fs: hide names_cachep behind runtime access machinery
Subsystems (4)
PATCH v4 1/1 fs: hide names_cachep behind runtime access machinery
The var is used twice for every path lookup, while the cache is initialized early and stays valid for the duration.
---
ACHTUNG WARNING POZOR UWAGA Блять: the namei cache can be used by modules while the runtime machinery does not work with them. I did some testing and ifdef MODULE seems to work around the probnlem, but perhaps someone with build-fu could chime in? I verified with a hello world module that this works fine, but maybe I missed a case.
v4:
- unbotch the diff below, apologies for the spam
v3:
- fix compilation failure on longarch as reported by kernel test robot, used their repro script to confirm
v2:
- ifdef on module usage -- the runtime thing does *not* work with modules
- patch up the section warn, thanks to Pedro for spotting what's up with the problem
Linus cc'ed as he added the runtime thing + dcache usage in the first place.
Per the above the machinery does not support kernel modules and I have no interest in spending time to extend it.
I tried to add a compilation time warn should someone compile a module with it, but there is no shared header so I decided to drop the matter.
Should someone(tm) make this work for modules I'm not going to protest.
Vast majority of actual usage is coming from core kernel, which *is* getting the new treatment and I don't think the ifdef is particularly nasty.
fs/dcache.c | 3 +-- include/asm-generic/vmlinux.lds.h | 3 ++- include/linux/fs.h | 15 +++++++++++++-- 3 files changed, 16 insertions(+), 5 deletions(-)
fs/dcache.c +1 -2
@@ -35,8 +35,6 @@#include "internal.h" #include "mount.h" -#include <asm/runtime-const.h> -/* * Usage: * dcache->d_inode->i_lock protects:
@@ -3265,6 +3263,7 @@ void __init vfs_caches_init(void) { names_cachep =kmem_cache_create_usercopy ("names_cache" ,PATH_MAX ,0 ,SLAB_HWCACHE_ALIGN |SLAB_PANIC ,0 ,PATH_MAX ,NULL ); +runtime_const_init (ptr, names_cachep);dcache_init ();inode_init ();
include/asm-generic/vmlinux.lds.h +2 -1
@@ -939,7 +939,8 @@#define RUNTIME_CONST_VARIABLES \ RUNTIME_CONST(shift, d_hash_shift) \ - RUNTIME_CONST(ptr, dentry_hashtable) + RUNTIME_CONST(ptr, dentry_hashtable) \ + RUNTIME_CONST(ptr, names_cachep)/* Alignment must be consistent with (kunit_suite *) in include/kunit/test.h */ #define KUNIT_TABLE () \
include/linux/fs.h +13 -2
@@ -50,6 +50,8 @@#include <linux/unicode.h> #include <asm/byteorder.h> +#include <asm/runtime-const.h> +#include <uapi/linux/fs.h> struct backing_dev_info ;
@@ -2960,8 +2962,17 @@ extern void __init vfs_caches_init(void);extern struct kmem_cache *names_cachep; -#define __getname () kmem_cache_alloc(names_cachep, GFP_KERNEL) -#define __putname (name) kmem_cache_free(names_cachep, (void *)(name)) +/* +* XXX The runtime_const machinery does not support modules at the moment. +*/ +#ifdef MODULE +#define __names_cachep names_cachep +#else +#define __names_cachep runtime_const_ptr(names_cachep) +#endif + +#define __getname () kmem_cache_alloc(__names_cachep, GFP_KERNEL) +#define __putname (name) kmem_cache_free(__names_cachep, (void *)(name))extern struct super_block *blockdev_superblock;static inline bool sb_is_blkdev_sb (struct super_block *sb)
Signature · 1 line
2.34.1
kernel test robot
build botkernel test robot noticed the following build errors:
Hi Mateusz,
kernel test robot noticed the following build errors:
[auto build test ERROR on arnd-asm-generic/master]
[also build test ERROR on linus/master brauner-vfs/vfs.all linux/master v6.18-rc3 next-20251030] [If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]
url: https://github.com/intel-lab-lkp/linux/commits/Mateusz-Guzik/fs-hide-names_cachep-behind-runtime-access-machinery/20251030-185523 base: https://git.kernel.org/pub/scm/linux/kernel/git/arnd/asm-generic.git master patch link: https://lore.kernel.org/r/20251030105242.801528-1-mjguzik%40gmail.com patch subject: [PATCH v4] fs: hide names_cachep behind runtime access machinery config: riscv-allnoconfig (https://download.01.org/0day-ci/archive/20251030/[email protected]/config) compiler: riscv64-linux-gcc (GCC) 15.1.0 reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20251030/[email protected]/reproduce)
If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <[email protected]>
| Closes: https://lore.kernel.org/oe-kbuild-all/[email protected]/
All errors (new ones prefixed by >>):
In file included from arch/riscv/include/asm/runtime-const.h:7,
from include/linux/fs.h:53,
from include/linux/huge_mm.h:7,
from include/linux/mm.h:1016,
from arch/riscv/kernel/asm-offsets.c:8:
arch/riscv/include/asm/cacheflush.h: In function 'flush_cache_vmap':
>> arch/riscv/include/asm/cacheflush.h:49:13: error: implicit declaration of function 'is_vmalloc_or_module_addr' [-Wimplicit-function-declaration]
49 | if (is_vmalloc_or_module_addr((void *)start)) {
| ^~~~~~~~~~~~~~~~~~~~~~~~~
In file included from include/linux/compat.h:18,
from arch/riscv/include/asm/elf.h:12,
from include/linux/elf.h:6,
from include/linux/module.h:20,
from include/linux/device/driver.h:21,
from include/linux/device.h:32,
from include/linux/node.h:18,
from include/linux/memory.h:19,
from arch/riscv/include/asm/runtime-const.h:9:
include/uapi/linux/aio_abi.h: At top level:
>> include/uapi/linux/aio_abi.h:79:9: error: unknown type name '__kernel_rwf_t'; did you mean '__kernel_off_t'?
79 | __kernel_rwf_t aio_rw_flags; /* RWF_* flags */
| ^~~~~~~~~~~~~~
| __kernel_off_t make[3]: *** [scripts/Makefile.build:182: arch/riscv/kernel/asm-offsets.s] Error 1 make[3]: Target 'prepare' not remade because of errors.
make[2]: *** [Makefile:1282: prepare0] Error 2
make[2]: Target 'prepare' not remade because of errors.
make[1]: *** [Makefile:248: __sub-make] Error 2
make[1]: Target 'prepare' not remade because of errors.
make: *** [Makefile:248: __sub-make] Error 2
make: Target 'prepare' not remade because of errors.
vim +/is_vmalloc_or_module_addr +49 arch/riscv/include/asm/cacheflush.h
08f051eda33b51 Andrew Waterman 2017-10-25 42
7e3811521dc393 Alexandre Ghiti 2023-07-25 43 #ifdef CONFIG_64BIT
503638e0babf36 Alexandre Ghiti 2024-07-17 44 extern u64 new_vmalloc[NR_CPUS / sizeof(u64) + 1];
503638e0babf36 Alexandre Ghiti 2024-07-17 45 extern char _end[];
503638e0babf36 Alexandre Ghiti 2024-07-17 46 #define flush_cache_vmap flush_cache_vmap
503638e0babf36 Alexandre Ghiti 2024-07-17 47 static inline void flush_cache_vmap(unsigned long start, unsigned long end)
503638e0babf36 Alexandre Ghiti 2024-07-17 48 {
503638e0babf36 Alexandre Ghiti 2024-07-17 @49 if (is_vmalloc_or_module_addr((void *)start)) {
503638e0babf36 Alexandre Ghiti 2024-07-17 50 int i;
503638e0babf36 Alexandre Ghiti 2024-07-17 51
503638e0babf36 Alexandre Ghiti 2024-07-17 52 /*
503638e0babf36 Alexandre Ghiti 2024-07-17 53 * We don't care if concurrently a cpu resets this value since
503638e0babf36 Alexandre Ghiti 2024-07-17 54 * the only place this can happen is in handle_exception() where
503638e0babf36 Alexandre Ghiti 2024-07-17 55 * an sfence.vma is emitted.
503638e0babf36 Alexandre Ghiti 2024-07-17 56 */
503638e0babf36 Alexandre Ghiti 2024-07-17 57 for (i = 0; i < ARRAY_SIZE(new_vmalloc); ++i)
503638e0babf36 Alexandre Ghiti 2024-07-17 58 new_vmalloc[i] = -1ULL;
503638e0babf36 Alexandre Ghiti 2024-07-17 59 }
503638e0babf36 Alexandre Ghiti 2024-07-17 60 }
7a92fc8b4d2068 Alexandre Ghiti 2023-12-12 61 #define flush_cache_vmap_early(start, end) local_flush_tlb_kernel_range(start, end)
7e3811521dc393 Alexandre Ghiti 2023-07-25 62 #endif
7e3811521dc393 Alexandre Ghiti 2023-07-25 63 Signature · 2 lines
0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki
I'm not sending a v5. If you guys are fine with the patch I'm going to fix up whatever other fallout later.
Quoted 87 lines · kernel test robot
Hi Mateusz,
kernel test robot noticed the following build errors:
[auto build test ERROR on arnd-asm-generic/master]
[also build test ERROR on linus/master brauner-vfs/vfs.all linux/master v6.18-rc3 next-20251030] [If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]url: https://github.com/intel-lab-lkp/linux/commits/Mateusz-Guzik/fs-hide-names_cachep-behind-runtime-access-machinery/20251030-185523 base: https://git.kernel.org/pub/scm/linux/kernel/git/arnd/asm-generic.git master patch link: https://lore.kernel.org/r/20251030105242.801528-1-mjguzik%40gmail.com patch subject: [PATCH v4] fs: hide names_cachep behind runtime access machinery config: riscv-allnoconfig (https://download.01.org/0day-ci/archive/20251030/[email protected]/config) compiler: riscv64-linux-gcc (GCC) 15.1.0 reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20251030/[email protected]/reproduce)If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <[email protected]>
| Closes: https://lore.kernel.org/oe-kbuild-all/[email protected]/All errors (new ones prefixed by >>):
In file included from
arch/riscv/include/asm/runtime-const.h:7,from include/linux/fs.h:53, from include/linux/huge_mm.h:7, from include/linux/mm.h:1016, from arch/riscv/kernel/asm-offsets.c:8:
arch/riscv/include/asm/cacheflush.h: In function 'flush_cache_vmap':Quoted 1 line
Quoted 1 line
arch/riscv/include/asm/cacheflush.h:49:13: error: implicit declaration of function 'is_vmalloc_or_module_addr' [-Wimplicit-function-declaration]49 | if (is_vmalloc_or_module_addr((void *)start)) { | ^~~~~~~~~~~~~~~~~~~~~~~~~In file included from
include/linux/compat.h:18,
fromarch/riscv/include/asm/elf.h:12, frominclude/linux/elf.h:6,
frominclude/linux/module.h:20, frominclude/linux/device/driver.h:21, frominclude/linux/device.h:32, frominclude/linux/node.h:18,
frominclude/linux/memory.h:19, fromarch/riscv/include/asm/runtime-const.h:9:
include/uapi/linux/aio_abi.h: At top level:Quoted 1 line
Quoted 1 line
include/uapi/linux/aio_abi.h:79:9: error: unknown type name '__kernel_rwf_t'; did you mean '__kernel_off_t'?79 | __kernel_rwf_t aio_rw_flags; /* RWF_* flags */ | ^~~~~~~~~~~~~~ | __kernel_off_tmake[3]: *** [
scripts/Makefile.build:182:arch/riscv/kernel/asm-offsets.s] Error 1 make[3]: Target 'prepare' not remade because of errors.
make[2]: *** [Makefile:1282: prepare0] Error 2
make[2]: Target 'prepare' not remade because of errors.
make[1]: *** [Makefile:248: __sub-make] Error 2
make[1]: Target 'prepare' not remade because of errors.
make: *** [Makefile:248: __sub-make] Error 2
make: Target 'prepare' not remade because of errors.vim +/is_vmalloc_or_module_addr +49
arch/riscv/include/asm/cacheflush.h08f051eda33b51 Andrew Waterman 2017-10-25 42 7e3811521dc393 Alexandre Ghiti 2023-07-25 43 #ifdef CONFIG_64BIT 503638e0babf36 Alexandre Ghiti 2024-07-17 44 extern u64 new_vmalloc[NR_CPUS / sizeof(u64) + 1]; 503638e0babf36 Alexandre Ghiti 2024-07-17 45 extern char _end[]; 503638e0babf36 Alexandre Ghiti 2024-07-17 46 #define flush_cache_vmap flush_cache_vmap 503638e0babf36 Alexandre Ghiti 2024-07-17 47 static inline void flush_cache_vmap(unsigned long start, unsigned long end) 503638e0babf36 Alexandre Ghiti 2024-07-17 48 { 503638e0babf36 Alexandre Ghiti 2024-07-17 @49 if (is_vmalloc_or_module_addr((void *)start)) { 503638e0babf36 Alexandre Ghiti 2024-07-17 50 int i; 503638e0babf36 Alexandre Ghiti 2024-07-17 51 503638e0babf36 Alexandre Ghiti 2024-07-17 52 /* 503638e0babf36 Alexandre Ghiti 2024-07-17 53 * We don't care if concurrently a cpu resets this value since 503638e0babf36 Alexandre Ghiti 2024-07-17 54 * the only place this can happen is in handle_exception() where 503638e0babf36 Alexandre Ghiti 2024-07-17 55 * an sfence.vma is emitted. 503638e0babf36 Alexandre Ghiti 2024-07-17 56 */ 503638e0babf36 Alexandre Ghiti 2024-07-17 57 for (i = 0; i < ARRAY_SIZE(new_vmalloc); ++i) 503638e0babf36 Alexandre Ghiti 2024-07-17 58 new_vmalloc[i] = -1ULL; 503638e0babf36 Alexandre Ghiti 2024-07-17 59 } 503638e0babf36 Alexandre Ghiti 2024-07-17 60 } 7a92fc8b4d2068 Alexandre Ghiti 2023-12-12 61 #define flush_cache_vmap_early(start, end) local_flush_tlb_kernel_range(start, end) 7e3811521dc393 Alexandre Ghiti 2023-07-25 62 #endif 7e3811521dc393 Alexandre Ghiti 2023-07-25 63--
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki
Quoted 2 lines · Mateusz Guzik
Should someone(tm) make this work for modules I'm not going to protest.
Btw, that's a good point. When I did this all originally, I explicitly did *not* want to make it work for modules, but I do note that it can be used for modules very easily by mistake.
Quoted 3 lines
Vast majority of actual usage is coming from core kernel, which *is* getting the new treatment and I don't think the ifdef is particularly nasty.
I suspect we should make that #ifdef be an integral part of the runtime const headers. Because right now it's really much too easy to get it wrong, and I wonder if we already do.
Linus
Quoted 9 lines · Linus Torvalds
Quoted 2 lines · Mateusz Guzik
Should someone(tm) make this work for modules I'm not going to protest.
Btw, that's a good point. When I did this all originally, I explicitly did *not* want to make it work for modules, but I do note that it can be used for modules very easily by mistake.
Quoted 8 lines
Quoted 3 lines
Vast majority of actual usage is coming from core kernel, which *is* getting the new treatment and I don't think the ifdef is particularly nasty.
I suspect we should make that #ifdef be an integral part of the runtime const headers. Because right now it's really much too easy to get it wrong, and I wonder if we already do.
