Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Cross-merge networking fixes after downstream PR.

No conflicts or adjacent changes.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

25 files changed, 208 insertions, 154 deletions

diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 145b540ec34f..ec2174838f2a 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -322,7 +322,13 @@ static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf)
 	 *
 	 */
 
-	emit_bti(A64_BTI_C, ctx);
+	/* bpf function may be invoked by 3 instruction types:
+	 * 1. bl, attached via freplace to bpf prog via short jump
+	 * 2. br, attached via freplace to bpf prog via long jump
+	 * 3. blr, working as a function pointer, used by emit_call.
+	 * So BTI_JC should used here to support both br and blr.
+	 */
+	emit_bti(A64_BTI_JC, ctx);
 
 	emit(A64_MOV(1, A64_R(9), A64_LR), ctx);
 	emit(A64_NOP, ctx);
diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h
index b6ac4f86c87b..6472b08fa1b0 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-4k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h
@@ -136,12 +136,6 @@ static inline int hash__pmd_trans_huge(pmd_t pmd)
 	return 0;
 }
 
-static inline int hash__pmd_same(pmd_t pmd_a, pmd_t pmd_b)
-{
-	BUG();
-	return 0;
-}
-
 static inline pmd_t hash__pmd_mkhuge(pmd_t pmd)
 {
 	BUG();
diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h
index 338e62fbea0b..0bf6fd0bf42a 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-64k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h
@@ -263,11 +263,6 @@ static inline int hash__pmd_trans_huge(pmd_t pmd)
 		  (_PAGE_PTE | H_PAGE_THP_HUGE));
 }
 
-static inline int hash__pmd_same(pmd_t pmd_a, pmd_t pmd_b)
-{
-	return (((pmd_raw(pmd_a) ^ pmd_raw(pmd_b)) & ~cpu_to_be64(_PAGE_HPTEFLAGS)) == 0);
-}
-
 static inline pmd_t hash__pmd_mkhuge(pmd_t pmd)
 {
 	return __pmd(pmd_val(pmd) | (_PAGE_PTE | H_PAGE_THP_HUGE));
diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h
index 17e7a778c856..d4a19e6547ac 100644
--- a/arch/powerpc/include/asm/book3s/64/hash.h
+++ b/arch/powerpc/include/asm/book3s/64/hash.h
@@ -132,6 +132,11 @@ static inline int get_region_id(unsigned long ea)
 	return region_id;
 }
 
+static inline int hash__pmd_same(pmd_t pmd_a, pmd_t pmd_b)
+{
+	return (((pmd_raw(pmd_a) ^ pmd_raw(pmd_b)) & ~cpu_to_be64(_PAGE_HPTEFLAGS)) == 0);
+}
+
 #define	hash__pmd_bad(pmd)		(pmd_val(pmd) & H_PMD_BAD_BITS)
 #define	hash__pud_bad(pud)		(pud_val(pud) & H_PUD_BAD_BITS)
 static inline int hash__p4d_bad(p4d_t p4d)
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 3f86091e68b3..7ab4c8c0f1ab 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -5,6 +5,7 @@
  *  Copyright (C) 2007 Ben. Herrenschmidt (benh@kernel.crashing.org), IBM Corp.
  */
 
+#include <linux/linkage.h>
 #include <linux/threads.h>
 #include <asm/reg.h>
 #include <asm/page.h>
@@ -66,7 +67,7 @@
 #define SPECIAL_EXC_LOAD(reg, name) \
 	ld	reg, (SPECIAL_EXC_##name * 8 + SPECIAL_EXC_FRAME_OFFS)(r1)
 
-special_reg_save:
+SYM_CODE_START_LOCAL(special_reg_save)
 	/*
 	 * We only need (or have stack space) to save this stuff if
 	 * we interrupted the kernel.
@@ -131,8 +132,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
 	SPECIAL_EXC_STORE(r10,CSRR1)
 
 	blr
+SYM_CODE_END(special_reg_save)
 
-ret_from_level_except:
+SYM_CODE_START_LOCAL(ret_from_level_except)
 	ld	r3,_MSR(r1)
 	andi.	r3,r3,MSR_PR
 	beq	1f
@@ -206,6 +208,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
 	mtxer	r11
 
 	blr
+SYM_CODE_END(ret_from_level_except)
 
 .macro ret_from_level srr0 srr1 paca_ex scratch
 	bl	ret_from_level_except
@@ -232,13 +235,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
 	mfspr	r13,\scratch
 .endm
 
-ret_from_crit_except:
+SYM_CODE_START_LOCAL(ret_from_crit_except)
 	ret_from_level SPRN_CSRR0 SPRN_CSRR1 PACA_EXCRIT SPRN_SPRG_CRIT_SCRATCH
 	rfci
+SYM_CODE_END(ret_from_crit_except)
 
-ret_from_mc_except:
+SYM_CODE_START_LOCAL(ret_from_mc_except)
 	ret_from_level SPRN_MCSRR0 SPRN_MCSRR1 PACA_EXMC SPRN_SPRG_MC_SCRATCH
 	rfmci
+SYM_CODE_END(ret_from_mc_except)
 
 /* Exception prolog code for all exceptions */
 #define EXCEPTION_PROLOG(n, intnum, type, addition)	    		    \
@@ -978,20 +983,22 @@ masked_interrupt_book3e_0x2c0:
  * r14 and r15 containing the fault address and error code, with the
  * original values stashed away in the PACA
  */
-storage_fault_common:
+SYM_CODE_START_LOCAL(storage_fault_common)
 	addi	r3,r1,STACK_INT_FRAME_REGS
 	bl	do_page_fault
 	b	interrupt_return
+SYM_CODE_END(storage_fault_common)
 
 /*
  * Alignment exception doesn't fit entirely in the 0x100 bytes so it
  * continues here.
  */
-alignment_more:
+SYM_CODE_START_LOCAL(alignment_more)
 	addi	r3,r1,STACK_INT_FRAME_REGS
 	bl	alignment_exception
 	REST_NVGPRS(r1)
 	b	interrupt_return
+SYM_CODE_END(alignment_more)
 
 /*
  * Trampolines used when spotting a bad kernel stack pointer in
@@ -1030,8 +1037,7 @@ BAD_STACK_TRAMPOLINE(0xe00)
 BAD_STACK_TRAMPOLINE(0xf00)
 BAD_STACK_TRAMPOLINE(0xf20)
 
-	.globl	bad_stack_book3e
-bad_stack_book3e:
+_GLOBAL(bad_stack_book3e)
 	/* XXX: Needs to make SPRN_SPRG_GEN depend on exception type */
 	mfspr	r10,SPRN_SRR0;		  /* read SRR0 before touching stack */
 	ld	r1,PACAEMERGSP(r13)
@@ -1285,8 +1291,7 @@ have_hes:
 	 * ever takes any parameters, the SCOM code must also be updated to
 	 * provide them.
 	 */
-	.globl a2_tlbinit_code_start
-a2_tlbinit_code_start:
+_GLOBAL(a2_tlbinit_code_start)
 
 	ori	r11,r3,MAS0_WQ_ALLWAYS
 	oris	r11,r11,MAS0_ESEL(3)@h /* Use way 3: workaround A2 erratum 376 */
@@ -1479,8 +1484,7 @@ _GLOBAL(book3e_secondary_thread_init)
 	mflr	r28
 	b	3b
 
-	.globl init_core_book3e
-init_core_book3e:
+_GLOBAL(init_core_book3e)
 	/* Establish the interrupt vector base */
 	tovirt(r2,r2)
 	LOAD_REG_ADDR(r3, interrupt_base_book3e)
@@ -1488,7 +1492,7 @@ init_core_book3e:
 	sync
 	blr
 
-init_thread_book3e:
+SYM_CODE_START_LOCAL(init_thread_book3e)
 	lis	r3,(SPRN_EPCR_ICM | SPRN_EPCR_GICM)@h
 	mtspr	SPRN_EPCR,r3
 
@@ -1502,6 +1506,7 @@ init_thread_book3e:
 	mtspr	SPRN_TSR,r3
 
 	blr
+SYM_CODE_END(init_thread_book3e)
 
 _GLOBAL(__setup_base_ivors)
 	SET_IVOR(0, 0x020) /* Critical Input */
diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c
index 206475e3e0b4..4856e1a5161c 100644
--- a/arch/powerpc/kernel/security.c
+++ b/arch/powerpc/kernel/security.c
@@ -364,26 +364,27 @@ ssize_t cpu_show_spec_store_bypass(struct device *dev, struct device_attribute *
 
