Revision 048f49809c526348775425420fb5b8e84fd9a133 authored by Sean Christopherson on 25 March 2021, 20:01:18 UTC, committed by Paolo Bonzini on 30 March 2021, 17:19:55 UTC
Honor the "flush needed" return from kvm_tdp_mmu_zap_gfn_range(), which
does the flush itself if and only if it yields (which it will never do in
this particular scenario), and otherwise expects the caller to do the
flush.  If pages are zapped from the TDP MMU but not the legacy MMU, then
no flush will occur.

Fixes: 29cf0f5007a2 ("kvm: x86/mmu: NX largepage recovery for TDP MMU")
Cc: stable@vger.kernel.org
Cc: Ben Gardon <bgardon@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210325200119.1359384-3-seanjc@google.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
1 parent a835429
Raw File
ioremap.c
// SPDX-License-Identifier: GPL-2.0
/*
 * Re-map IO memory to kernel address space so that we can access it.
 * This is needed for high PCI addresses that aren't mapped in the
 * 640k-1MB IO memory area on PC's
 *
 * (C) Copyright 1995 1996 Linus Torvalds
 */
#include <linux/vmalloc.h>
#include <linux/mm.h>
#include <linux/sched.h>
#include <linux/io.h>
#include <linux/export.h>
#include <asm/cacheflush.h>

#include "pgalloc-track.h"

#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
static int __read_mostly ioremap_p4d_capable;
static int __read_mostly ioremap_pud_capable;
static int __read_mostly ioremap_pmd_capable;
static int __read_mostly ioremap_huge_disabled;

static int __init set_nohugeiomap(char *str)
{
	ioremap_huge_disabled = 1;
	return 0;
}
early_param("nohugeiomap", set_nohugeiomap);

void __init ioremap_huge_init(void)
{
	if (!ioremap_huge_disabled) {
		if (arch_ioremap_p4d_supported())
			ioremap_p4d_capable = 1;
		if (arch_ioremap_pud_supported())
			ioremap_pud_capable = 1;
		if (arch_ioremap_pmd_supported())
			ioremap_pmd_capable = 1;
	}
}

static inline int ioremap_p4d_enabled(void)
{
	return ioremap_p4d_capable;
}

static inline int ioremap_pud_enabled(void)
{
	return ioremap_pud_capable;
}

static inline int ioremap_pmd_enabled(void)
{
	return ioremap_pmd_capable;
}

#else	/* !CONFIG_HAVE_ARCH_HUGE_VMAP */
static inline int ioremap_p4d_enabled(void) { return 0; }
static inline int ioremap_pud_enabled(void) { return 0; }
static inline int ioremap_pmd_enabled(void) { return 0; }
#endif	/* CONFIG_HAVE_ARCH_HUGE_VMAP */

static int ioremap_pte_range(pmd_t *pmd, unsigned long addr,
		unsigned long end, phys_addr_t phys_addr, pgprot_t prot,
		pgtbl_mod_mask *mask)
{
	pte_t *pte;
	u64 pfn;

	pfn = phys_addr >> PAGE_SHIFT;
	pte = pte_alloc_kernel_track(pmd, addr, mask);
	if (!pte)
		return -ENOMEM;
	do {
		BUG_ON(!pte_none(*pte));
		set_pte_at(&init_mm, addr, pte, pfn_pte(pfn, prot));
		pfn++;
	} while (pte++, addr += PAGE_SIZE, addr != end);
	*mask |= PGTBL_PTE_MODIFIED;
	return 0;
}

static int ioremap_try_huge_pmd(pmd_t *pmd, unsigned long addr,
				unsigned long end, phys_addr_t phys_addr,
				pgprot_t prot)
{
	if (!ioremap_pmd_enabled())
		return 0;

	if ((end - addr) != PMD_SIZE)
		return 0;

	if (!IS_ALIGNED(addr, PMD_SIZE))
		return 0;

	if (!IS_ALIGNED(phys_addr, PMD_SIZE))
		return 0;

	if (pmd_present(*pmd) && !pmd_free_pte_page(pmd, addr))
		return 0;

	return pmd_set_huge(pmd, phys_addr, prot);
}

static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr,
		unsigned long end, phys_addr_t phys_addr, pgprot_t prot,
		pgtbl_mod_mask *mask)
{
	pmd_t *pmd;
	unsigned long next;

	pmd = pmd_alloc_track(&init_mm, pud, addr, mask);
	if (!pmd)
		return -ENOMEM;
	do {
		next = pmd_addr_end(addr, end);

		if (ioremap_try_huge_pmd(pmd, addr, next, phys_addr, prot)) {
			*mask |= PGTBL_PMD_MODIFIED;
			continue;
		}

		if (ioremap_pte_range(pmd, addr, next, phys_addr, prot, mask))
			return -ENOMEM;
	} while (pmd++, phys_addr += (next - addr), addr = next, addr != end);
	return 0;
}

