1
0
mirror of https://git.tartarus.org/simon/putty.git synced 2025-01-10 09:58:01 +00:00
putty-source/windows/winmiscs.c

286 lines
7.1 KiB
C
Raw Normal View History

/*
* winmiscs.c: Windows-specific standalone functions. Has the same
* relationship to winmisc.c that utils.c does to misc.c, but the
* corresponding name 'winutils.c' was already taken.
*/
#include "putty.h"
#ifndef NO_SECUREZEROMEMORY
/*
* Windows implementation of smemclr (see misc.c) using SecureZeroMemory.
*/
void smemclr(void *b, size_t n) {
if (b && n > 0)
SecureZeroMemory(b, n);
}
#endif
#ifdef MINEFIELD
/*
* Minefield - a Windows equivalent for Electric Fence
*/
#define PAGESIZE 4096
/*
* Design:
*
* We start by reserving as much virtual address space as Windows
* will sensibly (or not sensibly) let us have. We flag it all as
* invalid memory.
*
* Any allocation attempt is satisfied by committing one or more
* pages, with an uncommitted page on either side. The returned
* memory region is jammed up against the _end_ of the pages.
*
* Freeing anything causes instantaneous decommitment of the pages
* involved, so stale pointers are caught as soon as possible.
*/
static int minefield_initialised = 0;
static void *minefield_region = NULL;
static long minefield_size = 0;
static long minefield_npages = 0;
static long minefield_curpos = 0;
static unsigned short *minefield_admin = NULL;
static void *minefield_pages = NULL;
static void minefield_admin_hide(int hide)
{
int access = hide ? PAGE_NOACCESS : PAGE_READWRITE;
VirtualProtect(minefield_admin, minefield_npages * 2, access, NULL);
}
static void minefield_init(void)
{
int size;
int admin_size;
int i;
for (size = 0x40000000; size > 0; size = ((size >> 3) * 7) & ~0xFFF) {
minefield_region = VirtualAlloc(NULL, size,
MEM_RESERVE, PAGE_NOACCESS);
if (minefield_region)
break;
}
minefield_size = size;
/*
* Firstly, allocate a section of that to be the admin block.
* We'll need a two-byte field for each page.
*/
minefield_admin = minefield_region;
minefield_npages = minefield_size / PAGESIZE;
admin_size = (minefield_npages * 2 + PAGESIZE - 1) & ~(PAGESIZE - 1);
minefield_npages = (minefield_size - admin_size) / PAGESIZE;
minefield_pages = (char *) minefield_region + admin_size;
/*
* Commit the admin region.
*/
VirtualAlloc(minefield_admin, minefield_npages * 2,
MEM_COMMIT, PAGE_READWRITE);
/*
* Mark all pages as unused (0xFFFF).
*/
for (i = 0; i < minefield_npages; i++)
minefield_admin[i] = 0xFFFF;
/*
* Hide the admin region.
*/
minefield_admin_hide(1);
minefield_initialised = 1;
}
static void minefield_bomb(void)
{
div(1, *(int *) minefield_pages);
}
static void *minefield_alloc(int size)
{
int npages;
int pos, lim, region_end, region_start;
int start;
int i;
npages = (size + PAGESIZE - 1) / PAGESIZE;
minefield_admin_hide(0);
/*
* Search from current position until we find a contiguous
* bunch of npages+2 unused pages.
*/
pos = minefield_curpos;
lim = minefield_npages;
while (1) {
/* Skip over used pages. */
while (pos < lim && minefield_admin[pos] != 0xFFFF)
pos++;
/* Count unused pages. */
start = pos;
while (pos < lim && pos - start < npages + 2 &&
minefield_admin[pos] == 0xFFFF)
pos++;
if (pos - start == npages + 2)
break;
/* If we've reached the limit, reset the limit or stop. */
if (pos >= lim) {
if (lim == minefield_npages) {
/* go round and start again at zero */
lim = minefield_curpos;
pos = 0;
} else {
minefield_admin_hide(1);
return NULL;
}
}
}
minefield_curpos = pos - 1;
/*
* We have npages+2 unused pages starting at start. We leave
* the first and last of these alone and use the rest.
*/
region_end = (start + npages + 1) * PAGESIZE;
region_start = region_end - size;
/* FIXME: could align here if we wanted */
/*
* Update the admin region.
*/
for (i = start + 2; i < start + npages + 1; i++)
minefield_admin[i] = 0xFFFE; /* used but no region starts here */
minefield_admin[start + 1] = region_start % PAGESIZE;
minefield_admin_hide(1);
VirtualAlloc((char *) minefield_pages + region_start, size,
MEM_COMMIT, PAGE_READWRITE);
return (char *) minefield_pages + region_start;
}
static void minefield_free(void *ptr)
{
int region_start, i, j;
minefield_admin_hide(0);
region_start = (char *) ptr - (char *) minefield_pages;
i = region_start / PAGESIZE;
if (i < 0 || i >= minefield_npages ||
minefield_admin[i] != region_start % PAGESIZE)
minefield_bomb();
for (j = i; j < minefield_npages && minefield_admin[j] != 0xFFFF; j++) {
minefield_admin[j] = 0xFFFF;
}
VirtualFree(ptr, j * PAGESIZE - region_start, MEM_DECOMMIT);
minefield_admin_hide(1);
}
static int minefield_get_size(void *ptr)
{
int region_start, i, j;
minefield_admin_hide(0);
region_start = (char *) ptr - (char *) minefield_pages;
i = region_start / PAGESIZE;
if (i < 0 || i >= minefield_npages ||
minefield_admin[i] != region_start % PAGESIZE)
minefield_bomb();
for (j = i; j < minefield_npages && minefield_admin[j] != 0xFFFF; j++);
minefield_admin_hide(1);
return j * PAGESIZE - region_start;
}
void *minefield_c_malloc(size_t size)
{
if (!minefield_initialised)
minefield_init();
return minefield_alloc(size);
}
void minefield_c_free(void *p)
{
if (!minefield_initialised)
minefield_init();
minefield_free(p);
}
/*
* realloc _always_ moves the chunk, for rapid detection of code
* that assumes it won't.
*/
void *minefield_c_realloc(void *p, size_t size)
{
size_t oldsize;
void *q;
if (!minefield_initialised)
minefield_init();
q = minefield_alloc(size);
oldsize = minefield_get_size(p);
memcpy(q, p, (oldsize < size ? oldsize : size));
minefield_free(p);
return q;
}
#endif /* MINEFIELD */
Build testcrypt on Windows. The bulk of this commit is the changes necessary to make testcrypt compile under Visual Studio. Unfortunately, I've had to remove my fiddly clever uses of C99 variadic macros, because Visual Studio does something unexpected when a variadic macro's expansion puts __VA_ARGS__ in the argument list of a further macro invocation: the commas don't separate further arguments. In other words, if you write #define INNER(x,y,z) some expansion involving x, y and z #define OUTER(...) INNER(__VA_ARGS__) OUTER(1,2,3) then gcc and clang will translate OUTER(1,2,3) into INNER(1,2,3) in the obvious way, and the inner macro will be expanded with x=1, y=2 and z=3. But try this in Visual Studio, and you'll get the macro parameter x expanding to the entire string 1,2,3 and the other two empty (with warnings complaining that INNER didn't get the number of arguments it expected). It's hard to cite chapter and verse of the standard to say which of those is _definitely_ right, though my reading leans towards the gcc/clang behaviour. But I do know I can't depend on it in code that has to compile under both! So I've removed the system that allowed me to declare everything in testcrypt.h as FUNC(ret,fn,arg,arg,arg), and now I have to use a different macro for each arity (FUNC0, FUNC1, FUNC2 etc). Also, the WRAPPED_NAME system is gone (because that too depended on the use of a comma to shift macro arguments along by one), and now I put a custom C wrapper around a function by simply re-#defining that function's own name (and therefore the subsequent code has to be a little more careful to _not_ pass functions' names between several macros before stringifying them). That's all a bit tedious, and commits me to a small amount of ongoing annoyance because now I'll have to add an explicit argument count every time I add something to testcrypt.h. But then again, perhaps it will make the code less incomprehensible to someone trying to understand it!
