From cd3f8467afd470ccab0de2fbc7c76664af4a0bac Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Tue, 24 Sep 2024 21:10:23 +0100 Subject: mm: refactor mm_access() to not return NULL mm_access() can return NULL if the mm is not found, but this is handled the same as an error in all callers, with some translating this into an -ESRCH error. Only proc_mem_open() returns NULL if no mm is found, however in this case it is clearer and makes more sense to explicitly handle the error. Additionally we take the opportunity to refactor the function to eliminate unnecessary nesting. Simplify things by simply returning -ESRCH if no mm is found - this both eliminates confusing use of the IS_ERR_OR_NULL() macro, and simplifies callers which would return -ESRCH by returning this error directly. [lorenzo.stoakes@oracle.com: prefer neater pointer error comparison] Link: https://lkml.kernel.org/r/2fae1834-749a-45e1-8594-5e5979cf7103@lucifer.local Link: https://lkml.kernel.org/r/20240924201023.193135-1-lorenzo.stoakes@oracle.com Signed-off-by: Lorenzo Stoakes Suggested-by: Arnd Bergmann Cc: Al Viro Signed-off-by: Andrew Morton --- kernel/fork.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/fork.c b/kernel/fork.c index 22f43721d031..b2ab422f6230 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1546,8 +1546,9 @@ struct mm_struct *mm_access(struct task_struct *task, unsigned int mode) return ERR_PTR(err); mm = get_task_mm(task); - if (mm && mm != current->mm && - !ptrace_may_access(task, mode)) { + if (!mm) { + mm = ERR_PTR(-ESRCH); + } else if (mm != current->mm && !ptrace_may_access(task, mode)) { mmput(mm); mm = ERR_PTR(-EACCES); } -- cgit v1.2.3 From f2f484085ef1a2bb5aea861a06bc6b4dc50d2ab8 Mon Sep 17 00:00:00 2001 From: Nanyong Sun Date: Thu, 26 Sep 2024 15:49:22 +0800 Subject: mm: move mm flags to mm_types.h The types of mm flags are now far beyond the core dump related features. This patch moves mm flags from linux/sched/coredump.h to linux/mm_types.h. The linux/sched/coredump.h has include the mm_types.h, so the C files related to coredump does not need to change head file inclusion. In addition, the inclusion of sched/coredump.h now can be deleted from the C files that irrelevant to core dump. Link: https://lkml.kernel.org/r/20240926074922.2721274-1-sunnanyong@huawei.com Signed-off-by: Nanyong Sun Cc: Kefeng Wang Cc: Masami Hiramatsu Cc: Matthew Wilcox Cc: Oleg Nesterov Cc: Peter Zijlstra Signed-off-by: Andrew Morton --- kernel/events/uprobes.c | 1 - kernel/fork.c | 1 - 2 files changed, 2 deletions(-) (limited to 'kernel') diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 4b52cb2ae6d6..75ac18a3ac0f 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -15,7 +15,6 @@ #include #include #include -#include #include #include /* anon_vma_prepare */ #include diff --git a/kernel/fork.c b/kernel/fork.c index b2ab422f6230..61a4abd628f3 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -16,7 +16,6 @@ #include #include #include -#include #include #include #include -- cgit v1.2.3 From afe789b7367ad43ba8f079981d40851f8bd319ce Mon Sep 17 00:00:00 2001 From: John Hubbard Date: Tue, 8 Oct 2024 19:50:24 -0700 Subject: kaslr: rename physmem_end and PHYSMEM_END to direct_map_physmem_end For clarity. It's increasingly hard to reason about the code, when KASLR is moving around the boundaries. In this case where KASLR is randomizing the location of the kernel image within physical memory, the