From 7b7aa8a4adb62e3c3312d1c6086891014addc567 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 2 Apr 2025 19:17:03 +0100 Subject: mm: remove mk_huge_pte() The only remaining user of mk_huge_pte() is the debug code, so remove the API and replace its use with pfn_pte() which lets us remove the conversion to a page first. We should always call arch_make_huge_pte() to turn this PTE into a huge PTE before operating on it with huge_pte_mkdirty() etc. Link: https://lkml.kernel.org/r/20250402181709.2386022-10-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Cc: Zi Yan Cc: Alexander Gordeev Cc: Andreas Larsson Cc: Anton Ivanov Cc: Dave Hansen Cc: David Hildenbrand Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Johannes Berg Cc: Muchun Song Cc: Richard Weinberger Cc: Signed-off-by: Andrew Morton --- include/asm-generic/hugetlb.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/asm-generic') diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h index 2afc95bf1655..3e0a8fe9b108 100644 --- a/include/asm-generic/hugetlb.h +++ b/include/asm-generic/hugetlb.h @@ -5,11 +5,6 @@ #include #include -static inline pte_t mk_huge_pte(struct page *page, pgprot_t pgprot) -{ - return mk_pte(page, pgprot); -} - static inline unsigned long huge_pte_write(pte_t pte) { return pte_write(pte); -- cgit v1.2.3 From 17fc7b8f9bce5d3d61ef347dd8cfccb6365dcaa1 Mon Sep 17 00:00:00 2001 From: "Dmitry V. Levin" Date: Mon, 3 Mar 2025 13:20:09 +0200 Subject: syscall.h: add syscall_set_arguments() This function is going to be needed on all HAVE_ARCH_TRACEHOOK architectures to implement PTRACE_SET_SYSCALL_INFO API. This partially reverts commit 7962c2eddbfe ("arch: remove unused function syscall_set_arguments()") by reusing some of old syscall_set_arguments() implementations. [nathan@kernel.org: fix compile time fortify checks] Link: https://lkml.kernel.org/r/20250408213131.GA2872426@ax162 Link: https://lkml.kernel.org/r/20250303112009.GC24170@strace.io Signed-off-by: Dmitry V. Levin Signed-off-by: Nathan Chancellor Tested-by: Charlie Jenkins Reviewed-by: Charlie Jenkins Acked-by: Helge Deller # parisc Reviewed-by: Maciej W. Rozycki [mips] Cc: Alexander Gordeev Cc: Alexey Gladkov (Intel) Cc: Andreas Larsson Cc: anton ivanov Cc: Arnd Bergmann Cc: Borislav Betkov Cc: Brian Cain Cc: Christian Borntraeger Cc: Christian Zankel Cc: Christophe Leroy Cc: Dave Hansen Cc: Davide Berardi Cc: David S. Miller Cc: Dinh Nguyen Cc: Eugene Syromiatnikov Cc: Eugene Syromyatnikov Cc: Geert Uytterhoeven Cc: Guo Ren Cc: Heiko Carstens Cc: "H. Peter Anvin" Cc: Huacai Chen Cc: Ingo Molnar Cc: Johannes Berg Cc: John Paul Adrian Glaubitz Cc: Jonas Bonn Cc: Madhavan Srinivasan Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Mike Frysinger Cc: Naveen N Rao Cc: Nicholas Piggin Cc: Oleg Nesterov Cc: Renzo Davoi Cc: Richard Weinberger Cc: Rich Felker Cc: Russel King Cc: Shuah Khan Cc: Stafford Horne Cc: Stefan Kristiansson Cc: Sven Schnelle Cc: Thomas Gleinxer Cc: Vasily Gorbik Cc: Vineet Gupta Cc: WANG Xuerui Cc: Will Deacon Cc: Yoshinori Sato Signed-off-by: Andrew Morton --- arch/arc/include/asm/syscall.h | 14 ++++++++++++++ arch/arm/include/asm/syscall.h | 13 +++++++++++++ arch/arm64/include/asm/syscall.h | 13 +++++++++++++ arch/csky/include/asm/syscall.h | 13 +++++++++++++ arch/hexagon/include/asm/syscall.h | 7 +++++++ arch/loongarch/include/asm/syscall.h | 8 ++++++++ arch/mips/include/asm/syscall.h | 28 +++++++++++++++++++++++++++ arch/nios2/include/asm/syscall.h | 11 +++++++++++ arch/openrisc/include/asm/syscall.h | 7 +++++++ arch/parisc/include/asm/syscall.h | 12 ++++++++++++ arch/powerpc/include/asm/syscall.h | 10 ++++++++++ arch/riscv/include/asm/syscall.h | 12 ++++++++++++ arch/s390/include/asm/syscall.h | 9 +++++++++ arch/sh/include/asm/syscall_32.h | 12 ++++++++++++ arch/sparc/include/asm/syscall.h | 10 ++++++++++ arch/um/include/asm/syscall-generic.h | 14 ++++++++++++++ arch/x86/include/asm/syscall.h | 36 +++++++++++++++++++++++++++++++++++ arch/xtensa/include/asm/syscall.h | 11 +++++++++++ include/asm-generic/syscall.h | 16 ++++++++++++++++ 19 files changed, 256 insertions(+) (limited to 'include/asm-generic') diff --git a/arch/arc/include/asm/syscall.h b/arch/arc/include/asm/syscall.h index 9709256e31c8..89c1e1736356 100644 --- a/arch/arc/include/asm/syscall.h +++ b/arch/arc/include/asm/syscall.h @@ -67,6 +67,20 @@ syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, } } +static inline void +syscall_set_arguments(struct task_struct *task, struct pt_regs *regs, + unsigned long *args) +{ + unsigned long *inside_ptregs = ®s->r0; + unsigned int n = 6; + unsigned int i = 0; + + while (n--) { + *inside_ptregs = args[i++]; + inside_ptregs--; + } +} + static inline int syscall_get_arch(struct task_struct *task) { diff --git a/arch/arm/include/asm/syscall.h b/arch/arm/include/asm/syscall.h index fe4326d938c1..21927fa0ae2b 100644 --- a/arch/arm/include/asm/syscall.h +++ b/arch/arm/include/asm/syscall.h @@ -80,6 +80,19 @@ static inline void syscall_get_arguments(struct task_struct *task, memcpy(args, ®s->ARM_r0 + 1, 5 * sizeof(args[0])); } +static inline void syscall_set_arguments(struct task_struct *task, + struct pt_regs *regs, + const unsigned long *args) +{ + memcpy(®s->ARM_r0, args, 6 * sizeof(args[0])); + /* + * Also copy the first argument into ARM_ORIG_r0 + * so that syscall_get_arguments() would return it + * instead of the previous value. + */ + regs->ARM_ORIG_r0 = regs->ARM_r0; +} + static inline int syscall_get_arch(struct task_struct *task) { /* ARM tasks don't change audit architectures on the fly. */ diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h index ab8e14b96f68..76020b66286b 100644 --- a/arch/arm64/include/asm/syscall.h +++ b/arch/arm64/include/asm/syscall.h @@ -73,6 +73,19 @@ static inline void syscall_get_arguments(struct task_struct *task, memcpy(args, ®s->regs[1], 5 * sizeof(args[0])); } +static inline void syscall_set_arguments(struct task_struct *task, + struct pt_regs *regs, + const unsigned long *args) +{ + memcpy(®s->regs[0], args, 6 * sizeof(args[0])); + /* + * Also copy the first argument into orig_x0 + * so that syscall_get_arguments() would return it + * instead of the previous value. + */ + regs->orig_x0 = regs->regs[0]; +} + /* * We don't care about endianness (__AUDIT_ARCH_LE bit) here because * AArch64 has the same system calls both on little- and big- endian. diff --git a/arch/csky/include/asm/syscall.h b/arch/csky/include/asm/syscall.h index 0de5734950bf..717f44b4d26f 100644 --- a/arch/csky/include/asm/syscall.h +++ b/arch/csky/include/asm/syscall.h @@ -59,6 +59,19 @@ syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, memcpy(args, ®s->a1, 5 * sizeof(args[0])); } +static inline void +syscall_set_arguments(struct task_struct *task, struct pt_regs *regs, + const unsigned long *args) +{ + memcpy(®s->a0, args, 6 * sizeof(regs->a0)); + /* + * Also copy the first argument into orig_a0 + * so that syscall_get_arguments() would return it + * instead of the previous value. + */ + regs->orig_a0 = regs->a0; +} + static inline int syscall_get_arch(struct task_struct *task) { diff --git a/arch/hexagon/include/asm/syscall.h b/arch/hexagon/include/asm/syscall.h index 951ca0ed8376..1024a6548d78 100644 --- a/arch/hexagon/include/asm/syscall.h +++ b/arch/hexagon/include/asm/syscall.h @@ -33,6 +33,13 @@ static inline void syscall_get_arguments(struct task_struct *task, memcpy(args, &(®s->r00)[0], 6 * sizeof(args[0])); } +static inline void syscall_set_arguments(struct task_struct *task, + struct pt_regs *regs, + unsigned long *args) +{ + memcpy(&(®s->r00)[0], args, 6 * sizeof(args[0])); +} + static inline long syscall_get_error(struct task_struct *task, struct pt_regs *regs) { diff --git a/arch/loongarch/include/asm/syscall.h b/arch/loongarch/include/asm/syscall.h index e286dc58476e..ff415b3c0a8e 100644 --- a/arch/loongarch/include/asm/syscall.h +++ b/arch/loongarch/include/asm/syscall.h @@ -61,6 +61,14 @@ static inline void syscall_get_arguments(struct task_struct *task, memcpy(&args[1], ®s->regs[5], 5 * sizeof(long)); } +static inline void syscall_set_arguments(struct task_struct *task, + struct pt_regs *regs, + unsigned long *args) +{ + regs->orig_a0 = args[0]; + memcpy(®s->regs[5], &args[1], 5 * sizeof(long)); +} + static inline int syscall_get_arch(struct task_struct *task) { return AUDIT_ARCH_LOONGARCH64; diff --git a/arch/mips/include/asm/syscall.h b/arch/mips/include/asm/syscall.h index 056aa1b713e2..f1926ce30d4b 100644 --- a/arch/mips/include/asm/syscall.h +++ b/arch/mips/include/asm/syscall.h @@ -74,6 +74,23 @@ static inline void mips_get_syscall_arg(unsigned long *arg, #endif } +static inline void mips_set_syscall_arg(unsigned long *arg, + struct task_struct *task, struct pt_regs *regs, unsigned int n) +{ +#ifdef CONFIG_32BIT + switch (n) { + case 0: case 1: case 2: case 3: + regs->regs[4 + n] = *arg; + return; + case 4: case 5: case 6: case 7: + *arg = regs->args[n] = *arg; + return; + } +#else + regs->regs[4 + n] = *arg; +#endif +} + static inline long syscall_get_error(struct task_struct *task, struct pt_regs *regs) { @@ -120,6 +137,17 @@ static inline void syscall_get_arguments(struct task_struct *task, mips_get_syscall_arg(args++, task, regs, i++); } +static inline void syscall_set_arguments(struct task_struct *task, + struct pt_regs *regs, + unsigned long *args) +{ + unsigned int i = 0; + unsigned int n = 6; + + while (n--) + mips_set_syscall_arg(args++, task, regs, i++); +} + extern const unsigned long sys_call_table[]; extern const unsigned long sys32_call_table[]; extern const unsigned long sysn32_call_table[]; diff --git a/arch/nios2/include/asm/syscall.h b/arch/nios2/include/asm/syscall.h index fff52205fb65..526449edd768 100644 --- a/arch/nios2/include/asm/syscall.h +++ b/arch/nios2/include/asm/syscall.h @@ -58,6 +58,17 @@ static inline void syscall_get_arguments(struct task_struct *task, *args = regs->r9; } +static inline void syscall_set_arguments(struct task_struct *task, + struct pt_regs *regs, const unsigned long *args) +{ + regs->r4 = *args++; + regs->r5 = *args++; + regs->r6 = *args++; + regs->r7 = *args++; + regs->r8 = *args++; + regs->r9 = *args; +} + static inline int syscall_get_arch(struct task_struct *task) { return AUDIT_ARCH_NIOS2; diff --git a/arch/openrisc/include/asm/syscall.h b/arch/openrisc/include/asm/syscall.h index 903ed882bdec..e6383be2a195 100644 --- a/arch/openrisc/include/asm/syscall.h +++ b/arch/openrisc/include/asm/syscall.h @@ -57,6 +57,13 @@ syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, memcpy(args, ®s->gpr[3], 6 * sizeof(args[0])); } +static inline void +syscall_set_arguments(struct task_struct *task, struct pt_regs *regs, + const unsigned long *args) +{ + memcpy(®s->gpr[3], args, 6 * sizeof(args[0])); +} + static inline int syscall_get_arch(struct task_struct *task) { return AUDIT_ARCH_OPENRISC; diff --git a/arch/parisc/include/asm/syscall.h b/arch/parisc/include/asm/syscall.h index 00b127a5e09b..b146d0ae4c77 100644 --- a/arch/parisc/include/asm/syscall.h +++ b/arch/parisc/include/asm/syscall.h @@ -29,6 +29,18 @@ static inline void syscall_get_arguments(struct task_struct *tsk, args[0] = regs->gr[26]; } +static inline void syscall_set_arguments(struct task_struct *tsk, + struct pt_regs *regs, + unsigned long *args) +{ + regs->gr[21] = args[5]; + regs->gr[22] = args[4]; + regs->gr[23] = args[3]; + regs->gr[24] = args[2]; + regs->gr[25] = args[1]; + regs->gr[26] = args[0]; +} + static inline long syscall_get_error(struct task_struct *task, struct pt_regs *regs) { diff --git a/arch/powerpc/include/asm/syscall.h b/arch/powerpc/include/asm/syscall.h index 3dd36c5e334a..b2715448a660 100644 --- a/arch/powerpc/include/asm/syscall.h +++ b/arch/powerpc/include/asm/syscall.h @@ -110,6 +110,16 @@ static inline void syscall_get_arguments(struct task_struct *task, } } +static inline void syscall_set_arguments(struct task_struct *task, + struct pt_regs *regs, + const unsigned long *args) +{ + memcpy(®s->gpr[3], args, 6 * sizeof(args[0])); + + /* Also copy the first argument into orig_gpr3 */ + regs->orig_gpr3 = args[0]; +} + static inline int syscall_get_arch(struct task_struct *task) { if (is_tsk_32bit_task(task)) diff --git a/arch/riscv/include/asm/syscall.h b/arch/riscv/include/asm/syscall.h index eceabf59ae48..da56417b6705 100644 --- a/arch/riscv/include/asm/syscall.h +++ b/arch/riscv/include/asm/syscall.h @@ -69,6 +69,18 @@ static inline void syscall_get_arguments(struct task_struct *task, args[5] = regs->a5; } +static inline void syscall_set_arguments(struct task_struct *task, + struct pt_regs *regs, + const unsigned long *args) +{ + regs->orig_a0 = args[0]; + regs->a1 = args[1]; + regs->a2 = args[2]; + regs->a3 = args[3]; + regs->a4 = args[4]; + regs->a5 = args[5]; +} + static inline int syscall_get_arch(struct task_struct *task) { #ifdef CONFIG_64BIT diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h index 0213ec800b57..b87d8bb2cbaa 100644 --- a/arch/s390/include/asm/syscall.h +++ b/arch/s390/include/asm/syscall.h @@ -76,6 +76,15 @@ static inline void syscall_get_arguments(struct task_struct *task, args[0] = regs->orig_gpr2 & mask; } +static inline void syscall_set_arguments(struct task_struct *task, + struct pt_regs *regs, + const unsigned long *args) +{ + regs->orig_gpr2 = args[0]; + for (int n = 1; n < 6; n++) + regs->gprs[2 + n] = args[n]; +} + static inline int syscall_get_arch(struct task_struct *task) { #ifdef CONFIG_COMPAT diff --git a/arch/sh/include/asm/syscall_32.h b/arch/sh/include/asm/syscall_32.h index d87738eebe30..cb51a7528384 100644 --- a/arch/sh/include/asm/syscall_32.h +++ b/arch/sh/include/asm/syscall_32.h @@ -57,6 +57,18 @@ static inline void syscall_get_arguments(struct task_struct *task, args[0] = regs->regs[4]; } +static inline void syscall_set_arguments(struct task_struct *task, + struct pt_regs *regs, + const unsigned long *args) +{ + regs->regs[1] = args[5]; + regs->regs[0] = args[4]; + regs->regs[7] = args[3]; + regs->regs[6] = args[2]; + regs->regs[5] = args[1]; + regs->regs[4] = args[0]; +} + static inline int syscall_get_arch(struct task_struct *task) { int arch = AUDIT_ARCH_SH; diff --git a/arch/sparc/include/asm/syscall.h b/arch/sparc/include/asm/syscall.h index 20c109ac8cc9..62a5a78804c4 100644 --- a/arch/sparc/include/asm/syscall.h +++ b/arch/sparc/include/asm/syscall.h @@ -117,6 +117,16 @@ static inline void syscall_get_arguments(struct task_struct *task, } } +static inline void syscall_set_arguments(struct task_struct *task, + struct pt_regs *regs, + const unsigned long *args) +{ + unsigned int i; + + for (i = 0; i < 6; i++) + regs->u_regs[UREG_I0 + i] = args[i]; +} + static inline int syscall_get_arch(struct task_struct *task) { #if defined(CONFIG_SPARC64) && defined(CONFIG_COMPAT) diff --git