diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 1e89d122f084..5692e19199b3 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1111,7 +1111,7 @@ Kernel parameters
 			It will be ignored when crashkernel=X,high is not used
 			or memory reserved is below 4G.
 	crashkernel=size[KMG],cma
-			[KNL, X86] Reserve additional crash kernel memory from
+			[KNL, X86, ppc] Reserve additional crash kernel memory from
 			CMA. This reservation is usable by the first system's
 			userspace memory and kernel movable allocations (memory
 			balloon, zswap). Pages allocated from this memory range
@@ -7304,6 +7304,9 @@ Kernel parameters
 			them frequently to increase the rate of SLB faults
 			on kernel addresses.
 
+	no_slb_preload	[PPC,EARLY]
+			Disables slb preloading for userspace.
+
 	sunrpc.min_resvport=
 	sunrpc.max_resvport=
 			[NFS,SUNRPC]
diff --git a/arch/powerpc/boot/addnote.c b/arch/powerpc/boot/addnote.c
index 53b3b2621457..78704927453a 100644
--- a/arch/powerpc/boot/addnote.c
+++ b/arch/powerpc/boot/addnote.c
@@ -68,8 +68,8 @@ static int e_class = ELFCLASS32;
 #define PUT_16BE(off, v)(buf[off] = ((v) >> 8) & 0xff, \
 			 buf[(off) + 1] = (v) & 0xff)
 #define PUT_32BE(off, v)(PUT_16BE((off), (v) >> 16L), PUT_16BE((off) + 2, (v)))
-#define PUT_64BE(off, v)((PUT_32BE((off), (v) >> 32L), \
-			  PUT_32BE((off) + 4, (v))))
+#define PUT_64BE(off, v)((PUT_32BE((off), (unsigned long long)(v) >> 32L), \
+			  PUT_32BE((off) + 4, (unsigned long long)(v))))
 
 #define GET_16LE(off)	((buf[off]) + (buf[(off)+1] << 8))
 #define GET_32LE(off)	(GET_16LE(off) + (GET_16LE((off)+2U) << 16U))
@@ -78,7 +78,8 @@ static int e_class = ELFCLASS32;
 #define PUT_16LE(off, v) (buf[off] = (v) & 0xff, \
 			  buf[(off) + 1] = ((v) >> 8) & 0xff)
 #define PUT_32LE(off, v) (PUT_16LE((off), (v)), PUT_16LE((off) + 2, (v) >> 16L))
-#define PUT_64LE(off, v) (PUT_32LE((off), (v)), PUT_32LE((off) + 4, (v) >> 32L))
+#define PUT_64LE(off, v) (PUT_32LE((off), (unsigned long long)(v)), \
+			  PUT_32LE((off) + 4, (unsigned long long)(v) >> 32L))
 
 #define GET_16(off)	(e_data == ELFDATA2MSB ? GET_16BE(off) : GET_16LE(off))
 #define GET_32(off)	(e_data == ELFDATA2MSB ? GET_32BE(off) : GET_32LE(off))
diff --git a/arch/powerpc/boot/dts/asp834x-redboot.dts b/arch/powerpc/boot/dts/asp834x-redboot.dts
index 52a84561c4f0..33ddb17d1876 100644
--- a/arch/powerpc/boot/dts/asp834x-redboot.dts
+++ b/arch/powerpc/boot/dts/asp834x-redboot.dts
@@ -72,7 +72,7 @@ soc8349@ff000000 {
 		reg = <0xff000000 0x00000200>;
 		bus-frequency = <0>;
 
-		wdt@200 {
+		watchdog@200 {
 			device_type = "watchdog";
 			compatible = "mpc83xx_wdt";
 			reg = <0x200 0x100>;
diff --git a/arch/powerpc/boot/dts/fsl/ge_imp3a.dts b/arch/powerpc/boot/dts/fsl/ge_imp3a.dts
index da3de8e2b7d2..9e5c01cfac2f 100644
--- a/arch/powerpc/boot/dts/fsl/ge_imp3a.dts
+++ b/arch/powerpc/boot/dts/fsl/ge_imp3a.dts
@@ -94,7 +94,7 @@ gef_gpio: gpio@4,400 {
 			gpio-controller;
 		};
 
-		wdt@4,800 {
+		watchdog@4,800 {
 			compatible = "ge,imp3a-fpga-wdt", "gef,fpga-wdt-1.00",
 				"gef,fpga-wdt";
 			reg = <0x4 0x800 0x8>;
@@ -103,7 +103,7 @@ wdt@4,800 {
 		};
 
 		/* Second watchdog available, driver currently supports one.
-		wdt@4,808 {
+		watchdog@4,808 {
 			compatible = "gef,imp3a-fpga-wdt", "gef,fpga-wdt-1.00",
 				"gef,fpga-wdt";
 			reg = <0x4 0x808 0x8>;
diff --git a/arch/powerpc/boot/dts/fsl/gef_ppc9a.dts b/arch/powerpc/boot/dts/fsl/gef_ppc9a.dts
index fc92bb032c51..48a81430a8a3 100644
--- a/arch/powerpc/boot/dts/fsl/gef_ppc9a.dts
+++ b/arch/powerpc/boot/dts/fsl/gef_ppc9a.dts
@@ -82,7 +82,7 @@ fpga@4,0 {
 			reg = <0x4 0x0 0x40>;
 		};
 
-		wdt@4,2000 {
+		watchdog@4,2000 {
 			compatible = "gef,ppc9a-fpga-wdt", "gef,fpga-wdt-1.00",
 				"gef,fpga-wdt";
 			reg = <0x4 0x2000 0x8>;
@@ -90,7 +90,7 @@ wdt@4,2000 {
 			interrupt-parent = <&gef_pic>;
 		};
 		/* Second watchdog available, driver currently supports one.
-		wdt@4,2010 {
+		watchdog@4,2010 {
 			compatible = "gef,ppc9a-fpga-wdt", "gef,fpga-wdt-1.00",
 				"gef,fpga-wdt";
 			reg = <0x4 0x2010 0x8>;
diff --git a/arch/powerpc/boot/dts/fsl/gef_sbc310.dts b/arch/powerpc/boot/dts/fsl/gef_sbc310.dts
index 47ae85c34635..8eb254b1738d 100644
--- a/arch/powerpc/boot/dts/fsl/gef_sbc310.dts
+++ b/arch/powerpc/boot/dts/fsl/gef_sbc310.dts
@@ -79,7 +79,7 @@ fpga@4,0 {
 			reg = <0x4 0x0 0x40>;
 		};
 
-		wdt@4,2000 {
+		watchdog@4,2000 {
 			compatible = "gef,sbc310-fpga-wdt", "gef,fpga-wdt-1.00",
 				"gef,fpga-wdt";
 			reg = <0x4 0x2000 0x8>;
@@ -87,7 +87,7 @@ wdt@4,2000 {
 			interrupt-parent = <&gef_pic>;
 		};
 /*
-		wdt@4,2010 {
+		watchdog@4,2010 {
 			compatible = "gef,sbc310-fpga-wdt", "gef,fpga-wdt-1.00",
 				"gef,fpga-wdt";
 			reg = <0x4 0x2010 0x8>;
diff --git a/arch/powerpc/boot/dts/fsl/gef_sbc610.dts b/arch/powerpc/boot/dts/fsl/gef_sbc610.dts
index 5322be44b62e..02edbb262b8f 100644
--- a/arch/powerpc/boot/dts/fsl/gef_sbc610.dts
+++ b/arch/powerpc/boot/dts/fsl/gef_sbc610.dts
@@ -82,14 +82,14 @@ fpga@4,0 {
 			reg = <0x4 0x0 0x40>;
 		};
 
-		wdt@4,2000 {
+		watchdog@4,2000 {
 			compatible = "gef,fpga-wdt";
 			reg = <0x4 0x2000 0x8>;
 			interrupts = <0x1a 0x4>;
 			interrupt-parent = <&gef_pic>;
 		};
 		/* Second watchdog available, driver currently supports one.
-		wdt@4,2010 {
+		watchdog@4,2010 {
 			compatible = "gef,fpga-wdt";
 			reg = <0x4 0x2010 0x8>;
 			interrupts = <0x1b 0x4>;
diff --git a/arch/powerpc/boot/dts/mpc5121.dtsi b/arch/powerpc/boot/dts/mpc5121.dtsi
index d3fc8062fbcd..a278fb7b9e71 100644
--- a/arch/powerpc/boot/dts/mpc5121.dtsi
+++ b/arch/powerpc/boot/dts/mpc5121.dtsi
@@ -112,7 +112,7 @@ ipic: interrupt-controller@c00 {
 		};
 
