1 files changed, 173 insertions, 40 deletions

diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index c4aedd00c1ba..2e5a045731de 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -15,6 +15,11 @@
 #include <linux/gfp.h>
 #include <linux/pci.h>
 #include <linux/vmalloc.h>
+#include <linux/libnvdimm.h>
+#include <linux/vmstat.h>
+#include <linux/kernel.h>
+#include <linux/cc_platform.h>
+#include <linux/set_memory.h>
 
 #include <asm/e820/api.h>
 #include <asm/processor.h>
@@ -25,7 +30,8 @@
 #include <asm/pgalloc.h>
 #include <asm/proto.h>
 #include <asm/memtype.h>
-#include <asm/set_memory.h>
+#include <asm/hyperv-tlfs.h>
+#include <asm/mshyperv.h>
 
 #include "../mm_internal.h"
 
@@ -42,7 +48,8 @@ struct cpa_data {
 	unsigned long	pfn;
 	unsigned int	flags;
 	unsigned int	force_split		: 1,
-			force_static_prot	: 1;
+			force_static_prot	: 1,
+			force_flush_all		: 1;
 	struct page	**pages;
 };
 
@@ -67,6 +74,11 @@ static DEFINE_SPINLOCK(cpa_lock);
 #define CPA_PAGES_ARRAY 4
 #define CPA_NO_CHECK_ALIAS 8 /* Do not search for aliases */
 
+static inline pgprot_t cachemode2pgprot(enum page_cache_mode pcm)
+{
+	return __pgprot(cachemode2protval(pcm));
+}
+
 #ifdef CONFIG_PROC_FS
 static unsigned long direct_pages_count[PG_LEVEL_NUM];
 
@@ -84,6 +96,12 @@ static void split_page_count(int level)
 		return;
 
 	direct_pages_count[level]--;
+	if (system_state == SYSTEM_RUNNING) {
+		if (level == PG_LEVEL_2M)
+			count_vm_event(DIRECT_MAP_LEVEL2_SPLIT);
+		else if (level == PG_LEVEL_1G)
+			count_vm_event(DIRECT_MAP_LEVEL3_SPLIT);
+	}
 	direct_pages_count[level - 1] += PTRS_PER_PTE;
 }
 
@@ -128,7 +146,7 @@ static inline void cpa_inc_2m_checked(void)
 
 static inline void cpa_inc_4k_install(void)
 {
-	cpa_4k_install++;
+	data_race(cpa_4k_install++);
 }
 
 static inline void cpa_inc_lp_sameprot(int level)
@@ -304,11 +322,13 @@ void clflush_cache_range(void *vaddr, unsigned int size)
 }
 EXPORT_SYMBOL_GPL(clflush_cache_range);
 
+#ifdef CONFIG_ARCH_HAS_PMEM_API
 void arch_invalidate_pmem(void *addr, size_t size)
 {
 	clflush_cache_range(addr, size);
 }
 EXPORT_SYMBOL_GPL(arch_invalidate_pmem);
+#endif
 
 static void __cpa_flush_all(void *arg)
 {
@@ -337,7 +357,7 @@ static void __cpa_flush_tlb(void *data)
 	unsigned int i;
 
 	for (i = 0; i < cpa->numpages; i++)
-		__flush_tlb_one_kernel(fix_addr(__cpa_addr(cpa, i)));
+		flush_tlb_one_kernel(fix_addr(__cpa_addr(cpa, i)));
 }
 
 static void cpa_flush(struct cpa_data *data, int cache)
@@ -352,10 +372,10 @@ static void cpa_flush(struct cpa_data *data, int cache)
 		return;
 	}
 
-	if (cpa->numpages <= tlb_single_page_flush_ceiling)
-		on_each_cpu(__cpa_flush_tlb, cpa, 1);
-	else
+	if (cpa->force_flush_all || cpa->numpages > tlb_single_page_flush_ceiling)
 		flush_tlb_all();
+	else
+		on_each_cpu(__cpa_flush_tlb, cpa, 1);
 
 	if (!cache)
 		return;
@@ -560,6 +580,50 @@ 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 end;
+
+	/* Kernel text is rw at boot up */
+	if (system_state == SYSTEM_BOOTING)
+		return new;
+
+	/*
+	 * 32-bit has some unfixable W+X issues, like EFI code
+	 * and writeable data being in the same page.  Disable
+	 * detection and enforcement there.
+	 */
+	if (IS_ENABLED(CONFIG_X86_32))
+		return new;
+
+	/* Only verify when NX is supported: */
+	if (!(__supported_pte_mask & _PAGE_NX))
+		return new;
+
+	if (!((pgprot_val(old) ^ pgprot_val(new)) & (_PAGE_RW | _PAGE_NX)))
+		return new;
+
+	if ((pgprot_val(new) & (_PAGE_RW | _PAGE_NX)) != _PAGE_RW)
+		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),
+		  (unsigned long long)pgprot_val(new),
+		  start, end, pfn);
+
+	/*
+	 * For now, allow all permission change attempts by returning the
+	 * attempted permissions.  This can 'return old' to actively
+	 * refuse the permission change at a later time.
+	 */
+	return new;
+}
+
+/*
  * 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.
  */
@@ -618,17 +682,6 @@ pte_t *lookup_address(unsigned long address, unsigned int *level)
 }
 EXPORT_SYMBOL_GPL(lookup_address);
 
-/*
- * Lookup the page table entry for a virtual address in a given mm. Return a
- * pointer to the entry and the level of the mapping.
- */
-pte_t *lookup_address_in_mm(struct mm_struct *mm, unsigned long address,
-			    unsigned int *level)
-{
-	return lookup_address_in_pgd(pgd_offset(mm, address), address, level);
-}
-EXPORT_SYMBOL_GPL(lookup_address_in_mm);
-
 static pte_t *_lookup_address_cpa(struct cpa_data *cpa, unsigned long address,
 				  unsigned int *level)
 {
@@ -671,7 +724,7 @@ pmd_t *lookup_pmd_address(unsigned long address)
  * end up in this kind of memory, for instance.
  *
  * This could be optimized, but it is only intended to be
- * used at inititalization time, and keeping it
+ * used at initialization time, and keeping it
  * unoptimized should increase the testing coverage for
  * the more obscure platforms.
  */
@@ -876,6 +929,8 @@ 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);
+
 	/*
 	 * If there is a conflict, split the large page.
 	 *
@@ -1117,7 +1172,7 @@ static void __unmap_pmd_range(pud_t *pud, pmd_t *pmd,
 			      unsigned long start, unsigned long end)
 {
 	if (unmap_pte_range(pmd, start, end))
-		if (try_to_free_pmd_page((pmd_t *)pud_page_vaddr(*pud)))
+		if (try_to_free_pmd_page(pud_pgtable(*pud)))
 			pud_clear(pud);
 }
 
@@ -1161,7 +1216,7 @@ static void unmap_pmd_range(pud_t *pud, unsigned long start, unsigned long end)
 	 * Try again to free the PMD page if haven't succeeded above.
 	 */
 	if (!pud_none(*pud))
-		if (try_to_free_pmd_page((pmd_t *)pud_page_vaddr(*pud)))
+		if (try_to_free_pmd_page(pud_pgtable(*pud)))
 			pud_clear(pud);
 }
 
@@ -1516,6 +1571,7 @@ repeat:
 
 	if (level == PG_LEVEL_4K) {
 		pte_t new_pte;
+		pgprot_t old_prot = pte_pgprot(old_pte);
 		pgprot_t new_prot = pte_pgprot(old_pte);
 		unsigned long pfn = pte_pfn(old_pte);
 
@@ -1527,6 +1583,8 @@ 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 = pgprot_clear_protnone_bits(new_prot);
 
 		/*
@@ -1595,6 +1653,8 @@ static int cpa_process_alias(struct cpa_data *cpa)
 		alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY);
 		alias_cpa.curpage = 0;
 
