From 54956567a055345d17438f08c895c68aff3f4cf2 Mon Sep 17 00:00:00 2001 From: Nicolas Schier Date: Thu, 12 Dec 2024 14:05:29 +0100 Subject: [PATCH 01/16] kbuild: deb-pkg: Do not install maint scripts for arch 'um' Stop installing Debian maintainer scripts when building a user-mode-linux Debian package. Debian maintainer scripts are used for e.g. requesting rebuilds of initrd, rebuilding DKMS modules and updating of grub configuration. As all of this is not relevant for UML but also may lead to failures while processing the kernel hooks, do no more install maintainer scripts for the UML package. Suggested-by: Masahiro Yamada Signed-off-by: Nicolas Schier Signed-off-by: Masahiro Yamada --- scripts/package/builddeb | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/scripts/package/builddeb b/scripts/package/builddeb index fb686fd3266f..ad7aba0f268e 100755 --- a/scripts/package/builddeb +++ b/scripts/package/builddeb @@ -63,6 +63,12 @@ install_linux_image () { esac cp "$(${MAKE} -s -f ${srctree}/Makefile image_name)" "${pdir}/${installed_image_path}" + if [ "${ARCH}" != um ]; then + install_maint_scripts "${pdir}" + fi +} + +install_maint_scripts () { # Install the maintainer scripts # Note: hook scripts under /etc/kernel are also executed by official Debian # kernel packages, as well as kernel packages built using make-kpkg. -- 2.51.0 From 9435dc77a33fa20afec7cd35ceaae5f7f42dbbe2 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 13 Dec 2024 00:46:15 +0900 Subject: [PATCH 02/16] modpost: distinguish same module paths from different dump files Since commit 13b25489b6f8 ("kbuild: change working directory to external module directory with M="), module paths are always relative to the top of the external module tree. The module paths recorded in Module.symvers are no longer globally unique when they are passed via KBUILD_EXTRA_SYMBOLS for building other external modules, which may result in false-positive "exported twice" errors. Such errors should not occur because external modules should be able to override in-tree modules. To address this, record the dump file path in struct module and check it when searching for a module. Fixes: 13b25489b6f8 ("kbuild: change working directory to external module directory with M=") Reported-by: Jon Hunter Closes: https://lore.kernel.org/all/eb21a546-a19c-40df-b821-bbba80f19a3d@nvidia.com/ Signed-off-by: Masahiro Yamada Tested-by: Jon Hunter --- scripts/mod/modpost.c | 17 +++++++++-------- scripts/mod/modpost.h | 3 ++- 2 files changed, 11 insertions(+), 9 deletions(-) diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index fb787a5715f5..94ee49207a45 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -155,12 +155,13 @@ char *get_line(char **stringp) /* A list of all modules we processed */ LIST_HEAD(modules); -static struct module *find_module(const char *modname) +static struct module *find_module(const char *filename, const char *modname) { struct module *mod; list_for_each_entry(mod, &modules, list) { - if (strcmp(mod->name, modname) == 0) + if (!strcmp(mod->dump_file, filename) && + !strcmp(mod->name, modname)) return mod; } return NULL; @@ -2030,10 +2031,10 @@ static void read_dump(const char *fname) continue; } - mod = find_module(modname); + mod = find_module(fname, modname); if (!mod) { mod = new_module(modname, strlen(modname)); - mod->from_dump = true; + mod->dump_file = fname; } s = sym_add_exported(symname, mod, gpl_only, namespace); sym_set_crc(s, crc); @@ -2052,7 +2053,7 @@ static void write_dump(const char *fname) struct symbol *sym; list_for_each_entry(mod, &modules, list) { - if (mod->from_dump) + if (mod->dump_file) continue; list_for_each_entry(sym, &mod->exported_symbols, list) { if (trim_unused_exports && !sym->used) @@ -2076,7 +2077,7 @@ static void write_namespace_deps_files(const char *fname) list_for_each_entry(mod, &modules, list) { - if (mod->from_dump || list_empty(&mod->missing_namespaces)) + if (mod->dump_file || list_empty(&mod->missing_namespaces)) continue; buf_printf(&ns_deps_buf, "%s.ko:", mod->name); @@ -2194,7 +2195,7 @@ int main(int argc, char **argv) read_symbols_from_files(files_source); list_for_each_entry(mod, &modules, list) { - if (mod->from_dump || mod->is_vmlinux) + if (mod->dump_file || mod->is_vmlinux) continue; check_modname_len(mod); @@ -2205,7 +2206,7 @@ int main(int argc, char **argv) handle_white_list_exports(unused_exports_white_list); list_for_each_entry(mod, &modules, list) { - if (mod->from_dump) + if (mod->dump_file) continue; if (mod->is_vmlinux) diff --git a/scripts/mod/modpost.h b/scripts/mod/modpost.h index 49848fcbe2a1..8b72c227ebf4 100644 --- a/scripts/mod/modpost.h +++ b/scripts/mod/modpost.h @@ -95,14 +95,15 @@ struct module_alias { /** * struct module - represent a module (vmlinux or *.ko) * + * @dump_file: path to the .symvers file if loaded from a file * @aliases: list head for module_aliases */ struct module { struct list_head list; struct list_head exported_symbols; struct list_head unresolved_symbols; + const char *dump_file; bool is_gpl_compatible; - bool from_dump; /* true if module was loaded from *.symvers */ bool is_vmlinux; bool seen; bool has_init; -- 2.51.0 From e84a3bf7f4aa669c05e3884497774148ac111468 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 17 Dec 2024 10:19:04 -0500 Subject: [PATCH 03/16] staging: gpib: Fix allyesconfig build failures My tests run an allyesconfig build and it failed with the following errors: LD [M] samples/kfifo/dma-example.ko ld.lld: error: undefined symbol: nec7210_board_reset ld.lld: error: undefined symbol: nec7210_read ld.lld: error: undefined symbol: nec7210_write It appears that some modules call the function nec7210_board_reset() that