From db7cfc380900bc4243b09623fd72fabe0a8ff23b Mon Sep 17 00:00:00 2001 From: Alexey Gladkov Date: Wed, 22 Jun 2022 22:07:29 +0200 Subject: [PATCH 01/21] ipc: Free mq_sysctls if ipc namespace creation failed The problem that Dmitry Vyukov pointed out is that if setup_ipc_sysctls fails, mq_sysctls must be freed before return. executing program BUG: memory leak unreferenced object 0xffff888112fc9200 (size 512): comm "syz-executor237", pid 3648, jiffies 4294970469 (age 12.270s) hex dump (first 32 bytes): ef d3 60 85 ff ff ff ff 0c 9b d2 12 81 88 ff ff ..`............. 04 00 00 00 a4 01 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [] kmemdup+0x23/0x50 mm/util.c:129 [] kmemdup include/linux/fortify-string.h:456 [inline] [] setup_mq_sysctls+0x4b/0x1c0 ipc/mq_sysctl.c:89 [] create_ipc_ns ipc/namespace.c:63 [inline] [] copy_ipcs+0x292/0x390 ipc/namespace.c:91 [] create_new_namespaces+0xdc/0x4f0 kernel/nsproxy.c:90 [] unshare_nsproxy_namespaces+0x9b/0x120 kernel/nsproxy.c:226 [] ksys_unshare+0x2fe/0x600 kernel/fork.c:3165 [] __do_sys_unshare kernel/fork.c:3236 [inline] [] __se_sys_unshare kernel/fork.c:3234 [inline] [] __x64_sys_unshare+0x12/0x20 kernel/fork.c:3234 [] do_syscall_x64 arch/x86/entry/common.c:50 [inline] [] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 [] entry_SYSCALL_64_after_hwframe+0x46/0xb0 BUG: memory leak unreferenced object 0xffff888112fd5f00 (size 256): comm "syz-executor237", pid 3648, jiffies 4294970469 (age 12.270s) hex dump (first 32 bytes): 00 92 fc 12 81 88 ff ff 00 00 00 00 01 00 00 00 ................ 01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [] kmalloc include/linux/slab.h:605 [inline] [] kzalloc include/linux/slab.h:733 [inline] [] __register_sysctl_table+0x7b/0x7f0 fs/proc/proc_sysctl.c:1344 [] setup_mq_sysctls+0x12a/0x1c0 ipc/mq_sysctl.c:112 [] create_ipc_ns ipc/namespace.c:63 [inline] [] copy_ipcs+0x292/0x390 ipc/namespace.c:91 [] create_new_namespaces+0xdc/0x4f0 kernel/nsproxy.c:90 [] unshare_nsproxy_namespaces+0x9b/0x120 kernel/nsproxy.c:226 [] ksys_unshare+0x2fe/0x600 kernel/fork.c:3165 [] __do_sys_unshare kernel/fork.c:3236 [inline] [] __se_sys_unshare kernel/fork.c:3234 [inline] [] __x64_sys_unshare+0x12/0x20 kernel/fork.c:3234 [] do_syscall_x64 arch/x86/entry/common.c:50 [inline] [] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 [] entry_SYSCALL_64_after_hwframe+0x46/0xb0 BUG: memory leak unreferenced object 0xffff888112fbba00 (size 256): comm "syz-executor237", pid 3648, jiffies 4294970469 (age 12.270s) hex dump (first 32 bytes): 78 ba fb 12 81 88 ff ff 00 00 00 00 01 00 00 00 x............... 01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [] kmalloc include/linux/slab.h:605 [inline] [] kzalloc include/linux/slab.h:733 [inline] [] new_dir fs/proc/proc_sysctl.c:978 [inline] [] get_subdir fs/proc/proc_sysctl.c:1022 [inline] [] __register_sysctl_table+0x5a9/0x7f0 fs/proc/proc_sysctl.c:1373 [] setup_mq_sysctls+0x12a/0x1c0 ipc/mq_sysctl.c:112 [] create_ipc_ns ipc/namespace.c:63 [inline] [] copy_ipcs+0x292/0x390 ipc/namespace.c:91 [] create_new_namespaces+0xdc/0x4f0 kernel/nsproxy.c:90 [] unshare_nsproxy_namespaces+0x9b/0x120 kernel/nsproxy.c:226 [] ksys_unshare+0x2fe/0x600 kernel/fork.c:3165 [] __do_sys_unshare kernel/fork.c:3236 [inline] [] __se_sys_unshare kernel/fork.c:3234 [inline] [] __x64_sys_unshare+0x12/0x20 kernel/fork.c:3234 [] do_syscall_x64 arch/x86/entry/common.c:50 [inline] [] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 [] entry_SYSCALL_64_after_hwframe+0x46/0xb0 BUG: memory leak unreferenced object 0xffff888112fbb900 (size 256): comm "syz-executor237", pid 3648, jiffies 4294970469 (age 12.270s) hex dump (first 32 bytes): 78 b9 fb 12 81 88 ff ff 00 00 00 00 01 00 00 00 x............... 01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [] kmalloc include/linux/slab.h:605 [inline] [] kzalloc include/linux/slab.h:733 [inline] [] new_dir fs/proc/proc_sysctl.c:978 [inline] [] get_subdir fs/proc/proc_sysctl.c:1022 [inline] [] __register_sysctl_table+0x5a9/0x7f0 fs/proc/proc_sysctl.c:1373 [] setup_mq_sysctls+0x12a/0x1c0 ipc/mq_sysctl.c:112 [] create_ipc_ns ipc/namespace.c:63 [inline] [] copy_ipcs+0x292/0x390 ipc/namespace.c:91 [] create_new_namespaces+0xdc/0x4f0 kernel/nsproxy.c:90 [] unshare_nsproxy_namespaces+0x9b/0x120 kernel/nsproxy.c:226 [] ksys_unshare+0x2fe/0x600 kernel/fork.c:3165 [] __do_sys_unshare kernel/fork.c:3236 [inline] [] __se_sys_unshare kernel/fork.c:3234 [inline] [] __x64_sys_unshare+0x12/0x20 kernel/fork.c:3234 [] do_syscall_x64 arch/x86/entry/common.c:50 [inline] [] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 [] entry_SYSCALL_64_after_hwframe+0x46/0xb0 Reported-by: syzbot+b4b0d1b35442afbf6fd2@syzkaller.appspotmail.com Signed-off-by: Alexey Gladkov Link: https://lkml.kernel.org/r/000000000000f5004705e1db8bad@google.com Link: https://lkml.kernel.org/r/20220622200729.2639663-1-legion@kernel.org Signed-off-by: Eric W. Biederman --- ipc/namespace.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/ipc/namespace.c b/ipc/namespace.c index 754f3237194a..e1fcaedba4fa 100644 --- a/ipc/namespace.c +++ b/ipc/namespace.c @@ -64,7 +64,7 @@ static struct ipc_namespace *create_ipc_ns(struct user_namespace *user_ns, goto fail_put; if (!setup_ipc_sysctls(ns)) - goto fail_put; + goto fail_mq; sem_init_ns(ns); msg_init_ns(ns); @@ -72,6 +72,9 @@ static struct ipc_namespace *create_ipc_ns(struct user_namespace *user_ns, return ns; +fail_mq: + retire_mq_sysctls(ns); + fail_put: put_user_ns(ns->user_ns); ns_free_inum(&ns->ns); From 35adf9a4e55e0b0a9d5e313e65ad83681dc32e9a Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 1 Jul 2022 12:44:03 +0300 Subject: [PATCH 02/21] modules: Fix corruption of /proc/kallsyms The commit 91fb02f31505 ("module: Move kallsyms support into a separate file") changed from using strlcpy() to using strscpy() which created a buffer overflow. That happened because: 1) an incorrect value was passed as the buffer length 2) strscpy() (unlike strlcpy()) may copy beyond the length of the input string when copying word-by-word. The assumption was that because it was already known that the strings being copied would fit in the space available, it was not necessary to correctly set the buffer length. strscpy() breaks that assumption because although it will not touch bytes beyond the given buffer length it may write bytes beyond the input string length when writing word-by-word. The result of the buffer overflow is to corrupt the symbol type information that follows. e.g. $ sudo cat -v /proc/kallsyms | grep '\^' | head ffffffffc0615000 ^@ rfcomm_session_get [rfcomm] ffffffffc061c060 ^@ session_list [rfcomm] ffffffffc06150d0 ^@ rfcomm_send_frame [rfcomm] ffffffffc0615130 ^@ rfcomm_make_uih [rfcomm] ffffffffc07ed58d ^@ bnep_exit [bnep] ffffffffc07ec000 ^@ bnep_rx_control [bnep] ffffffffc07ec1a0 ^@ bnep_session [bnep] ffffffffc07e7000 ^@ input_leds_event [input_leds] ffffffffc07e9000 ^@ input_leds_handler [input_leds] ffffffffc07e7010 ^@ input_leds_disconnect [input_leds] Notably, the null bytes (represented above by ^@) can confuse tools. Fix by correcting the buffer length. Fixes: 91fb02f31505 ("module: Move kallsyms support into a separate file") Signed-off-by: Adrian Hunter Signed-off-by: Luis Chamberlain --- kernel/module/kallsyms.