summaryrefslogtreecommitdiffstats
path: root/arch/x86/mm/pat/set_memory.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/mm/pat/set_memory.c')
-rw-r--r--arch/x86/mm/pat/set_memory.c139
1 files changed, 108 insertions, 31 deletions
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index 80c9037ffadf..44f7b2ea6a07 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -619,7 +619,8 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long start,
* Validate strict W^X semantics.
*/
static inline pgprot_t verify_rwx(pgprot_t old, pgprot_t new, unsigned long start,
- unsigned long pfn, unsigned long npg)
+ unsigned long pfn, unsigned long npg,
+ bool nx, bool rw)
{
unsigned long end;
@@ -641,6 +642,10 @@ static inline pgprot_t verify_rwx(pgprot_t old, pgprot_t new, unsigned long star
if ((pgprot_val(new) & (_PAGE_RW | _PAGE_NX)) != _PAGE_RW)
return new;
+ /* Non-leaf translation entries can disable writing or execution. */
+ if (!rw || nx)
+ return new;
+
end = start + npg * PAGE_SIZE - 1;
WARN_ONCE(1, "CPA detected W^X violation: %016llx -> %016llx range: 0x%016lx - 0x%016lx PFN %lx\n",
(unsigned long long)pgprot_val(old),
@@ -657,56 +662,82 @@ static inline pgprot_t verify_rwx(pgprot_t old, pgprot_t new, unsigned long star
/*
* Lookup the page table entry for a virtual address in a specific pgd.
- * Return a pointer to the entry and the level of the mapping.
+ * Return a pointer to the entry (or NULL if the entry does not exist),
+ * the level of the entry, and the effective NX and RW bits of all
+ * page table levels.
*/
-pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
- unsigned int *level)
+pte_t *lookup_address_in_pgd_attr(pgd_t *pgd, unsigned long address,
+ unsigned int *level, bool *nx, bool *rw)
{
p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
- *level = PG_LEVEL_NONE;
+ *level = PG_LEVEL_256T;
+ *nx = false;
+ *rw = true;
if (pgd_none(*pgd))
return NULL;
+ *level = PG_LEVEL_512G;
+ *nx |= pgd_flags(*pgd) & _PAGE_NX;
+ *rw &= pgd_flags(*pgd) & _PAGE_RW;
+
p4d = p4d_offset(pgd, address);
if (p4d_none(*p4d))
return NULL;
- *level = PG_LEVEL_512G;
if (p4d_leaf(*p4d) || !p4d_present(*p4d))
return (pte_t *)p4d;
+ *level = PG_LEVEL_1G;
+ *nx |= p4d_flags(*p4d) & _PAGE_NX;
+ *rw &= p4d_flags(*p4d) & _PAGE_RW;
+
pud = pud_offset(p4d, address);
if (pud_none(*pud))
return NULL;
- *level = PG_LEVEL_1G;
if (pud_leaf(*pud) || !pud_present(*pud))
return (pte_t *)pud;
+ *level = PG_LEVEL_2M;
+ *nx |= pud_flags(*pud) & _PAGE_NX;
+ *rw &= pud_flags(*pud) & _PAGE_RW;
+
pmd = pmd_offset(pud, address);
if (pmd_none(*pmd))
return NULL;
- *level = PG_LEVEL_2M;
if (pmd_leaf(*pmd) || !pmd_present(*pmd))
return (pte_t *)pmd;
*level = PG_LEVEL_4K;
+ *nx |= pmd_flags(*pmd) & _PAGE_NX;
+ *rw &= pmd_flags(*pmd) & _PAGE_RW;
return pte_offset_kernel(pmd, address);
}
/*
+ * Lookup the page table entry for a virtual address in a specific pgd.
+ * Return a pointer to the entry and the level of the mapping.
+ */
+pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
+ unsigned int *level)
+{
+ bool nx, rw;
+
+ return lookup_address_in_pgd_attr(pgd, address, level, &nx, &rw);
+}
+
+/*
* Lookup the page table entry for a virtual address. Return a pointer
* to the entry and the level of the mapping.
*
- * Note: We return pud and pmd either when the entry is marked large
- * or when the present bit is not set. Otherwise we would return a
- * pointer to a nonexisting mapping.
+ * Note: the function returns p4d, pud or pmd either when the entry is marked
+ * large or when the present bit is not set. Otherwise it returns NULL.
*/
pte_t *lookup_address(unsigned long address, unsigned int *level)
{
@@ -715,13 +746,16 @@ pte_t *lookup_address(unsigned long address, unsigned int *level)
EXPORT_SYMBOL_GPL(lookup_address);
static pte_t *_lookup_address_cpa(struct cpa_data *cpa, unsigned long address,
- unsigned int *level)
+ unsigned int *level, bool *nx, bool *rw)
{
- if (cpa->pgd)
- return lookup_address_in_pgd(cpa->pgd + pgd_index(address),
- address, level);
+ pgd_t *pgd;
+
+ if (!cpa->pgd)
+ pgd = pgd_offset_k(address);
+ else
+ pgd = cpa->pgd + pgd_index(address);
- return lookup_address(address, level);
+ return lookup_address_in_pgd_attr(pgd, address, level, nx, rw);
}
/*
@@ -849,12 +883,13 @@ static int __should_split_large_page(pte_t *kpte, unsigned long address,
pgprot_t old_prot, new_prot, req_prot, chk_prot;
pte_t new_pte, *tmp;
enum pg_level level;
+ bool nx, rw;
/*
* Check for races, another CPU might have split this page
* up already:
*/
- tmp = _lookup_address_cpa(cpa, address, &level);
+ tmp = _lookup_address_cpa(cpa, address, &level, &nx, &rw);
if (tmp != kpte)
return 1;
@@ -965,7 +1000,8 @@ static int __should_split_large_page(pte_t *kpte, unsigned long address,
new_prot = static_protections(req_prot, lpaddr, old_pfn, numpages,
psize, CPA_DETECT);
- new_prot = verify_rwx(old_prot, new_prot, lpaddr, old_pfn, numpages);
+ new_prot = verify_rwx(old_prot, new_prot, lpaddr, old_pfn, numpages,
+ nx, rw);
/*
* If there is a conflict, split the large page.
