Merge branch 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 mm updates from Ingo Molnar:
 "The main changes in this cycle were:

   - Update and clean up x86 fault handling, by Andy Lutomirski.

   - Drop usage of __flush_tlb_all() in kernel_physical_mapping_init()
     and related fallout, by Dan Williams.

   - CPA cleanups and reorganization by Peter Zijlstra: simplify the
     flow and remove a few warts.

   - Other misc cleanups"

* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (29 commits)
  x86/mm/dump_pagetables: Use DEFINE_SHOW_ATTRIBUTE()
  x86/mm/cpa: Rename @addrinarray to @numpages
  x86/mm/cpa: Better use CLFLUSHOPT
  x86/mm/cpa: Fold cpa_flush_range() and cpa_flush_array() into a single cpa_flush() function
  x86/mm/cpa: Make cpa_data::numpages invariant
  x86/mm/cpa: Optimize cpa_flush_array() TLB invalidation
  x86/mm/cpa: Simplify the code after making cpa->vaddr invariant
  x86/mm/cpa: Make cpa_data::vaddr invariant
  x86/mm/cpa: Add __cpa_addr() helper
  x86/mm/cpa: Add ARRAY and PAGES_ARRAY selftests
  x86/mm: Drop usage of __flush_tlb_all() in kernel_physical_mapping_init()
  x86/mm: Validate kernel_physical_mapping_init() PTE population
  generic/pgtable: Introduce set_pte_safe()
  generic/pgtable: Introduce {p4d,pgd}_same()
  generic/pgtable: Make {pmd, pud}_same() unconditionally available
  x86/fault: Clean up the page fault oops decoder a bit
  x86/fault: Decode page fault OOPSes better
  x86/vsyscall/64: Use X86_PF constants in the simulated #PF error code
  x86/oops: Show the correct CS value in show_regs()
  x86/fault: Don't try to recover from an implicit supervisor access
  ...

1 files changed, 112 insertions, 159 deletions

diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index e44fe1a63f72..4f8972311a77 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -26,6 +26,8 @@
 #include <asm/pat.h>
 #include <asm/set_memory.h>
 
+#include "mm_internal.h"
+
 /*
  * The current flushing context - we pass it instead of 5 arguments:
  */
@@ -35,11 +37,11 @@ struct cpa_data {
 	pgprot_t	mask_set;
 	pgprot_t	mask_clr;
 	unsigned long	numpages;
-	int		flags;
+	unsigned long	curpage;
 	unsigned long	pfn;
-	unsigned	force_split		: 1,
+	unsigned int	flags;
+	unsigned int	force_split		: 1,
 			force_static_prot	: 1;
-	int		curpage;
 	struct page	**pages;
 };
 
@@ -228,19 +230,28 @@ static bool __cpa_pfn_in_highmap(unsigned long pfn)
 
 #endif
 
+static unsigned long __cpa_addr(struct cpa_data *cpa, unsigned long idx)
+{
+	if (cpa->flags & CPA_PAGES_ARRAY) {
+		struct page *page = cpa->pages[idx];
+
+		if (unlikely(PageHighMem(page)))
+			return 0;
+
+		return (unsigned long)page_address(page);
+	}
+
+	if (cpa->flags & CPA_ARRAY)
+		return cpa->vaddr[idx];
+
+	return *cpa->vaddr + idx * PAGE_SIZE;
+}
+
 /*
  * Flushing functions
  */
 
-/**
- * clflush_cache_range - flush a cache range with clflush
- * @vaddr:	virtual start address
- * @size:	number of bytes to flush
- *
- * clflushopt is an unordered instruction which needs fencing with mfence or
- * sfence to avoid ordering issues.
- */
-void clflush_cache_range(void *vaddr, unsigned int size)
+static void clflush_cache_range_opt(void *vaddr, unsigned int size)
 {
 	const unsigned long clflush_size = boot_cpu_data.x86_clflush_size;
 	void *p = (void *)((unsigned long)vaddr & ~(clflush_size - 1));
@@ -249,11 +260,22 @@ void clflush_cache_range(void *vaddr, unsigned int size)
 	if (p >= vend)
 		return;
 
-	mb();
-
 	for (; p < vend; p += clflush_size)
 		clflushopt(p);
+}
 
+/**
+ * clflush_cache_range - flush a cache range with clflush
+ * @vaddr:	virtual start address
+ * @size:	number of bytes to flush
+ *
+ * CLFLUSHOPT is an unordered instruction which needs fencing with MFENCE or
+ * SFENCE to avoid ordering issues.
+ */
+void clflush_cache_range(void *vaddr, unsigned int size)
+{
+	mb();
+	clflush_cache_range_opt(vaddr, size);
 	mb();
 }
 EXPORT_SYMBOL_GPL(clflush_cache_range);
@@ -285,87 +307,49 @@ static void cpa_flush_all(unsigned long cache)
 	on_each_cpu(__cpa_flush_all, (void *) cache, 1);
 }
 
-static bool __inv_flush_all(int cache)
+void __cpa_flush_tlb(void *data)
 {
-	BUG_ON(irqs_disabled() && !early_boot_irqs_disabled);
+	struct cpa_data *cpa = data;
+	unsigned int i;
 
-	if (cache && !static_cpu_has(X86_FEATURE_CLFLUSH)) {
-		cpa_flush_all(cache);
-		return true;
-	}
-
-	return false;
+	for (i = 0; i < cpa->numpages; i++)
+		__flush_tlb_one_kernel(__cpa_addr(cpa, i));
 }
 
-static void cpa_flush_range(unsigned long start, int numpages, int cache)
+static void cpa_flush(struct cpa_data *data, int cache)
 {
-	unsigned int i, level;
-	unsigned long addr;
+	struct cpa_data *cpa = data;
+	unsigned int i;
 
-	WARN_ON(PAGE_ALIGN(start) != start);
-
-	if (__inv_flush_all(cache))
-		return;
-
-	flush_tlb_kernel_range(start, start + PAGE_SIZE * numpages);
+	BUG_ON(irqs_disabled() && !early_boot_irqs_disabled);
 
-	if (!cache)
+	if (cache && !static_cpu_has(X86_FEATURE_CLFLUSH)) {
+		cpa_flush_all(cache);
 		return;
-
-	/*
-	 * We only need to flush on one CPU,
-	 * clflush is a MESI-coherent instruction that
-	 * will cause all other CPUs to flush the same
-	 * cachelines:
-	 */
-	for (i = 0, addr = start; i < numpages; i++, addr += PAGE_SIZE) {
-		pte_t *pte = lookup_address(addr, &level);
-
-		/*
-		 * Only flush present addresses:
-		 */
-		if (pte && (pte_val(*pte) & _PAGE_PRESENT))
-			clflush_cache_range((void *) addr, PAGE_SIZE);
 	}
-}
 
-static void cpa_flush_array(unsigned long baddr, unsigned long *start,
-			    int numpages, int cache,
-			    int in_flags, struct page **pages)
-{
-	unsigned int i, level;
-
-	if (__inv_flush_all(cache))
-		return;
-
-	flush_tlb_all();
+	if (cpa->numpages <= tlb_single_page_flush_ceiling)
+		on_each_cpu(__cpa_flush_tlb, cpa, 1);
+	else
+		flush_tlb_all();
 
 	if (!cache)
 		return;
 
-	/*
-	 * We only need to flush on one CPU,
-	 * clflush is a MESI-coherent instruction that
-	 * will cause all other CPUs to flush the same
-	 * cachelines:
-	 */
-	for (i = 0; i < numpages; i++) {
-		unsigned long addr;
-		pte_t *pte;
-
-		if (in_flags & CPA_PAGES_ARRAY)
-			addr = (unsigned long)page_address(pages[i]);
-		else
-			addr = start[i];
+	mb();
+	for (i = 0; i < cpa->numpages; i++) {
+		unsigned long addr = __cpa_addr(cpa, i);
+		unsigned int level;
 
