Merge "Merge android-4.4.104 (8bc4213) into msm-4.4"

71 files changed, 514 insertions, 313 deletions

diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi
index d23e2524d694..be9c37e89be1 100644
--- a/arch/arm/boot/dts/am33xx.dtsi
+++ b/arch/arm/boot/dts/am33xx.dtsi
@@ -142,10 +142,11 @@
 				};
 
 				scm_conf: scm_conf@0 {
-					compatible = "syscon";
+					compatible = "syscon", "simple-bus";
 					reg = <0x0 0x800>;
 					#address-cells = <1>;
 					#size-cells = <1>;
+					ranges = <0 0 0x800>;
 
 					scm_clocks: clocks {
 						#address-cells = <1>;
diff --git a/arch/arm/boot/dts/dm814x.dtsi b/arch/arm/boot/dts/dm814x.dtsi
index 7988b42e5764..c226c3d952d8 100644
--- a/arch/arm/boot/dts/dm814x.dtsi
+++ b/arch/arm/boot/dts/dm814x.dtsi
@@ -138,7 +138,7 @@
 			};
 
 			uart1: uart@20000 {
-				compatible = "ti,omap3-uart";
+				compatible = "ti,am3352-uart", "ti,omap3-uart";
 				ti,hwmods = "uart1";
 				reg = <0x20000 0x2000>;
 				clock-frequency = <48000000>;
@@ -148,7 +148,7 @@
 			};
 
 			uart2: uart@22000 {
-				compatible = "ti,omap3-uart";
+				compatible = "ti,am3352-uart", "ti,omap3-uart";
 				ti,hwmods = "uart2";
 				reg = <0x22000 0x2000>;
 				clock-frequency = <48000000>;
@@ -158,7 +158,7 @@
 			};
 
 			uart3: uart@24000 {
-				compatible = "ti,omap3-uart";
+				compatible = "ti,am3352-uart", "ti,omap3-uart";
 				ti,hwmods = "uart3";
 				reg = <0x24000 0x2000>;
 				clock-frequency = <48000000>;
@@ -189,10 +189,11 @@
 				ranges = <0 0x160000 0x16d000>;
 
 				scm_conf: scm_conf@0 {
-					compatible = "syscon";
+					compatible = "syscon", "simple-bus";
 					reg = <0x0 0x800>;
 					#address-cells = <1>;
 					#size-cells = <1>;
+					ranges = <0 0 0x800>;
 
 					scm_clocks: clocks {
 						#address-cells = <1>;
diff --git a/arch/arm/boot/dts/dm816x.dtsi b/arch/arm/boot/dts/dm816x.dtsi
index eee636de4cd8..e526928e6e96 100644
--- a/arch/arm/boot/dts/dm816x.dtsi
+++ b/arch/arm/boot/dts/dm816x.dtsi
@@ -347,7 +347,7 @@
 		};
 
 		uart1: uart@48020000 {
-			compatible = "ti,omap3-uart";
+			compatible = "ti,am3352-uart", "ti,omap3-uart";
 			ti,hwmods = "uart1";
 			reg = <0x48020000 0x2000>;
 			clock-frequency = <48000000>;
@@ -357,7 +357,7 @@
 		};
 
 		uart2: uart@48022000 {
-			compatible = "ti,omap3-uart";
+			compatible = "ti,am3352-uart", "ti,omap3-uart";
 			ti,hwmods = "uart2";
 			reg = <0x48022000 0x2000>;
 			clock-frequency = <48000000>;
@@ -367,7 +367,7 @@
 		};
 
 		uart3: uart@48024000 {
-			compatible = "ti,omap3-uart";
+			compatible = "ti,am3352-uart", "ti,omap3-uart";
 			ti,hwmods = "uart3";
 			reg = <0x48024000 0x2000>;
 			clock-frequency = <48000000>;
diff --git a/arch/arm/boot/dts/logicpd-torpedo-37xx-devkit.dts b/arch/arm/boot/dts/logicpd-torpedo-37xx-devkit.dts
index 5b0430041ec6..fec92cd36ae3 100644
--- a/arch/arm/boot/dts/logicpd-torpedo-37xx-devkit.dts
+++ b/arch/arm/boot/dts/logicpd-torpedo-37xx-devkit.dts
@@ -88,7 +88,7 @@
 	interrupts-extended = <&intc 83 &omap3_pmx_core 0x11a>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc1_pins &mmc1_cd>;
-	cd-gpios = <&gpio4 31 IRQ_TYPE_LEVEL_LOW>;		/* gpio127 */
+	cd-gpios = <&gpio4 31 GPIO_ACTIVE_LOW>;		/* gpio127 */
 	vmmc-supply = <&vmmc1>;
 	bus-width = <4>;
 	cap-power-off-card;
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index c5e1943e5427..09ebd37e01e0 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -221,6 +221,7 @@ CONFIG_SERIO=m
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_8250_NR_UARTS=32
+CONFIG_SERIAL_8250_RUNTIME_UARTS=6
 CONFIG_SERIAL_8250_EXTENDED=y
 CONFIG_SERIAL_8250_MANY_PORTS=y
 CONFIG_SERIAL_8250_SHARE_IRQ=y
diff --git a/arch/arm/crypto/aesbs-glue.c b/arch/arm/crypto/aesbs-glue.c
index 6d685298690e..648d5fac9cbf 100644
--- a/arch/arm/crypto/aesbs-glue.c
+++ b/arch/arm/crypto/aesbs-glue.c
@@ -357,7 +357,7 @@ static struct crypto_alg aesbs_algs[] = { {
 }, {
 	.cra_name		= "cbc(aes)",
 	.cra_driver_name	= "cbc-aes-neonbs",
-	.cra_priority		= 300,
+	.cra_priority		= 250,
 	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
 	.cra_blocksize		= AES_BLOCK_SIZE,
 	.cra_ctxsize		= sizeof(struct async_helper_ctx),
@@ -377,7 +377,7 @@ static struct crypto_alg aesbs_algs[] = { {
 }, {
 	.cra_name		= "ctr(aes)",
 	.cra_driver_name	= "ctr-aes-neonbs",
-	.cra_priority		= 300,
+	.cra_priority		= 250,
 	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
 	.cra_blocksize		= 1,
 	.cra_ctxsize		= sizeof(struct async_helper_ctx),
@@ -397,7 +397,7 @@ static struct crypto_alg aesbs_algs[] = { {
 }, {
 	.cra_name		= "xts(aes)",
 	.cra_driver_name	= "xts-aes-neonbs",
-	.cra_priority		= 300,
+	.cra_priority		= 250,
 	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
 	.cra_blocksize		= AES_BLOCK_SIZE,
 	.cra_ctxsize		= sizeof(struct async_helper_ctx),
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index cdefc69c656b..75a371951f1a 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -133,30 +133,26 @@ static void dump_mem(const char *lvl, const char *str, unsigned long bottom,
 	set_fs(fs);
 }
 
-static void dump_instr(const char *lvl, struct pt_regs *regs)
+static void __dump_instr(const char *lvl, struct pt_regs *regs)
 {
 	unsigned long addr = instruction_pointer(regs);
 	const int thumb = thumb_mode(regs);
 	const int width = thumb ? 4 : 8;
-	mm_segment_t fs;
 	char str[sizeof("00000000 ") * 5 + 2 + 1], *p = str;
 	int i;
 
 	/*
-	 * We need to switch to kernel mode so that we can use __get_user
-	 * to safely read from kernel space.  Note that we now dump the
-	 * code first, just in case the backtrace kills us.
+	 * Note that we now dump the code first, just in case the backtrace
+	 * kills us.
 	 */
-	fs = get_fs();
-	set_fs(KERNEL_DS);
 
 	for (i = -4; i < 1 + !!thumb; i++) {
 		unsigned int val, bad;
 
 		if (thumb)
-			bad = __get_user(val, &((u16 *)addr)[i]);
+			bad = get_user(val, &((u16 *)addr)[i]);
 		else
-			bad = __get_user(val, &((u32 *)addr)[i]);
+			bad = get_user(val, &((u32 *)addr)[i]);
 
 		if (!bad)
 			p += sprintf(p, i == 0 ? "(%0*x) " : "%0*x ",
@@ -167,8 +163,20 @@ static void dump_instr(const char *lvl, struct pt_regs *regs)
 		}
 	}
 	printk("%sCode: %s\n", lvl, str);
+}
 
-	set_fs(fs);
+static void dump_instr(const char *lvl, struct pt_regs *regs)
+{
+	mm_segment_t fs;
+
+	if (!user_mode(regs)) {
+		fs = get_fs();
+		set_fs(KERNEL_DS);
+		__dump_instr(lvl, regs);
+		set_fs(fs);
+	} else {
+		__dump_instr(lvl, regs);
+	}
 }
 
 #ifdef CONFIG_ARM_UNWIND
diff --git a/arch/arm/mach-omap2/pdata-quirks.c b/arch/arm/mach-omap2/pdata-quirks.c
index 58144779dec4..1e6e09841707 100644
--- a/arch/arm/mach-omap2/pdata-quirks.c
+++ b/arch/arm/mach-omap2/pdata-quirks.c
@@ -522,7 +522,6 @@ static void pdata_quirks_check(struct pdata_init *quirks)
 		if (of_machine_is_compatible(quirks->compatible)) {
 			if (quirks->fn)
 				quirks->fn();
-			break;
 		}
 		quirks++;
 	}
diff --git a/arch/arm/mm/dump.c b/arch/arm/mm/dump.c
index 9fe8e241335c..e1f6f0daa847 100644
--- a/arch/arm/mm/dump.c
+++ b/arch/arm/mm/dump.c
@@ -126,8 +126,8 @@ static const struct prot_bits section_bits[] = {
 		.val	= PMD_SECT_USER,
 		.set	= "USR",
 	}, {
-		.mask	= L_PMD_SECT_RDONLY,
-		.val	= L_PMD_SECT_RDONLY,
+		.mask	= L_PMD_SECT_RDONLY | PMD_SECT_AP2,
+		.val	= L_PMD_SECT_RDONLY | PMD_SECT_AP2,
 		.set	= "ro",
 		.clear	= "RW",
 #elif __LINUX_ARM_ARCH__ >= 6
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index d3d718772381..4d58a6eca48e 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -669,8 +669,8 @@ static struct section_perm ro_perms[] = {
 		.start  = (unsigned long)_stext,
 		.end    = (unsigned long)__init_begin,
 #ifdef CONFIG_ARM_LPAE
-		.mask   = ~L_PMD_SECT_RDONLY,
-		.prot   = L_PMD_SECT_RDONLY,
+		.mask   = ~(L_PMD_SECT_RDONLY | PMD_SECT_AP2),
+		.prot   = L_PMD_SECT_RDONLY | PMD_SECT_AP2,
 #else
 		.mask   = ~(PMD_SECT_APX | PMD_SECT_AP_WRITE),
 		.prot   = PMD_SECT_APX | PMD_SECT_AP_WRITE,
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 3cb501b93da6..4c72ce5955d9 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -104,6 +104,7 @@ config ARM64
 	select HAVE_CONTEXT_TRACKING
 	select HAVE_ARM_SMCCC
 	select THREAD_INFO_IN_TASK
+	select HAVE_ARM_SMCCC
 	help
 	  ARM 64-bit (AArch64) Linux support.
 
diff --git a/arch/arm64/boot/dts/broadcom/ns2.dtsi b/arch/arm64/boot/dts/broadcom/ns2.dtsi
index 3c92d92278e5..a14a6bb31887 100644
--- a/arch/arm64/boot/dts/broadcom/ns2.dtsi
+++ b/arch/arm64/boot/dts/broadcom/ns2.dtsi
@@ -30,6 +30,8 @@
  * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
 
+/memreserve/ 0x81000000 0x00200000;
+
 #include <dt-bindings/interrupt-controller/arm-gic.h>
 
 /memreserve/ 0x84b00000 0x00000008;
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 320dc9c7e4f4..c6aae0b85cef 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -266,7 +266,7 @@ static inline void __kvm_flush_dcache_pud(pud_t pud)
 	kvm_flush_dcache_to_poc(page_address(page), PUD_SIZE);
 }
 