+		cpa->force_flush_all = 1;
+
 		ret = __change_page_attr_set_clr(&alias_cpa, 0);
 		if (ret)
 			return ret;
@@ -1615,6 +1675,7 @@ static int cpa_process_alias(struct cpa_data *cpa)
 		alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY);
 		alias_cpa.curpage = 0;
 
+		cpa->force_flush_all = 1;
 		/*
 		 * The high mapping range is imprecise, so ignore the
 		 * return value.
@@ -1792,6 +1853,19 @@ static inline int cpa_clear_pages_array(struct page **pages, int numpages,
 		CPA_PAGES_ARRAY, pages);
 }
 
+/*
+ * __set_memory_prot is an internal helper for callers that have been passed
+ * a pgprot_t value from upper layers and a reservation has already been taken.
+ * If you want to set the pgprot to a specific page protocol, use the
+ * set_memory_xx() functions.
+ */
+int __set_memory_prot(unsigned long addr, int numpages, pgprot_t prot)
+{
+	return change_page_attr_set_clr(&addr, numpages, prot,
+					__pgprot(~pgprot_val(prot)), 0, 0,
+					NULL);
+}
+
 int _set_memory_uc(unsigned long addr, int numpages)
 {
 	/*
@@ -1889,6 +1963,51 @@ int set_memory_wb(unsigned long addr, int numpages)
 }
 EXPORT_SYMBOL(set_memory_wb);
 
+/* Prevent speculative access to a page by marking it not-present */
+#ifdef CONFIG_X86_64
+int set_mce_nospec(unsigned long pfn)
+{
+	unsigned long decoy_addr;
+	int rc;
+
+	/* SGX pages are not in the 1:1 map */
+	if (arch_is_platform_page(pfn << PAGE_SHIFT))
+		return 0;
+	/*
+	 * We would like to just call:
+	 *      set_memory_XX((unsigned long)pfn_to_kaddr(pfn), 1);
+	 * but doing that would radically increase the odds of a
+	 * speculative access to the poison page because we'd have
+	 * the virtual address of the kernel 1:1 mapping sitting
+	 * around in registers.
+	 * Instead we get tricky.  We create a non-canonical address
+	 * that looks just like the one we want, but has bit 63 flipped.
+	 * This relies on set_memory_XX() properly sanitizing any __pa()
+	 * results with __PHYSICAL_MASK or PTE_PFN_MASK.
+	 */
+	decoy_addr = (pfn << PAGE_SHIFT) + (PAGE_OFFSET ^ BIT(63));
+
+	rc = set_memory_np(decoy_addr, 1);
+	if (rc)
+		pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn);
+	return rc;
+}
+
+static int set_memory_p(unsigned long *addr, int numpages)
+{
+	return change_page_attr_set(addr, numpages, __pgprot(_PAGE_PRESENT), 0);
+}
+
+/* Restore full speculative operation to the pfn. */
+int clear_mce_nospec(unsigned long pfn)
+{
+	unsigned long addr = (unsigned long) pfn_to_kaddr(pfn);
+
+	return set_memory_p(&addr, 1);
+}
+EXPORT_SYMBOL_GPL(clear_mce_nospec);
+#endif /* CONFIG_X86_64 */
+
 int set_memory_x(unsigned long addr, int numpages)
 {
 	if (!(__supported_pte_mask & _PAGE_NX))
@@ -1947,15 +2066,16 @@ int set_memory_global(unsigned long addr, int numpages)
 				    __pgprot(_PAGE_GLOBAL), 0);
 }
 
-static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc)
+/*
+ * __set_memory_enc_pgtable() is used for the hypervisors that get
+ * informed about "encryption" status via page tables.
+ */
+static int __set_memory_enc_pgtable(unsigned long addr, int numpages, bool enc)
 {
+	pgprot_t empty = __pgprot(0);
 	struct cpa_data cpa;
 	int ret;
 
