[RFC V2] mm: Generalize notify_page_fault()
From: Anshuman Khandual <hidden>
Date: 2019-06-04 06:35:49
Also in:
linux-arm-kernel, linux-mm, linux-s390, linux-sh, lkml, sparclinux
Subsystem:
arm port, arm64 port (aarch64 architecture), linux for powerpc (32-bit and 64-bit), memory management, memory management - core, s390 architecture, sparc + ultrasparc (sparc/sparc64), superh, the rest, x86 architecture (32-bit and 64-bit), x86 mm · Maintainers:
Russell King, Catalin Marinas, Will Deacon, Madhavan Srinivasan, Andrew Morton, David Hildenbrand, Heiko Carstens, Vasily Gorbik, Alexander Gordeev, "David S. Miller", Andreas Larsson, Yoshinori Sato, Rich Felker, John Paul Adrian Glaubitz, Linus Torvalds, Thomas Gleixner, Ingo Molnar, Borislav Petkov, Dave Hansen, Andy Lutomirski, Peter Zijlstra
Similar notify_page_fault() definitions are being used by architectures duplicating much of the same code. This attempts to unify them into a single implementation, generalize it and then move it to a common place. kprobes_built_in() can detect CONFIG_KPROBES, hence notify_page_fault() need not be wrapped again within CONFIG_KPROBES. Trap number argument can now contain upto an 'unsigned int' accommodating all possible platforms. Cc: linux-arm-kernel@lists.infradead.org Cc: linux-ia64@vger.kernel.org Cc: linuxppc-dev@lists.ozlabs.org Cc: linux-s390@vger.kernel.org Cc: linux-sh@vger.kernel.org Cc: sparclinux@vger.kernel.org Cc: x86@kernel.org Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Christophe Leroy <redacted> Cc: Stephen Rothwell <redacted> Cc: Andrey Konovalov <redacted> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Paul Mackerras <redacted> Cc: Russell King <linux@armlinux.org.uk> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <redacted> Cc: Tony Luck <tony.luck@intel.com> Cc: Fenghua Yu <redacted> Cc: Martin Schwidefsky <redacted> Cc: Heiko Carstens <redacted> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: "David S. Miller" <davem@davemloft.net> Cc: Thomas Gleixner <redacted> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Dave Hansen <dave.hansen@linux.intel.com> Signed-off-by: Anshuman Khandual <redacted> --- Testing: - Build and boot tested on arm64 and x86 - Build tested on some other archs (arm, sparc64, alpha, powerpc etc) Changes in RFC V2: - Changed generic notify_page_fault() per Mathew Wilcox - Changed x86 to use new generic notify_page_fault() - s/must not/need not/ in commit message per Matthew Wilcox Changes in RFC V1: (https://patchwork.kernel.org/patch/10968273/) arch/arm/mm/fault.c | 22 ---------------------- arch/arm64/mm/fault.c | 22 ---------------------- arch/ia64/mm/fault.c | 22 ---------------------- arch/powerpc/mm/fault.c | 23 ++--------------------- arch/s390/mm/fault.c | 16 +--------------- arch/sh/mm/fault.c | 14 -------------- arch/sparc/mm/fault_64.c | 16 +--------------- arch/x86/mm/fault.c | 21 ++------------------- include/linux/mm.h | 1 + mm/memory.c | 16 ++++++++++++++++ 10 files changed, 23 insertions(+), 150 deletions(-)
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 58f69fa..1bc3b18 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c@@ -30,28 +30,6 @@ #ifdef CONFIG_MMU -#ifdef CONFIG_KPROBES -static inline int notify_page_fault(struct pt_regs *regs, unsigned int fsr) -{ - int ret = 0; - - if (!user_mode(regs)) { - /* kprobe_running() needs smp_processor_id() */ - preempt_disable(); - if (kprobe_running() && kprobe_fault_handler(regs, fsr)) - ret = 1; - preempt_enable(); - } - - return ret; -} -#else -static inline int notify_page_fault(struct pt_regs *regs, unsigned int fsr) -{ - return 0; -} -#endif - /* * This is useful to dump out the page tables associated with * 'addr' in mm 'mm'.
