- Linux-kselftest-mirror - lists.linaro.org

Re: [PATCH v6 1/3] mm: add new api to enable ksm per process

by David Hildenbrand

[...] Thanks for giving mu sugegstions a churn. I think we can further improve/simplify some things. I added some comments, but might have more regarding MMF_VM_MERGE_ANY / MMF_VM_MERGEABLE. [I'll try reowkring your patch after I send this mail to play with some simplifications] > arch/s390/mm/gmap.c | 1 + > include/linux/ksm.h | 23 +++++-- > include/linux/sched/coredump.h | 1 + > include/uapi/linux/prctl.h | 2 + > kernel/fork.c | 1 + > kernel/sys.c | 23 +++++++ > mm/ksm.c | 111 ++++++++++++++++++++++++++------- > mm/mmap.c | 7 +++ > 8 files changed, 142 insertions(+), 27 deletions(-) > > diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c > index 5a716bdcba05..9d85e5589474 100644 > --- a/arch/s390/mm/gmap.c > +++ b/arch/s390/mm/gmap.c > @@ -2591,6 +2591,7 @@ int gmap_mark_unmergeable(void) > int ret; > VMA_ITERATOR(vmi, mm, 0); > > + clear_bit(MMF_VM_MERGE_ANY, &mm->flags); Okay, that should keep the existing mechanism working. (but users can still mess it up) Might be worth a comment /* * Make sure to disable KSM (if enabled for the whole process or * individual VMAs). Note that nothing currently hinders user space * from re-enabling it. */ > for_each_vma(vmi, vma) { > /* Copy vm_flags to avoid partial modifications in ksm_madvise */ > vm_flags = vma->vm_flags; > diff --git a/include/linux/ksm.h b/include/linux/ksm.h > index 7e232ba59b86..f24f9faf1561 100644 > --- a/include/linux/ksm.h > +++ b/include/linux/ksm.h > @@ -18,20 +18,29 @@ > #ifdef CONFIG_KSM > int ksm_madvise(struct vm_area_struct *vma, unsigned long start, > unsigned long end, int advice, unsigned long *vm_flags); > -int __ksm_enter(struct mm_struct *mm); > -void __ksm_exit(struct mm_struct *mm); > + > +int ksm_add_mm(struct mm_struct *mm); > +void ksm_add_vma(struct vm_area_struct *vma); > +void ksm_add_vmas(struct mm_struct *mm); > + > +int __ksm_enter(struct mm_struct *mm, int flag); > +void __ksm_exit(struct mm_struct *mm, int flag); > > static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) > { > + if (test_bit(MMF_VM_MERGE_ANY, &oldmm->flags)) > + return ksm_add_mm(mm); ksm_fork() runs before copying any VMAs. Copying the bit should be sufficient. Would it be possible to rework to something like: if (test_bit(MMF_VM_MERGE_ANY, &oldmm->flags)) set_bit(MMF_VM_MERGE_ANY, &mm->flags) if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags)) return __ksm_enter(mm); work? IOW, not exporting ksm_add_mm() and not passing a flag to __ksm_enter() -- it would simply set MMF_VM_MERGEABLE ? I rememebr proposing that enabling MMF_VM_MERGE_ANY would simply enable MMF_VM_MERGEABLE. > if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags)) > - return __ksm_enter(mm); > + return __ksm_enter(mm, MMF_VM_MERGEABLE); > return 0; > } > > static inline void ksm_exit(struct mm_struct *mm) > { > - if (test_bit(MMF_VM_MERGEABLE, &mm->flags)) > - __ksm_exit(mm); > + if (test_bit(MMF_VM_MERGE_ANY, &mm->flags)) > + __ksm_exit(mm, MMF_VM_MERGE_ANY); > + else if (test_bit(MMF_VM_MERGEABLE, &mm->flags)) > + __ksm_exit(mm, MMF_VM_MERGEABLE); Can we do if (test_bit(MMF_VM_MERGEABLE, &mm->flags)) __ksm_exit(mm); And simply let __ksm_exit() clear both bits? > } > > /* > @@ -53,6 +62,10 @@ void folio_migrate_ksm(struct folio *newfolio, struct folio *folio); > > #else /* !CONFIG_KSM */ > [...] > #endif /* _LINUX_SCHED_COREDUMP_H */ > diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h > index 1312a137f7fb..759b3f53e53f 100644 > --- a/include/uapi/linux/prctl.h > +++ b/include/uapi/linux/prctl.h > @@ -290,4 +290,6 @@ struct prctl_mm_map { > #define PR_SET_VMA 0x53564d41 > # define PR_SET_VMA_ANON_NAME 0 > > +#define PR_SET_MEMORY_MERGE 67 > +#define PR_GET_MEMORY_MERGE 68 > #endif /* _LINUX_PRCTL_H */ > diff --git a/kernel/fork.c b/kernel/fork.c > index f68954d05e89..1520697cf6c7 100644 > --- a/kernel/fork.c > +++ b/kernel/fork.c > @@ -686,6 +686,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, > if (vma_iter_bulk_store(&vmi, tmp)) > goto fail_nomem_vmi_store; > > + ksm_add_vma(tmp); Is this really required? The relevant VMAs should have VM_MERGEABLE set. > mm->map_count++; > if (!