is defined in nec7210.c. In an allyesconfig build, these other modules are built in. But the file that holds nec7210_board_reset() has: obj-m += nec7210.o Where that "-m" means it only gets built as a module. With the other modules built in, they have no access to nec7210_board_reset() and the build fails. This isn't the only function. After fixing that one, I hit another: ld.lld: error: undefined symbol: push_gpib_event ld.lld: error: undefined symbol: gpib_match_device_path Where push_gpib_event() was also used outside of the file it was defined in, and that file too only was built as a module. Since the directory that nec7210.c is only traversed when CONFIG_GPIB_NEC7210 is set, and the directory with gpib_common.c is only traversed when CONFIG_GPIB_COMMON is set, use those configs as the option to build those modules. When it is an allyesconfig, then they will both be built in and their functions will be available to the other modules that are also built in. Fixes: 3ba84ac69b53e ("staging: gpib: Add nec7210 GPIB chip driver") Fixes: 9dde4559e9395 ("staging: gpib: Add GPIB common core driver") Signed-off-by: Steven Rostedt (Google) Reviewed-by: Palmer Dabbelt Signed-off-by: Linus Torvalds --- drivers/staging/gpib/common/Makefile | 2 +- drivers/staging/gpib/nec7210/Makefile | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/staging/gpib/common/Makefile b/drivers/staging/gpib/common/Makefile index 0c4c77bea75b..460586edb574 100644 --- a/drivers/staging/gpib/common/Makefile +++ b/drivers/staging/gpib/common/Makefile @@ -1,5 +1,5 @@ -obj-m += gpib_common.o +obj-$(CONFIG_GPIB_COMMON) += gpib_common.o gpib_common-objs := gpib_os.o iblib.o diff --git a/drivers/staging/gpib/nec7210/Makefile b/drivers/staging/gpib/nec7210/Makefile index 8d4d90f21109..64330f2e89d1 100644 --- a/drivers/staging/gpib/nec7210/Makefile +++ b/drivers/staging/gpib/nec7210/Makefile @@ -1,4 +1,4 @@ -obj-m += nec7210.o +obj-$(CONFIG_GPIB_NEC7210) += nec7210.o -- 2.51.0 From 37d1d99b8806b24ffe4a2b453620df932994a5c0 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Tue, 17 Dec 2024 08:05:40 +0100 Subject: [PATCH 04/16] KVM: VMX: don't include '' directly The header clearly states that it does not want to be included directly, only via ''. Replace the include accordingly. Signed-off-by: Wolfram Sang Message-ID: <20241217070539.2433-2-wsa+renesas@sang-engineering.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/posted_intr.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/vmx/posted_intr.h b/arch/x86/kvm/vmx/posted_intr.h index 1715d2ab07be..ad9116a99bcc 100644 --- a/arch/x86/kvm/vmx/posted_intr.h +++ b/arch/x86/kvm/vmx/posted_intr.h @@ -2,7 +2,7 @@ #ifndef __KVM_X86_VMX_POSTED_INTR_H #define __KVM_X86_VMX_POSTED_INTR_H -#include +#include #include void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu); -- 2.51.0 From 398b7b6cb9e046f137a188670da12f790492b56b Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 19 Dec 2024 07:43:20 -0500 Subject: [PATCH 05/16] KVM: x86: let it be known that ignore_msrs is a bad idea When running KVM with ignore_msrs=1 and report_ignored_msrs=0, the user has no clue that that the guest is being lied to. This may cause bug reports such as https://gitlab.com/qemu-project/qemu/-/issues/2571, where enabling a CPUID bit in QEMU caused Linux guests to try reading MSR_CU_DEF_ERR; and being lied about the existence of MSR_CU_DEF_ERR caused the guest to assume other things about the local APIC which were not true: Sep 14 12:02:53 kernel: mce: [Firmware Bug]: Your BIOS is not setting up LVT offset 0x2 for deferred error IRQs correctly. Sep 14 12:02:53 kernel: unchecked MSR access error: RDMSR from 0x852 at rIP: 0xffffffffb548ffa7 (native_read_msr+0x7/0x40) Sep 14 12:02:53 kernel: Call Trace: ... Sep 14 12:02:53 kernel: native_apic_msr_read+0x20/0x30 Sep 14 12:02:53 kernel: setup_APIC_eilvt+0x47/0x110 Sep 14 12:02:53 kernel: mce_amd_feature_init+0x485/0x4e0 ... Sep 14 12:02:53 kernel: [Firmware Bug]: cpu 0, try to use APIC520 (LVT offset 2) for vector 0xf4, but the register is already in use for vector 0x0 on this cpu Without reported_ignored_msrs=0 at least the host kernel log will contain enough information to avoid going on a wild goose chase. But if reports about individual MSR accesses are being silenced too, at least complain loudly the first time a VM is started. Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c8160baf3838..12fa68a06966 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -12724,6 +12724,13 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm_hv_init_vm(kvm); kvm_xen_init_vm(kvm); + if (ignore_msrs && !report_ignored_msrs) { + pr_warn_once("Running KVM with ignore_msrs=1 and report_ignored_msrs=0 is not a\n" + "a supported configuration. Lying to the guest about the existence of MSRs\n" + "may cause the guest operating system to hang or produce errors. If a guest\n" + "does not run without ignore_msrs=1, please report it to kvm@vger.kernel.org.