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

Pull arm64 updates from Will Deacon:
 "A bunch of good stuff in here. Worth noting is that we've pulled in
  the x86/mm branch from -tip so that we can make use of the core
  ioremap changes which allow us to put down huge mappings in the
  vmalloc area without screwing up the TLB. Much of the positive
  diffstat is because of the rseq selftest for arm64.

  Summary:

   - Wire up support for qspinlock, replacing our trusty ticket lock
     code

   - Add an IPI to flush_icache_range() to ensure that stale
     instructions fetched into the pipeline are discarded along with the
     I-cache lines

   - Support for the GCC "stackleak" plugin

   - Support for restartable sequences, plus an arm64 port for the
     selftest

   - Kexec/kdump support on systems booting with ACPI

   - Rewrite of our syscall entry code in C, which allows us to zero the
     GPRs on entry from userspace

   - Support for chained PMU counters, allowing 64-bit event counters to
     be constructed on current CPUs

   - Ensure scheduler topology information is kept up-to-date with CPU
     hotplug events

   - Re-enable support for huge vmalloc/IO mappings now that the core
     code has the correct hooks to use break-before-make sequences

   - Miscellaneous, non-critical fixes and cleanups"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (90 commits)
  arm64: alternative: Use true and false for boolean values
  arm64: kexec: Add comment to explain use of __flush_icache_range()
  arm64: sdei: Mark sdei stack helper functions as static
  arm64, kaslr: export offset in VMCOREINFO ELF notes
  arm64: perf: Add cap_user_time aarch64
  efi/libstub: Only disable stackleak plugin for arm64
  arm64: drop unused kernel_neon_begin_partial() macro
  arm64: kexec: machine_kexec should call __flush_icache_range
  arm64: svc: Ensure hardirq tracing is updated before return
  arm64: mm: Export __sync_icache_dcache() for xen-privcmd
  drivers/perf: arm-ccn: Use devm_ioremap_resource() to map memory
  arm64: Add support for STACKLEAK gcc plugin
  arm64: Add stack information to on_accessible_stack
  drivers/perf: hisi: update the sccl_id/ccl_id when MT is supported
  arm64: fix ACPI dependencies
  rseq/selftests: Add support for arm64
  arm64: acpi: fix alignment fault in accessing ACPI
  efi/arm: map UEFI memory map even w/o runtime services enabled
  efi/arm: preserve early mapping of UEFI memory map longer for BGRT
  drivers: acpi: add dependency of EFI for arm64
  ...

1 files changed, 23 insertions, 137 deletions

diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 28ad8799406f..09dbea221a27 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -41,19 +41,9 @@
  * Context tracking subsystem.  Used to instrument transitions
  * between user and kernel mode.
  */
-	.macro ct_user_exit, syscall = 0
+	.macro ct_user_exit
 #ifdef CONFIG_CONTEXT_TRACKING
 	bl	context_tracking_user_exit
-	.if \syscall == 1
-	/*
-	 * Save/restore needed during syscalls.  Restore syscall arguments from
-	 * the values already saved on stack during kernel_entry.
-	 */
-	ldp	x0, x1, [sp]
-	ldp	x2, x3, [sp, #S_X2]
-	ldp	x4, x5, [sp, #S_X4]
-	ldp	x6, x7, [sp, #S_X6]
-	.endif
 #endif
 	.endm
 
@@ -63,6 +53,12 @@
 #endif
 	.endm
 
+	.macro	clear_gp_regs
+	.irp	n,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29
+	mov	x\n, xzr
+	.endr
+	.endm
+
 /*
  * Bad Abort numbers
  *-----------------
@@ -140,20 +136,21 @@ alternative_else_nop_endif
 