a/arch/um/include/asm/syscall-generic.h b/arch/um/include/asm/syscall-generic.h index 172b74143c4b..2984feb9d576 100644 --- a/arch/um/include/asm/syscall-generic.h +++ b/arch/um/include/asm/syscall-generic.h @@ -62,6 +62,20 @@ static inline void syscall_get_arguments(struct task_struct *task, *args = UPT_SYSCALL_ARG6(r); } +static inline void syscall_set_arguments(struct task_struct *task, + struct pt_regs *regs, + const unsigned long *args) +{ + struct uml_pt_regs *r = ®s->regs; + + UPT_SYSCALL_ARG1(r) = *args++; + UPT_SYSCALL_ARG2(r) = *args++; + UPT_SYSCALL_ARG3(r) = *args++; + UPT_SYSCALL_ARG4(r) = *args++; + UPT_SYSCALL_ARG5(r) = *args++; + UPT_SYSCALL_ARG6(r) = *args; +} + /* See arch/x86/um/asm/syscall.h for syscall_get_arch() definition. */ #endif /* __UM_SYSCALL_GENERIC_H */ diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index 7c488ff0c764..b9c249dd9e3d 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -90,6 +90,18 @@ static inline void syscall_get_arguments(struct task_struct *task, args[5] = regs->bp; } +static inline void syscall_set_arguments(struct task_struct *task, + struct pt_regs *regs, + const unsigned long *args) +{ + regs->bx = args[0]; + regs->cx = args[1]; + regs->dx = args[2]; + regs->si = args[3]; + regs->di = args[4]; + regs->bp = args[5]; +} + static inline int syscall_get_arch(struct task_struct *task) { return AUDIT_ARCH_I386; @@ -121,6 +133,30 @@ static inline void syscall_get_arguments(struct task_struct *task, } } +static inline void syscall_set_arguments(struct task_struct *task, + struct pt_regs *regs, + const unsigned long *args) +{ +# ifdef CONFIG_IA32_EMULATION + if (task->thread_info.status & TS_COMPAT) { + regs->bx = *args++; + regs->cx = *args++; + regs->dx = *args++; + regs->si = *args++; + regs->di = *args++; + regs->bp = *args; + } else +# endif + { + regs->di = *args++; + regs->si = *args++; + regs->dx = *args++; + regs->r10 = *args++; + regs->r8 = *args++; + regs->r9 = *args; + } +} + static inline int syscall_get_arch(struct task_struct *task) { /* x32 tasks should be considered AUDIT_ARCH_X86_64. */ diff --git a/arch/xtensa/include/asm/syscall.h b/arch/xtensa/include/asm/syscall.h index 5ee974bf8330..f9a671cbf933 100644 --- a/arch/xtensa/include/asm/syscall.h +++ b/arch/xtensa/include/asm/syscall.h @@ -68,6 +68,17 @@ static inline void syscall_get_arguments(struct task_struct *task, args[i] = regs->areg[reg[i]]; } +static inline void syscall_set_arguments(struct task_struct *task, + struct pt_regs *regs, + const unsigned long *args) +{ + static const unsigned int reg[] = XTENSA_SYSCALL_ARGUMENT_REGS; + unsigned int i; + + for (i = 0; i < 6; ++i) + regs->areg[reg[i]] = args[i]; +} + asmlinkage long xtensa_rt_sigreturn(void); asmlinkage long xtensa_shmat(int, char __user *, int); asmlinkage long xtensa_fadvise64_64(int, int, diff --git a/include/asm-generic/syscall.h b/include/asm-generic/syscall.h index 182b039ce5fa..292b412f4e9a 100644 --- a/include/asm-generic/syscall.h +++ b/include/asm-generic/syscall.h @@ -117,6 +117,22 @@ void syscall_set_return_value(struct task_struct *task, struct pt_regs *regs, void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, unsigned long *args); +/** + * syscall_set_arguments - change system call parameter value + * @task: task of interest, must be in system call entry tracing + * @regs: task_pt_regs() of @task + * @args: array of argument values to store + * + * Changes 6 arguments to the system call. + * The first argument gets value @args[0], and so on. + * + * It's only valid to call this when @task is stopped for tracing on + * entry to a system call, due to %SYSCALL_WORK_SYSCALL_TRACE or + * %SYSCALL_WORK_SYSCALL_AUDIT. + */ +void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs, + const unsigned long *args); + /** * syscall_get_arch - return the AUDIT_ARCH for the current system call * @task: task of interest, must be blocked -- cgit v1.2.3 From cc6622730be77fa88acc4fb0942cd39e6fa5ca27 Mon Sep 17 00:00:00 2001 From: "Dmitry V. Levin" Date: Mon, 3 Mar 2025 13:20:20 +0200 Subject: syscall.h: introduce syscall_set_nr() Similar to syscall_set_arguments() that complements syscall_get_arguments(), introduce syscall_set_nr() that complements syscall_get_nr(). syscall_set_nr() is going to be needed along with syscall_set_arguments() on all HAVE_ARCH_TRACEHOOK architectures to implement PTRACE_SET_SYSCALL_INFO API. Link: https://lkml.kernel.org/r/20250303112020.GD24170@strace.io Signed-off-by: Dmitry V. Levin Tested-by: Charlie Jenkins Reviewed-by: Charlie Jenkins Acked-by: Helge Deller # parisc Reviewed-by: Maciej W. Rozycki # mips Cc: Alexander Gordeev Cc: Alexey Gladkov (Intel) Cc: Andreas Larsson Cc: anton ivanov Cc: Arnd Bergmann Cc: Borislav Betkov Cc: Brian Cain Cc: Christian Borntraeger Cc: Christian Zankel Cc: Christophe Leroy Cc: Dave Hansen Cc: Davide Berardi Cc: David S. Miller Cc: Dinh Nguyen Cc: Eugene Syromiatnikov Cc: Eugene Syromyatnikov Cc: Geert Uytterhoeven Cc: Guo Ren Cc: Heiko Carstens Cc: "H. Peter Anvin" Cc: Huacai Chen Cc: Ingo Molnar Cc: Johannes Berg Cc: John Paul Adrian Glaubitz Cc: Jonas Bonn Cc: Madhavan Srinivasan Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Mike Frysinger Cc: Naveen N Rao Cc: Nicholas Piggin Cc: Oleg Nesterov Cc: Renzo Davoi Cc: Richard Weinberger Cc: Rich Felker Cc: Russel King Cc: Shuah Khan Cc: Stafford Horne Cc: Stefan Kristiansson Cc: Sven Schnelle Cc: Thomas Gleinxer Cc: Vasily Gorbik Cc: Vineet Gupta Cc: WANG Xuerui Cc: Will Deacon Cc: Yoshinori Sato Signed-off-by: Andrew Morton --- arch/arc/include/asm/syscall.h | 11 +++++++++++ arch/arm/include/asm/syscall.h | 24 ++++++++++++++++++++++++ arch/arm64/include/asm/syscall.h | 16 ++++++++++++++++ arch/hexagon/include/asm/syscall.h | 7 +++++++ arch/loongarch/include/asm/syscall.h | 7 +++++++ arch/m68k/include/asm/syscall.h | 7 +++++++ arch/microblaze/include/asm/syscall.h | 7 +++++++ arch/mips/include/asm/syscall.h | 15 +++++++++++++++ arch/nios2/include/asm/syscall.h | 5 +++++ arch/openrisc/include/asm/syscall.h | 6 ++++++ arch/parisc/include/asm/syscall.h | 7 +++++++ arch/powerpc/include/asm/syscall.h | 10 ++++++++++ arch/riscv/include/asm/syscall.h | 7 +++++++ arch/s390/include/asm/syscall.h | 12 ++++++++++++ arch/sh/include/asm/syscall_32.h | 12 ++++++++++++ arch/sparc/include/asm/syscall.h | 12 ++++++++++++ arch/um/include/asm/syscall-generic.h | 5 +++++ arch/x86/include/asm/syscall.h | 7 +++++++ arch/xtensa/include/asm/syscall.h | 7 +++++++ include/asm-generic/syscall.h | 14 ++++++++++++++ 20 files changed, 198 insertions(+) (limited to 'include/asm-generic') diff --git a/arch/arc/include/asm/syscall.h b/arch/arc/include/asm/syscall.h index 89c1e1736356..728d625a10f1 100644 --- a/arch/arc/include/asm/syscall.h +++ b/arch/arc/include/asm/syscall.h @@ -23,6 +23,17 @@ syscall_get_nr(struct task_struct *task, struct pt_regs *regs) return -1; } +static inline void +syscall_set_nr(struct task_struct *task, struct pt_regs *regs, int nr) +{ + /* + * Unlike syscall_get_nr(), syscall_set_nr() can be called only when + * the target task is stopped for tracing on entering syscall, so + * there is no need to have the same check syscall_get_nr() has. + */ + regs->r8 = nr; +} + static inline void syscall_rollback(struct task_struct *task, struct pt_regs *regs) { diff --git a/arch/arm/include/asm/syscall.h b/arch/arm/include/asm/syscall.h index 21927fa0ae2b..18b102a30741 