Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm updates from Paolo Bonzini:
 "Quite a large pull request due to a selftest API overhaul and some
  patches that had come in too late for 5.19.

  ARM:

   - Unwinder implementations for both nVHE modes (classic and
     protected), complete with an overflow stack

   - Rework of the sysreg access from userspace, with a complete rewrite
     of the vgic-v3 view to allign with the rest of the infrastructure

   - Disagregation of the vcpu flags in separate sets to better track
     their use model.

   - A fix for the GICv2-on-v3 selftest

   - A small set of cosmetic fixes

  RISC-V:

   - Track ISA extensions used by Guest using bitmap

   - Added system instruction emulation framework

   - Added CSR emulation framework

   - Added gfp_custom flag in struct kvm_mmu_memory_cache

   - Added G-stage ioremap() and iounmap() functions

   - Added support for Svpbmt inside Guest

  s390:

   - add an interface to provide a hypervisor dump for secure guests

   - improve selftests to use TAP interface

   - enable interpretive execution of zPCI instructions (for PCI
     passthrough)

   - First part of deferred teardown

   - CPU Topology

   - PV attestation

   - Minor fixes

  x86:

   - Permit guests to ignore single-bit ECC errors

   - Intel IPI virtualization

   - Allow getting/setting pending triple fault with
     KVM_GET/SET_VCPU_EVENTS

   - PEBS virtualization

   - Simplify PMU emulation by just using PERF_TYPE_RAW events

   - More accurate event reinjection on SVM (avoid retrying
     instructions)

   - Allow getting/setting the state of the speaker port data bit

   - Refuse starting the kvm-intel module if VM-Entry/VM-Exit controls
     are inconsistent

   - "Notify" VM exit (detect microarchitectural hangs) for Intel

   - Use try_cmpxchg64 instead of cmpxchg64

   - Ignore benign host accesses to PMU MSRs when PMU is disabled

   - Allow disabling KVM's "MONITOR/MWAIT are NOPs!" behavior

   - Allow NX huge page mitigation to be disabled on a per-vm basis

   - Port eager page splitting to shadow MMU as well

   - Enable CMCI capability by default and handle injected UCNA errors

   - Expose pid of vcpu threads in debugfs

   - x2AVIC support for AMD

   - cleanup PIO emulation

   - Fixes for LLDT/LTR emulation

   - Don't require refcounted "struct page" to create huge SPTEs

   - Miscellaneous cleanups:
      - MCE MSR emulation
      - Use separate namespaces for guest PTEs and shadow PTEs bitmasks
      - PIO emulation
      - Reorganize rmap API, mostly around rmap destruction
      - Do not workaround very old KVM bugs for L0 that runs with nesting enabled
      - new selftests API for CPUID

  Generic:

   - Fix races in gfn->pfn cache refresh; do not pin pages tracked by
     the cache

   - new selftests API using struct kvm_vcpu instead of a (vm, id)
     tuple"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (606 commits)
  selftests: kvm: set rax before vmcall
  selftests: KVM: Add exponent check for boolean stats
  selftests: KVM: Provide descriptive assertions in kvm_binary_stats_test
  selftests: KVM: Check stat name before other fields
  KVM: x86/mmu: remove unused variable
  RISC-V: KVM: Add support for Svpbmt inside Guest/VM
  RISC-V: KVM: Use PAGE_KERNEL_IO in kvm_riscv_gstage_ioremap()
  RISC-V: KVM: Add G-stage ioremap() and iounmap() functions
  KVM: Add gfp_custom flag in struct kvm_mmu_memory_cache
  RISC-V: KVM: Add extensible CSR emulation framework
  RISC-V: KVM: Add extensible system instruction emulation framework
  RISC-V: KVM: Factor-out instruction emulation into separate sources
  RISC-V: KVM: move preempt_disable() call in kvm_arch_vcpu_ioctl_run
  RISC-V: KVM: Make kvm_riscv_guest_timer_init a void function
  RISC-V: KVM: Fix variable spelling mistake
  RISC-V: KVM: Improve ISA extension by using a bitmap
  KVM, x86/mmu: Fix the comment around kvm_tdp_mmu_zap_leafs()
  KVM: SVM: Dump Virtual Machine Save Area (VMSA) to klog
  KVM: x86/mmu: Treat NX as a valid SPTE bit for NPT
  KVM: x86: Do not block APIC write for non ICR registers
  ...

