From fa28237cfcc5827553044cbd6ee52e33692b0faa Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Thu, 24 Jan 2008 08:35:13 +1100 Subject: [POWERPC] Provide a way to protect 4k subpages when using 64k pages Using 64k pages on 64-bit PowerPC systems makes life difficult for emulators that are trying to emulate an ISA, such as x86, which use a smaller page size, since the emulator can no longer use the MMU and the normal system calls for controlling page protections. Of course, the emulator can emulate the MMU by checking and possibly remapping the address for each memory access in software, but that is pretty slow. This provides a facility for such programs to control the access permissions on individual 4k sub-pages of 64k pages. The idea is that the emulator supplies an array of protection masks to apply to a specified range of virtual addresses. These masks are applied at the level where hardware PTEs are inserted into the hardware page table based on the Linux PTEs, so the Linux PTEs are not affected. Note that this new mechanism does not allow any access that would otherwise be prohibited; it can only prohibit accesses that would otherwise be allowed. This new facility is only available on 64-bit PowerPC and only when the kernel is configured for 64k pages. The masks are supplied using a new subpage_prot system call, which takes a starting virtual address and length, and a pointer to an array of protection masks in memory. The array has a 32-bit word per 64k page to be protected; each 32-bit word consists of 16 2-bit fields, for which 0 allows any access (that is otherwise allowed), 1 prevents write accesses, and 2 or 3 prevent any access. Implicit in this is that the regions of the address space that are protected are switched to use 4k hardware pages rather than 64k hardware pages (on machines with hardware 64k page support). In fact the whole process is switched to use 4k hardware pages when the subpage_prot system call is used, but this could be improved in future to switch only the affected segments. The subpage protection bits are stored in a 3 level tree akin to the page table tree. The top level of this tree is stored in a structure that is appended to the top level of the page table tree, i.e., the pgd array. Since it will often only be 32-bit addresses (below 4GB) that are protected, the pointers to the first four bottom level pages are also stored in this structure (each bottom level page contains the protection bits for 1GB of address space), so the protection bits for addresses below 4GB can be accessed with one fewer loads than those for higher addresses. Signed-off-by: Paul Mackerras --- arch/powerpc/mm/subpage-prot.c | 213 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 213 insertions(+) create mode 100644 arch/powerpc/mm/subpage-prot.c (limited to 'arch/powerpc/mm/subpage-prot.c') diff --git a/arch/powerpc/mm/subpage-prot.c b/arch/powerpc/mm/subpage-prot.c new file mode 100644 index 000000000000..4cafc0c33d0a --- /dev/null +++ b/arch/powerpc/mm/subpage-prot.c @@ -0,0 +1,213 @@ +/* + * Copyright 2007-2008 Paul Mackerras, IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +/* + * Free all pages allocated for subpage protection maps and pointers. + * Also makes sure that the subpage_prot_table structure is + * reinitialized for the next user. + */ +void subpage_prot_free(pgd_t *pgd) +{ + struct subpage_prot_table *spt = pgd_subpage_prot(pgd); + unsigned long i, j, addr; + u32 **p; + + for (i = 0; i < 4; ++i) { + if (spt->low_prot[i]) { + free_page((unsigned long)spt->low_prot[i]); + spt->low_prot[i] = NULL; + } + } + addr = 0; + for (i = 0; i < 2; ++i) { + p = spt->protptrs[i]; + if (!p) + continue; + spt->protptrs[i] = NULL; + for (j = 0; j < SBP_L2_COUNT && addr < spt->maxaddr; + ++j, addr += PAGE_SIZE) + if (p[j]) + free_page((unsigned long)p[j]); + free_page((unsigned long)p); + } + spt->maxaddr = 0; +} + +static void hpte_flush_range(struct mm_struct *mm, unsigned long addr, + int npages) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + spinlock_t *ptl; + + pgd = pgd_offset(mm, addr); + if (pgd_none(*pgd)) + return; + pud = pud_offset(pgd, addr); + if (pud_none(*pud)) + return; + pmd = pmd_offset(pud, addr); + if (pmd_none(*pmd)) + return; + pte = pte_offset_map_lock(mm, pmd, addr, &ptl); + arch_enter_lazy_mmu_mode(); + for (; npages > 0; --npages) { + pte_update(mm, addr, pte, 0, 0); + addr += PAGE_SIZE; + ++pte; + } + arch_leave_lazy_mmu_mode(); + pte_unmap_unlock(pte - 1, ptl); +} + +/* + * Clear the subpage protection map for an address range, allowing + * all accesses that are allowed by the pte permissions. + */ +static void subpage_prot_clear(unsigned long addr, unsigned long len) +{ + struct mm_struct *mm = current->mm; + struct subpage_prot_table *spt = pgd_subpage_prot(mm->pgd); + u32 **spm, *spp; + int i, nw; + unsigned long next, limit; + + down_write(&mm->mmap_sem); + limit = addr + len; + if (limit > spt->maxaddr) + limit = spt->maxaddr; + for (; addr < limit; addr = next) { + next = pmd_addr_end(addr, limit); + if (addr < 0x100000000) { + spm = spt->low_prot; + } else { + spm = spt->protptrs[addr >> SBP_L3_SHIFT]; + if (!spm) + continue; + } + spp = spm[(addr >> SBP_L2_SHIFT) & (SBP_L2_COUNT - 1)]; + if (!spp) + continue; + spp += (addr >> PAGE_SHIFT) & (SBP_L1_COUNT - 1); + + i = (addr >> PAGE_SHIFT) & (PTRS_PER_PTE - 1); + nw = PTRS_PER_PTE - i; + if (addr + (nw << PAGE_SHIFT) > next) + nw = (next - addr) >> PAGE_SHIFT; + + memset(spp, 0, nw * sizeof(u32)); + + /* now flush any existing HPTEs for the range */ + hpte_flush_range(mm, addr, nw); + } + up_write(&mm->mmap_sem); +} + +/* + * Copy in a subpage protection map for an address range. + * The map has 2 bits per 4k subpage, so 32 bits per 64k page. + * Each 2-bit field is 0 to allow any access, 1 to prevent writes, + * 2 or 3 to prevent all accesses. + * Note that the normal page protections also apply; the subpage + * protection mechanism is an additional constraint, so putting 0 + * in a 2-bit field won't allow writes to a page that is otherwise + * write-protected. + */ +long sys_subpage_prot(unsigned long addr, unsigned long len, u32 __user *map) +{ + struct mm_struct *mm = current->mm; + struct subpage_prot_table *spt = pgd_subpage_prot(mm->pgd); + u32 **spm, *spp; + int i, nw; + unsigned long next, limit; + int err; + + /* Check parameters */ + if ((addr & ~PAGE_MASK) || (len & ~PAGE_MASK) || + addr >= TASK_SIZE || len >= TASK_SIZE || addr + len > TASK_SIZE) + return -EINVAL; + + if (is_hugepage_only_range(mm, addr, len)) + return -EINVAL; + + if (!map) { + /* Clear out the protection map for the address range */ + subpage_prot_clear(addr, len); + return 0; + } + + if (!access_ok(VERIFY_READ, map, (len >> PAGE_SHIFT) * sizeof(u32))) + return -EFAULT; + + down_write(&mm->mmap_sem); + for (limit = addr + len; addr < limit; addr = next) { + next = pmd_addr_end(addr, limit); + err = -ENOMEM; + if (addr < 0x100000000) { + spm = spt->low_prot; + } else { + spm = spt->protptrs[addr >> SBP_L3_SHIFT]; + if (!spm) { + spm = (u32 **)get_zeroed_page(GFP_KERNEL); + if (!spm) + goto out; + spt->protptrs[addr >> SBP_L3_SHIFT] = spm; + } + } + spm += (addr >> SBP_L2_SHIFT) & (SBP_L2_COUNT - 1); + spp = *spm; + if (!spp) { + spp = (u32 *)get_zeroed_page(GFP_KERNEL); + if (!spp) + goto out; + *spm = spp; + } + spp += (addr >> PAGE_SHIFT) & (SBP_L1_COUNT - 1); + + local_irq_disable(); + demote_segment_4k(mm, addr); + local_irq_enable(); + + i = (addr >> PAGE_SHIFT) & (PTRS_PER_PTE - 1); + nw = PTRS_PER_PTE - i; + if (addr + (nw << PAGE_SHIFT) > next) + nw = (next - addr) >> PAGE_SHIFT; + + up_write(&mm->mmap_sem); + err = -EFAULT; + if (__copy_from_user(spp, map, nw * sizeof(u32))) + goto out2; + map += nw; + down_write(&mm->mmap_sem); + + /* now flush any existing HPTEs for the range */ + hpte_flush_range(mm, addr, nw); + } + if (limit > spt->maxaddr) + spt->maxaddr = limit; + err = 0; + out: + up_write(&mm->mmap_sem); + out2: + return err; +} -- cgit v1.2.3