100644 --- a/arch/arm/include/asm/syscall.h +++ b/arch/arm/include/asm/syscall.h @@ -68,6 +68,30 @@ static inline void syscall_set_return_value(struct task_struct *task, regs->ARM_r0 = (long) error ? error : val; } +static inline void syscall_set_nr(struct task_struct *task, + struct pt_regs *regs, + int nr) +{ + if (nr == -1) { + task_thread_info(task)->abi_syscall = -1; + /* + * When the syscall number is set to -1, the syscall will be + * skipped. In this case the syscall return value has to be + * set explicitly, otherwise the first syscall argument is + * returned as the syscall return value. + */ + syscall_set_return_value(task, regs, -ENOSYS, 0); + return; + } + if ((IS_ENABLED(CONFIG_AEABI) && !IS_ENABLED(CONFIG_OABI_COMPAT))) { + task_thread_info(task)->abi_syscall = nr; + return; + } + task_thread_info(task)->abi_syscall = + (task_thread_info(task)->abi_syscall & ~__NR_SYSCALL_MASK) | + (nr & __NR_SYSCALL_MASK); +} + #define SYSCALL_MAX_ARGS 7 static inline void syscall_get_arguments(struct task_struct *task, diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h index 76020b66286b..712daa90e643 100644 --- a/arch/arm64/include/asm/syscall.h +++ b/arch/arm64/include/asm/syscall.h @@ -61,6 +61,22 @@ static inline void syscall_set_return_value(struct task_struct *task, regs->regs[0] = val; } +static inline void syscall_set_nr(struct task_struct *task, + struct pt_regs *regs, + int nr) +{ + regs->syscallno = nr; + if (nr == -1) { + /* + * When the syscall number is set to -1, the syscall will be + * skipped. In this case the syscall return value has to be + * set explicitly, otherwise the first syscall argument is + * returned as the syscall return value. + */ + syscall_set_return_value(task, regs, -ENOSYS, 0); + } +} + #define SYSCALL_MAX_ARGS 6 static inline void syscall_get_arguments(struct task_struct *task, diff --git a/arch/hexagon/include/asm/syscall.h b/arch/hexagon/include/asm/syscall.h index 1024a6548d78..70637261817a 100644 --- a/arch/hexagon/include/asm/syscall.h +++ b/arch/hexagon/include/asm/syscall.h @@ -26,6 +26,13 @@ static inline long syscall_get_nr(struct task_struct *task, return regs->r06; } +static inline void syscall_set_nr(struct task_struct *task, + struct pt_regs *regs, + int nr) +{ + regs->r06 = nr; +} + static inline void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, unsigned long *args) diff --git a/arch/loongarch/include/asm/syscall.h b/arch/loongarch/include/asm/syscall.h index ff415b3c0a8e..81d2733f7b94 100644 --- a/arch/loongarch/include/asm/syscall.h +++ b/arch/loongarch/include/asm/syscall.h @@ -26,6 +26,13 @@ static inline long syscall_get_nr(struct task_struct *task, return regs->regs[11]; } +static inline void syscall_set_nr(struct task_struct *task, + struct pt_regs *regs, + int nr) +{ + regs->regs[11] = nr; +} + static inline void syscall_rollback(struct task_struct *task, struct pt_regs *regs) { diff --git a/arch/m68k/include/asm/syscall.h b/arch/m68k/include/asm/syscall.h index d1453e850cdd..bf84b160c2eb 100644 --- a/arch/m68k/include/asm/syscall.h +++ b/arch/m68k/include/asm/syscall.h @@ -14,6 +14,13 @@ static inline int syscall_get_nr(struct task_struct *task, return regs->orig_d0; } +static inline void syscall_set_nr(struct task_struct *task, + struct pt_regs *regs, + int nr) +{ + regs->orig_d0 = nr; +} + static inline void syscall_rollback(struct task_struct *task, struct pt_regs *regs) { diff --git a/arch/microblaze/include/asm/syscall.h b/arch/microblaze/include/asm/syscall.h index 5eb3f624cc59..b5b6b91fae3e 100644 --- a/arch/microblaze/include/asm/syscall.h +++ b/arch/microblaze/include/asm/syscall.h @@ -14,6 +14,13 @@ static inline long syscall_get_nr(struct task_struct *task, return regs->r12; } +static inline void syscall_set_nr(struct task_struct *task, + struct pt_regs *regs, + int nr) +{ + regs->r12 = nr; +} + static inline void syscall_rollback(struct task_struct *task, struct pt_regs *regs) { diff --git a/arch/mips/include/asm/syscall.h b/arch/mips/include/asm/syscall.h index f1926ce30d4b..d19e67e2aa6a 100644 --- a/arch/mips/include/asm/syscall.h +++ b/arch/mips/include/asm/syscall.h @@ -41,6 +41,21 @@ static inline long syscall_get_nr(struct task_struct *task, return task_thread_info(task)->syscall; } +static inline void syscall_set_nr(struct task_struct *task, + struct pt_regs *regs, + int nr) +{ + /* + * New syscall number has to be assigned to regs[2] because + * it is loaded from there unconditionally after return from + * syscall_trace_enter() invocation. + * + * Consequently, if the syscall was indirect and nr != __NR_syscall, + * then after this assignment the syscall will cease to be indirect. + */ + task_thread_info(task)->syscall = regs->regs[2] = nr; +} + static inline void mips_syscall_update_nr(struct task_struct *task, struct pt_regs *regs) { diff --git a/arch/nios2/include/asm/syscall.h b/arch/nios2/include/asm/syscall.h index 526449edd768..8e3eb1d689bb 100644 --- a/arch/nios2/include/asm/syscall.h +++ b/arch/nios2/include/asm/syscall.h @@ -15,6 +15,11 @@ static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs) return regs->r2; } +static inline void syscall_set_nr(struct task_struct *task, struct pt_regs *regs, int nr) +{ + regs->r2 = nr; +} + static inline void syscall_rollback(struct task_struct *task, struct pt_regs *regs) { diff --git a/arch/openrisc/include/asm/syscall.h b/arch/openrisc/include/asm/syscall.h index e6383be2a195..5e037d9659c5 100644 --- a/arch/openrisc/include/asm/syscall.h +++ b/arch/openrisc/include/asm/syscall.h @@ -25,6 +25,12 @@ syscall_get_nr(struct task_struct *task, struct pt_regs *regs) return regs->orig_gpr11; } +static inline void +syscall_set_nr(struct task_struct *task, struct pt_regs *regs, int nr) +{ + regs->orig_gpr11 = nr; +} + static inline void syscall_rollback(struct task_struct *task, struct pt_regs *regs) { diff --git a/arch/parisc/include/asm/syscall.h b/arch/parisc/include/asm/syscall.h index b146d0ae4c77..c11222798ab2 100644 --- a/arch/parisc/include/asm/syscall.h +++ b/arch/parisc/include/asm/syscall.h @@ -17,6 +17,13 @@ static inline long syscall_get_nr(struct task_struct *tsk, return regs->gr[20]; } +static inline void syscall_set_nr(struct task_struct *tsk, + struct pt_regs *regs, + int nr) +{ + regs->gr[20] = nr; +} + static inline void syscall_get_arguments(struct task_struct *tsk, struct pt_regs *regs, unsigned long *args) diff --git a/arch/powerpc/include/asm/syscall.h b/arch/powerpc/include/asm/syscall.h index b2715448a660..4b3c52ed6e9d 100644 --- a/arch/powerpc/include/asm/syscall.h +++ b/arch/powerpc/include/asm/syscall.h @@ -39,6 +39,16 @@ static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs) return -1; } +static inline void syscall_set_nr(struct task_struct *task, struct pt_regs *regs, int nr) +{ + /* + * Unlike syscall_get_nr(), syscall_set_nr() can be called only when + * the target task is stopped for tracing on entering syscall, so + * there is no need to have the same check syscall_get_nr() has. + */ + regs->gpr[0] = nr; +} + static inline void syscall_rollback(struct task_struct *task, struct pt_regs *regs) { diff --git a/arch/riscv/include/asm/syscall.h b/arch/riscv/include/asm/syscall.h index da56417b6705..34313387f977 100644 --- a/arch/riscv/include/asm/syscall.h +++ b/arch/riscv/include/asm/syscall.h @@ -30,6 +30,13 @@ static inline int syscall_get_nr(struct task_struct *task, return