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index a30818e..152f1f1 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c@@ -70,28 +70,6 @@ static inline const struct fault_info *esr_to_debug_fault_info(unsigned int esr) return debug_fault_info + DBG_ESR_EVT(esr); } -#ifdef CONFIG_KPROBES -static inline int notify_page_fault(struct pt_regs *regs, unsigned int esr) -{ - int ret = 0; - - /* kprobe_running() needs smp_processor_id() */ - if (!user_mode(regs)) { - preempt_disable(); - if (kprobe_running() && kprobe_fault_handler(regs, esr)) - ret = 1; - preempt_enable(); - } - - return ret; -} -#else -static inline int notify_page_fault(struct pt_regs *regs, unsigned int esr) -{ - return 0; -} -#endif - static void data_abort_decode(unsigned int esr) { pr_alert("Data abort info:\n");
diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c
index 5baeb02..64283d2 100644
--- a/arch/ia64/mm/fault.c
+++ b/arch/ia64/mm/fault.c@@ -21,28 +21,6 @@ extern int die(char *, struct pt_regs *, long); -#ifdef CONFIG_KPROBES -static inline int notify_page_fault(struct pt_regs *regs, int trap) -{ - int ret = 0; - - if (!user_mode(regs)) { - /* kprobe_running() needs smp_processor_id() */ - preempt_disable(); - if (kprobe_running() && kprobe_fault_handler(regs, trap)) - ret = 1; - preempt_enable(); - } - - return ret; -} -#else -static inline int notify_page_fault(struct pt_regs *regs, int trap) -{ - return 0; -} -#endif - /* * Return TRUE if ADDRESS points at a page in the kernel's mapped segment * (inside region 5, on ia64) and that page is present.
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index b5d3578..5a0d71f 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c@@ -46,26 +46,6 @@ #include <asm/debug.h> #include <asm/kup.h> -static inline bool notify_page_fault(struct pt_regs *regs) -{ - bool ret = false; - -#ifdef CONFIG_KPROBES - /* kprobe_running() needs smp_processor_id() */ - if (!user_mode(regs)) { - preempt_disable(); - if (kprobe_running() && kprobe_fault_handler(regs, 11)) - ret = true; - preempt_enable(); - } -#endif /* CONFIG_KPROBES */ - - if (unlikely(debugger_fault_handler(regs))) - ret = true; - - return ret; -} - /* * Check whether the instruction inst is a store using * an update addressing form which will update r1.
@@ -466,8 +446,9 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address, int is_write = page_fault_is_write(error_code); vm_fault_t fault, major = 0; bool must_retry = false; + int kprobe_fault = notify_page_fault(regs, 11); - if (notify_page_fault(regs)) + if (unlikely(debugger_fault_handler(regs) || kprobe_fault)) return 0; if (unlikely(page_fault_is_bad(error_code))) {
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index c220399..d317263 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c@@ -67,20 +67,6 @@ static int __init fault_init(void) } early_initcall(fault_init); -static inline int notify_page_fault(struct pt_regs *regs) -{ - int ret = 0; - - /* kprobe_running() needs smp_processor_id() */ - if (kprobes_built_in() && !user_mode(regs)) { - preempt_disable(); - if (kprobe_running() && kprobe_fault_handler(regs, 14)) - ret = 1; - preempt_enable(); - } - return ret; -} - /* * Find out which address space caused the exception. * Access register mode is impossible, ignore space == 3.
