Merge branch '4.14-features' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus

Pull MIPS updates from Ralf Baechle:
 "This is the main pull request for 4.14 for MIPS; below a summary of
  the non-merge commits:

  CM:
   - Rename mips_cm_base to mips_gcr_base
   - Specify register size when generating accessors
   - Use BIT/GENMASK for register fields, order & drop shifts
   - Add cluster & block args to mips_cm_lock_other()

  CPC:
   - Use common CPS accessor generation macros
   - Use BIT/GENMASK for register fields, order & drop shifts
   - Introduce register modify (set/clear/change) accessors
   - Use change_*, set_* & clear_* where appropriate
   - Add CM/CPC 3.5 register definitions
   - Use GlobalNumber macros rather than magic numbers
   - Have asm/mips-cps.h include CM & CPC headers
   - Cluster support for topology functions
   - Detect CPUs in secondary clusters

  CPS:
   - Read GIC_VL_IDENT directly, not via irqchip driver

  DMA:
   - Consolidate coherent and non-coherent dma_alloc code
   - Don't use dma_cache_sync to implement fd_cacheflush

  FPU emulation / FP assist code:
   - Another series of 14 commits fixing corner cases such as NaN
     propgagation and other special input values.
   - Zero bits 32-63 of the result for a CLASS.D instruction.
   - Enhanced statics via debugfs
   - Do not use bools for arithmetic. GCC 7.1 moans about this.
   - Correct user fault_addr type

  Generic MIPS:
   - Enhancement of stack backtraces
   - Cleanup from non-existing options
   - Handle non word sized instructions when examining frame
   - Fix detection and decoding of ADDIUSP instruction
   - Fix decoding of SWSP16 instruction
   - Refactor handling of stack pointer in get_frame_info
   - Remove unreachable code from force_fcr31_sig()
   - Convert to using %pOF instead of full_name
   - Remove the R6000 support.
   - Move FP code from *_switch.S to *_fpu.S
   - Remove unused ST_OFF from r2300_switch.S
   - Allow platform to specify multiple its.S files
   - Add #includes to various files to ensure code builds reliable and
     without warning..
   - Remove __invalidate_kernel_vmap_range
   - Remove plat_timer_setup
   - Declare various variables & functions static
   - Abstract CPU core & VP(E) ID access through accessor functions
   - Store core & VP IDs in GlobalNumber-style variable
   - Unify checks for sibling CPUs
   - Add CPU cluster number accessors
   - Prevent direct use of generic_defconfig
   - Make CONFIG_MIPS_MT_SMP default y
   - Add __ioread64_copy
   - Remove unnecessary inclusions of linux/irqchip/mips-gic.h

  GIC:
   - Introduce asm/mips-gic.h with accessor functions
   - Use new GIC accessor functions in mips-gic-timer
   - Remove counter access functions from irq-mips-gic.c
   - Remove gic_read_local_vp_id() from irq-mips-gic.c
   - Simplify shared interrupt pending/mask reads in irq-mips-gic.c
   - Simplify gic_local_irq_domain_map() in irq-mips-gic.c
   - Drop gic_(re)set_mask() functions in irq-mips-gic.c
   - Remove gic_set_polarity(), gic_set_trigger(), gic_set_dual_edge(),
     gic_map_to_pin() and gic_map_to_vpe() from irq-mips-gic.c.
   - Convert remaining shared reg access, local int mask access and
     remaining local reg access to new accessors
   - Move GIC_LOCAL_INT_* to asm/mips-gic.h
   - Remove GIC_CPU_INT* macros from irq-mips-gic.c
   - Move various definitions to the driver
   - Remove gic_get_usm_range()
   - Remove __gic_irq_dispatch() forward declaration
   - Remove gic_init()
   - Use mips_gic_present() in place of gic_present and remove
     gic_present
   - Move gic_get_c0_*_int() to asm/mips-gic.h
   - Remove linux/irqchip/mips-gic.h
   - Inline __gic_init()
   - Inline gic_basic_init()
   - Make pcpu_masks a per-cpu variable
   - Use pcpu_masks to avoid reading GIC_SH_MASK*
   - Clean up mti, reserved-cpu-vectors handling
   - Use cpumask_first_and() in gic_set_affinity()
   - Let the core set struct irq_common_data affinity