-	/* Nothing to do if memory encryption is not active */
-	if (!mem_encrypt_active())
-		return 0;
-
 	/* Should not be working on unaligned addresses */
 	if (WARN_ONCE(addr & ~PAGE_MASK, "misaligned address: %#lx\n", addr))
 		addr &= PAGE_MASK;
@@ -1963,18 +2083,20 @@ static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc)
 	memset(&cpa, 0, sizeof(cpa));
 	cpa.vaddr = &addr;
 	cpa.numpages = numpages;
-	cpa.mask_set = enc ? __pgprot(_PAGE_ENC) : __pgprot(0);
-	cpa.mask_clr = enc ? __pgprot(0) : __pgprot(_PAGE_ENC);
+	cpa.mask_set = enc ? pgprot_encrypted(empty) : pgprot_decrypted(empty);
+	cpa.mask_clr = enc ? pgprot_decrypted(empty) : pgprot_encrypted(empty);
 	cpa.pgd = init_mm.pgd;
 
 	/* Must avoid aliasing mappings in the highmem code */
 	kmap_flush_unused();
 	vm_unmap_aliases();
 
-	/*
-	 * Before changing the encryption attribute, we need to flush caches.
-	 */
-	cpa_flush(&cpa, 1);
+	/* Flush the caches as needed before changing the encryption attribute. */
+	if (x86_platform.guest.enc_tlb_flush_required(enc))
+		cpa_flush(&cpa, x86_platform.guest.enc_cache_flush_required());
+
+	/* Notify hypervisor that we are about to set/clr encryption attribute. */
+	x86_platform.guest.enc_status_change_prepare(addr, numpages, enc);
 
 	ret = __change_page_attr_set_clr(&cpa, 1);
 
@@ -1987,9 +2109,26 @@ static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc)
 	 */
 	cpa_flush(&cpa, 0);
 
+	/* Notify hypervisor that we have successfully set/clr encryption attribute. */
+	if (!ret) {
+		if (!x86_platform.guest.enc_status_change_finish(addr, numpages, enc))
+			ret = -EIO;
+	}
+
 	return ret;
 }
 
+static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc)
+{
+	if (hv_is_isolation_supported())
+		return hv_set_mem_host_visibility(addr, numpages, !enc);
+
+	if (cc_platform_has(CC_ATTR_MEM_ENCRYPT))
+		return __set_memory_enc_pgtable(addr, numpages, enc);
+
+	return 0;
+}
+
 int set_memory_encrypted(unsigned long addr, int numpages)
 {
 	return __set_memory_enc_dec(addr, numpages, true);
@@ -2068,12 +2207,6 @@ int set_pages_array_wc(struct page **pages, int numpages)
 }
 EXPORT_SYMBOL(set_pages_array_wc);
 
-int set_pages_array_wt(struct page **pages, int numpages)
-{
-	return _set_pages_array(pages, numpages, _PAGE_CACHE_MODE_WT);
-}
-EXPORT_SYMBOL_GPL(set_pages_array_wt);
-
 int set_pages_wb(struct page *page, int numpages)
 {
 	unsigned long addr = (unsigned long)page_address(page);
@@ -2169,6 +2302,7 @@ int set_direct_map_default_noflush(struct page *page)
 	return __set_pages_p(page, 1);
 }
 
+#ifdef CONFIG_DEBUG_PAGEALLOC
 void __kernel_map_pages(struct page *page, int numpages, int enable)
 {
 	if (PageHighMem(page))
@@ -2200,8 +2334,8 @@ void __kernel_map_pages(struct page *page, int numpages, int enable)
 
 	arch_flush_lazy_mmu_mode();
 }
+#endif /* CONFIG_DEBUG_PAGEALLOC */
 
-#ifdef CONFIG_HIBERNATION
 bool kernel_page_present(struct page *page)
 {
 	unsigned int level;
@@ -2213,7 +2347,6 @@ bool kernel_page_present(struct page *page)
 	pte = lookup_address((unsigned long)page_address(page), &level);
 	return (pte_val(*pte) & _PAGE_PRESENT);
 }
-#endif /* CONFIG_HIBERNATION */
 
 int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
 				   unsigned numpages, unsigned long page_flags)