\n"); + } + return 0; out_uninit_mmu: -- 2.51.0 From 4bbf9020becbfd8fc2c3da790855b7042fad455b Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 22 Dec 2024 13:22:21 -0800 Subject: [PATCH 06/16] Linux 6.13-rc4 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index e5b8a8832c0c..5c9b1d2d59b4 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 13 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc4 NAME = Baby Opossum Posse # *DOCUMENTATION* -- 2.51.0 From 8ec396d05d1b737c87311fb7311f753b02c2a6b1 Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Thu, 28 Nov 2024 15:06:17 +0000 Subject: [PATCH 07/16] mm: reinstate ability to map write-sealed memfd mappings read-only Patch series "mm: reinstate ability to map write-sealed memfd mappings read-only". In commit 158978945f31 ("mm: perform the mapping_map_writable() check after call_mmap()") (and preceding changes in the same series) it became possible to mmap() F_SEAL_WRITE sealed memfd mappings read-only. Commit 5de195060b2e ("mm: resolve faulty mmap_region() error path behaviour") unintentionally undid this logic by moving the mapping_map_writable() check before the shmem_mmap() hook is invoked, thereby regressing this change. This series reworks how we both permit write-sealed mappings being mapped read-only and disallow mprotect() from undoing the write-seal, fixing this regression. We also add a regression test to ensure that we do not accidentally regress this in future. Thanks to Julian Orth for reporting this regression. This patch (of 2): In commit 158978945f31 ("mm: perform the mapping_map_writable() check after call_mmap()") (and preceding changes in the same series) it became possible to mmap() F_SEAL_WRITE sealed memfd mappings read-only. This was previously unnecessarily disallowed, despite the man page documentation indicating that it would be, thereby limiting the usefulness of F_SEAL_WRITE logic. We fixed this by adapting logic that existed for the F_SEAL_FUTURE_WRITE seal (one which disallows future writes to the memfd) to also be used for F_SEAL_WRITE. For background - the F_SEAL_FUTURE_WRITE seal clears VM_MAYWRITE for a read-only mapping to disallow mprotect() from overriding the seal - an operation performed by seal_check_write(), invoked from shmem_mmap(), the f_op->mmap() hook used by shmem mappings. By extending this to F_SEAL_WRITE and critically - checking mapping_map_writable() to determine if we may map the memfd AFTER we invoke shmem_mmap() - the desired logic becomes possible. This is because mapping_map_writable() explicitly checks for VM_MAYWRITE, which we will have cleared. Commit 5de195060b2e ("mm: resolve faulty mmap_region() error path behaviour") unintentionally undid this logic by moving the mapping_map_writable() check before the shmem_mmap() hook is invoked, thereby regressing this change. We reinstate this functionality by moving the check out of shmem_mmap() and instead performing it in do_mmap() at the point at which VMA flags are being determined, which seems in any case to be a more appropriate place in which to make this determination. In order to achieve this we rework memfd seal logic to allow us access to this information using existing logic and eliminate the clearing of VM_MAYWRITE from seal_check_write() which we are performing in do_mmap() instead. Link: https://lkml.kernel.org/r/99fc35d2c62bd2e05571cf60d9f8b843c56069e0.1732804776.git.lorenzo.stoakes@oracle.com Fixes: 5de195060b2e ("mm: resolve faulty mmap_region() error path behaviour") Signed-off-by: Lorenzo Stoakes Reported-by: Julian Orth Closes: https://lore.kernel.org/all/CAHijbEUMhvJTN9Xw1GmbM266FXXv=U7s4L_Jem5x3AaPZxrYpQ@mail.gmail.com/ Cc: Jann Horn Cc: Liam R. Howlett Cc: Linus Torvalds Cc: Shuah Khan Cc: Vlastimil Babka Cc: Signed-off-by: Andrew Morton --- include/linux/memfd.h | 14 +++++++++++ include/linux/mm.h | 58 +++++++++++++++++++++++++++++-------------- mm/memfd.c | 2 +- mm/mmap.c | 4 +++ 4 files changed, 59 insertions(+), 19 deletions(-) diff --git a/include/linux/memfd.h b/include/linux/memfd.h index 3f2cf339ceaf..d437e3070850 100644 --- a/include/linux/memfd.h +++ b/include/linux/memfd.h @@ -7,6 +7,7 @@ #ifdef CONFIG_MEMFD_CREATE extern long memfd_fcntl(struct file *file, unsigned int cmd, unsigned int arg); struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx); +unsigned int *memfd_file_seals_ptr(struct file *file); #else static inline long memfd_fcntl(struct file *f, unsigned int c, unsigned int a) { @@ -16,6 +17,19 @@ static inline struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx) { return ERR_PTR(-EINVAL); } + +static inline unsigned int *memfd_file_seals_ptr(struct file *file) +{ + return NULL; +} #endif +/* Retrieve memfd seals associated with the file, if any. */ +static inline unsigned int memfd_file_seals(struct file *file) +{ + unsigned int *sealsp = memfd_file_seals_ptr(file); + + return sealsp ? *sealsp : 0; +} + #endif /* __LINUX_MEMFD_H */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 338a76ce9083..fb397918c43d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -4101,6 +4101,37 @@ void mem_dump_obj(void *object); static inline void mem_dump_obj(void *object) {} #endif +static inline bool is_write_sealed(int seals) +{ + return seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE); +} + +/** + * is_readonly_sealed - Checks whether write-sealed but mapped read-only, + * in which case writes should be disallowing moving + * forwards. + * @seals: the seals to check + * @vm_flags: the VMA flags to check + * + * Returns whether readonly sealed, in which case writess should be disallowed + * going forward. + */ +static inline bool is_readonly_sealed(int seals, vm_flags_t vm_flags) +{ + /* + * Since an F_SEAL_[FUTURE_]WRITE sealed memfd can be mapped as + * MAP_SHARED and read-only, take care to not allow mprotect to + * revert protections on such mappings. Do this only for shared + * mappings. For private mappings, don't need to mask + * VM_MAYWRITE as we still want them to be COW-writable. + */ + if (is_write_sealed(seals) && + ((vm_flags & (VM_SHARED | VM_WRITE)) == VM_SHARED)) + return true; + + return false; +} + /** * seal_check_write - Check for F_SEAL_WRITE or F_SEAL_FUTURE_WRITE flags and * handle them. @@ -4112,24 +4143,15 @@ static inline void mem_dump_obj(void *object) {} */ static inline int seal_check_write(int seals, struct vm_area_struct *vma) { - if (seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) { - /* - * New PROT_WRITE and MAP_SHARED mmaps are not allowed when - * write seals are active. - */ - if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE)) - return -EPERM; - - /* - * Since an F_SEAL_[FUTURE_]WRITE sealed memfd can be mapped as - * MAP_SHARED and read-only, take care to not allow mprotect to - * revert protections on such mappings. Do this only for shared - * mappings. For private mappings, don't need to mask - * VM_MAYWRITE as we still want them to be COW-writable. - */ - if (vma->vm_flags & VM_SHARED) - vm_flags_clear(vma, VM_MAYWRITE); - } + if (!is_write_sealed(seals)) + return 0; + + /* + * New PROT_WRITE and MAP_SHARED mmaps are not allowed when + * write seals are active. + */ + if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE)) + return -EPERM; return 0; } diff --git a/mm/memfd.c b/mm/memfd.c index c17c3ea701a1..35a370d75c9a 100644 --- a/mm/memfd.c +++ b/mm/memfd.c @@ -170,7 +170,7 @@ static int memfd_wait_for_pins(struct address_space *mapping) return error; } -static unsigned int *memfd_file_seals_ptr(struct file *file) +unsigned int *memfd_file_seals_ptr(struct file *file) { if (shmem_file(file)) return &SHMEM_I(file_inode(file))->seals; diff --git a/mm/mmap.c b/mm/mmap.c index d32b7e701058..16f8e8be01f8 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -47,6 +47,7 @@ #include #include #include +#include #include #include @@ -368,6 +369,7 @@ unsigned long do_mmap(struct file *file, unsigned long addr, if (file) { struct inode *inode = file_inode(file); + unsigned int seals = memfd_file_seals(file); unsigned long flags_mask; if (!file_mmap_ok(file, inode, pgoff, len)) @@ -408,6 +410,8 @@ unsigned long do_mmap(struct file *file, unsigned long addr, vm_flags |= VM_SHARED | VM_MAYSHARE; if (!(file->f_mode & FMODE_WRITE)) vm_flags &= ~(VM_MAYWRITE | VM_SHARED); + else if (is_readonly_sealed(seals, vm_flags)) + vm_flags &= ~VM_MAYWRITE; fallthrough; case MAP_PRIVATE: if (!(file->f_mode & FMODE_READ)) -- 2.51.0 From ea0916e01d0b0f2cce1369ac1494239a79827270 Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Thu, 28 Nov 2024 15:06:18 +0000 Subject: [PATCH 08/16] selftests/memfd: add test for mapping write-sealed memfd read-only Now we have reinstated the ability to map F_SEAL_WRITE mappings read-only, assert that we are able to do this in a test to ensure that we do not regress this again. Link: https://lkml.kernel.org/r/a6377ec470b14c0539b4600cf8fa24bf2e4858ae.1732804776.git.lorenzo.stoakes@oracle.com Signed-off-by: Lorenzo Stoakes Cc: Jann Horn Cc: Julian Orth Cc: Liam R. Howlett Cc: Linus Torvalds Cc: Shuah Khan Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- tools/testing/selftests/memfd/memfd_test.c | 43 ++++++++++++++++++++++ 1 file changed, 43 insertions(+) diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c index 0a0b55516028..c0c53451a16d 100644 --- a/tools/testing/selftests/memfd/memfd_test.c +++ b/tools/testing/selftests/memfd/memfd_test.c @@ -282,6 +282,24 @@ static void *mfd_assert_mmap_shared(int fd) return p; } +static void *mfd_assert_mmap_read_shared(int fd) +{ + void *p; + + p = mmap(NULL, + mfd_def_size, + PROT_READ, + MAP_SHARED, + fd, + 0); + if (p == MAP_FAILED) { + printf("mmap() failed: %m\n"); + abort(); + } + + return p; +} + static void *mfd_assert_mmap_private(int fd) { void *p; @@ -980,6 +998,30 @@ static void test_seal_future_write(void) close(fd); } +static void test_seal_write_map_read_shared(void) +{ + int fd; + void *p; + + printf("%s SEAL-WRITE-MAP-READ\n", memfd_str); + + fd = mfd_assert_new("kern_memfd_seal_write_map_read", + mfd_def_size, + MFD_CLOEXEC | MFD_ALLOW_SEALING); + + mfd_assert_add_seals(fd, F_SEAL_WRITE); + mfd_assert_has_seals(fd, F_SEAL_WRITE); + + p = mfd_assert_mmap_read_shared(fd); + + mfd_assert_read(fd); + mfd_assert_read_shared(fd); + mfd_fail_write(fd); + + munmap(p, mfd_def_size); + close(fd); +} + /* * Test SEAL_SHRINK * Test whether SEAL_SHRINK actually prevents shrinking @@ -1593,6 +1635,7 @@ int main(int argc, char **argv) test_seal_write(); test_seal_future_write(); + test_seal_write_map_read_shared(); test_seal_shrink(); test_seal_grow(); test_seal_resize(); -- 2.51.0 From 6aaced5abd32e2a57cd94fd64f824514d0361da8 Mon Sep 17 00:00:00 2001 From: Seiji Nishikawa Date: Sun, 1 Dec 2024 01:12:34 +0900 Subject: [PATCH 09/16] mm: vmscan: account for free pages to prevent infinite Loop in throttle_direct_reclaim() The task sometimes continues looping in throttle_direct_reclaim() because allow_direct_reclaim(pgdat) keeps returning false. #0 [ffff80002cb6f8d0] __switch_to at ffff8000080095ac #1 [ffff80002cb6f900] __schedule at ffff800008abbd1c #2 [ffff80002cb6f990] schedule at ffff800008abc50c #3 [ffff80002cb6f9b0] throttle_direct_reclaim at ffff800008273550 #4 [ffff80002cb6fa20] try_to_free_pages at ffff800008277b68 #5 [ffff80002cb6fae0] __alloc_pages_nodemask at ffff8000082c4660 #6 [ffff80002cb6fc50] alloc_pages_vma at ffff8000082e4a98 #7 [ffff80002cb6fca0] do_anonymous_page at ffff80000829f5a8 #8 [ffff80002cb6fce0] __handle_mm_fault at ffff8000082a5974 #9 [ffff80002cb6fd90] handle_mm_fault at ffff8000082a5bd4 At this point, the pgdat contains the following two zones: NODE: 4 ZONE: 0 ADDR: ffff00817fffe540 NAME: "DMA32" SIZE: 20480 MIN/LOW/HIGH: 11/28/45 VM_STAT: NR_FREE_PAGES: 359 NR_ZONE_INACTIVE_ANON: 18813 NR_ZONE_ACTIVE_ANON: 0 NR_ZONE_INACTIVE_FILE: 50 NR_ZONE_ACTIVE_FILE: 0 NR_ZONE_UNEVICTABLE: 0 NR_ZONE_WRITE_PENDING: 0 NR_MLOCK: 0 NR_BOUNCE: 0 NR_ZSPAGES: 0 NR_FREE_CMA_PAGES: 0 NODE: 4 ZONE: 1 ADDR: ffff00817fffec00 NAME: "Normal" SIZE: 8454144 PRESENT: 98304 MIN/LOW/HIGH: 68/166/264 VM_STAT: NR_FREE_PAGES: 