(tmp->vm_flags & VM_WIPEONFORK)) > retval = copy_page_range(tmp, mpnt); > diff --git a/kernel/sys.c b/kernel/sys.c > index 495cd87d9bf4..9bba163d2d04 100644 > --- a/kernel/sys.c > +++ b/kernel/sys.c > @@ -15,6 +15,7 @@ > #include <linux/highuid.h> > #include <linux/fs.h> > #include <linux/kmod.h> > +#include <linux/ksm.h> > #include <linux/perf_event.h> > #include <linux/resource.h> > #include <linux/kernel.h> > @@ -2661,6 +2662,28 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, > case PR_SET_VMA: > error = prctl_set_vma(arg2, arg3, arg4, arg5); > break; > +#ifdef CONFIG_KSM > + case PR_SET_MEMORY_MERGE: > + if (mmap_write_lock_killable(me->mm)) > + return -EINTR; > + > + if (arg2) { > + int err = ksm_add_mm(me->mm); > + > + if (!err) > + ksm_add_vmas(me->mm); > + } else { > + clear_bit(MMF_VM_MERGE_ANY, &me->mm->flags); Okay, so disabling doesn't actually unshare anything. > + } > + mmap_write_unlock(me->mm); > + break; > + case PR_GET_MEMORY_MERGE: > + if (arg2 || arg3 || arg4 || arg5) > + return -EINVAL; > + > + error = !!test_bit(MMF_VM_MERGE_ANY, &me->mm->flags); > + break; > +#endif > default: > error = -EINVAL; > break; > diff --git a/mm/ksm.c b/mm/ksm.c > index d7bd28199f6c..ab95ae0f9def 100644 > --- a/mm/ksm.c > +++ b/mm/ksm.c > @@ -534,10 +534,33 @@ static int break_ksm(struct vm_area_struct *vma, unsigned long addr, > return (ret & VM_FAULT_OOM) ? -ENOMEM : 0; > } > > +static bool vma_ksm_compatible(struct vm_area_struct *vma) > +{ > + if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE | VM_PFNMAP | > + VM_IO | VM_DONTEXPAND | VM_HUGETLB | > + VM_MIXEDMAP)) > + return false; /* just ignore the advice */ > + > + if (vma_is_dax(vma)) > + return false; > + > +#ifdef VM_SAO > + if (vma->vm_flags & VM_SAO) > + return false; > +#endif > +#ifdef VM_SPARC_ADI > + if (vma->vm_flags & VM_SPARC_ADI) > + return false; > +#endif > + > + return true; > +} > + > static struct vm_area_struct *find_mergeable_vma(struct mm_struct *mm, > unsigned long addr) > { > struct vm_area_struct *vma; > + unrelated change > if (ksm_test_exit(mm)) > return NULL; > vma = vma_lookup(mm, addr); > @@ -1065,6 +1088,7 @@ static int unmerge_and_remove_all_rmap_items(void) > > mm_slot_free(mm_slot_cache, mm_slot); > clear_bit(MMF_VM_MERGEABLE, &mm->flags); > + clear_bit(MMF_VM_MERGE_ANY, &mm->flags); > mmdrop(mm); > } else > spin_unlock(&ksm_mmlist_lock); > @@ -2495,6 +2519,7 @@ static struct ksm_rmap_item *scan_get_next_rmap_item(struct page **page) > > mm_slot_free(mm_slot_cache, mm_slot); > clear_bit(MMF_VM_MERGEABLE, &mm->flags); > + clear_bit(MMF_VM_MERGE_ANY, &mm->flags); > mmap_read_unlock(mm); > mmdrop(mm); > } else { > @@ -2571,6 +2596,63 @@ static int ksm_scan_thread(void *nothing) > return 0; > } > > +static void __ksm_add_vma(struct vm_area_struct *vma) > +{ > + unsigned long vm_flags = vma->vm_flags; > + > + if (vm_flags & VM_MERGEABLE) > + return; > + > + if (vma_ksm_compatible(vma)) { > + vm_flags |= VM_MERGEABLE; > + vm_flags_reset(vma, vm_flags); > + } > +} > + > +/** > + * ksm_add_vma - Mark vma as mergeable "if compatible" > + * > + * @vma: Pointer to vma > + */ > +void ksm_add_vma(struct vm_area_struct *vma) > +{ > + struct mm_struct *mm = vma->vm_mm; > + > + if (test_bit(MMF_VM_MERGE_ANY, &mm->flags)) > + __ksm_add_vma(vma); > +} > + > +/** > + * ksm_add_vmas - Mark all vma's of a process as mergeable > + * > + * @mm: Pointer to mm > + */ > +void ksm_add_vmas(struct mm_struct *mm) I'd suggest calling this > +{ > + struct vm_area_struct *vma; > + > + VMA_ITERATOR(vmi, mm, 0); > + for_each_vma(vmi, vma) > + __ksm_add_vma(vma); > +} > + > +/** > + * ksm_add_mm - Add mm to mm ksm list > + * > + * @mm: Pointer to mm > + * > + * Returns 0 on success, otherwise