dma: Automatically enable page touching on Caspian

Documentation/ABI/testing/sysfs-class-bdi

@@ -55,6 +55,17 @@ Description:
 	mount that is prone to get stuck, or a FUSE mount which cannot
 	be trusted to play fair.
 
+	(read-write)
+What:		/sys/class/bdi/<bdi>/strict_limit
+Date:		October 2022
+Contact:	Stefan Roesch <shr@devkernel.io>
+Description:
+	Forces per-BDI checks for the share of given device in the write-back
+	cache even before the global background dirty limit is reached. This
+	is useful in situations where the global limit is much higher than
+	affordable for given relatively slow (or untrusted) device. Turning
+	strictlimit on has no visible effect if max_ratio is equal to 100%.
+
 	(read-write)
 What:		/sys/class/bdi/<bdi>/stable_pages_required
 Date:		January 2008

Documentation/admin-guide/kernel-parameters.txt

@@ -554,6 +554,10 @@
 			named mounts. Specifying both "all" and "named" disables
 			all v1 hierarchies.
 
+	cgroup_favordynmods= [KNL] Enable or Disable favordynmods.
+			Format: { "true" | "false" }
+			Defaults to the value of CONFIG_CGROUP_FAVOR_DYNMODS.
+
 	cgroup.memory=	[KNL] Pass options to the cgroup memory controller.
 			Format: <string>
 			nosocket -- Disable socket memory accounting.
@@ -669,7 +673,7 @@
 			kernel/dma/contiguous.c
 
 	cma_pernuma=nn[MG]
-			[ARM64,KNL,CMA]
+			[KNL,CMA]
 			Sets the size of kernel per-numa memory area for
 			contiguous memory allocations. A value of 0 disables
 			per-numa CMA altogether. And If this option is not
@@ -679,6 +683,17 @@
 			which is located in node nid, if the allocation fails,
 			they will fallback to the global default memory area.
 
+	numa_cma=<node>:nn[MG][,<node>:nn[MG]]
+			[KNL,CMA]
+			Sets the size of kernel numa memory area for
+			contiguous memory allocations. It will reserve CMA
+			area for the specified node.
+
+			With numa CMA enabled, DMA users on node nid will
+			first try to allocate buffer from the numa area
+			which is located in node nid, if the allocation fails,
+			they will fallback to the global default memory area.
+
 	cmo_free_hint=	[PPC] Format: { yes | no }
 			Specify whether pages are marked as being inactive
 			when they are freed.  This is used in CMO environments

MAINTAINERS

@@ -15577,6 +15577,13 @@ F:	Documentation/mm/page_table_check.rst
 F:	include/linux/page_table_check.h
 F:	mm/page_table_check.c
 
+PAGE TOUCHING DMA
+M:	James Gowans <jgowans@amazon.com>
+L:	ec2-memo@amazon.com
+S:	Supported
+F:	include/linux/dma-page-touching.h
+F:	kernel/dma/page_touching.c
+
 PANASONIC LAPTOP ACPI EXTRAS DRIVER
 M:	Kenneth Chan <kenneth.t.chan@gmail.com>
 L:	platform-driver-x86@vger.kernel.org

arch/arm64/Kconfig

@@ -180,8 +180,10 @@ config ARM64
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_DYNAMIC_FTRACE
+	select HAVE_DYNAMIC_FTRACE_WITH_ARGS
 	select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY \
 		if DYNAMIC_FTRACE_WITH_REGS
+	select HAVE_RELIABLE_STACKTRACE
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
 	select HAVE_FAST_GUP
 	select HAVE_FTRACE_MCOUNT_RECORD
@@ -193,6 +195,7 @@ config ARM64
 	select HAVE_IOREMAP_PROT
 	select HAVE_IRQ_TIME_ACCOUNTING
 	select HAVE_KVM
+	select HAVE_LIVEPATCH
 	select HAVE_NMI
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
@@ -204,6 +207,8 @@ config ARM64
 	select MMU_GATHER_RCU_TABLE_FREE
 	select HAVE_RSEQ
 	select HAVE_STACKPROTECTOR
+	select HAVE_OBJTOOL
+	select HAVE_STACK_VALIDATION
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_KPROBES
 	select HAVE_KRETPROBES
@@ -328,6 +333,24 @@ config GENERIC_CALIBRATE_DELAY
 config ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
 	def_bool y
 
