Merge tag 'powerpc-4.9-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Highlights:
   - Major rework of Book3S 64-bit exception vectors (Nicholas Piggin)
   - Use gas sections for arranging exception vectors et. al.
   - Large set of TM cleanups and selftests (Cyril Bur)
   - Enable transactional memory (TM) lazily for userspace (Cyril Bur)
   - Support for XZ compression in the zImage wrapper (Oliver
     O'Halloran)
   - Add support for bpf constant blinding (Naveen N. Rao)
   - Beginnings of upstream support for PA Semi Nemo motherboards
     (Darren Stevens)

  Fixes:
   - Ensure .mem(init|exit).text are within _stext/_etext (Michael
     Ellerman)
   - xmon: Don't use ld on 32-bit (Michael Ellerman)
   - vdso64: Use double word compare on pointers (Anton Blanchard)
   - powerpc/nvram: Fix an incorrect partition merge (Pan Xinhui)
   - powerpc: Fix usage of _PAGE_RO in hugepage (Christophe Leroy)
   - powerpc/mm: Update FORCE_MAX_ZONEORDER range to allow hugetlb w/4K
     (Aneesh Kumar K.V)
   - Fix memory leak in queue_hotplug_event() error path (Andrew
     Donnellan)
   - Replay hypervisor maintenance interrupt first (Nicholas Piggin)

  Various performance optimisations (Anton Blanchard):
   - Align hot loops of memset() and backwards_memcpy()
   - During context switch, check before setting mm_cpumask
   - Remove static branch prediction in atomic{, 64}_add_unless
   - Only disable HAVE_EFFICIENT_UNALIGNED_ACCESS on POWER7 little
     endian
   - Set default CPU type to POWER8 for little endian builds

  Cleanups & features:
   - Sparse fixes/cleanups (Daniel Axtens)
   - Preserve CFAR value on SLB miss caused by access to bogus address
     (Paul Mackerras)
   - Radix MMU fixups for POWER9 (Aneesh Kumar K.V)
   - Support for setting used_(vsr|vr|spe) in sigreturn path (for CRIU)
     (Simon Guo)
   - Optimise syscall entry for virtual, relocatable case (Nicholas
     Piggin)
   - Optimise MSR handling in exception handling (Nicholas Piggin)
   - Support for kexec with Radix MMU (Benjamin Herrenschmidt)
   - powernv EEH fixes (Russell Currey)
   - Suprise PCI hotplug support for powernv (Gavin Shan)
   - Endian/sparse fixes for powernv PCI (Gavin Shan)
   - Defconfig updates (Anton Blanchard)
   - KVM: PPC: Book3S HV: Migrate pinned pages out of CMA (Balbir Singh)
   - cxl: Flush PSL cache before resetting the adapter (Frederic Barrat)
   - cxl: replace loop with for_each_child_of_node(), remove unneeded
     of_node_put() (Andrew Donnellan)
   - Fix HV facility unavailable to use correct handler (Nicholas
     Piggin)
   - Remove unnecessary syscall trampoline (Nicholas Piggin)
   - fadump: Fix build break when CONFIG_PROC_VMCORE=n (Michael
     Ellerman)
   - Quieten EEH message when no adapters are found (Anton Blanchard)
   - powernv: Add PHB register dump debugfs handle (Russell Currey)
   - Use kprobe blacklist for exception handlers & asm functions
     (Nicholas Piggin)
   - Document the syscall ABI (Nicholas Piggin)
   - MAINTAINERS: Update cxl maintainers (Michael Neuling)
   - powerpc: Remove all usages of NO_IRQ (Michael Ellerman)

  Minor cleanups:
   - Andrew Donnellan, Christophe Leroy, Colin Ian King, Cyril Bur,
     Frederic Barrat, Pan Xinhui, PrasannaKumar Muralidharan, Rui Teng,
     Simon Guo"

* tag 'powerpc-4.9-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (156 commits)
  powerpc/bpf: Add support for bpf constant blinding
  powerpc/bpf: Implement support for tail calls
  powerpc/bpf: Introduce accessors for using the tmp local stack space
  powerpc/fadump: Fix build break when CONFIG_PROC_VMCORE=n
  powerpc: tm: Enable transactional memory (TM) lazily for userspace
  powerpc/tm: Add TM Unavailable Exception
  powerpc: Remove do_load_up_transact_{fpu,altivec}
  powerpc: tm: Rename transct_(*) to ck(\1)_state
  powerpc: tm: Always use fp_state and vr_state to store live registers
  selftests/powerpc: Add checks for transactional VSXs in signal contexts
  selftests/powerpc: Add checks for transactional VMXs in signal contexts
  selftests/powerpc: Add checks for transactional FPUs in signal contexts
  selftests/powerpc: Add checks for transactional GPRs in signal contexts
  selftests/powerpc: Check that signals always get delivered
  selftests/powerpc: Add TM tcheck helpers in C
  selftests/powerpc: Allow tests to extend their kill timeout
  selftests/powerpc: Introduce GPR asm helper header file
  selftests/powerpc: Move VMX stack frame macros to header file
  selftests/powerpc: Rework FPU stack placement macros and move to header file
  selftests/powerpc: Check for VSX preservation across userspace preemption
  ...

1 files changed, 5 insertions, 68 deletions

diff --git a/tools/testing/selftests/powerpc/math/fpu_asm.S b/tools/testing/selftests/powerpc/math/fpu_asm.S
index f3711d80e709..241f067a510f 100644
--- a/tools/testing/selftests/powerpc/math/fpu_asm.S
+++ b/tools/testing/selftests/powerpc/math/fpu_asm.S
@@ -8,70 +8,7 @@
  */
 
 #include "../basic_asm.h"
-
-#define PUSH_FPU(pos) \
-	stfd	f14,pos(sp); \
-	stfd	f15,pos+8(sp); \
-	stfd	f16,pos+16(sp); \
-	stfd	f17,pos+24(sp); \
-	stfd	f18,pos+32(sp); \
-	stfd	f19,pos+40(sp); \
-	stfd	f20,pos+48(sp); \
-	stfd	f21,pos+56(sp); \
-	stfd	f22,pos+64(sp); \
-	stfd	f23,pos+72(sp); \
-	stfd	f24,pos+80(sp); \
-	stfd	f25,pos+88(sp); \
-	stfd	f26,pos+96(sp); \
-	stfd	f27,pos+104(sp); \
-	stfd	f28,pos+112(sp); \
-	stfd	f29,pos+120(sp); \
-	stfd	f30,pos+128(sp); \
-	stfd	f31,pos+136(sp);
-
-#define POP_FPU(pos) \
-	lfd	f14,pos(sp); \
-	lfd	f15,pos+8(sp); \
-	lfd	f16,pos+16(sp); \
-	lfd	f17,pos+24(sp); \
-	lfd	f18,pos+32(sp); \
-	lfd	f19,pos+40(sp); \
-	lfd	f20,pos+48(sp); \
-	lfd	f21,pos+56(sp); \
-	lfd	f22,pos+64(sp); \
-	lfd	f23,pos+72(sp); \
-	lfd	f24,pos+80(sp); \
-	lfd	f25,pos+88(sp); \
-	lfd	f26,pos+96(sp); \
-	lfd	f27,pos+104(sp); \
-	lfd	f28,pos+112(sp); \
-	lfd	f29,pos+120(sp); \
-	lfd	f30,pos+128(sp); \
-	lfd	f31,pos+136(sp);
-
-# Careful calling this, it will 'clobber' fpu (by design)
-# Don't call this from C
-FUNC_START(load_fpu)
-	lfd	f14,0(r3)
-	lfd	f15,8(r3)
-	lfd	f16,16(r3)
-	lfd	f17,24(r3)
-	lfd	f18,32(r3)
-	lfd	f19,40(r3)
-	lfd	f20,48(r3)
-	lfd	f21,56(r3)
-	lfd	f22,64(r3)
-	lfd	f23,72(r3)
-	lfd	f24,80(r3)
-	lfd	f25,88(r3)
-	lfd	f26,96(r3)
-	lfd	f27,104(r3)
-	lfd	f28,112(r3)
-	lfd	f29,120(r3)
-	lfd	f30,128(r3)
-	lfd	f31,136(r3)
-	blr
-FUNC_END(load_fpu)
+#include "../fpu_asm.h"
 
 FUNC_START(check_fpu)
 	mr r4,r3
@@ -138,9 +75,9 @@ FUNC_START(test_fpu)
 	# r4 holds pointer to the pid
 	# f14-f31 are non volatiles
 	PUSH_BASIC_STACK(256)
+	PUSH_FPU(256)
 	std	r3,STACK_FRAME_PARAM(0)(sp) # Address of darray
 	std r4,STACK_FRAME_PARAM(1)(sp) # Address of pid
-	PUSH_FPU(STACK_FRAME_LOCAL(2,0))
 
 	bl load_fpu
 	nop
@@ -155,7 +92,7 @@ FUNC_START(test_fpu)
 	bl check_fpu
 	nop
 
-	POP_FPU(STACK_FRAME_LOCAL(2,0))
+	POP_FPU(256)
 	POP_BASIC_STACK(256)
 	blr
 FUNC_END(test_fpu)
@@ -166,10 +103,10 @@ FUNC_END(test_fpu)
 # registers while running is not zero.
 FUNC_START(preempt_fpu)
 	PUSH_BASIC_STACK(256)
+	PUSH_FPU(256)
 	std r3,STACK_FRAME_PARAM(0)(sp) # double *darray
 	std r4,STACK_FRAME_PARAM(1)(sp) # int *threads_starting
 	std r5,STACK_FRAME_PARAM(2)(sp) # int *running
-	PUSH_FPU(STACK_FRAME_LOCAL(3,0))
 
 	bl load_fpu
 	nop
@@ -192,7 +129,7 @@ FUNC_START(preempt_fpu)
 	cmpwi r5,0
 	bne 2b
 
-3:	POP_FPU(STACK_FRAME_LOCAL(3,0))
+3:	POP_FPU(256)
 	POP_BASIC_STACK(256)
 	blr
 FUNC_END(preempt_fpu)