error code > + */ > +int ksm_add_mm(struct mm_struct *mm) > +{ > + if (test_bit(MMF_VM_MERGE_ANY, &mm->flags)) > + return -EINVAL; > + if (test_bit(MMF_VM_MERGEABLE, &mm->flags)) > + return -EINVAL; > + > + return __ksm_enter(mm, MMF_VM_MERGE_ANY); > +} > + > int ksm_madvise(struct vm_area_struct *vma, unsigned long start, > unsigned long end, int advice, unsigned long *vm_flags) > { > @@ -2579,28 +2661,13 @@ int ksm_madvise(struct vm_area_struct *vma, unsigned long start, > > switch (advice) { > case MADV_MERGEABLE: > - /* > - * Be somewhat over-protective for now! > - */ > - if (*vm_flags & (VM_MERGEABLE | VM_SHARED | VM_MAYSHARE | > - VM_PFNMAP | VM_IO | VM_DONTEXPAND | > - VM_HUGETLB | VM_MIXEDMAP)) > - return 0; /* just ignore the advice */ > - > - if (vma_is_dax(vma)) > + if (vma->vm_flags & VM_MERGEABLE) > return 0; > - > -#ifdef VM_SAO > - if (*vm_flags & VM_SAO) > + if (!vma_ksm_compatible(vma)) > return 0; > -#endif > -#ifdef VM_SPARC_ADI > - if (*vm_flags & VM_SPARC_ADI) > - return 0; > -#endif > > if (!test_bit(MMF_VM_MERGEABLE, &mm->flags)) { > - err = __ksm_enter(mm); > + err = __ksm_enter(mm, MMF_VM_MERGEABLE); > if (err) > return err; > } > @@ -2626,7 +2693,7 @@ int ksm_madvise(struct vm_area_struct *vma, unsigned long start, > } > EXPORT_SYMBOL_GPL(ksm_madvise); > > -int __ksm_enter(struct mm_struct *mm) > +int __ksm_enter(struct mm_struct *mm, int flag) > { > struct ksm_mm_slot *mm_slot; > struct mm_slot *slot; > @@ -2659,7 +2726,7 @@ int __ksm_enter(struct mm_struct *mm) > list_add_tail(&slot->mm_node, &ksm_scan.mm_slot->slot.mm_node); > spin_unlock(&ksm_mmlist_lock); > > - set_bit(MMF_VM_MERGEABLE, &mm->flags); > + set_bit(flag, &mm->flags); > mmgrab(mm); > > if (needs_wakeup) > @@ -2668,7 +2735,7 @@ int __ksm_enter(struct mm_struct *mm) > return 0; > } > > -void __ksm_exit(struct mm_struct *mm) > +void __ksm_exit(struct mm_struct *mm, int flag) > { > struct ksm_mm_slot *mm_slot; > struct mm_slot *slot; > @@ -2700,7 +2767,7 @@ void __ksm_exit(struct mm_struct *mm) > > if (easy_to_free) { > mm_slot_free(mm_slot_cache, mm_slot); > - clear_bit(MMF_VM_MERGEABLE, &mm->flags); > + clear_bit(flag, &mm->flags); > mmdrop(mm); > } else if (mm_slot) { > mmap_write_lock(mm); > diff --git a/mm/mmap.c b/mm/mmap.c > index 740b54be3ed4..483e182e0b9d 100644 > --- a/mm/mmap.c > +++ b/mm/mmap.c > @@ -46,6 +46,7 @@ > #include <linux/pkeys.h> > #include <linux/oom.h> > #include <linux/sched/mm.h> > +#include <linux/ksm.h> > > #include <linux/uaccess.h> > #include <asm/cacheflush.h> > @@ -2213,6 +2214,8 @@ int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, > /* vma_complete stores the new vma */ > vma_complete(&vp, vmi, vma->vm_mm); > > + ksm_add_vma(new); > + Splitting a VMA shouldn't modify VM_MERGEABLE, so I assume this is not required? > /* Success. */ > if (new_below) > vma_next(vmi); > @@ -2664,6 +2667,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, > if (file && vm_flags & VM_SHARED) > mapping_unmap_writable(file->f_mapping); > file = vma->vm_file; > + ksm_add_vma(vma); > expanded: > perf_event_mmap(vma); > > @@ -2936,6 +2940,7 @@ static int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma, > goto mas_store_fail; > > mm->map_count++; > + ksm_add_vma(vma); > out: > perf_event_mmap(vma); > mm->total_vm += len >> PAGE_SHIFT; > @@ -3180,6 +3185,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, > if (vma_link(mm, new_vma)) > goto out_vma_link; > *need_rmap_locks = false; > + ksm_add_vma(new_vma); Copying shouldn't modify VM_MERGEABLE, so I think this is not required? > } > validate_mm_mt(mm); > return new_vma; > @@ -3356,6 +3362,7 @@ static struct vm_area_struct *__install_special_mapping( > vm_stat_account(mm, vma->vm_flags, len >> PAGE_SHIFT); > > perf_event_mmap(vma); > + ksm_add_vma(vma); IIUC, special mappings will never be considered a reasonable target for KSM (especially, because at least VM_DONTEXPAND is always set). I think you can just drop this call. -- Thanks, David / dhildenb