maximum number of address bits for physical memory has not changed. What has changed is the ending address of memory that is allowed to be directly mapped by the kernel. Let's name the variable, and the associated macro accordingly. Also, enhance the comment above the direct_map_physmem_end definition, to further clarify how this all works. Link: https://lkml.kernel.org/r/20241009025024.89813-1-jhubbard@nvidia.com Signed-off-by: John Hubbard Reviewed-by: Pankaj Gupta Acked-by: David Hildenbrand Acked-by: Will Deacon Reviewed-by: Mike Rapoport (Microsoft) Cc: Thomas Gleixner Cc: Alistair Popple Cc: Jordan Niethe Signed-off-by: Andrew Morton --- kernel/resource.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/resource.c b/kernel/resource.c index 4101016e8b20..d2c8143ae4ff 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -1869,7 +1869,7 @@ static resource_size_t gfr_start(struct resource *base, resource_size_t size, if (flags & GFR_DESCENDING) { resource_size_t end; - end = min_t(resource_size_t, base->end, PHYSMEM_END); + end = min_t(resource_size_t, base->end, DIRECT_MAP_PHYSMEM_END); return end - size + 1; } @@ -1886,7 +1886,7 @@ static bool gfr_continue(struct resource *base, resource_size_t addr, * @size did not wrap 0. */ return addr > addr - size && - addr <= min_t(resource_size_t, base->end, PHYSMEM_END); + addr <= min_t(resource_size_t, base->end, DIRECT_MAP_PHYSMEM_END); } static resource_size_t gfr_next(resource_size_t addr, resource_size_t size, -- cgit v1.2.3 From 0c133b1e78cd34dd9d18da707dc6f46170e9129e Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" Date: Wed, 23 Oct 2024 19:27:07 +0300 Subject: module: prepare to handle ROX allocations for text In order to support ROX allocations for module text, it is necessary to handle modifications to the code, such as relocations and alternatives patching, without write access to that memory. One option is to use text patching, but this would make module loading extremely slow and will expose executable code that is not finally formed. A better way is to have memory allocated with ROX permissions contain invalid instructions and keep a writable, but not executable copy of the module text. The relocations and alternative patches would be done on the writable copy using the addresses of the ROX memory. Once the module is completely ready, the updated text will be copied to ROX memory using text patching in one go and the writable copy will be freed. Add support for that to module initialization code and provide necessary interfaces in execmem. Link: https://lkml.kernel.org/r/20241023162711.2579610-5-rppt@kernel.org Signed-off-by: Mike Rapoport (Microsoft) Reviewd-by: Luis Chamberlain Tested-by: kdevops Cc: Andreas Larsson Cc: Andy Lutomirski Cc: Ard Biesheuvel Cc: Arnd Bergmann Cc: Borislav Petkov (AMD) Cc: Brian Cain Cc: Catalin Marinas Cc: Christophe Leroy Cc: Christoph Hellwig Cc: Dave Hansen Cc: Dinh Nguyen Cc: Geert Uytterhoeven Cc: Guo Ren Cc: Helge Deller Cc: Huacai Chen Cc: Ingo Molnar Cc: Johannes Berg Cc: John Paul Adrian Glaubitz Cc: Kent Overstreet Cc: Liam R. Howlett Cc: Mark Rutland Cc: Masami Hiramatsu (Google) Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Oleg Nesterov Cc: Palmer Dabbelt Cc: Peter Zijlstra Cc: Richard Weinberger Cc: Russell King Cc: Song Liu Cc: Stafford Horne Cc: Steven Rostedt (Google) Cc: Suren Baghdasaryan Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Uladzislau