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/kernel/module/kallsyms.c b/kernel/module/kallsyms.c index 3e11523bc6f6..18c23545b984 100644 --- a/kernel/module/kallsyms.c +++ b/kernel/module/kallsyms.c @@ -137,6 +137,7 @@ void layout_symtab(struct module *mod, struct load_info *info) info->symoffs = ALIGN(mod->data_layout.size, symsect->sh_addralign ?: 1); info->stroffs = mod->data_layout.size = info->symoffs + ndst * sizeof(Elf_Sym); mod->data_layout.size += strtab_size; + /* Note add_kallsyms() computes strtab_size as core_typeoffs - stroffs */ info->core_typeoffs = mod->data_layout.size; mod->data_layout.size += ndst * sizeof(char); mod->data_layout.size = strict_align(mod->data_layout.size); @@ -169,6 +170,7 @@ void add_kallsyms(struct module *mod, const struct load_info *info) Elf_Sym *dst; char *s; Elf_Shdr *symsec = &info->sechdrs[info->index.sym]; + unsigned long strtab_size; /* Set up to point into init section. */ mod->kallsyms = (void __rcu *)mod->init_layout.base + @@ -190,19 +192,26 @@ void add_kallsyms(struct module *mod, const struct load_info *info) mod->core_kallsyms.symtab = dst = mod->data_layout.base + info->symoffs; mod->core_kallsyms.strtab = s = mod->data_layout.base + info->stroffs; mod->core_kallsyms.typetab = mod->data_layout.base + info->core_typeoffs; + strtab_size = info->core_typeoffs - info->stroffs; src = rcu_dereference_sched(mod->kallsyms)->symtab; for (ndst = i = 0; i < rcu_dereference_sched(mod->kallsyms)->num_symtab; i++) { rcu_dereference_sched(mod->kallsyms)->typetab[i] = elf_type(src + i, info); if (i == 0 || is_livepatch_module(mod) || is_core_symbol(src + i, info->sechdrs, info->hdr->e_shnum, info->index.pcpu)) { + ssize_t ret; + mod->core_kallsyms.typetab[ndst] = rcu_dereference_sched(mod->kallsyms)->typetab[i]; dst[ndst] = src[i]; dst[ndst++].st_name = s - mod->core_kallsyms.strtab; - s += strscpy(s, - &rcu_dereference_sched(mod->kallsyms)->strtab[src[i].st_name], - KSYM_NAME_LEN) + 1; + ret = strscpy(s, + &rcu_dereference_sched(mod->kallsyms)->strtab[src[i].st_name], + strtab_size); + if (ret < 0) + break; + s += ret + 1; + strtab_size -= ret + 1; } } preempt_enable(); From cfa94c538be621a0ba645adfa9ead005b5fa02f6 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sun, 12 Jun 2022 17:21:56 +0200 Subject: [PATCH 03/21] module: Fix selfAssignment cppcheck warning cppcheck reports the following warnings: kernel/module/main.c:1455:26: warning: Redundant assignment of 'mod->core_layout.size' to itself. [selfAssignment] mod->core_layout.size = strict_align(mod->core_layout.size); ^ kernel/module/main.c:1489:26: warning: Redundant assignment of 'mod->init_layout.size' to itself. [selfAssignment] mod->init_layout.size = strict_align(mod->init_layout.size); ^ kernel/module/main.c:1493:26: warning: Redundant assignment of 'mod->init_layout.size' to itself. [selfAssignment] mod->init_layout.size = strict_align(mod->init_layout.size); ^ kernel/module/main.c:1504:26: warning: Redundant assignment of 'mod->init_layout.size' to itself. [selfAssignment] mod->init_layout.size = strict_align(mod->init_layout.size); ^ kernel/module/main.c:1459:26: warning: Redundant assignment of 'mod->data_layout.size' to itself. [selfAssignment] mod->data_layout.size = strict_align(mod->data_layout.size); ^ kernel/module/main.c:1463:26: warning: Redundant assignment of 'mod->data_layout.size' to itself. [selfAssignment] mod->data_layout.size = strict_align(mod->data_layout.size); ^ kernel/module/main.c:1467:26: warning: Redundant assignment of 'mod->data_layout.size' to itself. [selfAssignment] mod->data_layout.size = strict_align(mod->data_layout.size); ^ This is due to strict_align() being a no-op when CONFIG_STRICT_MODULE_RWX is not selected. Transform strict_align() macro into an inline function. It will allow type checking and avoid the selfAssignment warning. Reported-by: kernel test robot Signed-off-by: Christophe Leroy Signed-off-by: Luis Chamberlain --- kernel/module/internal.h | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/kernel/module/internal.h b/kernel/module/internal.h index bc5507ab8450..ec104c2950c3 100644 --- a/kernel/module/internal.h +++ b/kernel/module/internal.h @@ -11,6 +11,7 @@ #include #include #include +#include #ifndef ARCH_SHF_SMALL #define ARCH_SHF_SMALL 0 @@ -30,11 +31,13 @@ * to ensure complete separation of code and data, but * only when CONFIG_STRICT_MODULE_RWX=y */ -#ifdef CONFIG_STRICT_MODULE_RWX -# define strict_align(X) PAGE_ALIGN(X) -#else -# define strict_align(X) (X) -#endif +static inline unsigned int strict_align(unsigned int size) +{ + if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX)) + return PAGE_ALIGN(size); + else + return size; +} extern struct mutex module_mutex; extern struct list_head modules; From f963ef123900ac534aeb6141642e5351989ac14c Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sun, 12 Jun 2022 17:33:20 +0200 Subject: [PATCH 04/21] module: Fix "warning: variable 'exit' set but not used" When CONFIG_MODULE_UNLOAD is not selected, 'exit' is set but never used. It is not possible to replace the #ifdef CONFIG_MODULE_UNLOAD by IS_ENABLED(CONFIG_MODULE_UNLOAD) because mod->exit doesn't exist when CONFIG_MODULE_UNLOAD is not selected. And because of the rcu_read_lock_sched() section it is not easy to regroup everything in a single #ifdef. Let's regroup partially and add missing #ifdef to completely opt out the use of 'exit' when CONFIG_MODULE_UNLOAD is not selected. Reported-by: kernel test robot Signed-off-by: Christophe Leroy Signed-off-by: Luis Chamberlain --- kernel/module/main.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/kernel/module/main.c b/kernel/module/main.c index fed58d30725d..0548151dd933 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -2939,24 +2939,25 @@ static void cfi_init(struct module *mod) { #ifdef CONFIG_CFI_CLANG initcall_t *init; +#ifdef CONFIG_MODULE_UNLOAD exitcall_t *exit; +#endif rcu_read_lock_sched(); mod->cfi_check = (cfi_check_fn) find_kallsyms_symbol_value(mod, "__cfi_check"); init = (initcall_t *) find_kallsyms_symbol_value(mod, "__cfi_jt_init_module"); - exit = (exitcall_t *) - find_kallsyms_symbol_value(mod, "__cfi_jt_cleanup_module"); - rcu_read_unlock_sched(); - /* Fix init/exit functions to point to the CFI jump table */ if (init) mod->init = *init; #ifdef CONFIG_MODULE_UNLOAD + exit = (exitcall_t *) + find_kallsyms_symbol_value(mod, "__cfi_jt_cleanup_module"); if (exit) mod->exit = *exit; #endif + rcu_read_unlock_sched(); cfi_module_add(mod, mod_tree.addr_min); #endif From 2cc39179acbbe524127f0427cee92b629db4d64b Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 15 Jun 2022 06:33:03 +0900 Subject: [PATCH 05/21] doc: module: update file references Adjust documents to the file moves made by commit cfc1d277891e ("module: Move all into module/"). Thanks to Yanteng Si for helping me to update Documentation/translations/zh_CN/core-api/kernel-api.rst Signed-off-by: Masahiro Yamada Acked-by: Yanteng Si Signed-off-by: Luis Chamberlain --- Documentation/core-api/kernel-api.rst | 2 +- Documentation/core-api/symbol-namespaces.rst | 4 ++-- Documentation/livepatch/module-elf-format.rst | 10 +++++----- .../translations/it_IT/core-api/symbol-namespaces.rst | 6 +++--- .../translations/zh_CN/core-api/kernel-api.rst | 2 +- .../translations/zh_CN/core-api/symbol-namespaces.rst | 2 +- 6 files changed, 13 insertions(+), 13 deletions(-) diff --git a/Documentation/core-api/kernel-api.rst b/Documentation/core-api/kernel-api.rst index d6b3f94b9f1f..0793c400d4b0 100644 --- a/Documentation/core-api/kernel-api.rst +++ b/Documentation/core-api/kernel-api.rst @@ -223,7 +223,7 @@ Module Loading Inter Module support -------------------- -Refer to the file kernel/module.c for more information. +Refer to the files in kernel/module/ for more information. Hardware Interfaces =================== diff --git a/Documentation/core-api/symbol-namespaces.rst b/Documentation/core-api/symbol-namespaces.rst index 5ad9e0abe42c..12e4aecdae94 100644 --- a/Documentation/core-api/symbol-namespaces.rst +++ b/Documentation/core-api/symbol-namespaces.rst @@ -51,8 +51,8 @@ namespace ``USB_STORAGE``, use:: The corresponding ksymtab entry struct ``kernel_symbol`` will have the member ``namespace`` set accordingly. A symbol that is exported without a namespace will refer to ``NULL``. There is no default namespace if none is defined. ``modpost`` -and kernel/module.c make use the namespace at build time or module load time, -respectively. +and kernel/module/main.c make use the namespace at build time or module load +time, respectively. 2.2 Using the DEFAULT_SYMBOL_NAMESPACE define ============================================= diff --git a/Documentation/livepatch/module-elf-format.rst b/Documentation/livepatch/module-elf-format.rst index dbe9b400e39f..7347638895a0 100644 --- a/Documentation/livepatch/module-elf-format.rst +++ b/Documentation/livepatch/module-elf-format.rst @@ -210,11 +210,11 @@ module->symtab. ===================================== Normally, a stripped down copy of a module's symbol table (containing only "core" symbols) is made available through module->symtab (See layout_symtab() -in kernel/module.c). For livepatch modules, the symbol table copied into memory -on module load must be exactly the same as the symbol table produced when the -patch module was compiled. This is because the relocations in each livepatch -relocation section refer to their respective symbols with their symbol indices, -and the original symbol indices (and thus the symtab ordering) must be +in kernel/module/kallsyms.c). For livepatch modules, the symbol table copied +into memory on module load must be exactly the same as the symbol table produced +when the patch module was compiled. This is because the relocations in each +livepatch relocation section refer to their respective symbols with their symbol +indices, and the original symbol indices (and thus the symtab ordering) must be preserved in order for apply_relocate_add() to find the right symbol. For example, take this particular rela from a livepatch module::: diff --git a/Documentation/translations/it_IT/core-api/symbol-namespaces.rst b/Documentation/translations/it_IT/core-api/symbol-namespaces.rst index 42f5d04e38ec..0f6898860d6d 100644 --- a/Documentation/translations/it_IT/core-api/symbol-namespaces.rst +++ b/Documentation/translations/it_IT/core-api/symbol-namespaces.rst @@ -50,9 +50,9 @@ Di conseguenza, nella tabella dei simboli del kernel ci sarà una voce rappresentata dalla struttura ``kernel_symbol`` che avrà il campo ``namespace`` (spazio dei nomi) impostato. Un simbolo esportato senza uno spazio dei nomi avrà questo campo impostato a ``NULL``. Non esiste uno spazio dei nomi -di base. Il programma ``modpost`` e il codice in kernel/module.c usano lo spazio -dei nomi, rispettivamente, durante la compilazione e durante il caricamento -di un modulo. +di base. Il programma ``modpost`` e il codice in kernel/module/main.c usano lo +spazio dei nomi, rispettivamente, durante la compilazione e durante il +caricamento di un modulo. 2.2 Usare il simbolo di preprocessore DEFAULT_SYMBOL_NAMESPACE ============================================================== diff --git a/Documentation/translations/zh_CN/core-api/kernel-api.rst b/Documentation/translations/zh_CN/core-api/kernel-api.rst index e45fe80d1cd8..962d31d019d7 100644 --- a/Documentation/translations/zh_CN/core-api/kernel-api.rst +++ b/Documentation/translations/zh_CN/core-api/kernel-api.rst @@ -224,7 +224,7 @@ kernel/kmod.c 模块接口支持 ------------ -更多信息请参考文件kernel/module.c。 +更多信息请参阅kernel/module/目录下的文件。 硬件接口 ======== diff --git a/Documentation/translations/zh_CN/core-api/symbol-namespaces.rst b/Documentation/translations/zh_CN/core-api/symbol-namespaces.rst index 6abf7ed534ca..bb16f0611046 100644 --- a/Documentation/translations/zh_CN/core-api/symbol-namespaces.rst +++ b/Documentation/translations/zh_CN/core-api/symbol-namespaces.rst @@ -52,7 +52,7 @@ 相应的 ksymtab 条目结构体 ``kernel_symbol`` 将有相应的成员 ``命名空间`` 集。 导出时未指明命名空间的符号将指向 ``NULL`` 。如果没有定义命名空间，则默认没有。 -``modpost`` 和kernel/module.c分别在构建时或模块加载时使用名称空间。 +``modpost`` 和kernel/module/main.c分别在构建时或模块加载时使用名称空间。 2.2 使用DEFAULT_SYMBOL_NAMESPACE定义 ==================================== From 73f37dbcfe1763ee2294c7717a1f571e27d17fd8 Mon Sep 17 00:00:00 2001 From: Axel Rasmussen Date: Fri, 10 Jun 2022 10:38:12 -0700 Subject: [PATCH 06/21] mm: userfaultfd: fix UFFDIO_CONTINUE on fallocated shmem pages When fallocate() is used on a shmem file, the pages we allocate can end up with !PageUptodate. Since UFFDIO_CONTINUE tries to find the existing page the user wants to map with SGP_READ, we would fail to find such a page, since shmem_getpage_gfp returns with a "NULL" pagep for SGP_READ if it discovers !PageUptodate. As a result, UFFDIO_CONTINUE returns -EFAULT, as it would do if the page wasn't found in the page cache at all. This isn't the intended behavior. UFFDIO_CONTINUE is just trying to find if a page exists, and doesn't care whether it still needs to be cleared or not. So, instead of SGP_READ, pass in SGP_NOALLOC. This is the same, except for one critical difference: in the !PageUptodate case, SGP_NOALLOC will clear the page and then return it. With this change, UFFDIO_CONTINUE works properly (succeeds) on a shmem file which has been fallocated, but otherwise not modified. Link: https://lkml.kernel.org/r/20220610173812.1768919-1-axelrasmussen@google.com Fixes: 153132571f02 ("userfaultfd/shmem: support UFFDIO_CONTINUE for shmem") Signed-off-by: Axel Rasmussen Acked-by: Peter Xu Cc: Hugh Dickins Cc: Signed-off-by: Andrew Morton --- mm/userfaultfd.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 4f4892a5f767..07d3befc80e4 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -246,7 +246,10 @@ static int mcontinue_atomic_pte(struct mm_struct *dst_mm, struct page *page; int ret; - ret = shmem_getpage(inode, pgoff, &page, SGP_READ); + ret = shmem_getpage(inode, pgoff, &page, SGP_NOALLOC); + /* Our caller expects us to return -EFAULT if we failed to find page. */ + if (ret == -ENOENT) + ret = -EFAULT; if (ret) goto out; if (!page) { From d684e0a52d36f8939eda30a0f31ee235ee4ee741 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 20 Jun 2022 09:01:43 +0200 Subject: [PATCH 07/21] sh: convert nommu io{re,un}map() to static inline functions Recently, nommu iounmap() was converted from a static inline function to a macro again, basically reverting commit 4580ba4ad2e6b8dd ("sh: Convert iounmap() macros to inline functions"). With -Werror, this leads to build failures like: drivers/iio/adc/xilinx-ams.c: In function `ams_iounmap_ps': drivers/iio/adc/xilinx-ams.c:1195:14: error: unused variable `ams' [-Werror=unused-variable] 1195 | struct ams *ams = data; | ^~~ Fix this by replacing the macros for ioremap() and iounmap() by static inline functions, based on . Link: https://lkml.kernel.org/r/8d1b1766260961799b04035e7bc39a7f59729f72.1655708312.git.geert+renesas@glider.be Fixes: 13f1fc870dd74713 ("sh: move the ioremap implementation out of line") Signed-off-by: Geert Uytterhoeven Reported-by: kernel test robot Reported-by: Jonathan Cameron Acked-by: Jonathan Cameron Reviewed-by: Christoph Hellwig Signed-off-by: Andrew Morton --- arch/sh/include/asm/io.