined non-zero + When USE_LOCKS is defined, each public call to malloc, free, + etc is surrounded with a lock. By default, this uses a plain + pthread mutex, win32 critical section, or a spin-lock if if + available for the platform and not disabled by setting + USE_SPIN_LOCKS=0. However, if USE_RECURSIVE_LOCKS is defined, + recursive versions are used instead (which are not required for + base functionality but may be needed in layered extensions). + Using a global lock is not especially fast, and can be a major + bottleneck. It is designed only to provide minimal protection + in concurrent environments, and to provide a basis for + extensions. If you are using malloc in a concurrent program, + consider instead using nedmalloc + (http://www.nedprod.com/programs/portable/nedmalloc/) or + ptmalloc (See http://www.malloc.de), which are derived from + versions of this malloc. + + System requirements: Any combination of MORECORE and/or MMAP/MUNMAP + This malloc can use unix sbrk or any emulation (invoked using + the CALL_MORECORE macro) and/or mmap/munmap or any emulation + (invoked using CALL_MMAP/CALL_MUNMAP) to get and release system + memory. On most unix systems, it tends to work best if both + MORECORE and MMAP are enabled. On Win32, it uses emulations + based on VirtualAlloc. It also uses common C library functions + like memset. + + Compliance: I believe it is compliant with the Single Unix Specification + (See http://www.unix.org). Also SVID/XPG, ANSI C, and probably + others as well. + +* Overview of algorithms + + This is not the fastest, most space-conserving, most portable, or + most tunable malloc ever written. However it is among the fastest + while also being among the most space-conserving, portable and + tunable. Consistent balance across these factors results in a good + general-purpose allocator for malloc-intensive programs. + + In most ways, this malloc is a best-fit allocator. Generally, it + chooses the best-fitting existing chunk for a request, with ties + broken in approximately least-recently-used order. (This strategy + normally maintains low fragmentation.) However, for requests less + than 256bytes, it deviates from best-fit when there is not an + exactly fitting available chunk by preferring to use space adjacent + to that used for the previous small request, as well as by breaking + ties in approximately most-recently-used order. (These enhance + locality of series of small allocations.) And for very large requests + (>= 256Kb by default), it relies on system memory mapping + facilities, if supported. (This helps avoid carrying around and + possibly fragmenting memory used only for large chunks.) + + All operations (except malloc_stats and mallinfo) have execution + times that are bounded by a constant factor of the number of bits in + a size_t, not counting any clearing in calloc or copying in realloc, + or actions surrounding MORECORE and MMAP that have times + proportional to the number of non-contiguous regions returned by + system allocation routines, which is often just 1. In real-time + applications, you can optionally suppress segment traversals using + NO_SEGMENT_TRAVERSAL, which assures bounded execution even when + system allocators return non-contiguous spaces, at the typical + expense of carrying around more memory and increased fragmentation. + + The implementation is not very modular and seriously overuses + macros. Perhaps someday all C compilers will do as good a job + inlining modular code as can now be done by brute-force expansion, + but now, enough of them seem not to. + + Some compilers issue a lot of warnings about code that is + dead/unreachable only on some platforms, and also about intentional + uses of negation on unsigned types. All known cases of each can be + ignored. + + For a longer but out of date high-level description, see + http://gee.cs.oswego.edu/dl/html/malloc.html + +* MSPACES + If MSPACES is defined, then in addition to malloc, free, etc., + this file also defines mspace_malloc, mspace_free, etc. These + are versions of malloc routines that take an "mspace" argument + obtained using create_mspace, to control all internal bookkeeping. + If ONLY_MSPACES is defined, only these versions are compiled. + So if you would like to use this allocator for only some allocations, + and your system malloc for others, you can compile with + ONLY_MSPACES and then do something like... + static mspace mymspace = create_mspace(0,0); // for example + #define mymalloc(bytes) mspace_malloc(mymspace, bytes) + + (Note: If you only need one instance of an mspace, you can instead + use "USE_DL_PREFIX" to relabel the global malloc.) + + You can similarly create thread-local allocators by storing + mspaces as thread-locals. For example: + static __thread mspace tlms = 0; + void* tlmalloc(size_t bytes) { + if (tlms == 0) tlms = create_mspace(0, 0); + return mspace_malloc(tlms, bytes); + } + void tlfree(void* mem) { mspace_free(tlms, mem); } + + Unless FOOTERS is defined, each mspace is completely independent. + You cannot allocate from one and free to another (although + conformance is only weakly checked, so usage errors are not always + caught). If FOOTERS is defined, then each chunk carries around a tag + indicating its originating mspace, and frees are directed to their + originating spaces. Normally, this requires use of locks. + + ------------------------- Compile-time options --------------------------- + +Be careful in setting #define values for numerical constants of type +size_t. On some systems, literal values are not automatically extended +to size_t precision unless they are explicitly casted. You can also +use the symbolic values MAX_SIZE_T, SIZE_T_ONE, etc below. + +WIN32 default: defined if _WIN32 defined + Defining WIN32 sets up defaults for MS environment and compilers. + Otherwise defaults are for unix. Beware that there seem to be some + cases where this malloc might not be a pure drop-in replacement for + Win32 malloc: Random-looking failures from Win32 GDI API's (eg; + SetDIBits()) may be due to bugs in some video driver implementations + when pixel buffers are malloc()ed, and the region spans more than + one VirtualAlloc()ed region. Because dlmalloc uses a small (64Kb) + default granularity, pixel buffers may straddle virtual allocation + regions more often than when using the Microsoft allocator. You can + avoid this by using VirtualAlloc() and VirtualFree() for all pixel + buffers rather than using malloc(). If this is not possible, + recompile this malloc with a larger DEFAULT_GRANULARITY. Note: + in cases where MSC and gcc (cygwin) are known to differ on WIN32, + conditions use _MSC_VER to distinguish them. + +DLMALLOC_EXPORT default: extern + Defines how public APIs are declared. If you want to export via a + Windows DLL, you might define this as + #define DLMALLOC_EXPORT extern __declspec(dllexport) + If you want a POSIX ELF shared object, you might use + #define DLMALLOC_EXPORT extern __attribute__((visibility("default"))) + +MALLOC_ALIGNMENT default: (size_t)(2 * sizeof(void *)) + Controls the minimum alignment for malloc'ed chunks. It must be a + power of two and at least 8, even on machines for which smaller + alignments would suffice. It may be defined as larger than this + though. Note however that code and data structures are optimized for + the case of 8-byte alignment. + +MSPACES default: 0 (false) + If true, compile in support for independent allocation spaces. + This is only supported if HAVE_MMAP is true. + +ONLY_MSPACES default: 0 (false) + If true, only compile in mspace versions, not regular versions. + +USE_LOCKS default: 0 (false) + Causes each call to each public routine to be surrounded with + pthread or WIN32 mutex lock/unlock. (If set true, this can be + overridden on a per-mspace basis for mspace versions.) If set to a + non-zero value other than 1, locks are used, but their + implementation is left out, so lock functions must be supplied manually, + as described below. + +USE_SPIN_LOCKS default: 1 iff USE_LOCKS and spin locks available + If true, uses custom spin locks for locking. This is currently + supported only gcc >= 4.1, older gccs on x86 platforms, and recent + MS compilers. Otherwise, posix locks or win32 critical sections are + used. + +USE_RECURSIVE_LOCKS default: not defined + If defined nonzero, uses recursive (aka reentrant) locks, otherwise + uses plain mutexes. This is not required for malloc proper, but may + be needed for layered allocators such as nedmalloc. + +LOCK_AT_FORK default: not defined + If defined nonzero, performs pthread_atfork upon initialization + to initialize child lock while holding parent lock. The implementation + assumes that pthread locks (not custom locks) are being used. In other + cases, you may need to customize the implementation. + +FOOTERS default: 0 + If true, provide extra checking and dispatching by placing + information in the footers of allocated chunks. This adds + space and time overhead. + +INSECURE default: 0 + If true, omit checks for usage errors and heap space overwrites. + +USE_DL_PREFIX default: NOT defined + Causes compiler to prefix all public routines with the string 'dl'. + This can be useful when you only want to use this malloc in one part + of a program, using your regular system malloc elsewhere. + +MALLOC_INSPECT_ALL default: NOT defined + If defined, compiles malloc_inspect_all and mspace_inspect_all, that + perform traversal of all heap space. Unless access to these + functions is otherwise restricted, you probably do not want to + include them in secure implementations. + +ABORT default: defined as abort() + Defines how to abort on failed checks. On most systems, a failed + check cannot die with an "assert" or even print an informative + message, because the underlying print routines in turn call malloc, + which will fail again. Generally, the best policy is to simply call + abort(). It's not very useful to do more than this because many + errors due to overwriting will show up as address faults (null, odd + addresses etc) rather than malloc-triggered checks, so will also + abort. Also, most compilers know that abort() does not return, so + can better optimize code conditionally calling it. + +PROCEED_ON_ERROR default: defined as 0 (false) + Controls whether detected bad addresses cause them to bypassed + rather than aborting. If set, detected bad arguments to free and + realloc are ignored. And all bookkeeping information is zeroed out + upon a detected overwrite of freed heap space, thus losing the + ability to ever return it from malloc again, but enabling the + application to proceed. If PROCEED_ON_ERROR is defined, the + static variable malloc_corruption_error_count is compiled in + and can be examined to see if errors have occurred. This option + generates slower code than the default abort policy. + +DEBUG default: NOT defined + The DEBUG setting is mainly intended for people trying to modify + this code or diagnose problems when porting to new platforms. + However, it may also be able to better isolate user errors than just + using runtime checks. The assertions in the check routines spell + out in more detail the assumptions and invariants underlying the + algorithms. The checking is fairly extensive, and will slow down + execution noticeably. Calling malloc_stats or mallinfo with DEBUG + set will attempt to check every non-mmapped allocated and free chunk + in the course of computing the summaries. + +ABORT_ON_ASSERT_FAILURE default: defined as 1 (true) + Debugging assertion failures can be nearly impossible if your + version of the assert macro causes malloc to be called, which will + lead to a cascade of further failures, blowing the runtime stack. + ABORT_ON_ASSERT_FAILURE cause assertions failures to call abort(), + which will usually make debugging easier. + +MALLOC_FAILURE_ACTION default: sets errno to ENOMEM, or no-op on win32 + The action to take before "return 0" when malloc fails to be able to + return memory because there is none available. + +HAVE_MORECORE default: 1 (true) unless win32 or ONLY_MSPACES + True if this system supports sbrk or an emulation of it. + +MORECORE default: sbrk + The name of the sbrk-style system