- Linux-stable-mirror - lists.linaro.org

FAILED: patch "[PATCH] x86/its: explicitly manage permissions for ITS pages" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x a82b26451de126a5ae130361081986bc459afe9b # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025062014-smuggler-flip-4aaf@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From a82b26451de126a5ae130361081986bc459afe9b Mon Sep 17 00:00:00 2001 From: "Peter Zijlstra (Intel)" <peterz(a)infradead.org> Date: Tue, 3 Jun 2025 14:14:44 +0300 Subject: [PATCH] x86/its: explicitly manage permissions for ITS pages execmem_alloc() sets permissions differently depending on the kernel configuration, CPU support for PSE and whether a page is allocated before or after mark_rodata_ro(). Add tracking for pages allocated for ITS when patching the core kernel and make sure the permissions for ITS pages are explicitly managed for both kernel and module allocations. Fixes: 872df34d7c51 ("x86/its: Use dynamic thunks for indirect branches") Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Co-developed-by: Mike Rapoport (Microsoft) <rppt(a)kernel.org> Signed-off-by: Mike Rapoport (Microsoft) <rppt(a)kernel.org> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Reviewed-by: Nikolay Borisov <nik.borisov(a)suse.com> Cc: stable(a)vger.kernel.org Link: https://lkml.kernel.org/r/20250603111446.2609381-5-rppt@kernel.org diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index b50fe6ce4655..6455f7f751b3 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -116,6 +116,24 @@ static struct module *its_mod; #endif static void *its_page; static unsigned int its_offset; +struct its_array its_pages; + +static void *__its_alloc(struct its_array *pages) +{ + void *page __free(execmem) = execmem_alloc(EXECMEM_MODULE_TEXT, PAGE_SIZE); + if (!page) + return NULL; + + void *tmp = krealloc(pages->pages, (pages->num+1) * sizeof(void *), + GFP_KERNEL); + if (!tmp) + return NULL; + + pages->pages = tmp; + pages->pages[pages->num++] = page; + + return no_free_ptr(page); +} /* Initialize a thunk with the "jmp *reg; int3" instructions. */ static void *its_init_thunk(void *thunk, int reg) @@ -151,6 +169,21 @@ static void *its_init_thunk(void *thunk, int reg) return thunk + offset; } +static void its_pages_protect(struct its_array *pages) +{ + for (int i = 0; i < pages->num; i++) { + void *page = pages->pages[i]; + execmem_restore_rox(page, PAGE_SIZE); + } +} + +static void its_fini_core(void) +{ + if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX)) + its_pages_protect(&its_pages); + kfree(its_pages.pages); +} + #ifdef CONFIG_MODULES void its_init_mod(struct module *mod) { @@ -173,10 +206,8 @@ void its_fini_mod(struct module *mod) its_page = NULL; mutex_unlock(&text_mutex); - for (int i = 0; i < mod->arch.its_pages.num; i++) { - void *page = mod->arch.its_pages.pages[i]; - execmem_restore_rox(page, PAGE_SIZE); - } + if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX)) + its_pages_protect(&mod->arch.its_pages); } void its_free_mod(struct module *mod) @@ -194,28 +225,23 @@ void its_free_mod(struct module *mod) static void *its_alloc(void) { - void *page __free(execmem) = execmem_alloc(EXECMEM_MODULE_TEXT, PAGE_SIZE); + struct its_array *pages = &its_pages; + void *page; +#ifdef CONFIG_MODULE + if (its_mod) + pages = &its_mod->arch.its_pages; +#endif + + page = __its_alloc(pages); if (!page) return NULL; -#ifdef CONFIG_MODULES - if (its_mod) { - struct its_array *pages = &its_mod->arch.its_pages; - void *tmp = krealloc(pages->pages, - (pages->num+1) * sizeof(void *), - GFP_KERNEL); - if (!tmp) - return NULL; + execmem_make_temp_rw(page, PAGE_SIZE); + if (pages == &its_pages) + set_memory_x((unsigned long)page, 1); - pages->pages = tmp; - pages->pages[pages->num++] = page; - - execmem_make_temp_rw(page, PAGE_SIZE); - } -#endif /* CONFIG_MODULES */ - - return no_free_ptr(page); + return page; } static void *its_allocate_thunk(int reg) @@ -269,7 +295,9 @@ u8 *its_static_thunk(int reg) return thunk; } -#endif +#else +static inline void its_fini_core(void) {} +#endif /* CONFIG_MITIGATION_ITS */ /* * Nomenclature for variable names to simplify and clarify this code and ease @@ -2339,6 +2367,8 @@ void __init alternative_instructions(void) apply_retpolines(__retpoline_sites, __retpoline_sites_end); apply_returns(__return_sites, __return_sites_end); + its_fini_core(); + /* * Adjust all CALL instructions to point to func()-10, including * those in .altinstr_replacement.