 static int ssb_prctl_get(struct task_struct *task)
 {
+	/*
+	 * The STF_BARRIER feature is on by default, so if it's off that means
+	 * firmware has explicitly said the CPU is not vulnerable via either
+	 * the hypercall or device tree.
+	 */
+	if (!security_ftr_enabled(SEC_FTR_STF_BARRIER))
+		return PR_SPEC_NOT_AFFECTED;
+
+	/*
+	 * If the system's CPU has no known barrier (see setup_stf_barrier())
+	 * then assume that the CPU is not vulnerable.
+	 */
 	if (stf_enabled_flush_types == STF_BARRIER_NONE)
-		/*
-		 * We don't have an explicit signal from firmware that we're
-		 * vulnerable or not, we only have certain CPU revisions that
-		 * are known to be vulnerable.
-		 *
-		 * We assume that if we're on another CPU, where the barrier is
-		 * NONE, then we are not vulnerable.
-		 */
 		return PR_SPEC_NOT_AFFECTED;
-	else
-		/*
-		 * If we do have a barrier type then we are vulnerable. The
-		 * barrier is not a global or per-process mitigation, so the
-		 * only value we can report here is PR_SPEC_ENABLE, which
-		 * appears as "vulnerable" in /proc.
-		 */
-		return PR_SPEC_ENABLE;
-
-	return -EINVAL;
+
+	/*
+	 * Otherwise the CPU is vulnerable. The barrier is not a global or
+	 * per-process mitigation, so the only value that can be reported here
+	 * is PR_SPEC_ENABLE, which appears as "vulnerable" in /proc.
+	 */
+	return PR_SPEC_ENABLE;
 }
 
 int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which)
diff --git a/arch/powerpc/mm/book3s64/hash_native.c b/arch/powerpc/mm/book3s64/hash_native.c
index 9342e79870df..430d1d935a7c 100644
--- a/arch/powerpc/mm/book3s64/hash_native.c
+++ b/arch/powerpc/mm/book3s64/hash_native.c
@@ -328,10 +328,12 @@ static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn,
 
 static long native_hpte_remove(unsigned long hpte_group)
 {
+	unsigned long hpte_v, flags;
 	struct hash_pte *hptep;
 	int i;
 	int slot_offset;
-	unsigned long hpte_v;
+
+	local_irq_save(flags);
 
 	DBG_LOW("    remove(group=%lx)\n", hpte_group);
 
@@ -356,13 +358,16 @@ static long native_hpte_remove(unsigned long hpte_group)
 		slot_offset &= 0x7;
 	}
 
-	if (i == HPTES_PER_GROUP)
-		return -1;
+	if (i == HPTES_PER_GROUP) {
+		i = -1;
+		goto out;
+	}
 
 	/* Invalidate the hpte. NOTE: this also unlocks it */
 	release_hpte_lock();
 	hptep->v = 0;
-
+out:
+	local_irq_restore(flags);
 	return i;
 }
 
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index bdcf460ea53d..a8f66c015229 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -318,18 +318,13 @@ void __init riscv_fill_hwcap(void)
 		}
 
 		/*
-		 * Linux requires the following extensions, so we may as well
-		 * always set them.
-		 */
-		set_bit(RISCV_ISA_EXT_ZICSR, isainfo->isa);
-		set_bit(RISCV_ISA_EXT_ZIFENCEI, isainfo->isa);
-
-		/*
 		 * These ones were as they were part of the base ISA when the
 		 * port & dt-bindings were upstreamed, and so can be set
 		 * unconditionally where `i` is in riscv,isa on DT systems.
 		 */
 		if (acpi_disabled) {
+			set_bit(RISCV_ISA_EXT_ZICSR, isainfo->isa);
+			set_bit(RISCV_ISA_EXT_ZIFENCEI, isainfo->isa);
 			set_bit(RISCV_ISA_EXT_ZICNTR, isainfo->isa);
 			set_bit(RISCV_ISA_EXT_ZIHPM, isainfo->isa);
 		}
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 70fb31960b63..9ce504737d18 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -1346,7 +1346,7 @@ static void __init reserve_crashkernel(void)
 	 */
 	crash_base = memblock_phys_alloc_range(crash_size, PMD_SIZE,
 					       search_start,
-					       min(search_end, (unsigned long) SZ_4G));
+					       min(search_end, (unsigned long)(SZ_4G - 1)));
 	if (crash_base == 0) {
 		/* Try again without restricting region to 32bit addressible memory */
 		crash_base = memblock_phys_alloc_range(crash_size, PMD_SIZE,
diff --git a/arch/sparc/include/asm/cmpxchg_32.h b/arch/sparc/include/asm/cmpxchg_32.h
index 7a1339533d1d..d0af82c240b7 100644
--- a/arch/sparc/include/asm/cmpxchg_32.h
+++ b/arch/sparc/include/asm/cmpxchg_32.h
@@ -15,7 +15,7 @@
 unsigned long __xchg_u32(volatile u32 *m, u32 new);
 void __xchg_called_with_bad_pointer(void);
 