routine to call to obtain more + memory. See below for guidance on writing custom MORECORE + functions. The type of the argument to sbrk/MORECORE varies across + systems. It cannot be size_t, because it supports negative + arguments, so it is normally the signed type of the same width as + size_t (sometimes declared as "intptr_t"). It doesn't much matter + though. Internally, we only call it with arguments less than half + the max value of a size_t, which should work across all reasonable + possibilities, although sometimes generating compiler warnings. + +MORECORE_CONTIGUOUS default: 1 (true) if HAVE_MORECORE + If true, take advantage of fact that consecutive calls to MORECORE + with positive arguments always return contiguous increasing + addresses. This is true of unix sbrk. It does not hurt too much to + set it true anyway, since malloc copes with non-contiguities. + Setting it false when definitely non-contiguous saves time + and possibly wasted space it would take to discover this though. + +MORECORE_CANNOT_TRIM default: NOT defined + True if MORECORE cannot release space back to the system when given + negative arguments. This is generally necessary only if you are + using a hand-crafted MORECORE function that cannot handle negative + arguments. + +NO_SEGMENT_TRAVERSAL default: 0 + If non-zero, suppresses traversals of memory segments + returned by either MORECORE or CALL_MMAP. This disables + merging of segments that are contiguous, and selectively + releasing them to the OS if unused, but bounds execution times. + +HAVE_MMAP default: 1 (true) + True if this system supports mmap or an emulation of it. If so, and + HAVE_MORECORE is not true, MMAP is used for all system + allocation. If set and HAVE_MORECORE is true as well, MMAP is + primarily used to directly allocate very large blocks. It is also + used as a backup strategy in cases where MORECORE fails to provide + space from system. Note: A single call to MUNMAP is assumed to be + able to unmap memory that may have be allocated using multiple calls + to MMAP, so long as they are adjacent. + +HAVE_MREMAP default: 1 on linux, else 0 + If true realloc() uses mremap() to re-allocate large blocks and + extend or shrink allocation spaces. + +MMAP_CLEARS default: 1 except on WINCE. + True if mmap clears memory so calloc doesn't need to. This is true + for standard unix mmap using /dev/zero and on WIN32 except for WINCE. + +USE_BUILTIN_FFS default: 0 (i.e., not used) + Causes malloc to use the builtin ffs() function to compute indices. + Some compilers may recognize and intrinsify ffs to be faster than the + supplied C version. Also, the case of x86 using gcc is special-cased + to an asm instruction, so is already as fast as it can be, and so + this setting has no effect. Similarly for Win32 under recent MS compilers. + (On most x86s, the asm version is only slightly faster than the C version.) + +malloc_getpagesize default: derive from system includes, or 4096. + The system page size. To the extent possible, this malloc manages + memory from the system in page-size units. This may be (and + usually is) a function rather than a constant. This is ignored + if WIN32, where page size is determined using getSystemInfo during + initialization. + +USE_DEV_RANDOM default: 0 (i.e., not used) + Causes malloc to use /dev/random to initialize secure magic seed for + stamping footers. Otherwise, the current time is used. + +NO_MALLINFO default: 0 + If defined, don't compile "mallinfo". This can be a simple way + of dealing with mismatches between system declarations and + those in this file. + +MALLINFO_FIELD_TYPE default: size_t + The type of the fields in the mallinfo struct. This was originally + defined as "int" in SVID etc, but is more usefully defined as + size_t. The value is used only if HAVE_USR_INCLUDE_MALLOC_H is not set + +NO_MALLOC_STATS default: 0 + If defined, don't compile "malloc_stats". This avoids calls to + fprintf and bringing in stdio dependencies you might not want. + +REALLOC_ZERO_BYTES_FREES default: not defined + This should be set if a call to realloc with zero bytes should + be the same as a call to free. Some people think it should. Otherwise, + since this malloc returns a unique pointer for malloc(0), so does + realloc(p, 0). + +LACKS_UNISTD_H, LACKS_FCNTL_H, LACKS_SYS_PARAM_H, LACKS_SYS_MMAN_H +LACKS_STRINGS_H, LACKS_STRING_H, LACKS_SYS_TYPES_H, LACKS_ERRNO_H +LACKS_STDLIB_H LACKS_SCHED_H LACKS_TIME_H default: NOT defined unless on WIN32 + Define these if your system does not have these header files. + You might need to manually insert some of the declarations they provide. + +DEFAULT_GRANULARITY default: page size if MORECORE_CONTIGUOUS, + system_info.dwAllocationGranularity in WIN32, + otherwise 64K. + Also settable using mallopt(M_GRANULARITY, x) + The unit for allocating and deallocating memory from the system. On + most systems with contiguous MORECORE, there is no reason to + make this more than a page. However, systems with MMAP tend to + either require or encourage larger granularities. You can increase + this value to prevent system allocation functions to be called so + often, especially if they are slow. The value must be at least one + page and must be a power of two. Setting to 0 causes initialization + to either page size or win32 region size. (Note: In previous + versions of malloc, the equivalent of this option was called + "TOP_PAD") + +DEFAULT_TRIM_THRESHOLD default: 2MB + Also settable using mallopt(M_TRIM_THRESHOLD, x) + The maximum amount of unused top-most memory to keep before + releasing via malloc_trim in free(). Automatic trimming is mainly + useful in long-lived programs using contiguous MORECORE. Because + trimming via sbrk can be slow on some systems, and can sometimes be + wasteful (in cases where programs immediately afterward allocate + more large chunks) the value should be high enough so that your + overall system performance would improve by releasing this much + memory. As a rough guide, you might set to a value close to the + average size of a process (program) running on your system. + Releasing this much memory would allow such a process to run in + memory. Generally, it is worth tuning trim thresholds when a + program undergoes phases where several large chunks are allocated + and released in ways that can reuse each other's storage, perhaps + mixed with phases where there are no such chunks at all. The trim + value must be greater than page size to have any useful effect. To + disable trimming completely, you can set to MAX_SIZE_T. Note that the trick + some people use of mallocing a huge space and then freeing it at + program startup, in an attempt to reserve system memory, doesn't + have the intended effect under automatic trimming, since that memory + will immediately be returned to the system. + +DEFAULT_MMAP_THRESHOLD default: 256K + Also settable using mallopt(M_MMAP_THRESHOLD, x) + The request size threshold for using MMAP to directly service a + request. Requests of at least this size that cannot be allocated + using already-existing space will be serviced via mmap. (If enough + normal freed space already exists it is used instead.) Using mmap + segregates relatively large chunks of memory so that they can be + individually obtained and released from the host system. A request + serviced through mmap is never reused by any other request (at least + not directly; the system may just so happen to remap successive + requests to the same locations). Segregating space in this way has + the benefits that: Mmapped space can always be individually released + back to the system, which helps keep the system level memory demands + of a long-lived program low. Also, mapped memory doesn't become + `locked' between other chunks, as can happen with normally allocated + chunks, which means that even trimming via malloc_trim would not + release them. However, it has the disadvantage that the space + cannot be reclaimed, consolidated, and then used to service later + requests, as happens with normal chunks. The advantages of mmap + nearly always outweigh disadvantages for "large" chunks, but the + value of "large" may vary across systems. The default is an + empirically derived value that works well in most systems. You can + disable mmap by setting to MAX_SIZE_T. + +MAX_RELEASE_CHECK_RATE default: 4095 unless not HAVE_MMAP + The number of consolidated frees between checks to release + unused segments when freeing. When using non-contiguous segments, + especially with multiple mspaces, checking only for topmost space + doesn't always suffice to trigger trimming. To compensate for this, + free() will, with a period of MAX_RELEASE_CHECK_RATE (or the + current number of segments, if greater) try to release unused + segments to the OS when freeing chunks that result in + consolidation. The best value for this parameter is a compromise + between slowing down frees with relatively costly checks that + rarely trigger versus holding on to unused memory. To effectively + disable, set to MAX_SIZE_T. This may lead to a very slight speed + improvement at the expense of carrying around more memory. */ #include #include #include -struct malloc_chunk { - size_t prev_foot; /* Size of previous chunk (if free). */ - size_t head; /* Size and inuse bits. */ - struct malloc_chunk* fd; /* double links -- used only if free. */ - struct malloc_chunk* bk; -}; - -typedef struct malloc_chunk mchunk; -typedef struct malloc_chunk* mchunkptr; -typedef struct malloc_chunk* sbinptr; /* The type of bins of chunks */ -typedef unsigned int bindex_t; /* Described below */ -typedef unsigned int binmap_t; /* Described below */ -typedef unsigned int flag_t; /* The type of various bit flag sets */ +/* Version identifier to allow people to support multiple versions */ +#ifndef DLMALLOC_VERSION +#define DLMALLOC_VERSION 20806 +#endif /* DLMALLOC_VERSION */ +/* + malloc(size_t n) + Returns a pointer to a newly allocated chunk of at least n bytes, or + null if no space is available, in which case errno is set to ENOMEM + on ANSI C systems. + + If n is zero, malloc returns a minimum-sized chunk. (The minimum + size is 16 bytes on most 32bit systems, and 32 bytes on 64bit + systems.) Note that size_t is an unsigned type, so calls with + arguments that would be negative if signed are interpreted as + requests for huge amounts of space, which will often fail. The + maximum supported value of n differs across systems, but is in all + cases less than the maximum representable value of a size_t. +*/ + +/* + free(void* p) + Releases the chunk of memory pointed to by p, that had been previously + allocated using malloc or a related routine such as realloc. + It has no effect if p is null. If p was not malloced or already + freed, free(p) will by default cause the current program to abort. +*/ + +/* + calloc(size_t n_elements, size_t element_size); + Returns a pointer to n_elements * element_size bytes, with all locations + set to zero. +*/ + +/* + realloc(void* p, size_t n) + Returns a pointer to a chunk of size n that contains the same data + as does chunk p up to the minimum of (n, p's size) bytes, or null + if no space is available. + + The returned pointer may or may not be the same as p. The algorithm + prefers extending p in most cases when possible, otherwise it + employs the equivalent of a malloc-copy-free sequence. + + If p is null, realloc is equivalent to malloc. + + If space is not available, realloc returns null, errno is set (if on + ANSI) and p is NOT freed. + + if n is for fewer bytes than already held by p, the newly unused + space is lopped off and freed if possible. realloc with a size + argument of zero (re)allocates a minimum-sized chunk. + + The old unix realloc convention of allowing the last-free'd chunk + to be used as an argument to realloc is not supported. +*/ +/* + memalign(size_t alignment, size_t n); + Returns a pointer to a newly allocated chunk of n bytes, aligned + in accord with the alignment argument. + + The alignment argument should be a power of two. If the argument is + not a power of two, the nearest greater power is used. + 8-byte alignment is guaranteed by normal malloc calls, so don't + bother calling memalign with an argument of 8 or less. + + Overreliance on memalign is a sure way to fragment space. +*/ + + +#define DEBUG 1 + + + + + + + + + + + + +#define assert(x) + +#define MAX_SIZE_T (~(size_t)0) + +#define CALL_DIRECT_MMAP(s) MMAP_DEFAULT(s) /* ------------------- size_t and alignment properties -------------------- */ -/* The maximum possible size_t value has all bits set */ -#define MAX_SIZE_T (~(size_t)0) - /* The byte and bit size of a size_t */ #define SIZE_T_SIZE (sizeof(size_t)) #define SIZE_T_BITSIZE (sizeof(size_t) << 3) @@ -82,6 +640,8 @@ typedef unsigned int flag_t; /* The type of various bit flag sets */ #define EXTERN_BIT (8U) #define HAVE_MMAP 1 +#define HAVE_MORECORE 0 +#define MORECORE_CANNOT_TRIM 1 #define CALL_MMAP(s) MMAP_DEFAULT(s) #define CALL_MUNMAP(a, s) MUNMAP_DEFAULT((a), (s)) #define CALL_MREMAP(addr, osz, nsz, mv) MFAIL @@ -104,25 +664,220 @@ typedef unsigned int flag_t; /* The type of various bit flag sets */ ((((size_t)(A) & CHUNK_ALIGN_MASK) == 0)? 