/* * Memory Migration functionality - linux/mm/migration.c * * Copyright (C) 2006 Silicon Graphics, Inc., Christoph Lameter * * Page migration was first developed in the context of the memory hotplug * project. The main authors of the migration code are: * * IWAMOTO Toshihiro * Hirokazu Takahashi * Dave Hansen * Christoph Lameter */ #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include "internal.h" /* * migrate_prep() needs to be called before we start compiling a list of pages * to be migrated using isolate_lru_page(). If scheduling work on other CPUs is * undesirable, use migrate_prep_local() */ int migrate_prep(void) { /* * Clear the LRU lists so pages can be isolated. * Note that pages may be moved off the LRU after we have * drained them. Those pages will fail to migrate like other * pages that may be busy. */ lru_add_drain_all(); return 0; } /* Do the necessary work of migrate_prep but not if it involves other CPUs */ int migrate_prep_local(void) { lru_add_drain(); return 0; } /* * Add isolated pages on the list back to the LRU under page lock * to avoid leaking evictable pages back onto unevictable list. */ void putback_lru_pages(struct list_head *l) { struct page *page; struct page *page2; list_for_each_entry_safe(page, page2, l, lru) { list_del(&page->lru); dec_zone_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); putback_lru_page(page); } } /* * Restore a potential migration pte to a working pte entry */ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma, unsigned long addr, void *old) { struct mm_struct *mm = vma->vm_mm; swp_entry_t entry; pgd_t *pgd; pud_t *pud; pmd_t *pmd; pte_t *ptep, pte; spinlock_t *ptl; if (unlikely(PageHuge(new))) { ptep = huge_pte_offset(mm, addr); if (!ptep) goto out; ptl = &mm->page_table_lock; } else { pgd = pgd_offset(mm, addr); if (!pgd_present(*pgd)) goto out; pud = pud_offset(pgd, addr); if (!pud_present(*pud)) goto out; pmd = pmd_offset(pud, addr); if (pmd_trans_huge(*pmd)) goto out; if (!pmd_present(*pmd)) goto out; ptep = pte_offset_map(pmd, addr); /* * Peek to check is_swap_pte() before taking ptlock? No, we * can race mremap's move_ptes(), which skips anon_vma lock. */ ptl = pte_lockptr(mm, pmd); } spin_lock(ptl); pte = *ptep; if (!is_swap_pte(pte)) goto unlock; entry = pte_to_swp_entry(pte); if (!is_migration_entry(entry) || migration_entry_to_page(entry) != old) goto unlock; get_page(new); pte = pte_mkold(mk_pte(new, vma->vm_page_prot)); if (is_write_migration_entry(entry)) pte = pte_mkwrite(pte); #ifdef CONFIG_HUGETLB_PAGE if (PageHuge(new)) pte = pte_mkhuge(pte); #endif flush_cache_page(vma, addr, pte_pfn(pte)); set_pte_at(mm, addr, ptep, pte); if (PageHuge(new)) { if (PageAnon(new)) hugepage_add_anon_rmap(new, vma, addr); else page_dup_rmap(new); } else if (PageAnon(new)) page_add_anon_rmap(new, vma, addr); else page_add_file_rmap(new); /* No need to invalidate - it was non-present before */ update_mmu_cache(vma, addr, ptep); unlock: pte_unmap_unlock(ptep, ptl); out: return SWAP_AGAIN; } /* * Get rid of all migration entries and replace them by * references to the indicated page. */ static void remove_migration_ptes(struct page *old, struct page *new) { rmap_walk(new, remove_migration_pte, old); } /* * Something used the pte of a page under migration. We need to * get to the page and wait until migration is finished. * When we return from this function the fault will be retried. */ void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address) { pte_t *ptep, pte; spinlock_t *ptl; swp_entry_t entry; struct page *page; ptep = pte_offset_map_lock(mm, pmd, address, &ptl); pte = *ptep; if (!is_swap_pte(pte)) goto out; entry = pte_to_swp_entry(pte); if (!is_migration_entry(entry)) goto out; page = migration_entry_to_page(entry); /* * Once radix-tree