Merge tag 'powerpc-5.2-1' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Slightly delayed due to the issue with printk() calling
  probe_kernel_read() interacting with our new user access prevention
  stuff, but all fixed now.

  The only out-of-area changes are the addition of a cpuhp_state, small
  additions to Documentation and MAINTAINERS updates.

  Highlights:

   - Support for Kernel Userspace Access/Execution Prevention (like
     SMAP/SMEP/PAN/PXN) on some 64-bit and 32-bit CPUs. This prevents
     the kernel from accidentally accessing userspace outside
     copy_to/from_user(), or ever executing userspace.

   - KASAN support on 32-bit.

   - Rework of where we map the kernel, vmalloc, etc. on 64-bit hash to
     use the same address ranges we use with the Radix MMU.

   - A rewrite into C of large parts of our idle handling code for
     64-bit Book3S (ie. power8 & power9).

   - A fast path entry for syscalls on 32-bit CPUs, for a 12-17% speedup
     in the null_syscall benchmark.

   - On 64-bit bare metal we have support for recovering from errors
     with the time base (our clocksource), however if that fails
     currently we hang in __delay() and never crash. We now have support
     for detecting that case and short circuiting __delay() so we at
     least panic() and reboot.

   - Add support for optionally enabling the DAWR on Power9, which had
     to be disabled by default due to a hardware erratum. This has the
     effect of enabling hardware breakpoints for GDB, the downside is a
     badly behaved program could crash the machine by pointing the DAWR
     at cache inhibited memory. This is opt-in obviously.

   - xmon, our crash handler, gets support for a read only mode where
     operations that could change memory or otherwise disturb the system
     are disabled.

  Plus many clean-ups, reworks and minor fixes etc.

  Thanks to: Christophe Leroy, Akshay Adiga, Alastair D'Silva, Alexey
  Kardashevskiy, Andrew Donnellan, Aneesh Kumar K.V, Anju T Sudhakar,
  Anton Blanchard, Ben Hutchings, Bo YU, Breno Leitao, Cédric Le Goater,
  Christopher M. Riedl, Christoph Hellwig, Colin Ian King, David Gibson,
  Ganesh Goudar, Gautham R. Shenoy, George Spelvin, Greg Kroah-Hartman,
  Greg Kurz, Horia Geantă, Jagadeesh Pagadala, Joel Stanley, Joe
  Perches, Julia Lawall, Laurentiu Tudor, Laurent Vivier, Lukas Bulwahn,
  Madhavan Srinivasan, Mahesh Salgaonkar, Mathieu Malaterre, Michael
  Neuling, Mukesh Ojha, Nathan Fontenot, Nathan Lynch, Nicholas Piggin,
  Nick Desaulniers, Oliver O'Halloran, Peng Hao, Qian Cai, Ravi
  Bangoria, Rick Lindsley, Russell Currey, Sachin Sant, Stewart Smith,
  Sukadev Bhattiprolu, Thomas Huth, Tobin C. Harding, Tyrel Datwyler,
  Valentin Schneider, Wei Yongjun, Wen Yang, YueHaibing"

* tag 'powerpc-5.2-1' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (205 commits)
  powerpc/64s: Use early_mmu_has_feature() in set_kuap()
  powerpc/book3s/64: check for NULL pointer in pgd_alloc()
  powerpc/mm: Fix hugetlb page initialization
  ocxl: Fix return value check in afu_ioctl()
  powerpc/mm: fix section mismatch for setup_kup()
  powerpc/mm: fix redundant inclusion of pgtable-frag.o in Makefile
  powerpc/mm: Fix makefile for KASAN
  powerpc/kasan: add missing/lost Makefile
  selftests/powerpc: Add a signal fuzzer selftest
  powerpc/booke64: set RI in default MSR
  ocxl: Provide global MMIO accessors for external drivers
  ocxl: move event_fd handling to frontend
  ocxl: afu_irq only deals with IRQ IDs, not offsets
  ocxl: Allow external drivers to use OpenCAPI contexts
  ocxl: Create a clear delineation between ocxl backend & frontend
  ocxl: Don't pass pci_dev around
  ocxl: Split pci.c
  ocxl: Remove some unused exported symbols
  ocxl: Remove superfluous 'extern' from headers
  ocxl: read_pasid never returns an error, so make it void
  ...