I don't know if you are suggesting to make the entire thing fail to compile if included for a module, or to transparently convert runtime-optimized access into plain access.
I presume the former.
Even then, there is the cosmetic issue of deciding whether to ifdef within headers or create include/linux/runtime-constants.h which pulls in the per-arch stuff and ifdef in there.
Personally I'm leaning towards just forcing compilation failure and duplicating the code to do it within per-arch headers, for example:
(quoted diff) +0 -0
b/arch/x86/include/asm/runtime-const.h
index 8d983cfd06ea..42e6303b52f7 100644
arch/x86/include/asm/runtime-const.h +4 -0
@@ -2,6 +2,10 @@#ifndef _ASM_RUNTIME_CONST_H#define _ASM_RUNTIME_CONST_H +#ifdef MODULE +#error "this functionality is not available for modules" +#endif +#ifdef __ASSEMBLY__ .macro RUNTIME_CONST_PTR sym reg
Just tell me which way you want this sorted out and if it is less than few minutes of screwing around I'll take care of it.
[ Adding Thomas, because he's been working on our x86 uaccess code, and I actually think we get this all wrong for access_ok() etc ]
Quoted 6 lines · Mateusz Guzik
I don't know if you are suggesting to make the entire thing fail to compile if included for a module, or to transparently convert runtime-optimized access into plain access.
I presume the former.
I think *including* it should be ok, because we have things like <asm/uaccess.h> - or your addition to <linux/fs.h> - that use it for core functionality that is then not supported for module use.
Yeah, in a perfect world we'd have those things only in "internal" headers and people couldn't include them even by mistake, but that ends up being a pain.
So I don't think your
+#ifdef MODULE
+#error "this functionality is not available for modules" +#endif
model works, because I think it might be too painful to fix (but hey, maybe I'm wrong).
I was thinking more along the lines of forcing linker errors or something like that.
ENTIRELY UNTESTED PATCH attached - may not compile at all, but something like this *might* work to show when a module uses the runtime_const infrastructure.
And I think I should have made the default runtime const value something small. But the original use of this was just the dcache code, and that used it purely as a pointer, so a non-fixed-up address would cause a nice clean oops. Then I started using it for the user access limit, and now it's actually wrong if used by modules.
Thanks for making me think about this. I thought about the module case *originally*, but then with some of the expanded use I definitely did not.
Linus
arch/x86/include/asm/runtime-const.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-)
arch/x86/include/asm/runtime-const.h +12 -1
@@ -2,7 +2,18 @@#ifndef _ASM_RUNTIME_CONST_H#define _ASM_RUNTIME_CONST_H -#ifdef __ASSEMBLY__ +#ifdef MODULE + +/* +* None of this is available to modules, so we force link errors +* if people try to use it +*/ +extern unsigned long no_runtime_const; +#define runtime_const_ptr (sym) ((typeof(sym))no_runtime_const) +#define runtime_const_shift_right_32 (val, sym) ((u32)no_runtime_const) +#define runtime_const_init (type,sym) do { no_runtime_const=1; } while (0) + +#elif defined(__ASSEMBLY__) .macro RUNTIME_CONST_PTR sym reg movq $0x0123456789abcdef, %\reg
Quoted 4 lines · Linus Torvalds
ENTIRELY UNTESTED PATCH attached - may not compile at all, but something like this *might* work to show when a module uses the
runtime_constinfrastructure.
Hmm. I tested it, and it seems to work. And by "work", I mean "show real existing problems":
ERROR: modpost: "no_runtime_const" [arch/x86/kvm/kvm.ko] undefined!
ERROR: modpost: "no_runtime_const" [arch/x86/kvm/kvm-amd.ko] undefined!
ERROR: modpost: "no_runtime_const" [fs/erofs/erofs.ko] undefined!
ERROR: modpost: "no_runtime_const" [lib/tests/usercopy_kunit.ko] undefined!
ERROR: modpost: "no_runtime_const" [lib/test_lockup.ko] undefined!
ERROR: modpost: "no_runtime_const" [drivers/acpi/acpi_dbg.ko] undefined!
ERROR: modpost: "no_runtime_const" [drivers/xen/xen-privcmd.ko] undefined!
ERROR: modpost: "no_runtime_const"
[drivers/iommu/iommufd/iommufd.ko] undefined!
ERROR: modpost: "no_runtime_const" [drivers/gpu/drm/drm.ko] undefined!
ERROR: modpost: "no_runtime_const"
[drivers/gpu/drm/radeon/radeon.ko] undefined!
WARNING: modpost: suppressed 29 unresolved symbol warnings because
there were too many)
and yeah, I think it comes from access_ok() use.
It turns out that all of this "works", but entirely by mistake, and not really properly.
I picked the default value for the runtime_const pointer of 0x0123456789abcdef because it's easy to see in disassembly, and because it causes a nice oops if not fixed up because it's a non-canonical address on normal x86-64.
And *because* it's in that non-canonical range, it's actually "good enough" for access_ok() in practice. But it sure as hell ain't right.
I think that for x86-64 and for the short term, the right thing to do is to make access_ok() be out-of-line. Nobody should use it any more anyway, it's a legacy operation for back when doing access_ok() + __get_user() was a big and valid optimization.
So I think the other thing that kind of saved us - but probably also meant that the bug wasn't as obvious as it should have been - was exactly the fact that it affects that operation that really nobody should use anyway.
Linus
Quoted 26 lines · Linus Torvalds
[ Adding Thomas, because he's been working on our x86 uaccess code, and I actually think we get this all wrong for
access_ok()etc ]Quoted 6 lines · Mateusz Guzik
I don't know if you are suggesting to make the entire thing fail to compile if included for a module, or to transparently convert runtime-optimized access into plain access.
I presume the former.
I think *including* it should be ok, because we have things like <
asm/uaccess.h> - or your addition to <linux/fs.h> - that use it for core functionality that is then not supported for module use.Yeah, in a perfect world we'd have those things only in "internal" headers and people couldn't include them even by mistake, but that ends up being a pain.
So I don't think your
(quoted diff) +3
-0+#ifdef MODULE +#error "this functionality is not available for modules" +#endif
Quoted 3 lines
model works, because I think it might be too painful to fix (but hey, maybe I'm wrong).
In my proposal the patch which messes with the namei cache address would have the following in fs.h:
#ifndef MODULE
#include <asm/runtime-const.h>
#endif
As in, unless the kernel itself is being compiled, it would pretend the runtime machinery does not even exist, which imo is preferable to failing later at link time.
Then whatever functionality using runtime-const is straight up not available and code insisting on providing something for modules anyway is forced to provide an ifdefed implementation.
Ignoring the safety vs modules thing and back to the names_cachep
patch: the reported riscv build failure has proven problematic to fix. Turns out mm.h includes mm_huge.h, which then includes fs.h(!). Adding the runtime-const.h include into fs.h then results in compilation failure on that platform as it depends on vmalloc-related symbols which are only getting declared *after* fs.h gets included.
I tried to get rid of the fs.h inclusion in mm_huge.h, but that uncovered a bunch of other build failures where code works only because fs.h got sneaked in by someone else.
Given the level of bullshit here it may be it is just straight up infeasible to include runtime-const.h in fs.h without major rototoiling, which I'm not signing up for.
I wonder if it would make sense to bypass the problem by moving the pathname handling routines to a different header -- might be useful in its own right to slim down the kitchen sink that fs.h turned out to be, but that's another bikeshed-y material.
I may end up just ditching this for the time being.
Quoted 38 lines · Mateusz Guzik
Quoted 26 lines · Linus Torvalds
[ Adding Thomas, because he's been working on our x86 uaccess code, and I actually think we get this all wrong for
access_ok()etc ]Quoted 6 lines · Mateusz Guzik
I don't know if you are suggesting to make the entire thing fail to compile if included for a module, or to transparently convert runtime-optimized access into plain access.
I presume the former.
I think *including* it should be ok, because we have things like <
asm/uaccess.h> - or your addition to <linux/fs.h> - that use it for core functionality that is then not supported for module use.Yeah, in a perfect world we'd have those things only in "internal" headers and people couldn't include them even by mistake, but that ends up being a pain.
So I don't think your
(quoted diff) +3
-0+#ifdef MODULE +#error "this functionality is not available for modules" +#endifQuoted 3 lines
model works, because I think it might be too painful to fix (but hey, maybe I'm wrong).
In my proposal the patch which messes with the namei cache address would have the following in
fs.h:
#ifndef MODULE
#include <asm/runtime-const.h>
#endif
Quoted 8 lines
As in, unless the kernel itself is being compiled, it would pretend the runtime machinery does not even exist, which imo is preferable to failing later at link time.
Then whatever functionality using runtime-const is straight up not available and code insisting on providing something for modules anyway is forced to provide an ifdefed implementation.
Here is a build-tested diff for bzImage itself and M=fs/erofs on the x86-64 architecture.
It keeps access_ok() inline for demostrative purposes, I have no opinion what to do with this specific sucker.
arch/x86/include/asm/runtime-const.h +4 -0
@@ -2,6 +2,10 @@#ifndef _ASM_RUNTIME_CONST_H#define _ASM_RUNTIME_CONST_H +#ifdef MODULE +#error "this functionality is not available for modules" +#endif +#ifdef __ASSEMBLY__ .macro RUNTIME_CONST_PTR sym reg
arch/x86/include/asm/uaccess_64.h +8 -7
@@ -12,13 +12,14 @@#include <asm/cpufeatures.h> #include <asm/page.h> #include <asm/percpu.h> -#include <asm/runtime-const.h> -/* -* Virtual variable: there's no actual backing store for this, -* it can purely be used as 'runtime_const_ptr(USER_PTR_MAX)' -*/ extern unsigned long USER_PTR_MAX ; +#ifdef MODULE +#define __USER_PTR_MAX USER_PTR_MAX +#else +#include <asm/runtime-const.h> +#define __USER_PTR_MAX runtime_const_ptr(USER_PTR_MAX) +#endif #ifdef CONFIG_ADDRESS_MASKING /*
@@ -54,7 +55,7 @@ static inline unsigned long __untagged_addr_remote(struct mm_struct *mm,#endif #define valid_user_address (x) \ - likely((__force unsigned long)(x) <= runtime_const_ptr(USER_PTR_MAX)) + likely((__force unsigned long)(x) <= __USER_PTR_MAX)/* * Masking the user address is an alternative to a conditional
@@ -67,7 +68,7 @@ static inline void __user *mask_user_address(const void __user *ptr) asm("cmp %1,%0\n\t" "cmova %1,%0" :"=r" (ret) - :"r" (runtime_const_ptr (USER_PTR_MAX )), + :"r" (__USER_PTR_MAX),"0" (ptr));return ret; }
arch/x86/kernel/cpu/common.c +3 -2
@@ -78,6 +78,9 @@ DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info);EXPORT_PER_CPU_SYMBOL (cpu_info); +unsigned long USER_PTR_MAX __ro_after_init =TASK_SIZE_MAX ; +EXPORT_SYMBOL (USER_PTR_MAX ); +u32 elf_hwcap2__read_mostly ;/* Number of siblings per CPU package */
@@ -2575,8 +2578,6 @@ void __init arch_cpu_finalize_init(void)alternative_instructions ();if (IS_ENABLED (CONFIG_X86_64 )) { -unsigned long USER_PTR_MAX =TASK_SIZE_MAX ; -/* * Enable this when LAM is gated on LASS support if (cpu_feature_enabled(X86_FEATURE_LAM))
Christian Brauner
maintainerQuoted 4 lines
I wonder if it would make sense to bypass the problem by moving the pathname handling routines to a different header -- might be useful in its own right to slim down the kitchen sink that
fs.hturned out to be, but that's another bikeshed-y material.
fs.h needs to be split up. It's on my ToDo but let's just say there's a lot of stuff on it so it's not really high-priority. If you have a good reason to move something out of there by my guest. It would be appreciated!
Quoted 10 lines · Christian Brauner
Quoted 5 lines
I wonder if it would make sense to bypass the problem by moving the pathname handling routines to a different header -- might be useful in its own right to slim down the kitchen sink that
fs.hturned out to be, but that's another bikeshed-y material.
fs.hneeds to be split up. It's on my ToDo but let's just say there's a lot of stuff on it so it's not really high-priority. If you have a good reason to move something out of there by my guest. It would be appreciated!
I slept on it and I think the pragmatic way forward is to split up runtime-const.h instead.
The code to emit patchable access has very little requirements in terms header files. In contrast, the code to do the patching can pull in all kinds of headers with riscv being a great example.
While I ran into problems with fs.h on riscv specifically, one has to expect the pre-existing mess will be posing an issue in other places should they try to use the machinery.
So I think runtime-const-accessors.h (pardon the long name) for things like fs.h would be the way forward, regardless of what happens with the latter in the long run. I'm going to hack it up later.
Quoted 3 lines · Mateusz Guzik
I slept on it and I think the pragmatic way forward is to split up
runtime-const.hinstead.
I don't think that would be wrong, but I do think the real bug was to include runtime-const.h in any headers at all.
It should only be included by C code that is always built-in.
And it's all my fault and due to incompetence: this was introduced by me in commit 86e6b1547b3d ("x86: fix user address masking non-canonical speculation issue").
The original runtime const design was for core code optimization only, and I just didn't think about the module case when I did that thing.
Sadly, this goes beyond just the trivial "access_ok()" - which can trivially be fixed by just making it out-of-line. It ends up impacting user address masking too.
It so happens that all our can_do_masked_user_access() optimizations are in core code, so it's not an *actual* bug, just a potential one, but it's one that Thomas' patches to do the nice scoped user accesses will likely make much more common, just because his interface is so much more convenient.
End result: I think your patch to just use
#ifdef MODULE
in the header was the right one. Except instead of that
+#ifdef MODULE
+#define __USER_PTR_MAX USER_PTR_MAX
+#else
thing, I think the right thing to do is to just do
#ifdef MODULE
#include <asm-generic/runtime-const.h>
#undef runtime_const_init
#else
#include <asm/runtime-const.h>
#endif
in the x86 uaccess_64.h header file.
Let me think about this a bit more, but I feel really bad about having missed this bug. I'm relieved to say that it looks largely harmless in practice, but it really is me having royally messed up.
Linus
Quoted 9 lines · Linus Torvalds
Quoted 3 lines · Mateusz Guzik
I slept on it and I think the pragmatic way forward is to split up
runtime-const.hinstead.I don't think that would be wrong, but I do think the real bug was to include
runtime-const.hin any headers at all.
I think that was the right call, just that realities of going past amd64 caught up with the header mixing the dependency-lean (if you will) access with dependency-heavy patching of it.
Again with names_cachep as an example: there are different spots which use it. On paper, fs.h can include the right header(tm) and everyone is transparently covered. Without that every single .c file has to be adjusted.
But that's only few spots, so one could argue that's a minor inconvenience.
Suppose one was trying to make systemic use of of the machinery for other stuff. For sake of argument, say everything marked ro_after_init?
With a lean header it will be feasible to sneak it in to something de facto included everywhere.
[snip]
Quoted 12 lines
End result: I think your patch to just use
#ifdef MODULEin the header was the right one. Except instead of that
(quoted diff) +3
-0+#ifdef MODULE +#define __USER_PTR_MAX USER_PTR_MAX +#elsething, I think the right thing to do is to just do
Quoted 9 lines
#ifdef MODULE #include <asm-generic/runtime-const.h> #undef runtime_const_init #else #include <asm/runtime-const.h>#endif
in the x86
uaccess_64.hheader file.
While I can concede __USER_PTR_MAX naming is not the best here, I think your approach looks weird but it also complicates things.