-		pte = lookup_address(addr, &level);
+		pte_t *pte = lookup_address(addr, &level);
 
 		/*
 		 * Only flush present addresses:
 		 */
 		if (pte && (pte_val(*pte) & _PAGE_PRESENT))
-			clflush_cache_range((void *)addr, PAGE_SIZE);
+			clflush_cache_range_opt((void *)addr, PAGE_SIZE);
 	}
+	mb();
 }
 
 static bool overlaps(unsigned long r1_start, unsigned long r1_end,
@@ -1476,15 +1460,7 @@ static int __change_page_attr(struct cpa_data *cpa, int primary)
 	unsigned int level;
 	pte_t *kpte, old_pte;
 
-	if (cpa->flags & CPA_PAGES_ARRAY) {
-		struct page *page = cpa->pages[cpa->curpage];
-		if (unlikely(PageHighMem(page)))
-			return 0;
-		address = (unsigned long)page_address(page);
-	} else if (cpa->flags & CPA_ARRAY)
-		address = cpa->vaddr[cpa->curpage];
-	else
-		address = *cpa->vaddr;
+	address = __cpa_addr(cpa, cpa->curpage);
 repeat:
 	kpte = _lookup_address_cpa(cpa, address, &level);
 	if (!kpte)
@@ -1565,22 +1541,14 @@ static int cpa_process_alias(struct cpa_data *cpa)
 	 * No need to redo, when the primary call touched the direct
 	 * mapping already:
 	 */
-	if (cpa->flags & CPA_PAGES_ARRAY) {
-		struct page *page = cpa->pages[cpa->curpage];
-		if (unlikely(PageHighMem(page)))
-			return 0;
-		vaddr = (unsigned long)page_address(page);
-	} else if (cpa->flags & CPA_ARRAY)
-		vaddr = cpa->vaddr[cpa->curpage];
-	else
-		vaddr = *cpa->vaddr;
-
+	vaddr = __cpa_addr(cpa, cpa->curpage);
 	if (!(within(vaddr, PAGE_OFFSET,
 		    PAGE_OFFSET + (max_pfn_mapped << PAGE_SHIFT)))) {
 
 		alias_cpa = *cpa;
 		alias_cpa.vaddr = &laddr;
 		alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY);
+		alias_cpa.curpage = 0;
 
 		ret = __change_page_attr_set_clr(&alias_cpa, 0);
 		if (ret)
@@ -1600,6 +1568,7 @@ static int cpa_process_alias(struct cpa_data *cpa)
 		alias_cpa = *cpa;
 		alias_cpa.vaddr = &temp_cpa_vaddr;
 		alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY);
+		alias_cpa.curpage = 0;
 
 		/*
 		 * The high mapping range is imprecise, so ignore the
@@ -1615,14 +1584,15 @@ static int cpa_process_alias(struct cpa_data *cpa)
 static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias)
 {
 	unsigned long numpages = cpa->numpages;
-	int ret;
+	unsigned long rempages = numpages;
+	int ret = 0;
 
-	while (numpages) {
+	while (rempages) {
 		/*
 		 * Store the remaining nr of pages for the large page
 		 * preservation check.
 		 */
-		cpa->numpages = numpages;
+		cpa->numpages = rempages;
 		/* for array changes, we can't use large page */
 		if (cpa->flags & (CPA_ARRAY | CPA_PAGES_ARRAY))
 			cpa->numpages = 1;
@@ -1633,12 +1603,12 @@ static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias)
 		if (!debug_pagealloc_enabled())
 			spin_unlock(&cpa_lock);
 		if (ret)
-			return ret;
+			goto out;
 
 		if (checkalias) {
 			ret = cpa_process_alias(cpa);
 			if (ret)
-				return ret;
+				goto out;
 		}
 