replacement of page migration started, page_count * *must* be zero. And, we don't want to call wait_on_page_locked() * against a page without get_page(). * So, we use get_page_unless_zero(), here. Even failed, page fault * will occur again. */ if (!get_page_unless_zero(page)) goto out; pte_unmap_unlock(ptep, ptl); wait_on_page_locked(page); put_page(page); return; out: pte_unmap_unlock(ptep, ptl); } #ifdef CONFIG_BLOCK /* Returns true if all buffers are successfully locked */ static bool buffer_migrate_lock_buffers(struct buffer_head *head, enum migrate_mode mode) { struct buffer_head *bh = head; /* Simple case, sync compaction */ if (mode != MIGRATE_ASYNC) { do { get_bh(bh); lock_buffer(bh); bh = bh->b_this_page; } while (bh != head); return true; } /* async case, we cannot block on lock_buffer so use trylock_buffer */ do { get_bh(bh); if (!trylock_buffer(bh)) { /* * We failed to lock the buffer and cannot stall in * async migration. Release the taken locks */ struct buffer_head *failed_bh = bh; put_bh(failed_bh); bh = head; while (bh != failed_bh) { unlock_buffer(bh); put_bh(bh); bh = bh->b_this_page; } return false; } bh = bh->b_this_page; } while (bh != head); return true; } #else static inline bool buffer_migrate_lock_buffers(struct buffer_head *head, enum migrate_mode mode) { return true; } #endif /* CONFIG_BLOCK */ /* * Replace the page in the mapping. * * The number of remaining references must be: * 1 for anonymous pages without a mapping * 2 for pages with a mapping * 3 for pages with a mapping and PagePrivate/PagePrivate2 set. */ static int migrate_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page, struct buffer_head *head, enum migrate_mode mode) { int expected_count; void **pslot; if (!mapping) { /* Anonymous page without mapping */ if (page_count(page) != 1) return -EAGAIN; return 0; } spin_lock_irq(&mapping->tree_lock); pslot = radix_tree_lookup_slot(&mapping->page_tree, page_index(page)); expected_count = 2 + page_has_private(page); if (page_count(page) != expected_count || radix_tree_deref_slot_protected(pslot, &mapping->tree_lock) != page) { spin_unlock_irq(&mapping->tree_lock); return -EAGAIN; } if (!page_freeze_refs(page, expected_count)) { spin_unlock_irq(&mapping->tree_lock); return -EAGAIN; } /* * In the async migration case of moving a page with buffers, lock the * buffers using trylock before the mapping is moved. If the mapping * was moved, we later failed to lock the buffers and could not move * the mapping back due to an elevated page count, we would have to * block waiting on other references to be dropped. */ if (mode == MIGRATE_ASYNC && head && !buffer_migrate_lock_buffers(head, mode)) { page_unfreeze_refs(page, expected_count); spin_unlock_irq(&mapping->tree_lock); return -EAGAIN; } /* * Now we know that no one else is looking at the page. */ get_page(newpage); /* add cache reference */ if (PageSwapCache(page)) { SetPageSwapCache(newpage); set_page_private(newpage, page_private(page)); } radix_tree_replace_slot(pslot, newpage); /* * Drop cache reference from old page by unfreezing * to one less reference. * We know this isn't the last reference. */ page_unfreeze_refs(page, expected_count - 1); /* * If moved to a different zone then also account * the page for that zone. Other VM counters will be * taken care of when we establish references to the * new page and drop references to the old page. * * Note that anonymous pages are accounted for * via NR_FILE_PAGES and NR_ANON_PAGES if they * are mapped to swap space. */ __dec_zone_page_state(page, NR_FILE_PAGES); __inc_zone_page_state(newpage, NR_FILE_PAGES); if (!PageSwapCache(page) && PageSwapBacked(page)) { __dec_zone_page_state(page, NR_SHMEM); __inc_zone_page_state(newpage, NR_SHMEM); } spin_unlock_irq(&mapping->tree_lock); return 0; } /* * The expected number of remaining references is the same as that * of migrate_page_move_mapping(). */ int migrate_huge_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page) { int expected_count; void **pslot; if (!mapping) { if (page_count(page) != 1) return -EAGAIN; return 0; } spin_lock_irq(&mapping->tree_lock); pslot = radix_tree_lookup_slot(&mapping->page_tree, page_index(page)); expected_count = 2 + page_has_private(page); if (page_count(page) != expected_count || radix_tree_deref_slot_protected(pslot, &mapping->tree_lock) != page) { spin_unlock_irq(&mapping->tree_lock); return -EAGAIN; } if (!page_freeze_refs(page, expected_count)) { spin_unlock_irq(&mapping->tree_lock); return -EAGAIN; } get_page(newpage); radix_tree_replace_slot(pslot, newpage); page_unfreeze_refs(page, expected_count - 1); spin_unlock_irq(&mapping->tree_lock); return 0; } /* * Copy the page to its new location */ void migrate_page_copy(struct page *newpage, struct page *page) { if (PageHuge(page)) copy_huge_page(newpage, page); else copy_highpage(newpage, page); if (PageError(page)) SetPageError(newpage); if (PageReferenced(page)) SetPageReferenced(newpage); if (PageUptodate(page)) SetPageUptodate(newpage); if (TestClearPageActive(page)) { VM_BUG_ON(PageUnevictable(page)); SetPageActive(newpage); } else if (TestClearPageUnevictable(page)) SetPageUnevictable(newpage); if (PageChecked(page)) SetPageChecked(newpage); if (PageMappedToDisk(page)) SetPageMappedToDisk(newpage); if (PageDirty(page)) { clear_page_dirty_for_io(page); /* * Want to mark the page and the radix tree as dirty, and * redo the accounting that clear_page_dirty_for_io undid, * but we can't use set_page_dirty because that function * is actually a signal that all of the page has become dirty. * Whereas only part of our page may be dirty. */ __set_page_dirty_nobuffers(newpage); } mlock_migrate_page(newpage, page); ksm_migrate_page(newpage, page); ClearPageSwapCache(page); ClearPagePrivate(page); set_page_private(page, 0); /* * If any waiters have accumulated on the new page then * wake them up. */ if (PageWriteback(newpage)) end_page_writeback(newpage); } /************************************************************ * Migration functions ***********************************************************/ /* Always fail migration. Used for mappings that are not movable */ int fail_migrate_page(struct address_space *mapping, struct page *newpage, struct page *page) { return -EIO; } EXPORT_SYMBOL(fail_migrate_page); /* * Common logic to directly migrate a single page suitable for * pages that do not use PagePrivate/PagePrivate2. * * Pages are locked upon entry and exit. */ int migrate_page(struct address_space *mapping, struct page *newpage, struct page *page, enum migrate_mode mode) { int rc; BUG_ON(PageWriteback(page)); /* Writeback must be complete */ rc = migrate_page_move_mapping(mapping, newpage, page, NULL, mode); if (rc) return rc; migrate_page_copy(newpage, page); return 0; } EXPORT_SYMBOL(migrate_page); #ifdef CONFIG_BLOCK /* * Migration function for pages with buffers. This function can only be used * if the underlying filesystem guarantees that no other references to "page" * exist. */ int buffer_migrate_page(struct address_space *mapping, struct page *newpage, struct page *page, enum migrate_mode mode) { struct buffer_head *bh, *head; int rc; if (!page_has_buffers(page)) return migrate_page(mapping, newpage, page, mode); head = page_buffers(page); rc = migrate_page_move_mapping(mapping, newpage, page, head, mode); if (rc) return rc; /* * In the async case, migrate_page_move_mapping locked the buffers * with an IRQ-safe spinlock held. In the sync case, the buffers * need to be locked now */ if (mode != MIGRATE_ASYNC) BUG_ON(!buffer_migrate_lock_buffers(head, mode)); ClearPagePrivate(page); set_page_private(newpage, page_private(page)); set_page_private(page, 0); put_page(page); get_page(newpage); bh = head; do { set_bh_page(bh, newpage, bh_offset(bh)); bh = bh->b_this_page; } while (bh != head); SetPagePrivate(newpage); migrate_page_copy(newpage, page); bh = head; do { unlock_buffer(bh); put_bh(bh); bh = bh->b_this_page; } while (bh != head); return 0; } EXPORT_SYMBOL(buffer_migrate_page); #endif /* * Writeback a page to clean the dirty state */ static int writeout(struct address_space *mapping, struct page *page) { struct writeback_control wbc = { .sync_mode = WB_SYNC_NONE, .nr_to_write = 1, .range_start = 0, .range_end = LLONG_MAX, .for_reclaim = 1 }; int rc; if (!mapping->a_ops->writepage) /* No write method for the address space */ return -EINVAL; if (!clear_page_dirty_for_io(page)) /* Someone else already triggered a write */ return -EAGAIN; /* * A dirty page may imply that the underlying filesystem has * the page on some queue. So the page must be clean for * migration. Writeout may mean we loose the lock and the * page state is no longer what we checked for earlier. * At this point we know that the migration attempt cannot * be successful. */ remove_migration_ptes(page, page); rc = mapping->a_ops->writepage(page, &wbc); if (rc != AOP_WRITEPAGE_ACTIVATE) /* unlocked. Relock */ lock_page(page); return (rc < 0) ? -EIO : -EAGAIN; } /* * Default handling if a filesystem does not provide a migration function. */ static int fallback_migrate_page(struct address_space *mapping, struct page *newpage, struct page *page, enum migrate_mode mode) { if (PageDirty(page)) { /* Only writeback pages in full synchronous migration */ if (mode != MIGRATE_SYNC) return -EBUSY; return writeout(mapping, page); } /* * Buffers may be managed in a filesystem specific way. * We must have no buffers or drop them. */ if (page_has_private(page) && !try_to_release_page(page, GFP_KERNEL)) return -EAGAIN; return migrate_page(mapping, newpage, page, mode); } /* * Move a page to a newly allocated page * The page is locked and all ptes have been successfully removed. * * The new page will have replaced the old page if this function * is successful. * * Return value: * < 0 - error code * == 0 - success */ static int move_to_new_page(struct page *newpage, struct page *page, int remap_swapcache, enum migrate_mode mode) { struct address_space *mapping; int rc; /* * Block others from accessing the page when we get around to * establishing additional references. We are the only one * holding a reference to the new page at this point. */ if (!trylock_page(newpage)) BUG(); /* Prepare mapping for the new page.*/ newpage->index = page->index; newpage->mapping = page->mapping; if (PageSwapBacked(page)) SetPageSwapBacked(newpage); mapping = page_mapping(page); if (!mapping) rc = migrate_page(mapping, newpage, page, mode); else if (mapping->a_ops->migratepage) /* * Most pages have a mapping and most filesystems provide a * migratepage callback. Anonymous pages are part of swap * space which also has its own migratepage callback. This * is the most common path for page migration. */ rc = mapping->a_ops->migratepage(mapping, newpage, page, mode); else rc = fallback_migrate_page(mapping, newpage, page, mode); if (rc) { newpage->mapping = NULL; } else { if (remap_swapcache) remove_migration_ptes(page, newpage); page->mapping = NULL; } unlock_page(newpage); #include <video/vga.h> /* Terminator for register set */ #define VGA_REGSET_END_VAL 0xFF #define VGA_REGSET_END {VGA_REGSET_END_VAL, 0, 0} struct vga_regset { u8 regnum; u8 lowbit; u8 highbit; }; /* ------------------------------------------------------------------------- */ #define SVGA_FORMAT_END_VAL 0xFFFF #define SVGA_FORMAT_END {SVGA_FORMAT_END_VAL, {0, 0, 0}, {0, 0, 0}, {0, 0, 0}, {0, 0, 0}, 0, 0, 0, 0, 0, 0} struct svga_fb_format { /* var part */ u32 bits_per_pixel; struct fb_bitfield red; struct fb_bitfield green; struct fb_bitfield blue; struct fb_bitfield transp; u32 nonstd; /* fix part */ u32 type; u32 type_aux; u32 visual; u32 xpanstep; u32 xresstep; }; struct svga_timing_regs { const struct vga_regset *h_total_regs; const struct vga_regset *h_display_regs; const struct vga_regset *h_blank_start_regs; const struct vga_regset *h_blank_end_regs; const struct vga_regset *h_sync_start_regs; const struct vga_regset *h_sync_end_regs; const struct vga_regset *v_total_regs; const struct vga_regset *v_display_regs; const struct vga_regset *v_blank_start_regs; const struct vga_regset *v_blank_end_regs; const struct vga_regset *v_sync_start_regs; const struct vga_regset *v_sync_end_regs; }; struct svga_pll { u16 m_min; u16 m_max; u16 n_min; u16 n_max; u16 r_min; u16 r_max; /* r_max < 32 */ u32 f_vco_min; u32 f_vco_max; u32 f_base; }; /* Write a value to the attribute register */ static inline void svga_wattr(u8 index, u8 data) { inb(0x3DA); outb(index, 0x3C0); outb(data, 0x3C0); } /* Write a value to a sequence register with a mask */ static inline void svga_wseq_mask(u8 index, u8 data, u8 mask) { vga_wseq(NULL, index, (data & mask) | (vga_rseq(NULL, index) & ~mask)); } /* Write a value to a CRT register with a mask */ static inline void svga_wcrt_mask(u8 index, u8 data, u8 mask) { vga_wcrt(NULL, index, (data & mask) | (vga_rcrt(NULL, index) & ~mask)); } static inline int svga_primary_device(struct pci_dev *dev) { u16 flags; pci_read_config_word(dev, PCI_COMMAND, &flags); return (flags & PCI_COMMAND_IO); } void svga_wcrt_multi(const struct vga_regset *regset, u32 value); void svga_wseq_multi(const struct vga_regset *regset, u32 value); void svga_set_default_gfx_regs(void); void svga_set_default_atc_regs(void); void svga_set_default_seq_regs(void); void svga_set_default_crt_regs(void); void svga_set_textmode_vga_regs(void); void svga_settile(struct fb_info *info, struct fb_tilemap *map); void svga_tilecopy(struct fb_info *info, struct fb_tilearea *area); void svga_tilefill(struct fb_info *info, struct fb_tilerect *rect); void svga_tileblit(struct fb_info *info, struct fb_tileblit *blit); void svga_tilecursor(struct fb_info *info, struct fb_tilecursor *cursor); int svga_get_tilemax(struct fb_info *info); void svga_get_caps(struct fb_info *info, struct fb_blit_caps *caps, struct fb_var_screeninfo *var); int svga_compute_pll(const struct svga_pll *pll, u32 f_wanted, u16 *m, u16 *n, u16 *r, int node); int svga_check_timings(const struct svga_timing_regs *tm, struct fb_var_screeninfo *var, int node); void svga_set_timings(const struct svga_timing_regs *tm, struct fb_var_screeninfo *var, u32 hmul, u32 hdiv, u32 vmul, u32 vdiv, u32 hborder, int node); int svga_match_format(const struct svga_fb_format *frm, struct fb_var_screeninfo *var, struct fb_fix_screeninfo *fix); #endif /* __KERNEL__ */ #endif /* _LINUX_SVGA_H */
generated by cgit v1.2.2 (git 2.25.0) at 2025-01-23 18:10:35 -0500
*/ for (j = 0; j < chunk_nr_pages; j++) { const void __user *p; int node; err = -EFAULT; if (get_user(p, pages + j + chunk_start)) goto out_pm; pm[j].addr = (unsigned long) p; if (get_user(node, nodes + j + chunk_start)) goto out_pm; err = -ENODEV; if (node < 0 || node >= MAX_NUMNODES) goto out_pm; if (!node_state(node, N_HIGH_MEMORY)) goto out_pm; err = -EACCES; if (!node_isset(node, task_nodes)) goto out_pm; pm[j].node = node; } /* End marker for this chunk */ pm[chunk_nr_pages].node = MAX_NUMNODES; /* Migrate this chunk */ err = do_move_page_to_node_array(mm, pm, flags & MPOL_MF_MOVE_ALL); if (err < 0) goto out_pm; /* Return status information */ for (j = 0; j < chunk_nr_pages; j++) if (put_user(pm[j].status, status + j + chunk_start)) { err = -EFAULT; goto out_pm; } } err = 0; out_pm: free_page((unsigned long)pm); out: return err; } /* * Determine the nodes of an array of pages and store it in an array of status. */ static void do_pages_stat_array(struct mm_struct *mm, unsigned long nr_pages, const void __user **pages, int *status) { unsigned long i; down_read(&mm->mmap_sem); for (i = 0; i < nr_pages; i++) { unsigned long addr = (unsigned long)(*pages); struct vm_area_struct *vma; struct page *page; int err = -EFAULT; vma = find_vma(mm, addr); if (!vma || addr < vma->vm_start) goto set_status; page = follow_page(vma, addr, 0); err = PTR_ERR(page); if (IS_ERR(page)) goto set_status; err = -ENOENT; /* Use PageReserved to check for zero page */ if (!page || PageReserved(page) || PageKsm(page)) goto set_status; err = page_to_nid(page); set_status: *status = err; pages++; status++; } up_read(&mm->mmap_sem); } /* * Determine the nodes of a user array of pages and store it in * a user array of status. */ static int do_pages_stat(struct mm_struct *mm, unsigned long nr_pages, const void __user * __user *pages, int __user *status) { #define DO_PAGES_STAT_CHUNK_NR 16 const void __user *chunk_pages[DO_PAGES_STAT_CHUNK_NR]; int chunk_status[DO_PAGES_STAT_CHUNK_NR]; while (nr_pages) { unsigned long chunk_nr; chunk_nr = nr_pages; if (chunk_nr > DO_PAGES_STAT_CHUNK_NR) chunk_nr = DO_PAGES_STAT_CHUNK_NR; if (copy_from_user(chunk_pages, pages, chunk_nr * sizeof(*chunk_pages))) break; do_pages_stat_array(mm, chunk_nr, chunk_pages, chunk_status); if (copy_to_user(status, chunk_status, chunk_nr * sizeof(*status))) break; pages += chunk_nr; status += chunk_nr; nr_pages -= chunk_nr; } return nr_pages ? -EFAULT : 0; } /* * Move a list of pages in the address space of the currently executing * process. */ SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages, const void __user * __user *, pages, const int __user *, nodes, int __user *, status, int, flags) { const struct cred *cred = current_cred(), *tcred; struct task_struct *task; struct mm_struct *mm; int err; nodemask_t task_nodes; /* Check flags */ if (flags & ~(MPOL_MF_MOVE|MPOL_MF_MOVE_ALL)) return -EINVAL; if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE)) return -EPERM; /* Find the mm_struct */ rcu_read_lock(); task = pid ? find_task_by_vpid(pid) : current; if (!task) { rcu_read_unlock(); return -ESRCH; } get_task_struct(task); /* * Check if this process has the right to modify the specified * process. The right exists if the process has administrative * capabilities, superuser privileges or the same * userid as the target process. */ tcred = __task_cred(task); if (!uid_eq(cred->euid, tcred->suid) && !uid_eq(cred->euid, tcred->uid) && !uid_eq(cred->uid, tcred->suid) && !uid_eq(cred->uid, tcred->uid) && !capable(CAP_SYS_NICE)) { rcu_read_unlock(); err = -EPERM; goto out; } rcu_read_unlock(); err = security_task_movememory(task); if (err) goto out; task_nodes = cpuset_mems_allowed(task); mm = get_task_mm(task); put_task_struct(task); if (!mm) return -EINVAL; if (nodes) err = do_pages_move(mm, task_nodes, nr_pages, pages, nodes, status, flags); else err = do_pages_stat(mm, nr_pages, pages, status); mmput(mm); return err; out: put_task_struct(task); return err; } /* * Call migration functions in the vma_ops that may prepare * memory in a vm for migration. migration functions may perform * the migration for vmas that do not have an underlying page struct. */ int migrate_vmas(struct mm_struct *mm, const nodemask_t *to, const nodemask_t *from, unsigned long flags) { struct vm_area_struct *vma; int err = 0; for (vma = mm->mmap; vma && !err; vma = vma->vm_next) { if (vma->vm_ops && vma->vm_ops->migrate) { err = vma->vm_ops->migrate(vma, to, from, flags); if (err) break; } } return err; } #endif