 		/* Watchdog timer */
-		wdt@900 {
+		watchdog@900 {
 			compatible = "fsl,mpc5121-wdt";
 			reg = <0x900 0x100>;
 		};
diff --git a/arch/powerpc/boot/dts/mpc8313erdb.dts b/arch/powerpc/boot/dts/mpc8313erdb.dts
index a8315795b2c9..09508b4c8c73 100644
--- a/arch/powerpc/boot/dts/mpc8313erdb.dts
+++ b/arch/powerpc/boot/dts/mpc8313erdb.dts
@@ -99,7 +99,7 @@ soc8313@e0000000 {
 		reg = <0xe0000000 0x00000200>;
 		bus-frequency = <0>;
 
-		wdt@200 {
+		watchdog@200 {
 			device_type = "watchdog";
 			compatible = "mpc83xx_wdt";
 			reg = <0x200 0x100>;
diff --git a/arch/powerpc/boot/dts/mpc8315erdb.dts b/arch/powerpc/boot/dts/mpc8315erdb.dts
index a89cb3139ca8..a8f68d6e50b0 100644
--- a/arch/powerpc/boot/dts/mpc8315erdb.dts
+++ b/arch/powerpc/boot/dts/mpc8315erdb.dts
@@ -100,7 +100,7 @@ immr@e0000000 {
 		reg = <0xe0000000 0x00000200>;
 		bus-frequency = <0>;
 
-		wdt@200 {
+		watchdog@200 {
 			device_type = "watchdog";
 			compatible = "mpc83xx_wdt";
 			reg = <0x200 0x100>;
diff --git a/arch/powerpc/boot/dts/mpc832x_rdb.dts b/arch/powerpc/boot/dts/mpc832x_rdb.dts
index ecebc27a2898..ba7caaf98fd5 100644
--- a/arch/powerpc/boot/dts/mpc832x_rdb.dts
+++ b/arch/powerpc/boot/dts/mpc832x_rdb.dts
@@ -52,7 +52,7 @@ soc8323@e0000000 {
 		reg = <0xe0000000 0x00000200>;
 		bus-frequency = <0>;
 
-		wdt@200 {
+		watchdog@200 {
 			device_type = "watchdog";
 			compatible = "mpc83xx_wdt";
 			reg = <0x200 0x100>;
diff --git a/arch/powerpc/boot/dts/mpc8349emitx.dts b/arch/powerpc/boot/dts/mpc8349emitx.dts
index d4ebbb93de0b..13f17232ba83 100644
--- a/arch/powerpc/boot/dts/mpc8349emitx.dts
+++ b/arch/powerpc/boot/dts/mpc8349emitx.dts
@@ -53,7 +53,7 @@ soc8349@e0000000 {
 		reg = <0xe0000000 0x00000200>;
 		bus-frequency = <0>;                    // from bootloader
 
-		wdt@200 {
+		watchdog@200 {
 			device_type = "watchdog";
 			compatible = "mpc83xx_wdt";
 			reg = <0x200 0x100>;
diff --git a/arch/powerpc/boot/dts/mpc8349emitxgp.dts b/arch/powerpc/boot/dts/mpc8349emitxgp.dts
index bcf68a0a7b55..eae0afd5abbc 100644
--- a/arch/powerpc/boot/dts/mpc8349emitxgp.dts
+++ b/arch/powerpc/boot/dts/mpc8349emitxgp.dts
@@ -51,7 +51,7 @@ soc8349@e0000000 {
 		reg = <0xe0000000 0x00000200>;
 		bus-frequency = <0>;                    // from bootloader
 
-		wdt@200 {
+		watchdog@200 {
 			device_type = "watchdog";
 			compatible = "mpc83xx_wdt";
 			reg = <0x200 0x100>;
diff --git a/arch/powerpc/boot/dts/mpc836x_rdk.dts b/arch/powerpc/boot/dts/mpc836x_rdk.dts
index a0cc1953484d..4ff38e1a2185 100644
--- a/arch/powerpc/boot/dts/mpc836x_rdk.dts
+++ b/arch/powerpc/boot/dts/mpc836x_rdk.dts
@@ -62,7 +62,7 @@ soc@e0000000 {
 		/* filled by u-boot */
 		bus-frequency = <0>;
 
-		wdt@200 {
+		watchdog@200 {
 			compatible = "mpc83xx_wdt";
 			reg = <0x200 0x100>;
 		};
diff --git a/arch/powerpc/boot/dts/mpc8377_rdb.dts b/arch/powerpc/boot/dts/mpc8377_rdb.dts
index 7df452efa957..f137ccb8cfde 100644
--- a/arch/powerpc/boot/dts/mpc8377_rdb.dts
+++ b/arch/powerpc/boot/dts/mpc8377_rdb.dts
@@ -99,7 +99,7 @@ immr@e0000000 {
 		reg = <0xe0000000 0x00000200>;
 		bus-frequency = <0>;
 
-		wdt@200 {
+		watchdog@200 {
 			device_type = "watchdog";
 			compatible = "mpc83xx_wdt";
 			reg = <0x200 0x100>;
diff --git a/arch/powerpc/boot/dts/mpc8377_wlan.dts b/arch/powerpc/boot/dts/mpc8377_wlan.dts
index d8e7d40aeae4..ce254dd74dd0 100644
--- a/arch/powerpc/boot/dts/mpc8377_wlan.dts
+++ b/arch/powerpc/boot/dts/mpc8377_wlan.dts
@@ -89,7 +89,7 @@ immr@e0000000 {
 		reg = <0xe0000000 0x00000200>;
 		bus-frequency = <0>;
 
-		wdt@200 {
+		watchdog@200 {
 			device_type = "watchdog";
 			compatible = "mpc83xx_wdt";
 			reg = <0x200 0x100>;
diff --git a/arch/powerpc/boot/dts/mpc8378_rdb.dts b/arch/powerpc/boot/dts/mpc8378_rdb.dts
index bdcfe83a561e..19e5473d4161 100644
--- a/arch/powerpc/boot/dts/mpc8378_rdb.dts
+++ b/arch/powerpc/boot/dts/mpc8378_rdb.dts
@@ -99,7 +99,7 @@ immr@e0000000 {
 		reg = <0xe0000000 0x00000200>;
 		bus-frequency = <0>;
 
-		wdt@200 {
+		watchdog@200 {
 			device_type = "watchdog";
 			compatible = "mpc83xx_wdt";
 			reg = <0x200 0x100>;
diff --git a/arch/powerpc/boot/dts/mpc8379_rdb.dts b/arch/powerpc/boot/dts/mpc8379_rdb.dts
index a5f702304a35..61519acca228 100644
--- a/arch/powerpc/boot/dts/mpc8379_rdb.dts
+++ b/arch/powerpc/boot/dts/mpc8379_rdb.dts
@@ -97,7 +97,7 @@ immr@e0000000 {
 		reg = <0xe0000000 0x00000200>;
 		bus-frequency = <0>;
 
-		wdt@200 {
+		watchdog@200 {
 			device_type = "watchdog";
 			compatible = "mpc83xx_wdt";
 			reg = <0x200 0x100>;
diff --git a/arch/powerpc/boot/wrapper b/arch/powerpc/boot/wrapper
index a75baefd1cff..1efd1206fcab 100755
--- a/arch/powerpc/boot/wrapper
+++ b/arch/powerpc/boot/wrapper
@@ -21,7 +21,7 @@
 #		(default ./arch/powerpc/boot)
 # -W dir	specify working directory for temporary files (default .)
 # -z		use gzip (legacy)
-# -Z zsuffix    compression to use (gz, xz or none)
+# -Z zsuffix    compression to use (gz, xz, lzma, lzo or none)
 