2 years, 6 months

2
5
0 0

[PATCH AUTOSEL 5.15 6/8] selftests mount: Fix mount_setattr_test builds failed

by Sasha Levin

From: Anh Tuan Phan <tuananhlfc(a)gmail.com> [ Upstream commit f1594bc676579133a3cd906d7d27733289edfb86 ] When compiling selftests with target mount_setattr I encountered some errors with the below messages: mount_setattr_test.c: In function ‘mount_setattr_thread’: mount_setattr_test.c:343:16: error: variable ‘attr’ has initializer but incomplete type 343 | struct mount_attr attr = { | ^~~~~~~~~~ These errors might be because of linux/mount.h is not included. This patch resolves that issue. Signed-off-by: Anh Tuan Phan <tuananhlfc(a)gmail.com> Acked-by: Christian Brauner <brauner(a)kernel.org> Signed-off-by: Shuah Khan <skhan(a)linuxfoundation.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/mount_setattr/mount_setattr_test.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/mount_setattr/mount_setattr_test.c b/tools/testing/selftests/mount_setattr/mount_setattr_test.c index 8c5fea68ae677..969647228817b 100644 --- a/tools/testing/selftests/mount_setattr/mount_setattr_test.c +++ b/tools/testing/selftests/mount_setattr/mount_setattr_test.c @@ -18,6 +18,7 @@ #include <grp.h> #include <stdbool.h> #include <stdarg.h> +#include <linux/mount.h> #include "../kselftest_harness.h" -- 2.39.2

2 years, 6 months

1
0
0 0

[PATCH AUTOSEL 6.1 10/17] selftests mount: Fix mount_setattr_test builds failed

by Sasha Levin

From: Anh Tuan Phan <tuananhlfc(a)gmail.com> [ Upstream commit f1594bc676579133a3cd906d7d27733289edfb86 ] When compiling selftests with target mount_setattr I encountered some errors with the below messages: mount_setattr_test.c: In function ‘mount_setattr_thread’: mount_setattr_test.c:343:16: error: variable ‘attr’ has initializer but incomplete type 343 | struct mount_attr attr = { | ^~~~~~~~~~ These errors might be because of linux/mount.h is not included. This patch resolves that issue. Signed-off-by: Anh Tuan Phan <tuananhlfc(a)gmail.com> Acked-by: Christian Brauner <brauner(a)kernel.org> Signed-off-by: Shuah Khan <skhan(a)linuxfoundation.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/mount_setattr/mount_setattr_test.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/mount_setattr/mount_setattr_test.c b/tools/testing/selftests/mount_setattr/mount_setattr_test.c index 8c5fea68ae677..969647228817b 100644 --- a/tools/testing/selftests/mount_setattr/mount_setattr_test.c +++ b/tools/testing/selftests/mount_setattr/mount_setattr_test.c @@ -18,6 +18,7 @@ #include <grp.h> #include <stdbool.h> #include <stdarg.h> +#include <linux/mount.h> #include "../kselftest_harness.h" -- 2.39.2

2 years, 6 months

1
0
0 0

[PATCH AUTOSEL 6.2 12/20] selftests mount: Fix mount_setattr_test builds failed

by Sasha Levin

From: Anh Tuan Phan <tuananhlfc(a)gmail.com> [ Upstream commit f1594bc676579133a3cd906d7d27733289edfb86 ] When compiling selftests with target mount_setattr I encountered some errors with the below messages: mount_setattr_test.c: In function ‘mount_setattr_thread’: mount_setattr_test.c:343:16: error: variable ‘attr’ has initializer but incomplete type 343 | struct mount_attr attr = { | ^~~~~~~~~~ These errors might be because of linux/mount.h is not included. This patch resolves that issue. Signed-off-by: Anh Tuan Phan <tuananhlfc(a)gmail.com> Acked-by: Christian Brauner <brauner(a)kernel.org> Signed-off-by: Shuah Khan <skhan(a)linuxfoundation.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/mount_setattr/mount_setattr_test.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/mount_setattr/mount_setattr_test.c b/tools/testing/selftests/mount_setattr/mount_setattr_test.c index 8c5fea68ae677..969647228817b 100644 --- a/tools/testing/selftests/mount_setattr/mount_setattr_test.c +++ b/tools/testing/selftests/mount_setattr/mount_setattr_test.c @@ -18,6 +18,7 @@ #include <grp.h> #include <stdbool.h> #include <stdarg.h> +#include <linux/mount.h> #include "../kselftest_harness.h" -- 2.39.2