-#define kvm_virt_to_phys(x)		__virt_to_phys((unsigned long)(x))
+#define kvm_virt_to_phys(x)		__pa_symbol(x)
 
 void kvm_set_way_flush(struct kvm_vcpu *vcpu);
 void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled);
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index ae11e8fdbfd2..915b2422d9d0 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -188,6 +188,7 @@ static inline void *phys_to_virt(phys_addr_t x)
 #define __va(x)			((void *)__phys_to_virt((phys_addr_t)(x)))
 #define pfn_to_kaddr(pfn)	__va((pfn) << PAGE_SHIFT)
 #define virt_to_pfn(x)      __phys_to_pfn(__virt_to_phys(x))
+#define sym_to_pfn(x)	    __phys_to_pfn(__pa_symbol(x))
 
 /*
  *  virt_to_page(k)	convert a _valid_ virtual address to struct page *
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index ba8343303284..2e36504f56b6 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -55,7 +55,7 @@ static inline void contextidr_thread_switch(struct task_struct *next)
  */
 static inline void cpu_set_reserved_ttbr0(void)
 {
-	unsigned long ttbr = virt_to_phys(empty_zero_page);
+	unsigned long ttbr = __pa_symbol(empty_zero_page);
 
 	asm(
 	"	msr	ttbr0_el1, %0			// set TTBR0\n"
@@ -129,7 +129,7 @@ static inline void cpu_install_idmap(void)
 	local_flush_tlb_all();
 	cpu_set_idmap_tcr_t0sz();
 
-	cpu_switch_mm(idmap_pg_dir, &init_mm);
+	cpu_switch_mm(lm_alias(idmap_pg_dir), &init_mm);
 }
 
 /*
@@ -144,7 +144,7 @@ static inline void cpu_replace_ttbr1(pgd_t *pgd)
 
 	phys_addr_t pgd_phys = virt_to_phys(pgd);
 
-	replace_phys = (void *)virt_to_phys(idmap_cpu_replace_ttbr1);
+	replace_phys = (void *)__pa_symbol(idmap_cpu_replace_ttbr1);
 
 	cpu_install_idmap();
 	replace_phys(pgd_phys);
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index ecd7dc14330c..6c3848f50fcc 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -120,7 +120,7 @@ extern void __pgd_error(const char *file, int line, unsigned long val);
  * for zero-mapped memory areas etc..
  */
 extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
-#define ZERO_PAGE(vaddr)	virt_to_page(empty_zero_page)
+#define ZERO_PAGE(vaddr)	phys_to_page(__pa_symbol(empty_zero_page))
 
 #define pte_ERROR(pte)		__pte_error(__FILE__, __LINE__, pte_val(pte))
 
diff --git a/arch/arm64/kernel/acpi_parking_protocol.c b/arch/arm64/kernel/acpi_parking_protocol.c
index 4b1e5a7a98da..89c96bd1aab9 100644
--- a/arch/arm64/kernel/acpi_parking_protocol.c
+++ b/arch/arm64/kernel/acpi_parking_protocol.c
@@ -17,6 +17,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 #include <linux/acpi.h>
+#include <linux/mm.h>
 #include <linux/types.h>
 
 #include <asm/cpu_ops.h>
@@ -102,7 +103,7 @@ static int acpi_parking_protocol_cpu_boot(unsigned int cpu)
 	 * that read this address need to convert this address to the
 	 * Boot-Loader's endianness before jumping.
 	 */
-	writeq_relaxed(__pa(secondary_entry), &mailbox->entry_point);
+	writeq_relaxed(__pa_symbol(secondary_entry), &mailbox->entry_point);
 	writel_relaxed(cpu_entry->gic_cpu_id, &mailbox->cpu_id);
 
 	arch_send_wakeup_ipi_mask(cpumask_of(cpu));
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index f75000996e4c..3beb2b5cad6f 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -23,6 +23,7 @@
 #include <linux/sort.h>
 #include <linux/stop_machine.h>
 #include <linux/types.h>
+#include <linux/mm.h>
 #include <asm/cpu.h>
 #include <asm/cpufeature.h>
 #include <asm/cpu_ops.h>
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index 5f72243e5ba7..a3f8f8bbfc92 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -98,7 +98,7 @@ static void __kprobes *patch_map(void *addr, int fixmap)
 		page = vmalloc_to_page(addr);
 	else if (!module && (IS_ENABLED(CONFIG_DEBUG_RODATA)
 			       	|| IS_ENABLED(CONFIG_KERNEL_TEXT_RDONLY)))
-		page = virt_to_page(addr);
+		page = phys_to_page(__pa_symbol(addr));
 	else
 		return addr;
 
diff --git a/arch/arm64/kernel/io.c b/arch/arm64/kernel/io.c
index 471fb3cb8c5f..d43ea93dc68d 100644
--- a/arch/arm64/kernel/io.c
+++ b/arch/arm64/kernel/io.c
@@ -26,8 +26,7 @@
  */
 void __memcpy_fromio(void *to, const volatile void __iomem *from, size_t count)
 {
-	while (count && (!IS_ALIGNED((unsigned long)from, 8) ||
-			 !IS_ALIGNED((unsigned long)to, 8))) {
+	while (count && !IS_ALIGNED((unsigned long)from, 8)) {
 		*(u8 *)to = __raw_readb_no_log(from);
 		from++;
 		to++;
@@ -55,23 +54,22 @@ EXPORT_SYMBOL(__memcpy_fromio);
  */
 void __memcpy_toio(volatile void __iomem *to, const void *from, size_t count)
 {
-	while (count && (!IS_ALIGNED((unsigned long)to, 8) ||
-			 !IS_ALIGNED((unsigned long)from, 8))) {
-		__raw_writeb_no_log(*(volatile u8 *)from, to);
+	while (count && !IS_ALIGNED((unsigned long)to, 8)) {
+		__raw_writeb_no_log(*(u8 *)from, to);
 		from++;
 		to++;
 		count--;
 	}
 
 	while (count >= 8) {
-		__raw_writeq_no_log(*(volatile u64 *)from, to);
+		__raw_writeq_no_log(*(u64 *)from, to);
 		from += 8;
 		to += 8;
 		count -= 8;
 	}
 
 	while (count) {
-		__raw_writeb_no_log(*(volatile u8 *)from, to);
+		__raw_writeb_no_log(*(u8 *)from, to);
 		from++;
 		to++;
 		count--;
diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c
index b9e7c42cd8eb..9006af285c39 100644
--- a/arch/arm64/kernel/psci.c
+++ b/arch/arm64/kernel/psci.c
@@ -19,6 +19,7 @@
 #include <linux/of.h>
 #include <linux/smp.h>
 #include <linux/delay.h>
+#include <linux/mm.h>
 #include <linux/psci.h>
 
 #include <uapi/linux/psci.h>
@@ -46,7 +47,8 @@ static int __init cpu_psci_cpu_prepare(unsigned int cpu)
 
 static int cpu_psci_cpu_boot(unsigned int cpu)
 {
-	int err = psci_ops.cpu_on(cpu_logical_map(cpu), __pa(secondary_entry));
+	int err = psci_ops.cpu_on(cpu_logical_map(cpu),
+				  __pa_symbol(secondary_entry));
 	if (err)
 		pr_err("failed to boot CPU%d (%d)\n", cpu, err);
 
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index b8b40d95ebef..0b93365e8cf0 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -45,6 +45,7 @@
 #include <linux/efi.h>
 #include <linux/psci.h>
 #include <linux/dma-mapping.h>
+#include <linux/mm.h>
 
 #include <asm/acpi.h>
 #include <asm/fixmap.h>
@@ -212,10 +213,10 @@ static void __init request_standard_resources(void)
 	struct memblock_region *region;
 	struct resource *res;
 
-	kernel_code.start   = virt_to_phys(_text);
-	kernel_code.end     = virt_to_phys(__init_begin - 1);
-	kernel_data.start   = virt_to_phys(_sdata);
-	kernel_data.end     = virt_to_phys(_end - 1);
+	kernel_code.start   = __pa_symbol(_text);
+	kernel_code.end     = __pa_symbol(__init_begin - 1);
+	kernel_data.start   = __pa_symbol(_sdata);
+	kernel_data.end     = __pa_symbol(_end - 1);
 
 	for_each_memblock(memory, region) {
 		res = alloc_bootmem_low(sizeof(*res));
@@ -367,9 +368,9 @@ void __init setup_arch(char **cmdline_p)
 	 * thread.
 	 */
 #ifdef CONFIG_THREAD_INFO_IN_TASK
-	init_task.thread_info.ttbr0 = virt_to_phys(empty_zero_page);
+	init_task.thread_info.ttbr0 = __pa_symbol(empty_zero_page);
 #else
-	init_thread_info.ttbr0 = virt_to_phys(empty_zero_page);
+	init_thread_info.ttbr0 = __pa_symbol(empty_zero_page);
 #endif
 #endif
 
diff --git a/arch/arm64/kernel/smp_spin_table.c b/arch/arm64/kernel/smp_spin_table.c
index aef3605a8c47..2ccb883353d9 100644
--- a/arch/arm64/kernel/smp_spin_table.c
+++ b/arch/arm64/kernel/smp_spin_table.c
@@ -21,6 +21,7 @@
 #include <linux/of.h>
 #include <linux/smp.h>
 #include <linux/types.h>
+#include <linux/mm.h>
 
 #include <asm/cacheflush.h>
 #include <asm/cpu_ops.h>
@@ -96,7 +97,7 @@ static int smp_spin_table_cpu_prepare(unsigned int cpu)
 	 * boot-loader's endianess before jumping. This is mandated by
 	 * the boot protocol.
 	 */
-	writeq_relaxed(__pa(secondary_holding_pen), release_addr);
+	writeq_relaxed(__pa_symbol(secondary_holding_pen), release_addr);
 	__flush_dcache_area((__force void *)release_addr,
 			    sizeof(*release_addr));
 
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index 3b8acfae7797..7e9dd94452bb 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -114,6 +114,7 @@ static struct vm_special_mapping vdso_spec[2];
 static int __init vdso_init(void)
 {
 	int i;
+	unsigned long pfn;
 
 	if (memcmp(&vdso_start, "\177ELF", 4)) {
 		pr_err("vDSO is not a valid ELF object!\n");
@@ -131,11 +132,14 @@ static int __init vdso_init(void)
 		return -ENOMEM;
 
 	/* Grab the vDSO data page. */
-	vdso_pagelist[0] = virt_to_page(vdso_data);
+	vdso_pagelist[0] = phys_to_page(__pa_symbol(vdso_data));
+
 
 	/* Grab the vDSO code pages. */
+	pfn = sym_to_pfn(&vdso_start);
+
 	for (i = 0; i < vdso_pages; i++)
-		vdso_pagelist[i + 1] = virt_to_page(&vdso_start + i * PAGE_SIZE);
+		vdso_pagelist[i + 1] = pfn_to_page(pfn + i);
 
 	/* Populate the special mapping structures */
 	vdso_spec[0] = (struct vm_special_mapping) {
@@ -214,8 +218,8 @@ void update_vsyscall(struct timekeeper *tk)
 	if (!use_syscall) {
 		/* tkr_mono.cycle_last == tkr_raw.cycle_last */
 		vdso_data->cs_cycle_last	= tk->tkr_mono.cycle_last;
-		vdso_data->raw_time_sec		= tk->raw_time.tv_sec;
-		vdso_data->raw_time_nsec	= tk->raw_time.tv_nsec;
+		vdso_data->raw_time_sec         = tk->raw_sec;
+		vdso_data->raw_time_nsec        = tk->tkr_raw.xtime_nsec;
 		vdso_data->xtime_clock_sec	= tk->xtime_sec;
 		vdso_data->xtime_clock_nsec	= tk->tkr_mono.xtime_nsec;
 		/* tkr_raw.xtime_nsec == 0 */
diff --git a/arch/arm64/kernel/vdso/gettimeofday.S b/arch/arm64/kernel/vdso/gettimeofday.S
index e00b4671bd7c..c97ce91cf023 100644
--- a/arch/arm64/kernel/vdso/gettimeofday.S
+++ b/arch/arm64/kernel/vdso/gettimeofday.S
@@ -310,7 +310,7 @@ ENTRY(__kernel_clock_getres)
 	b.ne	4f
 	ldr	x2, 6f
 2:
-	cbz	w1, 3f
+	cbz	x1, 3f
 	stp	xzr, x2, [x1]
 
