Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Catalin Marinas:
 "Mostly refactoring/clean-up:

   - CPU ops and PSCI (Power State Coordination Interface) refactoring
     following the merging of the arm64 ACPI support, together with
     handling of Trusted (secure) OS instances

   - Using fixmap for permanent FDT mapping, removing the initial dtb
     placement requirements (within 512MB from the start of the kernel
     image).  This required moving the FDT self reservation out of the
     memreserve processing

   - Idmap (1:1 mapping used for MMU on/off) handling clean-up

   - Removing flush_cache_all() - not safe on ARM unless the MMU is off.
     Last stages of CPU power down/up are handled by firmware already

   - "Alternatives" (run-time code patching) refactoring and support for
     immediate branch patching, GICv3 CPU interface access

   - User faults handling clean-up

  And some fixes:

   - Fix for VDSO building with broken ELF toolchains

   - Fix another case of init_mm.pgd usage for user mappings (during
     ASID roll-over broadcasting)

   - Fix for FPSIMD reloading after CPU hotplug

   - Fix for missing syscall trace exit

   - Workaround for .inst asm bug

   - Compat fix for switching the user tls tpidr_el0 register"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (42 commits)
  arm64: use private ratelimit state along with show_unhandled_signals
  arm64: show unhandled SP/PC alignment faults
  arm64: vdso: work-around broken ELF toolchains in Makefile
  arm64: kernel: rename __cpu_suspend to keep it aligned with arm
  arm64: compat: print compat_sp instead of sp
  arm64: mm: Fix freeing of the wrong memmap entries with !SPARSEMEM_VMEMMAP
  arm64: entry: fix context tracking for el0_sp_pc
  arm64: defconfig: enable memtest
  arm64: mm: remove reference to tlb.S from comment block
  arm64: Do not attempt to use init_mm in reset_context()
  arm64: KVM: Switch vgic save/restore to alternative_insn
  arm64: alternative: Introduce feature for GICv3 CPU interface
  arm64: psci: fix !CONFIG_HOTPLUG_CPU build warning
  arm64: fix bug for reloading FPSIMD state after CPU hotplug.
  arm64: kernel thread don't need to save fpsimd context.
  arm64: fix missing syscall trace exit
  arm64: alternative: Work around .inst assembler bugs
  arm64: alternative: Merge alternative-asm.h into alternative.h
  arm64: alternative: Allow immediate branch as alternative instruction
  arm64: Rework alternate sequence for ARM erratum 845719
  ...

8 files changed, 87 insertions, 125 deletions

diff --git a/arch/arm64/mm/Makefile b/arch/arm64/mm/Makefile
index 773d37a..9d84feb 100644
--- a/arch/arm64/mm/Makefile
+++ b/arch/arm64/mm/Makefile
@@ -4,3 +4,5 @@ obj-y				:= dma-mapping.o extable.o fault.o init.o \
 				   context.o proc.o pageattr.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
 obj-$(CONFIG_ARM64_PTDUMP)	+= dump.o
+
+CFLAGS_mmu.o			:= -I$(srctree)/scripts/dtc/libfdt/
diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
index 2560e1e..bdeb5d3 100644
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -22,84 +22,11 @@
 #include <linux/init.h>
 #include <asm/assembler.h>
 #include <asm/cpufeature.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
 
 #include "proc-macros.S"
 