2 years, 6 months

1
0
0 0

[PATCH v3 00/11] clk: Add kunit tests for fixed rate and parent data

by Stephen Boyd

This patch series adds unit tests for the clk fixed rate basic type and the clk registration functions that use struct clk_parent_data. To get there, we add support for loading device tree overlays onto the live DTB along with probing platform drivers to bind to device nodes in the overlays. With this series, we're able to exercise some of the code in the common clk framework that uses devicetree lookups to find parents and the fixed rate clk code that scans device tree directly and creates clks. Please review. I Cced everyone to all the patches so they get the full context. I'm hoping I can take the whole pile through the clk tree as they almost all depend on each other. Changes from v2 (https://lore.kernel.org/r/20230315183729.2376178-1-sboyd@kernel.org): * Overlays don't depend on __symbols__ node * Depend on Frank's always create root node if CONFIG_OF series[1] * Added kernel-doc to KUnit API doc * Fixed some kernel-doc on functions * More test cases for fixed rate clk Changes from v1 (https://lore.kernel.org/r/20230302013822.1808711-1-sboyd@kernel.org): * Don't depend on UML, use unittest data approach to attach nodes * Introduce overlay loading API for KUnit * Move platform_device KUnit code to drivers/base/test * Use #define macros for constants shared between unit tests and overlays * Settle on "test" as a vendor prefix * Make KUnit wrappers have "_kunit" postfix Stephen Boyd (11): of: Add KUnit test to confirm DTB is loaded of: Add test managed wrappers for of_overlay_apply()/of_node_put() dt-bindings: vendor-prefixes: Add "test" vendor for KUnit and friends dt-bindings: test: Add KUnit empty node binding of: Add a KUnit test for overlays and test managed APIs platform: Add test managed platform_device/driver APIs dt-bindings: kunit: Add fixed rate clk consumer test clk: Add test managed clk provider/consumer APIs clk: Add KUnit tests for clk fixed rate basic type dt-bindings: clk: Add KUnit clk_parent_data test clk: Add KUnit tests for clks registered with struct clk_parent_data Documentation/dev-tools/kunit/api/clk.rst | 10 + Documentation/dev-tools/kunit/api/index.rst | 22 + Documentation/dev-tools/kunit/api/of.rst | 13 + .../dev-tools/kunit/api/platformdevice.rst | 10 + .../bindings/clock/test,clk-parent-data.yaml | 47 ++ .../bindings/test/test,clk-fixed-rate.yaml | 35 ++ .../devicetree/bindings/test/test,empty.yaml | 30 ++ .../devicetree/bindings/vendor-prefixes.yaml | 2 + drivers/base/test/Makefile | 3 + drivers/base/test/platform_kunit-test.c | 140 ++++++ drivers/base/test/platform_kunit.c | 215 ++++++++ drivers/clk/.kunitconfig | 3 + drivers/clk/Kconfig | 7 + drivers/clk/Makefile | 9 +- drivers/clk/clk-fixed-rate_test.c | 374 ++++++++++++++ drivers/clk/clk-fixed-rate_test.h | 8 + drivers/clk/clk_kunit.c | 224 +++++++++ drivers/clk/clk_parent_data_test.h | 10 + drivers/clk/clk_test.c | 459 +++++++++++++++++- drivers/clk/kunit_clk_fixed_rate_test.dtso | 19 + drivers/clk/kunit_clk_parent_data_test.dtso | 28 ++ drivers/of/.kunitconfig | 5 + drivers/of/Kconfig | 19 + drivers/of/Makefile | 4 + drivers/of/kunit_overlay_test.dtso | 9 + drivers/of/of_kunit.c | 125 +++++ drivers/of/of_test.c | 34 ++ drivers/of/overlay_test.c | 110 +++++ include/kunit/clk.h | 28 ++ include/kunit/of.h | 94 ++++ include/kunit/platform_device.h | 15 + 31 files changed, 2109 insertions(+), 2 deletions(-) create mode 100644 Documentation/dev-tools/kunit/api/clk.rst create mode 100644 Documentation/dev-tools/kunit/api/of.rst create mode 100644 Documentation/dev-tools/kunit/api/platformdevice.rst create mode 100644 Documentation/devicetree/bindings/clock/test,clk-parent-data.yaml create mode 100644 Documentation/devicetree/bindings/test/test,clk-fixed-rate.yaml create mode 100644 Documentation/devicetree/bindings/test/test,empty.yaml create mode 100644 drivers/base/test/platform_kunit-test.c create mode 100644 drivers/base/test/platform_kunit.c create mode 100644 drivers/clk/clk-fixed-rate_test.c create mode 100644 drivers/clk/clk-fixed-rate_test.h create mode 100644 drivers/clk/clk_kunit.c create mode 100644 drivers/clk/clk_parent_data_test.h create mode 100644 drivers/clk/kunit_clk_fixed_rate_test.dtso create mode 100644 drivers/clk/kunit_clk_parent_data_test.dtso create mode 100644 drivers/of/.kunitconfig create mode 100644 drivers/of/kunit_overlay_test.dtso create mode 100644 drivers/of/of_kunit.c create mode 100644 drivers/of/of_test.c create mode 100644 drivers/of/overlay_test.c create mode 100644 include/kunit/clk.h create mode 100644 include/kunit/of.h create mode 100644 include/kunit/platform_device.h [1] https://lore.kernel.org/r/20230317053415.2254616-1-frowand.list@gmail.com base-commit: fe15c26ee26efa11741a7b632e9f23b01aca4cc6 prerequisite-patch-id: 33517b96dd0768ab9c265f5721629786354ee320 prerequisite-patch-id: 909221815eeca0a2b0cdd385c76f57e185fb9e33 -- https://git.kernel.org/pub/scm/linux/kernel/git/clk/linux.git/ https://git.kernel.org/pub/scm/linux/kernel/git/sboyd/spmi.git

