busybox-w32/scripts/kconfig, branch embed

Merge branch 'busybox' into merge

2018-04-09T07:50:34+00:00

scripts/kconfig/mconf.c: survive is SIGWINCH is not defined

2018-04-06T17:05:53+00:00

Signed-off-by: Denys Vlasenko

placate gcc 8.0.1 sprintf overflow warnings in config tools

2018-04-05T13:21:34+00:00

Signed-off-by: Denys Vlasenko

Merge branch 'busybox' into merge

2017-09-27T09:11:19+00:00

build system: fix a compiler warning

2017-09-07T12:50:00+00:00

Signed-off-by: Denys Vlasenko

build system: fix "allnoconfig" to clear all options. Closes 10296

2017-09-07T12:40:28+00:00

Signed-off-by: Denys Vlasenko

kbuild: avoid warning when building with KBUILD_NO_NLS

2017-07-14T14:14:37+00:00

The return values of bindtextdomain() and textdomain() are not actually used at all... Signed-off-by: Johannes Schindelin

kbuild: simulate force-renaming on Windows

2017-07-14T14:14:37+00:00

Calling rename() when a file with the target name exists already fails on Windows. Let's simply delete the target file, if it exists. This is usually a dangerous thing as it leaves time between deleting and renaming, during which (theoretically) another thread or process could have created the same file, and the rename() would fail again. Practically, we are talking about the kbuild system used to configure the build, where it does not matter, as we do not expect any other thread or process to interfere with the configuration files. Signed-off-by: Johannes Schindelin

kbuild: support at least non-interactive mode on Windows

2017-07-14T14:14:30+00:00

without POSIX, kbuild has some trouble compiling its support executables. Luckily, the parts that really lean on POSIX functionality are pretty much all only needed when configuring the build interactively. When compiling BusyBox for Win32, we do not actually need interactive configuration at all: we simply choose the default. Therefore, a lot of the stuff that is typically built for the Kconfig system is totally unnecessary (such as: compiling documentation via fork()&exec(), changing the window size, etc). Liberally put all of the problematic code behind #ifndef __MINGW32__ guards, just to get `make mingw64_defconfig` going in Git for Windows' SDK (which is a special-purpose version of MSYS2). Signed-off-by: Johannes Schindelin

fixdep: fix assumption that `long` is as large as `void *`

2017-07-14T12:47:31+00:00

It is not. At least not in general. And in particular not on 64-bit Windows, where sizeof(long) == 4. What the code wanted to use is actually called intptr_t. Note: `intptr_t` is a C99 feature. Signed-off-by: Johannes Schindelin