 /*
- *	__flush_dcache_all()
- *
- *	Flush the whole D-cache.
- *
- *	Corrupted registers: x0-x7, x9-x11
- */
-__flush_dcache_all:
-	dmb	sy				// ensure ordering with previous memory accesses
-	mrs	x0, clidr_el1			// read clidr
-	and	x3, x0, #0x7000000		// extract loc from clidr
-	lsr	x3, x3, #23			// left align loc bit field
-	cbz	x3, finished			// if loc is 0, then no need to clean
-	mov	x10, #0				// start clean at cache level 0
-loop1:
-	add	x2, x10, x10, lsr #1		// work out 3x current cache level
-	lsr	x1, x0, x2			// extract cache type bits from clidr
-	and	x1, x1, #7			// mask of the bits for current cache only
-	cmp	x1, #2				// see what cache we have at this level
-	b.lt	skip				// skip if no cache, or just i-cache
-	save_and_disable_irqs x9		// make CSSELR and CCSIDR access atomic
-	msr	csselr_el1, x10			// select current cache level in csselr
-	isb					// isb to sych the new cssr&csidr
-	mrs	x1, ccsidr_el1			// read the new ccsidr
-	restore_irqs x9
-	and	x2, x1, #7			// extract the length of the cache lines
-	add	x2, x2, #4			// add 4 (line length offset)
-	mov	x4, #0x3ff
-	and	x4, x4, x1, lsr #3		// find maximum number on the way size
-	clz	w5, w4				// find bit position of way size increment
-	mov	x7, #0x7fff
-	and	x7, x7, x1, lsr #13		// extract max number of the index size
-loop2:
-	mov	x9, x4				// create working copy of max way size
-loop3:
-	lsl	x6, x9, x5
-	orr	x11, x10, x6			// factor way and cache number into x11
-	lsl	x6, x7, x2
-	orr	x11, x11, x6			// factor index number into x11
-	dc	cisw, x11			// clean & invalidate by set/way
-	subs	x9, x9, #1			// decrement the way
-	b.ge	loop3
-	subs	x7, x7, #1			// decrement the index
-	b.ge	loop2
-skip:
-	add	x10, x10, #2			// increment cache number
-	cmp	x3, x10
-	b.gt	loop1
-finished:
-	mov	x10, #0				// swith back to cache level 0
-	msr	csselr_el1, x10			// select current cache level in csselr
-	dsb	sy
-	isb
-	ret
-ENDPROC(__flush_dcache_all)
-
-/*
- *	flush_cache_all()
- *
- *	Flush the entire cache system.  The data cache flush is now achieved
- *	using atomic clean / invalidates working outwards from L1 cache. This
- *	is done using Set/Way based cache maintainance instructions.  The
- *	instruction cache can still be invalidated back to the point of
- *	unification in a single instruction.
- */
-ENTRY(flush_cache_all)
-	mov	x12, lr
-	bl	__flush_dcache_all
-	mov	x0, #0
-	ic	ialluis				// I+BTB cache invalidate
-	ret	x12
-ENDPROC(flush_cache_all)
-
-/*
  *	flush_icache_range(start,end)
  *
  *	Ensure that the I and D caches are coherent within specified region.
diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
index baa758d..76c1e6c 100644
--- a/arch/arm64/mm/context.c
+++ b/arch/arm64/mm/context.c
@@ -92,6 +92,14 @@ static void reset_context(void *info)
 	unsigned int cpu = smp_processor_id();
 	struct mm_struct *mm = current->active_mm;
 
+	/*
+	 * current->active_mm could be init_mm for the idle thread immediately
+	 * after secondary CPU boot or hotplug. TTBR0_EL1 is already set to
+	 * the reserved value, so no need to reset any context.
+	 */
+	if (mm == &init_mm)
+		return;
+
 	smp_rmb();
 	asid = cpu_last_asid + cpu;
 
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 0948d32..b1fc69c 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -115,8 +115,7 @@ static void __do_user_fault(struct task_struct *tsk, unsigned long addr,
 {
 	struct siginfo si;
 
-	if (show_unhandled_signals && unhandled_signal(tsk, sig) &&
-	    printk_ratelimit()) {
+	if (show_unhandled_signals_ratelimited() && unhandled_signal(tsk, sig)) {
 		pr_info("%s[%d]: unhandled %s (%d) at 0x%08lx, esr 0x%03x\n",
 			tsk->comm, task_pid_nr(tsk), fault_name(esr), sig,
 			addr, esr);
@@ -478,12 +477,19 @@ asmlinkage void __exception do_sp_pc_abort(unsigned long addr,
 					   struct pt_regs *regs)
 {
 	struct siginfo info;
+	struct task_struct *tsk = current;
+
+	if (show_unhandled_signals && unhandled_signal(tsk, SIGBUS))
+		pr_info_ratelimited("%s[%d]: %s exception: pc=%p sp=%p\n",
+				    tsk->comm, task_pid_nr(tsk),
+				    esr_get_class_string(esr), (void *)regs->pc,
+				    (void *)regs->sp);
 
 	info.si_signo = SIGBUS;
 	info.si_errno = 0;
 	info.si_code  = BUS_ADRALN;
 	info.si_addr  = (void __user *)addr;
-	arm64_notify_die("", regs, &info, esr);
+	arm64_notify_die("Oops - SP/PC alignment exception", regs, &info, esr);
 }
 
 static struct fault_info debug_fault_info[] = {
diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index b6f14e8..4dfa397 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -102,7 +102,6 @@ EXPORT_SYMBOL(flush_dcache_page);
 /*
  * Additional functions defined in assembly.
  */
-EXPORT_SYMBOL(flush_cache_all);
 EXPORT_SYMBOL(flush_icache_range);
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 597831b..ad87ce8 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -262,7 +262,7 @@ static void __init free_unused_memmap(void)
 		 * memmap entries are valid from the bank end aligned to
 		 * MAX_ORDER_NR_PAGES.
 		 */
-		prev_end = ALIGN(start + __phys_to_pfn(reg->size),
+		prev_end = ALIGN(__phys_to_pfn(reg->base + reg->size),
 				 MAX_ORDER_NR_PAGES);
 	}
 
