826 lines · 20.4 KB · C
RawDownload
// SPDX-License-Identifier: GPL-2.0/* * High memory handling common code and variables. * * (C) 1999 Andrea Arcangeli, SuSE GmbH, andrea@suse.de *          Gerhard Wichert, Siemens AG, Gerhard.Wichert@pdb.siemens.de * * * Redesigned the x86 32-bit VM architecture to deal with * 64-bit physical space. With current x86 CPUs this * means up to 64 Gigabytes physical RAM. * * Rewrote high memory support to move the page cache into * high memory. Implemented permanent (schedulable) kmaps * based on Linus' idea. * * Copyright (C) 1999 Ingo Molnar <mingo@redhat.com> */ #include <linux/mm.h>#include <linux/export.h>#include <linux/swap.h>#include <linux/bio.h>#include <linux/pagemap.h>#include <linux/mempool.h>#include <linux/init.h>#include <linux/hash.h>#include <linux/highmem.h>#include <linux/kgdb.h>#include <asm/tlbflush.h>#include <linux/vmalloc.h> #ifdef CONFIG_KMAP_LOCALstatic inline int kmap_local_calc_idx(int idx){	return idx + KM_MAX_IDX * smp_processor_id();} #ifndef arch_kmap_local_map_idx#define arch_kmap_local_map_idx(idx, pfn)	kmap_local_calc_idx(idx)#endif#endif /* CONFIG_KMAP_LOCAL */ /* * Virtual_count is not a pure "count". *  0 means that it is not mapped, and has not been mapped *    since a TLB flush - it is usable. *  1 means that there are no users, but it has been mapped *    since the last TLB flush - so we can't use it. *  n means that there are (n-1) current users of it. */#ifdef CONFIG_HIGHMEM /* * Architecture with aliasing data cache may define the following family of * helper functions in its asm/highmem.h to control cache color of virtual * addresses where physical memory pages are mapped by kmap. */#ifndef get_pkmap_color /* * Determine color of virtual address where the page should be mapped. */static inline unsigned int get_pkmap_color(const struct page *page){	return 0;}#define get_pkmap_color get_pkmap_color /* * Get next index for mapping inside PKMAP region for page with given color. */static inline unsigned int get_next_pkmap_nr(unsigned int color){	static unsigned int last_pkmap_nr; 	last_pkmap_nr = (last_pkmap_nr + 1) & LAST_PKMAP_MASK;	return last_pkmap_nr;} /* * Determine if page index inside PKMAP region (pkmap_nr) of given color * has wrapped around PKMAP region end. When this happens an attempt to * flush all unused PKMAP slots is made. */static inline int no_more_pkmaps(unsigned int pkmap_nr, unsigned int color){	return pkmap_nr == 0;} /* * Get the number of PKMAP entries of the given color. If no free slot is * found after checking that many entries, kmap will sleep waiting for * someone to call kunmap and free PKMAP slot. */static inline int get_pkmap_entries_count(unsigned int color){	return LAST_PKMAP;} /* * Get head of a wait queue for PKMAP entries of the given color. * Wait queues for different mapping colors should be independent to avoid * unnecessary wakeups caused by freeing of slots of other colors. */static inline wait_queue_head_t *get_pkmap_wait_queue_head(unsigned int color){	static DECLARE_WAIT_QUEUE_HEAD(pkmap_map_wait); 	return &pkmap_map_wait;}#endif unsigned long __nr_free_highpages(void){	unsigned long pages = 0;	struct zone *zone; 	for_each_populated_zone(zone) {		if (is_highmem(zone))			pages += zone_page_state(zone, NR_FREE_PAGES);	} 	return pages;} unsigned long __totalhigh_pages(void){	unsigned long pages = 0;	struct zone *zone; 	for_each_populated_zone(zone) {		if (is_highmem(zone))			pages += zone_managed_pages(zone);	} 	return pages;}EXPORT_SYMBOL(__totalhigh_pages); static int pkmap_count[LAST_PKMAP];static  __cacheline_aligned_in_smp DEFINE_SPINLOCK(kmap_lock); pte_t *pkmap_page_table; /* * Most architectures have no use for kmap_high_get(), so let's abstract * the disabling of IRQ out of the locking in that case to save on a * potential useless overhead. */#ifdef ARCH_NEEDS_KMAP_HIGH_GET#define lock_kmap()             spin_lock_irq(&kmap_lock)#define unlock_kmap()           spin_unlock_irq(&kmap_lock)#define lock_kmap_any(flags)    spin_lock_irqsave(&kmap_lock, flags)#define unlock_kmap_any(flags)  spin_unlock_irqrestore(&kmap_lock, flags)#else#define lock_kmap()             spin_lock(&kmap_lock)#define unlock_kmap()           spin_unlock(&kmap_lock)#define lock_kmap_any(flags)    \		do { spin_lock(&kmap_lock); (void)(flags); } while (0)#define unlock_kmap_any(flags)  \		do { spin_unlock(&kmap_lock); (void)(flags); } while (0)#endif struct page *__kmap_to_page(void *vaddr){	unsigned long base = (unsigned long) vaddr & PAGE_MASK;	struct kmap_ctrl *kctrl = &current->kmap_ctrl;	unsigned long addr = (unsigned long)vaddr;	int i; 	/* kmap() mappings */	if (WARN_ON_ONCE(addr >= PKMAP_ADDR(0) &&			 addr < PKMAP_ADDR(LAST_PKMAP)))		return pte_page(ptep_get(&pkmap_page_table[PKMAP_NR(addr)])); 	/* kmap_local_page() mappings */	if (WARN_ON_ONCE(base >= __fix_to_virt(FIX_KMAP_END) &&			 base < __fix_to_virt(FIX_KMAP_BEGIN))) {		for (i = 0; i < kctrl->idx; i++) {			unsigned long base_addr;			int idx;			pte_t pteval = kctrl->pteval[i]; 			idx = arch_kmap_local_map_idx(i, pte_pfn(pteval));			base_addr = __fix_to_virt(FIX_KMAP_BEGIN + idx); 			if (base_addr == base)				return pte_page(pteval);		}	} 	return virt_to_page(vaddr);}EXPORT_SYMBOL(__kmap_to_page); static void flush_all_zero_pkmaps(void){	int i;	int need_flush = 0; 	flush_cache_kmaps(); 	for (i = 0; i < LAST_PKMAP; i++) {		struct page *page;		pte_t ptent; 		/*		 * zero means we don't have anything to do,		 * >1 means that it is still in use. Only		 * a count of 1 means that it is free but		 * needs to be unmapped		 */		if (pkmap_count[i] != 1)			continue;		pkmap_count[i] = 0; 		/* sanity check */		ptent = ptep_get(&pkmap_page_table[i]);		BUG_ON(pte_none(ptent)); 		/*		 * Don't need an atomic fetch-and-clear op here;		 * no-one has the page mapped, and cannot get at		 * its virtual address (and hence PTE) without first		 * getting the kmap_lock (which is held here).		 * So no dangers, even with speculative execution.		 */		page = pte_page(ptent);		pte_clear(&init_mm, PKMAP_ADDR(i), &pkmap_page_table[i]); 		set_page_address(page, NULL);		need_flush = 1;	}	if (need_flush)		flush_tlb_kernel_range(PKMAP_ADDR(0), PKMAP_ADDR(LAST_PKMAP));} void __kmap_flush_unused(void){	lock_kmap();	flush_all_zero_pkmaps();	unlock_kmap();} static inline unsigned long map_new_virtual(struct page *page){	unsigned long vaddr;	int count;	unsigned int last_pkmap_nr;	unsigned int color = get_pkmap_color(page); start:	count = get_pkmap_entries_count(color);	/* Find an empty entry */	for (;;) {		last_pkmap_nr = get_next_pkmap_nr(color);		if (no_more_pkmaps(last_pkmap_nr, color)) {			flush_all_zero_pkmaps();			count = get_pkmap_entries_count(color);		}		if (!pkmap_count[last_pkmap_nr])			break;	/* Found a usable entry */		if (--count)			continue; 		/*		 * Sleep for somebody else to unmap their entries		 */		{			DECLARE_WAITQUEUE(wait, current);			wait_queue_head_t *pkmap_map_wait =				get_pkmap_wait_queue_head(color); 			__set_current_state(TASK_UNINTERRUPTIBLE);			add_wait_queue(pkmap_map_wait, &wait);			unlock_kmap();			schedule();			remove_wait_queue(pkmap_map_wait, &wait);			lock_kmap(); 			/* Somebody else might have mapped it while we slept */			if (page_address(page))				return (unsigned long)page_address(page); 			/* Re-start */			goto start;		}	}	vaddr = PKMAP_ADDR(last_pkmap_nr);	set_pte_at(&init_mm, vaddr,		   &(pkmap_page_table[last_pkmap_nr]), mk_pte(page, kmap_prot)); 	pkmap_count[last_pkmap_nr] = 1;	set_page_address(page, (void *)vaddr); 	return vaddr;} /** * kmap_high - map a highmem page into memory * @page: &struct page to map * * Returns the page's virtual memory address. * * We cannot call this from interrupts, as it may block. */void *kmap_high(struct page *page){	unsigned long vaddr; 	/*	 * For highmem pages, we can't trust "virtual" until	 * after we have the lock.	 */	lock_kmap();	vaddr = (unsigned long)page_address(page);	if (!vaddr)		vaddr = map_new_virtual(page);	pkmap_count[PKMAP_NR(vaddr)]++;	BUG_ON(pkmap_count[PKMAP_NR(vaddr)] < 2);	unlock_kmap();	return (void *) vaddr;}EXPORT_SYMBOL(kmap_high); #ifdef ARCH_NEEDS_KMAP_HIGH_GET/** * kmap_high_get - pin a highmem page into memory * @page: &struct page to pin * * Returns the page's current virtual memory address, or NULL if no mapping * exists.  If and only if a non null address is returned then a * matching call to kunmap_high() is necessary. * * This can be called from any context. */void *kmap_high_get(const struct page *page){	unsigned long vaddr, flags; 	lock_kmap_any(flags);	vaddr = (unsigned long)page_address(page);	if (vaddr) {		BUG_ON(pkmap_count[PKMAP_NR(vaddr)] < 1);		pkmap_count[PKMAP_NR(vaddr)]++;	}	unlock_kmap_any(flags);	return (void *) vaddr;}#endif /** * kunmap_high - unmap a highmem page into memory * @page: &struct page to unmap * * If ARCH_NEEDS_KMAP_HIGH_GET is not defined then this may be called * only from user context. */void kunmap_high(const struct page *page){	unsigned long vaddr;	unsigned long nr;	unsigned long flags;	int need_wakeup;	unsigned int color = get_pkmap_color(page);	wait_queue_head_t *pkmap_map_wait; 	lock_kmap_any(flags);	vaddr = (unsigned long)page_address(page);	BUG_ON(!vaddr);	nr = PKMAP_NR(vaddr); 	/*	 * A count must never go down to zero	 * without a TLB flush!	 */	need_wakeup = 0;	switch (--pkmap_count[nr]) {	case 0:		BUG();	case 1:		/*		 * Avoid an unnecessary wake_up() function call.		 * The common case is pkmap_count[] == 1, but		 * no waiters.		 * The tasks queued in the wait-queue are guarded		 * by both the lock in the wait-queue-head and by		 * the kmap_lock.  As the kmap_lock is held here,		 * no need for the wait-queue-head's lock.  Simply		 * test if the queue is empty.		 */		pkmap_map_wait = get_pkmap_wait_queue_head(color);		need_wakeup = waitqueue_active(pkmap_map_wait);	}	unlock_kmap_any(flags); 	/* do wake-up, if needed, race-free outside of the spin lock */	if (need_wakeup)		wake_up(pkmap_map_wait);}EXPORT_SYMBOL(kunmap_high); void zero_user_segments(struct page *page, unsigned start1, unsigned end1,		unsigned start2, unsigned end2){	unsigned int i; 	BUG_ON(end1 > page_size(page) || end2 > page_size(page)); 	if (start1 >= end1)		start1 = end1 = 0;	if (start2 >= end2)		start2 = end2 = 0; 	for (i = 0; i < compound_nr(page); i++) {		void *kaddr = NULL; 		if (start1 >= PAGE_SIZE) {			start1 -= PAGE_SIZE;			end1 -= PAGE_SIZE;		} else {			unsigned this_end = min_t(unsigned, end1, PAGE_SIZE); 			if (end1 > start1) {				kaddr = kmap_local_page(page + i);				memset(kaddr + start1, 0, this_end - start1);			}			end1 -= this_end;			start1 = 0;		} 		if (start2 >= PAGE_SIZE) {			start2 -= PAGE_SIZE;			end2 -= PAGE_SIZE;		} else {			unsigned this_end = min_t(unsigned, end2, PAGE_SIZE); 			if (end2 > start2) {				if (!kaddr)					kaddr = kmap_local_page(page + i);				memset(kaddr + start2, 0, this_end - start2);			}			end2 -= this_end;			start2 = 0;		} 		if (kaddr) {			kunmap_local(kaddr);			flush_dcache_page(page + i);		} 		if (!end1 && !end2)			break;	} 	BUG_ON((start1 | start2 | end1 | end2) != 0);}EXPORT_SYMBOL(zero_user_segments);#endif /* CONFIG_HIGHMEM */ #ifdef CONFIG_KMAP_LOCAL #include <asm/kmap_size.h> /* * With DEBUG_KMAP_LOCAL the stack depth is doubled and every second * slot is unused which acts as a guard page */#ifdef CONFIG_DEBUG_KMAP_LOCAL# define KM_INCR	2#else# define KM_INCR	1#endif static inline int kmap_local_idx_push(void){	WARN_ON_ONCE(in_hardirq() && !irqs_disabled());	current->kmap_ctrl.idx += KM_INCR;	BUG_ON(current->kmap_ctrl.idx >= KM_MAX_IDX);	return current->kmap_ctrl.idx - 1;} static inline int kmap_local_idx(void){	return current->kmap_ctrl.idx - 1;} static inline void kmap_local_idx_pop(void){	current->kmap_ctrl.idx -= KM_INCR;	BUG_ON(current->kmap_ctrl.idx < 0);} #ifndef arch_kmap_local_post_map# define arch_kmap_local_post_map(vaddr, pteval)	do { } while (0)#endif #ifndef arch_kmap_local_pre_unmap# define arch_kmap_local_pre_unmap(vaddr)		do { } while (0)

Lines 1–500 of 826.