Rezki (Sony) Cc: Vineet Gupta Cc: Will Deacon Signed-off-by: Andrew Morton --- kernel/module/debug_kmemleak.c | 3 +- kernel/module/main.c | 74 ++++++++++++++++++++++++++++++++++++++---- kernel/module/strict_rwx.c | 3 ++ 3 files changed, 72 insertions(+), 8 deletions(-) (limited to 'kernel') diff --git a/kernel/module/debug_kmemleak.c b/kernel/module/debug_kmemleak.c index b4cc03842d70..df873dad049d 100644 --- a/kernel/module/debug_kmemleak.c +++ b/kernel/module/debug_kmemleak.c @@ -14,7 +14,8 @@ void kmemleak_load_module(const struct module *mod, { /* only scan writable, non-executable sections */ for_each_mod_mem_type(type) { - if (type != MOD_DATA && type != MOD_INIT_DATA) + if (type != MOD_DATA && type != MOD_INIT_DATA && + !mod->mem[type].is_rox) kmemleak_no_scan(mod->mem[type].base); } } diff --git a/kernel/module/main.c b/kernel/module/main.c index 49b9bca9de12..73b588fe98d4 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -1189,6 +1189,18 @@ void __weak module_arch_freeing_init(struct module *mod) { } +void *__module_writable_address(struct module *mod, void *loc) +{ + for_class_mod_mem_type(type, text) { + struct module_memory *mem = &mod->mem[type]; + + if (loc >= mem->base && loc < mem->base + mem->size) + return loc + (mem->rw_copy - mem->base); + } + + return loc; +} + static int module_memory_alloc(struct module *mod, enum mod_mem_type type) { unsigned int size = PAGE_ALIGN(mod->mem[type].size); @@ -1206,6 +1218,23 @@ static int module_memory_alloc(struct module *mod, enum mod_mem_type type) if (!ptr) return -ENOMEM; + mod->mem[type].base = ptr; + + if (execmem_is_rox(execmem_type)) { + ptr = vzalloc(size); + + if (!ptr) { + execmem_free(mod->mem[type].base); + return -ENOMEM; + } + + mod->mem[type].rw_copy = ptr; + mod->mem[type].is_rox = true; + } else { + mod->mem[type].rw_copy = mod->mem[type].base; + memset(mod->mem[type].base, 0, size); + } + /* * The pointer to these blocks of memory are stored on the module * structure and we keep that around so long as the module is @@ -1219,16 +1248,17 @@ static int module_memory_alloc(struct module *mod, enum mod_mem_type type) */ kmemleak_not_leak(ptr); - memset(ptr, 0, size); - mod->mem[type].base = ptr; - return 0; } static void module_memory_free(struct module *mod, enum mod_mem_type type, bool unload_codetags) { - void *ptr = mod->mem[type].base; + struct module_memory *mem = &mod->mem[type]; + void *ptr = mem->base; + + if (mem->is_rox) + vfree(mem->rw_copy); if (!unload_codetags && mod_mem_type_is_core_data(type)) return; @@ -2251,6 +2281,7 @@ static int move_module(struct module *mod, struct load_info *info) for_each_mod_mem_type(type) { if (!mod->mem[type].size) { mod->mem[type].base = NULL; + mod->mem[type].rw_copy = NULL; continue; } @@ -2267,11 +2298,14 @@ static int move_module(struct module *mod, struct load_info *info) void *dest; Elf_Shdr *shdr = &info->sechdrs[i]; enum mod_mem_type type = shdr->sh_entsize >> SH_ENTSIZE_TYPE_SHIFT; + unsigned long offset = shdr->sh_entsize & SH_ENTSIZE_OFFSET_MASK; + unsigned long addr; if (!