regs->a7; } +static inline void syscall_set_nr(struct task_struct *task, + struct pt_regs *regs, + int nr) +{ + regs->a7 = nr; +} + static inline void syscall_rollback(struct task_struct *task, struct pt_regs *regs) { diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h index b87d8bb2cbaa..bd4cb00ccd5e 100644 --- a/arch/s390/include/asm/syscall.h +++ b/arch/s390/include/asm/syscall.h @@ -24,6 +24,18 @@ static inline long syscall_get_nr(struct task_struct *task, (regs->int_code & 0xffff) : -1; } +static inline void syscall_set_nr(struct task_struct *task, + struct pt_regs *regs, + int nr) +{ + /* + * Unlike syscall_get_nr(), syscall_set_nr() can be called only when + * the target task is stopped for tracing on entering syscall, so + * there is no need to have the same check syscall_get_nr() has. + */ + regs->int_code = (regs->int_code & ~0xffff) | (nr & 0xffff); +} + static inline void syscall_rollback(struct task_struct *task, struct pt_regs *regs) { diff --git a/arch/sh/include/asm/syscall_32.h b/arch/sh/include/asm/syscall_32.h index cb51a7528384..7027d87d901d 100644 --- a/arch/sh/include/asm/syscall_32.h +++ b/arch/sh/include/asm/syscall_32.h @@ -15,6 +15,18 @@ static inline long syscall_get_nr(struct task_struct *task, return (regs->tra >= 0) ? regs->regs[3] : -1L; } +static inline void syscall_set_nr(struct task_struct *task, + struct pt_regs *regs, + int nr) +{ + /* + * Unlike syscall_get_nr(), syscall_set_nr() can be called only when + * the target task is stopped for tracing on entering syscall, so + * there is no need to have the same check syscall_get_nr() has. + */ + regs->regs[3] = nr; +} + static inline void syscall_rollback(struct task_struct *task, struct pt_regs *regs) { diff --git a/arch/sparc/include/asm/syscall.h b/arch/sparc/include/asm/syscall.h index 62a5a78804c4..b0233924d323 100644 --- a/arch/sparc/include/asm/syscall.h +++ b/arch/sparc/include/asm/syscall.h @@ -25,6 +25,18 @@ static inline long syscall_get_nr(struct task_struct *task, return (syscall_p ? regs->u_regs[UREG_G1] : -1L); } +static inline void syscall_set_nr(struct task_struct *task, + struct pt_regs *regs, + int nr) +{ + /* + * Unlike syscall_get_nr(), syscall_set_nr() can be called only when + * the target task is stopped for tracing on entering syscall, so + * there is no need to have the same check syscall_get_nr() has. + */ + regs->u_regs[UREG_G1] = nr; +} + static inline void syscall_rollback(struct task_struct *task, struct pt_regs *regs) { diff --git a/arch/um/include/asm/syscall-generic.h b/arch/um/include/asm/syscall-generic.h index 2984feb9d576..bcd73bcfe577 100644 --- a/arch/um/include/asm/syscall-generic.h +++ b/arch/um/include/asm/syscall-generic.h @@ -21,6 +21,11 @@ static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs) return PT_REGS_SYSCALL_NR(regs); } +static inline void syscall_set_nr(struct task_struct *task, struct pt_regs *regs, int nr) +{ + PT_REGS_SYSCALL_NR(regs) = nr; +} + static inline void syscall_rollback(struct task_struct *task, struct pt_regs *regs) { diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index b9c249dd9e3d..c10dbb74cd00 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -38,6 +38,13 @@ static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs) return regs->orig_ax; } +static inline void syscall_set_nr(struct task_struct *task, + struct pt_regs *regs, + int nr) +{ + regs->orig_ax = nr; +} + static inline void syscall_rollback(struct task_struct *task, struct pt_regs *regs) { diff --git a/arch/xtensa/include/asm/syscall.h b/arch/xtensa/include/asm/syscall.h index f9a671cbf933..7db3b489c8ad 100644 --- a/arch/xtensa/include/asm/syscall.h +++ b/arch/xtensa/include/asm/syscall.h @@ -28,6 +28,13 @@ static inline long syscall_get_nr(struct task_struct *task, return regs->syscall; } +static inline void syscall_set_nr(struct task_struct *task, + struct pt_regs *regs, + int nr) +{ + regs->syscall = nr; +} + static inline void syscall_rollback(struct task_struct *task, struct pt_regs *regs) { diff --git a/include/asm-generic/syscall.h b/include/asm-generic/syscall.h index 292b412f4e9a..c5a3ad53beec 100644 --- a/include/asm-generic/syscall.h +++ b/include/asm-generic/syscall.h @@ -37,6 +37,20 @@ struct pt_regs; */ int syscall_get_nr(struct task_struct *task, struct pt_regs *regs); +/** + * syscall_set_nr - change the system call a task is executing + * @task: task of interest, must be blocked + * @regs: task_pt_regs() of @task + * @nr: system call number + * + * Changes the system call number @task is about to execute. + * + * It's only valid to call this when @task is stopped for tracing on + * entry to a system call, due to %SYSCALL_WORK_SYSCALL_TRACE or + * %SYSCALL_WORK_SYSCALL_AUDIT. + */ +void syscall_set_nr(struct task_struct *task, struct pt_regs *regs, int nr); + /** * syscall_rollback - roll back registers after an aborted system call * @task: task of interest, must be in system call exit tracing -- cgit v1.2.3 From d82d3bf4115217bb3f43f9320bad5d68a35c278f Mon Sep 17 00:00:00 2001 From: Kevin Brodsky Date: Tue, 8 Apr 2025 10:52:11 +0100 Subject: mm: pass mm down to pagetable_{pte,pmd}_ctor Patch series "Always call constructor for kernel page tables", v2. There has been much confusion around exactly when page table constructors/destructors (pagetable_*_[cd]tor) are supposed to be called. They were initially introduced for user PTEs only (to support split page table locks), then at the PMD level for the same purpose. Accounting was added later on, starting at the PTE level and then moving to higher levels (PMD, PUD). Finally, with my earlier series "Account page tables at all levels" [1], the ctor/dtor is run for all levels, all the way to PGD. I thought this was the end of the story, and it hopefully is for user pgtables, but I was wrong for what concerns kernel pgtables. The current situation there makes very little sense: * At the PTE level, the ctor/dtor is not called (at least in the generic implementation). Specific helpers are used for kernel pgtables at this level (pte_{alloc,free}_kernel()) and those have never called the ctor/dtor, most likely because they were initially irrelevant in the kernel case. * At all other levels, the ctor/dtor is normally called. This is potentially wasteful at the PMD level (more on that later). This series aims to ensure that the ctor/dtor is always called for kernel pgtables, as it already is for user pgtables. Besides consistency, the main motivation is to guarantee that ctor/dtor hooks are systematically called; this makes it possible to insert hooks to protect page tables [2], for instance. There is however an extra challenge: split locks are not used for kernel pgtables, and it would therefore be wasteful to initialise them (ptlock_init()). It is worth clarifying exactly when split locks are used. They clearly are for user pgtables, but as illustrated in commit 61444cde9170 ("ARM: 8591/1: mm: use fully constructed struct pages for EFI pgd allocations"), they also are for special page tables like efi_mm. The one case where split locks are definitely unused is pgtables owned by init_mm; this is consistent with the behaviour of apply_to_pte_range(). The approach chosen in this series is therefore to pass the mm associated to the pgtables being constructed to pagetable_{pte,pmd}_ctor() (patch 1), and skip ptlock_init() if mm == &init_mm (patch 3 and 7). This makes it possible to call the PTE ctor/dtor from pte_{alloc,free}_kernel() without unintended consequences (patch 3). As a result the accounting functions are now called at all levels for kernel pgtables, and split locks are never initialised. In configurations where ptlocks are dynamically allocated (32-bit, PREEMPT_RT, etc.) and ARCH_ENABLE_SPLIT_PMD_PTLOCK is selected, this series results in the removal of a kmem_cache allocation for every kernel PMD. Additionally, for certain architectures that do not use such as s390, the same optimisation occurs at the PTE level. === Things get more complicated when it comes to special pgtable allocators (patch 8-12). All architectures need such allocators to create initial kernel pgtables; we are not concerned with those as the ctor cannot be called so early in the boot sequence. However, those allocators may also be used later in the boot sequence or during normal operations. There are two main use-cases: 1. Mapping EFI memory: efi_mm (arm, arm64, riscv) 2. arch_add_memory(): init_mm The ctor is already explicitly run (at the PTE/PMD level) in the first case, as required for pgtables that are not associated with init_mm. However the same allocators may also be used for the second use-case (or others), and this is where it gets messy. Patch 1 calls the ctor with NULL as mm in those situations, as the actual mm isn't available. Practically this means that ptlocks will be unconditionally initialised. This is fine on arm - create_mapping_late() is only used for the EFI mapping. On arm64, __create_pgd_mapping() is also used by arch_add_memory(); patch 8/9/11 ensure that ctors are called at all levels with the appropriate mm. The situation is similar on riscv, but propagating the mm down to the ctor would require significant refactoring. Since they are already called unconditionally, this series leaves riscv no worse off - patch 10 adds comments to clarify the situation. From a cursory look at other architectures implementing arch_add_memory(), s390 and x86 may also need a similar treatment to add constructor calls. This is to be taken care of in a future version or as a follow-up. === The complications in those special pgtable allocators beg the question: does it really make sense to treat efi_mm and init_mm differently in e.g. apply_to_pte_range()? Maybe what we really need is a way to tell if an mm corresponds to user memory or not, and never use split locks for non-user mm's. Feedback and suggestions welcome! This patch (of 12): In preparation for calling constructors for all kernel page tables while eliding unnecessary ptlock initialisation, let's pass down the associated mm to the PTE/PMD level ctors. (These are the two levels where ptlocks are used.) In most cases the mm is already around at the point of calling the ctor so we simply pass it down. This is however not the case for special page table allocators: * arch/arm/mm/mmu.c * arch/arm64/mm/mmu.c * arch/riscv/mm/init.c In those cases, the page tables being allocated are either for standard kernel memory (init_mm) or special page directories, which may not be associated to any mm. For now let's pass NULL as mm; this will be refined where possible in future patches. No functional change in this patch. Link: https://lore.kernel.org/linux-mm/20250103184415.2744423-1-kevin.brodsky@arm.com/ [1] Link: https://lore.kernel.org/linux-hardening/20250203101839.1223008-1-kevin.brodsky@arm.com/ [2] Link: https://lkml.kernel.org/r/20250408095222.860601-1-kevin.brodsky@arm.com Link: https://lkml.kernel.org/r/20250408095222.860601-2-kevin.brodsky@arm.com Signed-off-by: Kevin Brodsky Reviewed-by: Alexander Gordeev [s390] Cc: Albert Ou Cc: Andreas Larsson Cc: Catalin Marinas Cc: David S. Miller Cc: Geert Uytterhoeven Cc: Kevin Brodsky Cc: Linus Waleij Cc: Madhavan Srinivasan Cc: Mark Rutland Cc: Matthew Wilcox (Oracle) Cc: Michael Ellerman Cc: Mike Rapoport Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Peter Zijlstra Cc: Qi Zheng Cc: Ryan Roberts Cc: Will Deacon Cc: Yang Shi Cc: Cc: Dave Hansen Signed-off-by: Andrew Morton --- arch/arm/mm/mmu.c | 2 +- arch/arm64/mm/mmu.c | 4 ++-- arch/loongarch/include/asm/pgalloc.h | 2 +- arch/m68k/include/asm/mcf_pgalloc.h | 2 +- arch/m68k/include/asm/motorola_pgalloc.h | 10 +++++----- arch/m68k/mm/motorola.c | 6 +++--- arch/mips/include/asm/pgalloc.h | 2 +- arch/parisc/include/asm/pgalloc.h | 2 +- arch/powerpc/mm/book3s64/pgtable.c | 2 +- arch/powerpc/mm/pgtable-frag.c | 2 +- arch/riscv/mm/init.c | 4 ++-- arch/s390/include/asm/pgalloc.h | 2 +- arch/s390/mm/pgalloc.c | 2 +- arch/sparc/mm/init_64.c | 2 +- arch/sparc/mm/srmmu.c | 2 +- arch/x86/mm/pgtable.c | 2 +- include/asm-generic/pgalloc.h | 4 ++-- include/linux/mm.h | 6 ++++-- 18 files changed, 30 insertions(+), 28 deletions(-) (limited to 'include/asm-generic') diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index f02f872ea8a9..edb7f56b7c91 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -735,7 +735,7 @@ static void *__init late_alloc(unsigned long sz) void *ptdesc = pagetable_alloc(GFP_PGTABLE_KERNEL & ~__GFP_HIGHMEM, get_order(sz)); - if (!ptdesc || !pagetable_pte_ctor(ptdesc)) + if (!ptdesc || !pagetable_pte_ctor(NULL, ptdesc)) BUG(); return ptdesc_to_virt(ptdesc); } diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index ea6695d53fb9..8c5c471cfb06 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -494,9 +494,9 @@ static phys_addr_t pgd_pgtable_alloc(int shift) * folded, and if so pagetable_pte_ctor() becomes nop. */ if (shift == PAGE_SHIFT) - BUG_ON(!pagetable_pte_ctor(ptdesc)); + BUG_ON(!pagetable_pte_ctor(NULL, ptdesc)); else if (shift == PMD_SHIFT) - BUG_ON(!pagetable_pmd_ctor(ptdesc)); + BUG_ON(!pagetable_pmd_ctor(NULL, ptdesc)); return pa; } diff --git a/arch/loongarch/include/asm/pgalloc.h b/arch/loongarch/include/asm/pgalloc.h index b58f587f0f0a..1c63a9d9a6d3 100644 --- a/arch/loongarch/include/asm/pgalloc.h +++ b/arch/loongarch/include/asm/pgalloc.h @@ -69,7 +69,7 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address) if (!ptdesc) return NULL; - if (!pagetable_pmd_ctor(ptdesc)) { + if (!pagetable_pmd_ctor(mm, ptdesc)) { pagetable_free(ptdesc); return NULL; } diff --git a/arch/m68k/include/asm/mcf_pgalloc.h b/arch/m68k/include/asm/mcf_pgalloc.h index 4c648b51e7fd..465a71101b7d 100644 --- a/arch/m68k/include/asm/mcf_pgalloc.h +++ b/arch/m68k/include/asm/mcf_pgalloc.h @@ -48,7 +48,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm) if (!ptdesc) return NULL; - if (!pagetable_pte_ctor(ptdesc)) { + if (!pagetable_pte_ctor(mm, ptdesc)) { pagetable_free(ptdesc); return NULL; } diff --git a/arch/m68k/include/asm/motorola_pgalloc.h b/arch/m68k/include/asm/motorola_pgalloc.h index 5abe7da8ac5a..1091fb0affbe 100644 --- a/arch/m68k/include/asm/motorola_pgalloc.h +++ b/arch/m68k/include/asm/motorola_pgalloc.h @@ -15,7 +15,7 @@ enum m68k_table_types { }; extern void init_pointer_table(void *table, int type); -extern void *get_pointer_table(int type); +extern void *get_pointer_table(struct mm_struct *mm, int type); extern int free_pointer_table(void *table, int type); /* @@ -26,7 +26,7 @@ extern int free_pointer_table(void *table, int type); static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm) { - return get_pointer_table(TABLE_PTE); + return get_pointer_table(mm, TABLE_PTE); } static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) @@ -36,7 +36,7 @@ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) static inline pgtable_t pte_alloc_one(struct mm_struct *mm) { - return get_pointer_table(TABLE_PTE); + return get_pointer_table(mm, TABLE_PTE); } static inline void pte_free(struct mm_struct *mm, pgtable_t pgtable) @@ -53,7 +53,7 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pgtable, static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address) { - return get_pointer_table(TABLE_PMD); + return get_pointer_table(mm, TABLE_PMD); } static inline int pmd_free(struct mm_struct *mm, pmd_t *pmd) @@ -75,7 +75,7 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) static inline pgd_t *pgd_alloc(struct mm_struct *mm) { - return get_pointer_table(TABLE_PGD); + return get_pointer_table(mm, TABLE_PGD); } diff --git a/arch/m68k/mm/motorola.c b/arch/m68k/mm/motorola.c index 73651e093c4d..6ab3ef39ba7a 100644 --- a/arch/m68k/mm/motorola.c +++ b/arch/m68k/mm/motorola.c @@ -139,7 +139,7 @@ void __init init_pointer_table(void *table, int type) return; } -void *get_pointer_table(int type) +void *get_pointer_table(struct mm_struct *mm, int type) { ptable_desc *dp = ptable_list[type].next; unsigned int mask = list_empty(&ptable_list[type]) ? 0 : PD_MARKBITS(dp); @@ -164,10 +164,10 @@ void *get_pointer_table(int type) * m68k doesn't have SPLIT_PTE_PTLOCKS for not having * SMP. */ - pagetable_pte_ctor(virt_to_ptdesc(page)); + pagetable_pte_ctor(mm, virt_to_ptdesc(page)); break; case TABLE_PMD: - pagetable_pmd_ctor(virt_to_ptdesc(page)); + pagetable_pmd_ctor(mm, virt_to_ptdesc(page)); break; case TABLE_PGD: pagetable_pgd_ctor(virt_to_ptdesc(page)); diff --git a/arch/mips/include/asm/pgalloc.h b/arch/mips/include/asm/pgalloc.h index bbca420c96d3..942af87f1cdd 100644 --- a/arch/mips/include/asm/pgalloc.h +++ b/arch/mips/include/asm/pgalloc.h @@ -62,7 +62,7 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address) if (!ptdesc) return NULL; - if (!pagetable_pmd_ctor(ptdesc)) { + if (!pagetable_pmd_ctor(mm, ptdesc)) { pagetable_free(ptdesc); return NULL; } diff --git a/arch/parisc/include/asm/pgalloc.h b/arch/parisc/include/asm/pgalloc.h index 2ca74a56415c..3b84ee93edaa 100644 --- a/arch/parisc/include/asm/pgalloc.h +++ b/arch/parisc/include/asm/pgalloc.h @@ -39,7 +39,7 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address) ptdesc = pagetable_alloc(gfp, PMD_TABLE_ORDER); if (!ptdesc) return NULL; - if (!pagetable_pmd_ctor(ptdesc)) { + if (!pagetable_pmd_ctor(mm, ptdesc)) { pagetable_free(ptdesc); return NULL; } diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c index 0e62d25062f8..0db01e10a3f8 100644 --- a/arch/powerpc/mm/book3s64/pgtable.c +++ b/arch/powerpc/mm/book3s64/pgtable.c @@ -417,7 +417,7 @@ static pmd_t *__alloc_for_pmdcache(struct mm_struct *mm) ptdesc = pagetable_alloc(gfp, 0); if (!ptdesc) return NULL; - if (!pagetable_pmd_ctor(ptdesc)) { + if (!pagetable_pmd_ctor(mm, ptdesc)) { pagetable_free(ptdesc); return NULL; } diff --git a/arch/powerpc/mm/pgtable-frag.c b/arch/powerpc/mm/pgtable-frag.c index 713268ccb1a0..387e9b1fe12c 100644 --- a/arch/powerpc/mm/pgtable-frag.c +++ b/arch/powerpc/mm/pgtable-frag.c @@ -61,7 +61,7 @@ static pte_t *__alloc_for_ptecache(struct mm_struct *mm, int kernel) ptdesc = pagetable_alloc(PGALLOC_GFP | __GFP_ACCOUNT, 0); if (!ptdesc) return NULL; - if (!pagetable_pte_ctor(ptdesc)) { + if (!pagetable_pte_ctor(mm, ptdesc)) { pagetable_free(ptdesc); return NULL; } diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index ab475ec6ca42..e5ef693fc778 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -442,7 +442,7 @@ static phys_addr_t __meminit alloc_pte_late(uintptr_t va) { struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL & ~__GFP_HIGHMEM, 0); - BUG_ON(!ptdesc || !pagetable_pte_ctor(ptdesc)); + BUG_ON(!ptdesc || !pagetable_pte_ctor(NULL, ptdesc)); return __pa((pte_t *)ptdesc_address(ptdesc)); } @@ -522,7 +522,7 @@ static phys_addr_t __meminit alloc_pmd_late(uintptr_t va) { struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL & ~__GFP_HIGHMEM, 0); - BUG_ON(!ptdesc || !pagetable_pmd_ctor(ptdesc)); + BUG_ON(!ptdesc || !pagetable_pmd_ctor(NULL, ptdesc)); return __pa((pmd_t *)ptdesc_address(ptdesc)); } diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h index 005497ffebda..5345398df653 100644 --- a/arch/s390/include/asm/pgalloc.h +++ b/arch/s390/include/asm/pgalloc.h @@ -97,7 +97,7 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long vmaddr) if (!table) return NULL; crst_table_init(table, _SEGMENT_ENTRY_EMPTY); - if (!pagetable_pmd_ctor(virt_to_ptdesc(table))) { + if (!pagetable_pmd_ctor(mm, virt_to_ptdesc(table))) { crst_table_free(mm, table); return NULL; } diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c index e3a6f8ae156c..619d6917e3b7 100644 --- a/arch/s390/mm/pgalloc.c +++ b/arch/s390/mm/pgalloc.c @@ -145,7 +145,7 @@ unsigned long *page_table_alloc(struct mm_struct *mm) ptdesc = pagetable_alloc(GFP_KERNEL, 0); if (!ptdesc) return NULL; - if (!pagetable_pte_ctor(ptdesc)) { + if (!pagetable_pte_ctor(mm, ptdesc)) { pagetable_free(ptdesc); return NULL; } diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 760818950464..5c8eabda1d17 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -2895,7 +2895,7 @@ pgtable_t pte_alloc_one(struct mm_struct *mm) if (!ptdesc) return NULL; - if (!pagetable_pte_ctor(ptdesc)) { + if (!pagetable_pte_ctor(mm, ptdesc)) { pagetable_free(ptdesc); return NULL; } diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c index dd32711022f5..f8fb4911d360 100644 --- a/arch/sparc/mm/srmmu.c +++ b/arch/sparc/mm/srmmu.c @@ -350,7 +350,7 @@ pgtable_t pte_alloc_one(struct mm_struct *mm) page = pfn_to_page(__nocache_pa((unsigned long)ptep) >> PAGE_SHIFT); spin_lock(&mm->page_table_lock); if (page_ref_inc_return(page) == 2 && - !pagetable_pte_ctor(page_ptdesc(page))) { + !pagetable_pte_ctor(mm, page_ptdesc(page))) { page_ref_dec(page); ptep = NULL; } diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index f7ae44d3dd9e..9dbd25e52f10 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -205,7 +205,7 @@ static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[], int count) if (!ptdesc) failed = true; - if (ptdesc && !pagetable_pmd_ctor(ptdesc)) { + if (ptdesc && !pagetable_pmd_ctor(mm, ptdesc)) { pagetable_free(ptdesc); ptdesc = NULL; failed = true; diff --git a/include/asm-generic/pgalloc.h b/include/asm-generic/pgalloc.h index 892ece4558a2..e164ca66f0f6 100644 --- a/include/asm-generic/pgalloc.h +++ b/include/asm-generic/pgalloc.h @@ -70,7 +70,7 @@ static inline pgtable_t __pte_alloc_one_noprof(struct mm_struct *mm, gfp_t gfp) ptdesc = pagetable_alloc_noprof(gfp, 0); if (!ptdesc) return NULL; - if (!pagetable_pte_ctor(ptdesc)) { + if (!pagetable_pte_ctor(mm, ptdesc)) { pagetable_free(ptdesc); return NULL; } @@ -137,7 +137,7 @@ static inline pmd_t *pmd_alloc_one_noprof(struct mm_struct *mm, unsigned long ad ptdesc = pagetable_alloc_noprof(gfp, 0); if (!ptdesc) return NULL; - if (!pagetable_pmd_ctor(ptdesc)) { + if (!pagetable_pmd_ctor(mm, ptdesc)) { pagetable_free(ptdesc); return NULL; } diff --git a/include/linux/mm.h b/include/linux/mm.h index 1690f21e7808..fa22b17e337e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3147,7 +3147,8 @@ static inline void pagetable_dtor_free(struct ptdesc *ptdesc) pagetable_free(ptdesc); } -static inline bool pagetable_pte_ctor(struct ptdesc *ptdesc) +static inline bool pagetable_pte_ctor(struct mm_struct *mm, + struct ptdesc *ptdesc) { if (!ptlock_init(ptdesc)) return false; @@ -3253,7 +3254,8 @@ static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd) return ptl; } -static inline bool pagetable_pmd_ctor(struct ptdesc *ptdesc) +static inline bool pagetable_pmd_ctor(struct mm_struct *mm, + struct ptdesc *ptdesc) { if (!pmd_ptlock_init(ptdesc)) return false; -- cgit v1.2.3 From 49f5996664201a3581ee5ea5949ee7d5fafb9d86 Mon Sep 17 00:00:00 2001 From: Kevin Brodsky Date: Tue, 8 Apr 2025 10:52:13 +0100 Subject: mm: call ctor/dtor for kernel PTEs Since [1], constructors/destructors are expected to be called for all page table pages, at all levels and for both user and kernel pgtables. There is however one glaring exception: kernel PTEs are managed via separate helpers (pte_alloc_kernel/pte_free_kernel), which do not call the [cd]tor, at least not in the generic implementation. The most obvious reason for this anomaly is that init_mm is special-cased not to use split page table locks. As a result calling ptlock_init() for PTEs associated with init_mm would be wasteful, potentially resulting in dynamic memory allocation. However, pgtable [cd]tors perform other actions - currently related to accounting/statistics, and potentially more functionally significant in the future. Now that pagetable_pte_ctor() is passed the associated mm, we can make it skip the call to ptlock_init() for init_mm; this allows us to call the ctor from pte_alloc_one_kernel() too. This is matched by a call to the pgtable destructor in pte_free_kernel(); no special-casing is needed on that path, as ptlock_free() is already called unconditionally. (ptlock_free() is a no-op unless a ptlock was allocated for the given PTP.) This patch ensures that all architectures that rely on call the [cd]tor for kernel PTEs. pte_free_kernel() cannot be overridden so changing the generic implementation is sufficient. pte_alloc_one_kernel() can be overridden using __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL, and a few architectures implement it by calling the page allocator directly. We amend those so that they call the generic __pte_alloc_one_kernel() instead, if possible, ensuring that the ctor is called. A few architectures do not use ; those will be taken care of separately. [1] https://lore.kernel.org/linux-mm/20250103184415.2744423-1-kevin.brodsky@arm.com/ Link: https://lkml.kernel.org/r/20250408095222.860601-4-kevin.brodsky@arm.com Signed-off-by: Kevin Brodsky Reviewed-by: Alexander Gordeev # s390 Cc: Albert Ou Cc: Andreas Larsson Cc: Catalin Marinas Cc: David S. Miller Cc: Geert Uytterhoeven Cc: Linus Waleij Cc: Madhavan Srinivasan Cc: Mark Rutland Cc: Matthew Wilcox (Oracle) Cc: Michael Ellerman Cc: Mike Rapoport Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Peter Zijlstra Cc: Qi Zheng Cc: Ryan Roberts Cc: Will Deacon Cc: Cc: Yang Shi Cc: Dave Hansen Signed-off-by: Andrew Morton --- arch/csky/include/asm/pgalloc.h | 2 +- arch/microblaze/mm/pgtable.c | 2 +- arch/openrisc/mm/ioremap.c | 2 +- include/asm-generic/pgalloc.h | 7 ++++++- include/linux/mm.h | 2 +- 5 files changed, 10 insertions(+), 5 deletions(-) (limited to 'include/asm-generic') diff --git a/arch/csky/include/asm/pgalloc.h b/arch/csky/include/asm/pgalloc.h index 11055c574968..9ed2b15ffd94 100644 --- a/arch/csky/include/asm/pgalloc.h +++ b/arch/csky/include/asm/pgalloc.h @@ -29,7 +29,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm) pte_t *pte; unsigned long i; - pte = (pte_t *) __get_free_page(GFP_KERNEL); + pte = __pte_alloc_one_kernel(mm); if (!pte) return NULL; diff --git a/arch/microblaze/mm/pgtable.c b/arch/microblaze/mm/pgtable.c index 9f73265aad4e..e96dd1b7aba4 100644 --- a/arch/microblaze/mm/pgtable.c +++ b/arch/microblaze/mm/pgtable.c @@ -245,7 +245,7 @@ unsigned long iopa(unsigned long addr) __ref pte_t *pte_alloc_one_kernel(struct mm_struct *mm) { if (mem_init_done) - return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO); + return __pte_alloc_one_kernel(mm); else return memblock_alloc_try_nid(PAGE_SIZE, PAGE_SIZE, MEMBLOCK_LOW_LIMIT, diff --git a/arch/openrisc/mm/ioremap.c b/arch/openrisc/mm/ioremap.c index 8e63e86251ca..3b352f97fecb 100644 --- a/arch/openrisc/mm/ioremap.c +++ b/arch/openrisc/mm/ioremap.c @@ -36,7 +36,7 @@ pte_t __ref *pte_alloc_one_kernel(struct mm_struct *mm) pte_t *pte; if (likely(mem_init_done)) { - pte = (pte_t *)get_zeroed_page(GFP_KERNEL); + pte = __pte_alloc_one_kernel(mm); } else { pte = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE); } diff --git a/include/asm-generic/pgalloc.h b/include/asm-generic/pgalloc.h index e164ca66f0f6..3c8ec3bfea44 100644 --- a/include/asm-generic/pgalloc.h +++ b/include/asm-generic/pgalloc.h @@ -23,6 +23,11 @@ static inline pte_t *__pte_alloc_one_kernel_noprof(struct mm_struct *mm) if (!ptdesc) return NULL; + if (!pagetable_pte_ctor(mm, ptdesc)) { + pagetable_free(ptdesc); + return NULL; + } + return ptdesc_address(ptdesc); } #define __pte_alloc_one_kernel(...) alloc_hooks(__pte_alloc_one_kernel_noprof(__VA_ARGS__)) @@ -48,7 +53,7 @@ static inline pte_t *pte_alloc_one_kernel_noprof(struct mm_struct *mm) */ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) { - pagetable_free(virt_to_ptdesc(pte)); + pagetable_dtor_free(virt_to_ptdesc(pte)); } /** diff --git a/include/linux/mm.h b/include/linux/mm.h index fa22b17e337e..ce6832787f6d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3150,7 +3150,7 @@ static inline void pagetable_dtor_free(struct ptdesc *ptdesc) static inline bool pagetable_pte_ctor(struct mm_struct *mm, struct ptdesc *ptdesc) { - if (!ptlock_init(ptdesc)) + if (mm != &init_mm && !ptlock_init(ptdesc)) return false; __pagetable_ctor(ptdesc); return true; -- cgit v1.2.3 From 928930c2e0a8e1d9252aedb1fa9be83c3669dfd7 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Wed, 23 Apr 2025 14:33:38 +0100 Subject: mm: implement for_each_valid_pfn() for CONFIG_FLATMEM In the FLATMEM case, the default pfn_valid() just checks that the PFN is within the range [ ARCH_PFN_OFFSET .. ARCH_PFN_OFFSET + max_mapnr ). The for_each_valid_pfn() function can therefore be a simple for() loop using those as min/max respectively. Link: https://lkml.kernel.org/r/20250423133821.789413-3-dwmw2@infradead.org Signed-off-by: David Woodhouse Reviewed-by: Mike Rapoport (Microsoft) Acked-by: David Hildenbrand Cc: Anshuman Khandual Cc: Ard Biesheuvel Cc: Catalin Marinas Cc: Marc Rutland Cc: Marc Zyngier Cc: Ruihan Li Cc: Will Deacon Cc: Lorenzo Stoakes Signed-off-by: Andrew Morton --- include/asm-generic/memory_model.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/asm-generic') diff --git a/include/asm-generic/memory_model.h b/include/asm-generic/memory_model.h index a3b5029aebbd..74d0077cc5fa 100644 --- a/include/asm-generic/memory_model.h +++ b/include/asm-generic/memory_model.h @@ -30,7 +30,15 @@ static inline int pfn_valid(unsigned long pfn) return pfn >= pfn_offset && (pfn - pfn_offset) < max_mapnr; } #define pfn_valid pfn_valid -#endif + +#ifndef for_each_valid_pfn +#define for_each_valid_pfn(pfn, start_pfn, end_pfn) \ + for ((pfn) = max_t(unsigned long, (start_pfn), ARCH_PFN_OFFSET); \ + (pfn) < min_t(unsigned long, (end_pfn), \ + ARCH_PFN_OFFSET + max_mapnr); \ + (pfn)++) +#endif /* for_each_valid_pfn */ +#endif /* valid_pfn */ #elif defined(CONFIG_SPARSEMEM_VMEMMAP) -- cgit v1.2.3