From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Fri, 17 May 2019 17:33:30 +0000 (-0700)
Subject: Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
X-Git-Tag: v5.2-rc1~17
X-Git-Url: http://git.osdn.net/view?a=commitdiff_plain;h=0ef0fd351550130129bbdb77362488befd7b69d2;p=uclinux-h8%2Flinux.git

Merge tag 'for-linus' of git://git./virt/kvm/kvm

Pull KVM updates from Paolo Bonzini:
 "ARM:
   - support for SVE and Pointer Authentication in guests
   - PMU improvements

  POWER:
   - support for direct access to the POWER9 XIVE interrupt controller
   - memory and performance optimizations

  x86:
   - support for accessing memory not backed by struct page
   - fixes and refactoring

  Generic:
   - dirty page tracking improvements"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (155 commits)
  kvm: fix compilation on aarch64
  Revert "KVM: nVMX: Expose RDPMC-exiting only when guest supports PMU"
  kvm: x86: Fix L1TF mitigation for shadow MMU
  KVM: nVMX: Disable intercept for FS/GS base MSRs in vmcs02 when possible
  KVM: PPC: Book3S: Remove useless checks in 'release' method of KVM device
  KVM: PPC: Book3S HV: XIVE: Fix spelling mistake "acessing" -> "accessing"
  KVM: PPC: Book3S HV: Make sure to load LPID for radix VCPUs
  kvm: nVMX: Set nested_run_pending in vmx_set_nested_state after checks complete
  tests: kvm: Add tests for KVM_SET_NESTED_STATE
  KVM: nVMX: KVM_SET_NESTED_STATE - Tear down old EVMCS state before setting new state
  tests: kvm: Add tests for KVM_CAP_MAX_VCPUS and KVM_CAP_MAX_CPU_ID
  tests: kvm: Add tests to .gitignore
  KVM: Introduce KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2
  KVM: Fix kvm_clear_dirty_log_protect off-by-(minus-)one
  KVM: Fix the bitmap range to copy during clear dirty
  KVM: arm64: Fix ptrauth ID register masking logic
  KVM: x86: use direct accessors for RIP and RSP
  KVM: VMX: Use accessors for GPRs outside of dedicated caching logic
  KVM: x86: Omit caching logic for always-available GPRs
  kvm, x86: Properly check whether a pfn is an MMIO or not
  ...
---

0ef0fd351550130129bbdb77362488befd7b69d2
diff --cc Documentation/virtual/kvm/api.txt
index 64b38dfcc243,73a501eb9291..ba6c42c576dd
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@@ -3809,8 -3936,8 +3936,8 @@@ to I/O ports
  
  4.117 KVM_CLEAR_DIRTY_LOG (vm ioctl)
  
- Capability: KVM_CAP_MANUAL_DIRTY_LOG_PROTECT
+ Capability: KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2
 -Architectures: x86
 +Architectures: x86, arm, arm64, mips
  Type: vm ioctl
  Parameters: struct kvm_dirty_log (in)
  Returns: 0 on success, -1 on error
@@@ -4798,9 -4968,9 +4968,9 @@@ and injected exceptions
  * For the new DR6 bits, note that bit 16 is set iff the #DB exception
    will clear DR6.RTM.
  
- 7.18 KVM_CAP_MANUAL_DIRTY_LOG_PROTECT
+ 7.18 KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2
  
 -Architectures: all
 +Architectures: x86, arm, arm64, mips
  Parameters: args[0] whether feature should be enabled or not
  
  With this capability enabled, KVM_GET_DIRTY_LOG will not automatically
diff --cc arch/x86/kvm/paging_tmpl.h
index 08715034e315,c40af67d0f44..367a47df4ba0
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@@ -140,16 -140,36 +140,36 @@@ static int FNAME(cmpxchg_gpte)(struct k
  	pt_element_t *table;
  	struct page *page;
  
 -	npages = get_user_pages_fast((unsigned long)ptep_user, 1, 1, &page);
 +	npages = get_user_pages_fast((unsigned long)ptep_user, 1, FOLL_WRITE, &page);
- 	/* Check if the user is doing something meaningless. */
- 	if (unlikely(npages != 1))
- 		return -EFAULT;
- 
- 	table = kmap_atomic(page);
- 	ret = CMPXCHG(&table[index], orig_pte, new_pte);
- 	kunmap_atomic(table);
- 
- 	kvm_release_page_dirty(page);
+ 	if (likely(npages == 1)) {
+ 		table = kmap_atomic(page);
+ 		ret = CMPXCHG(&table[index], orig_pte, new_pte);
+ 		kunmap_atomic(table);
+ 
+ 		kvm_release_page_dirty(page);
+ 	} else {
+ 		struct vm_area_struct *vma;
+ 		unsigned long vaddr = (unsigned long)ptep_user & PAGE_MASK;
+ 		unsigned long pfn;
+ 		unsigned long paddr;
+ 
+ 		down_read(&current->mm->mmap_sem);
+ 		vma = find_vma_intersection(current->mm, vaddr, vaddr + PAGE_SIZE);
+ 		if (!vma || !(vma->vm_flags & VM_PFNMAP)) {
+ 			up_read(&current->mm->mmap_sem);
+ 			return -EFAULT;
+ 		}
+ 		pfn = ((vaddr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
+ 		paddr = pfn << PAGE_SHIFT;
+ 		table = memremap(paddr, PAGE_SIZE, MEMREMAP_WB);
+ 		if (!table) {
+ 			up_read(&current->mm->mmap_sem);
+ 			return -EFAULT;
+ 		}
+ 		ret = CMPXCHG(&table[index], orig_pte, new_pte);
+ 		memunmap(table);
+ 		up_read(&current->mm->mmap_sem);
+ 	}
  
  	return (ret != orig_pte);
  }
diff --cc arch/x86/kvm/x86.c
index b9591abde62a,dc621f73e96b..536b78c4af6e
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@@ -6558,22 -6586,11 +6596,22 @@@ static int complete_fast_pio_out(struc
  static int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size,
  			    unsigned short port)
  {
- 	unsigned long val = kvm_register_read(vcpu, VCPU_REGS_RAX);
+ 	unsigned long val = kvm_rax_read(vcpu);
  	int ret = emulator_pio_out_emulated(&vcpu->arch.emulate_ctxt,
  					    size, port, &val, 1);
 +	if (ret)
 +		return ret;
  
 -	if (!ret) {
 +	/*
 +	 * Workaround userspace that relies on old KVM behavior of %rip being
 +	 * incremented prior to exiting to userspace to handle "OUT 0x7e".
 +	 */
 +	if (port == 0x7e &&
 +	    kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_OUT_7E_INC_RIP)) {
 +		vcpu->arch.complete_userspace_io =
 +			complete_fast_pio_out_port_0x7e;
 +		kvm_skip_emulated_instruction(vcpu);
 +	} else {
  		vcpu->arch.pio.linear_rip = kvm_get_linear_rip(vcpu);
  		vcpu->arch.complete_userspace_io = complete_fast_pio_out;
  	}