-static inline unsigned long __arch_xchg(unsigned long x, __volatile__ void * ptr, int size)
+static __always_inline unsigned long __arch_xchg(unsigned long x, __volatile__ void * ptr, int size)
 {
 	switch (size) {
 	case 4:
diff --git a/arch/sparc/include/asm/cmpxchg_64.h b/arch/sparc/include/asm/cmpxchg_64.h
index 66cd61dde9ec..3de25262c411 100644
--- a/arch/sparc/include/asm/cmpxchg_64.h
+++ b/arch/sparc/include/asm/cmpxchg_64.h
@@ -87,7 +87,7 @@ xchg16(__volatile__ unsigned short *m, unsigned short val)
 	return (load32 & mask) >> bit_shift;
 }
 
-static inline unsigned long
+static __always_inline unsigned long
 __arch_xchg(unsigned long x, __volatile__ void * ptr, int size)
 {
 	switch (size) {
diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c
index 918fed7ad4d8..b1bfed0c8528 100644
--- a/arch/um/kernel/um_arch.c
+++ b/arch/um/kernel/um_arch.c
@@ -437,7 +437,7 @@ void __init arch_cpu_finalize_init(void)
 	os_check_bugs();
 }
 
-void apply_ibt_endbr(s32 *start, s32 *end)
+void apply_seal_endbr(s32 *start, s32 *end)
 {
 }
 
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 91397f58ac30..6e6af42e044a 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -720,26 +720,6 @@ SYM_CODE_END(__switch_to_asm)
 .popsection
 
 /*
- * The unwinder expects the last frame on the stack to always be at the same
- * offset from the end of the page, which allows it to validate the stack.
- * Calling schedule_tail() directly would break that convention because its an
- * asmlinkage function so its argument has to be pushed on the stack.  This
- * wrapper creates a proper "end of stack" frame header before the call.
- */
-.pushsection .text, "ax"
-SYM_FUNC_START(schedule_tail_wrapper)
-	FRAME_BEGIN
-
-	pushl	%eax
-	call	schedule_tail
-	popl	%eax
-
-	FRAME_END
-	RET
-SYM_FUNC_END(schedule_tail_wrapper)
-.popsection
-
-/*
  * A newly forked process directly context switches into this address.
  *
  * eax: prev task we switched from
@@ -747,29 +727,22 @@ SYM_FUNC_END(schedule_tail_wrapper)
  * edi: kernel thread arg
  */
 .pushsection .text, "ax"
-SYM_CODE_START(ret_from_fork)
-	call	schedule_tail_wrapper
+SYM_CODE_START(ret_from_fork_asm)
+	movl	%esp, %edx	/* regs */
 
-	testl	%ebx, %ebx
-	jnz	1f		/* kernel threads are uncommon */
+	/* return address for the stack unwinder */
+	pushl	$.Lsyscall_32_done
 
-2:
-	/* When we fork, we trace the syscall return in the child, too. */
-	movl    %esp, %eax
-	call    syscall_exit_to_user_mode
-	jmp     .Lsyscall_32_done
+	FRAME_BEGIN
+	/* prev already in EAX */
+	movl	%ebx, %ecx	/* fn */
+	pushl	%edi		/* fn_arg */
+	call	ret_from_fork
+	addl	$4, %esp
+	FRAME_END
 
-	/* kernel thread */
-1:	movl	%edi, %eax
-	CALL_NOSPEC ebx
-	/*
-	 * A kernel thread is allowed to return here after successfully
-	 * calling kernel_execve().  Exit to userspace to complete the execve()
-	 * syscall.
-	 */
-	movl	$0, PT_EAX(%esp)
-	jmp	2b
-SYM_CODE_END(ret_from_fork)
+	RET
+SYM_CODE_END(ret_from_fork_asm)
 .popsection
 
 SYM_ENTRY(__begin_SYSENTER_singlestep_region, SYM_L_GLOBAL, SYM_A_NONE)
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index f31e286c2977..91f6818884fa 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -284,36 +284,19 @@ SYM_FUNC_END(__switch_to_asm)
  * r12: kernel thread arg
  */
 .pushsection .text, "ax"
-	__FUNC_ALIGN
-SYM_CODE_START_NOALIGN(ret_from_fork)
-	UNWIND_HINT_END_OF_STACK
+SYM_CODE_START(ret_from_fork_asm)
+	UNWIND_HINT_REGS
 	ANNOTATE_NOENDBR // copy_thread
 	CALL_DEPTH_ACCOUNT
-	movq	%rax, %rdi
-	call	schedule_tail			/* rdi: 'prev' task parameter */
 
-	testq	%rbx, %rbx			/* from kernel_thread? */
-	jnz	1f				/* kernel threads are uncommon */
+	movq	%rax, %rdi		/* prev */
+	movq	%rsp, %rsi		/* regs */
+	movq	%rbx, %rdx		/* fn */
+	movq	%r12, %rcx		/* fn_arg */
+	call	ret_from_fork
 
-2:
-	UNWIND_HINT_REGS
-	movq	%rsp, %rdi
-	call	syscall_exit_to_user_mode	/* returns with IRQs disabled */
 	jmp	swapgs_restore_regs_and_return_to_usermode
-
-1:
-	/* kernel thread */
-	UNWIND_HINT_END_OF_STACK
-	movq	%r12, %rdi
-	CALL_NOSPEC rbx
-	/*
-	 * A kernel thread is allowed to return here after successfully
-	 * calling kernel_execve().  Exit to userspace to complete the execve()
-	 * syscall.
-	 */
-	movq	$0, RAX(%rsp)
-	jmp	2b
-SYM_CODE_END(ret_from_fork)
+SYM_CODE_END(ret_from_fork_asm)
 .popsection
 
 .macro DEBUG_ENTRY_ASSERT_IRQS_OFF
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index a149fafad813..2a284ba951b7 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3993,6 +3993,13 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		struct perf_event *leader = event->group_leader;
 		struct perf_event *sibling = NULL;
 
+		/*
+		 * When this memload event is also the first event (no group
+		 * exists yet), then there is no aux event before it.
+		 */
+		if (leader == event)
+			return -ENODATA;
+
 		if (!is_mem_loads_aux_event(leader)) {
 			for_each_sibling_event(sibling, leader) {
 				if (is_mem_loads_aux_event(sibling))
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 6c15a622ad60..9c4da699e11a 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -96,7 +96,7 @@ extern void alternative_instructions(void);
 extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
 extern void apply_retpolines(s32 *start, s32 *end);
 extern void apply_returns(s32 *start, s32 *end);
-extern void apply_ibt_endbr(s32 *start, s32 *end);
+extern void apply_seal_endbr(s32 *start, s32 *end);
 extern void apply_fineibt(s32 *start_retpoline, s32 *end_retpoine,
 			  s32 *start_cfi, s32 *end_cfi);
 
diff --git a/arch/x86/include/asm/ibt.h b/arch/x86/include/asm/ibt.h
index baae6b4fea23..1e59581d500c 100644
--- a/arch/x86/include/asm/ibt.h
+++ b/arch/x86/include/asm/ibt.h
@@ -34,7 +34,7 @@
 /*
  * Create a dummy function pointer reference to prevent objtool from marking
  * the function as needing to be "sealed" (i.e. ENDBR converted to NOP by
- * apply_ibt_endbr()).
+ * apply_seal_endbr()).
  */
 #define IBT_NOSEAL(fname)				\
 	".pushsection .discard.ibt_endbr_noseal\n\t"	\
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 55388c9f7601..1a65cf4acb2b 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -234,6 +234,10 @@
  * JMP_NOSPEC and CALL_NOSPEC macros can be used instead of a simple
  * indirect jmp/call which may be susceptible to the Spectre variant 2
  * attack.
+ *
+ * NOTE: these do not take kCFI into account and are thus not comparable to C
+ * indirect calls, take care when using. The target of these should be an ENDBR
+ * instruction irrespective of kCFI.
  */
 .macro JMP_NOSPEC reg:req
 #ifdef CONFIG_RETPOLINE
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index 5c91305d09d2..f42dbf17f52b 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -12,7 +12,9 @@ struct task_struct *__switch_to_asm(struct task_struct *prev,
 __visible struct task_struct *__switch_to(struct task_struct *prev,
 					  struct task_struct *next);
 
-asmlinkage void ret_from_fork(void);
+asmlinkage void ret_from_fork_asm(void);
+__visible void ret_from_fork(struct task_struct *prev, struct pt_regs *regs,
+			     int (*fn)(void *), void *fn_arg);
 
 /*
  * This is the structure pointed to by thread.sp for an inactive task.  The
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 72646d75b6ff..2dcf3a06af09 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -778,6 +778,8 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end) { }
 
 #ifdef CONFIG_X86_KERNEL_IBT
 
+static void poison_cfi(void *addr);
+
 static void __init_or_module poison_endbr(void *addr, bool warn)
 {
 	u32 endbr, poison = gen_endbr_poison();
@@ -802,8 +804,11 @@ static void __init_or_module poison_endbr(void *addr, bool warn)
 
 /*
  * Generated by: objtool --ibt
+ *
+ * Seal the functions for indirect calls by clobbering the ENDBR instructions
+ * and the kCFI hash value.
  */
-void __init_or_module noinline apply_ibt_endbr(s32 *start, s32 *end)
+void __init_or_module noinline apply_seal_endbr(s32 *start, s32 *end)
 {
 	s32 *s;
 
@@ -812,13 +817,13 @@ void __init_or_module noinline apply_ibt_endbr(s32 *start, s32 *end)
 
 		poison_endbr(addr, true);
 		if (IS_ENABLED(CONFIG_FINEIBT))
-			poison_endbr(addr - 16, false);
+			poison_cfi(addr - 16);
 	}
 }
 
 #else
 
-void __init_or_module apply_ibt_endbr(s32 *start, s32 *end) { }
+void __init_or_module apply_seal_endbr(s32 *start, s32 *end) { }
 
 #endif /* CONFIG_X86_KERNEL_IBT */
 
@@ -1063,6 +1068,17 @@ static int cfi_rewrite_preamble(s32 *start, s32 *end)
 	return 0;
 }
 
+static void cfi_rewrite_endbr(s32 *start, s32 *end)
+{
+	s32 *s;
+
+	for (s = start; s < end; s++) {
+		void *addr = (void *)s + *s;
+
+		poison_endbr(addr+16, false);
+	}
+}
+
 /* .retpoline_sites */
 static int cfi_rand_callers(s32 *start, s32 *end)
 {
@@ -1157,14 +1173,19 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
 		return;
 
 	case CFI_FINEIBT:
+		/* place the FineIBT preamble at func()-16 */
 		ret = cfi_rewrite_preamble(start_cfi, end_cfi);
 		if (ret)
 			goto err;
 
+		/* rewrite the callers to target func()-16 */
 		ret = cfi_rewrite_callers(start_retpoline, end_retpoline);
 		if (ret)
 			goto err;
 
+		/* now that nobody targets func()+0, remove ENDBR there */
+		cfi_rewrite_endbr(start_cfi, end_cfi);
+
 		if (builtin)
 			pr_info("Using FineIBT CFI\n");
 		return;
@@ -1177,6 +1198,41 @@ err:
 	pr_err("Something went horribly wrong trying to rewrite the CFI implementation.\n");
 }
 
+static inline void poison_hash(void *addr)
+{
+	*(u32 *)addr = 0;
+}
+
+static void poison_cfi(void *addr)
+{
+	switch (cfi_mode) {
+	case CFI_FINEIBT:
+		/*
+		 * __cfi_\func:
+		 *	osp nopl (%rax)
+		 *	subl	$0, %r10d
+		 *	jz	1f
+		 *	ud2
+		 * 1:	nop
+		 */
+		poison_endbr(addr, false);
+		poison_hash(addr + fineibt_preamble_hash);
+		break;
+
+	case CFI_KCFI:
+		/*
+		 * __cfi_\func:
+		 *	movl	$0, %eax
+		 *	.skip	11, 0x90
+		 */
+		poison_hash(addr + 1);
+		break;
+
+	default:
+		break;
+	}
+}
+
 #else
 
 static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
@@ -1184,6 +1240,10 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
 {
 }
 
+#ifdef CONFIG_X86_KERNEL_IBT
+static void poison_cfi(void *addr) { }
+#endif
+
 #endif
 
 void apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
@@ -1565,7 +1625,10 @@ void __init alternative_instructions(void)
 	 */
 	callthunks_patch_builtin_calls();
 
-	apply_ibt_endbr(__ibt_endbr_seal, __ibt_endbr_seal_end);
+	/*
+	 * Seal all functions that do not have their address taken.
+	 */
+	apply_seal_endbr(__ibt_endbr_seal, __ibt_endbr_seal_end);
 