  microMIPS:
   - Fix microMIPS stack unwinding on big endian systems

  MIPS-GIC:
   - SYNC after enabling GIC region

  NUMA:
   - Remove the unused parent_node() macro

  R6:
   - Constify r2_decoder_tables
   - Add accessor & bit definitions for GlobalNumber

  SMP:
   - Constify smp ops
   - Allow boot_secondary SMP op to return errors

  VDSO:
   - Drop gic_get_usm_range() usage
   - Avoid use of linux/irqchip/mips-gic.h

  Platform changes:

  Alchemy:
   - Add devboard machine type to cpuinfo
   - update cpu feature overrides
   - Threaded carddetect irqs for devboards

  AR7:
   - allow NULL clock for clk_get_rate

  BCM63xx:
   - Fix ENETDMA_6345_MAXBURST_REG offset
   - Allow NULL clock for clk_get_rate

  CI20:
   - Enable GPIO and RTC drivers in defconfig
   - Add ethernet and fixed-regulator nodes to DTS

  Generic platform:
   - Move Boston and NI 169445 FIT image source to their own files
   - Include asm/bootinfo.h for plat_fdt_relocated()
   - Include asm/time.h for get_c0_*_int()
   - Include asm/bootinfo.h for plat_fdt_relocated()
   - Include asm/time.h for get_c0_*_int()
   - Allow filtering enabled boards by requirements
   - Don't explicitly disable CONFIG_USB_SUPPORT
   - Bump default NR_CPUS to 16

  JZ4700:
   - Probe the jz4740-rtc driver from devicetree

  Lantiq:
   - Drop check of boot select from the spi-falcon driver.
   - Drop check of boot select from the lantiq-flash MTD driver.
   - Access boot cause register in the watchdog driver through regmap
   - Add device tree binding documentation for the watchdog driver
   - Add docs for the RCU DT bindings.
   - Convert the fpi bus driver to a platform_driver
   - Remove ltq_reset_cause() and ltq_boot_select(
   - Switch to a proper reset driver
   - Switch to a new drivers/soc GPHY driver
   - Add an USB PHY driver for the Lantiq SoCs using the RCU module
   - Use of_platform_default_populate instead of __dt_register_buses
   - Enable MFD_SYSCON to be able to use it for the RCU MFD
   - Replace ltq_boot_select() with dummy implementation.

  Loongson 2F:
   - Allow NULL clock for clk_get_rate

  Malta:
   - Use new GIC accessor functions

  NI 169445:
   - Add support for NI 169445 board.
   - Only include in 32r2el kernels

  Octeon:
   - Add support for watchdog of 78XX SOCs.
   - Add support for watchdog of CN68XX SOCs.
   - Expose support for mips32r1, mips32r2 and mips64r1
   - Enable more drivers in config file
   - Add support for accessing the boot vector.
   - Remove old boot vector code from watchdog driver
   - Define watchdog registers for 70xx, 73xx, 78xx, F75xx.
   - Make CSR functions node aware.
   - Allow access to CIU3 IRQ domains.
   - Misc cleanups in the watchdog driver

  Omega2+:
   - New board, add support and defconfig

  Pistachio:
   - Enable Root FS on NFS in defconfig

  Ralink:
   - Add Mediatek MT7628A SoC
   - Allow NULL clock for clk_get_rate
   - Explicitly request exclusive reset control in the pci-mt7620 PCI driver.