0 :\ ((MALLOC_ALIGNMENT - ((size_t)(A) & CHUNK_ALIGN_MASK)) & CHUNK_ALIGN_MASK)) +/* -------------------------- MMAP preliminaries ------------------------- */ +/* + If HAVE_MORECORE or HAVE_MMAP are false, we just define calls and + checks to fail so compiler optimizer can delete code rather than + using so many "#if"s. +*/ + + +/* MORECORE and MMAP must return MFAIL on failure */ #define MFAIL ((void*)(MAX_SIZE_T)) #define CMFAIL ((char*)(MFAIL)) /* defined for convenience */ -/* For sys_alloc, enough padding to ensure can malloc request on success */ -#define SYS_ALLOC_PADDING (TOP_FOOT_SIZE + MALLOC_ALIGNMENT) +#define should_trim(M,s) (0) + + + +/* --------------------------- Lock preliminaries ------------------------ */ /* - TOP_FOOT_SIZE is padding at the end of a segment, including space - that may be needed to place segment records and fenceposts when new - noncontiguous segments are added. + When locks are defined, there is one global lock, plus + one per-mspace lock. + + The global lock_ensures that mparams.magic and other unique + mparams values are initialized only once. It also protects + sequences of calls to MORECORE. In many cases sys_alloc requires + two calls, that should not be interleaved with calls by other + threads. This does not protect against direct calls to MORECORE + by other threads not using this lock, so there is still code to + cope the best we can on interference. + + Per-mspace locks surround calls to malloc, free, etc. + By default, locks are simple non-reentrant mutexes. + + Because lock-protected regions generally have bounded times, it is + OK to use the supplied simple spinlocks. Spinlocks are likely to + improve performance for lightly contended applications, but worsen + performance under heavy contention. + + If USE_LOCKS is > 1, the definitions of lock routines here are + bypassed, in which case you will need to define the type MLOCK_T, + and at least INITIAL_LOCK, DESTROY_LOCK, ACQUIRE_LOCK, RELEASE_LOCK + and TRY_LOCK. You must also declare a + static MLOCK_T malloc_global_mutex = { initialization values };. + */ -#define TOP_FOOT_SIZE\ - (align_offset(chunk2mem(0))+pad_request(sizeof(struct malloc_segment))+MIN_CHUNK_SIZE) + +static DEFINE_MUTEX(malloc_global_mutex); + +#define ACQUIRE_MALLOC_GLOBAL_LOCK() MutexLock(&malloc_global_mutex); +#define RELEASE_MALLOC_GLOBAL_LOCK() MutexUnlock(&malloc_global_mutex); + + +/* ----------------------- Chunk representations ------------------------ */ + +/* + (The following includes lightly edited explanations by Colin Plumb.) + + The malloc_chunk declaration below is misleading (but accurate and + necessary). It declares a "view" into memory allowing access to + necessary fields at known offsets from a given base. + + Chunks of memory are maintained using a `boundary tag' method as + originally described by Knuth. (See the paper by Paul Wilson + ftp://ftp.cs.utexas.edu/pub/garbage/allocsrv.ps for a survey of such + techniques.) Sizes of free chunks are stored both in the front of + each chunk and at the end. This makes consolidating fragmented + chunks into bigger chunks fast. The head fields also hold bits + representing whether chunks are free or in use. + + Here are some pictures to make it clearer. They are "exploded" to + show that the state of a chunk can be thought of as extending from + the high 31 bits of the head field of its header through the + prev_foot and PINUSE_BIT bit of the following chunk header. + + A chunk that's in use looks like: + + chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Size of previous chunk (if P = 0) | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ |P| + | Size of this chunk 1| +-+ + mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | | + +- -+ + | | + +- -+ + | : + +- size - sizeof(size_t) available payload bytes -+ + : | + chunk-> +- -+ + | | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ |1| + | Size of next chunk (may or may not be in use) | +-+ + mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + + And if it's free, it looks like this: + + chunk-> +- -+ + | User payload (must be in use, or we would have merged!) | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ |P| + | Size of this chunk 0| +-+ + mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Next pointer | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Prev pointer | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | : + +- size - sizeof(struct chunk) unused bytes -+ + : | + chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Size of this chunk | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ |0| + | Size of next chunk (must be in use, or we would have merged)| +-+ + mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | : + +- User payload -+ + : | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + |0| + +-+ + Note that since we always merge adjacent free chunks, the chunks + adjacent to a free chunk must be in use. + + Given a pointer to a chunk (which can be derived trivially from the + payload pointer) we can, in O(1) time, find out whether the adjacent + chunks are free, and if so, unlink them from the lists that they + are on and merge them with the current chunk. + + Chunks always begin on even word boundaries, so the mem portion + (which is returned to the user) is also on an even word boundary, and + thus at least double-word aligned. + + The P (PINUSE_BIT) bit, stored in the unused low-order bit of the + chunk size (which is always a multiple of two words), is an in-use + bit for the *previous* chunk. If that bit is *clear*, then the + word before the current chunk size contains the previous chunk + size, and can be used to find the front of the previous chunk. + The very first chunk allocated always has this bit set, preventing + access to non-existent (or non-owned) memory. If pinuse is set for + any given chunk, then you CANNOT determine the size of the + previous chunk, and might even get a memory addressing fault when + trying to do so. + + The C (CINUSE_BIT) bit, stored in the unused second-lowest bit of + the chunk size redundantly records whether the current chunk is + inuse (unless the chunk is mmapped). This redundancy enables usage + checks within free and realloc, and reduces indirection when freeing + and consolidating chunks. + + Each freshly allocated chunk must have both cinuse and pinuse set. + That is, each allocated chunk borders either a previously allocated + and still in-use chunk, or the base of its memory arena. This is + ensured by making all allocations from the `lowest' part of any + found chunk. Further, no free chunk physically borders another one, + so each free chunk is known to be preceded and followed by either + inuse chunks or the ends of memory. + + Note that the `foot' of the current chunk is actually represented + as the prev_foot of the NEXT chunk. This makes it easier to + deal with alignments etc but can be very confusing when trying + to extend or adapt this code. + + The exceptions to all this are + + 1. The special chunk `top' is the top-most available chunk (i.e., + the one bordering the end of available memory). It is treated + specially. Top is never included in any bin, is used only if + no other chunk is available, and is released back to the + system if it is very large (see M_TRIM_THRESHOLD). In effect, + the top chunk is treated as larger (and thus less well + fitting) than any other available chunk. The top chunk + doesn't update its trailing size field since there is no next + contiguous chunk that would have to index off it. However, + space is still allocated for it (TOP_FOOT_SIZE) to enable + separation or merging when space is extended. + + 3. Chunks allocated via mmap, have both cinuse and pinuse bits + cleared in their head fields. Because they are allocated + one-by-one, each must carry its own prev_foot field, which is + also used to hold the offset this chunk has within its mmapped + region, which is needed to preserve alignment. Each mmapped + chunk is trailed by the first two fields of a fake next-chunk + for sake of usage checks. + +*/ + +struct malloc_chunk { + size_t prev_foot; /* Size of previous chunk (if free). */ + size_t head; /* Size and inuse bits. */ + struct malloc_chunk* fd; /* double links -- used only if free. */ + struct malloc_chunk* bk; +}; + +typedef struct malloc_chunk mchunk; +typedef struct malloc_chunk* mchunkptr; +typedef struct malloc_chunk* sbinptr; /* The type of bins of chunks */ +typedef unsigned int bindex_t; /* Described below */ +typedef unsigned int binmap_t; /* Described below */ +typedef unsigned int flag_t; /* The type of various bit flag sets */ /* ------------------- Chunks sizes and alignments ----------------------- */ #define MCHUNK_SIZE (sizeof(mchunk)) +#if FOOTERS +#define CHUNK_OVERHEAD (TWO_SIZE_T_SIZES) +#else /* FOOTERS */ +#define CHUNK_OVERHEAD (SIZE_T_SIZE) +#endif /* FOOTERS */ + /* MMapped chunks need a second word of overhead ... */ #define MMAP_CHUNK_OVERHEAD (TWO_SIZE_T_SIZES) /* ... and additional padding for fake next-chunk at foot */ @@ -150,6 +905,7 @@ typedef unsigned int flag_t; /* The type of various bit flag sets */ #define request2size(req) \ (((req) < MIN_REQUEST)? MIN_CHUNK_SIZE : pad_request(req)) + /* ------------------ Operations on head and foot fields ----------------- */ /* @@ -172,12 +928,15 @@ typedef unsigned int flag_t; /* The type of various bit flag sets */ /* extraction of fields from head words */ #define cinuse(p) ((p)->head & CINUSE_BIT) #define pinuse(p) ((p)->head & PINUSE_BIT) +#define flag4inuse(p) ((p)->head & FLAG4_BIT) #define is_inuse(p) (((p)->head & INUSE_BITS) != PINUSE_BIT) #define is_mmapped(p) (((p)->head & INUSE_BITS) == 0) #define chunksize(p) ((p)->head & ~(FLAG_BITS)) #define clear_pinuse(p) ((p)->head &= ~PINUSE_BIT) +#define set_flag4(p) ((p)->head |= FLAG4_BIT) +#define clear_flag4(p) ((p)->head &= ~FLAG4_BIT) /* Treat space at ptr +/- offset as a chunk */ #define chunk_plus_offset(p, s) ((mchunkptr)(((char*)(p)) + (s))) @@ -190,6 +949,10 @@ typedef unsigned int flag_t; /* The type of various bit flag sets */ /* extract next chunk's pinuse bit */ #define next_pinuse(p) ((next_chunk(p)->head) & PINUSE_BIT) +/* Get/set size at footer */ +#define get_foot(p, s) (((mchunkptr)((char*)(p) + (s)))->prev_foot) +#define set_foot(p, s) (((mchunkptr)((char*)(p) + (s)))->prev_foot = (s)) + /* Set size, pinuse bit, and foot */ #define set_size_and_pinuse_of_free_chunk(p, s)\ ((p)->head = (s|PINUSE_BIT), set_foot(p, s)) @@ -202,6 +965,103 @@ typedef unsigned int flag_t; /* The type of various bit flag sets */ #define overhead_for(p)\ (is_mmapped(p)? MMAP_CHUNK_OVERHEAD : CHUNK_OVERHEAD) +/* Return true if malloced space is not necessarily cleared */ +#if MMAP_CLEARS +#define calloc_must_clear(p) (!is_mmapped(p)) +#else /* MMAP_CLEARS */ +#define calloc_must_clear(p) (1) +#endif /* MMAP_CLEARS */ + +/* ---------------------- Overlaid data structures ----------------------- */ + +/* + When chunks are not in use, they are treated as nodes of either + lists or trees. + + "Small" chunks are stored in circular doubly-linked lists, and look + like this: + + chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Size of previous chunk | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + `head:' | Size of chunk, in bytes |P| + mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Forward pointer to next chunk in list | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Back pointer to previous chunk in list | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Unused space (may be 0 bytes long) . + . . + . | +nextchunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + `foot:' | Size of chunk, in bytes | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + + Larger chunks are kept in a form of bitwise digital trees (aka + tries) keyed on chunksizes. Because malloc_tree_chunks are only for + free chunks greater than 256 bytes, their size doesn't impose any + constraints on user chunk sizes. Each node looks like: + + chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Size of previous chunk | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + `head:' | Size of chunk, in bytes |P| + mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Forward pointer to next chunk of same size | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Back pointer to previous chunk of same size | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Pointer to left child (child[0]) | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Pointer to right child (child[1]) | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Pointer to parent | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | bin index of this chunk | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Unused space . + . | +nextchunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + `foot:' | Size of chunk, in bytes | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + + Each tree holding treenodes is a tree of unique chunk sizes. Chunks + of the same size are arranged in a circularly-linked list, with only + the oldest chunk (the next to be used, in our FIFO ordering) + actually in the tree. (Tree members are distinguished by a non-null + parent pointer.) If a chunk with the same size an an existing node + is inserted, it is linked off the existing node using pointers that + work in the same way as fd/bk pointers of small chunks. + + Each tree contains a power of 2 sized range of chunk sizes (the + smallest is 0x100 <= x < 0x180), which is is divided in half at each + tree level, with the chunks in the smaller half of the range (0x100 + <= x < 0x140 for the top nose) in the left subtree and the larger + half (0x140 <= x < 0x180) in the right subtree. This is, of course, + done by inspecting individual bits. + + Using these rules, each node's left subtree contains all smaller + sizes than its right subtree. However, the node at the root of each + subtree has no particular ordering relationship to either. (The + dividing line between the subtree sizes is based on trie relation.) + If we remove the last chunk of a given size from the interior of the + tree, we need to replace it with a leaf node. The tree ordering + rules permit a node to be replaced by any leaf below it. + + The smallest chunk in a tree (a common operation in a best-fit + allocator) can be found by walking a path to the leftmost leaf in + the tree. Unlike a usual binary tree, where we follow left child + pointers until we reach a null, here we follow the right child + pointer any time the left one is null, until we reach a leaf with + both child pointers null. The smallest chunk in the tree will be + somewhere along that path. + + The worst case number of steps to add, find, or remove a node is + bounded by the number of bits differentiating chunks within + bins. Under current bin calculations, this ranges from 6 up to 21 + (for 32 bit sizes) or up to 53 (for 64 bit sizes). The typical case + is of course much better. +*/ struct malloc_tree_chunk { /* The first four fields must be compatible with malloc_chunk */ @@ -222,6 +1082,62 @@ typedef struct malloc_tree_chunk* tbinptr; /* The type of bins of trees */ /* A little helper macro for trees */ #define leftmost_child(t) ((t)->child[0] != 0? (t)->child[0] : (t)->child[1]) +/* ----------------------------- Segments -------------------------------- */ + +/* + Each malloc space may include non-contiguous segments, held in a + list headed by an embedded malloc_segment record representing the + top-most space. Segments also include flags holding properties of + the space. Large chunks that are directly allocated by mmap are not + included in this list. They are instead independently created and + destroyed without otherwise keeping track of them. + + Segment management mainly comes into play for spaces allocated by + MMAP. Any call to MMAP might or might not return memory that is + adjacent to an existing segment. MORECORE normally contiguously + extends the current space, so this space is almost always adjacent, + which is simpler and faster to deal with. (This is why MORECORE is + used preferentially to MMAP when both are available -- see + sys_alloc.) When allocating using MMAP, we don't use any of the + hinting mechanisms (inconsistently) supported in various + implementations of unix mmap, or distinguish reserving from + committing memory. Instead, we just ask for space, and exploit + contiguity when we get it. It is probably possible to do + better than this on some systems, but no general scheme seems + to be significantly better. + + Management entails a simpler variant of the consolidation scheme + used for chunks to reduce fragmentation -- new adjacent memory is + normally prepended or appended to an existing segment. However, + there are limitations compared to chunk consolidation that mostly + reflect the fact that segment processing is relatively infrequent + (occurring only when getting memory from system) and that we + don't expect to have huge numbers of segments: + + * Segments are not indexed, so traversal requires linear scans. (It + would be possible to index these, but is not worth the extra + overhead and complexity for most programs on most platforms.) + * New segments are only appended to old ones when holding top-most + memory; if they cannot be prepended to others, they are held in + different segments. + + Except for the top-most segment of an mstate, each segment record + is kept at the tail of its segment. Segments are added by pushing + segment records onto the list headed by &mstate.seg for the + containing mstate. + + Segment flags control allocation/merge/deallocation policies: + * If EXTERN_BIT set, then we did not allocate this segment, + and so should not try to deallocate or merge with others. + (This currently holds only for the initial segment passed + into create_mspace_with_base.) + * If USE_MMAP_BIT set, the segment may be merged with + other surrounding mmapped segments and trimmed/de-allocated + using munmap. + * If neither bit is set, then the segment was obtained using + MORECORE so can be merged with surrounding MORECORE'd segments + and deallocated/trimmed using MORECORE with negative arguments. +*/ struct malloc_segment { char* base; /* base address */ @@ -299,6 +1215,9 @@ typedef struct malloc_segment* msegmentptr; Magic tag A cross-check field that should always hold same value as mparams.magic. + Max allowed footprint + The maximum allowed bytes to allocate from system (zero means no limit) + Flags Bits recording whether to use MMAP, locks, or contiguous MORECORE @@ -308,7 +1227,7 @@ typedef struct malloc_segment* msegmentptr; Trim support Fields holding the amount of unused topmost memory that should trigger - timming, and a counter to force periodic scanning to release unused + trimming, and a counter to force periodic scanning to release unused non-topmost segments. Locking @@ -345,6 +1264,7 @@ struct malloc_state { tbinptr treebins[NTREEBINS]; size_t footprint; size_t max_footprint; + size_t footprint_limit; /* zero means no limit */ flag_t mflags; struct mutex lock; /* locate lock among fields that rarely change */ msegment seg; @@ -363,9 +1283,8 @@ typedef struct malloc_state* mstate; also serves as an initialization flag. */ -struct malloc_params -{ - volatile size_t magic; +struct malloc_params { + size_t magic; size_t page_size; size_t granularity; size_t mmap_threshold; @@ -375,6 +1294,7 @@ struct malloc_params static struct malloc_params mparams; +/* Ensure mparams initialized */ #define ensure_initialization() (void)(mparams.magic != 0 || init_mparams()) static struct malloc_state _gm_; @@ -383,22 +1303,143 @@ static struct malloc_state _gm_; #define is_initialized(M) ((M)->top != 0) +/* -------------------------- system alloc setup ------------------------- */ -//struct mutex malloc_global_mutex; +/* Operations on mflags */ -static DEFINE_MUTEX(malloc_global_mutex); +#define use_lock(M) ((M)->mflags & USE_LOCK_BIT) +#define enable_lock(M) ((M)->mflags |= USE_LOCK_BIT) +#if USE_LOCKS +#define disable_lock(M) ((M)->mflags &= ~USE_LOCK_BIT) +#else +#define disable_lock(M) +#endif -#define ACQUIRE_MALLOC_GLOBAL_LOCK() MutexLock(&malloc_global_mutex); -#define RELEASE_MALLOC_GLOBAL_LOCK() MutexUnlock(&malloc_global_mutex); +#define use_mmap(M) ((M)->mflags & USE_MMAP_BIT) +#define enable_mmap(M) ((M)->mflags |= USE_MMAP_BIT) +#if HAVE_MMAP +#define disable_mmap(M) ((M)->mflags &= ~USE_MMAP_BIT) +#else +#define disable_mmap(M) +#endif + +#define use_noncontiguous(M) ((M)->mflags & USE_NONCONTIGUOUS_BIT) +#define disable_contiguous(M) ((M)->mflags |= USE_NONCONTIGUOUS_BIT) + +#define set_lock(M,L)\ + ((M)->mflags = (L)?\ + ((M)->mflags | USE_LOCK_BIT) :\ + ((M)->mflags & ~USE_LOCK_BIT)) + +/* page-align a size */ +#define page_align(S)\ + (((S) + (mparams.page_size - SIZE_T_ONE)) & ~(mparams.page_size - SIZE_T_ONE)) + +/* granularity-align a size */ +#define granularity_align(S)\ + (((S) + (mparams.granularity - SIZE_T_ONE))\ + & ~(mparams.granularity - SIZE_T_ONE)) + + +/* For mmap, use granularity alignment on windows, else page-align */ +#ifdef WIN32 +#define mmap_align(S) granularity_align(S) +#else +#define mmap_align(S) page_align(S) +#endif + +/* For sys_alloc, enough padding to ensure can malloc request on success */ +#define SYS_ALLOC_PADDING (TOP_FOOT_SIZE + MALLOC_ALIGNMENT) + +#define is_page_aligned(S)\ + (((size_t)(S) & (mparams.page_size - SIZE_T_ONE)) == 0) +#define is_granularity_aligned(S)\ + (((size_t)(S) & (mparams.granularity - SIZE_T_ONE)) == 0) + +/* True if segment S holds address A */ +#define segment_holds(S, A)\ + ((char*)(A) >= S->base && (char*)(A) < S->base + S->size) + +/* Return segment holding given address */ +static msegmentptr segment_holding(mstate m, char* addr) { + msegmentptr sp = &m->seg; + for (;;) { + if (addr >= sp->base && addr < sp->base + sp->size) + return sp; + if ((sp = sp->next) == 0) + return 0; + } +} + +/* Return true if segment contains a segment link */ +static int has_segment_link(mstate m, msegmentptr ss) { + msegmentptr sp = &m->seg; + for (;;) { + if ((char*)sp >= ss->base && (char*)sp < ss->base + ss->size) + return 1; + if ((sp = sp->next) == 0) + return 0; + } +} + + +/* + TOP_FOOT_SIZE is padding at the end of a segment, including space + that may be needed to place segment records and fenceposts when new + noncontiguous segments are added. +*/ +#define TOP_FOOT_SIZE\ + (align_offset(chunk2mem(0))+pad_request(sizeof(struct malloc_segment))+MIN_CHUNK_SIZE) + + +/* ------------------------------- Hooks -------------------------------- */ + +/* + PREACTION should be defined to return 0 on success, and nonzero on + failure. If you are not using locking, you can redefine these to do + anything you like. +*/ #define PREACTION(M) ( MutexLock(&(M)->lock)) #define POSTACTION(M) { MutexUnlock(&(M)->lock); } +/* -------------------------- Debugging setup ---------------------------- */ + +#if ! DEBUG + +#define check_free_chunk(M,P) +#define check_inuse_chunk(M,P) +#define check_malloced_chunk(M,P,N) +#define check_mmapped_chunk(M,P) +#define check_malloc_state(M) +#define check_top_chunk(M,P) + +#else /* DEBUG */ +#define check_free_chunk(M,P) do_check_free_chunk(M,P) +#define check_inuse_chunk(M,P) do_check_inuse_chunk(M,P) +#define check_top_chunk(M,P) do_check_top_chunk(M,P) +#define check_malloced_chunk(M,P,N) do_check_malloced_chunk(M,P,N) +#define check_mmapped_chunk(M,P) do_check_mmapped_chunk(M,P) +#define check_malloc_state(M) do_check_malloc_state(M) + +static void do_check_any_chunk(mstate m, mchunkptr p); +static void do_check_top_chunk(mstate m, mchunkptr p); +static void do_check_mmapped_chunk(mstate m, mchunkptr p); +static void do_check_inuse_chunk(mstate m, mchunkptr p); +static void do_check_free_chunk(mstate m, mchunkptr p); +static void do_check_malloced_chunk(mstate m, void* mem, size_t s); +static void do_check_tree(mstate m, tchunkptr t); +static void do_check_treebin(mstate m, bindex_t i); +static void do_check_smallbin(mstate m, bindex_t i); +static void do_check_malloc_state(mstate m); +static int bin_find(mstate m, mchunkptr x); +static size_t traverse_and_check(mstate m); +#endif /* DEBUG */ /* ---------------------------- Indexing Bins ---------------------------- */ #define is_small(s) (((s) >> SMALLBIN_SHIFT) < NSMALLBINS) -#define small_index(s) ((s) >> SMALLBIN_SHIFT) +#define small_index(s) (bindex_t)((s) >> SMALLBIN_SHIFT) #define small_index2size(i) ((i) << SMALLBIN_SHIFT) #define MIN_SMALL_INDEX (small_index(MIN_CHUNK_SIZE)) @@ -406,7 +1447,6 @@ static DEFINE_MUTEX(malloc_global_mutex); #define smallbin_at(M, i) ((sbinptr)((char*)&((M)->smallbins[(i)<<1]))) #define treebin_at(M,i) (&((M)->treebins[i])) - #define compute_tree_index(S, I)\ {\ unsigned int X = S >> TREEBIN_SHIFT;\ @@ -415,12 +1455,13 @@ static DEFINE_MUTEX(malloc_global_mutex); else if (X > 0xFFFF)\ I = NTREEBINS-1;\ else {\ - unsigned int K;\ - __asm__("bsrl\t%1, %0\n\t" : "=r" (K) : "g" (X));\ + unsigned int K = (unsigned) sizeof(X)*__CHAR_BIT__ - 1 - (unsigned) __builtin_clz(X); \ I = (bindex_t)((K << 1) + ((S >> (K + (TREEBIN_SHIFT-1)) & 1)));\ }\ } + + /* Bit representing maximum resolved size in a treebin at i */ #define bit_for_tree_index(i) \ (i == NTREEBINS-1)? (SIZE_T_BITSIZE-1) : (((i) >> 1) + TREEBIN_SHIFT - 2) @@ -459,23 +1500,82 @@ static DEFINE_MUTEX(malloc_global_mutex); /* mask with all bits to left of or equal to least bit of x on */ #define same_or_left_bits(x) ((x) | -(x)) - -/* index corresponding to given bit. Use x86 asm if possible */ - #define compute_bit2idx(X, I)\ {\ unsigned int J;\ - __asm__("bsfl\t%1, %0\n\t" : "=r" (J) : "g" (X));\ + J = __builtin_ctz(X); \ I = (bindex_t)J;\ } +/* ----------------------- Runtime Check Support ------------------------- */ + +/* + For security, the main invariant is that malloc/free/etc never + writes to a static address other than malloc_state, unless static + malloc_state itself has been corrupted, which cannot occur via + malloc (because of these checks). In essence this means that we + believe all pointers, sizes, maps etc held in malloc_state, but + check all of those linked or offsetted from other embedded data + structures. These checks are interspersed with main code in a way + that tends to minimize their run-time cost. + + When FOOTERS is defined, in addition to range checking, we also + verify footer fields of inuse chunks, which can be used guarantee + that the mstate controlling malloc/free is intact. This is a + streamlined version of the approach described by William Robertson + et al in "Run-time Detection of Heap-based Overflows" LISA'03 + http://www.usenix.org/events/lisa03/tech/robertson.html The footer + of an inuse chunk holds the xor of its mstate and a random seed, + that is checked upon calls to free() and realloc(). This is + (probabalistically) unguessable from outside the program, but can be + computed by any code successfully malloc'ing any chunk, so does not + itself provide protection against code that has already broken + security through some other means. Unlike Robertson et al, we + always dynamically check addresses of all offset chunks (previous, + next, etc). This turns out to be cheaper than relying on hashes. +*/ + +#if !INSECURE +/* Check if address a is at least as high as any from MORECORE or MMAP */ +#define ok_address(M, a) ((char*)(a) >= (M)->least_addr) +/* Check if address of next chunk n is higher than base chunk p */ +#define ok_next(p, n) ((char*)(p) < (char*)(n)) +/* Check if p has inuse status */ +#define ok_inuse(p) is_inuse(p) +/* Check if p has its pinuse bit on */ +#define ok_pinuse(p) pinuse(p) + +#else /* !INSECURE */ +#define ok_address(M, a) (1) +#define ok_next(b, n) (1) +#define ok_inuse(p) (1) +#define ok_pinuse(p) (1) +#endif /* !INSECURE */ + +#if (FOOTERS && !INSECURE) +/* Check if (alleged) mstate m has expected magic field */ +#define ok_magic(M) ((M)->magic == mparams.magic) +#else /* (FOOTERS && !INSECURE) */ +#define ok_magic(M) (1) +#endif /* (FOOTERS && !INSECURE) */ + +/* In gcc, use __builtin_expect to minimize impact of checks */ +#if !INSECURE +#if defined(__GNUC__) && __GNUC__ >= 3 +#define RTCHECK(e) __builtin_expect(e, 1) +#else /* GNUC */ +#define RTCHECK(e) (e) +#endif /* GNUC */ +#else /* !INSECURE */ +#define RTCHECK(e) (1) +#endif /* !INSECURE */ + +/* macros to set up inuse chunks with or without footers */ + +#if !FOOTERS #define mark_inuse_foot(M,p,s) -/* Get/set size at footer */ -#define get_foot(p, s) (((mchunkptr)((char*)(p) + (s)))->prev_foot) -#define set_foot(p, s) (((mchunkptr)((char*)(p) + (s)))->prev_foot = (s)) - /* Macros for setting head/foot of non-mmapped chunks */ /* Set cinuse bit and pinuse bit of next chunk */ @@ -492,25 +1592,344 @@ static DEFINE_MUTEX(malloc_global_mutex); #define set_size_and_pinuse_of_inuse_chunk(M, p, s)\ ((p)->head = (s|PINUSE_BIT|CINUSE_BIT)) +#else /* FOOTERS */ -#define assert(x) -#define RTCHECK(e) __builtin_expect(e, 1) +/* Set foot of inuse chunk to be xor of mstate and seed */ +#define mark_inuse_foot(M,p,s)\ + (((mchunkptr)((char*)(p) + (s)))->prev_foot = ((size_t)(M) ^ mparams.magic)) -#define check_free_chunk(M,P) -#define check_inuse_chunk(M,P) -#define check_malloced_chunk(M,P,N) -#define check_mmapped_chunk(M,P) -#define check_malloc_state(M) -#define check_top_chunk(M,P) +#define get_mstate_for(p)\ + ((mstate)(((mchunkptr)((char*)(p) +\ + (chunksize(p))))->prev_foot ^ mparams.magic)) -/* Check if address a is at least as high as any from MORECORE or MMAP */ -#define ok_address(M, a) ((char*)(a) >= (M)->least_addr) -/* Check if address of next chunk n is higher than base chunk p */ -#define ok_next(p, n) ((char*)(p) < (char*)(n)) -/* Check if p has inuse status */ -#define ok_inuse(p) is_inuse(p) -/* Check if p has its pinuse bit on */ -#define ok_pinuse(p) pinuse(p) +#define set_inuse(M,p,s)\ + ((p)->head = (((p)->head & PINUSE_BIT)|s|CINUSE_BIT),\ + (((mchunkptr)(((char*)(p)) + (s)))->head |= PINUSE_BIT), \ + mark_inuse_foot(M,p,s)) + +#define set_inuse_and_pinuse(M,p,s)\ + ((p)->head = (s|PINUSE_BIT|CINUSE_BIT),\ + (((mchunkptr)(((char*)(p)) + (s)))->head |= PINUSE_BIT),\ + mark_inuse_foot(M,p,s)) + +#define set_size_and_pinuse_of_inuse_chunk(M, p, s)\ + ((p)->head = (s|PINUSE_BIT|CINUSE_BIT),\ + mark_inuse_foot(M, p, s)) + +#endif /* !FOOTERS */ + +/* ---------------------------- setting mparams -------------------------- */ + +#if LOCK_AT_FORK +static void pre_fork(void) { ACQUIRE_LOCK(&(gm)->mutex); } +static void post_fork_parent(void) { RELEASE_LOCK(&(gm)->mutex); } +static void post_fork_child(void) { INITIAL_LOCK(&(gm)->mutex); } +#endif /* LOCK_AT_FORK */ + +/* Initialize mparams */ +static int init_mparams(void) { + + ACQUIRE_MALLOC_GLOBAL_LOCK(); + if (mparams.magic == 0) { + size_t magic; + size_t psize; + size_t gsize; + + psize = 4096; + gsize = ((DEFAULT_GRANULARITY != 0)? DEFAULT_GRANULARITY : psize); + + mparams.granularity = gsize; + mparams.page_size = psize; + mparams.mmap_threshold = DEFAULT_MMAP_THRESHOLD; + mparams.trim_threshold = DEFAULT_TRIM_THRESHOLD; + mparams.default_mflags = USE_LOCK_BIT|USE_MMAP_BIT|USE_NONCONTIGUOUS_BIT; + + /* Set up lock for main malloc area */ + gm->mflags = mparams.default_mflags; + MutexInit(&gm->lock); + + { + magic = (size_t)&magic ^ (size_t)0x55555555U; + magic |= (size_t)8U; /* ensure nonzero */ + magic &= ~(size_t)7U; /* improve chances of fault for bad values */ + /* Until memory modes commonly available, use volatile-write */ + (*(volatile size_t *)(&(mparams.magic))) = magic; + } + } + + RELEASE_MALLOC_GLOBAL_LOCK(); + return 1; +} + + +#if DEBUG +/* ------------------------- Debugging Support --------------------------- */ + +/* Check properties of any chunk, whether free, inuse, mmapped etc */ +static void do_check_any_chunk(mstate m, mchunkptr p) { + assert((is_aligned(chunk2mem(p))) || (p->head == FENCEPOST_HEAD)); + assert(ok_address(m, p)); +} + +/* Check properties of top chunk */ +static void do_check_top_chunk(mstate m, mchunkptr p) { + msegmentptr sp = segment_holding(m, (char*)p); + size_t sz = p->head & ~INUSE_BITS; /* third-lowest bit can be set! */ + assert(sp != 0); + assert((is_aligned(chunk2mem(p))) || (p->head == FENCEPOST_HEAD)); + assert(ok_address(m, p)); + assert(sz == m->topsize); + assert(sz > 0); + assert(sz == ((sp->base + sp->size) - (char*)p) - TOP_FOOT_SIZE); + assert(pinuse(p)); + assert(!pinuse(chunk_plus_offset(p, sz))); +} + +/* Check properties of (inuse) mmapped chunks */ +static void do_check_mmapped_chunk(mstate m, mchunkptr p) { + size_t sz = chunksize(p); + size_t len = (sz + (p->prev_foot) + MMAP_FOOT_PAD); + assert(is_mmapped(p)); + assert(use_mmap(m)); + assert((is_aligned(chunk2mem(p))) || (p->head == FENCEPOST_HEAD)); + assert(ok_address(m, p)); + assert(!is_small(sz)); + assert((len & (mparams.page_size-SIZE_T_ONE)) == 0); + assert(chunk_plus_offset(p, sz)->head == FENCEPOST_HEAD); + assert(chunk_plus_offset(p, sz+SIZE_T_SIZE)->head == 0); +} + +/* Check properties of inuse chunks */ +static void do_check_inuse_chunk(mstate m, mchunkptr p) { + do_check_any_chunk(m, p); + assert(is_inuse(p)); + assert(next_pinuse(p)); + /* If not pinuse and not mmapped, previous chunk has OK offset */ + assert(is_mmapped(p) || pinuse(p) || next_chunk(prev_chunk(p)) == p); + if (is_mmapped(p)) + do_check_mmapped_chunk(m, p); +} + +/* Check properties of free chunks */ +static void do_check_free_chunk(mstate m, mchunkptr p) { + size_t sz = chunksize(p); + mchunkptr next = chunk_plus_offset(p, sz); + do_check_any_chunk(m, p); + assert(!is_inuse(p)); + assert(!next_pinuse(p)); + assert (!is_mmapped(p)); + if (p != m->dv && p != m->top) { + if (sz >= MIN_CHUNK_SIZE) { + assert((sz & CHUNK_ALIGN_MASK) == 0); + assert(is_aligned(chunk2mem(p))); + assert(next->prev_foot == sz); + assert(pinuse(p)); + assert (next == m->top || is_inuse(next)); + assert(p->fd->bk == p); + assert(p->bk->fd == p); + } + else /* markers are always of size SIZE_T_SIZE */ + assert(sz == SIZE_T_SIZE); + } +} + +/* Check properties of malloced chunks at the point they are malloced */ +static void do_check_malloced_chunk(mstate m, void* mem, size_t s) { + if (mem != 0) { + mchunkptr p = mem2chunk(mem); + size_t sz = p->head & ~INUSE_BITS; + do_check_inuse_chunk(m, p); + assert((sz & CHUNK_ALIGN_MASK) == 0); + assert(sz >= MIN_CHUNK_SIZE); + assert(sz >= s); + /* unless mmapped, size is less than MIN_CHUNK_SIZE more than request */ + assert(is_mmapped(p) || sz < (s + MIN_CHUNK_SIZE)); + } +} + +/* Check a tree and its subtrees. */ +static void do_check_tree(mstate m, tchunkptr t) { + tchunkptr head = 0; + tchunkptr u = t; + bindex_t tindex = t->index; + size_t tsize = chunksize(t); + bindex_t idx; + compute_tree_index(tsize, idx); + assert(tindex == idx); + assert(tsize >= MIN_LARGE_SIZE); + assert(tsize >= minsize_for_tree_index(idx)); + assert((idx == NTREEBINS-1) || (tsize < minsize_for_tree_index((idx+1)))); + + do { /* traverse through chain of same-sized nodes */ + do_check_any_chunk(m, ((mchunkptr)u)); + assert(u->index == tindex); + assert(chunksize(u) == tsize); + assert(!is_inuse(u)); + assert(!next_pinuse(u)); + assert(u->fd->bk == u); + assert(u->bk->fd == u); + if (u->parent == 0) { + assert(u->child[0] == 0); + assert(u->child[1] == 0); + } + else { + assert(head == 0); /* only one node on chain has parent */ + head = u; + assert(u->parent != u); + assert (u->parent->child[0] == u || + u->parent->child[1] == u || + *((tbinptr*)(u->parent)) == u); + if (u->child[0] != 0) { + assert(u->child[0]->parent == u); + assert(u->child[0] != u); + do_check_tree(m, u->child[0]); + } + if (u->child[1] != 