(shdr->sh_flags & SHF_ALLOC)) continue; - dest = mod->mem[type].base + (shdr->sh_entsize & SH_ENTSIZE_OFFSET_MASK); + addr = (unsigned long)mod->mem[type].base + offset; + dest = mod->mem[type].rw_copy + offset; if (shdr->sh_type != SHT_NOBITS) { /* @@ -2293,7 +2327,7 @@ static int move_module(struct module *mod, struct load_info *info) * users of info can keep taking advantage and using the newly * minted official memory area. */ - shdr->sh_addr = (unsigned long)dest; + shdr->sh_addr = addr; pr_debug("\t0x%lx 0x%.8lx %s\n", (long)shdr->sh_addr, (long)shdr->sh_size, info->secstrings + shdr->sh_name); } @@ -2441,8 +2475,17 @@ int __weak module_finalize(const Elf_Ehdr *hdr, return 0; } +int __weak module_post_finalize(const Elf_Ehdr *hdr, + const Elf_Shdr *sechdrs, + struct module *me) +{ + return 0; +} + static int post_relocation(struct module *mod, const struct load_info *info) { + int ret; + /* Sort exception table now relocations are done. */ sort_extable(mod->extable, mod->extable + mod->num_exentries); @@ -2454,7 +2497,24 @@ static int post_relocation(struct module *mod, const struct load_info *info) add_kallsyms(mod, info); /* Arch-specific module finalizing. */ - return module_finalize(info->hdr, info->sechdrs, mod); + ret = module_finalize(info->hdr, info->sechdrs, mod); + if (ret) + return ret; + + for_each_mod_mem_type(type) { + struct module_memory *mem = &mod->mem[type]; + + if (mem->is_rox) { + if (!execmem_update_copy(mem->base, mem->rw_copy, + mem->size)) + return -ENOMEM; + + vfree(mem->rw_copy); + mem->rw_copy = NULL; + } + } + + return module_post_finalize(info->hdr, info->sechdrs, mod); } /* Call module constructors. */ diff --git a/kernel/module/strict_rwx.c b/kernel/module/strict_rwx.c index c45caa4690e5..239e5013359d 100644 --- a/kernel/module/strict_rwx.c +++ b/kernel/module/strict_rwx.c @@ -34,6 +34,9 @@ int module_enable_text_rox(const struct module *mod) for_class_mod_mem_type(type, text) { int ret; + if (mod->mem[type].is_rox) + continue; + if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX)) ret = module_set_memory(mod, type, set_memory_rox); else -- cgit v1.2.3 From 0db6f8d7820a4b788565dac8eed52bfc2c3216da Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Wed, 23 Oct 2024 10:07:56 -0700 Subject: alloc_tag: load module tags into separate contiguous memory When a module gets unloaded there is a possibility that some of the allocations it made are still used and therefore the allocation tags corresponding to these allocations are still referenced. As such, the memory for these tags can't be freed. This is currently handled as an abnormal situation and module's data section is not being unloaded. To handle this situation without keeping module's data in memory, allow codetags with longer lifespan than the module to be loaded into their own separate memory. The in-use memory areas and gaps after module unloading in this separate memory are tracked using maple trees. Allocation tags arrange their separate memory so that it is virtually contiguous and that will allow simple allocation tag indexing later on in this patchset. The size of this virtually contiguous memory is set to store up to 100000 allocation tags. [surenb@google.com: fix empty codetag module section handling] Link: https://lkml.kernel.org/r/20241101000017.3856204-1-surenb@google.com [akpm@linux-foundation.org: update comment, per Dan] Link: https://lkml.kernel.org/r/20241023170759.999909-4-surenb@google.com Signed-off-by: Suren Baghdasaryan Reviewed-by: Pasha Tatashin Cc: Ard Biesheuvel Cc: Arnd Bergmann Cc: Borislav Petkov (AMD) Cc: Christoph Hellwig Cc: Daniel Gomez Cc: David Hildenbrand Cc: Davidlohr Bueso Cc: David Rientjes Cc: Dennis Zhou Cc: Johannes Weiner Cc: John Hubbard Cc: Jonathan Corbet Cc: Joonsoo Kim Cc: Kalesh Singh Cc: Kees Cook Cc: Kent Overstreet Cc: Liam R. Howlett Cc: Luis Chamberlain Cc: Matthew Wilcox Cc: Michal Hocko Cc: Mike Rapoport (Microsoft) Cc: Minchan Kim Cc: Paul E. McKenney Cc: Petr Pavlu Cc: Roman Gushchin Cc: Sami Tolvanen Cc: Sourav Panda Cc: Steven Rostedt (Google) Cc: Thomas Gleixner Cc: Thomas Huth Cc: Uladzislau Rezki (Sony) Cc: Vlastimil Babka Cc: Xiongwei Song Cc: Yu Zhao Cc: Dan Carpenter Signed-off-by: Andrew Morton --- kernel/module/main.c | 84 ++++++++++++++++++++++++++++++++++++---------------- 1 file changed, 58 insertions(+), 26 deletions(-) (limited to 'kernel') diff --git a/kernel/module/main.c b/kernel/module/main.c index 73b588fe98d4..00c16f5c5568 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -1251,22 +1251,17 @@ static int module_memory_alloc(struct module *mod, enum mod_mem_type type) return 0; } -static void module_memory_free(struct module *mod, enum mod_mem_type type, - bool unload_codetags) +static void module_memory_free(struct module *mod, enum mod_mem_type type) { struct module_memory *mem = &mod->mem[type]; - void *ptr = mem->base; if (mem->is_rox) vfree(mem->rw_copy); - if (!unload_codetags && mod_mem_type_is_core_data(type)) - return; - - execmem_free(ptr); + execmem_free(mem->base); } -static void free_mod_mem(struct module *mod, bool unload_codetags) +static void free_mod_mem(struct module *mod) { for_each_mod_mem_type(type) { struct module_memory *mod_mem = &mod->mem[type]; @@ -1277,25 +1272,20 @@ static void free_mod_mem(struct module *mod, bool unload_codetags) /* Free lock-classes; relies on the preceding sync_rcu(). */ lockdep_free_key_range(mod_mem->base, mod_mem->size); if (mod_mem->size) - module_memory_free(mod, type, unload_codetags); + module_memory_free(mod, type); } /* MOD_DATA hosts mod, so free it at last */ lockdep_free_key_range(mod->mem[MOD_DATA].base, mod->mem[MOD_DATA].size); - module_memory_free(mod, MOD_DATA, unload_codetags); + module_memory_free(mod, MOD_DATA); } /* Free a module, remove from lists, etc. */ static void free_module(struct module *mod) { - bool unload_codetags; - trace_module_free(mod); - unload_codetags = codetag_unload_module(mod); - if (!unload_codetags) - pr_warn("%s: memory allocation(s) from the module still alive, cannot unload cleanly\n", - mod->name); + codetag_unload_module(mod); mod_sysfs_teardown(mod); @@ -1338,7 +1328,7 @@ static void free_module(struct module *mod) kfree(mod->args); percpu_modfree(mod); - free_mod_mem(mod, unload_codetags); + free_mod_mem(mod); } void *__symbol_get(const char *symbol) @@ -1603,6 +1593,20 @@ static void __layout_sections(struct module *mod, struct load_info *info, bool i if (WARN_ON_ONCE(type == MOD_INVALID)) continue; + /* + * Do not allocate codetag memory as we load it into + * preallocated contiguous memory. + */ + if (codetag_needs_module_section(mod, sname, s->sh_size)) { + /* + * s->sh_entsize won't be used but populate the + * type field to avoid confusion. + */ + s->sh_entsize = ((unsigned long)(type) & SH_ENTSIZE_TYPE_MASK) + << SH_ENTSIZE_TYPE_SHIFT; + continue; + } + s->sh_entsize = module_get_offset_and_type(mod, type, s, i); pr_debug("\t%s\n", sname); } @@ -2277,6 +2281,7 @@ static int move_module(struct module *mod, struct load_info *info) int i; enum mod_mem_type t = 0; int ret = -ENOMEM; + bool codetag_section_found = false; for_each_mod_mem_type(type) { if (!mod->mem[type].size) { @@ -2288,7 +2293,7 @@ static int move_module(struct module *mod, struct load_info *info) ret = module_memory_alloc(mod, type); if (ret) { t = type; - goto out_enomem; + goto out_err; } } @@ -2297,15 +2302,37 @@ static int move_module(struct module *mod, struct load_info *info) for (i = 0; i < info->hdr->e_shnum; i++) { void *dest; Elf_Shdr *shdr = &info->sechdrs[i]; - enum mod_mem_type type = shdr->sh_entsize >> SH_ENTSIZE_TYPE_SHIFT; - unsigned long offset = shdr->sh_entsize & SH_ENTSIZE_OFFSET_MASK; + const char *sname; unsigned long addr; if (!