  SEAD3:
   - Only include in 32 bit kernels by default

  VoCore:
   - Add VoCore as a vendor t0 dt-bindings
   - Add defconfig file"

* '4.14-features' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus: (167 commits)
  MIPS: Refactor handling of stack pointer in get_frame_info
  MIPS: Stacktrace: Fix microMIPS stack unwinding on big endian systems
  MIPS: microMIPS: Fix decoding of swsp16 instruction
  MIPS: microMIPS: Fix decoding of addiusp instruction
  MIPS: microMIPS: Fix detection of addiusp instruction
  MIPS: Handle non word sized instructions when examining frame
  MIPS: ralink: allow NULL clock for clk_get_rate
  MIPS: Loongson 2F: allow NULL clock for clk_get_rate
  MIPS: BCM63XX: allow NULL clock for clk_get_rate
  MIPS: AR7: allow NULL clock for clk_get_rate
  MIPS: BCM63XX: fix ENETDMA_6345_MAXBURST_REG offset
  mips: Save all registers when saving the frame
  MIPS: Add DWARF unwinding to assembly
  MIPS: Make SAVE_SOME more standard
  MIPS: Fix issues in backtraces
  MIPS: jz4780: DTS: Probe the jz4740-rtc driver from devicetree
  MIPS: Ci20: Enable RTC driver
  watchdog: octeon-wdt: Add support for 78XX SOCs.
  watchdog: octeon-wdt: Add support for cn68XX SOCs.
  watchdog: octeon-wdt: File cleaning.
  ...

1 files changed, 168 insertions, 112 deletions

diff --git a/arch/mips/include/asm/stackframe.h b/arch/mips/include/asm/stackframe.h
index eaa5a4d7d5e5..5d3563c55e0c 100644
--- a/arch/mips/include/asm/stackframe.h
+++ b/arch/mips/include/asm/stackframe.h
@@ -19,20 +19,43 @@
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
 
+/* Make the addition of cfi info a little easier. */
+	.macro cfi_rel_offset reg offset=0 docfi=0
+	.if \docfi
+	.cfi_rel_offset \reg, \offset
+	.endif
+	.endm
+
+	.macro cfi_st reg offset=0 docfi=0
+	LONG_S	\reg, \offset(sp)
+	cfi_rel_offset \reg, \offset, \docfi
+	.endm
+
+	.macro cfi_restore reg offset=0 docfi=0
+	.if \docfi
+	.cfi_restore \reg
+	.endif
+	.endm
+
+	.macro cfi_ld reg offset=0 docfi=0
+	LONG_L	\reg, \offset(sp)
+	cfi_restore \reg \offset \docfi
+	.endm
+
 #if defined(CONFIG_CPU_R3000) || defined(CONFIG_CPU_TX39XX)
 #define STATMASK 0x3f
 #else
 #define STATMASK 0x1f
 #endif
 
-		.macro	SAVE_AT
+		.macro	SAVE_AT docfi=0
 		.set	push
 		.set	noat
-		LONG_S	$1, PT_R1(sp)
+		cfi_st	$1, PT_R1, \docfi
 		.set	pop
 		.endm
 
-		.macro	SAVE_TEMP
+		.macro	SAVE_TEMP docfi=0
 #ifdef CONFIG_CPU_HAS_SMARTMIPS
 		mflhxu	v1
 		LONG_S	v1, PT_LO(sp)
@@ -44,20 +67,20 @@
 		mfhi	v1
 #endif
 #ifdef CONFIG_32BIT
-		LONG_S	$8, PT_R8(sp)
-		LONG_S	$9, PT_R9(sp)
+		cfi_st	$8, PT_R8, \docfi
+		cfi_st	$9, PT_R9, \docfi
 #endif
-		LONG_S	$10, PT_R10(sp)
-		LONG_S	$11, PT_R11(sp)
-		LONG_S	$12, PT_R12(sp)
+		cfi_st	$10, PT_R10, \docfi
+		cfi_st	$11, PT_R11, \docfi
+		cfi_st	$12, PT_R12, \docfi
 #if !defined(CONFIG_CPU_HAS_SMARTMIPS) && !defined(CONFIG_CPU_MIPSR6)
 		LONG_S	v1, PT_HI(sp)
 		mflo	v1
 #endif
-		LONG_S	$13, PT_R13(sp)
-		LONG_S	$14, PT_R14(sp)
-		LONG_S	$15, PT_R15(sp)
-		LONG_S	$24, PT_R24(sp)
+		cfi_st	$13, PT_R13, \docfi
+		cfi_st	$14, PT_R14, \docfi
+		cfi_st	$15, PT_R15, \docfi
+		cfi_st	$24, PT_R24, \docfi
 #if !defined(CONFIG_CPU_HAS_SMARTMIPS) && !defined(CONFIG_CPU_MIPSR6)
 		LONG_S	v1, PT_LO(sp)
 #endif
@@ -71,20 +94,28 @@
 #endif
 		.endm
 
-		.macro	SAVE_STATIC
-		LONG_S	$16, PT_R16(sp)
-		LONG_S	$17, PT_R17(sp)
-		LONG_S	$18, PT_R18(sp)
-		LONG_S	$19, PT_R19(sp)
-		LONG_S	$20, PT_R20(sp)
-		LONG_S	$21, PT_R21(sp)
-		LONG_S	$22, PT_R22(sp)
-		LONG_S	$23, PT_R23(sp)
-		LONG_S	$30, PT_R30(sp)
+		.macro	SAVE_STATIC docfi=0
+		cfi_st	$16, PT_R16, \docfi
+		cfi_st	$17, PT_R17, \docfi
+		cfi_st	$18, PT_R18, \docfi
+		cfi_st	$19, PT_R19, \docfi
+		cfi_st	$20, PT_R20, \docfi
+		cfi_st	$21, PT_R21, \docfi
+		cfi_st	$22, PT_R22, \docfi
+		cfi_st	$23, PT_R23, \docfi
+		cfi_st	$30, PT_R30, \docfi
 		.endm
 
+/*
+ * get_saved_sp returns the SP for the current CPU by looking in the
+ * kernelsp array for it.  If tosp is set, it stores the current sp in
+ * k0 and loads the new value in sp.  If not, it clobbers k0 and
+ * stores the new value in k1, leaving sp unaffected.
+ */
 #ifdef CONFIG_SMP
-		.macro	get_saved_sp	/* SMP variation */
+
+		/* SMP variation */
+		.macro	get_saved_sp docfi=0 tosp=0
 		ASM_CPUID_MFC0	k0, ASM_SMP_CPUID_REG
 #if defined(CONFIG_32BIT) || defined(KBUILD_64BIT_SYM32)
 		lui	k1, %hi(kernelsp)
@@ -97,7 +128,15 @@
 #endif
 		LONG_SRL	k0, SMP_CPUID_PTRSHIFT
 		LONG_ADDU	k1, k0
+		.if \tosp
+		move	k0, sp
+		.if \docfi
+		.cfi_register sp, k0
+		.endif
+		LONG_L	sp, %lo(kernelsp)(k1)
+		.else
 		LONG_L	k1, %lo(kernelsp)(k1)
+		.endif
 		.endm
 
 		.macro	set_saved_sp stackp temp temp2
@@ -106,7 +145,8 @@
 		LONG_S	\stackp, kernelsp(\temp)
 		.endm
 #else /* !CONFIG_SMP */
-		.macro	get_saved_sp	/* Uniprocessor variation */
+		/* Uniprocessor variation */
+		.macro	get_saved_sp docfi=0 tosp=0
 #ifdef CONFIG_CPU_JUMP_WORKAROUNDS
 		/*
 		 * Clear BTB (branch target buffer), forbid RAS (return address
@@ -135,7 +175,15 @@
 		daddiu	k1, %hi(kernelsp)
 		dsll	k1, k1, 16
 #endif
+		.if \tosp
+		move	k0, sp
+		.if \docfi
+		.cfi_register sp, k0
+		.endif
+		LONG_L	sp, %lo(kernelsp)(k1)
+		.else
 		LONG_L	k1, %lo(kernelsp)(k1)
+		.endif
 		.endm
 