 	// This macro corrupts x0-x3. It is the caller's duty
 	// to save/restore them if required.
-	.macro	apply_ssbd, state, targ, tmp1, tmp2
+	.macro	apply_ssbd, state, tmp1, tmp2
 #ifdef CONFIG_ARM64_SSBD
 alternative_cb	arm64_enable_wa2_handling
-	b	\targ
+	b	.L__asm_ssbd_skip\@
 alternative_cb_end
 	ldr_this_cpu	\tmp2, arm64_ssbd_callback_required, \tmp1
-	cbz	\tmp2, \targ
+	cbz	\tmp2,	.L__asm_ssbd_skip\@
 	ldr	\tmp2, [tsk, #TSK_TI_FLAGS]
-	tbnz	\tmp2, #TIF_SSBD, \targ
+	tbnz	\tmp2, #TIF_SSBD, .L__asm_ssbd_skip\@
 	mov	w0, #ARM_SMCCC_ARCH_WORKAROUND_2
 	mov	w1, #\state
 alternative_cb	arm64_update_smccc_conduit
 	nop					// Patched to SMC/HVC #0
 alternative_cb_end
+.L__asm_ssbd_skip\@:
 #endif
 	.endm
 
@@ -178,20 +175,14 @@ alternative_cb_end
 	stp	x28, x29, [sp, #16 * 14]
 
 	.if	\el == 0
+	clear_gp_regs
 	mrs	x21, sp_el0
 	ldr_this_cpu	tsk, __entry_task, x20	// Ensure MDSCR_EL1.SS is clear,
 	ldr	x19, [tsk, #TSK_TI_FLAGS]	// since we can unmask debug
 	disable_step_tsk x19, x20		// exceptions when scheduling.
 
-	apply_ssbd 1, 1f, x22, x23
-
-#ifdef CONFIG_ARM64_SSBD
-	ldp	x0, x1, [sp, #16 * 0]
-	ldp	x2, x3, [sp, #16 * 1]
-#endif
-1:
+	apply_ssbd 1, x22, x23
 
-	mov	x29, xzr			// fp pointed to user-space
 	.else
 	add	x21, sp, #S_FRAME_SIZE
 	get_thread_info tsk
@@ -331,8 +322,7 @@ alternative_if ARM64_WORKAROUND_845719
 alternative_else_nop_endif
 #endif
 3:
-	apply_ssbd 0, 5f, x0, x1
-5:
+	apply_ssbd 0, x0, x1
 	.endif
 
 	msr	elr_el1, x21			// set up the return data
@@ -720,14 +710,9 @@ el0_sync_compat:
 	b.ge	el0_dbg
 	b	el0_inv
 el0_svc_compat:
-	/*
-	 * AArch32 syscall handling
-	 */
-	ldr	x16, [tsk, #TSK_TI_FLAGS]	// load thread flags
-	adrp	stbl, compat_sys_call_table	// load compat syscall table pointer
-	mov	wscno, w7			// syscall number in w7 (r7)
-	mov     wsc_nr, #__NR_compat_syscalls
-	b	el0_svc_naked
+	mov	x0, sp
+	bl	el0_svc_compat_handler
+	b	ret_to_user
 
 	.align	6
 el0_irq_compat:
@@ -896,25 +881,6 @@ el0_error_naked:
 	b	ret_to_user
 ENDPROC(el0_error)
 
-
-/*
- * This is the fast syscall return path.  We do as little as possible here,
- * and this includes saving x0 back into the kernel stack.
- */
-ret_fast_syscall:
-	disable_daif
-	str	x0, [sp, #S_X0]			// returned x0
-	ldr	x1, [tsk, #TSK_TI_FLAGS]	// re-check for syscall tracing
-	and	x2, x1, #_TIF_SYSCALL_WORK
-	cbnz	x2, ret_fast_syscall_trace
-	and	x2, x1, #_TIF_WORK_MASK
-	cbnz	x2, work_pending
-	enable_step_tsk x1, x2
-	kernel_exit 0
-ret_fast_syscall_trace:
-	enable_daif
-	b	__sys_trace_return_skipped	// we already saved x0
-
 /*
  * Ok, we need to do extra processing, enter the slow path.
  */
@@ -936,6 +902,9 @@ ret_to_user:
 	cbnz	x2, work_pending
 finish_ret_to_user:
 	enable_step_tsk x1, x2
+#ifdef CONFIG_GCC_PLUGIN_STACKLEAK
+	bl	stackleak_erase
+#endif
 	kernel_exit 0
 ENDPROC(ret_to_user)
 
@@ -944,85 +913,10 @@ ENDPROC(ret_to_user)
  */
 	.align	6
 el0_svc:
-	ldr	x16, [tsk, #TSK_TI_FLAGS]	// load thread flags
-	adrp	stbl, sys_call_table		// load syscall table pointer
-	mov	wscno, w8			// syscall number in w8
-	mov	wsc_nr, #__NR_syscalls
-
-#ifdef CONFIG_ARM64_SVE
-alternative_if_not ARM64_SVE
-	b	el0_svc_naked
-alternative_else_nop_endif
-	tbz	x16, #TIF_SVE, el0_svc_naked	// Skip unless TIF_SVE set:
-	bic	x16, x16, #_TIF_SVE		// discard SVE state
-	str	x16, [tsk, #TSK_TI_FLAGS]
-
-	/*
-	 * task_fpsimd_load() won't be called to update CPACR_EL1 in
-	 * ret_to_user unless TIF_FOREIGN_FPSTATE is still set, which only
-	 * happens if a context switch or kernel_neon_begin() or context
-	 * modification (sigreturn, ptrace) intervenes.
-	 * So, ensure that CPACR_EL1 is already correct for the fast-path case:
-	 */
-	mrs	x9, cpacr_el1
-	bic	x9, x9, #CPACR_EL1_ZEN_EL0EN	// disable SVE for el0
-	msr	cpacr_el1, x9			// synchronised by eret to el0
-#endif
-
-el0_svc_naked:					// compat entry point
-	stp	x0, xscno, [sp, #S_ORIG_X0]	// save the original x0 and syscall number
-	enable_daif
-	ct_user_exit 1
-
-	tst	x16, #_TIF_SYSCALL_WORK		// check for syscall hooks
-	b.ne	__sys_trace
-	cmp     wscno, wsc_nr			// check upper syscall limit
-	b.hs	ni_sys
-	mask_nospec64 xscno, xsc_nr, x19	// enforce bounds for syscall number
-	ldr	x16, [stbl, xscno, lsl #3]	// address in the syscall table
-	blr	x16				// call sys_* routine
-	b	ret_fast_syscall
-ni_sys:
-	mov	x0, sp
-	bl	do_ni_syscall
-	b	ret_fast_syscall
-ENDPROC(el0_svc)
-
-	/*
-	 * This is the really slow path.  We're going to be doing context
-	 * switches, and waiting for our parent to respond.
-	 */
-__sys_trace:
-	cmp     wscno, #NO_SYSCALL		// user-issued syscall(-1)?
-	b.ne	1f
-	mov	x0, #-ENOSYS			// set default errno if so
-	str	x0, [sp, #S_X0]
-1:	mov	x0, sp
-	bl	syscall_trace_enter
-	cmp	w0, #NO_SYSCALL			// skip the syscall?
-	b.eq	__sys_trace_return_skipped
-	mov	wscno, w0			// syscall number (possibly new)
-	mov	x1, sp				// pointer to regs
-	cmp	wscno, wsc_nr			// check upper syscall limit
-	b.hs	__ni_sys_trace
-	ldp	x0, x1, [sp]			// restore the syscall args
-	ldp	x2, x3, [sp, #S_X2]
-	ldp	x4, x5, [sp, #S_X4]
-	ldp	x6, x7, [sp, #S_X6]
-	ldr	x16, [stbl, xscno, lsl #3]	// address in the syscall table
-	blr	x16				// call sys_* routine
-
-__sys_trace_return:
-	str	x0, [sp, #S_X0]			// save returned x0
-__sys_trace_return_skipped:
 	mov	x0, sp
-	bl	syscall_trace_exit
+	bl	el0_svc_handler
 	b	ret_to_user
-
-__ni_sys_trace:
-	mov	x0, sp
-	bl	do_ni_syscall
-	b	__sys_trace_return
+ENDPROC(el0_svc)
 
 	.popsection				// .entry.text
 
@@ -1138,14 +1032,6 @@ __entry_tramp_data_start:
 #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
 
 /*
- * Special system call wrappers.
- */
-ENTRY(sys_rt_sigreturn_wrapper)
-	mov	x0, sp
-	b	sys_rt_sigreturn
-ENDPROC(sys_rt_sigreturn_wrapper)
-
-/*
  * Register switch for AArch64. The callee-saved registers need to be saved
  * and restored. On entry:
  *   x0 = previous task_struct (must be preserved across the switch)