 3:	/* res == NULL. */
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 7fd74d55c68e..30f1a600a7c9 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -34,6 +34,7 @@
 #include <linux/dma-contiguous.h>
 #include <linux/efi.h>
 #include <linux/swiotlb.h>
+#include <linux/mm.h>
 
 #include <asm/boot.h>
 #include <asm/fixmap.h>
@@ -191,8 +192,8 @@ void __init arm64_memblock_init(void)
 	 * linear mapping. Take care not to clip the kernel which may be
 	 * high in memory.
 	 */
-	memblock_remove(max_t(u64, memstart_addr + linear_region_size, __pa(_end)),
-			ULLONG_MAX);
+	memblock_remove(max_t(u64, memstart_addr + linear_region_size,
+			__pa_symbol(_end)), ULLONG_MAX);
 	if (memstart_addr + linear_region_size < memblock_end_of_DRAM()) {
 		/* ensure that memstart_addr remains sufficiently aligned */
 		memstart_addr = round_up(memblock_end_of_DRAM() - linear_region_size,
@@ -212,7 +213,7 @@ void __init arm64_memblock_init(void)
 		 */
 		bootloader_memory_limit = memblock_end_of_DRAM();
 		memblock_enforce_memory_limit(memory_limit);
-		memblock_add(__pa(_text), (u64)(_end - _text));
+		memblock_add(__pa_symbol(_text), (u64)(_end - _text));
 	}
 
 	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
@@ -236,7 +237,7 @@ void __init arm64_memblock_init(void)
 	 * Register the kernel text, kernel data, initrd, and initial
 	 * pagetables with memblock.
 	 */
-	memblock_reserve(__pa(_text), _end - _text);
+	memblock_reserve(__pa_symbol(_text), _end - _text);
 #ifdef CONFIG_BLK_DEV_INITRD
 	if (initrd_start) {
 		memblock_reserve(initrd_start, initrd_end - initrd_start);
diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c
index 757009daa9ed..03588d136f93 100644
--- a/arch/arm64/mm/kasan_init.c
+++ b/arch/arm64/mm/kasan_init.c
@@ -15,6 +15,7 @@
 #include <linux/kernel.h>
 #include <linux/memblock.h>
 #include <linux/start_kernel.h>
+#include <linux/mm.h>
 
 #include <asm/mmu_context.h>
 #include <asm/kernel-pgtable.h>
@@ -26,6 +27,13 @@
 
 static pgd_t tmp_pg_dir[PTRS_PER_PGD] __initdata __aligned(PGD_SIZE);
 
+/*
+ * The p*d_populate functions call virt_to_phys implicitly so they can't be used
+ * directly on kernel symbols (bm_p*d). All the early functions are called too
+ * early to use lm_alias so __p*d_populate functions must be used to populate
+ * with the physical address from __pa_symbol.
+ */
+
 static void __init kasan_early_pte_populate(pmd_t *pmd, unsigned long addr,
 					unsigned long end)
 {
@@ -33,12 +41,13 @@ static void __init kasan_early_pte_populate(pmd_t *pmd, unsigned long addr,
 	unsigned long next;
 
 	if (pmd_none(*pmd))
-		pmd_populate_kernel(&init_mm, pmd, kasan_zero_pte);
+		__pmd_populate(pmd, __pa_symbol(kasan_zero_pte),
+			       PMD_TYPE_TABLE);
 
 	pte = pte_offset_kimg(pmd, addr);
 	do {
 		next = addr + PAGE_SIZE;
-		set_pte(pte, pfn_pte(virt_to_pfn(kasan_zero_page),
+		set_pte(pte, pfn_pte(sym_to_pfn(kasan_zero_page),
 					PAGE_KERNEL));
 	} while (pte++, addr = next, addr != end && pte_none(*pte));
 }
@@ -51,7 +60,8 @@ static void __init kasan_early_pmd_populate(pud_t *pud,
 	unsigned long next;
 
 	if (pud_none(*pud))
-		pud_populate(&init_mm, pud, kasan_zero_pmd);
+		__pud_populate(pud, __pa_symbol(kasan_zero_pmd),
+			       PMD_TYPE_TABLE);
 
 	pmd = pmd_offset_kimg(pud, addr);
 	do {
@@ -68,7 +78,8 @@ static void __init kasan_early_pud_populate(pgd_t *pgd,
 	unsigned long next;
 
 	if (pgd_none(*pgd))
-		pgd_populate(&init_mm, pgd, kasan_zero_pud);
+		__pgd_populate(pgd, __pa_symbol(kasan_zero_pud),
+			       PUD_TYPE_TABLE);
 
 	pud = pud_offset_kimg(pgd, addr);
 	do {
@@ -148,7 +159,7 @@ void __init kasan_init(void)
 	 */
 	memcpy(tmp_pg_dir, swapper_pg_dir, sizeof(tmp_pg_dir));
 	dsb(ishst);
-	cpu_replace_ttbr1(tmp_pg_dir);
+	cpu_replace_ttbr1(lm_alias(tmp_pg_dir));
 
 	clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END);
 
@@ -199,10 +210,10 @@ void __init kasan_init(void)
 	 */
 	for (i = 0; i < PTRS_PER_PTE; i++)
 		set_pte(&kasan_zero_pte[i],
-			pfn_pte(virt_to_pfn(kasan_zero_page), PAGE_KERNEL_RO));
+			pfn_pte(sym_to_pfn(kasan_zero_page), PAGE_KERNEL_RO));
 
 	memset(kasan_zero_page, 0, PAGE_SIZE);
-	cpu_replace_ttbr1(swapper_pg_dir);
+	cpu_replace_ttbr1(lm_alias(swapper_pg_dir));
 
 	/* At this point kasan is fully initialized. Enable error messages */
 	init_task.kasan_depth = 0;
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 8c063d39bc17..b1411e933bb3 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -31,6 +31,7 @@
 #include <linux/stop_machine.h>
 #include <linux/dma-contiguous.h>
 #include <linux/cma.h>
+#include <linux/mm.h>
 
 #include <asm/barrier.h>
 #include <asm/cputype.h>
@@ -391,8 +392,8 @@ static void create_mapping_late(phys_addr_t phys, unsigned long virt,
 
 static void __init __map_memblock(pgd_t *pgd, phys_addr_t start, phys_addr_t end)
 {
-	unsigned long kernel_start = __pa(_text);
-	unsigned long kernel_end = __pa(__init_begin);
+	unsigned long kernel_start = __pa_symbol(_text);
+	unsigned long kernel_end = __pa_symbol(__init_begin);
 
 	/*
 	 * Take care not to create a writable alias for the
@@ -456,14 +457,15 @@ void mark_rodata_ro(void)
 	unsigned long section_size;
 
 	section_size = (unsigned long)_etext - (unsigned long)_text;
-	create_mapping_late(__pa(_text), (unsigned long)_text,
+	create_mapping_late(__pa_symbol(_text), (unsigned long)_text,
 			    section_size, PAGE_KERNEL_ROX);
 	/*
 	 * mark .rodata as read only. Use __init_begin rather than __end_rodata
 	 * to cover NOTES and EXCEPTION_TABLE.
 	 */
 	section_size = (unsigned long)__init_begin - (unsigned long)__start_rodata;
-	create_mapping_late(__pa(__start_rodata), (unsigned long)__start_rodata,
+	create_mapping_late(__pa_symbol(__start_rodata),
+			    (unsigned long)__start_rodata,
 			    section_size, PAGE_KERNEL_RO);
 }
 
@@ -480,7 +482,7 @@ void fixup_init(void)
 static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end,
 				      pgprot_t prot, struct vm_struct *vma)
 {
-	phys_addr_t pa_start = __pa(va_start);
+	phys_addr_t pa_start = __pa_symbol(va_start);
 	unsigned long size = va_end - va_start;
 
 	BUG_ON(!PAGE_ALIGNED(pa_start));
@@ -528,7 +530,7 @@ static void __init map_kernel(pgd_t *pgd)
 		 */
 		BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES));
 		set_pud(pud_set_fixmap_offset(pgd, FIXADDR_START),
-			__pud(__pa(bm_pmd) | PUD_TYPE_TABLE));
+			__pud(__pa_symbol(bm_pmd) | PUD_TYPE_TABLE));
 		pud_clear_fixmap();
 	} else {
 		BUG();
@@ -590,7 +592,7 @@ void __init paging_init(void)
 	 */
 	cpu_replace_ttbr1(__va(pgd_phys));
 	memcpy(swapper_pg_dir, pgd, PAGE_SIZE);
-	cpu_replace_ttbr1(swapper_pg_dir);
+	cpu_replace_ttbr1(lm_alias(swapper_pg_dir));
 
 	pgd_clear_fixmap();
 	memblock_free(pgd_phys, PAGE_SIZE);
@@ -599,7 +601,7 @@ void __init paging_init(void)
 	 * We only reuse the PGD from the swapper_pg_dir, not the pud + pmd
 	 * allocated with it.
 	 */
-	memblock_free(__pa(swapper_pg_dir) + PAGE_SIZE,
+	memblock_free(__pa_symbol(swapper_pg_dir) + PAGE_SIZE,
 		      SWAPPER_DIR_SIZE - PAGE_SIZE);
 
 	bootmem_init();
@@ -1141,6 +1143,12 @@ static inline pte_t * fixmap_pte(unsigned long addr)
 	return &bm_pte[pte_index(addr)];
 }
 
+/*
+ * The p*d_populate functions call virt_to_phys implicitly so they can't be used
+ * directly on kernel symbols (bm_p*d). This function is called too early to use
+ * lm_alias so __p*d_populate functions must be used to populate with the
+ * physical address from __pa_symbol.
+ */
 void __init early_fixmap_init(void)
 {
 	pgd_t *pgd;
@@ -1150,7 +1158,7 @@ void __init early_fixmap_init(void)
 
 	pgd = pgd_offset_k(addr);
 	if (CONFIG_PGTABLE_LEVELS > 3 &&
-	    !(pgd_none(*pgd) || pgd_page_paddr(*pgd) == __pa(bm_pud))) {
+	    !(pgd_none(*pgd) || pgd_page_paddr(*pgd) == __pa_symbol(bm_pud))) {
 		/*
 		 * We only end up here if the kernel mapping and the fixmap
 		 * share the top level pgd entry, which should only happen on
@@ -1159,12 +1167,15 @@ void __init early_fixmap_init(void)
 		BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES));
 		pud = pud_offset_kimg(pgd, addr);
 	} else {
-		pgd_populate(&init_mm, pgd, bm_pud);
+		if (pgd_none(*pgd))
+			__pgd_populate(pgd, __pa_symbol(bm_pud),
+				       PUD_TYPE_TABLE);
 		pud = fixmap_pud(addr);
 	}
-	pud_populate(&init_mm, pud, bm_pmd);
+	if (pud_none(*pud))
+		__pud_populate(pud, __pa_symbol(bm_pmd), PMD_TYPE_TABLE);
 	pmd = fixmap_pmd(addr);
-	pmd_populate_kernel(&init_mm, pmd, bm_pte);
+	__pmd_populate(pmd, __pa_symbol(bm_pte), PMD_TYPE_TABLE);
 