 		/*
@@ -1646,15 +1616,15 @@ static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias)
 		 * CPA operation. Either a large page has been
 		 * preserved or a single page update happened.
 		 */
-		BUG_ON(cpa->numpages > numpages || !cpa->numpages);
-		numpages -= cpa->numpages;
-		if (cpa->flags & (CPA_PAGES_ARRAY | CPA_ARRAY))
-			cpa->curpage++;
-		else
-			*cpa->vaddr += cpa->numpages * PAGE_SIZE;
-
+		BUG_ON(cpa->numpages > rempages || !cpa->numpages);
+		rempages -= cpa->numpages;
+		cpa->curpage += cpa->numpages;
 	}
-	return 0;
+
+out:
+	/* Restore the original numpages */
+	cpa->numpages = numpages;
+	return ret;
 }
 
 /*
@@ -1687,7 +1657,6 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
 {
 	struct cpa_data cpa;
 	int ret, cache, checkalias;
-	unsigned long baddr = 0;
 
 	memset(&cpa, 0, sizeof(cpa));
 
@@ -1721,11 +1690,6 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
 			 */
 			WARN_ON_ONCE(1);
 		}
-		/*
-		 * Save address for cache flush. *addr is modified in the call
-		 * to __change_page_attr_set_clr() below.
-		 */
-		baddr = make_addr_canonical_again(*addr);
 	}
 
 	/* Must avoid aliasing mappings in the highmem code */
@@ -1773,13 +1737,7 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
 		goto out;
 	}
 
-	if (cpa.flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) {
-		cpa_flush_array(baddr, addr, numpages, cache,
-				cpa.flags, pages);
-	} else {
-		cpa_flush_range(baddr, numpages, cache);
-	}
-
+	cpa_flush(&cpa, cache);
 out:
 	return ret;
 }
@@ -1850,14 +1808,14 @@ out_err:
 }
 EXPORT_SYMBOL(set_memory_uc);
 
-static int _set_memory_array(unsigned long *addr, int addrinarray,
+static int _set_memory_array(unsigned long *addr, int numpages,
 		enum page_cache_mode new_type)
 {
 	enum page_cache_mode set_type;
 	int i, j;
 	int ret;
 
-	for (i = 0; i < addrinarray; i++) {
+	for (i = 0; i < numpages; i++) {
 		ret = reserve_memtype(__pa(addr[i]), __pa(addr[i]) + PAGE_SIZE,
 					new_type, NULL);
 		if (ret)
@@ -1868,11 +1826,11 @@ static int _set_memory_array(unsigned long *addr, int addrinarray,
 	set_type = (new_type == _PAGE_CACHE_MODE_WC) ?
 				_PAGE_CACHE_MODE_UC_MINUS : new_type;
 
-	ret = change_page_attr_set(addr, addrinarray,
+	ret = change_page_attr_set(addr, numpages,
 				   cachemode2pgprot(set_type), 1);
 
 	if (!ret && new_type == _PAGE_CACHE_MODE_WC)
-		ret = change_page_attr_set_clr(addr, addrinarray,
+		ret = change_page_attr_set_clr(addr, numpages,
 					       cachemode2pgprot(
 						_PAGE_CACHE_MODE_WC),
 					       __pgprot(_PAGE_CACHE_MASK),
@@ -1889,36 +1847,34 @@ out_free:
 	return ret;
 }
 
-int set_memory_array_uc(unsigned long *addr, int addrinarray)
+int set_memory_array_uc(unsigned long *addr, int numpages)
 {
-	return _set_memory_array(addr, addrinarray, _PAGE_CACHE_MODE_UC_MINUS);
+	return _set_memory_array(addr, numpages, _PAGE_CACHE_MODE_UC_MINUS);
 }
 EXPORT_SYMBOL(set_memory_array_uc);
 