2019-01-11 06:25:28 +00:00
Replace mkfiles.pl with a CMake build system. This brings various concrete advantages over the previous system: - consistent support for out-of-tree builds on all platforms - more thorough support for Visual Studio IDE project files - support for Ninja-based builds, which is particularly useful on Windows where the alternative nmake has no parallel option - a really simple set of build instructions that work the same way on all the major platforms (look how much shorter README is!) - better decoupling of the project configuration from the toolchain configuration, so that my Windows cross-building doesn't need (much) special treatment in CMakeLists.txt - configure-time tests on Windows as well as Linux, so that a lot of ad-hoc #ifdefs second-guessing a particular feature's presence from the compiler version can now be replaced by tests of the feature itself Also some longer-term software-engineering advantages: - other people have actually heard of CMake, so they'll be able to produce patches to the new build setup more easily - unlike the old mkfiles.pl, CMake is not my personal problem to maintain - most importantly, mkfiles.pl was just a horrible pile of unmaintainable cruft, which even I found it painful to make changes to or to use, and desperately needed throwing in the bin. I've already thrown away all the variants of it I had in other projects of mine, and was only delaying this one so we could make the 0.75 release branch first. This change comes with a noticeable build-level restructuring. The previous Recipe worked by compiling every object file exactly once, and then making each executable by linking a precisely specified subset of the same object files. But in CMake, that's not the natural way to work - if you write the obvious command that puts the same source file into two executable targets, CMake generates a makefile that compiles it once per target. That can be an advantage, because it gives you the freedom to compile it differently in each case (e.g. with a #define telling it which program it's part of). But in a project that has many executable targets and had carefully contrived to _never_ need to build any module more than once, all it does is bloat the build time pointlessly! To avoid slowing down the build by a large factor, I've put most of the modules of the code base into a collection of static libraries organised vaguely thematically (SSH, other backends, crypto, network, ...). That means all those modules can still be compiled just once each, because once each library is built it's reused unchanged for all the executable targets. One upside of this library-based structure is that now I don't have to manually specify exactly which objects go into which programs any more - it's enough to specify which libraries are needed, and the linker will figure out the fine detail automatically. So there's less maintenance to do in CMakeLists.txt when the source code changes. But that reorganisation also adds fragility, because of the trad Unix linker semantics of walking along the library list once each, so that cyclic references between your libraries will provoke link errors. The current setup builds successfully, but I suspect it only just manages it. (In particular, I've found that MinGW is the most finicky on this score of the Windows compilers I've tried building with. So I've included a MinGW test build in the new-look Buildscr, because otherwise I think there'd be a significant risk of introducing MinGW-only build failures due to library search order, which wasn't a risk in the previous library-free build organisation.) In the longer term I hope to be able to reduce the risk of that, via gradual reorganisation (in particular, breaking up too-monolithic modules, to reduce the risk of knock-on references when you included a module for function A and it also contains function B with an unsatisfied dependency you didn't really need). Ideally I want to reach a state in which the libraries all have sensibly described purposes, a clearly documented (partial) order in which they're permitted to depend on each other, and a specification of what stubs you have to put where if you're leaving one of them out (e.g. nocrypto) and what callbacks you have to define in your non-library objects to satisfy dependencies from things low in the stack (e.g. out_of_memory()). One thing that's gone completely missing in this migration, unfortunately, is the unfinished MacOS port linked against Quartz GTK. That's because it turned out that I can't currently build it myself, on my own Mac: my previous installation of GTK had bit-rotted as a side effect of an Xcode upgrade, and I haven't yet been able to persuade jhbuild to make me a new one. So I can't even build the MacOS port with the _old_ makefiles, and hence, I have no way of checking that the new ones also work. I hope to bring that port back to life at some point, but I don't want it to block the rest of this change.