 		.macro	set_saved_sp stackp temp temp2
@@ -143,7 +191,7 @@
 		.endm
 #endif
 
-		.macro	SAVE_SOME
+		.macro	SAVE_SOME docfi=0
 		.set	push
 		.set	noat
 		.set	reorder
@@ -151,7 +199,6 @@
 		sll	k0, 3		/* extract cu0 bit */
 		.set	noreorder
 		bltz	k0, 8f
-		 move	k1, sp
 #ifdef CONFIG_EVA
 		/*
 		 * Flush interAptiv's Return Prediction Stack (RPS) by writing
@@ -178,20 +225,26 @@
 		MTC0	k0, CP0_ENTRYHI
 #endif
 		.set	reorder
+		 move	k0, sp
+		.if \docfi
+		.cfi_register sp, k0
+		.endif
 		/* Called from user mode, new stack. */
-		get_saved_sp
-#ifndef CONFIG_CPU_DADDI_WORKAROUNDS
-8:		move	k0, sp
-		PTR_SUBU sp, k1, PT_SIZE
-#else
-		.set	at=k0
-8:		PTR_SUBU k1, PT_SIZE
+		get_saved_sp docfi=\docfi tosp=1
+8:
+#ifdef CONFIG_CPU_DADDI_WORKAROUNDS
+		.set	at=k1
+#endif
+		PTR_SUBU sp, PT_SIZE
+#ifdef CONFIG_CPU_DADDI_WORKAROUNDS
 		.set	noat
-		move	k0, sp
-		move	sp, k1
 #endif
-		LONG_S	k0, PT_R29(sp)
-		LONG_S	$3, PT_R3(sp)
+		.if \docfi
+		.cfi_def_cfa sp,0
+		.endif
+		cfi_st	k0, PT_R29, \docfi
+		cfi_rel_offset  sp, PT_R29, \docfi
+		cfi_st	v1, PT_R3, \docfi
 		/*
 		 * You might think that you don't need to save $0,
 		 * but the FPU emulator and gdb remote debug stub
@@ -199,23 +252,26 @@
 		 */
 		LONG_S	$0, PT_R0(sp)
 		mfc0	v1, CP0_STATUS
-		LONG_S	$2, PT_R2(sp)
+		cfi_st	v0, PT_R2, \docfi
 		LONG_S	v1, PT_STATUS(sp)
-		LONG_S	$4, PT_R4(sp)
+		cfi_st	$4, PT_R4, \docfi
 		mfc0	v1, CP0_CAUSE
-		LONG_S	$5, PT_R5(sp)
+		cfi_st	$5, PT_R5, \docfi
 		LONG_S	v1, PT_CAUSE(sp)
-		LONG_S	$6, PT_R6(sp)
-		MFC0	v1, CP0_EPC
-		LONG_S	$7, PT_R7(sp)
+		cfi_st	$6, PT_R6, \docfi
+		cfi_st	ra, PT_R31, \docfi
+		MFC0	ra, CP0_EPC
+		cfi_st	$7, PT_R7, \docfi
 #ifdef CONFIG_64BIT
-		LONG_S	$8, PT_R8(sp)
-		LONG_S	$9, PT_R9(sp)
+		cfi_st	$8, PT_R8, \docfi
+		cfi_st	$9, PT_R9, \docfi
 #endif
-		LONG_S	v1, PT_EPC(sp)
-		LONG_S	$25, PT_R25(sp)
-		LONG_S	$28, PT_R28(sp)
-		LONG_S	$31, PT_R31(sp)
+		LONG_S	ra, PT_EPC(sp)
+		.if \docfi
+		.cfi_rel_offset ra, PT_EPC
+		.endif
+		cfi_st	$25, PT_R25, \docfi
+		cfi_st	$28, PT_R28, \docfi
 