+config ARCH_MEMORY_PROBE
+	bool "Enable /sys/devices/system/memory/probe interface"
+	depends on MEMORY_HOTPLUG
+	help
+	  This option enables a sysfs /sys/devices/system/memory/probe
+	  interface for testing. See Documentation/memory-hotplug.txt
+	  for more information. If you are unsure how to answer this
+	  question, answer N.
+
+config ARCH_MEMORY_REMOVE
+	bool "Enable /sys/devices/system/memory/remove interface"
+	depends on MEMORY_HOTREMOVE
+	help
+	   This option enables a sysfs /sys/devices/system/memory/remove
+	   interface for testing. See Documentation/memory-hotplug.txt
+	   for more information. If you are unsure how to answer this
+	   question, answer N.
+
 config SMP
 	def_bool y
 
@@ -2304,3 +2327,4 @@ source "drivers/acpi/Kconfig"
 
 source "arch/arm64/kvm/Kconfig"
 
+source "kernel/livepatch/Kconfig"

arch/arm64/Kconfig.debug

@@ -20,4 +20,25 @@ config ARM64_RELOC_TEST
 	depends on m
 	tristate "Relocation testing module"
 
+choice
+    prompt "Choose kernel unwinder"
+    default UNWINDER_FRAME_POINTER
+    help
+      This determines which method will be used for unwinding kernel stack
+      traces for panics, oopses, bugs, warnings, perf, /proc/<pid>/stack,
+      livepatch, lockdep, and more.
+
+config UNWINDER_FRAME_POINTER
+    bool "Frame pointer unwinder"
+    select FRAME_POINTER
+    help
+      This option enables the frame pointer unwinder for unwinding kernel
+      stack traces.
+
+      The unwinder itself is fast and it uses less RAM than the ORC
+      unwinder, but the kernel text size will grow by ~3% and the kernel's
+      overall performance will degrade by roughly 5-10%.
+
+endchoice
+
 source "drivers/hwtracing/coresight/Kconfig"

arch/arm64/Makefile

@@ -63,20 +63,19 @@ ifeq ($(CONFIG_AS_HAS_ARMV8_2), y)
 asm-arch := armv8.2-a
 endif
 
-# Ensure that if the compiler supports branch protection we default it
-# off, this will be overridden if we are using branch protection.
-branch-prot-flags-y += $(call cc-option,-mbranch-protection=none)
-
-ifeq ($(CONFIG_ARM64_PTR_AUTH_KERNEL),y)
-branch-prot-flags-$(CONFIG_CC_HAS_SIGN_RETURN_ADDRESS) := -msign-return-address=all
-# We enable additional protection for leaf functions as there is some
-# narrow potential for ROP protection benefits and no substantial
-# performance impact has been observed.
 ifeq ($(CONFIG_ARM64_BTI_KERNEL),y)
-branch-prot-flags-$(CONFIG_CC_HAS_BRANCH_PROT_PAC_RET_BTI) := -mbranch-protection=pac-ret+leaf+bti
+  KBUILD_CFLAGS += -mbranch-protection=pac-ret+bti
+else ifeq ($(CONFIG_ARM64_PTR_AUTH_KERNEL),y)
+  ifeq ($(CONFIG_CC_HAS_BRANCH_PROT_PAC_RET),y)
+    KBUILD_CFLAGS += -mbranch-protection=pac-ret
+  else
+    KBUILD_CFLAGS += -msign-return-address=non-leaf
+  endif
 else
-branch-prot-flags-$(CONFIG_CC_HAS_BRANCH_PROT_PAC_RET) := -mbranch-protection=pac-ret+leaf
+  KBUILD_CFLAGS += $(call cc-option,-mbranch-protection=none)
 endif
+
+ifeq ($(CONFIG_ARM64_PTR_AUTH_KERNEL),y)
 # -march=armv8.3-a enables the non-nops instructions for PAC, to avoid the
 # compiler to generate them and consequently to break the single image contract
 # we pass it only to the assembler. This option is utilized only in case of non
@@ -86,8 +85,6 @@ asm-arch := armv8.3-a
 endif
 endif
 
-KBUILD_CFLAGS += $(branch-prot-flags-y)
-
 ifeq ($(CONFIG_AS_HAS_ARMV8_4), y)
 # make sure to pass the newest target architecture to -march.
 asm-arch := armv8.4-a
@@ -133,6 +130,10 @@ ifeq ($(CONFIG_DYNAMIC_FTRACE_WITH_REGS),y)
   CC_FLAGS_FTRACE := -fpatchable-function-entry=2
 endif
 
+ifeq ($(CONFIG_STACK_VALIDATION),y)
+KBUILD_CFLAGS	+= -fno-jump-tables
+endif
+
 ifeq ($(CONFIG_KASAN_SW_TAGS), y)
 KASAN_SHADOW_SCALE_SHIFT := 4
 else ifeq ($(CONFIG_KASAN_GENERIC), y)

arch/arm64/crypto/aes-neonbs-core.S

@@ -368,15 +368,15 @@
 
 
 	.align		6
-M0:	.octa		0x0004080c0105090d02060a0e03070b0f
+SYM_DATA_LOCAL(M0,	.octa		0x0004080c0105090d02060a0e03070b0f)
 
-M0SR:	.octa		0x0004080c05090d010a0e02060f03070b
-SR:	.octa		0x0f0e0d0c0a09080b0504070600030201
-SRM0:	.octa		0x01060b0c0207080d0304090e00050a0f
+SYM_DATA_LOCAL(M0SR,	.octa		0x0004080c05090d010a0e02060f03070b)
+SYM_DATA_LOCAL(SR,	.octa		0x0f0e0d0c0a09080b0504070600030201)
+SYM_DATA_LOCAL(SRM0,	.octa		0x01060b0c0207080d0304090e00050a0f)
 
-M0ISR:	.octa		0x0004080c0d0105090a0e0206070b0f03
-ISR:	.octa		0x0f0e0d0c080b0a090504070602010003
-ISRM0:	.octa		0x0306090c00070a0d01040b0e0205080f
+SYM_DATA_LOCAL(M0ISR,	.octa		0x0004080c0d0105090a0e0206070b0f03)
+SYM_DATA_LOCAL(ISR,	.octa		0x0f0e0d0c080b0a090504070602010003)
+SYM_DATA_LOCAL(ISRM0,	.octa		0x0306090c00070a0d01040b0e0205080f)
 
 	/*
 	 * void aesbs_convert_key(u8 out[], u32 const rk[], int rounds)

arch/arm64/crypto/crct10dif-ce-core.S

@@ -63,6 +63,7 @@
 //
 
 #include <linux/linkage.h>
+#include <linux/objtool.h>
 #include <asm/assembler.h>
 
 	.text
@@ -132,6 +133,8 @@
 	.endm
 
 SYM_FUNC_START_LOCAL(__pmull_p8_core)
+	stp		x29, x30, [sp, #-16]!
+	mov		x29, sp
 .L__pmull_p8_core:
 	ext		t4.8b, ad.8b, ad.8b, #1			// A1
 	ext		t5.8b, ad.8b, ad.8b, #2			// A2
@@ -193,6 +196,7 @@ SYM_FUNC_START_LOCAL(__pmull_p8_core)
 
 	eor		t4.16b, t4.16b, t5.16b
 	eor		t6.16b, t6.16b, t3.16b
+	ldp		x29, x30, [sp], #16
 	ret
 SYM_FUNC_END(__pmull_p8_core)
 
@@ -207,6 +211,7 @@ SYM_FUNC_END(__pmull_p8_core)
 	pmull2		\rq\().8h, \ad\().16b, \bd\().16b	// D = A*B
 	.endif
 
+	ANNOTATE_INTRA_FUNCTION_CALL
 	bl		.L__pmull_p8_core\i
 
 	eor		\rq\().16b, \rq\().16b, t4.16b

arch/arm64/crypto/poly1305-armv8.pl

@@ -47,6 +47,8 @@
 my ($h0,$h1,$h2,$r0,$r1,$s1,$t0,$t1,$d0,$d1,$d2) = map("x$_",(4..14));
 
 $code.=<<___;
+#include <linux/linkage.h>
+
 #ifndef __KERNEL__
 # include "arm_arch.h"
 .extern	OPENSSL_armcap_P
@@ -888,8 +890,10 @@
 .align	5
 .Lzeros:
 .long	0,0,0,0,0,0,0,0
+SYM_DATA_START_LOCAL(POLY1305_str)
 .asciz	"Poly1305 for ARMv8, CRYPTOGAMS by \@dot-asm"
 .align	2
+SYM_DATA_END(POLY1305_str)
 #if !defined(__KERNEL__) && !defined(_WIN64)
 .comm	OPENSSL_armcap_P,4,4
 .hidden	OPENSSL_armcap_P

arch/arm64/crypto/sha512-armv8.pl

@@ -193,6 +193,8 @@ sub BODY_00_xx {
 }
 
 $code.=<<___;
+#include <linux/linkage.h>
+
 #ifndef	__KERNEL__
 # include "arm_arch.h"
 #endif
@@ -208,11 +210,11 @@ sub BODY_00_xx {
 $code.=<<___	if ($SZ==4);
 #ifndef	__KERNEL__
 # ifdef	__ILP32__
-	ldrsw	x16,.LOPENSSL_armcap_P
+	ldrsw	x16,OPENSSL_armcap_P_rel
 # else
-	ldr	x16,.LOPENSSL_armcap_P
+	ldr	x16,OPENSSL_armcap_P_rel
 # endif
-	adr	x17,.LOPENSSL_armcap_P
+	adr	x17,OPENSSL_armcap_P_rel
 	add	x16,x16,x17
 	ldr	w16,[x16]
 	tst	w16,#ARMV8_SHA256
@@ -237,7 +239,7 @@ sub BODY_00_xx {
 	ldp	$E,$F,[$ctx,#4*$SZ]
 	add	$num,$inp,$num,lsl#`log(16*$SZ)/log(2)`	// end of input
 	ldp	$G,$H,[$ctx,#6*$SZ]
-	adr	$Ktbl,.LK$BITS
+	adr	$Ktbl,K$BITS
 	stp	$ctx,$num,[x29,#96]
 
 .Loop:
@@ -287,8 +289,7 @@ sub BODY_00_xx {
 .size	$func,.-$func
 
 .align	6
-.type	.LK$BITS,%object
-.LK$BITS:
+SYM_DATA_START_LOCAL(K$BITS)
 ___
 $code.=<<___ if ($SZ==8);
 	.quad	0x428a2f98d728ae22,0x7137449123ef65cd
@@ -353,18 +354,21 @@ sub BODY_00_xx {
 	.long	0	//terminator
 ___
 $code.=<<___;
-.size	.LK$BITS,.-.LK$BITS
+SYM_DATA_END(K$BITS)
 #ifndef	__KERNEL__
 .align	3
-.LOPENSSL_armcap_P:
+SYM_DATA_START_LOCAL(OPENSSL_armcap_P_rel)
 # ifdef	__ILP32__
 	.long	OPENSSL_armcap_P-.
 # else
 	.quad	OPENSSL_armcap_P-.
 # endif
+SYM_DATA_END(OPENSSL_armcap_P_rel)
 #endif
+SYM_DATA_START_LOCAL(OPENSSL_str)
 .asciz	"SHA$BITS block transform for ARMv8, CRYPTOGAMS by <appro\@openssl.org>"
 .align	2
+SYM_DATA_END(OPENSSL_str)
 ___
 
 if ($SZ==4) {
@@ -385,7 +389,7 @@ sub BODY_00_xx {
 	add		x29,sp,#0
 
 	ld1.32		{$ABCD,$EFGH},[$ctx]
-	adr		$Ktbl,.LK256
+	adr		$Ktbl,K256
 
 .Loop_hw:
 	ld1		{@MSG[0]-@MSG[3]},[$inp],#64
@@ -644,11 +648,9 @@ ()
 .align	4
 sha256_block_neon:
 .Lneon_entry:
-	stp	x29, x30, [sp, #-16]!
-	mov	x29, sp
 	sub	sp,sp,#16*4
 
-	adr	$Ktbl,.LK256
+	adr	$Ktbl,K256
 	add	$num,$inp,$num,lsl#6	// len to point at the end of inp
 
 	ld1.8	{@X[0]},[$inp], #16
@@ -732,8 +734,7 @@ ()
 	 mov	$Xfer,sp
 	b.ne	.L_00_48
 
-	ldr	x29,[x29]
-	add	sp,sp,#16*4+16
+	add	sp,sp,#16*4
 	ret
 .size	sha256_block_neon,.-sha256_block_neon
 ___

arch/arm64/include/asm/alternative-macros.h

@@ -230,7 +230,7 @@ alternative_has_feature_likely(unsigned long feature)
 			   "feature must be < ARM64_NCAPS");
 
 	asm goto(
-	ALTERNATIVE_CB("b	%l[l_no]", %[feature], alt_cb_patch_nops)
+	ALTERNATIVE("b	%l[l_no]", "nop", %[feature])
 	:
 	: [feature] "i" (feature)
 	: