From 28080329ede3e4110bb14306b4529a5b9a2ce163 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Mon, 14 May 2012 15:33:28 +0900 Subject: sh: Enable shared page fault handler for _32/_64. This moves the now generic _32 page fault handling code to a shared place and adapts the _64 implementation to make use of it. Signed-off-by: Paul Mundt --- arch/sh/mm/fault.c | 508 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 508 insertions(+) create mode 100644 arch/sh/mm/fault.c (limited to 'arch/sh/mm/fault.c') diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c new file mode 100644 index 000000000000..16799f920f90 --- /dev/null +++ b/arch/sh/mm/fault.c @@ -0,0 +1,508 @@ +/* + * Page fault handler for SH with an MMU. + * + * Copyright (C) 1999 Niibe Yutaka + * Copyright (C) 2003 - 2012 Paul Mundt + * + * Based on linux/arch/i386/mm/fault.c: + * Copyright (C) 1995 Linus Torvalds + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +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) +{ + siginfo_t info; + + info.si_signo = si_signo; + info.si_errno = 0; + info.si_code = si_code; + info.si_addr = (void __user *)address; + + force_sig_info(si_signo, &info, tsk); +} + +/* + * This is useful to dump out the page tables associated with + * 'addr' in mm 'mm'. + */ +static void show_pte(struct mm_struct *mm, unsigned long addr) +{ + pgd_t *pgd; + + if (mm) + pgd = mm->pgd; + else + pgd = get_TTB(); + + printk(KERN_ALERT "pgd = %p\n", pgd); + pgd += pgd_index(addr); + printk(KERN_ALERT "[%08lx] *pgd=%0*Lx", addr, + (u32)(sizeof(*pgd) * 2), (u64)pgd_val(*pgd)); + + do { + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + if (pgd_none(*pgd)) + break; + + if (pgd_bad(*pgd)) { + printk("(bad)"); + break; + } + + pud = pud_offset(pgd, addr); + if (PTRS_PER_PUD != 1) + printk(", *pud=%0*Lx", (u32)(sizeof(*pud) * 2), + (u64)pud_val(*pud)); + + if (pud_none(*pud)) + break; + + if (pud_bad(*pud)) { + printk("(bad)"); + break; + } + + pmd = pmd_offset(pud, addr); + if (PTRS_PER_PMD != 1) + printk(", *pmd=%0*Lx", (u32)(sizeof(*pmd) * 2), + (u64)pmd_val(*pmd)); + + if (pmd_none(*pmd)) + break; + + if (pmd_bad(*pmd)) { + printk("(bad)"); + break; + } + + /* We must not map this if we have highmem enabled */ + if (PageHighMem(pfn_to_page(pmd_val(*pmd) >> PAGE_SHIFT))) + break; + + pte = pte_offset_kernel(pmd, addr); + printk(", *pte=%0*Lx", (u32)(sizeof(*pte) * 2), + (u64)pte_val(*pte)); + } while (0); + + printk("\n"); +} + +static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address) +{ + unsigned index = pgd_index(address); + pgd_t *pgd_k; + pud_t *pud, *pud_k; + pmd_t *pmd, *pmd_k; + + pgd += index; + pgd_k = init_mm.pgd + index; + + if (!pgd_present(*pgd_k)) + return NULL; + + pud = pud_offset(pgd, address); + pud_k = pud_offset(pgd_k, address); + if (!pud_present(*pud_k)) + return NULL; + + if (!pud_present(*pud)) + set_pud(pud, *pud_k); + + pmd = pmd_offset(pud, address); + pmd_k = pmd_offset(pud_k, address); + if (!pmd_present(*pmd_k)) + return NULL; + + if (!pmd_present(*pmd)) + set_pmd(pmd, *pmd_k); + else { + /* + * The page tables are fully synchronised so there must + * be another reason for the fault. Return NULL here to + * signal that we have not taken care of the fault. + */ + BUG_ON(pmd_page(*pmd) != pmd_page(*pmd_k)); + return NULL; + } + + return pmd_k; +} + +/* + * Handle a fault on the vmalloc or module mapping area + */ +static noinline int vmalloc_fault(unsigned long address) +{ + pgd_t *pgd_k; + pmd_t *pmd_k; + pte_t *pte_k; + + /* Make sure we are in vmalloc/module