 		/* Set thread_info if we're coming from user mode */
 		mfc0	k0, CP0_STATUS
@@ -232,21 +288,21 @@
 		.set	pop
 		.endm
 
-		.macro	SAVE_ALL
-		SAVE_SOME
-		SAVE_AT
-		SAVE_TEMP
-		SAVE_STATIC
+		.macro	SAVE_ALL docfi=0
+		SAVE_SOME \docfi
+		SAVE_AT \docfi
+		SAVE_TEMP \docfi
+		SAVE_STATIC \docfi
 		.endm
 
-		.macro	RESTORE_AT
+		.macro	RESTORE_AT docfi=0
 		.set	push
 		.set	noat
-		LONG_L	$1,  PT_R1(sp)
+		cfi_ld	$1, PT_R1, \docfi
 		.set	pop
 		.endm
 
-		.macro	RESTORE_TEMP
+		.macro	RESTORE_TEMP docfi=0
 #ifdef CONFIG_CPU_CAVIUM_OCTEON
 		/* Restore the Octeon multiplier state */
 		jal	octeon_mult_restore
@@ -265,33 +321,37 @@
 		mthi	$24
 #endif
 #ifdef CONFIG_32BIT
-		LONG_L	$8, PT_R8(sp)
-		LONG_L	$9, PT_R9(sp)
+		cfi_ld	$8, PT_R8, \docfi
+		cfi_ld	$9, PT_R9, \docfi
 #endif
-		LONG_L	$10, PT_R10(sp)
-		LONG_L	$11, PT_R11(sp)
-		LONG_L	$12, PT_R12(sp)
-		LONG_L	$13, PT_R13(sp)
-		LONG_L	$14, PT_R14(sp)
-		LONG_L	$15, PT_R15(sp)
-		LONG_L	$24, PT_R24(sp)
+		cfi_ld	$10, PT_R10, \docfi
+		cfi_ld	$11, PT_R11, \docfi
+		cfi_ld	$12, PT_R12, \docfi
+		cfi_ld	$13, PT_R13, \docfi
+		cfi_ld	$14, PT_R14, \docfi
+		cfi_ld	$15, PT_R15, \docfi
+		cfi_ld	$24, PT_R24, \docfi
 		.endm
 
-		.macro	RESTORE_STATIC
-		LONG_L	$16, PT_R16(sp)
-		LONG_L	$17, PT_R17(sp)
-		LONG_L	$18, PT_R18(sp)
-		LONG_L	$19, PT_R19(sp)
-		LONG_L	$20, PT_R20(sp)
-		LONG_L	$21, PT_R21(sp)
-		LONG_L	$22, PT_R22(sp)
-		LONG_L	$23, PT_R23(sp)
-		LONG_L	$30, PT_R30(sp)
+		.macro	RESTORE_STATIC docfi=0
+		cfi_ld	$16, PT_R16, \docfi
+		cfi_ld	$17, PT_R17, \docfi
+		cfi_ld	$18, PT_R18, \docfi
+		cfi_ld	$19, PT_R19, \docfi
+		cfi_ld	$20, PT_R20, \docfi
+		cfi_ld	$21, PT_R21, \docfi
+		cfi_ld	$22, PT_R22, \docfi
+		cfi_ld	$23, PT_R23, \docfi
+		cfi_ld	$30, PT_R30, \docfi
+		.endm
+
+		.macro	RESTORE_SP docfi=0
+		cfi_ld	sp, PT_R29, \docfi
 		.endm
 
 #if defined(CONFIG_CPU_R3000) || defined(CONFIG_CPU_TX39XX)
 
-		.macro	RESTORE_SOME
+		.macro	RESTORE_SOME docfi=0
 		.set	push
 		.set	reorder
 		.set	noat
@@ -306,30 +366,30 @@
 		and	v0, v1
 		or	v0, a0
 		mtc0	v0, CP0_STATUS
-		LONG_L	$31, PT_R31(sp)
-		LONG_L	$28, PT_R28(sp)
-		LONG_L	$25, PT_R25(sp)
-		LONG_L	$7,  PT_R7(sp)
-		LONG_L	$6,  PT_R6(sp)
-		LONG_L	$5,  PT_R5(sp)
-		LONG_L	$4,  PT_R4(sp)
-		LONG_L	$3,  PT_R3(sp)
-		LONG_L	$2,  PT_R2(sp)
+		cfi_ld	$31, PT_R31, \docfi
+		cfi_ld	$28, PT_R28, \docfi
+		cfi_ld	$25, PT_R25, \docfi
+		cfi_ld	$7,  PT_R7, \docfi
+		cfi_ld	$6,  PT_R6, \docfi
+		cfi_ld	$5,  PT_R5, \docfi
+		cfi_ld	$4,  PT_R4, \docfi
+		cfi_ld	$3,  PT_R3, \docfi
+		cfi_ld	$2,  PT_R2, \docfi
 		.set	pop
 		.endm
 
-		.macro	RESTORE_SP_AND_RET
+		.macro	RESTORE_SP_AND_RET docfi=0
 		.set	push
 		.set	noreorder
 		LONG_L	k0, PT_EPC(sp)
-		LONG_L	sp, PT_R29(sp)
+		RESTORE_SP \docfi
 		jr	k0
 		 rfe
 		.set	pop
 		.endm
 
 #else
-		.macro	RESTORE_SOME
+		.macro	RESTORE_SOME docfi=0
 		.set	push
 		.set	reorder
 		.set	noat
@@ -346,24 +406,24 @@
 		mtc0	v0, CP0_STATUS
 		LONG_L	v1, PT_EPC(sp)
 		MTC0	v1, CP0_EPC
-		LONG_L	$31, PT_R31(sp)
-		LONG_L	$28, PT_R28(sp)
-		LONG_L	$25, PT_R25(sp)
+		cfi_ld	$31, PT_R31, \docfi
+		cfi_ld	$28, PT_R28, \docfi
+		cfi_ld	$25, PT_R25, \docfi
 #ifdef CONFIG_64BIT
-		LONG_L	$8, PT_R8(sp)
-		LONG_L	$9, PT_R9(sp)
+		cfi_ld	$8, PT_R8, \docfi
+		cfi_ld	$9, PT_R9, \docfi
 #endif
-		LONG_L	$7,  PT_R7(sp)
-		LONG_L	$6,  PT_R6(sp)
-		LONG_L	$5,  PT_R5(sp)
-		LONG_L	$4,  PT_R4(sp)
-		LONG_L	$3,  PT_R3(sp)
-		LONG_L	$2,  PT_R2(sp)
+		cfi_ld	$7,  PT_R7, \docfi
+		cfi_ld	$6,  PT_R6, \docfi
+		cfi_ld	$5,  PT_R5, \docfi
+		cfi_ld	$4,  PT_R4, \docfi
+		cfi_ld	$3,  PT_R3, \docfi
+		cfi_ld	$2,  PT_R2, \docfi
 		.set	pop
 		.endm
 
-		.macro	RESTORE_SP_AND_RET
-		LONG_L	sp, PT_R29(sp)
+		.macro	RESTORE_SP_AND_RET docfi=0
+		RESTORE_SP \docfi
 #ifdef CONFIG_CPU_MIPSR6
 		eretnc
 #else
@@ -375,16 +435,12 @@
 
 #endif
 
-		.macro	RESTORE_SP
-		LONG_L	sp, PT_R29(sp)
-		.endm
-
-		.macro	RESTORE_ALL
-		RESTORE_TEMP
-		RESTORE_STATIC
-		RESTORE_AT
-		RESTORE_SOME
-		RESTORE_SP
+		.macro	RESTORE_ALL docfi=0
+		RESTORE_TEMP \docfi
+		RESTORE_STATIC \docfi
+		RESTORE_AT \docfi
+		RESTORE_SOME \docfi
+		RESTORE_SP \docfi
 		.endm
 
 /*