 	/*
 	 * The boot-ioremap range spans multiple pmds, for which
diff --git a/arch/mips/ar7/platform.c b/arch/mips/ar7/platform.c
index 58fca9ad5fcc..3446b6fb3acb 100644
--- a/arch/mips/ar7/platform.c
+++ b/arch/mips/ar7/platform.c
@@ -576,6 +576,7 @@ static int __init ar7_register_uarts(void)
 	uart_port.type		= PORT_AR7;
 	uart_port.uartclk	= clk_get_rate(bus_clk) / 2;
 	uart_port.iotype	= UPIO_MEM32;
+	uart_port.flags		= UPF_FIXED_TYPE;
 	uart_port.regshift	= 2;
 
 	uart_port.line		= 0;
@@ -654,6 +655,10 @@ static int __init ar7_register_devices(void)
 	u32 val;
 	int res;
 
+	res = ar7_gpio_init();
+	if (res)
+		pr_warn("unable to register gpios: %d\n", res);
+
 	res = ar7_register_uarts();
 	if (res)
 		pr_err("unable to setup uart(s): %d\n", res);
diff --git a/arch/mips/ar7/prom.c b/arch/mips/ar7/prom.c
index a23adc49d50f..36aabee9cba4 100644
--- a/arch/mips/ar7/prom.c
+++ b/arch/mips/ar7/prom.c
@@ -246,8 +246,6 @@ void __init prom_init(void)
 	ar7_init_cmdline(fw_arg0, (char **)fw_arg1);
 	ar7_init_env((struct env_var *)fw_arg2);
 	console_config();
-
-	ar7_gpio_init();
 }
 
 #define PORT(offset) (KSEG1ADDR(AR7_REGS_UART0 + (offset * 4)))
diff --git a/arch/mips/bcm47xx/leds.c b/arch/mips/bcm47xx/leds.c
index d20ae63eb3c2..46abe9e4e0e0 100644
--- a/arch/mips/bcm47xx/leds.c
+++ b/arch/mips/bcm47xx/leds.c
@@ -330,7 +330,7 @@ bcm47xx_leds_linksys_wrt54g3gv2[] __initconst = {
 /* Verified on: WRT54GS V1.0 */
 static const struct gpio_led
 bcm47xx_leds_linksys_wrt54g_type_0101[] __initconst = {
-	BCM47XX_GPIO_LED(0, "green", "wlan", 0, LEDS_GPIO_DEFSTATE_OFF),
+	BCM47XX_GPIO_LED(0, "green", "wlan", 1, LEDS_GPIO_DEFSTATE_OFF),
 	BCM47XX_GPIO_LED(1, "green", "power", 0, LEDS_GPIO_DEFSTATE_ON),
 	BCM47XX_GPIO_LED(7, "green", "dmz", 1, LEDS_GPIO_DEFSTATE_OFF),
 };
diff --git a/arch/mips/include/asm/asm.h b/arch/mips/include/asm/asm.h
index 7c26b28bf252..859cf7048347 100644
--- a/arch/mips/include/asm/asm.h
+++ b/arch/mips/include/asm/asm.h
@@ -54,7 +54,8 @@
 		.align	2;				\
 		.type	symbol, @function;		\
 		.ent	symbol, 0;			\
-symbol:		.frame	sp, 0, ra
+symbol:		.frame	sp, 0, ra;			\
+		.insn
 
 /*
  * NESTED - declare nested routine entry point
@@ -63,8 +64,9 @@ symbol:		.frame	sp, 0, ra
 		.globl	symbol;				\
 		.align	2;				\
 		.type	symbol, @function;		\
-		.ent	symbol, 0;			 \
-symbol:		.frame	sp, framesize, rpc
+		.ent	symbol, 0;			\
+symbol:		.frame	sp, framesize, rpc;		\
+		.insn
 
 /*
  * END - mark end of function
@@ -86,7 +88,7 @@ symbol:
 #define FEXPORT(symbol)					\
 		.globl	symbol;				\
 		.type	symbol, @function;		\
-symbol:
+symbol:		.insn
 
 /*
  * ABS - export absolute symbol
diff --git a/arch/mips/include/asm/mips-cm.h b/arch/mips/include/asm/mips-cm.h
index 6516e9da5133..b836ddec82b7 100644
--- a/arch/mips/include/asm/mips-cm.h
+++ b/arch/mips/include/asm/mips-cm.h
@@ -238,8 +238,8 @@ BUILD_CM_Cx_R_(tcid_8_priority,	0x80)
 #define CM_GCR_BASE_GCRBASE_MSK			(_ULCAST_(0x1ffff) << 15)
 #define CM_GCR_BASE_CMDEFTGT_SHF		0
 #define CM_GCR_BASE_CMDEFTGT_MSK		(_ULCAST_(0x3) << 0)
-#define  CM_GCR_BASE_CMDEFTGT_DISABLED		0
-#define  CM_GCR_BASE_CMDEFTGT_MEM		1
+#define  CM_GCR_BASE_CMDEFTGT_MEM		0
+#define  CM_GCR_BASE_CMDEFTGT_RESERVED		1
 #define  CM_GCR_BASE_CMDEFTGT_IOCU0		2
 #define  CM_GCR_BASE_CMDEFTGT_IOCU1		3
 
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index 477ba026c3e5..163b3449a8de 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -49,9 +49,7 @@
 #ifdef CONFIG_HOTPLUG_CPU
 void arch_cpu_idle_dead(void)
 {
-	/* What the heck is this check doing ? */
-	if (!cpumask_test_cpu(smp_processor_id(), &cpu_callin_map))
-		play_dead();
+	play_dead();
 }
 #endif
 
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index 24c115a0721a..a3f38e6b7ea1 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -650,6 +650,19 @@ static const struct user_regset_view user_mips64_view = {
 	.n		= ARRAY_SIZE(mips64_regsets),
 };
 
+#ifdef CONFIG_MIPS32_N32
+
+static const struct user_regset_view user_mipsn32_view = {
+	.name		= "mipsn32",
+	.e_flags	= EF_MIPS_ABI2,
+	.e_machine	= ELF_ARCH,
+	.ei_osabi	= ELF_OSABI,
+	.regsets	= mips64_regsets,
+	.n		= ARRAY_SIZE(mips64_regsets),
+};
+
+#endif /* CONFIG_MIPS32_N32 */
+
 #endif /* CONFIG_64BIT */
 
 const struct user_regset_view *task_user_regset_view(struct task_struct *task)
@@ -661,6 +674,10 @@ const struct user_regset_view *task_user_regset_view(struct task_struct *task)
 	if (test_tsk_thread_flag(task, TIF_32BIT_REGS))
 		return &user_mips_view;
 #endif
+#ifdef CONFIG_MIPS32_N32
+	if (test_tsk_thread_flag(task, TIF_32BIT_ADDR))
+		return &user_mipsn32_view;
+#endif
 	return &user_mips64_view;
 #endif
 }
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 8acae316f26b..4f9f1ae49213 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -152,6 +152,35 @@ void __init detect_memory_region(phys_addr_t start, phys_addr_t sz_min, phys_add
 	add_memory_region(start, size, BOOT_MEM_RAM);
 }
 
+bool __init memory_region_available(phys_addr_t start, phys_addr_t size)
+{
+	int i;
+	bool in_ram = false, free = true;
+
+	for (i = 0; i < boot_mem_map.nr_map; i++) {
+		phys_addr_t start_, end_;
+
+		start_ = boot_mem_map.map[i].addr;
+		end_ = boot_mem_map.map[i].addr + boot_mem_map.map[i].size;
+
+		switch (boot_mem_map.map[i].type) {
+		case BOOT_MEM_RAM:
+			if (start >= start_ && start + size <= end_)
+				in_ram = true;
+			break;
+		case BOOT_MEM_RESERVED:
+			if ((start >= start_ && start < end_) ||
+			    (start < start_ && start + size >= start_))
+				free = false;
+			break;
+		default:
+			continue;
+		}
+	}
+
+	return in_ram && free;
+}
+
 static void __init print_memory_map(void)
 {
 	int i;
@@ -300,11 +329,19 @@ static void __init bootmem_init(void)
 
 #else  /* !CONFIG_SGI_IP27 */
 
+static unsigned long __init bootmap_bytes(unsigned long pages)
+{
+	unsigned long bytes = DIV_ROUND_UP(pages, 8);
+
+	return ALIGN(bytes, sizeof(long));
+}
+
 static void __init bootmem_init(void)
 {
 	unsigned long reserved_end;
 	unsigned long mapstart = ~0UL;
 	unsigned long bootmap_size;
+	bool bootmap_valid = false;
 	int i;
 
 	/*
@@ -385,11 +422,42 @@ static void __init bootmem_init(void)
 #endif
 
 	/*
-	 * Initialize the boot-time allocator with low memory only.
+	 * check that mapstart doesn't overlap with any of
+	 * memory regions that have been reserved through eg. DTB
 	 */
-	bootmap_size = init_bootmem_node(NODE_DATA(0), mapstart,
-					 min_low_pfn, max_low_pfn);
+	bootmap_size = bootmap_bytes(max_low_pfn - min_low_pfn);
+
+	bootmap_valid = memory_region_available(PFN_PHYS(mapstart),
+						bootmap_size);
+	for (i = 0; i < boot_mem_map.nr_map && !bootmap_valid; i++) {
+		unsigned long mapstart_addr;
+
+		switch (boot_mem_map.map[i].type) {
+		case BOOT_MEM_RESERVED:
+			mapstart_addr = PFN_ALIGN(boot_mem_map.map[i].addr +
+						boot_mem_map.map[i].size);
+			if (PHYS_PFN(mapstart_addr) < mapstart)
+				break;
+
+			bootmap_valid = memory_region_available(mapstart_addr,
+								bootmap_size);
+			if (bootmap_valid)
+				mapstart = PHYS_PFN(mapstart_addr);
+			break;
+		default:
+			break;
+		}
+	}
 
+	if (!bootmap_valid)
+		panic("No memory area to place a bootmap bitmap");
+
+	/*
+	 * Initialize the boot-time allocator with low memory only.
+	 */
+	if (bootmap_size != init_bootmem_node(NODE_DATA(0), mapstart,
+					 min_low_pfn, max_low_pfn))
+		panic("Unexpected memory size required for bootmap");
 
 	for (i = 0; i < boot_mem_map.nr_map; i++) {
 		unsigned long start, end;
@@ -438,6 +506,10 @@ static void __init bootmem_init(void)
 			continue;
 		default:
 			/* Not usable memory */
+			if (start > min_low_pfn && end < max_low_pfn)
+				reserve_bootmem(boot_mem_map.map[i].addr,
+						boot_mem_map.map[i].size,
+						BOOTMEM_DEFAULT);
 			continue;
 		}
 
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index 7fef02a9eb85..4af08c197177 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -64,6 +64,9 @@ EXPORT_SYMBOL(cpu_sibling_map);
 cpumask_t cpu_core_map[NR_CPUS] __read_mostly;
 EXPORT_SYMBOL(cpu_core_map);
 
+static DECLARE_COMPLETION(cpu_starting);
+static DECLARE_COMPLETION(cpu_running);
+
 /*
  * A logcal cpu mask containing only one VPE per core to
  * reduce the number of IPIs on large MT systems.
@@ -174,9 +177,12 @@ asmlinkage void start_secondary(void)
 	cpumask_set_cpu(cpu, &cpu_coherent_mask);
 	notify_cpu_starting(cpu);
 
-	cpumask_set_cpu(cpu, &cpu_callin_map);
+	/* Notify boot CPU that we're starting & ready to sync counters */
+	complete(&cpu_starting);
+
 	synchronise_count_slave(cpu);
 
+	/* The CPU is running and counters synchronised, now mark it online */
 	set_cpu_online(cpu, true);
 
 	set_cpu_sibling_map(cpu);
@@ -185,6 +191,12 @@ asmlinkage void start_secondary(void)
 	calculate_cpu_foreign_map();
 
 	/*
+	 * Notify boot CPU that we're up & online and it can safely return
+	 * from __cpu_up
+	 */
+	complete(&cpu_running);
+
+	/*
 	 * irq will be enabled in ->smp_finish(), enabling it too early
 	 * is dangerous.
 	 */
@@ -242,22 +254,23 @@ void smp_prepare_boot_cpu(void)
 {
 	set_cpu_possible(0, true);
 	set_cpu_online(0, true);
-	cpumask_set_cpu(0, &cpu_callin_map);
 }
 
 int __cpu_up(unsigned int cpu, struct task_struct *tidle)
 {
 	mp_ops->boot_secondary(cpu, tidle);
 