@@ -1046,6 +1082,7 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address,
pte_t *pbase = (pte_t *)page_address(base);
unsigned int i, level;
pgprot_t ref_prot;
+ bool nx, rw;
pte_t *tmp;
spin_lock(&pgd_lock);
@@ -1053,7 +1090,7 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address,
* Check for races, another CPU might have split this page
* up for us already:
*/
- tmp = _lookup_address_cpa(cpa, address, &level);
+ tmp = _lookup_address_cpa(cpa, address, &level, &nx, &rw);
if (tmp != kpte) {
spin_unlock(&pgd_lock);
return 1;
@@ -1082,8 +1119,8 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address,
lpinc = PMD_SIZE;
/*
* Clear the PSE flags if the PRESENT flag is not set
- * otherwise pmd_present/pmd_huge will return true
- * even on a non present pmd.
+ * otherwise pmd_present() will return true even on a non
+ * present pmd.
*/
if (!(pgprot_val(ref_prot) & _PAGE_PRESENT))
pgprot_val(ref_prot) &= ~_PAGE_PSE;
@@ -1594,10 +1631,11 @@ static int __change_page_attr(struct cpa_data *cpa, int primary)
int do_split, err;
unsigned int level;
pte_t *kpte, old_pte;
+ bool nx, rw;
address = __cpa_addr(cpa, cpa->curpage);
repeat:
- kpte = _lookup_address_cpa(cpa, address, &level);
+ kpte = _lookup_address_cpa(cpa, address, &level, &nx, &rw);
if (!kpte)
return __cpa_process_fault(cpa, address, primary);
@@ -1619,7 +1657,8 @@ repeat:
new_prot = static_protections(new_prot, address, pfn, 1, 0,
CPA_PROTECT);
- new_prot = verify_rwx(old_prot, new_prot, address, pfn, 1);
+ new_prot = verify_rwx(old_prot, new_prot, address, pfn, 1,
+ nx, rw);
new_prot = pgprot_clear_protnone_bits(new_prot);
@@ -2156,7 +2195,8 @@ static int __set_memory_enc_pgtable(unsigned long addr, int numpages, bool enc)
cpa_flush(&cpa, x86_platform.guest.enc_cache_flush_required());
/* Notify hypervisor that we are about to set/clr encryption attribute. */
- if (!x86_platform.guest.enc_status_change_prepare(addr, numpages, enc))
+ ret = x86_platform.guest.enc_status_change_prepare(addr, numpages, enc);
+ if (ret)
goto vmm_fail;
ret = __change_page_attr_set_clr(&cpa, 1);
@@ -2174,24 +2214,61 @@ static int __set_memory_enc_pgtable(unsigned long addr, int numpages, bool enc)
return ret;
/* Notify hypervisor that we have successfully set/clr encryption attribute. */
- if (!x86_platform.guest.enc_status_change_finish(addr, numpages, enc))
+ ret = x86_platform.guest.enc_status_change_finish(addr, numpages, enc);
+ if (ret)
goto vmm_fail;
return 0;
vmm_fail:
- WARN_ONCE(1, "CPA VMM failure to convert memory (addr=%p, numpages=%d) to %s.\n",
- (void *)addr, numpages, enc ? "private" : "shared");
+ WARN_ONCE(1, "CPA VMM failure to convert memory (addr=%p, numpages=%d) to %s: %d\n",
+ (void *)addr, numpages, enc ? "private" : "shared", ret);
+
+ return ret;
+}
+
+/*
+ * The lock serializes conversions between private and shared memory.
+ *
+ * It is taken for read on conversion. A write lock guarantees that no
+ * concurrent conversions are in progress.
+ */
+static DECLARE_RWSEM(mem_enc_lock);
+
+/*
+ * Stop new private<->shared conversions.
+ *
+ * Taking the exclusive mem_enc_lock waits for in-flight conversions to complete.
+ * The lock is not released to prevent new conversions from being started.
+ */
+bool set_memory_enc_stop_conversion(void)
+{
+ /*
+ * In a crash scenario, sleep is not allowed. Try to take the lock.
+ * Failure indicates that there is a race with the conversion.
+ */
+ if (oops_in_progress)
+ return down_write_trylock(&mem_enc_lock);
- return -EIO;
+ down_write(&mem_enc_lock);
+
+ return true;
}
static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc)
{
- if (cc_platform_has(CC_ATTR_MEM_ENCRYPT))
- return __set_memory_enc_pgtable(addr, numpages, enc);
+ int ret = 0;
- return 0;
+ if (cc_platform_has(CC_ATTR_MEM_ENCRYPT)) {
+ if (!down_read_trylock(&mem_enc_lock))
+ return -EBUSY;
+
+ ret = __set_memory_enc_pgtable(addr, numpages, enc);
+
+ up_read(&mem_enc_lock);
+ }
+
+ return ret;
}
int set_memory_encrypted(unsigned long addr, int numpages)