I take the intent would be still to fail compilation if runtime-const.h is included. The file is there for the premier platforms, but most platforms still resort to asm-generic/runtime-const.h. I think it would be beneficial to have that sucker also cause compilation failure if included for a module. That way someone developing on a non-mainstream platform is less likely to post a patch bogus on this front.
Quoted 4 lines
Let me think about this a bit more, but I feel really bad about having missed this bug. I'm relieved to say that it looks largely harmless in practice, but it really is me having royally messed up.
Sure, there is no rush whatsoever. The original patch was meant to be a 5 minute detour and it is not holding up any work.
Quoted 6 lines · Mateusz Guzik
I take the intent would be still to fail compilation if
runtime-const.his included. The file is there for the premier platforms, but most platforms still resort toasm-generic/runtime-const.h. I think it would be beneficial to have that sucker also cause compilation failure if included for a module.
Good point. Yeah, I think you're right.
Linus
cover runtime-const header split and whatnot
So I slapped together what I described into a WIP patchset.
The runtime header treatment so far only done for x86 and riscv.
I verified things still compile with this in fs.h:
#ifndef MODULE
#include <asm/runtime-const-accessors.h> #endif
The -accessors suffix is not my favourite, but I don't have a better name.
If this looks like I'm going to do the needful(tm).
Mateusz Guzik (3):
x86: fix access_ok() and valid_user_address() using wrong USER_PTR_MAX
in modules
runtime-const: split headers between accessors and fixup; disable for
modules
fs: hide names_cachep behind runtime access machinery
.../include/asm/runtime-const-accessors.h | 151 ++++++++++++++++++ arch/riscv/include/asm/runtime-const.h | 142 +--------------- .../x86/include/asm/runtime-const-accessors.h | 45 ++++++ arch/x86/include/asm/runtime-const.h | 38 +---- arch/x86/include/asm/uaccess_64.h | 17 +- arch/x86/kernel/cpu/common.c | 8 +- fs/dcache.c | 1 + include/asm-generic/vmlinux.lds.h | 3 +- include/linux/fs.h | 17 +- 9 files changed, 232 insertions(+), 190 deletions(-) create mode 100644 arch/riscv/include/asm/runtime-const-accessors.h create mode 100644 arch/x86/include/asm/runtime-const-accessors.h
Signature · 1 line
2.34.1
PATCH 1/3 x86: fix access_ok() and valid_user_address() using wrong USER_PTR_MAX in modules
[real commit message will land here later]
--- arch/x86/include/asm/uaccess_64.h | 17 +++++++++-------- arch/x86/kernel/cpu/common.c | 8 +++++--- 2 files changed, 14 insertions(+), 11 deletions(-)
arch/x86/include/asm/uaccess_64.h +9 -8
@@ -12,13 +12,14 @@#include <asm/cpufeatures.h> #include <asm/page.h> #include <asm/percpu.h> -#include <asm/runtime-const.h> -/* -* Virtual variable: there's no actual backing store for this, -* it can purely be used as 'runtime_const_ptr(USER_PTR_MAX)' -*/ -extern unsigned long USER_PTR_MAX ; +extern unsigned long user_ptr_max; +#ifdef MODULE +#define __user_ptr_max_accessor user_ptr_max +#else +#include <asm/runtime-const.h> +#define __user_ptr_max_accessor runtime_const_ptr(user_ptr_max) +#endif #ifdef CONFIG_ADDRESS_MASKING /*
@@ -54,7 +55,7 @@ static inline unsigned long __untagged_addr_remote(struct mm_struct *mm,#endif #define valid_user_address (x) \ - likely((__force unsigned long)(x) <= runtime_const_ptr(USER_PTR_MAX)) + likely((__force unsigned long)(x) <= __user_ptr_max_accessor)/* * Masking the user address is an alternative to a conditional
@@ -67,7 +68,7 @@ static inline void __user *mask_user_address(const void __user *ptr) asm("cmp %1,%0\n\t" "cmova %1,%0" :"=r" (ret) - :"r" (runtime_const_ptr (USER_PTR_MAX )), + :"r" (__user_ptr_max_accessor),"0" (ptr));return ret; }
arch/x86/kernel/cpu/common.c +5 -3
@@ -78,6 +78,9 @@ DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info);EXPORT_PER_CPU_SYMBOL (cpu_info); +unsigned long user_ptr_max__ro_after_init ; +EXPORT_SYMBOL (user_ptr_max); +u32 elf_hwcap2__read_mostly ;/* Number of siblings per CPU package */
@@ -2575,14 +2578,13 @@ void __init arch_cpu_finalize_init(void)alternative_instructions ();if (IS_ENABLED (CONFIG_X86_64 )) { -unsigned long USER_PTR_MAX =TASK_SIZE_MAX ; - + user_ptr_max =TASK_SIZE_MAX ;/* * Enable this when LAM is gated on LASS support if (cpu_feature_enabled(X86_FEATURE_LAM)) USER_PTR_MAX = (1ul << 63) - PAGE_SIZE; */ -runtime_const_init (ptr,USER_PTR_MAX ); +runtime_const_init (ptr, user_ptr_max);/* * Make sure the first 2MB area is not mapped by huge pages
Signature · 1 line
2.34.1
Re: [PATCH 1/3] x86: fix access_ok() and valid_user_address() using wrong USER_PTR_MAX in modules
arch/x86/include/asm/uaccess_64.h line 16
Quoted 3 lines · Mateusz Guzik
arch/x86/include/asm/uaccess_64.h +1
-1-extern unsigned long USER_PTR_MAX ; +extern unsigned long user_ptr_max;
Yeah, this doesn't work at all.
We still use USER_PTR_MAX in other places, including the linker script and arch/x86/lib/getuser.S
So you changed about half the places to the new name, breaking the others.
Linus
Re: [PATCH 1/3] x86: fix access_ok() and valid_user_address() using wrong USER_PTR_MAX in modules
Quoted 8 lines · Linus Torvalds
arch/x86/include/asm/uaccess_64.h line 16
Quoted 3 lines · Mateusz Guzik
arch/x86/include/asm/uaccess_64.h +1
-1-extern unsigned long USER_PTR_MAX ; +extern unsigned long user_ptr_max;Yeah, this doesn't work at all.
Quoted 5 lines
We still use
USER_PTR_MAXin other places, including the linker script andarch/x86/lib/getuser.SSo you changed about half the places to the new name, breaking the others.
True, but note there is no sign-off on the patch as this is not a real submission yet.
Changing this to lower case was a last minute adjustment and it really does not matter in this context, interestingly enough the kernel still built just fine, just threw the following:
ld: warning: orphan section runtime_ptr_user_ptr_max' from vmlinux.o' being placed in section `runtime_ptr_user_ptr_max'
Anyway, the thing which does matter in this patchset is that a riscv kernel now builds with fs.h including runtime-const-accessors.h and this is the bit I'm fishing for comments on.
Re: [PATCH 1/3] x86: fix access_ok() and valid_user_address() using wrong USER_PTR_MAX in modules
In reply to Mateusz GuzikQuoted 1 line · On Fri, 31 Oct 2025 18:42:18 +0100 Mateusz Guzik <[email protected]> wrote:
[real commit message will land here later]
Hmmm... modules use the 0x123456789abcdef0 placeholder (the 0 might not be in the right place), this is non-canonical so nothing is badly broken. Just allows speculative accesses to kernel space on some cpu.
Quoted 53 lines
--- arch/x86/include/asm/uaccess_64.h | 17 +++++++++-------- arch/x86/kernel/cpu/common.c | 8 +++++--- 2 files changed, 14 insertions(+), 11 deletions(-)arch/x86/include/asm/uaccess_64.h +9
-8@@ -12,13 +12,14 @@#include <asm/cpufeatures.h> #include <asm/page.h> #include <asm/percpu.h> -#include <asm/runtime-const.h> -/* -* Virtual variable: there's no actual backing store for this, -* it can purely be used as 'runtime_const_ptr(USER_PTR_MAX)' -*/ -extern unsigned long USER_PTR_MAX ; +extern unsigned long user_ptr_max; +#ifdef MODULE +#define __user_ptr_max_accessor user_ptr_max +#else +#include <asm/runtime-const.h> +#define __user_ptr_max_accessor runtime_const_ptr(user_ptr_max) +#endif #ifdef CONFIG_ADDRESS_MASKING /* @@ -54,7 +55,7 @@ static inline unsigned long __untagged_addr_remote(struct mm_struct *mm,#endif #define valid_user_address (x) \ - likely((__force unsigned long)(x) <= runtime_const_ptr(USER_PTR_MAX)) + likely((__force unsigned long)(x) <= __user_ptr_max_accessor)/* * Masking the user address is an alternative to a conditional @@ -67,7 +68,7 @@ static inline void __user *mask_user_address(const void __user *ptr) asm("cmp %1,%0\n\t" "cmova %1,%0" :"=r" (ret) - :"r" (runtime_const_ptr (USER_PTR_MAX )), + :"r" (__user_ptr_max_accessor),"0" (ptr));return ret; }arch/x86/kernel/cpu/common.c +0
-0
arch/x86/kernel/cpu/common.c line 82
Quoted 5 lines
arch/x86/kernel/cpu/common.c +2
-0@@ -78,6 +78,9 @@ DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info);EXPORT_PER_CPU_SYMBOL (cpu_info); +unsigned long user_ptr_max__ro_after_init ; +EXPORT_SYMBOL (user_ptr_max);
That doesn't appear to be inside a CONFIG_X86_64 define.
I think I'd initialise it to one of its two values - probably the LA48 one.
David
Quoted 21 lines
arch/x86/kernel/cpu/common.c +3
-3+u32 elf_hwcap2__read_mostly ;/* Number of siblings per CPU package */ @@ -2575,14 +2578,13 @@ void __init arch_cpu_finalize_init(void)alternative_instructions ();if (IS_ENABLED (CONFIG_X86_64 )) { -unsigned long USER_PTR_MAX =TASK_SIZE_MAX ; - + user_ptr_max =TASK_SIZE_MAX ;/* * Enable this when LAM is gated on LASS support if (cpu_feature_enabled(X86_FEATURE_LAM)) USER_PTR_MAX = (1ul << 63) - PAGE_SIZE; */ -runtime_const_init (ptr,USER_PTR_MAX ); +runtime_const_init (ptr, user_ptr_max);/* * Make sure the first 2MB area is not mapped by huge pages
Re: [PATCH 1/3] x86: fix access_ok() and valid_user_address() using wrong USER_PTR_MAX in modules
In reply to Mateusz Guzik[ Adding x86 maintainers - I had added Thomas earlier, but I guess at least Borislav might actually care and have input too ]
So I think the patch I will commit would look like the attached: it's similar to your suggestion, but without the renaming of USER_PTR_MAX, and with just a
#ifdef MODULE
#define runtime_const_ptr(sym) (sym)
#else
#include <asm/runtime-const.h>
#endifin the x86 asm/uaccess_64.h header file and an added '#error' for the MODULE case in the actual x86 runtime-const.h file.
As it is, this bug really only affects modular code that uses access_ok() and __{get,put}_user(), which is a really broken pattern to begin with these days, and is happily fairly rare.
That is an old optimization that is no longer an optimization at all (since a plain "get_user()" is actually *faster* than the access_ok() and __get_user() these days), and I wish we didn't have any such code any more, but there are a handful of things that have never been converted to the modern world order.
So it is what it is, and we have to deal with it.
Also, even that kind of rare and broken code actually *works*, although the whole "non-canonical reads can speculatively leak possibly kernel data" does end up being an issue (largely theoretical because it's now limited to just a couple of odd-ball code sequences)
And yes, it works just because I picked a runtime-const value that is non-canonical. I'd say it's "by luck", but I did pick that value partly *because* it's non-canonical, so it's not _entirely_ just luck. But mostly.
That was all a long explanation for why I am planning on committing this as a real fix, even if the actual impact of it is largely theoretical.
Borislav - comments? Generating this patch took longer than it should have, but I had travel and jetlag and a flight that I expected to have wifi but didn't... And properly it should probably be committed by x86 maintainers rather than me, but I did mess this code up in the first place.
The patch *looks* very straightforward, but since I'm on the road I am doing this on my laptop and haven't actually tested it yet (well, I've built this, and booted it, but nothing past that).
Mateusz - I'd like to just credit you with this, since your comment about modules was why I started looking into this all in the first place (and you then wrote a similar patch). But I'm not going to do that without your ack.
Linus
arch/x86/include/asm/runtime-const.h | 4 ++++ arch/x86/include/asm/uaccess_64.h | 10 +++++----- arch/x86/kernel/cpu/common.c | 6 +++++- 3 files changed, 14 insertions(+), 6 deletions(-)
arch/x86/include/asm/runtime-const.h +4 -0
@@ -2,6 +2,10 @@#ifndef _ASM_RUNTIME_CONST_H#define _ASM_RUNTIME_CONST_H +#ifdef MODULE +#error "Cannot use runtime-const infrastructure from modules" +#endif +#ifdef __ASSEMBLY__ .macro RUNTIME_CONST_PTR sym reg
arch/x86/include/asm/uaccess_64.h +5 -5
@@ -12,12 +12,12 @@#include <asm/cpufeatures.h> #include <asm/page.h> #include <asm/percpu.h> -#include <asm/runtime-const.h> -/* -* Virtual variable: there's no actual backing store for this, -* it can purely be used as 'runtime_const_ptr(USER_PTR_MAX)' -*/ +#ifdef MODULE +#define runtime_const_ptr (sym) (sym) +#else +#include <asm/runtime-const.h> +#endif extern unsigned long USER_PTR_MAX ;#ifdef CONFIG_ADDRESS_MASKING
arch/x86/kernel/cpu/common.c +5 -1
@@ -78,6 +78,10 @@ DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info);EXPORT_PER_CPU_SYMBOL (cpu_info); +/* Used for modules: built-in code uses runtime constants */ +unsigned long USER_PTR_MAX ; +EXPORT_SYMBOL (USER_PTR_MAX ); +u32 elf_hwcap2__read_mostly ;/* Number of siblings per CPU package */
@@ -2579,7 +2583,7 @@ void __init arch_cpu_finalize_init(void)alternative_instructions ();if (IS_ENABLED (CONFIG_X86_64 )) { -unsigned long USER_PTR_MAX =TASK_SIZE_MAX ; +USER_PTR_MAX =TASK_SIZE_MAX ;/* * Enable this when LAM is gated on LASS support
Re: [PATCH 1/3] x86: fix access_ok() and valid_user_address() using wrong USER_PTR_MAX in modules
Quoted 5 lines · Linus Torvalds
Mateusz - I'd like to just credit you with this, since your comment about modules was why I started looking into this all in the first place (and you then wrote a similar patch). But I'm not going to do that without your ack.
I don't think crediting me here is warranted.
I would appreciate some feedback on the header split idea though. :)
Re: [PATCH 1/3] x86: fix access_ok() and valid_user_address() using wrong USER_PTR_MAX in modules
Quoted 2 lines · Mateusz Guzik
I would appreciate some feedback on the header split idea though. :)
I don't think it's wrong, but I don't think it buys us much either.
And it does make it harder to see what the bigger pattern is - the code that initializes the constants is deeply intertwined with the code that uses it, and you split it up into different files, so now you can't see what the interdependence is...
Linus
Borislav Petkov
maintainerRe: [PATCH 1/3] x86: fix access_ok() and valid_user_address() using wrong USER_PTR_MAX in modules
In reply to Linus TorvaldsQuoted 1 line · Linus Torvalds
Borislav - comments?