 #ifdef CONFIG_SMP
 	/* Patch to UP if other cpus not imminent. */
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index b05f62ee2344..5f71a0cf4399 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -358,7 +358,7 @@ int module_finalize(const Elf_Ehdr *hdr,
 	}
 	if (ibt_endbr) {
 		void *iseg = (void *)ibt_endbr->sh_addr;
-		apply_ibt_endbr(iseg, iseg + ibt_endbr->sh_size);
+		apply_seal_endbr(iseg, iseg + ibt_endbr->sh_size);
 	}
 	if (locks) {
 		void *lseg = (void *)locks->sh_addr;
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index ff9b80a0e3e3..72015dba72ab 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -28,6 +28,7 @@
 #include <linux/static_call.h>
 #include <trace/events/power.h>
 #include <linux/hw_breakpoint.h>
+#include <linux/entry-common.h>
 #include <asm/cpu.h>
 #include <asm/apic.h>
 #include <linux/uaccess.h>
@@ -134,6 +135,25 @@ static int set_new_tls(struct task_struct *p, unsigned long tls)
 		return do_set_thread_area_64(p, ARCH_SET_FS, tls);
 }
 
+__visible void ret_from_fork(struct task_struct *prev, struct pt_regs *regs,
+				     int (*fn)(void *), void *fn_arg)
+{
+	schedule_tail(prev);
+
+	/* Is this a kernel thread? */
+	if (unlikely(fn)) {
+		fn(fn_arg);
+		/*
+		 * A kernel thread is allowed to return here after successfully
+		 * calling kernel_execve().  Exit to userspace to complete the
+		 * execve() syscall.
+		 */
+		regs->ax = 0;
+	}
+
+	syscall_exit_to_user_mode(regs);
+}
+
 int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
 	unsigned long clone_flags = args->flags;
@@ -149,7 +169,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	frame = &fork_frame->frame;
 
 	frame->bp = encode_frame_pointer(childregs);
-	frame->ret_addr = (unsigned long) ret_from_fork;
+	frame->ret_addr = (unsigned long) ret_from_fork_asm;
 	p->thread.sp = (unsigned long) fork_frame;
 	p->thread.io_bitmap = NULL;
 	p->thread.iopl_warn = 0;
diff --git a/arch/xtensa/kernel/align.S b/arch/xtensa/kernel/align.S
index 20d6b4961001..ee97edce2300 100644
--- a/arch/xtensa/kernel/align.S
+++ b/arch/xtensa/kernel/align.S
@@ -1,7 +1,7 @@
 /*
  * arch/xtensa/kernel/align.S
  *
- * Handle unalignment exceptions in kernel space.
+ * Handle unalignment and load/store exceptions.
  *
  * This file is subject to the terms and conditions of the GNU General
  * Public License.  See the file "COPYING" in the main directory of
@@ -26,20 +26,18 @@
 #define LOAD_EXCEPTION_HANDLER
 #endif
 
-#if XCHAL_UNALIGNED_STORE_EXCEPTION || defined LOAD_EXCEPTION_HANDLER
+#if XCHAL_UNALIGNED_STORE_EXCEPTION || defined CONFIG_XTENSA_LOAD_STORE
+#define STORE_EXCEPTION_HANDLER
+#endif
+
+#if defined LOAD_EXCEPTION_HANDLER || defined STORE_EXCEPTION_HANDLER
 #define ANY_EXCEPTION_HANDLER
 #endif
 
-#if XCHAL_HAVE_WINDOWED
+#if XCHAL_HAVE_WINDOWED && defined CONFIG_MMU
 #define UNALIGNED_USER_EXCEPTION
 #endif
 
-/*  First-level exception handler for unaligned exceptions.
- *
- *  Note: This handler works only for kernel exceptions.  Unaligned user
- *        access should get a seg fault.
- */
-
 /* Big and little endian 16-bit values are located in
  * different halves of a register.  HWORD_START helps to
  * abstract the notion of extracting a 16-bit value from a
@@ -228,8 +226,6 @@ ENDPROC(fast_load_store)
 #ifdef ANY_EXCEPTION_HANDLER
 ENTRY(fast_unaligned)
 
-#if XCHAL_UNALIGNED_LOAD_EXCEPTION || XCHAL_UNALIGNED_STORE_EXCEPTION
-
 	call0	.Lsave_and_load_instruction
 
 	/* Analyze the instruction (load or store?). */
@@ -244,8 +240,7 @@ ENTRY(fast_unaligned)
 	/* 'store indicator bit' not set, jump */
 	_bbci.l	a4, OP1_SI_BIT + INSN_OP1, .Lload
 
-#endif
-#if XCHAL_UNALIGNED_STORE_EXCEPTION
+#ifdef STORE_EXCEPTION_HANDLER
 
 	/* Store: Jump to table entry to get the value in the source register.*/
 
@@ -254,7 +249,7 @@ ENTRY(fast_unaligned)
 	addx8	a5, a6, a5
 	jx	a5			# jump into table
 #endif
-#if XCHAL_UNALIGNED_LOAD_EXCEPTION
+#ifdef LOAD_EXCEPTION_HANDLER
 
 	/* Load: Load memory address. */
 
@@ -328,7 +323,7 @@ ENTRY(fast_unaligned)
 	mov	a14, a3		;	_j .Lexit;	.align 8
 	mov	a15, a3		;	_j .Lexit;	.align 8
 #endif
-#if XCHAL_UNALIGNED_STORE_EXCEPTION
+#ifdef STORE_EXCEPTION_HANDLER
 .Lstore_table:
 	l32i	a3, a2, PT_AREG0;	_j .Lstore_w;	.align 8
 	mov	a3, a1;			_j .Lstore_w;	.align 8	# fishy??
@@ -348,7 +343,6 @@ ENTRY(fast_unaligned)
 	mov	a3, a15		;	_j .Lstore_w;	.align 8
 #endif
 
-#ifdef ANY_EXCEPTION_HANDLER
 	/* We cannot handle this exception. */
 
 	.extern _kernel_exception
@@ -377,8 +371,8 @@ ENTRY(fast_unaligned)
 
 2:	movi	a0, _user_exception
 	jx	a0
-#endif
-#if XCHAL_UNALIGNED_STORE_EXCEPTION
+
+#ifdef STORE_EXCEPTION_HANDLER
 
 	# a7: instruction pointer, a4: instruction, a3: value
 .Lstore_w:
@@ -444,7 +438,7 @@ ENTRY(fast_unaligned)
 	s32i	a6, a4, 4
 #endif
 #endif
-#ifdef ANY_EXCEPTION_HANDLER
+
 .Lexit:
 #if XCHAL_HAVE_LOOPS
 	rsr	a4, lend		# check if we reached LEND
@@ -539,7 +533,7 @@ ENTRY(fast_unaligned)
 	__src_b	a4, a4, a5	# a4 has the instruction
 
 	ret
-#endif
+
 ENDPROC(fast_unaligned)
 
 ENTRY(fast_unaligned_fixup)
diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c
index 17eb180eff7c..427c125a137a 100644
--- a/arch/xtensa/kernel/traps.c
+++ b/arch/xtensa/kernel/traps.c
@@ -102,7 +102,8 @@ static dispatch_init_table_t __initdata dispatch_init_table[] = {
 #endif
 { EXCCAUSE_INTEGER_DIVIDE_BY_ZERO, 0,	   do_div0 },
 /* EXCCAUSE_PRIVILEGED unhandled */
-#if XCHAL_UNALIGNED_LOAD_EXCEPTION || XCHAL_UNALIGNED_STORE_EXCEPTION
+#if XCHAL_UNALIGNED_LOAD_EXCEPTION || XCHAL_UNALIGNED_STORE_EXCEPTION || \
+		IS_ENABLED(CONFIG_XTENSA_LOAD_STORE)
 #ifdef CONFIG_XTENSA_UNALIGNED_USER
 { EXCCAUSE_UNALIGNED,		USER,	   fast_unaligned },
 #endif
diff --git a/arch/xtensa/platforms/iss/network.c b/arch/xtensa/platforms/iss/network.c
index 9ac46ab3a296..85c82cd42188 100644
--- a/arch/xtensa/platforms/iss/network.c
+++ b/arch/xtensa/platforms/iss/network.c
@@ -237,7 +237,7 @@ static int tuntap_probe(struct iss_net_private *lp, int index, char *init)
 
 	init += sizeof(TRANSPORT_TUNTAP_NAME) - 1;
 	if (*init == ',') {
-		rem = split_if_spec(init + 1, &mac_str, &dev_name);
+		rem = split_if_spec(init + 1, &mac_str, &dev_name, NULL);
 		if (rem != NULL) {
 			pr_err("%s: extra garbage on specification : '%s'\n",
 			       dev->name, rem);
@@ -540,6 +540,7 @@ static void iss_net_configure(int index, char *init)
 		rtnl_unlock();
 		pr_err("%s: error registering net device!\n", dev->name);
 		platform_device_unregister(&lp->pdev);
+		/* dev is freed by the iss_net_pdev_release callback */
 		return;
 	}
 	rtnl_unlock();