(shdr->sh_flags & SHF_ALLOC)) continue; - addr = (unsigned long)mod->mem[type].base + offset; - dest = mod->mem[type].rw_copy + offset; + sname = info->secstrings + shdr->sh_name; + /* + * Load codetag sections separately as they might still be used + * after module unload. + */ + if (codetag_needs_module_section(mod, sname, shdr->sh_size)) { + dest = codetag_alloc_module_section(mod, sname, shdr->sh_size, + arch_mod_section_prepend(mod, i), shdr->sh_addralign); + if (WARN_ON(!dest)) { + ret = -EINVAL; + goto out_err; + } + if (IS_ERR(dest)) { + ret = PTR_ERR(dest); + goto out_err; + } + addr = (unsigned long)dest; + codetag_section_found = true; + } else { + enum mod_mem_type type = shdr->sh_entsize >> SH_ENTSIZE_TYPE_SHIFT; + unsigned long offset = shdr->sh_entsize & SH_ENTSIZE_OFFSET_MASK; + + addr = (unsigned long)mod->mem[type].base + offset; + dest = mod->mem[type].rw_copy + offset; + } if (shdr->sh_type != SHT_NOBITS) { /* @@ -2317,7 +2344,7 @@ static int move_module(struct module *mod, struct load_info *info) if (i == info->index.mod && (WARN_ON_ONCE(shdr->sh_size != sizeof(struct module)))) { ret = -ENOEXEC; - goto out_enomem; + goto out_err; } memcpy(dest, (void *)shdr->sh_addr, shdr->sh_size); } @@ -2333,9 +2360,12 @@ static int move_module(struct module *mod, struct load_info *info) } return 0; -out_enomem: +out_err: for (t--; t >= 0; t--) - module_memory_free(mod, t, true); + module_memory_free(mod, t); + if (codetag_section_found) + codetag_free_module_sections(mod); + return ret; } @@ -2456,6 +2486,8 @@ static struct module *layout_and_allocate(struct load_info *info, int flags) /* Module has been copied to its final place now: return it. */ mod = (void *)info->sechdrs[info->index.mod].sh_addr; kmemleak_load_module(mod, info); + codetag_module_replaced(info->mod, mod); + return mod; } @@ -2465,7 +2497,7 @@ static void module_deallocate(struct module *mod, struct load_info *info) percpu_modfree(mod); module_arch_freeing_init(mod); - free_mod_mem(mod, true); + free_mod_mem(mod); } int __weak module_finalize(const Elf_Ehdr *hdr, -- cgit v1.2.3 From 7d3e93eca3ca28bb5927b09b9b603c0c995bcd24 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sat, 5 Oct 2024 21:01:13 +0100 Subject: mm: use page_pgoff() in more places There are several places which currently open-code page_pgoff(), convert them to call it. Link: https://lkml.kernel.org/r/20241005200121.3231142-3-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- kernel/futex/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/futex/core.c b/kernel/futex/core.c index 136768ae2637..342dc4dd328b 100644 --- a/kernel/futex/core.c +++ b/kernel/futex/core.c @@ -399,7 +399,7 @@ again: key->both.offset |= FUT_OFF_INODE; /* inode-based key */ key->shared.i_seq = get_inode_sequence_number(inode); - key->shared.pgoff = folio->index + folio_page_idx(folio, page); + key->shared.pgoff = page_pgoff(folio, page); rcu_read_unlock(); } -- cgit v1.2.3