1 files changed, 29 insertions, 96 deletions

diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index fcaa151b81f1..ce190ee18a20 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -7,75 +7,16 @@
 #include <linux/kernel.h>
 #include <linux/export.h>
 #include <linux/ftrace.h>
-#include <linux/kprobes.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task_stack.h>
 #include <linux/stacktrace.h>
 
 #include <asm/irq.h>
-#include <asm/pointer_auth.h>
 #include <asm/stack_pointer.h>
 #include <asm/stacktrace.h>
 
 /*
- * A snapshot of a frame record or fp/lr register values, along with some
- * accounting information necessary for robust unwinding.
- *
- * @fp:          The fp value in the frame record (or the real fp)
- * @pc:          The lr value in the frame record (or the real lr)
- *
- * @stacks_done: Stacks which have been entirely unwound, for which it is no
- *               longer valid to unwind to.
- *
- * @prev_fp:     The fp that pointed to this frame record, or a synthetic value
- *               of 0. This is used to ensure that within a stack, each
- *               subsequent frame record is at an increasing address.
- * @prev_type:   The type of stack this frame record was on, or a synthetic
- *               value of STACK_TYPE_UNKNOWN. This is used to detect a
- *               transition from one stack to another.
- *
- * @kr_cur:      When KRETPROBES is selected, holds the kretprobe instance
- *               associated with the most recently encountered replacement lr
- *               value.
- *
- * @task:        The task being unwound.
- */
-struct unwind_state {
-	unsigned long fp;
-	unsigned long pc;
-	DECLARE_BITMAP(stacks_done, __NR_STACK_TYPES);
-	unsigned long prev_fp;
-	enum stack_type prev_type;
-#ifdef CONFIG_KRETPROBES
-	struct llist_node *kr_cur;
-#endif
-	struct task_struct *task;
-};
-
-static void unwind_init_common(struct unwind_state *state,
-			       struct task_struct *task)
-{
-	state->task = task;
-#ifdef CONFIG_KRETPROBES
-	state->kr_cur = NULL;
-#endif
-
-	/*
-	 * Prime the first unwind.
-	 *
-	 * In unwind_next() we'll check that the FP points to a valid stack,
-	 * which can't be STACK_TYPE_UNKNOWN, and the first unwind will be
-	 * treated as a transition to whichever stack that happens to be. The
-	 * prev_fp value won't be used, but we set it to 0 such that it is
-	 * definitely not an accessible stack address.
-	 */
-	bitmap_zero(state->stacks_done, __NR_STACK_TYPES);
-	state->prev_fp = 0;
-	state->prev_type = STACK_TYPE_UNKNOWN;
-}
-
-/*
  * Start an unwind from a pt_regs.
  *
  * The unwind will begin at the PC within the regs.
@@ -127,6 +68,31 @@ static inline void unwind_init_from_task(struct unwind_state *state,
 }
 
 /*
+ * We can only safely access per-cpu stacks from current in a non-preemptible
+ * context.
+ */
+static bool on_accessible_stack(const struct task_struct *tsk,
+				unsigned long sp, unsigned long size,
+				struct stack_info *info)
+{
+	if (info)
+		info->type = STACK_TYPE_UNKNOWN;
+
+	if (on_task_stack(tsk, sp, size, info))
+		return true;
+	if (tsk != current || preemptible())
+		return false;
+	if (on_irq_stack(sp, size, info))
+		return true;
+	if (on_overflow_stack(sp, size, info))
+		return true;
+	if (on_sdei_stack(sp, size, info))
+		return true;
+
+	return false;
+}
+
+/*
  * Unwind from one frame record (A) to the next frame record (B).
  *
  * We terminate early if the location of B indicates a malformed chain of frame
@@ -138,48 +104,15 @@ static int notrace unwind_next(struct unwind_state *state)
 	struct task_struct *tsk = state->task;
 	unsigned long fp = state->fp;
 	struct stack_info info;
+	int err;
 
 	/* Final frame; nothing to unwind */
 	if (fp == (unsigned long)task_pt_regs(tsk)->stackframe)
 		return -ENOENT;
 
-	if (fp & 0x7)
-		return -EINVAL;
-
-	if (!on_accessible_stack(tsk, fp, 16, &info))
-		return -EINVAL;
-
-	if (test_bit(info.type, state->stacks_done))
-		return -EINVAL;
-
-	/*
-	 * As stacks grow downward, any valid record on the same stack must be
-	 * at a strictly higher address than the prior record.
-	 *
-	 * Stacks can nest in several valid orders, e.g.
-	 *
-	 * TASK -> IRQ -> OVERFLOW -> SDEI_NORMAL
-	 * TASK -> SDEI_NORMAL -> SDEI_CRITICAL -> OVERFLOW
-	 *
-	 * ... but the nesting itself is strict. Once we transition from one
-	 * stack to another, it's never valid to unwind back to that first
-	 * stack.
-	 */
-	if (info.type == state->prev_type) {
-		if (fp <= state->prev_fp)
-			return -EINVAL;
-	} else {
-		__set_bit(state->prev_type, state->stacks_done);
-	}
-
-	/*
-	 * Record this frame record's values and location. The prev_fp and
-	 * prev_type are only meaningful to the next unwind_next() invocation.
-	 */
-	state->fp = READ_ONCE(*(unsigned long *)(fp));
-	state->pc = READ_ONCE(*(unsigned long *)(fp + 8));
-	state->prev_fp = fp;
-	state->prev_type = info.type;
+	err = unwind_next_common(state, &info, on_accessible_stack, NULL);
+	if (err)
+		return err;
 
 	state->pc = ptrauth_strip_insn_pac(state->pc);