LGTM at a quick glance but lemme take it for a spin around the hw jungle here later and give it a more thorough look, once I've put out all the daily fires...
Thx.
Signature · 4 lines
Regards/Gruss,
Boris.
https://people.kernel.org/tglx/notes-about-netiquetteBorislav Petkov
maintainerRe: [PATCH 1/3] x86: fix access_ok() and valid_user_address() using wrong USER_PTR_MAX in modules
Quoted 6 lines · Borislav Petkov
Quoted 1 line · Linus Torvalds
Borislav - comments?
LGTM at a quick glance but lemme take it for a spin around the hw jungle here later and give it a more thorough look, once I've put out all the daily fires...
Did a deeper look, did randbuilds, boots fine on a couple of machines, so all good AFAIIC.
I sincerely hope that helps.
Signature · 4 lines
Regards/Gruss,
Boris.
https://people.kernel.org/tglx/notes-about-netiquetteRe: [PATCH 1/3] x86: fix access_ok() and valid_user_address() using wrong USER_PTR_MAX in modules
Quoted 5 lines · Borislav Petkov
Did a deeper look, did randbuilds, boots fine on a couple of machines, so all good AFAIIC.
I sincerely hope that helps.
I pushed it out with a proper commit message etc. It might not be an acute bug right now, but I do want it fixed in 6.18, so that when Thomas' new scoped accessors get merged - and maybe cause the whole inlining pattern to be much more commonly used - this is all behind us.
And the patch certainly _looks_ ObviouslyCorrect(tm). Famous last words.
Linus
Borislav Petkov
maintainerRe: [PATCH 1/3] x86: fix access_ok() and valid_user_address() using wrong USER_PTR_MAX in modules
Quoted 5 lines · Linus Torvalds
I pushed it out with a proper commit message etc. It might not be an acute bug right now, but I do want it fixed in 6.18, so that when Thomas' new scoped accessors get merged - and maybe cause the whole inlining pattern to be much more commonly used - this is all behind us.
Right.
Quoted 1 line
And the patch certainly _looks_ ObviouslyCorrect(tm). Famous last words.
Yeah, and we are testing the lineup in the coming weeks on a lot of hw so if anything fires, we will catch it. So we should be good.
Thx.
Signature · 4 lines
Regards/Gruss,
Boris.
https://people.kernel.org/tglx/notes-about-netiquetteRe: [PATCH 1/3] x86: fix access_ok() and valid_user_address() using wrong USER_PTR_MAX in modules
In reply to Borislav PetkovQuoted 5 lines · Borislav Petkov
Quoted 3 lines · Borislav Petkov
Quoted 1 line · Linus Torvalds
Borislav - comments?
Quoted 9 lines
Quoted 3 lines
LGTM at a quick glance but lemme take it for a spin around the hw jungle here later and give it a more thorough look, once I've put out all the daily fires...
Did a deeper look, did randbuilds, boots fine on a couple of machines, so all good AFAIIC.
I sincerely hope that helps.
Derailing the thread from the previous derailment with the following:
For unrelated reasons I disassembled kmem_cache_free and the following goodies popped up:
sub 0x18e033f(%rip),%rax # ffffffff82f944d0 <page_offset_base>
[..]
add 0x18e031d(%rip),%rax # ffffffff82f944c0 <vmemmap_base>
[..]
mov 0x2189e19(%rip),%rax # ffffffff8383e010 <__pi_phys_base>
These are definitely worthwhile to get rid of.
I'm just worried that given their low level nature they may happen to be used before the runtime machinery is done patching and for now can't be bothered to test that.
Worst case separate helpers could be added which are only legally used after the patching and select cases like the above can get converted to do it. Again not looking into it myself.
But perhaps someone would be interested? ;)
I'm responding to this e-mail since this would require some testing on a bunch of uarchs most likely, especially with LA57.
Borislav Petkov
maintainerRe: [PATCH 1/3] x86: fix access_ok() and valid_user_address() using wrong USER_PTR_MAX in modules
Quoted 9 lines · Mateusz Guzik
For unrelated reasons I disassembled
kmem_cache_freeand the following goodies popped up:
sub 0x18e033f(%rip),%rax #ffffffff82f944d0<page_offset_base>
[..]
add 0x18e031d(%rip),%rax #ffffffff82f944c0<vmemmap_base>
[..]
mov 0x2189e19(%rip),%rax #ffffffff8383e010<__pi_phys_base>These are definitely worthwhile to get rid of.
Says which semi-respectable benchmark?
If none, why bother?
Signature · 4 lines
Regards/Gruss,
Boris.
https://people.kernel.org/tglx/notes-about-netiquetteRe: [PATCH 1/3] x86: fix access_ok() and valid_user_address() using wrong USER_PTR_MAX in modules
Quoted 10 lines · Borislav Petkov
Quoted 8 lines · Mateusz Guzik
For unrelated reasons I disassembled
kmem_cache_freeand the following goodies popped up:
sub 0x18e033f(%rip),%rax #ffffffff82f944d0<page_offset_base>
[..]
add 0x18e031d(%rip),%rax #ffffffff82f944c0<vmemmap_base>
[..]
mov 0x2189e19(%rip),%rax #ffffffff8383e010<__pi_phys_base>
Quoted 6 lines
Quoted 1 line
These are definitely worthwhile to get rid of.
Says which semi-respectable benchmark?
If none, why bother?
I don't know what are you trying to say here.
Are you protesting the notion that reducing cache footprint of the memory allocator is a good idea, or perhaps are you claiming these vars are too problematic to warrant the effort, or something else?
I'll note that contrary to popular belief the Linux kernel is very much *slow* in terms of single-threaded performance and it is not about mitigations or hardening measures. There are tidbits of heavy microoptimization here and there, but that's all paired with massive perf loss few instructions later -- inlined rep movsq/stosq for small sizes (gcc is at fault here), lock-prefixed instructions when they can be avoided, but also cache-cold memory accesses which don't need to be there and so on.
One great example of slowness is the SLUB allocator with its cmpxchg16b-using fast paths, but that got recently damage-controlled with introduction of "shaves". Even then, it still leaves performance on the table.
I don't know if you consider this semi-respectable or better, but years back Ingo Molnar created a simple benchmark for i-cache
footprint: https://lkml.org/lkml/2015/5/19/1009
I have been using a modified version of it on and off to optimize FreeBSD and through systemic removal of tons of avoidable work (including memory references which did not need to be there) I got to single-threaded performance beating Linux. It's not that anything clever is taking place there (in fact there is still plenty of room for improvement), rather Linux has systemic issues where it loses on performance when it does not have to.
All that said, will you notice not taking a cache miss in there in the sea of other cache misses and other slowdows which are currently present? I don't think so, but it does not invalidate the notion that they should be eliminated if feasible.
I feel compelled to note runtime-consting of USER_PTR_MAX came in with no benchmark results (semi-respectable or otherwise) and still received no pushback despite a bug being uncovered related to it. Per the above, I think runtime-consting of the thing makes perfect sense and does not warrant benchmarking. Like I said, I'm not sure what you were trying to state. If your position is that a benchmark is required to remove a memory reference from a frequently used codepath, then you should be protesting USER_PTR_MAX.
Borislav Petkov
maintainerRe: [PATCH 1/3] x86: fix access_ok() and valid_user_address() using wrong USER_PTR_MAX in modules
Quoted 5 lines · Mateusz Guzik
I don't know what are you trying to say here.
Are you protesting the notion that reducing cache footprint of the memory allocator is a good idea, or perhaps are you claiming these vars are too problematic to warrant the effort, or something else?
I'm saying all work which does not change the code in a trivial way should have numbers to back it up. As in: "this change X shows this perf improvement Y with the benchmark Z."
Because code uglification better have a fair justification.
Not just random "oh yeah, it would be better to have this." If the changes are trivial, sure. But the runtime const thing was added for a very narrow case, AFAIR, and it wasn't supposed to have a widespread use. And it ain't that trivial, codewise.
IOW, no non-trivial changes which become a burden to maintainers without a really good reason for them. This has been the guiding principle for non-trivial perf optimizations in Linux. AFAIR at least.
But hey, what do I know...
Signature · 4 lines
Regards/Gruss,
Boris.
https://people.kernel.org/tglx/notes-about-netiquetteRe: [PATCH 1/3] x86: fix access_ok() and valid_user_address() using wrong USER_PTR_MAX in modules
Quoted 19 lines · Borislav Petkov
Quoted 5 lines · Mateusz Guzik
I don't know what are you trying to say here.
Are you protesting the notion that reducing cache footprint of the memory allocator is a good idea, or perhaps are you claiming these vars are too problematic to warrant the effort, or something else?
I'm saying all work which does not change the code in a trivial way should have numbers to back it up. As in: "this change X shows this perf improvement Y with the benchmark Z."
Because code uglification better have a fair justification.
Not just random "oh yeah, it would be better to have this." If the changes are trivial, sure. But the runtime const thing was added for a very narrow case, AFAIR, and it wasn't supposed to have a widespread use. And it ain't that trivial, codewise.
Quoted 5 lines
IOW, no non-trivial changes which become a burden to maintainers without a really good reason for them. This has been the guiding principle for non-trivial perf optimizations in Linux. AFAIR at least.
But hey, what do I know...
Then, as I pointed out, you should be protesting the patching of USER_PTR_MAX as it came with no benchmarks and also resulted in a regression.
Borislav Petkov
maintainerRe: [PATCH 1/3] x86: fix access_ok() and valid_user_address() using wrong USER_PTR_MAX in modules
Quoted 2 lines · Mateusz Guzik
Then, as I pointed out, you should be protesting the patching of
USER_PTR_MAXas it came with no benchmarks
That came in as a security fix. I'd say correctness before performance. And if anyone finds a better and faster fix and can prove it, I'm all ears.
Quoted 1 line
and also resulted in a regression.
Oh well, shit happens on a daily basis. And then we fix it and move on.
Signature · 4 lines
Regards/Gruss,
Boris.
https://people.kernel.org/tglx/notes-about-netiquetteRe: [PATCH 1/3] x86: fix access_ok() and valid_user_address() using wrong USER_PTR_MAX in modules
Quoted 8 lines · Borislav Petkov
Quoted 2 lines · Mateusz Guzik
Then, as I pointed out, you should be protesting the patching of
USER_PTR_MAXas it came with no benchmarksThat came in as a security fix. I'd say correctness before performance. And if anyone finds a better and faster fix and can prove it, I'm all ears.
Perhaps I failed to state my point clearly.
The position you are describing above does not line up with your behavior concerning the use of runtime-const machinery for USER_PTR_MAX.
It is purely an optimization and it has nothing to do with fixing the problem the commit introducing it was aiming to solve. You accept it without a benchmark. Later when a bug was identified you did some testing to make sure it works. I think it that made sense. However, per what you are describing above I would expect you would be questioning whether this is warranted in the first place.
kmem is probably used about as often as user access (if not more so). To my reading you rejected the idea of patching up some of its memory accesses without a benchmark from the get go, which is quite a different stance and I find myself confused about the discrepancy.
I have not tried to write patches to optimize these. There is a threshold of complexity/ugliness where I would drop the idea myself. But in a hypothetical case where they turn out fine, I don't understand what's up with the insistence on benchmarks for this particular thing, especially in light of your position on USER_PTR_MAX. Per what I described previously, this would be hard to arrange anyway even if someone genuinely tried.
Re: [PATCH 1/3] x86: fix access_ok() and valid_user_address() using wrong USER_PTR_MAX in modules
In reply to Mateusz GuzikQuoted 24 lines · On Thu, 6 Nov 2025 14:19:06 +0100 Mateusz Guzik <[email protected]> wrote:
Quoted 23 lines · Borislav Petkov
Quoted 5 lines · Mateusz Guzik
I don't know what are you trying to say here.
Are you protesting the notion that reducing cache footprint of the memory allocator is a good idea, or perhaps are you claiming these vars are too problematic to warrant the effort, or something else?
I'm saying all work which does not change the code in a trivial way should have numbers to back it up. As in: "this change X shows this perf improvement Y with the benchmark Z."
Because code uglification better have a fair justification.
Not just random "oh yeah, it would be better to have this." If the changes are trivial, sure. But the runtime const thing was added for a very narrow case, AFAIR, and it wasn't supposed to have a widespread use. And it ain't that trivial, codewise.
IOW, no non-trivial changes which become a burden to maintainers without a really good reason for them. This has been the guiding principle for non-trivial perf optimizations in Linux. AFAIR at least.
Quoted 6 lines
Quoted 1 line
But hey, what do I know...
Then, as I pointed out, you should be protesting the patching of
USER_PTR_MAXas it came with no benchmarks and also resulted in a regression.
IIRC it was a definite performance improvement for a specific workload (compiling kernels) on a system where the relatively small d-cache caused significant overhead reading the value from memory.
Look at the patch author for more info.
David
Re: [PATCH 1/3] x86: fix access_ok() and valid_user_address() using wrong USER_PTR_MAX in modules
Quoted 4 lines · David Laight
IIRC it was a definite performance improvement for a specific workload (compiling kernels) on a system where the relatively small d-cache caused significant overhead reading the value from memory.
Some background:
https://lore.kernel.org/lkml/[email protected]/
https://lore.kernel.org/lkml/CAHk-=whHvMbfL2ov1MRbT9QfebO2d6-xXi1ynznCCi-k_m6Q0w@mail.gmail.com/
where that "load address from memory" was particularly noticeable on my 128-core Altra box in profiles.
That machine really has fairly weak cores and caches (it's what I call a "flock of chickens" design: individual cores are not particularly interesting, and the only point of that machine is "reasonable performance on multithreaded loads thanks to many cores").
I did have numbers, but never posted them, because as mentioned in one of the emails:
For example, making d_hash() avoid indirection just means that now pretty much _all_ the cost of __d_lookup_rcu() is in the cache misses on the hash table itself. Which was always the bulk of it. And on my arm64 machine, it turns out that the best optimization for the load I tested would be to make that hash table smaller to actually be a bit denser in the cache, But that's such a load-dependent optimization that I'm not doing this.
IOW, the actual biggest impact on that machine was when I hacked the dcache hash tables to be smaller, so that it fit better in the L2.
But that's one of those "tune for the benchmark and the particular machine" things that I despise, so I never did that except locally for testing.
The patches that actually got committed are "these improve performance a bit by just making the code do the same thing, just being less stupid". Much less noticeable than the "tune for the machine".
Linus
Re: [PATCH 1/3] x86: fix access_ok() and valid_user_address() using wrong USER_PTR_MAX in modules
In reply to Linus TorvaldsQuoted 13 lines · Linus Torvalds
[ Adding x86 maintainers - I had added Thomas earlier, but I guess at least Borislav might actually care and have input too ]
So I think the patch I will commit would look like the attached: it's similar to your suggestion, but without the renaming of
USER_PTR_MAX, and with just a#ifdef MODULE #define runtime_const_ptr(sym) (sym) #else #include <asm/runtime-const.h> #endif
Quoted 4 lines
in the x86
asm/uaccess_64.hheader file and an added '#error' for the MODULE case in the actual x86runtime-const.hfile.As it is, this bug really only affects modular code that uses
What exactly is the bug? Is the problem that module usage of runtime_const_ptr() doesn't get patched on module load, and so module code ends up using the 0x0123456789abcdef placeholder?
Quoted 2 lines
access_ok()and __{get,put}_user(), which is a really broken pattern to begin with these days, and is happily fairly rare.
Just to make sure I understand the impact, doesn't this also affect all flavors of "nocheck" uaccesses? E.g. access_ok() + __copy_{from,to}_user()?
Quoted 5 lines
That is an old optimization that is no longer an optimization at all (since a plain "
get_user()" is actually *faster* than theaccess_ok()and__get_user()these days), and I wish we didn't have any such code any more, but there are a handful of things that have never been converted to the modern world order.
Looking at the assembly, I assume get_user() is faster than __get_user() due to the LFENCE in ASM_BARRIER_NOSPEC?
Quoted 1 line
So it is what it is, and we have to deal with it.
Assuming __{get,put}_user() are slower on x86 in all scenarios, would it make sense to kill them off entirely for x86? E.g. could we reroute them to the "checked" variants?
For KVM x86, I'm more than happy to switch all two __{get,put}_user() calls to the checked variants if they're faster.
Quoted 20 lines
Also, even that kind of rare and broken code actually *works*, although the whole "non-canonical reads can speculatively leak possibly kernel data" does end up being an issue (largely theoretical because it's now limited to just a couple of odd-ball code sequences)
And yes, it works just because I picked a runtime-const value that is non-canonical. I'd say it's "by luck", but I did pick that value partly *because* it's non-canonical, so it's not _entirely_ just luck. But mostly.
That was all a long explanation for why I am planning on committing this as a real fix, even if the actual impact of it is largely theoretical.
Borislav - comments? Generating this patch took longer than it should have, but I had travel and jetlag and a flight that I expected to have wifi but didn't... And properly it should probably be committed by x86 maintainers rather than me, but I did mess this code up in the first place.
Quoted 3 lines
The patch *looks* very straightforward, but since I'm on the road I am doing this on my laptop and haven't actually tested it yet (well, I've built this, and booted it, but nothing past that).
FWIW, AFAICT it doesn't cause any regressions for KVM's usage of access_ok().
Re: [PATCH 1/3] x86: fix access_ok() and valid_user_address() using wrong USER_PTR_MAX in modules
Quoted 4 lines · Sean Christopherson
What exactly is the bug? Is the problem that module usage of
runtime_const_ptr()doesn't get patched on module load, and so module code ends up using the0x0123456789abcdefplaceholder?
Yes. The runtime-const fixup is intentionally simplistic, because the ordering concerns with the more generic instruction rewriting was painful (and architecture-specific).
And as part of being simple and stupid, it doesn't deal with modules, and only runs early at boot.
Quoted 2 lines
Just to make sure I understand the impact, doesn't this also affect all flavors of "nocheck" uaccesses? E.g.
access_ok()+ __copy_{from,to}_user()?
The access_ok() issue happens with those too, but I don't think there was any way to then trigger the speculative leak with non-canonical addresses that way. Iirc, you needed a load-load gadget and only had a few cycles in which to do it.
But in theory, yes.
Quoted 2 lines
Looking at the assembly, I assume
get_user()is faster than__get_user()due to the LFENCE inASM_BARRIER_NOSPEC?
The access_ok() itself is also slower than the address masking, with the whole "add size and check for overflow" dance that a plain get_user() simply doesn't need.
Of course, at some point it can be advantageous to only check the address once, and then do multiple __get_user() calls, and that was obviously the *original* advantage (along with inlining the single-instruction __get_user).
But with SMAP, the inlining advantage hasn't existed for years, and the "avoid 3*N cheap ALU instructions by using a much more expensive access_ok()" is dubious even for somewhat larger values of N.
Quoted 3 lines
Assuming __{get,put}_user() are slower on x86 in all scenarios, would it make sense to kill them off entirely for x86? E.g. could we reroute them to the "checked" variants?
Sadly, no. We've wanted to do that many times for various other reasons, and we really should, but because of historical semantics, some horrendous users still use "__get_user()" for addresses that might be user space or might be kernel space depending on use-case.
Maybe we should bite the bullet and just break any remaining cases of that horrendous historical pattern. There might not be any actual relevant ones left, and they should all be easyish to fix if we just *find* them. But we had that pattern in at least some tracing code, and I'd expect some random drivers too, just because it *used* to historically work to do "the user access path does access_ok(), the kernel access path doesn't, and then both can use __get_user()".
In fact, Josh Poimboeuf tried to do that __get_user() fix fairly recently, but he hit at least the "coco" code mis-using this thing.
See vc_read_mem() in arch/x86/coco/sev/vc-handle.c.
Are there others? Probably not very many. But *finding* all those cases is the painful part.
Anybody want a new pet project?
Linus
Re: [PATCH 1/3] x86: fix access_ok() and valid_user_address() using wrong USER_PTR_MAX in modules
Quoted 8 lines · Linus Torvalds
Sadly, no. We've wanted to do that many times for various other reasons, and we really should, but because of historical semantics, some horrendous users still use "
__get_user()" for addresses that might be user space or might be kernel space depending on use-case.Maybe we should bite the bullet and just break any remaining cases of that horrendous historical pattern. [...]
What I think is probably the right approach is to just take the normal __get_user() calls - the ones that are obviously to user space, and have an access_ok() - and just replace them with get_user().
That should all be very simple and straightforward for any half-way normal code, and you won't see any downsides.
And in the unlikely case that you can measure any performance impact because you had one single access_ok() and many __get_user() calls, and *if* you really really care, that kind of code should be using "user_read_access_begin()" and friends anyway, because unlike the range checking, the *real* performance issue is almost certainly going to be the cost of the CLAC/STAC instructions.
Put another way: __get_user() is simply always wrong these days. Either it's wrong because it's a bad historical optimization that isn't an optimization any more, or it's wrong because it's mis-using the old semantics to play tricks with kernel-vs-user memory.
So we shouldn't try to "fix" __get_user(). We should aim to get rid of it.
LInus
Re: [PATCH 1/3] x86: fix access_ok() and valid_user_address() using wrong USER_PTR_MAX in modules
Quoted 7 lines · Linus Torvalds
Quoted 5 lines · Linus Torvalds
Sadly, no. We've wanted to do that many times for various other reasons, and we really should, but because of historical semantics, some horrendous users still use "
__get_user()" for addresses that might be user space or might be kernel space depending on use-case.
Eww.
Quoted 17 lines
Quoted 2 lines
Maybe we should bite the bullet and just break any remaining cases of that horrendous historical pattern. [...]
What I think is probably the right approach is to just take the normal
__get_user()calls - the ones that are obviously to user space, and have anaccess_ok()- and just replace them withget_user().That should all be very simple and straightforward for any half-way normal code, and you won't see any downsides.
And in the unlikely case that you can measure any performance impact because you had one single
access_ok()and many__get_user()calls, and *if* you really really care, that kind of code should be using "user_read_access_begin()" and friends anyway, because unlike the range checking, the *real* performance issue is almost certainly going to be the cost of the CLAC/STAC instructions.
Quoted 6 lines
Put another way:
__get_user()is simply always wrong these days. Either it's wrong because it's a bad historical optimization that isn't an optimization any more, or it's wrong because it's mis-using the old semantics to play tricks with kernel-vs-user memory.So we shouldn't try to "fix"
__get_user(). We should aim to get rid of it.
Curiosity got the better of me :-)
TL;DR: I agree, we should kill __get_user().
KVM x86's use case is a bit of a snowflake. KVM does the access_ok() check when host userspace configures memory regions for the guest, and then does __get_user() when reading guest PTEs (i.e. when walking the guest's page tables for shadow paging).
For each access_ok(), there are potentially billions (with a 'b') of __get_user() calls throughout the lifetime of the guest when KVM is using shadow paging. E.g. just booting a Linux guest hits the __get_user() in arch/x86/kvm/mmu/paging_tmpl.h a few million times. So if there's any chance that split access_ok() + __get_user() provides a performance advantage, then it should show up in KVM's shadow paging use case.
Unless I botched the measurements, get_user() is straight up faster on both Intel (EMR) and AMD (Turin). Over tens of millions of calls, get_user() is 12%+ faster on Intel and 25%+ faster on AMD, relative to __get_user(). The extra overhead is pretty much entirely due to the LFENCE, as open coding the equivalent via __uaccess_begin_nospec()+unsafe_get_user()+__uaccess_end(), to avoid the CALL+RET, yields identical numbers to __get_user(). Dropping the LFENCE, by using __uaccess_begin(), manages to eke out a victory over get_user() by ~2 cycles, but that's not remotely worth having to think about whether or not the LFENCE is necessary.
The only setup I can think of that _might_ benefit from __get_user() would be ancient CPUs without EPT/NPT (i.e. CPUs on which KVM _must_ use shadow paging) and without SMAP, but those CPUs are so old that IMO they simply aren't relevant when it comes to performance. Or I suppose the horrors where RET is actually something else entirely, but that's also a "don't care", at least as far as KVM is concerned.
Cycles per guest PTE read:
__get_user() get_user() open-coded open-coded, no LFENCE
Intel (EMR) 75.1 67.6 75.3 65.5
AMD (Turin) 68.1 51.1 67.5 49.3
Borislav Petkov
maintainerRe: [PATCH 1/3] x86: fix access_ok() and valid_user_address() using wrong USER_PTR_MAX in modules
In reply to Linus Torvalds+ Joerg and Tom.
Quoted 4 lines · Linus Torvalds
In fact, Josh Poimboeuf tried to do that
__get_user()fix fairly recently, but he hit at least the "coco" code mis-using this thing.See
vc_read_mem()inarch/x86/coco/sev/vc-handle.c.
So Tom and I did pre-fault this whole deal just now: so we need an atomic way to figure out whether we'll fault on the address and then handle that result properly. Which we do. So we only need to know whether it'll fault or not, without sleeping.
So the question is, what would be an alternative to do that? Should we do something homegrown?
Thx.
Signature · 4 lines
Regards/Gruss,
Boris.
https://people.kernel.org/tglx/notes-about-netiquetteRe: [PATCH 1/3] x86: fix access_ok() and valid_user_address() using wrong USER_PTR_MAX in modules
Quoted 7 lines · Borislav Petkov
Quoted 4 lines · Linus Torvalds
In fact, Josh Poimboeuf tried to do that
__get_user()fix fairly recently, but he hit at least the "coco" code mis-using this thing.See
vc_read_mem()inarch/x86/coco/sev/vc-handle.c.
Quoted 7 lines
So Tom and I did pre-fault this whole deal just now: so we need an atomic way to figure out whether we'll fault on the address and then handle that result properly. Which we do. So we only need to know whether it'll fault or not, without sleeping.
So the question is, what would be an alternative to do that? Should we do something homegrown?
So I think that since it's x86-specific code, maybe something homegrown is the way to go. I mean, that cdoe already effectively is.
With a *BIG* comment about what is going on, something like
pagefault_disable();
stac();
unsafe_get_user(val, ptr, fault_label);
clac();
pagefault_enable();
return 0; fault_label:
clac();
return 1;but any other users of __get_user() that aren't in x86-specific code can't do that, so I do think it's probably better to just migrate the *good* cases - the ones known to actually be about user space - away from __get_user() and just leave these turds alone.
Linus
Borislav Petkov
maintainerRe: [PATCH 1/3] x86: fix access_ok() and valid_user_address() using wrong USER_PTR_MAX in modules
Quoted 4 lines · Linus Torvalds
but any other users of
__get_user()that aren't in x86-specific code can't do that, so I do think it's probably better to just migrate the *good* cases - the ones known to actually be about user space - away from__get_user()and just leave these turds alone.
We probably should think of a scheme to stop __get_user() from spreading around by hiding it in an arch-specific header which doesn't get exposed to modules/drivers/etc and then once that is in place, take care of the existing offenders and convert them slowly.
It'll need careful conversion and testing, I'd say but at least we'll have a finite, non-growing number of occurrences to convert:
$ git grep -w __get_user *.c | grep -v arch | wc -l 43
Not a lot. (The headers are mostly macro definitions AFAICT).
The arches would then be a separate deal...
Signature · 4 lines
Regards/Gruss,
Boris.
