[uClinux-dev] [PATCH] NOMMU: fix malloc performance by adding uninitialized flag
From: Jie Zhang jie.zh...@analog.com The no-mmu code currently clears all anonymous mmap-ed memory. While this is what we want in the default case, all memory allocation from userspace under no-mmu has to go through this interface, including malloc() which is allowed to return uninitialized memory. This can easily be a significant performance slow down. So for constrained embedded systems were security is irrelevant, allow people to avoid unnecessarily clearing memory. Signed-off-by: Jie Zhang jie.zh...@analog.com Signed-off-by: Robin Getz rg...@analog.com Signed-off-by: Mike Frysinger vap...@gentoo.org --- Documentation/nommu-mmap.txt | 21 + fs/binfmt_elf_fdpic.c |2 +- include/asm-generic/mman-common.h |5 + init/Kconfig | 16 mm/nommu.c|7 --- 5 files changed, 47 insertions(+), 4 deletions(-) diff --git a/Documentation/nommu-mmap.txt b/Documentation/nommu-mmap.txt index b565e82..30d09e8 100644 --- a/Documentation/nommu-mmap.txt +++ b/Documentation/nommu-mmap.txt @@ -16,6 +16,27 @@ the CLONE_VM flag. The behaviour is similar between the MMU and no-MMU cases, but not identical; and it's also much more restricted in the latter case: + (*) Anonymous mappings - general case + + Anonymous mappings are not backed by any file, and according to the + Linux man pages (ver 2.22 or later) contents are initialized to zero. + + In the MMU case, regions are backed by arbitrary virtual pages, and the + contents are only mapped with physical pages and initialized to zero + when a read or write happens in that specific page. This spreads out + the time it takes to initialize the contents depending on the + read/write usage of the map. + + In the no-MMU case, anonymous mappings are backed by physical pages, + and the entire map is initialized to zero at allocation time. This + can cause significant delays in userspace during malloc() as the C + library does an anonymous mapping, and the kernel is doing a memset + for the entire map. Since malloc's memory is not required to be + cleared, an (optional) flag MAP_UNINITIALIZE can be passed to the + kernel's do_mmap, which will not initialize the contents to zero. + + uClibc supports this to provide a pretty significant speedup for malloc(). + (*) Anonymous mapping, MAP_PRIVATE In the MMU case: VM regions backed by arbitrary pages; copy-on-write diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index 38502c6..85db4a4 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -380,7 +380,7 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm, down_write(current-mm-mmap_sem); current-mm-start_brk = do_mmap(NULL, 0, stack_size, PROT_READ | PROT_WRITE | PROT_EXEC, -MAP_PRIVATE | MAP_ANONYMOUS | MAP_GROWSDOWN, +MAP_PRIVATE | MAP_ANONYMOUS | MAP_UNINITIALIZE | MAP_GROWSDOWN, 0); if (IS_ERR_VALUE(current-mm-start_brk)) { diff --git a/include/asm-generic/mman-common.h b/include/asm-generic/mman-common.h index 5ee13b2..dddf626 100644 --- a/include/asm-generic/mman-common.h +++ b/include/asm-generic/mman-common.h @@ -19,6 +19,11 @@ #define MAP_TYPE 0x0f/* Mask for type of mapping */ #define MAP_FIXED 0x10/* Interpret addr exactly */ #define MAP_ANONYMOUS 0x20/* don't use a file */ +#ifdef CONFIG_MMAP_ALLOW_UNINITIALIZE +# define MAP_UNINITIALIZE 0x400/* For anonymous mmap, memory could be uninitialized */ +#else +# define MAP_UNINITIALIZE 0x0 /* Don't support this flag */ +#endif #define MS_ASYNC 1 /* sync memory asynchronously */ #define MS_INVALIDATE 2 /* invalidate the caches */ diff --git a/init/Kconfig b/init/Kconfig index 09c5c64..ae15849 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1069,6 +1069,22 @@ config SLOB endchoice +config MMAP_ALLOW_UNINITIALIZE + bool Allow mmaped anonymous memory to be un-initialized + depends on EMBEDDED ! MMU + default n + help + Normally (and according to the Linux spec) mmap'ed MAP_ANONYMOUS + memory has it's contents initialized to zero. This kernel option + gives you the option of not doing that by adding a MAP_UNINITIALIZE + mmap flag (which uClibc's malloc() takes takes advantage of) + which provides a huge performance boost. + + Because of the obvious security issues, this option should only be + enabled on embedded devices which you control what is run in + userspace. Since that isn't a problem on no-MMU systems, it is + normally safe to say Y here. + config PROFILING
[uClinux-dev] Re: [PATCH v2] NOMMU: fix malloc performance by adding uninitialized flag
On Tue, Oct 13, 2009 at 07:20:21AM -0400, Mike Frysinger wrote: From: Jie Zhang jie.zh...@analog.com The NOMMU code currently clears all anonymous mmapped memory. While this is what we want in the default case, all memory allocation from userspace under NOMMU has to go through this interface, including malloc() which is allowed to return uninitialized memory. This can easily be a significant performance penalty. So for constrained embedded systems were security is irrelevant, allow people to avoid clearing memory unnecessarily. This also alters the ELF-FDPIC binfmt such that it obtains uninitialised memory for the brk and stack region. Signed-off-by: Jie Zhang jie.zh...@analog.com Signed-off-by: Robin Getz rg...@analog.com Signed-off-by: Mike Frysinger vap...@gentoo.org Signed-off-by: David Howells dhowe...@redhat.com Acked-by: Paul Mundt let...@linux-sh.org ___ uClinux-dev mailing list uClinux-dev@uclinux.org http://mailman.uclinux.org/mailman/listinfo/uclinux-dev This message was resent by uclinux-dev@uclinux.org To unsubscribe see: http://mailman.uclinux.org/mailman/options/uclinux-dev
Re: [uClinux-dev] building uClibc
On Mon, Oct 12, 2009 at 11:53:45AM +0100, Philip Nye wrote: I am trying to build a system for Coldfire with an up-to-date kernel, tools and library. I have the latest uClinux dist (patched to 20090810) and Codesourcery tools 4.3-209. This refused to build with an error of limits.h not found. Rather than a symlink hack, this led me to try a recent release of uClibc as the one in the uClinux dist is not so new (and I found this: http://gcc.gnu.org/ml/gcc/2008-08/msg00273.html), but I now get failures down the line because uClibc headers contain lots of libc_hidden_proto() declarations. As I understand it, these headers should be sanitized to remove this internal code for public use, but this is not happening, and I cannot see where it should be carried out. If I simply enter the uClibc directory and try to build from there, I get a different set of errors with missing header files. Can anyone suggest what I am doing wrong? Does the uClibc tree need to be patched for uClinux? Is there some extra configuration or build stage I need to do? Is there more to installing Codesourcery toolchain than simply setting PATH so it can be found? I am currently using a coldfire (5270/5271) with gcc 4.3.3, binutils 2.19.1, elf2flt (blackfin version from a late april checkout, other versions didn't work with gcc 4.3 at the time), 2.6.30 kernel, and uclibc 0.9.30.1 (with daemon() function #ifdef'd out to fix compile error). Anything you need? -- Len Sorensen ___ uClinux-dev mailing list uClinux-dev@uclinux.org http://mailman.uclinux.org/mailman/listinfo/uclinux-dev This message was resent by uclinux-dev@uclinux.org To unsubscribe see: http://mailman.uclinux.org/mailman/options/uclinux-dev
Re: [uClinux-dev] [PATCH] NOMMU: fix malloc performance by addinguninitialized flag
On Tue 13 Oct 2009 03:44, Mike Frysinger pondered: From: Jie Zhang jie.zh...@analog.com The no-mmu code currently clears all anonymous mmap-ed memory. While this is what we want in the default case, all memory allocation from userspace under no-mmu has to go through this interface, including malloc() which is allowed to return uninitialized memory. This can easily be a significant performance slow down. So for constrained embedded systems were security is irrelevant, allow people to avoid unnecessarily clearing memory. Signed-off-by: Jie Zhang jie.zh...@analog.com Signed-off-by: Robin Getz rg...@analog.com Should be rg...@blackfin.uclinux.org -- rg...@analog.com does not exist and will bounce. ___ uClinux-dev mailing list uClinux-dev@uclinux.org http://mailman.uclinux.org/mailman/listinfo/uclinux-dev This message was resent by uclinux-dev@uclinux.org To unsubscribe see: http://mailman.uclinux.org/mailman/options/uclinux-dev
[uClinux-dev] Re: [PATCH v3] NOMMU: fix malloc performance by adding uninitialized flag