0) { + assert(u->child[1]->parent == u); + assert(u->child[1] != u); + do_check_tree(m, u->child[1]); + } + if (u->child[0] != 0 && u->child[1] != 0) { + assert(chunksize(u->child[0]) < chunksize(u->child[1])); + } + } + u = u->fd; + } while (u != t); + assert(head != 0); +} + +/* Check all the chunks in a treebin. */ +static void do_check_treebin(mstate m, bindex_t i) { + tbinptr* tb = treebin_at(m, i); + tchunkptr t = *tb; + int empty = (m->treemap & (1U << i)) == 0; + if (t == 0) + assert(empty); + if (!empty) + do_check_tree(m, t); +} + +/* Check all the chunks in a smallbin. */ +static void do_check_smallbin(mstate m, bindex_t i) { + sbinptr b = smallbin_at(m, i); + mchunkptr p = b->bk; + unsigned int empty = (m->smallmap & (1U << i)) == 0; + if (p == b) + assert(empty); + if (!empty) { + for (; p != b; p = p->bk) { + size_t size = chunksize(p); + mchunkptr q; + /* each chunk claims to be free */ + do_check_free_chunk(m, p); + /* chunk belongs in bin */ + assert(small_index(size) == i); + assert(p->bk == b || chunksize(p->bk) == chunksize(p)); + /* chunk is followed by an inuse chunk */ + q = next_chunk(p); + if (q->head != FENCEPOST_HEAD) + do_check_inuse_chunk(m, q); + } + } +} + +/* Find x in a bin. Used in other check functions. */ +static int bin_find(mstate m, mchunkptr x) { + size_t size = chunksize(x); + if (is_small(size)) { + bindex_t sidx = small_index(size); + sbinptr b = smallbin_at(m, sidx); + if (smallmap_is_marked(m, sidx)) { + mchunkptr p = b; + do { + if (p == x) + return 1; + } while ((p = p->fd) != b); + } + } + else { + bindex_t tidx; + compute_tree_index(size, tidx); + if (treemap_is_marked(m, tidx)) { + tchunkptr t = *treebin_at(m, tidx); + size_t sizebits = size << leftshift_for_tree_index(tidx); + while (t != 0 && chunksize(t) != size) { + t = t->child[(sizebits >> (SIZE_T_BITSIZE-SIZE_T_ONE)) & 1]; + sizebits <<= 1; + } + if (t != 0) { + tchunkptr u = t; + do { + if (u == (tchunkptr)x) + return 1; + } while ((u = u->fd) != t); + } + } + } + return 0; +} + +/* Traverse each chunk and check it; return total */ +static size_t traverse_and_check(mstate m) { + size_t sum = 0; + if (is_initialized(m)) { + msegmentptr s = &m->seg; + sum += m->topsize + TOP_FOOT_SIZE; + while (s != 0) { + mchunkptr q = align_as_chunk(s->base); + mchunkptr lastq = 0; + assert(pinuse(q)); + while (segment_holds(s, q) && + q != m->top && q->head != FENCEPOST_HEAD) { + sum += chunksize(q); + if (is_inuse(q)) { + assert(!bin_find(m, q)); + do_check_inuse_chunk(m, q); + } + else { + assert(q == m->dv || bin_find(m, q)); + assert(lastq == 0 || is_inuse(lastq)); /* Not 2 consecutive free */ + do_check_free_chunk(m, q); + } + lastq = q; + q = next_chunk(q); + } + s = s->next; + } + } + return sum; +} + + +/* Check all properties of malloc_state. */ +static void do_check_malloc_state(mstate m) { + bindex_t i; + size_t total; + /* check bins */ + for (i = 0; i < NSMALLBINS; ++i) + do_check_smallbin(m, i); + for (i = 0; i < NTREEBINS; ++i) + do_check_treebin(m, i); + + if (m->dvsize != 0) { /* check dv chunk */ + do_check_any_chunk(m, m->dv); + assert(m->dvsize == chunksize(m->dv)); + assert(m->dvsize >= MIN_CHUNK_SIZE); + assert(bin_find(m, m->dv) == 0); + } + + if (m->top != 0) { /* check top chunk */ + do_check_top_chunk(m, m->top); + /*assert(m->topsize == chunksize(m->top)); redundant */ + assert(m->topsize > 0); + assert(bin_find(m, m->top) == 0); + } + + total = traverse_and_check(m); + assert(total <= m->footprint); + assert(m->footprint <= m->max_footprint); +} +#endif /* DEBUG */ #define CORRUPTION_ERROR_ACTION(m) \ do { \ @@ -540,6 +1959,33 @@ static DEFINE_MUTEX(malloc_global_mutex); compilers. */ +/* Link a free chunk into a smallbin */ +#define insert_small_chunk(M, P, S) {\ + bindex_t I = small_index(S);\ + mchunkptr B = smallbin_at(M, I);\ + mchunkptr F = B;\ + assert(S >= MIN_CHUNK_SIZE);\ + if (!smallmap_is_marked(M, I))\ + mark_smallmap(M, I);\ + else if (RTCHECK(ok_address(M, B->fd)))\ + F = B->fd;\ + else {\ + CORRUPTION_ERROR_ACTION(M);\ + }\ + B->fd = P;\ + F->bk = P;\ + P->fd = F;\ + P->bk = B;\ +} +/* ----------------------- Operations on smallbins ----------------------- */ + +/* + Various forms of linking and unlinking are defined as macros. Even + the ones for trees, which are very long but have very short typical + paths. This is ugly but reduces reliance on inlining support of + compilers. +*/ + /* Link a free chunk into a smallbin */ #define insert_small_chunk(M, P, S) {\ bindex_t I = small_index(S);\ @@ -567,16 +2013,22 @@ static DEFINE_MUTEX(malloc_global_mutex); assert(P != B);\ assert(P != F);\ assert(chunksize(P) == small_index2size(I));\ - if (F == B)\ + if (RTCHECK(F == smallbin_at(M,I) || (ok_address(M, F) && F->bk == P))) { \ + if (B == F) {\ clear_smallmap(M, I);\ - else if (RTCHECK((F == smallbin_at(M,I) || ok_address(M, F)) &&\ - (B == smallbin_at(M,I) || ok_address(M, B)))) {\ + }\ + else if (RTCHECK(B == smallbin_at(M,I) ||\ + (ok_address(M, B) && B->fd == P))) {\ F->bk = B;\ B->fd = F;\ }\ else {\ CORRUPTION_ERROR_ACTION(M);\ }\ + }\ + else {\ + CORRUPTION_ERROR_ACTION(M);\ + }\ } /* Unlink the first chunk from a smallbin */ @@ -585,11 +2037,12 @@ static DEFINE_MUTEX(malloc_global_mutex); assert(P != B);\ assert(P != F);\ assert(chunksize(P) == small_index2size(I));\ - if (B == F)\ + if (B == F) {\ clear_smallmap(M, I);\ - else if (RTCHECK(ok_address(M, F))) {\ - B->fd = F;\ + }\ + else if (RTCHECK(ok_address(M, F) && F->bk == P)) {\ F->bk = B;\ + B->fd = F;\ }\ else {\ CORRUPTION_ERROR_ACTION(M);\ @@ -600,16 +2053,15 @@ static DEFINE_MUTEX(malloc_global_mutex); /* Used only when dvsize known to be small */ #define replace_dv(M, P, S) {\ size_t DVS = M->dvsize;\ + assert(is_small(DVS));\ if (DVS != 0) {\ mchunkptr DV = M->dv;\ - assert(is_small(DVS));\ insert_small_chunk(M, DV, DVS);\ }\ M->dvsize = S;\ M->dv = P;\ } - /* ------------------------- Operations on trees ------------------------- */ /* Insert chunk into tree */ @@ -687,7 +2139,7 @@ static DEFINE_MUTEX(malloc_global_mutex); if (X->bk != X) {\ tchunkptr F = X->fd;\ R = X->bk;\ - if (RTCHECK(ok_address(M, F))) {\ + if (RTCHECK(ok_address(M, F) && F->bk == X && R->fd == X)) {\ F->bk = R;\ R->fd = F;\ }\ @@ -763,74 +2215,8 @@ static DEFINE_MUTEX(malloc_global_mutex); else { tchunkptr TP = (tchunkptr)(P); unlink_large_chunk(M, TP); } -/* -------------------------- system alloc setup ------------------------- */ - -/* Operations on mflags */ - -#define use_lock(M) ((M)->mflags & USE_LOCK_BIT) -#define enable_lock(M) ((M)->mflags |= USE_LOCK_BIT) -#define disable_lock(M) ((M)->mflags &= ~USE_LOCK_BIT) - -#define use_mmap(M) ((M)->mflags & USE_MMAP_BIT) -#define enable_mmap(M) ((M)->mflags |= USE_MMAP_BIT) -#define disable_mmap(M) ((M)->mflags &= ~USE_MMAP_BIT) - -#define use_noncontiguous(M) ((M)->mflags & USE_NONCONTIGUOUS_BIT) -#define disable_contiguous(M) ((M)->mflags |= USE_NONCONTIGUOUS_BIT) - -#define set_lock(M,L)\ - ((M)->mflags = (L)?\ - ((M)->mflags | USE_LOCK_BIT) :\ - ((M)->mflags & ~USE_LOCK_BIT)) - -/* page-align a size */ -#define page_align(S)\ - (((S) + (mparams.page_size - SIZE_T_ONE)) & ~(mparams.page_size - SIZE_T_ONE)) - -/* granularity-align a size */ -#define granularity_align(S)\ - (((S) + (mparams.granularity - SIZE_T_ONE))\ - & ~(mparams.granularity - SIZE_T_ONE)) -/* For mmap, use granularity alignment */ -#define mmap_align(S) granularity_align(S) - -/* For sys_alloc, enough padding to ensure can malloc request on success */ -#define SYS_ALLOC_PADDING (TOP_FOOT_SIZE + MALLOC_ALIGNMENT) - -#define is_page_aligned(S)\ - (((size_t)(S) & (mparams.page_size - SIZE_T_ONE)) == 0) -#define is_granularity_aligned(S)\ - (((size_t)(S) & (mparams.granularity - SIZE_T_ONE)) == 0) - -/* True if segment S holds address A */ -#define segment_holds(S, A)\ - ((char*)(A) >= S->base && (char*)(A) < S->base + S->size) - -/* Return segment holding given address */ -static msegmentptr segment_holding(mstate m, char* addr) -{ - msegmentptr sp = &m->seg; - for (;;) { - if (addr >= sp->base && addr < sp->base + sp->size) - return sp; - if ((sp = sp->next) == 0) - return 0; - } -} - -/* Return true if segment contains a segment link */ -static int has_segment_link(mstate m, msegmentptr ss) -{ - msegmentptr sp = &m->seg; - for (;;) { - if ((char*)sp >= ss->base && (char*)sp < ss->base + ss->size) - return 1; - if ((sp = sp->next) == 0) - return 0; - } -} static inline void* os_mmap(size_t size) { @@ -844,15 +2230,12 @@ static inline int os_munmap(void* ptr, size_t size) return (KernelFree(ptr) != 0) ? 0 : -1; } -#define should_trim(M,s) ((s) > (M)->trim_check) #define MMAP_DEFAULT(s) os_mmap(s) #define MUNMAP_DEFAULT(a, s) os_munmap((a), (s)) #define DIRECT_MMAP_DEFAULT(s) os_mmap(s) -#define internal_malloc(m, b) malloc(b) -#define internal_free(m, mem) free(mem) /* ----------------------- Direct-mmapping chunks ----------------------- */ @@ -865,14 +2248,16 @@ static inline int os_munmap(void* ptr, size_t size) */ /* Malloc using mmap */ -static void* mmap_alloc(mstate m, size_t nb) -{ +static void* mmap_alloc(mstate m, size_t nb) { size_t mmsize = mmap_align(nb + SIX_SIZE_T_SIZES + CHUNK_ALIGN_MASK); - if (mmsize > nb) /* Check for wrap around 0 */ - { - char* mm = (char*)(os_mmap(mmsize)); - if (mm != CMFAIL) - { + if (m->footprint_limit != 0) { + size_t fp = m->footprint + mmsize; + if (fp <= m->footprint || fp > m->footprint_limit) + return 0; + } + if (mmsize > nb) { /* Check for wrap around 0 */ + char* mm = (char*)(CALL_DIRECT_MMAP(mmsize)); + if (mm != CMFAIL) { size_t offset = align_offset(chunk2mem(mm)); size_t psize = mmsize - offset - MMAP_FOOT_PAD; mchunkptr p = (mchunkptr)(mm + offset); @@ -895,24 +2280,22 @@ static void* mmap_alloc(mstate m, size_t nb) } /* Realloc using mmap */ -static mchunkptr mmap_resize(mstate m, mchunkptr oldp, size_t nb) -{ +static mchunkptr mmap_resize(mstate m, mchunkptr oldp, size_t nb, int flags) { size_t oldsize = chunksize(oldp); + (void)flags; /* placate people compiling -Wunused */ if (is_small(nb)) /* Can't shrink mmap regions below small size */ return 0; /* Keep old chunk if big enough but not too big */ if (oldsize >= nb + SIZE_T_SIZE && (oldsize - nb) <= (mparams.granularity << 1)) return oldp; - else - { + else { size_t offset = oldp->prev_foot; size_t oldmmsize = oldsize + offset + MMAP_FOOT_PAD; size_t newmmsize = mmap_align(nb + SIX_SIZE_T_SIZES + CHUNK_ALIGN_MASK); char* cp = (char*)CALL_MREMAP((char*)oldp - offset, - oldmmsize, newmmsize, 1); - if (cp != CMFAIL) - { + oldmmsize, newmmsize, flags); + if (cp != CMFAIL) { mchunkptr newp = (mchunkptr)(cp + offset); size_t psize = newmmsize - offset - MMAP_FOOT_PAD; newp->head = psize; @@ -920,65 +2303,22 @@ static mchunkptr mmap_resize(mstate m, mchunkptr oldp, size_t nb) chunk_plus_offset(newp, psize)->head = FENCEPOST_HEAD; chunk_plus_offset(newp, psize+SIZE_T_SIZE)->head = 0; - if (cp < m->least_addr) - m->least_addr = cp; - if ((m->footprint += newmmsize - oldmmsize) > m->max_footprint) - m->max_footprint = m->footprint; - check_mmapped_chunk(m, newp); - return newp; - } + if (cp < m->least_addr) + m->least_addr = cp; + if ((m->footprint += newmmsize - oldmmsize) > m->max_footprint) + m->max_footprint = m->footprint; + check_mmapped_chunk(m, newp); + return newp; } - return 0; + } + return 0; } -/* ---------------------------- setting mparams -------------------------- */ - -/* Initialize mparams */ -static int init_mparams(void) { - - ACQUIRE_MALLOC_GLOBAL_LOCK(); - - if (mparams.magic == 0) - { - size_t magic; - size_t psize; - size_t gsize; - - psize = 4096; - gsize = DEFAULT_GRANULARITY; - - /* Sanity-check configuration: - size_t must be unsigned and as wide as pointer type. - ints must be at least 4 bytes. - alignment must be at least 8. - Alignment, min chunk size, and page size must all be powers of 2. - */ - - mparams.granularity = gsize; - mparams.page_size = psize; - mparams.mmap_threshold = DEFAULT_MMAP_THRESHOLD; - mparams.trim_threshold = DEFAULT_TRIM_THRESHOLD; - mparams.default_mflags = USE_LOCK_BIT|USE_MMAP_BIT|USE_NONCONTIGUOUS_BIT; - - /* Set up lock for main malloc area */ - gm->mflags = mparams.default_mflags; - MutexInit(&gm->lock); - - magic = (size_t)(GetTimerTicks() ^ (size_t)0x55555555U); - magic |= (size_t)8U; /* ensure nonzero */ - magic &= ~(size_t)7U; /* improve chances of fault for bad values */ - mparams.magic = magic; - } - - RELEASE_MALLOC_GLOBAL_LOCK(); - return 1; -} /* -------------------------- mspace management -------------------------- */ /* Initialize top chunk and its size */ -static void init_top(mstate m, mchunkptr p, size_t psize) -{ +static void init_top(mstate m, mchunkptr p, size_t psize) { /* Ensure alignment */ size_t offset = align_offset(chunk2mem(p)); p = (mchunkptr)((char*)p + offset); @@ -993,8 +2333,7 @@ static void init_top(mstate m, mchunkptr p, size_t psize) } /* Initialize bins for a new mstate that is otherwise zeroed out */ -static void init_bins(mstate m) -{ +static void init_bins(mstate m) { /* Establish circular links for smallbins */ bindex_t i; for (i = 0; i < NSMALLBINS; ++i) { @@ -1005,8 +2344,7 @@ static void init_bins(mstate m) /* Allocate chunk and prepend remainder with chunk in successor base. */ static void* prepend_alloc(mstate m, char* newbase, char* oldbase, - size_t nb) -{ + size_t nb) { mchunkptr p = align_as_chunk(newbase); mchunkptr oldfirst = align_as_chunk(oldbase); size_t psize = (char*)oldfirst - (char*)p; @@ -1047,8 +2385,7 @@ static void* prepend_alloc(mstate m, char* newbase, char* oldbase, } /* Add a segment to hold a new noncontiguous region */ -static void add_segment(mstate m, char* tbase, size_t tsize, flag_t mmapped) -{ +static void add_segment(mstate m, char* tbase, size_t tsize, flag_t mmapped) { /* Determine locations and sizes of segment, fenceposts, old top */ char* old_top = (char*)m->top; msegmentptr oldsp = segment_holding(m, old_top); @@ -1103,24 +2440,32 @@ static void add_segment(mstate m, char* tbase, size_t tsize, flag_t mmapped) /* -------------------------- System allocation -------------------------- */ /* Get memory from system using MORECORE or MMAP */ -static void* sys_alloc(mstate m, size_t nb) -{ +static void* sys_alloc(mstate m, size_t nb) { char* tbase = CMFAIL; size_t tsize = 0; flag_t mmap_flag = 0; + size_t asize; /* allocation size */ ensure_initialization(); printf("%s %d bytes\n", __FUNCTION__, nb); /* Directly map large chunks, but only if already initialized */ - if (use_mmap(m) && nb >= mparams.mmap_threshold && m->topsize != 0) - { + if (use_mmap(m) && nb >= mparams.mmap_threshold && m->topsize != 0) { void* mem = mmap_alloc(m, nb); if (mem != 0) return mem; } + asize = granularity_align(nb + SYS_ALLOC_PADDING); + if (asize <= nb) + return 0; /* wraparound */ + if (m->footprint_limit != 0) { + size_t fp = m->footprint + asize; + if (fp <= m->footprint || fp > m->footprint_limit) + return 0; + } + /* Try getting memory in any of three ways (in most-preferred to least-preferred order): @@ -1143,30 +2488,104 @@ static void* sys_alloc(mstate m, size_t nb) not on boundary, and round this up to a granularity unit. */ - if (HAVE_MMAP && tbase == CMFAIL) /* Try MMAP */ - { - size_t rsize = granularity_align(nb + SYS_ALLOC_PADDING); - if (rsize > nb) /* Fail if wraps around zero */ - { - char* mp = (char*)(CALL_MMAP(rsize)); - if (mp != CMFAIL) - { - tbase = mp; - tsize = rsize; - mmap_flag = USE_MMAP_BIT; +#if 0 + if (MORECORE_CONTIGUOUS && !use_noncontiguous(m)) { + char* br = CMFAIL; + size_t ssize = asize; /* sbrk call size */ + msegmentptr ss = (m->top == 0)? 0 : segment_holding(m, (char*)m->top); + ACQUIRE_MALLOC_GLOBAL_LOCK(); + + if (ss == 0) { /* First time through or recovery */ + char* base = (char*)CALL_MORECORE(0); + if (base != CMFAIL) { + size_t fp; + /* Adjust to end on a page boundary */ + if (!is_page_aligned(base)) + ssize += (page_align((size_t)base) - (size_t)base); + fp = m->footprint + ssize; /* recheck limits */ + if (ssize > nb && ssize < HALF_MAX_SIZE_T && + (m->footprint_limit == 0 || + (fp > m->footprint && fp <= m->footprint_limit)) && + (br = (char*)(CALL_MORECORE(ssize))) == base) { + tbase = base; + tsize = ssize; + } + } + } + else { + /* Subtract out existing available top space from MORECORE request. */ + ssize = granularity_align(nb - m->topsize + SYS_ALLOC_PADDING); + /* Use mem here only if it did continuously extend old space */ + if (ssize < HALF_MAX_SIZE_T && + (br = (char*)(CALL_MORECORE(ssize))) == ss->base+ss->size) { + tbase = br; + tsize = ssize; + } + } + + if (tbase == CMFAIL) { /* Cope with partial failure */ + if (br != CMFAIL) { /* Try to use/extend the space we did get */ + if (ssize < HALF_MAX_SIZE_T && + ssize < nb + SYS_ALLOC_PADDING) { + size_t esize = granularity_align(nb + SYS_ALLOC_PADDING - ssize); + if (esize < HALF_MAX_SIZE_T) { + char* end = (char*)CALL_MORECORE(esize); + if (end != CMFAIL) + ssize += esize; + else { /* Can't use; try to release */ + (void) CALL_MORECORE(-ssize); + br = CMFAIL; + } + } + } + } + if (br != CMFAIL) { /* Use the space we did get */ + tbase = br; + tsize = ssize; + } + else + disable_contiguous(m); /* Don't try contiguous path in the future */ + } + + RELEASE_MALLOC_GLOBAL_LOCK(); + } +#endif + + if (HAVE_MMAP && tbase == CMFAIL) { /* Try MMAP */ + char* mp = (char*)(CALL_MMAP(asize)); + if (mp != CMFAIL) { + tbase = mp; + tsize = asize; + mmap_flag = USE_MMAP_BIT; + } + } + +#if 0 + if (HAVE_MORECORE && tbase == CMFAIL) { /* Try noncontiguous MORECORE */ + if (asize < HALF_MAX_SIZE_T) { + char* br = CMFAIL; + char* end = CMFAIL; + ACQUIRE_MALLOC_GLOBAL_LOCK(); + br = (char*)(CALL_MORECORE(asize)); + end = (char*)(CALL_MORECORE(0)); + RELEASE_MALLOC_GLOBAL_LOCK(); + if (br != CMFAIL && end != CMFAIL && br < end) { + size_t ssize = end - br; + if (ssize > nb + TOP_FOOT_SIZE) { + tbase = br; + tsize = ssize; + } } } } +#endif - - if (tbase != CMFAIL) - { + if (tbase != CMFAIL) { if ((m->footprint += tsize) > m->max_footprint) m->max_footprint = m->footprint; - if (!is_initialized(m)) /* first-time initialization */ - { + if (!is_initialized(m)) { /* first-time initialization */ if (m->least_addr == 0 || tbase < m->least_addr) m->least_addr = tbase; m->seg.base = tbase; @@ -1185,22 +2604,21 @@ static void* sys_alloc(mstate m, size_t nb) init_top(m, mn, (size_t)((tbase + tsize) - (char*)mn) -TOP_FOOT_SIZE); } } - else - { + + else { /* Try to merge with an existing segment */ msegmentptr sp = &m->seg; /* Only consider most recent segment if traversal suppressed */ while (sp != 0 && tbase != sp->base + sp->size) sp = (NO_SEGMENT_TRAVERSAL) ? 0 : sp->next; - if (sp != 0 && !is_extern_segment(sp) && + if (sp != 0 && + !is_extern_segment(sp) && (sp->sflags & USE_MMAP_BIT) == mmap_flag && - segment_holds(sp, m->top)) /* append */ - { + segment_holds(sp, m->top)) { /* append */ sp->size += tsize; init_top(m, m->top, m->topsize + tsize); } - else - { + else { if (tbase < m->least_addr) m->least_addr = tbase; sp = &m->seg; @@ -1208,8 +2626,7 @@ static void* sys_alloc(mstate m, size_t nb) sp = (NO_SEGMENT_TRAVERSAL) ? 0 : sp->next; if (sp != 0 && !is_extern_segment(sp) && - (sp->sflags & USE_MMAP_BIT) == mmap_flag) - { + (sp->sflags & USE_MMAP_BIT) == mmap_flag) { char* oldbase = sp->base; sp->base = tbase; sp->size += tsize; @@ -1220,8 +2637,7 @@ static void* sys_alloc(mstate m, size_t nb) } } - if (nb < m->topsize) /* Allocate from new or extended top space */ - { + if (nb < m->topsize) { /* Allocate from new or extended top space */ size_t rsize = m->topsize -= nb; mchunkptr p = m->top; mchunkptr r = m->top = chunk_plus_offset(p, nb); @@ -1237,29 +2653,24 @@ static void* sys_alloc(mstate m, size_t nb) return 0; } - /* ----------------------- system deallocation -------------------------- */ /* Unmap and unlink any mmapped segments that don't contain used chunks */ -static size_t release_unused_segments(mstate m) -{ +static size_t release_unused_segments(mstate m) { size_t released = 0; int nsegs = 0; msegmentptr pred = &m->seg; msegmentptr sp = pred->next; - while (sp != 0) - { + while (sp != 0) { char* base = sp->base; size_t size = sp->size; msegmentptr next = sp->next; ++nsegs; - if (is_mmapped_segment(sp) && !is_extern_segment(sp)) - { + if (is_mmapped_segment(sp) && !is_extern_segment(sp)) { mchunkptr p = align_as_chunk(base); size_t psize = chunksize(p); /* Can unmap if first chunk holds entire segment and not pinned */ - if (!is_inuse(p) && (char*)p + psize >= base + size - TOP_FOOT_SIZE) - { + if (!is_inuse(p) && (char*)p + psize >= base + size - TOP_FOOT_SIZE) { tchunkptr tp = (tchunkptr)p; assert(segment_holds(sp, (char*)sp)); if (p == m->dv) { @@ -1269,8 +2680,7 @@ static size_t release_unused_segments(mstate m) else { unlink_large_chunk(m, tp); } - if (CALL_MUNMAP(base, size) == 0) - { + if (CALL_MUNMAP(base, size) == 0) { released += size; m->footprint -= size; /* unlink obsoleted record */ @@ -1288,48 +2698,57 @@ static size_t release_unused_segments(mstate m) sp = next; } /* Reset check counter */ - m->release_checks = ((nsegs > MAX_RELEASE_CHECK_RATE)? - nsegs : MAX_RELEASE_CHECK_RATE); + m->release_checks = (((size_t) nsegs > (size_t) MAX_RELEASE_CHECK_RATE)? + (size_t) nsegs : (size_t) MAX_RELEASE_CHECK_RATE); return released; } -static int sys_trim(mstate m, size_t pad) -{ +static int sys_trim(mstate m, size_t pad) { size_t released = 0; ensure_initialization(); - if (pad < MAX_REQUEST && is_initialized(m)) - { + if (pad < MAX_REQUEST && is_initialized(m)) { pad += TOP_FOOT_SIZE; /* ensure enough room for segment overhead */ - if (m->topsize > pad) - { + if (m->topsize > pad) { /* Shrink top space in granularity-size units, keeping at least one */ size_t unit = mparams.granularity; size_t extra = ((m->topsize - pad + (unit - SIZE_T_ONE)) / unit - SIZE_T_ONE) * unit; msegmentptr sp = segment_holding(m, (char*)m->top); - if (!is_extern_segment(sp)) - { - if (is_mmapped_segment(sp)) - { + if (!is_extern_segment(sp)) { + if (is_mmapped_segment(sp)) { if (HAVE_MMAP && sp->size >= extra && - !has_segment_link(m, sp)) /* can't shrink if pinned */ - { + !has_segment_link(m, sp)) { /* can't shrink if pinned */ size_t newsize = sp->size - extra; + (void)newsize; /* placate people compiling -Wunused-variable */ /* Prefer mremap, fall back to munmap */ if ((CALL_MREMAP(sp->base, sp->size, newsize, 0) != MFAIL) || - (CALL_MUNMAP(sp->base + newsize, extra) == 0)) + (CALL_MUNMAP(sp->base + newsize, extra) == 0)) { + released = extra; + } + } + } + else if (HAVE_MORECORE) { + if (extra >= HALF_MAX_SIZE_T) /* Avoid wrapping negative */ + extra = (HALF_MAX_SIZE_T) + SIZE_T_ONE - unit; + ACQUIRE_MALLOC_GLOBAL_LOCK(); { - released = extra; + /* Make sure end of memory is where we last set it. */ + char* old_br = (char*)(CALL_MORECORE(0)); + if (old_br == sp->base + sp->size) { + char* rel_br = (char*)(CALL_MORECORE(-extra)); + char* new_br = (char*)(CALL_MORECORE(0)); + if (rel_br != CMFAIL && new_br < old_br) + released = old_br - new_br; } } + RELEASE_MALLOC_GLOBAL_LOCK(); } } - if (released != 0) - { + if (released != 0) { sp->size -= released; m->footprint -= released; init_top(m, m->top, m->topsize - released); @@ -1349,9 +2768,78 @@ static int sys_trim(mstate m, size_t pad) return (released != 0)? 1 : 0; } +/* Consolidate and bin a chunk. Differs from exported versions + of free mainly in that the chunk need not be marked as inuse. +*/ +static void dispose_chunk(mstate m, mchunkptr p, size_t psize) { + mchunkptr next = chunk_plus_offset(p, psize); + if (!pinuse(p)) { + mchunkptr prev; + size_t prevsize = p->prev_foot; + if (is_mmapped(p)) { + psize += prevsize + MMAP_FOOT_PAD; + if (CALL_MUNMAP((char*)p - prevsize, psize) == 0) + m->footprint -= psize; + return; + } + prev = chunk_minus_offset(p, prevsize); + psize += prevsize; + p = prev; + if (RTCHECK(ok_address(m, prev))) { /* consolidate backward */ + if (p != m->dv) { + unlink_chunk(m, p, prevsize); + } + else if ((next->head & INUSE_BITS) == INUSE_BITS) { + m->dvsize = psize; + set_free_with_pinuse(p, psize, next); + return; + } + } + else { + CORRUPTION_ERROR_ACTION(m); + return; + } + } + if (RTCHECK(ok_address(m, next))) { + if (!cinuse(next)) { /* consolidate forward */ + if (next == m->top) { + size_t tsize = m->topsize += psize; + m->top = p; + p->head = tsize | PINUSE_BIT; + if (p == m->dv) { + m->dv = 0; + m->dvsize = 0; + } + return; + } + else if (next == m->dv) { + size_t dsize = m->dvsize += psize; + m->dv = p; + set_size_and_pinuse_of_free_chunk(p, dsize); + return; + } + else { + size_t nsize = chunksize(next); + psize += nsize; + unlink_chunk(m, next, nsize); + set_size_and_pinuse_of_free_chunk(p, psize); + if (p == m->dv) { + m->dvsize = psize; + return; + } + } + } + else { + set_free_with_pinuse(p, psize, next); + } + insert_chunk(m, p, psize); + } + else { + CORRUPTION_ERROR_ACTION(m); + } +} - -/* ---------------------------- malloc support --------------------------- */ +/* ---------------------------- malloc --------------------------- */ /* allocate a large request from the best fitting chunk in a treebin */ static void* tmalloc_large(mstate m, size_t nb) { @@ -1425,8 +2913,7 @@ static void* tmalloc_large(mstate m, size_t nb) { } /* allocate a small request from the best fitting chunk in a treebin */ -static void* tmalloc_small(mstate m, size_t nb) -{ +static void* tmalloc_small(mstate m, size_t nb) { tchunkptr t, v; size_t rsize; bindex_t i; @@ -1463,105 +2950,6 @@ static void* tmalloc_small(mstate m, size_t nb) return 0; } -/* --------------------------- memalign support -------------------------- */ - -static void* internal_memalign(mstate m, size_t alignment, size_t bytes) -{ - if (alignment <= MALLOC_ALIGNMENT) /* Can just use malloc */ - return internal_malloc(m, bytes); - if (alignment < MIN_CHUNK_SIZE) /* must be at least a minimum chunk size */ - alignment = MIN_CHUNK_SIZE; - if ((alignment & (alignment-SIZE_T_ONE)) != 0) {/* Ensure a power of 2 */ - size_t a = MALLOC_ALIGNMENT << 1; - while (a < alignment) a <<= 1; - alignment = a; - } - - if (bytes >= MAX_REQUEST - alignment) { - if (m != 0) { /* Test isn't needed but avoids compiler warning */ -// MALLOC_FAILURE_ACTION; - } - } - else - { - size_t nb = request2size(bytes); - size_t req = nb + alignment + MIN_CHUNK_SIZE - CHUNK_OVERHEAD; - char* mem = (char*)internal_malloc(m, req); - if (mem != 0) - { - void* leader = 0; - void* trailer = 0; - mchunkptr p = mem2chunk(mem); - - PREACTION(m); - - if ((((size_t)(mem)) % alignment) != 0) /* misaligned */ - { - /* - Find an aligned spot inside chunk. Since we need to give - back leading space in a chunk of at least MIN_CHUNK_SIZE, if - the first calculation places us at a spot with less than - MIN_CHUNK_SIZE leader, we can move to the next aligned spot. - We've allocated enough total room so that this is always - possible. - */ - char* br = (char*)mem2chunk((size_t)(((size_t)(mem + - alignment - - SIZE_T_ONE)) & - -alignment)); - char* pos = ((size_t)(br - (char*)(p)) >= MIN_CHUNK_SIZE)? - br : br+alignment; - mchunkptr newp = (mchunkptr)pos; - size_t leadsize = pos - (char*)(p); - size_t newsize = chunksize(p) - leadsize; - - if (is_mmapped(p)) { /* For mmapped chunks, just adjust offset */ - newp->prev_foot = p->prev_foot + leadsize; - newp->head = newsize; - } - else { /* Otherwise, give back leader, use the rest */ - set_inuse(m, newp, newsize); - set_inuse(m, p, leadsize); - leader = chunk2mem(p); - } - p = newp; - } - - /* Give back spare room at the end */ - if (!is_mmapped(p)) - { - size_t size = chunksize(p); - if (size > nb + MIN_CHUNK_SIZE) - { - size_t remainder_size = size - nb; - mchunkptr remainder = chunk_plus_offset(p, nb); - set_inuse(m, p, nb); - set_inuse(m, remainder, remainder_size); - trailer = chunk2mem(remainder); - } - } - - assert (chunksize(p) >= nb); - assert((((size_t)(chunk2mem(p))) % alignment) == 0); - check_inuse_chunk(m, p); - POSTACTION(m); - if (leader != 0) { - internal_free(m, leader); - } - if (trailer != 0) { - internal_free(m, trailer); - } - return chunk2mem(p); - } - } - return 0; -} - -void* memalign(size_t alignment, size_t bytes) -{ - return internal_memalign(gm, alignment, bytes); -} - void* malloc(size_t bytes) { @@ -1594,17 +2982,14 @@ void* malloc(size_t bytes) { void* mem; size_t nb; - - if (bytes <= MAX_SMALL_REQUEST) - { + if (bytes <= MAX_SMALL_REQUEST) { bindex_t idx; binmap_t smallbits; nb = (bytes < MIN_REQUEST)? MIN_CHUNK_SIZE : pad_request(bytes); idx = small_index(nb); smallbits = gm->smallmap >> idx; - if ((smallbits & 0x3U) != 0) /* Remainderless fit to a smallbin. */ - { + if ((smallbits & 0x3U) != 0) { /* Remainderless fit to a smallbin. */ mchunkptr b, p; idx += ~smallbits & 1; /* Uses next bin if idx empty */ b = smallbin_at(gm, idx); @@ -1616,10 +3001,9 @@ void* malloc(size_t bytes) check_malloced_chunk(gm, mem, nb); goto postaction; } - else if (nb > gm->dvsize) - { - if (smallbits != 0) /* Use chunk in next nonempty smallbin */ - { + + else if (nb > gm->dvsize) { + if (smallbits != 0) { /* Use chunk in next nonempty smallbin */ mchunkptr b, p, r; size_t rsize; bindex_t i; @@ -1634,8 +3018,7 @@ void* malloc(size_t bytes) /* Fit here cannot be remainderless if 4byte sizes */ if (SIZE_T_SIZE != 4 && rsize < MIN_CHUNK_SIZE) set_inuse_and_pinuse(gm, p, small_index2size(i)); - else - { + else { set_size_and_pinuse_of_inuse_chunk(gm, p, nb); r = chunk_plus_offset(p, nb); set_size_and_pinuse_of_free_chunk(r, rsize); @@ -1645,8 +3028,8 @@ void* malloc(size_t bytes) check_malloced_chunk(gm, mem, nb); goto postaction; } - else if (gm->treemap != 0 && (mem = tmalloc_small(gm, nb)) != 0) - { + + else if (gm->treemap != 0 && (mem = tmalloc_small(gm, nb)) != 0) { check_malloced_chunk(gm, mem, nb); goto postaction; } @@ -1654,11 +3037,9 @@ void* malloc(size_t bytes) } else if (bytes >= MAX_REQUEST) nb = MAX_SIZE_T; /* Too big to allocate. Force failure (in sys alloc) */ - else - { + else { nb = pad_request(bytes); - if (gm->treemap != 0 && (mem = tmalloc_large(gm, nb)) != 0) - { + if (gm->treemap != 0 && (mem = tmalloc_large(gm, nb)) != 0) { check_malloced_chunk(gm, mem, nb); goto postaction; } @@ -1683,6 +3064,7 @@ void* malloc(size_t bytes) check_malloced_chunk(gm, mem, nb); goto postaction; } + else if (nb < gm->topsize) { /* Split top */ size_t rsize = gm->topsize -= nb; mchunkptr p = gm->top; @@ -1699,12 +3081,14 @@ void* malloc(size_t bytes) postaction: POSTACTION(gm); +// printf("%s %p %d\n", __FUNCTION__, mem, bytes); return mem; } - +// FAIL(); return 0; } +/* ---------------------------- free --------------------------- */ void free(void* mem) { @@ -1714,42 +3098,42 @@ void free(void* mem) with special cases for top, dv, mmapped chunks, and usage errors. */ - if (mem != 0) - { +// dbgprintf("%s %p\n", __FUNCTION__, mem); + + if (mem != 0) { mchunkptr p = mem2chunk(mem); - +#if FOOTERS + mstate fm = get_mstate_for(p); + if (!ok_magic(fm)) { + USAGE_ERROR_ACTION(fm, p); + return; + } +#else /* FOOTERS */ #define fm gm - +#endif /* FOOTERS */ PREACTION(fm); { check_inuse_chunk(fm, p); - if (RTCHECK(ok_address(fm, p) && ok_inuse(p))) - { + if (RTCHECK(ok_address(fm, p) && ok_inuse(p))) { size_t psize = chunksize(p); mchunkptr next = chunk_plus_offset(p, psize); - if (!pinuse(p)) - { + if (!pinuse(p)) { size_t prevsize = p->prev_foot; - if (is_mmapped(p)) - { + if (is_mmapped(p)) { psize += prevsize + MMAP_FOOT_PAD; if (CALL_MUNMAP((char*)p - prevsize, psize) == 0) fm->footprint -= psize; goto postaction; } - else - { + else { mchunkptr prev = chunk_minus_offset(p, prevsize); psize += prevsize; p = prev; - if (RTCHECK(ok_address(fm, prev))) /* consolidate backward */ - { - if (p != fm->dv) - { + if (RTCHECK(ok_address(fm, prev))) { /* consolidate backward */ + if (p != fm->dv) { unlink_chunk(fm, p, prevsize); } - else if ((next->head & INUSE_BITS) == INUSE_BITS) - { + else if ((next->head & INUSE_BITS) == INUSE_BITS) { fm->dvsize = psize; set_free_with_pinuse(p, psize, next); goto postaction; @@ -1760,17 +3144,13 @@ void free(void* mem) } } - if (RTCHECK(ok_next(p, next) && ok_pinuse(next))) - { - if (!cinuse(next)) /* consolidate forward */ - { - if (next == fm->top) - { + if (RTCHECK(ok_next(p, next) && ok_pinuse(next))) { + if (!cinuse(next)) { /* consolidate forward */ + if (next == fm->top) { size_t tsize = fm->topsize += psize; fm->top = p; p->head = tsize | PINUSE_BIT; - if (p == fm->dv) - { + if (p == fm->dv) { fm->dv = 0; fm->dvsize = 0; } @@ -1778,21 +3158,18 @@ void free(void* mem) sys_trim(fm, 0); goto postaction; } - else if (next == fm->dv) - { + else if (next == fm->dv) { size_t dsize = fm->dvsize += psize; fm->dv = p; set_size_and_pinuse_of_free_chunk(p, dsize); goto postaction; } - else - { + else { size_t nsize = chunksize(next); psize += nsize; unlink_chunk(fm, next, nsize); set_size_and_pinuse_of_free_chunk(p, psize); - if (p == fm->dv) - { + if (p == fm->dv) { fm->dvsize = psize; goto postaction; } @@ -1801,13 +3178,11 @@ void free(void* mem) else set_free_with_pinuse(p, psize, next); - if (is_small(psize)) - { + if (is_small(psize)) { insert_small_chunk(fm, p, psize); check_free_chunk(fm, p); } - else - { + else { tchunkptr tp = (tchunkptr)p; insert_large_chunk(fm, tp, psize); check_free_chunk(fm, p); @@ -1823,7 +3198,12 @@ void free(void* mem) POSTACTION(fm); } } + +// LEAVE(); + +#if !FOOTERS #undef fm +#endif /* FOOTERS */ } diff --git a/drivers/include/drm/drmP.h b/drivers/include/drm/drmP.h index 48bd11d39b..7f38300f69 100644 --- a/drivers/include/drm/drmP.h +++ b/drivers/include/drm/drmP.h @@ -171,7 +171,7 @@ int drm_err(const char *func, const char *format, ...); /** \name Begin the DRM... */ /*@{*/ -#define DRM_DEBUG_CODE 2 /**< Include debugging code if > 1, then +#define DRM_DEBUG_CODE 0 /**< Include debugging code if > 1, then also include looping detection. */ #define DRM_MAGIC_HASH_ORDER 4 /**< Size of key hash table. Must be power of 2. */ diff --git a/drivers/include/linux/asm/scatterlist.h b/drivers/include/linux/asm/scatterlist.h index 5de07355fa..5e087944a6 100644 --- a/drivers/include/linux/asm/scatterlist.h +++ b/drivers/include/linux/asm/scatterlist.h @@ -31,4 +31,6 @@ struct scatterlist { #define sg_dma_len(sg) ((sg)->length) #endif +#define ARCH_HAS_SG_CHAIN + #endif /* __ASM_GENERIC_SCATTERLIST_H */ diff --git a/drivers/include/linux/list.h b/drivers/include/linux/list.h index c6c68b1d8f..3acd346e99 100644 --- a/drivers/include/linux/list.h +++ b/drivers/include/linux/list.h @@ -202,7 +202,7 @@ static inline int list_empty(const struct list_head *head) */ static inline int list_empty_careful(const struct list_head *head) { - struct list_head *next = head->next; + struct list_head *next = head->next; return (next == head) && (next == head->prev); } diff --git a/drivers/include/linux/scatterlist.h b/drivers/include/linux/scatterlist.h index 41120d3322..93c48123b4 100644 --- a/drivers/include/linux/scatterlist.h +++ b/drivers/include/linux/scatterlist.h @@ -229,7 +229,7 @@ size_t sg_copy_to_buffer(struct scatterlist *sgl, unsigned int nents, * Maximum number of entries that will be allocated in one piece, if * a list larger than this is required then chaining will be utilized. */ -#define SG_MAX_SINGLE_ALLOC (PAGE_SIZE / sizeof(struct scatterlist)) +#define SG_MAX_SINGLE_ALLOC (4*PAGE_SIZE / sizeof(struct scatterlist)) /* diff --git a/drivers/include/linux/wait.h b/drivers/include/linux/wait.h index 15537a9146..679e0ceccc 100644 --- a/drivers/include/linux/wait.h +++ b/drivers/include/linux/wait.h @@ -1,6 +1,7 @@ #ifndef _LINUX_WAIT_H #define _LINUX_WAIT_H +#include #include typedef struct __wait_queue wait_queue_t; @@ -39,7 +40,6 @@ do { \ - #define wait_event_timeout(wq, condition, timeout) \ ({ \ long __ret = timeout; \ @@ -48,7 +48,7 @@ do{ \ .task_list = LIST_HEAD_INIT(__wait.task_list), \ .evnt = CreateEvent(NULL, MANUAL_DESTROY), \ }; \ - u32 flags; \ + unsigned long flags; \ \ spin_lock_irqsave(&wq.lock, flags); \ if (list_empty(&__wait.task_list)) \ @@ -60,7 +60,7 @@ do{ \ break; \ WaitEvent(__wait.evnt); \ }; \ - if (!list_empty_careful(&__wait.task_list)) { \ + if (!list_empty(&__wait.task_list)) { \ spin_lock_irqsave(&wq.lock, flags); \ list_del_init(&__wait.task_list); \ spin_unlock_irqrestore(&wq.lock, flags); \ @@ -80,7 +80,7 @@ do{ \ .task_list = LIST_HEAD_INIT(__wait.task_list), \ .evnt = CreateEvent(NULL, MANUAL_DESTROY), \ }; \ - u32 flags; \ + unsigned long flags; \ \ spin_lock_irqsave(&wq.lock, flags); \ if (list_empty(&__wait.task_list)) \ @@ -112,6 +112,8 @@ void wake_up_all(wait_queue_head_t *q) spin_lock_irqsave(&q->lock, flags); list_for_each_entry(curr, &q->task_list, task_list) { +// printf("raise event \n"); + kevent_t event; event.code = -1; RaiseEvent(curr->evnt, 0, &event);