-int set_memory_array_wc(unsigned long *addr, int addrinarray)
+int set_memory_array_wc(unsigned long *addr, int numpages)
 {
-	return _set_memory_array(addr, addrinarray, _PAGE_CACHE_MODE_WC);
+	return _set_memory_array(addr, numpages, _PAGE_CACHE_MODE_WC);
 }
 EXPORT_SYMBOL(set_memory_array_wc);
 
-int set_memory_array_wt(unsigned long *addr, int addrinarray)
+int set_memory_array_wt(unsigned long *addr, int numpages)
 {
-	return _set_memory_array(addr, addrinarray, _PAGE_CACHE_MODE_WT);
+	return _set_memory_array(addr, numpages, _PAGE_CACHE_MODE_WT);
 }
 EXPORT_SYMBOL_GPL(set_memory_array_wt);
 
 int _set_memory_wc(unsigned long addr, int numpages)
 {
 	int ret;
-	unsigned long addr_copy = addr;
 
 	ret = change_page_attr_set(&addr, numpages,
 				   cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS),
 				   0);
 	if (!ret) {
-		ret = change_page_attr_set_clr(&addr_copy, numpages,
-					       cachemode2pgprot(
-						_PAGE_CACHE_MODE_WC),
+		ret = change_page_attr_set_clr(&addr, numpages,
+					       cachemode2pgprot(_PAGE_CACHE_MODE_WC),
 					       __pgprot(_PAGE_CACHE_MASK),
 					       0, 0, NULL);
 	}
@@ -1985,18 +1941,18 @@ int set_memory_wb(unsigned long addr, int numpages)
 }
 EXPORT_SYMBOL(set_memory_wb);
 
-int set_memory_array_wb(unsigned long *addr, int addrinarray)
+int set_memory_array_wb(unsigned long *addr, int numpages)
 {
 	int i;
 	int ret;
 
 	/* WB cache mode is hard wired to all cache attribute bits being 0 */
-	ret = change_page_attr_clear(addr, addrinarray,
+	ret = change_page_attr_clear(addr, numpages,
 				      __pgprot(_PAGE_CACHE_MASK), 1);
 	if (ret)
 		return ret;
 
-	for (i = 0; i < addrinarray; i++)
+	for (i = 0; i < numpages; i++)
 		free_memtype(__pa(addr[i]), __pa(addr[i]) + PAGE_SIZE);
 
 	return 0;
@@ -2066,7 +2022,6 @@ int set_memory_global(unsigned long addr, int numpages)
 static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc)
 {
 	struct cpa_data cpa;
-	unsigned long start;
 	int ret;
 
 	/* Nothing to do if memory encryption is not active */
@@ -2077,8 +2032,6 @@ static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc)
 	if (WARN_ONCE(addr & ~PAGE_MASK, "misaligned address: %#lx\n", addr))
 		addr &= PAGE_MASK;
 
-	start = addr;
-
 	memset(&cpa, 0, sizeof(cpa));
 	cpa.vaddr = &addr;
 	cpa.numpages = numpages;
@@ -2093,18 +2046,18 @@ static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc)
 	/*
 	 * Before changing the encryption attribute, we need to flush caches.
 	 */
-	cpa_flush_range(start, numpages, 1);
+	cpa_flush(&cpa, 1);
 
 	ret = __change_page_attr_set_clr(&cpa, 1);
 
 	/*
-	 * After changing the encryption attribute, we need to flush TLBs
-	 * again in case any speculative TLB caching occurred (but no need
-	 * to flush caches again).  We could just use cpa_flush_all(), but
-	 * in case TLB flushing gets optimized in the cpa_flush_range()
-	 * path use the same logic as above.
+	 * After changing the encryption attribute, we need to flush TLBs again
+	 * in case any speculative TLB caching occurred (but no need to flush
+	 * caches again).  We could just use cpa_flush_all(), but in case TLB
+	 * flushing gets optimized in the cpa_flush() path use the same logic
+	 * as above.
 	 */
-	cpa_flush_range(start, numpages, 0);
+	cpa_flush(&cpa, 0);
 
 	return ret;
 }
@@ -2129,7 +2082,7 @@ int set_pages_uc(struct page *page, int numpages)
 }
 EXPORT_SYMBOL(set_pages_uc);
 
-static int _set_pages_array(struct page **pages, int addrinarray,
+static int _set_pages_array(struct page **pages, int numpages,
 		enum page_cache_mode new_type)
 {
 	unsigned long start;
@@ -2139,7 +2092,7 @@ static int _set_pages_array(struct page **pages, int addrinarray,
 	int free_idx;
 	int ret;
 
-	for (i = 0; i < addrinarray; i++) {
+	for (i = 0; i < numpages; i++) {
 		if (PageHighMem(pages[i]))
 			continue;
 		start = page_to_pfn(pages[i]) << PAGE_SHIFT;
@@ -2152,10 +2105,10 @@ static int _set_pages_array(struct page **pages, int addrinarray,
 	set_type = (new_type == _PAGE_CACHE_MODE_WC) ?
 				_PAGE_CACHE_MODE_UC_MINUS : new_type;
 
-	ret = cpa_set_pages_array(pages, addrinarray,
+	ret = cpa_set_pages_array(pages, numpages,
 				  cachemode2pgprot(set_type));
 	if (!ret && new_type == _PAGE_CACHE_MODE_WC)
-		ret = change_page_attr_set_clr(NULL, addrinarray,
+		ret = change_page_attr_set_clr(NULL, numpages,
 					       cachemode2pgprot(
 						_PAGE_CACHE_MODE_WC),
 					       __pgprot(_PAGE_CACHE_MASK),
@@ -2175,21 +2128,21 @@ err_out:
 	return -EINVAL;
 }
 
-int set_pages_array_uc(struct page **pages, int addrinarray)
+int set_pages_array_uc(struct page **pages, int numpages)
 {
-	return _set_pages_array(pages, addrinarray, _PAGE_CACHE_MODE_UC_MINUS);
+	return _set_pages_array(pages, numpages, _PAGE_CACHE_MODE_UC_MINUS);
 }
 EXPORT_SYMBOL(set_pages_array_uc);
 
-int set_pages_array_wc(struct page **pages, int addrinarray)
+int set_pages_array_wc(struct page **pages, int numpages)
 {
-	return _set_pages_array(pages, addrinarray, _PAGE_CACHE_MODE_WC);
+	return _set_pages_array(pages, numpages, _PAGE_CACHE_MODE_WC);
 }
 EXPORT_SYMBOL(set_pages_array_wc);
 
-int set_pages_array_wt(struct page **pages, int addrinarray)
+int set_pages_array_wt(struct page **pages, int numpages)
 {
-	return _set_pages_array(pages, addrinarray, _PAGE_CACHE_MODE_WT);
+	return _set_pages_array(pages, numpages, _PAGE_CACHE_MODE_WT);
 }
 EXPORT_SYMBOL_GPL(set_pages_array_wt);
 
@@ -2201,7 +2154,7 @@ int set_pages_wb(struct page *page, int numpages)
 }
 EXPORT_SYMBOL(set_pages_wb);
 
-int set_pages_array_wb(struct page **pages, int addrinarray)
+int set_pages_array_wb(struct page **pages, int numpages)
 {
 	int retval;
 	unsigned long start;
@@ -2209,12 +2162,12 @@ int set_pages_array_wb(struct page **pages, int addrinarray)
 	int i;
 
 	/* WB cache mode is hard wired to all cache attribute bits being 0 */
-	retval = cpa_clear_pages_array(pages, addrinarray,
+	retval = cpa_clear_pages_array(pages, numpages,
 			__pgprot(_PAGE_CACHE_MASK));
 	if (retval)
 		return retval;
 
-	for (i = 0; i < addrinarray; i++) {
+	for (i = 0; i < numpages; i++) {
 		if (PageHighMem(pages[i]))
 			continue;
 		start = page_to_pfn(pages[i]) << PAGE_SHIFT;