2 years, 6 months

3
18
0 0

[PATCH bpf-next v3 0/3] Add FOU support for externally controlled ipip devices

by Christian Ehrig

This patch set adds support for using FOU or GUE encapsulation with an ipip device operating in collect-metadata mode and a set of kfuncs for controlling encap parameters exposed to a BPF tc-hook. BPF tc-hooks allow us to read tunnel metadata (like remote IP addresses) in the ingress path of an externally controlled tunnel interface via the bpf_skb_get_tunnel_{key,opt} bpf-helpers. Packets can then be redirected to the same or a different externally controlled tunnel interface by overwriting metadata via the bpf_skb_set_tunnel_{key,opt} helpers and a call to bpf_redirect. This enables us to redirect packets between tunnel interfaces - and potentially change the encapsulation type - using only a single BPF program. Today this approach works fine for a couple of tunnel combinations. For example: redirecting packets between Geneve and GRE interfaces or GRE and plain ipip interfaces. However, redirecting using FOU or GUE is not supported today. The ip_tunnel module does not allow us to egress packets using additional UDP encapsulation from an ipip device in collect-metadata mode. Patch 1 lifts this restriction by adding a struct ip_tunnel_encap to the tunnel metadata. It can be filled by a new BPF kfunc introduced in Patch 2 and evaluated by the ip_tunnel egress path. This will allow us to use FOU and GUE encap with externally controlled ipip devices. Patch 2 introduces two new BPF kfuncs: bpf_skb_{set,get}_fou_encap. These helpers can be used to set and get UDP encap parameters from the BPF tc-hook doing the packet redirect. Patch 3 adds BPF tunnel selftests using the two kfuncs. --- v3: - Integrate selftest into test_progs (Alexei) v2: - Fixes for checkpatch.pl - Fixes for kernel test robot Christian Ehrig (3): ipip,ip_tunnel,sit: Add FOU support for externally controlled ipip devices bpf,fou: Add bpf_skb_{set,get}_fou_encap kfuncs selftests/bpf: Test FOU kfuncs for externally controlled ipip devices include/net/fou.h | 2 + include/net/ip_tunnels.h | 28 ++-- net/ipv4/Makefile | 2 +- net/ipv4/fou_bpf.c | 119 ++++++++++++++ net/ipv4/fou_core.c | 5 + net/ipv4/ip_tunnel.c | 22 ++- net/ipv4/ipip.c | 1 + net/ipv6/sit.c | 2 +- .../selftests/bpf/prog_tests/test_tunnel.c | 153 +++++++++++++++++- .../selftests/bpf/progs/test_tunnel_kern.c | 117 ++++++++++++++ 10 files changed, 432 insertions(+), 19 deletions(-) create mode 100644 net/ipv4/fou_bpf.c -- 2.39.2

