diff options
Diffstat (limited to 'arch/powerpc/mm/fault.c')
| -rw-r--r-- | arch/powerpc/mm/fault.c | 151 |
1 files changed, 99 insertions, 52 deletions
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index d53fed4eccbd..806c74e0d5ab 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -17,6 +17,7 @@ #include <linux/kernel.h> #include <linux/errno.h> #include <linux/string.h> +#include <linux/string_choices.h> #include <linux/types.h> #include <linux/pagemap.h> #include <linux/ptrace.h> @@ -71,28 +72,26 @@ static noinline int bad_area_nosemaphore(struct pt_regs *regs, unsigned long add return __bad_area_nosemaphore(regs, address, SEGV_MAPERR); } -static int __bad_area(struct pt_regs *regs, unsigned long address, int si_code) +static int __bad_area(struct pt_regs *regs, unsigned long address, int si_code, + struct mm_struct *mm, struct vm_area_struct *vma) { - 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.. */ - mmap_read_unlock(mm); + if (mm) + mmap_read_unlock(mm); + else + vma_end_read(vma); return __bad_area_nosemaphore(regs, address, si_code); } -static noinline int bad_area(struct pt_regs *regs, unsigned long address) -{ - return __bad_area(regs, address, SEGV_MAPERR); -} - static noinline int bad_access_pkey(struct pt_regs *regs, unsigned long address, + struct mm_struct *mm, struct vm_area_struct *vma) { - struct mm_struct *mm = current->mm; int pkey; /* @@ -114,7 +113,10 @@ static noinline int bad_access_pkey(struct pt_regs *regs, unsigned long address, */ pkey = vma_pkey(vma); - mmap_read_unlock(mm); + if (mm) + mmap_read_unlock(mm); + else + vma_end_read(vma); /* * If we are in kernel mode, bail out with a SEGV, this will @@ -129,9 +131,10 @@ static noinline int bad_access_pkey(struct pt_regs *regs, unsigned long address, return 0; } -static noinline int bad_access(struct pt_regs *regs, unsigned long address) +static noinline int bad_access(struct pt_regs *regs, unsigned long address, + struct mm_struct *mm, struct vm_area_struct *vma) { - return __bad_area(regs, address, SEGV_ACCERR); + return __bad_area(regs, address, SEGV_ACCERR, mm, vma); } static int do_sigbus(struct pt_regs *regs, unsigned long address, @@ -216,7 +219,7 @@ static bool bad_kernel_fault(struct pt_regs *regs, unsigned long error_code, // Read/write fault blocked by KUAP is bad, it can never succeed. if (bad_kuap_fault(regs, address, is_write)) { pr_crit_ratelimited("Kernel attempted to %s user page (%lx) - exploit attempt? (uid: %d)\n", - is_write ? "write" : "read", address, + str_write_read(is_write), address, from_kuid(&init_user_ns, current_uid())); // Fault on user outside of certain regions (eg. copy_tofrom_user()) is bad @@ -270,8 +273,18 @@ static bool access_error(bool is_write, bool is_exec, struct vm_area_struct *vma return false; } + /* + * VM_READ, VM_WRITE and VM_EXEC may imply read permissions, as + * defined in protection_map[]. In that case Read faults can only be + * caused by a PROT_NONE mapping. However a non exec access on a + * VM_EXEC only mapping is invalid anyway, so report it as such. + */ if (unlikely(!vma_is_accessible(vma))) return true; + + if ((vma->vm_flags & VM_ACCESS_FLAGS) == VM_EXEC) + return true; + /* * We should ideally do the vma pkey access check here. But in the * fault path, handle_mm_fault() also does the same check. To avoid @@ -356,18 +369,33 @@ static void sanity_check_fault(bool is_write, bool is_user, * Define the correct "is_write" bit in error_code based * on the processor family */ -#if (defined(CONFIG_4xx) || defined(CONFIG_BOOKE)) +#ifdef CONFIG_BOOKE #define page_fault_is_write(__err) ((__err) & ESR_DST) #else #define page_fault_is_write(__err) ((__err) & DSISR_ISSTORE) #endif -#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE) +#ifdef CONFIG_BOOKE #define page_fault_is_bad(__err) (0) #elif defined(CONFIG_PPC_8xx) #define page_fault_is_bad(__err) ((__err) & DSISR_NOEXEC_OR_G) #elif defined(CONFIG_PPC64) -#define page_fault_is_bad(__err) ((__err) & DSISR_BAD_FAULT_64S) +static int page_fault_is_bad(unsigned long err) +{ + unsigned long flag = DSISR_BAD_FAULT_64S; + + /* + * PAPR+ v2.11 ยง 14.15.3.4.1 (unreleased) + * If byte 0, bit 3 of pi-attribute-specifier-type in + * ibm,pi-features property is defined, ignore the DSI error + * which is caused by the paste instruction on the + * suspended NX window. + */ + if (mmu_has_feature(MMU_FTR_NX_DSI)) + flag &= ~DSISR_BAD_COPYPASTE; + + return err & flag; +} #else #define page_fault_is_bad(__err) ((__err) & DSISR_BAD_FAULT_32S) #endif @@ -412,10 +440,16 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address, /* * The kernel should never take an execute fault nor should it * take a page fault to a kernel address or a page fault to a user - * address outside of dedicated places + * address outside of dedicated places. + * + * Rather than kfence directly reporting false negatives, search whether + * the NIP belongs to the fixup table for cases where fault could come + * from functions like copy_from_kernel_nofault(). */ if (unlikely(!is_user && bad_kernel_fault(regs, error_code, address, is_write))) { - if (kfence_handle_page_fault(address, is_write, regs)) + if (is_kfence_address((void *)address) && + !search_exception_tables(instruction_pointer(regs)) && + kfence_handle_page_fault(address, is_write, regs)) return 0; return SIGSEGV; @@ -450,6 +484,41 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address, if (is_exec) flags |= FAULT_FLAG_INSTRUCTION; + if (!(flags & FAULT_FLAG_USER)) + goto lock_mmap; + + vma = lock_vma_under_rcu(mm, address); + if (!vma) + goto lock_mmap; + + if (unlikely(access_pkey_error(is_write, is_exec, + (error_code & DSISR_KEYFAULT), vma))) { + count_vm_vma_lock_event(VMA_LOCK_SUCCESS); + return bad_access_pkey(regs, address, NULL, vma); + } + + if (unlikely(access_error(is_write, is_exec, vma))) { + count_vm_vma_lock_event(VMA_LOCK_SUCCESS); + return bad_access(regs, address, NULL, vma); + } + + fault = handle_mm_fault(vma, address, flags | FAULT_FLAG_VMA_LOCK, regs); + if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED))) + vma_end_read(vma); + + if (!(fault & VM_FAULT_RETRY)) { + count_vm_vma_lock_event(VMA_LOCK_SUCCESS); + goto done; + } + count_vm_vma_lock_event(VMA_LOCK_RETRY); + if (fault & VM_FAULT_MAJOR) + flags |= FAULT_FLAG_TRIED; + + if (fault_signal_pending(fault, regs)) + return user_mode(regs) ? 0 : SIGBUS; + +lock_mmap: + /* When running in the kernel we expect faults to occur only to * addresses in user space. All other faults represent errors in the * kernel and should generate an OOPS. Unfortunately, in the case of an @@ -457,47 +526,19 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address, * we will deadlock attempting to validate the fault against the * address space. Luckily the kernel only validly references user * space from well defined areas of code, which are listed in the - * exceptions table. - * - * As the vast majority of faults will be valid we will only perform - * the source reference check when there is a possibility of a deadlock. - * Attempt to lock the address space, if we cannot we then validate the - * source. If this is invalid we can skip the address space check, - * thus avoiding the deadlock. + * exceptions table. lock_mm_and_find_vma() handles that logic. */ - if (unlikely(!mmap_read_trylock(mm))) { - if (!is_user && !search_exception_tables(regs->nip)) - return bad_area_nosemaphore(regs, address); - retry: - mmap_read_lock(mm); - } else { - /* - * The above down_read_trylock() might have succeeded in - * which case we'll have missed the might_sleep() from - * down_read(): - */ - might_sleep(); - } - - vma = find_vma(mm, address); + vma = lock_mm_and_find_vma(mm, address, regs); if (unlikely(!vma)) - return bad_area(regs, address); - - if (unlikely(vma->vm_start > address)) { - if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) - return bad_area(regs, address); - - if (unlikely(expand_stack(vma, address))) - return bad_area(regs, address); - } + return bad_area_nosemaphore(regs, address); if (unlikely(access_pkey_error(is_write, is_exec, (error_code & DSISR_KEYFAULT), vma))) - return bad_access_pkey(regs, address, vma); + return bad_access_pkey(regs, address, mm, vma); if (unlikely(access_error(is_write, is_exec, vma))) - return bad_access(regs, address); + return bad_access(regs, address, mm, vma); /* * If for any reason at all we couldn't handle the fault, @@ -511,6 +552,10 @@ retry: if (fault_signal_pending(fault, regs)) return user_mode(regs) ? 0 : SIGBUS; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + goto out; + /* * Handle the retry right now, the mmap_lock has been released in that * case. @@ -522,9 +567,11 @@ retry: mmap_read_unlock(current->mm); +done: if (unlikely(fault & VM_FAULT_ERROR)) return mm_fault_error(regs, address, fault); +out: /* * Major/minor page fault accounting. */ @@ -579,7 +626,7 @@ static void __bad_page_fault(struct pt_regs *regs, int sig) case INTERRUPT_DATA_STORAGE: case INTERRUPT_H_DATA_STORAGE: pr_alert("BUG: %s on %s at 0x%08lx\n", msg, - is_write ? "write" : "read", regs->dar); + str_write_read(is_write), regs->dar); break; case INTERRUPT_DATA_SEGMENT: pr_alert("BUG: %s at 0x%08lx\n", msg, regs->dar); |