-	/*
-	 * Trust is futile.  We should really have timeouts ...
-	 */
-	while (!cpumask_test_cpu(cpu, &cpu_callin_map)) {
-		udelay(100);
-		schedule();
+	/* Wait for CPU to start and be ready to sync counters */
+	if (!wait_for_completion_timeout(&cpu_starting,
+					 msecs_to_jiffies(1000))) {
+		pr_crit("CPU%u: failed to start\n", cpu);
+		return -EIO;
 	}
 
 	synchronise_count_master(cpu);
+
+	/* Wait for CPU to finish startup & mark itself online before return */
+	wait_for_completion(&cpu_running);
 	return 0;
 }
 
diff --git a/arch/mips/mm/uasm-micromips.c b/arch/mips/mm/uasm-micromips.c
index d78178daea4b..e2fe48dd67b5 100644
--- a/arch/mips/mm/uasm-micromips.c
+++ b/arch/mips/mm/uasm-micromips.c
@@ -75,7 +75,7 @@ static struct insn insn_table_MM[] = {
 	{ insn_jr, M(mm_pool32a_op, 0, 0, 0, mm_jalr_op, mm_pool32axf_op), RS },
 	{ insn_lb, M(mm_lb32_op, 0, 0, 0, 0, 0), RT | RS | SIMM },
 	{ insn_ld, 0, 0 },
-	{ insn_lh, M(mm_lh32_op, 0, 0, 0, 0, 0), RS | RS | SIMM },
+	{ insn_lh, M(mm_lh32_op, 0, 0, 0, 0, 0), RT | RS | SIMM },
 	{ insn_ll, M(mm_pool32c_op, 0, 0, (mm_ll_func << 1), 0, 0), RS | RT | SIMM },
 	{ insn_lld, 0, 0 },
 	{ insn_lui, M(mm_pool32i_op, mm_lui_op, 0, 0, 0, 0), RS | SIMM },
diff --git a/arch/mips/netlogic/common/irq.c b/arch/mips/netlogic/common/irq.c
index 3660dc67d544..f4961bc9a61d 100644
--- a/arch/mips/netlogic/common/irq.c
+++ b/arch/mips/netlogic/common/irq.c
@@ -275,7 +275,7 @@ asmlinkage void plat_irq_dispatch(void)
 	do_IRQ(nlm_irq_to_xirq(node, i));
 }
 
-#ifdef CONFIG_OF
+#ifdef CONFIG_CPU_XLP
 static const struct irq_domain_ops xlp_pic_irq_domain_ops = {
 	.xlate = irq_domain_xlate_onetwocell,
 };
@@ -348,7 +348,7 @@ void __init arch_init_irq(void)
 #if defined(CONFIG_CPU_XLR)
 	nlm_setup_fmn_irq();
 #endif
-#if defined(CONFIG_OF)
+#ifdef CONFIG_CPU_XLP
 	of_irq_init(xlp_pic_irq_ids);
 #endif
 }
diff --git a/arch/mips/ralink/mt7620.c b/arch/mips/ralink/mt7620.c
index 48d6349fd9d7..c5f45fc96c74 100644
--- a/arch/mips/ralink/mt7620.c
+++ b/arch/mips/ralink/mt7620.c
@@ -141,8 +141,8 @@ static struct rt2880_pmx_func i2c_grp_mt7628[] = {
 	FUNC("i2c", 0, 4, 2),
 };
 
-static struct rt2880_pmx_func refclk_grp_mt7628[] = { FUNC("reclk", 0, 36, 1) };
-static struct rt2880_pmx_func perst_grp_mt7628[] = { FUNC("perst", 0, 37, 1) };
+static struct rt2880_pmx_func refclk_grp_mt7628[] = { FUNC("refclk", 0, 37, 1) };
+static struct rt2880_pmx_func perst_grp_mt7628[] = { FUNC("perst", 0, 36, 1) };
 static struct rt2880_pmx_func wdt_grp_mt7628[] = { FUNC("wdt", 0, 38, 1) };
 static struct rt2880_pmx_func spi_grp_mt7628[] = { FUNC("spi", 0, 7, 4) };
 
diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S
index c6b855f7892c..9f22195b90ed 100644
--- a/arch/parisc/kernel/syscall.S
+++ b/arch/parisc/kernel/syscall.S
@@ -688,15 +688,15 @@ cas_action:
 	/* ELF32 Process entry path */
 lws_compare_and_swap_2:
 #ifdef CONFIG_64BIT
-	/* Clip the input registers */
+	/* Clip the input registers. We don't need to clip %r23 as we
+	   only use it for word operations */
 	depdi	0, 31, 32, %r26
 	depdi	0, 31, 32, %r25
 	depdi	0, 31, 32, %r24
-	depdi	0, 31, 32, %r23
 #endif
 
 	/* Check the validity of the size pointer */
-	subi,>>= 4, %r23, %r0
+	subi,>>= 3, %r23, %r0
 	b,n	lws_exit_nosys
 
 	/* Jump to the functions which will load the old and new values into
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index ec7b8f1e4822..c628f47a9052 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -1083,11 +1083,6 @@ source "arch/powerpc/Kconfig.debug"
 
 source "security/Kconfig"
 
-config KEYS_COMPAT
-	bool
-	depends on COMPAT && KEYS
-	default y
-
 source "crypto/Kconfig"
 
 config PPC_LIB_RHEAP
diff --git a/arch/powerpc/boot/dts/fsl/kmcoge4.dts b/arch/powerpc/boot/dts/fsl/kmcoge4.dts
index 6858ec9ef295..1a953d9edf1e 100644
--- a/arch/powerpc/boot/dts/fsl/kmcoge4.dts
+++ b/arch/powerpc/boot/dts/fsl/kmcoge4.dts
@@ -83,6 +83,10 @@
 			};
 		};
 
+		sdhc@114000 {
+			status = "disabled";
+		};
+
 		i2c@119000 {
 			status = "disabled";
 		};
diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
index cf8c7e4e0b21..984a54c85952 100644
--- a/arch/powerpc/kernel/signal.c
+++ b/arch/powerpc/kernel/signal.c
@@ -102,7 +102,7 @@ static void check_syscall_restart(struct pt_regs *regs, struct k_sigaction *ka,
 static void do_signal(struct pt_regs *regs)
 {
 	sigset_t *oldset = sigmask_to_save();
-	struct ksignal ksig;
+	struct ksignal ksig = { .sig = 0 };
 	int ret;
 	int is32 = is_32bit_task();
 
diff --git a/arch/powerpc/kvm/book3s_hv_rm_xics.c b/arch/powerpc/kvm/book3s_hv_rm_xics.c
index 24f58076d49e..1d2bc84338bf 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_xics.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_xics.c
@@ -280,6 +280,7 @@ static void icp_rm_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp,
 		 */
 		if (reject && reject != XICS_IPI) {
 			arch_spin_unlock(&ics->lock);
+			icp->n_reject++;
 			new_irq = reject;
 			goto again;
 		}
@@ -611,10 +612,8 @@ int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr)
 	state = &ics->irq_state[src];
 
 	/* Still asserted, resend it */
-	if (state->asserted) {
-		icp->n_reject++;
+	if (state->asserted)
 		icp_rm_deliver_irq(xics, icp, irq);
-	}
 
 	if (!hlist_empty(&vcpu->kvm->irq_ack_notifier_list)) {
 		icp->rm_action |= XICS_RM_NOTIFY_EOI;
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 60530fd93d6d..9510ddfff59b 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -347,9 +347,6 @@ config COMPAT
 config SYSVIPC_COMPAT
 	def_bool y if COMPAT && SYSVIPC
 
-config KEYS_COMPAT
-	def_bool y if COMPAT && KEYS
-
 config SMP
 	def_bool y
 	prompt "Symmetric multi-processing support"
diff --git a/arch/s390/include/asm/asm-prototypes.h b/arch/s390/include/asm/asm-prototypes.h
new file mode 100644
index 000000000000..2c3413b0ca52
--- /dev/null
+++ b/arch/s390/include/asm/asm-prototypes.h
@@ -0,0 +1,8 @@
+#ifndef _ASM_S390_PROTOTYPES_H
+
+#include <linux/kvm_host.h>
+#include <linux/ftrace.h>
+#include <asm/fpu/api.h>
+#include <asm-generic/asm-prototypes.h>
+
+#endif /* _ASM_S390_PROTOTYPES_H */
diff --git a/arch/s390/include/asm/switch_to.h b/arch/s390/include/asm/switch_to.h
index 12d45f0cfdd9..dde6b52359c5 100644
--- a/arch/s390/include/asm/switch_to.h
+++ b/arch/s390/include/asm/switch_to.h
@@ -34,8 +34,8 @@ static inline void restore_access_regs(unsigned int *acrs)
 		save_access_regs(&prev->thread.acrs[0]);		\
 		save_ri_cb(prev->thread.ri_cb);				\
 	}								\
+	update_cr_regs(next);						\
 	if (next->mm) {							\
-		update_cr_regs(next);					\
 		set_cpu_flag(CIF_FPU);					\
 		restore_access_regs(&next->thread.acrs[0]);		\
 		restore_ri_cb(next->thread.ri_cb, prev->thread.ri_cb);	\
diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c
index 6e72961608f0..07477ba392b7 100644
--- a/arch/s390/kernel/dis.c
+++ b/arch/s390/kernel/dis.c
@@ -1549,6 +1549,7 @@ static struct s390_insn opcode_e7[] = {
 	{ "vfsq", 0xce, INSTR_VRR_VV000MM },
 	{ "vfs", 0xe2, INSTR_VRR_VVV00MM },
 	{ "vftci", 0x4a, INSTR_VRI_VVIMM },
+	{ "", 0, INSTR_INVALID }
 };
 
 static struct s390_insn opcode_eb[] = {
@@ -1961,7 +1962,7 @@ void show_code(struct pt_regs *regs)
 {
 	char *mode = user_mode(regs) ? "User" : "Krnl";
 	unsigned char code[64];
-	char buffer[64], *ptr;
+	char buffer[128], *ptr;
 	mm_segment_t old_fs;
 	unsigned long addr;
 	int start, end, opsize, hops, i;
@@ -2024,7 +2025,7 @@ void show_code(struct pt_regs *regs)
 		start += opsize;
 		printk(buffer);
 		ptr = buffer;
-		ptr += sprintf(ptr, "\n          ");
+		ptr += sprintf(ptr, "\n\t  ");
 		hops++;
 	}
 	printk("\n");
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index 3c31609df959..ee7b8e7ca4f8 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -325,8 +325,10 @@ static __init void detect_machine_facilities(void)
 		S390_lowcore.machine_flags |= MACHINE_FLAG_IDTE;
 	if (test_facility(40))
 		S390_lowcore.machine_flags |= MACHINE_FLAG_LPP;
-	if (test_facility(50) && test_facility(73))
+	if (test_facility(50) && test_facility(73)) {
 		S390_lowcore.machine_flags |= MACHINE_FLAG_TE;
+		__ctl_set_bit(0, 55);
+	}
 	if (test_facility(51))
 		S390_lowcore.machine_flags |= MACHINE_FLAG_TLB_LC;
 	if (test_facility(129)) {
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 114ee8b96f17..efa035a31b98 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -137,6 +137,7 @@ int copy_thread(unsigned long clone_flags, unsigned long new_stackp,
 	memset(&p->thread.per_user, 0, sizeof(p->thread.per_user));
 	memset(&p->thread.per_event, 0, sizeof(p->thread.per_event));
 	clear_tsk_thread_flag(p, TIF_SINGLE_STEP);
+	p->thread.per_flags = 0;
 	/* Initialize per thread user and system timer values */
 	ti = task_thread_info(p);
 	ti->user_timer = 0;
diff --git a/arch/s390/kernel/runtime_instr.c b/arch/s390/kernel/runtime_instr.c
index fffa0e5462af..70cdb03d4acd 100644
--- a/arch/s390/kernel/runtime_instr.c
+++ b/arch/s390/kernel/runtime_instr.c
@@ -47,11 +47,13 @@ void exit_thread_runtime_instr(void)
 {
 	struct task_struct *task = current;
 
+	preempt_disable();
 	if (!task->thread.ri_cb)
 		return;
 	disable_runtime_instr();
 	kfree(task->thread.ri_cb);
 	task->thread.ri_cb = NULL;
+	preempt_enable();
 }
 
 SYSCALL_DEFINE1(s390_runtime_instr, int, command)
@@ -62,9 +64,7 @@ SYSCALL_DEFINE1(s390_runtime_instr, int, command)
 		return -EOPNOTSUPP;
 
 	if (command == S390_RUNTIME_INSTR_STOP) {
-		preempt_disable();
 		exit_thread_runtime_instr();
-		preempt_enable();
 		return 0;
 	}
 
diff --git a/arch/sh/kernel/cpu/sh3/setup-sh770x.c b/arch/sh/kernel/cpu/sh3/setup-sh770x.c
index 538c10db3537..8dc315b212c2 100644
--- a/arch/sh/kernel/cpu/sh3/setup-sh770x.c
+++ b/arch/sh/kernel/cpu/sh3/setup-sh770x.c
@@ -165,7 +165,6 @@ static struct plat_sci_port scif2_platform_data = {
 	.scscr		= SCSCR_TE | SCSCR_RE,
 	.type		= PORT_IRDA,
 	.ops		= &sh770x_sci_port_ops,
-	.regshift	= 1,
 };
 
 static struct resource scif2_resources[] = {
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 894bcaed002e..1cf6a15102d8 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -550,9 +550,6 @@ config SYSVIPC_COMPAT
 	depends on COMPAT && SYSVIPC
 	default y
 
-config KEYS_COMPAT
-	def_bool y if COMPAT && KEYS
-
 endmenu
 
 source "net/Kconfig"
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 8dc3b07ee3cc..f37e01e6b7f2 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2657,10 +2657,6 @@ config COMPAT_FOR_U64_ALIGNMENT
 config SYSVIPC_COMPAT
 	def_bool y
 	depends on SYSVIPC
-
-config KEYS_COMPAT
-	def_bool y
-	depends on KEYS
 endif
 
 endmenu
diff --git a/arch/x86/crypto/sha-mb/sha1_mb_mgr_flush_avx2.S b/arch/x86/crypto/sha-mb/sha1_mb_mgr_flush_avx2.S
index 85c4e1cf7172..e1693457c178 100644
--- a/arch/x86/crypto/sha-mb/sha1_mb_mgr_flush_avx2.S
+++ b/arch/x86/crypto/sha-mb/sha1_mb_mgr_flush_avx2.S
@@ -174,8 +174,8 @@ LABEL skip_ %I
 .endr
 
 	# Find min length
-	vmovdqa _lens+0*16(state), %xmm0
-	vmovdqa _lens+1*16(state), %xmm1
+	vmovdqu _lens+0*16(state), %xmm0
+	vmovdqu _lens+1*16(state), %xmm1
 
 	vpminud %xmm1, %xmm0, %xmm2     # xmm2 has {D,C,B,A}
 	vpalignr $8, %xmm2, %xmm3, %xmm3   # xmm3 has {x,x,D,C}
@@ -195,8 +195,8 @@ LABEL skip_ %I
 	vpsubd  %xmm2, %xmm0, %xmm0
 	vpsubd  %xmm2, %xmm1, %xmm1
 
-	vmovdqa %xmm0, _lens+0*16(state)
-	vmovdqa %xmm1, _lens+1*16(state)
+	vmovdqu %xmm0, _lens+0*16(state)
+	vmovdqu %xmm1, _lens+1*16(state)
 
 	# "state" and "args" are the same address, arg1
 	# len is arg2
@@ -260,8 +260,8 @@ ENTRY(sha1_mb_mgr_get_comp_job_avx2)
 	jc      .return_null
 
 	# Find min length
-	vmovdqa _lens(state), %xmm0
-	vmovdqa _lens+1*16(state), %xmm1
+	vmovdqu _lens(state), %xmm0
+	vmovdqu _lens+1*16(state), %xmm1
 
 	vpminud %xmm1, %xmm0, %xmm2        # xmm2 has {D,C,B,A}
 	vpalignr $8, %xmm2, %xmm3, %xmm3   # xmm3 has {x,x,D,C}
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 08b1f2f6ea50..c9e6eab2075b 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -3,6 +3,7 @@
 
 #include <asm/fpu/api.h>
 #include <asm/pgtable.h>
+#include <asm/tlb.h>
 
 /*
  * We map the EFI regions needed for runtime services non-contiguously,
@@ -66,6 +67,17 @@ extern u64 asmlinkage efi_call(void *fp, ...);
 
 #define efi_call_phys(f, args...)		efi_call((f), args)
 
+/*
+ * Scratch space used for switching the pagetable in the EFI stub
+ */
+struct efi_scratch {
+	u64	r15;
+	u64	prev_cr3;
+	pgd_t	*efi_pgt;
+	bool	use_pgd;
+	u64	phys_stack;
+} __packed;
+
 #define efi_call_virt(f, ...)						\
 ({									\
 	efi_status_t __s;						\
@@ -73,7 +85,20 @@ extern u64 asmlinkage efi_call(void *fp, ...);
 	efi_sync_low_kernel_mappings();					\
 	preempt_disable();						\
 	__kernel_fpu_begin();						\
+									\
+	if (efi_scratch.use_pgd) {					\
+		efi_scratch.prev_cr3 = read_cr3();			\
+		write_cr3((unsigned long)efi_scratch.efi_pgt);		\
+		__flush_tlb_all();					\
+	}								\
+									\
 	__s = efi_call((void *)efi.systab->runtime->f, __VA_ARGS__);	\
+									\
+	if (efi_scratch.use_pgd) {					\
+		write_cr3(efi_scratch.prev_cr3);			\
+		__flush_tlb_all();					\
+	}								\
+									\
 	__kernel_fpu_end();						\
 	preempt_enable();						\
 	__s;								\
@@ -113,6 +138,7 @@ extern void __init efi_memory_uc(u64 addr, unsigned long size);
 extern void __init efi_map_region(efi_memory_desc_t *md);
 extern void __init efi_map_region_fixed(efi_memory_desc_t *md);
 extern void efi_sync_low_kernel_mappings(void);
+extern int __init efi_alloc_page_tables(void);
 extern int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages);
 extern void __init efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages);
 extern void __init old_map_region(efi_memory_desc_t *md);
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 19d14ac23ef9..fc3c7e49c8e4 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -296,6 +296,7 @@ struct x86_emulate_ctxt {
 
 	bool perm_ok; /* do not check permissions if true */
 	bool ud;	/* inject an #UD if host doesn't support insn */
+	bool tf;	/* TF value before instruction (after for syscall/sysret) */
 
 	bool have_exception;
 	struct x86_exception exception;
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 7402eb4b509d..6a07c05956a6 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -7,6 +7,7 @@
 #include <linux/compiler.h>
 #include <linux/thread_info.h>
 #include <linux/string.h>
+#include <linux/preempt.h>
 #include <asm/asm.h>
 #include <asm/page.h>
 #include <asm/smap.h>
@@ -66,6 +67,12 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un
 	__chk_range_not_ok((unsigned long __force)(addr), size, limit); \
 })
 
+#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
+# define WARN_ON_IN_IRQ()	WARN_ON_ONCE(!in_task())
+#else
+# define WARN_ON_IN_IRQ()
+#endif
+
 /**
  * access_ok: - Checks if a user space pointer is valid
  * @type: Type of access: %VERIFY_READ or %VERIFY_WRITE.  Note that
@@ -86,8 +93,11 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un
  * checks that the pointer is in the user space range - after calling
  * this function, memory access functions may still return -EFAULT.
  */
-#define access_ok(type, addr, size) \
-	likely(!__range_not_ok(addr, size, user_addr_max()))
+#define access_ok(type, addr, size)					\
+({									\
+	WARN_ON_IN_IRQ();						\
+	likely(!__range_not_ok(addr, size, user_addr_max()));		\
+})
 
 /*
  * The exception table consists of pairs of addresses relative to the
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 04b2f3cad7ba..684edebb4a0c 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2726,6 +2726,7 @@ static int em_syscall(struct x86_emulate_ctxt *ctxt)
 		ctxt->eflags &= ~(X86_EFLAGS_VM | X86_EFLAGS_IF);
 	}
 
+	ctxt->tf = (ctxt->eflags & X86_EFLAGS_TF) != 0;
 	return X86EMUL_CONTINUE;
 }
 
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 899c40f826dd..4b1152e57340 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1696,6 +1696,8 @@ static int ud_interception(struct vcpu_svm *svm)
 	int er;
 
 	er = emulate_instruction(&svm->vcpu, EMULTYPE_TRAP_UD);
+	if (er == EMULATE_USER_EXIT)
+		return 0;
 	if (er != EMULATE_DONE)
 		kvm_queue_exception(&svm->vcpu, UD_VECTOR);
 	return 1;
@@ -3114,6 +3116,13 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	u32 ecx = msr->index;
 	u64 data = msr->data;
 	switch (ecx) {
+	case MSR_IA32_CR_PAT:
+		if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data))
+			return 1;
+		vcpu->arch.pat = data;
+		svm->vmcb->save.g_pat = data;
+		mark_dirty(svm->vmcb, VMCB_NPT);
+		break;
 	case MSR_IA32_TSC:
 		kvm_write_tsc(vcpu, msr);
 		break;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 9114588e3e61..253a8c8207bb 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -5267,6 +5267,8 @@ static int handle_exception(struct kvm_vcpu *vcpu)
 			return 1;
 		}
 		er = emulate_instruction(vcpu, EMULTYPE_TRAP_UD);
+		if (er == EMULATE_USER_EXIT)
+			return 0;
 		if (er != EMULATE_DONE)
 			kvm_queue_exception(vcpu, UD_VECTOR);
 		return 1;
@@ -10394,6 +10396,8 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 	vmcs_writel(GUEST_SYSENTER_EIP, vmcs12->host_ia32_sysenter_eip);
 	vmcs_writel(GUEST_IDTR_BASE, vmcs12->host_idtr_base);
 	vmcs_writel(GUEST_GDTR_BASE, vmcs12->host_gdtr_base);
+	vmcs_write32(GUEST_IDTR_LIMIT, 0xFFFF);
+	vmcs_write32(GUEST_GDTR_LIMIT, 0xFFFF);
 
 	/* If not VM_EXIT_CLEAR_BNDCFGS, the L2 value propagates to L1.  */
 	if (vmcs12->vm_exit_controls & VM_EXIT_CLEAR_BNDCFGS)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 8e526c6fd784..df81717a92f3 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1812,6 +1812,9 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 	 */
 	BUILD_BUG_ON(offsetof(struct pvclock_vcpu_time_info, version) != 0);
 
+	if (guest_hv_clock.version & 1)
+		++guest_hv_clock.version;  /* first time write, random junk */
+
 	vcpu->hv_clock.version = guest_hv_clock.version + 1;
 	kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
 				&vcpu->hv_clock,
@@ -5095,6 +5098,8 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu)
 	kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
 
 	ctxt->eflags = kvm_get_rflags(vcpu);
+	ctxt->tf = (ctxt->eflags & X86_EFLAGS_TF) != 0;
+
 	ctxt->eip = kvm_rip_read(vcpu);
 	ctxt->mode = (!is_protmode(vcpu))		? X86EMUL_MODE_REAL :
 		     (ctxt->eflags & X86_EFLAGS_VM)	? X86EMUL_MODE_VM86 :
@@ -5315,37 +5320,26 @@ static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7,
 	return dr6;
 }
 