https://people.kernel.org/tglx/notes-about-netiquettePATCH 2/3 runtime-const: split headers between accessors and fixup; disable for modules
In reply to Mateusz Guzikrisv and x86 covered as a POC
--- .../include/asm/runtime-const-accessors.h | 151 ++++++++++++++++++ arch/riscv/include/asm/runtime-const.h | 142 +--------------- .../x86/include/asm/runtime-const-accessors.h | 45 ++++++ arch/x86/include/asm/runtime-const.h | 38 +---- 4 files changed, 200 insertions(+), 176 deletions(-) create mode 100644 arch/riscv/include/asm/runtime-const-accessors.h create mode 100644 arch/x86/include/asm/runtime-const-accessors.h
arch/riscv/include/asm/runtime-const-accessors.h new file +151 -0
@@ -0,0 +1,151 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_RISCV_RUNTIME_CONST_ACCESSORS_H +#define _ASM_RISCV_RUNTIME_CONST_ACCESSORS_H + +#ifdef MODULE +#error "this functionality is not available for modules" +#endif + +#ifdef CONFIG_32BIT +#define runtime_const_ptr (sym) \ +({ \ + typeof(sym) __ret; \ + asm_inline(".option push\n\t" \ + ".option norvc\n\t" \ + "1:\t" \ + "lui %[__ret],0x89abd\n\t" \ + "addi %[__ret],%[__ret],-0x211\n\t" \ + ".option pop\n\t" \ + ".pushsection runtime_ptr_" #sym ",\"a\"\n\t" \ + ".long 1b - .\n\t" \ + ".popsection" \ + : [__ret] "=r" (__ret)); \ + __ret; \ +}) +#else +/* +* Loading 64-bit constants into a register from immediates is a non-trivial +* task on riscv64. To get it somewhat performant, load 32 bits into two +* different registers and then combine the results. +* +* If the processor supports the Zbkb extension, we can combine the final +* "slli,slli,srli,add" into the single "pack" instruction. If the processor +* doesn't support Zbkb but does support the Zbb extension, we can +* combine the final "slli,srli,add" into one instruction "add.uw". +*/ +#define RISCV_RUNTIME_CONST_64_PREAMBLE \ + ".option push\n\t" \ + ".option norvc\n\t" \ + "1:\t" \ + "lui %[__ret],0x89abd\n\t" \ + "lui %[__tmp],0x1234\n\t" \ + "addiw %[__ret],%[__ret],-0x211\n\t" \ + "addiw %[__tmp],%[__tmp],0x567\n\t" \ + +#define RISCV_RUNTIME_CONST_64_BASE \ + "slli %[__tmp],%[__tmp],32\n\t" \ + "slli %[__ret],%[__ret],32\n\t" \ + "srli %[__ret],%[__ret],32\n\t" \ + "add %[__ret],%[__ret],%[__tmp]\n\t" \ + +#define RISCV_RUNTIME_CONST_64_ZBA \ + ".option push\n\t" \ + ".option arch,+zba\n\t" \ + ".option norvc\n\t" \ + "slli %[__tmp],%[__tmp],32\n\t" \ + "add.uw %[__ret],%[__ret],%[__tmp]\n\t" \ + "nop\n\t" \ + "nop\n\t" \ + ".option pop\n\t" \ + +#define RISCV_RUNTIME_CONST_64_ZBKB \ + ".option push\n\t" \ + ".option arch,+zbkb\n\t" \ + ".option norvc\n\t" \ + "pack %[__ret],%[__ret],%[__tmp]\n\t" \ + "nop\n\t" \ + "nop\n\t" \ + "nop\n\t" \ + ".option pop\n\t" \ + +#define RISCV_RUNTIME_CONST_64_POSTAMBLE (sym) \ + ".option pop\n\t" \ + ".pushsection runtime_ptr_" #sym ",\"a\"\n\t" \ + ".long 1b - .\n\t" \ + ".popsection" \ + +#if defined(CONFIG_RISCV_ISA_ZBA ) && defined(CONFIG_TOOLCHAIN_HAS_ZBA ) \ + && defined(CONFIG_RISCV_ISA_ZBKB ) +#define runtime_const_ptr (sym) \ +({ \ + typeof(sym) __ret, __tmp; \ + asm_inline(RISCV_RUNTIME_CONST_64_PREAMBLE \ + ALTERNATIVE_2( \ + RISCV_RUNTIME_CONST_64_BASE, \ + RISCV_RUNTIME_CONST_64_ZBA, \ + 0, RISCV_ISA_EXT_ZBA, 1, \ + RISCV_RUNTIME_CONST_64_ZBKB, \ + 0, RISCV_ISA_EXT_ZBKB, 1 \ + ) \ + RISCV_RUNTIME_CONST_64_POSTAMBLE(sym) \ + : [__ret] "=r" (__ret), [__tmp] "=r" (__tmp)); \ + __ret; \ +}) +#elif defined(CONFIG_RISCV_ISA_ZBA ) && defined(CONFIG_TOOLCHAIN_HAS_ZBA ) +#define runtime_const_ptr (sym) \ +({ \ + typeof(sym) __ret, __tmp; \ + asm_inline(RISCV_RUNTIME_CONST_64_PREAMBLE \ + ALTERNATIVE( \ + RISCV_RUNTIME_CONST_64_BASE, \ + RISCV_RUNTIME_CONST_64_ZBA, \ + 0, RISCV_ISA_EXT_ZBA, 1 \ + ) \ + RISCV_RUNTIME_CONST_64_POSTAMBLE(sym) \ + : [__ret] "=r" (__ret), [__tmp] "=r" (__tmp)); \ + __ret; \ +}) +#elif defined(CONFIG_RISCV_ISA_ZBKB ) +#define runtime_const_ptr (sym) \ +({ \ + typeof(sym) __ret, __tmp; \ + asm_inline(RISCV_RUNTIME_CONST_64_PREAMBLE \ + ALTERNATIVE( \ + RISCV_RUNTIME_CONST_64_BASE, \ + RISCV_RUNTIME_CONST_64_ZBKB, \ + 0, RISCV_ISA_EXT_ZBKB, 1 \ + ) \ + RISCV_RUNTIME_CONST_64_POSTAMBLE(sym) \ + : [__ret] "=r" (__ret), [__tmp] "=r" (__tmp)); \ + __ret; \ +}) +#else +#define runtime_const_ptr (sym) \ +({ \ + typeof(sym) __ret, __tmp; \ + asm_inline(RISCV_RUNTIME_CONST_64_PREAMBLE \ + RISCV_RUNTIME_CONST_64_BASE \ + RISCV_RUNTIME_CONST_64_POSTAMBLE(sym) \ + : [__ret] "=r" (__ret), [__tmp] "=r" (__tmp)); \ + __ret; \ +}) +#endif +#endif + +#define runtime_const_shift_right_32 (val, sym) \ +({ \ + u32 __ret; \ + asm_inline(".option push\n\t" \ + ".option norvc\n\t" \ + "1:\t" \ + SRLI " %[__ret],%[__val],12\n\t" \ + ".option pop\n\t" \ + ".pushsection runtime_shift_" #sym ",\"a\"\n\t" \ + ".long 1b - .\n\t" \ + ".popsection" \ + : [__ret] "=r" (__ret) \ + : [__val] "r" (val)); \ + __ret; \ +}) + +#endif /* _ASM_RISCV_RUNTIME_CONST_ACCESSORS_H */
arch/riscv/include/asm/runtime-const.h +1 -141
148 lines not on this page · raw message
arch/x86/include/asm/runtime-const-accessors.h new file +45 -0
45 lines not on this page · raw message
arch/x86/include/asm/runtime-const.h +3 -35
@@ -2,41 +2,9 @@#ifndef _ASM_RUNTIME_CONST_H#define _ASM_RUNTIME_CONST_H -#ifdef __ASSEMBLY__ - -.macro RUNTIME_CONST_PTR sym reg - movq $0x0123456789abcdef, %\reg - 1: - .pushsection runtime_ptr_\sym, "a" - .long 1b - 8 - . - .popsection -.endm - -#else /* __ASSEMBLY__ */ - -#define runtime_const_ptr(sym) ({ \ - typeof(sym) __ret; \ - asm_inline("mov %1,%0\n1:\n" \ - ".pushsection runtime_ptr_" #sym ",\"a\"\n\t" \ - ".long 1b - %c2 - .\n" \ - ".popsection" \ - :"=r" (__ret) \ - :"i" ((unsigned long)0x0123456789abcdefull), \ - "i" (sizeof(long))); \ - __ret; }) - -// The 'typeof' will create at _least_ a 32-bit type, but -// will happily also take a bigger type and the 'shrl' will -// clear the upper bits -#define runtime_const_shift_right_32(val, sym) ({ \ - typeof(0u+(val)) __ret = (val); \ - asm_inline("shrl $12,%k0\n1:\n" \ - ".pushsection runtime_shift_" #sym ",\"a\"\n\t" \ - ".long 1b - 1 - .\n" \ - ".popsection" \ - :"+r" (__ret)); \ - __ret; }) +#include <asm/runtime-const-accessors.h> +#ifndef __ASSEMBLY__#define runtime_const_init (type, sym) do { \ extern s32 __start_runtime_##type##_##sym[]; \ extern s32 __stop_runtime_##type##_##sym[]; \
@@ -70,5 +38,5 @@ static inline void runtime_const_fixup(void (*fn)(void *, unsigned long), } } -#endif /* __ASSEMBLY__ */ +#endif /* !__ASSEMBLY__ */ #endif
Signature · 1 line
2.34.1
PATCH 3/3 fs: hide names_cachep behind runtime access machinery
In reply to Mateusz GuzikThe var is used twice for every path lookup, while the cache is initialized early and stays valid for the duration.
--- fs/dcache.c | 1 + include/asm-generic/vmlinux.lds.h | 3 ++- include/linux/fs.h | 17 +++++++++++++++-- 3 files changed, 18 insertions(+), 3 deletions(-)
fs/dcache.c +1 -0
@@ -3259,6 +3259,7 @@ void __init vfs_caches_init(void) { names_cachep =kmem_cache_create_usercopy ("names_cache" ,PATH_MAX ,0 ,SLAB_HWCACHE_ALIGN |SLAB_PANIC ,0 ,PATH_MAX ,NULL ); +runtime_const_init (ptr, names_cachep);dcache_init ();inode_init ();
include/asm-generic/vmlinux.lds.h +2 -1
@@ -939,7 +939,8 @@#define RUNTIME_CONST_VARIABLES \ RUNTIME_CONST(shift, d_hash_shift) \ - RUNTIME_CONST(ptr, dentry_hashtable) + RUNTIME_CONST(ptr, dentry_hashtable) \ + RUNTIME_CONST(ptr, names_cachep)/* Alignment must be consistent with (kunit_suite *) in include/kunit/test.h */ #define KUNIT_TABLE () \
include/linux/fs.h +15 -2
@@ -50,6 +50,10 @@#include <linux/unicode.h> #include <asm/byteorder.h> +#ifndef MODULE +#include <asm/runtime-const-accessors.h> +#endif +#include <uapi/linux/fs.h> struct backing_dev_info ;
@@ -3044,8 +3048,17 @@ extern void __init vfs_caches_init(void);extern struct kmem_cache *names_cachep; -#define __getname () kmem_cache_alloc(names_cachep, GFP_KERNEL) -#define __putname (name) kmem_cache_free(names_cachep, (void *)(name)) +/* +* XXX The runtime_const machinery does not support modules at the moment. +*/ +#ifdef MODULE +#define __names_cachep_accessor names_cachep +#else +#define __names_cachep_accessor runtime_const_ptr(names_cachep) +#endif + +#define __getname () kmem_cache_alloc(__names_cachep_accessor, GFP_KERNEL) +#define __putname (name) kmem_cache_free(__names_cachep_accessor, (void *)(name))extern struct super_block *blockdev_superblock;static inline bool sb_is_blkdev_sb (struct super_block *sb)
Signature · 1 line
2.34.1
kernel test robot
build botkernel test robot noticed the following build errors:
Hi Mateusz,
kernel test robot noticed the following build errors:
[auto build test ERROR on arnd-asm-generic/master]
[also build test ERROR on linus/master brauner-vfs/vfs.all v6.18-rc3 next-20251031] [cannot apply to linux/master]
[If your patch is applied to the wrong git tree, kindly drop us a note. And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]
url: https://github.com/intel-lab-lkp/linux/commits/Mateusz-Guzik/x86-fix-access_ok-and-valid_user_address-using-wrong-USER_PTR_MAX-in-modules/20251101-054539 base: https://git.kernel.org/pub/scm/linux/kernel/git/arnd/asm-generic.git master patch link: https://lore.kernel.org/r/20251031174220.43458-4-mjguzik%40gmail.com patch subject: [PATCH 3/3] fs: hide names_cachep behind runtime access machinery config: alpha-allnoconfig (https://download.01.org/0day-ci/archive/20251101/[email protected]/config) compiler: alpha-linux-gcc (GCC) 15.1.0 reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20251101/[email protected]/reproduce)
If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <[email protected]>
| Closes: https://lore.kernel.org/oe-kbuild-all/[email protected]/
All errors (new ones prefixed by >>):
In file included from include/linux/huge_mm.h:7,
from include/linux/mm.h:1016,
from include/linux/pid_namespace.h:7,
from include/linux/ptrace.h:10,
from arch/alpha/kernel/asm-offsets.c:11:
>> include/linux/fs.h:54:10: fatal error: asm/runtime-const-accessors.h: No such file or directory 54 | #include <asm/runtime-const-accessors.h>
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
compilation terminated.
make[3]: *** [scripts/Makefile.build:182: arch/alpha/kernel/asm-offsets.s] Error 1 make[3]: Target 'prepare' not remade because of errors.
make[2]: *** [Makefile:1282: prepare0] Error 2
make[2]: Target 'prepare' not remade because of errors.
make[1]: *** [Makefile:248: __sub-make] Error 2
make[1]: Target 'prepare' not remade because of errors.
make: *** [Makefile:248: __sub-make] Error 2
make: Target 'prepare' not remade because of errors.
vim +54 include/linux/fs.h
51
52 #include <asm/byteorder.h>
53 #ifndef MODULE
> 54 #include <asm/runtime-const-accessors.h>
55 #endif
56 Signature · 2 lines
0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki
kernel test robot
build botkernel test robot noticed the following build warnings:
Hi Mateusz,
kernel test robot noticed the following build warnings:
[auto build test WARNING on arnd-asm-generic/master]
[also build test WARNING on linus/master brauner-vfs/vfs.all v6.18-rc3 next-20251031] [cannot apply to linux/master]
[If your patch is applied to the wrong git tree, kindly drop us a note. And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]
url: https://github.com/intel-lab-lkp/linux/commits/Mateusz-Guzik/x86-fix-access_ok-and-valid_user_address-using-wrong-USER_PTR_MAX-in-modules/20251101-054539 base: https://git.kernel.org/pub/scm/linux/kernel/git/arnd/asm-generic.git master patch link: https://lore.kernel.org/r/20251031174220.43458-4-mjguzik%40gmail.com patch subject: [PATCH 3/3] fs: hide names_cachep behind runtime access machinery config: um-allnoconfig (https://download.01.org/0day-ci/archive/20251101/[email protected]/config) compiler: clang version 22.0.0git (https://github.com/llvm/llvm-project d1c086e82af239b245fe8d7832f2753436634990) reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20251101/[email protected]/reproduce)
If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <[email protected]>
| Closes: https://lore.kernel.org/oe-kbuild-all/[email protected]/
All warnings (new ones prefixed by >>):
In file included from fs/dcache.c:38:
In file included from ./arch/um/include/generated/asm/runtime-const.h:1:
>> include/asm-generic/runtime-const.h:11:9: warning: 'runtime_const_ptr' macro redefined [-Wmacro-redefined]
11 | #define runtime_const_ptr(sym) (sym)
| ^
arch/x86/include/asm/runtime-const-accessors.h:21:9: note: previous definition is here
21 | #define runtime_const_ptr(sym) ({ \
| ^
In file included from fs/dcache.c:38:
In file included from ./arch/um/include/generated/asm/runtime-const.h:1:
>> include/asm-generic/runtime-const.h:12:9: warning: 'runtime_const_shift_right_32' macro redefined [-Wmacro-redefined]
12 | #define runtime_const_shift_right_32(val, sym) ((u32)(val)>>(sym))
| ^
arch/x86/include/asm/runtime-const-accessors.h:35:9: note: previous definition is here
35 | #define runtime_const_shift_right_32(val, sym) ({ \
| ^2 warnings generated.
vim +/runtime_const_ptr +11 include/asm-generic/runtime-const.h
e78298556ee5d8 Linus Torvalds 2024-06-04 4
e78298556ee5d8 Linus Torvalds 2024-06-04 5 /*
e78298556ee5d8 Linus Torvalds 2024-06-04 6 * This is the fallback for when the architecture doesn't
e78298556ee5d8 Linus Torvalds 2024-06-04 7 * support the runtime const operations.
e78298556ee5d8 Linus Torvalds 2024-06-04 8 *
e78298556ee5d8 Linus Torvalds 2024-06-04 9 * We just use the actual symbols as-is.
e78298556ee5d8 Linus Torvalds 2024-06-04 10 */
e78298556ee5d8 Linus Torvalds 2024-06-04 @11 #define runtime_const_ptr(sym) (sym)
e78298556ee5d8 Linus Torvalds 2024-06-04 @12 #define runtime_const_shift_right_32(val, sym) ((u32)(val)>>(sym))
e78298556ee5d8 Linus Torvalds 2024-06-04 13 #define runtime_const_init(type,sym) do { } while (0)e78298556ee5d8 Linus Torvalds 2024-06-04 14
Signature · 2 lines
0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki
kernel test robot
build botkernel test robot noticed the following build errors:
Hi Mateusz,
kernel test robot noticed the following build errors:
[auto build test ERROR on arnd-asm-generic/master]
[also build test ERROR on linus/master brauner-vfs/vfs.all v6.18-rc3 next-20251031] [cannot apply to linux/master]
[If your patch is applied to the wrong git tree, kindly drop us a note. And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]
url: https://github.com/intel-lab-lkp/linux/commits/Mateusz-Guzik/x86-fix-access_ok-and-valid_user_address-using-wrong-USER_PTR_MAX-in-modules/20251101-054539 base: https://git.kernel.org/pub/scm/linux/kernel/git/arnd/asm-generic.git master patch link: https://lore.kernel.org/r/20251031174220.43458-4-mjguzik%40gmail.com patch subject: [PATCH 3/3] fs: hide names_cachep behind runtime access machinery config: arm-allnoconfig (https://download.01.org/0day-ci/archive/20251101/[email protected]/config) compiler: clang version 22.0.0git (https://github.com/llvm/llvm-project d1c086e82af239b245fe8d7832f2753436634990) reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20251101/[email protected]/reproduce)
If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <[email protected]>
| Closes: https://lore.kernel.org/oe-kbuild-all/[email protected]/
All errors (new ones prefixed by >>):
In file included from arch/arm/kernel/asm-offsets.c:12:
In file included from include/linux/mm.h:1016:
In file included from include/linux/huge_mm.h:7:
>> include/linux/fs.h:54:10: fatal error: 'asm/runtime-const-accessors.h' file not found
54 | #include <asm/runtime-const-accessors.h>
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
1 error generated.