3 files changed, 88 insertions, 58 deletions

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index b2b29d4f9842..7bdcd4d7a9f0 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -74,6 +74,7 @@
 #include <asm/opal.h>
 #include <asm/xics.h>
 #include <asm/xive.h>
+#include <asm/hw_breakpoint.h>
 
 #include "book3s.h"
 
@@ -3374,7 +3375,7 @@ static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit,
 	mtspr(SPRN_PURR, vcpu->arch.purr);
 	mtspr(SPRN_SPURR, vcpu->arch.spurr);
 
-	if (cpu_has_feature(CPU_FTR_DAWR)) {
+	if (dawr_enabled()) {
 		mtspr(SPRN_DAWR, vcpu->arch.dawr);
 		mtspr(SPRN_DAWRX, vcpu->arch.dawrx);
 	}
diff --git a/arch/powerpc/kvm/book3s_hv_rm_xics.c b/arch/powerpc/kvm/book3s_hv_rm_xics.c
index 3b9662a4207e..085509148d95 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_xics.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_xics.c
@@ -822,7 +822,7 @@ static inline void this_cpu_inc_rm(unsigned int __percpu *addr)
 	raddr = per_cpu_ptr(addr, cpu);
 	l = (unsigned long)raddr;
 
-	if (REGION_ID(l) == VMALLOC_REGION_ID) {
+	if (get_region_id(l) == VMALLOC_REGION_ID) {
 		l = vmalloc_to_phys(raddr);
 		raddr = (unsigned int *)l;
 	}
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 3a5e719ef032..dd014308f065 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -35,6 +35,7 @@
 #include <asm/thread_info.h>
 #include <asm/asm-compat.h>
 #include <asm/feature-fixups.h>
+#include <asm/cpuidle.h>
 
 /* Sign-extend HDEC if not on POWER9 */
 #define EXTEND_HDEC(reg)			\
@@ -45,6 +46,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
 /* Values in HSTATE_NAPPING(r13) */
 #define NAPPING_CEDE	1
 #define NAPPING_NOVCPU	2
+#define NAPPING_UNSPLIT	3
 
 /* Stack frame offsets for kvmppc_hv_entry */
 #define SFS			208
@@ -290,17 +292,19 @@ kvm_novcpu_exit:
 	b	kvmhv_switch_to_host
 
 /*
- * We come in here when wakened from nap mode.
- * Relocation is off and most register values are lost.
- * r13 points to the PACA.
+ * We come in here when wakened from Linux offline idle code.
+ * Relocation is off
  * r3 contains the SRR1 wakeup value, SRR1 is trashed.
  */
-	.globl	kvm_start_guest
-kvm_start_guest:
-	/* Set runlatch bit the minute you wake up from nap */
-	mfspr	r0, SPRN_CTRLF
-	ori 	r0, r0, 1
-	mtspr	SPRN_CTRLT, r0
+_GLOBAL(idle_kvm_start_guest)
+	ld	r4,PACAEMERGSP(r13)
+	mfcr	r5
+	mflr	r0
+	std	r1,0(r4)
+	std	r5,8(r4)
+	std	r0,16(r4)
+	subi	r1,r4,STACK_FRAME_OVERHEAD
+	SAVE_NVGPRS(r1)
 
 	/*
 	 * Could avoid this and pass it through in r3. For now,
@@ -308,27 +312,23 @@ kvm_start_guest:
 	 */
 	mtspr	SPRN_SRR1,r3
 
-	ld	r2,PACATOC(r13)
-
 	li	r0,0
 	stb	r0,PACA_FTRACE_ENABLED(r13)
 
 	li	r0,KVM_HWTHREAD_IN_KVM
 	stb	r0,HSTATE_HWTHREAD_STATE(r13)
 