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/arch/sh/include/asm/io.h b/arch/sh/include/asm/io.h index cf9a3ec32406..fba90e670ed4 100644 --- a/arch/sh/include/asm/io.h +++ b/arch/sh/include/asm/io.h @@ -271,8 +271,12 @@ static inline void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size, #endif /* CONFIG_HAVE_IOREMAP_PROT */ #else /* CONFIG_MMU */ -#define iounmap(addr) do { } while (0) -#define ioremap(offset, size) ((void __iomem *)(unsigned long)(offset)) +static inline void __iomem *ioremap(phys_addr_t offset, size_t size) +{ + return (void __iomem *)(unsigned long)offset; +} + +static inline void iounmap(volatile void __iomem *addr) { } #endif /* CONFIG_MMU */ #define ioremap_uc ioremap From ed1523a895ffdabcab6e067af18685ed00f5ce15 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Mon, 20 Jun 2022 10:34:42 +0800 Subject: [PATCH 08/21] mm/damon: use set_huge_pte_at() to make huge pte old The huge_ptep_set_access_flags() can not make the huge pte old according to the discussion [1], that means we will always mornitor the young state of the hugetlb though we stopped accessing the hugetlb, as a result DAMON will get inaccurate accessing statistics. So changing to use set_huge_pte_at() to make the huge pte old to fix this issue. [1] https://lore.kernel.org/all/Yqy97gXI4Nqb7dYo@arm.com/ Link: https://lkml.kernel.org/r/1655692482-28797-1-git-send-email-baolin.wang@linux.alibaba.com Fixes: 49f4203aae06 ("mm/damon: add access checking for hugetlb pages") Signed-off-by: Baolin Wang Reviewed-by: SeongJae Park Acked-by: Mike Kravetz Reviewed-by: Muchun Song Cc: Signed-off-by: Andrew Morton --- mm/damon/vaddr.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index 59e1653799f8..3c7b9d6dca95 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -336,8 +336,7 @@ static void damon_hugetlb_mkold(pte_t *pte, struct mm_struct *mm, if (pte_young(entry)) { referenced = true; entry = pte_mkold(entry); - huge_ptep_set_access_flags(vma, addr, pte, entry, - vma->vm_flags & VM_WRITE); + set_huge_pte_at(mm, addr, pte, entry); } #ifdef CONFIG_MMU_NOTIFIER From 39d35edee4537487e5178f258e23518272a66413 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Mon, 20 Jun 2022 10:30:19 +0800 Subject: [PATCH 09/21] mm: sparsemem: fix missing higher order allocation splitting Higher order allocations for vmemmap pages from buddy allocator must be able to be treated as indepdenent small pages as they can be freed individually by the caller. There is no problem for higher order vmemmap pages allocated at boot time since each individual small page will be initialized at boot time. However, it will be an issue for memory hotplug case since those higher order vmemmap pages are allocated from buddy allocator without initializing each individual small page's refcount. The system will panic in put_page_testzero() when CONFIG_DEBUG_VM is enabled if the vmemmap page is freed. Link: https://lkml.kernel.org/r/20220620023019.94257-1-songmuchun@bytedance.com Fixes: d8d55f5616cf ("mm: sparsemem: use page table lock to protect kernel pmd operations") Signed-off-by: Muchun Song Reviewed-by: Mike Kravetz Cc: Xiongchun Duan Cc: Signed-off-by: Andrew Morton --- mm/sparse-vmemmap.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index f4fa61dbbee3..dbbd1a7e65f3 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -78,6 +78,14 @@ static int __split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start) spin_lock(&init_mm.page_table_lock); if (likely(pmd_leaf(*pmd))) { + /* + * Higher order allocations from buddy allocator must be able to + * be treated as indepdenent small pages (as they can be freed + * individually). + */ + if (!PageReserved(page)) + split_page(page, get_order(PMD_SIZE)); + /* Make pte visible before pmd. See comment in pmd_install(). */ smp_wmb(); pmd_populate_kernel(&init_mm, pmd, pgtable); From cffe57bee62b155c08d71218fc0e9e84a0a90bbb Mon Sep 17 00:00:00 2001 From: Bagas Sanjaya Date: Wed, 22 Jun 2022 15:45:46 +0700 Subject: [PATCH 10/21] Documentation: highmem: use literal block for code example in highmem.h comment When building htmldocs on Linus's tree, there are inline emphasis warnings on include/linux/highmem.h: Documentation/vm/highmem:166: ./include/linux/highmem.h:154: WARNING: Inline emphasis start-string without end-string. Documentation/vm/highmem:166: ./include/linux/highmem.h:157: WARNING: Inline emphasis start-string without end-string. These warnings above are due to comments in code example at the mentioned lines above are enclosed by double dash (--), which confuses Sphinx as inline markup delimiters instead. Fix these warnings by indenting the code example with literal block indentation and making the comments C comments. Link: https://lkml.kernel.org/r/20220622084546.17745-1-bagasdotme@gmail.com Fixes: 85a85e7601263f ("Documentation/vm: move "Using kmap-atomic" to highmem.h") Signed-off-by: Bagas Sanjaya Reviewed-by: Ira Weiny Tested-by: Ira Weiny Cc: "Matthew Wilcox (Oracle)" Cc: "Fabio M. De Francesco" Cc: Sebastian Andrzej Siewior Signed-off-by: Andrew Morton --- include/linux/highmem.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 3af34de54330..56d6a0196534 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -149,19 +149,19 @@ static inline void *kmap_local_folio(struct folio *folio, size_t offset); * It is used in atomic context when code wants to access the contents of a * page that might be allocated from high memory (see __GFP_HIGHMEM), for * example a page in the pagecache. The API has two functions, and they - * can be used in a manner similar to the following: + * can be used in a manner similar to the following:: * - * -- Find the page of interest. -- - * struct page *page = find_get_page(mapping, offset); + * // Find the page of interest. + * struct page *page = find_get_page(mapping, offset); * - * -- Gain access to the contents of that page. -- - * void *vaddr = kmap_atomic(page); + * // Gain access to the contents of that page. + * void *vaddr = kmap_atomic(page); * - * -- Do something to the contents of that page. -- - * memset(vaddr, 0, PAGE_SIZE); + * // Do something to the contents of that page. + * memset(vaddr, 0, PAGE_SIZE); * - * -- Unmap that page. -- - * kunmap_atomic(vaddr); + * // Unmap that page. + * kunmap_atomic(vaddr); * * Note that the kunmap_atomic() call takes the result of the kmap_atomic() * call, not the argument. From 34c0a5b04da8a543bc7335953c635dea1099d757 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Fri, 24 Jun 2022 16:52:36 +0800 Subject: [PATCH 11/21] riscv/mm: fix build error while PAGE_TABLE_CHECK enabled without MMU mm/page_table_check.c: In function `__page_table_check_pte_clear': mm/page_table_check.c:148:6: error: implicit declaration of function `pte_user_accessible_page'; did you mean `user_access_save'? [-Werror=implicit-function-declaration] if (pte_user_accessible_page(pte)) { ^~~~~~~~~~~~~~~~~~~~~~~~ user_access_save ARCH_SUPPORTS_PAGE_TABLE_CHECK should only enabled with MMU. Link: https://lkml.kernel.org/r/20220624085236.18544-1-yuehaibing@huawei.com Fixes: 3fee229a8eb9 ("riscv/mm: enable ARCH_SUPPORTS_PAGE_TABLE_CHECK") Signed-off-by: YueHaibing Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Albert Ou Cc: Pasha Tatashin Cc: Tong Tiangen Signed-off-by: Andrew Morton --- arch/riscv/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 32ffef9f6e5b..fcbb81feb7ad 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -38,7 +38,7 @@ config RISCV select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_SUPPORTS_DEBUG_PAGEALLOC if MMU select ARCH_SUPPORTS_HUGETLBFS if MMU - select ARCH_SUPPORTS_PAGE_TABLE_CHECK + select ARCH_SUPPORTS_PAGE_TABLE_CHECK if MMU select ARCH_USE_MEMTEST select ARCH_USE_QUEUED_RWLOCKS select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU From 1118234e4bc22ff50e9eae40ad95b17a6b12cefa Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 23 Jun 2022 22:53:32 +0200 Subject: [PATCH 12/21] mm/rmap: fix dereferencing invalid subpage pointer in try_to_migrate_one() The subpage we calculate is an invalid pointer for device private pages, because device private pages are mapped via non-present device private entries, not ordinary present PTEs. Let's just not compute broken pointers and fixup later. Move the proper assignment of the correct subpage to the beginning of the function and assert that we really only have a single page in our folio. This currently results in a BUG when tying to compute anon_exclusive, because: [ 528.727237] BUG: unable to handle page fault for address: ffffea1fffffffc0 [ 528.739585] #PF: supervisor read access in kernel mode [ 528.745324] #PF: error_code(0x0000) - not-present page [ 528.751062] PGD 44eaf2067 P4D 44eaf2067 PUD 0 [ 528.756026] Oops: 0000 [#1] PREEMPT SMP NOPTI [ 528.760890] CPU: 120 PID: 18275 Comm: hmm-tests Not tainted 5.19.0-rc3-kfd-alex #257 [ 528.769542] Hardware name: AMD Corporation BardPeak/BardPeak, BIOS RTY1002BDS 09/17/2021 [ 528.778579] RIP: 0010:try_to_migrate_one+0x21a/0x1000 [ 528.784225] Code: f6 48 89 c8 48 2b 05 45 d1 6a 01 48 c1 f8 06 48 29 c3 48 8b 45 a8 48 c1 e3 06 48 01 cb f6 41 18 01 48 89 85 50 ff ff ff 74 0b <4c> 8b 33 49 c1 ee 11 41 83 e6 01 48 8b bd 48 ff ff ff e8 3f 99 02 [ 528.805194] RSP: 0000:ffffc90003cdfaa0 EFLAGS: 00010202 [ 528.811027] RAX: 00007ffff7ff4000 RBX: ffffea1fffffffc0 RCX: ffffeaffffffffc0 [ 528.818995] RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffffc90003cdfaf8 [ 528.826962] RBP: ffffc90003cdfb70 R08: 0000000000000000 R09: 0000000000000000 [ 528.834930] R10: ffffc90003cdf910 R11: 0000000000000002 R12: ffff888194450540 [ 528.842899] R13: ffff888160d057c0 R14: 0000000000000000 R15: 03ffffffffffffff [ 528.850865] FS: 00007ffff7fdb740(0000) GS:ffff8883b0600000(0000) knlGS:0000000000000000 [ 528.859891] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 528.866308] CR2: ffffea1fffffffc0 CR3: 00000001562b4003 CR4: 0000000000770ee0 [ 528.874275] PKRU: 55555554 [ 528.877286] Call Trace: [ 528.880016] [ 528.882356] ? lock_is_held_type+0xdf/0x130 [ 528.887033] rmap_walk_anon+0x167/0x410 [ 528.891316] try_to_migrate+0x90/0xd0 [ 528.895405] ? try_to_unmap_one+0xe10/0xe10 [ 528.900074] ? anon_vma_ctor+0x50/0x50 [ 528.904260] ? put_anon_vma+0x10/0x10 [ 528.908347] ? invalid_mkclean_vma+0x20/0x20 [ 528.913114] migrate_vma_setup+0x5f4/0x750 [ 528.917691] dmirror_devmem_fault+0x8c/0x250 [test_hmm] [ 528.923532] do_swap_page+0xac0/0xe50 [ 528.927623] ? __lock_acquire+0x4b2/0x1ac0 [ 528.932199] __handle_mm_fault+0x949/0x1440 [ 528.936876] handle_mm_fault+0x13f/0x3e0 [ 528.941256] do_user_addr_fault+0x215/0x740 [ 528.945928] exc_page_fault+0x75/0x280 [ 528.950115] asm_exc_page_fault+0x27/0x30 [ 528.954593] RIP: 0033:0x40366b ... Link: https://lkml.kernel.org/r/20220623205332.319257-1-david@redhat.com Fixes: 6c287605fd56 ("mm: remember exclusively mapped anonymous pages with PG_anon_exclusive") Signed-off-by: David Hildenbrand Reported-by: "Sierra Guiza, Alejandro (Alex)" Reviewed-by: Alistair Popple Tested-by: Alistair Popple Cc: Vlastimil Babka Cc: Christoph Hellwig Cc: "Matthew Wilcox (Oracle)" Signed-off-by: Andrew Morton --- mm/rmap.c | 27 +++++++++++++++++---------- 1 file changed, 17 insertions(+), 10 deletions(-) diff --git a/mm/rmap.c b/mm/rmap.c index 5bcb334cd6f2..746c05acad27 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1899,8 +1899,23 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, /* Unexpected PMD-mapped THP? */ VM_BUG_ON_FOLIO(!pvmw.pte, folio); - subpage = folio_page(folio, - pte_pfn(*pvmw.pte) - folio_pfn(folio)); + if (folio_is_zone_device(folio)) { + /* + * Our PTE is a non-present device exclusive entry and + * calculating the subpage as for the common case would + * result in an invalid pointer. + * + * Since only PAGE_SIZE pages can currently be + * migrated, just set it to page. This will need to be + * changed when hugepage migrations to device private + * memory are supported. + */ + VM_BUG_ON_FOLIO(folio_nr_pages(folio) > 1, folio); + subpage = &folio->page; + } else { + subpage = folio_page(folio, + pte_pfn(*pvmw.pte) - folio_pfn(folio)); + } address = pvmw.address; anon_exclusive = folio_test_anon(folio) && PageAnonExclusive(subpage); @@ -1993,15 +2008,7 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, /* * No need to invalidate here it will synchronize on * against the special swap migration pte. - * - * The assignment to subpage above was computed from a - * swap PTE which results in an invalid pointer. - * Since only PAGE_SIZE pages can currently be - * migrated, just set it to page. This will need to be - * changed when hugepage migrations to device private - * memory are supported. */ - subpage = &folio->page; } else if (PageHWPoison(subpage)) { pteval = swp_entry_to_pte(make_hwpoison_entry(subpage)); if (folio_test_hugetlb(folio)) { From 5924e6ec1585445f251ea92713eb15beb732622a Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Thu, 23 Jun 2022 17:54:01 +0900 Subject: [PATCH 13/21] nilfs2: fix incorrect masking of permission flags for symlinks The permission flags of newly created symlinks are wrongly dropped on nilfs2 with the current umask value even though symlinks should have 777 (rwxrwxrwx) permissions: $ umask 0022 $ touch file && ln -s file symlink; ls -l file symlink -rw-r--r--. 1 root root 0 Jun 23 16:29 file lrwxr-xr-x. 1 root root 4 Jun 23 16:29 symlink -> file This fixes the bug by inserting a missing check that excludes symlinks. Link: https://lkml.kernel.org/r/1655974441-5612-1-git-send-email-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi Reported-by: Tommy Pettersson Reported-by: Ciprian Craciun Tested-by: Ryusuke Konishi Signed-off-by: Andrew Morton --- fs/nilfs2/nilfs.h | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index 1344f7d475d3..aecda4fc95f5 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -198,6 +198,9 @@ static inline int nilfs_acl_chmod(struct inode *inode) static inline int nilfs_init_acl(struct inode *inode, struct inode *dir) { + if (S_ISLNK(inode->i_mode)) + return 0; + inode->i_mode &= ~current_umask(); return 0; } From 14c99d65941538aa33edd8dc7b1bbbb593c324a2 Mon Sep 17 00:00:00 2001 From: "Gowans, James" Date: Thu, 23 Jun 2022 05:24:03 +0000 Subject: [PATCH 14/21] mm: split huge PUD on wp_huge_pud fallback MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently the implementation will split the PUD when a fallback is taken inside the create_huge_pud function. This isn't where it should be done: the splitting should be done in wp_huge_pud, just like it's done for PMDs. Reason being that if a callback is taken during create, there is no PUD yet so nothing to split, whereas if a fallback is taken when encountering a write protection fault there is something to split. It looks like this was the original intention with the commit where the splitting was introduced, but somehow it got moved to the wrong place between v1 and v2 of the patch series. Rebase mistake perhaps. Link: https://lkml.kernel.org/r/6f48d622eb8bce1ae5dd75327b0b73894a2ec407.camel@amazon.com Fixes: 327e9fd48972 ("mm: Split huge pages on write-notify or COW") Signed-off-by: James Gowans Reviewed-by: Thomas Hellström Cc: Christian König Cc: Jan H. Schönherr Signed-off-by: Andrew Morton --- mm/memory.c | 27 ++++++++++++++------------- 1 file changed, 14 insertions(+), 13 deletions(-) diff --git a/mm/memory.c b/mm/memory.c index 7a089145cad4..4cf7d4b6c950 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4798,6 +4798,19 @@ static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf) static vm_fault_t create_huge_pud(struct vm_fault *vmf) { +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ + defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) + /* No support for anonymous transparent PUD pages yet */ + if (vma_is_anonymous(vmf->vma)) + return VM_FAULT_FALLBACK; + if (vmf->vma->vm_ops->huge_fault) + return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD); +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + return VM_FAULT_FALLBACK; +} + +static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud) +{ #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) /* No support for anonymous transparent PUD pages yet */ @@ -4812,19 +4825,7 @@ static vm_fault_t create_huge_pud(struct vm_fault *vmf) split: /* COW or write-notify not handled on PUD level: split pud.*/ __split_huge_pud(vmf->vma, vmf->pud, vmf->address); -#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ - return VM_FAULT_FALLBACK; -} - -static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud) -{ -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - /* No support for anonymous transparent PUD pages yet */ - if (vma_is_anonymous(vmf->vma)) - return VM_FAULT_FALLBACK; - if (vmf->vma->vm_ops->huge_fault) - return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD); -#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +#endif /* CONFIG_TRANSPARENT_HUGEPAGE && CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ return VM_FAULT_FALLBACK; } From afe4e376ac5d568367b447ca90c12858d0935b86 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 4 Jul 2022 22:10:50 -0300 Subject: [PATCH 15/21] vfio: Move IOMMU_CAP_CACHE_COHERENCY test to after we know we have a group The test isn't going to work if a group doesn't exist. Normally this isn't a problem since VFIO isn't going to create a device if there is no group, but the special CONFIG_VFIO_NOIOMMU behavior allows bypassing this prevention. The new cap test effectively forces a group and breaks this config option. Move the cap test to vfio_group_find_or_alloc() which is the earliest time we know we have a group available and thus are not running in noiommu mode. Fixes: e8ae0e140c05 ("vfio: Require that devices support DMA cache coherence") Reported-by: Xiang Chen Tested-by: Xiang Chen Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/0-v1-e8934b490f36+f4-vfio_cap_fix_jgg@nvidia.com Signed-off-by: Alex Williamson --- drivers/vfio/vfio.c | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 61e71c1154be..e60b06f2ac22 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -549,6 +549,16 @@ static struct vfio_group *vfio_group_find_or_alloc(struct device *dev) if (!iommu_group) return ERR_PTR(-EINVAL); + /* + * VFIO always sets IOMMU_CACHE because we offer no way for userspace to + * restore cache coherency. It has to be checked here because it is only + * valid for cases where we are using iommu groups. + */ + if (!iommu_capable(dev->bus, IOMMU_CAP_CACHE_COHERENCY)) { + iommu_group_put(iommu_group); + return ERR_PTR(-EINVAL); + } + group = vfio_group_get_from_iommu(iommu_group); if (!group) group = vfio_create_group(iommu_group, VFIO_IOMMU); @@ -601,13 +611,6 @@ static int __vfio_register_dev(struct vfio_device *device, int vfio_register_group_dev(struct vfio_device *device) { - /* - * VFIO always sets IOMMU_CACHE because we offer no way for userspace to - * restore cache coherency. - */ - if (!iommu_capable(device->dev->bus, IOMMU_CAP_CACHE_COHERENCY)) - return -EINVAL; - return __vfio_register_dev(device, vfio_group_find_or_alloc(device->dev)); } From a4527e1853f8ff6e0b7c2dadad6268bd38427a31 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 4 Jul 2022 12:42:03 +0100 Subject: [PATCH 16/21] btrfs: return -EAGAIN for NOWAIT dio reads/writes on compressed and inline extents When doing a direct IO read or write, we always return -ENOTBLK when we find a compressed extent (or an inline extent) so that we fallback to buffered IO. This however is not ideal in case we are in a NOWAIT context (io_uring for example), because buffered IO can block and we currently have no support for NOWAIT semantics for buffered IO, so if we need to fallback to buffered IO we should first signal the caller that we may need to block by returning -EAGAIN instead. This behaviour can also result in short reads being returned to user space, which although it's not incorrect and user space should be able to deal with partial reads, it's somewhat surprising and even some popular applications like QEMU (Link tag #1) and MariaDB (Link tag #2) don't deal with short reads properly (or at all). The short read case happens when we try to read from a range that has a non-compressed and non-inline extent followed by a compressed extent. After having read the first extent, when we find the compressed extent we return -ENOTBLK from btrfs_dio_iomap_begin(), which results in iomap to treat the request as a short read, returning 0 (success) and waiting for previously submitted bios to complete (this happens at fs/iomap/direct-io.c:__iomap_dio_rw()). After that, and while at btrfs_file_read_iter(), we call filemap_read() to use buffered IO to read the remaining data, and pass it the number of bytes we were able to read with direct IO. Than at filemap_read() if we get a page fault error when accessing the read buffer, we return a partial read instead of an -EFAULT error, because the number of bytes previously read is greater than zero. So fix this by returning -EAGAIN for NOWAIT direct IO when we find a compressed or an inline extent. Reported-by: Dominique MARTINET Link: https://lore.kernel.org/linux-btrfs/YrrFGO4A1jS0GI0G@atmark-techno.com/ Link: https://jira.mariadb.org/browse/MDEV-27900?focusedCommentId=216582&page=com.atlassian.jira.plugin.system.issuetabpanels%3Acomment-tabpanel#comment-216582 Tested-by: Dominique MARTINET CC: stable@vger.kernel.org # 5.10+ Reviewed-by: Christoph Hellwig Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/inode.