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, 5 insertions, 101 deletions

diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 641fc5f3d7dd..925a7231abb3 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -42,39 +42,7 @@
 #include <asm/kup.h>
 #include <asm/inst.h>
 
-/*
- * Check whether the instruction inst is a store using
- * an update addressing form which will update r1.
- */
-static bool store_updates_sp(struct ppc_inst inst)
-{
-	/* check for 1 in the rA field */
-	if (((ppc_inst_val(inst) >> 16) & 0x1f) != 1)
-		return false;
-	/* check major opcode */
-	switch (ppc_inst_primary_opcode(inst)) {
-	case OP_STWU:
-	case OP_STBU:
-	case OP_STHU:
-	case OP_STFSU:
-	case OP_STFDU:
-		return true;
-	case OP_STD:	/* std or stdu */
-		return (ppc_inst_val(inst) & 3) == 1;
-	case OP_31:
-		/* check minor opcode */
-		switch ((ppc_inst_val(inst) >> 1) & 0x3ff) {
-		case OP_31_XOP_STDUX:
-		case OP_31_XOP_STWUX:
-		case OP_31_XOP_STBUX:
-		case OP_31_XOP_STHUX:
-		case OP_31_XOP_STFSUX:
-		case OP_31_XOP_STFDUX:
-			return true;
-		}
-	}
-	return false;
-}
+
 /*
  * do_page_fault error handling helpers
  */
@@ -267,54 +235,6 @@ static bool bad_kernel_fault(struct pt_regs *regs, unsigned long error_code,
 	return false;
 }
 
-static bool bad_stack_expansion(struct pt_regs *regs, unsigned long address,
-				struct vm_area_struct *vma, unsigned int flags,
-				bool *must_retry)
-{
-	/*
-	 * N.B. The POWER/Open ABI allows programs to access up to
-	 * 288 bytes below the stack pointer.
-	 * The kernel signal delivery code writes up to about 1.5kB
-	 * below the stack pointer (r1) before decrementing it.
-	 * The exec code can write slightly over 640kB to the stack
-	 * before setting the user r1.  Thus we allow the stack to
-	 * expand to 1MB without further checks.
-	 */
-	if (address + 0x100000 < vma->vm_end) {
-		struct ppc_inst __user *nip = (struct ppc_inst __user *)regs->nip;
-		/* get user regs even if this fault is in kernel mode */
-		struct pt_regs *uregs = current->thread.regs;
-		if (uregs == NULL)
-			return true;
-
-		/*
-		 * A user-mode access to an address a long way below
-		 * the stack pointer is only valid if the instruction
-		 * is one which would update the stack pointer to the
-		 * address accessed if the instruction completed,
-		 * i.e. either stwu rs,n(r1) or stwux rs,r1,rb
-		 * (or the byte, halfword, float or double forms).
-		 *
-		 * If we don't check this then any write to the area
-		 * between the last mapped region and the stack will
-		 * expand the stack rather than segfaulting.
-		 */
-		if (address + 2048 >= uregs->gpr[1])
-			return false;
-
-		if ((flags & FAULT_FLAG_WRITE) && (flags & FAULT_FLAG_USER) &&
-		    access_ok(nip, sizeof(*nip))) {
-			struct ppc_inst inst;
-
-			if (!probe_user_read_inst(&inst, nip))
-				return !store_updates_sp(inst);
-			*must_retry = true;
-		}
-		return true;
-	}
-	return false;
-}
-
 #ifdef CONFIG_PPC_MEM_KEYS
 static bool access_pkey_error(bool is_write, bool is_exec, bool is_pkey,
 			      struct vm_area_struct *vma)
@@ -480,7 +400,6 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
 	int is_user = user_mode(regs);
 	int is_write = page_fault_is_write(error_code);
 	vm_fault_t fault, major = 0;
-	bool must_retry = false;
 	bool kprobe_fault = kprobe_page_fault(regs, 11);
 
 	if (unlikely(debugger_fault_handler(regs) || kprobe_fault))
@@ -569,30 +488,15 @@ retry:
 	vma = find_vma(mm, address);
 	if (unlikely(!vma))
 		return bad_area(regs, address);
-	if (likely(vma->vm_start <= address))
-		goto good_area;
-	if (unlikely(!(vma->vm_flags & VM_GROWSDOWN)))
-		return bad_area(regs, address);
 
-	/* The stack is being expanded, check if it's valid */
-	if (unlikely(bad_stack_expansion(regs, address, vma, flags,
-					 &must_retry))) {
-		if (!must_retry)
+	if (unlikely(vma->vm_start > address)) {
+		if (unlikely(!(vma->vm_flags & VM_GROWSDOWN)))
 			return bad_area(regs, address);
 
-		mmap_read_unlock(mm);
-		if (fault_in_pages_readable((const char __user *)regs->nip,
-					    sizeof(unsigned int)))
-			return bad_area_nosemaphore(regs, address);
-		goto retry;
+		if (unlikely(expand_stack(vma, address)))
+			return bad_area(regs, address);
 	}
 
-	/* Try to expand it */
-	if (unlikely(expand_stack(vma, address)))
-		return bad_area(regs, address);
-
-good_area:
-
 #ifdef CONFIG_PPC_MEM_KEYS
 	if (unlikely(access_pkey_error(is_write, is_exec,
 				       (error_code & DSISR_KEYFAULT), vma)))