146 NR_ZONE_INACTIVE_ANON: 94668 NR_ZONE_ACTIVE_ANON: 3 NR_ZONE_INACTIVE_FILE: 735 NR_ZONE_ACTIVE_FILE: 78 NR_ZONE_UNEVICTABLE: 0 NR_ZONE_WRITE_PENDING: 0 NR_MLOCK: 0 NR_BOUNCE: 0 NR_ZSPAGES: 0 NR_FREE_CMA_PAGES: 0 In allow_direct_reclaim(), while processing ZONE_DMA32, the sum of inactive/active file-backed pages calculated in zone_reclaimable_pages() based on the result of zone_page_state_snapshot() is zero. Additionally, since this system lacks swap, the calculation of inactive/ active anonymous pages is skipped. crash> p nr_swap_pages nr_swap_pages = $1937 = { counter = 0 } As a result, ZONE_DMA32 is deemed unreclaimable and skipped, moving on to the processing of the next zone, ZONE_NORMAL, despite ZONE_DMA32 having free pages significantly exceeding the high watermark. The problem is that the pgdat->kswapd_failures hasn't been incremented. crash> px ((struct pglist_data *) 0xffff00817fffe540)->kswapd_failures $1935 = 0x0 This is because the node deemed balanced. The node balancing logic in balance_pgdat() evaluates all zones collectively. If one or more zones (e.g., ZONE_DMA32) have enough free pages to meet their watermarks, the entire node is deemed balanced. This causes balance_pgdat() to exit early before incrementing the kswapd_failures, as it considers the overall memory state acceptable, even though some zones (like ZONE_NORMAL) remain under significant pressure. The patch ensures that zone_reclaimable_pages() includes free pages (NR_FREE_PAGES) in its calculation when no other reclaimable pages are available (e.g., file-backed or anonymous pages). This change prevents zones like ZONE_DMA32, which have sufficient free pages, from being mistakenly deemed unreclaimable. By doing so, the patch ensures proper node balancing, avoids masking pressure on other zones like ZONE_NORMAL, and prevents infinite loops in throttle_direct_reclaim() caused by allow_direct_reclaim(pgdat) repeatedly returning false. The kernel hangs due to a task stuck in throttle_direct_reclaim(), caused by a node being incorrectly deemed balanced despite pressure in certain zones, such as ZONE_NORMAL. This issue arises from zone_reclaimable_pages() returning 0 for zones without reclaimable file- backed or anonymous pages, causing zones like ZONE_DMA32 with sufficient free pages to be skipped. The lack of swap or reclaimable pages results in ZONE_DMA32 being ignored during reclaim, masking pressure in other zones. Consequently, pgdat->kswapd_failures remains 0 in balance_pgdat(), preventing fallback mechanisms in allow_direct_reclaim() from being triggered, leading to an infinite loop in throttle_direct_reclaim(). This patch modifies zone_reclaimable_pages() to account for free pages (NR_FREE_PAGES) when no other reclaimable pages exist. This ensures zones with sufficient free pages are not skipped, enabling proper balancing and reclaim behavior. [akpm@linux-foundation.org: coding-style cleanups] Link: https://lkml.kernel.org/r/20241130164346.436469-1-snishika@redhat.com Link: https://lkml.kernel.org/r/20241130161236.433747-2-snishika@redhat.com Fixes: 5a1c84b404a7 ("mm: remove reclaim and compaction retry approximations") Signed-off-by: Seiji Nishikawa Cc: Mel Gorman Cc: Signed-off-by: Andrew Morton --- mm/vmscan.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/mm/vmscan.c b/mm/vmscan.c index 76378bc257e3..9a859b7d18d7 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -374,7 +374,14 @@ unsigned long zone_reclaimable_pages(struct zone *zone) if (can_reclaim_anon_pages(NULL, zone_to_nid(zone), NULL)) nr += zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_ANON) + zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_ANON); - + /* + * If there are no reclaimable file-backed or anonymous pages, + * ensure zones with sufficient free pages are not skipped. + * This prevents zones like DMA32 from being ignored in reclaim + * scenarios where they can still help alleviate memory pressure. + */ + if (nr == 0) + nr = zone_page_state_snapshot(zone, NR_FREE_PAGES); return nr; } -- 2.51.0 From 34d7cf637c437d5c2a8a6ef23ea45193bad8a91c Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Fri, 6 Dec 2024 15:03:45 +0800 Subject: [PATCH 10/16] mm: don't try THP alignment for FS without get_unmapped_area Commit ed48e87c7df3 ("thp: add thp_get_unmapped_area_vmflags()") changes thp_get_unmapped_area() to thp_get_unmapped_area_vmflags() in __get_unmapped_area(), which doesn't initialize local get_area for anonymous mappings. This leads to us always trying THP alignment even for file_operations which have a NULL ->get_unmapped_area() callback. Since commit efa7df3e3bb5 ("mm: align larger anonymous mappings on THP boundaries") we only want to enable THP alignment for anonymous mappings, so add a !file check to avoid attempting THP alignment for file mappings. Found issue by code inspection. THP alignment is used for easy or more pmd mappings, from vma side. This may cause unnecessary VMA fragmentation and potentially worse performance on filesystems that do not actually support THPs and thus cannot benefit from the alignment. Link: https://lkml.kernel.org/r/20241206070345.2526501-1-wangkefeng.wang@huawei.com Fixes: ed48e87c7df3 ("thp: add thp_get_unmapped_area_vmflags()") Signed-off-by: Kefeng Wang Reviewed-by: Vlastimil Babka Reviewed-by: Yang Shi Cc: Christophe Leroy Cc: David Hildenbrand Cc: Jann Horn Cc: Liam R. Howlett Cc: Lorenzo Stoakes Cc: Rick Edgecombe Cc: Ryan Roberts Signed-off-by: Andrew Morton --- mm/mmap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/mmap.c b/mm/mmap.c index 16f8e8be01f8..aec208f90337 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -892,7 +892,7 @@ __get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, if (get_area) { addr = get_area(file, addr, len, pgoff, flags); - } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) + } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && !file && !addr /* no hint */ && IS_ALIGNED(len, PMD_SIZE)) { /* Ensures that larger anonymous mappings are THP aligned. */ -- 2.51.0 From 158cdce87c8c172787063998ad5dd3e2f658b963 Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Fri, 6 Dec 2024 16:30:25 +0800 Subject: [PATCH 11/16] mm/readahead: fix large folio support in async readahead When testing large folio support with XFS on our servers, we observed that only a few large folios are mapped when reading large files via mmap. After a thorough analysis, I identified it was caused by the `/sys/block/*/queue/read_ahead_kb` setting. On our test servers, this parameter is set to 128KB. After I tune it to 2MB, the large folio can work as expected. However, I believe the large folio behavior should not be dependent on the value of read_ahead_kb. It would be more robust if the kernel can automatically adopt to it. With /sys/block/*/queue/read_ahead_kb set to 128KB and performing a sequential read on a 1GB file using MADV_HUGEPAGE, the differences in /proc/meminfo are as follows: - before this patch FileHugePages: 18432 kB FilePmdMapped: 4096 kB - after this patch FileHugePages: 1067008 kB FilePmdMapped: 1048576 kB This shows that after applying the patch, the entire 1GB file is mapped to huge pages. The stable list is CCed, as without this patch, large folios don't function optimally in the readahead path. It's worth noting that if read_ahead_kb is set to a larger value that isn't aligned with huge page sizes (e.g., 4MB + 128KB), it may still fail to map to hugepages. Link: https://lkml.kernel.org/r/20241108141710.9721-1-laoar.shao@gmail.com Link: https://lkml.kernel.org/r/20241206083025.3478-1-laoar.shao@gmail.com Fixes: 4687fdbb805a ("mm/filemap: Support VM_HUGEPAGE for file mappings") Signed-off-by: Yafang Shao Tested-by: kernel test robot Cc: Matthew Wilcox Cc: David Hildenbrand Cc: Signed-off-by: Andrew Morton --- mm/readahead.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/mm/readahead.c b/mm/readahead.c index ea650b8b02fb..e151f4b13ca4 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -646,7 +646,11 @@ void page_cache_async_ra(struct readahead_control *ractl, 1UL << order); if (index == expected) { ra->start += ra->size; - ra->size = get_next_ra_size(ra, max_pages); + /* + * In the case of MADV_HUGEPAGE, the actual size might exceed + * the readahead window. + */ + ra->size = max(ra->size, get_next_ra_size(ra, max_pages)); ra->async_size = ra->size; goto readit; } -- 2.51.0 From 1fd8bc7cd889bd73d07a83cb32d674ac68f99153 Mon Sep 17 00:00:00 2001 From: Yang Erkun Date: Sat, 14 Dec 2024 17:30:05 +0800 Subject: [PATCH 12/16] maple_tree: reload mas before the second call for mas_empty_area Change the LONG_MAX in simple_offset_add to 1024, and do latter: [root@fedora ~]# mkdir /tmp/dir [root@fedora ~]# for i in {1..1024}; do touch /tmp/dir/$i; done touch: cannot touch '/tmp/dir/1024': Device or resource busy [root@fedora ~]# rm /tmp/dir/123 [root@fedora ~]# touch /tmp/dir/1024 [root@fedora ~]# rm /tmp/dir/100 [root@fedora ~]# touch /tmp/dir/1025 touch: cannot touch '/tmp/dir/1025': Device or resource busy After we delete file 100, actually this is a empty entry, but the latter create failed unexpected. mas_alloc_cyclic has two chance to find empty entry. First find the entry with range range_lo and range_hi, if no empty entry exist, and range_lo > min, retry find with range min and range_hi. However, the first call mas_empty_area may mark mas as EBUSY, and the second call for mas_empty_area will return false directly. Fix this by reload mas before second call for mas_empty_area. [Liam.Howlett@Oracle.com: fix mas_alloc_cyclic() second search] Link: https://lore.kernel.org/all/20241216060600.287B4C4CED0@smtp.kernel.org/ Link: https://lkml.kernel.org/r/20241216190113.1226145-2-Liam.Howlett@oracle.com Link: https://lkml.kernel.org/r/20241214093005.72284-1-yangerkun@huaweicloud.com Fixes: 9b6713cc7522 ("maple_tree: Add mtree_alloc_cyclic()") Signed-off-by: Yang Erkun Signed-off-by: Liam R. Howlett Cc: Christian Brauner Cc: Chuck Lever says: Cc: Liam R. Howlett Cc: Signed-off-by: Andrew Morton --- lib/maple_tree.c | 1 + 1 file changed, 1 insertion(+) diff --git a/lib/maple_tree.c b/lib/maple_tree.c index d0ae808f3a14..047397136f15 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -4354,6 +4354,7 @@ int mas_alloc_cyclic(struct ma_state *mas, unsigned long *startp, ret = 1; } if (ret < 0 && range_lo > min) { + mas_reset(mas); ret = mas_empty_area(mas, min, range_hi, 1); if (ret == 0) ret = 1; -- 2.51.0 From 59d9094df3d79443937add8700b2ef1a866b1081 Mon Sep 17 00:00:00 2001 From: Liu Shixin Date: Mon, 16 Dec 2024 15:11:47 +0800 Subject: [PATCH 13/16] mm: hugetlb: independent PMD page table shared count The folio refcount may be increased unexpectly through try_get_folio() by caller such as split_huge_pages. In huge_pmd_unshare(), we use refcount to check whether a pmd page table is shared. The check is incorrect if the refcount is increased by the above caller, and this can cause the page table leaked: BUG: Bad page state in process sh pfn:109324 page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x66 pfn:0x109324 flags: 0x17ffff800000000(node=0|zone=2|lastcpupid=0xfffff) page_type: f2(table) raw: 017ffff800000000 0000000000000000 0000000000000000 0000000000000000 raw: 0000000000000066 0000000000000000 00000000f2000000 0000000000000000 page dumped because: nonzero mapcount ... CPU: 31 UID: 0 PID: 7515 Comm: sh Kdump: loaded Tainted: G B 6.13.0-rc2master+ #7 Tainted: [B]=BAD_PAGE Hardware name: QEMU KVM Virtual Machine, BIOS 0.0.0 02/06/2015 Call trace: show_stack+0x20/0x38 (C) dump_stack_lvl+0x80/0xf8 dump_stack+0x18/0x28 bad_page+0x8c/0x130 free_page_is_bad_report+0xa4/0xb0 free_unref_page+0x3cc/0x620 __folio_put+0xf4/0x158 split_huge_pages_all+0x1e0/0x3e8 split_huge_pages_write+0x25c/0x2d8 full_proxy_write+0x64/0xd8 vfs_write+0xcc/0x280 ksys_write+0x70/0x110 __arm64_sys_write+0x24/0x38 invoke_syscall+0x50/0x120 el0_svc_common.constprop.0+0xc8/0xf0 do_el0_svc+0x24/0x38 el0_svc+0x34/0x128 el0t_64_sync_handler+0xc8/0xd0 el0t_64_sync+0x190/0x198 The issue may be triggered by damon, offline_page, page_idle, etc, which will increase the refcount of page table. 