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index ba527da61732..00c9ad053a7a 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7681,7 +7681,19 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start, if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags) || em->block_start == EXTENT_MAP_INLINE) { free_extent_map(em); - ret = -ENOTBLK; + /* + * If we are in a NOWAIT context, return -EAGAIN in order to + * fallback to buffered IO. This is not only because we can + * block with buffered IO (no support for NOWAIT semantics at + * the moment) but also to avoid returning short reads to user + * space - this happens if we were able to read some data from + * previous non-compressed extents and then when we fallback to + * buffered IO, at btrfs_file_read_iter() by calling + * filemap_read(), we fail to fault in pages for the read buffer, + * in which case filemap_read() returns a short read (the number + * of bytes previously read is > 0, so it does not return -EFAULT). + */ + ret = (flags & IOMAP_NOWAIT) ? -EAGAIN : -ENOTBLK; goto unlock_err; } From 2963457829decf0c824a443238d251151ed18ff5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 30 Jun 2022 18:03:19 +0200 Subject: [PATCH 17/21] btrfs: zoned: fix a leaked bioc in read_zone_info The bioc would leak on the normal completion path and also on the RAID56 check (but that one won't happen in practice due to the invalid combination with zoned mode). Fixes: 7db1c5d14dcd ("btrfs: zoned: support dev-replace in zoned filesystems") CC: stable@vger.kernel.org # 5.16+ Reviewed-by: Anand Jain Signed-off-by: Christoph Hellwig [ update changelog ] Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/zoned.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 8aec53528efa..9892f7413705 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1736,12 +1736,14 @@ static int read_zone_info(struct btrfs_fs_info *fs_info, u64 logical, ret = btrfs_map_sblock(fs_info, BTRFS_MAP_GET_READ_MIRRORS, logical, &mapped_length, &bioc); if (ret || !bioc || mapped_length < PAGE_SIZE) { - btrfs_put_bioc(bioc); - return -EIO; + ret = -EIO; + goto out_put_bioc; } - if (bioc->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK) - return -EINVAL; + if (bioc->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK) { + ret = -EINVAL; + goto out_put_bioc; + } nofs_flag = memalloc_nofs_save(); nmirrors = (int)bioc->num_stripes; @@ -1760,7 +1762,8 @@ static int read_zone_info(struct btrfs_fs_info *fs_info, u64 logical, break; } memalloc_nofs_restore(nofs_flag); - +out_put_bioc: + btrfs_put_bioc(bioc); return ret; } From b3a3b0255797e1d395253366ba24a4cc6c8bdf9c Mon Sep 17 00:00:00 2001 From: Naohiro Aota Date: Wed, 29 Jun 2022 11:00:38 +0900 Subject: [PATCH 18/21] btrfs: zoned: drop optimization of zone finish We have an optimization in do_zone_finish() to send REQ_OP_ZONE_FINISH only when necessary, i.e. we don't send REQ_OP_ZONE_FINISH when we assume we wrote fully into the zone. The assumption is determined by "alloc_offset == capacity". This condition won't work if the last ordered extent is canceled due to some errors. In that case, we consider the zone is deactivated without sending the finish command while it's still active. This inconstancy results in activating another block group while we cannot really activate the underlying zone, which causes the active zone exceeds errors like below. BTRFS error (device nvme3n2): allocation failed flags 1, wanted 520192 tree-log 0, relocation: 0 nvme3n2: I/O Cmd(0x7d) @ LBA 160432128, 127 blocks, I/O Error (sct 0x1 / sc 0xbd) MORE DNR active zones exceeded error, dev nvme3n2, sector 0 op 0xd:(ZONE_APPEND) flags 0x4800 phys_seg 1 prio class 0 nvme3n2: I/O Cmd(0x7d) @ LBA 160432128, 127 blocks, I/O Error (sct 0x1 / sc 0xbd) MORE DNR active zones exceeded error, dev nvme3n2, sector 0 op 0xd:(ZONE_APPEND) flags 0x4800 phys_seg 1 prio class 0 Fix the issue by removing the optimization for now. Fixes: 8376d9e1ed8f ("btrfs: zoned: finish superblock zone once no space left for new SB") Reviewed-by: Johannes Thumshirn Signed-off-by: Naohiro Aota Signed-off-by: David Sterba --- fs/btrfs/zoned.c | 21 ++++++--------------- 1 file changed, 6 insertions(+), 15 deletions(-) diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 9892f7413705..e33987cefbd4 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1889,7 +1889,6 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ { struct btrfs_fs_info *fs_info = block_group->fs_info; struct map_lookup *map; - bool need_zone_finish; int ret = 0; int i; @@ -1946,12 +1945,6 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ } } - /* - * The block group is not fully allocated, so not fully written yet. We - * need to send ZONE_FINISH command to free up an active zone. - */ - need_zone_finish = !btrfs_zoned_bg_is_full(block_group); - block_group->zone_is_active = 0; block_group->alloc_offset = block_group->zone_capacity; block_group->free_space_ctl->free_space = 0; @@ -1967,15 +1960,13 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ if (device->zone_info->max_active_zones == 0) continue; - if (need_zone_finish) { - ret = blkdev_zone_mgmt(device->bdev, REQ_OP_ZONE_FINISH, - physical >> SECTOR_SHIFT, - device->zone_info->zone_size >> SECTOR_SHIFT, - GFP_NOFS); + ret = blkdev_zone_mgmt(device->bdev, REQ_OP_ZONE_FINISH, + physical >> SECTOR_SHIFT, + device->zone_info->zone_size >> SECTOR_SHIFT, + GFP_NOFS); - if (ret) - return ret; - } + if (ret) + return ret; btrfs_dev_clear_active_zone(device, physical); } From 3418357a32db6c8ce5e4417964bac1edcc3f281a Mon Sep 17 00:00:00 2001 From: Sven Schnelle Date: Wed, 6 Jul 2022 12:16:25 +0200 Subject: [PATCH 19/21] ptrace: fix clearing of JOBCTL_TRACED in ptrace_unfreeze_traced() CI reported the following splat while running the strace testsuite: [ 3976.640309] WARNING: CPU: 1 PID: 3570031 at kernel/ptrace.c:272 ptrace_check_attach+0x12e/0x178 [ 3976.640391] CPU: 1 PID: 3570031 Comm: strace Tainted: G OE 5.19.0-20220624.rc3.git0.ee819a77d4e7.300.fc36.s390x #1 [ 3976.640410] Hardware name: IBM 3906 M04 704 (z/VM 7.1.0) [ 3976.640452] Call Trace: [ 3976.640454] [<00000000ab4b645a>] ptrace_check_attach+0x132/0x178 [ 3976.640457] ([<00000000ab4b6450>] ptrace_check_attach+0x128/0x178) [ 3976.640460] [<00000000ab4b6cde>] __s390x_sys_ptrace+0x86/0x160 [ 3976.640463] [<00000000ac03fcec>] __do_syscall+0x1d4/0x200 [ 3976.640468] [<00000000ac04e312>] system_call+0x82/0xb0 [ 3976.640470] Last Breaking-Event-Address: [ 3976.640471] [<00000000ab4ea3c8>] wait_task_inactive+0x98/0x190 This is because JOBCTL_TRACED is set, but the task is not in TASK_TRACED state. Caused by ptrace_unfreeze_traced() which does: task->jobctl &= ~TASK_TRACED but it should be: task->jobctl &= ~JOBCTL_TRACED Fixes: 31cae1eaae4f ("sched,signal,ptrace: Rework TASK_TRACED, TASK_STOPPED state") Signed-off-by: Sven Schnelle Link: https://lkml.kernel.org/r/20220706101625.2100298-1-svens@linux.ibm.com Link: https://lkml.kernel.org/r/YrHA5UkJLornOdCz@li-4a3a4a4c-28e5-11b2-a85c-a8d192c6f089.ibm.com