area: */ + if (!is_vmalloc_addr((void *)address)) + return -1; + + /* + * Synchronize this task's top level page-table + * with the 'reference' page table. + * + * Do _not_ use "current" here. We might be inside + * an interrupt in the middle of a task switch.. + */ + pgd_k = get_TTB(); + pmd_k = vmalloc_sync_one(pgd_k, address); + if (!pmd_k) + return -1; + + pte_k = pte_offset_kernel(pmd_k, address); + if (!pte_present(*pte_k)) + return -1; + + return 0; +} + +static void +show_fault_oops(struct pt_regs *regs, unsigned long address) +{ + if (!oops_may_print()) + return; + + printk(KERN_ALERT "BUG: unable to handle kernel "); + if (address < PAGE_SIZE) + printk(KERN_CONT "NULL pointer dereference"); + else + printk(KERN_CONT "paging request"); + + printk(KERN_CONT " at %08lx\n", address); + printk(KERN_ALERT "PC:"); + printk_address(regs->pc, 1); + + show_pte(NULL, address); +} + +static noinline void +no_context(struct pt_regs *regs, unsigned long error_code, + unsigned long address) +{ + /* Are we prepared to handle this kernel fault? */ + if (fixup_exception(regs)) + return; + + if (handle_trapped_io(regs, address)) + return; + + /* + * Oops. The kernel tried to access some bad page. We'll have to + * terminate things with extreme prejudice. + */ + bust_spinlocks(1); + + show_fault_oops(regs, address); + + die("Oops", regs, error_code); + bust_spinlocks(0); + do_exit(SIGKILL); +} + +static void +__bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, + unsigned long address, int si_code) +{ + struct task_struct *tsk = current; + + /* User mode accesses just cause a SIGSEGV */ + if (user_mode(regs)) { + /* + * It's possible to have interrupts off here: + */ + local_irq_enable(); + + force_sig_info_fault(SIGSEGV, si_code, address, tsk); + + return; + } + + no_context(regs, error_code, address); +} + +static noinline void +bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, + unsigned long address) +{ + __bad_area_nosemaphore(regs, error_code, address, SEGV_MAPERR); +} + +static void +__bad_area(struct pt_regs *regs, unsigned long error_code, + unsigned long address, int si_code) +{ + struct mm_struct *mm = current->mm; + + /* + * Something tried to access memory that isn't in our memory map.. + * Fix it, but check if it's kernel or user first.. + */ + up_read(&mm->mmap_sem); + + __bad_area_nosemaphore(regs, error_code, address, si_code); +} + +static noinline void +bad_area(struct pt_regs *regs, unsigned long error_code, unsigned long address) +{ + __bad_area(regs, error_code, address, SEGV_MAPERR); +} + +static noinline void +bad_area_access_error(struct pt_regs *regs, unsigned long error_code, + unsigned long address) +{ + __bad_area(regs, error_code, address, SEGV_ACCERR); +} + +static void out_of_memory(void) +{ + /* + * We ran out of memory, call the OOM killer, and return the userspace + * (which will retry the fault, or kill us if we got oom-killed): + */ + up_read(¤t->mm->mmap_sem); + + pagefault_out_of_memory(); +} + +static void +do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address) +{ + struct task_struct *tsk = current; + struct mm_struct *mm = tsk->mm; + + up_read(&mm->mmap_sem); + + /* Kernel mode? Handle exceptions or die: */ + if (!user_mode(regs)) + no_context(regs, error_code, address); + + force_sig_info_fault(SIGBUS, BUS_ADRERR, address, tsk); +} + +static noinline int +mm_fault_error(struct pt_regs *regs, unsigned long error_code, + unsigned long address, unsigned int fault) +{ + /* + * Pagefault was interrupted by SIGKILL. We have no reason to + * continue pagefault. + */ + if (fatal_signal_pending(current)) { + if (!