1. The page table itself will be discarded after reporting the "nonzero mapcount". 2. The HugeTLB page mapped by the page table miss freeing since we treat the page table as shared and a shared page table will not be unmapped. Fix it by introducing independent PMD page table shared count. As described by comment, pt_index/pt_mm/pt_frag_refcount are used for s390 gmap, x86 pgds and powerpc, pt_share_count is used for x86/arm64/riscv pmds, so we can reuse the field as pt_share_count. Link: https://lkml.kernel.org/r/20241216071147.3984217-1-liushixin2@huawei.com Fixes: 39dde65c9940 ("[PATCH] shared page table for hugetlb page") Signed-off-by: Liu Shixin Cc: Kefeng Wang Cc: Ken Chen Cc: Muchun Song Cc: Nanyong Sun Cc: Jane Chu Cc: Signed-off-by: Andrew Morton --- include/linux/mm.h | 1 + include/linux/mm_types.h | 30 ++++++++++++++++++++++++++++++ mm/hugetlb.c | 16 +++++++--------- 3 files changed, 38 insertions(+), 9 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index fb397918c43d..b1c3db9cf355 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3125,6 +3125,7 @@ static inline bool pagetable_pmd_ctor(struct ptdesc *ptdesc) if (!pmd_ptlock_init(ptdesc)) return false; __folio_set_pgtable(folio); + ptdesc_pmd_pts_init(ptdesc); lruvec_stat_add_folio(folio, NR_PAGETABLE); return true; } diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 7361a8f3ab68..332cee285662 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -445,6 +445,7 @@ FOLIO_MATCH(compound_head, _head_2a); * @pt_index: Used for s390 gmap. * @pt_mm: Used for x86 pgds. * @pt_frag_refcount: For fragmented page table tracking. Powerpc only. + * @pt_share_count: Used for HugeTLB PMD page table share count. * @_pt_pad_2: Padding to ensure proper alignment. * @ptl: Lock for the page table. * @__page_type: Same as page->page_type. Unused for page tables. @@ -471,6 +472,9 @@ struct ptdesc { pgoff_t pt_index; struct mm_struct *pt_mm; atomic_t pt_frag_refcount; +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING + atomic_t pt_share_count; +#endif }; union { @@ -516,6 +520,32 @@ static_assert(sizeof(struct ptdesc) <= sizeof(struct page)); const struct page *: (const struct ptdesc *)(p), \ struct page *: (struct ptdesc *)(p))) +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING +static inline void ptdesc_pmd_pts_init(struct ptdesc *ptdesc) +{ + atomic_set(&ptdesc->pt_share_count, 0); +} + +static inline void ptdesc_pmd_pts_inc(struct ptdesc *ptdesc) +{ + atomic_inc(&ptdesc->pt_share_count); +} + +static inline void ptdesc_pmd_pts_dec(struct ptdesc *ptdesc) +{ + atomic_dec(&ptdesc->pt_share_count); +} + +static inline int ptdesc_pmd_pts_count(struct ptdesc *ptdesc) +{ + return atomic_read(&ptdesc->pt_share_count); +} +#else +static inline void ptdesc_pmd_pts_init(struct ptdesc *ptdesc) +{ +} +#endif + /* * Used for sizing the vmemmap region on some architectures */ diff --git a/mm/hugetlb.c b/mm/hugetlb.c index cec4b121193f..c498874a7170 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -7211,7 +7211,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, spte = hugetlb_walk(svma, saddr, vma_mmu_pagesize(svma)); if (spte) { - get_page(virt_to_page(spte)); + ptdesc_pmd_pts_inc(virt_to_ptdesc(spte)); break; } } @@ -7226,7 +7226,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, (pmd_t *)((unsigned long)spte & PAGE_MASK)); mm_inc_nr_pmds(mm); } else { - put_page(virt_to_page(spte)); + ptdesc_pmd_pts_dec(virt_to_ptdesc(spte)); } spin_unlock(&mm->page_table_lock); out: @@ -7238,10 +7238,6 @@ out: /* * unmap huge page backed by shared pte. * - * Hugetlb pte page is ref counted at the time of mapping. If pte is shared - * indicated by page_count > 1, unmap is achieved by clearing pud and - * decrementing the ref count. If count == 1, the pte page is not shared. - * * Called with page table lock held. * * returns: 1 successfully unmapped a shared pte page @@ -7250,18 +7246,20 @@ out: int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { + unsigned long sz = huge_page_size(hstate_vma(vma)); pgd_t *pgd = pgd_offset(mm, addr); p4d_t *p4d = p4d_offset(pgd, addr); pud_t *pud = pud_offset(p4d, addr); i_mmap_assert_write_locked(vma->vm_file->f_mapping); hugetlb_vma_assert_locked(vma); - BUG_ON(page_count(virt_to_page(ptep)) == 0); - if (page_count(virt_to_page(ptep)) == 1) + if (sz != PMD_SIZE) + return 0; + if (!ptdesc_pmd_pts_count(virt_to_ptdesc(ptep))) return 0; pud_clear(pud); - put_page(virt_to_page(ptep)); + ptdesc_pmd_pts_dec(virt_to_ptdesc(ptep)); mm_dec_nr_pmds(mm); return 1; } -- 2.51.0 From cddc76b165161a02ff14c4d84d0f5266d9d32b9e Mon Sep 17 00:00:00 2001 From: Alessandro Carminati Date: Tue, 17 Dec 2024 14:20:33 +0000 Subject: [PATCH 14/16] mm/kmemleak: fix sleeping function called from invalid context at print message MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit Address a bug in the kernel that triggers a "sleeping function called from invalid context" warning when /sys/kernel/debug/kmemleak is printed under specific conditions: - CONFIG_PREEMPT_RT=y - Set SELinux as the LSM for the system - Set kptr_restrict to 1 - kmemleak buffer contains at least one item BUG: sleeping function called from invalid context at kernel/locking/spinlock_rt.c:48 in_atomic(): 1, irqs_disabled(): 1, non_block: 0, pid: 136, name: cat preempt_count: 1, expected: 0 RCU nest depth: 2, expected: 2 6 locks held by cat/136: #0: ffff32e64bcbf950 (&p->lock){+.+.}-{3:3}, at: seq_read_iter+0xb8/0xe30 #1: ffffafe6aaa9dea0 (scan_mutex){+.+.}-{3:3}, at: kmemleak_seq_start+0x34/0x128 #3: ffff32e6546b1cd0 (&object->lock){....}-{2:2}, at: kmemleak_seq_show+0x3c/0x1e0 #4: ffffafe6aa8d8560 (rcu_read_lock){....}-{1:2}, at: has_ns_capability_noaudit+0x8/0x1b0 #5: ffffafe6aabbc0f8 (notif_lock){+.+.}-{2:2}, at: avc_compute_av+0xc4/0x3d0 irq event stamp: 136660 hardirqs last enabled at (136659): [] _raw_spin_unlock_irqrestore+0xa8/0xd8 hardirqs last disabled at (136660): [] _raw_spin_lock_irqsave+0x8c/0xb0 softirqs last enabled at (0): [] copy_process+0x11d8/0x3df8 softirqs last disabled at (0): [<0000000000000000>] 0x0 Preemption disabled at: [] kmemleak_seq_show+0x3c/0x1e0 CPU: 1 UID: 0 PID: 136 Comm: cat Tainted: G E 6.11.0-rt7+ #34 Tainted: [E]=UNSIGNED_MODULE Hardware name: linux,dummy-virt (DT) Call trace: dump_backtrace+0xa0/0x128 show_stack+0x1c/0x30 dump_stack_lvl+0xe8/0x198 dump_stack+0x18/0x20 rt_spin_lock+0x8c/0x1a8 avc_perm_nonode+0xa0/0x150 cred_has_capability.isra.0+0x118/0x218 selinux_capable+0x50/0x80 security_capable+0x7c/0xd0 has_ns_capability_noaudit+0x94/0x1b0 has_capability_noaudit+0x20/0x30 restricted_pointer+0x21c/0x4b0 pointer+0x298/0x760 vsnprintf+0x330/0xf70 seq_printf+0x178/0x218 print_unreferenced+0x1a4/0x2d0 kmemleak_seq_show+0xd0/0x1e0 seq_read_iter+0x354/0xe30 seq_read+0x250/0x378 full_proxy_read+0xd8/0x148 vfs_read+0x190/0x918 ksys_read+0xf0/0x1e0 __arm64_sys_read+0x70/0xa8 invoke_syscall.constprop.0+0xd4/0x1d8 el0_svc+0x50/0x158 el0t_64_sync+0x17c/0x180 %pS and %pK, in the same back trace line, are redundant, and %pS can void %pK service in certain contexts. %pS alone already provides the necessary information, and if it cannot resolve the symbol, it falls back to printing the raw address voiding the original intent behind the %pK. Additionally, %pK requires a privilege check CAP_SYSLOG enforced through the LSM, which can trigger a "sleeping function called from invalid context" warning under RT_PREEMPT kernels when the check occurs in an atomic context. This issue may also affect other LSMs. This change avoids the unnecessary privilege check and resolves the sleeping function warning without any loss of information. Link: https://lkml.kernel.org/r/20241217142032.55793-1-acarmina@redhat.com Fixes: 3a6f33d86baa ("mm/kmemleak: use %pK to display kernel pointers in backtrace") Signed-off-by: Alessandro Carminati Acked-by: Sebastian Andrzej Siewior Acked-by: Catalin Marinas Cc: Clément Léger Cc: Alessandro Carminati Cc: Eric Chanudet Cc: Gabriele Paoloni Cc: Juri Lelli Cc: Steven Rostedt Cc: Thomas Weißschuh Cc: Signed-off-by: Andrew Morton --- mm/kmemleak.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 2a945c07ae99..737af23f4f4e 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -373,7 +373,7 @@ static void print_unreferenced(struct seq_file *seq, for (i = 0; i < nr_entries; i++) { void *ptr = (void *)entries[i]; - warn_or_seq_printf(seq, " [<%pK>] %pS\n", ptr, ptr); + warn_or_seq_printf(seq, " %pS\n", ptr); } } -- 2.51.0 From 4d9b90df2eb49ab9becdbfd1fd60071bb107406e Mon Sep 17 00:00:00 2001 From: Mathieu Othacehe Date: Tue, 17 Dec 2024 11:09:21 +0100 Subject: [PATCH 15/16] mailmap: modify the entry for Mathieu Othacehe Set my gnu address as the main one. Link: https://lkml.kernel.org/r/20241217100924.7821-1-othacehe@gnu.org Signed-off-by: Mathieu Othacehe Cc: Alex Elder Cc: David S. Miller Cc: Geliang Tang Cc: Kees Cook Cc: Matthieu Baerts (NGI0) Cc: Neeraj Upadhyay Cc: Quentin Monnet Signed-off-by: Andrew Morton --- .mailmap | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.mailmap b/.mailmap index 7efe43237ca8..f5f97f947020 100644 --- a/.mailmap +++ b/.mailmap @@ -435,7 +435,7 @@ Martin Kepplinger Martin Kepplinger Martin Kepplinger Martyna Szapar-Mudlaw -Mathieu Othacehe +Mathieu Othacehe Mat Martineau Mat Martineau Matthew Wilcox -- 2.51.0 From 472098f23323c39cc6269d7b7bf76cba62830a4c Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Tue, 17 Dec 2024 16:55:39 +0800 Subject: [PATCH 16/16] docs: mm: fix the incorrect 'FileHugeMapped' field The '/proc/PID/smaps' does not have the 'FileHugeMapped' field to count the file transparent huge pages, instead, the 'FilePmdMapped' field should be used. Fix it. Link: https://lkml.kernel.org/r/d520ce3aba2b03b088be30bece732426a939049a.1734425264.git.baolin.wang@linux.alibaba.com Signed-off-by: Baolin Wang Acked-by: David Hildenbrand Signed-off-by: Andrew Morton --- Documentation/admin-guide/mm/transhuge.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst index 5034915f4e8e..8872203df088 100644 --- a/Documentation/admin-guide/mm/transhuge.rst +++ b/Documentation/admin-guide/mm/transhuge.rst @@ -436,7 +436,7 @@ AnonHugePmdMapped). The number of file transparent huge pages mapped to userspace is available by reading ShmemPmdMapped and ShmemHugePages fields in ``/proc/meminfo``. To identify what applications are mapping file transparent huge pages, it -is necessary to read ``/proc/PID/smaps`` and count the FileHugeMapped fields +is necessary to read ``/proc/PID/smaps`` and count the FilePmdMapped fields for each mapping. Note that reading the smaps file is expensive and reading it -- 2.51.0