2 years, 6 months

2
2
0 0

[PATCH v1 RESEND 0/6] mm: (pte|pmd)_mkdirty() should not unconditionally allow for write access

by David Hildenbrand

This is the follow-up on [1], adding selftests (testing for known issues we added workarounds for and other issues that haven't been fixed yet), fixing sparc64, reverting the workarounds, and perform one cleanup. The patch from [1] was modified slightly (updated/extended patch description, dropped one unnecessary NOP instruction from the ASM in __pte_mkhwwrite()). Retested on x86_64 and sparc64 (sun4u in QEMU). I scanned most architectures to make sure their (pte|pmd)_mkdirty() handling is correct. To be sure, we can run the selftests and find out if other architectures are still affectes (loongarch was fixed recently as well). Based on master for now. I don't expect surprises regarding mm-tress, but I can rebase if there are any problems. [1] https://lkml.kernel.org/r/20221212130213.136267-1-david@redhat.com Cc: Andrew Morton <akpm(a)linux-foundation.org> Cc: "David S. Miller" <davem(a)davemloft.net> Cc: Peter Xu <peterx(a)redhat.com> Cc: Hugh Dickins <hughd(a)google.com> Cc: Shuah Khan <shuah(a)kernel.org> Cc: Sam Ravnborg <sam(a)ravnborg.org> Cc: Yu Zhao <yuzhao(a)google.com> Cc: Anshuman Khandual <anshuman.khandual(a)arm.com> David Hildenbrand (6): selftests/mm: reuse read_pmd_pagesize() in COW selftest selftests/mm: mkdirty: test behavior of (pte|pmd)_mkdirty on VMAs without write permissions sparc/mm: don't unconditionally set HW writable bit when setting PTE dirty on 64bit mm/migrate: revert "mm/migrate: fix wrongly apply write bit after mkdirty on sparc64" mm/huge_memory: revert "Partly revert "mm/thp: carry over dirty bit when thp splits on pmd"" mm/huge_memory: conditionally call maybe_mkwrite() and drop pte_wrprotect() in __split_huge_pmd_locked() arch/sparc/include/asm/pgtable_64.h | 116 +++--- mm/huge_memory.c | 16 +- mm/migrate.c | 2 - tools/testing/selftests/mm/Makefile | 2 + tools/testing/selftests/mm/cow.c | 33 +- tools/testing/selftests/mm/khugepaged.c | 4 + tools/testing/selftests/mm/mkdirty.c | 379 ++++++++++++++++++ tools/testing/selftests/mm/soft-dirty.c | 3 + .../selftests/mm/split_huge_page_test.c | 4 + tools/testing/selftests/mm/vm_util.c | 4 +- 10 files changed, 468 insertions(+), 95 deletions(-) create mode 100644 tools/testing/selftests/mm/mkdirty.c -- 2.39.2

2 years, 6 months

3
9
0 0

[RFC PATCH 0/5] cgroup/cpuset: A new "isolcpus" paritition

by Waiman Long

This patch series introduces a new "isolcpus" partition type to the existing list of {member, root, isolated} types. The primary reason of adding this new "isolcpus" partition is to facilitate the distribution of isolated CPUs down the cgroup v2 hierarchy. The other non-member partition types have the limitation that their parents have to be valid partitions too. It will be hard to create a partition a few layers down the hierarchy. It is relatively rare to have applications that require creation of a separate scheduling domain (root). However, it is more common to have applications that require the use of isolated CPUs (isolated), e.g. DPDK. One can use the "isolcpus" or "nohz_full" boot command options to get that statically. Of course, the "isolated" partition is another way to achieve that dynamically. Modern container orchestration tools like Kubernetes use the cgroup hierarchy to manage different containers. If a container needs to use isolated CPUs, it is hard to get those with existing set of cpuset partition types. With this patch series, a new "isolcpus" partition can be created to hold a set of isolated CPUs that can be pull into other "isolated" partitions. The "isolcpus" partition is special that there can have at most one instance of this in a system. It serves as a pool for isolated CPUs and cannot hold tasks or sub-cpusets underneath it. It is also not cpu-exclusive so that the isolated CPUs can be distributed down the sibling hierarchies, though those isolated CPUs will not be useable until the partition type becomes "isolated". Once isolated CPUs are needed in a cgroup, the administrator can write a list of isolated CPUs into its "cpuset.cpus" and change its partition type to "isolated" to pull in those isolated CPUs from the "isolcpus" partition and use them in that cgroup. That will make the distribution of isolated CPUs to cgroups that need them much easier. In the future, we may be able to extend this special "isolcpus" partition type to support other isolation attributes like those that can be specified with the "isolcpus" boot command line and related options. Waiman Long (5): cgroup/cpuset: Extract out CS_CPU_EXCLUSIVE & CS_SCHED_LOAD_BALANCE handling cgroup/cpuset: Add a new "isolcpus" paritition root state cgroup/cpuset: Make isolated partition pull CPUs from isolcpus partition cgroup/cpuset: Documentation update for the new "isolcpus" partition cgroup/cpuset: Extend test_cpuset_prs.sh to test isolcpus partition Documentation/admin-guide/cgroup-v2.rst | 89 ++- kernel/cgroup/cpuset.c | 548 +++++++++++++++--- .../selftests/cgroup/test_cpuset_prs.sh | 376 ++++++++---- 3 files changed, 789 insertions(+), 224 deletions(-) -- 2.31.1

