Merge tag 'powerpc-5.9-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:

 - Add support for (optionally) using queued spinlocks & rwlocks.

 - Support for a new faster system call ABI using the scv instruction on
   Power9 or later.

 - Drop support for the PROT_SAO mmap/mprotect flag as it will be
   unsupported on Power10 and future processors, leaving us with no way
   to implement the functionality it requests. This risks breaking
   userspace, though we believe it is unused in practice.

 - A bug fix for, and then the removal of, our custom stack expansion
   checking. We now allow stack expansion up to the rlimit, like other
   architectures.

 - Remove the remnants of our (previously disabled) topology update
   code, which tried to react to NUMA layout changes on virtualised
   systems, but was prone to crashes and other problems.

 - Add PMU support for Power10 CPUs.

 - A change to our signal trampoline so that we don't unbalance the link
   stack (branch return predictor) in the signal delivery path.

 - Lots of other cleanups, refactorings, smaller features and so on as
   usual.

Thanks to: Abhishek Goel, Alastair D'Silva, Alexander A. Klimov, Alexey
Kardashevskiy, Alistair Popple, Andrew Donnellan, Aneesh Kumar K.V, Anju
T Sudhakar, Anton Blanchard, Arnd Bergmann, Athira Rajeev, Balamuruhan
S, Bharata B Rao, Bill Wendling, Bin Meng, Cédric Le Goater, Chris
Packham, Christophe Leroy, Christoph Hellwig, Daniel Axtens, Dan
Williams, David Lamparter, Desnes A. Nunes do Rosario, Erhard F., Finn
Thain, Frederic Barrat, Ganesh Goudar, Gautham R. Shenoy, Geoff Levand,
Greg Kurz, Gustavo A. R. Silva, Hari Bathini, Harish, Imre Kaloz, Joel
Stanley, Joe Perches, John Crispin, Jordan Niethe, Kajol Jain, Kamalesh
Babulal, Kees Cook, Laurent Dufour, Leonardo Bras, Li RongQing, Madhavan
Srinivasan, Mahesh Salgaonkar, Mark Cave-Ayland, Michal Suchanek, Milton
Miller, Mimi Zohar, Murilo Opsfelder Araujo, Nathan Chancellor, Nathan
Lynch, Naveen N. Rao, Nayna Jain, Nicholas Piggin, Oliver O'Halloran,
Palmer Dabbelt, Pedro Miraglia Franco de Carvalho, Philippe Bergheaud,
Pingfan Liu, Pratik Rajesh Sampat, Qian Cai, Qinglang Miao, Randy
Dunlap, Ravi Bangoria, Sachin Sant, Sam Bobroff, Sandipan Das, Santosh
Sivaraj, Satheesh Rajendran, Shirisha Ganta, Sourabh Jain, Srikar
Dronamraju, Stan Johnson, Stephen Rothwell, Thadeu Lima de Souza
Cascardo, Thiago Jung Bauermann, Tom Lane, Vaibhav Jain, Vladis Dronov,
Wei Yongjun, Wen Xiong, YueHaibing.

* tag 'powerpc-5.9-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (337 commits)
  selftests/powerpc: Fix pkey syscall redefinitions
  powerpc: Fix circular dependency between percpu.h and mmu.h
  powerpc/powernv/sriov: Fix use of uninitialised variable
  selftests/powerpc: Skip vmx/vsx/tar/etc tests on older CPUs
  powerpc/40x: Fix assembler warning about r0
  powerpc/papr_scm: Add support for fetching nvdimm 'fuel-gauge' metric
  powerpc/papr_scm: Fetch nvdimm performance stats from PHYP
  cpuidle: pseries: Fixup exit latency for CEDE(0)
  cpuidle: pseries: Add function to parse extended CEDE records
  cpuidle: pseries: Set the latency-hint before entering CEDE
  selftests/powerpc: Fix online CPU selection
  powerpc/perf: Consolidate perf_callchain_user_[64|32]()
  powerpc/pseries/hotplug-cpu: Remove double free in error path
  powerpc/pseries/mobility: Add pr_debug() for device tree changes
  powerpc/pseries/mobility: Set pr_fmt()
  powerpc/cacheinfo: Warn if cache object chain becomes unordered
  powerpc/cacheinfo: Improve diagnostics about malformed cache lists
  powerpc/cacheinfo: Use name@unit instead of full DT path in debug messages
  powerpc/cacheinfo: Set pr_fmt()
  powerpc: fix function annotations to avoid section mismatch warnings with gcc-10
  ...

1 files changed, 143 insertions, 7 deletions

diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 446e54c3f71e..f7d748b88705 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -508,8 +508,24 @@ DEFINE_FIXED_SYMBOL(\name\()_common_real)
 
 .macro __GEN_COMMON_BODY name
 	.if IMASK
+		.if ! ISTACK
+		.error "No support for masked interrupt to use custom stack"
+		.endif
+
+		/* If coming from user, skip soft-mask tests. */
+		andi.	r10,r12,MSR_PR
+		bne	2f
+
+		/* Kernel code running below __end_interrupts is implicitly
+		 * soft-masked */
+		LOAD_HANDLER(r10, __end_interrupts)
+		cmpld	r11,r10
+		li	r10,IMASK
+		blt-	1f
+
+		/* Test the soft mask state against our interrupt's bit */
 		lbz	r10,PACAIRQSOFTMASK(r13)
-		andi.	r10,r10,IMASK
+1:		andi.	r10,r10,IMASK
 		/* Associate vector numbers with bits in paca->irq_happened */
 		.if IVEC == 0x500 || IVEC == 0xea0
 		li	r10,PACA_IRQ_EE
@@ -540,7 +556,7 @@ DEFINE_FIXED_SYMBOL(\name\()_common_real)
 
 	.if ISTACK
 	andi.	r10,r12,MSR_PR		/* See if coming from user	*/
-	mr	r10,r1			/* Save r1			*/
+2:	mr	r10,r1			/* Save r1			*/
 	subi	r1,r1,INT_FRAME_SIZE	/* alloc frame on kernel stack	*/
 	beq-	100f
 	ld	r1,PACAKSAVE(r13)	/* kernel stack to use		*/
@@ -740,6 +756,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_CAN_NAP)
  * guarantee they will be delivered virtually. Some conditions (see the ISA)
  * cause exceptions to be delivered in real mode.
  *
+ * The scv instructions are a special case. They get a 0x3000 offset applied.
+ * scv exceptions have unique reentrancy properties, see below.
+ *
  * It's impossible to receive interrupts below 0x300 via AIL.
  *
  * KVM: None of the virtual exceptions are from the guest. Anything that
@@ -749,8 +768,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_CAN_NAP)
  * We layout physical memory as follows:
  * 0x0000 - 0x00ff : Secondary processor spin code
  * 0x0100 - 0x18ff : Real mode pSeries interrupt vectors
- * 0x1900 - 0x3fff : Real mode trampolines
- * 0x4000 - 0x58ff : Relon (IR=1,DR=1) mode pSeries interrupt vectors
+ * 0x1900 - 0x2fff : Real mode trampolines
+ * 0x3000 - 0x58ff : Relon (IR=1,DR=1) mode pSeries interrupt vectors
  * 0x5900 - 0x6fff : Relon mode trampolines
  * 0x7000 - 0x7fff : FWNMI data area
  * 0x8000 -   .... : Common interrupt handlers, remaining early
@@ -761,8 +780,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_CAN_NAP)
  * vectors there.
  */
 OPEN_FIXED_SECTION(real_vectors,        0x0100, 0x1900)
-OPEN_FIXED_SECTION(real_trampolines,    0x1900, 0x4000)
-OPEN_FIXED_SECTION(virt_vectors,        0x4000, 0x5900)
+OPEN_FIXED_SECTION(real_trampolines,    0x1900, 0x3000)
+OPEN_FIXED_SECTION(virt_vectors,        0x3000, 0x5900)
 OPEN_FIXED_SECTION(virt_trampolines,    0x5900, 0x7000)
 
 #ifdef CONFIG_PPC_POWERNV
@@ -798,6 +817,77 @@ USE_FIXED_SECTION(real_vectors)
 	.globl __start_interrupts
 __start_interrupts:
 
+/**
+ * Interrupt 0x3000 - System Call Vectored Interrupt (syscall).
+ * This is a synchronous interrupt invoked with the "scv" instruction. The
+ * system call does not alter the HV bit, so it is directed to the OS.
+ *
+ * Handling:
+ * scv instructions enter the kernel without changing EE, RI, ME, or HV.
+ * In particular, this means we can take a maskable interrupt at any point
+ * in the scv handler, which is unlike any other interrupt. This is solved
+ * by treating the instruction addresses below __end_interrupts as being
+ * soft-masked.
+ *
+ * AIL-0 mode scv exceptions go to 0x17000-0x17fff, but we set AIL-3 and
+ * ensure scv is never executed with relocation off, which means AIL-0
+ * should never happen.
+ *
+ * Before leaving the below __end_interrupts text, at least of the following
+ * must be true:
+ * - MSR[PR]=1 (i.e., return to userspace)
+ * - MSR_EE|MSR_RI is set (no reentrant exceptions)
+ * - Standard kernel environment is set up (stack, paca, etc)
+ *
+ * Call convention:
+ *
+ * syscall register convention is in Documentation/powerpc/syscall64-abi.rst
+ */
+EXC_VIRT_BEGIN(system_call_vectored, 0x3000, 0x1000)
+	/* SCV 0 */
+	mr	r9,r13
+	GET_PACA(r13)
+	mflr	r11
+	mfctr	r12
+	li	r10,IRQS_ALL_DISABLED
+	stb	r10,PACAIRQSOFTMASK(r13)
+#ifdef CONFIG_RELOCATABLE
+	b	system_call_vectored_tramp
+#else
+	b	system_call_vectored_common
+#endif
+	nop
+
+	/* SCV 1 - 127 */
+	.rept	127
+	mr	r9,r13
+	GET_PACA(r13)
+	mflr	r11
+	mfctr	r12
+	li	r10,IRQS_ALL_DISABLED
+	stb	r10,PACAIRQSOFTMASK(r13)
+	li	r0,-1 /* cause failure */
+#ifdef CONFIG_RELOCATABLE
+	b	system_call_vectored_sigill_tramp
+#else
+	b	system_call_vectored_sigill
+#endif
+	.endr
+EXC_VIRT_END(system_call_vectored, 0x3000, 0x1000)
+
+#ifdef CONFIG_RELOCATABLE
+TRAMP_VIRT_BEGIN(system_call_vectored_tramp)
+	__LOAD_HANDLER(r10, system_call_vectored_common)
+	mtctr	r10
+	bctr
+
+TRAMP_VIRT_BEGIN(system_call_vectored_sigill_tramp)
+	__LOAD_HANDLER(r10, system_call_vectored_sigill)
+	mtctr	r10
+	bctr
+#endif
+
+
 /* No virt vectors corresponding with 0x0..0x100 */
 EXC_VIRT_NONE(0x4000, 0x100)
 
@@ -2838,7 +2928,8 @@ masked_interrupt:
 	ld	r10,PACA_EXGEN+EX_R10(r13)
 	ld	r11,PACA_EXGEN+EX_R11(r13)
 	ld	r12,PACA_EXGEN+EX_R12(r13)
-	/* returns to kernel where r13 must be set up, so don't restore it */
+	ld	r13,PACA_EXGEN+EX_R13(r13)
+	/* May return to masked low address where r13 is not set up */
 	.if \hsrr
 	HRFI_TO_KERNEL
 	.else
@@ -2946,6 +3037,47 @@ TRAMP_REAL_BEGIN(hrfi_flush_fallback)
 	GET_SCRATCH0(r13);
 	hrfid
 
+TRAMP_REAL_BEGIN(rfscv_flush_fallback)
+	/* system call volatile */
+	mr	r7,r13
+	GET_PACA(r13);
+	mr	r8,r1
+	ld	r1,PACAKSAVE(r13)
+	mfctr	r9
+	ld	r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13)
+	ld	r11,PACA_L1D_FLUSH_SIZE(r13)
+	srdi	r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */
+	mtctr	r11
+	DCBT_BOOK3S_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */
+
+	/* order ld/st prior to dcbt stop all streams with flushing */
+	sync
+
+	/*
+	 * The load adresses are at staggered offsets within cachelines,
+	 * which suits some pipelines better (on others it should not
+	 * hurt).
+	 */
+1:
+	ld	r11,(0x80 + 8)*0(r10)
+	ld	r11,(0x80 + 8)*1(r10)
+	ld	r11,(0x80 + 8)*2(r10)
+	ld	r11,(0x80 + 8)*3(r10)
+	ld	r11,(0x80 + 8)*4(r10)
+	ld	r11,(0x80 + 8)*5(r10)
+	ld	r11,(0x80 + 8)*6(r10)
+	ld	r11,(0x80 + 8)*7(r10)
+	addi	r10,r10,0x80*8
+	bdnz	1b
+
+	mtctr	r9
+	li	r9,0
+	li	r10,0
+	li	r11,0
+	mr	r1,r8
+	mr	r13,r7
+	RFSCV
+
 USE_TEXT_SECTION()
 	MASKED_INTERRUPT
 	MASKED_INTERRUPT hsrr=1
@@ -2997,6 +3129,10 @@ EXC_COMMON_BEGIN(ppc64_runlatch_on_trampoline)
 
 USE_FIXED_SECTION(virt_trampolines)
 	/*
+	 * All code below __end_interrupts is treated as soft-masked. If
+	 * any code runs here with MSR[EE]=1, it must then cope with pending
+	 * soft interrupt being raised (i.e., by ensuring it is replayed).
+	 *
 	 * The __end_interrupts marker must be past the out-of-line (OOL)
 	 * handlers, so that they are copied to real address 0x100 when running
 	 * a relocatable kernel. This ensures they can be reached from the short