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 5b8b664..82d3435 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -21,6 +21,7 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/init.h>
+#include <linux/libfdt.h>
 #include <linux/mman.h>
 #include <linux/nodemask.h>
 #include <linux/memblock.h>
@@ -643,3 +644,68 @@ void __set_fixmap(enum fixed_addresses idx,
 		flush_tlb_kernel_range(addr, addr+PAGE_SIZE);
 	}
 }
+
+void *__init fixmap_remap_fdt(phys_addr_t dt_phys)
+{
+	const u64 dt_virt_base = __fix_to_virt(FIX_FDT);
+	pgprot_t prot = PAGE_KERNEL | PTE_RDONLY;
+	int granularity, size, offset;
+	void *dt_virt;
+
+	/*
+	 * Check whether the physical FDT address is set and meets the minimum
+	 * alignment requirement. Since we are relying on MIN_FDT_ALIGN to be
+	 * at least 8 bytes so that we can always access the size field of the
+	 * FDT header after mapping the first chunk, double check here if that
+	 * is indeed the case.
+	 */
+	BUILD_BUG_ON(MIN_FDT_ALIGN < 8);
+	if (!dt_phys || dt_phys % MIN_FDT_ALIGN)
+		return NULL;
+
+	/*
+	 * Make sure that the FDT region can be mapped without the need to
+	 * allocate additional translation table pages, so that it is safe
+	 * to call create_mapping() this early.
+	 *
+	 * On 64k pages, the FDT will be mapped using PTEs, so we need to
+	 * be in the same PMD as the rest of the fixmap.
+	 * On 4k pages, we'll use section mappings for the FDT so we only
+	 * have to be in the same PUD.
+	 */
+	BUILD_BUG_ON(dt_virt_base % SZ_2M);
+
+	if (IS_ENABLED(CONFIG_ARM64_64K_PAGES)) {
+		BUILD_BUG_ON(__fix_to_virt(FIX_FDT_END) >> PMD_SHIFT !=
+			     __fix_to_virt(FIX_BTMAP_BEGIN) >> PMD_SHIFT);
+
+		granularity = PAGE_SIZE;
+	} else {
+		BUILD_BUG_ON(__fix_to_virt(FIX_FDT_END) >> PUD_SHIFT !=
+			     __fix_to_virt(FIX_BTMAP_BEGIN) >> PUD_SHIFT);
+
+		granularity = PMD_SIZE;
+	}
+
+	offset = dt_phys % granularity;
+	dt_virt = (void *)dt_virt_base + offset;
+
+	/* map the first chunk so we can read the size from the header */
+	create_mapping(round_down(dt_phys, granularity), dt_virt_base,
+		       granularity, prot);
+
+	if (fdt_check_header(dt_virt) != 0)
+		return NULL;
+
+	size = fdt_totalsize(dt_virt);
+	if (size > MAX_FDT_SIZE)
+		return NULL;
+
+	if (offset + size > granularity)
+		create_mapping(round_down(dt_phys, granularity), dt_virt_base,
+			       round_up(offset + size, granularity), prot);
+
+	memblock_reserve(dt_phys, size);
+
+	return dt_virt;
+}
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index cdd754e..39139a3 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -46,52 +46,6 @@
 #define MAIR(attr, mt)	((attr) << ((mt) * 8))
 
 /*
- *	cpu_cache_off()
- *
- *	Turn the CPU D-cache off.
- */
-ENTRY(cpu_cache_off)
-	mrs	x0, sctlr_el1
-	bic	x0, x0, #1 << 2			// clear SCTLR.C
-	msr	sctlr_el1, x0
-	isb
-	ret
-ENDPROC(cpu_cache_off)
-
-/*
- *	cpu_reset(loc)
- *
- *	Perform a soft reset of the system.  Put the CPU into the same state
- *	as it would be if it had been reset, and branch to what would be the
- *	reset vector. It must be executed with the flat identity mapping.
- *
- *	- loc   - location to jump to for soft reset
- */
-	.align	5
-ENTRY(cpu_reset)
-	mrs	x1, sctlr_el1
-	bic	x1, x1, #1
-	msr	sctlr_el1, x1			// disable the MMU
-	isb
-	ret	x0
-ENDPROC(cpu_reset)
-
-ENTRY(cpu_soft_restart)
-	/* Save address of cpu_reset() and reset address */
-	mov	x19, x0
-	mov	x20, x1
-
-	/* Turn D-cache off */
-	bl	cpu_cache_off
-
-	/* Push out all dirty data, and ensure cache is empty */
-	bl	flush_cache_all
-
-	mov	x0, x20
-	ret	x19
-ENDPROC(cpu_soft_restart)
-
-/*
  *	cpu_do_idle()
  *
  *	Idle the processor (wait for interrupt).