Jivin Mike Frysinger lays it down ... From: Jie Zhang jie.zh...@analog.com The NOMMU code currently clears all anonymous mmapped memory. While this is what we want in the default case, all memory allocation from userspace under NOMMU has to go through this interface, including malloc() which is allowed to return uninitialized memory. This can easily be a significant performance penalty. So for constrained embedded systems were security is irrelevant, allow people to avoid clearing memory unnecessarily. This also alters the ELF-FDPIC binfmt such that it obtains uninitialised memory for the brk and stack region. Signed-off-by: Jie Zhang jie.zh...@analog.com Signed-off-by: Robin Getz robin.g...@analog.com Signed-off-by: Mike Frysinger vap...@gentoo.org Signed-off-by: David Howells dhowe...@redhat.com Acked-by: Paul Mundt let...@linux-sh.org Acked-by: David McCullough dav...@snapgear.com Cheers, Davidm v3 - tweak kconfig desc Documentation/nommu-mmap.txt | 26 ++ fs/binfmt_elf_fdpic.c |3 ++- include/asm-generic/mman-common.h |5 + init/Kconfig | 22 ++ mm/nommu.c|8 +--- 5 files changed, 60 insertions(+), 4 deletions(-) diff --git a/Documentation/nommu-mmap.txt b/Documentation/nommu-mmap.txt index b565e82..8e1ddec 100644 --- a/Documentation/nommu-mmap.txt +++ b/Documentation/nommu-mmap.txt @@ -119,6 +119,32 @@ FURTHER NOTES ON NO-MMU MMAP granule but will only discard the excess if appropriately configured as this has an effect on fragmentation. + (*) The memory allocated by a request for an anonymous mapping will normally + be cleared by the kernel before being returned in accordance with the + Linux man pages (ver 2.22 or later). + + In the MMU case this can be achieved with reasonable performance as + regions are backed by virtual pages, with the contents only being mapped + to cleared physical pages when a write happens on that specific page + (prior to which, the pages are effectively mapped to the global zero page + from which reads can take place). This spreads out the time it takes to + initialize the contents of a page - depending on the write-usage of the + mapping. + + In the no-MMU case, however, anonymous mappings are backed by physical + pages, and the entire map is cleared at allocation time. This can cause + significant delays during a userspace malloc() as the C library does an + anonymous mapping and the kernel then does a memset for the entire map. + + However, for memory that isn't required to be precleared - such as that + returned by malloc() - mmap() can take a MAP_UNINITIALIZED flag to + indicate to the kernel that it shouldn't bother clearing the memory before + returning it. Note that CONFIG_MMAP_ALLOW_UNINITIALIZED must be enabled + to permit this, otherwise the flag will be ignored. + + uClibc uses this to speed up malloc(), and the ELF-FDPIC binfmt uses this + to allocate the brk and stack region. + (*) A list of all the private copy and anonymous mappings on the system is visible through /proc/maps in no-MMU mode. diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index 38502c6..79d2b1a 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -380,7 +380,8 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm, down_write(current-mm-mmap_sem); current-mm-start_brk = do_mmap(NULL, 0, stack_size, PROT_READ | PROT_WRITE | PROT_EXEC, - MAP_PRIVATE | MAP_ANONYMOUS | MAP_GROWSDOWN, + MAP_PRIVATE | MAP_ANONYMOUS | + MAP_UNINITIALIZED | MAP_GROWSDOWN, 0); if (IS_ERR_VALUE(current-mm-start_brk)) { diff --git a/include/asm-generic/mman-common.h b/include/asm-generic/mman-common.h index 5ee13b2..2011126 100644 --- a/include/asm-generic/mman-common.h +++ b/include/asm-generic/mman-common.h @@ -19,6 +19,11 @@ #define MAP_TYPE 0x0f/* Mask for type of mapping */ #define MAP_FIXED0x10/* Interpret addr exactly */ #define MAP_ANONYMOUS0x20/* don't use a file */ +#ifdef CONFIG_MMAP_ALLOW_UNINITIALIZED +# define MAP_UNINITIALIZED 0x400 /* For anonymous mmap, memory could be uninitialized */ +#else +# define MAP_UNINITIALIZED 0x0 /* Don't support this flag */ +#endif #define MS_ASYNC 1 /* sync memory asynchronously */ #define MS_INVALIDATE2 /* invalidate the caches */ diff --git a/init/Kconfig b/init/Kconfig index 09c5c64..309cd9a 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1069,6 +1069,28