-	/* NV GPR values from power7_idle() will no longer be valid */
-	li	r0,1
-	stb	r0,PACA_NAPSTATELOST(r13)
-
-	/* were we napping due to cede? */
+	/* kvm cede / napping does not come through here */
 	lbz	r0,HSTATE_NAPPING(r13)
-	cmpwi	r0,NAPPING_CEDE
-	beq	kvm_end_cede
-	cmpwi	r0,NAPPING_NOVCPU
-	beq	kvm_novcpu_wakeup
+	twnei	r0,0
 
-	ld	r1,PACAEMERGSP(r13)
-	subi	r1,r1,STACK_FRAME_OVERHEAD
+	b	1f
+
+kvm_unsplit_wakeup:
+	li	r0, 0
+	stb	r0, HSTATE_NAPPING(r13)
+
+1:
 
 	/*
 	 * We weren't napping due to cede, so this must be a secondary
@@ -437,19 +437,25 @@ kvm_no_guest:
 	lbz	r3, HSTATE_HWTHREAD_REQ(r13)
 	cmpwi	r3, 0
 	bne	54f
-/*
- * We jump to pnv_wakeup_loss, which will return to the caller
- * of power7_nap in the powernv cpu offline loop.  The value we
- * put in r3 becomes the return value for power7_nap. pnv_wakeup_loss
- * requires SRR1 in r12.
- */
+
+	/*
+	 * Jump to idle_return_gpr_loss, which returns to the
+	 * idle_kvm_start_guest caller.
+	 */
 	li	r3, LPCR_PECE0
 	mfspr	r4, SPRN_LPCR
 	rlwimi	r4, r3, 0, LPCR_PECE0 | LPCR_PECE1
 	mtspr	SPRN_LPCR, r4
-	li	r3, 0
-	mfspr	r12,SPRN_SRR1
-	b	pnv_wakeup_loss
+	/* set up r3 for return */
+	mfspr	r3,SPRN_SRR1
+	REST_NVGPRS(r1)
+	addi	r1, r1, STACK_FRAME_OVERHEAD
+	ld	r0, 16(r1)
+	ld	r5, 8(r1)
+	ld	r1, 0(r1)
+	mtlr	r0
+	mtcr	r5
+	blr
 
 53:	HMT_LOW
 	ld	r5, HSTATE_KVM_VCORE(r13)
@@ -534,6 +540,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	lbz	r0, KVM_SPLIT_DO_NAP(r3)
 	cmpwi	r0, 0
 	beq	57f
+	li	r3, NAPPING_UNSPLIT
+	stb	r3, HSTATE_NAPPING(r13)
 	li	r3, (LPCR_PECEDH | LPCR_PECE0) >> 4
 	mfspr	r5, SPRN_LPCR
 	rlwimi	r5, r3, 4, (LPCR_PECEDP | LPCR_PECEDH | LPCR_PECE0 | LPCR_PECE1)
@@ -822,18 +830,21 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 	mtspr	SPRN_IAMR, r5
 	mtspr	SPRN_PSPB, r6
 	mtspr	SPRN_FSCR, r7
-	ld	r5, VCPU_DAWR(r4)
-	ld	r6, VCPU_DAWRX(r4)
-	ld	r7, VCPU_CIABR(r4)
-	ld	r8, VCPU_TAR(r4)
 	/*
 	 * Handle broken DAWR case by not writing it. This means we
 	 * can still store the DAWR register for migration.
 	 */
-BEGIN_FTR_SECTION
+	LOAD_REG_ADDR(r5, dawr_force_enable)
+	lbz	r5, 0(r5)
+	cmpdi	r5, 0
+	beq	1f
+	ld	r5, VCPU_DAWR(r4)
+	ld	r6, VCPU_DAWRX(r4)
 	mtspr	SPRN_DAWR, r5
 	mtspr	SPRN_DAWRX, r6
-END_FTR_SECTION_IFSET(CPU_FTR_DAWR)
+1:
+	ld	r7, VCPU_CIABR(r4)
+	ld	r8, VCPU_TAR(r4)
 	mtspr	SPRN_CIABR, r7
 	mtspr	SPRN_TAR, r8
 	ld	r5, VCPU_IC(r4)
@@ -2513,11 +2524,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	blr
 