-static void kvm_vcpu_check_singlestep(struct kvm_vcpu *vcpu, unsigned long rflags, int *r)
+static void kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu, int *r)
 {
 	struct kvm_run *kvm_run = vcpu->run;
 
-	/*
-	 * rflags is the old, "raw" value of the flags.  The new value has
-	 * not been saved yet.
-	 *
-	 * This is correct even for TF set by the guest, because "the
-	 * processor will not generate this exception after the instruction
-	 * that sets the TF flag".
-	 */
-	if (unlikely(rflags & X86_EFLAGS_TF)) {
-		if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
-			kvm_run->debug.arch.dr6 = DR6_BS | DR6_FIXED_1 |
-						  DR6_RTM;
-			kvm_run->debug.arch.pc = vcpu->arch.singlestep_rip;
-			kvm_run->debug.arch.exception = DB_VECTOR;
-			kvm_run->exit_reason = KVM_EXIT_DEBUG;
-			*r = EMULATE_USER_EXIT;
-		} else {
-			vcpu->arch.emulate_ctxt.eflags &= ~X86_EFLAGS_TF;
-			/*
-			 * "Certain debug exceptions may clear bit 0-3.  The
-			 * remaining contents of the DR6 register are never
-			 * cleared by the processor".
-			 */
-			vcpu->arch.dr6 &= ~15;
-			vcpu->arch.dr6 |= DR6_BS | DR6_RTM;
-			kvm_queue_exception(vcpu, DB_VECTOR);
-		}
+	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
+		kvm_run->debug.arch.dr6 = DR6_BS | DR6_FIXED_1 | DR6_RTM;
+		kvm_run->debug.arch.pc = vcpu->arch.singlestep_rip;
+		kvm_run->debug.arch.exception = DB_VECTOR;
+		kvm_run->exit_reason = KVM_EXIT_DEBUG;
+		*r = EMULATE_USER_EXIT;
+	} else {
+		vcpu->arch.emulate_ctxt.eflags &= ~X86_EFLAGS_TF;
+		/*
+		 * "Certain debug exceptions may clear bit 0-3.  The
+		 * remaining contents of the DR6 register are never
+		 * cleared by the processor".
+		 */
+		vcpu->arch.dr6 &= ~15;
+		vcpu->arch.dr6 |= DR6_BS | DR6_RTM;
+		kvm_queue_exception(vcpu, DB_VECTOR);
 	}
 }
 
@@ -5435,6 +5429,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 			if (reexecute_instruction(vcpu, cr2, write_fault_to_spt,
 						emulation_type))
 				return EMULATE_DONE;
+			if (ctxt->have_exception && inject_emulated_exception(vcpu))
+				return EMULATE_DONE;
 			if (emulation_type & EMULTYPE_SKIP)
 				return EMULATE_FAIL;
 			return handle_emulation_failure(vcpu);
@@ -5500,8 +5496,9 @@ restart:
 		toggle_interruptibility(vcpu, ctxt->interruptibility);
 		vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
 		kvm_rip_write(vcpu, ctxt->eip);
-		if (r == EMULATE_DONE)
-			kvm_vcpu_check_singlestep(vcpu, rflags, &r);
+		if (r == EMULATE_DONE &&
+		    (ctxt->tf || (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)))
+			kvm_vcpu_do_singlestep(vcpu, &r);
 		if (!ctxt->have_exception ||
 		    exception_type(ctxt->exception.vector) == EXCPT_TRAP)
 			__kvm_set_rflags(vcpu, ctxt->eflags);
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index d388de72eaca..ec039f2a0c13 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -833,7 +833,7 @@ EndTable
 
 GrpTable: Grp3_1
 0: TEST Eb,Ib
-1:
+1: TEST Eb,Ib
 2: NOT Eb
 3: NEG Eb
 4: MUL AL,Eb
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 4540e8880cd9..1924bba0f3af 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -911,15 +911,10 @@ static void populate_pte(struct cpa_data *cpa,
 	pte = pte_offset_kernel(pmd, start);
 
 	while (num_pages-- && start < end) {
-
-		/* deal with the NX bit */
-		if (!(pgprot_val(pgprot) & _PAGE_NX))
-			cpa->pfn &= ~_PAGE_NX;
-
-		set_pte(pte, pfn_pte(cpa->pfn >> PAGE_SHIFT, pgprot));
+		set_pte(pte, pfn_pte(cpa->pfn, pgprot));
 
 		start	 += PAGE_SIZE;
-		cpa->pfn += PAGE_SIZE;
+		cpa->pfn++;
 		pte++;
 	}
 }
@@ -975,11 +970,11 @@ static int populate_pmd(struct cpa_data *cpa,
 
 		pmd = pmd_offset(pud, start);
 
-		set_pmd(pmd, __pmd(cpa->pfn | _PAGE_PSE |
+		set_pmd(pmd, __pmd(cpa->pfn << PAGE_SHIFT | _PAGE_PSE |
 				   massage_pgprot(pmd_pgprot)));
 
 		start	  += PMD_SIZE;
-		cpa->pfn  += PMD_SIZE;
+		cpa->pfn  += PMD_SIZE >> PAGE_SHIFT;
 		cur_pages += PMD_SIZE >> PAGE_SHIFT;
 	}
 
@@ -1048,11 +1043,11 @@ static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd,
 	 * Map everything starting from the Gb boundary, possibly with 1G pages
 	 */
 	while (end - start >= PUD_SIZE) {
-		set_pud(pud, __pud(cpa->pfn | _PAGE_PSE |
+		set_pud(pud, __pud(cpa->pfn << PAGE_SHIFT | _PAGE_PSE |
 				   massage_pgprot(pud_pgprot)));
 
 		start	  += PUD_SIZE;
-		cpa->pfn  += PUD_SIZE;
+		cpa->pfn  += PUD_SIZE >> PAGE_SHIFT;
 		cur_pages += PUD_SIZE >> PAGE_SHIFT;
 		pud++;
 	}
diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c
index d90528ea5412..12c051d19e4b 100644
--- a/arch/x86/oprofile/op_model_ppro.c
+++ b/arch/x86/oprofile/op_model_ppro.c
@@ -212,8 +212,8 @@ static void arch_perfmon_setup_counters(void)
 	eax.full = cpuid_eax(0xa);
 
 	/* Workaround for BIOS bugs in 6/15. Taken from perfmon2 */
-	if (eax.split.version_id == 0 && __this_cpu_read(cpu_info.x86) == 6 &&
-		__this_cpu_read(cpu_info.x86_model) == 15) {
+	if (eax.split.version_id == 0 && boot_cpu_data.x86 == 6 &&
+	    boot_cpu_data.x86_model == 15) {
 		eax.split.version_id = 2;
 		eax.split.num_counters = 2;
 		eax.split.bit_width = 40;
diff --git a/arch/x86/platform/efi/efi-bgrt.c b/arch/x86/platform/efi/efi-bgrt.c
index ea48449b2e63..64fbc7e33226 100644
--- a/arch/x86/platform/efi/efi-bgrt.c
+++ b/arch/x86/platform/efi/efi-bgrt.c
@@ -28,8 +28,7 @@ struct bmp_header {
 void __init efi_bgrt_init(void)
 {
 	acpi_status status;
-	void __iomem *image;
-	bool ioremapped = false;
+	void *image;
 	struct bmp_header bmp_header;
 
 	if (acpi_disabled)
@@ -70,20 +69,14 @@ void __init efi_bgrt_init(void)
 		return;
 	}
 
-	image = efi_lookup_mapped_addr(bgrt_tab->image_address);
+	image = memremap(bgrt_tab->image_address, sizeof(bmp_header), MEMREMAP_WB);
 	if (!image) {
-		image = early_ioremap(bgrt_tab->image_address,
-				       sizeof(bmp_header));
-		ioremapped = true;
-		if (!image) {
-			pr_err("Ignoring BGRT: failed to map image header memory\n");
-			return;
-		}
+		pr_err("Ignoring BGRT: failed to map image header memory\n");
+		return;
 	}
 
-	memcpy_fromio(&bmp_header, image, sizeof(bmp_header));
-	if (ioremapped)
-		early_iounmap(image, sizeof(bmp_header));
+	memcpy(&bmp_header, image, sizeof(bmp_header));
+	memunmap(image);
 	bgrt_image_size = bmp_header.size;
 
 	bgrt_image = kmalloc(bgrt_image_size, GFP_KERNEL | __GFP_NOWARN);
@@ -93,18 +86,14 @@ void __init efi_bgrt_init(void)
 		return;
 	}
 
-	if (ioremapped) {
-		image = early_ioremap(bgrt_tab->image_address,
-				       bmp_header.size);
-		if (!image) {
-			pr_err("Ignoring BGRT: failed to map image memory\n");
-			kfree(bgrt_image);
-			bgrt_image = NULL;
-			return;
-		}
+	image = memremap(bgrt_tab->image_address, bmp_header.size, MEMREMAP_WB);
+	if (!image) {
+		pr_err("Ignoring BGRT: failed to map image memory\n");
+		kfree(bgrt_image);
+		bgrt_image = NULL;
+		return;
 	}
 
-	memcpy_fromio(bgrt_image, image, bgrt_image_size);
-	if (ioremapped)
-		early_iounmap(image, bmp_header.size);
+	memcpy(bgrt_image, image, bgrt_image_size);
+	memunmap(image);
 }
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index ad285404ea7f..3c1f3cd7b2ba 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -869,7 +869,7 @@ static void __init kexec_enter_virtual_mode(void)
  * This function will switch the EFI runtime services to virtual mode.
  * Essentially, we look through the EFI memmap and map every region that
  * has the runtime attribute bit set in its memory descriptor into the
- * ->trampoline_pgd page table using a top-down VA allocation scheme.
+ * efi_pgd page table.
  *
  * The old method which used to update that memory descriptor with the
  * virtual address obtained from ioremap() is still supported when the
@@ -879,8 +879,8 @@ static void __init kexec_enter_virtual_mode(void)
  *
  * The new method does a pagetable switch in a preemption-safe manner
  * so that we're in a different address space when calling a runtime
- * function. For function arguments passing we do copy the PGDs of the
- * kernel page table into ->trampoline_pgd prior to each call.
+ * function. For function arguments passing we do copy the PUDs of the
+ * kernel page table into efi_pgd prior to each call.
  *
  * Specially for kexec boot, efi runtime maps in previous kernel should
  * be passed in via setup_data. In that case runtime ranges will be mapped
@@ -895,6 +895,12 @@ static void __init __efi_enter_virtual_mode(void)
 
 	efi.systab = NULL;
 
+	if (efi_alloc_page_tables()) {
+		pr_err("Failed to allocate EFI page tables\n");
+		clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+		return;
+	}
+
 	efi_merge_regions();
 	new_memmap = efi_map_regions(&count, &pg_shift);
 	if (!new_memmap) {
@@ -954,28 +960,11 @@ static void __init __efi_enter_virtual_mode(void)
 	efi_runtime_mkexec();
 
 	/*
-	 * We mapped the descriptor array into the EFI pagetable above but we're
-	 * not unmapping it here. Here's why:
-	 *
-	 * We're copying select PGDs from the kernel page table to the EFI page
-	 * table and when we do so and make changes to those PGDs like unmapping
-	 * stuff from them, those changes appear in the kernel page table and we
-	 * go boom.
-	 *
-	 * From setup_real_mode():
-	 *
-	 * ...
-	 * trampoline_pgd[0] = init_level4_pgt[pgd_index(__PAGE_OFFSET)].pgd;
-	 *
-	 * In this particular case, our allocation is in PGD 0 of the EFI page
-	 * table but we've copied that PGD from PGD[272] of the EFI page table:
-	 *
-	 *	pgd_index(__PAGE_OFFSET = 0xffff880000000000) = 272
-	 *
-	 * where the direct memory mapping in kernel space is.
-	 *
-	 * new_memmap's VA comes from that direct mapping and thus clearing it,
-	 * it would get cleared in the kernel page table too.
+	 * We mapped the descriptor array into the EFI pagetable above
+	 * but we're not unmapping it here because if we're running in
+	 * EFI mixed mode we need all of memory to be accessible when
+	 * we pass parameters to the EFI runtime services in the
+	 * thunking code.
 	 *
 	 * efi_cleanup_page_tables(__pa(new_memmap), 1 << pg_shift);
 	 */
diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c
index ed5b67338294..58d669bc8250 100644
--- a/arch/x86/platform/efi/efi_32.c
+++ b/arch/x86/platform/efi/efi_32.c
@@ -38,6 +38,11 @@
  * say 0 - 3G.
  */
 
+int __init efi_alloc_page_tables(void)
+{
+	return 0;
+}
+
 void efi_sync_low_kernel_mappings(void) {}
 void __init efi_dump_pagetable(void) {}
 int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index a0ac0f9c307f..18dfaad71c99 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -40,6 +40,7 @@
 #include <asm/fixmap.h>
 #include <asm/realmode.h>
 #include <asm/time.h>
+#include <asm/pgalloc.h>
 
 /*
  * We allocate runtime services regions bottom-up, starting from -4G, i.e.
@@ -47,16 +48,7 @@
  */
 static u64 efi_va = EFI_VA_START;
 
-/*
- * Scratch space used for switching the pagetable in the EFI stub
- */
-struct efi_scratch {
-	u64 r15;
-	u64 prev_cr3;
-	pgd_t *efi_pgt;
-	bool use_pgd;
-	u64 phys_stack;
-} __packed;
+struct efi_scratch efi_scratch;
 
 static void __init early_code_mapping_set_exec(int executable)
 {
@@ -83,8 +75,11 @@ pgd_t * __init efi_call_phys_prolog(void)
 	int pgd;
 	int n_pgds;
 
-	if (!efi_enabled(EFI_OLD_MEMMAP))
-		return NULL;
+	if (!efi_enabled(EFI_OLD_MEMMAP)) {
+		save_pgd = (pgd_t *)read_cr3();
+		write_cr3((unsigned long)efi_scratch.efi_pgt);
+		goto out;
+	}
 
 	early_code_mapping_set_exec(1);
 
@@ -96,6 +91,7 @@ pgd_t * __init efi_call_phys_prolog(void)
 		vaddress = (unsigned long)__va(pgd * PGDIR_SIZE);
 		set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), *pgd_offset_k(vaddress));
 	}
+out:
 	__flush_tlb_all();
 
 	return save_pgd;
@@ -109,8 +105,11 @@ void __init efi_call_phys_epilog(pgd_t *save_pgd)
 	int pgd_idx;
 	int nr_pgds;
 
-	if (!save_pgd)
+	if (!efi_enabled(EFI_OLD_MEMMAP)) {
+		write_cr3((unsigned long)save_pgd);
+		__flush_tlb_all();
 		return;
+	}
 
 	nr_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT) , PGDIR_SIZE);
 
@@ -123,27 +122,97 @@ void __init efi_call_phys_epilog(pgd_t *save_pgd)
 	early_code_mapping_set_exec(0);
 }
 
+static pgd_t *efi_pgd;
+
+/*
+ * We need our own copy of the higher levels of the page tables
+ * because we want to avoid inserting EFI region mappings (EFI_VA_END
+ * to EFI_VA_START) into the standard kernel page tables. Everything
+ * else can be shared, see efi_sync_low_kernel_mappings().
+ */
+int __init efi_alloc_page_tables(void)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	gfp_t gfp_mask;
+
+	if (efi_enabled(EFI_OLD_MEMMAP))
+		return 0;
+
+	gfp_mask = GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO;
+	efi_pgd = (pgd_t *)__get_free_page(gfp_mask);
+	if (!efi_pgd)
+		return -ENOMEM;
+
+	pgd = efi_pgd + pgd_index(EFI_VA_END);
+
+	pud = pud_alloc_one(NULL, 0);
+	if (!pud) {
+		free_page((unsigned long)efi_pgd);
+		return -ENOMEM;
+	}
+
+	pgd_populate(NULL, pgd, pud);
+
+	return 0;
+}
+
 /*
  * Add low kernel mappings for passing arguments to EFI functions.
  */
 void efi_sync_low_kernel_mappings(void)
 {
-	unsigned num_pgds;
-	pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd);
+	unsigned num_entries;
+	pgd_t *pgd_k, *pgd_efi;
+	pud_t *pud_k, *pud_efi;
 
 	if (efi_enabled(EFI_OLD_MEMMAP))
 		return;
 
-	num_pgds = pgd_index(MODULES_END - 1) - pgd_index(PAGE_OFFSET);
+	/*
+	 * We can share all PGD entries apart from the one entry that
+	 * covers the EFI runtime mapping space.
+	 *
+	 * Make sure the EFI runtime region mappings are guaranteed to
+	 * only span a single PGD entry and that the entry also maps
+	 * other important kernel regions.
+	 */
+	BUILD_BUG_ON(pgd_index(EFI_VA_END) != pgd_index(MODULES_END));
+	BUILD_BUG_ON((EFI_VA_START & PGDIR_MASK) !=
+			(EFI_VA_END & PGDIR_MASK));
+
+	pgd_efi = efi_pgd + pgd_index(PAGE_OFFSET);
+	pgd_k = pgd_offset_k(PAGE_OFFSET);
 
-	memcpy(pgd + pgd_index(PAGE_OFFSET),
-		init_mm.pgd + pgd_index(PAGE_OFFSET),
-		sizeof(pgd_t) * num_pgds);
+	num_entries = pgd_index(EFI_VA_END) - pgd_index(PAGE_OFFSET);
+	memcpy(pgd_efi, pgd_k, sizeof(pgd_t) * num_entries);
+
+	/*
+	 * We share all the PUD entries apart from those that map the
+	 * EFI regions. Copy around them.
+	 */
+	BUILD_BUG_ON((EFI_VA_START & ~PUD_MASK) != 0);
+	BUILD_BUG_ON((EFI_VA_END & ~PUD_MASK) != 0);
+
+	pgd_efi = efi_pgd + pgd_index(EFI_VA_END);
+	pud_efi = pud_offset(pgd_efi, 0);
+
+	pgd_k = pgd_offset_k(EFI_VA_END);
+	pud_k = pud_offset(pgd_k, 0);
+
+	num_entries = pud_index(EFI_VA_END);
+	memcpy(pud_efi, pud_k, sizeof(pud_t) * num_entries);
+
+	pud_efi = pud_offset(pgd_efi, EFI_VA_START);
+	pud_k = pud_offset(pgd_k, EFI_VA_START);
+
+	num_entries = PTRS_PER_PUD - pud_index(EFI_VA_START);
+	memcpy(pud_efi, pud_k, sizeof(pud_t) * num_entries);
 }
 
 int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
 {
-	unsigned long text;
+	unsigned long pfn, text;
 	struct page *page;
 	unsigned npages;
 	pgd_t *pgd;
@@ -151,8 +220,8 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
 	if (efi_enabled(EFI_OLD_MEMMAP))
 		return 0;
 
-	efi_scratch.efi_pgt = (pgd_t *)(unsigned long)real_mode_header->trampoline_pgd;
-	pgd = __va(efi_scratch.efi_pgt);
+	efi_scratch.efi_pgt = (pgd_t *)__pa(efi_pgd);
+	pgd = efi_pgd;
 
 	/*
 	 * It can happen that the physical address of new_memmap lands in memory
@@ -160,7 +229,8 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
 	 * and ident-map those pages containing the map before calling
 	 * phys_efi_set_virtual_address_map().
 	 */
-	if (kernel_map_pages_in_pgd(pgd, pa_memmap, pa_memmap, num_pages, _PAGE_NX)) {
+	pfn = pa_memmap >> PAGE_SHIFT;
+	if (kernel_map_pages_in_pgd(pgd, pfn, pa_memmap, num_pages, _PAGE_NX)) {
 		pr_err("Error ident-mapping new memmap (0x%lx)!\n", pa_memmap);
 		return 1;
 	}
@@ -185,8 +255,9 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
 
 	npages = (_end - _text) >> PAGE_SHIFT;
 	text = __pa(_text);
+	pfn = text >> PAGE_SHIFT;
 
-	if (kernel_map_pages_in_pgd(pgd, text >> PAGE_SHIFT, text, npages, 0)) {
+	if (kernel_map_pages_in_pgd(pgd, pfn, text, npages, 0)) {
 		pr_err("Failed to map kernel text 1:1\n");
 		return 1;
 	}
@@ -196,20 +267,20 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
 
 void __init efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages)
 {
-	pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd);
-
-	kernel_unmap_pages_in_pgd(pgd, pa_memmap, num_pages);
+	kernel_unmap_pages_in_pgd(efi_pgd, pa_memmap, num_pages);
 }
 
 static void __init __map_region(efi_memory_desc_t *md, u64 va)
 {
-	pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd);
-	unsigned long pf = 0;
+	unsigned long flags = 0;
+	unsigned long pfn;
+	pgd_t *pgd = efi_pgd;
 
 	if (!(md->attribute & EFI_MEMORY_WB))
-		pf |= _PAGE_PCD;
+		flags |= _PAGE_PCD;
 
-	if (kernel_map_pages_in_pgd(pgd, md->phys_addr, va, md->num_pages, pf))
+	pfn = md->phys_addr >> PAGE_SHIFT;
+	if (kernel_map_pages_in_pgd(pgd, pfn, va, md->num_pages, flags))
 		pr_warn("Error mapping PA 0x%llx -> VA 0x%llx!\n",
 			   md->phys_addr, va);
 }
@@ -312,9 +383,7 @@ void __init efi_runtime_mkexec(void)
 void __init efi_dump_pagetable(void)
 {
 #ifdef CONFIG_EFI_PGT_DUMP
-	pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd);
-
-	ptdump_walk_pgd_level(NULL, pgd);
+	ptdump_walk_pgd_level(NULL, efi_pgd);
 #endif
 }
 
diff --git a/arch/x86/platform/efi/efi_stub_64.S b/arch/x86/platform/efi/efi_stub_64.S
index 86d0f9e08dd9..32020cb8bb08 100644
--- a/arch/x86/platform/efi/efi_stub_64.S
+++ b/arch/x86/platform/efi/efi_stub_64.S
@@ -38,41 +38,6 @@
 	mov %rsi, %cr0;			\
 	mov (%rsp), %rsp
 
-	/* stolen from gcc */
-	.macro FLUSH_TLB_ALL
-	movq %r15, efi_scratch(%rip)
-	movq %r14, efi_scratch+8(%rip)
-	movq %cr4, %r15
-	movq %r15, %r14
-	andb $0x7f, %r14b
-	movq %r14, %cr4
-	movq %r15, %cr4
-	movq efi_scratch+8(%rip), %r14
-	movq efi_scratch(%rip), %r15
-	.endm
-
-	.macro SWITCH_PGT
-	cmpb $0, efi_scratch+24(%rip)
-	je 1f
-	movq %r15, efi_scratch(%rip)		# r15
-	# save previous CR3
-	movq %cr3, %r15
-	movq %r15, efi_scratch+8(%rip)		# prev_cr3
-	movq efi_scratch+16(%rip), %r15		# EFI pgt
-	movq %r15, %cr3
-	1:
-	.endm
-
-	.macro RESTORE_PGT
-	cmpb $0, efi_scratch+24(%rip)
-	je 2f
-	movq efi_scratch+8(%rip), %r15
-	movq %r15, %cr3
-	movq efi_scratch(%rip), %r15
-	FLUSH_TLB_ALL
-	2:
-	.endm
-
 ENTRY(efi_call)
 	SAVE_XMM
 	mov (%rsp), %rax
@@ -83,16 +48,8 @@ ENTRY(efi_call)
 	mov %r8, %r9
 	mov %rcx, %r8
 	mov %rsi, %rcx
-	SWITCH_PGT
 	call *%rdi
-	RESTORE_PGT
 	addq $48, %rsp
 	RESTORE_XMM
 	ret
 ENDPROC(efi_call)
-
-	.data
-ENTRY(efi_scratch)
-	.fill 3,8,0
-	.byte 0
-	.quad 0