static int ioremap_try_huge_pud(pud_t *pud, unsigned long addr,
				unsigned long end, phys_addr_t phys_addr,
				pgprot_t prot)
{
	if (!ioremap_pud_enabled())
		return 0;

	if ((end - addr) != PUD_SIZE)
		return 0;

	if (!IS_ALIGNED(addr, PUD_SIZE))
		return 0;

	if (!IS_ALIGNED(phys_addr, PUD_SIZE))
		return 0;

	if (pud_present(*pud) && !pud_free_pmd_page(pud, addr))
		return 0;

	return pud_set_huge(pud, phys_addr, prot);
}

static inline int ioremap_pud_range(p4d_t *p4d, unsigned long addr,
		unsigned long end, phys_addr_t phys_addr, pgprot_t prot,
		pgtbl_mod_mask *mask)
{
	pud_t *pud;
	unsigned long next;

	pud = pud_alloc_track(&init_mm, p4d, addr, mask);
	if (!pud)
		return -ENOMEM;
	do {
		next = pud_addr_end(addr, end);

		if (ioremap_try_huge_pud(pud, addr, next, phys_addr, prot)) {
			*mask |= PGTBL_PUD_MODIFIED;
			continue;
		}

		if (ioremap_pmd_range(pud, addr, next, phys_addr, prot, mask))
			return -ENOMEM;
	} while (pud++, phys_addr += (next - addr), addr = next, addr != end);
	return 0;
}

static int ioremap_try_huge_p4d(p4d_t *p4d, unsigned long addr,
				unsigned long end, phys_addr_t phys_addr,
				pgprot_t prot)
{
	if (!ioremap_p4d_enabled())
		return 0;

	if ((end - addr) != P4D_SIZE)
		return 0;

	if (!IS_ALIGNED(addr, P4D_SIZE))
		return 0;

	if (!IS_ALIGNED(phys_addr, P4D_SIZE))
		return 0;

	if (p4d_present(*p4d) && !p4d_free_pud_page(p4d, addr))
		return 0;

	return p4d_set_huge(p4d, phys_addr, prot);
}

static inline int ioremap_p4d_range(pgd_t *pgd, unsigned long addr,
		unsigned long end, phys_addr_t phys_addr, pgprot_t prot,
		pgtbl_mod_mask *mask)
{
	p4d_t *p4d;
	unsigned long next;

	p4d = p4d_alloc_track(&init_mm, pgd, addr, mask);
	if (!p4d)
		return -ENOMEM;
	do {
		next = p4d_addr_end(addr, end);

		if (ioremap_try_huge_p4d(p4d, addr, next, phys_addr, prot)) {
			*mask |= PGTBL_P4D_MODIFIED;
			continue;
		}

		if (ioremap_pud_range(p4d, addr, next, phys_addr, prot, mask))
			return -ENOMEM;
	} while (p4d++, phys_addr += (next - addr), addr = next, addr != end);
	return 0;
}

int ioremap_page_range(unsigned long addr,
		       unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
{
	pgd_t *pgd;
	unsigned long start;
	unsigned long next;
	int err;
	pgtbl_mod_mask mask = 0;

	might_sleep();
	BUG_ON(addr >= end);

	start = addr;
	pgd = pgd_offset_k(addr);
	do {
		next = pgd_addr_end(addr, end);
		err = ioremap_p4d_range(pgd, addr, next, phys_addr, prot,
					&mask);
		if (err)
			break;
	} while (pgd++, phys_addr += (next - addr), addr = next, addr != end);

	flush_cache_vmap(start, end);

	if (mask & ARCH_PAGE_TABLE_SYNC_MASK)
		arch_sync_kernel_mappings(start, end);

	return err;
}

#ifdef CONFIG_GENERIC_IOREMAP
void __iomem *ioremap_prot(phys_addr_t addr, size_t size, unsigned long prot)
{
	unsigned long offset, vaddr;
	phys_addr_t last_addr;
	struct vm_struct *area;

	/* Disallow wrap-around or zero size */
	last_addr = addr + size - 1;
	if (!size || last_addr < addr)
		return NULL;

	/* Page-align mappings */
	offset = addr & (~PAGE_MASK);
	addr -= offset;
	size = PAGE_ALIGN(size + offset);

	area = get_vm_area_caller(size, VM_IOREMAP,
			__builtin_return_address(0));
	if (!area)
		return NULL;
	vaddr = (unsigned long)area->addr;

	if (ioremap_page_range(vaddr, vaddr + size, addr, __pgprot(prot))) {
		free_vm_area(area);
		return NULL;
	}

	return (void __iomem *)(vaddr + offset);
}
EXPORT_SYMBOL(ioremap_prot);

void iounmap(volatile void __iomem *addr)
{
	vunmap((void *)((unsigned long)addr & PAGE_MASK));
}
EXPORT_SYMBOL(iounmap);
#endif /* CONFIG_GENERIC_IOREMAP */
back to top