make[3]: *** [scripts/Makefile.build:182: arch/arm/kernel/asm-offsets.s] Error 1 make[3]: Target 'prepare' not remade because of errors.
make[2]: *** [Makefile:1282: prepare0] Error 2
make[2]: Target 'prepare' not remade because of errors.
make[1]: *** [Makefile:248: __sub-make] Error 2
make[1]: Target 'prepare' not remade because of errors.
make: *** [Makefile:248: __sub-make] Error 2
make: Target 'prepare' not remade because of errors.
vim +54 include/linux/fs.h
51
52 #include <asm/byteorder.h>
53 #ifndef MODULE
> 54 #include <asm/runtime-const-accessors.h>
55 #endif
56 Signature · 2 lines
0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki
kernel test robot
build botkernel test robot noticed the following build warnings:
Hi Mateusz,
kernel test robot noticed the following build warnings:
[auto build test WARNING on arnd-asm-generic/master]
[also build test WARNING on linus/master brauner-vfs/vfs.all v6.18-rc3 next-20251031] [cannot apply to linux/master]
[If your patch is applied to the wrong git tree, kindly drop us a note. And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]
url: https://github.com/intel-lab-lkp/linux/commits/Mateusz-Guzik/x86-fix-access_ok-and-valid_user_address-using-wrong-USER_PTR_MAX-in-modules/20251101-054539 base: https://git.kernel.org/pub/scm/linux/kernel/git/arnd/asm-generic.git master patch link: https://lore.kernel.org/r/20251031174220.43458-4-mjguzik%40gmail.com patch subject: [PATCH 3/3] fs: hide names_cachep behind runtime access machinery config: i386-randconfig-061-20251101 (https://download.01.org/0day-ci/archive/20251102/[email protected]/config) compiler: gcc-14 (Debian 14.2.0-19) 14.2.0 reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20251102/[email protected]/reproduce)
If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <[email protected]>
| Closes: https://lore.kernel.org/oe-kbuild-all/[email protected]/
sparse warnings: (new ones prefixed by >>)
fs/smb/client/link.c: note: in included file:
>> fs/smb/client/cifsproto.h:71:16: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) >> fs/smb/client/cifsproto.h:71:16: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) fs/smb/client/cifsproto.h:77:17: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) -- fs/smb/client/dir.c: note: in included file: >> fs/smb/client/cifsproto.h:71:16: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) >> fs/smb/client/cifsproto.h:71:16: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) fs/smb/client/cifsproto.h:77:17: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) -- fs/smb/client/misc.c: note: in included file: >> fs/smb/client/cifsproto.h:71:16: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) >> fs/smb/client/cifsproto.h:71:16: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) fs/smb/client/cifsproto.h:77:17: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) -- fs/smb/client/cifsfs.c: note: in included file: >> fs/smb/client/cifsproto.h:71:16: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) >> fs/smb/client/cifsproto.h:71:16: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) fs/smb/client/cifsproto.h:77:17: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) -- fs/smb/client/ioctl.c: note: in included file: >> fs/smb/client/cifsproto.h:71:16: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) >> fs/smb/client/cifsproto.h:71:16: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) fs/smb/client/cifsproto.h:77:17: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) -- fs/smb/client/inode.c: note: in included file: >> fs/smb/client/cifsproto.h:71:16: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) >> fs/smb/client/cifsproto.h:71:16: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) fs/smb/client/cifsproto.h:77:17: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) -- fs/smb/client/file.c: note: in included file: >> fs/smb/client/cifsproto.h:71:16: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) >> fs/smb/client/cifsproto.h:71:16: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) fs/smb/client/cifsproto.h:77:17: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) -- fs/smb/client/readdir.c: note: in included file: >> fs/smb/client/cifsproto.h:71:16: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) >> fs/smb/client/cifsproto.h:71:16: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) fs/smb/client/cifsproto.h:77:17: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) -- fs/smb/client/namespace.c: note: in included file: >> fs/smb/client/cifsproto.h:71:16: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) >> fs/smb/client/cifsproto.h:71:16: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) fs/smb/client/cifsproto.h:77:17: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) -- fs/smb/client/smb2ops.c: note: in included file: >> fs/smb/client/cifsproto.h:71:16: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) >> fs/smb/client/cifsproto.h:71:16: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef)
fs/smb/client/cifsproto.h:77:17: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef)
vim +71 fs/smb/client/cifsproto.h
b6b38f704a8193 fs/cifs/cifsproto.h Joe Perches 2010-04-21 48
6d5786a34d98bf fs/cifs/cifsproto.h Pavel Shilovsky 2012-06-20 49 #define free_xid(curr_xid) \
b6b38f704a8193 fs/cifs/cifsproto.h Joe Perches 2010-04-21 50 do { \
6d5786a34d98bf fs/cifs/cifsproto.h Pavel Shilovsky 2012-06-20 51 _free_xid(curr_xid); \
a0a3036b81f1f6 fs/cifs/cifsproto.h Joe Perches 2020-04-14 52 cifs_dbg(FYI, "VFS: leaving %s (xid = %u) rc = %d\n", \
b6b38f704a8193 fs/cifs/cifsproto.h Joe Perches 2010-04-21 53 __func__, curr_xid, (int)rc); \
d683bcd3e5d157 fs/cifs/cifsproto.h Steve French 2018-05-19 54 if (rc) \
d683bcd3e5d157 fs/cifs/cifsproto.h Steve French 2018-05-19 55 trace_smb3_exit_err(curr_xid, __func__, (int)rc); \
d683bcd3e5d157 fs/cifs/cifsproto.h Steve French 2018-05-19 56 else \
d683bcd3e5d157 fs/cifs/cifsproto.h Steve French 2018-05-19 57 trace_smb3_exit_done(curr_xid, __func__); \
b6b38f704a8193 fs/cifs/cifsproto.h Joe Perches 2010-04-21 58 } while (0)
4d79dba0e00749 fs/cifs/cifsproto.h Shirish Pargaonkar 2011-04-27 59 extern int init_cifs_idmap(void);
4d79dba0e00749 fs/cifs/cifsproto.h Shirish Pargaonkar 2011-04-27 60 extern void exit_cifs_idmap(void);
b74cb9a80268be fs/cifs/cifsproto.h Sachin Prabhu 2016-05-17 61 extern int init_cifs_spnego(void);
b74cb9a80268be fs/cifs/cifsproto.h Sachin Prabhu 2016-05-17 62 extern void exit_cifs_spnego(void);
f6a9bc336b600e fs/cifs/cifsproto.h Al Viro 2021-03-05 63 extern const char *build_path_from_dentry(struct dentry *, void *);
7ad54b98fc1f14 fs/cifs/cifsproto.h Paulo Alcantara 2022-12-18 64 char *__build_path_from_dentry_optional_prefix(struct dentry *direntry, void *page,
7ad54b98fc1f14 fs/cifs/cifsproto.h Paulo Alcantara 2022-12-18 65 const char *tree, int tree_len,
7ad54b98fc1f14 fs/cifs/cifsproto.h Paulo Alcantara 2022-12-18 66 bool prefix);
268a635d414df4 fs/cifs/cifsproto.h Aurelien Aptel 2017-02-13 67 extern char *build_path_from_dentry_optional_prefix(struct dentry *direntry,
f6a9bc336b600e fs/cifs/cifsproto.h Al Viro 2021-03-05 68 void *page, bool prefix);
f6a9bc336b600e fs/cifs/cifsproto.h Al Viro 2021-03-05 69 static inline void *alloc_dentry_path(void)
f6a9bc336b600e fs/cifs/cifsproto.h Al Viro 2021-03-05 70 {
f6a9bc336b600e fs/cifs/cifsproto.h Al Viro 2021-03-05 @71 return __getname();
f6a9bc336b600e fs/cifs/cifsproto.h Al Viro 2021-03-05 72 }
f6a9bc336b600e fs/cifs/cifsproto.h Al Viro 2021-03-05 73 Signature · 2 lines
0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki
kernel test robot
build botkernel test robot noticed the following build errors:
Hi Mateusz,
kernel test robot noticed the following build errors:
[auto build test ERROR on arnd-asm-generic/master]
[also build test ERROR on linus/master brauner-vfs/vfs.all linux/master v6.18-rc3 next-20251031] [If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]
url: https://github.com/intel-lab-lkp/linux/commits/Mateusz-Guzik/fs-hide-names_cachep-behind-runtime-access-machinery/20251030-185523 base: https://git.kernel.org/pub/scm/linux/kernel/git/arnd/asm-generic.git master patch link: https://lore.kernel.org/r/20251030105242.801528-1-mjguzik%40gmail.com patch subject: [PATCH v4] fs: hide names_cachep behind runtime access machinery config: riscv-randconfig-002-20251031 (https://download.01.org/0day-ci/archive/20251031/[email protected]/config) compiler: clang version 17.0.6 (https://github.com/llvm/llvm-project 6009708b4367171ccdbf4b5905cb6a803753fe18) reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20251031/[email protected]/reproduce)
If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <[email protected]>
| Closes: https://lore.kernel.org/oe-kbuild-all/[email protected]/
All errors (new ones prefixed by >>):
In file included from arch/riscv/kernel/asm-offsets.c:8:
In file included from include/linux/mm.h:1016:
In file included from include/linux/huge_mm.h:7:
In file included from include/linux/fs.h:53:
In file included from arch/riscv/include/asm/runtime-const.h:7:
>> arch/riscv/include/asm/cacheflush.h:49:6: error: call to undeclared function 'is_vmalloc_or_module_addr'; ISO C99 and later do not support implicit function declarations [-Wimplicit-function-declaration]
49 | if (is_vmalloc_or_module_addr((void *)start)) {
| ^
In file included from arch/riscv/kernel/asm-offsets.c:8:
In file included from include/linux/mm.h:1016:
In file included from include/linux/huge_mm.h:7:
In file included from include/linux/fs.h:53:
In file included from arch/riscv/include/asm/runtime-const.h:9:
In file included from include/linux/memory.h:19:
In file included from include/linux/node.h:18:
In file included from include/linux/device.h:32:
In file included from include/linux/device/driver.h:21:
In file included from include/linux/module.h:20:
In file included from include/linux/elf.h:6:
In file included from arch/riscv/include/asm/elf.h:12:
In file included from include/linux/compat.h:18:
include/uapi/linux/aio_abi.h:79:2: error: unknown type name '__kernel_rwf_t'; did you mean '__kernel_off_t'?
79 | __kernel_rwf_t aio_rw_flags; /* RWF_* flags */
| ^~~~~~~~~~~~~~
| __kernel_off_t
include/uapi/asm-generic/posix_types.h:87:25: note: '__kernel_off_t' declared here
87 | typedef __kernel_long_t __kernel_off_t;
| ^ 2 errors generated.
make[3]: *** [scripts/Makefile.build:182: arch/riscv/kernel/asm-offsets.s] Error 1 shuffle=1341192968 make[3]: Target 'prepare' not remade because of errors.
make[2]: *** [Makefile:1282: prepare0] Error 2 shuffle=1341192968
make[2]: Target 'prepare' not remade because of errors.
make[1]: *** [Makefile:248: __sub-make] Error 2 shuffle=1341192968
make[1]: Target 'prepare' not remade because of errors.
make: *** [Makefile:248: __sub-make] Error 2 shuffle=1341192968
make: Target 'prepare' not remade because of errors.
vim +/is_vmalloc_or_module_addr +49 arch/riscv/include/asm/cacheflush.h
08f051eda33b51e Andrew Waterman 2017-10-25 42
7e3811521dc3934 Alexandre Ghiti 2023-07-25 43 #ifdef CONFIG_64BIT
503638e0babf364 Alexandre Ghiti 2024-07-17 44 extern u64 new_vmalloc[NR_CPUS / sizeof(u64) + 1];
503638e0babf364 Alexandre Ghiti 2024-07-17 45 extern char _end[];
503638e0babf364 Alexandre Ghiti 2024-07-17 46 #define flush_cache_vmap flush_cache_vmap
503638e0babf364 Alexandre Ghiti 2024-07-17 47 static inline void flush_cache_vmap(unsigned long start, unsigned long end)
503638e0babf364 Alexandre Ghiti 2024-07-17 48 {
503638e0babf364 Alexandre Ghiti 2024-07-17 @49 if (is_vmalloc_or_module_addr((void *)start)) {
503638e0babf364 Alexandre Ghiti 2024-07-17 50 int i;
503638e0babf364 Alexandre Ghiti 2024-07-17 51
503638e0babf364 Alexandre Ghiti 2024-07-17 52 /*
503638e0babf364 Alexandre Ghiti 2024-07-17 53 * We don't care if concurrently a cpu resets this value since
503638e0babf364 Alexandre Ghiti 2024-07-17 54 * the only place this can happen is in handle_exception() where
503638e0babf364 Alexandre Ghiti 2024-07-17 55 * an sfence.vma is emitted.