 # Stop execution if any command fails
 set -e
@@ -69,7 +69,7 @@ usage() {
     echo 'Usage: wrapper [-o output] [-p platform] [-i initrd]' >&2
     echo '       [-d devtree] [-s tree.dts] [-e esm_blob]' >&2
     echo '       [-c] [-C cross-prefix] [-D datadir] [-W workingdir]' >&2
-    echo '       [-Z (gz|xz|none)] [--no-compression] [vmlinux]' >&2
+    echo '       [-Z (gz|xz|lzma|lzo|none)] [--no-compression] [vmlinux]' >&2
     exit 1
 }
 
diff --git a/arch/powerpc/include/asm/book3s/32/tlbflush.h b/arch/powerpc/include/asm/book3s/32/tlbflush.h
index e43534da5207..4be2200a3c7e 100644
--- a/arch/powerpc/include/asm/book3s/32/tlbflush.h
+++ b/arch/powerpc/include/asm/book3s/32/tlbflush.h
@@ -11,6 +11,7 @@
 void hash__flush_tlb_mm(struct mm_struct *mm);
 void hash__flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
 void hash__flush_range(struct mm_struct *mm, unsigned long start, unsigned long end);
+void hash__flush_gather(struct mmu_gather *tlb);
 
 #ifdef CONFIG_SMP
 void _tlbie(unsigned long address);
@@ -29,7 +30,9 @@ void _tlbia(void);
 static inline void tlb_flush(struct mmu_gather *tlb)
 {
 	/* 603 needs to flush the whole TLB here since it doesn't use a hash table. */
-	if (!mmu_has_feature(MMU_FTR_HPTE_TABLE))
+	if (mmu_has_feature(MMU_FTR_HPTE_TABLE))
+		hash__flush_gather(tlb);
+	else
 		_tlbia();
 }
 
diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
index 346351423207..af12e2ba8eb8 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
@@ -524,7 +524,6 @@ void slb_save_contents(struct slb_entry *slb_ptr);
 void slb_dump_contents(struct slb_entry *slb_ptr);
 
 extern void slb_vmalloc_update(void);
-void preload_new_slb_context(unsigned long start, unsigned long sp);
 
 #ifdef CONFIG_PPC_64S_HASH_MMU
 void slb_set_size(u16 size);
diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h
index 4bbf9f699aaa..bd4a6c42a5f3 100644
--- a/arch/powerpc/include/asm/kexec.h
+++ b/arch/powerpc/include/asm/kexec.h
@@ -115,9 +115,11 @@ int setup_new_fdt_ppc64(const struct kimage *image, void *fdt, struct crash_mem
 #ifdef CONFIG_CRASH_RESERVE
 int __init overlaps_crashkernel(unsigned long start, unsigned long size);
 extern void arch_reserve_crashkernel(void);
+extern void kdump_cma_reserve(void);
 #else
 static inline void arch_reserve_crashkernel(void) {}
 static inline int overlaps_crashkernel(unsigned long start, unsigned long size) { return 0; }
+static inline void kdump_cma_reserve(void) { }
 #endif
 
 #if defined(CONFIG_CRASH_DUMP)
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index f19ca44512d1..66ed5fe1b718 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -132,15 +132,18 @@ static inline int cpu_to_coregroup_id(int cpu)
 #include <asm/cputable.h>
 
 struct cpumask *cpu_coregroup_mask(int cpu);
+const struct cpumask *cpu_die_mask(int cpu);
+int cpu_die_id(int cpu);
 
 #ifdef CONFIG_PPC64
 #include <asm/smp.h>
 
 #define topology_physical_package_id(cpu)	(cpu_to_chip_id(cpu))
-
-#define topology_sibling_cpumask(cpu)	(per_cpu(cpu_sibling_map, cpu))
-#define topology_core_cpumask(cpu)	(per_cpu(cpu_core_map, cpu))
-#define topology_core_id(cpu)		(cpu_to_core_id(cpu))
+#define topology_sibling_cpumask(cpu)		(per_cpu(cpu_sibling_map, cpu))
+#define topology_core_cpumask(cpu)		(per_cpu(cpu_core_map, cpu))
+#define topology_core_id(cpu)			(cpu_to_core_id(cpu))
+#define topology_die_id(cpu)			(cpu_die_id(cpu))
+#define topology_die_cpumask(cpu)		(cpu_die_mask(cpu))
 
 #endif
 #endif
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index f4a8c9877249..16f8ee6cb2cd 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -101,6 +101,17 @@ SYM_FUNC_END(__kuep_unlock)
 .endm
 #endif
 
+.macro	clr_ri trash
+#ifndef CONFIG_BOOKE
+#ifdef CONFIG_PPC_8xx
+	mtspr   SPRN_NRI, \trash
+#else
+	li	\trash, MSR_KERNEL & ~MSR_RI
+	mtmsr	\trash
+#endif
+#endif
+.endm
+
 	.globl	transfer_to_syscall
 transfer_to_syscall:
 	stw	r3, ORIG_GPR3(r1)
@@ -149,6 +160,7 @@ ret_from_syscall:
 	cmpwi	r3,0
 	REST_GPR(3, r1)
 syscall_exit_finish:
+	clr_ri	r4
 	mtspr	SPRN_SRR0,r7
 	mtspr	SPRN_SRR1,r8
 
@@ -168,6 +180,7 @@ syscall_exit_finish:
 	REST_GPR(0, r1)
 	REST_GPRS(3, 12, r1)
 	b	1b
+_ASM_NOKPROBE_SYMBOL(syscall_exit_finish)
 
 #ifdef CONFIG_44x
 .L44x_icache_flush:
@@ -216,7 +229,7 @@ fast_exception_return:
 	beq	3f			/* if not, we've got problems */
 #endif
 
-2:	lwz	r10,_CCR(r11)
+	lwz	r10,_CCR(r11)
 	REST_GPRS(1, 6, r11)
 	mtcr	r10
 	lwz	r10,_LINK(r11)
@@ -224,13 +237,11 @@ fast_exception_return:
 	/* Clear the exception marker on the stack to avoid confusing stacktrace */
 	li	r10, 0
 	stw	r10, 8(r11)
-	REST_GPR(10, r11)
-#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS)
-	mtspr	SPRN_NRI, r0
-#endif
+	clr_ri	r10
 	mtspr	SPRN_SRR1,r9
 	mtspr	SPRN_SRR0,r12
 	REST_GPR(9, r11)
+	REST_GPR(10, r11)
 	REST_GPR(12, r11)
 	REST_GPR(11, r11)
 	rfi
@@ -259,14 +270,14 @@ interrupt_return:
 .Lfast_user_interrupt_return:
 	lwz	r11,_NIP(r1)
 	lwz	r12,_MSR(r1)
+	clr_ri	r4
 	mtspr	SPRN_SRR0,r11
 	mtspr	SPRN_SRR1,r12
 
 BEGIN_FTR_SECTION
+	lwarx   r0,0,r1
+END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
 	stwcx.	r0,0,r1		/* to clear the reservation */
-FTR_SECTION_ELSE
-	lwarx	r0,0,r1
-ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
 
 	lwz	r3,_CCR(r1)
 	lwz	r4,_LINK(r1)
@@ -302,14 +313,14 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
 	cmpwi	cr1,r3,0
 	lwz	r11,_NIP(r1)
 	lwz	r12,_MSR(r1)
+	clr_ri	r4
 	mtspr	SPRN_SRR0,r11
 	mtspr	SPRN_SRR1,r12
 
 BEGIN_FTR_SECTION
+	lwarx   r0,0,r1
+END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
 	stwcx.	r0,0,r1		/* to clear the reservation */
-FTR_SECTION_ELSE
-	lwarx	r0,0,r1
-ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
 
 	lwz	r3,_LINK(r1)
 	lwz	r4,_CTR(r1)
diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
index e0c681d0b076..aea6f7e8e9c6 100644
--- a/arch/powerpc/kernel/interrupt.c
+++ b/arch/powerpc/kernel/interrupt.c
@@ -38,7 +38,7 @@ static inline bool exit_must_hard_disable(void)
 #else
 static inline bool exit_must_hard_disable(void)
 {
-	return true;
+	return false;
 }
 #endif
 
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index eb23966ac0a9..a45fe147868b 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1897,8 +1897,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	return 0;
 }
 
-void preload_new_slb_context(unsigned long start, unsigned long sp);
-
 /*
  * Set up a thread for executing a new program
  */
@@ -1906,9 +1904,6 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
 {
 #ifdef CONFIG_PPC64
 	unsigned long load_addr = regs->gpr[2];	/* saved by ELF_PLAT_INIT */
-
-	if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && !radix_enabled())
-		preload_new_slb_context(start, sp);
 #endif
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 68d47c53876c..c8c42b419742 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -35,6 +35,7 @@
 #include <linux/of_irq.h>
 #include <linux/hugetlb.h>
 #include <linux/pgtable.h>
+#include <asm/kexec.h>
 #include <asm/io.h>
 #include <asm/paca.h>
 #include <asm/processor.h>
@@ -995,11 +996,12 @@ void __init setup_arch(char **cmdline_p)
 	initmem_init();
 
 	/*
-	 * Reserve large chunks of memory for use by CMA for fadump, KVM and
+	 * Reserve large chunks of memory for use by CMA for kdump, fadump, KVM and
 	 * hugetlb. These must be called after initmem_init(), so that
 	 * pageblock_order is initialised.
 	 */
 	fadump_cma_init();
+	kdump_cma_reserve();
 	kvm_cma_reserve();
 	gigantic_hugetlb_cma_reserve();
 
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 68edb66c2964..292fee8809bc 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -1085,6 +1085,29 @@ static int __init init_big_cores(void)
 	return 0;
 }
 
+/*
+ * die_mask and die_id are only available on systems which support
+ * multiple coregroups within a same package. On all other systems, die_mask
+ * would be same as package mask and die_id would be set to -1.
+ */
+const struct cpumask *cpu_die_mask(int cpu)
+{
+	if (has_coregroup_support())
+		return per_cpu(cpu_coregroup_map, cpu);
+	else
+		return cpu_node_mask(cpu);
+}
+EXPORT_SYMBOL_GPL(cpu_die_mask);
+
+int cpu_die_id(int cpu)
+{
+	if (has_coregroup_support())
+		return cpu_to_coregroup_id(cpu);
+	else
+		return -1;
+}
+EXPORT_SYMBOL_GPL(cpu_die_id);
+
 void __init smp_prepare_cpus(unsigned int max_cpus)
 {
 	unsigned int cpu, num_threads;
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index de6ee7d35cff..15850296c0a9 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -330,7 +330,6 @@ SECTIONS
 	}
 	.hash : AT(ADDR(.hash) - LOAD_OFFSET) { *(.hash) }
 	.gnu.hash : AT(ADDR(.gnu.hash) - LOAD_OFFSET) { *(.gnu.hash) }
-	.interp : AT(ADDR(.interp) - LOAD_OFFSET) { *(.interp) }
 	.rela.dyn : AT(ADDR(.rela.dyn) - LOAD_OFFSET)
 	{
 		__rela_dyn_start = .;
diff --git a/arch/powerpc/kexec/core.c b/arch/powerpc/kexec/core.c
index d1a2d755381c..104c05520bf0 100644
--- a/arch/powerpc/kexec/core.c
+++ b/arch/powerpc/kexec/core.c
@@ -22,6 +22,8 @@
 #include <asm/setup.h>
 #include <asm/firmware.h>
 
+#define cpu_to_be_ulong __PASTE(cpu_to_be, BITS_PER_LONG)
+
 #ifdef CONFIG_CRASH_DUMP
 void machine_crash_shutdown(struct pt_regs *regs)
 {
@@ -59,6 +61,8 @@ void machine_kexec(struct kimage *image)
 
 #ifdef CONFIG_CRASH_RESERVE
 
+static unsigned long long crashk_cma_size;
+
 static unsigned long long __init get_crash_base(unsigned long long crash_base)
 {
 
@@ -110,7 +114,7 @@ void __init arch_reserve_crashkernel(void)
 
 	/* use common parsing */
 	ret = parse_crashkernel(boot_command_line, total_mem_sz, &crash_size,
-				&crash_base, NULL, NULL, NULL);
+				&crash_base, NULL, &crashk_cma_size, NULL);
 
 	if (ret)
 		return;
@@ -130,23 +134,22 @@ void __init arch_reserve_crashkernel(void)
 	reserve_crashkernel_generic(crash_size, crash_base, 0, false);
 }
 
+void __init kdump_cma_reserve(void)
+{
+	if (crashk_cma_size)
+		reserve_crashkernel_cma(crashk_cma_size);
+}
+
 int __init overlaps_crashkernel(unsigned long start, unsigned long size)
 {
 	return (start + size) > crashk_res.start && start <= crashk_res.end;
 }
 
 /* Values we need to export to the second kernel via the device tree. */
-static phys_addr_t kernel_end;
 static phys_addr_t crashk_base;
 static phys_addr_t crashk_size;
 static unsigned long long mem_limit;
 
-static struct property kernel_end_prop = {
-	.name = "linux,kernel-end",
-	.length = sizeof(phys_addr_t),
-	.value = &kernel_end,
-};
-
 static struct property crashk_base_prop = {
 	.name = "linux,crashkernel-base",
 	.length = sizeof(phys_addr_t),
@@ -165,8 +168,6 @@ static struct property memory_limit_prop = {
 	.value = &mem_limit,
 };
 
-#define cpu_to_be_ulong	__PASTE(cpu_to_be, BITS_PER_LONG)
-
 static void __init export_crashk_values(struct device_node *node)
 {
 	/* There might be existing crash kernel properties, but we can't
@@ -190,6 +191,15 @@ static void __init export_crashk_values(struct device_node *node)
 	mem_limit = cpu_to_be_ulong(memory_limit);
 	of_update_property(node, &memory_limit_prop);
 }
+#endif /* CONFIG_CRASH_RESERVE */
+
+static phys_addr_t kernel_end;
+
+static struct property kernel_end_prop = {
+	.name = "linux,kernel-end",
+	.length = sizeof(phys_addr_t),
+	.value = &kernel_end,
+};
 
 static int __init kexec_setup(void)
 {
@@ -200,16 +210,17 @@ static int __init kexec_setup(void)
 		return -ENOENT;
 
 	/* remove any stale properties so ours can be found */
-	of_remove_property(node, of_find_property(node, kernel_end_prop.name, NULL));
+	of_remove_property(node, of_find_property(node, kernel_end_prop.name,
+						  NULL));
 
 	/* information needed by userspace when using default_machine_kexec */
 	kernel_end = cpu_to_be_ulong(__pa(_end));
 	of_add_property(node, &kernel_end_prop);
 
+#ifdef CONFIG_CRASH_RESERVE
 	export_crashk_values(node);
-
+#endif
 	of_node_put(node);
 	return 0;
 }
 late_initcall(kexec_setup);
-#endif /* CONFIG_CRASH_RESERVE */
diff --git a/arch/powerpc/kexec/ranges.c b/arch/powerpc/kexec/ranges.c
index 3702b0bdab14..867135560e5c 100644
--- a/arch/powerpc/kexec/ranges.c
+++ b/arch/powerpc/kexec/ranges.c
@@ -515,7 +515,7 @@ int get_exclude_memory_ranges(struct crash_mem **mem_ranges)
  */
 int get_usable_memory_ranges(struct crash_mem **mem_ranges)
 {
-	int ret;
+	int ret, i;
 
 	/*
 	 * Early boot failure observed on guests when low memory (first memory
@@ -528,6 +528,13 @@ int get_usable_memory_ranges(struct crash_mem **mem_ranges)
 	if (ret)
 		goto out;
 
+	for (i = 0; i < crashk_cma_cnt; i++) {
+		ret = add_mem_range(mem_ranges, crashk_cma_ranges[i].start,
+				    crashk_cma_ranges[i].end - crashk_cma_ranges[i].start + 1);
+		if (ret)
+			goto out;
+	}
+
 	ret = add_rtas_mem_range(mem_ranges);
 	if (ret)
 		goto out;
@@ -546,6 +553,22 @@ int get_usable_memory_ranges(struct crash_mem **mem_ranges)
 #endif /* CONFIG_KEXEC_FILE */
 
 #ifdef CONFIG_CRASH_DUMP
+static int crash_exclude_mem_range_guarded(struct crash_mem **mem_ranges,
+					   unsigned long long mstart,
+					   unsigned long long mend)
+{
+	struct crash_mem *tmem = *mem_ranges;
+
+	/* Reallocate memory ranges if there is no space to split ranges */
+	if (tmem && (tmem->nr_ranges == tmem->max_nr_ranges)) {
+		tmem = realloc_mem_ranges(mem_ranges);
+		if (!tmem)
+			return -ENOMEM;
+	}
+
+	return crash_exclude_mem_range(tmem, mstart, mend);
+}
+
 /**
  * get_crash_memory_ranges - Get crash memory ranges. This list includes
  *                           first/crashing kernel's memory regions that
@@ -557,7 +580,6 @@ int get_usable_memory_ranges(struct crash_mem **mem_ranges)
 int get_crash_memory_ranges(struct crash_mem **mem_ranges)
 {
 	phys_addr_t base, end;
-	struct crash_mem *tmem;
 	u64 i;
 	int ret;
 
@@ -582,19 +604,18 @@ int get_crash_memory_ranges(struct crash_mem **mem_ranges)
 			sort_memory_ranges(*mem_ranges, true);
 	}
 
-	/* Reallocate memory ranges if there is no space to split ranges */
-	tmem = *mem_ranges;
-	if (tmem && (tmem->nr_ranges == tmem->max_nr_ranges)) {
-		tmem = realloc_mem_ranges(mem_ranges);
-		if (!tmem)
-			goto out;
-	}
-
 	/* Exclude crashkernel region */
-	ret = crash_exclude_mem_range(tmem, crashk_res.start, crashk_res.end);
+	ret = crash_exclude_mem_range_guarded(mem_ranges, crashk_res.start, crashk_res.end);
 	if (ret)
 		goto out;
 
+	for (i = 0; i < crashk_cma_cnt; ++i) {
+		ret = crash_exclude_mem_range_guarded(mem_ranges, crashk_cma_ranges[i].start,
+					      crashk_cma_ranges[i].end);
+		if (ret)
+			goto out;
+	}
+
 	/*
 	 * FIXME: For now, stay in parity with kexec-tools but if RTAS/OPAL
 	 *        regions are exported to save their context at the time of
@@ -697,8 +718,8 @@ int remove_mem_range(struct crash_mem **mem_ranges, u64 base, u64 size)
 		 * two half.
 		 */
 		else {
+			size = mem_rngs->ranges[i].end - end + 1;
 			mem_rngs->ranges[i].end = base - 1;
-			size = mem_rngs->ranges[i].end - end;
 			ret = add_mem_range(mem_ranges, end + 1, size);
 		}
 	}
diff --git a/arch/powerpc/mm/book3s32/tlb.c b/arch/powerpc/mm/book3s32/tlb.c
index 9ad6b56bfec9..e54a7b011232 100644
--- a/arch/powerpc/mm/book3s32/tlb.c
+++ b/arch/powerpc/mm/book3s32/tlb.c
@@ -105,3 +105,12 @@ void hash__flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
 		flush_hash_pages(mm->context.id, vmaddr, pmd_val(*pmd), 1);
 }
 EXPORT_SYMBOL(hash__flush_tlb_page);
+
+void hash__flush_gather(struct mmu_gather *tlb)
+{
+	if (tlb->fullmm || tlb->need_flush_all)
+		hash__flush_tlb_mm(tlb->mm);
+	else
+		hash__flush_range(tlb->mm, tlb->start, tlb->end);
+}
+EXPORT_SYMBOL(hash__flush_gather);
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index 3aee3af614af..9dc5889d6ecb 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -47,6 +47,7 @@
 #include <asm/mmu.h>
 #include <asm/mmu_context.h>
 #include <asm/page.h>
+#include <asm/pgalloc.h>
 #include <asm/types.h>
 #include <linux/uaccess.h>
 #include <asm/machdep.h>
@@ -449,6 +450,7 @@ static __init void hash_kfence_map_pool(void)
 {
 	unsigned long kfence_pool_start, kfence_pool_end;
 	unsigned long prot = pgprot_val(PAGE_KERNEL);
+	unsigned int pshift = mmu_psize_defs[mmu_linear_psize].shift;
 
 	if (!kfence_pool)
 		return;
@@ -459,6 +461,7 @@ static __init void hash_kfence_map_pool(void)
 	BUG_ON(htab_bolt_mapping(kfence_pool_start, kfence_pool_end,
 				    kfence_pool, prot, mmu_linear_psize,
 				    mmu_kernel_ssize));
+	update_page_count(mmu_linear_psize, KFENCE_POOL_SIZE >> pshift);
 	memblock_clear_nomap(kfence_pool, KFENCE_POOL_SIZE);
 }
 
@@ -952,7 +955,7 @@ static int __init htab_dt_scan_hugepage_blocks(unsigned long node,
 	block_size = be64_to_cpu(addr_prop[1]);
 	if (block_size != (16 * GB))
 		return 0;
-	printk(KERN_INFO "Huge page(16GB) memory: "
+	pr_info("Huge page(16GB) memory: "
 			"addr = 0x%lX size = 0x%lX pages = %d\n",
 			phys_addr, block_size, expected_pages);
 	if (phys_addr + block_size * expected_pages <= memblock_end_of_DRAM()) {
@@ -1135,7 +1138,7 @@ static void __init htab_init_page_sizes(void)
 		mmu_vmemmap_psize = mmu_virtual_psize;
 #endif /* CONFIG_SPARSEMEM_VMEMMAP */
 
-	printk(KERN_DEBUG "Page orders: linear mapping = %d, "
+	pr_info("Page orders: linear mapping = %d, "
 	       "virtual = %d, io = %d"
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 	       ", vmemmap = %d"
@@ -1234,6 +1237,7 @@ int hash__create_section_mapping(unsigned long start, unsigned long end,
 				 int nid, pgprot_t prot)
 {
 	int rc;
+	unsigned int pshift = mmu_psize_defs[mmu_linear_psize].shift;
 
 	if (end >= H_VMALLOC_START) {
 		pr_warn("Outside the supported range\n");
@@ -1251,17 +1255,22 @@ int hash__create_section_mapping(unsigned long start, unsigned long end,
 					      mmu_kernel_ssize);
 		BUG_ON(rc2 && (rc2 != -ENOENT));
 	}
+	update_page_count(mmu_linear_psize, (end - start) >> pshift);
 	return rc;
 }
 
 int hash__remove_section_mapping(unsigned long start, unsigned long end)
 {
+	unsigned int pshift = mmu_psize_defs[mmu_linear_psize].shift;
+
 	int rc = htab_remove_mapping(start, end, mmu_linear_psize,
 				     mmu_kernel_ssize);
 
 	if (resize_hpt_for_hotplug(memblock_phys_mem_size()) == -ENOSPC)
 		pr_warn("Hash collision while resizing HPT\n");
 
+	if (!rc)
+		update_page_count(mmu_linear_psize, -((end - start) >> pshift));
 	return rc;
 }
 #endif /* CONFIG_MEMORY_HOTPLUG */
@@ -1302,27 +1311,34 @@ static void __init htab_initialize(void)
 	unsigned long table;
 	unsigned long pteg_count;
 	unsigned long prot;
-	phys_addr_t base = 0, size = 0, end;
+	phys_addr_t base = 0, size = 0, end, limit = MEMBLOCK_ALLOC_ANYWHERE;
 	u64 i;
+	unsigned int pshift = mmu_psize_defs[mmu_linear_psize].shift;
 
 	DBG(" -> htab_initialize()\n");
 
+	if (firmware_has_feature(FW_FEATURE_LPAR))
+		limit = ppc64_rma_size;
+
 	if (mmu_has_feature(MMU_FTR_1T_SEGMENT)) {
 		mmu_kernel_ssize = MMU_SEGSIZE_1T;
 		mmu_highuser_ssize = MMU_SEGSIZE_1T;
-		printk(KERN_INFO "Using 1TB segments\n");
+		pr_info("Using 1TB segments\n");
 	}
 
 	if (stress_slb_enabled)
 		static_branch_enable(&stress_slb_key);
 
+	if (no_slb_preload)
+		static_branch_enable(&no_slb_preload_key);
+
 	if (stress_hpt_enabled) {
 		unsigned long tmp;
 		static_branch_enable(&stress_hpt_key);
 		// Too early to use nr_cpu_ids, so use NR_CPUS
 		tmp = memblock_phys_alloc_range(sizeof(struct stress_hpt_struct) * NR_CPUS,
 						__alignof__(struct stress_hpt_struct),
-						0, MEMBLOCK_ALLOC_ANYWHERE);
+						MEMBLOCK_LOW_LIMIT, limit);
 		memset((void *)tmp, 0xff, sizeof(struct stress_hpt_struct) * NR_CPUS);
 		stress_hpt_struct = __va(tmp);
 
@@ -1356,11 +1372,10 @@ static void __init htab_initialize(void)
 			mmu_hash_ops.hpte_clear_all();
 #endif
 	} else {
-		unsigned long limit = MEMBLOCK_ALLOC_ANYWHERE;
 
 		table = memblock_phys_alloc_range(htab_size_bytes,
 						  htab_size_bytes,
-						  0, limit);
+						  MEMBLOCK_LOW_LIMIT, limit);
 		if (!table)
 			panic("ERROR: Failed to allocate %pa bytes below %pa\n",
 			      &htab_size_bytes, &limit);
@@ -1392,8 +1407,8 @@ static void __init htab_initialize(void)
 		size = end - base;
 		base = (unsigned long)__va(base);
 
-		DBG("creating mapping for region: %lx..%lx (prot: %lx)\n",
-		    base, size, prot);
+		pr_debug("creating mapping for region: 0x%pa..0x%pa (prot: %lx)\n",
+				&base, &size, prot);
 
 		if ((base + size) >= H_VMALLOC_START) {
 			pr_warn("Outside the supported range\n");
@@ -1402,6 +1417,8 @@ static void __init htab_initialize(void)
 
 		BUG_ON(htab_bolt_mapping(base, base + size, __pa(base),
 				prot, mmu_linear_psize, mmu_kernel_ssize));
+
+		update_page_count(mmu_linear_psize, size >> pshift);
 	}
 	hash_kfence_map_pool();
 	memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE);
@@ -1423,6 +1440,8 @@ static void __init htab_initialize(void)
 		BUG_ON(htab_bolt_mapping(tce_alloc_start, tce_alloc_end,
 					 __pa(tce_alloc_start), prot,
 					 mmu_linear_psize, mmu_kernel_ssize));
+		update_page_count(mmu_linear_psize,
+				  (tce_alloc_end - tce_alloc_start) >> pshift);
 	}
 
 
@@ -1867,7 +1886,7 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea,
 			 * in vmalloc space, so switch vmalloc
 			 * to 4k pages
 			 */
-			printk(KERN_ALERT "Reducing vmalloc segment "
+			pr_alert("Reducing vmalloc segment "
 			       "to 4kB pages because of "
 			       "non-cacheable mapping\n");
 			psize = mmu_vmalloc_psize = MMU_PAGE_4K;
@@ -2432,6 +2451,8 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_hpt_order, hpt_order_get, hpt_order_set, "%llu\n")
 
 static int __init hash64_debugfs(void)
 {
+	if (radix_enabled())
+		return 0;
 	debugfs_create_file("hpt_order", 0600, arch_debugfs_dir, NULL,
 			    &fops_hpt_order);
 	return 0;
diff --git a/arch/powerpc/mm/book3s64/internal.h b/arch/powerpc/mm/book3s64/internal.h
index a57a25f06a21..cad08d83369c 100644
--- a/arch/powerpc/mm/book3s64/internal.h
+++ b/arch/powerpc/mm/book3s64/internal.h
@@ -22,9 +22,14 @@ static inline bool stress_hpt(void)
 	return static_branch_unlikely(&stress_hpt_key);
 }
 
-void hpt_do_stress(unsigned long ea, unsigned long hpte_group);
+extern bool no_slb_preload;
+DECLARE_STATIC_KEY_FALSE(no_slb_preload_key);
+static inline bool slb_preload_disabled(void)
+{
+	return static_branch_unlikely(&no_slb_preload_key);
+}
 
-void slb_setup_new_exec(void);
+void hpt_do_stress(unsigned long ea, unsigned long hpte_group);
 
 void exit_lazy_flush_tlb(struct mm_struct *mm, bool always_flush);
 
diff --git a/arch/powerpc/mm/book3s64/mmu_context.c b/arch/powerpc/mm/book3s64/mmu_context.c
index 4e1e45420bd4..fb9dcf9ca599 100644
--- a/arch/powerpc/mm/book3s64/mmu_context.c
+++ b/arch/powerpc/mm/book3s64/mmu_context.c
@@ -150,8 +150,6 @@ static int hash__init_new_context(struct mm_struct *mm)
 void hash__setup_new_exec(void)
 {
 	slice_setup_new_exec();
-
-	slb_setup_new_exec();
 }
 #else
 static inline int hash__init_new_context(struct mm_struct *mm)
diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c
index c9431ae7f78a..e3485db7de02 100644
--- a/arch/powerpc/mm/book3s64/pgtable.c
+++ b/arch/powerpc/mm/book3s64/pgtable.c
@@ -510,20 +510,21 @@ atomic_long_t direct_pages_count[MMU_PAGE_COUNT];
 
 void arch_report_meminfo(struct seq_file *m)
 {
-	/*
-	 * Hash maps the memory with one size mmu_linear_psize.
-	 * So don't bother to print these on hash
-	 */
-	if (!radix_enabled())
-		return;
 	seq_printf(m, "DirectMap4k:    %8lu kB\n",
 		   atomic_long_read(&direct_pages_count[MMU_PAGE_4K]) << 2);
-	seq_printf(m, "DirectMap64k:    %8lu kB\n",
+	seq_printf(m, "DirectMap64k:   %8lu kB\n",
 		   atomic_long_read(&direct_pages_count[MMU_PAGE_64K]) << 6);
-	seq_printf(m, "DirectMap2M:    %8lu kB\n",
-		   atomic_long_read(&direct_pages_count[MMU_PAGE_2M]) << 11);
-	seq_printf(m, "DirectMap1G:    %8lu kB\n",
-		   atomic_long_read(&direct_pages_count[MMU_PAGE_1G]) << 20);
+	if (radix_enabled()) {
+		seq_printf(m, "DirectMap2M:    %8lu kB\n",
+			   atomic_long_read(&direct_pages_count[MMU_PAGE_2M]) << 11);
+		seq_printf(m, "DirectMap1G:    %8lu kB\n",
+			   atomic_long_read(&direct_pages_count[MMU_PAGE_1G]) << 20);
+	} else {
+		seq_printf(m, "DirectMap16M:   %8lu kB\n",
+			   atomic_long_read(&direct_pages_count[MMU_PAGE_16M]) << 14);
+		seq_printf(m, "DirectMap16G:   %8lu kB\n",
+			   atomic_long_read(&direct_pages_count[MMU_PAGE_16G]) << 24);
+	}
 }
 #endif /* CONFIG_PROC_FS */
 
diff --git a/arch/powerpc/mm/book3s64/slb.c b/arch/powerpc/mm/book3s64/slb.c
index 6b783552403c..15f73abd1506 100644
--- a/arch/powerpc/mm/book3s64/slb.c
+++ b/arch/powerpc/mm/book3s64/slb.c
@@ -42,6 +42,15 @@ early_param("stress_slb", parse_stress_slb);
 
 __ro_after_init DEFINE_STATIC_KEY_FALSE(stress_slb_key);
 
+bool no_slb_preload __initdata;
+static int __init parse_no_slb_preload(char *p)
+{
+	no_slb_preload = true;
+	return 0;
+}
+early_param("no_slb_preload", parse_no_slb_preload);
+__ro_after_init DEFINE_STATIC_KEY_FALSE(no_slb_preload_key);
+
 static void assert_slb_presence(bool present, unsigned long ea)
 {
 #ifdef CONFIG_DEBUG_VM
@@ -294,11 +303,14 @@ static bool preload_hit(struct thread_info *ti, unsigned long esid)
 	return false;
 }
 
-static bool preload_add(struct thread_info *ti, unsigned long ea)
+static void preload_add(struct thread_info *ti, unsigned long ea)
 {
 	unsigned char idx;
 	unsigned long esid;
 
+	if (slb_preload_disabled())
+		return;
+
 	if (mmu_has_feature(MMU_FTR_1T_SEGMENT)) {
 		/* EAs are stored >> 28 so 256MB segments don't need clearing */
 		if (ea & ESID_MASK_1T)
@@ -308,7 +320,7 @@ static bool preload_add(struct thread_info *ti, unsigned long ea)
 	esid = ea >> SID_SHIFT;
 
 	if (preload_hit(ti, esid))
-		return false;
+		return;
 
 	idx = (ti->slb_preload_tail + ti->slb_preload_nr) % SLB_PRELOAD_NR;
 	ti->slb_preload_esid[idx] = esid;
@@ -316,8 +328,6 @@ static bool preload_add(struct thread_info *ti, unsigned long ea)
 		ti->slb_preload_tail = (ti->slb_preload_tail + 1) % SLB_PRELOAD_NR;
 	else
 		ti->slb_preload_nr++;
-
-	return true;
 }
 
 static void preload_age(struct thread_info *ti)
@@ -328,94 +338,6 @@ static void preload_age(struct thread_info *ti)
 	ti->slb_preload_tail = (ti->slb_preload_tail + 1) % SLB_PRELOAD_NR;
 }
 
-void slb_setup_new_exec(void)
-{
-	struct thread_info *ti = current_thread_info();
-	struct mm_struct *mm = current->mm;
-	unsigned long exec = 0x10000000;
-
-	WARN_ON(irqs_disabled());
-
-	/*
-	 * preload cache can only be used to determine whether a SLB
-	 * entry exists if it does not start to overflow.
-	 */
-	if (ti->slb_preload_nr + 2 > SLB_PRELOAD_NR)
-		return;
-
-	hard_irq_disable();
-
-	/*
-	 * We have no good place to clear the slb preload cache on exec,
-	 * flush_thread is about the earliest arch hook but that happens
-	 * after we switch to the mm and have already preloaded the SLBEs.
-	 *
-	 * For the most part that's probably okay to use entries from the
-	 * previous exec, they will age out if unused. It may turn out to
-	 * be an advantage to clear the cache before switching to it,
-	 * however.
-	 */
-
-	/*
-	 * preload some userspace segments into the SLB.
-	 * Almost all 32 and 64bit PowerPC executables are linked at
-	 * 0x10000000 so it makes sense to preload this segment.
-	 */
-	if (!is_kernel_addr(exec)) {
-		if (preload_add(ti, exec))
-			slb_allocate_user(mm, exec);
-	}
-
-	/* Libraries and mmaps. */
-	if (!is_kernel_addr(mm->mmap_base)) {
-		if (preload_add(ti, mm->mmap_base))
-			slb_allocate_user(mm, mm->mmap_base);
-	}
-
-	/* see switch_slb */
-	asm volatile("isync" : : : "memory");
-
-	local_irq_enable();
-}
-
-void preload_new_slb_context(unsigned long start, unsigned long sp)
-{
-	struct thread_info *ti = current_thread_info();
-	struct mm_struct *mm = current->mm;
-	unsigned long heap = mm->start_brk;
-
-	WARN_ON(irqs_disabled());
-
-	/* see above */
-	if (ti->slb_preload_nr + 3 > SLB_PRELOAD_NR)
-		return;
-
-	hard_irq_disable();
-
-	/* Userspace entry address. */
-	if (!is_kernel_addr(start)) {
-		if (preload_add(ti, start))
-			slb_allocate_user(mm, start);
-	}
-
-	/* Top of stack, grows down. */
-	if (!is_kernel_addr(sp)) {
-		if (preload_add(ti, sp))
-			slb_allocate_user(mm, sp);
-	}
-
-	/* Bottom of heap, grows up. */
-	if (heap && !is_kernel_addr(heap)) {
-		if (preload_add(ti, heap))
-			slb_allocate_user(mm, heap);
-	}
-
-	/* see switch_slb */
-	asm volatile("isync" : : : "memory");
-
-	local_irq_enable();
-}
-
 static void slb_cache_slbie_kernel(unsigned int index)
 {
 	unsigned long slbie_data = get_paca()->slb_cache[index];
@@ -502,6 +424,9 @@ void switch_slb(struct task_struct *tsk, struct mm_struct *mm)
 
 	copy_mm_to_paca(mm);
 
+	if (slb_preload_disabled())
+		return;
+
 	/*
 	 * We gradually age out SLBs after a number of context switches to
 	 * reduce reload overhead of unused entries (like we do with FP/VEC
diff --git a/arch/powerpc/mm/ptdump/8xx.c b/arch/powerpc/mm/ptdump/8xx.c
index 4ca9cf7a90c9..ff845f251724 100644
--- a/arch/powerpc/mm/ptdump/8xx.c
+++ b/arch/powerpc/mm/ptdump/8xx.c
@@ -71,18 +71,23 @@ static const struct flag_info flag_array[] = {
 
 struct ptdump_pg_level pg_level[5] = {
 	{ /* pgd */
+		.name	= "PGD",
 		.flag	= flag_array,
 		.num	= ARRAY_SIZE(flag_array),
 	}, { /* p4d */
+		.name	= "P4D",
 		.flag	= flag_array,
 		.num	= ARRAY_SIZE(flag_array),
 	}, { /* pud */
+		.name	= "PUD",
 		.flag	= flag_array,
 		.num	= ARRAY_SIZE(flag_array),
 	}, { /* pmd */
+		.name	= "PMD",
 		.flag	= flag_array,
 		.num	= ARRAY_SIZE(flag_array),
 	}, { /* pte */
+		.name	= "PTE",
 		.flag	= flag_array,
 		.num	= ARRAY_SIZE(flag_array),
 	},
diff --git a/arch/powerpc/mm/ptdump/book3s64.c b/arch/powerpc/mm/ptdump/book3s64.c
index 6b2da9241d4c..e8a21c6dc32e 100644
--- a/arch/powerpc/mm/ptdump/book3s64.c
+++ b/arch/powerpc/mm/ptdump/book3s64.c
@@ -104,18 +104,23 @@ static const struct flag_info flag_array[] = {
 
 struct ptdump_pg_level pg_level[5] = {
 	{ /* pgd */
+		.name	= "PGD",
 		.flag	= flag_array,
 		.num	= ARRAY_SIZE(flag_array),
 	}, { /* p4d */
+		.name	= "P4D",
 		.flag	= flag_array,
 		.num	= ARRAY_SIZE(flag_array),
 	}, { /* pud */
+		.name	= "PUD",
 		.flag	= flag_array,
 		.num	= ARRAY_SIZE(flag_array),
 	}, { /* pmd */
+		.name	= "PMD",
 		.flag	= flag_array,
 		.num	= ARRAY_SIZE(flag_array),
 	}, { /* pte */
+		.name	= "PTE",
 		.flag	= flag_array,
 		.num	= ARRAY_SIZE(flag_array),
 	},
diff --git a/arch/powerpc/mm/ptdump/hashpagetable.c b/arch/powerpc/mm/ptdump/hashpagetable.c
index a6baa6166d94..671d0dc00c6d 100644
--- a/arch/powerpc/mm/ptdump/hashpagetable.c
+++ b/arch/powerpc/mm/ptdump/hashpagetable.c
@@ -216,6 +216,8 @@ static int native_find(unsigned long ea, int psize, bool primary, u64 *v, u64
 	vpn  = hpt_vpn(ea, vsid, ssize);
 	hash = hpt_hash(vpn, shift, ssize);
 	want_v = hpte_encode_avpn(vpn, psize, ssize);
+	if (cpu_has_feature(CPU_FTR_ARCH_300))
+		want_v = hpte_old_to_new_v(want_v);
 
 	/* to check in the secondary hash table, we invert the hash */
 	if (!primary)
@@ -229,6 +231,10 @@ static int native_find(unsigned long ea, int psize, bool primary, u64 *v, u64
 			/* HPTE matches */
 			*v = be64_to_cpu(hptep->v);
 			*r = be64_to_cpu(hptep->r);
+			if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+				*v = hpte_new_to_old_v(*v, *r);
+				*r = hpte_new_to_old_r(*r);
+			}
 			return 0;
 		}
 		++hpte_group;
diff --git a/arch/powerpc/mm/ptdump/ptdump.c b/arch/powerpc/mm/ptdump/ptdump.c
index b2358d794855..0d499aebee72 100644
--- a/arch/powerpc/mm/ptdump/ptdump.c
+++ b/arch/powerpc/mm/ptdump/ptdump.c
@@ -178,6 +178,7 @@ static void dump_addr(struct pg_state *st, unsigned long addr)
 	pt_dump_seq_printf(st->seq, REG "-" REG " ", st->start_address, addr - 1);
 	pt_dump_seq_printf(st->seq, " " REG " ", st->start_pa);
 	pt_dump_size(st->seq, addr - st->start_address);
+	pt_dump_seq_printf(st->seq, "%s ", pg_level[st->level].name);
 }
 
 static void note_prot_wx(struct pg_state *st, unsigned long addr)
diff --git a/arch/powerpc/mm/ptdump/ptdump.h b/arch/powerpc/mm/ptdump/ptdump.h
index 4232aa4b57ea..12aa9eca8b0c 100644
--- a/arch/powerpc/mm/ptdump/ptdump.h
+++ b/arch/powerpc/mm/ptdump/ptdump.h
@@ -13,6 +13,7 @@ struct flag_info {
 
 struct ptdump_pg_level {
 	const struct flag_info *flag;
+	char name[4];
 	size_t num;
 	u64 mask;
 };
diff --git a/arch/powerpc/mm/ptdump/shared.c b/arch/powerpc/mm/ptdump/shared.c
index 58998960eb9a..edc69da19b85 100644
--- a/arch/powerpc/mm/ptdump/shared.c
+++ b/arch/powerpc/mm/ptdump/shared.c
@@ -69,18 +69,23 @@ static const struct flag_info flag_array[] = {
 
 struct ptdump_pg_level pg_level[5] = {
 	{ /* pgd */
+		.name	= "PGD",
 		.flag	= flag_array,
 		.num	= ARRAY_SIZE(flag_array),
 	}, { /* p4d */
+		.name	= "P4D",
 		.flag	= flag_array,
 		.num	= ARRAY_SIZE(flag_array),
 	}, { /* pud */
+		.name	= "PUD",
 		.flag	= flag_array,
 		.num	= ARRAY_SIZE(flag_array),
 	}, { /* pmd */
+		.name	= "PMD",
 		.flag	= flag_array,
 		.num	= ARRAY_SIZE(flag_array),
 	}, { /* pte */
+		.name	= "PTE",
 		.flag	= flag_array,
 		.num	= ARRAY_SIZE(flag_array),
 	},
diff --git a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
index cb7b9498f291..80d944f29288 100644
--- a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
+++ b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
@@ -123,6 +123,8 @@ static int mcu_gpiochip_add(struct mcu *mcu)
 
 	gc->owner = THIS_MODULE;
 	gc->label = kasprintf(GFP_KERNEL, "%pfw", dev_fwnode(dev));
+	if (!gc->label)
+		return -ENOMEM;
 	gc->can_sleep = 1;
 	gc->ngpio = MCU_NUM_GPIO;
 	gc->base = -1;
diff --git a/arch/powerpc/platforms/powermac/backlight.c b/arch/powerpc/platforms/powermac/backlight.c
index 79741370c40c..1796327955c6 100644
--- a/arch/powerpc/platforms/powermac/backlight.c
+++ b/arch/powerpc/platforms/powermac/backlight.c
@@ -11,6 +11,7 @@
 #include <linux/kernel.h>
 #include <linux/backlight.h>
 #include <linux/adb.h>
+#include <linux/of.h>
 #include <linux/pmu.h>
 #include <linux/atomic.h>
 #include <linux/export.h>
diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c
index cc22924f159f..6554537984fb 100644
--- a/arch/powerpc/platforms/pseries/lparcfg.c
+++ b/arch/powerpc/platforms/pseries/lparcfg.c
@@ -78,6 +78,8 @@ struct hvcall_ppp_data {
 	u8	capped;
 	u8	weight;
 	u8	unallocated_weight;
+	u8      resource_group_index;
+	u16     active_procs_in_resource_group;
 	u16	active_procs_in_pool;
 	u16	active_system_procs;
 	u16	phys_platform_procs;
@@ -86,7 +88,7 @@ struct hvcall_ppp_data {
 };
 
 /*
- * H_GET_PPP hcall returns info in 4 parms.
+ * H_GET_PPP hcall returns info in 5 parms.
  *  entitled_capacity,unallocated_capacity,
  *  aggregation, resource_capability).
  *
@@ -94,11 +96,11 @@ struct hvcall_ppp_data {
  *  R5 = Unallocated Processor Capacity Percentage.
  *  R6 (AABBCCDDEEFFGGHH).
  *      XXXX - reserved (0)
- *          XXXX - reserved (0)
+ *          XXXX - Active Cores in Resource Group
  *              XXXX - Group Number
  *                  XXXX - Pool Number.
  *  R7 (IIJJKKLLMMNNOOPP).
- *      XX - reserved. (0)
+ *      XX - Resource group Number
  *        XX - bit 0-6 reserved (0).   bit 7 is Capped indicator.
  *          XX - variable processor Capacity Weight
  *            XX - Unallocated Variable Processor Capacity Weight.
@@ -120,9 +122,11 @@ static unsigned int h_get_ppp(struct hvcall_ppp_data *ppp_data)
 	ppp_data->entitlement = retbuf[0];
 	ppp_data->unallocated_entitlement = retbuf[1];
 
+	ppp_data->active_procs_in_resource_group = (retbuf[2] >> 4 * 8) & 0xffff;
 	ppp_data->group_num = (retbuf[2] >> 2 * 8) & 0xffff;
 	ppp_data->pool_num = retbuf[2] & 0xffff;
 
+	ppp_data->resource_group_index = (retbuf[3] >> 7 *  8) & 0xff;
 	ppp_data->capped = (retbuf[3] >> 6 * 8) & 0x01;
 	ppp_data->weight = (retbuf[3] >> 5 * 8) & 0xff;
 	ppp_data->unallocated_weight = (retbuf[3] >> 4 * 8) & 0xff;
@@ -236,6 +240,13 @@ static void parse_ppp_data(struct seq_file *m)
 	seq_printf(m, "unallocated_capacity=%lld\n",
 		   ppp_data.unallocated_entitlement);
 
+	if (ppp_data.active_procs_in_resource_group)  {
+		seq_printf(m, "resource_group_number=%d\n",
+				ppp_data.resource_group_index);
+		seq_printf(m, "resource_group_active_processors=%d\n",
+				ppp_data.active_procs_in_resource_group);
+	}
+
 	/* The last bits of information returned from h_get_ppp are only
 	 * valid if the ibm,partition-performance-parameters-level
 	 * property is >= 1.
diff --git a/arch/powerpc/tools/head_check.sh b/arch/powerpc/tools/head_check.sh
index 689907cda996..a9cd06958921 100644
--- a/arch/powerpc/tools/head_check.sh
+++ b/arch/powerpc/tools/head_check.sh
@@ -1,3 +1,4 @@
+#!/bin/sh
 # Copyright © 2016 IBM Corporation
 
 # This program is free software; you can redistribute it and/or
diff --git a/drivers/macintosh/mac_hid.c b/drivers/macintosh/mac_hid.c
index 369d72f59b3c..06fd910b3fd1 100644
--- a/drivers/macintosh/mac_hid.c
+++ b/drivers/macintosh/mac_hid.c
@@ -187,13 +187,14 @@ static int mac_hid_toggle_emumouse(const struct ctl_table *table, int write,
 				   void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int *valp = table->data;
-	int old_val = *valp;
+	int old_val;
 	int rc;
 
 	rc = mutex_lock_killable(&mac_hid_emumouse_mutex);
 	if (rc)
 		return rc;
 
+	old_val = *valp;
 	rc = proc_dointvec(table, write, buffer, lenp, ppos);
 
 	if (rc == 0 && write && *valp != old_val) {
diff --git a/drivers/macintosh/via-pmu-backlight.c b/drivers/macintosh/via-pmu-backlight.c
index 26bd9ed5e664..d91825bb0a5c 100644
--- a/drivers/macintosh/via-pmu-backlight.c
+++ b/drivers/macintosh/via-pmu-backlight.c
@@ -11,6 +11,8 @@
 #include <asm/ptrace.h>
 #include <linux/adb.h>
 #include <linux/backlight.h>
+#include <linux/fb.h>
+#include <linux/of.h>
 #include <linux/pmu.h>
 #include <asm/backlight.h>