2 years, 6 months

2
1
0 0

[PATCH v8 0/6] Some improvements of resctrl selftest

by Shaopeng Tan

Hello, The aim of this patch series is to improve the resctrl selftest. Without these fixes, some unnecessary processing will be executed and test results will be confusing. There is no behavior change in test themselves. [patch 1] Make write_schemata() run to set up shemata with 100% allocation on first run in MBM test. [patch 2] The MBA test result message is always output as "ok", make output message to be "not ok" if MBA check result is failed. [patch 3] When a child process is created by fork(), the buffer of the parent process is also copied. Flush the buffer before executing fork(). [patch 4] An error occurs whether in parents process or child process, the parents process always kills child process and runs umount_resctrlfs(), and the child process always waits to be killed by the parent process. [patch 5] If a signal received, to cleanup properly before exiting the parent process, commonize the signal handler registered for CMT/MBM/MBA tests and reuse it in CAT, also unregister the signal handler at the end of each test. [patch 6] Before exiting each test CMT/CAT/MBM/MBA, clear test result files function cat/cmt/mbm/mba_test_cleanup() are called twice. Delete once. This patch series is based on Linux v6.2-rc7. Difference from v7: [patch 4] - Fix commitlog. [patch 5] - Fix commitlog. Pervious versions of this series: [v1] https://lore.kernel.org/lkml/20220914015147.3071025-1-tan.shaopeng@jp.fujit… [v2] https://lore.kernel.org/lkml/20221005013933.1486054-1-tan.shaopeng@jp.fujit… [v3] https://lore.kernel.org/lkml/20221101094341.3383073-1-tan.shaopeng@jp.fujit… [v4] https://lore.kernel.org/lkml/20221117010541.1014481-1-tan.shaopeng@jp.fujit… [v5] https://lore.kernel.org/lkml/20230111075802.3556803-1-tan.shaopeng@jp.fujit… [v6] https://lore.kernel.org/lkml/20230131054655.396270-1-tan.shaopeng@jp.fujits… [v7] https://lore.kernel.org/lkml/20230213062428.1721572-1-tan.shaopeng@jp.fujit… Shaopeng Tan (6): selftests/resctrl: Fix set up schemata with 100% allocation on first run in MBM test selftests/resctrl: Return MBA check result and make it to output message selftests/resctrl: Flush stdout file buffer before executing fork() selftests/resctrl: Cleanup properly when an error occurs in CAT test selftests/resctrl: Commonize the signal handler register/unregister for all tests selftests/resctrl: Remove duplicate codes that clear each test result file tools/testing/selftests/resctrl/cat_test.c | 29 ++++---- tools/testing/selftests/resctrl/cmt_test.c | 7 +- tools/testing/selftests/resctrl/fill_buf.c | 14 ---- tools/testing/selftests/resctrl/mba_test.c | 23 +++---- tools/testing/selftests/resctrl/mbm_test.c | 20 +++--- tools/testing/selftests/resctrl/resctrl.h | 2 + .../testing/selftests/resctrl/resctrl_tests.c | 4 -- tools/testing/selftests/resctrl/resctrl_val.c | 67 ++++++++++++++----- tools/testing/selftests/resctrl/resctrlfs.c | 5 +- 9 files changed, 96 insertions(+), 75 deletions(-) -- 2.27.0

2 years, 6 months

2
9
0 0

Re: [PATCH v6 1/3] mm: add new api to enable ksm per process

by Matthew Wilcox

On Tue, Apr 11, 2023 at 08:16:46PM -0700, Stefan Roesch wrote: > case PR_SET_VMA: > error = prctl_set_vma(arg2, arg3, arg4, arg5); > break; > +#ifdef CONFIG_KSM > + case PR_SET_MEMORY_MERGE: > + if (mmap_write_lock_killable(me->mm)) > + return -EINTR; > + > + if (arg2) { > + int err = ksm_add_mm(me->mm); > + > + if (!err) > + ksm_add_vmas(me->mm); in the last version of this patch, you reported the error. Now you swallow the error. I have no idea which is correct, but you've changed the behaviour without explaining it, so I assume it's wrong. > + } else { > + clear_bit(MMF_VM_MERGE_ANY, &me->mm->flags); > + } > + mmap_write_unlock(me->mm); > + break; > + case PR_GET_MEMORY_MERGE: > + if (arg2 || arg3 || arg4 || arg5) > + return -EINVAL; > + > + error = !!test_bit(MMF_VM_MERGE_ANY, &me->mm->flags); > + break; Why do we need a GET? Just for symmetry, or is there an actual need for it?

2 years, 6 months

2
2
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror