Merge tag 'for-linus' of git://git.armlinux.org.uk/~rmk/linux-arm

Pull ARM updates from Russell King:
 "Updates for IRQ stacks and virtually mapped stack support, and ftrace:

   - Support for IRQ and vmap'ed stacks

     This covers all the work related to implementing IRQ stacks and
     vmap'ed stacks for all 32-bit ARM systems that are currently
     supported by the Linux kernel, including RiscPC and Footbridge. It
     has been submitted for review in four different waves:

      - IRQ stacks support for v7 SMP systems [0]

      - vmap'ed stacks support for v7 SMP systems[1]

      - extending support for both IRQ stacks and vmap'ed stacks for all
        remaining configurations, including v6/v7 SMP multiplatform
        kernels and uniprocessor configurations including v7-M [2]

      - fixes and updates in [3]

   - ftrace fixes and cleanups

     Make all flavors of ftrace available on all builds, regardless of
     ISA choice, unwinder choice or compiler [4]:

      - use ADD not POP where possible

      - fix a couple of Thumb2 related issues

      - enable HAVE_FUNCTION_GRAPH_FP_TEST for robustness

      - enable the graph tracer with the EABI unwinder

      - avoid clobbering frame pointer registers to make Clang happy

   - Fixes for the above"

[0] https://lore.kernel.org/linux-arm-kernel/20211115084732.3704393-1-ardb@kernel.org/
[1] https://lore.kernel.org/linux-arm-kernel/20211122092816.2865873-1-ardb@kernel.org/
[2] https://lore.kernel.org/linux-arm-kernel/20211206164659.1495084-1-ardb@kernel.org/
[3] https://lore.kernel.org/linux-arm-kernel/20220124174744.1054712-1-ardb@kernel.org/
[4] https://lore.kernel.org/linux-arm-kernel/20220203082204.1176734-1-ardb@kernel.org/

* tag 'for-linus' of git://git.armlinux.org.uk/~rmk/linux-arm: (62 commits)
  ARM: fix building NOMMU ARMv4/v5 kernels
  ARM: unwind: only permit stack switch when unwinding call_with_stack()
  ARM: Revert "unwind: dump exception stack from calling frame"
  ARM: entry: fix unwinder problems caused by IRQ stacks
  ARM: unwind: set frame.pc correctly for current-thread unwinding
  ARM: 9184/1: return_address: disable again for CONFIG_ARM_UNWIND=y
  ARM: 9183/1: unwind: avoid spurious warnings on bogus code addresses
  Revert "ARM: 9144/1: forbid ftrace with clang and thumb2_kernel"
  ARM: mach-bcm: disable ftrace in SMC invocation routines
  ARM: cacheflush: avoid clobbering the frame pointer
  ARM: kprobes: treat R7 as the frame pointer register in Thumb2 builds
  ARM: ftrace: enable the graph tracer with the EABI unwinder
  ARM: unwind: track location of LR value in stack frame
  ARM: ftrace: enable HAVE_FUNCTION_GRAPH_FP_TEST
  ARM: ftrace: avoid unnecessary literal loads
  ARM: ftrace: avoid redundant loads or clobbering IP
  ARM: ftrace: use trampolines to keep .init.text in branching range
  ARM: ftrace: use ADD not POP to counter PUSH at entry
  ARM: ftrace: ensure that ADR takes the Thumb bit into account
  ARM: make get_current() and __my_cpu_offset() __always_inline
  ...

4 files changed, 31 insertions, 31 deletions

diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 9724c16e9076..d30ee26ccc87 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -386,6 +386,7 @@ config CPU_V6
 	select CPU_PABRT_V6
 	select CPU_THUMB_CAPABLE
 	select CPU_TLB_V6 if MMU
+	select SMP_ON_UP if SMP
 
 # ARMv6k
 config CPU_V6K
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index 830bbfb26ca5..7c9499b728c4 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -90,7 +90,7 @@ ENDPROC(v7_flush_icache_all)
  *
  *     Flush the D-cache up to the Level of Unification Inner Shareable
  *
- *     Corrupted registers: r0-r7, r9-r11 (r6 only in Thumb mode)
+ *     Corrupted registers: r0-r6, r9-r10
  */
 