(fault & VM_FAULT_RETRY)) + up_read(¤t->mm->mmap_sem); + if (!user_mode(regs)) + no_context(regs, error_code, address); + return 1; + } + + if (!(fault & VM_FAULT_ERROR)) + return 0; + + if (fault & VM_FAULT_OOM) { + /* Kernel mode? Handle exceptions or die: */ + if (!user_mode(regs)) { + up_read(¤t->mm->mmap_sem); + no_context(regs, error_code, address); + return 1; + } + + out_of_memory(); + } else { + if (fault & VM_FAULT_SIGBUS) + do_sigbus(regs, error_code, address); + else + BUG(); + } + + return 1; +} + +static inline int access_error(int error_code, struct vm_area_struct *vma) +{ + if (error_code & FAULT_CODE_WRITE) { + /* write, present and write, not present: */ + if (unlikely(!(vma->vm_flags & VM_WRITE))) + return 1; + return 0; + } + + /* ITLB miss on NX page */ + if (unlikely((error_code & FAULT_CODE_ITLB) && + !(vma->vm_flags & VM_EXEC))) + return 1; + + /* read, not present: */ + if (unlikely(!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))) + return 1; + + return 0; +} + +static int fault_in_kernel_space(unsigned long address) +{ + return address >= TASK_SIZE; +} + +/* + * This routine handles page faults. It determines the address, + * and the problem, and then passes it off to one of the appropriate + * routines. + */ +asmlinkage void __kprobes do_page_fault(struct pt_regs *regs, + unsigned long error_code, + unsigned long address) +{ + unsigned long vec; + struct task_struct *tsk; + struct mm_struct *mm; + struct vm_area_struct * vma; + int fault; + int write = error_code & FAULT_CODE_WRITE; + unsigned int flags = (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE | + (write ? FAULT_FLAG_WRITE : 0)); + + tsk = current; + mm = tsk->mm; + vec = lookup_exception_vector(); + + /* + * We fault-in kernel-space virtual memory on-demand. The + * 'reference' page table is init_mm.pgd. + * + * NOTE! We MUST NOT take any locks for this case. We may + * be in an interrupt or a critical region, and should + * only copy the information from the master page table, + * nothing more. + */ + if (unlikely(fault_in_kernel_space(address))) { + if (vmalloc_fault(address) >= 0) + return; + if (notify_page_fault(regs, vec)) + return; + + bad_area_nosemaphore(regs, error_code, address); + return; + } + + if (unlikely(notify_page_fault(regs, vec))) + return; + + /* Only enable interrupts if they were on before the fault */ + if ((regs->sr & SR_IMASK) != SR_IMASK) + local_irq_enable(); + + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); + + /* + * If we're in an interrupt, have no user context or are running + * in an atomic region then we must not take the fault: + */ + if (unlikely(in_atomic() || !mm)) { + bad_area_nosemaphore(regs, error_code, address); + return; + } + +retry: + down_read(&mm->mmap_sem); + + vma = find_vma(mm, address); + if (unlikely(!vma)) { + bad_area(regs, error_code, address); + return; + } + if (likely(vma->vm_start <= address)) + goto good_area; + if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) { + bad_area(regs, error_code, address); + return; + } + if (unlikely(expand_stack(vma, address))) { + bad_area(regs, error_code, address); + return; + } + + /* + * Ok, we have a good vm_area for this memory access, so + * we can handle it.. + */ +good_area: + if (unlikely(access_error(error_code, vma))) { + bad_area_access_error(regs, error_code, address); + return; + } + + set_thread_fault_code(error_code); + + /* + * If for any reason at all we couldn't handle the fault, + * make sure