 2:
-BEGIN_FTR_SECTION
-	/* POWER9 with disabled DAWR */
+	LOAD_REG_ADDR(r11, dawr_force_enable)
+	lbz	r11, 0(r11)
+	cmpdi	r11, 0
 	li	r3, H_HARDWARE
-	blr
-END_FTR_SECTION_IFCLR(CPU_FTR_DAWR)
+	beqlr
 	/* Emulate H_SET_DABR/X on P8 for the sake of compat mode guests */
 	rlwimi	r5, r4, 5, DAWRX_DR | DAWRX_DW
 	rlwimi	r5, r4, 2, DAWRX_WT
@@ -2654,6 +2665,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 
 	lis	r3, LPCR_PECEDP@h	/* Do wake on privileged doorbell */
 
+	/* Go back to host stack */
+	ld	r1, HSTATE_HOST_R1(r13)
+
 	/*
 	 * Take a nap until a decrementer or external or doobell interrupt
 	 * occurs, with PECE1 and PECE0 set in LPCR.
@@ -2682,26 +2696,42 @@ BEGIN_FTR_SECTION
 	 *		requested level = 0 (just stop dispatching)
 	 */
 	lis	r3, (PSSCR_EC | PSSCR_ESL)@h
-	mtspr	SPRN_PSSCR, r3
 	/* Set LPCR_PECE_HVEE bit to enable wakeup by HV interrupts */
 	li	r4, LPCR_PECE_HVEE@higher
 	sldi	r4, r4, 32
 	or	r5, r5, r4
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
+FTR_SECTION_ELSE
+	li	r3, PNV_THREAD_NAP
+ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300)
 	mtspr	SPRN_LPCR,r5
 	isync
-	li	r0, 0
-	std	r0, HSTATE_SCRATCH0(r13)
-	ptesync
-	ld	r0, HSTATE_SCRATCH0(r13)
-1:	cmpd	r0, r0
-	bne	1b
+
 BEGIN_FTR_SECTION
-	nap
+	bl	isa300_idle_stop_mayloss
 FTR_SECTION_ELSE
-	PPC_STOP
-ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
-	b	.
+	bl	isa206_idle_insn_mayloss
+ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300)
+
+	mfspr	r0, SPRN_CTRLF
+	ori	r0, r0, 1
+	mtspr	SPRN_CTRLT, r0
+
+	mtspr	SPRN_SRR1, r3
+
+	li	r0, 0
+	stb	r0, PACA_FTRACE_ENABLED(r13)
+
+	li	r0, KVM_HWTHREAD_IN_KVM
+	stb	r0, HSTATE_HWTHREAD_STATE(r13)
+
+	lbz	r0, HSTATE_NAPPING(r13)
+	cmpwi	r0, NAPPING_CEDE
+	beq	kvm_end_cede
+	cmpwi	r0, NAPPING_NOVCPU
+	beq	kvm_novcpu_wakeup
+	cmpwi	r0, NAPPING_UNSPLIT
+	beq	kvm_unsplit_wakeup
+	twi	31,0,0 /* Nap state must not be zero */
 
 33:	mr	r4, r3
 	li	r3, 0
@@ -2709,12 +2739,11 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
 	b	34f
 
 kvm_end_cede:
+	/* Woken by external or decrementer interrupt */
+
 	/* get vcpu pointer */
 	ld	r4, HSTATE_KVM_VCPU(r13)
 
-	/* Woken by external or decrementer interrupt */
-	ld	r1, HSTATE_HOST_R1(r13)
-
 #ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
 	addi	r3, r4, VCPU_TB_RMINTR
 	bl	kvmhv_accumulate_time