/*
* Unmapping vs dcache management:
*
* If a guest maps certain memory pages as uncached, all writes will
* bypass the data cache and go directly to RAM. However, the CPUs
* can still speculate reads (not writes) and fill cache lines with
* data.
*
* Those cache lines will be *clean* cache lines though, so a
* clean+invalidate operation is equivalent to an invalidate
* operation, because no cache lines are marked dirty.
*
* Those clean cache lines could be filled prior to an uncached write
* by the guest, and the cache coherent IO subsystem would therefore
* end up writing old data to disk.
*
* This is why right after unmapping a page/section and invalidating
* the corresponding TLBs, we call kvm_flush_dcache_p*() to make sure
* the IO subsystem will never hit in the cache.
*/
static void unmap_ptes(struct kvm *kvm, pmd_t *pmd,
phys_addr_t addr, phys_addr_t end)
{
phys_addr_t start_addr = addr;
pte_t *pte, *start_pte;
start_pte = pte = pte_offset_kernel(pmd, addr);
do {
if (!pte_none(*pte)) {
pte_t old_pte = *pte;
kvm_set_pte(pte, __pte(0));
kvm_tlb_flush_vmid_ipa(kvm, addr);
/* No need to invalidate the cache for device mappings */
if ((pte_val(old_pte) & PAGE_S2_DEVICE) != PAGE_S2_DEVICE)
kvm_flush_dcache_pte(old_pte);
put_page(virt_to_page(pte));
}
} while (pte++, addr += PAGE_SIZE, addr != end);
if (kvm_pte_table_empty(kvm, start_pte))
clear_pmd_entry(kvm, pmd, start_addr);
}
static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
unsigned long long start, u64 size)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
unsigned long long addr = start, end = start + size;
u64 next;
while (addr < end) {
pgd = pgdp + pgd_index(addr);
pud = pud_offset(pgd, addr);
if (pud_none(*pud)) {
addr = kvm_pud_addr_end(addr, end);
continue;
}
if (pud_huge(*pud)) {
/*
* If we are dealing with a huge pud, just clear it and
* move on.
*/
clear_pud_entry(kvm, pud, addr);
addr = kvm_pud_addr_end(addr, end);
continue;
}
pmd = pmd_offset(pud, addr);
if (pmd_none(*pmd)) {
addr = kvm_pmd_addr_end(addr, end);
continue;
}
if (!kvm_pmd_huge(*pmd)) {
pte = pte_offset_kernel(pmd, addr);
clear_pte_entry(kvm, pte, addr);
next = addr + PAGE_SIZE;
}
/*
* If the pmd entry is to be cleared, walk back up the ladder
*/
if (kvm_pmd_huge(*pmd) || page_empty(pte)) {
clear_pmd_entry(kvm, pmd, addr);
next = kvm_pmd_addr_end(addr, end);
if (page_empty(pmd) && !page_empty(pud)) {
clear_pud_entry(kvm, pud, addr);
next = kvm_pud_addr_end(addr, end);
}
}
addr = next;
}
}
static void unmap_ptes(struct kvm *kvm, pmd_t *pmd,
phys_addr_t addr, phys_addr_t end)
{
phys_addr_t start_addr = addr;
pte_t *pte, *start_pte;
start_pte = pte = pte_offset_kernel(pmd, addr);
do {
if (!pte_none(*pte)) {
kvm_set_pte(pte, __pte(0));
put_page(virt_to_page(pte));
kvm_tlb_flush_vmid_ipa(kvm, addr);
}
} while (pte++, addr += PAGE_SIZE, addr != end);
if (kvm_pte_table_empty(kvm, start_pte))
clear_pmd_entry(kvm, pmd, start_addr);
}
static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
unsigned long long start, u64 size)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
unsigned long long addr = start, end = start + size;
u64 next;
while (addr < end) {
pgd = pgdp + pgd_index(addr);
pud = pud_offset(pgd, addr);
if (pud_none(*pud)) {
addr = pud_addr_end(addr, end);
continue;
}
pmd = pmd_offset(pud, addr);
if (pmd_none(*pmd)) {
addr = pmd_addr_end(addr, end);
continue;
}
pte = pte_offset_kernel(pmd, addr);
clear_pte_entry(kvm, pte, addr);
next = addr + PAGE_SIZE;
/* If we emptied the pte, walk back up the ladder */
if (page_empty(pte)) {
clear_pmd_entry(kvm, pmd, addr);
next = pmd_addr_end(addr, end);
if (page_empty(pmd) && !page_empty(pud)) {
clear_pud_entry(kvm, pud, addr);
next = pud_addr_end(addr, end);
}
}
addr = next;
}
}