1 week, 5 days

1
0
0 0

FAILED: patch "[PATCH] x86/its: explicitly manage permissions for ITS pages" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x a82b26451de126a5ae130361081986bc459afe9b # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025062014-unvaried-ranch-2d7c@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From a82b26451de126a5ae130361081986bc459afe9b Mon Sep 17 00:00:00 2001 From: "Peter Zijlstra (Intel)" <peterz(a)infradead.org> Date: Tue, 3 Jun 2025 14:14:44 +0300 Subject: [PATCH] x86/its: explicitly manage permissions for ITS pages execmem_alloc() sets permissions differently depending on the kernel configuration, CPU support for PSE and whether a page is allocated before or after mark_rodata_ro(). Add tracking for pages allocated for ITS when patching the core kernel and make sure the permissions for ITS pages are explicitly managed for both kernel and module allocations. Fixes: 872df34d7c51 ("x86/its: Use dynamic thunks for indirect branches") Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Co-developed-by: Mike Rapoport (Microsoft) <rppt(a)kernel.org> Signed-off-by: Mike Rapoport (Microsoft) <rppt(a)kernel.org> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Reviewed-by: Nikolay Borisov <nik.borisov(a)suse.com> Cc: stable(a)vger.kernel.org Link: https://lkml.kernel.org/r/20250603111446.2609381-5-rppt@kernel.org diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index b50fe6ce4655..6455f7f751b3 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -116,6 +116,24 @@ static struct module *its_mod; #endif static void *its_page; static unsigned int its_offset; +struct its_array its_pages; + +static void *__its_alloc(struct its_array *pages) +{ + void *page __free(execmem) = execmem_alloc(EXECMEM_MODULE_TEXT, PAGE_SIZE); + if (!page) + return NULL; + + void *tmp = krealloc(pages->pages, (pages->num+1) * sizeof(void *), + GFP_KERNEL); + if (!tmp) + return NULL; + + pages->pages = tmp; + pages->pages[pages->num++] = page; + + return no_free_ptr(page); +} /* Initialize a thunk with the "jmp *reg; int3" instructions. */ static void *its_init_thunk(void *thunk, int reg) @@ -151,6 +169,21 @@ static void *its_init_thunk(void *thunk, int reg) return thunk + offset; } +static void its_pages_protect(struct its_array *pages) +{ + for (int i = 0; i < pages->num; i++) { + void *page = pages->pages[i]; + execmem_restore_rox(page, PAGE_SIZE); + } +} + +static void its_fini_core(void) +{ + if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX)) + its_pages_protect(&its_pages); + kfree(its_pages.pages); +} + #ifdef CONFIG_MODULES void its_init_mod(struct module *mod) { @@ -173,10 +206,8 @@ void its_fini_mod(struct module *mod) its_page = NULL; mutex_unlock(&text_mutex); - for (int i = 0; i < mod->arch.its_pages.num; i++) { - void *page = mod->arch.its_pages.pages[i]; - execmem_restore_rox(page, PAGE_SIZE); - } + if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX)) + its_pages_protect(&mod->arch.its_pages); } void its_free_mod(struct module *mod) @@ -194,28 +225,23 @@ void its_free_mod(struct module *mod) static void *its_alloc(void) { - void *page __free(execmem) = execmem_alloc(EXECMEM_MODULE_TEXT, PAGE_SIZE); + struct its_array *pages = &its_pages; + void *page; +#ifdef CONFIG_MODULE + if (its_mod) + pages = &its_mod->arch.its_pages; +#endif + + page = __its_alloc(pages); if (!page) return NULL; -#ifdef CONFIG_MODULES - if (its_mod) { - struct its_array *pages = &its_mod->arch.its_pages; - void *tmp = krealloc(pages->pages, - (pages->num+1) * sizeof(void *), - GFP_KERNEL); - if (!tmp) - return NULL; + execmem_make_temp_rw(page, PAGE_SIZE); + if (pages == &its_pages) + set_memory_x((unsigned long)page, 1); - pages->pages = tmp; - pages->pages[pages->num++] = page; - - execmem_make_temp_rw(page, PAGE_SIZE); - } -#endif /* CONFIG_MODULES */ - - return no_free_ptr(page); + return page; } static void *its_allocate_thunk(int reg) @@ -269,7 +295,9 @@ u8 *its_static_thunk(int reg) return thunk; } -#endif +#else +static inline void its_fini_core(void) {} +#endif /* CONFIG_MITIGATION_ITS */ /* * Nomenclature for variable names to simplify and clarify this code and ease @@ -2339,6 +2367,8 @@ void __init alternative_instructions(void) apply_retpolines(__retpoline_sites, __retpoline_sites_end); apply_returns(__return_sites, __return_sites_end); + its_fini_core(); + /* * Adjust all CALL instructions to point to func()-10, including * those in .altinstr_replacement.