we exit gracefully rather than endlessly redo + * the fault. + */ + fault = handle_mm_fault(mm, vma, address, flags); + + if (unlikely(fault & (VM_FAULT_RETRY | VM_FAULT_ERROR))) + if (mm_fault_error(regs, error_code, address, fault)) + return; + + if (flags & FAULT_FLAG_ALLOW_RETRY) { + if (fault & VM_FAULT_MAJOR) { + tsk->maj_flt++; + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, + regs, address); + } else { + tsk->min_flt++; + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, + regs, address); + } + if (fault & VM_FAULT_RETRY) { + flags &= ~FAULT_FLAG_ALLOW_RETRY; + + /* + * No need to up_read(&mm->mmap_sem) as we would + * have already released it in __lock_page_or_retry + * in mm/filemap.c. + */ + goto retry; + } + } + + up_read(&mm->mmap_sem); +} -- cgit v1.2.3 From c3e0af98792f9f1c840dc969f883e46d0ced3e00 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Fri, 18 May 2012 19:30:05 +0900 Subject: Revert "sh: Ensure fixmap and store queue space can co-exist." This reverts commit 20e7c297efeca0861adcca073a0d283da659834b. With store queues enabled the area above P4SEG has special properties from the MMU's point of view, which was causing fixmap failure. We'll have to do something else to satisfy the vmalloc range check. Signed-off-by: Paul Mundt --- arch/sh/include/asm/fixmap.h | 2 +- arch/sh/mm/fault.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'arch/sh/mm/fault.c') diff --git a/arch/sh/include/asm/fixmap.h b/arch/sh/include/asm/fixmap.h index 41cda1264bb0..cbe0186b6794 100644 --- a/arch/sh/include/asm/fixmap.h +++ b/arch/sh/include/asm/fixmap.h @@ -94,7 +94,7 @@ extern void __clear_fixmap(enum fixed_addresses idx, pgprot_t flags); * at the top of mem.. */ #ifdef CONFIG_SUPERH32 -#define FIXADDR_TOP (P3_ADDR_MAX - PAGE_SIZE) +#define FIXADDR_TOP (P4SEG - PAGE_SIZE) #else #define FIXADDR_TOP ((unsigned long)(-PAGE_SIZE)) #endif diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c index 16799f920f90..b0345f09c197 100644 --- a/arch/sh/mm/fault.c +++ b/arch/sh/mm/fault.c @@ -169,8 +169,8 @@ static noinline int vmalloc_fault(unsigned long address) pmd_t *pmd_k; pte_t *pte_k; - /* Make sure we are in vmalloc/module area: */ - if (!is_vmalloc_addr((void *)address)) + /* Make sure we are in vmalloc/module/P3 area: */ + if (!(address >= P3SEG && address < P3_ADDR_MAX)) return -1; /* -- cgit v1.2.3 From d8fd35fc586f74b2defe011d3a2bfb507871a407 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Fri, 18 May 2012 20:01:16 +0900 Subject: sh64: Fix up vmalloc fault range check. With the previous attempt reverted this switches to conditionalizing the end address. Nominally VMALLOC_END, but extended for P3_ADDR_MAX in the store queue case. Signed-off-by: Paul Mundt --- arch/sh/mm/fault.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'arch/sh/mm/fault.c') diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c index b0345f09c197..1fc25d85e515 100644 --- a/arch/sh/mm/fault.c +++ b/arch/sh/mm/fault.c @@ -160,6 +160,12 @@ static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address) return pmd_k; } +#ifdef CONFIG_SH_STORE_QUEUES +#define __FAULT_ADDR_LIMIT P3_ADDR_MAX +#else +#define __FAULT_ADDR_LIMIT VMALLOC_END +#endif + /* * Handle a fault on the vmalloc or module mapping area */ @@ -170,7 +176,7 @@ static noinline int vmalloc_fault(unsigned long address) pte_t *pte_k; /* Make sure we are in vmalloc/module/P3 area: */ - if (!(address >= P3SEG && address < P3_ADDR_MAX)) + if (!(address >= VMALLOC_START && address < __FAULT_ADDR_LIMIT)) return -1; /* -- cgit v1.2.3