Link: https://bugzilla.redhat.com/show_bug.cgi?id=2101641 Acked-by: Peter Zijlstra (Intel) Tested-by: Alexander Gordeev Tested-by: Linus Torvalds Signed-off-by: Eric W. Biederman --- kernel/ptrace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 156a99283b11..1893d909e45c 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -222,7 +222,7 @@ static void ptrace_unfreeze_traced(struct task_struct *task) if (lock_task_sighand(task, &flags)) { task->jobctl &= ~JOBCTL_PTRACE_FROZEN; if (__fatal_signal_pending(task)) { - task->jobctl &= ~TASK_TRACED; + task->jobctl &= ~JOBCTL_TRACED; wake_up_state(task, __TASK_TRACED); } unlock_task_sighand(task, &flags); From d5b36a4dbd06c5e8e36ca8ccc552f679069e2946 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 11 Jul 2022 18:16:25 +0200 Subject: [PATCH 20/21] fix race between exit_itimers() and /proc/pid/timers As Chris explains, the comment above exit_itimers() is not correct, we can race with proc_timers_seq_ops. Change exit_itimers() to clear signal->posix_timers with ->siglock held. Cc: Reported-by: chris@accessvector.net Signed-off-by: Oleg Nesterov Signed-off-by: Linus Torvalds --- fs/exec.c | 2 +- include/linux/sched/task.h | 2 +- kernel/exit.c | 2 +- kernel/time/posix-timers.c | 19 ++++++++++++++----- 4 files changed, 17 insertions(+), 8 deletions(-) diff --git a/fs/exec.c b/fs/exec.c index 0989fb8472a1..778123259e42 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1301,7 +1301,7 @@ int begin_new_exec(struct linux_binprm * bprm) bprm->mm = NULL; #ifdef CONFIG_POSIX_TIMERS - exit_itimers(me->signal); + exit_itimers(me); flush_itimer_signals(); #endif diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 505aaf9fe477..81cab4b01edc 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -85,7 +85,7 @@ static inline void exit_thread(struct task_struct *tsk) extern __noreturn void do_group_exit(int); extern void exit_files(struct task_struct *); -extern void exit_itimers(struct signal_struct *); +extern void exit_itimers(struct task_struct *); extern pid_t kernel_clone(struct kernel_clone_args *kargs); struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node); diff --git a/kernel/exit.c b/kernel/exit.c index f072959fcab7..64c938ce36fe 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -766,7 +766,7 @@ void __noreturn do_exit(long code) #ifdef CONFIG_POSIX_TIMERS hrtimer_cancel(&tsk->signal->real_timer); - exit_itimers(tsk->signal); + exit_itimers(tsk); #endif if (tsk->mm) setmax_mm_hiwater_rss(&tsk->signal->maxrss, tsk->mm); diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 1cd10b102c51..5dead89308b7 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -1051,15 +1051,24 @@ retry_delete: } /* - * This is called by do_exit or de_thread, only when there are no more - * references to the shared signal_struct. + * This is called by do_exit or de_thread, only when nobody else can + * modify the signal->posix_timers list. Yet we need sighand->siglock + * to prevent the race with /proc/pid/timers. */ -void exit_itimers(struct signal_struct *sig) +void exit_itimers(struct task_struct *tsk) { + struct list_head timers; struct k_itimer *tmr; - while (!list_empty(&sig->posix_timers)) { - tmr = list_entry(sig->posix_timers.next, struct k_itimer, list); + if (list_empty(&tsk->signal->posix_timers)) + return; + + spin_lock_irq(&tsk->sighand->siglock); + list_replace_init(&tsk->signal->posix_timers, &timers); + spin_unlock_irq(&tsk->sighand->siglock); + + while (!list_empty(&timers)) { + tmr = list_first_entry(&timers, struct k_itimer, list); itimer_delete(tmr); } } From e69a66147d49506062cd837f3b230ee3e98102ab Mon Sep 17 00:00:00 2001 From: Aaron Tomlin Date: Mon, 11 Jul 2022 18:17:19 +0100 Subject: [PATCH 21/21] module: kallsyms: Ensure preemption in add_kallsyms() with PREEMPT_RT The commit 08126db5ff73 ("module: kallsyms: Fix suspicious rcu usage") under PREEMPT_RT=y, disabling preemption introduced an unbounded latency since the loop is not fixed. This change caused a regression since previously preemption was not disabled and we would dereference RCU-protected pointers explicitly. That being said, these pointers cannot change. Before kallsyms-specific data is prepared/or set-up, we ensure that the unformed module is known to be unique i.e. does not already exist (see load_module()). Therefore, we can fix this by using the common and more appropriate RCU flavour as this section of code can be safely preempted. Reported-by: Steven Rostedt Fixes: 08126db5ff73 ("module: kallsyms: Fix suspicious rcu usage") Signed-off-by: Aaron Tomlin Signed-off-by: Luis Chamberlain --- kernel/module/kallsyms.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) diff --git a/kernel/module/kallsyms.c b/kernel/module/kallsyms.c index 18c23545b984..77e75bead569 100644 --- a/kernel/module/kallsyms.c +++ b/kernel/module/kallsyms.c @@ -176,14 +176,14 @@ void add_kallsyms(struct module *mod, const struct load_info *info) mod->kallsyms = (void __rcu *)mod->init_layout.base + info->mod_kallsyms_init_off; - preempt_disable(); + rcu_read_lock(); /* The following is safe since this pointer cannot change */ - rcu_dereference_sched(mod->kallsyms)->symtab = (void *)symsec->sh_addr; - rcu_dereference_sched(mod->kallsyms)->num_symtab = symsec->sh_size / sizeof(Elf_Sym); + rcu_dereference(mod->kallsyms)->symtab = (void *)symsec->sh_addr; + rcu_dereference(mod->kallsyms)->num_symtab = symsec->sh_size / sizeof(Elf_Sym); /* Make sure we get permanent strtab: don't use info->strtab. */ - rcu_dereference_sched(mod->kallsyms)->strtab = + rcu_dereference(mod->kallsyms)->strtab = (void *)info->sechdrs[info->index.str].sh_addr; - rcu_dereference_sched(mod->kallsyms)->typetab = mod->init_layout.base + info->init_typeoffs; + rcu_dereference(mod->kallsyms)->typetab = mod->init_layout.base + info->init_typeoffs; /* * Now populate the cut down core kallsyms for after init @@ -193,20 +193,20 @@ void add_kallsyms(struct module *mod, const struct load_info *info) mod->core_kallsyms.strtab = s = mod->data_layout.base + info->stroffs; mod->core_kallsyms.typetab = mod->data_layout.base + info->core_typeoffs; strtab_size = info->core_typeoffs - info->stroffs; - src = rcu_dereference_sched(mod->kallsyms)->symtab; - for (ndst = i = 0; i < rcu_dereference_sched(mod->kallsyms)->num_symtab; i++) { - rcu_dereference_sched(mod->kallsyms)->typetab[i] = elf_type(src + i, info); + src = rcu_dereference(mod->kallsyms)->symtab; + for (ndst = i = 0; i < rcu_dereference(mod->kallsyms)->num_symtab; i++) { + rcu_dereference(mod->kallsyms)->typetab[i] = elf_type(src + i, info); if (i == 0 || is_livepatch_module(mod) || is_core_symbol(src + i, info->sechdrs, info->hdr->e_shnum, info->index.pcpu)) { ssize_t ret; mod->core_kallsyms.typetab[ndst] = - rcu_dereference_sched(mod->kallsyms)->typetab[i]; + rcu_dereference(mod->kallsyms)->typetab[i]; dst[ndst] = src[i]; dst[ndst++].st_name = s - mod->core_kallsyms.strtab; ret = strscpy(s, - &rcu_dereference_sched(mod->kallsyms)->strtab[src[i].st_name], + &rcu_dereference(mod->kallsyms)->strtab[src[i].st_name], strtab_size); if (ret < 0) break; @@ -214,7 +214,7 @@ void add_kallsyms(struct module *mod, const struct load_info *info) strtab_size -= ret + 1; } } - preempt_enable(); + rcu_read_unlock(); mod->core_kallsyms.num_symtab = ndst; }