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

Pull x86 boot updates from Thomas Gleixner:
 "Boot code updates for x86:

   - Allow to skip a given amount of huge pages for address layout
     randomization on the kernel command line to prevent regressions in
     the huge page allocation with small memory sizes

   - Various cleanups"

* 'x86-boot-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/boot: Use CC_SET()/CC_OUT() instead of open coding it
  x86/boot/KASLR: Make local variable mem_limit static
  x86/boot/KASLR: Skip specified number of 1GB huge pages when doing physical randomization (KASLR)
  x86/boot/KASLR: Add two new functions for 1GB huge pages handling

3 files changed, 97 insertions, 9 deletions

diff --git a/arch/x86/boot/bitops.h b/arch/x86/boot/bitops.h
index 0d41d68131cc..2e1382486e91 100644
--- a/arch/x86/boot/bitops.h
+++ b/arch/x86/boot/bitops.h
@@ -17,6 +17,7 @@
 #define _LINUX_BITOPS_H		/* Inhibit inclusion of <linux/bitops.h> */
 
 #include <linux/types.h>
+#include <asm/asm.h>
 
 static inline bool constant_test_bit(int nr, const void *addr)
 {
@@ -28,7 +29,7 @@ static inline bool variable_test_bit(int nr, const void *addr)
 	bool v;
 	const u32 *p = (const u32 *)addr;
 
-	asm("btl %2,%1; setc %0" : "=qm" (v) : "m" (*p), "Ir" (nr));
+	asm("btl %2,%1" CC_SET(c) : CC_OUT(c) (v) : "m" (*p), "Ir" (nr));
 	return v;
 }
 
diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c
index b87a7582853d..302517929932 100644
--- a/arch/x86/boot/compressed/kaslr.c
+++ b/arch/x86/boot/compressed/kaslr.c
@@ -102,7 +102,7 @@ static bool memmap_too_large;
 
 
 /* Store memory limit specified by "mem=nn[KMG]" or "memmap=nn[KMG]" */
-unsigned long long mem_limit = ULLONG_MAX;
+static unsigned long long mem_limit = ULLONG_MAX;
 
 
 enum mem_avoid_index {
@@ -215,7 +215,36 @@ static void mem_avoid_memmap(char *str)
 		memmap_too_large = true;
 }
 
-static int handle_mem_memmap(void)
+/* Store the number of 1GB huge pages which users specified: */
+static unsigned long max_gb_huge_pages;
+
+static void parse_gb_huge_pages(char *param, char *val)
+{
+	static bool gbpage_sz;
+	char *p;
+
+	if (!strcmp(param, "hugepagesz")) {
+		p = val;
+		if (memparse(p, &p) != PUD_SIZE) {
+			gbpage_sz = false;
+			return;
+		}
+
+		if (gbpage_sz)
+			warn("Repeatedly set hugeTLB page size of 1G!\n");
+		gbpage_sz = true;
+		return;
+	}
+
+	if (!strcmp(param, "hugepages") && gbpage_sz) {
+		p = val;
+		max_gb_huge_pages = simple_strtoull(p, &p, 0);
+		return;
+	}
+}
+
+
+static int handle_mem_options(void)
 {
 	char *args = (char *)get_cmd_line_ptr();
 	size_t len = strlen((char *)args);
@@ -223,7 +252,8 @@ static int handle_mem_memmap(void)
 	char *param, *val;
 	u64 mem_size;
 
-	if (!strstr(args, "memmap=") && !strstr(args, "mem="))
+	if (!strstr(args, "memmap=") && !strstr(args, "mem=") &&
+		!strstr(args, "hugepages"))
 		return 0;
 
 	tmp_cmdline = malloc(len + 1);
@@ -248,6 +278,8 @@ static int handle_mem_memmap(void)
 
 		if (!strcmp(param, "memmap")) {
 			mem_avoid_memmap(val);
+		} else if (strstr(param, "hugepages")) {
+			parse_gb_huge_pages(param, val);
 		} else if (!strcmp(param, "mem")) {
 			char *p = val;
 
@@ -387,7 +419,7 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size,
 	/* We don't need to set a mapping for setup_data. */
 
 	/* Mark the memmap regions we need to avoid */
-	handle_mem_memmap();
+	handle_mem_options();
 
 #ifdef CONFIG_X86_VERBOSE_BOOTUP
 	/* Make sure video RAM can be used. */
@@ -466,6 +498,60 @@ static void store_slot_info(struct mem_vector *region, unsigned long image_size)
 	}
 }
 
+/*
+ * Skip as many 1GB huge pages as possible in the passed region
+ * according to the number which users specified:
+ */
+static void
+process_gb_huge_pages(struct mem_vector *region, unsigned long image_size)
+{
+	unsigned long addr, size = 0;
+	struct mem_vector tmp;
+	int i = 0;
+
+	if (!max_gb_huge_pages) {
+		store_slot_info(region, image_size);
+		return;
+	}
+
+	addr = ALIGN(region->start, PUD_SIZE);
+	/* Did we raise the address above the passed in memory entry? */
+	if (addr < region->start + region->size)
+		size = region->size - (addr - region->start);
+
+	/* Check how many 1GB huge pages can be filtered out: */
+	while (size > PUD_SIZE && max_gb_huge_pages) {
+		size -= PUD_SIZE;
+		max_gb_huge_pages--;
+		i++;
+	}
+
+	/* No good 1GB huge pages found: */
+	if (!i) {
+		store_slot_info(region, image_size);
+		return;
+	}
+
+	/*
+	 * Skip those 'i'*1GB good huge pages, and continue checking and
+	 * processing the remaining head or tail part of the passed region
+	 * if available.
+	 */
+
+	if (addr >= region->start + image_size) {
+		tmp.start = region->start;
+		tmp.size = addr - region->start;
+		store_slot_info(&tmp, image_size);
+	}
+
+	size  = region->size - (addr - region->start) - i * PUD_SIZE;
+	if (size >= image_size) {
+		tmp.start = addr + i * PUD_SIZE;
+		tmp.size = size;
+		store_slot_info(&tmp, image_size);
+	}
+}
+
 static unsigned long slots_fetch_random(void)
 {
 	unsigned long slot;
@@ -546,7 +632,7 @@ static void process_mem_region(struct mem_vector *entry,
 
 		/* If nothing overlaps, store the region and return. */
 		if (!mem_avoid_overlap(&region, &overlap)) {
-			store_slot_info(&region, image_size);
+			process_gb_huge_pages(&region, image_size);
 			return;
 		}
 
@@ -556,7 +642,7 @@ static void process_mem_region(struct mem_vector *entry,
 
 			beginning.start = region.start;
 			beginning.size = overlap.start - region.start;
-			store_slot_info(&beginning, image_size);
+			process_gb_huge_pages(&beginning, image_size);
 		}
 
 		/* Return if overlap extends to or past end of region. */
diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c
index 16f49123d747..c4428a176973 100644
--- a/arch/x86/boot/string.c
+++ b/arch/x86/boot/string.c
@@ -13,6 +13,7 @@
  */
 
 #include <linux/types.h>
+#include <asm/asm.h>
 #include "ctype.h"
 #include "string.h"
 
@@ -28,8 +29,8 @@
 int memcmp(const void *s1, const void *s2, size_t len)
 {
 	bool diff;
-	asm("repe; cmpsb; setnz %0"
-	    : "=qm" (diff), "+D" (s1), "+S" (s2), "+c" (len));
+	asm("repe; cmpsb" CC_SET(nz)
+	    : CC_OUT(nz) (diff), "+D" (s1), "+S" (s2), "+c" (len));
 	return diff;
 }