Merge 4.4.113 into android-4.4

Changes in 4.4.113
	gcov: disable for COMPILE_TEST
	x86/cpu/AMD: Make LFENCE a serializing instruction
	x86/cpu/AMD: Use LFENCE_RDTSC in preference to MFENCE_RDTSC
	x86/mm/32: Move setup_clear_cpu_cap(X86_FEATURE_PCID) earlier
	x86/asm: Use register variable to get stack pointer value
	x86/kbuild: enable modversions for symbols exported from asm
	x86/asm: Make asm/alternative.h safe from assembly
	EXPORT_SYMBOL() for asm
	kconfig.h: use __is_defined() to check if MODULE is defined
	x86/retpoline: Add initial retpoline support
	x86/spectre: Add boot time option to select Spectre v2 mitigation
	x86/retpoline/crypto: Convert crypto assembler indirect jumps
	x86/retpoline/entry: Convert entry assembler indirect jumps
	x86/retpoline/ftrace: Convert ftrace assembler indirect jumps
	x86/retpoline/hyperv: Convert assembler indirect jumps
	x86/retpoline/xen: Convert Xen hypercall indirect jumps
	x86/retpoline/checksum32: Convert assembler indirect jumps
	x86/retpoline/irq32: Convert assembler indirect jumps
	x86/retpoline: Fill return stack buffer on vmexit
	x86/retpoline: Remove compile time warning
	scsi: sg: disable SET_FORCE_LOW_DMA
	futex: Prevent overflow by strengthen input validation
	ALSA: pcm: Remove yet superfluous WARN_ON()
	ALSA: hda - Apply headphone noise quirk for another Dell XPS 13 variant
	ALSA: hda - Apply the existing quirk to iMac 14,1
	af_key: fix buffer overread in verify_address_len()
	af_key: fix buffer overread in parse_exthdrs()
	scsi: hpsa: fix volume offline state
	sched/deadline: Zero out positive runtime after throttling constrained tasks
	x86/retpoline: Add LFENCE to the retpoline/RSB filling RSB macros
	module: Add retpoline tag to VERMAGIC
	pipe: avoid round_pipe_size() nr_pages overflow on 32-bit
	x86/apic/vector: Fix off by one in error path
	Input: 88pm860x-ts - fix child-node lookup
	Input: twl6040-vibra - fix DT node memory management
	Input: twl6040-vibra - fix child-node lookup
	Input: twl4030-vibra - fix sibling-node lookup
	tracing: Fix converting enum's from the map in trace_event_eval_update()
	phy: work around 'phys' references to usb-nop-xceiv devices
	ARM: dts: kirkwood: fix pin-muxing of MPP7 on OpenBlocks A7
	can: peak: fix potential bug in packet fragmentation
	libata: apply MAX_SEC_1024 to all LITEON EP1 series devices
	dm btree: fix serious bug in btree_split_beneath()
	dm thin metadata: THIN_MAX_CONCURRENT_LOCKS should be 6
	arm64: KVM: Fix SMCCC handling of unimplemented SMC/HVC calls
	x86/cpu, x86/pti: Do not enable PTI on AMD processors
	kbuild: modversions for EXPORT_SYMBOL() for asm
	x86/mce: Make machine check speculation protected
	retpoline: Introduce start/end markers of indirect thunk
	kprobes/x86: Blacklist indirect thunk functions for kprobes
	kprobes/x86: Disable optimizing on the function jumps to indirect thunk
	x86/pti: Document fix wrong index
	x86/retpoline: Optimize inline assembler for vmexit_fill_RSB
	MIPS: AR7: ensure the port type's FCR value is used
	Linux 4.4.113

Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>

3 files changed, 54 insertions, 3 deletions

diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 2b6561d97a46..7f46ea66eeb6 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -24,6 +24,7 @@ lib-y += usercopy_$(BITS).o usercopy.o getuser.o putuser.o
 lib-y += memcpy_$(BITS).o
 lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
 lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o
+lib-$(CONFIG_RETPOLINE) += retpoline.o
 
 obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o
 
diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S
index c1e623209853..90353a26ed95 100644
--- a/arch/x86/lib/checksum_32.S
+++ b/arch/x86/lib/checksum_32.S
@@ -28,7 +28,8 @@
 #include <linux/linkage.h>
 #include <asm/errno.h>
 #include <asm/asm.h>
-				
+#include <asm/nospec-branch.h>
+
 /*
  * computes a partial checksum, e.g. for TCP/UDP fragments
  */
@@ -155,7 +156,7 @@ ENTRY(csum_partial)
 	negl %ebx
 	lea 45f(%ebx,%ebx,2), %ebx
 	testl %esi, %esi
-	jmp *%ebx
+	JMP_NOSPEC %ebx
 
 	# Handle 2-byte-aligned regions
 20:	addw (%esi), %ax
@@ -437,7 +438,7 @@ ENTRY(csum_partial_copy_generic)
 	andl $-32,%edx
 	lea 3f(%ebx,%ebx), %ebx
 	testl %esi, %esi 
-	jmp *%ebx
+	JMP_NOSPEC %ebx
 1:	addl $64,%esi
 	addl $64,%edi 
 	SRC(movb -32(%edx),%bl)	; SRC(movb (%edx),%bl)
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
new file mode 100644
index 000000000000..e611a124c442
--- /dev/null
+++ b/arch/x86/lib/retpoline.S
@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <linux/stringify.h>
+#include <linux/linkage.h>
+#include <asm/dwarf2.h>
+#include <asm/cpufeature.h>
+#include <asm/alternative-asm.h>
+#include <asm-generic/export.h>
+#include <asm/nospec-branch.h>
+
+.macro THUNK reg
+	.section .text.__x86.indirect_thunk
+
+ENTRY(__x86_indirect_thunk_\reg)
+	CFI_STARTPROC
+	JMP_NOSPEC %\reg
+	CFI_ENDPROC
+ENDPROC(__x86_indirect_thunk_\reg)
+.endm
+
+/*
+ * Despite being an assembler file we can't just use .irp here
+ * because __KSYM_DEPS__ only uses the C preprocessor and would
+ * only see one instance of "__x86_indirect_thunk_\reg" rather
+ * than one per register with the correct names. So we do it
+ * the simple and nasty way...
+ */
+#define __EXPORT_THUNK(sym) _ASM_NOKPROBE(sym); EXPORT_SYMBOL(sym)
+#define EXPORT_THUNK(reg) __EXPORT_THUNK(__x86_indirect_thunk_ ## reg)
+#define GENERATE_THUNK(reg) THUNK reg ; EXPORT_THUNK(reg)
+
+GENERATE_THUNK(_ASM_AX)
+GENERATE_THUNK(_ASM_BX)
+GENERATE_THUNK(_ASM_CX)
+GENERATE_THUNK(_ASM_DX)
+GENERATE_THUNK(_ASM_SI)
+GENERATE_THUNK(_ASM_DI)
+GENERATE_THUNK(_ASM_BP)
+GENERATE_THUNK(_ASM_SP)
+#ifdef CONFIG_64BIT
+GENERATE_THUNK(r8)
+GENERATE_THUNK(r9)
+GENERATE_THUNK(r10)
+GENERATE_THUNK(r11)
+GENERATE_THUNK(r12)
+GENERATE_THUNK(r13)
+GENERATE_THUNK(r14)
+GENERATE_THUNK(r15)
+#endif