2021-04-10 14:21:11 +00:00
#if !HAVE_STRTOUMAX
Build testcrypt on Windows. The bulk of this commit is the changes necessary to make testcrypt compile under Visual Studio. Unfortunately, I've had to remove my fiddly clever uses of C99 variadic macros, because Visual Studio does something unexpected when a variadic macro's expansion puts __VA_ARGS__ in the argument list of a further macro invocation: the commas don't separate further arguments. In other words, if you write #define INNER(x,y,z) some expansion involving x, y and z #define OUTER(...) INNER(__VA_ARGS__) OUTER(1,2,3) then gcc and clang will translate OUTER(1,2,3) into INNER(1,2,3) in the obvious way, and the inner macro will be expanded with x=1, y=2 and z=3. But try this in Visual Studio, and you'll get the macro parameter x expanding to the entire string 1,2,3 and the other two empty (with warnings complaining that INNER didn't get the number of arguments it expected). It's hard to cite chapter and verse of the standard to say which of those is _definitely_ right, though my reading leans towards the gcc/clang behaviour. But I do know I can't depend on it in code that has to compile under both! So I've removed the system that allowed me to declare everything in testcrypt.h as FUNC(ret,fn,arg,arg,arg), and now I have to use a different macro for each arity (FUNC0, FUNC1, FUNC2 etc). Also, the WRAPPED_NAME system is gone (because that too depended on the use of a comma to shift macro arguments along by one), and now I put a custom C wrapper around a function by simply re-#defining that function's own name (and therefore the subsequent code has to be a little more careful to _not_ pass functions' names between several macros before stringifying them). That's all a bit tedious, and commits me to a small amount of ongoing annoyance because now I'll have to add an explicit argument count every time I add something to testcrypt.h. But then again, perhaps it will make the code less incomprehensible to someone trying to understand it!
2019-01-11 06:25:28 +00:00
/*
* Work around lack of strtoumax in older MSVC libraries
*/
uintmax_t strtoumax(const char *nptr, char **endptr, int base)
{
return _strtoui64(nptr, endptr, base);
}
#endif
#if defined _M_ARM || defined _M_ARM64
bool platform_aes_hw_available(void)
{
return IsProcessorFeaturePresent(PF_ARM_V8_CRYPTO_INSTRUCTIONS_AVAILABLE);
}
bool platform_sha256_hw_available(void)
{
return IsProcessorFeaturePresent(PF_ARM_V8_CRYPTO_INSTRUCTIONS_AVAILABLE);
}
bool platform_sha1_hw_available(void)
{
return IsProcessorFeaturePresent(PF_ARM_V8_CRYPTO_INSTRUCTIONS_AVAILABLE);
}
Hardware-accelerated SHA-512 on the Arm architecture. The NEON support for SHA-512 acceleration looks very like SHA-256, with a pair of chained instructions to generate a 128-bit vector register full of message schedule, and another pair to update the hash state based on those. But since SHA-512 is twice as big in all dimensions, those four instructions between them only account for two rounds of it, in place of four rounds of SHA-256. Also, it's a tighter squeeze to fit all the data needed by those instructions into their limited number of register operands. The NEON SHA-256 implementation was able to keep its hash state and message schedule stored as 128-bit vectors and then pass combinations of those vectors directly to the instructions that did the work; for SHA-512, in several places you have to make one of the input operands to the main instruction by combining two halves of different vectors from your existing state. But that operation is a quick single EXT instruction, so no trouble. The only other problem I've found is that clang - in particular the version on M1 macOS, but as far as I can tell, even on current trunk - doesn't seem to implement the NEON intrinsics for the SHA-512 extension. So I had to bodge my own versions with inline assembler in order to get my implementation to compile under clang. Hopefully at some point in the future the gap might be filled and I can relegate that to a backwards-compatibility hack! This commit adds the same kind of switching mechanism for SHA-512 that we already had for SHA-256, SHA-1 and AES, and as with all of those, plumbs it through to testcrypt so that you can explicitly ask for the hardware or software version of SHA-512. So the test suite can run the standard test vectors against both implementations in turn. On M1 macOS, I'm testing at run time for the presence of SHA-512 by checking a sysctl setting. You can perform the same test on the command line by running "sysctl hw.optional.armv8_2_sha512". As far as I can tell, on Windows there is not yet any flag to test for this CPU feature, so for the moment, the new accelerated SHA-512 is turned off unconditionally on Windows.
2020-12-24 11:40:15 +00:00
bool platform_sha512_hw_available(void)
{
/* As of 2020-12-24, as far as I can tell from docs.microsoft.com,
* Windows on Arm does not yet provide a PF_ARM_V8_* flag for the
* SHA-512 architecture extension. */
return false;
}
#endif
bool is_console_handle(HANDLE handle)
{
DWORD ignored_output;
if (GetConsoleMode(handle, &ignored_output))
return true;
return false;
}