 ENTRY(v7_flush_dcache_louis)
@@ -117,7 +117,7 @@ ENDPROC(v7_flush_dcache_louis)
  *
  *	Flush the whole D-cache.
  *
- *	Corrupted registers: r0-r7, r9-r11 (r6 only in Thumb mode)
+ *	Corrupted registers: r0-r6, r9-r10
  *
  *	- mm    - mm_struct describing address space
  */
@@ -149,22 +149,22 @@ flush_levels:
 	movw	r4, #0x3ff
 	ands	r4, r4, r1, lsr #3		@ find maximum number on the way size
 	clz	r5, r4				@ find bit position of way size increment
-	movw	r7, #0x7fff
-	ands	r7, r7, r1, lsr #13		@ extract max number of the index size
+	movw	r6, #0x7fff
+	and	r1, r6, r1, lsr #13		@ extract max number of the index size
+	mov	r6, #1
+	movne	r4, r4, lsl r5			@ # of ways shifted into bits [31:...]
+	movne	r6, r6, lsl r5			@ 1 shifted left by same amount
 loop1:
-	mov	r9, r7				@ create working copy of max index
+	mov	r9, r1				@ create working copy of max index
 loop2:
- ARM(	orr	r11, r10, r4, lsl r5	)	@ factor way and cache number into r11
- THUMB(	lsl	r6, r4, r5		)
- THUMB(	orr	r11, r10, r6		)	@ factor way and cache number into r11
- ARM(	orr	r11, r11, r9, lsl r2	)	@ factor index number into r11
- THUMB(	lsl	r6, r9, r2		)
- THUMB(	orr	r11, r11, r6		)	@ factor index number into r11
-	mcr	p15, 0, r11, c7, c14, 2		@ clean & invalidate by set/way
+	mov	r5, r9, lsl r2			@ factor set number into r5
+	orr	r5, r5, r4			@ factor way number into r5
+	orr	r5, r5, r10			@ factor cache level into r5
+	mcr	p15, 0, r5, c7, c14, 2		@ clean & invalidate by set/way
 	subs	r9, r9, #1			@ decrement the index
 	bge	loop2
-	subs	r4, r4, #1			@ decrement the way
-	bge	loop1
+	subs	r4, r4, r6			@ decrement the way
+	bcs	loop1
 skip:
 	add	r10, r10, #2			@ increment cache number
 	cmp	r3, r10
@@ -192,14 +192,12 @@ ENDPROC(v7_flush_dcache_all)
  *
  */
 ENTRY(v7_flush_kern_cache_all)
- ARM(	stmfd	sp!, {r4-r5, r7, r9-r11, lr}	)
- THUMB(	stmfd	sp!, {r4-r7, r9-r11, lr}	)
+	stmfd	sp!, {r4-r6, r9-r10, lr}
 	bl	v7_flush_dcache_all
 	mov	r0, #0
 	ALT_SMP(mcr	p15, 0, r0, c7, c1, 0)	@ invalidate I-cache inner shareable
 	ALT_UP(mcr	p15, 0, r0, c7, c5, 0)	@ I+BTB cache invalidate
- ARM(	ldmfd	sp!, {r4-r5, r7, r9-r11, lr}	)
- THUMB(	ldmfd	sp!, {r4-r7, r9-r11, lr}	)
+	ldmfd	sp!, {r4-r6, r9-r10, lr}
 	ret	lr
 ENDPROC(v7_flush_kern_cache_all)
 
@@ -210,14 +208,12 @@ ENDPROC(v7_flush_kern_cache_all)
  *     Invalidate the I-cache to the point of unification.
  */
 ENTRY(v7_flush_kern_cache_louis)
- ARM(	stmfd	sp!, {r4-r5, r7, r9-r11, lr}	)
- THUMB(	stmfd	sp!, {r4-r7, r9-r11, lr}	)
+	stmfd	sp!, {r4-r6, r9-r10, lr}
 	bl	v7_flush_dcache_louis
 	mov	r0, #0
 	ALT_SMP(mcr	p15, 0, r0, c7, c1, 0)	@ invalidate I-cache inner shareable
 	ALT_UP(mcr	p15, 0, r0, c7, c5, 0)	@ I+BTB cache invalidate
- ARM(	ldmfd	sp!, {r4-r5, r7, r9-r11, lr}	)
- THUMB(	ldmfd	sp!, {r4-r7, r9-r11, lr}	)
+	ldmfd	sp!, {r4-r6, r9-r10, lr}
 	ret	lr
 ENDPROC(v7_flush_kern_cache_louis)
 
diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c
index 48091870db89..4204ffa2d104 100644
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@@ -240,8 +240,7 @@ void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk)
 	unsigned int cpu = smp_processor_id();
 	u64 asid;
 
-	if (unlikely(mm->context.vmalloc_seq != init_mm.context.vmalloc_seq))
-		__check_vmalloc_seq(mm);
+	check_vmalloc_seq(mm);
 
 	/*
 	 * We cannot update the pgd and the ASID atomicly with classic
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index 197f8eb3a775..aa08bcb72db9 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -117,16 +117,21 @@ EXPORT_SYMBOL(ioremap_page);
 
 void __check_vmalloc_seq(struct mm_struct *mm)
 {
-	unsigned int seq;
+	int seq;
 
 	do {
-		seq = init_mm.context.vmalloc_seq;
+		seq = atomic_read(&init_mm.context.vmalloc_seq);
 		memcpy(pgd_offset(mm, VMALLOC_START),
 		       pgd_offset_k(VMALLOC_START),
 		       sizeof(pgd_t) * (pgd_index(VMALLOC_END) -
 					pgd_index(VMALLOC_START)));
-		mm->context.vmalloc_seq = seq;
-	} while (seq != init_mm.context.vmalloc_seq);
+		/*
+		 * Use a store-release so that other CPUs that observe the
+		 * counter's new value are guaranteed to see the results of the
+		 * memcpy as well.
+		 */
+		atomic_set_release(&mm->context.vmalloc_seq, seq);
+	} while (seq != atomic_read(&init_mm.context.vmalloc_seq));
 }
 
 #if !defined(CONFIG_SMP) && !defined(CONFIG_ARM_LPAE)
@@ -157,7 +162,7 @@ static void unmap_area_sections(unsigned long virt, unsigned long size)
 			 * Note: this is still racy on SMP machines.
 			 */
 			pmd_clear(pmdp);
-			init_mm.context.vmalloc_seq++;
+			atomic_inc_return_release(&init_mm.context.vmalloc_seq);
 
 			/*
 			 * Free the page table, if there was one.
@@ -174,8 +179,7 @@ static void unmap_area_sections(unsigned long virt, unsigned long size)
 	 * Ensure that the active_mm is up to date - we want to
 	 * catch any use-after-iounmap cases.
 	 */
-	if (current->active_mm->context.vmalloc_seq != init_mm.context.vmalloc_seq)
-		__check_vmalloc_seq(current->active_mm);
+	check_vmalloc_seq(current->active_mm);
 
 	flush_tlb_kernel_range(virt, end);
 }