@@ -409,7 +395,7 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access) */ clear_pt_regs_flag(regs, PIF_PER_TRAP); - if (notify_page_fault(regs)) + if (notify_page_fault(regs, 14)) return 0; mm = tsk->mm;
diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c
index 6defd2c6..94bdfcb 100644
--- a/arch/sh/mm/fault.c
+++ b/arch/sh/mm/fault.c@@ -24,20 +24,6 @@ #include <asm/tlbflush.h> #include <asm/traps.h> -static inline int notify_page_fault(struct pt_regs *regs, int trap) -{ - int ret = 0; - - if (kprobes_built_in() && !user_mode(regs)) { - preempt_disable(); - if (kprobe_running() && kprobe_fault_handler(regs, trap)) - ret = 1; - preempt_enable(); - } - - return ret; -} - static void force_sig_info_fault(int si_signo, int si_code, unsigned long address, struct task_struct *tsk)
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index 8f8a604..e5557a1 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c@@ -38,20 +38,6 @@ int show_unhandled_signals = 1; -static inline __kprobes int notify_page_fault(struct pt_regs *regs) -{ - int ret = 0; - - /* kprobe_running() needs smp_processor_id() */ - if (kprobes_built_in() && !user_mode(regs)) { - preempt_disable(); - if (kprobe_running() && kprobe_fault_handler(regs, 0)) - ret = 1; - preempt_enable(); - } - return ret; -} - static void __kprobes unhandled_fault(unsigned long address, struct task_struct *tsk, struct pt_regs *regs)
@@ -285,7 +271,7 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs) fault_code = get_thread_fault_code(); - if (notify_page_fault(regs)) + if (notify_page_fault(regs, 0)) goto exit_exception; si_code = SEGV_MAPERR;
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 46df4c6..1790859 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c@@ -46,23 +46,6 @@ kmmio_fault(struct pt_regs *regs, unsigned long addr) return 0; } -static nokprobe_inline int kprobes_fault(struct pt_regs *regs) -{ - if (!kprobes_built_in()) - return 0; - if (user_mode(regs)) - return 0; - /* - * To be potentially processing a kprobe fault and to be allowed to call - * kprobe_running(), we have to be non-preemptible. - */ - if (preemptible()) - return 0; - if (!kprobe_running()) - return 0; - return kprobe_fault_handler(regs, X86_TRAP_PF); -} - /* * Prefetch quirks: *
@@ -1280,7 +1263,7 @@ do_kern_addr_fault(struct pt_regs *regs, unsigned long hw_error_code, return; /* kprobes don't want to hook the spurious faults: */ - if (kprobes_fault(regs)) + if (notify_page_fault(regs, X86_TRAP_PF)) return; /*
@@ -1311,7 +1294,7 @@ void do_user_addr_fault(struct pt_regs *regs, mm = tsk->mm; /* kprobes don't want to hook the spurious faults: */ - if (unlikely(kprobes_fault(regs))) + if (unlikely(notify_page_fault(regs, X86_TRAP_PF))) return; /*
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0e8834a..c5a8dcf 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h@@ -1778,6 +1778,7 @@ static inline int pte_devmap(pte_t pte) } #endif +int notify_page_fault(struct pt_regs *regs, unsigned int trap); int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot); extern pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr,
diff --git a/mm/memory.c b/mm/memory.c
index ddf20bd..b6bae8f 100644
--- a/mm/memory.c
+++ b/mm/memory.c@@ -52,6 +52,7 @@ #include <linux/pagemap.h> #include <linux/memremap.h> #include <linux/ksm.h> +#include <linux/kprobes.h> #include <linux/rmap.h> #include <linux/export.h> #include <linux/delayacct.h>
@@ -141,6 +142,21 @@ static int __init init_zero_pfn(void) core_initcall(init_zero_pfn); +int __kprobes notify_page_fault(struct pt_regs *regs, unsigned int trap) +{ + int ret = 0; + + /* + * To be potentially processing a kprobe fault and to be allowed + * to call kprobe_running(), we have to be non-preemptible. + */ + if (kprobes_built_in() && !preemptible() && !user_mode(regs)) { + if (kprobe_running() && kprobe_fault_handler(regs, trap)) + ret = 1; + } + return ret; +} + #if defined(SPLIT_RSS_COUNTING) void sync_mm_rss(struct mm_struct *mm)
--
2.7.4