503638e0babf364 Alexandre Ghiti 2024-07-17 56 */
503638e0babf364 Alexandre Ghiti 2024-07-17 57 for (i = 0; i < ARRAY_SIZE(new_vmalloc); ++i)
503638e0babf364 Alexandre Ghiti 2024-07-17 58 new_vmalloc[i] = -1ULL;
503638e0babf364 Alexandre Ghiti 2024-07-17 59 }
503638e0babf364 Alexandre Ghiti 2024-07-17 60 }
7a92fc8b4d20680 Alexandre Ghiti 2023-12-12 61 #define flush_cache_vmap_early(start, end) local_flush_tlb_kernel_range(start, end)
7e3811521dc3934 Alexandre Ghiti 2023-07-25 62 #endif
7e3811521dc3934 Alexandre Ghiti 2023-07-25 63 Signature · 2 lines
0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki
kernel test robot
build botkernel test robot noticed the following build warnings:
Hi Mateusz,
kernel test robot noticed the following build warnings:
[auto build test WARNING on arnd-asm-generic/master]
[also build test WARNING on linus/master brauner-vfs/vfs.all linux/master v6.18-rc3 next-20251031] [If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]
url: https://github.com/intel-lab-lkp/linux/commits/Mateusz-Guzik/fs-hide-names_cachep-behind-runtime-access-machinery/20251030-185523 base: https://git.kernel.org/pub/scm/linux/kernel/git/arnd/asm-generic.git master patch link: https://lore.kernel.org/r/20251030105242.801528-1-mjguzik%40gmail.com patch subject: [PATCH v4] fs: hide names_cachep behind runtime access machinery config: i386-randconfig-061-20251031 (https://download.01.org/0day-ci/archive/20251101/[email protected]/config) compiler: gcc-14 (Debian 14.2.0-19) 14.2.0 reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20251101/[email protected]/reproduce)
If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <[email protected]>
| Closes: https://lore.kernel.org/oe-kbuild-all/[email protected]/
sparse warnings: (new ones prefixed by >>)
fs/d_path.c:195:9: sparse: sparse: context imbalance in 'prepend_path' - wrong count at exit fs/d_path.c:359:9: sparse: sparse: context imbalance in '__dentry_path' - wrong count at exit
>> fs/d_path.c:416:22: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) >> fs/d_path.c:416:22: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) fs/d_path.c:446:9: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) -- >> fs/namei.c:146:18: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) >> fs/namei.c:146:18: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef)
fs/namei.c:163:25: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) fs/namei.c:169:25: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) fs/namei.c:191:25: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) fs/namei.c:197:25: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) fs/namei.c:203:25: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) fs/namei.c:208:25: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) fs/namei.c:249:18: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) fs/namei.c:249:18: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) fs/namei.c:261:25: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) fs/namei.c:267:17: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) fs/namei.c:294:17: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) fs/namei.c:297:17: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) fs/namei.c: note: in included file (through include/linux/rbtree.h, include/linux/mm_types.h, include/linux/mmzone.h, ...):
include/linux/rcupdate.h:871:25: sparse: sparse: context imbalance in 'leave_rcu' - unexpected unlock fs/namei.c:2518:19: sparse: sparse: context imbalance in 'path_init' - different lock contexts for basic block
--
drivers/base/firmware_loader/main.c:229:9: sparse: sparse: context imbalance in 'free_fw_priv' - wrong count at exit
>> drivers/base/firmware_loader/main.c:509:16: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef) >> drivers/base/firmware_loader/main.c:509:16: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef)
drivers/base/firmware_loader/main.c:591:9: sparse: sparse: cast truncates bits from constant value (123456789abcdef becomes 89abcdef)
vim +416 fs/d_path.c
7a5cf791a74764 Al Viro 2018-03-05 393
7a5cf791a74764 Al Viro 2018-03-05 394 /*
7a5cf791a74764 Al Viro 2018-03-05 395 * NOTE! The user-level library version returns a
7a5cf791a74764 Al Viro 2018-03-05 396 * character pointer. The kernel system call just
7a5cf791a74764 Al Viro 2018-03-05 397 * returns the length of the buffer filled (which
7a5cf791a74764 Al Viro 2018-03-05 398 * includes the ending '\0' character), or a negative
7a5cf791a74764 Al Viro 2018-03-05 399 * error value. So libc would do something like
7a5cf791a74764 Al Viro 2018-03-05 400 *
7a5cf791a74764 Al Viro 2018-03-05 401 * char *getcwd(char * buf, size_t size)
7a5cf791a74764 Al Viro 2018-03-05 402 * {
7a5cf791a74764 Al Viro 2018-03-05 403 * int retval;
7a5cf791a74764 Al Viro 2018-03-05 404 *
7a5cf791a74764 Al Viro 2018-03-05 405 * retval = sys_getcwd(buf, size);
7a5cf791a74764 Al Viro 2018-03-05 406 * if (retval >= 0)
7a5cf791a74764 Al Viro 2018-03-05 407 * return buf;
7a5cf791a74764 Al Viro 2018-03-05 408 * errno = -retval;
7a5cf791a74764 Al Viro 2018-03-05 409 * return NULL;
7a5cf791a74764 Al Viro 2018-03-05 410 * }
7a5cf791a74764 Al Viro 2018-03-05 411 */
7a5cf791a74764 Al Viro 2018-03-05 412 SYSCALL_DEFINE2(getcwd, char __user *, buf, unsigned long, size)
7a5cf791a74764 Al Viro 2018-03-05 413 {
7a5cf791a74764 Al Viro 2018-03-05 414 int error;
7a5cf791a74764 Al Viro 2018-03-05 415 struct path pwd, root;7a5cf791a74764 Al Viro 2018-03-05 @416 char *page = __getname();
Signature · 2 lines
0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki
kernel test robot
build botkernel test robot noticed the following build errors:
Hi Mateusz,
kernel test robot noticed the following build errors:
[auto build test ERROR on arnd-asm-generic/master]
[also build test ERROR on linus/master linux/master v6.18-rc3 next-20251031] [If your patch is applied to the wrong git tree, kindly drop us a note. And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]
url: https://github.com/intel-lab-lkp/linux/commits/Mateusz-Guzik/fs-hide-names_cachep-behind-runtime-access-machinery/20251101-054539 base: https://git.kernel.org/pub/scm/linux/kernel/git/arnd/asm-generic.git master patch link: https://lore.kernel.org/r/20251030105242.801528-1-mjguzik%40gmail.com patch subject: [PATCH v4] fs: hide names_cachep behind runtime access machinery config: riscv-randconfig-r111-20251102 (https://download.01.org/0day-ci/archive/20251102/[email protected]/config) compiler: riscv64-linux-gcc (GCC) 11.5.0 reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20251102/[email protected]/reproduce)
If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <[email protected]>
| Closes: https://lore.kernel.org/oe-kbuild-all/[email protected]/
All errors (new ones prefixed by >>):
In file included from arch/riscv/include/asm/runtime-const.h:7,
from include/linux/fs.h:53,
from include/linux/huge_mm.h:7,
from include/linux/mm.h:1016,
from arch/riscv/kernel/asm-offsets.c:8:
arch/riscv/include/asm/cacheflush.h: In function 'flush_cache_vmap':
arch/riscv/include/asm/cacheflush.h:49:13: error: implicit declaration of function 'is_vmalloc_or_module_addr' [-Werror=implicit-function-declaration]
49 | if (is_vmalloc_or_module_addr((void *)start)) {
| ^~~~~~~~~~~~~~~~~~~~~~~~~
In file included from include/linux/compat.h:18,
from arch/riscv/include/asm/elf.h:12,
from include/linux/elf.h:6,
from include/linux/module.h:20,
from include/linux/device/driver.h:21,
from include/linux/device.h:32,
from include/linux/node.h:18,
from include/linux/memory.h:19,
from arch/riscv/include/asm/runtime-const.h:9,
from include/linux/fs.h:53,
from include/linux/huge_mm.h:7,
from include/linux/mm.h:1016,
from arch/riscv/kernel/asm-offsets.c:8:
include/uapi/linux/aio_abi.h: At top level:
include/uapi/linux/aio_abi.h:79:9: error: unknown type name '__kernel_rwf_t'
79 | __kernel_rwf_t aio_rw_flags; /* RWF_* flags */
| ^~~~~~~~~~~~~~
In file included from arch/riscv/kernel/asm-offsets.c:8:
>> include/linux/mm.h:1092:19: error: static declaration of 'is_vmalloc_or_module_addr' follows non-static declaration
1092 | static inline int is_vmalloc_or_module_addr(const void *x)
| ^~~~~~~~~~~~~~~~~~~~~~~~~
In file included from arch/riscv/include/asm/runtime-const.h:7,
from include/linux/fs.h:53,
from include/linux/huge_mm.h:7,
from include/linux/mm.h:1016,
from arch/riscv/kernel/asm-offsets.c:8:
arch/riscv/include/asm/cacheflush.h:49:13: note: previous implicit declaration of 'is_vmalloc_or_module_addr' with type 'int()'
49 | if (is_vmalloc_or_module_addr((void *)start)) {
| ^~~~~~~~~~~~~~~~~~~~~~~~~ cc1: some warnings being treated as errors
make[3]: *** [scripts/Makefile.build:182: arch/riscv/kernel/asm-offsets.s] Error 1 make[3]: Target 'prepare' not remade because of errors.
make[2]: *** [Makefile:1282: prepare0] Error 2
make[2]: Target 'prepare' not remade because of errors.
make[1]: *** [Makefile:248: __sub-make] Error 2
make[1]: Target 'prepare' not remade because of errors.
make: *** [Makefile:248: __sub-make] Error 2
make: Target 'prepare' not remade because of errors.
vim +/is_vmalloc_or_module_addr +1092 include/linux/mm.h
98b1917cdef92c David Hildenbrand 2025-04-10 1015
71e3aac0724ffe Andrea Arcangeli 2011-01-13 @1016 #include <linux/huge_mm.h>
^1da177e4c3f41 Linus Torvalds 2005-04-16 1017
^1da177e4c3f41 Linus Torvalds 2005-04-16 1018 /*
^1da177e4c3f41 Linus Torvalds 2005-04-16 1019 * Methods to modify the page usage count.
^1da177e4c3f41 Linus Torvalds 2005-04-16 1020 *
^1da177e4c3f41 Linus Torvalds 2005-04-16 1021 * What counts for a page usage:
^1da177e4c3f41 Linus Torvalds 2005-04-16 1022 * - cache mapping (page->mapping)
^1da177e4c3f41 Linus Torvalds 2005-04-16 1023 * - private data (page->private)
^1da177e4c3f41 Linus Torvalds 2005-04-16 1024 * - page mapped in a task's page tables, each mapping
^1da177e4c3f41 Linus Torvalds 2005-04-16 1025 * is counted separately
^1da177e4c3f41 Linus Torvalds 2005-04-16 1026 *
^1da177e4c3f41 Linus Torvalds 2005-04-16 1027 * Also, many kernel routines increase the page count before a critical
^1da177e4c3f41 Linus Torvalds 2005-04-16 1028 * routine so they can be sure the page doesn't go away from under them.
^1da177e4c3f41 Linus Torvalds 2005-04-16 1029 */
^1da177e4c3f41 Linus Torvalds 2005-04-16 1030
^1da177e4c3f41 Linus Torvalds 2005-04-16 1031 /*
da6052f7b33abe Nicholas Piggin 2006-09-25 1032 * Drop a ref, return true if the refcount fell to zero (the page has no users)
^1da177e4c3f41 Linus Torvalds 2005-04-16 1033 */
7c8ee9a86340db Nicholas Piggin 2006-03-22 1034 static inline int put_page_testzero(struct page *page)
7c8ee9a86340db Nicholas Piggin 2006-03-22 1035 {
fe896d1878949e Joonsoo Kim 2016-03-17 1036 VM_BUG_ON_PAGE(page_ref_count(page) == 0, page);
fe896d1878949e Joonsoo Kim 2016-03-17 1037 return page_ref_dec_and_test(page);
7c8ee9a86340db Nicholas Piggin 2006-03-22 1038 }
^1da177e4c3f41 Linus Torvalds 2005-04-16 1039
b620f63358cd35 Matthew Wilcox (Oracle 2020-12-06 1040) static inline int folio_put_testzero(struct folio *folio)
b620f63358cd35 Matthew Wilcox (Oracle 2020-12-06 1041) {
b620f63358cd35 Matthew Wilcox (Oracle 2020-12-06 1042) return put_page_testzero(&folio->page);
b620f63358cd35 Matthew Wilcox (Oracle 2020-12-06 1043) }
b620f63358cd35 Matthew Wilcox (Oracle 2020-12-06 1044)
^1da177e4c3f41 Linus Torvalds 2005-04-16 1045 /*
7c8ee9a86340db Nicholas Piggin 2006-03-22 1046 * Try to grab a ref unless the page has a refcount of zero, return false if
7c8ee9a86340db Nicholas Piggin 2006-03-22 1047 * that is the case.
8e0861fa3c4edf Alexey Kardashevskiy 2013-08-28 1048 * This can be called when MMU is off so it must not access
8e0861fa3c4edf Alexey Kardashevskiy 2013-08-28 1049 * any of the virtual mappings.
^1da177e4c3f41 Linus Torvalds 2005-04-16 1050 */
c25303281d7929 Matthew Wilcox (Oracle 2021-06-05 1051) static inline bool get_page_unless_zero(struct page *page)
7c8ee9a86340db Nicholas Piggin 2006-03-22 1052 {
fe896d1878949e Joonsoo Kim 2016-03-17 1053 return page_ref_add_unless(page, 1, 0);
7c8ee9a86340db Nicholas Piggin 2006-03-22 1054 }
^1da177e4c3f41 Linus Torvalds 2005-04-16 1055
3c1ea2c729ef8e Vishal Moola (Oracle 2023-01-30 1056) static inline struct folio *folio_get_nontail_page(struct page *page)
3c1ea2c729ef8e Vishal Moola (Oracle 2023-01-30 1057) {
3c1ea2c729ef8e Vishal Moola (Oracle 2023-01-30 1058) if (unlikely(!get_page_unless_zero(page)))
3c1ea2c729ef8e Vishal Moola (Oracle 2023-01-30 1059) return NULL;
3c1ea2c729ef8e Vishal Moola (Oracle 2023-01-30 1060) return (struct folio *)page;
3c1ea2c729ef8e Vishal Moola (Oracle 2023-01-30 1061) }
3c1ea2c729ef8e Vishal Moola (Oracle 2023-01-30 1062)
53df8fdc15fb64 Wu Fengguang 2010-01-27 1063 extern int page_is_ram(unsigned long pfn);
124fe20d94630b Dan Williams 2015-08-10 1064
124fe20d94630b Dan Williams 2015-08-10 1065 enum {
124fe20d94630b Dan Williams 2015-08-10 1066 REGION_INTERSECTS,
124fe20d94630b Dan Williams 2015-08-10 1067 REGION_DISJOINT,
124fe20d94630b Dan Williams 2015-08-10 1068 REGION_MIXED,
124fe20d94630b Dan Williams 2015-08-10 1069 };
124fe20d94630b Dan Williams 2015-08-10 1070
1c29f25bf5d6c5 Toshi Kani 2016-01-26 1071 int region_intersects(resource_size_t offset, size_t size, unsigned long flags,
1c29f25bf5d6c5 Toshi Kani 2016-01-26 1072 unsigned long desc);
53df8fdc15fb64 Wu Fengguang 2010-01-27 1073
48667e7a43c1a1 Christoph Lameter 2008-02-04 1074 /* Support for virtually mapped pages */
b3bdda02aa547a Christoph Lameter 2008-02-04 1075 struct page *vmalloc_to_page(const void *addr);
b3bdda02aa547a Christoph Lameter 2008-02-04 1076 unsigned long vmalloc_to_pfn(const void *addr);
48667e7a43c1a1 Christoph Lameter 2008-02-04 1077
0738c4bb8f2a8b Paul Mundt 2008-03-12 1078 /*
0738c4bb8f2a8b Paul Mundt 2008-03-12 1079 * Determine if an address is within the vmalloc range
0738c4bb8f2a8b Paul Mundt 2008-03-12 1080 *
0738c4bb8f2a8b Paul Mundt 2008-03-12 1081 * On nommu, vmalloc/vfree wrap through kmalloc/kfree directly, so there
0738c4bb8f2a8b Paul Mundt 2008-03-12 1082 * is no special casing required.
0738c4bb8f2a8b Paul Mundt 2008-03-12 1083 */
81ac3ad9061dd9 KAMEZAWA Hiroyuki 2009-09-22 1084 #ifdef CONFIG_MMU
186525bd6b83ef Ingo Molnar 2019-11-29 1085 extern bool is_vmalloc_addr(const void *x);
81ac3ad9061dd9 KAMEZAWA Hiroyuki 2009-09-22 1086 extern int is_vmalloc_or_module_addr(const void *x);
81ac3ad9061dd9 KAMEZAWA Hiroyuki 2009-09-22 1087 #else
186525bd6b83ef Ingo Molnar 2019-11-29 1088 static inline bool is_vmalloc_addr(const void *x)
186525bd6b83ef Ingo Molnar 2019-11-29 1089 {
186525bd6b83ef Ingo Molnar 2019-11-29 1090 return false;
186525bd6b83ef Ingo Molnar 2019-11-29 1091 }
934831d060ccd5 David Howells 2009-09-24 @1092 static inline int is_vmalloc_or_module_addr(const void *x)
81ac3ad9061dd9 KAMEZAWA Hiroyuki 2009-09-22 1093 {
81ac3ad9061dd9 KAMEZAWA Hiroyuki 2009-09-22 1094 return 0;
81ac3ad9061dd9 KAMEZAWA Hiroyuki 2009-09-22 1095 }
81ac3ad9061dd9 KAMEZAWA Hiroyuki 2009-09-22 1096 #endif
9e2779fa281cfd Christoph Lameter 2008-02-04 1097 Signature · 2 lines
0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki