// 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>
*/
/* * 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.
*/ staticinlineunsignedint get_pkmap_color(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.
*/ staticinlineunsignedint get_next_pkmap_nr(unsignedint color)
{ staticunsignedint 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.
*/ staticinlineint no_more_pkmaps(unsignedint pkmap_nr, unsignedint 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.
*/ staticinlineint get_pkmap_entries_count(unsignedint 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.
*/ staticinline wait_queue_head_t *get_pkmap_wait_queue_head(unsignedint color)
{ static DECLARE_WAIT_QUEUE_HEAD(pkmap_map_wait);
return &pkmap_map_wait;
} #endif
unsignedlong __nr_free_highpages(void)
{ unsignedlong pages = 0; struct zone *zone;
for_each_populated_zone(zone) { if (is_highmem(zone))
pages += zone_page_state(zone, NR_FREE_PAGES);
}
return pages;
}
unsignedlong __totalhigh_pages(void)
{ unsignedlong pages = 0; struct zone *zone;
for_each_populated_zone(zone) { if (is_highmem(zone))
pages += zone_managed_pages(zone);
}
/* * 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
/* 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++) { unsignedlong base_addr; int idx;
staticvoid 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;
/* * 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]);
/** * 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)
{ unsignedlong vaddr;
/* * For highmem pages, we can't trust "virtual" until * after we have the lock.
*/
lock_kmap();
vaddr = (unsignedlong)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(struct page *page)
{ unsignedlong vaddr, flags;
/** * 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(struct page *page)
{ unsignedlong vaddr; unsignedlong nr; unsignedlong flags; int need_wakeup; unsignedint color = get_pkmap_color(page);
wait_queue_head_t *pkmap_map_wait;
lock_kmap_any(flags);
vaddr = (unsignedlong)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);
/* * 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
/* Unmap a local mapping which was obtained by kmap_high_get() */ staticinlinebool kmap_high_unmap_local(unsignedlong vaddr)
{ #ifdef ARCH_NEEDS_KMAP_HIGH_GET if (vaddr >= PKMAP_ADDR(0) && vaddr < PKMAP_ADDR(LAST_PKMAP)) {
kunmap_high(pte_page(ptep_get(&pkmap_page_table[PKMAP_NR(vaddr)]))); returntrue;
} #endif returnfalse;
}
static pte_t *__kmap_pte;
static pte_t *kmap_get_pte(unsignedlong vaddr, int idx)
{ if (IS_ENABLED(CONFIG_KMAP_LOCAL_NON_LINEAR_PTE_ARRAY)) /* * Set by the arch if __kmap_pte[-idx] does not produce * the correct entry.
*/ return virt_to_kpte(vaddr); if (!__kmap_pte)
__kmap_pte = virt_to_kpte(__fix_to_virt(FIX_KMAP_BEGIN)); return &__kmap_pte[-idx];
}
/* * To broaden the usage of the actual kmap_local() machinery always map * pages when debugging is enabled and the architecture has no problems * with alias mappings.
*/ if (!IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP) && !PageHighMem(page)) return page_address(page);
/* Try kmap_high_get() if architecture has it enabled */
kmap = arch_kmap_local_high_get(page); if (kmap) return kmap;
if (addr < __fix_to_virt(FIX_KMAP_END) ||
addr > __fix_to_virt(FIX_KMAP_BEGIN)) { if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP)) { /* This _should_ never happen! See above. */
WARN_ON_ONCE(1); return;
} /* * Handle mappings which were obtained by kmap_high_get() * first as the virtual address of such mappings is below * PAGE_OFFSET. Warn for all other addresses which are in * the user space part of the virtual address space.
*/ if (!kmap_high_unmap_local(addr))
WARN_ON_ONCE(addr < PAGE_OFFSET); return;
}
/* * Invoked before switch_to(). This is safe even when during or after * clearing the maps an interrupt which needs a kmap_local happens because * the task::kmap_ctrl.idx is not modified by the unmapping code so a * nested kmap_local will use the next unused index and restore the index * on unmap. The already cleared kmaps of the outgoing task are irrelevant * because the interrupt context does not know about them. The same applies * when scheduling back in for an interrupt which happens before the * restore is complete.
*/ void __kmap_local_sched_out(void)
{ struct task_struct *tsk = current;
pte_t *kmap_pte; int i;
/* Clear kmaps */ for (i = 0; i < tsk->kmap_ctrl.idx; i++) {
pte_t pteval = tsk->kmap_ctrl.pteval[i]; unsignedlong addr; int idx;
/* With debug all even slots are unmapped and act as guard */ if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL) && !(i & 0x01)) {
WARN_ON_ONCE(pte_val(pteval) != 0); continue;
} if (WARN_ON_ONCE(pte_none(pteval))) continue;
/* * This is a horrible hack for XTENSA to calculate the * coloured PTE index. Uses the PFN encoded into the pteval * and the map index calculation because the actual mapped * virtual address is not stored in task::kmap_ctrl. * For any sane architecture this is optimized out.
*/
idx = arch_kmap_local_map_idx(i, pte_pfn(pteval));
/* Restore kmaps */ for (i = 0; i < tsk->kmap_ctrl.idx; i++) {
pte_t pteval = tsk->kmap_ctrl.pteval[i]; unsignedlong addr; int idx;
/* With debug all even slots are unmapped and act as guard */ if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL) && !(i & 0x01)) {
WARN_ON_ONCE(pte_val(pteval) != 0); continue;
} if (WARN_ON_ONCE(pte_none(pteval))) continue;
/** * page_address - get the mapped virtual address of a page * @page: &struct page to get the virtual address of * * Returns the page's virtual address.
*/ void *page_address(conststruct page *page)
{ unsignedlong flags; void *ret; struct page_address_slot *pas;
if (!PageHighMem(page)) return lowmem_page_address(page);
pas = page_slot(page);
ret = NULL;
spin_lock_irqsave(&pas->lock, flags); if (!list_empty(&pas->lh)) { struct page_address_map *pam;
list_for_each_entry(pam, &pas->lh, list) { if (pam->page == page) {
ret = pam->virtual; break;
}
}
}
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.