1 week, 5 days

1
0
0 0

FAILED: patch "[PATCH] x86/its: explicitly manage permissions for ITS pages" failed to apply to 6.12-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.12-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.12.y git checkout FETCH_HEAD git cherry-pick -x a82b26451de126a5ae130361081986bc459afe9b # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025062013-banter-graveyard-ed28@gregkh' --subject-prefix 'PATCH 6.12.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From a82b26451de126a5ae130361081986bc459afe9b Mon Sep 17 00:00:00 2001 From: "Peter Zijlstra (Intel)" <peterz(a)infradead.org> Date: Tue, 3 Jun 2025 14:14:44 +0300 Subject: [PATCH] x86/its: explicitly manage permissions for ITS pages execmem_alloc() sets permissions differently depending on the kernel configuration, CPU support for PSE and whether a page is allocated before or after mark_rodata_ro(). Add tracking for pages allocated for ITS when patching the core kernel and make sure the permissions for ITS pages are explicitly managed for both kernel and module allocations. Fixes: 872df34d7c51 ("x86/its: Use dynamic thunks for indirect branches") Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Co-developed-by: Mike Rapoport (Microsoft) <rppt(a)kernel.org> Signed-off-by: Mike Rapoport (Microsoft) <rppt(a)kernel.org> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Reviewed-by: Nikolay Borisov <nik.borisov(a)suse.com> Cc: stable(a)vger.kernel.org Link: https://lkml.kernel.org/r/20250603111446.2609381-5-rppt@kernel.org diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index b50fe6ce4655..6455f7f751b3 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -116,6 +116,24 @@ static struct module *its_mod; #endif static void *its_page; static unsigned int its_offset; +struct its_array its_pages; + +static void *__its_alloc(struct its_array *pages) +{ + void *page __free(execmem) = execmem_alloc(EXECMEM_MODULE_TEXT, PAGE_SIZE); + if (!page) + return NULL; + + void *tmp = krealloc(pages->pages, (pages->num+1) * sizeof(void *), + GFP_KERNEL); + if (!tmp) + return NULL; + + pages->pages = tmp; + pages->pages[pages->num++] = page; + + return no_free_ptr(page); +} /* Initialize a thunk with the "jmp *reg; int3" instructions. */ static void *its_init_thunk(void *thunk, int reg) @@ -151,6 +169,21 @@ static void *its_init_thunk(void *thunk, int reg) return thunk + offset; } +static void its_pages_protect(struct its_array *pages) +{ + for (int i = 0; i < pages->num; i++) { + void *page = pages->pages[i]; + execmem_restore_rox(page, PAGE_SIZE); + } +} + +static void its_fini_core(void) +{ + if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX)) + its_pages_protect(&its_pages); + kfree(its_pages.pages); +} + #ifdef CONFIG_MODULES void its_init_mod(struct module *mod) { @@ -173,10 +206,8 @@ void its_fini_mod(struct module *mod) its_page = NULL; mutex_unlock(&text_mutex); - for (int i = 0; i < mod->arch.its_pages.num; i++) { - void *page = mod->arch.its_pages.pages[i]; - execmem_restore_rox(page, PAGE_SIZE); - } + if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX)) + its_pages_protect(&mod->arch.its_pages); } void its_free_mod(struct module *mod) @@ -194,28 +225,23 @@ void its_free_mod(struct module *mod) static void *its_alloc(void) { - void *page __free(execmem) = execmem_alloc(EXECMEM_MODULE_TEXT, PAGE_SIZE); + struct its_array *pages = &its_pages; + void *page; +#ifdef CONFIG_MODULE + if (its_mod) + pages = &its_mod->arch.its_pages; +#endif + + page = __its_alloc(pages); if (!page) return NULL; -#ifdef CONFIG_MODULES - if (its_mod) { - struct its_array *pages = &its_mod->arch.its_pages; - void *tmp = krealloc(pages->pages, - (pages->num+1) * sizeof(void *), - GFP_KERNEL); - if (!tmp) - return NULL; + execmem_make_temp_rw(page, PAGE_SIZE); + if (pages == &its_pages) + set_memory_x((unsigned long)page, 1); - pages->pages = tmp; - pages->pages[pages->num++] = page; - - execmem_make_temp_rw(page, PAGE_SIZE); - } -#endif /* CONFIG_MODULES */ - - return no_free_ptr(page); + return page; } static void *its_allocate_thunk(int reg) @@ -269,7 +295,9 @@ u8 *its_static_thunk(int reg) return thunk; } -#endif +#else +static inline void its_fini_core(void) {} +#endif /* CONFIG_MITIGATION_ITS */ /* * Nomenclature for variable names to simplify and clarify this code and ease @@ -2339,6 +2367,8 @@ void __init alternative_instructions(void) apply_retpolines(__retpoline_sites, __retpoline_sites_end); apply_returns(__return_sites, __return_sites_end); + its_fini_core(); + /* * Adjust all CALL instructions to point to func()-10, including * those in .altinstr_replacement.

1 week, 5 days

1
0
0 0

FAILED: patch "[PATCH] x86/its: explicitly manage permissions for ITS pages" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x a82b26451de126a5ae130361081986bc459afe9b # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025062013-chlorine-rubbing-22b0@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From a82b26451de126a5ae130361081986bc459afe9b Mon Sep 17 00:00:00 2001 From: "Peter Zijlstra (Intel)" <peterz(a)infradead.org> Date: Tue, 3 Jun 2025 14:14:44 +0300 Subject: [PATCH] x86/its: explicitly manage permissions for ITS pages execmem_alloc() sets permissions differently depending on the kernel configuration, CPU support for PSE and whether a page is allocated before or after mark_rodata_ro(). Add tracking for pages allocated for ITS when patching the core kernel and make sure the permissions for ITS pages are explicitly managed for both kernel and module allocations. Fixes: 872df34d7c51 ("x86/its: Use dynamic thunks for indirect branches") Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Co-developed-by: Mike Rapoport (Microsoft) <rppt(a)kernel.org> Signed-off-by: Mike Rapoport (Microsoft) <rppt(a)kernel.org> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Reviewed-by: Nikolay Borisov <nik.borisov(a)suse.com> Cc: stable(a)vger.kernel.org Link: https://lkml.kernel.org/r/20250603111446.2609381-5-rppt@kernel.org diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index b50fe6ce4655..6455f7f751b3 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -116,6 +116,24 @@ static struct module *its_mod; #endif static void *its_page; static unsigned int its_offset; +struct its_array its_pages; + +static void *__its_alloc(struct its_array *pages) +{ + void *page __free(execmem) = execmem_alloc(EXECMEM_MODULE_TEXT, PAGE_SIZE); + if (!page) + return NULL; + + void *tmp = krealloc(pages->pages, (pages->num+1) * sizeof(void *), + GFP_KERNEL); + if (!tmp) + return NULL; + + pages->pages = tmp; + pages->pages[pages->num++] = page; + + return no_free_ptr(page); +} /* Initialize a thunk with the "jmp *reg; int3" instructions. */ static void *its_init_thunk(void *thunk, int reg) @@ -151,6 +169,21 @@ static void *its_init_thunk(void *thunk, int reg) return thunk + offset; } +static void its_pages_protect(struct its_array *pages) +{ + for (int i = 0; i < pages->num; i++) { + void *page = pages->pages[i]; + execmem_restore_rox(page, PAGE_SIZE); + } +} + +static void its_fini_core(void) +{ + if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX)) + its_pages_protect(&its_pages); + kfree(its_pages.pages); +} + #ifdef CONFIG_MODULES void its_init_mod(struct module *mod) { @@ -173,10 +206,8 @@ void its_fini_mod(struct module *mod) its_page = NULL; mutex_unlock(&text_mutex); - for (int i = 0; i < mod->arch.its_pages.num; i++) { - void *page = mod->arch.its_pages.pages[i]; - execmem_restore_rox(page, PAGE_SIZE); - } + if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX)) + its_pages_protect(&mod->arch.its_pages); } void its_free_mod(struct module *mod) @@ -194,28 +225,23 @@ void its_free_mod(struct module *mod) static void *its_alloc(void) { - void *page __free(execmem) = execmem_alloc(EXECMEM_MODULE_TEXT, PAGE_SIZE); + struct its_array *pages = &its_pages; + void *page; +#ifdef CONFIG_MODULE + if (its_mod) + pages = &its_mod->arch.its_pages; +#endif + + page = __its_alloc(pages); if (!page) return NULL; -#ifdef CONFIG_MODULES - if (its_mod) { - struct its_array *pages = &its_mod->arch.its_pages; - void *tmp = krealloc(pages->pages, - (pages->num+1) * sizeof(void *), - GFP_KERNEL); - if (!tmp) - return NULL; + execmem_make_temp_rw(page, PAGE_SIZE); + if (pages == &its_pages) + set_memory_x((unsigned long)page, 1); - pages->pages = tmp; - pages->pages[pages->num++] = page; - - execmem_make_temp_rw(page, PAGE_SIZE); - } -#endif /* CONFIG_MODULES */ - - return no_free_ptr(page); + return page; } static void *its_allocate_thunk(int reg) @@ -269,7 +295,9 @@ u8 *its_static_thunk(int reg) return thunk; } -#endif +#else +static inline void its_fini_core(void) {} +#endif /* CONFIG_MITIGATION_ITS */ /* * Nomenclature for variable names to simplify and clarify this code and ease @@ -2339,6 +2367,8 @@ void __init alternative_instructions(void) apply_retpolines(__retpoline_sites, __retpoline_sites_end); apply_returns(__return_sites, __return_sites_end); + its_fini_core(); + /* * Adjust all CALL instructions to point to func()-10, including * those in .altinstr_replacement.

1 week, 5 days

1
0
0 0

FAILED: patch "[PATCH] x86/its: move its_pages array to struct mod_arch_specific" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x 0b0cae7119a0ec9449d7261b5e672a5fed765068 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025062001-charity-anytime-66e2@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 0b0cae7119a0ec9449d7261b5e672a5fed765068 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" <rppt(a)kernel.org> Date: Tue, 3 Jun 2025 14:14:43 +0300 Subject: [PATCH] x86/its: move its_pages array to struct mod_arch_specific The of pages with ITS thunks allocated for modules are tracked by an array in 'struct module'. Since this is very architecture specific data structure, move it to 'struct mod_arch_specific'. No functional changes. Fixes: 872df34d7c51 ("x86/its: Use dynamic thunks for indirect branches") Suggested-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Signed-off-by: Mike Rapoport (Microsoft) <rppt(a)kernel.org> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Cc: stable(a)vger.kernel.org Link: https://lkml.kernel.org/r/20250603111446.2609381-4-rppt@kernel.org diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h index e988bac0a4a1..3c2de4ce3b10 100644 --- a/arch/x86/include/asm/module.h +++ b/arch/x86/include/asm/module.h @@ -5,12 +5,20 @@ #include <asm-generic/module.h> #include <asm/orc_types.h> +struct its_array { +#ifdef CONFIG_MITIGATION_ITS + void **pages; + int num; +#endif +}; + struct mod_arch_specific { #ifdef CONFIG_UNWINDER_ORC unsigned int num_orcs; int *orc_unwind_ip; struct orc_entry *orc_unwind; #endif + struct its_array its_pages; }; #endif /* _ASM_X86_MODULE_H */ diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index ecfe7b497cad..b50fe6ce4655 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -173,8 +173,8 @@ void its_fini_mod(struct module *mod) its_page = NULL; mutex_unlock(&text_mutex); - for (int i = 0; i < mod->its_num_pages; i++) { - void *page = mod->its_page_array[i]; + for (int i = 0; i < mod->arch.its_pages.num; i++) { + void *page = mod->arch.its_pages.pages[i]; execmem_restore_rox(page, PAGE_SIZE); } } @@ -184,11 +184,11 @@ void its_free_mod(struct module *mod) if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) return; - for (int i = 0; i < mod->its_num_pages; i++) { - void *page = mod->its_page_array[i]; + for (int i = 0; i < mod->arch.its_pages.num; i++) { + void *page = mod->arch.its_pages.pages[i]; execmem_free(page); } - kfree(mod->its_page_array); + kfree(mod->arch.its_pages.pages); } #endif /* CONFIG_MODULES */ @@ -201,14 +201,15 @@ static void *its_alloc(void) #ifdef CONFIG_MODULES if (its_mod) { - void *tmp = krealloc(its_mod->its_page_array, - (its_mod->its_num_pages+1) * sizeof(void *), + struct its_array *pages = &its_mod->arch.its_pages; + void *tmp = krealloc(pages->pages, + (pages->num+1) * sizeof(void *), GFP_KERNEL); if (!tmp) return NULL; - its_mod->its_page_array = tmp; - its_mod->its_page_array[its_mod->its_num_pages++] = page; + pages->pages = tmp; + pages->pages[pages->num++] = page; execmem_make_temp_rw(page, PAGE_SIZE); } diff --git a/include/linux/module.h b/include/linux/module.h index 92e1420fccdf..5faa1fb1f4b4 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -586,11 +586,6 @@ struct module { atomic_t refcnt; #endif -#ifdef CONFIG_MITIGATION_ITS - int its_num_pages; - void **its_page_array; -#endif - #ifdef CONFIG_CONSTRUCTORS /* Constructor functions. */ ctor_fn_t *ctors;

1 week, 5 days

1
0
0 0

FAILED: patch "[PATCH] x86/its: move its_pages array to struct mod_arch_specific" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x 0b0cae7119a0ec9449d7261b5e672a5fed765068 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025062000-untold-childhood-3862@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 0b0cae7119a0ec9449d7261b5e672a5fed765068 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" <rppt(a)kernel.org> Date: Tue, 3 Jun 2025 14:14:43 +0300 Subject: [PATCH] x86/its: move its_pages array to struct mod_arch_specific The of pages with ITS thunks allocated for modules are tracked by an array in 'struct module'. Since this is very architecture specific data structure, move it to 'struct mod_arch_specific'. No functional changes. Fixes: 872df34d7c51 ("x86/its: Use dynamic thunks for indirect branches") Suggested-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Signed-off-by: Mike Rapoport (Microsoft) <rppt(a)kernel.org> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Cc: stable(a)vger.kernel.org Link: https://lkml.kernel.org/r/20250603111446.2609381-4-rppt@kernel.org diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h index e988bac0a4a1..3c2de4ce3b10 100644 --- a/arch/x86/include/asm/module.h +++ b/arch/x86/include/asm/module.h @@ -5,12 +5,20 @@ #include <asm-generic/module.h> #include <asm/orc_types.h> +struct its_array { +#ifdef CONFIG_MITIGATION_ITS + void **pages; + int num; +#endif +}; + struct mod_arch_specific { #ifdef CONFIG_UNWINDER_ORC unsigned int num_orcs; int *orc_unwind_ip; struct orc_entry *orc_unwind; #endif + struct its_array its_pages; }; #endif /* _ASM_X86_MODULE_H */ diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index ecfe7b497cad..b50fe6ce4655 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -173,8 +173,8 @@ void its_fini_mod(struct module *mod) its_page = NULL; mutex_unlock(&text_mutex); - for (int i = 0; i < mod->its_num_pages; i++) { - void *page = mod->its_page_array[i]; + for (int i = 0; i < mod->arch.its_pages.num; i++) { + void *page = mod->arch.its_pages.pages[i]; execmem_restore_rox(page, PAGE_SIZE); } } @@ -184,11 +184,11 @@ void its_free_mod(struct module *mod) if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) return; - for (int i = 0; i < mod->its_num_pages; i++) { - void *page = mod->its_page_array[i]; + for (int i = 0; i < mod->arch.its_pages.num; i++) { + void *page = mod->arch.its_pages.pages[i]; execmem_free(page); } - kfree(mod->its_page_array); + kfree(mod->arch.its_pages.pages); } #endif /* CONFIG_MODULES */ @@ -201,14 +201,15 @@ static void *its_alloc(void) #ifdef CONFIG_MODULES if (its_mod) { - void *tmp = krealloc(its_mod->its_page_array, - (its_mod->its_num_pages+1) * sizeof(void *), + struct its_array *pages = &its_mod->arch.its_pages; + void *tmp = krealloc(pages->pages, + (pages->num+1) * sizeof(void *), GFP_KERNEL); if (!tmp) return NULL; - its_mod->its_page_array = tmp; - its_mod->its_page_array[its_mod->its_num_pages++] = page; + pages->pages = tmp; + pages->pages[pages->num++] = page; execmem_make_temp_rw(page, PAGE_SIZE); } diff --git a/include/linux/module.h b/include/linux/module.h index 92e1420fccdf..5faa1fb1f4b4 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -586,11 +586,6 @@ struct module { atomic_t refcnt; #endif -#ifdef CONFIG_MITIGATION_ITS - int its_num_pages; - void **its_page_array; -#endif - #ifdef CONFIG_CONSTRUCTORS /* Constructor functions. */ ctor_fn_t *ctors;

1 week, 5 days

1
0
0 0

FAILED: patch "[PATCH] x86/its: move its_pages array to struct mod_arch_specific" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x 0b0cae7119a0ec9449d7261b5e672a5fed765068 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025062000-reveal-jury-be96@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 0b0cae7119a0ec9449d7261b5e672a5fed765068 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" <rppt(a)kernel.org> Date: Tue, 3 Jun 2025 14:14:43 +0300 Subject: [PATCH] x86/its: move its_pages array to struct mod_arch_specific The of pages with ITS thunks allocated for modules are tracked by an array in 'struct module'. Since this is very architecture specific data structure, move it to 'struct mod_arch_specific'. No functional changes. Fixes: 872df34d7c51 ("x86/its: Use dynamic thunks for indirect branches") Suggested-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Signed-off-by: Mike Rapoport (Microsoft) <rppt(a)kernel.org> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Cc: stable(a)vger.kernel.org Link: https://lkml.kernel.org/r/20250603111446.2609381-4-rppt@kernel.org diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h index e988bac0a4a1..3c2de4ce3b10 100644 --- a/arch/x86/include/asm/module.h +++ b/arch/x86/include/asm/module.h @@ -5,12 +5,20 @@ #include <asm-generic/module.h> #include <asm/orc_types.h> +struct its_array { +#ifdef CONFIG_MITIGATION_ITS + void **pages; + int num; +#endif +}; + struct mod_arch_specific { #ifdef CONFIG_UNWINDER_ORC unsigned int num_orcs; int *orc_unwind_ip; struct orc_entry *orc_unwind; #endif + struct its_array its_pages; }; #endif /* _ASM_X86_MODULE_H */ diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index ecfe7b497cad..b50fe6ce4655 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -173,8 +173,8 @@ void its_fini_mod(struct module *mod) its_page = NULL; mutex_unlock(&text_mutex); - for (int i = 0; i < mod->its_num_pages; i++) { - void *page = mod->its_page_array[i]; + for (int i = 0; i < mod->arch.its_pages.num; i++) { + void *page = mod->arch.its_pages.pages[i]; execmem_restore_rox(page, PAGE_SIZE); } } @@ -184,11 +184,11 @@ void its_free_mod(struct module *mod) if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) return; - for (int i = 0; i < mod->its_num_pages; i++) { - void *page = mod->its_page_array[i]; + for (int i = 0; i < mod->arch.its_pages.num; i++) { + void *page = mod->arch.its_pages.pages[i]; execmem_free(page); } - kfree(mod->its_page_array); + kfree(mod->arch.its_pages.pages); } #endif /* CONFIG_MODULES */ @@ -201,14 +201,15 @@ static void *its_alloc(void) #ifdef CONFIG_MODULES if (its_mod) { - void *tmp = krealloc(its_mod->its_page_array, - (its_mod->its_num_pages+1) * sizeof(void *), + struct its_array *pages = &its_mod->arch.its_pages; + void *tmp = krealloc(pages->pages, + (pages->num+1) * sizeof(void *), GFP_KERNEL); if (!tmp) return NULL; - its_mod->its_page_array = tmp; - its_mod->its_page_array[its_mod->its_num_pages++] = page; + pages->pages = tmp; + pages->pages[pages->num++] = page; execmem_make_temp_rw(page, PAGE_SIZE); } diff --git a/include/linux/module.h b/include/linux/module.h index 92e1420fccdf..5faa1fb1f4b4 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -586,11 +586,6 @@ struct module { atomic_t refcnt; #endif -#ifdef CONFIG_MITIGATION_ITS - int its_num_pages; - void **its_page_array; -#endif - #ifdef CONFIG_CONSTRUCTORS /* Constructor functions. */ ctor_fn_t *ctors;

1 week, 5 days

1
0
0 0

FAILED: patch "[PATCH] x86/its: move its_pages array to struct mod_arch_specific" failed to apply to 6.12-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.12-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.12.y git checkout FETCH_HEAD git cherry-pick -x 0b0cae7119a0ec9449d7261b5e672a5fed765068 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025062059-map-powdering-0ee4@gregkh' --subject-prefix 'PATCH 6.12.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 0b0cae7119a0ec9449d7261b5e672a5fed765068 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" <rppt(a)kernel.org> Date: Tue, 3 Jun 2025 14:14:43 +0300 Subject: [PATCH] x86/its: move its_pages array to struct mod_arch_specific The of pages with ITS thunks allocated for modules are tracked by an array in 'struct module'. Since this is very architecture specific data structure, move it to 'struct mod_arch_specific'. No functional changes. Fixes: 872df34d7c51 ("x86/its: Use dynamic thunks for indirect branches") Suggested-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Signed-off-by: Mike Rapoport (Microsoft) <rppt(a)kernel.org> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Cc: stable(a)vger.kernel.org Link: https://lkml.kernel.org/r/20250603111446.2609381-4-rppt@kernel.org diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h index e988bac0a4a1..3c2de4ce3b10 100644 --- a/arch/x86/include/asm/module.h +++ b/arch/x86/include/asm/module.h @@ -5,12 +5,20 @@ #include <asm-generic/module.h> #include <asm/orc_types.h> +struct its_array { +#ifdef CONFIG_MITIGATION_ITS + void **pages; + int num; +#endif +}; + struct mod_arch_specific { #ifdef CONFIG_UNWINDER_ORC unsigned int num_orcs; int *orc_unwind_ip; struct orc_entry *orc_unwind; #endif + struct its_array its_pages; }; #endif /* _ASM_X86_MODULE_H */ diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index ecfe7b497cad..b50fe6ce4655 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -173,8 +173,8 @@ void its_fini_mod(struct module *mod) its_page = NULL; mutex_unlock(&text_mutex); - for (int i = 0; i < mod->its_num_pages; i++) { - void *page = mod->its_page_array[i]; + for (int i = 0; i < mod->arch.its_pages.num; i++) { + void *page = mod->arch.its_pages.pages[i]; execmem_restore_rox(page, PAGE_SIZE); } } @@ -184,11 +184,11 @@ void its_free_mod(struct module *mod) if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) return; - for (int i = 0; i < mod->its_num_pages; i++) { - void *page = mod->its_page_array[i]; + for (int i = 0; i < mod->arch.its_pages.num; i++) { + void *page = mod->arch.its_pages.pages[i]; execmem_free(page); } - kfree(mod->its_page_array); + kfree(mod->arch.its_pages.pages); } #endif /* CONFIG_MODULES */ @@ -201,14 +201,15 @@ static void *its_alloc(void) #ifdef CONFIG_MODULES if (its_mod) { - void *tmp = krealloc(its_mod->its_page_array, - (its_mod->its_num_pages+1) * sizeof(void *), + struct its_array *pages = &its_mod->arch.its_pages; + void *tmp = krealloc(pages->pages, + (pages->num+1) * sizeof(void *), GFP_KERNEL); if (!tmp) return NULL; - its_mod->its_page_array = tmp; - its_mod->its_page_array[its_mod->its_num_pages++] = page; + pages->pages = tmp; + pages->pages[pages->num++] = page; execmem_make_temp_rw(page, PAGE_SIZE); } diff --git a/include/linux/module.h b/include/linux/module.h index 92e1420fccdf..5faa1fb1f4b4 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -586,11 +586,6 @@ struct module { atomic_t refcnt; #endif -#ifdef CONFIG_MITIGATION_ITS - int its_num_pages; - void **its_page_array; -#endif - #ifdef CONFIG_CONSTRUCTORS /* Constructor functions. */ ctor_fn_t *ctors;

1 week, 5 days

1
0
0 0

FAILED: patch "[PATCH] mm: close theoretical race where stale TLB entries could" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y git checkout FETCH_HEAD git cherry-pick -x 383c4613c67c26e90e8eebb72e3083457d02033f # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025062029-saturday-conical-0eae@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 383c4613c67c26e90e8eebb72e3083457d02033f Mon Sep 17 00:00:00 2001 From: Ryan Roberts <ryan.roberts(a)arm.com> Date: Fri, 6 Jun 2025 10:28:07 +0100 Subject: [PATCH] mm: close theoretical race where stale TLB entries could linger Commit 3ea277194daa ("mm, mprotect: flush TLB if potentially racing with a parallel reclaim leaving stale TLB entries") described a theoretical race as such: """ Nadav Amit identified a theoretical race between page reclaim and mprotect due to TLB flushes being batched outside of the PTL being held. He described the race as follows: CPU0 CPU1 ---- ---- user accesses memory using RW PTE [PTE now cached in TLB] try_to_unmap_one() ==> ptep_get_and_clear() ==> set_tlb_ubc_flush_pending() mprotect(addr, PROT_READ) ==> change_pte_range() ==> [ PTE non-present - no flush ] user writes using cached RW PTE ... try_to_unmap_flush() The same type of race exists for reads when protecting for PROT_NONE and also exists for operations that can leave an old TLB entry behind such as munmap, mremap and madvise. """ The solution was to introduce flush_tlb_batched_pending() and call it under the PTL from mprotect/madvise/munmap/mremap to complete any pending tlb flushes. However, while madvise_free_pte_range() and madvise_cold_or_pageout_pte_range() were both retro-fitted to call flush_tlb_batched_pending() immediately after initially acquiring the PTL, they both temporarily release the PTL to split a large folio if they stumble upon one. In this case, where re-acquiring the PTL flush_tlb_batched_pending() must be called again, but it previously was not. Let's fix that. There are 2 Fixes: tags here: the first is the commit that fixed madvise_free_pte_range(). The second is the commit that added madvise_cold_or_pageout_pte_range(), which looks like it copy/pasted the faulty pattern from madvise_free_pte_range(). This is a theoretical bug discovered during code review. Link: https://lkml.kernel.org/r/20250606092809.4194056-1-ryan.roberts@arm.com Fixes: 3ea277194daa ("mm, mprotect: flush TLB if potentially racing with a parallel reclaim leaving stale TLB entries") Fixes: 9c276cc65a58 ("mm: introduce MADV_COLD") Signed-off-by: Ryan Roberts <ryan.roberts(a)arm.com> Reviewed-by: Jann Horn <jannh(a)google.com> Acked-by: David Hildenbrand <david(a)redhat.com> Cc: Liam Howlett <liam.howlett(a)oracle.com> Cc: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Cc: Mel Gorman <mgorman <mgorman(a)suse.de> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/madvise.c b/mm/madvise.c index 5f7a66a1617e..1d44a35ae85c 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -508,6 +508,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, pte_offset_map_lock(mm, pmd, addr, &ptl); if (!start_pte) break; + flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); if (!err) nr = 0; @@ -741,6 +742,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, start_pte = pte; if (!start_pte) break; + flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); if (!err) nr = 0;

1 week, 5 days

1
0
0 0

FAILED: patch "[PATCH] mm: close theoretical race where stale TLB entries could" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y git checkout FETCH_HEAD git cherry-pick -x 383c4613c67c26e90e8eebb72e3083457d02033f # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025062028-richly-basket-a70f@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 383c4613c67c26e90e8eebb72e3083457d02033f Mon Sep 17 00:00:00 2001 From: Ryan Roberts <ryan.roberts(a)arm.com> Date: Fri, 6 Jun 2025 10:28:07 +0100 Subject: [PATCH] mm: close theoretical race where stale TLB entries could linger Commit 3ea277194daa ("mm, mprotect: flush TLB if potentially racing with a parallel reclaim leaving stale TLB entries") described a theoretical race as such: """ Nadav Amit identified a theoretical race between page reclaim and mprotect due to TLB flushes being batched outside of the PTL being held. He described the race as follows: CPU0 CPU1 ---- ---- user accesses memory using RW PTE [PTE now cached in TLB] try_to_unmap_one() ==> ptep_get_and_clear() ==> set_tlb_ubc_flush_pending() mprotect(addr, PROT_READ) ==> change_pte_range() ==> [ PTE non-present - no flush ] user writes using cached RW PTE ... try_to_unmap_flush() The same type of race exists for reads when protecting for PROT_NONE and also exists for operations that can leave an old TLB entry behind such as munmap, mremap and madvise. """ The solution was to introduce flush_tlb_batched_pending() and call it under the PTL from mprotect/madvise/munmap/mremap to complete any pending tlb flushes. However, while madvise_free_pte_range() and madvise_cold_or_pageout_pte_range() were both retro-fitted to call flush_tlb_batched_pending() immediately after initially acquiring the PTL, they both temporarily release the PTL to split a large folio if they stumble upon one. In this case, where re-acquiring the PTL flush_tlb_batched_pending() must be called again, but it previously was not. Let's fix that. There are 2 Fixes: tags here: the first is the commit that fixed madvise_free_pte_range(). The second is the commit that added madvise_cold_or_pageout_pte_range(), which looks like it copy/pasted the faulty pattern from madvise_free_pte_range(). This is a theoretical bug discovered during code review. Link: https://lkml.kernel.org/r/20250606092809.4194056-1-ryan.roberts@arm.com Fixes: 3ea277194daa ("mm, mprotect: flush TLB if potentially racing with a parallel reclaim leaving stale TLB entries") Fixes: 9c276cc65a58 ("mm: introduce MADV_COLD") Signed-off-by: Ryan Roberts <ryan.roberts(a)arm.com> Reviewed-by: Jann Horn <jannh(a)google.com> Acked-by: David Hildenbrand <david(a)redhat.com> Cc: Liam Howlett <liam.howlett(a)oracle.com> Cc: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Cc: Mel Gorman <mgorman <mgorman(a)suse.de> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/madvise.c b/mm/madvise.c index 5f7a66a1617e..1d44a35ae85c 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -508,6 +508,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, pte_offset_map_lock(mm, pmd, addr, &ptl); if (!start_pte) break; + flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); if (!err) nr = 0; @@ -741,6 +742,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, start_pte = pte; if (!start_pte) break; + flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); if (!err) nr = 0;

1 week, 5 days

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror