Merge branch 'perf' of github.com:itsshashanksp/kernel_xiaomi_sm6150 …

…into perf-ksu

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 4
 PATCHLEVEL = 14
-SUBLEVEL = 328
+SUBLEVEL = 331
 EXTRAVERSION =
 NAME = Petit Gorille
 

arch/arm/boot/bootp/init.S

@@ -16,7 +16,7 @@
  *  size immediately following the kernel, we could build this into
  *  a binary blob, and concatenate the zImage using the cat command.
  */
-		.section .start,#alloc,#execinstr
+		.section .start, "ax"
 		.type	_start, #function
 		.globl	_start
 

arch/arm/boot/compressed/big-endian.S

@@ -6,7 +6,7 @@
  *  Author: Nicolas Pitre
  */
 
-	.section ".start", #alloc, #execinstr
+	.section ".start", "ax"
 
 	mrc	p15, 0, r0, c1, c0, 0	@ read control reg
 	orr	r0, r0, #(1 << 7)	@ enable big endian mode

arch/arm/boot/compressed/head.S

@@ -114,7 +114,7 @@
 #endif
 		.endm
 
-		.section ".start", #alloc, #execinstr
+		.section ".start", "ax"
 /*
  * sort out different calling conventions
  */

arch/arm/boot/compressed/piggy.S

@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-	.section .piggydata,#alloc
+	.section .piggydata, "a"
 	.globl	input_data
 input_data:
 	.incbin	"arch/arm/boot/compressed/piggy_data"

arch/arm/boot/dts/qcom-mdm9615.dtsi

@@ -82,14 +82,12 @@
 		};
 	};
 
-	regulators {
-		vsdcc_fixed: vsdcc-regulator {
-			compatible = "regulator-fixed";
-			regulator-name = "SDCC Power";
-			regulator-min-microvolt = <2700000>;
-			regulator-max-microvolt = <2700000>;
-			regulator-always-on;
-		};
+	vsdcc_fixed: vsdcc-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "SDCC Power";
+		regulator-min-microvolt = <2700000>;
+		regulator-max-microvolt = <2700000>;
+		regulator-always-on;
 	};
 
 	soc: soc {

arch/arm/lib/memset.S

@@ -19,6 +19,7 @@
 ENTRY(mmioset)
 ENTRY(memset)
 UNWIND( .fnstart         )
+	and	r1, r1, #255		@ cast to unsigned char
 	ands	r3, r0, #3		@ 1 unaligned?
 	mov	ip, r0			@ preserve r0 as return value
 	bne	6f			@ 1

arch/arm/mm/proc-arm1020.S

@@ -505,7 +505,7 @@ cpu_arm1020_name:
 
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 
 	.type	__arm1020_proc_info,#object
 __arm1020_proc_info:

arch/arm/mm/proc-arm1020e.S

@@ -463,7 +463,7 @@ arm1020e_crval:
 
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 
 	.type	__arm1020e_proc_info,#object
 __arm1020e_proc_info:

arch/arm/mm/proc-arm1022.S

@@ -448,7 +448,7 @@ arm1022_crval:
 
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 
 	.type	__arm1022_proc_info,#object
 __arm1022_proc_info:

arch/arm/mm/proc-arm1026.S

@@ -442,7 +442,7 @@ arm1026_crval:
 	string	cpu_arm1026_name, "ARM1026EJ-S"
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 
 	.type	__arm1026_proc_info,#object
 __arm1026_proc_info:

arch/arm/mm/proc-arm720.S

@@ -186,7 +186,7 @@ arm720_crval:
  * See <asm/procinfo.h> for a definition of this structure.
  */
 
-		.section ".proc.info.init", #alloc
+		.section ".proc.info.init", "a"
 
 .macro arm720_proc_info name:req, cpu_val:req, cpu_mask:req, cpu_name:req, cpu_flush:req
 		.type	__\name\()_proc_info,#object

arch/arm/mm/proc-arm740.S

@@ -132,7 +132,7 @@ __arm740_setup:
 
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 	.type	__arm740_proc_info,#object
 __arm740_proc_info:
 	.long	0x41807400

arch/arm/mm/proc-arm7tdmi.S

@@ -76,7 +76,7 @@ __arm7tdmi_setup:
 
 		.align
 
-		.section ".proc.info.init", #alloc
+		.section ".proc.info.init", "a"
 
 .macro arm7tdmi_proc_info name:req, cpu_val:req, cpu_mask:req, cpu_name:req, \
 	extra_hwcaps=0

arch/arm/mm/proc-arm920.S

@@ -448,7 +448,7 @@ arm920_crval:
 
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 
 	.type	__arm920_proc_info,#object
 __arm920_proc_info:

arch/arm/mm/proc-arm922.S

@@ -426,7 +426,7 @@ arm922_crval:
 
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 
 	.type	__arm922_proc_info,#object
 __arm922_proc_info:

arch/arm/mm/proc-arm925.S

@@ -491,7 +491,7 @@ arm925_crval:
 
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 
 .macro arm925_proc_info name:req, cpu_val:req, cpu_mask:req, cpu_name:req, cache
 	.type	__\name\()_proc_info,#object

arch/arm/mm/proc-arm926.S

@@ -474,7 +474,7 @@ arm926_crval:
 
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 
 	.type	__arm926_proc_info,#object
 __arm926_proc_info:

arch/arm/mm/proc-arm940.S

@@ -344,7 +344,7 @@ __arm940_setup:
 
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 
 	.type	__arm940_proc_info,#object
 __arm940_proc_info:

arch/arm/mm/proc-arm946.S

@@ -399,7 +399,7 @@ __arm946_setup:
 
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 	.type	__arm946_proc_info,#object
 __arm946_proc_info:
 	.long	0x41009460

arch/arm/mm/proc-arm9tdmi.S

@@ -70,7 +70,7 @@ __arm9tdmi_setup:
 
 		.align
 
-		.section ".proc.info.init", #alloc
+		.section ".proc.info.init", "a"
 
 .macro arm9tdmi_proc_info name:req, cpu_val:req, cpu_mask:req, cpu_name:req
 		.type	__\name\()_proc_info, #object

arch/arm/mm/proc-fa526.S

@@ -190,7 +190,7 @@ fa526_cr1_set:
 
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 
 	.type	__fa526_proc_info,#object
 __fa526_proc_info:

arch/arm/mm/proc-feroceon.S

@@ -584,7 +584,7 @@ feroceon_crval:
 
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 
 .macro feroceon_proc_info name:req, cpu_val:req, cpu_mask:req, cpu_name:req, cache:req
 	.type	__\name\()_proc_info,#object

arch/arm/mm/proc-mohawk.S

@@ -429,7 +429,7 @@ mohawk_crval:
 
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 
 	.type	__88sv331x_proc_info,#object
 __88sv331x_proc_info:

arch/arm/mm/proc-sa110.S

@@ -199,7 +199,7 @@ sa110_crval:
 
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 
 	.type	__sa110_proc_info,#object
 __sa110_proc_info:

arch/arm/mm/proc-sa1100.S

@@ -242,7 +242,7 @@ sa1100_crval:
 
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 
 .macro sa1100_proc_info name:req, cpu_val:req, cpu_mask:req, cpu_name:req
 	.type	__\name\()_proc_info,#object

arch/arm/mm/proc-v6.S

@@ -264,7 +264,7 @@ v6_crval:
 	string	cpu_elf_name, "v6"
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 
 	/*
 	 * Match any ARMv6 processor core.

arch/arm/mm/proc-v7.S

@@ -637,7 +637,7 @@ __v7_setup_stack:
 	string	cpu_elf_name, "v7"
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 
 	/*
 	 * Standard v7 proc info content

arch/arm/mm/proc-v7m.S

@@ -96,7 +96,7 @@ ENTRY(cpu_cm7_proc_fin)
 	ret	lr
 ENDPROC(cpu_cm7_proc_fin)
 
-	.section ".init.text", #alloc, #execinstr
+	.section ".init.text", "ax"
 
 __v7m_cm7_setup:
 	mov	r8, #(V7M_SCB_CCR_DC | V7M_SCB_CCR_IC| V7M_SCB_CCR_BP)
@@ -181,7 +181,7 @@ ENDPROC(__v7m_setup)
 	string cpu_elf_name "v7m"
 	string cpu_v7m_name "ARMv7-M"
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 
 .macro __v7m_proc name, initfunc, cache_fns = nop_cache_fns, hwcaps = 0,  proc_fns = v7m_processor_functions
 	.long	0			/* proc_info_list.__cpu_mm_mmu_flags */

arch/arm/mm/proc-xsc3.S

@@ -499,7 +499,7 @@ xsc3_crval:
 
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 
 .macro xsc3_proc_info name:req, cpu_val:req, cpu_mask:req
 	.type	__\name\()_proc_info,#object

arch/arm/mm/proc-xscale.S

@@ -613,7 +613,7 @@ xscale_crval:
 
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 
 .macro xscale_proc_info name:req, cpu_val:req, cpu_mask:req, cpu_name:req, cache
 	.type	__\name\()_proc_info,#object

arch/parisc/kernel/entry.S

@@ -521,22 +521,21 @@
 	 * to a CPU TLB 4k PFN (4k => 12 bits to shift) */
 	#define PAGE_ADD_SHIFT		(PAGE_SHIFT-12)
 	#define PAGE_ADD_HUGE_SHIFT	(REAL_HPAGE_SHIFT-12)
+	#define PFN_START_BIT	(63-ASM_PFN_PTE_SHIFT+(63-58)-PAGE_ADD_SHIFT)
 
 	/* Drop prot bits and convert to page addr for iitlbt and idtlbt */
 	.macro		convert_for_tlb_insert20 pte,tmp
 #ifdef CONFIG_HUGETLB_PAGE
 	copy		\pte,\tmp
-	extrd,u		\tmp,(63-ASM_PFN_PTE_SHIFT)+(63-58)+PAGE_ADD_SHIFT,\
-				64-PAGE_SHIFT-PAGE_ADD_SHIFT,\pte
+	extrd,u		\tmp,PFN_START_BIT,PFN_START_BIT+1,\pte
 
 	depdi		_PAGE_SIZE_ENCODING_DEFAULT,63,\
 				(63-58)+PAGE_ADD_SHIFT,\pte
 	extrd,u,*=	\tmp,_PAGE_HPAGE_BIT+32,1,%r0
 	depdi		_HUGE_PAGE_SIZE_ENCODING_DEFAULT,63,\
 				(63-58)+PAGE_ADD_HUGE_SHIFT,\pte
 #else /* Huge pages disabled */
-	extrd,u		\pte,(63-ASM_PFN_PTE_SHIFT)+(63-58)+PAGE_ADD_SHIFT,\
-				64-PAGE_SHIFT-PAGE_ADD_SHIFT,\pte
+	extrd,u		\pte,PFN_START_BIT,PFN_START_BIT+1,\pte
 	depdi		_PAGE_SIZE_ENCODING_DEFAULT,63,\
 				(63-58)+PAGE_ADD_SHIFT,\pte
 #endif

arch/parisc/kernel/head.S

@@ -69,9 +69,8 @@ $bss_loop:
 	stw,ma          %arg2,4(%r1)
 	stw,ma          %arg3,4(%r1)
 
-#if !defined(CONFIG_64BIT) && defined(CONFIG_PA20)
-	/* This 32-bit kernel was compiled for PA2.0 CPUs. Check current CPU
-	 * and halt kernel if we detect a PA1.x CPU. */
+#if defined(CONFIG_PA20)
+	/* check for 64-bit capable CPU as required by current kernel */
 	ldi		32,%r10
 	mtctl		%r10,%cr11
 	.level 2.0
@@ -84,7 +83,7 @@ $bss_loop:
 $iodc_panic:
 	copy		%arg0, %r10
 	copy		%arg1, %r11
-	load32		PA(init_stack),%sp
+	load32		PA(__bss_stop),%sp
 #define MEM_CONS 0x3A0
 	ldw		MEM_CONS+32(%r0),%arg0	// HPA
 	ldi		ENTRY_IO_COUT,%arg1

arch/sh/Kconfig.debug

@@ -29,6 +29,17 @@ config STACK_DEBUG
 	  every function call and will therefore incur a major
 	  performance hit. Most users should say N.
 
+config EARLY_PRINTK
+	bool "Early printk"
+	depends on SH_STANDARD_BIOS
+	help
+	  Say Y here to redirect kernel printk messages to the serial port
+	  used by the SH-IPL bootloader, starting very early in the boot
+	  process and ending when the kernel's serial console is initialised.
+	  This option is only useful while porting the kernel to a new machine,
+	  when the kernel may crash or hang before the serial console is
+	  initialised.  If unsure, say N.
+
 config 4KSTACKS
 	bool "Use 4Kb for kernel stacks instead of 8Kb"
 	depends on DEBUG_KERNEL && (MMU || BROKEN) && !PAGE_SIZE_64KB

arch/x86/include/asm/i8259.h

@@ -67,6 +67,8 @@ struct legacy_pic {
 	void (*make_irq)(unsigned int irq);
 };
 
+void legacy_pic_pcat_compat(void);
+
 extern struct legacy_pic *legacy_pic;
 extern struct legacy_pic null_legacy_pic;
 

arch/x86/include/asm/msr-index.h

@@ -414,6 +414,7 @@
 #define MSR_AMD64_OSVW_STATUS		0xc0010141
 #define MSR_AMD64_LS_CFG		0xc0011020
 #define MSR_AMD64_DC_CFG		0xc0011022
+#define MSR_AMD64_TW_CFG		0xc0011023
 
 #define MSR_AMD64_DE_CFG		0xc0011029
 #define MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT	 1

arch/x86/include/asm/numa.h

@@ -11,13 +11,6 @@
 
 #define NR_NODE_MEMBLKS		(MAX_NUMNODES*2)
 
-/*
- * Too small node sizes may confuse the VM badly. Usually they
- * result from BIOS bugs. So dont recognize nodes as standalone
- * NUMA entities that have less than this amount of RAM listed:
- */
-#define NODE_MIN_SIZE (4*1024*1024)
-
 extern int numa_off;
 
 /*